diff options
Diffstat (limited to 'arch')
194 files changed, 3649 insertions, 2239 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 26b8ed11639d..d3c4ab249e9c 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -991,6 +991,16 @@ config HAVE_ARCH_COMPAT_MMAP_BASES and vice-versa 32-bit applications to call 64-bit mmap(). Required for applications doing different bitness syscalls. +config PAGE_SIZE_LESS_THAN_64KB + def_bool y + depends on !ARM64_64K_PAGES + depends on !IA64_PAGE_SIZE_64KB + depends on !PAGE_SIZE_64KB + depends on !PARISC_PAGE_SIZE_64KB + depends on !PPC_64K_PAGES + depends on !PPC_256K_PAGES + depends on !PAGE_SIZE_256KB + # This allows to use a set of generic functions to determine mmap base # address by giving priority to top-down scheme only if the process # is not in legacy mode (compat task, unlimited stack size or diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index e4a041cd5715..ca5a32228cd6 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -488,3 +488,4 @@ 556 common landlock_restrict_self sys_landlock_restrict_self # 557 reserved for memfd_secret 558 common process_mrelease sys_process_mrelease +559 common futex_waitv sys_futex_waitv diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index e8c2c7469e10..e201b4b1655a 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -36,7 +36,6 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void dma_cache_wback_inv(phys_addr_t start, unsigned long sz); void dma_cache_inv(phys_addr_t start, unsigned long sz); diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi index 3b60297af7f6..9e01dbca4a01 100644 --- a/arch/arm/boot/dts/bcm2711.dtsi +++ b/arch/arm/boot/dts/bcm2711.dtsi @@ -506,11 +506,17 @@ #address-cells = <3>; #interrupt-cells = <1>; #size-cells = <2>; - interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>, + interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "pcie", "msi"; interrupt-map-mask = <0x0 0x0 0x0 0x7>; interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &gicv2 GIC_SPI 144 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &gicv2 GIC_SPI 145 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &gicv2 GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>; msi-controller; msi-parent = <&pcie0>; diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index d4f355015e3c..f69d2af3c1fa 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -242,6 +242,8 @@ gpio-controller; #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; }; pcie0: pcie@12000 { @@ -408,7 +410,7 @@ i2c0: i2c@18009000 { compatible = "brcm,iproc-i2c"; reg = <0x18009000 0x50>; - interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <1>; #size-cells = <0>; clock-frequency = <100000>; diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e68fb879e4f9..5e56288e343b 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -290,7 +290,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *folio); #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h index fc2608b18a0d..18f01190dcfd 100644 --- a/arch/arm/mach-socfpga/core.h +++ b/arch/arm/mach-socfpga/core.h @@ -33,7 +33,7 @@ extern void __iomem *sdr_ctl_base_addr; u32 socfpga_sdram_self_refresh(u32 sdr_base); extern unsigned int socfpga_sdram_self_refresh_sz; -extern char secondary_trampoline, secondary_trampoline_end; +extern char secondary_trampoline[], secondary_trampoline_end[]; extern unsigned long socfpga_cpu1start_addr; diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c index fbb80b883e5d..201191cf68f3 100644 --- a/arch/arm/mach-socfpga/platsmp.c +++ b/arch/arm/mach-socfpga/platsmp.c @@ -20,14 +20,14 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { /* This will put CPU #1 into reset. */ writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff)); @@ -45,12 +45,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_A10_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff)); diff --git a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi index 3e4727344b4a..a960c0bc2dba 100644 --- a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi +++ b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi @@ -296,8 +296,7 @@ pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>; phys = <&ufs_0_phy>; phy-names = "ufs-phy"; - samsung,sysreg = <&syscon_fsys2>; - samsung,ufs-shareability-reg-offset = <0x710>; + samsung,sysreg = <&syscon_fsys2 0x710>; status = "disabled"; }; }; diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 347b0cc68f07..1494cfa8639b 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -12,6 +12,17 @@ #define HAVE_FUNCTION_GRAPH_FP_TEST +/* + * HAVE_FUNCTION_GRAPH_RET_ADDR_PTR means that the architecture can provide a + * "return address pointer" which can be used to uniquely identify a return + * address which has been overwritten. + * + * On arm64 we use the address of the caller's frame record, which remains the + * same for the lifetime of the instrumented function, unlike the return + * address in the LR. + */ +#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS #define ARCH_SUPPORTS_FTRACE_OPS 1 #else diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index a39fcf318c77..01d47c5886dc 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -91,7 +91,7 @@ #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ -#define TCR_EL2_RES1 ((1 << 31) | (1 << 23)) +#define TCR_EL2_RES1 ((1U << 31) | (1 << 23)) #define TCR_EL2_TBI (1 << 20) #define TCR_EL2_PS_SHIFT 16 #define TCR_EL2_PS_MASK (7 << TCR_EL2_PS_SHIFT) @@ -276,7 +276,7 @@ #define CPTR_EL2_TFP_SHIFT 10 /* Hyp Coprocessor Trap Register */ -#define CPTR_EL2_TCPAC (1 << 31) +#define CPTR_EL2_TCPAC (1U << 31) #define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f4871e47b2d0..28acc65ccb17 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -41,6 +41,8 @@ void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); + static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2a5f7f38006f..0e75277be5d5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -717,7 +717,6 @@ void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} void kvm_arm_init_debug(void); void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 8433a2058eb1..237224484d0f 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -76,7 +76,7 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep) { - VM_BUG_ON(mm != &init_mm); + VM_BUG_ON(mm && mm != &init_mm); __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN); } diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index a4e046ef4568..6564a01cc085 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -47,9 +47,6 @@ struct stack_info { * @prev_type: The type of stack this frame record was on, or a synthetic * value of STACK_TYPE_UNKNOWN. This is used to detect a * transition from one stack to another. - * - * @graph: When FUNCTION_GRAPH_TRACER is selected, holds the index of a - * replacement lr value in the ftrace graph stack. */ struct stackframe { unsigned long fp; @@ -57,9 +54,6 @@ struct stackframe { DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); unsigned long prev_fp; enum stack_type prev_type; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - int graph; -#endif #ifdef CONFIG_KRETPROBES struct llist_node *kr_cur; #endif diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 6e2e0b7031ab..3a5ff5e20586 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -281,12 +281,22 @@ do { \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) +/* + * We must not call into the scheduler between uaccess_ttbr0_enable() and + * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, + * we must evaluate these outside of the critical section. + */ #define __raw_get_user(x, ptr, err) \ do { \ + __typeof__(*(ptr)) __user *__rgu_ptr = (ptr); \ + __typeof__(x) __rgu_val; \ __chk_user_ptr(ptr); \ + \ uaccess_ttbr0_enable(); \ - __raw_get_mem("ldtr", x, ptr, err); \ + __raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err); \ uaccess_ttbr0_disable(); \ + \ + (x) = __rgu_val; \ } while (0) #define __get_user_error(x, ptr, err) \ @@ -310,14 +320,22 @@ do { \ #define get_user __get_user +/* + * We must not call into the scheduler between __uaccess_enable_tco_async() and + * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * functions, we must evaluate these outside of the critical section. + */ #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ + __typeof__(dst) __gkn_dst = (dst); \ + __typeof__(src) __gkn_src = (src); \ int __gkn_err = 0; \ \ __uaccess_enable_tco_async(); \ - __raw_get_mem("ldr", *((type *)(dst)), \ - (__force type *)(src), __gkn_err); \ + __raw_get_mem("ldr", *((type *)(__gkn_dst)), \ + (__force type *)(__gkn_src), __gkn_err); \ __uaccess_disable_tco_async(); \ + \ if (unlikely(__gkn_err)) \ goto err_label; \ } while (0) @@ -351,11 +369,19 @@ do { \ } \ } while (0) +/* + * We must not call into the scheduler between uaccess_ttbr0_enable() and + * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, + * we must evaluate these outside of the critical section. + */ #define __raw_put_user(x, ptr, err) \ do { \ - __chk_user_ptr(ptr); \ + __typeof__(*(ptr)) __user *__rpu_ptr = (ptr); \ + __typeof__(*(ptr)) __rpu_val = (x); \ + __chk_user_ptr(__rpu_ptr); \ + \ uaccess_ttbr0_enable(); \ - __raw_put_mem("sttr", x, ptr, err); \ + __raw_put_mem("sttr", __rpu_val, __rpu_ptr, err); \ uaccess_ttbr0_disable(); \ } while (0) @@ -380,14 +406,22 @@ do { \ #define put_user __put_user +/* + * We must not call into the scheduler between __uaccess_enable_tco_async() and + * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * functions, we must evaluate these outside of the critical section. + */ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ + __typeof__(dst) __pkn_dst = (dst); \ + __typeof__(src) __pkn_src = (src); \ int __pkn_err = 0; \ \ __uaccess_enable_tco_async(); \ - __raw_put_mem("str", *((type *)(src)), \ - (__force type *)(dst), __pkn_err); \ + __raw_put_mem("str", *((type *)(__pkn_src)), \ + (__force type *)(__pkn_dst), __pkn_err); \ __uaccess_disable_tco_async(); \ + \ if (unlikely(__pkn_err)) \ goto err_label; \ } while(0) diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index b3e4f9a088b1..8cf970d219f5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -77,11 +77,17 @@ .endm SYM_CODE_START(ftrace_regs_caller) +#ifdef BTI_C + BTI_C +#endif ftrace_regs_entry 1 b ftrace_common SYM_CODE_END(ftrace_regs_caller) SYM_CODE_START(ftrace_caller) +#ifdef BTI_C + BTI_C +#endif ftrace_regs_entry 0 b ftrace_common SYM_CODE_END(ftrace_caller) diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index fc62dfe73f93..4506c4a90ac1 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -244,8 +244,6 @@ void arch_ftrace_update_code(int command) * on the way back to parent. For this purpose, this function is called * in _mcount() or ftrace_caller() to replace return address (*parent) on * the call stack to return_to_handler. - * - * Note that @frame_pointer is used only for sanity check later. */ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) @@ -263,8 +261,10 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, */ old = *parent; - if (!function_graph_enter(old, self_addr, frame_pointer, NULL)) + if (!function_graph_enter(old, self_addr, frame_pointer, + (void *)frame_pointer)) { *parent = return_hooker; + } } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 1038494135c8..6fb31c117ebe 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -147,7 +147,7 @@ int machine_kexec_post_load(struct kimage *kimage) if (rc) return rc; kimage->arch.ttbr1 = __pa(trans_pgd); - kimage->arch.zero_page = __pa(empty_zero_page); + kimage->arch.zero_page = __pa_symbol(empty_zero_page); reloc_size = __relocate_new_kernel_end - __relocate_new_kernel_start; memcpy(reloc_code, __relocate_new_kernel_start, reloc_size); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index c30624fff6ac..94f83cd44e50 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -38,9 +38,6 @@ void start_backtrace(struct stackframe *frame, unsigned long fp, { frame->fp = fp; frame->pc = pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame->graph = 0; -#endif #ifdef CONFIG_KRETPROBES frame->kr_cur = NULL; #endif @@ -116,20 +113,23 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->prev_fp = fp; frame->prev_type = info.type; + frame->pc = ptrauth_strip_insn_pac(frame->pc); + #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && - (ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) { - struct ftrace_ret_stack *ret_stack; + (frame->pc == (unsigned long)return_to_handler)) { + unsigned long orig_pc; /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame * to hook a function return. * So replace it to an original value. */ - ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++); - if (WARN_ON_ONCE(!ret_stack)) + orig_pc = ftrace_graph_ret_addr(tsk, NULL, frame->pc, + (void *)frame->fp); + if (WARN_ON_ONCE(frame->pc == orig_pc)) return -EINVAL; - frame->pc = ret_stack->ret; + frame->pc = orig_pc; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_KRETPROBES @@ -137,8 +137,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur); #endif - frame->pc = ptrauth_strip_insn_pac(frame->pc); - return 0; } NOKPROBE_SYMBOL(unwind_frame); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 8ffcbe29395e..f1f8fc069a97 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ menuconfig KVM select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE select SCHED_INFO + select INTERVAL_TREE help Support hosting virtualized guest machines. diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 989bb5dad2c8..04a53f71a6b6 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -5,14 +5,12 @@ ccflags-y += -I $(srctree)/$(src) -KVM=../../../virt/kvm +include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM) += hyp/ -kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ - $(KVM)/vfio.o $(KVM)/irqchip.o $(KVM)/binary_stats.o \ - arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ +kvm-y += arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ vgic-sys-reg-v3.o fpsimd.o pmu.o \ diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 3df67c127489..6e542e2eae32 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -467,7 +467,7 @@ out: } /* - * Schedule the background timer before calling kvm_vcpu_block, so that this + * Schedule the background timer before calling kvm_vcpu_halt, so that this * thread is removed from its waitqueue and made runnable when there's a timer * interrupt to handle. */ @@ -649,7 +649,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; - struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); if (unlikely(!timer->enabled)) return; @@ -672,7 +671,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); - if (rcuwait_active(wait)) + if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); /* @@ -750,7 +749,7 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) /* Make the updates of cntvoff for all vtimer contexts atomic */ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) { - int i; + unsigned long i; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; @@ -1189,8 +1188,8 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) { - int vtimer_irq, ptimer_irq; - int i, ret; + int vtimer_irq, ptimer_irq, ret; + unsigned long i; vtimer_irq = vcpu_vtimer(vcpu)->irq.irq; ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); @@ -1297,7 +1296,7 @@ void kvm_timer_init_vhe(void) static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu_vtimer(vcpu)->irq.irq = vtimer_irq; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e4727dc771bf..14106a7c75b5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -175,19 +175,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) */ void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - bitmap_free(kvm->arch.pmu_filter); kvm_vgic_destroy(kvm); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -368,27 +360,12 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - /* - * If we're about to block (most likely because we've just hit a - * WFI), we need to sync back the state of the GIC CPU interface - * so that we have the latest PMR and group enables. This ensures - * that kvm_arch_vcpu_runnable has up-to-date data to decide - * whether we have pending interrupts. - * - * For the same reason, we want to tell GICv4 that we need - * doorbells to be signalled, should an interrupt become pending. - */ - preempt_disable(); - kvm_vgic_vmcr_sync(vcpu); - vgic_v4_put(vcpu, true); - preempt_enable(); + } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - preempt_disable(); - vgic_v4_load(vcpu); - preempt_enable(); + } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -639,7 +616,7 @@ bool kvm_arch_intc_initialized(struct kvm *kvm) void kvm_arm_halt_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -649,12 +626,12 @@ void kvm_arm_halt_guest(struct kvm *kvm) void kvm_arm_resume_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); + __kvm_vcpu_wake_up(vcpu); } } @@ -679,6 +656,39 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) smp_rmb(); } +/** + * kvm_vcpu_wfi - emulate Wait-For-Interrupt behavior + * @vcpu: The VCPU pointer + * + * Suspend execution of a vCPU until a valid wake event is detected, i.e. until + * the vCPU is runnable. The vCPU may or may not be scheduled out, depending + * on when a wake event arrives, e.g. there may already be a pending wake event. + */ +void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) +{ + /* + * Sync back the state of the GIC CPU interface so that we have + * the latest PMR and group enables. This ensures that + * kvm_arch_vcpu_runnable has up-to-date data to decide whether + * we have pending interrupts, e.g. when determining if the + * vCPU should block. + * + * For the same reason, we want to tell GICv4 that we need + * doorbells to be signalled, should an interrupt become pending. + */ + preempt_disable(); + kvm_vgic_vmcr_sync(vcpu); + vgic_v4_put(vcpu, true); + preempt_enable(); + + kvm_vcpu_halt(vcpu); + kvm_clear_request(KVM_REQ_UNHALT, vcpu); + + preempt_disable(); + vgic_v4_load(vcpu); + preempt_enable(); +} + static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) { return vcpu->arch.target >= 0; @@ -2035,7 +2045,7 @@ static int finalize_hyp_mode(void) struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; mpidr &= MPIDR_HWID_BITMASK; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 275a27368a04..6d0baf71aa67 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -82,7 +82,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu) * * WFE: Yield the CPU and come back to this vcpu when the scheduler * decides to. - * WFI: Simply call kvm_vcpu_block(), which will halt execution of + * WFI: Simply call kvm_vcpu_halt(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. */ @@ -95,8 +95,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) } else { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false); vcpu->stat.wfi_exit_stat++; - kvm_vcpu_block(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); + kvm_vcpu_wfi(vcpu); } kvm_incr_pc(vcpu); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 7a0af1d39303..96c5f3fb7838 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -403,6 +403,8 @@ typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); + /* * Allow the hypervisor to handle the exit with an exit handler if it has one. * @@ -429,6 +431,18 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) */ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { + /* + * Save PSTATE early so that we can evaluate the vcpu mode + * early on. + */ + vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); + + /* + * Check whether we want to repaint the state one way or + * another. + */ + early_exit_filter(vcpu, exit_code); + if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index de7e14c862e6..7ecca8b07851 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -70,7 +70,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) { ctxt->regs.pc = read_sysreg_el2(SYS_ELR); - ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); + /* + * Guest PSTATE gets saved at guest fixup time in all + * cases. We still need to handle the nVHE host side here. + */ + if (!has_vhe() && ctxt->__hyp_running_vcpu) + ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index c0e3fed26d93..d13115a12434 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -233,7 +233,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) * Returns false if the guest ran in AArch32 when it shouldn't have, and * thus should exit to the host, or true if a the guest run loop can continue. */ -static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) { struct kvm *kvm = kern_hyp_va(vcpu->kvm); @@ -248,10 +248,7 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) vcpu->arch.target = -1; *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); *exit_code |= ARM_EXCEPTION_IL; - return false; } - - return true; } /* Switch to the guest for legacy non-VHE systems */ @@ -316,9 +313,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) /* Jump in the fire! */ exit_code = __guest_enter(vcpu); - if (unlikely(!handle_aarch32_guest(vcpu, &exit_code))) - break; - /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 5a2cb5d9bc4b..fbb26b93c347 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -112,6 +112,10 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) return hyp_exit_handlers; } +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) +{ +} + /* Switch to the guest for VHE systems running in EL2 */ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 326cdfec74a1..e65acf35cee3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -210,13 +210,13 @@ static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -595,14 +595,14 @@ void stage2_unmap_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); mmap_read_lock(current->mm); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -1463,7 +1463,6 @@ out: } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -1473,25 +1472,24 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * allocated dirty_bitmap[], dirty pages will be tracked while the * memory slot is write protected. */ - if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) { /* * If we're with initial-all-set, we don't need to write * protect any pages because they're all reported as dirty. * Huge pages and normal pages will be write protect gradually. */ if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) { - kvm_mmu_wp_memory_region(kvm, mem->slot); + kvm_mmu_wp_memory_region(kvm, new->id); } } } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - hva_t hva = mem->userspace_addr; - hva_t reg_end = hva + mem->memory_size; + hva_t hva, reg_end; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -1502,9 +1500,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ - if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) + if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) return -EFAULT; + hva = new->userspace_addr; + reg_end = hva + (new->npages << PAGE_SHIFT); + mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and any holes @@ -1536,7 +1537,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; break; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index a5e4bbf5e68f..0404357705a8 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -900,7 +900,7 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) */ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 74c47d420253..ad6c9ef32928 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -46,7 +46,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) * specification (ARM DEN 0022A). This means all suspend states * for KVM will preserve the register state. */ - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); return PSCI_RET_SUCCESS; @@ -121,8 +121,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) { - int i, matching_cpus = 0; - unsigned long mpidr; + int matching_cpus = 0; + unsigned long i, mpidr; unsigned long target_affinity; unsigned long target_affinity_mask; unsigned long lowest_affinity_level; @@ -164,7 +164,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; /* diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 426bd7fbc3fd..97de30a79770 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -170,7 +170,7 @@ static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) { struct kvm_vcpu *tmp; bool is32bit; - int i; + unsigned long i; is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 0a06d0648970..a7382bda9676 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -70,8 +70,9 @@ void kvm_vgic_early_init(struct kvm *kvm) */ int kvm_vgic_create(struct kvm *kvm, u32 type) { - int i, ret; struct kvm_vcpu *vcpu; + unsigned long i; + int ret; if (irqchip_in_kernel(kvm)) return -EEXIST; @@ -255,7 +256,8 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i, idx; + int ret = 0, i; + unsigned long idx; if (vgic_initialized(kvm)) return 0; @@ -308,7 +310,7 @@ int vgic_init(struct kvm *kvm) goto out; } - kvm_for_each_vcpu(i, vcpu, kvm) + kvm_for_each_vcpu(idx, vcpu, kvm) kvm_vgic_vcpu_enable(vcpu); ret = kvm_vgic_setup_default_irq_routing(kvm); @@ -370,7 +372,7 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static void __kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; vgic_debug_destroy(kvm); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 0d000d2fe8d2..c6d52a1fd9c8 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -325,7 +325,7 @@ void unlock_all_vcpus(struct kvm *kvm) bool lock_all_vcpus(struct kvm *kvm) { struct kvm_vcpu *tmp_vcpu; - int c; + unsigned long c; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index 5f9014ae595b..12e4c223e6b8 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -113,9 +113,8 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, int intid = val & 0xf; int targets = (val >> 16) & 0xff; int mode = (val >> 24) & 0x03; - int c; struct kvm_vcpu *vcpu; - unsigned long flags; + unsigned long flags, c; switch (mode) { case 0x0: /* as specified by targets */ diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index bf7ec4a78497..82906cb3f713 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -754,7 +754,8 @@ static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) static int vgic_register_all_redist_iodevs(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c, ret = 0; + unsigned long c; + int ret = 0; kvm_for_each_vcpu(c, vcpu, kvm) { ret = vgic_register_redist_iodev(vcpu); @@ -995,10 +996,10 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) struct kvm_vcpu *c_vcpu; u16 target_cpus; u64 mpidr; - int sgi, c; + int sgi; int vcpu_id = vcpu->vcpu_id; bool broadcast; - unsigned long flags; + unsigned long c, flags; sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT; broadcast = reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT); diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 04f62c4b07fb..5fedaee15e72 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -542,13 +542,13 @@ int vgic_v3_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int ret = 0; - int c; + unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { - kvm_debug("vcpu %d redistributor base not set\n", c); + kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 772dd15a22c7..ad06ba6c9b00 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -189,7 +189,7 @@ void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_arm_halt_guest(kvm); @@ -235,7 +235,8 @@ int vgic_v4_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i, nr_vcpus, ret; + int nr_vcpus, ret; + unsigned long i; if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 5dad4996cfb2..9b98876a8a93 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -990,7 +990,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) void vgic_kick_vcpus(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c; + unsigned long c; /* * We've injected an interrupt, time to find out who deserves diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 6fea1844fb95..707ae121f6d3 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -369,3 +369,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index 8ab46625ddd3..1ac55e7b47f0 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -250,7 +250,6 @@ static inline void __flush_page_to_ram(void *vaddr) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) __flush_page_to_ram(page_address(page)) -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page)) diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7976dff8f879..45bc32a41b90 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -448,3 +448,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 6b0e11362bd2..2204bde3ce4a 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index de60ad190057..0215dc1529e9 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -3097,7 +3097,7 @@ config STACKTRACE_SUPPORT config PGTABLE_LEVELS int default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48 - default 3 if 64BIT && !PAGE_SIZE_64KB + default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48) default 2 config MIPS_AUTO_PFN_OFFSET diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 2861a05c2e0c..f27cf31b4140 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -52,7 +52,7 @@ endif vmlinuzobjs-$(CONFIG_KERNEL_XZ) += $(obj)/ashldi3.o -vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o +vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o $(obj)/ashldi3.o targets := $(notdir $(vmlinuzobjs-y)) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index f207388541d5..b3dc9c589442 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -61,8 +61,6 @@ static inline void flush_dcache_page(struct page *page) SetPageDcacheDirty(page); } -void flush_dcache_folio(struct folio *folio); - #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 696f6b009377..72b90d45a46e 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -897,7 +897,6 @@ static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB int kvm_arch_flush_remote_tlb(struct kvm *kvm); diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index ac0e2cfc6d57..24a529c6c4be 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1734,8 +1734,6 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c) static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { - decode_configs(c); - /* All Loongson processors covered here define ExcCode 16 as GSExc. */ c->options |= MIPS_CPU_GSEXCEX; @@ -1796,6 +1794,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) panic("Unknown Loongson Processor ID!"); break; } + + decode_configs(c); } #else static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { } diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 376a6e2676e9..9f47a889b047 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -185,7 +185,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_puts(m, " tx39_cache"); if (cpu_has_octeon_cache) seq_puts(m, " octeon_cache"); - if (cpu_has_fpu) + if (raw_cpu_has_fpu) seq_puts(m, " fpu"); if (cpu_has_32fpr) seq_puts(m, " 32fpr"); diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index a77297480f56..91d197bee9c0 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select KVM_MMIO select MMU_NOTIFIER select SRCU + select INTERVAL_TREE help Support for hosting Guest kernels. diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index d3710959da55..21ff75bcdbc4 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -2,9 +2,10 @@ # Makefile for KVM support for MIPS # +include $(srctree)/virt/kvm/Makefile.kvm + ccflags-y += -Ivirt/kvm -Iarch/mips/kvm -kvm-y := $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o eventfd.o binary_stats.o) kvm-$(CONFIG_CPU_HAS_MSA) += msa.o kvm-y += mips.o emulate.o entry.o \ diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 22e745e49b0a..b494d8d39290 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -952,7 +952,7 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu) if (!vcpu->arch.pending_exceptions) { kvm_vz_lose_htimer(vcpu); vcpu->arch.wait = 1; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); /* * We we are runnable, then definitely go off to user space to diff --git a/arch/mips/kvm/loongson_ipi.c b/arch/mips/kvm/loongson_ipi.c index 3681fc8fba38..5d53f32d837c 100644 --- a/arch/mips/kvm/loongson_ipi.c +++ b/arch/mips/kvm/loongson_ipi.c @@ -120,7 +120,7 @@ static int loongson_vipi_write(struct loongson_kvm_ipi *ipi, s->status |= data; irq.cpu = id; irq.irq = 6; - kvm_vcpu_ioctl_interrupt(kvm->vcpus[id], &irq); + kvm_vcpu_ioctl_interrupt(kvm_get_vcpu(kvm, id), &irq); break; case CORE0_CLEAR_OFF: @@ -128,7 +128,7 @@ static int loongson_vipi_write(struct loongson_kvm_ipi *ipi, if (!s->status) { irq.cpu = id; irq.irq = -6; - kvm_vcpu_ioctl_interrupt(kvm->vcpus[id], &irq); + kvm_vcpu_ioctl_interrupt(kvm_get_vcpu(kvm, id), &irq); } break; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index aa20d074d388..e59cb6246f76 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -171,25 +171,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } -void kvm_mips_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_vcpu_destroy(vcpu); - } - - mutex_lock(&kvm->lock); - - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - - mutex_unlock(&kvm->lock); -} - static void kvm_mips_free_gpa_pt(struct kvm *kvm) { /* It should always be safe to remove after flushing the whole range */ @@ -199,7 +180,7 @@ static void kvm_mips_free_gpa_pt(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - kvm_mips_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); kvm_mips_free_gpa_pt(kvm); } @@ -233,25 +214,20 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { int needs_flush; - kvm_debug("%s: kvm: %p slot: %d, GPA: %llx, size: %llx, QVA: %llx\n", - __func__, kvm, mem->slot, mem->guest_phys_addr, - mem->memory_size, mem->userspace_addr); - /* * If dirty page logging is enabled, write protect all pages in the slot * ready for dirty logging. @@ -498,7 +474,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, if (irq->cpu == -1) dvcpu = vcpu; else - dvcpu = vcpu->kvm->vcpus[irq->cpu]; + dvcpu = kvm_get_vcpu(vcpu->kvm, irq->cpu); if (intr == 2 || intr == 3 || intr == 4 || intr == 6) { kvm_mips_callbacks->queue_io_int(dvcpu, irq); diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 3fc0bb7d6487..c2a222ebfa2a 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -27,7 +27,6 @@ void flush_cache_vunmap(unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, void *src, int len); void copy_from_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 1999561b22aa..d0b71dd71287 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -29,7 +29,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 8db4af4879d0..82d77f4b0d08 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -15,7 +15,12 @@ # Mike Shaver, Helge Deller and Martin K. Petersen # +ifdef CONFIG_PARISC_SELF_EXTRACT +boot := arch/parisc/boot +KBUILD_IMAGE := $(boot)/bzImage +else KBUILD_IMAGE := vmlinuz +endif NM = sh $(srctree)/arch/parisc/nm CHECKFLAGS += -D__hppa__=1 diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index d2daeac2b217..1b8fd80cbe7f 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -1,7 +1,9 @@ CONFIG_LOCALVERSION="-64bit" # CONFIG_LOCALVERSION_AUTO is not set +CONFIG_KERNEL_LZ4=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -35,6 +37,7 @@ CONFIG_MODVERSIONS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set +CONFIG_MEMORY_FAILURE=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -65,12 +68,15 @@ CONFIG_SCSI_ISCSI_ATTRS=y CONFIG_SCSI_SRP_ATTRS=y CONFIG_ISCSI_BOOT_SYSFS=y CONFIG_SCSI_MPT2SAS=y -CONFIG_SCSI_LASI700=m +CONFIG_SCSI_LASI700=y CONFIG_SCSI_SYM53C8XX_2=y CONFIG_SCSI_ZALON=y CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_DH=y CONFIG_ATA=y +CONFIG_SATA_SIL=y +CONFIG_SATA_SIS=y +CONFIG_SATA_VIA=y CONFIG_PATA_NS87415=y CONFIG_PATA_SIL680=y CONFIG_ATA_GENERIC=y @@ -79,6 +85,7 @@ CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_RAID=m CONFIG_DM_UEVENT=y +CONFIG_DM_AUDIT=y CONFIG_FUSION=y CONFIG_FUSION_SPI=y CONFIG_FUSION_SAS=y @@ -196,10 +203,15 @@ CONFIG_FB_MATROX_G=y CONFIG_FB_MATROX_I2C=y CONFIG_FB_MATROX_MAVEN=y CONFIG_FB_RADEON=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_CLUT224 is not set CONFIG_HIDRAW=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_UIO=y CONFIG_UIO_PDRV_GENIRQ=m CONFIG_UIO_AEC=m diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 39e7985086f9..6d13ae236fcb 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -147,6 +147,17 @@ extrd,u \r, 63-(\sa), 64-(\sa), \t .endm + /* Extract unsigned for 32- and 64-bit + * The extru instruction leaves the most significant 32 bits of the + * target register in an undefined state on PA 2.0 systems. */ + .macro extru_safe r, p, len, t +#ifdef CONFIG_64BIT + extrd,u \r, 32+(\p), \len, \t +#else + extru \r, \p, \len, \t +#endif + .endm + /* load 32-bit 'value' into 'reg' compensating for the ldil * sign-extension when running in wide mode. * WARNING!! neither 'value' nor 'reg' can be expressions diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index da0cd4b3a28f..859b8a34adcf 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -50,7 +50,6 @@ void invalidate_kernel_vmap_range(void *vaddr, int size); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) diff --git a/arch/parisc/install.sh b/arch/parisc/install.sh index 056d588befdd..70d3cffb0251 100644 --- a/arch/parisc/install.sh +++ b/arch/parisc/install.sh @@ -39,6 +39,7 @@ verify "$3" if [ -n "${INSTALLKERNEL}" ]; then if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi + if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi fi # Default install diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 88c188a965d8..6e9cdb269862 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -366,17 +366,9 @@ */ .macro L2_ptep pmd,pte,index,va,fault #if CONFIG_PGTABLE_LEVELS == 3 - extru \va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index + extru_safe \va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index #else -# if defined(CONFIG_64BIT) - extrd,u \va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index - #else - # if PAGE_SIZE > 4096 - extru \va,31-ASM_PGDIR_SHIFT,32-ASM_PGDIR_SHIFT,\index - # else - extru \va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index - # endif -# endif + extru_safe \va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index #endif dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ #if CONFIG_PGTABLE_LEVELS < 3 @@ -386,7 +378,7 @@ bb,>=,n \pmd,_PxD_PRESENT_BIT,\fault dep %r0,31,PxD_FLAG_SHIFT,\pmd /* clear flags */ SHLREG \pmd,PxD_VALUE_SHIFT,\pmd - extru \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index + extru_safe \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */ .endm diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 4fb3b6a993bf..d2497b339d13 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -566,7 +566,7 @@ lws_compare_and_swap: ldo R%lws_lock_start(%r20), %r28 /* Extract eight bits from r26 and hash lock (Bits 3-11) */ - extru %r26, 28, 8, %r20 + extru_safe %r26, 28, 8, %r20 /* Find lock to use, the hash is either one of 0 to 15, multiplied by 16 (keep it 16-byte aligned) @@ -751,7 +751,7 @@ cas2_lock_start: ldo R%lws_lock_start(%r20), %r28 /* Extract eight bits from r26 and hash lock (Bits 3-11) */ - extru %r26, 28, 8, %r20 + extru_safe %r26, 28, 8, %r20 /* Find lock to use, the hash is either one of 0 to 15, multiplied by 16 (keep it 16-byte aligned) diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 9fb1e794831b..061119a56fbe 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -249,30 +249,16 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs on - * different sockets, so mark them unstable and lower rating on - * multi-socket SMP systems. + * The cr16 interval timers are not syncronized across CPUs, even if + * they share the same socket. */ if (num_online_cpus() > 1 && !running_on_qemu) { - int cpu; - unsigned long cpu0_loc; - cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; - - for_each_online_cpu(cpu) { - if (cpu == 0) - continue; - if ((cpu0_loc != 0) && - (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) - continue; - - /* mark sched_clock unstable */ - clear_sched_clock_stable(); - - clocksource_cr16.name = "cr16_unstable"; - clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; - clocksource_cr16.rating = 0; - break; - } + /* mark sched_clock