diff options
Diffstat (limited to 'arch/x86')
39 files changed, 694 insertions, 261 deletions
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index a1f28a54f23a..60c4c342316c 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -244,6 +244,17 @@ ENTRY(__switch_to_asm) movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popl %esi popl %edi diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4f8e1d35a97c..ff6f8022612c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -491,6 +491,17 @@ ENTRY(__switch_to_asm) movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popq %r15 popq %r14 @@ -1253,7 +1264,7 @@ idtentry async_page_fault do_async_page_fault has_error_code=1 #endif #ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c index a6eee5ac4f58..2aefacf5c5b2 100644 --- a/arch/x86/events/amd/power.c +++ b/arch/x86/events/amd/power.c @@ -277,7 +277,7 @@ static int __init amd_power_pmu_init(void) int ret; if (!x86_match_cpu(cpu_match)) - return 0; + return -ENODEV; if (!boot_cpu_has(X86_FEATURE_ACC_POWER)) return -ENODEV; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8156e47da7ba..18c25ab28557 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -372,10 +372,9 @@ static int alloc_pebs_buffer(int cpu) static void release_pebs_buffer(int cpu) { struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); - struct debug_store *ds = hwev->ds; void *cea; - if (!ds || !x86_pmu.pebs) + if (!x86_pmu.pebs) return; kfree(per_cpu(insn_buffer, cpu)); @@ -384,7 +383,6 @@ static void release_pebs_buffer(int cpu) /* Clear the fixmap */ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; ds_clear_cea(cea, x86_pmu.pebs_buffer_size); - ds->pebs_buffer_base = 0; dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size); hwev->ds_pebs_vaddr = NULL; } @@ -419,16 +417,14 @@ static int alloc_bts_buffer(int cpu) static void release_bts_buffer(int cpu) { struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); - struct debug_store *ds = hwev->ds; void *cea; - if (!ds || !x86_pmu.bts) + if (!x86_pmu.bts) return; /* Clear the fixmap */ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer; ds_clear_cea(cea, BTS_BUFFER_SIZE); - ds->bts_buffer_base = 0; dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE); hwev->ds_bts_vaddr = NULL; } @@ -454,16 +450,22 @@ void release_ds_buffers(void) if (!x86_pmu.bts && !x86_pmu.pebs) return; - get_online_cpus(); - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) + release_ds_buffer(cpu); + + for_each_possible_cpu(cpu) { + /* + * Again, ignore errors from offline CPUs, they will no longer + * observe cpu_hw_events.ds and not program the DS_AREA when + * they come up. + */ fini_debug_store_on_cpu(cpu); + } for_each_possible_cpu(cpu) { release_pebs_buffer(cpu); release_bts_buffer(cpu); - release_ds_buffer(cpu); } - put_online_cpus(); } void reserve_ds_buffers(void) @@ -483,8 +485,6 @@ void reserve_ds_buffers(void) if (!x86_pmu.pebs) pebs_err = 1; - get_online_cpus(); - for_each_possible_cpu(cpu) { if (alloc_ds_buffer(cpu)) { bts_err = 1; @@ -521,11 +521,14 @@ void reserve_ds_buffers(void) if (x86_pmu.pebs && !pebs_err) x86_pmu.pebs_active = 1; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) { + /* + * Ignores wrmsr_on_cpu() errors for offline CPUs they + * will get this call through intel_pmu_cpu_starting(). + */ init_debug_store_on_cpu(cpu); + } } - - put_online_cpus(); } /* diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 005908ee9333..a2efb490f743 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -755,14 +755,14 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init), diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a9e57f08bfa6..98722773391d 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -136,6 +136,7 @@ extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); +extern void init_bsp_APIC(void); extern void apic_intr_mode_init(void); extern void setup_local_APIC(void); extern void init_apic_mappings(void); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 0927cdc4f946..1908214b9125 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,5 +38,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -INDIRECT_THUNK(sp) #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f275447862f4..25b9375c1484 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -206,11 +206,11 @@ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -245,6 +245,7 @@ #define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c9459a4c3c68..22c5f3e6f820 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sme_encrypt_kernel(void); +void __init sme_encrypt_kernel(struct boot_params *bp); void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); @@ -67,7 +67,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sme_encrypt_kernel(void) { } +static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } static inline bool sme_active(void) { return false; } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 402a11c803c3..4ad41087ce0e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,7 +11,7 @@ * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; jmp' loop to capture speculative execution. + * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to @@ -38,11 +38,13 @@ call 772f; \ 773: /* speculation trap */ \ pause; \ + lfence; \ jmp 773b; \ 772: \ call 774f; \ 775: /* speculation trap */ \ pause; \ + lfence; \ jmp 775b; \ 774: \ dec reg; \ @@ -73,6 +75,7 @@ call .Ldo_rop_\@ .Lspec_trap_\@: pause + lfence jmp .Lspec_trap_\@ .Ldo_rop_\@: mov \reg, (%_ASM_SP) @@ -165,6 +168,7 @@ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ + " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: addl $4, %%esp;\n" \ @@ -190,6 +194,9 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, }; +extern char __indirect_thunk_start[]; +extern char __indirect_thunk_end[]; + /* * On VMEXIT we must ensure that no RSB predictions learned in the guest * can be followed in the host, by overwriting the RSB completely. Both @@ -199,16 +206,17 @@ enum spectre_v2_mitigation { static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - unsigned long loops = RSB_CLEAR_LOOPS / 2; + unsigned long loops; asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE ALTERNATIVE("jmp 910f", __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), X86_FEATURE_RETPOLINE) "910:" - : "=&r" (loops), ASM_CALL_CONSTRAINT - : "r" (loops) : "memory" ); + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } + #endif /* __ASSEMBLY__ */ #endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 00223333821a..d25a638a2720 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -62,8 +62,6 @@ struct thread_info { .flags = 0, \ } -#define init_stack (init_thread_union.stack) - #else /* !