diff options
Diffstat (limited to 'arch/x86')
86 files changed, 3482 insertions, 1183 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index fcd3b4d24eea..63bf349b2b24 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,6 +55,7 @@ config X86 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PHYS_TO_DMA + select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 @@ -62,6 +63,7 @@ config X86 select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX + select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_ZONE_DEVICE if X86_64 select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -69,7 +71,6 @@ config X86 select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_SUPPORTS_ATOMIC_RMW - select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS @@ -117,6 +118,7 @@ config X86 select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER + select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 @@ -322,7 +324,7 @@ config X86_64_SMP config X86_32_LAZY_GS def_bool y - depends on X86_32 && !CC_STACKPROTECTOR + depends on X86_32 && CC_STACKPROTECTOR_NONE config ARCH_SUPPORTS_UPROBES def_bool y @@ -1266,9 +1268,9 @@ config MICROCODE CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the initrd for microcode blobs. - In addition, you can build-in the microcode into the kernel. For that you - need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode - to the CONFIG_EXTRA_FIRMWARE config option. + In addition, you can build the microcode into the kernel. For that you + need to add the vendor-supplied microcode to the CONFIG_EXTRA_FIRMWARE + config option. config MICROCODE_INTEL bool "Intel microcode loading support" diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 1e3883e45687..74f6eee15179 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -21,6 +21,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/user-return-notifier.h> +#include <linux/nospec.h> #include <linux/uprobes.h> #include <linux/livepatch.h> #include <linux/syscalls.h> @@ -206,7 +207,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -282,7 +283,8 @@ __visible void do_syscall_64(struct pt_regs *regs) * regs->orig_ax, which changes the behavior of some syscalls. */ if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { - regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls); + regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); } @@ -304,7 +306,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - current->thread.status |= TS_COMPAT; + ti->status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { @@ -318,6 +320,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) } if (likely(nr < IA32_NR_syscalls)) { + nr = array_index_nospec(nr, IA32_NR_syscalls); /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 2a35b1e0fb90..16c2c022540d 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -566,6 +566,11 @@ restore_all: .Lrestore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code .Lirq_return: + /* + * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization + * when returning from IPI handler and when returning from + * scheduler to user-space. + */ INTERRUPT_RETURN .section .fixup, "ax" @@ -895,6 +900,9 @@ BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, hyperv_vector_handler) +BUILD_INTERRUPT3(hyperv_reenlightenment_vector, HYPERV_REENLIGHTENMENT_VECTOR, + hyperv_reenlightenment_intr) + #endif /* CONFIG_HYPERV */ ENTRY(page_fault) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a83570495162..30c8c5344c4a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -236,91 +236,20 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ - sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ - UNWIND_HINT_REGS extra=0 - - TRACE_IRQS_OFF - - /* - * If we need to do entry work or if we guess we'll need to do - * exit work, go straight to the slow path. - */ - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz entry_SYSCALL64_slow_path - -entry_SYSCALL_64_fastpath: - /* - * Easy case: enable interrupts and issue the syscall. If the syscall - * needs pt_regs, we'll call a stub that disables interrupts again - * and jumps to the slow path. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx - - /* - * This call instruction is handled specially in stub_ptregs_64. - * It might end up jumping to the slow path. If it jumps, RAX - * and all argument registers are clobbered. - */ -#ifdef CONFIG_RETPOLINE - movq sys_call_table(, %rax, 8), %rax - call __x86_indirect_thunk_rax -#else - call *sys_call_table(, %rax, 8) -#endif -.Lentry_SYSCALL_64_after_fastpath_call: - - movq %rax, RAX(%rsp) -1: + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS - /* - * If we get here, then we know that pt_regs is clean for SYSRET64. - * If we see that no exit work is required (which we are required - * to check with IRQs off), then we can go straight to SYSRET64. - */ - DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz 1f - LOCKDEP_SYS_EXIT - TRACE_IRQS_ON /* user mode is traced as IRQs on */ - movq RIP(%rsp), %rcx - movq EFLAGS(%rsp), %r11 - addq $6*8, %rsp /* skip extra regs -- they were preserved */ - UNWIND_HINT_EMPTY - jmp .Lpop_c_regs_except_rcx_r11_and_sysret - -1: - /* - * The fast path looked good when we started, but something changed - * along the way and we need to switch to the slow path. Calling - * raise(3) will trigger this, for example. IRQs are off. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - SAVE_EXTRA_REGS - movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ - jmp return_from_SYSCALL_64 - -entry_SYSCALL64_slow_path: /* IRQs are off. */ - SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ -return_from_SYSCALL_64: TRACE_IRQS_IRETQ /* we're about to change IF */ /* @@ -393,7 +322,6 @@ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY POP_EXTRA_REGS -.Lpop_c_regs_except_rcx_r11_and_sysret: popq %rsi /* skip r11 */ popq %r10 popq %r9 @@ -424,47 +352,6 @@ syscall_return_via_sysret: USERGS_SYSRET64 END(entry_SYSCALL_64) -ENTRY(stub_ptregs_64) - /* - * Syscalls marked as needing ptregs land here. - * If we are on the fast path, we need to save the extra regs, - * which we achieve by trying again on the slow path. If we are on - * the slow path, the extra regs are already saved. - * - * RAX stores a pointer to the C function implementing the syscall. - * IRQs are on. - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow path - */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - popq %rax - UNWIND_HINT_REGS extra=0 - jmp entry_SYSCALL64_slow_path - -1: - JMP_NOSPEC %rax /* Called from C */ -END(stub_ptregs_64) - -.macro ptregs_stub func -ENTRY(ptregs_\func) - UNWIND_HINT_FUNC - leaq \func(%rip), %rax - jmp stub_ptregs_64 -END(ptregs_\func) -.endm - -/* Instantiate ptregs_stub for each ptregs-using syscall */ -#define __SYSCALL_64_QUAL_(sym) -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym -#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) -#include <asm/syscalls_64.h> - /* * %rdi: prev task * %rsi: next task @@ -804,6 +691,10 @@ GLOBAL(restore_regs_and_return_to_kernel) POP_EXTRA_REGS POP_C_REGS addq $8, %rsp /* skip regs->orig_ax */ + /* + * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization + * when returning from IPI handler. + */ INTERRUPT_RETURN ENTRY(native_iret) @@ -1245,6 +1136,9 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ #if IS_ENABLED(CONFIG_HYPERV) apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ hyperv_callback_vector hyperv_vector_handler + +apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \ + hyperv_reenlightenment_vector hyperv_reenlightenment_intr #endif /* CONFIG_HYPERV */ idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 9c09775e589d..c176d2fab1da 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -7,14 +7,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_64_QUAL_(sym) sym -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), +#define __SYSCALL_64(nr, sym, qual) [nr] = sym, extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 8e4ea143ed96..78f91ec1056e 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -93,7 +93,8 @@ struct amd_nb { PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \ - PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER) + PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \ + PERF_SAMPLE_PERIOD) #define PEBS_REGS \ (PERF_REG_X86_AX | \ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 189a398290db..2edc49e7409b 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -18,6 +18,8 @@ */ #include <linux/types.h> +#include <asm/apic.h> +#include <asm/desc.h> #include <asm/hypervisor.h> #include <asm/hyperv.h> #include <asm/mshyperv.h> @@ -37,6 +39,7 @@ struct ms_hyperv_tsc_page *hv_get_tsc_page(void) { return tsc_pg; } +EXPORT_SYMBOL_GPL(hv_get_tsc_page); static u64 read_hv_clock_tsc(struct clocksource *arg) { @@ -101,6 +104,115 @@ static int hv_cpu_init(unsigned int cpu) return 0; } +static void (*hv_reenlightenment_cb)(void); + +static void hv_reenlightenment_notify(struct work_struct *dummy) +{ + struct hv_tsc_emulation_status emu_status; + + rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status); + + /* Don't issue the callback if TSC accesses are not emulated */ + if (hv_reenlightenment_cb && emu_status.inprogress) + hv_reenlightenment_cb(); +} +static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify); + +void hyperv_stop_tsc_emulation(void) +{ + u64 freq; + struct hv_tsc_emulation_status emu_status; + + rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status); + emu_status.inprogress = 0; + wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status); + + rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq); + tsc_khz = div64_u64(freq, 1000); +} +EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation); + +static inline bool hv_reenlightenment_available(void) +{ + /* + * Check for required features and priviliges to make TSC frequency + * change notifications work. + */ + return ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE && + ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT; +} + +__visible void __irq_entry hyperv_reenlightenment_intr(struct pt_regs *regs) +{ + entering_ack_irq(); + + inc_irq_stat(irq_hv_reenlightenment_count); + + schedule_delayed_work(&hv_reenlightenment_work, HZ/10); + + exiting_irq(); +} + +void set_hv_tscchange_cb(void (*cb)(void)) +{ + struct hv_reenlightenment_control re_ctrl = { + .vector = HYPERV_REENLIGHTENMENT_VECTOR, + .enabled = 1, + .target_vp = hv_vp_index[smp_processor_id()] + }; + struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1}; + + if (!hv_reenlightenment_available()) { + pr_warn("Hyper-V: reenlightenment support is unavailable\n"); + return; + } + + hv_reenlightenment_cb = cb; + + /* Make sure callback is registered before we write to MSRs */ + wmb(); + + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); + wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl)); +} +EXPORT_SYMBOL_GPL(set_hv_tscchange_cb); + +void clear_hv_tscchange_cb(void) +{ + struct hv_reenlightenment_control re_ctrl; + + if (!hv_reenlightenment_available()) + return; + + rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl); + re_ctrl.enabled = 0; + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl); + + hv_reenlightenment_cb = NULL; +} +EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb); + +static int hv_cpu_die(unsigned int cpu) +{ + struct hv_reenlightenment_control re_ctrl; + unsigned int new_cpu; + + if (hv_reenlightenment_cb == NULL) + return 0; + + rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); + if (re_ctrl.target_vp == hv_vp_index[cpu]) { + /* Reassign to some other online CPU */ + new_cpu = cpumask_any_but(cpu_online_mask, cpu); + + re_ctrl.target_vp = hv_vp_index[new_cpu]; + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); + } + + return 0; +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -110,12 +222,19 @@ static int hv_cpu_init(unsigned int cpu) */ void hyperv_init(void) { - u64 guest_id; + u64 guest_id, required_msrs; union hv_x64_msr_hypercall_contents hypercall_msr; if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; + /* Absolutely required MSRs */ + required_msrs = HV_X64_MSR_HYPERCALL_AVAILABLE | + HV_X64_MSR_VP_INDEX_AVAILABLE; + + if ((ms_hyperv.features & required_msrs) != required_msrs) + return; + /* Allocate percpu VP index */ hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index), GFP_KERNEL); @@ -123,7 +242,7 @@ void hyperv_init(void) return; if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online", - hv_cpu_init, NULL) < 0) + hv_cpu_init, hv_cpu_die) < 0) goto free_vp_index; /* @@ -239,17 +358,24 @@ void hyperv_report_panic(struct pt_regs *regs, long err) } EXPORT_SYMBOL_GPL(hyperv_report_panic); -bool hv_is_hypercall_page_setup(void) +bool hv_is_hyperv_initialized(void) { union hv_x64_msr_hypercall_contents hypercall_msr; - /* Check if the hypercall page is setup */ + /* + * Ensure that we're really on Hyper-V, and not a KVM or Xen + * emulation of Hyper-V + */ + if (x86_hyper_type != X86_HYPER_MS_HYPERV) + return false; + + /* + * Verify that earlier initialization succeeded by checking + * that the hypercall page is setup + */ hypercall_msr.as_uint64 = 0; rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - if (!hypercall_msr.enable) - return false; - - return true; + return hypercall_msr.enable; } -EXPORT_SYMBOL_GPL(hv_is_hypercall_page_setup); +EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 5d6a53fd7521..de690c2d2e33 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -6,7 +6,6 @@ generated-y += unistd_32_ia32.h generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h -generic-y += clkdev.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 7fb336210e1b..30d406146016 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -24,6 +24,34 @@ #define wmb() asm volatile("sfence" ::: "memory") #endif +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * Returns: + * 0 - (index < size) + */ +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + asm ("cmp %1,%2; sbb %0,%0;" + :"=r" (mask) + :"r"(size),"r" (index) + :"cc"); + return mask; +} + +/* Override the default implementation from linux/nospec.h. */ +#define array_index_mask_nospec array_index_mask_nospec + +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ + "lfence", X86_FEATURE_LFENCE_RDTSC) + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1d9199e1c2ad..0dfe4d3f74e2 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -210,6 +210,7 @@ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ +#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 64c4a30e0d39..e203169931c7 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -137,8 +137,10 @@ enum fixed_addresses { extern void reserve_top_address(unsigned long reserve); -#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_TOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_TOT_START (FIXADDR_TOP - FIXADDR_TOT_SIZE) extern int fixmaps_set; diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 51cc979dd364..7c341a74ec8c 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -38,6 +38,9 @@ typedef struct { #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) unsigned int irq_hv_callback_count; #endif +#if IS_ENABLED(CONFIG_HYPERV) + unsigned int irq_hv_reenlightenment_count; +#endif } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 35a6bc4da8ad..cf090e584202 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -10,6 +10,10 @@ * * Things ending in "2" are usually because we have no better * name for them. There's no processor called "SILVERMONT2". + * + * While adding a new CPUID for a new microarchitecture, add a new + * group to keep logically sorted out in chronological order. Within + * that group keep the CPUID for the variants sorted by model number. */ #define INTEL_FAM6_CORE_YONAH 0x0E @@ -49,6 +53,8 @@ #define INTEL_FAM6_KABYLAKE_MOBILE 0x8E #define INTEL_FAM6_KABYLAKE_DESKTOP 0x9E +#define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_PINEVIEW 0x1C diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h index 528ed4be4393..9e7adcdbe031 100644 --- a/arch/x86/include/asm/intel_pmc_ipc.h +++ b/arch/x86/include/asm/intel_pmc_ipc.h @@ -38,6 +38,7 @@ int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen); int intel_pmc_s0ix_counter_read(u64 *data); int intel_pmc_gcr_read(u32 offset, u32 *data); +int intel_pmc_gcr_read64(u32 offset, u64 *data); int intel_pmc_gcr_write(u32 offset, u32 data); int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val); @@ -70,6 +71,11 @@ static inline int intel_pmc_gcr_read(u32 offset, u32 *data) return -EINVAL; } +static inline int intel_pmc_gcr_read64(u32 offset, u64 *data) +{ + return -EINVAL; +} + static inline int intel_pmc_gcr_write(u32 offset, u32 data) { return -EINVAL; diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 7d87437bd030..3de0489deade 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -147,6 +147,18 @@ int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb); int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb); /** + * iosf_mbi_unregister_pmic_bus_access_notifier_unlocked - Unregister PMIC bus + * notifier, unlocked + * + * Like iosf_mbi_unregister_pmic_bus_access_notifier(), but for use when the + * caller has already called iosf_mbi_punit_acquire() itself. + * + * @nb: notifier_block to unregister + */ +int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked( + struct notifier_block *nb); + +/** * iosf_mbi_call_pmic_bus_access_notifier_chain - Call PMIC bus notifier chain * * @val: action to pass into listener's notifier_call function @@ -154,6 +166,11 @@ int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb); */ int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v); +/** + * iosf_mbi_assert_punit_acquired - Assert that the P-Unit has been acquired. + */ +void iosf_mbi_assert_punit_acquired(void); + #else /* CONFIG_IOSF_MBI is not enabled */ static inline bool iosf_mbi_available(void) @@ -197,12 +214,20 @@ int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb) return 0; } +static inline int +iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(struct notifier_block *nb) +{ + return 0; +} + static inline int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v) { return 0; } +static inline void iosf_mbi_assert_punit_acquired(void) {} + #endif /* CONFIG_IOSF_MBI */ #endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 67421f649cfa..e71c1120426b 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -103,7 +103,12 @@ #endif #define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef -#define LOCAL_TIMER_VECTOR 0xee + +#if IS_ENABLED(CONFIG_HYPERV) +#define HYPERV_REENLIGHTENMENT_VECTOR 0xee +#endif + +#define LOCAL_TIMER_VECTOR 0xed #define NR_VECTORS 256 diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h index b577dd0916aa..13e70da38bed 100644 --- a/arch/x86/include/asm/kasan.h +++ b/arch/x86/include/asm/kasan.h @@ -4,6 +4,7 @@ #include <linux/const.h> #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) +#define KASAN_SHADOW_SCALE_SHIFT 3 /* * Compiler uses shadow offset assuming that addresses start @@ -12,12 +13,15 @@ * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT */ #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - ((-1UL << __VIRTUAL_MASK_SHIFT) >> 3)) + ((-1UL << __VIRTUAL_MASK_SHIFT) >> \ + KASAN_SHADOW_SCALE_SHIFT)) /* - * 47 bits for kernel address -> (47 - 3) bits for shadow - * 56 bits for kernel address -> (56 - 3) bits for shadow + * 47 bits for kernel address -> (47 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow + * 56 bits for kernel address -> (56 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow */ -#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3))) +#define KASAN_SHADOW_END (KASAN_SHADOW_START + \ + (1ULL << (__VIRTUAL_MASK_SHIFT - \ + KASAN_SHADOW_SCALE_SHIFT))) #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 516798431328..dd6f57a54a26 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -86,7 +86,7 @@ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ - | X86_CR4_SMAP | X86_CR4_PKE)) + | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) @@ -504,6 +504,7 @@ struct kvm_vcpu_arch { int mp_state; u64 ia32_misc_enable_msr; u64 smbase; + u64 smi_count; bool tpr_access_reporting; u64 ia32_xss; @@ -760,6 +761,15 @@ enum kvm_irqchip_mode { KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; +struct kvm_sev_info { + bool active; /* SEV enabled guest */ + unsigned int asid; /* ASID used for this guest */ + unsigned int handle; /* SEV firmware handle */ + int fd; /* SEV device fd */ + unsigned long pages_locked; /* Number of pages locked */ + struct list_head regions_list; /* List of registered regions */ +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -847,6 +857,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + struct kvm_sev_info sev_info; }; struct kvm_vm_stat { @@ -883,7 +895,6 @@ struct kvm_vcpu_stat { u64 request_irq_exits; u64 irq_exits; u64 host_state_reload; - u64 efer_reload; u64 fpu_reload; u64 insn_emulation; u64 insn_emulation_fail; @@ -965,7 +976,7 @@ struct kvm_x86_ops { unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); - void (*tlb_flush)(struct kvm_vcpu *vcpu); + void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); void (*run)(struct kvm_vcpu *vcpu); int (*handle_exit)(struct kvm_vcpu *vcpu); @@ -1017,6 +1028,7 @@ struct kvm_x86_ops { void (*handle_external_intr)(struct kvm_vcpu *vcpu); bool (*mpx_supported)(void); bool (*xsaves_supported)(void); + bool (*umip_emulated)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); @@ -1079,6 +1091,10 @@ struct kvm_x86_ops { int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); int (*enable_smi_window)(struct kvm_vcpu *vcpu); + + int (*mem_enc_op)(struct kvm *kvm, void __user *argp); + int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); + int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); }; struct kvm_arch_async_pf { diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 8bf450b13d9f..25283f7eb299 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -160,6 +160,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) #define hv_set_synint_state(int_num, val) wrmsrl(int_num, val) void hyperv_callback_vector(void); +void hyperv_reenlightenment_vector(void); #ifdef CONFIG_TRACING #define trace_hyperv_callback_vector hyperv_callback_vector #endif @@ -314,20 +315,29 @@ void hyperv_init(void); void hyperv_setup_mmu_ops(void); void hyper_alloc_mmu(void); void hyperv_report_panic(struct pt_regs *regs, long err); -bool hv_is_hypercall_page_setup(void); +bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); + +void hyperv_reenlightenment_intr(struct pt_regs *regs); +void set_hv_tscchange_cb(void (*cb)(void)); +void clear_hv_tscchange_cb(void); +void hyperv_stop_tsc_emulation(void); #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} -static inline bool hv_is_hypercall_page_setup(void) { return false; } +static inline bool hv_is_hyperv_initialized(void) { return false; } static inline void hyperv_cleanup(void) {} static inline void hyperv_setup_mmu_ops(void) {} +static inline void set_hv_tscchange_cb(void (*cb)(void)) {} +static inline void clear_hv_tscchange_cb(void) {} +static inline void hyperv_stop_tsc_emulation(void) {}; #endif /* CONFIG_HYPERV */ #ifdef CONFIG_HYPERV_TSCPAGE struct ms_hyperv_tsc_page *hv_get_tsc_page(void); -static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) +static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc) { - u64 scale, offset, cur_tsc; + u64 scale, offset; u32 sequence; /* @@ -358,7 +368,7 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) scale = READ_ONCE(tsc_pg->tsc_scale); offset = READ_ONCE(tsc_pg->tsc_offset); - cur_tsc = rdtsc_ordered(); + *cur_tsc = rdtsc_ordered(); /* * Make sure we read sequence after we read all other values @@ -368,7 +378,14 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence); - return mul_u64_u64_shr(cur_tsc, scale, 64) + offset; + return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset; +} + +static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) +{ + u64 cur_tsc; + + return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc); } #else @@ -376,5 +393,12 @@ static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) { return NULL; } + +static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc) +{ + BUG(); + return U64_MAX; +} #endif #endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e520a1e6fc11..c9084dedfcfa 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -397,6 +397,8 @@ #define MSR_K7_PERFCTR3 0xc0010007 #define MSR_K7_CLK_CTL 0xc001001b #define MSR_K7_HWCR 0xc0010015 +#define MSR_K7_HWCR_SMMLOCK_BIT 0 +#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 07962f5f6fba..30df295f6d94 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -214,8 +214,7 @@ static __always_inline unsigned long long rdtsc_ordered(void) * that some other imaginary CPU is updating continuously with a * time stamp. */ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); + barrier_nospec(); return rdtsc(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index d15d471348b8..4d57894635f2 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -150,7 +150,7 @@ extern char __indirect_thunk_end[]; * On VMEXIT we must ensure that no RSB predictions learned in the guest * can be followed in the host, by overwriting the RSB completely. Both * retpoline and IBRS mitigations for Spectre v2 need this; only on future - * CPUs with IBRS_ATT *might* it be avoided. + * CPUs with IBRS_ALL *might* it be avoided. */ static inline void vmexit_fill_RSB(void) { diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 8a3ee355b422..92015c65fa2a 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -22,4 +22,6 @@ int io_reserve_memtype(resource_size_t start, resource_size_t end, void io_free_memtype(resource_size_t start, resource_size_t end); +bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn); + #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index bc4af5453802..f24df59c40b2 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -158,7 +158,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep) #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) #endif -#ifdef CONFIG_SMP union split_pmd { struct { u32 pmd_low; @@ -166,6 +165,8 @@ union split_pmd { }; pmd_t pmd; }; + +#ifdef CONFIG_SMP static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp) { union split_pmd res, *orig = (union split_pmd *)pmdp; @@ -181,6 +182,40 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp) #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) #endif +#ifndef pmdp_establish +#define pmdp_establish pmdp_establish +static inline pmd_t pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old; + + /* + * If pmd has present bit cleared we can get away without expensive + * cmpxchg64: we can update pmdp half-by-half without racing with + * anybody. + */ + if (!