diff options
Diffstat (limited to 'mm/pagewalk.c')
| -rw-r--r-- | mm/pagewalk.c | 507 |
1 files changed, 390 insertions, 117 deletions
diff --git a/mm/pagewalk.c b/mm/pagewalk.c index f46c80b18ce4..e478777c86e1 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -3,6 +3,13 @@ #include <linux/highmem.h> #include <linux/sched.h> #include <linux/hugetlb.h> +#include <linux/mmu_context.h> +#include <linux/swap.h> +#include <linux/swapops.h> + +#include <asm/tlbflush.h> + +#include "internal.h" /* * We want to know the real level where a entry is located ignoring any @@ -27,9 +34,23 @@ static int walk_pte_range_inner(pte_t *pte, unsigned long addr, int err = 0; for (;;) { - err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); - if (err) - break; + if (ops->install_pte && pte_none(ptep_get(pte))) { + pte_t new_pte; + + err = ops->install_pte(addr, addr + PAGE_SIZE, &new_pte, + walk); + if (err) + break; + + set_pte_at(walk->mm, addr, pte, new_pte); + /* Non-present before, so for arches that need it. */ + if (!WARN_ON_ONCE(walk->no_vma)) + update_mmu_cache(walk->vma, addr, pte); + } else { + err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); + if (err) + break; + } if (addr >= end - PAGE_SIZE) break; addr += PAGE_SIZE; @@ -73,51 +94,14 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return err; } -#ifdef CONFIG_ARCH_HAS_HUGEPD -static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, - unsigned long end, struct mm_walk *walk, int pdshift) -{ - int err = 0; - const struct mm_walk_ops *ops = walk->ops; - int shift = hugepd_shift(*phpd); - int page_size = 1 << shift; - - if (!ops->pte_entry) - return 0; - - if (addr & (page_size - 1)) - return 0; - - for (;;) { - pte_t *pte; - - spin_lock(&walk->mm->page_table_lock); - pte = hugepte_offset(*phpd, addr, pdshift); - err = ops->pte_entry(pte, addr, addr + page_size, walk); - spin_unlock(&walk->mm->page_table_lock); - - if (err) - break; - if (addr >= end - page_size) - break; - addr += page_size; - } - return err; -} -#else -static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, - unsigned long end, struct mm_walk *walk, int pdshift) -{ - return 0; -} -#endif - static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, struct mm_walk *walk) { pmd_t *pmd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; int depth = real_depth(3); @@ -126,11 +110,14 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, again: next = pmd_addr_end(addr, end); if (pmd_none(*pmd)) { - if (ops->pte_hole) + if (has_install) + err = __pte_alloc(walk->mm, pmd); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; - continue; + if (!has_install) + continue; } walk->action = ACTION_SUBTREE; @@ -146,23 +133,27 @@ again: if (walk->action == ACTION_AGAIN) goto again; - - /* - * Check this here so we only break down trans_huge - * pages when we _need_ to - */ - if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) || - walk->action == ACTION_CONTINUE || - !(ops->pte_entry)) + if (walk->action == ACTION_CONTINUE) continue; + if (!has_handler) { /* No handlers for lower page tables. */ + if (!has_install) + continue; /* Nothing to do. */ + /* + * We are ONLY installing, so avoid unnecessarily + * splitting a present huge page. + */ + if (pmd_present(*pmd) && + (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) + continue; + } + if (walk->vma) split_huge_pmd(walk->vma, pmd, addr); + else if (pmd_leaf(*pmd) || !pmd_present(*pmd)) + continue; /* Nothing to do. */ - if (is_hugepd(__hugepd(pmd_val(*pmd)))) - err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT); - else - err = walk_pte_range(pmd, addr, next, walk); + err = walk_pte_range(pmd, addr, next, walk); if (err) break; @@ -180,6 +171,8 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pud_t *pud; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->pmd_entry || ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; int depth = real_depth(2); @@ -188,11 +181,14 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, again: next = pud_addr_end(addr, end); if (pud_none(*pud)) { - if (ops->pte_hole) + if (has_install) + err = __pmd_alloc(walk->mm, pud, addr); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; - continue; + if (!has_install) + continue; } walk->action = ACTION_SUBTREE; @@ -204,21 +200,30 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (walk->action == ACTION_AGAIN) goto again; - - if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) || - walk->action == ACTION_CONTINUE || - !