Merge kernel.org linux-3.0.y into HEAD

13 files changed, 126 insertions, 50 deletions

diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index f55ae23..790fa63 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -392,10 +392,12 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 		ino->flags |= AUTOFS_INF_PENDING;
 		spin_unlock(&sbi->fs_lock);
 		status = autofs4_mount_wait(dentry);
-		if (status)
-			return ERR_PTR(status);
 		spin_lock(&sbi->fs_lock);
 		ino->flags &= ~AUTOFS_INF_PENDING;
+		if (status) {
+			spin_unlock(&sbi->fs_lock);
+			return ERR_PTR(status);
+		}
 	}
 done:
 	if (!(ino->flags & AUTOFS_INF_EXPIRING)) {
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index f67b687..a080779 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -84,7 +84,7 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
  * FIXME: we should try harder by querying the mds for the ino.
  */
 static struct dentry *__fh_to_dentry(struct super_block *sb,
-				     struct ceph_nfs_fh *fh)
+				     struct ceph_nfs_fh *fh, int fh_len)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
@@ -92,6 +92,9 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 	struct ceph_vino vino;
 	int err;
 
+	if (fh_len < sizeof(*fh) / 4)
+		return ERR_PTR(-ESTALE);
+
 	dout("__fh_to_dentry %llx\n", fh->ino);
 	vino.ino = fh->ino;
 	vino.snap = CEPH_NOSNAP;
@@ -136,7 +139,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
  * convert connectable fh to dentry
  */
 static struct dentry *__cfh_to_dentry(struct super_block *sb,
-				      struct ceph_nfs_confh *cfh)
+				      struct ceph_nfs_confh *cfh, int fh_len)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
@@ -144,6 +147,9 @@ static struct dentry *__cfh_to_dentry(struct super_block *sb,
 	struct ceph_vino vino;
 	int err;
 
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
+
 	dout("__cfh_to_dentry %llx (%llx/%x)\n",
 	     cfh->ino, cfh->parent_ino, cfh->parent_name_hash);
 
@@ -193,9 +199,11 @@ static struct dentry *ceph_fh_to_dentry(struct super_block *sb, struct fid *fid,
 					int fh_len, int fh_type)
 {
 	if (fh_type == 1)
-		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw);
+		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw,
+								fh_len);
 	else
-		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw);
+		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw,
+								fh_len);
 }
 
 /*
@@ -216,6 +224,8 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
 
 	if (fh_type == 1)
 		return ERR_PTR(-ESTALE);
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
 
 	pr_debug("fh_to_parent %llx/%d\n", cfh->parent_ino,
 		 cfh->parent_name_hash);
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 61abb63..3deb58d 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -208,6 +208,8 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd,
 
 	err  = get_user(palp, &up->palette);
 	err |= get_user(length, &up->length);
+	if (err)
+		return -EFAULT;
 
 	up_native = compat_alloc_user_space(sizeof(struct video_spu_palette));
 	err  = put_user(compat_ptr(palp), &up_native->palette);
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index fe9945f..5235d6e 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -167,6 +167,8 @@ static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
 	case GFS2_SMALL_FH_SIZE:
 	case GFS2_LARGE_FH_SIZE:
 	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_SMALL_FH_SIZE)
+			return NULL;
 		this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
 		this.no_formal_ino |= be32_to_cpu(fh[1]);
 		this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
@@ -186,6 +188,8 @@ static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid,
 	switch (fh_type) {
 	case GFS2_LARGE_FH_SIZE:
 	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_LARGE_FH_SIZE)
+			return NULL;
 		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
 		parent.no_formal_ino |= be32_to_cpu(fh[5]);
 		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index dd4687f..516eb21 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -179,7 +179,7 @@ static struct dentry *isofs_fh_to_parent(struct super_block *sb,
 {
 	struct isofs_fid *ifid = (struct isofs_fid *)fid;
 
