diff options
| author | Paolo Bonzini <pbonzini@redhat.com> | 2021-02-12 11:23:44 -0500 |
|---|---|---|
| committer | Paolo Bonzini <pbonzini@redhat.com> | 2021-02-12 11:23:44 -0500 |
| commit | 8c6e67bec3192f16fa624203c8131e10cc4814ba (patch) | |
| tree | 533b140ab6bb926f5ec35f8e42d5a99590e0d945 /arch | |
| parent | 7137b7ae6f20076a1e05546db61f9fb3d3f9e97d (diff) | |
| parent | c93199e93e1232b7220482dffa05b7a32a195fe8 (diff) | |
Merge tag 'kvmarm-5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for Linux 5.12
- Make the nVHE EL2 object relocatable, resulting in much more
maintainable code
- Handle concurrent translation faults hitting the same page
in a more elegant way
- Support for the standard TRNG hypervisor call
- A bunch of small PMU/Debug fixes
- Allow the disabling of symbol export from assembly code
- Simplification of the early init hypercall handling
Diffstat (limited to 'arch')
68 files changed, 1051 insertions, 380 deletions
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 60e901cd0de6..5a957a9a0984 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -371,7 +371,7 @@ static int __init xen_guest_init(void) } gnttab_init(); if (!xen_initial_domain()) - xenbus_probe(NULL); + xenbus_probe(); /* * Making sure board specific code will not set up ops for diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 05e17351e4f3..f39568b28ec1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -174,8 +174,6 @@ config ARM64 select HAVE_NMI select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS - select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS - select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 015ddffaf6ca..b56a4b2bc248 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -17,7 +17,7 @@ #include <asm/lse.h> #define ATOMIC_OP(op) \ -static inline void arch_##op(int i, atomic_t *v) \ +static __always_inline void arch_##op(int i, atomic_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, op) \ -static inline int arch_##op##name(int i, atomic_t *v) \ +static __always_inline int arch_##op##name(int i, atomic_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return) #undef ATOMIC_FETCH_OPS #define ATOMIC64_OP(op) \ -static inline void arch_##op(long i, atomic64_t *v) \ +static __always_inline void arch_##op(long i, atomic64_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, op) \ -static inline long arch_##op##name(long i, atomic64_t *v) \ +static __always_inline long arch_##op##name(long i, atomic64_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return) #undef ATOMIC64_FETCH_OP #undef ATOMIC64_FETCH_OPS -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) +static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v) { return __lse_ll_sc_body(atomic64_dec_if_positive, v); } diff --git a/arch/arm64/include/asm/hyp_image.h b/arch/arm64/include/asm/hyp_image.h index daa1a1da539e..737ded6b6d0d 100644 --- a/arch/arm64/include/asm/hyp_image.h +++ b/arch/arm64/include/asm/hyp_image.h @@ -7,6 +7,9 @@ #ifndef __ARM64_HYP_IMAGE_H__ #define __ARM64_HYP_IMAGE_H__ +#define __HYP_CONCAT(a, b) a ## b +#define HYP_CONCAT(a, b) __HYP_CONCAT(a, b) + /* * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_, * to separate it from the kernel proper. @@ -21,9 +24,31 @@ */ #define HYP_SECTION_NAME(NAME) .hyp##NAME +/* Symbol defined at the beginning of each hyp section. */ +#define HYP_SECTION_SYMBOL_NAME(NAME) \ + HYP_CONCAT(__hyp_section_, HYP_SECTION_NAME(NAME)) + +/* + * Helper to generate linker script statements starting a hyp section. + * + * A symbol with a well-known name is defined at the first byte. This + * is used as a base for hyp relocations (see gen-hyprel.c). It must + * be defined inside the section so the linker of `vmlinux` cannot + * separate it from the section data. + */ +#define BEGIN_HYP_SECTION(NAME) \ + HYP_SECTION_NAME(NAME) : { \ + HYP_SECTION_SYMBOL_NAME(NAME) = .; + +/* Helper to generate linker script statements ending a hyp section. */ +#define END_HYP_SECTION \ + } + /* Defines an ELF hyp section from input section @NAME and its subsections. */ -#define HYP_SECTION(NAME) \ - HYP_SECTION_NAME(NAME) : { *(NAME NAME##.*) } +#define HYP_SECTION(NAME) \ + BEGIN_HYP_SECTION(NAME) \ + *(NAME NAME##.*) \ + END_HYP_SECTION /* * Defines a linker script alias of a kernel-proper symbol referenced by diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 8a33d83ea843..22d933e9b59e 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -199,32 +199,6 @@ extern void __vgic_v3_init_lrs(void); extern u32 __kvm_get_mdcr_el2(void); -#if defined(GCC_VERSION) && GCC_VERSION < 50000 -#define SYM_CONSTRAINT "i" -#else -#define SYM_CONSTRAINT "S" -#endif - -/* - * Obtain the PC-relative address of a kernel symbol - * s: symbol - * - * The goal of this macro is to return a symbol's address based on a - * PC-relative computation, as opposed to a loading the VA from a - * constant pool or something similar. This works well for HYP, as an - * absolute VA is guaranteed to be wrong. Only use this if trying to - * obtain the address of a symbol (i.e. not something you obtained by - * following a pointer). - */ -#define hyp_symbol_addr(s) \ - ({ \ - typeof(s) *addr; \ - asm("adrp %0, %1\n" \ - "add %0, %0, :lo12:%1\n" \ - : "=r" (addr) : SYM_CONSTRAINT (&s)); \ - addr; \ - }) - #define __KVM_EXTABLE(from, to) \ " .pushsection __kvm_ex_table, \"a\"\n" \ " .align 3\n" \ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 1b8a3d825276..3d10e6527f7d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -770,4 +770,6 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_vcpu_has_pmu(vcpu) \ (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) +int kvm_trng_call(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index e52d82aeadca..90873851f677 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -73,49 +73,39 @@ alternative_cb_end .endm /* - * Convert a kernel image address to a PA - * reg: kernel address to be converted in place + * Convert a hypervisor VA to a PA + * reg: hypervisor address to be converted in place * tmp: temporary register - * - * The actual code generation takes place in kvm_get_kimage_voffset, and - * the instructions below are only there to reserve the space and - * perform the register allocation (kvm_get_kimage_voffset uses the - * specific registers encoded in the instructions). */ -.macro kimg_pa reg, tmp -alternative_cb kvm_get_kimage_voffset - movz \tmp, #0 - movk \tmp, #0, lsl #16 - movk \tmp, #0, lsl #32 - movk \tmp, #0, lsl #48 -alternative_cb_end - - /* reg = __pa(reg) */ - sub \reg, \reg, \tmp +.macro hyp_pa reg, tmp + ldr_l \tmp, hyp_physvirt_offset + add \reg, \reg, \tmp .endm /* - * Convert a kernel image address to a hyp VA - * reg: kernel address to be converted in place + * Convert a hypervisor VA to a kernel image address + * reg: hypervisor address to be converted in place * tmp: temporary register * * The actual code generation takes place in kvm_get_kimage_voffset, and * the instructions below are only there to reserve the space and - * perform the register allocation (kvm_update_kimg_phys_offset uses the + * perform the register allocation (kvm_get_kimage_voffset uses the * specific registers encoded in the instructions). */ -.macro kimg_hyp_va reg, tmp -alternative_cb kvm_update_kimg_phys_offset +.macro hyp_kimg_va reg, tmp + /* Convert hyp VA -> PA. */ + hyp_pa \reg, \tmp + + /* Load kimage_voffset. */ +alternative_cb kvm_get_kimage_voffset movz \tmp, #0 movk \tmp, #0, lsl #16 movk \tmp, #0, lsl #32 movk \tmp, #0, lsl #48 alternative_cb_end - sub \reg, \reg, \tmp - mov_q \tmp, PAGE_OFFSET - orr \reg, \reg, \tmp - kern_hyp_va \reg + /* Convert PA -> kimg VA. */ + add \reg, \reg, \tmp .endm #else @@ -129,6 +119,7 @@ alternative_cb_end void kvm_update_va_mask(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void kvm_compute_layout(void); +void kvm_apply_hyp_relocations(void); static __always_inline unsigned long __kern_hyp_va(unsigned long v) { @@ -144,24 +135,6 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) #define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v)))) -static __always_inline unsigned long __kimg_hyp_va(unsigned long v) -{ - unsigned long offset; - - asm volatile(ALTERNATIVE_CB("movz %0, #0\n" - "movk %0, #0, lsl #16\n" - "movk %0, #0, lsl #32\n" - "movk %0, #0, lsl #48\n", - kvm_update_kimg_phys_offset) - : "=r" (offset)); - - return __kern_hyp_va((v - offset) | PAGE_OFFSET); -} - -#define kimg_fn_hyp_va(v) ((typeof(*v))(__kimg_hyp_va((unsigned long)(v)))) - -#define kimg_fn_ptr(x) (typeof(x) **)(x) - /* * We currently support using a VM-specified IPA size. For backward * compatibility, the default IPA size is fixed to 40bits. diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 52ab38db04c7..8886d43cfb11 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -157,6 +157,11 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); * If device attributes are not explicitly requested in @prot, then the * mapping will be normal, cacheable. * + * Note that the update of a valid leaf PTE in this function will be aborted, + * if it's trying to recreate the exact same mapping or only change the access + * permissions. Instead, the vCPU will exit one more time from guest if still + * needed and then go through the path of relaxing permissions. + * * Note that this function will both coalesce existing table entries and split * existing block mappings, relying on page-faults to fault back areas outside * of the new mapping lazily. diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 69ad25fbeae4..ca2cd75d3286 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -94,8 +94,7 @@ #endif /* CONFIG_ARM64_FORCE_52BIT */ extern phys_addr_t arm64_dma_phys_limit; -extern phys_addr_t arm64_dma32_phys_limit; -#define ARCH_LOW_ADDRESS_LIMIT ((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1) +#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) struct debug_info { #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 8ff579361731..2f36b16a5b5d 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -11,7 +11,8 @@ extern char __alt_instructions[], __alt_instructions_end[]; extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[]; extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; extern char __hyp_text_start[], __hyp_text_end[]; -extern char __hyp_data_ro_after_init_start[], __hyp_data_ro_after_init_end[]; +extern char __hyp_rodata_start[], __hyp_rodata_end[]; +extern char __hyp_reloc_begin[], __hyp_reloc_end[]; extern char __idmap_text_start[], __idmap_text_end[]; extern char __initdata_begin[], __initdata_end[]; extern char __inittext_begin[], __inittext_end[]; diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 8b5e7e5c3cc8..2fb3f386588c 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -846,7 +846,10 @@ #define ID_DFR0_PERFMON_SHIFT 24 +#define ID_DFR0_PERFMON_8_0 0x3 #define ID_DFR0_PERFMON_8_1 0x4 +#define ID_DFR0_PERFMON_8_4 0x5 +#define ID_DFR0_PERFMON_8_5 0x6 #define ID_ISAR4_SWP_FRAC_SHIFT 28 #define ID_ISAR4_PSR_M_SHIFT 24 diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f42fd9e33981..301784463587 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,7 +75,7 @@ int main(void) DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); - DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); + DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); BLANK(); #ifdef CONFIG_COMPAT DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0)); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index a338f40e64d3..b3e4f9a088b1 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -35,7 +35,7 @@ */ .macro ftrace_regs_entry, allregs=0 /* Make room for pt_regs, plus a callee frame */ - sub sp, sp, #(S_FRAME_SIZE + 16) + sub sp, sp, #(PT_REGS_SIZE + 16) /* Save function arguments (and x9 for simplicity) */ stp x0, x1, [sp, #S_X0] @@ -61,15 +61,15 @@ .endif /* Save the callsite's SP and LR */ - add x10, sp, #(S_FRAME_SIZE + 16) + add x10, sp, #(PT_REGS_SIZE + 16) stp x9, x10, [sp, #S_LR] /* Save the PC after the ftrace callsite */ str x30, [sp, #S_PC] /* Create a frame record for the callsite above pt_regs */ - stp x29, x9, [sp, #S_FRAME_SIZE] - add x29, sp, #S_FRAME_SIZE + stp x29, x9, [sp, #PT_REGS_SIZE] + add x29, sp, #PT_REGS_SIZE /* Create our frame record within pt_regs. */ stp x29, x30, [sp, #S_STACKFRAME] @@ -120,7 +120,7 @@ ftrace_common_return: ldr x9, [sp, #S_PC] /* Restore the callsite's SP */ - add sp, sp, #S_FRAME_SIZE + 16 + add sp, sp, #PT_REGS_SIZE + 16 ret x9 SYM_CODE_END(ftrace_common) @@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller) ldr x0, [sp, #S_PC] sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) add x1, sp, #S_LR // parent_ip (callsite's LR) - ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP) bl prepare_ftrace_return b ftrace_common_return SYM_CODE_END(ftrace_graph_caller) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a8c3e7aaca74..c9bae73f2621 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -75,7 +75,7 @@ alternative_else_nop_endif .endif #endif - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK /* * Test whether the SP has overflowed, without corrupting a GPR. @@ -96,7 +96,7 @@ alternative_else_nop_endif * userspace, and can clobber EL0 registers to free up GPRs. */ - /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */ + /* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */ msr tpidr_el0, x0 /* Recover the original x0 value and stash it in tpidrro_el0 */ @@ -253,7 +253,7 @@ alternative_else_nop_endif scs_load tsk, x20 .else - add x21, sp, #S_FRAME_SIZE + add x21, sp, #PT_REGS_SIZE get_current_task tsk .endif /* \el == 0 */ mrs x22, elr_el1 @@ -377,7 +377,7 @@ alternative_else_nop_endif ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] ldr lr, [sp, #S_LR] - add sp, sp, #S_FRAME_SIZE // restore sp + add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 @@ -580,12 +580,12 @@ __bad_stack: /* * Store the original GPRs to the new stack. The orginal SP (minus - * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry. + * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry. */ - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE kernel_entry 1 mrs x0, tpidr_el0 - add x0, x0, #S_FRAME_SIZE + add x0, x0, #PT_REGS_SIZE str x0, [sp, #S_SP] /* Stash the regs for handle_bad_stack */ diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index f676243abac6..23f1a557bd9f 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -64,7 +64,6 @@ __efistub__ctype = _ctype; /* Alternative callbacks for init-time patching of nVHE hyp code. */ KVM_NVHE_ALIAS(kvm_patch_vector_branch); KVM_NVHE_ALIAS(kvm_update_va_mask); -KVM_NVHE_ALIAS(kvm_update_kimg_phys_offset); KVM_NVHE_ALIAS(kvm_get_kimage_voffset); /* Global kernel state accessed by nVHE hyp code. */ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 38bb07eff872..3605f77ad4df 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -23,8 +23,6 @@ #include <linux/platform_device.h> #include <linux/sched_clock.h> #include <linux/smp.h> -#include <linux/nmi.h> -#include <linux/cpufreq.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = { static int __init armv8_pmu_driver_init(void) { - int ret; - if (acpi_disabled) - ret = platform_driver_register(&armv8_pmu_driver); + return platform_driver_register(&armv8_pmu_driver); else - ret = arm_pmu_acpi_probe(armv8_pmuv3_init); - - /* - * Try to re-initialize lockup detector after PMU init in - * case PMU events are triggered via NMIs. - */ - if (ret == 0 && arm_pmu_irq_is_nmi()) - lockup_detector_init(); - - return ret; + return arm_pmu_acpi_probe(armv8_pmuv3_init); } device_initcall(armv8_pmu_driver_init) @@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time_zero = 1; userpg->cap_user_time_short = 1; } - -#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF -/* - * Safe maximum CPU frequency in case a particular platform doesn't implement - * cpufreq driver. Although, architecture doesn't put any restrictions on - * maximum frequency but 5 GHz seems to be safe maximum given the available - * Arm CPUs in the market which are clocked much less than 5 GHz. On the other - * hand, we can't make it much higher as it would lead to a large hard-lockup - * detection timeout on parts which are running slower (eg. 1GHz on - * Developerbox) and doesn't possess a cpufreq driver. - */ -#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz -u64 hw_nmi_get_sample_period(int watchdog_thresh) -{ - unsigned int cpu = smp_processor_id(); - unsigned long max_cpu_freq; - - max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL; - if (!max_cpu_freq) - max_cpu_freq = SAFE_MAX_CPU_FREQ; - - return (u64)max_cpu_freq * watchdog_thresh; -} -#endif diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 890ca72c5a51..288a84e253cc 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -25,7 +25,7 @@ stp x24, x25, [sp, #S_X24] stp x26, x27, [sp, #S_X26] stp x28, x29, [sp, #S_X28] - add x0, sp, #S_FRAME_SIZE + add x0, sp, #PT_REGS_SIZE stp lr, x0, [sp, #S_LR] /* * Construct a useful saved PSTATE @@ -62,7 +62,7 @@ .endm SYM_CODE_START(kretprobe_trampoline) - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE save_all_base_regs @@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline) restore_all_base_regs - add sp, sp, #S_FRAME_SIZE + add sp, sp, #PT_REGS_SIZE ret SYM_CODE_END(kretprobe_trampoline) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index f71d6ce4673f..6237486ff6bb 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { - /* - * The assembly code enters us with IRQs off, but it hasn't - * informed the tracing code of that for efficiency reasons. - * Update the trace code with the current status. - */ - trace_hardirqs_off(); - do { if (thread_flags & _TIF_NEED_RESCHED) { /* Unmask Debug and SError for the next task */ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index ad00f99ee9b0..357590beaabb 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -434,8 +434,10 @@ static void __init hyp_mode_check(void) "CPU: CPUs started in inconsistent modes"); else pr_info("CPU: All CPU(s) started at EL1\n"); - if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode()) + if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode()) { kvm_compute_layout(); + kvm_apply_hyp_relocations(); + } } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index f61e9d8cc55a..c2877c332f2d 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -9,6 +9,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> +#include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { - /* - * We're off to userspace, where interrupts are - * always enabled after we restore the flags from - * the SPSR. - */ - trace_hardirqs_on(); + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) return; - } local_daif_restore(DAIF_PROCCTX); } diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 4c0b0c89ad59..636ca45aa1d4 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -31,10 +31,11 @@ jiffies = jiffies_64; __stop___kvm_ex_table = .; #define HYPERVISOR_DATA_SECTIONS \ - HYP_SECTION_NAME(.data..ro_after_init) : { \ - __hyp_data_ro_after_init_start = .; \ + HYP_SECTION_NAME(.rodata) : { \ + __hyp_rodata_start = .; \ *(HYP_SECTION_NAME(.data..ro_after_init)) \ - __hyp_data_ro_after_init_end = .; \ + *(HYP_SECTION_NAME(.rodata)) \ + __hyp_rodata_end = .; \ } #define HYPERVISOR_PERCPU_SECTION \ @@ -42,10 +43,19 @@ jiffies = jiffies_64; HYP_SECTION_NAME(.data..percpu) : { \ *(HYP_SECTION_NAME(.data..percpu)) \ } + +#define HYPERVISOR_RELOC_SECTION \ + .hyp.reloc : ALIGN(4) { \ + __hyp_reloc_begin = .; \ + *(.hyp.reloc) \ + __hyp_reloc_end = .; \ + } + #else /* CONFIG_KVM */ #define HYPERVISOR_EXTABLE #define HYPERVISOR_DATA_SECTIONS #define HYPERVISOR_PERCPU_SECTION +#define HYPERVISOR_RELOC_SECTION #endif #define HYPERVISOR_TEXT \ @@ -216,6 +226,8 @@ SECTIONS PERCPU_SECTION(L1_CACHE_BYTES) HYPERVISOR_PERCPU_SECTION + HYPERVISOR_RELOC_SECTION + .rela.dyn : ALIGN(8) { *(.rela .rela*) } diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 13b017284bf9..589921392cb1 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -16,7 +16,7 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ vgic-sys-reg-v3.o fpsimd.o pmu.o \ - arch_timer.o \ + arch_timer.o trng.o\ vgic/vgic.o vgic/vgic-init.o \ vgic/vgic-irqfd.o vgic/vgic-v2.o \ vgic/vgic-v3.o vgic/vgic-v4.o \ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index fe60d25c000e..bb85da1d5880 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1750,11 +1750,10 @@ static int init_hyp_mode(void) goto out_err; } - err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_ro_after_init_start), - kvm_ksym_ref(__hyp_data_ro_after_init_end), - PAGE_HYP_RO); + err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start), + kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO); if (err) { - kvm_err("Cannot map .hyp.data..ro_after_init section\n"); + kvm_err("Cannot map .hyp.rodata section\n"); goto out_err; } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 84473574c2e7..54f4860cd87c 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -505,8 +505,8 @@ static inline void __kvm_unexpected_el2_exception(void) struct exception_table_entry *entry, *end; unsigned long elr_el2 = read_sysreg(elr_el2); - entry = hyp_symbol_addr(__start___kvm_ex_table); - end = hyp_symbol_addr(__stop___kvm_ex_table); + entry = &__start___kvm_ex_table; + end = &__stop___kvm_ex_table; while (entry < end) { addr = (unsigned long)&entry->insn + entry->insn; diff --git a/arch/arm64/kvm/hyp/nvhe/.gitignore b/arch/arm64/kvm/hyp/nvhe/.gitignore index 695d73d0249e..5b6c43cc96f8 100644 --- a/arch/arm64/kvm/hyp/nvhe/.gitignore +++ b/arch/arm64/kvm/hyp/nvhe/.gitignore @@ -1,2 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only +gen-hyprel hyp.lds +hyp-reloc.S diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 1f1e351c5fe2..a6707df4f6c0 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -3,8 +3,11 @@ # Makefile for Kernel-based Virtual Machine module, HYP/nVHE part # -asflags-y := -D__KVM_NVHE_HYPERVISOR__ -ccflags-y := -D__KVM_NVHE_HYPERVISOR__ +asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS +ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS + +hostprogs := gen-hyprel +HOST_EXTRACFLAGS += -I$(objtree)/include obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \ hyp-main.o hyp-smp.o psci-relay.o @@ -19,7 +22,7 @@ obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ hyp-obj := $(patsubst %.o,%.nvhe.o,$(obj-y)) obj-y := kvm_nvhe.o -extra-y := $(hyp-obj) kvm_nvhe.tmp.o hyp.lds +extra-y := $(hyp-obj) kvm_nvhe.tmp.o kvm_nvhe.rel.o hyp.lds hyp-reloc.S hyp-reloc.o # 1) Compile all source files to `.nvhe.o` object files. The file extension # avoids file name clashes for files shared with VHE. @@ -42,11 +45,31 @@ LDFLAGS_kvm_nvhe.tmp.o := -r -T $(obj)/kvm_nvhe.tmp.o: $(obj)/hyp.lds $(addprefix $(obj)/,$(hyp-obj)) FORCE $(call if_changed,ld) -# 4) Produce the final 'kvm_nvhe.o', ready to be linked into 'vmlinux'. +# 4) Generate list of hyp code/data positions that need to be relocated at +# runtime. Because the hypervisor is part of the kernel binary, relocations +# produce a kernel VA. We enumerate relocations targeting hyp at build time +# and convert the kernel VAs at those positions to hyp VAs. +$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel + $(call if_changed,hyprel) + +# 5) Compile hyp-reloc.S and link it into the existing partially linked object. +# The object file now contains a section with pointers to hyp positions that +# will contain kernel VAs at runtime. These pointers have relocations on them +# so that they get updated as the hyp object is linked into `vmlinux`. +LDFLAGS_kvm_nvhe.rel.o := -r +$(obj)/kvm_nvhe.rel.o: $(obj)/kvm_nvhe.tmp.o $(obj)/hyp-reloc.o FORCE + $(call if_changed,ld) + +# 6) Produce the final 'kvm_nvhe.o', ready to be linked into 'vmlinux'. # Prefixes names of ELF symbols with '__kvm_nvhe_'. -$(obj)/kvm_nvhe.o: $(obj)/kvm_nvhe.tmp.o FORCE +$(obj)/kvm_nvhe.o: $(obj)/kvm_nvhe.rel.o FORCE $(call if_changed,hypcopy) +# The HYPREL command calls `gen-hyprel` to generate an assembly file with +# a list of relocations targeting hyp code/data. +quiet_cmd_hyprel = HYPREL $@ + cmd_hyprel = $(obj)/gen-hyprel $< > $@ + # The HYPCOPY command uses `objcopy` to prefix all ELF symbol names # to avoid clashes with VHE code/data. quiet_cmd_hypcopy = HYPCOPY $@ diff --git a/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c new file mode 100644 index 000000000000..ead02c6a7628 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c @@ -0,0 +1,438 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 - Google LLC + * Author: David Brazdil <dbrazdil@google.com> + * + * Generates relocation information used by the kernel to convert + * absolute addresses in hyp data from kernel VAs to hyp VAs. + * + * This is necessary because hyp code is linked into the same binary + * as the kernel but executes under different memory mappings. + * If the compiler used absolute addressing, those addresses need to + * be converted before they are used by hyp code. + * + * The input of this program is the relocatable ELF object containing + * all hyp code/data, not yet linked into vmlinux. Hyp section names + * should have been prefixed with `.hyp` at this point. + * + * The output (printed to stdout) is an assembly file containing + * an array of 32-bit integers and static relocations that instruct + * the linker of `vmlinux` to populate the array entries with offsets + * to positions in the kernel binary containing VAs used by hyp code. + * + * Note that dynamic relocations could be used for the same purpose. + * However, those are only generated if CONFIG_RELOCATABLE=y. + */ + +#include <elf.h> +#include <endian.h> +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include <generated/autoconf.h> + +#define HYP_SECTION_PREFIX ".hyp" +#define HYP_RELOC_SECTION ".hyp.reloc" +#define HYP_SECTION_SYMBOL_PREFIX "__hyp_section_" + +/* + * AArch64 relocation type constants. + * Included in case these are not defined in the host toolchain. + */ +#ifndef R_AARCH64_ABS64 +#define R_AARCH64_ABS64 257 +#endif +#ifndef R_AARCH64_LD_PREL_LO19 +#define R_AARCH64_LD_PREL_LO19 273 +#endif +#ifndef R_AARCH64_ADR_PREL_LO21 +#define R_AARCH64_ADR_PREL_LO21 274 +#endif +#ifndef R_AARCH64_ADR_PREL_PG_HI21 +#define R_AARCH64_ADR_PREL_PG_HI21 275 +#endif +#ifndef R_AARCH64_ADR_PREL_PG_HI21_NC +#define R_AARCH64_ADR_PREL_PG_HI21_NC 276 +#endif +#ifndef R_AARCH64_ADD_ABS_LO12_NC +#define R_AARCH64_ADD_ABS_LO12_NC 277 +#endif +#ifndef R_AARCH64_LDST8_ABS_LO12_NC +#define R_AARCH64_LDST8_ABS_LO12_NC 278 +#endif +#ifndef R_AARCH64_TSTBR14 +#define R_AARCH64_TSTBR14 279 +#endif +#ifndef R_AARCH64_CONDBR19 +#define R_AARCH64_CONDBR19 280 +#endif +#ifndef R_AARCH64_JUMP26 +#define R_AARCH64_JUMP26 282 +#endif +#ifndef R_AARCH64_CALL26 +#define R_AARCH64_CALL26 283 +#endif +#ifndef R_AARCH64_LDST16_ABS_LO12_NC +#define R_AARCH64_LDST16_ABS_LO12_NC 284 +#endif +#ifndef R_AARCH64_LDST32_ABS_LO12_NC +#define R_AARCH64_LDST32_ABS_LO12_NC 285 +#endif +#ifndef R_AARCH64_LDST64_ABS_LO12_NC +#define R_AARCH64_LDST64_ABS_LO12_NC 286 +#endif +#ifndef R_AARCH64_MOVW_PREL_G0 +#define R_AARCH64_MOVW_PREL_G0 287 +#endif +#ifndef R_AARCH64_MOVW_PREL_G0_NC +#define R_AARCH64_MOVW_PREL_G0_NC 288 +#endif +#ifndef R_AARCH64_MOVW_PREL_G1 +#define R_AARCH64_MOVW_PREL_G1 289 +#endif +#ifndef R_AARCH64_MOVW_PREL_G1_NC +#define R_AARCH64_MOVW_PREL_G1_NC 290 +#endif +#ifndef R_AARCH64_MOVW_PREL_G2 +#define R_AARCH64_MOVW_PREL_G2 291 +#endif +#ifndef R_AARCH64_MOVW_PREL_G2_NC +#define R_AARCH64_MOVW_PREL_G2_NC 292 +#endif +#ifndef R_AARCH64_MOVW_PREL_G3 +#define R_AARCH64_MOVW_PREL_G3 293 +#endif +#ifndef R_AARCH64_LDST128_ABS_LO12_NC +#define R_AARCH64_LDST128_ABS_LO12_NC 299 +#endif + +/* Global state of the processed ELF. */ +static struct { + const char *path; + char *begin; + size_t size; + Elf64_Ehdr *ehdr; + Elf64_Shdr *sh_table; + const char *sh_string; +} elf; + +#if defined(CONFIG_CPU_LITTLE_ENDIAN) + +#define elf16toh(x) le16toh(x) +#define elf32toh(x) le32toh(x) +#define elf64toh(x) le64toh(x) + +#define ELFENDIAN ELFDATA2LSB + +#elif defined(CONFIG_CPU_BIG_ENDIAN) + +#define elf16toh(x) be16toh(x) +#define elf32toh(x) be32toh(x) +#define elf64toh(x) be64toh(x) + +#define ELFENDIAN ELFDATA2MSB + +#else + +#error PDP-endian sadly unsupported... + +#endif + +#define fatal_error(fmt, ...) \ + ({ \ + fprintf(stderr, "error: %s: " fmt "\n", \ + elf.path, ## __VA_ARGS__); \ + exit(EXIT_FAILURE); \ + __builtin_unreachable(); \ + }) + +#define fatal_perror(msg) \ + ({ \ + fprintf(stderr, "error: %s: " msg ": %s\n", \ + elf.path, strerror(errno)); \ + exit(EXIT_FAILURE); \ + __builtin_unreachable(); \ + }) + +#define assert_op(lhs, rhs, fmt, op) \ + ({ \ + typeof(lhs) _lhs = (lhs); \ + typeof(rhs) _rhs = (rhs); \ + \ + if (!(_lhs op _rhs)) { \ + fatal_error("assertion " #lhs " " #op " " #rhs \ + " failed (lhs=" fmt ", rhs=" fmt \ + ", line=%d)", _lhs, _rhs, __LINE__); \ + } \ + }) + +#define assert_eq(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, ==) +#define assert_ne(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, !