diff options
Diffstat (limited to 'arch/x86')
52 files changed, 713 insertions, 264 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f9920f1341c8..42747e942a07 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -107,6 +107,8 @@ config X86 select ARCH_SUPPORTS_PAGE_TABLE_CHECK if X86_64 select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096 + select ARCH_SUPPORTS_CFI_CLANG if X86_64 + select ARCH_USES_CFI_TRAPS if X86_64 && CFI_CLANG select ARCH_SUPPORTS_LTO_CLANG select ARCH_SUPPORTS_LTO_CLANG_THIN select ARCH_USE_BUILTIN_BSWAP @@ -257,6 +259,7 @@ config X86 select HAVE_STATIC_CALL_INLINE if HAVE_OBJTOOL select HAVE_PREEMPT_DYNAMIC_CALL select HAVE_RSEQ + select HAVE_RUST if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UACCESS_VALIDATION if HAVE_OBJTOOL select HAVE_UNSTABLE_SCHED_CLOCK @@ -448,6 +451,11 @@ config X86_X2APIC This allows 32-bit apic IDs (so it can support very large systems), and accesses the local apic via MSRs not via mmio. + Some Intel systems circa 2022 and later are locked into x2APIC mode + and can not fall back to the legacy APIC modes if SGX or TDX are + enabled in the BIOS. They will be unable to boot without enabling + this option. + If you don't know what to do here, say N. config X86_MPPARSE @@ -1919,7 +1927,7 @@ endchoice config X86_SGX bool "Software Guard eXtensions (SGX)" - depends on X86_64 && CPU_SUP_INTEL + depends on X86_64 && CPU_SUP_INTEL && X86_X2APIC depends on CRYPTO=y depends on CRYPTO_SHA256=y select SRCU diff --git a/arch/x86/Makefile b/arch/x86/Makefile index bafbd905e6e7..2d7e640674c6 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -68,6 +68,7 @@ export BITS # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 ifeq ($(CONFIG_X86_KERNEL_IBT),y) # @@ -155,8 +156,17 @@ else cflags-$(CONFIG_GENERIC_CPU) += -mtune=generic KBUILD_CFLAGS += $(cflags-y) + rustflags-$(CONFIG_MK8) += -Ctarget-cpu=k8 + rustflags-$(CONFIG_MPSC) += -Ctarget-cpu=nocona + rustflags-$(CONFIG_MCORE2) += -Ctarget-cpu=core2 + rustflags-$(CONFIG_MATOM) += -Ctarget-cpu=atom + rustflags-$(CONFIG_GENERIC_CPU) += -Ztune-cpu=generic + KBUILD_RUSTFLAGS += $(rustflags-y) + KBUILD_CFLAGS += -mno-red-zone KBUILD_CFLAGS += -mcmodel=kernel + KBUILD_RUSTFLAGS += -Cno-redzone=y + KBUILD_RUSTFLAGS += -Ccode-model=kernel endif # diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 802d71582689..4a43e072d2d1 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -6,6 +6,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> .file "blowfish-x86_64-asm.S" .text @@ -141,7 +142,7 @@ SYM_FUNC_START(__blowfish_enc_blk) RET; SYM_FUNC_END(__blowfish_enc_blk) -SYM_FUNC_START(blowfish_dec_blk) +SYM_TYPED_FUNC_START(blowfish_dec_blk) /* input: * %rdi: ctx * %rsi: dst @@ -332,7 +333,7 @@ SYM_FUNC_START(__blowfish_enc_blk_4way) RET; SYM_FUNC_END(__blowfish_enc_blk_4way) -SYM_FUNC_START(blowfish_dec_blk_4way) +SYM_TYPED_FUNC_START(blowfish_dec_blk_4way) /* input: * %rdi: ctx * %rsi: dst diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 12f6c4d714cd..381d3333b996 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),) endif endif -$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) $(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO # @@ -153,6 +153,7 @@ KBUILD_CFLAGS_32 := $(filter-out $(RANDSTRUCT_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_CFI),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic KBUILD_CFLAGS_32 += -fno-stack-protector KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index cb98a05ee743..c20d8cd47c48 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +EVENT_ATTR_STR(mem-loads, mem_ld_grt, "event=0xd0,umask=0x5,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_grt, "event=0xd0,umask=0x6"); + +static struct attribute *grt_mem_attrs[] = { + EVENT_PTR(mem_ld_grt), + EVENT_PTR(mem_st_grt), + NULL +}; + static struct extra_reg intel_grt_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), @@ -4052,8 +4061,9 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) /* Disable guest PEBS if host PEBS is enabled. */ arr[pebs_enable].guest = 0; } else { - /* Disable guest PEBS for cross-mapped PEBS counters. */ + /* Disable guest PEBS thoroughly for cross-mapped PEBS counters. */ arr[pebs_enable].guest &= ~kvm_pmu->host_cross_mapped_mask; + arr[global_ctrl].guest &= ~kvm_pmu->host_cross_mapped_mask; /* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */ arr[global_ctrl].guest |= arr[pebs_enable].guest; } @@ -5974,6 +5984,36 @@ __init int intel_pmu_init(void) name = "Tremont"; break; + case INTEL_FAM6_ALDERLAKE_N: + x86_pmu.mid_ack = true; + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints; + x86_pmu.extra_regs = intel_grt_extra_regs; + + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.pebs_block = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + + intel_pmu_pebs_data_source_grt(); + x86_pmu.pebs_latency_data = adl_latency_data_small; + x86_pmu.get_event_constraints = tnt_get_event_constraints; + x86_pmu.limit_period = spr_limit_period; + td_attr = tnt_events_attrs; + mem_attr = grt_mem_attrs; + extra_attr = nhm_format_attr; + pr_cont("Gracemont events, "); + name = "gracemont"; + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: @@ -6316,7 +6356,6 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_ALDERLAKE_N: case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: /* diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index de1f55d51784..ac973c6f82ad 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem) __intel_pmu_pebs_data_source_skl(pmem, pebs_data_source); } -static void __init intel_pmu_pebs_data_source_grt(u64 *data_source) +static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source) { data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD); } +void __init intel_pmu_pebs_data_source_grt(void) +{ + __intel_pmu_pebs_data_source_grt(pebs_data_source); +} + void __init intel_pmu_pebs_data_source_adl(void) { u64 *data_source; @@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void) data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); - intel_pmu_pebs_data_source_grt(data_source); + __intel_pmu_pebs_data_source_grt(data_source); } static u64 precise_store_data(u64 status) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ba3d24a6a4ec..266143abcbd8 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1516,6 +1516,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem); void intel_pmu_pebs_data_source_adl(void); +void intel_pmu_pebs_data_source_grt(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h index e003a01b7c67..1dd14381bcb6 100644 --- a/arch/x86/include/asm/acrn.h +++ b/arch/x86/include/asm/acrn.h @@ -10,6 +10,15 @@ /* Bit 0 indicates whether guest VM is privileged */ #define ACRN_FEATURE_PRIVILEGED_VM BIT(0) +/* + * Timing Information. + * This leaf returns the current TSC frequency in kHz. + * + * EAX: (Virtual) TSC frequency in kHz. + * EBX, ECX, EDX: RESERVED (reserved fields are set to zero). + */ +#define ACRN_CPUID_TIMING_INFO 0x40000010 + void acrn_setup_intr_handler(void (*handler)(void)); void acrn_remove_intr_handler(void); @@ -21,6 +30,11 @@ static inline u32 acrn_cpuid_base(void) return 0; } +static inline unsigned long acrn_get_tsc_khz(void) +{ + return cpuid_eax(ACRN_CPUID_TIMING_INFO); +} + /* * Hypercalls for ACRN * diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h new file mode 100644 index 000000000000..58dacd90daef --- /dev/null +++ b/arch/x86/include/asm/cfi.