Re: [PATCH] [RESEND] KVM:VMX: Add support for Pause-Loop Exiting

["Zhai, Edwin" <edwin.zhai@intel.com>]

[-- Attachment #1: Type: text/plain, Size: 2039 bytes --]


Avi Kivity wrote:
> +#define KVM_VMX_DEFAULT_PLE_GAP    41
> +#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
> +static int __read_mostly ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
> +module_param(ple_gap, int, S_IRUGO);
> +
> +static int __read_mostly ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
> +module_param(ple_window, int, S_IRUGO);
>    
>   
>
> Shouldn't be __read_mostly since they're read very rarely (__read_mostly 
> should be for variables that are very often read, and rarely written).
>   

In general, they are read only except that experienced user may try 
different parameter for perf tuning.

> I'm not even sure they should be parameters.
>   

For different spinlock in different OS, and for different workloads, we 
need different parameter for tuning. It's similar as the enable_ept.

>   
>>   /*
>> + * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
>> + * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
>> + */
>> +static int handle_pause(struct kvm_vcpu *vcpu,
>> +				struct kvm_run *kvm_run)
>> +{
>> +	ktime_t expires;
>> +	skip_emulated_instruction(vcpu);
>> +
>> +	/* Sleep for 1 msec, and hope lock-holder got scheduled */
>> +	expires = ktime_add_ns(ktime_get(), 1000000UL);
>>    
>>     
>
> I think this should be much lower, 50-100us.  Maybe this should be a 
> parameter.  With 1ms we losing significant cpu time if the congestion 
> clears.
>   

I have made it a parameter with default value of 100 us.

>   
>> +	set_current_state(TASK_INTERRUPTIBLE);
>> +	schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
>> +
>>    
>>     
>
> Please add a tracepoint for this (since it can cause significant change 
> in behaviour), 

Isn't trace_kvm_exit(exit_reason, ...) enough? We can tell the PLE 
vmexit from other vmexits.

> and move the logic to kvm_main.c.  It will be reused by 
> the AMD implementation, possibly my software spinlock detector, 
> paravirtualized spinlocks, and hopefully other architectures.
>   

Done.
>   
>> +	return 1;
>> +}
>> +
>> +/*
>>    
>>     
>
>   

[-- Attachment #2: kvm_ple_hrtimer_v2.patch --]
[-- Type: application/octet-stream, Size: 7678 bytes --]

KVM:VMX: Add support for Pause-Loop Exiting

New NHM processors will support Pause-Loop Exiting by adding 2 VM-execution
control fields:
PLE_Gap    - upper bound on the amount of time between two successive
             executions of PAUSE in a loop.
PLE_Window - upper bound on the amount of time a guest is allowed to execute in
             a PAUSE loop

If the time, between this execution of PAUSE and previous one, exceeds the
PLE_Gap, processor consider this PAUSE belongs to a new loop.
Otherwise, processor determins the the total execution time of this loop(since
1st PAUSE in this loop), and triggers a VM exit if total time exceeds the
PLE_Window.
* Refer SDM volume 3b section 21.6.13 & 22.1.3.

Pause-Loop Exiting can be used to detect Lock-Holder Preemption, where one VP
is sched-out after hold a spinlock, then other VPs for same lock are sched-in
to waste the CPU time.

Our tests indicate that most spinlocks are held for less than 212 cycles.
Performance tests show that with 2X LP over-commitment we can get +2% perf
improvement for kernel build(Even more perf gain with more LPs).

