return pfn_to_page(pfn);
}
+struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr,
+ pte_t pte)
+{
+ struct page *page = vm_normal_page(vma, addr, pte);
+
+ if (page)
+ return page_folio(page);
+ return NULL;
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t pmd)
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, struct page *page)
+ struct folio **prealloc, struct page *page)
{
- struct page *new_page;
+ struct folio *new_folio;
pte_t pte;
- new_page = *prealloc;
- if (!new_page)
+ new_folio = *prealloc;
+ if (!new_folio)
return -EAGAIN;
/*
* 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);
- lru_cache_add_inactive_or_unevictable(new_page, dst_vma);
- rss[mm_counter(new_page)]++;
+ copy_user_highpage(&new_folio->page, page, addr, src_vma);
+ __folio_mark_uptodate(new_folio);
+ folio_add_new_anon_rmap(new_folio, dst_vma, addr);
+ folio_add_lru_vma(new_folio, dst_vma);
+ rss[MM_ANONPAGES]++;
/* All done, just insert the new page copy in the child */
- pte = mk_pte(new_page, dst_vma->vm_page_prot);
+ pte = mk_pte(&new_folio->page, dst_vma->vm_page_prot);
pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
if (userfaultfd_pte_wp(dst_vma, *src_pte))
/* Uffd-wp needs to be delivered to dest pte as well */
- pte = pte_wrprotect(pte_mkuffd_wp(pte));
+ pte = pte_mkuffd_wp(pte);
set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
return 0;
}
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 folio **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;
+ struct folio *folio;
page = vm_normal_page(src_vma, addr, pte);
- if (page && PageAnon(page)) {
+ if (page)
+ folio = page_folio(page);
+ if (page && folio_test_anon(folio)) {
/*
* If this page may have been pinned by the parent process,
* copy the page immediately for the child so that we'll always
* guarantee the pinned page won't be randomly replaced in the
* future.
*/
- get_page(page);
+ folio_get(folio);
if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) {
- /* Page maybe pinned, we have to copy. */
- put_page(page);
+ /* Page may be pinned, we have to copy. */
+ folio_put(folio);
return copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
addr, rss, prealloc, page);
}
- rss[mm_counter(page)]++;
+ rss[MM_ANONPAGES]++;
} else if (page) {
- get_page(page);
+ folio_get(folio);
page_dup_file_rmap(page, false);
- rss[mm_counter(page)]++;
+ rss[mm_counter_file(page)]++;
}
/*
ptep_set_wrprotect(src_mm, addr, src_pte);
pte = pte_wrprotect(pte);
}
- VM_BUG_ON(page && PageAnon(page) && PageAnonExclusive(page));
+ VM_BUG_ON(page && folio_test_anon(folio) && PageAnonExclusive(page));
/*
* If it's a shared mapping, mark it clean in
return 0;
}
-static inline struct page *
-page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
- unsigned long addr)
+static inline struct folio *page_copy_prealloc(struct mm_struct *src_mm,
+ struct vm_area_struct *vma, unsigned long addr)
{
- struct page *new_page;
+ struct folio *new_folio;
- new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr);
- if (!new_page)
+ new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false);
+ if (!new_folio)
return NULL;
- if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) {
- put_page(new_page);
+ if (mem_cgroup_charge(new_folio, src_mm, GFP_KERNEL)) {
+ folio_put(new_folio);
return NULL;
}
- cgroup_throttle_swaprate(new_page, GFP_KERNEL);
+ cgroup_throttle_swaprate(&new_folio->page, GFP_KERNEL);
- return new_page;
+ return new_folio;
}
static int
int progress, ret = 0;
int rss[NR_MM_COUNTERS];
swp_entry_t entry = (swp_entry_t){0};
- struct page *prealloc = NULL;
+ struct folio *prealloc = NULL;
again:
progress = 0;
* will allocate page according to address). This
* could only happen if one pinned pte changed.
