322 files changed, 8693 insertions, 4933 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index bb7991c7e5c7..53161ec058a7 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -451,7 +451,7 @@ void v9fs_evict_inode(struct inode *inode)
 {
         struct v9fs_inode *v9inode = V9FS_I(inode);
 
-        truncate_inode_pages(inode->i_mapping, 0);
+        truncate_inode_pages_final(inode->i_mapping);
         clear_inode(inode);
         filemap_fdatawrite(inode->i_mapping);
 
diff --git a/fs/Kconfig b/fs/Kconfig
index 7385e54be4b9..312393f32948 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -96,6 +96,7 @@ endif # BLOCK
 menu "Pseudo filesystems"
 
 source "fs/proc/Kconfig"
+source "fs/kernfs/Kconfig"
 source "fs/sysfs/Kconfig"
 
 config TMPFS
diff --git a/fs/Makefile b/fs/Makefile
index 47ac07bb4acc..f9cb9876e466 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -52,7 +52,8 @@ obj-$(CONFIG_FHANDLE)		+= fhandle.o
 obj-y                           += quota/
 
 obj-$(CONFIG_PROC_FS)           += proc/
-obj-$(CONFIG_SYSFS)             += sysfs/ kernfs/
+obj-$(CONFIG_KERNFS)            += kernfs/
+obj-$(CONFIG_SYSFS)             += sysfs/
 obj-$(CONFIG_CONFIGFS_FS)       += configfs/
 obj-y                           += devpts/
 
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 7b3003cb6f1b..952aeb048349 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -212,6 +212,7 @@ static int parse_options(struct super_block *sb, char *options)
 
 static int adfs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_NODIRATIME;
         return parse_options(sb, data);
 }
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 0e092d08680e..96df91e8c334 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -259,7 +259,7 @@ affs_evict_inode(struct inode *inode)
 {
         unsigned long cache_page;
         pr_debug("AFFS: evict_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         if (!inode->i_nlink) {
                 inode->i_size = 0;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index d098731b82ff..307453086c3f 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -530,6 +530,7 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 
         pr_debug("AFFS: remount(flags=0x%x,opts=\"%s\")\n",*flags,data);
 
+        sync_filesystem(sb);
         *flags |= MS_NODIRATIME;
 
         memcpy(volume, sbi->s_volume, 32);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index ce25d755b7aa..294671288449 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -422,7 +422,7 @@ void afs_evict_inode(struct inode *inode)
 
         ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
 
         afs_give_up_callback(vnode);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 6621f8008122..be75b500005d 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -75,6 +75,7 @@ struct afs_call {
         const struct afs_call_type *type;       /* type of call */
         const struct afs_wait_mode *wait_mode;  /* completion wait mode */
         wait_queue_head_t       waitq;          /* processes awaiting completion */
+        work_func_t             async_workfn;
         struct work_struct      async_work;     /* asynchronous work processor */
         struct work_struct      work;           /* actual work processor */
         struct sk_buff_head     rx_queue;       /* received packets */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 8ad8c2a0703a..ef943df73b8c 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -644,7 +644,7 @@ static void afs_process_async_call(struct work_struct *work)
 
                 /* we can't just delete the call because the work item may be
                  * queued */
-                PREPARE_WORK(&call->async_work, afs_delete_async_call);
+                call->async_workfn = afs_delete_async_call;
                 queue_work(afs_async_calls, &call->async_work);
         }
 
@@ -663,6 +663,13 @@ void afs_transfer_reply(struct afs_call *call, struct sk_buff *skb)
         call->reply_size += len;
 }
 
+static void afs_async_workfn(struct work_struct *work)
+{
+        struct afs_call *call = container_of(work, struct afs_call, async_work);
+
+        call->async_workfn(work);
+}
+
 /*
  * accept the backlog of incoming calls
  */
@@ -685,7 +692,8 @@ static void afs_collect_incoming_call(struct work_struct *work)
                                 return;
                         }
 
-                        INIT_WORK(&call->async_work, afs_process_async_call);
+                        call->async_workfn = afs_process_async_call;
+                        INIT_WORK(&call->async_work, afs_async_workfn);
                         call->wait_mode = &afs_async_incoming_call;
                         call->type = &afs_RXCMxxxx;
                         init_waitqueue_head(&call->waitq);
diff --git a/fs/befs/Makefile b/fs/befs/Makefile
index 2f370bd7a50d..8b9f66642a83 100644
--- a/fs/befs/Makefile
+++ b/fs/befs/Makefile
@@ -3,5 +3,5 @@
 #
  
 obj-$(CONFIG_BEFS_FS) += befs.o
-
+ccflags-$(CONFIG_BEFS_DEBUG)    += -DDEBUG
 befs-objs := datastream.o btree.o super.o inode.o debug.o io.o linuxvfs.o
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index b26642839156..3a7813ab8c95 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -88,8 +88,11 @@ enum befs_err {
 
 /****************************/
 /* debug.c */
+__printf(2, 3)
 void befs_error(const struct super_block *sb, const char *fmt, ...);
+__printf(2, 3)
 void befs_warning(const struct super_block *sb, const char *fmt, ...);
+__printf(2, 3)
 void befs_debug(const struct super_block *sb, const char *fmt, ...);
 
 void befs_dump_super_block(const struct super_block *sb, befs_super_block *);
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index 74e397db0b8b..a2cd305a993a 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -137,7 +137,7 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
         struct buffer_head *bh = NULL;
         befs_disk_btree_super *od_sup = NULL;
 
-        befs_debug(sb, "---> befs_btree_read_super()");
+        befs_debug(sb, "---> %s", __func__);
 
         bh = befs_read_datastream(sb, ds, 0, NULL);
 
@@ -162,11 +162,11 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
                 goto error;
         }
 
-        befs_debug(sb, "<--- befs_btree_read_super()");
+        befs_debug(sb, "<--- %s", __func__);
         return BEFS_OK;
 
       error:
-        befs_debug(sb, "<--- befs_btree_read_super() ERROR");
+        befs_debug(sb, "<--- %s ERROR", __func__);
         return BEFS_ERR;
 }
 
@@ -195,16 +195,16 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
 {
         uint off = 0;
 
-        befs_debug(sb, "---> befs_bt_read_node()");
+        befs_debug(sb, "---> %s", __func__);
 
         if (node->bh)
                 brelse(node->bh);
 
         node->bh = befs_read_datastream(sb, ds, node_off, &off);
         if (!node->bh) {
-                befs_error(sb, "befs_bt_read_node() failed to read "
-                           "node at %Lu", node_off);
-                befs_debug(sb, "<--- befs_bt_read_node() ERROR");
+                befs_error(sb, "%s failed to read "
+                           "node at %llu", __func__, node_off);
+                befs_debug(sb, "<--- %s ERROR", __func__);
 
                 return BEFS_ERR;
         }
@@ -221,7 +221,7 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
         node->head.all_key_length =
             fs16_to_cpu(sb, node->od_node->all_key_length);
 
-        befs_debug(sb, "<--- befs_btree_read_node()");
+        befs_debug(sb, "<--- %s", __func__);
         return BEFS_OK;
 }
 
@@ -252,7 +252,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
         befs_off_t node_off;
         int res;
 
-        befs_debug(sb, "---> befs_btree_find() Key: %s", key);
+        befs_debug(sb, "---> %s Key: %s", __func__, key);
 
         if (befs_bt_read_super(sb, ds, &bt_super) != BEFS_OK) {
                 befs_error(sb,
@@ -263,7 +263,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
         this_node = kmalloc(sizeof (befs_btree_node),
                                                 GFP_NOFS);
         if (!this_node) {
-                befs_error(sb, "befs_btree_find() failed to allocate %u "
+                befs_error(sb, "befs_btree_find() failed to allocate %zu "
                            "bytes of memory", sizeof (befs_btree_node));
                 goto error;
         }
@@ -274,7 +274,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
         node_off = bt_super.root_node_ptr;
         if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) {
                 befs_error(sb, "befs_btree_find() failed to read "
-                           "node at %Lu", node_off);
+                           "node at %llu", node_off);
                 goto error_alloc;
         }
 
@@ -285,7 +285,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
                 /* if no match, go to overflow node */
                 if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) {
                         befs_error(sb, "befs_btree_find() failed to read "
-                                   "node at %Lu", node_off);
+                                   "node at %llu", node_off);
                         goto error_alloc;
                 }
         }
@@ -298,11 +298,11 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
         kfree(this_node);
 
         if (res != BEFS_BT_MATCH) {
-                befs_debug(sb, "<--- befs_btree_find() Key %s not found", key);
+                befs_debug(sb, "<--- %s Key %s not found", __func__, key);
                 *value = 0;
                 return BEFS_BT_NOT_FOUND;
         }
-        befs_debug(sb, "<--- befs_btree_find() Found key %s, value %Lu",
+        befs_debug(sb, "<--- %s Found key %s, value %llu", __func__,
                    key, *value);
         return BEFS_OK;
 
@@ -310,7 +310,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
         kfree(this_node);
       error:
         *value = 0;
-        befs_debug(sb, "<--- befs_btree_find() ERROR");
+        befs_debug(sb, "<--- %s ERROR", __func__);
         return BEFS_ERR;
 }
 
@@ -343,7 +343,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
         char *thiskey;
         fs64 *valarray;
 
-        befs_debug(sb, "---> befs_find_key() %s", findkey);
+        befs_debug(sb, "---> %s %s", __func__, findkey);
 
         *value = 0;
 
@@ -355,7 +355,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
 
         eq = befs_compare_strings(thiskey, keylen, findkey, findkey_len);
         if (eq < 0) {
-                befs_debug(sb, "<--- befs_find_key() %s not found", findkey);
+                befs_debug(sb, "<--- %s %s not found", __func__, findkey);
                 return BEFS_BT_NOT_FOUND;
         }
 
@@ -373,8 +373,8 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
                                           findkey_len);
 
                 if (eq == 0) {
-                        befs_debug(sb, "<--- befs_find_key() found %s at %d",
-                                   thiskey, mid);
+                        befs_debug(sb, "<--- %s found %s at %d",
+                                   __func__, thiskey, mid);
 
                         *value = fs64_to_cpu(sb, valarray[mid]);
                         return BEFS_BT_MATCH;
@@ -388,7 +388,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
                 *value = fs64_to_cpu(sb, valarray[mid + 1]);
         else
                 *value = fs64_to_cpu(sb, valarray[mid]);
-        befs_debug(sb, "<--- befs_find_key() found %s at %d", thiskey, mid);
+        befs_debug(sb, "<--- %s found %s at %d", __func__, thiskey, mid);
         return BEFS_BT_PARMATCH;
 }
 
@@ -428,7 +428,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 
         uint key_sum = 0;
 
-        befs_debug(sb, "---> befs_btree_read()");
+        befs_debug(sb, "---> %s", __func__);
 
         if (befs_bt_read_super(sb, ds, &bt_super) != BEFS_OK) {
                 befs_error(sb,
@@ -437,7 +437,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
         }
 
         if ((this_node = kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) {
-                befs_error(sb, "befs_btree_read() failed to allocate %u "
+                befs_error(sb, "befs_btree_read() failed to allocate %zu "
                            "bytes of memory", sizeof (befs_btree_node));
                 goto error;
         }
@@ -452,7 +452,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
                 kfree(this_node);
                 *value = 0;
                 *keysize = 0;
-                befs_debug(sb, "<--- befs_btree_read() Tree is EMPTY");
+                befs_debug(sb, "<--- %s Tree is EMPTY", __func__);
                 return BEFS_BT_EMPTY;
         } else if (res == BEFS_ERR) {
                 goto error_alloc;
@@ -467,7 +467,8 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
                         *keysize = 0;
                         *value = 0;
                         befs_debug(sb,
-                                   "<--- befs_btree_read() END of keys at %Lu",
+                                   "<--- %s END of keys at %llu", __func__,
+                                   (unsigned long long)
                                    key_sum + this_node->head.all_key_count);
                         brelse(this_node->bh);
                         kfree(this_node);
@@ -478,8 +479,8 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
                 node_off = this_node->head.right;
 
                 if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) {
-                        befs_error(sb, "befs_btree_read() failed to read "
-                                   "node at %Lu", node_off);
+                        befs_error(sb, "%s failed to read node at %llu",
+                                  __func__, (unsigned long long)node_off);
                         goto error_alloc;
                 }
         }
@@ -492,11 +493,13 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 
         keystart = befs_bt_get_key(sb, this_node, cur_key, &keylen);
 
-        befs_debug(sb, "Read [%Lu,%d]: keysize %d", node_off, cur_key, keylen);
+        befs_debug(sb, "Read [%llu,%d]: keysize %d",
+                   (long long unsigned int)node_off, (int)cur_key,
+                   (int)keylen);
 
         if (bufsize < keylen + 1) {
-                befs_error(sb, "befs_btree_read() keybuf too small (%u) "
-                           "for key of size %d", bufsize, keylen);
+                befs_error(sb, "%s keybuf too small (%zu) "
+                           "for key of size %d", __func__, bufsize, keylen);
                 brelse(this_node->bh);
                 goto error_alloc;
         };
@@ -506,13 +509,13 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
         *keysize = keylen;
         keybuf[keylen] = '\0';
 
-        befs_debug(sb, "Read [%Lu,%d]: Key \"%.*s\", Value %Lu", node_off,
+        befs_debug(sb, "Read [%llu,%d]: Key \"%.*s\", Value %llu", node_off,
                    cur_key, keylen, keybuf, *value);
 
         brelse(this_node->bh);
         kfree(this_node);
 
-        befs_debug(sb, "<--- befs_btree_read()");
+        befs_debug(sb, "<--- %s", __func__);
 
         return BEFS_OK;
 
@@ -522,7 +525,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
       error:
         *keysize = 0;
         *value = 0;
-        befs_debug(sb, "<--- befs_btree_read() ERROR");
+        befs_debug(sb, "<--- %s ERROR", __func__);
         return BEFS_ERR;
 }
 
@@ -547,26 +550,26 @@ befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
                     befs_off_t * node_off)
 {
 
-        befs_debug(sb, "---> befs_btree_seekleaf()");
+        befs_debug(sb, "---> %s", __func__);
 
         if (befs_bt_read_node(sb, ds, this_node, *node_off) != BEFS_OK) {
-                befs_error(sb, "befs_btree_seekleaf() failed to read "
-                           "node at %Lu", *node_off);
+                befs_error(sb, "%s failed to read "
+                           "node at %llu", __func__, *node_off);
                 goto error;
         }
-        befs_debug(sb, "Seekleaf to root node %Lu", *node_off);
+        befs_debug(sb, "Seekleaf to root node %llu", *node_off);
 
         if (this_node->head.all_key_count == 0 && befs_leafnode(this_node)) {
-                befs_debug(sb, "<--- befs_btree_seekleaf() Tree is EMPTY");
+                befs_debug(sb, "<--- %s Tree is EMPTY", __func__);
                 return BEFS_BT_EMPTY;
         }
 
         while (!befs_leafnode(this_node)) {
 
                 if (this_node->head.all_key_count == 0) {
-                        befs_debug(sb, "befs_btree_seekleaf() encountered "
-                                   "an empty interior node: %Lu. Using Overflow "
-                                   "node: %Lu", *node_off,
+                        befs_debug(sb, "%s encountered "
+                                   "an empty interior node: %llu. Using Overflow "
+                                   "node: %llu", __func__, *node_off,
                                    this_node->head.overflow);
                         *node_off = this_node->head.overflow;
                 } else {
@@ -574,19 +577,19 @@ befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
                         *node_off = fs64_to_cpu(sb, valarray[0]);
                 }
                 if (befs_bt_read_node(sb, ds, this_node, *node_off) != BEFS_OK) {
-                        befs_error(sb, "befs_btree_seekleaf() failed to read "
-                                   "node at %Lu", *node_off);
+                        befs_error(sb, "%s failed to read "
+                                   "node at %llu", __func__, *node_off);
                         goto error;
                 }
 
-                befs_debug(sb, "Seekleaf to child node %Lu", *node_off);
+                befs_debug(sb, "Seekleaf to child node %llu", *node_off);
         }
-        befs_debug(sb, "Node %Lu is a leaf node", *node_off);
+        befs_debug(sb, "Node %llu is a leaf node", *node_off);
 
         return BEFS_OK;
 
       error:
-        befs_debug(sb, "<--- befs_btree_seekleaf() ERROR");
+        befs_debug(sb, "<--- %s ERROR", __func__);
         return BEFS_ERR;
 }
 
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index 59096b5e0fc7..c467bebd50af 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -52,26 +52,25 @@ befs_read_datastream(struct super_block *sb, befs_data_stream * ds,
         befs_block_run run;
         befs_blocknr_t block;   /* block coresponding to pos */
 
-        befs_debug(sb, "---> befs_read_datastream() %Lu", pos);
+        befs_debug(sb, "---> %s %llu", __func__, pos);
         block = pos >> BEFS_SB(sb)->block_shift;
         if (off)
                 *off = pos - (block << BEFS_SB(sb)->block_shift);
 
         if (befs_fblock2brun(sb, ds, block, &run) != BEFS_OK) {
                 befs_error(sb, "BeFS: Error finding disk addr of block %lu",
-                           block);
-                befs_debug(sb, "<--- befs_read_datastream() ERROR");
+                           (unsigned long)block);
+                befs_debug(sb, "<--- %s ERROR", __func__);
                 return NULL;
         }
         bh = befs_bread_iaddr(sb, run);
         if (!bh) {
                 befs_error(sb, "BeFS: Error reading block %lu from datastream",
-                           block);
+                           (unsigned long)block);
                 return NULL;
         }
 
-        befs_debug(sb, "<--- befs_read_datastream() read data, starting at %Lu",
-                   pos);
+        befs_debug(sb, "<--- %s read data, starting at %llu", __func__, pos);
 
         return bh;
 }
@@ -106,7 +105,8 @@ befs_fblock2brun(struct super_block *sb, befs_data_stream * data,
         } else {
                 befs_error(sb,
                            "befs_fblock2brun() was asked to find block %lu, "
-                           "which is not mapped by the datastream\n", fblock);
+                           "which is not mapped by the datastream\n",
+                           (unsigned long)fblock);
                 err = BEFS_ERR;
         }
         return err;
@@ -128,14 +128,14 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff,
         befs_off_t bytes_read = 0;      /* bytes readed */
         u16 plen;
         struct buffer_head *bh = NULL;
-        befs_debug(sb, "---> befs_read_lsymlink() length: %Lu", len);
+        befs_debug(sb, "---> %s length: %llu", __func__, len);
 
         while (bytes_read < len) {
                 bh = befs_read_datastream(sb, ds, bytes_read, NULL);
                 if (!bh) {
                         befs_error(sb, "BeFS: Error reading datastream block "
-                                   "starting from %Lu", bytes_read);
-                        befs_debug(sb, "<--- befs_read_lsymlink() ERROR");
+                                   "starting from %llu", bytes_read);
+                        befs_debug(sb, "<--- %s ERROR", __func__);
                         return bytes_read;
 
                 }
@@ -146,7 +146,8 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff,
                 bytes_read += plen;
         }
 
-        befs_debug(sb, "<--- befs_read_lsymlink() read %u bytes", bytes_read);
+        befs_debug(sb, "<--- %s read %u bytes", __func__, (unsigned int)
+                   bytes_read);
         return bytes_read;
 }
 
@@ -169,7 +170,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds)
         befs_blocknr_t metablocks;      /* FS metadata blocks */
         befs_sb_info *befs_sb = BEFS_SB(sb);
 
-        befs_debug(sb, "---> befs_count_blocks()");
+        befs_debug(sb, "---> %s", __func__);
 
         datablocks = ds->size >> befs_sb->block_shift;
         if (ds->size & (befs_sb->block_size - 1))
@@ -206,7 +207,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds)
         }
 
         blocks = datablocks + metablocks;
-        befs_debug(sb, "<--- befs_count_blocks() %u blocks", blocks);
+        befs_debug(sb, "<--- %s %u blocks", __func__, (unsigned int)blocks);
 
         return blocks;
 }
@@ -251,11 +252,11 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data,
         befs_blocknr_t max_block =
             data->max_direct_range >> BEFS_SB(sb)->block_shift;
 
-        befs_debug(sb, "---> befs_find_brun_direct(), find %lu", blockno);
+        befs_debug(sb, "---> %s, find %lu", __func__, (unsigned long)blockno);
 
         if (blockno > max_block) {
-                befs_error(sb, "befs_find_brun_direct() passed block outside of"
-                           "direct region");
+                befs_error(sb, "%s passed block outside of direct region",
+                           __func__);
                 return BEFS_ERR;
         }
 
@@ -267,13 +268,14 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data,
                         run->start = array[i].start + offset;
                         run->len = array[i].len - offset;
 
-                        befs_debug(sb, "---> befs_find_brun_direct(), "
-                                   "found %lu at direct[%d]", blockno, i);
+                        befs_debug(sb, "---> %s, "
+                                   "found %lu at direct[%d]", __func__,
+                                   (unsigned long)blockno, i);
                         return BEFS_OK;
                 }
         }
 
-        befs_debug(sb, "---> befs_find_brun_direct() ERROR");
+        befs_debug(sb, "---> %s ERROR", __func__);
         return BEFS_ERR;
 }
 
@@ -316,7 +318,7 @@ befs_find_brun_indirect(struct super_block *sb,
         befs_blocknr_t indirblockno = iaddr2blockno(sb, &indirect);
         int arraylen = befs_iaddrs_per_block(sb);
 
-        befs_debug(sb, "---> befs_find_brun_indirect(), find %lu", blockno);
+        befs_debug(sb, "---> %s, find %lu", __func__, (unsigned long)blockno);
 
         indir_start_blk = data->max_direct_range >> BEFS_SB(sb)->block_shift;
         search_blk = blockno - indir_start_blk;
@@ -325,10 +327,9 @@ befs_find_brun_indirect(struct super_block *sb,
         for (i = 0; i < indirect.len; i++) {
                 indirblock = befs_bread(sb, indirblockno + i);
                 if (indirblock == NULL) {
-                        befs_debug(sb,
-                                   "---> befs_find_brun_indirect() failed to "
-                                   "read disk block %lu from the indirect brun",
-                                   indirblockno + i);
+                        befs_debug(sb, "---> %s failed to read "
+                                   "disk block %lu from the indirect brun",
+                                   __func__, (unsigned long)indirblockno + i);
                         return BEFS_ERR;
                 }
 
@@ -348,9 +349,10 @@ befs_find_brun_indirect(struct super_block *sb,
 
                                 brelse(indirblock);
                                 befs_debug(sb,
-                                           "<--- befs_find_brun_indirect() found "
-                                           "file block %lu at indirect[%d]",
-                                           blockno, j + (i * arraylen));
+                                           "<--- %s found file block "
+                                           "%lu at indirect[%d]", __func__,
+                                           (unsigned long)blockno,
+                                           j + (i * arraylen));
                                 return BEFS_OK;
                         }
                         sum += len;
@@ -360,10 +362,10 @@ befs_find_brun_indirect(struct super_block *sb,
         }
 
         /* Only fallthrough is an error */
-        befs_error(sb, "BeFS: befs_find_brun_indirect() failed to find "
-                   "file block %lu", blockno);
+        befs_error(sb, "BeFS: %s failed to find "
+                   "file block %lu", __func__, (unsigned long)blockno);
 
-        befs_debug(sb, "<--- befs_find_brun_indirect() ERROR");
+        befs_debug(sb, "<--- %s ERROR", __func__);
         return BEFS_ERR;
 }
 
@@ -444,7 +446,7 @@ befs_find_brun_dblindirect(struct super_block *sb,
         size_t diblklen = iblklen * befs_iaddrs_per_block(sb)
             * BEFS_DBLINDIR_BRUN_LEN;
 
-        befs_debug(sb, "---> befs_find_brun_dblindirect() find %lu", blockno);
+        befs_debug(sb, "---> %s find %lu", __func__, (unsigned long)blockno);
 
         /* First, discover which of the double_indir->indir blocks
          * contains pos. Then figure out how much of pos that
@@ -460,8 +462,9 @@ befs_find_brun_dblindirect(struct super_block *sb,
         dbl_which_block = dblindir_indx / befs_iaddrs_per_block(sb);
         if (dbl_which_block > data->double_indirect.len) {
                 befs_error(sb, "The double-indirect index calculated by "
-                           "befs_read_brun_dblindirect(), %d, is outside the range "
-                           "of the double-indirect block", dblindir_indx);
+                           "%s, %d, is outside the range "
+                           "of the double-indirect block", __func__,
+                           dblindir_indx);
                 return BEFS_ERR;
         }
 
@@ -469,10 +472,10 @@ befs_find_brun_dblindirect(struct super_block *sb,
             befs_bread(sb, iaddr2blockno(sb, &data->double_indirect) +
                                         dbl_which_block);
         if (dbl_indir_block == NULL) {
-                befs_error(sb, "befs_read_brun_dblindirect() couldn't read the "
-                           "double-indirect block at blockno %lu",
-                           iaddr2blockno(sb,
-                                         &data->double_indirect) +
+                befs_error(sb, "%s couldn't read the "
+                           "double-indirect block at blockno %lu", __func__,
+                           (unsigned long)
+                           iaddr2blockno(sb, &data->double_indirect) +
                            dbl_which_block);
                 brelse(dbl_indir_block);
                 return BEFS_ERR;
@@ -489,16 +492,16 @@ befs_find_brun_dblindirect(struct super_block *sb,
         which_block = indir_indx / befs_iaddrs_per_block(sb);
         if (which_block > indir_run.len) {
                 befs_error(sb, "The indirect index calculated by "
-                           "befs_read_brun_dblindirect(), %d, is outside the range "
-                           "of the indirect block", indir_indx);
+                           "%s, %d, is outside the range "
+                           "of the indirect block", __func__, indir_indx);
                 return BEFS_ERR;
         }
 
         indir_block =
             befs_bread(sb, iaddr2blockno(sb, &indir_run) + which_block);
         if (indir_block == NULL) {
-                befs_error(sb, "befs_read_brun_dblindirect() couldn't read the "
-                           "indirect block at blockno %lu",
+                befs_error(sb, "%s couldn't read the indirect block "
+                           "at blockno %lu", __func__, (unsigned long)
                            iaddr2blockno(sb, &indir_run) + which_block);
                 brelse(indir_block);
                 return BEFS_ERR;
@@ -519,7 +522,7 @@ befs_find_brun_dblindirect(struct super_block *sb,
         run->len -= offset;
 
         befs_debug(sb, "Found file block %lu in double_indirect[%d][%d],"
-                   " double_indirect_leftover = %lu",
+                   " double_indirect_leftover = %lu", (unsigned long)
                    blockno, dblindir_indx, indir_indx, dblindir_leftover);
 
         return BEFS_OK;
diff --git a/fs/befs/debug.c b/fs/befs/debug.c
index 622e73775c83..4de7cffcd662 100644
--- a/fs/befs/debug.c
+++ b/fs/befs/debug.c
@@ -10,6 +10,7 @@
  * debug functions
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #ifdef __KERNEL__
 
 #include <stdarg.h>
@@ -23,43 +24,30 @@
 
 #include "befs.h"
 
-#define ERRBUFSIZE 1024
-
 void
 befs_error(const struct super_block *sb, const char *fmt, ...)
 {
+        struct va_format vaf;
         va_list args;
-        char *err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL);
-        if (err_buf == NULL) {
-                printk(KERN_ERR "could not allocate %d bytes\n", ERRBUFSIZE);
-                return;
-        }
 
         va_start(args, fmt);
-        vsnprintf(err_buf, ERRBUFSIZE, fmt, args);
+        vaf.fmt = fmt;
+        vaf.va = &args;
+        pr_err("(%s): %pV\n", sb->s_id, &vaf);
         va_end(args);
-
-        printk(KERN_ERR "BeFS(%s): %s\n", sb->s_id, err_buf);
-        kfree(err_buf);
 }
 
 void
 befs_warning(const struct super_block *sb, const char *fmt, ...)
 {
+        struct va_format vaf;
         va_list args;
-        char *err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL);
-        if (err_buf == NULL) {
-                printk(KERN_ERR "could not allocate %d bytes\n", ERRBUFSIZE);
-                return;
-        }
 
         va_start(args, fmt);
-        vsnprintf(err_buf, ERRBUFSIZE, fmt, args);
+        vaf.fmt = fmt;
+        vaf.va = &args;
+        pr_warn("(%s): %pV\n", sb->s_id, &vaf);
         va_end(args);
-
-        printk(KERN_WARNING "BeFS(%s): %s\n", sb->s_id, err_buf);
-
-        kfree(err_buf);
 }
 
 void
@@ -67,25 +55,13 @@ befs_debug(const struct super_block *sb, const char *fmt, ...)
 {
 #ifdef CONFIG_BEFS_DEBUG
 
+        struct va_format vaf;
         va_list args;
-        char *err_buf = NULL;
-
-        if (BEFS_SB(sb)->mount_opts.debug) {
-                err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL);
-                if (err_buf == NULL) {
-                        printk(KERN_ERR "could not allocate %d bytes\n",
-                                ERRBUFSIZE);
-                        return;
-                }
-
-                va_start(args, fmt);
-                vsnprintf(err_buf, ERRBUFSIZE, fmt, args);
-                va_end(args);
-
-                printk(KERN_DEBUG "BeFS(%s): %s\n", sb->s_id, err_buf);
-
-                kfree(err_buf);
-        }
+        va_start(args, fmt);
+        vaf.fmt = fmt;
+        vaf.va = &args;
+        pr_debug("(%s): %pV\n", sb->s_id, &vaf);
+        va_end(args);
 
 #endif                          //CONFIG_BEFS_DEBUG
 }
@@ -109,9 +85,9 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
         befs_debug(sb, "  gid %u", fs32_to_cpu(sb, inode->gid));
         befs_debug(sb, "  mode %08x", fs32_to_cpu(sb, inode->mode));
         befs_debug(sb, "  flags %08x", fs32_to_cpu(sb, inode->flags));
-        befs_debug(sb, "  create_time %Lu",
+        befs_debug(sb, "  create_time %llu",
                    fs64_to_cpu(sb, inode->create_time));
-        befs_debug(sb, "  last_modified_time %Lu",
+        befs_debug(sb, "  last_modified_time %llu",
                    fs64_to_cpu(sb, inode->last_modified_time));
 
         tmp_run = fsrun_to_cpu(sb, inode->parent);
@@ -137,7 +113,7 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
                                    tmp_run.allocation_group, tmp_run.start,
                                    tmp_run.len);
                 }
-                befs_debug(sb, "  max_direct_range %Lu",
+                befs_debug(sb, "  max_direct_range %llu",
                            fs64_to_cpu(sb,
                                        inode->data.datastream.
                                        max_direct_range));
@@ -147,7 +123,7 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
                            tmp_run.allocation_group,
                            tmp_run.start, tmp_run.len);
 
-                befs_debug(sb, "  max_indirect_range %Lu",
+                befs_debug(sb, "  max_indirect_range %llu",
                            fs64_to_cpu(sb,
                                        inode->data.datastream.
                                        max_indirect_range));
@@ -158,12 +134,12 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
                            tmp_run.allocation_group, tmp_run.start,
                            tmp_run.len);
 
-                befs_debug(sb, "  max_double_indirect_range %Lu",
+                befs_debug(sb, "  max_double_indirect_range %llu",
                            fs64_to_cpu(sb,
                                        inode->data.datastream.
                                        max_double_indirect_range));
 
-                befs_debug(sb, "  size %Lu",
+                befs_debug(sb, "  size %llu",
                            fs64_to_cpu(sb, inode->data.datastream.size));
         }
 
@@ -191,8 +167,8 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup)
         befs_debug(sb, "  block_size %u", fs32_to_cpu(sb, sup->block_size));
         befs_debug(sb, "  block_shift %u", fs32_to_cpu(sb, sup->block_shift));
 
-        befs_debug(sb, "  num_blocks %Lu", fs64_to_cpu(sb, sup->num_blocks));
-        befs_debug(sb, "  used_blocks %Lu", fs64_to_cpu(sb, sup->used_blocks));
+        befs_debug(sb, "  num_blocks %llu", fs64_to_cpu(sb, sup->num_blocks));
+        befs_debug(sb, "  used_blocks %llu", fs64_to_cpu(sb, sup->used_blocks));
 
         befs_debug(sb, "  magic2 %08x", fs32_to_cpu(sb, sup->magic2));
         befs_debug(sb, "  blocks_per_ag %u",
@@ -206,8 +182,8 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup)
         befs_debug(sb, "  log_blocks %u, %hu, %hu",
                    tmp_run.allocation_group, tmp_run.start, tmp_run.len);
 
-        befs_debug(sb, "  log_start %Ld", fs64_to_cpu(sb, sup->log_start));
-        befs_debug(sb, "  log_end %Ld", fs64_to_cpu(sb, sup->log_end));
+        befs_debug(sb, "  log_start %lld", fs64_to_cpu(sb, sup->log_start));
+        befs_debug(sb, "  log_end %lld", fs64_to_cpu(sb, sup->log_end));
 
         befs_debug(sb, "  magic3 %08x", fs32_to_cpu(sb, sup->magic3));
 
diff --git a/fs/befs/inode.c b/fs/befs/inode.c
index 94c17f9a9576..fa4b718de597 100644
--- a/fs/befs/inode.c
+++ b/fs/befs/inode.c
@@ -25,7 +25,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
         /* check magic header. */
         if (magic1 != BEFS_INODE_MAGIC1) {
                 befs_error(sb,
-                           "Inode has a bad magic header - inode = %lu", inode);
+                           "Inode has a bad magic header - inode = %lu",
+                           (unsigned long)inode);
                 return BEFS_BAD_INODE;
         }
 
@@ -34,8 +35,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
          */
         if (inode != iaddr2blockno(sb, &ino_num)) {
                 befs_error(sb, "inode blocknr field disagrees with vfs "
-                           "VFS: %lu, Inode %lu",
-                           inode, iaddr2blockno(sb, &ino_num));
+                           "VFS: %lu, Inode %lu", (unsigned long)
+                           inode, (unsigned long)iaddr2blockno(sb, &ino_num));
                 return BEFS_BAD_INODE;
         }
 
@@ -44,7 +45,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
          */
 
         if (!(flags & BEFS_INODE_IN_USE)) {
-                befs_error(sb, "inode is not used - inode = %lu", inode);
+                befs_error(sb, "inode is not used - inode = %lu",
+                           (unsigned long)inode);
                 return BEFS_BAD_INODE;
         }
 
diff --git a/fs/befs/io.c b/fs/befs/io.c
index ddef98aa255d..0408a3d601d0 100644
--- a/fs/befs/io.c
+++ b/fs/befs/io.c
@@ -30,9 +30,9 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
         befs_blocknr_t block = 0;
         befs_sb_info *befs_sb = BEFS_SB(sb);
 
-        befs_debug(sb, "---> Enter befs_read_iaddr() "
-                   "[%u, %hu, %hu]",
-                   iaddr.allocation_group, iaddr.start, iaddr.len);
+        befs_debug(sb, "---> Enter %s "
+                   "[%u, %hu, %hu]", __func__, iaddr.allocation_group,
+                   iaddr.start, iaddr.len);
 
         if (iaddr.allocation_group > befs_sb->num_ags) {
                 befs_error(sb, "BEFS: Invalid allocation group %u, max is %u",
@@ -42,20 +42,21 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
 
         block = iaddr2blockno(sb, &iaddr);
 
-        befs_debug(sb, "befs_read_iaddr: offset = %lu", block);
+        befs_debug(sb, "%s: offset = %lu", __func__, (unsigned long)block);
 
         bh = sb_bread(sb, block);
 
         if (bh == NULL) {
-                befs_error(sb, "Failed to read block %lu", block);
+                befs_error(sb, "Failed to read block %lu",
+                           (unsigned long)block);
                 goto error;
         }
 
-        befs_debug(sb, "<--- befs_read_iaddr()");
+        befs_debug(sb, "<--- %s", __func__);
         return bh;
 
       error:
-        befs_debug(sb, "<--- befs_read_iaddr() ERROR");
+        befs_debug(sb, "<--- %s ERROR", __func__);
         return NULL;
 }
 
@@ -64,20 +65,21 @@ befs_bread(struct super_block *sb, befs_blocknr_t block)
 {
         struct buffer_head *bh = NULL;
 
-        befs_debug(sb, "---> Enter befs_read() %Lu", block);
+        befs_debug(sb, "---> Enter %s %lu", __func__, (unsigned long)block);
 
         bh = sb_bread(sb, block);
 
         if (bh == NULL) {
-                befs_error(sb, "Failed to read block %lu", block);
+                befs_error(sb, "Failed to read block %lu",
+                           (unsigned long)block);
                 goto error;
         }
 
-        befs_debug(sb, "<--- befs_read()");
+        befs_debug(sb, "<--- %s", __func__);
 
         return bh;
 
       error:
-        befs_debug(sb, "<--- befs_read() ERROR");
+        befs_debug(sb, "<--- %s ERROR", __func__);
         return NULL;
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 845d2d690ce2..d626756ff721 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -5,6 +5,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
@@ -39,7 +41,6 @@ static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int)
 static struct inode *befs_iget(struct super_block *, unsigned long);
 static struct inode *befs_alloc_inode(struct super_block *sb);
 static void befs_destroy_inode(struct inode *inode);
-static int befs_init_inodecache(void);
 static void befs_destroy_inodecache(void);
 static void *befs_follow_link(struct dentry *, struct nameidata *);
 static void *befs_fast_follow_link(struct dentry *, struct nameidata *);
@@ -131,26 +132,28 @@ befs_get_block(struct inode *inode, sector_t block,
         ulong disk_off;
 
         befs_debug(sb, "---> befs_get_block() for inode %lu, block %ld",
-                   inode->i_ino, block);
+                   (unsigned long)inode->i_ino, (long)block);
 
         if (block < 0) {
                 befs_error(sb, "befs_get_block() was asked for a block "
                            "number less than zero: block %ld in inode %lu",
-                           block, inode->i_ino);
+                           (long)block, (unsigned long)inode->i_ino);
                 return -EIO;
         }
 
         if (create) {
                 befs_error(sb, "befs_get_block() was asked to write to "
-                           "block %ld in inode %lu", block, inode->i_ino);
+                           "block %ld in inode %lu", (long)block,
+                           (unsigned long)inode->i_ino);
                 return -EPERM;
         }
 
         res = befs_fblock2brun(sb, ds, block, &run);
         if (res != BEFS_OK) {
                 befs_error(sb,
-                           "<--- befs_get_block() for inode %lu, block "
-                           "%ld ERROR", inode->i_ino, block);
+                           "<--- %s for inode %lu, block %ld ERROR",
+                           __func__, (unsigned long)inode->i_ino,
+                           (long)block);
                 return -EFBIG;
         }
 
@@ -158,8 +161,9 @@ befs_get_block(struct inode *inode, sector_t block,
 
         map_bh(bh_result, inode->i_sb, disk_off);
 
-        befs_debug(sb, "<--- befs_get_block() for inode %lu, block %ld, "
-                   "disk address %lu", inode->i_ino, block, disk_off);
+        befs_debug(sb, "<--- %s for inode %lu, block %ld, disk address %lu",
+                  __func__, (unsigned long)inode->i_ino, (long)block,
+                  (unsigned long)disk_off);
 
         return 0;
 }
@@ -176,15 +180,15 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
         char *utfname;
         const char *name = dentry->d_name.name;
 
-        befs_debug(sb, "---> befs_lookup() "
-                   "name %s inode %ld", dentry->d_name.name, dir->i_ino);
+        befs_debug(sb, "---> %s name %s inode %ld", __func__,
+                   dentry->d_name.name, dir->i_ino);
 
