linux/fs/gfs2/aops.c
Linus Torvalds 3822a7c409 - Daniel Verkamp has contributed a memfd series ("mm/memfd: add
F_SEAL_EXEC") which permits the setting of the memfd execute bit at
   memfd creation time, with the option of sealing the state of the X bit.
 
 - Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset()
   thread-safe for pmd unshare") which addresses a rare race condition
   related to PMD unsharing.
 
 - Several folioification patch serieses from Matthew Wilcox, Vishal
   Moola, Sidhartha Kumar and Lorenzo Stoakes
 
 - Johannes Weiner has a series ("mm: push down lock_page_memcg()") which
   does perform some memcg maintenance and cleanup work.
 
 - SeongJae Park has added DAMOS filtering to DAMON, with the series
   "mm/damon/core: implement damos filter".  These filters provide users
   with finer-grained control over DAMOS's actions.  SeongJae has also done
   some DAMON cleanup work.
 
 - Kairui Song adds a series ("Clean up and fixes for swap").
 
 - Vernon Yang contributed the series "Clean up and refinement for maple
   tree".
 
 - Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series.  It
   adds to MGLRU an LRU of memcgs, to improve the scalability of global
   reclaim.
 
 - David Hildenbrand has added some userfaultfd cleanup work in the
   series "mm: uffd-wp + change_protection() cleanups".
 
 - Christoph Hellwig has removed the generic_writepages() library
   function in the series "remove generic_writepages".
 
 - Baolin Wang has performed some maintenance on the compaction code in
   his series "Some small improvements for compaction".
 
 - Sidhartha Kumar is doing some maintenance work on struct page in his
   series "Get rid of tail page fields".
 
 - David Hildenbrand contributed some cleanup, bugfixing and
   generalization of pte management and of pte debugging in his series "mm:
   support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with swap
   PTEs".
 
 - Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation
   flag in the series "Discard __GFP_ATOMIC".
 
 - Sergey Senozhatsky has improved zsmalloc's memory utilization with his
   series "zsmalloc: make zspage chain size configurable".
 
 - Joey Gouly has added prctl() support for prohibiting the creation of
   writeable+executable mappings.  The previous BPF-based approach had
   shortcomings.  See "mm: In-kernel support for memory-deny-write-execute
   (MDWE)".
 
 - Waiman Long did some kmemleak cleanup and bugfixing in the series
   "mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF".
 
 - T.J.  Alumbaugh has contributed some MGLRU cleanup work in his series
   "mm: multi-gen LRU: improve".
 
 - Jiaqi Yan has provided some enhancements to our memory error
   statistics reporting, mainly by presenting the statistics on a per-node
   basis.  See the series "Introduce per NUMA node memory error
   statistics".
 
 - Mel Gorman has a second and hopefully final shot at fixing a CPU-hog
   regression in compaction via his series "Fix excessive CPU usage during
   compaction".
 
 - Christoph Hellwig does some vmalloc maintenance work in the series
   "cleanup vfree and vunmap".
 
 - Christoph Hellwig has removed block_device_operations.rw_page() in ths
   series "remove ->rw_page".
 
 - We get some maple_tree improvements and cleanups in Liam Howlett's
   series "VMA tree type safety and remove __vma_adjust()".
 
 - Suren Baghdasaryan has done some work on the maintainability of our
   vm_flags handling in the series "introduce vm_flags modifier functions".
 
 - Some pagemap cleanup and generalization work in Mike Rapoport's series
   "mm, arch: add generic implementation of pfn_valid() for FLATMEM" and
   "fixups for generic implementation of pfn_valid()"
 
 - Baoquan He has done some work to make /proc/vmallocinfo and
   /proc/kcore better represent the real state of things in his series
   "mm/vmalloc.c: allow vread() to read out vm_map_ram areas".
 
 - Jason Gunthorpe rationalized the GUP system's interface to the rest of
   the kernel in the series "Simplify the external interface for GUP".
 
