diff options
Diffstat (limited to 'arch')
65 files changed, 486 insertions, 333 deletions
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 55bc8546d9c7..b45f0124cc16 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -165,6 +165,7 @@ zinstall install: PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@ # We use MRPROPER_FILES and CLEAN_FILES now archclean: diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 65568b23868a..e52c927aade5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -473,7 +473,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6bd1d3ad037a..c332d49780dc 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -910,6 +910,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM erratum 1418040", .capability = ARM64_WORKAROUND_1418040, ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), + .type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU | + ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU), }, #endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2646178c8329..55af8b504b65 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -170,19 +170,6 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 - .if \regsize == 32 - /* - * If we're returning from a 32-bit task on a system affected by - * 1418040 then re-enable userspace access to the virtual counter. - */ -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - orr x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - .endif clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 @@ -294,14 +281,6 @@ alternative_else_nop_endif tst x22, #PSR_MODE32_BIT // native task? b.eq 3f -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - bic x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - #ifdef CONFIG_ARM64_ERRATUM_845719 alternative_if ARM64_WORKAROUND_845719 #ifdef CONFIG_PID_IN_CONTEXTIDR diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 84ec630b8ab5..b63ce4c54cfe 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -516,6 +516,39 @@ static void entry_task_switch(struct task_struct *next) } /* + * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. + * Assuming the virtual counter is enabled at the beginning of times: + * + * - disable access when switching from a 64bit task to a 32bit task + * - enable access when switching from a 32bit task to a 64bit task + */ +static void erratum_1418040_thread_switch(struct task_struct *prev, + struct task_struct *next) +{ + bool prev32, next32; + u64 val; + + if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && + cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + return; + + prev32 = is_compat_thread(task_thread_info(prev)); + next32 = is_compat_thread(task_thread_info(next)); + + if (prev32 == next32) + return; + + val = read_sysreg(cntkctl_el1); + + if (!next32) + val |= ARCH_TIMER_USR_VCT_ACCESS_EN; + else + val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN; + + write_sysreg(val, cntkctl_el1); +} + +/* * Thread switching. */ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, @@ -530,6 +563,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ssbs_thread_switch(next); + erratum_1418040_thread_switch(prev, next); /* * Complete any pending TLB or cache maintenance on this CPU in case diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 5139a5f19256..d6adb4677c25 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -208,7 +208,7 @@ quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ # Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ +quiet_cmd_vdso_install = INSTALL32 $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so vdso.so: $(obj)/vdso.so.dbg diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 691d21e4c717..46dc3d75cf13 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1640,6 +1640,10 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)) + kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ + "Only trusted guests should be used on this system.\n"); + for_each_online_cpu(cpu) { smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); if (ret < 0) { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0121ef2c7c8d..ba00bcc0c884 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -343,7 +343,8 @@ static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd, * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ -static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, + bool may_block) { struct kvm *kvm = mmu->kvm; pgd_t *pgd; @@ -369,11 +370,16 @@ static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 si * If the range is too large, release the kvm->mmu_lock * to prevent starvation and lockup detector warnings. */ - if (next != end) + if (may_block && next != end) cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } +static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +{ + __unmap_stage2_range(mmu, start, size, true); +} + static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -2208,18 +2214,21 @@ static int handle_hva_to_gpa(struct kvm *kvm, static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) { - unmap_stage2_range(&kvm->arch.mmu, gpa, size); + unsigned flags = *(unsigned *)data; + bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE; + + __unmap_stage2_range(&kvm->arch.mmu, gpa, size, may_block); return 0; } int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, unsigned flags) { if (!kvm->arch.mmu.pgd) return 0; trace_kvm_unmap_hva_range(start, end); - handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags); return 0; } diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 10850897a91c..779b6972aa84 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -366,6 +366,15 @@ pgd_index (unsigned long address) } #define pgd_index pgd_index +/* + * In the kernel's mapped region we know everything is in region number 5, so + * as an optimisation its PGD already points to the area for that region. + * However, this