summaryrefslogtreecommitdiff
path: root/mm/filemap.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/filemap.c')
-rw-r--r--mm/filemap.c425
1 files changed, 247 insertions, 178 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index a8c69c8c0a90..daef091d4c50 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -95,8 +95,8 @@
* ->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)
@@ -114,17 +114,14 @@ static void page_cache_tree_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
struct radix_tree_node *node;
- unsigned long index;
- unsigned int offset;
- unsigned int tag;
- void **slot;
-
- VM_BUG_ON(!PageLocked(page));
+ int i, nr = PageHuge(page) ? 1 : hpage_nr_pages(page);
- __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_PAGE(PageTail(page), page);
+ VM_BUG_ON_PAGE(nr != 1 && shadow, page);
if (shadow) {
- mapping->nrexceptional++;
+ mapping->nrexceptional += nr;
/*
* Make sure the nrexceptional update is committed before
* the nrpages update so that final truncate racing
@@ -133,43 +130,38 @@ static void page_cache_tree_delete(struct address_space *mapping,
*/
smp_wmb();
}
- mapping->nrpages--;
-
- if (!node) {
- /* Clear direct pointer tags in root node */
- mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;
- radix_tree_replace_slot(slot, shadow);
- return;
- }
+ mapping->nrpages -= nr;
- /* Clear tree tags for the removed page */
- index = page->index;
- offset = index & RADIX_TREE_MAP_MASK;
- for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
- if (test_bit(offset, node->tags[tag]))
- radix_tree_tag_clear(&mapping->page_tree, index, tag);
- }
-
- /* Delete page, swap shadow entry */
- radix_tree_replace_slot(slot, shadow);
- workingset_node_pages_dec(node);
- if (shadow)
- workingset_node_shadows_inc(node);
- else
- if (__radix_tree_delete_node(&mapping->page_tree, node))
+ for (i = 0; i < nr; i++) {
+ node = radix_tree_replace_clear_tags(&mapping->page_tree,
+ page->index + i, shadow);
+ if (!node) {
+ VM_BUG_ON_PAGE(nr != 1, page);
return;
+ }
- /*
- * Track node that only contains shadow entries.
- *
- * 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 (!workingset_node_pages(node) &&
- list_empty(&node->private_list)) {
- node->private_data = mapping;
- list_lru_add(&workingset_shadow_nodes, &node->private_list);
+ 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);
+ }
}
}
@@ -181,6 +173,7 @@ static void page_cache_tree_delete(struct address_space *mapping,
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);
/*
@@ -193,6 +186,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
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;
@@ -213,7 +207,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
* some other bad page check should catch it later.
*/
page_mapcount_reset(page);
- atomic_sub(mapcount, &page->_count);
+ page_ref_sub(page, mapcount);
}
}
@@ -224,9 +218,14 @@ void __delete_from_page_cache(struct page *page, void *shadow)
/* 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.
@@ -250,9 +249,8 @@ void __delete_from_page_cache(struct page *page, void *shadow)
*/
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));
@@ -265,11 +263,17 @@ void delete_from_page_cache(struct page *page)
if (freepage)
freepage(page);
- page_cache_release(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 */
@@ -281,6 +285,7 @@ static int filemap_check_errors(struct address_space *mapping)
ret = -EIO;
return ret;
}
+EXPORT_SYMBOL(filemap_check_errors);
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
@@ -352,8 +357,8 @@ EXPORT_SYMBOL(filemap_flush);
static int __filemap_fdatawait_range(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
- pgoff_t index = start_byte >> PAGE_CACHE_SHIFT;
- pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;
+ pgoff_t index = start_byte >> PAGE_SHIFT;
+ pgoff_t end = end_byte >> PAGE_SHIFT;
struct pagevec pvec;
int nr_pages;
int ret = 0;
@@ -550,7 +555,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
pgoff_t offset = old->index;
freepage = mapping->a_ops->freepage;
- page_cache_get(new);
+ get_page(new);
new->mapping = mapping;
new->index = offset;
@@ -564,15 +569,15 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
* 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();
if (freepage)
freepage(old);
- page_cache_release(old);
+ put_page(old);
}
return error;
@@ -597,14 +602,24 @@ static int page_cache_tree_insert(struct address_space *mapping,
if (!radix_tree_exceptional_entry(p))
return -EEXIST;
- if (WARN_ON(dax_mapping(mapping)))
- return -EINVAL;
-
- if (shadowp)
- *shadowp = p;
mapping->nrexceptional--;
- if (node)
- workingset_node_shadows_dec(node);
+ 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++;
@@ -651,7 +666,7 @@ static int __add_to_page_cache_locked(struct page *page,
return error;
}
- page_cache_get(page);
+ get_page(page);
page->mapping = mapping;
page->index = offset;
@@ -663,7 +678,7 @@ static int __add_to_page_cache_locked(struct page *page,
/* 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);
@@ -675,7 +690,7 @@ err_insert:
spin_unlock_irq(&mapping->tree_lock);
if (!huge)
mem_cgroup_cancel_charge(page, memcg, false);
- page_cache_release(page);
+ put_page(page);
return error;
}
@@ -713,8 +728,12 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
* The page might have been evicted from cache only
* recently, in which case it should be activated like
* any other repeatedly accessed page.
+ * The exception is pages getting rewritten; evicting other
+ * data from the working set, only to cache data that will
+ * get overwritten with something else, is a waste of memory.
*/
- if (shadow && workingset_refault(shadow)) {
+ if (!(gfp_mask & __GFP_WRITE) &&
+ shadow && workingset_refault(shadow)) {
SetPageActive(page);
workingset_activation(page);
} else
@@ -868,9 +887,9 @@ EXPORT_SYMBOL(end_page_writeback);
* 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, int op, int err)
{
- if (rw == READ) {
+ if (!op_is_write(op)) {
if (!err) {
SetPageUptodate(page);
} else {
@@ -878,7 +897,7 @@ void page_endio(struct page *page, int rw, int err)
SetPageError(page);
}
unlock_page(page);
- } else { /* rw == WRITE */
+ } else {
if (err) {
SetPageError(page);
if (page->mapping)
@@ -1054,7 +1073,7 @@ EXPORT_SYMBOL(page_cache_prev_hole);
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:
@@ -1074,8 +1093,16 @@ 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?
@@ -1083,7 +1110,7 @@ repeat:
* include/linux/pagemap.h for details.
*/
if (unlikely(page != *pagep)) {
- page_cache_release(page);
+ put_page(head);
goto repeat;
}
}
@@ -1119,12 +1146,12 @@ 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);
- page_cache_release(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;
}
@@ -1168,7 +1195,7 @@ repeat:
if (fgp_flags & FGP_LOCK) {
if (fgp_flags & FGP_NOWAIT) {
if (!trylock_page(page)) {
- page_cache_release(page);
+ put_page(page);
return NULL;
}
} else {
@@ -1178,7 +1205,7 @@ repeat:
/* Has the page been truncated? */
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
goto repeat;
}
VM_BUG_ON_PAGE(page->index != offset, page);
@@ -1209,7 +1236,7 @@ no_page:
err = add_to_page_cache_lru(page, mapping, offset,
gfp_mask & GFP_RECLAIM_MASK);
if (unlikely(err)) {
- page_cache_release(page);
+ put_page(page);
page = NULL;
if (err == -EEXIST)
goto repeat;
@@ -1256,7 +1283,7 @@ unsigned find_get_entries(struct address_space *mapping,
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))
@@ -1273,12 +1300,20 @@ repeat:
*/
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)) {
- page_cache_release(page);
+ put_page(head);
goto repeat;
}
export:
@@ -1319,7 +1354,7 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
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))
@@ -1338,12 +1373,19 @@ repeat:
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)) {
- page_cache_release(page);
