From patchwork Fri Jan 8 17:15:15 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Will Deacon X-Patchwork-Id: 12007063 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6D775C433E0 for ; Fri, 8 Jan 2021 17:15:35 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id F034523A00 for ; Fri, 8 Jan 2021 17:15:34 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org F034523A00 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 8A9E86B02AB; Fri, 8 Jan 2021 12:15:34 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 832D96B02B2; Fri, 8 Jan 2021 12:15:34 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 6FB996B02B6; Fri, 8 Jan 2021 12:15:34 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0254.hostedemail.com [216.40.44.254]) by kanga.kvack.org (Postfix) with ESMTP id 4CB836B02AB for ; Fri, 8 Jan 2021 12:15:34 -0500 (EST) Received: from smtpin17.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id 0E770181AEF31 for ; Fri, 8 Jan 2021 17:15:34 +0000 (UTC) X-FDA: 77683259388.17.jump73_4c0a323274f4 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin17.hostedemail.com (Postfix) with ESMTP id DA0B4180D018B for ; Fri, 8 Jan 2021 17:15:33 +0000 (UTC) X-HE-Tag: jump73_4c0a323274f4 X-Filterd-Recvd-Size: 21953 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by imf22.hostedemail.com (Postfix) with ESMTP for ; Fri, 8 Jan 2021 17:15:32 +0000 (UTC) Received: by mail.kernel.org (Postfix) with ESMTPSA id A7D8323A05; Fri, 8 Jan 2021 17:15:29 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1610126132; bh=M8AZVL12e49/HvtFjbLeqMjI3o8CZSFxY7zNSCZNwCM=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=plVMuJPP/1dUKv6/bTMw2VMskeonDA64Ps3nusu/DT1fiiqhZPk8vvd5ffmIOV17a GuKfSHsyfiL4xU3M6g6CqejAIDQ4FjOLOX+3rCUxL1NgTGcR4SK1I/8qC3Qgir8sTm qhwHNKN+f56AvU8iVXgRkI+XCkRTeqYpxFcz9TL5McB0wxjbieMRbprvEdwjWWVRKY Nqi/ZxDRJQcjeisheEfsxVCQ8pYFFqCh81SBjT1tZHxA2irrg//BmX3x87BX44lx6I WEyH4HDuxC4dlNSa5C4qkEJKW/mxBod7tkMvQ6WpnCIFqHL2auq4r7yrHD9uPIP+eT q2Au8SpFkzOXw== From: Will Deacon To: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, Will Deacon , Catalin Marinas , Jan Kara , Minchan Kim , Andrew Morton , "Kirill A . Shutemov" , Linus Torvalds , Vinayak Menon , Hugh Dickins , kernel-team@android.com Subject: [PATCH v2 1/3] mm: Cleanup faultaround and finish_fault() codepaths Date: Fri, 8 Jan 2021 17:15:15 +0000 Message-Id: <20210108171517.5290-2-will@kernel.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20210108171517.5290-1-will@kernel.org> References: <20210108171517.5290-1-will@kernel.org> MIME-Version: 1.0 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: "Kirill A. Shutemov" alloc_set_pte() has two users with different requirements: in the faultaround code, it called from an atomic context and PTE page table has to be preallocated. finish_fault() can sleep and allocate page table as needed. PTL locking rules are also strange, hard to follow and overkill for finish_fault(). Let's untangle the mess. alloc_set_pte() has gone now. All locking is explicit. The price is some code duplication to handle huge pages in faultaround path, but it should be fine, having overall improvement in readability. Signed-off-by: Kirill A. Shutemov Signed-off-by: Will Deacon --- fs/xfs/xfs_file.c | 6 +- include/linux/mm.h | 12 ++- include/linux/pgtable.h | 11 +++ mm/filemap.c | 177 ++++++++++++++++++++++++++--------- mm/memory.c | 199 ++++++++++++---------------------------- 5 files changed, 213 insertions(+), 192 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 5b0f93f73837..111fe73bb8a7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1319,17 +1319,19 @@ xfs_filemap_pfn_mkwrite( return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true); } -static void +static vm_fault_t xfs_filemap_map_pages( struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct inode *inode = file_inode(vmf->vma->vm_file); + vm_fault_t ret; xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - filemap_map_pages(vmf, start_pgoff, end_pgoff); + ret = filemap_map_pages(vmf, start_pgoff, end_pgoff); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + return ret; } static const struct vm_operations_struct xfs_file_vm_ops = { diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..801dd99f733c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -542,8 +542,8 @@ struct vm_fault { * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. - * vm_ops->map_pages() calls - * alloc_set_pte() from atomic context. + * vm_ops->map_pages() sets up a page + * table from from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. @@ -578,7 +578,7 @@ struct vm_operations_struct { vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); - void (*map_pages)(struct vm_fault *vmf, + vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); @@ -988,7 +988,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); +void do_set_pte(struct vm_fault *vmf, struct page *page); + vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif @@ -2622,7 +2624,7 @@ extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); -extern void filemap_map_pages(struct vm_fault *vmf, +extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 8fcdfa52eb4b..36eb748f3c97 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1314,6 +1314,17 @@ static inline int pmd_trans_unstable(pmd_t *pmd) #endif } +/* + * the ordering of these checks is important for pmds with _page_devmap set. + * if we check pmd_trans_unstable() first we will trip the bad_pmd() check + * inside of pmd_none_or_trans_huge_or_clear_bad(). this will end up correctly + * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. + */ +static inline int pmd_devmap_trans_unstable(pmd_t *pmd) +{ + return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); +} + #ifndef CONFIG_NUMA_BALANCING /* * Technically a PTE can be PROTNONE even when not doing NUMA balancing but diff --git a/mm/filemap.c b/mm/filemap.c index 5c9d564317a5..c1f2dc89b8a7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -42,6 +42,7 @@ #include #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -2911,74 +2912,164 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_fault); -void filemap_map_pages(struct vm_fault *vmf, - pgoff_t start_pgoff, pgoff_t end_pgoff) +static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) { - struct file *file = vmf->vma->vm_file; + struct mm_struct *mm = vmf->vma->vm_mm; + + /* Huge page is mapped? No need to proceed. */ + if (pmd_trans_huge(*vmf->pmd)) { + unlock_page(page); + put_page(page); + return true; + } + + if (pmd_none(*vmf->pmd) && PageTransHuge(page)) { + vm_fault_t ret = do_set_pmd(vmf, page); + if (!ret) { + /* The page is mapped successfully, reference consumed. */ + unlock_page(page); + return true; + } + } + + if (pmd_none(*vmf->pmd)) { + vmf->ptl = pmd_lock(mm, vmf->pmd); + if (likely(pmd_none(*vmf->pmd))) { + mm_inc_nr_ptes(mm); + pmd_populate(mm, vmf->pmd, vmf->prealloc_pte); + vmf->prealloc_pte = NULL; + } + spin_unlock(vmf->ptl); + } + + /* See comment in handle_pte_fault() */ + if (pmd_devmap_trans_unstable(vmf->pmd)) { + unlock_page(page); + put_page(page); + return true; + } + + return false; +} + +static struct page *next_uptodate_page(struct page *page, + struct address_space *mapping, + struct xa_state *xas, pgoff_t end_pgoff) +{ + unsigned long max_idx; + + do { + if (!page) + return NULL; + if (xas_retry(xas, page)) + continue; + if (xa_is_value(page)) + continue; + if (PageLocked(page)) + continue; + if (!page_cache_get_speculative(page)) + continue; + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(xas))) + goto skip; + if (!PageUptodate(page) || PageReadahead(page)) + goto skip; + if (PageHWPoison(page)) + goto skip; + if (!trylock_page(page)) + goto skip; + if (page->mapping != mapping) + goto unlock; + if (!PageUptodate(page)) + goto unlock; + max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + if (xas->xa_index >= max_idx) + goto unlock; + return page; +unlock: + unlock_page(page); +skip: + put_page(page); + } while ((page = xas_next_entry(xas, end_pgoff)) != NULL); + + return NULL; +} + +static inline struct page *first_map_page(struct address_space *mapping, + struct xa_state *xas, + pgoff_t end_pgoff) +{ + return next_uptodate_page(xas_find(xas, end_pgoff), + mapping, xas, end_pgoff); +} + +static inline struct page *next_map_page(struct address_space *mapping, + struct