diff options
Diffstat (limited to 'arch/x86')
41 files changed, 663 insertions, 175 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 340e5468980e..71019b3b54ea 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -89,7 +89,7 @@ config X86 select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN select ARCH_HAS_EARLY_DEBUG if KGDB select ARCH_HAS_ELF_RANDOMIZE - select ARCH_HAS_EXECMEM_ROX if X86_64 + select ARCH_HAS_EXECMEM_ROX if X86_64 && STRICT_MODULE_RWX select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 466283326630..c2fb729c270e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2826,7 +2826,7 @@ static void intel_pmu_read_event(struct perf_event *event) * If the PEBS counters snapshotting is enabled, * the topdown event is available in PEBS records. */ - if (is_topdown_event(event) && !is_pebs_counter_event_group(event)) + if (is_topdown_count(event) && !is_pebs_counter_event_group(event)) static_call(intel_pmu_update_topdown_event)(event, NULL); else intel_pmu_drain_pebs_buffer(); @@ -2900,6 +2900,7 @@ static void intel_pmu_config_acr(int idx, u64 mask, u32 reload) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int msr_b, msr_c; + int msr_offset; if (!mask && !cpuc->acr_cfg_b[idx]) return; @@ -2907,19 +2908,20 @@ static void intel_pmu_config_acr(int idx, u64 mask, u32 reload) if (idx < INTEL_PMC_IDX_FIXED) { msr_b = MSR_IA32_PMC_V6_GP0_CFG_B; msr_c = MSR_IA32_PMC_V6_GP0_CFG_C; + msr_offset = x86_pmu.addr_offset(idx, false); } else { msr_b = MSR_IA32_PMC_V6_FX0_CFG_B; msr_c = MSR_IA32_PMC_V6_FX0_CFG_C; - idx -= INTEL_PMC_IDX_FIXED; + msr_offset = x86_pmu.addr_offset(idx - INTEL_PMC_IDX_FIXED, false); } if (cpuc->acr_cfg_b[idx] != mask) { - wrmsrl(msr_b + x86_pmu.addr_offset(idx, false), mask); + wrmsrl(msr_b + msr_offset, mask); cpuc->acr_cfg_b[idx] = mask; } /* Only need to update the reload value when there is a valid config value. */ if (mask && cpuc->acr_cfg_c[idx] != reload) { - wrmsrl(msr_c + x86_pmu.addr_offset(idx, false), reload); + wrmsrl(msr_c + msr_offset, reload); cpuc->acr_cfg_c[idx] = reload; } } diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e988bac0a4a1..3c2de4ce3b10 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,12 +5,20 @@ #include <asm-generic/module.h> #include <asm/orc_types.h> +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + struct mod_arch_specific { #ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; #endif + struct its_array its_pages; }; #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 774430c3abff..97954c936c54 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1561,7 +1561,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte) return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); } -static inline int pte_swp_exclusive(pte_t pte) +static inline bool pte_swp_exclusive(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE; } diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index 2f3820342598..d8525e6ef50a 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -80,6 +80,7 @@ #define TDVMCALL_STATUS_RETRY 0x0000000000000001ULL #define TDVMCALL_STATUS_INVALID_OPERAND 0x8000000000000000ULL #define TDVMCALL_STATUS_ALIGN_ERROR 0x8000000000000002ULL +#define TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED 0x8000000000000003ULL /* * Bitmasks of exposed registers (with VMM). diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index e770c4fc47f4..8727c7e21dd1 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -24,4 +24,26 @@ int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); +/* + * To prevent immediate repeat of single step trap on return from SIGTRAP + * handler if the trap flag (TF) is set without an external debugger attached, + * clear the software event flag in the augmented SS, ensuring no single-step + * trap is pending upon ERETU completion. + * + * Note, this function should be called in sigreturn() before the original + * state is restored to make sure the TF is read from the entry frame. + */ +static __always_inline void prevent_single_step_upon_eretu(struct pt_regs *regs) +{ + /* + * If the trap flag (TF) is set, i.e., the sigreturn() SYSCALL instruction + * is being single-stepped, do not clear the software event flag in the + * augmented SS, thus a debugger won't skip over the following instruction. + */ +#ifdef CONFIG_X86_FRED + if (!(regs->flags & X86_EFLAGS_TF)) + regs->fred_ss.swevent = 0; +#endif +} + #endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index 8b19294600c4..7ddef3a69866 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -106,7 +106,7 @@ void tdx_init(void); typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args); -static inline u64 sc_retry(sc_func_t func, u64 fn, +static __always_inline u64 sc_retry(sc_func_t func, u64 fn, struct tdx_module_args *args) { int retry = RDRAND_RETRY_LOOPS; diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 0454d5e60e5d..721b408d9a67 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -44,16 +44,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_after_save, TP_ARGS(fpu) ); -DEFINE_EVENT(x86_fpu, x86_fpu_before_restore, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - -DEFINE_EVENT(x86_fpu, x86_fpu_after_restore, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) @@ -64,11 +54,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated, TP_ARGS(fpu) ); -DEFINE_EVENT(x86_fpu, x86_fpu_init_state, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - DEFINE_EVENT(x86_fpu, x86_fpu_dropped, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 99a783fd4691..0d2a6d953be9 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -3,7 +3,7 @@ # Makefile for the linux kernel. # -extra-y += vmlinux.lds +always-$(KBUILD_BUILTIN) += vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ecfe7b497cad..ea1d984166cd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -116,6 +116,24 @@ static struct module *its_mod; #endif static void *its_page; static unsigned int its_offset; +struct its_array its_pages; + +static void *__its_alloc(struct its_array *pages) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + if (!page) + return NULL; + + void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + pages->pages = tmp; + pages->pages[pages->num++] = page; + + return no_free_ptr(page); +} /* Initialize a thunk with the "jmp *reg; int3" instructions. */ static void *its_init_thunk(void *thunk, int reg) @@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg) return thunk + offset; } +static void its_pages_protect(struct its_array *pages) +{ + for (int i = 0; i < pages->num; i++) { + void *page = pages->pages[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +static void its_fini_core(void) +{ + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + its_pages_protect(&its_pages); + kfree(its_pages.pages); +} + #ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { @@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; - execmem_restore_rox(page, PAGE_SIZE); - } + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + its_pages_protect(&mod->arch.its_pages); } void its_free_mod(struct module *mod) @@ -184,37 +215,33 @@ void its_free_mod(struct module *mod) if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) return; - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_free(page); } - kfree(mod->its_page_array); + kfree(mod->arch.its_pages.pages); } #endif /* CONFIG_MODULES */ static void *its_alloc(void) { - void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); - - if (!page) - return NULL; + struct its_array *pages = &its_pages; + void *page; #ifdef CONFIG_MODULES - if (its_mod) { - void *tmp = krealloc(its_mod->its_page_array, - (its_mod->its_num_pages+1) * sizeof(void *), - GFP_KERNEL); - if (!tmp) - return NULL; + if (its_mod) + pages = &its_mod->arch.its_pages; +#endif - its_mod->its_page_array = tmp; - its_mod->its_page_array[its_mod->its_num_pages++] = page; + page = __its_alloc(pages); + if (!page) + return NULL; - execmem_make_temp_rw(page, PAGE_SIZE); - } -#endif /* CONFIG_MODULES */ + execmem_make_temp_rw(page, PAGE_SIZE); + if (pages == &its_pages) + set_memory_x((unsigned long)page, 1); - return no_free_ptr(page); + return page; } static void *its_allocate_thunk(int reg) @@ -268,7 +295,9 @@ u8 *its_static_thunk(int reg) return thunk; } -#endif +#else +static inline void its_fini_core(void) {} +#endif /* CONFIG_MITIGATION_ITS */ /* * Nomenclature for variable names to simplify and clarify this code and ease @@ -2338,6 +2367,8 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); + its_fini_core(); + /* * Adjust all CALL instructions to point to func()-10, including * those in .altinstr_replacement. @@ -3107,6 +3138,6 @@ void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, c */ void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate) { - __smp_text_poke_batch_add(addr, opcode, len, emulate); + smp_text_poke_batch_add(addr, opcode, len, emulate); smp_text_poke_batch_finish(); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 93da466dfe2c..b2ad8d13211a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -31,7 +31,7 @@ #include "cpu.h" -u16 invlpgb_count_max __ro_after_init; +u16 invlpgb_count_max __ro_after_init = 1; static inline int rdmsrq_amd_safe(unsigned msr, u64 *p) { diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 7109cbfcad4f..187d527ef73b 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) struct rdt_hw_mon_domain *hw_dom; struct rdt_domain_hdr *hdr; struct rdt_mon_domain *d; + struct cacheinfo *ci; int err; lockdep_assert_held(&domain_list_lock); @@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) d = &hw_dom->d_resctrl; d->hdr.id = id; d->hdr.type = RESCTRL_MON_DOMAIN; - d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!d->ci) { + ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + if (!ci) { pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name); mon_domain_free(hw_dom); return; } + d->ci_id = ci->id; cpumask_set_cpu(cpu, &d->hdr.cpu_mask); arch_mon_domain_online(r, d); diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 6290dd120f5e..ff40f09ad911 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -33,8 +33,9 @@ void io_bitmap_share(struct task_struct *tsk) set_tsk_thread_flag(tsk, TIF_IO_BITMAP); } -static void task_update_io_bitmap(struct task_struct *tsk) +static void task_update_io_bitmap(void) { + struct task_struct *tsk = current; struct thread_struct *t = &tsk->thread; if (t->iopl_emul == 3 || t->io_bitmap) { @@ -54,7 +55,12 @@ void io_bitmap_exit(struct task_struct *tsk) struct io_bitmap *iobm = tsk->thread.io_bitmap; tsk->thread.io_bitmap = NULL; - task_update_io_bitmap(tsk); + /* + * Don't touch the TSS when invoked on a failed fork(). TSS + * reflects the state of @current and not the state of @tsk. + */ + if (tsk == current) + task_update_io_bitmap(); if (iobm && refcount_dec_and_test(&iobm->refcnt)) kfree(iobm); } @@ -192,8 +198,7 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) } t->iopl_emul = level; - task_update_io_bitmap(current); - + task_update_io_bitmap(); return 0; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c1d2dac72b9c..704883c21f3a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -176,6 +176,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame->ret_addr = (unsigned long) ret_from_fork_asm; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; + clear_tsk_thread_flag(p, TIF_IO_BITMAP); p->thread.iopl_warn = 0; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); @@ -464,6 +465,11 @@ void native_tss_update_io_bitmap(void) } else { struct io_bitmap *iobm = t->io_bitmap; + if (WARN_ON_ONCE(!iobm)) { + clear_thread_flag(TIF_IO_BITMAP); + native_tss_invalidate_io_bitmap(); + } + /* * Only copy bitmap data when the sequence number differs. The * update time is accounted to the incoming task. diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index 98123ff10506..42bbc42bd350 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -152,6 +152,8 @@ SYSCALL32_DEFINE0(sigreturn) struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); sigset_t set; + prevent_single_step_upon_eretu(regs); + if (!access_ok(frame, sizeof(*frame))) goto badframe; if (__get_user(set.sig[0], &frame->sc.oldmask) @@ -175,6 +177,8 @@ SYSCALL32_DEFINE0(rt_sigreturn) struct rt_sigframe_ia32 __user *frame; sigset_t set; + prevent_single_step_upon_eretu(regs); + frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4); if (!access_ok(frame, sizeof(*frame))) diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index ee9453891901..d483b585c6c6 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -250,6 +250,8 @@ SYSCALL_DEFINE0(rt_sigreturn) sigset_t set; unsigned long uc_flags; + prevent_single_step_upon_eretu(regs); + frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); if (!access_ok(frame, sizeof(*frame))) goto badframe; @@ -366,6 +368,8 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) sigset_t set; unsigned long uc_flags; + prevent_single_step_upon_eretu(regs); + frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); if (!access_ok(frame, sizeof(*frame))) diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 18266cc3d98c..b014e6d229f9 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -299,3 +299,27 @@ struct smp_ops smp_ops = { .send_call_func_single_ipi = native_send_call_func_single_ipi, }; EXPORT_SYMBOL_GPL(smp_ops); + +int arch_cpu_rescan_dead_smt_siblings(void) +{ + enum cpuhp_smt_control old = cpu_smt_control; + int ret; + + /* + * If SMT has been disabled and SMT siblings are in HLT, bring them back + * online and offline them again so that they end up in MWAIT proper. + * + * Called with hotplug enabled. + */ + if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED) + return 0; + + ret = cpuhp_smt_enable(); + if (ret) + return ret; + + ret = cpuhp_smt_disable(old); + + return ret; +} +EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fc78c2325fd2..58ede3fa6a75 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1244,6 +1244,10 @@ void play_dead_common(void) local_irq_disable(); } +/* + * We need to flush the caches before going to sleep, lest we have + * dirty data in our caches when we come back up. + */ void __noreturn mwait_play_dead(unsigned int eax_hint) { struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead); @@ -1290,50 +1294,6 @@ void __noreturn mwait_play_dead(unsigned int eax_hint) } /* - * We need to flush the caches before going to sleep, lest we have - * dirty data in our caches when we come back up. - */ -static inline void mwait_play_dead_cpuid_hint(void) -{ - unsigned int eax, ebx, ecx, edx; - unsigned int highest_cstate = 0; - unsigned int highest_subcstate = 0; - int i; - - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - return; - if (!this_cpu_has(X86_FEATURE_MWAIT)) - return; - if (!this_cpu_has(X86_FEATURE_CLFLUSH)) - return; - - eax = CPUID_LEAF_MWAIT; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - - /* - * eax will be 0 if EDX enumeration is not valid. - * Initialized below to cstate, sub_cstate value when EDX is valid. - */ - if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) { - eax = 0; - } else { - edx >>= MWAIT_SUBSTATE_SIZE; - for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) { - if (edx & MWAIT_SUBSTATE_MASK) { - highest_cstate = i; - highest_subcstate = edx & MWAIT_SUBSTATE_MASK; - } - } - eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) | - (highest_subcstate - 1); - } - - mwait_play_dead(eax); -} - -/* * Kick all "offline" CPUs out of mwait on kexec(). See comment in * mwait_play_dead(). */ @@ -1383,9 +1343,9 @@ void native_play_dead(void) play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); - mwait_play_dead_cpuid_hint(); - if (cpuidle_play_dead()) - hlt_play_dead(); + /* Below returns only on error. */ + cpuidle_play_dead(); + hlt_play_dead(); } #else /* ... !CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index cbc84c6abc2e..4e06e2e89a8f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4896,12 +4896,16 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, { u64 error_code = PFERR_GUEST_FINAL_MASK; u8 level = PG_LEVEL_4K; + u64 direct_bits; u64 end; int r; if (!vcpu->kvm->arch.pre_fault_allowed) return -EOPNOTSUPP; + if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa))) + return -EINVAL; + /* * reload is efficient when called repeatedly, so we can do it on * every iteration. @@ -4910,15 +4914,18 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, if (r) return r; + direct_bits = 0; if (kvm_arch_has_private_mem(vcpu->kvm) && kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa))) error_code |= PFERR_PRIVATE_ACCESS; + else + direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm)); /* * Shadow paging uses GVA for kvm page fault, so restrict to * two-dimensional paging. */ - r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level); + r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level); if (r < 0) return r; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 5a69b657dae9..459c3b791fd4 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2871,6 +2871,33 @@ void __init sev_set_cpu_caps(void) } } +static bool is_sev_snp_initialized(void) +{ + struct sev_user_data_snp_status *status; + struct sev_data_snp_addr buf; + bool initialized = false; + int ret, error = 0; + + status = snp_alloc_firmware_page(GFP_KERNEL | __GFP_ZERO); + if (!status) + return false; + + buf.address = __psp_pa(status); + ret = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &error); + if (ret) { + pr_err("SEV: SNP_PLATFORM_STATUS failed ret=%d, fw_error=%d (%#x)\n", + ret, error, error); + goto out; + } + + initialized = !!status->state; + +out: + snp_free_firmware_page(status); + + return initialized; +} + void __init sev_hardware_setup(void) { unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count; @@ -2975,6 +3002,14 @@ void __init sev_hardware_setup(void) sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP); out: + if (sev_enabled) { + init_args.probe = true; + if (sev_platform_init(&init_args)) + sev_supported = sev_es_supported = sev_snp_supported = false; + else if (sev_snp_supported) + sev_snp_supported = is_sev_snp_initialized(); + } + if (boot_cpu_has(X86_FEATURE_SEV)) pr_info("SEV %s (ASIDs %u - %u)\n", sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : @@ -3001,15 +3036,6 @@ out: sev_supported_vmsa_features = 0; if (sev_es_debug_swap_enabled) sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP; - - if (!sev_enabled) - return; - - /* - * Do both SNP and SEV initialization at KVM module load. - */ - init_args.probe = true; - sev_platform_init(&init_args); } void sev_hardware_unsetup(void) diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index b952bc673271..1ad20c273f3b 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -1212,11 +1212,13 @@ static int tdx_map_gpa(struct kvm_vcpu *vcpu) /* * Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires * userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE - * bit set. If not, the error code is not defined in GHCI for TDX, use - * TDVMCALL_STATUS_INVALID_OPERAND for this case. + * bit set. This is a base call so it should always be supported, but + * KVM has no way to ensure that userspace implements the GHCI correctly. + * So if KVM_HC_MAP_GPA_RANGE does not cause a VMEXIT, return an error + * to the guest. */ if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) { - ret = TDVMCALL_STATUS_INVALID_OPERAND; + ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED; goto error; } @@ -1449,20 +1451,85 @@ error: return 1; } +static int tdx_complete_get_td_vm_call_info(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + + tdvmcall_set_return_code(vcpu, vcpu->run->tdx.get_tdvmcall_info.ret); + + /* + * For now, there is no TDVMCALL beyond GHCI base API supported by KVM + * directly without the support from userspace, just set the value + * returned from userspace. + */ + tdx->vp_enter_args.r11 = vcpu->run->tdx.get_tdvmcall_info.r11; + tdx->vp_enter_args.r12 = vcpu->run->tdx.get_tdvmcall_info.r12; + tdx->vp_enter_args.r13 = vcpu->run->tdx.get_tdvmcall_info.r13; + tdx->vp_enter_args.r14 = vcpu->run->tdx.get_tdvmcall_info.r14; + + return 1; +} + static int tdx_get_td_vm_call_info(struct kvm_vcpu *vcpu) { struct vcpu_tdx *tdx = to_tdx(vcpu); - if (tdx->vp_enter_args.r12) - tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); - else { + switch (tdx->vp_enter_args.r12) { + case 0: tdx->vp_enter_args.r11 = 0; + tdx->vp_enter_args.r12 = 0; tdx->vp_enter_args.r13 = 0; tdx->vp_enter_args.r14 = 0; + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS); + return 1; + case 1: + vcpu->run->tdx.get_tdvmcall_info.leaf = tdx->vp_enter_args.r12; + vcpu->run->exit_reason = KVM_EXIT_TDX; + vcpu->run->tdx.flags = 0; + vcpu->run->tdx.nr = TDVMCALL_GET_TD_VM_CALL_INFO; + vcpu->run->tdx.get_tdvmcall_info.ret = TDVMCALL_STATUS_SUCCESS; + vcpu->run->tdx.get_tdvmcall_info.r11 = 0; + vcpu->run->tdx.get_tdvmcall_info.r12 = 0; + vcpu->run->tdx.get_tdvmcall_info.r13 = 0; + vcpu->run->tdx.get_tdvmcall_info.r14 = 0; + vcpu->arch.complete_userspace_io = tdx_complete_get_td_vm_call_info; + return 0; + default: + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + return 1; } +} + +static int tdx_complete_simple(struct kvm_vcpu *vcpu) +{ + tdvmcall_set_return_code(vcpu, vcpu->run->tdx.unknown.ret); return 1; } +static int tdx_get_quote(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + u64 gpa = tdx->vp_enter_args.r12; + u64 size = tdx->vp_enter_args.r13; + + /* The gpa of buffer must have shared bit set. */ + if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) { + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_TDX; + vcpu->run->tdx.flags = 0; + vcpu->run->tdx.nr = TDVMCALL_GET_QUOTE; + vcpu->run->tdx.get_quote.