(pmd_val(pmd) & _PAGE_PRESENT)) { + union split_pmd old, new, *ptr; + + ptr = (union split_pmd *)pmdp; + + new.pmd = pmd; + + /* xchg acts as a barrier before setting of the high bits */ + old.pmd_low = xchg(&ptr->pmd_low, new.pmd_low); + old.pmd_high = ptr->pmd_high; + ptr->pmd_high = new.pmd_high; + return old.pmd; + } + + do { + old = *pmdp; + } while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd); + + return old; +} +#endif + #ifdef CONFIG_SMP union split_pud { struct { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e42b8943cb1a..63c2552b6b65 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1109,6 +1109,21 @@ static inline int pud_write(pud_t pud) return pud_flags(pud) & _PAGE_RW; } +#ifndef pmdp_establish +#define pmdp_establish pmdp_establish +static inline pmd_t pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + if (IS_ENABLED(CONFIG_SMP)) { + return xchg(pmdp, pmd); + } else { + pmd_t old = *pmdp; + *pmdp = pmd; + return old; + } +} +#endif + /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index ce245b0cdfca..0777e18a1d23 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -44,8 +44,9 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ */ #define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK) +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ + & PMD_MASK) #define PKMAP_BASE \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) diff --git a/arch/x86/include/asm/pmc_core.h b/arch/x86/include/asm/pmc_core.h deleted file mode 100644 index d4855f11136d..000000000000 --- a/arch/x86/include/asm/pmc_core.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Intel Core SoC Power Management Controller Header File - * - * Copyright (c) 2016, Intel Corporation. - * All Rights Reserved. - * - * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com> - * Vishwanath Somayaji <vishwanath.somayaji@intel.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - */ - -#ifndef _ASM_PMC_CORE_H -#define _ASM_PMC_CORE_H - -/* API to read SLP_S0_RESIDENCY counter */ -int intel_pmc_slp_s0_counter_read(u32 *data); - -#endif /* _ASM_PMC_CORE_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index efbde088a718..793bae7e7ce3 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -460,8 +460,6 @@ struct thread_struct { unsigned short gsindex; #endif - u32 status; /* thread synchronous flags */ - #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; @@ -507,6 +505,14 @@ struct thread_struct { */ }; +/* Whitelist the FPU state from the task_struct for hardened usercopy. */ +static inline void arch_thread_struct_whitelist(unsigned long *offset, + unsigned long *size) +{ + *offset = offsetof(struct thread_struct, fpu.state); + *size = fpu_kernel_xstate_size; +} + /* * Thread-synchronous status. * diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 78dd9df88157..0487ac054870 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -146,6 +146,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL #define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL +#define SVM_NESTED_CTL_NP_ENABLE BIT(0) +#define SVM_NESTED_CTL_SEV_ENABLE BIT(1) + struct __attribute__ ((__packed__)) vmcb_seg { u16 selector; u16 attrib; diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h new file mode 100644 index 000000000000..c67caafd3381 --- /dev/null +++ b/arch/x86/include/asm/sync_core.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SYNC_CORE_H +#define _ASM_X86_SYNC_CORE_H + +#include <linux/preempt.h> +#include <asm/processor.h> +#include <asm/cpufeature.h> + +/* + * Ensure that a core serializing instruction is issued before returning + * to user-mode. x86 implements return to user-space through sysexit, + * sysrel, and sysretq, which are not core serializing. + */ +static inline void sync_core_before_usermode(void) +{ + /* With PTI, we unconditionally serialize before running user code. */ + if (static_cpu_has(X86_FEATURE_PTI)) + return; + /* + * Return from interrupt and NMI is done through iret, which is core + * serializing. + */ + if (in_irq() || in_nmi()) + return; + sync_core(); +} + +#endif /* _ASM_X86_SYNC_CORE_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index e3c95e8e61c5..03eedc21246d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d25a638a2720..a5d9521bb2cb 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -55,6 +55,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ }; #define INIT_THREAD_INFO(tsk) \ @@ -219,7 +220,7 @@ static inline int arch_within_stack_frames(const void * const stack, #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ - current->thread.status & TS_COMPAT) + current_thread_info()->status & TS_COMPAT) #endif /* diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index d33e4a26dc7e..2b8f18ca5874 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -174,6 +174,8 @@ struct tlb_state { struct mm_struct *loaded_mm; u16 loaded_mm_asid; u16 next_asid; + /* last user mm's ctx id */ + u64 last_ctx_id; /* * We can be in one of several states: diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 574dff4d2913..aae77eb8491c 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -124,6 +124,11 @@ extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) /* * This is a type: either unsigned long, if the argument fits into @@ -445,7 +450,7 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -487,6 +492,10 @@ struct __large_struct { unsigned long buf[100]; }; __uaccess_begin(); \ barrier(); +#define uaccess_try_nospec do { \ + current->thread.uaccess_err = 0; \ + __uaccess_begin_nospec(); \ + #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ @@ -548,7 +557,7 @@ struct __large_struct { unsigned long buf[100]; }; * get_user_ex(...); * } get_user_catch(err) */ -#define get_user_try uaccess_try +#define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ @@ -582,7 +591,7 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 72950401b223..ba2dc1930630 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -29,21 +29,21 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)to, from, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)to, from, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)to, from, ret, "l", "k", "=r", 4); __uaccess_end(); diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f07ef3c575db..62546b3a398e 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -55,31 +55,31 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) @@ -89,7 +89,7 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) __uaccess_end(); return ret; case 16: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 1a5bfead93b4..197c2e6c7376 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -40,6 +40,9 @@ */ #define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11) +/* AccessReenlightenmentControls privilege */ +#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13) + /* * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available @@ -234,6 +237,30 @@ #define HV_X64_MSR_CRASH_PARAMS \ (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) +/* TSC emulation after migration */ +#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 + +struct hv_reenlightenment_control { + u64 vector:8; + u64 reserved1:8; + u64 enabled:1; + u64 reserved2:15; + u64 target_vp:32; +}; + +#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 +#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 + +struct hv_tsc_emulation_control { + u64 enabled:1; + u64 reserved:63; +}; + +struct hv_tsc_emulation_status { + u64 inprogress:1; + u64 reserved:63; +}; + #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 09cc06483bed..7a2ade4aa235 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -25,6 +25,7 @@ #define KVM_FEATURE_STEAL_TIME 5 #define KVM_FEATURE_PV_EOI 6 #define KVM_FEATURE_PV_UNHALT 7 +#define KVM_FEATURE_PV_TLB_FLUSH 9 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. @@ -51,6 +52,9 @@ struct kvm_steal_time { __u32 pad[11]; }; +#define KVM_VCPU_PREEMPTED (1 << 0) +#define KVM_VCPU_FLUSH_TLB (1 << 1) + #define KVM_CLOCK_PAIRING_WALLCLOCK 0 struct kvm_clock_pairing { __s64 sec; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index ec3a286163c3..2aa92094b59d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -36,6 +36,7 @@ #include <linux/ioport.h> #include <linux/pci.h> #include <linux/efi-bgrt.h> +#include <linux/serial_core.h> #include <asm/e820/api.h> #include <asm/irqdomain.h> @@ -1625,6 +1626,8 @@ int __init acpi_boot_init(void) if (!acpi_noirq) x86_init.pci.init = pci_acpi_init; + /* Do not enable ACPI SPCR console by default */ + acpi_parse_spcr(earlycon_acpi_spcr_enable, false); return 0; } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 30571fdaaf6f..a481763a3776 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -599,9 +588,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ab1865342002..dc0ca8e29c75 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -2389,6 +2389,7 @@ static int __init apm_init(void) if (HZ != 100) idle_period = (idle_period * HZ) / 100; if (idle_threshold < 100) { + cpuidle_poll_state_init(&apm_idle_driver); if (!cpuidle_register_driver(&apm_idle_driver)) if (cpuidle_register_device(&apm_cpuidle_device)) cpuidle_unregister_driver(&apm_idle_driver); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ea831c858195..5bddbdcbc4a3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -556,6 +556,51 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } } +static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) +{ + u64 msr; + + /* + * BIOS support is required for SME and SEV. + * For SME: If BIOS has enabled SME then adjust x86_phys_bits by + * the SME physical address space reduction value. + * If BIOS has not enabled SME then don't advertise the + * SME feature (set in scattered.c). + * For SEV: If BIOS has not enabled SEV then don't advertise the + * SEV feature (set in scattered.c). + * + * In all cases, since support for SME and SEV requires long mode, + * don't advertise the feature under CONFIG_X86_32. + */ + if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) { + /* Check if memory encryption is enabled */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + goto clear_all; + + /* + * Always adjust physical address bits. Even though this + * will be a value above 32-bits this is still done for + * CONFIG_X86_32 so that accurate values are reported. + */ + c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f; + + if (IS_ENABLED(CONFIG_X86_32)) + goto clear_all; + + rdmsrl(MSR_K7_HWCR, msr); + if (!(msr & MSR_K7_HWCR_SMMLOCK)) + goto clear_sev; + + return; + +clear_all: + clear_cpu_cap(c, X86_FEATURE_SME); +clear_sev: + clear_cpu_cap(c, X86_FEATURE_SEV); + } +} + static void early_init_amd(struct cpuinfo_x86 *c) { u32 dummy; @@ -627,26 +672,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_E400); - /* - * BIOS support is required for SME. If BIOS has enabled SME then - * adjust x86_phys_bits by the SME physical address space reduction - * value. If BIOS has not enabled SME then don't advertise the - * feature (set in scattered.c). Also, since the SME support requires - * long mode, don't advertise the feature under CONFIG_X86_32. - */ - if (cpu_has(c, X86_FEATURE_SME)) { - u64 msr; - - /* Check if SME is enabled */ - rdmsrl(MSR_K8_SYSCFG, msr); - if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) { - c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f; - if (IS_ENABLED(CONFIG_X86_32)) - clear_cpu_cap(c, X86_FEATURE_SME); - } else { - clear_cpu_cap(c, X86_FEATURE_SME); - } - } + early_detect_mem_encrypt(c); } static void init_amd_k8(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3bfb2b23d79c..71949bf2de5a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -103,7 +103,7 @@ bool retpoline_module_ok(bool has_retpoline) if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) return true; - pr_err("System may be vunerable to spectre v2\n"); + pr_err("System may be vulnerable to spectre v2\n"); spectre_v2_bad_module = true; return false; } @@ -119,13 +119,13 @@ static inline const char *spectre_v2_module_string(void) { return ""; } static void __init spec2_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static void __init spec2_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static inline bool retp_compiler(void) @@ -140,42 +140,68 @@ static inline bool match_option(const char *arg, int arglen, const char *opt) return len == arglen && !strncmp(arg, opt, len); } +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { char arg[20]; - int ret; - - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); - if (ret > 0) { - if (match_option(arg, ret, "off")) { - goto disable; - } else if (match_option(arg, ret, "on")) { - spec2_print_if_secure("force enabled on command line."); - return SPECTRE_V2_CMD_FORCE; - } else if (match_option(arg, ret, "retpoline")) { - spec2_print_if_insecure("retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE; - } else if (match_option(arg, ret, "retpoline,amd")) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); - return SPECTRE_V2_CMD_AUTO; - } - spec2_print_if_insecure("AMD retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_AMD; - } else if (match_option(arg, ret, "retpoline,generic")) { - spec2_print_if_insecure("generic retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_GENERIC; - } else if (match_option(arg, ret, "auto")) { + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; } - if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); return SPECTRE_V2_CMD_AUTO; -disable: - spec2_print_if_insecure("disabled on command line."); - return SPECTRE_V2_CMD_NONE; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; } /* Check for Skylake-like CPUs (for RSB handling) */ @@ -213,10 +239,10 @@ static void __init spectre_v2_select_mitigation(void) return; case SPECTRE_V2_CMD_FORCE: - /* FALLTRHU */ case SPECTRE_V2_CMD_AUTO: - goto retpoline_auto; - + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; case SPECTRE_V2_CMD_RETPOLINE_AMD: if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_amd; @@ -297,7 +323,7 @@ ssize_t cpu_show_spectre_v1(struct device *dev, { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Vulnerable\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } ssize_t cpu_show_spectre_v2(struct device *dev, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c7c996a692fd..d63f4b5706e4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -750,6 +750,26 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) } } +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -844,6 +864,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); /* * Clear/Set all flags overridden by options, after probe. @@ -879,7 +900,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } -static const __initdata struct x86_cpu_id cpu_no_speculation[] = { +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, @@ -892,7 +913,7 @@ static const __initdata struct x86_cpu_id cpu_no_speculation[] = { {} }; -static const __initdata struct x86_cpu_id cpu_no_meltdown[] = { +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { { X86_VENDOR_AMD }, {} }; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 6936d14d4c77..319bf989fad1 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -175,28 +175,17 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) c->microcode = intel_get_microcode_revision(); - /* - * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, - * and they also have a different bit for STIBP support. Also, - * a hypervisor might have set the individual AMD bits even on - * Intel CPUs, for finer-grained selection of what's available. - */ - if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { - set_cpu_cap(c, X86_FEATURE_IBRS); - set_cpu_cap(c, X86_FEATURE_IBPB); - } - if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) - set_cpu_cap(c, X86_FEATURE_STIBP); - /* Now if any of them are set, check the blacklist and clear the lot */ - if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); - clear_cpu_cap(c, X86_FEATURE_IBRS); - clear_cpu_cap(c, X86_FEATURE_IBPB); - clear_cpu_cap(c, X86_FEATURE_STIBP); - clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL); - clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index ba1f9555fbc5..3a8e88a611eb 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -14,7 +14,6 @@ #include <linux/capability.h> #include <linux/miscdevice.h> #include <linux/ratelimit.h> -#include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/kobject.h> #include <linux/uaccess.h> @@ -235,7 +234,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - print_symbol("{%s}", m->ip); + pr_cont("{%pS}", (void *)m->ip); pr_cont("\n"); } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index e4fc595cd6ea..319dd65f98a2 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -560,7 +560,7 @@ static ssize_t pf_show(struct device *dev, return sprintf(buf, "0x%x\n", uci->cpu_sig.pf); } -static DEVICE_ATTR(reload, 0200, NULL, reload_store); +static DEVICE_ATTR_WO(reload); static DEVICE_ATTR(version, 0400, version_show, NULL); static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 85eb5fc180c8..9340f41ce8d3 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -251,6 +251,12 @@ static void __init ms_hyperv_init_platform(void) hyperv_setup_mmu_ops(); /* Setup the IDT for hypervisor callback */ alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + + /* Setup the IDT for reenlightenment notifications */ + if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT) + alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR, + hyperv_reenlightenment_vector); + #endif } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 4075d2be5357..772c219b6889 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -30,6 +30,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, + { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 76e07698e6d1..25de5f6ca997 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -2,7 +2,6 @@ /* * Architecture specific OF callbacks. */ -#include <linux/bootmem.h> #include <linux/export.h> #include <linux/io.h> #include <linux/interrupt.h> @@ -39,11 +38,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) BUG(); } -void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) -{ - return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); -} - void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index afbecff161d1..a2d8a3908670 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -109,7 +109,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, struct stack_info stack_info = {0}; unsigned long visit_mask = 0; int graph_idx = 0; - bool partial; + bool partial = false; printk("%sCall Trace:\n", log_lvl); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 1e82f787c160..bae0d32e327b 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -243,7 +243,7 @@ static void __init intel_remapping_check(int num, int slot, int func) #define KB(x) ((x) * 1024UL) #define MB(x) (KB (KB (x))) -static size_t __init i830_tseg_size(void) +static resource_size_t __init i830_tseg_size(void) { u8 esmramc = read_pci_config_byte(0, 0, 0, I830_ESMRAMC); @@ -256,7 +256,7 @@ static size_t __init i830_tseg_size(void) return KB(512); } -static size_t __init i845_tseg_size(void) +static resource_size_t __init i845_tseg_size(void) { u8 esmramc = read_pci_config_byte(0, 0, 0, I845_ESMRAMC); u8 tseg_size = esmramc & I845_TSEG_SIZE_MASK; @@ -273,7 +273,7 @@ static size_t __init i845_tseg_size(void) return 0; } -static size_t __init i85x_tseg_size(void) +static resource_size_t __init i85x_tseg_size(void) { u8 esmramc = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC); @@ -283,12 +283,12 @@ static size_t __init i85x_tseg_size(void) return MB(1); } -static size_t __init i830_mem_size(void) +static resource_size_t __init i830_mem_size(void) { return read_pci_config_byte(0, 0, 0, I830_DRB3) * MB(32); } -static size_t __init i85x_mem_size(void) +static resource_size_t __init i85x_mem_size(void) { return read_pci_config_byte(0, 0, 1, I85X_DRB3) * MB(32); } @@ -297,36 +297,36 @@ static size_t __init i85x_mem_size(void) * On 830/845/85x the stolen memory base isn't available in any * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size. */ -static phys_addr_t __init i830_stolen_base(int num, int slot, int func, - size_t stolen_size) +static resource_size_t __init i830_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) { - return (phys_addr_t)i830_mem_size() - i830_tseg_size() - stolen_size; + return i830_mem_size() - i830_tseg_size() - stolen_size; } -static phys_addr_t __init i845_stolen_base(int num, int slot, int func, - size_t stolen_size) +static resource_size_t __init i845_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) { - return (phys_addr_t)i830_mem_size() - i845_tseg_size() - stolen_size; + return i830_mem_size() - i845_tseg_size() - stolen_size; } -static phys_addr_t __init i85x_stolen_base(int num, int slot, int func, - size_t stolen_size) +static resource_size_t __init i85x_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) { - return (phys_addr_t)i85x_mem_size() - i85x_tseg_size() - stolen_size; + return i85x_mem_size() - i85x_tseg_size() - stolen_size; } -static phys_addr_t __init i865_stolen_base(int num, int slot, int func, - size_t stolen_size) +static resource_size_t __init i865_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) { u16 toud = 0; toud = read_pci_config_16(0, 0, 0, I865_TOUD); - return (phys_addr_t)(toud << 16) + i845_tseg_size(); + return toud * KB(64) + i845_tseg_size(); } -static phys_addr_t __init gen3_stolen_base(int num, int slot, int func, - size_t stolen_size) +static resource_size_t __init gen3_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) { u32 bsm; @@ -337,10 +337,10 @@ static phys_addr_t __init gen3_stolen_base(int num, int slot, int func, */ bsm = read_pci_config(num, slot, func, INTEL_BSM); - return (phys_addr_t)bsm & INTEL_BSM_MASK; + return bsm & INTEL_BSM_MASK; } -static size_t __init i830_stolen_size(int num, int slot, int func) +static resource_size_t __init i830_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; u16 gms; @@ -361,7 +361,7 @@ static size_t __init i830_stolen_size(int num, int slot, int func) return 0; } -static size_t __init gen3_stolen_size(int num, int slot, int func) +static resource_size_t __init gen3_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; u16 gms; @@ -390,7 +390,7 @@ static size_t __init gen3_stolen_size(int num, int