diff options
Diffstat (limited to 'arch/x86')
38 files changed, 418 insertions, 226 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7b6dd10b162a..21f851179ff0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -19,6 +19,7 @@ config X86_32 select KMAP_LOCAL select MODULES_USE_ELF_REL select OLD_SIGACTION + select ARCH_SPLIT_ARG64 config X86_64 def_bool y diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 18d8f17f755c..0904f5676e4d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -73,10 +73,8 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, unsigned int nr) { if (likely(nr < IA32_NR_syscalls)) { - instrumentation_begin(); nr = array_index_nospec(nr, IA32_NR_syscalls); regs->ax = ia32_sys_call_table[nr](regs); - instrumentation_end(); } } @@ -91,8 +89,11 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) * or may not be necessary, but it matches the old asm behavior. */ nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + instrumentation_begin(); do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); } @@ -121,11 +122,12 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) res = get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp); } - instrumentation_end(); if (res) { /* User code screwed up. */ regs->ax = -EFAULT; + + instrumentation_end(); syscall_exit_to_user_mode(regs); return false; } @@ -135,6 +137,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); return true; } diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index e04d90af4c27..6375967a8244 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -16,6 +16,7 @@ #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/idtentry.h> +#include <linux/kexec.h> #include <linux/version.h> #include <linux/vmalloc.h> #include <linux/mm.h> @@ -26,6 +27,8 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> +int hyperv_init_cpuhp; + void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -312,6 +315,25 @@ static struct syscore_ops hv_syscore_ops = { .resume = hv_resume, }; +static void (* __initdata old_setup_percpu_clockev)(void); + +static void __init hv_stimer_setup_percpu_clockev(void) +{ + /* + * Ignore any errors in setting up stimer clockevents + * as we can run with the LAPIC timer as a fallback. + */ + (void)hv_stimer_alloc(); + + /* + * Still register the LAPIC timer, because the direct-mode STIMER is + * not supported by old versions of Hyper-V. This also allows users + * to switch to LAPIC timer via /sys, if they want to. + */ + if (old_setup_percpu_clockev) + old_setup_percpu_clockev(); +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -390,10 +412,14 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* - * Ignore any errors in setting up stimer clockevents - * as we can run with the LAPIC timer as a fallback. + * hyperv_init() is called before LAPIC is initialized: see + * apic_intr_mode_init() -> x86_platform.apic_post_init() and + * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER + * depends on LAPIC, so hv_stimer_alloc() should be called from + * x86_init.timers.setup_percpu_clockev. */ - (void)hv_stimer_alloc(); + old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev; + x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev; hv_apic_init(); @@ -401,6 +427,7 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); + hyperv_init_cpuhp = cpuhp; return; remove_cpuhp_state: diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 5208ba49c89a..2c87350c1fb0 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (!hv_hypercall_pg) goto do_native; - if (cpumask_empty(cpus)) - return; - local_irq_save(flags); + /* + * Only check the mask _after_ interrupt has been disabled to avoid the + * mask changing under our feet. + */ + if (cpumask_empty(cpus)) { + local_irq_restore(flags); + return; + } + flush_pcpu = (struct hv_tlb_flush **) this_cpu_ptr(hyperv_pcpu_input_arg); diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a5aba4ab0224..67a4f1cb2aac 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -16,14 +16,25 @@ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods * of time. - * If you intend to use the FPU in softirq you need to check first with + * If you intend to use the FPU in irq/softirq you need to check first with * irq_fpu_usable() if it is possible. */ -extern void kernel_fpu_begin(void); + +/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ +#define KFPU_387 _BITUL(0) /* 387 state will be initialized */ +#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ + +extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +/* Code that is unaware of kernel_fpu_begin_mask() can use this */ +static inline void kernel_fpu_begin(void) +{ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. * A context switch will (and softirq might) save CPU's FPU registers to diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5e658ba2654a..9abe842dbd84 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -97,6 +97,7 @@ #define INTEL_FAM6_LAKEFIELD 0x8A #define INTEL_FAM6_ALDERLAKE 0x97 +#define INTEL_FAM6_ALDERLAKE_L 0x9A /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3ab7b46087b7..3d6616f6f6ef 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1010,9 +1010,21 @@ struct kvm_arch { */ bool tdp_mmu_enabled; - /* List of struct tdp_mmu_pages being used as roots */ + /* + * List of struct kvmp_mmu_pages being used as roots. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set. + * All struct kvm_mmu_pages in the list should have a positive + * root_count except when a thread holds the MMU lock and is removing + * an entry from the list. + */ struct list_head tdp_mmu_roots; - /* List of struct tdp_mmu_pages not being used as roots */ + + /* + * List of struct kvmp_mmu_pages not being used as roots. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set and a root_count of 0. + */ struct list_head tdp_mmu_pages; }; @@ -1287,6 +1299,8 @@ struct kvm_x86_ops { void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); + + void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); }; struct kvm_x86_nested_ops { @@ -1468,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/x86/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ffc289992d1b..30f76b966857 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) +extern int hyperv_init_cpuhp; + extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 0b4920a7238e..e16cccdd0420 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 488a8e848754..9239399e5491 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -110,6 +110,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +extern unsigned int __max_die_per_package; + #ifdef CONFIG_SMP #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) @@ -118,8 +120,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); extern unsigned int __max_logical_packages; #define topology_max_packages() (__max_logical_packages) -extern unsigned int __max_die_per_package; - static inline int topology_max_die_per_package(void) { return __max_die_per_package; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f8ca66f3d861..347a956f71ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) u32 ecx; ecx = cpuid_ecx(0x8000001e); - nodes_per_socket = ((ecx >> 8) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; } if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 13d3f1cbda17..e133ce1e562b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) * that out because it's an indirect call. Annotate it. */ instrumentation_begin(); - trace_hardirqs_off_finish(); + machine_check_vector(regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); + instrumentation_end(); irqentry_nmi_exit(regs, irq_state); } @@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); irqentry_exit_to_user_mode(regs); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f628e3dc150f..43b54bef5448 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -135,14 +135,32 @@ static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) hv_kexec_handler(); + + /* + * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor + * corrupts the old VP Assist Pages and can crash the kexec kernel. + */ + if (kexec_in_progress && hyperv_init_cpuhp > 0) + cpuhp_remove_state(hyperv_init_cpuhp); + + /* The function calls stop_other_cpus(). */ native_machine_shutdown(); + + /* Disable the hypercall page when there is only 1 active CPU. */ + if (kexec_in_progress) + hyperv_cleanup(); } static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); + + /* The function calls crash_smp_send_stop(). */ native_machine_crash_shutdown(regs); + + /* Disable the hypercall page when there is only 1 active CPU. */ + hyperv_cleanup(); } #endif /* CONFIG_KEXEC_CORE */ #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 23ad8e953dfb..a29997e6cf9e 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -167,9 +167,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, *repeat = 0; *uniform = 1; - /* Make end inclusive instead of exclusive */ - end--; - prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state, inclusive; @@ -261,6 +258,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) int repeat; u64 partial_end; + /* Make end inclusive instead of exclusive */ + end--; + if (!mtrr_state_set) return MTRR_TYPE_INVALID; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 29ffb95b25ff..460f3e0df106 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -525,89 +525,70 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp) kfree(rdtgrp); } -struct task_move_callback { - struct callback_head work; - struct rdtgroup *rdtgrp; -}; - -static void move_myself(struct callback_head *head) +static void _update_task_closid_rmid(void *task) { - struct task_move_callback *callback; - struct rdtgroup *rdtgrp; - - callback = container_of(head, struct task_move_callback, work); - rdtgrp = callback->rdtgrp; - /* - * If resource group was deleted before this task work callback - * was invoked, then assign the task to root group and free the - * resource group. + * If the task is still current on this CPU, update PQR_ASSOC MSR. + * Otherwise, the MSR is updated when the task is scheduled in. */ - if (atomic_dec_and_test(&rdtgrp->waitcount) && - (rdtgrp->flags & RDT_DELETED)) { - current->closid = 0; - current->rmid = 0; - rdtgroup_remove(rdtgrp); - } - - if (unlikely(current->flags & PF_EXITING)) - goto out; - - preempt_disable(); - /* update PQR_ASSOC MSR to make resource group go into effect */ - resctrl_sched_in(); - preempt_enable(); + if (task == current) + resctrl_sched_in(); +} -out: - kfree(callback); +static void update_task_closid_rmid(struct task_struct *t) +{ + if (IS_ENABLED(CONFIG_SMP) && task_curr(t)) + smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1); + else + _update_task_closid_rmid(t); } static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { - struct task_move_callback *callback; - int ret; - - callback = kzalloc(sizeof(*callback), GFP_KERNEL); - if (!callback) - return -ENOMEM; - callback->work.func = move_myself; - callback->rdtgrp = rdtgrp; + /* If the task is already in rdtgrp, no need to move the task. */ + if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && + tsk->rmid == rdtgrp->mon.rmid) || + (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && + tsk->closid == rdtgrp->mon.parent->closid)) + return 0; /* - * Take a