__ASSEMBLY__ */ #include <asm/asm-offsets.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 31051f35cbb7..3de69330e6c5 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -88,6 +88,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *, long); #endif +dotraplinkage void do_mce(struct pt_regs *, long); static inline int get_si_code(unsigned long condition) { diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 81bb565f4497..7e2baf7304ae 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,10 +29,13 @@ KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y +ifdef CONFIG_FRAME_POINTER +OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y +endif + # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, # boot, dumpstack/stacktrace, etc are either non-interesting or can lead to diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 880441f24146..25ddf02598d2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1286,6 +1286,55 @@ static int __init apic_intr_mode_select(void) return APIC_SYMMETRIC_IO; } +/* + * An initial setup of the virtual wire mode. + */ +void __init init_bsp_APIC(void) +{ + unsigned int value; + + /* + * Don't do the setup now if we have a SMP BIOS as the + * through-I/O-APIC virtual wire mode might be active. + */ + if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) + return; + + /* + * Do not trust the local APIC being empty at bootup. + */ + clear_local_APIC(); + + /* + * Enable APIC. + */ + value = apic_read(APIC_SPIV); + value &= ~APIC_VECTOR_MASK; + value |= APIC_SPIV_APIC_ENABLED; + +#ifdef CONFIG_X86_32 + /* This bit is reserved on P4/Xeon and should be cleared */ + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && + (boot_cpu_data.x86 == 15)) + value &= ~APIC_SPIV_FOCUS_DISABLED; + else +#endif + value |= APIC_SPIV_FOCUS_DISABLED; + value |= SPURIOUS_APIC_VECTOR; + apic_write(APIC_SPIV, value); + + /* + * Set up the virtual wire mode. + */ + apic_write(APIC_LVT0, APIC_DM_EXTINT); + value = APIC_DM_NMI; + if (!lapic_is_integrated()) /* 82489DX */ + value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; + apic_write(APIC_LVT1, value); +} + /* Init the interrupt delivery mode for the BSP */ void __init apic_intr_mode_init(void) { diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f8b03bb8e725..3cc471beb50b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -542,14 +542,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, err = assign_irq_vector_policy(irqd, info); trace_vector_setup(virq + i, false, err); - if (err) + if (err) { + irqd->chip_data = NULL; + free_apic_chip_data(apicd); goto error; + } } return 0; error: - x86_vector_free_irqs(domain, virq, i + 1); + x86_vector_free_irqs(domain, virq, i); return err; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e4dc26185aa7..390b3dc3d438 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -23,6 +23,7 @@ #include <asm/alternative.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/intel-family.h> static void __init spectre_v2_select_mitigation(void); @@ -155,6 +156,23 @@ disable: return SPECTRE_V2_CMD_NONE; } +/* Check for Skylake-like CPUs (for RSB handling) */ +static bool __init is_skylake_era(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return true; + } + } + return false; +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -213,6 +231,24 @@ retpoline_auto: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); + + /* + * If neither SMEP or KPTI are available, there is a risk of + * hitting userspace addresses in the RSB after a context switch + * from a shallow call stack to a deeper one. To prevent this fill + * the entire RSB, even when using IBRS. + * + * Skylake era CPUs have a separate issue with *underflow* of the + * RSB, when they will predict 'ret' targets from the generic BTB. + * The proper mitigation for this is IBRS. If IBRS is not supported + * or deactivated in favour of retpolines the RSB fill on context + * switch is required. + */ + if ((!boot_cpu_has(X86_FEATURE_PTI) && + !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Filling RSB on context switch\n"); + } } #undef pr_fmt diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 88dcf8479013..99442370de40 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -525,10 +525,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) */ if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); - kfree(d->ctrl_val); - kfree(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); list_del(&d->list); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); @@ -545,6 +541,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); kfree(d); return; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index b1d616d08eee..868e412b4f0c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1785,6 +1785,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; +dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +{ + machine_check_vector(regs, error_code); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off: diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index c4fa4a85d4cb..e4fc595cd6ea 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -239,7 +239,7 @@ static int __init save_microcode_in_initrd(void) break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(cpuid_eax(1)); + ret = save_microcode_in_initrd_amd(cpuid_eax(1)); break; default: break; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index d9e460fc7a3b..f7c55b0e753a 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -45,6 +45,9 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; /* Current microcode patch used in early patching on the APs. */ static struct microcode_intel *intel_ucode_patch; +/* last level cache size per core */ +static int llc_size_per_core; + static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, unsigned int s2, unsigned int p2) { @@ -912,12 +915,14 @@ static bool is_blacklisted(unsigned int cpu) /* * Late loading on model 79 with microcode revision less than 0x0b000021 - * may result in a