Merge branch 'xfs-buf-iosubmit' into for-next
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d8b77b5..c2aaa58 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1122,14 +1122,6 @@
if (endoff > XFS_ISIZE(ip))
endoff = XFS_ISIZE(ip);
- bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
- mp->m_rtdev_targp : mp->m_ddev_targp,
- BTOBB(mp->m_sb.sb_blocksize), 0);
- if (!bp)
- return -ENOMEM;
-
- xfs_buf_unlock(bp);
-
for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
uint lock_mode;
@@ -1152,42 +1144,24 @@
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
if (imap.br_state == XFS_EXT_UNWRITTEN)
continue;
- XFS_BUF_UNDONE(bp);
- XFS_BUF_UNWRITE(bp);
- XFS_BUF_READ(bp);
- XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
- if (XFS_FORCED_SHUTDOWN(mp)) {
- error = -EIO;
- break;
- }
- xfs_buf_iorequest(bp);
- error = xfs_buf_iowait(bp);
- if (error) {
- xfs_buf_ioerror_alert(bp,
- "xfs_zero_remaining_bytes(read)");
- break;
- }
+ error = xfs_buf_read_uncached(XFS_IS_REALTIME_INODE(ip) ?
+ mp->m_rtdev_targp : mp->m_ddev_targp,
+ xfs_fsb_to_db(ip, imap.br_startblock),
+ BTOBB(mp->m_sb.sb_blocksize),
+ 0, &bp, NULL);
+ if (error)
+ return error;
+
memset(bp->b_addr +
- (offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
- 0, lastoffset - offset + 1);
- XFS_BUF_UNDONE(bp);
- XFS_BUF_UNREAD(bp);
- XFS_BUF_WRITE(bp);
+ (offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
+ 0, lastoffset - offset + 1);
- if (XFS_FORCED_SHUTDOWN(mp)) {
- error = -EIO;
- break;
- }
- xfs_buf_iorequest(bp);
- error = xfs_buf_iowait(bp);
- if (error) {
- xfs_buf_ioerror_alert(bp,
- "xfs_zero_remaining_bytes(write)");
- break;
- }
+ error = xfs_bwrite(bp);
+ xfs_buf_relse(bp);
+ if (error)
+ return error;
}
- xfs_buf_free(bp);
return error;
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index ec65050..017b6af 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -623,10 +623,11 @@
bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
- xfs_buf_iorequest(bp);
- if (flags & XBF_ASYNC)
+ if (flags & XBF_ASYNC) {
+ xfs_buf_submit(bp);
return 0;
- return xfs_buf_iowait(bp);
+ }
+ return xfs_buf_submit_wait(bp);
}
xfs_buf_t *
@@ -687,34 +688,39 @@
* Read an uncached buffer from disk. Allocates and returns a locked
* buffer containing the disk contents or nothing.
*/
-struct xfs_buf *
+int
xfs_buf_read_uncached(
struct xfs_buftarg *target,
xfs_daddr_t daddr,
size_t numblks,
int flags,
+ struct xfs_buf **bpp,
const struct xfs_buf_ops *ops)
{
struct xfs_buf *bp;
+ *bpp = NULL;
+
bp = xfs_buf_get_uncached(target, numblks, flags);
if (!bp)
- return NULL;
+ return -ENOMEM;
/* set up the buffer for a read IO */
ASSERT(bp->b_map_count == 1);
- bp->b_bn = daddr;
+ bp->b_bn = XFS_BUF_DADDR_NULL; /* always null for uncached buffers */
bp->b_maps[0].bm_bn = daddr;
bp->b_flags |= XBF_READ;
bp->b_ops = ops;
- if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
+ xfs_buf_submit_wait(bp);
+ if (bp->b_error) {
+ int error = bp->b_error;
xfs_buf_relse(bp);
- return NULL;
+ return error;
}
- xfs_buf_iorequest(bp);
- xfs_buf_iowait(bp);
- return bp;
+
+ *bpp = bp;
+ return 0;
}
/*
@@ -998,53 +1004,56 @@
* Buffer Utility Routines
*/
-STATIC void
-xfs_buf_iodone_work(
- struct work_struct *work)
+void
+xfs_buf_ioend(
+ struct xfs_buf *bp)
{
- struct xfs_buf *bp =
- container_of(work, xfs_buf_t, b_iodone_work);
- bool read = !!(bp->b_flags & XBF_READ);
+ bool read = bp->b_flags & XBF_READ;
+
+ trace_xfs_buf_iodone(bp, _RET_IP_);
bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
- /* only validate buffers that were read without errors */
- if (read && bp->b_ops && !bp->b_error && (bp->b_flags & XBF_DONE))
+ /*
+ * Pull in IO completion errors now. We are guaranteed to be running
+ * single threaded, so we don't need the lock to read b_io_error.
