diff --git a/MAINTAINERS b/MAINTAINERS index 11dde284a426e626ac0e240696e2bfe82f6cc752..fb63e53ea3c8af52bb8dc34aac67826143b987e3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6312,6 +6312,7 @@ L: devel@linuxdriverproject.org S: Maintained F: Documentation/networking/netvsc.txt F: arch/x86/include/asm/mshyperv.h +F: arch/x86/include/asm/trace/hyperv.h F: arch/x86/include/uapi/asm/hyperv.h F: arch/x86/kernel/cpu/mshyperv.c F: arch/x86/hyperv @@ -6325,6 +6326,7 @@ F: drivers/uio/uio_hv_generic.c F: drivers/video/fbdev/hyperv_fb.c F: net/vmw_vsock/hyperv_transport.c F: include/linux/hyperv.h +F: include/uapi/linux/hyperv.h F: tools/hv/ F: Documentation/ABI/stable/sysfs-bus-vmbus diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index f65a804b86f0535927f4c3fca23eb920755a6409..0038a2d10a7a575f1aa24aa6485fd277503d1753 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -8,7 +8,7 @@ obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_XEN) += xen/ # Hyper-V paravirtualization support -obj-$(CONFIG_HYPERVISOR_GUEST) += hyperv/ +obj-$(subst m,y,$(CONFIG_HYPERV)) += hyperv/ obj-y += realmode/ obj-y += kernel/ diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 171ae09864d7dc24199c0d316bbb3a28a17b7425..367a8203cfcf5e556b5583b037d0ad65a72225d3 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1 +1 @@ -obj-y := hv_init.o +obj-y := hv_init.o mmu.o diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 5b882cc0c0e9a96e1bd8beeec260ef657a439de4..1a8eb550c40f13d8f4f4f5d049e09d323a2bb185 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -26,6 +26,8 @@ #include #include #include +#include +#include #ifdef CONFIG_HYPERV_TSCPAGE @@ -75,10 +77,25 @@ static struct clocksource hyperv_cs_msr = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static void *hypercall_pg; +void *hv_hypercall_pg; +EXPORT_SYMBOL_GPL(hv_hypercall_pg); struct clocksource *hyperv_cs; EXPORT_SYMBOL_GPL(hyperv_cs); +u32 *hv_vp_index; +EXPORT_SYMBOL_GPL(hv_vp_index); + +static int hv_cpu_init(unsigned int cpu) +{ + u64 msr_vp_index; + + hv_get_vp_index(msr_vp_index); + + hv_vp_index[smp_processor_id()] = msr_vp_index; + + return 0; +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -94,6 +111,16 @@ void hyperv_init(void) if (x86_hyper != &x86_hyper_ms_hyperv) return; + /* Allocate percpu VP index */ + hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index), + GFP_KERNEL); + if (!hv_vp_index) + return; + + if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online", + hv_cpu_init, NULL) < 0) + goto free_vp_index; + /* * Setup the hypercall page and enable hypercalls. * 1. Register the guest ID @@ -102,17 +129,19 @@ void hyperv_init(void) guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); - hypercall_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX); - if (hypercall_pg == NULL) { + hv_hypercall_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX); + if (hv_hypercall_pg == NULL) { wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); - return; + goto free_vp_index; } rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); hypercall_msr.enable = 1; - hypercall_msr.guest_physical_address = vmalloc_to_pfn(hypercall_pg); + hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hyper_alloc_mmu(); + /* * Register Hyper-V specific clocksource. */ @@ -148,6 +177,12 @@ void hyperv_init(void) hyperv_cs = &hyperv_cs_msr; if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); + + return; + +free_vp_index: + kfree(hv_vp_index); + hv_vp_index = NULL; } /* @@ -170,51 +205,6 @@ void hyperv_cleanup(void) } EXPORT_SYMBOL_GPL(hyperv_cleanup); -/* - * hv_do_hypercall- Invoke the specified hypercall - */ -u64 hv_do_hypercall(u64 control, void *input, void *output) -{ - u64 input_address = (input) ? virt_to_phys(input) : 0; - u64 output_address = (output) ? virt_to_phys(output) : 0; -#ifdef CONFIG_X86_64 - u64 hv_status = 0; - - if (!hypercall_pg) - return (u64)ULLONG_MAX; - - __asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8"); - __asm__ __volatile__("call *%3" : "=a" (hv_status) : - "c" (control), "d" (input_address), - "m" (hypercall_pg)); - - return hv_status; - -#else - - u32 