system hang. This behavior is documented in item - * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family). + * and LLC size per core bigger than 2.5MB may result in a system hang. + * This behavior is documented in item BDF90, #334165 (Intel Xeon + * Processor E7-8800/4800 v4 Product Family). */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && c->x86_mask == 0x01 && + llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); @@ -975,6 +980,15 @@ static struct microcode_ops microcode_intel_ops = { .apply_microcode = apply_microcode_intel, }; +static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +{ + u64 llc_size = c->x86_cache_size * 1024; + + do_div(llc_size, c->x86_max_cores); + + return (int)llc_size; +} + struct microcode_ops * __init init_intel_microcode(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -985,5 +999,7 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; } + llc_size_per_core = calc_llc_size_per_core(c); + return µcode_intel_ops; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 05459ad3db46..d0e69769abfd 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,7 +21,6 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 7cb8ba08beb9..91b2cff4b79a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -8,6 +8,7 @@ #include <asm/ftrace.h> #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/unwind_hints.h> .code64 .section .entry.text, "ax" @@ -20,7 +21,6 @@ EXPORT_SYMBOL(__fentry__) EXPORT_SYMBOL(mcount) #endif -/* All cases save the original rbp (8 bytes) */ #ifdef CONFIG_FRAME_POINTER # ifdef CC_USING_FENTRY /* Save parent and function stack frames (rip and rbp) */ @@ -31,7 +31,7 @@ EXPORT_SYMBOL(mcount) # endif #else /* No need to save a stack frame */ -# define MCOUNT_FRAME_SIZE 8 +# define MCOUNT_FRAME_SIZE 0 #endif /* CONFIG_FRAME_POINTER */ /* Size of stack used to save mcount regs in save_mcount_regs */ @@ -64,10 +64,10 @@ EXPORT_SYMBOL(mcount) */ .macro save_mcount_regs added=0 - /* Always save the original rbp */ +#ifdef CONFIG_FRAME_POINTER + /* Save the original rbp */ pushq %rbp -#ifdef CONFIG_FRAME_POINTER /* * Stack traces will stop at the ftrace trampoline if the frame pointer * is not set up properly. If fentry is used, we need to save a frame @@ -105,7 +105,11 @@ EXPORT_SYMBOL(mcount) * Save the original RBP. Even though the mcount ABI does not * require this, it helps out callers. */ +#ifdef CONFIG_FRAME_POINTER movq MCOUNT_REG_SIZE-8(%rsp), %rdx +#else + movq %rbp, %rdx +#endif movq %rdx, RBP(%rsp) /* Copy the parent address into %rsi (second parameter) */ @@ -148,7 +152,7 @@ EXPORT_SYMBOL(mcount) ENTRY(function_hook) retq -END(function_hook) +ENDPROC(function_hook) ENTRY(ftrace_caller) /* save_mcount_regs fills in first two parameters */ @@ -184,7 +188,7 @@ GLOBAL(ftrace_graph_call) /* This is weak to keep gas from relaxing the jumps */ WEAK(ftrace_stub) retq -END(ftrace_caller) +ENDPROC(ftrace_caller) ENTRY(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ @@ -255,7 +259,7 @@ GLOBAL(ftrace_regs_caller_end) jmp ftrace_epilogue -END(ftrace_regs_caller) +ENDPROC(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -291,7 +295,7 @@ trace: restore_mcount_regs jmp fgraph_trace -END(function_hook) +ENDPROC(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -313,9 +317,10 @@ ENTRY(ftrace_graph_caller) restore_mcount_regs retq -END(ftrace_graph_caller) +ENDPROC(ftrace_graph_caller) -GLOBAL(return_to_handler) +ENTRY(return_to_handler) + UNWIND_HINT_EMPTY subq $24, %rsp /* Save the return values */ @@ -330,4 +335,5 @@ GLOBAL(return_to_handler) movq (%rsp), %rax addq $24, %rsp JMP_NOSPEC %rdi +END(return_to_handler) #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 6a5d757b9cfd..7ba5d819ebe3 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr, p = fixup_pointer(&phys_base, physaddr); *p += load_delta - sme_get_me_mask(); - /* Encrypt the kernel (if SME is active) */ - sme_encrypt_kernel(); + /* Encrypt the kernel and related (if SME is active) */ + sme_encrypt_kernel(bp); /* * Return the SME encryption mask (if SME is active) to be used as a diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index d985cef3984f..56d99be3706a 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -56,7 +56,7 @@ struct idt_data { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_idts[] = { +static const __initconst struct idt_data early_idts[] = { INTG(X86_TRAP_DB, debug), SYSG(X86_TRAP_BP, int3), #ifdef CONFIG_X86_32 @@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = { * the traps which use them are reinitialized with IST after cpu_init() has * set up TSS. */ -static const __initdata struct idt_data def_idts[] = { +static const __initconst struct idt_data def_idts[] = { INTG(X86_TRAP_DE, divide_error), INTG(X86_TRAP_NMI, nmi), INTG(X86_TRAP_BR, bounds), @@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = { /* * The APIC and SMP idt entries */ -static const __initdata struct idt_data apic_idts[] = { +static const __initconst struct idt_data apic_idts[] = { #ifdef CONFIG_SMP INTG(RESCHEDULE_VECTOR, reschedule_interrupt), INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), @@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_pf_idts[] = { +static const __initconst struct idt_data early_pf_idts[] = { INTG(X86_TRAP_PF, page_fault), }; @@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = { * Override for the debug_idt. Same as the default, but with interrupt * stack set to DEFAULT_STACK (0). Required for NMI trap handling. */ -static const __initdata struct idt_data dbg_idts[] = { +static const __initconst struct idt_data dbg_idts[] = { INTG(X86_TRAP_DB, debug), INTG(X86_TRAP_BP, int3), }; @@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; * The exceptions which use Interrupt stacks. They are setup after * cpu_init() when the TSS has been initialized. */ -static const __initdata struct idt_data ist_idts[] = { +static const __initconst struct idt_data ist_idts[] = { ISTG(X86_TRAP_DB, debug, DEBUG_STACK), ISTG(X86_TRAP_NMI, nmi, NMI_STACK), SISTG(X86_TRAP_BP, int3, DEBUG_STACK), diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 8da3e909e967..a539410c4ea9 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -61,6 +61,9 @@ void __init init_ISA_irqs(void) struct irq_chip *chip = legacy_pic->chip; int i; +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) + init_bsp_APIC(); +#endif legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e941136e24d8..203d398802a3 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -40,6 +40,7 @@ #include <asm/debugreg.h> #include <asm/set_memory.h> #include <asm/sections.h> +#include <asm/nospec-branch.h> #include "common.h" @@ -203,7 +204,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) } /* Check whether insn is indirect jump */ -static int insn_is_indirect_jump(struct insn *insn) +static int __insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -237,6 +238,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) return (start <= target && target <= start + len); } +static int insn_is_indirect_jump(struct insn *insn) +{ + int ret = __insn_is_indirect_jump(insn); + +#ifdef CONFIG_RETPOLINE + /* + * Jump to x86_indirect_thunk_* is treated as an indirect jump. + * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with + * older gcc may use indirect jump. So we add this check instead of + * replace indirect-jump check. + */ + if (!ret) + ret = insn_jump_into_range(insn, + (unsigned long)__indirect_thunk_start, + (unsigned long)__indirect_thunk_end - + (unsigned long)__indirect_thunk_start); +#endif + return ret; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 832a6acd730f..cb368c2a22ab 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -380,19 +380,24 @@ void stop_this_cpu(void *dummy) disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); + /* + * Use wbinvd on processors that support SME. This provides support + * for performing a successful kexec when going from SME inactive + * to SME active (or vice-versa). The cache must be cleared so that + * if there are entries with the same physical address, both with and + * without the encryption bit, they don't race each other when flushed + * and potentially end up with the wrong entry being committed to + * memory. + */ + if (boot_cpu_has(X86_FEATURE_SME)) + native_wbinvd(); for (;;) { /* - * Use wbinvd followed by hlt to stop the processor. This - * provides support for kexec on a processor that supports - * SME. With kexec, going from SME inactive to SME active - * requires clearing cache entries so that addresses without - * the encryption bit set don't corrupt the same physical - * address that has the encryption bit set when caches are - * flushed. To achieve this a wbinvd is performed followed by - * a hlt. Even if the processor is not in the kexec/SME - * scenario this only adds a wbinvd to a halting processor. + * Use native_halt() so that memory contents don't change + * (stack usage and variables) after possibly issuing the + * native_wbinvd() above. */ - asm volatile("wbinvd; hlt" : : : "memory"); + native_halt(); } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 145810b0edf6..68d7ab81c62f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -364,16 +364,6 @@ static void __init reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ - /* - * If SME is active, this memory will be marked encrypted by the - * kernel when it is accessed (including relocation). However, the - * ramdisk image was loaded decrypted by the bootloader, so make - * sure that it is encrypted before accessing it. For SEV the - * ramdisk will already be encrypted, so only do this for SME. - */ - if (sme_active()) - sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); - initrd_start = 0; mapped_size = memblock_mem_size(max_pfn_mapped); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 8ea117f8142e..e169e85db434 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -602,7 +602,6 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; @@ -612,6 +611,8 @@ unsigned long native_calibrate_tsc(void) } } + if (crystal_khz == 0) + return 0; /* * TSC frequency determined by CPUID is a "hardware reported" * frequency and is the most accurate one so far we have. This @@ -1315,6 +1316,12 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + if (cpu_khz != tsc_khz) { + pr_info("Detected %lu.%03lu MHz TSC", + (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); + } + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index be86a865087a..1f9188f5357c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -74,8 +74,50 @@ static struct orc_entry *orc_module_find(unsigned long ip) } #endif +#ifdef CONFIG_DYNAMIC_FTRACE +static struct orc_entry *orc_find(unsigned long ip); + +/* + * Ftrace dynamic trampolines do not have orc entries of their own. + * But they are copies of the ftrace entries that are static and + * defined in ftrace_*.S, which do have orc entries. + * + * If the undwinder comes across a ftrace trampoline, then find the + * ftrace function that was used to create it, and use that ftrace + * function's orc entrie, as the placement of the return code in + * the stack will be identical. + */ +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + struct ftrace_ops *ops; + unsigned long caller; + + ops = ftrace_ops_trampoline(ip); + if (!ops) + return NULL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + caller = (unsigned long)ftrace_regs_call; + else + caller = (unsigned long)ftrace_call; + + /* Prevent unlikely recursion */ + if (ip == caller) + return NULL; + + return orc_find(caller); +} +#else +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + return NULL; +} +#endif + static struct orc_entry *orc_find(unsigned long ip) { + static struct orc_entry *orc; + if (!orc_init) return NULL; @@ -111,7 +153,11 @@ static struct orc_entry *orc_find(unsigned long ip) __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); /* Module lookup: */ - return orc_module_find(ip); + orc = orc_module_find(ip); + if (orc) + return orc; + + return orc_ftrace_find(ip); } static void orc_sort_swap(void *_a, void *_b, int size) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 1e413a9326aa..9b138a06c1a4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -124,6 +124,12 @@ SECTIONS ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif +#ifdef CONFIG_RETPOLINE + __indirect_thunk_start = .; + *(.text.__x86.indirect_thunk) + __indirect_thunk_end = .; +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1cec2c62a0b0..c53298dfbf50 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7496,13 +7496,13 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) { + if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in * 64-bit mode (though maybe in a 32-bit code segment). * CR4.PAE and EFER.LMA must be set. */ - if (!