-	if (fh_type != 2)
+	if (fh_len < 2 || fh_type != 2)
 		return NULL;
 
 	return isofs_export_iget(sb,
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 72ffa97..dcd23f8 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -85,7 +85,12 @@ nope:
 static void release_data_buffer(struct buffer_head *bh)
 {
 	if (buffer_freed(bh)) {
+		WARN_ON_ONCE(buffer_dirty(bh));
 		clear_buffer_freed(bh);
+		clear_buffer_mapped(bh);
+		clear_buffer_new(bh);
+		clear_buffer_req(bh);
+		bh->b_bdev = NULL;
 		release_buffer_page(bh);
 	} else
 		put_bh(bh);
@@ -840,17 +845,35 @@ restart_loop:
 		 * there's no point in keeping a checkpoint record for
 		 * it. */
 
-		/* A buffer which has been freed while still being
-		 * journaled by a previous transaction may end up still
-		 * being dirty here, but we want to avoid writing back
-		 * that buffer in the future after the "add to orphan"
-		 * operation been committed,  That's not only a performance
-		 * gain, it also stops aliasing problems if the buffer is
-		 * left behind for writeback and gets reallocated for another
-		 * use in a different page. */
-		if (buffer_freed(bh) && !jh->b_next_transaction) {
-			clear_buffer_freed(bh);
-			clear_buffer_jbddirty(bh);
+		/*
+		 * A buffer which has been freed while still being journaled by
+		 * a previous transaction.
+		 */
+		if (buffer_freed(bh)) {
+			/*
+			 * If the running transaction is the one containing
+			 * "add to orphan" operation (b_next_transaction !=
+			 * NULL), we have to wait for that transaction to
+			 * commit before we can really get rid of the buffer.
+			 * So just clear b_modified to not confuse transaction
+			 * credit accounting and refile the buffer to
+			 * BJ_Forget of the running transaction. If the just
+			 * committed transaction contains "add to orphan"
+			 * operation, we can completely invalidate the buffer
+			 * now. We are rather throughout in that since the
+			 * buffer may be still accessible when blocksize <
+			 * pagesize and it is attached to the last partial
+			 * page.
+			 */
+			jh->b_modified = 0;
+			if (!jh->b_next_transaction) {
+				clear_buffer_freed(bh);
+				clear_buffer_jbddirty(bh);
+				clear_buffer_mapped(bh);
+				clear_buffer_new(bh);
+				clear_buffer_req(bh);
+				bh->b_bdev = NULL;
+			}
 		}
 
 		if (buffer_jbddirty(bh)) {
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index f7ee81a..b0161a6 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1837,15 +1837,16 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
  * We're outside-transaction here.  Either or both of j_running_transaction
  * and j_committing_transaction may be NULL.
  */
-static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
+static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
+				int partial_page)
 {
 	transaction_t *transaction;
 	struct journal_head *jh;
 	int may_free = 1;
-	int ret;
 
 	BUFFER_TRACE(bh, "entry");
 