control_hi = control >> 32; - u32 control_lo = control & 0xFFFFFFFF; - u32 hv_status_hi = 1; - u32 hv_status_lo = 1; - u32 input_address_hi = input_address >> 32; - u32 input_address_lo = input_address & 0xFFFFFFFF; - u32 output_address_hi = output_address >> 32; - u32 output_address_lo = output_address & 0xFFFFFFFF; - - if (!hypercall_pg) - return (u64)ULLONG_MAX; - - __asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi), - "=a"(hv_status_lo) : "d" (control_hi), - "a" (control_lo), "b" (input_address_hi), - "c" (input_address_lo), "D"(output_address_hi), - "S"(output_address_lo), "m" (hypercall_pg)); - - return hv_status_lo | ((u64)hv_status_hi << 32); -#endif /* !x86_64 */ -} -EXPORT_SYMBOL_GPL(hv_do_hypercall); - void hyperv_report_panic(struct pt_regs *regs) { static bool panic_reported; diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c new file mode 100644 index 0000000000000000000000000000000000000000..39e7f6e50919117087fe663e013cd77d12b16b7b --- /dev/null +++ b/arch/x86/hyperv/mmu.c @@ -0,0 +1,272 @@ +#define pr_fmt(fmt) "Hyper-V: " fmt + +#include +#include +#include +#include + +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ +struct hv_flush_pcpu { + u64 address_space; + u64 flags; + u64 processor_mask; + u64 gva_list[]; +}; + +/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ +struct hv_flush_pcpu_ex { + u64 address_space; + u64 flags; + struct { + u64 format; + u64 valid_bank_mask; + u64 bank_contents[]; + } hv_vp_set; + u64 gva_list[]; +}; + +/* Each gva in gva_list encodes up to 4096 pages to flush */ +#define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) + +static struct hv_flush_pcpu __percpu *pcpu_flush; + +static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex; + +/* + * Fills in gva_list starting from offset. Returns the number of items added. + */ +static inline int fill_gva_list(u64 gva_list[], int offset, + unsigned long start, unsigned long end) +{ + int gva_n = offset; + unsigned long cur = start, diff; + + do { + diff = end > cur ? end - cur : 0; + + gva_list[gva_n] = cur & PAGE_MASK; + /* + * Lower 12 bits encode the number of additional + * pages to flush (in addition to the 'cur' page). + */ + if (diff >= HV_TLB_FLUSH_UNIT) + gva_list[gva_n] |= ~PAGE_MASK; + else if (diff) + gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT; + + cur += HV_TLB_FLUSH_UNIT; + gva_n++; + + } while (cur < end); + + return gva_n - offset; +} + +/* Return the number of banks in the resulting vp_set */ +static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, + const struct cpumask *cpus) +{ + int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + + /* + * Some banks may end up being empty but this is acceptable. + */ + for_each_cpu(cpu, cpus) { + vcpu = hv_cpu_number_to_vp_number(cpu); + vcpu_bank = vcpu / 64; + vcpu_offset = vcpu % 64; + + /* valid_bank_mask can represent up to 64 banks */ + if (vcpu_bank >= 64) + return 0; + + __set_bit(vcpu_offset, (unsigned long *) + &flush->hv_vp_set.bank_contents[vcpu_bank]); + if (vcpu_bank >= nr_bank) + nr_bank = vcpu_bank + 1; + } + flush->hv_vp_set.valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0); + + return nr_bank; +} + +static void hyperv_flush_tlb_others(const struct cpumask *cpus, + const struct flush_tlb_info *info) +{ + int cpu, vcpu, gva_n, max_gvas; + struct hv_flush_pcpu *flush; + u64 status = U64_MAX; + unsigned long flags; + + trace_hyperv_mmu_flush_tlb_others(cpus, info); + + if (!pcpu_flush || !hv_hypercall_pg) + goto do_native; + + if (cpumask_empty(cpus)) + return; + + local_irq_save(flags); + + flush = this_cpu_ptr(pcpu_flush); + + if (info->mm) { + flush->address_space = virt_to_phys(info->mm->pgd); + flush->flags = 0; + } else { + flush->address_space = 0; + flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + } + + flush->processor_mask = 0; + if (cpumask_equal(cpus, cpu_present_mask)) { + flush->flags |= HV_FLUSH_ALL_PROCESSORS; + } else { + for_each_cpu(cpu, cpus) { + vcpu = hv_cpu_number_to_vp_number(cpu); + if (vcpu >= 64) + goto do_native; + + __set_bit(vcpu, (unsigned long *) + &flush->processor_mask); + } + } + + /* + * We can flush not