aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_aops.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/xfs_aops.c')
-rw-r--r--fs/xfs/xfs_aops.c322
1 files changed, 217 insertions, 105 deletions
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4111a40ebe1..faaf716e208 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -16,21 +16,25 @@
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
-#include "xfs_log.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_trans.h"
#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_iomap.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dinode.h"
+#include <linux/aio.h>
#include <linux/gfp.h>
#include <linux/mpage.h>
#include <linux/pagevec.h>
@@ -85,14 +89,6 @@ xfs_destroy_ioend(
bh->b_end_io(bh, !ioend->io_error);
}
- if (ioend->io_iocb) {
- if (ioend->io_isasync) {
- aio_complete(ioend->io_iocb, ioend->io_error ?
- ioend->io_error : ioend->io_result, 0);
- }
- inode_dio_done(ioend->io_inode);
- }
-
mempool_free(ioend, xfs_ioend_pool);
}
@@ -115,7 +111,7 @@ xfs_setfilesize_trans_alloc(
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
- error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
@@ -280,7 +276,6 @@ xfs_alloc_ioend(
* all the I/O from calling the completion routine too early.
*/
atomic_set(&ioend->io_remaining, 1);
- ioend->io_isasync = 0;
ioend->io_isdirect = 0;
ioend->io_error = 0;
ioend->io_list = NULL;
@@ -290,8 +285,6 @@ xfs_alloc_ioend(
ioend->io_buffer_tail = NULL;
ioend->io_offset = 0;
ioend->io_size = 0;
- ioend->io_iocb = NULL;
- ioend->io_result = 0;
ioend->io_append_trans = NULL;
INIT_WORK(&ioend->io_work, xfs_end_io);
@@ -343,7 +336,7 @@ xfs_map_blocks(
if (type == XFS_IO_DELALLOC &&
(!nimaps || isnullstartblock(imap->br_startblock))) {
- error = xfs_iomap_write_allocate(ip, offset, count, imap);
+ error = xfs_iomap_write_allocate(ip, offset, imap);
if (!error)
trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
return -XFS_ERROR(error);
@@ -414,7 +407,7 @@ xfs_alloc_ioend_bio(
struct bio *bio = bio_alloc(GFP_NOIO, nvecs);
ASSERT(bio->bi_private == NULL);
- bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
return bio;
}
@@ -450,7 +443,7 @@ xfs_start_page_writeback(
end_page_writeback(page);
}
-static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
+static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
{
return bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
}
@@ -524,7 +517,7 @@ xfs_submit_ioend(
goto retry;
}
- if (bio_add_buffer(bio, bh) != bh->b_size) {
+ if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
xfs_submit_ioend_bio(wbc, ioend, bio);
goto retry;
}
@@ -639,38 +632,46 @@ xfs_map_at_offset(
}
/*
- * Test if a given page is suitable for writing as part of an unwritten
- * or delayed allocate extent.
+ * Test if a given page contains at least one buffer of a given @type.
+ * If @check_all_buffers is true, then we walk all the buffers in the page to
+ * try to find one of the type passed in. If it is not set, then the caller only
+ * needs to check the first buffer on the page for a match.
*/
-STATIC int
+STATIC bool
xfs_check_page_type(
struct page *page,
- unsigned int type)
+ unsigned int type,
+ bool check_all_buffers)
{
- if (PageWriteback(page))
- return 0;
+ struct buffer_head *bh;
+ struct buffer_head *head;
- if (page->mapping && page_has_buffers(page)) {
- struct buffer_head *bh, *head;
- int acceptable = 0;
+ if (PageWriteback(page))
+ return false;
+ if (!page->mapping)
+ return false;
+ if (!page_has_buffers(page))
+ return false;
- bh = head = page_buffers(page);
- do {
- if (buffer_unwritten(bh))
- acceptable += (type == XFS_IO_UNWRITTEN);
- else if (buffer_delay(bh))
- acceptable += (type == XFS_IO_DELALLOC);
- else if (buffer_dirty(bh) && buffer_mapped(bh))
- acceptable += (type == XFS_IO_OVERWRITE);
- else
- break;
- } while ((bh = bh->b_this_page) != head);
+ bh = head = page_buffers(page);
+ do {
+ if (buffer_unwritten(bh)) {
+ if (type == XFS_IO_UNWRITTEN)
+ return true;
+ } else if (buffer_delay(bh)) {
+ if (type == XFS_IO_DELALLOC)
+ return true;
+ } else if (buffer_dirty(bh) && buffer_mapped(bh)) {
+ if (type == XFS_IO_OVERWRITE)
+ return true;
+ }
- if (acceptable)
- return 1;
- }
+ /* If we are only checking the first buffer, we are done now. */
+ if (!check_all_buffers)
+ break;
+ } while ((bh = bh->b_this_page) != head);
- return 0;
+ return false;
}
/*
@@ -704,7 +705,7 @@ xfs_convert_page(
goto fail_unlock_page;
if (page->mapping != inode->i_mapping)
goto fail_unlock_page;
- if (!xfs_check_page_type(page, (*ioendp)->io_type))
+ if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
goto fail_unlock_page;
/*
@@ -724,12 +725,40 @@ xfs_convert_page(
(xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
i_size_read(inode));
+ /*
+ * If the current map does not span the entire page we are about to try
+ * to write, then give up. The only way we can write a page that spans
+ * multiple mappings in a single writeback iteration is via the
+ * xfs_vm_writepage() function. Data integrity writeback requires the
+ * entire page to be written in a single attempt, otherwise the part of
+ * the page we don't write here doesn't get written as part of the data
+ * integrity sync.
+ *
+ * For normal writeback, we also don't attempt to write partial pages
+ * here as it simply means that write_cache_pages() will see it under
+ * writeback and ignore the page until some point in the future, at
+ * which time this will be the only page in the file that needs
+ * writeback. Hence for more optimal IO patterns, we should always
+ * avoid partial page writeback due to multiple mappings on a page here.
+ */
+ if (!xfs_imap_valid(inode, imap, end_offset))
+ goto fail_unlock_page;
+
len = 1 << inode->i_blkbits;
p_offset = min_t(unsigned long, end_offset & (PAGE_CACHE_SIZE - 1),
PAGE_CACHE_SIZE);
p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
page_dirty = p_offset / len;
+ /*
+ * The moment we find a buffer that doesn't match our current type
+ * specification or can't be written, abort the loop and start
+ * writeback. As per the above xfs_imap_valid() check, only
+ * xfs_vm_writepage() can handle partial page writeback fully - we are
+ * limited here to the buffers that are contiguous with the current
+ * ioend, and hence a buffer we can't write breaks that contiguity and
+ * we have to defer the rest of the IO to xfs_vm_writepage().
+ */
bh = head = page_buffers(page);
do {
if (offset >= end_offset)
@@ -738,7 +767,7 @@ xfs_convert_page(
uptodate = 0;
if (!(PageUptodate(page) || buffer_uptodate(bh))) {
done = 1;
- continue;
+ break;
}
if (buffer_unwritten(bh) || buffer_delay(bh) ||
@@ -750,10 +779,11 @@ xfs_convert_page(
else
type = XFS_IO_OVERWRITE;
- if (!xfs_imap_valid(inode, imap, offset)) {
- done = 1;
- continue;
- }
+ /*
+ * imap should always be valid because of the above
+ * partial page end_offset check on the imap.
+ */
+ ASSERT(xfs_imap_valid(inode, imap, offset));
lock_buffer(bh);
if (type != XFS_IO_OVERWRITE)
@@ -765,6 +795,7 @@ xfs_convert_page(
count++;
} else {
done = 1;
+ break;
}
} while (offset += len, (bh = bh->b_this_page) != head);
@@ -823,10 +854,12 @@ xfs_cluster_write(
STATIC void
xfs_vm_invalidatepage(
struct page *page,
- unsigned long offset)
+ unsigned int offset,
+ unsigned int length)
{
- trace_xfs_invalidatepage(page->mapping->host, page, offset);
- block_invalidatepage(page, offset);
+ trace_xfs_invalidatepage(page->mapping->host, page, offset,
+ length);
+ block_invalidatepage(page, offset, length);
}
/*
@@ -854,7 +887,7 @@ xfs_aops_discard_page(
struct buffer_head *bh, *head;
loff_t offset = page_offset(page);
- if (!xfs_check_page_type(page, XFS_IO_DELALLOC))
+ if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
goto out_invalidate;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -890,7 +923,7 @@ next_buffer:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_invalidate:
- xfs_vm_invalidatepage(page, 0);
+ xfs_vm_invalidatepage(page, 0, PAGE_CACHE_SIZE);
return;
}
@@ -920,7 +953,7 @@ xfs_vm_writepage(
int count = 0;
int nonblocking = 0;
- trace_xfs_writepage(inode, page, 0);
+ trace_xfs_writepage(inode, page, 0, 0);
ASSERT(page_has_buffers(page));
@@ -942,39 +975,76 @@ xfs_vm_writepage(
* Given that we do not allow direct reclaim to call us, we should
* never be called while in a filesystem transaction.
*/
- if (WARN_ON(current->flags & PF_FSTRANS))
+ if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
goto redirty;
/* Is this page beyond the end of the file? */
offset = i_size_read(inode);
end_index = offset >> PAGE_CACHE_SHIFT;
last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
- if (page->index >= end_index) {
+
+ /*
+ * The page index is less than the end_index, adjust the end_offset
+ * to the highest offset that this page should represent.
+ * -----------------------------------------------------
+ * | file mapping | <EOF> |
+ * -----------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | |
+ * ^--------------------------------^----------|--------
+ * | desired writeback range | see else |
+ * ---------------------------------^------------------|
+ */
+ if (page->index < end_index)
+ end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
+ else {
+ /*
+ * Check whether the page to write out is beyond or straddles
+ * i_size or not.
+ * -------------------------------------------------------
+ * | file mapping | <EOF> |
+ * -------------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | Beyond |
+ * ^--------------------------------^-----------|---------
+ * | | Straddles |
+ * ---------------------------------^-----------|--------|
+ */
unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
/*
- * Just skip the page if it is fully outside i_size, e.g. due
- * to a truncate operation that is in progress.
+ * Skip the page if it is fully outside i_size, e.g. due to a
+ * truncate operation that is in progress. We must redirty the
+ * page so that reclaim stops reclaiming it. Otherwise
+ * xfs_vm_releasepage() is called on it and gets confused.
+ *
+ * Note that the end_index is unsigned long, it would overflow
+ * if the given offset is greater than 16TB on 32-bit system
+ * and if we do check the page is fully outside i_size or not
+ * via "if (page->index >= end_index + 1)" as "end_index + 1"
+ * will be evaluated to 0. Hence this page will be redirtied
+ * and be written out repeatedly which would result in an
+ * infinite loop, the user program that perform this operation
+ * will hang. Instead, we can verify this situation by checking
+ * if the page to write is totally beyond the i_size or if it's
+ * offset is just equal to the EOF.
*/
- if (page->index >= end_index + 1 || offset_into_page == 0) {
- unlock_page(page);
- return 0;
- }
+ if (page->index > end_index ||
+ (page->index == end_index && offset_into_page == 0))
+ goto redirty;
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invocation because it may be mmapped.
* "A file is mapped in multiples of the page size. For a file
- * that is not a multiple of the page size, the remaining
+ * that is not a multiple of the page size, the remaining
* memory is zeroed when mapped, and writes to that region are
* not written out to the file."
*/
zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
+
+ /* Adjust the end_offset to the end of file */
+ end_offset = offset;
}
- end_offset = min_t(unsigned long long,
- (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
- offset);
len = 1 << inode->i_blkbits;
bh = head = page_buffers(page);
@@ -1151,13 +1221,13 @@ xfs_vm_releasepage(
{
int delalloc, unwritten;
- trace_xfs_releasepage(page->mapping->host, page, 0);
+ trace_xfs_releasepage(page->mapping->host, page, 0, 0);
xfs_count_page_state(page, &delalloc, &unwritten);
- if (WARN_ON(delalloc))
+ if (WARN_ON_ONCE(delalloc))
return 0;
- if (WARN_ON(unwritten))
+ if (WARN_ON_ONCE(unwritten))
return 0;
return try_to_free_buffers(page);
@@ -1203,7 +1273,7 @@ __xfs_get_blocks(
lockmode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lockmode);
} else {
- lockmode = xfs_ilock_map_shared(ip);
+ lockmode = xfs_ilock_data_map_shared(ip);
}
ASSERT(offset <= mp->m_super->s_maxbytes);
@@ -1270,8 +1340,10 @@ __xfs_get_blocks(
if (create || !ISUNWRITTEN(&imap))
xfs_map_buffer(inode, bh_result, &imap, offset);
if (create && ISUNWRITTEN(&imap)) {
- if (direct)
+ if (direct) {
bh_result->b_private = inode;
+ set_buffer_defer_completion(bh_result);
+ }
set_buffer_unwritten(bh_result);
}
}
@@ -1309,6 +1381,14 @@ __xfs_get_blocks(
/*
* If this is O_DIRECT or the mpage code calling tell them how large
* the mapping is, so that we can avoid repeated get_blocks calls.
+ *
+ * If the mapping spans EOF, then we have to break the mapping up as the
+ * mapping for blocks beyond EOF must be marked new so that sub block
+ * regions can be correctly zeroed. We can't do this for mappings within
+ * EOF unless the mapping was just allocated or is unwritten, otherwise
+ * the callers would overwrite existing data with zeros. Hence we have
+ * to split the mapping into a range up to and including EOF, and a
+ * second mapping for beyond EOF.
*/
if (direct || size > (1 << inode->i_blkbits)) {
xfs_off_t mapping_size;
@@ -1319,6 +1399,12 @@ __xfs_get_blocks(
ASSERT(mapping_size > 0);
if (mapping_size > size)
mapping_size = size;
+ if (offset < i_size_read(inode) &&
+ offset + mapping_size >= i_size_read(inode)) {
+ /* limit mapping to block that spans EOF */
+ mapping_size = roundup_64(i_size_read(inode) - offset,
+ 1 << inode->i_blkbits);
+ }
if (mapping_size > LONG_MAX)
mapping_size = LONG_MAX;
@@ -1368,9 +1454,7 @@ xfs_end_io_direct_write(
struct kiocb *iocb,
loff_t offset,
ssize_t size,
- void *private,
- int ret,
- bool is_async)
+ void *private)
{
struct xfs_ioend *ioend = iocb->private;
@@ -1392,26 +1476,18 @@ xfs_end_io_direct_write(
ioend->io_offset = offset;
ioend->io_size = size;
- ioend->io_iocb = iocb;
- ioend->io_result = ret;
if (private && size > 0)
ioend->io_type = XFS_IO_UNWRITTEN;
- if (is_async) {
- ioend->io_isasync = 1;
- xfs_finish_ioend(ioend);
- } else {
- xfs_finish_ioend_sync(ioend);
- }
+ xfs_finish_ioend_sync(ioend);
}
STATIC ssize_t
xfs_vm_direct_IO(
int rw,
struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t offset)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
struct block_device *bdev = xfs_find_bdev_for_inode(inode);
@@ -1419,7 +1495,7 @@ xfs_vm_direct_IO(
ssize_t ret;
if (rw & WRITE) {
- size_t size = iov_length(iov, nr_segs);
+ size_t size = iov_iter_count(iter);
/*
* We cannot preallocate a size update transaction here as we
@@ -1431,16 +1507,15 @@ xfs_vm_direct_IO(
if (offset + size > XFS_I(inode)->i_d.di_size)
ioend->io_isdirect = 1;
- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
- xfs_get_blocks_direct,
- xfs_end_io_direct_write, NULL, 0);
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+ offset, xfs_get_blocks_direct,
+ xfs_end_io_direct_write, NULL,
+ DIO_ASYNC_EXTEND);
if (ret != -EIOCBQUEUED && iocb->private)
goto out_destroy_ioend;
} else {
- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
- xfs_get_blocks_direct,
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+ offset, xfs_get_blocks_direct,
NULL, NULL, 0);
}
@@ -1494,13 +1569,26 @@ xfs_vm_write_failed(
loff_t pos,
unsigned len)
{
- loff_t block_offset = pos & PAGE_MASK;
+ loff_t block_offset;
loff_t block_start;
loff_t block_end;
loff_t from = pos & (PAGE_CACHE_SIZE - 1);
loff_t to = from + len;
struct buffer_head *bh, *head;
+ /*
+ * The request pos offset might be 32 or 64 bit, this is all fine
+ * on 64-bit platform. However, for 64-bit pos request on 32-bit
+ * platform, the high 32-bit will be masked off if we evaluate the
+ * block_offset via (pos & PAGE_MASK) because the PAGE_MASK is
+ * 0xfffff000 as an unsigned long, hence the result is incorrect
+ * which could cause the following ASSERT failed in most cases.
+ * In order to avoid this, we can evaluate the block_offset of the
+ * start of the page by using shifts rather than masks the mismatch
+ * problem.
+ */
+ block_offset = (pos >> PAGE_CACHE_SHIFT) << PAGE_CACHE_SHIFT;
+
ASSERT(block_offset + from == pos);
head = page_buffers(page);
@@ -1526,6 +1614,16 @@ xfs_vm_write_failed(
xfs_vm_kill_delalloc_range(inode, block_offset,
block_offset + bh->b_size);
+
+ /*
+ * This buffer does not contain data anymore. make sure anyone
+ * who finds it knows that for certain.
+ */
+ clear_buffer_delay(bh);
+ clear_buffer_uptodate(bh);
+ clear_buffer_mapped(bh);
+ clear_buffer_new(bh);
+ clear_buffer_dirty(bh);
}
}
@@ -1552,20 +1650,28 @@ xfs_vm_write_begin(
ASSERT(len <= PAGE_CACHE_SIZE);
- page = grab_cache_page_write_begin(mapping, index,
- flags | AOP_FLAG_NOFS);
+ page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
status = __block_write_begin(page, pos, len, xfs_get_blocks);
if (unlikely(status)) {
struct inode *inode = mapping->host;
+ size_t isize = i_size_read(inode);
xfs_vm_write_failed(inode, page, pos, len);
unlock_page(page);
- if (pos + len > i_size_read(inode))
- truncate_pagecache(inode, pos + len, i_size_read(inode));
+ /*
+ * If the write is beyond EOF, we only want to kill blocks
+ * allocated in this write, not blocks that were previously
+ * written successfully.
+ */
+ if (pos + len > isize) {
+ ssize_t start = max_t(ssize_t, pos, isize);
+
+ truncate_pagecache_range(inode, start, pos + len);
+ }
page_cache_release(page);
page = NULL;
@@ -1576,9 +1682,12 @@ xfs_vm_write_begin(
}
/*
- * On failure, we only need to kill delalloc blocks beyond EOF because they
- * will never be written. For blocks within EOF, generic_write_end() zeros them
- * so they are safe to leave alone and be written with all the other valid data.
+ * On failure, we only need to kill delalloc blocks beyond EOF in the range of
+ * this specific write because they will never be written. Previous writes
+ * beyond EOF where block allocation succeeded do not need to be trashed, so
+ * only new blocks from this write should be trashed. For blocks within
+ * EOF, generic_write_end() zeros them so they are safe to leave alone and be
+ * written with all the other valid data.
*/
STATIC int
xfs_vm_write_end(
@@ -1601,8 +1710,11 @@ xfs_vm_write_end(
loff_t to = pos + len;
if (to > isize) {
- truncate_pagecache(inode, to, isize);
+ /* only kill blocks in this write beyond EOF */
+ if (pos > isize)
+ isize = pos;
xfs_vm_kill_delalloc_range(inode, isize, to);
+ truncate_pagecache_range(inode, isize, to);
}
}
return ret;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 20:31:33 +0000