diff options
Diffstat (limited to 'mm/memory.c')
-rw-r--r-- | mm/memory.c | 415 |
1 files changed, 288 insertions, 127 deletions
diff --git a/mm/memory.c b/mm/memory.c index 469af373ae76..589afe45d0b3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -65,7 +65,6 @@ #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> -#include <linux/dma-debug.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> @@ -695,84 +694,181 @@ out: * covered by this vma. */ -static inline unsigned long -copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, +static unsigned long +copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr, int *rss) { unsigned long vm_flags = vma->vm_flags; pte_t pte = *src_pte; struct page *page; + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); - /* pte contains position in swap or file, so copy. */ - if (unlikely(!pte_present(pte))) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - rss[mm_counter(page)]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - if (pte_swp_uffd_wp(*src_pte)) - pte = pte_swp_mkuffd_wp(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } - } else if (is_device_private_entry(entry)) { - page = device_private_entry_to_page(entry); + rss[mm_counter(page)]++; + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { /* - * Update rss count even for unaddressable pages, as - * they should treated just like normal pages in this - * respect. - * - * We will likely want to have some new rss counters - * for unaddressable pages, at some point. But for now - * keep things as they are. + * COW mappings require pages in both + * parent and child to be set to read. */ - get_page(page); - rss[mm_counter(page)]++; - page_dup_rmap(page, false); + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (is_device_private_entry(entry)) { + page = device_private_entry_to_page(entry); - /* - * We do not preserve soft-dirty information, because so - * far, checkpoint/restore is the only feature that - * requires that. And checkpoint/restore does not work - * when a device driver is involved (you cannot easily - * save and restore device driver state). - */ - if (is_write_device_private_entry(entry) && - is_cow_mapping(vm_flags)) { - make_device_private_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_uffd_wp(*src_pte)) - pte = pte_swp_mkuffd_wp(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } + /* + * Update rss count even for unaddressable pages, as + * they should treated just like normal pages in this + * respect. + * + * We will likely want to have some new rss counters + * for unaddressable pages, at some point. But for now + * keep things as they are. + */ + get_page(page); + rss[mm_counter(page)]++; + page_dup_rmap(page, false); + + /* + * We do not preserve soft-dirty information, because so + * far, checkpoint/restore is the only feature that + * requires that. And checkpoint/restore does not work + * when a device driver is involved (you cannot easily + * save and restore device driver state). + */ + if (is_write_device_private_entry(entry) && + is_cow_mapping(vm_flags)) { + make_device_private_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); } - goto out_set_pte; + } + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy a present and normal page if necessary. + * + * NOTE! The usual case is that this doesn't need to do + * anything, and can just return a positive value. That + * will let the caller know that it can just increase + * the page refcount and re-use the pte the traditional + * way. + * + * But _if_ we need to copy it because it needs to be + * pinned in the parent (and the child should get its own + * copy rather than just a reference to the same page), + * we'll do that here and return zero to let the caller + * know we're done. + * + * And if we need a pre-allocated page but don't yet have + * one, return a negative error to let the preallocation + * code know so that it can do so outside the page table + * lock. + */ +static inline int +copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, + struct page **prealloc, pte_t pte, struct page *page) +{ + struct mm_struct *src_mm = src_vma->vm_mm; + struct page *new_page; + + if (!is_cow_mapping(src_vma->vm_flags)) + return 1; + + /* + * What we want to do is to check whether this page may + * have been pinned by the parent process. If so, + * instead of wrprotect the pte on both sides, we copy + * the page immediately so that we'll always guarantee + * the pinned page won't be randomly replaced in the + * future. + * + * The page pinning checks are just "has this mm ever + * seen pinning", along with the (inexact) check of + * the page count. That might give false positives for + * for pinning, but it will work correctly. + */ + if (likely(!atomic_read(&src_mm->has_pinned))) + return 1; + if (likely(!page_maybe_dma_pinned(page))) + return 1; + + new_page = *prealloc; + if (!new_page) + return -EAGAIN; + + /* + * We have a prealloc page, all good! Take it + * over and copy the page & arm it. + */ + *prealloc = NULL; + copy_user_highpage(new_page, page, addr, src_vma); + __SetPageUptodate(new_page); + page_add_new_anon_rmap(new_page, dst_vma, addr, false); + lru_cache_add_inactive_or_unevictable(new_page, dst_vma); + rss[mm_counter(new_page)]++; + + /* All done, just insert the new page copy in the child */ + pte = mk_pte(new_page, dst_vma->vm_page_prot); + pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page + * is required to copy this pte. + */ +static inline int +copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, + struct page **prealloc) +{ + struct mm_struct *src_mm = src_vma->vm_mm; + unsigned long vm_flags = src_vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; + + page = vm_normal_page(src_vma, addr, pte); + if (page) { + int retval; + + retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, pte, page); + if (retval <= 0) + return retval; + + get_page(page); + page_dup_rmap(page, false); + rss[mm_counter(page)]++; } /* @@ -800,35 +896,53 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!