unstable */ + clear_sched_clock_stable(); + + clocksource_cr16.name = "cr16_unstable"; + clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; + clocksource_cr16.rating = 0; } /* register at clocksource framework */ diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 3d208afd15bc..2769eb991f58 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -57,8 +57,6 @@ SECTIONS { . = KERNEL_BINARY_TEXT_START; - _stext = .; /* start of kernel text, includes init code & data */ - __init_begin = .; HEAD_TEXT_SECTION MLONGCALL_DISCARD(INIT_TEXT_SECTION(8)) @@ -82,6 +80,7 @@ SECTIONS /* freed after init ends here */ _text = .; /* Text and read-only data */ + _stext = .; MLONGCALL_KEEP(INIT_TEXT_SECTION(8)) .text ALIGN(PAGE_SIZE) : { TEXT_TEXT diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 222823861a67..41b8a1e1144a 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -141,11 +141,6 @@ static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ -void kvmhv_save_host_pmu(void); -void kvmhv_load_host_pmu(void); -void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use); -void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu); - void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu); long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr); diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index fbbf3cec92e9..d68d71987d5c 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -79,6 +79,7 @@ #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 #define BOOK3S_INTERRUPT_DECREMENTER 0x900 #define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980 +#define BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER 0x1980 #define BOOK3S_INTERRUPT_DOORBELL 0xa00 #define BOOK3S_INTERRUPT_SYSCALL 0xc00 #define BOOK3S_INTERRUPT_TRACE 0xd00 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 3d31f2c59e43..91c9f937edcd 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -406,6 +406,12 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return vcpu->arch.fault_dar; } +/* Expiry time of vcpu DEC relative to host TB */ +static inline u64 kvmppc_dec_expires_host_tb(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.dec_expires - vcpu->arch.vcore->tb_offset; +} + static inline bool is_kvmppc_resume_guest(int r) { return (r == RESUME_GUEST || r == RESUME_GUEST_NV); diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fff391b9b97b..fe07558173ef 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -44,7 +44,6 @@ struct kvm_nested_guest { struct mutex tlb_lock; /* serialize page faults and tlbies */ struct kvm_nested_guest *next; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; short prev_cpu[NR_CPUS]; u8 radix; /* is this nested guest radix */ }; @@ -154,7 +153,9 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu) return radix; } -int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr); +unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr); + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb); #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e4d23193eba7..a770443cd6e0 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -287,7 +287,6 @@ struct kvm_arch { u32 online_vcores; atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; u8 radix; u8 fwnmi_enabled; u8 secure_guest; @@ -579,6 +578,10 @@ struct kvm_vcpu_arch { ulong cfar; ulong ppr; u32 pspb; + u8 load_ebb; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + u8 load_tm; +#endif ulong fscr; ulong shadow_fscr; ulong ebbhr; @@ -741,7 +744,7 @@ struct kvm_vcpu_arch { struct hrtimer dec_timer; u64 dec_jiffies; - u64 dec_expires; + u64 dec_expires; /* Relative to guest timebase. */ unsigned long pending_exceptions; u8 ceded; u8 prodded; @@ -749,6 +752,7 @@ struct kvm_vcpu_arch { u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; + struct rcuwait wait; struct rcuwait *waitp; struct kvmppc_vcore *vcore; int ret; @@ -864,6 +868,5 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_exit(void) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 671fbd1a765e..a14dbcd1b8ce 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -200,12 +200,11 @@ extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, @@ -274,12 +273,11 @@ struct kvmppc_ops { int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log); void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void (*commit_memory_region)(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range); @@ -552,8 +550,7 @@ extern void kvm_hv_vm_activated(void); extern void kvm_hv_vm_deactivated(void); extern bool kvm_hv_mode_active(void); -extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, - struct kvm_nested_guest *nested); +extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu); #else static inline void __init kvm_cma_reserve(void) @@ -760,6 +757,7 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu); void kvmppc_subcore_enter_guest(void); void kvmppc_subcore_exit_guest(void); long kvmppc_realmode_hmi_handler(void); +long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu); long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel); long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 9d1fbd8be1c7..1f43ef696033 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -112,6 +112,9 @@ static inline void clear_task_ebb(struct task_struct *t) #endif } +void kvmppc_save_user_regs(void); +void kvmppc_save_current_sprs(void); + extern int set_thread_tidr(struct task_struct *t); #endif /* _ASM_POWERPC_SWITCH_TO_H */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 8c2c3dd4ddba..924b2157882f 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -18,6 +18,8 @@ #include <asm/vdso/timebase.h> /* time.c */ +extern u64 decrementer_max; + extern unsigned long tb_ticks_per_jiffy; extern unsigned long tb_ticks_per_usec; extern unsigned long tb_ticks_per_sec; @@ -97,19 +99,16 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low, extern void secondary_cpu_time_init(void); extern void __init time_init(void); -#ifdef CONFIG_PPC64 -static inline unsigned long test_irq_work_pending(void) -{ - unsigned long x; +DECLARE_PER_CPU(u64, decrementers_next_tb); - asm volatile("lbz %0,%1(13)" - : "=r" (x) - : "i" (offsetof(struct paca_struct, irq_work_pending))); - return x; +static inline u64 timer_get_next_tb(void) +{ + return __this_cpu_read(decrementers_next_tb); } -#endif -DECLARE_PER_CPU(u64, decrementers_next_tb); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now); +#endif /* Convert timebase ticks to nanoseconds */ unsigned long long tb_to_ns(unsigned long long tb_ticks); diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c index 3cca88ee96d7..3dc61e203f37 100644 --- a/arch/powerpc/kernel/cpu_setup_power.c +++ b/arch/powerpc/kernel/cpu_setup_power.c @@ -109,7 +109,7 @@ static void init_PMU_HV_ISA207(void) static void init_PMU(void) { mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -123,7 +123,7 @@ static void init_PMU_ISA31(void) { mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } /* @@ -137,6 +137,7 @@ void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -150,6 +151,7 @@ void __restore_cpu_power7(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -164,6 +166,7 @@ void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -184,6 +187,7 @@ void __restore_cpu_power8(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -202,6 +206,7 @@ void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -223,6 +228,7 @@ void __restore_cpu_power9(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -242,6 +248,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -264,6 +271,7 @@ void __restore_cpu_power10(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index ba527fb52993..d2b35fb9181d 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -80,6 +80,7 @@ static void __restore_cpu_cpufeatures(void) mtspr(SPRN_LPCR, system_registers.lpcr); if (hv_mode) { mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_HFSCR, system_registers.hfscr); mtspr(SPRN_PCR, system_registers.pcr); } @@ -216,6 +217,7 @@ static int __init feat_enable_hv(struct dt_cpu_feature *f) } mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); lpcr = mfspr(SPRN_LPCR); lpcr &= ~LPCR_LPES0; /* HV external interrupts */ @@ -351,7 +353,7 @@ static void init_pmu_power8(void) } mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); mtspr(SPRN_MMCRS, 0); @@ -390,7 +392,7 @@ static void init_pmu_power9(void) mtspr(SPRN_MMCRC, 0); mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -426,7 +428,7 @@ static void init_pmu_power10(void) mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 6b1ec9e3541b..349c4a820231 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -202,11 +202,11 @@ vmap_stack_overflow: mfspr r1, SPRN_SPRG_THREAD lwz r1, TASK_CPU - THREAD(r1) slwi r1, r1, 3 - addis r1, r1, emergency_ctx@ha + addis r1, r1, emergency_ctx-PAGE_OFFSET@ha #else - lis r1, emergency_ctx@ha + lis r1, emergency_ctx-PAGE_OFFSET@ha #endif - lwz r1, emergency_ctx@l(r1) + lwz r1, emergency_ctx-PAGE_OFFSET@l(r1) addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE EXCEPTION_PROLOG_2 0 vmap_stack_overflow prepare_transfer_to_handler diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 406d7ee9e322..5d2333d2a283 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1156,6 +1156,40 @@ static inline void save_sprs(struct thread_struct *t) #endif } +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void kvmppc_save_user_regs(void) +{ + unsigned long usermsr; + + if (!current->thread.regs) + return; + + usermsr = current->thread.regs->msr; + + if (usermsr & MSR_FP) + save_fpu(current); + + if (usermsr & MSR_VEC) + save_altivec(current); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (usermsr & MSR_TM) { + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + current->thread.regs->msr &= ~MSR_TM; + } +#endif +} +EXPORT_SYMBOL_GPL(kvmppc_save_user_regs); + +void kvmppc_save_current_sprs(void) +{ + save_sprs(¤t->thread); +} +EXPORT_SYMBOL_GPL(kvmppc_save_current_sprs); +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ + static inline void restore_sprs(struct thread_struct *old_thread, struct thread_struct *new_thread) { diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 7bef917cc84e..15109af9d075 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -528,3 +528,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index cae8f03a44fe..f7cddb82938f 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -88,6 +88,7 @@ static struct clocksource clocksource_timebase = { #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF u64 decrementer_max = DECREMENTER_DEFAULT_MAX; +EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev); @@ -107,6 +108,7 @@ struct clock_event_device decrementer_clockevent = { EXPORT_SYMBOL(decrementer_clockevent); DEFINE_PER_CPU(u64, decrementers_next_tb); +EXPORT_SYMBOL_GPL(decrementers_next_tb); static DEFINE_PER_CPU(struct clock_event_device, decrementers); #define XSEC_PER_SEC (1024*1024) @@ -496,6 +498,16 @@ EXPORT_SYMBOL(profile_pc); * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */ #ifdef CONFIG_PPC64 +static inline unsigned long test_irq_work_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, irq_work_pending))); + return x; +} + static inline void set_irq_work_pending_flag(void) { asm volatile("stb %0,%1(13)" : : @@ -539,13 +551,44 @@ void arch_irq_work_raise(void) preempt_enable(); } +static void set_dec_or_work(u64 val) +{ + set_dec(val); + /* We may have raced with new irq work */ + if (unlikely(test_irq_work_pending())) + set_dec(1); +} + #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 #define clear_irq_work_pending() +static void set_dec_or_work(u64 val) +{ + set_dec(val); +} #endif /* CONFIG_IRQ_WORK */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now) +{ + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + + WARN_ON_ONCE(!arch_irqs_disabled()); + WARN_ON_ONCE(mfmsr() & MSR_EE); + + if (now >= *next_tb) { + local_paca->irq_happened |= PACA_IRQ_DEC; + } else { + now = *next_tb - now; + if (now <= decrementer_max) + set_dec_or_work(now); + } +} +EXPORT_SYMBOL_GPL(timer_rearm_host_dec); +#endif + /* * timer_interrupt - gets called when the decrementer overflows, * with interrupts disabled. @@ -606,10 +649,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) } else { now = *next_tb - now; if (now <= decrementer_max) - set_dec(now); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + set_dec_or_work(now); __this_cpu_inc(irq_stat.timer_irqs_others); } @@ -843,11 +883,7 @@ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { __this_cpu_write(decrementers_next_tb, get_tb() + evt); - set_dec(evt); - - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + set_dec_or_work(evt); return 0; } diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index ff581d70f20c..c8e156011db9 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -26,6 +26,7 @@ config KVM select KVM_VFIO select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS + select INTERVAL_TREE config KVM_BOOK3S_HANDLER bool @@ -130,6 +131,21 @@ config KVM_BOOK3S_HV_EXIT_TIMING If unsure, say N. +config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND + bool "Nested L0 host workaround for L1 KVM host PMU handling bug" if EXPERT + depends on KVM_BOOK3S_HV_POSSIBLE + default !EXPERT + help + Old nested HV capable Linux guests have a bug where they don't + reflect the PMU in-use status of their L2 guest to the L0 host + while the L2 PMU registers are live. This can result in loss + of L2 PMU register state, causing perf to not work correctly in + L2 guests. + + Selecting this option for the L0 host implements a workaround for + those buggy L1s which saves the L2 state, at the cost of performance + in all nested-capable guest entry/exit. + config KVM_BOOKE_HV bool diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 583c14ef596e..9bdfc8b50899 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -4,11 +4,8 @@ # ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm -KVM := ../../../virt/kvm -common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o -common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o -common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o +include $(srctree)/virt/kvm/Makefile.kvm common-objs-y += powerpc.o emulate_loadstore.o obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o @@ -125,9 +122,8 @@ kvm-book3s_32-objs := \ kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o -kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o -kvm-objs := $(kvm-objs-m) $(kvm-objs-y) +kvm-y += $(kvm-objs-m) $(kvm-objs-y) obj-$(CONFIG_KVM_E500V2) += kvm.o obj-$(CONFIG_KVM_E500MC) += kvm.o diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index b785f6772391..6d525285dbe8 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -847,21 +847,19 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem, - change); + return kvm->arch.kvm_ops->prepare_memory_region(kvm, old, new, change); } void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); + kvm->arch.kvm_ops->commit_memory_region(kvm, old, new, change); } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 3fbd570f9c1e..0215f32932a9 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -337,7 +337,7 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large) { - int i; + unsigned long i; struct kvm_vcpu *v; /* flush this VA on all cpus */ diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 983b8c18bc31..05e003eb5d90 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -374,11 +374,16 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) BEGIN_FTR_SECTION mtspr SPRN_DAWRX1,r10 END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) - mtspr SPRN_PID,r10 /* - * Switch to host MMU mode + * Switch to host MMU mode (don't have the real host PID but we aren't + * going back to userspace). */ + hwsync + isync + + mtspr SPRN_PID,r10 + ld r10, HSTATE_KVM_VCPU(r13) ld r10, VCPU_KVM(r10) lwz r10, KVM_HOST_LPID(r10) @@ -389,6 +394,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) ld r10, KVM_HOST_LPCR(r10) mtspr SPRN_LPCR,r10 + isync + /* * Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear * MSR_RI in r12 ([H]SRR1) so the handler won't try to return. diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index feee40cb2ba1..61290282fd9e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -530,7 +530,7 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va, bool large) { u64 mask = 0xFFFFFFFFFULL; - long i; + unsigned long i; struct kvm_vcpu *v; dprintk("KVM MMU: tlbie(0x%lx)\n", va); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c63e263312a4..213232914367 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -734,11 +734,11 @@ void kvmppc_rmap_reset(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { /* Mutual exclusion with kvm_unmap_hva_range etc. */ spin_lock(&kvm->mmu_lock); /* diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 16359525a40f..8cebe5542256 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -57,6 +57,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, preempt_disable(); + asm volatile("hwsync" ::: "memory"); + isync(); /* switch the lpid first to avoid running host with unallocated pid */ old_lpid = mfspr(SPRN_LPID); if (old_lpid != lpid) @@ -75,6 +77,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, ret = __copy_to_user_inatomic((void __user *)to, from, n); pagefault_enable(); + asm volatile("hwsync" ::: "memory"); + isync(); /* switch the pid first to avoid running host with unallocated pid */ if (quadrant == 1 && pid != old_pid) mtspr(SPRN_PID, old_pid); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 7b74fc0a986b..d1817cd9a691 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -80,6 +80,7 @@ #include <asm/plpar_wrappers.h> #include "book3s.h" +#include "book3s_hv.h" #define CREATE_TRACE_POINTS #include "trace_hv.h" @@ -127,11 +128,6 @@ static bool nested = true; module_param(nested, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(nested, "Enable nested virtualization (only on POWER9)"); -static inline bool nesting_enabled(struct kvm *kvm) -{ - return kvm->arch.nested_enable && kvm_is_radix(kvm); -} - static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); /* @@ -276,22 +272,26 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) * they should never fail.) */ -static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); - vc->preempt_tb = mftb(); + vc->preempt_tb = tb; spin_unlock_irqrestore(&vc->stoltb_lock, flags); } -static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); if (vc->preempt_tb != TB_NIL) { - vc->stolen_tb += mftb() - vc->preempt_tb; + vc->stolen_tb += tb - vc->preempt_tb; vc->preempt_tb = TB_NIL; } spin_unlock_irqrestore(&vc->stoltb_lock, flags); @@ -301,6 +301,12 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + now = mftb(); /* * We can test vc->runner without taking the vcore lock, @@ -309,12 +315,12 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) * ever sets it to NULL. */ if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_end_stolen(vc); + kvmppc_core_end_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST && vcpu->arch.busy_preempt != TB_NIL) { - vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt; + vcpu->arch.busy_stolen += now - vcpu->arch.busy_preempt; vcpu->arch.busy_preempt = TB_NIL; } spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); @@ -324,13 +330,19 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + now = mftb(); if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) - vcpu->arch.busy_preempt = mftb(); + vcpu->arch.busy_preempt = now; spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } @@ -675,6 +687,8 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) u64 p; unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); p = vc->stolen_tb; if (vc->vcore_state != VCORE_INACTIVE && @@ -684,35 +698,30 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) return p; } -static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, - struct kvmppc_vcore *vc) +static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + unsigned int pcpu, u64 now, + unsigned long stolen) { struct dtl_entry *dt; struct lppaca *vpa; - unsigned long stolen; - unsigned long core_stolen; - u64 now; - unsigned long flags; dt = vcpu->arch.dtl_ptr; vpa = vcpu->arch.vpa.pinned_addr; - now = mftb(); - core_stolen = vcore_stolen_time(vc, now); - stolen = core_stolen - vcpu->arch.stolen_logged; - vcpu->arch.stolen_logged = core_stolen; - spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); - stolen += vcpu->arch.busy_stolen; - vcpu->arch.busy_stolen = 0; - spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); + if (!dt || !vpa) return; - memset(dt, 0, sizeof(struct dtl_entry)); + dt->dispatch_reason = 7; - dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid); - dt->timebase = cpu_to_be64(now + vc->tb_offset); + dt->preempt_reason = 0; + dt->processor_id = cpu_to_be16(pcpu + vcpu->arch.ptid); dt->enqueue_to_dispatch_time = cpu_to_be32(stolen); + dt->ready_to_enqueue_time = 0; + dt->waiting_to_ready_time = 0; + dt->timebase = cpu_to_be64(now); + dt->fault_addr = 0; dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu)); dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr); + ++dt; if (dt == vcpu->arch.dtl.pinned_end) dt = vcpu->arch.dtl.pinned_addr; @@ -723,6 +732,27 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, vcpu->arch.dtl.dirty = true; } +static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + struct kvmppc_vcore *vc) +{ + unsigned long stolen; + unsigned long core_stolen; + u64 now; + unsigned long flags; + + now = mftb(); + + core_stolen = vcore_stolen_time(vc, now); + stolen = core_stolen - vcpu->arch.stolen_logged; + vcpu->arch.stolen_logged = core_stolen; + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); + stolen += vcpu->arch.busy_stolen; + vcpu->arch.busy_stolen = 0; + spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); + + __kvmppc_create_dtl_entry(vcpu, vc->pcpu, now + vc->tb_offset, stolen); +} + /* See if there is a doorbell interrupt pending for a vcpu */ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) { @@ -731,6 +761,8 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) if (vcpu->arch.doorbell_request) return true; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return false; /* * Ensure that the read of vcore->dpdes comes after the read * of vcpu->doorbell_request. This barrier matches the @@ -900,13 +932,14 @@ static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target) * mode handler is not called but no other threads are in the * source vcore. */ - - spin_lock(&vcore->lock); - if (target->arch.state == KVMPPC_VCPU_RUNNABLE && - vcore->vcore_state != VCORE_INACTIVE && - vcore->runner) - target = vcore->runner; - spin_unlock(&vcore->lock); + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + spin_lock(&vcore->lock); + if (target->arch.state == KVMPPC_VCPU_RUNNABLE && + vcore->vcore_state != VCORE_INACTIVE && + vcore->runner) + target = vcore->runner; + spin_unlock(&vcore->lock); + } return kvm_vcpu_yield_to(target); } @@ -1421,6 +1454,43 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +/* + * If the lppaca had pmcregs_in_use clear when we exited the guest, then + * HFSCR_PM is cleared for next entry. If the guest then tries to access + * the PMU SPRs, we get this facility unavailable interrupt. Putting HFSCR_PM + * back in the guest HFSCR will cause the next entry to load the PMU SPRs and + * allow the guest access to continue. + */ +static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_PM)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_PM; + + return RESUME_GUEST; +} + +static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_EBB; + + return RESUME_GUEST; +} + +static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_TM)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_TM; + + return RESUME_GUEST; +} + static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, struct task_struct *tsk) { @@ -1451,6 +1521,10 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { /* We're good on these - the host merely wanted to get our attention */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + WARN_ON_ONCE(1); /* Should never happen */ + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + fallthrough; case BOOK3S_INTERRUPT_HV_DECREMENTER: vcpu->stat.dec_exits++; r = RESUME_GUEST; @@ -1575,7 +1649,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, unsigned long vsid; long err; - if (vcpu->arch.fault_dsisr == HDSISR_CANARY) { + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) && + unlikely(vcpu->arch.fault_dsisr == HDSISR_CANARY)) { r = RESUME_GUEST; /* Just retry if it's the canary */ break; } @@ -1702,16 +1777,26 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * to emulate. * Otherwise, we just generate a program interrupt to the guest. */ - case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: + case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: { + u64 cause = vcpu->arch.hfscr >> 56; + r = EMULATE_FAIL; - if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) && - cpu_has_feature(CPU_FTR_ARCH_300)) - r = kvmppc_emulate_doorbell_instr(vcpu); + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (cause == FSCR_MSGP_LG) + r = kvmppc_emulate_doorbell_instr(vcpu); + if (cause == FSCR_PM_LG) + r = kvmppc_pmu_unavailable(vcpu); + if (cause == FSCR_EBB_LG) + r = kvmppc_ebb_unavailable(vcpu); + if (cause == FSCR_TM_LG) + r = kvmppc_tm_unavailable(vcpu); + } if (r == EMULATE_FAIL) { kvmppc_core_queue_program(vcpu, SRR1_PROGILL); r = RESUME_GUEST; } break; + } case BOOK3S_INTERRUPT_HV_RM_HARD: r = RESUME_PASSTHROUGH; @@ -1768,6 +1853,12 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + /* These need to go to the nested HV */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + vcpu->stat.dec_exits++; + r = RESUME_HOST; + break; /* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/ case BOOK3S_INTERRUPT_HMI: case BOOK3S_INTERRUPT_PERFMON: @@ -1993,7 +2084,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, */ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.vcore != vc) @@ -2096,8 +2187,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, * either vcore->dpdes or doorbell_request. * On POWER8, doorbell_request is 0. */ - *val = get_reg_val(id, vcpu->arch.vcore->dpdes | - vcpu->arch.doorbell_request); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + *val = get_reg_val(id, vcpu->arch.doorbell_request); + else + *val = get_reg_val(id, vcpu->arch.vcore->dpdes); break; case KVM_REG_PPC_VTB: *val = get_reg_val(id, vcpu->arch.vcore->vtb); @@ -2238,8 +2331,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); break; case KVM_REG_PPC_DEC_EXPIRY: - *val = get_reg_val(id, vcpu->arch.dec_expires + - vcpu->arch.vcore->tb_offset); + *val = get_reg_val(id, vcpu->arch.dec_expires); break; case KVM_REG_PPC_ONLINE: *val = get_reg_val(id, vcpu->arch.online); @@ -2335,7 +2427,10 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.pspb = set_reg_val(id, *val); break; case KVM_REG_PPC_DPDES: - vcpu->arch.vcore->dpdes = set_reg_val(id, *val); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.doorbell_request = set_reg_val(id, *val) & 1; + else + vcpu->arch.vcore->dpdes = set_reg_val(id, *val); break; case KVM_REG_PPC_VTB: vcpu->arch.vcore->vtb = set_reg_val(id, *val); @@ -2491,8 +2586,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DEC_EXPIRY: - vcpu->arch.dec_expires = set_reg_val(id, *val) - - vcpu->arch.vcore->tb_offset; + vcpu->arch.dec_expires = set_reg_val(id, *val); break; case KVM_REG_PPC_ONLINE: i = set_reg_val(id, *val); @@ -2715,6 +2809,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) #endif #endif vcpu->arch.mmcr[0] = MMCR0_FC; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[0] |= MMCR0_PMCCEXT; + vcpu->arch.mmcra = MMCRA_BHRB_DISABLE; + } + vcpu->arch.ctrl = CTRL_RUNLATCH; /* default to host PVR, since we can't spoof it */ kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR)); @@ -2745,6 +2844,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) vcpu->arch.hfscr_permitted = vcpu->arch.hfscr; + /* + * PM, EBB, TM are demand-faulted so start with it clear. + */ + vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM); + kvmppc_mmu_book3s_hv_init(vcpu); vcpu->arch.state = KVMPPC_VCPU_NOTREADY; @@ -2869,13 +2973,13 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) unsigned long dec_nsec, now; now = get_tb(); - if (now > vcpu->arch.dec_expires) { + if (now > kvmppc_dec_expires_host_tb(vcpu)) { /* decrementer has already gone negative */ kvmppc_core_queue_dec(vcpu); kvmppc_core_prepare_to_enter(vcpu); return; } - dec_nsec = tb_to_ns(vcpu->arch.dec_expires - now); + dec_nsec = tb_to_ns(kvmppc_dec_expires_host_tb(vcpu) - now); hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL); vcpu->arch.timer_running = 1; } @@ -2883,14 +2987,14 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) extern int __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, u64 tb) { u64 now; if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) return; spin_lock_irq(&vcpu->arch.tbacct_lock); - now = mftb(); + now = tb; vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) - vcpu->arch.stolen_logged; vcpu->arch.busy_preempt = now; @@ -2945,30 +3049,59 @@ static void kvmppc_release_hwthread(int cpu) tpaca->kvm_hstate.kvm_split_mode = NULL; } +static DEFINE_PER_CPU(struct kvm *, cpu_in_guest); + static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) { struct kvm_nested_guest *nested = vcpu->arch.nested; - cpumask_t *cpu_in_guest; + cpumask_t *need_tlb_flush; int i; + if (nested) + need_tlb_flush = &nested->need_tlb_flush; + else + need_tlb_flush = &kvm->arch.need_tlb_flush; + cpu = cpu_first_tlb_thread_sibling(cpu); - if (nested) { - cpumask_set_cpu(cpu, &nested->need_tlb_flush); - cpu_in_guest = &nested->cpu_in_guest; - } else { - cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush); - cpu_in_guest = &kvm->arch.cpu_in_guest; - } + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); + i += cpu_tlb_thread_sibling_step()) + cpumask_set_cpu(i, need_tlb_flush); + /* - * Make sure setting of bit in need_tlb_flush precedes - * testing of cpu_in_guest bits. The matching barrier on - * the other side is the first smp_mb() in kvmppc_run_core(). + * Make sure setting of bit in need_tlb_flush precedes testing of + * cpu_in_guest. The matching barrier on the other side is hwsync + * when switching to guest MMU mode, which happens between + * cpu_in_guest being set to the guest kvm, and need_tlb_flush bit + * being tested. */ smp_mb(); + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); - i += cpu_tlb_thread_sibling_step()) - if (cpumask_test_cpu(i, cpu_in_guest)) + i += cpu_tlb_thread_sibling_step()) { + struct kvm *running = *per_cpu_ptr(&cpu_in_guest, i); + + if (running == kvm) smp_call_function_single(i, do_nothing, NULL, 1); + } +} + +static void do_migrate_away_vcpu(void *arg) +{ + struct kvm_vcpu *vcpu = arg; + struct kvm *kvm = vcpu->kvm; + + /* + * If the guest has GTSE, it may execute tlbie, so do a eieio; tlbsync; + * ptesync sequence on the old CPU before migrating to a new one, in + * case we interrupted the guest between a tlbie ; eieio ; + * tlbsync; ptesync sequence. + * + * Otherwise, ptesync is sufficient for ordering tlbiel sequences. + */ + if (kvm->arch.lpcr & LPCR_GTSE) + asm volatile("eieio; tlbsync; ptesync"); + else + asm volatile("ptesync"); } static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) @@ -2994,14 +3127,17 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) * can move around between pcpus. To cope with this, when * a vcpu moves from one pcpu to another, we need to tell * any vcpus running on the same core as this vcpu previously - * ran to flush the TLB. The TLB is shared between threads, - * so we use a single bit in .need_tlb_flush for all 4 threads. + * ran to flush the TLB. */ if (prev_cpu != pcpu) { - if (prev_cpu >= 0 && - cpu_first_tlb_thread_sibling(prev_cpu) != - cpu_first_tlb_thread_sibling(pcpu)) - radix_flush_cpu(kvm, prev_cpu, vcpu); + if (prev_cpu >= 0) { + if (cpu_first_tlb_thread_sibling(prev_cpu) != + cpu_first_tlb_thread_sibling(pcpu)) + radix_flush_cpu(kvm, prev_cpu, vcpu); + + smp_call_function_single(prev_cpu, + do_migrate_away_vcpu, vcpu, 1); + } if (nested) nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu; else @@ -3013,7 +3149,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) { int cpu; struct paca_struct *tpaca; - struct kvm *kvm = vc->kvm; cpu = vc->pcpu; if (vcpu) { @@ -3024,7 +3159,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) cpu += vcpu->arch.ptid; vcpu->cpu = vc->pcpu; vcpu->arch.thread_cpu = cpu; - cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest); } tpaca = paca_ptrs[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; @@ -3125,6 +3259,8 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + vc->vcore_state = VCORE_PREEMPT; vc->pcpu = smp_processor_id(); if (vc->num_threads < threads_per_vcore(vc->kvm)) { @@ -3134,14 +3270,16 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) } /* Start accumulating stolen time */ - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp; - kvmppc_core_end_stolen(vc); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + + kvmppc_core_end_stolen(vc, mftb()); if (!list_empty(&vc->preempt_list)) { lp = &per_cpu(preempted_vcores, vc->pcpu); spin_lock(&lp->lock); @@ -3268,7 +3406,7 @@ static void prepare_threads(struct kvmppc_vcore *vc) vcpu->arch.ret = RESUME_GUEST; else continue; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -3287,7 +3425,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) list_del_init(&pvc->preempt_list); if (pvc->runner == NULL) { pvc->vcore_state = VCORE_INACTIVE; - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); } spin_unlock(&pvc->lock); continue; @@ -3296,7 +3434,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) spin_unlock(&pvc->lock); continue; } - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); pvc->vcore_state = VCORE_PIGGYBACK; if (cip->total_threads >= target_threads) break; @@ -3340,7 +3478,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) */ spin_unlock(&vc->lock); /* cancel pending dec exception if dec is positive */ - if (now < vcpu->arch.dec_expires && + if (now < kvmppc_dec_expires_host_tb(vcpu) && kvmppc_core_pending_dec(vcpu)) kvmppc_core_dequeue_dec(vcpu); @@ -3363,7 +3501,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) else ++still_running; } else { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -3372,7 +3510,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) kvmppc_vcore_preempt(vc); } else if (vc->runner) { vc->vcore_state = VCORE_PREEMPT; - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } else { vc->vcore_state = VCORE_INACTIVE; } @@ -3503,7 +3641,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { for_each_runnable_thread(i, vcpu, vc) { vcpu->arch.ret = -EBUSY; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } goto out; @@ -3748,7 +3886,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_release_hwthread(pcpu + i); if (sip && sip->napped[i]) kvmppc_ipi_thread(pcpu + i); - cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest); } spin_unlock(&vc->lock); @@ -3770,211 +3907,137 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) trace_kvmppc_run_core(vc, 1); } -static void load_spr_state(struct kvm_vcpu *vcpu) -{ - mtspr(SPRN_DSCR, vcpu->arch.dscr); - mtspr(SPRN_IAMR, vcpu->arch.iamr); - mtspr(SPRN_PSPB, vcpu->arch.pspb); - mtspr(SPRN_FSCR, vcpu->arch.fscr); - mtspr(SPRN_TAR, vcpu->arch.tar); - mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); - mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); - mtspr(SPRN_BESCR, vcpu->arch.bescr); - mtspr(SPRN_TIDR, vcpu->arch.tid); - mtspr(SPRN_AMR, vcpu->arch.amr); - mtspr(SPRN_UAMOR, vcpu->arch.uamor); - - /* - * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI] - * clear (or hstate set appropriately to catch those registers - * being clobbered if we take a MCE or SRESET), so those are done - * later. - */ - - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1); -} - -static void store_spr_state(struct kvm_vcpu *vcpu) -{ - vcpu->arch.ctrl = mfspr(SPRN_CTRLF); - - vcpu->arch.iamr = mfspr(SPRN_IAMR); - vcpu->arch.pspb = mfspr(SPRN_PSPB); - vcpu->arch.fscr = mfspr(SPRN_FSCR); - vcpu->arch.tar = mfspr(SPRN_TAR); - vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); - vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); - vcpu->arch.bescr = mfspr(SPRN_BESCR); - vcpu->arch.tid = mfspr(SPRN_TIDR); - vcpu->arch.amr = mfspr(SPRN_AMR); - vcpu->arch.uamor = mfspr(SPRN_UAMOR); - vcpu->arch.dscr = mfspr(SPRN_DSCR); -} - -/* - * Privileged (non-hypervisor) host registers to save. - */ -struct p9_host_os_sprs { - unsigned long dscr; - unsigned long tidr; - unsigned long iamr; - unsigned long amr; - unsigned long fscr; -}; - -static void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs) -{ - host_os_sprs->dscr = mfspr(SPRN_DSCR); - host_os_sprs->tidr = mfspr(SPRN_TIDR); - host_os_sprs->iamr = mfspr(SPRN_IAMR); - host_os_sprs->amr = mfspr(SPRN_AMR); - host_os_sprs->fscr = mfspr(SPRN_FSCR); -} - -/* vcpu guest regs must already be saved */ -static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, - struct p9_host_os_sprs *host_os_sprs) -{ - mtspr(SPRN_PSPB, 0); - mtspr(SPRN_UAMOR, 0); - - mtspr(SPRN_DSCR, host_os_sprs->dscr); - mtspr(SPRN_TIDR, host_os_sprs->tidr); - mtspr(SPRN_IAMR, host_os_sprs->iamr); - - if (host_os_sprs->amr != vcpu->arch.amr) - mtspr(SPRN_AMR, host_os_sprs->amr); - - if (host_os_sprs->fscr != vcpu->arch.fscr) - mtspr(SPRN_FSCR, host_os_sprs->fscr); - - /* Save guest CTRL register, set runlatch to 1 */ - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, 1); -} - static inline bool hcall_is_xics(unsigned long req) { return req == H_EOI || req == H_CPPR || req == H_IPI || req == H_IPOLL || req == H_XIRR || req == H_XIRR_X; } -/* - * Guest entry for POWER9 and later CPUs. - */ -static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, - unsigned long lpcr) +static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) +{ + struct lppaca *lp = vcpu->arch.vpa.pinned_addr; + if (lp) { + u32 yield_count = be32_to_cpu(lp->yield_count) + 1; + lp->yield_count = cpu_to_be32(yield_count); + vcpu->arch.vpa.dirty = 1; + } +} + +/* call our hypervisor to load up HV regs and go */ +static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) { struct kvmppc_vcore *vc = vcpu->arch.vcore; + unsigned long host_psscr; + unsigned long msr; + struct hv_guest_state hvregs; struct p9_host_os_sprs host_os_sprs; s64 dec; - u64 tb; - int trap, save_pmu; + int trap; - WARN_ON_ONCE(vcpu->arch.ceded); - - dec = mfspr(SPRN_DEC); - tb = mftb(); - if (dec < 0) - return BOOK3S_INTERRUPT_HV_DECREMENTER; - local_paca->kvm_hstate.dec_expires = dec + tb; - if (local_paca->kvm_hstate.dec_expires < time_limit) - time_limit = local_paca->kvm_hstate.dec_expires; + msr = mfmsr(); save_p9_host_os_sprs(&host_os_sprs); - kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */ + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_vcpu_entry_p9() below otherwise. + */ + host_psscr = mfspr(SPRN_PSSCR_PR); - kvmppc_subcore_enter_guest(); + kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) + return 0; - vc->entry_exit_map = 1; - vc->in_guest = 1; + if (unlikely(load_vcpu_state(vcpu, &host_os_sprs))) + msr = mfmsr(); /* TM restore can update msr */ - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - } - - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true); + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use; - } else { - get_lppaca()->pmcregs_in_use = 1; - } - barrier(); + kvmhv_save_hv_regs(vcpu, &hvregs); + hvregs.lpcr = lpcr; + vcpu->arch.regs.msr = vcpu->arch.shregs.msr; + hvregs.version = HV_GUEST_STATE_VERSION; + if (vcpu->arch.nested) { + hvregs.lpid = vcpu->arch.nested->shadow_lpid; + hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; + } else { + hvregs.lpid = vcpu->kvm->arch.lpid; + hvregs.vcpu_token = vcpu->vcpu_id; } -#endif - kvmhv_load_guest_pmu(vcpu); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - load_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - load_vr_state(&vcpu->arch.vr); -#endif - mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); - - load_spr_state(vcpu); + hvregs.hdec_expiry = time_limit; /* - * When setting DEC, we must always deal with irq_work_raise via NMI vs - * setting DEC. The problem occurs right as we switch into guest mode - * if a NMI hits and sets pending work and sets DEC, then that will - * apply to the guest and not bring us back to the host. + * When setting DEC, we must always deal with irq_work_raise + * via NMI vs setting DEC. The problem occurs right as we + * switch into guest mode if a NMI hits and sets pending work + * and sets DEC, then that will apply to the guest and not + * bring us back to the host. * - * irq_work_raise could check a flag (or possibly LPCR[HDICE] for - * example) and set HDEC to 1? That wouldn't solve the nested hv - * case which needs to abort the hcall or zero the time limit. + * irq_work_raise could check a flag (or possibly LPCR[HDICE] + * for example) and set HDEC to 1? That wouldn't solve the + * nested hv case which needs to abort the hcall or zero the + * time limit. * * XXX: Another day's problem. */ - mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); + mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb); + + mtspr(SPRN_DAR, vcpu->arch.shregs.dar); + mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); + switch_pmu_to_guest(vcpu, &host_os_sprs); + trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), + __pa(&vcpu->arch.regs)); + kvmhv_restore_hv_return_state(vcpu, &hvregs); + switch_pmu_to_host(vcpu, &host_os_sprs); + vcpu->arch.shregs.msr = vcpu->arch.regs.msr; + vcpu->arch.shregs.dar = mfspr(SPRN_DAR); + vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + + store_vcpu_state(vcpu); - if (kvmhv_on_pseries()) { - /* - * We need to save and restore the guest visible part of the - * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor - * doesn't do this for us. Note only required if pseries since - * this is done in kvmhv_vcpu_entry_p9() below otherwise. - */ - unsigned long host_psscr; - /* call our hypervisor to load up HV regs and go */ - struct hv_guest_state hvregs; + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset); - host_psscr = mfspr(SPRN_PSSCR_PR); - mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); - kvmhv_save_hv_regs(vcpu, &hvregs); - hvregs.lpcr = lpcr; - vcpu->arch.regs.msr = vcpu->arch.shregs.msr; - hvregs.version = HV_GUEST_STATE_VERSION; - if (vcpu->arch.nested) { - hvregs.lpid = vcpu->arch.nested->shadow_lpid; - hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; - } else { - hvregs.lpid = vcpu->kvm->arch.lpid; - hvregs.vcpu_token = vcpu->vcpu_id; - } - hvregs.hdec_expiry = time_limit; - mtspr(SPRN_DAR, vcpu->arch.shregs.dar); - mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); - trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), - __pa(&vcpu->arch.regs)); - kvmhv_restore_hv_return_state(vcpu, &hvregs); - vcpu->arch.shregs.msr = vcpu->arch.regs.msr; - vcpu->arch.shregs.dar = mfspr(SPRN_DAR); - vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); - vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + timer_rearm_host_dec(*tb); + + restore_p9_host_os_sprs(vcpu, &host_os_sprs); + if (vcpu->arch.psscr != host_psscr) mtspr(SPRN_PSSCR_PR, host_psscr); + return trap; +} + +/* + * Guest entry for POWER9 and later CPUs. + */ +static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, + unsigned long lpcr, u64 *tb) +{ + u64 next_timer; + int trap; + + next_timer = timer_get_next_tb(); + if (*tb >= next_timer) + return BOOK3S_INTERRUPT_HV_DECREMENTER; + if (next_timer < time_limit) + time_limit = next_timer; + else if (*tb >= time_limit) /* nested time limit */ + return BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER; + + vcpu->arch.ceded = 0; + + vcpu_vpa_increment_dispatch(vcpu); + + if (kvmhv_on_pseries()) { + trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb); + /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { @@ -3982,9 +4045,16 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } + } else { + struct kvm *kvm = vcpu->kvm; + kvmppc_xive_push_vcpu(vcpu); - trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr); + + __this_cpu_write(cpu_in_guest, kvm); + trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr, tb); + __this_cpu_write(cpu_in_guest, NULL); + if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && !(vcpu->arch.shregs.msr & MSR_PR)) { unsigned long req = kvmppc_get_gpr(vcpu, 3); @@ -4009,65 +4079,11 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, } kvmppc_xive_pull_vcpu(vcpu); - if (kvm_is_radix(vcpu->kvm)) + if (kvm_is_radix(kvm)) vcpu->arch.slb_max = 0; } - dec = mfspr(SPRN_DEC); - if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ - dec = (s32) dec; - tb = mftb(); - vcpu->arch.dec_expires = dec + tb; - vcpu->cpu = -1; - vcpu->arch.thread_cpu = -1; - - store_spr_state(vcpu); - - restore_p9_host_os_sprs(vcpu, &host_os_sprs); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - store_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - store_vr_state(&vcpu->arch.vr); -#endif - vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); - - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true); - - save_pmu = 1; - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - save_pmu = lp->pmcregs_in_use; - } - /* Must save pmu if this guest is capable of running nested guests */ - save_pmu |= nesting_enabled(vcpu->kvm); - - kvmhv_save_guest_pmu(vcpu, save_pmu); -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); - barrier(); - } -#endif - - vc->entry_exit_map = 0x101; - vc->in_guest = 0; - - mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb()); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); - mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); - - kvmhv_load_host_pmu(); - - kvmppc_subcore_exit_guest(); + vcpu_vpa_increment_dispatch(vcpu); return trap; } @@ -4132,6 +4148,13 @@ static bool kvmppc_vcpu_woken(struct kvm_vcpu *vcpu) return false; } +static bool kvmppc_vcpu_check_block(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + return true; + return false; +} + /* * Check to see if any of the runnable vcpus on the vcore have pending * exceptions or are no longer ceded @@ -4142,7 +4165,7 @@ static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc) int i; for_each_runnable_thread(i, vcpu, vc) { - if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + if (kvmppc_vcpu_check_block(vcpu)) return 1; } @@ -4159,6 +4182,8 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) int do_sleep = 1; u64 block_ns; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + /* Poll for pending exceptions and ceded state */ cur = start_poll = ktime_get(); if (vc->halt_poll_ns) { @@ -4355,7 +4380,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) for_each_runnable_thread(i, v, vc) { kvmppc_core_prepare_to_enter(v); if (signal_pending(v->arch.run_task)) { - kvmppc_remove_runnable(vc, v); + kvmppc_remove_runnable(vc, v, mftb()); v->stat.signal_exits++; v->run->exit_reason = KVM_EXIT_INTR; v->arch.ret = -EINTR; @@ -4396,7 +4421,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) kvmppc_vcore_end_preempt(vc); if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); vcpu->stat.signal_exits++; run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; @@ -4417,12 +4442,15 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) { + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); struct kvm_run *run = vcpu->run; int trap, r, pcpu; int srcu_idx; struct kvmppc_vcore *vc; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; + unsigned long flags; + u64 tb; trace_kvmppc_run_vcpu_enter(vcpu); @@ -4433,16 +4461,11 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, vc = vcpu->arch.vcore; vcpu->arch.ceded = 0; vcpu->arch.run_task = current; - vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb()); vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; - vcpu->arch.busy_preempt = TB_NIL; vcpu->arch.last_inst = KVM_INST_FETCH_FAILED; - vc->runnable_threads[0] = vcpu; - vc->n_runnable = 1; - vc->runner = vcpu; /* See if the MMU is ready to go */ - if (!kvm->arch.mmu_ready) { + if (unlikely(!kvm->arch.mmu_ready)) { r = kvmhv_setup_mmu(vcpu); if (r) { run->exit_reason = KVM_EXIT_FAIL_ENTRY; @@ -4457,29 +4480,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_update_vpas(vcpu); - init_vcore_to_run(vc); - vc->preempt_tb = TB_NIL; - preempt_disable(); pcpu = smp_processor_id(); - vc->pcpu = pcpu; if (kvm_is_radix(kvm)) kvmppc_prepare_radix_vcpu(vcpu, pcpu); - local_irq_disable(); - hard_irq_disable(); + /* flags save not required, but irq_pmu has no disable/enable API */ + powerpc_local_irq_pmu_save(flags); + if (signal_pending(current)) goto sigpend; - if (lazy_irq_pending() || need_resched() || !kvm->arch.mmu_ready) + if (need_resched() || !kvm->arch.mmu_ready) goto out; if (!nested) { kvmppc_core_prepare_to_enter(vcpu); - if (vcpu->arch.doorbell_request) { - vc->dpdes = 1; - smp_wmb(); - vcpu->arch.doorbell_request = 0; - } if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions)) lpcr |= LPCR_MER; @@ -4490,16 +4505,23 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, goto out; } - kvmppc_clear_host_core(pcpu); + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } - local_paca->kvm_hstate.napping = 0; - local_paca->kvm_hstate.kvm_split_mode = NULL; - kvmppc_start_thread(vcpu, vc); - kvmppc_create_dtl_entry(vcpu, vc); - trace_kvm_guest_enter(vcpu); + tb = mftb(); - vc->vcore_state = VCORE_RUNNING; - trace_kvmppc_run_core(vc, 0); + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); + + trace_kvm_guest_enter(vcpu); guest_enter_irqoff(); @@ -4510,7 +4532,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, /* Tell lockdep that we're about to enable interrupts */ trace_hardirqs_on(); - trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr); + trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr, &tb); vcpu->arch.trap = trap; trace_hardirqs_off(); @@ -4521,8 +4543,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, set_irq_happened(trap); - kvmppc_set_host_core(pcpu); - context_tracking_guest_exit(); if (!vtime_accounting_enabled_this_cpu()) { local_irq_enable(); @@ -4538,9 +4558,10 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, } vtime_account_guest_exit(); - local_irq_enable(); + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; - cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest); + powerpc_local_irq_pmu_restore(flags); preempt_enable(); @@ -4550,7 +4571,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, * by L2 and the L1 decrementer is provided in hdec_expires */ if (kvmppc_core_pending_dec(vcpu) && - ((get_tb() < vcpu->arch.dec_expires) || + ((tb < kvmppc_dec_expires_host_tb(vcpu)) || (trap == BOOK3S_INTERRUPT_SYSCALL && kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED))) kvmppc_core_dequeue_dec(vcpu); @@ -4565,28 +4586,31 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, } vcpu->arch.ret = r; - if (is_kvmppc_resume_guest(r) && vcpu->arch.ceded && - !kvmppc_vcpu_woken(vcpu)) { + if (is_kvmppc_resume_guest(r) && !kvmppc_vcpu_check_block(vcpu)) { kvmppc_set_timer(vcpu); - while (vcpu->arch.ceded && !kvmppc_vcpu_woken(vcpu)) { + + prepare_to_rcuwait(wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) { vcpu->stat.signal_exits++; run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; break; } - spin_lock(&vc->lock); - kvmppc_vcore_blocked(vc); - spin_unlock(&vc->lock); + + if (kvmppc_vcpu_check_block(vcpu)) + break; + + trace_kvmppc_vcore_blocked(vc, 0); + schedule(); + trace_kvmppc_vcore_blocked(vc, 1); } + finish_rcuwait(wait); } vcpu->arch.ceded = 0; - vc->vcore_state = VCORE_INACTIVE; - trace_kvmppc_run_core(vc, 1); - done: - kvmppc_remove_runnable(vc, vcpu); trace_kvmppc_run_vcpu_exit(vcpu); return vcpu->arch.ret; @@ -4596,7 +4620,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: - local_irq_enable(); + powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; } @@ -4606,23 +4630,25 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) struct kvm_run *run = vcpu->run; int r; int srcu_idx; - unsigned long ebb_regs[3] = {}; /* shut up GCC */ - unsigned long user_tar = 0; - unsigned int user_vrsave; struct kvm *kvm; + unsigned long msr; if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } + /* No need to go into the guest when all we'll do is come back out */ + if (signal_pending(current)) { + run->exit_reason = KVM_EXIT_INTR; + return -EINTR; + } + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* * Don't allow entry with a suspended transaction, because * the guest entry/exit code will lose it. - * If the guest has TM enabled, save away their TM-related SPRs - * (they will get restored by the TM unavailable interrupt). */ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && (current->thread.regs->msr & MSR_TM)) { if (MSR_TM_ACTIVE(current->thread.regs->msr)) { @@ -4630,12 +4656,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) run->fail_entry.hardware_entry_failure_reason = 0; return -EINVAL; } - /* Enable TM so we can read the TM SPRs */ - mtmsr(mfmsr() | MSR_TM); - current->thread.tm_tfhar = mfspr(SPRN_TFHAR); - current->thread.tm_tfiar = mfspr(SPRN_TFIAR); - current->thread.tm_texasr = mfspr(SPRN_TEXASR); - current->thread.regs->msr &= ~MSR_TM; } #endif @@ -4650,29 +4670,30 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) kvmppc_core_prepare_to_enter(vcpu); - /* No need to go into the guest when all we'll do is come back out */ - if (signal_pending(current)) { - run->exit_reason = KVM_EXIT_INTR; - return -EINTR; - } - kvm = vcpu->kvm; atomic_inc(&kvm->arch.vcpus_running); /* Order vcpus_running vs. mmu_ready, see kvmppc_alloc_reset_hpt */ smp_mb(); - flush_all_to_thread(current); + msr = 0; + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr |= MSR_FP; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr |= MSR_VEC; + if (cpu_has_feature(CPU_FTR_VSX)) + msr |= MSR_VSX; + if ((cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && + (vcpu->arch.hfscr & HFSCR_TM)) + msr |= MSR_TM; + msr = msr_check_and_set(msr); - /* Save userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - ebb_regs[0] = mfspr(SPRN_EBBHR); - ebb_regs[1] = mfspr(SPRN_EBBRR); - ebb_regs[2] = mfspr(SPRN_BESCR); - user_tar = mfspr(SPRN_TAR); - } - user_vrsave = mfspr(SPRN_VRSAVE); + kvmppc_save_user_regs(); + + kvmppc_save_current_sprs(); - vcpu->arch.waitp = &vcpu->arch.vcore->wait; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.waitp = &vcpu->arch.vcore->wait; vcpu->arch.pgdir = kvm->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; @@ -4711,15 +4732,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) } } while (is_kvmppc_resume_guest(r)); - /* Restore userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - mtspr(SPRN_EBBHR, ebb_regs[0]); - mtspr(SPRN_EBBRR, ebb_regs[1]); - mtspr(SPRN_BESCR, ebb_regs[2]); - mtspr(SPRN_TAR, user_tar); - } - mtspr(SPRN_VRSAVE, user_vrsave); - vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&kvm->arch.vcpus_running); @@ -4786,8 +4798,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int i, r; - unsigned long n; + int r; + unsigned long n, i; unsigned long *buf, *p; struct kvm_vcpu *vcpu; @@ -4854,37 +4866,38 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot) } static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, - struct kvm_memory_slot *slot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - unsigned long npages = mem->memory_size >> PAGE_SHIFT; - if (change == KVM_MR_CREATE) { - slot->arch.rmap = vzalloc(array_size(npages, - sizeof(*slot->arch.rmap))); - if (!slot->arch.rmap) + unsigned long size = array_size(new->npages, sizeof(*new->arch.rmap)); + + if ((size >> PAGE_SHIFT) > totalram_pages()) + return -ENOMEM; + + new->arch.rmap = vzalloc(size); + if (!new->arch.rmap) return -ENOMEM; + } else if (change != KVM_MR_DELETE) { + new->arch.rmap = old->arch.rmap; } return 0; } static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - unsigned long npages = mem->memory_size >> PAGE_SHIFT; - /* - * If we are making a new memslot, it might make + * If we are creating or modifying a memslot, it might make * some address that was previously cached as emulated * MMIO be no longer emulated MMIO, so invalidate * all the caches of emulated MMIO translations. */ - if (npages) + if (change != KVM_MR_DELETE) atomic64_inc(&kvm->arch.mmio_update); /* @@ -5072,6 +5085,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) */ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; + if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvmppc_rmap_reset(kvm); @@ -5081,8 +5096,13 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) kvm->arch.radix = 0; spin_unlock(&kvm->mmu_lock); kvmppc_free_radix(kvm); - kvmppc_update_lpcr(kvm, LPCR_VPM1, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_VPM1; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) + lpcr_mask |= LPCR_HAIL; + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -5092,6 +5112,7 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) */ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; int err; err = kvmppc_init_vm_radix(kvm); @@ -5103,8 +5124,17 @@ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) kvm->arch.radix = 1; spin_unlock(&kvm->mmu_lock); kvmppc_free_hpt(&kvm->arch.hpt); - kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_UPRT | LPCR_GTSE | LPCR_HR; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + lpcr_mask |= LPCR_HAIL; + if (cpu_has_feature(CPU_FTR_HVMODE) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; + } + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -5126,6 +5156,9 @@ void kvmppc_alloc_host_rm_ops(void) int cpu, core; int size; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + /* Not the first time here ? */ if (kvmppc_host_rm_ops_hv != NULL) return; @@ -5268,6 +5301,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.mmu_ready = 1; lpcr &= ~LPCR_VPM1; lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_31) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; ret = kvmppc_init_vm_radix(kvm); if (ret) { kvmppc_free_lpid(kvm->arch.lpid); @@ -5861,7 +5898,7 @@ static int kvmhv_svm_off(struct kvm *kvm) int mmu_was_ready; int srcu_idx; int ret = 0; - int i; + unsigned long i; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) return ret; @@ -5883,11 +5920,12 @@ static int kvmhv_svm_off(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_memory_slot *memslot; struct kvm_memslots *slots = __kvm_memslots(kvm, i); + int bkt; if (!slots) continue; - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { kvmppc_uvmem_drop_pages(memslot, kvm, true); uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); } @@ -6063,9 +6101,11 @@ static int kvmppc_book3s_init_hv(void) if (r) return r; - r = kvm_init_subcore_bitmap(); - if (r) - return r; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + r = kvm_init_subcore_bitmap(); + if (r) + return r; + } /* * We need a way of accessing the XICS interrupt controller, diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h new file mode 100644 index 000000000000..6b7f07d9026b --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv.h @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Privileged (non-hypervisor) host registers to save. + */ +struct p9_host_os_sprs { + unsigned long iamr; + unsigned long amr; + + unsigned int pmc1; + unsigned int pmc2; + unsigned int pmc3; + unsigned int pmc4; + unsigned int pmc5; + unsigned int pmc6; + unsigned long mmcr0; + unsigned long mmcr1; + unsigned long mmcr2; + unsigned long mmcr3; + unsigned long mmcra; + unsigned long siar; + unsigned long sier1; + unsigned long sier2; + unsigned long sier3; + unsigned long sdar; +}; + +static inline bool nesting_enabled(struct kvm *kvm) +{ + return kvm->arch.nested_enable && kvm_is_radix(kvm); +} + +bool load_vcpu_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void store_vcpu_state(struct kvm_vcpu *vcpu); +void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs); +void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index fcf4760a3a0e..7d6d91338c3f 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -649,6 +649,8 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu) int ext; unsigned long lpcr; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + /* Insert EXTERNAL bit into LPCR at the MER bit position */ ext = (vcpu->arch.pending_exceptions >> BOOK3S_IRQPRIO_EXTERNAL) & 1; lpcr = mfspr(SPRN_LPCR); @@ -682,57 +684,23 @@ static void flush_guest_tlb(struct kvm *kvm) unsigned long rb, set; rb = PPC_BIT(52); /* IS = 2 */ - if (kvm_is_radix(kvm)) { - /* R=1 PRS=1 RIC=2 */ + for (set = 0; set < kvm->arch.tlb_sets; ++set) { + /* R=0 PRS=0 RIC=0 */ asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (1), "i" (1), "i" (2), + : : "r" (rb), "i" (0), "i" (0), "i" (0), "r" (0) : "memory"); - for (set = 1; set < kvm->arch.tlb_sets; ++set) { - rb += PPC_BIT(51); /* increment set number */ - /* R=1 PRS=1 RIC=0 */ - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (1), "i" (1), "i" (0), - "r" (0) : "memory"); - } - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); - } else { - for (set = 0; set < kvm->arch.tlb_sets; ++set) { - /* R=0 PRS=0 RIC=0 */ - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (0), "i" (0), "i" (0), - "r" (0) : "memory"); - rb += PPC_BIT(51); /* increment set number */ - } - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + rb += PPC_BIT(51); /* increment set number */ } + asm volatile("ptesync": : :"memory"); } -void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, - struct kvm_nested_guest *nested) +void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu) { - cpumask_t *need_tlb_flush; - - /* - * On POWER9, individual threads can come in here, but the - * TLB is shared between the 4 threads in a core, hence - * invalidating on one thread invalidates for all. - * Thus we make all 4 threads use the same bit. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - pcpu = cpu_first_tlb_thread_sibling(pcpu); - - if (nested) - need_tlb_flush = &nested->need_tlb_flush; - else - need_tlb_flush = &kvm->arch.need_tlb_flush; - - if (cpumask_test_cpu(pcpu, need_tlb_flush)) { + if (cpumask_test_cpu(pcpu, &kvm->arch.need_tlb_flush)) { flush_guest_tlb(kvm); /* Clear the bit after the TLB flush */ - cpumask_clear_cpu(pcpu, need_tlb_flush); + cpumask_clear_cpu(pcpu, &kvm->arch.need_tlb_flush); } } EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush); diff --git a/arch/powerpc/kvm/book3s_hv_hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c index 9af660476314..1ec50c69678b 100644 --- a/arch/powerpc/kvm/book3s_hv_hmi.c +++ b/arch/powerpc/kvm/book3s_hv_hmi.c @@ -20,10 +20,15 @@ void wait_for_subcore_guest_exit(void) /* * NULL bitmap pointer indicates that KVM module hasn't - * been loaded yet and hence no guests are running. + * been loaded yet and hence no guests are running, or running + * on POWER9 or newer CPU. + * * If no KVM is in use, no need to co-ordinate among threads * as all of them will always be in host and no one is going * to modify TB other than the opal hmi handler. + * + * POWER9 and newer don't need this synchronisation. + * * Hence, just return from here. */ if (!local_paca->sibling_subcore_state) diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 4444f83cb133..59d89e4b154a 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -104,7 +104,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) mtlr r0 blr -_GLOBAL(kvmhv_save_host_pmu) +/* + * void kvmhv_save_host_pmu(void) + */ +kvmhv_save_host_pmu: BEGIN_FTR_SECTION /* Work around P8 PMAE bug */ li r3, -1 @@ -138,14 +141,6 @@ BEGIN_FTR_SECTION std r8, HSTATE_MMCR2(r13) std r9, HSTATE_SIER(r13) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - mfspr r5, SPRN_MMCR3 - mfspr r6, SPRN_SIER2 - mfspr r7, SPRN_SIER3 - std r5, HSTATE_MMCR3(r13) - std r6, HSTATE_SIER2(r13) - std r7, HSTATE_SIER3(r13) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mfspr r3, SPRN_PMC1 mfspr r5, SPRN_PMC2 mfspr r6, SPRN_PMC3 diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index ed8a2c9f5629..8f8daaeeb3b7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -358,6 +358,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* convert TB values/offsets to host (L0) values */ hdec_exp = l2_hv.hdec_expiry - vc->tb_offset; vc->tb_offset += l2_hv.tb_offset; + vcpu->arch.dec_expires += l2_hv.tb_offset; /* set L1 state to L2 state */ vcpu->arch.nested = l2; @@ -374,11 +375,6 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; do { - if (mftb() >= hdec_exp) { - vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; - r = RESUME_HOST; - break; - } r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr); } while (is_kvmppc_resume_guest(r)); @@ -399,6 +395,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) if (l2_regs.msr & MSR_TS_MASK) vcpu->arch.shregs.msr |= MSR_TS_S; vc->tb_offset = saved_l1_hv.tb_offset; + /* XXX: is this always the same delta as saved_l1_hv.tb_offset? */ + vcpu->arch.dec_expires -= l2_hv.tb_offset; restore_hv_regs(vcpu, &saved_l1_hv); vcpu->arch.purr += delta_purr; vcpu->arch.spurr += delta_spurr; @@ -582,7 +580,7 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) if (eaddr & (0xFFFUL << 52)) return H_PARAMETER; - buf = kzalloc(n, GFP_KERNEL); + buf = kzalloc(n, GFP_KERNEL | __GFP_NOWARN); if (!buf) return H_NO_MEM; @@ -749,7 +747,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) struct kvm_nested_guest *gp; struct kvm_nested_guest *freelist = NULL; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; spin_lock(&kvm->mmu_lock); for (i = 0; i <= kvm->arch.max_nested_lpid; i++) { @@ -770,7 +768,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) } srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmhv_free_memslot_nest_rmap(memslot); srcu_read_unlock(&kvm->srcu, srcu_idx); } diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c index 961b3d70483c..a28e5b3daabd 100644 --- a/arch/powerpc/kvm/book3s_hv_p9_entry.c +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -4,8 +4,439 @@ #include <asm/asm-prototypes.h> #include <asm/dbell.h> #include <asm/kvm_ppc.h> +#include <asm/pmc.h> #include <asm/ppc-opcode.h> +#include "book3s_hv.h" + +static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra) +{ + if (!(mmcr0 & MMCR0_FC)) + goto do_freeze; + if (mmcra & MMCRA_SAMPLE_ENABLE) + goto do_freeze; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + if (!(mmcr0 & MMCR0_PMCCEXT)) + goto do_freeze; + if (!(mmcra & MMCRA_BHRB_DISABLE)) + goto do_freeze; + } + return; + +do_freeze: + mmcr0 = MMCR0_FC; + mmcra = 0; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mmcr0 |= MMCR0_PMCCEXT; + mmcra = MMCRA_BHRB_DISABLE; + } + + mtspr(SPRN_MMCR0, mmcr0); + mtspr(SPRN_MMCRA, mmcra); + isync(); +} + +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int load_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + load_pmu = lp->pmcregs_in_use; + + /* Save host */ + if (ppc_get_pmu_inuse()) { + /* + * It might be better to put PMU handling (at least for the + * host) in the perf subsystem because it knows more about what + * is being used. + */ + + /* POWER9, POWER10 do not implement HPMC or SPMC */ + + host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0); + host_os_sprs->mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra); + + host_os_sprs->pmc1 = mfspr(SPRN_PMC1); + host_os_sprs->pmc2 = mfspr(SPRN_PMC2); + host_os_sprs->pmc3 = mfspr(SPRN_PMC3); + host_os_sprs->pmc4 = mfspr(SPRN_PMC4); + host_os_sprs->pmc5 = mfspr(SPRN_PMC5); + host_os_sprs->pmc6 = mfspr(SPRN_PMC6); + host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1); + host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2); + host_os_sprs->sdar = mfspr(SPRN_SDAR); + host_os_sprs->siar = mfspr(SPRN_SIAR); + host_os_sprs->sier1 = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3); + host_os_sprs->sier2 = mfspr(SPRN_SIER2); + host_os_sprs->sier3 = mfspr(SPRN_SIER3); + } + } + +#ifdef CONFIG_PPC_PSERIES + /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */ + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = load_pmu; + barrier(); + } +#endif + + /* + * Load guest. If the VPA said the PMCs are not in use but the guest + * tried to access them anyway, HFSCR[PM] will be set by the HFAC + * fault so we can make forward progress. + */ + if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) { + mtspr(SPRN_PMC1, vcpu->arch.pmc[0]); + mtspr(SPRN_PMC2, vcpu->arch.pmc[1]); + mtspr(SPRN_PMC3, vcpu->arch.pmc[2]); + mtspr(SPRN_PMC4, vcpu->arch.pmc[3]); + mtspr(SPRN_PMC5, vcpu->arch.pmc[4]); + mtspr(SPRN_PMC6, vcpu->arch.pmc[5]); + mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]); + mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]); + mtspr(SPRN_SDAR, vcpu->arch.sdar); + mtspr(SPRN_SIAR, vcpu->arch.siar); + mtspr(SPRN_SIER, vcpu->arch.sier[0]); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]); + mtspr(SPRN_SIER2, vcpu->arch.sier[1]); + mtspr(SPRN_SIER3, vcpu->arch.sier[2]); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, vcpu->arch.mmcra); + mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]); + /* No isync necessary because we're starting counters */ + + if (!vcpu->arch.nested && + (vcpu->arch.hfscr_permitted & HFSCR_PM)) + vcpu->arch.hfscr |= HFSCR_PM; + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_guest); + +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int save_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + save_pmu = lp->pmcregs_in_use; + if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) { + /* + * Save pmu if this guest is capable of running nested guests. + * This is option is for old L1s that do not set their + * lppaca->pmcregs_in_use properly when entering their L2. + */ + save_pmu |= nesting_enabled(vcpu->kvm); + } + + if (save_pmu) { + vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0); + vcpu->arch.mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra); + + vcpu->arch.pmc[0] = mfspr(SPRN_PMC1); + vcpu->arch.pmc[1] = mfspr(SPRN_PMC2); + vcpu->arch.pmc[2] = mfspr(SPRN_PMC3); + vcpu->arch.pmc[3] = mfspr(SPRN_PMC4); + vcpu->arch.pmc[4] = mfspr(SPRN_PMC5); + vcpu->arch.pmc[5] = mfspr(SPRN_PMC6); + vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1); + vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2); + vcpu->arch.sdar = mfspr(SPRN_SDAR); + vcpu->arch.siar = mfspr(SPRN_SIAR); + vcpu->arch.sier[0] = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3); + vcpu->arch.sier[1] = mfspr(SPRN_SIER2); + vcpu->arch.sier[2] = mfspr(SPRN_SIER3); + } + + } else if (vcpu->arch.hfscr & HFSCR_PM) { + /* + * The guest accessed PMC SPRs without specifying they should + * be preserved, or it cleared pmcregs_in_use after the last + * access. Just ensure they are frozen. + */ + freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA)); + + /* + * Demand-fault PMU register access in the guest. + * + * This is used to grab the guest's VPA pmcregs_in_use value + * and reflect it into the host's VPA in the case of a nested + * hypervisor. + * + * It also avoids having to zero-out SPRs after each guest + * exit to avoid side-channels when. + * + * This is cleared here when we exit the guest, so later HFSCR + * interrupt handling can add it back to run the guest with + * PM enabled next time. + */ + if (!vcpu->arch.nested) + vcpu->arch.hfscr &= ~HFSCR_PM; + } /* otherwise the PMU should still be frozen */ + +#ifdef CONFIG_PPC_PSERIES + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); + barrier(); + } +#endif + + if (ppc_get_pmu_inuse()) { + mtspr(SPRN_PMC1, host_os_sprs->pmc1); + mtspr(SPRN_PMC2, host_os_sprs->pmc2); + mtspr(SPRN_PMC3, host_os_sprs->pmc3); + mtspr(SPRN_PMC4, host_os_sprs->pmc4); + mtspr(SPRN_PMC5, host_os_sprs->pmc5); + mtspr(SPRN_PMC6, host_os_sprs->pmc6); + mtspr(SPRN_MMCR1, host_os_sprs->mmcr1); + mtspr(SPRN_MMCR2, host_os_sprs->mmcr2); + mtspr(SPRN_SDAR, host_os_sprs->sdar); + mtspr(SPRN_SIAR, host_os_sprs->siar); + mtspr(SPRN_SIER, host_os_sprs->sier1); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, host_os_sprs->mmcr3); + mtspr(SPRN_SIER2, host_os_sprs->sier2); + mtspr(SPRN_SIER3, host_os_sprs->sier3); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, host_os_sprs->mmcra); + mtspr(SPRN_MMCR0, host_os_sprs->mmcr0); + isync(); + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_host); + +static void load_spr_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + /* TAR is very fast */ + mtspr(SPRN_TAR, vcpu->arch.tar); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + current->thread.vrsave != vcpu->arch.vrsave) + mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); +#endif + + if (vcpu->arch.hfscr & HFSCR_EBB) { + if (current->thread.ebbhr != vcpu->arch.ebbhr) + mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); + if (current->thread.ebbrr != vcpu->arch.ebbrr) + mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); + if (current->thread.bescr != vcpu->arch.bescr) + mtspr(SPRN_BESCR, vcpu->arch.bescr); + } + + if (cpu_has_feature(CPU_FTR_P9_TIDR) && + current->thread.tidr != vcpu->arch.tid) + mtspr(SPRN_TIDR, vcpu->arch.tid); + if (host_os_sprs->iamr != vcpu->arch.iamr) + mtspr(SPRN_IAMR, vcpu->arch.iamr); + if (host_os_sprs->amr != vcpu->arch.amr) + mtspr(SPRN_AMR, vcpu->arch.amr); + if (vcpu->arch.uamor != 0) + mtspr(SPRN_UAMOR, vcpu->arch.uamor); + if (current->thread.fscr != vcpu->arch.fscr) + mtspr(SPRN_FSCR, vcpu->arch.fscr); + if (current->thread.dscr != vcpu->arch.dscr) + mtspr(SPRN_DSCR, vcpu->arch.dscr); + if (vcpu->arch.pspb != 0) + mtspr(SPRN_PSPB, vcpu->arch.pspb); + + /* + * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI] + * clear (or hstate set appropriately to catch those registers + * being clobbered if we take a MCE or SRESET), so those are done + * later. + */ + + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, 0); +} + +static void store_spr_state(struct kvm_vcpu *vcpu) +{ + vcpu->arch.tar = mfspr(SPRN_TAR); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); +#endif + + if (vcpu->arch.hfscr & HFSCR_EBB) { + vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); + vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); + vcpu->arch.bescr = mfspr(SPRN_BESCR); + } + + if (cpu_has_feature(CPU_FTR_P9_TIDR)) + vcpu->arch.tid = mfspr(SPRN_TIDR); + vcpu->arch.iamr = mfspr(SPRN_IAMR); + vcpu->arch.amr = mfspr(SPRN_AMR); + vcpu->arch.uamor = mfspr(SPRN_UAMOR); + vcpu->arch.fscr = mfspr(SPRN_FSCR); + vcpu->arch.dscr = mfspr(SPRN_DSCR); + vcpu->arch.pspb = mfspr(SPRN_PSPB); + + vcpu->arch.ctrl = mfspr(SPRN_CTRLF); +} + +/* Returns true if current MSR and/or guest MSR may have changed */ +bool load_vcpu_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + bool ret = false; + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + unsigned long guest_msr = vcpu->arch.shregs.msr; + if (MSR_TM_ACTIVE(guest_msr)) { + kvmppc_restore_tm_hv(vcpu, guest_msr, true); + ret = true; + } else if (vcpu->arch.hfscr & HFSCR_TM) { + mtspr(SPRN_TEXASR, vcpu->arch.texasr); + mtspr(SPRN_TFHAR, vcpu->arch.tfhar); + mtspr(SPRN_TFIAR, vcpu->arch.tfiar); + } + } +#endif + + load_spr_state(vcpu, host_os_sprs); + + load_fp_state(&vcpu->arch.fp); +#ifdef CONFIG_ALTIVEC + load_vr_state(&vcpu->arch.vr); +#endif + + return ret; +} +EXPORT_SYMBOL_GPL(load_vcpu_state); + +void store_vcpu_state(struct kvm_vcpu *vcpu) +{ + store_spr_state(vcpu); + + store_fp_state(&vcpu->arch.fp); +#ifdef CONFIG_ALTIVEC + store_vr_state(&vcpu->arch.vr); +#endif + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + unsigned long guest_msr = vcpu->arch.shregs.msr; + if (MSR_TM_ACTIVE(guest_msr)) { + kvmppc_save_tm_hv(vcpu, guest_msr, true); + } else if (vcpu->arch.hfscr & HFSCR_TM) { + vcpu->arch.texasr = mfspr(SPRN_TEXASR); + vcpu->arch.tfhar = mfspr(SPRN_TFHAR); + vcpu->arch.tfiar = mfspr(SPRN_TFIAR); + + if (!vcpu->arch.nested) { + vcpu->arch.load_tm++; /* see load_ebb comment */ + if (!vcpu->arch.load_tm) + vcpu->arch.hfscr &= ~HFSCR_TM; + } + } + } +#endif +} +EXPORT_SYMBOL_GPL(store_vcpu_state); + +void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs) +{ + host_os_sprs->iamr = mfspr(SPRN_IAMR); + host_os_sprs->amr = mfspr(SPRN_AMR); +} +EXPORT_SYMBOL_GPL(save_p9_host_os_sprs); + +/* vcpu guest regs must already be saved */ +void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + /* + * current->thread.xxx registers must all be restored to host + * values before a potential context switch, othrewise the context + * switch itself will overwrite current->thread.xxx with the values + * from the guest SPRs. + */ + + mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); + + if (cpu_has_feature(CPU_FTR_P9_TIDR) && + current->thread.tidr != vcpu->arch.tid) + mtspr(SPRN_TIDR, current->thread.tidr); + if (host_os_sprs->iamr != vcpu->arch.iamr) + mtspr(SPRN_IAMR, host_os_sprs->iamr); + if (vcpu->arch.uamor != 0) + mtspr(SPRN_UAMOR, 0); + if (host_os_sprs->amr != vcpu->arch.amr) + mtspr(SPRN_AMR, host_os_sprs->amr); + if (current->thread.fscr != vcpu->arch.fscr) + mtspr(SPRN_FSCR, current->thread.fscr); + if (current->thread.dscr != vcpu->arch.dscr) + mtspr(SPRN_DSCR, current->thread.dscr); + if (vcpu->arch.pspb != 0) + mtspr(SPRN_PSPB, 0); + + /* Save guest CTRL register, set runlatch to 1 */ + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, 1); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + vcpu->arch.vrsave != current->thread.vrsave) + mtspr(SPRN_VRSAVE, current->thread.vrsave); +#endif + if (vcpu->arch.hfscr & HFSCR_EBB) { + if (vcpu->arch.bescr != current->thread.bescr) + mtspr(SPRN_BESCR, current->thread.bescr); + if (vcpu->arch.ebbhr != current->thread.ebbhr) + mtspr(SPRN_EBBHR, current->thread.ebbhr); + if (vcpu->arch.ebbrr != current->thread.ebbrr) + mtspr(SPRN_EBBRR, current->thread.ebbrr); + + if (!vcpu->arch.nested) { + /* + * This is like load_fp in context switching, turn off + * the facility after it wraps the u8 to try avoiding + * saving and restoring the registers each partition + * switch. + */ + vcpu->arch.load_ebb++; + if (!vcpu->arch.load_ebb) + vcpu->arch.hfscr &= ~HFSCR_EBB; + } + } + + if (vcpu->arch.tar != current->thread.tar) + mtspr(SPRN_TAR, current->thread.tar); +} +EXPORT_SYMBOL_GPL(restore_p9_host_os_sprs); + #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) { @@ -56,10 +487,22 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator #define accumulate_time(vcpu, next) do {} while (0) #endif -static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev) +static inline u64 mfslbv(unsigned int idx) { - asm volatile("slbmfev %0,%1" : "=r" (*slbev) : "r" (idx)); - asm volatile("slbmfee %0,%1" : "=r" (*slbee) : "r" (idx)); + u64 slbev; + + asm volatile("slbmfev %0,%1" : "=r" (slbev) : "r" (idx)); + + return slbev; +} + +static inline u64 mfslbe(unsigned int idx) +{ + u64 slbee; + + asm volatile("slbmfee %0,%1" : "=r" (slbee) : "r" (idx)); + + return slbee; } static inline void mtslb(u64 slbee, u64 slbev) @@ -100,17 +543,19 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6 lpid = nested ? nested->shadow_lpid : kvm->arch.lpid; /* - * All the isync()s are overkill but trivially follow the ISA - * requirements. Some can likely be replaced with justification - * comment for why they are not needed. + * Prior memory accesses to host PID Q3 must be completed before we + * start switching, and stores must be drained to avoid not-my-LPAR + * logic (see switch_mmu_to_host). */ + asm volatile("hwsync" ::: "memory"); isync(); mtspr(SPRN_LPID, lpid); - isync(); mtspr(SPRN_LPCR, lpcr); - isync(); mtspr(SPRN_PID, vcpu->arch.pid); - isync(); + /* + * isync not required here because we are HRFID'ing to guest before + * any guest context access, which is context synchronising. + */ } static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr) @@ -120,25 +565,41 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpid = kvm->arch.lpid; + /* + * See switch_mmu_to_guest_radix. ptesync should not be required here + * even if the host is in HPT mode because speculative accesses would + * not cause RC updates (we are in real mode). + */ + asm volatile("hwsync" ::: "memory"); + isync(); mtspr(SPRN_LPID, lpid); mtspr(SPRN_LPCR, lpcr); mtspr(SPRN_PID, vcpu->arch.pid); for (i = 0; i < vcpu->arch.slb_max; i++) mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv); - - isync(); + /* + * isync not required here, see switch_mmu_to_guest_radix. + */ } static void switch_mmu_to_host(struct kvm *kvm, u32 