@@ -22,6 +22,7 @@
#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"
@@ -36,10 +37,11 @@
#include "super.h"
#include "util.h"
#include "glops.h"
+#include "aops.h"
-static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
- unsigned int from, unsigned int len)
+void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+ unsigned int from, unsigned int len)
{
struct buffer_head *head = page_buffers(page);
unsigned int bsize = head->b_size;
@@ -462,7 +464,7 @@ static int gfs2_jdata_writepages(struct address_space *mapping,
* Returns: errno
*/
-static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
+int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
{
struct buffer_head *dibh;
u64 dsize = i_size_read(&ip->i_inode);
@@ -773,7 +775,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
* adjust_fs_space - Adjusts the free space available due to gfs2_grow
* @inode: the rindex inode
*/
-static void adjust_fs_space(struct inode *inode)
+void adjust_fs_space(struct inode *inode)
{
struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
@@ -819,11 +821,11 @@ static void adjust_fs_space(struct inode *inode)
* This copies the data from the page into the inode block after
* the inode data structure itself.
*
- * Returns: errno
+ * Returns: copied bytes or errno
*/
-static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
- loff_t pos, unsigned copied,
- struct page *page)
+int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+ loff_t pos, unsigned copied,
+ struct page *page)
{
struct gfs2_inode *ip = GFS2_I(inode);
u64 to = pos + copied;
@@ -862,7 +864,7 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
* The main write_end function for GFS2. We just put our locking around the VFS
* provided functions.
*
- * Returns: errno
+ * Returns: copied bytes or errno
*/
static int gfs2_write_end(struct file *file, struct address_space *mapping,
new file mode 100644
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2017 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.
+ */
+
+#ifndef __AOPS_DOT_H__
+#define __AOPS_DOT_H__
+
+#include "incore.h"
+
+extern int stuffed_readpage(struct gfs2_inode *ip, struct page *page);
+extern int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+ loff_t pos, unsigned copied,
+ struct page *page);
+extern void adjust_fs_space(struct inode *inode);
+extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+ unsigned int from, unsigned int len);
+
+#endif /* __AOPS_DOT_H__ */
@@ -28,6 +28,7 @@
#include "trans.h"
#include "dir.h"
#include "util.h"
+#include "aops.h"
#include "trace_gfs2.h"
/* This doesn't need to be that large as max 64 bit pointers in a 4k
@@ -41,6 +42,8 @@ struct metapath {
int mp_aheight; /* actual height (lookup height) */
};
+static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length);
+
/**
* gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
* @ip: the inode
@@ -389,7 +392,7 @@ static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h)
return mp->mp_aheight - x - 1;
}
-static inline void release_metapath(struct metapath *mp)
+static void release_metapath(struct metapath *mp)
{
int i;
@@ -397,6 +400,7 @@ static inline void release_metapath(struct metapath *mp)
if (mp->mp_bh[i] == NULL)
break;
brelse(mp->mp_bh[i]);
+ mp->mp_bh[i] = NULL;
}
}
@@ -609,11 +613,13 @@ enum alloc_state {
* ii) Indirect blocks to fill in lower part of the metadata tree
* iii) Data blocks
*
- * The function is in two parts. The first part works out the total
- * number of blocks which we need. The second part does the actual
- * allocation asking for an extent at a time (if enough contiguous free
- * blocks are available, there will only be one request per bmap call)
- * and uses the state machine to initialise the blocks in order.
+ * This function is called after gfs2_iomap_get, which works out the
+ * total number of blocks which we need via gfs2_alloc_size.
+ *
+ * We then do the actual allocation asking for an extent at a time (if
+ * enough contiguous free blocks are available, there will only be one
+ * allocation request per call) and uses the state machine to initialise
+ * the blocks in order.
*
* Right now, this function will allocate at most one indirect block
* worth of data -- with a default block size of 4K, that's slightly
@@ -633,39 +639,26 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
struct buffer_head *dibh = mp->mp_bh[0];
u64 bn;
unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
- unsigned dblks = 0;
- unsigned ptrs_per_blk;
+ size_t dblks = iomap->length >> inode->i_blkbits;
const unsigned end_of_metadata = mp->mp_fheight - 1;
int ret;
enum alloc_state state;
__be64 *ptr;
__be64 zero_bn = 0;
- size_t maxlen = iomap->length >> inode->i_blkbits;
BUG_ON(mp->mp_aheight < 1);
BUG_ON(dibh == NULL);
+ BUG_ON(dblks < 1);
gfs2_trans_add_meta(ip->i_gl, dibh);
down_write(&ip->i_rw_mutex);
if (mp->mp_fheight == mp->mp_aheight) {
- struct buffer_head *bh;
- int eob;
-
- /* Bottom indirect block exists, find unalloced extent size */
- ptr = metapointer(end_of_metadata, mp);
- bh = mp->mp_bh[end_of_metadata];
- dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr,
- maxlen, &eob);
- BUG_ON(dblks < 1);
+ /* Bottom indirect block exists */
state = ALLOC_DATA;
} else {
/* Need to allocate indirect blocks */
- ptrs_per_blk = mp->mp_fheight > 1 ? sdp->sd_inptrs :
- sdp->sd_diptrs;
- dblks = min(maxlen, (size_t)(ptrs_per_blk -
- mp->mp_list[end_of_metadata]));
if (mp->mp_fheight == ip->i_height) {
/* Writing into existing tree, extend tree down */
iblks = mp->mp_fheight - mp->mp_aheight;
@@ -750,6 +743,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
}
} while (iomap->addr == IOMAP_NULL_ADDR);
+ iomap->type = IOMAP_MAPPED;
iomap->length = (u64)dblks << inode->i_blkbits;
ip->i_height = mp->mp_fheight;
gfs2_add_inode_blocks(&ip->i_inode, alloced);
@@ -759,18 +753,63 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
return ret;
}
-static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
+static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap,
+ u64 length)
{
struct gfs2_inode *ip = GFS2_I(inode);
iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
sizeof(struct gfs2_dinode);
iomap->offset = 0;
- iomap->length = i_size_read(inode);
+ iomap->length = length;
iomap->type = IOMAP_INLINE;
iomap->flags = 0;
}
+/**
+ * gfs2_alloc_size - Compute the maximum allocation size
+ * @inode: The inode
+ * @mp: The metapath
+ * @size: Requested size in blocks
+ *
+ * Compute the maximum size of the next allocation at @mp.
+ *
+ * Returns: size in blocks
+ */
+static u64 gfs2_alloc_size(struct inode *inode, struct metapath *mp, u64 size)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ const __be64 *first, *ptr, *end;
+
+ /*
+ * For writes to stuffed files, this function is called twice via
+ * gfs2_iomap_get, before and after unstuffing. The size we return the
+ * first time needs to be large enough to get the reservation and
+ * allocation sizes right. The size we return the second time must
+ * be exact or else gfs2_iomap_alloc won't do the right thing.
+ */
+
+ if (gfs2_is_stuffed(ip) || mp->mp_fheight != mp->mp_aheight) {
+ unsigned maxsize = mp->mp_fheight > 1 ?
+ sdp->sd_inptrs : sdp->sd_diptrs;
+ maxsize -= mp->mp_list[mp->mp_fheight - 1];
+ if (size > maxsize)
+ size = maxsize;
+ return size;
+ }
+
+ first = metapointer(ip->i_height - 1, mp);
+ end = metaend(ip->i_height - 1, mp);
+ if (end - first > size)
+ end = first + size;
+ for (ptr = first; ptr < end; ptr++) {
+ if (*ptr)
+ break;
+ }
+ return ptr - first;
+}
+
/**
* gfs2_iomap_get - Map blocks from an inode to disk blocks
* @inode: The inode
@@ -804,10 +843,15 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
if (flags & IOMAP_REPORT) {
if (pos >= i_size_read(inode))
return -ENOENT;
- gfs2_stuffed_iomap(inode, iomap);
+ gfs2_stuffed_iomap(inode, iomap,
+ i_size_read(inode));
+ return 0;
+ }
+ if (pos + length <= gfs2_max_stuffed_size(ip)) {
+ gfs2_stuffed_iomap(inode, iomap,
+ gfs2_max_stuffed_size(ip));
return 0;
}
- BUG_ON(!(flags & IOMAP_WRITE));
}
lblock = pos >> inode->i_blkbits;
iomap->offset = lblock << inode->i_blkbits;
@@ -867,10 +911,160 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
else
iomap->length = size - pos;
+ } else if (flags & IOMAP_WRITE) {
+ u64 size;
+ size = gfs2_alloc_size(inode, mp, len) << inode->i_blkbits;
+ if (size < iomap->length)
+ iomap->length = size;
+ } else {
+ if (height == ip->i_height)
+ ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
}
goto out;
}
+static int gfs2_write_lock(struct inode *inode)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ int error;
+
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+ error = gfs2_glock_nq(&ip->i_gh);
+ if (error)
+ goto out_uninit;
+ if (&ip->i_inode == sdp->sd_rindex) {
+ struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+ error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
+ GL_NOCACHE, &m_ip->i_gh);
+ if (error)
+ goto out_unlock;
+ }
+ return 0;
+
+out_unlock:
+ gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+ gfs2_holder_uninit(&ip->i_gh);
+ return error;
+}
+
+static void gfs2_write_unlock(struct inode *inode)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+ if (&ip->i_inode == sdp->sd_rindex) {
+ struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+ gfs2_glock_dq_uninit(&m_ip->i_gh);
+ }
+ gfs2_glock_dq_uninit(&ip->i_gh);
+}
+
+static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, loff_t length,
+ unsigned flags, struct iomap *iomap)
+{
+ struct metapath mp = { .mp_aheight = 1, };
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+ bool unstuff, alloc_required;
+ struct buffer_head *dibh = NULL;
+ int ret;
+
+ ret = gfs2_write_lock(inode);
+ if (ret)
+ return ret;
+
+ unstuff = gfs2_is_stuffed(ip) &&
+ pos + length > gfs2_max_stuffed_size(ip);
+
+ ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+ if (ret)
+ goto out_release;
+
+ if (iomap->type == IOMAP_INLINE) {
+ ret = gfs2_meta_inode_buffer(ip, &dibh);
+ if (ret)
+ goto out_release;
+ iomap->inline_data = dibh->b_data + sizeof(struct gfs2_dinode);
+ /* dibh reference put in gfs2_iomap_end */
+ }
+
+ alloc_required = unstuff || iomap->type == IOMAP_HOLE;
+
+ if (alloc_required || gfs2_is_jdata(ip))
+ gfs2_write_calc_reserv(ip, iomap->length, &data_blocks, &ind_blocks);
+
+ if (alloc_required) {
+ struct gfs2_alloc_parms ap = { .target = data_blocks + ind_blocks };
+ ret = gfs2_quota_lock_check(ip, &ap);
+ if (ret)
+ goto out_release;
+
+ ret = gfs2_inplace_reserve(ip, &ap);
+ if (ret)
+ goto out_qunlock;
+ }
+
+ rblocks = RES_DINODE + ind_blocks;
+ if (gfs2_is_jdata(ip))
+ rblocks += data_blocks;
+ if (ind_blocks || data_blocks)
+ rblocks += RES_STATFS + RES_QUOTA;
+ if (inode == sdp->sd_rindex)
+ rblocks += 2 * RES_STATFS;
+ if (alloc_required)
+ rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
+
+ ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits);
+ if (ret)
+ goto out_trans_fail;
+
+ if (unstuff) {
+ ret = gfs2_unstuff_dinode(ip, NULL);
+ if (ret)
+ goto out_trans_end;
+ release_metapath(&mp);
+ ret = gfs2_iomap_get(inode, iomap->offset, iomap->length,
+ flags, iomap, &mp);
+ if (ret)
+ goto out_trans_end;
+ }
+
+ if (iomap->type == IOMAP_HOLE) {
+ ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
+ if (ret) {
+ gfs2_trans_end(sdp);
+ if (alloc_required)
+ gfs2_inplace_release(ip);
+ punch_hole(ip, iomap->offset, iomap->length);
+ goto out_qunlock;
+ }
+ }
+ release_metapath(&mp);
+ return 0;
+
+out_trans_end:
+ gfs2_trans_end(sdp);
+out_trans_fail:
+ if (alloc_required)
+ gfs2_inplace_release(ip);
+out_qunlock:
+ if (alloc_required)
+ gfs2_quota_unlock(ip);
+out_release:
+ release_metapath(&mp);
+ if (dibh) {
+ brelse(dibh);
+ iomap->inline_data = NULL;
+ }
+ gfs2_write_unlock(inode);
+ return ret;
+}
+
static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
unsigned flags, struct iomap *iomap)
{
@@ -880,10 +1074,7 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
trace_gfs2_iomap_start(ip, pos, length, flags);
if (flags & IOMAP_WRITE) {
- ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
- if (!ret && iomap->type == IOMAP_HOLE)
- ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
- release_metapath(&mp);
+ ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap);
} else {
ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
release_metapath(&mp);
@@ -892,8 +1083,82 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
return ret;
}
+static void gfs2_iomap_page_write_end(struct inode *inode, loff_t pos,
+ unsigned copied, struct page *page)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+
+ if (gfs2_is_jdata(ip))
+ gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+}
+
+static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
+ ssize_t written, unsigned flags, struct iomap *iomap)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ struct gfs2_trans *tr = current->journal_info;
+
+ if (!(flags & IOMAP_WRITE))
+ return 0;
+
+ if (iomap->type == IOMAP_INLINE) {
+ struct buffer_head *dibh;
+
+ dibh = gfs2_getbuf(ip->i_gl, ip->i_no_addr, NO_CREATE);
+ if (likely(dibh)) {
+ gfs2_trans_add_meta(ip->i_gl, dibh);
+ put_bh(dibh);
+ brelse(dibh);
+ }
+ iomap->inline_data = NULL;
+ goto out;
+ }
+
+ gfs2_ordered_add_inode(ip);
+
+ if (tr->tr_num_buf_new)
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+ else {
+ struct buffer_head *dibh;
+
+ dibh = gfs2_getbuf(ip->i_gl, ip->i_no_addr, NO_CREATE);
+ if (likely(dibh)) {
+ gfs2_trans_add_meta(ip->i_gl, dibh);
+ brelse(dibh);
+ }
+ }
+
+out:
+ if (inode == sdp->sd_rindex) {
+ adjust_fs_space(inode);
+ sdp->sd_rindex_uptodate = 0;
+ }
+
+ gfs2_trans_end(sdp);
+ gfs2_inplace_release(ip);
+
+ if (length != written && (iomap->flags & IOMAP_F_NEW)) {
+ /* Deallocate blocks that were just allocated. */
+ loff_t blockmask = i_blocksize(inode) - 1;
+ loff_t end = (pos + length) & ~blockmask;
+ pos = (pos + written + blockmask) & ~blockmask;
+ if (pos < end) {
+ truncate_pagecache_range(inode, pos, end - 1);
+ punch_hole(ip, pos, end - pos);
+ }
+ }
+
+ if (ip->i_qadata && ip->i_qadata->qa_qd_num)
+ gfs2_quota_unlock(ip);
+ gfs2_write_unlock(inode);
+ return 0;
+}
+
const struct iomap_ops gfs2_iomap_ops = {
.iomap_begin = gfs2_iomap_begin,
+ .page_write_end = gfs2_iomap_page_write_end,
+ .iomap_end = gfs2_iomap_end,
};
/**
@@ -26,10 +26,12 @@
#include <linux/dlm.h>
#include <linux/dlm_plock.h>
#include <linux/delay.h>
+#include <linux/backing-dev.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
+#include "aops.h"
#include "dir.h"
#include "glock.h"
#include "glops.h"
@@ -691,9 +693,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
/**
* gfs2_file_write_iter - Perform a write to a file
* @iocb: The io context
- * @iov: The data to write
- * @nr_segs: Number of @iov segments
- * @pos: The file position
+ * @from: The data to write
*
* We have to do a lock/unlock here to refresh the inode size for
* O_APPEND writes, otherwise we can land up writing at the wrong
@@ -705,8 +705,9 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
- struct gfs2_inode *ip = GFS2_I(file_inode(file));
- int ret;
+ struct inode *inode = file_inode(file);
+ struct gfs2_inode *ip = GFS2_I(inode);
+ ssize_t ret;
ret = gfs2_rsqa_alloc(ip);
if (ret)
@@ -723,7 +724,38 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
gfs2_glock_dq_uninit(&gh);
}
- return generic_file_write_iter(iocb, from);
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return generic_file_write_iter(iocb, from);
+
+ inode_lock(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out;
+
+ /* We can write back this queue in page reclaim */
+ current->backing_dev_info = inode_to_bdi(inode);
+
+ ret = file_remove_privs(file);
+ if (ret)
+ goto out2;
+
+ ret = file_update_time(file);
+ if (ret)
+ goto out2;
+
+ ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+
+out2:
+ current->backing_dev_info = NULL;
+out:
+ inode_unlock(inode);
+ if (likely(ret > 0)) {
+ iocb->ki_pos += ret;
+
+ /* Handle various SYNC-type writes */
+ ret = generic_write_sync(iocb, ret);
+ }
+ return ret;
}
static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
@@ -754,7 +786,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
if (error)
goto out;
offset = iomap.offset + iomap.length;
- if (iomap.type != IOMAP_HOLE)
+ if (!(iomap.flags & IOMAP_F_NEW))
continue;
error = sb_issue_zeroout(sb, iomap.addr >> inode->i_blkbits,
iomap.length >> inode->i_blkbits,
With the traditional page-based writes, blocks are allocated separately for each page written to. With iomap writes, we can allocate a lot more blocks at once, with a fraction of the allocation overhead for each page. Split calculating the number of blocks that can be allocated at a given position (gfs2_alloc_size) off from gfs2_iomap_alloc: that size determines the number of blocks to allocate and reserve in the journal. In gfs2_iomap_alloc, set the type of newly allocated extents to IOMAP_MAPPED so that iomap_to_bh will set the bh states correctly: otherwise, the bhs would not be marked as mapped, confusing __mpage_writepage. This means that we need to check for the IOMAP_F_NEW flag in fallocate_chunk now. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> --- fs/gfs2/aops.c | 20 +-- fs/gfs2/aops.h | 22 ++++ fs/gfs2/bmap.c | 325 ++++++++++++++++++++++++++++++++++++++++++++----- fs/gfs2/file.c | 46 +++++-- 4 files changed, 367 insertions(+), 46 deletions(-) create mode 100644 fs/gfs2/aops.h