Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: prevent NMI timeouts in cmn_err
  xfs: Add log level to assertion printk
  xfs: fix an assignment within an ASSERT()
  xfs: fix error handling for synchronous writes
  xfs: add FITRIM support
  xfs: ensure log covering transactions are synchronous
  xfs: serialise unaligned direct IOs
  xfs: factor common write setup code
  xfs: split buffered IO write path from xfs_file_aio_write
  xfs: split direct IO write path from xfs_file_aio_write
  xfs: introduce xfs_rw_lock() helpers for locking the inode
  xfs: factor post-write newsize updates
  xfs: factor common post-write isize handling code
  xfs: ensure sync write errors are returned

10 files changed, 573 insertions, 247 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 92f1f2a..ac1c7e8 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -896,7 +896,6 @@ xfs_buf_rele(
 	trace_xfs_buf_rele(bp, _RET_IP_);
 
 	if (!pag) {
-		ASSERT(!bp->b_relse);
 		ASSERT(list_empty(&bp->b_lru));
 		ASSERT(RB_EMPTY_NODE(&bp->b_rbnode));
 		if (atomic_dec_and_test(&bp->b_hold))
@@ -908,11 +907,7 @@ xfs_buf_rele(
 
 	ASSERT(atomic_read(&bp->b_hold) > 0);
 	if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
-		if (bp->b_relse) {
-			atomic_inc(&bp->b_hold);
-			spin_unlock(&pag->pag_buf_lock);
-			bp->b_relse(bp);
-		} else if (!(bp->b_flags & XBF_STALE) &&
+		if (!(bp->b_flags & XBF_STALE) &&
 			   atomic_read(&bp->b_lru_ref)) {
 			xfs_buf_lru_add(bp);
 			spin_unlock(&pag->pag_buf_lock);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index a76c242..cbe6595 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -152,8 +152,6 @@ typedef struct xfs_buftarg {
 
 struct xfs_buf;
 typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
-typedef void (*xfs_buf_relse_t)(struct xfs_buf *);
-typedef int (*xfs_buf_bdstrat_t)(struct xfs_buf *);
 
 #define XB_PAGES	2
 
@@ -183,7 +181,6 @@ typedef struct xfs_buf {
 	void			*b_addr;	/* virtual address of buffer */
 	struct work_struct	b_iodone_work;
 	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
-	xfs_buf_relse_t		b_relse;	/* releasing function */
 	struct completion	b_iowait;	/* queue for I/O waiters */
 	void			*b_fspriv;
 	void			*b_fspriv2;
@@ -323,7 +320,6 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_FSPRIVATE2(bp, type)		((type)(bp)->b_fspriv2)
 #define XFS_BUF_SET_FSPRIVATE2(bp, val)		((bp)->b_fspriv2 = (void*)(val))
 #define XFS_BUF_SET_START(bp)			do { } while (0)
-#define XFS_BUF_SET_BRELSE_FUNC(bp, func)	((bp)->b_relse = (func))
 
 #define XFS_BUF_PTR(bp)			(xfs_caddr_t)((bp)->b_addr)
 #define XFS_BUF_SET_PTR(bp, val, cnt)	xfs_buf_associate_memory(bp, val, cnt)
@@ -360,8 +356,7 @@ xfs_buf_set_ref(
 
