return mp->m_ddev_targp->bt_bdev;
}
-/*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
- */
-STATIC void
-xfs_finish_ioend(
- xfs_ioend_t *ioend,
- int wait)
-{
- if (atomic_dec_and_test(&ioend->io_remaining)) {
- queue_work(xfsdatad_workqueue, &ioend->io_work);
- if (wait)
- flush_workqueue(xfsdatad_workqueue);
- }
-}
-
/*
* We're now finished for good with this ioend structure.
* Update the page state via the associated buffer_heads,
xfs_destroy_ioend(ioend);
}
+/*
+ * Schedule IO completion handling on a xfsdatad if this was
+ * the final hold on this ioend. If we are asked to wait,
+ * flush the workqueue.
+ */
+STATIC void
+xfs_finish_ioend(
+ xfs_ioend_t *ioend,
+ int wait)
+{
+ if (atomic_dec_and_test(&ioend->io_remaining)) {
+ struct workqueue_struct *wq = xfsdatad_workqueue;
+ if (ioend->io_work.func == xfs_end_bio_unwritten)
+ wq = xfsconvertd_workqueue;
+
+ queue_work(wq, &ioend->io_work);
+ if (wait)
+ flush_workqueue(wq);
+ }
+}
+
/*
* Allocate and initialise an IO completion structure.
* We need to track unwritten extent write completion here initially.
#define __XFS_AOPS_H__
extern struct workqueue_struct *xfsdatad_workqueue;
+extern struct workqueue_struct *xfsconvertd_workqueue;
extern mempool_t *xfs_ioend_pool;
/*
static struct workqueue_struct *xfslogd_workqueue;
struct workqueue_struct *xfsdatad_workqueue;
+struct workqueue_struct *xfsconvertd_workqueue;
#ifdef XFS_BUF_TRACE
void
xfs_buf_t *bp, *n;
int pincount = 0;
+ xfs_buf_runall_queues(xfsconvertd_workqueue);
xfs_buf_runall_queues(xfsdatad_workqueue);
xfs_buf_runall_queues(xfslogd_workqueue);
if (!xfsdatad_workqueue)
goto out_destroy_xfslogd_workqueue;
+ xfsconvertd_workqueue = create_workqueue("xfsconvertd");
+ if (!xfsconvertd_workqueue)
+ goto out_destroy_xfsdatad_workqueue;
+
register_shrinker(&xfs_buf_shake);
return 0;
+ out_destroy_xfsdatad_workqueue:
+ destroy_workqueue(xfsdatad_workqueue);
out_destroy_xfslogd_workqueue:
destroy_workqueue(xfslogd_workqueue);
out_free_buf_zone:
xfs_buf_terminate(void)
{
unregister_shrinker(&xfs_buf_shake);
+ destroy_workqueue(xfsconvertd_workqueue);
destroy_workqueue(xfsdatad_workqueue);
destroy_workqueue(xfslogd_workqueue);
kmem_zone_destroy(xfs_buf_zone);
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
xfs_iflags_clear(ip, XFS_ITRUNCATED);
- ret = filemap_fdatawrite(mapping);
- if (flags & XFS_B_ASYNC)
- return -ret;
- ret2 = filemap_fdatawait(mapping);
- if (!ret)
- ret = ret2;
+ ret = -filemap_fdatawrite(mapping);
}
- return -ret;
+ if (flags & XFS_B_ASYNC)
+ return ret;
+ ret2 = xfs_wait_on_pages(ip, first, last);
+ if (!ret)
+ ret = ret2;
+ return ret;
}
int
goto relock;
}
} else {
+ int enospc = 0;
+ ssize_t ret2 = 0;
+
+write_retry:
xfs_rw_enter_trace(XFS_WRITE_ENTER, xip, (void *)iovp, segs,
*offset, ioflags);
- ret = generic_file_buffered_write(iocb, iovp, segs,
+ ret2 = generic_file_buffered_write(iocb, iovp, segs,
pos, offset, count, ret);
+ /*
+ * if we just got an ENOSPC, flush the inode now we
+ * aren't holding any page locks and retry *once*
+ */
+ if (ret2 == -ENOSPC && !enospc) {
+ error = xfs_flush_pages(xip, 0, -1, 0, FI_NONE);
+ if (error)
+ goto out_unlock_internal;
+ enospc = 1;
+ goto write_retry;
+ }
+ ret = ret2;
}
current->backing_dev_info = NULL;
uint32_t first_index = 0;
int error = 0;
int last_error = 0;
- int fflag = XFS_B_ASYNC;
-
- if (flags & SYNC_DELWRI)
- fflag = XFS_B_DELWRI;
- if (flags & SYNC_WAIT)
- fflag = 0; /* synchronous overrides all */
do {
struct inode *inode;
* If we have to flush data or wait for I/O completion
* we need to hold the iolock.