*/
- put_page(prealloc);
+ folio_put(prealloc);
prealloc = NULL;
}
progress += 8;
goto again;
out:
if (unlikely(prealloc))
- put_page(prealloc);
+ folio_put(prealloc);
return ret;
}
if (is_cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
- 0, src_vma, src_mm, addr, end);
+ 0, src_mm, addr, end);
mmu_notifier_invalidate_range_start(&range);
/*
* Disabling preemption is not needed for the write side, as
force_flush = 1;
}
}
- if (pte_young(ptent) &&
- likely(!(vma->vm_flags & VM_SEQ_READ)))
+ if (pte_young(ptent) && likely(vma_has_recency(vma)))
mark_page_accessed(page);
}
rss[mm_counter(page)]--;
static void unmap_single_vma(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr,
- struct zap_details *details)
+ struct zap_details *details, bool mm_wr_locked)
{
unsigned long start = max(vma->vm_start, start_addr);
unsigned long end;
uprobe_munmap(vma, start, end);
if (unlikely(vma->vm_flags & VM_PFNMAP))
- untrack_pfn(vma, 0, 0);
+ untrack_pfn(vma, 0, 0, mm_wr_locked);
if (start != end) {
if (unlikely(is_vm_hugetlb_page(vma))) {
*/
void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
struct vm_area_struct *vma, unsigned long start_addr,
- unsigned long end_addr)
+ unsigned long end_addr, bool mm_wr_locked)
{
struct mmu_notifier_range range;
struct zap_details details = {
};
MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
- mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm,
start_addr, end_addr);
mmu_notifier_invalidate_range_start(&range);
do {
- unmap_single_vma(tlb, vma, start_addr, end_addr, &details);
+ unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+ mm_wr_locked);
} while ((vma = mas_find(&mas, end_addr - 1)) != NULL);
mmu_notifier_invalidate_range_end(&range);
}
-/**
- * zap_page_range - remove user pages in a given range
- * @vma: vm_area_struct holding the applicable pages
- * @start: starting address of pages to zap
- * @size: number of bytes to zap
- *
- * Caller must protect the VMA list
- */
-void zap_page_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long size)
-{
- struct maple_tree *mt = &vma->vm_mm->mm_mt;
- unsigned long end = start + size;
- struct mmu_notifier_range range;
- struct mmu_gather tlb;
- MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
-
- lru_add_drain();
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
- start, start + size);
- tlb_gather_mmu(&tlb, vma->vm_mm);
- update_hiwater_rss(vma->vm_mm);
- mmu_notifier_invalidate_range_start(&range);
- do {
- unmap_single_vma(&tlb, vma, start, range.end, NULL);
- } while ((vma = mas_find(&mas, end - 1)) != NULL);
- mmu_notifier_invalidate_range_end(&range);
- tlb_finish_mmu(&tlb);
-}
-
/**
* zap_page_range_single - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
struct mmu_gather tlb;
lru_add_drain();
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address, end);
if (is_vm_hugetlb_page(vma))
adjust_range_if_pmd_sharing_possible(vma, &range.start,
* unmap 'address-end' not 'range.start-range.end' as range
* could have been expanded for hugetlb pmd sharing.
*/
- unmap_single_vma(&tlb, vma, address, end, details);
+ unmap_single_vma(&tlb, vma, address, end, details, false);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
}
if (!(vma->vm_flags & VM_MIXEDMAP)) {
BUG_ON(mmap_read_trylock(vma->vm_mm));
BUG_ON(vma->vm_flags & VM_PFNMAP);
- vma->vm_flags |= VM_MIXEDMAP;
+ vm_flags_set(vma, VM_MIXEDMAP);
}
/* Defer page refcount checking till we're about to map that page. */
return insert_pages(vma, addr, pages, num, vma->vm_page_prot);
if (!(vma->vm_flags & VM_MIXEDMAP)) {
BUG_ON(mmap_read_trylock(vma->vm_mm));
BUG_ON(vma->vm_flags & VM_PFNMAP);
- vma->vm_flags |= VM_MIXEDMAP;
+ vm_flags_set(vma, VM_MIXEDMAP);
}
return insert_page(vma, addr, page, vma->vm_page_prot);
}
vma->vm_pgoff = pfn;
}
- vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+ vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
if (err)
- untrack_pfn(vma, pfn, PAGE_ALIGN(size));
+ untrack_pfn(vma, pfn, PAGE_ALIGN(size), true);
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
- struct page *old_page = vmf->page;
- struct page *new_page = NULL;
+ struct folio *old_folio = NULL;
+ struct folio *new_folio = NULL;
pte_t entry;
int page_copied = 0;
struct mmu_notifier_range range;
delayacct_wpcopy_start();
+ if (vmf->page)
+ old_folio = page_folio(vmf->page);
if (unlikely(anon_vma_prepare(vma)))
goto oom;
if (is_zero_pfn(pte_pfn(vmf->orig_pte))) {
- new_page = alloc_zeroed_user_highpage_movable(vma,
- vmf->address);
- if (!new_page)
+ new_folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
+ if (!new_folio)
goto oom;
} else {
- new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
- vmf->address);
- if (!new_page)
+ new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
+ vmf->address, false);
+ if (!new_folio)
goto oom;
- ret = __wp_page_copy_user(new_page, old_page, vmf);
+ ret = __wp_page_copy_user(&new_folio->page, vmf->page, vmf);
if (ret) {
/*
* COW failed, if the fault was solved by other,
* from the second attempt.
