linux/fs/gfs2/lops.c
Linus Torvalds 088737f44b Writeback error handling fixes (pile #2)
-----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJZXhmCAAoJEAAOaEEZVoIVpRkP/1qlYn3pq6d5Kuz84pejOmlL
 5jbkS/cOmeTxeUU4+B1xG8Lx7bAk8PfSXQOADbSJGiZd0ug95tJxplFYIGJzR/tG
 aNMHeu/BVKKhUKORGuKR9rJKtwC839L/qao+yPBo5U3mU4L73rFWX8fxFuhSJ8HR
 hvkgBu3Hx6GY59CzxJ8iJzj+B+uPSFrNweAk0+0UeWkBgTzEdiGqaXBX4cHIkq/5
 hMoCG+xnmwHKbCBsQ5js+YJT+HedZ4lvfjOqGxgElUyjJ7Bkt/IFYOp8TUiu193T
 tA4UinDjN8A7FImmIBIftrECmrAC9HIGhGZroYkMKbb8ReDR2ikE5FhKEpuAGU3a
 BXBgX2mPQuArvZWM7qeJCkxV9QJ0u/8Ykbyzo30iPrICyrzbEvIubeB/mDA034+Z
 Z0/z8C3v7826F3zP/NyaQEojUgRq30McMOIS8GMnx15HJwRsRKlzjfy9Wm4tWhl0
 t3nH1jMqAZ7068s6rfh/oCwdgGOwr5o4hW/bnlITzxbjWQUOnZIe7KBxIezZJ2rv
 OcIwd5qE8PNtpagGj5oUbnjGOTkERAgsMfvPk5tjUNt28/qUlVs2V0aeo47dlcsh
 oYr8WMOIzw98Rl7Bo70mplLrqLD6nGl0LfXOyUlT4STgLWW4ksmLVuJjWIUxcO/0
 yKWjj9wfYRQ0vSUqhsI5
 =3Z93
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-v4.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux

Pull Writeback error handling updates from Jeff Layton:
 "This pile represents the bulk of the writeback error handling fixes
  that I have for this cycle. Some of the earlier patches in this pile
  may look trivial but they are prerequisites for later patches in the
  series.

  The aim of this set is to improve how we track and report writeback
  errors to userland. Most applications that care about data integrity
  will periodically call fsync/fdatasync/msync to ensure that their
  writes have made it to the backing store.

  For a very long time, we have tracked writeback errors using two flags
  in the address_space: AS_EIO and AS_ENOSPC. Those flags are set when a
  writeback error occurs (via mapping_set_error) and are cleared as a
  side-effect of filemap_check_errors (as you noted yesterday). This
  model really sucks for userland.

  Only the first task to call fsync (or msync or fdatasync) will see the
  error. Any subsequent task calling fsync on a file will get back 0
  (unless another writeback error occurs in the interim). If I have
  several tasks writing to a file and calling fsync to ensure that their
  writes got stored, then I need to have them coordinate with one
  another. That's difficult enough, but in a world of containerized
  setups that coordination may even not be possible.

  But wait...it gets worse!

  The calls to filemap_check_errors can be buried pretty far down in the
  call stack, and there are internal callers of filemap_write_and_wait
  and the like that also end up clearing those errors. Many of those
  callers ignore the error return from that function or return it to
  userland at nonsensical times (e.g. truncate() or stat()). If I get
  back -EIO on a truncate, there is no reason to think that it was
  because some previous writeback failed, and a subsequent fsync() will
  (incorrectly) return 0.

  This pile aims to do three things:

   1) ensure that when a writeback error occurs that that error will be
      reported to userland on a subsequent fsync/fdatasync/msync call,
      regardless of what internal callers are doing

   2) report writeback errors on all file descriptions that were open at
      the time that the error occurred. This is a user-visible change,
      but I think most applications are written to assume this behavior
      anyway. Those that aren't are unlikely to be hurt by it.

   3) document what filesystems should do when there is a writeback
      error. Today, there is very little consistency between them, and a
      lot of cargo-cult copying. We need to make it very clear what
      filesystems should do in this situation.

  To achieve this, the set adds a new data type (errseq_t) and then
  builds new writeback error tracking infrastructure around that. Once
  all of that is in place, we change the filesystems to use the new
  infrastructure for reporting wb errors to userland.

  Note that this is just the initial foray into cleaning up this mess.
  There is a lot of work remaining here:

   1) convert the rest of the filesystems in a similar fashion. Once the
      initial set is in, then I think most other fs' will be fairly
      simple to convert. Hopefully most of those can in via individual
      filesystem trees.

   2) convert internal waiters on writeback to use errseq_t for
      detecting errors instead of relying on the AS_* flags. I have some
      draft patches for this for ext4, but they are not quite ready for
      prime time yet.

  This was a discussion topic this year at LSF/MM too. If you're
  interested in the gory details, LWN has some good articles about this:

      https://lwn.net/Articles/718734/
      https://lwn.net/Articles/724307/"

* tag 'for-linus-v4.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux:
  btrfs: minimal conversion to errseq_t writeback error reporting on fsync
  xfs: minimal conversion to errseq_t writeback error reporting
  ext4: use errseq_t based error handling for reporting data writeback errors
  fs: convert __generic_file_fsync to use errseq_t based reporting
  block: convert to errseq_t based writeback error tracking
  dax: set errors in mapping when writeback fails
  Documentation: flesh out the section in vfs.txt on storing and reporting writeback errors
  mm: set both AS_EIO/AS_ENOSPC and errseq_t in mapping_set_error
  fs: new infrastructure for writeback error handling and reporting
  lib: add errseq_t type and infrastructure for handling it
  mm: don't TestClearPageError in __filemap_fdatawait_range
  mm: clear AS_EIO/AS_ENOSPC when writeback initiation fails
  jbd2: don't clear and reset errors after waiting on writeback
  buffer: set errors in mapping at the time that the error occurs
  fs: check for writeback errors after syncing out buffers in generic_file_fsync
  buffer: use mapping_set_error instead of setting the flag
  mm: fix mapping_set_error call in me_pagecache_dirty
2017-07-07 19:38:17 -07:00

