Re: Performance issue

[Vadim Rozenfeld <vrozenfe@redhat.com>]

[-- Attachment #1: Type: Text/Plain, Size: 751 bytes --]

On Tuesday, November 27, 2012 11:13:12 PM George-Cristian Bîrzan wrote:
> On Tue, Nov 27, 2012 at 10:38 PM, Vadim Rozenfeld <vrozenfe@redhat.com> 
wrote:
> > I have some code which do both reference time and invariant TSC but it
> > will not work after migration. I will send it later today.
> 
> Do you mean migrating guests? This is not an issue for us.
OK, but don't say I didn't warn you :)

There are two patches, one for kvm and another one for qemu.
you will probably need to rebase them.
Add "hv_tsc" cpu parameter to activate this feature.
you will probably need to deactivate hpet by adding "-no-hpet"
parameter as well.

best regards,
Vadim.

> 
> Also, it would be much appreciated!
> 
> --
> George-Cristian Bîrzan

[-- Attachment #2: hv_time_kvm.diff --]
[-- Type: text/x-patch, Size: 4028 bytes --]

diff --git a/arch/x86/include/asm/hyperv.h b/arch/x86/include/asm/hyperv.h
index b80420b..9c5ffef 100644
--- a/arch/x86/include/asm/hyperv.h
+++ b/arch/x86/include/asm/hyperv.h
@@ -136,6 +136,9 @@
 /* MSR used to read the per-partition time reference counter */
 #define HV_X64_MSR_TIME_REF_COUNT		0x40000020
 
+/* A partition's reference time stamp counter (TSC) page */
+#define HV_X64_MSR_REFERENCE_TSC		0x40000021
+
 /* Define the virtual APIC registers */
 #define HV_X64_MSR_EOI				0x40000070
 #define HV_X64_MSR_ICR				0x40000071
@@ -179,6 +182,10 @@
 #define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_MASK	\
 		(~((1ull << HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
 
+#define HV_X64_MSR_TSC_REFERENCE_ENABLE			0x00000001
+#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT		12
+
+
 #define HV_PROCESSOR_POWER_STATE_C0		0
 #define HV_PROCESSOR_POWER_STATE_C1		1
 #define HV_PROCESSOR_POWER_STATE_C2		2
@@ -191,4 +198,11 @@
 #define HV_STATUS_INVALID_ALIGNMENT		4
 #define HV_STATUS_INSUFFICIENT_BUFFERS		19
 
+typedef struct _HV_REFERENCE_TSC_PAGE {
+    uint32_t TscSequence;
+    uint32_t Rserved1;
+    uint64_t TscScale;
+    int64_t  TscOffset;
+} HV_REFERENCE_TSC_PAGE, * PHV_REFERENCE_TSC_PAGE;
+
 #endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b2e11f4..63ee09e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -565,6 +565,8 @@ struct kvm_arch {
 	/* fields used by HYPER-V emulation */
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
+	u64 hv_ref_count;
+	u64 hv_tsc_page;
 
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4f76417..4538295 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -813,7 +813,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
-	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_REFERENCE_TSC,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
@@ -1428,6 +1428,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 	switch (msr) {
 	case HV_X64_MSR_GUEST_OS_ID:
 	case HV_X64_MSR_HYPERCALL:
+	case HV_X64_MSR_TIME_REF_COUNT:
+	case HV_X64_MSR_REFERENCE_TSC:
 		r = true;
 		break;
 	}
@@ -1438,6 +1440,7 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
 static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	struct kvm *kvm = vcpu->kvm;
+	unsigned long addr;
 
 	switch (msr) {
 	case HV_X64_MSR_GUEST_OS_ID:
@@ -1467,6 +1470,27 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (__copy_to_user((void __user *)addr, instructions, 4))
 			return 1;
 		kvm->arch.hv_hypercall = data;
+		kvm->arch.hv_ref_count = get_kernel_ns();
+		break;
+	}
+	case HV_X64_MSR_REFERENCE_TSC: {
+		HV_REFERENCE_TSC_PAGE tsc_ref;
+		tsc_ref.TscSequence =
+			boot_cpu_has(X86_FEATURE_CONSTANT_TSC) ? 1 : 0;
+		tsc_ref.TscScale =
+			((10000LL << 32) /vcpu->arch.virtual_tsc_khz) << 32;
+		tsc_ref.TscOffset = 0;
+		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) {
+			kvm->arch.hv_tsc_page = data;
+			break;
+		}
+		addr = gfn_to_hva(vcpu->kvm, data >>
+			HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		if(__copy_to_user((void __user *)addr, &tsc_ref, sizeof(tsc_ref)))
+			return 1;
+		kvm->arch.hv_tsc_page = data;
 		break;
 	}
 	default:
@@ -1881,6 +1905,13 @@ static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case HV_X64_MSR_HYPERCALL:
 		data = kvm->arch.hv_hypercall;
 		break;
+	case HV_X64_MSR_TIME_REF_COUNT:
+		data = get_kernel_ns() - kvm->arch.hv_ref_count;
+		do_div(data, 100);
+		break;
+	case HV_X64_MSR_REFERENCE_TSC:
+		data = kvm->arch.hv_tsc_page;
+		break;
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
 		return 1;

