Merge branch 'master' of /pub/scm/linux/kernel/git/torvalds/linux-2.6

11 files changed, 73 insertions, 33 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 60d27bc..6b61ded 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1560,9 +1560,10 @@ retry_locked:
 		/* NOTE: no side-effects allowed, until we take s_mutex */
 
 		revoking = cap->implemented & ~cap->issued;
-		if (revoking)
-			dout(" mds%d revoking %s\n", cap->mds,
-			     ceph_cap_string(revoking));
+		dout(" mds%d cap %p issued %s implemented %s revoking %s\n",
+		     cap->mds, cap, ceph_cap_string(cap->issued),
+		     ceph_cap_string(cap->implemented),
+		     ceph_cap_string(revoking));
 
 		if (cap == ci->i_auth_cap &&
 		    (cap->issued & CEPH_CAP_FILE_WR)) {
@@ -1658,6 +1659,8 @@ ack:
 
 		if (cap == ci->i_auth_cap && ci->i_dirty_caps)
 			flushing = __mark_caps_flushing(inode, session);
+		else
+			flushing = 0;
 
 		mds = cap->mds;  /* remember mds, so we don't repeat */
 		sent++;
@@ -1940,6 +1943,35 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 	}
 }
 
+static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
+				     struct ceph_mds_session *session,
+				     struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_cap *cap;
+	int delayed = 0;
+
+	spin_lock(&inode->i_lock);
+	cap = ci->i_auth_cap;
+	dout("kick_flushing_inode_caps %p flushing %s flush_seq %lld\n", inode,
+	     ceph_cap_string(ci->i_flushing_caps), ci->i_cap_flush_seq);
+	__ceph_flush_snaps(ci, &session, 1);
+	if (ci->i_flushing_caps) {
+		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+				     __ceph_caps_used(ci),
+				     __ceph_caps_wanted(ci),
+				     cap->issued | cap->implemented,
+				     ci->i_flushing_caps, NULL);
+		if (delayed) {
+			spin_lock(&inode->i_lock);
+			__cap_delay_requeue(mdsc, ci);
+			spin_unlock(&inode->i_lock);
+		}
+	} else {
+		spin_unlock(&inode->i_lock);
+	}
+}
+
 
 /*
  * Take references to capabilities we hold, so that we don't release
@@ -2687,7 +2719,7 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
 	ceph_add_cap(inode, session, cap_id, -1,
 		     issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
 		     NULL /* no caps context */);
-	try_flush_caps(inode, session, NULL);
+	kick_flushing_inode_caps(mdsc, session, inode);
 	up_read(&mdsc->snap_rwsem);
 
 	/* make sure we re-request max_size, if necessary */
@@ -2785,8 +2817,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	case CEPH_CAP_OP_IMPORT:
 		handle_cap_import(mdsc, inode, h, session,
 				  snaptrace, snaptrace_len);
-		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_NODELAY,
-				session);
+		ceph_check_caps(ceph_inode(inode), 0, session);
 		goto done_unlocked;
 	}
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e835eff..5625463 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -710,10 +710,6 @@ static int fill_inode(struct inode *inode,
 			ci->i_ceph_flags |= CEPH_I_COMPLETE;
 			ci->i_max_offset = 2;
 		}
-
-		/* it may be better to set st_size in getattr instead? */
-		if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
-			inode->i_size = ci->i_rbytes;
 		break;
 	default:
 		pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
@@ -1819,7 +1815,11 @@ int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		else
 			stat->dev = 0;
 		if (S_ISDIR(inode->i_mode)) {
-			stat->size = ci->i_rbytes;
+			if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb),
+						RBYTES))
+				stat->size = ci->i_rbytes;
+			else
+				stat->size = ci->i_files + ci->i_subdirs;
 			stat->blocks = 0;
 			stat->blksize = 65536;
 		}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 1e30d19..a1ee8fa 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -693,9 +693,11 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				dout("choose_mds %p %llx.%llx "
 				     "frag %u mds%d (%d/%d)\n",
 				     inode, ceph_vinop(inode),
-				     frag.frag, frag.mds,
+				     frag.frag, mds,
 				     (int)r, frag.ndist);
-				return mds;
+				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+				    CEPH_MDS_STATE_ACTIVE)
+					return mds;
 			}
 
 			/* since this file/dir wasn't known to be
@@ -708,7 +710,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				dout("choose_mds %p %llx.%llx "
 				     "frag %u mds%d (auth)\n",
 				     inode, ceph_vinop(inode), frag.frag, mds);
-				return mds;
+				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+				    CEPH_MDS_STATE_ACTIVE)
+					return mds;
 			}
 		}
 	}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index bf6f0f3..9c50854 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -290,6 +290,8 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 
         fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
         fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+	fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
+	fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
         fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
         fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
         fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 6e12a6b..8c9eba6 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -219,6 +219,7 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
+	int name_len = strlen(name);
 	int c;
 
 	p = &ci->i_xattrs.index.rb_node;
@@ -226,6 +227,8 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 		parent = *p;
 		xattr = rb_entry(parent, struct ceph_inode_xattr, node);
 		c = strncmp(name, xattr->name, xattr->name_len);
+		if (c == 0 && name_len > xattr->name_len)
+			c = 1;
 		if (c < 0)
 			p = &(*p)->rb_left;
 		else if (c > 0)
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 0994f6a7..58fd707 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -704,7 +704,8 @@ skip_mount_setup:
 	sbp[0]->s_state =
 		cpu_to_le16(le16_to_cpu(sbp[0]->s_state) & ~NILFS_VALID_FS);
 	/* synchronize sbp[1] with sbp[0] */
-	memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
+	if (sbp[1])
+		memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
 	return nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
 }
 
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index b572b67..326e747 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -1,7 +1,7 @@
 /**
  * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2006 Anton Altaparmakov
+ * Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -2576,6 +2576,8 @@ mft_rec_already_initialized:
 	flush_dcache_page(page);
 	SetPageUptodate(page);
 	if (base_ni) {
+		MFT_RECORD *m_tmp;
+
 		/*
 		 * Setup the base mft record in the extent mft record.  This
 		 * completes initialization of the allocated extent mft record
@@ -2588,11 +2590,11 @@ mft_rec_already_initialized:
 		 * attach it to the base inode @base_ni and map, pin, and lock
 		 * its, i.e. the allocated, mft record.
 		 */
-		m = map_extent_mft_record(base_ni, bit, &ni);
-		if (IS_ERR(m)) {
+		m_tmp = map_extent_mft_record(base_ni, bit, &ni);
+		if (IS_ERR(m_tmp)) {
 			ntfs_error(vol->sb, "Failed to map allocated extent "
 					"mft record 0x%llx.", (long long)bit);
-			err = PTR_ERR(m);
+			err = PTR_ERR(m_tmp);
 			/* Set the mft record itself not in use. */
 			m->flags &= cpu_to_le16(
 					~le16_to_cpu(MFT_RECORD_IN_USE));
@@ -2603,6 +2605,7 @@ mft_rec_already_initialized:
 			ntfs_unmap_page(page);
 			goto undo_mftbmp_alloc;
 		}
+		BUG_ON(m != m_tmp);
 		/*
 		 * Make sure the allocated mft record is written out to disk.
 		 * No need to set the inode dirty because the caller is going
diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c
index eafc22a..b701eaa 100644
--- a/fs/proc/consoles.c
+++ b/fs/proc/consoles.c
@@ -67,7 +67,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 	struct console *con;
 	loff_t off = 0;
 
-	acquire_console_sem();
+	console_lock();
 	for_each_console(con)
 		if (off++ == *pos)
 			break;
@@ -84,7 +84,7 @@ static void *c_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void c_stop(struct seq_file *m, void *v)
 {
-	release_console_sem();
+	console_unlock();
 }
 
 static const struct seq_operations consoles_op = {
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 2fb2882..8ab48bc 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -63,6 +63,14 @@ static struct buffer_head *get_block_length(struct super_block *sb,
 		*length = (unsigned char) bh->b_data[*offset] |
 			(unsigned char) bh->b_data[*offset + 1] << 8;
 		*offset += 2;
+
+		if (*offset == msblk->devblksize) {
+			put_bh(bh);
+			bh = sb_bread(sb, ++(*cur_index));
+			if (bh == NULL)
+				return NULL;
+			*offset = 0;
+		}
 	}
 
 	return bh;
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index 856756c..c4eb400 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -95,12 +95,6 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 			if (!buffer_uptodate(bh[k]))
 				goto release_mutex;
 
-			if (avail == 0) {
-				offset = 0;
-				put_bh(bh[k++]);
-				continue;
-			}
-
 			stream->buf.in = bh[k]->b_data + offset;
 			stream->buf.in_size = avail;
 			stream->buf.in_pos = 0;
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 818a5e0..4661ae2 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -82,12 +82,6 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 			if (!buffer_uptodate(bh[k]))
 				goto release_mutex;
 
-			if (avail == 0) {
-				offset = 0;
-				put_bh(bh[k++]);
-				continue;
-			}
-
 			stream->next_in = bh[k]->b_data + offset;
 			stream->avail_in = avail;
 			offset = 0;