slot, int func) return 0; } -static size_t __init gen6_stolen_size(int num, int slot, int func) +static resource_size_t __init gen6_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; u16 gms; @@ -398,10 +398,10 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); gms = (gmch_ctrl >> SNB_GMCH_GMS_SHIFT) & SNB_GMCH_GMS_MASK; - return (size_t)gms * MB(32); + return gms * MB(32); } -static size_t __init gen8_stolen_size(int num, int slot, int func) +static resource_size_t __init gen8_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; u16 gms; @@ -409,10 +409,10 @@ static size_t __init gen8_stolen_size(int num, int slot, int func) gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); gms = (gmch_ctrl >> BDW_GMCH_GMS_SHIFT) & BDW_GMCH_GMS_MASK; - return (size_t)gms * MB(32); + return gms * MB(32); } -static size_t __init chv_stolen_size(int num, int slot, int func) +static resource_size_t __init chv_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; u16 gms; @@ -426,14 +426,14 @@ static size_t __init chv_stolen_size(int num, int slot, int func) * 0x17 to 0x1d: 4MB increments start at 36MB */ if (gms < 0x11) - return (size_t)gms * MB(32); + return gms * MB(32); else if (gms < 0x17) - return (size_t)(gms - 0x11 + 2) * MB(4); + return (gms - 0x11) * MB(4) + MB(8); else - return (size_t)(gms - 0x17 + 9) * MB(4); + return (gms - 0x17) * MB(4) + MB(36); } -static size_t __init gen9_stolen_size(int num, int slot, int func) +static resource_size_t __init gen9_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; u16 gms; @@ -444,14 +444,15 @@ static size_t __init gen9_stolen_size(int num, int slot, int func) /* 0x0 to 0xef: 32MB increments starting at 0MB */ /* 0xf0 to 0xfe: 4MB increments starting at 4MB */ if (gms < 0xf0) - return (size_t)gms * MB(32); + return gms * MB(32); else - return (size_t)(gms - 0xf0 + 1) * MB(4); + return (gms - 0xf0) * MB(4) + MB(4); } struct intel_early_ops { - size_t (*stolen_size)(int num, int slot, int func); - phys_addr_t (*stolen_base)(int num, int slot, int func, size_t size); + resource_size_t (*stolen_size)(int num, int slot, int func); + resource_size_t (*stolen_base)(int num, int slot, int func, + resource_size_t size); }; static const struct intel_early_ops i830_early_ops __initconst = { @@ -527,16 +528,20 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_SKL_IDS(&gen9_early_ops), INTEL_BXT_IDS(&gen9_early_ops), INTEL_KBL_IDS(&gen9_early_ops), + INTEL_CFL_IDS(&gen9_early_ops), INTEL_GLK_IDS(&gen9_early_ops), INTEL_CNL_IDS(&gen9_early_ops), }; +struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0); +EXPORT_SYMBOL(intel_graphics_stolen_res); + static void __init intel_graphics_stolen(int num, int slot, int func, const struct intel_early_ops *early_ops) { - phys_addr_t base, end; - size_t size; + resource_size_t base, size; + resource_size_t end; size = early_ops->stolen_size(num, slot, func); base = early_ops->stolen_base(num, slot, func, size); @@ -545,8 +550,12 @@ intel_graphics_stolen(int num, int slot, int func, return; end = base + size - 1; - printk(KERN_INFO "Reserving Intel graphics memory at %pa-%pa\n", - &base, &end); + + intel_graphics_stolen_res.start = base; + intel_graphics_stolen_res.end = end; + + printk(KERN_INFO "Reserving Intel graphics memory at %pR\n", + &intel_graphics_stolen_res); /* Mark this space as reserved */ e820__range_add(base, size, E820_TYPE_RESERVED); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 68e1867cca80..45fb4d2565f8 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -142,6 +142,15 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Hypervisor callback interrupts\n"); } #endif +#if IS_ENABLED(CONFIG_HYPERV) + if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) { + seq_printf(p, "%*s: ", prec, "HRE"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->irq_hv_reenlightenment_count); + seq_puts(p, " Hyper-V reenlightenment interrupts\n"); + } +#endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b40ffbf156c1..4e37d1a851a6 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -498,6 +498,34 @@ static void __init kvm_apf_trap_init(void) update_intr_gate(X86_TRAP_PF, async_page_fault); } +static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask); + +static void kvm_flush_tlb_others(const struct cpumask *cpumask, + const struct flush_tlb_info *info) +{ + u8 state; + int cpu; + struct kvm_steal_time *src; + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask); + + cpumask_copy(flushmask, cpumask); + /* + * We have to call flush only on online vCPUs. And + * queue flush_on_enter for pre-empted vCPUs + */ + for_each_cpu(cpu, flushmask) { + src = &per_cpu(steal_time, cpu); + state = READ_ONCE(src->preempted); + if ((state & KVM_VCPU_PREEMPTED)) { + if (try_cmpxchg(&src->preempted, &state, + state | KVM_VCPU_FLUSH_TLB)) + __cpumask_clear_cpu(cpu, flushmask); + } + } + + native_flush_tlb_others(flushmask, info); +} + static void __init kvm_guest_init(void) { int i; @@ -517,6 +545,9 @@ static void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) + pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); @@ -598,6 +629,22 @@ static __init int activate_jump_labels(void) } arch_initcall(activate_jump_labels); +static __init int kvm_setup_pv_tlb_flush(void) +{ + int cpu; + + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) { + for_each_possible_cpu(cpu) { + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + } + pr_info("KVM setup pv remote TLB flush\n"); + } + + return 0; +} +arch_initcall(kvm_setup_pv_tlb_flush); + #ifdef CONFIG_PARAVIRT_SPINLOCKS /* Kick a cpu by its apicid. Used to wake up a halted vcpu */ @@ -643,7 +690,7 @@ __visible bool __kvm_vcpu_is_preempted(long cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); - return !!src->preempted; + return !!(src->preempted & KVM_VCPU_PREEMPTED); } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c75466232016..9eb448c7859d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -557,7 +557,7 @@ static void __set_personality_x32(void) * Pretend to come from a x32 execve. */ task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT; - current->thread.status &= ~TS_COMPAT; + current_thread_info()->status &= ~TS_COMPAT; #endif } @@ -571,7 +571,7 @@ static void __set_personality_ia32(void) current->personality |= force_personality32; /* Prepare the first "return" to user space */ task_pt_regs(current)->orig_ax = __NR_ia32_execve; - current->thread.status |= TS_COMPAT; + current_thread_info()->status |= TS_COMPAT; #endif } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f37d18124648..ed5c4cdf0a34 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -935,7 +935,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - child->thread.status |= TS_I386_REGS_POKED; + child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 307d3bac5f04..11eda21eb697 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -68,6 +68,9 @@ relocate_kernel: movq %cr4, %rax movq %rax, CR4(%r11) + /* Save CR4. Required to enable the right paging mode later. */ + movq %rax, %r13 + /* zero out flags, and disable interrupts */ pushq $0 popfq @@ -126,8 +129,13 @@ identity_mapped: /* * Set cr4 to a known state: * - physical address extension enabled + * - 5-level paging, if it was enabled before */ movl $X86_CR4_PAE, %eax + testq $X86_CR4_LA57, %r13 + jz 1f + orl $X86_CR4_LA57, %eax +1: movq %rax, %cr4 jmp 1f diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b9e00e8f1c9b..4cdc0b27ec82 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -787,7 +787,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3df51c287844..92fd433c50b9 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -81,6 +81,14 @@ config KVM_AMD To compile this as a module, choose M here: the module will be called kvm-amd. +config KVM_AMD_SEV + def_bool y + bool "AMD Secure Encrypted Virtualization (SEV) support" + depends on KVM_AMD && X86_64 + depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP + ---help--- + Provides support for launching Encrypted VMs on AMD processors. + config KVM_MMU_AUDIT bool "Audit KVM MMU" depends on KVM && TRACEPOINTS diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0099e10eb045..a0c5a69bc7c4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -67,9 +67,7 @@ u64 kvm_supported_xcr0(void) #define F(x) bit(X86_FEATURE_##x) -/* These are scattered features in cpufeatures.h. */ -#define KVM_CPUID_BIT_AVX512_4VNNIW 2 -#define KVM_CPUID_BIT_AVX512_4FMAPS 3 +/* For scattered features from cpufeatures.h; we currently expose none */ #define KF(x) bit(KVM_CPUID_BIT_##x) int kvm_update_cpuid(struct kvm_vcpu *vcpu) @@ -293,13 +291,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, { switch (func) { case 0: - entry->eax = 1; /* only one leaf currently */ + entry->eax = 7; ++*nent; break; case 1: entry->ecx = F(MOVBE); ++*nent; break; + case 7: + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + if (index == 0) + entry->ecx = F(RDPID); + ++*nent; default: break; } @@ -327,6 +330,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0; unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0; + unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; /* cpuid 1.edx */ const u32 kvm_cpuid_1_edx_x86_features = @@ -365,7 +369,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | + F(TOPOEXT); + + /* cpuid 0x80000008.ebx */ + const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(IBPB) | F(IBRS); /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -387,12 +396,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | - 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ); + F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | + F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG); /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS); + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -473,11 +484,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ebx |= F(TSC_ADJUST); entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; cpuid_mask(&entry->ecx, CPUID_7_ECX); + entry->ecx |= f_umip; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; - entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); + cpuid_mask(&entry->edx, CPUID_7_EDX); } else { entry->ebx = 0; entry->ecx = 0; @@ -594,7 +606,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_ASYNC_PF) | (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | - (1 << KVM_FEATURE_PV_UNHALT); + (1 << KVM_FEATURE_PV_UNHALT) | + (1 << KVM_FEATURE_PV_TLB_FLUSH); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); @@ -604,7 +617,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->edx = 0; break; case 0x80000000: - entry->eax = min(entry->eax, 0x8000001a); + entry->eax = min(entry->eax, 0x8000001f); break; case 0x80000001: entry->edx &= kvm_cpuid_8000_0001_edx_x86_features; @@ -627,7 +640,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; + entry->edx = 0; + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; } case 0x80000019: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c2cea6651279..9a327d5b6d1f 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -54,6 +54,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX}, [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, + [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, }; static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 290ecf711aec..d91eaeb01034 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3533,6 +3533,16 @@ static int em_cwd(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_rdpid(struct x86_emulate_ctxt *ctxt) +{ + u64 tsc_aux = 0; + + if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) + return emulate_gp(ctxt, 0); + ctxt->dst.val = tsc_aux; + return X86EMUL_CONTINUE; +} + static int em_rdtsc(struct x86_emulate_ctxt *ctxt) { u64 tsc = 0; @@ -3652,17 +3662,27 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) +static int em_store_sreg(struct x86_emulate_ctxt *ctxt, int segment) { - if (ctxt->modrm_reg > VCPU_SREG_GS) - return emulate_ud(ctxt); + if (segment > VCPU_SREG_GS && + (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) && + ctxt->ops->cpl(ctxt) > 0) + return emulate_gp(ctxt, 0); - ctxt->dst.val = get_segment_selector(ctxt, ctxt->modrm_reg); + ctxt->dst.val = get_segment_selector(ctxt, segment); if (ctxt->dst.bytes == 4 && ctxt->dst.type == OP_MEM) ctxt->dst.bytes = 2; return X86EMUL_CONTINUE; } +static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) +{ + if (ctxt->modrm_reg > VCPU_SREG_GS) + return emulate_ud(ctxt); + + return em_store_sreg(ctxt, ctxt->modrm_reg); +} + static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; @@ -3678,6 +3698,11 @@ static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg); } +static int em_sldt(struct x86_emulate_ctxt *ctxt) +{ + return em_store_sreg(ctxt, VCPU_SREG_LDTR); +} + static int em_lldt(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; @@ -3687,6 +3712,11 @@ static int em_lldt(struct x86_emulate_ctxt *ctxt) return load_segment_descriptor(ctxt, sel, VCPU_SREG_LDTR); } +static int em_str(struct x86_emulate_ctxt *ctxt) +{ + return em_store_sreg(ctxt, VCPU_SREG_TR); +} + static int em_ltr(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; @@ -3739,6 +3769,10 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, { struct desc_ptr desc_ptr; + if ((ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) && + ctxt->ops->cpl(ctxt) > 0) + return emulate_gp(ctxt, 0); + if (ctxt->mode == X86EMUL_MODE_PROT64) ctxt->op_bytes = 8; get(ctxt, &desc_ptr); @@ -3798,6 +3832,10 @@ static int em_lidt(struct x86_emulate_ctxt *ctxt) static int em_smsw(struct x86_emulate_ctxt *ctxt) { + if ((ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) && + ctxt->ops->cpl(ctxt) > 0) + return emulate_gp(ctxt, 0); + if (ctxt->dst.type == OP_MEM) ctxt->dst.bytes = 2; ctxt->dst.val = ctxt->ops->get_cr(ctxt, 0); @@ -4383,8 +4421,8 @@ static const struct opcode group5[] = { }; static const struct opcode group6[] = { - DI(Prot | DstMem, sldt), - DI(Prot | DstMem, str), + II(Prot | DstMem, em_sldt, sldt), + II(Prot | DstMem, em_str, str), II(Prot | Priv | SrcMem16, em_lldt, lldt), II(Prot | Priv | SrcMem16, em_ltr, ltr), N, N, N, N, @@ -4415,10 +4453,20 @@ static const struct opcode group8[] = { F(DstMem | SrcImmByte | Lock | PageTable, em_btc), }; +/* + * The "memory" destination is actually always a register, since we come + * from the register case of group9. + */ +static const struct gprefix pfx_0f_c7_7 = { + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), +}; + + static const struct group_dual group9 = { { N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { - N, N, N, N, N, N, N, N, + N, N, N, N, N, N, N, + GP(0, &pfx_0f_c7_7), } }; static const struct opcode group11[] = { diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 5c24811e8b0b..f171051eecf3 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -79,7 +79,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (kvm_cpu_has_extint(v)) return 1; - if (kvm_vcpu_apicv_active(v)) + if (!is_guest_mode(v) && kvm_vcpu_apicv_active(v)) return 0; return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e2c1fb8d35ce..924ac8ce9d50 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -364,32 +364,41 @@ static u8 count_vectors(void *bitmap) return count; } -int __kvm_apic_update_irr(u32 *pir, void *regs) +bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr) { u32 i, vec; - u32 pir_val, irr_val; - int max_irr = -1; + u32 pir_val, irr_val, prev_irr_val; + int max_updated_irr; + + max_updated_irr = -1; + *max_irr = -1; for (i = vec = 0; i <= 7; i++, vec += 32) { pir_val = READ_ONCE(pir[i]); irr_val = *((u32 *)(regs + APIC_IRR + i * 0x10)); if (pir_val) { + prev_irr_val = irr_val; irr_val |= xchg(&pir[i], 0); *((u32 *)(regs + APIC_IRR + i * 0x10)) = irr_val; + if (prev_irr_val != irr_val) { + max_updated_irr = + __fls(irr_val ^ prev_irr_val) + vec; + } } if (irr_val) - max_irr = __fls(irr_val) + vec; + *max_irr = __fls(irr_val) + vec; } - return max_irr; + return ((max_updated_irr != -1) && + (max_updated_irr == *max_irr)); } EXPORT_SYMBOL_GPL(__kvm_apic_update_irr); -int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) +bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr) { struct kvm_lapic *apic = vcpu->arch.apic; - return __kvm_apic_update_irr(pir, apic->regs); + return __kvm_apic_update_irr(pir, apic->regs, max_irr); } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); @@ -581,7 +590,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; - if (kvm_x86_ops->sync_pir_to_irr && apic->vcpu->arch.apicv_active) + if (apic->vcpu->arch.apicv_active) highest_irr = kvm_x86_ops->sync_pir_to_irr(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 4b9935a38347..56c36014f7b7 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -75,8 +75,8 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); -int __kvm_apic_update_irr(u32 *pir, void *regs); -int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); +bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); +bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2b8eb4da4d08..8eca1d04aeb8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -42,6 +42,7 @@ #include <linux/kern_levels.h> #include <asm/page.h> +#include <asm/pat.h> #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/vmx.h> @@ -381,7 +382,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); -void kvm_mmu_clear_all_pte_masks(void) +static void kvm_mmu_clear_all_pte_masks(void) { shadow_user_mask = 0; shadow_accessed_mask = 0; @@ -2708,7 +2709,18 @@ static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) - return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) && + /* + * Some reserved pages, such as those from NVDIMM + * DAX devices, are not for MMIO, and can be mapped + * with cached memory type for better performance. + * However, the above check misconceives those pages + * as MMIO, and results in KVM mapping them with UC + * memory type, which would hurt the performance. + * Therefore, we check the host memory type in addition + * and only treat UC/UC-/WC pages as MMIO. + */ + (!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn)); return true; } @@ -4951,6 +4963,16 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, if (mmio_info_in_cache(vcpu, cr2, direct)) emulation_type = 0; emulate: + /* + * On AMD platforms, under certain conditions insn_len may be zero on #NPF. + * This can happen if a guest gets a page-fault on data access but the HW + * table walker is not able to read the instruction page (e.g instruction + * page is not present in memory). In those cases we simply restart the + * guest. + */ + if (unlikely(insn && !insn_len)) + return 1; + er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); switch (er) { diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index d22ddbdf5e6e..1272861e77b9 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -19,7 +19,7 @@ #include <linux/ratelimit.h> -char const *audit_point_name[] = { +static char const *audit_point_name[] = { "pre page fault", "post page fault", "pre pte write", diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f40d0da1f1d3..b3e488a74828 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -37,6 +37,10 @@ #include <linux/amd-iommu.h> #include <linux/hashtable.h> #include <linux/frame.h> +#include <linux/psp-sev.h> +#include <linux/file.h> +#include <linux/pagemap.h> +#include <linux/swap.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -184,6 +188,8 @@ struct vcpu_svm { u64 gs_base; } host; + u64 spec_ctrl; + u32 *msrpm; ulong nmi_iret_rip; @@ -212,6 +218,9 @@ struct vcpu_svm { */ struct list_head ir_list; spinlock_t ir_list_lock; + + /* which host CPU was used for running this vcpu */ + unsigned int last_cpu; }; /* @@ -249,6 +258,8 @@ static const struct svm_direct_access_msrs { { .index = MSR_CSTAR, .always = true }, { .index = MSR_SYSCALL_MASK, .always = true }, #endif + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -285,8 +296,12 @@ module_param(vls, int, 0444); static int vgif = true; module_param(vgif, int, 0444); +/* enable/disable SEV support */ +static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); +module_param(sev, int, 0444); + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -static void svm_flush_tlb(struct kvm_vcpu *vcpu); +static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); static int nested_svm_exit_handled(struct vcpu_svm *svm); @@ -320,6 +335,38 @@ enum { #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL +static unsigned int max_sev_asid; +static unsigned int min_sev_asid; +static unsigned long *sev_asid_bitmap; +#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) + +struct enc_region { + struct list_head list; + unsigned long npages; + struct page **pages; + unsigned long uaddr; + unsigned long size; +}; + +static inline bool svm_sev_enabled(void) +{ + return max_sev_asid; +} + +static inline bool sev_guest(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + return sev->active; +} + +static inline int sev_get_asid(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + return sev->asid; +} + static inline void mark_all_dirty(struct vmcb *vmcb) { vmcb->control.clean = 0; @@ -526,9 +573,14 @@ struct svm_cpu_data { u64 asid_generation; u32 max_asid; u32 next_asid; + u32 min_asid; struct kvm_ldttss_desc *tss_desc; struct page *save_area; + struct vmcb *current_vmcb; + + /* index = sev_asid, value = vmcb pointer */ + struct vmcb **sev_vmcbs; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -783,6 +835,7 @@ static int svm_hardware_enable(void) sd->asid_generation = 1; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; + sd->min_asid = max_sev_asid + 1; gdt = get_current_gdt_rw(); sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); @@ -841,6 +894,7 @@ static void svm_cpu_uninit(int cpu) return; per_cpu(svm_data, raw_smp_processor_id()) = NULL; + kfree(sd->sev_vmcbs); __free_page(sd->save_area); kfree(sd); } @@ -854,11 +908,18 @@ static int svm_cpu_init(int cpu) if (!sd) return -ENOMEM; sd->cpu = cpu; - sd->save_area = alloc_page(GFP_KERNEL); r = -ENOMEM; + sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) goto err_1; + if (svm_sev_enabled()) { + r = -ENOMEM; + sd->sev_vmcbs = kmalloc((max_sev_asid + 1) * sizeof(void *), GFP_KERNEL); + if (!sd->sev_vmcbs) + goto err_1; + } + per_cpu(svm_data, cpu) = sd; return 0; @@ -880,6 +941,25 @@ static bool valid_msr_intercept(u32 index) return false; } +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr) +{ + u8 bit_write; + unsigned long tmp; + u32 offset; + u32 *msrpm; + + msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: + to_svm(vcpu)->msrpm; + + offset = svm_msrpm_offset(msr); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + return !!test_bit(bit_write, &tmp); +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { @@ -1046,6 +1126,48 @@ static int avic_ga_log_notifier(u32 ga_tag) return 0; } +static __init int sev_hardware_setup(void) +{ + struct sev_user_data_status *status; + int rc; + + /* Maximum number of encrypted guests supported simultaneously */ + max_sev_asid = cpuid_ecx(0x8000001F); + + if (!max_sev_asid) + return 1; + + /* Minimum ASID value that should be used for SEV guest */ + min_sev_asid = cpuid_edx(0x8000001F); + + /* Initialize SEV ASID bitmap */ + sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid), + sizeof(unsigned long), GFP_KERNEL); + if (!sev_asid_bitmap) + return 1; + + status = kmalloc(sizeof(*status), GFP_KERNEL); + if (!status) + return 1; + + /* + * Check SEV platform status. + * + * PLATFORM_STATUS can be called in any state, if we failed to query + * the PLATFORM status then either PSP firmware does not support SEV + * feature or SEV firmware is dead. + */ + rc = sev_platform_status(status, NULL); + if (rc) + goto err; + + pr_info("SEV supported\n"); + +err: + kfree(status); + return rc; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1081,6 +1203,17 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); } + if (sev) { + if (boot_cpu_has(X86_FEATURE_SEV) && + IS_ENABLED(CONFIG_KVM_AMD_SEV)) { + r = sev_hardware_setup(); + if (r) + sev = false; + } else { + sev = false; + } + } + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -1142,6 +1275,9 @@ static __exit void svm_hardware_unsetup(void) { int cpu; + if (svm_sev_enabled()) + kfree(sev_asid_bitmap); + for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -1294,7 +1430,7 @@ static void init_vmcb(struct vcpu_svm *svm) if (npt_enabled) { /* Setup VMCB for Nested Paging */ - control->nested_ctl = 1; + control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE; clr_intercept(svm, INTERCEPT_INVLPG); clr_exception_intercept(svm, PF_VECTOR); clr_cr_intercept(svm, INTERCEPT_CR3_READ); @@ -1332,6 +1468,11 @@ static void init_vmcb(struct vcpu_svm *svm) svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK; } + if (sev_guest(svm->vcpu.kvm)) { + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; + clr_exception_intercept(svm, UD_VECTOR); + } + mark_all_dirty(svm->vmcb); enable_gif(svm); @@ -1414,6 +1555,179 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +static void __sev_asid_free(int asid) +{ + struct svm_cpu_data *sd; + int cpu, pos; + + pos = asid - 1; + clear_bit(pos, sev_asid_bitmap); + + for_each_possible_cpu(cpu) { + sd = per_cpu(svm_data, cpu); + sd->sev_vmcbs[pos] = NULL; + } +} + +static void sev_asid_free(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + __sev_asid_free(sev->asid); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ + struct sev_data_decommission *decommission; + struct sev_data_deactivate *data; + + if (!handle) + return; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return; + + /* deactivate handle */ + data->handle = handle; + sev_guest_deactivate(data, NULL); + + wbinvd_on_all_cpus(); + sev_guest_df_flush(NULL); + kfree(data); + + decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); + if (!decommission) + return; + + /* decommission handle */ + decommission->handle = handle; + sev_guest_decommission(decommission, NULL); + + kfree(decommission); +} + +static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, + unsigned long ulen, unsigned long *n, + int write) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + unsigned long npages, npinned, size; + unsigned long locked, lock_limit; + struct page **pages; + int first, last; + + /* Calculate number of pages. */ + first = (uaddr & PAGE_MASK) >> PAGE_SHIFT; + last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT; + npages = (last - first + 1); + + locked = sev->pages_locked + npages; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { + pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit); + return NULL; + } + + /* Avoid using vmalloc for smaller buffers. */ + size = npages * sizeof(struct page *); + if (size > PAGE_SIZE) + pages = vmalloc(size); + else + pages = kmalloc(size, GFP_KERNEL); + + if (!pages) + return NULL; + + /* Pin the user virtual address. */ + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); + if (npinned != npages) { + pr_err("SEV: Failure locking %lu pages.