From 961a6ee5c7759afce06c27a83b36756d7b81a784 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 18 Mar 2024 16:03:58 -0400 Subject: mm/arm64: merge pXd_huge() and pXd_leaf() definitions Unlike most archs, aarch64 defines pXd_huge() and pXd_leaf() slightly differently. Redefine the pXd_huge() with pXd_leaf(). There used to be two traps for old aarch64 definitions over these APIs that I found when reading the code around, they're: (1) 4797ec2dc83a ("arm64: fix pud_huge() for 2-level pagetables") (2) 23bc8f69f0ec ("arm64: mm: fix p?d_leaf()") Define pXd_huge() with the current pXd_leaf() will make sure (2) isn't a problem (on PROT_NONE checks). To make sure it also works for (1), we move over the __PAGETABLE_PMD_FOLDED check to pud_leaf(), allowing it to constantly returning "false" for 2-level pgtables, which looks even safer to cover both now. Link: https://lkml.kernel.org/r/20240318200404.448346-9-peterx@redhat.com Signed-off-by: Peter Xu Cc: Muchun Song Cc: Mark Salter Cc: Catalin Marinas Cc: Will Deacon Cc: Alistair Popple Cc: Andreas Larsson Cc: "Aneesh Kumar K.V" Cc: Arnd Bergmann Cc: Bjorn Andersson Cc: Borislav Petkov Cc: Christophe Leroy Cc: Dave Hansen Cc: David S. Miller Cc: Fabio Estevam Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Konrad Dybcio Cc: Krzysztof Kozlowski Cc: Lucas Stach Cc: "Matthew Wilcox (Oracle)" Cc: Michael Ellerman Cc: Mike Rapoport (IBM) Cc: Naoya Horiguchi Cc: "Naveen N. Rao" Cc: Nicholas Piggin Cc: Russell King Cc: Shawn Guo Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/arm64/include/asm/pgtable.h') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index afdd56d26ad7..ec406e761e04 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -709,7 +709,11 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) +#ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) +#else +#define pud_leaf(pud) false +#endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) -- cgit v1.2.3 From 1965e933ddeba5e27e68ed80cfc7241931f70d4c Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 18 Mar 2024 16:04:01 -0400 Subject: mm/treewide: replace pXd_huge() with pXd_leaf() Now after we're sure all pXd_huge() definitions are the same as pXd_leaf(), reuse it. Luckily, pXd_huge() isn't widely used. Link: https://lkml.kernel.org/r/20240318200404.448346-12-peterx@redhat.com Signed-off-by: Peter Xu 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: Jason Gunthorpe 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 --- arch/arm64/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm64/include/asm/pgtable.h') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index ec406e761e04..a5c84f38c528 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -517,7 +517,7 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd) return pmd; } -#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) +#define pmd_thp_or_huge(pmd) (pmd_leaf(pmd) || pmd_trans_huge(pmd)) #define pmd_write(pmd) pte_write(pmd_pte(pmd)) -- cgit v1.2.3 From 502016e33ae6474177097bc43ee26bad8f4d6919 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 18 Mar 2024 16:04:03 -0400 Subject: mm/arm: remove pmd_thp_or_huge() ARM/ARM64 used to define pmd_thp_or_huge(). Now this macro is completely redundant. Remove it and use pmd_leaf(). Link: https://lkml.kernel.org/r/20240318200404.448346-14-peterx@redhat.com Signed-off-by: Peter Xu Cc: Mark Salter Cc: Catalin Marinas Cc: Will Deacon Cc: Russell King Cc: Shawn Guo Cc: Krzysztof Kozlowski Cc: Bjorn Andersson Cc: Arnd Bergmann Cc: Konrad Dybcio Cc: Fabio Estevam Cc: Alistair Popple Cc: Andreas Larsson Cc: "Aneesh Kumar K.V" Cc: Borislav Petkov Cc: Christophe Leroy Cc: Dave Hansen Cc: David S. Miller Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Lucas Stach 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: Thomas Gleixner Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/arm64/include/asm/pgtable.h') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index a5c84f38c528..6870b60158fc 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -517,8 +517,6 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd) return pmd; } -#define pmd_thp_or_huge(pmd) (pmd_leaf(pmd) || pmd_trans_huge(pmd)) - #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) -- 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 --- arch/arm64/include/asm/pgtable.h | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) (limited to 'arch/arm64/include/asm/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 */ -- cgit v1.2.3 From 89e86854fb0aa6e20c0f3d88285fa9cedef4f4e0 Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Thu, 18 Apr 2024 21:44:33 +0800 Subject: mm/arm64: override clear_young_dirty_ptes() batch helper The per-pte get_and_clear/modify/set approach would result in unfolding/refolding for contpte mappings on arm64. So we need to override clear_young_dirty_ptes() for arm64 to avoid it. Link: https://lkml.kernel.org/r/20240418134435.6092-3-ioworker0@gmail.com Signed-off-by: Lance Yang Suggested-by: Barry Song <21cnbao@gmail.com> Suggested-by: Ryan Roberts Reviewed-by: Ryan Roberts Cc: David Hildenbrand 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 --- arch/arm64/include/asm/pgtable.h | 55 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'arch/arm64/include/asm/pgtable.h') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 9fd8613b2db2..1303d30287dc 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1223,6 +1223,46 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, __ptep_set_wrprotect(mm, address, ptep); } +static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, cydp_t flags) +{ + pte_t old_pte; + + do { + old_pte = pte; + + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + + pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), + pte_val(old_pte), pte_val(pte)); + } while (pte_val(pte) != pte_val(old_pte)); +} + +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 (;;) { + pte = __ptep_get(ptep); + + if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) + __set_pte(ptep, pte_mkclean(pte_mkold(pte))); + else + __clear_young_dirty_pte(vma, addr, ptep, pte, flags); + + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, @@ -1379,6 +1419,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); +extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) @@ -1603,6 +1646,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } +#define clear_young_dirty_ptes clear_young_dirty_ptes +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); + else + contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); +} + #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get @@ -1622,6 +1676,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags +#define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ -- cgit v1.2.3