         /* Convert to UTF-8 */
         if (BEFS_SB(sb)->nls) {
                 ret =
                     befs_nls2utf(sb, name, strlen(name), &utfname, &utfnamelen);
                 if (ret < 0) {
-                        befs_debug(sb, "<--- befs_lookup() ERROR");
+                        befs_debug(sb, "<--- %s ERROR", __func__);
                         return ERR_PTR(ret);
                 }
                 ret = befs_btree_find(sb, ds, utfname, &offset);
@@ -195,12 +199,12 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
         }
 
         if (ret == BEFS_BT_NOT_FOUND) {
-                befs_debug(sb, "<--- befs_lookup() %s not found",
+                befs_debug(sb, "<--- %s %s not found", __func__,
                            dentry->d_name.name);
                 return ERR_PTR(-ENOENT);
 
         } else if (ret != BEFS_OK || offset == 0) {
-                befs_warning(sb, "<--- befs_lookup() Error");
+                befs_warning(sb, "<--- %s Error", __func__);
                 return ERR_PTR(-ENODATA);
         }
 
@@ -210,7 +214,7 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 
         d_add(dentry, inode);
 
-        befs_debug(sb, "<--- befs_lookup()");
+        befs_debug(sb, "<--- %s", __func__);
 
         return NULL;
 }
@@ -228,26 +232,25 @@ befs_readdir(struct file *file, struct dir_context *ctx)
         char keybuf[BEFS_NAME_LEN + 1];
         const char *dirname = file->f_path.dentry->d_name.name;
 
-        befs_debug(sb, "---> befs_readdir() "
-                   "name %s, inode %ld, ctx->pos %Ld",
-                   dirname, inode->i_ino, ctx->pos);
+        befs_debug(sb, "---> %s name %s, inode %ld, ctx->pos %lld",
+                  __func__, dirname, inode->i_ino, ctx->pos);
 
 more:
         result = befs_btree_read(sb, ds, ctx->pos, BEFS_NAME_LEN + 1,
                                  keybuf, &keysize, &value);
 
         if (result == BEFS_ERR) {
-                befs_debug(sb, "<--- befs_readdir() ERROR");
+                befs_debug(sb, "<--- %s ERROR", __func__);
                 befs_error(sb, "IO error reading %s (inode %lu)",
                            dirname, inode->i_ino);
                 return -EIO;
 
         } else if (result == BEFS_BT_END) {
-                befs_debug(sb, "<--- befs_readdir() END");
+                befs_debug(sb, "<--- %s END", __func__);
                 return 0;
 
         } else if (result == BEFS_BT_EMPTY) {
-                befs_debug(sb, "<--- befs_readdir() Empty directory");
+                befs_debug(sb, "<--- %s Empty directory", __func__);
                 return 0;
         }
 
@@ -260,7 +263,7 @@ more:
                 result =
                     befs_utf2nls(sb, keybuf, keysize, &nlsname, &nlsnamelen);
                 if (result < 0) {
-                        befs_debug(sb, "<--- befs_readdir() ERROR");
+                        befs_debug(sb, "<--- %s ERROR", __func__);
                         return result;
                 }
                 if (!dir_emit(ctx, nlsname, nlsnamelen,
@@ -277,7 +280,7 @@ more:
         ctx->pos++;
         goto more;
 
-        befs_debug(sb, "<--- befs_readdir() pos %Ld", ctx->pos);
+        befs_debug(sb, "<--- %s pos %lld", __func__, ctx->pos);
 
         return 0;
 }
@@ -321,7 +324,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
         struct inode *inode;
         long ret = -EIO;
 
-        befs_debug(sb, "---> befs_read_inode() " "inode = %lu", ino);
+        befs_debug(sb, "---> %s inode = %lu", __func__, ino);
 
         inode = iget_locked(sb, ino);
         if (!inode)
@@ -428,7 +431,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
         }
 
         brelse(bh);
-        befs_debug(sb, "<--- befs_read_inode()");
+        befs_debug(sb, "<--- %s", __func__);
         unlock_new_inode(inode);
         return inode;
 
@@ -437,7 +440,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 
       unacquire_none:
         iget_failed(inode);
-        befs_debug(sb, "<--- befs_read_inode() - Bad inode");
+        befs_debug(sb, "<--- %s - Bad inode", __func__);
         return ERR_PTR(ret);
 }
 
@@ -445,7 +448,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
  *
  * Taken from NFS implementation by Al Viro.
  */
-static int
+static int __init
 befs_init_inodecache(void)
 {
         befs_inode_cachep = kmem_cache_create("befs_inode_cache",
@@ -454,11 +457,9 @@ befs_init_inodecache(void)
                                                 SLAB_MEM_SPREAD),
                                               init_once);
         if (befs_inode_cachep == NULL) {
-                printk(KERN_ERR "befs_init_inodecache: "
-                       "Couldn't initialize inode slabcache\n");
+                pr_err("%s: Couldn't initialize inode slabcache\n", __func__);
                 return -ENOMEM;
         }
-
         return 0;
 }
 
@@ -544,16 +545,16 @@ befs_utf2nls(struct super_block *sb, const char *in,
          */
         int maxlen = in_len + 1;
 
-        befs_debug(sb, "---> utf2nls()");
+        befs_debug(sb, "---> %s", __func__);
 
         if (!nls) {
-                befs_error(sb, "befs_utf2nls called with no NLS table loaded");
+                befs_error(sb, "%s called with no NLS table loaded", __func__);
                 return -EINVAL;
         }
 
         *out = result = kmalloc(maxlen, GFP_NOFS);
         if (!*out) {
-                befs_error(sb, "befs_utf2nls() cannot allocate memory");
+                befs_error(sb, "%s cannot allocate memory", __func__);
                 *out_len = 0;
                 return -ENOMEM;
         }
@@ -575,14 +576,14 @@ befs_utf2nls(struct super_block *sb, const char *in,
         result[o] = '\0';
         *out_len = o;
 
-        befs_debug(sb, "<--- utf2nls()");
+        befs_debug(sb, "<--- %s", __func__);
 
         return o;
 
       conv_err:
         befs_error(sb, "Name using character set %s contains a character that "
                    "cannot be converted to unicode.", nls->charset);
-        befs_debug(sb, "<--- utf2nls()");
+        befs_debug(sb, "<--- %s", __func__);
         kfree(result);
         return -EILSEQ;
 }
@@ -623,16 +624,17 @@ befs_nls2utf(struct super_block *sb, const char *in,
          * in special cases */
         int maxlen = (3 * in_len) + 1;
 
-        befs_debug(sb, "---> nls2utf()\n");
+        befs_debug(sb, "---> %s\n", __func__);
 
         if (!nls) {
-                befs_error(sb, "befs_nls2utf called with no NLS table loaded.");
+                befs_error(sb, "%s called with no NLS table loaded.",
+                           __func__);
                 return -EINVAL;
         }
 
         *out = result = kmalloc(maxlen, GFP_NOFS);
         if (!*out) {
-                befs_error(sb, "befs_nls2utf() cannot allocate memory");
+                befs_error(sb, "%s cannot allocate memory", __func__);
                 *out_len = 0;
                 return -ENOMEM;
         }
@@ -653,14 +655,14 @@ befs_nls2utf(struct super_block *sb, const char *in,
         result[o] = '\0';
         *out_len = o;
 
-        befs_debug(sb, "<--- nls2utf()");
+        befs_debug(sb, "<--- %s", __func__);
 
         return i;
 
       conv_err:
         befs_error(sb, "Name using charecter set %s contains a charecter that "
                    "cannot be converted to unicode.", nls->charset);
-        befs_debug(sb, "<--- nls2utf()");
+        befs_debug(sb, "<--- %s", __func__);
         kfree(result);
         return -EILSEQ;
 }
@@ -715,8 +717,8 @@ parse_options(char *options, befs_mount_options * opts)
                         if (option >= 0)
                                 uid = make_kuid(current_user_ns(), option);
                         if (!uid_valid(uid)) {
-                                printk(KERN_ERR "BeFS: Invalid uid %d, "
-                                                "using default\n", option);
+                                pr_err("Invalid uid %d, "
+                                       "using default\n", option);
                                 break;
                         }
                         opts->uid = uid;
@@ -729,8 +731,8 @@ parse_options(char *options, befs_mount_options * opts)
                         if (option >= 0)
                                 gid = make_kgid(current_user_ns(), option);
                         if (!gid_valid(gid)) {
-                                printk(KERN_ERR "BeFS: Invalid gid %d, "
-                                                "using default\n", option);
+                                pr_err("Invalid gid %d, "
+                                       "using default\n", option);
                                 break;
                         }
                         opts->gid = gid;
@@ -740,8 +742,8 @@ parse_options(char *options, befs_mount_options * opts)
                         kfree(opts->iocharset);
                         opts->iocharset = match_strdup(&args[0]);
                         if (!opts->iocharset) {
-                                printk(KERN_ERR "BeFS: allocation failure for "
-                                                "iocharset string\n");
+                                pr_err("allocation failure for "
+                                       "iocharset string\n");
                                 return 0;
                         }
                         break;
@@ -749,8 +751,8 @@ parse_options(char *options, befs_mount_options * opts)
                         opts->debug = 1;
                         break;
                 default:
-                        printk(KERN_ERR "BeFS: Unrecognized mount option \"%s\" "
-                                        "or missing value\n", p);
+                        pr_err("Unrecognized mount option \"%s\" "
+                               "or missing value\n", p);
                         return 0;
                 }
         }
@@ -791,22 +793,20 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 
         save_mount_options(sb, data);
 
-        sb->s_fs_info = kmalloc(sizeof (*befs_sb), GFP_KERNEL);
+        sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL);
         if (sb->s_fs_info == NULL) {
-                printk(KERN_ERR
-                       "BeFS(%s): Unable to allocate memory for private "
+                pr_err("(%s): Unable to allocate memory for private "
                        "portion of superblock. Bailing.\n", sb->s_id);
                 goto unacquire_none;
         }
         befs_sb = BEFS_SB(sb);
-        memset(befs_sb, 0, sizeof(befs_sb_info));
 
         if (!parse_options((char *) data, &befs_sb->mount_opts)) {
                 befs_error(sb, "cannot parse mount options");
                 goto unacquire_priv_sbp;
         }
 
-        befs_debug(sb, "---> befs_fill_super()");
+        befs_debug(sb, "---> %s", __func__);
 
 #ifndef CONFIG_BEFS_RW
         if (!(sb->s_flags & MS_RDONLY)) {
@@ -854,7 +854,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
                 goto unacquire_priv_sbp;
 
         if( befs_sb->num_blocks > ~((sector_t)0) ) {
-                befs_error(sb, "blocks count: %Lu "
+                befs_error(sb, "blocks count: %llu "
                         "is larger than the host can use",
                         befs_sb->num_blocks);
                 goto unacquire_priv_sbp;
@@ -913,6 +913,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 static int
 befs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         if (!(*flags & MS_RDONLY))
                 return -EINVAL;
         return 0;
@@ -924,7 +925,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
         struct super_block *sb = dentry->d_sb;
         u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
-        befs_debug(sb, "---> befs_statfs()");
+        befs_debug(sb, "---> %s", __func__);
 
         buf->f_type = BEFS_SUPER_MAGIC;
         buf->f_bsize = sb->s_blocksize;
@@ -937,7 +938,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
         buf->f_fsid.val[1] = (u32)(id >> 32);
         buf->f_namelen = BEFS_NAME_LEN;
 
-        befs_debug(sb, "<--- befs_statfs()");
+        befs_debug(sb, "<--- %s", __func__);
 
         return 0;
 }
@@ -963,7 +964,7 @@ init_befs_fs(void)
 {
         int err;
 
-        printk(KERN_INFO "BeFS version: %s\n", BEFS_VERSION);
+        pr_info("version: %s\n", BEFS_VERSION);
 
         err = befs_init_inodecache();
         if (err)
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 8defc6b3f9a2..29aa5cf6639b 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -172,7 +172,7 @@ static void bfs_evict_inode(struct inode *inode)
 
         dprintf("ino=%08lx\n", ino);
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         invalidate_inode_buffers(inode);
         clear_inode(inode);
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 67be2951b98a..0f59799fa105 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -46,10 +46,15 @@
 #endif
 
 static int load_elf_binary(struct linux_binprm *bprm);
-static int load_elf_library(struct file *);
 static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *,
                                 int, int, unsigned long);
 
+#ifdef CONFIG_USELIB
+static int load_elf_library(struct file *);
+#else
+#define load_elf_library NULL
+#endif
+
 /*
  * If we don't support core dumping, then supply a NULL so we
  * don't even try.
@@ -1005,6 +1010,7 @@ out_free_ph:
         goto out;
 }
 
+#ifdef CONFIG_USELIB
 /* This is really simpleminded and specialized - we are loading an
    a.out library that is given an ELF header. */
 static int load_elf_library(struct file *file)
@@ -1083,6 +1089,7 @@ out_free_ph:
 out:
         return error;
 }
+#endif /* #ifdef CONFIG_USELIB */
 
 #ifdef CONFIG_ELF_CORE
 /*
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 1c740e152f38..b60500300dd7 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -656,6 +656,7 @@ static ssize_t bm_status_write(struct file * file, const char __user * buffer,
 
                         mutex_unlock(&root->d_inode->i_mutex);
                         dput(root);
+                        break;
                 default: return res;
         }
         return count;
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 4f70f383132c..29696b78d1f4 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -301,25 +301,25 @@ int bio_integrity_get_tag(struct bio *bio, void *tag_buf, unsigned int len)
 EXPORT_SYMBOL(bio_integrity_get_tag);
 
 /**
- * bio_integrity_generate - Generate integrity metadata for a bio
- * @bio:        bio to generate integrity metadata for
- *
- * Description: Generates integrity metadata for a bio by calling the
- * block device's generation callback function.  The bio must have a
- * bip attached with enough room to accommodate the generated
- * integrity metadata.
+ * bio_integrity_generate_verify - Generate/verify integrity metadata for a bio
+ * @bio:        bio to generate/verify integrity metadata for
+ * @operate:    operate number, 1 for generate, 0 for verify
  */
-static void bio_integrity_generate(struct bio *bio)
+static int bio_integrity_generate_verify(struct bio *bio, int operate)
 {
         struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
         struct blk_integrity_exchg bix;
         struct bio_vec bv;
         struct bvec_iter iter;
-        sector_t sector = bio->bi_iter.bi_sector;
-        unsigned int sectors, total;
+        sector_t sector;
+        unsigned int sectors, ret = 0;
         void *prot_buf = bio->bi_integrity->bip_buf;
 
-        total = 0;
+        if (operate)
+                sector = bio->bi_iter.bi_sector;
+        else
+                sector = bio->bi_integrity->bip_iter.bi_sector;
+
         bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
         bix.sector_size = bi->sector_size;
 
@@ -330,16 +330,37 @@ static void bio_integrity_generate(struct bio *bio)
                 bix.prot_buf = prot_buf;
                 bix.sector = sector;
 
-                bi->generate_fn(&bix);
+                if (operate) {
+                        bi->generate_fn(&bix);
+                } else {
+                        ret = bi->verify_fn(&bix);
+                        if (ret) {
+                                kunmap_atomic(kaddr);
+                                return ret;
+                        }
+                }
 
                 sectors = bv.bv_len / bi->sector_size;
                 sector += sectors;
                 prot_buf += sectors * bi->tuple_size;
-                total += sectors * bi->tuple_size;
-                BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
 
                 kunmap_atomic(kaddr);
         }
+        return ret;
+}
+
+/**
+ * bio_integrity_generate - Generate integrity metadata for a bio
+ * @bio:        bio to generate integrity metadata for
+ *
+ * Description: Generates integrity metadata for a bio by calling the
+ * block device's generation callback function.  The bio must have a
+ * bip attached with enough room to accommodate the generated
+ * integrity metadata.
+ */
+static void bio_integrity_generate(struct bio *bio)
+{
+        bio_integrity_generate_verify(bio, 1);
 }
 
 static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
@@ -454,40 +475,7 @@ EXPORT_SYMBOL(bio_integrity_prep);
  */
 static int bio_integrity_verify(struct bio *bio)
 {
-        struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-        struct blk_integrity_exchg bix;
-        struct bio_vec *bv;
-        sector_t sector = bio->bi_integrity->bip_iter.bi_sector;
-        unsigned int sectors, ret = 0;
-        void *prot_buf = bio->bi_integrity->bip_buf;
-        int i;
-
-        bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
-        bix.sector_size = bi->sector_size;
-
-        bio_for_each_segment_all(bv, bio, i) {
-                void *kaddr = kmap_atomic(bv->bv_page);
-
-                bix.data_buf = kaddr + bv->bv_offset;
-                bix.data_size = bv->bv_len;
-                bix.prot_buf = prot_buf;
-                bix.sector = sector;
-
-                ret = bi->verify_fn(&bix);
-
-                if (ret) {
-                        kunmap_atomic(kaddr);
-                        return ret;
-                }
-
-                sectors = bv->bv_len / bi->sector_size;
-                sector += sectors;
-                prot_buf += sectors * bi->tuple_size;
-
-                kunmap_atomic(kaddr);
-        }
-
-        return ret;
+        return bio_integrity_generate_verify(bio, 0);
 }
 
 /**
diff --git a/fs/bio.c b/fs/bio.c
index 8754e7b6eb49..b1bc722b89aa 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -116,7 +116,6 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
         if (!slab)
                 goto out_unlock;
 
-        printk(KERN_INFO "bio: create slab <%s> at %d\n", bslab->name, entry);
         bslab->slab = slab;
         bslab->slab_ref = 1;
         bslab->slab_size = sz;
@@ -1970,7 +1969,7 @@ int bio_associate_current(struct bio *bio)
 
         /* associate blkcg if exists */
         rcu_read_lock();
-        css = task_css(current, blkio_subsys_id);
+        css = task_css(current, blkio_cgrp_id);
         if (css && css_tryget(css))
                 bio->bi_css = css;
         rcu_read_unlock();
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1e86823a9cbd..ba0d2b05bb78 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -83,7 +83,7 @@ void kill_bdev(struct block_device *bdev)
 {
         struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-        if (mapping->nrpages == 0)
+        if (mapping->nrpages == 0 && mapping->nrshadows == 0)
                 return;
 
         invalidate_bh_lrus();
@@ -419,7 +419,7 @@ static void bdev_evict_inode(struct inode *inode)
 {
         struct block_device *bdev = &BDEV_I(inode)->bdev;
         struct list_head *p;
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         invalidate_inode_buffers(inode); /* is it needed here? */
         clear_inode(inode);
         spin_lock(&bdev_lock);
@@ -1523,7 +1523,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
                 ssize_t err;
 
                 err = generic_write_sync(file, pos, ret);
-                if (err < 0 && ret > 0)
+                if (err < 0)
                         ret = err;
         }
         blk_finish_plug(&plug);
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index c1e0b0caf9cc..ecb5832c0967 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2014 Fujitsu.  All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public
@@ -21,708 +22,313 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
+#include <linux/workqueue.h>
 #include "async-thread.h"
+#include "ctree.h"
+
+#define WORK_DONE_BIT 0
+#define WORK_ORDER_DONE_BIT 1
+#define WORK_HIGH_PRIO_BIT 2
+
+#define NO_THRESHOLD (-1)
+#define DFT_THRESHOLD (32)
+
+struct __btrfs_workqueue {
+        struct workqueue_struct *normal_wq;
+        /* List head pointing to ordered work list */
+        struct list_head ordered_list;
+
+        /* Spinlock for ordered_list */
+        spinlock_t list_lock;
+
+        /* Thresholding related variants */
+        atomic_t pending;
+        int max_active;
+        int current_max;
+        int thresh;
+        unsigned int count;
+        spinlock_t thres_lock;
+};
 
-#define WORK_QUEUED_BIT 0
-#define WORK_DONE_BIT 1
-#define WORK_ORDER_DONE_BIT 2
-#define WORK_HIGH_PRIO_BIT 3
-
-/*
- * container for the kthread task pointer and the list of pending work
- * One of these is allocated per thread.
- */
-struct btrfs_worker_thread {
-        /* pool we belong to */
-        struct btrfs_workers *workers;
-
-        /* list of struct btrfs_work that are waiting for service */
-        struct list_head pending;
-        struct list_head prio_pending;
-
-        /* list of worker threads from struct btrfs_workers */
-        struct list_head worker_list;
-
-        /* kthread */
-        struct task_struct *task;
+struct btrfs_workqueue {
+        struct __btrfs_workqueue *normal;
+        struct __btrfs_workqueue *high;
+};
 
-        /* number of things on the pending list */
-        atomic_t num_pending;
+static inline struct __btrfs_workqueue
+*__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
+                         int thresh)
+{
+        struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
 
-        /* reference counter for this struct */
-        atomic_t refs;
+        if (unlikely(!ret))
+                return NULL;
 
-        unsigned long sequence;
+        ret->max_active = max_active;
+        atomic_set(&ret->pending, 0);
+        if (thresh == 0)
+                thresh = DFT_THRESHOLD;
+        /* For low threshold, disabling threshold is a better choice */
+        if (thresh < DFT_THRESHOLD) {
+                ret->current_max = max_active;
+                ret->thresh = NO_THRESHOLD;
+        } else {
+                ret->current_max = 1;
+                ret->thresh = thresh;
+        }
 
-        /* protects the pending list. */
-        spinlock_t lock;
+        if (flags & WQ_HIGHPRI)
+                ret->normal_wq = alloc_workqueue("%s-%s-high", flags,
+                                                 ret->max_active,
+                                                 "btrfs", name);
+        else
+                ret->normal_wq = alloc_workqueue("%s-%s", flags,
+                                                 ret->max_active, "btrfs",
+                                                 name);
+        if (unlikely(!ret->normal_wq)) {
+                kfree(ret);
+                return NULL;
+        }
 
-        /* set to non-zero when this thread is already awake and kicking */
-        int working;
+        INIT_LIST_HEAD(&ret->ordered_list);
+        spin_lock_init(&ret->list_lock);
+        spin_lock_init(&ret->thres_lock);
+        trace_btrfs_workqueue_alloc(ret, name, flags & WQ_HIGHPRI);
+        return ret;
+}
 
-        /* are we currently idle */
-        int idle;
-};
+static inline void
+__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq);
 
-static int __btrfs_start_workers(struct btrfs_workers *workers);
+struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
+                                              int flags,
+                                              int max_active,
+                                              int thresh)
+{
+        struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
 
-/*
- * btrfs_start_workers uses kthread_run, which can block waiting for memory
- * for a very long time.  It will actually throttle on page writeback,
- * and so it may not make progress until after our btrfs worker threads
- * process all of the pending work structs in their queue
- *
- * This means we can't use btrfs_start_workers from inside a btrfs worker
- * thread that is used as part of cleaning dirty memory, which pretty much
- * involves all of the worker threads.
- *
- * Instead we have a helper queue who never has more than one thread
- * where we scheduler thread start operations.  This worker_start struct
- * is used to contain the work and hold a pointer to the queue that needs
- * another worker.
- */
-struct worker_start {
-        struct btrfs_work work;
-        struct btrfs_workers *queue;
-};
+        if (unlikely(!ret))
+                return NULL;
 
-static void start_new_worker_func(struct btrfs_work *work)
-{
-        struct worker_start *start;
-        start = container_of(work, struct worker_start, work);
-        __btrfs_start_workers(start->queue);
-        kfree(start);
-}
+        ret->normal = __btrfs_alloc_workqueue(name, flags & ~WQ_HIGHPRI,
+                                              max_active, thresh);
+        if (unlikely(!ret->normal)) {
+                kfree(ret);
+                return NULL;
+        }
 
-/*
- * helper function to move a thread onto the idle list after it
- * has finished some requests.
- */
-static void check_idle_worker(struct btrfs_worker_thread *worker)
-{
-        if (!worker->idle && atomic_read(&worker->num_pending) <
-            worker->workers->idle_thresh / 2) {
-                unsigned long flags;
-                spin_lock_irqsave(&worker->workers->lock, flags);
-                worker->idle = 1;
-
-                /* the list may be empty if the worker is just starting */
-                if (!list_empty(&worker->worker_list) &&
-                    !worker->workers->stopping) {
-                        list_move(&worker->worker_list,
-                                 &worker->workers->idle_list);
+        if (flags & WQ_HIGHPRI) {
+                ret->high = __btrfs_alloc_workqueue(name, flags, max_active,
+                                                    thresh);
+                if (unlikely(!ret->high)) {
+                        __btrfs_destroy_workqueue(ret->normal);
+                        kfree(ret);
+                        return NULL;
                 }
-                spin_unlock_irqrestore(&worker->workers->lock, flags);
         }
+        return ret;
 }
 
 /*
- * helper function to move a thread off the idle list after new
- * pending work is added.
+ * Hook for threshold which will be called in btrfs_queue_work.
+ * This hook WILL be called in IRQ handler context,
+ * so workqueue_set_max_active MUST NOT be called in this hook
  */
-static void check_busy_worker(struct btrfs_worker_thread *worker)
+static inline void thresh_queue_hook(struct __btrfs_workqueue *wq)
 {
-        if (worker->idle && atomic_read(&worker->num_pending) >=
-            worker->workers->idle_thresh) {
-                unsigned long flags;
-                spin_lock_irqsave(&worker->workers->lock, flags);
-                worker->idle = 0;
-
-                if (!list_empty(&worker->worker_list) &&
-                    !worker->workers->stopping) {
-                        list_move_tail(&worker->worker_list,
-                                      &worker->workers->worker_list);
-                }
-                spin_unlock_irqrestore(&worker->workers->lock, flags);
-        }
+        if (wq->thresh == NO_THRESHOLD)
+                return;
+        atomic_inc(&wq->pending);
 }
 
-static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
+/*
+ * Hook for threshold which will be called before executing the work,
+ * This hook is called in kthread content.
+ * So workqueue_set_max_active is called here.
+ */
+static inline void thresh_exec_hook(struct __btrfs_workqueue *wq)
 {
-        struct btrfs_workers *workers = worker->workers;
-        struct worker_start *start;
-        unsigned long flags;
+        int new_max_active;
+        long pending;
+        int need_change = 0;
 
-        rmb();
-        if (!workers->atomic_start_pending)
+        if (wq->thresh == NO_THRESHOLD)
                 return;
 
-        start = kzalloc(sizeof(*start), GFP_NOFS);
-        if (!start)
-                return;
-
-        start->work.func = start_new_worker_func;
-        start->queue = workers;
-
-        spin_lock_irqsave(&workers->lock, flags);
-        if (!workers->atomic_start_pending)
-                goto out;
-
-        workers->atomic_start_pending = 0;
-        if (workers->num_workers + workers->num_workers_starting >=
-            workers->max_workers)
-                goto out;
-
-        workers->num_workers_starting += 1;
-        spin_unlock_irqrestore(&workers->lock, flags);
-        btrfs_queue_worker(workers->atomic_worker_start, &start->work);
-        return;
+        atomic_dec(&wq->pending);
+        spin_lock(&wq->thres_lock);
+        /*
+         * Use wq->count to limit the calling frequency of
+         * workqueue_set_max_active.
+         */
+        wq->count++;
+        wq->count %= (wq->thresh / 4);
+        if (!wq->count)
+                goto  out;
+        new_max_active = wq->current_max;
 
+        /*
+         * pending may be changed later, but it's OK since we really
+         * don't need it so accurate to calculate new_max_active.
+         */
+        pending = atomic_read(&wq->pending);
+        if (pending > wq->thresh)
+                new_max_active++;
+        if (pending < wq->thresh / 2)
+                new_max_active--;
+        new_max_active = clamp_val(new_max_active, 1, wq->max_active);
+        if (new_max_active != wq->current_max)  {
+                need_change = 1;
+                wq->current_max = new_max_active;
+        }
 out:
-        kfree(start);
-        spin_unlock_irqrestore(&workers->lock, flags);
+        spin_unlock(&wq->thres_lock);
+
+        if (need_change) {
+                workqueue_set_max_active(wq->normal_wq, wq->current_max);
+        }
 }
 
-static noinline void run_ordered_completions(struct btrfs_workers *workers,
-                                            struct btrfs_work *work)
+static void run_ordered_work(struct __btrfs_workqueue *wq)
 {
-        if (!workers->ordered)
-                return;
-
-        set_bit(WORK_DONE_BIT, &work->flags);
-
-        spin_lock(&workers->order_lock);
+        struct list_head *list = &wq->ordered_list;
+        struct btrfs_work *work;
+        spinlock_t *lock = &wq->list_lock;
+        unsigned long flags;
 
         while (1) {
-                if (!list_empty(&workers->prio_order_list)) {
-                        work = list_entry(workers->prio_order_list.next,
-                                          struct btrfs_work, order_list);
-                } else if (!list_empty(&workers->order_list)) {
-                        work = list_entry(workers->order_list.next,
-                                          struct btrfs_work, order_list);
-                } else {
+                spin_lock_irqsave(lock, flags);
+                if (list_empty(list))
                         break;
-                }
+                work = list_entry(list->next, struct btrfs_work,
+                                  ordered_list);
                 if (!test_bit(WORK_DONE_BIT, &work->flags))
                         break;
 
-                /* we are going to call the ordered done function, but
+                /*
+                 * we are going to call the ordered done function, but
                  * we leave the work item on the list as a barrier so
                  * that later work items that are done don't have their
                  * functions called before this one returns
                  */
                 if (test_and_set_bit(WORK_ORDER_DONE_BIT, &work->flags))
                         break;
-
-                spin_unlock(&workers->order_lock);
-
+                trace_btrfs_ordered_sched(work);
+                spin_unlock_irqrestore(lock, flags);
                 work->ordered_func(work);
 
                 /* now take the lock again and drop our item from the list */
-                spin_lock(&workers->order_lock);
-                list_del(&work->order_list);
-                spin_unlock(&workers->order_lock);
+                spin_lock_irqsave(lock, flags);
+                list_del(&work->ordered_list);
+                spin_unlock_irqrestore(lock, flags);
 
                 /*
                  * we don't want to call the ordered free functions
                  * with the lock held though
                  */
                 work->ordered_free(work);
-                spin_lock(&workers->order_lock);
-        }
-
-        spin_unlock(&workers->order_lock);
-}
-
-static void put_worker(struct btrfs_worker_thread *worker)
-{
-        if (atomic_dec_and_test(&worker->refs))
-                kfree(worker);
-}
-
-static int try_worker_shutdown(struct btrfs_worker_thread *worker)
-{
-        int freeit = 0;
-
-        spin_lock_irq(&worker->lock);
-        spin_lock(&worker->workers->lock);
-        if (worker->workers->num_workers > 1 &&
-            worker->idle &&
-            !worker->working &&
-            !list_empty(&worker->worker_list) &&
-            list_empty(&worker->prio_pending) &&
-            list_empty(&worker->pending) &&
-            atomic_read(&worker->num_pending) == 0) {
-                freeit = 1;
-                list_del_init(&worker->worker_list);
-                worker->workers->num_workers--;
+                trace_btrfs_all_work_done(work);
         }
-        spin_unlock(&worker->workers->lock);
-        spin_unlock_irq(&worker->lock);
-
-        if (freeit)
-                put_worker(worker);
-        return freeit;
+        spin_unlock_irqrestore(lock, flags);
 }
 
-static struct btrfs_work *get_next_work(struct btrfs_worker_thread *worker,
-                                        struct list_head *prio_head,
-                                        struct list_head *head)
-{
-        struct btrfs_work *work = NULL;
-        struct list_head *cur = NULL;
-
-        if (!list_empty(prio_head))
-                cur = prio_head->next;
-
-        smp_mb();
-        if (!list_empty(&worker->prio_pending))
-                goto refill;
-
-        if (!list_empty(head))
-                cur = head->next;
-
-        if (cur)
-                goto out;
-
-refill:
-        spin_lock_irq(&worker->lock);
-        list_splice_tail_init(&worker->prio_pending, prio_head);
-        list_splice_tail_init(&worker->pending, head);
-
-        if (!list_empty(prio_head))
-                cur = prio_head->next;
-        else if (!list_empty(head))
-                cur = head->next;
-        spin_unlock_irq(&worker->lock);
-
-        if (!cur)
-                goto out_fail;
-
-out:
-        work = list_entry(cur, struct btrfs_work, list);
-
-out_fail:
-        return work;
-}
-
-/*
- * main loop for servicing work items
- */
-static int worker_loop(void *arg)
+static void normal_work_helper(struct work_struct *arg)
 {
-        struct btrfs_worker_thread *worker = arg;
-        struct list_head head;
-        struct list_head prio_head;
         struct btrfs_work *work;
+        struct __btrfs_workqueue *wq;
+        int need_order = 0;
 
-        INIT_LIST_HEAD(&head);
-        INIT_LIST_HEAD(&prio_head);
-
-        do {
-again:
-                while (1) {
-
-
-                        work = get_next_work(worker, &prio_head, &head);
-                        if (!work)
-                                break;
-
-                        list_del(&work->list);
-                        clear_bit(WORK_QUEUED_BIT, &work->flags);
-
-                        work->worker = worker;
-
-                        work->func(work);
-
-                        atomic_dec(&worker->num_pending);
-                        /*
-                         * unless this is an ordered work queue,
-                         * 'work' was probably freed by func above.
-                         */
-                        run_ordered_completions(worker->workers, work);
-
-                        check_pending_worker_creates(worker);
-                        cond_resched();
-                }
-
-                spin_lock_irq(&worker->lock);
-                check_idle_worker(worker);
-
-                if (freezing(current)) {
-                        worker->working = 0;
-                        spin_unlock_irq(&worker->lock);
-                        try_to_freeze();
-                } else {
-                        spin_unlock_irq(&worker->lock);
-                        if (!kthread_should_stop()) {
-                                cpu_relax();
-                                /*
-                                 * we've dropped the lock, did someone else
-                                 * jump_in?
-                                 */
-                                smp_mb();
-                                if (!list_empty(&worker->pending) ||
-                                    !list_empty(&worker->prio_pending))
-                                        continue;
-
-                                /*
-                                 * this short schedule allows more work to
-                                 * come in without the queue functions
-                                 * needing to go through wake_up_process()
-                                 *
-                                 * worker->working is still 1, so nobody
-                                 * is going to try and wake us up
-                                 */
-                                schedule_timeout(1);
-                                smp_mb();
-                                if (!list_empty(&worker->pending) ||
-                                    !list_empty(&worker->prio_pending))
-                                        continue;
-
-                                if (kthread_should_stop())
-                                        break;
-
-                                /* still no more work?, sleep for real */
-                                spin_lock_irq(&worker->lock);
-                                set_current_state(TASK_INTERRUPTIBLE);
-                                if (!list_empty(&worker->pending) ||
-                                    !list_empty(&worker->prio_pending)) {
-                                        spin_unlock_irq(&worker->lock);
-                                        set_current_state(TASK_RUNNING);
-                                        goto again;
-                                }
-
-                                /*
-                                 * this makes sure we get a wakeup when someone
-                                 * adds something new to the queue
-                                 */
-                                worker->working = 0;
-                                spin_unlock_irq(&worker->lock);
-
-                                if (!kthread_should_stop()) {
-                                        schedule_timeout(HZ * 120);
-                                        if (!worker->working &&
-                                            try_worker_shutdown(worker)) {
-                                                return 0;
-                                        }
-                                }
-                        }
-                        __set_current_state(TASK_RUNNING);
-                }
-        } while (!kthread_should_stop());
-        return 0;
-}
-
-/*
- * this will wait for all the worker threads to shutdown
- */
-void btrfs_stop_workers(struct btrfs_workers *workers)
-{
-        struct list_head *cur;
-        struct btrfs_worker_thread *worker;
-        int can_stop;
-
-        spin_lock_irq(&workers->lock);
-        workers->stopping = 1;
-        list_splice_init(&workers->idle_list, &workers->worker_list);
-        while (!list_empty(&workers->worker_list)) {
-                cur = workers->worker_list.next;
-                worker = list_entry(cur, struct btrfs_worker_thread,
-                                    worker_list);
-
-                atomic_inc(&worker->refs);
-                workers->num_workers -= 1;
-                if (!list_empty(&worker->worker_list)) {
-                        list_del_init(&worker->worker_list);
-                        put_worker(worker);
-                        can_stop = 1;
-                } else
-                        can_stop = 0;
-                spin_unlock_irq(&workers->lock);
-                if (can_stop)
-                        kthread_stop(worker->task);
-                spin_lock_irq(&workers->lock);
-                put_worker(worker);
+        work = container_of(arg, struct btrfs_work, normal_work);
+        /*
+         * We should not touch things inside work in the following cases:
+         * 1) after work->func() if it has no ordered_free
+         *    Since the struct is freed in work->func().
+         * 2) after setting WORK_DONE_BIT
+         *    The work may be freed in other threads almost instantly.
+         * So we save the needed things here.
+         */
+        if (work->ordered_func)
+                need_order = 1;
+        wq = work->wq;
+
+        trace_btrfs_work_sched(work);
+        thresh_exec_hook(wq);
+        work->func(work);
+        if (need_order) {
+                set_bit(WORK_DONE_BIT, &work->flags);
+                run_ordered_work(wq);
         }
-        spin_unlock_irq(&workers->lock);
+        if (!need_order)
+                trace_btrfs_all_work_done(work);
 }
 
-/*
- * simple init on struct btrfs_workers
- */
-void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
-                        struct btrfs_workers *async_helper)
+void btrfs_init_work(struct btrfs_work *work,
+                     btrfs_func_t func,
+                     btrfs_func_t ordered_func,
+                     btrfs_func_t ordered_free)
 {
-        workers->num_workers = 0;
-        workers->num_workers_starting = 0;
-        INIT_LIST_HEAD(&workers->worker_list);
-        INIT_LIST_HEAD(&workers->idle_list);
-        INIT_LIST_HEAD(&workers->order_list);
-        INIT_LIST_HEAD(&workers->prio_order_list);
-        spin_lock_init(&workers->lock);
-        spin_lock_init(&workers->order_lock);
-        workers->max_workers = max;
-        workers->idle_thresh = 32;
-        workers->name = name;
-        workers->ordered = 0;
-        workers->atomic_start_pending = 0;
-        workers->atomic_worker_start = async_helper;
-        workers->stopping = 0;
+        work->func = func;
+        work->ordered_func = ordered_func;
+        work->ordered_free = ordered_free;
+        INIT_WORK(&work->normal_work, normal_work_helper);
+        INIT_LIST_HEAD(&work->ordered_list);
+        work->flags = 0;
 }
 
-/*
- * starts new worker threads.  This does not enforce the max worker
- * count in case you need to temporarily go past it.
- */
-static int __btrfs_start_workers(struct btrfs_workers *workers)
+static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
+                                      struct btrfs_work *work)
 {
-        struct btrfs_worker_thread *worker;
-        int ret = 0;
-
-        worker = kzalloc(sizeof(*worker), GFP_NOFS);
-        if (!worker) {
-                ret = -ENOMEM;
-                goto fail;
-        }
-
-        INIT_LIST_HEAD(&worker->pending);
-        INIT_LIST_HEAD(&worker->prio_pending);
-        INIT_LIST_HEAD(&worker->worker_list);
-        spin_lock_init(&worker->lock);
-
-        atomic_set(&worker->num_pending, 0);
-        atomic_set(&worker->refs, 1);
-        worker->workers = workers;
-        worker->task = kthread_create(worker_loop, worker,
-                                      "btrfs-%s-%d", workers->name,
-                                      workers->num_workers + 1);
-        if (IS_ERR(worker->task)) {
-                ret = PTR_ERR(worker->task);
-                goto fail;
-        }
+        unsigned long flags;
 