also means that we cannot use pgd_index() and we must + * never add the region here. + */ +#define pgd_offset_k(addr) \ + (init_mm.pgd + (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))) + /* Look up a pgd entry in the gate area. On IA-64, the gate-area resides in the kernel-mapped segment, hence we use pgd_offset_k() here. */ diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index d35eaed1668f..825d337a505a 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -969,7 +969,7 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 87fa8d8a1031..28c366d307e7 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -486,7 +486,8 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index fdddb822d564..e005b4581023 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -9,6 +9,11 @@ #ifndef __ASSEMBLY__ +/* + * Added to include __machine_check_early_realmode_* functions + */ +#include <asm/mce.h> + /* This structure can grow, it's real size is used by head.S code * via the mkdefs mechanism. */ diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 925cf89cbf4b..6bfc87915d5d 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -52,7 +52,7 @@ enum fixed_addresses { FIX_HOLE, /* reserve the top 128K for early debugging purposes */ FIX_EARLY_DEBUG_TOP = FIX_HOLE, - FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1, + FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index d635b96c7ea6..7355ed05e65e 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -15,11 +15,18 @@ #ifndef __ASSEMBLY__ #include <asm/page.h> +#include <linux/sizes.h> #define KASAN_SHADOW_SCALE_SHIFT 3 +#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_MODULES) && defined(CONFIG_STRICT_KERNEL_RWX) +#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M) +#else +#define KASAN_KERN_START PAGE_OFFSET +#endif + #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT)) + (KASAN_KERN_START >> KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e020d269416d..10ded83414de 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -58,7 +58,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + unsigned flags); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index adf2cda67f9a..89aa8248a57d 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -210,6 +210,9 @@ struct mce_error_info { #define MCE_EVENT_RELEASE true #define MCE_EVENT_DONTRELEASE false +struct pt_regs; +struct notifier_block; + extern void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t nip, uint64_t addr, uint64_t phys_addr); @@ -225,5 +228,9 @@ int mce_register_notifier(struct notifier_block *nb); int mce_unregister_notifier(struct notifier_block *nb); #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); +long __machine_check_early_realmode_p7(struct pt_regs *regs); +long __machine_check_early_realmode_p8(struct pt_regs *regs); +long __machine_check_early_realmode_p9(struct pt_regs *regs); +long __machine_check_early_realmode_p10(struct pt_regs *regs); #endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 1e8b2e1ec1db..daec64d41b44 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -40,4 +40,7 @@ static inline bool is_sier_available(void) { return false; } /* To support perf_regs sier update */ extern bool is_sier_available(void); +/* To define perf extended regs mask value */ +extern u64 PERF_REG_EXTENDED_MASK; +#define PERF_REG_EXTENDED_MASK PERF_REG_EXTENDED_MASK #endif diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 86c9eb064b22..f6acabb6c9be 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -62,6 +62,11 @@ struct power_pmu { int *blacklist_ev; /* BHRB entries in the PMU */ int bhrb_nr; + /* + * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if + * the pmu supports extended perf regs capability + */ + int capabilities; }; /* diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index f599064dd8dc..bdf5f10f8b9f 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -48,6 +48,24 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, PERF_REG_POWERPC_MMCRA, - PERF_REG_POWERPC_MAX, + /* Extended registers */ + PERF_REG_POWERPC_MMCR0, + PERF_REG_POWERPC_MMCR1, + PERF_REG_POWERPC_MMCR2, + PERF_REG_POWERPC_MMCR3, + PERF_REG_POWERPC_SIER2, + PERF_REG_POWERPC_SIER3, + /* Max regs without the extended regs */ + PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1, }; + +#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) + +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */ +#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) - PERF_REG_PMU_MASK) +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */ +#define PERF_REG_PMU_MASK_31 (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) - PERF_REG_PMU_MASK) + +#define PERF_REG_MAX_ISA_300 (PERF_REG_POWERPC_MMCR2 + 1) +#define PERF_REG_MAX_ISA_31 (PERF_REG_POWERPC_SIER3 + 1) #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 3d406a9626e8..2aa89c6b2896 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -72,9 +72,6 @@ extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power9(void); extern void __setup_cpu_power10(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power10(void); -extern long __machine_check_early_realmode_p7(struct pt_regs *regs); -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -542,6 +539,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, + { /* Power10 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00800000, + .cpu_name = "POWER10 (raw)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power10", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .machine_check_early = __machine_check_early_realmode_p10, + .platform = "power10", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 6f8c0c6b937a..8dc46f38680b 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -64,10 +64,6 @@ struct dt_cpu_feature { * Set up the base CPU */ -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); -extern