refcount, so rdtgrp cannot be freed before the - * callback has been invoked. + * Set the task's closid/rmid before the PQR_ASSOC MSR can be + * updated by them. + * + * For ctrl_mon groups, move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. */ - atomic_inc(&rdtgrp->waitcount); - ret = task_work_add(tsk, &callback->work, TWA_RESUME); - if (ret) { - /* - * Task is exiting. Drop the refcount and free the callback. - * No need to check the refcount as the group cannot be - * deleted before the write function unlocks rdtgroup_mutex. - */ - atomic_dec(&rdtgrp->waitcount); - kfree(callback); - rdt_last_cmd_puts("Task exited\n"); - } else { - /* - * For ctrl_mon groups move both closid and rmid. - * For monitor groups, can move the tasks only from - * their parent CTRL group. - */ - if (rdtgrp->type == RDTCTRL_GROUP) { - tsk->closid = rdtgrp->closid; + + if (rdtgrp->type == RDTCTRL_GROUP) { + tsk->closid = rdtgrp->closid; + tsk->rmid = rdtgrp->mon.rmid; + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) { tsk->rmid = rdtgrp->mon.rmid; - } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) { - tsk->rmid = rdtgrp->mon.rmid; - } else { - rdt_last_cmd_puts("Can't move task to different control group\n"); - ret = -EINVAL; - } + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } } - return ret; + + /* + * Ensure the task's closid and rmid are written before determining if + * the task is current that will decide if it will be interrupted. + */ + barrier(); + + /* + * By now, the task's closid and rmid are set. If the task is current + * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource + * group go into effect. If the task is not current, the MSR will be + * updated when the task is scheduled in. + */ + update_task_closid_rmid(tsk); + + return 0; } static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 1068002c8532..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -25,10 +25,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -#ifdef CONFIG_SMP unsigned int __max_die_per_package __read_mostly = 1; EXPORT_SYMBOL(__max_die_per_package); +#ifdef CONFIG_SMP /* * Check if given CPUID extended toplogy "leaf" is implemented */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eb86a2b831b1..571220ac8bea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(copy_fpregs_to_fpstate); -void kernel_fpu_begin(void) +void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); @@ -141,13 +141,14 @@ void kernel_fpu_begin(void) } __cpu_invalidate_fpregs_state(); - if (boot_cpu_has(X86_FEATURE_XMM)) + /* Put sane initial values into the control registers. */ + if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); - if (boot_cpu_has(X86_FEATURE_FPU)) + if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } -EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 740f3bdb3f61..3412c4595efd 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -661,17 +661,6 @@ static void __init trim_platform_memory_ranges(void) static void __init trim_bios_range(void) { /* - * A special case is the first 4Kb of memory; - * This is a BIOS owned area, not kernel ram, but generally - * not listed as such in the E820 table. - * - * This typically reserves additional memory (64KiB by default) - * since some BIOSes are known to corrupt low memory. See the - * Kconfig help text for X86_RESERVE_LOW. - */ - e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); - - /* * special case: Some BIOSes report the PC BIOS * area (640Kb -> 1Mb) as RAM even though it is not. * take them out. @@ -728,6 +717,15 @@ early_param("reservelow", parse_reservelow); static void __init trim_low_memory_range(void) { + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. + */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); } diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 7d04b356d44d..cdc04d091242 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -305,14 +305,14 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0xe4: case 0xe5: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* OUT immediate opcodes */ case 0xe6: case 0xe7: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* IN register opcodes */ diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0bd1a0fc587e..84c1821819af 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void) return __rdmsr(MSR_AMD64_SEV_ES_GHCB); } -static inline void sev_es_wr_ghcb_msr(u64 val) +static __always_inline void sev_es_wr_ghcb_msr(u64 val) { u32 low, high; @@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(target, size)) { + memcpy(dst, buf, size); + return ES_OK; + } + switch (size) { case 1: memcpy(&d1, buf, 1); @@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(s, size)) { + memcpy(buf, src, size); + return ES_OK; + } + switch (size) { case 1: if (get_user(d1, s)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8ca66af96a54..117e24fbfd8a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> +#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -2083,6 +2084,23 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) +{ + /* Bail out if registered already. */ + if (freq_invariance_syscore_ops.node.prev) + return; + + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif + static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2109,6 +2127,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready) if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3136e05831cf..43cceadd073e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -674,7 +674,7 @@ static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) (unsigned long long)vcpu->arch.pv_eoi.msr_val); return false; } - return val & 0x1; + return val & KVM_PV_EOI_ENABLED; } static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) @@ -2898,7 +2898,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) /* evaluate pending_events before reading the vector */ smp_rmb(); sipi_vector = apic->sipi_vector; - kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); + kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9c4a9c8e43d9..581925e476d6 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -49,7 +49,7 @@ static inline u64 rsvd_bits(int s, int e) if (e < s) return 0; - return ((1ULL << (e - s + 1)) - 1) << s; + return ((2ULL << (e - s)) - 1) << s; } void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c478904af518..6d16481aa29d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3493,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { struct kvm_shadow_walk_iterator iterator; - int leaf = vcpu->arch.mmu->root_level; + int leaf = -1; u64 spte; - walk_shadow_page_lockless_begin(vcpu); - for (shadow_walk_init(&iterator, vcpu, addr); + for (shadow_walk_init(&iterator, vcpu, addr), + *root_level = iterator.level; shadow_walk_okay(&iterator); __shadow_walk_next(&iterator, spte)) { leaf = iterator.level; spte = mmu_spte_get_lockless(iterator.sptep); - sptes[leaf - 1] = spte; + sptes[leaf] = spte; if (!is_shadow_present_pte(spte)) break; - } walk_shadow_page_lockless_end(vcpu); @@ -3520,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) return leaf; } -/* return true if reserved bit is detected on spte. */ +/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { - u64 sptes[PT64_ROOT_MAX_LEVEL]; + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->shadow_root_level; - int leaf; - int level; + int root, leaf, level; bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) { @@ -3536,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) } if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) - leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes); + leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else - leaf = get_walk(vcpu, addr, sptes); + leaf = get_walk(vcpu, addr, sptes, &root); + + if (unlikely(leaf < 0)) { + *sptep = 0ull; + return reserved; + } + + *sptep = sptes[leaf]; + + /* + * Skip reserved bits checks on the terminal leaf if it's not a valid + * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by + * design, always have reserved bits set. The purpose of the checks is + * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs. + */ + if (!is_shadow_present_pte(sptes[leaf])) + leaf++; rsvd_check = &vcpu->arch.mmu->shadow_zero_check; - for (level = root; level >= leaf; level--) { - if (!is_shadow_present_pte(sptes[level - 1])) - break; + for (level = root; level >= leaf; level--) /* * Use a bitwise-OR instead of a logical-OR to aggregate the * reserved bit and EPT's invalid memtype/XWR checks to avoid * adding a Jcc in the loop. */ - reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) | - __is_rsvd_bits_set(rsvd_check, sptes[level - 1], - level); - } + reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) | + __is_rsvd_bits_set(rsvd_check, sptes[level], level); if (reserved) { pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", __func__, addr); for (level = root; level >= leaf; level--) pr_err("------ spte 0x%llx level %d.\n", - sptes[level - 1], level); + sptes[level], level); } - *sptep = sptes[leaf - 1]; - return reserved; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 4bd2f1dc0172..2ef8615f9dba 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -44,7 +44,48 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); } -#define for_each_tdp_mmu_root(_kvm, _root) \ +static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) +{ + if (kvm_mmu_put_root(kvm, root)) + kvm_tdp_mmu_free_root(kvm, root); +} + +static inline bool tdp_mmu_next_root_valid(struct kvm *kvm, + struct kvm_mmu_page *root) +{ + lockdep_assert_held(&kvm->mmu_lock); + + if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link)) + return false; + + kvm_mmu_get_root(kvm, root); + return true; + +} + +static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, + struct kvm_mmu_page *root) +{ + struct kvm_mmu_page *next_root; + + next_root = list_next_entry(root, link); + tdp_mmu_put_root(kvm, root); + return next_root; +} + +/* + * Note: this iterator gets and puts references to the roots it iterates over. + * This makes it safe to release the MMU lock and yield within the loop, but + * if exiting the loop early, the caller must drop the reference to the most + * recent root. (Unless keeping a live reference is desirable.) + */ +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = list_first_entry(&_kvm->arch.tdp_mmu_roots, \ + typeof(*_root), link); \ + tdp_mmu_next_root_valid(_kvm, _root); \ + _root = tdp_mmu_next_root(_kvm, _root)) + +#define for_each_tdp_mmu_root(_kvm, _root) \ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) @@ -447,18 +488,9 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) struct kvm_mmu_page *root; bool flush = false; - for_each_tdp_mmu_root(kvm, root) { - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - + for_each_tdp_mmu_root_yield_safe(kvm, root) flush |= zap_gfn_range(kvm, root, start, end, true); - kvm_mmu_put_root(kvm, root); - } - return flush; } @@ -619,13 +651,7 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start, int ret = 0; int as_id; - for_each_tdp_mmu_root(kvm, root) { - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - + for_each_tdp_mmu_root_yield_safe(kvm, root) { as_id = kvm_mmu_page_as_id(root); slots = __kvm_memslots(kvm, as_id); kvm_for_each_memslot(memslot, slots) { @@ -647,8 +673,6 