diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/Kconfig | 1 | ||||
-rw-r--r-- | arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 5 | ||||
-rw-r--r-- | arch/x86/include/asm/syscalls.h | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel.c | 13 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_lbr.c | 27 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.c | 17 | ||||
-rw-r--r-- | arch/x86/kernel/head64.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/head_64.S | 1 | ||||
-rw-r--r-- | arch/x86/kernel/irq.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/microcode_intel_early.c | 5 | ||||
-rw-r--r-- | arch/x86/kernel/vm86_32.c | 11 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 46 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 6 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 20 | ||||
-rw-r--r-- | arch/x86/xen/smp.c | 2 | ||||
-rw-r--r-- | arch/x86/xen/time.c | 6 |
16 files changed, 134 insertions, 37 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 15b5cef4aa3..6ef2a378e3a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -107,7 +107,6 @@ config X86 select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL if X86_64 select KTIME_SCALAR if X86_32 - select ALWAYS_USE_PERSISTENT_CLOCK select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index cf1a7ec4cc3..a59c64311d4 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -42,6 +42,7 @@ * SOFTWARE. */ +#include <asm/inst.h> #include <linux/linkage.h> ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction @@ -225,10 +226,10 @@ LABEL crc_ %i movdqa (bufp), %xmm0 # 2 consts: K1:K2 movq crc_init, %xmm1 # CRC for block 1 - pclmulqdq $0x00,%xmm0,%xmm1 # Multiply by K2 + PCLMULQDQ 0x00,%xmm0,%xmm1 # Multiply by K2 movq crc1, %xmm2 # CRC for block 2 - pclmulqdq $0x10, %xmm0, %xmm2 # Multiply by K1 + PCLMULQDQ 0x10, %xmm0, %xmm2 # Multiply by K1 pxor %xmm2,%xmm1 movq %xmm1, %rax diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 6cf0a9cc60c..5a0be0af46c 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -37,8 +37,8 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *); unsigned long sys_sigreturn(void); /* kernel/vm86_32.c */ -int sys_vm86old(struct vm86_struct __user *); -int sys_vm86(unsigned long, unsigned long); +asmlinkage long sys_vm86old(struct vm86_struct __user *); +asmlinkage long sys_vm86(unsigned long, unsigned long); #else /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index cc45deb791b..4a0a462d5e9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -125,10 +125,15 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + /* + * Errata BV98 -- MEM_*_RETIRED events can leak between counters of SMT + * siblings; disable these events because they can corrupt unrelated + * counters. + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0x0), /* MEM_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0x0), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0x0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0x0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index da02e9cc375..d978353c939 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -310,7 +310,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -318,8 +318,11 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_USER) mask |= X86_BR_USER; - if (br_type & PERF_SAMPLE_BRANCH_KERNEL) + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) { + if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EACCES; mask |= X86_BR_KERNEL; + } /* we ignore BRANCH_HV here */ @@ -339,6 +342,8 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; + + return 0; } /* @@ -386,7 +391,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - intel_pmu_setup_sw_lbr_filter(event); + ret = intel_pmu_setup_sw_lbr_filter(event); + if (ret) + return ret; /* * setup HW LBR filter, if any @@ -442,8 +449,18 @@ static int branch_type(unsigned long from, unsigned long to) return X86_BR_NONE; addr = buf; - } else - addr = (void *)from; + } else { + /* + * The LBR logs any address in the IP, even if the IP just + * faulted. This means userspace can control the from address. + * Ensure we don't blindy read any address by validating it is + * a known text address. + */ + if (kernel_text_address(from)) + addr = (void *)from; + else + return X86_BR_NONE; + } /* * decoder needs to know the ABI especially diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index b43200dbfe7..3e091f04487 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2428,7 +2428,7 @@ static void __init uncore_types_exit(struct intel_uncore_type **types) static int __init uncore_type_init(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmus; - struct attribute_group *events_group; + struct attribute_group *attr_group; struct attribute **attrs; int i, j; @@ -2455,19 +2455,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type) while (type->event_descs[i].attr.attr.name) i++; - events_group = kzalloc(sizeof(struct attribute *) * (i + 1) + - sizeof(*events_group), GFP_KERNEL); - if (!events_group) + attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + + sizeof(*attr_group), GFP_KERNEL); + if (!attr_group) goto fail; - attrs = (struct attribute **)(events_group + 1); - events_group->name = "events"; - events_group->attrs = attrs; + attrs = (struct attribute **)(attr_group + 1); + attr_group->name = "events"; + attr_group->attrs = attrs; for (j = 0; j < i; j++) attrs[j] = &type->event_descs[j].attr.attr; - type->events_group = events_group; + type->events_group = attr_group; } type->pmu_group = &uncore_pmu_attr_group; @@ -2853,6 +2853,7 @@ static int __init uncore_cpu_init(void) msr_uncores = nhm_msr_uncores; break; case 42: /* Sandy Bridge */ + case 58: /* Ivy Bridge */ if (snb_uncore_cbox.num_boxes > max_cores) snb_uncore_cbox.num_boxes = max_cores; msr_uncores = snb_msr_uncores; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index c5e403f6d86..8f3201d59b1 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -34,6 +34,7 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt = 2; +pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) @@ -99,7 +100,7 @@ again: pmd_p[i] = 0; *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } - pmd = (physaddr & PMD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL); + pmd = (physaddr & PMD_MASK) + early_pmd_flags; pmd_p[pmd_index(address)] = pmd; return 0; diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 6859e962644..08f7e803909 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -200,6 +200,7 @@ ENTRY(secondary_startup_64) btl $20,%edi /* No Execute supported? */ jnc 1f btsl $_EFER_NX, %eax + btsq $_PAGE_BIT_NX,early_pmd_flags(%rip) 1: wrmsr /* Make changes effective */ /* Setup cr0 */ diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index e4595f10591..84b778962c6 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -165,10 +165,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) u64 arch_irq_stat(void) { u64 sum = atomic_read(&irq_err_count); - -#ifdef CONFIG_X86_IO_APIC - sum += atomic_read(&irq_mis_count); -#endif return sum; } diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c index d893e8ed8ac..2e9e12871c2 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/microcode_intel_early.c @@ -487,6 +487,7 @@ static inline void show_saved_mc(void) #endif #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) +static DEFINE_MUTEX(x86_cpu_microcode_mutex); /* * Save this mc into mc_saved_data. So it will be loaded early when a CPU is * hot added or resumes. @@ -507,7 +508,7 @@ int save_mc_for_early(u8 *mc) * Hold hotplug lock so mc_saved_data is not accessed by a CPU in * hotplug. */ - cpu_hotplug_driver_lock(); + mutex_lock(&x86_cpu_microcode_mutex); mc_saved_count_init = mc_saved_data.mc_saved_count; mc_saved_count = mc_saved_data.mc_saved_count; @@ -544,7 +545,7 @@ int save_mc_for_early(u8 *mc) } out: - cpu_hotplug_driver_unlock(); + mutex_unlock(&x86_cpu_microcode_mutex); return ret; } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 1cf5766dde1..3dbdd9c839d 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -33,6 +33,7 @@ #include <linux/capability.h> #include <linux/errno.h> #include <linux/interrupt.h> +#include <linux/syscalls.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/signal.h> @@ -48,7 +49,6 @@ #include <asm/io.h> #include <asm/tlbflush.h> #include <asm/irq.h> -#include <asm/syscalls.h> /* * Known problems: @@ -202,17 +202,16 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); -int sys_vm86old(struct vm86_struct __user *v86) +SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, v86) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. * This remains on the stack until we * return to 32 bit user space. */ - struct task_struct *tsk; + struct task_struct *tsk = current; int tmp, ret = -EPERM; - tsk = current; if (tsk->thread.saved_sp0) goto out; tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, @@ -227,11 +226,12 @@ int sys_vm86old(struct vm86_struct __user *v86) do_sys_vm86(&info, tsk); ret = 0; /* we never return here */ out: + asmlinkage_protect(1, ret, v86); return ret; } -int sys_vm86(unsigned long cmd, unsigned long arg) +SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. @@ -278,6 +278,7 @@ int sys_vm86(unsigned long cmd, unsigned long arg) do_sys_vm86(&info, tsk); ret = 0; /* we never return here */ out: + asmlinkage_protect(2, ret, cmd, arg); return ret; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a335cc6cde7..59622c9cc63 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -60,6 +60,7 @@ #define OpGS 25ull /* GS */ #define OpMem8 26ull /* 8-bit zero extended memory operand */ #define OpImm64 27ull /* Sign extended 16/32/64-bit immediate */ +#define OpXLat 28ull /* memory at BX/EBX/RBX + zero-extended AL */ #define OpBits 5 /* Width of operand field */ #define OpMask ((1ull << OpBits) - 1) @@ -99,6 +100,7 @@ #define SrcImmUByte (OpImmUByte << SrcShift) #define SrcImmU (OpImmU << SrcShift) #define SrcSI (OpSI << SrcShift) +#define SrcXLat (OpXLat << SrcShift) #define SrcImmFAddr (OpImmFAddr << SrcShift) #define SrcMemFAddr (OpMemFAddr << SrcShift) #define SrcAcc (OpAcc << SrcShift) @@ -532,6 +534,9 @@ FOP_SETCC(setle) FOP_SETCC(setnle) FOP_END; +FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET +FOP_END; + #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex) \ do { \ unsigned long _tmp; \ @@ -2986,6 +2991,28 @@ static int em_das(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_aam(struct x86_emulate_ctxt *ctxt) +{ + u8 al, ah; + + if (ctxt->src.val == 0) + return emulate_de(ctxt); + + al = ctxt->dst.val & 0xff; + ah = al / ctxt->src.val; + al %= ctxt->src.val; + + ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al | (ah << 8); + + /* Set PF, ZF, SF */ + ctxt->src.type = OP_IMM; + ctxt->src.val = 0; + ctxt->src.bytes = 1; + fastop(ctxt, em_or); + + return X86EMUL_CONTINUE; +} + static int em_aad(struct x86_emulate_ctxt *ctxt) { u8 al = ctxt->dst.val & 0xff; @@ -3926,7 +3953,10 @@ static const struct opcode opcode_table[256] = { /* 0xD0 - 0xD7 */ G(Src2One | ByteOp, group2), G(Src2One, group2), G(Src2CL | ByteOp, group2), G(Src2CL, group2), - N, I(DstAcc | SrcImmByte | No64, em_aad), N, N, + I(DstAcc | SrcImmUByte | No64, em_aam), + I(DstAcc | SrcImmUByte | No64, em_aad), + F(DstAcc | ByteOp | No64, em_salc), + I(DstAcc | SrcXLat | ByteOp, em_mov), /* 0xD8 - 0xDF */ N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N, /* 0xE0 - 0xE7 */ @@ -4162,6 +4192,10 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, break; case OpMem8: ctxt->memop.bytes = 1; + if (ctxt->memop.type == OP_REG) { + ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1); + fetch_register_operand(&ctxt->memop); + } goto mem_common; case OpMem16: ctxt->memop.bytes = 2; @@ -4184,6 +4218,16 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, op->val = 0; op->count = 1; break; + case OpXLat: + op->type = OP_MEM; + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.mem.ea = + register_address(ctxt, + reg_read(ctxt, VCPU_REGS_RBX) + + (reg_read(ctxt, VCPU_REGS_RAX) & 0xff)); + op->addr.mem.seg = seg_override(ctxt); + op->val = 0; + break; case OpImmFAddr: op->type = OP_IMM; op->addr.mem.ea = ctxt->_eip; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6667042714c..0af18077012 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5197,6 +5197,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) return 0; } + if (vcpu->arch.halt_request) { + vcpu->arch.halt_request = 0; + ret = kvm_emulate_halt(vcpu); + goto out; + } + if (signal_pending(current)) goto out; if (need_resched()) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c8e1c7b95c3..cf95e192d05 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -156,6 +156,21 @@ static void xen_vcpu_setup(int cpu) BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); + /* + * This path is called twice on PVHVM - first during bootup via + * smp_init -> xen_hvm_cpu_notify, and then if the VCPU is being + * hotplugged: cpu_up -> xen_hvm_cpu_notify. + * As we can only do the VCPUOP_register_vcpu_info once lets + * not over-write its result. + * + * For PV it is called during restore (xen_vcpu_restore) and bootup + * (xen_setup_vcpu_info_placement). The hotplug mechanism does not + * use this function. + */ + if (xen_hvm_domain()) { + if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu)) + return; + } if (cpu < MAX_VIRT_CPUS) per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; @@ -1589,8 +1604,11 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: xen_vcpu_setup(cpu); - if (xen_have_vector_callback) + if (xen_have_vector_callback) { xen_init_lock_cpu(cpu); + if (xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_setup_timer(cpu); + } break; default: break; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 09ea61d2e02..22c800af180 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -662,6 +662,8 @@ static void xen_hvm_cpu_die(unsigned int cpu) unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); native_cpu_die(cpu); } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 0296a952250..054cc01bb84 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -497,7 +497,11 @@ static void xen_hvm_setup_cpu_clockevents(void) { int cpu = smp_processor_id(); xen_setup_runstate_info(cpu); - xen_setup_timer(cpu); + /* + * xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence + * doing it xen_hvm_cpu_notify (which gets called by smp_init during + * early bootup and also during CPU hotplug events). + */ xen_setup_cpu_clockevents(); } |