 static inline void xfs_buf_relse(xfs_buf_t *bp)
 {
-	if (!bp->b_relse)
-		xfs_buf_unlock(bp);
+	xfs_buf_unlock(bp);
 	xfs_buf_rele(bp);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/linux-2.6/xfs_discard.c
new file mode 100644
index 0000000..05201ae
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_discard.c
@@ -0,0 +1,191 @@
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_sb.h"
+#include "xfs_inum.h"
+#include "xfs_log.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_quota.h"
+#include "xfs_trans.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_btree.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_error.h"
+#include "xfs_discard.h"
+#include "xfs_trace.h"
+
+STATIC int
+xfs_trim_extents(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_fsblock_t		start,
+	xfs_fsblock_t		len,
+	xfs_fsblock_t		minlen,
+	__uint64_t		*blocks_trimmed)
+{
+	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agbp;
+	struct xfs_perag	*pag;
+	int			error;
+	int			i;
+
+	pag = xfs_perag_get(mp, agno);
+
+	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	if (error || !agbp)
+		goto out_put_perag;
+
+	cur = xfs_allocbt_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_CNT);
+
+	/*
+	 * Force out the log.  This means any transactions that might have freed
+	 * space before we took the AGF buffer lock are now on disk, and the
+	 * volatile disk cache is flushed.
+	 */
+	xfs_log_force(mp, XFS_LOG_SYNC);
+
+	/*
+	 * Look up the longest btree in the AGF and start with it.
+	 */
+	error = xfs_alloc_lookup_le(cur, 0,
+				    XFS_BUF_TO_AGF(agbp)->agf_longest, &i);
+	if (error)
+		goto out_del_cursor;
+
+	/*
+	 * Loop until we are done with all extents that are large
+	 * enough to be worth discarding.
+	 */
+	while (i) {
+		xfs_agblock_t fbno;
+		xfs_extlen_t flen;
+
+		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
+		if (error)
+			goto out_del_cursor;
+		XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor);
+		ASSERT(flen <= XFS_BUF_TO_AGF(agbp)->agf_longest);
+
+		/*
+		 * Too small?  Give up.
+		 */
+		if (flen < minlen) {
+			trace_xfs_discard_toosmall(mp, agno, fbno, flen);
+			goto out_del_cursor;
+		}
+
+		/*
+		 * If the extent is entirely outside of the range we are
+		 * supposed to discard skip it.  Do not bother to trim
+		 * down partially overlapping ranges for now.
+		 */
+		if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
+		    XFS_AGB_TO_FSB(mp, agno, fbno) >= start + len) {
+			trace_xfs_discard_exclude(mp, agno, fbno, flen);
+			goto next_extent;
+		}
+
+		/*
+		 * If any blocks in the range are still busy, skip the
+		 * discard and try again the next time.
+		 */
+		if (xfs_alloc_busy_search(mp, agno, fbno, flen)) {
+			trace_xfs_discard_busy(mp, agno, fbno, flen);
+			goto next_extent;
+		}
+
+		trace_xfs_discard_extent(mp, agno, fbno, flen);
+		error = -blkdev_issue_discard(bdev,
+				XFS_AGB_TO_DADDR(mp, agno, fbno),
+				XFS_FSB_TO_BB(mp, flen),
+				GFP_NOFS, 0);
+		if (error)
+			goto out_del_cursor;
+		*blocks_trimmed += flen;
+
+next_extent:
+		error = xfs_btree_decrement(cur, 0, &i);
+		if (error)
+			goto out_del_cursor;
+	}
+
+out_del_cursor:
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_buf_relse(agbp);
+out_put_perag:
+	xfs_perag_put(pag);
+	return error;
+}
+
+int
+xfs_ioc_trim(
+	struct xfs_mount		*mp,
+	struct fstrim_range __user	*urange)
+{
+	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
+	unsigned int		granularity = q->limits.discard_granularity;
+	struct fstrim_range	range;
+	xfs_fsblock_t		start, len, minlen;
+	xfs_agnumber_t		start_agno, end_agno, agno;
+	__uint64_t		blocks_trimmed = 0;
+	int			error, last_error = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -XFS_ERROR(EPERM);
+	if (copy_from_user(&range, urange, sizeof(range)))
+		return -XFS_ERROR(EFAULT);
+
+	/*
+	 * Truncating down the len isn't actually quite correct, but using
+	 * XFS_B_TO_FSB would mean we trivially get overflows for values
+	 * of ULLONG_MAX or slightly lower.  And ULLONG_MAX is the default
+	 * used by the fstrim application.  In the end it really doesn't
+	 * matter as trimming blocks is an advisory interface.
+	 */
+	start = XFS_B_TO_FSBT(mp, range.start);
+	len = XFS_B_TO_FSBT(mp, range.len);
+	minlen = XFS_B_TO_FSB(mp, max_t(u64, granularity, range.minlen));
+
+	start_agno = XFS_FSB_TO_AGNO(mp, start);
+	if (start_agno >= mp->m_sb.sb_agcount)
+		return -XFS_ERROR(EINVAL);
+
+	end_agno = XFS_FSB_TO_AGNO(mp, start + len);
+	if (end_agno >= mp->m_sb.sb_agcount)
+		end_agno = mp->m_sb.sb_agcount - 1;
+
+	for (agno = start_agno; agno <= end_agno; agno++) {
+		error = -xfs_trim_extents(mp, agno, start, len, minlen,
+					  &blocks_trimmed);
+		if (error)
+			last_error = error;
+	}
+
+	if (last_error)
+		return last_error;
+
+	range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
+	if (copy_to_user(urange, &range, sizeof(range)))
+		return -XFS_ERROR(EFAULT);
+	return 0;
+}
diff --git a/fs/xfs/linux-2.6/xfs_discard.h b/fs/xfs/linux-2.6/xfs_discard.h
new file mode 100644
index 0000000..e82b6dd
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_discard.h
@@ -0,0 +1,8 @@
+#ifndef XFS_DISCARD_H
+#define XFS_DISCARD_H 1
+
+struct fstrim_range;
+
+extern int	xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *);
+
+#endif /* XFS_DISCARD_H */
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index ba8ad42..ef51eb43e 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -41,6 +41,40 @@
 static const struct vm_operations_struct xfs_file_vm_ops;
 