+ put_page(head);
goto repeat;
}
@@ -1380,7 +1422,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
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 */
@@ -1400,12 +1442,19 @@ repeat:
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)) {
- page_cache_release(page);
+ put_page(head);
goto repeat;
}
@@ -1414,8 +1463,8 @@ 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) {
- page_cache_release(page);
+ if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
+ put_page(page);
break;
}
@@ -1452,7 +1501,7 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
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))
@@ -1477,12 +1526,19 @@ repeat:
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)) {
- page_cache_release(page);
+ put_page(head);
goto repeat;
}
@@ -1526,7 +1582,7 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
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))
@@ -1544,12 +1600,20 @@ repeat:
*/
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)) {
- page_cache_release(page);
+ put_page(head);
goto repeat;
}
export:
@@ -1610,11 +1674,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
unsigned int prev_offset;
int error = 0;
- index = *ppos >> PAGE_CACHE_SHIFT;
- prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT;
- prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1);
- last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
- offset = *ppos & ~PAGE_CACHE_MASK;
+ index = *ppos >> PAGE_SHIFT;
+ prev_index = ra->prev_pos >> PAGE_SHIFT;
+ prev_offset = ra->prev_pos & (PAGE_SIZE-1);
+ last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
+ offset = *ppos & ~PAGE_MASK;
for (;;) {
struct page *page;
@@ -1648,7 +1712,7 @@ find_page:
if (PageUptodate(page))
goto page_ok;
- if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
+ if (inode->i_blkbits == PAGE_SHIFT ||
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
if (!trylock_page(page))
@@ -1672,18 +1736,18 @@ page_ok:
*/
isize = i_size_read(inode);
- end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+ end_index = (isize - 1) >> PAGE_SHIFT;
if (unlikely(!isize || index > end_index)) {
- page_cache_release(page);
+ put_page(page);
goto out;
}
/* nr is the maximum number of bytes to copy from this page */
- nr = PAGE_CACHE_SIZE;
+ nr = PAGE_SIZE;
if (index == end_index) {
- nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+ nr = ((isize - 1) & ~PAGE_MASK) + 1;
if (nr <= offset) {
- page_cache_release(page);
+ put_page(page);
goto out;
}
}
@@ -1711,11 +1775,11 @@ page_ok:
ret = copy_page_to_iter(page, offset, nr, iter);
offset += ret;
- index += offset >> PAGE_CACHE_SHIFT;
- offset &= ~PAGE_CACHE_MASK;
+ index += offset >> PAGE_SHIFT;
+ offset &= ~PAGE_MASK;
prev_offset = offset;
- page_cache_release(page);
+ put_page(page);
written += ret;
if (!iov_iter_count(iter))
goto out;
@@ -1735,7 +1799,7 @@ page_not_up_to_date_locked:
/* Did it get truncated before we got the lock? */
if (!page->mapping) {
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
continue;
}
@@ -1757,7 +1821,7 @@ readpage:
if (unlikely(error)) {
if (error == AOP_TRUNCATED_PAGE) {
- page_cache_release(page);
+ put_page(page);
error = 0;
goto find_page;
}
@@ -1774,7 +1838,7 @@ readpage:
* invalidate_mapping_pages got it
*/
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
goto find_page;
}
unlock_page(page);
@@ -1789,7 +1853,7 @@ readpage:
readpage_error:
/* UHHUH! A synchronous read error occurred. Report it */
- page_cache_release(page);
+ put_page(page);
goto out;
no_cached_page:
@@ -1805,7 +1869,7 @@ no_cached_page:
error = add_to_page_cache_lru(page, mapping, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (error) {
- page_cache_release(page);
+ put_page(page);
if (error == -EEXIST) {
error = 0;
goto find_page;
@@ -1817,10 +1881,10 @@ no_cached_page:
out:
ra->prev_pos = prev_index;
- ra->prev_pos <<= PAGE_CACHE_SHIFT;
+ ra->prev_pos <<= PAGE_SHIFT;
ra->prev_pos |= prev_offset;
- *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
+ *ppos = ((loff_t)index << PAGE_SHIFT) + offset;
file_accessed(filp);
return written ? written : error;
}
@@ -1838,8 +1902,6 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
ssize_t retval = 0;
- loff_t *ppos = &iocb->ki_pos;
- loff_t pos = *ppos;
size_t count = iov_iter_count(iter);
if (!count)
@@ -1851,15 +1913,15 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
loff_t size;
size = i_size_read(inode);
- retval = filemap_write_and_wait_range(mapping, pos,
- pos + count - 1);
+ 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, pos);
+ retval = mapping->a_ops->direct_IO(iocb, &data);
}
if (retval > 0) {
- *ppos = pos + retval;
+ iocb->ki_pos += retval;
iov_iter_advance(iter, retval);
}
@@ -1872,14 +1934,14 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
* the rest of the read. Buffered reads will not work for
* DAX files, so don't bother trying.