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED; + vcpu->run->tdx.get_quote.gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm)); + vcpu->run->tdx.get_quote.size = size; + + vcpu->arch.complete_userspace_io = tdx_complete_simple; + + return 0; +} + static int handle_tdvmcall(struct kvm_vcpu *vcpu) { switch (tdvmcall_leaf(vcpu)) { @@ -1472,11 +1539,13 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu) return tdx_report_fatal_error(vcpu); case TDVMCALL_GET_TD_VM_CALL_INFO: return tdx_get_td_vm_call_info(vcpu); + case TDVMCALL_GET_QUOTE: + return tdx_get_quote(vcpu); default: break; } - tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED); return 1; } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 38b33cdd4232..9b029bb29a16 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1571,7 +1571,8 @@ out: static void cancel_evtchn_poll(struct timer_list *t) { - struct kvm_vcpu *vcpu = from_timer(vcpu, t, arch.xen.poll_timer); + struct kvm_vcpu *vcpu = timer_container_of(vcpu, t, + arch.xen.poll_timer); kvm_make_request(KVM_REQ_UNBLOCK, vcpu); kvm_vcpu_kick(vcpu); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 607d6a2e66e2..8a34fff6ab2b 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -30,7 +30,6 @@ #include <linux/initrd.h> #include <linux/cpumask.h> #include <linux/gfp.h> -#include <linux/execmem.h> #include <asm/asm.h> #include <asm/bios_ebda.h> @@ -749,8 +748,6 @@ void mark_rodata_ro(void) pr_info("Write protecting kernel text and read-only data: %luk\n", size >> 10); - execmem_cache_make_ro(); - kernel_set_to_readonly = 1; #ifdef CONFIG_CPA_DEBUG diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ee66fae9ebcc..fdb6cab524f0 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -34,7 +34,6 @@ #include <linux/gfp.h> #include <linux/kcore.h> #include <linux/bootmem_info.h> -#include <linux/execmem.h> #include <asm/processor.h> #include <asm/bios_ebda.h> @@ -1392,8 +1391,6 @@ void mark_rodata_ro(void) (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); - execmem_cache_make_ro(); - kernel_set_to_readonly = 1; /* diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 46edc11726b7..8834c76f91c9 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1257,6 +1257,9 @@ static int collapse_pmd_page(pmd_t *pmd, unsigned long addr, pgprot_t pgprot; int i = 0; + if (!cpu_feature_enabled(X86_FEATURE_PSE)) + return 0; + addr &= PMD_MASK; pte = pte_offset_kernel(pmd, addr); first = *pte; diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 190299834011..c0c40b67524e 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -98,6 +98,11 @@ void __init pti_check_boottime_disable(void) return; setup_force_cpu_cap(X86_FEATURE_PTI); + + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) { + pr_debug("PTI enabled, disabling INVLPGB\n"); + setup_clear_cpu_cap(X86_FEATURE_INVLPGB); + } } static int __init pti_parse_cmdline(char *arg) diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 4933fb337983..c1efd5b0d198 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -8,13 +8,13 @@ obj-$(CONFIG_PCI_OLPC) += olpc.o obj-$(CONFIG_PCI_XEN) += xen.o obj-y += fixup.o -obj-$(CONFIG_X86_INTEL_CE) += ce4100.o obj-$(CONFIG_ACPI) += acpi.o obj-y += legacy.o irq.o -obj-$(CONFIG_X86_NUMACHIP) += numachip.o +obj-$(CONFIG_X86_INTEL_CE) += ce4100.o +obj-$(CONFIG_X86_INTEL_MID) += intel_mid.o -obj-$(CONFIG_X86_INTEL_MID) += intel_mid_pci.o +obj-$(CONFIG_X86_NUMACHIP) += numachip.o obj-y += common.o early.o obj-y += bus_numa.o diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid.c index b433b1753016..b433b1753016 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid.c diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c index a7c23f2a58c9..a2294c1649f6 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -192,7 +192,8 @@ out: int arch_resume_nosmt(void) { - int ret = 0; + int ret; + /* * We reached this while coming out of hibernation. This means * that SMT siblings are sleeping in hlt, as mwait is not safe @@ -206,18 +207,10 @@ int arch_resume_nosmt(void) * Called with hotplug disabled. */ cpu_hotplug_enable(); - if (cpu_smt_control == CPU_SMT_DISABLED || - cpu_smt_control == CPU_SMT_FORCE_DISABLED) { - enum cpuhp_smt_control old = cpu_smt_control; - - ret = cpuhp_smt_enable(); - if (ret) - goto out; - ret = cpuhp_smt_disable(old); - if (ret) - goto out; - } -out: + + ret = arch_cpu_rescan_dead_smt_siblings(); + cpu_hotplug_disable(); + return ret; } diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index b07824500363..ddc144657efa 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -20,6 +20,9 @@ */ extern __wsum csum_partial(const void *buff, int len, __wsum sum); +/* Do not call this directly. Declared for export type visibility. */ +extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len); + /** * csum_fold - Fold and invert a 32bit checksum. * sum: 32bit unfolded sum diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 478710384b34..e222d2ae28fd 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -21,10 +21,10 @@ #include <asm/user.h> -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static __always_inline void rep_nop(void) +/* PAUSE is a good thing to insert into busy-wait loops. */ +static __always_inline void native_pause(void) { - __asm__ __volatile__("rep;nop": : :"memory"); + __asm__ __volatile__("pause": : :"memory"); } static __always_inline void cpu_relax(void) @@ -33,7 +33,7 @@ static __always_inline void cpu_relax(void) time_travel_mode == TT_MODE_EXTERNAL) time_travel_ndelay(1); else - rep_nop(); + native_pause(); } #define task_pt_regs(t) (&(t)->thread.regs) diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c index 37decaa74761..a21403df6663 100644 --- a/arch/x86/um/os-Linux/mcontext.c +++ b/arch/x86/um/os-Linux/mcontext.