long __machine_check_early_realmode_p10(struct pt_regs *regs); - static int hv_mode; static struct { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b198b0ff25bc..808ec9fab605 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -311,6 +311,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) min = pvr & 0xFF; break; case 0x004e: /* POWER9 bits 12-15 give chip type */ + case 0x0080: /* POWER10 bit 12 gives SMT8/4 */ maj = (pvr >> 8) & 0x0F; min = pvr & 0xFF; break; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 41fedec69ac3..49db50d1db04 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -834,7 +834,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index d6c1069e9954..ed0c9c43d0cf 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -734,7 +734,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index c0162911f6cb..d426eaf76bb0 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -191,10 +191,17 @@ static bool is_module_segment(unsigned long addr) { if (!IS_ENABLED(CONFIG_MODULES)) return false; +#ifdef MODULES_VADDR + if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M)) + return false; + if (addr > ALIGN(MODULES_END, SZ_256M) - 1) + return false; +#else if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M)) return false; - if (addr >= ALIGN(VMALLOC_END, SZ_256M)) + if (addr > ALIGN(VMALLOC_END, SZ_256M) - 1) return false; +#endif return true; } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 1da9dbba9217..890a71c5293e 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1115,8 +1115,10 @@ void hash__early_init_mmu_secondary(void) && cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); - if (IS_ENABLED(CONFIG_PPC_MEM_KEYS) && mmu_has_feature(MMU_FTR_PKEY)) +#ifdef CONFIG_PPC_MEM_KEYS + if (mmu_has_feature(MMU_FTR_PKEY)) mtspr(SPRN_UAMOR, default_uamor); +#endif } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 78fe34986594..93d20e1ed845 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2141,6 +2141,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); + } else if (period) { + /* Account for interrupt in case of invalid SIAR */ + if (perf_event_account_interrupt(event)) + power_pmu_stop(event, 0); } } @@ -2323,6 +2327,7 @@ int register_power_pmu(struct power_pmu *pmu) pmu->name); power_pmu.attr_groups = ppmu->attr_groups; + power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS); #ifdef MSR_HV /* diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index cdb7bfbd157e..6e7e820508df 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1128,6 +1128,15 @@ static struct bin_attribute *if_bin_attrs[] = { NULL, }; +static struct attribute *cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cpumask_attrs, +}; + static struct attribute *if_attrs[] = { &dev_attr_catalog_len.attr, &dev_attr_catalog_version.attr, @@ -1135,7 +1144,6 @@ static struct attribute *if_attrs[] = { &dev_attr_sockets.attr, &dev_attr_chipspersocket.attr, &dev_attr_coresperchip.attr, - &dev_attr_cpumask.attr, NULL, }; @@ -1151,6 +1159,7 @@ static const struct attribute_group *attr_groups[] = { &event_desc_group, &event_long_desc_group, &if_group, + &cpumask_attr_group, NULL, }; diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index a213a0aa5d25..8e53f2fc3fe0 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -13,9 +13,11 @@ #include <asm/ptrace.h> #include <asm/perf_regs.h> +u64 PERF_REG_EXTENDED_MASK; + #define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) -#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1)) +#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK)) static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_R0, gpr[0]), @@ -69,10 +71,36 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr), }; +/* Function to return the extended register values */ +static u64 get_ext_regs_value(int idx) +{ + switch (idx) { + case PERF_REG_POWERPC_MMCR0: + return mfspr(SPRN_MMCR0); + case PERF_REG_POWERPC_MMCR1: + return mfspr(SPRN_MMCR1); + case PERF_REG_POWERPC_MMCR2: + return mfspr(SPRN_MMCR2); +#ifdef CONFIG_PPC64 + case PERF_REG_POWERPC_MMCR3: + return mfspr(SPRN_MMCR3); + case PERF_REG_POWERPC_SIER2: + return mfspr(SPRN_SIER2); + case PERF_REG_POWERPC_SIER3: + return mfspr(SPRN_SIER3); +#endif + default: return 0; + } +} + u64 perf_reg_value(struct pt_regs *regs, int idx) { - if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX)) - return 0; + u64 perf_reg_extended_max = PERF_REG_POWERPC_MAX; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + perf_reg_extended_max = PERF_REG_MAX_ISA_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) + perf_reg_extended_max = PERF_REG_MAX_ISA_300; if (idx == PERF_REG_POWERPC_SIER && (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) || @@ -85,6 +113,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) IS_ENABLED(CONFIG_PPC32))) return 0; + if (idx >= PERF_REG_POWERPC_MAX && idx < perf_reg_extended_max) + return get_ext_regs_value(idx); + + /* + * If the idx is referring to value beyond the + * supported registers, return 0 with a warning + */ + if (WARN_ON_ONCE(idx >= perf_reg_extended_max)) + return 0; + return regs_get_register(regs, pt_regs_offset[idx]); } diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index f7cff7f36a1c..83148656b524 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -87,6 +87,8 @@ #define POWER10_MMCRA_IFM3 0x00000000C0000000UL #define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { { PM_RUN_CYC_ALT, PM_RUN_CYC }, @@ -397,6 +399,7 @@ static struct power_pmu power10_pmu = { .cache_events = &power10_cache_events, .attr_groups = power10_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power10_pmu(void) @@ -408,6 +411,9 @@ int init_power10_pmu(void) strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10")) return -ENODEV; + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31; + rc = register_power_pmu(&power10_pmu); if (rc) return rc; diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 05dae38b969a..2a57e93a79dc 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -90,6 +90,8 @@ enum { #define POWER9_MMCRA_IFM3 0x00000000C0000000UL #define POWER9_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Nasty Power9 specific hack */ #define PVR_POWER9_CUMULUS 0x00002000 @@ -434,6 +436,7 @@ static struct power_pmu power9_pmu = { .cache_events = &power9_cache_events, .attr_groups = power9_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power9_pmu(void) @@ -457,6 +460,9 @@ int init_power9_pmu(void) } } + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300; + rc = register_power_pmu(&power9_pmu); if (rc) return rc; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c9c25fb0783c..023a4f987bb2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2705,7 +2705,7 @@ void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) struct iommu_table *tbl = pe->table_group.tables[0]; int64_t rc; - if (pe->dma_setup_done) + if (!pe->dma_setup_done) return; rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index c6e0d8abf75e..7a974ed6b240 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -107,22 +107,28 @@ static int pseries_cpu_disable(void) */ static void pseries_cpu_die(unsigned int cpu) { - int tries; int cpu_status = 1; unsigned int pcpu = get_hard_smp_processor_id(cpu); + unsigned long timeout = jiffies + msecs_to_jiffies(120000); - for (tries = 0; tries < 25; tries++) { + while (true) { cpu_status = smp_query_cpu_stopped(pcpu); if (cpu_status == QCSS_STOPPED || cpu_status == QCSS_HARDWARE_ERROR) break; - cpu_relax(); + if (time_after(jiffies, timeout)) { + pr_warn("CPU %i (hwid %i) didn't die after 120 seconds\n", + cpu, pcpu); + timeout = jiffies + msecs_to_jiffies(120000); + } + + cond_resched(); } - if (cpu_status != 0) { - printk("Querying DEAD? cpu %i (%i) shows %i\n", - cpu, pcpu, cpu_status); + if (cpu_status == QCSS_HARDWARE_ERROR) { + pr_warn("CPU %i (hwid %i) reported error while dying\n", + cpu, pcpu); } /* Isolation and deallocation are definitely done by diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index f3736fcd98fc..13c86a292c6d 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -184,7 +184,6 @@ static void handle_system_shutdown(char event_modifier) case EPOW_SHUTDOWN_ON_UPS: pr_emerg("Loss of system power detected. System is running on" " UPS/battery. Check RTAS error log for details\n"); - orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7b5905529146..df18372861d8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -81,7 +81,7 @@ config RISCV select PCI_DOMAINS_GENERIC if PCI select PCI_MSI if PCI select RISCV_INTC - select RISCV_TIMER + select RISCV_TIMER if RISCV_SBI select SPARSEMEM_STATIC if 32BIT select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6c88148f1b9b..8a55f6156661 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -12,6 +12,7 @@ config SOC_SIFIVE config SOC_VIRT bool "QEMU Virt Machine" + select CLINT_TIMER if RISCV_M_MODE select POWER_RESET select POWER_RESET_SYSCON select POWER_RESET_SYSCON_POWEROFF @@ -24,6 +25,7 @@ config SOC_VIRT config SOC_KENDRYTE bool "Kendryte K210 SoC" depends on !MMU + select CLINT_TIMER if RISCV_M_MODE select SERIAL_SIFIVE if TTY select SERIAL_SIFIVE_CONSOLE if TTY select SIFIVE_PLIC diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig index f27596e9663e..e046a0babde4 100644 --- a/arch/riscv/configs/nommu_virt_defconfig +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -26,6 +26,7 @@ CONFIG_EXPERT=y CONFIG_SLOB=y # CONFIG_SLAB_MERGE_DEFAULT is not set # CONFIG_MMU is not set +CONFIG_SOC_VIRT=y CONFIG_MAXPHYSMEM_2GB=y CONFIG_SMP=y CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0" @@ -49,7 +50,6 @@ CONFIG_VIRTIO_BLK=y # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set # CONFIG_LDISC_AUTOLOAD is not set -# CONFIG_DEVMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y @@ -57,16 +57,13 @@ CONFIG_SERIAL_8250_NR_UARTS=1 CONFIG_SERIAL_8250_RUNTIME_UARTS=1 CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y -CONFIG_SIFIVE_PLIC=y -# CONFIG_VALIDATE_FS_PARSER is not set CONFIG_EXT2_FS=y # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 3a55f0e00d6c..2c2cda6cc1c5 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y +CONFIG_SOC_SIFIVE=y CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y @@ -62,6 +63,8 @@ CONFIG_HVC_RISCV_SBI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_SPI=y +CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y @@ -77,6 +80,8 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y CONFIG_RTC_CLASS=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h deleted file mode 100644 index a279b17a6aad..000000000000 --- a/arch/riscv/include/asm/clint.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_RISCV_CLINT_H -#define _ASM_RISCV_CLINT_H 1 - -#include <linux/io.h> -#include <linux/smp.h> - -#ifdef CONFIG_RISCV_M_MODE -extern u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void); - -static inline void clint_send_ipi_single(unsigned long hartid) -{ - writel(1, clint_ipi_base + hartid); -} - -static inline void clint_send_ipi_mask(const struct cpumask *mask) -{ - int cpu; - - for_each_cpu(cpu, mask) - clint_send_ipi_single(cpuid_to_hartid_map(cpu)); -} - -static inline void clint_clear_ipi(unsigned long hartid) -{ - writel(0, clint_ipi_base + hartid); -} -#else /* CONFIG_RISCV_M_MODE */ -#define clint_init_boot_cpu() do { } while (0) - -/* stubs to for code is only reachable under IS_ENABLED(CONFIG_RISCV_M_MODE): */ -void clint_send_ipi_single(unsigned long hartid); -void clint_send_ipi_mask(const struct cpumask *hartid_mask); -void clint_clear_ipi(unsigned long hartid); -#endif /* CONFIG_RISCV_M_MODE */ - -#endif /* _ASM_RISCV_CLINT_H */ diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index 