diff options
Diffstat (limited to 'arch/x86')
66 files changed, 874 insertions, 464 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4e001bbbb425..d9830e7e1060 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -339,6 +339,11 @@ config NEED_PER_CPU_PAGE_FIRST_CHUNK config ARCH_HIBERNATION_POSSIBLE def_bool y +config ARCH_NR_GPIO + int + default 1024 if X86_64 + default 512 + config ARCH_SUSPEND_POSSIBLE def_bool y @@ -1400,7 +1405,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 + depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6 select X86_PAE help Select this if you have a 32-bit processor and more than 4 @@ -1520,7 +1525,6 @@ config AMD_MEM_ENCRYPT config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT bool "Activate AMD Secure Memory Encryption (SME) by default" - default y depends on AMD_MEM_ENCRYPT help Say yes to have system memory encrypted by default if running on @@ -2605,7 +2609,6 @@ config PCI_OLPC config PCI_XEN def_bool y depends on PCI && XEN - select SWIOTLB_XEN config MMCONF_FAM10H def_bool y @@ -2828,8 +2831,6 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 -source "drivers/firmware/Kconfig" - source "arch/x86/kvm/Kconfig" source "arch/x86/Kconfig.assembler" diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index e7355f8b51c2..94834c4b5e5e 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -4,6 +4,12 @@ tune = $(call cc-option,-mtune=$(1),$(2)) +ifdef CONFIG_CC_IS_CLANG +align := -falign-functions=0 $(call cc-option,-falign-jumps=0) $(call cc-option,-falign-loops=0) +else +align := -falign-functions=0 -falign-jumps=0 -falign-loops=0 +endif + cflags-$(CONFIG_M486SX) += -march=i486 cflags-$(CONFIG_M486) += -march=i486 cflags-$(CONFIG_M586) += -march=i586 @@ -19,11 +25,11 @@ cflags-$(CONFIG_MK6) += -march=k6 # They make zero difference whatsosever to performance at this time. cflags-$(CONFIG_MK7) += -march=athlon cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) -cflags-$(CONFIG_MCRUSOE) += -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0 -cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0 +cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align) +cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align) cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586) -cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) -falign-functions=0 -falign-jumps=0 -falign-loops=0 +cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align) cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) cflags-$(CONFIG_MVIAC7) += -march=i686 cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index fa2c3f50aecb..18d2f5199194 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -367,10 +367,11 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8) * %rdx: src (1..8 blocks) * %rcx: num blocks (1..8) */ - FRAME_BEGIN - cmpq $5, %rcx; jb sm4_aesni_avx_crypt4; + + FRAME_BEGIN + vmovdqu (0 * 16)(%rdx), RA0; vmovdqu (1 * 16)(%rdx), RA1; vmovdqu (2 * 16)(%rdx), RA2; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..6dfa8ddaa60f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2465,6 +2465,7 @@ static int x86_pmu_event_init(struct perf_event *event) if (err) { if (event->destroy) event->destroy(event); + event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..9a044438072b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -263,6 +263,7 @@ static struct event_constraint intel_icl_event_constraints[] = { INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT(0xef, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), EVENT_CONSTRAINT_END }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index c853b28efa33..96c775abe31f 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -68,6 +68,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_D: case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: + case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 90e682a92820..db2d92fb44da 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -99,7 +99,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val) /* * IPI implementation on Hyper-V. */ -static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) +static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, + bool exclude_self) { struct hv_send_ipi_ex **arg; struct hv_send_ipi_ex *ipi_arg; @@ -121,14 +122,27 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) ipi_arg->reserved = 0; ipi_arg->vp_set.valid_bank_mask = 0; - if (!cpumask_equal(mask, cpu_present_mask)) { + /* + * Use HV_GENERIC_SET_ALL and avoid converting cpumask to VP_SET + * when the IPI is sent to all currently present CPUs. + */ + if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); - } - if (nr_bank < 0) - goto ipi_mask_ex_done; - if (!nr_bank) + if (exclude_self) + nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask); + else + nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); + + /* + * 'nr_bank <= 0' means some CPUs in cpumask can't be + * represented in VP_SET. Return an error and fall back to + * native (architectural) method of sending IPIs. + */ + if (nr_bank <= 0) + goto ipi_mask_ex_done; + } else { ipi_arg->vp_set.format = HV_GENERIC_SET_ALL; + } status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank, ipi_arg, NULL); @@ -138,15 +152,25 @@ ipi_mask_ex_done: return hv_result_success(status); } -static bool __send_ipi_mask(const struct cpumask *mask, int vector) +static bool __send_ipi_mask(const struct cpumask *mask, int vector, + bool exclude_self) { - int cur_cpu, vcpu; + int cur_cpu, vcpu, this_cpu = smp_processor_id(); struct hv_send_ipi ipi_arg; u64 status; + unsigned int weight; trace_hyperv_send_ipi_mask(mask, vector); - if (cpumask_empty(mask)) + weight = cpumask_weight(mask); + + /* + * Do nothing if + * 1. the mask is empty + * 2. the mask only contains self when exclude_self is true + */ + if (weight == 0 || + (exclude_self && weight == 1 && cpumask_test_cpu(this_cpu, mask))) return true; if (!hv_hypercall_pg) @@ -172,6 +196,8 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) ipi_arg.cpu_mask = 0; for_each_cpu(cur_cpu, mask) { + if (exclude_self && cur_cpu == this_cpu) + continue; vcpu = hv_cpu_number_to_vp_number(cur_cpu); if (vcpu == VP_INVAL) return false; @@ -191,7 +217,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) return hv_result_success(status); do_ex_hypercall: - return __send_ipi_mask_ex(mask, vector); + return __send_ipi_mask_ex(mask, vector, exclude_self); } static bool __send_ipi_one(int cpu, int vector) @@ -208,7 +234,7 @@ static bool __send_ipi_one(int cpu, int vector) return false; if (vp >= 64) - return __send_ipi_mask_ex(cpumask_of(cpu), vector); + return __send_ipi_mask_ex(cpumask_of(cpu), vector, false); status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp)); return hv_result_success(status); @@ -222,20 +248,13 @@ static void hv_send_ipi(int cpu, int vector) static void hv_send_ipi_mask(const struct cpumask *mask, int vector) { - if (!__send_ipi_mask(mask, vector)) + if (!__send_ipi_mask(mask, vector, false)) orig_apic.send_IPI_mask(mask, vector); } static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) { - unsigned int this_cpu = smp_processor_id(); - struct cpumask new_mask; - const struct cpumask *local_mask; - - cpumask_copy(&new_mask, mask); - cpumask_clear_cpu(this_cpu, &new_mask); - local_mask = &new_mask; - if (!__send_ipi_mask(local_mask, vector)) + if (!__send_ipi_mask(mask, vector, true)) orig_apic.send_IPI_mask_allbutself(mask, vector); } @@ -246,7 +265,7 @@ static void hv_send_ipi_allbutself(int vector) static void hv_send_ipi_all(int vector) { - if (!__send_ipi_mask(cpu_online_mask, vector)) + if (!__send_ipi_mask(cpu_online_mask, vector, false)) orig_apic.send_IPI_all(vector); } diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 14ebd2196569..43184640b579 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -25,7 +25,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) * For !SMAP hardware we patch out CLAC on entry. */ if (boot_cpu_has(X86_FEATURE_SMAP) || - (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV))) + (IS_ENABLED(CONFIG_64BIT) && boot_cpu_has(X86_FEATURE_XENPV))) mask |= X86_EFLAGS_AC; WARN_ON_ONCE(flags & mask); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8f48a7ec577..5a0298aa56ba 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -702,7 +702,8 @@ struct kvm_vcpu_arch { struct kvm_pio_request pio; void *pio_data; - void *guest_ins_data; + void *sev_pio_data; + unsigned sev_pio_count; u8 event_exit_inst_len; diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 87bd6025d91d..6a5f3acf2b33 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -46,7 +46,7 @@ struct kvm_page_track_notifier_node { struct kvm_page_track_notifier_node *node); }; -void kvm_page_track_init(struct kvm *kvm); +int kvm_page_track_init(struct kvm *kvm); void kvm_page_track_cleanup(struct kvm *kvm); void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index eceea9299097..6c5765192102 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -2,6 +2,20 @@ #ifndef _ASM_X86_KVM_CLOCK_H #define _ASM_X86_KVM_CLOCK_H +#include <linux/percpu.h> + extern struct clocksource kvm_clock; +DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} + #endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 5c7bcaa79623..1d5f14aff5f6 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H -#define ARCH_DEFAULT_PKEY 0 - /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index f3fbb84ff8a7..68c257a3de0d 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -275,7 +275,7 @@ static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } __iomem *__dst = dst; - int zf; + bool zf; /* * ENQCMDS %(rdx), rax diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index c9fa7be3df82..5c95d242f38d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -301,8 +301,8 @@ do { \ unsigned int __gu_low, __gu_high; \ const unsigned int __user *__gu_ptr; \ __gu_ptr = (const void __user *)(ptr); \ - __get_user_asm(__gu_low, ptr, "l", "=r", label); \ - __get_user_asm(__gu_high, ptr+1, "l", "=r", label); \ + __get_user_asm(__gu_low, __gu_ptr, "l", "=r", label); \ + __get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label); \ (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ } while (0) #else diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 3506d8c598c1..4557f7cb0fa6 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -14,16 +14,19 @@ static inline int pci_xen_hvm_init(void) return -1; } #endif -#if defined(CONFIG_XEN_DOM0) +#ifdef CONFIG_XEN_PV_DOM0 int __init pci_xen_initial_domain(void); -int xen_find_device_domain_owner(struct pci_dev *dev); -int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); -int xen_unregister_device_domain_owner(struct pci_dev *dev); #else static inline int __init pci_xen_initial_domain(void) { return -1; } +#endif +#ifdef CONFIG_XEN_DOM0 +int xen_find_device_domain_owner(struct pci_dev *dev); +int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); +int xen_unregister_device_domain_owner(struct pci_dev *dev); +#else static inline int xen_find_device_domain_owner(struct pci_dev *dev) { return -1; diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h index 6b56d0d45d15..66b4ddde7743 100644 --- a/arch/x86/include/asm/xen/swiotlb-xen.h +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -3,14 +3,10 @@ #define _ASM_X86_SWIOTLB_XEN_H #ifdef CONFIG_SWIOTLB_XEN -extern int xen_swiotlb; extern int __init pci_xen_swiotlb_detect(void); -extern void __init pci_xen_swiotlb_init(void); extern int pci_xen_swiotlb_init_late(void); #else -#define xen_swiotlb (0) -static inline int __init pci_xen_swiotlb_detect(void) { return 0; } -static inline void __init pci_xen_swiotlb_init(void) { } +#define pci_xen_swiotlb_detect NULL static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; } #endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 14bcd59bcdee..5b6d1a95776f 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -62,6 +62,7 @@ int acpi_fix_pin2_polarity __initdata; #ifdef CONFIG_X86_LOCAL_APIC static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; +static bool acpi_support_online_capable; #endif #ifdef CONFIG_X86_IO_APIC @@ -138,6 +139,8 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) pr_debug("Local APIC address 0x%08x\n", madt->address); } + if (madt->header.revision >= 5) + acpi_support_online_capable = true; default_acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id); @@ -239,6 +242,12 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) if (processor->id == 0xff) return 0; + /* don't register processors that can not be onlined */ + if (acpi_support_online_capable && + !(processor->lapic_flags & ACPI_MADT_ENABLED) && + !(processor->lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 7de599eba7f0..7945eae5b315 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -79,6 +79,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, */ flags->bm_control = 0; } + if (c->x86_vendor == X86_VENDOR_AMD && c->x86 >= 0x17) { + /* + * For all AMD Zen or newer CPUs that support C3, caches + * should not be flushed by software while entering C3 + * type state. Set bm->check to 1 so that kernel doesn't + * need to execute cache flush operation. + */ + flags->bm_check = 1; + /* + * In current AMD C state implementation ARB_DIS is no longer + * used. So set bm_control to zero to indicate ARB_DIS is not + * required while entering C3 type state. + */ + flags->bm_control = 0; + } } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0f8885949e8c..b3410f1ac217 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -326,6 +326,7 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_SMAP cr4_set_bits(X86_CR4_SMAP); #else + clear_cpu_cap(c, X86_FEATURE_SMAP); cr4_clear_bits(X86_CR4_SMAP); #endif } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 8cb7816d03b4..193204aee880 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin static void kill_me_now(struct callback_head *ch) { + struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me); + + p->mce_count = 0; force_sig(SIGBUS); } @@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb) int flags = MF_ACTION_REQUIRED; int ret; + p->mce_count = 0; pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); if (!p->mce_ripv) @@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb) } } -static void queue_task_work(struct mce *m, int kill_current_task) +static void queue_task_work(struct mce *m, char *msg, int kill_current_task) { - current->mce_addr = m->addr; - current->mce_kflags = m->kflags; - current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); - current->mce_whole_page = whole_page(m); + int count = ++current->mce_count; - if (kill_current_task) - current->mce_kill_me.func = kill_me_now; - else - current->mce_kill_me.func = kill_me_maybe; + /* First call, save all the details */ + if (count == 1) { + current->mce_addr = m->addr; + current->mce_kflags = m->kflags; + current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); + current->mce_whole_page = whole_page(m); + + if (kill_current_task) + current->mce_kill_me.func = kill_me_now; + else + current->mce_kill_me.func = kill_me_maybe; + } + + /* Ten is likely overkill. Don't expect more than two faults before task_work() */ + if (count > 10) + mce_panic("Too many consecutive machine checks while accessing user data", m, msg); + + /* Second or later call, make sure page address matches the one from first call */ + if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT)) + mce_panic("Consecutive machine checks to different user pages", m, msg); + + /* Do not call task_work_add() more than once */ + if (count > 1) + return; task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); } @@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } else { /* @@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } out: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 4b8813bafffd..bb1c3f5f60c8 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -527,12 +527,14 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) rdt_domain_reconfigure_cdp(r); if (r->alloc_capable && domain_setup_ctrlval(r, d)) { - kfree(d); + kfree(hw_dom); return; } if (r->mon_capable && domain_setup_mon_state(r, d)) { - kfree(d); + kfree(hw_dom->ctrl_val); + kfree(hw_dom->mbps_val); + kfree(hw_dom); return; } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 38837dad46e6..391a4e2b8604 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -714,12 +714,6 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x3e20, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x3ec4, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x8a12, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 445c57c9c539..831b25c5e705 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -379,9 +379,14 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, sizeof(fpu->state.fxsave))) return -EFAULT; - /* Reject invalid MXCSR values. */ - if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask) - return -EINVAL; + if (IS_ENABLED(CONFIG_X86_64)) { + /* Reject invalid MXCSR values. */ + if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask) + return -EINVAL; + } else { + /* Mask invalid bits out for historical reasons (broken hardware). */ + fpu->state.fxsave.mxcsr &= mxcsr_feature_mask; + } /* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */ if (use_xsave()) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 42fc41dd0e1f..882213df3713 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -10,6 +10,7 @@ #include <asm/irq_remapping.h> #include <asm/hpet.h> #include <asm/time.h> +#include <asm/mwait.h> #undef pr_fmt #define pr_fmt(fmt) "hpet: " fmt @@ -916,6 +917,83 @@ static bool __init hpet_counting(void) return false; } +static bool __init mwait_pc10_supported(void) +{ + unsigned int eax, ebx, ecx, mwait_substates; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + if (!cpu_feature_enabled(X86_FEATURE_MWAIT)) + return false; + + if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) + return false; + + cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates); + + return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) && + (ecx & CPUID5_ECX_INTERRUPT_BREAK) && + (mwait_substates & (0xF << 28)); +} + +/* + * Check whether the system supports PC10. If so force disable HPET as that + * stops counting in PC10. This check is overbroad as it does not take any + * of the following into account: + * + * - ACPI tables + * - Enablement of intel_idle + * - Command line arguments which limit intel_idle C-state support + * + * That's perfectly fine. HPET is a piece of hardware designed by committee + * and the only reasons why it is still in use on modern systems is the + * fact that it is impossible to reliably query TSC and CPU frequency via + * CPUID or firmware. + * + * If HPET is functional it is useful for calibrating TSC, but this can be + * done via PMTIMER as well which seems to be the last remaining timer on + * X86/INTEL platforms that has not been completely wreckaged by feature + * creep. + * + * In theory HPET support should be removed altogether, but there are older + * systems out there which depend on it because TSC and APIC timer are + * dysfunctional in deeper C-states. + * + * It's only 20 years now that hardware people have been asked to provide + * reliable and discoverable facilities which can be used for timekeeping + * and per CPU timer interrupts. + * + * The probability that this problem is going to be solved in the + * forseeable future is close to zero, so the kernel has to be cluttered + * with heuristics to keep up with the ever growing amount of hardware and + * firmware trainwrecks. Hopefully some day hardware people will understand + * that the approach of "This can be fixed in software" is not sustainable. + * Hope dies last... + */ +static bool __init hpet_is_pc10_damaged(void) +{ + unsigned long long pcfg; + + /* Check whether PC10 substates are supported */ + if (!mwait_pc10_supported()) + return false; + + /* Check whether PC10 is enabled in PKG C-state limit */ + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg); + if ((pcfg & 0xF) < 8) + return false; + + if (hpet_force_user) { + pr_warn("HPET force enabled via command line, but dysfunctional in PC10.