| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1491911135-216950-1-git-send-email-agraf@suse.de>
Date: Tue, 11 Apr 2017 13:45:35 +0200
From: Alexander Graf <agraf@...e.de>
To: kvm list <kvm@...r.kernel.org>
Cc: Radim Krčmář <rkrcmar@...hat.com>,
Jim Mattson <jmattson@...gle.com>,
"Michael S. Tsirkin" <mst@...hat.com>,
LKML <linux-kernel@...r.kernel.org>,
"Gabriel L. Somlo" <gsomlo@...il.com>,
Paolo Bonzini <pbonzini@...hat.com>,
Jonathan Corbet <corbet@....net>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>,
the arch/x86 maintainers <x86@...nel.org>,
Joerg Roedel <joro@...tes.org>, linux-doc@...r.kernel.org,
qemu-devel@...gnu.org
Subject: [PATCH v6] kvm: better MWAIT emulation for guests
From: "Michael S. Tsirkin" <mst@...hat.com>
Guests that are heavy on futexes end up IPI'ing each other a lot. That
can lead to significant slowdowns and latency increase for those guests
when running within KVM.
If only a single guest is needed on a host, we have a lot of spare host
CPU time we can throw at the problem. Modern CPUs implement a feature
called "MWAIT" which allows guests to wake up sleeping remote CPUs without
an IPI - thus without an exit - at the expense of never going out of guest
context.
The decision whether this is something sensible to use should be up to the
VM admin, so to user space. We can however allow MWAIT execution on systems
that support it properly hardware wise.
This patch adds a CAP to user space and a KVM cpuid leaf to indicate
availability of native MWAIT execution. With that enabled, the worst a
guest can do is waste as many cycles as a "jmp ." would do, so it's not
a privilege problem.
We consciously do *not* expose the feature in our CPUID bitmap, as most
people will want to benefit from sleeping vCPUs to allow for over commit.
Reported-by: "Gabriel L. Somlo" <gsomlo@...il.com>
Signed-off-by: Michael S. Tsirkin <mst@...hat.com>
[agraf: fix amd, change commit message]
Signed-off-by: Alexander Graf <agraf@...e.de>
---
v5 -> v6:
- Fix AMD check, so that we're consistent between svm and vmx
- Clarify commit message
---
Documentation/virtual/kvm/api.txt | 9 +++++++++
Documentation/virtual/kvm/cpuid.txt | 6 ++++++
arch/x86/include/uapi/asm/kvm_para.h | 1 +
arch/x86/kvm/cpuid.c | 3 +++
arch/x86/kvm/svm.c | 7 +++++--
arch/x86/kvm/vmx.c | 6 ++++--
arch/x86/kvm/x86.c | 3 +++
arch/x86/kvm/x86.h | 36 ++++++++++++++++++++++++++++++++++++
include/uapi/linux/kvm.h | 1 +
9 files changed, 68 insertions(+), 4 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 1a18484..dacc3d7 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4094,3 +4094,12 @@ reserved.
2: MIPS64 or microMIPS64 with access to all address segments.
Both registers and addresses are 64-bits wide.
It will be possible to run 64-bit or 32-bit guest code.
+
+8.8 KVM_CAP_X86_GUEST_MWAIT
+
+Architectures: x86
+
+This capability indicates that guest using memory monotoring instructions
+(MWAIT/MWAITX) to stop the virtual CPU will not cause a VM exit. As such time
+spent while virtual CPU is halted in this way will then be accounted for as
+guest running time on the host (as opposed to e.g. HLT).
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 3c65feb..04c201c 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -54,6 +54,12 @@ KVM_FEATURE_PV_UNHALT || 7 || guest checks this feature bit
|| || before enabling paravirtualized
|| || spinlock support.
------------------------------------------------------------------------------
+KVM_FEATURE_MWAIT || 8 || guest can use monitor/mwait
+ || || to halt the VCPU without exits,
+ || || time spent while halted in this
+ || || way is accounted for on host as
+ || || VCPU run time.
+------------------------------------------------------------------------------
KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side
|| || per-cpu warps are expected in
|| || kvmclock.