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start, ret |= handler(kvm, memslot, root, gfn_start, gfn_end, data); } - - kvm_mmu_put_root(kvm, root); } return ret; @@ -838,21 +862,13 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot, int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); - - kvm_mmu_put_root(kvm, root); } return spte_set; @@ -906,21 +922,13 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot) int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } return spte_set; @@ -1029,21 +1037,13 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } return spte_set; } @@ -1089,21 +1089,13 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; int root_as_id; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - zap_collapsible_spte_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } } @@ -1160,16 +1152,19 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level) { struct tdp_iter iter; struct kvm_mmu *mmu = vcpu->arch.mmu; - int leaf = vcpu->arch.mmu->shadow_root_level; gfn_t gfn = addr >> PAGE_SHIFT; + int leaf = -1; + + *root_level = vcpu->arch.mmu->shadow_root_level; tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { leaf = iter.level; - sptes[leaf - 1] = iter.old_spte; + sptes[leaf] = iter.old_spte; } return leaf; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 556e065503f6..cbbdbadd1526 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes); +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level); + #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b0b667456b2e..cb4c6ee10029 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -199,6 +199,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (!nested_svm_vmrun_msrpm(svm)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = @@ -595,6 +596,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm->nested.vmcb12_gpa = 0; WARN_ON_ONCE(svm->nested.nested_run_pending); + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu); + /* in case we halted in L2 */ svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -754,6 +757,7 @@ void svm_leave_nested(struct vcpu_svm *svm) leave_guest_mode(&svm->vcpu); copy_vmcb_control_area(&vmcb->control, &hsave->control); nested_svm_uninit_mmu_context(&svm->vcpu); + vmcb_mark_all_dirty(svm->vmcb); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu); @@ -1194,6 +1198,10 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * in the registers, the save area of the nested state instead * contains saved L1 state. */ + + svm->nested.nested_run_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + copy_vmcb_control_area(&hsave->control, &svm->vmcb->control); hsave->save = *save; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 9858d5ae9ddd..c8ffdbc81709 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1563,6 +1563,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: + case SVM_VMGEXIT_AP_HLT_LOOP: case SVM_VMGEXIT_AP_JUMP_TABLE: case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; @@ -1888,6 +1889,9 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); break; + case SVM_VMGEXIT_AP_HLT_LOOP: + ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + break; case SVM_VMGEXIT_AP_JUMP_TABLE: { struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; @@ -2001,7 +2005,7 @@ void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu) * of which one step is to perform a VMLOAD. Since hardware does not * perform a VMSAVE on VMRUN, the host savearea must be updated. */ - asm volatile(__ex("vmsave") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); + asm volatile(__ex("vmsave %0") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); /* * Certain MSRs are restored on VMEXIT, only save ones that aren't @@ -2040,3 +2044,21 @@ void sev_es_vcpu_put(struct vcpu_svm *svm) wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); } } + +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* First SIPI: Use the values as initially set by the VMM */ + if (!svm->received_first_sipi) { + svm->received_first_sipi = true; + return; + } + + /* + * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where + * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a + * non-zero value. + */ + ghcb_set_sw_exit_info_2(svm->ghcb, 1); +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index cce0143a6f80..7ef171790d02 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3677,8 +3677,6 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } -void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); - static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_svm *svm) { @@ -4384,6 +4382,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT)); } +static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + if (!sev_es_guest(vcpu->kvm)) + return kvm_vcpu_deliver_sipi_vector(vcpu, vector); + + sev_vcpu_deliver_sipi_vector(vcpu, vector); +} + static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); @@ -4526,6 +4532,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .msr_filter_changed = svm_msr_filter_changed, .complete_emulated_msr = svm_complete_emulated_msr, + + .