+ */
+ if (!bp->b_error && bp->b_io_error)
+ xfs_buf_ioerror(bp, bp->b_io_error);
+
+ /* Only validate buffers that were read without errors */
+ if (read && !bp->b_error && bp->b_ops) {
+ ASSERT(!bp->b_iodone);
bp->b_ops->verify_read(bp);
+ }
+
+ if (!bp->b_error)
+ bp->b_flags |= XBF_DONE;
if (bp->b_iodone)
(*(bp->b_iodone))(bp);
else if (bp->b_flags & XBF_ASYNC)
xfs_buf_relse(bp);
- else {
- ASSERT(read && bp->b_ops);
+ else
complete(&bp->b_iowait);
- }
+}
+
+static void
+xfs_buf_ioend_work(
+ struct work_struct *work)
+{
+ struct xfs_buf *bp =
+ container_of(work, xfs_buf_t, b_iodone_work);
+
+ xfs_buf_ioend(bp);
}
void
-xfs_buf_ioend(
- struct xfs_buf *bp,
- int schedule)
+xfs_buf_ioend_async(
+ struct xfs_buf *bp)
{
- bool read = !!(bp->b_flags & XBF_READ);
-
- trace_xfs_buf_iodone(bp, _RET_IP_);
-
- if (bp->b_error == 0)
- bp->b_flags |= XBF_DONE;
-
- if (bp->b_iodone || (read && bp->b_ops) || (bp->b_flags & XBF_ASYNC)) {
- if (schedule) {
- INIT_WORK(&bp->b_iodone_work, xfs_buf_iodone_work);
- queue_work(xfslogd_workqueue, &bp->b_iodone_work);
- } else {
- xfs_buf_iodone_work(&bp->b_iodone_work);
- }
- } else {
- bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
- complete(&bp->b_iowait);
- }
+ INIT_WORK(&bp->b_iodone_work, xfs_buf_ioend_work);
+ queue_work(xfslogd_workqueue, &bp->b_iodone_work);
}
void
@@ -1067,96 +1076,6 @@
(__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
}
-/*
- * Called when we want to stop a buffer from getting written or read.
- * We attach the EIO error, muck with its flags, and call xfs_buf_ioend
- * so that the proper iodone callbacks get called.
- */
-STATIC int
-xfs_bioerror(
- xfs_buf_t *bp)
-{
-#ifdef XFSERRORDEBUG
- ASSERT(XFS_BUF_ISREAD(bp) || bp->b_iodone);
-#endif
-
- /*
- * No need to wait until the buffer is unpinned, we aren't flushing it.
- */
- xfs_buf_ioerror(bp, -EIO);
-
- /*
- * We're calling xfs_buf_ioend, so delete XBF_DONE flag.
- */
- XFS_BUF_UNREAD(bp);
- XFS_BUF_UNDONE(bp);
- xfs_buf_stale(bp);
-
- xfs_buf_ioend(bp, 0);
-
- return -EIO;
-}
-
-/*
- * Same as xfs_bioerror, except that we are releasing the buffer
- * here ourselves, and avoiding the xfs_buf_ioend call.
- * This is meant for userdata errors; metadata bufs come with
- * iodone functions attached, so that we can track down errors.
- */
-int
-xfs_bioerror_relse(
- struct xfs_buf *bp)
-{
- int64_t fl = bp->b_flags;
- /*
- * No need to wait until the buffer is unpinned.
- * We aren't flushing it.
- *
- * chunkhold expects B_DONE to be set, whether
- * we actually finish the I/O or not. We don't want to
- * change that interface.