(vm_flags & VM_UFFD_WP)) pte = pte_clear_uffd_wp(pte); - page = vm_normal_page(vma, addr, pte); - if (page) { - get_page(page); - page_dup_rmap(page, false); - rss[mm_counter(page)]++; + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); + return 0; +} + +static inline struct page * +page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *new_page; + + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); + if (!new_page) + return NULL; + + if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { + put_page(new_page); + return NULL; } + cgroup_throttle_swaprate(new_page, GFP_KERNEL); -out_set_pte: - set_pte_at(dst_mm, addr, dst_pte, pte); - return 0; + return new_page; } -static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static int +copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; - int progress = 0; + int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; + struct page *prealloc = NULL; again: + progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); - if (!dst_pte) - return -ENOMEM; + if (!dst_pte) { + ret = -ENOMEM; + goto out; + } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -851,10 +965,34 @@ again: progress++; continue; } - entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, - vma, addr, rss); - if (entry.val) + if (unlikely(!pte_present(*src_pte))) { + entry.val = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, + src_vma, addr, rss); + if (entry.val) + break; + progress += 8; + continue; + } + /* copy_present_pte() will clear `*prealloc' if consumed */ + ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, &prealloc); + /* + * If we need a pre-allocated page for this pte, drop the + * locks, allocate, and try again. + */ + if (unlikely(ret == -EAGAIN)) break; + if (unlikely(prealloc)) { + /* + * pre-alloc page cannot be reused by next time so as + * to strictly follow mempolicy (e.g., alloc_page_vma() + * will allocate page according to address). This + * could only happen if one pinned pte changed. + */ + put_page(prealloc); + prealloc = NULL; + } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); @@ -866,19 +1004,34 @@ again: cond_resched(); if (entry.val) { - if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) + if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { + ret = -ENOMEM; + goto out; + } + entry.val = 0; + } else if (ret) { + WARN_ON_ONCE(ret != -EAGAIN); + prealloc = page_copy_prealloc(src_mm, src_vma, addr); + if (!prealloc) return -ENOMEM; - progress = 0; + /* We've captured and resolved the error. Reset, try again. */ + ret = 0; } if (addr != end) goto again; - return 0; +out: + if (unlikely(prealloc)) + put_page(prealloc); + return ret; } -static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static inline int +copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; @@ -891,9 +1044,9 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; - VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma); + VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, - dst_pmd, src_pmd, addr, vma); + dst_pmd, src_pmd, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -902,17 +1055,20 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src } if (pmd_none_or_clear_bad(src_pmd)) continue; - if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, - vma, addr, next)) + if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, + addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } -static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static inline int +copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; @@ -925,9 +1081,9 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; - VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma); + VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, - dst_pud, src_pud, addr, vma); + dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -936,17 +1092,19 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src } if (pud_none_or_clear_bad(src_pud)) continue; - if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, - vma, addr, next)) + if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, + addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } -static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static inline int +copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; @@ -958,20 +1116,22 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, - vma, addr, next)) + if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, + addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } -int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - struct vm_area_struct *vma) +int +copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; - unsigned long addr = vma->vm_start; - unsigned long end = vma->vm_end; + unsigned long addr = src_vma->vm_start; + unsigned long end = src_vma->vm_end; + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; @@ -982,19 +1142,19 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && - !vma->anon_vma) + if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && + !src_vma->anon_vma) return 0; - if (is_vm_hugetlb_page(vma)) - return copy_hugetlb_page_range(dst_mm, src_mm, vma); + if (is_vm_hugetlb_page(src_vma)) + return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); - if (unlikely(vma->vm_flags & VM_PFNMAP)) { + if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ - ret = track_pfn_copy(vma); + ret = track_pfn_copy(src_vma); if (ret) return ret; } @@ -1005,11 +1165,11 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ - is_cow = is_cow_mapping(vma->vm_flags); + is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, - 0, vma, src_mm, addr, end); + 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); } @@ -1020,8 +1180,8 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next))) { + if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, + addr, next))) { ret = -ENOMEM; break; } @@ -2955,8 +3115,8 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ - wp_page_reuse(vmf); unlock_page(page); + wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { @@ -3433,7 +3593,7 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) * unlock_page(A) * lock_page(B) * lock_page(B) - * pte_alloc_pne + * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) @@ -3441,7 +3601,7 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { - vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); + vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ @@ -3549,13 +3709,14 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; int i; - vm_fault_t ret; + vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) - return VM_FAULT_FALLBACK; + return ret; - ret = VM_FAULT_FALLBACK; page = compound_head(page); + if (compound_order(page) != HPAGE_PMD_ORDER) + return ret; /* * Archs like ppc64 need additonal space to store information @@ -3608,7 +3769,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) /** * alloc_set_pte - setup new PTE entry for given page and add reverse page - * mapping. If needed, the fucntion allocates page table or use pre-allocated. + * mapping. If needed, the function allocates page table or use pre-allocated. * * @vmf: fault environment * @page: page to map |