xa_state *xas, + pgoff_t end_pgoff) +{ + return next_uptodate_page(xas_next_entry(xas, end_pgoff), + mapping, xas, end_pgoff); +} + +vm_fault_t filemap_map_pages(struct vm_fault *vmf, + pgoff_t start_pgoff, pgoff_t end_pgoff) +{ + struct vm_area_struct *vma = vmf->vma; + struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; - unsigned long max_idx; + unsigned long address = vmf->address; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *head, *page; unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); + vm_fault_t ret = 0; rcu_read_lock(); - xas_for_each(&xas, head, end_pgoff) { - if (xas_retry(&xas, head)) - continue; - if (xa_is_value(head)) - goto next; + head = first_map_page(mapping, &xas, end_pgoff); + if (!head) + goto out; - /* - * Check for a locked page first, as a speculative - * reference may adversely influence page migration. - */ - if (PageLocked(head)) - goto next; - if (!page_cache_get_speculative(head)) - goto next; + if (filemap_map_pmd(vmf, head)) { + ret = VM_FAULT_NOPAGE; + goto out; + } - /* Has the page moved or been split? */ - if (unlikely(head != xas_reload(&xas))) - goto skip; + vmf->address = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); + do { page = find_subpage(head, xas.xa_index); - - if (!PageUptodate(head) || - PageReadahead(page) || - PageHWPoison(page)) - goto skip; - if (!trylock_page(head)) - goto skip; - - if (head->mapping != mapping || !PageUptodate(head)) - goto unlock; - - max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); - if (xas.xa_index >= max_idx) + if (PageHWPoison(page)) goto unlock; if (mmap_miss > 0) mmap_miss--; vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; - if (vmf->pte) - vmf->pte += xas.xa_index - last_pgoff; + vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; - if (alloc_set_pte(vmf, page)) + + if (!pte_none(*vmf->pte)) goto unlock; + + do_set_pte(vmf, page); + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, vmf->address, vmf->pte); unlock_page(head); - goto next; + + /* The fault is handled */ + if (vmf->address == address) + ret = VM_FAULT_NOPAGE; + continue; unlock: unlock_page(head); -skip: put_page(head); -next: - /* Huge page is mapped? No need to proceed. */ - if (pmd_trans_huge(*vmf->pmd)) - break; - } + } while ((head = next_map_page(mapping, &xas, end_pgoff)) != NULL); + pte_unmap_unlock(vmf->pte, vmf->ptl); +out: rcu_read_unlock(); + vmf->address = address; WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); + return ret; } EXPORT_SYMBOL(filemap_map_pages); diff --git a/mm/memory.c b/mm/memory.c index feff48e1465a..3e2fc2950ad7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3503,7 +3503,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; - /* See the comment in pte_alloc_one_map() */ + /* See comment in handle_pte_fault() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; @@ -3643,66 +3643,6 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) return ret; } -/* - * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. - * If we check pmd_trans_unstable() first we will trip the bad_pmd() check - * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly - * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. - */ -static int pmd_devmap_trans_unstable(pmd_t *pmd) -{ - return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); -} - -static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) -{ - struct vm_area_struct *vma = vmf->vma; - - if (!pmd_none(*vmf->pmd)) - goto map_pte; - if (vmf->prealloc_pte) { - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_none(*vmf->pmd))) { - spin_unlock(vmf->ptl); - goto map_pte; - } - - mm_inc_nr_ptes(vma->vm_mm); - pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); - spin_unlock(vmf->ptl); - vmf->prealloc_pte = NULL; - } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { - return VM_FAULT_OOM; - } -map_pte: - /* - * If a huge pmd materialized under us just retry later. Use - * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of - * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge - * under us and then back to pmd_none, as a result of MADV_DONTNEED - * running immediately after a huge pmd fault in a different thread