 - SeongJae Park wishes to migrate people from DAMON's debugfs interface
   over to its sysfs interface.  To support this, we'll temporarily be
   printing warnings when people use the debugfs interface.  See the series
   "mm/damon: deprecate DAMON debugfs interface".
 
 - Andrey Konovalov provided the accurately named "lib/stackdepot: fixes
   and clean-ups" series.
 
 - Huang Ying has provided a dramatic reduction in migration's TLB flush
   IPI rates with the series "migrate_pages(): batch TLB flushing".
 
 - Arnd Bergmann has some objtool fixups in "objtool warning fixes".
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCY/PoPQAKCRDdBJ7gKXxA
 jlvpAPsFECUBBl20qSue2zCYWnHC7Yk4q9ytTkPB/MMDrFEN9wD/SNKEm2UoK6/K
 DmxHkn0LAitGgJRS/W9w81yrgig9tAQ=
 =MlGs
 -----END PGP SIGNATURE-----

Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Daniel Verkamp has contributed a memfd series ("mm/memfd: add
   F_SEAL_EXEC") which permits the setting of the memfd execute bit at
   memfd creation time, with the option of sealing the state of the X
   bit.

 - Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset()
   thread-safe for pmd unshare") which addresses a rare race condition
   related to PMD unsharing.

 - Several folioification patch serieses from Matthew Wilcox, Vishal
   Moola, Sidhartha Kumar and Lorenzo Stoakes

 - Johannes Weiner has a series ("mm: push down lock_page_memcg()")
   which does perform some memcg maintenance and cleanup work.

 - SeongJae Park has added DAMOS filtering to DAMON, with the series
   "mm/damon/core: implement damos filter".

   These filters provide users with finer-grained control over DAMOS's
   actions. SeongJae has also done some DAMON cleanup work.

 - Kairui Song adds a series ("Clean up and fixes for swap").

 - Vernon Yang contributed the series "Clean up and refinement for maple
   tree".

 - Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It
   adds to MGLRU an LRU of memcgs, to improve the scalability of global
   reclaim.

 - David Hildenbrand has added some userfaultfd cleanup work in the
   series "mm: uffd-wp + change_protection() cleanups".

 - Christoph Hellwig has removed the generic_writepages() library
   function in the series "remove generic_writepages".

 - Baolin Wang has performed some maintenance on the compaction code in
   his series "Some small improvements for compaction".

 - Sidhartha Kumar is doing some maintenance work on struct page in his
   series "Get rid of tail page fields".

 - David Hildenbrand contributed some cleanup, bugfixing and
   generalization of pte management and of pte debugging in his series
   "mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with
   swap PTEs".

 - Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation
   flag in the series "Discard __GFP_ATOMIC".

 - Sergey Senozhatsky has improved zsmalloc's memory utilization with
   his series "zsmalloc: make zspage chain size configurable".

 - Joey Gouly has added prctl() support for prohibiting the creation of
   writeable+executable mappings.

   The previous BPF-based approach had shortcomings. See "mm: In-kernel
   support for memory-deny-write-execute (MDWE)".

 - Waiman Long did some kmemleak cleanup and bugfixing in the series
   "mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF".

 - T.J. Alumbaugh has contributed some MGLRU cleanup work in his series
   "mm: multi-gen LRU: improve".

 - Jiaqi Yan has provided some enhancements to our memory error
   statistics reporting, mainly by presenting the statistics on a
   per-node basis. See the series "Introduce per NUMA node memory error
   statistics".

 - Mel Gorman has a second and hopefully final shot at fixing a CPU-hog
   regression in compaction via his series "Fix excessive CPU usage
   during compaction".

 - Christoph Hellwig does some vmalloc maintenance work in the series
   "cleanup vfree and vunmap".

 - Christoph Hellwig has removed block_device_operations.rw_page() in
   ths series "remove ->rw_page".