- */
- XFS_BUF_UNREAD(bp);
- XFS_BUF_DONE(bp);
- xfs_buf_stale(bp);
- bp->b_iodone = NULL;
- if (!(fl & XBF_ASYNC)) {
- /*
- * Mark b_error and B_ERROR _both_.
- * Lot's of chunkcache code assumes that.
- * There's no reason to mark error for
- * ASYNC buffers.
- */
- xfs_buf_ioerror(bp, -EIO);
- complete(&bp->b_iowait);
- } else {
- xfs_buf_relse(bp);
- }
-
- return -EIO;
-}
-
-STATIC int
-xfs_bdstrat_cb(
- struct xfs_buf *bp)
-{
- if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
- trace_xfs_bdstrat_shut(bp, _RET_IP_);
- /*
- * Metadata write that didn't get logged but
- * written delayed anyway. These aren't associated
- * with a transaction, and can be ignored.
- */
- if (!bp->b_iodone && !XFS_BUF_ISREAD(bp))
- return xfs_bioerror_relse(bp);
- else
- return xfs_bioerror(bp);
- }
-
- xfs_buf_iorequest(bp);
- return 0;
-}
-
int
xfs_bwrite(
struct xfs_buf *bp)
@@ -1166,11 +1085,10 @@
ASSERT(xfs_buf_islocked(bp));
bp->b_flags |= XBF_WRITE;
- bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
+ bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
+ XBF_WRITE_FAIL | XBF_DONE);
- xfs_bdstrat_cb(bp);
-
- error = xfs_buf_iowait(bp);
+ error = xfs_buf_submit_wait(bp);
if (error) {
xfs_force_shutdown(bp->b_target->bt_mount,
SHUTDOWN_META_IO_ERROR);
@@ -1179,15 +1097,6 @@
}
STATIC void
-_xfs_buf_ioend(
- xfs_buf_t *bp,
- int schedule)
-{
- if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
- xfs_buf_ioend(bp, schedule);
-}
-
-STATIC void
xfs_buf_bio_end_io(
struct bio *bio,
int error)
@@ -1198,13 +1107,18 @@
* don't overwrite existing errors - otherwise we can lose errors on
* buffers that require multiple bios to complete.
*/
- if (!bp->b_error)
- xfs_buf_ioerror(bp, error);
+ if (error) {
+ spin_lock(&bp->b_lock);
+ if (!bp->b_io_error)
+ bp->b_io_error = error;
+ spin_unlock(&bp->b_lock);
+ }
if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
- _xfs_buf_ioend(bp, 1);
+ if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+ xfs_buf_ioend_async(bp);
bio_put(bio);
}
@@ -1283,7 +1197,7 @@
} else {
/*
* This is guaranteed not to be the last io reference count
- * because the caller (xfs_buf_iorequest) holds a count itself.
+ * because the caller (xfs_buf_submit) holds a count itself.
*/
atomic_dec(&bp->b_io_remaining);
xfs_buf_ioerror(bp, -EIO);
@@ -1373,53 +1287,131 @@
blk_finish_plug(&plug);
}
+/*
+ * Asynchronous IO submission path. This transfers the buffer lock ownership and
+ * the current reference to the IO. It is not safe to reference the buffer after
+ * a call to this function unless the caller holds an additional reference
+ * itself.
+ */
void
-xfs_buf_iorequest(
- xfs_buf_t *bp)
+xfs_buf_submit(
+ struct xfs_buf *bp)
{
- trace_xfs_buf_iorequest(bp, _RET_IP_);
+ trace_xfs_buf_submit(bp, _RET_IP_);
ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
+ ASSERT(bp->b_flags & XBF_ASYNC);
+
+ /* on shutdown we stale and complete the buffer immediately */
+ if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+ xfs_buf_ioerror(bp, -EIO);
+ bp->b_flags &= ~XBF_DONE;
+ xfs_buf_stale(bp);
+ xfs_buf_ioend(bp);
+ return;
+ }
if (bp->b_flags & XBF_WRITE)
xfs_buf_wait_unpin(bp);
+
+ /* clear the internal error state to avoid spurious errors */
+ bp->b_io_error = 0;
+
+ /*
+ * The caller's reference is released during I/O completion.
+ * This occurs some time after the last b_io_remaining reference is
+ * released, so after we drop our Io reference we have to have some
+ * other reference to ensure the buffer doesn't go away from underneath
+ * us. Take a direct reference to ensure we have safe access to the
+ * buffer until we are finished with it.
+ */
xfs_buf_hold(bp);
/*
- * Set the count to 1 initially, this will stop an I/O
- * completion callout which happens before we have started
- * all the I/O from calling xfs_buf_ioend too early.
+ * Set the count to 1 initially, this will stop an I/O completion
+ * callout which happens before we have started all the I/O from calling
+ * xfs_buf_ioend too early.
*/
atomic_set(&bp->b_io_remaining, 1);
_xfs_buf_ioapply(bp);
+
/*
- * If _xfs_buf_ioapply failed, we'll get back here with
- * only the reference we took above. _xfs_buf_ioend will
- * drop it to zero, so we'd better not queue it for later,
- * or we'll free it before it's done.
+ * If _xfs_buf_ioapply failed, we can get back here with only the IO
+ * reference we took above. If we drop it to zero, run completion so
+ * that we don't return to the caller with completion still pending.
*/
- _xfs_buf_ioend(bp, bp->b_error ? 0 : 1);
+ if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
+ if (bp->b_error)
+ xfs_buf_ioend(bp);
+ else
+ xfs_buf_ioend_async(bp);
+ }
xfs_buf_rele(bp);
+ /* Note: it is not safe to reference bp now we've dropped our ref */
}
/*
- * Waits for I/O to complete on the buffer supplied. It returns immediately if
- * no I/O is pending or there is already a pending error on the buffer, in which
- * case nothing will ever complete. It returns the I/O error code, if any, or
- * 0 if there was no error.
+ * Synchronous buffer IO submission path, read or write.
*/
int
-xfs_buf_iowait(
- xfs_buf_t *bp)
+xfs_buf_submit_wait(
+ struct xfs_buf *bp)
{
+ int error;
+
+ trace_xfs_buf_submit_wait(bp, _RET_IP_);
+
+ ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC)));
+
+ if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+ xfs_buf_ioerror(bp, -EIO);
+ xfs_buf_stale(bp);
+ bp->b_flags &= ~XBF_DONE;
+ return -EIO;
+ }
+
+ if (bp->b_flags & XBF_WRITE)
+ xfs_buf_wait_unpin(bp);
+
+ /* clear the internal error state to avoid spurious errors */
+ bp->b_io_error = 0;
+
+ /*
+ * For synchronous IO, the IO does not inherit the submitters reference
+ * count, nor the buffer lock. Hence we cannot release the reference we
+ * are about to take until we've waited for all IO completion to occur,
+ * including any xfs_buf_ioend_async() work that may be pending.
+ */
+ xfs_buf_hold(bp);
+
+ /*
+ * Set the count to 1 initially, this will stop an I/O completion
+ * callout which happens before we have started all the I/O from calling
+ * xfs_buf_ioend too early.
+ */
+ atomic_set(&bp->b_io_remaining, 1);
+ _xfs_buf_ioapply(bp);
+
+ /*
+ * make sure we run completion synchronously if it raced with us and is
+ * already complete.
+ */
+ if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+ xfs_buf_ioend(bp);
+
+ /* wait for completion before gathering the error from the buffer */
trace_xfs_buf_iowait(bp, _RET_IP_);
-
- if (!bp->b_error)
- wait_for_completion(&bp->b_iowait);
-
+ wait_for_completion(&bp->b_iowait);
trace_xfs_buf_iowait_done(bp, _RET_IP_);
- return bp->b_error;
+ error = bp->b_error;
+
+ /*
+ * all done now, we can release the hold that keeps the buffer
+ * referenced for the entire IO.
+ */
+ xfs_buf_rele(bp);
+ return error;
}
xfs_caddr_t
@@ -1813,13 +1805,19 @@
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;
+ bp->b_flags |= XBF_WRITE | XBF_ASYNC;
- if (!wait) {
- bp->b_flags |= 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.
+ */
+ if (wait)
+ xfs_buf_hold(bp);
+ else
list_del_init(&bp->b_list);
- }
- xfs_bdstrat_cb(bp);
+
+ xfs_buf_submit(bp);
}
blk_finish_plug(&plug);
@@ -1866,7 +1864,10 @@
bp = list_first_entry(&io_list, struct xfs_buf, b_list);
list_del_init(&bp->b_list);
- error2 = xfs_buf_iowait(bp);
+
+ /* locking the buffer will wait for async IO completion. */
+ xfs_buf_lock(bp);
+ error2 = bp->b_error;
xfs_buf_relse(bp);
if (!error)
error = error2;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c753183..82002c0 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -158,6 +158,7 @@
struct list_head b_lru; /* lru list */
spinlock_t b_lock; /* internal state lock */
unsigned int b_state; /* internal state flags */
+ int b_io_error; /* internal IO error state */
wait_queue_head_t b_waiters; /* unpin waiters */
struct list_head b_list;
struct xfs_perag *b_pag; /* contains rbtree root */
@@ -268,9 +269,9 @@
struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
int flags);
-struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target,
- xfs_daddr_t daddr, size_t numblks, int flags,
- const struct xfs_buf_ops *ops);
+int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
+ size_t numblks, int flags, struct xfs_buf **bpp,
+ const struct xfs_buf_ops *ops);
void xfs_buf_hold(struct xfs_buf *bp);
/* Releasing Buffers */
@@ -286,18 +287,16 @@
/* Buffer Read and Write Routines */
extern int xfs_bwrite(struct xfs_buf *bp);
-extern void xfs_buf_ioend(xfs_buf_t *, int);
+extern void xfs_buf_ioend(struct xfs_buf *bp);
extern void xfs_buf_ioerror(xfs_buf_t *, int);
extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
-extern void xfs_buf_iorequest(xfs_buf_t *);
-extern int xfs_buf_iowait(xfs_buf_t *);
+extern void xfs_buf_submit(struct xfs_buf *bp);
+extern int xfs_buf_submit_wait(struct xfs_buf *bp);
extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
xfs_buf_rw_t);
#define xfs_buf_zero(bp, off, len) \
xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
-extern int xfs_bioerror_relse(struct xfs_buf *);
-
/* Buffer Utility Routines */
extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 30fa5db..f159695 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -491,7 +491,7 @@
xfs_buf_ioerror(bp, -EIO);
XFS_BUF_UNDONE(bp);
xfs_buf_stale(bp);
- xfs_buf_ioend(bp, 0);
+ xfs_buf_ioend(bp);
}
}
@@ -1081,7 +1081,7 @@
* a way to shut the filesystem down if the writes keep failing.
*
* In practice we'll shut the filesystem down soon as non-transient
- * erorrs tend to affect the whole device and a failing log write
+ * errors tend to affect the whole device and a failing log write
* will make us give up. But we really ought to do better here.
*/
if (XFS_BUF_ISASYNC(bp)) {
@@ -1094,7 +1094,7 @@
if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
bp->b_flags |= XBF_WRITE | XBF_ASYNC |
XBF_DONE | XBF_WRITE_FAIL;
- xfs_buf_iorequest(bp);
+ xfs_buf_submit(bp);
} else {
xfs_buf_relse(bp);
}
@@ -1115,7 +1115,7 @@
xfs_buf_do_callbacks(bp);
bp->b_fspriv = NULL;
bp->b_iodone = NULL;
- xfs_buf_ioend(bp, 0);
+ xfs_buf_ioend(bp);
}
/*
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index f91de1e..c05ac8b 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -172,16 +172,11 @@
if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
return error;
dpct = pct - mp->m_sb.sb_imax_pct;
- bp = xfs_buf_read_uncached(mp->m_ddev_targp,
+ error = xfs_buf_read_uncached(mp->m_ddev_targp,
XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
- XFS_FSS_TO_BB(mp, 1), 0, NULL);
- if (!bp)
- return -EIO;
- if (bp->b_error) {
- error = bp->b_error;
- xfs_buf_relse(bp);
+ XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+ if (error)
return error;
- }
xfs_buf_relse(bp);
new = nb; /* use new as a temporary here */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c92cb48..e5bbc1f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3062,7 +3062,7 @@
XFS_BUF_UNDONE(bp);
xfs_buf_stale(bp);
xfs_buf_ioerror(bp, -EIO);
- xfs_buf_ioend(bp, 0);
+ xfs_buf_ioend(bp);
} else {
xfs_buf_stale(bp);
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ca4fd5b..fe88ef6 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1678,7 +1678,7 @@
if (iclog->ic_state & XLOG_STATE_IOERROR) {
xfs_buf_ioerror(bp, -EIO);
xfs_buf_stale(bp);
- xfs_buf_ioend(bp, 0);
+ xfs_buf_ioend(bp);
/*
* It would seem logical to return EIO here, but we rely on
* the log state machine to propagate I/O errors instead of
@@ -1688,7 +1688,7 @@
return 0;
}
- xfs_buf_iorequest(bp);
+ xfs_buf_submit(bp);
return 0;
}
@@ -3867,18 +3867,17 @@
* This is called from xfs_force_shutdown, when we're forcibly
* shutting down the filesystem, typically because of an IO error.
