From 5b0a67008b0d608bb7585fe4c3c0c09d5ceaf1c9 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 16 Mar 2024 12:52:41 +0100 Subject: mm: remove guard around pgd_offset_k() macro The last architecture redefining pgd_offset_k() was IA64 and it was removed by commit cf8e8658100d ("arch: Remove Itanium (IA-64) architecture") There is no need anymore to guard generic version of pgd_offset_k() with #ifndef pgd_offset_k Link: https://lkml.kernel.org/r/59d3f47d5615d18cca1986f269be2fcb3df34556.1710589838.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 85fc7554cd52..bd9c7180718c 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -149,9 +149,7 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ -#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) -#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE -- cgit v1.2.3 From 64078b3d57dd9aaa4dde4a4f5851a53a79ac4d42 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 18 Mar 2024 16:04:04 -0400 Subject: mm: document pXd_leaf() API There's one small section already, but since we're going to remove pXd_huge(), that comment may start to obsolete. Rewrite that section with more information, hopefully with that the API is crystal clear on what it implies. Link: https://lkml.kernel.org/r/20240318200404.448346-15-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe Cc: Alistair Popple Cc: Andreas Larsson Cc: "Aneesh Kumar K.V" Cc: Arnd Bergmann Cc: Bjorn Andersson Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: David S. Miller Cc: Fabio Estevam Cc: Ingo Molnar Cc: Konrad Dybcio Cc: Krzysztof Kozlowski Cc: Lucas Stach Cc: Mark Salter Cc: "Matthew Wilcox (Oracle)" Cc: Michael Ellerman Cc: Mike Rapoport (IBM) Cc: Muchun Song Cc: Naoya Horiguchi Cc: "Naveen N. Rao" Cc: Nicholas Piggin Cc: Russell King Cc: Shawn Guo Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index bd9c7180718c..2a1c044ae467 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1768,11 +1768,25 @@ typedef unsigned int pgtbl_mod_mask; #endif /* - * p?d_leaf() - true if this entry is a final mapping to a physical address. - * This differs from p?d_huge() by the fact that they are always available (if - * the architecture supports large pages at the appropriate level) even - * if CONFIG_HUGETLB_PAGE is not defined. - * Only meaningful when called on a valid entry. + * pXd_leaf() is the API to check whether a pgtable entry is a huge page + * mapping. It should work globally across all archs, without any + * dependency on CONFIG_* options. For architectures that do not support + * huge mappings on specific levels, below fallbacks will be used. + * + * A leaf pgtable entry should always imply the following: + * + * - It is a "present" entry. IOW, before using this API, please check it + * with pXd_present() first. NOTE: it may not always mean the "present + * bit" is set. For example, PROT_NONE entries are always "present". + * + * - It should _never_ be a swap entry of any type. Above "present" check + * should have guarded this, but let's be crystal clear on this. + * + * - It should contain a huge PFN, which points to a huge page larger than + * PAGE_SIZE of the platform. The PFN format isn't important here. + * + * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(), + * pXd_devmap(), or hugetlb mappings). */ #ifndef pgd_leaf #define pgd_leaf(x) false -- cgit v1.2.3 From f238b8c33c6738f146bbfbb09b78870ea157c2b7 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sat, 23 Mar 2024 00:41:36 +1300 Subject: arm64: mm: swap: support THP_SWAP on hardware with MTE Commit d0637c505f8a1 ("arm64: enable THP_SWAP for arm64") brings up THP_SWAP on ARM64, but it doesn't enable THP_SWP on hardware with MTE as the MTE code works with the assumption tags save/restore is always handling a folio with only one page. The limitation should be removed as more and more ARM64 SoCs have this feature. Co-existence of MTE and THP_SWAP becomes more and more important. This patch makes MTE tags saving support large folios, then we don't need to split large folios into base pages for swapping out on ARM64 SoCs with MTE any more. arch_prepare_to_swap() should take folio rather than page as parameter because we support THP swap-out as a whole. It saves tags for all pages in a large folio. As now we are restoring tags based-on folio, in arch_swap_restore(), we may increase some extra loops and early-exitings while refaulting a large folio which is still in swapcache in do_swap_page(). In case a large folio has nr pages, do_swap_page() will only set the PTE of the particular page which is causing the page fault. Thus do_swap_page() runs nr times, and each time, arch_swap_restore() will loop nr times for those subpages in the folio. So right now the algorithmic complexity becomes O(nr^2). Once we support mapping large folios in do_swap_page(), extra loops and early-exitings