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 v1.2.3-59-g8ed1b 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 v1.2.3-59-g8ed1b 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 --- arch/arm64/include/asm/pgtable.h | 19 ++--------------- arch/arm64/mm/mteswap.c | 45 ++++++++++++++++++++++++++++++++++++++++ include/linux/huge_mm.h | 12 ----------- include/linux/pgtable.h | 2 +- mm/internal.h | 14 +++++++++++++ mm/memory.c | 2 +- mm/page_io.c | 2 +- mm/shmem.c | 2 +- mm/swap_slots.c | 2 +- mm/swapfile.c | 2 +- 10 files changed, 67 insertions(+), 35 deletions(-) (limited to 'include/linux/pgtable.h') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6870b60158fc..9fd8613b2db2 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -49,12 +49,6 @@ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline bool arch_thp_swp_supported(void) -{ - return !system_supports_mte(); -} -#define arch_thp_swp_supported arch_thp_swp_supported - /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page @@ -1282,12 +1276,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) -{ - if (system_supports_mte()) - return mte_save_tags(page); - return 0; -} +extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) @@ -1303,11 +1292,7 @@ static inline void arch_swap_invalidate_area(int type) } #define __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) -{ - if (system_supports_mte()) - mte_restore_tags(entry, &folio->page); -} +extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index a31833e3ddc5..63e8d72f202a 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -68,6 +68,13 @@ void mte_invalidate_tags(int type, pgoff_t offset) mte_free_tag_storage(tags); } +static inline void __mte_invalidate_tags(struct page *page) +{ + swp_entry_t entry = page_swap_entry(page); + + mte_invalidate_tags(swp_type(entry), swp_offset(entry)); +} + void mte_invalidate_tags_area(int type) { swp_entry_t entry = swp_entry(type, 0); @@ -83,3 +90,41 @@ void mte_invalidate_tags_area(int type) } xa_unlock(&mte_pages); } + +int arch_prepare_to_swap(struct folio *folio) +{ + long i, nr; + int err; + + if (!system_supports_mte()) + return 0; + + nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + err = mte_save_tags(folio_page(folio, i)); + if (err) + goto out; + } + return 0; + +out: + while (i--) + __mte_invalidate_tags(folio_page(folio, i)); + return err; +} + +void arch_swap_restore(swp_entry_t entry, struct folio *folio) +{ + long i, nr; + + if (!system_supports_mte()) + return; + + nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + mte_restore_tags(entry, folio_page(folio, i)); + entry.val++; + } +} diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 0e16451adaba..7576025db55d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -532,16 +532,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) #define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0) #define split_folio(f) split_folio_to_order(f, 0) -/* - * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to - * limitations in the implementation like arm64 MTE can override this to - * false - */ -#ifndef arch_thp_swp_supported -static inline bool arch_thp_swp_supported(void) -{ - return true; -} -#endif - #endif /* _LINUX_HUGE_MM_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; } diff --git a/mm/internal.h b/mm/internal.h index 63bdac6d0413..6c8d3844b6a3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -76,6 +76,20 @@ static inline int folio_nr_pages_mapped(struct folio *folio) return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } +/* + * Retrieve the first entry of a folio based on a provided entry within the + * folio. We cannot rely on folio->swap as there is no guarantee that it has + * been initialized. Used for calling arch_swap_restore() + */ +static inline swp_entry_t folio_swap(swp_entry_t entry, struct folio *folio) +{ + swp_entry_t swap = { + .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), + }; + + return swap; +} + static inline void *folio_raw_mapping(struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; diff --git a/mm/memory.c b/mm/memory.c index c859a09b4f72..805cebb6fd72 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4190,7 +4190,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ - arch_swap_restore(entry, folio); + arch_swap_restore(folio_swap(entry, folio), folio); /* * Remove the swap entry and conditionally try to free up the swapcache. diff --git a/mm/page_io.c b/mm/page_io.c index ae2b49055e43..a9a7c236aecc 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -189,7 +189,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) * Arch