* [PATCH] riscv: mm: Limit per-page TLB flushes for large PTE batches
@ 2026-11-12 3:05 hu.shengming
2026-11-12 8:21 ` Yicong Yang
2026-11-12 12:00 ` Jisheng Zhang
0 siblings, 2 replies; 3+ messages in thread
From: hu.shengming @ 2026-11-12 3:05 UTC (permalink / raw)
To: pjw, palmer, aou
Cc: alex, akpm, baolin.wang, wangruikang, linux-riscv, linux-kernel,
zhang.run, luo.haiyang
From: Shengming Hu <hu.shengming@zte.com.cn>
On systems without Svvptc, update_mmu_cache_range() performs one local
TLB invalidation per PTE. With 4 KiB pages, installing a PTE-mapped
1 MiB anonymous folio requires 256 SFENCE.VMA instructions, or 256
SINVAL.VMA instructions bracketed by SFENCE.W.INVAL and
SFENCE.INVAL.IR.
Apply the existing local TLB range-flush policy to PTE batch updates.
When nr exceeds tlb_flush_all_threshold, use local_flush_tlb_all_asid()
to replace per-page invalidations with a single ASID-wide SFENCE.VMA.
This orders the PTE writes before subsequent implicit page-table
accesses and invalidates translations for the entire batch. As with
range flushes, this may also evict unrelated translations for the same
ASID.
Benchmark results from will-it-scale's page_fault1_processes under
QEMU 9.1.93 (qemu-9.2.0-0.3.rc3.fc40), with svvptc=false and
CONFIG_TRANSPARENT_HUGEPAGE=y (higher is better):
Folio size Before After Change
=============================================
4 KiB 116537 113503 -2.6%
512 KiB 1431962 1977519 +38.1%
1 MiB 1528457 2208209 +44.5%
Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
---
arch/riscv/include/asm/pgtable.h | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 2ebd5fa5adc5..ebe42fcf35ae 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -571,6 +571,11 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC))
return;
+ if (nr > tlb_flush_all_threshold) {
+ local_flush_tlb_all_asid(asid);
+ return;
+ }
+
if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)) {
local_sfence_w_inval();
while (nr--)
--
2.25.1
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [PATCH] riscv: mm: Limit per-page TLB flushes for large PTE batches
2026-11-12 3:05 [PATCH] riscv: mm: Limit per-page TLB flushes for large PTE batches hu.shengming
@ 2026-11-12 8:21 ` Yicong Yang
2026-11-12 12:00 ` Jisheng Zhang
1 sibling, 0 replies; 3+ messages in thread
From: Yicong Yang @ 2026-11-12 8:21 UTC (permalink / raw)
To: hu.shengming, pjw, palmer, aou
Cc: yang.yicong, alex, akpm, baolin.wang, wangruikang, linux-riscv,
linux-kernel, zhang.run, luo.haiyang
On 11/12/26 11:05 AM, hu.shengming@zte.com.cn wrote:
> From: Shengming Hu <hu.shengming@zte.com.cn>
>
> On systems without Svvptc, update_mmu_cache_range() performs one local
> TLB invalidation per PTE. With 4 KiB pages, installing a PTE-mapped
> 1 MiB anonymous folio requires 256 SFENCE.VMA instructions, or 256
> SINVAL.VMA instructions bracketed by SFENCE.W.INVAL and
> SFENCE.INVAL.IR.
>
> Apply the existing local TLB range-flush policy to PTE batch updates.
> When nr exceeds tlb_flush_all_threshold, use local_flush_tlb_all_asid()
> to replace per-page invalidations with a single ASID-wide SFENCE.VMA.
> This orders the PTE writes before subsequent implicit page-table
> accesses and invalidates translations for the entire batch. As with
> range flushes, this may also evict unrelated translations for the same
> ASID.
