diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/include/asm/fpu/internal.h | 30 | ||||
-rw-r--r-- | arch/x86/include/asm/proto.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/svm.h | 2 | ||||
-rw-r--r-- | arch/x86/kernel/fpu/xstate.c | 37 | ||||
-rw-r--r-- | arch/x86/kernel/reboot.c | 3 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 8 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 6 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 6 | ||||
-rw-r--r-- | arch/x86/mm/init_64.c | 6 | ||||
-rw-r--r-- | arch/x86/tools/chkobjdump.awk | 1 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 15 | ||||
-rw-r--r-- | arch/x86/xen/p2m.c | 4 |
12 files changed, 81 insertions, 39 deletions
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 66a5e60f60c4..4fb38927128c 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -217,6 +217,14 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) } } +static inline void fxsave(struct fxregs_state *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); + else + asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); +} + /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" @@ -290,28 +298,6 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ -static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) -{ - u64 mask = -1; - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (static_cpu_has(X86_FEATURE_XSAVES)) - XSTATE_OP(XSAVES, xstate, lmask, hmask, err); - else - XSTATE_OP(XSAVE, xstate, lmask, hmask, err); - - /* We should never fault when copying to a kernel buffer: */ - WARN_ON_FPU(err); -} - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) { u64 mask = -1; diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index a4a77286cb1d..ae6f1592530b 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -3,6 +3,8 @@ #include <asm/ldt.h> +struct task_struct; + /* misc architecture specific prototypes */ void syscall_init(void); diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 6136d99f537b..c1adb2ed6d41 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -108,6 +108,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define V_IGN_TPR_SHIFT 20 #define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) +#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK) + #define V_INTR_MASKING_SHIFT 24 #define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 3fa200ecca62..1ff1adbc843b 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -293,12 +293,31 @@ static void __init setup_xstate_comp(void) } /* + * All supported features have either init state all zeros or are + * handled in setup_init_fpu() individually. This is an explicit + * feature list and does not use XFEATURE_MASK*SUPPORTED to catch + * newly added supported features at build time and make people + * actually look at the init state for the new feature. + */ +#define XFEATURES_INIT_FPSTATE_HANDLED \ + (XFEATURE_MASK_FP | \ + XFEATURE_MASK_SSE | \ + XFEATURE_MASK_YMM | \ + XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM | \ + XFEATURE_MASK_BNDREGS | \ + XFEATURE_MASK_BNDCSR) + +/* * setup the xstate image representing the init state */ static void __init setup_init_fpu_buf(void) { static int on_boot_cpu = 1; + BUILD_BUG_ON(XCNTXT_MASK != XFEATURES_INIT_FPSTATE_HANDLED); + WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -319,10 +338,22 @@ static void __init setup_init_fpu_buf(void) copy_kernel_to_xregs_booting(&init_fpstate.xsave); /* - * Dump the init state again. This is to identify the init state - * of any feature which is not represented by all zero's. + * All components are now in init state. Read the state back so + * that init_fpstate contains all non-zero init state. This only + * works with XSAVE, but not with XSAVEOPT and XSAVES because + * those use the init optimization which skips writing data for + * components in init state. + * + * XSAVE could be used, but that would require to reshuffle the + * data when XSAVES is available because XSAVES uses xstate + * compaction. But doing so is a pointless exercise because most + * components have an all zeros init state except for the legacy + * ones (FP and SSE). Those can be saved with FXSAVE into the + * legacy area. Adding new features requires to ensure that init + * state is all zeroes or if not to add the necessary handling + * here. */ - copy_xregs_to_kernel_booting(&init_fpstate.xsave); + fxsave(&init_fpstate.fxsave); } static int xfeature_is_supervisor(int xfeature_nr) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 1c2451107e49..143c06f84596 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -337,10 +337,11 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, { /* Handle problems with rebooting on the OptiPlex 990. */ .callback = set_pci_reboot, - .ident = "Dell OptiPlex 990", + .ident = "Dell OptiPlex 990 BIOS