From: Ryan Roberts <ryan.roberts@arm.com>
To: Andrew Morton <akpm@linux-foundation.org>,
Matthew Wilcox <willy@infradead.org>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Yin Fengwei <fengwei.yin@intel.com>,
David Hildenbrand <david@redhat.com>, Yu Zhao <yuzhao@google.com>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Yang Shi <shy828301@gmail.com>,
"Huang, Ying" <ying.huang@intel.com>, Zi Yan <ziy@nvidia.com>,
Luis Chamberlain <mcgrof@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH v3 2/4] mm: Default implementation of arch_wants_pte_order()
Date: Fri, 14 Jul 2023 17:17:31 +0100 [thread overview]
Message-ID: <20230714161733.4144503-2-ryan.roberts@arm.com> (raw)
In-Reply-To: <20230714160407.4142030-1-ryan.roberts@arm.com>
arch_wants_pte_order() can be overridden by the arch to return the
preferred folio order for pte-mapped memory. This is useful as some
architectures (e.g. arm64) can coalesce TLB entries when the physical
memory is suitably contiguous.
The first user for this hint will be FLEXIBLE_THP, which aims to
allocate large folios for anonymous memory to reduce page faults and
other per-page operation costs.
Here we add the default implementation of the function, used when the
architecture does not define it, which returns -1, implying that the HW
has no preference. In this case, mm will choose it's own default order.
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
include/linux/pgtable.h | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 5063b482e34f..2a1d83775837 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -313,6 +313,19 @@ static inline bool arch_has_hw_pte_young(void)
}
#endif
+#ifndef arch_wants_pte_order
+/*
+ * Returns preferred folio order for pte-mapped memory. Must be in range [0,
+ * PMD_SHIFT-PAGE_SHIFT) and must not be order-1 since THP requires large folios
+ * to be at least order-2. Negative value implies that the HW has no preference
+ * and mm will choose it's own default order.
+ */
+static inline int arch_wants_pte_order(void)
+{
+ return -1;
+}
+#endif
+
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long address,
--
2.25.1
next prev parent reply other threads:[~2023-07-14 16:17 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-14 16:04 [PATCH v3 0/4] variable-order, large folios for anonymous memory Ryan Roberts
2023-07-14 16:17 ` [PATCH v3 1/4] mm: Non-pmd-mappable, large folios for folio_add_new_anon_rmap() Ryan Roberts
2023-07-14 16:52 ` Yu Zhao
2023-07-14 18:01 ` Ryan Roberts
2023-07-17 13:00 ` David Hildenbrand
2023-07-17 13:13 ` Ryan Roberts
2023-07-17 13:19 ` David Hildenbrand
2023-07-17 13:21 ` Ryan Roberts
2023-07-14 16:17 ` Ryan Roberts [this message]
2023-07-14 16:54 ` [PATCH v3 2/4] mm: Default implementation of arch_wants_pte_order() Yu Zhao
2023-07-17 11:13 ` Yin Fengwei
2023-07-17 13:01 ` David Hildenbrand
2023-07-17 13:15 ` Ryan Roberts
2023-07-14 16:17 ` [PATCH v3 3/4] mm: FLEXIBLE_THP for improved performance Ryan Roberts
2023-07-14 17:17 ` Yu Zhao
2023-07-14 17:59 ` Ryan Roberts
2023-07-14 22:11 ` Yu Zhao
2023-07-17 13:36 ` Ryan Roberts
2023-07-17 19:31 ` Yu Zhao
2023-07-17 20:35 ` Yu Zhao
2023-07-17 23:37 ` Hugh Dickins
2023-07-18 10:36 ` Ryan Roberts
2023-07-17 13:06 ` David Hildenbrand
2023-07-17 13:20 ` Ryan Roberts
2023-07-17 13:56 ` David Hildenbrand
2023-07-17 14:47 ` Ryan Roberts
2023-07-17 14:55 ` David Hildenbrand
2023-07-17 17:07 ` Yu Zhao
2023-07-17 17:16 ` David Hildenbrand
2023-07-21 10:57 ` Ryan Roberts
2023-07-14 16:17 ` [PATCH v3 4/4] arm64: mm: Override arch_wants_pte_order() Ryan Roberts
2023-07-14 16:47 ` Yu Zhao
2023-07-24 11:59 ` [PATCH v3 0/4] variable-order, large folios for anonymous memory Ryan Roberts
2023-07-24 14:58 ` Zi Yan
2023-07-24 15:41 ` Ryan Roberts
2023-07-26 7:36 ` Itaru Kitayama
2023-07-26 8:42 ` Ryan Roberts
2023-07-26 8:47 ` Itaru Kitayama
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=20230714161733.4144503-2-ryan.roberts@arm.com \
--to=ryan.roberts@arm.com \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.com \
--cc=catalin.marinas@arm.com \
--cc=david@redhat.com \
--cc=fengwei.yin@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mcgrof@kernel.org \
--cc=shy828301@gmail.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=ying.huang@intel.com \
--cc=yuzhao@google.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