-        spin_lock_irq(&workers->lock);
-        if (workers->stopping) {
-                spin_unlock_irq(&workers->lock);
-                ret = -EINVAL;
-                goto fail_kthread;
+        work->wq = wq;
+        thresh_queue_hook(wq);
+        if (work->ordered_func) {
+                spin_lock_irqsave(&wq->list_lock, flags);
+                list_add_tail(&work->ordered_list, &wq->ordered_list);
+                spin_unlock_irqrestore(&wq->list_lock, flags);
         }
-        list_add_tail(&worker->worker_list, &workers->idle_list);
-        worker->idle = 1;
-        workers->num_workers++;
-        workers->num_workers_starting--;
-        WARN_ON(workers->num_workers_starting < 0);
-        spin_unlock_irq(&workers->lock);
-
-        wake_up_process(worker->task);
-        return 0;
-
-fail_kthread:
-        kthread_stop(worker->task);
-fail:
-        kfree(worker);
-        spin_lock_irq(&workers->lock);
-        workers->num_workers_starting--;
-        spin_unlock_irq(&workers->lock);
-        return ret;
+        queue_work(wq->normal_wq, &work->normal_work);
+        trace_btrfs_work_queued(work);
 }
 
-int btrfs_start_workers(struct btrfs_workers *workers)
+void btrfs_queue_work(struct btrfs_workqueue *wq,
+                      struct btrfs_work *work)
 {
-        spin_lock_irq(&workers->lock);
-        workers->num_workers_starting++;
-        spin_unlock_irq(&workers->lock);
-        return __btrfs_start_workers(workers);
-}
-
-/*
- * run through the list and find a worker thread that doesn't have a lot
- * to do right now.  This can return null if we aren't yet at the thread
- * count limit and all of the threads are busy.
- */
-static struct btrfs_worker_thread *next_worker(struct btrfs_workers *workers)
-{
-        struct btrfs_worker_thread *worker;
-        struct list_head *next;
-        int enforce_min;
-
-        enforce_min = (workers->num_workers + workers->num_workers_starting) <
-                workers->max_workers;
-
-        /*
-         * if we find an idle thread, don't move it to the end of the
-         * idle list.  This improves the chance that the next submission
-         * will reuse the same thread, and maybe catch it while it is still
-         * working
-         */
-        if (!list_empty(&workers->idle_list)) {
-                next = workers->idle_list.next;
-                worker = list_entry(next, struct btrfs_worker_thread,
-                                    worker_list);
-                return worker;
-        }
-        if (enforce_min || list_empty(&workers->worker_list))
-                return NULL;
-
-        /*
-         * if we pick a busy task, move the task to the end of the list.
-         * hopefully this will keep things somewhat evenly balanced.
-         * Do the move in batches based on the sequence number.  This groups
-         * requests submitted at roughly the same time onto the same worker.
-         */
-        next = workers->worker_list.next;
-        worker = list_entry(next, struct btrfs_worker_thread, worker_list);
-        worker->sequence++;
+        struct __btrfs_workqueue *dest_wq;
 
-        if (worker->sequence % workers->idle_thresh == 0)
-                list_move_tail(next, &workers->worker_list);
-        return worker;
+        if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags) && wq->high)
+                dest_wq = wq->high;
+        else
+                dest_wq = wq->normal;
+        __btrfs_queue_work(dest_wq, work);
 }
 
-/*
- * selects a worker thread to take the next job.  This will either find
- * an idle worker, start a new worker up to the max count, or just return
- * one of the existing busy workers.
- */
-static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
+static inline void
+__btrfs_destroy_workqueue(struct __btrfs_workqueue *wq)
 {
-        struct btrfs_worker_thread *worker;
-        unsigned long flags;
-        struct list_head *fallback;
-        int ret;
-
-        spin_lock_irqsave(&workers->lock, flags);
-again:
-        worker = next_worker(workers);
-
-        if (!worker) {
-                if (workers->num_workers + workers->num_workers_starting >=
-                    workers->max_workers) {
-                        goto fallback;
-                } else if (workers->atomic_worker_start) {
-                        workers->atomic_start_pending = 1;
-                        goto fallback;
-                } else {
-                        workers->num_workers_starting++;
-                        spin_unlock_irqrestore(&workers->lock, flags);
-                        /* we're below the limit, start another worker */
-                        ret = __btrfs_start_workers(workers);
-                        spin_lock_irqsave(&workers->lock, flags);
-                        if (ret)
-                                goto fallback;
-                        goto again;
-                }
-        }
-        goto found;
-
-fallback:
-        fallback = NULL;
-        /*
-         * we have failed to find any workers, just
-         * return the first one we can find.
-         */
-        if (!list_empty(&workers->worker_list))
-                fallback = workers->worker_list.next;
-        if (!list_empty(&workers->idle_list))
-                fallback = workers->idle_list.next;
-        BUG_ON(!fallback);
-        worker = list_entry(fallback,
-                  struct btrfs_worker_thread, worker_list);
-found:
-        /*
-         * this makes sure the worker doesn't exit before it is placed
-         * onto a busy/idle list
-         */
-        atomic_inc(&worker->num_pending);
-        spin_unlock_irqrestore(&workers->lock, flags);
-        return worker;
+        destroy_workqueue(wq->normal_wq);
+        trace_btrfs_workqueue_destroy(wq);
+        kfree(wq);
 }
 
-/*
- * btrfs_requeue_work just puts the work item back on the tail of the list
- * it was taken from.  It is intended for use with long running work functions
- * that make some progress and want to give the cpu up for others.
- */
-void btrfs_requeue_work(struct btrfs_work *work)
+void btrfs_destroy_workqueue(struct btrfs_workqueue *wq)
 {
-        struct btrfs_worker_thread *worker = work->worker;
-        unsigned long flags;
-        int wake = 0;
-
-        if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
+        if (!wq)
                 return;
-
-        spin_lock_irqsave(&worker->lock, flags);
-        if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags))
-                list_add_tail(&work->list, &worker->prio_pending);
-        else
-                list_add_tail(&work->list, &worker->pending);
-        atomic_inc(&worker->num_pending);
-
-        /* by definition we're busy, take ourselves off the idle
-         * list
-         */
-        if (worker->idle) {
-                spin_lock(&worker->workers->lock);
-                worker->idle = 0;
-                list_move_tail(&worker->worker_list,
-                              &worker->workers->worker_list);
-                spin_unlock(&worker->workers->lock);
-        }
-        if (!worker->working) {
-                wake = 1;
-                worker->working = 1;
-        }
-
-        if (wake)
-                wake_up_process(worker->task);
-        spin_unlock_irqrestore(&worker->lock, flags);
+        if (wq->high)
+                __btrfs_destroy_workqueue(wq->high);
+        __btrfs_destroy_workqueue(wq->normal);
+        kfree(wq);
 }
 
-void btrfs_set_work_high_prio(struct btrfs_work *work)
+void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max)
 {
-        set_bit(WORK_HIGH_PRIO_BIT, &work->flags);
+        wq->normal->max_active = max;
+        if (wq->high)
+                wq->high->max_active = max;
 }
 
-/*
- * places a struct btrfs_work into the pending queue of one of the kthreads
- */
-void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
+void btrfs_set_work_high_priority(struct btrfs_work *work)
 {
-        struct btrfs_worker_thread *worker;
-        unsigned long flags;
-        int wake = 0;
-
-        /* don't requeue something already on a list */
-        if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
-                return;
-
-        worker = find_worker(workers);
-        if (workers->ordered) {
-                /*
-                 * you're not allowed to do ordered queues from an
-                 * interrupt handler
-                 */
-                spin_lock(&workers->order_lock);
-                if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags)) {
-                        list_add_tail(&work->order_list,
-                                      &workers->prio_order_list);
-                } else {
-                        list_add_tail(&work->order_list, &workers->order_list);
-                }
-                spin_unlock(&workers->order_lock);
-        } else {
-                INIT_LIST_HEAD(&work->order_list);
-        }
-
-        spin_lock_irqsave(&worker->lock, flags);
-
-        if (test_bit(WORK_HIGH_PRIO_BIT, &work->flags))
-                list_add_tail(&work->list, &worker->prio_pending);
-        else
-                list_add_tail(&work->list, &worker->pending);
-        check_busy_worker(worker);
-
-        /*
-         * avoid calling into wake_up_process if this thread has already
-         * been kicked
-         */
-        if (!worker->working)
-                wake = 1;
-        worker->working = 1;
-
-        if (wake)
-                wake_up_process(worker->task);
-        spin_unlock_irqrestore(&worker->lock, flags);
+        set_bit(WORK_HIGH_PRIO_BIT, &work->flags);
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 1f26792683ed..9c6b66d15fb0 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2014 Fujitsu.  All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public
@@ -19,103 +20,35 @@
 #ifndef __BTRFS_ASYNC_THREAD_
 #define __BTRFS_ASYNC_THREAD_
 
-struct btrfs_worker_thread;
+struct btrfs_workqueue;
+/* Internal use only */
+struct __btrfs_workqueue;
+struct btrfs_work;
+typedef void (*btrfs_func_t)(struct btrfs_work *arg);
 
-/*
- * This is similar to a workqueue, but it is meant to spread the operations
- * across all available cpus instead of just the CPU that was used to
- * queue the work.  There is also some batching introduced to try and
- * cut down on context switches.
- *
- * By default threads are added on demand up to 2 * the number of cpus.
- * Changing struct btrfs_workers->max_workers is one way to prevent
- * demand creation of kthreads.
- *
- * the basic model of these worker threads is to embed a btrfs_work
- * structure in your own data struct, and use container_of in a
- * work function to get back to your data struct.
- */
 struct btrfs_work {
-        /*
-         * func should be set to the function you want called
-         * your work struct is passed as the only arg
-         *
-         * ordered_func must be set for work sent to an ordered work queue,
-         * and it is called to complete a given work item in the same
-         * order they were sent to the queue.
-         */
-        void (*func)(struct btrfs_work *work);
-        void (*ordered_func)(struct btrfs_work *work);
-        void (*ordered_free)(struct btrfs_work *work);
-
-        /*
-         * flags should be set to zero.  It is used to make sure the
-         * struct is only inserted once into the list.
-         */
+        btrfs_func_t func;
+        btrfs_func_t ordered_func;
+        btrfs_func_t ordered_free;
+
+        /* Don't touch things below */
+        struct work_struct normal_work;
+        struct list_head ordered_list;
+        struct __btrfs_workqueue *wq;
         unsigned long flags;
-
-        /* don't touch these */
-        struct btrfs_worker_thread *worker;
-        struct list_head list;
-        struct list_head order_list;
-};
-
-struct btrfs_workers {
-        /* current number of running workers */
-        int num_workers;
-
-        int num_workers_starting;
-
-        /* max number of workers allowed.  changed by btrfs_start_workers */
-        int max_workers;
-
-        /* once a worker has this many requests or fewer, it is idle */
-        int idle_thresh;
-
-        /* force completions in the order they were queued */
-        int ordered;
-
-        /* more workers required, but in an interrupt handler */
-        int atomic_start_pending;
-
-        /*
-         * are we allowed to sleep while starting workers or are we required
-         * to start them at a later time?  If we can't sleep, this indicates
-         * which queue we need to use to schedule thread creation.
-         */
-        struct btrfs_workers *atomic_worker_start;
-
-        /* list with all the work threads.  The workers on the idle thread
-         * may be actively servicing jobs, but they haven't yet hit the
-         * idle thresh limit above.
-         */
-        struct list_head worker_list;
-        struct list_head idle_list;
-
-        /*
-         * when operating in ordered mode, this maintains the list
-         * of work items waiting for completion
-         */
-        struct list_head order_list;
-        struct list_head prio_order_list;
-
-        /* lock for finding the next worker thread to queue on */
-        spinlock_t lock;
-
-        /* lock for the ordered lists */
-        spinlock_t order_lock;
-
-        /* extra name for this worker, used for current->name */
-        char *name;
-
-        int stopping;
 };
 
-void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
-int btrfs_start_workers(struct btrfs_workers *workers);
-void btrfs_stop_workers(struct btrfs_workers *workers);
-void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
-                        struct btrfs_workers *async_starter);
-void btrfs_requeue_work(struct btrfs_work *work);
-void btrfs_set_work_high_prio(struct btrfs_work *work);
+struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
+                                              int flags,
+                                              int max_active,
+                                              int thresh);
+void btrfs_init_work(struct btrfs_work *work,
+                     btrfs_func_t func,
+                     btrfs_func_t ordered_func,
+                     btrfs_func_t ordered_free);
+void btrfs_queue_work(struct btrfs_workqueue *wq,
+                      struct btrfs_work *work);
+void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
+void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
+void btrfs_set_work_high_priority(struct btrfs_work *work);
 #endif
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index aded3ef3d3d4..aad7201ad11b 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -220,7 +220,8 @@ static int __add_prelim_ref(struct list_head *head, u64 root_id,
 
 static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
                            struct ulist *parents, struct __prelim_ref *ref,
-                           int level, u64 time_seq, const u64 *extent_item_pos)
+                           int level, u64 time_seq, const u64 *extent_item_pos,
+                           u64 total_refs)
 {
         int ret = 0;
         int slot;
@@ -249,7 +250,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
         if (path->slots[0] >= btrfs_header_nritems(path->nodes[0]))
                 ret = btrfs_next_old_leaf(root, path, time_seq);
 
-        while (!ret && count < ref->count) {
+        while (!ret && count < total_refs) {
                 eb = path->nodes[0];
                 slot = path->slots[0];
 
@@ -306,7 +307,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
                                   struct btrfs_path *path, u64 time_seq,
                                   struct __prelim_ref *ref,
                                   struct ulist *parents,
-                                  const u64 *extent_item_pos)
+                                  const u64 *extent_item_pos, u64 total_refs)
 {
         struct btrfs_root *root;
         struct btrfs_key root_key;
@@ -361,7 +362,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
         }
 
         ret = add_all_parents(root, path, parents, ref, level, time_seq,
-                              extent_item_pos);
+                              extent_item_pos, total_refs);
 out:
         path->lowest_level = 0;
         btrfs_release_path(path);
@@ -374,7 +375,7 @@ out:
 static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
                                    struct btrfs_path *path, u64 time_seq,
                                    struct list_head *head,
-                                   const u64 *extent_item_pos)
+                                   const u64 *extent_item_pos, u64 total_refs)
 {
         int err;
         int ret = 0;
@@ -400,7 +401,8 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
                 if (ref->count == 0)
                         continue;
                 err = __resolve_indirect_ref(fs_info, path, time_seq, ref,
-                                             parents, extent_item_pos);
+                                             parents, extent_item_pos,
+                                             total_refs);
                 /*
                  * we can only tolerate ENOENT,otherwise,we should catch error
                  * and return directly.
@@ -557,7 +559,7 @@ static void __merge_refs(struct list_head *head, int mode)
  * smaller or equal that seq to the list
  */
 static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
-                              struct list_head *prefs)
+                              struct list_head *prefs, u64 *total_refs)
 {
         struct btrfs_delayed_extent_op *extent_op = head->extent_op;
         struct rb_node *n = &head->node.rb_node;
@@ -593,6 +595,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
                 default:
                         BUG_ON(1);
                 }
+                *total_refs += (node->ref_mod * sgn);
                 switch (node->type) {
                 case BTRFS_TREE_BLOCK_REF_KEY: {
                         struct btrfs_delayed_tree_ref *ref;
@@ -653,7 +656,8 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
  */
 static int __add_inline_refs(struct btrfs_fs_info *fs_info,
                              struct btrfs_path *path, u64 bytenr,
-                             int *info_level, struct list_head *prefs)
+                             int *info_level, struct list_head *prefs,
+                             u64 *total_refs)
 {
         int ret = 0;
         int slot;
@@ -677,6 +681,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info,
 
         ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
         flags = btrfs_extent_flags(leaf, ei);
+        *total_refs += btrfs_extent_refs(leaf, ei);
         btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
         ptr = (unsigned long)(ei + 1);
@@ -859,6 +864,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
         struct list_head prefs;
         struct __prelim_ref *ref;
         struct extent_inode_elem *eie = NULL;
+        u64 total_refs = 0;
 
         INIT_LIST_HEAD(&prefs);
         INIT_LIST_HEAD(&prefs_delayed);
@@ -873,8 +879,10 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
-        if (!trans)
+        if (!trans) {
                 path->search_commit_root = 1;
+                path->skip_locking = 1;
+        }
 
         /*
          * grab both a lock on the path and a lock on the delayed ref head.
@@ -915,7 +923,7 @@ again:
                         }
                         spin_unlock(&delayed_refs->lock);
                         ret = __add_delayed_refs(head, time_seq,
-                                                 &prefs_delayed);
+                                                 &prefs_delayed, &total_refs);
                         mutex_unlock(&head->mutex);
                         if (ret)
                                 goto out;
@@ -936,7 +944,8 @@ again:
                     (key.type == BTRFS_EXTENT_ITEM_KEY ||
                      key.type == BTRFS_METADATA_ITEM_KEY)) {
                         ret = __add_inline_refs(fs_info, path, bytenr,
-                                                &info_level, &prefs);
+                                                &info_level, &prefs,
+                                                &total_refs);
                         if (ret)
                                 goto out;
                         ret = __add_keyed_refs(fs_info, path, bytenr,
@@ -956,7 +965,7 @@ again:
         __merge_refs(&prefs, 1);
 
         ret = __resolve_indirect_refs(fs_info, path, time_seq, &prefs,
-                                      extent_item_pos);
+                                      extent_item_pos, total_refs);
         if (ret)
                 goto out;
 
@@ -965,7 +974,7 @@ again:
         while (!list_empty(&prefs)) {
                 ref = list_first_entry(&prefs, struct __prelim_ref, list);
                 WARN_ON(ref->count < 0);
-                if (ref->count && ref->root_id && ref->parent == 0) {
+                if (roots && ref->count && ref->root_id && ref->parent == 0) {
                         /* no parent == root of tree */
                         ret = ulist_add(roots, ref->root_id, 0, GFP_NOFS);
                         if (ret < 0)
@@ -1061,22 +1070,14 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
                                 u64 time_seq, struct ulist **leafs,
                                 const u64 *extent_item_pos)
 {
-        struct ulist *tmp;
         int ret;
 
-        tmp = ulist_alloc(GFP_NOFS);
-        if (!tmp)
-                return -ENOMEM;
         *leafs = ulist_alloc(GFP_NOFS);
-        if (!*leafs) {
-                ulist_free(tmp);
+        if (!*leafs)
                 return -ENOMEM;
-        }
 
         ret = find_parent_nodes(trans, fs_info, bytenr,
-                                time_seq, *leafs, tmp, extent_item_pos);
-        ulist_free(tmp);
-
+                                time_seq, *leafs, NULL, extent_item_pos);
         if (ret < 0 && ret != -ENOENT) {
                 free_leaf_list(*leafs);
                 return ret;
@@ -1333,38 +1334,13 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
         if (ret < 0)
                 return ret;
 
-        while (1) {
-                u32 nritems;
-                if (path->slots[0] == 0) {
-                        btrfs_set_path_blocking(path);
-                        ret = btrfs_prev_leaf(fs_info->extent_root, path);
-                        if (ret != 0) {
-                                if (ret > 0) {
-                                        pr_debug("logical %llu is not within "
-                                                 "any extent\n", logical);
-                                        ret = -ENOENT;
-                                }
-                                return ret;
-                        }
-                } else {
-                        path->slots[0]--;
-                }
-                nritems = btrfs_header_nritems(path->nodes[0]);
-                if (nritems == 0) {
-                        pr_debug("logical %llu is not within any extent\n",
-                                 logical);
-                        return -ENOENT;
-                }
-                if (path->slots[0] == nritems)
-                        path->slots[0]--;
-
-                btrfs_item_key_to_cpu(path->nodes[0], found_key,
-                                      path->slots[0]);
-                if (found_key->type == BTRFS_EXTENT_ITEM_KEY ||
-                    found_key->type == BTRFS_METADATA_ITEM_KEY)
-                        break;
+        ret = btrfs_previous_extent_item(fs_info->extent_root, path, 0);
+        if (ret) {
+                if (ret > 0)
+                        ret = -ENOENT;
+                return ret;
         }
-
+        btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]);
         if (found_key->type == BTRFS_METADATA_ITEM_KEY)
                 size = fs_info->extent_root->leafsize;
         else if (found_key->type == BTRFS_EXTENT_ITEM_KEY)
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 8fed2125689e..c9a24444ec9a 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -109,14 +109,17 @@ struct btrfs_inode {
         u64 last_trans;
 
         /*
-         * log transid when this inode was last modified
+         * transid that last logged this inode
          */
-        u64 last_sub_trans;
+        u64 logged_trans;
 
         /*
-         * transid that last logged this inode
+         * log transid when this inode was last modified
          */
-        u64 logged_trans;
+        int last_sub_trans;
+
+        /* a local copy of root's last_log_commit */
+        int last_log_commit;
 
         /* total number of bytes pending delalloc, used by stat to calc the
          * real block usage of the file
@@ -155,9 +158,6 @@ struct btrfs_inode {
         /* flags field from the on disk inode */
         u32 flags;
 
-        /* a local copy of root's last_log_commit */
-        unsigned long last_log_commit;
-
         /*
          * Counters to keep track of the number of extent item's we may use due
          * to delalloc and such.  outstanding_extents is the number of extent
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b01fb6c527e3..d43c544d3b68 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
                 rcu_read_lock();
                 page = radix_tree_lookup(&mapping->page_tree, pg_index);
                 rcu_read_unlock();
-                if (page) {
+                if (page && !radix_tree_exceptional_entry(page)) {
                         misses++;
                         if (misses > 4)
                                 break;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index cbd3a7d6fa68..88d1b1eedc9c 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -5376,6 +5376,8 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
         int advance_right;
         u64 left_blockptr;
         u64 right_blockptr;
+        u64 left_gen;
+        u64 right_gen;
         u64 left_start_ctransid;
         u64 right_start_ctransid;
         u64 ctransid;
@@ -5640,7 +5642,14 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
                                 right_blockptr = btrfs_node_blockptr(
                                                 right_path->nodes[right_level],
                                                 right_path->slots[right_level]);
-                                if (left_blockptr == right_blockptr) {
+                                left_gen = btrfs_node_ptr_generation(
+                                                left_path->nodes[left_level],
+                                                left_path->slots[left_level]);
+                                right_gen = btrfs_node_ptr_generation(
+                                                right_path->nodes[right_level],
+                                                right_path->slots[right_level]);
+                                if (left_blockptr == right_blockptr &&
+                                    left_gen == right_gen) {
                                         /*
                                          * As we're on a shared block, don't
                                          * allow to go deeper.
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2c1a42ca519f..bc96c03dd259 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -351,6 +351,7 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 #define BTRFS_FS_STATE_ERROR            0
 #define BTRFS_FS_STATE_REMOUNTING       1
 #define BTRFS_FS_STATE_TRANS_ABORTED    2
+#define BTRFS_FS_STATE_DEV_REPLACING    3
 
 /* Super block flags */
 /* Errors detected */
@@ -1489,6 +1490,7 @@ struct btrfs_fs_info {
          */
         struct list_head ordered_roots;
 
+        struct mutex delalloc_root_mutex;
         spinlock_t delalloc_root_lock;
         /* all fs/file tree roots that have delalloc inodes. */
         struct list_head delalloc_roots;
@@ -1503,28 +1505,27 @@ struct btrfs_fs_info {
          * A third pool does submit_bio to avoid deadlocking with the other
          * two
          */
-        struct btrfs_workers generic_worker;
-        struct btrfs_workers workers;
-        struct btrfs_workers delalloc_workers;
-        struct btrfs_workers flush_workers;
-        struct btrfs_workers endio_workers;
-        struct btrfs_workers endio_meta_workers;
-        struct btrfs_workers endio_raid56_workers;
-        struct btrfs_workers rmw_workers;
-        struct btrfs_workers endio_meta_write_workers;
-        struct btrfs_workers endio_write_workers;
-        struct btrfs_workers endio_freespace_worker;
-        struct btrfs_workers submit_workers;
-        struct btrfs_workers caching_workers;
-        struct btrfs_workers readahead_workers;
+        struct btrfs_workqueue *workers;
+        struct btrfs_workqueue *delalloc_workers;
+        struct btrfs_workqueue *flush_workers;
+        struct btrfs_workqueue *endio_workers;
+        struct btrfs_workqueue *endio_meta_workers;
+        struct btrfs_workqueue *endio_raid56_workers;
+        struct btrfs_workqueue *rmw_workers;
+        struct btrfs_workqueue *endio_meta_write_workers;
+        struct btrfs_workqueue *endio_write_workers;
+        struct btrfs_workqueue *endio_freespace_worker;
+        struct btrfs_workqueue *submit_workers;
+        struct btrfs_workqueue *caching_workers;
+        struct btrfs_workqueue *readahead_workers;
 
         /*
          * fixup workers take dirty pages that didn't properly go through
          * the cow mechanism and make them safe to write.  It happens
          * for the sys_munmap function call path
          */
-        struct btrfs_workers fixup_workers;
-        struct btrfs_workers delayed_workers;
+        struct btrfs_workqueue *fixup_workers;
+        struct btrfs_workqueue *delayed_workers;
         struct task_struct *transaction_kthread;
         struct task_struct *cleaner_kthread;
         int thread_pool_size;
@@ -1604,9 +1605,9 @@ struct btrfs_fs_info {
         atomic_t scrub_cancel_req;
         wait_queue_head_t scrub_pause_wait;
         int scrub_workers_refcnt;
-        struct btrfs_workers scrub_workers;
-        struct btrfs_workers scrub_wr_completion_workers;
-        struct btrfs_workers scrub_nocow_workers;
+        struct btrfs_workqueue *scrub_workers;
+        struct btrfs_workqueue *scrub_wr_completion_workers;
+        struct btrfs_workqueue *scrub_nocow_workers;
 
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
         u32 check_integrity_print_mask;
@@ -1647,7 +1648,7 @@ struct btrfs_fs_info {
         /* qgroup rescan items */
         struct mutex qgroup_rescan_lock; /* protects the progress item */
         struct btrfs_key qgroup_rescan_progress;
-        struct btrfs_workers qgroup_rescan_workers;
+        struct btrfs_workqueue *qgroup_rescan_workers;
         struct completion qgroup_rescan_completion;
         struct btrfs_work qgroup_rescan_work;
 
@@ -1674,10 +1675,18 @@ struct btrfs_fs_info {
 
         atomic_t mutually_exclusive_operation_running;
 
+        struct percpu_counter bio_counter;
+        wait_queue_head_t replace_wait;
+
         struct semaphore uuid_tree_rescan_sem;
         unsigned int update_uuid_tree_gen:1;
 };
 
+struct btrfs_subvolume_writers {
+        struct percpu_counter   counter;
+        wait_queue_head_t       wait;
+};
+
 /*
  * in ram representation of the tree.  extent_root is used for all allocations
  * and for the extent tree extent_root root.
@@ -1714,11 +1723,15 @@ struct btrfs_root {
         struct mutex log_mutex;
         wait_queue_head_t log_writer_wait;
         wait_queue_head_t log_commit_wait[2];
+        struct list_head log_ctxs[2];
         atomic_t log_writers;
         atomic_t log_commit[2];
         atomic_t log_batch;
-        unsigned long log_transid;
-        unsigned long last_log_commit;
+        int log_transid;
+        /* No matter the commit succeeds or not*/
+        int log_transid_committed;
+        /* Just be updated when the commit succeeds. */
+        int last_log_commit;
         pid_t log_start_pid;
         bool log_multiple_pids;
 
@@ -1793,6 +1806,7 @@ struct btrfs_root {
         spinlock_t root_item_lock;
         atomic_t refs;
 
+        struct mutex delalloc_mutex;
         spinlock_t delalloc_lock;
         /*
          * all of the inodes that have delalloc bytes.  It is possible for
@@ -1802,6 +1816,8 @@ struct btrfs_root {
         struct list_head delalloc_inodes;
         struct list_head delalloc_root;
         u64 nr_delalloc_inodes;
+
+        struct mutex ordered_extent_mutex;
         /*
          * this is used by the balancing code to wait for all the pending
          * ordered extents
@@ -1822,6 +1838,8 @@ struct btrfs_root {
          * manipulation with the read-only status via SUBVOL_SETFLAGS
          */
         int send_in_progress;
+        struct btrfs_subvolume_writers *subv_writers;
+        atomic_t will_be_snapshoted;
 };
 
 struct btrfs_ioctl_defrag_range_args {
@@ -3346,6 +3364,9 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
 int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
                                          struct btrfs_fs_info *fs_info);
 int __get_raid_index(u64 flags);
+
+int btrfs_start_nocow_write(struct btrfs_root *root);
+void btrfs_end_nocow_write(struct btrfs_root *root);
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
                      int level, int *slot);
@@ -3723,7 +3744,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
                                u32 min_type);
 
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
+                               int nr);
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
                               struct extent_state **cached_state);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
@@ -4005,6 +4027,11 @@ int btrfs_scrub_cancel_dev(struct btrfs_fs_info *info,
 int btrfs_scrub_progress(struct btrfs_root *root, u64 devid,
                          struct btrfs_scrub_progress *progress);
 
+/* dev-replace.c */
+void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
+void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info);
+void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info);
+
 /* reada.c */
 struct reada_control {
         struct btrfs_root       *root;          /* tree to prefetch */
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 451b00c86f6c..33e561a84013 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1392,11 +1392,11 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
                 return -ENOMEM;
 
         async_work->delayed_root = delayed_root;
-        async_work->work.func = btrfs_async_run_delayed_root;
-        async_work->work.flags = 0;
+        btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root,
+                        NULL, NULL);
         async_work->nr = nr;
 
-        btrfs_queue_worker(&root->fs_info->delayed_workers, &async_work->work);
+        btrfs_queue_work(root->fs_info->delayed_workers, &async_work->work);
         return 0;
 }
 
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index f3bff89eecf0..31299646024d 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -199,44 +199,31 @@ static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
  */
 static struct btrfs_delayed_ref_head *
 find_ref_head(struct rb_root *root, u64 bytenr,
-              struct btrfs_delayed_ref_head **last, int return_bigger)
+              int return_bigger)
 {
         struct rb_node *n;
         struct btrfs_delayed_ref_head *entry;
-        int cmp = 0;
 
-again:
         n = root->rb_node;
         entry = NULL;
         while (n) {
                 entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node);
-                if (last)
-                        *last = entry;
 
                 if (bytenr < entry->node.bytenr)
-                        cmp = -1;
-                else if (bytenr > entry->node.bytenr)
-                        cmp = 1;
-                else
-                        cmp = 0;
-
-                if (cmp < 0)
                         n = n->rb_left;
-                else if (cmp > 0)
+                else if (bytenr > entry->node.bytenr)
                         n = n->rb_right;
                 else
                         return entry;
         }
         if (entry && return_bigger) {
-                if (cmp > 0) {
+                if (bytenr > entry->node.bytenr) {
                         n = rb_next(&entry->href_node);
                         if (!n)
                                 n = rb_first(root);
                         entry = rb_entry(n, struct btrfs_delayed_ref_head,
                                          href_node);
-                        bytenr = entry->node.bytenr;
-                        return_bigger = 0;
-                        goto again;
+                        return entry;
                 }
                 return entry;
         }
@@ -415,12 +402,12 @@ btrfs_select_ref_head(struct btrfs_trans_handle *trans)
 
 again:
         start = delayed_refs->run_delayed_start;
-        head = find_ref_head(&delayed_refs->href_root, start, NULL, 1);
+        head = find_ref_head(&delayed_refs->href_root, start, 1);
         if (!head && !loop) {
                 delayed_refs->run_delayed_start = 0;
                 start = 0;
                 loop = true;
-                head = find_ref_head(&delayed_refs->href_root, start, NULL, 1);
+                head = find_ref_head(&delayed_refs->href_root, start, 1);
                 if (!head)
                         return NULL;
         } else if (!head && loop) {
@@ -508,6 +495,7 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
         ref = btrfs_delayed_node_to_head(update);
         BUG_ON(existing_ref->is_data != ref->is_data);
 
+        spin_lock(&existing_ref->lock);
         if (ref->must_insert_reserved) {
                 /* if the extent was freed and then
                  * reallocated before the delayed ref
@@ -549,7 +537,6 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
          * only need the lock for this case cause we could be processing it
          * currently, for refs we just added we know we're a-ok.
          */
-        spin_lock(&existing_ref->lock);
         existing->ref_mod += update->ref_mod;
         spin_unlock(&existing_ref->lock);
 }
@@ -898,7 +885,7 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
         struct btrfs_delayed_ref_root *delayed_refs;
 
         delayed_refs = &trans->transaction->delayed_refs;
-        return find_ref_head(&delayed_refs->href_root, bytenr, NULL, 0);
+        return find_ref_head(&delayed_refs->href_root, bytenr, 0);
 }
 
 void btrfs_delayed_ref_exit(void)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 564c92638b20..9f2290509aca 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -431,6 +431,35 @@ leave_no_lock:
         return ret;
 }
 
+/*
+ * blocked until all flighting bios are finished.
+ */
+static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info)
+{
+        s64 writers;
+        DEFINE_WAIT(wait);
+
+        set_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state);
+        do {
+                prepare_to_wait(&fs_info->replace_wait, &wait,
+                                TASK_UNINTERRUPTIBLE);
+                writers = percpu_counter_sum(&fs_info->bio_counter);
+                if (writers)
+                        schedule();
+                finish_wait(&fs_info->replace_wait, &wait);
+        } while (writers);
+}
+
+/*
+ * we have removed target device, it is safe to allow new bios request.
+ */
+static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info)
+{
+        clear_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state);
+        if (waitqueue_active(&fs_info->replace_wait))
+                wake_up(&fs_info->replace_wait);
+}
+
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
                                        int scrub_ret)
 {
@@ -458,17 +487,11 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
         src_device = dev_replace->srcdev;
         btrfs_dev_replace_unlock(dev_replace);
 
-        /* replace old device with new one in mapping tree */
-        if (!scrub_ret)
-                btrfs_dev_replace_update_device_in_mapping_tree(fs_info,
-                                                                src_device,
-                                                                tgt_device);
-
         /*
          * flush all outstanding I/O and inode extent mappings before the
          * copy operation is declared as being finished
          */
-        ret = btrfs_start_delalloc_roots(root->fs_info, 0);
+        ret = btrfs_start_delalloc_roots(root->fs_info, 0, -1);
         if (ret) {
                 mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
                 return ret;
@@ -484,6 +507,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
         WARN_ON(ret);
 
         /* keep away write_all_supers() during the finishing procedure */
+        mutex_lock(&root->fs_info->chunk_mutex);
         mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
         btrfs_dev_replace_lock(dev_replace);
         dev_replace->replace_state =
@@ -494,7 +518,12 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
         dev_replace->time_stopped = get_seconds();
         dev_replace->item_needs_writeback = 1;
 
-        if (scrub_ret) {
+        /* replace old device with new one in mapping tree */
+        if (!scrub_ret) {
+                btrfs_dev_replace_update_device_in_mapping_tree(fs_info,
+                                                                src_device,
+                                                                tgt_device);
+        } else {
                 printk_in_rcu(KERN_ERR
                               "BTRFS: btrfs_scrub_dev(%s, %llu, %s) failed %d\n",
                               src_device->missing ? "<missing disk>" :
@@ -503,6 +532,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
                               rcu_str_deref(tgt_device->name), scrub_ret);
                 btrfs_dev_replace_unlock(dev_replace);
                 mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+                mutex_unlock(&root->fs_info->chunk_mutex);
                 if (tgt_device)
                         btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
                 mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
@@ -532,8 +562,12 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
                 fs_info->fs_devices->latest_bdev = tgt_device->bdev;
         list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 
+        btrfs_rm_dev_replace_blocked(fs_info);
+
         btrfs_rm_dev_replace_srcdev(fs_info, src_device);
 
+        btrfs_rm_dev_replace_unblocked(fs_info);
+
         /*
          * this is again a consistent state where no dev_replace procedure
          * is running, the target device is part of the filesystem, the
@@ -543,6 +577,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
          */
         btrfs_dev_replace_unlock(dev_replace);
         mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+        mutex_unlock(&root->fs_info->chunk_mutex);
 
         /* write back the superblocks */
         trans = btrfs_start_transaction(root, 0);
@@ -862,3 +897,31 @@ void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace)
                 mutex_unlock(&dev_replace->lock_management_lock);
         }
 }
+
+void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
+{
+        percpu_counter_inc(&fs_info->bio_counter);
+}
+
+void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info)
+{
+        percpu_counter_dec(&fs_info->bio_counter);
+
+        if (waitqueue_active(&fs_info->replace_wait))
+                wake_up(&fs_info->replace_wait);
+}
+
+void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info)
+{
+        DEFINE_WAIT(wait);
+again:
+        percpu_counter_inc(&fs_info->bio_counter);
+        if (test_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state)) {
+                btrfs_bio_counter_dec(fs_info);
+                wait_event(fs_info->replace_wait,
+                           !test_bit(BTRFS_FS_STATE_DEV_REPLACING,
+                                     &fs_info->fs_state));
+                goto again;
+        }
+
+}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 81ea55314b1f..bd0f752b797b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -678,32 +678,31 @@ static void end_workqueue_bio(struct bio *bio, int err)
 
         fs_info = end_io_wq->info;
         end_io_wq->error = err;
-        end_io_wq->work.func = end_workqueue_fn;
-        end_io_wq->work.flags = 0;
+        btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
 
         if (bio->bi_rw & REQ_WRITE) {
                 if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
-                        btrfs_queue_worker(&fs_info->endio_meta_write_workers,
-                                           &end_io_wq->work);
+                        btrfs_queue_work(fs_info->endio_meta_write_workers,
+                                         &end_io_wq->work);
                 else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
-                        btrfs_queue_worker(&fs_info->endio_freespace_worker,
-                                           &end_io_wq->work);
+                        btrfs_queue_work(fs_info->endio_freespace_worker,
+                                         &end_io_wq->work);
                 else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-                        btrfs_queue_worker(&fs_info->endio_raid56_workers,
-                                           &end_io_wq->work);
+                        btrfs_queue_work(fs_info->endio_raid56_workers,
+                                         &end_io_wq->work);
                 else
-                        btrfs_queue_worker(&fs_info->endio_write_workers,
-                                           &end_io_wq->work);
+                        btrfs_queue_work(fs_info->endio_write_workers,
+                                         &end_io_wq->work);
         } else {
                 if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-                        btrfs_queue_worker(&fs_info->endio_raid56_workers,
-                                           &end_io_wq->work);
+                        btrfs_queue_work(fs_info->endio_raid56_workers,
+                                         &end_io_wq->work);
                 else if (end_io_wq->metadata)
-                        btrfs_queue_worker(&fs_info->endio_meta_workers,
-                                           &end_io_wq->work);
+                        btrfs_queue_work(fs_info->endio_meta_workers,
+                                         &end_io_wq->work);
                 else
-                        btrfs_queue_worker(&fs_info->endio_workers,
-                                           &end_io_wq->work);
+                        btrfs_queue_work(fs_info->endio_workers,
+                                         &end_io_wq->work);
         }
 }
 
@@ -738,7 +737,7 @@ int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
 {
         unsigned long limit = min_t(unsigned long,
-                                    info->workers.max_workers,
+                                    info->thread_pool_size,
                                     info->fs_devices->open_devices);
         return 256 * limit;
 }
@@ -811,11 +810,9 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
         async->submit_bio_start = submit_bio_start;
         async->submit_bio_done = submit_bio_done;
 
-        async->work.func = run_one_async_start;
-        async->work.ordered_func = run_one_async_done;
-        async->work.ordered_free = run_one_async_free;
+        btrfs_init_work(&async->work, run_one_async_start,
+                        run_one_async_done, run_one_async_free);
 
-        async->work.flags = 0;
         async->bio_flags = bio_flags;
         async->bio_offset = bio_offset;
 
@@ -824,9 +821,9 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
         atomic_inc(&fs_info->nr_async_submits);
 
         if (rw & REQ_SYNC)
-                btrfs_set_work_high_prio(&async->work);
+                btrfs_set_work_high_priority(&async->work);
 