pid) { + /* + * The guest has exited, so guest MMU context is no longer being + * non-speculatively accessed, but a hwsync is needed before the + * mtLPIDR / mtPIDR switch, in order to ensure all stores are drained, + * so the not-my-LPAR tlbie logic does not overlook them. + */ + asm volatile("hwsync" ::: "memory"); isync(); mtspr(SPRN_PID, pid); - isync(); mtspr(SPRN_LPID, kvm->arch.host_lpid); - isync(); mtspr(SPRN_LPCR, kvm->arch.host_lpcr); - isync(); + /* + * isync is not required after the switch, because mtmsrd with L=0 + * is performed after this switch, which is context synchronising. + */ if (!radix_enabled()) slb_restore_bolted_realmode(); @@ -171,8 +632,10 @@ static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu) */ for (i = 0; i < vcpu->arch.slb_nr; i++) { u64 slbee, slbev; - mfslb(i, &slbee, &slbev); + + slbee = mfslbe(i); if (slbee & SLB_ESID_V) { + slbev = mfslbv(i); vcpu->arch.slb[nr].orige = slbee | i; vcpu->arch.slb[nr].origv = slbev; nr++; @@ -183,15 +646,128 @@ static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu) } } -int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) +static void flush_guest_tlb(struct kvm *kvm) { + unsigned long rb, set; + + rb = PPC_BIT(52); /* IS = 2 */ + if (kvm_is_radix(kvm)) { + /* R=1 PRS=1 RIC=2 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (1), "i" (1), "i" (2), + "r" (0) : "memory"); + for (set = 1; set < kvm->arch.tlb_sets; ++set) { + rb += PPC_BIT(51); /* increment set number */ + /* R=1 PRS=1 RIC=0 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (1), "i" (1), "i" (0), + "r" (0) : "memory"); + } + asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); + } else { + for (set = 0; set < kvm->arch.tlb_sets; ++set) { + /* R=0 PRS=0 RIC=0 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (0), "i" (0), "i" (0), + "r" (0) : "memory"); + rb += PPC_BIT(51); /* increment set number */ + } + asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + } +} + +static void check_need_tlb_flush(struct kvm *kvm, int pcpu, + struct kvm_nested_guest *nested) +{ + cpumask_t *need_tlb_flush; + bool all_set = true; + int i; + + if (nested) + need_tlb_flush = &nested->need_tlb_flush; + else + need_tlb_flush = &kvm->arch.need_tlb_flush; + + if (likely(!cpumask_test_cpu(pcpu, need_tlb_flush))) + return; + + /* + * Individual threads can come in here, but the TLB is shared between + * the 4 threads in a core, hence invalidating on one thread + * invalidates for all, so only invalidate the first time (if all bits + * were set. The others must still execute a ptesync. + * + * If a race occurs and two threads do the TLB flush, that is not a + * problem, just sub-optimal. + */ + for (i = cpu_first_tlb_thread_sibling(pcpu); + i <= cpu_last_tlb_thread_sibling(pcpu); + i += cpu_tlb_thread_sibling_step()) { + if (!cpumask_test_cpu(i, need_tlb_flush)) { + all_set = false; + break; + } + } + if (all_set) + flush_guest_tlb(kvm); + else + asm volatile("ptesync" ::: "memory"); + + /* Clear the bit after the TLB flush */ + cpumask_clear_cpu(pcpu, need_tlb_flush); +} + +unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr) +{ + unsigned long msr_needed = 0; + + msr &= ~MSR_EE; + + /* MSR bits may have been cleared by context switch so must recheck */ + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr_needed |= MSR_FP; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr_needed |= MSR_VEC; + if (cpu_has_feature(CPU_FTR_VSX)) + msr_needed |= MSR_VSX; + if ((cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && + (vcpu->arch.hfscr & HFSCR_TM)) + msr_needed |= MSR_TM; + + /* + * This could be combined with MSR[RI] clearing, but that expands + * the unrecoverable window. It would be better to cover unrecoverable + * with KVM bad interrupt handling rather than use MSR[RI] at all. + * + * Much more difficult and less worthwhile to combine with IR/DR + * disable. + */ + if ((msr & msr_needed) != msr_needed) { + msr |= msr_needed; + __mtmsrd(msr, 0); + } else { + __hard_irq_disable(); + } + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + return msr; +} +EXPORT_SYMBOL_GPL(kvmppc_msr_hard_disable_set_facilities); + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) +{ + struct p9_host_os_sprs host_os_sprs; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; struct kvmppc_vcore *vc = vcpu->arch.vcore; - s64 hdec; - u64 tb, purr, spurr; + s64 hdec, dec; + u64 purr, spurr; u64 *exsave; - bool ri_set; int trap; unsigned long msr; unsigned long host_hfscr; @@ -199,11 +775,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc unsigned long host_dawr0; unsigned long host_dawrx0; unsigned long host_psscr; + unsigned long host_hpsscr; unsigned long host_pidr; unsigned long host_dawr1; unsigned long host_dawrx1; + unsigned long dpdes; - hdec = time_limit - mftb(); + hdec = time_limit - *tb; if (hdec < 0) return BOOK3S_INTERRUPT_HV_DECREMENTER; @@ -214,51 +792,84 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc vcpu->arch.ceded = 0; - if (vc->tb_offset) { - u64 new_tb = mftb() + vc->tb_offset; - mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); - vc->tb_offset_applied = vc->tb_offset; - } - - msr = mfmsr(); + /* Save MSR for restore, with EE clear. */ + msr = mfmsr() & ~MSR_EE; host_hfscr = mfspr(SPRN_HFSCR); host_ciabr = mfspr(SPRN_CIABR); - host_dawr0 = mfspr(SPRN_DAWR0); - host_dawrx0 = mfspr(SPRN_DAWRX0); - host_psscr = mfspr(SPRN_PSSCR); + host_psscr = mfspr(SPRN_PSSCR_PR); + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) + host_hpsscr = mfspr(SPRN_PSSCR); host_pidr = mfspr(SPRN_PID); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - host_dawr1 = mfspr(SPRN_DAWR1); - host_dawrx1 = mfspr(SPRN_DAWRX1); - } - if (vc->pcr) - mtspr(SPRN_PCR, vc->pcr | PCR_MASK); - mtspr(SPRN_DPDES, vc->dpdes); - mtspr(SPRN_VTB, vc->vtb); + if (dawr_enabled()) { + host_dawr0 = mfspr(SPRN_DAWR0); + host_dawrx0 = mfspr(SPRN_DAWRX0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + host_dawr1 = mfspr(SPRN_DAWR1); + host_dawrx1 = mfspr(SPRN_DAWRX1); + } + } local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR); local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR); + + save_p9_host_os_sprs(&host_os_sprs); + + msr = kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) { + trap = 0; + goto out; + } + + if (unlikely(load_vcpu_state(vcpu, &host_os_sprs))) + msr = mfmsr(); /* MSR may have been updated */ + + if (vc->tb_offset) { + u64 new_tb = *tb + vc->tb_offset; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + *tb = new_tb; + vc->tb_offset_applied = vc->tb_offset; + } + + mtspr(SPRN_VTB, vc->vtb); mtspr(SPRN_PURR, vcpu->arch.purr); mtspr(SPRN_SPURR, vcpu->arch.spurr); + if (vc->pcr) + mtspr(SPRN_PCR, vc->pcr | PCR_MASK); + if (vcpu->arch.doorbell_request) { + vcpu->arch.doorbell_request = 0; + mtspr(SPRN_DPDES, 1); + } + if (dawr_enabled()) { - mtspr(SPRN_DAWR0, vcpu->arch.dawr0); - mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); + if (vcpu->arch.dawr0 != host_dawr0) + mtspr(SPRN_DAWR0, vcpu->arch.dawr0); + if (vcpu->arch.dawrx0 != host_dawrx0) + mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, vcpu->arch.dawr1); - mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); + if (vcpu->arch.dawr1 != host_dawr1) + mtspr(SPRN_DAWR1, vcpu->arch.dawr1); + if (vcpu->arch.dawrx1 != host_dawrx1) + mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); } } - mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_IC, vcpu->arch.ic); + if (vcpu->arch.ciabr != host_ciabr) + mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + } else { + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); + } mtspr(SPRN_HFSCR, vcpu->arch.hfscr); @@ -276,18 +887,34 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc * HDSI which should correctly update the HDSISR the second time HDSI * entry. * - * Just do this on all p9 processors for now. + * The "radix prefetch bug" test can be used to test for this bug, as + * it also exists fo DD2.1 and below. */ - mtspr(SPRN_HDSISR, HDSISR_CANARY); + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + mtspr(SPRN_HDSISR, HDSISR_CANARY); mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0); mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1); mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2); mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3); - mtspr(SPRN_AMOR, ~0UL); + /* + * It might be preferable to load_vcpu_state here, in order to get the + * GPR/FP register loads executing in parallel with the previous mtSPR + * instructions, but for now that can't be done because the TM handling + * in load_vcpu_state can change some SPRs and vcpu state (nip, msr). + * But TM could be split out if this would be a significant benefit. + */ - local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_HV_P9; + /* + * MSR[RI] does not need to be cleared (and is not, for radix guests + * with no prefetch bug), because in_guest is set. If we take a SRESET + * or MCE with in_guest set but still in HV mode, then + * kvmppc_p9_bad_interrupt handles the interrupt, which effectively + * clears MSR[RI] and doesn't return. + */ + WRITE_ONCE(local_paca->kvm_hstate.in_guest, KVM_GUEST_MODE_HV_P9); + barrier(); /* Open in_guest critical section */ /* * Hash host, hash guest, or radix guest with prefetch bug, all have @@ -299,17 +926,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc save_clear_host_mmu(kvm); - if (kvm_is_radix(kvm)) { + if (kvm_is_radix(kvm)) switch_mmu_to_guest_radix(kvm, vcpu, lpcr); - if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) - __mtmsrd(0, 1); /* clear RI */ - - } else { + else switch_mmu_to_guest_hpt(kvm, vcpu, lpcr); - } /* TLBIEL uses LPID=LPIDR, so run this after setting guest LPID */ - kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested); + check_need_tlb_flush(kvm, vc->pcpu, nested); /* * P9 suppresses the HDEC exception when LPCR[HDICE] = 0, @@ -317,6 +940,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc */ mtspr(SPRN_HDEC, hdec); + mtspr(SPRN_DEC, vcpu->arch.dec_expires - *tb); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_return_to_guest: #endif @@ -327,7 +952,9 @@ tm_return_to_guest: accumulate_time(vcpu, &vcpu->arch.guest_time); + switch_pmu_to_guest(vcpu, &host_os_sprs); kvmppc_p9_enter_guest(vcpu); + switch_pmu_to_host(vcpu, &host_os_sprs); accumulate_time(vcpu, &vcpu->arch.rm_intr); @@ -340,36 +967,27 @@ tm_return_to_guest: /* 0x2 bit for HSRR is only used by PR and P7/8 HV paths, clear it */ trap = local_paca->kvm_hstate.scratch0 & ~0x2; - /* HSRR interrupts leave MSR[RI] unchanged, SRR interrupts clear it. */ - ri_set = false; - if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) { - if (trap != BOOK3S_INTERRUPT_SYSCALL && - (vcpu->arch.shregs.msr & MSR_RI)) - ri_set = true; + if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) exsave = local_paca->exgen; - } else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) { + else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) exsave = local_paca->exnmi; - } else { /* trap == 0x200 */ + else /* trap == 0x200 */ exsave = local_paca->exmc; - } vcpu->arch.regs.gpr[1] = local_paca->kvm_hstate.scratch1; vcpu->arch.regs.gpr[3] = local_paca->kvm_hstate.scratch2; /* - * Only set RI after reading machine check regs (DAR, DSISR, SRR0/1) - * and hstate scratch (which we need to move into exsave to make - * re-entrant vs SRESET/MCE) + * After reading machine check regs (DAR, DSISR, SRR0/1) and hstate + * scratch (which we need to move into exsave to make re-entrant vs + * SRESET/MCE), register state is protected from reentrancy. However + * timebase, MMU, among other state is still set to guest, so don't + * enable MSR[RI] here. It gets enabled at the end, after in_guest + * is cleared. + * + * It is possible an NMI could come in here, which is why it is + * important to save the above state early so it can be debugged. */ - if (ri_set) { - if (unlikely(!(mfmsr() & MSR_RI))) { - __mtmsrd(MSR_RI, 1); - WARN_ON_ONCE(1); - } - } else { - WARN_ON_ONCE(mfmsr() & MSR_RI); - __mtmsrd(MSR_RI, 1); - } vcpu->arch.regs.gpr[9] = exsave[EX_R9/sizeof(u64)]; vcpu->arch.regs.gpr[10] = exsave[EX_R10/sizeof(u64)]; @@ -388,7 +1006,7 @@ tm_return_to_guest: kvmppc_realmode_machine_check(vcpu); } else if (unlikely(trap == BOOK3S_INTERRUPT_HMI)) { - kvmppc_realmode_hmi_handler(); + kvmppc_p9_realmode_hmi_handler(vcpu); } else if (trap == BOOK3S_INTERRUPT_H_EMUL_ASSIST) { vcpu->arch.emul_inst = mfspr(SPRN_HEIR); @@ -427,13 +1045,6 @@ tm_return_to_guest: */ mtspr(SPRN_HSRR0, vcpu->arch.regs.nip); mtspr(SPRN_HSRR1, vcpu->arch.shregs.msr); - - /* - * tm_return_to_guest re-loads SRR0/1, DAR, - * DSISR after RI is cleared, in case they had - * been clobbered by a MCE. - */ - __mtmsrd(0, 1); /* clear RI */ goto tm_return_to_guest; } } @@ -445,81 +1056,109 @@ tm_return_to_guest: /* Advance host PURR/SPURR by the amount used by guest */ purr = mfspr(SPRN_PURR); spurr = mfspr(SPRN_SPURR); - mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr + - purr - vcpu->arch.purr); - mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr + - spurr - vcpu->arch.spurr); + local_paca->kvm_hstate.host_purr += purr - vcpu->arch.purr; + local_paca->kvm_hstate.host_spurr += spurr - vcpu->arch.spurr; vcpu->arch.purr = purr; vcpu->arch.spurr = spurr; vcpu->arch.ic = mfspr(SPRN_IC); vcpu->arch.pid = mfspr(SPRN_PID); - vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS; + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0); vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1); vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); - /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ - mtspr(SPRN_PSSCR, host_psscr | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); - mtspr(SPRN_HFSCR, host_hfscr); - mtspr(SPRN_CIABR, host_ciabr); - mtspr(SPRN_DAWR0, host_dawr0); - mtspr(SPRN_DAWRX0, host_dawrx0); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, host_dawr1); - mtspr(SPRN_DAWRX1, host_dawrx1); - } - - if (kvm_is_radix(kvm)) { - /* - * Since this is radix, do a eieio; tlbsync; ptesync sequence - * in case we interrupted the guest between a tlbie and a - * ptesync. - */ - asm volatile("eieio; tlbsync; ptesync"); - } + dpdes = mfspr(SPRN_DPDES); + if (dpdes) + vcpu->arch.doorbell_request = 1; - /* - * cp_abort is required if the processor supports local copy-paste - * to clear the copy buffer that was under control of the guest. - */ - if (cpu_has_feature(CPU_FTR_ARCH_31)) - asm volatile(PPC_CP_ABORT); - - vc->dpdes = mfspr(SPRN_DPDES); vc->vtb = mfspr(SPRN_VTB); - mtspr(SPRN_DPDES, 0); - if (vc->pcr) - mtspr(SPRN_PCR, PCR_MASK); + + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + *tb; if (vc->tb_offset_applied) { - u64 new_tb = mftb() - vc->tb_offset_applied; + u64 new_tb = *tb - vc->tb_offset_applied; mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + *tb = new_tb; vc->tb_offset_applied = 0; } - mtspr(SPRN_HDEC, 0x7fffffff); - save_clear_guest_mmu(kvm, vcpu); switch_mmu_to_host(kvm, host_pidr); - local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE; /* - * If we are in real mode, only switch MMU on after the MMU is - * switched to host, to avoid the P9_RADIX_PREFETCH_BUG. + * Enable MSR here in order to have facilities enabled to save + * guest registers. This enables MMU (if we were in realmode), so + * only switch MMU on after the MMU is switched to host, to avoid + * the P9_RADIX_PREFETCH_BUG or hash guest context. */ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && - vcpu->arch.shregs.msr & MSR_TS_MASK) + vcpu->arch.shregs.msr & MSR_TS_MASK) msr |= MSR_TS_S; - __mtmsrd(msr, 0); + store_vcpu_state(vcpu); + + mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr); + mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr); + + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ + mtspr(SPRN_PSSCR, host_hpsscr | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + } + + mtspr(SPRN_HFSCR, host_hfscr); + if (vcpu->arch.ciabr != host_ciabr) + mtspr(SPRN_CIABR, host_ciabr); + + if (dawr_enabled()) { + if (vcpu->arch.dawr0 != host_dawr0) + mtspr(SPRN_DAWR0, host_dawr0); + if (vcpu->arch.dawrx0 != host_dawrx0) + mtspr(SPRN_DAWRX0, host_dawrx0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + if (vcpu->arch.dawr1 != host_dawr1) + mtspr(SPRN_DAWR1, host_dawr1); + if (vcpu->arch.dawrx1 != host_dawrx1) + mtspr(SPRN_DAWRX1, host_dawrx1); + } + } + + if (dpdes) + mtspr(SPRN_DPDES, 0); + if (vc->pcr) + mtspr(SPRN_PCR, PCR_MASK); + + /* HDEC must be at least as large as DEC, so decrementer_max fits */ + mtspr(SPRN_HDEC, decrementer_max); + + timer_rearm_host_dec(*tb); + + restore_p9_host_os_sprs(vcpu, &host_os_sprs); + + barrier(); /* Close in_guest critical section */ + WRITE_ONCE(local_paca->kvm_hstate.in_guest, KVM_GUEST_MODE_NONE); + /* Interrupts are recoverable at this point */ + + /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + asm volatile(PPC_CP_ABORT); + +out: end_timing(vcpu); return trap; diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index d4bca93b79f6..ccfd96965630 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -136,6 +136,60 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu) vcpu->arch.mce_evt = mce_evt; } + +long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + long ret = 0; + + /* + * Unapply and clear the offset first. That way, if the TB was not + * resynced then it will remain in host-offset, and if it was resynced + * then it is brought into host-offset. Then the tb offset is + * re-applied before continuing with the KVM exit. + * + * This way, we don't need to actually know whether not OPAL resynced + * the timebase or do any of the complicated dance that the P7/8 + * path requires. + */ + if (vc->tb_offset_applied) { + u64 new_tb = mftb() - vc->tb_offset_applied; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + vc->tb_offset_applied = 0; + } + + local_paca->hmi_irqs++; + + if (hmi_handle_debugtrig(NULL) >= 0) { + ret = 1; + goto out; + } + + if (ppc_md.hmi_exception_early) + ppc_md.hmi_exception_early(NULL); + +out: + if (vc->tb_offset) { + u64 new_tb = mftb() + vc->tb_offset; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + vc->tb_offset_applied = vc->tb_offset; + } + + return ret; +} + +/* + * The following subcore HMI handling is all only for pre-POWER9 CPUs. + */ + /* Check if dynamic split is in force and return subcore size accordingly. */ static inline int kvmppc_cur_subcore_size(void) { diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 2c1f3c6e72d1..2257fb18cb72 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -55,12 +55,6 @@ static int global_invalidates(struct kvm *kvm) smp_wmb(); cpumask_setall(&kvm->arch.need_tlb_flush); cpu = local_paca->kvm_hstate.kvm_vcore->pcpu; - /* - * On POWER9, threads are independent but the TLB is shared, - * so use the bit for the first thread to represent the core. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - cpu = cpu_first_tlb_thread_sibling(cpu); cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 32a4b4d412b9..3f1aeff72438 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -778,17 +778,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Restore AMR and UAMOR, set AMOR to all 1s */ ld r5,VCPU_AMR(r4) ld r6,VCPU_UAMOR(r4) - li r7,-1 mtspr SPRN_AMR,r5 mtspr SPRN_UAMOR,r6 - mtspr SPRN_AMOR,r7 - /* Restore state of CTRL run bit; assume 1 on entry */ + /* Restore state of CTRL run bit; the host currently has it set to 1 */ lwz r5,VCPU_CTRL(r4) andi. r5,r5,1 bne 4f - mfspr r6,SPRN_CTRLF - clrrdi r6,r6,1 + li r6,0 mtspr SPRN_CTRLT,r6 4: /* Secondary threads wait for primary to have done partition switch */ @@ -817,10 +814,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) * Set the decrementer to the guest decrementer. */ ld r8,VCPU_DEC_EXPIRES(r4) - /* r8 is a host timebase value here, convert to guest TB */ - ld r5,HSTATE_KVM_VCORE(r13) - ld r6,VCORE_TB_OFFSET_APPL(r5) - add r8,r8,r6 mftb r7 subf r3,r7,r8 mtspr SPRN_DEC,r3 @@ -1195,9 +1188,6 @@ guest_bypass: mftb r6 extsw r5,r5 16: add r5,r5,r6 - /* r5 is a guest timebase value here, convert to host TB */ - ld r4,VCORE_TB_OFFSET_APPL(r3) - subf r5,r4,r5 std r5,VCPU_DEC_EXPIRES(r9) /* Increment exit count, poke other threads to exit */ @@ -1211,12 +1201,12 @@ guest_bypass: stw r0, VCPU_CPU(r9) stw r0, VCPU_THREAD_CPU(r9) - /* Save guest CTRL register, set runlatch to 1 */ + /* Save guest CTRL register, set runlatch to 1 if it was clear */ mfspr r6,SPRN_CTRLF stw r6,VCPU_CTRL(r9) andi. r0,r6,1 bne 4f - ori r6,r6,1 + li r6,1 mtspr SPRN_CTRLT,r6 4: /* @@ -2163,9 +2153,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* save expiry time of guest decrementer */ add r3, r3, r5 ld r4, HSTATE_KVM_VCPU(r13) - ld r5, HSTATE_KVM_VCORE(r13) - ld r6, VCORE_TB_OFFSET_APPL(r5) - subf r3, r6, r3 /* convert to host TB value */ std r3, VCPU_DEC_EXPIRES(r4) #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING @@ -2186,8 +2173,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) * Also clear the runlatch bit before napping. */ kvm_do_nap: - mfspr r0, SPRN_CTRLF - clrrdi r0, r0, 1 + li r0,0 mtspr SPRN_CTRLT, r0 li r0,1 @@ -2206,8 +2192,7 @@ kvm_nap_sequence: /* desired LPCR value in r5 */ bl isa206_idle_insn_mayloss - mfspr r0, SPRN_CTRLF - ori r0, r0, 1 + li r0,1 mtspr SPRN_CTRLT, r0 mtspr SPRN_SRR1, r3 @@ -2264,9 +2249,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* Restore guest decrementer */ ld r3, VCPU_DEC_EXPIRES(r4) - ld r5, HSTATE_KVM_VCORE(r13) - ld r6, VCORE_TB_OFFSET_APPL(r5) - add r3, r3, r6 /* convert host TB to guest TB value */ mftb r7 subf r3, r7, r3 mtspr SPRN_DEC, r3 @@ -2778,10 +2760,11 @@ kvmppc_msr_interrupt: blr /* + * void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu) + * * Load up guest PMU state. R3 points to the vcpu struct. */ -_GLOBAL(kvmhv_load_guest_pmu) -EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu) +kvmhv_load_guest_pmu: mr r4, r3 mflr r0 li r3, 1 @@ -2816,26 +2799,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) mtspr SPRN_SIAR, r7 mtspr SPRN_SDAR, r8 BEGIN_FTR_SECTION - ld r5, VCPU_MMCR + 24(r4) - ld r6, VCPU_SIER + 8(r4) - ld r7, VCPU_SIER + 16(r4) - mtspr SPRN_MMCR3, r5 - mtspr SPRN_SIER2, r6 - mtspr SPRN_SIER3, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) -BEGIN_FTR_SECTION ld r5, VCPU_MMCR + 16(r4) ld r6, VCPU_SIER(r4) mtspr SPRN_MMCR2, r5 mtspr SPRN_SIER, r6 -BEGIN_FTR_SECTION_NESTED(96) lwz r7, VCPU_PMC + 24(r4) lwz r8, VCPU_PMC + 28(r4) ld r9, VCPU_MMCRS(r4) mtspr SPRN_SPMC1, r7 mtspr SPRN_SPMC2, r8 mtspr SPRN_MMCRS, r9 -END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_MMCR0, r3 isync @@ -2843,10 +2816,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) blr /* + * void kvmhv_load_host_pmu(void) + * * Reload host PMU state saved in the PACA by kvmhv_save_host_pmu. */ -_GLOBAL(kvmhv_load_host_pmu) -EXPORT_SYMBOL_GPL(kvmhv_load_host_pmu) +kvmhv_load_host_pmu: mflr r0 lbz r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */ cmpwi r4, 0 @@ -2884,25 +2858,18 @@ BEGIN_FTR_SECTION mtspr SPRN_MMCR2, r8 mtspr SPRN_SIER, r9 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - ld r5, HSTATE_MMCR3(r13) - ld r6, HSTATE_SIER2(r13) - ld r7, HSTATE_SIER3(r13) - mtspr SPRN_MMCR3, r5 - mtspr SPRN_SIER2, r6 - mtspr SPRN_SIER3, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mtspr SPRN_MMCR0, r3 isync mtlr r0 23: blr /* + * void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use) + * * Save guest PMU state into the vcpu struct. * r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA) */ -_GLOBAL(kvmhv_save_guest_pmu) -EXPORT_SYMBOL_GPL(kvmhv_save_guest_pmu) +kvmhv_save_guest_pmu: mr r9, r3 mr r8, r4 BEGIN_FTR_SECTION @@ -2951,14 +2918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) BEGIN_FTR_SECTION std r10, VCPU_MMCR + 16(r9) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - mfspr r5, SPRN_MMCR3 - mfspr r6, SPRN_SIER2 - mfspr r7, SPRN_SIER3 - std r5, VCPU_MMCR + 24(r9) - std r6, VCPU_SIER + 8(r9) - std r7, VCPU_SIER + 16(r9) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) std r7, VCPU_SIAR(r9) std r8, VCPU_SDAR(r9) mfspr r3, SPRN_PMC1 @@ -2976,7 +2935,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) BEGIN_FTR_SECTION mfspr r5, SPRN_SIER std r5, VCPU_SIER(r9) -BEGIN_FTR_SECTION_NESTED(96) mfspr r6, SPRN_SPMC1 mfspr r7, SPRN_SPMC2 mfspr r8, SPRN_MMCRS @@ -2985,7 +2943,6 @@ BEGIN_FTR_SECTION_NESTED(96) std r8, VCPU_MMCRS(r9) lis r4, 0x8000 mtspr SPRN_MMCRS, r4 -END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 22: blr diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 28c436df9935..e414ca44839f 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -459,7 +459,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) struct kvm_memslots *slots; struct kvm_memory_slot *memslot, *m; int ret = H_SUCCESS; - int srcu_idx; + int srcu_idx, bkt; kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START; @@ -478,7 +478,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) /* register the memslot */ slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = __kvmppc_uvmem_memslot_create(kvm, memslot); if (ret) break; @@ -486,7 +486,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) if (ret) { slots = kvm_memslots(kvm); - kvm_for_each_memslot(m, slots) { + kvm_for_each_memslot(m, bkt, slots) { if (m == memslot) break; __kvmppc_uvmem_memslot_delete(kvm, memslot); @@ -647,7 +647,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) { - int srcu_idx; + int srcu_idx, bkt; struct kvm_memory_slot *memslot; /* @@ -662,7 +662,7 @@ unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmppc_uvmem_drop_pages(memslot, kvm, false); srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -821,7 +821,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; long ret = H_SUCCESS; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) @@ -830,7 +830,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) /* migrate any unmoved normal pfn to device pfns*/ srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = kvmppc_uv_migrate_mem_slot(kvm, memslot); if (ret) { /* diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 6bc9425acb32..34a801c3604a 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -428,7 +428,7 @@ static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) /************* MMU Notifiers *************/ static bool do_kvm_unmap_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - long i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -492,7 +492,7 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr) if (msr & MSR_POW) { if (!vcpu->arch.pending_exceptions) { - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; @@ -1899,16 +1899,15 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, } static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { return 0; } static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index ac14239f3424..1f10e7dfcdd0 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -376,7 +376,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_stuff_tce(vcpu); case H_CEDE: kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; return EMULATE_DONE; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index ebd5d920de8c..9cc466006e8b 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -942,8 +942,8 @@ static int xics_debug_show(struct seq_file *m, void *private) struct kvmppc_xics *xics = m->private; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; - int icsid, i; - unsigned long flags; + int icsid; + unsigned long flags, i; unsigned long t_rm_kick_vcpu, t_rm_check_resend; unsigned long t_rm_notify_eoi; unsigned long t_reject, t_check_resend; @@ -1340,7 +1340,7 @@ static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) static void kvmppc_xics_release(struct kvm_device *dev) { struct kvmppc_xics *xics = dev->private; - int i; + unsigned long i; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 6231f76bdd66..8e4c79e2fcd8 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -116,7 +116,7 @@ static inline struct kvmppc_icp *kvmppc_xics_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.icp && nr == vcpu->arch.icp->server_num) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 225008882958..e216c068075d 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -368,7 +368,8 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio) { struct kvmppc_xive *xive = kvm->arch.xive; struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; lockdep_assert_held(&xive->lock); @@ -439,7 +440,8 @@ static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio) int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio) { struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; /* Locate target server */ vcpu = kvmppc_xive_find_server(kvm, *server); @@ -1519,7 +1521,8 @@ static void xive_pre_save_queue(struct kvmppc_xive *xive, struct xive_q *q) static void xive_pre_save_scan(struct kvmppc_xive *xive) { struct kvm_vcpu *vcpu = NULL; - int i, j; + unsigned long i; + int j; /* * See comment in xive_get_source() about how this @@ -1700,7 +1703,7 @@ static bool xive_check_delayed_irq(struct kvmppc_xive *xive, u32 irq) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -2037,7 +2040,7 @@ static void kvmppc_xive_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive device\n"); @@ -2291,7 +2294,7 @@ static int xive_debug_show(struct seq_file *m, void *private) u64 t_vm_h_cppr = 0; u64 t_vm_h_eoi = 0; u64 t_vm_h_ipi = 0; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index e6a9651c6f1e..09d0657596c3 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -199,7 +199,7 @@ struct kvmppc_xive_vcpu { static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num) @@ -240,7 +240,7 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 99db9ac49901..561a5bfe0468 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -807,7 +807,7 @@ static int kvmppc_xive_reset(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -916,7 +916,7 @@ static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -1017,7 +1017,7 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive native device\n"); @@ -1214,7 +1214,7 @@ static int xive_native_debug_show(struct seq_file *m, void *private) struct kvmppc_xive *xive = m->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 8c15c90dd3a9..06c5830a93f9 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -718,7 +718,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) if (vcpu->arch.shared->msr & MSR_WE) { local_irq_enable(); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); hard_irq_disable(); @@ -1821,16 +1821,15 @@ void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; } void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 64eb833e9f02..051102d50c31 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -65,7 +65,7 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb) ulong param = vcpu->arch.regs.gpr[rb]; int prio = dbell2prio(rb); int pir = param & PPC_DBELL_PIR_MASK; - int i; + unsigned long i; struct kvm_vcpu *cvcpu; if (prio < 0) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a72920f4f221..2ad0ccd202d5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -236,7 +236,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) break; case EV_HCALL_TOKEN(EV_IDLE): r = EV_SUCCESS; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); break; default: @@ -463,9 +463,6 @@ err_out: void kvm_arch_destroy_vm(struct kvm *kvm) { - unsigned int i; - struct kvm_vcpu *vcpu; - #ifdef CONFIG_KVM_XICS /* * We call kick_all_cpus_sync() to ensure that all @@ -476,14 +473,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kick_all_cpus_sync(); #endif - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); + kvm_destroy_vcpus(kvm); mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); kvmppc_core_destroy_vm(kvm); @@ -706,20 +698,19 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - return kvmppc_core_prepare_memory_region(kvm, memslot, mem, change); + return kvmppc_core_prepare_memory_region(kvm, old, new, change); } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - kvmppc_core_commit_memory_region(kvm, mem, old, new, change); + kvmppc_core_commit_memory_region(kvm, old, new, change); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, @@ -762,7 +753,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) goto out_vcpu_uninit; - vcpu->arch.waitp = &vcpu->wait; + rcuwait_init(&vcpu->arch.wait); + vcpu->arch.waitp = &vcpu->arch.wait; kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); return 0; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 3a600bd7fbc6..77820036c722 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -572,18 +572,6 @@ void __init radix__early_init_devtree(void) return; } -static void radix_init_amor(void) -{ - /* - * In HV mode, we init AMOR (Authority Mask Override Register) so that - * the hypervisor and guest can setup IAMR (Instruction Authority Mask - * Register), enable key 0 and set it to 1. - * - * AMOR = 0b1100 .... 0000 (Mask for key 0 is 11) - */ - mtspr(SPRN_AMOR, (3ul << 62)); -} - void __init radix__early_init_mmu(void) { unsigned long lpcr; @@ -644,7 +632,6 @@ void __init radix__early_init_mmu(void) lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); - radix_init_amor(); } else { radix_init_pseries(); } @@ -668,8 +655,6 @@ void radix__early_init_mmu_secondary(void) set_ptcr_when_no_uv(__pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); - - radix_init_amor(); } radix__switch_mmu_context(NULL, &init_mm); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 73e62e9b179b..8d4ff93462fb 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2419,8 +2419,24 @@ int register_power_pmu(struct power_pmu *pmu) } #ifdef CONFIG_PPC64 +static bool pmu_override = false; +static unsigned long pmu_override_val; +static void do_pmu_override(void *data) +{ + ppc_set_pmu_inuse(1); + if (pmu_override_val) + mtspr(SPRN_MMCR1, pmu_override_val); + mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC); +} + static int __init init_ppc64_pmu(void) { + if (cpu_has_feature(CPU_FTR_HVMODE) && pmu_override) { + pr_warn("disabling perf due to pmu_override= command line option.\n"); + on_each_cpu(do_pmu_override, NULL, 1); + return 0; + } + /* run through all the pmu drivers one at a time */ if (!init_power5_pmu()) return 0; @@ -2442,4 +2458,23 @@ static int __init init_ppc64_pmu(void) return init_generic_compat_pmu(); } early_initcall(init_ppc64_pmu); + +static int __init pmu_setup(char *str) +{ + unsigned long val; + + if (!early_cpu_has_feature(CPU_FTR_HVMODE)) + return 0; + + pmu_override = true; + + if (kstrtoul(str, 0, &val)) + val = 0; + + pmu_override_val = val; + + return 1; +} +__setup("pmu_override=", pmu_setup); + #endif diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index e3ffdc8e8567..3bc84e2fe064 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -306,8 +306,8 @@ struct p7_sprs { /* per thread SPRs that get lost in shallow states */ u64 amr; u64 iamr; - u64 amor; u64 uamor; + /* amor is restored to constant ~0 */ }; static unsigned long power7_idle_insn(unsigned long type) @@ -378,7 +378,6 @@ static unsigned long power7_idle_insn(unsigned long type) if (cpu_has_feature(CPU_FTR_ARCH_207S)) { sprs.amr = mfspr(SPRN_AMR); sprs.iamr = mfspr(SPRN_IAMR); - sprs.amor = mfspr(SPRN_AMOR); sprs.uamor = mfspr(SPRN_UAMOR); } @@ -397,7 +396,7 @@ static unsigned long power7_idle_insn(unsigned long type) */ mtspr(SPRN_AMR, sprs.amr); mtspr(SPRN_IAMR, sprs.iamr); - mtspr(SPRN_AMOR, sprs.amor); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_UAMOR, sprs.uamor); } } @@ -589,7 +588,6 @@ struct p9_sprs { u64 purr; u64 spurr; u64 dscr; - u64 wort; u64 ciabr; u64 mmcra; @@ -687,7 +685,6 @@ static unsigned long power9_idle_stop(unsigned long psscr) sprs.amr = mfspr(SPRN_AMR); sprs.iamr = mfspr(SPRN_IAMR); - sprs.amor = mfspr(SPRN_AMOR); sprs.uamor = mfspr(SPRN_UAMOR); srr1 = isa300_idle_stop_mayloss(psscr); /* go idle */ @@ -708,7 +705,7 @@ static unsigned long power9_idle_stop(unsigned long psscr) */ mtspr(SPRN_AMR, sprs.amr); mtspr(SPRN_IAMR, sprs.iamr); - mtspr(SPRN_AMOR, sprs.amor); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_UAMOR, sprs.uamor); /* diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 8b28ff9d98d1..83100c6524cc 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2107,8 +2107,14 @@ static void dump_300_sprs(void) if (!cpu_has_feature(CPU_FTR_ARCH_300)) return; - printf("pidr = %.16lx tidr = %.16lx\n", - mfspr(SPRN_PID), mfspr(SPRN_TIDR)); + if (cpu_has_feature(CPU_FTR_P9_TIDR)) { + printf("pidr = %.16lx tidr = %.16lx\n", + mfspr(SPRN_PID), mfspr(SPRN_TIDR)); + } else { + printf("pidr = %.16lx\n", + mfspr(SPRN_PID)); + } + printf("psscr = %.16lx\n", hv ? mfspr(SPRN_PSSCR) : mfspr(SPRN_PSSCR_PR)); diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 25ba21f98504..907fafea787e 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -12,14 +12,12 @@ #include <linux/types.h> #include <linux/kvm.h> #include <linux/kvm_types.h> +#include <asm/csr.h> #include <asm/kvm_vcpu_fp.h> #include <asm/kvm_vcpu_timer.h> -#ifdef CONFIG_64BIT -#define KVM_MAX_VCPUS (1U << 16) -#else -#define KVM_MAX_VCPUS (1U << 9) -#endif +#define KVM_MAX_VCPUS \ + ((HGATP_VMID_MASK >> HGATP_VMID_SHIFT) + 1) #define KVM_HALT_POLL_NS_DEFAULT 500000 @@ -210,7 +208,6 @@ struct kvm_vcpu_arch { static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #define KVM_ARCH_WANT_MMU_NOTIFIER diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 30cdd1df0098..300590225348 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -5,14 +5,10 @@ ccflags-y += -I $(srctree)/$(src) -KVM := ../../../virt/kvm +include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o -kvm-y += $(KVM)/kvm_main.o -kvm-y += $(KVM)/coalesced_mmio.o -kvm-y += $(KVM)/binary_stats.o -kvm-y += $(KVM)/eventfd.o kvm-y += main.o kvm-y += vm.o kvm-y += vmid.o diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index d81bae8eb55e..7d884b15cf5e 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -453,10 +453,15 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { + gpa_t gpa = slot->base_gfn << PAGE_SHIFT; + phys_addr_t size = slot->npages << PAGE_SHIFT; + + spin_lock(&kvm->mmu_lock); + stage2_unmap_range(kvm, gpa, size, false); + spin_unlock(&kvm->mmu_lock); } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -466,18 +471,18 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * allocated dirty_bitmap[], dirty pages will be tracked while * the memory slot is write protected. */ - if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) - stage2_wp_memory_region(kvm, mem->slot); + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) + stage2_wp_memory_region(kvm, new->id); } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - hva_t hva = mem->userspace_addr; - hva_t reg_end = hva + mem->memory_size; - bool writable = !(mem->flags & KVM_MEM_READONLY); + hva_t hva, reg_end, size; + gpa_t base_gpa; + bool writable; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -488,10 +493,16 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the GPA * space addressable by the KVM guest GPA space. */ - if ((memslot->base_gfn + memslot->npages) >= + if ((new->base_gfn + new->npages) >= (stage2_gpa_size >> PAGE_SHIFT)) return -EFAULT; + hva = new->userspace_addr; + size = new->npages << PAGE_SHIFT; + reg_end = hva + size; + base_gpa = new->base_gfn << PAGE_SHIFT; + writable = !