| 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
| ||
|
Message-Id: <20250804123923.296230-1-liqiang01@kylinos.cn> Date: Mon, 4 Aug 2025 20:39:23 +0800 From: Li Qiang <liqiang01@...inos.cn> To: akpm@...ux-foundation.org, david@...hat.com Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org, lorenzo.stoakes@...cle.com, Liam.Howlett@...cle.com, vbabka@...e.cz, rppt@...nel.org, surenb@...gle.com, mhocko@...e.com, Li Qiang <liqiang01@...inos.cn> Subject: [PATCH] mm: memory: Force-inline PTE/PMD zapping functions for performance This change converts several critical page table zapping functions from `inline` to `__always_inline`, resulting in measurable performance improvements in process spawning workloads. Performance Impact (Intel Xeon Gold 6430 2.1GHz): - UnixBench 'context1' test shows ~6% improvement (single-core) - UnixBench shows ~0.6% improvement (single-core) - mm/memory.o size reduced by 2.49% (70190 -> 68445 bytes) - Net code reduction of 1745 bytes (add/remove: 211/166) The modified functions form a hot path during process teardown: 1. zap_present_ptes() 2. do_zap_pte_range() 3. zap_pte_range() 4. zap_pmd_range() Signed-off-by: Li Qiang <liqiang01@...inos.cn> --- mm/memory.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index b0cda5aab398..281a353fae7b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1543,7 +1543,7 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, * * Returns the number of processed (skipped or zapped) PTEs (at least 1). */ -static inline int zap_present_ptes(struct mmu_gather *tlb, +static __always_inline int zap_present_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, @@ -1662,7 +1662,7 @@ static inline int zap_nonpresent_ptes(struct mmu_gather *tlb, return nr; } -static inline int do_zap_pte_range(struct mmu_gather *tlb, +static __always_inline int do_zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, unsigned long addr, unsigned long end, struct zap_details *details, int *rss, @@ -1698,7 +1698,7 @@ static inline int do_zap_pte_range(struct mmu_gather *tlb, return nr; } -static unsigned long zap_pte_range(struct mmu_gather *tlb, +static __always_inline unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) @@ -1790,7 +1790,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, return addr; } -static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, +static __always_inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) @@ -1832,7 +1832,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, return addr; } -static inline unsigned long zap_pud_range(struct mmu_gather *tlb, +static __always_inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) @@ -1861,7 +1861,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb, return addr; } -static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, +static __always_inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) -- 2.25.1
Powered by blists - more mailing lists