(sregs->cr4 & X86_CR4_PAE_BIT) + if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return -EINVAL; } else { diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index cb45c6cb465f..c909961e678a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -9,7 +9,7 @@ #include <asm/nospec-branch.h> .macro THUNK reg - .section .text.__x86.indirect_thunk.\reg + .section .text.__x86.indirect_thunk ENTRY(__x86_indirect_thunk_\reg) CFI_STARTPROC @@ -25,7 +25,8 @@ ENDPROC(__x86_indirect_thunk_\reg) * than one per register with the correct names. So we do it * the simple and nasty way... */ -#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg) +#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) +#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) #define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) GENERATE_THUNK(_ASM_AX) @@ -35,7 +36,6 @@ GENERATE_THUNK(_ASM_DX) GENERATE_THUNK(_ASM_SI) GENERATE_THUNK(_ASM_DI) GENERATE_THUNK(_ASM_BP) -GENERATE_THUNK(_ASM_SP) #ifdef CONFIG_64BIT GENERATE_THUNK(r8) GENERATE_THUNK(r9) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 06fe3d51d385..800de815519c 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) +static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info, + u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; /* Fault not from Protection Keys: nothing to do */ - if (si_code != SEGV_PKUERR) + if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV)) return; /* * force_sig_info_fault() is called from a number of @@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, pkey); + fill_sig_info_pkey(si_signo, si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } @@ -438,18 +439,13 @@ static noinline int vmalloc_fault(unsigned long address) if (pgd_none(*pgd_ref)) return -1; - if (pgd_none(*pgd)) { - set_pgd(pgd, *pgd_ref); - arch_flush_lazy_mmu_mode(); - } else if (CONFIG_PGTABLE_LEVELS > 4) { - /* - * With folded p4d, pgd_none() is always false, so the pgd may - * point to an empty page table entry and pgd_page_vaddr() - * will return garbage. - * - * We will do the correct sanity check on the p4d level. - */ - BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + if (CONFIG_PGTABLE_LEVELS > 4) { + if (pgd_none(*pgd)) { + set_pgd(pgd, *pgd_ref); + arch_flush_lazy_mmu_mode(); + } else { + BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + } } /* With 4-level paging, copying happens on the p4d level. */ @@ -458,7 +454,7 @@ static noinline int vmalloc_fault(unsigned long address) if (p4d_none(*p4d_ref)) return -1; - if (p4d_none(*p4d)) { + if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) { set_p4d(p4d, *p4d_ref); arch_flush_lazy_mmu_mode(); } else { @@ -469,6 +465,7 @@ static noinline int vmalloc_fault(unsigned long address) * Below here mismatches are bugs because these lower tables * are shared: */ + BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4); pud = pud_offset(p4d, address); pud_ref = pud_offset(p4d_ref, address); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 47388f0c0e59..af6f2f9c6a26 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -21,10 +21,14 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static __init void *early_alloc(size_t size, int nid) +static __init void *early_alloc(size_t size, int nid, bool panic) { - return memblock_virt_alloc_try_nid_nopanic(size, size, - __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + if (panic) + return memblock_virt_alloc_try_nid(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + else + return memblock_virt_alloc_try_nid_nopanic(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, @@ -38,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (boot_cpu_has(X86_FEATURE_PSE) && ((end - addr) == PMD_SIZE) && IS_ALIGNED(addr, PMD_SIZE)) { - p = early_alloc(PMD_SIZE, nid); + p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PMD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pmd_populate_kernel(&init_mm, pmd, p); } @@ -57,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (!pte_none(*pte)) continue; - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL); set_pte_at(&init_mm, addr, pte, entry); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -75,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, if (boot_cpu_has(X86_FEATURE_GBPAGES) && ((end - addr) == PUD_SIZE) && IS_ALIGNED(addr, PUD_SIZE)) { - p = early_alloc(PUD_SIZE, nid); + p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PUD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pud_populate(&init_mm, pud, p); } @@ -101,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, unsigned long next; if (p4d_none(*p4d)) { - void *p = early_alloc(PAGE_SIZE, nid); + void *p = early_alloc(PAGE_SIZE, nid, true); p4d_populate(&init_mm, p4d, p); } @@ -122,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, unsigned long next; if (pgd_none(*pgd)) { - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pgd_populate(&init_mm, pgd, p); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 391b13402e40..e1d61e8500f9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); } -static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start, - unsigned long end) +struct sme_populate_pgd_data { + void *pgtable_area; + pgd_t *pgd; + + pmdval_t pmd_flags; + pteval_t pte_flags; + unsigned long paddr; + + unsigned long vaddr; + unsigned long vaddr_end; +}; + +static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; - pgd_start = start & PGDIR_MASK; - pgd_end = end & PGDIR_MASK; + pgd_start = ppd->vaddr & PGDIR_MASK; + pgd_end = ppd->vaddr_end & PGDIR_MASK; - pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1); - pgd_size *= sizeof(pgd_t); + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t); - pgd_p = pgd_base + pgd_index(start); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); memset(pgd_p, 0, pgd_size); } -#define PGD_FLAGS _KERNPG_TABLE_NOENC -#define P4D_FLAGS _KERNPG_TABLE_NOENC -#define PUD_FLAGS _KERNPG_TABLE_NOENC -#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS _KERNPG_TABLE_NOENC + +#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +#define PMD_FLAGS_DEC PMD_FLAGS_LARGE +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) + +#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) + +#define