Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751874AbdFIN3L (ORCPT ); Fri, 9 Jun 2017 09:29:11 -0400 Received: from mx1.redhat.com ([209.132.183.28]:21874 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751543AbdFIN3J (ORCPT ); Fri, 9 Jun 2017 09:29:09 -0400 DMARC-Filter: OpenDMARC Filter v1.3.2 mx1.redhat.com AC926659AE Authentication-Results: ext-mx09.extmail.prod.ext.phx2.redhat.com; dmarc=none (p=none dis=none) header.from=redhat.com Authentication-Results: ext-mx09.extmail.prod.ext.phx2.redhat.com; spf=pass smtp.mailfrom=vkuznets@redhat.com DKIM-Filter: OpenDKIM Filter v2.11.0 mx1.redhat.com AC926659AE From: Vitaly Kuznetsov To: devel@linuxdriverproject.org Cc: x86@kernel.org, linux-kernel@vger.kernel.org, "K. Y. Srinivasan" , Haiyang Zhang , Stephen Hemminger , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Steven Rostedt , Jork Loeser , Simon Xiao , Andy Lutomirski , Andy Shevchenko Subject: [PATCH v8 08/10] x86/hyper-v: use hypercall for remote TLB flush Date: Fri, 9 Jun 2017 15:27:34 +0200 Message-Id: <20170609132736.13699-9-vkuznets@redhat.com> In-Reply-To: <20170609132736.13699-1-vkuznets@redhat.com> References: <20170609132736.13699-1-vkuznets@redhat.com> X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.38]); Fri, 09 Jun 2017 13:28:39 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7588 Lines: 248 Hyper-V host can suggest us to use hypercall for doing remote TLB flush, this is supposed to work faster than IPIs. Implementation details: to do HvFlushVirtualAddress{Space,List} hypercalls we need to put the input somewhere in memory and we don't really want to have memory allocation on each call so we pre-allocate per cpu memory areas on boot. pv_ops patching is happening very early so we need to separate hyperv_setup_mmu_ops() and hyper_alloc_mmu(). It is possible and easy to implement local TLB flushing too and there is even a hint for that. However, I don't see a room for optimization on the host side as both hypercall and native tlb flush will result in vmexit. The hint is also not set on modern Hyper-V versions. Signed-off-by: Vitaly Kuznetsov --- arch/x86/hyperv/Makefile | 2 +- arch/x86/hyperv/hv_init.c | 2 + arch/x86/hyperv/mmu.c | 135 +++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/mshyperv.h | 3 + arch/x86/include/uapi/asm/hyperv.h | 7 ++ arch/x86/kernel/cpu/mshyperv.c | 1 + 6 files changed, 149 insertions(+), 1 deletion(-) create mode 100644 arch/x86/hyperv/mmu.c diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 171ae09..367a820 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 e93b9a0..1a8eb55 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -140,6 +140,8 @@ void hyperv_init(void) 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. */ diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c new file mode 100644 index 0000000..fe87ffe --- /dev/null +++ b/arch/x86/hyperv/mmu.c @@ -0,0 +1,135 @@ +#include +#include +#include +#include + +#include +#include +#include +#include + +/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ +struct hv_flush_pcpu { + u64 address_space; + u64 flags; + u64 processor_mask; + 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; + +/* + * Fills in gva_list starting from offset. Returns the number of items filled + * in gva_list (including offset) + */ +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; +} + +static void hyperv_flush_tlb_others(const struct cpumask *cpus, + struct mm_struct *mm, unsigned long start, + unsigned long end) +{ + int cpu, vcpu, gva_n, max_gvas; + struct hv_flush_pcpu *flush; + u64 status = U64_MAX; + unsigned long flags; + + 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 (mm) { + flush->address_space = virt_to_phys(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) + __set_bit(vcpu, (unsigned long *) + &flush->processor_mask); + else + goto do_native; + } + } + + /* + * 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 (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 (end && ((end - 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, start, 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, mm, start, end); +} + +void hyperv_setup_mmu_ops(void) +{ + if (ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED) { + pr_info("Hyper-V: Using hypercall for remote TLB flush\n"); + pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; + } +} + +void hyper_alloc_mmu(void) +{ + if (ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED) + pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); +} diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 7581251..3710c84 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -309,6 +309,8 @@ static inline int hv_cpu_number_to_vp_number(int 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); @@ -316,6 +318,7 @@ void hyperv_cleanup(void); static inline void hyperv_init(void) {} static inline bool hv_is_hypercall_page_setup(void) { return false; } static inline hyperv_cleanup(void) {} +static inline void hyperv_setup_mmu_ops(void) {} #endif /* CONFIG_HYPERV */ #ifdef CONFIG_HYPERV_TSCPAGE diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 432df4b..cc0e70c 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -239,6 +239,8 @@ (~((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_POST_MESSAGE 0x005c #define HVCALL_SIGNAL_EVENT 0x005d @@ -256,6 +258,11 @@ #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) + /* 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 f259e01..2a1918d 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -239,6 +239,7 @@ 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 } -- 2.9.4