diff options
Diffstat (limited to 'include/linux/pgtable.h')
| -rw-r--r-- | include/linux/pgtable.h | 376 |
1 files changed, 301 insertions, 75 deletions
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 652f287c1ef6..cdd68ed3ae1a 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -23,25 +23,6 @@ #endif /* - * On almost all architectures and configurations, 0 can be used as the - * upper ceiling to free_pgtables(): on many architectures it has the same - * effect as using TASK_SIZE. However, there is one configuration which - * must impose a more careful limit, to avoid freeing kernel pgtables. - */ -#ifndef USER_PGTABLES_CEILING -#define USER_PGTABLES_CEILING 0UL -#endif - -/* - * This defines the first usable user address. Platforms - * can override its value with custom FIRST_USER_ADDRESS - * defined in their respective <asm/pgtable.h>. - */ -#ifndef FIRST_USER_ADDRESS -#define FIRST_USER_ADDRESS 0UL -#endif - -/* * This defines the generic helper for accessing PMD page * table page. Although platforms can still override this * via their respective <asm/pgtable.h>. @@ -225,16 +206,156 @@ static inline int pmd_dirty(pmd_t pmd) * up to date. * * In the general case, no lock is guaranteed to be held between entry and exit - * of the lazy mode. So the implementation must assume preemption may be enabled - * and cpu migration is possible; it must take steps to be robust against this. - * (In practice, for user PTE updates, the appropriate page table lock(s) are - * held, but for kernel PTE updates, no lock is held). Nesting is not permitted - * and the mode cannot be used in interrupt context. + * of the lazy mode. (In practice, for user PTE updates, the appropriate page + * table lock(s) are held, but for kernel PTE updates, no lock is held). + * The implementation must therefore assume preemption may be enabled upon + * entry to the mode and cpu migration is possible; it must take steps to be + * robust against this. An implementation may handle this by disabling + * preemption, as a consequence generic code may not sleep while the lazy MMU + * mode is active. + * + * The mode is disabled in interrupt context and calls to the lazy_mmu API have + * no effect. + * + * The lazy MMU mode is enabled for a given block of code using: + * + * lazy_mmu_mode_enable(); + * <code> + * lazy_mmu_mode_disable(); + * + * Nesting is permitted: <code> may itself use an enable()/disable() pair. + * A nested call to enable() has no functional effect; however disable() causes + * any batched architectural state to be flushed regardless of nesting. After a + * call to disable(), the caller can therefore rely on all previous page table + * modifications to have taken effect, but the lazy MMU mode may still be + * enabled. + * + * In certain cases, it may be desirable to temporarily pause the lazy MMU mode. + * This can be done using: + * + * lazy_mmu_mode_pause(); + * <code> + * lazy_mmu_mode_resume(); + * + * pause() ensures that the mode is exited regardless of the nesting level; + * resume() re-enters the mode at the same nesting level. Any call to the + * lazy_mmu_mode_* API between those two calls has no effect. In particular, + * this means that pause()/resume() pairs may nest. + * + * is_lazy_mmu_mode_active() can be used to check whether the lazy MMU mode is + * currently enabled. + */ +#ifdef CONFIG_ARCH_HAS_LAZY_MMU_MODE +/** + * lazy_mmu_mode_enable() - Enable the lazy MMU mode. + * + * Enters a new lazy MMU mode section; if the mode was not already enabled, + * enables it and calls arch_enter_lazy_mmu_mode(). + * + * Must be paired with a call to lazy_mmu_mode_disable(). + * + * Has no effect if called: + * - While paused - see lazy_mmu_mode_pause() + * - In interrupt context + */ +static inline void lazy_mmu_mode_enable(void) +{ + struct lazy_mmu_state *state = ¤t->lazy_mmu_state; + + if (in_interrupt() || state->pause_count > 0) + return; + + VM_WARN_ON_ONCE(state->enable_count == U8_MAX); + + if (state->enable_count++ == 0) + arch_enter_lazy_mmu_mode(); +} + +/** + * lazy_mmu_mode_disable() - Disable the lazy MMU mode. + * + * Exits the current lazy MMU mode section. If it is the outermost section, + * disables the mode and calls arch_leave_lazy_mmu_mode(). Otherwise (nested + * section), calls arch_flush_lazy_mmu_mode(). + * + * Must match a call to lazy_mmu_mode_enable(). + * + * Has no effect if called: + * - While paused - see lazy_mmu_mode_pause() + * - In interrupt context + */ +static inline void lazy_mmu_mode_disable(void) +{ + struct lazy_mmu_state *state = ¤t->lazy_mmu_state; + + if (in_interrupt() || state->pause_count > 0) + return; + + VM_WARN_ON_ONCE(state->enable_count == 0); + + if (--state->enable_count == 0) + arch_leave_lazy_mmu_mode(); + else /* Exiting a nested section */ + arch_flush_lazy_mmu_mode(); + +} + +/** + * lazy_mmu_mode_pause() - Pause the lazy MMU mode. + * + * Pauses the lazy MMU mode; if it is currently active, disables it and calls + * arch_leave_lazy_mmu_mode(). + * + * Must be paired with a call to lazy_mmu_mode_resume(). Calls to the + * lazy_mmu_mode_* API have no effect until the matching resume() call. + * + * Has no effect if called: + * - While paused (inside another pause()/resume() pair) + * - In interrupt context */ -#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE -static inline void arch_enter_lazy_mmu_mode(void) {} -static inline void arch_leave_lazy_mmu_mode(void) {} -static inline void arch_flush_lazy_mmu_mode(void) {} +static inline void lazy_mmu_mode_pause(void) +{ + struct lazy_mmu_state *state = ¤t->lazy_mmu_state; + + if (in_interrupt()) + return; + + VM_WARN_ON_ONCE(state->pause_count == U8_MAX); + + if (state->pause_count++ == 0 && state->enable_count > 0) + arch_leave_lazy_mmu_mode(); +} + +/** + * lazy_mmu_mode_resume() - Resume the lazy MMU mode. + * + * Resumes the lazy MMU mode; if it was active at the point where the matching + * call to lazy_mmu_mode_pause() was made, re-enables it and calls + * arch_enter_lazy_mmu_mode(). + * + * Must match a call to lazy_mmu_mode_pause(). + * + * Has no effect if called: + * - While paused (inside another pause()/resume() pair) + * - In interrupt context + */ +static inline void lazy_mmu_mode_resume(void) +{ + struct lazy_mmu_state *state = ¤t->lazy_mmu_state; + + if (in_interrupt()) + return; + + VM_WARN_ON_ONCE(state->pause_count == 0); + + if (--state->pause_count == 0 && state->enable_count > 0) + arch_enter_lazy_mmu_mode(); +} +#else +static inline void lazy_mmu_mode_enable(void) {} +static inline void lazy_mmu_mode_disable(void) {} +static inline void lazy_mmu_mode_pause(void) {} +static inline void lazy_mmu_mode_resume(void) {} #endif #ifndef pte_batch_hint @@ -289,7 +410,7 @@ static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) static inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { - page_table_check_ptes_set(mm, ptep, pte, nr); + page_table_check_ptes_set(mm, addr, ptep, pte, nr); for (;;) { set_pte(ptep, pte); @@ -370,64 +491,63 @@ static inline pgd_t pgdp_get(pgd_t *pgdp) #endif #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pte_t *ptep) +static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { pte_t pte = ptep_get(ptep); - int r = 1; + bool young = true; + if (!pte_young(pte)) - r = 0; + young = false; else set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); - return r; + return young; } #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, - unsigned long address, - pmd_t *pmdp) +static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; - int r = 1; + bool young = true; + if (!pmd_young(pmd)) - r = 0; + young = false; else set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); - return r; + return young; } #else -static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmdp) +static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { BUILD_BUG(); - return 0; + return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -int ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep); +bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH #ifdef CONFIG_TRANSPARENT_HUGEPAGE -extern int pmdp_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); +bool pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); #else /* * Despite relevant to THP only, this API is called from generic rmap code * under PageTransHuge(), hence needs a dummy implementation for !THP */ -static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) +static inline bool pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { BUILD_BUG(); - return 0; + return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif @@ -494,7 +614,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = ptep_get(ptep); pte_clear(mm, address, ptep); - page_table_check_pte_clear(mm, pte); + page_table_check_pte_clear(mm, address, pte); return pte; } #endif @@ -553,7 +673,7 @@ static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, * No need for ptep_get_and_clear(): page table check doesn't care about * any bits that could have been set by HW concurrently. */ - page_table_check_pte_clear(mm, pte); + page_table_check_pte_clear(mm, addr, pte); } #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH @@ -648,7 +768,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, pmd_t pmd = *pmdp; pmd_clear(pmdp); - page_table_check_pmd_clear(mm, pmd); + page_table_check_pmd_clear(mm, address, pmd); return pmd; } @@ -661,7 +781,7 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, pud_t pud = *pudp; pud_clear(pudp); - page_table_check_pud_clear(mm, pud); + page_table_check_pud_clear(mm, address, pud); return pud; } @@ -947,6 +1067,78 @@ static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, } #endif +#ifndef clear_flush_young_ptes +/** + * clear_flush_young_ptes - Mark PTEs that map consecutive pages of the same + * folio as old and flush the TLB. + * @vma: The virtual memory area 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 clear access bit. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over ptep_clear_flush_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 bool clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) +{ + bool young = false; + + for (;;) { + young |= ptep_clear_flush_young(vma, addr, ptep); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } + + return young; +} +#endif + +#ifndef test_and_clear_young_ptes +/** + * test_and_clear_young_ptes - Mark PTEs that map consecutive pages of the same + * folio as old + * @vma: The virtual memory area 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 clear access bit. + * + * 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. + * + * Returns: whether any PTE was young. + */ +static inline bool test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) +{ + bool young = false; + + for (;;) { + young |= ptep_test_and_clear_young(vma, addr, ptep); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } + + return young; +} +#endif + /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibility of software setting this bit. It brings @@ -1490,6 +1682,25 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end); #endif /* CONFIG_MMU */ /* + * On almost all architectures and configurations, 0 can be used as the + * upper ceiling to free_pgtables(): on many architectures it has the same + * effect as using TASK_SIZE. However, there is one configuration which + * must impose a more careful limit, to avoid freeing kernel pgtables. + */ +#ifndef USER_PGTABLES_CEILING +#define USER_PGTABLES_CEILING 0UL +#endif + +/* + * This defines the first usable user address. Platforms + * can override its value with custom FIRST_USER_ADDRESS + * defined in their respective <asm/pgtable.h>. + */ +#ifndef FIRST_USER_ADDRESS +#define FIRST_USER_ADDRESS 0UL +#endif + +/* * No-op macros that just return the current protection value. Defined here * because these macros can be used even if CONFIG_MMU is not defined. */ @@ -1742,41 +1953,56 @@ static inline void pfnmap_setup_cachemode_pfn(unsigned long pfn, pgprot_t *prot) pfnmap_setup_cachemode(pfn, PAGE_SIZE, prot); } -#ifdef CONFIG_MMU +/* + * ZERO_PAGE() is global shared page(s) that is always zero. It is used for + * zero-mapped memory areas, CoW etc. + * + * On architectures that __HAVE_COLOR_ZERO_PAGE there are several such pages + * for different ranges in the virtual address space. + * + * zero_page_pfn identifies the first (or the only) pfn for these pages. + * + * For architectures that don't __HAVE_COLOR_ZERO_PAGE the zero page lives in + * empty_zero_page in BSS. + */ +void arch_setup_zero_pages(void); + #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { - extern unsigned long zero_pfn; - unsigned long offset_from_zero_pfn = pfn - zero_pfn; + extern unsigned long zero_page_pfn; + unsigned long offset_from_zero_pfn = pfn - zero_page_pfn; + return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); } -#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) +#define zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) #else static inline int is_zero_pfn(unsigned long pfn) { - extern unsigned long zero_pfn; - return pfn == zero_pfn; -} + extern unsigned long zero_page_pfn; -static inline unsigned long my_zero_pfn(unsigned long addr) -{ - extern unsigned long zero_pfn; - return zero_pfn; + return pfn == zero_page_pfn; } -#endif -#else -static inline int is_zero_pfn(unsigned long pfn) + +static inline unsigned long zero_pfn(unsigned long addr) { - return 0; + extern unsigned long zero_page_pfn; + + return zero_page_pfn; } -static inline unsigned long my_zero_pfn(unsigned long addr) +extern uint8_t empty_zero_page[PAGE_SIZE]; +extern struct page *__zero_page; + +static inline struct page *_zero_page(unsigned long addr) { - return 0; + return __zero_page; } -#endif /* CONFIG_MMU */ +#define ZERO_PAGE(vaddr) _zero_page(vaddr) + +#endif /* __HAVE_COLOR_ZERO_PAGE */ #ifdef CONFIG_MMU @@ -1814,7 +2040,7 @@ static inline int pud_trans_unstable(pud_t *pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) - pud_t pudval = READ_ONCE(*pud); + pud_t pudval = pudp_get(pud); if (pud_none(pudval) || pud_trans_huge(pudval)) return 1; |