*/
- if (retval < 0 || !iov_iter_count(iter) || *ppos >= size ||
+ if (retval < 0 || !iov_iter_count(iter) || iocb->ki_pos >= size ||
IS_DAX(inode)) {
file_accessed(file);
goto out;
}
}
- retval = do_generic_file_read(file, ppos, iter, retval);
+ retval = do_generic_file_read(file, &iocb->ki_pos, iter, retval);
out:
return retval;
}
@@ -1912,7 +1974,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
else if (ret == -EEXIST)
ret = 0; /* losing race to add is OK */
- page_cache_release(page);
+ put_page(page);
} while (ret == AOP_TRUNCATED_PAGE);
@@ -2022,8 +2084,8 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
loff_t size;
int ret = 0;
- size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
- if (offset >= size >> PAGE_CACHE_SHIFT)
+ size = round_up(i_size_read(inode), PAGE_SIZE);
+ if (offset >= size >> PAGE_SHIFT)
return VM_FAULT_SIGBUS;
/*
@@ -2049,7 +2111,7 @@ retry_find:
}
if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
- page_cache_release(page);
+ put_page(page);
return ret | VM_FAULT_RETRY;
}
@@ -2072,10 +2134,10 @@ retry_find:
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
*/
- size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
- if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) {
+ size = round_up(i_size_read(inode), PAGE_SIZE);
+ if (unlikely(offset >= size >> PAGE_SHIFT)) {
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
return VM_FAULT_SIGBUS;
}
@@ -2120,7 +2182,7 @@ page_not_uptodate:
if (!PageUptodate(page))
error = -EIO;
}
- page_cache_release(page);
+ put_page(page);
if (!error || error == AOP_TRUNCATED_PAGE)
goto retry_find;
@@ -2131,21 +2193,21 @@ page_not_uptodate:
}
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);
@@ -2159,12 +2221,19 @@ repeat:
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)) {
- page_cache_release(page);
+ put_page(head);
goto repeat;
}
@@ -2178,26 +2247,30 @@ repeat:
if (page->mapping != mapping || !PageUptodate(page))
goto unlock;
- size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE);
- if (page->index >= size >> PAGE_CACHE_SHIFT)
- goto unlock;
-
- pte = vmf->pte + page->index - vmf->pgoff;
- if (!pte_none(*pte))
+ size = round_up(i_size_read(mapping->host), PAGE_SIZE);
+ if (page->index >= size >> PAGE_SHIFT)
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:
unlock_page(page);
skip:
- page_cache_release(page);
+ 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();
@@ -2278,7 +2351,7 @@ static struct page *wait_on_page_read(struct page *page)
if (!IS_ERR(page)) {
wait_on_page_locked(page);
if (!PageUptodate(page)) {
- page_cache_release(page);
+ put_page(page);
page = ERR_PTR(-EIO);
}
}
@@ -2301,7 +2374,7 @@ repeat:
return ERR_PTR(-ENOMEM);
err = add_to_page_cache_lru(page, mapping, index, gfp);
if (unlikely(err)) {
- page_cache_release(page);
+ put_page(page);
if (err == -EEXIST)
goto repeat;
/* Presumably ENOMEM for radix tree node */
@@ -2311,7 +2384,7 @@ repeat:
filler:
err = filler(data, page);
if (err < 0) {
- page_cache_release(page);
+ put_page(page);
return ERR_PTR(err);
}
@@ -2364,7 +2437,7 @@ filler:
/* Case c or d, restart the operation */
if (!page->mapping) {
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
goto repeat;
}
@@ -2500,18 +2573,19 @@ int pagecache_write_end(struct file *file, struct address_space *mapping,