more than max_gvas with one hypercall. Flush the + * whole address space if we were asked to do more. + */ + max_gvas = (PAGE_SIZE - sizeof(*flush)) / sizeof(flush->gva_list[0]); + + if (info->end == TLB_FLUSH_ALL) { + flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; + status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, + flush, NULL); + } else if (info->end && + ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { + status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, + flush, NULL); + } else { + gva_n = fill_gva_list(flush->gva_list, 0, + info->start, info->end); + status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST, + gva_n, 0, flush, NULL); + } + + local_irq_restore(flags); + + if (!(status & HV_HYPERCALL_RESULT_MASK)) + return; +do_native: + native_flush_tlb_others(cpus, info); +} + +static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, + const struct flush_tlb_info *info) +{ + int nr_bank = 0, max_gvas, gva_n; + struct hv_flush_pcpu_ex *flush; + u64 status = U64_MAX; + unsigned long flags; + + trace_hyperv_mmu_flush_tlb_others(cpus, info); + + if (!pcpu_flush_ex || !hv_hypercall_pg) + goto do_native; + + if (cpumask_empty(cpus)) + return; + + local_irq_save(flags); + + flush = this_cpu_ptr(pcpu_flush_ex); + + if (info->mm) { + flush->address_space = virt_to_phys(info->mm->pgd); + flush->flags = 0; + } else { + flush->address_space = 0; + flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + } + + flush->hv_vp_set.valid_bank_mask = 0; + + if (!cpumask_equal(cpus, cpu_present_mask)) { + flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K; + nr_bank = cpumask_to_vp_set(flush, cpus); + } + + if (!nr_bank) { + flush->hv_vp_set.format = HV_GENERIC_SET_ALL; + flush->flags |= HV_FLUSH_ALL_PROCESSORS; + } + + /* + * We can flush not more than max_gvas with one hypercall. Flush the + * whole address space if we were asked to do more. + */ + max_gvas = + (PAGE_SIZE - sizeof(*flush) - nr_bank * + sizeof(flush->hv_vp_set.bank_contents[0])) / + sizeof(flush->gva_list[0]); + + if (info->end == TLB_FLUSH_ALL) { + flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; + status = hv_do_rep_hypercall( + HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, + 0, nr_bank + 2, flush, NULL); + } else if (info->end && + ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { + status = hv_do_rep_hypercall( + HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, + 0, nr_bank + 2, flush, NULL); + } else { + gva_n = fill_gva_list(flush->gva_list, nr_bank, + info->start, info->end); + status = hv_do_rep_hypercall( + HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX, + gva_n, nr_bank + 2, flush, NULL); + } + + local_irq_restore(flags); + + if (!(status & HV_HYPERCALL_RESULT_MASK)) + return; +do_native: + native_flush_tlb_others(cpus, info); +} + +void hyperv_setup_mmu_ops(void) +{ + if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) + return; + + setup_clear_cpu_cap(X86_FEATURE_PCID); + + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) { + pr_info("Using hypercall for remote TLB flush\n"); + pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; + } else { + pr_info("Using ext hypercall for remote TLB flush\n"); + pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex; + } +} + +void hyper_alloc_mmu(void) +{ + if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) + return; + + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + else + pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); +} diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 58b9291b46d87184fdba3b6069e84ca700f43624..63cc96f064dc4987813352eb8ceba869d3738856 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -3,6 +3,8 @@ #include #include +#include +#include #include /* @@ -170,12 +172,155 @@ void hv_remove_crash_handler(void); #if IS_ENABLED(CONFIG_HYPERV) extern struct clocksource *hyperv_cs; +extern void *hv_hypercall_pg; + +static inline u64 hv_do_hypercall(u64 control, void *input, void *output) +{ + u64 input_address = input ? virt_to_phys(input) : 0; + u64 output_address = output ? virt_to_phys(output) : 0; + u64 hv_status; + register