6dfd2a1446d5..df1f7c4cd433 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -15,6 +15,11 @@ struct seq_file; extern unsigned long boot_cpu_hartid; +struct riscv_ipi_ops { + void (*ipi_inject)(const struct cpumask *target); + void (*ipi_clear)(void); +}; + #ifdef CONFIG_SMP /* * Mapping between linux logical cpu index and hartid. @@ -40,6 +45,12 @@ void arch_send_call_function_single_ipi(int cpu); int riscv_hartid_to_cpuid(int hartid); void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out); +/* Set custom IPI operations */ +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops); + +/* Clear IPI for current CPU */ +void riscv_clear_ipi(void); + /* Secondary hart entry */ asmlinkage void smp_callin(void); @@ -81,6 +92,14 @@ static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in, cpumask_set_cpu(boot_cpu_hartid, out); } +static inline void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ +} + +static inline void riscv_clear_ipi(void) +{ +} + #endif /* CONFIG_SMP */ #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP) diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index bad2a7c2cda5..a3fb85d505d4 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -7,41 +7,27 @@ #define _ASM_RISCV_TIMEX_H #include <asm/csr.h> -#include <asm/mmio.h> typedef unsigned long cycles_t; -extern u64 __iomem *riscv_time_val; -extern u64 __iomem *riscv_time_cmp; - -#ifdef CONFIG_64BIT -#define mmio_get_cycles() readq_relaxed(riscv_time_val) -#else -#define mmio_get_cycles() readl_relaxed(riscv_time_val) -#define mmio_get_cycles_hi() readl_relaxed(((u32 *)riscv_time_val) + 1) -#endif - static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIME); - return mmio_get_cycles(); + return csr_read(CSR_TIME); } #define get_cycles get_cycles +static inline u32 get_cycles_hi(void) +{ + return csr_read(CSR_TIMEH); +} +#define get_cycles_hi get_cycles_hi + #ifdef CONFIG_64BIT static inline u64 get_cycles64(void) { return get_cycles(); } #else /* CONFIG_64BIT */ -static inline u32 get_cycles_hi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIMEH); - return mmio_get_cycles_hi(); -} - static inline u64 get_cycles64(void) { u32 hi, lo; diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index a5287ab9f7f2..dc93710f0b2f 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -31,7 +31,7 @@ obj-y += cacheinfo.o obj-y += patch.o obj-$(CONFIG_MMU) += vdso.o vdso/ -obj-$(CONFIG_RISCV_M_MODE) += clint.o traps_misaligned.o +obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/riscv/kernel/clint.c b/arch/riscv/kernel/clint.c deleted file mode 100644 index 3647980d14c3..000000000000 --- a/arch/riscv/kernel/clint.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2019 Christoph Hellwig. - */ - -#include <linux/io.h> -#include <linux/of_address.h> -#include <linux/types.h> -#include <asm/clint.h> -#include <asm/csr.h> -#include <asm/timex.h> -#include <asm/smp.h> - -/* - * This is the layout used by the SiFive clint, which is also shared by the qemu - * virt platform, and the Kendryte KD210 at least. - */ -#define CLINT_IPI_OFF 0 -#define CLINT_TIME_CMP_OFF 0x4000 -#define CLINT_TIME_VAL_OFF 0xbff8 - -u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void) -{ - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "riscv,clint0"); - if (!np) { - panic("clint not found"); - return; - } - - base = of_iomap(np, 0); - if (!base) - panic("could not map CLINT"); - - clint_ipi_base = base + CLINT_IPI_OFF; - riscv_time_cmp = base + CLINT_TIME_CMP_OFF; - riscv_time_val = base + CLINT_TIME_VAL_OFF; - - clint_clear_ipi(boot_cpu_hartid); -} diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f383ef5672b2..226ccce0f9e0 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -547,6 +547,18 @@ static inline long sbi_get_firmware_version(void) return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); } +static void sbi_send_cpumask_ipi(const struct cpumask *target) +{ + struct cpumask hartid_mask; + + riscv_cpuid_to_hartid_mask(target, &hartid_mask); + + sbi_send_ipi(cpumask_bits(&hartid_mask)); +} + +static struct riscv_ipi_ops sbi_ipi_ops = { + .ipi_inject = sbi_send_cpumask_ipi +}; int __init sbi_init(void) { @@ -587,5 +599,7 @@ int __init sbi_init(void) __sbi_rfence = __sbi_rfence_v01; } + riscv_set_ipi_ops(&sbi_ipi_ops); + return 0; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f04373be54a6..2c6dd329312b 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -18,7 +18,6 @@ #include <linux/swiotlb.h> #include <linux/smp.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/setup.h> #include <asm/sections.h> @@ -79,7 +78,6 @@ void __init setup_arch(char **cmdline_p) #else unflatten_device_tree(); #endif - clint_init_boot_cpu(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 554b0fb47060..ea028d9e0d24 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -18,7 +18,6 @@ #include <linux/delay.h> #include <linux/irq_work.h> -#include <asm/clint.h> #include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> @@ -86,9 +85,25 @@ static void ipi_stop(void) wait_for_interrupt(); } +static struct riscv_ipi_ops *ipi_ops; + +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ + ipi_ops = ops; +} +EXPORT_SYMBOL_GPL(riscv_set_ipi_ops); + +void riscv_clear_ipi(void) +{ + if (ipi_ops && ipi_ops->ipi_clear) + ipi_ops->ipi_clear(); + + csr_clear(CSR_IP, IE_SIE); +} +EXPORT_SYMBOL_GPL(riscv_clear_ipi); + static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) { - struct cpumask hartid_mask; int cpu; smp_mb__before_atomic(); @@ -96,33 +111,22 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - riscv_cpuid_to_hartid_mask(mask, &hartid_mask); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(&hartid_mask)); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(mask); else - clint_send_ipi_mask(mask); + pr_warn("SMP: IPI inject method not