From d063de55f4799261858676d5cfa49a1612cd57ea Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Wed, 9 Mar 2022 16:46:50 +0800 Subject: [PATCH] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint If guest kernel is configured with nopvspin, or CONFIG_PARAVIRT_SPINLOCK is disabled, or guest find its has dedicated pCPUs from realtime hint feature, the pvspinlock will be disabled, and vCPU preemption check is disabled too. Hoever, KVM still can emulating HLT for vCPU for both cases. Checking if a vCPU is preempted or not can still boost performance in IPI-heavy scenarios such as unixbench file copy and pipe-based context switching tests: Here the vCPU is running with a dedicated pCPU, so the guest kernel has nopvspin but is emulating HLT for the vCPU: Testcase Base with patch System Benchmarks Index Values INDEX INDEX Dhrystone 2 using register variables 3278.4 3277.7 Double-Precision Whetstone 822.8 825.8 Execl Throughput 1296.5 941.1 File Copy 1024 bufsize 2000 maxblocks 2124.2 2142.7 File Copy 256 bufsize 500 maxblocks 1335.9 1353.6 File Copy 4096 bufsize 8000 maxblocks 4256.3 4760.3 Pipe Throughput 1050.1 1054.0 Pipe-based Context Switching 243.3 352.0 Process Creation 820.1 814.4 Shell Scripts (1 concurrent) 2169.0 2086.0 Shell Scripts (8 concurrent) 7710.3 7576.3 System Call Overhead 672.4 673.9 ======== ======= System Benchmarks Index Score 1467.2 1483.0 Move the setting of pv_ops.lock.vcpu_is_preempted to kvm_guest_init, so that it does not depend on pvspinlock. Signed-off-by: Li RongQing Message-Id: <1646815610-43315-1-git-send-email-lirongqing@baidu.com> Signed-off-by: Paolo Bonzini --- arch/x86/kernel/asm-offsets_64.c | 4 +-- arch/x86/kernel/kvm.c | 75 ++++++++++++++++++++-------------------- 2 files changed, 40 insertions(+), 39 deletions(-) diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index b14533a..9b69821 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -5,7 +5,7 @@ #include -#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#if defined(CONFIG_KVM_GUEST) #include #endif @@ -20,7 +20,7 @@ int main(void) BLANK(); #endif -#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#if defined(CONFIG_KVM_GUEST) OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted); BLANK(); #endif diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index ed8a13a..774d924 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -752,6 +752,41 @@ static void kvm_crash_shutdown(struct pt_regs *regs) } #endif +#if defined(CONFIG_X86_32) || !defined(CONFIG_SMP) +bool __kvm_vcpu_is_preempted(long cpu); + +__visible bool __kvm_vcpu_is_preempted(long cpu) +{ + struct kvm_steal_time *src = &per_cpu(steal_time, cpu); + + return !!(src->preempted & KVM_VCPU_PREEMPTED); +} +PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); + +#else + +#include + +extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); + +/* + * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and + * restoring to/from the stack. + */ +asm( +".pushsection .text;" +".global __raw_callee_save___kvm_vcpu_is_preempted;" +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" +"__raw_callee_save___kvm_vcpu_is_preempted:" +"movq __per_cpu_offset(,%rdi,8), %rax;" +"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" +"setne %al;" +"ret;" +".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;" +".popsection"); + +#endif + static void __init kvm_guest_init(void) { int i; @@ -764,6 +799,9 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { has_steal_clock = 1; static_call_update(pv_steal_clock, kvm_steal_clock); + + pv_ops.lock.vcpu_is_preempted = + PV_CALLEE_SAVE(__kvm_vcpu_is_preempted); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -1005,39 +1043,6 @@ static void kvm_wait(u8 *ptr, u8 val) } } -#ifdef CONFIG_X86_32 -__visible bool __kvm_vcpu_is_preempted(long cpu) -{ - struct kvm_steal_time *src = &per_cpu(steal_time, cpu); - - return !!(src->preempted & KVM_VCPU_PREEMPTED); -} -PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); - -#else - -#include - -extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); - -/* - * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and - * restoring to/from the stack. - */ -asm( -".pushsection .text;" -".global __raw_callee_save___kvm_vcpu_is_preempted;" -".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" -"__raw_callee_save___kvm_vcpu_is_preempted:" -"movq __per_cpu_offset(,%rdi,8), %rax;" -"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" -"setne %al;" -"ret;" -".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;" -".popsection"); - -#endif - /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -1081,10 +1086,6 @@ void __init kvm_spinlock_init(void) pv_ops.lock.wait = kvm_wait; pv_ops.lock.kick = kvm_kick_cpu; - if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { - pv_ops.lock.vcpu_is_preempted = - PV_CALLEE_SAVE(__kvm_vcpu_is_preempted); - } /* * When PV spinlock is enabled which is preferred over * virt_spin_lock(), virt_spin_lock_key's value is meaningless. -- 2.7.4