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CFI_H +#define _ASM_X86_CFI_H + +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2022 Google LLC + */ + +#include <linux/cfi.h> + +#ifdef CONFIG_CFI_CLANG +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); +#else +static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_NONE; +} +#endif /* CONFIG_CFI_CLANG */ + +#endif /* _ASM_X86_CFI_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 8cbf623f0ecf..b472ef76826a 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -94,4 +94,6 @@ static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1, return p1 & p2; } +extern u64 x86_read_arch_cap_msr(void); + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index aeb38023a703..5d75fe229342 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -115,6 +115,9 @@ #define INTEL_FAM6_RAPTORLAKE_P 0xBA #define INTEL_FAM6_RAPTORLAKE_S 0xBF +#define INTEL_FAM6_METEORLAKE 0xAC +#define INTEL_FAM6_METEORLAKE_L 0xAA + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 63f818aedf77..147cb8fdda92 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -203,7 +203,7 @@ IRQ_CONSTRAINTS, regs, vector); \ } -#ifndef CONFIG_PREEMPT_RT +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK /* * Macro to invoke __do_softirq on the irq stack. This is only called from * task context when bottom halves are about to be reenabled and soft diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2c96c43c313a..aa381ab69a19 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -729,6 +729,7 @@ struct kvm_vcpu_arch { struct fpu_guest guest_fpu; u64 xcr0; + u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 73ca20049835..f484d656d34e 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -43,6 +43,18 @@ #endif /* __ASSEMBLY__ */ +#define __CFI_TYPE(name) \ + SYM_START(__cfi_##name, SYM_L_LOCAL, SYM_A_NONE) \ + .fill 11, 1, 0x90 ASM_NL \ + .byte 0xb8 ASM_NL \ + .long __kcfi_typeid_##name ASM_NL \ + SYM_FUNC_END(__cfi_##name) + +/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */ +#define SYM_TYPED_FUNC_START(name) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + ENDBR + /* SYM_FUNC_START -- use for global functions */ #define SYM_FUNC_START(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 97198001e567..6115bb3d5795 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -95,7 +95,7 @@ static inline unsigned char current_lock_cmos_reg(void) unsigned char rtc_cmos_read(unsigned char addr); void rtc_cmos_write(unsigned char val, unsigned char addr); -extern int mach_set_rtc_mmss(const struct timespec64 *now); +extern int mach_set_cmos_time(const struct timespec64 *now); extern void mach_get_cmos_time(struct timespec64 *now); #define RTC_IRQ 8 diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cc73061e7255..6e986088817d 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -42,6 +42,7 @@ #define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */ #define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38) #define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT) +#define MCI_STATUS_MSCOD(m) (((m) >> 16) & 0xffff) /* AMD-specific bits */ #define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 6674bdb096f3..1e086b37a307 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -155,6 +155,11 @@ * Return Stack Buffer Predictions. */ +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ + #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* * Writeback and invalidate the @@ -1054,4 +1059,12 @@ #define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 #define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 +/* x2APIC locked status */ +#define MSR_IA32_XAPIC_DISABLE_STATUS 0xBD +#define LEGACY_XAPIC_DISABLED BIT(0) /* + * x2APIC mode is locked and + * disabling x2APIC will cause + * a #GP + */ + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 89df6c6617f5..b1ab5d94881b 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -328,7 +328,7 @@ int paravirt_disable_iospace(void); * Unfortunately, this is a relatively slow operation for modern CPUs, * because it cannot necessarily determine what the destination * address is. In this case, the address is a runtime constant, so at - * the very least we can patch the call to e a simple direct call, or + * the very least we can patch the call to a simple direct call, or, * ideally, patch an inline implementation into the callsite. (Direct * calls are essentially free, because the call and return addresses * are completely predictable.) @@ -339,10 +339,10 @@ int paravirt_disable_iospace(void); * on the stack. All caller-save registers (eax,edx,ecx) are expected * to be modified (either clobbered or used for return values). * X86_64, on the other hand, already specifies a register-based calling - * conventions, returning at %rax, with parameters going on %rdi, %rsi, + * conventions, returning at %rax, with parameters going in %rdi, %rsi, * %rdx, and %rcx. Note that for this reason, x86_64 does not need any * special handling for dealing with 4 arguments, unlike i386. - * However, x86_64 also have to clobber all caller saved registers, which + * However, x86_64 also has to clobber all caller saved registers, which * unfortunately, are quite a bit (r8 - r11) * * The call instruction itself is marked by placing its start address @@ -360,22 +360,22 @@ int paravirt_disable_iospace(void); * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments. * It could be extended to more arguments, but there would be little * to be gained from that. For each number of arguments, there are - * the two VCALL and CALL variants for void and non-void functions. + * two VCALL and CALL variants for void and non-void functions. * * When there is a return value, the invoker of the macro must specify * the return type. The macro then uses sizeof() on that type to - * determine whether its a 32 or 64 bit value, and places the return + * determine whether it's a 32 or 64 bit value and places the return * in the right register(s) (just %eax for 32-bit, and %edx:%eax for - * 64-bit). For x86_64 machines, it just returns at %rax regardless of + * 64-bit). For x86_64 machines, it just returns in %rax regardless of * the return value size. * - * 64-bit arguments are passed as a pair of adjacent 32-bit arguments + * 64-bit arguments are passed as a pair of adjacent 32-bit arguments; * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments * in low,high order * * Small structures are passed and returned in registers. The macro * calling convention can't directly deal with this, so the wrapper - * functions must do this. + * functions must do it. * * These PVOP_* macros are only defined within this header. This * means that all uses must be wrapped in inline functions. This also @@ -414,8 +414,17 @@ int paravirt_disable_iospace(void); "=c" (__ecx) #define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax) -/* void functions are still allowed [re]ax for scratch */ +/* + * void functions are still allowed [re]ax for scratch. + * + * The ZERO_CALL_USED REGS feature may end up zeroing out callee-saved + * registers. Make sure we model this with the appropriate clobbers. + */ +#ifdef CONFIG_ZERO_CALL_USED_REGS +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), PVOP_VCALL_CLOBBERS +#else #define PVOP_VCALLEE_CLOBBERS "=a" (__eax) +#endif #define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS #define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11" diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 81a0211a372d..a73bced40e24 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,16 +21,6 @@ DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); -static inline struct cpumask *cpu_llc_shared_mask(int cpu) -{ - return per_cpu(cpu_llc_shared_map, cpu); -} - -static inline struct cpumask *cpu_l2c_shared_mask(int cpu) -{ - return per_cpu(cpu_l2c_shared_map, cpu); -} - DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); @@ -172,6 +162,16 @@ extern int safe_smp_processor_id(void); # define safe_smp_processor_id() smp_processor_id() #endif +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return per_cpu(cpu_llc_shared_map, cpu); +} + +static inline struct cpumask *cpu_l2c_shared_mask(int cpu) +{ + return per_cpu(cpu_l2c_shared_map, cpu); +} + #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) @@ -179,6 +179,11 @@ static inline int wbinvd_on_all_cpus(void) wbinvd(); return 0; } + +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return (struct cpumask *)cpumask_of(0); +} #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 913e593a3b45..c46207946e05 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -502,9 +502,6 @@ strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); -unsigned long __must_check clear_user(void __user *mem, unsigned long len); -unsigned long __must_check __clear_user(void __user *mem, unsigned long len); - #ifdef CONFIG_ARCH_HAS_COPY_MC unsigned long __must_check copy_mc_to_kernel(void *to, const void *from, unsigned len); @@ -526,6 +523,8 @@ extern struct movsl_mask { #define ARCH_HAS_NOCACHE_UACCESS 1 #ifdef CONFIG_X86_32 +unsigned long __must_check clear_user(void __user *mem, unsigned long len); +unsigned long __must_check __clear_user(void __user *mem, unsigned long len); # include <asm/uaccess_32.h> #else # include <asm/uaccess_64.h> diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 45697e04d771..d13d71af5cf6 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -79,4 +79,49 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } + +/* + * Zero Userspace. + */ + +__must_check unsigned long +clear_user_original(void __user *addr, unsigned long len); +__must_check unsigned long +clear_user_rep_good(void __user *addr, unsigned long len); +__must_check unsigned long +clear_user_erms(void __user *addr, unsigned long len); + +static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size) +{ + might_fault(); + stac(); + + /* + * No memory constraint because it doesn't change any memory gcc + * knows about. + */ + asm volatile( + "1:\n\t" + ALTERNATIVE_3("rep stosb", + "call clear_user_erms", ALT_NOT(X86_FEATURE_FSRM), + "call clear_user_rep_good", ALT_NOT(X86_FEATURE_ERMS), + "call clear_user_original", ALT_NOT(X86_FEATURE_REP_GOOD)) + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT + : "a" (0) + /* rep_good clobbers %rdx */ + : "rdx"); + + clac(); + + return size; +} + +static __always_inline unsigned long clear_user(void __user *to, unsigned long n) +{ + if (access_ok(to, n)) + return __clear_user(to, n); + return n; +} #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a20a5ebfacd7..1286a73ebdbc 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -139,6 +139,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o +obj-$(CONFIG_CFI_CLANG) += cfi.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 68d84cf8e001..5cadcea035e0 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1328,22 +1328,23 @@ struct bp_patching_desc { atomic_t refs; }; -static struct bp_patching_desc *bp_desc; +static struct bp_patching_desc bp_desc; static __always_inline -struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +struct bp_patching_desc *try_get_desc(void) { - /* rcu_dereference */ - struct bp_patching_desc *desc = __READ_ONCE(*descp); + struct bp_patching_desc *desc = &bp_desc; - if (!desc || !arch_atomic_inc_not_zero(&desc->refs)) + if (!arch_atomic_inc_not_zero(&desc->refs)) return NULL; return desc; } -static __always_inline void put_desc(struct bp_patching_desc *desc) +static __always_inline void put_desc(void) { + struct bp_patching_desc *desc = &bp_desc; + smp_mb__before_atomic(); arch_atomic_dec(&desc->refs); } @@ -1376,15 +1377,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs) /* * Having observed our INT3 instruction, we now must observe - * bp_desc: + * bp_desc with non-zero refcount: * - * bp_desc = desc INT3 + * bp_desc.refs = 1 INT3 * WMB RMB - * write INT3 if (desc) + * write INT3 if (bp_desc.refs != 0) */ smp_rmb(); - desc = try_get_desc(&bp_desc); + desc = try_get_desc(); if (!desc) return 0; @@ -1438,7 +1439,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs) ret = 1; out_put: - put_desc(desc); + put_desc(); return ret; } @@ -1469,18 +1470,20 @@ static int tp_vec_nr; */ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { - struct bp_patching_desc desc = { - .vec = tp, - .nr_entries = nr_entries, - .refs = ATOMIC_INIT(1), - }; unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; int do_sync; lockdep_assert_held(&text_mutex); - smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ + bp_desc.vec = tp; + bp_desc.nr_entries = nr_entries; + + /* + * Corresponds to the implicit memory barrier in try_get_desc() to + * ensure reading a non-zero refcount provides up to date bp_desc data. + */ + atomic_set_release(&bp_desc.refs, 1); /* * Corresponding read barrier in int3 notifier for making sure the @@ -1568,12 +1571,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries text_poke_sync(); /* - * Remove and synchronize_rcu(), except we have a very primitive - * refcount based completion. + * Remove and wait for refs to be zero. */ - WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ - if (!atomic_dec_and_test(&desc.refs)) - atomic_cond_read_acquire(&desc.refs, !VAL); + if (!atomic_dec_and_test(&bp_desc.refs)) + atomic_cond_read_acquire(&bp_desc.refs, !VAL); } static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6d303d1d276c..c6876d3ea4b1 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -61,6 +61,7 @@ #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/irq_regs.h> +#include <asm/cpu.h> unsigned int num_processors; @@ -1751,11 +1752,26 @@ EXPORT_SYMBOL_GPL(x2apic_mode); enum { X2APIC_OFF, - X2APIC_ON, X2APIC_DISABLED, + /* All states below here have X2APIC enabled */ + X2APIC_ON, + X2APIC_ON_LOCKED }; static int x2apic_state; +static bool x2apic_hw_locked(void) +{ + u64 ia32_cap; + u64 msr; + + ia32_cap = x86_read_arch_cap_msr(); + if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); + return (msr & LEGACY_XAPIC_DISABLED); + } + return false; +} + static void __x2apic_disable(void) { u64 msr; @@ -1793,6 +1809,10 @@ static int __init setup_nox2apic(char *str) apicid); return 0; } + if (x2apic_hw_locked()) { + pr_warn("APIC locked in x2apic mode, can't disable\n"); + return 0; + } pr_warn("x2apic already enabled.