* The -EHWPOISON case will not be retried.
*/
- put_page(new_page);
- if (old_page)
- put_page(old_page);
+ folio_put(new_folio);
+ if (old_folio)
+ folio_put(old_folio);
delayacct_wpcopy_end();
return ret == -EHWPOISON ? VM_FAULT_HWPOISON : 0;
}
- kmsan_copy_page_meta(new_page, old_page);
+ kmsan_copy_page_meta(&new_folio->page, vmf->page);
}
- if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL))
+ if (mem_cgroup_charge(new_folio, mm, GFP_KERNEL))
goto oom_free_new;
- cgroup_throttle_swaprate(new_page, GFP_KERNEL);
+ cgroup_throttle_swaprate(&new_folio->page, GFP_KERNEL);
- __SetPageUptodate(new_page);
+ __folio_mark_uptodate(new_folio);
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE);
mmu_notifier_invalidate_range_start(&range);
*/
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
- if (old_page) {
- if (!PageAnon(old_page)) {
- dec_mm_counter(mm, mm_counter_file(old_page));
+ if (old_folio) {
+ if (!folio_test_anon(old_folio)) {
+ dec_mm_counter(mm, mm_counter_file(&old_folio->page));
inc_mm_counter(mm, MM_ANONPAGES);
}
} else {
inc_mm_counter(mm, MM_ANONPAGES);
}
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
- entry = mk_pte(new_page, vma->vm_page_prot);
+ entry = mk_pte(&new_folio->page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
if (unlikely(unshare)) {
if (pte_soft_dirty(vmf->orig_pte))
* some TLBs while the old PTE remains in others.
*/
ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
- page_add_new_anon_rmap(new_page, vma, vmf->address);
- lru_cache_add_inactive_or_unevictable(new_page, vma);
+ folio_add_new_anon_rmap(new_folio, vma, vmf->address);
+ folio_add_lru_vma(new_folio, vma);
/*
* We call the notify macro here because, when using secondary
* mmu page tables (such as kvm shadow page tables), we want the
BUG_ON(unshare && pte_write(entry));
set_pte_at_notify(mm, vmf->address, vmf->pte, entry);
update_mmu_cache(vma, vmf->address, vmf->pte);
- if (old_page) {
+ if (old_folio) {
/*
* Only after switching the pte to the new page may
* we remove the mapcount here. Otherwise another
* mapcount is visible. So transitively, TLBs to
* old page will be flushed before it can be reused.
*/
- page_remove_rmap(old_page, vma, false);
+ page_remove_rmap(vmf->page, vma, false);
}
/* Free the old page.. */
- new_page = old_page;
+ new_folio = old_folio;
page_copied = 1;
} else {
update_mmu_tlb(vma, vmf->address, vmf->pte);
}
- if (new_page)
- put_page(new_page);
+ if (new_folio)
+ folio_put(new_folio);
pte_unmap_unlock(vmf->pte, vmf->ptl);
/*
* the above ptep_clear_flush_notify() did already call it.
