* ->swap_lock (try_to_unmap_one)
* ->private_lock (try_to_unmap_one)
* ->tree_lock (try_to_unmap_one)
- * ->zone.lru_lock (follow_page->mark_page_accessed)
- * ->zone.lru_lock (check_pte_range->isolate_lru_page)
+ * ->zone_lru_lock(zone) (follow_page->mark_page_accessed)
+ * ->zone_lru_lock(zone) (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->tree_lock (page_remove_rmap->set_page_dirty)
* bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
* ->tasklist_lock (memory_failure, collect_procs_ao)
*/
+static int page_cache_tree_insert(struct address_space *mapping,
+ struct page *page, void **shadowp)
+{
+ struct radix_tree_node *node;
+ void **slot;
+ int error;
+
+ error = __radix_tree_create(&mapping->page_tree, page->index, 0,
+ &node, &slot);
+ if (error)
+ return error;
+ if (*slot) {
+ void *p;
+
+ p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+ if (!radix_tree_exceptional_entry(p))
+ return -EEXIST;
+
+ mapping->nrexceptional--;
+ if (!dax_mapping(mapping)) {
+ if (shadowp)
+ *shadowp = p;
+ if (node)
+ workingset_node_shadows_dec(node);
+ } else {
+ /* DAX can replace empty locked entry with a hole */
+ WARN_ON_ONCE(p !=
+ (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+ RADIX_DAX_ENTRY_LOCK));
+ /* DAX accounts exceptional entries as normal pages */
+ if (node)
+ workingset_node_pages_dec(node);
+ /* Wakeup waiters for exceptional entry lock */
+ dax_wake_mapping_entry_waiter(mapping, page->index,
+ false);
+ }
+ }
+ radix_tree_replace_slot(slot, page);
+ mapping->nrpages++;
+ if (node) {
+ workingset_node_pages_inc(node);
+ /*
+ * Don't track node that contains actual pages.
+ *
+ * Avoid acquiring the list_lru lock if already
+ * untracked. The list_empty() test is safe as
+ * node->private_list is protected by
+ * mapping->tree_lock.
+ */
+ if (!list_empty(&node->private_list))
+ list_lru_del(&workingset_shadow_nodes,
+ &node->private_list);
+ }
+ return 0;
+}
+
static void page_cache_tree_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
- struct radix_tree_node *node;
+ int i, nr = PageHuge(page) ? 1 : hpage_nr_pages(page);
+
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_PAGE(PageTail(page), page);
+ VM_BUG_ON_PAGE(nr != 1 && shadow, page);
+
+ for (i = 0; i < nr; i++) {
+ struct radix_tree_node *node;
+ void **slot;
+
+ __radix_tree_lookup(&mapping->page_tree, page->index + i,
+ &node, &slot);
+
+ radix_tree_clear_tags(&mapping->page_tree, node, slot);
+
+ if (!node) {
+ VM_BUG_ON_PAGE(nr != 1, page);
+ /*
+ * We need a node to properly account shadow
+ * entries. Don't plant any without. XXX
+ */
+ shadow = NULL;
+ }
- VM_BUG_ON(!PageLocked(page));
+ radix_tree_replace_slot(slot, shadow);
- node = radix_tree_replace_clear_tags(&mapping->page_tree, page->index,
- shadow);
+ if (!node)
+ break;
+
+ workingset_node_pages_dec(node);
+ if (shadow)
+ workingset_node_shadows_inc(node);
+ else
+ if (__radix_tree_delete_node(&mapping->page_tree, node))
+ continue;
+
+ /*
+ * Track node that only contains shadow entries. DAX mappings
+ * contain no shadow entries and may contain other exceptional
+ * entries so skip those.
+ *
+ * Avoid acquiring the list_lru lock if already tracked.
+ * The list_empty() test is safe as node->private_list is
+ * protected by mapping->tree_lock.