>
> Benchmark results from will-it-scale's page_fault1_processes under
> QEMU 9.1.93 (qemu-9.2.0-0.3.rc3.fc40), with svvptc=false and
> CONFIG_TRANSPARENT_HUGEPAGE=y (higher is better):
>
> Folio size Before After Change
> =============================================
> 4 KiB 116537 113503 -2.6%
> 512 KiB 1431962 1977519 +38.1%
> 1 MiB 1528457 2208209 +44.5%
>
> Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
> ---
> arch/riscv/include/asm/pgtable.h | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
> index 2ebd5fa5adc5..ebe42fcf35ae 100644
> --- a/arch/riscv/include/asm/pgtable.h
> +++ b/arch/riscv/include/asm/pgtable.h
> @@ -571,6 +571,11 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
> if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC))
> return;
>
> + if (nr > tlb_flush_all_threshold) {
> + local_flush_tlb_all_asid(asid);
> + return;
> + }
> +
could we reuse local_flush_tlb_range_threshold_asid() or
local_flush_tlb_range_asid()? now the logic is exactly
the same.
thanks.
> if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)) {
> local_sfence_w_inval();
> while (nr--)
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [PATCH] riscv: mm: Limit per-page TLB flushes for large PTE batches
2026-11-12 3:05 [PATCH] riscv: mm: Limit per-page TLB flushes for large PTE batches hu.shengming
2026-11-12 8:21 ` Yicong Yang
@ 2026-11-12 12:00 ` Jisheng Zhang
1 sibling, 0 replies; 3+ messages in thread
From: Jisheng Zhang @ 2026-11-12 12:00 UTC (permalink / raw)
To: hu.shengming
Cc: pjw, palmer, aou, alex, akpm, baolin.wang, wangruikang,
linux-riscv, linux-kernel, zhang.run, luo.haiyang
On Thu, Nov 12, 2026 at 11:05:25AM +0800, hu.shengming@zte.com.cn wrote:
> From: Shengming Hu <hu.shengming@zte.com.cn>
>
> On systems without Svvptc, update_mmu_cache_range() performs one local
> TLB invalidation per PTE. With 4 KiB pages, installing a PTE-mapped
> 1 MiB anonymous folio requires 256 SFENCE.VMA instructions, or 256
> SINVAL.VMA instructions bracketed by SFENCE.W.INVAL and
> SFENCE.INVAL.IR.
>
> Apply the existing local TLB range-flush policy to PTE batch updates.
> When nr exceeds tlb_flush_all_threshold, use local_flush_tlb_all_asid()
> to replace per-page invalidations with a single ASID-wide SFENCE.VMA.
> This orders the PTE writes before subsequent implicit page-table
> accesses and invalidates translations for the entire batch. As with
> range flushes, this may also evict unrelated translations for the same
> ASID.
>
> Benchmark results from will-it-scale's page_fault1_processes under
> QEMU 9.1.93 (qemu-9.2.0-0.3.rc3.fc40), with svvptc=false and
> CONFIG_TRANSPARENT_HUGEPAGE=y (higher is better):
Can you test on real hw rather than on qemu to get the performance numbers?
>
> Folio size Before After Change
> =============================================
> 4 KiB 116537 113503 -2.6%
> 512 KiB 1431962 1977519 +38.1%
> 1 MiB 1528457 2208209 +44.5%
Since one page is the most case, if we really regressed about 2.6%, then I
think we need to evaluate whether the gain deserves the pay.
>
> Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
> ---
> arch/riscv/include/asm/pgtable.h | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
> index 2ebd5fa5adc5..ebe42fcf35ae 100644
> --- a/arch/riscv/include/asm/pgtable.h
> +++ b/arch/riscv/include/asm/pgtable.h
> @@ -571,6 +571,11 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
> if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC))
> return;
>
> + if (nr > tlb_flush_all_threshold) {
unlikely(...)
> + local_flush_tlb_all_asid(asid);
> + return;
> + }
> +
> if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)) {
> local_sfence_w_inval();
> while (nr--)
> --
> 2.25.1
>
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-11-12 12:20 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-12 3:05 [PATCH] riscv: mm: Limit per-page TLB flushes for large PTE batches hu.shengming
2026-11-12 8:21 ` Yicong Yang
2026-11-12 12:00 ` Jisheng Zhang
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®