#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/fs.h>
+ #include <linux/iomap.h>
#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <trace/events/block.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
-static int submit_bh_wbc(int rw, struct buffer_head *bh,
+static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
unsigned long bio_flags,
struct writeback_control *wbc);
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- /* This happens, due to failed READA attempts. */
+ /* This happens, due to failed read-ahead attempts. */
clear_buffer_uptodate(bh);
}
unlock_buffer(bh);
struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
if (bh) {
if (buffer_dirty(bh))
- ll_rw_block(WRITE, 1, &bh);
+ ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
put_bh(bh);
}
}
} else {
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(READ, bh);
+ submit_bh(REQ_OP_READ, 0, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
{
struct buffer_head *bh = __getblk(bdev, block, size);
if (likely(bh)) {
- ll_rw_block(READA, 1, &bh);
+ ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
brelse(bh);
}
}
* WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this
* causes the writes to be flagged as synchronous writes.
*/
-static int __block_write_full_page(struct inode *inode, struct page *page,
+int __block_write_full_page(struct inode *inode, struct page *page,
get_block_t *get_block, struct writeback_control *wbc,
bh_end_io_t *handler)
{
struct buffer_head *bh, *head;
unsigned int blocksize, bbits;
int nr_underway = 0;
- int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+ int write_flags = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : 0);
head = create_page_buffers(page, inode,
(1 << BH_Dirty)|(1 << BH_Uptodate));
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh_wbc(write_op, bh, 0, wbc);
+ submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, 0, wbc);
nr_underway++;
}
bh = next;
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh_wbc(write_op, bh, 0, wbc);
+ submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, 0, wbc);
nr_underway++;
}
bh = next;
unlock_page(page);
goto done;
}
+EXPORT_SYMBOL(__block_write_full_page);
/*
* If a page has any new buffers, zero them out here, and mark them uptodate
}
EXPORT_SYMBOL(page_zero_new_buffers);
- int __block_write_begin(struct page *page, loff_t pos, unsigned len,
- get_block_t *get_block)
+ static void
+ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
+ struct iomap *iomap)
+ {
+ loff_t offset = block << inode->i_blkbits;
+
+ bh->b_bdev = iomap->bdev;
+
+ /*
+ * Block points to offset in file we need to map, iomap contains
+ * the offset at which the map starts. If the map ends before the
+ * current block, then do not map the buffer and let the caller
+ * handle it.
+ */
+ BUG_ON(offset >= iomap->offset + iomap->length);
+
+ switch (iomap->type) {
+ case IOMAP_HOLE:
+ /*
+ * If the buffer is not up to date or beyond the current EOF,
+ * we need to mark it as new to ensure sub-block zeroing is
+ * executed if necessary.
+ */
+ if (!buffer_uptodate(bh) ||
+ (offset >= i_size_read(inode)))
+ set_buffer_new(bh);
+ break;
+ case IOMAP_DELALLOC:
+ if (!buffer_uptodate(bh) ||
+ (offset >= i_size_read(inode)))
+ set_buffer_new(bh);
+ set_buffer_uptodate(bh);
+ set_buffer_mapped(bh);
+ set_buffer_delay(bh);
+ break;
+ case IOMAP_UNWRITTEN:
+ /*
+ * For unwritten regions, we always need to ensure that
+ * sub-block writes cause the regions in the block we are not
+ * writing to are zeroed. Set the buffer as new to ensure this.
+ */
+ set_buffer_new(bh);
+ set_buffer_unwritten(bh);
+ /* FALLTHRU */
+ case IOMAP_MAPPED:
+ if (offset >= i_size_read(inode))
+ set_buffer_new(bh);
+ bh->b_blocknr = (iomap->blkno >> (inode->i_blkbits - 9)) +
+ ((offset - iomap->offset) >> inode->i_blkbits);
+ set_buffer_mapped(bh);
+ break;
+ }
+ }
+
+ int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
+ get_block_t *get_block, struct iomap *iomap)
{
unsigned from = pos & (PAGE_SIZE - 1);
unsigned to = from + len;
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
- err = get_block(inode, block, bh, 1);
- if (err)
- break;
+ if (get_block) {
+ err = get_block(inode, block, bh, 1);
+ if (err)
+ break;
+ } else {
+ iomap_to_bh(inode, block, bh, iomap);
+ }
+
if (buffer_new(bh)) {
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
- ll_rw_block(READ, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 0, 1, &bh);
*wait_bh++=bh;
}
}
page_zero_new_buffers(page, from, to);
return err;
}
+
+ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+ get_block_t *get_block)
+ {
+ return __block_write_begin_int(page, pos, len, get_block, NULL);
+ }
EXPORT_SYMBOL(__block_write_begin);
static int __block_commit_write(struct inode *inode, struct page *page,
if (buffer_uptodate(bh))
end_buffer_async_read(bh, 1);
else
- submit_bh(READ, bh);
+ submit_bh(REQ_OP_READ, 0, bh);
}
return 0;
}
if (block_start < from || block_end > to) {
lock_buffer(bh);
bh->b_end_io = end_buffer_read_nobh;
- submit_bh(READ, bh);
+ submit_bh(REQ_OP_READ, 0, bh);
nr_reads++;
}
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
err = -EIO;
- ll_rw_block(READ, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 0, 1, &bh);
wait_on_buffer(bh);
/* Uhhuh. Read error. Complain and punt. */
if (!buffer_uptodate(bh))
* errors, this only handles the "we need to be able to
* do IO at the final sector" case.