 - We get some maple_tree improvements and cleanups in Liam Howlett's
   series "VMA tree type safety and remove __vma_adjust()".

 - Suren Baghdasaryan has done some work on the maintainability of our
   vm_flags handling in the series "introduce vm_flags modifier
   functions".

 - Some pagemap cleanup and generalization work in Mike Rapoport's
   series "mm, arch: add generic implementation of pfn_valid() for
   FLATMEM" and "fixups for generic implementation of pfn_valid()"

 - Baoquan He has done some work to make /proc/vmallocinfo and
   /proc/kcore better represent the real state of things in his series
   "mm/vmalloc.c: allow vread() to read out vm_map_ram areas".

 - Jason Gunthorpe rationalized the GUP system's interface to the rest
   of the kernel in the series "Simplify the external interface for
   GUP".

 - SeongJae Park wishes to migrate people from DAMON's debugfs interface
   over to its sysfs interface. To support this, we'll temporarily be
   printing warnings when people use the debugfs interface. See the
   series "mm/damon: deprecate DAMON debugfs interface".

 - Andrey Konovalov provided the accurately named "lib/stackdepot: fixes
   and clean-ups" series.

 - Huang Ying has provided a dramatic reduction in migration's TLB flush
   IPI rates with the series "migrate_pages(): batch TLB flushing".

 - Arnd Bergmann has some objtool fixups in "objtool warning fixes".

* tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (505 commits)
  include/linux/migrate.h: remove unneeded externs
  mm/memory_hotplug: cleanup return value handing in do_migrate_range()
  mm/uffd: fix comment in handling pte markers
  mm: change to return bool for isolate_movable_page()
  mm: hugetlb: change to return bool for isolate_hugetlb()
  mm: change to return bool for isolate_lru_page()
  mm: change to return bool for folio_isolate_lru()
  objtool: add UACCESS exceptions for __tsan_volatile_read/write
  kmsan: disable ftrace in kmsan core code
  kasan: mark addr_has_metadata __always_inline
  mm: memcontrol: rename memcg_kmem_enabled()
  sh: initialize max_mapnr
  m68k/nommu: add missing definition of ARCH_PFN_OFFSET
  mm: percpu: fix incorrect size in pcpu_obj_full_size()
  maple_tree: reduce stack usage with gcc-9 and earlier
  mm: page_alloc: call panic() when memoryless node allocation fails
  mm: multi-gen LRU: avoid futile retries
  migrate_pages: move THP/hugetlb migration support check to simplify code
  migrate_pages: batch flushing TLB
  migrate_pages: share more code between _unmap and _move
  ...
2023-02-23 17:09:35 -08:00