 /*
+ * Locking primitives for read and write IO paths to ensure we consistently use
+ * and order the inode->i_mutex, ip->i_lock and ip->i_iolock.
+ */
+static inline void
+xfs_rw_ilock(
+	struct xfs_inode	*ip,
+	int			type)
+{
+	if (type & XFS_IOLOCK_EXCL)
+		mutex_lock(&VFS_I(ip)->i_mutex);
+	xfs_ilock(ip, type);
+}
+
+static inline void
+xfs_rw_iunlock(
+	struct xfs_inode	*ip,
+	int			type)
+{
+	xfs_iunlock(ip, type);
+	if (type & XFS_IOLOCK_EXCL)
+		mutex_unlock(&VFS_I(ip)->i_mutex);
+}
+
+static inline void
+xfs_rw_ilock_demote(
+	struct xfs_inode	*ip,
+	int			type)
+{
+	xfs_ilock_demote(ip, type);
+	if (type & XFS_IOLOCK_EXCL)
+		mutex_unlock(&VFS_I(ip)->i_mutex);
+}
+
+/*
  *	xfs_iozero
  *
  *	xfs_iozero clears the specified range of buffer supplied,
@@ -262,22 +296,21 @@ xfs_file_aio_read(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (unlikely(ioflags & IO_ISDIRECT))
-		mutex_lock(&inode->i_mutex);
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
-
 	if (unlikely(ioflags & IO_ISDIRECT)) {
+		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
+
 		if (inode->i_mapping->nrpages) {
 			ret = -xfs_flushinval_pages(ip,
 					(iocb->ki_pos & PAGE_CACHE_MASK),
 					-1, FI_REMAPF_LOCKED);
+			if (ret) {
+				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
+				return ret;
+			}
 		}
-		mutex_unlock(&inode->i_mutex);
-		if (ret) {
-			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-			return ret;
-		}
-	}
+		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+	} else
+		xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 
 	trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
 
@@ -285,7 +318,7 @@ xfs_file_aio_read(
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
-	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
@@ -309,7 +342,7 @@ xfs_file_splice_read(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 
 	trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
 
