All of lore.kernel.org
 help / color / mirror / Atom feed
From: Gleb Natapov <gleb@redhat.com>
To: avi@redhat.com
Cc: kvm@vger.kernel.org, joerg.roedel@amd.com, sheng@linux.intel.com,
	Gleb Natapov <gleb@redhat.com>
Subject: [PATCH 11/15] Do not report TPR write to userspace if new value bigger or equal to a previous one.
Date: Mon, 13 Apr 2009 12:55:41 +0300	[thread overview]
Message-ID: <1239616545-25199-12-git-send-email-gleb@redhat.com> (raw)
In-Reply-To: <1239616545-25199-1-git-send-email-gleb@redhat.com>

Saves many exits to userspace in a case of IRQ chip in userspace.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 arch/x86/kvm/svm.c |    4 ++++
 arch/x86/kvm/vmx.c |   19 ++++++++++++-------
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 52bd999..9a8eb14 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1853,9 +1853,13 @@ static int emulate_on_interception(struct vcpu_svm *svm,
 
 static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
+	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
+	/* instruction emulation calls kvm_set_cr8() */
 	emulate_instruction(&svm->vcpu, NULL, 0, 0, 0);
 	if (irqchip_in_kernel(svm->vcpu.kvm))
 		return 1;
+	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
+		return 1;
 	kvm_run->exit_reason = KVM_EXIT_SET_TPR;
 	return 0;
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9162b4c..51f804c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2724,13 +2724,18 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			kvm_set_cr4(vcpu, kvm_register_read(vcpu, reg));
 			skip_emulated_instruction(vcpu);
 			return 1;
-		case 8:
-			kvm_set_cr8(vcpu, kvm_register_read(vcpu, reg));
-			skip_emulated_instruction(vcpu);
-			if (irqchip_in_kernel(vcpu->kvm))
-				return 1;
-			kvm_run->exit_reason = KVM_EXIT_SET_TPR;
-			return 0;
+		case 8: {
+				u8 cr8_prev = kvm_get_cr8(vcpu);
+				u8 cr8 = kvm_register_read(vcpu, reg);
+				kvm_set_cr8(vcpu, cr8);
+				skip_emulated_instruction(vcpu);
+				if (irqchip_in_kernel(vcpu->kvm))
+					return 1;
+				if (cr8_prev <= cr8)
+					return 1;
+				kvm_run->exit_reason = KVM_EXIT_SET_TPR;
+				return 0;
+			}
 		};
 		break;
 	case 2: /* clts */
-- 
1.5.6.5


  parent reply	other threads:[~2009-04-13  9:55 UTC|newest]