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 -#include <sys/ucontext.h> #define __FRAME_OFFSETS +#include <linux/errno.h> +#include <linux/string.h> +#include <sys/ucontext.h> #include <asm/ptrace.h> +#include <asm/sigcontext.h> #include <sysdep/ptrace.h> #include <sysdep/mcontext.h> #include <arch.h> @@ -18,6 +21,10 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) COPY2(UESP, ESP); /* sic */ COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX); COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS); +#undef COPY2 +#undef COPY +#undef COPY_SEG +#undef COPY_SEG_CPL3 #else #define COPY2(X,Y) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##Y] #define COPY(X) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##X] @@ -29,6 +36,8 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) COPY2(EFLAGS, EFL); COPY2(CS, CSGSFS); regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48; +#undef COPY2 +#undef COPY #endif } @@ -42,3 +51,210 @@ void mc_set_rip(void *_mc, void *target) mc->gregs[REG_RIP] = (unsigned long)target; #endif } + +/* Same thing, but the copy macros are turned around. */ +void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, int single_stepping) +{ +#ifdef __i386__ +#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X] +#define COPY(X) mc->gregs[REG_##X] = regs->gp[X] +#define COPY_SEG(X) mc->gregs[REG_##X] = regs->gp[X] & 0xffff; +#define COPY_SEG_CPL3(X) mc->gregs[REG_##X] = (regs->gp[X] & 0xffff) | 3; + COPY_SEG(GS); COPY_SEG(FS); COPY_SEG(ES); COPY_SEG(DS); + COPY(EDI); COPY(ESI); COPY(EBP); + COPY2(UESP, ESP); /* sic */ + COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX); + COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS); +#else +#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X/sizeof(unsigned long)] +#define COPY(X) mc->gregs[REG_##X] = regs->gp[X/sizeof(unsigned long)] + COPY(R8); COPY(R9); COPY(R10); COPY(R11); + COPY(R12); COPY(R13); COPY(R14); COPY(R15); + COPY(RDI); COPY(RSI); COPY(RBP); COPY(RBX); + COPY(RDX); COPY(RAX); COPY(RCX); COPY(RSP); + COPY(RIP); + COPY2(EFLAGS, EFL); + mc->gregs[REG_CSGSFS] = mc->gregs[REG_CSGSFS] & 0xffffffffffffl; + mc->gregs[REG_CSGSFS] |= (regs->gp[SS / sizeof(unsigned long)] & 0xffff) << 48; +#endif + + if (single_stepping) + mc->gregs[REG_EFL] |= X86_EFLAGS_TF; + else + mc->gregs[REG_EFL] &= ~X86_EFLAGS_TF; +} + +#ifdef CONFIG_X86_32 +struct _xstate_64 { + struct _fpstate_64 fpstate; + struct _header xstate_hdr; + struct _ymmh_state ymmh; + /* New processor state extensions go here: */ +}; + +/* Not quite the right structures as these contain more information */ +int um_i387_from_fxsr(struct _fpstate_32 *i387, + const struct _fpstate_64 *fxsave); +int um_fxsr_from_i387(struct _fpstate_64 *fxsave, + const struct _fpstate_32 *from); +#else +#define _xstate_64 _xstate +#endif + +static struct _fpstate *get_fpstate(struct stub_data *data, + mcontext_t *mcontext, + int *fp_size) +{ + struct _fpstate *res; + + /* Assume floating point registers are on the same page */ + res = (void *)(((unsigned long)mcontext->fpregs & + (UM_KERN_PAGE_SIZE - 1)) + + (unsigned long)&data->sigstack[0]); + + if ((void *)res + sizeof(struct _fpstate) > + (void *)data->sigstack + sizeof(data->sigstack)) + return NULL; + + if (res->sw_reserved.magic1 != FP_XSTATE_MAGIC1) { + *fp_size = sizeof(struct _fpstate); + } else { + char *magic2_addr; + + magic2_addr = (void *)res; + magic2_addr += res->sw_reserved.extended_size; + magic2_addr -= FP_XSTATE_MAGIC2_SIZE; + + /* We still need to be within our stack */ + if ((void *)magic2_addr > + (void *)data->sigstack + sizeof(data->sigstack)) + return NULL; + + /* If we do not read MAGIC2, then we did something wrong */ + if (*(__u32 *)magic2_addr != FP_XSTATE_MAGIC2) + return NULL; + + /* Remove MAGIC2 from the size, we do not save/restore it */ + *fp_size = res->sw_reserved.extended_size - + FP_XSTATE_MAGIC2_SIZE; + } + + return res; +} + +int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + unsigned long *fp_size_out) +{ + mcontext_t *mcontext; + struct _fpstate *fpstate_stub; + struct _xstate_64 *xstate_stub; + int fp_size, xstate_size; + + /* mctx_offset is verified by wait_stub_done_seccomp */ + mcontext = (void *)&data->sigstack[data->mctx_offset]; + + get_regs_from_mc(regs, mcontext); + + fpstate_stub = get_fpstate(data, mcontext, &fp_size); + if (!fpstate_stub) + return -EINVAL; + +#ifdef CONFIG_X86_32 + xstate_stub = (void *)&fpstate_stub->_fxsr_env; + xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env); +#else + xstate_stub = (void *)fpstate_stub; + xstate_size = fp_size; +#endif + + if (fp_size_out) + *fp_size_out = xstate_size; + + if (xstate_size > host_fp_size) + return -ENOSPC; + + memcpy(®s->fp, xstate_stub, xstate_size); + + /* We do not need to read the