PTE_FLAGS_DEC PTE_FLAGS +#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) -static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, - unsigned long vaddr, pmdval_t pmd_val) +static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd_p; p4d_t *p4d_p; pud_t *pud_p; pmd_t *pmd_p; - pgd_p = pgd_base + pgd_index(vaddr); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); if (native_pgd_val(*pgd_p)) { if (IS_ENABLED(CONFIG_X86_5LEVEL)) p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); @@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, pgd_t pgd; if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p = pgtable_area; + p4d_p = ppd->pgtable_area; memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); - pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; + ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); } else { - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); } @@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, } if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p += p4d_index(vaddr); + p4d_p += p4d_index(ppd->vaddr); if (native_p4d_val(*p4d_p)) { pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); } else { p4d_t p4d; - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); native_set_p4d(p4d_p, p4d); } } - pud_p += pud_index(vaddr); + pud_p += pud_index(ppd->vaddr); if (native_pud_val(*pud_p)) { if (native_pud_val(*pud_p) & _PAGE_PSE) - goto out; + return NULL; pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); } else { pud_t pud; - pmd_p = pgtable_area; + pmd_p = ppd->pgtable_area; memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); - pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; + ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); native_set_pud(pud_p, pud); } - pmd_p += pmd_index(vaddr); + return pmd_p; +} + +static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) - native_set_pmd(pmd_p, native_make_pmd(pmd_val)); + native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags)); +} -out: - return pgtable_area; +static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + pte_t *pte_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); + if (native_pmd_val(*pmd_p)) { + if (native_pmd_val(*pmd_p) & _PAGE_PSE) + return; + + pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK); + } else { + pmd_t pmd; + + pte_p = ppd->pgtable_area; + memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE; + + pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS); + native_set_pmd(pmd_p, pmd); + } + + pte_p += pte_index(ppd->vaddr); + if (!native_pte_val(*pte_p)) + native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags)); +} + +static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd_large(ppd); + + ppd->vaddr += PMD_PAGE_SIZE; + ppd->paddr += PMD_PAGE_SIZE; + } +} + +static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd(ppd); + + ppd->vaddr += PAGE_SIZE; + ppd->paddr += PAGE_SIZE; + } +} + +static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, + pmdval_t pmd_flags, pteval_t pte_flags) +{ + unsigned long vaddr_end; + + ppd->pmd_flags = pmd_flags; + ppd->pte_flags = pte_flags; + + /* Save original end value since we modify the struct value */ + vaddr_end = ppd->vaddr_end; + + /* If start is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); + __sme_map_range_pte(ppd); + + /* Create PMD entries */ + ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; + __sme_map_range_pmd(ppd); + + /* If end is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = vaddr_end; + __sme_map_range_pte(ppd); +} + +static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); +} + +static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); +} + +static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } static unsigned long __init sme_pgtable_calc(unsigned long len) { - unsigned long p4d_size, pud_size, pmd_size; + unsigned long p4d_size, pud_size, pmd_size, pte_size; unsigned long total; /* * Perform a relatively simplistic calculation of the pagetable - * entries that are needed. That mappings will be covered by 2MB - * PMD entries so we can conservatively calculate the required + * entries that are needed. Those mappings will be covered mostly + * by 2MB PMD entries so we can conservatively calculate the required * number of P4D, PUD and PMD structures needed to perform the - * mappings. Incrementing the count for each covers the case where - * the addresses cross entries. + * mappings. For mappings that are not 2MB aligned, PTE mappings + * would be needed for the start and end portion of the address range + * that fall outside of the 2MB alignment. This results in, at most, + * two extra pages to hold PTE entries for each range that is mapped. + * Incrementing the count for each covers the case where the addresses + * cross entries. */ if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; @@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) } pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE; - total = p4d_size + pud_size + pmd_size; + total = p4d_size + pud_size + pmd_size + pte_size; /* * Now calculate the added pagetable structures needed to populate @@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return total; } -void __init sme_encrypt_kernel(void) +void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; unsigned long kernel_start, kernel_end, kernel_len; + unsigned long initrd_start, initrd_end, initrd_len; + struct sme_populate_pgd_data ppd; unsigned long pgtable_area_len; - unsigned long paddr, pmd_flags; unsigned long decrypted_base; - void *pgtable_area; - pgd_t *pgd; if (!sme_active()) return; /* - * Prepare for encrypting the kernel by building new pagetables with - * the necessary attributes needed to encrypt the kernel in place. + * Prepare for encrypting the kernel and initrd by building new + * pagetables with the necessary attributes needed to encrypt the + * kernel in place. * * One range of virtual addresses will map the memory occupied - * by the kernel as encrypted. + * by the kernel and initrd as encrypted. * * Another range of virtual addresses will map the memory occupied - * by the kernel as decrypted and write-protected. + * by the kernel and initrd as decrypted and write-protected. * * The use of write-protect attribute