code may have to preserve more data than just the page * contents, e.g. memory tags. */ - ret = arch_prepare_to_swap(&folio->page); + ret = arch_prepare_to_swap(folio); if (ret) { folio_mark_dirty(folio); folio_unlock(folio); diff --git a/mm/shmem.c b/mm/shmem.c index 94ab99b6b574..98985179f495 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1907,7 +1907,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, * Some architectures may have to restore extra metadata to the * folio after reading from swap. */ - arch_swap_restore(swap, folio); + arch_swap_restore(folio_swap(swap, folio), folio); if (shmem_should_replace_folio(folio, gfp)) { error = shmem_replace_folio(&folio, gfp, info, index); diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 90973ce7881d..53abeaf1371d 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -310,7 +310,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio) entry.val = 0; if (folio_test_large(folio)) { - if (IS_ENABLED(CONFIG_THP_SWAP) && arch_thp_swp_supported()) + if (IS_ENABLED(CONFIG_THP_SWAP)) get_swap_pages(1, &entry, folio_nr_pages(folio)); goto out; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 4919423cce76..5e6d2304a2a4 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1806,7 +1806,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ - arch_swap_restore(entry, folio); + arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); -- cgit v1.2.3-59-g8ed1b 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 ++ mm/huge_memory.c | 6 +++--- mm/madvise.c | 2 +- mm/mempolicy.c | 2 +- mm/mlock.c | 2 +- mm/userfaultfd.c | 2 +- 6 files changed, 9 insertions(+), 7 deletions(-) (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] * diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5c043c7b5062..712263e3b1f6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1816,7 +1816,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, goto out; } - folio = pfn_folio(pmd_pfn(orig_pmd)); + folio = pmd_folio(orig_pmd); /* * If other processes are mapping this folio, we couldn't discard * the folio unless they all do MADV_FREE so let's skip the folio. @@ -2086,7 +2086,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (pmd_protnone(*pmd)) goto unlock; - folio = page_folio(pmd_page(*pmd)); + folio = pmd_folio(*pmd); toptier = node_is_toptier(folio_nid(folio)); /* * Skip scanning top tier node if normal numa @@ -2663,7 +2663,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * It's safe to call pmd_page when folio is set because it's * guaranteed that pmd is present. */ - if (folio && folio != page_folio(pmd_page(*pmd))) + if (folio && folio != pmd_folio(*pmd)) goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); } diff --git a/mm/madvise.c b/mm/madvise.c index 7625830d6ae9..1f77a51baaac 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -363,7 +363,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, goto huge_unlock; } - folio = pfn_folio(pmd_pfn(orig_pmd)); + folio = pmd_folio(orig_pmd); /* Do not interfere with other mappings of this folio */ if (folio_likely_mapped_shared(folio)) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 5743028a63a5..aec756ae5637 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -509,7 +509,7 @@ static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) qp->nr_failed++; return; } - folio = pfn_folio(pmd_pfn(*pmd)); + folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; diff --git a/mm/mlock.c b/mm/mlock.c index 1ed2f2ab37cd..30b51cdea89d 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -378,7 +378,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, goto out; if (is_huge_zero_pmd(*pmd)) goto out; - folio = page_folio(pmd_page(*pmd)); + folio = pmd_folio(*pmd); if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index a0ec14553fbe..b70618e8dcd2 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1662,7 +1662,7 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { - struct folio *folio = pfn_folio(pmd_pfn(*src_pmd)); + struct folio *folio = pmd_folio(*src_pmd); if (!folio || (!is_huge_zero_folio(folio) && !PageAnonExclusive(&folio->page))) { -- cgit v1.2.3-59-g8ed1b 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 --- arch/riscv/include/asm/pgtable.h | 1 + arch/s390/include/asm/pgtable.h | 1 + arch/sparc/include/asm/pgtable_64.h | 1 + arch/x86/include/asm/pgtable.h | 1 + include/linux/pgtable.h | 14 ++++++++++++++ 5 files changed, 18 insertions(+) (limited to 'include/linux/pgtable.h') diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 9f8ea0e33eb1..661b2b4fe758 