\n", npages); + goto err; + } + + *n = npages; + sev->pages_locked = locked; + + return pages; + +err: + if (npinned > 0) + release_pages(pages, npinned); + + kvfree(pages); + return NULL; +} + +static void sev_unpin_memory(struct kvm *kvm, struct page **pages, + unsigned long npages) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + release_pages(pages, npages); + kvfree(pages); + sev->pages_locked -= npages; +} + +static void sev_clflush_pages(struct page *pages[], unsigned long npages) +{ + uint8_t *page_virtual; + unsigned long i; + + if (npages == 0 || pages == NULL) + return; + + for (i = 0; i < npages; i++) { + page_virtual = kmap_atomic(pages[i]); + clflush_cache_range(page_virtual, PAGE_SIZE); + kunmap_atomic(page_virtual); + } +} + +static void __unregister_enc_region_locked(struct kvm *kvm, + struct enc_region *region) +{ + /* + * The guest may change the memory encryption attribute from C=0 -> C=1 + * or vice versa for this memory range. Lets make sure caches are + * flushed to ensure that guest data gets written into memory with + * correct C-bit. + */ + sev_clflush_pages(region->pages, region->npages); + + sev_unpin_memory(kvm, region->pages, region->npages); + list_del(®ion->list); + kfree(region); +} + +static void sev_vm_destroy(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct list_head *head = &sev->regions_list; + struct list_head *pos, *q; + + if (!sev_guest(kvm)) + return; + + mutex_lock(&kvm->lock); + + /* + * if userspace was terminated before unregistering the memory regions + * then lets unpin all the registered memory. + */ + if (!list_empty(head)) { + list_for_each_safe(pos, q, head) { + __unregister_enc_region_locked(kvm, + list_entry(pos, struct enc_region, list)); + } + } + + mutex_unlock(&kvm->lock); + + sev_unbind_asid(kvm, sev->handle); + sev_asid_free(kvm); +} + static void avic_vm_destroy(struct kvm *kvm) { unsigned long flags; @@ -1432,6 +1746,12 @@ static void avic_vm_destroy(struct kvm *kvm) spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); } +static void svm_vm_destroy(struct kvm *kvm) +{ + avic_vm_destroy(kvm); + sev_vm_destroy(kvm); +} + static int avic_vm_init(struct kvm *kvm) { unsigned long flags; @@ -1582,6 +1902,8 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + svm->spec_ctrl = 0; + if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; @@ -1703,11 +2025,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So do a full IBPB now. + */ + indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int i; if (unlikely(cpu != vcpu->cpu)) { @@ -1736,6 +2064,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (static_cpu_has(X86_FEATURE_RDTSCP)) wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + indirect_branch_prediction_barrier(); + } avic_vcpu_load(vcpu, cpu); } @@ -2030,7 +2362,7 @@ static int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); vcpu->arch.cr4 = cr4; if (!npt_enabled) @@ -2089,7 +2421,7 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) { if (sd->next_asid > sd->max_asid) { ++sd->asid_generation; - sd->next_asid = 1; + sd->next_asid = sd->min_asid; svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; } @@ -2137,22 +2469,24 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) static int pf_interception(struct vcpu_svm *svm) { - u64 fault_address = svm->vmcb->control.exit_info_2; + u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); u64 error_code = svm->vmcb->control.exit_info_1; return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address, - svm->vmcb->control.insn_bytes, + static_cpu_has(X86_FEATURE_DECODEASSISTS) ? + svm->vmcb->control.insn_bytes : NULL, svm->vmcb->control.insn_len); } static int npf_interception(struct vcpu_svm *svm) { - u64 fault_address = svm->vmcb->control.exit_info_2; + u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); u64 error_code = svm->vmcb->control.exit_info_1; trace_kvm_page_fault(fault_address, error_code); return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code, - svm->vmcb->control.insn_bytes, + static_cpu_has(X86_FEATURE_DECODEASSISTS) ? + svm->vmcb->control.insn_bytes : NULL, svm->vmcb->control.insn_len); } @@ -2379,7 +2713,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, @@ -2921,7 +3255,8 @@ static bool nested_vmcb_checks(struct vmcb *vmcb) if (vmcb->control.asid == 0) return false; - if (vmcb->control.nested_ctl && !npt_enabled) + if ((vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && + !npt_enabled) return false; return true; @@ -2935,7 +3270,7 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, else svm->vcpu.arch.hflags &= ~HF_HIF_MASK; - if (nested_vmcb->control.nested_ctl) { + if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) { kvm_mmu_unload(&svm->vcpu); svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3; nested_svm_init_mmu_context(&svm->vcpu); @@ -2983,7 +3318,7 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; svm->nested.intercept = nested_vmcb->control.intercept; - svm_flush_tlb(&svm->vcpu); + svm_flush_tlb(&svm->vcpu, true); svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; @@ -3593,6 +3928,13 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_VM_CR: msr_info->data = svm->nested.vm_cr_msr; break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + msr_info->data = svm->spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3684,6 +4026,49 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; + case MSR_IA32_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + svm->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_svm_vmrun_msrpm. + * We update the L1 MSR bit as well since it will end up + * touching the MSR anyway now. + */ + set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + break; + case MSR_IA32_PRED_CMD: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + if (is_guest_mode(vcpu)) + break; + set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -4356,12 +4741,39 @@ static void reload_tss(struct kvm_vcpu *vcpu) load_TR_desc(); } +static void pre_sev_run(struct vcpu_svm *svm, int cpu) +{ + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + int asid = sev_get_asid(svm->vcpu.kvm); + + /* Assign the asid allocated with this SEV guest */ + svm->vmcb->control.asid = asid; + + /* + * Flush guest TLB: + * + * 1) when different VMCB for the same ASID is to be run on the same host CPU. + * 2) or this VMCB was executed on different host CPU in previous VMRUNs. + */ + if (sd->sev_vmcbs[asid] == svm->vmcb && + svm->last_cpu == cpu) + return; + + svm->last_cpu = cpu; + sd->sev_vmcbs[asid] = svm->vmcb; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; + mark_dirty(svm->vmcb, VMCB_ASID); +} + static void pre_svm_run(struct vcpu_svm *svm) { int cpu = raw_smp_processor_id(); struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + if (sev_guest(svm->vcpu.kvm)) + return pre_sev_run(svm, cpu); + /* FIXME: handle wraparound of asid_generation */ if (svm->asid_generation != sd->asid_generation) new_asid(svm, sd); @@ -4779,7 +5191,7 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void svm_flush_tlb(struct kvm_vcpu *vcpu) +static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4936,6 +5348,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + asm volatile ( "push %%" _ASM_BP "; \n\t" "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" @@ -5028,6 +5449,27 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -5092,7 +5534,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_CR); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) @@ -5106,7 +5548,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = kvm_read_cr3(vcpu); mark_dirty(svm->vmcb, VMCB_CR); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static int is_disabled(void) @@ -5192,6 +5634,12 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) entry->edx |= SVM_FEATURE_NPT; break; + case 0x8000001F: + /* Support memory encryption cpuid if host supports it */ + if (boot_cpu_has(X86_FEATURE_SEV)) + cpuid(0x8000001f, &entry->eax, &entry->ebx, + &entry->ecx, &entry->edx); + } } @@ -5220,6 +5668,11 @@ static bool svm_xsaves_supported(void) return false; } +static bool svm_umip_emulated(void) +{ + return false; +} + static bool svm_has_wbinvd_exit(void) { return true; @@ -5521,6 +5974,828 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static int sev_asid_new(void) +{ + int pos; + + /* + * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. + */ + pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1); + if (pos >= max_sev_asid) + return -EBUSY; + + set_bit(pos, sev_asid_bitmap); + return pos + 1; +} + +static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + int asid, ret; + + ret = -EBUSY; + asid = sev_asid_new(); + if (asid < 0) + return ret; + + ret = sev_platform_init(&argp->error); + if (ret) + goto e_free; + + sev->active = true; + sev->asid = asid; + INIT_LIST_HEAD(&sev->regions_list); + + return 0; + +e_free: + __sev_asid_free(asid); + return ret; +} + +static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) +{ + struct sev_data_activate *data; + int asid = sev_get_asid(kvm); + int ret; + + wbinvd_on_all_cpus(); + + ret = sev_guest_df_flush(error); + if (ret) + return ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* activate ASID on the given handle */ + data->handle = handle; + data->asid = asid; + ret = sev_guest_activate(data, error); + kfree(data); + + return ret; +} + +static int __sev_issue_cmd(int fd, int id, void *data, int *error) +{ + struct fd f; + int ret; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = sev_issue_cmd_external_user(f.file, id, data, error); + + fdput(f); + return ret; +} + +static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + return __sev_issue_cmd(sev->fd, id, data, error); +} + +static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_start *start; + struct kvm_sev_launch_start params; + void *dh_blob, *session_blob; + int *error = &argp->error; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + start = kzalloc(sizeof(*start), GFP_KERNEL); + if (!start) + return -ENOMEM; + + dh_blob = NULL; + if (params.dh_uaddr) { + dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len); + if (IS_ERR(dh_blob)) { + ret = PTR_ERR(dh_blob); + goto e_free; + } + + start->dh_cert_address = __sme_set(__pa(dh_blob)); + start->dh_cert_len = params.dh_len; + } + + session_blob = NULL; + if (params.session_uaddr) { + session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len); + if (IS_ERR(session_blob)) { + ret = PTR_ERR(session_blob); + goto e_free_dh; + } + + start->session_address = __sme_set(__pa(session_blob)); + start->session_len = params.session_len; + } + + start->handle = params.handle; + start->policy = params.policy; + + /* create memory encryption context */ + ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, start, error); + if (ret) + goto e_free_session; + + /* Bind ASID to this guest */ + ret = sev_bind_asid(kvm, start->handle, error); + if (ret) + goto e_free_session; + + /* return handle to userspace */ + params.handle = start->handle; + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { + sev_unbind_asid(kvm, start->handle); + ret = -EFAULT; + goto e_free_session; + } + + sev->handle = start->handle; + sev->fd = argp->sev_fd; + +e_free_session: + kfree(session_blob); +e_free_dh: + kfree(dh_blob); +e_free: + kfree(start); + return ret; +} + +static int get_num_contig_pages(int idx, struct page **inpages, + unsigned long npages) +{ + unsigned long paddr, next_paddr; + int i = idx + 1, pages = 1; + + /* find the number of contiguous pages starting from idx */ + paddr = __sme_page_pa(inpages[idx]); + while (i < npages) { + next_paddr = __sme_page_pa(inpages[i++]); + if ((paddr + PAGE_SIZE) == next_paddr) { + pages++; + paddr = next_paddr; + continue; + } + break; + } + + return pages; +} + +static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + unsigned long vaddr, vaddr_end, next_vaddr, npages, size; + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct kvm_sev_launch_update_data params; + struct sev_data_launch_update_data *data; + struct page **inpages; + int i, ret, pages; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + vaddr = params.uaddr; + size = params.len; + vaddr_end = vaddr + size; + + /* Lock the user memory. */ + inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1); + if (!inpages) { + ret = -ENOMEM; + goto e_free; + } + + /* + * The LAUNCH_UPDATE command will perform in-place encryption of the + * memory content (i.e it will write the same memory region with C=1). + * It's possible that the cache may contain the data with C=0, i.e., + * unencrypted so invalidate it first. + */ + sev_clflush_pages(inpages, npages); + + for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) { + int offset, len; + + /* + * If the user buffer is not page-aligned, calculate the offset + * within the page. + */ + offset = vaddr & (PAGE_SIZE - 1); + + /* Calculate the number of pages that can be encrypted in one go. */ + pages = get_num_contig_pages(i, inpages, npages); + + len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size); + + data->handle = sev->handle; + data->len = len; + data->address = __sme_page_pa(inpages[i]) + offset; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, data, &argp->error); + if (ret) + goto e_unpin; + + size -= len; + next_vaddr = vaddr + len; + } + +e_unpin: + /* content of memory is updated, mark pages dirty */ + for (i = 0; i < npages; i++) { + set_page_dirty_lock(inpages[i]); + mark_page_accessed(inpages[i]); + } + /* unlock the user pages */ + sev_unpin_memory(kvm, inpages, npages); +e_free: + kfree(data); + return ret; +} + +static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_measure *data; + struct kvm_sev_launch_measure params; + void *blob = NULL; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* User wants to query the blob length */ + if (!params.len) + goto cmd; + + if (params.uaddr) { + if (params.len > SEV_FW_BLOB_MAX_SIZE) { + ret = -EINVAL; + goto e_free; + } + + if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) { + ret = -EFAULT; + goto e_free; + } + + ret = -ENOMEM; + blob = kmalloc(params.len, GFP_KERNEL); + if (!blob) + goto e_free; + + data->address = __psp_pa(blob); + data->len = params.len; + } + +cmd: + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, data, &argp->error); + + /* + * If we query the session length, FW responded with expected data. + */ + if (!params.len) + goto done; + + if (ret) + goto e_free_blob; + + if (blob) { + if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len)) + ret = -EFAULT; + } + +done: + params.len = data->len; + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free_blob: + kfree(blob); +e_free: + kfree(data); + return ret; +} + +static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_finish *data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, data, &argp->error); + + kfree(data); + return ret; +} + +static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct kvm_sev_guest_status params; + struct sev_data_guest_status *data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error); + if (ret) + goto e_free; + + params.policy = data->policy; + params.state = data->state; + params.handle = data->handle; + + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free: + kfree(data); + return ret; +} + +static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, + unsigned long dst, int size, + int *error, bool enc) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_dbg *data; + int ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + data->dst_addr = dst; + data->src_addr = src; + data->len = size; + + ret = sev_issue_cmd(kvm, + enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT, + data, error); + kfree(data); + return ret; +} + +static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, + unsigned long dst_paddr, int sz, int *err) +{ + int offset; + + /* + * Its safe to read more than we are asked, caller should ensure that + * destination has enough space. + */ + src_paddr = round_down(src_paddr, 16); + offset = src_paddr & 15; + sz = round_up(sz + offset, 16); + + return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); +} + +static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, + unsigned long __user dst_uaddr, + unsigned long dst_paddr, + int size, int *err) +{ + struct page *tpage = NULL; + int ret, offset; + + /* if inputs are not 16-byte then use intermediate buffer */ + if (!IS_ALIGNED(dst_paddr, 16) || + !IS_ALIGNED(paddr, 16) || + !IS_ALIGNED(size, 16)) { + tpage = (void *)alloc_page(GFP_KERNEL); + if (!tpage) + return -ENOMEM; + + dst_paddr = __sme_page_pa(tpage); + } + + ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err); + if (ret) + goto e_free; + + if (tpage) { + offset = paddr & 15; + if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, + page_address(tpage) + offset, size)) + ret = -EFAULT; + } + +e_free: + if (tpage) + __free_page(tpage); + + return ret; +} + +static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, + unsigned long __user vaddr, + unsigned long dst_paddr, + unsigned long __user dst_vaddr, + int size, int *error) +{ + struct page *src_tpage = NULL; + struct page *dst_tpage = NULL; + int ret, len = size; + + /* If source buffer is not aligned then use an intermediate buffer */ + if (!IS_ALIGNED(vaddr, 16)) { + src_tpage = alloc_page(GFP_KERNEL); + if (!src_tpage) + return -ENOMEM; + + if (copy_from_user(page_address(src_tpage), + (void __user *)(uintptr_t)vaddr, size)) { + __free_page(src_tpage); + return -EFAULT; + } + + paddr = __sme_page_pa(src_tpage); + } + + /* + * If destination buffer or length is not aligned then do read-modify-write: + * - decrypt destination in an intermediate buffer + * - copy the source buffer in an intermediate buffer + * - use the intermediate buffer as source buffer + */ + if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + int dst_offset; + + dst_tpage = alloc_page(GFP_KERNEL); + if (!dst_tpage) { + ret = -ENOMEM; + goto e_free; + } + + ret = __sev_dbg_decrypt(kvm, dst_paddr, + __sme_page_pa(dst_tpage), size, error); + if (ret) + goto e_free; + + /* + * If source is kernel buffer then use memcpy() otherwise + * copy_from_user(). + */ + dst_offset = dst_paddr & 15; + + if (src_tpage) + memcpy(page_address(dst_tpage) + dst_offset, + page_address(src_tpage), size); + else { + if (copy_from_user(page_address(dst_tpage) + dst_offset, + (void __user *)(uintptr_t)vaddr, size)) { + ret = -EFAULT; + goto e_free; + } + } + + paddr = __sme_page_pa(dst_tpage); + dst_paddr = round_down(dst_paddr, 16); + len = round_up(size, 16); + } + + ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true); + +e_free: + if (src_tpage) + __free_page(src_tpage); + if (dst_tpage) + __free_page(dst_tpage); + return ret; +} + +static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) +{ + unsigned long vaddr, vaddr_end, next_vaddr; + unsigned long dst_vaddr, dst_vaddr_end; + struct page **src_p, **dst_p; + struct kvm_sev_dbg debug; + unsigned long n; + int ret, size; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) + return -EFAULT; + + vaddr = debug.src_uaddr; + size = debug.len; + vaddr_end = vaddr + size; + dst_vaddr = debug.dst_uaddr; + dst_vaddr_end = dst_vaddr + size; + + for (; vaddr < vaddr_end; vaddr = next_vaddr) { + int len, s_off, d_off; + + /* lock userspace source and destination page */ + src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0); + if (!src_p) + return -EFAULT; + + dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1); + if (!dst_p) { + sev_unpin_memory(kvm, src_p, n); + return -EFAULT; + } + + /* + * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the + * memory content (i.e it will write the same memory region with C=1). + * It's possible that the cache may contain the data with C=0, i.e., + * unencrypted so invalidate it first. + */ + sev_clflush_pages(src_p, 1); + sev_clflush_pages(dst_p, 1); + + /* + * Since user buffer may not be page aligned, calculate the + * offset within the page. + */ + s_off = vaddr & ~PAGE_MASK; + d_off = dst_vaddr & ~PAGE_MASK; + len = min_t(size_t, (PAGE_SIZE - s_off), size); + + if (dec) + ret = __sev_dbg_decrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + dst_vaddr, + __sme_page_pa(dst_p[0]) + d_off, + len, &argp->error); + else + ret = __sev_dbg_encrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + vaddr, + __sme_page_pa(dst_p[0]) + d_off, + dst_vaddr, + len, &argp->error); + + sev_unpin_memory(kvm, src_p, 1); + sev_unpin_memory(kvm, dst_p, 1); + + if (ret) + goto err; + + next_vaddr = vaddr + len; + dst_vaddr = dst_vaddr + len; + size -= len; + } +err: + return ret; +} + +static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_secret *data; + struct kvm_sev_launch_secret params; + struct page **pages; + void *blob, *hdr; + unsigned long n; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1); + if (!pages) + return -ENOMEM; + + /* + * The secret must be copied into contiguous memory region, lets verify + * that userspace memory pages are contiguous before we issue command. + */ + if (get_num_contig_pages(0, pages, n) != n) { + ret = -EINVAL; + goto e_unpin_memory; + } + + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto e_unpin_memory; + + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); + if (IS_ERR(blob)) { + ret = PTR_ERR(blob); + goto e_free; + } + + data->trans_address = __psp_pa(blob); + data->trans_len = params.trans_len; + + hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); + if (IS_ERR(hdr)) { + ret = PTR_ERR(hdr); + goto e_free_blob; + } + data->trans_address = __psp_pa(blob); + data->trans_len = params.trans_len; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); + + kfree(hdr); + +e_free_blob: + kfree(blob); +e_free: + kfree(data); +e_unpin_memory: + sev_unpin_memory(kvm, pages, n); + return ret; +} + +static int svm_mem_enc_op(struct kvm *kvm, void __user *argp) +{ + struct kvm_sev_cmd sev_cmd; + int r; + + if (!svm_sev_enabled()) + return -ENOTTY; + + if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) + return -EFAULT; + + mutex_lock(&kvm->lock); + + switch (sev_cmd.id) { + case KVM_SEV_INIT: + r = sev_guest_init(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_START: + r = sev_launch_start(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_UPDATE_DATA: + r = sev_launch_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_MEASURE: + r = sev_launch_measure(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_FINISH: + r = sev_launch_finish(kvm, &sev_cmd); + break; + case KVM_SEV_GUEST_STATUS: + r = sev_guest_status(kvm, &sev_cmd); + break; + case KVM_SEV_DBG_DECRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, true); + break; + case KVM_SEV_DBG_ENCRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, false); + break; + case KVM_SEV_LAUNCH_SECRET: + r = sev_launch_secret(kvm, &sev_cmd); + break; + default: + r = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) + r = -EFAULT; + +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int svm_register_enc_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct enc_region *region; + int ret = 0; + + if (!sev_guest(kvm)) + return -ENOTTY; + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return -ENOMEM; + + region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); + if (!region->pages) { + ret = -ENOMEM; + goto e_free; + } + + /* + * The guest may change the memory encryption attribute from C=0 -> C=1 + * or vice versa for this memory range. Lets make sure caches are + * flushed to ensure that guest data gets written into memory with + * correct C-bit. + */ + sev_clflush_pages(region->pages, region->npages); + + region->uaddr = range->addr; + region->size = range->size; + + mutex_lock(&kvm->lock); + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + + return ret; + +e_free: + kfree(region); + return ret; +} + +static struct enc_region * +find_enc_region(struct kvm *kvm, struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct list_head *head = &sev->regions_list; + struct enc_region *i; + + list_for_each_entry(i, head, list) { + if (i->uaddr == range->addr && + i->size == range->size) + return i; + } + + return NULL; +} + + +static int svm_unregister_enc_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct enc_region *region; + int ret; + + mutex_lock(&kvm->lock); + + if (!sev_guest(kvm)) { + ret = -ENOTTY; + goto failed; + } + + region = find_enc_region(kvm, range); + if (!region) { + ret = -EINVAL; + goto failed; + } + + __unregister_enc_region_locked(kvm, region); + + mutex_unlock(&kvm->lock); + return 0; + +failed: + mutex_unlock(&kvm->lock); + return ret; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -5537,7 +6812,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vcpu_reset = svm_vcpu_reset, .vm_init = avic_vm_init, - .vm_destroy = avic_vm_destroy, + .vm_destroy = svm_vm_destroy, .prepare_guest_switch = svm_prepare_guest_switch, .vcpu_load = svm_vcpu_load, @@ -5597,6 +6872,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, + .sync_pir_to_irr = kvm_lapic_find_highest_irr, .apicv_post_state_restore = avic_post_state_restore, .set_tss_addr = svm_set_tss_addr, @@ -5613,6 +6889,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .invpcid_supported = svm_invpcid_supported, .mpx_supported = svm_mpx_supported, .xsaves_supported = svm_xsaves_supported, + .umip_emulated = svm_umip_emulated, .set_supported_cpuid = svm_set_supported_cpuid, @@ -5636,6 +6913,10 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .pre_enter_smm = svm_pre_enter_smm, .pre_leave_smm = svm_pre_leave_smm, .enable_smi_window = enable_smi_window, + + .mem_enc_op = svm_mem_enc_op, + .mem_enc_reg_region = svm_register_enc_region, + .mem_enc_unreg_region = svm_unregister_enc_region, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a8b96dc4cd83..f427723dc7db 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -34,6 +34,7 @@ #include <linux/tboot.h> #include <linux/hrtimer.h> #include <linux/frame.