will decrease while not being completely removed as a large folio might get partially tagged in corner cases such as, 1. a large folio in swapcache can be partially unmapped, thus, MTE tags for the unmapped pages will be invalidated; 2. users might use mprotect() to set MTEs on a part of a large folio. arch_thp_swp_supported() is dropped since ARM64 MTE was the only one who needed it. Link: https://lkml.kernel.org/r/20240322114136.61386-2-21cnbao@gmail.com Signed-off-by: Barry Song Reviewed-by: Steven Price Acked-by: Chris Li Reviewed-by: Ryan Roberts Cc: Catalin Marinas Cc: Will Deacon Cc: Mark Rutland Cc: David Hildenbrand Cc: Kemeng Shi Cc: "Matthew Wilcox (Oracle)" Cc: Anshuman Khandual Cc: Peter Collingbourne Cc: Yosry Ahmed Cc: Peter Xu Cc: Lorenzo Stoakes Cc: "Mike Rapoport (IBM)" Cc: Hugh Dickins Cc: "Aneesh Kumar K.V" Cc: Rick Edgecombe Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 2a1c044ae467..600e17d03659 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1050,7 +1050,7 @@ static inline int arch_unmap_one(struct mm_struct *mm, * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) +static inline int arch_prepare_to_swap(struct folio *folio) { return 0; } -- cgit v1.2.3 From e06d03d5590ae1c257b8aa2cfbfe6765e0755c14 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 26 Mar 2024 20:28:23 +0000 Subject: mm: add pmd_folio() Convert directly from a pmd to a folio without going through another representation first. For now this is just a slightly shorter way to write it, but it might end up being more efficient later. Link: https://lkml.kernel.org/r/20240326202833.523759-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 600e17d03659..09c85c7bf9c2 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -50,6 +50,8 @@ #define pmd_pgtable(pmd) pmd_page(pmd) #endif +#define pmd_folio(pmd) page_folio(pmd_page(pmd)) + /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * -- cgit v1.2.3 From 35a76f5c0863fc6b570bf02ab6dbf4cd65d1e001 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 27 Mar 2024 11:23:24 -0400 Subject: mm/arch: provide pud_pfn() fallback The comment in the code explains the reasons. We took a different approach comparing to pmd_pfn() by providing a fallback function. Another option is to provide some lower level config options (compare to HUGETLB_PAGE or THP) to identify which layer an arch can support for such huge mappings. However that can be an overkill. [peterx@redhat.com: fix loongson defconfig] Link: https://lkml.kernel.org/r/20240403013249.1418299-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20240327152332.950956-6-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe Tested-by: Ryan Roberts Cc: Mike Rapoport (IBM) Cc: Matthew Wilcox Cc: Andrea Arcangeli Cc: Andrew Jones Cc: Aneesh Kumar K.V (IBM) Cc: Axel Rasmussen Cc: Christophe Leroy Cc: Christoph Hellwig Cc: David Hildenbrand Cc: James Houghton Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Lorenzo Stoakes Cc: Michael Ellerman Cc: Muchun Song Cc: Rik van Riel Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 09c85c7bf9c2..f108c7a3c1d9 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1819,6 +1819,20 @@ typedef unsigned int pgtbl_mod_mask; #define pte_leaf_size(x) PAGE_SIZE #endif +/* + * We always define pmd_pfn for all archs as it's used in lots of generic + * code. Now it happens too for pud_pfn (and can happen for larger + * mappings too in the future; we're not there yet). Instead of defining + * it for all archs (like pmd_pfn), provide a fallback. + * + * Note that returning 0 here means any arch that didn't define this can + * get severely wrong when it hits a real pud leaf. It's arch's + * responsibility to properly define it when a huge pud is possible. + */ +#ifndef pud_pfn +#define pud_pfn(x) 0 +#endif + /* * Some architectures have MMUs that are configurable or selectable at boot * time. These lead to variable PTRS_PER_x. For statically allocated arrays it -- cgit v1.2.3 From 82a616d0f33b77b1cadd0652efbe11874771320f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 27 Mar 2024 15:33:01 +0100 Subject: mm: remove "prot" parameter from move_pte() The "prot" parameter is unused, and using it instead of what's stored in that particular PTE would very likely be wrong. Let's simply remove it. Link: https://lkml.kernel.org/r/20240327143301.741807-1-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Vishal Moola (Oracle) Cc: "David S. Miller" Cc: Andreas Larsson Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f108c7a3c1d9..a3fc8150b047 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1079,7 +1079,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef __HAVE_ARCH_MOVE_PTE -#define move_pte(pte, prot, old_addr, new_addr) (pte) +#define move_pte(pte, old_addr, new_addr) (pte) #endif #ifndef pte_accessible -- cgit v1.2.3 From