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -648,6 +648,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd) #define __pud_to_phys(pud) (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT) +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 60950e7a25f5..2cb2a2e7b34b 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1405,6 +1405,7 @@ static inline unsigned long pud_deref(pud_t pud) return (unsigned long)__va(pud_val(pud) & origin_mask); } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { return __pa(pud_deref(pud)) >> PAGE_SHIFT; diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 4d1bafaba942..26efc9bb644a 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -875,6 +875,7 @@ static inline bool pud_leaf(pud_t pud) return pte_val(pte) & _PAGE_PMD_HUGE; } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { pte_t pte = __pte(pud_val(pud)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index cefc7a84f7a4..273f7557218c 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -234,6 +234,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); 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 v1.2.3-59-g8ed1b 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 --- arch/sparc/include/asm/pgtable_64.h | 2 +- include/linux/pgtable.h | 2 +- mm/mremap.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/pgtable.h') diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 26efc9bb644a..3fe429d73a65 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -957,7 +957,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, #ifdef DCACHE_ALIASING_POSSIBLE #define __HAVE_ARCH_MOVE_PTE -#define move_pte(pte, prot, old_addr, new_addr) \ +#define move_pte(pte, old_addr, new_addr) \ ({ \ pte_t newpte = (pte); \ if (tlb_type != hypervisor && pte_present(pte)) { \ 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 diff --git a/mm/mremap.c b/mm/mremap.c index 38d98465f3d8..f5aba752d35f 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -205,7 +205,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, */ if (pte_present(pte)) force_flush = true; - pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); + pte = move_pte(pte, old_addr, new_addr); pte = move_soft_dirty_pte(pte); set_pte_at(mm, new_addr, new_pte, pte); } -- cgit v1.2.3-59-g8ed1b 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 +++++++++++++++ include/linux/swap.h | 12 ++++-- mm/internal.h | 64 ++++++++++++++++++++++++++++++++ mm/madvise.c | 12 ++++-- mm/memory.c | 13 ++++--- mm/swapfile.c | 97 ++++++++++++++++++++++++++++++++++++++++--------- 6 files changed, 196 insertions(+), 31 deletions(-) (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, diff --git a/include/linux/swap.h b/include/linux/swap.h index a803de0ac24f..2d8f2b950ddf 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -468,7 +468,7 @@ extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); -extern int free_swap_and_cache(swp_entry_t); +extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); @@ -517,8 +517,9 @@ static inline void put_swap_device(struct swap_info_struct *si) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ -#define free_swap_and_cache(e) is_pfn_swap_entry(e) +static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) +{ +} static inline void free_swap_cache(struct folio *folio) { @@ -586,6 +587,11 @@ static inline int add_swap_extent(struct swap_info_struct *sis, } #endif /* CONFIG_SWAP */ +static inline void free_swap_and_cache(swp_entry_t entry) +{ + free_swap_and_cache_nr(entry, 1); +} + #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { diff --git a/mm/internal.h b/mm/internal.h index d567381b12cc..d34df04b11f6 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include struct folio_batch; @@ -189,6 +191,68 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, return min(ptep - start_ptep, max_nr); } + +/** + * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. + * @pte: The initial pte state; is_swap_pte(pte) must be true and + * non_swap_entry() must be false. + * + * Increments the swap offset, while maintaining all other fields, including + * swap type, and any swp pte bits. The resulting pte is returned. + */ +static inline pte_t pte_next_swp_offset(pte_t pte) +{ + swp_entry_t entry = pte_to_swp_entry(pte); + pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), + (swp_offset(entry) + 1))); + + if (pte_swp_soft_dirty(pte)) + new = pte_swp_mksoft_dirty(new); + if (pte_swp_exclusive(pte)) + new = pte_swp_mkexclusive(new); + if (pte_swp_uffd_wp(pte)) + new = pte_swp_mkuffd_wp(new); + + return