From: "Nikunj A. Dadhania" <nikunj@linux.vnet.ibm.com>
To: peterz@infradead.org, mingo@elte.hu
Cc: jeremy@goop.org, mtosatti@redhat.com, kvm@vger.kernel.org,
x86@kernel.org, vatsa@linux.vnet.ibm.com,
linux-kernel@vger.kernel.org, avi@redhat.com, hpa@zytor.com
Subject: [RFC PATCH v1 3/5] KVM: Add paravirt kvm_flush_tlb_others
Date: Fri, 27 Apr 2012 21:54:37 +0530 [thread overview]
Message-ID: <20120427162401.27082.59387.stgit@abhimanyu> (raw)
In-Reply-To: <20120427161727.27082.43096.stgit@abhimanyu>
flush_tlb_others_ipi depends on lot of statics in tlb.c. Replicated
the flush_tlb_others_ipi as kvm_flush_tlb_others to further adapt to
paravirtualization.
Use the vcpu state information inside the kvm_flush_tlb_others to
avoid sending ipi to pre-empted vcpus.
* Do not send ipi's to offline vcpus and set flush_on_enter flag
* For online vcpus: Wait for them to clear the flag
The approach was discussed here: https://lkml.org/lkml/2012/2/20/157
Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com>
--
Pseudo Algo:
Write()
======
guest_exit()
flush_on_enter[i]=0;
running[i] = 0;
guest_enter()
running[i] = 1;
if(flush_on_enter[i]) {
tlb_flush()
flush_on_enter[i]=0;
}
Read()
======
GUEST KVM-HV
f->flushcpumask = cpumask - me;
again:
for_each_cpu(i, f->flushmask) {
if (!running[i]) {
case 1:
running[n]=1
(cpuN does not see
flush_on_enter set,
guest later finds it
running and sends ipi,
we are fine here, need
to clear the flag on
guest_exit)
flush_on_enter[i] = 1;
case2:
running[n]=1
(cpuN - will see flush
on enter and an IPI as
well - addressed in patch-4)
if (!running[i])
cpu_clear(f->flushmask); All is well, vm_enter
will do the fixup
}
case 3:
running[n] = 0;
(cpuN went to sleep,
we saw it as awake,
ipi sent, but wait
will break without
zero_mask and goto
again will take care)
}
send_ipi(f->flushmask)
wait_a_while_for_zero_mask();
if (!zero_mask)
goto again;
---
arch/x86/include/asm/kvm_para.h | 3 +-
arch/x86/include/asm/tlbflush.h | 9 ++++++
arch/x86/kernel/kvm.c | 1 +
arch/x86/kvm/x86.c | 6 ++++
arch/x86/mm/tlb.c | 57 +++++++++++++++++++++++++++++++++++++++
5 files changed, 75 insertions(+), 1 deletions(-)
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index f57b5cc..684a285 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -55,7 +55,8 @@ struct kvm_steal_time {
struct kvm_vcpu_state {
__u32 state;
- __u32 pad[15];
+ __u32 flush_on_enter;
+ __u32 pad[14];
};
#define KVM_VCPU_STATE_ALIGN_BITS 5
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index c0e108e..29470bd 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -119,6 +119,12 @@ static inline void native_flush_tlb_others(const struct cpumask *cpumask,
{
}
+static inline void kvm_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm,
+ unsigned long va)
+{
+}
+
static inline void reset_lazy_tlbstate(void)
{
}
@@ -145,6 +151,9 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm, unsigned long va);
+void kvm_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm, unsigned long va);
+
#define TLBSTATE_OK 1
#define TLBSTATE_LAZY 2
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index bb686a6..66db54e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -465,6 +465,7 @@ void __init kvm_guest_init(void)
}
has_vcpu_state = 1;
+ pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
#ifdef CONFIG_SMP
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 60546e9..6c42056 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1549,6 +1549,11 @@ static void kvm_set_vcpu_state(struct kvm_vcpu *vcpu)
return;
vs->state = 1;
+ if (vs->flush_on_enter) {
+ kvm_mmu_flush_tlb(vcpu);
+ vs->flush_on_enter = 0;
+ }
+
kvm_write_guest_cached(vcpu->kvm, ghc, vs, 2*sizeof(__u32));
smp_wmb();
}
@@ -1561,6 +1566,7 @@ static void kvm_clear_vcpu_state(struct kvm_vcpu *vcpu)
if (!(vcpu->arch.v_state.msr_val & KVM_MSR_ENABLED))
return;
+ vs->flush_on_enter = 0;
vs->state = 0;
kvm_write_guest_cached(vcpu->kvm, ghc, vs, 2*sizeof(__u32));
smp_wmb();
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index d6c0418..91ae34e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -6,6 +6,7 @@
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/cpu.h>
+#include <linux/kvm_para.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
@@ -69,6 +70,7 @@ void leave_mm(int cpu)
}
EXPORT_SYMBOL_GPL(leave_mm);
+DECLARE_PER_CPU(struct kvm_vcpu_state, vcpu_state) __aligned(64);
/*
*
* The flush IPI assumes that a thread switch happens in this order:
@@ -202,6 +204,61 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
raw_spin_unlock(&f->tlbstate_lock);
}
+void kvm_flush_tlb_others(const struct cpumask *cpumask,
+ struct mm_struct *mm, unsigned long va)
+{
+ unsigned int sender;
+ union smp_flush_state *f;
+ int cpu, loop;
+ struct kvm_vcpu_state *v_state;
+
+ /* Caller has disabled preemption */
+ sender = this_cpu_read(tlb_vector_offset);
+ f = &flush_state[sender];
+
+ if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+ raw_spin_lock(&f->tlbstate_lock);
+
+ f->flush_mm = mm;
+ f->flush_va = va;
+ if (cpumask_andnot(to_cpumask(f->flush_cpumask), cpumask, cpumask_of(smp_processor_id()))) {
+ /*
+ * We have to send the IPI only to online vCPUs
+ * affected. And queue flush_on_enter for pre-empted
+ * vCPUs
+ */
+again:
+ for_each_cpu(cpu, to_cpumask(f->flush_cpumask)) {
+ v_state = &per_cpu(vcpu_state, cpu);
+
+ if (!v_state->state) {
+ v_state->flush_on_enter = 1;
+ smp_mb();
+ if (!v_state->state)
+ cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
+ }
+ }
+
+ if (cpumask_empty(to_cpumask(f->flush_cpumask)))
+ goto out;
+
+ apic->send_IPI_mask(to_cpumask(f->flush_cpumask),
+ INVALIDATE_TLB_VECTOR_START + sender);
+
+ loop = 1000;
+ while (!cpumask_empty(to_cpumask(f->flush_cpumask)) && --loop)
+ cpu_relax();
+
+ if (!cpumask_empty(to_cpumask(f->flush_cpumask)))
+ goto again;
+ }
+out:
+ f->flush_mm = NULL;
+ f->flush_va = 0;
+ if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
+ raw_spin_unlock(&f->tlbstate_lock);
+}
+
void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm, unsigned long va)
{
next prev parent reply other threads:[~2012-04-27 16:25 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-04-27 16:23 [RFC PATCH v1 0/5] KVM paravirt remote flush tlb Nikunj A. Dadhania
2012-04-27 16:23 ` [RFC PATCH v1 1/5] KVM Guest: Add VCPU running/pre-empted state for guest Nikunj A. Dadhania
2012-05-01 1:03 ` Raghavendra K T
2012-05-01 3:25 ` Nikunj A Dadhania
2012-04-27 16:23 ` [RFC PATCH v1 2/5] KVM-HV: " Nikunj A. Dadhania
2012-04-27 16:24 ` Nikunj A. Dadhania [this message]
2012-04-29 12:23 ` [RFC PATCH v1 3/5] KVM: Add paravirt kvm_flush_tlb_others Avi Kivity
2012-05-01 3:34 ` Nikunj A Dadhania
2012-05-01 9:39 ` Peter Zijlstra
2012-05-01 10:47 ` Avi Kivity
2012-05-01 10:57 ` Peter Zijlstra
2012-05-01 10:59 ` Peter Zijlstra
2012-05-01 22:49 ` Jeremy Fitzhardinge
2012-05-03 14:09 ` Stefano Stabellini
2012-05-01 12:12 ` Avi Kivity
2012-05-01 14:59 ` Peter Zijlstra
2012-05-01 15:31 ` Avi Kivity
2012-05-01 15:36 ` Peter Zijlstra
2012-05-01 15:39 ` Avi Kivity
2012-05-01 15:42 ` Peter Zijlstra
2012-05-01 15:11 ` Peter Zijlstra
2012-05-01 15:33 ` Avi Kivity
2012-05-01 15:14 ` Peter Zijlstra
2012-05-01 15:36 ` Avi Kivity
2012-05-01 16:16 ` Peter Zijlstra
2012-05-01 16:43 ` Paul E. McKenney
2012-05-01 16:18 ` Peter Zijlstra
2012-05-01 16:20 ` Peter Zijlstra
2012-05-02 8:51 ` Nikunj A Dadhania
2012-05-02 10:20 ` Peter Zijlstra
2012-05-02 13:53 ` Nikunj A Dadhania
2012-05-04 4:32 ` Nikunj A Dadhania
2012-05-04 11:44 ` Srivatsa Vaddagiri
2012-05-07 3:10 ` Nikunj A Dadhania
2012-04-27 16:26 ` [RFC PATCH v1 4/5] KVM: get kvm_kick_vcpu out for pv_flush Nikunj A. Dadhania
2012-04-27 16:27 ` [RFC PATCH v1 5/5] KVM: Introduce PV kick in flush tlb Nikunj A. Dadhania
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=20120427162401.27082.59387.stgit@abhimanyu \
--to=nikunj@linux.vnet.ibm.com \
--cc=avi@redhat.com \
--cc=hpa@zytor.com \
--cc=jeremy@goop.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mtosatti@redhat.com \
--cc=peterz@infradead.org \
--cc=vatsa@linux.vnet.ibm.com \
--cc=x86@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).