/* SPDX-License-Identifier: GPL-2.0-or-later *//* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */#ifndef _ASM_GENERIC__TLB_H#define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h>#include <linux/swap.h>#include <linux/hugetlb_inline.h>#include <asm/tlbflush.h>#include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */#ifndef nmi_uaccess_okay# define nmi_uaccess_okay() true#endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / * tlb_finish_mmu() * * start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_free_vmas() * * tlb_free_vmas() marks the start of unlinking of one or more vmas * and freeing page-tables. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / tlb_remove_page_size() * - __tlb_remove_folio_pages() / __tlb_remove_page_size() * - __tlb_remove_folio_pages_size() * * __tlb_remove_folio_pages_size() is the basic primitive that queues pages * for freeing. It will return a boolean indicating if the queue is (now) * full and a call to tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * __tlb_remove_folio_pages() is similar to __tlb_remove_page_size(), * however, instead of removing a single page, assume PAGE_SIZE and remove * the given number of consecutive pages that are all part of the * same (large) folio. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() or * use the generic __tlb_remove_table(), which does the actual freeing of these * pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_FLUSH_CACHE * * Indicates the architecture has flush_cache_range() but it needs *NOT* be called * before unmapping a VMA. * * NOTE: strictly speaking we shouldn't have this knob and instead rely on * flush_cache_range() being a NOP, except Sparc64 seems to be * different here. * * MMU_GATHER_MERGE_VMAS * * Indicates the architecture wants to merge ranges over VMAs; typical when * multiple range invalidates are more expensive than a full invalidate. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). This * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch {#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu;#endif unsigned int nr; void *tables[];}; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) #ifndef CONFIG_HAVE_ARCH_TLB_REMOVE_TABLEstatic inline void __tlb_remove_table(void *table){ struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor_free(ptdesc);}#endif extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page);/* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */static inline void tlb_remove_table(struct mmu_gather *tlb, void *table){ struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor(ptdesc); tlb_remove_page(tlb, ptdesc_page(ptdesc));}#endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE/* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */#ifndef tlb_needs_table_invalidate#define tlb_needs_table_invalidate() (true)#endif void tlb_remove_table_sync_one(void); void tlb_remove_table_sync_rcu(void); #else #ifdef tlb_needs_table_invalidate#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE#endif static inline void tlb_remove_table_sync_one(void) { } static inline void tlb_remove_table_sync_rcu(void) { } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER/* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */#define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct encoded_page *encoded_pages[];}; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */#define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size);bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap); #ifdef CONFIG_SMP/* * This both sets 'delayed_rmap', and returns true. It would be an inline * function, except we define it before the 'struct mmu_gather'. */#define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true)extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma);#endif #endif /* * We have a no-op version of the rmap removal that doesn't * delay anything. That is used on S390, which flushes remote * TLBs synchronously, and on UP, which doesn't have any * remote TLBs to flush and is not preemptible due to this * all happening under the page table lock. */#ifndef tlb_delay_rmap#define tlb_delay_rmap(tlb) (false)static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { }#endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch;#endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * Do we have pending delayed rmap removals? */ unsigned int delayed_rmap : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int vma_pfn : 1; /* * Did we unshare (unmap) any shared page tables? For now only * used for hugetlb PMD table sharing. */ unsigned int unshared_tables : 1; /* * Did we unshare any page tables such that they are now exclusive * and could get reused+modified by the new owner? When setting this * flag, "unshared_tables" will be set as well. For now only used * for hugetlb PMD table sharing. */ unsigned int fully_unshared_tables : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size;#endif#endif}; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size){ tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size);} static inline void __tlb_reset_range(struct mmu_gather *tlb){ if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */} #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush)#error MMU_GATHER_NO_RANGE relies on default tlb_flush()#endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */static inline void tlb_flush(struct mmu_gather *tlb){ if (tlb->end) flush_tlb_mm(tlb->mm);} #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush/* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */static inline void tlb_flush(struct mmu_gather *tlb){ if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); }}#endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline voidtlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma){ /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); /* * Track if there's at least one VM_PFNMAP/VM_MIXEDMAP vma * in the tracked range, see tlb_free_vmas(). */ tlb->vma_pfn |= !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP));} static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb){Lines 1–500 of 854. Load more