779 lines
20 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
*/
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/fs.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/gfs2_ondisk.h>
#include <linux/backing-dev.h>
#include <linux/uio.h>
#include <trace/events/writeback.h>
#include <linux/sched/signal.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "trans.h"
#include "rgrp.h"
#include "super.h"
#include "util.h"
#include "glops.h"
#include "aops.h"
void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio,
unsigned int from, unsigned int len)
{
struct buffer_head *head = folio_buffers(folio);
unsigned int bsize = head->b_size;
struct buffer_head *bh;
unsigned int to = from + len;
unsigned int start, end;
for (bh = head, start = 0; bh != head || !start;
bh = bh->b_this_page, start = end) {
end = start + bsize;
if (end <= from)
continue;
if (start >= to)
break;
set_buffer_uptodate(bh);
gfs2_trans_add_data(ip->i_gl, bh);
}
}
/**
* gfs2_get_block_noalloc - Fills in a buffer head with details about a block
* @inode: The inode
* @lblock: The block number to look up
* @bh_result: The buffer head to return the result in
* @create: Non-zero if we may add block to the file
*
* Returns: errno
*/
static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
struct buffer_head *bh_result, int create)
{
int error;
error = gfs2_block_map(inode, lblock, bh_result, 0);
if (error)
return error;
if (!buffer_mapped(bh_result))
return -ENODATA;
return 0;
}
/**
* gfs2_write_jdata_page - gfs2 jdata-specific version of block_write_full_page
* @page: The page to write
* @wbc: The writeback control
*
* This is the same as calling block_write_full_page, but it also
* writes pages outside of i_size
*/
static int gfs2_write_jdata_page(struct page *page,
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;
/*
* 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."
*/
offset = i_size & (PAGE_SIZE - 1);
if (page->index == end_index && offset)
zero_user_segment(page, offset, PAGE_SIZE);
return __block_write_full_page(inode, page, gfs2_get_block_noalloc, wbc,
end_buffer_async_write);
}
/**
* __gfs2_jdata_writepage - The core of jdata writepage
* @page: The page to write
* @wbc: The writeback control
*
* This is shared between writepage and writepages and implements the
* core of the writepage operation. If a transaction is required then
* PageChecked will have been set and the transaction will have
* already been started before this is called.
*/
static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
if (PageChecked(page)) {
ClearPageChecked(page);
if (!page_has_buffers(page)) {
create_empty_buffers(page, inode->i_sb->s_blocksize,
BIT(BH_Dirty)|BIT(BH_Uptodate));
}
gfs2_trans_add_databufs(ip, page_folio(page), 0, PAGE_SIZE);
}
return gfs2_write_jdata_page(page, wbc);
}
/**
* gfs2_jdata_writepage - Write complete page
* @page: Page to write
* @wbc: The writeback control
*
* Returns: errno
*
*/
static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
goto out;
if (PageChecked(page) || current->journal_info)
goto out_ignore;
return __gfs2_jdata_writepage(page, wbc);
out_ignore:
redirty_page_for_writepage(wbc, page);
out:
unlock_page(page);
return 0;
}
/**
* gfs2_writepages - Write a bunch of dirty pages back to disk
* @mapping: The mapping to write
* @wbc: Write-back control
*
* Used for both ordered and writeback modes.
*/
static int gfs2_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
struct iomap_writepage_ctx wpc = { };
int ret;
/*
* Even if we didn't write any pages here, we might still be holding
* dirty pages in the ail. We forcibly flush the ail because we don't
* want balance_dirty_pages() to loop indefinitely trying to write out
* pages held in the ail that it can't find.
*/
ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops);
if (ret == 0)
set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
return ret;
}
/**
* gfs2_write_jdata_batch - Write back a folio batch's worth of folios