(new->flags & KVM_MEM_READONLY); + mmap_read_lock(current->mm); /* @@ -527,15 +538,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, vm_end = min(reg_end, vma->vm_end); if (vma->vm_flags & VM_PFNMAP) { - gpa_t gpa = mem->guest_phys_addr + - (vm_start - mem->userspace_addr); + gpa_t gpa = base_gpa + (vm_start - hva); phys_addr_t pa; pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; goto out; } @@ -553,8 +563,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, spin_lock(&kvm->mmu_lock); if (ret) - stage2_unmap_range(kvm, mem->guest_phys_addr, - mem->memory_size, false); + stage2_unmap_range(kvm, base_gpa, size, false); spin_unlock(&kvm->mmu_lock); out: diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 7f2d742ae4c6..571f319e995a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -146,7 +146,7 @@ static int system_opcode_insn(struct kvm_vcpu *vcpu, vcpu->stat.wfi_exit_stat++; if (!kvm_arch_vcpu_runnable(vcpu)) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 3b0e703d22cf..d0d2bcab2f7b 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -60,7 +60,7 @@ int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; kvm_for_each_vcpu(i, tmp, vcpu->kvm) diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index fb18af34a4b5..7619691d8953 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -46,15 +46,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 2c6253b293bc..807228f8f409 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -65,7 +65,7 @@ bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid) void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) { - int i; + unsigned long i; struct kvm_vcpu *v; struct cpumask hmask; struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid; diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index fd825097cf04..b626bc6e0eaf 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -403,7 +403,6 @@ CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y @@ -476,6 +475,7 @@ CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_VXLAN=m CONFIG_BAREUDP=m +CONFIG_AMT=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -489,6 +489,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ASIX is not set # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set @@ -571,6 +572,7 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m +# CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y @@ -775,12 +777,14 @@ CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m CONFIG_RANDOM32_SELFTEST=y +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y CONFIG_HEADERS_INSTALL=y CONFIG_DEBUG_SECTION_MISMATCH=y @@ -807,6 +811,7 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_KFENCE=y +CONFIG_KFENCE_STATIC_KEYS=y CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y @@ -842,6 +847,7 @@ CONFIG_FTRACE_STARTUP_TEST=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m +CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m CONFIG_DEBUG_ENTRY=y CONFIG_CIO_INJECT=y CONFIG_KUNIT=m @@ -860,7 +866,7 @@ CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y -CONFIG_KPROBES_SANITY_TEST=y +CONFIG_KPROBES_SANITY_TEST=m CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index c9c3cedff2d8..0056cab27372 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -394,7 +394,6 @@ CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y @@ -467,6 +466,7 @@ CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_VXLAN=m CONFIG_BAREUDP=m +CONFIG_AMT=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -480,6 +480,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ASIX is not set # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set @@ -762,12 +763,14 @@ CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y @@ -792,9 +795,11 @@ CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m +CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m CONFIG_KUNIT=m CONFIG_KUNIT_DEBUGFS=y CONFIG_LKDTM=m +CONFIG_KPROBES_SANITY_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index aceccf3b9a88..eed3b9acfa71 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -65,9 +65,11 @@ CONFIG_ZFCP=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" # CONFIG_ZLIB_DFLTCC is not set +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y # CONFIG_SYMBOLIC_ERRNAME is not set CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index a604d51acfc8..a22c9266ea05 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1010,6 +1010,4 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu); - #endif diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index e4dc64cc9c55..287bb88f7698 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -14,12 +14,13 @@ /* I/O Map */ #define ZPCI_IOMAP_SHIFT 48 -#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000UL +#define ZPCI_IOMAP_ADDR_SHIFT 62 +#define ZPCI_IOMAP_ADDR_BASE (1UL << ZPCI_IOMAP_ADDR_SHIFT) #define ZPCI_IOMAP_ADDR_OFF_MASK ((1UL << ZPCI_IOMAP_SHIFT) - 1) #define ZPCI_IOMAP_MAX_ENTRIES \ - ((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT)) + (1UL << (ZPCI_IOMAP_ADDR_SHIFT - ZPCI_IOMAP_SHIFT)) #define ZPCI_IOMAP_ADDR_IDX_MASK \ - (~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE) + ((ZPCI_IOMAP_ADDR_BASE - 1) & ~ZPCI_IOMAP_ADDR_OFF_MASK) struct zpci_iomap_entry { u32 fh; diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 67a8e770e369..2e84d3922f7c 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -33,6 +33,7 @@ config KVM select HAVE_KVM_NO_POLL select SRCU select KVM_VFIO + select INTERVAL_TREE help Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index b3aaadc60ead..26f4a74e5ce4 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -3,13 +3,11 @@ # # Copyright IBM Corp. 2008 -KVM := ../../../virt/kvm -common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o \ - $(KVM)/irqchip.o $(KVM)/vfio.o $(KVM)/binary_stats.o +include $(srctree)/virt/kvm/Makefile.kvm ccflags-y := -Ivirt/kvm -Iarch/s390/kvm -kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o +kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o +kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 0576d5c99138..db933c252dbc 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1335,7 +1335,8 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); + vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); @@ -2666,7 +2667,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr) static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = 0; - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; switch (attr->group) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ef299aad4009..9c6d45d0d345 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -295,7 +295,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { @@ -682,7 +682,7 @@ out: static void icpt_operexc_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -936,7 +936,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_s390_vcpu_block_all(kvm); @@ -1021,7 +1021,7 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) { - int cx; + unsigned long cx; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(cx, vcpu, kvm) @@ -1037,13 +1037,13 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) struct kvm_memory_slot *ms; struct kvm_memslots *slots; unsigned long ram_pages = 0; - int slotnr; + int bkt; /* migration mode already enabled */ if (kvm->arch.migration_mode) return 0; slots = kvm_memslots(kvm); - if (!slots || !slots->used_slots) + if (!slots || kvm_memslots_empty(slots)) return -EINVAL; if (!kvm->arch.use_cmma) { @@ -1051,8 +1051,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) return 0; } /* mark all the pages in active slots as dirty */ - for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { - ms = slots->memslots + slotnr; + kvm_for_each_memslot(ms, bkt, slots) { if (!ms->dirty_bitmap) return -EINVAL; /* @@ -1943,41 +1942,6 @@ out: /* for consistency */ #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) -/* - * Similar to gfn_to_memslot, but returns the index of a memslot also when the - * address falls in a hole. In that case the index of one of the memslots - * bordering the hole is returned. - */ -static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) -{ - int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->last_used_slot); - struct kvm_memory_slot *memslots = slots->memslots; - - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return slot; - - while (start < end) { - slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - if (start >= slots->used_slots) - return slots->used_slots - 1; - - if (gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->last_used_slot, start); - } - - return start; -} - static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, u8 *res, unsigned long bufsize) { @@ -2001,26 +1965,31 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, return 0; } +static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots, + gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, true); +} + static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, unsigned long cur_gfn) { - int slotidx = gfn_to_memslot_approx(slots, cur_gfn); - struct kvm_memory_slot *ms = slots->memslots + slotidx; + struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn); unsigned long ofs = cur_gfn - ms->base_gfn; + struct rb_node *mnode = &ms->gfn_node[slots->node_idx]; if (ms->base_gfn + ms->npages <= cur_gfn) { - slotidx--; + mnode = rb_next(mnode); /* If we are above the highest slot, wrap around */ - if (slotidx < 0) - slotidx = slots->used_slots - 1; + if (!mnode) + mnode = rb_first(&slots->gfn_tree); - ms = slots->memslots + slotidx; + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = 0; } ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs); - while ((slotidx > 0) && (ofs >= ms->npages)) { - slotidx--; - ms = slots->memslots + slotidx; + while (ofs >= ms->npages && (mnode = rb_next(mnode))) { + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0); } return ms->base_gfn + ofs; @@ -2033,7 +2002,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *ms; - if (unlikely(!slots->used_slots)) + if (unlikely(kvm_memslots_empty(slots))) return 0; cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); @@ -2043,7 +2012,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, if (!ms) return 0; next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1); - mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages; + mem_end = kvm_s390_get_gfn_end(slots); while (args->count < bufsize) { hva = gfn_to_hva(kvm, cur_gfn); @@ -2206,7 +2175,7 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) struct kvm_vcpu *vcpu; u16 rc, rrc; int ret = 0; - int i; + unsigned long i; /* * We ignore failures and try to destroy as many CPUs as possible. @@ -2230,7 +2199,8 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) { - int i, r = 0; + unsigned long i; + int r = 0; u16 dummy; struct kvm_vcpu *vcpu; @@ -2821,27 +2791,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)(vcpu->arch.sie_block)); } -static void kvm_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); -} - void kvm_arch_destroy_vm(struct kvm *kvm) { u16 rc, rrc; - kvm_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); sca_dispose(kvm); kvm_s390_gisa_destroy(kvm); /* @@ -2945,7 +2899,7 @@ static int sca_switch_to_extended(struct kvm *kvm) struct bsca_block *old_sca = kvm->arch.sca; struct esca_block *new_sca; struct kvm_vcpu *vcpu; - unsigned int vcpu_idx; + unsigned long vcpu_idx; u32 scaol, scaoh; if (kvm->arch.use_esca) @@ -3427,7 +3381,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct kvm_vcpu *vcpu; unsigned long prefix; - int i; + unsigned long i; if (gmap_is_shadow(gmap)) return; @@ -3449,7 +3403,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { /* do not poll with more than halt_poll_max_steal percent of steal time */ if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >= - halt_poll_max_steal) { + READ_ONCE(halt_poll_max_steal)) { vcpu->stat.halt_no_poll_steal++; return true; } @@ -3920,7 +3874,7 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, { struct kvm_vcpu *vcpu; union tod_clock clk; - int i; + unsigned long i; mutex_lock(&kvm->lock); preempt_disable(); @@ -4552,7 +4506,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) static void __disable_ibs_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -4590,7 +4544,7 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) } for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) + if (!is_vcpu_stopped(kvm_get_vcpu(vcpu->kvm, i))) started_vcpus++; } @@ -4657,9 +4611,11 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) __disable_ibs_on_vcpu(vcpu); for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) { + struct kvm_vcpu *tmp = kvm_get_vcpu(vcpu->kvm, i); + + if (!is_vcpu_stopped(tmp)) { started_vcpus++; - started_vcpu = vcpu->kvm->vcpus[i]; + started_vcpu = tmp; } } @@ -5025,32 +4981,38 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { + gpa_t size; + + /* When we are protected, we should not change the memory slots */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; + + if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY) + return 0; + /* A few sanity checks. We can have memory slots which have to be located/ended at a segment boundary (1MB). The memory in userland is ok to be fragmented into various different vmas. It is okay to mmap() and munmap() stuff in this slot after doing this call at any time */ - if (mem->userspace_addr & 0xffffful) + if (new->userspace_addr & 0xffffful) return -EINVAL; - if (mem->memory_size & 0xffffful) + size = new->npages * PAGE_SIZE; + if (size & 0xffffful) return -EINVAL; - if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) + if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit) return -EINVAL; - /* When we are protected, we should not change the memory slots */ - if (kvm_s390_pv_get_handle(kvm)) - return -EINVAL; return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -5069,8 +5031,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, break; fallthrough; case KVM_MR_CREATE: - rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, - mem->guest_phys_addr, mem->memory_size); + rc = gmap_map_segment(kvm->arch.gmap, new->userspace_addr, + new->base_gfn * PAGE_SIZE, + new->npages * PAGE_SIZE); break; case KVM_MR_FLAGS_ONLY: break; @@ -5089,11 +5052,6 @@ static inline unsigned long nonhyp_mask(int i) return 0x0000ffffffffffffUL >> (nonhyp_fai << 4); } -void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) -{ - vcpu->valid_wakeup = false; -} - static int __init kvm_s390_init(void) { int i; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 1876ab0c293f..098831e815e6 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -217,6 +217,20 @@ static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm) kvm->arch.user_cpu_state_ctrl = 1; } +/* get the end gfn of the last (highest gfn) memslot */ +static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) +{ + struct rb_node *node; + struct kvm_memory_slot *ms; + + if (WARN_ON(kvm_memslots_empty(slots))) + return 0; + + node = rb_last(&slots->gfn_tree); + ms = container_of(node, struct kvm_memory_slot, gfn_node[slots->node_idx]); + return ms->base_gfn + ms->npages; +} + /* implemented in pv.c */ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); @@ -357,7 +371,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; WARN_ON(!mutex_is_locked(&kvm->lock)); @@ -367,7 +381,7 @@ static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 00d272d134c2..7f7c0d6af2ce 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -116,7 +116,6 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) unsigned long base = uv_info.guest_base_stor_len; unsigned long virt = uv_info.guest_virt_var_stor_len; unsigned long npages = 0, vlen = 0; - struct kvm_memory_slot *memslot; kvm->arch.pv.stor_var = NULL; kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(base)); @@ -130,8 +129,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) * Slots are sorted by GFN */ mutex_lock(&kvm->slots_lock); - memslot = kvm_memslots(kvm)->memslots; - npages = memslot->base_gfn + memslot->npages; + npages = kvm_s390_get_gfn_end(kvm_memslots(kvm)); mutex_unlock(&kvm->slots_lock); kvm->arch.pv.guest_len = npages * PAGE_SIZE; diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index cfc5f5557c06..bc7973359ae2 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -173,10 +173,11 @@ static noinline int unwindme_func4(struct unwindme *u) } /* - * trigger specification exception + * Trigger operation exception; use insn notation to bypass + * llvm's integrated assembler sanity checks. */ asm volatile( - " mvcl %%r1,%%r1\n" + " .insn e,0x0000\n" /* illegal opcode */ "0: nopr %%r7\n" EX_TABLE(0b, 0b) :); diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index c7a97f32432f..481a664287e2 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -43,7 +43,6 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); #define flush_icache_user_range flush_icache_range extern void flush_icache_page(struct vm_area_struct *vma, diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 208f131659c5..d9539d28bdaa 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index c37764dc764d..46adabcb1720 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -494,3 +494,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e38a4cf795d9..97b1f84bb53f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -574,6 +574,10 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) ud2 1: #endif +#ifdef CONFIG_XEN_PV + ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV +#endif + POP_REGS pop_rdi=0 /* @@ -890,6 +894,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) .Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ movl $1, %ebx + /* * The kernel-enforced convention is a negative GSBASE indicates * a kernel value. No SWAPGS needed on entry and exit. @@ -897,21 +902,14 @@ SYM_CODE_START_LOCAL(paranoid_entry) movl $MSR_GS_BASE, %ecx rdmsr testl %edx, %edx - jns .Lparanoid_entry_swapgs - ret + js .Lparanoid_kernel_gsbase -.Lparanoid_entry_swapgs: + /* EBX = 0 -> SWAPGS required on exit */ + xorl %ebx, %ebx swapgs +.Lparanoid_kernel_gsbase: - /* - * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an - * unconditional CR3 write, even in the PTI case. So do an lfence - * to prevent GS speculation, regardless of whether PTI is enabled. - */ FENCE_SWAPGS_KERNEL_ENTRY - - /* EBX = 0 -> SWAPGS required on exit */ - xorl %ebx, %ebx ret SYM_CODE_END(paranoid_entry) @@ -993,11 +991,6 @@ SYM_CODE_START_LOCAL(error_entry) pushq %r12 ret -.Lerror_entry_done_lfence: - FENCE_SWAPGS_KERNEL_ENTRY -.Lerror_entry_done: - ret - /* * There are two places in the kernel that can potentially fault with * usergs. Handle them here. B stepping K8s sometimes report a @@ -1020,8 +1013,14 @@ SYM_CODE_START_LOCAL(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS - FENCE_SWAPGS_USER_ENTRY - jmp .Lerror_entry_done + + /* + * Issue an LFENCE to prevent GS speculation, regardless of whether it is a + * kernel or user gsbase. + */ +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY + ret .Lbstep_iret: /* Fix truncated RIP */ diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 6053674f9132..c2767a6a387e 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -102,12 +102,6 @@ extern void switch_fpu_return(void); */ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); -/* - * Tasks that are not using SVA have mm->pasid set to zero to note that they - * will not have the valid bit set in MSR_IA32_PASID while they are running. - */ -#define PASID_DISABLED 0 - /* Trap handling */ extern int fpu__exception_code(struct fpu *fpu, int trap_nr); extern void fpu_sync_fpstate(struct fpu *fpu); diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5a0bcf8b78d7..048b6d5aff50 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -108,7 +108,7 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ -#define INTEL_FAM6_RAPTOR_LAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE 0xB7 /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index cefe1d81e2e8..9e50da3ed01a 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -47,6 +47,7 @@ KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) KVM_X86_OP(set_rflags) +KVM_X86_OP(get_if_flag) KVM_X86_OP(tlb_flush_all) KVM_X86_OP(tlb_flush_current) KVM_X86_OP_NULL(tlb_remote_flush) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6ac61f85e07b..344ced0b6b68 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -97,7 +97,7 @@ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) #define KVM_REQ_TLB_FLUSH_GUEST \ - KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) + KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) #define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ @@ -135,7 +135,7 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -#define KVM_PERMILLE_MMU_PAGES 20 +#define KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO 50 #define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) @@ -291,25 +291,31 @@ struct kvm_kernel_irq_routing_entry; * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * - * But, even though there are 18 bits in the mask below, not all combinations - * of modes and flags are possible. The maximum number of possible upper-level - * shadow pages for a single gfn is in the neighborhood of 2^13. + * But, even though there are 19 bits in the mask below, not all combinations + * of modes and flags are possible: * - * - invalid shadow pages are not accounted. - * - level is effectively limited to four combinations, not 16 as the number - * bits would imply, as 4k SPs are not tracked (allowed to go unsync). - * - level is effectively unused for non-PAE paging because there is exactly - * one upper level (see 4k SP exception above). - * - quadrant is used only for non-PAE paging and is exclusive with - * gpte_is_8_bytes. - * - execonly and ad_disabled are used only for nested EPT, which makes it - * exclusive with quadrant. + * - invalid shadow pages are not accounted, so the bits are effectively 18 + * + * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); + * execonly and ad_disabled are only used for nested EPT which has + * has_4_byte_gpte=0. Therefore, 2 bits are always unused. + * + * - the 4 bits of level are effectively limited to the values 2/3/4/5, + * as 4k SPs are not tracked (allowed to go unsync). In addition non-PAE + * paging has exactly one upper level, making level completely redundant + * when has_4_byte_gpte=1. + * + * - on top of this, smep_andnot_wp and smap_andnot_wp are only set if + * cr0_wp=0, therefore these three bits only give rise to 5 possibilities. + * + * Therefore, the maximum number of possible upper-level shadow pages for a + * single gfn is a bit less than 2^13. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned gpte_is_8_bytes:1; + unsigned has_4_byte_gpte:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; @@ -420,10 +426,9 @@ struct kvm_mmu { int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, - u32 access, struct x86_exception *exception); - gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t gva_or_gpa, u32 access, + struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); @@ -1036,6 +1041,7 @@ struct kvm_x86_msr_filter { #define APICV_INHIBIT_REASON_PIT_REINJ 4 #define APICV_INHIBIT_REASON_X2APIC 5 #define APICV_INHIBIT_REASON_BLOCKIRQ 6 +#define APICV_INHIBIT_REASON_ABSENT 7 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1348,6 +1354,7 @@ struct kvm_x86_ops { void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + bool (*get_if_flag)(struct kvm_vcpu *vcpu); void (*tlb_flush_all)(struct kvm_vcpu *vcpu); void (*tlb_flush_current)(struct kvm_vcpu *vcpu); @@ -1585,10 +1592,9 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); -unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); @@ -1638,7 +1644,8 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to * decode the instruction length. For use *only* by - * kvm_x86_ops.skip_emulated_instruction() implementations. + * kvm_x86_ops.skip_emulated_instruction() implementations if + * EMULTYPE_COMPLETE_USER_EXIT is not set. * * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to * retry native execution under certain conditions, @@ -1658,6 +1665,10 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which * case the CR2/GPA value pass on the stack is valid. + * + * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility + * state and inject single-step #DBs after skipping + * an instruction (after completing userspace I/O). */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) @@ -1666,6 +1677,7 @@ extern u64 kvm_mce_cap_supported; #define EMULTYPE_TRAP_UD_FORCED (1 << 4) #define EMULTYPE_VMWARE_GP (1 << 5) #define EMULTYPE_PF (1 << 6) +#define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, @@ -1690,7 +1702,7 @@ int kvm_emulate_monitor(struct kvm_vcpu *vcpu); int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); -int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu); int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); @@ -1756,12 +1768,9 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu); -gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, @@ -1925,8 +1934,6 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static_call_cond(kvm_x86_vcpu_unblocking)(vcpu); } -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} - static inline int kvm_cpu_get_apicid(int mps_cpu) { #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 9d4a3b1b25b9..eb186bc57f6a 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -63,9 +63,9 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, void kvm_slot_page_track_remove_page(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, enum kvm_page_track_mode mode); -bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode); +bool kvm_slot_page_track_is_active(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode); void kvm_page_track_register_notifier(struct kvm *kvm, diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 2cef6c5a52c2..6acaf5af0a3d 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -73,4 +73,15 @@ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) +/* + * Error codes related to GHCB input that can be communicated back to the guest + * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2. + */ +#define GHCB_ERR_NOT_REGISTERED 1 +#define GHCB_ERR_INVALID_USAGE 2 +#define GHCB_ERR_INVALID_SCRATCH_AREA 3 +#define GHCB_ERR_MISSING_INPUT 4 +#define GHCB_ERR_INVALID_INPUT 5 +#define GHCB_ERR_INVALID_EVENT 6 + #endif diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 0575f5863b7f..e5e0fe10c692 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -281,13 +281,13 @@ HYPERVISOR_callback_op(int cmd, void *arg) return _hypercall2(int, callback_op, cmd, arg); } -static inline int +static __always_inline int HYPERVISOR_set_debugreg(int reg, unsigned long value) { return _hypercall2(int, set_debugreg, reg, value); } -static inline unsigned long +static __always_inline unsigned long HYPERVISOR_get_debugreg(int reg) { return _hypercall1(unsigned long, get_debugreg, reg); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 4957f59deb40..5adab895127e 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -64,6 +64,7 @@ void xen_arch_unregister_cpu(int num); #ifdef CONFIG_PVH void __init xen_pvh_init(struct boot_params *boot_params); +void __init mem_map_via_hcall(struct boot_params *boot_params_p); #endif #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index d5958278eba6..91d4b6de58ab 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, struct fpstate *fpstate) { struct xregs_state __user *x = buf; - struct _fpx_sw_bytes sw_bytes; + struct _fpx_sw_bytes sw_bytes = {}; u32 xfeatures; int err; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c410be738ae7..6a190c7f4d71 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -742,7 +742,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } -static char *prepare_command_line(void) +static char * __init prepare_command_line(void) { #ifdef CONFIG_CMDLINE_BOOL #ifdef CONFIG_CMDLINE_OVERRIDE diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 74f0ec955384..a9fc2ac7a8bd 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -294,11 +294,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, char *dst, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT | X86_PF_WRITE; - char __user *target = (char __user *)dst; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __put_user() independent of whether kernel or user @@ -320,26 +315,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *target = (u8 __user *)dst; + memcpy(&d1, buf, 1); if (__put_user(d1, target)) goto fault; break; - case 2: + } + case 2: { + u16 d2; + u16 __user *target = (u16 __user *)dst; + memcpy(&d2, buf, 2); if (__put_user(d2, target)) goto fault; break; - case 4: + } + case 4: { + u32 d4; + u32 __user *target = (u32 __user *)dst; + memcpy(&d4, buf, 4); if (__put_user(d4, target)) goto fault; break; - case 8: + } + case 8: { + u64 d8; + u64 __user *target = (u64 __user *)dst; + memcpy(&d8, buf, 8); if (__put_user(d8, target)) goto fault; break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; @@ -362,11 +373,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, char *src, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT; - char __user *s = (char __user *)src; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __get_user() independent of whether kernel or user @@ -388,26 +394,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *s = (u8 __user *)src; + if (__get_user(d1, s)) goto fault; memcpy(buf, &d1, 1); break; - case 2: + } + case 2: { + u16 d2; + u16 __user *s = (u16 __user *)src; + if (__get_user(d2, s)) goto fault; memcpy(buf, &d2, 2); break; - case 4: + } + case 4: { + u32 d4; + u32 __user *s = (u32 __user *)src; + if (__get_user(d4, s)) goto fault; memcpy(buf, &d4, 4); break; - case 8: + } + case 8: { + u64 d8; + u64 __user *s = (u64 __user *)src; if (__get_user(d8, s)) goto fault; memcpy(buf, &d8, 8); break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 2e076a459a0c..a698196377be 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason) EXPORT_SYMBOL_GPL(mark_tsc_unstable); +static void __init tsc_disable_clocksource_watchdog(void) +{ + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; +} + static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) @@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void) #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; + + /* + * Disable the clocksource watchdog when the system has: + * - TSC running at constant frequency + * - TSC which does not stop in C-States + * - the TSC_ADJUST register which allows to detect even minimal + * modifications + * - not more than two sockets. As the number of sockets cannot be + * evaluated at the early boot stage where this has to be + * invoked, check the number of online memory nodes as a + * fallback solution which is an reasonable estimate. + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + boot_cpu_has(X86_FEATURE_TSC_ADJUST) && + nr_online_nodes <= 2) + tsc_disable_clocksource_watchdog(); } /* @@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void) if (tsc_unstable) goto unreg; - if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; - if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; @@ -1527,7 +1547,7 @@ void __init tsc_init(void) } if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 50a4515fe0ad..9452dc9664b5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -30,6 +30,7 @@ struct tsc_adjust { }; static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); +static struct timer_list tsc_sync_check_timer; /* * TSC's on different sockets may be reset asynchronously. @@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume) } } +/* + * Normally the tsc_sync will be checked every time system enters idle + * state, but there is still caveat that a system won't enter idle, + * either because it's too busy or configured purposely to not enter + * idle. + * + * So setup a periodic timer (every 10 minutes) to make sure the check + * is always on. + */ + +#define SYNC_CHECK_INTERVAL (HZ * 600) + +static void tsc_sync_check_timer_fn(struct timer_list *unused) +{ + int next_cpu; + + tsc_verify_tsc_adjust(false); + + /* Run the check for all onlined CPUs in turn */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + + tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL; + add_timer_on(&tsc_sync_check_timer, next_cpu); +} + +static int __init start_sync_check_timer(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable) + return 0; + + timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0); + tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL; + add_timer(&tsc_sync_check_timer); + + return 0; +} +late_initcall(start_sync_check_timer); + static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, unsigned int cpu, bool bootcpu) { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 619186138176..03b2ce34e7f4 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD + select HAVE_KVM_DIRTY_RING select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING @@ -43,6 +44,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU + select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM help Support hosting fully virtualized guest machines using hardware diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 75dfd27b6e8a..30f244b64523 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -7,12 +7,7 @@ ifeq ($(CONFIG_FRAME_POINTER),y) OBJECT_FILES_NON_STANDARD_vmenter.o := y endif -KVM := ../../../virt/kvm - -kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ - $(KVM)/dirty_ring.o $(KVM)/binary_stats.o -kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o +include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 07e9215e911d..0b920e12bb6d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -523,7 +523,7 @@ void kvm_set_cpu_caps(void) 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) | - F(TOPOEXT) | F(PERFCTR_CORE) + F(TOPOEXT) | 0 /* PERFCTR_CORE */ ); kvm_cpu_cap_mask(CPUID_8000_0001_EDX, diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 54a83a744538..543a8c04025c 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -107,9 +107,10 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + int bkt; + slots = __kvm_memslots(kvm, i); - for (j = 0; j < slots->used_slots; j++) { - slot = &slots->memslots[j]; + kvm_for_each_memslot(slot, bkt, slots) for (k = 0; k < KVM_NR_PAGE_SIZES; k++) { rmap = slot->arch.rmap[k]; lpage_size = kvm_mmu_slot_lpages(slot, k + 1); @@ -121,7 +122,6 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) cur[index]++; } } - } } write_unlock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5e19e6e4c2ce..6e38a7d22e97 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -164,7 +164,7 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (vpidx >= KVM_MAX_VCPUS) return NULL; @@ -1716,7 +1716,8 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( { struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; - int i, bank, sbank = 0; + int bank, sbank = 0; + unsigned long i; memset(vp_bitmap, 0, KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap)); @@ -1863,7 +1864,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, .vector = vector }; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) @@ -1922,11 +1923,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; + if (all_cpus) + goto check_and_send_ipi; + if (!sparse_banks_len) goto ret_success; - if (!all_cpus && - kvm_read_guest(kvm, + if (kvm_read_guest(kvm, hc->ingpa + offsetof(struct hv_send_ipi_ex, vp_set.bank_contents), sparse_banks, @@ -1934,6 +1937,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool return HV_STATUS_INVALID_HYPERCALL_INPUT; } +check_and_send_ipi: if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -2516,6 +2520,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; + if (evmcs_ver) + ent->eax |= HV_X64_NESTED_MSR_BITMAP; break; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 5a69cce4d72d..0b65a764ed3a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -242,7 +242,7 @@ static void pit_do_work(struct kthread_work *work) struct kvm_pit *pit = container_of(work, struct kvm_pit, expired); struct kvm *kvm = pit->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; struct kvm_kpit_state *ps = &pit->pit_state; if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0)) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 0b80263d46d8..814064d06016 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -50,7 +50,7 @@ static void pic_unlock(struct kvm_pic *s) { bool wakeup = s->wakeup_needed; struct kvm_vcpu *vcpu; - int i; + unsigned long i; s->wakeup_needed = false; @@ -270,7 +270,8 @@ int kvm_pic_read_irq(struct kvm *kvm) static void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, i; + int irq; + unsigned long i; struct kvm_vcpu *vcpu; u8 edge_irr = s->irr & ~s->elcr; bool found = false; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 816a82515dcd..decfa36b7891 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -149,7 +149,7 @@ void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; if (RTC_GSI >= IOAPIC_NUM_PINS) return; @@ -184,7 +184,7 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index e66e620c3bed..539333ac4b38 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -81,7 +81,6 @@ struct kvm_ioapic { unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; - void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; struct rtc_status rtc_status; struct delayed_work eoi_inject; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 650642b18d15..c2d7cfe82d00 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -56,7 +56,6 @@ struct kvm_pic { struct kvm_io_device dev_master; struct kvm_io_device dev_slave; struct kvm_io_device dev_elcr; - void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[PIC_NUM_PINS]; }; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index d5b72a08e566..39ad02d6dc63 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -45,9 +45,9 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map) { - int i, r = -1; + int r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) @@ -320,7 +320,8 @@ int kvm_set_routing_entry(struct kvm *kvm, bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { - int i, r = 0; + int r = 0; + unsigned long i; struct kvm_vcpu *vcpu; if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 90e1ffdc05b7..3febc342360c 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,6 +9,12 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) +#define X86_CR0_PDPTR_BITS (X86_CR0_CD | X86_CR0_NW | X86_CR0_PG) +#define X86_CR4_TLBFLUSH_BITS (X86_CR4_PGE | X86_CR4_PCIDE | X86_CR4_PAE | X86_CR4_SMEP) +#define X86_CR4_PDPTR_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP) + +static_assert(!