\n"); __x2apic_disable(); } @@ -1807,10 +1827,18 @@ early_param("nox2apic", setup_nox2apic); void x2apic_setup(void) { /* - * If x2apic is not in ON state, disable it if already enabled + * Try to make the AP's APIC state match that of the BSP, but if the + * BSP is unlocked and the AP is locked then there is a state mismatch. + * Warn about the mismatch in case a GP fault occurs due to a locked AP + * trying to be turned off. + */ + if (x2apic_state != X2APIC_ON_LOCKED && x2apic_hw_locked()) + pr_warn("x2apic lock mismatch between BSP and AP.\n"); + /* + * If x2apic is not in ON or LOCKED state, disable it if already enabled * from BIOS. */ - if (x2apic_state != X2APIC_ON) { + if (x2apic_state < X2APIC_ON) { __x2apic_disable(); return; } @@ -1831,6 +1859,11 @@ static __init void x2apic_disable(void) if (x2apic_id >= 255) panic("Cannot disable x2apic, id: %08x\n", x2apic_id); + if (x2apic_hw_locked()) { + pr_warn("Cannot disable locked x2apic, id: %08x\n", x2apic_id); + return; + } + __x2apic_disable(); register_lapic_address(mp_lapic_addr); } @@ -1889,7 +1922,10 @@ void __init check_x2apic(void) if (x2apic_enabled()) { pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); x2apic_mode = 1; - x2apic_state = X2APIC_ON; + if (x2apic_hw_locked()) + x2apic_state = X2APIC_ON_LOCKED; + else + x2apic_state = X2APIC_ON; } else if (!boot_cpu_has(X86_FEATURE_X2APIC)) { x2apic_state = X2APIC_DISABLED; } diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c new file mode 100644 index 000000000000..8674a5c0c031 --- /dev/null +++ b/arch/x86/kernel/cfi.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2022 Google LLC + */ +#include <asm/cfi.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <linux/string.h> + +/* + * Returns the target address and the expected type when regs->ip points + * to a compiler-generated CFI trap. + */ +static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target, + u32 *type) +{ + char buffer[MAX_INSN_SIZE]; + struct insn insn; + int offset = 0; + + *target = *type = 0; + + /* + * The compiler generates the following instruction sequence + * for indirect call checks: + * + * Â movl -<id>, %r10d ; 6 bytes + * addl -4(%reg), %r10d ; 4 bytes + * je .Ltmp1 ; 2 bytes + * ud2 ; <- regs->ip + * .Ltmp1: + * + * We can decode the expected type and the target address from the + * movl/addl instructions. + */ + if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 12, MAX_INSN_SIZE)) + return false; + if (insn_decode_kernel(&insn, &buffer[offset])) + return false; + if (insn.opcode.value != 0xBA) + return false; + + *type = -(u32)insn.immediate.value; + + if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 6, MAX_INSN_SIZE)) + return false; + if (insn_decode_kernel(&insn, &buffer[offset])) + return false; + if (insn.opcode.value != 0x3) + return false; + + /* Read the target address from the register. */ + offset = insn_get_modrm_rm_off(&insn, regs); + if (offset < 0) + return false; + + *target = *(unsigned long *)((void *)regs + offset); + + return true; +} + +/* + * Checks if a ud2 trap is because of a CFI failure, and handles the trap + * if needed. Returns a bug_trap_type value similarly to report_bug. + */ +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + unsigned long target; + u32 type; + + if (!is_cfi_trap(regs->ip)) + return BUG_TRAP_TYPE_NONE; + + if (!decode_cfi_insn(regs, &target, &type)) + return report_cfi_failure_noaddr(regs, regs->ip); + + return report_cfi_failure(regs, regs->ip, &target, type); +} + +/* + * Ensure that __kcfi_typeid_ symbols are emitted for functions that may + * not be indirectly called with all configurations. + */ +__ADDRESSABLE(__memcpy) diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index 23f5f27b5a02..485441b7f030 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -28,6 +28,9 @@ static void __init acrn_init_platform(void) { /* Setup the IDT for ACRN hypervisor callback */ alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback); + + x86_platform.calibrate_tsc = acrn_get_tsc_khz; + x86_platform.calibrate_cpu = acrn_get_tsc_khz; } static bool acrn_x2apic_available(void) diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 717192915f28..8ed341714686 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -29,15 +29,26 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) { struct mce m; + int lsb; if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) return; + /* + * Even if the ->validation_bits are set for address mask, + * to be extra safe, check and reject an error radius '0', + * and fall back to the default page size. + */ + if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK) + lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT); + else + lsb = PAGE_SHIFT; + mce_setup(&m); m.bank = -1; /* Fake a memory read error with unknown channel */ m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f; - m.misc = (MCI_MISC_ADDR_PHYS << 6) | PAGE_SHIFT; + m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb; if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 24c1bb8eb196..9f13d724172e 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,6 +12,9 @@ #include "encls.h" #include "sgx.h" +static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing); + #define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd)) /* * 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to @@ -344,8 +347,11 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, } va_page = sgx_encl_grow(encl, false); - if (IS_ERR(va_page)) + if (IS_ERR(va_page)) { + if (PTR_ERR(va_page) == -EBUSY) + vmret = VM_FAULT_NOPAGE; goto err_out_epc; + } if (va_page) list_add(&va_page->list, &encl->va_pages); @@ -914,7 +920,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, } /** - * sgx_encl_get_backing() - Pin the backing storage + * __sgx_encl_get_backing() - Pin the backing storage * @encl: an enclave pointer * @page_index: enclave page index * @backing: data for accessing backing storage for the page @@ -926,7 +932,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, * 0 on success, * -errno otherwise. */ -static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, +static int __sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); @@ -1001,7 +1007,7 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl) } /** - * sgx_encl_alloc_backing() - allocate a new backing storage page + * sgx_encl_alloc_backing() - create a new backing storage page * @encl: an enclave pointer * @page_index: enclave page index * @backing: data for accessing backing storage for the page @@ -1009,7 +1015,9 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl) * When called from ksgxd, sets the active memcg from one of the * mms in the enclave's mm_list prior to any backing page allocation, * in order to ensure that shmem page allocations are charged to the - * enclave. + * enclave. Create a backing page for loading data back into an EPC page with + * ELDU. This function takes a reference on a new backing page which + * must be dropped with a corresponding call to sgx_encl_put_backing(). * * Return: * 0 on success, @@ -1022,7 +1030,7 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, struct mem_cgroup *memcg = set_active_memcg(encl_memcg); int ret; - ret = sgx_encl_get_backing(encl, page_index, backing); + ret = __sgx_encl_get_backing(encl, page_index, backing); set_active_memcg(memcg); mem_cgroup_put(encl_memcg); @@ -1040,15 +1048,17 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, * It is the caller's responsibility to ensure that it is