* @mapping: The mapping
* @wbc: The writeback control
* @fbatch: The batch of folios
* @done_index: Page index
*
* Returns: non-zero if loop should terminate, zero otherwise
*/
static int gfs2_write_jdata_batch(struct address_space *mapping,
struct writeback_control *wbc,
struct folio_batch *fbatch,
pgoff_t *done_index)
{
struct inode *inode = mapping->host;
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned nrblocks;
int i;
int ret;
int nr_pages = 0;
int nr_folios = folio_batch_count(fbatch);
for (i = 0; i < nr_folios; i++)
nr_pages += folio_nr_pages(fbatch->folios[i]);
nrblocks = nr_pages * (PAGE_SIZE >> inode->i_blkbits);
ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
if (ret < 0)
return ret;
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch->folios[i];
*done_index = folio->index;
folio_lock(folio);
if (unlikely(folio->mapping != mapping)) {
continue_unlock:
folio_unlock(folio);
continue;
}
if (!folio_test_dirty(folio)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (folio_test_writeback(folio)) {
if (wbc->sync_mode != WB_SYNC_NONE)
folio_wait_writeback(folio);
else
goto continue_unlock;
}
BUG_ON(folio_test_writeback(folio));
if (!folio_clear_dirty_for_io(folio))
goto continue_unlock;
trace_wbc_writepage(wbc, inode_to_bdi(inode));
ret = __gfs2_jdata_writepage(&folio->page, wbc);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
folio_unlock(folio);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
*done_index = folio->index +
folio_nr_pages(folio);
ret = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) {
ret = 1;
break;
}
}
gfs2_trans_end(sdp);
return ret;
}
/**
* gfs2_write_cache_jdata - Like write_cache_pages but different
* @mapping: The mapping to write
* @wbc: The writeback control
*
* The reason that we use our own function here is that we need to
* start transactions before we grab page locks. This allows us
* to get the ordering right.
*/
static int gfs2_write_cache_jdata(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret = 0;
int done = 0;
struct folio_batch fbatch;
int nr_folios;
pgoff_t writeback_index;
pgoff_t index;
pgoff_t end;
pgoff_t done_index;
int cycled;
int range_whole = 0;
xa_mark_t tag;
folio_batch_init(&fbatch);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
nr_folios = filemap_get_folios_tag(mapping, &index, end,
tag, &fbatch);
if (nr_folios == 0)
break;
ret = gfs2_write_jdata_batch(mapping, wbc, &fbatch,
&done_index);
if (ret)
done = 1;
if (ret > 0)
ret = 0;
folio_batch_release(&fbatch);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
/**
* gfs2_jdata_writepages - Write a bunch of dirty pages back to disk
* @mapping: The mapping to write
* @wbc: The writeback control
*
*/
static int gfs2_jdata_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct gfs2_inode *ip = GFS2_I(mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
int ret;
ret = gfs2_write_cache_jdata(mapping, wbc);
if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
gfs2_log_flush(sdp, ip->i_gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_JDATA_WPAGES);
ret = gfs2_write_cache_jdata(mapping, wbc);
}
return ret;
}
/**
* stuffed_readpage - Fill in a Linux page with stuffed file data
* @ip: the inode
* @page: the page
*
* Returns: errno
*/
static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
{
struct buffer_head *dibh;
u64 dsize = i_size_read(&ip->i_inode);
void *kaddr;
int error;
/*
* Due to the order of unstuffing files and ->fault(), we can be
* asked for a zero page in the case of a stuffed file being extended,
* so we need to supply one here. It doesn't happen often.
*/
if (unlikely(page->index)) {
zero_user(page, 0, PAGE_SIZE);
SetPageUptodate(page);
return 0;
}
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
return error;
kaddr = kmap_atomic(page);
memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
memset(kaddr + dsize, 0, PAGE_SIZE - dsize);
kunmap_atomic(kaddr);
flush_dcache_page(page);