\n"); + return false; + } + + pr_info("HPET dysfunctional in PC10. Force disabled.\n"); + boot_hpet_disable = true; + return true; +} + /** * hpet_enable - Try to setup the HPET timer. Returns 1 on success. */ @@ -929,6 +1007,9 @@ int __init hpet_enable(void) if (!is_hpet_capable()) return 0; + if (hpet_is_pc10_damaged()) + return 0; + hpet_set_mapping(); if (!hpet_virt_address) return 0; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index ad273e5861c1..73c74b961d0f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); static struct pvclock_vsyscall_time_info hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); static struct pvclock_wall_clock wall_clock __bss_decrypted; -static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static struct pvclock_vsyscall_time_info *hvclock_mem; - -static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) -{ - return &this_cpu_read(hv_clock_per_cpu)->pvti; -} - -static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) -{ - return this_cpu_read(hv_clock_per_cpu); -} +DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu); /* * The wallclock is the time of day when we booted. Since then, some time may diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 79f164141116..40ed44ead063 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -830,6 +830,20 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); + /* + * Do some memory reservations *before* memory is added to memblock, so + * memblock allocations won't overwrite it. + * + * After this point, everything still needed from the boot loader or + * firmware or kernel text should be early reserved or marked not RAM in + * e820. All other memory is free game. + * + * This call needs to happen before e820__memory_setup() which calls the + * xen_memory_setup() on Xen dom0 which relies on the fact that those + * early reservations have happened already. + */ + early_reserve_memory(); + iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; e820__memory_setup(); parse_setup_data(); @@ -876,18 +890,6 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); - /* - * Do some memory reservations *before* memory is added to - * memblock, so memblock allocations won't overwrite it. - * Do it after early param, so we could get (unlikely) panic from - * serial. - * - * After this point everything still needed from the boot loader or - * firmware or kernel text should be early reserved or marked not - * RAM in e820. All other memory is free game. - */ - early_reserve_memory(); - #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 78a32b956e81..5afd98559193 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_free_ptr(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 9f90f460a28c..bf1033a62e48 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -130,6 +130,8 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, } else { ret = ES_VMM_ERROR; } + } else if (ghcb->save.sw_exit_info_1 & 0xffffffff) { + ret = ES_VMM_ERROR; } else { ret = ES_OK; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index fe03bd978761..751aa85a3001 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( for (i = 0; i < nent; i++) { e = &entries[i]; - if (e->function == function && (e->index == index || - !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + if (e->function == function && + (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)) return e; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2837110e66ed..9a144ca8e146 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -435,7 +435,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); __FOP_RET(#op) asm(".pushsection .fixup, \"ax\"\n" - ".global kvm_fastop_exception \n" "kvm_fastop_exception: xor %esi, %esi; ret\n" ".popsection"); @@ -4206,7 +4205,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt) u64 cr4 = ctxt->ops->get_cr(ctxt, 4); if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt)) - return emulate_ud(ctxt); + return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 232a86a6faaf..d5124b520f76 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_init(&hv_vcpu->stimer[i], i); - hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); + hv_vcpu->vp_index = vcpu->vcpu_idx; return 0; } @@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); - int vcpu_idx = kvm_vcpu_get_idx(vcpu); u32 new_vp_index = (u32)data; if (!host || new_vp_index >= KVM_MAX_VCPUS) @@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) * VP index is changing, adjust num_mismatched_vp_indexes if * it now matches or no longer matches vcpu_idx. */ - if (hv_vcpu->vp_index == vcpu_idx) + if (hv_vcpu->vp_index == vcpu->vcpu_idx) atomic_inc(&hv->num_mismatched_vp_indexes); - else if (new_vp_index == vcpu_idx) + else if (new_vp_index == vcpu->vcpu_idx) atomic_dec(&hv->num_mismatched_vp_indexes); hv_vcpu->vp_index = new_vp_index; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 730da8537d05..ed1c4e546d04 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu); + return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx; } int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index ff005fe738a4..8c065da73f8e 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -319,8 +319,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) unsigned index; bool mask_before, mask_after; union kvm_ioapic_redirect_entry *e; - unsigned long vcpu_bitmap; int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; + DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS); switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -384,9 +384,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) irq.shorthand = APIC_DEST_NOSHORT; irq.dest_id = e->fields.dest_id; irq.msi_redir_hint = false; - bitmap_zero(&vcpu_bitmap, 16); + bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); if (old_dest_mode != e->fields.dest_mode || old_dest_id != e->fields.dest_id) { /* @@ -399,10 +399,10 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) kvm_lapic_irq_dest_mode( !!e->fields.dest_mode); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); } kvm_make_scan_ioapic_request_mask(ioapic->kvm, - &vcpu_bitmap); + vcpu_bitmap); } else { kvm_make_scan_ioapic_request(ioapic->kvm); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 76fb00921203..d6ac32f3f650 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2321,13 +2321,14 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_apicv); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic = vcpu->arch.apic; + u64 msr_val; int i; if (!init_event) { - vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; + msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) - vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; + msr_val |= MSR_IA32_APICBASE_BSP; + kvm_lapic_set_base(vcpu, msr_val); } if (!apic) @@ -2336,11 +2337,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - if (!init_event) { - apic->base_address = APIC_DEFAULT_PHYS_BASE; - + /* The xAPIC ID is set at RESET even if the APIC was already enabled. */ + if (!init_event) kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); - } kvm_apic_set_version(apic->vcpu); for (i = 0; i < KVM_APIC_LVT_NUM; i++) @@ -2481,6 +2480,11 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) lapic_timer_advance_dynamic = false; } + /* + * Stuff the APIC ENABLE bit in lieu of temporarily incrementing + * apic_hw_disabled; the full RESET value is set by kvm_lapic_reset(). + */ + vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_iodevice_init(&apic->dev, &apic_mmio_ops); @@ -2942,5 +2946,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu) void kvm_lapic_exit(void) { static_key_deferred_flush(&apic_hw_disabled); + WARN_ON(static_branch_unlikely(&apic_hw_disabled.key)); static_key_deferred_flush(&apic_sw_disabled); + WARN_ON(static_branch_unlikely(&apic_sw_disabled.key)); } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2d7e61122af8..0cc58901bf7a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2027,8 +2027,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) } while (!sp->unsync_children); } -static void mmu_sync_children(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *parent) +static int mmu_sync_children(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *parent, bool can_yield) { int i; struct kvm_mmu_page *sp; @@ -2055,12 +2055,18 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + if (!can_yield) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + return -EINTR; + } + cond_resched_rwlock_write(&vcpu->kvm->mmu_lock); flush = false; } } kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + return 0; } static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) @@ -2146,9 +2152,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (sp->unsync_children) - kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - __clear_sp_write_flooding_count(sp); trace_get_page: @@ -3684,7 +3687,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); write_unlock(&vcpu->kvm->mmu_lock); @@ -3700,7 +3703,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) if (IS_VALID_PAE_ROOT(root)) { root &= PT64_BASE_ADDR_MASK; sp = to_shadow_page(root); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); } } @@ -4593,10 +4596,10 @@ static void update_pkru_bitmask(struct kvm_mmu *mmu) unsigned bit; bool wp; - if (!is_cr4_pke(mmu)) { - mmu->pkru_mask = 0; + mmu->pkru_mask = 0; + + if (!is_cr4_pke(mmu)) return; - } wp = is_cr0_wp(mmu); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 269f11f92fd0..21427e84a82e 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -164,13 +164,13 @@ void