Merge commit 'linus/master' into merge-linus

Conflicts:

	arch/x86/kvm/i8254.c

10 files changed, 136 insertions, 142 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index f42f80a..a44d68e 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1338,6 +1338,10 @@ __xfs_get_blocks(
 	offset = (xfs_off_t)iblock << inode->i_blkbits;
 	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
 	size = bh_result->b_size;
+
+	if (!create && direct && offset >= i_size_read(inode))
+		return 0;
+
 	error = xfs_iomap(XFS_I(inode), offset, size,
 			     create ? flags : BMAPI_READ, &iomap, &niomap);
 	if (error)
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 986061a..36d5fcd 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1001,12 +1001,13 @@ xfs_buf_iodone_work(
 	 * We can get an EOPNOTSUPP to ordered writes.  Here we clear the
 	 * ordered flag and reissue them.  Because we can't tell the higher
 	 * layers directly that they should not issue ordered I/O anymore, they
-	 * need to check if the ordered flag was cleared during I/O completion.
+	 * need to check if the _XFS_BARRIER_FAILED flag was set during I/O completion.
 	 */
 	if ((bp->b_error == EOPNOTSUPP) &&
 	    (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) {
 		XB_TRACE(bp, "ordered_retry", bp->b_iodone);
 		bp->b_flags &= ~XBF_ORDERED;
+		bp->b_flags |= _XFS_BARRIER_FAILED;
 		xfs_buf_iorequest(bp);
 	} else if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index fe01099..456519a 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -85,6 +85,14 @@ typedef enum {
 	 * modifications being lost.
 	 */
 	_XBF_PAGE_LOCKED = (1 << 22),
+
+	/*
+	 * If we try a barrier write, but it fails we have to communicate
+	 * this to the upper layers.  Unfortunately b_error gets overwritten
+	 * when the buffer is re-issued so we have to add another flag to
+	 * keep this information.
+	 */
+	_XFS_BARRIER_FAILED = (1 << 23),
 } xfs_buf_flags_t;
 
 typedef enum {
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 73c65f1..e390136 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -158,7 +158,7 @@ enum {
 	Opt_barrier, Opt_nobarrier, Opt_err
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
 	{Opt_barrier, "barrier"},
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_err, NULL}
@@ -1302,9 +1302,29 @@ xfs_fs_remount(
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
 			break;
 		default:
+			/*
+			 * Logically we would return an error here to prevent
+			 * users from believing they might have changed
+			 * mount options using remount which can't be changed.
+			 *
+			 * But unfortunately mount(8) adds all options from
+			 * mtab and fstab to the mount arguments in some cases
+			 * so we can't blindly reject options, but have to
+			 * check for each specified option if it actually
+			 * differs from the currently set option and only
+			 * reject it if that's the case.
+			 *
+			 * Until that is implemented we return success for
+			 * every remount request, and silently ignore all
+			 * options that we can't actually change.
+			 */
+#if 0
 			printk(KERN_INFO
 	"XFS: mount option \"%s\" not supported for remount\n", p);
 			return -EINVAL;
+#else
+			break;
+#endif
 		}
 	}
 
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 608c30c..002fc26 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -732,6 +732,7 @@ xfs_buf_item_init(
 	bip->bli_item.li_ops = &xfs_buf_item_ops;
 	bip->bli_item.li_mountp = mp;
 	bip->bli_buf = bp;
+	xfs_buf_hold(bp);
 	bip->bli_format.blf_type = XFS_LI_BUF;
 	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
 	bip->bli_format.blf_len = (ushort)BTOBB(XFS_BUF_COUNT(bp));
@@ -867,6 +868,21 @@ xfs_buf_item_dirty(
 	return (bip->bli_flags & XFS_BLI_DIRTY);
 }
 
+STATIC void
+xfs_buf_item_free(
+	xfs_buf_log_item_t	*bip)
+{
+#ifdef XFS_TRANS_DEBUG
+	kmem_free(bip->bli_orig);
+	kmem_free(bip->bli_logged);
+#endif /* XFS_TRANS_DEBUG */
+
+#ifdef XFS_BLI_TRACE
+	ktrace_free(bip->bli_trace);
+#endif
+	kmem_zone_free(xfs_buf_item_zone, bip);
+}
+
 /*
  * This is called when the buf log item is no longer needed.  It should
  * free the buf log item associated with the given buffer and clear
@@ -887,18 +903,8 @@ xfs_buf_item_relse(
 	    (XFS_BUF_IODONE_FUNC(bp) != NULL)) {
 		XFS_BUF_CLR_IODONE_FUNC(bp);
 	}
-
-#ifdef XFS_TRANS_DEBUG
-	kmem_free(bip->bli_orig);
-	bip->bli_orig = NULL;
-	kmem_free(bip->bli_logged);
-	bip->bli_logged = NULL;
-#endif /* XFS_TRANS_DEBUG */
-
-#ifdef XFS_BLI_TRACE
-	ktrace_free(bip->bli_trace);
-#endif
-	kmem_zone_free(xfs_buf_item_zone, bip);
+	xfs_buf_rele(bp);
+	xfs_buf_item_free(bip);
 }
 
 
@@ -1120,6 +1126,7 @@ xfs_buf_iodone(
 
 	ASSERT(bip->bli_buf == bp);
 
+	xfs_buf_rele(bp);
 	mp = bip->bli_item.li_mountp;
 
 	/*
@@ -1136,18 +1143,7 @@ xfs_buf_iodone(
 	 * xfs_trans_delete_ail() drops the AIL lock.
 	 */
 	xfs_trans_delete_ail(mp, (xfs_log_item_t *)bip);
-
-#ifdef XFS_TRANS_DEBUG
-	kmem_free(bip->bli_orig);
-	bip->bli_orig = NULL;
-	kmem_free(bip->bli_logged);
-	bip->bli_logged = NULL;
-#endif /* XFS_TRANS_DEBUG */
-
-#ifdef XFS_BLI_TRACE
-	ktrace_free(bip->bli_trace);
-#endif
-	kmem_zone_free(xfs_buf_item_zone, bip);
+	xfs_buf_item_free(bip);
 }
 
 #if defined(XFS_BLI_TRACE)
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 760f4c5..75b0cd4 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -149,7 +149,14 @@ xfs_swap_extents(
 
 	sbp = &sxp->sx_stat;
 
-	xfs_lock_two_inodes(ip, tip, lock_flags);
+	/*
+	 * we have to do two separate lock calls here to keep lockdep
+	 * happy. If we try to get all the locks in one call, lock will
+	 * report false positives when we drop the ILOCK and regain them
+	 * below.
+	 */
+	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
+	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
 	locked = 1;
 
 	/* Verify that both files have the same format */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 00e80df..dbd9cef 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -4118,7 +4118,7 @@ xfs_iext_indirect_to_direct(
 	ASSERT(nextents <= XFS_LINEAR_EXTS);
 	size = nextents * sizeof(xfs_bmbt_rec_t);
 
-	xfs_iext_irec_compact_full(ifp);
+	xfs_iext_irec_compact_pages(ifp);
 	ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ);
 
 	ep = ifp->if_u1.if_ext_irec->er_extbuf;
@@ -4449,8 +4449,7 @@ xfs_iext_irec_remove(
  * compaction policy is as follows:
  *
  *    Full Compaction: Extents fit into a single page (or inline buffer)
- *    Full Compaction: Extents occupy less than 10% of allocated space
- * Partial Compaction: Extents occupy > 10% and < 50% of allocated space
+ * Partial Compaction: Extents occupy less than 50% of allocated space
  *      No Compaction: Extents occupy at least 50% of allocated space
  */
 void
@@ -4471,8 +4470,6 @@ xfs_iext_irec_compact(
 		xfs_iext_direct_to_inline(ifp, nextents);
 	} else if (nextents <= XFS_LINEAR_EXTS) {
 		xfs_iext_indirect_to_direct(ifp);
-	} else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 3) {
-		xfs_iext_irec_compact_full(ifp);
 	} else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 1) {
 		xfs_iext_irec_compact_pages(ifp);
 	}
@@ -4496,7 +4493,7 @@ xfs_iext_irec_compact_pages(
 		erp_next = erp + 1;
 		if (erp_next->er_extcount <=
 		    (XFS_LINEAR_EXTS - erp->er_extcount)) {
-			memmove(&erp->er_extbuf[erp->er_extcount],
+			memcpy(&erp->er_extbuf[erp->er_extcount],
 				erp_next->er_extbuf, erp_next->er_extcount *
 				sizeof(xfs_bmbt_rec_t));
 			erp->er_extcount += erp_next->er_extcount;
@@ -4516,91 +4513,6 @@ xfs_iext_irec_compact_pages(
 }
 
 /*
- * Fully compact the extent records managed by the indirection array.
- */
-void
-xfs_iext_irec_compact_full(
-	xfs_ifork_t	*ifp)			/* inode fork pointer */
-{
-	xfs_bmbt_rec_host_t *ep, *ep_next;	/* extent record pointers */
-	xfs_ext_irec_t	*erp, *erp_next;	/* extent irec pointers */
-	int		erp_idx = 0;		/* extent irec index */
-	int		ext_avail;		/* empty entries in ex list */
-	int		ext_diff;		/* number of exts to add */
-	int		nlists;			/* number of irec's (ex lists) */
-
-	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
-
-	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-	erp = ifp->if_u1.if_ext_irec;
-	ep = &erp->er_extbuf[erp->er_extcount];
-	erp_next = erp + 1;
-	ep_next = erp_next->er_extbuf;
-
-	while (erp_idx < nlists - 1) {
-		/*
-		 * Check how many extent records are available in this irec.
-		 * If there is none skip the whole exercise.
-		 */
-		ext_avail = XFS_LINEAR_EXTS - erp->er_extcount;
-		if (ext_avail) {
-
-			/*
-			 * Copy over as many as possible extent records into
-			 * the previous page.
-			 */
-			ext_diff = MIN(ext_avail, erp_next->er_extcount);
-			memcpy(ep, ep_next, ext_diff * sizeof(xfs_bmbt_rec_t));
-			erp->er_extcount += ext_diff;
-			erp_next->er_extcount -= ext_diff;
-
-			/*
-			 * If the next irec is empty now we can simply
-			 * remove it.
-			 */
-			if (erp_next->er_extcount == 0) {
-				/*
-				 * Free page before removing extent record
-				 * so er_extoffs don't get modified in
-				 * xfs_iext_irec_remove.
-				 */
-				kmem_free(erp_next->er_extbuf);
-				erp_next->er_extbuf = NULL;
-				xfs_iext_irec_remove(ifp, erp_idx + 1);
-				erp = &ifp->if_u1.if_ext_irec[erp_idx];
-				nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-
-			/*
-			 * If the next irec is not empty move up the content
-			 * that has not been copied to the previous page to
-			 * the beggining of this one.
-			 */
-			} else {
-				memmove(erp_next->er_extbuf, &ep_next[ext_diff],
-					erp_next->er_extcount *
-					sizeof(xfs_bmbt_rec_t));
-				ep_next = erp_next->er_extbuf;
-				memset(&ep_next[erp_next->er_extcount], 0,
-					(XFS_LINEAR_EXTS -
-						erp_next->er_extcount) *
-					sizeof(xfs_bmbt_rec_t));
-			}
-		}
-
-		if (erp->er_extcount == XFS_LINEAR_EXTS) {
-			erp_idx++;
-			if (erp_idx < nlists)
-				erp = &ifp->if_u1.if_ext_irec[erp_idx];
-			else
-				break;
-		}
-		ep = &erp->er_extbuf[erp->er_extcount];
-		erp_next = erp + 1;
-		ep_next = erp_next->er_extbuf;
-	}
-}
-
-/*
  * This is called to update the er_extoff field in the indirection
  * array when extents have been added or removed from one of the
  * extent lists. erp_idx contains the irec index to begin updating
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ccba14e..0b02c64 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -124,16 +124,27 @@ STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
 STATIC int	xlog_iclogs_empty(xlog_t *log);
 
 #if defined(XFS_LOG_TRACE)
+
+#define XLOG_TRACE_LOGGRANT_SIZE	2048
+#define XLOG_TRACE_ICLOG_SIZE		256
+
+void
+xlog_trace_loggrant_alloc(xlog_t *log)
+{
+	log->l_grant_trace = ktrace_alloc(XLOG_TRACE_LOGGRANT_SIZE, KM_NOFS);
+}
+
+void
+xlog_trace_loggrant_dealloc(xlog_t *log)
+{
+	ktrace_free(log->l_grant_trace);
+}
+
 void
 xlog_trace_loggrant(xlog_t *log, xlog_ticket_t *tic, xfs_caddr_t string)
 {
 	unsigned long cnts;
 
-	if (!log->l_grant_trace) {
-		log->l_grant_trace = ktrace_alloc(2048, KM_NOSLEEP);
-		if (!log->l_grant_trace)
-			return;
-	}
 	/* ticket counts are 1 byte each */
 	cnts = ((unsigned long)tic->t_ocnt) | ((unsigned long)tic->t_cnt) << 8;
 
@@ -157,10 +168,20 @@ xlog_trace_loggrant(xlog_t *log, xlog_ticket_t *tic, xfs_caddr_t string)
 }
 
 void
+xlog_trace_iclog_alloc(xlog_in_core_t *iclog)
+{
+	iclog->ic_trace = ktrace_alloc(XLOG_TRACE_ICLOG_SIZE, KM_NOFS);
+}
+
+void
+xlog_trace_iclog_dealloc(xlog_in_core_t *iclog)
+{
+	ktrace_free(iclog->ic_trace);
+}
+
+void
 xlog_trace_iclog(xlog_in_core_t *iclog, uint state)
 {
-	if (!iclog->ic_trace)
-		iclog->ic_trace = ktrace_alloc(256, KM_NOFS);
 	ktrace_enter(iclog->ic_trace,
 		     (void *)((unsigned long)state),
 		     (void *)((unsigned long)current_pid()),
@@ -170,8 +191,15 @@ xlog_trace_iclog(xlog_in_core_t *iclog, uint state)
 		     (void *)NULL, (void *)NULL);
 }
 #else
+
+#define	xlog_trace_loggrant_alloc(log)
+#define	xlog_trace_loggrant_dealloc(log)
 #define	xlog_trace_loggrant(log,tic,string)
+
+#define	xlog_trace_iclog_alloc(iclog)
+#define	xlog_trace_iclog_dealloc(iclog)
 #define	xlog_trace_iclog(iclog,state)
+
 #endif /* XFS_LOG_TRACE */
 
 
@@ -1005,11 +1033,12 @@ xlog_iodone(xfs_buf_t *bp)
 	l = iclog->ic_log;
 
 	/*
-	 * If the ordered flag has been removed by a lower
-	 * layer, it means the underlyin device no longer supports
+	 * If the _XFS_BARRIER_FAILED flag was set by a lower
+	 * layer, it means the underlying device no longer supports
 	 * barrier I/O. Warn loudly and turn off barriers.
 	 */
-	if ((l->l_mp->m_flags & XFS_MOUNT_BARRIER) && !XFS_BUF_ORDERED(bp)) {
+	if (bp->b_flags & _XFS_BARRIER_FAILED) {
+		bp->b_flags &= ~_XFS_BARRIER_FAILED;
 		l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER;
 		xfs_fs_cmn_err(CE_WARN, l->l_mp,
 				"xlog_iodone: Barriers are no longer supported"
@@ -1231,6 +1260,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	spin_lock_init(&log->l_grant_lock);
 	sv_init(&log->l_flush_wait, 0, "flush_wait");
 
+	xlog_trace_loggrant_alloc(log);
 	/* log record size must be multiple of BBSIZE; see xlog_rec_header_t */
 	ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0);
 
@@ -1285,6 +1315,8 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		sv_init(&iclog->ic_force_wait, SV_DEFAULT, "iclog-force");
 		sv_init(&iclog->ic_write_wait, SV_DEFAULT, "iclog-write");
 
+		xlog_trace_iclog_alloc(iclog);
+
 		iclogp = &iclog->ic_next;
 	}
 	*iclogp = log->l_iclog;			/* complete ring */
@@ -1565,11 +1597,7 @@ xlog_dealloc_log(xlog_t *log)
 		sv_destroy(&iclog->ic_force_wait);
 		sv_destroy(&iclog->ic_write_wait);
 		xfs_buf_free(iclog->ic_bp);
-#ifdef XFS_LOG_TRACE
-		if (iclog->ic_trace != NULL) {
-			ktrace_free(iclog->ic_trace);
-		}
-#endif
+		xlog_trace_iclog_dealloc(iclog);
 		next_iclog = iclog->ic_next;
 		kmem_free(iclog);
 		iclog = next_iclog;
@@ -1578,14 +1606,7 @@ xlog_dealloc_log(xlog_t *log)
 	spinlock_destroy(&log->l_grant_lock);
 
 	xfs_buf_free(log->l_xbuf);
-#ifdef XFS_LOG_TRACE
-	if (log->l_trace != NULL) {
-		ktrace_free(log->l_trace);
-	}
-	if (log->l_grant_trace != NULL) {
-		ktrace_free(log->l_grant_trace);
-	}
-#endif
+	xlog_trace_loggrant_dealloc(log);
 	log->l_mp->m_log = NULL;
 	kmem_free(log);
 }	/* xlog_dealloc_log */
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index c8a5b22..e7d8f84 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -448,7 +448,6 @@ typedef struct log {
 	int			l_grant_write_bytes;
 
 #ifdef XFS_LOG_TRACE
-	struct ktrace		*l_trace;
 	struct ktrace		*l_grant_trace;
 #endif
 
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index aa238c8..8b6812f 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -1838,6 +1838,12 @@ again:
 #endif
 }
 
+/*
+ * xfs_lock_two_inodes() can only be used to lock one type of lock
+ * at a time - the iolock or the ilock, but not both at once. If
+ * we lock both at once, lockdep will report false positives saying
+ * we have violated locking orders.
+ */
 void
 xfs_lock_two_inodes(
 	xfs_inode_t		*ip0,
@@ -1848,6 +1854,8 @@ xfs_lock_two_inodes(
 	int			attempts = 0;
 	xfs_log_item_t		*lp;
 
+	if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
+		ASSERT((lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) == 0);
 	ASSERT(ip0->i_ino != ip1->i_ino);
 
 	if (ip0->i_ino > ip1->i_ino) {
@@ -3152,6 +3160,13 @@ error1:	/* Just cancel transaction */
 /*
  * Zero file bytes between startoff and endoff inclusive.
  * The iolock is held exclusive and no blocks are buffered.
+ *
+ * This function is used by xfs_free_file_space() to zero
+ * partial blocks when the range to free is not block aligned.
+ * When unreserving space with boundaries that are not block
+ * aligned we round up the start and round down the end
+ * boundaries and then use this function to zero the parts of
+ * the blocks that got dropped during the rounding.
  */
 STATIC int
 xfs_zero_remaining_bytes(
@@ -3168,6 +3183,17 @@ xfs_zero_remaining_bytes(
 	int			nimap;
 	int			error = 0;
 
+	/*
+	 * Avoid doing I/O beyond eof - it's not necessary
+	 * since nothing can read beyond eof.  The space will
+	 * be zeroed when the file is extended anyway.
+	 */
+	if (startoff >= ip->i_size)
+		return 0;
+
+	if (endoff > ip->i_size)
+		endoff = ip->i_size;
+
 	bp = xfs_buf_get_noaddr(mp->m_sb.sb_blocksize,
 				XFS_IS_REALTIME_INODE(ip) ?
 				mp->m_rtdev_targp : mp->m_ddev_targp);