Merge tag 'v3.2.45' into v3.2-rt

This is the 3.2.45 stable release

15 files changed, 96 insertions, 64 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 3b65ee767ce6..8cdd8ea0f44a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1112,9 +1112,9 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
 	spin_unlock(&info->ring_lock);
 
 out:
-	kunmap_atomic(ring, KM_USER0);
 	dprintk("leaving aio_read_evt: %d  h%lu t%lu\n", ret,
 		 (unsigned long)ring->head, (unsigned long)ring->tail);
+	kunmap_atomic(ring, KM_USER0);
 	return ret;
 }
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 8c10224cddf2..0d4d80703720 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1177,8 +1177,10 @@ void shrink_dcache_parent(struct dentry * parent)
 	LIST_HEAD(dispose);
 	int found;
 
-	while ((found = select_parent(parent, &dispose)) != 0)
+	while ((found = select_parent(parent, &dispose)) != 0) {
 		shrink_dentry_list(&dispose);
+		cond_resched();
+	}
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
 
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 9ed1bb1f319f..5459168d9db0 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -82,4 +82,5 @@ config EXT4_DEBUG
 	  Enables run-time debugging support for the ext4 filesystem.
 
 	  If you select Y here, then you will be able to turn on debugging
-	  with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug"
+	  with a command such as:
+		echo 1 > /sys/module/ext4/parameters/mballoc_debug
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index bb6c7d811313..a8d03a4d3f8b 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -260,8 +260,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
 		needs_barrier = true;
-	jbd2_log_start_commit(journal, commit_tid);
-	ret = jbd2_log_wait_commit(journal, commit_tid);
+	ret = jbd2_complete_transaction(journal, commit_tid);
 	if (needs_barrier)
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
  out:
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3270ffd791fb..025b4b6573d7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -147,8 +147,7 @@ void ext4_evict_inode(struct inode *inode)
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
-			jbd2_log_start_commit(journal, commit_tid);
-			jbd2_log_wait_commit(journal, commit_tid);
+			jbd2_complete_transaction(journal, commit_tid);
 			filemap_write_and_wait(&inode->i_data);
 		}
 		truncate_inode_pages(&inode->i_data, 0);
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 4765190d537f..73c0bd7f7424 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -276,5 +276,5 @@ const struct file_operations fscache_stats_fops = {
 	.open		= fscache_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release        = single_release,
 };
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index d751f04763c1..ab9463a1947e 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -326,7 +326,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	int space_left = 0;
 	int first_tag = 0;
 	int tag_flag;
-	int i, to_free = 0;
+	int i;
 	int tag_bytes = journal_tag_bytes(journal);
 	struct buffer_head *cbh = NULL; /* For transactional checksums */
 	__u32 crc32_sum = ~0;
@@ -996,7 +996,7 @@ restart_loop:
 	journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
 	spin_unlock(&journal->j_history_lock);
 
-	commit_transaction->t_state = T_FINISHED;
+	commit_transaction->t_state = T_COMMIT_CALLBACK;
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
 	journal->j_commit_sequence = commit_transaction->t_tid;
 	journal->j_committing_transaction = NULL;
@@ -1011,38 +1011,44 @@ restart_loop:
 				journal->j_average_commit_time*3) / 4;
 	else
 		journal->j_average_commit_time = commit_time;
+
 	write_unlock(&journal->j_state_lock);
 