=) +#define assert_lt(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, <) +#define assert_ge(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, >=) + +/* + * Return a pointer of a given type at a given offset from + * the beginning of the ELF file. + */ +#define elf_ptr(type, off) ((type *)(elf.begin + (off))) + +/* Iterate over all sections in the ELF. */ +#define for_each_section(var) \ + for (var = elf.sh_table; var < elf.sh_table + elf16toh(elf.ehdr->e_shnum); ++var) + +/* Iterate over all Elf64_Rela relocations in a given section. */ +#define for_each_rela(shdr, var) \ + for (var = elf_ptr(Elf64_Rela, elf64toh(shdr->sh_offset)); \ + var < elf_ptr(Elf64_Rela, elf64toh(shdr->sh_offset) + elf64toh(shdr->sh_size)); var++) + +/* True if a string starts with a given prefix. */ +static inline bool starts_with(const char *str, const char *prefix) +{ + return memcmp(str, prefix, strlen(prefix)) == 0; +} + +/* Returns a string containing the name of a given section. */ +static inline const char *section_name(Elf64_Shdr *shdr) +{ + return elf.sh_string + elf32toh(shdr->sh_name); +} + +/* Returns a pointer to the first byte of section data. */ +static inline const char *section_begin(Elf64_Shdr *shdr) +{ + return elf_ptr(char, elf64toh(shdr->sh_offset)); +} + +/* Find a section by its offset from the beginning of the file. */ +static inline Elf64_Shdr *section_by_off(Elf64_Off off) +{ + assert_ne(off, 0UL, "%lu"); + return elf_ptr(Elf64_Shdr, off); +} + +/* Find a section by its index. */ +static inline Elf64_Shdr *section_by_idx(uint16_t idx) +{ + assert_ne(idx, SHN_UNDEF, "%u"); + return &elf.sh_table[idx]; +} + +/* + * Memory-map the given ELF file, perform sanity checks, and + * populate global state. + */ +static void init_elf(const char *path) +{ + int fd, ret; + struct stat stat; + + /* Store path in the global struct for error printing. */ + elf.path = path; + + /* Open the ELF file. */ + fd = open(path, O_RDONLY); + if (fd < 0) + fatal_perror("Could not open ELF file"); + + /* Get status of ELF file to obtain its size. */ + ret = fstat(fd, &stat); + if (ret < 0) { + close(fd); + fatal_perror("Could not get status of ELF file"); + } + + /* mmap() the entire ELF file read-only at an arbitrary address. */ + elf.begin = mmap(0, stat.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (elf.begin == MAP_FAILED) { + close(fd); + fatal_perror("Could not mmap ELF file"); + } + + /* mmap() was successful, close the FD. */ + close(fd); + + /* Get pointer to the ELF header. */ + assert_ge(stat.st_size, sizeof(*elf.ehdr), "%lu"); + elf.ehdr = elf_ptr(Elf64_Ehdr, 0); + + /* Check the ELF magic. */ + assert_eq(elf.ehdr->e_ident[EI_MAG0], ELFMAG0, "0x%x"); + assert_eq(elf.ehdr->e_ident[EI_MAG1], ELFMAG1, "0x%x"); + assert_eq(elf.ehdr->e_ident[EI_MAG2], ELFMAG2, "0x%x"); + assert_eq(elf.ehdr->e_ident[EI_MAG3], ELFMAG3, "0x%x"); + + /* Sanity check that this is an ELF64 relocatable object for AArch64. */ + assert_eq(elf.ehdr->e_ident[EI_CLASS], ELFCLASS64, "%u"); + assert_eq(elf.ehdr->e_ident[EI_DATA], ELFENDIAN, "%u"); + assert_eq(elf16toh(elf.ehdr->e_type), ET_REL, "%u"); + assert_eq(elf16toh(elf.ehdr->e_machine), EM_AARCH64, "%u"); + + /* Populate fields of the global struct. */ + elf.sh_table = section_by_off(elf64toh(elf.ehdr->e_shoff)); + elf.sh_string = section_begin(section_by_idx(elf16toh(elf.ehdr->e_shstrndx))); +} + +/* Print the prologue of the output ASM file. */ +static void emit_prologue(void) +{ + printf(".data\n" + ".pushsection " HYP_RELOC_SECTION ", \"a\"\n"); +} + +/* Print ASM statements needed as a prologue to a processed hyp section. */ +static void emit_section_prologue(const char *sh_orig_name) +{ + /* Declare the hyp section symbol. */ + printf(".global %s%s\n", HYP_SECTION_SYMBOL_PREFIX, sh_orig_name); +} + +/* + * Print ASM statements to create a hyp relocation entry for a given + * R_AARCH64_ABS64 relocation. + * + * The linker of vmlinux will populate the position given by `rela` with + * an absolute 64-bit kernel VA. If the kernel is relocatable, it will + * also generate a dynamic relocation entry so that the kernel can shift + * the address at runtime for KASLR. + * + * Emit a 32-bit offset from the current address to the position given + * by `rela`. This way the kernel can iterate over all kernel VAs used + * by hyp at runtime and convert them to hyp VAs. However, that offset + * will not be known until linking of `vmlinux`, so emit a PREL32 + * relocation referencing a symbol that the hyp linker script put at + * the beginning of the relocated section + the offset from `rela`. + */ +static void emit_rela_abs64(Elf64_Rela *rela, const char *sh_orig_name) +{ + /* Offset of this reloc from the beginning of HYP_RELOC_SECTION. */ + static size_t reloc_offset; + + /* Create storage for the 32-bit offset. */ + printf(".word 0\n"); + + /* + * Create a PREL32 relocation which instructs the linker of `vmlinux` + * to insert offset to position <base> + <offset>, where <base> is + * a symbol at the beginning of the relocated section, and <offset> + * is `rela->r_offset`. + */ + printf(".reloc %lu, R_AARCH64_PREL32, %s%s + 0x%lx\n", + reloc_offset, HYP_SECTION_SYMBOL_PREFIX, sh_orig_name, + elf64toh(rela->r_offset)); + + reloc_offset += 4; +} + +/* Print the epilogue of the output ASM file. */ +static void emit_epilogue(void) +{ + printf(".popsection\n"); +} + +/* + * Iterate over all RELA relocations in a given section and emit + * hyp relocation data for all absolute addresses in hyp code/data. + * + * Static relocations that generate PC-relative-addressing are ignored. + * Failure is reported for unexpected relocation types. + */ +static void emit_rela_section(Elf64_Shdr *sh_rela) +{ + Elf64_Shdr *sh_orig = &elf.sh_table[elf32toh(sh_rela->sh_info)]; + const char *sh_orig_name = section_name(sh_orig); + Elf64_Rela *rela; + + /* Skip all non-hyp sections. */ + if (!starts_with(sh_orig_name, HYP_SECTION_PREFIX)) + return; + + emit_section_prologue(sh_orig_name); + + for_each_rela(sh_rela, rela) { + uint32_t type = (uint32_t)elf64toh(rela->r_info); + + /* Check that rela points inside the relocated section. */ + assert_lt(elf64toh(rela->r_offset), elf64toh(sh_orig->sh_size), "0x%lx"); + + switch (type) { + /* + * Data relocations to generate absolute addressing. + * Emit a hyp relocation. + */ + case R_AARCH64_ABS64: + emit_rela_abs64(rela, sh_orig_name); + break; + /* Allow relocations to generate PC-relative addressing. */ + case R_AARCH64_LD_PREL_LO19: + case R_AARCH64_ADR_PREL_LO21: + case R_AARCH64_ADR_PREL_PG_HI21: + case R_AARCH64_ADR_PREL_PG_HI21_NC: + case R_AARCH64_ADD_ABS_LO12_NC: + case R_AARCH64_LDST8_ABS_LO12_NC: + case R_AARCH64_LDST16_ABS_LO12_NC: + case R_AARCH64_LDST32_ABS_LO12_NC: + case R_AARCH64_LDST64_ABS_LO12_NC: + case R_AARCH64_LDST128_ABS_LO12_NC: + break; + /* Allow relative relocations for control-flow instructions. */ + case R_AARCH64_TSTBR14: + case R_AARCH64_CONDBR19: + case R_AARCH64_JUMP26: + case R_AARCH64_CALL26: + break; + /* Allow group relocations to create PC-relative offset inline. */ + case R_AARCH64_MOVW_PREL_G0: + case R_AARCH64_MOVW_PREL_G0_NC: + case R_AARCH64_MOVW_PREL_G1: + case R_AARCH64_MOVW_PREL_G1_NC: + case R_AARCH64_MOVW_PREL_G2: + case R_AARCH64_MOVW_PREL_G2_NC: + case R_AARCH64_MOVW_PREL_G3: + break; + default: + fatal_error("Unexpected RELA type %u", type); + } + } +} + +/* Iterate over all sections and emit hyp relocation data for RELA sections. */ +static void emit_all_relocs(void) +{ + Elf64_Shdr *shdr; + + for_each_section(shdr) { + switch (elf32toh(shdr->sh_type)) { + case SHT_REL: + fatal_error("Unexpected SHT_REL section \"%s\"", + section_name(shdr)); + case SHT_RELA: + emit_rela_section(shdr); + break; + } + } +} + +int main(int argc, const char **argv) +{ + if (argc != 2) { + fprintf(stderr, "Usage: %s <elf_input>\n", argv[0]); + return EXIT_FAILURE; + } + + init_elf(argv[1]); + + emit_prologue(); + emit_all_relocs(); + emit_epilogue(); + + return EXIT_SUCCESS; +} diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index a820dfdc9c25..6585a7cbbc56 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -74,27 +74,28 @@ SYM_FUNC_END(__host_enter) * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par); */ SYM_FUNC_START(__hyp_do_panic) - /* Load the format arguments into x1-7 */ - mov x6, x3 - get_vcpu_ptr x7, x3 - - mrs x3, esr_el2 - mrs x4, far_el2 - mrs x5, hpfar_el2 - /* Prepare and exit to the host's panic funciton. */ mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ PSR_MODE_EL1h) msr spsr_el2, lr ldr lr, =panic + hyp_kimg_va lr, x6 msr elr_el2, lr - /* - * Set the panic format string and enter the host, conditionally - * restoring the host context. - */ + /* Set the panic format string. Use the, now free, LR as scratch. */ + ldr lr, =__hyp_panic_string + hyp_kimg_va lr, x6 + + /* Load the format arguments into x1-7. */ + mov x6, x3 + get_vcpu_ptr x7, x3 + mrs x3, esr_el2 + mrs x4, far_el2 + mrs x5, hpfar_el2 + + /* Enter the host, conditionally restoring the host context. */ cmp x0, xzr - ldr x0, =__hyp_panic_string + mov x0, lr b.eq __host_enter_without_restoring b __host_enter_for_panic SYM_FUNC_END(__hyp_do_panic) @@ -124,7 +125,7 @@ SYM_FUNC_END(__hyp_do_panic) * Preserve x0-x4, which may contain stub parameters. */ ldr x5, =__kvm_handle_stub_hvc - kimg_pa x5, x6 + hyp_pa x5, x6 br x5 .L__vect_end\@: .if ((.L__vect_end\@ - .L__vect_start\@) > 0x80) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index b17bf19217f1..50be6f4e6b99 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -18,7 +18,7 @@ #include <asm/virt.h> .text - .pushsection .hyp.idmap.text, "ax" + .pushsection .idmap.text, "ax" .align 11 @@ -57,17 +57,10 @@ __do_hyp_init: cmp x0, #HVC_STUB_HCALL_NR b.lo __kvm_handle_stub_hvc - // We only actively check bits [24:31], and everything - // else has to be zero, which we check at build time. -#if (KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) & 0xFFFFFFFF00FFFFFF) -#error Unexpected __KVM_HOST_SMCCC_FUNC___kvm_hyp_init value -#endif - - ror x0, x0, #24 - eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 24) & 0xF) - ror x0, x0, #4 - eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 28) & 0xF) - cbz x0, 1f + mov x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) + cmp x0, x3 + b.eq 1f + mov x0, #SMCCC_RET_NOT_SUPPORTED eret @@ -141,7 +134,6 @@ alternative_else_nop_endif /* Set the host vector */ ldr x0, =__kvm_hyp_host_vector - kimg_hyp_va x0, x1 msr vbar_el2, x0 ret @@ -200,7 +192,6 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu) /* Leave idmap. */ mov x0, x29 ldr x1, =kvm_host_psci_cpu_entry - kimg_hyp_va x1, x2 br x1 SYM_CODE_END(__kvm_hyp_init_cpu) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index a906f9e2ff34..f012f8665ecc 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -108,9 +108,9 @@ static void handle___vgic_v3_restore_aprs(struct kvm_cpu_context *host_ctxt) typedef void (*hcall_t)(struct kvm_cpu_context *); -#define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = kimg_fn_ptr(handle_##x) +#define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x -static const hcall_t *host_hcall[] = { +static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_vcpu_run), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), @@ -130,7 +130,6 @@ static const hcall_t *host_hcall[] = { static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(unsigned long, id, host_ctxt, 0); - const hcall_t *kfn; hcall_t hfn; id -= KVM_HOST_SMCCC_ID(0); @@ -138,13 +137,11 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) if (unlikely(id >= ARRAY_SIZE(host_hcall))) goto inval; - kfn = host_hcall[id]; - if (unlikely(!kfn)) + hfn = host_hcall[id]; + if (unlikely(!hfn)) goto inval; cpu_reg(host_ctxt, 0) = SMCCC_RET_SUCCESS; - - hfn = kimg_fn_hyp_va(kfn); hfn(host_ctxt); return; diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c index 2997aa156d8e..879559057dee 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c @@ -33,8 +33,8 @@ unsigned long __hyp_per_cpu_offset(unsigned int cpu) if (cpu >= ARRAY_SIZE(kvm_arm_hyp_percpu_base)) hyp_panic(); - cpu_base_array = (unsigned long *)hyp_symbol_addr(kvm_arm_hyp_percpu_base); + cpu_base_array = (unsigned long *)&kvm_arm_hyp_percpu_base; this_cpu_base = kern_hyp_va(cpu_base_array[cpu]); - elf_base = (unsigned long)hyp_symbol_addr(__per_cpu_start); + elf_base = (unsigned long)&__per_cpu_start; return this_cpu_base - elf_base; } diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S index 1206d0d754d5..cd119d82d8e3 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -12,14 +12,17 @@ #include <asm/memory.h> SECTIONS { + HYP_SECTION(.idmap.text) HYP_SECTION(.text) + HYP_SECTION(.data..ro_after_init) + HYP_SECTION(.rodata) + /* * .hyp..data..percpu needs to be page aligned to maintain the same * alignment for when linking into vmlinux. */ . = ALIGN(PAGE_SIZE); - HYP_SECTION_NAME(.data..percpu) : { + BEGIN_HYP_SECTION(.data..percpu) PERCPU_INPUT(L1_CACHE_BYTES) - } - HYP_SECTION(.data..ro_after_init) + END_HYP_SECTION } diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index 8e7128cb7667..63de71c0481e 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -128,8 +128,8 @@ static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt) if (cpu_id == INVALID_CPU_ID) return PSCI_RET_INVALID_PARAMS; - boot_args = per_cpu_ptr(hyp_symbol_addr(cpu_on_args), cpu_id); - init_params = per_cpu_ptr(hyp_symbol_addr(kvm_init_params), cpu_id); + boot_args = per_cpu_ptr(&cpu_on_args, cpu_id); + init_params = per_cpu_ptr(&kvm_init_params, cpu_id); /* Check if the target CPU is already being booted. */ if (!try_acquire_boot_args(boot_args)) @@ -140,7 +140,7 @@ static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt) wmb(); ret = psci_call(func_id, mpidr, - __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_entry)), + __hyp_pa(&kvm_hyp_cpu_entry), __hyp_pa(init_params)); /* If successful, the lock will be released by the target CPU. */ @@ -159,8 +159,8 @@ static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) struct psci_boot_args *boot_args; struct kvm_nvhe_init_params *init_params; - boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args)); - init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params)); + boot_args = this_cpu_ptr(&suspend_args); + init_params = this_cpu_ptr(&kvm_init_params); /* * No need to acquire a lock before writing to boot_args because a core @@ -174,7 +174,7 @@ static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) * point if it is a deep sleep state. */ return psci_call(func_id, power_state, - __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)), + __hyp_pa(&kvm_hyp_cpu_resume), __hyp_pa(init_params)); } @@ -186,8 +186,8 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) struct psci_boot_args *boot_args; struct kvm_nvhe_init_params *init_params; - boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args)); - init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params)); + boot_args = this_cpu_ptr(&suspend_args); + init_params = this_cpu_ptr(&kvm_init_params); /* * No need to acquire a lock before writing to boot_args because a core @@ -198,7 +198,7 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) /* Will only return on error. */ return psci_call(func_id, - __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)), + __hyp_pa(&kvm_hyp_cpu_resume), __hyp_pa(init_params), 0); } @@ -207,12 +207,12 @@ asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on) struct psci_boot_args *boot_args; struct kvm_cpu_context *host_ctxt; - host_ctxt = &this_cpu_ptr(hyp_symbol_addr(kvm_host_data))->host_ctxt; + host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; if (is_cpu_on) - boot_args = this_cpu_ptr(hyp_symbol_addr(cpu_on_args)); + boot_args = this_cpu_ptr(&cpu_on_args); else - boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args)); + boot_args = this_cpu_ptr(&suspend_args); cpu_reg(host_ctxt, 0) = boot_args->r0; write_sysreg_el2(boot_args->pc, SYS_ELR); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index bdf8e55ed308..4d177ce1d536 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -45,6 +45,10 @@ #define KVM_PTE_LEAF_ATTR_HI_S2_XN BIT(54) +#define KVM_PTE_LEAF_ATTR_S2_PERMS (KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \ + KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \ + KVM_PTE_LEAF_ATTR_HI_S2_XN) + struct kvm_pgtable_walk_data { struct kvm_pgtable *pgt; struct kvm_pgtable_walker *walker; @@ -170,10 +174,9 @@ static void kvm_set_table_pte(kvm_pte_t *ptep, kvm_pte_t *childp) smp_store_release(ptep, pte); } -static bool kvm_set_valid_leaf_pte(kvm_pte_t *ptep, u64 pa, kvm_pte_t attr, - u32 level) +static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level) { - kvm_pte_t old = *ptep, pte = kvm_phys_to_pte(pa); + kvm_pte_t pte = kvm_phys_to_pte(pa); u64 type = (level == KVM_PGTABLE_MAX_LEVELS - 1) ? KVM_PTE_TYPE_PAGE : KVM_PTE_TYPE_BLOCK; @@ -181,12 +184,7 @@ static bool kvm_set_valid_leaf_pte(kvm_pte_t *ptep, u64 pa, kvm_pte_t attr, pte |= FIELD_PREP(KVM_PTE_TYPE, type); pte |= KVM_PTE_VALID; - /* Tolerate KVM recreating the exact same mapping. */ - if (kvm_pte_valid(old)) - return old == pte; - - smp_store_release(ptep, pte); - return true; + return pte; } static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, u64 addr, @@ -341,12 +339,17 @@ static int hyp_map_set_prot_attr(enum kvm_pgtable_prot prot, static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct hyp_map_data *data) { + kvm_pte_t new, old = *ptep; u64 granule = kvm_granule_size(level), phys = data->phys; if (!kvm_block_mapping_supported(addr, end, phys, level)) return false; - WARN_ON(!kvm_set_valid_leaf_pte(ptep, phys, data->attr, level)); + /* Tolerate KVM recreating the exact same mapping */ + new = kvm_init_valid_leaf_pte(phys, data->attr, level); + if (old != new && !WARN_ON(kvm_pte_valid(old))) + smp_store_release(ptep, new); + data->phys += granule; return true; } @@ -461,34 +464,41 @@ static int stage2_map_set_prot_attr(enum kvm_pgtable_prot prot, return 0; } -static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - struct stage2_map_data *data) +static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, + kvm_pte_t *ptep, + struct stage2_map_data *data) { + kvm_pte_t new, old = *ptep; u64 granule = kvm_granule_size(level), phys = data->phys; + struct page *page = virt_to_page(ptep); if (!kvm_block_mapping_supported(addr, end, phys, level)) - return false; - - /* - * If the PTE was already valid, drop the refcount on the table - * early, as it will be bumped-up again in stage2_map_walk_leaf(). - * This ensures that the refcount stays constant across a valid to - * valid PTE update. - */ - if (kvm_pte_valid(*ptep)) - put_page(virt_to_page(ptep)); - - if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level)) - goto out; + return -E2BIG; + + new = kvm_init_valid_leaf_pte(phys, data->attr, level); + if (kvm_pte_valid(old)) { + /* + * Skip updating the PTE if we are trying to recreate the exact + * same mapping or only change the access permissions. Instead, + * the vCPU will exit one more time from guest if still needed + * and then go through the path of relaxing permissions. + */ + if (!