linux-kernel - [PATCH v5 24/25] arm64/mm: __always

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Fri,  2 Feb 2024 08:07:55 +0000
From: Ryan Roberts <ryan.roberts@....com>
To: Catalin Marinas <catalin.marinas@....com>,
	Will Deacon <will@...nel.org>,
	Ard Biesheuvel <ardb@...nel.org>,
	Marc Zyngier <maz@...nel.org>,
	James Morse <james.morse@....com>,
	Andrey Ryabinin <ryabinin.a.a@...il.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Matthew Wilcox <willy@...radead.org>,
	Mark Rutland <mark.rutland@....com>,
	David Hildenbrand <david@...hat.com>,
	Kefeng Wang <wangkefeng.wang@...wei.com>,
	John Hubbard <jhubbard@...dia.com>,
	Zi Yan <ziy@...dia.com>,
	Barry Song <21cnbao@...il.com>,
	Alistair Popple <apopple@...dia.com>,
	Yang Shi <shy828301@...il.com>,
	Nicholas Piggin <npiggin@...il.com>,
	Christophe Leroy <christophe.leroy@...roup.eu>,
	"Aneesh Kumar K.V" <aneesh.kumar@...nel.org>,
	"Naveen N. Rao" <naveen.n.rao@...ux.ibm.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...hat.com>,
	Borislav Petkov <bp@...en8.de>,
	Dave Hansen <dave.hansen@...ux.intel.com>,
	"H. Peter Anvin" <hpa@...or.com>
Cc: Ryan Roberts <ryan.roberts@....com>,
	linux-arm-kernel@...ts.infradead.org,
	x86@...nel.org,
	linuxppc-dev@...ts.ozlabs.org,
	linux-mm@...ck.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH v5 24/25] arm64/mm: __always_inline to improve fork() perf

As set_ptes() and wrprotect_ptes() become a bit more complex, the
compiler may choose not to inline them. But this is critical for fork()
performance. So mark the functions, along with contpte_try_unfold()
which is called by them, as __always_inline. This is worth ~1% on the
fork() microbenchmark with order-0 folios (the common case).

Signed-off-by: Ryan Roberts <ryan.roberts@....com>
---
 arch/arm64/include/asm/pgtable.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 353ea67b5d75..cdc310880a3b 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1213,8 +1213,8 @@ extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep,
 				pte_t entry, int dirty);
 
-static inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
-					pte_t *ptep, pte_t pte)
+static __always_inline void contpte_try_unfold(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep, pte_t pte)
 {
 	if (unlikely(pte_valid_cont(pte)))
 		__contpte_try_unfold(mm, addr, ptep, pte);
@@ -1279,7 +1279,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 }
 
 #define set_ptes set_ptes
-static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
+static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, pte_t pte, unsigned int nr)
 {
 	pte = pte_mknoncont(pte);
@@ -1361,8 +1361,8 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 }
 
 #define wrprotect_ptes wrprotect_ptes
-static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
-				pte_t *ptep, unsigned int nr)
+static __always_inline void wrprotect_ptes(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep, unsigned int nr)
 {
 	if (likely(nr == 1)) {
 		/*
-- 
2.25.1