of - * this mm, in turn leading to a misleading pmd_trans_huge() retval. - * All we have to ensure is that it is a regular pmd that we can walk - * with pte_offset_map() and we can do that through an atomic read in - * C, which is what pmd_trans_unstable() provides. - */ - if (pmd_devmap_trans_unstable(vmf->pmd)) - return VM_FAULT_NOPAGE; - - /* - * At this point we know that our vmf->pmd points to a page of ptes - * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() - * for the duration of the fault. If a racing MADV_DONTNEED runs and - * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still - * be valid and we will re-check to make sure the vmf->pte isn't - * pte_none() under vmf->ptl protection when we return to - * alloc_set_pte(). - */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); - return 0; -} - #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { @@ -3717,7 +3657,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf) vmf->prealloc_pte = NULL; } -static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; @@ -3775,52 +3715,17 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) return ret; } #else -static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { - BUILD_BUG(); - return 0; + return VM_FAULT_FALLBACK; } #endif -/** - * alloc_set_pte - setup new PTE entry for given page and add reverse page - * mapping. If needed, the function allocates page table or use pre-allocated. - * - * @vmf: fault environment - * @page: page to map - * - * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on - * return. - * - * Target users are page handler itself and implementations of - * vm_ops->map_pages. - * - * Return: %0 on success, %VM_FAULT_ code in case of error. - */ -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) +void do_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; pte_t entry; - vm_fault_t ret; - - if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { - ret = do_set_pmd(vmf, page); - if (ret != VM_FAULT_FALLBACK) - return ret; - } - - if (!vmf->pte) { - ret = pte_alloc_one_map(vmf); - if (ret) - return ret; - } - - /* Re-check under ptl */ - if (unlikely(!pte_none(*vmf->pte))) { - update_mmu_tlb(vma, vmf->address, vmf->pte); - return VM_FAULT_NOPAGE; - } flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); @@ -3837,14 +3742,8 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) page_add_file_rmap(page, false); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); - - /* no need to invalidate: a not-present page won't be cached */ - update_mmu_cache(vma, vmf->address, vmf->pte); - - return 0; } - /** * finish_fault - finish page fault once we have prepared the page to fault * @@ -3862,12 +3761,12 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) */ vm_fault_t finish_fault(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct page *page; - vm_fault_t ret = 0; + vm_fault_t ret; /* Did we COW the page? */ - if ((vmf->flags & FAULT_FLAG_WRITE) && - !(vmf->vma->vm_flags & VM_SHARED)) + if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; @@ -3876,12 +3775,38 @@ vm_fault_t finish_fault(struct vm_fault *vmf) * check even for read faults because we might have lost our CoWed * page */ - if (!(vmf->vma->vm_flags & VM_SHARED)) - ret = check_stable_address_space(vmf->vma->vm_mm); - if (!ret) - ret = alloc_set_pte(vmf, page); - if (vmf->pte) - pte_unmap_unlock(vmf->pte, vmf->ptl); + if (!(vma->vm_flags & VM_SHARED)) { + ret = check_stable_address_space(vma->vm_mm); + if (ret) + return ret; + } + + if (pmd_none(*vmf->pmd)) { + if (PageTransCompound(page)) { + ret = do_set_pmd(vmf, page); + if (ret != VM_FAULT_FALLBACK) + return ret; + } + + if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) + return VM_FAULT_OOM; + } + + /* See comment in handle_pte_fault() */ + if (pmd_devmap_trans_unstable(vmf->pmd)) + return 0; + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + ret = 0; + /* Re-check under ptl */ + if (likely(pte_none(*vmf->pte))) + do_set_pte(vmf, page); + else + ret = VM_FAULT_NOPAGE; + + update_mmu_tlb(vma, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } @@ -3951,13 +3876,12 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) pgoff_t