@@ -317,10 +350,61 @@ xfs_file_splice_read(
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
-	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
+STATIC void
+xfs_aio_write_isize_update(
+	struct inode	*inode,
+	loff_t		*ppos,
+	ssize_t		bytes_written)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	xfs_fsize_t		isize = i_size_read(inode);
+
+	if (bytes_written > 0)
+		XFS_STATS_ADD(xs_write_bytes, bytes_written);
+
+	if (unlikely(bytes_written < 0 && bytes_written != -EFAULT &&
+					*ppos > isize))
+		*ppos = isize;
+
+	if (*ppos > ip->i_size) {
+		xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
+		if (*ppos > ip->i_size)
+			ip->i_size = *ppos;
+		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+}
+
+/*
+ * If this was a direct or synchronous I/O that failed (such as ENOSPC) then
+ * part of the I/O may have been written to disk before the error occured.  In
+ * this case the on-disk file size may have been adjusted beyond the in-memory
+ * file size and now needs to be truncated back.
+ */
+STATIC void
+xfs_aio_write_newsize_update(
+	struct xfs_inode	*ip)
+{
+	if (ip->i_new_size) {
+		xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
+		ip->i_new_size = 0;
+		if (ip->i_d.di_size > ip->i_size)
+			ip->i_d.di_size = ip->i_size;
+		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+}
+
+/*
+ * xfs_file_splice_write() does not use xfs_rw_ilock() because
+ * generic_file_splice_write() takes the i_mutex itself. This, in theory,
+ * couuld cause lock inversions between the aio_write path and the splice path
+ * if someone is doing concurrent splice(2) based writes and write(2) based
+ * writes to the same inode. The only real way to fix this is to re-implement
+ * the generic code here with correct locking orders.
+ */
 STATIC ssize_t
 xfs_file_splice_write(
 	struct pipe_inode_info	*pipe,
@@ -331,7 +415,7 @@ xfs_file_splice_write(
 {
 	struct inode		*inode = outfilp->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	xfs_fsize_t		isize, new_size;
+	xfs_fsize_t		new_size;
 	int			ioflags = 0;
 	ssize_t			ret;
 
@@ -355,27 +439,9 @@ xfs_file_splice_write(
 	trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
 
 	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_write_bytes, ret);
-
-	isize = i_size_read(inode);
-	if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
-		*ppos = isize;
 
-	if (*ppos > ip->i_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		if (*ppos > ip->i_size)
-			ip->i_size = *ppos;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-
-	if (ip->i_new_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		ip->i_new_size = 0;
-		if (ip->i_d.di_size > ip->i_size)
-			ip->i_d.di_size = ip->i_size;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
+	xfs_aio_write_isize_update(inode, ppos, ret);
+	xfs_aio_write_newsize_update(ip);
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	return ret;
 }
@@ -562,245 +628,258 @@ out_lock:
 	return error;
 }
 
+/*
+ * Common pre-write limit and setup checks.
+ *
+ * Returns with iolock held according to @iolock.
+ */
 STATIC ssize_t
-xfs_file_aio_write(
-	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos)
+xfs_file_aio_write_checks(
+	struct file		*file,
+	loff_t			*pos,
+	size_t			*count,
+	int			*iolock)
 {
-	struct file		*file = iocb->ki_filp;
-	struct address_space	*mapping = file->f_mapping;
-	struct inode		*inode = mapping->host;
+	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	ssize_t			ret = 0, error = 0;
-	int			ioflags = 0;
-	xfs_fsize_t		isize, new_size;
-	int			iolock;
-	size_t			ocount = 0, count;
-	int			need_i_mutex;
+	xfs_fsize_t		new_size;
+	int			error = 0;
 
-	XFS_STATS_INC(xs_write_calls);
+	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
+	if (error) {
+		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
+		*iolock = 0;
+		return error;
+	}
 
-	BUG_ON(iocb->ki_pos != pos);
+	new_size = *pos + *count;
+	if (new_size > ip->i_size)
+		ip->i_new_size = new_size;
 
-	if (unlikely(file->f_flags & O_DIRECT))
-		ioflags |= IO_ISDIRECT;
-	if (file->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+	if (likely(!(file->f_mode & FMODE_NOCMTIME)))
+		file_update_time(file);
 
-	error = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
+	/*
+	 * If the offset is beyond the size of the file, we need to zero any
+	 * blocks that fall between the existing EOF and the start of this
+	 * write.
+	 */
+	if (*pos > ip->i_size)
+		error = -xfs_zero_eof(ip, *pos, ip->i_size);
+
+	xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
 	if (error)
 		return error;
 