a62fb92ac12ed39df4930dca599a3b427552882a Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Mon, 8 Apr 2024 19:39:41 +0100 Subject: mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache() Now that we no longer have a convenient flag in the cluster to determine if a folio is large, free_swap_and_cache() will take a reference and lock a large folio much more often, which could lead to contention and (e.g.) failure to split large folios, etc. Let's solve that problem by batch freeing swap and cache with a new function, free_swap_and_cache_nr(), to free a contiguous range of swap entries together. This allows us to first drop a reference to each swap slot before we try to release the cache folio. This means we only try to release the folio once, only taking the reference and lock once - much better than the previous 512 times for the 2M THP case. Contiguous swap entries are gathered in zap_pte_range() and madvise_free_pte_range() in a similar way to how present ptes are already gathered in zap_pte_range(). While we are at it, let's simplify by converting the return type of both functions to void. The return value was used only by zap_pte_range() to print a bad pte, and was ignored by everyone else, so the extra reporting wasn't exactly guaranteed. We will still get the warning with most of the information from get_swap_device(). With the batch version, we wouldn't know which pte was bad anyway so could print the wrong one. [ryan.roberts@arm.com: fix a build warning on parisc] Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com Signed-off-by: Ryan Roberts Acked-by: David Hildenbrand Cc: Barry Song <21cnbao@gmail.com> Cc: Barry Song Cc: Chris Li Cc: Gao Xiang Cc: "Huang, Ying" Cc: Kefeng Wang Cc: Lance Yang Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Yang Shi Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a3fc8150b047..75096025fe52 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -708,6 +708,35 @@ static inline void pte_clear_not_present_full(struct mm_struct *mm, } #endif +#ifndef clear_not_present_full_ptes +/** + * clear_not_present_full_ptes - Clear multiple not present PTEs which are + * consecutive in the pgtable. + * @mm: Address space the ptes represent. + * @addr: Address of the first pte. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * @full: Whether we are clearing a full mm. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over pte_clear_not_present_full(). + * + * Context: The caller holds the page table lock. The PTEs are all not present. + * The PTEs are all in the same PMD. + */ +static inline void clear_not_present_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, unsigned int nr, int full) +{ + for (;;) { + pte_clear_not_present_full(mm, addr, ptep, full); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, -- cgit v1.2.3 From 3931b871c4936c00c4e27c469056d8da47a3493f Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Mon, 8 Apr 2024 19:39:46 +0100 Subject: mm: madvise: avoid split during MADV_PAGEOUT and MADV_COLD Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large folio that is fully and contiguously mapped in the pageout/cold vm range. This change means that large folios will be maintained all the way to swap storage. This both improves performance during swap-out, by eliding the cost of splitting the folio, and sets us up nicely for maintaining the large folio when it is swapped back in (to be covered in a separate series). Folios that are not fully mapped in the target range are still split, but note that behavior is changed so that if the split fails for any reason (folio locked, shared, etc) we now leave it as is and move to the next pte in the range and continue work on the proceeding folios. Previously any failure of this sort would cause the entire operation to give up and no folios mapped at higher addresses were paged out or made cold. Given large folios are becoming more common, this old behavior would have likely lead to wasted opportunities. While we are at it, change the code that clears young from the ptes to use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper function. This is more efficent than get_and_clear/modify/set, especially for contpte mappings on arm64, where the old approach would require unfolding/refolding and the new approach can be done in place. Link: https://lkml.kernel.org/r/20240408183946.2991168-8-ryan.roberts@arm.com Signed-off-by: Ryan Roberts Reviewed-by: Barry Song Acked-by: David Hildenbrand Cc: Barry Song <21cnbao@gmail.com> Cc: Chris Li Cc: Gao Xiang Cc: "Huang, Ying" Cc: Kefeng Wang Cc: Lance Yang Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Yang Shi Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 75096025fe52..e2f45e22a6d1 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -361,6 +361,36 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, } #endif +#ifndef mkold_ptes +/** + * mkold_ptes - Mark PTEs that map consecutive pages of the same folio as old. + * @vma: VMA the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to mark old. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over ptep_test_and_clear_young(). + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void mkold_ptes(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, unsigned int nr) +{ + for (;;) { + ptep_test_and_clear_young(vma, addr, ptep); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, -- cgit v1.2.3 From 1b68112c40395b3b0fed3c8bb648e2d9d0b37ec2 Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Thu, 18 Apr 2024 21:44:32 +0800 Subject: mm/madvise: introduce clear_young_dirty_ptes() batch helper Patch series "mm/madvise: enhance lazyfreeing with mTHP in madvise_free", v10. This patchset adds support for lazyfreeing multi-size THP (mTHP) without needing to first split the large folio via split_folio(). However, we still need to split a large folio that is not fully mapped within the target range. If a large folio is locked or shared, or if we fail to split it, we just leave it in place and advance to the next PTE in the range. But note that the behavior is changed; previously, any failure of this sort would cause the entire operation to give up. As large folios become more common, sticking to the old way could result in wasted opportunities. Performance Testing =================== On an Intel I5 CPU, lazyfreeing a 1GiB VMA backed by PTE-mapped folios of the same size results in the following runtimes for madvise(MADV_FREE) in seconds (shorter is better): Folio Size | Old | New | Change ------------------------------------------ 4KiB | 0.590251 | 0.590259 | 0% 16KiB | 2.990447 | 0.185655 | -94% 32KiB | 2.547831 | 0.104870 | -95% 64KiB | 2.457796 | 0.052812 | -97% 128KiB | 2.281034 | 0.032777 | -99% 256KiB | 2.230387 | 0.017496 | -99% 512KiB | 2.189106 | 0.010781 | -99% 1024KiB | 2.183949 | 0.007753 | -99% 2048KiB | 0.002799 | 0.002804 | 0% This patch (of 4): This commit introduces clear_young_dirty_ptes() to replace mkold_ptes(). By doing so, we can use the same function for both use cases (madvise_pageout and madvise_free), and it also provides the flexibility to only clear the dirty flag in the future if needed. Link: https://lkml.kernel.org/r/20240418134435.6092-1-ioworker0@gmail.com Link: https://lkml.kernel.org/r/20240418134435.6092-2-ioworker0@gmail.com Signed-off-by: Lance Yang Suggested-by: Ryan Roberts Acked-by: David Hildenbrand Reviewed-by: Ryan Roberts Cc: Barry Song <21cnbao@gmail.com> Cc: Jeff Xie Cc: Kefeng Wang Cc: Michal Hocko Cc: Minchan Kim Cc: Muchun Song Cc: Peter Xu Cc: Yang Shi Cc: Yin Fengwei Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 74 +++++++++++++++++++++++++++++-------------------- 1 file changed, 44 insertions(+), 30 deletions(-) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e2f45e22a6d1..18019f037bae 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -361,36 +361,6 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, } #endif -#ifndef mkold_ptes -/** - * mkold_ptes - Mark PTEs that map consecutive pages of the same folio as old. - * @vma: VMA the pages are mapped into. - * @addr: Address the first page is mapped at. - * @ptep: Page table pointer for the first entry. - * @nr: Number of entries to mark old. - * - * May be overridden by the architecture; otherwise, implemented as a simple - * loop over ptep_test_and_clear_young(). - * - * Note that PTE bits in the PTE range besides the PFN can differ. For example, - * some PTEs might be write-protected. - * - * Context: The caller holds the page table lock. The PTEs map consecutive - * pages that belong to the same folio. The PTEs are all in the same PMD. - */ -static inline void mkold_ptes(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep, unsigned int nr) -{ - for (;;) { - ptep_test_and_clear_young(vma, addr, ptep); - if (--nr == 0) - break; - ptep++; - addr += PAGE_SIZE; - } -} -#endif - #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, @@ -489,6 +459,50 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif +#ifndef clear_young_dirty_ptes +/** + * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the + * same folio as old/clean. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to mark old/clean. + * @flags: Flags to modify the PTE batch semantics. + * + * May be overridden by the architecture; otherwise, implemented by + * get_and_clear/modify/set for each pte in the range. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + if (flags == CYDP_CLEAR_YOUNG) + ptep_test_and_clear_young(vma, addr, ptep); + else { + pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + set_pte_at(vma->vm_mm, addr, ptep, pte); + } + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { -- cgit v1.2.3