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -111,6 +112,14 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define MSR_BITMAP_MODE_X2APIC 1 +#define MSR_BITMAP_MODE_X2APIC_APICV 2 +#define MSR_BITMAP_MODE_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ @@ -185,7 +194,6 @@ module_param(ple_window_max, int, S_IRUGO); extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 -#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -210,6 +218,7 @@ struct loaded_vmcs { int soft_vnmi_blocked; ktime_t entry_time; s64 vnmi_blocked_time; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -226,7 +235,7 @@ struct shared_msr_entry { * stored in guest memory specified by VMPTRLD, but is opaque to the guest, * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. * More than one of these structures may exist, if L1 runs multiple L2 guests. - * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). @@ -409,12 +418,11 @@ struct __packed vmcs12 { */ #define VMCS12_SIZE 0x1000 -/* Used to remember the last vmcs02 used for some recently used vmcs12s */ -struct vmcs02_list { - struct list_head list; - gpa_t vmptr; - struct loaded_vmcs vmcs02; -}; +/* + * VMCS12_MAX_FIELD_INDEX is the highest index value used in any + * supported VMCS12 field encoding. + */ +#define VMCS12_MAX_FIELD_INDEX 0x17 /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need @@ -439,16 +447,17 @@ struct nested_vmx { * data hold by vmcs12 */ bool sync_shadow_vmcs; + bool dirty_vmcs12; - /* vmcs02_list cache of VMCSs recently used to run L2 guests */ - struct list_head vmcs02_pool; - int vmcs02_num; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + + struct loaded_vmcs vmcs02; + /* - * Guest pages referred to in vmcs02 with host-physical pointers, so - * we must keep them pinned while L2 runs. + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. */ struct page *apic_access_page; struct page *virtual_apic_page; @@ -457,8 +466,6 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; - unsigned long *msr_bitmap; - struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -581,6 +588,7 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; + u8 msr_bitmap_mode; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -592,6 +600,10 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + + u64 arch_capabilities; + u64 spec_ctrl; + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; u32 secondary_exec_control; @@ -659,6 +671,8 @@ struct vcpu_vmx { u32 host_pkru; + unsigned long host_debugctlmsr; + /* * Only bits masked by msr_ia32_feature_control_valid_bits can be set in * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included @@ -687,67 +701,24 @@ static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } +#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n))))) #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x) -#define FIELD(number, name) [number] = VMCS12_OFFSET(name) -#define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ - [number##_HIGH] = VMCS12_OFFSET(name)+4 +#define FIELD(number, name) [ROL16(number, 6)] = VMCS12_OFFSET(name) +#define FIELD64(number, name) \ + FIELD(number, name), \ + [ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32) -static unsigned long shadow_read_only_fields[] = { - /* - * We do NOT shadow fields that are modified when L0 - * traps and emulates any vmx instruction (e.g. VMPTRLD, - * VMXON...) executed by L1. - * For example, VM_INSTRUCTION_ERROR is read - * by L1 if a vmx instruction fails (part of the error path). - * Note the code assumes this logic. If for some reason - * we start shadowing these fields then we need to - * force a shadow sync when L0 emulates vmx instructions - * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified - * by nested_vmx_failValid) - */ - VM_EXIT_REASON, - VM_EXIT_INTR_INFO, - VM_EXIT_INSTRUCTION_LEN, - IDT_VECTORING_INFO_FIELD, - IDT_VECTORING_ERROR_CODE, - VM_EXIT_INTR_ERROR_CODE, - EXIT_QUALIFICATION, - GUEST_LINEAR_ADDRESS, - GUEST_PHYSICAL_ADDRESS +static u16 shadow_read_only_fields[] = { +#define SHADOW_FIELD_RO(x) x, +#include "vmx_shadow_fields.h" }; static int max_shadow_read_only_fields = ARRAY_SIZE(shadow_read_only_fields); -static unsigned long shadow_read_write_fields[] = { - TPR_THRESHOLD, - GUEST_RIP, - GUEST_RSP, - GUEST_CR0, - GUEST_CR3, - GUEST_CR4, - GUEST_INTERRUPTIBILITY_INFO, - GUEST_RFLAGS, - GUEST_CS_SELECTOR, - GUEST_CS_AR_BYTES, - GUEST_CS_LIMIT, - GUEST_CS_BASE, - GUEST_ES_BASE, - GUEST_BNDCFGS, - CR0_GUEST_HOST_MASK, - CR0_READ_SHADOW, - CR4_READ_SHADOW, - TSC_OFFSET, - EXCEPTION_BITMAP, - CPU_BASED_VM_EXEC_CONTROL, - VM_ENTRY_EXCEPTION_ERROR_CODE, - VM_ENTRY_INTR_INFO_FIELD, - VM_ENTRY_INSTRUCTION_LEN, - VM_ENTRY_EXCEPTION_ERROR_CODE, - HOST_FS_BASE, - HOST_GS_BASE, - HOST_FS_SELECTOR, - HOST_GS_SELECTOR +static u16 shadow_read_write_fields[] = { +#define SHADOW_FIELD_RW(x) x, +#include "vmx_shadow_fields.h" }; static int max_shadow_read_write_fields = ARRAY_SIZE(shadow_read_write_fields); @@ -898,21 +869,22 @@ static const unsigned short vmcs_field_to_offset_table[] = { static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; + unsigned index; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + if (field >> 15) return -ENOENT; - /* - * FIXME: Mitigation for CVE-2017-5753. To be replaced with a - * generic mechanism. - */ - asm("lfence"); - - if (vmcs_field_to_offset_table[field] == 0) + index = ROL16(field, 6); + if (index >= size) return -ENOENT; - return vmcs_field_to_offset_table[field]; + index = array_index_nospec(index, size); + offset = vmcs_field_to_offset_table[index]; + if (offset == 0) + return -ENOENT; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) @@ -935,6 +907,9 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, u16 error_code); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -952,14 +927,6 @@ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); enum { - VMX_IO_BITMAP_A, - VMX_IO_BITMAP_B, - VMX_MSR_BITMAP_LEGACY, - VMX_MSR_BITMAP_LONGMODE, - VMX_MSR_BITMAP_LEGACY_X2APIC_APICV, - VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV, - VMX_MSR_BITMAP_LEGACY_X2APIC, - VMX_MSR_BITMAP_LONGMODE_X2APIC, VMX_VMREAD_BITMAP, VMX_VMWRITE_BITMAP, VMX_BITMAP_NR @@ -967,14 +934,6 @@ enum { static unsigned long *vmx_bitmap[VMX_BITMAP_NR]; -#define vmx_io_bitmap_a (vmx_bitmap[VMX_IO_BITMAP_A]) -#define vmx_io_bitmap_b (vmx_bitmap[VMX_IO_BITMAP_B]) -#define vmx_msr_bitmap_legacy (vmx_bitmap[VMX_MSR_BITMAP_LEGACY]) -#define vmx_msr_bitmap_longmode (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE]) -#define vmx_msr_bitmap_legacy_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC_APICV]) -#define vmx_msr_bitmap_longmode_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV]) -#define vmx_msr_bitmap_legacy_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC]) -#define vmx_msr_bitmap_longmode_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC]) #define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP]) #define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP]) @@ -1918,6 +1877,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2296,6 +2301,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -2333,6 +2339,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vmx_vcpu_pi_load(vcpu, cpu); vmx->host_pkru = read_pkru(); + vmx->host_debugctlmsr = get_debugctlmsr(); } static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) @@ -2572,36 +2579,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } -static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) -{ - unsigned long *msr_bitmap; - - if (is_guest_mode(vcpu)) - msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; - else if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv; - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; - } - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - } - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); -} - /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -2642,7 +2619,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(&vmx->vcpu); + vmx_update_msr_bitmap(&vmx->vcpu); } /* @@ -2920,7 +2897,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) rdmsrl(MSR_IA32_VMX_CR4_FIXED1, vmx->nested.nested_vmx_cr4_fixed1); /* highest index: VMX_PREEMPTION_TIMER_VALUE */ - vmx->nested.nested_vmx_vmcs_enum = 0x2e; + vmx->nested.nested_vmx_vmcs_enum = VMCS12_MAX_FIELD_INDEX << 1; } /* @@ -3256,6 +3233,7 @@ static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, */ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { + struct vcpu_vmx *vmx = to_vmx(vcpu); struct shared_msr_entry *msr; switch (msr_info->index) { @@ -3267,8 +3245,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: - vmx_load_host_state(to_vmx(vcpu)); - msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + vmx_load_host_state(vmx); + msr_info->data = vmx->msr_guest_kernel_gs_base; break; #endif case MSR_EFER: @@ -3276,6 +3254,20 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = to_vmx(vcpu)->arch_capabilities; + break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3294,13 +3286,13 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_MCG_EXT_CTL: if (!msr_info->host_initiated && - !(to_vmx(vcpu)->msr_ia32_feature_control & + !(vmx->msr_ia32_feature_control & FEATURE_CONTROL_LMCE)) return 1; msr_info->data = vcpu->arch.mcg_ext_ctl; break; case MSR_IA32_FEATURE_CONTROL: - msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control; + msr_info->data = vmx->msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) @@ -3317,7 +3309,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; /* Otherwise falls through */ default: - msr = find_msr_entry(to_vmx(vcpu), msr_info->index); + msr = find_msr_entry(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; break; @@ -3383,6 +3375,70 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vmx->arch_capabilities = data; + break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -3639,7 +3695,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) #endif CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_USE_IO_BITMAPS | + CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_MOV_DR_EXITING | CPU_BASED_USE_TSC_OFFSETING | CPU_BASED_INVLPG_EXITING | @@ -3669,6 +3725,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_ENABLE_EPT | SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_PAUSE_LOOP_EXITING | + SECONDARY_EXEC_DESC | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_APIC_REGISTER_VIRT | @@ -3837,11 +3894,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return vmcs; } -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3857,9 +3909,38 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + if (loaded_vmcs->msr_bitmap) + free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs_init(loaded_vmcs); + + if (cpu_has_vmx_msr_bitmap()) { + loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!loaded_vmcs->msr_bitmap) + goto out_vmcs; + memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + } + return 0; + +out_vmcs: + free_loaded_vmcs(loaded_vmcs); + return -ENOMEM; +} + static void free_kvm_area(void) { int cpu; @@ -3870,17 +3951,17 @@ static void free_kvm_area(void) } } -enum vmcs_field_type { - VMCS_FIELD_TYPE_U16 = 0, - VMCS_FIELD_TYPE_U64 = 1, - VMCS_FIELD_TYPE_U32 = 2, - VMCS_FIELD_TYPE_NATURAL_WIDTH = 3 +enum vmcs_field_width { + VMCS_FIELD_WIDTH_U16 = 0, + VMCS_FIELD_WIDTH_U64 = 1, + VMCS_FIELD_WIDTH_U32 = 2, + VMCS_FIELD_WIDTH_NATURAL_WIDTH = 3 }; -static inline int vmcs_field_type(unsigned long field) +static inline int vmcs_field_width(unsigned long field) { if (0x1 & field) /* the *_HIGH fields are all 32 bit */ - return VMCS_FIELD_TYPE_U32; + return VMCS_FIELD_WIDTH_U32; return (field >> 13) & 0x3 ; } @@ -3893,43 +3974,66 @@ static void init_vmcs_shadow_fields(void) { int i, j; - /* No checks for read only fields yet */ + for (i = j = 0; i < max_shadow_read_only_fields; i++) { + u16 field = shadow_read_only_fields[i]; + if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && + (i + 1 == max_shadow_read_only_fields || + shadow_read_only_fields[i + 1] != field + 1)) + pr_err("Missing field from shadow_read_only_field %x\n", + field + 1); + + clear_bit(field, vmx_vmread_bitmap); +#ifdef CONFIG_X86_64 + if (field & 1) + continue; +#endif + if (j < i) + shadow_read_only_fields[j] = field; + j++; + } + max_shadow_read_only_fields = j; for (i = j = 0; i < max_shadow_read_write_fields; i++) { - switch (shadow_read_write_fields[i]) { - case GUEST_BNDCFGS: - if (!kvm_mpx_supported()) + u16 field = shadow_read_write_fields[i]; + if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && + (i + 1 == max_shadow_read_write_fields || + shadow_read_write_fields[i + 1] != field + 1)) + pr_err("Missing field from shadow_read_write_field %x\n", + field + 1); + + /* + * PML and the preemption timer can be emulated, but the + * processor cannot vmwrite to fields that don't exist + * on bare metal. + */ + switch (field) { + case GUEST_PML_INDEX: + if (!cpu_has_vmx_pml()) + continue; + break; + case VMX_PREEMPTION_TIMER_VALUE: + if (!cpu_has_vmx_preemption_timer()) + continue; + break; + case GUEST_INTR_STATUS: + if (!cpu_has_vmx_apicv()) continue; break; default: break; } + clear_bit(field, vmx_vmwrite_bitmap); + clear_bit(field, vmx_vmread_bitmap); +#ifdef CONFIG_X86_64 + if (field & 1) + continue; +#endif if (j < i) - shadow_read_write_fields[j] = - shadow_read_write_fields[i]; + shadow_read_write_fields[j] = field; j++; } max_shadow_read_write_fields = j; - - /* shadowed fields guest access without vmexit */ - for (i = 0; i < max_shadow_read_write_fields; i++) { - unsigned long field = shadow_read_write_fields[i]; - - clear_bit(field, vmx_vmwrite_bitmap); - clear_bit(field, vmx_vmread_bitmap); - if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) { - clear_bit(field + 1, vmx_vmwrite_bitmap); - clear_bit(field + 1, vmx_vmread_bitmap); - } - } - for (i = 0; i < max_shadow_read_only_fields; i++) { - unsigned long field = shadow_read_only_fields[i]; - - clear_bit(field, vmx_vmread_bitmap); - if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) - clear_bit(field + 1, vmx_vmread_bitmap); - } } static __init int alloc_kvm_area(void) @@ -4142,9 +4246,10 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) +static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid, + bool invalidate_gpa) { - if (enable_ept) { + if (enable_ept && (invalidate_gpa || !enable_vpid)) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa)); @@ -4153,15 +4258,15 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) } } -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa); } static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu) { if (enable_ept) - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) @@ -4359,7 +4464,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) ept_load_pdptrs(vcpu); } - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); vmcs_writel(GUEST_CR3, guest_cr3); } @@ -4376,6 +4481,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) (to_vmx(vcpu)->rmode.vm86_active ? KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); + if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_DESC); + hw_cr4 &= ~X86_CR4_UMIP; + } else + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_DESC); + if (cr4 & X86_CR4_VMXE) { /* * To use VMXON (and later other VMX instructions), a guest @@ -4918,10 +5031,8 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4955,6 +5066,50 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, } } +static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) +{ + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return; + + /* + * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals + * have the write-low and read-high bitmap offsets the wrong way round. + * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. + */ + if (msr <= 0x1fff) { + if (type & MSR_TYPE_R) + /* read-low */ + __set_bit(msr, msr_bitmap + 0x000 / f); + + if (type & MSR_TYPE_W) + /* write-low */ + __set_bit(msr, msr_bitmap + 0x800 / f); + + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + if (type & MSR_TYPE_R) + /* read-high */ + __set_bit(msr, msr_bitmap + 0x400 / f); + + if (type & MSR_TYPE_W) + /* write-high */ + __set_bit(msr, msr_bitmap + 0xc00 / f); + + } +} + +static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type, bool value) +{ + if (value) + vmx_enable_intercept_for_msr(msr_bitmap, msr, type); + else + vmx_disable_intercept_for_msr(msr_bitmap, msr, type); +} + /* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. @@ -4965,11 +5120,6 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, { int f = sizeof(unsigned long); - if (!cpu_has_vmx_msr_bitmap()) { - WARN_ON(1); - return; - } - /* * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals * have the write-low and read-high bitmap offsets the wrong way round. @@ -5001,30 +5151,70 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) +static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { - if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, - msr, MSR_TYPE_R | MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, - msr, MSR_TYPE_R | MSR_TYPE_W); + u8 mode = 0; + + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; + } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_active) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv, - msr, type); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, type); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } + + if (mode & MSR_BITMAP_MODE_X2APIC) { + /* + * TPR reads and writes can be virtualized even if virtual interrupt + * delivery is not in use. + */ + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { + vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + } } } +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + u8 mode = vmx_msr_bitmap_mode(vcpu); + u8 changed = mode ^ vmx->msr_bitmap_mode; + + if (!changed) + return; + + vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, + !(mode & MSR_BITMAP_MODE_LM)); + + if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; +} + static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) { return enable_apicv; @@ -5069,7 +5259,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); - __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); + __kvm_apic_update_irr(vmx->nested.pi_desc->pir, + vapic_page, &max_irr); kunmap(vmx->nested.virtual_apic_page); status = vmcs_read16(GUEST_INTR_STATUS); @@ -5129,14 +5320,15 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { - /* the PIR and ON have been set by L1. */ - kvm_vcpu_trigger_posted_interrupt(vcpu, true); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + /* the PIR and ON have been set by L1. */ + if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) + kvm_vcpu_kick(vcpu); return 0; } return -1; @@ -5274,7 +5466,7 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) @@ -5315,6 +5507,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) struct kvm_vcpu *vcpu = &vmx->vcpu; u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; + if (!cpu_need_virtualize_apic_accesses(vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) @@ -5333,6 +5526,11 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + + /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, + * in vmx_set_cr4. */ + exec_control &= ~SECONDARY_EXEC_DESC; + /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD (handle_vmptrld). We can NOT enable shadow_vmcs here because we don't have yet @@ -5452,16 +5650,12 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) #endif int i; - /* I/O */ - vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a)); - vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b)); - if (enable_shadow_vmcs) { vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); + vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ @@ -5539,6 +5733,8 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -5567,6 +5763,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(vcpu, 0); @@ -6107,6 +6304,12 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) return kvm_set_cr4(vcpu, val); } +static int handle_desc(struct kvm_vcpu *vcpu) +{ + WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); + return emulate_instruction(vcpu, 0) == EMULATE_DONE; +} + static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; @@ -6563,7 +6766,21 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu) && !