+retry:
 	/*
 	 * It is safe to proceed here without the j_list_lock because the
 	 * buffers cannot be stolen by try_to_free_buffers as long as we are
@@ -1873,10 +1874,18 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 	 * clear the buffer dirty bit at latest at the moment when the
 	 * transaction marking the buffer as freed in the filesystem
 	 * structures is committed because from that moment on the
-	 * buffer can be reallocated and used by a different page.
+	 * block can be reallocated and used by a different page.
 	 * Since the block hasn't been freed yet but the inode has
 	 * already been added to orphan list, it is safe for us to add
 	 * the buffer to BJ_Forget list of the newest transaction.
+	 *
+	 * Also we have to clear buffer_mapped flag of a truncated buffer
+	 * because the buffer_head may be attached to the page straddling
+	 * i_size (can happen only when blocksize < pagesize) and thus the
+	 * buffer_head can be reused when the file is extended again. So we end
+	 * up keeping around invalidated buffers attached to transactions'
+	 * BJ_Forget list just to stop checkpointing code from cleaning up
+	 * the transaction this buffer was modified in.
 	 */
 	transaction = jh->b_transaction;
 	if (transaction == NULL) {
@@ -1903,13 +1912,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 			 * committed, the buffer won't be needed any
 			 * longer. */
 			JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
-			ret = __dispose_buffer(jh,
+			may_free = __dispose_buffer(jh,
 					journal->j_running_transaction);
-			journal_put_journal_head(jh);
-			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
-			spin_unlock(&journal->j_state_lock);
-			return ret;
+			goto zap_buffer;
 		} else {
 			/* There is no currently-running transaction. So the
 			 * orphan record which we wrote for this file must have
@@ -1917,13 +1922,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 			 * the committing transaction, if it exists. */
 			if (journal->j_committing_transaction) {
 				JBUFFER_TRACE(jh, "give to committing trans");
-				ret = __dispose_buffer(jh,
+				may_free = __dispose_buffer(jh,
 					journal->j_committing_transaction);
-				journal_put_journal_head(jh);
-				spin_unlock(&journal->j_list_lock);
-				jbd_unlock_bh_state(bh);
-				spin_unlock(&journal->j_state_lock);
-				return ret;
+				goto zap_buffer;
 			} else {
 				/* The orphan record's transaction has
 				 * committed.  We can cleanse this buffer */
@@ -1944,10 +1945,24 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 		}
 		/*
 		 * The buffer is committing, we simply cannot touch
-		 * it. So we just set j_next_transaction to the
-		 * running transaction (if there is one) and mark
-		 * buffer as freed so that commit code knows it should
-		 * clear dirty bits when it is done with the buffer.
+		 * it. If the page is straddling i_size we have to wait
+		 * for commit and try again.
+		 */
+		if (partial_page) {
+			tid_t tid = journal->j_committing_transaction->t_tid;
+
+			journal_put_journal_head(jh);
+			spin_unlock(&journal->j_list_lock);
+			jbd_unlock_bh_state(bh);
+			spin_unlock(&journal->j_state_lock);
+			log_wait_commit(journal, tid);
+			goto retry;
+		}
+		/*
+		 * OK, buffer won't be reachable after truncate. We just set
+		 * j_next_transaction to the running transaction (if there is
+		 * one) and mark buffer as freed so that commit code knows it
+		 * should clear dirty bits when it is done with the buffer.
 		 */
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
@@ -1970,6 +1985,14 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
 	}
 
 zap_buffer:
+	/*
+	 * This is tricky. Although the buffer is truncated, it may be reused
+	 * if blocksize < pagesize and it is attached to the page straddling
+	 * EOF. Since the buffer might have been added to BJ_Forget list of the
+	 * running transaction, journal_get_write_access() won't clear
+	 * b_modified and credit accounting gets confused. So clear b_modified
+	 * here. */
+	jh->b_modified = 0;
 	journal_put_journal_head(jh);
 zap_buffer_no_jh:
 	spin_unlock(&journal->j_list_lock);
@@ -2018,7 +2041,8 @@ void journal_invalidatepage(journal_t *journal,
 		if (offset <= curr_off) {
 			/* This block is wholly outside the truncation point */
 			lock_buffer(bh);
-			may_free &= journal_unmap_buffer(journal, bh);
+			may_free &= journal_unmap_buffer(journal, bh,
+							 offset > 0);
 			unlock_buffer(bh);
 		}
 		curr_off = next_off;
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 36057ce..6e2a2d5 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -223,7 +223,7 @@ static void encode_nlm_stat(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	BUG_ON(be32_to_cpu(stat) > NLM_LCK_DENIED_GRACE_PERIOD);
+	WARN_ON_ONCE(be32_to_cpu(stat) > NLM_LCK_DENIED_GRACE_PERIOD);
 	p = xdr_reserve_space(xdr, 4);
 	*p = stat;
 }
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index d27aab1..d413af3 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -67,7 +67,8 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 	/* Obtain file pointer. Not used by FREE_ALL call. */
 	if (filp != NULL) {
-		if ((error = nlm_lookup_file(rqstp, &file, &lock->fh)) != 0)
+		error = cast_status(nlm_lookup_file(rqstp, &file, &lock->fh));
+		if (error != 0)
 			goto no_locks;
 		*filp = file;
 
