OpenCloudOS-Kernel/fs/gfs2/meta_io.c

555 lines
13 KiB
C
Raw Normal View History

// 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/mm.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/delay.h>
#include <linux/bio.h>
#include <linux/gfs2_ondisk.h>
#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "trace_gfs2.h"
static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
{
struct buffer_head *bh, *head;
int nr_underway = 0;
blk_opf_t write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc);
BUG_ON(!PageLocked(page));
BUG_ON(!page_has_buffers(page));
head = page_buffers(page);
bh = head;
do {
if (!buffer_mapped(bh))
continue;
/*
* If it's a fully non-blocking write attempt and we cannot
* lock the buffer then redirty the page. Note that this can
* potentially cause a busy-wait loop from flusher thread and kswapd
* activity, but those code paths have their own higher-level
* throttling.
*/
if (wbc->sync_mode != WB_SYNC_NONE) {
lock_buffer(bh);
} else if (!trylock_buffer(bh)) {
redirty_page_for_writepage(wbc, page);
continue;
}
if (test_clear_buffer_dirty(bh)) {
mark_buffer_async_write(bh);
} else {
unlock_buffer(bh);
}
} while ((bh = bh->b_this_page) != head);
/*
* The page and its buffers are protected by PageWriteback(), so we can
* drop the bh refcounts early.
*/
BUG_ON(PageWriteback(page));
set_page_writeback(page);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
submit_bh(REQ_OP_WRITE | write_flags, bh);
nr_underway++;
}
bh = next;
} while (bh != head);
unlock_page(page);
if (nr_underway == 0)
end_page_writeback(page);
return 0;
}
const struct address_space_operations gfs2_meta_aops = {
.dirty_folio = block_dirty_folio,
.invalidate_folio = block_invalidate_folio,
.writepage = gfs2_aspace_writepage,
.release_folio = gfs2_release_folio,
};
const struct address_space_operations gfs2_rgrp_aops = {
.dirty_folio = block_dirty_folio,
.invalidate_folio = block_invalidate_folio,
.writepage = gfs2_aspace_writepage,
.release_folio = gfs2_release_folio,
};
/**
* gfs2_getbuf - Get a buffer with a given address space
* @gl: the glock
* @blkno: the block number (filesystem scope)
* @create: 1 if the buffer should be created
*
* Returns: the buffer
*/
struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
{
struct address_space *mapping = gfs2_glock2aspace(gl);
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct page *page;
struct buffer_head *bh;
unsigned int shift;
unsigned long index;
unsigned int bufnum;
if (mapping == NULL)
mapping = &sdp->sd_aspace;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift;
index = blkno >> shift; /* convert block to page */
bufnum = blkno - (index << shift); /* block buf index within page */
if (create) {
for (;;) {
page = grab_cache_page(mapping, index);
if (page)
break;
yield();
}
if (!page_has_buffers(page))
create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
} else {
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:10:31 +08:00
page = find_get_page_flags(mapping, index,
FGP_LOCK|FGP_ACCESSED);
if (!page)
return NULL;
if (!page_has_buffers(page)) {
bh = NULL;
goto out_unlock;
}
}
/* Locate header for our buffer within our page */
for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
/* Do nothing */;
get_bh(bh);
if (!buffer_mapped(bh))
map_bh(bh, sdp->sd_vfs, blkno);
out_unlock:
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
return bh;
}
static void meta_prep_new(struct buffer_head *bh)
{
struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
lock_buffer(bh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
}
/**
* gfs2_meta_new - Get a block
* @gl: The glock associated with this block
* @blkno: The block number
*
* Returns: The buffer
*/
struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
{
struct buffer_head *bh;
bh = gfs2_getbuf(gl, blkno, CREATE);
meta_prep_new(bh);
return bh;
}
static void gfs2_meta_read_endio(struct bio *bio)
{
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
struct buffer_head *bh = page_buffers(page);
unsigned int len = bvec->bv_len;
while (bh_offset(bh) < bvec->bv_offset)
bh = bh->b_this_page;
do {
struct buffer_head *next = bh->b_this_page;
len -= bh->b_size;
bh->b_end_io(bh, !bio->bi_status);
bh = next;
} while (bh && len);
}
bio_put(bio);
}
/*
* Submit several consecutive buffer head I/O requests as a single bio I/O
* request. (See submit_bh_wbc.)
*/
static void gfs2_submit_bhs(blk_opf_t opf, struct buffer_head *bhs[], int num)
{
while (num > 0) {
struct buffer_head *bh = *bhs;
struct bio *bio;
bio = bio_alloc(bh->b_bdev, num, opf, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
while (num > 0) {
bh = *bhs;
if (!bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh))) {
BUG_ON(bio->bi_iter.bi_size == 0);
break;
}
bhs++;
num--;
}
bio->bi_end_io = gfs2_meta_read_endio;
submit_bio(bio);
}
}
/**
* gfs2_meta_read - Read a block from disk
* @gl: The glock covering the block
* @blkno: The block number
* @flags: flags
* @rahead: Do read-ahead
* @bhp: the place where the buffer is returned (NULL on failure)
*
* Returns: errno
*/
int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
int rahead, struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct buffer_head *bh, *bhs[2];
int num = 0;
if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp)) {
*bhp = NULL;
return -EIO;
}
*bhp = bh = gfs2_getbuf(gl, blkno, CREATE);
lock_buffer(bh);
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
flags &= ~DIO_WAIT;
} else {
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
bhs[num++] = bh;
}
if (rahead) {
bh = gfs2_getbuf(gl, blkno + 1, CREATE);
lock_buffer(bh);
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
brelse(bh);
} else {
bh->b_end_io = end_buffer_read_sync;
bhs[num++] = bh;
}
}
gfs2_submit_bhs(REQ_OP_READ | REQ_META | REQ_PRIO, bhs, num);
if (!(flags & DIO_WAIT))
return 0;
bh = *bhp;
wait_on_buffer(bh);
if (unlikely(!buffer_uptodate(bh))) {
struct gfs2_trans *tr = current->journal_info;
if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
gfs2_io_error_bh_wd(sdp, bh);
brelse(bh);
*bhp = NULL;
return -EIO;
}
return 0;
}
/**
* gfs2_meta_wait - Reread a block from disk
* @sdp: the filesystem
* @bh: The block to wait for
*
* Returns: errno
*/
int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp))
return -EIO;
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
struct gfs2_trans *tr = current->journal_info;
if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
gfs2_io_error_bh_wd(sdp, bh);
return -EIO;
}
if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp))
return -EIO;
return 0;
}
void gfs2_remove_from_journal(struct buffer_head *bh, int meta)
{
struct address_space *mapping = bh->b_folio->mapping;
struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
struct gfs2_bufdata *bd = bh->b_private;
struct gfs2_trans *tr = current->journal_info;
int was_pinned = 0;
if (test_clear_buffer_pinned(bh)) {
trace_gfs2_pin(bd, 0);
atomic_dec(&sdp->sd_log_pinned);
list_del_init(&bd->bd_list);
if (meta == REMOVE_META)
tr->tr_num_buf_rm++;
else
tr->tr_num_databuf_rm++;
set_bit(TR_TOUCHED, &tr->tr_flags);
was_pinned = 1;
brelse(bh);
}
if (bd) {
if (bd->bd_tr) {
gfs2_trans_add_revoke(sdp, bd);
} else if (was_pinned) {
bh->b_private = NULL;
kmem_cache_free(gfs2_bufdata_cachep, bd);
} else if (!list_empty(&bd->bd_ail_st_list) &&
!list_empty(&bd->bd_ail_gl_list)) {
gfs2_remove_from_ail(bd);
}
}
clear_buffer_dirty(bh);
clear_buffer_uptodate(bh);
}
/**
* gfs2_ail1_wipe - remove deleted/freed buffers from the ail1 list
* @sdp: superblock
* @bstart: starting block address of buffers to remove
* @blen: length of buffers to be removed
*
* This function is called from gfs2_journal wipe, whose job is to remove
* buffers, corresponding to deleted blocks, from the journal. If we find any
* bufdata elements on the system ail1 list, they haven't been written to
* the journal yet. So we remove them.
*/
static void gfs2_ail1_wipe(struct gfs2_sbd *sdp, u64 bstart, u32 blen)
{
struct gfs2_trans *tr, *s;
struct gfs2_bufdata *bd, *bs;
struct buffer_head *bh;
u64 end = bstart + blen;
gfs2_log_lock(sdp);
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe(tr, s, &sdp->sd_ail1_list, tr_list) {
list_for_each_entry_safe(bd, bs, &tr->tr_ail1_list,
bd_ail_st_list) {
bh = bd->bd_bh;
if (bh->b_blocknr < bstart || bh->b_blocknr >= end)
continue;
gfs2_remove_from_journal(bh, REMOVE_JDATA);
}
}
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
}
static struct buffer_head *gfs2_getjdatabuf(struct gfs2_inode *ip, u64 blkno)
{
struct address_space *mapping = ip->i_inode.i_mapping;
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct page *page;
struct buffer_head *bh;
unsigned int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift;
unsigned long index = blkno >> shift; /* convert block to page */
unsigned int bufnum = blkno - (index << shift);
page = find_get_page_flags(mapping, index, FGP_LOCK|FGP_ACCESSED);
if (!page)
return NULL;
if (!page_has_buffers(page)) {
unlock_page(page);
put_page(page);
return NULL;
}
/* Locate header for our buffer within our page */
for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
/* Do nothing */;
get_bh(bh);
unlock_page(page);
put_page(page);
return bh;
}
/**
* gfs2_journal_wipe - make inode's buffers so they aren't dirty/pinned anymore
* @ip: the inode who owns the buffers
* @bstart: the first buffer in the run
* @blen: the number of buffers in the run
*
*/
void gfs2_journal_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct buffer_head *bh;
int ty;
if (!ip->i_gl) {
/* This can only happen during incomplete inode creation. */
BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags));
return;
}
gfs2_ail1_wipe(sdp, bstart, blen);
while (blen) {
ty = REMOVE_META;
bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE);
if (!bh && gfs2_is_jdata(ip)) {
bh = gfs2_getjdatabuf(ip, bstart);
ty = REMOVE_JDATA;
}
if (bh) {
lock_buffer(bh);
gfs2_log_lock(sdp);
spin_lock(&sdp->sd_ail_lock);
gfs2_remove_from_journal(bh, ty);
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
brelse(bh);
}
bstart++;
blen--;
}
}
/**
* gfs2_meta_buffer - Get a metadata buffer
* @ip: The GFS2 inode
* @mtype: The block type (GFS2_METATYPE_*)
* @num: The block number (device relative) of the buffer
* @bhp: the buffer is returned here
*
* Returns: errno
*/
int gfs2_meta_buffer(struct gfs2_inode *ip, u32 mtype, u64 num,
struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_glock *gl = ip->i_gl;
struct buffer_head *bh;
int ret = 0;
int rahead = 0;
if (num == ip->i_no_addr)
rahead = ip->i_rahead;
ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh);
if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
brelse(bh);
ret = -EIO;
} else {
*bhp = bh;
}
return ret;
}
/**
* gfs2_meta_ra - start readahead on an extent of a file
* @gl: the glock the blocks belong to
* @dblock: the starting disk block
* @extlen: the number of blocks in the extent
*
* returns: the first buffer in the extent
*/
struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct buffer_head *first_bh, *bh;
u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
sdp->sd_sb.sb_bsize_shift;
BUG_ON(!extlen);
if (max_ra < 1)
max_ra = 1;
if (extlen > max_ra)
extlen = max_ra;
first_bh = gfs2_getbuf(gl, dblock, CREATE);
if (buffer_uptodate(first_bh))
goto out;
bh_read_nowait(first_bh, REQ_META | REQ_PRIO);
dblock++;
extlen--;
while (extlen) {
bh = gfs2_getbuf(gl, dblock, CREATE);
bh_readahead(bh, REQ_RAHEAD | REQ_META | REQ_PRIO);
brelse(bh);
dblock++;
extlen--;
if (!buffer_locked(first_bh) && buffer_uptodate(first_bh))
goto out;
}
wait_on_buffer(first_bh);
out:
return first_bh;
}