will prevent any of the * memory from being cached. @@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void) kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); kernel_len = kernel_end - kernel_start; + initrd_start = 0; + initrd_end = 0; + initrd_len = 0; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_len = (unsigned long)bp->hdr.ramdisk_size | + ((unsigned long)bp->ext_ramdisk_size << 32); + if (initrd_len) { + initrd_start = (unsigned long)bp->hdr.ramdisk_image | + ((unsigned long)bp->ext_ramdisk_image << 32); + initrd_end = PAGE_ALIGN(initrd_start + initrd_len); + initrd_len = initrd_end - initrd_start; + } +#endif + /* Set the encryption workarea to be immediately after the kernel */ workarea_start = kernel_end; @@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void) */ pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + if (initrd_len) + pgtable_area_len += sme_pgtable_calc(initrd_len) * 2; /* PUDs and PMDs needed in the current pagetables for the workarea */ pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); /* * The total workarea includes the executable encryption area and - * the pagetable area. + * the pagetable area. The start of the workarea is already 2MB + * aligned, align the end of the workarea on a 2MB boundary so that + * we don't try to create/allocate PTE entries from the workarea + * before it is mapped. */ workarea_len = execute_len + pgtable_area_len; - workarea_end = workarea_start + workarea_len; + workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); /* * Set the address to the start of where newly created pagetable @@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void) * pagetables and when the new encrypted and decrypted kernel * mappings are populated. */ - pgtable_area = (void *)execute_end; + ppd.pgtable_area = (void *)execute_end; /* * Make sure the current pagetable structure has entries for * addressing the workarea. */ - pgd = (pgd_t *)native_read_cr3_pa(); - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = (pgd_t *)native_read_cr3_pa(); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); /* * A new pagetable structure is being built to allow for the kernel - * to be encrypted. It starts with an empty PGD that will then be - * populated with new PUDs and PMDs as the encrypted and decrypted - * kernel mappings are created. + * and initrd to be encrypted. It starts with an empty PGD that will + * then be populated with new PUDs and PMDs as the encrypted and + * decrypted kernel mappings are created. */ - pgd = pgtable_area; - memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD); - pgtable_area += sizeof(*pgd) * PTRS_PER_PGD; - - /* Add encrypted kernel (identity) mappings */ - pmd_flags = PMD_FLAGS | _PAGE_ENC; - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = ppd.pgtable_area; + memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD); + ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD; /* * A different PGD index/entry must be used to get different @@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void) * the base of the mapping. */ decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + if (initrd_len) { + unsigned long check_base; + + check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base = max(decrypted_base, check_base); + } decrypted_base <<= PGDIR_SHIFT; + /* Add encrypted kernel (identity) mappings */ + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start; + ppd.vaddr_end = kernel_end; + sme_map_range_encrypted(&ppd); + /* Add decrypted, write-protected kernel (non-identity) mappings */ - pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT); - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); + + if (initrd_len) { + /* Add encrypted initrd (identity) mappings */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start; + ppd.vaddr_end = initrd_end; + sme_map_range_encrypted(&ppd); + /* + * Add decrypted, write-protected initrd (non-identity) mappings + */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); } /* Add decrypted workarea mappings to both kernel mappings */ - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_map_range_decrypted(&ppd); /* Perform the encryption */ sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, - kernel_len, workarea_start, (unsigned long)pgd); + kernel_len, workarea_start, (unsigned long)ppd.pgd); + + if (initrd_len) + sme_encrypt_execute(initrd_start, initrd_start + decrypted_base, + initrd_len, workarea_start, + (unsigned long)ppd.pgd); /* * At this point we are running encrypted. Remove the mappings for * the decrypted areas - all that is needed for this is to remove * the PGD entry/entries. */ - sme_clear_pgd(pgd, kernel_start + decrypted_base, - kernel_end + decrypted_base); + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_clear_pgd(&ppd); + + if (initrd_len) { + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_clear_pgd(&ppd); + } - sme_clear_pgd(pgd, workarea_start + decrypted_base, - workarea_end + decrypted_base); + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_clear_pgd(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 730e6d541df1..01f682cf77a8 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute) /* * Entry parameters: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping - * RDX - length of kernel + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping + * RDX - length to encrypt * RCX - virtual address of the encryption workarea, including: * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) @@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute) addq $PAGE_SIZE, %rax /* Workarea encryption routine */ push %r12 - movq %rdi, %r10 /* Encrypted kernel */ - movq %rsi, %r11 /* Decrypted kernel */ - movq %rdx, %r12 /* Kernel length */ + movq %rdi, %r10 /* Encrypted area */ + movq %rsi, %r11 /* Decrypted area */ + movq %rdx, %r12 /* Area length */ /* Copy encryption routine into the workarea */ movq %rax, %rdi /* Workarea encryption routine */ @@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute) rep movsb /* Setup registers for call */ - movq %r10, %rdi /* Encrypted kernel */ - movq %r11, %rsi /* Decrypted kernel */ + movq %r10, %rdi /* Encrypted area */ + movq %r11, %rsi /* Decrypted area */ movq %r8, %rdx /* Pagetables used for encryption */ - movq %r12, %rcx /* Kernel length */ + movq %r12, %rcx /* Area length */ movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ @@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute) ENTRY(__enc_copy) /* - * Routine used to encrypt kernel. + * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since * the kernel will be encrypted during the process. So this * routine is defined here and then copied to an area outside @@ -79,19 +79,19 @@ ENTRY(__enc_copy) * during execution. * * On entry the registers must be: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping * RDX - address of the pagetables to use for encryption - * RCX - length of kernel + * RCX - length of area * R8 - intermediate copy buffer * * RAX - points to this routine * - * The kernel will be encrypted by copying from the non-encrypted - * kernel space to an intermediate buffer and then copying from the - * intermediate buffer back to the encrypted kernel space. The physical - * addresses of the two kernel space mappings are the same which - * results in the kernel being encrypted "in place". + * The area will be encrypted by copying from the non-encrypted + * memory space to an intermediate buffer and then copying from the + * intermediate buffer back to the encrypted memory space. The physical + * addresses of the two mappings are the same which results in the area + * being encrypted "in place". */ /* Enable the new page tables */ mov %rdx, %cr3 @@ -103,47 +103,55 @@ ENTRY(__enc_copy) orq $X86_CR4_PGE, %rdx mov %rdx, %cr4 + push %r15 + push %r12 + + movq %rcx, %r9 /* Save area length */ + movq %rdi, %r10 /* Save encrypted area address */ + movq %rsi, %r11 /* Save decrypted area address */ + /* Set the PAT register PA5 entry to write-protect */ - push %rcx movl $MSR_IA32_CR_PAT, %ecx rdmsr - push %rdx /* Save original PAT value */ + mov %rdx, %r15 /* Save original PAT value */ andl $0xffff00ff, %edx /* Clear PA5 */ orl $0x00000500, %edx /* Set PA5 to WP */ wrmsr - pop %rdx /* RDX contains original PAT value */ - pop %rcx - - movq %rcx, %r9 /* Save kernel length */ - movq %rdi, %r10 /* Save encrypted kernel address */ - movq %rsi, %r11 /* Save decrypted kernel address */ wbinvd /* Invalidate any cache entries */ - /* Copy/encrypt 2MB at a time */ + /* Copy/encrypt up to 2MB at a time */ + movq $PMD_PAGE_SIZE, %r12 1: - movq %r11, %rsi /* Source - decrypted kernel */ + cmpq %r12, %r9 + jnb 2f + movq %r9, %r12 + +2: + movq %r11, %rsi /* Source - decrypted area */ movq %r8, %rdi /* Dest - intermediate copy buffer */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r12, %rcx rep movsb movq %r8, %rsi /* Source - intermediate copy buffer */ - movq %r10, %rdi /* Dest - encrypted kernel */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r10, %rdi /* Dest - encrypted area */ + movq %r12, %rcx rep movsb - addq $PMD_PAGE_SIZE, %r11 - addq $PMD_PAGE_SIZE, %r10 - subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */ + addq %r12, %r11 + addq %r12, %r10 + subq %r12, %r9 /* Kernel length decrement */ jnz 1b /* Kernel length not zero? */ /* Restore PAT register */ - push %rdx /* Save original PAT value */ movl $MSR_IA32_CR_PAT, %ecx rdmsr - pop %rdx /* Restore original PAT value */ + mov %r15, %rdx /* Restore original PAT value */ wrmsr + pop %r12 + pop %r15 + ret .L__enc_copy_end: ENDPROC(__enc_copy) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a1561957dccb..5bfe61a5e8e3 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -151,6 +151,34 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } +static void sync_current_stack_to_mm(struct mm_struct *mm) +{ + unsigned long sp = current_stack_pointer; + pgd_t *pgd = pgd_offset(mm, sp); + + if (CONFIG_PGTABLE_LEVELS > 4) { + if (unlikely(pgd_none(*pgd))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + + set_pgd(pgd, *pgd_ref); + } + } else { + /* + * "pgd" is faked. The top level entries are "p4d"s, so sync + * the p4d. This compiles to approximately the same code as + * the 5-level case. + */ + p4d_t *p4d = p4d_offset(pgd, sp); + + if (unlikely(p4d_none(*p4d))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + p4d_t *p4d_ref = p4d_offset(pgd_ref, sp); + + set_p4d(p4d, *p4d_ref); + } + } +} + void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -226,11 +254,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer); - pgd_t *pgd = next->pgd + index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[index]); + sync_current_stack_to_mm(next); } /* Stop remote flushes for the previous mm */ diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f6a26e3cb476..54ef19e90705 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -662,11 +662,11 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid); */ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) { + static const char *name = "PCI Bus 0000:00"; + struct resource *res, *conflict; u32 base, limit, high; struct pci_dev *other; - struct resource *res; unsigned i; - int r; if (!(pci_probe & PCI_BIG_ROOT_WINDOW)) return; @@ -707,21 +707,26 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) * Allocate a 256GB window directly below the 0xfd00000000 hardware * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6). */ - res->name = "PCI Bus 0000:00"; + res->name = name; res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_WINDOW; res->start = 0xbd00000000ull; res->end = 0xfd00000000ull - 1; - r = request_resource(&iomem_resource, res); - if (r) { + conflict = request_resource_conflict(&iomem_resource, res); + if (conflict) { kfree(res); - return; - } + if (conflict->name != name) + return; - dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", - res); - add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + /* We are resuming from suspend; just reenable the window */ + res = conflict; + } else { + dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", + res); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + pci_bus_add_resource(dev->bus, res, 0); + } base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) | AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK; @@ -733,13 +738,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high); pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit); pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base); - - pci_bus_add_resource(dev->bus, res, 0); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); #endif |