From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EE1CA230BD9 for ; Thu, 8 May 2025 23:36:49 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746747410; cv=none; b=qRjrNvrWLyHzxaWFBlSvpqawh4XQkxPU94Ao+93xEkg4i+jVSX6Derb50VWa3saVSpmLBRDH/V7+q8QFCUowRjW/iez7k/EKaX0kSP1SOFOkH0t96Ba/Y+2fvAQgenymT+iH+jIyySTEY1f+KR8xwrHYR6bDzhrCbQ4eKN1sNyI= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746747410; c=relaxed/simple; bh=1e8F0S67Lhq11t+oSW4n+1v636V8sCKPt0vUKLgwfdI=; h=Date:To:From:Subject:Message-Id; b=O63BGzwCC9MNMEavc9dBpibSdJSI0r6r2YqkZfICPu0BsUlS2UZJl4Tq07PGNUPAXc47JoxbwN8ruDXyxAcMSrwGEK69bDnoXgj8/NJ+1Abh9PNBgOWdjWO+VOel3e5FfhUKeHnEcJd/cBbRcFHRuNYSeKNO8EwDYol/7GQPGD4= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b=wgJ9q+3k; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b="wgJ9q+3k" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 481FDC4CEEF; Thu, 8 May 2025 23:36:49 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1746747409; bh=1e8F0S67Lhq11t+oSW4n+1v636V8sCKPt0vUKLgwfdI=; h=Date:To:From:Subject:From; b=wgJ9q+3kJscQ4yvvKS9UNgEHTMRqqv8NiOUJ15EtdBXlaEgPNmY6uVewMld10edZk 7F8MCx6zHBCbNpE/lvyJOkOXmsTCR/ljfB/YHSerGZ5X75Qdmz4+2lGo8HytYO2PA7 C1AS8LMc+gjMMqsp09Hk9KV35DWblPUOx2ntVcOw= Date: Thu, 08 May 2025 16:36:48 -0700 To: mm-commits@vger.kernel.org,ziy@nvidia.com,zhengqi.arch@bytedance.com,yang@os.amperecomputing.com,willy@infradead.org,vbabka@suse.cz,ryan.roberts@arm.com,peterx@redhat.com,mingo@kernel.org,maobibo@loongson.cn,lorenzo.stoakes@oracle.com,libang.li@antgroup.com,liam.howlett@oracle.com,jannh@google.com,ioworker0@gmail.com,hughd@google.com,david@redhat.com,baolin.wang@linux.alibaba.com,baohua@kernel.org,anshuman.khandual@arm.com,dev.jain@arm.com,akpm@linux-foundation.org From: Andrew Morton Subject: [to-be-updated] mm-call-pointers-to-ptes-as-ptep.patch removed from -mm tree Message-Id: <20250508233649.481FDC4CEEF@smtp.kernel.org> Precedence: bulk X-Mailing-List: mm-commits@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: The quilt patch titled Subject: mm: call pointers to ptes as ptep has been removed from the -mm tree. Its filename was mm-call-pointers-to-ptes-as-ptep.patch This patch was dropped because an updated version will be issued ------------------------------------------------------ From: Dev Jain Subject: mm: call pointers to ptes as ptep Date: Wed, 7 May 2025 11:32:55 +0530 Patch series "Optimize mremap() for large folios", v2. Currently move_ptes() iterates through ptes one by one. If the underlying folio mapped by the ptes is large, we can process those ptes in a batch using folio_pte_batch(), thus clearing and setting the PTEs in one go. For arm64 specifically, this results in a 16x reduction in the number of ptep_get() calls (since on a contig block, ptep_get() on arm64 will iterate through all 16 entries to collect a/d bits), and we also elide extra TLBIs through get_and_clear_full_ptes, replacing ptep_get_and_clear. Mapping 512K of memory, memsetting it, remapping it to src + 512K, and munmapping it 10,000 times, the average execution time reduces from 1.9 to 1.2 seconds, giving a 37% performance optimization, on Apple M3 (arm64). Test program for reference: #define _GNU_SOURCE #include #include #include #include #include #include #define SIZE (1UL << 20) // 512 KB int main(void) { void *new_addr, *addr; for (int i = 0; i < 10000; ++i) { addr = mmap((void *)(1UL << 30), SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); return 1; } memset(addr, 0xAA, SIZE); new_addr = mremap(addr, SIZE, SIZE, MREMAP_MAYMOVE | MREMAP_FIXED, addr + SIZE); if (new_addr != (addr + SIZE)) { perror("mremap"); return 