mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Glauber Costa <glommer@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Rik van Riel <riel@redhat.com>,
	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Avi Kivity <avi@redhat.com>,
	Anthony Liguori <aliguori@us.ibm.com>,
	Eric B Munson <emunson@mgebm.net>
Subject: [PATCH v3 9/9] KVM-GST: KVM Steal time registration
Date: Wed, 29 Jun 2011 11:29:48 -0400	[thread overview]
Message-ID: <1309361388-30163-10-git-send-email-glommer@redhat.com> (raw)
In-Reply-To: <1309361388-30163-1-git-send-email-glommer@redhat.com>

Register steal time within KVM. Everytime we sample the steal time
information, we update a local variable that tells what was the
last time read. We then account the difference.

Signed-off-by: Glauber Costa <glommer@redhat.com>
CC: Rik van Riel <riel@redhat.com>
CC: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Avi Kivity <avi@redhat.com>
CC: Anthony Liguori <aliguori@us.ibm.com>
CC: Eric B Munson <emunson@mgebm.net>
---
 Documentation/kernel-parameters.txt |    4 ++
 arch/x86/include/asm/kvm_para.h     |    1 +
 arch/x86/kernel/kvm.c               |   73 +++++++++++++++++++++++++++++++++++
 arch/x86/kernel/kvmclock.c          |    2 +
 4 files changed, 80 insertions(+), 0 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index fd248a31..a722574 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1737,6 +1737,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	no-kvmapf	[X86,KVM] Disable paravirtualized asynchronous page
 			fault handling.
 
+	no-steal-acc    [X86,KVM] Disable paravirtualized steal time accounting.
+			steal time is computed, but won't influence scheduler
+			behaviour
+
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c484ba8..35d732d 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -94,6 +94,7 @@ struct kvm_vcpu_pv_apf_data {
 
 extern void kvmclock_init(void);
 extern int kvm_register_clock(char *txt);
+extern void kvm_disable_steal_time(void);
 
 
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 33c07b0..58331c2 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -51,6 +51,15 @@ static int parse_no_kvmapf(char *arg)
 
 early_param("no-kvmapf", parse_no_kvmapf);
 
+static int steal_acc = 1;
+static int parse_no_stealacc(char *arg)
+{
+        steal_acc = 0;
+        return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
 struct kvm_para_state {
 	u8 mmu_queue[MMU_QUEUE_SIZE];
 	int mmu_queue_len;
@@ -58,6 +67,8 @@ struct kvm_para_state {
 
 static DEFINE_PER_CPU(struct kvm_para_state, para_state);
 static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
+static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
+static int has_steal_clock = 0;
 
 static struct kvm_para_state *kvm_para_state(void)
 {
@@ -441,6 +452,21 @@ static void __init paravirt_ops_setup(void)
 #endif
 }
 
+static void kvm_register_steal_time(void)
+{
+	int cpu = smp_processor_id();
+	struct kvm_steal_time *st = &per_cpu(steal_time, cpu);
+
+	if (!has_steal_clock)
+		return;
+
+	memset(st, 0, sizeof(*st));
+
+	wrmsrl(MSR_KVM_STEAL_TIME, (__pa(st) | KVM_MSR_ENABLED));
+	printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n",
+		cpu, __pa(st));
+}
+
 void __cpuinit kvm_guest_cpu_init(void)
 {
 	if (!kvm_para_available())
@@ -457,6 +483,9 @@ void __cpuinit kvm_guest_cpu_init(void)
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
 	}
+
+	if (has_steal_clock)
+		kvm_register_steal_time();
 }
 
 static void kvm_pv_disable_apf(void *unused)
@@ -483,6 +512,31 @@ static struct notifier_block kvm_pv_reboot_nb = {
 	.notifier_call = kvm_pv_reboot_notify,
 };
 
+static u64 kvm_steal_clock(int cpu)
+{
+	u64 steal;
+	struct kvm_steal_time *src;
+	int version;
+
+	src = &per_cpu(steal_time, cpu);
+	do {
+		version = src->version;
+		rmb();
+		steal = src->steal;
+		rmb();
+	} while ((version & 1) || (version != src->version));
+
+	return steal;
+}
+
+void kvm_disable_steal_time(void)
+{
+	if (!has_steal_clock)
+		return;
+
+	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
+}
+
 #ifdef CONFIG_SMP
 static void __init kvm_smp_prepare_boot_cpu(void)
 {
@@ -500,6 +554,7 @@ static void __cpuinit kvm_guest_cpu_online(void *dummy)
 
 static void kvm_guest_cpu_offline(void *dummy)
 {
+	kvm_disable_steal_time();
 	kvm_pv_disable_apf(NULL);
 	apf_task_wake_all();
 }
@@ -548,6 +603,11 @@ void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
 		x86_init.irqs.trap_init = kvm_apf_trap_init;
 
