From nobody Tue Dec 16 22:55:06 2025 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id C4C1523BD0F for ; Tue, 6 May 2025 05:01:26 +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=1746507688; cv=none; b=DC3ugcxZGNZDGmyFAPkfrBGVm30+ka0Yw2psgLRSQLmXKHMXCY0RRd2eBOdU3lWcm5wyjwUhasIq2Ea1OF2hRiMSArSE87hxQNny/Qv+Uh2mjDB6auxw+65jSKMo5dvthD80eWHtSxf0plWoGxuHB6xGlqAxzRWbJ0QlElkYfb8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746507688; c=relaxed/simple; bh=NkZ64+CnfHQMQV0l6Oc9aXix7vbqM7RwwEd3cD87pjs=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=q5xxLxC3s8LmDpiC4SkzSMq5NSoKB7Pempm91QBbwQ1MgGttNmUOi+EOuiYOODqyO3rkjqcUlEgFvt+Lq8sUC7czGDjx8QAeHcqAor+ZOUz94qmgK0gENEV6gKQ/3oFfcLidsCUzZvffXtIM0muTfOETqmkQ+1oZPwYfE5vm2cE= 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 619271A2D; Mon, 5 May 2025 22:01:16 -0700 (PDT) Received: from K4MQJ0H1H2.emea.arm.com (K4MQJ0H1H2.blr.arm.com [10.162.43.13]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 802EC3F5A1; Mon, 5 May 2025 22:01:19 -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, Dev Jain Subject: [PATCH 1/3] mm: Call pointers to ptes as ptep Date: Tue, 6 May 2025 10:30:54 +0530 Message-Id: <20250506050056.59250-2-dev.jain@arm.com> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20250506050056.59250-1-dev.jain@arm.com> References: <20250506050056.59250-1-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 appending pointer type variables by p. No functional change. Signed-off-by: Dev Jain --- mm/mremap.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/mm/mremap.c b/mm/mremap.c index 7db9da609c84..1a08a7c3b92f 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -176,7 +176,7 @@ 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; pmd_t dummy_pmdval; spinlock_t *old_ptl, *new_ptl; bool force_flush =3D false; @@ -211,8 +211,8 @@ 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 +223,10 @@ 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; } @@ -235,12 +235,12 @@ 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) { - if (pte_none(ptep_get(old_pte))) + for (; old_addr < old_end; old_ptep++, old_addr +=3D PAGE_SIZE, + new_ptep++, new_addr +=3D PAGE_SIZE) { + 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 @@ -258,7 +258,7 @@ 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)) @@ -266,7 +266,7 @@ 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 @@ -275,8 +275,8 @@ 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 Tue Dec 16 22:55:06 2025 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 38FC323C8A8 for ; Tue, 6 May 2025 05:01:32 +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=1746507694; cv=none; b=AAdPbaBtOI5Z7liPDJ8A0VlWM6DjOo2ORYTbGfLCd301sdVp2/cBnXhlnJf2I8E1j+94BHUrAukZI7eKbzTuFtmmy9awIMqt2ocV7B7Y9rGC/NSgt86tGKRfhf5sIcgfy6Y0BVXcrWCpMpVmNcf3JPAqiTb1zDQ4zIkjzWyvIAU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746507694; c=relaxed/simple; bh=tzOGaduVxkJCjoBvnKim0M+stVllkyzS5NkeCZriEVk=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=dR1lUdguJde0IL9dz2sBOF59RcUHoJWB7a7POfHxxv0a4vgitFdi82F16NE2VbJ1ysx9Obm6HcdZa9Gkiu2VOLTGaw/uSGTPWE8JtXpPj1rUksOuhNG+BHgpKgk2bec6ba9GF4TGeIFL0rtxFekcN1Em3Mdt/8F0WJN/8y/Uyvc= 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 E63CF1E5E; Mon, 5 May 2025 22:01:22 -0700 (PDT) Received: from K4MQJ0H1H2.emea.arm.com (K4MQJ0H1H2.blr.arm.com [10.162.43.13]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 7F33F3F5A1; Mon, 5 May 2025 22:01:26 -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, Dev Jain Subject: [PATCH 2/3] mm: Add generic helper to hint a large folio Date: Tue, 6 May 2025 10:30:55 +0530 Message-Id: <20250506050056.59250-3-dev.jain@arm.com> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20250506050056.59250-1-dev.jain@arm.com> References: <20250506050056.59250-1-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" To use PTE batching, we want to determine whether the folio mapped by the PTE is large, thus requiring the use of vm_normal_folio(). We want to avoid the cost of vm_normal_folio() if the code path doesn't already require the folio. For arm64, pte_batch_hint() does the job. To generalize this hint, add a helper which will determine whether two consecutive PTEs point to consecutive PFNs, in which case there is a high probability that the underlying folio is large. Signed-off-by: Dev Jain --- include/linux/pgtable.