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index cff0bb6..9cc77a7 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -24,6 +24,7 @@
#define KVM_FEATURE_STEAL_TIME 5
#define KVM_FEATURE_PV_EOI 6
#define KVM_FEATURE_PV_UNHALT 7
+#define KVM_FEATURE_MWAIT 8
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index efde6cc..5638102 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -594,6 +594,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
if (sched_info_on())
entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
+ if (kvm_mwait_in_guest())
+ entry->eax |= (1 << KVM_FEATURE_MWAIT);
+
entry->ebx = 0;
entry->ecx = 0;
entry->edx = 0;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1b203ab..c41f03e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1198,10 +1198,13 @@ static void init_vmcb(struct vcpu_svm *svm)
set_intercept(svm, INTERCEPT_CLGI);
set_intercept(svm, INTERCEPT_SKINIT);
set_intercept(svm, INTERCEPT_WBINVD);
- set_intercept(svm, INTERCEPT_MONITOR);
- set_intercept(svm, INTERCEPT_MWAIT);
set_intercept(svm, INTERCEPT_XSETBV);
+ if (!kvm_mwait_in_guest()) {
+ set_intercept(svm, INTERCEPT_MONITOR);
+ set_intercept(svm, INTERCEPT_MWAIT);
+ }
+
control->iopm_base_pa = iopm_base;
control->msrpm_base_pa = __pa(svm->msrpm);
control->int_ctl = V_INTR_MASKING_MASK;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index cfdb0d9..2e62f9d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3547,11 +3547,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
CPU_BASED_USE_IO_BITMAPS |
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING |
- CPU_BASED_MWAIT_EXITING |
- CPU_BASED_MONITOR_EXITING |
CPU_BASED_INVLPG_EXITING |
CPU_BASED_RDPMC_EXITING;
+ if (!kvm_mwait_in_guest())
+ min |= CPU_BASED_MWAIT_EXITING |
+ CPU_BASED_MONITOR_EXITING;
+
opt = CPU_BASED_TPR_SHADOW |
CPU_BASED_USE_MSR_BITMAPS |
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6bc47e2..ffaa76d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2679,6 +2679,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_ADJUST_CLOCK:
r = KVM_CLOCK_TSC_STABLE;
break;
+ case KVM_CAP_X86_GUEST_MWAIT:
+ r = kvm_mwait_in_guest();
+ break;
case KVM_CAP_X86_SMM:
/* SMBASE is usually relocated above 1M on modern chipsets,
* and SMM handlers might indeed rely on 4G segment limits,
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index e8ff3e4..6120670 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -1,6 +1,8 @@
#ifndef ARCH_X86_KVM_X86_H
#define ARCH_X86_KVM_X86_H
+#include <asm/processor.h>
+#include <asm/mwait.h>
#include <linux/kvm_host.h>
#include <asm/pvclock.h>
#include "kvm_cache_regs.h"
@@ -212,4 +214,38 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
__rem; \
})
+static inline bool kvm_mwait_in_guest(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+
+ if (!cpu_has(&boot_cpu_data, X86_FEATURE_MWAIT))
+ return false;
+
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_AMD:
+ /* All AMD CPUs have a working MWAIT implementation */
+ return true;
+ case X86_VENDOR_INTEL:
+ /* Handle Intel below */
+ break;
+ default:
+ return false;
+ }
+
+ /*
+ * Intel CPUs without CPUID5_ECX_INTERRUPT_BREAK are problematic as
+ * they would allow guest to stop the CPU completely by disabling
+ * interrupts then invoking MWAIT.
+ */
+ if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+ return false;
+
+ cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
+
+ if (!(ecx & CPUID5_ECX_INTERRUPT_BREAK))
+ return false;
+
+ return true;
+}
+
#endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 1e1a6c7..a3f03d3 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -890,6 +890,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_MIPS_VZ 137
#define KVM_CAP_MIPS_TE 138
#define KVM_CAP_MIPS_64BIT 139
+#define KVM_CAP_X86_GUEST_MWAIT 140
#ifdef KVM_CAP_IRQ_ROUTING
--
1.8.5.6
Powered by blists - more mailing lists