+ */
+ if (!dax_mapping(mapping) && !workingset_node_pages(node) &&
+ list_empty(&node->private_list)) {
+ node->private_data = mapping;
+ list_lru_add(&workingset_shadow_nodes,
+ &node->private_list);
+ }
+ }
if (shadow) {
- mapping->nrexceptional++;
+ mapping->nrexceptional += nr;
/*
* Make sure the nrexceptional update is committed before
* the nrpages update so that final truncate racing
*/
smp_wmb();
}
- mapping->nrpages--;
-
- if (!node)
- return;
-
- workingset_node_pages_dec(node);
- if (shadow)
- workingset_node_shadows_inc(node);
- else
- if (__radix_tree_delete_node(&mapping->page_tree, node))
- return;
-
- /*
- * Track node that only contains shadow entries. DAX mappings contain
- * no shadow entries and may contain other exceptional entries so skip
- * those.
- *
- * Avoid acquiring the list_lru lock if already tracked. The
- * list_empty() test is safe as node->private_list is
- * protected by mapping->tree_lock.
- */
- if (!dax_mapping(mapping) && !workingset_node_pages(node) &&
- list_empty(&node->private_list)) {
- node->private_data = mapping;
- list_lru_add(&workingset_shadow_nodes, &node->private_list);
- }
+ mapping->nrpages -= nr;
}
/*
void __delete_from_page_cache(struct page *page, void *shadow)
{
struct address_space *mapping = page->mapping;
+ int nr = hpage_nr_pages(page);
trace_mm_filemap_delete_from_page_cache(page);
/*
else
cleancache_invalidate_page(mapping, page);
+ VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(page_mapped(page), page);
if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
int mapcount;
/* hugetlb pages do not participate in page cache accounting. */
if (!PageHuge(page))
- __dec_zone_page_state(page, NR_FILE_PAGES);
- if (PageSwapBacked(page))
- __dec_zone_page_state(page, NR_SHMEM);
+ __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
+ if (PageSwapBacked(page)) {
+ __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
+ if (PageTransHuge(page))
+ __dec_node_page_state(page, NR_SHMEM_THPS);
+ } else {
+ VM_BUG_ON_PAGE(PageTransHuge(page) && !PageHuge(page), page);
+ }
/*
* At this point page must be either written or cleaned by truncate.
*/
void delete_from_page_cache(struct page *page)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = page_mapping(page);
unsigned long flags;
-
void (*freepage)(struct page *);
BUG_ON(!PageLocked(page));
if (freepage)
freepage(page);
- put_page(page);
+
+ if (PageTransHuge(page) && !PageHuge(page)) {
+ page_ref_sub(page, HPAGE_PMD_NR);
+ VM_BUG_ON_PAGE(page_count(page) <= 0, page);
+ } else {
+ put_page(page);
+ }
}
EXPORT_SYMBOL(delete_from_page_cache);
-static int filemap_check_errors(struct address_space *mapping)
+int filemap_check_errors(struct address_space *mapping)
{
int ret = 0;
/* Check for outstanding write errors */
ret = -EIO;
return ret;
}
+EXPORT_SYMBOL(filemap_check_errors);
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
spin_lock_irqsave(&mapping->tree_lock, flags);
__delete_from_page_cache(old, NULL);
- error = radix_tree_insert(&mapping->page_tree, offset, new);
+ error = page_cache_tree_insert(mapping, new, NULL);
BUG_ON(error);
- mapping->nrpages++;
/*
* hugetlb pages do not participate in page cache accounting.
*/
if (!PageHuge(new))
- __inc_zone_page_state(new, NR_FILE_PAGES);
+ __inc_node_page_state(new, NR_FILE_PAGES);
if (PageSwapBacked(new))
- __inc_zone_page_state(new, NR_SHMEM);
+ __inc_node_page_state(new, NR_SHMEM);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
mem_cgroup_migrate(old, new);
radix_tree_preload_end();
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
-static int page_cache_tree_insert(struct address_space *mapping,
- struct page *page, void **shadowp)
-{
- struct radix_tree_node *node;
- void **slot;
- int error;
-
- error = __radix_tree_create(&mapping->page_tree, page->index, 0,
- &node, &slot);
- if (error)
- return error;
- if (*slot) {
- void *p;
-
- p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
- if (!radix_tree_exceptional_entry(p))
- return -EEXIST;
-
- mapping->nrexceptional--;
- if (!dax_mapping(mapping)) {
- if (shadowp)
- *shadowp = p;
- if (node)
- workingset_node_shadows_dec(node);
- } else {
- /* DAX can replace empty locked entry with a hole */
- WARN_ON_ONCE(p !=
- (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
- RADIX_DAX_ENTRY_LOCK));
- /* DAX accounts exceptional entries as normal pages */
- if (node)
- workingset_node_pages_dec(node);
- /* Wakeup waiters for exceptional entry lock */
- dax_wake_mapping_entry_waiter(mapping, page->index,
- false);
- }
- }
- radix_tree_replace_slot(slot, page);
- mapping->nrpages++;
- if (node) {
- workingset_node_pages_inc(node);
- /*
- * Don't track node that contains actual pages.
- *
- * Avoid acquiring the list_lru lock if already
- * untracked. The list_empty() test is safe as
- * node->private_list is protected by
- * mapping->tree_lock.
- */
- if (!list_empty(&node->private_list))
- list_lru_del(&workingset_shadow_nodes,
- &node->private_list);
- }
- return 0;
-}
-
static int __add_to_page_cache_locked(struct page *page,
struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask,
/* hugetlb pages do not participate in page cache accounting. */
if (!huge)
- __inc_zone_page_state(page, NR_FILE_PAGES);
+ __inc_node_page_state(page, NR_FILE_PAGES);
spin_unlock_irq(&mapping->tree_lock);
if (!huge)
mem_cgroup_commit_charge(page, memcg, false, false);
* After completing I/O on a page, call this routine to update the page
* flags appropriately
*/
-void page_endio(struct page *page, int rw, int err)
+void page_endio(struct page *page, bool is_write, int err)
{
- if (rw == READ) {
+ if (!is_write) {
if (!err) {
SetPageUptodate(page);
} else {
SetPageError(page);
}
unlock_page(page);
- } else { /* rw == WRITE */
+ } else {
if (err) {
SetPageError(page);
if (page->mapping)
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
{
void **pagep;
- struct page *page;
+ struct page *head, *page;
rcu_read_lock();
repeat:
*/
goto out;
}
- if (!page_cache_get_speculative(page))
+
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
goto repeat;
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
+ goto repeat;
+ }
+
/*
* Has the page moved?
* This is part of the lockless pagecache protocol. See
* include/linux/pagemap.h for details.
*/
if (unlikely(page != *pagep)) {
- put_page(page);
+ put_page(head);
goto repeat;
}
}
if (page && !radix_tree_exception(page)) {
lock_page(page);
/* Has the page been truncated? */
- if (unlikely(page->mapping != mapping)) {
+ if (unlikely(page_mapping(page) != mapping)) {
unlock_page(page);
put_page(page);
goto repeat;
}
- VM_BUG_ON_PAGE(page->index != offset, page);
+ VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
}
return page;
}
rcu_read_lock();
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
- struct page *page;
+ struct page *head, *page;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
*/
goto export;
}
- if (!page_cache_get_speculative(page))
+
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
+ goto repeat;
+
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
goto repeat;
+ }
/* Has the page moved? */
if (unlikely(page != *slot)) {
- put_page(page);
+ put_page(head);
goto repeat;
}
export:
rcu_read_lock();
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
- struct page *page;
+ struct page *head, *page;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
continue;
}
- if (!page_cache_get_speculative(page))
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
goto repeat;
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
+ goto repeat;
+ }
+
/* Has the page moved? */
if (unlikely(page != *slot)) {
- put_page(page);
+ put_page(head);
goto repeat;
}
rcu_read_lock();
radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) {
- struct page *page;
+ struct page *head, *page;
repeat:
page = radix_tree_deref_slot(slot);
/* The hole, there no reason to continue */
break;
}
- if (!page_cache_get_speculative(page))
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
goto repeat;
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
+ goto repeat;
+ }
+
/* Has the page moved? */
if (unlikely(page != *slot)) {
- put_page(page);
+ put_page(head);
goto repeat;
}
* otherwise we can get both false positives and false
* negatives, which is just confusing to the caller.
*/
- if (page->mapping == NULL || page->index != iter.index) {
+ if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
put_page(page);
break;
}
rcu_read_lock();
radix_tree_for_each_tagged(slot, &mapping->page_tree,
&iter, *index, tag) {
- struct page *page;
+ struct page *head, *page;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
continue;
}
- if (!page_cache_get_speculative(page))
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
goto repeat;
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
+ goto repeat;
+ }
+
/* Has the page moved? */
if (unlikely(page != *slot)) {
- put_page(page);
+ put_page(head);
goto repeat;
}
rcu_read_lock();
radix_tree_for_each_tagged(slot, &mapping->page_tree,
&iter, start, tag) {
- struct page *page;
+ struct page *head, *page;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
*/
goto export;
}
- if (!page_cache_get_speculative(page))
+
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
goto repeat;
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
+ goto repeat;
+ }
+
/* Has the page moved? */
if (unlikely(page != *slot)) {
- put_page(page);
+ put_page(head);
goto repeat;
}
export:
* wait_on_page_locked is used to avoid unnecessarily
* serialisations and why it's safe.
*/
- wait_on_page_locked_killable(page);
+ error = wait_on_page_locked_killable(page);
+ if (unlikely(error))
+ goto readpage_error;
if (PageUptodate(page))
goto page_ok;
if (iocb->ki_flags & IOCB_DIRECT) {
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
+ struct iov_iter data = *iter;
loff_t size;
size = i_size_read(inode);
retval = filemap_write_and_wait_range(mapping, iocb->ki_pos,
iocb->ki_pos + count - 1);
- if (!retval) {
- struct iov_iter data = *iter;
- retval = mapping->a_ops->direct_IO(iocb, &data);
- }
+ if (retval < 0)
+ goto out;
+
+ file_accessed(file);
+ retval = mapping->a_ops->direct_IO(iocb, &data);
if (retval > 0) {
iocb->ki_pos += retval;
iov_iter_advance(iter, retval);
* DAX files, so don't bother trying.
*/
if (retval < 0 || !iov_iter_count(iter) || iocb->ki_pos >= size ||
- IS_DAX(inode)) {
- file_accessed(file);
+ IS_DAX(inode))
goto out;
- }
}
retval = do_generic_file_read(file, &iocb->ki_pos, iter, retval);
}
EXPORT_SYMBOL(filemap_fault);
-void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+void filemap_map_pages(struct fault_env *fe,
+ pgoff_t start_pgoff, pgoff_t end_pgoff)
{
struct radix_tree_iter iter;
void **slot;
- struct file *file = vma->vm_file;
+ struct file *file = fe->vma->vm_file;
struct address_space *mapping = file->f_mapping;
+ pgoff_t last_pgoff = start_pgoff;
loff_t size;
- struct page *page;
- unsigned long address = (unsigned long) vmf->virtual_address;
- unsigned long addr;
- pte_t *pte;
+ struct page *head, *page;
rcu_read_lock();
- radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) {
- if (iter.index > vmf->max_pgoff)
+ radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
+ start_pgoff) {
+ if (iter.index > end_pgoff)
break;
repeat:
page = radix_tree_deref_slot(slot);
goto next;
}
- if (!page_cache_get_speculative(page))
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
goto repeat;
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
+ goto repeat;
+ }
+
/* Has the page moved? */
if (unlikely(page != *slot)) {
- put_page(page);
+ put_page(head);
goto repeat;
}
if (page->index >= size >> PAGE_SHIFT)
goto unlock;
- pte = vmf->pte + page->index - vmf->pgoff;
- if (!pte_none(*pte))
- goto unlock;
-
if (file->f_ra.mmap_miss > 0)
file->f_ra.mmap_miss--;
- addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
- do_set_pte(vma, addr, page, pte, false, false);
+
+ fe->address += (iter.index - last_pgoff) << PAGE_SHIFT;
+ if (fe->pte)
+ fe->pte += iter.index - last_pgoff;
+ last_pgoff = iter.index;
+ if (alloc_set_pte(fe, NULL, page))
+ goto unlock;
unlock_page(page);
goto next;
unlock:
skip:
put_page(page);
next:
- if (iter.index == vmf->max_pgoff)
+ /* Huge page is mapped? No need to proceed. */
+ if (pmd_trans_huge(*fe->pmd))
+ break;
+ if (iter.index == end_pgoff)
break;
}
rcu_read_unlock();
projects / cascardo / linux.git / blobdiff