* Our main objectives here are to make sure that:
- * a. the filesystem gets marked 'SHUTDOWN' for all interested
+ * a. if !logerror, flush the logs to disk. Anything modified
+ * after this is ignored.
+ * b. the filesystem gets marked 'SHUTDOWN' for all interested
* parties to find out, 'atomically'.
- * b. those who're sleeping on log reservations, pinned objects and
+ * c. those who're sleeping on log reservations, pinned objects and
* other resources get woken up, and be told the bad news.
- * c. nothing new gets queued up after (a) and (b) are done.
- * d. if !logerror, flush the iclogs to disk, then seal them off
- * for business.
+ * d. nothing new gets queued up after (b) and (c) are done.
*
- * Note: for delayed logging the !logerror case needs to flush the regions
- * held in memory out to the iclogs before flushing them to disk. This needs
- * to be done before the log is marked as shutdown, otherwise the flush to the
- * iclogs will fail.
+ * Note: for the !logerror case we need to flush the regions held in memory out
+ * to disk first. This needs to be done before the log is marked as shutdown,
+ * otherwise the iclog writes will fail.
*/
int
xfs_log_force_umount(
@@ -3910,16 +3909,16 @@
ASSERT(XLOG_FORCED_SHUTDOWN(log));
return 1;
}
- retval = 0;
/*
- * Flush the in memory commit item list before marking the log as
- * being shut down. We need to do it in this order to ensure all the
- * completed transactions are flushed to disk with the xfs_log_force()
- * call below.
+ * Flush all the completed transactions to disk before marking the log
+ * being shut down. We need to do it in this order to ensure that
+ * completed operations are safely on disk before we shut down, and that
+ * we don't have to issue any buffer IO after the shutdown flags are set
+ * to guarantee this.
*/
if (!logerror)
- xlog_cil_force(log);
+ _xfs_log_force(mp, XFS_LOG_SYNC, NULL);
/*
* mark the filesystem and the as in a shutdown state and wake
@@ -3931,18 +3930,11 @@
XFS_BUF_DONE(mp->m_sb_bp);
/*
- * This flag is sort of redundant because of the mount flag, but
- * it's good to maintain the separation between the log and the rest
- * of XFS.
+ * Mark the log and the iclogs with IO error flags to prevent any
+ * further log IO from being issued or completed.
*/
log->l_flags |= XLOG_IO_ERROR;
-
- /*
- * If we hit a log error, we want to mark all the iclogs IOERROR
- * while we're still holding the loglock.
- */
- if (logerror)
- retval = xlog_state_ioerror(log);
+ retval = xlog_state_ioerror(log);
spin_unlock(&log->l_icloglock);
/*
@@ -3955,19 +3947,6 @@
xlog_grant_head_wake_all(&log->l_reserve_head);
xlog_grant_head_wake_all(&log->l_write_head);
- if (!(log->l_iclog->ic_state & XLOG_STATE_IOERROR)) {
- ASSERT(!logerror);
- /*
- * Force the incore logs to disk before shutting the
- * log down completely.
- */
- _xfs_log_force(mp, XFS_LOG_SYNC, NULL);
-
- spin_lock(&log->l_icloglock);
- retval = xlog_state_ioerror(log);
- spin_unlock(&log->l_icloglock);
- }
-
/*
* Wake up everybody waiting on xfs_log_force. Wake the CIL push first
* as if the log writes were completed. The abort handling in the log
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 79cfe7e..00cd7f3 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -193,12 +193,8 @@
bp->b_io_length = nbblks;
bp->b_error = 0;
- if (XFS_FORCED_SHUTDOWN(log->l_mp))
- return -EIO;
-
- xfs_buf_iorequest(bp);
- error = xfs_buf_iowait(bp);
- if (error)
+ error = xfs_buf_submit_wait(bp);
+ if (error && !XFS_FORCED_SHUTDOWN(log->l_mp))
xfs_buf_ioerror_alert(bp, __func__);
return error;
}
@@ -378,12 +374,14 @@
* We're not going to bother about retrying
* this during recovery. One strike!
*/
- xfs_buf_ioerror_alert(bp, __func__);
- xfs_force_shutdown(bp->b_target->bt_mount,
- SHUTDOWN_META_IO_ERROR);
+ if (!XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+ xfs_buf_ioerror_alert(bp, __func__);
+ xfs_force_shutdown(bp->b_target->bt_mount,
+ SHUTDOWN_META_IO_ERROR);
+ }
}
bp->b_iodone = NULL;
- xfs_buf_ioend(bp, 0);
+ xfs_buf_ioend(bp);
}
/*
@@ -4452,16 +4450,12 @@
XFS_BUF_UNASYNC(bp);
bp->b_ops = &xfs_sb_buf_ops;
- if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
- xfs_buf_relse(bp);
- return -EIO;
- }
-
- xfs_buf_iorequest(bp);
- error = xfs_buf_iowait(bp);
+ error = xfs_buf_submit_wait(bp);
if (error) {
- xfs_buf_ioerror_alert(bp, __func__);
- ASSERT(0);
+ if (!XFS_FORCED_SHUTDOWN(log->l_mp)) {
+ xfs_buf_ioerror_alert(bp, __func__);
+ ASSERT(0);
+ }
xfs_buf_relse(bp);
return error;
}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d36bdbc..51435db 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -300,21 +300,15 @@
* access to the superblock.
*/
reread:
- bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), 0, buf_ops);
- if (!bp) {
- if (loud)
- xfs_warn(mp, "SB buffer read failed");
- return -EIO;
- }
- if (bp->b_error) {
- error = bp->b_error;
+ error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
+ BTOBB(sector_size), 0, &bp, buf_ops);
+ if (error) {
if (loud)
xfs_warn(mp, "SB validate failed with error %d.", error);
/* bad CRC means corrupted metadata */
if (error == -EFSBADCRC)
error = -EFSCORRUPTED;
- goto release_buf;
+ return error;
}
/*
@@ -544,40 +538,43 @@
* Check that the data (and log if separate) is an ok size.
*/
STATIC int
-xfs_check_sizes(xfs_mount_t *mp)
+xfs_check_sizes(
+ struct xfs_mount *mp)
{
- xfs_buf_t *bp;
+ struct xfs_buf *bp;
xfs_daddr_t d;
+ int error;
d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
xfs_warn(mp, "filesystem size mismatch detected");
return -EFBIG;
}
- bp = xfs_buf_read_uncached(mp->m_ddev_targp,
+ error = xfs_buf_read_uncached(mp->m_ddev_targp,
d - XFS_FSS_TO_BB(mp, 1),
- XFS_FSS_TO_BB(mp, 1), 0, NULL);
- if (!bp) {
+ XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+ if (error) {
xfs_warn(mp, "last sector read failed");
- return -EIO;
+ return error;
}
xfs_buf_relse(bp);
- if (mp->m_logdev_targp != mp->m_ddev_targp) {
- d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
- if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
- xfs_warn(mp, "log size mismatch detected");
- return -EFBIG;
- }
- bp = xfs_buf_read_uncached(mp->m_logdev_targp,
- d - XFS_FSB_TO_BB(mp, 1),
- XFS_FSB_TO_BB(mp, 1), 0, NULL);
- if (!bp) {
- xfs_warn(mp, "log device read failed");
- return -EIO;
- }
- xfs_buf_relse(bp);
+ if (mp->m_logdev_targp == mp->m_ddev_targp)
+ return 0;
+
+ d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+ if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
+ xfs_warn(mp, "log size mismatch detected");
+ return -EFBIG;
}
+ error = xfs_buf_read_uncached(mp->m_logdev_targp,
+ d - XFS_FSB_TO_BB(mp, 1),
+ XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+ if (error) {
+ xfs_warn(mp, "log device read failed");
+ return error;
+ }
+ xfs_buf_relse(bp);
return 0;
}
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index d45aebe..e1175ea 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -921,16 +921,11 @@
/*
* Read in the last block of the device, make sure it exists.
*/
- bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
+ error = xfs_buf_read_uncached(mp->m_rtdev_targp,
XFS_FSB_TO_BB(mp, nrblocks - 1),
- XFS_FSB_TO_BB(mp, 1), 0, NULL);
- if (!bp)
- return -EIO;
- if (bp->b_error) {
- error = bp->b_error;
- xfs_buf_relse(bp);
+ XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+ if (error)
return error;
- }
xfs_buf_relse(bp);
/*
@@ -1184,11 +1179,12 @@
*/
int /* error */
xfs_rtmount_init(
- xfs_mount_t *mp) /* file system mount structure */
+ struct xfs_mount *mp) /* file system mount structure */
{
- xfs_buf_t *bp; /* buffer for last block of subvolume */
- xfs_daddr_t d; /* address of last block of subvolume */
- xfs_sb_t *sbp; /* filesystem superblock copy in mount */
+ struct xfs_buf *bp; /* buffer for last block of subvolume */
+ struct xfs_sb *sbp; /* filesystem superblock copy in mount */
+ xfs_daddr_t d; /* address of last block of subvolume */
+ int error;
sbp = &mp->m_sb;
if (sbp->sb_rblocks == 0)
@@ -1214,14 +1210,12 @@
(unsigned long long) mp->m_sb.sb_rblocks);
return -EFBIG;
}
- bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
+ error = xfs_buf_read_uncached(mp->m_rtdev_targp,
d - XFS_FSB_TO_BB(mp, 1),
- XFS_FSB_TO_BB(mp, 1), 0, NULL);
- if (!bp || bp->b_error) {
+ XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+ if (error) {
xfs_warn(mp, "realtime device size check failed");
- if (bp)
- xfs_buf_relse(bp);
- return -EIO;
+ return error;
}
xfs_buf_relse(bp);
return 0;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 152f827..51372e3 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -349,7 +349,8 @@
DEFINE_BUF_EVENT(xfs_buf_hold);
DEFINE_BUF_EVENT(xfs_buf_rele);
DEFINE_BUF_EVENT(xfs_buf_iodone);
-DEFINE_BUF_EVENT(xfs_buf_iorequest);
+DEFINE_BUF_EVENT(xfs_buf_submit);
+DEFINE_BUF_EVENT(xfs_buf_submit_wait);
DEFINE_BUF_EVENT(xfs_buf_bawrite);
DEFINE_BUF_EVENT(xfs_buf_lock);
DEFINE_BUF_EVENT(xfs_buf_lock_done);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 96c898e..e2b2216 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -318,20 +318,10 @@
XFS_BUF_READ(bp);
bp->b_ops = ops;
- /*
- * XXX(hch): clean up the error handling here to be less
- * of a mess..
- */
- if (XFS_FORCED_SHUTDOWN(mp)) {
- trace_xfs_bdstrat_shut(bp, _RET_IP_);
- xfs_bioerror_relse(bp);
- } else {
- xfs_buf_iorequest(bp);
- }
-
- error = xfs_buf_iowait(bp);
+ error = xfs_buf_submit_wait(bp);
if (error) {
- xfs_buf_ioerror_alert(bp, __func__);
+ if (!XFS_FORCED_SHUTDOWN(mp))
+ xfs_buf_ioerror_alert(bp, __func__);
xfs_buf_relse(bp);
/*
* We can gracefully recover from most read