Thread overview: 99+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-04-13  9:55 [PATCH 00/15] interrupt injection rework Gleb Natapov
2009-04-13  9:55 ` [PATCH 01/15] Make kvm_cpu_(has|get)_interrupt() work for userspace irqchip too Gleb Natapov
2009-04-13  9:55 ` [PATCH 02/15] Consolidate userspace and kernel interrupt injection for VMX Gleb Natapov
2009-04-13  9:55 ` [PATCH 03/15] Cleanup vmx_intr_assist() Gleb Natapov
2009-04-13  9:55 ` [PATCH 04/15] Use kvm_arch_interrupt_allowed() instead of checking interrupt_window_open directly Gleb Natapov
2009-04-13  9:55 ` [PATCH 05/15] Coalesce userspace/kernel irqchip interrupt injection logic Gleb Natapov
2009-04-14 14:14   ` Dmitry Eremin-Solenikov
2009-04-14 14:24     ` Gleb Natapov
2009-04-14 14:32       ` Dmitry Eremin-Solenikov
2009-04-14 14:55         ` Gleb Natapov
2009-04-14 15:38           ` Gleb Natapov
2009-04-14 19:29           ` Dmitry Eremin-Solenikov
2009-04-14 19:41             ` Gleb Natapov
2009-04-15  6:11               ` Gleb Natapov
2009-04-15  9:30               ` Dmitry Eremin-Solenikov
2009-04-15  9:39                 ` Gleb Natapov
2009-04-15 10:22                   ` Jan Kiszka
2009-04-15 10:36                     ` Gleb Natapov
2009-04-15 10:51                       ` Jan Kiszka
2009-04-15 10:57                         ` Gleb Natapov
2009-04-15  9:44                 ` Gleb Natapov
2009-04-15 11:11                   ` Dmitry Eremin-Solenikov
2009-04-15 11:26                     ` Jan Kiszka
2009-04-15 11:53                       ` Dmitry Eremin-Solenikov
2009-04-15 11:58                         ` Dmitry Eremin-Solenikov
2009-04-15 12:01                         ` Gleb Natapov
2009-04-15 12:02                           ` Dmitry Eremin-Solenikov
2009-04-15 12:03                         ` Jan Kiszka
2009-04-15 12:39                           ` Dmitry Eremin-Solenikov
2009-04-15 12:48                             ` Jan Kiszka
2009-04-14 16:10       ` Avi Kivity
2009-04-14 16:18         ` Gleb Natapov
2009-04-17 12:39   ` Jan Kiszka
2009-04-17 12:50     ` Jan Kiszka
2009-04-17 14:13   ` Dmitry Eremin-Solenikov
2009-04-18  9:16     ` Jan Kiszka
2009-04-18 16:28       ` Gleb Natapov
2009-04-19 13:57         ` Gleb Natapov
2009-04-19 14:05           ` Jan Kiszka
2009-04-19 14:05             ` [Qemu-devel] " Jan Kiszka
2009-04-19 14:28             ` Gleb Natapov
2009-04-19 14:28               ` [Qemu-devel] " Gleb Natapov
2009-04-19 15:06             ` Jan Kiszka
2009-04-19 15:06               ` [Qemu-devel] " Jan Kiszka
2009-04-19 15:20               ` Gleb Natapov
2009-04-19 15:20                 ` [Qemu-devel] " Gleb Natapov
2009-04-18  9:05   ` Jan Kiszka
2009-04-18 16:20     ` Gleb Natapov
2009-04-19  8:52     ` Avi Kivity
2009-04-13  9:55 ` [PATCH 06/15] Use EVENTINJ to inject interrupts Gleb Natapov
2009-04-13  9:55 ` [PATCH 07/15] Remove exception_injected() callback Gleb Natapov
2009-04-13  9:55 ` [PATCH 08/15] Remove inject_pending_vectors() callback Gleb Natapov
2009-04-13  9:55 ` [PATCH 09/15] kvm_push_irq() no longer used Gleb Natapov
2009-04-13  9:55 ` [PATCH 10/15] sync_lapic_to_cr8() should always sync cr8 to V_TPR Gleb Natapov
2009-04-13  9:55 ` Gleb Natapov [this message]
2009-04-13  9:55 ` [PATCH 12/15] Get rid of arch.interrupt_window_open & arch.nmi_window_open Gleb Natapov
2009-04-13  9:55 ` [PATCH 13/15] Add NMI injection support to SVM Gleb Natapov
2009-04-17 11:59   ` Jan Kiszka
2009-04-17 15:12   ` Dmitry Eremin-Solenikov
2009-04-19 13:11     ` Gleb Natapov
2009-04-20 12:08       ` Dmitry Eremin-Solenikov
2009-04-20 15:50       ` Jan Kiszka
2009-04-21 14:07         ` Gleb Natapov
2009-04-17 19:13   ` Dmitry Eremin-Solenikov
2009-04-17 19:53     ` Jan Kiszka
2009-04-18  9:08       ` Jan Kiszka
2009-04-17 19:55   ` Jan Kiszka
2009-04-19  8:57     ` Avi Kivity
2009-04-19  9:12       ` Jan Kiszka
2009-04-19 13:17     ` Gleb Natapov
2009-04-19 13:21       ` Avi Kivity
2009-04-19 13:24         ` Gleb Natapov
2009-04-19 13:28           ` Avi Kivity
2009-04-19 13:40             ` Gleb Natapov
2009-04-19 13:43               ` Jan Kiszka
2009-04-19 13:49                 ` Avi Kivity
2009-04-19 13:51                   ` Gleb Natapov
2009-04-19 13:59                   ` Jan Kiszka
2009-04-19 13:27       ` Jan Kiszka
2009-04-19 13:32         ` Gleb Natapov
2009-04-19 13:40           ` Jan Kiszka
2009-04-19 13:40           ` Avi Kivity
2009-04-19 13:41             ` Gleb Natapov
2009-04-19 13:43               ` Avi Kivity
2009-04-19 13:44                 ` Gleb Natapov
2009-04-19 14:07                   ` Julian Stecklina
2009-04-19 14:13                     ` Gleb Natapov
2009-04-19 14:20                       ` Avi Kivity
2009-04-19 14:29                         ` Gleb Natapov
2009-04-19 14:57                           ` Avi Kivity
2009-04-19 16:36                             ` Gleb Natapov
2009-04-13  9:55 ` [PATCH 14/15] Move interrupt injection logic to x86.c Gleb Natapov
2009-04-14  7:22   ` Gleb Natapov
2009-04-13  9:55 ` [PATCH 15/15] Get rid of get_irq() callback Gleb Natapov
2009-04-13 11:51 ` [PATCH 00/15] interrupt injection rework Avi Kivity
2009-04-14  3:20   ` Sheng Yang
2009-04-14  5:20     ` Gleb Natapov
2009-04-14 15:33 ` Joerg Roedel
2009-04-14 15:37   ` Gleb Natapov

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=1239616545-25199-12-git-send-email-gleb@redhat.com \
    --to=gleb@redhat.com \
    --cc=avi@redhat.com \
    --cc=joerg.roedel@amd.com \
    --cc=kvm@vger.kernel.org \
    --cc=sheng@linux.intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.