-	if (commit_transaction->t_checkpoint_list == NULL &&
-	    commit_transaction->t_checkpoint_io_list == NULL) {
-		__jbd2_journal_drop_transaction(journal, commit_transaction);
-		to_free = 1;
+	if (journal->j_checkpoint_transactions == NULL) {
+		journal->j_checkpoint_transactions = commit_transaction;
+		commit_transaction->t_cpnext = commit_transaction;
+		commit_transaction->t_cpprev = commit_transaction;
 	} else {
-		if (journal->j_checkpoint_transactions == NULL) {
-			journal->j_checkpoint_transactions = commit_transaction;
-			commit_transaction->t_cpnext = commit_transaction;
-			commit_transaction->t_cpprev = commit_transaction;
-		} else {
-			commit_transaction->t_cpnext =
-				journal->j_checkpoint_transactions;
-			commit_transaction->t_cpprev =
-				commit_transaction->t_cpnext->t_cpprev;
-			commit_transaction->t_cpnext->t_cpprev =
-				commit_transaction;
-			commit_transaction->t_cpprev->t_cpnext =
+		commit_transaction->t_cpnext =
+			journal->j_checkpoint_transactions;
+		commit_transaction->t_cpprev =
+			commit_transaction->t_cpnext->t_cpprev;
+		commit_transaction->t_cpnext->t_cpprev =
+			commit_transaction;
+		commit_transaction->t_cpprev->t_cpnext =
 				commit_transaction;
-		}
 	}
 	spin_unlock(&journal->j_list_lock);
-
+	/* Drop all spin_locks because commit_callback may be block.
+	 * __journal_remove_checkpoint() can not destroy transaction
+	 * under us because it is not marked as T_FINISHED yet */
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
-	if (to_free)
-		kfree(commit_transaction);
 
+	write_lock(&journal->j_state_lock);
+	spin_lock(&journal->j_list_lock);
+	commit_transaction->t_state = T_FINISHED;
+	/* Recheck checkpoint lists after j_list_lock was dropped */
+	if (commit_transaction->t_checkpoint_list == NULL &&
+	    commit_transaction->t_checkpoint_io_list == NULL) {
+		__jbd2_journal_drop_transaction(journal, commit_transaction);
+		kfree(commit_transaction);
+	}
+	spin_unlock(&journal->j_list_lock);
+	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
 }
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0fa0123151d3..17b04fcf5fa6 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -663,6 +663,37 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 }
 
 /*
+ * When this function returns the transaction corresponding to tid
+ * will be completed.  If the transaction has currently running, start
+ * committing that transaction before waiting for it to complete.  If
+ * the transaction id is stale, it is by definition already completed,
+ * so just return SUCCESS.
+ */
+int jbd2_complete_transaction(journal_t *journal, tid_t tid)
+{
+	int	need_to_wait = 1;
+
+	read_lock(&journal->j_state_lock);
+	if (journal->j_running_transaction &&
+	    journal->j_running_transaction->t_tid == tid) {
+		if (journal->j_commit_request != tid) {
+			/* transaction not yet started, so request it */
+			read_unlock(&journal->j_state_lock);
+			jbd2_log_start_commit(journal, tid);
+			goto wait_commit;
+		}
+	} else if (!(journal->j_committing_transaction &&
+		     journal->j_committing_transaction->t_tid == tid))
+		need_to_wait = 0;
+	read_unlock(&journal->j_state_lock);
+	if (!need_to_wait)
+		return 0;
+wait_commit:
+	return jbd2_log_wait_commit(journal, tid);
+}
+EXPORT_SYMBOL(jbd2_complete_transaction);
+
+/*
  * Log buffer allocation routines:
  */
 
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 8d4ea8351e3d..de889223174a 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -141,6 +141,9 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
 			timeout);
 	if (ret < 0)
 		return -ERESTARTSYS;
+	/* Reset the lock status after a server reboot so we resend */
+	if (block->b_status == nlm_lck_denied_grace_period)
+		block->b_status = nlm_lck_blocked;
 	req->a_res.status = block->b_status;
 	return 0;
 }
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index a3a09877ea62..8392cb85bd54 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -551,9 +551,6 @@ again:
 		status = nlmclnt_block(block, req, NLMCLNT_POLL_TIMEOUT);
 		if (status < 0)
 			break;
-		/* Resend the blocking lock request after a server reboot */
-		if (resp->status ==  nlm_lck_denied_grace_period)
-			continue;
 		if (resp->status != nlm_lck_blocked)
 			break;
 	}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index fe5c5fb6ac6c..08921b8854a3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -880,14 +880,14 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	nfs4_lock_state();
 	status = nfs4_preprocess_stateid_op(cstate, stateid, WR_STATE, &filp);
-	if (filp)
-		get_file(filp);
-	nfs4_unlock_state();
-
 	if (status) {
+		nfs4_unlock_state();
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
 	}
+	if (filp)
+		get_file(filp);
+	nfs4_unlock_state();
 