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 4fd5bb3..0363aa4 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1568,8 +1568,10 @@ struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 			reiserfs_warning(sb, "reiserfs-13077",
 				"nfsd/reiserfs, fhtype=%d, len=%d - odd",
 				fh_type, fh_len);
-		fh_type = 5;
+		fh_type = fh_len;
 	}
+	if (fh_len < 2)
+		return NULL;
 
 	return reiserfs_get_dentry(sb, fid->raw[0], fid->raw[1],
 		(fh_type == 3 || fh_type >= 5) ? fid->raw[2] : 0);
@@ -1578,6 +1580,8 @@ struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid,
 		int fh_len, int fh_type)
 {
+	if (fh_type > fh_len)
+		fh_type = fh_len;
 	if (fh_type < 4)
 		return NULL;
 
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index ea9120a..567b3db 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -404,20 +404,18 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 /**
  *	sysfs_pathname - return full path to sysfs dirent
  *	@sd: sysfs_dirent whose path we want
- *	@path: caller allocated buffer
+ *	@path: caller allocated buffer of size PATH_MAX
  *
  *	Gives the name "/" to the sysfs_root entry; any path returned
  *	is relative to wherever sysfs is mounted.
- *
- *	XXX: does no error checking on @path size
  */
 static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
 {
 	if (sd->s_parent) {
 		sysfs_pathname(sd->s_parent, path);
-		strcat(path, "/");
+		strlcat(path, "/", PATH_MAX);
 	}
-	strcat(path, sd->s_name);
+	strlcat(path, sd->s_name, PATH_MAX);
 	return path;
 }
 
@@ -450,9 +448,11 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 		char *path = kzalloc(PATH_MAX, GFP_KERNEL);
 		WARN(1, KERN_WARNING
 		     "sysfs: cannot create duplicate filename '%s'\n",
-		     (path == NULL) ? sd->s_name :
-		     strcat(strcat(sysfs_pathname(acxt->parent_sd, path), "/"),
-		            sd->s_name));
+		     (path == NULL) ? sd->s_name
+				    : (sysfs_pathname(acxt->parent_sd, path),
+				       strlcat(path, "/", PATH_MAX),
+				       strlcat(path, sd->s_name, PATH_MAX),
+				       path));
 		kfree(path);
 	}
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index a8e867a..b0c7b53 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -1316,6 +1316,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 		udf_error(sb, __func__, "error loading logical volume descriptor: "
 			"Partition table too long (%u > %lu)\n", table_len,
 			sb->s_blocksize - sizeof(*lvd));
+		ret = 1;
 		goto out_bh;
 	}
 
@@ -1360,8 +1361,10 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 						UDF_ID_SPARABLE,
 						strlen(UDF_ID_SPARABLE))) {
 				if (udf_load_sparable_map(sb, map,
-				    (struct sparablePartitionMap *)gpm) < 0)
+				    (struct sparablePartitionMap *)gpm) < 0) {
+					ret = 1;
 					goto out_bh;
+				}
 			} else if (!strncmp(upm2->partIdent.ident,
 						UDF_ID_METADATA,
 						strlen(UDF_ID_METADATA))) {
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index fed3f3c..844b22b 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -195,6 +195,9 @@ xfs_fs_fh_to_parent(struct super_block *sb, struct fid *fid,
 	struct xfs_fid64	*fid64 = (struct xfs_fid64 *)fid;
 	struct inode		*inode = NULL;
 
+	if (fh_len < xfs_fileid_length(fileid_type))
+		return NULL;
+
 	switch (fileid_type) {
 	case FILEID_INO32_GEN_PARENT:
 		inode = xfs_nfs_get_inode(sb, fid->i32.parent_ino,