Signed-off-by: Zhai Edwin <edwin.zhai@intel.com>

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 272514c..2b49454 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -56,6 +56,7 @@
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
@@ -144,6 +145,8 @@ enum vmcs_field {
 	VM_ENTRY_INSTRUCTION_LEN        = 0x0000401a,
 	TPR_THRESHOLD                   = 0x0000401c,
 	SECONDARY_VM_EXEC_CONTROL       = 0x0000401e,
+	PLE_GAP                         = 0x00004020,
+	PLE_WINDOW                      = 0x00004022,
 	VM_INSTRUCTION_ERROR            = 0x00004400,
 	VM_EXIT_REASON                  = 0x00004402,
 	VM_EXIT_INTR_INFO               = 0x00004404,
@@ -248,6 +251,7 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_PAUSE_INSTRUCTION   40
 #define EXIT_REASON_MCE_DURING_VMENTRY	 41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3fe0d42..ed40386 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -61,6 +61,31 @@ module_param_named(unrestricted_guest,
 static int __read_mostly emulate_invalid_guest_state = 0;
 module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 
+/*
+ * These 2 parameters are used to config the controls for Pause-Loop Exiting:
+ * ple_gap:    upper bound on the amount of time between two successive
+ *             executions of PAUSE in a loop. Also indicate if ple enabled.
+ *             According to test, this time is usually small than 41 cycles.
+ * ple_window: upper bound on the amount of time a guest is allowed to execute
+ *             in a PAUSE loop. Tests indicate that most spinlocks are held for
+ *             less than 2^12 cycles
+ * Time is measured based on a counter that runs at the same rate as the TSC,
+ * refer SDM volume 3b section 21.6.13 & 22.1.3.
+ */
+#define KVM_VMX_DEFAULT_PLE_GAP    41
+#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
+static int __read_mostly ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
+module_param(ple_gap, int, S_IRUGO);
+
+static int __read_mostly ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
+module_param(ple_window, int, S_IRUGO);
+
+/*
+ * ple_sleep controls how long(us) the VCPU sleep upon a PLE vmexit
+ */
+static int __read_mostly ple_sleep = 100;
+module_param(ple_sleep, int, S_IRUGO);
+
 struct vmcs {
 	u32 revision_id;
 	u32 abort;
@@ -319,6 +344,12 @@ static inline int cpu_has_vmx_unrestricted_guest(void)
 		SECONDARY_EXEC_UNRESTRICTED_GUEST;
 }
 
+static inline int cpu_has_vmx_ple(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
+}
+
 static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
 {
 	return flexpriority_enabled &&
@@ -1256,7 +1287,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 			SECONDARY_EXEC_WBINVD_EXITING |
 			SECONDARY_EXEC_ENABLE_VPID |
 			SECONDARY_EXEC_ENABLE_EPT |
-			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+			SECONDARY_EXEC_UNRESTRICTED_GUEST |
+			SECONDARY_EXEC_PAUSE_LOOP_EXITING;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
@@ -1400,6 +1432,9 @@ static __init int hardware_setup(void)
 	if (enable_ept && !cpu_has_vmx_ept_2m_page())
 		kvm_disable_largepages();
 
+	if (!cpu_has_vmx_ple())
+		ple_gap = 0;
+
 	return alloc_kvm_area();
 }
 
@@ -2312,9 +2347,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 			exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
 		if (!enable_unrestricted_guest)
 			exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
+		if (!ple_gap)
+			exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
 	}
 
+	if (ple_gap) {
+		vmcs_write32(PLE_GAP, ple_gap);
+		vmcs_write32(PLE_WINDOW, ple_window);
+	}
+
 	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf);
 	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
 	vmcs_write32(CR3_TARGET_COUNT, 0);           /* 22.2.1 */
@@ -3362,6 +3404,19 @@ out:
 }
 
 /*
+ * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
+ * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
+ */
+static int handle_pause(struct kvm_vcpu *vcpu,
+				struct kvm_run *kvm_run)
+{
+	skip_emulated_instruction(vcpu);
+	kvm_vcpu_sleep(vcpu, ple_sleep);
+
+	return 1;
+}
+
+/*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
  * to be done to userspace and return 0.
@@ -3397,6 +3452,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_MCE_DURING_VMENTRY]      = handle_machine_check,
 	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
 	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
+	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
 };
 
 static const int kvm_vmx_max_exit_handlers =
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0bf9ee9..3723d62 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -287,6 +287,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_vcpu_sleep(struct kvm_vcpu *vcpu, unsigned int sleep_time);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e27b7a9..ff006ce 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1095,6 +1095,17 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
+void kvm_vcpu_sleep(struct kvm_vcpu *vcpu, unsigned int sleep_time)
+{
+	/* Sleep for required time(us), and hope lock-holder got scheduled */
+	ktime_t expires;
+
+	expires = ktime_add_ns(ktime_get(), 1000UL * sleep_time);
+	set_current_state(TASK_INTERRUPTIBLE);
+	schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_sleep);
+
 static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct kvm_vcpu *vcpu = vma->vm_file->private_data;