void *__sp asm(_ASM_SP); + +#ifdef CONFIG_X86_64 + if (!hv_hypercall_pg) + return U64_MAX; + + __asm__ __volatile__("mov %4, %%r8\n" + "call *%5" + : "=a" (hv_status), "+r" (__sp), + "+c" (control), "+d" (input_address) + : "r" (output_address), "m" (hv_hypercall_pg) + : "cc", "memory", "r8", "r9", "r10", "r11"); +#else + u32 input_address_hi = upper_32_bits(input_address); + u32 input_address_lo = lower_32_bits(input_address); + u32 output_address_hi = upper_32_bits(output_address); + u32 output_address_lo = lower_32_bits(output_address); + + if (!hv_hypercall_pg) + return U64_MAX; + + __asm__ __volatile__("call *%7" + : "=A" (hv_status), + "+c" (input_address_lo), "+r" (__sp) + : "A" (control), + "b" (input_address_hi), + "D"(output_address_hi), "S"(output_address_lo), + "m" (hv_hypercall_pg) + : "cc", "memory"); +#endif /* !x86_64 */ + return hv_status; +} + +#define HV_HYPERCALL_RESULT_MASK GENMASK_ULL(15, 0) +#define HV_HYPERCALL_FAST_BIT BIT(16) +#define HV_HYPERCALL_VARHEAD_OFFSET 17 +#define HV_HYPERCALL_REP_COMP_OFFSET 32 +#define HV_HYPERCALL_REP_COMP_MASK GENMASK_ULL(43, 32) +#define HV_HYPERCALL_REP_START_OFFSET 48 +#define HV_HYPERCALL_REP_START_MASK GENMASK_ULL(59, 48) + +/* Fast hypercall with 8 bytes of input and no output */ +static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) +{ + u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; + register void *__sp asm(_ASM_SP); + +#ifdef CONFIG_X86_64 + { + __asm__ __volatile__("call *%4" + : "=a" (hv_status), "+r" (__sp), + "+c" (control), "+d" (input1) + : "m" (hv_hypercall_pg) + : "cc", "r8", "r9", "r10", "r11"); + } +#else + { + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + + __asm__ __volatile__ ("call *%5" + : "=A"(hv_status), + "+c"(input1_lo), + "+r"(__sp) + : "A" (control), + "b" (input1_hi), + "m" (hv_hypercall_pg) + : "cc", "edi", "esi"); + } +#endif + return hv_status; +} + +/* + * Rep hypercalls. Callers of this functions are supposed to ensure that + * rep_count and varhead_size comply with Hyper-V hypercall definition. + */ +static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, + void *input, void *output) +{ + u64 control = code; + u64 status; + u16 rep_comp; + + control |= (u64)varhead_size << HV_HYPERCALL_VARHEAD_OFFSET; + control |= (u64)rep_count << HV_HYPERCALL_REP_COMP_OFFSET; + + do { + status = hv_do_hypercall(control, input, output); + if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) + return status; + + /* Bits 32-43 of status have 'Reps completed' data. */ + rep_comp = (status & HV_HYPERCALL_REP_COMP_MASK) >> + HV_HYPERCALL_REP_COMP_OFFSET; + + control &= ~HV_HYPERCALL_REP_START_MASK; + control |= (u64)rep_comp << HV_HYPERCALL_REP_START_OFFSET; + + touch_nmi_watchdog(); + } while (rep_comp < rep_count); + + return status; +} + +/* + * Hypervisor's notion of virtual processor ID is different from + * Linux' notion of CPU ID. This information can only be retrieved + * in the context of the calling CPU. Setup a map for easy access + * to this information. + */ +extern u32 *hv_vp_index; + +/** + * hv_cpu_number_to_vp_number() - Map CPU to VP. + * @cpu_number: CPU number in Linux terms + * + * This function returns the mapping between the Linux processor + * number and the hypervisor's virtual processor number, useful + * in making hypercalls and such that talk about specific + * processors. + * + * Return: Virtual processor number in Hyper-V terms + */ +static inline int hv_cpu_number_to_vp_number(int cpu_number) +{ + return hv_vp_index[cpu_number]; +} void hyperv_init(void); +void hyperv_setup_mmu_ops(void); +void hyper_alloc_mmu(void); void hyperv_report_panic(struct pt_regs *regs); bool hv_is_hypercall_page_setup(void); void hyperv_cleanup(void); -#endif +#else /* CONFIG_HYPERV */ +static inline void hyperv_init(void) {} +static inline bool hv_is_hypercall_page_setup(void) { return false; } +static inline void hyperv_cleanup(void) {} +static inline void hyperv_setup_mmu_ops(void) {} +#endif /* CONFIG_HYPERV */ + #ifdef CONFIG_HYPERV_TSCPAGE struct ms_hyperv_tsc_page *hv_get_tsc_page(void); static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h new file mode 100644 index 0000000000000000000000000000000000000000..4253bca9998904e882803690e023d970d20dd5cd --- /dev/null +++ b/arch/x86/include/asm/trace/hyperv.h @@ -0,0 +1,40 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hyperv + +#if !defined(_TRACE_HYPERV_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_HYPERV_H + +#include + +#if IS_ENABLED(CONFIG_HYPERV) + +TRACE_EVENT(hyperv_mmu_flush_tlb_others, + TP_PROTO(const struct cpumask *cpus, + const struct flush_tlb_info *info), + TP_ARGS(cpus, info), + TP_STRUCT__entry( + __field(unsigned int, ncpus) + __field(struct mm_struct *, mm) + __field(unsigned long, addr) + __field(unsigned long, end) + ), + TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); + __entry->mm = info->mm; + __entry->addr = info->start; + __entry->end = info->end; + ), + TP_printk("ncpus %d mm %p addr %lx, end %lx", + __entry->ncpus, __entry->mm, + __entry->addr, __entry->end) + ); + +#endif /* CONFIG_HYPERV */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/trace/ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE hyperv +#endif /* _TRACE_HYPERV_H */ + +/* This part must be outside protection */ +#include diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 127ddadee1a5ae2317db5682fe9132eb88326504..7032f4d8dff30be9557eedb26f6dcb779b26d3eb 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -149,6 +149,9 @@ */ #define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9) +/* Recommend using the newer ExProcessorMasks interface */ +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED (1 << 11) + /* * HV_VP_SET available */ @@ -242,7 +245,11 @@ (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) /* Declare the various hypercall operations. */ +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 #define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 #define HVCALL_POST_MESSAGE 0x005c #define HVCALL_SIGNAL_EVENT 0x005d @@ -259,6 +266,16 @@ #define HV_PROCESSOR_POWER_STATE_C2 2 #define HV_PROCESSOR_POWER_STATE_C3 3 +#define HV_FLUSH_ALL_PROCESSORS BIT(0) +#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) +#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) +#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3) + +enum HV_GENERIC_SET_FORMAT { + HV_GENERIC_SET_SPARCE_4K, + HV_GENERIC_SET_ALL, +}; + /* hypercall status code */ #define HV_STATUS_SUCCESS 0 #define HV_STATUS_INVALID_HYPERCALL_CODE 2 diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index fbafd24174afe5c3dfccb5ff024b78f7974213d4..3b3f713e15e5fea418ebc8eae3bc7a948570dd73 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -250,6 +250,7 @@ static void __init ms_hyperv_init_platform(void) * Setup the hook to get control post apic initialization. */ x86_platform.apic_post_init = hyperv_init; + hyperv_setup_mmu_ops(); #endif } diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 5a18aedcb3410bb461aca29998b324ef57970d3c..b901ece278dddb4f6aaf61c8b6479a26526af71a 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,16 +215,23 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) struct irq_alloc_info info; int polarity; int ret; + u8 gsi; if (dev->irq_managed && dev->irq > 0) return 0; + ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); + if (ret < 0) { + dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret); + return ret; + } + switch (intel_mid_identify_cpu()) { case INTEL_MID_CPU_CHIP_TANGIER: polarity = IOAPIC_POL_HIGH; /* Special treatment for IRQ0 */ - if (dev->irq == 0) { + if (gsi == 0) { /* * Skip HS UART common registers device since it has * IRQ0 assigned and not used by the kernel. @@ -253,10 +260,11 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to * IOAPIC RTE entries, so we just enable RTE for the device. */ - ret = mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info); + ret = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info); if (ret < 0) return ret; + dev->irq = ret; dev->irq_managed = 1; return 0; diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c index 5a0483e7bf662cb27044b7684567b644dfe49b81..dc036e511f48d3adc3261ca4d4214c1c6244dbe6 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c @@ -60,7 +60,7 @@ static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata) return 0; } -static struct bt_sfi_data tng_bt_sfi_data __initdata = { +static const struct bt_sfi_data tng_bt_sfi_data __initdata = { .setup = tng_bt_sfi_setup, }; diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c index 9e304e2ea4f55c456e7f0037a8963f6586ad2b19..4f5fa65a10110344aa3d763fdf5b73a5d6652c0b 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c @@ -30,13 +30,13 @@ static int tangier_probe(struct platform_device *pdev) { struct irq_alloc_info info; struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; - int gsi, irq; + int gsi = TANGIER_EXT_TIMER0_MSI; + int irq; if (!pdata) return -EINVAL; /* IOAPIC builds identity mapping between GSI and IRQ on MID */ - gsi = pdata->irq; ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0); irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info); if (irq < 0) { @@ -44,11 +44,11 @@ static int tangier_probe(struct platform_device *pdev) return irq; } + pdata->irq = irq; return 0; } static struct intel_mid_wdt_pdata tangier_pdata = { - .irq = TANGIER_EXT_TIMER0_MSI, .probe = tangier_probe, }; diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 12a272582cdc9f03553954f9f09cec265ce506b4..86676cec99a13fabd8761b64c8b8a2ec68ca97eb 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -183,6 +183,7 @@ void __init x86_intel_mid_early_setup(void) x86_init.timers.timer_init = intel_mid_time_init; x86_init.timers.setup_percpu_clockev = x86_init_noop; + x86_init.timers.wallclock_init = intel_mid_rtc_init; x86_init.irqs.pre_vector_init = x86_init_noop; @@ -191,7 +192,6 @@ void __init x86_intel_mid_early_setup(void) x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock; x86_platform.calibrate_tsc = intel_mid_calibrate_tsc; - x86_init.timers.wallclock_init = intel_mid_rtc_init; x86_platform.get_nmi_reason = intel_mid_get_nmi_reason; x86_init.pci.init = intel_mid_pci_init; diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c index ef03852ea6e8fdf2896a990398201ba24fd72e4f..49ec5b94c71f958868711ebc048cd068c3fbec23 100644 --- a/arch/x86/platform/intel-mid/pwr.c +++ b/arch/x86/platform/intel-mid/pwr.c @@ -444,7 +444,7 @@ static int mid_set_initial_state(struct mid_pwr *pwr, const u32 *states) static int pnw_set_initial_state(struct mid_pwr *pwr) { /* On Penwell SRAM must stay powered on */ - const u32 states[] = { + static const u32 states[] = { 0xf00fffff, /* PM_SSC(0) */ 0xffffffff, /* PM_SSC(1) */ 0xffffffff, /* PM_SSC(2) */ @@ -455,7 +455,7 @@ static int pnw_set_initial_state(struct mid_pwr *pwr) static int tng_set_initial_state(struct mid_pwr *pwr) { - const u32 states[] = { + static const u32 states[] = { 0xffffffff, /* PM_SSC(0) */ 0xffffffff, /* PM_SSC(1) */ 0xffffffff, /* PM_SSC(2) */ diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index c29cd5387a353ef013ff164bb8ee459a443d87a3..50b89ea0e60f85934b1ca97c7c179deda9f307da 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -3,6 +3,7 @@ menu "Microsoft Hyper-V guest support" config HYPERV tristate "Microsoft Hyper-V client drivers" depends on X86 && ACPI && PCI && X86_LOCAL_APIC && HYPERVISOR_GUEST + select PARAVIRT help Select this option to run Linux as a Hyper-V client operating system. diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 968af173c4c192f32beba063797f716cccb517f6..060df71c2e8b72f42020168fb574ff42f6827729 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -603,7 +603,7 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type) */ channel->numa_node = 0; channel->target_cpu = 0; - channel->target_vp = hv_context.vp_index[0]; + channel->target_vp = hv_cpu_number_to_vp_number(0); return; } @@ -687,7 +687,7 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type) } channel->target_cpu = cur_cpu; - channel->target_vp = hv_context.vp_index[cur_cpu]; + channel->target_vp = hv_cpu_number_to_vp_number(cur_cpu); } static void vmbus_wait_for_unload(void) @@ -809,21 +809,12 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr) /* * Setup state for signalling the host. */ - newchannel->sig_event = (struct hv_input_signal_event *) - (ALIGN((unsigned long) - &newchannel->sig_buf, - HV_HYPERCALL_PARAM_ALIGN)); - - newchannel->sig_event->connectionid.asu32 = 0; - newchannel->sig_event->connectionid.u.id = VMBUS_EVENT_CONNECTION_ID; - newchannel->sig_event->flag_number = 0; - newchannel->sig_event->rsvdz = 0; + newchannel->sig_event = VMBUS_EVENT_CONNECTION_ID; if (vmbus_proto_version != VERSION_WS2008) { newchannel->is_dedicated_interrupt = (offer->is_dedicated_interrupt != 0); - newchannel->sig_event->connectionid.u.id = - offer->connection_id; + newchannel->sig_event = offer->connection_id; } memcpy(&newchannel->offermsg, offer, @@ -1251,8 +1242,7 @@ struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary) return outgoing_channel; } - cur_cpu = hv_context.vp_index[get_cpu()]; - put_cpu(); + cur_cpu = hv_cpu_number_to_vp_number(smp_processor_id()); list_for_each_safe(cur, tmp, &primary->sc_list) { cur_channel = list_entry(cur, struct vmbus_channel, sc_list); if (cur_channel->state != CHANNEL_OPENED_STATE) diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 59c11ff90d1285addd24faa205b4b589ab4e646f..f41901f80b6456bf12f5cf0d1c98761520a3f68d 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -32,6 +32,8 @@ #include #include #include +#include + #include "hyperv_vmbus.h" @@ -94,7 +96,8 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, * the CPU attempting to connect may not be CPU 0. */ if (version >= VERSION_WIN8_1) { - msg->target_vcpu = hv_context.vp_index[smp_processor_id()]; + msg->target_vcpu = + hv_cpu_number_to_vp_number(smp_processor_id()); vmbus_connection.connect_cpu = smp_processor_id(); } else { msg->target_vcpu = 0; @@ -406,6 +409,6 @@ void vmbus_set_event(struct vmbus_channel *channel) if (!channel->is_dedicated_interrupt) vmbus_send_interrupt(child_relid); - hv_do_hypercall(HVCALL_SIGNAL_EVENT, channel->sig_event, NULL); + hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event); } EXPORT_SYMBOL_GPL(vmbus_set_event); diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 2ea12207caa01901beea079cd541b13ee67aa488..8267439dd1eec0ac32ed217edda4ff324f8e57fe 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -234,7 +234,6 @@ int hv_synic_init(unsigned int cpu) union hv_synic_siefp siefp; union hv_synic_sint shared_sint; union hv_synic_scontrol sctrl; - u64 vp_index; /* Setup the Synic's message page */ hv_get_simp(simp.as_uint64); @@ -275,14 +274,6 @@ int hv_synic_init(unsigned int cpu) hv_context.synic_initialized = true; - /* - * Setup the mapping between Hyper-V's notion - * of cpuid and Linux' notion of cpuid. - * This array will be indexed using Linux cpuid. - */ - hv_get_vp_index(vp_index); - hv_context.vp_index[cpu] = (u32)vp_index; - /* * Register the per-cpu clockevent source. */ diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 1b6a5e0dfa7511b07ff6ed15ad4563d9b5a2ff05..49569f8fe038ad4cac53bce3e9c596e91feaf1c1 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -228,17 +228,6 @@ struct hv_context { struct hv_per_cpu_context __percpu *cpu_context; - /* - * Hypervisor's notion of virtual processor ID is different from - * Linux' notion of CPU ID. This information can only be retrieved - * in the context of the calling CPU. Setup a map for easy access - * to this information: - * - * vp_index[a] is the Hyper-V's processor ID corresponding to - * Linux cpuid 'a'. - */ - u32 vp_index[NR_CPUS]; - /* * To manage allocations in a NUMA node. * Array indexed by numa node ID. diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 43160a2eafe0e33c319c1e42468bc790867b80d6..a9d49f6f6501ccb1965217abb429d13571f26f12 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1454,23 +1454,6 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size) } EXPORT_SYMBOL_GPL(vmbus_free_mmio); -/** - * vmbus_cpu_number_to_vp_number() - Map CPU to VP. - * @cpu_number: CPU number in Linux terms - * - * This function returns the mapping between the Linux processor - * number and the hypervisor's virtual processor number, useful - * in making hypercalls and such that talk about specific - * processors. - * - * Return: Virtual processor number in Hyper-V terms - */ -int vmbus_cpu_number_to_vp_number(int cpu_number) -{ - return