From: Nadav Amit <namit@vmware.com>
To: Peter Zijlstra <peterz@infradead.org>, Andy Lutomirski <luto@kernel.org>
Cc: linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Borislav Petkov <bp@alien8.de>,
x86@kernel.org, Thomas Gleixner <tglx@linutronix.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
Nadav Amit <namit@vmware.com>,
Paolo Bonzini <pbonzini@redhat.com>,
kvm@vger.kernel.org
Subject: [PATCH 6/9] KVM: x86: Provide paravirtualized flush_tlb_multi()
Date: Wed, 12 Jun 2019 23:48:10 -0700 [thread overview]
Message-ID: <20190613064813.8102-7-namit@vmware.com> (raw)
In-Reply-To: <20190613064813.8102-1-namit@vmware.com>
Support the new interface of flush_tlb_multi, which also flushes the
local CPU's TLB, instead of flush_tlb_others that does not. This
interface is more performant since it parallelize remote and local TLB
flushes.
The actual implementation of flush_tlb_multi() is almost identical to
that of flush_tlb_others().
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org
Signed-off-by: Nadav Amit <namit@vmware.com>
---
arch/x86/kernel/kvm.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 00d81e898717..d00d551d4a2a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -580,7 +580,7 @@ static void __init kvm_apf_trap_init(void)
static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
-static void kvm_flush_tlb_others(const struct cpumask *cpumask,
+static void kvm_flush_tlb_multi(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
u8 state;
@@ -594,6 +594,11 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask,
* queue flush_on_enter for pre-empted vCPUs
*/
for_each_cpu(cpu, flushmask) {
+ /*
+ * The local vCPU is never preempted, so we do not explicitly
+ * skip check for local vCPU - it will never be cleared from
+ * flushmask.
+ */
src = &per_cpu(steal_time, cpu);
state = READ_ONCE(src->preempted);
if ((state & KVM_VCPU_PREEMPTED)) {
@@ -603,7 +608,7 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask,
}
}
- native_flush_tlb_others(flushmask, info);
+ native_flush_tlb_multi(flushmask, info);
}
static void __init kvm_guest_init(void)
@@ -628,9 +633,8 @@ static void __init kvm_guest_init(void)
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
+ pv_ops.mmu.flush_tlb_multi = kvm_flush_tlb_multi;
pv_ops.mmu.tlb_remove_table = tlb_remove_table;
- static_key_disable(&flush_tlb_multi_enabled.key);
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
--
2.20.1
next prev parent reply other threads:[~2019-06-13 16:42 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-13 6:48 [PATCH 0/9] x86: Concurrent TLB flushes and other improvements Nadav Amit
2019-06-13 6:48 ` [PATCH 1/9] smp: Remove smp_call_function() and on_each_cpu() return values Nadav Amit
2019-06-23 12:32 ` [tip:smp/hotplug] " tip-bot for Nadav Amit
2019-06-13 6:48 ` [PATCH 2/9] smp: Run functions concurrently in smp_call_function_many() Nadav Amit
2019-06-13 6:48 ` [PATCH 3/9] x86/mm/tlb: Refactor common code into flush_tlb_on_cpus() Nadav Amit
2019-06-25 21:07 ` Dave Hansen
2019-06-26 1:57 ` Nadav Amit
2019-06-13 6:48 ` [PATCH 4/9] x86/mm/tlb: Flush remote and local TLBs concurrently Nadav Amit
2019-06-13 6:48 ` [Xen-devel] " Nadav Amit
2019-06-13 6:48 ` Nadav Amit via Virtualization
2019-06-25 21:29 ` Dave Hansen
2019-06-25 21:29 ` [Xen-devel] " Dave Hansen
2019-06-25 21:29 ` Dave Hansen
2019-06-26 2:35 ` Nadav Amit
2019-06-26 2:35 ` [Xen-devel] " Nadav Amit
2019-06-26 3:00 ` Dave Hansen
2019-06-26 3:00 ` [Xen-devel] " Dave Hansen
2019-06-26 3:32 ` Nadav Amit
2019-06-26 3:32 ` [Xen-devel] " Nadav Amit
2019-06-26 3:32 ` Nadav Amit via Virtualization
2019-06-26 3:00 ` Dave Hansen
2019-06-26 2:35 ` Nadav Amit via Virtualization
2019-06-26 3:36 ` Andy Lutomirski
2019-06-26 3:36 ` [Xen-devel] " Andy Lutomirski
2019-06-26 3:36 ` Andy Lutomirski
2019-06-26 3:48 ` Nadav Amit
2019-06-26 3:48 ` [Xen-devel] " Nadav Amit
2019-06-26 3:48 ` Nadav Amit via Virtualization
2019-06-26 3:51 ` Andy Lutomirski
2019-06-26 3:51 ` Andy Lutomirski
2019-06-26 3:51 ` [Xen-devel] " Andy Lutomirski
2019-06-13 6:48 ` [PATCH 5/9] x86/mm/tlb: Optimize local TLB flushes Nadav Amit
2019-06-25 21:36 ` Dave Hansen
2019-06-26 16:33 ` Andy Lutomirski
2019-06-26 16:39 ` Nadav Amit
2019-06-26 16:50 ` Andy Lutomirski
2019-06-13 6:48 ` Nadav Amit [this message]
2019-06-25 21:40 ` [PATCH 6/9] KVM: x86: Provide paravirtualized flush_tlb_multi() Dave Hansen
2019-06-26 2:39 ` Nadav Amit
2019-06-26 3:35 ` Andy Lutomirski
2019-06-26 3:41 ` Nadav Amit
2019-06-26 3:56 ` Andy Lutomirski
2019-06-26 6:30 ` Nadav Amit
2019-06-26 16:37 ` Andy Lutomirski
2019-06-26 17:41 ` Vitaly Kuznetsov
2019-06-26 18:21 ` Andy Lutomirski
2019-06-13 6:48 ` [PATCH 7/9] smp: Do not mark call_function_data as shared Nadav Amit
2019-06-23 12:31 ` [tip:smp/hotplug] " tip-bot for Nadav Amit
2019-06-13 6:48 ` [PATCH 8/9] x86/tlb: Privatize cpu_tlbstate Nadav Amit
2019-06-14 15:58 ` Sean Christopherson
2019-06-17 17:10 ` Nadav Amit
2019-06-25 21:52 ` Dave Hansen
2019-06-26 1:22 ` Nadav Amit
2019-06-26 3:57 ` Andy Lutomirski
2019-06-13 6:48 ` [PATCH 9/9] x86/apic: Use non-atomic operations when possible Nadav Amit
2019-06-23 12:16 ` [tip:x86/apic] " tip-bot for Nadav Amit
2019-06-25 21:58 ` [PATCH 9/9] " Dave Hansen
2019-06-25 22:03 ` Thomas Gleixner
2019-06-23 12:37 ` [PATCH 0/9] x86: Concurrent TLB flushes and other improvements Thomas Gleixner
2019-06-25 22:02 ` Dave Hansen
2019-06-26 1:34 ` Nadav Amit
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=20190613064813.8102-7-namit@vmware.com \
--to=namit@vmware.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--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 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.