kvm_page_track_cleanup(struct kvm *kvm) cleanup_srcu_struct(&head->track_srcu); } -void kvm_page_track_init(struct kvm *kvm) +int kvm_page_track_init(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; head = &kvm->arch.track_notifier_head; - init_srcu_struct(&head->track_srcu); INIT_HLIST_HEAD(&head->track_notifier_list); + return init_srcu_struct(&head->track_srcu); } /* diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 7d03e9b7ccfa..913d52a7923e 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -707,8 +707,27 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; access = gw->pt_access[it.level - 2]; - sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, - false, access); + sp = kvm_mmu_get_page(vcpu, table_gfn, addr, + it.level-1, false, access); + /* + * We must synchronize the pagetable before linking it + * because the guest doesn't need to flush tlb when + * the gpte is changed from non-present to present. + * Otherwise, the guest may use the wrong mapping. + * + * For PG_LEVEL_4K, kvm_mmu_get_page() has already + * synchronized it transiently via kvm_sync_page(). + * + * For higher level pagetable, we synchronize it via + * the slower mmu_sync_children(). If it needs to + * break, some progress has been made; return + * RET_PF_RETRY and retry on the next #PF. + * KVM_REQ_MMU_SYNC is not necessary but it + * expedites the process. + */ + if (sp->unsync_children && + mmu_sync_children(vcpu, sp, false)) + return RET_PF_RETRY; } /* @@ -1047,14 +1066,6 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, * Using the cached information from sp->gfns is safe because: * - The spte has a reference to the struct page, so the pfn for a given gfn * can't change unless all sptes pointing to it are nuked first. - * - * Note: - * We should flush all tlbs if spte is dropped even though guest is - * responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page - * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't - * used by guest then tlbs are not flushed, so guest is allowed to access the - * freed pages. - * And we increase kvm->tlbs_dirty to delay tlbs flush in this case. */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -1107,13 +1118,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return 0; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - /* - * Update spte before increasing tlbs_dirty to make - * sure no tlb flush is lost after spte is zapped; see - * the comments in kvm_flush_remote_tlbs(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; continue; } @@ -1128,12 +1133,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (gfn != sp->gfns[i]) { drop_spte(vcpu->kvm, &sp->spt[i]); - /* - * The same as above where we are doing - * prefetch_invalid_gpte(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; continue; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 2545d0c61985..510b833cbd39 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -545,7 +545,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits); - svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; svm->vmcb->control.int_state = svm->nested.ctl.int_state; svm->vmcb->control.event_inj = svm->nested.ctl.event_inj; @@ -579,7 +578,7 @@ static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, - struct vmcb *vmcb12) + struct vmcb *vmcb12, bool from_vmrun) { struct vcpu_svm *svm = to_svm(vcpu); int ret; @@ -609,13 +608,16 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, - nested_npt_enabled(svm), true); + nested_npt_enabled(svm), from_vmrun); if (ret) return ret; if (!npt_enabled) vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested; + if (!from_vmrun) + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + svm_set_gif(svm, true); return 0; @@ -681,7 +683,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) svm->nested.nested_run_pending = 1; - if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12)) + if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true)) goto out_exit_err; if (nested_svm_vmrun_msrpm(svm)) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 75e0b21ad07c..2e4916be290e 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -595,43 +595,55 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) return 0; } -static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) +static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, + int *error) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_update_vmsa vmsa; + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + /* Perform some pre-encryption checks against the VMSA */ + ret = sev_es_sync_vmsa(svm); + if (ret) + return ret; + + /* + * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of + * the VMSA memory content (i.e it will write the same memory region + * with the guest's key), so invalidate it first. + */ + clflush_cache_range(svm->vmsa, PAGE_SIZE); + + vmsa.reserved = 0; + vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; + vmsa.address = __sme_pa(svm->vmsa); + vmsa.len = PAGE_SIZE; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); + if (ret) + return ret; + + vcpu->arch.guest_state_protected = true; + return 0; +} + +static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ struct kvm_vcpu *vcpu; int i, ret; if (!sev_es_guest(kvm)) return -ENOTTY; - vmsa.reserved = 0; - kvm_for_each_vcpu(i, vcpu, kvm) { - struct vcpu_svm *svm = to_svm(vcpu); - - /* Perform some pre-encryption checks against the VMSA */ - ret = sev_es_sync_vmsa(svm); + ret = mutex_lock_killable(&vcpu->mutex); if (ret) return ret; - /* - * The LAUNCH_UPDATE_VMSA command will perform in-place - * encryption of the VMSA memory content (i.e it will write - * the same memory region with the guest's key), so invalidate - * it first. - */ - clflush_cache_range(svm->vmsa, PAGE_SIZE); + ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error); - vmsa.handle = sev->handle; - vmsa.address = __sme_pa(svm->vmsa); - vmsa.len = PAGE_SIZE; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, - &argp->error); + mutex_unlock(&vcpu->mutex); if (ret) return ret; - - svm->vcpu.arch.guest_state_protected = true; } return 0; @@ -1397,8 +1409,10 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start.handle, error); - if (ret) + if (ret) { + sev_decommission(start.handle); goto e_free_session; + } params.handle = start.handle; if (copy_to_user((void __user *)(uintptr_t)argp->data, @@ -1464,12 +1478,19 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, - PAGE_SIZE, &n, 0); + PAGE_SIZE, &n, 1); if (IS_ERR(guest_page)) { ret = PTR_ERR(guest_page); goto e_free_trans; } + /* + * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP + * encrypts the written data with the guest's key, and the cache may + * contain dirty, unencrypted data. + */ + sev_clflush_pages(guest_page, n); + /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; data.guest_address |= sev_me_mask; @@ -1501,6 +1522,20 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); } +static bool cmd_allowed_from_miror(u32 cmd_id) +{ + /* + * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES + * active mirror VMs. Also allow the debugging and status commands. + */ + if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA || + cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT || + cmd_id == KVM_SEV_DBG_ENCRYPT) + return true; + + return false; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1517,8 +1552,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) mutex_lock(&kvm->lock); - /* enc_context_owner handles all memory enc operations */ - if (is_mirroring_enc_context(kvm)) { + /* Only the enc_context_owner handles some memory enc operations. */ + if (is_mirroring_enc_context(kvm) && + !cmd_allowed_from_miror(sev_cmd.id)) { r = -EINVAL; goto out; } @@ -1715,8 +1751,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info *mirror_sev; - unsigned int asid; + struct kvm_sev_info source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); @@ -1739,7 +1774,8 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) goto e_source_unlock; } - asid = to_kvm_svm(source_kvm)->sev_info.asid; + memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, + sizeof(source_sev)); /* * The mirror kvm holds an enc_context_owner ref so its asid can't @@ -1759,8 +1795,16 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; - mirror_sev->asid = asid; mirror_sev->active = true; + mirror_sev->asid = source_sev.asid; + mirror_sev->fd = source_sev.fd; + mirror_sev->es_active = source_sev.es_active; + mirror_sev->handle = source_sev.handle; + /* + * Do not copy ap_jump_table. Since the mirror does not share the same + * KVM contexts as the original, and they may have different + * memory-views. + */ mutex_unlock(&kvm->lock); return 0; @@ -2551,7 +2595,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) return -EINVAL; return kvm_sev_es_string_io(&svm->vcpu, size, port, - svm->ghcb_sa, svm->ghcb_sa_len, in); + svm->ghcb_sa, svm->ghcb_sa_len / size, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 05e8d4d27969..989685098b3e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1566,6 +1566,8 @@ static void svm_clear_vintr(struct vcpu_svm *svm) svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & V_IRQ_INJECTION_BITS_MASK; + + svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; } vmcb_mark_dirty(svm->vmcb, VMCB_INTR); @@ -2222,6 +2224,10 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (error_code) goto reinject; + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + /* Decode the instruction for usage later */ if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) goto reinject; @@ -4285,43 +4291,44 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) struct kvm_host_map map_save; int ret; - if (is_guest_mode(vcpu)) { - /* FED8h - SVM Guest */ - put_smstate(u64, smstate, 0x7ed8, 1); - /* FEE0h - SVM Guest VMCB Physical Address */ - put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); + if (!is_guest_mode(vcpu)) + return 0; - svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + /* FED8h - SVM Guest */ + put_smstate(u64, smstate, 0x7ed8, 1); + /* FEE0h - SVM Guest VMCB Physical Address */ + put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); - ret = nested_svm_vmexit(svm); - if (ret) - return ret; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; - /* - * KVM uses VMCB01 to store L1 host state while L2 runs but - * VMCB01 is going to be used during SMM and thus the state will - * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save - * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the - * format of the area is identical to guest save area offsetted - * by 0x400 (matches the offset of 'struct vmcb_save_area' - * within 'struct vmcb'). Note: HSAVE area may also be used by - * L1 hypervisor to save additional host context (e.g. KVM does - * that, see svm_prepare_guest_switch()) which must be - * preserved. - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + ret = nested_svm_vmexit(svm); + if (ret) + return ret; - BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_guest_switch()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; - svm_copy_vmrun_state(map_save.hva + 0x400, - &svm->vmcb01.ptr->save); + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); - kvm_vcpu_unmap(vcpu, &map_save, true); - } + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); return 0; } @@ -4329,50 +4336,54 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map, map_save; - int ret = 0; + u64 saved_efer, vmcb12_gpa; + struct vmcb *vmcb12; + int ret; - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { - u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); - u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); - u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); - struct vmcb *vmcb12; + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 0; - if (guest) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - return 1; + /* Non-zero if SMI arrived while vCPU was in guest mode. */ + if (!GET_SMSTATE(u64, smstate, 0x7ed8)) + return 0; - if (!(saved_efer & EFER_SVME)) - return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; - if (kvm_vcpu_map(vcpu, - gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) - return 1; + saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); + if (!(saved_efer & EFER_SVME)) + return 1; - if (svm_allocate_nested(svm)) - return 1; + vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) + return 1; - vmcb12 = map.hva; + ret = 1; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL) + goto unmap_map; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + if (svm_allocate_nested(svm)) + goto unmap_save; - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); - kvm_vcpu_unmap(vcpu, &map, true); + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ - /* - * Restore L1 host state from L1 HSAVE area as VMCB01 was - * used during SMM (see svm_enter_smm()) - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400); - svm_copy_vmrun_state(&svm->vmcb01.ptr->save, - map_save.hva + 0x400); + /* + * Enter the nested guest now + */ - kvm_vcpu_unmap(vcpu, &map_save, true); - } - } + vmcb12 = map.hva; + nested_load_control_from_vmcb12(svm, &vmcb12->control); + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); +unmap_save: + kvm_vcpu_unmap(vcpu, &map_save, true); +unmap_map: + kvm_vcpu_unmap(vcpu, &map, true); return ret; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 524d943f3efc..5d30db599e10 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -191,7 +191,7 @@ struct vcpu_svm { /* SEV-ES scratch area support */ void *ghcb_sa; - u64 ghcb_sa_len; + u32 ghcb_sa_len; bool ghcb_sa_sync; bool ghcb_sa_free; @@ -459,7 +459,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } -int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12); +int enter_svm_guest_mode(struct kvm_vcpu *vcpu, + u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 0dab1b7b529f..ba6f99f584ac 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -353,14 +353,20 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; + break; + case MSR_IA32_VMX_PINBASED_CTLS: + ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; + break; + case MSR_IA32_VMX_VMFUNC: + ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC; break; } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ccb03d69546c..eedcebf58004 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2583,8 +2583,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Guest state is invalid and unrestricted guest is disabled, * which means L1 attempted VMEntry to L2 with invalid state. * Fail the VMEntry. + * + * However when force loading the guest state (SMM exit or + * loading nested state after migration, it is possible to + * have invalid guest state now, which will be later fixed by + * restoring L2 register state */ - if (CC(!vmx_guest_state_valid(vcpu))) { + if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -4351,6 +4356,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); + + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) @@ -4899,14 +4906,7 @@ out_vmcs02: return -ENOMEM; } -/* - * Emulate the VMXON instruction. - * Currently, we just remember that VMX is active, and do not save or even - * inspect the argument to VMXON (the so-called "VMXON pointer") because we - * do not currently need to store anything in that guest-allocated memory - * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their - * argument is different from the VMXON pointer (which the spec says they do). - */ +/* Emulate the VMXON instruction. */ static int handle_vmon(struct kvm_vcpu *vcpu) { int ret; @@ -5903,6 +5903,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ return true; + case EXIT_REASON_BUS_LOCK: + /* + * At present, bus lock VM exit is never exposed to L1. + * Handle L2's bus locks in L0 directly. + */ + return true; default: break; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0c2c0d5ae873..7d595effb66f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1323,7 +1323,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) vmx_prepare_switch_to_host(to_vmx(vcpu)); } -static bool emulation_required(struct kvm_vcpu *vcpu) +bool vmx_emulation_required(struct kvm_vcpu *vcpu) { return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu); } @@ -1367,7 +1367,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) @@ -1837,10 +1837,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &msr_info->data)) return 1; /* - * Enlightened VMCS v1 doesn't have certain fields, but buggy - * Hyper-V versions are still trying to use corresponding - * features when they are exposed. Filter out the essential - * minimum. + * Enlightened VMCS v1 doesn't have certain VMCS fields but + * instead of just ignoring the features, different Hyper-V + * versions are either trying to use them and fail or do some + * sanity checking and refuse to boot. Filter all unsupported + * features out. */ if (!msr_info->host_initiated && vmx->nested.enlightened_vmcs_enabled) @@ -3077,7 +3078,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } static int vmx_get_max_tdp_level(void) @@ -3330,7 +3331,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int { __vmx_set_segment(vcpu, var, seg); - to_vmx(vcpu)->emulation_required = emulation_required(vcpu); + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -5561,9 +5562,13 @@ static int handle_encls(struct kvm_vcpu *vcpu) static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) { - vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; - vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; - return 0; + /* + * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK + * VM-Exits. Unconditionally set the flag here and leave the handling to + * vmx_handle_exit(). + */ + to_vmx(vcpu)->exit_reason.bus_lock_detected = true; + return 1; } /* @@ -6050,9 +6055,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) int ret = __vmx_handle_exit(vcpu, exit_fastpath); /* - * Even when current exit reason is handled by KVM internally, we - * still need to exit to user space when bus lock detected to inform - * that there is a bus lock in guest. + * Exit to user space when bus lock detected to inform that there is + * a bus lock in guest. */ if (to_vmx(vcpu)->exit_reason.bus_lock_detected) { if (ret > 0) @@ -6301,18 +6305,13 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) /* * If we are running L2 and L1 has a new pending interrupt - * which can be injected, we should re-evaluate - * what should be done with this new L1 interrupt. - * If L1 intercepts external-interrupts, we should - * exit from L2 to L1. Otherwise, interrupt should be - * delivered directly to L2. + * which can be injected, this may cause a vmexit or it may + * be injected into L2. Either way, this interrupt will be + * processed via KVM_REQ_EVENT, not RVI, because we do not use + * virtual interrupt delivery to inject L1 interrupts into L2. */ - if (is_guest_mode(vcpu) && max_irr_updated) { - if (nested_exit_on_intr(vcpu)) - kvm_vcpu_exiting_guest_mode(vcpu); - else - kvm_make_request(KVM_REQ_EVENT, vcpu); - } + if (is_guest_mode(vcpu) && max_irr_updated) + kvm_make_request(KVM_REQ_EVENT, vcpu); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); } @@ -6621,10 +6620,24 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->entry_time = ktime_get(); - /* Don't enter VMX if guest state is invalid, let the exit handler - start emulation until we arrive back to a valid state */ - if (vmx->emulation_required) + /* + * Don't enter VMX if guest state is invalid, let the exit handler + * start emulation until we arrive back to a valid state. Synthesize a + * consistency check VM-Exit due to invalid guest state and bail. + */ + if (unlikely(vmx->emulation_required)) { + + /* We don't emulate invalid state of a nested guest */ + vmx->fail = is_guest_mode(vcpu); + + vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; + vmx->exit_reason.failed_vmentry = 1; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + vmx->exit_qualification = ENTRY_FAIL_DEFAULT; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + vmx->exit_intr_info = 0; return EXIT_FASTPATH_NONE; + } trace_kvm_entry(vcpu); @@ -6833,7 +6846,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) - vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4858c5fd95f2..592217fd7d92 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -248,12 +248,8 @@ struct vcpu_vmx { * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to * be loaded into hardware if those conditions aren't met. - * nr_active_uret_msrs tracks the number of MSRs that need to be loaded - * into hardware when running the guest. guest_uret_msrs[] is resorted - * whenever the number of "active" uret MSRs is modified. */ struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; - int nr_active_uret_msrs; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; @@ -359,6 +355,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); +bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 28ef14155726..b26647a5ea22 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1332,6 +1332,13 @@ static const u32 msrs_to_save_all[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; @@ -2969,7 +2976,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (v == kvm_get_vcpu(v->kvm, 0)) + if (!v->vcpu_idx) kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -6899,7 +6906,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) } static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, + unsigned short port, unsigned int count, bool in) { vcpu->arch.pio.port = port; @@ -6907,10 +6914,8 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - vcpu->arch.pio.count = 0; + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) return 1; - } vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; @@ -6922,26 +6927,39 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, return 0; } -static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, unsigned int count) +static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, unsigned int count) { - int ret; + WARN_ON(vcpu->arch.pio.count); + memset(vcpu->arch.pio_data, 0, size * count); + return emulator_pio_in_out(vcpu, size, port, count, true); +} - if (vcpu->arch.pio.count) - goto data_avail; +static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val) +{ + int size = vcpu->arch.pio.size; + unsigned count = vcpu->arch.pio.count; + memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data); + vcpu->arch.pio.count = 0; +} - memset(vcpu->arch.pio_data, 0, size * count); +static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, unsigned int count) +{ + if (vcpu->arch.pio.count) { + /* Complete previous iteration. */ + } else { + int r = __emulator_pio_in(vcpu, size, port, count); + if (!r) + return r; - ret = emulator_pio_in_out(vcpu, size, port, val, count, true); - if (ret) { -data_avail: - memcpy(val, vcpu->arch.pio_data, size * count); - trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); - vcpu->arch.pio.count = 0; - return 1; + /* Results already available, fall through. */ } - return 0; + WARN_ON(count != vcpu->arch.pio.count); + complete_emulator_pio_in(vcpu, val); + return 1; } static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, @@ -6956,9 +6974,15 @@ static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port, const void *val, unsigned int count) { + int ret; + memcpy(vcpu->arch.pio_data, val, size * count); trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); - return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); + ret = emulator_pio_in_out(vcpu, size, port, count, false); + if (ret) + vcpu->arch.pio.count = 0; + + return ret; } static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, @@ -7658,6 +7682,13 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) /* Process a latched INIT or SMI, if any. */ kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, + * on SMM exit we still need to reload them from + * guest memory + */ + vcpu->arch.pdptrs_from_userspace = false; } kvm_mmu_reset_context(vcpu); @@ -9629,14 +9660,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; - if (unlikely(kvm_vcpu_exit_request(vcpu))) { + if (vcpu->arch.apicv_active) + static_call(kvm_x86_sync_pir_to_irr)(vcpu); + + if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; break; } - - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); - } + } /* * Do this here before restoring debug registers on the host. And @@ -10652,6 +10683,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) int r; vcpu->arch.last_vmentry_cpu = -1; + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -10893,6 +10926,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); + vcpu->arch.cr3 = 0; + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + /* * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions * of Intel's SDM list CD/NW as being set on INIT, but they contradict @@ -11139,9 +11175,15 @@ void kvm_arch_free_vm(struct kvm *kvm) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { + int ret; + if (type) return -EINVAL; + ret = kvm_page_track_init(kvm); + if (ret) + return ret; + INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); @@ -11174,7 +11216,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); - kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); kvm_xen_init_vm(kvm); @@ -11368,7 +11409,8 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot, int level = i + 1; int lpages = __kvm_mmu_slot_lpages(slot, npages, level); - WARN_ON(slot->arch.rmap[i]); + if (slot->arch.rmap[i]) + continue; slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) { @@ -12343,44 +12385,81 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, } EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read); -static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port); + +static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu) { - memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data, - vcpu->arch.pio.count * vcpu->arch.pio.size); - vcpu->arch.pio.count = 0; + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + vcpu->arch.pio.count = 0; + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_outs(vcpu, size, port); return 1; } static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, - unsigned int port, void *data, unsigned int count) + unsigned int port) { - int ret; - - ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port, - data, count); - if (ret) - return ret; + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count); + + /* memcpy done already by emulator_pio_out. */ + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; + if (!ret) + break; - vcpu->arch.pio.count = 0; + /* Emulation done by the kernel. */ + if (!vcpu->arch.sev_pio_count) + return 1; + } + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs; return 0; } static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, - unsigned int port, void *data, unsigned int count) + unsigned int port); + +static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu) { - int ret; + unsigned count = vcpu->arch.pio.count; + complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data); + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; +} - ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port, - data, count); - if (ret) { - vcpu->arch.pio.count = 0; - } else { - vcpu->arch.guest_ins_data = data; - vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; +static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +{ + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + + advance_sev_es_emulated_ins(vcpu); + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_ins(vcpu, size, port); + return 1; +} + +static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port) +{ + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + if (!__emulator_pio_in(vcpu, size, port, count)) + break; + + /* Emulation done by the kernel. */ + advance_sev_es_emulated_ins(vcpu); + if (!vcpu->arch.sev_pio_count) + return 1; } + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; return 0; } @@ -12388,8 +12467,10 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port, void *data, unsigned int count, int in) { - return in ? kvm_sev_es_ins(vcpu, size, port, data, count) - : kvm_sev_es_outs(vcpu, size, port, data, count); + vcpu->arch.sev_pio_data = data; + vcpu->arch.sev_pio_count = count; + return in ? kvm_sev_es_ins(vcpu, size, port) + : kvm_sev_es_outs(vcpu, size, port); } EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 058f19b20465..c565def611e2 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -37,10 +37,10 @@ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b2eefdefc108..84a2c8c4af73 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -710,7 +710,8 @@ oops: static noinline void kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, - unsigned long address, int signal, int si_code) + unsigned long address, int signal, int si_code, + u32 pkey) { WARN_ON_ONCE(user_mode(regs)); @@ -735,8 +736,12 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, set_signal_archinfo(address, error_code); - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); + if (si_code == SEGV_PKUERR) { + force_sig_pkuerr((void __user *)address, pkey); + } else { + /* XXX: hwpoison faults will set the wrong code. */ + force_sig_fault(signal, si_code, (void __user *)address); + } } /* @@ -798,7 +803,8 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, pkey, si_code); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGSEGV, si_code, pkey); return; } @@ -930,7 +936,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } @@ -1396,7 +1403,8 @@ good_area: */ if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, - SIGBUS, BUS_ADRERR); + SIGBUS, BUS_ADRERR, + ARCH_DEFAULT_PKEY); return; } @@ -1416,7 +1424,8 @@ good_area: return; if (fatal_signal_pending(current) && !user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, 0, 0); + kernelmode_fixup_or_oops(regs, error_code, address, + 0, 0, ARCH_DEFAULT_PKEY); return; } @@ -1424,7 +1433,8 @@ good_area: /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, - SIGSEGV, SEGV_MAPERR); + SIGSEGV, SEGV_MAPERR, + ARCH_DEFAULT_PKEY); return; } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a6e11763763f..36098226a957 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1432,18 +1432,18 @@ int kern_addr_valid(unsigned long addr) return 0; p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) + if (!p4d_present(*p4d)) return 0; pud = pud_offset(p4d, 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)) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1a50434c8a4d..ef885370719a 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PMD_SIZE); + memblock_free_ptr(p, PMD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); @@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PUD_SIZE); + memblock_free_ptr(p, PUD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index a1b5c71099e6..1e9b93b088db 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -355,7 +355,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 737491b13728..e801e30089c4 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } /* free the copied physical distance table */ - if (phys_dist) - memblock_free(__pa(phys_dist), phys_size); + memblock_free_ptr(phys_dist, phys_size); return; no_emu: diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 3112ca7786ed..4ba2a3ee4bce 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -583,7 +583,12 @@ int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type, int err = 0; start = sanitize_phys(start); - end = sanitize_phys(end); + + /* + * The end address passed into this function is exclusive, but + * sanitize_phys() expects an inclusive address. + */ + end = sanitize_phys(end - 1) + 1; if (start >= end) { WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__, start, end - 1, cattr_name(req_type)); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0fe6aacef3db..9ea57389c554 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1341,9 +1341,10 @@ st: if (is_imm8(insn->off)) if (insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH)) { - u8 *branch_target; bool is64 = BPF_SIZE(insn->code) == BPF_DW; u32 real_src_reg = src_reg; + u32 real_dst_reg = dst_reg; + u8 *branch_target; /* * Can't be implemented with a single x86 insn. @@ -1354,11 +1355,13 @@ st: if (is_imm8(insn->off)) emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0); if (src_reg == BPF_REG_0) real_src_reg = BPF_REG_AX; + if (dst_reg == BPF_REG_0) + real_dst_reg = BPF_REG_AX; branch_target = prog; /* Load old value */ emit_ldx(&prog, BPF_SIZE(insn->code), - BPF_REG_0, dst_reg, insn->off); + BPF_REG_0, real_dst_reg, insn->off); /* * Perform the (commutative) operation locally, * put the result in the AUX_REG. @@ -1369,7 +1372,8 @@ st: if (is_imm8(insn->off)) add_2reg(0xC0, AUX_REG, real_src_reg)); /* Attempt to swap in new value */ err = emit_atomic(&prog, BPF_CMPXCHG, - dst_reg, AUX_REG, insn->off, + real_dst_reg, AUX_REG, + insn->off, BPF_SIZE(insn->code)); if (WARN_ON(err)) return err; @@ -1383,11 +1387,10 @@ st: if (is_imm8(insn->off)) /* Restore R0 after clobbering RAX */ emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX); break; - } err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, - insn->off, BPF_SIZE(insn->code)); + insn->off, BPF_SIZE(insn->code)); if (err) return err; break; @@ -1744,7 +1747,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, - struct bpf_prog *p, int stack_size, bool mod_ret) + struct bpf_prog *p, int stack_size, bool save_ret) { u8 *prog = *pprog; u8 *jmp_insn; @@ -1777,11 +1780,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (emit_call(&prog, p->bpf_func, prog)) return -EINVAL; - /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + /* + * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return * of the previous call which is then passed on the stack to * the next BPF program. + * + * BPF_TRAMP_FENTRY trampoline may need to return the return + * value of BPF_PROG_TYPE_STRUCT_OPS prog. */ - if (mod_ret) + if (save_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); /* replace 2 nops with JE insn, since jmp target is known */ @@ -1828,13 +1835,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) } static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, - struct bpf_tramp_progs *tp, int stack_size) + struct bpf_tramp_progs *tp, int stack_size, + bool save_ret) { int i; u8 *prog = *pprog; for (i = 0; i < tp->nr_progs; i++) { - if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, + save_ret)) return -EINVAL; } *pprog = prog; @@ -1877,6 +1886,23 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, return 0; } +static bool is_valid_bpf_tramp_flags(unsigned int flags) +{ + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return false; + + /* + * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, + * and it must be used alone. + */ + if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) && + (flags & ~BPF_TRAMP_F_RET_FENTRY_RET)) + return false; + + return true; +} + /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -1949,17 +1975,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; u8 **branches = NULL; u8 *prog; + bool save_ret; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ if (nr_args > 6) return -ENOTSUPP; - if ((flags & BPF_TRAMP_F_RESTORE_REGS) && - (flags & BPF_TRAMP_F_SKIP_FRAME)) + if (!is_valid_bpf_tramp_flags(flags)) return -EINVAL; - if (flags & BPF_TRAMP_F_CALL_ORIG) - stack_size += 8; /* room for return value of orig_call */ + /* room for return value of orig_call or fentry prog */ + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) + stack_size += 8; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2005,7 +2033,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fentry->nr_progs) - if (invoke_bpf(m, &prog, fentry, stack_size)) + if (invoke_bpf(m, &prog, fentry, stack_size, + flags & BPF_TRAMP_F_RET_FENTRY_RET)) return -EINVAL; if (fmod_ret->nr_progs) { @@ -2052,7 +2081,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fexit->nr_progs) - if (invoke_bpf(m, &prog, fexit, stack_size)) { + if (invoke_bpf(m, &prog, fexit, stack_size, false)) { ret = -EINVAL; goto cleanup; } @@ -2072,9 +2101,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - /* restore original return value back into RAX */ - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); } + /* restore return value of orig_call or fentry prog back into RAX */ + if (save_ret) + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); EMIT1(0x5B); /* pop rbx */ EMIT1(0xC9); /* leave */ diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 3d41a09c2c14..5debe4ac6f81 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -113,7 +113,7 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, false /* no mapping of GSI to PIRQ */); } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 static int xen_register_gsi(u32 gsi, int triggering, int polarity) { int rc, irq; @@ -261,7 +261,7 @@ error: return irq; } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 static bool __read_mostly pci_seg_supported = true; static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) @@ -375,10 +375,10 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev) WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret); } } -#else /* CONFIG_XEN_DOM0 */ +#else /* CONFIG_XEN_PV_DOM0 */ #define xen_initdom_setup_msi_irqs NULL #define xen_initdom_restore_msi_irqs NULL -#endif /* !CONFIG_XEN_DOM0 */ +#endif /* !CONFIG_XEN_PV_DOM0 */ static void xen_teardown_msi_irqs(struct pci_dev *dev) { @@ -555,7 +555,7 @@ int __init pci_xen_hvm_init(void) return 0; } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 int __init pci_xen_initial_domain(void) { int irq; @@ -583,6 +583,9 @@ int __init pci_xen_initial_domain(void) } return 0; } +#endif + +#ifdef CONFIG_XEN_DOM0 struct xen_device_domain_owner { domid_t domain; @@ -656,4 +659,4 @@ int xen_unregister_device_domain_owner(struct pci_dev *dev) return 0; } EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner); -#endif +#endif /* CONFIG_XEN_DOM0 */ diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index ee2beda590d0..1d4a00e767ec 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -274,7 +274,7 @@ static struct olpc_ec_driver ec_xo1_driver = { static struct olpc_ec_driver ec_xo1_5_driver = { .ec_cmd = olpc_xo1_ec_cmd, -#ifdef CONFIG_OLPC_XO1_5_SCI +#ifdef CONFIG_OLPC_XO15_SCI /* * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is * compiled in diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 9ac7457f52a3..ed0442e35434 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -16,15 +16,15 @@ /* * PVH variables. * - * pvh_bootparams and pvh_start_info need to live in the data segment since + * pvh_bootparams and pvh_start_info need to live in a data segment since * they are used after startup_{32|64}, which clear .bss, are invoked. */ -struct boot_params pvh_bootparams __section(".data"); -struct hvm_start_info pvh_start_info __section(".data"); +struct boot_params __initdata pvh_bootparams; +struct hvm_start_info __initdata pvh_start_info; -unsigned int pvh_start_info_sz = sizeof(pvh_start_info); +const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info); -static u64 pvh_get_root_pointer(void) +static u64 __init pvh_get_root_pointer(void) { return pvh_start_info.rsdp_paddr; } @@ -107,7 +107,7 @@ void __init __weak xen_pvh_init(struct boot_params *boot_params) BUG(); } -static void hypervisor_specific_init(bool xen_guest) +static void __init hypervisor_specific_init(bool xen_guest) { if (xen_guest) xen_pvh_init(&pvh_bootparams); diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index afc1da68b06d..6bcd3d8ca6ac 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -43,13 +43,9 @@ config XEN_PV_SMP def_bool y depends on XEN_PV && SMP -config XEN_DOM0 - bool "Xen PV Dom0 support" - default y - depends on XEN_PV && PCI_XEN && SWIOTLB_XEN - depends on X86_IO_APIC && ACPI && PCI - help - Support running as a Xen PV Dom0 guest. +config XEN_PV_DOM0 + def_bool y + depends on XEN_PV && XEN_DOM0 config XEN_PVHVM def_bool y @@ -86,3 +82,12 @@ config XEN_PVH def_bool n help Support for running as a Xen PVH guest. + +config XEN_DOM0 + bool "Xen Dom0 support" + default XEN_PV + depends on (XEN_PV && SWIOTLB_XEN) || (XEN_PVH && X86_64) + depends on X86_IO_APIC && ACPI && PCI + select X86_X2APIC if XEN_PVH && X86_64 + help + Support running as a Xen Dom0 guest. diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 40b5779fce21..4953260e281c 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -45,7 +45,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += vga.o +obj-$(CONFIG_XEN_PV_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c79bd0af2e8c..95d970359e17 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -3,6 +3,7 @@ #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG #include <linux/memblock.h> #endif +#include <linux/console.h> #include <linux/cpu.h> #include <linux/kexec.h> #include <linux/slab.h> @@ -10,12 +11,15 @@ #include <xen/xen.h> #include <xen/features.h> +#include <xen/interface/sched.h> +#include <xen/interface/version.h> #include <xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> #include <asm/cpu.h> #include <asm/e820/api.h> +#include <asm/setup.h> #include "xen-ops.h" #include "smp.h" @@ -52,9 +56,6 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); -enum xen_domain_type xen_domain_type = XEN_NATIVE; -EXPORT_SYMBOL_GPL(xen_domain_type); - unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; EXPORT_SYMBOL(machine_to_phys_mapping); unsigned long machine_to_phys_nr; @@ -69,10 +70,12 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* - * NB: needs to live in .data because it's used by xen_prepare_pvh which runs - * before clearing the bss. + * NB: These need to live in .data or alike because they're used by + * xen_prepare_pvh() which runs before clearing the bss. */ -uint32_t xen_start_flags __section(".data") = 0; +enum xen_domain_type __ro_after_init xen_domain_type = XEN_NATIVE; +EXPORT_SYMBOL_GPL(xen_domain_type); +uint32_t __ro_after_init xen_start_flags; EXPORT_SYMBOL(xen_start_flags); /* @@ -258,6 +261,45 @@ int xen_vcpu_setup(int cpu) return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0); } +void __init xen_banner(void) +{ + unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); + struct xen_extraversion extra; + + HYPERVISOR_xen_version(XENVER_extraversion, &extra); + + pr_info("Booting kernel on %s\n", pv_info.name); + pr_info("Xen version: %u.%u%s%s\n", + version >> 16, version & 0xffff, extra.extraversion, + xen_feature(XENFEAT_mmu_pt_update_preserve_ad) + ? " (preserve-AD)" : ""); +} + +/* Check if running on Xen version (major, minor) or later */ +bool xen_running_on_version_or_later(unsigned int major, unsigned int minor) +{ + unsigned int version; + + if (!xen_domain()) + return false; + + version = HYPERVISOR_xen_version(XENVER_version, NULL); + if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || + ((version >> 16) > major)) + return true; + return false; +} + +void __init xen_add_preferred_consoles(void) +{ + add_preferred_console("xenboot", 0, NULL); + if (!boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); + add_preferred_console("hvc", 0, NULL); + if (boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); +} + void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 753f63734c13..a7b7d674f500 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -28,7 +28,6 @@ #include <linux/mm.h> #include <linux/page-flags.h> #include <linux/highmem.h> -#include <linux/console.h> #include <linux/pci.h> #include <linux/gfp.h> #include <linux/edd.h> @@ -109,17 +108,6 @@ struct tls_descs { */ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); -static void __init xen_banner(void) -{ - unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); - struct xen_extraversion extra; - HYPERVISOR_xen_version(XENVER_extraversion, &extra); - - pr_info("Booting paravirtualized kernel on %s\n", pv_info.name); - pr_info("Xen version: %d.%d%s (preserve-AD)\n", - version >> 16, version & 0xffff, extra.extraversion); -} - static void __init xen_pv_init_platform(void) { populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); @@ -142,22 +130,6 @@ static void __init xen_pv_guest_late_init(void) #endif } -/* Check if running on Xen version (major, minor) or later */ -bool -xen_running_on_version_or_later(unsigned int major, unsigned int minor) -{ - unsigned int version; - - if (!xen_domain()) - return false; - - version = HYPERVISOR_xen_version(XENVER_version, NULL); - if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || - ((version >> 16) > major)) - return true; - return false; -} - static __read_mostly unsigned int cpuid_leaf5_ecx_val; static __read_mostly unsigned int cpuid_leaf5_edx_val; @@ -755,8 +727,8 @@ 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; @@ -766,17 +738,18 @@ 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 @@ -786,6 +759,7 @@ 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); @@ -793,7 +767,8 @@ 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)) @@ -1214,6 +1189,11 @@ static void __init xen_dom0_set_legacy_features(void) x86_platform.legacy.rtc = 1; } +static void __init xen_domu_set_legacy_features(void) +{ + x86_platform.legacy.rtc = 0; +} + /* First C function to be called on Xen boot */ asmlinkage __visible void __init xen_start_kernel(void) { @@ -1356,9 +1336,10 @@ asmlinkage __visible void __init xen_start_kernel(void) boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN; if (!xen_initial_domain()) { - add_preferred_console("xenboot", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; + x86_platform.set_legacy_features = + xen_domu_set_legacy_features; } else { const struct dom0_vga_console_info *info = (void *)((char *)xen_start_info + @@ -1399,11 +1380,7 @@ asmlinkage __visible void __init xen_start_kernel(void) #endif } - if (!boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); - add_preferred_console("hvc", 0, NULL); - if (boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); + xen_add_preferred_consoles(); #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 0d5e34b9e6f9..bcae606bbc5c 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> +#include <linux/export.h> #include <xen/hvc-console.h> @@ -18,10 +19,11 @@ /* * PVH variables. * - * The variable xen_pvh needs to live in the data segment since it is used + * The variable xen_pvh needs to live in a data segment since it is used * after startup_{32|64} is invoked, which will clear the .bss segment. */ -bool xen_pvh __section(".data") = 0; +bool __ro_after_init xen_pvh; +EXPORT_SYMBOL_GPL(xen_pvh); void __init xen_pvh_init(struct boot_params *boot_params) { @@ -36,6 +38,10 @@ void __init xen_pvh_init(struct boot_params *boot_params) pfn = __pa(hypercall_page); wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + if (xen_initial_domain()) + x86_init.oem.arch_setup = xen_add_preferred_consoles; + x86_init.oem.banner = xen_banner; + xen_efi_init(boot_params); } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1df5f01529e5..3359c23573c5 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1518,14 +1518,17 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, if (pinned) { struct page *page = pfn_to_page(pfn); - if (static_branch_likely(&xen_struct_pages_ready)) + pinned = false; + if (static_branch_likely(&xen_struct_pages_ready)) { + pinned = PagePinned(page); SetPagePinned(page); + } xen_mc_batch(); __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); xen_mc_issue(PARAVIRT_LAZY_MMU); @@ -2395,7 +2398,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages) + unsigned int domid, bool no_translate) { int err = 0; struct remap_data rmd; diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 54f9aa7e8457..46df59aeaa06 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -18,7 +18,7 @@ #endif #include <linux/export.h> -int xen_swiotlb __read_mostly; +static int xen_swiotlb __read_mostly; /* * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary @@ -56,7 +56,7 @@ int __init pci_xen_swiotlb_detect(void) return xen_swiotlb; } -void __init pci_xen_swiotlb_init(void) +static void __init pci_xen_swiotlb_init(void) { if (xen_swiotlb) { xen_swiotlb_init_early(); diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 96afadf9878e..7ed56c6075b0 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -290,8 +290,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) gdt = get_cpu_gdt_rw(cpu); - memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); - /* * Bring up the CPU in cpu_bringup_and_idle() with the stack * pointing just below where pt_regs would be if it were a normal @@ -308,8 +306,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) xen_copy_trap_info(ctxt->trap_ctxt); - ctxt->ldt_ents = 0; - BUG_ON((unsigned long)gdt & ~PAGE_MASK); gdt_mfn = arbitrary_virt_to_mfn(gdt); diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 8d7ec49a35fb..8bc8b72a205d 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -51,6 +51,7 @@ void __init xen_remap_memory(void); phys_addr_t __init xen_find_free_area(phys_addr_t size); char * __init xen_memory_setup(void); void __init xen_arch_setup(void); +void xen_banner(void); void xen_enable_sysenter(void); void xen_enable_syscall(void); void xen_vcpu_restore(void); @@ -109,7 +110,7 @@ static inline void xen_uninit_lock_cpu(int cpu) struct dom0_vga_console_info; -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, @@ -118,6 +119,8 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, } #endif +void xen_add_preferred_consoles(void); + void __init xen_init_apic(void); #ifdef CONFIG_XEN_EFI |