new; +} + +/** + * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries + * @start_ptep: Page table pointer for the first entry. + * @max_nr: The maximum number of table entries to consider. + * @pte: Page table entry for the first entry. + * + * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs + * containing swap entries all with consecutive offsets and targeting the same + * swap type, all with matching swp pte bits. + * + * max_nr must be at least one and must be limited by the caller so scanning + * cannot exceed a single page table. + * + * Return: the number of table entries in the batch. + */ +static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) +{ + pte_t expected_pte = pte_next_swp_offset(pte); + const pte_t *end_ptep = start_ptep + max_nr; + pte_t *ptep = start_ptep + 1; + + VM_WARN_ON(max_nr < 1); + VM_WARN_ON(!is_swap_pte(pte)); + VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte))); + + while (ptep < end_ptep) { + pte = ptep_get(ptep); + + if (!pte_same(pte, expected_pte)) + break; + + expected_pte = pte_next_swp_offset(expected_pte); + ptep++; + } + + return ptep - start_ptep; +} #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, diff --git a/mm/madvise.c b/mm/madvise.c index 1f77a51baaac..5011ecb24344 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -628,6 +628,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; int nr_swap = 0; unsigned long next; + int nr, max_nr; next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) @@ -640,7 +641,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); - for (; addr != end; pte++, addr += PAGE_SIZE) { + for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) { + nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) @@ -655,9 +657,11 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, entry = pte_to_swp_entry(ptent); if (!non_swap_entry(entry)) { - nr_swap--; - free_swap_and_cache(entry); - pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + max_nr = (end - addr) / PAGE_SIZE; + nr = swap_pte_batch(pte, max_nr, ptent); + nr_swap -= nr; + free_swap_and_cache_nr(entry, nr); + clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); diff --git a/mm/memory.c b/mm/memory.c index 694e18837cd8..7880400370c8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1637,12 +1637,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, folio_remove_rmap_pte(folio, page, vma); folio_put(folio); } else if (!non_swap_entry(entry)) { - /* Genuine swap entry, hence a private anon page */ + max_nr = (end - addr) / PAGE_SIZE; + nr = swap_pte_batch(pte, max_nr, ptent); + /* Genuine swap entries, hence a private anon pages */ if (!should_zap_cows(details)) continue; - rss[MM_SWAPENTS]--; - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); + rss[MM_SWAPENTS] -= nr; + free_swap_and_cache_nr(entry, nr); } else if (is_migration_entry(entry)) { folio = pfn_swap_entry_folio(entry); if (!should_zap_folio(details, folio)) @@ -1665,8 +1666,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pr_alert("unrecognized swap entry 0x%lx\n", entry.val); WARN_ON_ONCE(1); } - pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); - zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent); + clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); + zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); add_mm_rss_vec(mm, rss); diff --git a/mm/swapfile.c b/mm/swapfile.c index 1ded6d1dcab4..20c45757f2b2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -130,7 +130,11 @@ static inline unsigned char swap_count(unsigned char ent) /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 -/* returns 1 if swap entry is freed */ +/* + * returns number of pages in the folio that backs the swap entry. If positive, + * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no + * folio was associated with the swap entry. + */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { @@ -155,6 +159,7 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, ret = folio_free_swap(folio); folio_unlock(folio); } + ret = ret ? folio_nr_pages(folio) : -folio_nr_pages(folio); folio_put(folio); return ret; } @@ -895,7 +900,7 @@ checks: swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ - if (swap_was_freed) + if (swap_was_freed > 0) goto checks; goto scan; /* check next one */ } @@ -1572,32 +1577,88 @@ bool folio_free_swap(struct folio *folio) return true; } -/* - * Free the swap entry like above, but also try to - * free the page cache entry if it is the last user. +/** + * free_swap_and_cache_nr() - Release reference on range of swap entries and + * reclaim their cache if no more references remain. + * @entry: First entry of range. + * @nr: Number of entries in range. + * + * For each swap entry in the contiguous range, release a reference. If any swap + * entries become free, try to reclaim their underlying folios, if present. The + * offset range is defined by [entry.offset, entry.offset + nr). */ -int free_swap_and_cache(swp_entry_t entry) +void free_swap_and_cache_nr(swp_entry_t entry, int nr) { - struct swap_info_struct *p; + const unsigned long start_offset = swp_offset(entry); + const unsigned long end_offset = start_offset + nr; + unsigned int type = swp_type(entry); + struct swap_info_struct *si; + bool any_only_cache = false; + unsigned long offset; unsigned char count; if (non_swap_entry(entry)) - return 1; + return; - p = get_swap_device(entry); - if (p) { - if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { - put_swap_device(p); - return 0; + si = get_swap_device(entry); + if (!si) + return; + + if (WARN_ON(end_offset > si->max)) + goto out; + + /* + * First free all entries in the range. + */ + for (offset = start_offset; offset < end_offset; offset++) { + if (data_race(si->swap_map[offset])) { + count = __swap_entry_free(si, swp_entry(type, offset)); + if (count == SWAP_HAS_CACHE) + any_only_cache = true; + } else { + WARN_ON_ONCE(1); } + } + + /* + * Short-circuit the below loop if none of the entries had their + * reference drop to zero. + */ + if (!any_only_cache) + goto out; - count = __swap_entry_free(p, entry); - if (count == SWAP_HAS_CACHE) - __try_to_reclaim_swap(p, swp_offset(entry), + /* + * Now go back over the range trying to reclaim the swap cache. This is + * more efficient for large folios because we will only try to reclaim + * the swap once per folio in the common case. If we do + * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the + * latter will get a reference and lock the folio for every individual + * page but will only succeed once the swap slot for every subpage is + * zero. + */ + for (offset = start_offset; offset < end_offset; offset += nr) { + nr = 1; + if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { + /* + * Folios are always naturally aligned in swap so + * advance forward to the next boundary. Zero means no + * folio was found for the swap entry, so advance by 1 + * in this case. Negative value means folio was found + * but could not be reclaimed. Here we can still advance + * to the next boundary. + */ + nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); - put_swap_device(p); + if (nr == 0) + nr = 1; + else if (nr < 0) + nr = -nr; + nr = ALIGN(offset + 1, nr) - offset; + } } - return p != NULL; + +out: + put_swap_device(si); } #ifdef CONFIG_HIBERNATION -- cgit v1.2.3-59-g8ed1b 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 +++++++++++++++++ mm/internal.h | 12 +++++-- mm/madvise.c | 87 ++++++++++++++++++++++++++++--------------------- mm/memory.c | 4 +-- 4 files changed, 92 insertions(+), 41 deletions(-) (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, diff --git a/mm/internal.h b/mm/internal.h index d34df04b11f6..640298a98a3c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -130,6 +130,8 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. + * @any_young: Optional pointer to indicate whether any entry except the + * first one is young. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. @@ -145,16 +147,18 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, - bool *any_writable) + bool *any_writable, bool *any_young) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; - bool writable; + bool writable, young; int nr; if (any_writable) *any_writable = false; + if (any_young) + *any_young = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); @@ -168,6 +172,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); + if (any_young) + young = !!pte_young(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) @@ -183,6 +189,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (any_writable) *any_writable |= writable; + if (any_young) + *any_young |= young; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); diff --git a/mm/madvise.c b/mm/madvise.c index 5011ecb24344..f59169888b8e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -336,6 +336,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; + int nr; if (fatal_signal_pending(current)) return -EINTR; @@ -423,7 +424,8 @@ restart: return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); - for (; addr < end; pte++, addr += PAGE_SIZE) { + for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { + nr = 1; ptent = ptep_get(pte); if (++batch_count == SWAP_CLUSTER_MAX) { @@ -447,55 +449,66 @@ restart: continue; /* - * Creating a THP page is expensive so split it only if we - * are sure it's worth. Split it if we are only owner. + * If we encounter a large folio, only split it if it is not + * fully mapped within the range we are operating on. Otherwise + * leave it as is so that it can be swapped out whole. If we + * fail to split a folio, leave it in place and advance to the + * next pte in the range. */ if (folio_test_large(folio)) { - int err; - - if (folio_likely_mapped_shared(folio)) - break; - if (pageout_anon_only_filter && !folio_test_anon(folio)) - break; - if (!folio_trylock(folio)) - break; - folio_get(folio); - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(start_pte, ptl); - start_pte = NULL; - err = split_folio(folio); - folio_unlock(folio); - folio_put(folio); - if (err) - break; - start_pte = pte = - pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!start_pte) - break; - arch_enter_lazy_mmu_mode(); - pte--; - addr -= PAGE_SIZE; - continue; + const fpb_t fpb_flags = FPB_IGNORE_DIRTY | + FPB_IGNORE_SOFT_DIRTY; + int max_nr = (end - addr) / PAGE_SIZE; + bool any_young; + + nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, + fpb_flags, NULL, &any_young); + if (any_young) + ptent = pte_mkyoung(ptent); + + if (nr < folio_nr_pages(folio)) { + int err; + + if (folio_likely_mapped_shared(folio)) + continue; + if (pageout_anon_only_filter && !folio_test_anon(folio)) + continue; + if (!folio_trylock(folio)) + continue; + folio_get(folio); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(start_pte, ptl); + start_pte = NULL; + err = split_folio(folio); + folio_unlock(folio); + folio_put(folio); + start_pte = pte = + pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!start_pte) + break; + arch_enter_lazy_mmu_mode(); + if (!err) + nr = 0; + continue; + } } /* * Do not interfere with other mappings of this folio and - * non-LRU folio. + * non-LRU folio. If we have a large folio at this point, we + * know it is fully mapped so if its mapcount is the same as its + * number of pages, it must be exclusive. */ - if (!folio_test_lru(folio) || folio_mapcount(folio) != 1) + if (!folio_test_lru(folio) || + folio_mapcount(folio) != folio_nr_pages(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; - VM_BUG_ON_FOLIO(folio_test_large(folio), folio); - if (!pageout && pte_young(ptent)) { - ptent = ptep_get_and_clear_full(mm, addr, pte, - tlb->fullmm); - ptent = pte_mkold(ptent); - set_pte_at(mm, addr, pte, ptent); - tlb_remove_tlb_entry(tlb, pte, addr); + mkold_ptes(vma, addr, pte, nr); + tlb_remove_tlb_entries(tlb, pte, nr, addr); } /* diff --git a/mm/memory.c b/mm/memory.c index 7880400370c8..59c05dc8b18a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -989,7 +989,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma flags |= FPB_IGNORE_SOFT_DIRTY; nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags, - &any_writable); + &any_writable, NULL); folio_ref_add(folio, nr); if (folio_test_anon(folio)) { if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, @@ -1559,7 +1559,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, */ if (unlikely(folio_test_large(folio) && max_nr != 1)) { nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags, - NULL); + NULL, NULL); zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush, -- cgit v1.2.3-59-g8ed1b 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/mm_types.h | 9 ++++++ include/linux/pgtable.h | 74 ++++++++++++++++++++++++++++-------------------- mm/madvise.c | 3 +- 3 files changed, 55 insertions(+), 31 deletions(-) (limited to 'include/linux/pgtable.h') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index db0adf5721cc..24323c7d0bd4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1368,6 +1368,15 @@ enum fault_flag { typedef unsigned int __bitwise zap_flags_t; +/* Flags for clear_young_dirty_ptes(). */ +typedef int __bitwise cydp_t; + +/* Clear the access bit */ +#define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0)) + +/* Clear the dirty bit */ +#define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1)) + /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: 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) { diff --git a/mm/madvise.c b/mm/madvise.c index f59169888b8e..edb592adb749 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -507,7 +507,8 @@ restart: continue; if (!pageout && pte_young(ptent)) { - mkold_ptes(vma, addr, pte, nr); + clear_young_dirty_ptes(vma, addr, pte, nr, + CYDP_CLEAR_YOUNG); tlb_remove_tlb_entries(tlb, pte, nr, addr); } -- cgit v1.2.3-59-g8ed1b