x86_64 FS_BASE/GS_BASE registers as + * we do not permit userspace to set them directly. + */ + +#ifdef CONFIG_X86_32 + /* Read the i387 legacy FP registers */ + if (um_fxsr_from_i387((void *)®s->fp, fpstate_stub)) + return -EINVAL; +#endif + + return 0; +} + +/* Copied because we cannot include regset.h here. */ +struct task_struct; +struct user_regset; +struct membuf { + void *p; + size_t left; +}; + +int fpregs_legacy_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to); + +int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + int single_stepping) +{ + mcontext_t *mcontext; + struct _fpstate *fpstate_stub; + struct _xstate_64 *xstate_stub; + int fp_size, xstate_size; + + /* mctx_offset is verified by wait_stub_done_seccomp */ + mcontext = (void *)&data->sigstack[data->mctx_offset]; + + if ((unsigned long)mcontext < (unsigned long)data->sigstack || + (unsigned long)mcontext > + (unsigned long) data->sigstack + + sizeof(data->sigstack) - sizeof(*mcontext)) + return -EINVAL; + + get_mc_from_regs(regs, mcontext, single_stepping); + + fpstate_stub = get_fpstate(data, mcontext, &fp_size); + if (!fpstate_stub) + return -EINVAL; + +#ifdef CONFIG_X86_32 + xstate_stub = (void *)&fpstate_stub->_fxsr_env; + xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env); +#else + xstate_stub = (void *)fpstate_stub; + xstate_size = fp_size; +#endif + + memcpy(xstate_stub, ®s->fp, xstate_size); + +#ifdef __i386__ + /* + * On x86, the GDT entries are updated by arch_set_tls. + */ + + /* Store the i387 legacy FP registers which the host will use */ + if (um_i387_from_fxsr(fpstate_stub, (void *)®s->fp)) + return -EINVAL; +#else + /* + * On x86_64, we need to sync the FS_BASE/GS_BASE registers using the + * arch specific data. + */ + if (data->arch_data.fs_base != regs->gp[FS_BASE / sizeof(unsigned long)]) { + data->arch_data.fs_base = regs->gp[FS_BASE / sizeof(unsigned long)]; + data->arch_data.sync |= STUB_SYNC_FS_BASE; + } + if (data->arch_data.gs_base != regs->gp[GS_BASE / sizeof(unsigned long)]) { + data->arch_data.gs_base = regs->gp[GS_BASE / sizeof(unsigned long)]; + data->arch_data.sync |= STUB_SYNC_GS_BASE; + } +#endif + + return 0; +} diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c index 57c504fd5626..fae8aabad10f 100644 --- a/arch/x86/um/ptrace.c +++ b/arch/x86/um/ptrace.c @@ -25,7 +25,8 @@ static inline unsigned short twd_i387_to_fxsr(unsigned short twd) return tmp; } -static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave) +static inline unsigned long +twd_fxsr_to_i387(const struct user_fxsr_struct *fxsave) { struct _fpxreg *st = NULL; unsigned long twd = (unsigned long) fxsave->twd; @@ -69,12 +70,16 @@ static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave) return ret; } -/* Get/set the old 32bit i387 registers (pre-FPX) */ -static int fpregs_legacy_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) +/* + * Get/set the old 32bit i387 registers (pre-FPX) + * + * We provide simple wrappers for mcontext.c, they are only defined locally + * because mcontext.c is userspace facing and needs to a different definition + * of the structures. + */ +static int _um_i387_from_fxsr(struct membuf to, + const struct user_fxsr_struct *fxsave) { - struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; int i; membuf_store(&to, (unsigned long)fxsave->cwd | 0xffff0000ul); @@ -91,23 +96,36 @@ static int fpregs_legacy_get(struct task_struct *target, return 0; } -static int fpregs_legacy_set(struct task_struct *target, +int um_i387_from_fxsr(struct user_i387_struct *i387, + const struct user_fxsr_struct *fxsave); + +int um_i387_from_fxsr(struct user_i387_struct *i387, + const struct user_fxsr_struct *fxsave) +{ + struct membuf to = { + .p = i387, + .left = sizeof(*i387), + }; + + return _um_i387_from_fxsr(to, fxsave); +} + +static int fpregs_legacy_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + struct membuf to) { struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; - const struct user_i387_struct *from; - struct user_i387_struct buf; - int i; - if (ubuf) { - if (copy_from_user(&buf, ubuf, sizeof(buf))) - return -EFAULT; - from = &buf; - } else { - from = kbuf; - } + return _um_i387_from_fxsr(to, fxsave); +} + +int um_fxsr_from_i387(struct user_fxsr_struct *fxsave, + const struct user_i387_struct *from); + +int um_fxsr_from_i387(struct user_fxsr_struct *fxsave, + const struct user_i387_struct *from) +{ + int i; fxsave->cwd = (unsigned short)(from->cwd & 0xffff); fxsave->swd = (unsigned short)(from->swd & 0xffff); @@ -125,6 +143,26 @@ static int fpregs_legacy_set(struct task_struct *target, return 0; } + +static int fpregs_legacy_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; + const struct user_i387_struct *from; + struct user_i387_struct buf; + + if (ubuf) { + if (copy_from_user(&buf, ubuf, sizeof(buf))) + return -EFAULT; + from = &buf; + } else { + from = kbuf; + } + + return um_fxsr_from_i387(fxsave, from); +} #endif static int genregs_get(struct task_struct *target, diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index 48de3a71f845..6fd1ed400399 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -4,7 +4,9 @@ #include <linux/elf.h> #include <linux/crypto.h> #include <linux/kbuild.h> +#include <linux/audit.h> #include <asm/mman.h> +#include <asm/seccomp.h> /* workaround for a warning with -Wmissing-prototypes */ void foo(void); diff --git