((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS))) + return -EAGAIN; + + /* + * There's an existing different valid leaf entry, so perform + * break-before-make. + */ + kvm_set_invalid_pte(ptep); + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, level); + put_page(page); + } - /* There's an existing valid leaf entry, so perform break-before-make */ - kvm_set_invalid_pte(ptep); - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, level); - kvm_set_valid_leaf_pte(ptep, phys, data->attr, level); -out: + smp_store_release(ptep, new); + get_page(page); data->phys += granule; - return true; + return 0; } static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, @@ -516,6 +526,7 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct stage2_map_data *data) { + int ret; kvm_pte_t *childp, pte = *ptep; struct page *page = virt_to_page(ptep); @@ -526,8 +537,9 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, return 0; } - if (stage2_map_walker_try_leaf(addr, end, level, ptep, data)) - goto out_get_page; + ret = stage2_map_walker_try_leaf(addr, end, level, ptep, data); + if (ret != -E2BIG) + return ret; if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1)) return -EINVAL; @@ -551,9 +563,8 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, } kvm_set_table_pte(ptep, childp); - -out_get_page: get_page(page); + return 0; } diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index 8f0585640241..87a54375bd6e 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -64,7 +64,7 @@ int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) } rd = kvm_vcpu_dabt_get_rd(vcpu); - addr = hyp_symbol_addr(kvm_vgic_global_state)->vcpu_hyp_va; + addr = kvm_vgic_global_state.vcpu_hyp_va; addr += fault_ipa - vgic->vgic_cpu_base; if (kvm_vcpu_dabt_iswrite(vcpu)) { diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 25ea4ecb6449..ead21b98b620 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -71,6 +71,12 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) if (gpa != GPA_INVALID) val = gpa; break; + case ARM_SMCCC_TRNG_VERSION: + case ARM_SMCCC_TRNG_FEATURES: + case ARM_SMCCC_TRNG_GET_UUID: + case ARM_SMCCC_TRNG_RND32: + case ARM_SMCCC_TRNG_RND64: + return kvm_trng_call(vcpu); default: return kvm_psci_call(vcpu); } diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 7d2257cc5438..77cb2d28f2a4 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -879,11 +879,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (vma_pagesize == PAGE_SIZE && !force_pte) vma_pagesize = transparent_hugepage_adjust(memslot, hva, &pfn, &fault_ipa); - if (writable) { + if (writable) prot |= KVM_PGTABLE_PROT_W; - kvm_set_pfn_dirty(pfn); - mark_page_dirty(kvm, gfn); - } if (fault_status != FSC_PERM && !device) clean_dcache_guest_page(pfn, vma_pagesize); @@ -911,11 +908,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, memcache); } + /* Mark the page dirty only if the fault is handled successfully */ + if (writable && !ret) { + kvm_set_pfn_dirty(pfn); + mark_page_dirty(kvm, gfn); + } + out_unlock: spin_unlock(&kvm->mmu_lock); kvm_set_pfn_accessed(pfn); kvm_release_pfn_clean(pfn); - return ret; + return ret != -EAGAIN ? ret : 0; } /* Resolve the access fault by making the page young again. */ diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 247422ac78a9..e9ec08b0b070 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -23,11 +23,11 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc); static u32 kvm_pmu_event_mask(struct kvm *kvm) { switch (kvm->arch.pmuver) { - case 1: /* ARMv8.0 */ + case ID_AA64DFR0_PMUVER_8_0: return GENMASK(9, 0); - case 4: /* ARMv8.1 */ - case 5: /* ARMv8.4 */ - case 6: /* ARMv8.5 */ + case ID_AA64DFR0_PMUVER_8_1: + case ID_AA64DFR0_PMUVER_8_4: + case ID_AA64DFR0_PMUVER_8_5: return GENMASK(15, 0); default: /* Shouldn't be here, just for sanity */ WARN_ONCE(1, "Unknown PMU version %d\n", kvm->arch.pmuver); @@ -795,6 +795,12 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) base = 0; } else { val = read_sysreg(pmceid1_el0); + /* + * Don't advertise STALL_SLOT, as PMMIR_EL0 is handled + * as RAZ + */ + if (vcpu->kvm->arch.pmuver >= ID_AA64DFR0_PMUVER_8_4) + val &= ~BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32); base = 32; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7c4f79532406..4f2f1e3145de 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -9,6 +9,7 @@ * Christoffer Dall <c.dall@virtualopensystems.com> */ +#include <linux/bitfield.h> #include <linux/bsearch.h> #include <linux/kvm_host.h> #include <linux/mm.h> @@ -700,14 +701,18 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - u64 pmceid; + u64 pmceid, mask, shift; BUG_ON(p->is_write); if (pmu_access_el0_disabled(vcpu)) return false; + get_access_mask(r, &mask, &shift); + pmceid = kvm_pmu_get_pmceid(vcpu, (p->Op2 & 1)); + pmceid &= mask; + pmceid >>= shift; p->regval = pmceid; @@ -1021,6 +1026,8 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, return true; } +#define FEATURE(x) (GENMASK_ULL(x##_SHIFT + 3, x##_SHIFT)) + /* Read a sanitised cpufeature ID register by sys_reg_desc */ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r, bool raz) @@ -1028,36 +1035,41 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, u32 id = reg_to_encoding(r); u64 val = raz ? 0 : read_sanitised_ftr_reg(id); - if (id == SYS_ID_AA64PFR0_EL1) { + switch (id) { + case SYS_ID_AA64PFR0_EL1: if (!vcpu_has_sve(vcpu)) - val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); - val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT); - val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT); - val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT); - val &= ~(0xfUL << ID_AA64PFR0_CSV3_SHIFT); - val |= ((u64)vcpu->kvm->arch.pfr0_csv3 << ID_AA64PFR0_CSV3_SHIFT); - } else if (id == SYS_ID_AA64PFR1_EL1) { - val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT); - } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) { - val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) | - (0xfUL << ID_AA64ISAR1_API_SHIFT) | - (0xfUL << ID_AA64ISAR1_GPA_SHIFT) | - (0xfUL << ID_AA64ISAR1_GPI_SHIFT)); - } else if (id == SYS_ID_AA64DFR0_EL1) { - u64 cap = 0; - - /* Limit guests to PMUv3 for ARMv8.1 */ - if (kvm_vcpu_has_pmu(vcpu)) - cap = ID_AA64DFR0_PMUVER_8_1; - + val &= ~FEATURE(ID_AA64PFR0_SVE); + val &= ~FEATURE(ID_AA64PFR0_AMU); + val &= ~FEATURE(ID_AA64PFR0_CSV2); + val |= FIELD_PREP(FEATURE(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2); + val &= ~FEATURE(ID_AA64PFR0_CSV3); + val |= FIELD_PREP(FEATURE(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3); + break; + case SYS_ID_AA64PFR1_EL1: + val &= ~FEATURE(ID_AA64PFR1_MTE); + break; + case SYS_ID_AA64ISAR1_EL1: + if (!vcpu_has_ptrauth(vcpu)) + val &= ~(FEATURE(ID_AA64ISAR1_APA) | + FEATURE(ID_AA64ISAR1_API) | + FEATURE(ID_AA64ISAR1_GPA) | + FEATURE(ID_AA64ISAR1_GPI)); + break; + case SYS_ID_AA64DFR0_EL1: + /* Limit debug to ARMv8.0 */ + val &= ~FEATURE(ID_AA64DFR0_DEBUGVER); + val |= FIELD_PREP(FEATURE(ID_AA64DFR0_DEBUGVER), 6); + /* Limit guests to PMUv3 for ARMv8.4 */ val = cpuid_feature_cap_perfmon_field(val, - ID_AA64DFR0_PMUVER_SHIFT, - cap); - } else if (id == SYS_ID_DFR0_EL1) { - /* Limit guests to PMUv3 for ARMv8.1 */ + ID_AA64DFR0_PMUVER_SHIFT, + kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_PMUVER_8_4 : 0); + break; + case SYS_ID_DFR0_EL1: + /* Limit guests to PMUv3 for ARMv8.4 */ val = cpuid_feature_cap_perfmon_field(val, - ID_DFR0_PERFMON_SHIFT, - ID_DFR0_PERFMON_8_1); + ID_DFR0_PERFMON_SHIFT, + kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_PERFMON_8_4 : 0); + break; } return val; @@ -1493,6 +1505,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { .access = access_pminten, .reg = PMINTENSET_EL1 }, { PMU_SYS_REG(SYS_PMINTENCLR_EL1), .access = access_pminten, .reg = PMINTENSET_EL1 }, + { SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, @@ -1720,7 +1733,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 }, }; -static bool trap_dbgidr(struct kvm_vcpu *vcpu, +static bool trap_dbgdidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { @@ -1734,7 +1747,7 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu, p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) | (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) | (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) - | (6 << 16) | (el3 << 14) | (el3 << 12)); + | (6 << 16) | (1 << 15) | (el3 << 14) | (el3 << 12)); return true; } } @@ -1767,8 +1780,8 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu, * guest. Revisit this one day, would this principle change. */ static const struct sys_reg_desc cp14_regs[] = { - /* DBGIDR */ - { Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr }, + /* DBGDIDR */ + { Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgdidr }, /* DBGDTRRXext */ { Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi }, @@ -1918,8 +1931,8 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 9), CRm(12), Op2( 3), access_pmovs }, { Op1( 0), CRn( 9), CRm(12), Op2( 4), access_pmswinc }, { Op1( 0), CRn( 9), CRm(12), Op2( 5), access_pmselr }, - { Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid }, - { Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid }, + { AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid }, + { AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid }, { Op1( 0), CRn( 9), CRm(13), Op2( 0), access_pmu_evcntr }, { Op1( 0), CRn( 9), CRm(13), Op2( 1), access_pmu_evtyper }, { Op1( 0), CRn( 9), CRm(13), Op2( 2), access_pmu_evcntr }, @@ -1927,6 +1940,10 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 9), CRm(14), Op2( 1), access_pminten }, { Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten }, { Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs }, + { AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 4), access_pmceid }, + { AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 5), access_pmceid }, + /* PMMIR */ + { Op1( 0), CRn( 9), CRm(14), Op2( 6), trap_raz_wi }, /* PRRR/MAIR0 */ { AA32(LO), Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, MAIR_EL1 }, diff --git a/arch/arm64/kvm/trng.c b/arch/arm64/kvm/trng.c new file mode 100644 index 000000000000..99bdd7103c9c --- /dev/null +++ b/arch/arm64/kvm/trng.