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { trace_kvm_fast_mmio(gpa); - return kvm_skip_emulated_instruction(vcpu); + /* + * Doing kvm_skip_emulated_instruction() depends on undefined + * behavior: Intel's manual doesn't mandate + * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG + * occurs and while on real hardware it was observed to be set, + * other hypervisors (namely Hyper-V) don't set it, we end up + * advancing IP with some random value. Disable fast mmio when + * running nested and keep it for real hardware in hope that + * VM_EXIT_INSTRUCTION_LEN will always be set correctly. + */ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + return kvm_skip_emulated_instruction(vcpu); + else + return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP, + NULL, 0) == EMULATE_DONE; } ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -6744,7 +6961,7 @@ void vmx_enable_tdp(void) static __init int hardware_setup(void) { - int r = -ENOMEM, i, msr; + int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -6760,13 +6977,6 @@ static __init int hardware_setup(void) memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); - memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE); - - memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - - memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; goto out; @@ -6779,11 +6989,6 @@ static __init int hardware_setup(void) !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; - if (!cpu_has_vmx_shadow_vmcs()) - enable_shadow_vmcs = 0; - if (enable_shadow_vmcs) - init_vmcs_shadow_fields(); - if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels() || !cpu_has_vmx_ept_mt_wb() || @@ -6835,42 +7040,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - - memcpy(vmx_msr_bitmap_legacy_x2apic_apicv, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic_apicv, - vmx_msr_bitmap_longmode, PAGE_SIZE); - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - for (msr = 0x800; msr <= 0x8ff; msr++) { - if (msr == 0x839 /* TMCCT */) - continue; - vmx_disable_intercept_msr_x2apic(msr, MSR_TYPE_R, true); - } - - /* - * TPR reads and writes can be virtualized even if virtual interrupt - * delivery is not in use. - */ - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_W, true); - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_R | MSR_TYPE_W, false); - - /* EOI */ - vmx_disable_intercept_msr_x2apic(0x80b, MSR_TYPE_W, true); - /* SELF-IPI */ - vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true); - if (enable_ept) vmx_enable_tdp(); else @@ -6903,6 +7074,11 @@ static __init int hardware_setup(void) kvm_x86_ops->cancel_hv_timer = NULL; } + if (!cpu_has_vmx_shadow_vmcs()) + enable_shadow_vmcs = 0; + if (enable_shadow_vmcs) + init_vmcs_shadow_fields(); + kvm_set_posted_intr_wakeup_handler(wakeup_handler); kvm_mce_cap_supported |= MCG_LMCE_P; @@ -6974,94 +7150,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu) } /* - * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. - * We could reuse a single VMCS for all the L2 guests, but we also want the - * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this - * allows keeping them loaded on the processor, and in the future will allow - * optimizations where prepare_vmcs02 doesn't need to set all the fields on - * every entry if they never change. - * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE - * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first. - * - * The following functions allocate and free a vmcs02 in this pool. - */ - -/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */ -static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmx->nested.current_vmptr) { - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { - /* Recycle the least recently used VMCS. */ - item = list_last_entry(&vmx->nested.vmcs02_pool, - struct vmcs02_list, list); - item->vmptr = vmx->nested.current_vmptr; - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - /* Create a new VMCS */ - item = kzalloc(sizeof(struct vmcs02_list), GFP_KERNEL); - if (!item) - return NULL; - item->vmcs02.vmcs = alloc_vmcs(); - item->vmcs02.shadow_vmcs = NULL; - if (!item->vmcs02.vmcs) { - kfree(item); - return NULL; - } - loaded_vmcs_init(&item->vmcs02); - item->vmptr = vmx->nested.current_vmptr; - list_add(&(item->list), &(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num++; - return &item->vmcs02; -} - -/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */ -static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmptr) { - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - return; - } -} - -/* - * Free all VMCSs saved for this vcpu, except the one pointed by - * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs - * must be &vmx->vmcs01. - */ -static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item, *n; - - WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01); - list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) { - /* - * Something will leak if the above WARN triggers. Better than - * a use-after-free. - */ - if (vmx->loaded_vmcs == &item->vmcs02) - continue; - - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - } -} - -/* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction, as specified * by Vol 2B, VMX Instruction Reference, "Conventions". @@ -7241,13 +7329,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs *shadow_vmcs; + int r; - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) + goto out_vmcs02; vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) @@ -7264,9 +7350,6 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = shadow_vmcs; } - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; @@ -7278,9 +7361,9 @@ out_shadow_vmcs: kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); + free_loaded_vmcs(&vmx->nested.vmcs02); -out_msr_bitmap: +out_vmcs02: return -ENOMEM; } @@ -7423,10 +7506,6 @@ static void free_nested(struct vcpu_vmx *vmx) free_vpid(vmx->nested.vpid02); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - if (vmx->nested.msr_bitmap) { - free_page((unsigned long)vmx->nested.msr_bitmap); - vmx->nested.msr_bitmap = NULL; - } if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); @@ -7434,7 +7513,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); - /* Unpin physical memory we referred to in current vmcs02 */ + /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; @@ -7450,7 +7529,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.pi_desc = NULL; } - nested_free_all_saved_vmcss(vmx); + free_loaded_vmcs(&vmx->nested.vmcs02); } /* Emulate the VMXOFF instruction */ @@ -7493,8 +7572,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - nested_free_vmcs02(vmx, vmptr); - nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); } @@ -7532,17 +7609,17 @@ static inline int vmcs12_read_any(struct kvm_vcpu *vcpu, p = ((char *)(get_vmcs12(vcpu))) + offset; - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_NATURAL_WIDTH: + switch (vmcs_field_width(field)) { + case VMCS_FIELD_WIDTH_NATURAL_WIDTH: *ret = *((natural_width *)p); return 0; - case VMCS_FIELD_TYPE_U16: + case VMCS_FIELD_WIDTH_U16: *ret = *((u16 *)p); return 0; - case VMCS_FIELD_TYPE_U32: + case VMCS_FIELD_WIDTH_U32: *ret = *((u32 *)p); return 0; - case VMCS_FIELD_TYPE_U64: + case VMCS_FIELD_WIDTH_U64: *ret = *((u64 *)p); return 0; default: @@ -7559,17 +7636,17 @@ static inline int vmcs12_write_any(struct kvm_vcpu *vcpu, if (offset < 0) return offset; - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: + switch (vmcs_field_width(field)) { + case VMCS_FIELD_WIDTH_U16: *(u16 *)p = field_value; return 0; - case VMCS_FIELD_TYPE_U32: + case VMCS_FIELD_WIDTH_U32: *(u32 *)p = field_value; return 0; - case VMCS_FIELD_TYPE_U64: + case VMCS_FIELD_WIDTH_U64: *(u64 *)p = field_value; return 0; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: + case VMCS_FIELD_WIDTH_NATURAL_WIDTH: *(natural_width *)p = field_value; return 0; default: @@ -7585,7 +7662,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) unsigned long field; u64 field_value; struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; - const unsigned long *fields = shadow_read_write_fields; + const u16 *fields = shadow_read_write_fields; const int num_fields = max_shadow_read_write_fields; preempt_disable(); @@ -7594,23 +7671,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) for (i = 0; i < num_fields; i++) { field = fields[i]; - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: - field_value = vmcs_read16(field); - break; - case VMCS_FIELD_TYPE_U32: - field_value = vmcs_read32(field); - break; - case VMCS_FIELD_TYPE_U64: - field_value = vmcs_read64(field); - break; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: - field_value = vmcs_readl(field); - break; - default: - WARN_ON(1); - continue; - } + field_value = __vmcs_readl(field); vmcs12_write_any(&vmx->vcpu, field, field_value); } @@ -7622,7 +7683,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) { - const unsigned long *fields[] = { + const u16 *fields[] = { shadow_read_write_fields, shadow_read_only_fields }; @@ -7641,24 +7702,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) for (i = 0; i < max_fields[q]; i++) { field = fields[q][i]; vmcs12_read_any(&vmx->vcpu, field, &field_value); - - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: - vmcs_write16(field, (u16)field_value); - break; - case VMCS_FIELD_TYPE_U32: - vmcs_write32(field, (u32)field_value); - break; - case VMCS_FIELD_TYPE_U64: - vmcs_write64(field, (u64)field_value); - break; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: - vmcs_writel(field, (long)field_value); - break; - default: - WARN_ON(1); - break; - } + __vmcs_writel(field, field_value); } } @@ -7727,8 +7771,10 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) { unsigned long field; gva_t gva; + struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + /* The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 @@ -7771,6 +7817,20 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } + switch (field) { +#define SHADOW_FIELD_RW(x) case x: +#include "vmx_shadow_fields.h" + /* + * The fields that can be updated by L1 without a vmexit are + * always updated in the vmcs02, the others go down the slow + * path of prepare_vmcs02. + */ + break; + default: + vmx->nested.dirty_vmcs12 = true; + break; + } + nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); } @@ -7785,6 +7845,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) __pa(vmx->vmcs01.shadow_vmcs)); vmx->nested.sync_shadow_vmcs = true; } + vmx->nested.dirty_vmcs12 = true; } /* Emulate the VMPTRLD instruction */ @@ -8005,7 +8066,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } - __vmx_flush_tlb(vcpu, vmx->nested.vpid02); + __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); @@ -8199,6 +8260,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_XSETBV] = handle_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, + [EXIT_REASON_GDTR_IDTR] = handle_desc, + [EXIT_REASON_LDTR_TR] = handle_desc, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, @@ -8406,10 +8469,11 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) /* * The host physical addresses of some pages of guest memory - * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU - * may write to these pages via their host physical address while - * L2 is running, bypassing any address-translation-based dirty - * tracking (e.g. EPT write protection). + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). * * Mark them dirty on every exit from L2 to prevent them from * getting out of sync with dirty tracking. @@ -8943,7 +9007,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) @@ -9007,36 +9071,23 @@ static void vmx_set_rvi(int vector) static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) { - if (!is_guest_mode(vcpu)) { - vmx_set_rvi(max_irr); - return; - } - - if (max_irr == -1) - return; - /* - * In guest mode. If a vmexit is needed, vmx_check_nested_events - * handles it. + * When running L2, updating RVI is only relevant when + * vmcs12 virtual-interrupt-delivery enabled. + * However, it can be enabled only when L1 also + * intercepts external-interrupts and in that case + * we should not update vmcs02 RVI but instead intercept + * interrupt. Therefore, do nothing when running L2. */ - if (nested_exit_on_intr(vcpu)) - return; - - /* - * Else, fall back to pre-APICv interrupt injection since L2 - * is run without virtual interrupt delivery. - */ - if (!kvm_event_needs_reinjection(vcpu) && - vmx_interrupt_allowed(vcpu)) { - kvm_queue_interrupt(vcpu, max_irr, false); - vmx_inject_irq(vcpu); - } + if (!is_guest_mode(vcpu)) + vmx_set_rvi(max_irr); } static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; + bool max_irr_updated; WARN_ON(!vcpu->arch.apicv_active); if (pi_test_on(&vmx->pi_desc)) { @@ -9046,7 +9097,23 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); - max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + max_irr_updated = + kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); + + /* + * 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. + */ + 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); + } } else { max_irr = kvm_lapic_find_highest_irr(vcpu); } @@ -9161,6 +9228,12 @@ static bool vmx_xsaves_supported(void) SECONDARY_EXEC_XSAVES; } +static bool vmx_umip_emulated(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_DESC; +} + static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -9316,7 +9389,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr, cr3, cr4; + unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -9369,10 +9442,18 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vcpu->arch.pkru); atomic_switch_perf_msrs(vmx); - debugctlmsr = get_debugctlmsr(); vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -9491,12 +9572,33 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ - if (debugctlmsr) - update_debugctlmsr(debugctlmsr); + if (vmx->host_debugctlmsr) + update_debugctlmsr(vmx->host_debugctlmsr); #ifndef CONFIG_X86_64 /* @@ -9576,10 +9678,8 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int r; - r = vcpu_load(vcpu); - BUG_ON(r); + vcpu_load(vcpu); vmx_switch_vmcs(vcpu, &vmx->vmcs01); free_nested(vmx); vcpu_put(vcpu); @@ -9604,6 +9704,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + unsigned long *msr_bitmap; int cpu; if (!vmx) @@ -9636,13 +9737,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; - vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - vmx->loaded_vmcs->shadow_vmcs = NULL; - if (!vmx->loaded_vmcs->vmcs) + err = alloc_loaded_vmcs(&vmx->vmcs01); + if (err < 0) goto free_msrs; - loaded_vmcs_init(vmx->loaded_vmcs); + msr_bitmap = vmx->vmcs01.msr_bitmap; + vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + vmx->msr_bitmap_mode = 0; + + vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; @@ -9771,7 +9879,8 @@ static void vmcs_set_secondary_exec_control(u32 new_ctl) u32 mask = SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_DESC; u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); @@ -9937,8 +10046,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, } } -static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12); +static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12); static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) @@ -10027,11 +10136,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); } - if (cpu_has_vmx_msr_bitmap() && - nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) && - nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) - ; - else + if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_USE_MSR_BITMAPS); } @@ -10099,48 +10204,90 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. */ -static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) { int msr; struct page *page; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd & spec_ctrl are trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); + + /* Nothing to do if the MSR bitmap is not in use. */ + if (!cpu_has_vmx_msr_bitmap() || + !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) + return false; - /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd && !spec_ctrl) return false; page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap); if (is_error_page(page)) return false; + msr_bitmap_l1 = (unsigned long *)kmap(page); + if (nested_cpu_has_apic_reg_virt(vmcs12)) { + /* + * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it + * just lets the processor take the value from the virtual-APIC page; + * take those 256 bits directly from the L1 bitmap. + */ + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap_l0[word] = msr_bitmap_l1[word]; + msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; + } + } else { + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap_l0[word] = ~0; + msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; + } + } - memset(msr_bitmap_l0, 0xff, PAGE_SIZE); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_TASKPRI), + MSR_TYPE_W); - if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { - if (nested_cpu_has_apic_reg_virt(vmcs12)) - for (msr = 0x800; msr <= 0x8ff; msr++) - nested_vmx_disable_intercept_for_msr( + if (nested_cpu_has_vid(vmcs12)) { + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_EOI), + MSR_TYPE_W); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_SELF_IPI), + MSR_TYPE_W); + } + + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( msr_bitmap_l1, msr_bitmap_l0, - msr, MSR_TYPE_R); + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + if (pred_cmd) nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - APIC_BASE_MSR + (APIC_TASKPRI >> 4), - MSR_TYPE_R | MSR_TYPE_W); - - if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - APIC_BASE_MSR + (APIC_EOI >> 4), - MSR_TYPE_W); - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - APIC_BASE_MSR + (APIC_SELF_IPI >> 4), - MSR_TYPE_W); - } - } + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); kvm_release_page_clean(page); @@ -10406,25 +10553,12 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne return 0; } -/* - * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested - * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it - * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2 - * guest in a way that will both be appropriate to L1's requests, and our - * needs. In addition to modifying the active vmcs (which is vmcs02), this - * function also has additional necessary side-effects, like setting various - * vcpu->arch fields. - * Returns 0 on success, 1 on failure. Invalid state exit qualification code - * is assigned to entry_failure_code on failure. - */ -static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - bool from_vmentry, u32 *entry_failure_code) +static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exec_control, vmcs12_exec_ctrl; vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); - vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector); vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector); vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector); @@ -10432,7 +10566,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector); vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector); vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit); - vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit); vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit); vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit); vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit); @@ -10442,15 +10575,12 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit); vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit); vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes); - vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes); vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes); vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes); vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes); vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes); vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes); vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes); - vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base); - vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base); vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base); vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base); vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base); @@ -10460,6 +10590,125 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); + vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vmcs12->guest_pending_dbg_exceptions); + vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp); + vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip); + + if (nested_cpu_has_xsaves(vmcs12)) + vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap); + vmcs_write64(VMCS_LINK_POINTER, -1ull); + + if (cpu_has_vmx_posted_intr()) + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR); + + /* + * Whether page-faults are trapped is determined by a combination of + * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. + * If enable_ept, L0 doesn't care about page faults and we should + * set all of these to L1's desires. However, if !enable_ept, L0 does + * care about (at least some) page faults, and because it is not easy + * (if at all possible?) to merge L0 and L1's desires, we simply ask + * to exit on each and every L2 page fault. This is done by setting + * MASK=MATCH=0 and (see below) EB.PF=1. + * Note that below we don't need special code to set EB.PF beyond the + * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, + * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when + * !enable_ept, EB.PF is 1, so the "or" will always be 1. + */ + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, + enable_ept ? vmcs12->page_fault_error_code_mask : 0); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, + enable_ept ? vmcs12->page_fault_error_code_match : 0); + + /* All VMFUNCs are currently emulated through L0 vmexits. */ + if (cpu_has_vmx_vmfunc()) + vmcs_write64(VM_FUNCTION_CONTROL, 0); + + if (cpu_has_vmx_apicv()) { + vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0); + vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1); + vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2); + vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3); + } + + /* + * Set host-state according to L0's settings (vmcs12 is irrelevant here) + * Some constant fields are set here by vmx_set_constant_host_state(). + * Other fields are different per CPU, and will be set later when + * vmx_vcpu_load() is called, and when vmx_save_host_state() is called. + */ + vmx_set_constant_host_state(vmx); + + /* + * Set the MSR load/store lists to match L0's settings. + */ + vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); + vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); + vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); + + set_cr4_guest_host_mask(vmx); + + if (vmx_mpx_supported()) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + + if (enable_vpid) { + if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); + else + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + } + + /* + * L1 may access the L2's PDPTR, so save them to construct vmcs12 + */ + if (enable_ept) { + vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); + vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); + vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); + vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); + } + + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); +} + +/* + * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested + * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it + * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2 + * guest in a way that will both be appropriate to L1's requests, and our + * needs. In addition to modifying the active vmcs (which is vmcs02), this + * function also has additional necessary side-effects, like setting various + * vcpu->arch fields. + * Returns 0 on success, 1 on failure. Invalid state exit qualification code + * is assigned to entry_failure_code on failure. + */ +static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + bool from_vmentry, u32 *entry_failure_code) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 exec_control, vmcs12_exec_ctrl; + + /* + * First, the fields that are shadowed. This must be kept in sync + * with vmx_shadow_fields.h. + */ + + vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); + vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit); + vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes); + vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base); + vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base); + + /* + * Not in vmcs02: GUEST_PML_INDEX, HOST_FS_SELECTOR, HOST_GS_SELECTOR, + * HOST_FS_BASE, HOST_GS_BASE. + */ + if (from_vmentry && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); @@ -10482,16 +10731,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } else { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } - vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); - vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, - vmcs12->guest_pending_dbg_exceptions); - vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp); - vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip); - - if (nested_cpu_has_xsaves(vmcs12)) - vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap); - vmcs_write64(VMCS_LINK_POINTER, -1ull); exec_control = vmcs12->pin_based_vm_exec_control; @@ -10505,7 +10745,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR); } else { exec_control &= ~PIN_BASED_POSTED_INTR; } @@ -10516,25 +10755,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_preemption_timer(vmcs12)) vmx_start_preemption_timer(vcpu); - /* - * Whether page-faults are trapped is determined by a combination of - * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. - * If enable_ept, L0 doesn't care about page faults and we should - * set all of these to L1's desires. However, if !enable_ept, L0 does - * care about (at least some) page faults, and because it is not easy - * (if at all possible?) to merge L0 and L1's desires, we simply ask - * to exit on each and every L2 page fault. This is done by setting - * MASK=MATCH=0 and (see below) EB.PF=1. - * Note that below we don't need special code to set EB.PF beyond the - * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, - * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when - * !enable_ept, EB.PF is 1, so the "or" will always be 1. - */ - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, - enable_ept ? vmcs12->page_fault_error_code_mask : 0); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, - enable_ept ? vmcs12->page_fault_error_code_match : 0); - if (cpu_has_secondary_exec_ctrls()) { exec_control = vmx->secondary_exec_control; @@ -10553,22 +10773,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control |= vmcs12_exec_ctrl; } - /* All VMFUNCs are currently emulated through L0 vmexits. */ - if (exec_control & SECONDARY_EXEC_ENABLE_VMFUNC) - vmcs_write64(VM_FUNCTION_CONTROL, 0); - - if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { - vmcs_write64(EOI_EXIT_BITMAP0, - vmcs12->eoi_exit_bitmap0); - vmcs_write64(EOI_EXIT_BITMAP1, - vmcs12->eoi_exit_bitmap1); - vmcs_write64(EOI_EXIT_BITMAP2, - vmcs12->eoi_exit_bitmap2); - vmcs_write64(EOI_EXIT_BITMAP3, - vmcs12->eoi_exit_bitmap3); + if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) vmcs_write16(GUEST_INTR_STATUS, vmcs12->guest_intr_status); - } /* * Write an illegal value to APIC_ACCESS_ADDR. Later, @@ -10581,24 +10788,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } - - /* - * Set host-state according to L0's settings (vmcs12 is irrelevant here) - * Some constant fields are set here by vmx_set_constant_host_state(). - * Other fields are different per CPU, and will be set later when - * vmx_vcpu_load() is called, and when vmx_save_host_state() is called. - */ - vmx_set_constant_host_state(vmx); - - /* - * Set the MSR load/store lists to match L0's settings. - */ - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); - /* * HOST_RSP is normally set correctly in vmx_vcpu_run() just before * entry, but only if the current (host) sp changed from the value @@ -10630,8 +10819,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } /* - * Merging of IO bitmap not currently supported. - * Rather, exit every time. + * A vmexit (to either L1 hypervisor or L0 userspace) is always needed + * for I/O port accesses. */ exec_control &= ~CPU_BASED_USE_IO_BITMAPS; exec_control |= CPU_BASED_UNCOND_IO_EXITING; @@ -10668,12 +10857,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); } - set_cr4_guest_host_mask(vmx); - - if (from_vmentry && - vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) - vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset + vmcs12->tsc_offset); @@ -10692,16 +10875,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * even if spawn a lot of nested vCPUs. */ if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) { - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true); } } else { - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } - } if (enable_pml) { @@ -10750,6 +10930,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */ vmx_set_efer(vcpu, vcpu->arch.efer); + if (vmx->nested.dirty_vmcs12) { + prepare_vmcs02_full(vcpu, vmcs12, from_vmentry); + vmx->nested.dirty_vmcs12 = false; + } + /* Shadow page tables on either EPT or shadow page tables. */ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), entry_failure_code)) @@ -10758,16 +10943,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; - /* - * L1 may access the L2's PDPTR, so save them to construct vmcs12 - */ - if (enable_ept) { - vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); - vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); - vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); - vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); - } - kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp); kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip); return 0; @@ -10903,20 +11078,15 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - struct loaded_vmcs *vmcs02; u32 msr_entry_idx; u32 exit_qual; - vmcs02 = nested_get_current_vmcs02(vmx); - if (!vmcs02) - return -ENOMEM; - enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); - vmx_switch_vmcs(vcpu, vmcs02); + vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { @@ -11128,7 +11298,6 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); - vcpu->arch.exception.pending = false; return 0; } @@ -11409,11 +11578,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * L1's vpid. TODO: move to a more elaborate solution, giving * each L2 its own vpid and exposing the vpid feature to L1. */ - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } - /* Restore posted intr vector. */ - if (nested_cpu_has_posted_intr(vmcs12)) - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp); @@ -11485,7 +11651,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -11534,10 +11700,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); - /* if no vmcs02 cache requested, remove the one we used */ - if (VMCS02_POOL_SIZE == 0) - nested_free_vmcs02(vmx, vmx->nested.current_vmptr); - /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); @@ -11678,6 +11840,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + /* + * RDPID causes #UD if disabled through secondary execution controls. + * Because it is marked as EmulateOnUD, we need to intercept it here. + */ + if (info->intercept == x86_intercept_rdtscp && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + + /* TODO: check more intercepts... */ return X86EMUL_CONTINUE; } @@ -12191,6 +12368,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .handle_external_intr = vmx_handle_external_intr, .mpx_supported = vmx_mpx_supported, .xsaves_supported = vmx_xsaves_supported, + .umip_emulated = vmx_umip_emulated, .check_nested_events = vmx_check_nested_events, diff --git a/arch/x86/kvm/vmx_shadow_fields.h b/arch/x86/kvm/vmx_shadow_fields.h new file mode 100644 index 000000000000..cd0c75f6d037 --- /dev/null +++ b/arch/x86/kvm/vmx_shadow_fields.h @@ -0,0 +1,77 @@ +#ifndef SHADOW_FIELD_RO +#define SHADOW_FIELD_RO(x) +#endif +#ifndef SHADOW_FIELD_RW +#define SHADOW_FIELD_RW(x) +#endif + +/* + * We do NOT shadow fields that are modified when L0 + * traps and emulates any vmx instruction (e.g. VMPTRLD, + * VMXON...) executed by L1. + * For example, VM_INSTRUCTION_ERROR is read + * by L1 if a vmx instruction fails (part of the error path). + * Note the code assumes this logic. If for some reason + * we start shadowing these fields then we need to + * force a shadow sync when L0 emulates vmx instructions + * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified + * by nested_vmx_failValid) + * + * When adding or removing fields here, note that shadowed + * fields must always be synced by prepare_vmcs02, not just + * prepare_vmcs02_full. + */ + +/* + * Keeping the fields ordered by size is an attempt at improving + * branch prediction in vmcs_read_any and vmcs_write_any. + */ + +/* 16-bits */ +SHADOW_FIELD_RW(GUEST_CS_SELECTOR) +SHADOW_FIELD_RW(GUEST_INTR_STATUS) +SHADOW_FIELD_RW(GUEST_PML_INDEX) +SHADOW_FIELD_RW(HOST_FS_SELECTOR) +SHADOW_FIELD_RW(HOST_GS_SELECTOR) + +/* 32-bits */ +SHADOW_FIELD_RO(VM_EXIT_REASON) +SHADOW_FIELD_RO(VM_EXIT_INTR_INFO) +SHADOW_FIELD_RO(VM_EXIT_INSTRUCTION_LEN) +SHADOW_FIELD_RO(IDT_VECTORING_INFO_FIELD) +SHADOW_FIELD_RO(IDT_VECTORING_ERROR_CODE) +SHADOW_FIELD_RO(VM_EXIT_INTR_ERROR_CODE) +SHADOW_FIELD_RW(CPU_BASED_VM_EXEC_CONTROL) +SHADOW_FIELD_RW(EXCEPTION_BITMAP) +SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE) +SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD) +SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN) +SHADOW_FIELD_RW(TPR_THRESHOLD) +SHADOW_FIELD_RW(GUEST_CS_LIMIT) +SHADOW_FIELD_RW(GUEST_CS_AR_BYTES) +SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO) +SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE) + +/* Natural width */ +SHADOW_FIELD_RO(EXIT_QUALIFICATION) +SHADOW_FIELD_RO(GUEST_LINEAR_ADDRESS) +SHADOW_FIELD_RW(GUEST_RIP) +SHADOW_FIELD_RW(GUEST_RSP) +SHADOW_FIELD_RW(GUEST_CR0) +SHADOW_FIELD_RW(GUEST_CR3) +SHADOW_FIELD_RW(GUEST_CR4) +SHADOW_FIELD_RW(GUEST_RFLAGS) +SHADOW_FIELD_RW(GUEST_CS_BASE) +SHADOW_FIELD_RW(GUEST_ES_BASE) +SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK) +SHADOW_FIELD_RW(CR0_READ_SHADOW) +SHADOW_FIELD_RW(CR4_READ_SHADOW) +SHADOW_FIELD_RW(HOST_FS_BASE) +SHADOW_FIELD_RW(HOST_GS_BASE) + +/* 64-bit */ +SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS) +SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS_HIGH) + +#undef SHADOW_FIELD_RO +#undef SHADOW_FIELD_RW diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c53298dfbf50..c8a0b545ac20 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -67,6 +67,8 @@ #include <asm/pvclock.h> #include <asm/div64.h> #include <asm/irq_remapping.h> +#include <asm/mshyperv.h> +#include <asm/hypervisor.h> #define CREATE_TRACE_POINTS #include "trace.h" @@ -177,7 +179,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "request_irq", VCPU_STAT(request_irq_exits) }, { "irq_exits", VCPU_STAT(irq_exits) }, { "host_state_reload", VCPU_STAT(host_state_reload) }, - { "efer_reload", VCPU_STAT(efer_reload) }, { "fpu_reload", VCPU_STAT(fpu_reload) }, { "insn_emulation", VCPU_STAT(insn_emulation) }, { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, @@ -702,7 +703,8 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { /* kvm_set_xcr() also depends on this */ - xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); + if (vcpu->arch.xcr0 != host_xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); vcpu->guest_xcr0_loaded = 1; } } @@ -794,6 +796,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + return 1; + if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; @@ -1009,6 +1014,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES }; static unsigned num_msrs_to_save; @@ -1036,6 +1042,7 @@ static u32 emulated_msrs[] = { MSR_IA32_MCG_CTL, MSR_IA32_MCG_EXT_CTL, MSR_IA32_SMBASE, + MSR_SMI_COUNT, MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, }; @@ -1377,6 +1384,11 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +static inline int gtod_is_based_on_tsc(int mode) +{ + return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK; +} + static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 @@ -1396,7 +1408,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) * perform request to enable masterclock. */ if (ka->use_master_clock || - (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched)) + (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -1459,6 +1471,19 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) vcpu->arch.tsc_offset = offset; } +static inline bool kvm_check_tsc_unstable(void) +{ +#ifdef CONFIG_X86_64 + /* + * TSC is marked unstable when we're running on Hyper-V, + * 'TSC page' clocksource is good. + */ + if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK) + return false; +#endif + return check_tsc_unstable(); +} + void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; @@ -1504,7 +1529,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) */ if (synchronizing && vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { - if (!check_tsc_unstable()) { + if (!kvm_check_tsc_unstable()) { offset = kvm->arch.cur_tsc_offset; pr_debug("kvm: matched tsc offset for %llu\n", data); } else { @@ -1604,18 +1629,43 @@ static u64 read_tsc(void) return last; } -static inline u64 vgettsc(u64 *cycle_now) +static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) { long v; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + u64 tsc_pg_val; + + switch (gtod->clock.vclock_mode) { + case VCLOCK_HVCLOCK: + tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(), + tsc_timestamp); + if (tsc_pg_val != U64_MAX) { + /* TSC page valid */ + *mode = VCLOCK_HVCLOCK; + v = (tsc_pg_val - gtod->clock.cycle_last) & + gtod->clock.mask; + } else { + /* TSC page invalid */ + *mode = VCLOCK_NONE; + } + break; + case VCLOCK_TSC: + *mode = VCLOCK_TSC; + *tsc_timestamp = read_tsc(); + v = (*tsc_timestamp - gtod->clock.cycle_last) & + gtod->clock.mask; + break; + default: + *mode = VCLOCK_NONE; + } - *cycle_now = read_tsc(); + if (*mode == VCLOCK_NONE) + *tsc_timestamp = v = 0; - v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask; return v * gtod->clock.mult; } -static int do_monotonic_boot(s64 *t, u64 *cycle_now) +static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1624,9 +1674,8 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now) do { seq = read_seqcount_begin(>od->seq); - mode = gtod->clock.vclock_mode; ns = gtod->nsec_base; - ns += vgettsc(cycle_now); + ns += vgettsc(tsc_timestamp, &mode); ns >>= gtod->clock.shift; ns += gtod->boot_ns; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -1635,7 +1684,7 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now) return mode; } -static int do_realtime(struct timespec *ts, u64 *cycle_now) +static int do_realtime(struct timespec *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1644,10 +1693,9 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now) do { seq = read_seqcount_begin(>od->seq); - mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->nsec_base; - ns += vgettsc(cycle_now); + ns += vgettsc(tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -1657,25 +1705,26 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now) return mode; } -/* returns true if host is using tsc clocksource */ -static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now) +/* returns true if host is using TSC based clocksource */ +static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ - if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC; + return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns, + tsc_timestamp)); } -/* returns true if host is using tsc clocksource */ +/* returns true if host is using TSC based clocksource */ static bool kvm_get_walltime_and_clockread(struct timespec *ts, - u64 *cycle_now) + u64 *tsc_timestamp) { /* checked again under seqlock below */ - if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return do_realtime(ts, cycle_now) == VCLOCK_TSC; + return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp)); } #endif @@ -2118,6 +2167,12 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) vcpu->arch.pv_time_enabled = false; } +static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) +{ + ++vcpu->stat.tlb_flush; + kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa); +} + static void record_steal_time(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) @@ -2127,7 +2182,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu) &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) return; - vcpu->arch.st.steal.preempted = 0; + /* + * Doing a TLB flush here, on the guest's behalf, can avoid + * expensive IPIs. + */ + if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) + kvm_vcpu_flush_tlb(vcpu, false); if (vcpu->arch.st.steal.version & 1) vcpu->arch.st.steal.version += 1; /* first time write, random junk */ @@ -2228,6 +2288,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.smbase = data; break; + case MSR_SMI_COUNT: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.smi_count = data; + break; case MSR_KVM_WALL_CLOCK_NEW: case MSR_KVM_WALL_CLOCK: vcpu->kvm->arch.wall_clock = data; @@ -2502,6 +2567,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; msr_info->data = vcpu->arch.smbase; break; + case MSR_SMI_COUNT: + msr_info->data = vcpu->arch.smi_count; + break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ msr_info->data = 1000ULL; @@ -2869,13 +2937,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } - if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { + if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) { s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); - if (check_tsc_unstable()) { + if (kvm_check_tsc_unstable()) { u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); @@ -2904,7 +2972,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - vcpu->arch.st.steal.preempted = 1; + vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, &vcpu->arch.st.steal.preempted, @@ -2938,12 +3006,18 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) pagefault_enable(); kvm_x86_ops->vcpu_put(vcpu); vcpu->arch.last_host_tsc = rdtsc(); + /* + * If userspace has set any breakpoints or watchpoints, dr6 is restored + * on every vmexit, but if not, we might have a stale dr6 from the + * guest. do_debug expects dr6 to be cleared after it runs, do the same. + */ + set_debugreg(0, 6); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) + if (vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); return kvm_apic_get_state(vcpu, s); @@ -3472,6 +3546,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void *buffer; } u; + vcpu_load(vcpu); + u.buffer = NULL; switch (ioctl) { case KVM_GET_LAPIC: { @@ -3497,8 +3573,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!lapic_in_kernel(vcpu)) goto out; u.lapic = memdup_user(argp, sizeof(*u.lapic)); - if (IS_ERR(u.lapic)) - return PTR_ERR(u.lapic); + if (IS_ERR(u.lapic)) { + r = PTR_ERR(u.lapic); + goto out_nofree; + } r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); break; @@ -3672,8 +3750,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_SET_XSAVE: { u.xsave = memdup_user(argp, sizeof(*u.xsave)); - if (IS_ERR(u.xsave)) - return PTR_ERR(u.xsave); + if (IS_ERR(u.xsave)) { + r = PTR_ERR(u.xsave); + goto out_nofree; + } r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; @@ -3695,8 +3775,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_SET_XCRS: { u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); - if (IS_ERR(u.xcrs)) - return PTR_ERR(u.xcrs); + if (IS_ERR(u.xcrs)) { + r = PTR_ERR(u.xcrs); + goto out_nofree; + } r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; @@ -3740,6 +3822,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } out: kfree(u.buffer); +out_nofree: + vcpu_put(vcpu); return r; } @@ -4237,13 +4321,14 @@ set_identity_unlock: mutex_unlock(&kvm->lock); break; case KVM_XEN_HVM_CONFIG: { + struct kvm_xen_hvm_config xhc; r = -EFAULT; - if (copy_from_user(&kvm->arch.xen_hvm_config, argp, - sizeof(struct kvm_xen_hvm_config))) + if (copy_from_user(&xhc, argp, sizeof(xhc))) goto out; r = -EINVAL; - if (kvm->arch.xen_hvm_config.flags) + if (xhc.flags) goto out; + memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc)); r = 0; break; } @@ -4295,6 +4380,36 @@ set_identity_unlock: r = kvm_vm_ioctl_enable_cap(kvm, &cap); break; } + case KVM_MEMORY_ENCRYPT_OP: { + r = -ENOTTY; + if (kvm_x86_ops->mem_enc_op) + r = kvm_x86_ops->mem_enc_op(kvm, argp); + break; + } + case KVM_MEMORY_ENCRYPT_REG_REGION: { + struct kvm_enc_region region; + + r = -EFAULT; + if (copy_from_user(®ion, argp, sizeof(region))) + goto out; + + r = -ENOTTY; + if (kvm_x86_ops->mem_enc_reg_region) + r = kvm_x86_ops->mem_enc_reg_region(kvm, ®ion); + break; + } + case KVM_MEMORY_ENCRYPT_UNREG_REGION: { + struct kvm_enc_region region; + + r = -EFAULT; + if (copy_from_user(®ion, argp, sizeof(region))) + goto out; + + r = -ENOTTY; + if (kvm_x86_ops->mem_enc_unreg_region) + r = kvm_x86_ops->mem_enc_unreg_region(kvm, ®ion); + break; + } default: r = -ENOTTY; } @@ -5703,7 +5818,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, * handle watchpoints yet, those would be handled in * the emulate_ops. */ - if (kvm_vcpu_check_breakpoint(vcpu, &r)) + if (!(emulation_type & EMULTYPE_SKIP) && + kvm_vcpu_check_breakpoint(vcpu, &r)) return r; ctxt->interruptibility = 0; @@ -5889,6 +6005,43 @@ static void tsc_khz_changed(void *data) __this_cpu_write(cpu_tsc_khz, khz); } +#ifdef CONFIG_X86_64 +static void kvm_hyperv_tsc_notifier(void) +{ + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int cpu; + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) + kvm_make_mclock_inprogress_request(kvm); + + hyperv_stop_tsc_emulation(); + + /* TSC frequency always matches when on Hyper-V */ + for_each_present_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + kvm_max_guest_tsc_khz = tsc_khz; + + list_for_each_entry(kvm, &vm_list, vm_list) { + struct kvm_arch *ka = &kvm->arch; + + spin_lock(&ka->pvclock_gtod_sync_lock); + + pvclock_update_vm_gtod_copy(kvm); + + kvm_for_each_vcpu(cpu, vcpu, kvm) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + + kvm_for_each_vcpu(cpu, vcpu, kvm) + kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); + + spin_unlock(&ka->pvclock_gtod_sync_lock); + } + spin_unlock(&kvm_lock); +} +#endif + static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -6110,9 +6263,9 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, update_pvclock_gtod(tk); /* disable master clock if host does not trust, or does not - * use, TSC clocksource + * use, TSC based clocksource. */ - if (gtod->clock.vclock_mode != VCLOCK_TSC && + if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) queue_work(system_long_wq, &pvclock_gtod_work); @@ -6174,6 +6327,9 @@ int kvm_arch_init(void *opaque) kvm_lapic_init(); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); + + if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) + set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif return 0; @@ -6186,6 +6342,10 @@ out: void kvm_arch_exit(void) { +#ifdef CONFIG_X86_64 + if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) + clear_hv_tscchange_cb(); +#endif kvm_lapic_exit(); perf_unregister_guest_info_callbacks(&kvm_guest_cbs); @@ -6448,6 +6608,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) kvm_x86_ops->queue_exception(vcpu); } else if (vcpu->arch.smi_pending && !is_smm(vcpu) && kvm_x86_ops->smi_allowed(vcpu)) { vcpu->arch.smi_pending = false; + ++vcpu->arch.smi_count; enter_smm(vcpu); } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { --vcpu->arch.nmi_pending; @@ -6749,7 +6910,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) + if (vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -6758,12 +6919,6 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } -static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu); -} - void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end) { @@ -6832,7 +6987,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) - kvm_vcpu_flush_tlb(vcpu); + kvm_vcpu_flush_tlb(vcpu, true); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; @@ -6981,10 +7136,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * This handles the case where a posted interrupt was * notified with kvm_vcpu_kick. */ - if (kvm_lapic_enabled(vcpu)) { - if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); - } + if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || need_resched() || signal_pending(current)) { @@ -7005,7 +7158,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); + if (lapic_timer_advance_ns) + wait_lapic_expire(vcpu); guest_enter_irqoff(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -7266,8 +7420,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; + vcpu_load(vcpu); kvm_sigset_activate(vcpu); - kvm_load_guest_fpu(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { @@ -7314,11 +7468,14 @@ out: post_kvm_run_save(vcpu); kvm_sigset_deactivate(vcpu); + vcpu_put(vcpu); return r; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + vcpu_load(vcpu); + if (vcpu->arch.emulate_regs_need_sync_to_vcpu) { /* * We are here if userspace calls get_regs() in the middle of @@ -7352,11 +7509,14 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) regs->rip = kvm_rip_read(vcpu); regs->rflags = kvm_get_rflags(vcpu); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + vcpu_load(vcpu); + vcpu->arch.emulate_regs_need_sync_from_vcpu = true; vcpu->arch.emulate_regs_need_sync_to_vcpu = false; @@ -7386,6 +7546,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_make_request(KVM_REQ_EVENT, vcpu); + vcpu_put(vcpu); return 0; } @@ -7404,6 +7565,8 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, { struct desc_ptr dt; + vcpu_load(vcpu); + kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); @@ -7435,12 +7598,15 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + vcpu_load(vcpu); + kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && vcpu->arch.pv.pv_unhalted) @@ -7448,21 +7614,26 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int ret = -EINVAL; + + vcpu_load(vcpu); + if (!lapic_in_kernel(vcpu) && mp_state->mp_state != KVM_MP_STATE_RUNNABLE) - return -EINVAL; + goto out; /* INITs are latched while in SMM */ if ((is_smm(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) - return -EINVAL; + goto out; if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; @@ -7470,7 +7641,11 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, } else vcpu->arch.mp_state = mp_state->mp_state; kvm_make_request(KVM_REQ_EVENT, vcpu); - return 0; + + ret = 0; +out: + vcpu_put(vcpu); + return ret; } int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, @@ -7524,18 +7699,21 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int mmu_reset_needed = 0; int pending_vec, max_bits, idx; struct desc_ptr dt; + int ret = -EINVAL; + + vcpu_load(vcpu); if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; + goto out; if (kvm_valid_sregs(vcpu, sregs)) - return -EINVAL; + goto out; apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) - return -EINVAL; + goto out; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; @@ -7601,7 +7779,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_EVENT, vcpu); - return 0; + ret = 0; +out: + vcpu_put(vcpu); + return ret; } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, @@ -7610,6 +7791,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, unsigned long rflags; int i, r; + vcpu_load(vcpu); + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; if (vcpu->arch.exception.pending) @@ -7655,7 +7838,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, r = 0; out: - + vcpu_put(vcpu); return r; } @@ -7669,6 +7852,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, gpa_t gpa; int idx; + vcpu_load(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -7677,14 +7862,17 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, tr->writeable = 1; tr->usermode = 0; + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxregs_state *fxsave = - &vcpu->arch.guest_fpu.state.fxsave; + struct fxregs_state *fxsave; + + vcpu_load(vcpu); + fxsave = &vcpu->arch.guest_fpu.state.