a/arch/x86/um/shared/sysdep/mcontext.h b/arch/x86/um/shared/sysdep/mcontext.h index b724c54da316..6fe490cc5b98 100644 --- a/arch/x86/um/shared/sysdep/mcontext.h +++ b/arch/x86/um/shared/sysdep/mcontext.h @@ -6,7 +6,16 @@ #ifndef __SYS_SIGCONTEXT_X86_H #define __SYS_SIGCONTEXT_X86_H +#include <stub-data.h> + extern void get_regs_from_mc(struct uml_pt_regs *, mcontext_t *); +extern void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, + int single_stepping); + +extern int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + unsigned long *fp_size_out); +extern int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + int single_stepping); #ifdef __i386__ diff --git a/arch/x86/um/shared/sysdep/stub-data.h b/arch/x86/um/shared/sysdep/stub-data.h new file mode 100644 index 000000000000..82b1b7f8ac3d --- /dev/null +++ b/arch/x86/um/shared/sysdep/stub-data.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ARCH_STUB_DATA_H +#define __ARCH_STUB_DATA_H + +#ifdef __i386__ +#include <generated/asm-offsets.h> +#include <asm/ldt.h> + +struct stub_data_arch { + int sync; + struct user_desc tls[UM_KERN_GDT_ENTRY_TLS_ENTRIES]; +}; +#else +#define STUB_SYNC_FS_BASE (1 << 0) +#define STUB_SYNC_GS_BASE (1 << 1) +struct stub_data_arch { + int sync; + unsigned long fs_base; + unsigned long gs_base; +}; +#endif + +#endif /* __ARCH_STUB_DATA_H */ diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h index dc89f4423454..4fa58f5b4fca 100644 --- a/arch/x86/um/shared/sysdep/stub.h +++ b/arch/x86/um/shared/sysdep/stub.h @@ -13,3 +13,5 @@ extern void stub_segv_handler(int, siginfo_t *, void *); extern void stub_syscall_handler(void); +extern void stub_signal_interrupt(int, siginfo_t *, void *); +extern void stub_signal_restorer(void); diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index 390988132c0a..df568fc3ceb4 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -131,4 +131,17 @@ static __always_inline void *get_stub_data(void) "call *%%eax ;" \ :: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \ "i" (&fn)) + +static __always_inline void +stub_seccomp_restore_state(struct stub_data_arch *arch) +{ + for (int i = 0; i < sizeof(arch->tls) / sizeof(arch->tls[0]); i++) { + if (arch->sync & (1 << i)) + stub_syscall1(__NR_set_thread_area, + (unsigned long) &arch->tls[i]); + } + + arch->sync = 0; +} + #endif diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index 294affbec742..9cfd31afa769 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -10,6 +10,7 @@ #include <sysdep/ptrace_user.h> #include <generated/asm-offsets.h> #include <linux/stddef.h> +#include <asm/prctl.h> #define STUB_MMAP_NR __NR_mmap #define MMAP_OFFSET(o) (o) @@ -134,4 +135,20 @@ static __always_inline void *get_stub_data(void) "call *%%rax ;" \ :: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \ "i" (&fn)) + +static __always_inline void +stub_seccomp_restore_state(struct stub_data_arch *arch) +{ + /* + * We could use _writefsbase_u64/_writegsbase_u64 if the host reports + * support in the hwcaps (HWCAP2_FSGSBASE). + */ + if (arch->sync & STUB_SYNC_FS_BASE) + stub_syscall2(__NR_arch_prctl, ARCH_SET_FS, arch->fs_base); + if (arch->sync & STUB_SYNC_GS_BASE) + stub_syscall2(__NR_arch_prctl, ARCH_SET_GS, arch->gs_base); + + arch->sync = 0; +} + #endif diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index fbb129023080..cb3f17627d16 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -12,6 +12,7 @@ #include <skas.h> #include <sysdep/tls.h> #include <asm/desc.h> +#include <stub-data.h> /* * If needed we can detect when it's uninitialized. @@ -21,14 +22,25 @@ static int host_supports_tls = -1; int host_gdt_entry_tls_min; -static int do_set_thread_area(struct user_desc *info) +static int do_set_thread_area(struct task_struct* task, struct user_desc *info) { int ret; - u32 cpu; - cpu = get_cpu(); - ret = os_set_thread_area(info, userspace_pid[cpu]); - put_cpu(); + if (info->entry_number < host_gdt_entry_tls_min || + info->entry_number >= host_gdt_entry_tls_min + GDT_ENTRY_TLS_ENTRIES) + return -EINVAL; + + if (using_seccomp) { + int idx = info->entry_number - host_gdt_entry_tls_min; + struct stub_data *data = (void *)task->mm->context.id.stack; + + data->arch_data.tls[idx] = *info; + data->arch_data.sync |= BIT(idx); + + return 0; + } + + ret = os_set_thread_area(info, task->mm->context.id.pid); if (ret) printk(KERN_ERR "PTRACE_SET_THREAD_AREA failed, err = %d, " @@ -97,7 +109,7 @@ static int load_TLS(int flags, struct task_struct *to) if (!(flags & O_FORCE) && curr->flushed) continue; - ret = do_set_thread_area(&curr->tls); + ret = do_set_thread_area(current, &curr->tls); if (ret) goto out; @@ -275,7 +287,7 @@ SYSCALL_DEFINE1(set_thread_area, struct user_desc __user *, user_desc) return -EFAULT; } - ret = do_set_thread_area(&info); + ret = do_set_thread_area(current, &info); if (ret) return ret; return set_tls_entry(current, &info, idx, 1); diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index 2457d13c3f9e..c7a9a087ccaf 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -75,8 +75,9 @@ static inline void seamcall_err_ret(u64 fn, u64 err, args->r9, args->r10, args->r11); } -static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func, - u64 fn, struct tdx_module_args *args) +static __always_inline int sc_retry_prerr(sc_func_t func, + sc_err_func_t err_func, + u64 fn, struct tdx_module_args *args) { u64 sret = sc_retry(func, fn, args); |