*/
-void guard_bio_eod(int rw, struct bio *bio)
+void guard_bio_eod(int op, struct bio *bio)
{
sector_t maxsector;
struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
bvec->bv_len -= truncated_bytes;
/* ..and clear the end of the buffer for reads */
- if ((rw & RW_MASK) == READ) {
+ if (op == REQ_OP_READ) {
zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
truncated_bytes);
}
}
-static int submit_bh_wbc(int rw, struct buffer_head *bh,
+static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
unsigned long bio_flags, struct writeback_control *wbc)
{
struct bio *bio;
/*
* Only clear out a write error when rewriting
*/
- if (test_set_buffer_req(bh) && (rw & WRITE))
+ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
clear_buffer_write_io_error(bh);
/*
bio->bi_flags |= bio_flags;
/* Take care of bh's that straddle the end of the device */
- guard_bio_eod(rw, bio);
+ guard_bio_eod(op, bio);
if (buffer_meta(bh))
- rw |= REQ_META;
+ op_flags |= REQ_META;
if (buffer_prio(bh))
- rw |= REQ_PRIO;
+ op_flags |= REQ_PRIO;
+ bio_set_op_attrs(bio, op, op_flags);
- submit_bio(rw, bio);
+ submit_bio(bio);
return 0;
}
-int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
+int _submit_bh(int op, int op_flags, struct buffer_head *bh,
+ unsigned long bio_flags)
{
- return submit_bh_wbc(rw, bh, bio_flags, NULL);
+ return submit_bh_wbc(op, op_flags, bh, bio_flags, NULL);
}
EXPORT_SYMBOL_GPL(_submit_bh);
-int submit_bh(int rw, struct buffer_head *bh)
+int submit_bh(int op, int op_flags, struct buffer_head *bh)
{
- return submit_bh_wbc(rw, bh, 0, NULL);
+ return submit_bh_wbc(op, op_flags, bh, 0, NULL);
}
EXPORT_SYMBOL(submit_bh);
/**
* ll_rw_block: low-level access to block devices (DEPRECATED)
- * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
+ * @op: whether to %READ or %WRITE
+ * @op_flags: rq_flag_bits
* @nr: number of &struct buffer_heads in the array
* @bhs: array of pointers to &struct buffer_head
*
* ll_rw_block() takes an array of pointers to &struct buffer_heads, and
- * requests an I/O operation on them, either a %READ or a %WRITE. The third
- * %READA option is described in the documentation for generic_make_request()
- * which ll_rw_block() calls.
+ * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE.
+ * @op_flags contains flags modifying the detailed I/O behavior, most notably
+ * %REQ_RAHEAD.
*
* This function drops any buffer that it cannot get a lock on (with the
* BH_Lock state bit), any buffer that appears to be clean when doing a write
* All of the buffers must be for the same device, and must also be a
* multiple of the current approved size for the device.
*/
-void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
+void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[])
{
int i;
if (!trylock_buffer(bh))
continue;
- if (rw == WRITE) {
+ if (op == WRITE) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(WRITE, bh);
+ submit_bh(op, op_flags, bh);
continue;
}
} else {
if (!buffer_uptodate(bh)) {
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(rw, bh);
+ submit_bh(op, op_flags, bh);
continue;
}
}
}
EXPORT_SYMBOL(ll_rw_block);
-void write_dirty_buffer(struct buffer_head *bh, int rw)
+void write_dirty_buffer(struct buffer_head *bh, int op_flags)
{
lock_buffer(bh);
if (!test_clear_buffer_dirty(bh)) {
}
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(rw, bh);
+ submit_bh(REQ_OP_WRITE, op_flags, bh);
}
EXPORT_SYMBOL(write_dirty_buffer);
* and then start new I/O and then wait upon it. The caller must have a ref on
* the buffer_head.
*/
-int __sync_dirty_buffer(struct buffer_head *bh, int rw)
+int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
{
int ret = 0;
if (test_clear_buffer_dirty(bh)) {
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(rw, bh);
+ ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
wait_on_buffer(bh);
if (!ret && !buffer_uptodate(bh))
ret = -EIO;
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(READ, bh);
+ submit_bh(REQ_OP_READ, 0, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return 0;
struct super_block;
struct file_system_type;
+ struct iomap;
struct linux_binprm;
struct path;
struct mount;
* buffer.c
*/
extern void guard_bio_eod(int rw, struct bio *bio);
+ extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
+ get_block_t *get_block, struct iomap *iomap);
/*
* char_dev.c
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
extern int d_set_mounted(struct dentry *dentry);
extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
+extern struct dentry *d_alloc_cursor(struct dentry *);
/*
* read_write.c
* Copyright (c) 2014-2016 Christoph Hellwig.
*/
#include <linux/exportfs.h>
+ #include <linux/iomap.h>
#include <linux/genhd.h>
#include <linux/slab.h>
#include <linux/pr.h>
return error;
}
-#define NFSD_MDS_PR_KEY 0x0100000000000000
+#define NFSD_MDS_PR_KEY 0x0100000000000000ULL
/*
* We use the client ID as a unique key for the reservations.
* We're now finished for good with this page. Update the page state via the
* associated buffer_heads, paying attention to the start and end offsets that
* we need to process on the page.
+ *
+ * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last
+ * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or
+ * the page at all, as we may be racing with memory reclaim and it can free both
+ * the bufferhead chain and the page as it will see the page as clean and
+ * unused.
*/
static void
xfs_finish_page_writeback(
int error)
{
unsigned int end = bvec->bv_offset + bvec->bv_len - 1;
- struct buffer_head *head, *bh;
+ struct buffer_head *head, *bh, *next;
unsigned int off = 0;
+ unsigned int bsize;
ASSERT(bvec->bv_offset < PAGE_SIZE);
ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
bh = head = page_buffers(bvec->bv_page);
+ bsize = bh->b_size;
do {
+ next = bh->b_this_page;
if (off < bvec->bv_offset)
goto next_bh;
if (off > end)
break;
bh->b_end_io(bh, !error);
next_bh:
- off += bh->b_size;
- } while ((bh = bh->b_this_page) != head);
+ off += bsize;
+ } while ((bh = next) != head);
}
/*
ioend->io_bio->bi_private = ioend;
ioend->io_bio->bi_end_io = xfs_end_bio;
-
+ bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE,
+ (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0);
/*
* If we are failing the IO now, just mark the ioend with an
* error and finish it. This will run IO completion immediately
return status;
}
- submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
- ioend->io_bio);
+ submit_bio(ioend->io_bio);
return 0;
}
bio_chain(ioend->io_bio, new);
bio_get(ioend->io_bio); /* for xfs_destroy_ioend */
- submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
- ioend->io_bio);
+ bio_set_op_attrs(ioend->io_bio, REQ_OP_WRITE,
+ (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0);
+ submit_bio(ioend->io_bio);
ioend->io_bio = new;
}
trace_xfs_releasepage(page->mapping->host, page, 0, 0);
+ /*
+ * mm accommodates an old ext3 case where clean pages might not have had
+ * the dirty bit cleared. Thus, it can send actual dirty pages to
+ * ->releasepage() via shrink_active_list(). Conversely,
+ * block_invalidatepage() can send pages that are still marked dirty
+ * but otherwise have invalidated buffers.
+ *
+ * We've historically freed buffers on the latter. Instead, quietly
+ * filter out all dirty pages to avoid spurious buffer state warnings.
+ * This can likely be removed once shrink_active_list() is fixed.
+ */
+ if (PageDirty(page))
+ return 0;
+
xfs_count_page_state(page, &delalloc, &unwritten);
if (WARN_ON_ONCE(delalloc))
ssize_t size;
int new = 0;
+ BUG_ON(create && !direct);
+
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
size = bh_result->b_size;
- if (!create && direct && offset >= i_size_read(inode))
+ if (!create && offset >= i_size_read(inode))
return 0;
/*
* Direct I/O is usually done on preallocated files, so try getting
- * a block mapping without an exclusive lock first. For buffered
- * writes we already have the exclusive iolock anyway, so avoiding
- * a lock roundtrip here by taking the ilock exclusive from the
- * beginning is a useful micro optimization.
+ * a block mapping without an exclusive lock first.
*/
- if (create && !direct) {
- lockmode = XFS_ILOCK_EXCL;
- xfs_ilock(ip, lockmode);
- } else {
- lockmode = xfs_ilock_data_map_shared(ip);
- }
+ lockmode = xfs_ilock_data_map_shared(ip);
ASSERT(offset <= mp->m_super->s_maxbytes);
if (offset + size > mp->m_super->s_maxbytes)
(imap.br_startblock == HOLESTARTBLOCK ||
imap.br_startblock == DELAYSTARTBLOCK) ||
(IS_DAX(inode) && ISUNWRITTEN(&imap)))) {
- if (direct || xfs_get_extsz_hint(ip)) {
- /*
- * xfs_iomap_write_direct() expects the shared lock. It
- * is unlocked on return.
- */
- if (lockmode == XFS_ILOCK_EXCL)
- xfs_ilock_demote(ip, lockmode);
-
- error = xfs_iomap_write_direct(ip, offset, size,
- &imap, nimaps);
- if (error)
- return error;
- new = 1;
+ /*
+ * xfs_iomap_write_direct() expects the shared lock. It
+ * is unlocked on return.
+ */
+ if (lockmode == XFS_ILOCK_EXCL)
+ xfs_ilock_demote(ip, lockmode);
- } else {
- /*
- * Delalloc reservations do not require a transaction,
- * we can go on without dropping the lock here. If we
- * are allocating a new delalloc block, make sure that
- * we set the new flag so that we mark the buffer new so
- * that we know that it is newly allocated if the write
- * fails.
- */
- if (nimaps && imap.br_startblock == HOLESTARTBLOCK)
- new = 1;
- error = xfs_iomap_write_delay(ip, offset, size, &imap);
- if (error)
- goto out_unlock;
+ error = xfs_iomap_write_direct(ip, offset, size,
+ &imap, nimaps);
+ if (error)
+ return error;
+ new = 1;
- xfs_iunlock(ip, lockmode);
- }
trace_xfs_get_blocks_alloc(ip, offset, size,
ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN
: XFS_IO_DELALLOC, &imap);
}
/* trim mapping down to size requested */
- if (direct || size > (1 << inode->i_blkbits))
- xfs_map_trim_size(inode, iblock, bh_result,
- &imap, offset, size);
+ xfs_map_trim_size(inode, iblock, bh_result, &imap, offset, size);
/*
* For unwritten extents do not report a disk address in the buffered
if (ISUNWRITTEN(&imap))
set_buffer_unwritten(bh_result);
/* direct IO needs special help */
- if (create && direct) {
+ if (create) {
if (dax_fault)
ASSERT(!ISUNWRITTEN(&imap));
else
(new || ISUNWRITTEN(&imap))))
set_buffer_new(bh_result);
- if (imap.br_startblock == DELAYSTARTBLOCK) {
- BUG_ON(direct);
- if (create) {
- set_buffer_uptodate(bh_result);
- set_buffer_mapped(bh_result);
- set_buffer_delay(bh_result);
- }
- }
+ BUG_ON(direct && imap.br_startblock == DELAYSTARTBLOCK);
return 0;
* whereas if we have flags set we will always be called in task context
* (i.e. from a workqueue).
*/
- STATIC int
+ int
xfs_end_io_direct_write(
struct kiocb *iocb,
loff_t offset,
struct kiocb *iocb,
struct iov_iter *iter)
{
- struct inode *inode = iocb->ki_filp->f_mapping->host;
- dio_iodone_t *endio = NULL;
- int flags = 0;
- struct block_device *bdev;
-
- if (iov_iter_rw(iter) == WRITE) {
- endio = xfs_end_io_direct_write;
- flags = DIO_ASYNC_EXTEND;
- }
-
- if (IS_DAX(inode)) {
- return dax_do_io(iocb, inode, iter,
- xfs_get_blocks_direct, endio, 0);
- }
-
- bdev = xfs_find_bdev_for_inode(inode);
- return __blockdev_direct_IO(iocb, inode, bdev, iter,
- xfs_get_blocks_direct, endio, NULL, flags);
- }
-
- /*
- * Punch out the delalloc blocks we have already allocated.
- *
- * Don't bother with xfs_setattr given that nothing can have made it to disk yet
- * as the page is still locked at this point.
- */
- STATIC void
- xfs_vm_kill_delalloc_range(
- struct inode *inode,
- loff_t start,
- loff_t end)
- {
- struct xfs_inode *ip = XFS_I(inode);
- xfs_fileoff_t start_fsb;
- xfs_fileoff_t end_fsb;
- int error;
-
- start_fsb = XFS_B_TO_FSB(ip->i_mount, start);
- end_fsb = XFS_B_TO_FSB(ip->i_mount, end);
- if (end_fsb <= start_fsb)
- return;
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
- end_fsb - start_fsb);
- if (error) {
- /* something screwed, just bail */
- if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- xfs_alert(ip->i_mount,
- "xfs_vm_write_failed: unable to clean up ino %lld",
- ip->i_ino);
- }
- }
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- }
-
- STATIC void
- xfs_vm_write_failed(
- struct inode *inode,
- struct page *page,
- loff_t pos,
- unsigned len)
- {
- loff_t block_offset;
- loff_t block_start;
- loff_t block_end;
- loff_t from = pos & (PAGE_SIZE - 1);
- loff_t to = from + len;
- struct buffer_head *bh, *head;
- struct xfs_mount *mp = XFS_I(inode)->i_mount;
-
/*
- * 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.
+ * We just need the method present so that open/fcntl allow direct I/O.
*/
- block_offset = (pos >> PAGE_SHIFT) << PAGE_SHIFT;
-
- ASSERT(block_offset + from == pos);
-
- head = page_buffers(page);
- block_start = 0;
- for (bh = head; bh != head || !block_start;
- bh = bh->b_this_page, block_start = block_end,
- block_offset += bh->b_size) {
- block_end = block_start + bh->b_size;
-
- /* skip buffers before the write */
- if (block_end <= from)
- continue;
-
- /* if the buffer is after the write, we're done */
- if (block_start >= to)
- break;
-
- /*
- * Process delalloc and unwritten buffers beyond EOF. We can
- * encounter unwritten buffers in the event that a file has
- * post-EOF unwritten extents and an extending write happens to
- * fail (e.g., an unaligned write that also involves a delalloc
- * to the same page).
- */
- if (!buffer_delay(bh) && !buffer_unwritten(bh))
- continue;
-
- if (!xfs_mp_fail_writes(mp) && !buffer_new(bh) &&
- block_offset < i_size_read(inode))
- continue;
-
- if (buffer_delay(bh))
- 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);
- clear_buffer_unwritten(bh);
- }
-
- }
-
- /*
- * This used to call block_write_begin(), but it unlocks and releases the page
- * on error, and we need that page to be able to punch stale delalloc blocks out
- * on failure. hence we copy-n-waste it here and call xfs_vm_write_failed() at
- * the appropriate point.
- */
- STATIC int
- xfs_vm_write_begin(
- struct file *file,
- struct address_space *mapping,
- loff_t pos,
- unsigned len,
- unsigned flags,
- struct page **pagep,
- void **fsdata)
- {
- pgoff_t index = pos >> PAGE_SHIFT;
- struct page *page;
- int status;
- struct xfs_mount *mp = XFS_I(mapping->host)->i_mount;
-
- ASSERT(len <= PAGE_SIZE);
-
- page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page)
- return -ENOMEM;
-
- status = __block_write_begin(page, pos, len, xfs_get_blocks);
- if (xfs_mp_fail_writes(mp))
- status = -EIO;
- 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 the write is beyond EOF, we only want to kill blocks
- * allocated in this write, not blocks that were previously
- * written successfully.
- */
- if (xfs_mp_fail_writes(mp))
- isize = 0;
- if (pos + len > isize) {
- ssize_t start = max_t(ssize_t, pos, isize);
-
- truncate_pagecache_range(inode, start, pos + len);
- }
-
- put_page(page);
- page = NULL;
- }
-
- *pagep = page;
- return status;
- }
-
- /*
- * 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(
- struct file *file,
- struct address_space *mapping,
- loff_t pos,
- unsigned len,
- unsigned copied,
- struct page *page,
- void *fsdata)
- {
- int ret;
-
- ASSERT(len <= PAGE_SIZE);
-
- ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
- if (unlikely(ret < len)) {
- struct inode *inode = mapping->host;
- size_t isize = i_size_read(inode);
- loff_t to = pos + len;
-
- if (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;
+ return -EINVAL;
}
STATIC sector_t
.set_page_dirty = xfs_vm_set_page_dirty,
.releasepage = xfs_vm_releasepage,
.invalidatepage = xfs_vm_invalidatepage,
- .write_begin = xfs_vm_write_begin,
- .write_end = xfs_vm_write_end,
.bmap = xfs_vm_bmap,
.direct_IO = xfs_vm_direct_IO,
.migratepage = buffer_migrate_page,
return (bp->b_page_count * PAGE_SIZE) - bp->b_offset;
}
+ /*
+ * Bump the I/O in flight count on the buftarg if we haven't yet done so for
+ * this buffer. The count is incremented once per buffer (per hold cycle)
+ * because the corresponding decrement is deferred to buffer release. Buffers
+ * can undergo I/O multiple times in a hold-release cycle and per buffer I/O
+ * tracking adds unnecessary overhead. This is used for sychronization purposes
+ * with unmount (see xfs_wait_buftarg()), so all we really need is a count of
+ * in-flight buffers.
+ *
+ * Buffers that are never released (e.g., superblock, iclog buffers) must set
+ * the XBF_NO_IOACCT flag before I/O submission. Otherwise, the buftarg count
+ * never reaches zero and unmount hangs indefinitely.
+ */
+ static inline void
+ xfs_buf_ioacct_inc(
+ struct xfs_buf *bp)
+ {
+ if (bp->b_flags & (XBF_NO_IOACCT|_XBF_IN_FLIGHT))
+ return;
+
+ ASSERT(bp->b_flags & XBF_ASYNC);
+ bp->b_flags |= _XBF_IN_FLIGHT;
+ percpu_counter_inc(&bp->b_target->bt_io_count);
+ }
+
+ /*
+ * Clear the in-flight state on a buffer about to be released to the LRU or
+ * freed and unaccount from the buftarg.
+ */
+ static inline void
+ xfs_buf_ioacct_dec(
+ struct xfs_buf *bp)
+ {
+ if (!(bp->b_flags & _XBF_IN_FLIGHT))
+ return;
+
+ ASSERT(bp->b_flags & XBF_ASYNC);
+ bp->b_flags &= ~_XBF_IN_FLIGHT;
+ percpu_counter_dec(&bp->b_target->bt_io_count);
+ }
+
/*
* When we mark a buffer stale, we remove the buffer from the LRU and clear the
* b_lru_ref count so that the buffer is freed immediately when the buffer
*/
bp->b_flags &= ~_XBF_DELWRI_Q;
+ /*
+ * Once the buffer is marked stale and unlocked, a subsequent lookup
+ * could reset b_flags. There is no guarantee that the buffer is
+ * unaccounted (released to LRU) before that occurs. Drop in-flight
+ * status now to preserve accounting consistency.
+ */
+ xfs_buf_ioacct_dec(bp);
+
spin_lock(&bp->b_lock);
atomic_set(&bp->b_lru_ref, 0);
if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
struct xfs_buf *bp;
DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
- bp = _xfs_buf_alloc(target, &map, 1, 0);
+ /* flags might contain irrelevant bits, pass only what we care about */
+ bp = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT);
if (unlikely(bp == NULL))
goto fail;
}
/*
- * Releases a hold on the specified buffer. If the
- * the hold count is 1, calls xfs_buf_free.
+ * Release a hold on the specified buffer. If the hold count is 1, the buffer is
+ * placed on LRU or freed (depending on b_lru_ref).
*/
void
xfs_buf_rele(
xfs_buf_t *bp)
{
struct xfs_perag *pag = bp->b_pag;
+ bool release;
+ bool freebuf = false;
trace_xfs_buf_rele(bp, _RET_IP_);
if (!pag) {
ASSERT(list_empty(&bp->b_lru));
ASSERT(RB_EMPTY_NODE(&bp->b_rbnode));
- if (atomic_dec_and_test(&bp->b_hold))
+ if (atomic_dec_and_test(&bp->b_hold)) {
+ xfs_buf_ioacct_dec(bp);
xfs_buf_free(bp);
+ }
return;
}
ASSERT(!RB_EMPTY_NODE(&bp->b_rbnode));
ASSERT(atomic_read(&bp->b_hold) > 0);
- if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
- spin_lock(&bp->b_lock);
- if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
- /*
- * If the buffer is added to the LRU take a new
- * reference to the buffer for the LRU and clear the
- * (now stale) dispose list state flag
- */
- if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
- bp->b_state &= ~XFS_BSTATE_DISPOSE;
- atomic_inc(&bp->b_hold);
- }
- spin_unlock(&bp->b_lock);
- spin_unlock(&pag->pag_buf_lock);
- } else {
- /*
- * most of the time buffers will already be removed from
- * the LRU, so optimise that case by checking for the
- * XFS_BSTATE_DISPOSE flag indicating the last list the
- * buffer was on was the disposal list
- */
- if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
- list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
- } else {
- ASSERT(list_empty(&bp->b_lru));
- }
- spin_unlock(&bp->b_lock);
- ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
- rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
- spin_unlock(&pag->pag_buf_lock);
- xfs_perag_put(pag);
- xfs_buf_free(bp);
+ release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock);
+ spin_lock(&bp->b_lock);
+ if (!release) {
+ /*
+ * Drop the in-flight state if the buffer is already on the LRU
+ * and it holds the only reference. This is racy because we
+ * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT
+ * ensures the decrement occurs only once per-buf.
+ */
+ if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru))
+ xfs_buf_ioacct_dec(bp);
+ goto out_unlock;
+ }
+
+ /* the last reference has been dropped ... */
+ xfs_buf_ioacct_dec(bp);
+ if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
+ /*
+ * If the buffer is added to the LRU take a new reference to the
+ * buffer for the LRU and clear the (now stale) dispose list
+ * state flag
+ */
+ if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
+ bp->b_state &= ~XFS_BSTATE_DISPOSE;
+ atomic_inc(&bp->b_hold);
+ }
+ spin_unlock(&pag->pag_buf_lock);
+ } else {
+ /*
+ * most of the time buffers will already be removed from the
+ * LRU, so optimise that case by checking for the
+ * XFS_BSTATE_DISPOSE flag indicating the last list the buffer
+ * was on was the disposal list
+ */
+ if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
+ list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
+ } else {
+ ASSERT(list_empty(&bp->b_lru));
}
+
+ ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
+ rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
+ spin_unlock(&pag->pag_buf_lock);
+ xfs_perag_put(pag);
+ freebuf = true;
}
+
+ out_unlock:
+ spin_unlock(&bp->b_lock);
+
+ if (freebuf)
+ xfs_buf_free(bp);
}
int locked;
locked = down_trylock(&bp->b_sema) == 0;
- if (locked)
+ if (locked) {
XB_SET_OWNER(bp);
-
- trace_xfs_buf_trylock(bp, _RET_IP_);
+ trace_xfs_buf_trylock(bp, _RET_IP_);
+ } else {
+ trace_xfs_buf_trylock_fail(bp, _RET_IP_);
+ }
return locked;
}
int map,
int *buf_offset,
int *count,
- int rw)
+ int op,
+ int op_flags)
{
int page_index;
int total_nr_pages = bp->b_page_count;
next_chunk:
atomic_inc(&bp->b_io_remaining);
- nr_pages = BIO_MAX_SECTORS >> (PAGE_SHIFT - BBSHIFT);
- if (nr_pages > total_nr_pages)
- nr_pages = total_nr_pages;
+ nr_pages = min(total_nr_pages, BIO_MAX_PAGES);
bio = bio_alloc(GFP_NOIO, nr_pages);
bio->bi_bdev = bp->b_target->bt_bdev;
bio->bi_iter.bi_sector = sector;
bio->bi_end_io = xfs_buf_bio_end_io;
bio->bi_private = bp;
-
+ bio_set_op_attrs(bio, op, op_flags);
for (; size && nr_pages; nr_pages--, page_index++) {
int rbytes, nbytes = PAGE_SIZE - offset;
flush_kernel_vmap_range(bp->b_addr,
xfs_buf_vmap_len(bp));
}
- submit_bio(rw, bio);
+ submit_bio(bio);
if (size)
goto next_chunk;
} else {
struct xfs_buf *bp)
{
struct blk_plug plug;
- int rw;
+ int op;
+ int op_flags = 0;
int offset;
int size;
int i;
bp->b_ioend_wq = bp->b_target->bt_mount->m_buf_workqueue;
if (bp->b_flags & XBF_WRITE) {
+ op = REQ_OP_WRITE;
if (bp->b_flags & XBF_SYNCIO)
- rw = WRITE_SYNC;
- else
- rw = WRITE;
+ op_flags = WRITE_SYNC;
if (bp->b_flags & XBF_FUA)
- rw |= REQ_FUA;
+ op_flags |= REQ_FUA;
if (bp->b_flags & XBF_FLUSH)
- rw |= REQ_FLUSH;
+ op_flags |= REQ_PREFLUSH;
/*
* Run the write verifier callback function if it exists. If
}
}
} else if (bp->b_flags & XBF_READ_AHEAD) {
- rw = READA;
+ op = REQ_OP_READ;
+ op_flags = REQ_RAHEAD;
} else {
- rw = READ;
+ op = REQ_OP_READ;
}
/* we only use the buffer cache for meta-data */
- rw |= REQ_META;
+ op_flags |= REQ_META;
/*
* Walk all the vectors issuing IO on them. Set up the initial offset
size = BBTOB(bp->b_io_length);
blk_start_plug(&plug);
for (i = 0; i < bp->b_map_count; i++) {
- xfs_buf_ioapply_map(bp, i, &offset, &size, rw);
+ xfs_buf_ioapply_map(bp, i, &offset, &size, op, op_flags);
if (bp->b_error)
break;
if (size <= 0)
* xfs_buf_ioend too early.
*/
atomic_set(&bp->b_io_remaining, 1);
+ xfs_buf_ioacct_inc(bp);
_xfs_buf_ioapply(bp);
/*
int loop = 0;
/*
- * We need to flush the buffer workqueue to ensure that all IO
- * completion processing is 100% done. Just waiting on buffer locks is
- * not sufficient for async IO as the reference count held over IO is
- * not released until after the buffer lock is dropped. Hence we need to
- * ensure here that all reference counts have been dropped before we
- * start walking the LRU list.
+ * First wait on the buftarg I/O count for all in-flight buffers to be
+ * released. This is critical as new buffers do not make the LRU until
+ * they are released.
+ *
+ * Next, flush the buffer workqueue to ensure all completion processing
+ * has finished. Just waiting on buffer locks is not sufficient for
+ * async IO as the reference count held over IO is not released until
+ * after the buffer lock is dropped. Hence we need to ensure here that
+ * all reference counts have been dropped before we start walking the
+ * LRU list.
*/
+ while (percpu_counter_sum(&btp->bt_io_count))
+ delay(100);
drain_workqueue(btp->bt_mount->m_buf_workqueue);
/* loop until there is nothing left on the lru list. */
struct xfs_buftarg *btp)
{
unregister_shrinker(&btp->bt_shrinker);
+ ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0);
+ percpu_counter_destroy(&btp->bt_io_count);
list_lru_destroy(&btp->bt_lru);
if (mp->m_flags & XFS_MOUNT_BARRIER)
if (list_lru_init(&btp->bt_lru))
goto error;
+ if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL))
+ goto error;
+
btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count;
btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
btp->bt_shrinker.seeks = DEFAULT_SEEKS;
return 0;
}
+ /*
+ * submit buffers for write.
+ *
+ * When we have a large buffer list, we do not want to hold all the buffers
+ * locked while we block on the request queue waiting for IO dispatch. To avoid
+ * this problem, we lock and submit buffers in groups of 50, thereby minimising
+ * the lock hold times for lists which may contain thousands of objects.
+ *
+ * To do this, we sort the buffer list before we walk the list to lock and
+ * submit buffers, and we plug and unplug around each group of buffers we
+ * submit.
+ */
static int
- __xfs_buf_delwri_submit(
+ xfs_buf_delwri_submit_buffers(
struct list_head *buffer_list,
- struct list_head *io_list,
- bool wait)
+ struct list_head *wait_list)
{
- struct blk_plug plug;
struct xfs_buf *bp, *n;
+ LIST_HEAD (submit_list);
int pinned = 0;
+ struct blk_plug plug;
+ list_sort(NULL, buffer_list, xfs_buf_cmp);
+
+ blk_start_plug(&plug);
list_for_each_entry_safe(bp, n, buffer_list, b_list) {
- if (!wait) {
+ if (!wait_list) {
if (xfs_buf_ispinned(bp)) {
pinned++;
continue;
continue;
}
- list_move_tail(&bp->b_list, io_list);
trace_xfs_buf_delwri_split(bp, _RET_IP_);
- }
-
- list_sort(NULL, io_list, xfs_buf_cmp);
-
- blk_start_plug(&plug);
- list_for_each_entry_safe(bp, n, io_list, b_list) {
- bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
- bp->b_flags |= XBF_WRITE | XBF_ASYNC;
/*
- * we do all Io submission async. This means if we need to wait
- * for IO completion we need to take an extra reference so the
- * buffer is still valid on the other side.
+ * We do all IO submission async. This means if we need
+ * to wait for IO completion we need to take an extra
+ * reference so the buffer is still valid on the other
+ * side. We need to move the buffer onto the io_list
+ * at this point so the caller can still access it.
*/
- if (wait)
+ bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
+ bp->b_flags |= XBF_WRITE | XBF_ASYNC;
+ if (wait_list) {
xfs_buf_hold(bp);
- else
+ list_move_tail(&bp->b_list, wait_list);
+ } else
list_del_init(&bp->b_list);
xfs_buf_submit(bp);
xfs_buf_delwri_submit_nowait(
struct list_head *buffer_list)
{
- LIST_HEAD (io_list);
- return __xfs_buf_delwri_submit(buffer_list, &io_list, false);
+ return xfs_buf_delwri_submit_buffers(buffer_list, NULL);
}
/*
xfs_buf_delwri_submit(
struct list_head *buffer_list)
{
- LIST_HEAD (io_list);
+ LIST_HEAD (wait_list);
int error = 0, error2;
struct xfs_buf *bp;
- __xfs_buf_delwri_submit(buffer_list, &io_list, true);
+ xfs_buf_delwri_submit_buffers(buffer_list, &wait_list);
/* Wait for IO to complete. */
- while (!list_empty(&io_list)) {
- bp = list_first_entry(&io_list, struct xfs_buf, b_list);
+ while (!list_empty(&wait_list)) {
+ bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
list_del_init(&bp->b_list);
#include "xfs_log.h"
#include "xfs_icache.h"
#include "xfs_pnfs.h"
+ #include "xfs_iomap.h"
#include <linux/dcache.h>
#include <linux/falloc.h>
}
/*
- * xfs_iozero clears the specified range supplied via the page cache (except in
- * the DAX case). Writes through the page cache will allocate blocks over holes,
- * though the callers usually map the holes first and avoid them. If a block is
- * not completely zeroed, then it will be read from disk before being partially
- * zeroed.
- *
- * In the DAX case, we can just directly write to the underlying pages. This
- * will not allocate blocks, but will avoid holes and unwritten extents and so
- * not do unnecessary work.
+ * Clear the specified ranges to zero through either the pagecache or DAX.
+ * Holes and unwritten extents will be left as-is as they already are zeroed.
*/
int
- xfs_iozero(
- struct xfs_inode *ip, /* inode */
- loff_t pos, /* offset in file */
- size_t count) /* size of data to zero */
+ xfs_zero_range(
+ struct xfs_inode *ip,
+ xfs_off_t pos,
+ xfs_off_t count,
+ bool *did_zero)
{
- struct page *page;
- struct address_space *mapping;
- int status = 0;
-
-
- mapping = VFS_I(ip)->i_mapping;
- do {
- unsigned offset, bytes;
- void *fsdata;
-
- offset = (pos & (PAGE_SIZE -1)); /* Within page */
- bytes = PAGE_SIZE - offset;
- if (bytes > count)
- bytes = count;
-
- if (IS_DAX(VFS_I(ip))) {
- status = dax_zero_page_range(VFS_I(ip), pos, bytes,
- xfs_get_blocks_direct);
- if (status)
- break;
- } else {
- status = pagecache_write_begin(NULL, mapping, pos, bytes,
- AOP_FLAG_UNINTERRUPTIBLE,
- &page, &fsdata);
- if (status)
- break;
-
- zero_user(page, offset, bytes);
-
- status = pagecache_write_end(NULL, mapping, pos, bytes,
- bytes, page, fsdata);
- WARN_ON(status <= 0); /* can't return less than zero! */
- status = 0;
- }
- pos += bytes;
- count -= bytes;
- } while (count);
-
- return status;
+ return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops);
}
int
}
STATIC ssize_t
- xfs_file_read_iter(
+ xfs_file_dio_aio_read(
struct kiocb *iocb,
struct iov_iter *to)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
+ struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
- struct xfs_mount *mp = ip->i_mount;
- size_t size = iov_iter_count(to);
+ loff_t isize = i_size_read(inode);
+ size_t count = iov_iter_count(to);
+ struct iov_iter data;
+ struct xfs_buftarg *target;
ssize_t ret = 0;
- int ioflags = 0;
- xfs_fsize_t n;
- loff_t pos = iocb->ki_pos;
- XFS_STATS_INC(mp, xs_read_calls);
-
- if (unlikely(iocb->ki_flags & IOCB_DIRECT))
- ioflags |= XFS_IO_ISDIRECT;
- if (file->f_mode & FMODE_NOCMTIME)
- ioflags |= XFS_IO_INVIS;
-
- if ((ioflags & XFS_IO_ISDIRECT) && !IS_DAX(inode)) {
- xfs_buftarg_t *target =
- XFS_IS_REALTIME_INODE(ip) ?
- mp->m_rtdev_targp : mp->m_ddev_targp;
- /* DIO must be aligned to device logical sector size */
- if ((pos | size) & target->bt_logical_sectormask) {
- if (pos == i_size_read(inode))
- return 0;
- return -EINVAL;
- }
- }
+ trace_xfs_file_direct_read(ip, count, iocb->ki_pos);
- n = mp->m_super->s_maxbytes - pos;
- if (n <= 0 || size == 0)
- return 0;
+ if (!count)
+ return 0; /* skip atime */
- if (n < size)
- size = n;
+ if (XFS_IS_REALTIME_INODE(ip))
+ target = ip->i_mount->m_rtdev_targp;
+ else
+ target = ip->i_mount->m_ddev_targp;
- if (XFS_FORCED_SHUTDOWN(mp))
- return -EIO;
+ /* DIO must be aligned to device logical sector size */
+ if ((iocb->ki_pos | count) & target->bt_logical_sectormask) {
+ if (iocb->ki_pos == isize)
+ return 0;
+ return -EINVAL;
+ }
/*
* Locking is a bit tricky here. If we take an exclusive lock for direct
* serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
- if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
+ if (mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
* flush and reduce the chances of repeated iolock cycles going
* forward.
*/
- if (inode->i_mapping->nrpages) {
- ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+ if (mapping->nrpages) {
+ ret = filemap_write_and_wait(mapping);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
* we fail to invalidate a page, but this should never
* happen on XFS. Warn if it does fail.
*/
- ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
+ ret = invalidate_inode_pages2(mapping);
WARN_ON_ONCE(ret);
ret = 0;
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
- trace_xfs_file_read(ip, size, pos, ioflags);
+ data = *to;
+ ret = __blockdev_direct_IO(iocb, inode, target->bt_bdev, &data,
+ xfs_get_blocks_direct, NULL, NULL, 0);
+ if (ret > 0) {
+ iocb->ki_pos += ret;
+ iov_iter_advance(to, ret);
+ }
+ xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+ file_accessed(iocb->ki_filp);
+ return ret;
+ }
+
+ static noinline ssize_t
+ xfs_file_dax_read(
+ struct kiocb *iocb,
+ struct iov_iter *to)
+ {
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
+ struct inode *inode = mapping->host;
+ struct xfs_inode *ip = XFS_I(inode);
+ struct iov_iter data = *to;
+ size_t count = iov_iter_count(to);
+ ssize_t ret = 0;
+
+ trace_xfs_file_dax_read(ip, count, iocb->ki_pos);
+
+ if (!count)
+ return 0; /* skip atime */
+
+ xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+ ret = dax_do_io(iocb, inode, &data, xfs_get_blocks_direct, NULL, 0);
+ if (ret > 0) {
+ iocb->ki_pos += ret;
+ iov_iter_advance(to, ret);
+ }
+ xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+
+ file_accessed(iocb->ki_filp);
+ return ret;
+ }
+
+ STATIC ssize_t
+ xfs_file_buffered_aio_read(
+ struct kiocb *iocb,
+ struct iov_iter *to)
+ {
+ struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp));
+ ssize_t ret;
+
+ trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos);
+
+ xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
ret = generic_file_read_iter(iocb, to);
+ xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+
+ return ret;
+ }
+
+ STATIC ssize_t
+ xfs_file_read_iter(
+ struct kiocb *iocb,
+ struct iov_iter *to)
+ {
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct xfs_mount *mp = XFS_I(inode)->i_mount;
+ ssize_t ret = 0;
+
+ XFS_STATS_INC(mp, xs_read_calls);
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
+
+ if (IS_DAX(inode))
+ ret = xfs_file_dax_read(iocb, to);
+ else if (iocb->ki_flags & IOCB_DIRECT)
+ ret = xfs_file_dio_aio_read(iocb, to);
+ else
+ ret = xfs_file_buffered_aio_read(iocb, to);
+
if (ret > 0)
XFS_STATS_ADD(mp, xs_read_bytes, ret);
-
- xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
unsigned int flags)
{
struct xfs_inode *ip = XFS_I(infilp->f_mapping->host);
- int ioflags = 0;
ssize_t ret;
XFS_STATS_INC(ip->i_mount, xs_read_calls);
- if (infilp->f_mode & FMODE_NOCMTIME)
- ioflags |= XFS_IO_INVIS;
-
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
- trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
+ trace_xfs_file_splice_read(ip, count, *ppos);
/*
* DAX inodes cannot ues the page cache for splice, so we have to push
return ret;
}
- /*
- * This routine is called to handle zeroing any space in the last block of the
- * file that is beyond the EOF. We do this since the size is being increased
- * without writing anything to that block and we don't want to read the
- * garbage on the disk.
- */
- STATIC int /* error (positive) */
- xfs_zero_last_block(
- struct xfs_inode *ip,
- xfs_fsize_t offset,
- xfs_fsize_t isize,
- bool *did_zeroing)
- {
- struct xfs_mount *mp = ip->i_mount;
- xfs_fileoff_t last_fsb = XFS_B_TO_FSBT(mp, isize);
- int zero_offset = XFS_B_FSB_OFFSET(mp, isize);
- int zero_len;
- int nimaps = 1;
- int error = 0;
- struct xfs_bmbt_irec imap;
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- if (error)
- return error;
-
- ASSERT(nimaps > 0);
-
- /*
- * If the block underlying isize is just a hole, then there
- * is nothing to zero.
- */
- if (imap.br_startblock == HOLESTARTBLOCK)
- return 0;
-
- zero_len = mp->m_sb.sb_blocksize - zero_offset;
- if (isize + zero_len > offset)
- zero_len = offset - isize;
- *did_zeroing = true;
- return xfs_iozero(ip, isize, zero_len);
- }
-
/*
* Zero any on disk space between the current EOF and the new, larger EOF.
*
xfs_fsize_t isize, /* current inode size */
bool *did_zeroing)
{
- struct xfs_mount *mp = ip->i_mount;
- xfs_fileoff_t start_zero_fsb;
- xfs_fileoff_t end_zero_fsb;
- xfs_fileoff_t zero_count_fsb;
- xfs_fileoff_t last_fsb;
- xfs_fileoff_t zero_off;
- xfs_fsize_t zero_len;
- int nimaps;
- int error = 0;
- struct xfs_bmbt_irec imap;
-
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(offset > isize);
trace_xfs_zero_eof(ip, isize, offset - isize);
-
- /*
- * First handle zeroing the block on which isize resides.
- *
- * We only zero a part of that block so it is handled specially.
- */
- if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
- error = xfs_zero_last_block(ip, offset, isize, did_zeroing);
- if (error)
- return error;
- }
-
- /*
- * Calculate the range between the new size and the old where blocks
- * needing to be zeroed may exist.
- *
- * To get the block where the last byte in the file currently resides,
- * we need to subtract one from the size and truncate back to a block
- * boundary. We subtract 1 in case the size is exactly on a block
- * boundary.
- */
- last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
- start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
- end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
- ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
- if (last_fsb == end_zero_fsb) {
- /*
- * The size was only incremented on its last block.
- * We took care of that above, so just return.
- */
- return 0;
- }
-
- ASSERT(start_zero_fsb <= end_zero_fsb);
- while (start_zero_fsb <= end_zero_fsb) {
- nimaps = 1;
- zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb,
- &imap, &nimaps, 0);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- if (error)
- return error;
-
- ASSERT(nimaps > 0);
-
- if (imap.br_state == XFS_EXT_UNWRITTEN ||
- imap.br_startblock == HOLESTARTBLOCK) {
- start_zero_fsb = imap.br_startoff + imap.br_blockcount;
- ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
- continue;
- }
-
- /*
- * There are blocks we need to zero.
- */
- zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
- zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
-
- if ((zero_off + zero_len) > offset)
- zero_len = offset - zero_off;
-
- error = xfs_iozero(ip, zero_off, zero_len);
- if (error)
- return error;
-
- *did_zeroing = true;
- start_zero_fsb = imap.br_startoff + imap.br_blockcount;
- ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
- }
-
- return 0;
+ return xfs_zero_range(ip, isize, offset - isize, did_zeroing);
}
/*
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
- if (!IS_DAX(inode) &&
- ((iocb->ki_pos | count) & target->bt_logical_sectormask))
+ if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
/* "unaligned" here means not aligned to a filesystem block */
end = iocb->ki_pos + count - 1;
/*
- * See xfs_file_read_iter() for why we do a full-file flush here.
+ * See xfs_file_dio_aio_read() for why we do a full-file flush here.
*/
if (mapping->nrpages) {
ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
iolock = XFS_IOLOCK_SHARED;
}
- trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
+ trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
data = *from;
- ret = mapping->a_ops->direct_IO(iocb, &data);
+ ret = __blockdev_direct_IO(iocb, inode, target->bt_bdev, &data,
+ xfs_get_blocks_direct, xfs_end_io_direct_write,
+ NULL, DIO_ASYNC_EXTEND);
/* see generic_file_direct_write() for why this is necessary */
if (mapping->nrpages) {
xfs_rw_iunlock(ip, iolock);
/*
- * No fallback to buffered IO on errors for XFS. DAX can result in
- * partial writes, but direct IO will either complete fully or fail.
+ * No fallback to buffered IO on errors for XFS, direct IO will either
+ * complete fully or fail.
*/
- ASSERT(ret < 0 || ret == count || IS_DAX(VFS_I(ip)));
+ ASSERT(ret < 0 || ret == count);
+ return ret;
+ }
+
+ static noinline ssize_t
+ xfs_file_dax_write(
+ struct kiocb *iocb,
+ struct iov_iter *from)
+ {
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
+ struct inode *inode = mapping->host;
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+ ssize_t ret = 0;
+ int unaligned_io = 0;
+ int iolock;
+ struct iov_iter data;
+
+ /* "unaligned" here means not aligned to a filesystem block */
+ if ((iocb->ki_pos & mp->m_blockmask) ||
+ ((iocb->ki_pos + iov_iter_count(from)) & mp->m_blockmask)) {
+ unaligned_io = 1;
+ iolock = XFS_IOLOCK_EXCL;
+ } else if (mapping->nrpages) {
+ iolock = XFS_IOLOCK_EXCL;
+ } else {
+ iolock = XFS_IOLOCK_SHARED;
+ }
+ xfs_rw_ilock(ip, iolock);
+
+ ret = xfs_file_aio_write_checks(iocb, from, &iolock);
+ if (ret)
+ goto out;
+
+ /*
+ * Yes, even DAX files can have page cache attached to them: A zeroed
+ * page is inserted into the pagecache when we have to serve a write
+ * fault on a hole. It should never be dirtied and can simply be
+ * dropped from the pagecache once we get real data for the page.
+ */
+ if (mapping->nrpages) {
+ ret = invalidate_inode_pages2(mapping);
+ WARN_ON_ONCE(ret);
+ }
+
+ if (iolock == XFS_IOLOCK_EXCL && !unaligned_io) {
+ xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+ iolock = XFS_IOLOCK_SHARED;
+ }
+
+ trace_xfs_file_dax_write(ip, iov_iter_count(from), iocb->ki_pos);
+
+ data = *from;
+ ret = dax_do_io(iocb, inode, &data, xfs_get_blocks_direct,
+ xfs_end_io_direct_write, 0);
+ if (ret > 0) {
+ iocb->ki_pos += ret;
+ iov_iter_advance(from, ret);
+ }
+ out:
+ xfs_rw_iunlock(ip, iolock);
return ret;
}
current->backing_dev_info = inode_to_bdi(inode);
write_retry:
- trace_xfs_file_buffered_write(ip, iov_iter_count(from),
- iocb->ki_pos, 0);
- ret = generic_perform_write(file, from, iocb->ki_pos);
+ trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos);
+ ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops);
if (likely(ret >= 0))
iocb->ki_pos += ret;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
- if ((iocb->ki_flags & IOCB_DIRECT) || IS_DAX(inode))
+ if (IS_DAX(inode))
+ ret = xfs_file_dax_write(iocb, from);
+ else if (iocb->ki_flags & IOCB_DIRECT)
ret = xfs_file_dio_aio_write(iocb, from);
else
ret = xfs_file_buffered_aio_write(iocb, from);
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
+ ret = dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
} else {
- ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
+ ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
ret = block_page_mkwrite_return(ret);
}
* changes to xfs_get_blocks_direct() to map unwritten extent
* ioend for conversion on read-only mappings.
*/
- ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
+ ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
} else
ret = filemap_fault(vma, vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
+ ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (flags & FAULT_FLAG_WRITE)