(ops->pmd_entry || ops->pte_entry)) + if (walk->action == ACTION_CONTINUE) continue; + if (!has_handler) { /* No handlers for lower page tables. */ + if (!has_install) + continue; /* Nothing to do. */ + /* + * We are ONLY installing, so avoid unnecessarily + * splitting a present huge page. + */ + if (pud_present(*pud) && + (pud_trans_huge(*pud) || pud_devmap(*pud))) + continue; + } + if (walk->vma) split_huge_pud(walk->vma, pud, addr); + else if (pud_leaf(*pud) || !pud_present(*pud)) + continue; /* Nothing to do. */ + if (pud_none(*pud)) goto again; - if (is_hugepd(__hugepd(pud_val(*pud)))) - err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT); - else - err = walk_pmd_range(pud, addr, next, walk); + err = walk_pmd_range(pud, addr, next, walk); if (err) break; } while (pud++, addr = next, addr != end); @@ -232,6 +237,8 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, p4d_t *p4d; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->pud_entry || ops->pmd_entry || ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; int depth = real_depth(1); @@ -239,20 +246,21 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) { - if (ops->pte_hole) + if (has_install) + err = __pud_alloc(walk->mm, p4d, addr); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; - continue; + if (!has_install) + continue; } if (ops->p4d_entry) { err = ops->p4d_entry(p4d, addr, next, walk); if (err) break; } - if (is_hugepd(__hugepd(p4d_val(*p4d)))) - err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT); - else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (has_handler || has_install) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -267,6 +275,9 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, pgd_t *pgd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->p4d_entry || ops->pud_entry || ops->pmd_entry || + ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; if (walk->pgd) @@ -276,20 +287,21 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) { - if (ops->pte_hole) + if (has_install) + err = __p4d_alloc(walk->mm, pgd, addr); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, 0, walk); if (err) break; - continue; + if (!has_install) + continue; } if (ops->pgd_entry) { err = ops->pgd_entry(pgd, addr, next, walk); if (err) break; } - if (is_hugepd(__hugepd(pgd_val(*pgd)))) - err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT); - else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (has_handler || has_install) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; @@ -381,6 +393,11 @@ static int __walk_page_range(unsigned long start, unsigned long end, int err = 0; struct vm_area_struct *vma = walk->vma; const struct mm_walk_ops *ops = walk->ops; + bool is_hugetlb = is_vm_hugetlb_page(vma); + + /* We do not support hugetlb PTE installation. */ + if (ops->install_pte && is_hugetlb) + return -EINVAL; if (ops->pre_vma) { err = ops->pre_vma(start, end, walk); @@ -388,7 +405,7 @@ static int __walk_page_range(unsigned long start, unsigned long end, return err; } - if (is_vm_hugetlb_page(vma)) { + if (is_hugetlb) { if (ops->hugetlb_entry) err = walk_hugetlb_range(start, end, walk); } else @@ -427,47 +444,14 @@ static inline void process_vma_walk_lock(struct vm_area_struct *vma, #endif } -/** - * walk_page_range - walk page table with caller specific callbacks - * @mm: mm_struct representing the target process of page table walk - * @start: start address of the virtual address range - * @end: end address of the virtual address range - * @ops: operation to call during the walk - * @private: private data for callbacks' usage - * - * Recursively walk the page table tree of the process represented by @mm - * within the virtual address range [@start, @end). During walking, we can do - * some caller-specific works for each entry, by setting up pmd_entry(), - * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these - * callbacks, the associated entries/pages are just ignored. - * The return values of these callbacks are