[PATCH v7 3/4] mm/memory.c: Add memory read privilege on page fault handling

From: Bibo Mao <maobibo@loongson.cn>
To: "Thomas Bogendoerfer" <tsbogend@alpha.franken.de>,
	"Jiaxun Yang" <jiaxun.yang@flygoat.com>,
	"Huacai Chen" <chenhc@lemote.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Paul Burton" <paulburton@kernel.org>,
	"Dmitry Korotin" <dkorotin@wavecomp.com>,
	"Philippe Mathieu-Daudé" <f4bug@amsat.org>,
	"Stafford Horne" <shorne@gmail.com>,
	"Steven Price" <steven.price@arm.com>,
	"Anshuman Khandual" <anshuman.khandual@arm.com>
Cc: linux-mips@vger.kernel.org, linux-kernel@vger.kernel.org,
	Mike Rapoport <rppt@linux.ibm.com>,
	Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>,
	"Maciej W. Rozycki" <macro@wdc.com>,
	linux-mm@kvack.org, David Hildenbrand <david@redhat.com>
Subject: [PATCH v7 3/4] mm/memory.c: Add memory read privilege on page fault handling
Date: Wed, 27 May 2020 10:25:19 +0800	[thread overview]
Message-ID: <1590546320-21814-4-git-send-email-maobibo@loongson.cn> (raw)
In-Reply-To: <1590546320-21814-1-git-send-email-maobibo@loongson.cn>

Here add pte_sw_mkyoung function to make page readable on MIPS
platform during page fault handling. This patch improves page
fault latency about 10% on my MIPS machine with lmbench
lat_pagefault case.

It is noop function on other arches, there is no negative
influence on those architectures.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/mips/include/asm/pgtable.h |  2 ++
 include/asm-generic/pgtable.h   | 16 ++++++++++++++++
 mm/memory.c                     |  3 +++
 3 files changed, 21 insertions(+)

diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 6f40612..d9772aff 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -414,6 +414,8 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	return pte;
 }
 
+#define pte_sw_mkyoung	pte_mkyoung
+
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 static inline int pte_huge(pte_t pte)	{ return pte_val(pte) & _PAGE_HUGE; }
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index fa5c73f..b5278ec 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -244,6 +244,22 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 }
 #endif
 
+/*
+ * On some architectures hardware does not set page access bit when accessing
+ * memory page, it is responsibilty of software setting this bit. It brings
+ * out extra page fault penalty to track page access bit. For optimization page
+ * access bit can be set during all page fault flow on these arches.
+ * To be differentiate with macro pte_mkyoung, this macro is used on platforms
+ * where software maintains page access bit.
+ */
+#ifndef pte_sw_mkyoung
+static inline pte_t pte_sw_mkyoung(pte_t pte)
+{
+	return pte;
+}
+#define pte_sw_mkyoung	pte_sw_mkyoung
+#endif
+
 #ifndef pte_savedwrite
 #define pte_savedwrite pte_write
 #endif
diff --git a/mm/memory.c b/mm/memory.c
index 8bb31c4..c7c8960 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2704,6 +2704,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
+		entry = pte_sw_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		/*
 		 * Clear the pte entry and flush it first, before updating the
@@ -3378,6 +3379,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	__SetPageUptodate(page);
 
 	entry = mk_pte(page, vma->vm_page_prot);
+	entry = pte_sw_mkyoung(entry);
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
@@ -3660,6 +3662,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 
 	flush_icache_page(vma, page);
 	entry = mk_pte(page, vma->vm_page_prot);
+	entry = pte_sw_mkyoung(entry);
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	/* copy-on-write page */
-- 
1.8.3.1

