return 0;
}
-static unsigned int dio_bio_write_op(struct kiocb *iocb)
+static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
{
- unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+ blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
/* avoid the need for a I/O completion work item */
if (iocb->ki_flags & IOCB_DSYNC)
- op |= REQ_FUA;
- return op;
+ opf |= REQ_FUA;
+ return opf;
+}
+
+static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
+ struct iov_iter *iter)
+{
+ return pos & (bdev_logical_block_size(bdev) - 1) ||
+ !bdev_iter_is_aligned(bdev, iter);
}
#define DIO_INLINE_BIO_VECS 4
struct bio bio;
ssize_t ret;
- if ((pos | iov_iter_alignment(iter)) &
- (bdev_logical_block_size(bdev) - 1))
+ if (blkdev_dio_unaligned(bdev, pos, iter))
return -EINVAL;
if (nr_pages <= DIO_INLINE_BIO_VECS)
struct blkdev_dio *dio;
struct bio *bio;
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
- unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+ blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
loff_t pos = iocb->ki_pos;
int ret = 0;
- if ((pos | iov_iter_alignment(iter)) &
- (bdev_logical_block_size(bdev) - 1))
+ if (blkdev_dio_unaligned(bdev, pos, iter))
return -EINVAL;
if (iocb->ki_flags & IOCB_ALLOC_CACHE)
{
struct block_device *bdev = iocb->ki_filp->private_data;
bool is_read = iov_iter_rw(iter) == READ;
- unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+ blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
struct blkdev_dio *dio;
struct bio *bio;
loff_t pos = iocb->ki_pos;
int ret = 0;
- if ((pos | iov_iter_alignment(iter)) &
- (bdev_logical_block_size(bdev) - 1))
+ if (blkdev_dio_unaligned(bdev, pos, iter))
return -EINVAL;
if (iocb->ki_flags & IOCB_ALLOC_CACHE)
.write_end = blkdev_write_end,
.writepages = blkdev_writepages,
.direct_IO = blkdev_direct_IO,
- .migratepage = buffer_migrate_page_norefs,
+ .migrate_folio = buffer_migrate_folio_norefs,
.is_dirty_writeback = buffer_check_dirty_writeback,
};
#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/vmalloc.h>
-#include <linux/blktrace_api.h>
#include <linux/raid/detect.h>
#include "check.h"
case BLK_ZONED_HA:
pr_info("%s: disabling host aware zoned block device support due to partitions\n",
disk->disk_name);
- blk_queue_set_zoned(disk, BLK_ZONED_NONE);
+ disk_set_zoned(disk, BLK_ZONED_NONE);
break;
case BLK_ZONED_NONE:
break;
void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p)
{
struct address_space *mapping = state->disk->part0->bd_inode->i_mapping;
- struct page *page;
+ struct folio *folio;
if (n >= get_capacity(state->disk)) {
state->access_beyond_eod = true;
- return NULL;
+ goto out;
}
- page = read_mapping_page(mapping,
- (pgoff_t)(n >> (PAGE_SHIFT - 9)), NULL);
- if (IS_ERR(page))
+ folio = read_mapping_folio(mapping, n >> PAGE_SECTORS_SHIFT, NULL);
+ if (IS_ERR(folio))
goto out;
- if (PageError(page))
- goto out_put_page;
-
- p->v = page;
- return (unsigned char *)page_address(page) +
- ((n & ((1 << (PAGE_SHIFT - 9)) - 1)) << SECTOR_SHIFT);
- out_put_page:
- put_page(page);
+
+ p->v = folio;
+ return folio_address(folio) + offset_in_folio(folio, n * SECTOR_SIZE);
out:
p->v = NULL;
return NULL;
#include <linux/fs.h>
#include <linux/blkdev.h>
+#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
fs_info->nodesize);
- /* A dirty eb shouldn't disappear from extent_buffers */
+ /* A dirty eb shouldn't disappear from buffer_radix */
if (WARN_ON(!eb))
return -EUCLEAN;
}
#ifdef CONFIG_MIGRATION
- static int btree_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page,
- enum migrate_mode mode)
+ static int btree_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
{
/*
* we can't safely write a btree page from here,
* we haven't done the locking hook
*/
- if (PageDirty(page))
+ if (folio_test_dirty(src))
return -EAGAIN;
/*
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
- if (page_has_private(page) &&
- !try_to_release_page(page, GFP_KERNEL))
+ if (folio_get_private(src) &&
+ !filemap_release_folio(src, GFP_KERNEL))
return -EAGAIN;
- return migrate_page(mapping, newpage, page, mode);
+ return migrate_folio(mapping, dst, src, mode);
}
+ #else
+ #define btree_migrate_folio NULL
#endif
-
static int btree_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
.writepages = btree_writepages,
.release_folio = btree_release_folio,
.invalidate_folio = btree_invalidate_folio,
- #ifdef CONFIG_MIGRATION
- .migratepage = btree_migratepage,
- #endif
- .dirty_folio = btree_dirty_folio,
+ .migrate_folio = btree_migrate_folio,
+ .dirty_folio = btree_dirty_folio,
};
struct extent_buffer *btrfs_find_create_tree_block(
root->nr_delalloc_inodes = 0;
root->nr_ordered_extents = 0;
root->inode_tree = RB_ROOT;
- xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);
+ INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
btrfs_init_root_block_rsv(root);
btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
#ifdef CONFIG_BTRFS_DEBUG
INIT_LIST_HEAD(&root->leak_list);
- spin_lock(&fs_info->fs_roots_lock);
+ spin_lock(&fs_info->fs_roots_radix_lock);
list_add_tail(&root->leak_list, &fs_info->allocated_roots);
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
#endif
}
{
struct btrfs_root *root;
- spin_lock(&fs_info->fs_roots_lock);
- root = xa_load(&fs_info->fs_roots, (unsigned long)root_id);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ root = radix_tree_lookup(&fs_info->fs_roots_radix,
+ (unsigned long)root_id);
if (root)
root = btrfs_grab_root(root);
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
return root;
}
{
int ret;
- spin_lock(&fs_info->fs_roots_lock);
- ret = xa_insert(&fs_info->fs_roots, (unsigned long)root->root_key.objectid,
- root, GFP_NOFS);
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret)
+ return ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ ret = radix_tree_insert(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ root);
if (ret == 0) {
btrfs_grab_root(root);
- set_bit(BTRFS_ROOT_REGISTERED, &root->state);
+ set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ radix_tree_preload_end();
return ret;
}
btrfs_drew_lock_destroy(&root->snapshot_lock);
free_root_extent_buffers(root);
#ifdef CONFIG_BTRFS_DEBUG
- spin_lock(&root->fs_info->fs_roots_lock);
+ spin_lock(&root->fs_info->fs_roots_radix_lock);
list_del_init(&root->leak_list);
- spin_unlock(&root->fs_info->fs_roots_lock);
+ spin_unlock(&root->fs_info->fs_roots_radix_lock);
#endif
kfree(root);
}
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *root;
- unsigned long index = 0;
+ int ret;
+ struct btrfs_root *gang[8];
+ int i;
while (!list_empty(&fs_info->dead_roots)) {
- root = list_entry(fs_info->dead_roots.next,
- struct btrfs_root, root_list);
- list_del(&root->root_list);
+ gang[0] = list_entry(fs_info->dead_roots.next,
+ struct btrfs_root, root_list);
+ list_del(&gang[0]->root_list);
- if (test_bit(BTRFS_ROOT_REGISTERED, &root->state))
- btrfs_drop_and_free_fs_root(fs_info, root);
- btrfs_put_root(root);
+ if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state))
+ btrfs_drop_and_free_fs_root(fs_info, gang[0]);
+ btrfs_put_root(gang[0]);
}
- xa_for_each(&fs_info->fs_roots, index, root) {
- btrfs_drop_and_free_fs_root(fs_info, root);
+ while (1) {
+ ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, 0,
+ ARRAY_SIZE(gang));
+ if (!ret)
+ break;
+ for (i = 0; i < ret; i++)
+ btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
}
void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
{
- xa_init_flags(&fs_info->fs_roots, GFP_ATOMIC);
- xa_init_flags(&fs_info->extent_buffers, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
INIT_LIST_HEAD(&fs_info->caching_block_groups);
spin_lock_init(&fs_info->delalloc_root_lock);
spin_lock_init(&fs_info->trans_lock);
- spin_lock_init(&fs_info->fs_roots_lock);
+ spin_lock_init(&fs_info->fs_roots_radix_lock);
spin_lock_init(&fs_info->delayed_iput_lock);
spin_lock_init(&fs_info->defrag_inodes_lock);
spin_lock_init(&fs_info->super_lock);
/*
* btrfs_find_orphan_roots() is responsible for finding all the dead
* roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
- * them into the fs_info->fs_roots. This must be done before
+ * them into the fs_info->fs_roots_radix tree. This must be done before
* calling btrfs_orphan_cleanup() on the tree root. If we don't do it
* first, then btrfs_orphan_cleanup() will delete a dead root's orphan
* item before the root's tree is deleted - this means that if we unmount
{
bool drop_ref = false;
- spin_lock(&fs_info->fs_roots_lock);
- xa_erase(&fs_info->fs_roots, (unsigned long)root->root_key.objectid);
- if (test_and_clear_bit(BTRFS_ROOT_REGISTERED, &root->state))
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ radix_tree_delete(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid);
+ if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state))
drop_ref = true;
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
if (BTRFS_FS_ERROR(fs_info)) {
ASSERT(root->log_root == NULL);
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *roots[8];
- unsigned long index = 0;
- int i;
+ u64 root_objectid = 0;
+ struct btrfs_root *gang[8];
+ int i = 0;
int err = 0;
- int grabbed;
+ unsigned int ret = 0;
while (1) {
- struct btrfs_root *root;
-
- spin_lock(&fs_info->fs_roots_lock);
- if (!xa_find(&fs_info->fs_roots, &index, ULONG_MAX, XA_PRESENT)) {
- spin_unlock(&fs_info->fs_roots_lock);
- return err;
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, root_objectid,
+ ARRAY_SIZE(gang));
+ if (!ret) {
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ break;
}
+ root_objectid = gang[ret - 1]->root_key.objectid + 1;
- grabbed = 0;
- xa_for_each_start(&fs_info->fs_roots, index, root, index) {
- /* Avoid grabbing roots in dead_roots */
- if (btrfs_root_refs(&root->root_item) > 0)
- roots[grabbed++] = btrfs_grab_root(root);
- if (grabbed >= ARRAY_SIZE(roots))
- break;
+ for (i = 0; i < ret; i++) {
+ /* Avoid to grab roots in dead_roots */
+ if (btrfs_root_refs(&gang[i]->root_item) == 0) {
+ gang[i] = NULL;
+ continue;
+ }
+ /* grab all the search result for later use */
+ gang[i] = btrfs_grab_root(gang[i]);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
- for (i = 0; i < grabbed; i++) {
- if (!roots[i])
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
continue;
- index = roots[i]->root_key.objectid;
- err = btrfs_orphan_cleanup(roots[i]);
+ root_objectid = gang[i]->root_key.objectid;
+ err = btrfs_orphan_cleanup(gang[i]);
if (err)
- goto out;
- btrfs_put_root(roots[i]);
+ break;
+ btrfs_put_root(gang[i]);
}
- index++;
+ root_objectid++;
}
-out:
- /* Release the roots that remain uncleaned due to error */
- for (; i < grabbed; i++) {
- if (roots[i])
- btrfs_put_root(roots[i]);
+ /* release the uncleaned roots due to error */
+ for (; i < ret; i++) {
+ if (gang[i])
+ btrfs_put_root(gang[i]);
}
return err;
}
static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
{
- unsigned long index = 0;
- int grabbed = 0;
- struct btrfs_root *roots[8];
-
- spin_lock(&fs_info->fs_roots_lock);
- while ((grabbed = xa_extract(&fs_info->fs_roots, (void **)roots, index,
- ULONG_MAX, 8, XA_PRESENT))) {
- for (int i = 0; i < grabbed; i++)
- roots[i] = btrfs_grab_root(roots[i]);
- spin_unlock(&fs_info->fs_roots_lock);
-
- for (int i = 0; i < grabbed; i++) {
- if (!roots[i])
+ struct btrfs_root *gang[8];
+ u64 root_objectid = 0;
+ int ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, root_objectid,
+ ARRAY_SIZE(gang))) != 0) {
+ int i;
+
+ for (i = 0; i < ret; i++)
+ gang[i] = btrfs_grab_root(gang[i]);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
continue;
- index = roots[i]->root_key.objectid;
- btrfs_free_log(NULL, roots[i]);
- btrfs_put_root(roots[i]);
+ root_objectid = gang[i]->root_key.objectid;
+ btrfs_free_log(NULL, gang[i]);
+ btrfs_put_root(gang[i]);
}
- index++;
- spin_lock(&fs_info->fs_roots_lock);
+ root_objectid++;
+ spin_lock(&fs_info->fs_roots_radix_lock);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
btrfs_free_log_root_tree(NULL, fs_info);
}
struct page *locked_page;
u64 start;
u64 end;
- unsigned int write_flags;
+ blk_opf_t write_flags;
struct list_head extents;
struct cgroup_subsys_state *blkcg_css;
struct btrfs_work work;
int i;
bool should_compress;
unsigned nofs_flag;
- const unsigned int write_flags = wbc_to_write_flags(wbc);
+ const blk_opf_t write_flags = wbc_to_write_flags(wbc);
unlock_extent(&inode->io_tree, start, end);
ordered_extent->file_offset,
ordered_extent->file_offset +
logical_len);
+ btrfs_zoned_release_data_reloc_bg(fs_info, ordered_extent->disk_bytenr,
+ ordered_extent->disk_num_bytes);
} else {
BUG_ON(root == fs_info->tree_root);
ret = insert_ordered_extent_file_extent(trans, ordered_extent);
u64 last_objectid = 0;
int ret = 0, nr_unlink = 0;
- /* Bail out if the cleanup is already running. */
if (test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &root->state))
return 0;
*
* btrfs_find_orphan_roots() ran before us, which has
* found all deleted roots and loaded them into
- * fs_info->fs_roots. So here we can find if an
+ * fs_info->fs_roots_radix. So here we can find if an
* orphan item corresponds to a deleted root by looking
- * up the root from that xarray.
+ * up the root from that radix tree.
*/
- spin_lock(&fs_info->fs_roots_lock);
- dead_root = xa_load(&fs_info->fs_roots,
- (unsigned long)found_key.objectid);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ dead_root = radix_tree_lookup(&fs_info->fs_roots_radix,
+ (unsigned long)found_key.objectid);
if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0)
is_dead_root = 1;
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
if (is_dead_root) {
/* prevent this orphan from being found again */
* cache.
*
* This is required for both inode re-read from disk and delayed inode
- * in the delayed_nodes xarray.
+ * in delayed_nodes_tree.
*/
if (BTRFS_I(inode)->last_trans == fs_info->generation)
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
em->block_start == EXTENT_MAP_INLINE) {
free_extent_map(em);
- ret = -ENOTBLK;
+ /*
+ * If we are in a NOWAIT context, return -EAGAIN in order to
+ * fallback to buffered IO. This is not only because we can
+ * block with buffered IO (no support for NOWAIT semantics at
+ * the moment) but also to avoid returning short reads to user
+ * space - this happens if we were able to read some data from
+ * previous non-compressed extents and then when we fallback to
+ * buffered IO, at btrfs_file_read_iter() by calling
+ * filemap_read(), we fail to fault in pages for the read buffer,
+ * in which case filemap_read() returns a short read (the number
+ * of bytes previously read is > 0, so it does not return -EFAULT).
+ */
+ ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK;
goto unlock_err;
}
}
#ifdef CONFIG_MIGRATION
- static int btrfs_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page,
+ static int btrfs_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src,
enum migrate_mode mode)
{
- int ret;
+ int ret = filemap_migrate_folio(mapping, dst, src, mode);
- ret = migrate_page_move_mapping(mapping, newpage, page, 0);
if (ret != MIGRATEPAGE_SUCCESS)
return ret;
- if (page_has_private(page))
- attach_page_private(newpage, detach_page_private(page));
-
- if (PageOrdered(page)) {
- ClearPageOrdered(page);
- SetPageOrdered(newpage);
+ if (folio_test_ordered(src)) {
+ folio_clear_ordered(src);
+ folio_set_ordered(dst);
}
- if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
- else
- migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
+ #else
+ #define btrfs_migrate_folio NULL
#endif
static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
extent_info.file_offset = file_offset;
extent_info.extent_buf = (char *)&stack_fi;
extent_info.is_new_extent = true;
+ extent_info.update_times = true;
extent_info.qgroup_reserved = qgroup_released;
extent_info.insertions = 0;
.direct_IO = noop_direct_IO,
.invalidate_folio = btrfs_invalidate_folio,
.release_folio = btrfs_release_folio,
- #ifdef CONFIG_MIGRATION
- .migratepage = btrfs_migratepage,
- #endif
+ .migrate_folio = btrfs_migrate_folio,
.dirty_folio = filemap_dirty_folio,
.error_remove_page = generic_error_remove_page,
.swap_activate = btrfs_swap_activate,
#include "internal.h"
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
-static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
struct writeback_control *wbc);
#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
/*
- * If none of the buffers had errors and they are all
- * uptodate then we can set the page uptodate.
+ * If all of the buffers are uptodate then we can set the page
+ * uptodate.
*/
- if (page_uptodate && !PageError(page))
+ if (page_uptodate)
SetPageUptodate(page);
unlock_page(page);
return;
struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
if (bh) {
if (buffer_dirty(bh))
- ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
+ ll_rw_block(REQ_OP_WRITE, 1, &bh);
put_bh(bh);
}
}
} else {
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
{
struct buffer_head *bh = __getblk(bdev, block, size);
if (likely(bh)) {
- ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
brelse(bh);
}
}
{
struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
if (likely(bh)) {
- ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
brelse(bh);
}
}
{
struct inode *bd_inode = bdev->bd_inode;
struct address_space *bd_mapping = bd_inode->i_mapping;
- struct pagevec pvec;
+ struct folio_batch fbatch;
pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
pgoff_t end;
int i, count;
struct buffer_head *head;
end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits);
- pagevec_init(&pvec);
- while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) {
- count = pagevec_count(&pvec);
+ folio_batch_init(&fbatch);
+ while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) {
+ count = folio_batch_count(&fbatch);
for (i = 0; i < count; i++) {
- struct page *page = pvec.pages[i];
+ struct folio *folio = fbatch.folios[i];
- if (!page_has_buffers(page))
+ if (!folio_buffers(folio))
continue;
/*
- * We use page lock instead of bd_mapping->private_lock
+ * We use folio lock instead of bd_mapping->private_lock
* to pin buffers here since we can afford to sleep and
* it scales better than a global spinlock lock.
*/
- lock_page(page);
- /* Recheck when the page is locked which pins bhs */
- if (!page_has_buffers(page))
+ folio_lock(folio);
+ /* Recheck when the folio is locked which pins bhs */
+ head = folio_buffers(folio);
+ if (!head)
goto unlock_page;
- head = page_buffers(page);
bh = head;
do {
if (!buffer_mapped(bh) || (bh->b_blocknr < block))
bh = bh->b_this_page;
} while (bh != head);
unlock_page:
- unlock_page(page);
+ folio_unlock(folio);
}
- pagevec_release(&pvec);
+ folio_batch_release(&fbatch);
cond_resched();
/* End of range already reached? */
if (index > end || !index)
struct buffer_head *bh, *head;
unsigned int blocksize, bbits;
int nr_underway = 0;
- int write_flags = wbc_to_write_flags(wbc);
+ blk_opf_t write_flags = wbc_to_write_flags(wbc);
head = create_page_buffers(page, inode,
(1 << BH_Dirty)|(1 << BH_Uptodate));
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
+ submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
nr_underway++;
}
bh = next;
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
+ submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
nr_underway++;
}
bh = next;
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
*wait_bh++=bh;
}
}
unsigned int blocksize, bbits;
int nr, i;
int fully_mapped = 1;
+ bool page_error = false;
VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
if (iblock < lblock) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, iblock, bh, 0);
- if (err)
+ if (err) {
folio_set_error(folio);
+ page_error = true;
+ }
}
if (!buffer_mapped(bh)) {
folio_zero_range(folio, i * blocksize,
* All buffers are uptodate - we can set the folio uptodate
* as well. But not if get_block() returned an error.
*/
- if (!folio_test_error(folio))
+ if (!page_error)
folio_mark_uptodate(folio);
folio_unlock(folio);
return 0;
if (buffer_uptodate(bh))
end_buffer_async_read(bh, 1);
else
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
}
return 0;
}
}
EXPORT_SYMBOL(block_page_mkwrite);
- /*
- * nobh_write_begin()'s prereads are special: the buffer_heads are freed
- * immediately, while under the page lock. So it needs a special end_io
- * handler which does not touch the bh after unlocking it.
- */
- static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate)
- {
- __end_buffer_read_notouch(bh, uptodate);
- }
-
- /*
- * Attach the singly-linked list of buffers created by nobh_write_begin, to
- * the page (converting it to circular linked list and taking care of page
- * dirty races).
- */
- static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
- {
- struct buffer_head *bh;
-
- BUG_ON(!PageLocked(page));
-
- spin_lock(&page->mapping->private_lock);
- bh = head;
- do {
- if (PageDirty(page))
- set_buffer_dirty(bh);
- if (!bh->b_this_page)
- bh->b_this_page = head;
- bh = bh->b_this_page;
- } while (bh != head);
- attach_page_private(page, head);
- spin_unlock(&page->mapping->private_lock);
- }
-
- /*
- * On entry, the page is fully not uptodate.
- * On exit the page is fully uptodate in the areas outside (from,to)
- * The filesystem needs to handle block truncation upon failure.
- */
- int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
- struct page **pagep, void **fsdata,
- get_block_t *get_block)
- {
- struct inode *inode = mapping->host;
- const unsigned blkbits = inode->i_blkbits;
- const unsigned blocksize = 1 << blkbits;
- struct buffer_head *head, *bh;
- struct page *page;
- pgoff_t index;
- unsigned from, to;
- unsigned block_in_page;
- unsigned block_start, block_end;
- sector_t block_in_file;
- int nr_reads = 0;
- int ret = 0;
- int is_mapped_to_disk = 1;
-
- index = pos >> PAGE_SHIFT;
- from = pos & (PAGE_SIZE - 1);
- to = from + len;
-
- page = grab_cache_page_write_begin(mapping, index);
- if (!page)
- return -ENOMEM;
- *pagep = page;
- *fsdata = NULL;
-
- if (page_has_buffers(page)) {
- ret = __block_write_begin(page, pos, len, get_block);
- if (unlikely(ret))
- goto out_release;
- return ret;
- }
-
- if (PageMappedToDisk(page))
- return 0;
-
- /*
- * Allocate buffers so that we can keep track of state, and potentially
- * attach them to the page if an error occurs. In the common case of
- * no error, they will just be freed again without ever being attached
- * to the page (which is all OK, because we're under the page lock).
- *
- * Be careful: the buffer linked list is a NULL terminated one, rather
- * than the circular one we're used to.
- */
- head = alloc_page_buffers(page, blocksize, false);
- if (!head) {
- ret = -ENOMEM;
- goto out_release;
- }
-
- block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
-
- /*
- * We loop across all blocks in the page, whether or not they are
- * part of the affected region. This is so we can discover if the
- * page is fully mapped-to-disk.
- */
- for (block_start = 0, block_in_page = 0, bh = head;
- block_start < PAGE_SIZE;
- block_in_page++, block_start += blocksize, bh = bh->b_this_page) {
- int create;
-
- block_end = block_start + blocksize;
- bh->b_state = 0;
- create = 1;
- if (block_start >= to)
- create = 0;
- ret = get_block(inode, block_in_file + block_in_page,
- bh, create);
- if (ret)
- goto failed;
- if (!buffer_mapped(bh))
- is_mapped_to_disk = 0;
- if (buffer_new(bh))
- clean_bdev_bh_alias(bh);
- if (PageUptodate(page)) {
- set_buffer_uptodate(bh);
- continue;
- }
- if (buffer_new(bh) || !buffer_mapped(bh)) {
- zero_user_segments(page, block_start, from,
- to, block_end);
- continue;
- }
- if (buffer_uptodate(bh))
- continue; /* reiserfs does this */
- if (block_start < from || block_end > to) {
- lock_buffer(bh);
- bh->b_end_io = end_buffer_read_nobh;
- submit_bh(REQ_OP_READ, bh);
- nr_reads++;
- }
- }
-
- if (nr_reads) {
- /*
- * The page is locked, so these buffers are protected from
- * any VM or truncate activity. Hence we don't need to care
- * for the buffer_head refcounts.
- */
- for (bh = head; bh; bh = bh->b_this_page) {
- wait_on_buffer(bh);
- if (!buffer_uptodate(bh))
- ret = -EIO;
- }
- if (ret)
- goto failed;
- }
-
- if (is_mapped_to_disk)
- SetPageMappedToDisk(page);
-
- *fsdata = head; /* to be released by nobh_write_end */
-
- return 0;
-
- failed:
- BUG_ON(!ret);
- /*
- * Error recovery is a bit difficult. We need to zero out blocks that
- * were newly allocated, and dirty them to ensure they get written out.
- * Buffers need to be attached to the page at this point, otherwise
- * the handling of potential IO errors during writeout would be hard
- * (could try doing synchronous writeout, but what if that fails too?)
- */
- attach_nobh_buffers(page, head);
- page_zero_new_buffers(page, from, to);
-
- out_release:
- unlock_page(page);
- put_page(page);
- *pagep = NULL;
-
- return ret;
- }
- EXPORT_SYMBOL(nobh_write_begin);
-
- int nobh_write_end(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
- {
- struct inode *inode = page->mapping->host;
- struct buffer_head *head = fsdata;
- struct buffer_head *bh;
- BUG_ON(fsdata != NULL && page_has_buffers(page));
-
- if (unlikely(copied < len) && head)
- attach_nobh_buffers(page, head);
- if (page_has_buffers(page))
- return generic_write_end(file, mapping, pos, len,
- copied, page, fsdata);
-
- SetPageUptodate(page);
- set_page_dirty(page);
- if (pos+copied > inode->i_size) {
- i_size_write(inode, pos+copied);
- mark_inode_dirty(inode);
- }
-
- unlock_page(page);
- put_page(page);
-
- while (head) {
- bh = head;
- head = head->b_this_page;
- free_buffer_head(bh);
- }
-
- return copied;
- }
- EXPORT_SYMBOL(nobh_write_end);
-
- /*
- * nobh_writepage() - based on block_full_write_page() except
- * that it tries to operate without attaching bufferheads to
- * the page.
- */
- int nobh_writepage(struct page *page, get_block_t *get_block,
- struct writeback_control *wbc)
- {
- struct inode * const inode = page->mapping->host;
- loff_t i_size = i_size_read(inode);
- const pgoff_t end_index = i_size >> PAGE_SHIFT;
- unsigned offset;
- int ret;
-
- /* Is the page fully inside i_size? */
- if (page->index < end_index)
- goto out;
-
- /* Is the page fully outside i_size? (truncate in progress) */
- offset = i_size & (PAGE_SIZE-1);
- if (page->index >= end_index+1 || !offset) {
- unlock_page(page);
- return 0; /* don't care */
- }
-
- /*
- * The page straddles i_size. It must be zeroed out on each and every
- * writepage invocation because it may be mmapped. "A file is mapped
- * in multiples of the page size. For a file that is not a multiple of
- * the page size, the remaining memory is zeroed when mapped, and
- * writes to that region are not written out to the file."
- */
- zero_user_segment(page, offset, PAGE_SIZE);
- out:
- ret = mpage_writepage(page, get_block, wbc);
- if (ret == -EAGAIN)
- ret = __block_write_full_page(inode, page, get_block, wbc,
- end_buffer_async_write);
- return ret;
- }
- EXPORT_SYMBOL(nobh_writepage);
-
- int nobh_truncate_page(struct address_space *mapping,
- loff_t from, get_block_t *get_block)
- {
- pgoff_t index = from >> PAGE_SHIFT;
- struct inode *inode = mapping->host;
- unsigned blocksize = i_blocksize(inode);
- struct folio *folio;
- struct buffer_head map_bh;
- size_t offset;
- sector_t iblock;
- int err;
-
- /* Block boundary? Nothing to do */
- if (!(from & (blocksize - 1)))
- return 0;
-
- folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_CREAT,
- mapping_gfp_mask(mapping));
- err = -ENOMEM;
- if (!folio)
- goto out;
-
- if (folio_buffers(folio))
- goto has_buffers;
-
- iblock = from >> inode->i_blkbits;
- map_bh.b_size = blocksize;
- map_bh.b_state = 0;
- err = get_block(inode, iblock, &map_bh, 0);
- if (err)
- goto unlock;
- /* unmapped? It's a hole - nothing to do */
- if (!buffer_mapped(&map_bh))
- goto unlock;
-
- /* Ok, it's mapped. Make sure it's up-to-date */
- if (!folio_test_uptodate(folio)) {
- err = mapping->a_ops->read_folio(NULL, folio);
- if (err) {
- folio_put(folio);
- goto out;
- }
- folio_lock(folio);
- if (!folio_test_uptodate(folio)) {
- err = -EIO;
- goto unlock;
- }
- if (folio_buffers(folio))
- goto has_buffers;
- }
- offset = offset_in_folio(folio, from);
- folio_zero_segment(folio, offset, round_up(offset, blocksize));
- folio_mark_dirty(folio);
- err = 0;
-
- unlock:
- folio_unlock(folio);
- folio_put(folio);
- out:
- return err;
-
- has_buffers:
- folio_unlock(folio);
- folio_put(folio);
- return block_truncate_page(mapping, from, get_block);
- }
- EXPORT_SYMBOL(nobh_truncate_page);
-
int block_truncate_page(struct address_space *mapping,
loff_t from, get_block_t *get_block)
{
if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
err = -EIO;
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
/* Uhhuh. Read error. Complain and punt. */
if (!buffer_uptodate(bh))
bio_put(bio);
}
-static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
struct writeback_control *wbc)
{
+ const enum req_op op = opf & REQ_OP_MASK;
struct bio *bio;
BUG_ON(!buffer_locked(bh));
clear_buffer_write_io_error(bh);
if (buffer_meta(bh))
- op_flags |= REQ_META;
+ opf |= REQ_META;
if (buffer_prio(bh))
- op_flags |= REQ_PRIO;
+ opf |= REQ_PRIO;
- bio = bio_alloc(bh->b_bdev, 1, op | op_flags, GFP_NOIO);
+ bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO);
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
return 0;
}
-int submit_bh(int op, int op_flags, struct buffer_head *bh)
+int submit_bh(blk_opf_t opf, struct buffer_head *bh)
{
- return submit_bh_wbc(op, op_flags, bh, NULL);
+ return submit_bh_wbc(opf, bh, NULL);
}
EXPORT_SYMBOL(submit_bh);
/**
* ll_rw_block: low-level access to block devices (DEPRECATED)
- * @op: whether to %READ or %WRITE
- * @op_flags: req_flag_bits
+ * @opf: block layer request operation and flags.
* @nr: number of &struct buffer_heads in the array
* @bhs: array of pointers to &struct buffer_head
*
* ll_rw_block() takes an array of pointers to &struct buffer_heads, and
* requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE.
- * @op_flags contains flags modifying the detailed I/O behavior, most notably
+ * @opf contains flags modifying the detailed I/O behavior, most notably
* %REQ_RAHEAD.
*
* This function drops any buffer that it cannot get a lock on (with the
* All of the buffers must be for the same device, and must also be a
* multiple of the current approved size for the device.
*/
-void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[])
+void ll_rw_block(const blk_opf_t opf, int nr, struct buffer_head *bhs[])
{
+ const enum req_op op = opf & REQ_OP_MASK;
int i;
for (i = 0; i < nr; i++) {
if (!trylock_buffer(bh))
continue;
- if (op == WRITE) {
+ if (op == REQ_OP_WRITE) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(op, op_flags, bh);
+ submit_bh(opf, bh);
continue;
}
} else {
if (!buffer_uptodate(bh)) {
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(op, op_flags, bh);
+ submit_bh(opf, bh);
continue;
}
}
}
EXPORT_SYMBOL(ll_rw_block);
-void write_dirty_buffer(struct buffer_head *bh, int op_flags)
+void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
lock_buffer(bh);
if (!test_clear_buffer_dirty(bh)) {
}
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(REQ_OP_WRITE, op_flags, bh);
+ submit_bh(REQ_OP_WRITE | op_flags, bh);
}
EXPORT_SYMBOL(write_dirty_buffer);
* and then start new I/O and then wait upon it. The caller must have a ref on
* the buffer_head.
*/
-int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
+int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
int ret = 0;
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
+ ret = submit_bh(REQ_OP_WRITE | op_flags, bh);
wait_on_buffer(bh);
if (!ret && !buffer_uptodate(bh))
ret = -EIO;
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return 0;
return ret;
}
- static int
- ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, struct page **pagep, void **fsdata)
- {
- int ret;
-
- ret = nobh_write_begin(mapping, pos, len, pagep, fsdata,
- ext2_get_block);
- if (ret < 0)
- ext2_write_failed(mapping, pos + len);
- return ret;
- }
-
- static int ext2_nobh_writepage(struct page *page,
- struct writeback_control *wbc)
- {
- return nobh_writepage(page, ext2_get_block, wbc);
- }
-
static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
{
return generic_block_bmap(mapping,block,ext2_get_block);
.bmap = ext2_bmap,
.direct_IO = ext2_direct_IO,
.writepages = ext2_writepages,
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
- const struct address_space_operations ext2_nobh_aops = {
- .dirty_folio = block_dirty_folio,
- .invalidate_folio = block_invalidate_folio,
- .read_folio = ext2_read_folio,
- .readahead = ext2_readahead,
- .writepage = ext2_nobh_writepage,
- .write_begin = ext2_nobh_write_begin,
- .write_end = nobh_write_end,
- .bmap = ext2_bmap,
- .direct_IO = ext2_direct_IO,
- .writepages = ext2_writepages,
- .migratepage = buffer_migrate_page,
- .error_remove_page = generic_error_remove_page,
- };
-
static const struct address_space_operations ext2_dax_aops = {
.writepages = ext2_dax_writepages,
.direct_IO = noop_direct_IO,
inode_dio_wait(inode);
- if (IS_DAX(inode)) {
+ if (IS_DAX(inode))
error = dax_zero_range(inode, newsize,
PAGE_ALIGN(newsize) - newsize, NULL,
&ext2_iomap_ops);
- } else if (test_opt(inode->i_sb, NOBH))
- error = nobh_truncate_page(inode->i_mapping,
- newsize, ext2_get_block);
else
error = block_truncate_page(inode->i_mapping,
newsize, ext2_get_block);
inode->i_fop = &ext2_file_operations;
if (IS_DAX(inode))
inode->i_mapping->a_ops = &ext2_dax_aops;
- else if (test_opt(inode->i_sb, NOBH))
- inode->i_mapping->a_ops = &ext2_nobh_aops;
else
inode->i_mapping->a_ops = &ext2_aops;
}
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &ext2_dir_inode_operations;
inode->i_fop = &ext2_dir_operations;
- if (test_opt(inode->i_sb, NOBH))
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- else
- inode->i_mapping->a_ops = &ext2_aops;
+ inode->i_mapping->a_ops = &ext2_aops;
} else if (S_ISLNK(inode->i_mode)) {
if (ext2_inode_is_fast_symlink(inode)) {
inode->i_link = (char *)ei->i_data;
} else {
inode->i_op = &ext2_symlink_inode_operations;
inode_nohighmem(inode);
- if (test_opt(inode->i_sb, NOBH))
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- else
- inode->i_mapping->a_ops = &ext2_aops;
+ inode->i_mapping->a_ops = &ext2_aops;
}
} else {
inode->i_op = &ext2_special_inode_operations;
if (error)
return error;
- if (is_quota_modification(inode, iattr)) {
+ if (is_quota_modification(mnt_userns, inode, iattr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
- if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
- (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
- error = dquot_transfer(inode, iattr);
+ if (i_uid_needs_update(mnt_userns, iattr, inode) ||
+ i_gid_needs_update(mnt_userns, iattr, inode)) {
+ error = dquot_transfer(mnt_userns, inode, iattr);
if (error)
return error;
}
seq_puts(seq, ",noacl");
#endif
- if (test_opt(sb, NOBH))
- seq_puts(seq, ",nobh");
-
if (test_opt(sb, USRQUOTA))
seq_puts(seq, ",usrquota");
clear_opt (opts->s_mount_opt, OLDALLOC);
break;
case Opt_nobh:
- set_opt (opts->s_mount_opt, NOBH);
+ ext2_msg(sb, KERN_INFO,
+ "nobh option not supported");
break;
#ifdef CONFIG_EXT2_FS_XATTR
case Opt_user_xattr:
sbi->s_frags_per_group);
goto failed_mount;
}
- if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
+ if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+ sbi->s_inodes_per_group > sb->s_blocksize * 8) {
ext2_msg(sb, KERN_ERR,
- "error: #inodes per group too big: %lu",
+ "error: invalid #inodes per group: %lu",
sbi->s_inodes_per_group);
goto failed_mount;
}
sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) - 1)
/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+ if ((u64)sbi->s_groups_count * sbi->s_inodes_per_group !=
+ le32_to_cpu(es->s_inodes_count)) {
+ ext2_msg(sb, KERN_ERR, "error: invalid #inodes: %u vs computed %llu",
+ le32_to_cpu(es->s_inodes_count),
+ (u64)sbi->s_groups_count * sbi->s_inodes_per_group);
+ goto failed_mount;
+ }
db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
EXT2_DESC_PER_BLOCK(sb);
sbi->s_group_desc = kmalloc_array(db_count,
len = i_size-off;
toread = len;
while (toread > 0) {
- tocopy = sb->s_blocksize - offset < toread ?
- sb->s_blocksize - offset : toread;
+ tocopy = min_t(size_t, sb->s_blocksize - offset, toread);
tmp_bh.b_state = 0;
tmp_bh.b_size = sb->s_blocksize;
struct buffer_head *bh;
while (towrite > 0) {
- tocopy = sb->s_blocksize - offset < towrite ?
- sb->s_blocksize - offset : towrite;
+ tocopy = min_t(size_t, sb->s_blocksize - offset, towrite);
tmp_bh.b_state = 0;
tmp_bh.b_size = sb->s_blocksize;
static void mpage_release_unused_pages(struct mpage_da_data *mpd,
bool invalidate)
{
- int nr_pages, i;
+ unsigned nr, i;
pgoff_t index, end;
- struct pagevec pvec;
+ struct folio_batch fbatch;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
ext4_es_remove_extent(inode, start, last - start + 1);
}
- pagevec_init(&pvec);
+ folio_batch_init(&fbatch);
while (index <= end) {
- nr_pages = pagevec_lookup_range(&pvec, mapping, &index, end);
- if (nr_pages == 0)
+ nr = filemap_get_folios(mapping, &index, end, &fbatch);
+ if (nr == 0)
break;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
- struct folio *folio = page_folio(page);
+ for (i = 0; i < nr; i++) {
+ struct folio *folio = fbatch.folios[i];
+ if (folio->index < mpd->first_page)
+ continue;
+ if (folio->index + folio_nr_pages(folio) - 1 > end)
+ continue;
BUG_ON(!folio_test_locked(folio));
BUG_ON(folio_test_writeback(folio));
if (invalidate) {
}
folio_unlock(folio);
}
- pagevec_release(&pvec);
+ folio_batch_release(&fbatch);
}
}
*/
static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
{
- struct pagevec pvec;
- int nr_pages, i;
+ struct folio_batch fbatch;
+ unsigned nr, i;
struct inode *inode = mpd->inode;
int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
pgoff_t start, end;
lblk = start << bpp_bits;
pblock = mpd->map.m_pblk;
- pagevec_init(&pvec);
+ folio_batch_init(&fbatch);
while (start <= end) {
- nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping,
- &start, end);
- if (nr_pages == 0)
+ nr = filemap_get_folios(inode->i_mapping, &start, end, &fbatch);
+ if (nr == 0)
break;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
+ for (i = 0; i < nr; i++) {
+ struct page *page = &fbatch.folios[i]->page;
err = mpage_process_page(mpd, page, &lblk, &pblock,
&map_bh);
if (err < 0)
goto out;
}
- pagevec_release(&pvec);
+ folio_batch_release(&fbatch);
}
/* Extent fully mapped and matches with page boundary. We are done. */
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
return 0;
out:
- pagevec_release(&pvec);
+ folio_batch_release(&fbatch);
return err;
}
.invalidate_folio = ext4_invalidate_folio,
.release_folio = ext4_release_folio,
.direct_IO = noop_direct_IO,
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.swap_activate = ext4_iomap_swap_activate,
.invalidate_folio = ext4_invalidate_folio,
.release_folio = ext4_release_folio,
.direct_IO = noop_direct_IO,
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.swap_activate = ext4_iomap_swap_activate,
if (error)
return error;
- if (is_quota_modification(inode, attr)) {
+ if (is_quota_modification(mnt_userns, inode, attr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
- if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
- (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
+ if (i_uid_needs_update(mnt_userns, attr, inode) ||
+ i_gid_needs_update(mnt_userns, attr, inode)) {
handle_t *handle;
/* (user+group)*(old+new) structure, inode write (sb,
* counts xattr inode references.
*/
down_read(&EXT4_I(inode)->xattr_sem);
- error = dquot_transfer(inode, attr);
+ error = dquot_transfer(mnt_userns, inode, attr);
up_read(&EXT4_I(inode)->xattr_sem);
if (error) {
}
/* Update corresponding info in inode so that everything is in
* one transaction */
- if (attr->ia_valid & ATTR_UID)
- inode->i_uid = attr->ia_uid;
- if (attr->ia_valid & ATTR_GID)
- inode->i_gid = attr->ia_gid;
+ i_uid_update(mnt_userns, attr, inode);
+ i_gid_update(mnt_userns, attr, inode);
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
if (unlikely(error)) {
return 0;
}
-static unsigned int f2fs_io_flags(struct f2fs_io_info *fio)
+static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
{
unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1;
unsigned int fua_flag, meta_flag, io_flag;
- unsigned int op_flags = 0;
+ blk_opf_t op_flags = 0;
if (fio->op != REQ_OP_WRITE)
return 0;
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
- unsigned nr_pages, unsigned op_flag,
+ unsigned nr_pages, blk_opf_t op_flag,
pgoff_t first_idx, bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
- block_t blkaddr, int op_flags, bool for_write)
+ block_t blkaddr, blk_opf_t op_flags,
+ bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
}
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
- int op_flags, bool for_write)
+ blk_opf_t op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
return blknr;
}
- #ifdef CONFIG_MIGRATION
- #include <linux/migrate.h>
-
- int f2fs_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode)
- {
- int rc, extra_count = 0;
-
- BUG_ON(PageWriteback(page));
-
- rc = migrate_page_move_mapping(mapping, newpage,
- page, extra_count);
- if (rc != MIGRATEPAGE_SUCCESS)
- return rc;
-
- /* guarantee to start from no stale private field */
- set_page_private(newpage, 0);
- if (PagePrivate(page)) {
- set_page_private(newpage, page_private(page));
- SetPagePrivate(newpage);
- get_page(newpage);
-
- set_page_private(page, 0);
- ClearPagePrivate(page);
- put_page(page);
- }
-
- if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
- else
- migrate_page_states(newpage, page);
-
- return MIGRATEPAGE_SUCCESS;
- }
- #endif
-
#ifdef CONFIG_SWAP
static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk,
unsigned int blkcnt)
.write_begin = f2fs_write_begin,
.write_end = f2fs_write_end,
.dirty_folio = f2fs_dirty_data_folio,
+ .migrate_folio = filemap_migrate_folio,
.invalidate_folio = f2fs_invalidate_folio,
.release_folio = f2fs_release_folio,
.direct_IO = noop_direct_IO,
.bmap = f2fs_bmap,
.swap_activate = f2fs_swap_activate,
.swap_deactivate = f2fs_swap_deactivate,
- #ifdef CONFIG_MIGRATION
- .migratepage = f2fs_migrate_page,
- #endif
};
void f2fs_clear_page_cache_dirty_tag(struct page *page)
nid_t ino; /* inode number */
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
enum temp_type temp; /* contains HOT/WARM/COLD */
- int op; /* contains REQ_OP_ */
- int op_flags; /* req_flag_bits */
+ enum req_op op; /* contains REQ_OP_ */
+ blk_opf_t op_flags; /* req_flag_bits */
block_t new_blkaddr; /* new block address to be written */
block_t old_blkaddr; /* old block address before Cow */
struct page *page; /* page to be written */
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
- int op_flags, bool for_write);
+ blk_opf_t op_flags, bool for_write);
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write);
void f2fs_write_failed(struct inode *inode, loff_t to);
void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
bool f2fs_release_folio(struct folio *folio, gfp_t wait);
- #ifdef CONFIG_MIGRATION
- int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
- struct page *page, enum migrate_mode mode);
- #endif
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
void f2fs_clear_page_cache_dirty_tag(struct page *page);
int f2fs_init_post_read_processing(void);
* 0: f2fs_put_page(page, 0)
* LOCKED_PAGE or error: f2fs_put_page(page, 1)
*/
-static int read_node_page(struct page *page, int op_flags)
+static int read_node_page(struct page *page, blk_opf_t op_flags)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct node_info ni;
.dirty_folio = f2fs_dirty_node_folio,
.invalidate_folio = f2fs_invalidate_folio,
.release_folio = f2fs_release_folio,
- #ifdef CONFIG_MIGRATION
- .migratepage = f2fs_migrate_page,
- #endif
+ .migrate_folio = filemap_migrate_folio,
};
static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
* there is no pending bio, then this is a no-op.
*/
-void gfs2_log_submit_bio(struct bio **biop, int opf)
+void gfs2_log_submit_bio(struct bio **biop, blk_opf_t opf)
{
struct bio *bio = *biop;
if (bio) {
*/
static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno,
- struct bio **biop, int op,
+ struct bio **biop, enum req_op op,
bio_end_io_t *end_io, bool flush)
{
struct bio *bio = *biop;
* @head: The journal head to start from
* @done: If set, perform only cleanup, else search and set if found.
*
- * Find the page with 'index' in the journal's mapping. Search the page for
+ * Find the folio with 'index' in the journal's mapping. Search the folio for
* the journal head if requested (cleanup == false). Release refs on the
- * page so the page cache can reclaim it (put_page() twice). We grabbed a
- * reference on this page two times, first when we did a find_or_create_page()
- * to obtain the page to add it to the bio and second when we do a
- * find_get_page() here to get the page to wait on while I/O on it is being
+ * folio so the page cache can reclaim it. We grabbed a
+ * reference on this folio twice, first when we did a find_or_create_page()
+ * to obtain the folio to add it to the bio and second when we do a
+ * filemap_get_folio() here to get the folio to wait on while I/O on it is being
* completed.
- * This function is also used to free up a page we might've grabbed but not
+ * This function is also used to free up a folio we might've grabbed but not
* used. Maybe we added it to a bio, but not submitted it for I/O. Or we
* submitted the I/O, but we already found the jhead so we only need to drop
- * our references to the page.
+ * our references to the folio.
*/
static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index,
struct gfs2_log_header_host *head,
bool *done)
{
- struct page *page;
+ struct folio *folio;
- page = find_get_page(jd->jd_inode->i_mapping, index);
- wait_on_page_locked(page);
+ folio = filemap_get_folio(jd->jd_inode->i_mapping, index);
- if (PageError(page))
+ folio_wait_locked(folio);
+ if (folio_test_error(folio))
*done = true;
if (!*done)
- *done = gfs2_jhead_pg_srch(jd, head, page);
+ *done = gfs2_jhead_pg_srch(jd, head, &folio->page);
- put_page(page); /* Once for find_get_page */
- put_page(page); /* Once more for find_or_create_page */
+ /* filemap_get_folio() and the earlier find_or_create_page() */
+ folio_put_refs(folio, 2);
}
static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs)
}
#endif
- static void huge_pagevec_release(struct pagevec *pvec)
- {
- int i;
-
- for (i = 0; i < pagevec_count(pvec); ++i)
- put_page(pvec->pages[i]);
-
- pagevec_reinit(pvec);
- }
-
/*
* Mask used when checking the page offset value passed in via system
* calls. This value will be converted to a loff_t which is signed.
struct address_space *mapping = &inode->i_data;
const pgoff_t start = lstart >> huge_page_shift(h);
const pgoff_t end = lend >> huge_page_shift(h);
- struct pagevec pvec;
+ struct folio_batch fbatch;
pgoff_t next, index;
int i, freed = 0;
bool truncate_op = (lend == LLONG_MAX);
- pagevec_init(&pvec);
+ folio_batch_init(&fbatch);
next = start;
- while (next < end) {
- /*
- * When no more pages are found, we are done.
- */
- if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1))
- break;
-
- for (i = 0; i < pagevec_count(&pvec); ++i) {
- struct page *page = pvec.pages[i];
+ while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) {
+ for (i = 0; i < folio_batch_count(&fbatch); ++i) {
+ struct folio *folio = fbatch.folios[i];
u32 hash = 0;
- index = page->index;
+ index = folio->index;
if (!truncate_op) {
/*
* Only need to hold the fault mutex in the
}
/*
- * If page is mapped, it was faulted in after being
+ * If folio is mapped, it was faulted in after being
* unmapped in caller. Unmap (again) now after taking
* the fault mutex. The mutex will prevent faults
- * until we finish removing the page.
+ * until we finish removing the folio.
*
* This race can only happen in the hole punch case.
* Getting here in a truncate operation is a bug.
*/
- if (unlikely(page_mapped(page))) {
+ if (unlikely(folio_mapped(folio))) {
BUG_ON(truncate_op);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
i_mmap_unlock_write(mapping);
}
- lock_page(page);
+ folio_lock(folio);
/*
* We must free the huge page and remove from page
* cache (remove_huge_page) BEFORE removing the
* the subpool and global reserve usage count can need
* to be adjusted.
*/
- VM_BUG_ON(HPageRestoreReserve(page));
- remove_huge_page(page);
+ VM_BUG_ON(HPageRestoreReserve(&folio->page));
+ remove_huge_page(&folio->page);
freed++;
if (!truncate_op) {
if (unlikely(hugetlb_unreserve_pages(inode,
hugetlb_fix_reserve_counts(inode);
}
- unlock_page(page);
+ folio_unlock(folio);
if (!truncate_op)
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
}
- huge_pagevec_release(&pvec);
+ folio_batch_release(&fbatch);
cond_resched();
}
remove_inode_hugepages(inode, offset, LLONG_MAX);
}
+static void hugetlbfs_zero_partial_page(struct hstate *h,
+ struct address_space *mapping,
+ loff_t start,
+ loff_t end)
+{
+ pgoff_t idx = start >> huge_page_shift(h);
+ struct folio *folio;
+
+ folio = filemap_lock_folio(mapping, idx);
+ if (!folio)
+ return;
+
+ start = start & ~huge_page_mask(h);
+ end = end & ~huge_page_mask(h);
+ if (!end)
+ end = huge_page_size(h);
+
+ folio_zero_segment(folio, (size_t)start, (size_t)end);
+
+ folio_unlock(folio);
+ folio_put(folio);
+}
+
static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
+ struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
+ struct address_space *mapping = inode->i_mapping;
struct hstate *h = hstate_inode(inode);
loff_t hpage_size = huge_page_size(h);
loff_t hole_start, hole_end;
/*
- * For hole punch round up the beginning offset of the hole and
- * round down the end.
+ * hole_start and hole_end indicate the full pages within the hole.
*/
hole_start = round_up(offset, hpage_size);
hole_end = round_down(offset + len, hpage_size);
- if (hole_end > hole_start) {
- struct address_space *mapping = inode->i_mapping;
- struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
+ inode_lock(inode);
+
+ /* protected by i_rwsem */
+ if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
+ inode_unlock(inode);
+ return -EPERM;
+ }
- inode_lock(inode);
+ i_mmap_lock_write(mapping);
- /* protected by i_rwsem */
- if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
- inode_unlock(inode);
- return -EPERM;
- }
+ /* If range starts before first full page, zero partial page. */
+ if (offset < hole_start)
+ hugetlbfs_zero_partial_page(h, mapping,
+ offset, min(offset + len, hole_start));
- i_mmap_lock_write(mapping);
+ /* Unmap users of full pages in the hole. */
+ if (hole_end > hole_start) {
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap,
hole_start >> PAGE_SHIFT,
hole_end >> PAGE_SHIFT, 0);
- i_mmap_unlock_write(mapping);
- remove_inode_hugepages(inode, hole_start, hole_end);
- inode_unlock(inode);
}
+ /* If range extends beyond last full page, zero partial page. */
+ if ((offset + len) > hole_end && (offset + len) > hole_start)
+ hugetlbfs_zero_partial_page(h, mapping,
+ hole_end, offset + len);
+
+ i_mmap_unlock_write(mapping);
+
+ /* Remove full pages from the file. */
+ if (hole_end > hole_start)
+ remove_inode_hugepages(inode, hole_start, hole_end);
+
+ inode_unlock(inode);
+
return 0;
}
SetHPageMigratable(page);
/*
- * unlock_page because locked by add_to_page_cache()
+ * unlock_page because locked by huge_add_to_page_cache()
* put_page() due to reference from alloc_huge_page()
*/
unlock_page(page);
return error;
}
- static int hugetlbfs_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page,
+ #ifdef CONFIG_MIGRATION
+ static int hugetlbfs_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src,
enum migrate_mode mode)
{
int rc;
- rc = migrate_huge_page_move_mapping(mapping, newpage, page);
+ rc = migrate_huge_page_move_mapping(mapping, dst, src);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
- if (hugetlb_page_subpool(page)) {
- hugetlb_set_page_subpool(newpage, hugetlb_page_subpool(page));
- hugetlb_set_page_subpool(page, NULL);
+ if (hugetlb_page_subpool(&src->page)) {
+ hugetlb_set_page_subpool(&dst->page,
+ hugetlb_page_subpool(&src->page));
+ hugetlb_set_page_subpool(&src->page, NULL);
}
if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
+ folio_migrate_copy(dst, src);
else
- migrate_page_states(newpage, page);
+ folio_migrate_flags(dst, src);
return MIGRATEPAGE_SUCCESS;
}
+ #else
+ #define hugetlbfs_migrate_folio NULL
+ #endif
static int hugetlbfs_error_remove_page(struct address_space *mapping,
struct page *page)
.write_begin = hugetlbfs_write_begin,
.write_end = hugetlbfs_write_end,
.dirty_folio = noop_dirty_folio,
- .migratepage = hugetlbfs_migrate_page,
+ .migrate_folio = hugetlbfs_migrate_folio,
.error_remove_page = hugetlbfs_error_remove_page,
};
{
/*
* We have to cycle the i_pages lock here because reclaim can be in the
- * process of removing the last page (in __delete_from_page_cache())
+ * process of removing the last page (in __filemap_remove_folio())
* and we must not free the mapping under it.
*/
xa_lock_irq(&inode->i_data.i_pages);
return notify_change(mnt_userns, dentry, &newattrs, NULL);
}
-/*
- * Remove special file priviledges (suid, capabilities) when file is written
- * to or truncated.
- */
-int file_remove_privs(struct file *file)
+static int __file_remove_privs(struct file *file, unsigned int flags)
{
struct dentry *dentry = file_dentry(file);
struct inode *inode = file_inode(file);
+ int error;
int kill;
- int error = 0;
- /*
- * Fast path for nothing security related.
- * As well for non-regular files, e.g. blkdev inodes.
- * For example, blkdev_write_iter() might get here
- * trying to remove privs which it is not allowed to.
- */
if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
return 0;
kill = dentry_needs_remove_privs(dentry);
- if (kill < 0)
+ if (kill <= 0)
return kill;
- if (kill)
- error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
+
+ if (flags & IOCB_NOWAIT)
+ return -EAGAIN;
+
+ error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
if (!error)
inode_has_no_xattr(inode);
return error;
}
-EXPORT_SYMBOL(file_remove_privs);
/**
- * file_update_time - update mtime and ctime time
- * @file: file accessed
- *
- * Update the mtime and ctime members of an inode and mark the inode
- * for writeback. Note that this function is meant exclusively for
- * usage in the file write path of filesystems, and filesystems may
- * choose to explicitly ignore update via this function with the
- * S_NOCMTIME inode flag, e.g. for network filesystem where these
- * timestamps are handled by the server. This can return an error for
- * file systems who need to allocate space in order to update an inode.
+ * file_remove_privs - remove special file privileges (suid, capabilities)
+ * @file: file to remove privileges from
+ *
+ * When file is modified by a write or truncation ensure that special
+ * file privileges are removed.
+ *
+ * Return: 0 on success, negative errno on failure.
*/
+int file_remove_privs(struct file *file)
+{
+ return __file_remove_privs(file, 0);
+}
+EXPORT_SYMBOL(file_remove_privs);
-int file_update_time(struct file *file)
+static int inode_needs_update_time(struct inode *inode, struct timespec64 *now)
{
- struct inode *inode = file_inode(file);
- struct timespec64 now;
int sync_it = 0;
- int ret;
/* First try to exhaust all avenues to not sync */
if (IS_NOCMTIME(inode))
return 0;
- now = current_time(inode);
- if (!timespec64_equal(&inode->i_mtime, &now))
+ if (!timespec64_equal(&inode->i_mtime, now))
sync_it = S_MTIME;
- if (!timespec64_equal(&inode->i_ctime, &now))
+ if (!timespec64_equal(&inode->i_ctime, now))
sync_it |= S_CTIME;
if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
if (!sync_it)
return 0;
- /* Finally allowed to write? Takes lock. */
- if (__mnt_want_write_file(file))
- return 0;
+ return sync_it;
+}
- ret = inode_update_time(inode, &now, sync_it);
- __mnt_drop_write_file(file);
+static int __file_update_time(struct file *file, struct timespec64 *now,
+ int sync_mode)
+{
+ int ret = 0;
+ struct inode *inode = file_inode(file);
+
+ /* try to update time settings */
+ if (!__mnt_want_write_file(file)) {
+ ret = inode_update_time(inode, now, sync_mode);
+ __mnt_drop_write_file(file);
+ }
return ret;
}
+
+/**
+ * file_update_time - update mtime and ctime time
+ * @file: file accessed
+ *
+ * Update the mtime and ctime members of an inode and mark the inode for
+ * writeback. Note that this function is meant exclusively for usage in
+ * the file write path of filesystems, and filesystems may choose to
+ * explicitly ignore updates via this function with the _NOCMTIME inode
+ * flag, e.g. for network filesystem where these imestamps are handled
+ * by the server. This can return an error for file systems who need to
+ * allocate space in order to update an inode.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int file_update_time(struct file *file)
+{
+ int ret;
+ struct inode *inode = file_inode(file);
+ struct timespec64 now = current_time(inode);
+
+ ret = inode_needs_update_time(inode, &now);
+ if (ret <= 0)
+ return ret;
+
+ return __file_update_time(file, &now, ret);
+}
EXPORT_SYMBOL(file_update_time);
-/* Caller must hold the file's inode lock */
-int file_modified(struct file *file)
+/**
+ * file_modified_flags - handle mandated vfs changes when modifying a file
+ * @file: file that was modified
+ * @flags: kiocb flags
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * If IOCB_NOWAIT is set, special file privileges will not be removed and
+ * time settings will not be updated. It will return -EAGAIN.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+static int file_modified_flags(struct file *file, int flags)
{
- int err;
+ int ret;
+ struct inode *inode = file_inode(file);
+ struct timespec64 now = current_time(inode);
/*
* Clear the security bits if the process is not being run by root.
* This keeps people from modifying setuid and setgid binaries.
*/
- err = file_remove_privs(file);
- if (err)
- return err;
+ ret = __file_remove_privs(file, flags);
+ if (ret)
+ return ret;
if (unlikely(file->f_mode & FMODE_NOCMTIME))
return 0;
- return file_update_time(file);
+ ret = inode_needs_update_time(inode, &now);
+ if (ret <= 0)
+ return ret;
+ if (flags & IOCB_NOWAIT)
+ return -EAGAIN;
+
+ return __file_update_time(file, &now, ret);
+}
+
+/**
+ * file_modified - handle mandated vfs changes when modifying a file
+ * @file: file that was modified
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int file_modified(struct file *file)
+{
+ return file_modified_flags(file, 0);
}
EXPORT_SYMBOL(file_modified);
+/**
+ * kiocb_modified - handle mandated vfs changes when modifying a file
+ * @iocb: iocb that was modified
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int kiocb_modified(struct kiocb *iocb)
+{
+ return file_modified_flags(iocb->ki_filp, iocb->ki_flags);
+}
+EXPORT_SYMBOL_GPL(kiocb_modified);
+
int inode_needs_sync(struct inode *inode)
{
if (IS_SYNC(inode))
static struct bio_set iomap_ioend_bioset;
static struct iomap_page *
-iomap_page_create(struct inode *inode, struct folio *folio)
+iomap_page_create(struct inode *inode, struct folio *folio, unsigned int flags)
{
struct iomap_page *iop = to_iomap_page(folio);
unsigned int nr_blocks = i_blocks_per_folio(inode, folio);
+ gfp_t gfp;
if (iop || nr_blocks <= 1)
return iop;
+ if (flags & IOMAP_NOWAIT)
+ gfp = GFP_NOWAIT;
+ else
+ gfp = GFP_NOFS | __GFP_NOFAIL;
+
iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
- GFP_NOFS | __GFP_NOFAIL);
- spin_lock_init(&iop->uptodate_lock);
- if (folio_test_uptodate(folio))
- bitmap_fill(iop->uptodate, nr_blocks);
- folio_attach_private(folio, iop);
+ gfp);
+ if (iop) {
+ spin_lock_init(&iop->uptodate_lock);
+ if (folio_test_uptodate(folio))
+ bitmap_fill(iop->uptodate, nr_blocks);
+ folio_attach_private(folio, iop);
+ }
return iop;
}
static void iomap_set_range_uptodate(struct folio *folio,
struct iomap_page *iop, size_t off, size_t len)
{
- if (folio_test_error(folio))
- return;
-
if (iop)
iomap_iop_set_range_uptodate(folio, iop, off, len);
else
if (WARN_ON_ONCE(size > iomap->length))
return -EIO;
if (offset > 0)
- iop = iomap_page_create(iter->inode, folio);
+ iop = iomap_page_create(iter->inode, folio, iter->flags);
else
iop = to_iomap_page(folio);
return iomap_read_inline_data(iter, folio);
/* zero post-eof blocks as the page may be mapped */
- iop = iomap_page_create(iter->inode, folio);
+ iop = iomap_page_create(iter->inode, folio, iter->flags);
iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen);
if (plen == 0)
goto done;
}
EXPORT_SYMBOL_GPL(iomap_invalidate_folio);
- #ifdef CONFIG_MIGRATION
- int
- iomap_migrate_page(struct address_space *mapping, struct page *newpage,
- struct page *page, enum migrate_mode mode)
- {
- struct folio *folio = page_folio(page);
- struct folio *newfolio = page_folio(newpage);
- int ret;
-
- ret = folio_migrate_mapping(mapping, newfolio, folio, 0);
- if (ret != MIGRATEPAGE_SUCCESS)
- return ret;
-
- if (folio_test_private(folio))
- folio_attach_private(newfolio, folio_detach_private(folio));
-
- if (mode != MIGRATE_SYNC_NO_COPY)
- folio_migrate_copy(newfolio, folio);
- else
- folio_migrate_flags(newfolio, folio);
- return MIGRATEPAGE_SUCCESS;
- }
- EXPORT_SYMBOL_GPL(iomap_migrate_page);
- #endif /* CONFIG_MIGRATION */
-
static void
iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
{
size_t len, struct folio *folio)
{
const struct iomap *srcmap = iomap_iter_srcmap(iter);
- struct iomap_page *iop = iomap_page_create(iter->inode, folio);
+ struct iomap_page *iop;
loff_t block_size = i_blocksize(iter->inode);
loff_t block_start = round_down(pos, block_size);
loff_t block_end = round_up(pos + len, block_size);
+ unsigned int nr_blocks = i_blocks_per_folio(iter->inode, folio);
size_t from = offset_in_folio(folio, pos), to = from + len;
size_t poff, plen;
return 0;
folio_clear_error(folio);
+ iop = iomap_page_create(iter->inode, folio, iter->flags);
+ if ((iter->flags & IOMAP_NOWAIT) && !iop && nr_blocks > 1)
+ return -EAGAIN;
+
do {
iomap_adjust_read_range(iter->inode, folio, &block_start,
block_end - block_start, &poff, &plen);
return -EIO;
folio_zero_segments(folio, poff, from, to, poff + plen);
} else {
- int status = iomap_read_folio_sync(block_start, folio,
+ int status;
+
+ if (iter->flags & IOMAP_NOWAIT)
+ return -EAGAIN;
+
+ status = iomap_read_folio_sync(block_start, folio,
poff, plen, srcmap);
if (status)
return status;
unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
int status = 0;
+ if (iter->flags & IOMAP_NOWAIT)
+ fgp |= FGP_NOWAIT;
+
BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length);
if (srcmap != &iter->iomap)
BUG_ON(pos + len > srcmap->offset + srcmap->length);
folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
fgp, mapping_gfp_mask(iter->inode->i_mapping));
if (!folio) {
- status = -ENOMEM;
+ status = (iter->flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOMEM;
goto out_no_page;
}
if (pos + len > folio_pos(folio) + folio_size(folio))
loff_t pos = iter->pos;
ssize_t written = 0;
long status = 0;
+ struct address_space *mapping = iter->inode->i_mapping;
+ unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
do {
struct folio *folio;
bytes = min_t(unsigned long, PAGE_SIZE - offset,
iov_iter_count(i));
again:
+ status = balance_dirty_pages_ratelimited_flags(mapping,
+ bdp_flags);
+ if (unlikely(status))
+ break;
+
if (bytes > length)
bytes = length;
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
+ *
+ * For async buffered writes the assumption is that the user
+ * page has already been faulted in. This can be optimized by
+ * faulting the user page.
*/
if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
status = -EFAULT;
break;
page = folio_file_page(folio, pos >> PAGE_SHIFT);
- if (mapping_writably_mapped(iter->inode->i_mapping))
+ if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
copied = copy_page_from_iter_atomic(page, offset, bytes, i);
pos += status;
written += status;
length -= status;
-
- balance_dirty_pages_ratelimited(iter->inode->i_mapping);
} while (iov_iter_count(i) && length);
+ if (status == -EAGAIN) {
+ iov_iter_revert(i, written);
+ return -EAGAIN;
+ }
return written ? written : status;
}
};
int ret;
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ iter.flags |= IOMAP_NOWAIT;
+
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.processed = iomap_write_iter(&iter, i);
if (iter.pos == iocb->ki_pos)
struct writeback_control *wbc, struct inode *inode,
struct folio *folio, u64 end_pos)
{
- struct iomap_page *iop = iomap_page_create(inode, folio);
+ struct iomap_page *iop = iomap_page_create(inode, folio, 0);
struct iomap_ioend *ioend, *next;
unsigned len = i_blocksize(inode);
unsigned nblocks = i_blocks_per_folio(inode, folio);
* them. So when the buffer is up to date and the page size == block size,
* this marks the page up to date instead of adding new buffers.
*/
- static void
- map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
+ static void map_buffer_to_folio(struct folio *folio, struct buffer_head *bh,
+ int page_block)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
struct buffer_head *page_bh, *head;
int block = 0;
- if (!page_has_buffers(page)) {
+ head = folio_buffers(folio);
+ if (!head) {
/*
* don't make any buffers if there is only one buffer on
- * the page and the page just needs to be set up to date
+ * the folio and the folio just needs to be set up to date
*/
if (inode->i_blkbits == PAGE_SHIFT &&
buffer_uptodate(bh)) {
- SetPageUptodate(page);
+ folio_mark_uptodate(folio);
return;
}
- create_empty_buffers(page, i_blocksize(inode), 0);
+ create_empty_buffers(&folio->page, i_blocksize(inode), 0);
+ head = folio_buffers(folio);
}
- head = page_buffers(page);
+
page_bh = head;
do {
if (block == page_block) {
struct mpage_readpage_args {
struct bio *bio;
- struct page *page;
+ struct folio *folio;
unsigned int nr_pages;
bool is_readahead;
sector_t last_block_in_bio;
*/
static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
{
- struct page *page = args->page;
- struct inode *inode = page->mapping->host;
+ struct folio *folio = args->folio;
+ struct inode *inode = folio->mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
const unsigned blocksize = 1 << blkbits;
struct block_device *bdev = NULL;
int length;
int fully_mapped = 1;
- int op = REQ_OP_READ;
+ blk_opf_t opf = REQ_OP_READ;
unsigned nblocks;
unsigned relative_block;
- gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
+ gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL);
+
+ /* MAX_BUF_PER_PAGE, for example */
+ VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
if (args->is_readahead) {
- op |= REQ_RAHEAD;
+ opf |= REQ_RAHEAD;
gfp |= __GFP_NORETRY | __GFP_NOWARN;
}
- if (page_has_buffers(page))
+ if (folio_buffers(folio))
goto confused;
- block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
+ block_in_file = (sector_t)folio->index << (PAGE_SHIFT - blkbits);
last_block = block_in_file + args->nr_pages * blocks_per_page;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
}
/*
- * Then do more get_blocks calls until we are done with this page.
+ * Then do more get_blocks calls until we are done with this folio.
*/
- map_bh->b_page = page;
+ map_bh->b_page = &folio->page;
while (page_block < blocks_per_page) {
map_bh->b_state = 0;
map_bh->b_size = 0;
/* some filesystems will copy data into the page during
* the get_block call, in which case we don't want to
- * read it again. map_buffer_to_page copies the data
- * we just collected from get_block into the page's buffers
- * so readpage doesn't have to repeat the get_block call
+ * read it again. map_buffer_to_folio copies the data
+ * we just collected from get_block into the folio's buffers
+ * so read_folio doesn't have to repeat the get_block call
*/
if (buffer_uptodate(map_bh)) {
- map_buffer_to_page(page, map_bh, page_block);
+ map_buffer_to_folio(folio, map_bh, page_block);
goto confused;
}
}
if (first_hole != blocks_per_page) {
- zero_user_segment(page, first_hole << blkbits, PAGE_SIZE);
+ folio_zero_segment(folio, first_hole << blkbits, PAGE_SIZE);
if (first_hole == 0) {
- SetPageUptodate(page);
- unlock_page(page);
+ folio_mark_uptodate(folio);
+ folio_unlock(folio);
goto out;
}
} else if (fully_mapped) {
- SetPageMappedToDisk(page);
+ folio_set_mappedtodisk(folio);
}
/*
- * This page will go to BIO. Do we need to send this BIO off first?
+ * This folio will go to BIO. Do we need to send this BIO off first?
*/
if (args->bio && (args->last_block_in_bio != blocks[0] - 1))
args->bio = mpage_bio_submit(args->bio);
if (args->bio == NULL) {
if (first_hole == blocks_per_page) {
if (!bdev_read_page(bdev, blocks[0] << (blkbits - 9),
- page))
+ &folio->page))
goto out;
}
- args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), op,
+ args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), opf,
gfp);
if (args->bio == NULL)
goto confused;
}
length = first_hole << blkbits;
- if (bio_add_page(args->bio, page, length, 0) < length) {
+ if (!bio_add_folio(args->bio, folio, length, 0)) {
args->bio = mpage_bio_submit(args->bio);
goto alloc_new;
}
confused:
if (args->bio)
args->bio = mpage_bio_submit(args->bio);
- if (!PageUptodate(page))
- block_read_full_folio(page_folio(page), args->get_block);
+ if (!folio_test_uptodate(folio))
+ block_read_full_folio(folio, args->get_block);
else
- unlock_page(page);
+ folio_unlock(folio);
goto out;
}
*/
void mpage_readahead(struct readahead_control *rac, get_block_t get_block)
{
- struct page *page;
+ struct folio *folio;
struct mpage_readpage_args args = {
.get_block = get_block,
.is_readahead = true,
};
- while ((page = readahead_page(rac))) {
- prefetchw(&page->flags);
- args.page = page;
+ while ((folio = readahead_folio(rac))) {
+ prefetchw(&folio->flags);
+ args.folio = folio;
args.nr_pages = readahead_count(rac);
args.bio = do_mpage_readpage(&args);
- put_page(page);
}
if (args.bio)
mpage_bio_submit(args.bio);
int mpage_read_folio(struct folio *folio, get_block_t get_block)
{
struct mpage_readpage_args args = {
- .page = &folio->page,
+ .folio = folio,
.nr_pages = 1,
.get_block = get_block,
};
- VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
-
args.bio = do_mpage_readpage(&args);
if (args.bio)
mpage_bio_submit(args.bio);
struct bio *bio;
sector_t last_block_in_bio;
get_block_t *get_block;
- unsigned use_writepage;
};
/*
if (bio)
bio = mpage_bio_submit(bio);
- if (mpd->use_writepage) {
- ret = mapping->a_ops->writepage(page, wbc);
- } else {
- ret = -EAGAIN;
- goto out;
- }
/*
* The caller has a ref on the inode, so *mapping is stable
*/
+ ret = block_write_full_page(page, mpd->get_block, wbc);
mapping_set_error(mapping, ret);
out:
mpd->bio = bio;
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @get_block: the filesystem's block mapper function.
- * If this is NULL then use a_ops->writepage. Otherwise, go
- * direct-to-BIO.
*
* This is a library function, which implements the writepages()
* address_space_operation.
mpage_writepages(struct address_space *mapping,
struct writeback_control *wbc, get_block_t get_block)
{
+ struct mpage_data mpd = {
+ .get_block = get_block,
+ };
struct blk_plug plug;
int ret;
blk_start_plug(&plug);
-
- if (!get_block)
- ret = generic_writepages(mapping, wbc);
- else {
- struct mpage_data mpd = {
- .bio = NULL,
- .last_block_in_bio = 0,
- .get_block = get_block,
- .use_writepage = 1,
- };
-
- ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
- if (mpd.bio)
- mpage_bio_submit(mpd.bio);
- }
- blk_finish_plug(&plug);
- return ret;
- }
- EXPORT_SYMBOL(mpage_writepages);
-
- int mpage_writepage(struct page *page, get_block_t get_block,
- struct writeback_control *wbc)
- {
- struct mpage_data mpd = {
- .bio = NULL,
- .last_block_in_bio = 0,
- .get_block = get_block,
- .use_writepage = 0,
- };
- int ret = __mpage_writepage(page, wbc, &mpd);
+ ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
if (mpd.bio)
mpage_bio_submit(mpd.bio);
+ blk_finish_plug(&plug);
return ret;
}
- EXPORT_SYMBOL(mpage_writepage);
+ EXPORT_SYMBOL(mpage_writepages);
for (i = 0; i < nr; i++) {
tbh = arr[i];
if (likely(!buffer_uptodate(tbh)))
- submit_bh(REQ_OP_READ, 0, tbh);
+ submit_bh(REQ_OP_READ, tbh);
else
ntfs_end_buffer_async_read(tbh, 1);
}
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
need_end_writeback = false;
}
bh = next;
BUG_ON(!buffer_mapped(tbh));
get_bh(tbh);
tbh->b_end_io = end_buffer_write_sync;
- submit_bh(REQ_OP_WRITE, 0, tbh);
+ submit_bh(REQ_OP_WRITE, tbh);
}
/* Synchronize the mft mirror now if not @sync. */
if (is_mft && !sync)
.dirty_folio = block_dirty_folio,
#endif /* NTFS_RW */
.bmap = ntfs_bmap,
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
.writepage = ntfs_writepage,
.dirty_folio = block_dirty_folio,
#endif /* NTFS_RW */
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
.writepage = ntfs_writepage, /* Write dirty page to disk. */
.dirty_folio = filemap_dirty_folio,
#endif /* NTFS_RW */
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
err = PTR_ERR(page);
goto init_err_out;
}
- if (unlikely(PageError(page))) {
- put_page(page);
- err = -EIO;
- goto init_err_out;
- }
/*
* Update the initialized size in the ntfs inode. This is
* enough to make ntfs_writepage() work.
lock_buffer(bh);
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- return submit_bh(REQ_OP_READ, 0, bh);
+ return submit_bh(REQ_OP_READ, bh);
}
/**
bh->b_size = block_size;
off = vbo & (PAGE_SIZE - 1);
set_bh_page(bh, page, off);
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
err = -EIO;
static int ntfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct inode *inode = mapping->host;
- struct ntfs_inode *ni = ntfs_i(inode);
/* Redirect call to 'ntfs_writepage' for resident files. */
- get_block_t *get_block = is_resident(ni) ? NULL : &ntfs_get_block;
-
- return mpage_writepages(mapping, wbc, get_block);
+ if (is_resident(ntfs_i(mapping->host)))
+ return generic_writepages(mapping, wbc);
+ return mpage_writepages(mapping, wbc, ntfs_get_block);
}
static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn,
struct ntfs_buffers *nb, int sync);
int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run,
struct page **pages, u32 nr_pages, u64 vbo, u32 bytes,
- u32 op);
+ enum req_op op);
int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run);
int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run,
u64 vbo, u64 *lbo, u64 *bytes);
{
struct page *page = read_mapping_page(mapping, index, NULL);
- if (!IS_ERR(page)) {
+ if (!IS_ERR(page))
kmap(page);
- if (!PageError(page))
- return page;
- ntfs_unmap_page(page);
- return ERR_PTR(-EIO);
- }
return page;
}
static int ocfs2_read_folio(struct file *file, struct folio *folio)
{
- struct page *page = &folio->page;
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
- loff_t start = (loff_t)page->index << PAGE_SHIFT;
+ loff_t start = folio_pos(folio);
int ret, unlock = 1;
- trace_ocfs2_readpage((unsigned long long)oi->ip_blkno,
- (page ? page->index : 0));
+ trace_ocfs2_readpage((unsigned long long)oi->ip_blkno, folio->index);
- ret = ocfs2_inode_lock_with_page(inode, NULL, 0, page);
+ ret = ocfs2_inode_lock_with_page(inode, NULL, 0, &folio->page);
if (ret != 0) {
if (ret == AOP_TRUNCATED_PAGE)
unlock = 0;
if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
/*
- * Unlock the page and cycle ip_alloc_sem so that we don't
+ * Unlock the folio and cycle ip_alloc_sem so that we don't
* busyloop waiting for ip_alloc_sem to unlock
*/
ret = AOP_TRUNCATED_PAGE;
- unlock_page(page);
+ folio_unlock(folio);
unlock = 0;
down_read(&oi->ip_alloc_sem);
up_read(&oi->ip_alloc_sem);
* block_read_full_folio->get_block freaks out if it is asked to read
* beyond the end of a file, so we check here. Callers
* (generic_file_read, vm_ops->fault) are clever enough to check i_size
- * and notice that the page they just read isn't needed.
+ * and notice that the folio they just read isn't needed.
*
* XXX sys_readahead() seems to get that wrong?
*/
if (start >= i_size_read(inode)) {
- zero_user(page, 0, PAGE_SIZE);
- SetPageUptodate(page);
+ folio_zero_segment(folio, 0, folio_size(folio));
+ folio_mark_uptodate(folio);
ret = 0;
goto out_alloc;
}
if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
- ret = ocfs2_readpage_inline(inode, page);
+ ret = ocfs2_readpage_inline(inode, &folio->page);
else
- ret = block_read_full_folio(page_folio(page), ocfs2_get_block);
+ ret = block_read_full_folio(folio, ocfs2_get_block);
unlock = 0;
out_alloc:
ocfs2_inode_unlock(inode, 0);
out:
if (unlock)
- unlock_page(page);
+ folio_unlock(folio);
return ret;
}
!buffer_new(bh) &&
ocfs2_should_read_blk(inode, page, block_start) &&
(block_start < from || block_end > to)) {
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
*wait_bh++=bh;
}
.direct_IO = ocfs2_direct_IO,
.invalidate_folio = block_invalidate_folio,
.release_folio = ocfs2_release_folio,
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
* Otherwise, make sure the count is also block-aligned, having
* already confirmed the starting offsets' block alignment.
*/
- if (pos_in + count == size_in) {
+ if (pos_in + count == size_in &&
+ (!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) {
bcount = ALIGN(size_in, bs) - pos_in;
} else {
if (!IS_ALIGNED(count, bs))
/* Read a page's worth of file data into the page cache. */
static struct folio *vfs_dedupe_get_folio(struct file *file, loff_t pos)
{
- struct folio *folio;
-
- folio = read_mapping_folio(file->f_mapping, pos >> PAGE_SHIFT, file);
- if (IS_ERR(folio))
- return folio;
- if (!folio_test_uptodate(folio)) {
- folio_put(folio);
- return ERR_PTR(-EIO);
- }
- return folio;
+ return read_mapping_folio(file->f_mapping, pos >> PAGE_SHIFT, file);
}
/*
}
}
-static inline int zonefs_zone_mgmt(struct inode *inode,
- enum req_opf op)
+static inline int zonefs_zone_mgmt(struct inode *inode, enum req_op op)
{
struct zonefs_inode_info *zi = ZONEFS_I(inode);
int ret;
.dirty_folio = filemap_dirty_folio,
.release_folio = iomap_release_folio,
.invalidate_folio = iomap_invalidate_folio,
- .migratepage = iomap_migrate_page,
+ .migrate_folio = filemap_migrate_folio,
.is_partially_uptodate = iomap_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.direct_IO = noop_direct_IO,
{
struct zonefs_inode_info *zi = ZONEFS_I(inode);
loff_t old_isize;
- enum req_opf op;
+ enum req_op op;
int ret = 0;
/*
!uid_eq(iattr->ia_uid, inode->i_uid)) ||
((iattr->ia_valid & ATTR_GID) &&
!gid_eq(iattr->ia_gid, inode->i_gid))) {
- ret = dquot_transfer(inode, iattr);
+ ret = dquot_transfer(mnt_userns, inode, iattr);
if (ret)
return ret;
}
{
struct super_block *sb = parent->i_sb;
- inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
+ inode->i_ino = bdev_nr_zones(sb->s_bdev) + type + 1;
inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
inode->i_op = &zonefs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/*
* The first zone contains the super block: skip it.
*/
- end = zd->zones + blkdev_nr_zones(sb->s_bdev->bd_disk);
+ end = zd->zones + bdev_nr_zones(sb->s_bdev);
for (zone = &zd->zones[1]; zone < end; zone = next) {
next = zone + 1;
struct block_device *bdev = zd->sb->s_bdev;
int ret;
- zd->zones = kvcalloc(blkdev_nr_zones(bdev->bd_disk),
- sizeof(struct blk_zone), GFP_KERNEL);
+ zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone),
+ GFP_KERNEL);
if (!zd->zones)
return -ENOMEM;
return ret;
}
- if (ret != blkdev_nr_zones(bdev->bd_disk)) {
+ if (ret != bdev_nr_zones(bdev)) {
zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
- ret, blkdev_nr_zones(bdev->bd_disk));
+ ret, bdev_nr_zones(bdev));
return -EIO;
}
if (ret)
goto cleanup;
- zonefs_info(sb, "Mounting %u zones",
- blkdev_nr_zones(sb->s_bdev->bd_disk));
+ zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev));
if (!sbi->s_max_wro_seq_files &&
!sbi->s_max_active_seq_files &&
if (!inode)
goto cleanup;
- inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk);
+ inode->i_ino = bdev_nr_zones(sb->s_bdev);
inode->i_mode = S_IFDIR | 0555;
inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode);
inode->i_op = &zonefs_dir_inode_operations;
#define _LINUX_BUFFER_HEAD_H
#include <linux/types.h>
+#include <linux/blk_types.h>
#include <linux/fs.h>
#include <linux/linkage.h>
#include <linux/pagemap.h>
void free_buffer_head(struct buffer_head * bh);
void unlock_buffer(struct buffer_head *bh);
void __lock_buffer(struct buffer_head *bh);
-void ll_rw_block(int, int, int, struct buffer_head * bh[]);
+void ll_rw_block(blk_opf_t, int, struct buffer_head * bh[]);
int sync_dirty_buffer(struct buffer_head *bh);
-int __sync_dirty_buffer(struct buffer_head *bh, int op_flags);
-void write_dirty_buffer(struct buffer_head *bh, int op_flags);
-int submit_bh(int, int, struct buffer_head *);
+int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
+void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
+int submit_bh(blk_opf_t, struct buffer_head *);
void write_boundary_block(struct block_device *bdev,
sector_t bblock, unsigned blocksize);
int bh_uptodate_or_lock(struct buffer_head *bh);
}
sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
int block_truncate_page(struct address_space *, loff_t, get_block_t *);
- int nobh_write_begin(struct address_space *, loff_t, unsigned len,
- struct page **, void **, get_block_t*);
- int nobh_write_end(struct file *, struct address_space *,
- loff_t, unsigned, unsigned,
- struct page *, void *);
- int nobh_truncate_page(struct address_space *, loff_t, get_block_t *);
- int nobh_writepage(struct page *page, get_block_t *get_block,
- struct writeback_control *wbc);
+
+ #ifdef CONFIG_MIGRATION
+ extern int buffer_migrate_folio(struct address_space *,
+ struct folio *dst, struct folio *src, enum migrate_mode);
+ extern int buffer_migrate_folio_norefs(struct address_space *,
+ struct folio *dst, struct folio *src, enum migrate_mode);
+ #else
+ #define buffer_migrate_folio NULL
+ #define buffer_migrate_folio_norefs NULL
+ #endif
void buffer_init(void);
/* File supports async buffered reads */
#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000)
+/* File supports async nowait buffered writes */
+#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000)
+
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
struct iattr {
unsigned int ia_valid;
umode_t ia_mode;
- kuid_t ia_uid;
- kgid_t ia_gid;
+ /*
+ * The two anonymous unions wrap structures with the same member.
+ *
+ * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which
+ * are a dedicated type requiring the filesystem to use the dedicated
+ * helpers. Other filesystem can continue to use ia_{g,u}id until they
+ * have been ported.
+ *
+ * They always contain the same value. In other words FS_ALLOW_IDMAP
+ * pass down the same value on idmapped mounts as they would on regular
+ * mounts.
+ */
+ union {
+ kuid_t ia_uid;
+ vfsuid_t ia_vfsuid;
+ };
+ union {
+ kgid_t ia_gid;
+ vfsgid_t ia_vfsgid;
+ };
loff_t ia_size;
struct timespec64 ia_atime;
struct timespec64 ia_mtime;
void (*free_folio)(struct folio *folio);
ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
/*
- * migrate the contents of a page to the specified target. If
+ * migrate the contents of a folio to the specified target. If
* migrate_mode is MIGRATE_ASYNC, it must not block.
*/
- int (*migratepage) (struct address_space *,
- struct page *, struct page *, enum migrate_mode);
- bool (*isolate_page)(struct page *, isolate_mode_t);
- void (*putback_page)(struct page *);
+ int (*migrate_folio)(struct address_space *, struct folio *dst,
+ struct folio *src, enum migrate_mode);
int (*launder_folio)(struct folio *);
bool (*is_partially_uptodate) (struct folio *, size_t from,
size_t count);
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to map
*
+ * Note, this will eventually be removed completely in favor of the type-safe
+ * i_uid_into_vfsuid().
+ *
* Return: the inode's i_uid mapped down according to @mnt_userns.
* If the inode's i_uid has no mapping INVALID_UID is returned.
*/
static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns,
const struct inode *inode)
{
- return mapped_kuid_fs(mnt_userns, i_user_ns(inode), inode->i_uid);
+ return AS_KUIDT(make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid));
+}
+
+/**
+ * i_uid_into_vfsuid - map an inode's i_uid down into a mnt_userns
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: inode to map
+ *
+ * Return: whe inode's i_uid mapped down according to @mnt_userns.
+ * If the inode's i_uid has no mapping INVALID_VFSUID is returned.
+ */
+static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns,
+ const struct inode *inode)
+{
+ return make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid);
+}
+
+/**
+ * i_uid_needs_update - check whether inode's i_uid needs to be updated
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Check whether the $inode's i_uid field needs to be updated taking idmapped
+ * mounts into account if the filesystem supports it.
+ *
+ * Return: true if @inode's i_uid field needs to be updated, false if not.
+ */
+static inline bool i_uid_needs_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ const struct inode *inode)
+{
+ return ((attr->ia_valid & ATTR_UID) &&
+ !vfsuid_eq(attr->ia_vfsuid,
+ i_uid_into_vfsuid(mnt_userns, inode)));
+}
+
+/**
+ * i_uid_update - update @inode's i_uid field
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Safely update @inode's i_uid field translating the vfsuid of any idmapped
+ * mount into the filesystem kuid.
+ */
+static inline void i_uid_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ struct inode *inode)
+{
+ if (attr->ia_valid & ATTR_UID)
+ inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode),
+ attr->ia_vfsuid);
}
/**
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to map
*
+ * Note, this will eventually be removed completely in favor of the type-safe
+ * i_gid_into_vfsgid().
+ *
* Return: the inode's i_gid mapped down according to @mnt_userns.
* If the inode's i_gid has no mapping INVALID_GID is returned.
*/
static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns,
const struct inode *inode)
{
- return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid);
+ return AS_KGIDT(make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid));
+}
+
+/**
+ * i_gid_into_vfsgid - map an inode's i_gid down into a mnt_userns
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: inode to map
+ *
+ * Return: the inode's i_gid mapped down according to @mnt_userns.
+ * If the inode's i_gid has no mapping INVALID_VFSGID is returned.
+ */
+static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns,
+ const struct inode *inode)
+{
+ return make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid);
+}
+
+/**
+ * i_gid_needs_update - check whether inode's i_gid needs to be updated
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Check whether the $inode's i_gid field needs to be updated taking idmapped
+ * mounts into account if the filesystem supports it.
+ *
+ * Return: true if @inode's i_gid field needs to be updated, false if not.
+ */
+static inline bool i_gid_needs_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ const struct inode *inode)
+{
+ return ((attr->ia_valid & ATTR_GID) &&
+ !vfsgid_eq(attr->ia_vfsgid,
+ i_gid_into_vfsgid(mnt_userns, inode)));
+}
+
+/**
+ * i_gid_update - update @inode's i_gid field
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Safely update @inode's i_gid field translating the vfsgid of any idmapped
+ * mount into the filesystem kgid.
+ */
+static inline void i_gid_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ struct inode *inode)
+{
+ if (attr->ia_valid & ATTR_GID)
+ inode->i_gid = from_vfsgid(mnt_userns, i_user_ns(inode),
+ attr->ia_vfsgid);
}
/**
static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns,
struct inode *inode)
{
- return !uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
- !gid_valid(i_gid_into_mnt(mnt_userns, inode));
+ return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) ||
+ !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode));
}
static inline int iocb_flags(struct file *file);
}
extern int file_modified(struct file *file);
+int kiocb_modified(struct kiocb *iocb);
int sync_inode_metadata(struct inode *inode, int wait);
extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
- #ifdef CONFIG_MIGRATION
- extern int buffer_migrate_page(struct address_space *,
- struct page *, struct page *,
- enum migrate_mode);
- extern int buffer_migrate_page_norefs(struct address_space *,
- struct page *, struct page *,
- enum migrate_mode);
- #else
- #define buffer_migrate_page NULL
- #define buffer_migrate_page_norefs NULL
- #endif
-
int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
unsigned int ia_valid);
int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *);
void (*issue_read)(struct netfs_io_subrequest *subreq);
bool (*is_still_valid)(struct netfs_io_request *rreq);
int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
- struct folio *folio, void **_fsdata);
+ struct folio **foliop, void **_fsdata);
void (*done)(struct netfs_io_request *rreq);
};
};
struct readahead_control;
- extern void netfs_readahead(struct readahead_control *);
+ void netfs_readahead(struct readahead_control *);
int netfs_read_folio(struct file *, struct folio *);
- extern int netfs_write_begin(struct netfs_inode *,
- struct file *, struct address_space *,
- loff_t, unsigned int, struct folio **,
- void **);
-
- extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
- extern void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
- enum netfs_sreq_ref_trace what);
- extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
- bool was_async, enum netfs_sreq_ref_trace what);
- extern void netfs_stats_show(struct seq_file *);
+ int netfs_write_begin(struct netfs_inode *, struct file *,
+ struct address_space *, loff_t pos, unsigned int len,
+ struct folio **, void **fsdata);
+
+ void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
+ void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
+ enum netfs_sreq_ref_trace what);
+ void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
+ bool was_async, enum netfs_sreq_ref_trace what);
+ void netfs_stats_show(struct seq_file *);
/**
* netfs_inode - Get the netfs inode context from the inode
}
ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
- /**
- * 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.
- *
- * Return: %0 on success, negative error code otherwise.
- */
- int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
- {
- return __filemap_add_folio(mapping, page_folio(page), offset,
- gfp_mask, NULL);
- }
- EXPORT_SYMBOL(add_to_page_cache_locked);
-
int filemap_add_folio(struct address_space *mapping, struct folio *folio,
pgoff_t index, gfp_t gfp)
{
gfp |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
gfp &= ~__GFP_FS;
+ if (fgp_flags & FGP_NOWAIT) {
+ gfp &= ~GFP_KERNEL;
+ gfp |= GFP_NOWAIT | __GFP_NOWARN;
+ }
folio = filemap_alloc_folio(gfp, 0);
if (!folio)
return folio_batch_count(fbatch);
}
- static inline
- bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
- {
- if (!folio_test_large(folio) || folio_test_hugetlb(folio))
- return false;
- if (index >= max)
- return false;
- return index < folio->index + folio_nr_pages(folio) - 1;
- }
-
/**
- * find_get_pages_range - gang pagecache lookup
+ * filemap_get_folios - Get a batch of folios
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
- * @nr_pages: The maximum number of pages
- * @pages: Where the resulting pages are placed
+ * @fbatch: The batch to fill.
*
- * find_get_pages_range() will search for and return a group of up to @nr_pages
- * pages in the mapping starting at index @start and up to index @end
- * (inclusive). The pages are placed at @pages. find_get_pages_range() takes
- * a reference against the returned pages.
+ * Search for and return a batch of folios in the mapping starting at
+ * index @start and up to index @end (inclusive). The folios are returned
+ * in @fbatch with an elevated reference count.
*
- * The search returns a group of mapping-contiguous pages with ascending
- * indexes. There may be holes in the indices due to not-present pages.
- * We also update @start to index the next page for the traversal.
+ * The first folio may start before @start; if it does, it will contain
+ * @start. The final folio may extend beyond @end; if it does, it will
+ * contain @end. The folios have ascending indices. There may be gaps
+ * between the folios if there are indices which have no folio in the
+ * page cache. If folios are added to or removed from the page cache
+ * while this is running, they may or may not be found by this call.
*
- * Return: the number of pages which were found. If this number is
- * smaller than @nr_pages, the end of specified range has been
- * reached.
+ * Return: The number of folios which were found.
+ * We also update @start to index the next folio for the traversal.
*/
- unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
- pgoff_t end, unsigned int nr_pages,
- struct page **pages)
+ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
+ pgoff_t end, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
- unsigned ret = 0;
-
- if (unlikely(!nr_pages))
- return 0;
rcu_read_lock();
- while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
+ while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) {
/* Skip over shadow, swap and DAX entries */
if (xa_is_value(folio))
continue;
+ if (!folio_batch_add(fbatch, folio)) {
+ unsigned long nr = folio_nr_pages(folio);
- again:
- pages[ret] = folio_file_page(folio, xas.xa_index);
- if (++ret == nr_pages) {
- *start = xas.xa_index + 1;
+ if (folio_test_hugetlb(folio))
+ nr = 1;
+ *start = folio->index + nr;
goto out;
}
- if (folio_more_pages(folio, xas.xa_index, end)) {
- xas.xa_index++;
- folio_ref_inc(folio);
- goto again;
- }
}
/*
out:
rcu_read_unlock();
- return ret;
+ return folio_batch_count(fbatch);
+ }
+ EXPORT_SYMBOL(filemap_get_folios);
+
+ static inline
+ bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
+ {
+ if (!folio_test_large(folio) || folio_test_hugetlb(folio))
+ return false;
+ if (index >= max)
+ return false;
+ return index < folio->index + folio_nr_pages(folio) - 1;
}
/**
rcu_read_unlock();
}
- static int filemap_read_folio(struct file *file, struct address_space *mapping,
+ static int filemap_read_folio(struct file *file, filler_t filler,
struct folio *folio)
{
int error;
*/
folio_clear_error(folio);
/* Start the actual read. The read will unlock the page. */
- error = mapping->a_ops->read_folio(file, folio);
+ error = filler(file, folio);
if (error)
return error;
return error;
if (folio_test_uptodate(folio))
return 0;
- shrink_readahead_size_eio(&file->f_ra);
+ if (file)
+ shrink_readahead_size_eio(&file->f_ra);
return -EIO;
}
if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
goto unlock;
- error = filemap_read_folio(iocb->ki_filp, mapping, folio);
+ error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio,
+ folio);
goto unlock_mapping;
unlock:
folio_unlock(folio);
if (error)
goto error;
- error = filemap_read_folio(file, mapping, folio);
+ error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
if (error)
goto error;
* and we need to check for errors.
*/
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- error = filemap_read_folio(file, mapping, folio);
+ error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
if (fpin)
goto out_retry;
folio_put(folio);
return ERR_PTR(err);
}
- filler:
- err = filler(file, folio);
- if (err < 0) {
- folio_put(folio);
- return ERR_PTR(err);
- }
-
- folio_wait_locked(folio);
- if (!folio_test_uptodate(folio)) {
- folio_put(folio);
- return ERR_PTR(-EIO);
- }
-
- goto out;
+ goto filler;
}
if (folio_test_uptodate(folio))
goto out;
goto out;
}
- /*
- * A previous I/O error may have been due to temporary
- * failures.
- * Clear page error before actual read, PG_error will be
- * set again if read page fails.
- */
- folio_clear_error(folio);
- goto filler;
+ filler:
+ err = filemap_read_folio(file, filler, folio);
+ if (err) {
+ folio_put(folio);
+ if (err == AOP_TRUNCATED_PAGE)
+ goto repeat;
+ return ERR_PTR(err);
+ }
out:
folio_mark_accessed(folio);
* sharing with another vma.
*/
;
- } else if (unlikely(is_hugetlb_entry_migration(entry) ||
- is_hugetlb_entry_hwpoisoned(entry))) {
+ } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
+ bool uffd_wp = huge_pte_uffd_wp(entry);
+
+ if (!userfaultfd_wp(dst_vma) && uffd_wp)
+ entry = huge_pte_clear_uffd_wp(entry);
+ set_huge_pte_at(dst, addr, dst_pte, entry);
+ } else if (unlikely(is_hugetlb_entry_migration(entry))) {
swp_entry_t swp_entry = pte_to_swp_entry(entry);
bool uffd_wp = huge_pte_uffd_wp(entry);
int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t idx)
{
+ struct folio *folio = page_folio(page);
struct inode *inode = mapping->host;
struct hstate *h = hstate_inode(inode);
- int err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+ int err;
- if (err)
+ __folio_set_locked(folio);
+ err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL);
+
+ if (unlikely(err)) {
+ __folio_clear_locked(folio);
return err;
+ }
ClearHPageRestoreReserve(page);
/*
- * set page dirty so that it will not be removed from cache/file
+ * mark folio dirty so that it will not be removed from cache/file
* by non-hugetlbfs specific code paths.
*/
- set_page_dirty(page);
+ folio_mark_dirty(folio);
spin_lock(&inode->i_lock);
inode->i_blocks += blocks_per_huge_page(h);
page = alloc_huge_page(dst_vma, dst_addr, 0);
if (IS_ERR(page)) {
+ put_page(*pagep);
ret = -ENOMEM;
*pagep = NULL;
goto out;
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
+static bool hw_memory_failure __read_mostly = false;
+
static bool __page_handle_poison(struct page *page)
{
int ret;
mutex_lock(&mf_mutex);
+ if (!(flags & MF_SW_SIMULATED))
+ hw_memory_failure = true;
+
p = pfn_to_online_page(pfn);
if (!p) {
res = arch_memory_failure(pfn, flags);
/*
* Now take care of user space mappings.
- * Abort on fail: __delete_from_page_cache() assumes unmapped page.
+ * Abort on fail: __filemap_remove_folio() assumes unmapped page.
*/
if (!hwpoison_user_mappings(p, pfn, flags, p)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
mutex_lock(&mf_mutex);
+ if (hw_memory_failure) {
+ unpoison_pr_info("Unpoison: Disabled after HW memory failure %#lx\n",
+ pfn, &unpoison_rs);
+ ret = -EOPNOTSUPP;
+ goto unlock_mutex;
+ }
+
if (!PageHWPoison(p)) {
unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
pfn, &unpoison_rs);
gfp_t gfp = vmf->gfp_mask;
unsigned long addr;
struct page *page;
+ vm_fault_t ret;
int err;
if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
return vmf_error(-EINVAL);
+ filemap_invalidate_lock_shared(mapping);
+
retry:
page = find_lock_page(mapping, offset);
if (!page) {
page = alloc_page(gfp | __GFP_ZERO);
- if (!page)
- return VM_FAULT_OOM;
+ if (!page) {
+ ret = VM_FAULT_OOM;
+ goto out;
+ }
err = set_direct_map_invalid_noflush(page);
if (err) {
put_page(page);
- return vmf_error(err);
+ ret = vmf_error(err);
+ goto out;
}
__SetPageUptodate(page);
if (err == -EEXIST)
goto retry;
- return vmf_error(err);
+ ret = vmf_error(err);
+ goto out;
}
addr = (unsigned long)page_address(page);
}
vmf->page = page;
- return VM_FAULT_LOCKED;
+ ret = VM_FAULT_LOCKED;
+
+out:
+ filemap_invalidate_unlock_shared(mapping);
+ return ret;
}
static const struct vm_operations_struct secretmem_vm_ops = {
.mmap = secretmem_mmap,
};
- static bool secretmem_isolate_page(struct page *page, isolate_mode_t mode)
- {
- return false;
- }
-
- static int secretmem_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page,
- enum migrate_mode mode)
+ static int secretmem_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
{
return -EBUSY;
}
const struct address_space_operations secretmem_aops = {
.dirty_folio = noop_dirty_folio,
.free_folio = secretmem_free_folio,
- .migratepage = secretmem_migratepage,
- .isolate_page = secretmem_isolate_page,
+ .migrate_folio = secretmem_migrate_folio,
};
static int secretmem_setattr(struct user_namespace *mnt_userns,
struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
+ struct address_space *mapping = inode->i_mapping;
unsigned int ia_valid = iattr->ia_valid;
+ int ret;
+
+ filemap_invalidate_lock(mapping);
if ((ia_valid & ATTR_SIZE) && inode->i_size)
- return -EINVAL;
+ ret = -EINVAL;
+ else
+ ret = simple_setattr(mnt_userns, dentry, iattr);
- return simple_setattr(mnt_userns, dentry, iattr);
+ filemap_invalidate_unlock(mapping);
+
+ return ret;
}
static const struct inode_operations secretmem_iops = {
{
struct file *file = ERR_PTR(-ENOMEM);
struct inode *inode;
+ const char *anon_name = "[secretmem]";
+ const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name));
+ int err;
inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
if (IS_ERR(inode))
return ERR_CAST(inode);
+ err = security_inode_init_security_anon(inode, &qname, NULL);
+ if (err) {
+ file = ERR_PTR(err);
+ goto err_free_inode;
+ }
+
file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
O_RDWR, &secretmem_fops);
if (IS_ERR(file))
struct shmem_inode_info *info = SHMEM_I(inode);
unsigned long flags;
- /* nrpages adjustment done by __delete_from_page_cache() or caller */
+ /* nrpages adjustment done by __filemap_remove_folio() or caller */
spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * Like add_to_page_cache_locked, but error if expected item has gone.
+ * Like filemap_add_folio, but error if expected item has gone.
*/
static int shmem_add_to_page_cache(struct folio *folio,
struct address_space *mapping,
*/
void shmem_unlock_mapping(struct address_space *mapping)
{
- struct pagevec pvec;
+ struct folio_batch fbatch;
pgoff_t index = 0;
- pagevec_init(&pvec);
+ folio_batch_init(&fbatch);
/*
* Minor point, but we might as well stop if someone else SHM_LOCKs it.
*/
- while (!mapping_unevictable(mapping)) {
- if (!pagevec_lookup(&pvec, mapping, &index))
- break;
- check_move_unevictable_pages(&pvec);
- pagevec_release(&pvec);
+ while (!mapping_unevictable(mapping) &&
+ filemap_get_folios(mapping, &index, ~0UL, &fbatch)) {
+ check_move_unevictable_folios(&fbatch);
+ folio_batch_release(&fbatch);
cond_resched();
}
}
break;
case Opt_nr_blocks:
ctx->blocks = memparse(param->string, &rest);
- if (*rest)
+ if (*rest || ctx->blocks > S64_MAX)
goto bad_value;
ctx->seen |= SHMEM_SEEN_BLOCKS;
break;
raw_spin_lock(&sbinfo->stat_lock);
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
- if (ctx->blocks > S64_MAX) {
- err = "Number of blocks too large";
- goto out;
- }
+
if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
if (!sbinfo->max_blocks) {
err = "Cannot retroactively limit size";
.write_end = shmem_write_end,
#endif
#ifdef CONFIG_MIGRATION
- .migratepage = migrate_page,
+ .migrate_folio = migrate_folio,
#endif
.error_remove_page = shmem_error_remove_page,
};
* lru_disable_count = 0 will have exited the critical
* section when synchronize_rcu() returns.
*/
- synchronize_rcu();
+ synchronize_rcu_expedited();
#ifdef CONFIG_SMP
__lru_add_drain_all(true);
#else
fbatch->nr = j;
}
- /**
- * pagevec_lookup_range - gang pagecache lookup
- * @pvec: Where the resulting pages are placed
- * @mapping: The address_space to search
- * @start: The starting page index
- * @end: The final page index
- *
- * pagevec_lookup_range() will search for & return a group of up to PAGEVEC_SIZE
- * pages in the mapping starting from index @start and upto index @end
- * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a
- * reference against the pages in @pvec.
- *
- * The search returns a group of mapping-contiguous pages with ascending
- * indexes. There may be holes in the indices due to not-present pages. We
- * also update @start to index the next page for the traversal.
- *
- * pagevec_lookup_range() returns the number of pages which were found. If this
- * number is smaller than PAGEVEC_SIZE, the end of specified range has been
- * reached.
- */
- unsigned pagevec_lookup_range(struct pagevec *pvec,
- struct address_space *mapping, pgoff_t *start, pgoff_t end)
- {
- pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE,
- pvec->pages);
- return pagevec_count(pvec);
- }
- EXPORT_SYMBOL(pagevec_lookup_range);
-
unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
xa_mark_t tag)