From nobody Sat Feb 7 22:56:43 2026 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 9DB5811712 for ; Tue, 10 Jun 2025 03:51:02 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749527464; cv=none; b=Mg+KwUdYPDPp+oEPLokYDt93iQgN2aJgJwQ/yltSKLQ4h8MDh9fM3PtfSDnk+A65mWCzIzSyDCBKTj1Q6RW74feYgiSALRotoWqORJRBbCKPv+ns9+pSnFvv7LNKjxMbZtiEHAng5Zq3VQs+rfiD2mqaVKdyImoCCOaI5VdZBnc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749527464; c=relaxed/simple; bh=/M5qnazF1rOsciFb4BaLzrUm3AHPuSaxuv5NrLuO7Jk=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=DPj2D8HYVNHXeLXsWYxMR1aAjGe0zm4AF9Bt34v2I4Z962+Xkk3xY71Uh4I8ttSy6YXfJES4XCmk56LCLhOkVCDl4w1qNvkRIx8fdtLWvvFCZD8JT/zxw3GdbObL7f5MBFZdS8CZMrPASdZp1UUHrNCR0CvKHPrfd1MEu53/69U= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id CCB1416A3; Mon, 9 Jun 2025 20:50:42 -0700 (PDT) Received: from MacBook-Pro.blr.arm.com (MacBook-Pro.blr.arm.com [10.164.18.48]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 3E0B33F59E; Mon, 9 Jun 2025 20:50:54 -0700 (PDT) From: Dev Jain To: akpm@linux-foundation.org Cc: Liam.Howlett@oracle.com, lorenzo.stoakes@oracle.com, vbabka@suse.cz, jannh@google.com, pfalcato@suse.de, linux-mm@kvack.org, linux-kernel@vger.kernel.org, david@redhat.com, peterx@redhat.com, ryan.roberts@arm.com, mingo@kernel.org, libang.li@antgroup.com, maobibo@loongson.cn, zhengqi.arch@bytedance.com, baohua@kernel.org, anshuman.khandual@arm.com, willy@infradead.org, ioworker0@gmail.com, yang@os.amperecomputing.com, baolin.wang@linux.alibaba.com, ziy@nvidia.com, hughd@google.com, Dev Jain Subject: [PATCH v4 1/2] mm: Call pointers to ptes as ptep Date: Tue, 10 Jun 2025 09:20:42 +0530 Message-Id: <20250610035043.75448-2-dev.jain@arm.com> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20250610035043.75448-1-dev.jain@arm.com> References: <20250610035043.75448-1-dev.jain@arm.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Avoid confusion between pte_t* and pte_t data types by suffixing pointer type variables with p. No functional change. Reviewed-by: Barry Song Reviewed-by: Anshuman Khandual Reviewed-by: Lorenzo Stoakes Signed-off-by: Dev Jain Acked-by: David Hildenbrand Reviewed-by: Pedro Falcato --- mm/mremap.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/mm/mremap.c b/mm/mremap.c index 60f6b8d0d5f0..180b12225368 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -176,7 +176,8 @@ static int move_ptes(struct pagetable_move_control *pmc, struct vm_area_struct *vma =3D pmc->old; bool need_clear_uffd_wp =3D vma_has_uffd_without_event_remap(vma); struct mm_struct *mm =3D 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 =3D false; @@ -211,8 +212,8 @@ static int move_ptes(struct pagetable_move_control *pmc, * We don't have to worry about the ordering of src and dst * pte locks because exclusive mmap_lock prevents deadlock. */ - old_pte =3D pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); - if (!old_pte) { + old_ptep =3D pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); + if (!old_ptep) { err =3D -EAGAIN; goto out; } @@ -223,10 +224,10 @@ static int move_ptes(struct pagetable_move_control *p= mc, * mmap_lock, so this new_pte page is stable, so there is no need to get * pmdval and do pmd_same() check. */ - new_pte =3D pte_offset_map_rw_nolock(mm, new_pmd, new_addr, &dummy_pmdval, + new_ptep =3D pte_offset_map_rw_nolock(mm, new_pmd, new_addr, &dummy_pmdva= l, &new_ptl); - if (!new_pte) { - pte_unmap_unlock(old_pte, old_ptl); + if (!new_ptep) { + pte_unmap_unlock(old_ptep, old_ptl); err =3D -EAGAIN; goto out; } @@ -235,14 +236,14 @@ static int move_ptes(struct pagetable_move_control *p= mc, flush_tlb_batched_pending(vma->vm_mm); arch_enter_lazy_mmu_mode(); =20 - for (; old_addr < old_end; old_pte++, old_addr +=3D PAGE_SIZE, - new_pte++, new_addr +=3D PAGE_SIZE) { - VM_WARN_ON_ONCE(!pte_none(*new_pte)); + for (; old_addr < old_end; old_ptep++, old_addr +=3D PAGE_SIZE, + new_ptep++, new_addr +=3D PAGE_SIZE) { + VM_WARN_ON_ONCE(!pte_none(*new_ptep)); =20 - if (pte_none(ptep_get(old_pte))) + if (pte_none(ptep_get(old_ptep))) continue; =20 - pte =3D ptep_get_and_clear(mm, old_addr, old_pte); + pte =3D 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 @@ -260,7 +261,7 @@ static int move_ptes(struct pagetable_move_control *pmc, pte =3D move_soft_dirty_pte(pte); =20 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)) @@ -268,7 +269,7 @@ static int move_ptes(struct pagetable_move_control *pmc, else if (is_swap_pte(pte)) pte =3D pte_swp_clear_uffd_wp(pte); } - set_pte_at(mm, new_addr, new_pte, pte); + set_pte_at(mm, new_addr, new_ptep, pte); } } =20 @@ -277,8 +278,8 @@ static int move_ptes(struct pagetable_move_control *pmc, flush_tlb_range(vma, old_end - len, old_end); if (new_ptl !=3D 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); --=20 2.30.2 From nobody Sat Feb 7 22:56:43 2026 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id CB9E411712 for ; Tue, 10 Jun 2025 03:51:09 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749527471; cv=none; b=ndJayDQIUgrfnvN1WGoUUcTicDfne+m6wYh3OZc+SBUyzGMa8HokE+bjj6e+s1pcf6zMs3qWQl+whJQc4Nzqk2WJT3wgydEELzM/6qAmItNzJbXVzB+e3EMJKtW8ZCZUURrAZpa51EBZKaNztFRx8bJovQIuqJp0l1M0FNsmuI8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1749527471; c=relaxed/simple; bh=K33aBlSZM2s8aovcnzMuvaa9PJqADPD9Al72bAky4+U=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=k9sDrew52vWyUH3B2C+GjYJfDCC5mSkIOPI0HSrb1D3hqRQwIFFHL0/m72EuEthszZge2iRo6BQBwLo+w2X7cOtd7qwJn/3I1u75jOXVLe6fk9Vxp2vB9zNnR0E3ivCTYqMtXtbvJcyQKKERIQQw2kz8cMXPr+/QtW6G/263fH8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 0ED402680; Mon, 9 Jun 2025 20:50:50 -0700 (PDT) Received: from MacBook-Pro.blr.arm.com (MacBook-Pro.blr.arm.com [10.164.18.48]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 7D4493F59E; Mon, 9 Jun 2025 20:51:02 -0700 (PDT) From: Dev Jain To: akpm@linux-foundation.org Cc: Liam.Howlett@oracle.com, lorenzo.stoakes@oracle.com, vbabka@suse.cz, jannh@google.com, pfalcato@suse.de, linux-mm@kvack.org, linux-kernel@vger.kernel.org, david@redhat.com, peterx@redhat.com, ryan.roberts@arm.com, mingo@kernel.org, libang.li@antgroup.com, maobibo@loongson.cn, zhengqi.arch@bytedance.com, baohua@kernel.org, anshuman.khandual@arm.com, willy@infradead.org, ioworker0@gmail.com, yang@os.amperecomputing.com, baolin.wang@linux.alibaba.com, ziy@nvidia.com, hughd@google.com, Dev Jain Subject: [PATCH v4 2/2] mm: Optimize mremap() by PTE batching Date: Tue, 10 Jun 2025 09:20:43 +0530 Message-Id: <20250610035043.75448-3-dev.jain@arm.com> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20250610035043.75448-1-dev.jain@arm.com> References: <20250610035043.75448-1-dev.jain@arm.