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index b50447ef1c92..28e21fcc7837 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -369,6 +369,22 @@ static inline pgd_t pgdp_get(pgd_t *pgdp) } #endif =20 +/* Caller must ensure that ptep + 1 exists */ +static inline bool maybe_contiguous_pte_pfns(pte_t *ptep, pte_t pte) +{ + pte_t *next_ptep, next_pte; + + if (pte_batch_hint(ptep, pte) !=3D 1) + return true; + + next_ptep =3D ptep + 1; + next_pte =3D ptep_get(next_ptep); + if (!pte_present(next_pte)) + return false; + + return unlikely(pte_pfn(next_pte) - pte_pfn(pte) =3D=3D PAGE_SIZE); +} + #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, --=20 2.30.2 From nobody Tue Dec 16 22:55:06 2025 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id B8BA923C8BE for ; Tue, 6 May 2025 05:01:39 +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=1746507701; cv=none; b=SYTbnOi96lWjc7+nwlOcmA4/7JKufm+XjEg4Y4f7+PvppJn0ywkQGyuneyme73pCMNtoveknOO+Emh0hIhTttT11Zl3BknGKRqBzS9QfPFfapxvlwKpbYFknMj+72qfllTzfIqQklWl+Af0SThwkd1oNdPC5FGQw1DJ5HX3aBMY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746507701; c=relaxed/simple; bh=ue4CNnv4c/0imbT/7fs2S/8y/JnUgfdHYmeIPCw4uwA=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=RH2CmiG35GH9SiwfOJPiTNkWpXjkteoEiDn8cEnleCtvNs1BueDz0Css9E2ZQ+vFAN/r3m3aHCEkS6Pn0Rv52wRZvp/Dys/8GpOzyClEbIXRMh0Y2n2KkikZE/0lp0kEOMX6fWzpwxUoCsU9GSf47m7PvtmOQLtjJUc+uW0SNSk= 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 AA970113E; Mon, 5 May 2025 22:01:29 -0700 (PDT) Received: from K4MQJ0H1H2.emea.arm.com (K4MQJ0H1H2.blr.arm.com [10.162.43.13]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 0F0973F5A1; Mon, 5 May 2025 22:01:32 -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, Dev Jain Subject: [PATCH 3/3] mm: Optimize mremap() by PTE batching Date: Tue, 6 May 2025 10:30:56 +0530 Message-Id: <20250506050056.59250-4-dev.jain@arm.com> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20250506050056.59250-1-dev.jain@arm.com> References: <20250506050056.59250-1-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(). Use get_and_clear_full_ptes() so as to elide TLBIs on each contig block, which was previously done by ptep_get_and_clear(). Signed-off-by: Dev Jain --- mm/mremap.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/mm/mremap.c b/mm/mremap.c index 1a08a7c3b92f..3621c07d8eea 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -176,7 +176,7 @@ 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_ptep, *new_ptep, pte; + pte_t *old_ptep, *new_ptep, old_pte, pte; pmd_t dummy_pmdval; spinlock_t *old_ptl, *new_ptl; bool force_flush =3D false; @@ -185,6 +185,7 @@ static int move_ptes(struct pagetable_move_control *pmc, unsigned long old_end =3D old_addr + extent; unsigned long len =3D old_end - old_addr; int err =3D 0; + int nr; =20 /* * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma @@ -237,10 +238,14 @@ static int move_ptes(struct pagetable_move_control *p= mc, =20 for (; old_addr < old_end; old_ptep++, old_addr +=3D PAGE_SIZE, new_ptep++, new_addr +=3D PAGE_SIZE) { - if (pte_none(ptep_get(old_ptep))) + const fpb_t fpb_flags =3D FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; + int max_nr =3D (old_end - old_addr) >> PAGE_SHIFT; + + nr =3D 1; + 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 @@ -252,8 +257,17 @@ 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)) { + if ((max_nr !=3D 1) && maybe_contiguous_pte_pfns(old_ptep, old_pte)) { + struct folio *folio =3D vm_normal_folio(vma, old_addr, old_pte); + + if (folio && folio_test_large(folio)) + nr =3D folio_pte_batch(folio, old_addr, old_ptep, + old_pte, max_nr, fpb_flags, NULL, NULL, NULL); + } force_flush =3D true; + } + pte =3D get_and_clear_full_ptes(mm, old_addr, old_ptep, nr, 0); pte =3D move_pte(pte, old_addr, new_addr); pte =3D move_soft_dirty_pte(pte); =20 @@ -266,7 +280,7 @@ 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); } } =20 --=20 2.30.2