*/
- if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
- xfs_ilock(ip, XFS_IOLOCK_SHARED);
- lock_flags |= XFS_IOLOCK_SHARED;
- error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
- if (flags & SYNC_IOWAIT)
+ if (flags & SYNC_DELWRI) {
+ if (VN_DIRTY(inode)) {
+ if (flags & SYNC_TRYLOCK) {
+ if (xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+ lock_flags |= XFS_IOLOCK_SHARED;
+ } else {
+ xfs_ilock(ip, XFS_IOLOCK_SHARED);
+ lock_flags |= XFS_IOLOCK_SHARED;
+ }
+ if (lock_flags & XFS_IOLOCK_SHARED) {
+ error = xfs_flush_pages(ip, 0, -1,
+ (flags & SYNC_WAIT) ? 0
+ : XFS_B_ASYNC,
+ FI_NONE);
+ }
+ }
+ if (VN_CACHED(inode) && (flags & SYNC_IOWAIT))
xfs_ioend_wait(ip);
}
xfs_ilock(ip, XFS_ILOCK_SHARED);
xfs_syncd_queue_work(
struct xfs_mount *mp,
void *data,
- void (*syncer)(struct xfs_mount *, void *))
+ void (*syncer)(struct xfs_mount *, void *),
+ struct completion *completion)
{
- struct bhv_vfs_sync_work *work;
+ struct xfs_sync_work *work;
- work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
+ work = kmem_alloc(sizeof(struct xfs_sync_work), KM_SLEEP);
INIT_LIST_HEAD(&work->w_list);
work->w_syncer = syncer;
work->w_data = data;
work->w_mount = mp;
+ work->w_completion = completion;
spin_lock(&mp->m_sync_lock);
list_add_tail(&work->w_list, &mp->m_sync_list);
spin_unlock(&mp->m_sync_lock);
* heads, looking about for more room...
*/
STATIC void
-xfs_flush_inode_work(
- struct xfs_mount *mp,
- void *arg)
-{
- struct inode *inode = arg;
- filemap_flush(inode->i_mapping);
- iput(inode);
-}
-
-void
-xfs_flush_inode(
- xfs_inode_t *ip)
-{
- struct inode *inode = VFS_I(ip);
-
- igrab(inode);
- xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
- delay(msecs_to_jiffies(500));
-}
-
-/*
- * This is the "bigger hammer" version of xfs_flush_inode_work...
- * (IOW, "If at first you don't succeed, use a Bigger Hammer").
- */
-STATIC void
-xfs_flush_device_work(
+xfs_flush_inodes_work(
struct xfs_mount *mp,
void *arg)
{
struct inode *inode = arg;
- sync_blockdev(mp->m_super->s_bdev);
+ xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK);
+ xfs_sync_inodes(mp, SYNC_DELWRI | SYNC_TRYLOCK | SYNC_IOWAIT);
iput(inode);
}
void
-xfs_flush_device(
+xfs_flush_inodes(
xfs_inode_t *ip)
{
struct inode *inode = VFS_I(ip);
+ DECLARE_COMPLETION_ONSTACK(completion);
igrab(inode);
- xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
- delay(msecs_to_jiffies(500));
+ xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion);
+ wait_for_completion(&completion);
xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
}
{
struct xfs_mount *mp = arg;
long timeleft;
- bhv_vfs_sync_work_t *work, *n;
+ xfs_sync_work_t *work, *n;
LIST_HEAD (tmp);
set_freezable();
list_del(&work->w_list);
if (work == &mp->m_sync_work)
continue;
+ if (work->w_completion)
+ complete(work->w_completion);
kmem_free(work);
}
}
{
mp->m_sync_work.w_syncer = xfs_sync_worker;
mp->m_sync_work.w_mount = mp;
+ mp->m_sync_work.w_completion = NULL;
mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
if (IS_ERR(mp->m_sync_task))
return -PTR_ERR(mp->m_sync_task);
struct xfs_mount;
struct xfs_perag;
-typedef struct bhv_vfs_sync_work {
+typedef struct xfs_sync_work {
struct list_head w_list;
struct xfs_mount *w_mount;
void *w_data; /* syncer routine argument */
void (*w_syncer)(struct xfs_mount *, void *);
-} bhv_vfs_sync_work_t;
+ struct completion *w_completion;
+} xfs_sync_work_t;
#define SYNC_ATTR 0x0001 /* sync attributes */
#define SYNC_DELWRI 0x0002 /* look at delayed writes */
#define SYNC_WAIT 0x0004 /* wait for i/o to complete */
#define SYNC_BDFLUSH 0x0008 /* BDFLUSH is calling -- don't block */
#define SYNC_IOWAIT 0x0010 /* wait for all I/O to complete */
