public inbox for linux-riscv@lists.infradead.org
 help / color / mirror / Atom feed
From: Xu Lu <luxu.kernel@bytedance.com>
To: paul.walmsley@sifive.com, palmer@dabbelt.com,
	aou@eecs.berkeley.edu, ardb@kernel.org, anup@brainfault.org,
	atishp@atishpatra.org
Cc: xieyongji@bytedance.com, lihangjing@bytedance.com,
	punit.agrawal@bytedance.com, linux-kernel@vger.kernel.org,
	linux-riscv@lists.infradead.org,
	Xu Lu <luxu.kernel@bytedance.com>
Subject: [RFC PATCH v2 17/21] riscv: mm: Apply Svnapot for base page mapping if possible
Date: Thu,  5 Dec 2024 18:37:25 +0800	[thread overview]
Message-ID: <20241205103729.14798-18-luxu.kernel@bytedance.com> (raw)
In-Reply-To: <20241205103729.14798-1-luxu.kernel@bytedance.com>

All hardware pages in the same software page point to the same contiguous
memory region (the region size is equal to the software page size) and
has same prots. Thus this commit uses Svnapot extension to optimize the
mapping to software page to reduce tlb pressure.

Signed-off-by: Xu Lu <luxu.kernel@bytedance.com>
---
 arch/riscv/include/asm/pgtable.h | 16 +++++++++++++++-
 arch/riscv/mm/pgtable.c          |  6 ++++++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 5b2ca92ad833..9f347e5eefeb 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -483,13 +483,27 @@ static inline unsigned long __pte_mknapot(unsigned long pteval,
 	return pteval;
 }
 
+static inline unsigned long __pte_denapot(unsigned long pteval)
+{
+	unsigned long prot_mask = ~(_PAGE_HW_PFN_MASK | _PAGE_NAPOT);
+	unsigned long res;
+
+	if (!__pte_napot(pteval))
+		return pteval;
+	res = __page_val_to_hwpfn(pteval);
+	res = res & (res - 1UL);
+	pteval = (res << _PAGE_HWPFN_SHIFT) | (pteval & prot_mask);
+
+	return pteval;
+}
+
 #ifdef CONFIG_RISCV_USE_SW_PAGE
 static inline pte_t pte_mknapot(pte_t pte, unsigned int order)
 {
 	unsigned long pteval = pte_val(pte);
 	unsigned int i;
 
-	pteval = __pte_mknapot(pteval, order);
+	pteval = __pte_denapot(pteval);
 	for (i = 0; i < HW_PAGES_PER_PAGE; i++)
 		pte.ptes[i] = pteval;
 
diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
index 150aea8e2d7a..0bcaffe798d5 100644
--- a/arch/riscv/mm/pgtable.c
+++ b/arch/riscv/mm/pgtable.c
@@ -11,6 +11,12 @@ pte_t __pte(unsigned long pteval)
 {
 	pte_t pte;
 	unsigned int i;
+	unsigned int order;
+
+	if (has_svnapot() && __pte_present(pteval) && !__pte_napot(pteval))
+		for_each_napot_order(order)
+			if (napot_cont_shift(order) == PAGE_SHIFT)
+				pteval = __pte_mknapot(pteval, order);
 
 	for (i = 0; i < HW_PAGES_PER_PAGE; i++) {
 		pte.ptes[i] = pteval;
-- 
2.20.1


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

  parent reply	other threads:[~2024-12-05 10:45 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-05 10:37 [RFC PATCH v2 00/21] riscv: Introduce 64K base page Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 01/21] riscv: mm: Distinguish hardware base page and software " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 02/21] riscv: mm: Configure satp with hw page pfn Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 03/21] riscv: mm: Reimplement page table entry structures Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 04/21] riscv: mm: Reimplement page table entry constructor function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 05/21] riscv: mm: Reimplement conversion functions between page table entry Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 06/21] riscv: mm: Avoid pte constructor during pte conversion Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 07/21] riscv: mm: Reimplement page table entry get function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 08/21] riscv: mm: Reimplement page table entry atomic " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 09/21] riscv: mm: Replace READ_ONCE with atomic pte " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 10/21] riscv: mm: Reimplement PTE A/D bit check function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 11/21] riscv: mm: Reimplement mk_huge_pte function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 12/21] riscv: mm: Reimplement tlb flush function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 13/21] riscv: mm: Adjust PGDIR/P4D/PUD/PMD_SHIFT Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 14/21] riscv: mm: Only apply svnapot region bigger than software page Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 15/21] riscv: mm: Adjust FIX_BTMAPS_SLOTS for variable PAGE_SIZE Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 16/21] riscv: mm: Adjust FIX_FDT_SIZE for variable PMD_SIZE Xu Lu
2024-12-05 10:37 ` Xu Lu [this message]
2024-12-05 10:37 ` [RFC PATCH v2 18/21] riscv: Kconfig: Introduce 64K page size Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 19/21] riscv: Kconfig: Adjust mmap rnd bits for 64K Page Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 20/21] riscv: mm: Adjust address space layout and init page table " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 21/21] riscv: mm: Update EXEC_PAGESIZE " Xu Lu
2024-12-06  2:00 ` [RFC PATCH v2 00/21] riscv: Introduce 64K base page Zi Yan
2024-12-06  2:41   ` [External] " Xu Lu
2024-12-06 10:13   ` David Hildenbrand
2024-12-06 13:42     ` [External] " Xu Lu
2024-12-06 18:48       ` Pedro Falcato
2024-12-07  8:03         ` Xu Lu
2024-12-07 22:02           ` Yu Zhao
2024-12-09  3:36             ` Xu Lu

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=20241205103729.14798-18-luxu.kernel@bytedance.com \
    --to=luxu.kernel@bytedance.com \
    --cc=anup@brainfault.org \
    --cc=aou@eecs.berkeley.edu \
    --cc=ardb@kernel.org \
    --cc=atishp@atishpatra.org \
    --cc=lihangjing@bytedance.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    --cc=punit.agrawal@bytedance.com \
    --cc=xieyongji@bytedance.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