A0x", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), + DMI_MATCH(DMI_BIOS_VERSION, "A0"), }, }, { /* Handle problems with rebooting on Dell 300's */ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 13bda3fcf42b..b60ffd1b3ae2 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -611,8 +611,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); unsigned phys_as = entry->eax & 0xff; - if (!g_phys_as) + /* + * Use bare metal's MAXPHADDR if the CPU doesn't report guest + * MAXPHYADDR separately, or if TDP (NPT) is disabled, as the + * guest version "applies only to guests using nested paging". + */ + if (!g_phys_as || !tdp_enabled) g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; /* diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 931acac69703..77bee73faebc 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2564,7 +2564,11 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->nested.intercept = nested_vmcb->control.intercept; svm_flush_tlb(&svm->vcpu); - svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; + svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl & + (V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK); + + svm->vmcb->control.int_ctl |= V_INTR_MASKING_MASK; + if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; else diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4b8c83100fad..8dce61ca934b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2172,6 +2172,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; adjust_tsc_offset_guest(vcpu, adj); + /* Before back to guest, tsc_timestamp must be adjusted + * as well, otherwise guest's percpu pvclock time could jump. + */ + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } vcpu->arch.ia32_tsc_adjust_msr = data; } @@ -6724,6 +6728,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[3], 3); set_debugreg(vcpu->arch.dr6, 6); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; + } else if (unlikely(hw_breakpoint_active())) { + set_debugreg(0, 7); } kvm_x86_ops->run(vcpu); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index d76ec9348cff..547d80fc76d7 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1182,21 +1182,21 @@ int kern_addr_valid(unsigned long addr) return 0; pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + if (!pud_present(*pud)) return 0; if (pud_large(*pud)) return pfn_valid(pud_pfn(*pud)); pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + if (!pmd_present(*pmd)) return 0; if (pmd_large(*pmd)) return pfn_valid(pmd_pfn(*pmd)); pte = pte_offset_kernel(pmd, addr); - if (pte_none(*pte)) + if (!pte_present(*pte)) return 0; return pfn_valid(pte_pfn(*pte)); diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk index fd1ab80be0de..a4cf678cf5c8 100644 --- a/arch/x86/tools/chkobjdump.awk +++ b/arch/x86/tools/chkobjdump.awk @@ -10,6 +10,7 @@ BEGIN { /^GNU objdump/ { verstr = "" + gsub(/\(.*\)/, ""); for (i = 3; i <= NF; i++) if (match($(i), "^[0-9]")) { verstr = $(i); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 79aff24eed65..28725a6ed5de 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -861,8 +861,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) preempt_enable(); } -static void xen_convert_trap_info(const struct desc_ptr *desc, - struct trap_info *traps) +static unsigned xen_convert_trap_info(const struct desc_ptr *desc, + struct trap_info *traps, bool full) { unsigned in, out, count; @@ -872,17 +872,18 @@ static void xen_convert_trap_info(const struct desc_ptr *desc, for (in = out = 0; in < count; in++) { gate_desc *entry = (gate_desc*)(desc->address) + in; - if (cvt_gate_to_trap(in, entry, &traps[out])) + if (cvt_gate_to_trap(in, entry, &traps[out]) || full) out++; } - traps[out].address = 0; + + return out; } void xen_copy_trap_info(struct trap_info *traps) { const struct desc_ptr *desc = this_cpu_ptr(&idt_desc); - xen_convert_trap_info(desc, traps); + xen_convert_trap_info(desc, traps, true); } /* Load a new IDT into Xen. In principle this can be per-CPU, so we @@ -892,6 +893,7 @@ static void xen_load_idt(const struct desc_ptr *desc) { static DEFINE_SPINLOCK(lock); static struct trap_info traps[257]; + unsigned out; trace_xen_cpu_load_idt(desc); @@ -899,7 +901,8 @@ static void xen_load_idt(const struct desc_ptr *desc) memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); - xen_convert_trap_info(desc, traps); + out = xen_convert_trap_info(desc, traps, false); + memset(&traps[out], 0, sizeof(traps[0])); xen_mc_flush(); if (HYPERVISOR_set_trap_table(traps)) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 86047b18b013..af0ebe18248a 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -623,8 +623,8 @@ int xen_alloc_p2m_entry(unsigned long pfn) } /* Expanded the p2m? */ - if (pfn > xen_p2m_last_pfn) { - xen_p2m_last_pfn = pfn; + if (pfn >= xen_p2m_last_pfn) { + xen_p2m_last_pfn = ALIGN(pfn + 1, P2M_PER_PAGE); HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; } |