 	cnt = write->wr_buflen;
 	write->wr_how_written = write->wr_stable_how;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7d189dc3d767..4cef99ff2408 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -188,13 +188,7 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 {
 	if (atomic_dec_and_test(&fp->fi_access[oflag])) {
 		nfs4_file_put_fd(fp, oflag);
-		/*
-		 * It's also safe to get rid of the RDWR open *if*
-		 * we no longer have need of the other kind of access
-		 * or if we already have the other kind of open:
-		 */
-		if (fp->fi_fds[1-oflag]
-			|| atomic_read(&fp->fi_access[1 - oflag]) == 0)
+		if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
 			nfs4_file_put_fd(fp, O_RDWR);
 	}
 }
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 24afa96de4fa..ade5316d0cf5 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -360,10 +360,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ32(dummy32);
-			if (dummy32)
-				return nfserr_inval;
-			READ32(iattr->ia_atime.tv_sec);
+			READ64(iattr->ia_atime.tv_sec);
 			READ32(iattr->ia_atime.tv_nsec);
 			if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
@@ -386,10 +383,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ32(dummy32);
-			if (dummy32)
-				return nfserr_inval;
-			READ32(iattr->ia_mtime.tv_sec);
+			READ64(iattr->ia_mtime.tv_sec);
 			READ32(iattr->ia_mtime.tv_nsec);
 			if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
@@ -2374,8 +2368,7 @@ out_acl:
 	if (bmval1 & FATTR4_WORD1_TIME_ACCESS) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.atime.tv_sec);
+		WRITE64((s64)stat.atime.tv_sec);
 		WRITE32(stat.atime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
@@ -2388,15 +2381,13 @@ out_acl:
 	if (bmval1 & FATTR4_WORD1_TIME_METADATA) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.ctime.tv_sec);
+		WRITE64((s64)stat.ctime.tv_sec);
 		WRITE32(stat.ctime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_MODIFY) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.mtime.tv_sec);
+		WRITE64((s64)stat.mtime.tv_sec);
 		WRITE32(stat.mtime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 6f292dd53c6d..f255d372a5df 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -577,7 +577,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 	int add = (arg & IN_MASK_ADD);
 	int ret;
 
-	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
@@ -628,7 +627,6 @@ static int inotify_new_watch(struct fsnotify_group *group,
 	struct idr *idr = &group->inotify_data.idr;
 	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
 
-	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 
 	tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
@@ -757,6 +755,10 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	int ret, fput_needed;
 	unsigned flags = 0;
 
+	/* don't allow invalid bits: we don't want flags set */
+	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
+		return -EINVAL;
+
 	filp = fget_light(fd, &fput_needed);
 	if (unlikely(!filp))
 		return -EBADF;
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 3899e240c292..e756bc4d98a3 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -977,6 +977,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	enum kobj_ns_type type;
 	const void *ns;
 	ino_t ino;
+	loff_t off;
 
 	type = sysfs_ns_type(parent_sd);
 	ns = sysfs_info(dentry->d_sb)->ns[type];
@@ -999,6 +1000,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 			return 0;
 	}
 	mutex_lock(&sysfs_mutex);
+	off = filp->f_pos;
 	for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
 	     pos;
 	     pos = sysfs_dir_next_pos(ns, parent_sd, filp->f_pos, pos)) {
@@ -1010,19 +1012,24 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		len = strlen(name);
 		ino = pos->s_ino;
 		type = dt_type(pos);
-		filp->f_pos = ino;
+		off = filp->f_pos = ino;
 		filp->private_data = sysfs_get(pos);
 
 		mutex_unlock(&sysfs_mutex);
-		ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+		ret = filldir(dirent, name, len, off, ino, type);
 		mutex_lock(&sysfs_mutex);
 		if (ret < 0)
 			break;
 	}
 	mutex_unlock(&sysfs_mutex);
-	if ((filp->f_pos > 1) && !pos) { /* EOF */
-		filp->f_pos = INT_MAX;
+
+	/* don't reference last entry if its refcount is dropped */
+	if (!pos) {
 		filp->private_data = NULL;
+
+		/* EOF and not changed as 0 or 1 in read/write path */
+		if (off == filp->f_pos && off > 1)
+			filp->f_pos = INT_MAX;
 	}
 	return 0;
 }