linux/fs/ocfs2/aops.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
 */

#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <asm/byteorder.h>
#include <linux/swap.h>
#include <linux/mpage.h>
#include <linux/quotaops.h>
#include <linux/blkdev.h>
#include <linux/uio.h>
#include <linux/mm.h>

#include <cluster/masklog.h>

#include "ocfs2.h"

#include "alloc.h"
#include "aops.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "file.h"
#include "inode.h"
#include "journal.h"
#include "suballoc.h"
#include "super.h"
#include "symlink.h"
#include "refcounttree.h"
#include "ocfs2_trace.h"

#include "buffer_head_io.h"
#include "dir.h"
#include "namei.h"
#include "sysfile.h"

static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
				   struct buffer_head *bh_result, int create)
{ … }

static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock,
		    struct buffer_head *bh_result, int create)
{ … }

int ocfs2_get_block(struct inode *inode, sector_t iblock,
		    struct buffer_head *bh_result, int create)
{ … }

int ocfs2_read_inline_data(struct inode *inode, struct page *page,
			   struct buffer_head *di_bh)
{ … }

static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
{ … }

static int ocfs2_read_folio(struct file *file, struct folio *folio)
{ … }

/*
 * This is used only for read-ahead. Failures or difficult to handle
 * situations are safe to ignore.
 *
 * Right now, we don't bother with BH_Boundary - in-inode extent lists
 * are quite large (243 extents on 4k blocks), so most inodes don't
 * grow out to a tree. If need be, detecting boundary extents could
 * trivially be added in a future version of ocfs2_get_block().
 */
static void ocfs2_readahead(struct readahead_control *rac)
{ … }

/* Note: Because we don't support holes, our allocation has
 * already happened (allocation writes zeros to the file data)
 * so we don't have to worry about ordered writes in
 * ocfs2_writepages.
 *
 * ->writepages is called during the process of invalidating the page cache
 * during blocked lock processing.  It can't block on any cluster locks
 * to during block mapping.  It's relying on the fact that the block
 * mapping can't have disappeared under the dirty pages that it is
 * being asked to write back.
 */
static int ocfs2_writepages(struct address_space *mapping,
		struct writeback_control *wbc)
{ … }

/* Taken from ext3. We don't necessarily need the full blown
 * functionality yet, but IMHO it's better to cut and paste the whole
 * thing so we can avoid introducing our own bugs (and easily pick up
 * their fixes when they happen) --Mark */
int walk_page_buffers(	handle_t *handle,
			struct buffer_head *head,
			unsigned from,
			unsigned to,
			int *partial,
			int (*fn)(	handle_t *handle,
					struct buffer_head *bh))
{ … }

static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
{ … }

static bool ocfs2_release_folio(struct folio *folio, gfp_t wait)
{ … }

static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
					    u32 cpos,
					    unsigned int *start,
					    unsigned int *end)
{ … }

/*
 * 'from' and 'to' are the region in the page to avoid zeroing.
 *
 * If pagesize > clustersize, this function will avoid zeroing outside
 * of the cluster boundary.
 *
 * from == to == 0 is code for "zero the entire cluster region"
 */
static void ocfs2_clear_page_regions(struct page *page,
				     struct ocfs2_super *osb, u32 cpos,
				     unsigned from, unsigned to)
{ … }

/*
 * Nonsparse file systems fully allocate before we get to the write
 * code. This prevents ocfs2_write() from tagging the write as an
 * allocating one, which means ocfs2_map_page_blocks() might try to
 * read-in the blocks at the tail of our file. Avoid reading them by
 * testing i_size against each block offset.
 */
static int ocfs2_should_read_blk(struct inode *inode, struct folio *folio,
				 unsigned int block_start)
{ … }

/*
 * Some of this taken from __block_write_begin(). We already have our
 * mapping by now though, and the entire write will be allocating or
 * it won't, so not much need to use BH_New.
 *
 * This will also skip zeroing, which is handled externally.
 */
int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
			  struct inode *inode, unsigned int from,
			  unsigned int to, int new)
{ … }

#if (PAGE_SIZE >= OCFS2_MAX_CLUSTERSIZE)
#define OCFS2_MAX_CTXT_PAGES …
#else
#define OCFS2_MAX_CTXT_PAGES …
#endif

#define OCFS2_MAX_CLUSTERS_PER_PAGE …

struct ocfs2_unwritten_extent { … };

/*
 * Describe the state of a single cluster to be written to.
 */
struct ocfs2_write_cluster_desc { … };

struct ocfs2_write_ctxt { … };

void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
{ … }

static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
{ … }

static void ocfs2_free_unwritten_list(struct inode *inode,
				 struct list_head *head)
{ … }

static void ocfs2_free_write_ctxt(struct inode *inode,
				  struct ocfs2_write_ctxt *wc)
{ … }

static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
				  struct ocfs2_super *osb, loff_t pos,
				  unsigned len, ocfs2_write_type_t type,
				  struct buffer_head *di_bh)
{ … }

/*
 * If a page has any new buffers, zero them out here, and mark them uptodate
 * and dirty so they'll be written out (in order to prevent uninitialised
 * block data from leaking). And clear the new bit.
 */
static void ocfs2_zero_new_buffers(struct page *page, unsigned from, unsigned to)
{ … }

/*
 * Only called when we have a failure during allocating write to write
 * zero's to the newly allocated region.
 */
static void ocfs2_write_failure(struct inode *inode,
				struct ocfs2_write_ctxt *wc,
				loff_t user_pos, unsigned user_len)
{ … }

static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
					struct ocfs2_write_ctxt *wc,
					struct page *page, u32 cpos,
					loff_t user_pos, unsigned user_len,
					int new)
{ … }