-        btrfs_queue_worker(&fs_info->workers, &async->work);
+        btrfs_queue_work(fs_info->workers, &async->work);
 
         while (atomic_read(&fs_info->async_submit_draining) &&
               atomic_read(&fs_info->nr_async_submits)) {
@@ -1149,6 +1146,32 @@ void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
         }
 }
 
+static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
+{
+        struct btrfs_subvolume_writers *writers;
+        int ret;
+
+        writers = kmalloc(sizeof(*writers), GFP_NOFS);
+        if (!writers)
+                return ERR_PTR(-ENOMEM);
+
+        ret = percpu_counter_init(&writers->counter, 0);
+        if (ret < 0) {
+                kfree(writers);
+                return ERR_PTR(ret);
+        }
+
+        init_waitqueue_head(&writers->wait);
+        return writers;
+}
+
+static void
+btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers)
+{
+        percpu_counter_destroy(&writers->counter);
+        kfree(writers);
+}
+
 static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
                          u32 stripesize, struct btrfs_root *root,
                          struct btrfs_fs_info *fs_info,
@@ -1194,16 +1217,22 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
         spin_lock_init(&root->log_extents_lock[1]);
         mutex_init(&root->objectid_mutex);
         mutex_init(&root->log_mutex);
+        mutex_init(&root->ordered_extent_mutex);
+        mutex_init(&root->delalloc_mutex);
         init_waitqueue_head(&root->log_writer_wait);
         init_waitqueue_head(&root->log_commit_wait[0]);
         init_waitqueue_head(&root->log_commit_wait[1]);
+        INIT_LIST_HEAD(&root->log_ctxs[0]);
+        INIT_LIST_HEAD(&root->log_ctxs[1]);
         atomic_set(&root->log_commit[0], 0);
         atomic_set(&root->log_commit[1], 0);
         atomic_set(&root->log_writers, 0);
         atomic_set(&root->log_batch, 0);
         atomic_set(&root->orphan_inodes, 0);
         atomic_set(&root->refs, 1);
+        atomic_set(&root->will_be_snapshoted, 0);
         root->log_transid = 0;
+        root->log_transid_committed = -1;
         root->last_log_commit = 0;
         if (fs_info)
                 extent_io_tree_init(&root->dirty_log_pages,
@@ -1417,6 +1446,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
         WARN_ON(root->log_root);
         root->log_root = log_root;
         root->log_transid = 0;
+        root->log_transid_committed = -1;
         root->last_log_commit = 0;
         return 0;
 }
@@ -1498,6 +1528,7 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
 int btrfs_init_fs_root(struct btrfs_root *root)
 {
         int ret;
+        struct btrfs_subvolume_writers *writers;
 
         root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
         root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
@@ -1507,6 +1538,13 @@ int btrfs_init_fs_root(struct btrfs_root *root)
                 goto fail;
         }
 
+        writers = btrfs_alloc_subvolume_writers();
+        if (IS_ERR(writers)) {
+                ret = PTR_ERR(writers);
+                goto fail;
+        }
+        root->subv_writers = writers;
+
         btrfs_init_free_ino_ctl(root);
         mutex_init(&root->fs_commit_mutex);
         spin_lock_init(&root->cache_lock);
@@ -1514,8 +1552,11 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 
         ret = get_anon_bdev(&root->anon_dev);
         if (ret)
-                goto fail;
+                goto free_writers;
         return 0;
+
+free_writers:
+        btrfs_free_subvolume_writers(root->subv_writers);
 fail:
         kfree(root->free_ino_ctl);
         kfree(root->free_ino_pinned);
@@ -1990,23 +2031,22 @@ static noinline int next_root_backup(struct btrfs_fs_info *info,
 /* helper to cleanup workers */
 static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 {
-        btrfs_stop_workers(&fs_info->generic_worker);
-        btrfs_stop_workers(&fs_info->fixup_workers);
-        btrfs_stop_workers(&fs_info->delalloc_workers);
-        btrfs_stop_workers(&fs_info->workers);
-        btrfs_stop_workers(&fs_info->endio_workers);
-        btrfs_stop_workers(&fs_info->endio_meta_workers);
-        btrfs_stop_workers(&fs_info->endio_raid56_workers);
-        btrfs_stop_workers(&fs_info->rmw_workers);
-        btrfs_stop_workers(&fs_info->endio_meta_write_workers);
-        btrfs_stop_workers(&fs_info->endio_write_workers);
-        btrfs_stop_workers(&fs_info->endio_freespace_worker);
-        btrfs_stop_workers(&fs_info->submit_workers);
-        btrfs_stop_workers(&fs_info->delayed_workers);
-        btrfs_stop_workers(&fs_info->caching_workers);
-        btrfs_stop_workers(&fs_info->readahead_workers);
-        btrfs_stop_workers(&fs_info->flush_workers);
-        btrfs_stop_workers(&fs_info->qgroup_rescan_workers);
+        btrfs_destroy_workqueue(fs_info->fixup_workers);
+        btrfs_destroy_workqueue(fs_info->delalloc_workers);
+        btrfs_destroy_workqueue(fs_info->workers);
+        btrfs_destroy_workqueue(fs_info->endio_workers);
+        btrfs_destroy_workqueue(fs_info->endio_meta_workers);
+        btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
+        btrfs_destroy_workqueue(fs_info->rmw_workers);
+        btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
+        btrfs_destroy_workqueue(fs_info->endio_write_workers);
+        btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
+        btrfs_destroy_workqueue(fs_info->submit_workers);
+        btrfs_destroy_workqueue(fs_info->delayed_workers);
+        btrfs_destroy_workqueue(fs_info->caching_workers);
+        btrfs_destroy_workqueue(fs_info->readahead_workers);
+        btrfs_destroy_workqueue(fs_info->flush_workers);
+        btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
 }
 
 static void free_root_extent_buffers(struct btrfs_root *root)
@@ -2097,6 +2137,8 @@ int open_ctree(struct super_block *sb,
         int err = -EINVAL;
         int num_backups_tried = 0;
         int backup_index = 0;
+        int max_active;
+        int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
         bool create_uuid_tree;
         bool check_uuid_tree;
 
@@ -2133,10 +2175,16 @@ int open_ctree(struct super_block *sb,
                 goto fail_dirty_metadata_bytes;
         }
 
+        ret = percpu_counter_init(&fs_info->bio_counter, 0);
+        if (ret) {
+                err = ret;
+                goto fail_delalloc_bytes;
+        }
+
         fs_info->btree_inode = new_inode(sb);
         if (!fs_info->btree_inode) {
                 err = -ENOMEM;
-                goto fail_delalloc_bytes;
+                goto fail_bio_counter;
         }
 
         mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
@@ -2159,6 +2207,7 @@ int open_ctree(struct super_block *sb,
         spin_lock_init(&fs_info->buffer_lock);
         rwlock_init(&fs_info->tree_mod_log_lock);
         mutex_init(&fs_info->reloc_mutex);
+        mutex_init(&fs_info->delalloc_root_mutex);
         seqlock_init(&fs_info->profiles_lock);
 
         init_completion(&fs_info->kobj_unregister);
@@ -2211,6 +2260,7 @@ int open_ctree(struct super_block *sb,
         atomic_set(&fs_info->scrub_pause_req, 0);
         atomic_set(&fs_info->scrubs_paused, 0);
         atomic_set(&fs_info->scrub_cancel_req, 0);
+        init_waitqueue_head(&fs_info->replace_wait);
         init_waitqueue_head(&fs_info->scrub_pause_wait);
         fs_info->scrub_workers_refcnt = 0;
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
@@ -2458,104 +2508,68 @@ int open_ctree(struct super_block *sb,
                 goto fail_alloc;
         }
 
-        btrfs_init_workers(&fs_info->generic_worker,
-                           "genwork", 1, NULL);
-
-        btrfs_init_workers(&fs_info->workers, "worker",
-                           fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
+        max_active = fs_info->thread_pool_size;
 
-        btrfs_init_workers(&fs_info->delalloc_workers, "delalloc",
-                           fs_info->thread_pool_size, NULL);
+        fs_info->workers =
+                btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI,
+                                      max_active, 16);
 
-        btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc",
-                           fs_info->thread_pool_size, NULL);
+        fs_info->delalloc_workers =
+                btrfs_alloc_workqueue("delalloc", flags, max_active, 2);
 
-        btrfs_init_workers(&fs_info->submit_workers, "submit",
-                           min_t(u64, fs_devices->num_devices,
-                           fs_info->thread_pool_size), NULL);
+        fs_info->flush_workers =
+                btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0);
 
-        btrfs_init_workers(&fs_info->caching_workers, "cache",
-                           fs_info->thread_pool_size, NULL);
+        fs_info->caching_workers =
+                btrfs_alloc_workqueue("cache", flags, max_active, 0);
 
-        /* a higher idle thresh on the submit workers makes it much more
+        /*
+         * a higher idle thresh on the submit workers makes it much more
          * likely that bios will be send down in a sane order to the
          * devices
          */
-        fs_info->submit_workers.idle_thresh = 64;
-
-        fs_info->workers.idle_thresh = 16;
-        fs_info->workers.ordered = 1;
-
-        fs_info->delalloc_workers.idle_thresh = 2;
-        fs_info->delalloc_workers.ordered = 1;
-
-        btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->endio_workers, "endio",
-                           fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta",
-                           fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->endio_meta_write_workers,
-                           "endio-meta-write", fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->endio_raid56_workers,
-                           "endio-raid56", fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->rmw_workers,
-                           "rmw", fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->endio_write_workers, "endio-write",
-                           fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write",
-                           1, &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta",
-                           fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->readahead_workers, "readahead",
-                           fs_info->thread_pool_size,
-                           &fs_info->generic_worker);
-        btrfs_init_workers(&fs_info->qgroup_rescan_workers, "qgroup-rescan", 1,
-                           &fs_info->generic_worker);
+        fs_info->submit_workers =
+                btrfs_alloc_workqueue("submit", flags,
+                                      min_t(u64, fs_devices->num_devices,
+                                            max_active), 64);
+
+        fs_info->fixup_workers =
+                btrfs_alloc_workqueue("fixup", flags, 1, 0);
 
         /*
          * endios are largely parallel and should have a very
          * low idle thresh
          */
-        fs_info->endio_workers.idle_thresh = 4;
-        fs_info->endio_meta_workers.idle_thresh = 4;
-        fs_info->endio_raid56_workers.idle_thresh = 4;
-        fs_info->rmw_workers.idle_thresh = 2;
-
-        fs_info->endio_write_workers.idle_thresh = 2;
-        fs_info->endio_meta_write_workers.idle_thresh = 2;
-        fs_info->readahead_workers.idle_thresh = 2;
-
-        /*
-         * btrfs_start_workers can really only fail because of ENOMEM so just
-         * return -ENOMEM if any of these fail.
-         */
-        ret = btrfs_start_workers(&fs_info->workers);
-        ret |= btrfs_start_workers(&fs_info->generic_worker);
-        ret |= btrfs_start_workers(&fs_info->submit_workers);
-        ret |= btrfs_start_workers(&fs_info->delalloc_workers);
-        ret |= btrfs_start_workers(&fs_info->fixup_workers);
-        ret |= btrfs_start_workers(&fs_info->endio_workers);
-        ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
-        ret |= btrfs_start_workers(&fs_info->rmw_workers);
-        ret |= btrfs_start_workers(&fs_info->endio_raid56_workers);
-        ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
-        ret |= btrfs_start_workers(&fs_info->endio_write_workers);
-        ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
-        ret |= btrfs_start_workers(&fs_info->delayed_workers);
-        ret |= btrfs_start_workers(&fs_info->caching_workers);
-        ret |= btrfs_start_workers(&fs_info->readahead_workers);
-        ret |= btrfs_start_workers(&fs_info->flush_workers);
-        ret |= btrfs_start_workers(&fs_info->qgroup_rescan_workers);
-        if (ret) {
+        fs_info->endio_workers =
+                btrfs_alloc_workqueue("endio", flags, max_active, 4);
+        fs_info->endio_meta_workers =
+                btrfs_alloc_workqueue("endio-meta", flags, max_active, 4);
+        fs_info->endio_meta_write_workers =
+                btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
+        fs_info->endio_raid56_workers =
+                btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
+        fs_info->rmw_workers =
+                btrfs_alloc_workqueue("rmw", flags, max_active, 2);
+        fs_info->endio_write_workers =
+                btrfs_alloc_workqueue("endio-write", flags, max_active, 2);
+        fs_info->endio_freespace_worker =
+                btrfs_alloc_workqueue("freespace-write", flags, max_active, 0);
+        fs_info->delayed_workers =
+                btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0);
+        fs_info->readahead_workers =
+                btrfs_alloc_workqueue("readahead", flags, max_active, 2);
+        fs_info->qgroup_rescan_workers =
+                btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0);
+
+        if (!(fs_info->workers && fs_info->delalloc_workers &&
+              fs_info->submit_workers && fs_info->flush_workers &&
+              fs_info->endio_workers && fs_info->endio_meta_workers &&
+              fs_info->endio_meta_write_workers &&
+              fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
+              fs_info->endio_freespace_worker && fs_info->rmw_workers &&
+              fs_info->caching_workers && fs_info->readahead_workers &&
+              fs_info->fixup_workers && fs_info->delayed_workers &&
+              fs_info->qgroup_rescan_workers)) {
                 err = -ENOMEM;
                 goto fail_sb_buffer;
         }
@@ -2963,6 +2977,8 @@ fail_iput:
         btrfs_mapping_tree_free(&fs_info->mapping_tree);
 
         iput(fs_info->btree_inode);
+fail_bio_counter:
+        percpu_counter_destroy(&fs_info->bio_counter);
 fail_delalloc_bytes:
         percpu_counter_destroy(&fs_info->delalloc_bytes);
 fail_dirty_metadata_bytes:
@@ -3244,6 +3260,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
         /* send down all the barriers */
         head = &info->fs_devices->devices;
         list_for_each_entry_rcu(dev, head, dev_list) {
+                if (dev->missing)
+                        continue;
                 if (!dev->bdev) {
                         errors_send++;
                         continue;
@@ -3258,6 +3276,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 
         /* wait for all the barriers */
         list_for_each_entry_rcu(dev, head, dev_list) {
+                if (dev->missing)
+                        continue;
                 if (!dev->bdev) {
                         errors_wait++;
                         continue;
@@ -3477,6 +3497,8 @@ static void free_fs_root(struct btrfs_root *root)
         root->orphan_block_rsv = NULL;
         if (root->anon_dev)
                 free_anon_bdev(root->anon_dev);
+        if (root->subv_writers)
+                btrfs_free_subvolume_writers(root->subv_writers);
         free_extent_buffer(root->node);
         free_extent_buffer(root->commit_root);
         kfree(root->free_ino_ctl);
@@ -3610,6 +3632,7 @@ int close_ctree(struct btrfs_root *root)
 
         percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
         percpu_counter_destroy(&fs_info->delalloc_bytes);
+        percpu_counter_destroy(&fs_info->bio_counter);
         bdi_destroy(&fs_info->bdi);
         cleanup_srcu_struct(&fs_info->subvol_srcu);
 
@@ -3791,9 +3814,11 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
                 list_move_tail(&root->ordered_root,
                                &fs_info->ordered_roots);
 
+                spin_unlock(&fs_info->ordered_root_lock);
                 btrfs_destroy_ordered_extents(root);
 
-                cond_resched_lock(&fs_info->ordered_root_lock);
+                cond_resched();
+                spin_lock(&fs_info->ordered_root_lock);
         }
         spin_unlock(&fs_info->ordered_root_lock);
 }
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 32312e09f0f5..c6b6a6e3e735 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -549,7 +549,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
         caching_ctl->block_group = cache;
         caching_ctl->progress = cache->key.objectid;
         atomic_set(&caching_ctl->count, 1);
-        caching_ctl->work.func = caching_thread;
+        btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
 
         spin_lock(&cache->lock);
         /*
@@ -640,7 +640,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 
         btrfs_get_block_group(cache);
 
-        btrfs_queue_worker(&fs_info->caching_workers, &caching_ctl->work);
+        btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);
 
         return ret;
 }
@@ -3971,7 +3971,7 @@ static int can_overcommit(struct btrfs_root *root,
 }
 
 static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root,
-                                         unsigned long nr_pages)
+                                         unsigned long nr_pages, int nr_items)
 {
         struct super_block *sb = root->fs_info->sb;
 
@@ -3986,9 +3986,9 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root,
                  * the filesystem is readonly(all dirty pages are written to
                  * the disk).
                  */
-                btrfs_start_delalloc_roots(root->fs_info, 0);
+                btrfs_start_delalloc_roots(root->fs_info, 0, nr_items);
                 if (!current->journal_info)
-                        btrfs_wait_ordered_roots(root->fs_info, -1);
+                        btrfs_wait_ordered_roots(root->fs_info, nr_items);
         }
 }
 
@@ -4045,7 +4045,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
         while (delalloc_bytes && loops < 3) {
                 max_reclaim = min(delalloc_bytes, to_reclaim);
                 nr_pages = max_reclaim >> PAGE_CACHE_SHIFT;
-                btrfs_writeback_inodes_sb_nr(root, nr_pages);
+                btrfs_writeback_inodes_sb_nr(root, nr_pages, items);
                 /*
                  * We need to wait for the async pages to actually start before
                  * we do anything.
@@ -4112,13 +4112,9 @@ static int may_commit_transaction(struct btrfs_root *root,
                 goto commit;
 
         /* See if there is enough pinned space to make this reservation */
-        spin_lock(&space_info->lock);
         if (percpu_counter_compare(&space_info->total_bytes_pinned,
-                                   bytes) >= 0) {
-                spin_unlock(&space_info->lock);
+                                   bytes) >= 0)
                 goto commit;
-        }
-        spin_unlock(&space_info->lock);
 
         /*
          * See if there is some space in the delayed insertion reservation for
@@ -4127,16 +4123,13 @@ static int may_commit_transaction(struct btrfs_root *root,
         if (space_info != delayed_rsv->space_info)
                 return -ENOSPC;
 
-        spin_lock(&space_info->lock);
         spin_lock(&delayed_rsv->lock);
         if (percpu_counter_compare(&space_info->total_bytes_pinned,
                                    bytes - delayed_rsv->size) >= 0) {
                 spin_unlock(&delayed_rsv->lock);
-                spin_unlock(&space_info->lock);
                 return -ENOSPC;
         }
         spin_unlock(&delayed_rsv->lock);
-        spin_unlock(&space_info->lock);
 
 commit:
         trans = btrfs_join_transaction(root);
@@ -4181,7 +4174,7 @@ static int flush_space(struct btrfs_root *root,
                 break;
         case FLUSH_DELALLOC:
         case FLUSH_DELALLOC_WAIT:
-                shrink_delalloc(root, num_bytes, orig_bytes,
+                shrink_delalloc(root, num_bytes * 2, orig_bytes,
                                 state == FLUSH_DELALLOC_WAIT);
                 break;
         case ALLOC_CHUNK:
@@ -8938,3 +8931,38 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
         range->len = trimmed;
         return ret;
 }
+
+/*
+ * btrfs_{start,end}_write() is similar to mnt_{want, drop}_write(),
+ * they are used to prevent the some tasks writing data into the page cache
+ * by nocow before the subvolume is snapshoted, but flush the data into
+ * the disk after the snapshot creation.
+ */
+void btrfs_end_nocow_write(struct btrfs_root *root)
+{
+        percpu_counter_dec(&root->subv_writers->counter);
+        /*
+         * Make sure counter is updated before we wake up
+         * waiters.
+         */
+        smp_mb();
+        if (waitqueue_active(&root->subv_writers->wait))
+                wake_up(&root->subv_writers->wait);
+}
+
+int btrfs_start_nocow_write(struct btrfs_root *root)
+{
+        if (unlikely(atomic_read(&root->will_be_snapshoted)))
+                return 0;
+
+        percpu_counter_inc(&root->subv_writers->counter);
+        /*
+         * Make sure counter is updated before we check for snapshot creation.
+         */
+        smp_mb();
+        if (unlikely(atomic_read(&root->will_be_snapshoted))) {
+                btrfs_end_nocow_write(root);
+                return 0;
+        }
+        return 1;
+}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 85bbd01f1271..ae69a00387e7 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -229,12 +229,14 @@ void free_extent_state(struct extent_state *state)
         }
 }
 
-static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
+static struct rb_node *tree_insert(struct rb_root *root,
+                                   struct rb_node *search_start,
+                                   u64 offset,
                                    struct rb_node *node,
                                    struct rb_node ***p_in,
                                    struct rb_node **parent_in)
 {
-        struct rb_node **p = &root->rb_node;
+        struct rb_node **p;
         struct rb_node *parent = NULL;
         struct tree_entry *entry;
 
@@ -244,6 +246,7 @@ static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
                 goto do_insert;
         }
 
+        p = search_start ? &search_start : &root->rb_node;
         while (*p) {
                 parent = *p;
                 entry = rb_entry(parent, struct tree_entry, rb_node);
@@ -430,7 +433,7 @@ static int insert_state(struct extent_io_tree *tree,
 
         set_state_bits(tree, state, bits);
 
-        node = tree_insert(&tree->state, end, &state->rb_node, p, parent);
+        node = tree_insert(&tree->state, NULL, end, &state->rb_node, p, parent);
         if (node) {
                 struct extent_state *found;
                 found = rb_entry(node, struct extent_state, rb_node);
@@ -477,8 +480,8 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
         prealloc->state = orig->state;
         orig->start = split;
 
-        node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node,
-                           NULL, NULL);
+        node = tree_insert(&tree->state, &orig->rb_node, prealloc->end,
+                           &prealloc->rb_node, NULL, NULL);
         if (node) {
                 free_extent_state(prealloc);
                 return -EEXIST;
@@ -2757,7 +2760,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
 
         if (em_cached && *em_cached) {
                 em = *em_cached;
-                if (em->in_tree && start >= em->start &&
+                if (extent_map_in_tree(em) && start >= em->start &&
                     start < extent_map_end(em)) {
                         atomic_inc(&em->refs);
                         return em;
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 996ad56b57db..1874aee69c86 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -51,7 +51,7 @@ struct extent_map *alloc_extent_map(void)
         em = kmem_cache_zalloc(extent_map_cache, GFP_NOFS);
         if (!em)
                 return NULL;
-        em->in_tree = 0;
+        RB_CLEAR_NODE(&em->rb_node);
         em->flags = 0;
         em->compress_type = BTRFS_COMPRESS_NONE;
         em->generation = 0;
@@ -73,7 +73,7 @@ void free_extent_map(struct extent_map *em)
                 return;
         WARN_ON(atomic_read(&em->refs) == 0);
         if (atomic_dec_and_test(&em->refs)) {
-                WARN_ON(em->in_tree);
+                WARN_ON(extent_map_in_tree(em));
                 WARN_ON(!list_empty(&em->list));
                 kmem_cache_free(extent_map_cache, em);
         }
@@ -99,8 +99,6 @@ static int tree_insert(struct rb_root *root, struct extent_map *em)
                 parent = *p;
                 entry = rb_entry(parent, struct extent_map, rb_node);
 
-                WARN_ON(!entry->in_tree);
-
                 if (em->start < entry->start)
                         p = &(*p)->rb_left;
                 else if (em->start >= extent_map_end(entry))
@@ -128,7 +126,6 @@ static int tree_insert(struct rb_root *root, struct extent_map *em)
                 if (end > entry->start && em->start < extent_map_end(entry))
                         return -EEXIST;
 
-        em->in_tree = 1;
         rb_link_node(&em->rb_node, orig_parent, p);
         rb_insert_color(&em->rb_node, root);
         return 0;
@@ -153,8 +150,6 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 offset,
                 prev = n;
                 prev_entry = entry;
 
-                WARN_ON(!entry->in_tree);
-
                 if (offset < entry->start)
                         n = n->rb_left;
                 else if (offset >= extent_map_end(entry))
@@ -240,12 +235,12 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
                         em->len += merge->len;
                         em->block_len += merge->block_len;
                         em->block_start = merge->block_start;
-                        merge->in_tree = 0;
                         em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start;
                         em->mod_start = merge->mod_start;
                         em->generation = max(em->generation, merge->generation);
 
                         rb_erase(&merge->rb_node, &tree->map);
+                        RB_CLEAR_NODE(&merge->rb_node);
                         free_extent_map(merge);
                 }
         }
@@ -257,7 +252,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
                 em->len += merge->len;
                 em->block_len += merge->block_len;
                 rb_erase(&merge->rb_node, &tree->map);
-                merge->in_tree = 0;
+                RB_CLEAR_NODE(&merge->rb_node);
                 em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
                 em->generation = max(em->generation, merge->generation);
                 free_extent_map(merge);
@@ -319,7 +314,21 @@ out:
 void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
 {
         clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
-        if (em->in_tree)
+        if (extent_map_in_tree(em))
+                try_merge_map(tree, em);
+}
+
+static inline void setup_extent_mapping(struct extent_map_tree *tree,
+                                        struct extent_map *em,
+                                        int modified)
+{
+        atomic_inc(&em->refs);
+        em->mod_start = em->start;
+        em->mod_len = em->len;
+
+        if (modified)
+                list_move(&em->list, &tree->modified_extents);
+        else
                 try_merge_map(tree, em);
 }
 
@@ -342,15 +351,7 @@ int add_extent_mapping(struct extent_map_tree *tree,
         if (ret)
                 goto out;
 
-        atomic_inc(&em->refs);
-
-        em->mod_start = em->start;
-        em->mod_len = em->len;
-
-        if (modified)
-                list_move(&em->list, &tree->modified_extents);
-        else
-                try_merge_map(tree, em);
+        setup_extent_mapping(tree, em, modified);
 out:
         return ret;
 }
@@ -434,6 +435,21 @@ int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
         rb_erase(&em->rb_node, &tree->map);
         if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
                 list_del_init(&em->list);
-        em->in_tree = 0;
+        RB_CLEAR_NODE(&em->rb_node);
         return ret;
 }
+
+void replace_extent_mapping(struct extent_map_tree *tree,
+                            struct extent_map *cur,
+                            struct extent_map *new,
+                            int modified)
+{
+        WARN_ON(test_bit(EXTENT_FLAG_PINNED, &cur->flags));
+        ASSERT(extent_map_in_tree(cur));
+        if (!test_bit(EXTENT_FLAG_LOGGING, &cur->flags))
+                list_del_init(&cur->list);
+        rb_replace_node(&cur->rb_node, &new->rb_node, &tree->map);
+        RB_CLEAR_NODE(&cur->rb_node);
+
+        setup_extent_mapping(tree, new, modified);
+}
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 93fba716d7f8..e7fd8a56a140 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -33,7 +33,6 @@ struct extent_map {
         unsigned long flags;
         struct block_device *bdev;
         atomic_t refs;
-        unsigned int in_tree;
         unsigned int compress_type;
         struct list_head list;
 };
@@ -44,6 +43,11 @@ struct extent_map_tree {
         rwlock_t lock;
 };
 
+static inline int extent_map_in_tree(const struct extent_map *em)
+{
+        return !RB_EMPTY_NODE(&em->rb_node);
+}
+
 static inline u64 extent_map_end(struct extent_map *em)
 {
         if (em->start + em->len < em->start)
@@ -64,6 +68,10 @@ struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
 int add_extent_mapping(struct extent_map_tree *tree,
                        struct extent_map *em, int modified);
 int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em);
+void replace_extent_mapping(struct extent_map_tree *tree,
+                            struct extent_map *cur,
+                            struct extent_map *new,
+                            int modified);
 
 struct extent_map *alloc_extent_map(void);
 void free_extent_map(struct extent_map *em);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0165b8672f09..e1ffb1e22898 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -591,7 +591,6 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
                 clear_bit(EXTENT_FLAG_PINNED, &em->flags);
                 clear_bit(EXTENT_FLAG_LOGGING, &flags);
                 modified = !list_empty(&em->list);
-                remove_extent_mapping(em_tree, em);
                 if (no_splits)
                         goto next;
 
@@ -622,8 +621,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
                         split->bdev = em->bdev;
                         split->flags = flags;
                         split->compress_type = em->compress_type;
-                        ret = add_extent_mapping(em_tree, split, modified);
-                        BUG_ON(ret); /* Logic error */
+                        replace_extent_mapping(em_tree, em, split, modified);
                         free_extent_map(split);
                         split = split2;
                         split2 = NULL;
@@ -661,12 +659,20 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
                                 split->orig_block_len = 0;
                         }
 
-                        ret = add_extent_mapping(em_tree, split, modified);
-                        BUG_ON(ret); /* Logic error */
+                        if (extent_map_in_tree(em)) {
+                                replace_extent_mapping(em_tree, em, split,
+                                                       modified);
+                        } else {
+                                ret = add_extent_mapping(em_tree, split,
+                                                         modified);
+                                ASSERT(ret == 0); /* Logic error */
+                        }
                         free_extent_map(split);
                         split = NULL;
                 }
 next:
+                if (extent_map_in_tree(em))
+                        remove_extent_mapping(em_tree, em);
                 write_unlock(&em_tree->lock);
 
                 /* once for us */
@@ -720,7 +726,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
         if (drop_cache)
                 btrfs_drop_extent_cache(inode, start, end - 1, 0);
 
-        if (start >= BTRFS_I(inode)->disk_i_size)
+        if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
                 modify_tree = 0;
 
         while (1) {
@@ -798,7 +804,10 @@ next_slot:
                  */
                 if (start > key.offset && end < extent_end) {
                         BUG_ON(del_nr > 0);
-                        BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+                        if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+                                ret = -EINVAL;
+                                break;
+                        }
 
                         memcpy(&new_key, &key, sizeof(new_key));
                         new_key.offset = start;
@@ -841,7 +850,10 @@ next_slot:
                  *      | -------- extent -------- |
                  */
                 if (start <= key.offset && end < extent_end) {
-                        BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+                        if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+                                ret = -EINVAL;
+                                break;
+                        }
 
                         memcpy(&new_key, &key, sizeof(new_key));
                         new_key.offset = end;
@@ -864,7 +876,10 @@ next_slot:
                  */
                 if (start > key.offset && end >= extent_end) {
                         BUG_ON(del_nr > 0);
-                        BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+                        if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+                                ret = -EINVAL;
+                                break;
+                        }
 
                         btrfs_set_file_extent_num_bytes(leaf, fi,
                                                         start - key.offset);
@@ -938,34 +953,42 @@ next_slot:
                  * Set path->slots[0] to first slot, so that after the delete
                  * if items are move off from our leaf to its immediate left or
                  * right neighbor leafs, we end up with a correct and adjusted
-                 * path->slots[0] for our insertion.
+                 * path->slots[0] for our insertion (if replace_extent != 0).
                  */
                 path->slots[0] = del_slot;
                 ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
                 if (ret)
                         btrfs_abort_transaction(trans, root, ret);
+        }
 
-                leaf = path->nodes[0];
-                /*
-                 * leaf eb has flag EXTENT_BUFFER_STALE if it was deleted (that
-                 * is, its contents got pushed to its neighbors), in which case
-                 * it means path->locks[0] == 0
-                 */
-                if (!ret && replace_extent && leafs_visited == 1 &&
-                    path->locks[0] &&
-                    btrfs_leaf_free_space(root, leaf) >=
-                    sizeof(struct btrfs_item) + extent_item_size) {
-
-                        key.objectid = ino;
-                        key.type = BTRFS_EXTENT_DATA_KEY;
-                        key.offset = start;
-                        setup_items_for_insert(root, path, &key,
-                                               &extent_item_size,
-                                               extent_item_size,
-                                               sizeof(struct btrfs_item) +
-                                               extent_item_size, 1);
-                        *key_inserted = 1;
+        leaf = path->nodes[0];
+        /*
+         * If btrfs_del_items() was called, it might have deleted a leaf, in
+         * which case it unlocked our path, so check path->locks[0] matches a
+         * write lock.
+         */
+        if (!ret && replace_extent && leafs_visited == 1 &&
+            (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING ||
+             path->locks[0] == BTRFS_WRITE_LOCK) &&
+            btrfs_leaf_free_space(root, leaf) >=
+            sizeof(struct btrfs_item) + extent_item_size) {
+
+                key.objectid = ino;
+                key.type = BTRFS_EXTENT_DATA_KEY;
+                key.offset = start;
+                if (!del_nr && path->slots[0] < btrfs_header_nritems(leaf)) {
+                        struct btrfs_key slot_key;
+
+                        btrfs_item_key_to_cpu(leaf, &slot_key, path->slots[0]);
+                        if (btrfs_comp_cpu_keys(&key, &slot_key) > 0)
+                                path->slots[0]++;
                 }
+                setup_items_for_insert(root, path, &key,
+                                       &extent_item_size,
+                                       extent_item_size,
+                                       sizeof(struct btrfs_item) +
+                                       extent_item_size, 1);
+                *key_inserted = 1;
         }
 
         if (!replace_extent || !(*key_inserted))
@@ -1346,11 +1369,11 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
                 struct btrfs_ordered_extent *ordered;
                 lock_extent_bits(&BTRFS_I(inode)->io_tree,
                                  start_pos, last_pos, 0, cached_state);
-                ordered = btrfs_lookup_first_ordered_extent(inode, last_pos);
+                ordered = btrfs_lookup_ordered_range(inode, start_pos,
+                                                     last_pos - start_pos + 1);
                 if (ordered &&
                     ordered->file_offset + ordered->len > start_pos &&
                     ordered->file_offset <= last_pos) {
-                        btrfs_put_ordered_extent(ordered);
                         unlock_extent_cached(&BTRFS_I(inode)->io_tree,
                                              start_pos, last_pos,
                                              cached_state, GFP_NOFS);
@@ -1358,12 +1381,9 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
                                 unlock_page(pages[i]);
                                 page_cache_release(pages[i]);
                         }
-                        ret = btrfs_wait_ordered_range(inode, start_pos,
-                                                last_pos - start_pos + 1);
-                        if (ret)
-                                return ret;
-                        else
-                                return -EAGAIN;
+                        btrfs_start_ordered_extent(inode, ordered, 1);
+                        btrfs_put_ordered_extent(ordered);
+                        return -EAGAIN;
                 }
                 if (ordered)
                         btrfs_put_ordered_extent(ordered);
@@ -1396,8 +1416,12 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
         u64 num_bytes;
         int ret;
 
+        ret = btrfs_start_nocow_write(root);
+        if (!ret)
+                return -ENOSPC;
+
         lockstart = round_down(pos, root->sectorsize);
-        lockend = lockstart + round_up(*write_bytes, root->sectorsize) - 1;
+        lockend = round_up(pos + *write_bytes, root->sectorsize) - 1;
 
         while (1) {
                 lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
@@ -1415,12 +1439,10 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
         ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
         if (ret <= 0) {
                 ret = 0;
+                btrfs_end_nocow_write(root);
         } else {
-                clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-                                 EXTENT_DIRTY | EXTENT_DELALLOC |
-                                 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
-                                 NULL, GFP_NOFS);
-                *write_bytes = min_t(size_t, *write_bytes, num_bytes);
+                *write_bytes = min_t(size_t, *write_bytes ,
+                                     num_bytes - pos + lockstart);
         }
 
         unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
@@ -1510,6 +1532,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
                         if (!only_release_metadata)
                                 btrfs_free_reserved_data_space(inode,
                                                                reserve_bytes);
+                        else
+                                btrfs_end_nocow_write(root);
                         break;
                 }
 
@@ -1598,6 +1622,9 @@ again:
                 }
 
                 release_bytes = 0;
+                if (only_release_metadata)
+                        btrfs_end_nocow_write(root);
+
                 if (only_release_metadata && copied > 0) {
                         u64 lockstart = round_down(pos, root->sectorsize);
                         u64 lockend = lockstart +
@@ -1624,10 +1651,12 @@ again:
         kfree(pages);
 
         if (release_bytes) {
-                if (only_release_metadata)
+                if (only_release_metadata) {
+                        btrfs_end_nocow_write(root);
                         btrfs_delalloc_release_metadata(inode, release_bytes);
-                else
+                } else {
                         btrfs_delalloc_release_space(inode, release_bytes);
+                }
         }
 
         return num_written ? num_written : ret;
@@ -1797,7 +1826,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
         BTRFS_I(inode)->last_sub_trans = root->log_transid;
         if (num_written > 0) {
                 err = generic_write_sync(file, pos, num_written);
-                if (err < 0 && num_written > 0)
+                if (err < 0)
                         num_written = err;
         }
 
@@ -1856,8 +1885,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
         struct dentry *dentry = file->f_path.dentry;
         struct inode *inode = dentry->d_inode;
         struct btrfs_root *root = BTRFS_I(inode)->root;
-        int ret = 0;
         struct btrfs_trans_handle *trans;
+        struct btrfs_log_ctx ctx;
+        int ret = 0;
         bool full_sync = 0;
 
         trace_btrfs_sync_file(file, datasync);
@@ -1951,7 +1981,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
         }
         trans->sync = true;
 
-        ret = btrfs_log_dentry_safe(trans, root, dentry);
+        btrfs_init_log_ctx(&ctx);
+
+        ret = btrfs_log_dentry_safe(trans, root, dentry, &ctx);
         if (ret < 0) {
                 /* Fallthrough and commit/free transaction. */
                 ret = 1;
@@ -1971,7 +2003,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
         if (ret != BTRFS_NO_LOG_SYNC) {
                 if (!ret) {
-                        ret = btrfs_sync_log(trans, root);
+                        ret = btrfs_sync_log(trans, root, &ctx);
                         if (!ret) {
                                 ret = btrfs_end_transaction(trans, root);
                                 goto out;
@@ -2157,6 +2189,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
         bool same_page = ((offset >> PAGE_CACHE_SHIFT) ==
                           ((offset + len - 1) >> PAGE_CACHE_SHIFT));
         bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
+        u64 ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
 
         ret = btrfs_wait_ordered_range(inode, offset, len);
         if (ret)
@@ -2172,14 +2205,14 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
          * entire page.
          */
         if (same_page && len < PAGE_CACHE_SIZE) {
-                if (offset < round_up(inode->i_size, PAGE_CACHE_SIZE))
+                if (offset < ino_size)
                         ret = btrfs_truncate_page(inode, offset, len, 0);
                 mutex_unlock(&inode->i_mutex);
                 return ret;
         }
 
         /* zero back part of the first page */
-        if (offset < round_up(inode->i_size, PAGE_CACHE_SIZE)) {
+        if (offset < ino_size) {
                 ret = btrfs_truncate_page(inode, offset, 0, 0);
                 if (ret) {
                         mutex_unlock(&inode->i_mutex);
@@ -2188,7 +2221,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
         }
 
         /* zero the front end of the last page */
-        if (offset + len < round_up(inode->i_size, PAGE_CACHE_SIZE)) {
+        if (offset + len < ino_size) {
                 ret = btrfs_truncate_page(inode, offset + len, 0, 1);
                 if (ret) {
                         mutex_unlock(&inode->i_mutex);
@@ -2277,10 +2310,13 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
                 trans->block_rsv = &root->fs_info->trans_block_rsv;
 
-                ret = fill_holes(trans, inode, path, cur_offset, drop_end);
-                if (ret) {
-                        err = ret;
-                        break;
+                if (cur_offset < ino_size) {
+                        ret = fill_holes(trans, inode, path, cur_offset,
+                                         drop_end);
+                        if (ret) {
+                                err = ret;
+                                break;
+                        }
                 }
 
                 cur_offset = drop_end;
@@ -2313,10 +2349,12 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
         }
 
         trans->block_rsv = &root->fs_info->trans_block_rsv;
-        ret = fill_holes(trans, inode, path, cur_offset, drop_end);
-        if (ret) {
-                err = ret;
-                goto out_trans;
+        if (cur_offset < ino_size) {
+                ret = fill_holes(trans, inode, path, cur_offset, drop_end);
+                if (ret) {
+                        err = ret;
+                        goto out_trans;
+                }
         }
 
 out_trans:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d3d44486290b..06e9a4152b14 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -864,7 +864,8 @@ static noinline int cow_file_range(struct inode *inode,
 
         if (btrfs_is_free_space_inode(inode)) {
                 WARN_ON_ONCE(1);
-                return -EINVAL;
+                ret = -EINVAL;
+                goto out_unlock;
         }
 
         num_bytes = ALIGN(end - start + 1, blocksize);
@@ -1075,17 +1076,15 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
                 async_cow->end = cur_end;
                 INIT_LIST_HEAD(&async_cow->extents);
 