available\n"); } static void send_ipi_single(int cpu, enum ipi_message_type op) { - int hartid = cpuid_to_hartid_map(cpu); - smp_mb__before_atomic(); set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(cpumask_of(hartid))); - else - clint_send_ipi_single(hartid); -} - -static inline void clear_ipi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - csr_clear(CSR_IP, IE_SIE); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(cpumask_of(cpu)); else - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + pr_warn("SMP: IPI inject method not available\n"); } #ifdef CONFIG_IRQ_WORK @@ -140,7 +144,7 @@ void handle_IPI(struct pt_regs *regs) irq_enter(); - clear_ipi(); + riscv_clear_ipi(); while (true) { unsigned long ops; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 356825a57551..96167d55ed98 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -24,7 +24,6 @@ #include <linux/of.h> #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/irq.h> #include <asm/mmu_context.h> @@ -147,8 +146,7 @@ asmlinkage __visible void smp_callin(void) struct mm_struct *mm = &init_mm; unsigned int curr_cpuid = smp_processor_id(); - if (!IS_ENABLED(CONFIG_RISCV_SBI)) - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + riscv_clear_ipi(); /* All kernel threads share the same mm context. */ mmgrab(mm); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 11d2f7d05f91..a76dd27fb2e8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1268,7 +1268,6 @@ static bool is_ri_cb_valid(struct runtime_instr_cb *cb) cb->pc == 1 && cb->qc == 0 && cb->reserved2 == 0 && - cb->key == PAGE_DEFAULT_KEY && cb->reserved3 == 0 && cb->reserved4 == 0 && cb->reserved5 == 0 && @@ -1330,7 +1329,11 @@ static int s390_runtime_instr_set(struct task_struct *target, kfree(data); return -EINVAL; } - + /* + * Override access key in any case, since user space should + * not be able to set it, nor should it care about it. + */ + ri_cb.key = PAGE_DEFAULT_KEY >> 4; preempt_disable(); if (!target->thread.ri_cb) target->thread.ri_cb = data; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 125c7f6e8715..1788a5454b6f 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -57,7 +57,7 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb) cb->k = 1; cb->ps = 1; cb->pc = 1; - cb->key = PAGE_DEFAULT_KEY; + cb->key = PAGE_DEFAULT_KEY >> 4; cb->v = 1; } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 3902c9f6f2d6..4b62d6b55024 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -672,6 +672,19 @@ int zpci_disable_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_disable_device); +void zpci_remove_device(struct zpci_dev *zdev) +{ + struct zpci_bus *zbus = zdev->zbus; + struct pci_dev *pdev; + + pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (pdev) { + if (pdev->is_virtfn) + return zpci_remove_virtfn(pdev, zdev->vfn); + pci_stop_and_remove_bus_device_locked(pdev); + } +} + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -716,13 +729,8 @@ void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); - if (zdev->zbus->bus) { - struct pci_dev *pdev; - - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); - if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); - } + if (zdev->zbus->bus) + zpci_remove_device(zdev); switch (zdev->state) { case ZPCI_FN_STATE_ONLINE: diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 642a99384688..5967f3014156 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -132,13 +132,14 @@ static int zpci_bus_link_virtfn(struct pci_dev *pdev, { int rc; - virtfn->physfn = pci_dev_get(pdev); rc = pci_iov_sysfs_link(pdev, virtfn, vfid); - if (rc) { - pci_dev_put(pdev); - virtfn->physfn = NULL; + if (rc) return rc; - } + + virtfn->is_virtfn = 1; + virtfn->multifunction = 0; + virtfn->physfn = pci_dev_get(pdev); + return 0; } @@ -151,9 +152,9 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ int rc = 0; - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; - WARN_ON(vfid < 0); + if (!zbus->multifunction) + return 0; + /* If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what @@ -165,11 +166,17 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, zdev = zbus->function[i]; if (zdev && zdev->is_physfn) { pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (!pdev) + continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); if (cand_devfn == virtfn->devfn) { rc = zpci_bus_link_virtfn(pdev, virtfn, vfid); + /* balance pci_get_slot() */ + pci_dev_put(pdev); break; } + /* balance pci_get_slot() */ + pci_dev_put(pdev); } } return rc; @@ -178,12 +185,23 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) { - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; return 0; } #endif +void pcibios_bus_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + /* + * With pdev->no_vf_scan the common PCI probing code does not + * perform PF/VF linking. + */ + if (zdev->vfn) + zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); + +} + static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) { struct pci_bus *bus; @@ -214,20 +232,10 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) } pdev = pci_scan_single_device(bus, zdev->devfn); - if (pdev) { - if (!zdev->is_physfn) { - rc = zpci_bus_setup_virtfn(zbus, pdev, zdev->vfn); - if (rc) - goto failed_with_pdev; - } + if (pdev) pci_bus_add_device(pdev); - } - return 0; -failed_with_pdev: - pci_stop_and_remove_bus_device(pdev); - pci_dev_put(pdev); - return rc; + return 0; } static void zpci_bus_add_devices(struct zpci_bus *zbus) diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index 89be3c354b7b..4972433df458 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -29,3 +29,16 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn]; } + +#ifdef CONFIG_PCI_IOV +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) +{ + + pci_lock_rescan_remove(); + /* Linux' vfid's start at 0 vfn at 1 */ + pci_iov_remove_virtfn(pdev->physfn, vfn - 1); + pci_unlock_rescan_remove(); +} +#else /* CONFIG_PCI_IOV */ +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {} +#endif /* CONFIG_PCI_IOV */ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index fdebd286f402..9a3a291cad43 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -92,6 +92,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 1); break; } + /* the configuration request may be stale */ + if (zdev->state != ZPCI_FN_STATE_STANDBY) + break; zdev->fh = ccdf->fh; zdev->state = ZPCI_FN_STATE_CONFIGURED; ret = zpci_enable_device(zdev); @@ -118,7 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) break; if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); ret = zpci_disable_device(zdev); if (ret) @@ -137,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) /* Give the driver a hint that the function is * already unusable. */ pdev->error_state = pci_channel_io_perm_failure; - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); } zdev->state = ZPCI_FN_STATE_STANDBY; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 39e592d0e0b4..e478e40fbe5a 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,12 +30,9 @@ #define STATIC static /* - * Use normal definitions of mem*() from string.c. There are already - * included header files which expect a definition of memset() and by - * the time we define memset macro, it is too late. + * Provide definitions of memzero and memmove as some of the decompressors will + * try to define their own functions if these are not defined as macros. */ -#undef memcpy -#undef memset #define memzero(s, n) memset((s), 0, (n)) #define memmove memmove diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 995f7b7ad512..a232da487cd2 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); int memcmp(const void *s1, const void *s2, size_t len); -/* - * Access builtin version by default. If one needs to use optimized version, - * do "undef memcpy" in .c file and link against right string.c - */ +/* Access builtin version by default. */ #define memcpy(d,s,l) __builtin_memcpy(d,s,l) #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 98e4d8886f11..ae9b0d4615b3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -374,12 +374,14 @@ For 32-bit we have the following conventions - kernel is built with * Fetch the per-CPU GSBASE value for this processor and put it in @reg. * We normally use %gs for accessing per-CPU data, but we are setting up * %gs here and obviously can not use %gs itself to access per-CPU data. + * + * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and + * may not restore the host's value until the CPU returns to userspace. + * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives + * while running KVM's run loop. */ .macro GET_PERCPU_BASE reg:req - ALTERNATIVE \ - "LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \ - "RDPID \reg", \ - X86_FEATURE_RDPID + LOAD_CPU_AND_NODE_SEG_LIMIT \reg andq $VDSO_CPUNODE_MASK, \reg movq __per_cpu_offset(, \reg, 8), \reg .endm diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index cb94ba86efd2..6a4ca27b2c9e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -390,6 +390,18 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(gt_requests, "event=0x03"), + INTEL_UNCORE_EVENT_DESC(gt_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(gt_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ia_requests, "event=0x04"), + INTEL_UNCORE_EVENT_DESC(ia_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(ia_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(io_requests, "event=0x05"), + INTEL_UNCORE_EVENT_DESC(io_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(io_requests.unit, "MiB"), + { /* end: all zeroes */ }, }; @@ -405,13 +417,35 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 #define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE +/* BW break down- legacy counters */ +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS 0x3 +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE 0x5040 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS 0x4 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE 0x5044 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS 0x5 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE 0x5048 + enum perf_snb_uncore_imc_freerunning_types { - SNB_PCI_UNCORE_IMC_DATA = 0, + SNB_PCI_UNCORE_IMC_DATA_READS = 0, + SNB_PCI_UNCORE_IMC_DATA_WRITES, + SNB_PCI_UNCORE_IMC_GT_REQUESTS, + SNB_PCI_UNCORE_IMC_IA_REQUESTS, + SNB_PCI_UNCORE_IMC_IO_REQUESTS, + SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, }; static struct freerunning_counters snb_uncore_imc_freerunning[] = { - [SNB_PCI_UNCORE_IMC_DATA] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IA_REQUESTS] = { SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IO_REQUESTS] = { SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, }; static struct attribute *snb_uncore_imc_formats_attr[] = { @@ -525,6 +559,18 @@ static int snb_uncore_imc_event_init(struct perf_event *event) base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; idx = UNCORE_PMC_IDX_FREERUNNING; break; + case SNB_UNCORE_PCI_IMC_GT_REQUESTS: + base = SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IA_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IO_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; default: return -EINVAL; } @@ -598,7 +644,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { static struct intel_uncore_type snb_uncore_imc = { .name = "imc", - .num_counters = 2, + .num_counters = 5, .num_boxes = 1, .num_freerunning_types = SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, .mmio_map_size = SNB_UNCORE_PCI_IMC_MAP_SIZE, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index b9c2667ac46c..bc9758ef292e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -81,11 +81,8 @@ extern unsigned long