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5431e6335e2e..0fe874ae5498 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -185,6 +185,7 @@ struct vcpu_svm { struct vmcb_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; + bool received_first_sipi; /* SEV-ES scratch area support */ void *ghcb_sa; @@ -591,6 +592,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu); void sev_es_vcpu_put(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e2f26564a12d..0fbb46990dfc 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4442,6 +4442,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + /* Service the TLB flush request for L2 before switching to L1. */ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 75c9c6a0a3a4..2af05d3b0590 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7707,6 +7707,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, .cpu_dirty_log_size = vmx_cpu_dirty_log_size, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; static __init int hardware_setup(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3f7c1fc7a3ce..9a8969a6dd06 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7976,17 +7976,22 @@ void kvm_arch_exit(void) kmem_cache_destroy(x86_fpu_cache); } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) { ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + vcpu->arch.mp_state = state; return 1; } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; + vcpu->run->exit_reason = reason; return 0; } } + +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +{ + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} EXPORT_SYMBOL_GPL(kvm_vcpu_halt); int kvm_emulate_halt(struct kvm_vcpu *vcpu) @@ -8000,6 +8005,14 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -8789,7 +8802,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { - if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { + if (WARN_ON_ONCE(!is_guest_mode(vcpu))) + ; + else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; goto out; } @@ -9094,6 +9109,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) kvm_apic_accept_events(vcpu); switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -9520,8 +9536,9 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); - if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && - vcpu->arch.pv.pv_unhalted) + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || + vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && + vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; @@ -10152,6 +10169,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } +EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); int kvm_arch_hardware_enable(void) { diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index 4321fa02e18d..419365c48b2a 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -26,6 +26,16 @@ #include <asm/fpu/api.h> #include <asm/asm.h> +/* + * Use KFPU_387. MMX instructions are not affected by MXCSR, + * but both AMD and Intel documentation states that even integer MMX + * operations will result in #MF if an exception is pending in FCW. + * + * EMMS is not needed afterwards because, after calling kernel_fpu_end(), + * any subsequent user of the 387 stack will reinitialize it using + * KFPU_387. + */ + void *_mmx_memcpy(void *to, const void *from, size_t len) { void *p; @@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) p = to; i = len >> 6; /* len/64 */ - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" /* This set is 28 bytes */ @@ -127,7 +137,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -160,7 +170,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); /* * maybe the prefetch stuff can go before the expensive fnsave... @@ -247,7 +257,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -282,7 +292,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index dfd82f51ba66..f6a9e2e36642 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -829,6 +829,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) } free_page((unsigned long)pmd_sv); + + pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); return 1; diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 9e87ab010c82..e68ea5f4ad1c 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) else per_cpu(xen_vcpu_id, cpu) = cpu; rc = xen_vcpu_setup(cpu); - if (rc) + if (rc || !xen_have_vector_callback) return rc; - if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) + if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); @@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu) return 0; } +static bool no_vector_callback __initdata; + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) + if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; xen_hvm_smp_init(); @@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg) } early_param("xen_nopv", xen_parse_nopv); +static __init int xen_parse_no_vector_callback(char *arg) +{ + no_vector_callback = true; + return 0; +} +early_param("xen_no_vector_callback", xen_parse_no_vector_callback); + bool __init xen_hvm_need_lapic(void) { if (xen_pv_domain()) diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f5e7db4f82ab..6ff3c887e0b9 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) int cpu; native_smp_prepare_cpus(max_cpus); - WARN_ON(xen_smp_intr_init(0)); - xen_init_lock_cpu(0); + if (xen_have_vector_callback) { + WARN_ON(xen_smp_intr_init(0)); + xen_init_lock_cpu(0); + } for_each_possible_cpu(cpu) { if (cpu == 0) @@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static void xen_hvm_cpu_die(unsigned int cpu) { if (common_cpu_die(cpu) == 0) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); + if (xen_have_vector_callback) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + } } } #else @@ -64,14 +68,19 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) + smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_cpus_done = xen_smp_cpus_done; + smp_ops.cpu_die = xen_hvm_cpu_die; + + if (!xen_have_vector_callback) { +#ifdef CONFIG_PARAVIRT_SPINLOCKS + nopvspin = true; +#endif return; + } - smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; - smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; - smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; - smp_ops.smp_cpus_done = xen_smp_cpus_done; } |