-                async_cow->work.func = async_cow_start;
-                async_cow->work.ordered_func = async_cow_submit;
-                async_cow->work.ordered_free = async_cow_free;
-                async_cow->work.flags = 0;
+                btrfs_init_work(&async_cow->work, async_cow_start,
+                                async_cow_submit, async_cow_free);
 
                 nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
                         PAGE_CACHE_SHIFT;
                 atomic_add(nr_pages, &root->fs_info->async_delalloc_pages);
 
-                btrfs_queue_worker(&root->fs_info->delalloc_workers,
-                                   &async_cow->work);
+                btrfs_queue_work(root->fs_info->delalloc_workers,
+                                 &async_cow->work);
 
                 if (atomic_read(&root->fs_info->async_delalloc_pages) > limit) {
                         wait_event(root->fs_info->async_submit_wait,
@@ -1843,9 +1842,9 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
 
         SetPageChecked(page);
         page_cache_get(page);
-        fixup->work.func = btrfs_writepage_fixup_worker;
+        btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
         fixup->page = page;
-        btrfs_queue_worker(&root->fs_info->fixup_workers, &fixup->work);
+        btrfs_queue_work(root->fs_info->fixup_workers, &fixup->work);
         return -EBUSY;
 }
 
@@ -2239,6 +2238,11 @@ static noinline int relink_extent_backref(struct btrfs_path *path,
                 return PTR_ERR(root);
         }
 
+        if (btrfs_root_readonly(root)) {
+                srcu_read_unlock(&fs_info->subvol_srcu, index);
+                return 0;
+        }
+
         /* step 2: get inode */
         key.objectid = backref->inum;
         key.type = BTRFS_INODE_ITEM_KEY;
@@ -2759,7 +2763,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
         struct inode *inode = page->mapping->host;
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_ordered_extent *ordered_extent = NULL;
-        struct btrfs_workers *workers;
+        struct btrfs_workqueue *workers;
 
         trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -2768,14 +2772,13 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
                                             end - start + 1, uptodate))
                 return 0;
 
-        ordered_extent->work.func = finish_ordered_fn;
-        ordered_extent->work.flags = 0;
+        btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
 
         if (btrfs_is_free_space_inode(inode))
-                workers = &root->fs_info->endio_freespace_worker;
+                workers = root->fs_info->endio_freespace_worker;
         else
-                workers = &root->fs_info->endio_write_workers;
-        btrfs_queue_worker(workers, &ordered_extent->work);
+                workers = root->fs_info->endio_write_workers;
+        btrfs_queue_work(workers, &ordered_extent->work);
 
         return 0;
 }
@@ -4593,7 +4596,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
         struct rb_node *node;
 
         ASSERT(inode->i_state & I_FREEING);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         write_lock(&map_tree->lock);
         while (!RB_EMPTY_ROOT(&map_tree->map)) {
@@ -4924,7 +4927,8 @@ void btrfs_invalidate_inodes(struct btrfs_root *root)
         struct inode *inode;
         u64 objectid = 0;
 
-        WARN_ON(btrfs_root_refs(&root->root_item) != 0);
+        if (!test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
+                WARN_ON(btrfs_root_refs(&root->root_item) != 0);
 
         spin_lock(&root->inode_lock);
 again:
@@ -5799,6 +5803,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
         }
 out_unlock:
         btrfs_end_transaction(trans, root);
+        btrfs_balance_delayed_items(root);
         btrfs_btree_balance_dirty(root);
         if (drop_inode) {
                 inode_dec_link_count(inode);
@@ -5872,6 +5877,7 @@ out_unlock:
                 inode_dec_link_count(inode);
                 iput(inode);
         }
+        btrfs_balance_delayed_items(root);
         btrfs_btree_balance_dirty(root);
         return err;
 }
@@ -5930,6 +5936,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
         }
 
         btrfs_end_transaction(trans, root);
+        btrfs_balance_delayed_items(root);
 fail:
         if (drop_inode) {
                 inode_dec_link_count(inode);
@@ -5996,6 +6003,7 @@ out_fail:
         btrfs_end_transaction(trans, root);
         if (drop_on_err)
                 iput(inode);
+        btrfs_balance_delayed_items(root);
         btrfs_btree_balance_dirty(root);
         return err;
 }
@@ -6550,6 +6558,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
         int ret;
         struct extent_buffer *leaf;
         struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
         struct btrfs_file_extent_item *fi;
         struct btrfs_key key;
         u64 disk_bytenr;
@@ -6626,6 +6635,20 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 
         if (btrfs_extent_readonly(root, disk_bytenr))
                 goto out;
+
+        num_bytes = min(offset + *len, extent_end) - offset;
+        if (!nocow && found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+                u64 range_end;
+
+                range_end = round_up(offset + num_bytes, root->sectorsize) - 1;
+                ret = test_range_bit(io_tree, offset, range_end,
+                                     EXTENT_DELALLOC, 0, NULL);
+                if (ret) {
+                        ret = -EAGAIN;
+                        goto out;
+                }
+        }
+
         btrfs_release_path(path);
 
         /*
@@ -6654,7 +6677,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
          */
         disk_bytenr += backref_offset;
         disk_bytenr += offset - key.offset;
-        num_bytes = min(offset + *len, extent_end) - offset;
         if (csum_exist_in_range(root, disk_bytenr, num_bytes))
                                 goto out;
         /*
@@ -7024,10 +7046,9 @@ again:
         if (!ret)
                 goto out_test;
 
-        ordered->work.func = finish_ordered_fn;
-        ordered->work.flags = 0;
-        btrfs_queue_worker(&root->fs_info->endio_write_workers,
-                           &ordered->work);
+        btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL);
+        btrfs_queue_work(root->fs_info->endio_write_workers,
+                         &ordered->work);
 out_test:
         /*
          * our bio might span multiple ordered extents.  If we haven't
@@ -7404,15 +7425,15 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
         smp_mb__after_atomic_inc();
 
         /*
-         * The generic stuff only does filemap_write_and_wait_range, which isn't
-         * enough if we've written compressed pages to this area, so we need to
-         * call btrfs_wait_ordered_range to make absolutely sure that any
-         * outstanding dirty pages are on disk.
+         * The generic stuff only does filemap_write_and_wait_range, which
+         * isn't enough if we've written compressed pages to this area, so
+         * we need to flush the dirty pages again to make absolutely sure
+         * that any outstanding dirty pages are on disk.
          */
         count = iov_length(iov, nr_segs);
-        ret = btrfs_wait_ordered_range(inode, offset, count);
-        if (ret)
-                return ret;
+        if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+                     &BTRFS_I(inode)->runtime_flags))
+                filemap_fdatawrite_range(inode->i_mapping, offset, count);
 
         if (rw & WRITE) {
                 /*
@@ -8404,7 +8425,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
         work->inode = inode;
         work->wait = wait;
         work->delay_iput = delay_iput;
-        work->work.func = btrfs_run_delalloc_work;
+        btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
 
         return work;
 }
@@ -8419,7 +8440,8 @@ void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
  * some fairly slow code that needs optimization. This walks the list
  * of all the inodes with pending delalloc and forces them to disk.
  */
-static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
+static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
+                                   int nr)
 {
         struct btrfs_inode *binode;
         struct inode *inode;
@@ -8431,6 +8453,7 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
         INIT_LIST_HEAD(&works);
         INIT_LIST_HEAD(&splice);
 
+        mutex_lock(&root->delalloc_mutex);
         spin_lock(&root->delalloc_lock);
         list_splice_init(&root->delalloc_inodes, &splice);
         while (!list_empty(&splice)) {
@@ -8453,12 +8476,14 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
                         else
                                 iput(inode);
                         ret = -ENOMEM;
-                        goto out;
+                        break;
                 }
                 list_add_tail(&work->list, &works);
-                btrfs_queue_worker(&root->fs_info->flush_workers,
-                                   &work->work);
-
+                btrfs_queue_work(root->fs_info->flush_workers,
+                                 &work->work);
+                ret++;
+                if (nr != -1 && ret >= nr)
+                        break;
                 cond_resched();
                 spin_lock(&root->delalloc_lock);
         }
@@ -8468,18 +8493,13 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
                 list_del_init(&work->list);
                 btrfs_wait_and_free_delalloc_work(work);
         }
-        return 0;
-out:
-        list_for_each_entry_safe(work, next, &works, list) {
-                list_del_init(&work->list);
-                btrfs_wait_and_free_delalloc_work(work);
-        }
 
         if (!list_empty_careful(&splice)) {
                 spin_lock(&root->delalloc_lock);
                 list_splice_tail(&splice, &root->delalloc_inodes);
                 spin_unlock(&root->delalloc_lock);
         }
+        mutex_unlock(&root->delalloc_mutex);
         return ret;
 }
 
@@ -8490,7 +8510,9 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
         if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
                 return -EROFS;
 
-        ret = __start_delalloc_inodes(root, delay_iput);
+        ret = __start_delalloc_inodes(root, delay_iput, -1);
+        if (ret > 0)
+                ret = 0;
         /*
          * the filemap_flush will queue IO into the worker threads, but
          * we have to make sure the IO is actually started and that
@@ -8507,7 +8529,8 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
         return ret;
 }
 
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
+                               int nr)
 {
         struct btrfs_root *root;
         struct list_head splice;
@@ -8518,9 +8541,10 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput)
 
         INIT_LIST_HEAD(&splice);
 
+        mutex_lock(&fs_info->delalloc_root_mutex);
         spin_lock(&fs_info->delalloc_root_lock);
         list_splice_init(&fs_info->delalloc_roots, &splice);
-        while (!list_empty(&splice)) {
+        while (!list_empty(&splice) && nr) {
                 root = list_first_entry(&splice, struct btrfs_root,
                                         delalloc_root);
                 root = btrfs_grab_fs_root(root);
@@ -8529,15 +8553,20 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput)
                                &fs_info->delalloc_roots);
                 spin_unlock(&fs_info->delalloc_root_lock);
 
-                ret = __start_delalloc_inodes(root, delay_iput);
+                ret = __start_delalloc_inodes(root, delay_iput, nr);
                 btrfs_put_fs_root(root);
-                if (ret)
+                if (ret < 0)
                         goto out;
 
+                if (nr != -1) {
+                        nr -= ret;
+                        WARN_ON(nr < 0);
+                }
                 spin_lock(&fs_info->delalloc_root_lock);
         }
         spin_unlock(&fs_info->delalloc_root_lock);
 
+        ret = 0;
         atomic_inc(&fs_info->async_submit_draining);
         while (atomic_read(&fs_info->nr_async_submits) ||
               atomic_read(&fs_info->async_delalloc_pages)) {
@@ -8546,13 +8575,13 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput)
                     atomic_read(&fs_info->async_delalloc_pages) == 0));
         }
         atomic_dec(&fs_info->async_submit_draining);
-        return 0;
 out:
         if (!list_empty_careful(&splice)) {
                 spin_lock(&fs_info->delalloc_root_lock);
                 list_splice_tail(&splice, &fs_info->delalloc_roots);
                 spin_unlock(&fs_info->delalloc_root_lock);
         }
+        mutex_unlock(&fs_info->delalloc_root_mutex);
         return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a6d8efa46bfe..0401397b5c92 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -59,6 +59,32 @@
 #include "props.h"
 #include "sysfs.h"
 
+#ifdef CONFIG_64BIT
+/* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
+ * structures are incorrect, as the timespec structure from userspace
+ * is 4 bytes too small. We define these alternatives here to teach
+ * the kernel about the 32-bit struct packing.
+ */
+struct btrfs_ioctl_timespec_32 {
+        __u64 sec;
+        __u32 nsec;
+} __attribute__ ((__packed__));
+
+struct btrfs_ioctl_received_subvol_args_32 {
+        char    uuid[BTRFS_UUID_SIZE];  /* in */
+        __u64   stransid;               /* in */
+        __u64   rtransid;               /* out */
+        struct btrfs_ioctl_timespec_32 stime; /* in */
+        struct btrfs_ioctl_timespec_32 rtime; /* out */
+        __u64   flags;                  /* in */
+        __u64   reserved[16];           /* in */
+} __attribute__ ((__packed__));
+
+#define BTRFS_IOC_SET_RECEIVED_SUBVOL_32 _IOWR(BTRFS_IOCTL_MAGIC, 37, \
+                                struct btrfs_ioctl_received_subvol_args_32)
+#endif
+
+
 static int btrfs_clone(struct inode *src, struct inode *inode,
                        u64 off, u64 olen, u64 olen_aligned, u64 destoff);
 
@@ -585,6 +611,23 @@ fail:
         return ret;
 }
 
+static void btrfs_wait_nocow_write(struct btrfs_root *root)
+{
+        s64 writers;
+        DEFINE_WAIT(wait);
+
+        do {
+                prepare_to_wait(&root->subv_writers->wait, &wait,
+                                TASK_UNINTERRUPTIBLE);
+
+                writers = percpu_counter_sum(&root->subv_writers->counter);
+                if (writers)
+                        schedule();
+
+                finish_wait(&root->subv_writers->wait, &wait);
+        } while (writers);
+}
+
 static int create_snapshot(struct btrfs_root *root, struct inode *dir,
                            struct dentry *dentry, char *name, int namelen,
                            u64 *async_transid, bool readonly,
@@ -598,15 +641,21 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
         if (!root->ref_cows)
                 return -EINVAL;
 
+        atomic_inc(&root->will_be_snapshoted);
+        smp_mb__after_atomic_inc();
+        btrfs_wait_nocow_write(root);
+
         ret = btrfs_start_delalloc_inodes(root, 0);
         if (ret)
-                return ret;
+                goto out;
 
         btrfs_wait_ordered_extents(root, -1);
 
         pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
-        if (!pending_snapshot)
-                return -ENOMEM;
+        if (!pending_snapshot) {
+                ret = -ENOMEM;
+                goto out;
+        }
 
         btrfs_init_block_rsv(&pending_snapshot->block_rsv,
                              BTRFS_BLOCK_RSV_TEMP);
@@ -623,7 +672,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
                                         &pending_snapshot->qgroup_reserved,
                                         false);
         if (ret)
-                goto out;
+                goto free;
 
         pending_snapshot->dentry = dentry;
         pending_snapshot->root = root;
@@ -674,8 +723,10 @@ fail:
         btrfs_subvolume_release_metadata(BTRFS_I(dir)->root,
                                          &pending_snapshot->block_rsv,
                                          pending_snapshot->qgroup_reserved);
-out:
+free:
         kfree(pending_snapshot);
+out:
+        atomic_dec(&root->will_be_snapshoted);
         return ret;
 }
 
@@ -884,12 +935,14 @@ static int find_new_extents(struct btrfs_root *root,
         min_key.type = BTRFS_EXTENT_DATA_KEY;
         min_key.offset = *off;
 
-        path->keep_locks = 1;
-
         while (1) {
+                path->keep_locks = 1;
                 ret = btrfs_search_forward(root, &min_key, path, newer_than);
                 if (ret != 0)
                         goto none;
+                path->keep_locks = 0;
+                btrfs_unlock_up_safe(path, 1);
+process_slot:
                 if (min_key.objectid != ino)
                         goto none;
                 if (min_key.type != BTRFS_EXTENT_DATA_KEY)
@@ -908,6 +961,12 @@ static int find_new_extents(struct btrfs_root *root,
                         return 0;
                 }
 
+                path->slots[0]++;
+                if (path->slots[0] < btrfs_header_nritems(leaf)) {
+                        btrfs_item_key_to_cpu(leaf, &min_key, path->slots[0]);
+                        goto process_slot;
+                }
+
                 if (min_key.offset == (u64)-1)
                         goto none;
 
@@ -935,10 +994,13 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
         read_unlock(&em_tree->lock);
 
         if (!em) {
+                struct extent_state *cached = NULL;
+                u64 end = start + len - 1;
+
                 /* get the big lock and read metadata off disk */
-                lock_extent(io_tree, start, start + len - 1);
+                lock_extent_bits(io_tree, start, end, 0, &cached);
                 em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
-                unlock_extent(io_tree, start, start + len - 1);
+                unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS);
 
                 if (IS_ERR(em))
                         return NULL;
@@ -957,7 +1019,8 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em)
                 return false;
 
         next = defrag_lookup_extent(inode, em->start + em->len);
-        if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
+        if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE ||
+            (em->block_start + em->block_len == next->block_start))
                 ret = false;
 
         free_extent_map(next);
@@ -1076,10 +1139,12 @@ again:
                 page_start = page_offset(page);
                 page_end = page_start + PAGE_CACHE_SIZE - 1;
                 while (1) {
-                        lock_extent(tree, page_start, page_end);
+                        lock_extent_bits(tree, page_start, page_end,
+                                         0, &cached_state);
                         ordered = btrfs_lookup_ordered_extent(inode,
                                                               page_start);
-                        unlock_extent(tree, page_start, page_end);
+                        unlock_extent_cached(tree, page_start, page_end,
+                                             &cached_state, GFP_NOFS);
                         if (!ordered)
                                 break;
 
@@ -1356,8 +1421,12 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
                 }
         }
 
-        if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO))
+        if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO)) {
                 filemap_flush(inode->i_mapping);
+                if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+                             &BTRFS_I(inode)->runtime_flags))
+                        filemap_flush(inode->i_mapping);
+        }
 
         if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
                 /* the filemap_flush will queue IO into the worker threads, but
@@ -1573,7 +1642,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
                 if (src_inode->i_sb != file_inode(file)->i_sb) {
                         btrfs_info(BTRFS_I(src_inode)->root->fs_info,
                                    "Snapshot src from another FS");
-                        ret = -EINVAL;
+                        ret = -EXDEV;
                 } else if (!inode_owner_or_capable(src_inode)) {
                         /*
                          * Subvolume creation is not restricted, but snapshots
@@ -1797,7 +1866,9 @@ static noinline int may_destroy_subvol(struct btrfs_root *root)
         if (di && !IS_ERR(di)) {
                 btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
                 if (key.objectid == root->root_key.objectid) {
-                        ret = -ENOTEMPTY;
+                        ret = -EPERM;
+                        btrfs_err(root->fs_info, "deleting default subvolume "
+                                  "%llu is not allowed", key.objectid);
                         goto out;
                 }
                 btrfs_release_path(path);
@@ -2994,8 +3065,9 @@ process_slot:
                                                          new_key.offset + datal,
                                                          1);
                                 if (ret) {
-                                        btrfs_abort_transaction(trans, root,
-                                                                ret);
+                                        if (ret != -EINVAL)
+                                                btrfs_abort_transaction(trans,
+                                                                root, ret);
                                         btrfs_end_transaction(trans, root);
                                         goto out;
                                 }
@@ -3153,8 +3225,9 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
          *   decompress into destination's address_space (the file offset
          *   may change, so source mapping won't do), then recompress (or
          *   otherwise reinsert) a subrange.
-         * - allow ranges within the same file to be cloned (provided
-         *   they don't overlap)?
+         *
+         * - split destination inode's inline extents.  The inline extents can
+         *   be either compressed or non-compressed.
          */
 
         /* the destination must be opened for writing */
@@ -4353,10 +4426,9 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
         return btrfs_qgroup_wait_for_completion(root->fs_info);
 }
 
-static long btrfs_ioctl_set_received_subvol(struct file *file,
-                                            void __user *arg)
+static long _btrfs_ioctl_set_received_subvol(struct file *file,
+                                            struct btrfs_ioctl_received_subvol_args *sa)
 {
-        struct btrfs_ioctl_received_subvol_args *sa = NULL;
         struct inode *inode = file_inode(file);
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_root_item *root_item = &root->root_item;
@@ -4384,13 +4456,6 @@ static long btrfs_ioctl_set_received_subvol(struct file *file,
                 goto out;
         }
 
-        sa = memdup_user(arg, sizeof(*sa));
-        if (IS_ERR(sa)) {
-                ret = PTR_ERR(sa);
-                sa = NULL;
-                goto out;
-        }
-
         /*
          * 1 - root item
          * 2 - uuid items (received uuid + subvol uuid)
@@ -4444,14 +4509,91 @@ static long btrfs_ioctl_set_received_subvol(struct file *file,
                 goto out;
         }
 
+out:
+        up_write(&root->fs_info->subvol_sem);
+        mnt_drop_write_file(file);
+        return ret;
+}
+
+#ifdef CONFIG_64BIT
+static long btrfs_ioctl_set_received_subvol_32(struct file *file,
+                                                void __user *arg)
+{
+        struct btrfs_ioctl_received_subvol_args_32 *args32 = NULL;
+        struct btrfs_ioctl_received_subvol_args *args64 = NULL;
+        int ret = 0;
+
+        args32 = memdup_user(arg, sizeof(*args32));
+        if (IS_ERR(args32)) {
+                ret = PTR_ERR(args32);
+                args32 = NULL;
+                goto out;
+        }
+
+        args64 = kmalloc(sizeof(*args64), GFP_NOFS);
+        if (IS_ERR(args64)) {
+                ret = PTR_ERR(args64);
+                args64 = NULL;
+                goto out;
+        }
+
+        memcpy(args64->uuid, args32->uuid, BTRFS_UUID_SIZE);
+        args64->stransid = args32->stransid;
+        args64->rtransid = args32->rtransid;
+        args64->stime.sec = args32->stime.sec;
+        args64->stime.nsec = args32->stime.nsec;
+        args64->rtime.sec = args32->rtime.sec;
+        args64->rtime.nsec = args32->rtime.nsec;
+        args64->flags = args32->flags;
+
+        ret = _btrfs_ioctl_set_received_subvol(file, args64);
+        if (ret)
+                goto out;
+
+        memcpy(args32->uuid, args64->uuid, BTRFS_UUID_SIZE);
+        args32->stransid = args64->stransid;
+        args32->rtransid = args64->rtransid;
+        args32->stime.sec = args64->stime.sec;
+        args32->stime.nsec = args64->stime.nsec;
+        args32->rtime.sec = args64->rtime.sec;
+        args32->rtime.nsec = args64->rtime.nsec;
+        args32->flags = args64->flags;
+
+        ret = copy_to_user(arg, args32, sizeof(*args32));
+        if (ret)
+                ret = -EFAULT;
+
+out:
+        kfree(args32);
+        kfree(args64);
+        return ret;
+}
+#endif
+
+static long btrfs_ioctl_set_received_subvol(struct file *file,
+                                            void __user *arg)
+{
+        struct btrfs_ioctl_received_subvol_args *sa = NULL;
+        int ret = 0;
+
+        sa = memdup_user(arg, sizeof(*sa));
+        if (IS_ERR(sa)) {
+                ret = PTR_ERR(sa);
+                sa = NULL;
+                goto out;
+        }
+
+        ret = _btrfs_ioctl_set_received_subvol(file, sa);
+
+        if (ret)
+                goto out;
+
         ret = copy_to_user(arg, sa, sizeof(*sa));
         if (ret)
                 ret = -EFAULT;
 
 out:
         kfree(sa);
-        up_write(&root->fs_info->subvol_sem);
-        mnt_drop_write_file(file);
         return ret;
 }
 
@@ -4746,7 +4888,7 @@ long btrfs_ioctl(struct file *file, unsigned int
         case BTRFS_IOC_SYNC: {
                 int ret;
 
-                ret = btrfs_start_delalloc_roots(root->fs_info, 0);
+                ret = btrfs_start_delalloc_roots(root->fs_info, 0, -1);
                 if (ret)
                         return ret;
                 ret = btrfs_sync_fs(file->f_dentry->d_sb, 1);
@@ -4770,6 +4912,10 @@ long btrfs_ioctl(struct file *file, unsigned int
                 return btrfs_ioctl_balance_progress(root, argp);
         case BTRFS_IOC_SET_RECEIVED_SUBVOL:
                 return btrfs_ioctl_set_received_subvol(file, argp);
+#ifdef CONFIG_64BIT
+        case BTRFS_IOC_SET_RECEIVED_SUBVOL_32:
+                return btrfs_ioctl_set_received_subvol_32(file, argp);
+#endif
         case BTRFS_IOC_SEND:
                 return btrfs_ioctl_send(file, argp);
         case BTRFS_IOC_GET_DEV_STATS:
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index b16450b840e7..a94b05f72869 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -349,10 +349,13 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
         if (!uptodate)
                 set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
 
-        if (entry->bytes_left == 0)
+        if (entry->bytes_left == 0) {
                 ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-        else
+                if (waitqueue_active(&entry->wait))
+                        wake_up(&entry->wait);
+        } else {
                 ret = 1;
+        }
 out:
         if (!ret && cached && entry) {
                 *cached = entry;
@@ -410,10 +413,13 @@ have_entry:
         if (!uptodate)
                 set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
 
-        if (entry->bytes_left == 0)
+        if (entry->bytes_left == 0) {
                 ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-        else
+                if (waitqueue_active(&entry->wait))
+                        wake_up(&entry->wait);
+        } else {
                 ret = 1;
+        }
 out:
         if (!ret && cached && entry) {
                 *cached = entry;
@@ -424,27 +430,48 @@ out:
 }
 
 /* Needs to either be called under a log transaction or the log_mutex */
-void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode)
+void btrfs_get_logged_extents(struct inode *inode,
+                              struct list_head *logged_list)
 {
         struct btrfs_ordered_inode_tree *tree;
         struct btrfs_ordered_extent *ordered;
         struct rb_node *n;
-        int index = log->log_transid % 2;
 
         tree = &BTRFS_I(inode)->ordered_tree;
         spin_lock_irq(&tree->lock);
         for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
                 ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
-                spin_lock(&log->log_extents_lock[index]);
-                if (list_empty(&ordered->log_list)) {
-                        list_add_tail(&ordered->log_list, &log->logged_list[index]);
-                        atomic_inc(&ordered->refs);
-                }
-                spin_unlock(&log->log_extents_lock[index]);
+                if (!list_empty(&ordered->log_list))
+                        continue;
+                list_add_tail(&ordered->log_list, logged_list);
+                atomic_inc(&ordered->refs);
         }
         spin_unlock_irq(&tree->lock);
 }
 
+void btrfs_put_logged_extents(struct list_head *logged_list)
+{
+        struct btrfs_ordered_extent *ordered;
+
+        while (!list_empty(logged_list)) {
+                ordered = list_first_entry(logged_list,
+                                           struct btrfs_ordered_extent,
+                                           log_list);
+                list_del_init(&ordered->log_list);
+                btrfs_put_ordered_extent(ordered);
+        }
+}
+
+void btrfs_submit_logged_extents(struct list_head *logged_list,
+                                 struct btrfs_root *log)
+{
+        int index = log->log_transid % 2;
+
+        spin_lock_irq(&log->log_extents_lock[index]);
+        list_splice_tail(logged_list, &log->logged_list[index]);
+        spin_unlock_irq(&log->log_extents_lock[index]);
+}
+
 void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
 {
         struct btrfs_ordered_extent *ordered;
@@ -577,7 +604,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
         INIT_LIST_HEAD(&splice);
         INIT_LIST_HEAD(&works);
 
-        mutex_lock(&root->fs_info->ordered_operations_mutex);
+        mutex_lock(&root->ordered_extent_mutex);
         spin_lock(&root->ordered_extent_lock);
         list_splice_init(&root->ordered_extents, &splice);
         while (!list_empty(&splice) && nr) {
@@ -588,10 +615,11 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
                 atomic_inc(&ordered->refs);
                 spin_unlock(&root->ordered_extent_lock);
 
-                ordered->flush_work.func = btrfs_run_ordered_extent_work;
+                btrfs_init_work(&ordered->flush_work,
+                                btrfs_run_ordered_extent_work, NULL, NULL);
                 list_add_tail(&ordered->work_list, &works);
-                btrfs_queue_worker(&root->fs_info->flush_workers,
-                                   &ordered->flush_work);
+                btrfs_queue_work(root->fs_info->flush_workers,
+                                 &ordered->flush_work);
 
                 cond_resched();
                 spin_lock(&root->ordered_extent_lock);
@@ -608,7 +636,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
                 btrfs_put_ordered_extent(ordered);
                 cond_resched();
         }
-        mutex_unlock(&root->fs_info->ordered_operations_mutex);
+        mutex_unlock(&root->ordered_extent_mutex);
 
         return count;
 }
@@ -621,6 +649,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 
         INIT_LIST_HEAD(&splice);
 
+        mutex_lock(&fs_info->ordered_operations_mutex);
         spin_lock(&fs_info->ordered_root_lock);
         list_splice_init(&fs_info->ordered_roots, &splice);
         while (!list_empty(&splice) && nr) {
@@ -643,6 +672,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
         }
         list_splice_tail(&splice, &fs_info->ordered_roots);
         spin_unlock(&fs_info->ordered_root_lock);
+        mutex_unlock(&fs_info->ordered_operations_mutex);
 }
 
 /*
@@ -704,8 +734,8 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
                         goto out;
                 }
                 list_add_tail(&work->list, &works);
-                btrfs_queue_worker(&root->fs_info->flush_workers,
-                                   &work->work);
+                btrfs_queue_work(root->fs_info->flush_workers,
+                                 &work->work);
 
                 cond_resched();
                 spin_lock(&root->fs_info->ordered_root_lock);
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 9b0450f7ac20..246897058efb 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -197,7 +197,11 @@ void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
                                  struct inode *inode);
 int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr);
 void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr);
-void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode);
+void btrfs_get_logged_extents(struct inode *inode,
+                              struct list_head *logged_list);
+void btrfs_put_logged_extents(struct list_head *logged_list);
+void btrfs_submit_logged_extents(struct list_head *logged_list,
+                                 struct btrfs_root *log);
 void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid);
 void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
 int __init ordered_data_init(void);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 472302a2d745..2cf905877aaf 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1509,8 +1509,8 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
                 ret = qgroup_rescan_init(fs_info, 0, 1);
                 if (!ret) {
                         qgroup_rescan_zero_tracking(fs_info);
-                        btrfs_queue_worker(&fs_info->qgroup_rescan_workers,
-                                           &fs_info->qgroup_rescan_work);
+                        btrfs_queue_work(fs_info->qgroup_rescan_workers,
+                                         &fs_info->qgroup_rescan_work);
                 }
                 ret = 0;
         }
@@ -2095,7 +2095,8 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 
         memset(&fs_info->qgroup_rescan_work, 0,
                sizeof(fs_info->qgroup_rescan_work));
-        fs_info->qgroup_rescan_work.func = btrfs_qgroup_rescan_worker;
+        btrfs_init_work(&fs_info->qgroup_rescan_work,
+                        btrfs_qgroup_rescan_worker, NULL, NULL);
 
         if (ret) {
 err:
@@ -2158,8 +2159,8 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 
         qgroup_rescan_zero_tracking(fs_info);
 
-        btrfs_queue_worker(&fs_info->qgroup_rescan_workers,
-                           &fs_info->qgroup_rescan_work);
+        btrfs_queue_work(fs_info->qgroup_rescan_workers,
+                         &fs_info->qgroup_rescan_work);
 
         return 0;
 }
@@ -2190,6 +2191,6 @@ void
 btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
 {
         if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
-                btrfs_queue_worker(&fs_info->qgroup_rescan_workers,
-                                   &fs_info->qgroup_rescan_work);
+                btrfs_queue_work(fs_info->qgroup_rescan_workers,
+                                 &fs_info->qgroup_rescan_work);
 }
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 9af0b25d991a..4055291a523e 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1416,20 +1416,18 @@ cleanup:
 
 static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
 {
-        rbio->work.flags = 0;
-        rbio->work.func = rmw_work;
+        btrfs_init_work(&rbio->work, rmw_work, NULL, NULL);
 
-        btrfs_queue_worker(&rbio->fs_info->rmw_workers,
-                           &rbio->work);
+        btrfs_queue_work(rbio->fs_info->rmw_workers,
+                         &rbio->work);
 }
 
 static void async_read_rebuild(struct btrfs_raid_bio *rbio)
 {
-        rbio->work.flags = 0;
-        rbio->work.func = read_rebuild_work;
+        btrfs_init_work(&rbio->work, read_rebuild_work, NULL, NULL);
 
-        btrfs_queue_worker(&rbio->fs_info->rmw_workers,
-                           &rbio->work);
+        btrfs_queue_work(rbio->fs_info->rmw_workers,
+                         &rbio->work);
 }
 
 /*
@@ -1667,10 +1665,9 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
         plug = container_of(cb, struct btrfs_plug_cb, cb);
 
         if (from_schedule) {
-                plug->work.flags = 0;
-                plug->work.func = unplug_work;
-                btrfs_queue_worker(&plug->info->rmw_workers,
-                                   &plug->work);
+                btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
+                btrfs_queue_work(plug->info->rmw_workers,
+                                 &plug->work);
                 return;
         }
         run_plug(plug);
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 31c797c48c3e..30947f923620 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -793,10 +793,10 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
                 /* FIXME we cannot handle this properly right now */
                 BUG();
         }
-        rmw->work.func = reada_start_machine_worker;
+        btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
         rmw->fs_info = fs_info;
 
-        btrfs_queue_worker(&fs_info->readahead_workers, &rmw->work);
+        btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
 }
 
 #ifdef DEBUG
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 07b3b36f40ee..def428a25b2a 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4248,7 +4248,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
         btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu",
                rc->block_group->key.objectid, rc->block_group->flags);
 
-        ret = btrfs_start_delalloc_roots(fs_info, 0);
+        ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
         if (ret < 0) {
                 err = ret;
                 goto out;
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 1389b69059de..38bb47e7d6b1 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/err.h>
 #include <linux/uuid.h>
 #include "ctree.h"
 #include "transaction.h"
@@ -271,7 +272,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
                 key.offset++;
 
                 root = btrfs_read_fs_root(tree_root, &root_key);
-                err = PTR_RET(root);
+                err = PTR_ERR_OR_ZERO(root);
                 if (err && err != -ENOENT) {
                         break;
                 } else if (err == -ENOENT) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index efba5d1282ee..93e6d7172844 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -315,6 +315,16 @@ static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx)
         atomic_inc(&fs_info->scrubs_running);
         atomic_inc(&fs_info->scrubs_paused);
         mutex_unlock(&fs_info->scrub_lock);
+
+        /*
+         * check if @scrubs_running=@scrubs_paused condition
+         * inside wait_event() is not an atomic operation.
+         * which means we may inc/dec @scrub_running/paused
+         * at any time. Let's wake up @scrub_pause_wait as
+         * much as we can to let commit transaction blocked less.
+         */
+        wake_up(&fs_info->scrub_pause_wait);
+
         atomic_inc(&sctx->workers_pending);
 }
 
@@ -418,7 +428,8 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
                 sbio->index = i;
                 sbio->sctx = sctx;
                 sbio->page_count = 0;
-                sbio->work.func = scrub_bio_end_io_worker;
+                btrfs_init_work(&sbio->work, scrub_bio_end_io_worker,
+                                NULL, NULL);
 
                 if (i != SCRUB_BIOS_PER_SCTX - 1)
                         sctx->bios[i]->next_free = i + 1;
@@ -987,9 +998,10 @@ nodatasum_case:
                 fixup_nodatasum->root = fs_info->extent_root;
                 fixup_nodatasum->mirror_num = failed_mirror_index + 1;
                 scrub_pending_trans_workers_inc(sctx);
-                fixup_nodatasum->work.func = scrub_fixup_nodatasum;
-                btrfs_queue_worker(&fs_info->scrub_workers,
-                                   &fixup_nodatasum->work);
+                btrfs_init_work(&fixup_nodatasum->work, scrub_fixup_nodatasum,
+                                NULL, NULL);
+                btrfs_queue_work(fs_info->scrub_workers,
+                                 &fixup_nodatasum->work);
                 goto out;
         }
 
@@ -1603,8 +1615,8 @@ static void scrub_wr_bio_end_io(struct bio *bio, int err)
         sbio->err = err;
         sbio->bio = bio;
 
-        sbio->work.func = scrub_wr_bio_end_io_worker;
-        btrfs_queue_worker(&fs_info->scrub_wr_completion_workers, &sbio->work);
+        btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
+        btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
 static void scrub_wr_bio_end_io_worker(struct btrfs_work *work)
@@ -2072,7 +2084,7 @@ static void scrub_bio_end_io(struct bio *bio, int err)
         sbio->err = err;
         sbio->bio = bio;
 
-        btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
+        btrfs_queue_work(fs_info->scrub_workers, &sbio->work);
 }
 
 static void scrub_bio_end_io_worker(struct btrfs_work *work)
@@ -2686,10 +2698,23 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
                 wait_event(sctx->list_wait,
                            atomic_read(&sctx->bios_in_flight) == 0);
-                atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+                atomic_inc(&fs_info->scrubs_paused);
+                wake_up(&fs_info->scrub_pause_wait);
+
+                /*
+                 * must be called before we decrease @scrub_paused.
+                 * make sure we don't block transaction commit while
+                 * we are waiting pending workers finished.
+                 */
                 wait_event(sctx->list_wait,
                            atomic_read(&sctx->workers_pending) == 0);
-                scrub_blocked_if_needed(fs_info);
+                atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+
+                mutex_lock(&fs_info->scrub_lock);
+                __scrub_blocked_if_needed(fs_info);
+                atomic_dec(&fs_info->scrubs_paused);
+                mutex_unlock(&fs_info->scrub_lock);
+                wake_up(&fs_info->scrub_pause_wait);
 
                 btrfs_put_block_group(cache);
                 if (ret)
@@ -2757,33 +2782,35 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
                                                 int is_dev_replace)
 {
         int ret = 0;
+        int flags = WQ_FREEZABLE | WQ_UNBOUND;
+        int max_active = fs_info->thread_pool_size;
 
         if (fs_info->scrub_workers_refcnt == 0) {
                 if (is_dev_replace)
-                        btrfs_init_workers(&fs_info->scrub_workers, "scrub", 1,
-                                        &fs_info->generic_worker);
+                        fs_info->scrub_workers =
+                                btrfs_alloc_workqueue("btrfs-scrub", flags,
+                                                      1, 4);
                 else
-                        btrfs_init_workers(&fs_info->scrub_workers, "scrub",
-                                        fs_info->thread_pool_size,
-                                        &fs_info->generic_worker);
-                fs_info->scrub_workers.idle_thresh = 4;
-                ret = btrfs_start_workers(&fs_info->scrub_workers);
-                if (ret)
+                        fs_info->scrub_workers =
+                                btrfs_alloc_workqueue("btrfs-scrub", flags,
+                                                      max_active, 4);
+                if (!fs_info->scrub_workers) {
+                        ret = -ENOMEM;
                         goto out;
-                btrfs_init_workers(&fs_info->scrub_wr_completion_workers,
-                                   "scrubwrc",
-                                   fs_info->thread_pool_size,
-                                   &fs_info->generic_worker);
-                fs_info->scrub_wr_completion_workers.idle_thresh = 2;
-                ret = btrfs_start_workers(
-                                &fs_info->scrub_wr_completion_workers);
-                if (ret)
+                }
+                fs_info->scrub_wr_completion_workers =
+                        btrfs_alloc_workqueue("btrfs-scrubwrc", flags,
+                                              max_active, 2);
+                if (!fs_info->scrub_wr_completion_workers) {
+                        ret = -ENOMEM;
                         goto out;
-                btrfs_init_workers(&fs_info->scrub_nocow_workers, "scrubnc", 1,
-                                   &fs_info->generic_worker);
-                ret = btrfs_start_workers(&fs_info->scrub_nocow_workers);
-                if (ret)
+                }
+                fs_info->scrub_nocow_workers =
+                        btrfs_alloc_workqueue("btrfs-scrubnc", flags, 1, 0);
+                if (!fs_info->scrub_nocow_workers) {
+                        ret = -ENOMEM;
                         goto out;
+                }
         }
         ++fs_info->scrub_workers_refcnt;
 out:
@@ -2793,9 +2820,9 @@ out:
 static noinline_for_stack void scrub_workers_put(struct btrfs_fs_info *fs_info)
 {
         if (--fs_info->scrub_workers_refcnt == 0) {
-                btrfs_stop_workers(&fs_info->scrub_workers);
-                btrfs_stop_workers(&fs_info->scrub_wr_completion_workers);
-                btrfs_stop_workers(&fs_info->scrub_nocow_workers);
+                btrfs_destroy_workqueue(fs_info->scrub_workers);
+                btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
+                btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
         }
         WARN_ON(fs_info->scrub_workers_refcnt < 0);
 }
@@ -3106,10 +3133,10 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
         nocow_ctx->len = len;
         nocow_ctx->mirror_num = mirror_num;
         nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
-        nocow_ctx->work.func = copy_nocow_pages_worker;
+        btrfs_init_work(&nocow_ctx->work, copy_nocow_pages_worker, NULL, NULL);
         INIT_LIST_HEAD(&nocow_ctx->inodes);
-        btrfs_queue_worker(&fs_info->scrub_nocow_workers,
-                           &nocow_ctx->work);
+        btrfs_queue_work(fs_info->scrub_nocow_workers,
+                         &nocow_ctx->work);
 
         return 0;
 }
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 9dde9717c1b9..9b6da9d55f9a 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -51,15 +51,18 @@ struct fs_path {
                 struct {
                         char *start;
                         char *end;
-                        char *prepared;
 
                         char *buf;
-                        int buf_len;
-                        unsigned int reversed:1;
-                        unsigned int virtual_mem:1;
+                        unsigned short buf_len:15;
+                        unsigned short reversed:1;
                         char inline_buf[];
                 };
-                char pad[PAGE_SIZE];
+                /*
+                 * Average path length does not exceed 200 bytes, we'll have
+                 * better packing in the slab and higher chance to satisfy
+                 * a allocation later during send.
+                 */
+                char pad[256];
         };
 };
 #define FS_PATH_INLINE_SIZE \
@@ -109,6 +112,7 @@ struct send_ctx {
         int cur_inode_deleted;
         u64 cur_inode_size;
         u64 cur_inode_mode;
+        u64 cur_inode_rdev;
         u64 cur_inode_last_extent;
 
         u64 send_progress;
@@ -120,6 +124,8 @@ struct send_ctx {
         struct list_head name_cache_list;
         int name_cache_size;
 
+        struct file_ra_state ra;
+
         char *read_buf;
 
         /*
@@ -175,6 +181,47 @@ struct send_ctx {
          * own move/rename can be performed.
          */
         struct rb_root waiting_dir_moves;
+
+        /*
+         * A directory that is going to be rm'ed might have a child directory
+         * which is in the pending directory moves index above. In this case,
+         * the directory can only be removed after the move/rename of its child
+         * is performed. Example:
+         *
+         * Parent snapshot:
+         *
+         * .                        (ino 256)
+         * |-- a/                   (ino 257)
+         *     |-- b/               (ino 258)
+         *         |-- c/           (ino 259)
+         *         |   |-- x/       (ino 260)
+         *         |
+         *         |-- y/           (ino 261)
+         *
+         * Send snapshot:
+         *
+         * .                        (ino 256)
+         * |-- a/                   (ino 257)
+         *     |-- b/               (ino 258)
+         *         |-- YY/          (ino 261)
+         *              |-- x/      (ino 260)
+         *
+         * Sequence of steps that lead to the send snapshot:
+         * rm -f /a/b/c/foo.txt
+         * mv /a/b/y /a/b/YY
+         * mv /a/b/c/x /a/b/YY
+         * rmdir /a/b/c
+         *
+         * When the child is processed, its move/rename is delayed until its
+         * parent is processed (as explained above), but all other operations
+         * like update utimes, chown, chgrp, etc, are performed and the paths
+         * that it uses for those operations must use the orphanized name of
+         * its parent (the directory we're going to rm later), so we need to
+         * memorize that name.
+         *
+         * Indexed by the inode number of the directory to be deleted.
+         */
+        struct rb_root orphan_dirs;
 };
 
 struct pending_dir_move {
@@ -189,6 +236,18 @@ struct pending_dir_move {
 struct waiting_dir_move {
         struct rb_node node;
         u64 ino;
+        /*
+         * There might be some directory that could not be removed because it
+         * was waiting for this directory inode to be moved first. Therefore
+         * after this directory is moved, we can try to rmdir the ino rmdir_ino.
+         */
+        u64 rmdir_ino;
+};
+
+struct orphan_dir_info {
+        struct rb_node node;
+        u64 ino;
+        u64 gen;
 };
 
 struct name_cache_entry {
@@ -214,6 +273,11 @@ struct name_cache_entry {
 
 static int is_waiting_for_move(struct send_ctx *sctx, u64 ino);
 
+static struct waiting_dir_move *
+get_waiting_dir_move(struct send_ctx *sctx, u64 ino);
+
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino);
+
 static int need_send_hole(struct send_ctx *sctx)
 {
         return (sctx->parent_root && !sctx->cur_inode_new &&
@@ -242,7 +306,6 @@ static struct fs_path *fs_path_alloc(void)
         if (!p)
                 return NULL;
         p->reversed = 0;
-        p->virtual_mem = 0;
         p->buf = p->inline_buf;
         p->buf_len = FS_PATH_INLINE_SIZE;
         fs_path_reset(p);
@@ -265,12 +328,8 @@ static void fs_path_free(struct fs_path *p)
 {
         if (!p)
                 return;
-        if (p->buf != p->inline_buf) {
-                if (p->virtual_mem)
-                        vfree(p->buf);
-                else
-                        kfree(p->buf);
-        }
+        if (p->buf != p->inline_buf)
+                kfree(p->buf);
         kfree(p);
 }
 
@@ -292,40 +351,23 @@ static int fs_path_ensure_buf(struct fs_path *p, int len)
 
         path_len = p->end - p->start;
         old_buf_len = p->buf_len;
-        len = PAGE_ALIGN(len);
-
-        if (p->buf == p->inline_buf) {
-                tmp_buf = kmalloc(len, GFP_NOFS | __GFP_NOWARN);
-                if (!tmp_buf) {
-                        tmp_buf = vmalloc(len);
-                        if (!tmp_buf)
-                                return -ENOMEM;
-                        p->virtual_mem = 1;
-                }
-                memcpy(tmp_buf, p->buf, p->buf_len);
-                p->buf = tmp_buf;
-                p->buf_len = len;
-        } else {
-                if (p->virtual_mem) {
-                        tmp_buf = vmalloc(len);
-                        if (!tmp_buf)
-                                return -ENOMEM;
-                        memcpy(tmp_buf, p->buf, p->buf_len);
-                        vfree(p->buf);
-                } else {
-                        tmp_buf = krealloc(p->buf, len, GFP_NOFS);
-                        if (!tmp_buf) {
-                                tmp_buf = vmalloc(len);
-                                if (!tmp_buf)
-                                        return -ENOMEM;
-                                memcpy(tmp_buf, p->buf, p->buf_len);
-                                kfree(p->buf);
-                                p->virtual_mem = 1;
-                        }
-                }
-                p->buf = tmp_buf;
-                p->buf_len = len;
-        }
+
+        /*
+         * First time the inline_buf does not suffice
+         */
+        if (p->buf == p->inline_buf)
+                tmp_buf = kmalloc(len, GFP_NOFS);
+        else
+                tmp_buf = krealloc(p->buf, len, GFP_NOFS);
+        if (!tmp_buf)
+                return -ENOMEM;
+        p->buf = tmp_buf;
+        /*
+         * The real size of the buffer is bigger, this will let the fast path
+         * happen most of the time
+         */
+        p->buf_len = ksize(p->buf);
+
         if (p->reversed) {
                 tmp_buf = p->buf + old_buf_len - path_len - 1;
                 p->end = p->buf + p->buf_len - 1;
@@ -338,7 +380,8 @@ static int fs_path_ensure_buf(struct fs_path *p, int len)
         return 0;
 }
 
-static int fs_path_prepare_for_add(struct fs_path *p, int name_len)
+static int fs_path_prepare_for_add(struct fs_path *p, int name_len,
+                                   char **prepared)
 {
         int ret;
         int new_len;
@@ -354,11 +397,11 @@ static int fs_path_prepare_for_add(struct fs_path *p, int name_len)
                 if (p->start != p->end)
                         *--p->start = '/';
                 p->start -= name_len;
-                p->prepared = p->start;
+                *prepared = p->start;
         } else {
                 if (p->start != p->end)
                         *p->end++ = '/';
-                p->prepared = p->end;
+                *prepared = p->end;
                 p->end += name_len;
                 *p->end = 0;
         }
@@ -370,12 +413,12 @@ out:
 static int fs_path_add(struct fs_path *p, const char *name, int name_len)
 {
         int ret;
+        char *prepared;
 
-        ret = fs_path_prepare_for_add(p, name_len);
+        ret = fs_path_prepare_for_add(p, name_len, &prepared);
         if (ret < 0)
                 goto out;
-        memcpy(p->prepared, name, name_len);
-        p->prepared = NULL;
+        memcpy(prepared, name, name_len);
 
 out:
         return ret;
@@ -384,12 +427,12 @@ out:
 static int fs_path_add_path(struct fs_path *p, struct fs_path *p2)
 {
         int ret;
+        char *prepared;
 
-        ret = fs_path_prepare_for_add(p, p2->end - p2->start);
+        ret = fs_path_prepare_for_add(p, p2->end - p2->start, &prepared);
         if (ret < 0)
                 goto out;
-        memcpy(p->prepared, p2->start, p2->end - p2->start);
-        p->prepared = NULL;
+        memcpy(prepared, p2->start, p2->end - p2->start);
 
 out:
         return ret;
@@ -400,13 +443,13 @@ static int fs_path_add_from_extent_buffer(struct fs_path *p,
                                           unsigned long off, int len)
 {
         int ret;
+        char *prepared;
 
-        ret = fs_path_prepare_for_add(p, len);
+        ret = fs_path_prepare_for_add(p, len, &prepared);
         if (ret < 0)
                 goto out;
 
-        read_extent_buffer(eb, p->prepared, off, len);
-        p->prepared = NULL;
+        read_extent_buffer(eb, prepared, off, len);
 
 out:
         return ret;
@@ -915,9 +958,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
         struct btrfs_dir_item *di;
         struct btrfs_key di_key;
         char *buf = NULL;
-        char *buf2 = NULL;
-        int buf_len;
-        int buf_virtual = 0;
+        const int buf_len = PATH_MAX;
         u32 name_len;
         u32 data_len;
         u32 cur;
@@ -927,7 +968,6 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
         int num;
         u8 type;
 
-        buf_len = PAGE_SIZE;
         buf = kmalloc(buf_len, GFP_NOFS);
         if (!buf) {
                 ret = -ENOMEM;
@@ -949,30 +989,12 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
                 type = btrfs_dir_type(eb, di);
                 btrfs_dir_item_key_to_cpu(eb, di, &di_key);
 
+                /*
+                 * Path too long
+                 */
                 if (name_len + data_len > buf_len) {
-                        buf_len = PAGE_ALIGN(name_len + data_len);
-                        if (buf_virtual) {
-                                buf2 = vmalloc(buf_len);
-                                if (!buf2) {
-                                        ret = -ENOMEM;
-                                        goto out;
-                                }
-                                vfree(buf);
-                        } else {
-                                buf2 = krealloc(buf, buf_len, GFP_NOFS);
-                                if (!buf2) {
-                                        buf2 = vmalloc(buf_len);
-                                        if (!buf2) {
-                                                ret = -ENOMEM;
-                                                goto out;
-                                        }
-                                        kfree(buf);
-                                        buf_virtual = 1;
-                                }
-                        }
-
-                        buf = buf2;
-                        buf2 = NULL;
+                        ret = -ENAMETOOLONG;
+                        goto out;
                 }
 
                 read_extent_buffer(eb, buf, (unsigned long)(di + 1),
@@ -995,10 +1017,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
         }
 
 out:
-        if (buf_virtual)
-                vfree(buf);
-        else
-                kfree(buf);
+        kfree(buf);
         return ret;
 }
 
@@ -1292,8 +1311,6 @@ static int find_extent_clone(struct send_ctx *sctx,
                 extent_item_pos = logical - found_key.objectid;
         else
                 extent_item_pos = 0;
-
-        extent_item_pos = logical - found_key.objectid;
         ret = iterate_extent_inodes(sctx->send_root->fs_info,
                                         found_key.objectid, extent_item_pos, 1,
                                         __iterate_backrefs, backref_ctx);
@@ -1418,11 +1435,7 @@ static int gen_unique_name(struct send_ctx *sctx,
         while (1) {
                 len = snprintf(tmp, sizeof(tmp), "o%llu-%llu-%llu",
                                 ino, gen, idx);
-                if (len >= sizeof(tmp)) {
-                        /* should really not happen */
-                        ret = -EOVERFLOW;
-                        goto out;
-                }
+                ASSERT(len < sizeof(tmp));
 
                 di = btrfs_lookup_dir_item(NULL, sctx->send_root,
                                 path, BTRFS_FIRST_FREE_OBJECTID,
@@ -1898,13 +1911,20 @@ static void name_cache_delete(struct send_ctx *sctx,
 
         nce_head = radix_tree_lookup(&sctx->name_cache,
                         (unsigned long)nce->ino);
-        BUG_ON(!nce_head);
+        if (!nce_head) {
+                btrfs_err(sctx->send_root->fs_info,
+              "name_cache_delete lookup failed ino %llu cache size %d, leaking memory",
+                        nce->ino, sctx->name_cache_size);
+        }
 
         list_del(&nce->radix_list);
         list_del(&nce->list);
         sctx->name_cache_size--;
 
-        if (list_empty(nce_head)) {
+        /*
+         * We may not get to the final release of nce_head if the lookup fails
+         */
+        if (nce_head && list_empty(nce_head)) {
                 radix_tree_delete(&sctx->name_cache, (unsigned long)nce->ino);
                 kfree(nce_head);
         }
@@ -1977,7 +1997,6 @@ static void name_cache_free(struct send_ctx *sctx)
  */
 static int __get_cur_name_and_parent(struct send_ctx *sctx,
                                      u64 ino, u64 gen,
-                                     int skip_name_cache,
                                      u64 *parent_ino,
                                      u64 *parent_gen,
                                      struct fs_path *dest)
@@ -1987,8 +2006,6 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
         struct btrfs_path *path = NULL;
         struct name_cache_entry *nce = NULL;
 
-        if (skip_name_cache)
-                goto get_ref;
         /*
          * First check if we already did a call to this function with the same
          * ino/gen. If yes, check if the cache entry is still up-to-date. If yes
@@ -2033,12 +2050,11 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
                 goto out_cache;
         }
 
-get_ref:
         /*
          * Depending on whether the inode was already processed or not, use
          * send_root or parent_root for ref lookup.
          */
-        if (ino < sctx->send_progress && !skip_name_cache)
+        if (ino < sctx->send_progress)
                 ret = get_first_ref(sctx->send_root, ino,
                                     parent_ino, parent_gen, dest);
         else
@@ -2062,8 +2078,6 @@ get_ref:
                         goto out;
                 ret = 1;
         }
-        if (skip_name_cache)
-                goto out;
 
 out_cache:
         /*
@@ -2131,9 +2145,6 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
         u64 parent_inode = 0;
         u64 parent_gen = 0;
         int stop = 0;
-        u64 start_ino = ino;
-        u64 start_gen = gen;
-        int skip_name_cache = 0;
 
         name = fs_path_alloc();
         if (!name) {
@@ -2141,31 +2152,33 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
                 goto out;
         }
 
-        if (is_waiting_for_move(sctx, ino))
-                skip_name_cache = 1;
-
-again:
         dest->reversed = 1;
         fs_path_reset(dest);
 
         while (!stop && ino != BTRFS_FIRST_FREE_OBJECTID) {
                 fs_path_reset(name);
 
-                ret = __get_cur_name_and_parent(sctx, ino, gen, skip_name_cache,
-                                &parent_inode, &parent_gen, name);
+                if (is_waiting_for_rm(sctx, ino)) {
+                        ret = gen_unique_name(sctx, ino, gen, name);
+                        if (ret < 0)
+                                goto out;
+                        ret = fs_path_add_path(dest, name);
+                        break;
+                }
+
+                if (is_waiting_for_move(sctx, ino)) {
+                        ret = get_first_ref(sctx->parent_root, ino,
+                                            &parent_inode, &parent_gen, name);
+                } else {
+                        ret = __get_cur_name_and_parent(sctx, ino, gen,
+                                                        &parent_inode,
+                                                        &parent_gen, name);
+                        if (ret)
+                                stop = 1;
+                }
+
                 if (ret < 0)
                         goto out;
-                if (ret)
-                        stop = 1;
-
-                if (!skip_name_cache &&
-                    is_waiting_for_move(sctx, parent_inode)) {
-                        ino = start_ino;
-                        gen = start_gen;
-                        stop = 0;
-                        skip_name_cache = 1;
-                        goto again;
-                }
 
                 ret = fs_path_add_path(dest, name);
                 if (ret < 0)
@@ -2429,10 +2442,16 @@ verbose_printk("btrfs: send_create_inode %llu\n", ino);
         if (!p)
                 return -ENOMEM;
 
-        ret = get_inode_info(sctx->send_root, ino, NULL, &gen, &mode, NULL,
-                        NULL, &rdev);
-        if (ret < 0)
-                goto out;
+        if (ino != sctx->cur_ino) {
+                ret = get_inode_info(sctx->send_root, ino, NULL, &gen, &mode,
+                                     NULL, NULL, &rdev);
+                if (ret < 0)
+                        goto out;
+        } else {
+                gen = sctx->cur_inode_gen;
+                mode = sctx->cur_inode_mode;
+                rdev = sctx->cur_inode_rdev;
+        }
 
         if (S_ISREG(mode)) {
                 cmd = BTRFS_SEND_C_MKFILE;
@@ -2512,17 +2531,26 @@ static int did_create_dir(struct send_ctx *sctx, u64 dir)
         key.objectid = dir;
         key.type = BTRFS_DIR_INDEX_KEY;
         key.offset = 0;
+        ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0);
+        if (ret < 0)
+                goto out;
+
         while (1) {
-                ret = btrfs_search_slot_for_read(sctx->send_root, &key, path,
-                                1, 0);
-                if (ret < 0)
-                        goto out;
-                if (!ret) {
-                        eb = path->nodes[0];
-                        slot = path->slots[0];
-                        btrfs_item_key_to_cpu(eb, &found_key, slot);
+                eb = path->nodes[0];
+                slot = path->slots[0];
+                if (slot >= btrfs_header_nritems(eb)) {
+                        ret = btrfs_next_leaf(sctx->send_root, path);
+                        if (ret < 0) {
+                                goto out;
+                        } else if (ret > 0) {
+                                ret = 0;
+                                break;
+                        }
+                        continue;
                 }
-                if (ret || found_key.objectid != key.objectid ||
+
+                btrfs_item_key_to_cpu(eb, &found_key, slot);
+                if (found_key.objectid != key.objectid ||
                     found_key.type != key.type) {
                         ret = 0;
                         goto out;
@@ -2537,8 +2565,7 @@ static int did_create_dir(struct send_ctx *sctx, u64 dir)
                         goto out;
                 }
 
-                key.offset = found_key.offset + 1;
-                btrfs_release_path(path);
+                path->slots[0]++;
         }
 
 out:
@@ -2590,7 +2617,7 @@ struct recorded_ref {
  * everything mixed. So we first record all refs and later process them.
  * This function is a helper to record one ref.
  */
-static int record_ref(struct list_head *head, u64 dir,
+static int __record_ref(struct list_head *head, u64 dir,
                       u64 dir_gen, struct fs_path *path)
 {
         struct recorded_ref *ref;
@@ -2676,12 +2703,78 @@ out:
         return ret;
 }
 
+static struct orphan_dir_info *
+add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+{
+        struct rb_node **p = &sctx->orphan_dirs.rb_node;
+        struct rb_node *parent = NULL;
+        struct orphan_dir_info *entry, *odi;
+
+        odi = kmalloc(sizeof(*odi), GFP_NOFS);
+        if (!odi)
+                return ERR_PTR(-ENOMEM);
+        odi->ino = dir_ino;
+        odi->gen = 0;
+
+        while (*p) {
+                parent = *p;
+                entry = rb_entry(parent, struct orphan_dir_info, node);
+                if (dir_ino < entry->ino) {
+                        p = &(*p)->rb_left;
+                } else if (dir_ino > entry->ino) {
+                        p = &(*p)->rb_right;
+                } else {
+                        kfree(odi);
+                        return entry;
+                }
+        }
+
+        rb_link_node(&odi->node, parent, p);
+        rb_insert_color(&odi->node, &sctx->orphan_dirs);
+        return odi;
+}
+
+static struct orphan_dir_info *
+get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+{
+        struct rb_node *n = sctx->orphan_dirs.rb_node;
+        struct orphan_dir_info *entry;
+
+        while (n) {
+                entry = rb_entry(n, struct orphan_dir_info, node);
+                if (dir_ino < entry->ino)
+                        n = n->rb_left;
+                else if (dir_ino > entry->ino)
+                        n = n->rb_right;
+                else
+                        return entry;
+        }
+        return NULL;
+}
+
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino)
+{
+        struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino);
+
+        return odi != NULL;
+}
+
+static void free_orphan_dir_info(struct send_ctx *sctx,
+                                 struct orphan_dir_info *odi)
+{
+        if (!odi)
+                return;
+        rb_erase(&odi->node, &sctx->orphan_dirs);
+        kfree(odi);
+}
+
 /*
  * Returns 1 if a directory can be removed at this point in time.
  * We check this by iterating all dir items and checking if the inode behind
  * the dir item was already processed.
  */
-static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 send_progress)
+static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
+                     u64 send_progress)
 {
         int ret = 0;
         struct btrfs_root *root = sctx->parent_root;
@@ -2704,31 +2797,52 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 send_progress)
         key.objectid = dir;
         key.type = BTRFS_DIR_INDEX_KEY;
         key.offset = 0;
+        ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+        if (ret < 0)
+                goto out;
 
         while (1) {
-                ret = btrfs_search_slot_for_read(root, &key, path, 1, 0);
-                if (ret < 0)
-                        goto out;
-                if (!ret) {
-                        btrfs_item_key_to_cpu(path->nodes[0], &found_key,
-                                        path->slots[0]);
+                struct waiting_dir_move *dm;
+
+                if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+                        ret = btrfs_next_leaf(root, path);
+                        if (ret < 0)
+                                goto out;
+                        else if (ret > 0)
+                                break;
+                        continue;
                 }
-                if (ret || found_key.objectid != key.objectid ||
-                    found_key.type != key.type) {
+                btrfs_item_key_to_cpu(path->nodes[0], &found_key,
+                                      path->slots[0]);
+                if (found_key.objectid != key.objectid ||
+                    found_key.type != key.type)
                         break;
-                }
 
                 di = btrfs_item_ptr(path->nodes[0], path->slots[0],
                                 struct btrfs_dir_item);
                 btrfs_dir_item_key_to_cpu(path->nodes[0], di, &loc);
 
+                dm = get_waiting_dir_move(sctx, loc.objectid);
+                if (dm) {
+                        struct orphan_dir_info *odi;
+
+                        odi = add_orphan_dir_info(sctx, dir);
+                        if (IS_ERR(odi)) {
+                                ret = PTR_ERR(odi);
+                                goto out;
+                        }
+                        odi->gen = dir_gen;
+                        dm->rmdir_ino = dir;
+                        ret = 0;
+                        goto out;
+                }
+
                 if (loc.objectid > send_progress) {
                         ret = 0;
                         goto out;
                 }
 
-                btrfs_release_path(path);
-                key.offset = found_key.offset + 1;
+                path->slots[0]++;
         }
 
         ret = 1;
@@ -2740,19 +2854,9 @@ out:
 
 static int is_waiting_for_move(struct send_ctx *sctx, u64 ino)
 {
-        struct rb_node *n = sctx->waiting_dir_moves.rb_node;
-        struct waiting_dir_move *entry;
+        struct waiting_dir_move *entry = get_waiting_dir_move(sctx, ino);
 
-        while (n) {
-                entry = rb_entry(n, struct waiting_dir_move, node);
-                if (ino < entry->ino)
-                        n = n->rb_left;
-                else if (ino > entry->ino)
-                        n = n->rb_right;
-                else
-                        return 1;
-        }
-        return 0;
+        return entry != NULL;
 }
 
 static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino)
@@ -2765,6 +2869,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino)
         if (!dm)
                 return -ENOMEM;
         dm->ino = ino;
+        dm->rmdir_ino = 0;
 
         while (*p) {
                 parent = *p;
@@ -2784,31 +2889,41 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino)
         return 0;
 }
 
-static int del_waiting_dir_move(struct send_ctx *sctx, u64 ino)
+static struct waiting_dir_move *
+get_waiting_dir_move(struct send_ctx *sctx, u64 ino)
 {
         struct rb_node *n = sctx->waiting_dir_moves.rb_node;
         struct waiting_dir_move *entry;
 
         while (n) {
                 entry = rb_entry(n, struct waiting_dir_move, node);
-                if (ino < entry->ino) {
+                if (ino < entry->ino)
                         n = n->rb_left;
-                } else if (ino > entry->ino) {
+                else if (ino > entry->ino)
                         n = n->rb_right;
-                } else {
-                        rb_erase(&entry->node, &sctx->waiting_dir_moves);
-                        kfree(entry);
-                        return 0;
-                }
+                else
+                        return entry;
         }
-        return -ENOENT;
+        return NULL;
+}
+
+static void free_waiting_dir_move(struct send_ctx *sctx,
+                                  struct waiting_dir_move *dm)
+{
+        if (!dm)
+                return;
+        rb_erase(&dm->node, &sctx->waiting_dir_moves);
+        kfree(dm);
 }
 
-static int add_pending_dir_move(struct send_ctx *sctx, u64 parent_ino)
+static int add_pending_dir_move(struct send_ctx *sctx,
+                                u64 ino,
+                                u64 ino_gen,
+                                u64 parent_ino)
 {
         struct rb_node **p = &sctx->pending_dir_moves.rb_node;
         struct rb_node *parent = NULL;
-        struct pending_dir_move *entry, *pm;
+        struct pending_dir_move *entry = NULL, *pm;
         struct recorded_ref *cur;
         int exists = 0;
         int ret;
@@ -2817,8 +2932,8 @@ static int add_pending_dir_move(struct send_ctx *sctx, u64 parent_ino)
         if (!pm)
                 return -ENOMEM;
         pm->parent_ino = parent_ino;
-        pm->ino = sctx->cur_ino;
-        pm->gen = sctx->cur_inode_gen;
+        pm->ino = ino;
+        pm->gen = ino_gen;
         INIT_LIST_HEAD(&pm->list);
         INIT_LIST_HEAD(&pm->update_refs);
         RB_CLEAR_NODE(&pm->node);
@@ -2888,19 +3003,52 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 {
         struct fs_path *from_path = NULL;
         struct fs_path *to_path = NULL;
+        struct fs_path *name = NULL;
         u64 orig_progress = sctx->send_progress;
         struct recorded_ref *cur;
+        u64 parent_ino, parent_gen;
+        struct waiting_dir_move *dm = NULL;
+        u64 rmdir_ino = 0;
         int ret;
 
+        name = fs_path_alloc();
         from_path = fs_path_alloc();
-        if (!from_path)
-                return -ENOMEM;
+        if (!name || !from_path) {
+                ret = -ENOMEM;
+                goto out;
+        }
 
-        sctx->send_progress = pm->ino;
-        ret = get_cur_path(sctx, pm->ino, pm->gen, from_path);
+        dm = get_waiting_dir_move(sctx, pm->ino);
+        ASSERT(dm);
+        rmdir_ino = dm->rmdir_ino;
+        free_waiting_dir_move(sctx, dm);
+
+        ret = get_first_ref(sctx->parent_root, pm->ino,
+                            &parent_ino, &parent_gen, name);
         if (ret < 0)
                 goto out;
 
+        if (parent_ino == sctx->cur_ino) {
+                /* child only renamed, not moved */
+                ASSERT(parent_gen == sctx->cur_inode_gen);
+                ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen,
+                                   from_path);
+                if (ret < 0)
+                        goto out;
+                ret = fs_path_add_path(from_path, name);
+                if (ret < 0)
+                        goto out;
+        } else {
+                /* child moved and maybe renamed too */
+                sctx->send_progress = pm->ino;
+                ret = get_cur_path(sctx, pm->ino, pm->gen, from_path);
+                if (ret < 0)
+                        goto out;
+        }
+
+        fs_path_free(name);
+        name = NULL;
+
         to_path = fs_path_alloc();
         if (!to_path) {
                 ret = -ENOMEM;
@@ -2908,9 +3056,6 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
         }
 
         sctx->send_progress = sctx->cur_ino + 1;
-        ret = del_waiting_dir_move(sctx, pm->ino);
-        ASSERT(ret == 0);
-
         ret = get_cur_path(sctx, pm->ino, pm->gen, to_path);
         if (ret < 0)
                 goto out;
@@ -2919,6 +3064,35 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
         if (ret < 0)
                 goto out;
 
+        if (rmdir_ino) {
+                struct orphan_dir_info *odi;
+
+                odi = get_orphan_dir_info(sctx, rmdir_ino);
+                if (!odi) {
+                        /* already deleted */
+                        goto finish;
+                }
+                ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino + 1);
+                if (ret < 0)
+                        goto out;
+                if (!ret)
+                        goto finish;
+
+                name = fs_path_alloc();
+                if (!name) {
+                        ret = -ENOMEM;
+                        goto out;
+                }
+                ret = get_cur_path(sctx, rmdir_ino, odi->gen, name);
+                if (ret < 0)
+                        goto out;
+                ret = send_rmdir(sctx, name);
+                if (ret < 0)
+                        goto out;
+                free_orphan_dir_info(sctx, odi);
+        }
+
+finish:
         ret = send_utimes(sctx, pm->ino, pm->gen);
         if (ret < 0)
                 goto out;
@@ -2928,12 +3102,15 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
          * and old parent(s).
          */
         list_for_each_entry(cur, &pm->update_refs, list) {
+                if (cur->dir == rmdir_ino)
+                        continue;
                 ret = send_utimes(sctx, cur->dir, cur->dir_gen);
                 if (ret < 0)
                         goto out;
         }
 
 out:
+        fs_path_free(name);
         fs_path_free(from_path);
         fs_path_free(to_path);
         sctx->send_progress = orig_progress;
@@ -3005,17 +3182,19 @@ static int wait_for_parent_move(struct send_ctx *sctx,
         int ret;
         u64 ino = parent_ref->dir;
         u64 parent_ino_before, parent_ino_after;
-        u64 new_gen, old_gen;
+        u64 old_gen;
         struct fs_path *path_before = NULL;
         struct fs_path *path_after = NULL;
         int len1, len2;
-
-        if (parent_ref->dir <= sctx->cur_ino)
-                return 0;
+        int register_upper_dirs;
+        u64 gen;
 
         if (is_waiting_for_move(sctx, ino))
                 return 1;
 
+        if (parent_ref->dir <= sctx->cur_ino)
+                return 0;
+
         ret = get_inode_info(sctx->parent_root, ino, NULL, &old_gen,
                              NULL, NULL, NULL, NULL);
         if (ret == -ENOENT)
@@ -3023,12 +3202,7 @@ static int wait_for_parent_move(struct send_ctx *sctx,
         else if (ret < 0)
                 return ret;
 
-        ret = get_inode_info(sctx->send_root, ino, NULL, &new_gen,
-                             NULL, NULL, NULL, NULL);
-        if (ret < 0)
-                return ret;
-
-        if (new_gen != old_gen)
+        if (parent_ref->dir_gen != old_gen)
                 return 0;
 
         path_before = fs_path_alloc();
@@ -3051,7 +3225,7 @@ static int wait_for_parent_move(struct send_ctx *sctx,
         }
 
         ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
-                            NULL, path_after);
+                            &gen, path_after);
         if (ret == -ENOENT) {
                 ret = 0;
                 goto out;
@@ -3061,13 +3235,67 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 
         len1 = fs_path_len(path_before);
         len2 = fs_path_len(path_after);
-        if ((parent_ino_before != parent_ino_after) && (len1 != len2 ||
-             memcmp(path_before->start, path_after->start, len1))) {
+        if (parent_ino_before != parent_ino_after || len1 != len2 ||
+             memcmp(path_before->start, path_after->start, len1)) {
                 ret = 1;
                 goto out;
         }
         ret = 0;
 
+        /*
+         * Ok, our new most direct ancestor has a higher inode number but
+         * wasn't moved/renamed. So maybe some of the new ancestors higher in
+         * the hierarchy have an higher inode number too *and* were renamed
+         * or moved - in this case we need to wait for the ancestor's rename
+         * or move operation before we can do the move/rename for the current
+         * inode.
+         */
+        register_upper_dirs = 0;
+        ino = parent_ino_after;
+again:
+        while ((ret == 0 || register_upper_dirs) && ino > sctx->cur_ino) {
+                u64 parent_gen;
+
+                fs_path_reset(path_before);
+                fs_path_reset(path_after);
+
+                ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
+                                    &parent_gen, path_after);
+                if (ret < 0)
+                        goto out;
+                ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before,
+                                    NULL, path_before);
+                if (ret == -ENOENT) {
+                        ret = 0;
+                        break;
+                } else if (ret < 0) {
+                        goto out;
+                }
+
+                len1 = fs_path_len(path_before);
+                len2 = fs_path_len(path_after);
+                if (parent_ino_before != parent_ino_after || len1 != len2 ||
+                    memcmp(path_before->start, path_after->start, len1)) {
+                        ret = 1;
+                        if (register_upper_dirs) {
+                                break;
+                        } else {
+                                register_upper_dirs = 1;
+                                ino = parent_ref->dir;
+                                gen = parent_ref->dir_gen;
+                                goto again;
+                        }
+                } else if (register_upper_dirs) {
+                        ret = add_pending_dir_move(sctx, ino, gen,
+                                                   parent_ino_after);
+                        if (ret < 0 && ret != -EEXIST)
+                                goto out;
+                }
+
+                ino = parent_ino_after;
+                gen = parent_gen;
+        }
+
 out:
         fs_path_free(path_before);
         fs_path_free(path_after);
@@ -3089,6 +3317,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
         u64 ow_gen;
         int did_overwrite = 0;
         int is_orphan = 0;
+        u64 last_dir_ino_rm = 0;
 
 verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 
@@ -3227,9 +3456,14 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
                                  * dirs, we always have one new and one deleted
                                  * ref. The deleted ref is ignored later.
                                  */
-                                if (wait_for_parent_move(sctx, cur)) {
+                                ret = wait_for_parent_move(sctx, cur);
+                                if (ret < 0)
+                                        goto out;
+                                if (ret) {
                                         ret = add_pending_dir_move(sctx,
-                                                                   cur->dir);
+                                                           sctx->cur_ino,
+                                                           sctx->cur_inode_gen,
+                                                           cur->dir);
                                         *pending_move = 1;
                                 } else {
                                         ret = send_rename(sctx, valid_path,
@@ -3259,7 +3493,8 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
                  * later, we do this check again and rmdir it then if possible.
                  * See the use of check_dirs for more details.
                  */
-                ret = can_rmdir(sctx, sctx->cur_ino, sctx->cur_ino);
+                ret = can_rmdir(sctx, sctx->cur_ino, sctx->cur_inode_gen,
+                                sctx->cur_ino);
                 if (ret < 0)
                         goto out;
                 if (ret) {
@@ -3350,8 +3585,10 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
                         ret = send_utimes(sctx, cur->dir, cur->dir_gen);
                         if (ret < 0)
                                 goto out;
-                } else if (ret == inode_state_did_delete) {
-                        ret = can_rmdir(sctx, cur->dir, sctx->cur_ino);
+                } else if (ret == inode_state_did_delete &&
+                           cur->dir != last_dir_ino_rm) {
+                        ret = can_rmdir(sctx, cur->dir, cur->dir_gen,
+                                        sctx->cur_ino);
                         if (ret < 0)
                                 goto out;
                         if (ret) {
@@ -3362,6 +3599,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
                                 ret = send_rmdir(sctx, valid_path);
                                 if (ret < 0)
                                         goto out;
+                                last_dir_ino_rm = cur->dir;
                         }
                 }
         }
@@ -3375,9 +3613,8 @@ out:
         return ret;
 }
 
-static int __record_new_ref(int num, u64 dir, int index,
-                            struct fs_path *name,
-                            void *ctx)
+static int record_ref(struct btrfs_root *root, int num, u64 dir, int index,
+                      struct fs_path *name, void *ctx, struct list_head *refs)
 {
         int ret = 0;
         struct send_ctx *sctx = ctx;
@@ -3388,7 +3625,7 @@ static int __record_new_ref(int num, u64 dir, int index,
         if (!p)
                 return -ENOMEM;
 
-        ret = get_inode_info(sctx->send_root, dir, NULL, &gen, NULL, NULL,
+        ret = get_inode_info(root, dir, NULL, &gen, NULL, NULL,
                         NULL, NULL);
         if (ret < 0)
                 goto out;
@@ -3400,7 +3637,7 @@ static int __record_new_ref(int num, u64 dir, int index,
         if (ret < 0)
                 goto out;
 
-        ret = record_ref(&sctx->new_refs, dir, gen, p);
+        ret = __record_ref(refs, dir, gen, p);
 
 out:
         if (ret)
@@ -3408,37 +3645,23 @@ out:
         return ret;
 }
 
+static int __record_new_ref(int num, u64 dir, int index,
+                            struct fs_path *name,
+                            void *ctx)
+{
+        struct send_ctx *sctx = ctx;
+        return record_ref(sctx->send_root, num, dir, index, name,
+                          ctx, &sctx->new_refs);
+}
+
+
 static int __record_deleted_ref(int num, u64 dir, int index,
                                 struct fs_path *name,
                                 void *ctx)
 {
-        int ret = 0;
         struct send_ctx *sctx = ctx;
-        struct fs_path *p;
-        u64 gen;
-
-        p = fs_path_alloc();
-        if (!p)
-                return -ENOMEM;
-
-        ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL, NULL,
-                        NULL, NULL);
-        if (ret < 0)
-                goto out;
-
-        ret = get_cur_path(sctx, dir, gen, p);
-        if (ret < 0)
-                goto out;
-        ret = fs_path_add_path(p, name);
-        if (ret < 0)
-                goto out;
-
-        ret = record_ref(&sctx->deleted_refs, dir, gen, p);
-
-out:
-        if (ret)
-                fs_path_free(p);
-        return ret;
+        return record_ref(sctx->parent_root, num, dir, index, name,
+                          ctx, &sctx->deleted_refs);
 }
 
 static int record_new_ref(struct send_ctx *sctx)
@@ -3619,21 +3842,31 @@ static int process_all_refs(struct send_ctx *sctx,
                 root = sctx->parent_root;
                 cb = __record_deleted_ref;
         } else {
-                BUG();
+                btrfs_err(sctx->send_root->fs_info,
+                                "Wrong command %d in process_all_refs", cmd);
+                ret = -EINVAL;
+                goto out;
         }
 
         key.objectid = sctx->cmp_key->objectid;
         key.type = BTRFS_INODE_REF_KEY;
         key.offset = 0;
-        while (1) {
-                ret = btrfs_search_slot_for_read(root, &key, path, 1, 0);
-                if (ret < 0)
-                        goto out;
-                if (ret)
-                        break;
+        ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+        if (ret < 0)
+                goto out;
 
+        while (1) {
                 eb = path->nodes[0];
                 slot = path->slots[0];
+                if (slot >= btrfs_header_nritems(eb)) {
+                        ret = btrfs_next_leaf(root, path);
+                        if (ret < 0)
+                                goto out;
+                        else if (ret > 0)
+                                break;
+                        continue;
+                }
+
                 btrfs_item_key_to_cpu(eb, &found_key, slot);
 
                 if (found_key.objectid != key.objectid ||
@@ -3642,11 +3875,10 @@ static int process_all_refs(struct send_ctx *sctx,
                         break;
 
                 ret = iterate_inode_ref(root, path, &found_key, 0, cb, sctx);
-                btrfs_release_path(path);
                 if (ret < 0)
                         goto out;
 
-                key.offset = found_key.offset + 1;
+                path->slots[0]++;
         }
         btrfs_release_path(path);
 
@@ -3927,19 +4159,25 @@ static int process_all_new_xattrs(struct send_ctx *sctx)
         key.objectid = sctx->cmp_key->objectid;
         key.type = BTRFS_XATTR_ITEM_KEY;
         key.offset = 0;
-        while (1) {
-                ret = btrfs_search_slot_for_read(root, &key, path, 1, 0);
-                if (ret < 0)
-                        goto out;
-                if (ret) {
-                        ret = 0;
-                        goto out;
-                }
+        ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+        if (ret < 0)
+                goto out;
 
+        while (1) {
                 eb = path->nodes[0];
                 slot = path->slots[0];
-                btrfs_item_key_to_cpu(eb, &found_key, slot);
+                if (slot >= btrfs_header_nritems(eb)) {
+                        ret = btrfs_next_leaf(root, path);
+                        if (ret < 0) {
+                                goto out;
+                        } else if (ret > 0) {
+                                ret = 0;
+                                break;
+                        }
+                        continue;
+                }
 
+                btrfs_item_key_to_cpu(eb, &found_key, slot);
                 if (found_key.objectid != key.objectid ||
                     found_key.type != key.type) {
                         ret = 0;
@@ -3951,8 +4189,7 @@ static int process_all_new_xattrs(struct send_ctx *sctx)
                 if (ret < 0)
                         goto out;
 
-                btrfs_release_path(path);
-                key.offset = found_key.offset + 1;
+                path->slots[0]++;
         }
 
 out:
@@ -3991,6 +4228,13 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
                 goto out;
 
         last_index = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+
+        /* initial readahead */
+        memset(&sctx->ra, 0, sizeof(struct file_ra_state));
+        file_ra_state_init(&sctx->ra, inode->i_mapping);
+        btrfs_force_ra(inode->i_mapping, &sctx->ra, NULL, index,
+                       last_index - index + 1);
+
         while (index <= last_index) {
                 unsigned cur_len = min_t(unsigned, len,
                                          PAGE_CACHE_SIZE - pg_offset);
@@ -4763,18 +5007,19 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
                 ret = apply_children_dir_moves(sctx);
                 if (ret)
                         goto out;
+                /*
+                 * Need to send that every time, no matter if it actually
+                 * changed between the two trees as we have done changes to
+                 * the inode before. If our inode is a directory and it's
+                 * waiting to be moved/renamed, we will send its utimes when
+                 * it's moved/renamed, therefore we don't need to do it here.
+                 */
+                sctx->send_progress = sctx->cur_ino + 1;
+                ret = send_utimes(sctx, sctx->cur_ino, sctx->cur_inode_gen);
+                if (ret < 0)
+                        goto out;
         }
 
-        /*
-         * Need to send that every time, no matter if it actually
-         * changed between the two trees as we have done changes to
-         * the inode before.
-         */
-        sctx->send_progress = sctx->cur_ino + 1;
-        ret = send_utimes(sctx, sctx->cur_ino, sctx->cur_inode_gen);
-        if (ret < 0)
-                goto out;
-
 out:
         return ret;
 }
@@ -4840,6 +5085,8 @@ static int changed_inode(struct send_ctx *sctx,
                                 sctx->left_path->nodes[0], left_ii);
                 sctx->cur_inode_mode = btrfs_inode_mode(
                                 sctx->left_path->nodes[0], left_ii);
+                sctx->cur_inode_rdev = btrfs_inode_rdev(
+                                sctx->left_path->nodes[0], left_ii);
                 if (sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID)
                         ret = send_create_inode_if_needed(sctx);
         } else if (result == BTRFS_COMPARE_TREE_DELETED) {
@@ -4884,6 +5131,8 @@ static int changed_inode(struct send_ctx *sctx,
                                         sctx->left_path->nodes[0], left_ii);
                         sctx->cur_inode_mode = btrfs_inode_mode(
                                         sctx->left_path->nodes[0], left_ii);
+                        sctx->cur_inode_rdev = btrfs_inode_rdev(
+                                        sctx->left_path->nodes[0], left_ii);
                         ret = send_create_inode_if_needed(sctx);
                         if (ret < 0)
                                 goto out;
@@ -5118,6 +5367,7 @@ out:
 static int full_send_tree(struct send_ctx *sctx)
 {
         int ret;
+        struct btrfs_trans_handle *trans = NULL;
         struct btrfs_root *send_root = sctx->send_root;
         struct btrfs_key key;
         struct btrfs_key found_key;
@@ -5139,6 +5389,19 @@ static int full_send_tree(struct send_ctx *sctx)
         key.type = BTRFS_INODE_ITEM_KEY;
         key.offset = 0;
 
+join_trans:
+        /*
+         * We need to make sure the transaction does not get committed
+         * while we do anything on commit roots. Join a transaction to prevent
+         * this.
+         */
+        trans = btrfs_join_transaction(send_root);
+        if (IS_ERR(trans)) {
+                ret = PTR_ERR(trans);
+                trans = NULL;
+                goto out;
+        }
+
         /*
          * Make sure the tree has not changed after re-joining. We detect this
          * by comparing start_ctransid and ctransid. They should always match.
@@ -5162,6 +5425,19 @@ static int full_send_tree(struct send_ctx *sctx)
                 goto out_finish;
 
         while (1) {
+                /*
+                 * When someone want to commit while we iterate, end the
+                 * joined transaction and rejoin.
+                 */
+                if (btrfs_should_end_transaction(trans, send_root)) {
+                        ret = btrfs_end_transaction(trans, send_root);
+                        trans = NULL;
+                        if (ret < 0)
+                                goto out;
+                        btrfs_release_path(path);
+                        goto join_trans;
+                }
+
                 eb = path->nodes[0];
                 slot = path->slots[0];
                 btrfs_item_key_to_cpu(eb, &found_key, slot);
@@ -5189,6 +5465,12 @@ out_finish:
 
 out:
         btrfs_free_path(path);
+        if (trans) {
+                if (!ret)
+                        ret = btrfs_end_transaction(trans, send_root);
+                else
+                        btrfs_end_transaction(trans, send_root);
+        }
         return ret;
 }
 
@@ -5340,6 +5622,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 
         sctx->pending_dir_moves = RB_ROOT;
         sctx->waiting_dir_moves = RB_ROOT;
+        sctx->orphan_dirs = RB_ROOT;
 
         sctx->clone_roots = vzalloc(sizeof(struct clone_root) *
                         (arg->clone_sources_count + 1));
@@ -5477,6 +5760,16 @@ out:
                 kfree(dm);
         }
 
+        WARN_ON(sctx && !ret && !RB_EMPTY_ROOT(&sctx->orphan_dirs));
+        while (sctx && !RB_EMPTY_ROOT(&sctx->orphan_dirs)) {
+                struct rb_node *n;
+                struct orphan_dir_info *odi;
+
+                n = rb_first(&sctx->orphan_dirs);
+                odi = rb_entry(n, struct orphan_dir_info, node);
+                free_orphan_dir_info(sctx, odi);
+        }
+
         if (sort_clone_roots) {
                 for (i = 0; i < sctx->clone_roots_cnt; i++)
                         btrfs_root_dec_send_in_progress(
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d04db817be5c..9dbf42395153 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1305,13 +1305,6 @@ error_fs_info:
         return ERR_PTR(error);
 }
 
-static void btrfs_set_max_workers(struct btrfs_workers *workers, int new_limit)
-{
-        spin_lock_irq(&workers->lock);
-        workers->max_workers = new_limit;
-        spin_unlock_irq(&workers->lock);
-}
-
 static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
                                      int new_pool_size, int old_pool_size)
 {
@@ -1323,21 +1316,20 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
         btrfs_info(fs_info, "resize thread pool %d -> %d",
                old_pool_size, new_pool_size);
 
-        btrfs_set_max_workers(&fs_info->generic_worker, new_pool_size);
-        btrfs_set_max_workers(&fs_info->workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->delalloc_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->submit_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->caching_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->fixup_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->endio_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->endio_meta_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->endio_meta_write_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->endio_write_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->endio_freespace_worker, new_pool_size);
-        btrfs_set_max_workers(&fs_info->delayed_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->readahead_workers, new_pool_size);
-        btrfs_set_max_workers(&fs_info->scrub_wr_completion_workers,
-                              new_pool_size);
+        btrfs_workqueue_set_max(fs_info->workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->endio_meta_write_workers,
+                                new_pool_size);
+        btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->readahead_workers, new_pool_size);
+        btrfs_workqueue_set_max(fs_info->scrub_wr_completion_workers,
+                                new_pool_size);
 }
 
 static inline void btrfs_remount_prepare(struct btrfs_fs_info *fs_info)
@@ -1388,6 +1380,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
         unsigned int old_metadata_ratio = fs_info->metadata_ratio;
         int ret;
 
+        sync_filesystem(sb);
         btrfs_remount_prepare(fs_info);
 
         ret = btrfs_parse_options(root, data);
@@ -1479,6 +1472,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
                 sb->s_flags &= ~MS_RDONLY;
         }
 out:
+        wake_up_process(fs_info->transaction_kthread);
         btrfs_remount_cleanup(fs_info, old_opts);
         return 0;
 
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 865f4cf9a769..c5eb2143dc66 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -24,6 +24,7 @@
 #include <linux/kobject.h>
 #include <linux/bug.h>
 #include <linux/genhd.h>
+#include <linux/debugfs.h>
 
 #include "ctree.h"
 #include "disk-io.h"
@@ -599,6 +600,12 @@ static int add_device_membership(struct btrfs_fs_info *fs_info)
 /* /sys/fs/btrfs/ entry */
 static struct kset *btrfs_kset;
 
+/* /sys/kernel/debug/btrfs */
+static struct dentry *btrfs_debugfs_root_dentry;
+
+/* Debugging tunables and exported data */
+u64 btrfs_debugfs_test;
+
 int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info)
 {
         int error;
@@ -642,27 +649,41 @@ failure:
         return error;
 }
 
+static int btrfs_init_debugfs(void)
+{
+#ifdef CONFIG_DEBUG_FS
+        btrfs_debugfs_root_dentry = debugfs_create_dir("btrfs", NULL);
+        if (!btrfs_debugfs_root_dentry)
+                return -ENOMEM;
+
+        debugfs_create_u64("test", S_IRUGO | S_IWUGO, btrfs_debugfs_root_dentry,
+                        &btrfs_debugfs_test);
+#endif
+        return 0;
+}
+
 int btrfs_init_sysfs(void)
 {
         int ret;
+
         btrfs_kset = kset_create_and_add("btrfs", NULL, fs_kobj);
         if (!btrfs_kset)
                 return -ENOMEM;
 
-        init_feature_attrs();
+        ret = btrfs_init_debugfs();
+        if (ret)
+                return ret;
 
+        init_feature_attrs();
         ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
-        if (ret) {
-                kset_unregister(btrfs_kset);
-                return ret;
-        }
 
-        return 0;
+        return ret;
 }
 
 void btrfs_exit_sysfs(void)
 {
         sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
         kset_unregister(btrfs_kset);
+        debugfs_remove_recursive(btrfs_debugfs_root_dentry);
 }
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index f3cea3710d44..9ab576318a84 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -1,6 +1,11 @@
 #ifndef _BTRFS_SYSFS_H_
 #define _BTRFS_SYSFS_H_
 
+/*
+ * Data exported through sysfs
+ */
+extern u64 btrfs_debugfs_test;
+
 enum btrfs_feature_set {
         FEAT_COMPAT,
         FEAT_COMPAT_RO,
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 34cd83184c4a..a04707f740d6 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -683,7 +683,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
         int lock = (trans->type != TRANS_JOIN_NOLOCK);
         int err = 0;
 
-        if (--trans->use_count) {
+        if (trans->use_count > 1) {
+                trans->use_count--;
                 trans->block_rsv = trans->orig_rsv;
                 return 0;
         }
@@ -731,17 +732,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
         }
 
         if (lock && ACCESS_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
-                if (throttle) {
-                        /*
-                         * We may race with somebody else here so end up having
-                         * to call end_transaction on ourselves again, so inc
-                         * our use_count.
-                         */
-                        trans->use_count++;
+                if (throttle)
                         return btrfs_commit_transaction(trans, root);
-                } else {
+                else
                         wake_up_process(info->transaction_kthread);
-                }
         }
 
         if (trans->type & __TRANS_FREEZABLE)
@@ -1578,10 +1572,9 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
 
         trace_btrfs_transaction_commit(root);
 
-        btrfs_scrub_continue(root);
-
         if (current->journal_info == trans)
                 current->journal_info = NULL;
+        btrfs_scrub_cancel(root->fs_info);
 
         kmem_cache_free(btrfs_trans_handle_cachep, trans);
 }
@@ -1621,7 +1614,7 @@ static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans,
 static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
         if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
-                return btrfs_start_delalloc_roots(fs_info, 1);
+                return btrfs_start_delalloc_roots(fs_info, 1, -1);
         return 0;
 }
 
@@ -1754,7 +1747,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         /* ->aborted might be set after the previous check, so check it */
         if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
                 ret = cur_trans->aborted;
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
         /*
          * the reloc mutex makes sure that we stop
@@ -1771,7 +1764,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         ret = create_pending_snapshots(trans, root->fs_info);
         if (ret) {
                 mutex_unlock(&root->fs_info->reloc_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         /*
@@ -1787,13 +1780,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         ret = btrfs_run_delayed_items(trans, root);
         if (ret) {
                 mutex_unlock(&root->fs_info->reloc_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
         if (ret) {
                 mutex_unlock(&root->fs_info->reloc_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         /*
@@ -1823,7 +1816,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         if (ret) {
                 mutex_unlock(&root->fs_info->tree_log_mutex);
                 mutex_unlock(&root->fs_info->reloc_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         /*
@@ -1844,7 +1837,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         if (ret) {
                 mutex_unlock(&root->fs_info->tree_log_mutex);
                 mutex_unlock(&root->fs_info->reloc_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         /*
@@ -1855,7 +1848,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                 ret = cur_trans->aborted;
                 mutex_unlock(&root->fs_info->tree_log_mutex);
                 mutex_unlock(&root->fs_info->reloc_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         btrfs_prepare_extent_commit(trans, root);
@@ -1891,13 +1884,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                 btrfs_error(root->fs_info, ret,
                             "Error while writing out transaction");
                 mutex_unlock(&root->fs_info->tree_log_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         ret = write_ctree_super(trans, root, 0);
         if (ret) {
                 mutex_unlock(&root->fs_info->tree_log_mutex);
-                goto cleanup_transaction;
+                goto scrub_continue;
         }
 
         /*
@@ -1940,6 +1933,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
         return ret;
 
+scrub_continue:
+        btrfs_scrub_continue(root);
 cleanup_transaction:
         btrfs_trans_release_metadata(trans, root);
         trans->block_rsv = NULL;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 39d83da03e03..e2f45fc02610 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -136,13 +136,20 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
  * syncing the tree wait for us to finish
  */
 static int start_log_trans(struct btrfs_trans_handle *trans,
-                           struct btrfs_root *root)
+                           struct btrfs_root *root,
+                           struct btrfs_log_ctx *ctx)
 {
+        int index;
         int ret;
-        int err = 0;
 
         mutex_lock(&root->log_mutex);
         if (root->log_root) {
+                if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
+                    trans->transid) {
+                        ret = -EAGAIN;
+                        goto out;
+                }
+
                 if (!root->log_start_pid) {
                         root->log_start_pid = current->pid;
                         root->log_multiple_pids = false;
@@ -152,27 +159,40 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 
                 atomic_inc(&root->log_batch);
                 atomic_inc(&root->log_writers);
+                if (ctx) {
+                        index = root->log_transid % 2;
+                        list_add_tail(&ctx->list, &root->log_ctxs[index]);
+                        ctx->log_transid = root->log_transid;
+                }
                 mutex_unlock(&root->log_mutex);
                 return 0;
         }
-        root->log_multiple_pids = false;
-        root->log_start_pid = current->pid;
+
+        ret = 0;
         mutex_lock(&root->fs_info->tree_log_mutex);
-        if (!root->fs_info->log_root_tree) {
+        if (!root->fs_info->log_root_tree)
                 ret = btrfs_init_log_root_tree(trans, root->fs_info);
-                if (ret)
-                        err = ret;
-        }
-        if (err == 0 && !root->log_root) {
+        mutex_unlock(&root->fs_info->tree_log_mutex);
+        if (ret)
+                goto out;
+
+        if (!root->log_root) {
                 ret = btrfs_add_log_tree(trans, root);
                 if (ret)
-                        err = ret;
+                        goto out;
         }
-        mutex_unlock(&root->fs_info->tree_log_mutex);
+        root->log_multiple_pids = false;
+        root->log_start_pid = current->pid;
         atomic_inc(&root->log_batch);
         atomic_inc(&root->log_writers);
+        if (ctx) {
+                index = root->log_transid % 2;
+                list_add_tail(&ctx->list, &root->log_ctxs[index]);
+                ctx->log_transid = root->log_transid;
+        }
+out:
         mutex_unlock(&root->log_mutex);
-        return err;
+        return ret;
 }
 
 /*
@@ -2359,8 +2379,8 @@ static int update_log_root(struct btrfs_trans_handle *trans,
         return ret;
 }
 
-static int wait_log_commit(struct btrfs_trans_handle *trans,
-                           struct btrfs_root *root, unsigned long transid)
+static void wait_log_commit(struct btrfs_trans_handle *trans,
+                            struct btrfs_root *root, int transid)
 {
         DEFINE_WAIT(wait);
         int index = transid % 2;
@@ -2375,36 +2395,63 @@ static int wait_log_commit(struct btrfs_trans_handle *trans,
                                 &wait, TASK_UNINTERRUPTIBLE);
                 mutex_unlock(&root->log_mutex);
 
-                if (root->fs_info->last_trans_log_full_commit !=
-                    trans->transid && root->log_transid < transid + 2 &&
+                if (root->log_transid_committed < transid &&
                     atomic_read(&root->log_commit[index]))
                         schedule();
 
                 finish_wait(&root->log_commit_wait[index], &wait);
                 mutex_lock(&root->log_mutex);
-        } while (root->fs_info->last_trans_log_full_commit !=
-                 trans->transid && root->log_transid < transid + 2 &&
+        } while (root->log_transid_committed < transid &&
                  atomic_read(&root->log_commit[index]));
-        return 0;
 }
 
 static void wait_for_writer(struct btrfs_trans_handle *trans,
                             struct btrfs_root *root)
 {
         DEFINE_WAIT(wait);
-        while (root->fs_info->last_trans_log_full_commit !=
-               trans->transid && atomic_read(&root->log_writers)) {
+
+        while (atomic_read(&root->log_writers)) {
                 prepare_to_wait(&root->log_writer_wait,
                                 &wait, TASK_UNINTERRUPTIBLE);
                 mutex_unlock(&root->log_mutex);
-                if (root->fs_info->last_trans_log_full_commit !=
-                    trans->transid && atomic_read(&root->log_writers))
+                if (atomic_read(&root->log_writers))
                         schedule();
                 mutex_lock(&root->log_mutex);
                 finish_wait(&root->log_writer_wait, &wait);
         }
 }
 
+static inline void btrfs_remove_log_ctx(struct btrfs_root *root,
+                                        struct btrfs_log_ctx *ctx)
+{
+        if (!ctx)
+                return;
+
+        mutex_lock(&root->log_mutex);
+        list_del_init(&ctx->list);
+        mutex_unlock(&root->log_mutex);
+}
+
+/* 
+ * Invoked in log mutex context, or be sure there is no other task which
+ * can access the list.
+ */
+static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root,
+                                             int index, int error)
+{
+        struct btrfs_log_ctx *ctx;
+
+        if (!error) {
+                INIT_LIST_HEAD(&root->log_ctxs[index]);
+                return;
+        }
+
+        list_for_each_entry(ctx, &root->log_ctxs[index], list)
+                ctx->log_ret = error;
+
+        INIT_LIST_HEAD(&root->log_ctxs[index]);
+}
+
 /*
  * btrfs_sync_log does sends a given tree log down to the disk and
  * updates the super blocks to record it.  When this call is done,
@@ -2418,7 +2465,7 @@ static void wait_for_writer(struct btrfs_trans_handle *trans,
  * that has happened.
  */
 int btrfs_sync_log(struct btrfs_trans_handle *trans,
-                   struct btrfs_root *root)
+                   struct btrfs_root *root, struct btrfs_log_ctx *ctx)
 {
         int index1;
         int index2;
@@ -2426,22 +2473,30 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
         int ret;
         struct btrfs_root *log = root->log_root;
         struct btrfs_root *log_root_tree = root->fs_info->log_root_tree;
-        unsigned long log_transid = 0;
+        int log_transid = 0;
+        struct btrfs_log_ctx root_log_ctx;
         struct blk_plug plug;
 
         mutex_lock(&root->log_mutex);
-        log_transid = root->log_transid;
-        index1 = root->log_transid % 2;
+        log_transid = ctx->log_transid;
+        if (root->log_transid_committed >= log_transid) {
+                mutex_unlock(&root->log_mutex);
+                return ctx->log_ret;
+        }
+
+        index1 = log_transid % 2;
         if (atomic_read(&root->log_commit[index1])) {
-                wait_log_commit(trans, root, root->log_transid);
+                wait_log_commit(trans, root, log_transid);
                 mutex_unlock(&root->log_mutex);
-                return 0;
+                return ctx->log_ret;
         }
+        ASSERT(log_transid == root->log_transid);
         atomic_set(&root->log_commit[index1], 1);
 
         /* wait for previous tree log sync to complete */
         if (atomic_read(&root->log_commit[(index1 + 1) % 2]))
-                wait_log_commit(trans, root, root->log_transid - 1);
+                wait_log_commit(trans, root, log_transid - 1);
+
         while (1) {
                 int batch = atomic_read(&root->log_batch);
                 /* when we're on an ssd, just kick the log commit out */
@@ -2456,7 +2511,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
         }
 
         /* bail out if we need to do a full commit */
-        if (root->fs_info->last_trans_log_full_commit == trans->transid) {
+        if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
+            trans->transid) {
                 ret = -EAGAIN;
                 btrfs_free_logged_extents(log, log_transid);
                 mutex_unlock(&root->log_mutex);
@@ -2477,6 +2533,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
                 blk_finish_plug(&plug);
                 btrfs_abort_transaction(trans, root, ret);
                 btrfs_free_logged_extents(log, log_transid);
+                ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
+                                                                trans->transid;
                 mutex_unlock(&root->log_mutex);
                 goto out;
         }
@@ -2486,7 +2544,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
         root->log_transid++;
         log->log_transid = root->log_transid;
         root->log_start_pid = 0;
-        smp_mb();
         /*
          * IO has been started, blocks of the log tree have WRITTEN flag set
          * in their headers. new modifications of the log will be written to
@@ -2494,9 +2551,16 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
          */
         mutex_unlock(&root->log_mutex);
 
+        btrfs_init_log_ctx(&root_log_ctx);
+
         mutex_lock(&log_root_tree->log_mutex);
         atomic_inc(&log_root_tree->log_batch);
         atomic_inc(&log_root_tree->log_writers);
+
+        index2 = log_root_tree->log_transid % 2;
+        list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
+        root_log_ctx.log_transid = log_root_tree->log_transid;
+
         mutex_unlock(&log_root_tree->log_mutex);
 
         ret = update_log_root(trans, log);
@@ -2509,13 +2573,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
         }
 
         if (ret) {
+                if (!list_empty(&root_log_ctx.list))
+                        list_del_init(&root_log_ctx.list);
+
                 blk_finish_plug(&plug);
+                ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
+                                                                trans->transid;
                 if (ret != -ENOSPC) {
                         btrfs_abort_transaction(trans, root, ret);
                         mutex_unlock(&log_root_tree->log_mutex);
                         goto out;
                 }
-                root->fs_info->last_trans_log_full_commit = trans->transid;
                 btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
                 btrfs_free_logged_extents(log, log_transid);
                 mutex_unlock(&log_root_tree->log_mutex);
@@ -2523,22 +2591,29 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
                 goto out;
         }
 
-        index2 = log_root_tree->log_transid % 2;
+        if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
+                mutex_unlock(&log_root_tree->log_mutex);
+                ret = root_log_ctx.log_ret;
+                goto out;
+        }
+
+        index2 = root_log_ctx.log_transid % 2;
         if (atomic_read(&log_root_tree->log_commit[index2])) {
                 blk_finish_plug(&plug);
                 btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
                 wait_log_commit(trans, log_root_tree,
-                                log_root_tree->log_transid);
+                                root_log_ctx.log_transid);
                 btrfs_free_logged_extents(log, log_transid);
                 mutex_unlock(&log_root_tree->log_mutex);
-                ret = 0;
+                ret = root_log_ctx.log_ret;
                 goto out;
         }
+        ASSERT(root_log_ctx.log_transid == log_root_tree->log_transid);
         atomic_set(&log_root_tree->log_commit[index2], 1);
 
         if (atomic_read(&log_root_tree->log_commit[(index2 + 1) % 2])) {
                 wait_log_commit(trans, log_root_tree,
-                                log_root_tree->log_transid - 1);
+                                root_log_ctx.log_transid - 1);
         }
 
         wait_for_writer(trans, log_root_tree);
@@ -2547,7 +2622,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
          * now that we've moved on to the tree of log tree roots,
          * check the full commit flag again
          */
-        if (root->fs_info->last_trans_log_full_commit == trans->transid) {
+        if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
+            trans->transid) {
                 blk_finish_plug(&plug);
                 btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
                 btrfs_free_logged_extents(log, log_transid);
@@ -2561,6 +2637,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
                                          EXTENT_DIRTY | EXTENT_NEW);
         blk_finish_plug(&plug);
         if (ret) {
+                ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
+                                                                trans->transid;
                 btrfs_abort_transaction(trans, root, ret);
                 btrfs_free_logged_extents(log, log_transid);
                 mutex_unlock(&log_root_tree->log_mutex);
@@ -2578,8 +2656,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
                                 btrfs_header_level(log_root_tree->node));
 
         log_root_tree->log_transid++;
-        smp_mb();
-
         mutex_unlock(&log_root_tree->log_mutex);
 
         /*
@@ -2591,6 +2667,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
          */
         ret = write_ctree_super(trans, root->fs_info->tree_root, 1);
         if (ret) {
+                ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
+                                                                trans->transid;
                 btrfs_abort_transaction(trans, root, ret);
                 goto out_wake_log_root;
         }
@@ -2601,13 +2679,28 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
         mutex_unlock(&root->log_mutex);
 
 out_wake_log_root:
+        /*
+         * We needn't get log_mutex here because we are sure all
+         * the other tasks are blocked.
+         */
+        btrfs_remove_all_log_ctxs(log_root_tree, index2, ret);
+
+        mutex_lock(&log_root_tree->log_mutex);
+        log_root_tree->log_transid_committed++;
         atomic_set(&log_root_tree->log_commit[index2], 0);
-        smp_mb();
+        mutex_unlock(&log_root_tree->log_mutex);
+
         if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
                 wake_up(&log_root_tree->log_commit_wait[index2]);
 out:
+        /* See above. */
+        btrfs_remove_all_log_ctxs(root, index1, ret);
+
+        mutex_lock(&root->log_mutex);
+        root->log_transid_committed++;
         atomic_set(&root->log_commit[index1], 0);
-        smp_mb();
+        mutex_unlock(&root->log_mutex);
+
         if (waitqueue_active(&root->log_commit_wait[index1]))
                 wake_up(&root->log_commit_wait[index1]);
         return ret;
@@ -3479,7 +3572,8 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
 
 static int log_one_extent(struct btrfs_trans_handle *trans,
                           struct inode *inode, struct btrfs_root *root,
-                          struct extent_map *em, struct btrfs_path *path)
+                          struct extent_map *em, struct btrfs_path *path,
+                          struct list_head *logged_list)
 {
         struct btrfs_root *log = root->log_root;
         struct btrfs_file_extent_item *fi;
@@ -3495,7 +3589,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
         u64 extent_offset = em->start - em->orig_start;
         u64 block_len;
         int ret;
-        int index = log->log_transid % 2;
         bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
         int extent_inserted = 0;
 
@@ -3579,17 +3672,12 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
          * First check and see if our csums are on our outstanding ordered
          * extents.
          */
-again:
-        spin_lock_irq(&log->log_extents_lock[index]);
-        list_for_each_entry(ordered, &log->logged_list[index], log_list) {
+        list_for_each_entry(ordered, logged_list, log_list) {
                 struct btrfs_ordered_sum *sum;
 
                 if (!mod_len)
                         break;
 
-                if (ordered->inode != inode)
-                        continue;
-
                 if (ordered->file_offset + ordered->len <= mod_start ||
                     mod_start + mod_len <= ordered->file_offset)
                         continue;
@@ -3632,12 +3720,6 @@ again:
                 if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM,
                                      &ordered->flags))
                         continue;
-                atomic_inc(&ordered->refs);
-                spin_unlock_irq(&log->log_extents_lock[index]);
-                /*
-                 * we've dropped the lock, we must either break or
-                 * start over after this.
-                 */
 
                 if (ordered->csum_bytes_left) {
                         btrfs_start_ordered_extent(inode, ordered, 0);
@@ -3647,16 +3729,11 @@ again:
 
                 list_for_each_entry(sum, &ordered->list, list) {
                         ret = btrfs_csum_file_blocks(trans, log, sum);
-                        if (ret) {
-                                btrfs_put_ordered_extent(ordered);
+                        if (ret)
                                 goto unlocked;
-                        }
                 }
-                btrfs_put_ordered_extent(ordered);
-                goto again;
 
         }
-        spin_unlock_irq(&log->log_extents_lock[index]);
 unlocked:
 
         if (!mod_len || ret)
@@ -3694,7 +3771,8 @@ unlocked:
 static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct inode *inode,
-                                     struct btrfs_path *path)
+                                     struct btrfs_path *path,
+                                     struct list_head *logged_list)
 {
         struct extent_map *em, *n;
         struct list_head extents;
@@ -3752,7 +3830,7 @@ process:
 
                 write_unlock(&tree->lock);
 
-                ret = log_one_extent(trans, inode, root, em, path);
+                ret = log_one_extent(trans, inode, root, em, path, logged_list);
                 write_lock(&tree->lock);
                 clear_em_logging(tree, em);
                 free_extent_map(em);
@@ -3788,6 +3866,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
         struct btrfs_key max_key;
         struct btrfs_root *log = root->log_root;
         struct extent_buffer *src = NULL;
+        LIST_HEAD(logged_list);
         u64 last_extent = 0;
         int err = 0;
         int ret;
@@ -3836,7 +3915,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
         mutex_lock(&BTRFS_I(inode)->log_mutex);
 
-        btrfs_get_logged_extents(log, inode);
+        btrfs_get_logged_extents(inode, &logged_list);
 
         /*
          * a brute force approach to making sure we get the most uptodate
@@ -3962,7 +4041,8 @@ log_extents:
         btrfs_release_path(path);
         btrfs_release_path(dst_path);
         if (fast_search) {
-                ret = btrfs_log_changed_extents(trans, root, inode, dst_path);
+                ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
+                                                &logged_list);
                 if (ret) {
                         err = ret;
                         goto out_unlock;
@@ -3987,8 +4067,10 @@ log_extents:
         BTRFS_I(inode)->logged_trans = trans->transid;
         BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans;
 out_unlock:
-        if (err)
-                btrfs_free_logged_extents(log, log->log_transid);
+        if (unlikely(err))
+                btrfs_put_logged_extents(&logged_list);
+        else
+                btrfs_submit_logged_extents(&logged_list, log);
         mutex_unlock(&BTRFS_I(inode)->log_mutex);
 
         btrfs_free_path(path);
@@ -4079,7 +4161,8 @@ out:
  */
 static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
                                   struct btrfs_root *root, struct inode *inode,
-                                  struct dentry *parent, int exists_only)
+                                  struct dentry *parent, int exists_only,
+                                  struct btrfs_log_ctx *ctx)
 {
         int inode_only = exists_only ? LOG_INODE_EXISTS : LOG_INODE_ALL;
         struct super_block *sb;
@@ -4116,9 +4199,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
                 goto end_no_trans;
         }
 
-        ret = start_log_trans(trans, root);
+        ret = start_log_trans(trans, root, ctx);
         if (ret)
-                goto end_trans;
+                goto end_no_trans;
 
         ret = btrfs_log_inode(trans, root, inode, inode_only);
         if (ret)
@@ -4166,6 +4249,9 @@ end_trans:
                 root->fs_info->last_trans_log_full_commit = trans->transid;
                 ret = 1;
         }
+
+        if (ret)
+                btrfs_remove_log_ctx(root, ctx);
         btrfs_end_log_trans(root);
 end_no_trans:
         return ret;
@@ -4178,12 +4264,14 @@ end_no_trans:
  * data on disk.
  */
 int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
-                          struct btrfs_root *root, struct dentry *dentry)
+                          struct btrfs_root *root, struct dentry *dentry,
+                          struct btrfs_log_ctx *ctx)
 {
         struct dentry *parent = dget_parent(dentry);
         int ret;
 
-        ret = btrfs_log_inode_parent(trans, root, dentry->d_inode, parent, 0);
+        ret = btrfs_log_inode_parent(trans, root, dentry->d_inode, parent,
+                                     0, ctx);
         dput(parent);
 
         return ret;
@@ -4420,6 +4508,6 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
                     root->fs_info->last_trans_committed))
                 return 0;
 
-        return btrfs_log_inode_parent(trans, root, inode, parent, 1);
+        return btrfs_log_inode_parent(trans, root, inode, parent, 1, NULL);
 }
 
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 1d4ae0d15a70..91b145fce333 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -22,14 +22,28 @@
 /* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
 #define BTRFS_NO_LOG_SYNC 256
 
+struct btrfs_log_ctx {
+        int log_ret;
+        int log_transid;
+        struct list_head list;
+};
+
+static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx)
+{
+        ctx->log_ret = 0;
+        ctx->log_transid = 0;
+        INIT_LIST_HEAD(&ctx->list);
+}
+
 int btrfs_sync_log(struct btrfs_trans_handle *trans,
-                   struct btrfs_root *root);
+                   struct btrfs_root *root, struct btrfs_log_ctx *ctx);
 int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root);
 int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
                              struct btrfs_fs_info *fs_info);
 int btrfs_recover_log_trees(struct btrfs_root *tree_root);
 int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
-                          struct btrfs_root *root, struct dentry *dentry);
+                          struct btrfs_root *root, struct dentry *dentry,
+                          struct btrfs_log_ctx *ctx);
 int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root,
                                  const char *name, int name_len,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bab0b84d8f80..d241130a32fd 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -415,7 +415,8 @@ loop_lock:
                         device->running_pending = 1;
 
                         spin_unlock(&device->io_lock);
-                        btrfs_requeue_work(&device->work);
+                        btrfs_queue_work(fs_info->submit_workers,
+                                         &device->work);
                         goto done;
                 }
                 /* unplug every 64 requests just for good measure */
@@ -5263,6 +5264,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 static void btrfs_end_bio(struct bio *bio, int err)
 {
         struct btrfs_bio *bbio = bio->bi_private;
+        struct btrfs_device *dev = bbio->stripes[0].dev;
         int is_orig_bio = 0;
 
         if (err) {
@@ -5270,7 +5272,6 @@ static void btrfs_end_bio(struct bio *bio, int err)
                 if (err == -EIO || err == -EREMOTEIO) {
                         unsigned int stripe_index =
                                 btrfs_io_bio(bio)->stripe_index;
-                        struct btrfs_device *dev;
 
                         BUG_ON(stripe_index >= bbio->num_stripes);
                         dev = bbio->stripes[stripe_index].dev;
@@ -5292,6 +5293,8 @@ static void btrfs_end_bio(struct bio *bio, int err)
         if (bio == bbio->orig_bio)
                 is_orig_bio = 1;
 
+        btrfs_bio_counter_dec(bbio->fs_info);
+
         if (atomic_dec_and_test(&bbio->stripes_pending)) {
                 if (!is_orig_bio) {
                         bio_put(bio);
@@ -5328,13 +5331,6 @@ static void btrfs_end_bio(struct bio *bio, int err)
         }
 }
 
-struct async_sched {
-        struct bio *bio;
-        int rw;
-        struct btrfs_fs_info *info;
-        struct btrfs_work work;
-};
-
 /*
  * see run_scheduled_bios for a description of why bios are collected for
  * async submit.
@@ -5391,8 +5387,8 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root,
         spin_unlock(&device->io_lock);
 
         if (should_queue)
-                btrfs_queue_worker(&root->fs_info->submit_workers,
-                                   &device->work);
+                btrfs_queue_work(root->fs_info->submit_workers,
+                                 &device->work);
 }
 
 static int bio_size_ok(struct block_device *bdev, struct bio *bio,
@@ -5447,6 +5443,9 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
         }
 #endif
         bio->bi_bdev = dev->bdev;
+
+        btrfs_bio_counter_inc_noblocked(root->fs_info);
+
         if (async)
                 btrfs_schedule_bio(root, dev, rw, bio);
         else
@@ -5515,28 +5514,38 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
         length = bio->bi_iter.bi_size;
         map_length = length;
 
+        btrfs_bio_counter_inc_blocked(root->fs_info);
         ret = __btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
                               mirror_num, &raid_map);
-        if (ret) /* -ENOMEM */
+        if (ret) {
+                btrfs_bio_counter_dec(root->fs_info);
                 return ret;
+        }
 
         total_devs = bbio->num_stripes;
         bbio->orig_bio = first_bio;
         bbio->private = first_bio->bi_private;
         bbio->end_io = first_bio->bi_end_io;
+        bbio->fs_info = root->fs_info;
         atomic_set(&bbio->stripes_pending, bbio->num_stripes);
 
         if (raid_map) {
                 /* In this case, map_length has been set to the length of
                    a single stripe; not the whole write */
                 if (rw & WRITE) {
-                        return raid56_parity_write(root, bio, bbio,
-                                                   raid_map, map_length);
+                        ret = raid56_parity_write(root, bio, bbio,
+                                                  raid_map, map_length);
                 } else {
-                        return raid56_parity_recover(root, bio, bbio,
-                                                     raid_map, map_length,
-                                                     mirror_num);
+                        ret = raid56_parity_recover(root, bio, bbio,
+                                                    raid_map, map_length,
+                                                    mirror_num);
                 }
+                /*
+                 * FIXME, replace dosen't support raid56 yet, please fix
+                 * it in the future.
+                 */
+                btrfs_bio_counter_dec(root->fs_info);
+                return ret;
         }
 
         if (map_length < length) {
@@ -5578,6 +5587,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
                                   async_submit);
                 dev_nr++;
         }
+        btrfs_bio_counter_dec(root->fs_info);
         return 0;
 }
 
