[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20201014005320.2233162-5-kaleshsingh@google.com>
Date: Wed, 14 Oct 2020 00:53:09 +0000
From: Kalesh Singh <kaleshsingh@...gle.com>
To: unlisted-recipients:; (no To-header on input)
Cc: surenb@...gle.com, minchan@...gle.com, joelaf@...gle.com,
lokeshgidra@...gle.com, kaleshsingh@...gle.com,
kernel-team@...roid.com,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
x86@...nel.org, "H. Peter Anvin" <hpa@...or.com>,
Shuah Khan <shuah@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
"Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
Kees Cook <keescook@...omium.org>,
Josh Poimboeuf <jpoimboe@...hat.com>,
Sami Tolvanen <samitolvanen@...gle.com>,
Masahiro Yamada <masahiroy@...nel.org>,
Arnd Bergmann <arnd@...db.de>,
Frederic Weisbecker <frederic@...nel.org>,
Krzysztof Kozlowski <krzk@...nel.org>,
Hassan Naveed <hnaveed@...ecomp.com>,
Christian Brauner <christian.brauner@...ntu.com>,
Stephen Boyd <sboyd@...nel.org>,
Anshuman Khandual <anshuman.khandual@....com>,
Gavin Shan <gshan@...hat.com>, Mike Rapoport <rppt@...nel.org>,
Steven Price <steven.price@....com>,
Jia He <justin.he@....com>, John Hubbard <jhubbard@...dia.com>,
Ram Pai <linuxram@...ibm.com>,
Ralph Campbell <rcampbell@...dia.com>,
Mina Almasry <almasrymina@...gle.com>,
Sandipan Das <sandipan@...ux.ibm.com>,
Dave Hansen <dave.hansen@...el.com>,
Brian Geffon <bgeffon@...gle.com>,
Masami Hiramatsu <mhiramat@...nel.org>,
Kamalesh Babulal <kamalesh@...ux.vnet.ibm.com>,
SeongJae Park <sjpark@...zon.de>, linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org, linux-mm@...ck.org,
linux-kselftest@...r.kernel.org
Subject: [PATCH v4 4/5] arm64: mremap speedup - Enable HAVE_MOVE_PUD
HAVE_MOVE_PUD enables remapping pages at the PUD level if both the
source and destination addresses are PUD-aligned.
With HAVE_MOVE_PUD enabled it can be inferred that there is approximately
a 19x improvement in performance on arm64. (See data below).
------- Test Results ---------
The following results were obtained using a 5.4 kernel, by remapping
a PUD-aligned, 1GB sized region to a PUD-aligned destination.
The results from 10 iterations of the test are given below:
Total mremap times for 1GB data on arm64. All times are in nanoseconds.
Control HAVE_MOVE_PUD
1247761 74271
1219896 46771
1094792 59687
1227760 48385
1043698 76666
1101771 50365
1159896 52500
1143594 75261
1025833 61354
1078125 48697
1134312.6 59395.7 <-- Mean time in nanoseconds
A 1GB mremap completion time drops from ~1.1 milliseconds
to ~59 microseconds on arm64. (~19x speed up).
Signed-off-by: Kalesh Singh <kaleshsingh@...gle.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Cc: Catalin Marinas <catalin.marinas@....com>
Cc: Will Deacon <will@...nel.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>
---
Changes in v3:
- Add set_pud_at() macro - Used by move_normal_pud().
Changes in v4:
- Add Kirill's Acked-by.
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/pgtable.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 434d6791e869..7191a79fb44d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -124,6 +124,7 @@ config ARM64
select HANDLE_DOMAIN_IRQ
select HARDIRQS_SW_RESEND
select HAVE_MOVE_PMD
+ select HAVE_MOVE_PUD
select HAVE_PCI
select HAVE_ACPI_APEI if (ACPI && EFI)
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index a11bf52e0c38..0b0b36974757 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -454,6 +454,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
#define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
+#define set_pud_at(mm, addr, pudp, pud) set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud))
#define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d))
#define __phys_to_p4d_val(phys) __phys_to_pte_val(phys)
--
2.28.0.1011.ga647a8990f-goog
Powered by blists - more mailing lists