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2020 Arm Ltd. + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> + +#include <kvm/arm_hypercalls.h> + +#define ARM_SMCCC_TRNG_VERSION_1_0 0x10000UL + +/* Those values are deliberately separate from the generic SMCCC definitions. */ +#define TRNG_SUCCESS 0UL +#define TRNG_NOT_SUPPORTED ((unsigned long)-1) +#define TRNG_INVALID_PARAMETER ((unsigned long)-2) +#define TRNG_NO_ENTROPY ((unsigned long)-3) + +#define TRNG_MAX_BITS64 192 + +static const uuid_t arm_smc_trng_uuid __aligned(4) = UUID_INIT( + 0x0d21e000, 0x4384, 0x11eb, 0x80, 0x70, 0x52, 0x44, 0x55, 0x4e, 0x5a, 0x4c); + +static int kvm_trng_do_rnd(struct kvm_vcpu *vcpu, int size) +{ + DECLARE_BITMAP(bits, TRNG_MAX_BITS64); + u32 num_bits = smccc_get_arg1(vcpu); + int i; + + if (num_bits > 3 * size) { + smccc_set_retval(vcpu, TRNG_INVALID_PARAMETER, 0, 0, 0); + return 1; + } + + /* get as many bits as we need to fulfil the request */ + for (i = 0; i < DIV_ROUND_UP(num_bits, BITS_PER_LONG); i++) + bits[i] = get_random_long(); + + bitmap_clear(bits, num_bits, TRNG_MAX_BITS64 - num_bits); + + if (size == 32) + smccc_set_retval(vcpu, TRNG_SUCCESS, lower_32_bits(bits[1]), + upper_32_bits(bits[0]), lower_32_bits(bits[0])); + else + smccc_set_retval(vcpu, TRNG_SUCCESS, bits[2], bits[1], bits[0]); + + memzero_explicit(bits, sizeof(bits)); + return 1; +} + +int kvm_trng_call(struct kvm_vcpu *vcpu) +{ + const __le32 *u = (__le32 *)arm_smc_trng_uuid.b; + u32 func_id = smccc_get_function(vcpu); + unsigned long val = TRNG_NOT_SUPPORTED; + int size = 64; + + switch (func_id) { + case ARM_SMCCC_TRNG_VERSION: + val = ARM_SMCCC_TRNG_VERSION_1_0; + break; + case ARM_SMCCC_TRNG_FEATURES: + switch (smccc_get_arg1(vcpu)) { + case ARM_SMCCC_TRNG_VERSION: + case ARM_SMCCC_TRNG_FEATURES: + case ARM_SMCCC_TRNG_GET_UUID: + case ARM_SMCCC_TRNG_RND32: + case ARM_SMCCC_TRNG_RND64: + val = TRNG_SUCCESS; + } + break; + case ARM_SMCCC_TRNG_GET_UUID: + smccc_set_retval(vcpu, le32_to_cpu(u[0]), le32_to_cpu(u[1]), + le32_to_cpu(u[2]), le32_to_cpu(u[3])); + return 1; + case ARM_SMCCC_TRNG_RND32: + size = 32; + fallthrough; + case ARM_SMCCC_TRNG_RND64: + return kvm_trng_do_rnd(vcpu, size); + } + + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; +} diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index 70fcd6a12fe1..978301392d67 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -81,6 +81,34 @@ __init void kvm_compute_layout(void) init_hyp_physvirt_offset(); } +/* + * The .hyp.reloc ELF section contains a list of kimg positions that + * contains kimg VAs but will be accessed only in hyp execution context. + * Convert them to hyp VAs. See gen-hyprel.c for more details. + */ +__init void kvm_apply_hyp_relocations(void) +{ + int32_t *rel; + int32_t *begin = (int32_t *)__hyp_reloc_begin; + int32_t *end = (int32_t *)__hyp_reloc_end; + + for (rel = begin; rel < end; ++rel) { + uintptr_t *ptr, kimg_va; + + /* + * Each entry contains a 32-bit relative offset from itself + * to a kimg VA position. + */ + ptr = (uintptr_t *)lm_alias((char *)rel + *rel); + + /* Read the kimg VA value at the relocation address. */ + kimg_va = *ptr; + + /* Convert to hyp VA and store back to the relocation address. */ + *ptr = __early_kern_hyp_va((uintptr_t)lm_alias(kimg_va)); + } +} + static u32 compute_instruction(int n, u32 rd, u32 rn) { u32 insn = AARCH64_BREAK_FAULT; @@ -255,12 +283,6 @@ static void generate_mov_q(u64 val, __le32 *origptr, __le32 *updptr, int nr_inst *updptr++ = cpu_to_le32(insn); } -void kvm_update_kimg_phys_offset(struct alt_instr *alt, - __le32 *origptr, __le32 *updptr, int nr_inst) -{ - generate_mov_q(kimage_voffset + PHYS_OFFSET, origptr, updptr, nr_inst); -} - void kvm_get_kimage_voffset(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 7deddf56f7c3..709d98fea90c 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* - * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of - * memory as some devices, namely the Raspberry Pi 4, have peripherals with - * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 - * bit addressable memory area. + * If the corresponding config options are enabled, we create both ZONE_DMA + * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory + * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). + * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, + * otherwise it is empty. */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, + crash_base = memblock_find_in_range(0, arm64_dma_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; unsigned int __maybe_unused acpi_zone_dma_bits; unsigned int __maybe_unused dt_zone_dma_bits; + phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); @@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = dma32_phys_limit; #endif + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max; free_area_init(max_zone_pfns); @@ -394,16 +399,9 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma32_phys_limit = max_zone_phys(32); - else - arm64_dma32_phys_limit = PHYS_MASK + 1; - reserve_elfcorehdr(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - - dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -439,6 +437,11 @@ void __init bootmem_init(void) zone_sizes_init(min, max); /* + * Reserve the CMA area after arm64_dma_phys_limit was initialised. + */ + dma_contiguous_reserve(arm64_dma_phys_limit); + + /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ @@ -455,7 +458,7 @@ void __init bootmem_init(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c61c641674e6..e3946b06e840 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> +#include <asm/unaligned.h> /* * These two variables specify the free mem region @@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start) dtb_size = fdt_totalsize((void *)&__appended_dtb); /* last four bytes is always image size in little endian */ - image_size = le32_to_cpup((void *)&__image_end - 4); + image_size = get_unaligned_le32((void *)&__image_end - 4); /* copy dtb to where the booted kernel will expect it */ memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index bd47e15d02c7..be5d4afcd30f 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void) static int __init octeon_irq_init_ciu( struct device_node *ciu_node, struct device_node *parent) { - unsigned int i, r; + int i, r; struct irq_chip *chip; struct irq_chip *chip_edge; struct irq_chip *chip_mbox; diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 6ee3f7218c67..c4441416e96b 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 6dd103d3cebb..7b2a23f48c1a 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 47aeb3350a76..0e365b7c742d 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset) static inline __init unsigned long rotate_xor(unsigned long hash, const void *area, size_t size) { - size_t i; - unsigned long *ptr = (unsigned long *)area; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + size_t diff, i; + + diff = (void *)ptr - area; + if (unlikely(size < diff + sizeof(hash))) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); for (i = 0; i < size / sizeof(hash); i++) { /* Rotate by odd number of bits and XOR. */ diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 81671aa365b3..77c635c2c90d 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); } +#ifdef __powerpc64__ + static __always_inline int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); } -#ifdef CONFIG_VDSO32 +#else #define BUILD_VDSO32 1 static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) { return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8e0b1298bf19..4ab426b8b0e0 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -187,6 +187,12 @@ SECTIONS .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT + + /* + *.init.text might be RO so we must ensure this section ends on + * a page boundary. + */ + . = ALIGN(PAGE_SIZE); _einittext = .; #ifdef CONFIG_PPC64 *(.tramp.ftrace.init); @@ -200,6 +206,8 @@ SECTIONS EXIT_TEXT } + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(16) . = ALIGN(8); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 81b76d44725d..e9e2c1f0a690 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -137,7 +137,7 @@ config PA_BITS config PAGE_OFFSET hex - default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB + default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB default 0x80000000 if 64BIT && !MMU default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB @@ -247,10 +247,12 @@ config MODULE_SECTIONS choice prompt "Maximum Physical Memory" - default MAXPHYSMEM_2GB if 32BIT + default MAXPHYSMEM_1GB if 32BIT default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY + config MAXPHYSMEM_1GB + bool "1GiB" config MAXPHYSMEM_2GB bool "2GiB" config MAXPHYSMEM_128GB diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 4a2729f5ca3f..24d75a146e02 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -88,7 +88,9 @@ phy-mode = "gmii"; phy-handle = <&phy0>; phy0: ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0771"; reg = <0>; + reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index d222d353d86d..8c3d1e451703 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 41a72861987c..251e1db088fa 