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Use folio_pte_batch() to optimize move_ptes(). On arm64, if the ptes are painted with the contig bit, then ptep_get() will iterate through all 16 entries to collect a/d bits. Hence this optimization will result in a 16x reduction in the number of ptep_get() calls. Next, ptep_get_and_clear() will eventually call contpte_try_unfold() on every contig block, thus flushing the TLB for the complete large folio range. Instead, use get_and_clear_full_ptes() so as to elide TLBIs on each contig block, and on= ly do them on the starting and ending contig block. For split folios, there will be no pte batching; nr_ptes will be 1. For pagetable splitting, the ptes will still point to the same large folio; for arm64, this results in the optimization described above, and for other arches (including the general case), a minor improvement is expected due to a reduction in the number of function calls. Signed-off-by: Dev Jain Reviewed-by: Barry Song Reviewed-by: Lorenzo Stoakes Reviewed-by: Pedro Falcato --- mm/mremap.c | 39 ++++++++++++++++++++++++++++++++------- 1 file changed, 32 insertions(+), 7 deletions(-) diff --git a/mm/mremap.c b/mm/mremap.c index 180b12225368..18b215521ada 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -170,6 +170,23 @@ static pte_t move_soft_dirty_pte(pte_t pte) return pte; } =20 +static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned lon= g addr, + pte_t *ptep, pte_t pte, int max_nr) +{ + const fpb_t flags =3D FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; + struct folio *folio; + + if (max_nr =3D=3D 1) + return 1; + + folio =3D vm_normal_folio(vma, addr, pte); + if (!folio || !folio_test_large(folio)) + return 1; + + return folio_pte_batch(folio, addr, ptep, pte, max_nr, flags, NULL, + NULL, NULL); +} + static int move_ptes(struct pagetable_move_control *pmc, unsigned long extent, pmd_t *old_pmd, pmd_t *new_pmd) { @@ -177,7 +194,7 @@ static int move_ptes(struct pagetable_move_control *pmc, bool need_clear_uffd_wp =3D vma_has_uffd_without_event_remap(vma); struct mm_struct *mm =3D vma->vm_mm; pte_t *old_ptep, *new_ptep; - pte_t pte; + pte_t old_pte, pte; pmd_t dummy_pmdval; spinlock_t *old_ptl, *new_ptl; bool force_flush =3D false; @@ -185,6 +202,8 @@ static int move_ptes(struct pagetable_move_control *pmc, unsigned long new_addr =3D pmc->new_addr; unsigned long old_end =3D old_addr + extent; unsigned long len =3D old_end - old_addr; + int max_nr_ptes; + int nr_ptes; int err =3D 0; =20 /* @@ -236,14 +255,16 @@ static int move_ptes(struct pagetable_move_control *p= mc, flush_tlb_batched_pending(vma->vm_mm); arch_enter_lazy_mmu_mode(); =20 - for (; old_addr < old_end; old_ptep++, old_addr +=3D PAGE_SIZE, - new_ptep++, new_addr +=3D PAGE_SIZE) { + for (; old_addr < old_end; old_ptep +=3D nr_ptes, old_addr +=3D nr_ptes *= PAGE_SIZE, + new_ptep +=3D nr_ptes, new_addr +=3D nr_ptes * PAGE_SIZE) { VM_WARN_ON_ONCE(!pte_none(*new_ptep)); =20 - if (pte_none(ptep_get(old_ptep))) + nr_ptes =3D 1; + max_nr_ptes =3D (old_end - old_addr) >> PAGE_SHIFT; + old_pte =3D ptep_get(old_ptep); + if (pte_none(old_pte)) continue; =20 - pte =3D 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 @@ -255,8 +276,12 @@ static int move_ptes(struct pagetable_move_control *pm= c, * the TLB entry for the old mapping has been * flushed. */ - if (pte_present(pte)) + if (pte_present(old_pte)) { + nr_ptes =3D mremap_folio_pte_batch(vma, old_addr, old_ptep, + old_pte, max_nr_ptes); force_flush =3D true; + } + pte =3D get_and_clear_full_ptes(mm, old_addr, old_ptep, nr_ptes, 0); pte =3D move_pte(pte, old_addr, new_addr); pte =3D move_soft_dirty_pte(pte); =20 @@ -269,7 +294,7 @@ static int move_ptes(struct pagetable_move_control *pmc, else if (is_swap_pte(pte)) pte =3D pte_swp_clear_uffd_wp(pte); } - set_pte_at(mm, new_addr, new_ptep, pte); + set_ptes(mm, new_addr, new_ptep, pte, nr_ptes); } } =20 --=20 2.30.2