+	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+		has_steal_clock = 1;
+		pv_time_ops.steal_clock = kvm_steal_clock;
+	}
+
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 	register_cpu_notifier(&kvm_cpu_notifier);
@@ -555,3 +615,16 @@ void __init kvm_guest_init(void)
 	kvm_guest_cpu_init();
 #endif
 }
+
+static __init int activate_jump_labels(void)
+{
+	if (has_steal_clock) {
+		jump_label_inc(&paravirt_steal_enabled);
+		if (steal_acc)
+			jump_label_inc(&paravirt_steal_rq_enabled);
+	}
+
+	return 0;
+}
+arch_initcall(activate_jump_labels);
+
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 6389a6b..c1a0188 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -160,6 +160,7 @@ static void __cpuinit kvm_setup_secondary_clock(void)
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_crash_shutdown(regs);
 }
 #endif
@@ -167,6 +168,7 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 static void kvm_shutdown(void)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_shutdown();
 }
 
-- 
1.7.3.4


  parent reply	other threads:[~2011-06-29 15:38 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-29 15:29 [PATCH v3 0/9] Steal time for KVM Glauber Costa
2011-06-29 15:29 ` [PATCH v3 1/9] introduce kvm_read_guest_cached Glauber Costa
2011-06-29 15:29 ` [PATCH v3 2/9] KVM-HDR Add constant to represent KVM MSRs enabled bit Glauber Costa
2011-06-29 21:56   ` Eric B Munson
2011-06-30  8:31     ` Avi Kivity
2011-06-30 12:59       ` Eric B Munson
2011-06-30 13:21         ` Glauber Costa
2011-06-30 14:13           ` Eric B Munson
2011-06-29 15:29 ` [PATCH v3 3/9] KVM-HDR: KVM Steal time implementation Glauber Costa
2011-06-29 21:56   ` Eric B Munson
2011-06-30 21:54   ` Peter Zijlstra
2011-06-29 15:29 ` [PATCH v3 4/9] KVM-HV: " Glauber Costa
2011-06-29 21:56   ` Eric B Munson
2011-06-29 15:29 ` [PATCH v3 5/9] KVM-HV: use schedstats to calculate steal time Glauber Costa
2011-06-29 21:56   ` Eric B Munson
2011-06-29 15:29 ` [PATCH v3 6/9] KVM-GST: Add a pv_ops stub for " Glauber Costa
2011-06-29 21:56   ` Eric B Munson
2011-06-29 15:29 ` [PATCH v3 7/9] KVM-GST: KVM Steal time accounting Glauber Costa
2011-06-29 21:57   ` Eric B Munson
2011-06-30 21:54   ` Peter Zijlstra
2011-07-01  2:53     ` Glauber Costa
2011-07-01  8:26       ` Peter Zijlstra
2011-06-30 21:54   ` Peter Zijlstra
2011-07-01  2:50     ` Glauber Costa
2011-06-30 21:54   ` Peter Zijlstra
2011-07-01  2:50     ` Glauber Costa
2011-07-01  8:25       ` Peter Zijlstra
2011-06-30 21:54   ` Peter Zijlstra
2011-06-29 15:29 ` [PATCH v3 8/9] KVM-GST: adjust scheduler cpu power Glauber Costa
2011-06-29 21:57   ` Eric B Munson
2011-06-30 21:54   ` Peter Zijlstra
2011-06-30 21:54   ` Peter Zijlstra
2011-06-30 21:54   ` Peter Zijlstra
2011-06-29 15:29 ` Glauber Costa [this message]
2011-06-29 21:57   ` [PATCH v3 9/9] KVM-GST: KVM Steal time registration Eric B Munson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1309361388-30163-10-git-send-email-glommer@redhat.com \
    --to=glommer@redhat.com \
    --cc=aliguori@us.ibm.com \
    --cc=avi@redhat.com \
    --cc=emunson@mgebm.net \
    --cc=jeremy.fitzhardinge@citrix.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®