start_pgoff = vmf->pgoff; pgoff_t end_pgoff; int off; - vm_fault_t ret = 0; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; - vmf->address = max(address & mask, vmf->vma->vm_start); - off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + address = max(address & mask, vmf->vma->vm_start); + off = ((vmf->address - address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); start_pgoff -= off; /* @@ -3965,7 +3889,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) * the vma or nr_pages from start_pgoff, depending what is nearest. */ end_pgoff = start_pgoff - - ((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + + ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, start_pgoff + nr_pages - 1); @@ -3973,31 +3897,11 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) - goto out; + return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } - vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); - - /* Huge page is mapped? Page fault is solved */ - if (pmd_trans_huge(*vmf->pmd)) { - ret = VM_FAULT_NOPAGE; - goto out; - } - - /* ->map_pages() haven't done anything useful. Cold page cache? */ - if (!vmf->pte) - goto out; - - /* check if the page fault is solved */ - vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); - if (!pte_none(*vmf->pte)) - ret = VM_FAULT_NOPAGE; - pte_unmap_unlock(vmf->pte, vmf->ptl); -out: - vmf->address = address; - vmf->pte = NULL; - return ret; + return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); } static vm_fault_t do_read_fault(struct vm_fault *vmf) @@ -4353,7 +4257,18 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) */ vmf->pte = NULL; } else { - /* See comment in pte_alloc_one_map() */ + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead + * of pmd_trans_huge() to ensure the pmd didn't become + * pmd_trans_huge under us and then back to pmd_none, as a + * result of MADV_DONTNEED running immediately after a huge pmd + * fault in a different thread of this mm, in turn leading to a + * misleading pmd_trans_huge() retval. All we have to ensure is + * that it is a regular pmd that we can walk with + * pte_offset_map() and we can do that through an atomic read + * in C, which is what pmd_trans_unstable() provides. + */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* From patchwork Fri Jan 8 17:15:16 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Will Deacon X-Patchwork-Id: 12007067 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id D5945C433E6 for ; Fri, 8 Jan 2021 17:15:42 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 65D3F23A00 for ; Fri, 8 Jan 2021 17:15:42 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 65D3F23A00 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 32D1E6B02B9; Fri, 8 Jan 2021 12:15:41 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 241A66B02BD; Fri, 8 Jan 2021 12:15:41 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 0DFDA6B02BF; Fri, 8 Jan 2021 12:15:41 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0175.hostedemail.com [216.40.44.175]) by kanga.kvack.org (Postfix) with ESMTP id DF7626B02B9 for ; Fri, 8 Jan 2021 12:15:40 -0500 (EST) Received: from smtpin03.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay02.hostedemail.com (Postfix) with ESMTP id 72A843642 for ; Fri, 8 Jan 2021 17:15:36 +0000 (UTC) X-FDA: 77683259472.03.join78_210b6a0274f4 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin03.hostedemail.com (Postfix) with ESMTP id 1652E28A4E8 for ; Fri, 8 Jan 2021 17:15:36 +0000 (UTC) X-HE-Tag: join78_210b6a0274f4 X-Filterd-Recvd-Size: 6700 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by imf11.hostedemail.com (Postfix) with ESMTP for ; Fri, 8 Jan 2021 17:15:35 +0000 (UTC) Received: by mail.kernel.org (Postfix) with ESMTPSA id 7BECD23A1E; Fri, 8 Jan 2021 17:15:32 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1610126134; bh=RQ63edxxspf278oJN0oZGKPL8Fi8yL2rV5xz0JAIPv8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=l1piDlIhX/f7OnjtPcJpJ4+WxCxxcyvn0iiTbR9lDZR6q0nMVPBTV7cjgwoxLQnoc cdEY2UWOe4xwjG2xKf562FaMUxxnniFbfGEoRUV7fj+ciTIkUy+NTU9wNfWINk9l1m 5uacUKtKOVQYgNHM/eo1DLLGT+P4cBjqznWyUaC5KQOsb7ndljYvtZXOrG/9OScwKp N7hBFkDQtiBjvBvud+jy4oLAVqdsFwY0F2GVjIHppJQWXsh6GdT/WZLqLBYgV0W3no xa3W9mCmCkkvvVQQDjViPOqb1mqSrQjdOCraxW+dBg1W4Di062CDKANGBOhcCStZqU tWOPBXbg9zTqQ== From: Will Deacon To: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, Will Deacon , Catalin Marinas , Jan Kara , Minchan Kim , Andrew Morton , "Kirill A . Shutemov" , Linus Torvalds , Vinayak Menon , Hugh Dickins , kernel-team@android.com Subject: [PATCH v2 2/3] mm: Allow architectures to request 'old' entries when prefaulting Date: Fri, 8 Jan 2021 17:15:16 +0000 Message-Id: <20210108171517.5290-3-will@kernel.