brelse(dibh);
SetPageUptodate(page);
return 0;
}
/**
* gfs2_read_folio - read a folio from a file
* @file: The file to read
* @folio: The folio in the file
*/
static int gfs2_read_folio(struct file *file, struct folio *folio)
{
struct inode *inode = folio->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
int error;
if (!gfs2_is_jdata(ip) ||
(i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) {
error = iomap_read_folio(folio, &gfs2_iomap_ops);
} else if (gfs2_is_stuffed(ip)) {
error = stuffed_readpage(ip, &folio->page);
folio_unlock(folio);
} else {
error = mpage_read_folio(folio, gfs2_block_map);
}
if (unlikely(gfs2_withdrawn(sdp)))
return -EIO;
return error;
}
/**
* gfs2_internal_read - read an internal file
* @ip: The gfs2 inode
* @buf: The buffer to fill
* @pos: The file position
* @size: The amount to read
*
*/
int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
unsigned size)
{
struct address_space *mapping = ip->i_inode.i_mapping;
unsigned long index = *pos >> PAGE_SHIFT;
unsigned offset = *pos & (PAGE_SIZE - 1);
unsigned copied = 0;
unsigned amt;
struct page *page;
void *p;
do {
amt = size - copied;
if (offset + size > PAGE_SIZE)
amt = PAGE_SIZE - offset;
page = read_cache_page(mapping, index, gfs2_read_folio, NULL);
if (IS_ERR(page))
return PTR_ERR(page);
p = kmap_atomic(page);
memcpy(buf + copied, p + offset, amt);
kunmap_atomic(p);
put_page(page);
copied += amt;
index++;
offset = 0;
} while(copied < size);
(*pos) += size;
return size;
}
/**
* gfs2_readahead - Read a bunch of pages at once
* @rac: Read-ahead control structure
*
* Some notes:
* 1. This is only for readahead, so we can simply ignore any things
* which are slightly inconvenient (such as locking conflicts between
* the page lock and the glock) and return having done no I/O. Its
* obviously not something we'd want to do on too regular a basis.
* Any I/O we ignore at this time will be done via readpage later.
* 2. We don't handle stuffed files here we let readpage do the honours.
* 3. mpage_readahead() does most of the heavy lifting in the common case.
* 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
*/
static void gfs2_readahead(struct readahead_control *rac)
{
struct inode *inode = rac->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
if (gfs2_is_stuffed(ip))
;
else if (gfs2_is_jdata(ip))
mpage_readahead(rac, gfs2_block_map);
else
iomap_readahead(rac, &gfs2_iomap_ops);
}
/**
* adjust_fs_space - Adjusts the free space available due to gfs2_grow
* @inode: the rindex inode
*/
void adjust_fs_space(struct inode *inode)
{
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct buffer_head *m_bh;
u64 fs_total, new_free;
if (gfs2_trans_begin(sdp, 2 * RES_STATFS, 0) != 0)
return;
/* Total up the file system space, according to the latest rindex. */
fs_total = gfs2_ri_total(sdp);
if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0)
goto out;
spin_lock(&sdp->sd_statfs_spin);
gfs2_statfs_change_in(m_sc, m_bh->b_data +
sizeof(struct gfs2_dinode));
if (fs_total > (m_sc->sc_total + l_sc->sc_total))
new_free = fs_total - (m_sc->sc_total + l_sc->sc_total);
else
new_free = 0;
spin_unlock(&sdp->sd_statfs_spin);
fs_warn(sdp, "File system extended by %llu blocks.\n",
(unsigned long long)new_free);
gfs2_statfs_change(sdp, new_free, new_free, 0);
update_statfs(sdp, m_bh);
brelse(m_bh);
out:
sdp->sd_rindex_uptodate = 0;
gfs2_trans_end(sdp);
}
static bool jdata_dirty_folio(struct address_space *mapping,
struct folio *folio)
{
if (current->journal_info)
folio_set_checked(folio);
return block_dirty_folio(mapping, folio);
}
/**
* gfs2_bmap - Block map function
* @mapping: Address space info
* @lblock: The block to map
*
* Returns: The disk address for the block or 0 on hole or error
*/
static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
{
struct gfs2_inode *ip = GFS2_I(mapping->host);
struct gfs2_holder i_gh;
sector_t dblock = 0;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