*/
mmu_notifier_invalidate_range_only_end(&range);
- if (old_page) {
+ if (old_folio) {
if (page_copied)
- free_swap_cache(old_page);
- put_page(old_page);
+ free_swap_cache(&old_folio->page);
+ folio_put(old_folio);
}
delayacct_wpcopy_end();
return 0;
oom_free_new:
- put_page(new_page);
+ folio_put(new_folio);
oom:
- if (old_page)
- put_page(old_page);
+ if (old_folio)
+ folio_put(old_folio);
delayacct_wpcopy_end();
return VM_FAULT_OOM;
if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags))
return VM_FAULT_RETRY;
- mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
+ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
vma->vm_mm, vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
mmu_notifier_invalidate_range_start(&range);
{
/*
* Just in case there're leftover special ptes even after the region
- * got unregistered - we can simply clear them. We can also do that
- * proactively when e.g. when we do UFFDIO_UNREGISTER upon some uffd-wp
- * ranges, but it should be more efficient to be done lazily here.
+ * got unregistered - we can simply clear them.
*/
if (unlikely(!userfaultfd_wp(vmf->vma) || vma_is_anonymous(vmf->vma)))
return pte_marker_clear(vmf);
if (unlikely(!page)) {
ret = VM_FAULT_OOM;
goto out_page;
+ } else if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+ ret = VM_FAULT_HWPOISON;
+ goto out_page;
}
folio = page_folio(page);
* the swap entry concurrently) for certainly exclusive pages.
*/
if (!folio_test_ksm(folio)) {
- /*
- * Note that pte_swp_exclusive() == false for architectures
- * without __HAVE_ARCH_PTE_SWP_EXCLUSIVE.
- */
exclusive = pte_swp_exclusive(vmf->orig_pte);
if (folio != swapcache) {
/*
flush_icache_page(vma, page);
if (pte_swp_soft_dirty(vmf->orig_pte))
pte = pte_mksoft_dirty(pte);
- if (pte_swp_uffd_wp(vmf->orig_pte)) {
+ if (pte_swp_uffd_wp(vmf->orig_pte))
pte = pte_mkuffd_wp(pte);
- pte = pte_wrprotect(pte);
- }
vmf->orig_pte = pte;
/* ksm created a completely new copy */
static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
- struct page *page;
+ struct folio *folio;
vm_fault_t ret = 0;
pte_t entry;
/* Allocate our own private page. */
if (unlikely(anon_vma_prepare(vma)))
goto oom;
- page = alloc_zeroed_user_highpage_movable(vma, vmf->address);
- if (!page)
+ folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
+ if (!folio)
goto oom;
- if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
+ if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL))
goto oom_free_page;
- cgroup_throttle_swaprate(page, GFP_KERNEL);
+ cgroup_throttle_swaprate(&folio->page, GFP_KERNEL);
/*
- * The memory barrier inside __SetPageUptodate makes sure that
+ * The memory barrier inside __folio_mark_uptodate makes sure that
* preceding stores to the page contents become visible before
* the set_pte_at() write.
*/
- __SetPageUptodate(page);
+ __folio_mark_uptodate(folio);
- entry = mk_pte(page, vma->vm_page_prot);
+ entry = mk_pte(&folio->page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
- put_page(page);
+ folio_put(folio);
return handle_userfault(vmf, VM_UFFD_MISSING);
}
inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
- page_add_new_anon_rmap(page, vma, vmf->address);
- lru_cache_add_inactive_or_unevictable(page, vma);
+ folio_add_new_anon_rmap(folio, vma, vmf->address);
+ folio_add_lru_vma(folio, vma);
setpte:
set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
release:
- put_page(page);
+ folio_put(folio);
goto unlock;
oom_free_page:
- put_page(page);
+ folio_put(folio);
oom:
return VM_FAULT_OOM;
}
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (unlikely(uffd_wp))
- entry = pte_mkuffd_wp(pte_wrprotect(entry));
+ entry = pte_mkuffd_wp(entry);
/* copy-on-write page */
if (write && !(vma->vm_flags & VM_SHARED)) {
inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
#ifdef CONFIG_LRU_GEN
static void lru_gen_enter_fault(struct vm_area_struct *vma)
{
- /* the LRU algorithm doesn't apply to sequential or random reads */
- current->in_lru_fault = !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ));
+ /* the LRU algorithm only applies to accesses with recency */
+ current->in_lru_fault = vma_has_recency(vma);
}
static void lru_gen_exit_fault(void)
git.samba.org / sfrench / cifs-2.6.git / blobdiff