commonly defined like below: - * - * - 0 : succeeded to handle the current entry, and if you don't reach the - * end address yet, continue to walk. - * - >0 : succeeded to handle the current entry, and return to the caller - * with caller specific value. - * - <0 : failed to handle the current entry, and return to the caller - * with error code. - * - * Before starting to walk page table, some callers want to check whether - * they really want to walk over the current vma, typically by checking - * its vm_flags. walk_page_test() and @ops->test_walk() are used for this - * purpose. - * - * If operations need to be staged before and committed after a vma is walked, - * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(), - * since it is intended to handle commit-type operations, can't return any - * errors. - * - * struct mm_walk keeps current values of some common data like vma and pmd, - * which are useful for the access from callbacks. If you want to pass some - * caller-specific data to callbacks, @private should be helpful. +/* + * See the comment for walk_page_range(), this performs the heavy lifting of the + * operation, only sets no restrictions on how the walk proceeds. * - * Locking: - * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock, - * because these function traverse vma list and/or access to vma's data. + * We usually restrict the ability to install PTEs, but this functionality is + * available to internal memory management code and provided in mm/internal.h. */ -int walk_page_range(struct mm_struct *mm, unsigned long start, +int walk_page_range_mm(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private) { @@ -526,6 +510,80 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, return err; } +/* + * Determine if the walk operations specified are permitted to be used for a + * page table walk. + * + * This check is performed on all functions which are parameterised by walk + * operations and exposed in include/linux/pagewalk.h. + * + * Internal memory management code can use the walk_page_range_mm() function to + * be able to use all page walking operations. + */ +static bool check_ops_valid(const struct mm_walk_ops *ops) +{ + /* + * The installation of PTEs is solely under the control of memory + * management logic and subject to many subtle locking, security and + * cache considerations so we cannot permit other users to do so, and + * certainly not for exported symbols. + */ + if (ops->install_pte) + return false; + + return true; +} + +/** + * walk_page_range - walk page table with caller specific callbacks + * @mm: mm_struct representing the target process of page table walk + * @start: start address of the virtual address range + * @end: end address of the virtual address range + * @ops: operation to call during the walk + * @private: private data for callbacks' usage + * + * Recursively walk the page table tree of the process represented by @mm + * within the virtual address range [@start, @end). During walking, we can do + * some caller-specific works for each entry, by setting up pmd_entry(), + * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these + * callbacks, the associated entries/pages are just ignored. + * The return values of these callbacks are commonly defined like below: + * + * - 0 : succeeded to handle the current entry, and if you don't reach the + * end address yet, continue to walk. + * - >0 : succeeded to handle the current entry, and return to the caller + * with caller specific value. + * - <0 : failed to handle the current entry, and return to the caller + * with error code. + * + * Before starting to walk page table, some callers want to check whether + * they really want to walk over the current vma, typically by checking + * its vm_flags. walk_page_test() and @ops->test_walk() are used for this + * purpose. + * + * If operations need to be staged before and committed after a vma is walked, + * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(), + * since it is intended to handle commit-type operations, can't return any + * errors. + * + * struct mm_walk keeps current values of some common data like vma and pmd, + * which are useful for the access from callbacks. If you want to pass some + * caller-specific data to callbacks, @private should be helpful. + * + * Locking: + * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock, + * because these function traverse vma list and/or access to vma's data. + */ +int walk_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private) +{ + if (!check_ops_valid(ops)) + return -EINVAL; + + return walk_page_range_mm(mm, start, end, ops, private); +} + /** * walk_page_range_novma - walk a range of pagetables not backed by a vma * @mm: mm_struct representing the target process of page table walk @@ -541,7 +599,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, * walking the kernel pages tables or page tables for firmware. * * Note: Be careful to walk the kernel pages tables, the caller may be need to - * take other effective approache (mmap lock may be insufficient) to prevent + * take other effective approaches (mmap lock may be insufficient) to prevent * the intermediate kernel page tables belonging to the specified address range * from being freed (e.g. memory hot-remove). */ @@ -560,6 +618,8 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, if (start >= end || !walk.mm) return -EINVAL; + if (!check_ops_valid(ops)) + return -EINVAL; /* * 1) For walking the user virtual address space: @@ -603,6 +663,8 @@ int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, return -EINVAL; if (start < vma->vm_start || end > vma->vm_end) return -EINVAL; + if (!check_ops_valid(ops)) + return -EINVAL; process_mm_walk_lock(walk.mm, ops->walk_lock); process_vma_walk_lock(vma, ops->walk_lock); @@ -621,6 +683,8 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, if (!walk.mm) return -EINVAL; + if (!check_ops_valid(ops)) + return -EINVAL; process_mm_walk_lock(walk.mm, ops->walk_lock); process_vma_walk_lock(vma, ops->walk_lock); @@ -670,6 +734,9 @@ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, unsigned long start_addr, end_addr; int err = 0; + if (!check_ops_valid(ops)) + return -EINVAL; + lockdep_assert_held(&mapping->i_mmap_rwsem); vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index, first_index + nr - 1) { @@ -703,3 +770,209 @@ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, return err; } + +/** + * folio_walk_start - walk the page tables to a folio + * @fw: filled with information on success. + * @vma: the VMA. + * @addr: the virtual address to use for the page table walk. + * @flags: flags modifying which folios to walk to. + * + * Walk the page tables using @addr in a given @vma to a mapped folio and + * return the folio, making sure that the page table entry referenced by + * @addr cannot change until folio_walk_end() was called. + * + * As default, this function returns only folios that are not special (e.g., not + * the zeropage) and never returns folios that are supposed to be ignored by the + * VM as documented by vm_normal_page(). If requested, zeropages will be + * returned as well. + * + * As default, this function only considers present page table entries. + * If requested, it will also consider migration entries. + * + * If this function returns NULL it might either indicate "there is nothing" or + * "there is nothing suitable". + * + * On success, @fw is filled and the function returns the folio while the PTL + * is still held and folio_walk_end() must be called to clean up, + * releasing any held locks. The returned folio must *not* be used after the + * call to folio_walk_end(), unless a short-term folio reference is taken before + * that call. + * + * @fw->page will correspond to the page that is effectively referenced by + * @addr. However, for migration entries and shared zeropages @fw->page is + * set to NULL. Note that large folios might be mapped by multiple page table + * entries, and this function will always only lookup a single entry as + * specified by @addr, which might or might not cover more than a single page of + * the returned folio. + * + * This function must *not* be used as a naive replacement for + * get_user_pages() / pin_user_pages(), especially not to perform DMA or + * to carelessly modify page content. This function may *only* be used to grab + * short-term folio references, never to grab long-term folio references. + * + * Using the page table entry pointers in @fw for