+#define SYNC_TRYLOCK 0x0020 /* only try to lock inodes */
int xfs_syncd_init(struct xfs_mount *mp);
void xfs_syncd_stop(struct xfs_mount *mp);
int xfs_quiesce_data(struct xfs_mount *mp);
void xfs_quiesce_attr(struct xfs_mount *mp);
-void xfs_flush_inode(struct xfs_inode *ip);
-void xfs_flush_device(struct xfs_inode *ip);
+void xfs_flush_inodes(struct xfs_inode *ip);
int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
int xfs_reclaim_inodes(struct xfs_mount *mp, int noblock, int mode);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(completion_done(&ip->i_flush));
- /*
- * initialise the VFS inode here to get failures
- * out of the way early.
- */
- if (!inode_init_always(mp->m_super, VFS_I(ip))) {
- kmem_zone_free(xfs_inode_zone, ip);
- return NULL;
- }
-
/* initialise the xfs inode */
ip->i_ino = ino;
ip->i_mount = mp;
#ifdef XFS_DIR2_TRACE
ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
#endif
+ /*
+ * Now initialise the VFS inode. We do this after the xfs_inode
+ * initialisation as internal failures will result in ->destroy_inode
+ * being called and that will pass down through the reclaim path and
+ * free the XFS inode. This path requires the XFS inode to already be
+ * initialised. Hence if this call fails, the xfs_inode has already
+ * been freed and we should not reference it at all in the error
+ * handling.
+ */
+ if (!inode_init_always(mp->m_super, VFS_I(ip)))
+ return NULL;
+
+ /* prevent anyone from using this yet */
+ VFS_I(ip)->i_state = I_NEW|I_LOCK;
return ip;
}
return 0;
}
-STATIC int
-xfs_flush_space(
- xfs_inode_t *ip,
- int *fsynced,
- int *ioflags)
-{
- switch (*fsynced) {
- case 0:
- if (ip->i_delayed_blks) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_flush_inode(ip);
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- *fsynced = 1;
- } else {
- *ioflags |= BMAPI_SYNC;
- *fsynced = 2;
- }
- return 0;
- case 1:
- *fsynced = 2;
- *ioflags |= BMAPI_SYNC;
- return 0;
- case 2:
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_flush_device(ip);
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- *fsynced = 3;
- return 0;
- }
- return 1;
-}
-
STATIC int
xfs_cmn_err_fsblock_zero(
xfs_inode_t *ip,
}
/*
- * If the caller is doing a write at the end of the file,
- * then extend the allocation out to the file system's write
- * iosize. We clean up any extra space left over when the
- * file is closed in xfs_inactive().
- *
- * For sync writes, we are flushing delayed allocate space to
- * try to make additional space available for allocation near
- * the filesystem full boundary - preallocation hurts in that
- * situation, of course.
+ * If the caller is doing a write at the end of the file, then extend the
+ * allocation out to the file system's write iosize. We clean up any extra
+ * space left over when the file is closed in xfs_inactive().
*/
STATIC int
xfs_iomap_eof_want_preallocate(
int n, error, imaps;
*prealloc = 0;
- if ((ioflag & BMAPI_SYNC) || (offset + count) <= ip->i_size)
+ if ((offset + count) <= ip->i_size)
return 0;
/*
xfs_extlen_t extsz;
int nimaps;
xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS];
- int prealloc, fsynced = 0;
+ int prealloc, flushed = 0;
int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
extsz = xfs_get_extsz_hint(ip);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
-retry:
error = xfs_iomap_eof_want_preallocate(mp, ip, offset, count,
ioflag, imap, XFS_WRITE_IMAPS, &prealloc);
if (error)
return error;
+retry:
if (prealloc) {
aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1));
ioalign = XFS_B_TO_FSBT(mp, aligned_offset);
/*
* If bmapi returned us nothing, and if we didn't get back EDQUOT,
- * then we must have run out of space - flush delalloc, and retry..
+ * then we must have run out of space - flush all other inodes with
+ * delalloc blocks and retry without EOF preallocation.
*/
if (nimaps == 0) {
xfs_iomap_enter_trace(XFS_IOMAP_WRITE_NOSPACE,
ip, offset, count);
- if (xfs_flush_space(ip, &fsynced, &ioflag))
+ if (flushed)
return XFS_ERROR(ENOSPC);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_flush_inodes(ip);
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+ flushed = 1;
error = 0;
+ prealloc = 0;
goto retry;
}
BMAPI_IGNSTATE = (1 << 4), /* ignore unwritten state on read */
BMAPI_DIRECT = (1 << 5), /* direct instead of buffered write */
BMAPI_MMAP = (1 << 6), /* allocate for mmap write */
- BMAPI_SYNC = (1 << 7), /* sync write to flush delalloc space */
- BMAPI_TRYLOCK = (1 << 8), /* non-blocking request */
+ BMAPI_TRYLOCK = (1 << 7), /* non-blocking request */
} bmapi_flags_t;
}
mp->m_log = xlog_alloc_log(mp, log_target, blk_offset, num_bblks);
- if (!mp->m_log) {
- cmn_err(CE_WARN, "XFS: Log allocation failed: No memory!");
- error = ENOMEM;
+ if (IS_ERR(mp->m_log)) {
+ error = -PTR_ERR(mp->m_log);
goto out;
}
xfs_buf_t *bp;
int i;
int iclogsize;
+ int error = ENOMEM;
log = kmem_zalloc(sizeof(xlog_t), KM_MAYFAIL);
- if (!log)
- return NULL;
+ if (!log) {
+ xlog_warn("XFS: Log allocation failed: No memory!");
+ goto out;
+ }
log->l_mp = mp;
log->l_targ = log_target;
log->l_grant_reserve_cycle = 1;
log->l_grant_write_cycle = 1;
+ error = EFSCORRUPTED;
if (xfs_sb_version_hassector(&mp->m_sb)) {
log->l_sectbb_log = mp->m_sb.sb_logsectlog - BBSHIFT;
- ASSERT(log->l_sectbb_log <= mp->m_sectbb_log);
+ if (log->l_sectbb_log < 0 ||
+ log->l_sectbb_log > mp->m_sectbb_log) {
+ xlog_warn("XFS: Log sector size (0x%x) out of range.",
+ log->l_sectbb_log);
+ goto out_free_log;
+ }
+
/* for larger sector sizes, must have v2 or external log */
- ASSERT(log->l_sectbb_log == 0 ||
- log->l_logBBstart == 0 ||
- xfs_sb_version_haslogv2(&mp->m_sb));
- ASSERT(mp->m_sb.sb_logsectlog >= BBSHIFT);
+ if (log->l_sectbb_log != 0 &&
+ (log->l_logBBstart != 0 &&
+ !xfs_sb_version_haslogv2(&mp->m_sb))) {
+ xlog_warn("XFS: log sector size (0x%x) invalid "
+ "for configuration.", log->l_sectbb_log);
+ goto out_free_log;
+ }
+ if (mp->m_sb.sb_logsectlog < BBSHIFT) {
+ xlog_warn("XFS: Log sector log (0x%x) too small.",
+ mp->m_sb.sb_logsectlog);
+ goto out_free_log;
+ }
}
log->l_sectbb_mask = (1 << log->l_sectbb_log) - 1;
xlog_get_iclog_buffer_size(mp, log);
+ error = ENOMEM;
bp = xfs_buf_get_empty(log->l_iclog_size, mp->m_logdev_targp);
if (!bp)
goto out_free_log;
xfs_buf_free(log->l_xbuf);
out_free_log:
kmem_free(log);
- return NULL;
+out:
+ return ERR_PTR(-error);
} /* xlog_alloc_log */
xlog_ins_ticketq(&log->l_reserve_headq, tic);
xlog_trace_loggrant(log, tic,
"xlog_grant_log_space: sleep 2");
+ spin_unlock(&log->l_grant_lock);
+ xlog_grant_push_ail(log->l_mp, need_bytes);
+ spin_lock(&log->l_grant_lock);
+
XFS_STATS_INC(xs_sleep_logspace);
sv_wait(&tic->t_wait, PINOD|PLTWAIT, &log->l_grant_lock, s);
- if (XLOG_FORCED_SHUTDOWN(log)) {
- spin_lock(&log->l_grant_lock);
+ spin_lock(&log->l_grant_lock);
+ if (XLOG_FORCED_SHUTDOWN(log))
goto error_return;
- }
xlog_trace_loggrant(log, tic,
"xlog_grant_log_space: wake 2");
- xlog_grant_push_ail(log->l_mp, need_bytes);
- spin_lock(&log->l_grant_lock);
goto redo;
} else if (tic->t_flags & XLOG_TIC_IN_Q)
xlog_del_ticketq(&log->l_reserve_headq, tic);
* for more free space, otherwise try to get some space for
* this transaction.
*/
-
+ need_bytes = tic->t_unit_res;
if ((ntic = log->l_write_headq)) {
free_bytes = xlog_space_left(log, log->l_grant_write_cycle,
log->l_grant_write_bytes);
xlog_trace_loggrant(log, tic,
"xlog_regrant_write_log_space: sleep 1");
+ spin_unlock(&log->l_grant_lock);
+ xlog_grant_push_ail(log->l_mp, need_bytes);
+ spin_lock(&log->l_grant_lock);
+
XFS_STATS_INC(xs_sleep_logspace);
sv_wait(&tic->t_wait, PINOD|PLTWAIT,
&log->l_grant_lock, s);
/* If we're shutting down, this tic is already
* off the queue */
- if (XLOG_FORCED_SHUTDOWN(log)) {
- spin_lock(&log->l_grant_lock);
+ spin_lock(&log->l_grant_lock);
+ if (XLOG_FORCED_SHUTDOWN(log))
goto error_return;
- }
xlog_trace_loggrant(log, tic,
"xlog_regrant_write_log_space: wake 1");
- xlog_grant_push_ail(log->l_mp, tic->t_unit_res);
- spin_lock(&log->l_grant_lock);
}
}
- need_bytes = tic->t_unit_res;
-
redo:
if (XLOG_FORCED_SHUTDOWN(log))
goto error_return;
if (free_bytes < need_bytes) {
if ((tic->t_flags & XLOG_TIC_IN_Q) == 0)
xlog_ins_ticketq(&log->l_write_headq, tic);
+ spin_unlock(&log->l_grant_lock);
+ xlog_grant_push_ail(log->l_mp, need_bytes);
+ spin_lock(&log->l_grant_lock);
+
XFS_STATS_INC(xs_sleep_logspace);
sv_wait(&tic->t_wait, PINOD|PLTWAIT, &log->l_grant_lock, s);
/* If we're shutting down, this tic is already off the queue */
- if (XLOG_FORCED_SHUTDOWN(log)) {
- spin_lock(&log->l_grant_lock);
+ spin_lock(&log->l_grant_lock);
+ if (XLOG_FORCED_SHUTDOWN(log))
goto error_return;
- }
xlog_trace_loggrant(log, tic,
"xlog_regrant_write_log_space: wake 2");
- xlog_grant_push_ail(log->l_mp, need_bytes);
- spin_lock(&log->l_grant_lock);
goto redo;
} else if (tic->t_flags & XLOG_TIC_IN_Q)
xlog_del_ticketq(&log->l_write_headq, tic);
#endif
struct xfs_mru_cache *m_filestream; /* per-mount filestream data */
struct task_struct *m_sync_task; /* generalised sync thread */
- bhv_vfs_sync_work_t m_sync_work; /* work item for VFS_SYNC */
+ xfs_sync_work_t m_sync_work; /* work item for VFS_SYNC */
struct list_head m_sync_list; /* sync thread work item list */
spinlock_t m_sync_lock; /* work item list lock */
int m_sync_seq; /* sync thread generation no. */
error = xfs_trans_reserve(tp, resblks, log_res, 0,
XFS_TRANS_PERM_LOG_RES, log_count);
if (error == ENOSPC) {
+ /* flush outstanding delalloc blocks and retry */
+ xfs_flush_inodes(dp);
+ error = xfs_trans_reserve(tp, resblks, XFS_CREATE_LOG_RES(mp), 0,
+ XFS_TRANS_PERM_LOG_RES, XFS_CREATE_LOG_COUNT);
+ }
+ if (error == ENOSPC) {
+ /* No space at all so try a "no-allocation" reservation */
resblks = 0;
error = xfs_trans_reserve(tp, 0, log_res, 0,
XFS_TRANS_PERM_LOG_RES, log_count);
git.openpandora.org / pandora-kernel.git / commitdiff