-	count = ocount;
-	if (count == 0)
-		return 0;
-
-	xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-relock:
-	if (ioflags & IO_ISDIRECT) {
-		iolock = XFS_IOLOCK_SHARED;
-		need_i_mutex = 0;
-	} else {
-		iolock = XFS_IOLOCK_EXCL;
-		need_i_mutex = 1;
-		mutex_lock(&inode->i_mutex);
-	}
+	/*
+	 * If we're writing the file then make sure to clear the setuid and
+	 * setgid bits if the process is not being run by root.  This keeps
+	 * people from modifying setuid and setgid binaries.
+	 */
+	return file_remove_suid(file);
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
+}
 
-start:
-	error = -generic_write_checks(file, &pos, &count,
-					S_ISBLK(inode->i_mode));
-	if (error) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
-		goto out_unlock_mutex;
+/*
+ * xfs_file_dio_aio_write - handle direct IO writes
+ *
+ * Lock the inode appropriately to prepare for and issue a direct IO write.
+ * By separating it from the buffered write path we remove all the tricky to
+ * follow locking changes and looping.
+ *
+ * If there are cached pages or we're extending the file, we need IOLOCK_EXCL
+ * until we're sure the bytes at the new EOF have been zeroed and/or the cached
+ * pages are flushed out.
+ *
+ * In most cases the direct IO writes will be done holding IOLOCK_SHARED
+ * allowing them to be done in parallel with reads and other direct IO writes.
+ * However, if the IO is not aligned to filesystem blocks, the direct IO layer
+ * needs to do sub-block zeroing and that requires serialisation against other
+ * direct IOs to the same block. In this case we need to serialise the
+ * submission of the unaligned IOs so that we don't get racing block zeroing in
+ * the dio layer.  To avoid the problem with aio, we also need to wait for
+ * outstanding IOs to complete so that unwritten extent conversion is completed
+ * before we try to map the overlapping block. This is currently implemented by
+ * hitting it with a big hammer (i.e. xfs_ioend_wait()).
+ *
+ * Returns with locks held indicated by @iolock and errors indicated by
+ * negative return values.
+ */
+STATIC ssize_t
+xfs_file_dio_aio_write(
+	struct kiocb		*iocb,
+	const struct iovec	*iovp,
+	unsigned long		nr_segs,
+	loff_t			pos,
+	size_t			ocount,
+	int			*iolock)
+{
+	struct file		*file = iocb->ki_filp;
+	struct address_space	*mapping = file->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;
+	size_t			count = ocount;
+	int			unaligned_io = 0;
+	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
+					mp->m_rtdev_targp : mp->m_ddev_targp;
+
+	*iolock = 0;
+	if ((pos & target->bt_smask) || (count & target->bt_smask))
+		return -XFS_ERROR(EINVAL);
+
+	if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
+		unaligned_io = 1;
+
+	if (unaligned_io || mapping->nrpages || pos > ip->i_size)
+		*iolock = XFS_IOLOCK_EXCL;
+	else
+		*iolock = XFS_IOLOCK_SHARED;
+	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+
+	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
+	if (ret)
+		return ret;
+
+	if (mapping->nrpages) {
+		WARN_ON(*iolock != XFS_IOLOCK_EXCL);
+		ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
+							FI_REMAPF_LOCKED);
+		if (ret)
+			return ret;
 	}
 
-	if (ioflags & IO_ISDIRECT) {
-		xfs_buftarg_t	*target =
-			XFS_IS_REALTIME_INODE(ip) ?
-				mp->m_rtdev_targp : mp->m_ddev_targp;
-
-		if ((pos & target->bt_smask) || (count & target->bt_smask)) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
-			return XFS_ERROR(-EINVAL);
-		}
-
-		if (!need_i_mutex && (mapping->nrpages || pos > ip->i_size)) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
-			iolock = XFS_IOLOCK_EXCL;
-			need_i_mutex = 1;
-			mutex_lock(&inode->i_mutex);
-			xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
-			goto start;
-		}
+	/*
+	 * If we are doing unaligned IO, wait for all other IO to drain,
+	 * otherwise demote the lock if we had to flush cached pages
+	 */
+	if (unaligned_io)
+		xfs_ioend_wait(ip);
+	else if (*iolock == XFS_IOLOCK_EXCL) {
+		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+		*iolock = XFS_IOLOCK_SHARED;
 	}
 
-	new_size = pos + count;
-	if (new_size > ip->i_size)
-		ip->i_new_size = new_size;
+	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
+	ret = generic_file_direct_write(iocb, iovp,
+			&nr_segs, pos, &iocb->ki_pos, count, ocount);
 
-	if (likely(!(ioflags & IO_INVIS)))
-		file_update_time(file);
+	/* No fallback to buffered IO on errors for XFS. */
+	ASSERT(ret < 0 || ret == count);
+	return ret;
+}
 
-	/*
-	 * If the offset is beyond the size of the file, we have a couple
-	 * of things to do. First, if there is already space allocated
-	 * we need to either create holes or zero the disk or ...
-	 *
-	 * If there is a page where the previous size lands, we need
-	 * to zero it out up to the new size.
-	 */
+STATIC ssize_t
+xfs_file_buffered_aio_write(
+	struct kiocb		*iocb,
+	const struct iovec	*iovp,
+	unsigned long		nr_segs,
+	loff_t			pos,
+	size_t			ocount,
+	int			*iolock)
+{
+	struct file		*file = iocb->ki_filp;
+	struct address_space	*mapping = file->f_mapping;
+	struct inode		*inode = mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	ssize_t			ret;
+	int			enospc = 0;
+	size_t			count = ocount;
 
-	if (pos > ip->i_size) {
-		error = xfs_zero_eof(ip, pos, ip->i_size);
-		if (error) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			goto out_unlock_internal;
-		}
-	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	*iolock = XFS_IOLOCK_EXCL;
+	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
 
-	/*
-	 * If we're writing the file then make sure to clear the
-	 * setuid and setgid bits if the process is not being run
-	 * by root.  This keeps people from modifying setuid and
-	 * setgid binaries.
-	 */
-	error = -file_remove_suid(file);
-	if (unlikely(error))
-		goto out_unlock_internal;
+	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
+	if (ret)
+		return ret;
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
 
-	if ((ioflags & IO_ISDIRECT)) {
-		if (mapping->nrpages) {
-			WARN_ON(need_i_mutex == 0);
-			error = xfs_flushinval_pages(ip,
-					(pos & PAGE_CACHE_MASK),
-					-1, FI_REMAPF_LOCKED);
-			if (error)
-				goto out_unlock_internal;
-		}
-
-		if (need_i_mutex) {
-			/* demote the lock now the cached pages are gone */
-			xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
-			mutex_unlock(&inode->i_mutex);
+write_retry:
+	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
+	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
+			pos, &iocb->ki_pos, count, ret);
+	/*
+	 * if we just got an ENOSPC, flush the inode now we aren't holding any
+	 * page locks and retry *once*
+	 */
+	if (ret == -ENOSPC && !enospc) {
+		ret = -xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
+		if (ret)
+			return ret;
+		enospc = 1;
+		goto write_retry;
+	}
+	current->backing_dev_info = NULL;
+	return ret;
+}
 
-			iolock = XFS_IOLOCK_SHARED;
-			need_i_mutex = 0;
-		}
+STATIC ssize_t
+xfs_file_aio_write(
+	struct kiocb		*iocb,
+	const struct iovec	*iovp,
+	unsigned long		nr_segs,
+	loff_t			pos)
+{
+	struct file		*file = iocb->ki_filp;
+	struct address_space	*mapping = file->f_mapping;
+	struct inode		*inode = mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	ssize_t			ret;
+	int			iolock;
+	size_t			ocount = 0;
 
-		trace_xfs_file_direct_write(ip, count, iocb->ki_pos, ioflags);
-		ret = generic_file_direct_write(iocb, iovp,
-				&nr_segs, pos, &iocb->ki_pos, count, ocount);
+	XFS_STATS_INC(xs_write_calls);
 
-		/*
-		 * direct-io write to a hole: fall through to buffered I/O
-		 * for completing the rest of the request.
-		 */
-		if (ret >= 0 && ret != count) {
-			XFS_STATS_ADD(xs_write_bytes, ret);
+	BUG_ON(iocb->ki_pos != pos);
 
-			pos += ret;
-			count -= ret;
+	ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
+	if (ret)
+		return ret;
 
-			ioflags &= ~IO_ISDIRECT;
-			xfs_iunlock(ip, iolock);
-			goto relock;
-		}
-	} else {
-		int enospc = 0;
-		ssize_t ret2 = 0;
+	if (ocount == 0)
+		return 0;
 
-write_retry:
-		trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, ioflags);
-		ret2 = generic_file_buffered_write(iocb, iovp, nr_segs,
-				pos, &iocb->ki_pos, 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(ip, 0, -1, 0, FI_NONE);
-			if (error)
-				goto out_unlock_internal;
-			enospc = 1;
-			goto write_retry;
-		}
-		ret = ret2;
-	}
+	xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);
 
-	current->backing_dev_info = NULL;
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
 
-	isize = i_size_read(inode);
-	if (unlikely(ret < 0 && ret != -EFAULT && iocb->ki_pos > isize))
-		iocb->ki_pos = isize;
+	if (unlikely(file->f_flags & O_DIRECT))
+		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos,
+						ocount, &iolock);
+	else
+		ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
+						ocount, &iolock);
 
-	if (iocb->ki_pos > ip->i_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		if (iocb->ki_pos > ip->i_size)
-			ip->i_size = iocb->ki_pos;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
+	xfs_aio_write_isize_update(inode, &iocb->ki_pos, ret);
 
-	error = -ret;
 	if (ret <= 0)
-		goto out_unlock_internal;
-
-	XFS_STATS_ADD(xs_write_bytes, ret);
+		goto out_unlock;
 
 	/* Handle various SYNC-type writes */
 	if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
 		loff_t end = pos + ret - 1;
-		int error2;
-
-		xfs_iunlock(ip, iolock);
-		if (need_i_mutex)
-			mutex_unlock(&inode->i_mutex);
+		int error, error2;
 
-		error2 = filemap_write_and_wait_range(mapping, pos, end);
-		if (!error)
-			error = error2;
-		if (need_i_mutex)
-			mutex_lock(&inode->i_mutex);
-		xfs_ilock(ip, iolock);
+		xfs_rw_iunlock(ip, iolock);
+		error = filemap_write_and_wait_range(mapping, pos, end);
+		xfs_rw_ilock(ip, iolock);
 
 		error2 = -xfs_file_fsync(file,
 					 (file->f_flags & __O_SYNC) ? 0 : 1);
-		if (!error)
-			error = error2;
+		if (error)
+			ret = error;
+		else if (error2)
+			ret = error2;
 	}
 
- out_unlock_internal:
-	if (ip->i_new_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		ip->i_new_size = 0;
-		/*
-		 * If this was a direct or synchronous I/O that failed (such
-		 * as ENOSPC) then part of the I/O may have been written to
-		 * disk before the error occured.  In this case the on-disk
-		 * file size may have been adjusted beyond the in-memory file
-		 * size and now needs to be truncated back.
-		 */
-		if (ip->i_d.di_size > ip->i_size)
-			ip->i_d.di_size = ip->i_size;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-	xfs_iunlock(ip, iolock);
- out_unlock_mutex:
-	if (need_i_mutex)
-		mutex_unlock(&inode->i_mutex);
-	return -error;
+out_unlock:
+	xfs_aio_write_newsize_update(ip);
+	xfs_rw_iunlock(ip, iolock);
+	return ret;
 }
 
 STATIC int
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index ad442d9..b06ede1 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -39,6 +39,7 @@
 #include "xfs_dfrag.h"
 #include "xfs_fsops.h"
 #include "xfs_vnodeops.h"
+#include "xfs_discard.h"
 #include "xfs_quota.h"
 #include "xfs_inode_item.h"
 #include "xfs_export.h"
@@ -1294,6 +1295,8 @@ xfs_file_ioctl(
 	trace_xfs_file_ioctl(ip);
 
 	switch (cmd) {
+	case FITRIM:
+		return xfs_ioc_trim(mp, arg);
 	case XFS_IOC_ALLOCSP:
 	case XFS_IOC_FREESP:
 	case XFS_IOC_RESVSP:
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index bd07f73..9731898 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1414,7 +1414,7 @@ xfs_fs_freeze(
 
 	xfs_save_resvblks(mp);
 	xfs_quiesce_attr(mp);
-	return -xfs_fs_log_dummy(mp, SYNC_WAIT);
+	return -xfs_fs_log_dummy(mp);
 }
 
 STATIC int
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index a02480d..e22f005 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -362,7 +362,7 @@ xfs_quiesce_data(
 
 	/* mark the log as covered if needed */
 	if (xfs_log_need_covered(mp))
-		error2 = xfs_fs_log_dummy(mp, SYNC_WAIT);
+		error2 = xfs_fs_log_dummy(mp);
 
 	/* flush data-only devices */
 	if (mp->m_rtdev_targp)
@@ -503,13 +503,14 @@ xfs_sync_worker(
 	int		error;
 
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-		xfs_log_force(mp, 0);
-		xfs_reclaim_inodes(mp, 0);
 		/* dgc: errors ignored here */
-		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
 		if (mp->m_super->s_frozen == SB_UNFROZEN &&
 		    xfs_log_need_covered(mp))
-			error = xfs_fs_log_dummy(mp, 0);
+			error = xfs_fs_log_dummy(mp);
+		else
+			xfs_log_force(mp, 0);
+		xfs_reclaim_inodes(mp, 0);
+		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
 	}
 	mp->m_sync_seq++;
 	wake_up(&mp->m_wait_single_sync_task);
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index 7bb5092..ee3cee0 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -18,6 +18,7 @@
 #include "xfs.h"
 #include <linux/sysctl.h>
 #include <linux/proc_fs.h>
+#include "xfs_error.h"
 
 static struct ctl_table_header *xfs_table_header;
 
@@ -51,6 +52,26 @@ xfs_stats_clear_proc_handler(
 
 	return ret;
 }
+
+STATIC int
+xfs_panic_mask_proc_handler(
+	ctl_table	*ctl,
+	int		write,
+	void		__user *buffer,
+	size_t		*lenp,
+	loff_t		*ppos)
+{
+	int		ret, *valp = ctl->data;
+
+	ret = proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+	if (!ret && write) {
+		xfs_panic_mask = *valp;
+#ifdef DEBUG
+		xfs_panic_mask |= (XFS_PTAG_SHUTDOWN_CORRUPT | XFS_PTAG_LOGRES);
+#endif
+	}
+	return ret;
+}
 #endif /* CONFIG_PROC_FS */
 
 static ctl_table xfs_table[] = {
@@ -77,7 +98,7 @@ static ctl_table xfs_table[] = {
 		.data		= &xfs_params.panic_mask.val,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= xfs_panic_mask_proc_handler,
 		.extra1		= &xfs_params.panic_mask.min,
 		.extra2		= &xfs_params.panic_mask.max
 	},
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index 647af2a..2d0bcb4 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -1759,6 +1759,39 @@ DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_recover);
 DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_cancel);
 DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_skip);
 
+DECLARE_EVENT_CLASS(xfs_discard_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 xfs_agblock_t agbno, xfs_extlen_t len),
+	TP_ARGS(mp, agno, agbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->agbno = agbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u len %u\n",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len)
+)
+
+#define DEFINE_DISCARD_EVENT(name) \
+DEFINE_EVENT(xfs_discard_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 xfs_agblock_t agbno, xfs_extlen_t len), \
+	TP_ARGS(mp, agno, agbno, len))
+DEFINE_DISCARD_EVENT(xfs_discard_extent);
+DEFINE_DISCARD_EVENT(xfs_discard_toosmall);
+DEFINE_DISCARD_EVENT(xfs_discard_exclude);
+DEFINE_DISCARD_EVENT(xfs_discard_busy);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH