xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'iomap-write' into linux-gfs2/for-next

Browse Source 
Pull in the gfs2 iomap-write changes: Tweak the existing code to
properly support iomap write and eliminate an unnecessary special case
in gfs2_block_map.  Implement iomap write support for buffered and
direct I/O.  Simplify some of the existing code and eliminate code that
is no longer used:

  gfs2: Remove gfs2_write_{begin,end}
  gfs2: iomap direct I/O support
  gfs2: gfs2_extent_length cleanup
  gfs2: iomap buffered write support
  gfs2: Further iomap cleanups

This is based on the following changes on the xfs 'iomap-4.19-merge'
branch:

  iomap: add private pointer to struct iomap
  iomap: add a page_done callback
  iomap: generic inline data handling
  iomap: complete partial direct I/O writes synchronously
  iomap: mark newly allocated buffer heads as new
  fs: factor out a __generic_write_end helper

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
This commit is contained in:
Andreas Gruenbacher
2018-07-24 20:02:40 +02:00
parent 109dbb1e6f 025d0e7f73
commit a3479c7fc0
3448 changed files with 64675 additions and 36730 deletions
Download Patch File Download Diff File Expand all files Collapse all files

331
fs/gfs2/aops.c
View File

@@ -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;
@@ -82,12 +84,6 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
return 0;
}
static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
struct buffer_head *bh_result, int create)
{
return gfs2_block_map(inode, lblock, bh_result, 0);
}
/**
* gfs2_writepage_common - Common bits of writepage
* @page: The page to be written
@@ -462,7 +458,7 @@ 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);
@@ -643,140 +639,11 @@ out_uninit:
return ret;
}
/**
* gfs2_write_begin - Begin to write to a file
* @file: The file to write to
* @mapping: The mapping in which to write
* @pos: The file offset at which to start writing
* @len: Length of the write
* @flags: Various flags
* @pagep: Pointer to return the page
* @fsdata: Pointer to return fs data (unused by GFS2)
*
* Returns: errno
*/
static int gfs2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct gfs2_inode *ip = GFS2_I(mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
unsigned requested = 0;
int alloc_required;
int error = 0;
pgoff_t index = pos >> PAGE_SHIFT;
unsigned from = pos & (PAGE_SIZE - 1);
struct page *page;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
error = gfs2_glock_nq(&ip->i_gh);
if (unlikely(error))
goto out_uninit;
if (&ip->i_inode == sdp->sd_rindex) {
error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
GL_NOCACHE, &m_ip->i_gh);
if (unlikely(error)) {
gfs2_glock_dq(&ip->i_gh);
goto out_uninit;
}
}
alloc_required = gfs2_write_alloc_required(ip, pos, len);
if (alloc_required || gfs2_is_jdata(ip))
gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
if (alloc_required) {
struct gfs2_alloc_parms ap = { .aflags = 0, };
requested = data_blocks + ind_blocks;
ap.target = requested;
error = gfs2_quota_lock_check(ip, &ap);
if (error)
goto out_unlock;
error = gfs2_inplace_reserve(ip, &ap);
if (error)
goto out_qunlock;
}
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks)
rblocks += RES_STATFS + RES_QUOTA;
if (&ip->i_inode == sdp->sd_rindex)
rblocks += 2 * RES_STATFS;
if (alloc_required)
rblocks += gfs2_rg_blocks(ip, requested);
error = gfs2_trans_begin(sdp, rblocks,
PAGE_SIZE/sdp->sd_sb.sb_bsize);
if (error)
goto out_trans_fail;
error = -ENOMEM;
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, index, flags);
*pagep = page;
if (unlikely(!page))
goto out_endtrans;
if (gfs2_is_stuffed(ip)) {
error = 0;
if (pos + len > gfs2_max_stuffed_size(ip)) {
error = gfs2_unstuff_dinode(ip, page);
if (error == 0)
goto prepare_write;
} else if (!PageUptodate(page)) {
error = stuffed_readpage(ip, page);
}
goto out;
}
prepare_write:
error = __block_write_begin(page, from, len, gfs2_block_map);
out:
if (error == 0)
return 0;
unlock_page(page);
put_page(page);
gfs2_trans_end(sdp);
if (alloc_required) {
gfs2_inplace_release(ip);
if (pos + len > ip->i_inode.i_size)
gfs2_trim_blocks(&ip->i_inode);
}
goto out_qunlock;
out_endtrans:
gfs2_trans_end(sdp);
out_trans_fail:
if (alloc_required)
gfs2_inplace_release(ip);
out_qunlock:
if (alloc_required)
gfs2_quota_unlock(ip);
out_unlock:
if (&ip->i_inode == sdp->sd_rindex) {
gfs2_glock_dq(&m_ip->i_gh);
gfs2_holder_uninit(&m_ip->i_gh);
}
gfs2_glock_dq(&ip->i_gh);
out_uninit:
gfs2_holder_uninit(&ip->i_gh);
return error;
}
/**
* 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);
@@ -822,11 +689,11 @@ out:
* 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;
@@ -852,84 +719,6 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
return copied;
}
/**
* gfs2_write_end
* @file: The file to write to
* @mapping: The address space to write to
* @pos: The file position
* @len: The length of the data
* @copied: How much was actually copied by the VFS
* @page: The page that has been written
* @fsdata: The fsdata (unused in GFS2)
*
* The main write_end function for GFS2. We just put our locking around the VFS
* provided functions.
*
* Returns: errno
*/
static int gfs2_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct buffer_head *dibh;
int ret;
struct gfs2_trans *tr = current->journal_info;
BUG_ON(!tr);
BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
ret = gfs2_meta_inode_buffer(ip, &dibh);
if (unlikely(ret))
goto out;
if (gfs2_is_stuffed(ip)) {
ret = gfs2_stuffed_write_end(inode, dibh, pos, copied, page);
page = NULL;
goto out2;
}
if (gfs2_is_jdata(ip))
gfs2_page_add_databufs(ip, page, pos & ~PAGE_MASK, len);
else
gfs2_ordered_add_inode(ip);
ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
page = NULL;
if (tr->tr_num_buf_new)
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
else
gfs2_trans_add_meta(ip->i_gl, dibh);
out2:
if (inode == sdp->sd_rindex) {
adjust_fs_space(inode);
sdp->sd_rindex_uptodate = 0;
}
brelse(dibh);
out:
if (page) {
unlock_page(page);
put_page(page);
}
gfs2_trans_end(sdp);
gfs2_inplace_release(ip);
if (ip->i_qadata && ip->i_qadata->qa_qd_num)
gfs2_quota_unlock(ip);
if (inode == sdp->sd_rindex) {
gfs2_glock_dq(&m_ip->i_gh);
gfs2_holder_uninit(&m_ip->i_gh);
}
gfs2_glock_dq(&ip->i_gh);
gfs2_holder_uninit(&ip->i_gh);
return ret;
}
/**
* jdata_set_page_dirty - Page dirtying function
* @page: The page to dirty
@@ -1022,96 +811,6 @@ out:
try_to_release_page(page, 0);
}
/**
* gfs2_ok_for_dio - check that dio is valid on this file
* @ip: The inode
* @offset: The offset at which we are reading or writing
*
* Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
* 1 (to accept the i/o request)
*/
static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset)
{
/*
* Should we return an error here? I can't see that O_DIRECT for
* a stuffed file makes any sense. For now we'll silently fall
* back to buffered I/O
*/
if (gfs2_is_stuffed(ip))
return 0;
if (offset >= i_size_read(&ip->i_inode))
return 0;
return 1;
}
static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
loff_t offset = iocb->ki_pos;
struct gfs2_holder gh;
int rv;
/*
* Deferred lock, even if its a write, since we do no allocation
* on this path. All we need change is atime, and this lock mode
* ensures that other nodes have flushed their buffered read caches
* (i.e. their page cache entries for this inode). We do not,
* unfortunately have the option of only flushing a range like
* the VFS does.
*/
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
rv = gfs2_glock_nq(&gh);
if (rv)
goto out_uninit;
rv = gfs2_ok_for_dio(ip, offset);
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
/*
* Now since we are holding a deferred (CW) lock at this point, you
* might be wondering why this is ever needed. There is a case however
* where we've granted a deferred local lock against a cached exclusive
* glock. That is ok provided all granted local locks are deferred, but
* it also means that it is possible to encounter pages which are
* cached and possibly also mapped. So here we check for that and sort
* them out ahead of the dio. The glock state machine will take care of
* everything else.
*
* If in fact the cached glock state (gl->gl_state) is deferred (CW) in
* the first place, mapping->nr_pages will always be zero.
*/
if (mapping->nrpages) {
loff_t lstart = offset & ~(PAGE_SIZE - 1);
loff_t len = iov_iter_count(iter);
loff_t end = PAGE_ALIGN(offset + len) - 1;
rv = 0;
if (len == 0)
goto out;
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
rv = filemap_write_and_wait_range(mapping, lstart, end);
if (rv)
goto out;
if (iov_iter_rw(iter) == WRITE)
truncate_inode_pages_range(mapping, lstart, end);
}
rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
gfs2_get_block_direct, NULL, NULL, 0);
out:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
return rv;
}
/**
* gfs2_releasepage - free the metadata associated with a page
* @page: the page that's being released
@@ -1187,12 +886,10 @@ static const struct address_space_operations gfs2_writeback_aops = {
.writepages = gfs2_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.bmap = gfs2_bmap,
.invalidatepage = gfs2_invalidatepage,
.releasepage = gfs2_releasepage,
.direct_IO = gfs2_direct_IO,
.direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
@@ -1203,13 +900,11 @@ static const struct address_space_operations gfs2_ordered_aops = {
.writepages = gfs2_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.set_page_dirty = __set_page_dirty_buffers,
.bmap = gfs2_bmap,
.invalidatepage = gfs2_invalidatepage,
.releasepage = gfs2_releasepage,
.direct_IO = gfs2_direct_IO,
.direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
@@ -1220,8 +915,6 @@ static const struct address_space_operations gfs2_jdata_aops = {
.writepages = gfs2_jdata_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.set_page_dirty = jdata_set_page_dirty,
.bmap = gfs2_bmap,
.invalidatepage = gfs2_invalidatepage,

19
fs/gfs2/aops.h Normal file
View File

@@ -0,0 +1,19 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2018 Red Hat, Inc. All rights reserved.
*/
#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__ */

398
fs/gfs2/bmap.c
View File

@@ -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;
@@ -397,27 +400,23 @@ 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;
}
}
/**
* gfs2_extent_length - Returns length of an extent of blocks
* @start: Start of the buffer
* @len: Length of the buffer in bytes
* @ptr: Current position in the buffer
* @limit: Max extent length to return (0 = unlimited)
* @bh: The metadata block
* @ptr: Current position in @bh
* @limit: Max extent length to return
* @eob: Set to 1 if we hit "end of block"
*
* If the first block is zero (unallocated) it will return the number of
* unallocated blocks in the extent, otherwise it will return the number
* of contiguous blocks in the extent.
*
* Returns: The length of the extent (minimum of one block)
*/
static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __be64 *ptr, size_t limit, int *eob)
static inline unsigned int gfs2_extent_length(struct buffer_head *bh, __be64 *ptr, size_t limit, int *eob)
{
const __be64 *end = (start + len);
const __be64 *end = (__be64 *)(bh->b_data + bh->b_size);
const __be64 *first = ptr;
u64 d = be64_to_cpu(*ptr);
@@ -426,14 +425,11 @@ static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __b
ptr++;
if (ptr >= end)
break;
if (limit && --limit == 0)
break;
if (d)
d++;
d++;
} while(be64_to_cpu(*ptr) == d);
if (ptr >= end)
*eob = 1;
return (ptr - first);
return ptr - first;
}
typedef const __be64 *(*gfs2_metadata_walker)(
@@ -609,11 +605,13 @@ 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 +631,26 @@ 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 +735,7 @@ 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);
@@ -759,19 +745,52 @@ out:
return ret;
}
static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
#define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE
/**
* 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;
iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
sizeof(struct gfs2_dinode);
iomap->offset = 0;
iomap->length = i_size_read(inode);
iomap->type = IOMAP_INLINE;
/*
* 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 int 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;
}
#define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE
/**
* gfs2_iomap_get - Map blocks from an inode to disk blocks
* @inode: The inode
@@ -789,37 +808,63 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
loff_t size = i_size_read(inode);
__be64 *ptr;
sector_t lblock;
sector_t lblock_stop;
int ret;
int eob;
u64 len;
struct buffer_head *bh;
struct buffer_head *dibh = NULL, *bh;
u8 height;
if (!length)
return -EINVAL;
down_read(&ip->i_rw_mutex);
ret = gfs2_meta_inode_buffer(ip, &dibh);
if (ret)
goto unlock;
iomap->private = dibh;
if (gfs2_is_stuffed(ip)) {
if (flags & IOMAP_REPORT) {
if (pos >= i_size_read(inode))
return -ENOENT;
gfs2_stuffed_iomap(inode, iomap);
return 0;
if (flags & IOMAP_WRITE) {
loff_t max_size = gfs2_max_stuffed_size(ip);
if (pos + length > max_size)
goto unstuff;
iomap->length = max_size;
} else {
if (pos >= size) {
if (flags & IOMAP_REPORT) {
ret = -ENOENT;
goto unlock;
} else {
/* report a hole */
iomap->offset = pos;
iomap->length = length;
goto do_alloc;
}
}
iomap->length = size;
}
BUG_ON(!(flags & IOMAP_WRITE));
iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
sizeof(struct gfs2_dinode);
iomap->type = IOMAP_INLINE;
iomap->inline_data = dibh->b_data + sizeof(struct gfs2_dinode);
goto out;
}
unstuff:
lblock = pos >> inode->i_blkbits;
iomap->offset = lblock << inode->i_blkbits;
lblock_stop = (pos + length - 1) >> inode->i_blkbits;
len = lblock_stop - lblock + 1;
iomap->length = len << inode->i_blkbits;
down_read(&ip->i_rw_mutex);
ret = gfs2_meta_inode_buffer(ip, &mp->mp_bh[0]);
if (ret)
goto unlock;
get_bh(dibh);
mp->mp_bh[0] = dibh;
height = ip->i_height;
while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height])
@@ -840,7 +885,7 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
goto do_alloc;
bh = mp->mp_bh[ip->i_height - 1];
len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, len, &eob);
len = gfs2_extent_length(bh, ptr, len, &eob);
iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
iomap->length = len << inode->i_blkbits;
@@ -853,25 +898,185 @@ out:
iomap->bdev = inode->i_sb->s_bdev;
unlock:
up_read(&ip->i_rw_mutex);
if (ret && dibh)
brelse(dibh);
return ret;
do_alloc:
iomap->addr = IOMAP_NULL_ADDR;
iomap->length = len << inode->i_blkbits;
iomap->type = IOMAP_HOLE;
iomap->flags = 0;
if (flags & IOMAP_REPORT) {
loff_t size = i_size_read(inode);
if (pos >= size)
ret = -ENOENT;
else if (height == ip->i_height)
ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
else
iomap->length = size - pos;
} else if (flags & IOMAP_WRITE) {
u64 alloc_size;
if (flags & IOMAP_DIRECT)
goto out; /* (see gfs2_file_direct_write) */
len = gfs2_alloc_size(inode, mp, len);
alloc_size = len << inode->i_blkbits;
if (alloc_size < iomap->length)
iomap->length = alloc_size;
} else {
if (pos < size && 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 void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
unsigned copied, struct page *page,
struct iomap *iomap)
{
struct gfs2_inode *ip = GFS2_I(inode);
gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
}
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;
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;
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);
brelse(iomap->private);
iomap->private = NULL;
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);
gfs2_inplace_release(ip);
punch_hole(ip, iomap->offset, iomap->length);
goto out_qunlock;
}
}
release_metapath(&mp);
if (gfs2_is_jdata(ip))
iomap->page_done = gfs2_iomap_journaled_page_done;
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:
if (iomap->private)
brelse(iomap->private);
release_metapath(&mp);
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)
{
@@ -880,21 +1085,76 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
int ret;
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);
if ((flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)) {
ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap);
} else {
ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
release_metapath(&mp);
/*
* Silently fall back to buffered I/O for stuffed files or if
* we've hot a hole (see gfs2_file_direct_write).
*/
if ((flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT) &&
iomap->type != IOMAP_MAPPED)
ret = -ENOTBLK;
}
trace_gfs2_iomap_end(ip, iomap, ret);
return ret;
}
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;
struct buffer_head *dibh = iomap->private;
if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != IOMAP_WRITE)
goto out;
if (iomap->type != IOMAP_INLINE) {
gfs2_ordered_add_inode(ip);
if (tr->tr_num_buf_new)
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
else
gfs2_trans_add_meta(ip->i_gl, dibh);
}
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);
out:
if (dibh)
brelse(dibh);
return 0;
}
const struct iomap_ops gfs2_iomap_ops = {
.iomap_begin = gfs2_iomap_begin,
.iomap_end = gfs2_iomap_end,
};
/**
@@ -941,12 +1201,6 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
} else {
ret = gfs2_iomap_get(inode, pos, length, 0, &iomap, &mp);
release_metapath(&mp);
/* Return unmapped buffer beyond the end of file. */
if (ret == -ENOENT) {
ret = 0;
goto out;
}
}
if (ret)
goto out;

12
fs/gfs2/dir.c
View File

@@ -871,7 +871,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
struct buffer_head *bh;
struct gfs2_leaf *leaf;
struct gfs2_dirent *dent;
struct timespec tv = current_time(inode);
struct timespec64 tv = current_time(inode);
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
if (error)
@@ -1055,7 +1055,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
/* Change the pointers.
Don't bother distinguishing stuffed from non-stuffed.
This code is complicated enough already. */
lp = kmalloc(half_len * sizeof(__be64), GFP_NOFS);
lp = kmalloc_array(half_len, sizeof(__be64), GFP_NOFS);
if (!lp) {
error = -ENOMEM;
goto fail_brelse;
@@ -1169,7 +1169,7 @@ static int dir_double_exhash(struct gfs2_inode *dip)
if (IS_ERR(hc))
return PTR_ERR(hc);
hc2 = kmalloc(hsize_bytes * 2, GFP_NOFS | __GFP_NOWARN);
hc2 = kmalloc_array(hsize_bytes, 2, GFP_NOFS | __GFP_NOWARN);
if (hc2 == NULL)
hc2 = __vmalloc(hsize_bytes * 2, GFP_NOFS, PAGE_KERNEL);
@@ -1596,7 +1596,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx,
error = -ENOMEM;
/* 96 is max number of dirents which can be stuffed into an inode */
darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_NOFS);
darr = kmalloc_array(96, sizeof(struct gfs2_dirent *), GFP_NOFS);
if (darr) {
g.pdent = (const struct gfs2_dirent **)darr;
g.offset = 0;
@@ -1802,7 +1802,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name,
struct gfs2_inode *ip = GFS2_I(inode);
struct buffer_head *bh = da->bh;
struct gfs2_dirent *dent = da->dent;
struct timespec tv;
struct timespec64 tv;
struct gfs2_leaf *leaf;
int error;
@@ -1880,7 +1880,7 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
const struct qstr *name = &dentry->d_name;
struct gfs2_dirent *dent, *prev = NULL;
struct buffer_head *bh;
struct timespec tv = current_time(&dip->i_inode);
struct timespec64 tv = current_time(&dip->i_inode);
/* Returns _either_ the entry (if its first in block) or the
previous entry otherwise */

162
fs/gfs2/file.c
View File

@@ -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"
@@ -688,12 +690,89 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
return ret ? ret : ret1;
}
static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
size_t count = iov_iter_count(to);
struct gfs2_holder gh;
ssize_t ret;
if (!count)
return 0; /* skip atime */
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
/* fall back to buffered I/O for stuffed files */
ret = -ENOTBLK;
if (gfs2_is_stuffed(ip))
goto out;
ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL);
out:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
return ret;
}
static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
size_t len = iov_iter_count(from);
loff_t offset = iocb->ki_pos;
struct gfs2_holder gh;
ssize_t ret;
/*
* Deferred lock, even if its a write, since we do no allocation on
* this path. All we need to change is the atime, and this lock mode
* ensures that other nodes have flushed their buffered read caches
* (i.e. their page cache entries for this inode). We do not,
* unfortunately, have the option of only flushing a range like the
* VFS does.
*/
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
/* Silently fall back to buffered I/O when writing beyond EOF */
if (offset + len > i_size_read(&ip->i_inode))
goto out;
ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL);
out:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
return ret;
}
static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
ssize_t ret;
if (iocb->ki_flags & IOCB_DIRECT) {
ret = gfs2_file_direct_read(iocb, to);
if (likely(ret != -ENOTBLK))
return ret;
iocb->ki_flags &= ~IOCB_DIRECT;
}
return generic_file_read_iter(iocb, to);
}
/**
* 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 +784,9 @@ 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 written = 0, ret;
ret = gfs2_rsqa_alloc(ip);
if (ret)
@@ -723,7 +803,71 @@ 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);
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;
if (iocb->ki_flags & IOCB_DIRECT) {
struct address_space *mapping = file->f_mapping;
loff_t pos, endbyte;
ssize_t buffered;
written = gfs2_file_direct_write(iocb, from);
if (written < 0 || !iov_iter_count(from))
goto out2;
ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
if (unlikely(ret < 0))
goto out2;
buffered = ret;
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
*/
pos = iocb->ki_pos;
endbyte = pos + buffered - 1;
ret = filemap_write_and_wait_range(mapping, pos, endbyte);
if (!ret) {
iocb->ki_pos += buffered;
written += buffered;
invalidate_mapping_pages(mapping,
pos >> PAGE_SHIFT,
endbyte >> PAGE_SHIFT);
} else {
/*
* We don't know how much we wrote, so just return
* the number of bytes which were direct-written
*/
}
} else {
ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
if (likely(ret > 0))
iocb->ki_pos += ret;
}
out2:
current->backing_dev_info = NULL;
out:
inode_unlock(inode);
if (likely(ret > 0)) {
/* Handle various SYNC-type writes */
ret = generic_write_sync(iocb, ret);
}
return written ? written : ret;
}
static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
@@ -754,7 +898,7 @@ 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,
@@ -1125,7 +1269,7 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
const struct file_operations gfs2_file_fops = {
.llseek = gfs2_llseek,
.read_iter = generic_file_read_iter,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
@@ -1155,7 +1299,7 @@ const struct file_operations gfs2_dir_fops = {
const struct file_operations gfs2_file_fops_nolock = {
.llseek = gfs2_llseek,
.read_iter = generic_file_read_iter,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,

3
fs/gfs2/glock.c
View File

@@ -1303,7 +1303,8 @@ int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs)
default:
if (num_gh <= 4)
break;
pph = kmalloc(num_gh * sizeof(struct gfs2_holder *), GFP_NOFS);
pph = kmalloc_array(num_gh, sizeof(struct gfs2_holder *),
GFP_NOFS);
if (!pph)
return -ENOMEM;
}

4
fs/gfs2/glops.c
View File

@@ -338,7 +338,7 @@ static int inode_go_demote_ok(const struct gfs2_glock *gl)
static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
{
const struct gfs2_dinode *str = buf;
struct timespec atime;
struct timespec64 atime;
u16 height, depth;
if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
@@ -361,7 +361,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
atime.tv_sec = be64_to_cpu(str->di_atime);
atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
if (timespec64_compare(&ip->i_inode.i_atime, &atime) < 0)
ip->i_inode.i_atime = atime;
ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);

2
fs/gfs2/quota.c
View File

@@ -886,7 +886,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
&data_blocks, &ind_blocks);
ghs = kmalloc(num_qd * sizeof(struct gfs2_holder), GFP_NOFS);
ghs = kmalloc_array(num_qd, sizeof(struct gfs2_holder), GFP_NOFS);
if (!ghs)
return -ENOMEM;

5
fs/gfs2/rgrp.c
View File

@@ -2622,8 +2622,9 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state)
{
unsigned int x;
rlist->rl_ghs = kmalloc(rlist->rl_rgrps * sizeof(struct gfs2_holder),
GFP_NOFS | __GFP_NOFAIL);
rlist->rl_ghs = kmalloc_array(rlist->rl_rgrps,
sizeof(struct gfs2_holder),
GFP_NOFS | __GFP_NOFAIL);
for (x = 0; x < rlist->rl_rgrps; x++)
gfs2_holder_init(rlist->rl_rgd[x]->rd_gl,
state, 0,

2
fs/gfs2/super.c
View File

@@ -1097,7 +1097,7 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
int error = 0, err;
memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
gha = kmalloc(slots * sizeof(struct gfs2_holder), GFP_KERNEL);
gha = kmalloc_array(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
if (!gha)
return -ENOMEM;
for (x = 0; x < slots; x++)