1; } munmap(new_addr, SIZE); } } This patch (of 2): Avoid confusion between pte_t* and pte_t data types by suffixing pointer type variables with p. No functional change. Link: https://lkml.kernel.org/r/20250507060256.78278-1-dev.jain@arm.com Link: https://lkml.kernel.org/r/20250507060256.78278-2-dev.jain@arm.com Signed-off-by: Dev Jain Reviewed-by: Barry Song Cc: Anshuman Khandual Cc: Bang Li Cc: Baolin Wang Cc: bibo mao Cc: David Hildenbrand Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jann Horn Cc: Lance Yang Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Qi Zheng Cc: Ryan Roberts Cc: Vlastimil Babka Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/mremap.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) --- a/mm/mremap.c~mm-call-pointers-to-ptes-as-ptep +++ a/mm/mremap.c @@ -176,7 +176,8 @@ static int move_ptes(struct pagetable_mo struct vm_area_struct *vma = pmc->old; bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct mm_struct *mm = vma->vm_mm; - pte_t *old_pte, *new_pte, pte; + pte_t *old_ptep, *new_ptep; + pte_t pte; pmd_t dummy_pmdval; spinlock_t *old_ptl, *new_ptl; bool force_flush = false; @@ -211,8 +212,8 @@ static int move_ptes(struct pagetable_mo * We don't have to worry about the ordering of src and dst * pte locks because exclusive mmap_lock prevents deadlock. */ - old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); - if (!old_pte) { + old_ptep = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); + if (!old_ptep) { err = -EAGAIN; goto out; } @@ -223,10 +224,10 @@ static int move_ptes(struct pagetable_mo * mmap_lock, so this new_pte page is stable, so there is no need to get * pmdval and do pmd_same() check. */ - new_pte = pte_offset_map_rw_nolock(mm, new_pmd, new_addr, &dummy_pmdval, + new_ptep = pte_offset_map_rw_nolock(mm, new_pmd, new_addr, &dummy_pmdval, &new_ptl); - if (!new_pte) { - pte_unmap_unlock(old_pte, old_ptl); + if (!new_ptep) { + pte_unmap_unlock(old_ptep, old_ptl); err = -EAGAIN; goto out; } @@ -235,12 +236,12 @@ static int move_ptes(struct pagetable_mo flush_tlb_batched_pending(vma->vm_mm); arch_enter_lazy_mmu_mode(); - for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, - new_pte++, new_addr += PAGE_SIZE) { - if (pte_none(ptep_get(old_pte))) + for (; old_addr < old_end; old_ptep++, old_addr += PAGE_SIZE, + new_ptep++, new_addr += PAGE_SIZE) { + if (pte_none(ptep_get(old_ptep))) continue; - pte = ptep_get_and_clear(mm, old_addr, old_pte); + pte = ptep_get_and_clear(mm, old_addr, old_ptep); /* * If we are remapping a valid PTE, make sure * to flush TLB before we drop the PTL for the @@ -258,7 +259,7 @@ static int move_ptes(struct pagetable_mo pte = move_soft_dirty_pte(pte); if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) - pte_clear(mm, new_addr, new_pte); + pte_clear(mm, new_addr, new_ptep); else { if (need_clear_uffd_wp) { if (pte_present(pte)) @@ -266,7 +267,7 @@ static int move_ptes(struct pagetable_mo else if (is_swap_pte(pte)) pte = pte_swp_clear_uffd_wp(pte); } - set_pte_at(mm, new_addr, new_pte, pte); + set_pte_at(mm, new_addr, new_ptep, pte); } } @@ -275,8 +276,8 @@ static int move_ptes(struct pagetable_mo flush_tlb_range(vma, old_end - len, old_end); if (new_ptl != old_ptl) spin_unlock(new_ptl); - pte_unmap(new_pte - 1); - pte_unmap_unlock(old_pte - 1, old_ptl); + pte_unmap(new_ptep - 1); + pte_unmap_unlock(old_ptep - 1, old_ptl); out: if (pmc->need_rmap_locks) drop_rmap_locks(vma); _ Patches currently in -mm which might be from dev.jain@arm.com are mempolicy-optimize-queue_folios_pte_range-by-pte-batching.patch mm-optimize-mremap-by-pte-batching.patch