(KVM_POSSIBLE_CR0_GUEST_BITS & X86_CR0_PDPTR_BITS)); + #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -37,6 +43,13 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif +/* + * avail dirty + * 0 0 register in VMCS/VMCB + * 0 1 *INVALID* + * 1 0 register in vcpu->arch + * 1 1 register in vcpu->arch, needs to be stored back + */ static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, enum kvm_reg reg) { @@ -55,13 +68,6 @@ static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); } -static inline void kvm_register_clear_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, enum kvm_reg reg) { diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index c7db2df50a7a..b469f45e3fe4 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -33,7 +33,8 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; - int ret = 0, i, nr_unique_valid_roots; + int ret = 0, nr_unique_valid_roots; + unsigned long i; hpa_t root; spin_lock(&kvm_arch->hv_root_tdp_lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 759952dd1222..c5028e6b0f96 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -185,7 +185,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; - int i; + unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ @@ -673,41 +673,40 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; } -static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) -{ - u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) { - printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return false; - } - return val & KVM_PV_EOI_ENABLED; -} - static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) { - printk(KERN_WARNING "Can't set EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) return; - } + __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) +static bool pv_eoi_test_and_clr_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) { - printk(KERN_WARNING "Can't clear EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return; - } + u8 val; + + if (pv_eoi_get_user(vcpu, &val) < 0) + return false; + + val &= KVM_PV_EOI_ENABLED; + + if (val && pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) + return false; + + /* + * Clear pending bit in any case: it will be set again on vmentry. + * While this might not be ideal from performance point of view, + * this makes sure pv eoi is only enabled when we know it's safe. + */ __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); + + return val; } static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; - if (apic->vcpu->arch.apicv_active) + if (kvm_x86_ops.sync_pir_to_irr) highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); @@ -1101,6 +1100,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); } break; @@ -1172,8 +1174,8 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_lapic *src = NULL; struct kvm_apic_map *map; struct kvm_vcpu *vcpu; - unsigned long bitmap; - int i, vcpu_idx; + unsigned long bitmap, i; + int vcpu_idx; bool ret; rcu_read_lock(); @@ -1931,7 +1933,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; - WARN_ON(rcuwait_active(&vcpu->wait)); + WARN_ON(kvm_vcpu_is_blocking(vcpu)); apic_timer_expired(apic, false); cancel_hv_timer(apic); @@ -2677,7 +2679,6 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, struct kvm_lapic *apic) { - bool pending; int vector; /* * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host @@ -2691,14 +2692,8 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, * -> host enabled PV EOI, guest executed EOI. */ BUG_ON(!pv_eoi_enabled(vcpu)); - pending = pv_eoi_get_pending(vcpu); - /* - * Clear pending bit in any case: it will be set again on vmentry. - * While this might not be ideal from performance point of view, - * this makes sure pv eoi is only enabled when we know it's safe. - */ - pv_eoi_clr_pending(vcpu); - if (pending) + + if (pv_eoi_test_and_clr_pending(vcpu)) return; vector = apic_set_eoi(apic); trace_kvm_pv_eoi(apic, vector); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9ae6168d381e..e9fbb2c8bbe2 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -71,7 +71,8 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, unsigned long cr4, u64 efer, gpa_t nested_cr3); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp); + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); @@ -351,4 +352,17 @@ static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count) { atomic64_add(count, &kvm->stat.pages[level - 1]); } + +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, + struct x86_exception *exception); + +static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, + gpa_t gpa, u32 access, + struct x86_exception *exception) +{ + if (mmu != &vcpu->arch.nested_mmu) + return gpa; + return translate_nested_gpa(vcpu, gpa, access, exception); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 3be9beea838d..1d275e9d76b5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -335,12 +335,6 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) return likely(kvm_gen == spte_gen); } -static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception) -{ - return gpa; -} - static int is_cpuid_PSE36(void) { return 1; @@ -1454,7 +1448,7 @@ static bool kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, { u64 *sptep; struct rmap_iterator iter; - int need_flush = 0; + bool need_flush = false; u64 new_spte; kvm_pfn_t new_pfn; @@ -1466,7 +1460,7 @@ restart: rmap_printk("spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); - need_flush = 1; + need_flush = true; if (pte_write(pte)) { pte_list_remove(kvm, rmap_head, sptep); @@ -1482,7 +1476,7 @@ restart: if (need_flush && kvm_available_flush_tlb_with_range()) { kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); - return 0; + return false; } return need_flush; @@ -1582,7 +1576,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); if (is_tdp_mmu_enabled(kvm)) - flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; } @@ -1623,8 +1617,8 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, for_each_rmap_spte(rmap_head, &iter, sptep) if (is_accessed_spte(*sptep)) - return 1; - return 0; + return true; + return false; } #define RMAP_RECYCLE_THRESHOLD 1000 @@ -1936,7 +1930,11 @@ static void mmu_audit_disable(void) { } static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { - return sp->role.invalid || + if (sp->role.invalid) + return true; + + /* TDP MMU pages due not use the MMU generation. */ + return !sp->tdp_mmu_page && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2082,10 +2080,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = direct; - if (role.direct) - role.gpte_is_8_bytes = true; role.access = access; - if (!direct_mmu && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) { + if (role.has_4_byte_gpte) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; @@ -2173,10 +2169,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato iterator->shadow_addr = root; iterator->level = vcpu->arch.mmu->shadow_root_level; - if (iterator->level == PT64_ROOT_4LEVEL && + if (iterator->level >= PT64_ROOT_4LEVEL && vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL && !vcpu->arch.mmu->direct_map) - --iterator->level; + iterator->level = PT32E_ROOT_LEVEL; if (iterator->level == PT32E_ROOT_LEVEL) { /* @@ -2561,10 +2557,10 @@ static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) return r; } -static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); - ++vcpu->kvm->stat.mmu_unsync; + ++kvm->stat.mmu_unsync; sp->unsync = 1; kvm_mmu_mark_parents_unsync(sp); @@ -2576,7 +2572,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must * be write-protected. */ -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch) { struct kvm_mmu_page *sp; @@ -2587,7 +2583,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_slot_page_track_is_active(vcpu, slot, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE)) return -EPERM; /* @@ -2596,7 +2592,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * that case, KVM must complete emulation of the guest TLB flush before * allowing shadow pages to become unsync (writable by the guest). */ - for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { + for_each_gfn_indirect_valid_sp(kvm, sp, gfn) { if (!can_unsync) return -EPERM; @@ -2615,7 +2611,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, */ if (!locked) { locked = true; - spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_lock(&kvm->arch.mmu_unsync_pages_lock); /* * Recheck after taking the spinlock, a different vCPU @@ -2630,10 +2626,10 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } WARN_ON(sp->role.level != PG_LEVEL_4K); - kvm_unsync_page(vcpu, sp); + kvm_unsync_page(kvm, sp); } if (locked) - spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_unlock(&kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -3405,7 +3401,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; - int r = 0, i; + int r = 0, i, bkt; /* * Check if this is the first shadow root being allocated before @@ -3430,7 +3426,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + kvm_for_each_memslot(slot, bkt, slots) { /* * Both of these functions are no-ops if the target is * already allocated, so unconditionally calling both @@ -3730,21 +3726,13 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu) kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); } -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, struct x86_exception *exception) -{ - if (exception) - exception->error_code = 0; - return vaddr; -} - -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, - struct x86_exception *exception) +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t vaddr, u32 access, + struct x86_exception *exception) { if (exception) exception->error_code = 0; - return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); + return kvm_translate_gpa(vcpu, mmu, vaddr, access, exception); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) @@ -3884,7 +3872,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_slot_page_track_is_active(vcpu, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) return true; return false; @@ -3976,6 +3964,34 @@ out_retry: return true; } +/* + * Returns true if the page fault is stale and needs to be retried, i.e. if the + * root was invalidated by a memslot update or a relevant mmu_notifier fired. + */ +static bool is_page_fault_stale(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, int mmu_seq) +{ + struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa); + + /* Special roots, e.g. pae_root, are not backed by shadow pages. */ + if (sp && is_obsolete_sp(vcpu->kvm, sp)) + return true; + + /* + * Roots without an associated shadow page are considered invalid if + * there is a pending request to free obsolete roots. The request is + * only a hint that the current root _may_ be obsolete and needs to be + * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a + * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs + * to reload even if no vCPU is actively using the root. + */ + if (!sp && kvm_test_request(KVM_REQ_MMU_RELOAD, vcpu)) + return true; + + return fault->slot && + mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva); +} + static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); @@ -4013,8 +4029,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; + r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; @@ -4355,22 +4372,28 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, bool execonly) + u64 pa_bits_rsvd, bool execonly, int huge_page_level) { u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); + u64 large_1g_rsvd = 0, large_2m_rsvd = 0; u64 bad_mt_xwr; + if (huge_page_level < PG_LEVEL_1G) + large_1g_rsvd = rsvd_bits(7, 7); + if (huge_page_level < PG_LEVEL_2M) + large_2m_rsvd = rsvd_bits(7, 7); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7); rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* large page */ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29); - rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20); + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ @@ -4386,10 +4409,11 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, } static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, bool execonly) + struct kvm_mmu *context, bool execonly, int huge_page_level) { __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, - vcpu->arch.reserved_gpa_bits, execonly); + vcpu->arch.reserved_gpa_bits, execonly, + huge_page_level); } static inline u64 reserved_hpa_bits(void) @@ -4465,7 +4489,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, false, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - reserved_hpa_bits(), false); + reserved_hpa_bits(), false, + max_huge_page_level); if (!shadow_me_mask) return; @@ -4485,7 +4510,8 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - reserved_hpa_bits(), execonly); + reserved_hpa_bits(), execonly, + max_huge_page_level); } #define BYTE_MASK(access) \ @@ -4734,7 +4760,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_mmu_get_tdp_level(vcpu); role.base.direct = true; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; return role; } @@ -4779,7 +4805,7 @@ kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu, role.base.smep_andnot_wp = role.ext.cr4_smep && !____is_cr0_wp(regs); role.base.smap_andnot_wp = role.ext.cr4_smap && !____is_cr0_wp(regs); - role.base.gpte_is_8_bytes = ____is_cr0_pg(regs) && ____is_cr4_pae(regs); + role.base.has_4_byte_gpte = ____is_cr0_pg(regs) && !____is_cr4_pae(regs); return role; } @@ -4855,7 +4881,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, struct kvm_mmu *context = &vcpu->arch.guest_mmu; struct kvm_mmu_role_regs regs = { .cr0 = cr0, - .cr4 = cr4, + .cr4 = cr4 & ~X86_CR4_PKE, .efer = efer, }; union kvm_mmu_role new_role; @@ -4878,7 +4904,7 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; role.base.level = level; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; @@ -4893,7 +4919,8 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, } void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp) + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp) { struct kvm_mmu *context = &vcpu->arch.guest_mmu; u8 level = vmx_eptp_page_walk_level(new_eptp); @@ -4919,8 +4946,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->direct_map = false; update_permission_bitmask(context, true); - update_pkru_bitmask(context); - reset_rsvds_bits_mask_ept(vcpu, context, execonly); + context->pkru_mask = 0; + reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); @@ -4984,13 +5011,13 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) - g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; + g_context->gva_to_gpa = nonpaging_gva_to_gpa; else if (is_long_mode(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else if (is_pae(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else - g_context->gva_to_gpa = paging32_gva_to_gpa_nested; + g_context->gva_to_gpa = paging32_gva_to_gpa; reset_guest_paging_metadata(vcpu, g_context); } @@ -5025,6 +5052,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) /* * Invalidate all MMU roles to force them to reinitialize as CPUID * information is factored into reserved bit calculations. + * + * Correctly handling multiple vCPU models with respect to paging and + * physical address properties) in a single VM would require tracking + * all relevant CPUID information in kvm_mmu_page_role. That is very + * undesirable as it would increase the memory requirements for + * gfn_track (see struct kvm_mmu_page_role comments). For now that + * problem is swept under the rug; KVM's CPUID API is horrific and + * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.mmu_role.ext.valid = 0; vcpu->arch.guest_mmu.mmu_role.ext.valid = 0; @@ -5032,24 +5067,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); /* - * KVM does not correctly handle changing guest CPUID after KVM_RUN, as - * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't - * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page - * faults due to reusing SPs/SPTEs. Alert userspace, but otherwise - * sweep the problem under the rug. - * - * KVM's horrific CPUID ABI makes the problem all but impossible to - * solve, as correctly handling multiple vCPU models (with respect to - * paging and physical address properties) in a single VM would require - * tracking all relevant CPUID information in kvm_mmu_page_role. That - * is very undesirable as it would double the memory requirements for - * gfn_track (see struct kvm_mmu_page_role comments), and in practice - * no sane VMM mucks with the core vCPU model on the fly. + * Changing guest CPUID after KVM_RUN is forbidden, see the comment in + * kvm_arch_vcpu_ioctl(). */ - if (vcpu->arch.last_vmentry_cpu != -1) { - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n"); - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n"); - } + KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm); } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) @@ -5161,7 +5182,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, gpa, bytes, sp->role.word); offset = offset_in_page(gpa); - pte_size = sp->role.gpte_is_8_bytes ? 8 : 4; + pte_size = sp->role.has_4_byte_gpte ? 4 : 8; /* * Sometimes, the OS only writes the last one bytes to update status @@ -5185,7 +5206,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; - if (!sp->role.gpte_is_8_bytes) { + if (sp->role.has_4_byte_gpte) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -5369,7 +5390,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE); + kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); @@ -5497,10 +5518,13 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root_hpa = INVALID_PAGE; mmu->root_pgd = 0; - mmu->translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + /* vcpu->arch.guest_mmu isn't used when !tdp_enabled. */ + if (!tdp_enabled && mmu == &vcpu->arch.guest_mmu) + return 0; + /* * When using PAE paging, the four PDPTEs are treated as 'root' pages, * while the PDP table is a per-vCPU construct that's allocated at MMU @@ -5510,7 +5534,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) * generally doesn't use PAE paging and can skip allocating the PDP * table. The main exception, handled here, is SVM's 32-bit NPT. The * other exception is for shadowing L1's 32-bit or PAE NPT on 64-bit - * KVM; that horror is handled on-demand by mmu_alloc_shadow_roots(). + * KVM; that horror is handled on-demand by mmu_alloc_special_roots(). */ if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; @@ -5555,8 +5579,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; - vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; - ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu); if (ret) return ret; @@ -5715,6 +5737,7 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { const struct kvm_memory_slot *memslot; struct kvm_memslots *slots; + struct kvm_memslot_iter iter; bool flush = false; gfn_t start, end; int i; @@ -5724,10 +5747,12 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { + + kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { + memslot = iter.slot; start = max(gfn_start, memslot->base_gfn); end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) + if (WARN_ON_ONCE(start >= end)) continue; flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, @@ -5748,6 +5773,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) bool flush; int i; + if (WARN_ON_ONCE(gfn_end <= gfn_start)) + return; + write_lock(&kvm->mmu_lock); kvm_inc_notifier_count(kvm, gfn_start, gfn_end); @@ -5854,8 +5882,6 @@ restart: void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); /* @@ -5863,17 +5889,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, * logging at a 4k granularity and never creates collapsible * 2m SPTEs during dirty logging. */ - flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true); - if (flush) + if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true)) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush); - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); + kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); read_unlock(&kvm->mmu_lock); } } @@ -6142,30 +6165,6 @@ out: return ret; } -/* - * Calculate mmu pages needed for kvm. - */ -unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) -{ - unsigned long nr_mmu_pages; - unsigned long nr_pages = 0; - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - int i; - - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - - kvm_for_each_memslot(memslot, slots) - nr_pages += memslot->npages; - } - - nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); - - return nr_mmu_pages; -} - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); @@ -6182,23 +6181,46 @@ void kvm_mmu_module_exit(void) mmu_audit_disable(); } +/* + * Calculate the effective recovery period, accounting for '0' meaning "let KVM + * select a halving time of 1 hour". Returns true if recovery is enabled. + */ +static bool calc_nx_huge_pages_recovery_period(uint *period) +{ + /* + * Use READ_ONCE to get the params, this may be called outside of the + * param setters, e.g. by the kthread to compute its next timeout. + */ + bool enabled = READ_ONCE(nx_huge_pages); + uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + + if (!enabled || !ratio) + return false; + + *period = READ_ONCE(nx_huge_pages_recovery_period_ms); + if (!*period) { + /* Make sure the period is not less than one second. */ + ratio = min(ratio, 3600u); + *period = 60 * 60 * 1000 / ratio; + } + return true; +} + static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp) { bool was_recovery_enabled, is_recovery_enabled; uint old_period, new_period; int err; - was_recovery_enabled = nx_huge_pages_recovery_ratio; - old_period = nx_huge_pages_recovery_period_ms; + was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); if (err) return err; - is_recovery_enabled = nx_huge_pages_recovery_ratio; - new_period = nx_huge_pages_recovery_period_ms; + is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period); - if (READ_ONCE(nx_huge_pages) && is_recovery_enabled && + if (is_recovery_enabled && (!was_recovery_enabled || old_period > new_period)) { struct kvm *kvm; @@ -6262,18 +6284,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) static long get_nx_lpage_recovery_timeout(u64 start_time) { - uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); - uint period = READ_ONCE(nx_huge_pages_recovery_period_ms); + bool enabled; + uint period; - if (!period && ratio) { - /* Make sure the period is not less than one second. */ - ratio = min(ratio, 3600u); - period = 60 * 60 * 1000 / ratio; - } + enabled = calc_nx_huge_pages_recovery_period(&period); - return READ_ONCE(nx_huge_pages) && ratio - ? start_time + msecs_to_jiffies(period) - get_jiffies_64() - : MAX_SCHEDULE_TIMEOUT; + return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; } static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 52c6527b1a06..da6166b5c377 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -104,7 +104,7 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } -static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* * When using the EPT page-modification log, the GPAs in the CPU dirty @@ -112,13 +112,12 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) * on write protection to record dirty pages, which bypasses PML, since * writes now result in a vmexit. Note, the check on CPU dirty logging * being enabled is mandatory as the bits used to denote WP-only SPTEs - * are reserved for NPT w/ PAE (32-bit KVM). + * are reserved for PAE paging (32-bit KVM). */ - return vcpu->arch.mmu == &vcpu->arch.guest_mmu && - kvm_x86_ops.cpu_dirty_log_size; + return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index b8151bbca36a..de5e8e4e1aa7 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -35,7 +35,7 @@ " %snxe %sad root %u %s%c", \ __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ - role.gpte_is_8_bytes ? 8 : 4, \ + role.has_4_byte_gpte ? 4 : 8, \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index cc4eb5b7fb76..68eb1fb548b6 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -173,9 +173,9 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); /* * check if the corresponding access on the specified guest page is tracked. */ -bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +bool kvm_slot_page_track_is_active(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode) { int index; @@ -186,7 +186,7 @@ bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, return false; if (mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(vcpu->kvm)) + !kvm_page_track_write_tracking_enabled(kvm)) return false; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f87d36898c44..5b5bdac97c7b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -403,9 +403,8 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), - nested_access, - &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(table_gfn), + nested_access, &walker->fault); /* * FIXME: This can happen if emulation (for of an INS/OUTS @@ -467,7 +466,7 @@ retry_walk: if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36()) gfn += pse36_gfn_delta(pte); - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault); if (real_gpa == UNMAPPED_GVA) return 0; @@ -547,16 +546,6 @@ static int FNAME(walk_addr)(struct guest_walker *walker, access); } -#if PTTYPE != PTTYPE_EPT -static int FNAME(walk_addr_nested)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, - u32 access) -{ - return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu, - addr, access); -} -#endif - static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, pt_element_t gpte, bool no_dirty_log) @@ -911,7 +900,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); @@ -999,50 +989,29 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) } /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, addr, access); - - if (r) { - gpa = gfn_to_gpa(walker.gfn); - gpa |= addr & ~PAGE_MASK; - } else if (exception) - *exception = walker.fault; - - return gpa; -} - -#if PTTYPE != PTTYPE_EPT -/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, - struct x86_exception *exception) -{ - struct guest_walker walker; - gpa_t gpa = UNMAPPED_GVA; - int r; - #ifndef CONFIG_X86_64 /* A 64-bit GVA should be impossible on 32-bit KVM. */ - WARN_ON_ONCE(vaddr >> 32); + WARN_ON_ONCE((addr >> 32) && mmu == vcpu->arch.walk_mmu); #endif - r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr_generic)(&walker, vcpu, mmu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; return gpa; } -#endif /* * Using the cached information from sp->gfns is safe because: diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 0c76c45fdb68..8a7b03207762 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,7 +90,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte) @@ -101,7 +101,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (sp->role.ad_disabled) spte |= SPTE_TDP_AD_DISABLED_MASK; - else if (kvm_vcpu_ad_need_write_protect(vcpu)) + else if (kvm_mmu_page_ad_need_write_protect(sp)) spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; /* @@ -161,7 +161,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * e.g. it's write-tracked (upper-level SPs) or has one or more * shadow pages and unsync'ing pages is not allowed. */ - if (mmu_try_to_unsync_pages(vcpu, slot, gfn, can_unsync, prefetch)) { + if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) { pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); wrprot = true; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index cc432f9a966b..a4af2a42695c 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -330,7 +330,7 @@ static inline u64 get_mmio_spte_generation(u64 spte) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte); diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index b3ed302c1a35..caa96c270b95 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -26,6 +26,7 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level) */ void tdp_iter_restart(struct tdp_iter *iter) { + iter->yielded = false; iter->yielded_gfn = iter->next_last_level_gfn; iter->level = iter->root_level; @@ -160,6 +161,11 @@ static bool try_step_up(struct tdp_iter *iter) */ void tdp_iter_next(struct tdp_iter *iter) { + if (iter->yielded) { + tdp_iter_restart(iter); + return; + } + if (try_step_down(iter)) return; diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index b1748b988d3a..e19cabbcb65c 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -45,6 +45,12 @@ struct tdp_iter { * iterator walks off the end of the paging structure. */ bool valid; + /* + * True if KVM dropped mmu_lock and yielded in the middle of a walk, in + * which case tdp_iter_next() needs to restart the walk at the root + * level instead of advancing to the next entry. + */ + bool yielded; }; /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index a54c3491af42..7b1bc816b7c3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -165,7 +165,7 @@ static union kvm_mmu_page_role page_role_for_level(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = true; - role.gpte_is_8_bytes = true; + role.has_4_byte_gpte = false; role.access = ACC_ALL; role.ad_disabled = !shadow_accessed_mask; @@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt)); int level = sp->role.level; gfn_t base_gfn = sp->gfn; - u64 old_child_spte; - u64 *sptep; - gfn_t gfn; int i; trace_kvm_mmu_prepare_zap_page(sp); @@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, tdp_mmu_unlink_page(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - sptep = rcu_dereference(pt) + i; - gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 *sptep = rcu_dereference(pt) + i; + gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 old_child_spte; if (shared) { /* @@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, shared); } - kvm_flush_remote_tlbs_with_address(kvm, gfn, + kvm_flush_remote_tlbs_with_address(kvm, base_gfn, KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -504,6 +502,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { + WARN_ON_ONCE(iter->yielded); + lockdep_assert_held_read(&kvm->mmu_lock); /* @@ -577,6 +577,8 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte, bool record_acc_track, bool record_dirty_log) { + WARN_ON_ONCE(iter->yielded); + lockdep_assert_held_write(&kvm->mmu_lock); /* @@ -642,18 +644,19 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm, * If this function should yield and flush is set, it will perform a remote * TLB flush before yielding. * - * If this function yields, it will also reset the tdp_iter's walk over the - * paging structure and the calling function should skip to the next - * iteration to allow the iterator to continue its traversal from the - * paging structure root. + * If this function yields, iter->yielded is set and the caller must skip to + * the next iteration, where tdp_iter_next() will reset the tdp_iter's walk + * over the paging structures to allow the iterator to continue its traversal + * from the paging structure root. * - * Return true if this function yielded and the iterator's traversal was reset. - * Return false if a yield was not needed. + * Returns true if this function yielded. */ -static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, - struct tdp_iter *iter, bool flush, - bool shared) +static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, + struct tdp_iter *iter, + bool flush, bool shared) { + WARN_ON(iter->yielded); + /* Ensure forward progress has been made before yielding. */ if (iter->next_last_level_gfn == iter->yielded_gfn) return false; @@ -673,12 +676,10 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, WARN_ON(iter->gfn > iter->next_last_level_gfn); - tdp_iter_restart(iter); - - return true; + iter->yielded = true; } - return false; + return iter->yielded; } /* @@ -1033,9 +1034,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root(kvm, root, range->slot->as_id) - flush |= zap_gfn_range(kvm, root, range->start, range->end, - range->may_block, flush, false); + for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + flush = zap_gfn_range(kvm, root, range->start, range->end, + range->may_block, flush, false); return flush; } @@ -1364,10 +1365,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, * Clear leaf entries which could be replaced by large mappings, for * GFNs within the slot. */ -static bool zap_collapsible_spte_range(struct kvm *kvm, +static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, - const struct kvm_memory_slot *slot, - bool flush) + const struct kvm_memory_slot *slot) { gfn_t start = slot->base_gfn; gfn_t end = start + slot->npages; @@ -1378,10 +1378,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm, tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) { - flush = false; + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - } if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) @@ -1393,6 +1391,7 @@ retry: pfn, PG_LEVEL_NUM)) continue; + /* Note, a successful atomic zap also does a remote TLB flush. */ if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) { /* * The iter must explicitly re-read the SPTE because @@ -1401,30 +1400,24 @@ retry: iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep)); goto retry; } - flush = true; } rcu_read_unlock(); - - return flush; } /* * Clear non-leaf entries (and free associated page tables) which could * be replaced by large mappings, for GFNs within the slot. */ -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush) +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot) { struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) - flush = zap_collapsible_spte_range(kvm, root, slot, flush); - - return flush; + zap_collapsible_spte_range(kvm, root, slot); } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 476b133544dd..3899004a5d91 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, unsigned long mask, bool wrprot); -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush); +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index affc0ea98d30..0e5b49294086 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -293,7 +293,7 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, source, @@ -675,10 +675,18 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) smp_mb__after_atomic(); if (avic_vcpu_is_running(vcpu)) { - int cpuid = vcpu->cpu; + int cpu = READ_ONCE(vcpu->cpu); - if (cpuid != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); + /* + * Note, the vCPU could get migrated to a different pCPU at any + * point, which could result in signalling the wrong/previous + * pCPU. But if that happens the vCPU is guaranteed to do a + * VMRUN (after being migrated) and thus will process pending + * interrupts, i.e. a doorbell is not needed (and the spurious + * one is harmless). + */ + if (cpu != get_cpu()) + wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); put_cpu(); } else kvm_vcpu_wake_up(vcpu); @@ -900,6 +908,7 @@ out: bool svm_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | @@ -989,16 +998,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) { struct vcpu_svm *svm = to_svm(vcpu); + int cpu = get_cpu(); + WARN_ON(cpu != vcpu->cpu); svm->avic_is_running = is_run; - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - if (is_run) - avic_vcpu_load(vcpu, vcpu->cpu); - else - avic_vcpu_put(vcpu); + if (kvm_vcpu_apicv_active(vcpu)) { + if (is_run) + avic_vcpu_load(vcpu, cpu); + else + avic_vcpu_put(vcpu); + } + put_cpu(); } void svm_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index f8b7bc04b3e7..cf206855ebf0 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -58,8 +58,9 @@ static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_excep struct vcpu_svm *svm = to_svm(vcpu); WARN_ON(!is_guest_mode(vcpu)); - if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && - !svm->nested.nested_run_pending) { + if (vmcb12_is_intercept(&svm->nested.ctl, + INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && + !svm->nested.nested_run_pending) { svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = fault->error_code; @@ -121,7 +122,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) void recalc_intercepts(struct vcpu_svm *svm) { - struct vmcb_control_area *c, *h, *g; + struct vmcb_control_area *c, *h; + struct vmcb_ctrl_area_cached *g; unsigned int i; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -163,37 +165,6 @@ void recalc_intercepts(struct vcpu_svm *svm) vmcb_set_intercept(c, INTERCEPT_VMSAVE); } -static void copy_vmcb_control_area(struct vmcb_control_area *dst, - struct vmcb_control_area *from) -{ - unsigned int i; - - for (i = 0; i < MAX_INTERCEPT; i++) - dst->intercepts[i] = from->intercepts[i]; - - dst->iopm_base_pa = from->iopm_base_pa; - dst->msrpm_base_pa = from->msrpm_base_pa; - dst->tsc_offset = from->tsc_offset; - /* asid not copied, it is handled manually for svm->vmcb. */ - dst->tlb_ctl = from->tlb_ctl; - dst->int_ctl = from->int_ctl; - dst->int_vector = from->int_vector; - dst->int_state = from->int_state; - dst->exit_code = from->exit_code; - dst->exit_code_hi = from->exit_code_hi; - dst->exit_info_1 = from->exit_info_1; - dst->exit_info_2 = from->exit_info_2; - dst->exit_int_info = from->exit_int_info; - dst->exit_int_info_err = from->exit_int_info_err; - dst->nested_ctl = from->nested_ctl; - dst->event_inj = from->event_inj; - dst->event_inj_err = from->event_inj_err; - dst->nested_cr3 = from->nested_cr3; - dst->virt_ext = from->virt_ext; - dst->pause_filter_count = from->pause_filter_count; - dst->pause_filter_thresh = from->pause_filter_thresh; -} - static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { /* @@ -203,7 +174,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) */ int i; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; for (i = 0; i < MSRPM_OFFSETS; i++) { @@ -250,10 +221,10 @@ static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) } } -static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, - struct vmcb_control_area *control) +static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, + struct vmcb_ctrl_area_cached *control) { - if (CC(!vmcb_is_intercept(control, INTERCEPT_VMRUN))) + if (CC(!vmcb12_is_intercept(control, INTERCEPT_VMRUN))) return false; if (CC(control->asid == 0)) @@ -275,9 +246,20 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, return true; } -static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +/* Common checks that apply to both L1 and L2 state. */ +static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, + struct vmcb_save_area_cached *save) { + if (CC(!(save->efer & EFER_SVME))) + return false; + + if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || + CC(save->cr0 & ~0xffffffffULL)) + return false; + + if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) + return false; + /* * These checks are also performed by KVM_SET_SREGS, * except that EFER.LMA is not checked by SVM against @@ -293,48 +275,90 @@ static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, if (CC(!kvm_is_valid_cr4(vcpu, save->cr4))) return false; + if (CC(!kvm_valid_efer(vcpu, save->efer))) + return false; + return true; } -/* Common checks that apply to both L1 and L2 state. */ -static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +static bool nested_vmcb_check_save(struct kvm_vcpu *vcpu) { - /* - * FIXME: these should be done after copying the fields, - * to avoid TOC/TOU races. For these save area checks - * the possible damage is limited since kvm_set_cr0 and - * kvm_set_cr4 handle failure; EFER_SVME is an exception - * so it is force-set later in nested_prepare_vmcb_save. - */ - if (CC(!