appropriate to use * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is * not used correctly, this will cause an allocation which is not accounted for. + * This function takes a reference on an existing backing page which must be + * dropped with a corresponding call to sgx_encl_put_backing(). * * Return: * 0 on success, * -errno otherwise. */ -int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, +static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { - return sgx_encl_get_backing(encl, page_index, backing); + return __sgx_encl_get_backing(encl, page_index, backing); } /** diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index a65a952116fd..f94ff14c9486 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -107,8 +107,6 @@ bool current_is_ksgxd(void); void sgx_encl_release(struct kref *ref); int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm); const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl); -int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, - struct sgx_backing *backing); int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing); void sgx_encl_put_backing(struct sgx_backing *backing); diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 515e2a5f25bb..0aad028f04d4 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -49,9 +49,13 @@ static LIST_HEAD(sgx_dirty_page_list); * Reset post-kexec EPC pages to the uninitialized state. The pages are removed * from the input list, and made available for the page allocator. SECS pages * prepending their children in the input list are left intact. + * + * Return 0 when sanitization was successful or kthread was stopped, and the + * number of unsanitized pages otherwise. */ -static void __sgx_sanitize_pages(struct list_head *dirty_page_list) +static unsigned long __sgx_sanitize_pages(struct list_head *dirty_page_list) { + unsigned long left_dirty = 0; struct sgx_epc_page *page; LIST_HEAD(dirty); int ret; @@ -59,7 +63,7 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) /* dirty_page_list is thread-local, no need for a lock: */ while (!list_empty(dirty_page_list)) { if (kthread_should_stop()) - return; + return 0; page = list_first_entry(dirty_page_list, struct sgx_epc_page, list); @@ -92,12 +96,14 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) } else { /* The page is not yet clean - move to the dirty list. */ list_move_tail(&page->list, &dirty); + left_dirty++; } cond_resched(); } list_splice(&dirty, dirty_page_list); + return left_dirty; } static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page) @@ -395,10 +401,7 @@ static int ksgxd(void *p) * required for SECS pages, whose child pages blocked EREMOVE. */ __sgx_sanitize_pages(&sgx_dirty_page_list); - __sgx_sanitize_pages(&sgx_dirty_page_list); - - /* sanity check: */ - WARN_ON(!list_empty(&sgx_dirty_page_list)); + WARN_ON(__sgx_sanitize_pages(&sgx_dirty_page_list)); while (!kthread_should_stop()) { if (try_to_freeze()) diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index e5dd6da78713..01833ebf5e8e 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -132,7 +132,7 @@ int irq_init_percpu_irqstack(unsigned int cpu) return 0; } -#ifndef CONFIG_PREEMPT_RT +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK void do_softirq_own_stack(void) { struct irq_stack *irqstk; diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 586f718b8e95..349046434513 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -4,11 +4,8 @@ */ #include <linux/platform_device.h> #include <linux/mc146818rtc.h> -#include <linux/acpi.h> -#include <linux/bcd.h> #include <linux/export.h> #include <linux/pnp.h> -#include <linux/of.h> #include <asm/vsyscall.h> #include <asm/x86_init.h> @@ -20,26 +17,23 @@ /* * This is a special lock that is owned by the CPU and holds the index * register we are working with. It is required for NMI access to the - * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details. + * CMOS/RTC registers. See arch/x86/include/asm/mc146818rtc.h for details. */ volatile unsigned long cmos_lock; EXPORT_SYMBOL(cmos_lock); #endif /* CONFIG_X86_32 */ -/* For two digit years assume time is always after that */ -#define CMOS_YEARS_OFFS 2000 - DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); /* - * In order to set the CMOS clock precisely, set_rtc_mmss has to be + * In order to set the CMOS clock precisely, mach_set_cmos_time has to be * called 500 ms after the second nowtime has started, because when * nowtime is written into the registers of the CMOS clock, it will * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. */ -int mach_set_rtc_mmss(const struct timespec64 *now) +int mach_set_cmos_time(const struct timespec64 *now) { unsigned long long nowtime = now->tv_sec; struct rtc_time tm; @@ -62,8 +56,7 @@ int mach_set_rtc_mmss(const struct timespec64 *now) void mach_get_cmos_time(struct timespec64 *now) { - unsigned int status, year, mon, day, hour, min, sec, century = 0; - unsigned long flags; + struct rtc_time tm; /* * If pm_trace abused the RTC as storage, set the timespec to 0, @@ -74,51 +67,13 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - spin_lock_irqsave(&rtc_lock, flags); - - /* - * If UIP is clear, then we have >= 244 microseconds before - * RTC registers will be updated. Spec sheet says that this - * is the reliable way to read RTC - registers. If UIP is set - * then the register access might be invalid. - */ - while ((CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) - cpu_relax(); - - sec = CMOS_READ(RTC_SECONDS); - min = CMOS_READ(RTC_MINUTES); - hour = CMOS_READ(RTC_HOURS); - day = CMOS_READ(RTC_DAY_OF_MONTH); - mon = CMOS_READ(RTC_MONTH); - year = CMOS_READ(RTC_YEAR); - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - century = CMOS_READ(acpi_gbl_FADT.century); -#endif - - status = CMOS_READ(RTC_CONTROL); - WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY)); - - spin_unlock_irqrestore(&rtc_lock, flags); - - if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) { - sec = bcd2bin(sec); - min = bcd2bin(min); - hour = bcd2bin(hour); - day = bcd2bin(day); - mon = bcd2bin(mon); - year = bcd2bin(year); + if (mc146818_get_time(&tm)) { + pr_err("Unable to read current time from RTC\n"); + now->tv_sec = now->tv_nsec = 0; + return; } - if (century) { - century = bcd2bin(century); - year += century * 100; - } else - year += CMOS_YEARS_OFFS; - - now->tv_sec = mktime64(year, mon, day, hour, min, sec); + now->tv_sec = rtc_tm_to_time64(&tm); now->tv_nsec = 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d62b2cb85cea..178015a820f0 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -63,6 +63,7 @@ #include <asm/insn-eval.h> #include <asm/vdso.h> #include <asm/tdx.h> +#include <asm/cfi.