if (error)
return 0;
if (!gfs2_is_stuffed(ip))
dblock = iomap_bmap(mapping, lblock, &gfs2_iomap_ops);
gfs2_glock_dq_uninit(&i_gh);
return dblock;
}
static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
struct gfs2_bufdata *bd;
lock_buffer(bh);
gfs2_log_lock(sdp);
clear_buffer_dirty(bh);
bd = bh->b_private;
if (bd) {
if (!list_empty(&bd->bd_list) && !buffer_pinned(bh))
list_del_init(&bd->bd_list);
else {
spin_lock(&sdp->sd_ail_lock);
gfs2_remove_from_journal(bh, REMOVE_JDATA);
spin_unlock(&sdp->sd_ail_lock);
}
}
bh->b_bdev = NULL;
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
}
static void gfs2_invalidate_folio(struct folio *folio, size_t offset,
size_t length)
{
struct gfs2_sbd *sdp = GFS2_SB(folio->mapping->host);
size_t stop = offset + length;
int partial_page = (offset || length < folio_size(folio));
struct buffer_head *bh, *head;
unsigned long pos = 0;
BUG_ON(!folio_test_locked(folio));
if (!partial_page)
folio_clear_checked(folio);
head = folio_buffers(folio);
if (!head)
goto out;
bh = head;
do {
if (pos + bh->b_size > stop)
return;
if (offset <= pos)
gfs2_discard(sdp, bh);
pos += bh->b_size;
bh = bh->b_this_page;
} while (bh != head);
out:
if (!partial_page)
filemap_release_folio(folio, 0);
}
/**
* gfs2_release_folio - free the metadata associated with a folio
* @folio: the folio that's being released
* @gfp_mask: passed from Linux VFS, ignored by us
*
* Calls try_to_free_buffers() to free the buffers and put the folio if the
* buffers can be released.
*
* Returns: true if the folio was put or else false
*/
bool gfs2_release_folio(struct folio *folio, gfp_t gfp_mask)
{
struct address_space *mapping = folio->mapping;
struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
struct buffer_head *bh, *head;
struct gfs2_bufdata *bd;
head = folio_buffers(folio);
if (!head)
return false;
/*
* mm accommodates an old ext3 case where clean folios might
* not have had the dirty bit cleared. Thus, it can send actual
* dirty folios to ->release_folio() via shrink_active_list().
*
* As a workaround, we skip folios that contain dirty buffers
* below. Once ->release_folio isn't called on dirty folios
* anymore, we can warn on dirty buffers like we used to here
* again.
*/
gfs2_log_lock(sdp);
bh = head;
do {
if (atomic_read(&bh->b_count))
goto cannot_release;
bd = bh->b_private;
if (bd && bd->bd_tr)
goto cannot_release;
if (buffer_dirty(bh) || WARN_ON(buffer_pinned(bh)))
goto cannot_release;
bh = bh->b_this_page;
} while (bh != head);
bh = head;
do {
bd = bh->b_private;
if (bd) {
gfs2_assert_warn(sdp, bd->bd_bh == bh);
bd->bd_bh = NULL;
bh->b_private = NULL;
/*
* The bd may still be queued as a revoke, in which
* case we must not dequeue nor free it.
*/
if (!bd->bd_blkno && !list_empty(&bd->bd_list))
list_del_init(&bd->bd_list);
if (list_empty(&bd->bd_list))
kmem_cache_free(gfs2_bufdata_cachep, bd);
}
bh = bh->b_this_page;
} while (bh != head);
gfs2_log_unlock(sdp);
return try_to_free_buffers(folio);
cannot_release:
gfs2_log_unlock(sdp);
return false;
}
static const struct address_space_operations gfs2_aops = {
.writepages = gfs2_writepages,
.read_folio = gfs2_read_folio,
.readahead = gfs2_readahead,
.dirty_folio = filemap_dirty_folio,
.release_folio = iomap_release_folio,
.invalidate_folio = iomap_invalidate_folio,
.bmap = gfs2_bmap,
.direct_IO = noop_direct_IO,
.migrate_folio = filemap_migrate_folio,
.is_partially_uptodate = iomap_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations gfs2_jdata_aops = {
.writepage = gfs2_jdata_writepage,
.writepages = gfs2_jdata_writepages,
.read_folio = gfs2_read_folio,
.readahead = gfs2_readahead,
.dirty_folio = jdata_dirty_folio,
.bmap = gfs2_bmap,
.invalidate_folio = gfs2_invalidate_folio,
.release_folio = gfs2_release_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
void gfs2_set_aops(struct inode *inode)
{
if (gfs2_is_jdata(GFS2_I(inode)))
inode->i_mapping->a_ops = &gfs2_jdata_aops;
else
inode->i_mapping->a_ops = &gfs2_aops;
}