(save->efer & EFER_SVME))) - return false; + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_save_area_cached *save = &svm->nested.save; - if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || - CC(save->cr0 & ~0xffffffffULL)) - return false; + return __nested_vmcb_check_save(vcpu, save); +} - if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) - return false; +static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_ctrl_area_cached *ctl = &svm->nested.ctl; - if (!nested_vmcb_check_cr3_cr4(vcpu, save)) - return false; + return __nested_vmcb_check_controls(vcpu, ctl); +} - if (CC(!kvm_valid_efer(vcpu, save->efer))) - return false; +static +void __nested_copy_vmcb_control_to_cache(struct vmcb_ctrl_area_cached *to, + struct vmcb_control_area *from) +{ + unsigned int i; - return true; + for (i = 0; i < MAX_INTERCEPT; i++) + to->intercepts[i] = from->intercepts[i]; + + to->iopm_base_pa = from->iopm_base_pa; + to->msrpm_base_pa = from->msrpm_base_pa; + to->tsc_offset = from->tsc_offset; + to->tlb_ctl = from->tlb_ctl; + to->int_ctl = from->int_ctl; + to->int_vector = from->int_vector; + to->int_state = from->int_state; + to->exit_code = from->exit_code; + to->exit_code_hi = from->exit_code_hi; + to->exit_info_1 = from->exit_info_1; + to->exit_info_2 = from->exit_info_2; + to->exit_int_info = from->exit_int_info; + to->exit_int_info_err = from->exit_int_info_err; + to->nested_ctl = from->nested_ctl; + to->event_inj = from->event_inj; + to->event_inj_err = from->event_inj_err; + to->nested_cr3 = from->nested_cr3; + to->virt_ext = from->virt_ext; + to->pause_filter_count = from->pause_filter_count; + to->pause_filter_thresh = from->pause_filter_thresh; + + /* Copy asid here because nested_vmcb_check_controls will check it. */ + to->asid = from->asid; + to->msrpm_base_pa &= ~0x0fffULL; + to->iopm_base_pa &= ~0x0fffULL; } -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control) +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control) { - copy_vmcb_control_area(&svm->nested.ctl, control); + __nested_copy_vmcb_control_to_cache(&svm->nested.ctl, control); +} + +static void __nested_copy_vmcb_save_to_cache(struct vmcb_save_area_cached *to, + struct vmcb_save_area *from) +{ + /* + * Copy only fields that are validated, as we need them + * to avoid TOC/TOU races. + */ + to->efer = from->efer; + to->cr0 = from->cr0; + to->cr3 = from->cr3; + to->cr4 = from->cr4; - /* Copy it here because nested_svm_check_controls will check it. */ - svm->nested.ctl.asid = control->asid; - svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL; - svm->nested.ctl.iopm_base_pa &= ~0x0fffULL; + to->dr6 = from->dr6; + to->dr7 = from->dr7; +} + +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save) +{ + __nested_copy_vmcb_save_to_cache(&svm->nested.save, save); } /* @@ -437,14 +461,13 @@ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, return -EINVAL; if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) + CC(!load_pdptrs(vcpu, cr3))) return -EINVAL; if (!nested_npt) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -490,15 +513,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - /* - * Force-set EFER_SVME even though it is checked earlier on the - * VMCB12, because the guest can flip the bit between the check - * and now. Clearing EFER_SVME would call svm_free_nested. - */ - svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_efer(&svm->vcpu, svm->nested.save.efer); - svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); - svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); + svm_set_cr0(&svm->vcpu, svm->nested.save.cr0); + svm_set_cr4(&svm->vcpu, svm->nested.save.cr4); svm->vcpu.arch.cr2 = vmcb12->save.cr2; @@ -513,8 +531,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 /* These bits will be set properly on the first execution when new_vmc12 is true */ if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) { - svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1; - svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_ACTIVE_LOW; + svm->vmcb->save.dr7 = svm->nested.save.dr7 | DR7_FIXED_1; + svm->vcpu.arch.dr6 = svm->nested.save.dr6 | DR6_ACTIVE_LOW; vmcb_mark_dirty(svm->vmcb, VMCB_DR); } } @@ -628,7 +646,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_control(svm); nested_vmcb02_prepare_save(svm, vmcb12); - ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, + ret = nested_svm_load_cr3(&svm->vcpu, svm->nested.save.cr3, nested_npt_enabled(svm), from_vmrun); if (ret) return ret; @@ -678,10 +696,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_valid_sregs(vcpu, &vmcb12->save) || - !nested_vmcb_check_controls(vcpu, &svm->nested.ctl)) { + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_code_hi = 0; vmcb12->control.exit_info_1 = 0; @@ -988,7 +1007,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) u32 offset, msr, value; int write, mask; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return NESTED_EXIT_HOST; msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; @@ -1015,7 +1034,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) u8 start_bit; u64 gpa; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) return NESTED_EXIT_HOST; port = svm->vmcb->control.exit_info_1 >> 16; @@ -1046,12 +1065,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) vmexit = nested_svm_intercept_ioio(svm); break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } @@ -1069,7 +1088,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) break; } default: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; } } @@ -1147,7 +1166,7 @@ static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) static inline bool nested_exit_on_init(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); } static int svm_check_nested_events(struct kvm_vcpu *vcpu) @@ -1251,11 +1270,47 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); } +/* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ +static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst, + struct vmcb_ctrl_area_cached *from) +{ + unsigned int i; + + memset(dst, 0, sizeof(struct vmcb_control_area)); + + for (i = 0; i < MAX_INTERCEPT; i++) + dst->intercepts[i] = from->intercepts[i]; + + dst->iopm_base_pa = from->iopm_base_pa; + dst->msrpm_base_pa = from->msrpm_base_pa; + dst->tsc_offset = from->tsc_offset; + dst->asid = from->asid; + dst->tlb_ctl = from->tlb_ctl; + dst->int_ctl = from->int_ctl; + dst->int_vector = from->int_vector; + dst->int_state = from->int_state; + dst->exit_code = from->exit_code; + dst->exit_code_hi = from->exit_code_hi; + dst->exit_info_1 = from->exit_info_1; + dst->exit_info_2 = from->exit_info_2; + dst->exit_int_info = from->exit_int_info; + dst->exit_int_info_err = from->exit_int_info_err; + dst->nested_ctl = from->nested_ctl; + dst->event_inj = from->event_inj; + dst->event_inj_err = from->event_inj_err; + dst->nested_cr3 = from->nested_cr3; + dst->virt_ext = from->virt_ext; + dst->pause_filter_count = from->pause_filter_count; + dst->pause_filter_thresh = from->pause_filter_thresh; +} + static int svm_get_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, u32 user_data_size) { struct vcpu_svm *svm; + struct vmcb_control_area *ctl; + unsigned long r; struct kvm_nested_state kvm_state = { .flags = 0, .format = KVM_STATE_NESTED_FORMAT_SVM, @@ -1297,9 +1352,18 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu, */ if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE)) return -EFAULT; - if (copy_to_user(&user_vmcb->control, &svm->nested.ctl, - sizeof(user_vmcb->control))) + + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return -ENOMEM; + + nested_copy_vmcb_cache_to_control(ctl, &svm->nested.ctl); + r = copy_to_user(&user_vmcb->control, ctl, + sizeof(user_vmcb->control)); + kfree(ctl); + if (r) return -EFAULT; + if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save, sizeof(user_vmcb->save))) return -EFAULT; @@ -1316,6 +1380,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, &user_kvm_nested_state->data.svm[0]; struct vmcb_control_area *ctl; struct vmcb_save_area *save; + struct vmcb_save_area_cached save_cached; + struct vmcb_ctrl_area_cached ctl_cached; unsigned long cr0; int ret; @@ -1368,7 +1434,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, goto out_free; ret = -EINVAL; - if (!nested_vmcb_check_controls(vcpu, ctl)) + __nested_copy_vmcb_control_to_cache(&ctl_cached, ctl); + if (!__nested_vmcb_check_controls(vcpu, &ctl_cached)) goto out_free; /* @@ -1383,10 +1450,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * Validate host state saved from before VMRUN (see * nested_svm_check_permissions). */ + __nested_copy_vmcb_save_to_cache(&save_cached, save); if (!(save->cr0 & X86_CR0_PG) || !(save->cr0 & X86_CR0_PE) || (save->rflags & X86_EFLAGS_VM) || - !nested_vmcb_valid_sregs(vcpu, save)) + !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; /* @@ -1422,7 +1490,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); - nested_load_control_from_vmcb12(svm, ctl); + nested_copy_vmcb_control_to_cache(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); @@ -1449,7 +1517,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; if (!nested_svm_vmrun_msrpm(svm)) { diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 871c426ec389..0cf05e4caa4c 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -16,6 +16,7 @@ #include "cpuid.h" #include "lapic.h" #include "pmu.h" +#include "svm.h" enum pmu_type { PMU_TYPE_COUNTER = 0, @@ -100,6 +101,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + if (!pmu) + return NULL; + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: @@ -281,7 +285,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; - pmu->reserved_bits = 0xffffffff00200000ull; + pmu->reserved_bits = 0xfffffff000280000ull; pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 21ac0a5de4e0..322553322202 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -636,7 +636,8 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_vcpu *vcpu; - int i, ret; + unsigned long i; + int ret; if (!sev_es_guest(kvm)) return -ENOTTY; @@ -1543,35 +1544,57 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id) return false; } -static int sev_lock_for_migration(struct kvm *kvm) +static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + int r = -EBUSY; + + if (dst_kvm == src_kvm) + return -EINVAL; /* - * Bail if this VM is already involved in a migration to avoid deadlock - * between two VMs trying to migrate to/from each other. + * Bail if these VMs are already involved in a migration to avoid + * deadlock between two VMs trying to migrate to/from each other. */ - if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1)) + if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1)) return -EBUSY; - mutex_lock(&kvm->lock); + if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1)) + goto release_dst; + r = -EINTR; + if (mutex_lock_killable(&dst_kvm->lock)) + goto release_src; + if (mutex_lock_killable(&src_kvm->lock)) + goto unlock_dst; return 0; + +unlock_dst: + mutex_unlock(&dst_kvm->lock); +release_src: + atomic_set_release(&src_sev->migration_in_progress, 0); +release_dst: + atomic_set_release(&dst_sev->migration_in_progress, 0); + return r; } -static void sev_unlock_after_migration(struct kvm *kvm) +static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; - mutex_unlock(&kvm->lock); - atomic_set_release(&sev->migration_in_progress, 0); + mutex_unlock(&dst_kvm->lock); + mutex_unlock(&src_kvm->lock); + atomic_set_release(&dst_sev->migration_in_progress, 0); + atomic_set_release(&src_sev->migration_in_progress, 0); } static int sev_lock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, j; + unsigned long i, j; kvm_for_each_vcpu(i, vcpu, kvm) { if (mutex_lock_killable(&vcpu->mutex)) @@ -1593,7 +1616,7 @@ out_unlock: static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { mutex_unlock(&vcpu->mutex); @@ -1607,19 +1630,20 @@ static void sev_migrate_from(struct kvm_sev_info *dst, dst->asid = src->asid; dst->handle = src->handle; dst->pages_locked = src->pages_locked; + dst->enc_context_owner = src->enc_context_owner; src->asid = 0; src->active = false; src->handle = 0; src->pages_locked = 0; + src->enc_context_owner = NULL; - INIT_LIST_HEAD(&dst->regions_list); - list_replace_init(&src->regions_list, &dst->regions_list); + list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); } static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) { - int i; + unsigned long i; struct kvm_vcpu *dst_vcpu, *src_vcpu; struct vcpu_svm *dst_svm, *src_svm; @@ -1666,15 +1690,6 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) bool charged = false; int ret; - ret = sev_lock_for_migration(kvm); - if (ret) - return ret; - - if (sev_guest(kvm)) { - ret = -EINVAL; - goto out_unlock; - } - source_kvm_file = fget(source_fd); if (!file_is_kvm(source_kvm_file)) { ret = -EBADF; @@ -1682,16 +1697,26 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) } source_kvm = source_kvm_file->private_data; - ret = sev_lock_for_migration(source_kvm); + ret = sev_lock_two_vms(kvm, source_kvm); if (ret) goto out_fput; - if (!sev_guest(source_kvm)) { + if (sev_guest(kvm) || !sev_guest(source_kvm)) { ret = -EINVAL; - goto out_source; + goto out_unlock; } src_sev = &to_kvm_svm(source_kvm)->sev_info; + + /* + * VMs mirroring src's encryption context rely on it to keep the + * ASID allocated, but below we are clearing src_sev->asid. + */ + if (src_sev->num_mirrored_vms) { + ret = -EBUSY; + goto out_unlock; + } + dst_sev->misc_cg = get_current_misc_cg(); cg_cleanup_sev = dst_sev; if (dst_sev->misc_cg != src_sev->misc_cg) { @@ -1728,13 +1753,11 @@ out_dst_cgroup: sev_misc_cg_uncharge(cg_cleanup_sev); put_misc_cg(cg_cleanup_sev->misc_cg); cg_cleanup_sev->misc_cg = NULL; -out_source: - sev_unlock_after_migration(source_kvm); +out_unlock: + sev_unlock_two_vms(kvm, source_kvm); out_fput: if (source_kvm_file) fput(source_kvm_file); -out_unlock: - sev_unlock_after_migration(kvm); return ret; } @@ -1953,76 +1976,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info source_sev, *mirror_sev; + struct kvm_sev_info *source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); if (!file_is_kvm(source_kvm_file)) { ret = -EBADF; - goto e_source_put; + goto e_source_fput; } source_kvm = source_kvm_file->private_data; - mutex_lock(&source_kvm->lock); - - if (!sev_guest(source_kvm)) { - ret = -EINVAL; - goto e_source_unlock; - } + ret = sev_lock_two_vms(kvm, source_kvm); + if (ret) + goto e_source_fput; - /* Mirrors of mirrors should work, but let's not get silly */ - if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) { + /* + * Mirrors of mirrors should work, but let's not get silly. Also + * disallow out-of-band SEV/SEV-ES init if the target is already an + * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being + * created after SEV/SEV-ES initialization, e.g. to init intercepts. + */ + if (sev_guest(kvm) || !sev_guest(source_kvm) || + is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) { ret = -EINVAL; - goto e_source_unlock; + goto e_unlock; } - memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, - sizeof(source_sev)); - /* * The mirror kvm holds an enc_context_owner ref so its asid can't * disappear until we're done with it */ + source_sev = &to_kvm_svm(source_kvm)->sev_info; kvm_get_kvm(source_kvm); - - fput(source_kvm_file); - mutex_unlock(&source_kvm->lock); - mutex_lock(&kvm->lock); - - /* - * Disallow out-of-band SEV/SEV-ES init if the target is already an - * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being - * created after SEV/SEV-ES initialization, e.g. to init intercepts. - */ - if (sev_guest(kvm) || kvm->created_vcpus) { - ret = -EINVAL; - goto e_mirror_unlock; - } + source_sev->num_mirrored_vms++; /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; mirror_sev->active = true; - mirror_sev->asid = source_sev.asid; - mirror_sev->fd = source_sev.fd; - mirror_sev->es_active = source_sev.es_active; - mirror_sev->handle = source_sev.handle; + mirror_sev->asid = source_sev->asid; + mirror_sev->fd = source_sev->fd; + mirror_sev->es_active = source_sev->es_active; + mirror_sev->handle = source_sev->handle; + INIT_LIST_HEAD(&mirror_sev->regions_list); + ret = 0; + /* * Do not copy ap_jump_table. Since the mirror does not share the same * KVM contexts as the original, and they may have different * memory-views. */ - mutex_unlock(&kvm->lock); - return 0; - -e_mirror_unlock: - mutex_unlock(&kvm->lock); - kvm_put_kvm(source_kvm); - return ret; -e_source_unlock: - mutex_unlock(&source_kvm->lock); -e_source_put: +e_unlock: + sev_unlock_two_vms(kvm, source_kvm); +e_source_fput: if (source_kvm_file) fput(source_kvm_file); return ret; @@ -2034,17 +2041,24 @@ void sev_vm_destroy(struct kvm *kvm) struct list_head *head = &sev->regions_list; struct list_head *pos, *q; + WARN_ON(sev->num_mirrored_vms); + if (!sev_guest(kvm)) return; /* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */ if (is_mirroring_enc_context(kvm)) { - kvm_put_kvm(sev->enc_context_owner); + struct kvm *owner_kvm = sev->enc_context_owner; + struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info; + + mutex_lock(&owner_kvm->lock); + if (!WARN_ON(!owner_sev->num_mirrored_vms)) + owner_sev->num_mirrored_vms--; + mutex_unlock(&owner_kvm->lock); + kvm_put_kvm(owner_kvm); return; } - mutex_lock(&kvm->lock); - /* * Ensure that all guest tagged cache entries are flushed before * releasing the pages back to the system for use. CLFLUSH will @@ -2064,8 +2078,6 @@ void sev_vm_destroy(struct kvm *kvm) } } - mutex_unlock(&kvm->lock); - sev_unbind_asid(kvm, sev->handle); sev_asid_free(sev); } @@ -2249,7 +2261,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) @@ -2341,24 +2353,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } -static int sev_es_validate_vmgexit(struct vcpu_svm *svm) +static bool sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu; struct ghcb *ghcb; - u64 exit_code = 0; + u64 exit_code; + u64 reason; ghcb = svm->sev_es.ghcb; - /* Only GHCB Usage code 0 is supported */ - if (ghcb->ghcb_usage) - goto vmgexit_err; - /* - * Retrieve the exit code now even though is may not be marked valid + * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ exit_code = ghcb_get_sw_exit_code(ghcb); + /* Only GHCB Usage code 0 is supported */ + if (ghcb->ghcb_usage) { + reason = GHCB_ERR_INVALID_USAGE; + goto vmgexit_err; + } + + reason = GHCB_ERR_MISSING_INPUT; + if (!ghcb_sw_exit_code_is_valid(ghcb) || !ghcb_sw_exit_info_1_is_valid(ghcb) || !ghcb_sw_exit_info_2_is_valid(ghcb)) @@ -2437,30 +2454,34 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; default: + reason = GHCB_ERR_INVALID_EVENT; goto vmgexit_err; } - return 0; + return true; vmgexit_err: vcpu = &svm->vcpu; - if (ghcb->ghcb_usage) { + if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", ghcb->ghcb_usage); + } else if (reason == GHCB_ERR_INVALID_EVENT) { + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n", + exit_code); } else { - vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n", + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n", exit_code); dump_ghcb(svm); } - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_code; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + /* Clear the valid entries fields */ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); + + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, reason); - return -EINVAL; + return false; } void sev_es_unmap_ghcb(struct vcpu_svm *svm) @@ -2482,7 +2503,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); svm->sev_es.ghcb_sa = NULL; svm->sev_es.ghcb_sa_free = false; } @@ -2530,14 +2551,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); - return false; + goto e_scratch; } scratch_gpa_end = scratch_gpa_beg + len; if (scratch_gpa_end < scratch_gpa_beg) { pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n", len, scratch_gpa_beg); - return false; + goto e_scratch; } if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { @@ -2555,7 +2576,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_end > ghcb_scratch_end) { pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n", scratch_gpa_beg, scratch_gpa_end); - return false; + goto e_scratch; } scratch_va = (void *)svm->sev_es.ghcb; @@ -2568,18 +2589,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) if (len > GHCB_SCRATCH_AREA_LIMIT) { pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", len, GHCB_SCRATCH_AREA_LIMIT); - return false; + goto e_scratch; } - scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT); + scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT); if (!scratch_va) - return false; + goto e_scratch; if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) { /* Unable to copy scratch area from guest */ pr_err("vmgexit: kvm_read_guest for scratch area failed\n"); - kfree(scratch_va); - return false; + kvfree(scratch_va); + goto e_scratch; } /* @@ -2596,6 +2617,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) svm->sev_es.ghcb_sa_len = len; return true; + +e_scratch: + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + + return false; } static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, @@ -2646,7 +2673,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID); if (!ret) { - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ break; } @@ -2682,10 +2709,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) GHCB_MSR_TERM_REASON_POS); pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", reason_set, reason_code); - fallthrough; + + ret = -EINVAL; + break; } default: - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ + break; } trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, @@ -2709,14 +2739,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) if (!ghcb_gpa) { vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n"); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; @@ -2726,15 +2760,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) exit_code = ghcb_get_sw_exit_code(ghcb); - ret = sev_es_validate_vmgexit(svm); - if (ret) - return ret; + if (!sev_es_validate_vmgexit(svm)) + return 1; sev_es_sync_from_ghcb(svm); ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); - ret = -EINVAL; + ret = 1; switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: if (!setup_vmgexit_scratch(svm, true, control->exit_info_2)) @@ -2775,20 +2808,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) default: pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", control->exit_info_1); - ghcb_set_sw_exit_info_1(ghcb, 1); - ghcb_set_sw_exit_info_2(ghcb, - X86_TRAP_UD | - SVM_EVTINJ_TYPE_EXEPT | - SVM_EVTINJ_VALID); + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT); } - ret = 1; break; } case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", control->exit_info_1, control->exit_info_2); + ret = -EINVAL; break; default: ret = svm_invoke_exit_handler(vcpu, exit_code); @@ -2810,7 +2840,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) return -EINVAL; if (!setup_vmgexit_scratch(svm, in, bytes)) - return -EINVAL; + return 1; return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, count, in); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5630c241d5f6..5557867dcb69 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -192,6 +192,10 @@ module_param(vgif, int, 0444); static int lbrv = true; module_param(lbrv, int, 0444); +/* enable/disable PMU virtualization */ +bool pmu = true; +module_param(pmu, bool, 0444); + static int tsc_scaling = true; module_param(tsc_scaling, int, 0444); @@ -265,7 +269,7 @@ u32 svm_msrpm_offset(u32 msr) #define MAX_INST_SIZE 15 -static int get_max_npt_level(void) +static int get_npt_level(void) { #ifdef CONFIG_X86_64 return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; @@ -585,12 +589,10 @@ static int svm_cpu_init(int cpu) if (!sd) return ret; sd->cpu = cpu; - sd->save_area = alloc_page(GFP_KERNEL); + sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!sd->save_area) goto free_cpu_data; - clear_page(page_address(sd->save_area)); - ret = sev_cpu_init(sd); if (ret) goto free_save_area; @@ -954,6 +956,10 @@ static __init void svm_set_cpu_caps(void) boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + /* AMD PMU PERFCTR_CORE CPUID */ + if (pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) + kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE); + /* CPUID 0x8000001F (SME/SEV features) */ sev_set_cpu_caps(); } @@ -1029,9 +1035,9 @@ static __init int svm_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; - /* Force VM NPT level equal to the host's max NPT level */ - kvm_configure_mmu(npt_enabled, get_max_npt_level(), - get_max_npt_level(), PG_LEVEL_1G); + /* Force VM NPT level equal to the host's paging level */ + kvm_configure_mmu(npt_enabled, get_npt_level(), + get_npt_level(), PG_LEVEL_1G); pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Note, SEV setup consumes npt_enabled. */ @@ -1087,6 +1093,9 @@ static __init int svm_hardware_setup(void) pr_info("LBR virtualization supported\n"); } + if (!pmu) + pr_info("PMU virtualization is disabled\n"); + svm_set_cpu_caps(); /* @@ -1585,12 +1594,27 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } +static bool svm_get_if_flag(struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = to_svm(vcpu)->vmcb; + + return sev_es_guest(vcpu->kvm) + ? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK + : kvm_get_rflags(vcpu) & X86_EFLAGS_IF; +} + static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { + kvm_register_mark_available(vcpu, reg); + switch (reg) { case VCPU_EXREG_PDPTR: - BUG_ON(!npt_enabled); - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + /* + * When !npt_enabled, mmu->pdptrs[] is already available since + * it is always updated per SDM when moving to CRs. + */ + if (npt_enabled) + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); break; default: KVM_BUG_ON(1, vcpu->kvm); @@ -2508,7 +2532,7 @@ static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu, bool ret = false; if (!is_guest_mode(vcpu) || - (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) + (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) return false; cr0 &= ~SVM_CR0_SELECTIVE_MASK; @@ -3568,14 +3592,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (!gif_set(svm)) return true; - if (sev_es_guest(vcpu->kvm)) { - /* - * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask - * bit to determine the state of the IF flag. - */ - if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK)) - return true; - } else if (is_guest_mode(vcpu)) { + if (is_guest_mode(vcpu)) { /* As long as interrupts are being delivered... */ if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) ? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF) @@ -3586,7 +3603,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (nested_exit_on_intr(svm)) return false; } else { - if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) + if (!svm_get_if_flag(vcpu)) return true; } @@ -3929,6 +3946,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; } + vcpu->arch.regs_dirty = 0; if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(vcpu); @@ -3963,8 +3981,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); - if (npt_enabled) - kvm_register_clear_available(vcpu, VCPU_EXREG_PDPTR); + vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET; /* * We need to handle MC intercepts here before the vcpu has a chance to @@ -3994,9 +4011,6 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, hv_track_root_tdp(vcpu, root_hpa); - /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - return; cr3 = vcpu->arch.cr3; } else if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) { cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu); @@ -4215,7 +4229,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, info->intercept == x86_intercept_clts) break; - if (!(vmcb_is_intercept(&svm->nested.ctl, + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))) break; @@ -4434,7 +4448,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) */ vmcb12 = map.hva; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); unmap_save: @@ -4621,6 +4636,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, + .get_if_flag = svm_get_if_flag, .tlb_flush_all = svm_flush_tlb, .tlb_flush_current = svm_flush_tlb, @@ -4651,7 +4667,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .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, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5faad3dc10e2..9f153c59f2c8 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -32,6 +32,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern bool intercept_smi; +extern bool pmu; /* * Clean bits in VMCB. @@ -79,6 +80,7 @@ struct kvm_sev_info { struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ + unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ atomic_t migration_in_progress; }; @@ -104,6 +106,40 @@ struct kvm_vmcb_info { uint64_t asid_generation; }; +struct vmcb_save_area_cached { + u64 efer; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; +}; + +struct vmcb_ctrl_area_cached { + u32 intercepts[MAX_INTERCEPT]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 virt_ext; +}; + struct svm_nested_state { struct kvm_vmcb_info vmcb02; u64 hsave_msr; @@ -119,7 +155,13 @@ struct svm_nested_state { bool nested_run_pending; /* cache for control fields of the guest */ - struct vmcb_control_area ctl; + struct vmcb_ctrl_area_cached ctl; + + /* + * Note: this struct is not kept up-to-date while L2 runs; it is only + * valid within nested_svm_vmrun. + */ + struct vmcb_save_area_cached save; bool initialized; }; @@ -284,6 +326,16 @@ static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_svm, vcpu); } +/* + * Only the PDPTRs are loaded on demand into the shadow MMU. All other + * fields are synchronized in handle_exit, because accessing the VMCB is cheap. + * + * CR3 might be out of date in the VMCB but it is not marked dirty; instead, + * KVM_REQ_LOAD_MMU_PGD is always requested when the cached vcpu->arch.cr3 + * is changed. svm_load_mmu_pgd() then syncs the new CR3 value into the VMCB. + */ +#define SVM_REGS_LAZY_LOAD_SET (1 << VCPU_EXREG_PDPTR) + static inline void vmcb_set_intercept(struct vmcb_control_area *control, u32 bit) { WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); @@ -302,6 +354,12 @@ static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit) return test_bit(bit, (unsigned long *)&control->intercepts); } +static inline bool vmcb12_is_intercept(struct vmcb_ctrl_area_cached *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + return test_bit(bit, (unsigned long *)&control->intercepts); +} + static inline void set_dr_intercepts(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -454,17 +512,17 @@ static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu) static inline bool nested_exit_on_smi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); } static inline bool nested_exit_on_intr(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); } static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, @@ -493,8 +551,10 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, int nested_svm_exit_special(struct vcpu_svm *svm); void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier); -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control); +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control); +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 953b0fcb21ee..92e6f6702f00 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1356,6 +1356,30 @@ TRACE_EVENT(kvm_apicv_update_request, __entry->bit) ); +TRACE_EVENT(kvm_apicv_accept_irq, + TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec), + TP_ARGS(apicid, dm, tm, vec), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( __u16, dm ) + __field( __u16, tm ) + __field( __u8, vec ) + ), + + TP_fast_assign( + __entry->apicid = apicid; + __entry->dm = dm; + __entry->tm = tm; + __entry->vec = vec; + ), + + TP_printk("apicid %x vec %u (%s|%s)", + __entry->apicid, __entry->vec, + __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode), + __entry->tm ? "level" : "edge") +); + /* * Tracepoint for AMD AVIC */ diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 4705ad55abb5..c8029b7845b6 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -312,6 +312,15 @@ static inline bool cpu_has_vmx_ept_1g_page(void) return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT; } +static inline int ept_caps_to_lpage_level(u32 ept_caps) +{ + if (ept_caps & VMX_EPT_1GB_PAGE_BIT) + return PG_LEVEL_1G; + if (ept_caps & VMX_EPT_2MB_PAGE_BIT) + return PG_LEVEL_2M; + return PG_LEVEL_4K; +} + static inline bool cpu_has_vmx_ept_ad_bits(void) { return vmx_capability.ept & VMX_EPT_AD_BIT; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1e2f66951566..2f6f465e575f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -269,7 +269,13 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET; + + /* + * All lazily updated registers will be reloaded from VMCS12 on both + * vmentry and vmexit. + */ + vcpu->arch.regs_dirty = 0; } /* @@ -391,9 +397,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) { - kvm_init_shadow_ept_mmu(vcpu, - to_vmx(vcpu)->nested.msrs.ept_caps & - VMX_EPT_EXECUTE_ONLY_BIT, + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT; + int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps); + + kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level, nested_ept_ad_enabled(vcpu), nested_ept_get_eptp(vcpu)); } @@ -591,6 +599,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ @@ -598,6 +607,19 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return false; + /* + * MSR bitmap update can be skipped when: + * - MSR bitmap for L1 hasn't changed. + * - Nested hypervisor (L1) is attempting to launch the same L2 as + * before. + * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature + * and tells KVM (L0) there were no changes in MSR bitmap for L2. + */ + if (!vmx->nested.force_msr_bitmap_recalc && evmcs && + evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) return false; @@ -664,6 +686,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); + vmx->nested.force_msr_bitmap_recalc = false; + return true; } @@ -1095,7 +1119,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, * must not be dereferenced. */ if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + CC(!load_pdptrs(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } @@ -1104,7 +1128,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -1162,29 +1186,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, WARN_ON(!enable_vpid); /* - * If VPID is enabled and used by vmc12, but L2 does not have a unique - * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate - * a VPID for L2, flush the current context as the effective ASID is - * common to both L1 and L2. - * - * Defer the flush so that it runs after vmcs02.EPTP has been set by - * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid - * redundant flushes further down the nested pipeline. - * - * If a TLB flush isn't required due to any of the above, and vpid12 is - * changing then the new "virtual" VPID (vpid12) will reuse the same - * "real" VPID (vpid02), and so needs to be flushed. There's no direct - * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for - * all nested vCPUs. Remember, a flush on VM-Enter does not invalidate - * guest-physical mappings, so there is no need to sync the nEPT MMU. + * VPID is enabled and in use by vmcs12. If vpid12 is changing, then + * emulate a guest TLB flush as KVM does not track vpid12 history nor + * is the VPID incorporated into the MMU context. I.e. KVM must assume + * that the new vpid12 has never been used and thus represents a new + * guest ASID that cannot have entries in the TLB. */ - if (!nested_has_guest_tlb_tag(vcpu)) { - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } else if (is_vmenter && - vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - vpid_sync_context(nested_get_vpid02(vcpu)); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return; } + + /* + * If VPID is enabled, used by vmc12, and vpid12 is not changing but + * does not have a unique TLB tag (ASID), i.e. EPT is disabled and + * KVM was unable to allocate a VPID for L2, flush the current context + * as the effective ASID is common to both L1 and L2. + */ + if (!nested_has_guest_tlb_tag(vcpu)) + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) @@ -2024,10 +2045,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ - if (from_launch || evmcs_gpa_changed) + if (from_launch || evmcs_gpa_changed) { vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + vmx->nested.force_msr_bitmap_recalc = true; + } + return EVMPTRLD_SUCCEEDED; } @@ -2594,8 +2618,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->guest_ia32_perf_global_ctrl))) + vmcs12->guest_ia32_perf_global_ctrl))) { + *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; + } kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); @@ -3028,7 +3054,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; bool vm_fail; if (!nested_early_check) @@ -3051,12 +3077,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ vmcs_writel(GUEST_RFLAGS, 0); - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -3146,7 +3166,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; } @@ -3344,8 +3364,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, }; u32 failed_index; - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); evaluate_pending_interrupts = exec_controls_get(vmx) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); @@ -3605,7 +3624,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } break; case GUEST_ACTIVITY_WAIT_SIPI: @@ -4502,9 +4521,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, (void)nested_get_evmcs_page(vcpu); } - /* Service the TLB flush request for L2 before switching to L1. */ - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + /* Service pending TLB flush requests for L2 before switching to L1. */ + kvm_service_local_tlb_flush_requests(vcpu); /* * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between @@ -4857,6 +4875,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; + vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA; vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; @@ -5260,6 +5279,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) vmx->nested.need_vmcs12_to_shadow_sync = true; } vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; } /* Emulate the VMPTRLD instruction */ @@ -5289,8 +5309,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache; struct vmcs_hdr hdr; - if (ghc->gpa != vmptr && - kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { /* * Reads from an unbacked page return all 1s, * which means that the 32 bits located at the @@ -6396,6 +6415,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) goto error_guest_mode; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f81ef092bd4..88c53c521094 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -5,15 +5,28 @@ #include <asm/cpu.h> #include "lapic.h" +#include "irq.h" #include "posted_intr.h" #include "trace.h" #include "vmx.h" /* - * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we - * can find which vCPU should be waken up. + * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler() + * when a WAKEUP_VECTOR interrupted is posted. vCPUs are added to the list when + * the vCPU is scheduled out and is blocking (e.g. in HLT) with IRQs enabled. + * The vCPUs posted interrupt descriptor is updated at the same time to set its + * notification vector to WAKEUP_VECTOR, so that posted interrupt from devices + * wake the target vCPUs. vCPUs are removed from the list and the notification + * vector is reset when the vCPU is scheduled in. */ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +/* + * Protect the per-CPU list with a per-CPU spinlock to handle task migration. + * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the + * ->sched_in() path will need to take the vCPU off the list of the _previous_ + * CPU. IRQs must be disabled when taking this lock, otherwise deadlock will + * occur if a wakeup IRQ arrives and attempts to acquire the lock. + */ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) @@ -21,6 +34,20 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } +static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new) +{ + /* + * PID.ON can be set at any time by a different vCPU or by hardware, + * e.g. a device. PID.control must be written atomically, and the + * update must be retried with a fresh snapshot an ON change causes + * the cmpxchg to fail. + */ + if (cmpxchg64(&pi_desc->control, old, new) != old) + return -EBUSY; + + return 0; +} + void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -28,11 +55,14 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) unsigned int dest; /* - * In case of hot-plug or hot-unplug, we may have to undo - * vmx_vcpu_pi_put even if there is no assigned device. And we - * always keep PI.NDST up to date for simplicity: it makes the - * code easier, and CPU migration is not a fast path. + * To simplify hot-plug and dynamic toggling of APICv, keep PI.NDST and + * PI.SN up-to-date even if there is no assigned device or if APICv is + * deactivated due to a dynamic inhibit bit, e.g. for Hyper-V's SyncIC. */ + if (!enable_apicv || !lapic_in_kernel(vcpu)) + return; + + /* Nothing to do if PI.SN and PI.NDST both have the desired value. */ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; @@ -48,20 +78,17 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) goto after_clear_sn; } - /* The full case. */ - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(cpu); + /* The full case. Set the new destination and clear SN. */ + dest = cpu_physical_id(cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); + new.ndst = dest; new.sn = 0; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); after_clear_sn: @@ -77,13 +104,18 @@ after_clear_sn: pi_set_on(pi_desc); } +static bool vmx_can_use_vtd_pi(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm) && enable_apicv && + kvm_arch_has_assigned_device(kvm) && + irq_remapping_cap(IRQ_POSTING_CAP); +} + void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return; /* Set SN when the vCPU is preempted */ @@ -97,29 +129,31 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; unsigned int dest; - do { - old.control = new.control = pi_desc->control; - WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, - "Wakeup handler not enabled while the VCPU is blocked\n"); + /* + * Remove the vCPU from the wakeup list of the _previous_ pCPU, which + * will not be the same as the current pCPU if the task was migrated. + */ + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - dest = cpu_physical_id(vcpu->cpu); + dest = cpu_physical_id(vcpu->cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the vCPU was blocking"); + + do { + old.control = new.control = READ_ONCE(pi_desc->control); + + new.ndst = dest; /* set 'NV' to 'notification vector' */ new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - vcpu->pre_pcpu = -1; - } + } while (pi_try_set_control(pi_desc, old.control, new.control)); + + vcpu->pre_pcpu = -1; } /* @@ -128,7 +162,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) * - Store the vCPU to the wakeup list, so when interrupts happen * we can find the right vCPU to wake up. * - Change the Posted-interrupt descriptor as below: - * 'NDST' <-- vcpu->pre_pcpu * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR * - If 'ON' is set during this process, which means at least one * interrupt is posted for this vCPU, we cannot block it, in @@ -137,70 +170,50 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) */ int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + unsigned long flags; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm) || + vmx_interrupt_blocked(vcpu)) return 0; - WARN_ON(irqs_disabled()); - local_irq_disable(); - if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { - vcpu->pre_pcpu = vcpu->cpu; - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - } - - do { - old.control = new.control = pi_desc->control; + local_irq_save(flags); - WARN((pi_desc->sn == 1), - "Warning: SN field of posted-interrupts " - "is set before blocking\n"); + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); - /* - * Since vCPU can be preempted during this process, - * vcpu->cpu could be different with pre_pcpu, we - * need to set pre_pcpu as the destination of wakeup - * notification event, then we can find the right vCPU - * to wakeup in wakeup handler if interrupts happen - * when the vCPU is in blocked state. - */ - dest = cpu_physical_id(vcpu->pre_pcpu); + WARN(pi_desc->sn == 1, + "Posted Interrupt Suppress Notification set before blocking"); - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); /* We should not block the vCPU if an interrupt is posted for it. */ - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); return (vcpu->pre_pcpu == -1); } void pi_post_block(struct kvm_vcpu *vcpu) { + unsigned long flags; + if (vcpu->pre_pcpu == -1) return; - WARN_ON(irqs_disabled()); - local_irq_disable(); + local_irq_save(flags); __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); } /* @@ -216,7 +229,7 @@ void pi_wakeup_handler(void) blocked_vcpu_list) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) kvm_vcpu_kick(vcpu); } spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); @@ -270,9 +283,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct vcpu_data vcpu_info; int idx, ret = 0; - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(kvm->vcpus[0])) + if (!vmx_can_use_vtd_pi(kvm)) return 0; idx = srcu_read_lock(&kvm->irq_srcu); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 7f7b2326caf5..36ae035f14aa 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -40,7 +40,7 @@ static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) { return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } @@ -74,13 +74,13 @@ static inline void pi_clear_sn(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_on(struct pi_desc *pi_desc) +static inline bool pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); } -static inline int pi_test_sn(struct pi_desc *pi_desc) +static inline bool pi_test_sn(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ba66c171d951..9bf65e5e4840 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -602,15 +602,13 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; - u64 old_msr_data = msr->data; - msr->data = data; if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, data, msr->mask); preempt_enable(); - if (ret) - msr->data = old_msr_data; } + if (!ret) + msr->data = data; return ret; } @@ -1105,6 +1103,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); #endif + unsigned long cr3; unsigned long fs_base, gs_base; u16 fs_sel, gs_sel; int i; @@ -1169,6 +1168,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #endif vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); + + /* Host CR3 including its PCID is stable when guest state is loaded. */ + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != host_state->cr3)) { + vmcs_writel(HOST_CR3, cr3); + host_state->cr3 = cr3; + } + vmx->guest_state_loaded = true; } @@ -1271,7 +1278,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, if (!already_loaded) { void *gdt = get_current_gdt_ro(); - unsigned long sysenter_esp; /* * Flush all EPTP/VPID contexts, the new pCPU may have stale @@ -1287,8 +1293,11 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); - vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + if (IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) { + /* 22.2.3 */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, + (unsigned long)(cpu_entry_stack(cpu) + 1)); + } vmx->loaded_vmcs->cpu = cpu; } @@ -1363,6 +1372,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmx->emulation_required = vmx_emulation_required(vcpu); } +static bool vmx_get_if_flag(struct kvm_vcpu *vcpu) +{ + return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; +} + u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -1748,7 +1762,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) } /* - * Reads an msr value (of 'msr_index') into 'pdata'. + * Reads an msr value (of 'msr_info->index') into 'msr_info->data'. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ @@ -2095,9 +2109,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } ret = kvm_set_msr_common(vcpu, msr_info); break; - case MSR_IA32_TSC_ADJUST: - ret = kvm_set_msr_common(vcpu, msr_info); - break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & @@ -2646,15 +2657,6 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); - - if (IS_ENABLED(CONFIG_HYPERV) && - static_branch_unlikely(&enable_evmcs) && - (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { - struct hv_enlightened_vmcs *evmcs = - (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; - - evmcs->hv_enlightenments_control.msr_bitmap = 1; - } } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); @@ -2918,6 +2920,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) } } +static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) + return nested_get_vpid02(vcpu); + return to_vmx(vcpu)->vpid; +} + static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -2930,31 +2939,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) if (enable_ept) ept_sync_context(construct_eptp(vcpu, root_hpa, mmu->shadow_root_level)); - else if (!is_guest_mode(vcpu)) - vpid_sync_context(to_vmx(vcpu)->vpid); else - vpid_sync_context(nested_get_vpid02(vcpu)); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* - * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in + * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in * vmx_flush_tlb_guest() for an explanation of why this is ok. */ - vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr); + vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* - * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0 - * or a vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit - * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is + * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a + * vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit are + * required to flush GVA->{G,H}PA mappings from the TLB if vpid is * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed), * i.e. no explicit INVVPID is necessary. */ - vpid_sync_context(to_vmx(vcpu)->vpid); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) @@ -2984,7 +2991,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); } #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ @@ -3109,9 +3116,9 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; - else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + else if (kvm_register_is_dirty(vcpu, VCPU_EXREG_CR3)) guest_cr3 = vcpu->arch.cr3; - else /* vmcs01.GUEST_CR3 is already up-to-date. */ + else /* vmcs.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { @@ -3686,6 +3693,19 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } +static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) +{ + /* + * When KVM is a nested hypervisor on top of Hyper-V and uses + * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR + * bitmap has changed. + */ + if (static_branch_unlikely(&enable_evmcs)) + evmcs_touch_msr_bitmap(); + + vmx->nested.force_msr_bitmap_recalc = true; +} + void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3694,8 +3714,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3739,8 +3758,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3930,6 +3948,19 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * This pairs with the smp_mb_*() after setting vcpu->mode in + * vcpu_enter_guest() to guarantee the vCPU sees the event + * request if triggering a posted interrupt "fails" because + * vcpu->mode != IN_GUEST_MODE. The extra barrier is needed as + * the smb_wmb() in kvm_make_request() only ensures everything + * done before making the request is visible when the request + * is visible, it doesn't ensure ordering between the store to + * vcpu->requests and the load from vcpu->mode. + */ + smp_mb__after_atomic(); + /* the PIR and ON have been set by L1. */ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) kvm_vcpu_kick(vcpu); @@ -3963,8 +3994,13 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return 0; - if (vcpu != kvm_get_running_vcpu() && - !kvm_vcpu_trigger_posted_interrupt(vcpu, false)) + /* + * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*() + * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is + * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a + * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE. + */ + if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); return 0; @@ -4021,6 +4057,12 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); vmcs_write32(HOST_IA32_SYSENTER_CS, low32); + + /* + * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites + * HOST_IA32_SYSENTER_ESP. + */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ @@ -4039,8 +4081,10 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vcpu->arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS & ~vcpu->arch.cr4_guest_rsvd_bits; - if (!enable_ept) - vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PGE; + if (!enable_ept) { + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_TLBFLUSH_BITS; + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PDPTR_BITS; + } if (is_guest_mode(&vmx->vcpu)) vcpu->arch.cr4_guest_owned_bits &= ~get_vmcs12(vcpu)->cr4_guest_host_mask; @@ -4692,7 +4736,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } return 1; } @@ -5363,7 +5407,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } /* @@ -5881,18 +5925,14 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) vmx_flush_pml_buffer(vcpu); /* - * We should never reach this point with a pending nested VM-Enter, and - * more specifically emulation of L2 due to invalid guest state (see - * below) should never happen as that means we incorrectly allowed a - * nested VM-Enter with an invalid vmcs12. + * KVM should never reach this point with a pending nested VM-Enter. + * More specifically, short-circuiting VM-Entry to emulate L2 due to + * invalid guest state should never happen as that means KVM knowingly + * allowed a nested VM-Enter with an invalid vmcs12. More below. */ if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm)) return -EIO; - /* If guest state is invalid, start emulating */ - if (vmx->emulation_required) - return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu)) { /* * PML is never enabled when running L2, bail immediately if a @@ -5914,10 +5954,30 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) */ nested_mark_vmcs12_pages_dirty(vcpu); + /* + * Synthesize a triple fault if L2 state is invalid. In normal + * operation, nested VM-Enter rejects any attempt to enter L2 + * with invalid state. However, those checks are skipped if + * state is being stuffed via RSM or KVM_SET_NESTED_STATE. If + * L2 state is invalid, it means either L1 modified SMRAM state + * or userspace provided bad state. Synthesize TRIPLE_FAULT as + * doing so is architecturally allowed in the RSM case, and is + * the least awful solution for the userspace case without + * risking false positives. + */ + if (vmx->emulation_required) { + nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); + return 1; + } + if (nested_vmx_reflect_vmexit(vcpu)) return 1; } + /* If guest state is invalid, start emulating. L2 is handled above. */ + if (vmx->emulation_required) + return handle_invalid_guest_state(vcpu); + if (exit_reason.failed_vmentry) { dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; @@ -6262,9 +6322,9 @@ 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; + bool got_posted_interrupt; - if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm)) + if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; if (pi_test_on(&vmx->pi_desc)) { @@ -6274,22 +6334,33 @@ 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_updated = + got_posted_interrupt = 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, this may cause a vmexit or it may - * be injected into L2. Either way, this interrupt will be - * processed via KVM_REQ_EVENT, not RVI, because we do not use - * virtual interrupt delivery to inject L1 interrupts into L2. - */ - if (is_guest_mode(vcpu) && max_irr_updated) - kvm_make_request(KVM_REQ_EVENT, vcpu); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); + got_posted_interrupt = false; } - vmx_hwapic_irr_update(vcpu, max_irr); + + /* + * Newly recognized interrupts are injected via either virtual interrupt + * delivery (RVI) or KVM_REQ_EVENT. Virtual interrupt delivery is + * disabled in two cases: + * + * 1) If L2 is running and the vCPU has a new pending interrupt. If L1 + * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a + * VM-Exit to L1. If L1 doesn't want to exit, the interrupt is injected + * into L2, but KVM doesn't use virtual interrupt delivery to inject + * interrupts into L2, and so KVM_REQ_EVENT is again needed. + * + * 2) If APICv is disabled for this vCPU, assigned devices may still + * attempt to post interrupts. The posted interrupt vector will cause + * a VM-Exit and the subsequent entry will call sync_pir_to_irr. + */ + if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu)) + vmx_set_rvi(max_irr); + else if (got_posted_interrupt) + kvm_make_request(KVM_REQ_EVENT, vcpu); + return max_irr; } @@ -6588,7 +6659,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6601,9 +6672,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * consistency check VM-Exit due to invalid guest state and bail. */ if (unlikely(vmx->emulation_required)) { - - /* We don't emulate invalid state of a nested guest */ - vmx->fail = is_guest_mode(vcpu); + vmx->fail = 0; vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; vmx->exit_reason.failed_vmentry = 1; @@ -6631,12 +6700,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } + vcpu->arch.regs_dirty = 0; cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { @@ -6725,7 +6789,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(es, __USER_DS); #endif - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; pt_guest_exit(vmx); @@ -6826,6 +6890,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (err < 0) goto free_pml; + /* + * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a + * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the + * feature only for vmcs01, KVM currently isn't equipped to realize any + * performance benefits from enabling it for vmcs02. + */ + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + evmcs->hv_enlightenments_control.msr_bitmap = 1; + } + /* The MSR bitmap starts with all ones */ bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); @@ -6931,7 +7008,6 @@ static int __init vmx_check_processor_compat(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; - u64 ipat = 0; /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. @@ -6951,30 +7027,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) * EPT memory type is used to emulate guest CD/MTRR. */ - if (is_mmio) { - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } + if (is_mmio) + return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { - ipat = VMX_EPT_IPAT_BIT; - cache = MTRR_TYPE_WRBACK; - goto exit; - } + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; if (kvm_read_cr0(vcpu) & X86_CR0_CD) { - ipat = VMX_EPT_IPAT_BIT; if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK; else cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + } -exit: - return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; + return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) @@ -7509,6 +7577,7 @@ static void hardware_unsetup(void) static bool vmx_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ); @@ -7558,6 +7627,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, + .get_if_flag = vmx_get_if_flag, .tlb_flush_all = vmx_flush_tlb_all, .tlb_flush_current = vmx_flush_tlb_current, @@ -7683,7 +7753,7 @@ static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, ept_lpage_level; + int r; store_idt(&dt); host_idt_base = dt.address; @@ -7761,10 +7831,10 @@ static __init int hardware_setup(void) ple_window_shrink = 0; } - if (!cpu_has_vmx_apicv()) { + if (!cpu_has_vmx_apicv()) enable_apicv = 0; + if (!enable_apicv) vmx_x86_ops.sync_pir_to_irr = NULL; - } if (cpu_has_vmx_tsc_scaling()) { kvm_has_tsc_control = true; @@ -7780,16 +7850,8 @@ static __init int hardware_setup(void) kvm_mmu_set_ept_masks(enable_ept_ad_bits, cpu_has_vmx_ept_execute_only()); - if (!enable_ept) - ept_lpage_level = 0; - else if (cpu_has_vmx_ept_1g_page()) - ept_lpage_level = PG_LEVEL_1G; - else if (cpu_has_vmx_ept_2m_page()) - ept_lpage_level = PG_LEVEL_2M; - else - ept_lpage_level = PG_LEVEL_4K; kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(), - ept_lpage_level); + ept_caps_to_lpage_level(vmx_capability.ept)); /* * Only enable PML when hardware supports PML feature, and both EPT diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4df2ac24ffc1..6c2c1aff1c3d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -159,6 +159,15 @@ struct nested_vmx { bool dirty_vmcs12; /* + * Indicates whether MSR bitmap for L2 needs to be rebuilt due to + * changes in MSR bitmap for L1 or switching to a different L2. Note, + * this flag can only be used reliably in conjunction with a paravirt L1 + * which informs L0 whether any changes to MSR bitmap for L2 were done + * on its side. + */ + bool force_msr_bitmap_recalc; + + /* * Indicates lazily loaded guest state has not yet been decached from * vmcs02. */ @@ -473,19 +482,21 @@ BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL) -static inline void vmx_register_cache_reset(struct kvm_vcpu *vcpu) -{ - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) - | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_PDPTR) - | (1 << VCPU_EXREG_SEGMENTS) - | (1 << VCPU_EXREG_CR0) - | (1 << VCPU_EXREG_CR3) - | (1 << VCPU_EXREG_CR4) - | (1 << VCPU_EXREG_EXIT_INFO_1) - | (1 << VCPU_EXREG_EXIT_INFO_2)); - vcpu->arch.regs_dirty = 0; -} +/* + * VMX_REGS_LAZY_LOAD_SET - The set of registers that will be updated in the + * cache on demand. Other registers not listed here are synced to + * the cache immediately after VM-Exit. + */ +#define VMX_REGS_LAZY_LOAD_SET ((1 << VCPU_REGS_RIP) | \ + (1 << VCPU_REGS_RSP) | \ + (1 << VCPU_EXREG_RFLAGS) | \ + (1 << VCPU_EXREG_PDPTR) | \ + (1 << VCPU_EXREG_SEGMENTS) | \ + (1 << VCPU_EXREG_CR0) | \ + (1 << VCPU_EXREG_CR3) | \ + (1 << VCPU_EXREG_CR4) | \ + (1 << VCPU_EXREG_EXIT_INFO_1) | \ + (1 << VCPU_EXREG_EXIT_INFO_2)) static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5a403d92833f..8912f44c640d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -118,6 +118,7 @@ static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); @@ -710,6 +711,17 @@ int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) } EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); +static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) +{ + if (err) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_COMPLETE_USER_EXIT); +} + void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; @@ -798,8 +810,9 @@ static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) /* * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; gpa_t real_gpa; int i; @@ -810,8 +823,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated * to an L1 GPA. */ - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(pdpt_gfn), - PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn), + PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); if (real_gpa == UNMAPPED_GVA) return 0; @@ -828,8 +841,12 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } } - memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); + if (memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) { + memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); + } vcpu->arch.pdptrs_from_userspace = false; return 1; @@ -856,7 +873,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG; cr0 |= X86_CR0_ET; @@ -886,11 +902,12 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && - is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) + is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && + !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; - if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + if (!(cr0 & X86_CR0_PG) && + (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))) return 1; static_call(kvm_x86_set_cr0)(vcpu, cr0); @@ -1050,8 +1067,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr4); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP; if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; @@ -1062,9 +1077,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if ((cr4 ^ old_cr4) & X86_CR4_LA57) return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) - && ((cr4 ^ old_cr4) & pdptr_bits) - && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, - kvm_read_cr3(vcpu))) + && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS) + && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { @@ -1153,14 +1167,14 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; - if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; if (cr3 != kvm_read_cr3(vcpu)) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); handle_tlb_flush: /* @@ -1330,7 +1344,7 @@ static const u32 msrs_to_save_all[] = { MSR_IA32_UMWAIT_CONTROL, MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, @@ -1814,22 +1828,36 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_msr); -static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { - int err = vcpu->run->msr.error; - if (!err) { + if (!vcpu->run->msr.error) { kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } +} + +static int complete_emulated_msr_access(struct kvm_vcpu *vcpu) +{ + return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error); +} - return static_call(kvm_x86_complete_emulated_msr)(vcpu, err); +static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_emulated_msr_access(vcpu); } -static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) +static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } +static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_fast_msr_access(vcpu); +} + static u64 kvm_msr_reason(int r) { switch (r) { @@ -1864,18 +1892,6 @@ static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, return 1; } -static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0, - complete_emulated_rdmsr, r); -} - -static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data, - complete_emulated_wrmsr, r); -} - int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); @@ -1884,18 +1900,16 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) r = kvm_get_msr(vcpu, ecx, &data); - /* MSR read failed? See if we should ask user space */ - if (r && kvm_get_msr_user_space(vcpu, ecx, r)) { - /* Bounce to user space */ - return 0; - } - if (!r) { trace_kvm_msr_read(ecx, data); kvm_rax_write(vcpu, data & -1u); kvm_rdx_write(vcpu, (data >> 32) & -1u); } else { + /* MSR read failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0, + complete_fast_rdmsr, r)) + return 0; trace_kvm_msr_read_ex(ecx); } @@ -1911,19 +1925,18 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) r = kvm_set_msr(vcpu, ecx, data); - /* MSR write failed? See if we should ask user space */ - if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) - /* Bounce to user space */ - return 0; - - /* Signal all other negative errors to userspace */ - if (r < 0) - return r; - - if (!r) + if (!r) { trace_kvm_msr_write(ecx, data); - else + } else { + /* MSR write failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data, + complete_fast_msr_access, r)) + return 0; + /* Signal all other negative errors to userspace */ + if (r < 0) + return r; trace_kvm_msr_write_ex(ecx, data); + } return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } @@ -2816,7 +2829,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; - int i; + unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); @@ -3065,7 +3078,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) static void kvmclock_update_fn(struct work_struct *work) { - int i; + unsigned long i; struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_update_work); @@ -3258,6 +3271,29 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static_call(kvm_x86_tlb_flush_guest)(vcpu); } + +static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + static_call(kvm_x86_tlb_flush_current)(vcpu); +} + +/* + * Service "local" TLB flush requests, which are specific to the current MMU + * context. In addition to the generic event handling in vcpu_enter_guest(), + * TLB flushes that are targeted at an MMU context also need to be serviced + * prior before nested VM-Enter/VM-Exit. + */ +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) +{ + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); + + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests); + static void record_steal_time(struct kvm_vcpu *vcpu) { struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; @@ -3389,7 +3425,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) return 1; - if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent)) + if (kvm_get_msr_feature(&msr_ent)) return 1; if (data & ~msr_ent.data) return 1; @@ -4133,6 +4169,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: @@ -4448,8 +4485,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -5124,6 +5160,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; + /* + * KVM does not correctly handle changing guest CPUID after KVM_RUN, as + * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't + * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page + * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with + * the core vCPU model on the fly, so fail. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5134,6 +5181,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; + /* + * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in + * KVM_SET_CPUID case above. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5650,7 +5705,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) * VM-Exit. */ struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); @@ -5698,6 +5753,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); @@ -5918,7 +5974,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, ret = 0; + unsigned long i; + int ret = 0; mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -6078,6 +6135,7 @@ set_identity_unlock: /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -6460,13 +6518,14 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.mmu; gpa_t t_gpa; BUG_ON(!mmu_is_nested(vcpu)); /* NPT walks are always user-walks */ access |= PFERR_USER_MASK; - t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception); + t_gpa = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception); return t_gpa; } @@ -6474,25 +6533,31 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); @@ -6500,19 +6565,21 @@ EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception); } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6540,13 +6607,14 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; /* Inline kvm_read_guest_virt_helper for speed. */ - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK, + exception); if (unlikely(gpa == UNMAPPED_GVA)) return X86EMUL_PROPAGATE_FAULT; @@ -6605,13 +6673,12 @@ static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, - access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6698,6 +6765,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); @@ -6715,7 +6783,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, return 1; } - *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + *gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); if (*gpa == UNMAPPED_GVA) return -1; @@ -7077,7 +7145,13 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count) { if (vcpu->arch.pio.count) { - /* Complete previous iteration. */ + /* + * Complete a previous iteration that required userspace I/O. + * Note, @count isn't guaranteed to match pio.count as userspace + * can modify ECX before rerunning the vCPU. Ignore any such + * shenanigans as KVM doesn't support modifying the rep count, + * and the emulator ensures @count doesn't overflow the buffer. + */ } else { int r = __emulator_pio_in(vcpu, size, port, count); if (!r) @@ -7086,7 +7160,6 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, /* Results already available, fall through. */ } - WARN_ON(count != vcpu->arch.pio.count); complete_emulator_pio_in(vcpu, val); return 1; } @@ -7344,7 +7417,8 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, r = kvm_get_msr(vcpu, msr_index, pdata); - if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -7360,7 +7434,8 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, r = kvm_set_msr(vcpu, msr_index, data); - if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, + complete_emulated_msr_access, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -8078,12 +8153,23 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } /* - * Note, EMULTYPE_SKIP is intended for use *only* by vendor callbacks - * for kvm_skip_emulated_instruction(). The caller is responsible for - * updating interruptibility state and injecting single-step #DBs. + * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT is intended for + * use *only* by vendor callbacks for kvm_skip_emulated_instruction(). + * The caller is responsible for updating interruptibility state and + * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { - kvm_rip_write(vcpu, ctxt->_eip); + if (ctxt->mode != X86EMUL_MODE_PROT64) + ctxt->eip = (u32)ctxt->_eip; + else + ctxt->eip = ctxt->_eip; + + if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) { + r = 1; + goto writeback; + } + + kvm_rip_write(vcpu, ctxt->eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); return 1; @@ -8147,11 +8233,15 @@ restart: writeback = false; r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; + } else if (vcpu->arch.complete_userspace_io) { + writeback = false; + r = 0; } else if (r == EMULATION_RESTART) goto restart; else r = 1; +writeback: if (writeback) { unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); @@ -8344,7 +8434,8 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i, send_ipi = 0; + int send_ipi = 0; + unsigned long i; /* * We allow guests to temporarily run on slowing clocks, @@ -8517,9 +8608,8 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; - struct kvm_vcpu *vcpu; - int i; + unsigned long i; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -8680,8 +8770,15 @@ void kvm_arch_exit(void) #endif } -static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = state; @@ -8692,11 +8789,11 @@ static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) } } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) { - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); } -EXPORT_SYMBOL_GPL(kvm_vcpu_halt); +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { @@ -8705,7 +8802,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ - return kvm_vcpu_halt(vcpu) && ret; + return kvm_emulate_halt_noskip(vcpu) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_halt); @@ -8713,7 +8810,8 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); @@ -8776,10 +8874,9 @@ static void kvm_apicv_init(struct kvm *kvm) { init_rwsem(&kvm->arch.apicv_update_lock); - if (enable_apicv) - clear_bit(APICV_INHIBIT_REASON_DISABLE, - &kvm->arch.apicv_inhibit_reasons); - else + set_bit(APICV_INHIBIT_REASON_ABSENT, + &kvm->arch.apicv_inhibit_reasons); + if (!enable_apicv) set_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); } @@ -8952,14 +9049,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - /* - * if_flag is obsolete and useless, so do not bother - * setting it for SEV-ES guests. Userspace can just - * use kvm_run->ready_for_interrupt_injection. - */ - kvm_run->if_flag = !vcpu->arch.guest_state_protected - && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - + kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu); kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); @@ -9528,8 +9618,7 @@ 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 (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -9648,10 +9737,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Flushing all ASIDs flushes the current ASID... */ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) - kvm_vcpu_flush_tlb_guest(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -9802,10 +9888,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* * This handles the case where a posted interrupt was - * notified with kvm_vcpu_kick. + * notified with kvm_vcpu_kick. Assigned devices can + * use the POSTED_INTR_VECTOR even if APICv is disabled, + * so do it even if APICv is disabled on this vCPU. */ - if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; @@ -9849,8 +9937,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; @@ -9956,7 +10044,10 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (!kvm_arch_vcpu_runnable(vcpu) && (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) + kvm_vcpu_halt(vcpu); + else + kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (kvm_x86_ops.post_block) @@ -10516,7 +10607,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, vcpu->arch.cr2 = sregs->cr2; *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); @@ -10533,7 +10624,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); *mmu_reset_needed = 1; } srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -10631,7 +10722,7 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { bool inhibit = false; struct kvm_vcpu *vcpu; - int i; + unsigned long i; down_write(&kvm->arch.apicv_update_lock); @@ -11119,7 +11210,7 @@ int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; @@ -11372,7 +11463,7 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; /* @@ -11382,15 +11473,8 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_clear_async_pf_completion_queue(vcpu); kvm_unload_vcpu_mmu(vcpu); } - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); + kvm_destroy_vcpus(kvm); } void kvm_arch_sync_events(struct kvm *kvm) @@ -11558,9 +11642,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) } static int kvm_alloc_memslot_metadata(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages) + struct kvm_memory_slot *slot) { + unsigned long npages = slot->npages; int i, r; /* @@ -11625,7 +11709,7 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; /* * memslots->generation has been incremented. @@ -11639,13 +11723,18 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(kvm, memslot, - mem->memory_size >> PAGE_SHIFT); + return kvm_alloc_memslot_metadata(kvm, new); + + if (change == KVM_MR_FLAGS_ONLY) + memcpy(&new->arch, &old->arch, sizeof(old->arch)); + else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) + return -EIO; + return 0; } @@ -11669,13 +11758,15 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES; + u32 old_flags = old ? old->flags : 0; + u32 new_flags = new ? new->flags : 0; + bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; /* * Update CPU dirty logging if dirty logging is being toggled. This * applies to all operations. */ - if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES) + if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* @@ -11693,7 +11784,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot(). */ - if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) + if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) return; /* @@ -11701,7 +11792,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty * logging isn't being toggled on or off. */ - if (WARN_ON_ONCE(!((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES))) + if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) return; if (!log_dirty_pages) { @@ -11737,14 +11828,18 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (!kvm->arch.n_requested_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, - kvm_mmu_calculate_default_mmu_pages(kvm)); + if (!kvm->arch.n_requested_mmu_pages && + (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { + unsigned long nr_mmu_pages; + + nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO; + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + } kvm_mmu_slot_apply_flags(kvm, old, new, change); @@ -12254,12 +12349,13 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; struct x86_exception fault; u32 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { + mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed @@ -12596,6 +12692,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 997669ae9caa..4abcd8d9836d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val, #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) @@ -185,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; } -static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.tlb_flush; - static_call(kvm_x86_tlb_flush_current)(vcpu); -} - static inline int is_pae(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_PAE); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 4a3da7592b99..38d24d2ab38b 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -72,6 +72,7 @@ static void __init setup_real_mode(void) #ifdef CONFIG_X86_64 u64 *trampoline_pgd; u64 efer; + int i; #endif base = (unsigned char *)real_mode_header; @@ -128,8 +129,17 @@ static void __init setup_real_mode(void) trampoline_header->flags = 0; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); + + /* Map the real mode stub as virtual == physical */ trampoline_pgd[0] = trampoline_pgd_entry.pgd; - trampoline_pgd[511] = init_top_pgt[511].pgd; + + /* + * Include the entirety of the kernel mapping into the trampoline + * PGD. This way, all mappings present in the normal kernel page + * tables are usable while running on trampoline_pgd. + */ + for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++) + trampoline_pgd[i] = init_top_pgt[i].pgd; #endif sme_sev_setup_real_mode(trampoline_header); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 220dd9678494..444d824775f6 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* @@ -193,6 +194,25 @@ SYM_CODE_START(xen_iret) SYM_CODE_END(xen_iret) /* + * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is + * also the kernel stack. Reusing swapgs_restore_regs_and_return_to_usermode() + * in XEN pv would cause %rsp to move up to the top of the kernel stack and + * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI + * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET + * frame at the same address is useless. + */ +SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode) + UNWIND_HINT_REGS + POP_REGS + + /* stackleak_erase() can work safely on the kernel stack. */ + STACKLEAK_ERASE_NOCLOBBER + + addq $8, %rsp /* skip regs->orig_ax */ + jmp xen_iret +SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) + +/* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: * - kernel gs diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index a8a041609c5d..7b4359312c25 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -121,7 +121,6 @@ void flush_cache_page(struct vm_area_struct*, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *); void local_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -138,9 +137,7 @@ void local_flush_cache_page(struct vm_area_struct *vma, #define flush_cache_vunmap(start,end) do { } while (0) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO #define flush_dcache_page(page) do { } while (0) -static inline void flush_dcache_folio(struct folio *folio) { } #define flush_icache_range local_flush_icache_range #define flush_cache_page(vma, addr, pfn) do { } while (0) diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 104b327f8ac9..3e3e1a506bed 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -419,3 +419,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv |