diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/hmm.c | 23 | ||||
-rw-r--r-- | mm/madvise.c | 41 | ||||
-rw-r--r-- | mm/memcontrol.c | 23 | ||||
-rw-r--r-- | mm/mempolicy.c | 15 | ||||
-rw-r--r-- | mm/migrate.c | 23 | ||||
-rw-r--r-- | mm/mincore.c | 15 | ||||
-rw-r--r-- | mm/mprotect.c | 24 | ||||
-rw-r--r-- | mm/pagewalk.c | 124 |
8 files changed, 140 insertions, 148 deletions
@@ -852,6 +852,13 @@ void hmm_range_unregister(struct hmm_range *range) } EXPORT_SYMBOL(hmm_range_unregister); +static const struct mm_walk_ops hmm_walk_ops = { + .pud_entry = hmm_vma_walk_pud, + .pmd_entry = hmm_vma_walk_pmd, + .pte_hole = hmm_vma_walk_hole, + .hugetlb_entry = hmm_vma_walk_hugetlb_entry, +}; + /** * hmm_range_fault - try to fault some address in a virtual address range * @range: range being faulted @@ -887,7 +894,6 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) struct hmm_vma_walk hmm_vma_walk; struct hmm *hmm = range->hmm; struct vm_area_struct *vma; - struct mm_walk mm_walk; int ret; lockdep_assert_held(&hmm->mmu_notifier.mm->mmap_sem); @@ -916,21 +922,14 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) hmm_vma_walk.last = start; hmm_vma_walk.flags = flags; hmm_vma_walk.range = range; - mm_walk.private = &hmm_vma_walk; end = min(range->end, vma->vm_end); - mm_walk.vma = vma; - mm_walk.mm = vma->vm_mm; - mm_walk.pte_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.hugetlb_entry = NULL; - mm_walk.pud_entry = hmm_vma_walk_pud; - mm_walk.pmd_entry = hmm_vma_walk_pmd; - mm_walk.pte_hole = hmm_vma_walk_hole; - mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry; + walk_page_range(vma->vm_mm, start, end, &hmm_walk_ops, + &hmm_vma_walk); do { - ret = walk_page_range(start, end, &mm_walk); + ret = walk_page_range(vma->vm_mm, start, end, + &hmm_walk_ops, &hmm_vma_walk); start = hmm_vma_walk.last; /* Keep trying while the range is valid. */ diff --git a/mm/madvise.c b/mm/madvise.c index 80a78bb16782..afe2b015ea58 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -226,19 +226,9 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, return 0; } -static void force_swapin_readahead(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - struct mm_walk walk = { - .mm = vma->vm_mm, - .pmd_entry = swapin_walk_pmd_entry, - .private = vma, - }; - - walk_page_range(start, end, &walk); - - lru_add_drain(); /* Push any new pages onto the LRU now */ -} +static const struct mm_walk_ops swapin_walk_ops = { + .pmd_entry = swapin_walk_pmd_entry, +}; static void force_shm_swapin_readahead(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -280,7 +270,8 @@ static long madvise_willneed(struct vm_area_struct *vma, *prev = vma; #ifdef CONFIG_SWAP if (!file) { - force_swapin_readahead(vma, start, end); + walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma); + lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } @@ -441,20 +432,9 @@ next: return 0; } -static void madvise_free_page_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, - unsigned long addr, unsigned long end) -{ - struct mm_walk free_walk = { - .pmd_entry = madvise_free_pte_range, - .mm = vma->vm_mm, - .private = tlb, - }; - - tlb_start_vma(tlb, vma); - walk_page_range(addr, end, &free_walk); - tlb_end_vma(tlb, vma); -} +static const struct mm_walk_ops madvise_free_walk_ops = { + .pmd_entry = madvise_free_pte_range, +}; static int madvise_free_single_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) @@ -481,7 +461,10 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); - madvise_free_page_range(&tlb, vma, range.start, range.end); + tlb_start_vma(&tlb, vma); + walk_page_range(vma->vm_mm, range.start, range.end, + &madvise_free_walk_ops, &tlb); + tlb_end_vma(&tlb, vma); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, range.start, range.end); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4c3af5d71ab1..9b2516a76be2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5283,17 +5283,16 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, return 0; } +static const struct mm_walk_ops precharge_walk_ops = { + .pmd_entry = mem_cgroup_count_precharge_pte_range, +}; + static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) { unsigned long precharge; - struct mm_walk mem_cgroup_count_precharge_walk = { - .pmd_entry = mem_cgroup_count_precharge_pte_range, - .mm = mm, - }; down_read(&mm->mmap_sem); - walk_page_range(0, mm->highest_vm_end, - &mem_cgroup_count_precharge_walk); + walk_page_range(mm, 0, mm->highest_vm_end, &precharge_walk_ops, NULL); up_read(&mm->mmap_sem); precharge = mc.precharge; @@ -5562,13 +5561,12 @@ put: /* get_mctgt_type() gets the page */ return ret; } +static const struct mm_walk_ops charge_walk_ops = { + .pmd_entry = mem_cgroup_move_charge_pte_range, +}; + static void mem_cgroup_move_charge(void) { - struct mm_walk mem_cgroup_move_charge_walk = { - .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mc.mm, - }; - lru_add_drain_all(); /* * Signal lock_page_memcg() to take the memcg's move_lock @@ -5594,7 +5592,8 @@ retry: * When we have consumed all precharges and failed in doing * additional charge, the page walk just aborts. */ - walk_page_range(0, mc.mm->highest_vm_end, &mem_cgroup_move_charge_walk); + walk_page_range(mc.mm, 0, mc.mm->highest_vm_end, &charge_walk_ops, + NULL); up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3a96def1e796..f000771558d8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -655,6 +655,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, return 1; } +static const struct mm_walk_ops queue_pages_walk_ops = { + .hugetlb_entry = queue_pages_hugetlb, + .pmd_entry = queue_pages_pte_range, + .test_walk = queue_pages_test_walk, +}; + /* * Walk through page tables and collect pages to be migrated. * @@ -679,15 +685,8 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .nmask = nodes, .prev = NULL, }; - struct mm_walk queue_pages_walk = { - .hugetlb_entry = queue_pages_hugetlb, - .pmd_entry = queue_pages_pte_range, - .test_walk = queue_pages_test_walk, - .mm = mm, - .private = &qp, - }; - return walk_page_range(start, end, &queue_pages_walk); + return walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); } /* diff --git a/mm/migrate.c b/mm/migrate.c index c9c73a35aca7..9f4ed4e985c1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2320,6 +2320,11 @@ next: return 0; } +static const struct mm_walk_ops migrate_vma_walk_ops = { + .pmd_entry = migrate_vma_collect_pmd, + .pte_hole = migrate_vma_collect_hole, +}; + /* * migrate_vma_collect() - collect pages over a range of virtual addresses * @migrate: migrate struct containing all migration information @@ -2331,21 +2336,15 @@ next: static void migrate_vma_collect(struct migrate_vma *migrate) { struct mmu_notifier_range range; - struct mm_walk mm_walk = { - .pmd_entry = migrate_vma_collect_pmd, - .pte_hole = migrate_vma_collect_hole, - .vma = migrate->vma, - .mm = migrate->vma->vm_mm, - .private = migrate, - }; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm, - migrate->start, - migrate->end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, + migrate->vma->vm_mm, migrate->start, migrate->end); mmu_notifier_invalidate_range_start(&range); - walk_page_range(migrate->start, migrate->end, &mm_walk); - mmu_notifier_invalidate_range_end(&range); + walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end, + &migrate_vma_walk_ops, migrate); + + mmu_notifier_invalidate_range_end(&range); migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT); } diff --git a/mm/mincore.c b/mm/mincore.c index 3b051b6ab3fe..f9a9dbe8cd33 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -193,6 +193,12 @@ static inline bool can_do_mincore(struct vm_area_struct *vma) inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; } +static const struct mm_walk_ops mincore_walk_ops = { + .pmd_entry = mincore_pte_range, + .pte_hole = mincore_unmapped_range, + .hugetlb_entry = mincore_hugetlb, +}; + /* * Do a chunk of "sys_mincore()". We've already checked * all the arguments, we hold the mmap semaphore: we should @@ -203,12 +209,6 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v struct vm_area_struct *vma; unsigned long end; int err; - struct mm_walk mincore_walk = { - .pmd_entry = mincore_pte_range, - .pte_hole = mincore_unmapped_range, - .hugetlb_entry = mincore_hugetlb, - .private = vec, - }; vma = find_vma(current->mm, addr); if (!vma || addr < vma->vm_start) @@ -219,8 +219,7 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v memset(vec, 1, pages); return pages; } - mincore_walk.mm = vma->vm_mm; - err = walk_page_range(addr, end, &mincore_walk); + err = walk_page_range(vma->vm_mm, addr, end, &mincore_walk_ops, vec); if (err < 0) return err; return (end - addr) >> PAGE_SHIFT; diff --git a/mm/mprotect.c b/mm/mprotect.c index cc73318dbc25..675e5d34a507 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -329,20 +329,11 @@ static int prot_none_test(unsigned long addr, unsigned long next, return 0; } -static int prot_none_walk(struct vm_area_struct *vma, unsigned long start, - unsigned long end, unsigned long newflags) -{ - pgprot_t new_pgprot = vm_get_page_prot(newflags); - struct mm_walk prot_none_walk = { - .pte_entry = prot_none_pte_entry, - .hugetlb_entry = prot_none_hugetlb_entry, - .test_walk = prot_none_test, - .mm = current->mm, - .private = &new_pgprot, - }; - - return walk_page_range(start, end, &prot_none_walk); -} +static const struct mm_walk_ops prot_none_walk_ops = { + .pte_entry = prot_none_pte_entry, + .hugetlb_entry = prot_none_hugetlb_entry, + .test_walk = prot_none_test, +}; int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, @@ -369,7 +360,10 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, if (arch_has_pfn_modify_check() && (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) { - error = prot_none_walk(vma, start, end, newflags); + pgprot_t new_pgprot = vm_get_page_prot(newflags); + + error = walk_page_range(current->mm, start, end, + &prot_none_walk_ops, &new_pgprot); if (error) return error; } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 8a92a961a2ee..b8762b673a3d 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -9,10 +9,11 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, { pte_t *pte; int err = 0; + const struct mm_walk_ops *ops = walk->ops; pte = pte_offset_map(pmd, addr); for (;;) { - err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk); + err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; addr += PAGE_SIZE; @@ -30,6 +31,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, { pmd_t *pmd; unsigned long next; + const struct mm_walk_ops *ops = walk->ops; int err = 0; pmd = pmd_offset(pud, addr); @@ -37,8 +39,8 @@ 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) || !walk->vma) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; @@ -47,8 +49,8 @@ again: * This implies that each ->pmd_entry() handler * needs to know about pmd_trans_huge() pmds */ - if (walk->pmd_entry) - err = walk->pmd_entry(pmd, addr, next, walk); + if (ops->pmd_entry) + err = ops->pmd_entry(pmd, addr, next, walk); if (err) break; @@ -56,7 +58,7 @@ again: * Check this here so we only break down trans_huge * pages when we _need_ to */ - if (!walk->pte_entry) + if (!ops->pte_entry) continue; split_huge_pmd(walk->vma, pmd, addr); @@ -75,6 +77,7 @@ 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; int err = 0; pud = pud_offset(p4d, addr); @@ -82,18 +85,18 @@ 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) || !walk->vma) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; } - if (walk->pud_entry) { + if (ops->pud_entry) { spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma); if (ptl) { - err = walk->pud_entry(pud, addr, next, walk); + err = ops->pud_entry(pud, addr, next, walk); spin_unlock(ptl); if (err) break; @@ -105,7 +108,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pud)) goto again; - if (walk->pmd_entry || walk->pte_entry) + if (ops->pmd_entry || ops->pte_entry) err = walk_pmd_range(pud, addr, next, walk); if (err) break; @@ -119,19 +122,20 @@ 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; int err = 0; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; } - if (walk->pmd_entry || walk->pte_entry) + if (ops->pmd_entry || ops->pte_entry) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -145,19 +149,20 @@ 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; int err = 0; pgd = pgd_offset(walk->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; } - if (walk->pmd_entry || walk->pte_entry) + if (ops->pmd_entry || ops->pte_entry) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; @@ -183,6 +188,7 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, unsigned long hmask = huge_page_mask(h); unsigned long sz = huge_page_size(h); pte_t *pte; + const struct mm_walk_ops *ops = walk->ops; int err = 0; do { @@ -190,9 +196,9 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, pte = huge_pte_offset(walk->mm, addr & hmask, sz); if (pte) - err = walk->hugetlb_entry(pte, hmask, addr, next, walk); - else if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + err = ops->hugetlb_entry(pte, hmask, addr, next, walk); + else if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; @@ -220,9 +226,10 @@ static int walk_page_test(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; + const struct mm_walk_ops *ops = walk->ops; - if (walk->test_walk) - return walk->test_walk(start, end, walk); + if (ops->test_walk) + return ops->test_walk(start, end, walk); /* * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP @@ -234,8 +241,8 @@ static int walk_page_test(unsigned long start, unsigned long end, */ if (vma->vm_flags & VM_PFNMAP) { int err = 1; - if (walk->pte_hole) - err = walk->pte_hole(start, end, walk); + if (ops->pte_hole) + err = ops->pte_hole(start, end, walk); return err ? err : 1; } return 0; @@ -248,7 +255,7 @@ static int __walk_page_range(unsigned long start, unsigned long end, struct vm_area_struct *vma = walk->vma; if (vma && is_vm_hugetlb_page(vma)) { - if (walk->hugetlb_entry) + if (walk->ops->hugetlb_entry) err = walk_hugetlb_range(start, end, walk); } else err = walk_pgd_range(start, end, walk); @@ -258,11 +265,13 @@ static int __walk_page_range(unsigned long start, unsigned long end, /** * walk_page_range - walk page table with caller specific callbacks - * @start: start address of the virtual address range - * @end: end address of the virtual address range - * @walk: mm_walk structure defining the callbacks and the target address space + * @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 @walk->mm + * 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 @@ -278,47 +287,52 @@ static int __walk_page_range(unsigned long start, unsigned long end, * * 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 @walk->test_walk() are used for this + * its vm_flags. walk_page_test() and @ops->test_walk() are used for this * purpose. * * 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, @walk->private should be helpful. + * caller-specific data to callbacks, @private should be helpful. * * Locking: - * Callers of walk_page_range() and walk_page_vma() should hold - * @walk->mm->mmap_sem, because these function traverse vma list and/or - * access to vma's data. + * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_sem, + * because these function traverse vma list and/or access to vma's data. */ -int walk_page_range(unsigned long start, unsigned long end, - struct mm_walk *walk) +int walk_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private) { int err = 0; unsigned long next; struct vm_area_struct *vma; + struct mm_walk walk = { + .ops = ops, + .mm = mm, + .private = private, + }; if (start >= end) return -EINVAL; - if (!walk->mm) + if (!walk.mm) return -EINVAL; - VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm); + VM_BUG_ON_MM(!rwsem_is_locked(&walk.mm->mmap_sem), walk.mm); - vma = find_vma(walk->mm, start); + vma = find_vma(walk.mm, start); do { if (!vma) { /* after the last vma */ - walk->vma = NULL; + walk.vma = NULL; next = end; } else if (start < vma->vm_start) { /* outside vma */ - walk->vma = NULL; + walk.vma = NULL; next = min(end, vma->vm_start); } else { /* inside vma */ - walk->vma = vma; + walk.vma = vma; next = min(end, vma->vm_end); vma = vma->vm_next; - err = walk_page_test(start, next, walk); + err = walk_page_test(start, next, &walk); if (err > 0) { /* * positive return values are purely for @@ -331,28 +345,34 @@ int walk_page_range(unsigned long start, unsigned long end, if (err < 0) break; } - if (walk->vma || walk->pte_hole) - err = __walk_page_range(start, next, walk); + if (walk.vma || walk.ops->pte_hole) + err = __walk_page_range(start, next, &walk); if (err) break; } while (start = next, start < end); return err; } -int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk) +int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, + void *private) { + struct mm_walk walk = { + .ops = ops, + .mm = vma->vm_mm, + .vma = vma, + .private = private, + }; int err; - if (!walk->mm) + if (!walk.mm) return -EINVAL; - VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); - VM_BUG_ON(!vma); - walk->vma = vma; - err = walk_page_test(vma->vm_start, vma->vm_end, walk); + VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem)); + + err = walk_page_test(vma->vm_start, vma->vm_end, &walk); if (err > 0) return 0; if (err < 0) return err; - return __walk_page_range(vma->vm_start, vma->vm_end, walk); + return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } |