loff_t len, int mode)
{
struct inode *inode = file_inode(file);
+ struct address_space *mapping = file->f_mapping;
handle_t *handle = NULL;
unsigned int max_blocks;
loff_t new_size = 0;
* Prevent page faults from reinstantiating pages we have
* released from page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
goto out_mutex;
}
ret = ext4_update_disksize_before_punch(inode, offset, len);
if (ret) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
goto out_mutex;
}
/* Now release the pages and zero block aligned part of pages */
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags);
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
if (ret)
goto out_mutex;
}
static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
+ struct address_space *mapping = inode->i_mapping;
ext4_lblk_t punch_start, punch_stop;
handle_t *handle;
unsigned int credits;
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret)
* Write tail of the last page before removed range since it will get
* removed from the page cache below.
*/
- ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+ ret = filemap_write_and_wait_range(mapping, ioffset, offset);
if (ret)
goto out_mmap;
/*
* Write data that will be shifted to preserve them when discarding
* page cache below. We are also protected from pages becoming dirty
- * by i_mmap_sem.
+ * by i_rwsem and invalidate_lock.
*/
- ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+ ret = filemap_write_and_wait_range(mapping, offset + len,
LLONG_MAX);
if (ret)
goto out_mmap;
ext4_journal_stop(handle);
ext4_fc_stop_ineligible(sb);
out_mmap:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
out_mutex:
inode_unlock(inode);
return ret;
static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
+ struct address_space *mapping = inode->i_mapping;
handle_t *handle;
struct ext4_ext_path *path;
struct ext4_extent *extent;
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret)
ext4_journal_stop(handle);
ext4_fc_stop_ineligible(sb);
out_mmap:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
out_mutex:
inode_unlock(inode);
return ret;
}
/* Check if *cur is a hole and if it is, skip it */
- static void skip_hole(struct inode *inode, ext4_lblk_t *cur)
+ static int skip_hole(struct inode *inode, ext4_lblk_t *cur)
{
int ret;
struct ext4_map_blocks map;
map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur;
ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret < 0)
+ return ret;
if (ret != 0)
- return;
+ return 0;
*cur = *cur + map.m_len;
+ return 0;
}
/* Count number of blocks used by this inode and update i_blocks */
* iblocks by total number of differences found.
*/
cur = 0;
- skip_hole(inode, &cur);
+ ret = skip_hole(inode, &cur);
+ if (ret < 0)
+ goto out;
path = ext4_find_extent(inode, cur, NULL, 0);
if (IS_ERR(path))
goto out;
}
cur = max(cur + 1, le32_to_cpu(ex->ee_block) +
ext4_ext_get_actual_len(ex));
- skip_hole(inode, &cur);
-
+ ret = skip_hole(inode, &cur);
+ if (ret < 0) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ break;
+ }
path2 = ext4_find_extent(inode, cur, NULL, 0);
if (IS_ERR(path2)) {
ext4_ext_drop_refs(path);
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int i_size_changed = 0;
- int inline_data = ext4_has_inline_data(inode);
bool verity = ext4_verity_in_progress(inode);
trace_ext4_write_end(inode, pos, len, copied);
- if (inline_data) {
- ret = ext4_write_inline_data_end(inode, pos, len,
- copied, page);
- if (ret < 0) {
- unlock_page(page);
- put_page(page);
- goto errout;
- }
- copied = ret;
- } else
- copied = block_write_end(file, mapping, pos,
- len, copied, page, fsdata);
+
+ if (ext4_has_inline_data(inode))
+ return ext4_write_inline_data_end(inode, pos, len, copied, page);
+
+ copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
/*
* it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
* ordering of page lock and transaction start for journaling
* filesystems.
*/
- if (i_size_changed || inline_data)
+ if (i_size_changed)
ret = ext4_mark_inode_dirty(handle, inode);
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
- errout:
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
int partial = 0;
unsigned from, to;
int size_changed = 0;
- int inline_data = ext4_has_inline_data(inode);
bool verity = ext4_verity_in_progress(inode);
trace_ext4_journalled_write_end(inode, pos, len, copied);
BUG_ON(!ext4_handle_valid(handle));
- if (inline_data) {
- ret = ext4_write_inline_data_end(inode, pos, len,
- copied, page);
- if (ret < 0) {
- unlock_page(page);
- put_page(page);
- goto errout;
- }
- copied = ret;
- } else if (unlikely(copied < len) && !PageUptodate(page)) {
+ if (ext4_has_inline_data(inode))
+ return ext4_write_inline_data_end(inode, pos, len, copied, page);
+
+ if (unlikely(copied < len) && !PageUptodate(page)) {
copied = 0;
ext4_journalled_zero_new_buffers(handle, inode, page, from, to);
} else {
if (old_size < pos && !verity)
pagecache_isize_extended(inode, old_size, pos);
- if (size_changed || inline_data) {
+ if (size_changed) {
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
*/
ext4_orphan_add(handle, inode);
- errout:
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int ret;
bool allocated = false;
+ bool reserved = false;
/*
* If the cluster containing lblk is shared with a delayed,
ret = ext4_da_reserve_space(inode);
if (ret != 0) /* ENOSPC */
goto errout;
+ reserved = true;
} else { /* bigalloc */
if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
if (!ext4_es_scan_clu(inode,
ret = ext4_da_reserve_space(inode);
if (ret != 0) /* ENOSPC */
goto errout;
+ reserved = true;
} else {
allocated = true;
}
}
ret = ext4_es_insert_delayed_block(inode, lblk, allocated);
+ if (ret && reserved)
+ ext4_da_release_space(inode, 1);
errout:
return ret;
}
/*
- * Delayed extent could be allocated by fallocate.
- * So we need to check it.
+ * the buffer head associated with a delayed and not unwritten
+ * block found in the extent status cache must contain an
+ * invalid block number and have its BH_New and BH_Delay bits
+ * set, reflecting the state assigned when the block was
+ * initially delayed allocated
*/
- if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
- map_bh(bh, inode->i_sb, invalid_block);
- set_buffer_new(bh);
- set_buffer_delay(bh);
+ if (ext4_es_is_delonly(&es)) {
+ BUG_ON(bh->b_blocknr != invalid_block);
+ BUG_ON(!buffer_new(bh));
+ BUG_ON(!buffer_delay(bh));
return 0;
}
return 0;
}
- /* We always reserve for an inode update; the superblock could be there too */
- static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len)
- {
- if (likely(ext4_has_feature_large_file(inode->i_sb)))
- return 1;
-
- if (pos + len <= 0x7fffffffULL)
- return 1;
-
- /* We might need to update the superblock to set LARGE_FILE */
- return 2;
- }
-
static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
struct page *page;
pgoff_t index;
struct inode *inode = mapping->host;
- handle_t *handle;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
return 0;
}
- /*
- * grab_cache_page_write_begin() can take a long time if the
- * system is thrashing due to memory pressure, or if the page
- * is being written back. So grab it first before we start
- * the transaction handle. This also allows us to allocate
- * the page (if needed) without using GFP_NOFS.
- */
- retry_grab:
+ retry:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
- unlock_page(page);
- /*
- * With delayed allocation, we don't log the i_disksize update
- * if there is delayed block allocation. But we still need
- * to journalling the i_disksize update if writes to the end
- * of file which has an already mapped buffer.
- */
- retry_journal:
- handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
- ext4_da_write_credits(inode, pos, len));
- if (IS_ERR(handle)) {
- put_page(page);
- return PTR_ERR(handle);
- }
-
- lock_page(page);
- if (page->mapping != mapping) {
- /* The page got truncated from under us */
- unlock_page(page);
- put_page(page);
- ext4_journal_stop(handle);
- goto retry_grab;
- }
/* In case writeback began while the page was unlocked */
wait_for_stable_page(page);
#endif
if (ret < 0) {
unlock_page(page);
- ext4_journal_stop(handle);
+ put_page(page);
/*
* block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
- * i_size_read because we hold i_mutex.
+ * i_size_read because we hold inode lock.
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry_journal;
-
- put_page(page);
+ goto retry;
return ret;
}
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
- int ret = 0, ret2;
- handle_t *handle = ext4_journal_current_handle();
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
len, copied, page, fsdata);
trace_ext4_da_write_end(inode, pos, len, copied);
+
+ if (write_mode != CONVERT_INLINE_DATA &&
+ ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
+ ext4_has_inline_data(inode))
+ return ext4_write_inline_data_end(inode, pos, len, copied, page);
+
start = pos & (PAGE_SIZE - 1);
end = start + copied - 1;
/*
- * generic_write_end() will run mark_inode_dirty() if i_size
- * changes. So let's piggyback the i_disksize mark_inode_dirty
- * into that.
+ * Since we are holding inode lock, we are sure i_disksize <=
+ * i_size. We also know that if i_disksize < i_size, there are
+ * delalloc writes pending in the range upto i_size. If the end of
+ * the current write is <= i_size, there's no need to touch
+ * i_disksize since writeback will push i_disksize upto i_size
+ * eventually. If the end of the current write is > i_size and
+ * inside an allocated block (ext4_da_should_update_i_disksize()
+ * check), we need to update i_disksize here as neither
+ * ext4_writepage() nor certain ext4_writepages() paths not
+ * allocating blocks update i_disksize.
+ *
+ * Note that we defer inode dirtying to generic_write_end() /
+ * ext4_da_write_inline_data_end().
*/
new_i_size = pos + copied;
- if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
- if (ext4_has_inline_data(inode) ||
- ext4_da_should_update_i_disksize(page, end)) {
- ext4_update_i_disksize(inode, new_i_size);
- /* We need to mark inode dirty even if
- * new_i_size is less that inode->i_size
- * bu greater than i_disksize.(hint delalloc)
- */
- ret = ext4_mark_inode_dirty(handle, inode);
- }
- }
+ if (copied && new_i_size > inode->i_size &&
+ ext4_da_should_update_i_disksize(page, end))
+ ext4_update_i_disksize(inode, new_i_size);
- if (write_mode != CONVERT_INLINE_DATA &&
- ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
- ext4_has_inline_data(inode))
- ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied,
- page);
- else
- ret2 = generic_write_end(file, mapping, pos, len, copied,
- page, fsdata);
-
- copied = ret2;
- if (ret2 < 0)
- ret = ret2;
- ret2 = ext4_journal_stop(handle);
- if (unlikely(ret2 && !ret))
- ret = ret2;
-
- return ret ? ret : copied;
+ return generic_write_end(file, mapping, pos, len, copied, page, fsdata);
}
/*
return ret;
}
-static void ext4_wait_dax_page(struct ext4_inode_info *ei)
+static void ext4_wait_dax_page(struct inode *inode)
{
- up_write(&ei->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
schedule();
- down_write(&ei->i_mmap_sem);
+ filemap_invalidate_lock(inode->i_mapping);
}
int ext4_break_layouts(struct inode *inode)
{
- struct ext4_inode_info *ei = EXT4_I(inode);
struct page *page;
int error;
- if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+ if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
return -EINVAL;
do {
error = ___wait_var_event(&page->_refcount,
atomic_read(&page->_refcount) == 1,
TASK_INTERRUPTIBLE, 0, 0,
- ext4_wait_dax_page(ei));
+ ext4_wait_dax_page(inode));
} while (error == 0);
return error;
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
if (ext4_has_inline_data(inode)) {
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_convert_inline_data(inode);
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
if (ret)
return ret;
}
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(mapping);
ret = ext4_break_layouts(inode);
if (ret)
out_stop:
ext4_journal_stop(handle);
out_dio:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(mapping);
out_mutex:
inode_unlock(inode);
return ret;
goto has_buffer;
lock_buffer(bh);
+ if (ext4_buffer_uptodate(bh)) {
+ /* Someone brought it uptodate while we waited */
+ unlock_buffer(bh);
+ goto has_buffer;
+ }
+
/*
* If we have all information of the inode in memory and this
* is the only valid inode in the block, we need not read the
inode_dio_wait(inode);
}
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(inode->i_mapping);
rc = ext4_break_layouts(inode);
if (rc) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
goto err_out;
}
error = rc;
}
out_mmap_sem:
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
}
if (!error) {
* data (and journalled aops don't know how to handle these cases).