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; fpu->fsw = fxsave->swd; @@ -7694,13 +7882,17 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fpu->last_dp = fxsave->rdp; memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxregs_state *fxsave = - &vcpu->arch.guest_fpu.state.fxsave; + struct fxregs_state *fxsave; + + vcpu_load(vcpu); + + fxsave = &vcpu->arch.guest_fpu.state.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -7711,6 +7903,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fxsave->rdp = fpu->last_dp; memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); + vcpu_put(vcpu); return 0; } @@ -7767,7 +7960,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, { struct kvm_vcpu *vcpu; - if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) printk_once(KERN_WARNING "kvm: SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); @@ -7779,16 +7972,12 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - int r; - kvm_vcpu_mtrr_init(vcpu); - r = vcpu_load(vcpu); - if (r) - return r; + vcpu_load(vcpu); kvm_vcpu_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); - return r; + return 0; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -7798,13 +7987,15 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) kvm_hv_vcpu_postcreate(vcpu); - if (vcpu_load(vcpu)) + if (mutex_lock_killable(&vcpu->mutex)) return; + vcpu_load(vcpu); msr.data = 0x0; msr.index = MSR_IA32_TSC; msr.host_initiated = true; kvm_write_tsc(vcpu, &msr); vcpu_put(vcpu); + mutex_unlock(&vcpu->mutex); if (!kvmclock_periodic_sync) return; @@ -7815,11 +8006,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - int r; vcpu->arch.apf.msr_val = 0; - r = vcpu_load(vcpu); - BUG_ON(r); + vcpu_load(vcpu); kvm_mmu_unload(vcpu); vcpu_put(vcpu); @@ -7831,6 +8020,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; + vcpu->arch.smi_count = 0; atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; @@ -7924,7 +8114,7 @@ int kvm_arch_hardware_enable(void) return ret; local_tsc = rdtsc(); - stable = !check_tsc_unstable(); + stable = !kvm_check_tsc_unstable(); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (!stable && vcpu->cpu == smp_processor_id()) @@ -8190,9 +8380,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { - int r; - r = vcpu_load(vcpu); - BUG_ON(r); + vcpu_load(vcpu); kvm_mmu_unload(vcpu); vcpu_put(vcpu); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index d0b95b7a90b4..b91215d1fd80 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -12,6 +12,7 @@ static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) { + vcpu->arch.exception.pending = false; vcpu->arch.exception.injected = false; } @@ -265,36 +266,8 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) static inline bool kvm_mwait_in_guest(void) { - unsigned int eax, ebx, ecx, edx; - - if (!cpu_has(&boot_cpu_data, X86_FEATURE_MWAIT)) - return false; - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - /* All AMD CPUs have a working MWAIT implementation */ - return true; - case X86_VENDOR_INTEL: - /* Handle Intel below */ - break; - default: - return false; - } - - /* - * Intel CPUs without CPUID5_ECX_INTERRUPT_BREAK are problematic as - * they would allow guest to stop the CPU completely by disabling - * interrupts then invoking MWAIT. - */ - if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) - return false; - - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); - - if (!(ecx & CPUID5_ECX_INTERRUPT_BREAK)) - return false; - - return true; + return boot_cpu_has(X86_FEATURE_MWAIT) && + !boot_cpu_has_bug(X86_BUG_MONITOR); } #endif diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index c97d935a29e8..49b167f73215 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -40,6 +40,8 @@ ENTRY(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -54,6 +56,8 @@ ENTRY(__get_user_2) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax @@ -68,6 +72,8 @@ ENTRY(__get_user_4) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 3: movl -3(%_ASM_AX),%edx xor %eax,%eax @@ -83,6 +89,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movq -7(%_ASM_AX),%rdx xor %eax,%eax @@ -94,6 +102,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user_8 + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movl -7(%_ASM_AX),%edx 5: movl -3(%_ASM_AX),%ecx diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1b377f734e64..7add8ba06887 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -331,12 +331,12 @@ do { \ unsigned long __copy_user_ll(void *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_user_ll); @@ -344,7 +344,7 @@ EXPORT_SYMBOL(__copy_user_ll); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); @@ -353,7 +353,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 135c9a7898c7..79cb066f40c0 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -829,23 +829,24 @@ void __init mem_init(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock) +int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, + bool want_memblock) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - return __add_pages(nid, start_pfn, nr_pages, want_memblock); + return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock); } #ifdef CONFIG_MEMORY_HOTREMOVE -int arch_remove_memory(u64 start, u64 size) +int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; struct zone *zone; zone = page_zone(pfn_to_page(start_pfn)); - return __remove_pages(zone, start_pfn, nr_pages); + return __remove_pages(zone, start_pfn, nr_pages, altmap); } #endif #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 4a837289f2ad..1ab42c852069 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -772,12 +772,12 @@ static void update_end_of_memory_vars(u64 start, u64 size) } } -int add_pages(int nid, unsigned long start_pfn, - unsigned long nr_pages, bool want_memblock) +int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, + struct vmem_altmap *altmap, bool want_memblock) { int ret; - ret = __add_pages(nid, start_pfn, nr_pages, want_memblock); + ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock); WARN_ON_ONCE(ret); /* update max_pfn, max_low_pfn and high_memory */ @@ -787,24 +787,24 @@ int add_pages(int nid, unsigned long start_pfn, return ret; } -int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock) +int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, + bool want_memblock) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; init_memory_mapping(start, start + size); - return add_pages(nid, start_pfn, nr_pages, want_memblock); + return add_pages(nid, start_pfn, nr_pages, altmap, want_memblock); } -EXPORT_SYMBOL_GPL(arch_add_memory); #define PAGE_INUSE 0xFD -static void __meminit free_pagetable(struct page *page, int order) +static void __meminit free_pagetable(struct page *page, int order, + struct vmem_altmap *altmap) { unsigned long magic; unsigned int nr_pages = 1 << order; - struct vmem_altmap *altmap = to_vmem_altmap((unsigned long) page); if (altmap) { vmem_altmap_free(altmap, nr_pages); @@ -826,7 +826,8 @@ static void __meminit free_pagetable(struct page *page, int order) free_pages((unsigned long)page_address(page), order); } -static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd, + struct vmem_altmap *altmap) { pte_t *pte; int i; @@ -838,13 +839,14 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) } /* free a pte talbe */ - free_pagetable(pmd_page(*pmd), 0); + free_pagetable(pmd_page(*pmd), 0, altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, + struct vmem_altmap *altmap) { pmd_t *pmd; int i; @@ -856,13 +858,14 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) } /* free a pmd talbe */ - free_pagetable(pud_page(*pud), 0); + free_pagetable(pud_page(*pud), 0, altmap); spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); } -static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d, + struct vmem_altmap *altmap) { pud_t *pud; int i; @@ -874,7 +877,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) } /* free a pud talbe */ - free_pagetable(p4d_page(*p4d), 0); + free_pagetable(p4d_page(*p4d), 0, altmap); spin_lock(&init_mm.page_table_lock); p4d_clear(p4d); spin_unlock(&init_mm.page_table_lock); @@ -882,7 +885,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, - bool direct) + struct vmem_altmap *altmap, bool direct) { unsigned long next, pages = 0; pte_t *pte; @@ -913,7 +916,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, * freed when offlining, or simplely not in use. */ if (!direct) - free_pagetable(pte_page(*pte), 0); + free_pagetable(pte_page(*pte), 0, altmap); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); @@ -936,7 +939,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, page_addr = page_address(pte_page(*pte)); if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) { - free_pagetable(pte_page(*pte), 0); + free_pagetable(pte_page(*pte), 0, altmap); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); @@ -953,7 +956,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, - bool direct) + bool direct, struct vmem_altmap *altmap) { unsigned long next, pages = 0; pte_t *pte_base; @@ -972,7 +975,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, IS_ALIGNED(next, PMD_SIZE)) { if (!direct) free_pagetable(pmd_page(*pmd), - get_order(PMD_SIZE)); + get_order(PMD_SIZE), + altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); @@ -986,7 +990,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, if (!memchr_inv(page_addr, PAGE_INUSE, PMD_SIZE)) { free_pagetable(pmd_page(*pmd), - get_order(PMD_SIZE)); + get_order(PMD_SIZE), + altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); @@ -998,8 +1003,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, } pte_base = (pte_t *)pmd_page_vaddr(*pmd); - remove_pte_table(pte_base, addr, next, direct); - free_pte_table(pte_base, pmd); + remove_pte_table(pte_base, addr, next, altmap, direct); + free_pte_table(pte_base, pmd, altmap); } /* Call free_pmd_table() in remove_pud_table(). */ @@ -1009,7 +1014,7 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, - bool direct) + struct vmem_altmap *altmap, bool direct) { unsigned long next, pages = 0; pmd_t *pmd_base; @@ -1028,7 +1033,8 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, IS_ALIGNED(next, PUD_SIZE)) { if (!direct) free_pagetable(pud_page(*pud), - get_order(PUD_SIZE)); + get_order(PUD_SIZE), + altmap); spin_lock(&init_mm.page_table_lock); pud_clear(pud); @@ -1042,7 +1048,8 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, if (!memchr_inv(page_addr, PAGE_INUSE, PUD_SIZE)) { free_pagetable(pud_page(*pud), - get_order(PUD_SIZE)); + get_order(PUD_SIZE), + altmap); spin_lock(&init_mm.page_table_lock); pud_clear(pud); @@ -1054,8 +1061,8 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, } pmd_base = pmd_offset(pud, 0); - remove_pmd_table(pmd_base, addr, next, direct); - free_pmd_table(pmd_base, pud); + remove_pmd_table(pmd_base, addr, next, direct, altmap); + free_pmd_table(pmd_base, pud, altmap); } if (direct) @@ -1064,7 +1071,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, static void __meminit remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, - bool direct) + struct vmem_altmap *altmap, bool direct) { unsigned long next, pages = 0; pud_t *pud_base; @@ -1080,14 +1087,14 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, BUILD_BUG_ON(p4d_large(*p4d)); pud_base = pud_offset(p4d, 0); - remove_pud_table(pud_base, addr, next, direct); + remove_pud_table(pud_base, addr, next, altmap, direct); /* * For 4-level page tables we do not want to free PUDs, but in the * 5-level case we should free them. This code will have to change * to adapt for boot-time switching between 4 and 5 level page tables. */ if (CONFIG_PGTABLE_LEVELS == 5) - free_pud_table(pud_base, p4d); + free_pud_table(pud_base, p4d, altmap); } if (direct) @@ -1096,7 +1103,8 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, /* start and end are both virtual address. */ static void __meminit -remove_pagetable(unsigned long start, unsigned long end, bool direct) +remove_pagetable(unsigned long start, unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long next; unsigned long addr; @@ -1111,15 +1119,16 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) continue; p4d = p4d_offset(pgd, 0); - remove_p4d_table(p4d, addr, next, direct); + remove_p4d_table(p4d, addr, next, altmap, direct); } flush_tlb_all(); } -void __ref vmemmap_free(unsigned long start, unsigned long end) +void __ref vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) { - remove_pagetable(start, end, false); + remove_pagetable(start, end, false, altmap); } #ifdef CONFIG_MEMORY_HOTREMOVE @@ -1129,24 +1138,22 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end) start = (unsigned long)__va(start); end = (unsigned long)__va(end); - remove_pagetable(start, end, true); + remove_pagetable(start, end, true, NULL); } -int __ref arch_remove_memory(u64 start, u64 size) +int __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; struct page *page = pfn_to_page(start_pfn); - struct vmem_altmap *altmap; struct zone *zone; int ret; /* With altmap the first mapped page is offset from @start */ - altmap = to_vmem_altmap((unsigned long) page); if (altmap) page += vmem_altmap_offset(altmap); zone = page_zone(page); - ret = __remove_pages(zone, start_pfn, nr_pages); + ret = __remove_pages(zone, start_pfn, nr_pages, altmap); WARN_ON_ONCE(ret); kernel_physical_mapping_remove(start, start + size); @@ -1378,7 +1385,10 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (pmd_none(*pmd)) { void *p; - p = __vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); + if (altmap) + p = altmap_alloc_block_buf(PMD_SIZE, altmap); + else + p = vmemmap_alloc_block_buf(PMD_SIZE, node); if (p) { pte_t entry; @@ -1411,9 +1421,9 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, return 0; } -int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) { - struct vmem_altmap *altmap = to_vmem_altmap(start); int err; if (boot_cpu_has(X86_FEATURE_PSE)) diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 4d434ddb75db..2c1ecf4763c4 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -29,7 +29,6 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/io.h> -#include <linux/kallsyms.h> #include <asm/pgtable.h> #include <linux/mmiotrace.h> #include <asm/e820/api.h> /* for ISA_START_ADDRESS */ @@ -123,8 +122,8 @@ static void die_kmmio_nesting_error(struct pt_regs *regs, unsigned long addr) pr_emerg("unexpected fault for address: 0x%08lx, last fault for address: 0x%08lx\n", addr, my_reason->addr); print_pte(addr); - print_symbol(KERN_EMERG "faulting IP is at %s\n", regs->ip); - print_symbol(KERN_EMERG "last faulting IP was at %s\n", my_reason->ip); + pr_emerg("faulting IP is at %pS\n", (void *)regs->ip); + pr_emerg("last faulting IP was at %pS\n", (void *)my_reason->ip); #ifdef __i386__ pr_emerg("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", regs->ax, regs->bx, regs->cx, regs->dx); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index fe7d57a8fb60..1555bd7d3449 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -678,6 +678,25 @@ static enum page_cache_mode lookup_memtype(u64 paddr) } /** + * pat_pfn_immune_to_uc_mtrr - Check whether the PAT memory type + * of @pfn cannot be overridden by UC MTRR memory type. + * + * Only to be called when PAT is enabled. + * + * Returns true, if the PAT memory type of @pfn is UC, UC-, or WC. + * Returns false in other cases. + */ +bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn) +{ + enum page_cache_mode cm = lookup_memtype(PFN_PHYS(pfn)); + + return cm == _PAGE_CACHE_MODE_UC || + cm == _PAGE_CACHE_MODE_UC_MINUS || + cm == _PAGE_CACHE_MODE_WC; +} +EXPORT_SYMBOL_GPL(pat_pfn_immune_to_uc_mtrr); + +/** * io_reserve_memtype - Request a memory type mapping for a region of memory * @start: start (physical address) of the region * @end: end (physical address) of the region diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5bfe61a5e8e3..8dcc0607f805 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -6,13 +6,14 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> -#include <linux/debugfs.h> /* * TLB flushing, formerly SMP-only @@ -228,6 +229,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, #endif this_cpu_write(cpu_tlbstate.is_lazy, false); + /* + * The membarrier system call requires a full memory barrier and + * core serialization before returning to user-space, after + * storing to rq->curr. Writing to CR3 provides that full + * memory barrier and core serializing instruction. + */ if (real_prev == next) { VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); @@ -247,6 +254,27 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } else { u16 new_asid; bool need_flush; + u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); + + /* + * Avoid user/user BTB poisoning by flushing the branch + * predictor when switching between processes. This stops + * one process from doing Spectre-v2 attacks on another. + * + * As an optimization, flush indirect branches only when + * switching into processes that disable dumping. This + * protects high value processes like gpg, without having + * too high performance overhead. IBPB is *expensive*! + * + * This will not flush branches when switching into kernel + * threads. It will also not flush if we switch to idle + * thread and back to the same process. It will flush if we + * switch to a different non-dumpable process. + */ + if (tsk && tsk->mm && + tsk->mm->context.ctx_id != last_ctx_id && + get_dumpable(tsk->mm) != SUID_DUMP_USER) + indirect_branch_prediction_barrier(); if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* @@ -292,6 +320,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); } @@ -369,6 +405,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ + this_cpu_write(cpu_tlbstate.last_ctx_id, mm->context.ctx_id); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 0452629148be..52e55108404e 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -839,7 +839,8 @@ static void __init pirq_find_router(struct irq_router *r) DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for [%04x:%04x]\n", rt->rtr_vendor, rt->rtr_device); - pirq_router_dev = pci_get_bus_and_slot(rt->rtr_bus, rt->rtr_devfn); + pirq_router_dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus, + rt->rtr_devfn); if (!pirq_router_dev) { DBG(KERN_DEBUG "PCI: Interrupt router not found at " "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index c4b3646bd04c..9542a746dc50 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -409,10 +409,8 @@ int __init pci_xen_init(void) pcibios_enable_irq = xen_pcifront_enable_irq; pcibios_disable_irq = NULL; -#ifdef CONFIG_ACPI /* Keep ACPI out of the picture */ - acpi_noirq = 1; -#endif + acpi_noirq_set(); #ifdef CONFIG_PCI_MSI x86_msi.setup_msi_irqs = xen_setup_msi_irqs; diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index a952ac199741..6f37a2137a79 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -218,14 +218,23 @@ int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(iosf_mbi_register_pmic_bus_access_notifier); +int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked( + struct notifier_block *nb) +{ + iosf_mbi_assert_punit_acquired(); + + return blocking_notifier_chain_unregister( + &iosf_mbi_pmic_bus_access_notifier, nb); +} +EXPORT_SYMBOL(iosf_mbi_unregister_pmic_bus_access_notifier_unlocked); + int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb) { int ret; /* Wait for the bus to go inactive before unregistering */ mutex_lock(&iosf_mbi_punit_mutex); - ret = blocking_notifier_chain_unregister( - &iosf_mbi_pmic_bus_access_notifier, nb); + ret = iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(nb); mutex_unlock(&iosf_mbi_punit_mutex); return ret; @@ -239,6 +248,12 @@ int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v) } EXPORT_SYMBOL(iosf_mbi_call_pmic_bus_access_notifier_chain); +void iosf_mbi_assert_punit_acquired(void) +{ + WARN_ON(!mutex_is_locked(&iosf_mbi_punit_mutex)); +} +EXPORT_SYMBOL(iosf_mbi_assert_punit_acquired); + #ifdef CONFIG_IOSF_MBI_DEBUG static u32 dbg_mdr; static u32 dbg_mcr; diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index c35fdb585c68..afc4ed7b1578 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -145,7 +145,7 @@ static inline void resume_init_first_level_page_table(pgd_t *pg_dir) #endif } -int swsusp_arch_resume(void) +asmlinkage int swsusp_arch_resume(void) { int error; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index f910c514438f..0ef5e5204968 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -174,7 +174,7 @@ out: return 0; } -int swsusp_arch_resume(void) +asmlinkage int swsusp_arch_resume(void) { int error; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 13b4f19b9131..159a897151d6 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -694,6 +694,9 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, int i, ret = 0; pte_t *pte; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + if (kmap_ops) { ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, kmap_ops, count); @@ -736,6 +739,9 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, { int i, ret = 0; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + for (i = 0; i < count; i++) { unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 497cc55a0c16..96f26e026783 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -9,7 +9,9 @@ #include <asm/boot.h> #include <asm/asm.h> +#include <asm/msr.h> #include <asm/page_types.h> +#include <asm/percpu.h> #include <asm/unwind_hints.h> #include <xen/interface/elfnote.h> @@ -35,6 +37,20 @@ ENTRY(startup_xen) mov %_ASM_SI, xen_start_info mov $init_thread_union+THREAD_SIZE, %_ASM_SP +#ifdef CONFIG_X86_64 + /* Set up %gs. + * + * The base of %gs always points to the bottom of the irqstack + * union. If the stack protector canary is enabled, it is + * located at %gs:40. Note that, on SMP, the boot cpu uses + * init data section till per cpu areas are set up. + */ + movl $MSR_GS_BASE,%ecx + movq $INIT_PER_CPU_VAR(irq_stack_union),%rax + cdq + wrmsr +#endif + jmp xen_start_kernel END(startup_xen) __FINIT |