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20210108171517.5290-1-will@kernel.org> References: <20210108171517.5290-1-will@kernel.org> MIME-Version: 1.0 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: Commit 5c0a85fad949 ("mm: make faultaround produce old ptes") changed the "faultaround" behaviour to initialise prefaulted PTEs as 'old', since this avoids vmscan wrongly assuming that they are hot, despite having never been explicitly accessed by userspace. The change has been shown to benefit numerous arm64 micro-architectures (with hardware access flag) running Android, where both application launch latency and direct reclaim time are significantly reduced. Unfortunately, commit 315d09bf30c2 ("Revert "mm: make faultaround produce old ptes"") reverted the change to it being identified as the cause of a ~6% regression in unixbench on x86. Experiments on a variety of recent arm64 micro-architectures indicate that unixbench is not affected by the original commit, yielding a 0-1% performance improvement. Since one size does not fit all for the initial state of prefaulted PTEs, introduce arch_wants_old_prefaulted_pte(), which allows an architecture to opt-in to 'old' prefaulted PTEs at runtime based on whatever criteria it may have. Cc: Jan Kara Cc: Minchan Kim Cc: Andrew Morton Cc: Kirill A. Shutemov Cc: Linus Torvalds Reported-by: Vinayak Menon Signed-off-by: Will Deacon --- include/linux/mm.h | 5 ++++- mm/filemap.c | 12 ++++++++---- mm/memory.c | 20 +++++++++++++++++++- 3 files changed, 31 insertions(+), 6 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 801dd99f733c..873e410d6238 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -434,6 +434,7 @@ extern pgprot_t protection_map[16]; * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * @FAULT_FLAG_PREFAULT: Fault was a prefault. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -464,6 +465,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_REMOTE 0x80 #define FAULT_FLAG_INSTRUCTION 0x100 #define FAULT_FLAG_INTERRUPTIBLE 0x200 +#define FAULT_FLAG_PREFAULT 0x400 /* * The default fault flags that should be used by most of the @@ -501,7 +503,8 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags) { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ - { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } + { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ + { FAULT_FLAG_PREFAULT, "PREFAULT" } /* * vm_fault is filled by the pagefault handler and passed to the vma's diff --git a/mm/filemap.c b/mm/filemap.c index c1f2dc89b8a7..0fb9d1714797 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3051,14 +3051,18 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, if (!pte_none(*vmf->pte)) goto unlock; + /* We're about to handle the fault */ + if (vmf->address == address) { + vmf->flags &= ~FAULT_FLAG_PREFAULT; + ret = VM_FAULT_NOPAGE; + } else { + vmf->flags |= FAULT_FLAG_PREFAULT; + } + do_set_pte(vmf, page); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock_page(head); - - /* The fault is handled */ - if (vmf->address == address) - ret = VM_FAULT_NOPAGE; continue; unlock: unlock_page(head); diff --git a/mm/memory.c b/mm/memory.c index 3e2fc2950ad7..f0e7c589ca9d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -134,6 +134,18 @@ static inline bool arch_faults_on_old_pte(void) } #endif +#ifndef arch_wants_old_prefaulted_pte +static inline bool arch_wants_old_prefaulted_pte(void) +{ + /* + * Transitioning a PTE from 'old' to 'young' can be expensive on + * some architectures, even if it's performed in hardware. By + * default, "false" means prefaulted entries will be 'young'. + */ + return false; +} +#endif + static int __init disable_randmaps(char *s) { randomize_va_space = 0; @@ -3725,11 +3737,17 @@ void do_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; + bool prefault = vmf->flags & FAULT_FLAG_PREFAULT; pte_t entry; flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); - entry = pte_sw_mkyoung(entry); + + if (prefault && arch_wants_old_prefaulted_pte()) + entry = pte_mkold(entry); + else + entry = pte_sw_mkyoung(entry); + if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ From patchwork Fri Jan 8 17:15:17 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Will Deacon X-Patchwork-Id: 12007065 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5FC94C433DB for ; Fri, 8 Jan 2021 17:15:41 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 1557523A00 for ; Fri, 8 Jan 2021 17:15:41 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 1557523A00 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 9E0FA6B02B2; Fri, 8 Jan 2021 12:15:40 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 96A956B02B9; Fri, 8 Jan 2021 12:15:40 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 834546B02BA; Fri, 8 Jan 2021 12:15:40 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0242.hostedemail.com [216.40.44.242]) by kanga.kvack.org (Postfix) with ESMTP id 6413F6B02B2 for ; Fri, 8 Jan 2021 12:15:40 -0500 (EST) Received: from smtpin15.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay01.hostedemail.com (Postfix) with ESMTP id 29C93180AD811 for ; Fri, 8 Jan 2021 17:15:40 +0000 (UTC) X-FDA: 77683259640.15.hook09_120947a274f4 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin15.hostedemail.com (Postfix) with ESMTP id C18AD1814B0C1 for ; Fri, 8 Jan 2021 17:15:39 +0000 (UTC) X-HE-Tag: hook09_120947a274f4 X-Filterd-Recvd-Size: 3110 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by imf27.hostedemail.com (Postfix) with ESMTP for ; Fri, 8 Jan 2021 17:15:38 +0000 (UTC) Received: by mail.kernel.org (Postfix) with ESMTPSA id 227E623A1D; Fri, 8 Jan 2021 17:15:34 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1610126137; bh=a8XtFnA7Zvrd0DWLoNyieMx6jPLocftcZJUWhZ6r6ng=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=W9nPI7ivwFyQT3P0dzQuu+zFqBTC4v2Wgv7wkX0WyHOzmeOnQYOmKVaQHDreD0RFh 0UFgmwKyA/o+dHv58kCLc7pdd9DTj6Rfki3fYqQ/ghiZiTQnbRGWExe0tWmjI+ynRr uGFzbQdWdameHsCIHXBXqhXL7ZaolzjQYGQXlzPQMHAvnHC0uw+ckErXkOc7s7RQ2D NX7Mh2z0TuDNU8YhSfJuB5D5cg+QaeKq7bFU2enyldXU8NtTZW/p/sFmYlSFvgVIek onUwKo5nbROA5DW3ShBzanFVGJP+D4+Lv0bBY1R7Yfw9zAQYFs3g+RiGAVy/2nowf8 ROpcP+z5L6/4w== From: Will Deacon To: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, Will Deacon , Catalin Marinas , Jan Kara , Minchan Kim , Andrew Morton , "Kirill A . Shutemov" , Linus Torvalds , Vinayak Menon , Hugh Dickins , kernel-team@android.com Subject: [PATCH v2 3/3] arm64: mm: Implement arch_wants_old_prefaulted_pte() Date: Fri, 8 Jan 2021 17:15:17 +0000 Message-Id: <20210108171517.5290-4-will@kernel.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20210108171517.5290-1-will@kernel.org> References: <20210108171517.5290-1-will@kernel.org> MIME-Version: 1.0 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On CPUs with hardware AF/DBM, initialising prefaulted PTEs as 'old' improves vmscan behaviour and does not appear to introduce any overhead. Implement arch_wants_old_prefaulted_pte() to return 'true' if we detect hardware access flag support at runtime. This can be extended in future based on MIDR matching if necessary. Cc: Catalin Marinas Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 501562793ce2..e17b96d0e4b5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -980,7 +980,17 @@ static inline bool arch_faults_on_old_pte(void) return !cpu_has_hw_af(); } -#define arch_faults_on_old_pte arch_faults_on_old_pte +#define arch_faults_on_old_pte arch_faults_on_old_pte + +/* + * Experimentally, it's cheap to set the access flag in hardware and we + * benefit from prefaulting mappings as 'old' to start with. + */ +static inline bool arch_wants_old_prefaulted_pte(void) +{ + return !arch_faults_on_old_pte(); +} +#define arch_wants_old_prefaulted_pte arch_wants_old_prefaulted_pte #endif /* !__ASSEMBLY__ */