Merge commit 'v2.6.38.5' into linaro-2.6.38

6 files changed, 65 insertions, 13 deletions

diff --git a/fs/file.c b/fs/file.c
index 0be344755c0..4c6992d8f3b 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/mmzone.h>
 #include <linux/time.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -39,14 +40,17 @@ int sysctl_nr_open_max = 1024 * 1024; /* raised later */
  */
 static DEFINE_PER_CPU(struct fdtable_defer, fdtable_defer_list);
 
-static inline void *alloc_fdmem(unsigned int size)
+static void *alloc_fdmem(unsigned int size)
 {
-	void *data;
-
-	data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
-	if (data != NULL)
-		return data;
-
+	/*
+	 * Very large allocations can stress page reclaim, so fall back to
+	 * vmalloc() if the allocation size will be considered "large" by the VM.
+	 */
+	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+		void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		if (data != NULL)
+			return data;
+	}
 	return vmalloc(size);
 }
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0592288f9f0..6221640397d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1600,7 +1600,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 	int status = 0;
 
 	/* Ensure exclusive access to NFSv4 state */
-	for(;;) {
+	do {
 		if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
 			/* We're going to have to re-establish a clientid */
 			status = nfs4_reclaim_lease(clp);
@@ -1684,7 +1684,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			break;
 		if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
 			break;
-	}
+	} while (atomic_read(&clp->cl_count) > 1);
 	return;
 out_error:
 	printk(KERN_WARNING "Error: state manager failed on NFSv4 server %s"
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index b68c8607770..6a2ec5043a0 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2077,6 +2077,15 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	if (error < 0)
 		goto out;
 
+	/*
+	 * noac is a special case. It implies -o sync, but that's not
+	 * necessarily reflected in the mtab options. do_remount_sb
+	 * will clear MS_SYNCHRONOUS if -o sync wasn't specified in the
+	 * remount options, so we have to explicitly reset it.
+	 */
+	if (data->flags & NFS_MOUNT_NOAC)
+		*flags |= MS_SYNCHRONOUS;
+
 	/* compare new mount options with old ones */
 	error = nfs_compare_remount_data(nfss, data);
 out:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 96aaaa47fd0..18c356cd50d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -258,6 +258,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 	if (atomic_dec_and_test(&fp->fi_delegees)) {
 		vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
 		fp->fi_lease = NULL;
+		fput(fp->fi_deleg_file);
 		fp->fi_deleg_file = NULL;
 	}
 }
@@ -402,8 +403,8 @@ static void free_generic_stateid(struct nfs4_stateid *stp)
 	if (stp->st_access_bmap) {
 		oflag = nfs4_access_bmap_to_omode(stp);
 		nfs4_file_put_access(stp->st_file, oflag);
-		put_nfs4_file(stp->st_file);
 	}
+	put_nfs4_file(stp->st_file);
 	kmem_cache_free(stateid_slab, stp);
 }
 
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 77e9b874b6c..c0c590feabe 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -300,6 +300,32 @@ int ubifs_recover_master_node(struct ubifs_info *c)
 			goto out_free;
 		}
 		memcpy(c->rcvrd_mst_node, c->mst_node, UBIFS_MST_NODE_SZ);
+
+		/*
+		 * We had to recover the master node, which means there was an
+		 * unclean reboot. However, it is possible that the master node
+		 * is clean at this point, i.e., %UBIFS_MST_DIRTY is not set.
+		 * E.g., consider the following chain of events:
+		 *
+		 * 1. UBIFS was cleanly unmounted, so the master node is clean
+		 * 2. UBIFS is being mounted R/W and starts changing the master
+		 *    node in the first (%UBIFS_MST_LNUM). A power cut happens,
+		 *    so this LEB ends up with some amount of garbage at the
+		 *    end.
+		 * 3. UBIFS is being mounted R/O. We reach this place and
+		 *    recover the master node from the second LEB
+		 *    (%UBIFS_MST_LNUM + 1). But we cannot update the media
+		 *    because we are being mounted R/O. We have to defer the
+		 *    operation.
+		 * 4. However, this master node (@c->mst_node) is marked as
+		 *    clean (since the step 1). And if we just return, the
+		 *    mount code will be confused and won't recover the master
+		 *    node when it is re-mounter R/W later.
+		 *
+		 *    Thus, to force the recovery by marking the master node as
+		 *    dirty.
+		 */
+		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
 	} else {
 		/* Write the recovered master node */
 		c->max_sqnum = le64_to_cpu(mst->ch.sqnum) - 1;
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 0f029e1732d..e94d9628a49 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1643,15 +1643,27 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 	if (err)
 		goto out;
 
+	dbg_gen("re-mounted read-write");
+	c->remounting_rw = 0;
+
 	if (c->need_recovery) {
 		c->need_recovery = 0;
 		ubifs_msg("deferred recovery completed");
+	} else {
+		/*
+		 * Do not run the debugging space check if the were doing
+		 * recovery, because when we saved the information we had the
+		 * file-system in a state where the TNC and lprops has been
+		 * modified in memory, but all the I/O operations (including a
+		 * commit) were deferred. So the file-system was in
+		 * "non-committed" state. Now the file-system is in committed
+		 * state, and of course the amount of free space will change
+		 * because, for example, the old index size was imprecise.
+		 */
+		err = dbg_check_space_info(c);
 	}
 
-	dbg_gen("re-mounted read-write");
-	c->remounting_rw = 0;
 	c->always_chk_crc = 0;
-	err = dbg_check_space_info(c);
 	mutex_unlock(&c->umount_mutex);
 	return err;