mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Zachary Amsden <zamsden@redhat.com>
To: kvm@vger.kernel.org
Cc: Zachary Amsden <zamsden@redhat.com>, Avi Kivity <avi@redhat.com>,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Joerg Roedel <joerg.roedel@amd.com>,
	linux-kernel@vger.kernel.org, Dor Laor <dlaor@redhat.com>
Subject: [PATCH RFC: kvm tsc virtualization 08/20] Export the reference TSC from KVM module
Date: Mon, 14 Dec 2009 18:08:35 -1000	[thread overview]
Message-ID: <1260850127-9766-9-git-send-email-zamsden@redhat.com> (raw)
In-Reply-To: <1260850127-9766-8-git-send-email-zamsden@redhat.com>

KVM now maintains a reference TSC, which can be exported to the
individual backends for private use.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
---
 arch/x86/kvm/x86.c |   25 +++++++++++++++++++++++++
 1 files changed, 25 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 144a820..170fd5d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -742,6 +742,7 @@ static DEFINE_PER_CPU(int, cpu_tsc_shift);
 static DEFINE_PER_CPU(s64, cpu_tsc_offset);
 static DEFINE_PER_CPU(u64, cpu_tsc_measure_base);
 static DEFINE_PER_CPU(atomic_t, cpu_tsc_synchronized);
+static DEFINE_PER_CPU(int, cpu_tsc_generation);
 static int tsc_base_cpu = -1;
 static unsigned long ref_tsc_khz;
 
@@ -813,6 +814,29 @@ static inline u64 compute_ref_tsc(int cpu)
 	return tsc + per_cpu(cpu_tsc_offset, cpu);
 }
 
+/*
+ * kvm_get_ref_tsc returns a reference TSC value which we attempt to keep
+ * stable across all CPUs, regardless of frequency shift, CPU hotplug, or
+ * pre-existing TSC offsets.
+ */
+u64 kvm_get_ref_tsc(void)
+{
+	int cpu, gen;
+	u64 tsc;
+
+	cpu = get_cpu();
+again:
+	gen = per_cpu(cpu_tsc_generation, cpu);
+	smp_rmb();
+	tsc = compute_ref_tsc(cpu);
+	smp_rmb();
+	if (unlikely(gen != per_cpu(cpu_tsc_generation, cpu)))
+		goto again;
+	put_cpu();
+	return tsc;
+}
+EXPORT_SYMBOL_GPL(kvm_get_ref_tsc);
+
 #define SYNC_TRIES 64
 
 /*
@@ -929,6 +953,7 @@ static void kvm_sync_tsc(void *cpup)
 			accumulator -= delta[i+SYNC_TRIES];
 		accumulator = accumulator / (SYNC_TRIES*2-12);
 		per_cpu(cpu_tsc_offset, new_cpu) = accumulator;
+		++per_cpu(cpu_tsc_generation, new_cpu);
 		atomic_set(&per_cpu(cpu_tsc_synchronized, new_cpu), 1);
 		pr_debug("%s: OUT, cpu = %d, cpu_tsc_offset = %lld, cpu_tsc_multiplier=%ld, cpu_tsc_shift=%d\n", __func__, raw_smp_processor_id(), per_cpu(cpu_tsc_offset, new_cpu), per_cpu(cpu_tsc_multiplier, new_cpu), per_cpu(cpu_tsc_shift, new_cpu));
 	}
-- 
1.6.5.2


  reply	other threads:[~2009-12-15  4:11 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <1260850127-9766-1-git-send-email-zamsden@redhat.com>
2009-12-15  4:08 ` [PATCH RFC: kvm tsc virtualization 01/20] Move TSC read to vmx_vcpu_put Zachary Amsden
2009-12-15  4:08   ` [PATCH RFC: kvm tsc virtualization 02/20] Add a hotplug notifier to KVM x86 backend Zachary Amsden
2009-12-15  4:08     ` [PATCH RFC: kvm tsc virtualization 03/20] TSC offset framework Zachary Amsden
2009-12-15  4:08       ` [PATCH RFC: kvm tsc virtualization 04/20] Synchronize TSC when a new CPU comes up Zachary Amsden
2009-12-15  4:08         ` [PATCH RFC: kvm tsc virtualization 05/20] Fix AMD C1 TSC desynchronization Zachary Amsden
2009-12-15  4:08           ` [PATCH RFC: kvm tsc virtualization 06/20] Make TSC reference stable across frequency changes Zachary Amsden
2009-12-15  4:08             ` [PATCH RFC: kvm tsc virtualization 07/20] Basic SVM implementation of RDTSC trapping Zachary Amsden
2009-12-15  4:08               ` Zachary Amsden [this message]
2009-12-15  4:08                 ` [PATCH RFC: kvm tsc virtualization 09/20] Use TSC reference for SVM Zachary Amsden
2009-12-15  4:08                   ` [PATCH RFC: kvm tsc virtualization 10/20] Add a stat counter for RDTSC exits Zachary Amsden
2009-12-15  4:08                     ` [PATCH RFC: kvm tsc virtualization 11/20] Use highest TSC frequency as reference clock Zachary Amsden
2009-12-15  4:08                       ` [PATCH RFC: kvm tsc virtualization 12/20] Higher accuracy TSC offset computation Zachary Amsden
2009-12-15  4:08                         ` [PATCH RFC: kvm tsc virtualization 13/20] Combine observed TSC deviation into moving average Zachary Amsden
2009-12-15  4:08                           ` [PATCH RFC: kvm tsc virtualization 14/20] Move TSC cpu vars to a struct Zachary Amsden
2009-12-15  4:08                             ` [PATCH RFC: kvm tsc virtualization 15/20] Fix longstanding races Zachary Amsden
2009-12-15  4:08                               ` [PATCH RFC: kvm tsc virtualization 16/20] Fix 32-bit mult_precise Zachary Amsden
2009-12-15  4:08                                 ` [PATCH RFC: kvm tsc virtualization 17/20] Periodically measure TSC skew Zachary Amsden
2009-12-15  4:08                                   ` [PATCH RFC: kvm tsc virtualization 18/20] Implement variable speed TSC Zachary Amsden
2009-12-15  4:08                                     ` [PATCH RFC: kvm tsc virtualization 19/20] IOCTL for different TSC modes Zachary Amsden
2009-12-15  4:08                                       ` [PATCH RFC: kvm tsc virtualization 20/20] Get passthrough TSC working in SVM again Zachary Amsden
2009-12-15 13:58                               ` [PATCH RFC: kvm tsc virtualization 15/20] Fix longstanding races Andi Kleen
2009-12-15 18:21                               ` Marcelo Tosatti
2009-12-15 21:26                                 ` Zachary Amsden
2009-12-16 14:41                                   ` Marcelo Tosatti

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=1260850127-9766-9-git-send-email-zamsden@redhat.com \
    --to=zamsden@redhat.com \
    --cc=avi@redhat.com \
    --cc=dlaor@redhat.com \
    --cc=joerg.roedel@amd.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@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®