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -313,7 +314,8 @@ static noinstr bool handle_bug(struct pt_regs *regs) */ if (regs->flags & X86_EFLAGS_IF) raw_local_irq_enable(); - if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { regs->ip += LEN_UD2; handled = true; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index e84ee5cdbd8c..57353519bc11 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -138,7 +138,7 @@ struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu_early, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, - .set_wallclock = mach_set_rtc_mmss, + .set_wallclock = mach_set_cmos_time, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 75dcf7a72605..2796dde06302 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -315,7 +315,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; - u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { @@ -327,10 +326,16 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - guest_supported_xcr0 = + vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; + /* + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; kvm_update_pv_runtime(vcpu); @@ -897,8 +902,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = 0; } break; - case 9: - break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; union cpuid10_edx edx; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d5ec3a2ed5a4..aacb28c83e43 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4132,6 +4132,9 @@ static int em_xsetbv(struct x86_emulate_ctxt *ctxt) { u32 eax, ecx, edx; + if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSXSAVE)) + return emulate_ud(ctxt); + eax = reg_read(ctxt, VCPU_REGS_RAX); edx = reg_read(ctxt, VCPU_REGS_RDX); ecx = reg_read(ctxt, VCPU_REGS_RCX); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 126fa9aec64c..3552e6af3684 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1596,6 +1596,8 @@ static void __rmap_add(struct kvm *kvm, rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); rmap_count = pte_list_add(cache, spte, rmap_head); + if (rmap_count > kvm->stat.max_mmu_rmap_size) + kvm->stat.max_mmu_rmap_size = rmap_count; if (rmap_count > RMAP_RECYCLE_THRESHOLD) { kvm_zap_all_rmap_sptes(kvm, rmap_head); kvm_flush_remote_tlbs_with_address( @@ -5361,19 +5363,6 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } -static bool need_remote_flush(u64 old, u64 new) -{ - if (!is_shadow_present_pte(old)) - return false; - if (!is_shadow_present_pte(new)) - return true; - if ((old ^ new) & SPTE_BASE_ADDR_MASK) - return true; - old ^= shadow_nx_mask; - new ^= shadow_nx_mask; - return (old & ~new & SPTE_PERM_MASK) != 0; -} - static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) { @@ -5519,7 +5508,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL); if (gentry && sp->role.level != PG_LEVEL_4K) ++vcpu->kvm->stat.mmu_pde_zapped; - if (need_remote_flush(entry, *spte)) + if (is_shadow_present_pte(entry)) flush = true; ++spte; } @@ -6085,47 +6074,18 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, const struct kvm_memory_slot *memslot, int start_level) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); - flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, - start_level, KVM_MAX_HUGEPAGE_LEVEL, - false); + slot_handle_level(kvm, memslot, slot_rmap_write_protect, + start_level, KVM_MAX_HUGEPAGE_LEVEL, false); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); + kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); read_unlock(&kvm->mmu_lock); } - - /* - * Flush TLBs if any SPTEs had to be write-protected to ensure that - * guest writes are reflected in the dirty bitmap before the memslot - * update completes, i.e. before enabling dirty logging is visible to - * userspace. - * - * Perform the TLB flush outside the mmu_lock to reduce the amount of - * time the lock is held. However, this does mean that another CPU can - * now grab mmu_lock and encounter a write-protected SPTE while CPUs - * still have a writable mapping for the associated GFN in their TLB. - * - * This is safe but requires KVM to be careful when making decisions - * based on the write-protection status of an SPTE. Specifically, KVM - * also write-protects SPTEs to monitor changes to guest page tables - * during shadow paging, and must guarantee no CPUs can write to those - * page before the lock is dropped. As mentioned in the previous - * paragraph, a write-protected SPTE is no guarantee that CPU cannot - * perform writes. So to determine if a TLB flush is truly required, KVM - * will clear a separate software-only bit (MMU-writable) and skip the - * flush if-and-only-if this bit was already clear. - * - * See is_writable_pte() for more details. - */ - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } static inline bool need_topup(struct kvm_mmu_memory_cache *cache, int min) @@ -6493,32 +6453,30 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); /* * Clear dirty bits only on 4k SPTEs since the legacy MMU only * support dirty logging at a 4k granularity. */ - flush = slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false); + slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); + kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); read_unlock(&kvm->mmu_lock); } /* + * The caller will flush the TLBs after this function returns. + * * It's also safe to flush TLBs out of mmu lock here as currently this * function is only used for dirty logging, in which case flushing TLB * out of mmu lock also guarantees no dirty pages will be lost in * dirty_bitmap. */ - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } void kvm_mmu_zap_all(struct kvm *kvm) diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index f3744eea45f5..7670c13ce251 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -343,7 +343,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, } /* - * An shadow-present leaf SPTE may be non-writable for 3 possible reasons: + * A shadow-present leaf SPTE may be non-writable for 4 possible reasons: * * 1. To intercept writes for dirty logging. KVM write-protects huge pages * so that they can be split be split down into the dirty logging @@ -361,8 +361,13 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * read-only memslot or guest memory backed by a read-only VMA. Writes to * such pages are disallowed entirely. * - * To keep track of why a given SPTE is write-protected, KVM uses 2 - * software-only bits in the SPTE: + * 4. To emulate the Accessed bit for SPTEs without A/D bits. Note, in this + * case, the SPTE is access-protected, not just write-protected! + * + * For cases #1 and #4, KVM can safely make such SPTEs writable without taking + * mmu_lock as capturing the Accessed/Dirty state doesn't require taking it. + * To differentiate #1 and #4 from #2 and #3, KVM uses two software-only bits + * in the SPTE: * * shadow_mmu_writable_mask, aka MMU-writable - * Cleared on SPTEs that KVM is currently write-protecting for shadow paging @@ -391,7 +396,8 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * shadow page tables between vCPUs. Write-protecting an SPTE for dirty logging * (which does not clear the MMU-writable bit), does not flush TLBs before * dropping the lock, as it only needs to synchronize guest writes with the - * dirty bitmap. + * dirty bitmap. Similarly, making the SPTE inaccessible (and non-writable) for + * access-tracking via the clear_young() MMU notifier also does not flush TLBs. * * So, there is the problem: clearing the MMU-writable bit can encounter a * write-protected SPTE while CPUs still have writable mappings for that SPTE diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7f8331d6f7e..c9b49a09e6b5 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -843,8 +843,7 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; - return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, - MSR_IA32_SPEC_CTRL); + return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr); } unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 