EXPORT_SYMBOL(pagecache_write_end);
ssize_t
-generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
+generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
+ loff_t pos = iocb->ki_pos;
ssize_t written;
size_t write_len;
pgoff_t end;
struct iov_iter data;
write_len = iov_iter_count(from);
- end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT;
+ end = (pos + write_len - 1) >> PAGE_SHIFT;
written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
if (written)
@@ -2525,7 +2599,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
*/
if (mapping->nrpages) {
written = invalidate_inode_pages2_range(mapping,
- pos >> PAGE_CACHE_SHIFT, end);
+ pos >> PAGE_SHIFT, end);
/*
* If a page can not be invalidated, return 0 to fall back
* to buffered write.
@@ -2538,7 +2612,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
}
data = *from;
- written = mapping->a_ops->direct_IO(iocb, &data, pos);
+ written = mapping->a_ops->direct_IO(iocb, &data);
/*
* Finally, try again to invalidate clean pages which might have been
@@ -2550,7 +2624,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
*/
if (mapping->nrpages) {
invalidate_inode_pages2_range(mapping,
- pos >> PAGE_CACHE_SHIFT, end);
+ pos >> PAGE_SHIFT, end);
}
if (written > 0) {
@@ -2575,7 +2649,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags)
{
struct page *page;
- int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT;
+ int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;
if (flags & AOP_FLAG_NOFS)
fgp_flags |= FGP_NOFS;
@@ -2611,8 +2685,8 @@ ssize_t generic_perform_write(struct file *file,
size_t copied; /* Bytes copied from user */
void *fsdata;
- offset = (pos & (PAGE_CACHE_SIZE - 1));
- bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
+ offset = (pos & (PAGE_SIZE - 1));
+ bytes = min_t(unsigned long, PAGE_SIZE - offset,
iov_iter_count(i));
again:
@@ -2665,7 +2739,7 @@ again:
* because not all segments in the iov can be copied at
* once without a pagefault.
*/
- bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
+ bytes = min_t(unsigned long, PAGE_SIZE - offset,
iov_iter_single_seg_count(i));
goto again;
}
@@ -2718,7 +2792,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (iocb->ki_flags & IOCB_DIRECT) {
loff_t pos, endbyte;
- written = generic_file_direct_write(iocb, from, iocb->ki_pos);
+ written = generic_file_direct_write(iocb, from);
/*
* If the write stopped short of completing, fall back to
* buffered writes. Some filesystems do this for writes to
@@ -2752,8 +2826,8 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
iocb->ki_pos = endbyte + 1;
written += status;
invalidate_mapping_pages(mapping,
- pos >> PAGE_CACHE_SHIFT,
- endbyte >> PAGE_CACHE_SHIFT);
+ pos >> PAGE_SHIFT,
+ endbyte >> PAGE_SHIFT);
} else {
/*
* We don't know how much we wrote, so just return
@@ -2792,13 +2866,8 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
ret = __generic_file_write_iter(iocb, from);
inode_unlock(inode);
- if (ret > 0) {
- ssize_t err;
-
- err = generic_write_sync(file, iocb->ki_pos - ret, ret);
- if (err < 0)
- ret = err;
- }
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
return ret;
}
EXPORT_SYMBOL(generic_file_write_iter);
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-09-25 01:02:21 +0000