#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
#include <linux/memcontrol.h>
#include <linux/cleancache.h>
+#include <linux/rmap.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
* ->mmap_sem
* ->lock_page (access_process_vm)
*
- * ->i_mutex (generic_file_buffered_write)
+ * ->i_mutex (generic_perform_write)
* ->mmap_sem (fault_in_pages_readable->do_page_fault)
*
* bdi->wb.list_lock
* ->tasklist_lock (memory_failure, collect_procs_ao)
*/
+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));
+
+ __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
+
+ if (shadow) {
+ mapping->nrshadows++;
+ /*
+ * Make sure the nrshadows update is committed before
+ * the nrpages update so that final truncate racing
+ * with reclaim does not see both counters 0 at the
+ * same time and miss a shadow entry.
+ */
+ 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;
+ }
+
+ /* 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))
+ 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);
+ }
+}
+
/*
* Delete a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
* is safe. The caller must hold the mapping's tree_lock.
*/
-void __delete_from_page_cache(struct page *page)
+void __delete_from_page_cache(struct page *page, void *shadow)
{
struct address_space *mapping = page->mapping;
else
cleancache_invalidate_page(mapping, page);
- radix_tree_delete(&mapping->page_tree, page->index);
+ page_cache_tree_delete(mapping, page, shadow);
+
page->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
- mapping->nrpages--;
+
__dec_zone_page_state(page, NR_FILE_PAGES);
if (PageSwapBacked(page))
__dec_zone_page_state(page, NR_SHMEM);
freepage = mapping->a_ops->freepage;
spin_lock_irq(&mapping->tree_lock);
- __delete_from_page_cache(page);
+ __delete_from_page_cache(page, NULL);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
new->index = offset;
spin_lock_irq(&mapping->tree_lock);
- __delete_from_page_cache(old);
+ __delete_from_page_cache(old, NULL);
error = radix_tree_insert(&mapping->page_tree, offset, new);
BUG_ON(error);
mapping->nrpages++;
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
-/**
- * add_to_page_cache_locked - add a locked page to the pagecache
- * @page: page to add
- * @mapping: the page's address_space
- * @offset: page index
- * @gfp_mask: page allocation mode
- *
- * This function is used to add a page to the pagecache. It must be locked.
- * This function does not add the page to the LRU. The caller must do that.
- */
-int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
+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,
+ &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;
+ if (shadowp)
+ *shadowp = p;
+ mapping->nrshadows--;
+ if (node)
+ workingset_node_shadows_dec(node);
+ }
+ 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,
+ void **shadowp)
{
int error;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapBacked(page), page);
- error = mem_cgroup_cache_charge(page, current->mm,
+ error = mem_cgroup_charge_file(page, current->mm,
gfp_mask & GFP_RECLAIM_MASK);
if (error)
return error;
page->index = offset;
spin_lock_irq(&mapping->tree_lock);
- error = radix_tree_insert(&mapping->page_tree, offset, page);
+ error = page_cache_tree_insert(mapping, page, shadowp);
radix_tree_preload_end();
if (unlikely(error))
goto err_insert;
- mapping->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
spin_unlock_irq(&mapping->tree_lock);
trace_mm_filemap_add_to_page_cache(page);
page_cache_release(page);
return error;
}
+
+/**
+ * add_to_page_cache_locked - add a locked page to the pagecache
+ * @page: page to add
+ * @mapping: the page's address_space
+ * @offset: page index
+ * @gfp_mask: page allocation mode
+ *
+ * This function is used to add a page to the pagecache. It must be locked.
+ * This function does not add the page to the LRU. The caller must do that.
+ */
+int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
+ pgoff_t offset, gfp_t gfp_mask)
+{
+ return __add_to_page_cache_locked(page, mapping, offset,
+ gfp_mask, NULL);
+}
EXPORT_SYMBOL(add_to_page_cache_locked);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
+ void *shadow = NULL;
int ret;
- ret = add_to_page_cache(page, mapping, offset, gfp_mask);
- if (ret == 0)
- lru_cache_add_file(page);
+ __set_page_locked(page);
+ ret = __add_to_page_cache_locked(page, mapping, offset,
+ gfp_mask, &shadow);
+ if (unlikely(ret))
+ __clear_page_locked(page);
+ else {
+ /*
+ * The page might have been evicted from cache only
+ * recently, in which case it should be activated like
+ * any other repeatedly accessed page.
+ */
+ if (shadow && workingset_refault(shadow)) {
+ SetPageActive(page);
+ workingset_activation(page);
+ } else
+ ClearPageActive(page);
+ lru_cache_add(page);
+ }
return ret;
}
EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
if (cpuset_do_page_mem_spread()) {
unsigned int cpuset_mems_cookie;
do {
- cpuset_mems_cookie = get_mems_allowed();
+ cpuset_mems_cookie = read_mems_allowed_begin();
n = cpuset_mem_spread_node();
page = alloc_pages_exact_node(n, gfp, 0);
- } while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+ } while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
return page;
}
}
/**
- * find_get_page - find and get a page reference
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+ pgoff_t index, unsigned long max_scan)
+{
+ unsigned long i;
+
+ for (i = 0; i < max_scan; i++) {
+ struct page *page;
+
+ page = radix_tree_lookup(&mapping->page_tree, index);
+ if (!page || radix_tree_exceptional_entry(page))
+ break;
+ index++;
+ if (index == 0)
+ break;
+ }
+
+ return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
+ * page_cache_prev_hole - find the prev hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search backwards in the range [max(index-max_scan+1, 0), index] for
+ * the first hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'index - return >=
+ * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
+ * will be returned.
+ *
+ * page_cache_prev_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 10, then subsequently a hole is created at
+ * index 5, page_cache_prev_hole covering both indexes may return 5 if
+ * called under rcu_read_lock.
+ */
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+ pgoff_t index, unsigned long max_scan)
+{
+ unsigned long i;
+
+ for (i = 0; i < max_scan; i++) {
+ struct page *page;
+
+ page = radix_tree_lookup(&mapping->page_tree, index);
+ if (!page || radix_tree_exceptional_entry(page))
+ break;
+ index--;
+ if (index == ULONG_MAX)
+ break;
+ }
+
+ return index;
+}
+EXPORT_SYMBOL(page_cache_prev_hole);
+
+/**
+ * find_get_entry - find and get a page cache entry
* @mapping: the address_space to search
- * @offset: the page index
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned with an increased refcount.
*
- * Is there a pagecache struct page at the given (mapping, offset) tuple?
- * If yes, increment its refcount and return it; if no, return NULL.
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
*/
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
{
void **pagep;
struct page *page;
return page;
}
-EXPORT_SYMBOL(find_get_page);
+EXPORT_SYMBOL(find_get_entry);
/**
- * find_lock_page - locate, pin and lock a pagecache page
+ * find_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
*
- * Locates the desired pagecache page, locks it, increments its reference
- * count and returns its address.
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned with an increased refcount.
*
- * Returns zero if the page was not present. find_lock_page() may sleep.
+ * Otherwise, %NULL is returned.
*/
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+{
+ struct page *page = find_get_entry(mapping, offset);
+
+ if (radix_tree_exceptional_entry(page))
+ page = NULL;
+ return page;
+}
+EXPORT_SYMBOL(find_get_page);
+
+/**
+ * find_lock_entry - locate, pin and lock a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_entry() may sleep.
+ */
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
{
struct page *page;
repeat:
- page = find_get_page(mapping, offset);
+ page = find_get_entry(mapping, offset);
if (page && !radix_tree_exception(page)) {
lock_page(page);
/* Has the page been truncated? */
}
return page;
}
+EXPORT_SYMBOL(find_lock_entry);
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_page() may sleep.
+ */
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+{
+ struct page *page = find_lock_entry(mapping, offset);
+
+ if (radix_tree_exceptional_entry(page))
+ page = NULL;
+ return page;
+}
EXPORT_SYMBOL(find_lock_page);
/**
* @index: the page's index into the mapping
* @gfp_mask: page allocation mode
*
- * Locates a page in the pagecache. If the page is not present, a new page
- * is allocated using @gfp_mask and is added to the pagecache and to the VM's
- * LRU list. The returned page is locked and has its reference count
- * incremented.
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the page is not present, a new page is allocated using @gfp_mask
+ * and added to the page cache and the VM's LRU list. The page is
+ * returned locked and with an increased refcount.
*
- * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
- * allocation!
+ * On memory exhaustion, %NULL is returned.
*
- * find_or_create_page() returns the desired page's address, or zero on
- * memory exhaustion.
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an
+ * atomic allocation!
*/
struct page *find_or_create_page(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask)
}
EXPORT_SYMBOL(find_or_create_page);
+/**
+ * find_get_entries - gang pagecache lookup
+ * @mapping: The address_space to search
+ * @start: The starting page cache index
+ * @nr_entries: The maximum number of entries
+ * @entries: Where the resulting entries are placed
+ * @indices: The cache indices corresponding to the entries in @entries
+ *
+ * find_get_entries() will search for and return a group of up to
+ * @nr_entries entries in the mapping. The entries are placed at
+ * @entries. find_get_entries() takes a reference against any actual
+ * pages it returns.
+ *
+ * The search returns a group of mapping-contiguous page cache entries
+ * with ascending indexes. There may be holes in the indices due to
+ * not-present pages.
+ *
+ * Any shadow entries of evicted pages are included in the returned
+ * array.
+ *
+ * find_get_entries() returns the number of pages and shadow entries
+ * which were found.
+ */
+unsigned find_get_entries(struct address_space *mapping,
+ pgoff_t start, unsigned int nr_entries,
+ struct page **entries, pgoff_t *indices)
+{
+ void **slot;
+ unsigned int ret = 0;
+ struct radix_tree_iter iter;
+
+ if (!nr_entries)
+ return 0;
+
+ rcu_read_lock();
+restart:
+ radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+ struct page *page;
+repeat:
+ page = radix_tree_deref_slot(slot);
+ if (unlikely(!page))
+ continue;
+ if (radix_tree_exception(page)) {
+ if (radix_tree_deref_retry(page))
+ goto restart;
+ /*
+ * Otherwise, we must be storing a swap entry
+ * here as an exceptional entry: so return it
+ * without attempting to raise page count.
+ */
+ goto export;
+ }
+ if (!page_cache_get_speculative(page))
+ goto repeat;
+
+ /* Has the page moved? */
+ if (unlikely(page != *slot)) {
+ page_cache_release(page);
+ goto repeat;
+ }
+export:
+ indices[ret] = iter.index;
+ entries[ret] = page;
+ if (++ret == nr_entries)
+ break;
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
/**
* find_get_pages - gang pagecache lookup
* @mapping: The address_space to search
* do_generic_file_read - generic file read routine
* @filp: the file to read
* @ppos: current file position
- * @desc: read_descriptor
+ * @iter: data destination
+ * @written: already copied
*
* This is a generic file read routine, and uses the
* mapping->a_ops->readpage() function for the actual low-level stuff.
* This is really ugly. But the goto's actually try to clarify some
* of the logic when it comes to error handling etc.
*/
-static void do_generic_file_read(struct file *filp, loff_t *ppos,
- read_descriptor_t *desc)
+static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
+ struct iov_iter *iter, ssize_t written)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
pgoff_t prev_index;
unsigned long offset; /* offset into pagecache page */
unsigned int prev_offset;
- int error;
+ 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 + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+ last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
for (;;) {
if (!page->mapping)
goto page_not_up_to_date_locked;
if (!mapping->a_ops->is_partially_uptodate(page,
- desc, offset))
+ offset, iter->count))
goto page_not_up_to_date_locked;
unlock_page(page);
}
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
- *
- * The file_read_actor routine returns how many bytes were
- * actually used..
- * NOTE! This may not be the same as how much of a user buffer
- * we filled up (we may be padding etc), so we can only update
- * "pos" here (the actor routine has to update the user buffer
- * pointers and the remaining count).
*/
- ret = file_read_actor(desc, page, offset, nr);
+
+ ret = copy_page_to_iter(page, offset, nr, iter);
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
prev_offset = offset;
page_cache_release(page);
- if (ret == nr && desc->count)
- continue;
- goto out;
+ written += ret;
+ if (!iov_iter_count(iter))
+ goto out;
+ if (ret < nr) {
+ error = -EFAULT;
+ goto out;
+ }
+ continue;
page_not_up_to_date:
/* Get exclusive access to the page ... */
if (unlikely(error)) {
if (error == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
+ error = 0;
goto find_page;
}
goto readpage_error;
readpage_error:
/* UHHUH! A synchronous read error occurred. Report it */
- desc->error = error;
page_cache_release(page);
goto out;
*/
page = page_cache_alloc_cold(mapping);
if (!page) {
- desc->error = -ENOMEM;
+ error = -ENOMEM;
goto out;
}
error = add_to_page_cache_lru(page, mapping,
index, GFP_KERNEL);
if (error) {
page_cache_release(page);
- if (error == -EEXIST)
+ if (error == -EEXIST) {
+ error = 0;
goto find_page;
- desc->error = error;
+ }
goto out;
}
goto readpage;
*ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
file_accessed(filp);
-}
-
-int file_read_actor(read_descriptor_t *desc, struct page *page,
- unsigned long offset, unsigned long size)
-{
- char *kaddr;
- unsigned long left, count = desc->count;
-
- if (size > count)
- size = count;
-
- /*
- * Faults on the destination of a read are common, so do it before
- * taking the kmap.
- */
- if (!fault_in_pages_writeable(desc->arg.buf, size)) {
- kaddr = kmap_atomic(page);
- left = __copy_to_user_inatomic(desc->arg.buf,
- kaddr + offset, size);
- kunmap_atomic(kaddr);
- if (left == 0)
- goto success;
- }
-
- /* Do it the slow way */
- kaddr = kmap(page);
- left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
- kunmap(page);
-
- if (left) {
- size -= left;
- desc->error = -EFAULT;
- }
-success:
- desc->count = count - size;
- desc->written += size;
- desc->arg.buf += size;
- return size;
+ return written ? written : error;
}
/*
{
struct file *filp = iocb->ki_filp;
ssize_t retval;
- unsigned long seg = 0;
size_t count;
loff_t *ppos = &iocb->ki_pos;
+ struct iov_iter i;
count = 0;
retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
if (retval)
return retval;
+ iov_iter_init(&i, iov, nr_segs, count, 0);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
if (retval > 0) {
*ppos = pos + retval;
count -= retval;
+ /*
+ * If we did a short DIO read we need to skip the
+ * section of the iov that we've already read data into.
+ */
+ iov_iter_advance(&i, retval);
}
/*
}
}
- count = retval;
- for (seg = 0; seg < nr_segs; seg++) {
- read_descriptor_t desc;
- loff_t offset = 0;
-
- /*
- * If we did a short DIO read we need to skip the section of the
- * iov that we've already read data into.
- */
- if (count) {
- if (count > iov[seg].iov_len) {
- count -= iov[seg].iov_len;
- continue;
- }
- offset = count;
- count = 0;
- }
-
- desc.written = 0;
- desc.arg.buf = iov[seg].iov_base + offset;
- desc.count = iov[seg].iov_len - offset;
- if (desc.count == 0)
- continue;
- desc.error = 0;
- do_generic_file_read(filp, ppos, &desc);
- retval += desc.written;
- if (desc.error) {
- retval = retval ?: desc.error;
- break;
- }
- if (desc.count > 0)
- break;
- }
+ retval = do_generic_file_read(filp, ppos, &i, retval);
out:
return retval;
}
struct inode *inode = mapping->host;
pgoff_t offset = vmf->pgoff;
struct page *page;
- pgoff_t size;
+ loff_t size;
int ret = 0;
- size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (offset >= size)
+ size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
+ if (offset >= size >> PAGE_CACHE_SHIFT)
return VM_FAULT_SIGBUS;
/*
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
*/
- size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (unlikely(offset >= size)) {
+ size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
+ if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) {
unlock_page(page);
page_cache_release(page);
return VM_FAULT_SIGBUS;
}
EXPORT_SYMBOL(filemap_fault);
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct radix_tree_iter iter;
+ void **slot;
+ struct file *file = vma->vm_file;
+ struct address_space *mapping = file->f_mapping;
+ loff_t size;
+ struct page *page;
+ unsigned long address = (unsigned long) vmf->virtual_address;
+ unsigned long addr;
+ pte_t *pte;
+
+ rcu_read_lock();
+ radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) {
+ if (iter.index > vmf->max_pgoff)
+ break;
+repeat:
+ page = radix_tree_deref_slot(slot);
+ if (unlikely(!page))
+ goto next;
+ if (radix_tree_exception(page)) {
+ if (radix_tree_deref_retry(page))
+ break;
+ else
+ goto next;
+ }
+
+ if (!page_cache_get_speculative(page))
+ goto repeat;
+
+ /* Has the page moved? */
+ if (unlikely(page != *slot)) {
+ page_cache_release(page);
+ goto repeat;
+ }
+
+ if (!PageUptodate(page) ||
+ PageReadahead(page) ||
+ PageHWPoison(page))
+ goto skip;
+ if (!trylock_page(page))
+ goto skip;
+
+ 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))
+ 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);
+ unlock_page(page);
+ goto next;
+unlock:
+ unlock_page(page);
+skip:
+ page_cache_release(page);
+next:
+ if (iter.index == vmf->max_pgoff)
+ break;
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
const struct vm_operations_struct generic_file_vm_ops = {
.fault = filemap_fault,
+ .map_pages = filemap_map_pages,
.page_mkwrite = filemap_page_mkwrite,
.remap_pages = generic_file_remap_pages,
};
EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);
+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);
+ page = ERR_PTR(-EIO);
+ }
+ }
+ return page;
+}
+
static struct page *__read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *, struct page *),
if (err < 0) {
page_cache_release(page);
page = ERR_PTR(err);
+ } else {
+ page = wait_on_page_read(page);
}
}
return page;
if (err < 0) {
page_cache_release(page);
return ERR_PTR(err);
+ } else {
+ page = wait_on_page_read(page);
+ if (IS_ERR(page))
+ return page;
}
out:
mark_page_accessed(page);
}
/**
- * read_cache_page_async - read into page cache, fill it if needed
+ * read_cache_page - read into page cache, fill it if needed
* @mapping: the page's address_space
* @index: the page index
* @filler: function to perform the read
* @data: first arg to filler(data, page) function, often left as NULL
*
- * Same as read_cache_page, but don't wait for page to become unlocked
- * after submitting it to the filler.
- *
* Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page but don't wait for it to become unlocked.
+ * not set, try to fill the page and wait for it to become unlocked.
*
* If the page does not get brought uptodate, return -EIO.
*/
-struct page *read_cache_page_async(struct address_space *mapping,
+struct page *read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *, struct page *),
void *data)
{
return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
}
-EXPORT_SYMBOL(read_cache_page_async);
-
-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);
- page = ERR_PTR(-EIO);
- }
- }
- return page;
-}
+EXPORT_SYMBOL(read_cache_page);
/**
* read_cache_page_gfp - read into page cache, using specified page allocation flags.
{
filler_t *filler = (filler_t *)mapping->a_ops->readpage;
- return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp));
+ return do_read_cache_page(mapping, index, filler, NULL, gfp);
}
EXPORT_SYMBOL(read_cache_page_gfp);
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping: the page's address_space
- * @index: the page index
- * @filler: function to perform the read
- * @data: first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page then wait for it to become unlocked.
- *
- * If the page does not get brought uptodate, return -EIO.
- */
-struct page *read_cache_page(struct address_space *mapping,
- pgoff_t index,
- int (*filler)(void *, struct page *),
- void *data)
-{
- return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
-}
-EXPORT_SYMBOL(read_cache_page);
-
-static size_t __iovec_copy_from_user_inatomic(char *vaddr,
- const struct iovec *iov, size_t base, size_t bytes)
-{
- size_t copied = 0, left = 0;
-
- while (bytes) {
- char __user *buf = iov->iov_base + base;
- int copy = min(bytes, iov->iov_len - base);
-
- base = 0;
- left = __copy_from_user_inatomic(vaddr, buf, copy);
- copied += copy;
- bytes -= copy;
- vaddr += copy;
- iov++;
-
- if (unlikely(left))
- break;
- }
- return copied - left;
-}
-
-/*
- * Copy as much as we can into the page and return the number of bytes which
- * were successfully copied. If a fault is encountered then return the number of
- * bytes which were copied.
- */
-size_t iov_iter_copy_from_user_atomic(struct page *page,
- struct iov_iter *i, unsigned long offset, size_t bytes)
-{
- char *kaddr;
- size_t copied;
-
- BUG_ON(!in_atomic());
- kaddr = kmap_atomic(page);
- if (likely(i->nr_segs == 1)) {
- int left;
- char __user *buf = i->iov->iov_base + i->iov_offset;
- left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
- copied = bytes - left;
- } else {
- copied = __iovec_copy_from_user_inatomic(kaddr + offset,
- i->iov, i->iov_offset, bytes);
- }
- kunmap_atomic(kaddr);
-
- return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
-
-/*
- * This has the same sideeffects and return value as
- * iov_iter_copy_from_user_atomic().
- * The difference is that it attempts to resolve faults.
- * Page must not be locked.
- */
-size_t iov_iter_copy_from_user(struct page *page,
- struct iov_iter *i, unsigned long offset, size_t bytes)
-{
- char *kaddr;
- size_t copied;
-
- kaddr = kmap(page);
- if (likely(i->nr_segs == 1)) {
- int left;
- char __user *buf = i->iov->iov_base + i->iov_offset;
- left = __copy_from_user(kaddr + offset, buf, bytes);
- copied = bytes - left;
- } else {
- copied = __iovec_copy_from_user_inatomic(kaddr + offset,
- i->iov, i->iov_offset, bytes);
- }
- kunmap(page);
- return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user);
-
-void iov_iter_advance(struct iov_iter *i, size_t bytes)
-{
- BUG_ON(i->count < bytes);
-
- if (likely(i->nr_segs == 1)) {
- i->iov_offset += bytes;
- i->count -= bytes;
- } else {
- const struct iovec *iov = i->iov;
- size_t base = i->iov_offset;
- unsigned long nr_segs = i->nr_segs;
-
- /*
- * The !iov->iov_len check ensures we skip over unlikely
- * zero-length segments (without overruning the iovec).
- */
- while (bytes || unlikely(i->count && !iov->iov_len)) {
- int copy;
-
- copy = min(bytes, iov->iov_len - base);
- BUG_ON(!i->count || i->count < copy);
- i->count -= copy;
- bytes -= copy;
- base += copy;
- if (iov->iov_len == base) {
- iov++;
- nr_segs--;
- base = 0;
- }
- }
- i->iov = iov;
- i->iov_offset = base;
- i->nr_segs = nr_segs;
- }
-}
-EXPORT_SYMBOL(iov_iter_advance);
-
-/*
- * Fault in the first iovec of the given iov_iter, to a maximum length
- * of bytes. Returns 0 on success, or non-zero if the memory could not be
- * accessed (ie. because it is an invalid address).
- *
- * writev-intensive code may want this to prefault several iovecs -- that
- * would be possible (callers must not rely on the fact that _only_ the
- * first iovec will be faulted with the current implementation).
- */
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
-{
- char __user *buf = i->iov->iov_base + i->iov_offset;
- bytes = min(bytes, i->iov->iov_len - i->iov_offset);
- return fault_in_pages_readable(buf, bytes);
-}
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
-
-/*
- * Return the count of just the current iov_iter segment.
- */
-size_t iov_iter_single_seg_count(const struct iov_iter *i)
-{
- const struct iovec *iov = i->iov;
- if (i->nr_segs == 1)
- return i->count;
- else
- return min(i->count, iov->iov_len - i->iov_offset);
-}
-EXPORT_SYMBOL(iov_iter_single_seg_count);
-
/*
* Performs necessary checks before doing a write
*
ssize_t
generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long *nr_segs, loff_t pos, loff_t *ppos,
+ unsigned long *nr_segs, loff_t pos,
size_t count, size_t ocount)
{
struct file *file = iocb->ki_filp;
i_size_write(inode, pos);
mark_inode_dirty(inode);
}
- *ppos = pos;
+ iocb->ki_pos = pos;
}
out:
return written;
}
EXPORT_SYMBOL(grab_cache_page_write_begin);
-static ssize_t generic_perform_write(struct file *file,
+ssize_t generic_perform_write(struct file *file,
struct iov_iter *i, loff_t pos)
{
struct address_space *mapping = file->f_mapping;
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
- pagefault_disable();
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
- pagefault_enable();
flush_dcache_page(page);
mark_page_accessed(page);
return written ? written : status;
}
-
-ssize_t
-generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos, loff_t *ppos,
- size_t count, ssize_t written)
-{
- struct file *file = iocb->ki_filp;
- ssize_t status;
- struct iov_iter i;
-
- iov_iter_init(&i, iov, nr_segs, count, written);
- status = generic_perform_write(file, &i, pos);
-
- if (likely(status >= 0)) {
- written += status;
- *ppos = pos + status;
- }
-
- return written ? written : status;
-}
-EXPORT_SYMBOL(generic_file_buffered_write);
+EXPORT_SYMBOL(generic_perform_write);
/**
* __generic_file_aio_write - write data to a file
* avoid syncing under i_mutex.
*/
ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
+ unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
- loff_t pos;
- ssize_t written;
+ loff_t pos = iocb->ki_pos;
+ ssize_t written = 0;
ssize_t err;
+ ssize_t status;
+ struct iov_iter from;
ocount = 0;
err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
return err;
count = ocount;
- pos = *ppos;
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
- written = 0;
-
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
goto out;
if (err)
goto out;
+ iov_iter_init(&from, iov, nr_segs, count, 0);
+
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
loff_t endbyte;
- ssize_t written_buffered;
- written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
- ppos, count, ocount);
+ written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
+ count, ocount);
if (written < 0 || written == count)
goto out;
+ iov_iter_advance(&from, written);
+
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
pos += written;
count -= written;
- written_buffered = generic_file_buffered_write(iocb, iov,
- nr_segs, pos, ppos, count,
- written);
+
+ status = generic_perform_write(file, &from, pos);
/*
- * If generic_file_buffered_write() retuned a synchronous error
+ * If generic_perform_write() returned a synchronous error
* then we want to return the number of bytes which were
* direct-written, or the error code if that was zero. Note
* that this differs from normal direct-io semantics, which
* will return -EFOO even if some bytes were written.
*/
- if (written_buffered < 0) {
- err = written_buffered;
+ if (unlikely(status < 0) && !written) {
+ err = status;
goto out;
}
-
+ iocb->ki_pos = pos + status;
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
*/
- endbyte = pos + written_buffered - written - 1;
+ endbyte = pos + status - 1;
err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
if (err == 0) {
- written = written_buffered;
+ written += status;
invalidate_mapping_pages(mapping,
pos >> PAGE_CACHE_SHIFT,
endbyte >> PAGE_CACHE_SHIFT);
*/
}
} else {
- written = generic_file_buffered_write(iocb, iov, nr_segs,
- pos, ppos, count, written);
+ written = generic_perform_write(file, &from, pos);
+ if (likely(written >= 0))
+ iocb->ki_pos = pos + written;
}
out:
current->backing_dev_info = NULL;
BUG_ON(iocb->ki_pos != pos);
mutex_lock(&inode->i_mutex);
- ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+ ret = __generic_file_aio_write(iocb, iov, nr_segs);
mutex_unlock(&inode->i_mutex);
if (ret > 0) {
projects / linux.git / blobdiff