efi_fw_vendor, efi_config_table; kernel_fpu_end(); \ }) - #define arch_efi_call_virt(p, f, args...) p->f(args) -#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) - #else /* !CONFIG_X86_32 */ #define EFI_LOADER_SIGNATURE "EL64" @@ -125,9 +122,6 @@ struct efi_scratch { kernel_fpu_end(); \ }) -extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, - u32 type, u64 attribute); - #ifdef CONFIG_KASAN /* * CONFIG_KASAN may redefine memset to __memset. __memset function is present @@ -143,17 +137,13 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; -extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern void __init efi_print_memmap(void); -extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern int __init efi_alloc_page_tables(void); extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); -extern void __init old_map_region(efi_memory_desc_t *md); -extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_update_mappings(void); extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5ab3af7275d8..5303dbc5c9bc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1596,7 +1596,8 @@ asmlinkage void kvm_spurious_fault(void); _ASM_EXTABLE(666b, 667b) #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4e03841f053d..a5d0207e7189 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1916,7 +1916,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 599d73206299..33945283fe07 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,7 +975,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + X86_CR4_SMEP; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -10751,9 +10751,11 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { struct x86_exception fault; + u32 access = error_code & + (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, error_code, &fault) != UNMAPPED_GVA) { + vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9f9aad42ccff..89395a5049bb 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -26,6 +26,7 @@ #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f6ea8f1a9d57..d37ebe6e70d7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -49,7 +49,6 @@ #include <asm/efi.h> #include <asm/e820/api.h> #include <asm/time.h> -#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> #include <asm/uv/uv.h> @@ -496,74 +495,6 @@ void __init efi_init(void) efi_print_memmap(); } -#if defined(CONFIG_X86_32) - -void __init efi_set_executable(efi_memory_desc_t *md, bool executable) -{ - u64 addr, npages; - - addr = md->virt_addr; - npages = md->num_pages; - - memrange_efi_to_native(&addr, &npages); - - if (executable) - set_memory_x(addr, npages); - else - set_memory_nx(addr, npages); -} - -void __init runtime_code_page_mkexec(void) -{ - efi_memory_desc_t *md; - - /* Make EFI runtime service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type != EFI_RUNTIME_SERVICES_CODE) - continue; - - efi_set_executable(md, true); - } -} - -void __init efi_memory_uc(u64 addr, unsigned long size) -{ - unsigned long page_shift = 1UL << EFI_PAGE_SHIFT; - u64 npages; - - npages = round_up(size, page_shift) / page_shift; - memrange_efi_to_native(&addr, &npages); - set_memory_uc(addr, npages); -} - -void __init old_map_region(efi_memory_desc_t *md) -{ - u64 start_pfn, end_pfn, end; - unsigned long size; - void *va; - - start_pfn = PFN_DOWN(md->phys_addr); - size = md->num_pages << PAGE_SHIFT; - end = md->phys_addr + size; - end_pfn = PFN_UP(end); - - if (pfn_range_is_mapped(start_pfn, end_pfn)) { - va = __va(md->phys_addr); - - if (!(md->attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)va, size); - } else - va = efi_ioremap(md->phys_addr, size, - md->type, md->attribute); - - md->virt_addr = (u64) (unsigned long) va; - if (!va) - pr_err("ioremap of 0x%llX failed!\n", - (unsigned long long)md->phys_addr); -} - -#endif - /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 826ead67753d..e06a199423c0 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -29,9 +29,35 @@ #include <asm/io.h> #include <asm/desc.h> #include <asm/page.h> +#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/efi.h> +void __init efi_map_region(efi_memory_desc_t *md) +{ + u64 start_pfn, end_pfn, end; + unsigned long size; + void *va; + + start_pfn = PFN_DOWN(md->phys_addr); + size = md->num_pages << PAGE_SHIFT; + end = md->phys_addr + size; + end_pfn = PFN_UP(end); + + if (pfn_range_is_mapped(start_pfn, end_pfn)) { + va = __va(md->phys_addr); + + if (!(md->attribute & EFI_MEMORY_WB)) + set_memory_uc((unsigned long)va, md->num_pages); + } else { + va = ioremap_cache(md->phys_addr, size); + } + + md->virt_addr = (unsigned long)va; + if (!va) + pr_err("ioremap of 0x%llX failed!\n", md->phys_addr); +} + /* * To make EFI call EFI runtime service in physical addressing mode we need * prolog/epilog before/after the invocation to claim the EFI runtime service @@ -58,11 +84,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 0; } -void __init efi_map_region(efi_memory_desc_t *md) -{ - old_map_region(md); -} - void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} @@ -107,6 +128,15 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, void __init efi_runtime_update_mappings(void) { - if (__supported_pte_mask & _PAGE_NX) - runtime_code_page_mkexec(); + if (__supported_pte_mask & _PAGE_NX) { + efi_memory_desc_t *md; + + /* Make EFI runtime service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type != EFI_RUNTIME_SERVICES_CODE) + continue; + + set_memory_x(md->virt_addr, md->num_pages); + } + } } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 413583f904a6..6af4da1149ba 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -259,6 +259,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; rodata = __pa(__start_rodata); pfn = rodata >> PAGE_SHIFT; + + pf = _PAGE_NX | _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { pr_err("Failed to map kernel rodata 1:1\n"); return 1; |