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -99,7 +99,6 @@ | _PAGE_DIRTY) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 8454f746bbfd..1453a2f563bc 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -10,7 +10,7 @@ #include <linux/types.h> -#ifndef GENERIC_TIME_VSYSCALL +#ifndef CONFIG_GENERIC_TIME_VSYSCALL struct vdso_data { }; #endif diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index de59dd457b41..d86781357044 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf) static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); struct cacheinfo *this_leaf; int index; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 524d918f3601..744f3209c48d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -124,15 +124,15 @@ skip_context_tracking: REG_L a1, (a1) jr a1 1: -#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on -#endif /* * Exceptions run with interrupts enabled or disabled depending on the * state of SR_PIE in m/sstatus. */ andi t0, s1, SR_PIE beqz t0, 1f +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_on +#endif csrs CSR_STATUS, SR_IE 1: @@ -155,6 +155,15 @@ skip_context_tracking: tail do_trap_unknown handle_syscall: +#ifdef CONFIG_RISCV_M_MODE + /* + * When running is M-Mode (no MMU config), MPIE does not get set. + * As a result, we need to force enable interrupts here because + * handle_exception did not do set SR_IE as it always sees SR_PIE + * being cleared. + */ + csrs CSR_STATUS, SR_IE +#endif #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING) /* Recover a0 - a7 for system calls */ REG_L a0, PT_A0(sp) @@ -186,14 +195,7 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - blt a7, t1, 1f + bgeu a7, t0, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 1d85e9bf783c..3fa3f26dde85 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -127,7 +127,9 @@ static void __init init_resources(void) { struct memblock_region *region = NULL; struct resource *res = NULL; - int ret = 0; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int ret = 0, i = 0; code_res.start = __pa_symbol(_text); code_res.end = __pa_symbol(_etext) - 1; @@ -145,16 +147,17 @@ static void __init init_resources(void) bss_res.end = __pa_symbol(__bss_stop) - 1; bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); + if (!mem_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); /* * Start by adding the reserved regions, if they overlap * with /memory regions, insert_resource later on will take * care of it. */ for_each_reserved_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; res->name = "Reserved"; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; @@ -171,8 +174,10 @@ static void __init init_resources(void) * Ignore any other reserved regions within * system memory. */ - if (memblock_is_memory(res->start)) + if (memblock_is_memory(res->start)) { + memblock_free((phys_addr_t) res, sizeof(struct resource)); continue; + } ret = add_resource(&iomem_resource, res); if (ret < 0) @@ -181,10 +186,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -205,9 +207,9 @@ static void __init init_resources(void) return; error: - memblock_free((phys_addr_t) res, sizeof(struct resource)); /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); + memblock_free((phys_addr_t) mem_res, mem_res_sz); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 48b870a685b3..df5d2da7c40b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register unsigned long sp_in_global __asm__("sp"); +register const unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER @@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp = sp_in_global; fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = sp_in_global; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 4d3a1048ad8b..8a5cf99c0776 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -24,6 +25,8 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 678204231700..3f1d35e7c98a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,7 +12,7 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else #include <asm/vdso.h> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index bf5379135e39..7cd4993f4ff2 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -157,9 +157,10 @@ disable: void __init setup_bootmem(void) { phys_addr_t mem_start = 0; - phys_addr_t start, end = 0; + phys_addr_t start, dram_end, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); + phys_addr_t max_mapped_addr = __pa(~(ulong)0); u64 i; /* Find the memory region containing the kernel */ @@ -181,7 +182,18 @@ void __init setup_bootmem(void) /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + dram_end = memblock_end_of_DRAM(); + + /* + * memblock allocator is not aware of the fact that last 4K bytes of + * the addressable memory can not be mapped because of IS_ERR_VALUE + * macro. Make sure that last 4k bytes are not usable by memblock + * if end of dram is equal to maximum addressable memory. + */ + if (max_mapped_addr == (dram_end - 1)) + memblock_set_current_limit(max_mapped_addr - 4096); + + max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 12ddd1f6bf70..a8a2ffd9114a 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -93,8 +93,8 @@ void __init kasan_init(void) VMALLOC_END)); for_each_mem_range(i, &_start, &_end) { - void *start = (void *)_start; - void *end = (void *)_end; + void *start = (void *)__va(_start); + void *end = (void *)__va(_end); if (start >= end) break; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index e04d90af4c27..4638a52d8eae 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -16,6 +16,7 @@ #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/idtentry.h> +#include <linux/kexec.h> #include <linux/version.h> #include <linux/vmalloc.h> #include <linux/mm.h> @@ -26,6 +27,8 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> +int hyperv_init_cpuhp; + void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -401,6 +404,7 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); + hyperv_init_cpuhp = cpuhp; return; remove_cpuhp_state: diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 5208ba49c89a..2c87350c1fb0 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (!hv_hypercall_pg) goto do_native; - if (cpumask_empty(cpus)) - return; - local_irq_save(flags); + /* + * Only check the mask _after_ interrupt has been disabled to avoid the + * mask changing under our feet. + */ + if (cpumask_empty(cpus)) { + local_irq_restore(flags); + return; + } + flush_pcpu = (struct hv_tlb_flush **) this_cpu_ptr(hyperv_pcpu_input_arg); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ffc289992d1b..30f76b966857 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) +extern int hyperv_init_cpuhp; + extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f628e3dc150f..43b54bef5448 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -135,14 +135,32 @@ static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) hv_kexec_handler(); + + /* + * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor + * corrupts the old VP Assist Pages and can crash the kexec kernel. + */ + if (kexec_in_progress && hyperv_init_cpuhp > 0) + cpuhp_remove_state(hyperv_init_cpuhp); + + /* The function calls stop_other_cpus(). */ native_machine_shutdown(); + + /* Disable the hypercall page when there is only 1 active CPU. */ + if (kexec_in_progress) + hyperv_cleanup(); } static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); + + /* The function calls crash_smp_send_stop(). */ native_machine_crash_shutdown(regs); + + /* Disable the hypercall page when there is only 1 active CPU. */ + hyperv_cleanup(); } #endif /* CONFIG_KEXEC_CORE */ #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 9e87ab010c82..e68ea5f4ad1c 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) else per_cpu(xen_vcpu_id, cpu) = cpu; rc = xen_vcpu_setup(cpu); - if (rc) + if (rc || !xen_have_vector_callback) return rc; - if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) + if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); @@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu) return 0; } +static bool no_vector_callback __initdata; + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) + if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; xen_hvm_smp_init(); @@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg) } early_param("xen_nopv", xen_parse_nopv); +static __init int xen_parse_no_vector_callback(char *arg) +{ + no_vector_callback = true; + return 0; +} +early_param("xen_no_vector_callback", xen_parse_no_vector_callback); + bool __init xen_hvm_need_lapic(void) { if (xen_pv_domain()) diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f5e7db4f82ab..056430a1080b 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) int cpu; native_smp_prepare_cpus(max_cpus); - WARN_ON(xen_smp_intr_init(0)); - xen_init_lock_cpu(0); + if (xen_have_vector_callback) { + WARN_ON(xen_smp_intr_init(0)); + xen_init_lock_cpu(0); + } for_each_possible_cpu(cpu) { if (cpu == 0) @@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static void xen_hvm_cpu_die(unsigned int cpu) { if (common_cpu_die(cpu) == 0) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); + if (xen_have_vector_callback) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + } } } #else @@ -64,14 +68,17 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) + smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_cpus_done = xen_smp_cpus_done; + smp_ops.cpu_die = xen_hvm_cpu_die; + + if (!xen_have_vector_callback) { + nopvspin = true; return; + } - smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; - smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; - smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; - smp_ops.smp_cpus_done = xen_smp_cpus_done; } |