reading or modifying the + * entry should be avoided where possible: however, there might be valid + * use cases. + * + * WARNING: Modifying page table entries in hugetlb VMAs requires a lot of care. + * For example, PMD page table sharing might require prior unsharing. Also, + * logical hugetlb entries might span multiple physical page table entries, + * which *must* be modified in a single operation (set_huge_pte_at(), + * huge_ptep_set_*, ...). Note that the page table entry stored in @fw might + * not correspond to the first physical entry of a logical hugetlb entry. + * + * The mmap lock must be held in read mode. + * + * Return: folio pointer on success, otherwise NULL. + */ +struct folio *folio_walk_start(struct folio_walk *fw, + struct vm_area_struct *vma, unsigned long addr, + folio_walk_flags_t flags) +{ + unsigned long entry_size; + bool expose_page = true; + struct page *page; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + pgd_t *pgdp; + p4d_t *p4dp; + + mmap_assert_locked(vma->vm_mm); + vma_pgtable_walk_begin(vma); + + if (WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end)) + goto not_found; + + pgdp = pgd_offset(vma->vm_mm, addr); + if (pgd_none_or_clear_bad(pgdp)) + goto not_found; + + p4dp = p4d_offset(pgdp, addr); + if (p4d_none_or_clear_bad(p4dp)) + goto not_found; + + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + if (pud_none(pud)) + goto not_found; + if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && + (!pud_present(pud) || pud_leaf(pud))) { + ptl = pud_lock(vma->vm_mm, pudp); + pud = pudp_get(pudp); + + entry_size = PUD_SIZE; + fw->level = FW_LEVEL_PUD; + fw->pudp = pudp; + fw->pud = pud; + + /* + * TODO: FW_MIGRATION support for PUD migration entries + * once there are relevant users. + */ + if (!pud_present(pud) || pud_devmap(pud) || pud_special(pud)) { + spin_unlock(ptl); + goto not_found; + } else if (!pud_leaf(pud)) { + spin_unlock(ptl); + goto pmd_table; + } + /* + * TODO: vm_normal_page_pud() will be handy once we want to + * support PUD mappings in VM_PFNMAP|VM_MIXEDMAP VMAs. + */ + page = pud_page(pud); + goto found; + } + +pmd_table: + VM_WARN_ON_ONCE(!pud_present(pud) || pud_leaf(pud)); + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get_lockless(pmdp); + if (pmd_none(pmd)) + goto not_found; + if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && + (!pmd_present(pmd) || pmd_leaf(pmd))) { + ptl = pmd_lock(vma->vm_mm, pmdp); + pmd = pmdp_get(pmdp); + + entry_size = PMD_SIZE; + fw->level = FW_LEVEL_PMD; + fw->pmdp = pmdp; + fw->pmd = pmd; + + if (pmd_none(pmd)) { + spin_unlock(ptl); + goto not_found; + } else if (pmd_present(pmd) && !pmd_leaf(pmd)) { + spin_unlock(ptl); + goto pte_table; + } else if (pmd_present(pmd)) { + page = vm_normal_page_pmd(vma, addr, pmd); + if (page) { + goto found; + } else if ((flags & FW_ZEROPAGE) && + is_huge_zero_pmd(pmd)) { + page = pfn_to_page(pmd_pfn(pmd)); + expose_page = false; + goto found; + } + } else if ((flags & FW_MIGRATION) && + is_pmd_migration_entry(pmd)) { + swp_entry_t entry = pmd_to_swp_entry(pmd); + + page = pfn_swap_entry_to_page(entry); + expose_page = false; + goto found; + } + spin_unlock(ptl); + goto not_found; + } + +pte_table: + VM_WARN_ON_ONCE(!pmd_present(pmd) || pmd_leaf(pmd)); + ptep = pte_offset_map_lock(vma->vm_mm, pmdp, addr, &ptl); + if (!ptep) + goto not_found; + pte = ptep_get(ptep); + + entry_size = PAGE_SIZE; + fw->level = FW_LEVEL_PTE; + fw->ptep = ptep; + fw->pte = pte; + + if (pte_present(pte)) { + page = vm_normal_page(vma, addr, pte); + if (page) + goto found; + if ((flags & FW_ZEROPAGE) && + is_zero_pfn(pte_pfn(pte))) { + page = pfn_to_page(pte_pfn(pte)); + expose_page = false; + goto found; + } + } else if (!pte_none(pte)) { + swp_entry_t entry = pte_to_swp_entry(pte); + + if ((flags & FW_MIGRATION) && + is_migration_entry(entry)) { + page = pfn_swap_entry_to_page(entry); + expose_page = false; + goto found; + } + } + pte_unmap_unlock(ptep, ptl); +not_found: + vma_pgtable_walk_end(vma); + return NULL; +found: + if (expose_page) + /* Note: Offset from the mapped page, not the folio start. */ + fw->page = nth_page(page, (addr & (entry_size - 1)) >> PAGE_SHIFT); + else + fw->page = NULL; + fw->ptl = ptl; + return page_folio(page); +} |