205ebdc2b11b..b0c47b41c264 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1011,15 +1011,10 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); -static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.guest_fpu.fpstate->user_xfeatures; -} - #ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) { - return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; + return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC; } #endif @@ -1042,7 +1037,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; + valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -1070,6 +1065,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { + /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { kvm_inject_gp(vcpu, 0); @@ -1557,12 +1553,32 @@ static const u32 msr_based_features_all[] = { static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_features; +/* + * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM + * does not yet virtualize. These include: + * 10 - MISC_PACKAGE_CTRLS + * 11 - ENERGY_FILTERING_CTL + * 12 - DOITM + * 18 - FB_CLEAR_CTRL + * 21 - XAPIC_DISABLE_STATUS + * 23 - OVERCLOCKING_STATUS + */ + +#define KVM_SUPPORTED_ARCH_CAP \ + (ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \ + ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ + ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ + ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO) + static u64 kvm_get_arch_capabilities(void) { u64 data = 0; - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); + data &= KVM_SUPPORTED_ARCH_CAP; + } /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that @@ -1610,9 +1626,6 @@ static u64 kvm_get_arch_capabilities(void) */ } - /* Guests don't need to know "Fill buffer clear control" exists */ - data &= ~ARCH_CAP_FB_CLEAR_CTRL; - return data; } @@ -10652,7 +10665,8 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) case KVM_MP_STATE_INIT_RECEIVED: break; default: - return -EINTR; + WARN_ON_ONCE(1); + break; } return 1; } @@ -11093,9 +11107,22 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, vcpu_load(vcpu); - if (!lapic_in_kernel(vcpu) && - mp_state->mp_state != KVM_MP_STATE_RUNNABLE) + switch (mp_state->mp_state) { + case KVM_MP_STATE_UNINITIALIZED: + case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: + case KVM_MP_STATE_INIT_RECEIVED: + case KVM_MP_STATE_SIPI_RECEIVED: + if (!lapic_in_kernel(vcpu)) + goto out; + break; + + case KVM_MP_STATE_RUNNABLE: + break; + + default: goto out; + } /* * KVM_MP_STATE_INIT_RECEIVED means the processor is in @@ -11563,7 +11590,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64), GFP_KERNEL_ACCOUNT); if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks) - goto fail_free_pio_data; + goto fail_free_mce_banks; vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, @@ -11617,7 +11644,6 @@ free_wbinvd_dirty_mask: fail_free_mce_banks: kfree(vcpu->arch.mce_banks); kfree(vcpu->arch.mci_ctl2_banks); -fail_free_pio_data: free_page((unsigned long)vcpu->arch.pio_data); fail_free_lapic: kvm_free_lapic(vcpu); @@ -12473,6 +12499,50 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } else { kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); } + + /* + * Unconditionally flush the TLBs after enabling dirty logging. + * A flush is almost always going to be necessary (see below), + * and unconditionally flushing allows the helpers to omit + * the subtly complex checks when removing write access. + * + * Do the flush outside of mmu_lock to reduce the amount of + * time mmu_lock is held. Flushing after dropping mmu_lock is + * safe as KVM only needs to guarantee the slot is fully + * write-protected before returning to userspace, i.e. before + * userspace can consume the dirty status. + * + * Flushing outside of mmu_lock requires KVM to be careful when + * making decisions based on writable status of an SPTE, e.g. a + * !writable SPTE doesn't guarantee a CPU can't perform writes. + * + * Specifically, KVM also write-protects guest page tables to + * monitor changes when using shadow paging, and must guarantee + * no CPUs can write to those page before mmu_lock is dropped. + * Because CPUs may have stale TLB entries at this point, a + * !writable SPTE doesn't guarantee CPUs can't perform writes. + * + * KVM also allows making SPTES writable outside of mmu_lock, + * e.g. to allow dirty logging without taking mmu_lock. + * + * To handle these scenarios, KVM uses a separate software-only + * bit (MMU-writable) to track if a SPTE is !writable due to + * a guest page table being write-protected (KVM clears the + * MMU-writable flag when write-protecting for shadow paging). + * + * The use of MMU-writable is also the primary motivation for + * the unconditional flush. Because KVM must guarantee that a + * CPU doesn't contain stale, writable TLB entries for a + * !MMU-writable SPTE, KVM must flush if it encounters any + * MMU-writable SPTE regardless of whether the actual hardware + * writable bit was set. I.e. KVM is almost guaranteed to need + * to flush, while unconditionally flushing allows the "remove + * write access" helpers to ignore MMU-writable entirely. + * + * See is_writable_pte() for more details (the case involving + * access-tracked SPTEs is particularly relevant). + */ + kvm_arch_flush_remote_tlbs_memslot(kvm, new); } } diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index fe59b8ac4fcc..ecbfb4dd3b01 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ #include <linux/linkage.h> +#include <asm/asm.h> #include <asm/export.h> /* @@ -50,3 +51,140 @@ SYM_FUNC_START(clear_page_erms) RET SYM_FUNC_END(clear_page_erms) EXPORT_SYMBOL_GPL(clear_page_erms) + +/* + * Default clear user-space. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + */ +SYM_FUNC_START(clear_user_original) + /* + * Copy only the lower 32 bits of size as that is enough to handle the rest bytes, + * i.e., no need for a 'q' suffix and thus a REX prefix. + */ + mov %ecx,%eax + shr $3,%rcx + jz .Lrest_bytes + + # do the qwords first + .p2align 4 +.Lqwords: + movq $0,(%rdi) + lea 8(%rdi),%rdi + dec %rcx + jnz .Lqwords + +.Lrest_bytes: + and $7, %eax + jz .Lexit + + # now do the rest bytes +.Lbytes: + movb $0,(%rdi) + inc %rdi + dec %eax + jnz .Lbytes + +.Lexit: + /* + * %rax still needs to be cleared in the exception case because this function is called + * from inline asm and the compiler expects %rax to be zero when exiting the inline asm, + * in case it might reuse it somewhere. + */ + xor %eax,%eax + RET + +.Lqwords_exception: + # convert remaining qwords back into bytes to return to caller + shl $3, %rcx + and $7, %eax + add %rax,%rcx + jmp .Lexit + +.Lbytes_exception: + mov %eax,%ecx + jmp .Lexit + + _ASM_EXTABLE_UA(.Lqwords, .Lqwords_exception) + _ASM_EXTABLE_UA(.Lbytes, .Lbytes_exception) +SYM_FUNC_END(clear_user_original) +EXPORT_SYMBOL(clear_user_original) + +/* + * Alternative clear user-space when CPU feature X86_FEATURE_REP_GOOD is + * present. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + */ +SYM_FUNC_START(clear_user_rep_good) + # call the original thing for less than a cacheline + cmp $64, %rcx + jb clear_user_original + +.Lprep: + # copy lower 32-bits for rest bytes + mov %ecx, %edx + shr $3, %rcx + jz .Lrep_good_rest_bytes + +.Lrep_good_qwords: + rep stosq + +.Lrep_good_rest_bytes: + and $7, %edx + jz .Lrep_good_exit + +.Lrep_good_bytes: + mov %edx, %ecx + rep stosb + +.Lrep_good_exit: + # see .Lexit comment above + xor %eax, %eax + RET + +.Lrep_good_qwords_exception: + # convert remaining qwords back into bytes to return to caller + shl $3, %rcx + and $7, %edx + add %rdx, %rcx + jmp .Lrep_good_exit + + _ASM_EXTABLE_UA(.Lrep_good_qwords, .Lrep_good_qwords_exception) + _ASM_EXTABLE_UA(.Lrep_good_bytes, .Lrep_good_exit) +SYM_FUNC_END(clear_user_rep_good) +EXPORT_SYMBOL(clear_user_rep_good) + +/* + * Alternative clear user-space when CPU feature X86_FEATURE_ERMS is present. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + * + */ +SYM_FUNC_START(clear_user_erms) + # call the original thing for less than a cacheline + cmp $64, %rcx + jb clear_user_original + +.Lerms_bytes: + rep stosb + +.Lerms_exit: + xorl %eax,%eax + RET + + _ASM_EXTABLE_UA(.Lerms_bytes, .Lerms_exit) +SYM_FUNC_END(clear_user_erms) +EXPORT_SYMBOL(clear_user_erms) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index d0d7b9bc6cad..dd8cd8831251 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -2,6 +2,7 @@ /* Copyright 2002 Andi Kleen */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/errno.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> @@ -27,7 +28,7 @@ * Output: * rax original destination */ -SYM_FUNC_START(__memcpy) +SYM_TYPED_FUNC_START(__memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index ad0139d25401..f1bb18617156 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -44,7 +44,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) * called from other contexts. */ pagefault_disable(); - ret = __copy_from_user_inatomic(to, from, n); + ret = raw_copy_from_user(to, from, n); pagefault_enable(); return ret; diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0ae6cf804197..6c1f8ac5e721 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -14,46 +14,6 @@ * Zero Userspace */ -unsigned long __clear_user(void __user *addr, unsigned long size) -{ - long __d0; - might_fault(); - /* no memory constraint because it doesn't change any memory gcc knows - about */ - stac(); - asm volatile( - " testq %[size8],%[size8]\n" - " jz 4f\n" - " .align 16\n" - "0: movq $0,(%[dst])\n" - " addq $8,%[dst]\n" - " decl %%ecx ; jnz 0b\n" - "4: movq %[size1],%%rcx\n" - " testl %%ecx,%%ecx\n" - " jz 2f\n" - "1: movb $0,(%[dst])\n" - " incq %[dst]\n" - " decl %%ecx ; jnz 1b\n" - "2:\n" - - _ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN8, %[size1]) - _ASM_EXTABLE_UA(1b, 2b) - - : [size8] "=&c"(size), [dst] "=&D" (__d0) - : [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr)); - clac(); - return size; -} -EXPORT_SYMBOL(__clear_user); - -unsigned long clear_user(void __user *to, unsigned long n) -{ - if (access_ok(to, n)) - return __clear_user(to, n); - return n; -} -EXPORT_SYMBOL(clear_user); - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * clean_cache_range - write back a cache range with CLWB diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index f8220fd2c169..829c1409ffbd 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -4,10 +4,12 @@ KCOV_INSTRUMENT_tlb.o := n KCOV_INSTRUMENT_mem_encrypt.o := n KCOV_INSTRUMENT_mem_encrypt_amd.o := n KCOV_INSTRUMENT_mem_encrypt_identity.o := n +KCOV_INSTRUMENT_pgprot.o := n KASAN_SANITIZE_mem_encrypt.o := n KASAN_SANITIZE_mem_encrypt_amd.o := n KASAN_SANITIZE_mem_encrypt_identity.o := n +KASAN_SANITIZE_pgprot.o := n # Disable KCSAN entirely, because otherwise we get warnings that some functions # reference __initdata sections. @@ -17,6 +19,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_mem_encrypt.o = -pg CFLAGS_REMOVE_mem_encrypt_amd.o = -pg CFLAGS_REMOVE_mem_encrypt_identity.o = -pg +CFLAGS_REMOVE_pgprot.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fa71a5d12e87..a498ae1fbe66 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -769,6 +769,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; + /* This is a racy snapshot, but it's better than nothing. */ + int cpu = raw_smp_processor_id(); if (!unhandled_signal(tsk, SIGSEGV)) return; @@ -782,6 +784,14 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, print_vma_addr(KERN_CONT " in ", regs->ip); + /* + * Dump the likely CPU where the fatal segfault happened. + * This can help identify faulty hardware. + */ + printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu, + topology_core_id(cpu), topology_physical_package_id(cpu)); + + printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 31c634a22818..58a200dc762d 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -55,6 +55,10 @@ ifdef CONFIG_RETPOLINE PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS) endif +ifdef CONFIG_CFI_CLANG +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI) +endif + CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_purgatory.o += $(PURGATORY_CFLAGS) diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index e2c5b296120d..2925074b9a58 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -56,6 +56,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "^(xen_irq_disable_direct_reloc$|" "xen_save_fl_direct_reloc$|" "VDSO|" + "__kcfi_typeid_|" "__crc_)", /* diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h index 68fd2cf526fd..f6e9f84397e7 100644 --- a/arch/x86/um/shared/sysdep/syscalls_32.h +++ b/arch/x86/um/shared/sysdep/syscalls_32.h @@ -6,10 +6,9 @@ #include <asm/unistd.h> #include <sysdep/ptrace.h> -typedef long syscall_handler_t(struct pt_regs); +typedef long syscall_handler_t(struct syscall_args); extern syscall_handler_t *sys_call_table[]; #define EXECUTE_SYSCALL(syscall, regs) \ - ((long (*)(struct syscall_args)) \ - (*sys_call_table[syscall]))(SYSCALL_ARGS(®s->regs)) + ((*sys_call_table[syscall]))(SYSCALL_ARGS(®s->regs)) diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index ac8eee093f9c..66162eafd8e8 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -65,9 +65,6 @@ static int get_free_idx(struct task_struct* task) struct thread_struct *t = &task->thread; int idx; - if (!t->arch.tls_array) - return GDT_ENTRY_TLS_MIN; - for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++) if (!t->arch.tls_array[idx].present) return idx + GDT_ENTRY_TLS_MIN; @@ -240,9 +237,6 @@ static int get_tls_entry(struct task_struct *task, struct user_desc *info, { struct thread_struct *t = &task->thread; - if (!t->arch.tls_array) - goto clear; - if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 8c0396fd0e6f..6fbe97c52c99 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -65,7 +65,7 @@ quiet_cmd_vdso = VDSO $@ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv +VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack GCOV_PROFILE := n # diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 0ed2e487a693..9b1a58dda935 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -765,6 +765,7 @@ static void xen_load_idt(const struct desc_ptr *desc) { static DEFINE_SPINLOCK(lock); static struct trap_info traps[257]; + static const struct trap_info zero = { }; unsigned out; trace_xen_cpu_load_idt(desc); @@ -774,7 +775,7 @@ static void xen_load_idt(const struct desc_ptr *desc) memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); out = xen_convert_trap_info(desc, traps, false); - memset(&traps[out], 0, sizeof(traps[0])); + traps[out] = zero; xen_mc_flush(); if (HYPERVISOR_set_trap_table(traps)) |