[-- Attachment #3: hv_time_qemu.diff --]
[-- Type: text/x-patch, Size: 4666 bytes --]

diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index f3708e6..ad77b72 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -1250,6 +1250,8 @@ static int cpu_x86_find_by_name(x86_def_t *x86_cpu_def, const char *cpu_model)
             hyperv_enable_relaxed_timing(true);
         } else if (!strcmp(featurestr, "hv_vapic")) {
             hyperv_enable_vapic_recommended(true);
+        } else if (!strcmp(featurestr, "hv_tsc")) {
+            hyperv_enable_tsc_recommended(true);
         } else {
             fprintf(stderr, "feature string `%s' not in format (+feature|-feature|feature=xyz)\n", featurestr);
             goto error;
diff --git a/target-i386/hyperv.c b/target-i386/hyperv.c
index f284e99..bd581a1 100644
--- a/target-i386/hyperv.c
+++ b/target-i386/hyperv.c
@@ -15,6 +15,12 @@
 static bool hyperv_vapic;
 static bool hyperv_relaxed_timing;
 static int hyperv_spinlock_attempts = HYPERV_SPINLOCK_NEVER_RETRY;
+static bool hyperv_tsc;
+
+void hyperv_enable_tsc_recommended(bool val)
+{
+    hyperv_tsc = val;
+}
 
 void hyperv_enable_vapic_recommended(bool val)
 {
@@ -42,12 +48,18 @@ bool hyperv_enabled(void)
 bool hyperv_hypercall_available(void)
 {
     if (hyperv_vapic ||
+        hyperv_tsc ||
         (hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_RETRY)) {
       return true;
     }
     return false;
 }
 
+bool hyperv_tsc_recommended(void)
+{
+    return hyperv_tsc;
+}
+
 bool hyperv_vapic_recommended(void)
 {
     return hyperv_vapic;
diff --git a/target-i386/hyperv.h b/target-i386/hyperv.h
index bacb1d4..94c2d6e 100644
--- a/target-i386/hyperv.h
+++ b/target-i386/hyperv.h
@@ -27,10 +27,12 @@
 #endif
 
 #if !defined(CONFIG_USER_ONLY) && defined(CONFIG_KVM)
+void hyperv_enable_tsc_recommended(bool val);
 void hyperv_enable_vapic_recommended(bool val);
 void hyperv_enable_relaxed_timing(bool val);
 void hyperv_set_spinlock_retries(int val);
 #else
+static inline void hyperv_enable_tsc_recommended(bool val) { }
 static inline void hyperv_enable_vapic_recommended(bool val) { }
 static inline void hyperv_enable_relaxed_timing(bool val) { }
 static inline void hyperv_set_spinlock_retries(int val) { }
@@ -38,6 +40,7 @@ static inline void hyperv_set_spinlock_retries(int val) { }
 
 bool hyperv_enabled(void);
 bool hyperv_hypercall_available(void);
+bool hyperv_tsc_recommended(void);
 bool hyperv_vapic_recommended(void);
 bool hyperv_relaxed_timing_enabled(void);
 int hyperv_get_spinlock_retries(void);
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 5b18383..dc7f259 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -390,13 +390,17 @@ int kvm_arch_init_vcpu(CPUX86State *env)
     c = &cpuid_data.entries[cpuid_i++];
     memset(c, 0, sizeof(*c));
     c->function = KVM_CPUID_SIGNATURE;
-    if (!hyperv_enabled()) {
-        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
-        c->eax = 0;
-    } else {
-        memcpy(signature, "Microsoft Hv", 12);
+    memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+    if (hyperv_enabled()) {
         c->eax = HYPERV_CPUID_MIN;
     }
+//    if (!hyperv_enabled()) {
+//        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+//        c->eax = 0;
+//    } else {
+//        memcpy(signature, "Microsoft Hv", 12);
+//        c->eax = HYPERV_CPUID_MIN;
+//    }
     c->ebx = signature[0];
     c->ecx = signature[1];
     c->edx = signature[2];
@@ -427,7 +431,11 @@ int kvm_arch_init_vcpu(CPUX86State *env)
             c->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
             c->eax |= HV_X64_MSR_APIC_ACCESS_AVAILABLE;
         }
-
+        if (hyperv_tsc_recommended()) {
+            c->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
+            c->eax |= HV_X64_MSR_TIME_REF_COUNT_AVAILABLE;
+            c->eax |= 0x200;
+        }
         c = &cpuid_data.entries[cpuid_i++];
         memset(c, 0, sizeof(*c));
         c->function = HYPERV_CPUID_ENLIGHTMENT_INFO;
@@ -445,14 +453,14 @@ int kvm_arch_init_vcpu(CPUX86State *env)
         c->eax = 0x40;
         c->ebx = 0x40;
 
-        c = &cpuid_data.entries[cpuid_i++];
-        memset(c, 0, sizeof(*c));
-        c->function = KVM_CPUID_SIGNATURE_NEXT;
-        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
-        c->eax = 0;
-        c->ebx = signature[0];
-        c->ecx = signature[1];
-        c->edx = signature[2];
+//        c = &cpuid_data.entries[cpuid_i++];
+//        memset(c, 0, sizeof(*c));
+//        c->function = KVM_CPUID_SIGNATURE_NEXT;
+//        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+//        c->eax = 0;
+//        c->ebx = signature[0];
+//        c->ecx = signature[1];
+//        c->edx = signature[2];
     }
 
     has_msr_async_pf_en = c->eax & (1 << KVM_FEATURE_ASYNC_PF);