From: Lance Yang <lance.yang@linux.dev>
To: Peter Zijlstra <peterz@infradead.org>
Cc: akpm@linux-foundation.org, david@kernel.org,
dave.hansen@intel.com, dave.hansen@linux.intel.com,
ypodemsk@redhat.com, hughd@google.com, will@kernel.org,
aneesh.kumar@kernel.org, npiggin@gmail.com, tglx@linutronix.de,
mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
arnd@arndb.de, lorenzo.stoakes@oracle.com, ziy@nvidia.com,
baolin.wang@linux.alibaba.com, Liam.Howlett@oracle.com,
npache@redhat.com, ryan.roberts@arm.com, dev.jain@arm.com,
baohua@kernel.org, shy828301@gmail.com, riel@surriel.com,
jannh@google.com, jgross@suse.com, seanjc@google.com,
pbonzini@redhat.com, boris.ostrovsky@oracle.com,
virtualization@lists.linux.dev, kvm@vger.kernel.org,
linux-arch@vger.kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, ioworker0@gmail.com
Subject: Re: [PATCH v5 2/2] x86/tlb: skip redundant sync IPIs for native TLB flush
Date: Mon, 2 Mar 2026 23:48:11 +0800 [thread overview]
Message-ID: <42a719d3-5fbd-4b96-a150-6c0b4a1521a3@linux.dev> (raw)
In-Reply-To: <20260302145652.GH1395266@noisy.programming.kicks-ass.net>
On 2026/3/2 22:56, Peter Zijlstra wrote:
> On Mon, Mar 02, 2026 at 02:30:36PM +0800, Lance Yang wrote:
>
>
>> @@ -221,3 +222,18 @@ NOKPROBE_SYMBOL(native_load_idt);
>>
>> EXPORT_SYMBOL(pv_ops);
>> EXPORT_SYMBOL_GPL(pv_info);
>> +
>> +void __init native_pv_tlb_init(void)
>> +{
>> + /*
>> + * If PV backend already set the property, respect it.
>> + * Otherwise, check if native TLB flush sends real IPIs to all target
>> + * CPUs (i.e., not using INVLPGB broadcast invalidation).
>> + */
>> + if (pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast)
>> + return;
>> +
>> + if (pv_ops.mmu.flush_tlb_multi == native_flush_tlb_multi &&
>> + !cpu_feature_enabled(X86_FEATURE_INVLPGB))
>> + pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast = true;
>> +}
>
> How about making this a static_branch instead?
Cool. Thanks for the suggestion!
>
>> diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
>> index 866ea78ba156..87ef7147eac8 100644
>> --- a/arch/x86/include/asm/tlb.h
>> +++ b/arch/x86/include/asm/tlb.h
>> @@ -5,10 +5,23 @@
>> #define tlb_flush tlb_flush
>> static inline void tlb_flush(struct mmu_gather *tlb);
>>
>> +#define tlb_table_flush_implies_ipi_broadcast tlb_table_flush_implies_ipi_broadcast
>> +static inline bool tlb_table_flush_implies_ipi_broadcast(void);
>> +
>> #include <asm-generic/tlb.h>
>> #include <linux/kernel.h>
>> #include <vdso/bits.h>
>> #include <vdso/page.h>
>> +#include <asm/paravirt.h>
>> +
>> +static inline bool tlb_table_flush_implies_ipi_broadcast(void)
>> +{
>> +#ifdef CONFIG_PARAVIRT
>> + return pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast;
>> +#else
>> + return !cpu_feature_enabled(X86_FEATURE_INVLPGB);
>> +#endif
>> +}
>
> Then this turns into:
>
> static inline bool tlb_table_flush_implies_ipi_broadcast(void)
> {
> return static_branch_likely(&tlb_ipi_broadcast_key);
> }
Right. That would be cleaner and faster, eliminating the branch overhead.
Trying using static_branch on top of this series, something like:
---8<---
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 87ef7147eac8..409bbf335f26 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -10,17 +10,16 @@ static inline bool
tlb_table_flush_implies_ipi_broadcast(void);
#include <asm-generic/tlb.h>
#include <linux/kernel.h>
+#include <linux/jump_label.h>
#include <vdso/bits.h>
#include <vdso/page.h>
#include <asm/paravirt.h>
+DECLARE_STATIC_KEY_FALSE(tlb_ipi_broadcast_key);
+
static inline bool tlb_table_flush_implies_ipi_broadcast(void)
{
-#ifdef CONFIG_PARAVIRT
- return pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast;
-#else
- return !cpu_feature_enabled(X86_FEATURE_INVLPGB);
-#endif
+ return static_branch_likely(&tlb_ipi_broadcast_key);
}
static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index b681b8319295..bcf28980c319 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -15,6 +15,7 @@
#include <linux/kprobes.h>
#include <linux/pgtable.h>
#include <linux/static_call.h>
+#include <linux/jump_label.h>
#include <asm/bug.h>
#include <asm/paravirt.h>
@@ -223,6 +224,8 @@ NOKPROBE_SYMBOL(native_load_idt);
EXPORT_SYMBOL(pv_ops);
EXPORT_SYMBOL_GPL(pv_info);
+DEFINE_STATIC_KEY_FALSE(tlb_ipi_broadcast_key);
+
void __init native_pv_tlb_init(void)
{
/*
@@ -230,10 +233,14 @@ void __init native_pv_tlb_init(void)
* Otherwise, check if native TLB flush sends real IPIs to all target
* CPUs (i.e., not using INVLPGB broadcast invalidation).
*/
- if (pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast)
+ if (pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast) {
+ static_branch_enable(&tlb_ipi_broadcast_key);
return;
+ }
if (pv_ops.mmu.flush_tlb_multi == native_flush_tlb_multi &&
- !cpu_feature_enabled(X86_FEATURE_INVLPGB))
+ !cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
pv_ops.mmu.flush_tlb_multi_implies_ipi_broadcast = true;
+ static_branch_enable(&tlb_ipi_broadcast_key);
+ }
}
---
Thanks,
Lance
prev parent reply other threads:[~2026-03-02 15:48 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-02 6:30 [PATCH v5 0/2] skip redundant sync IPIs when TLB flush sent them Lance Yang
2026-03-02 6:30 ` [PATCH v5 1/2] mm/mmu_gather: prepare to skip redundant sync IPIs Lance Yang
2026-03-02 6:30 ` [PATCH v5 2/2] x86/tlb: skip redundant sync IPIs for native TLB flush Lance Yang
2026-03-02 14:56 ` Peter Zijlstra
2026-03-02 15:48 ` Lance Yang [this message]
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=42a719d3-5fbd-4b96-a150-6c0b4a1521a3@linux.dev \
--to=lance.yang@linux.dev \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@kernel.org \
--cc=arnd@arndb.de \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=boris.ostrovsky@oracle.com \
--cc=bp@alien8.de \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=david@kernel.org \
--cc=dev.jain@arm.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=ioworker0@gmail.com \
--cc=jannh@google.com \
--cc=jgross@suse.com \
--cc=kvm@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=mingo@redhat.com \
--cc=npache@redhat.com \
--cc=npiggin@gmail.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--cc=ryan.roberts@arm.com \
--cc=seanjc@google.com \
--cc=shy828301@gmail.com \
--cc=tglx@linutronix.de \
--cc=virtualization@lists.linux.dev \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--cc=ypodemsk@redhat.com \
--cc=ziy@nvidia.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