*/
if (val) {
- down_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock(inode->i_mapping);
err = filemap_write_and_wait(inode->i_mapping);
if (err < 0) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
return err;
}
}
percpu_up_write(&sbi->s_writepages_rwsem);
if (val)
- up_write(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock(inode->i_mapping);
/* Finally we can mark the inode as dirty. */
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_lock_shared(mapping);
err = ext4_convert_inline_data(inode);
if (err)
out_ret:
ret = block_page_mkwrite_return(err);
out:
- up_read(&EXT4_I(inode)->i_mmap_sem);
+ filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(inode->i_sb);
return ret;
out_error:
ext4_journal_stop(handle);
goto out;
}
-
-vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)
-{
- struct inode *inode = file_inode(vmf->vma->vm_file);
- vm_fault_t ret;
-
- down_read(&EXT4_I(inode)->i_mmap_sem);
- ret = filemap_fault(vmf);
- up_read(&EXT4_I(inode)->i_mmap_sem);
-
- return ret;
-}
/*
* Lock ordering
*
- * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
- * i_mmap_rwsem (inode->i_mmap_rwsem)!
- *
* page fault path:
- * mmap_lock -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
- * page lock -> i_data_sem (rw)
+ * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
+ * -> page lock -> i_data_sem (rw)
*
* buffered write path:
* sb_start_write -> i_mutex -> mmap_lock
* i_data_sem (rw)
*
* truncate:
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> i_mmap_rwsem (w) -> page lock
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> transaction start ->
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
+ * page lock
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start ->
* i_data_sem (rw)
*
* direct IO:
* constraints, it may not be safe to do it right here so we
* defer superblock flushing to a workqueue.
*/
- if (continue_fs)
+ if (continue_fs && journal)
schedule_work(&EXT4_SB(sb)->s_error_work);
else
ext4_commit_super(sb);
true);
dump_stack();
}
+
+ if (EXT4_I(inode)->i_reserved_data_blocks)
+ ext4_msg(inode->i_sb, KERN_ERR,
+ "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!",
+ inode->i_ino, EXT4_I(inode),
+ EXT4_I(inode)->i_reserved_data_blocks);
}
static void init_once(void *foo)
INIT_LIST_HEAD(&ei->i_orphan);
init_rwsem(&ei->xattr_sem);
init_rwsem(&ei->i_data_sem);
- init_rwsem(&ei->i_mmap_sem);
inode_init_once(&ei->vfs_inode);
ext4_fc_init_inode(&ei->vfs_inode);
}
*/
static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
{
- loff_t res = EXT4_NDIR_BLOCKS;
+ unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS;
int meta_blocks;
- loff_t upper_limit;
- /* This is calculated to be the largest file size for a dense, block
+
+ /*
+ * This is calculated to be the largest file size for a dense, block
* mapped file such that the file's total number of 512-byte sectors,
* including data and all indirect blocks, does not exceed (2^48 - 1).
*
* __u32 i_blocks_lo and _u16 i_blocks_high represent the total
* number of 512-byte sectors of the file.
*/
-
if (!has_huge_files) {
/*
* !has_huge_files or implies that the inode i_block field
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
- return res;
+ return (loff_t)res;
}
static ext4_fsblk_t descriptor_loc(struct super_block *sb,
goto failed_mount;
}
- if (bdev_dax_supported(sb->s_bdev, blocksize))
+ if (dax_supported(dax_dev, sb->s_bdev, blocksize, 0,
+ bdev_nr_sectors(sb->s_bdev)))
set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
sbi->s_ea_block_cache = NULL;
if (sbi->s_journal) {
+ /* flush s_error_work before journal destroy. */
+ flush_work(&sbi->s_error_work);
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
failed_mount3a:
ext4_es_unregister_shrinker(sbi);
failed_mount3:
+ /* flush s_error_work before sbi destroy */
flush_work(&sbi->s_error_work);
del_timer_sync(&sbi->s_err_report);
ext4_stop_mmpd(sbi);
projects / platform / kernel / linux-rpi.git / commitdiff