877 lines
21 KiB
C

/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* of the GNU General Public License version 2.
*/
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/mempool.h>
#include <linux/gfs2_ondisk.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/list_sort.h>
#include "gfs2.h"
#include "incore.h"
#include "inode.h"
#include "glock.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "recovery.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "trace_gfs2.h"
/**
* gfs2_pin - Pin a buffer in memory
* @sdp: The superblock
* @bh: The buffer to be pinned
*
* The log lock must be held when calling this function
*/
void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
struct gfs2_bufdata *bd;
BUG_ON(!current->journal_info);
clear_buffer_dirty(bh);
if (test_set_buffer_pinned(bh))
gfs2_assert_withdraw(sdp, 0);
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
bd = bh->b_private;
/* If this buffer is in the AIL and it has already been written
* to in-place disk block, remove it from the AIL.
*/
spin_lock(&sdp->sd_ail_lock);
if (bd->bd_tr)
list_move(&bd->bd_ail_st_list, &bd->bd_tr->tr_ail2_list);
spin_unlock(&sdp->sd_ail_lock);
get_bh(bh);
atomic_inc(&sdp->sd_log_pinned);
trace_gfs2_pin(bd, 1);
}
static bool buffer_is_rgrp(const struct gfs2_bufdata *bd)
{
return bd->bd_gl->gl_name.ln_type == LM_TYPE_RGRP;
}
static void maybe_release_space(struct gfs2_bufdata *bd)
{
struct gfs2_glock *gl = bd->bd_gl;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
struct gfs2_bitmap *bi = rgd->rd_bits + index;
if (bi->bi_clone == NULL)
return;
if (sdp->sd_args.ar_discard)
gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi, 1, NULL);
memcpy(bi->bi_clone + bi->bi_offset,
bd->bd_bh->b_data + bi->bi_offset, bi->bi_len);
clear_bit(GBF_FULL, &bi->bi_flags);
rgd->rd_free_clone = rgd->rd_free;
rgd->rd_extfail_pt = rgd->rd_free;
}
/**
* gfs2_unpin - Unpin a buffer
* @sdp: the filesystem the buffer belongs to
* @bh: The buffer to unpin
* @ai:
* @flags: The inode dirty flags
*
*/
static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
struct gfs2_trans *tr)
{
struct gfs2_bufdata *bd = bh->b_private;
BUG_ON(!buffer_uptodate(bh));
BUG_ON(!buffer_pinned(bh));
lock_buffer(bh);
mark_buffer_dirty(bh);
clear_buffer_pinned(bh);
if (buffer_is_rgrp(bd))
maybe_release_space(bd);
spin_lock(&sdp->sd_ail_lock);
if (bd->bd_tr) {
list_del(&bd->bd_ail_st_list);
brelse(bh);
} else {
struct gfs2_glock *gl = bd->bd_gl;
list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
atomic_inc(&gl->gl_ail_count);
}
bd->bd_tr = tr;
list_add(&bd->bd_ail_st_list, &tr->tr_ail1_list);
spin_unlock(&sdp->sd_ail_lock);
clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
trace_gfs2_pin(bd, 0);
unlock_buffer(bh);
atomic_dec(&sdp->sd_log_pinned);
}
static void gfs2_log_incr_head(struct gfs2_sbd *sdp)
{
BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
(sdp->sd_log_flush_head != sdp->sd_log_head));
if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks)
sdp->sd_log_flush_head = 0;
}
static u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
{
unsigned int lbn = sdp->sd_log_flush_head;
struct gfs2_journal_extent *je;
u64 block;
list_for_each_entry(je, &sdp->sd_jdesc->extent_list, list) {
if ((lbn >= je->lblock) && (lbn < (je->lblock + je->blocks))) {
block = je->dblock + lbn - je->lblock;
gfs2_log_incr_head(sdp);
return block;
}
}
return -1;
}
/**
* gfs2_end_log_write_bh - end log write of pagecache data with buffers
* @sdp: The superblock
* @bvec: The bio_vec
* @error: The i/o status
*
* This finds the relavent buffers and unlocks then and sets the
* error flag according to the status of the i/o request. This is
* used when the log is writing data which has an in-place version
* that is pinned in the pagecache.
*/
static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
blk_status_t error)
{
struct buffer_head *bh, *next;
struct page *page = bvec->bv_page;
unsigned size;
bh = page_buffers(page);
size = bvec->bv_len;
while (bh_offset(bh) < bvec->bv_offset)
bh = bh->b_this_page;
do {
if (error)
mark_buffer_write_io_error(bh);
unlock_buffer(bh);
next = bh->b_this_page;
size -= bh->b_size;
brelse(bh);
bh = next;
} while(bh && size);
}
/**
* gfs2_end_log_write - end of i/o to the log
* @bio: The bio
* @error: Status of i/o request
*
* Each bio_vec contains either data from the pagecache or data
* relating to the log itself. Here we iterate over the bio_vec
* array, processing both kinds of data.
*
*/
static void gfs2_end_log_write(struct bio *bio)
{
struct gfs2_sbd *sdp = bio->bi_private;
struct bio_vec *bvec;
struct page *page;
int i;
if (bio->bi_status)
fs_err(sdp, "Error %d writing to log\n", bio->bi_status);
bio_for_each_segment_all(bvec, bio, i) {
page = bvec->bv_page;
if (page_has_buffers(page))
gfs2_end_log_write_bh(sdp, bvec, bio->bi_status);
else
mempool_free(page, gfs2_page_pool);
}
bio_put(bio);
if (atomic_dec_and_test(&sdp->sd_log_in_flight))
wake_up(&sdp->sd_log_flush_wait);
}
/**
* gfs2_log_flush_bio - Submit any pending log bio
* @sdp: The superblock
* @op: REQ_OP
* @op_flags: req_flag_bits
*
* Submit any pending part-built or full bio to the block device. If
* there is no pending bio, then this is a no-op.
*/
void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int op, int op_flags)
{
if (sdp->sd_log_bio) {
atomic_inc(&sdp->sd_log_in_flight);
bio_set_op_attrs(sdp->sd_log_bio, op, op_flags);
submit_bio(sdp->sd_log_bio);
sdp->sd_log_bio = NULL;
}
}
/**
* gfs2_log_alloc_bio - Allocate a new bio for log writing
* @sdp: The superblock
* @blkno: The next device block number we want to write to
*
* This should never be called when there is a cached bio in the
* super block. When it returns, there will be a cached bio in the
* super block which will have as many bio_vecs as the device is
* happy to handle.
*
* Returns: Newly allocated bio
*/
static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
{
struct super_block *sb = sdp->sd_vfs;
struct bio *bio;
BUG_ON(sdp->sd_log_bio);
bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
bio->bi_bdev = sb->s_bdev;
bio->bi_end_io = gfs2_end_log_write;
bio->bi_private = sdp;
sdp->sd_log_bio = bio;
return bio;
}
/**
* gfs2_log_get_bio - Get cached log bio, or allocate a new one
* @sdp: The superblock
* @blkno: The device block number we want to write to
*
* If there is a cached bio, then if the next block number is sequential
* with the previous one, return it, otherwise flush the bio to the
* device. If there is not a cached bio, or we just flushed it, then
* allocate a new one.
*
* Returns: The bio to use for log writes
*/
static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno)
{
struct bio *bio = sdp->sd_log_bio;
u64 nblk;
if (bio) {
nblk = bio_end_sector(bio);
nblk >>= sdp->sd_fsb2bb_shift;
if (blkno == nblk)
return bio;
gfs2_log_flush_bio(sdp, REQ_OP_WRITE, 0);
}
return gfs2_log_alloc_bio(sdp, blkno);
}
/**
* gfs2_log_write - write to log
* @sdp: the filesystem
* @page: the page to write
* @size: the size of the data to write
* @offset: the offset within the page
*
* Try and add the page segment to the current bio. If that fails,
* submit the current bio to the device and create a new one, and
* then add the page segment to that.
*/
static void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page,
unsigned size, unsigned offset)
{
u64 blkno = gfs2_log_bmap(sdp);
struct bio *bio;
int ret;
bio = gfs2_log_get_bio(sdp, blkno);
ret = bio_add_page(bio, page, size, offset);
if (ret == 0) {
gfs2_log_flush_bio(sdp, REQ_OP_WRITE, 0);
bio = gfs2_log_alloc_bio(sdp, blkno);
ret = bio_add_page(bio, page, size, offset);
WARN_ON(ret == 0);
}
}
/**
* gfs2_log_write_bh - write a buffer's content to the log
* @sdp: The super block
* @bh: The buffer pointing to the in-place location
*
* This writes the content of the buffer to the next available location
* in the log. The buffer will be unlocked once the i/o to the log has
* completed.
*/
static void gfs2_log_write_bh(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
gfs2_log_write(sdp, bh->b_page, bh->b_size, bh_offset(bh));
}
/**
* gfs2_log_write_page - write one block stored in a page, into the log
* @sdp: The superblock
* @page: The struct page
*
* This writes the first block-sized part of the page into the log. Note
* that the page must have been allocated from the gfs2_page_pool mempool
* and that after this has been called, ownership has been transferred and
* the page may be freed at any time.
*/
void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
{
struct super_block *sb = sdp->sd_vfs;
gfs2_log_write(sdp, page, sb->s_blocksize, 0);
}
static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type,
u32 ld_length, u32 ld_data1)
{
struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
struct gfs2_log_descriptor *ld = page_address(page);
clear_page(ld);
ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
ld->ld_type = cpu_to_be32(ld_type);
ld->ld_length = cpu_to_be32(ld_length);
ld->ld_data1 = cpu_to_be32(ld_data1);
ld->ld_data2 = 0;
return page;
}
static void gfs2_check_magic(struct buffer_head *bh)
{
void *kaddr;
__be32 *ptr;
clear_buffer_escaped(bh);
kaddr = kmap_atomic(bh->b_page);
ptr = kaddr + bh_offset(bh);
if (*ptr == cpu_to_be32(GFS2_MAGIC))
set_buffer_escaped(bh);
kunmap_atomic(kaddr);
}
static int blocknr_cmp(void *priv, struct list_head *a, struct list_head *b)
{
struct gfs2_bufdata *bda, *bdb;
bda = list_entry(a, struct gfs2_bufdata, bd_list);
bdb = list_entry(b, struct gfs2_bufdata, bd_list);
if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
return -1;
if (bda->bd_bh->b_blocknr > bdb->bd_bh->b_blocknr)
return 1;
return 0;
}
static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit,
unsigned int total, struct list_head *blist,
bool is_databuf)
{
struct gfs2_log_descriptor *ld;
struct gfs2_bufdata *bd1 = NULL, *bd2;
struct page *page;
unsigned int num;
unsigned n;
__be64 *ptr;
gfs2_log_lock(sdp);
list_sort(NULL, blist, blocknr_cmp);
bd1 = bd2 = list_prepare_entry(bd1, blist, bd_list);
while(total) {
num = total;
if (total > limit)
num = limit;
gfs2_log_unlock(sdp);
page = gfs2_get_log_desc(sdp,
is_databuf ? GFS2_LOG_DESC_JDATA :
GFS2_LOG_DESC_METADATA, num + 1, num);
ld = page_address(page);
gfs2_log_lock(sdp);
ptr = (__be64 *)(ld + 1);
n = 0;
list_for_each_entry_continue(bd1, blist, bd_list) {
*ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr);
if (is_databuf) {
gfs2_check_magic(bd1->bd_bh);
*ptr++ = cpu_to_be64(buffer_escaped(bd1->bd_bh) ? 1 : 0);
}
if (++n >= num)
break;
}
gfs2_log_unlock(sdp);
gfs2_log_write_page(sdp, page);
gfs2_log_lock(sdp);
n = 0;
list_for_each_entry_continue(bd2, blist, bd_list) {
get_bh(bd2->bd_bh);
gfs2_log_unlock(sdp);
lock_buffer(bd2->bd_bh);
if (buffer_escaped(bd2->bd_bh)) {
void *kaddr;
page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
ptr = page_address(page);
kaddr = kmap_atomic(bd2->bd_bh->b_page);
memcpy(ptr, kaddr + bh_offset(bd2->bd_bh),
bd2->bd_bh->b_size);
kunmap_atomic(kaddr);
*(__be32 *)ptr = 0;
clear_buffer_escaped(bd2->bd_bh);
unlock_buffer(bd2->bd_bh);
brelse(bd2->bd_bh);
gfs2_log_write_page(sdp, page);
} else {
gfs2_log_write_bh(sdp, bd2->bd_bh);
}
gfs2_log_lock(sdp);
if (++n >= num)
break;
}
BUG_ON(total < num);
total -= num;
}
gfs2_log_unlock(sdp);
}
static void buf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
unsigned int limit = buf_limit(sdp); /* 503 for 4k blocks */
unsigned int nbuf;
if (tr == NULL)
return;
nbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
gfs2_before_commit(sdp, limit, nbuf, &tr->tr_buf, 0);
}
static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head;
struct gfs2_bufdata *bd;
if (tr == NULL)
return;
head = &tr->tr_buf;
while (!list_empty(head)) {
bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
gfs2_unpin(sdp, bd->bd_bh, tr);
}
}
static void buf_lo_before_scan(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, int pass)
{
if (pass != 0)
return;
jd->jd_found_blocks = 0;
jd->jd_replayed_blocks = 0;
}
static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
struct gfs2_log_descriptor *ld, __be64 *ptr,
int pass)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
struct gfs2_glock *gl = ip->i_gl;
unsigned int blks = be32_to_cpu(ld->ld_data1);
struct buffer_head *bh_log, *bh_ip;
u64 blkno;
int error = 0;
if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_METADATA)
return 0;
gfs2_replay_incr_blk(jd, &start);
for (; blks; gfs2_replay_incr_blk(jd, &start), blks--) {
blkno = be64_to_cpu(*ptr++);
jd->jd_found_blocks++;
if (gfs2_revoke_check(jd, blkno, start))
continue;
error = gfs2_replay_read_block(jd, start, &bh_log);
if (error)
return error;
bh_ip = gfs2_meta_new(gl, blkno);
memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
if (gfs2_meta_check(sdp, bh_ip))
error = -EIO;
else
mark_buffer_dirty(bh_ip);
brelse(bh_log);
brelse(bh_ip);
if (error)
break;
jd->jd_replayed_blocks++;
}
return error;
}
/**
* gfs2_meta_sync - Sync all buffers associated with a glock
* @gl: The glock
*
*/
static void gfs2_meta_sync(struct gfs2_glock *gl)
{
struct address_space *mapping = gfs2_glock2aspace(gl);
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
int error;
if (mapping == NULL)
mapping = &sdp->sd_aspace;
filemap_fdatawrite(mapping);
error = filemap_fdatawait(mapping);
if (error)
gfs2_io_error(gl->gl_name.ln_sbd);
}
static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
gfs2_meta_sync(ip->i_gl);
return;
}
if (pass != 1)
return;
gfs2_meta_sync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
}
static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct gfs2_meta_header *mh;
unsigned int offset;
struct list_head *head = &sdp->sd_log_le_revoke;
struct gfs2_bufdata *bd;
struct page *page;
unsigned int length;
gfs2_write_revokes(sdp);
if (!sdp->sd_log_num_revoke)
return;
length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64));
page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke);
offset = sizeof(struct gfs2_log_descriptor);
list_for_each_entry(bd, head, bd_list) {
sdp->sd_log_num_revoke--;
if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
gfs2_log_write_page(sdp, page);
page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
mh = page_address(page);
clear_page(mh);
mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB);
mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB);
offset = sizeof(struct gfs2_meta_header);
}
*(__be64 *)(page_address(page) + offset) = cpu_to_be64(bd->bd_blkno);
offset += sizeof(u64);
}
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
gfs2_log_write_page(sdp, page);
}
static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head = &sdp->sd_log_le_revoke;
struct gfs2_bufdata *bd;
struct gfs2_glock *gl;
while (!list_empty(head)) {
bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
gl = bd->bd_gl;
atomic_dec(&gl->gl_revokes);
clear_bit(GLF_LFLUSH, &gl->gl_flags);
kmem_cache_free(gfs2_bufdata_cachep, bd);
}
}
static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, int pass)
{
if (pass != 0)
return;
jd->jd_found_revokes = 0;
jd->jd_replay_tail = head->lh_tail;
}
static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
struct gfs2_log_descriptor *ld, __be64 *ptr,
int pass)
{
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
unsigned int blks = be32_to_cpu(ld->ld_length);
unsigned int revokes = be32_to_cpu(ld->ld_data1);
struct buffer_head *bh;
unsigned int offset;
u64 blkno;
int first = 1;
int error;
if (pass != 0 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_REVOKE)
return 0;
offset = sizeof(struct gfs2_log_descriptor);
for (; blks; gfs2_replay_incr_blk(jd, &start), blks--) {
error = gfs2_replay_read_block(jd, start, &bh);
if (error)
return error;
if (!first)
gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LB);
while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));
error = gfs2_revoke_add(jd, blkno, start);
if (error < 0) {
brelse(bh);
return error;
}
else if (error)
jd->jd_found_revokes++;
if (!--revokes)
break;
offset += sizeof(u64);
}
brelse(bh);
offset = sizeof(struct gfs2_meta_header);
first = 0;
}
return 0;
}
static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
gfs2_revoke_clean(jd);
return;
}
if (pass != 1)
return;
fs_info(sdp, "jid=%u: Found %u revoke tags\n",
jd->jd_jid, jd->jd_found_revokes);
gfs2_revoke_clean(jd);
}
/**
* databuf_lo_before_commit - Scan the data buffers, writing as we go
*
*/
static void databuf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
unsigned int limit = databuf_limit(sdp);
unsigned int nbuf;
if (tr == NULL)
return;
nbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
gfs2_before_commit(sdp, limit, nbuf, &tr->tr_databuf, 1);
}
static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
struct gfs2_log_descriptor *ld,
__be64 *ptr, int pass)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_glock *gl = ip->i_gl;
unsigned int blks = be32_to_cpu(ld->ld_data1);
struct buffer_head *bh_log, *bh_ip;
u64 blkno;
u64 esc;
int error = 0;
if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_JDATA)
return 0;
gfs2_replay_incr_blk(jd, &start);
for (; blks; gfs2_replay_incr_blk(jd, &start), blks--) {
blkno = be64_to_cpu(*ptr++);
esc = be64_to_cpu(*ptr++);
jd->jd_found_blocks++;
if (gfs2_revoke_check(jd, blkno, start))
continue;
error = gfs2_replay_read_block(jd, start, &bh_log);
if (error)
return error;
bh_ip = gfs2_meta_new(gl, blkno);
memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
/* Unescape */
if (esc) {
__be32 *eptr = (__be32 *)bh_ip->b_data;
*eptr = cpu_to_be32(GFS2_MAGIC);
}
mark_buffer_dirty(bh_ip);
brelse(bh_log);
brelse(bh_ip);
jd->jd_replayed_blocks++;
}
return error;
}
/* FIXME: sort out accounting for log blocks etc. */
static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
gfs2_meta_sync(ip->i_gl);
return;
}
if (pass != 1)
return;
/* data sync? */
gfs2_meta_sync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
}
static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head;
struct gfs2_bufdata *bd;
if (tr == NULL)
return;
head = &tr->tr_databuf;
while (!list_empty(head)) {
bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
gfs2_unpin(sdp, bd->bd_bh, tr);
}
}
const struct gfs2_log_operations gfs2_buf_lops = {
.lo_before_commit = buf_lo_before_commit,
.lo_after_commit = buf_lo_after_commit,
.lo_before_scan = buf_lo_before_scan,
.lo_scan_elements = buf_lo_scan_elements,
.lo_after_scan = buf_lo_after_scan,
.lo_name = "buf",
};
const struct gfs2_log_operations gfs2_revoke_lops = {
.lo_before_commit = revoke_lo_before_commit,
.lo_after_commit = revoke_lo_after_commit,
.lo_before_scan = revoke_lo_before_scan,
.lo_scan_elements = revoke_lo_scan_elements,
.lo_after_scan = revoke_lo_after_scan,
.lo_name = "revoke",
};
const struct gfs2_log_operations gfs2_databuf_lops = {
.lo_before_commit = databuf_lo_before_commit,
.lo_after_commit = databuf_lo_after_commit,
.lo_scan_elements = databuf_lo_scan_elements,
.lo_after_scan = databuf_lo_after_scan,
.lo_name = "databuf",
};
const struct gfs2_log_operations *gfs2_log_ops[] = {
&gfs2_databuf_lops,
&gfs2_buf_lops,
&gfs2_revoke_lops,
NULL,
};