/*
 * This function will only grab one clusters worth of pages.
 */
static int ocfs2_grab_pages_for_write(struct address_space *mapping,
				      struct ocfs2_write_ctxt *wc,
				      u32 cpos, loff_t user_pos,
				      unsigned user_len, int new,
				      struct page *mmap_page)
{ … }

/*
 * Prepare a single cluster for write one cluster into the file.
 */
static int ocfs2_write_cluster(struct address_space *mapping,
			       u32 *phys, unsigned int new,
			       unsigned int clear_unwritten,
			       unsigned int should_zero,
			       struct ocfs2_alloc_context *data_ac,
			       struct ocfs2_alloc_context *meta_ac,
			       struct ocfs2_write_ctxt *wc, u32 cpos,
			       loff_t user_pos, unsigned user_len)
{ … }

static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
				       struct ocfs2_alloc_context *data_ac,
				       struct ocfs2_alloc_context *meta_ac,
				       struct ocfs2_write_ctxt *wc,
				       loff_t pos, unsigned len)
{ … }

/*
 * ocfs2_write_end() wants to know which parts of the target page it
 * should complete the write on. It's easiest to compute them ahead of
 * time when a more complete view of the write is available.
 */
static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
					struct ocfs2_write_ctxt *wc,
					loff_t pos, unsigned len, int alloc)
{ … }

/*
 * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to
 * do the zero work. And should not to clear UNWRITTEN since it will be cleared
 * by the direct io procedure.
 * If this is a new extent that allocated by direct io, we should mark it in
 * the ip_unwritten_list.
 */
static int ocfs2_unwritten_check(struct inode *inode,
				 struct ocfs2_write_ctxt *wc,
				 struct ocfs2_write_cluster_desc *desc)
{ … }

/*
 * Populate each single-cluster write descriptor in the write context
 * with information about the i/o to be done.
 *
 * Returns the number of clusters that will have to be allocated, as
 * well as a worst case estimate of the number of extent records that
 * would have to be created during a write to an unwritten region.
 */
static int ocfs2_populate_write_desc(struct inode *inode,
				     struct ocfs2_write_ctxt *wc,
				     unsigned int *clusters_to_alloc,
				     unsigned int *extents_to_split)
{ … }

static int ocfs2_write_begin_inline(struct address_space *mapping,
				    struct inode *inode,
				    struct ocfs2_write_ctxt *wc)
{ … }

int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size)
{ … }

static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
					  struct inode *inode, loff_t pos,
					  unsigned len, struct page *mmap_page,
					  struct ocfs2_write_ctxt *wc)
{ … }

/*
 * This function only does anything for file systems which can't
 * handle sparse files.
 *
 * What we want to do here is fill in any hole between the current end
 * of allocation and the end of our write. That way the rest of the
 * write path can treat it as an non-allocating write, which has no
 * special case code for sparse/nonsparse files.
 */
static int ocfs2_expand_nonsparse_inode(struct inode *inode,
					struct buffer_head *di_bh,
					loff_t pos, unsigned len,
					struct ocfs2_write_ctxt *wc)
{ … }

static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
			   loff_t pos)
{ … }

int ocfs2_write_begin_nolock(struct address_space *mapping,
			     loff_t pos, unsigned len, ocfs2_write_type_t type,
			     struct folio **foliop, void **fsdata,
			     struct buffer_head *di_bh, struct page *mmap_page)
{ … }

static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
			     loff_t pos, unsigned len,
			     struct folio **foliop, void **fsdata)
{ … }

static void ocfs2_write_end_inline(struct inode *inode, loff_t pos,
				   unsigned len, unsigned *copied,
				   struct ocfs2_dinode *di,
				   struct ocfs2_write_ctxt *wc)
{ … }

int ocfs2_write_end_nolock(struct address_space *mapping,
			   loff_t pos, unsigned len, unsigned copied, void *fsdata)
{ … }

static int ocfs2_write_end(struct file *file, struct address_space *mapping,
			   loff_t pos, unsigned len, unsigned copied,
			   struct folio *folio, void *fsdata)
{ … }

struct ocfs2_dio_write_ctxt { … };

static struct ocfs2_dio_write_ctxt *
ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
{ … }

static void ocfs2_dio_free_write_ctx(struct inode *inode,
				     struct ocfs2_dio_write_ctxt *dwc)
{ … }

/*
 * TODO: Make this into a generic get_blocks function.
 *
 * From do_direct_io in direct-io.c:
 *  "So what we do is to permit the ->get_blocks function to populate
 *   bh.b_size with the size of IO which is permitted at this offset and
 *   this i_blkbits."
 *
 * This function is called directly from get_more_blocks in direct-io.c.
 *
 * called like this: dio->get_blocks(dio->inode, fs_startblk,
 * 					fs_count, map_bh, dio->rw == WRITE);
 */
static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
			       struct buffer_head *bh_result, int create)
{ … }

static int ocfs2_dio_end_io_write(struct inode *inode,
				  struct ocfs2_dio_write_ctxt *dwc,
				  loff_t offset,
				  ssize_t bytes)
{ … }

/*
 * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
 * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
 * to protect io on one node from truncation on another.
 */
static int ocfs2_dio_end_io(struct kiocb *iocb,
			    loff_t offset,
			    ssize_t bytes,
			    void *private)
{ … }

static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{ … }

const struct address_space_operations ocfs2_aops = …;