hv_context.vp_index[cpu_number]; -} -EXPORT_SYMBOL_GPL(vmbus_cpu_number_to_vp_number); - static int vmbus_acpi_add(struct acpi_device *device) { acpi_status result; diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c index 415dcc69a5027d0f39d8a0ba33f9b579e2ebf9b3..aba041438566944c7be46dcd21fdc2b0476a87f4 100644 --- a/drivers/pci/host/pci-hyperv.c +++ b/drivers/pci/host/pci-hyperv.c @@ -562,52 +562,6 @@ static void put_pcichild(struct hv_pci_dev *hv_pcidev, static void get_hvpcibus(struct hv_pcibus_device *hv_pcibus); static void put_hvpcibus(struct hv_pcibus_device *hv_pcibus); - -/* - * Temporary CPU to vCPU mapping to address transitioning - * vmbus_cpu_number_to_vp_number() being migrated to - * hv_cpu_number_to_vp_number() in a separate patch. Once that patch - * has been picked up in the main line, remove this code here and use - * the official code. - */ -static struct hv_tmpcpumap -{ - bool initialized; - u32 vp_index[NR_CPUS]; -} hv_tmpcpumap; - -static void hv_tmpcpumap_init_cpu(void *_unused) -{ - int cpu = smp_processor_id(); - u64 vp_index; - - hv_get_vp_index(vp_index); - - hv_tmpcpumap.vp_index[cpu] = vp_index; -} - -static void hv_tmpcpumap_init(void) -{ - if (hv_tmpcpumap.initialized) - return; - - memset(hv_tmpcpumap.vp_index, -1, sizeof(hv_tmpcpumap.vp_index)); - on_each_cpu(hv_tmpcpumap_init_cpu, NULL, true); - hv_tmpcpumap.initialized = true; -} - -/** - * hv_tmp_cpu_nr_to_vp_nr() - Convert Linux CPU nr to Hyper-V vCPU nr - * - * Remove once vmbus_cpu_number_to_vp_number() has been converted to - * hv_cpu_number_to_vp_number() and replace callers appropriately. - */ -static u32 hv_tmp_cpu_nr_to_vp_nr(int cpu) -{ - return hv_tmpcpumap.vp_index[cpu]; -} - - /** * devfn_to_wslot() - Convert from Linux PCI slot to Windows * @devfn: The Linux representation of PCI slot @@ -971,7 +925,7 @@ static void hv_irq_unmask(struct irq_data *data) var_size = 1 + HV_VP_SET_BANK_COUNT_MAX; for_each_cpu_and(cpu, dest, cpu_online_mask) { - cpu_vmbus = hv_tmp_cpu_nr_to_vp_nr(cpu); + cpu_vmbus = hv_cpu_number_to_vp_number(cpu); if (cpu_vmbus >= HV_VP_SET_BANK_COUNT_MAX * 64) { dev_err(&hbus->hdev->device, @@ -986,7 +940,7 @@ static void hv_irq_unmask(struct irq_data *data) } else { for_each_cpu_and(cpu, dest, cpu_online_mask) { params->int_target.vp_mask |= - (1ULL << hv_tmp_cpu_nr_to_vp_nr(cpu)); + (1ULL << hv_cpu_number_to_vp_number(cpu)); } } @@ -1063,7 +1017,7 @@ static u32 hv_compose_msi_req_v2( */ cpu = cpumask_first_and(affinity, cpu_online_mask); int_pkt->int_desc.processor_array[0] = - hv_tmp_cpu_nr_to_vp_nr(cpu); + hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; return sizeof(*int_pkt); @@ -2490,8 +2444,6 @@ static int hv_pci_probe(struct hv_device *hdev, return -ENOMEM; hbus->state = hv_pcibus_init; - hv_tmpcpumap_init(); - /* * The PCI bus "domain" is what is called "segment" in ACPI and * other specs. Pull it from the instance ID, to get something diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index e4bbf7dc99322586d75b57a5a066f658d7bbbe7d..c458d7b7ad197688469772fb0c842180c668864c 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -661,18 +661,6 @@ union hv_connection_id { } u; }; -/* Definition of the hv_signal_event hypercall input structure. */ -struct hv_input_signal_event { - union hv_connection_id connectionid; - u16 flag_number; - u16 rsvdz; -}; - -struct hv_input_signal_event_buffer { - u64 align8; - struct hv_input_signal_event event; -}; - enum hv_numa_policy { HV_BALANCED = 0, HV_LOCALIZED, @@ -754,8 +742,7 @@ struct vmbus_channel { } callback_mode; bool is_dedicated_interrupt; - struct hv_input_signal_event_buffer sig_buf; - struct hv_input_signal_event *sig_event; + u64 sig_event; /* * Starting with win8, this field will be used to specify @@ -1151,8 +1138,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, resource_size_t size, resource_size_t align, bool fb_overlap_ok); void vmbus_free_mmio(resource_size_t start, resource_size_t size); -int vmbus_cpu_number_to_vp_number(int cpu_number); -u64 hv_do_hypercall(u64 control, void *input, void *output); /* * GUID definitions of various offer types - services offered to the guest.