/* SPDX-License-Identifier: GPL-2.0-or-later */ /* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */ #ifndef _ASM_GENERIC__TLB_H #define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/hugetlb_inline.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */ #ifndef nmi_uaccess_okay # define nmi_uaccess_okay() true #endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / * tlb_finish_mmu() * * start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_free_vmas() * * tlb_free_vmas() marks the start of unlinking of one or more vmas * and freeing page-tables. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / tlb_remove_page_size() * - __tlb_remove_folio_pages() / __tlb_remove_page_size() * - __tlb_remove_folio_pages_size() * * __tlb_remove_folio_pages_size() is the basic primitive that queues pages * for freeing. It will return a boolean indicating if the queue is (now) * full and a call to tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * __tlb_remove_folio_pages() is similar to __tlb_remove_page_size(), * however, instead of removing a single page, assume PAGE_SIZE and remove * the given number of consecutive pages that are all part of the * same (large) folio. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() or * use the generic __tlb_remove_table(), which does the actual freeing of these * pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_FLUSH_CACHE * * Indicates the architecture has flush_cache_range() but it needs *NOT* be called * before unmapping a VMA. * * NOTE: strictly speaking we shouldn't have this knob and instead rely on * flush_cache_range() being a NOP, except Sparc64 seems to be * different here. * * MMU_GATHER_MERGE_VMAS * * Indicates the architecture wants to merge ranges over VMAs; typical when * multiple range invalidates are more expensive than a full invalidate. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). This * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch { #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; #endif unsigned int nr; void *tables[]; }; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) #ifndef CONFIG_HAVE_ARCH_TLB_REMOVE_TABLE static inline void __tlb_remove_table(void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor_free(ptdesc); } #endif extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor(ptdesc); tlb_remove_page(tlb, ptdesc_page(ptdesc)); } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */ #ifndef tlb_needs_table_invalidate #define tlb_needs_table_invalidate() (true) #endif void tlb_remove_table_sync_one(void); void tlb_remove_table_sync_rcu(void); #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif static inline void tlb_remove_table_sync_one(void) { } static inline void tlb_remove_table_sync_rcu(void) { } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */ #define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct encoded_page *encoded_pages[]; }; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap); #ifdef CONFIG_SMP /* * This both sets 'delayed_rmap', and returns true. It would be an inline * function, except we define it before the 'struct mmu_gather'. */ #define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true) extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma); #endif #endif /* * We have a no-op version of the rmap removal that doesn't * delay anything. That is used on S390, which flushes remote * TLBs synchronously, and on UP, which doesn't have any * remote TLBs to flush and is not preemptible due to this * all happening under the page table lock. */ #ifndef tlb_delay_rmap #define tlb_delay_rmap(tlb) (false) static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * Do we have pending delayed rmap removals? */ unsigned int delayed_rmap : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int vma_pfn : 1; /* * Did we unshare (unmap) any shared page tables? For now only * used for hugetlb PMD table sharing. */ unsigned int unshared_tables : 1; /* * Did we unshare any page tables such that they are now exclusive * and could get reused+modified by the new owner? When setting this * flag, "unshared_tables" will be set as well. For now only used * for hugetlb PMD table sharing. */ unsigned int fully_unshared_tables : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size); } static inline void __tlb_reset_range(struct mmu_gather *tlb) { if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */ } #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush) #error MMU_GATHER_NO_RANGE relies on default tlb_flush() #endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->end) flush_tlb_mm(tlb->mm); } #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); } } #endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); /* * Track if there's at least one VM_PFNMAP/VM_MIXEDMAP vma * in the tracked range, see tlb_free_vmas(). */ tlb->vma_pfn |= !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)); } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) {