@@ -5666,7 +5676,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
         else
                 generate_random_uuid(dev->uuid);
 
-        dev->work.func = pending_bios_fn;
+        btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
 
         return dev;
 }
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 8b3cd142b373..80754f9dd3df 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -192,6 +192,7 @@ typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
 
 struct btrfs_bio {
         atomic_t stripes_pending;
+        struct btrfs_fs_info *fs_info;
         bio_end_io_t *end_io;
         struct bio *orig_bio;
         void *private;
diff --git a/fs/buffer.c b/fs/buffer.c
index 27265a8b43c1..8c53a2b15ecb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3088,7 +3088,7 @@ EXPORT_SYMBOL(submit_bh);
  * until the buffer gets unlocked).
  *
  * ll_rw_block sets b_end_io to simple completion handler that marks
- * the buffer up-to-date (if approriate), unlocks the buffer and wakes
+ * the buffer up-to-date (if appropriate), unlocks the buffer and wakes
  * any waiters. 
  *
  * All of the buffers must be for the same device, and must also be a
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ca65f39dc8dc..6494d9f673aa 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -391,12 +391,12 @@ try_again:
         path.dentry = dir;
         path_to_graveyard.mnt = cache->mnt;
         path_to_graveyard.dentry = cache->graveyard;
-        ret = security_path_rename(&path, rep, &path_to_graveyard, grave);
+        ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0);
         if (ret < 0) {
                 cachefiles_io_error(cache, "Rename security error %d", ret);
         } else {
                 ret = vfs_rename(dir->d_inode, rep,
-                                 cache->graveyard->d_inode, grave, NULL);
+                                 cache->graveyard->d_inode, grave, NULL, 0);
                 if (ret != 0 && ret != -ENOMEM)
                         cachefiles_io_error(cache,
                                             "Rename failed with error %d", ret);
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index ebaff368120d..4b1fb5ca65b8 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -265,24 +265,22 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
                                 goto nomem_monitor;
                 }
 
-                ret = add_to_page_cache(newpage, bmapping,
-                                        netpage->index, cachefiles_gfp);
+                ret = add_to_page_cache_lru(newpage, bmapping,
+                                            netpage->index, cachefiles_gfp);
                 if (ret == 0)
                         goto installed_new_backing_page;
                 if (ret != -EEXIST)
                         goto nomem_page;
         }
 
-        /* we've installed a new backing page, so now we need to add it
-         * to the LRU list and start it reading */
+        /* we've installed a new backing page, so now we need to start
+         * it reading */
 installed_new_backing_page:
         _debug("- new %p", newpage);
 
         backpage = newpage;
         newpage = NULL;
 
-        lru_cache_add_file(backpage);
-
 read_backing_page:
         ret = bmapping->a_ops->readpage(NULL, backpage);
         if (ret < 0)
@@ -510,24 +508,23 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
                                         goto nomem;
                         }
 
-                        ret = add_to_page_cache(newpage, bmapping,
-                                                netpage->index, cachefiles_gfp);
+                        ret = add_to_page_cache_lru(newpage, bmapping,
+                                                    netpage->index,
+                                                    cachefiles_gfp);
                         if (ret == 0)
                                 goto installed_new_backing_page;
                         if (ret != -EEXIST)
                                 goto nomem;
                 }
 
-                /* we've installed a new backing page, so now we need to add it
-                 * to the LRU list and start it reading */
+                /* we've installed a new backing page, so now we need
+                 * to start it reading */
         installed_new_backing_page:
                 _debug("- new %p", newpage);
 
                 backpage = newpage;
                 newpage = NULL;
 
-                lru_cache_add_file(backpage);
-
         reread_backing_page:
                 ret = bmapping->a_ops->readpage(NULL, backpage);
                 if (ret < 0)
@@ -538,8 +535,8 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
         monitor_backing_page:
                 _debug("- monitor add");
 
-                ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-                                        cachefiles_gfp);
+                ret = add_to_page_cache_lru(netpage, op->mapping,
+                                            netpage->index, cachefiles_gfp);
                 if (ret < 0) {
                         if (ret == -EEXIST) {
                                 page_cache_release(netpage);
@@ -549,8 +546,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
                         goto nomem;
                 }
 
-                lru_cache_add_file(netpage);
-
                 /* install a monitor */
                 page_cache_get(netpage);
                 monitor->netfs_page = netpage;
@@ -613,8 +608,8 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
         backing_page_already_uptodate:
                 _debug("- uptodate");
 
-                ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-                                        cachefiles_gfp);
+                ret = add_to_page_cache_lru(netpage, op->mapping,
+                                            netpage->index, cachefiles_gfp);
                 if (ret < 0) {
                         if (ret == -EEXIST) {
                                 page_cache_release(netpage);
@@ -631,8 +626,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 
                 fscache_mark_page_cached(op, netpage);
 
-                lru_cache_add_file(netpage);
-
                 /* the netpage is unlocked and marked up to date here */
                 fscache_end_io(op, netpage, 0);
                 page_cache_release(netpage);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 849f6132b327..2c70cbe35d39 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -286,7 +286,7 @@ cifs_destroy_inode(struct inode *inode)
 static void
 cifs_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         cifs_fscache_release_inode_cookie(inode);
 }
@@ -541,6 +541,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root)
 
 static int cifs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_NODIRATIME;
         return 0;
 }
@@ -1005,7 +1006,7 @@ cifs_init_once(void *inode)
         init_rwsem(&cifsi->lock_sem);
 }
 
-static int
+static int __init
 cifs_init_inodecache(void)
 {
         cifs_inode_cachep = kmem_cache_create("cifs_inode_cache",
diff --git a/fs/coda/coda_int.h b/fs/coda/coda_int.h
index b7143cf783ac..381c993b1427 100644
--- a/fs/coda/coda_int.h
+++ b/fs/coda/coda_int.h
@@ -10,7 +10,7 @@ extern int coda_hard;
 extern int coda_fake_statfs;
 
 void coda_destroy_inodecache(void);
-int coda_init_inodecache(void);
+int __init coda_init_inodecache(void);
 int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync);
 void coda_sysctl_init(void);
 void coda_sysctl_clean(void);
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 506de34a4ef3..d9c7751f10ac 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -73,7 +73,7 @@ static void init_once(void *foo)
         inode_init_once(&ei->vfs_inode);
 }
 
-int coda_init_inodecache(void)
+int __init coda_init_inodecache(void)
 {
         coda_inode_cachep = kmem_cache_create("coda_inode_cache",
                                 sizeof(struct coda_inode_info),
@@ -96,6 +96,7 @@ void coda_destroy_inodecache(void)
 
 static int coda_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_NOATIME;
         return 0;
 }
@@ -250,7 +251,7 @@ static void coda_put_super(struct super_block *sb)
 
 static void coda_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         coda_cache_clear_inode(inode);
 }
diff --git a/fs/compat.c b/fs/compat.c
index 6af20de2c1a3..ca926ad0430c 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -72,8 +72,8 @@ int compat_printk(const char *fmt, ...)
  * Not all architectures have sys_utime, so implement this in terms
  * of sys_utimes.
  */
-asmlinkage long compat_sys_utime(const char __user *filename,
-                                 struct compat_utimbuf __user *t)
+COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename,
+                       struct compat_utimbuf __user *, t)
 {
         struct timespec tv[2];
 
@@ -87,13 +87,13 @@ asmlinkage long compat_sys_utime(const char __user *filename,
         return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
 }
 
-asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, struct compat_timespec __user *t, int flags)
+COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags)
 {
         struct timespec tv[2];
 
         if  (t) {
-                if (get_compat_timespec(&tv[0], &t[0]) ||
-                    get_compat_timespec(&tv[1], &t[1]))
+                if (compat_get_timespec(&tv[0], &t[0]) ||
+                    compat_get_timespec(&tv[1], &t[1]))
                         return -EFAULT;
 
                 if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
@@ -102,7 +102,7 @@ asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filena
         return do_utimes(dfd, filename, t ? tv : NULL, flags);
 }
 
-asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct compat_timeval __user *t)
+COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t)
 {
         struct timespec tv[2];
 
@@ -121,7 +121,7 @@ asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filena
         return do_utimes(dfd, filename, t ? tv : NULL, 0);
 }
 
-asmlinkage long compat_sys_utimes(const char __user *filename, struct compat_timeval __user *t)
+COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t)
 {
         return compat_sys_futimesat(AT_FDCWD, filename, t);
 }
@@ -159,8 +159,8 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
         return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
 
-asmlinkage long compat_sys_newstat(const char __user * filename,
-                struct compat_stat __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
+                       struct compat_stat __user *, statbuf)
 {
         struct kstat stat;
         int error;
@@ -171,8 +171,8 @@ asmlinkage long compat_sys_newstat(const char __user * filename,
         return cp_compat_stat(&stat, statbuf);
 }
 
-asmlinkage long compat_sys_newlstat(const char __user * filename,
-                struct compat_stat __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
+                       struct compat_stat __user *, statbuf)
 {
         struct kstat stat;
         int error;
@@ -184,9 +184,9 @@ asmlinkage long compat_sys_newlstat(const char __user * filename,
 }
 
 #ifndef __ARCH_WANT_STAT64
-asmlinkage long compat_sys_newfstatat(unsigned int dfd,
-                const char __user *filename,
-                struct compat_stat __user *statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
+                       const char __user *, filename,
+                       struct compat_stat __user *, statbuf, int, flag)
 {
         struct kstat stat;
         int error;
@@ -198,8 +198,8 @@ asmlinkage long compat_sys_newfstatat(unsigned int dfd,
 }
 #endif
 
-asmlinkage long compat_sys_newfstat(unsigned int fd,
-                struct compat_stat __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
+                       struct compat_stat __user *, statbuf)
 {
         struct kstat stat;
         int error = vfs_fstat(fd, &stat);
@@ -247,7 +247,7 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
  * The following statfs calls are copies of code from fs/statfs.c and
  * should be checked against those from time to time
  */
-asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
+COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf)
 {
         struct kstatfs tmp;
         int error = user_statfs(pathname, &tmp);
@@ -256,7 +256,7 @@ asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_sta
         return error;
 }
 
-asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf)
+COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf)
 {
         struct kstatfs tmp;
         int error = fd_statfs(fd, &tmp);
@@ -298,7 +298,7 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
         return 0;
 }
 
-asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf)
+COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
 {
         struct kstatfs tmp;
         int error;
@@ -312,7 +312,7 @@ asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t s
         return error;
 }
 
-asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf)
+COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
 {
         struct kstatfs tmp;
         int error;
@@ -331,7 +331,7 @@ asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct c
  * Given how simple this syscall is that apporach is more maintainable
  * than the various conversion hacks.
  */
-asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u)
+COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u)
 {
         struct compat_ustat tmp;
         struct kstatfs sbuf;
@@ -399,12 +399,28 @@ static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *u
 }
 #endif
 
-asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
-                unsigned long arg)
+static unsigned int
+convert_fcntl_cmd(unsigned int cmd)
+{
+        switch (cmd) {
+        case F_GETLK64:
+                return F_GETLK;
+        case F_SETLK64:
+                return F_SETLK;
+        case F_SETLKW64:
+                return F_SETLKW;
+        }
+
+        return cmd;
+}
+
+COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
+                       compat_ulong_t, arg)
 {
         mm_segment_t old_fs;
         struct flock f;
         long ret;
+        unsigned int conv_cmd;
 
         switch (cmd) {
         case F_GETLK:
@@ -441,16 +457,18 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
         case F_GETLK64:
         case F_SETLK64:
         case F_SETLKW64:
+        case F_GETLKP:
+        case F_SETLKP:
+        case F_SETLKPW:
                 ret = get_compat_flock64(&f, compat_ptr(arg));
                 if (ret != 0)
                         break;
                 old_fs = get_fs();
                 set_fs(KERNEL_DS);
-                ret = sys_fcntl(fd, (cmd == F_GETLK64) ? F_GETLK :
-                                ((cmd == F_SETLK64) ? F_SETLK : F_SETLKW),
-                                (unsigned long)&f);
+                conv_cmd = convert_fcntl_cmd(cmd);
+                ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f);
                 set_fs(old_fs);
-                if (cmd == F_GETLK64 && ret == 0) {
+                if ((conv_cmd == F_GETLK || conv_cmd == F_GETLKP) && ret == 0) {
                         /* need to return lock information - see above for commentary */
                         if (f.l_start > COMPAT_LOFF_T_MAX)
                                 ret = -EOVERFLOW;
@@ -468,16 +486,22 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
         return ret;
 }
 
-asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
-                unsigned long arg)
+COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
+                       compat_ulong_t, arg)
 {
-        if ((cmd == F_GETLK64) || (cmd == F_SETLK64) || (cmd == F_SETLKW64))
+        switch (cmd) {
+        case F_GETLK64:
+        case F_SETLK64:
+        case F_SETLKW64:
+        case F_GETLKP:
+        case F_SETLKP:
+        case F_SETLKPW:
                 return -EINVAL;
+        }
         return compat_sys_fcntl64(fd, cmd, arg);
 }
 
-asmlinkage long
-compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p)
+COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_reqs, u32 __user *, ctx32p)
 {
         long ret;
         aio_context_t ctx64;
@@ -496,32 +520,24 @@ compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p)
         return ret;
 }
 
-asmlinkage long
-compat_sys_io_getevents(aio_context_t ctx_id,
-                                 unsigned long min_nr,
-                                 unsigned long nr,
-                                 struct io_event __user *events,
-                                 struct compat_timespec __user *timeout)
+COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
+                       compat_long_t, min_nr,
+                       compat_long_t, nr,
+                       struct io_event __user *, events,
+                       struct compat_timespec __user *, timeout)
 {
-        long ret;
         struct timespec t;
         struct timespec __user *ut = NULL;
 
-        ret = -EFAULT;
-        if (unlikely(!access_ok(VERIFY_WRITE, events, 
-                                nr * sizeof(struct io_event))))
-                goto out;
         if (timeout) {
-                if (get_compat_timespec(&t, timeout))
-                        goto out;
+                if (compat_get_timespec(&t, timeout))
+                        return -EFAULT;
 
                 ut = compat_alloc_user_space(sizeof(*ut));
                 if (copy_to_user(ut, &t, sizeof(t)) )
-                        goto out;
+                        return -EFAULT;
         } 
-        ret = sys_io_getevents(ctx_id, min_nr, nr, events, ut);
-out:
-        return ret;
+        return sys_io_getevents(ctx_id, min_nr, nr, events, ut);
 }
 
 /* A write operation does a read from user space and vice versa */
@@ -617,8 +633,8 @@ copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
 
 #define MAX_AIO_SUBMITS         (PAGE_SIZE/sizeof(struct iocb *))
 
-asmlinkage long
-compat_sys_io_submit(aio_context_t ctx_id, int nr, u32 __user *iocb)
+COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
+                       int, nr, u32 __user *, iocb)
 {
         struct iocb __user * __user *iocb64; 
         long ret;
@@ -770,10 +786,10 @@ static int do_nfs4_super_data_conv(void *raw_data)
 #define NCPFS_NAME      "ncpfs"
 #define NFS4_NAME       "nfs4"
 
-asmlinkage long compat_sys_mount(const char __user * dev_name,
-                                 const char __user * dir_name,
-                                 const char __user * type, unsigned long flags,
-                                 const void __user * data)
+COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
+                       const char __user *, dir_name,
+                       const char __user *, type, compat_ulong_t, flags,
+                       const void __user *, data)
 {
         char *kernel_type;
         unsigned long data_page;
@@ -869,8 +885,8 @@ efault:
         return -EFAULT;
 }
 
-asmlinkage long compat_sys_old_readdir(unsigned int fd,
-        struct compat_old_linux_dirent __user *dirent, unsigned int count)
+COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
+                struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
 {
         int error;
         struct fd f = fdget(fd);
@@ -948,8 +964,8 @@ efault:
         return -EFAULT;
 }
 
-asmlinkage long compat_sys_getdents(unsigned int fd,
-                struct compat_linux_dirent __user *dirent, unsigned int count)
+COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
+                struct compat_linux_dirent __user *, dirent, unsigned int, count)
 {
         struct fd f;
         struct compat_linux_dirent __user * lastdirent;
@@ -981,7 +997,7 @@ asmlinkage long compat_sys_getdents(unsigned int fd,
         return error;
 }
 
-#ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64
+#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64
 
 struct compat_getdents_callback64 {
         struct dir_context ctx;
@@ -1033,8 +1049,8 @@ efault:
         return -EFAULT;
 }
 
-asmlinkage long compat_sys_getdents64(unsigned int fd,
-                struct linux_dirent64 __user * dirent, unsigned int count)
+COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd,
+                struct linux_dirent64 __user *, dirent, unsigned int, count)
 {
         struct fd f;
         struct linux_dirent64 __user * lastdirent;
@@ -1066,7 +1082,7 @@ asmlinkage long compat_sys_getdents64(unsigned int fd,
         fdput(f);
         return error;
 }
-#endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */
+#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */
 
 /*
  * Exactly like fs/open.c:sys_open(), except that it doesn't set the
@@ -1287,9 +1303,9 @@ out_nofds:
         return ret;
 }
 
-asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
-        compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-        struct compat_timeval __user *tvp)
+COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
+        compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+        struct compat_timeval __user *, tvp)
 {
         struct timespec end_time, *to = NULL;
         struct compat_timeval tv;
@@ -1320,7 +1336,7 @@ struct compat_sel_arg_struct {
         compat_uptr_t tvp;
 };
 
-asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg)
+COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
 {
         struct compat_sel_arg_struct a;
 
@@ -1381,9 +1397,9 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp,
         return ret;
 }
 
-asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp,
-        compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-        struct compat_timespec __user *tsp, void __user *sig)
+COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
+        compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+        struct compat_timespec __user *, tsp, void __user *, sig)
 {
         compat_size_t sigsetsize = 0;
         compat_uptr_t up = 0;
@@ -1400,9 +1416,9 @@ asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp,
                                  sigsetsize);
 }
 
-asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
-        unsigned int nfds, struct compat_timespec __user *tsp,
-        const compat_sigset_t __user *sigmask, compat_size_t sigsetsize)
+COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
+        unsigned int,  nfds, struct compat_timespec __user *, tsp,
+        const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
 {
         compat_sigset_t ss32;
         sigset_t ksigmask, sigsaved;
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index a81147e2e4ef..4d24d17bcfc1 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -88,6 +88,11 @@ static void cputime_to_compat_timeval(const cputime_t cputime,
 #define ELF_HWCAP               COMPAT_ELF_HWCAP
 #endif
 
+#ifdef  COMPAT_ELF_HWCAP2
+#undef  ELF_HWCAP2
+#define ELF_HWCAP2              COMPAT_ELF_HWCAP2
+#endif
+
 #ifdef  COMPAT_ARCH_DLINFO
 #undef  ARCH_DLINFO
 #define ARCH_DLINFO             COMPAT_ARCH_DLINFO
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 3881610b6438..e82289047272 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1538,9 +1538,10 @@ static int compat_ioctl_check_table(unsigned int xcmd)
         return ioctl_pointer[i] == xcmd;
 }
 
-asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
-                                unsigned long arg)
+COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
+                       compat_ulong_t, arg32)
 {
+        unsigned long arg = arg32;
         struct fd f = fdget(fd);
         int error = -EBADF;
         if (!f.file)
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 06610cf94d57..ddcfe590b8a8 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
                 struct page *page = NULL;
 
                 if (blocknr + i < devsize) {
-                        page = read_mapping_page_async(mapping, blocknr + i,
-                                                                        NULL);
+                        page = read_mapping_page(mapping, blocknr + i, NULL);
                         /* synchronous error? */
                         if (IS_ERR(page))
                                 page = NULL;
@@ -244,6 +243,7 @@ static void cramfs_kill_sb(struct super_block *sb)
 
 static int cramfs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_RDONLY;
         return 0;
 }
diff --git a/fs/dcache.c b/fs/dcache.c
index ca02c13a84aa..66cba5a8a346 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2483,12 +2483,14 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
                         dentry->d_name.name = dentry->d_iname;
                 } else {
                         /*
-                         * Both are internal.  Just copy target to dentry
+                         * Both are internal.
                          */
-                        memcpy(dentry->d_iname, target->d_name.name,
-                                        target->d_name.len + 1);
-                        dentry->d_name.len = target->d_name.len;
-                        return;
+                        unsigned int i;
+                        BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+                        for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
+                                swap(((long *) &dentry->d_iname)[i],
+                                     ((long *) &target->d_iname)[i]);
+                        }
                 }
         }
         swap(dentry->d_name.len, target->d_name.len);
@@ -2545,13 +2547,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry,
  * __d_move - move a dentry
  * @dentry: entry to move
  * @target: new dentry
+ * @exchange: exchange the two dentries
  *
  * Update the dcache to reflect the move of a file name. Negative
  * dcache entries should not be moved in this way. Caller must hold
  * rename_lock, the i_mutex of the source and target directories,
  * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
  */
-static void __d_move(struct dentry * dentry, struct dentry * target)
+static void __d_move(struct dentry *dentry, struct dentry *target,
+                     bool exchange)
 {
         if (!dentry->d_inode)
                 printk(KERN_WARNING "VFS: moving negative dcache entry\n");
@@ -2573,8 +2577,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
         __d_drop(dentry);
         __d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
 
-        /* Unhash the target: dput() will then get rid of it */
+        /*
+         * Unhash the target (d_delete() is not usable here).  If exchanging
+         * the two dentries, then rehash onto the other's hash queue.
+         */
         __d_drop(target);
+        if (exchange) {
+                __d_rehash(target,
+                           d_hash(dentry->d_parent, dentry->d_name.hash));
+        }
 
         list_del(&dentry->d_u.d_child);
         list_del(&target->d_u.d_child);
@@ -2601,6 +2612,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
         write_seqcount_end(&dentry->d_seq);
 
         dentry_unlock_parents_for_move(dentry, target);
+        if (exchange)
+                fsnotify_d_move(target);
         spin_unlock(&target->d_lock);
         fsnotify_d_move(dentry);
         spin_unlock(&dentry->d_lock);
@@ -2618,11 +2631,30 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 void d_move(struct dentry *dentry, struct dentry *target)
 {
         write_seqlock(&rename_lock);
-        __d_move(dentry, target);
+        __d_move(dentry, target, false);
         write_sequnlock(&rename_lock);
 }
 EXPORT_SYMBOL(d_move);
 
+/*
+ * d_exchange - exchange two dentries
+ * @dentry1: first dentry
+ * @dentry2: second dentry
+ */
+void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
+{
+        write_seqlock(&rename_lock);
+
+        WARN_ON(!dentry1->d_inode);
+        WARN_ON(!dentry2->d_inode);
+        WARN_ON(IS_ROOT(dentry1));
+        WARN_ON(IS_ROOT(dentry2));
+
+        __d_move(dentry1, dentry2, true);
+
+        write_sequnlock(&rename_lock);
+}
+
 /**
  * d_ancestor - search for an ancestor
  * @p1: ancestor dentry
@@ -2670,7 +2702,7 @@ static struct dentry *__d_unalias(struct inode *inode,
         m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
         if (likely(!d_mountpoint(alias))) {
-                __d_move(alias, dentry);
+                __d_move(alias, dentry, false);
                 ret = alias;
         }
 out_err:
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 9c0444cccbe1..8c41b52da358 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -218,6 +218,7 @@ static int debugfs_remount(struct super_block *sb, int *flags, char *data)
         int err;
         struct debugfs_fs_info *fsi = sb->s_fs_info;
 
+        sync_filesystem(sb);
         err = debugfs_parse_options(data, &fsi->mount_opts);
         if (err)
                 goto fail;
@@ -358,7 +359,7 @@ exit:
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have.
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is NULL, then the
  *          file will be created in the root of the debugfs filesystem.
  * @data: a pointer to something that the caller will want to get to later
  *        on.  The inode.i_private pointer will point to this value on
@@ -400,7 +401,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_file);
  * @name: a pointer to a string containing the name of the directory to
  *        create.
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is NULL, then the
  *          directory will be created in the root of the debugfs filesystem.
  *
  * This function creates a directory in debugfs with the given name.
@@ -425,7 +426,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir);
  * @name: a pointer to a string containing the name of the symbolic link to
  *        create.
  * @parent: a pointer to the parent dentry for this symbolic link.  This
- *          should be a directory dentry if set.  If this paramater is NULL,
+ *          should be a directory dentry if set.  If this parameter is NULL,
  *          then the symbolic link will be created in the root of the debugfs
  *          filesystem.
  * @target: a pointer to a string containing the path to the target of the
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index a726b9f29cb7..c71038079b47 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -313,6 +313,7 @@ static int devpts_remount(struct super_block *sb, int *flags, char *data)
         struct pts_fs_info *fsi = DEVPTS_SB(sb);
         struct pts_mount_opts *opts = &fsi->mount_opts;
 
+        sync_filesystem(sb);
         err = parse_mount_options(data, PARSE_REMOUNT, opts);
 
         /*
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 160a5489a939..31ba0935e32e 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -664,7 +664,6 @@ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio,
                 goto out;
         sector = start_sector << (sdio->blkbits - 9);
         nr_pages = min(sdio->pages_in_io, bio_get_nr_vecs(map_bh->b_bdev));
-        nr_pages = min(nr_pages, BIO_MAX_PAGES);
         BUG_ON(nr_pages <= 0);
         dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages);
         sdio->boundary = 0;
@@ -1194,13 +1193,19 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
         }
 
         /*
-         * For file extending writes updating i_size before data
-         * writeouts complete can expose uninitialized blocks. So
-         * even for AIO, we need to wait for i/o to complete before
-         * returning in this case.
+         * For file extending writes updating i_size before data writeouts
+         * complete can expose uninitialized blocks in dumb filesystems.
+         * In that case we need to wait for I/O completion even if asked
+         * for an asynchronous write.
          */
-        dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) &&
-                (end > i_size_read(inode)));
+        if (is_sync_kiocb(iocb))
+                dio->is_async = false;
+        else if (!(dio->flags & DIO_ASYNC_EXTEND) &&
+            (rw & WRITE) && end > i_size_read(inode))
+                dio->is_async = false;
+        else
+                dio->is_async = true;
+
         dio->inode = inode;
         dio->rw = rw;
 
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index 0e90f0c91b93..dcea1e37a1b7 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -14,6 +14,7 @@
 #include "dlm_internal.h"
 #include "lock.h"
 #include "user.h"
+#include "ast.h"
 
 static uint64_t dlm_cb_seq;
 static DEFINE_SPINLOCK(dlm_cb_seq_spin);
@@ -308,6 +309,6 @@ void dlm_callback_resume(struct dlm_ls *ls)
         mutex_unlock(&ls->ls_cb_mutex);
 
         if (count)
-                log_debug(ls, "dlm_callback_resume %d", count);
+                log_rinfo(ls, "dlm_callback_resume %d", count);
 }
 
diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c
index 278a75cda446..d975851a7e1e 100644
--- a/fs/dlm/dir.c
+++ b/fs/dlm/dir.c
@@ -68,7 +68,7 @@ int dlm_recover_directory(struct dlm_ls *ls)
         uint16_t namelen;
         unsigned int count = 0, count_match = 0, count_bad = 0, count_add = 0;
 
-        log_debug(ls, "dlm_recover_directory");
+        log_rinfo(ls, "dlm_recover_directory");
 
         if (dlm_no_directory(ls))
                 goto out_status;
@@ -189,7 +189,7 @@ int dlm_recover_directory(struct dlm_ls *ls)
         error = 0;
         dlm_set_recover_status(ls, DLM_RS_DIR);
 
-        log_debug(ls, "dlm_recover_directory %u in %u new",
+        log_rinfo(ls, "dlm_recover_directory %u in %u new",
                   count, count_add);
  out_free:
         kfree(last_name);
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index e7665c31f7b1..5eff6ea3e27f 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -65,6 +65,8 @@ struct dlm_mhandle;
         printk(KERN_ERR "dlm: "fmt"\n" , ##args)
 #define log_error(ls, fmt, args...) \
         printk(KERN_ERR "dlm: %s: " fmt "\n", (ls)->ls_name , ##args)
+#define log_rinfo(ls, fmt, args...) \
+        printk(KERN_INFO "dlm: %s: " fmt "\n", (ls)->ls_name , ##args);
 
 #define log_debug(ls, fmt, args...) \
 do { \
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index e223a911a834..83f3d5520307 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -687,6 +687,7 @@ static int find_rsb_dir(struct dlm_ls *ls, char *name, int len,
                 log_error(ls, "find_rsb new from_other %d dir %d our %d %s",
                           from_nodeid, dir_nodeid, our_nodeid, r->res_name);
                 dlm_free_rsb(r);
+                r = NULL;
                 error = -ENOTBLK;
                 goto out_unlock;
         }
@@ -5462,7 +5463,7 @@ void dlm_recover_purge(struct dlm_ls *ls)
         up_write(&ls->ls_root_sem);
 
         if (lkb_count)
-                log_debug(ls, "dlm_recover_purge %u locks for %u nodes",
+                log_rinfo(ls, "dlm_recover_purge %u locks for %u nodes",
                           lkb_count, nodes_count);
 }
 
@@ -5536,7 +5537,7 @@ void dlm_recover_grant(struct dlm_ls *ls)
         }
 
         if (lkb_count)
-                log_debug(ls, "dlm_recover_grant %u locks on %u resources",
+                log_rinfo(ls, "dlm_recover_grant %u locks on %u resources",
                           lkb_count, rsb_count);
 }
 
@@ -5695,7 +5696,7 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
         put_rsb(r);
  out:
         if (error && error != -EEXIST)
-                log_debug(ls, "dlm_recover_master_copy remote %d %x error %d",
+                log_rinfo(ls, "dlm_recover_master_copy remote %d %x error %d",
                           from_nodeid, remid, error);
         rl->rl_result = cpu_to_le32(error);
         return error;
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index d5abafd56a6d..04d6398c1f1c 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -190,7 +190,7 @@ static int do_uevent(struct dlm_ls *ls, int in)
         else
                 kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE);
 
-        log_debug(ls, "%s the lockspace group...", in ? "joining" : "leaving");
+        log_rinfo(ls, "%s the lockspace group...", in ? "joining" : "leaving");
 
         /* dlm_controld will see the uevent, do the necessary group management
            and then write to sysfs to wake us */
@@ -198,7 +198,7 @@ static int do_uevent(struct dlm_ls *ls, int in)
         error = wait_event_interruptible(ls->ls_uevent_wait,
                         test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));
 
-        log_debug(ls, "group event done %d %d", error, ls->ls_uevent_result);
+        log_rinfo(ls, "group event done %d %d", error, ls->ls_uevent_result);
 
         if (error)
                 goto out;
@@ -640,7 +640,7 @@ static int new_lockspace(const char *name, const char *cluster,
 
         dlm_create_debug_file(ls);
 
-        log_debug(ls, "join complete");
+        log_rinfo(ls, "join complete");
         *lockspace = ls;
         return 0;
 
@@ -835,7 +835,7 @@ static int release_lockspace(struct dlm_ls *ls, int force)
         dlm_clear_members(ls);
         dlm_clear_members_gone(ls);
         kfree(ls->ls_node_array);
-        log_debug(ls, "release_lockspace final free");
+        log_rinfo(ls, "release_lockspace final free");
         kobject_put(&ls->ls_kobj);
         /* The ls structure will be freed when the kobject is done with */
 
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index 476557b54921..9c47f1c14a8b 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -60,18 +60,15 @@ void dlm_slots_copy_out(struct dlm_ls *ls, struct dlm_rcom *rc)
 
 #define SLOT_DEBUG_LINE 128
 
-static void log_debug_slots(struct dlm_ls *ls, uint32_t gen, int num_slots,
-                            struct rcom_slot *ro0, struct dlm_slot *array,
-                            int array_size)
+static void log_slots(struct dlm_ls *ls, uint32_t gen, int num_slots,
+                      struct rcom_slot *ro0, struct dlm_slot *array,
+                      int array_size)
 {
         char line[SLOT_DEBUG_LINE];
         int len = SLOT_DEBUG_LINE - 1;
         int pos = 0;
         int ret, i;
 
-        if (!dlm_config.ci_log_debug)
-                return;
-
         memset(line, 0, sizeof(line));
 
         if (array) {
@@ -95,7 +92,7 @@ static void log_debug_slots(struct dlm_ls *ls, uint32_t gen, int num_slots,
                 }
         }
 
-        log_debug(ls, "generation %u slots %d%s", gen, num_slots, line);
+        log_rinfo(ls, "generation %u slots %d%s", gen, num_slots, line);
 }
 
 int dlm_slots_copy_in(struct dlm_ls *ls)
@@ -129,7 +126,7 @@ int dlm_slots_copy_in(struct dlm_ls *ls)
                 ro->ro_slot = le16_to_cpu(ro->ro_slot);
         }
 
-        log_debug_slots(ls, gen, num_slots, ro0, NULL, 0);
+        log_slots(ls, gen, num_slots, ro0, NULL, 0);
 
         list_for_each_entry(memb, &ls->ls_nodes, list) {
                 for (i = 0, ro = ro0; i < num_slots; i++, ro++) {
@@ -274,7 +271,7 @@ int dlm_slots_assign(struct dlm_ls *ls, int *num_slots, int *slots_size,
 
         gen++;
 
-        log_debug_slots(ls, gen, num, NULL, array, array_size);
+        log_slots(ls, gen, num, NULL, array, array_size);
 
         max_slots = (dlm_config.ci_buffer_size - sizeof(struct dlm_rcom) -
                      sizeof(struct rcom_config)) / sizeof(struct rcom_slot);
@@ -447,7 +444,7 @@ static int ping_members(struct dlm_ls *ls)
                         break;
         }
         if (error)
-                log_debug(ls, "ping_members aborted %d last nodeid %d",
+                log_rinfo(ls, "ping_members aborted %d last nodeid %d",
                           error, ls->ls_recover_nodeid);
         return error;
 }
@@ -539,7 +536,7 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
            count as a negative change so the "neg" recovery steps will happen */
 
         list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
-                log_debug(ls, "prev removed member %d", memb->nodeid);
+                log_rinfo(ls, "prev removed member %d", memb->nodeid);
                 neg++;
         }
 
@@ -551,10 +548,10 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
                         continue;
 
                 if (!node) {
-                        log_debug(ls, "remove member %d", memb->nodeid);
+                        log_rinfo(ls, "remove member %d", memb->nodeid);
                 } else {
                         /* removed and re-added */
-                        log_debug(ls, "remove member %d comm_seq %u %u",
+                        log_rinfo(ls, "remove member %d comm_seq %u %u",
                                   memb->nodeid, memb->comm_seq, node->comm_seq);
                 }
 
@@ -571,7 +568,7 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
                 if (dlm_is_member(ls, node->nodeid))
                         continue;
                 dlm_add_member(ls, node);
-                log_debug(ls, "add member %d", node->nodeid);
+                log_rinfo(ls, "add member %d", node->nodeid);
         }
 
         list_for_each_entry(memb, &ls->ls_nodes, list) {
@@ -591,7 +588,7 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
                 complete(&ls->ls_members_done);
         }
 
-        log_debug(ls, "dlm_recover_members %d nodes", ls->ls_num_nodes);
+        log_rinfo(ls, "dlm_recover_members %d nodes", ls->ls_num_nodes);
         return error;
 }
 
diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c
index a6bc63f6e31b..eaea789bf97d 100644
--- a/fs/dlm/recover.c
+++ b/fs/dlm/recover.c
@@ -526,7 +526,7 @@ int dlm_recover_masters(struct dlm_ls *ls)
         int nodir = dlm_no_directory(ls);
         int error;
 
-        log_debug(ls, "dlm_recover_masters");
+        log_rinfo(ls, "dlm_recover_masters");
 
         down_read(&ls->ls_root_sem);
         list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
@@ -552,7 +552,7 @@ int dlm_recover_masters(struct dlm_ls *ls)
         }
         up_read(&ls->ls_root_sem);
 
-        log_debug(ls, "dlm_recover_masters %u of %u", count, total);
+        log_rinfo(ls, "dlm_recover_masters %u of %u", count, total);
 
         error = dlm_wait_function(ls, &recover_idr_empty);
  out:
@@ -685,7 +685,7 @@ int dlm_recover_locks(struct dlm_ls *ls)
         }
         up_read(&ls->ls_root_sem);
 
-        log_debug(ls, "dlm_recover_locks %d out", count);
+        log_rinfo(ls, "dlm_recover_locks %d out", count);
 
         error = dlm_wait_function(ls, &recover_list_empty);
  out:
@@ -883,7 +883,7 @@ void dlm_recover_rsbs(struct dlm_ls *ls)
         up_read(&ls->ls_root_sem);
 
         if (count)
-                log_debug(ls, "dlm_recover_rsbs %d done", count);
+                log_rinfo(ls, "dlm_recover_rsbs %d done", count);
 }
 
 /* Create a single list of all root rsb's to be used during recovery */
@@ -950,6 +950,6 @@ void dlm_clear_toss(struct dlm_ls *ls)
         }
 
         if (count)
-                log_debug(ls, "dlm_clear_toss %u done", count);
+                log_rinfo(ls, "dlm_clear_toss %u done", count);
 }
 
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index 32f9f8926ec3..6859b4bf971e 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -55,7 +55,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
         unsigned long start;
         int error, neg = 0;
 
-        log_debug(ls, "dlm_recover %llu", (unsigned long long)rv->seq);
+        log_rinfo(ls, "dlm_recover %llu", (unsigned long long)rv->seq);
 
         mutex_lock(&ls->ls_recoverd_active);
 
@@ -76,7 +76,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
         error = dlm_recover_members(ls, rv, &neg);
         if (error) {
-                log_debug(ls, "dlm_recover_members error %d", error);
+                log_rinfo(ls, "dlm_recover_members error %d", error);
                 goto fail;
         }
 
@@ -90,7 +90,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
         error = dlm_recover_members_wait(ls);
         if (error) {
-                log_debug(ls, "dlm_recover_members_wait error %d", error);
+                log_rinfo(ls, "dlm_recover_members_wait error %d", error);
                 goto fail;
         }
 
@@ -103,7 +103,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
         error = dlm_recover_directory(ls);
         if (error) {
-                log_debug(ls, "dlm_recover_directory error %d", error);
+                log_rinfo(ls, "dlm_recover_directory error %d", error);
                 goto fail;
         }
 
@@ -111,11 +111,11 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
         error = dlm_recover_directory_wait(ls);
         if (error) {
-                log_debug(ls, "dlm_recover_directory_wait error %d", error);
+                log_rinfo(ls, "dlm_recover_directory_wait error %d", error);
                 goto fail;
         }
 
-        log_debug(ls, "dlm_recover_directory %u out %u messages",
+        log_rinfo(ls, "dlm_recover_directory %u out %u messages",
                   ls->ls_recover_dir_sent_res, ls->ls_recover_dir_sent_msg);
 
         /*
@@ -144,7 +144,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
                 error = dlm_recover_masters(ls);
                 if (error) {
-                        log_debug(ls, "dlm_recover_masters error %d", error);
+                        log_rinfo(ls, "dlm_recover_masters error %d", error);
                         goto fail;
                 }
 
@@ -154,7 +154,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
                 error = dlm_recover_locks(ls);
                 if (error) {
-                        log_debug(ls, "dlm_recover_locks error %d", error);
+                        log_rinfo(ls, "dlm_recover_locks error %d", error);
                         goto fail;
                 }
 
@@ -162,11 +162,11 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
                 error = dlm_recover_locks_wait(ls);
                 if (error) {
-                        log_debug(ls, "dlm_recover_locks_wait error %d", error);
+                        log_rinfo(ls, "dlm_recover_locks_wait error %d", error);
                         goto fail;
                 }
 
-                log_debug(ls, "dlm_recover_locks %u in",
+                log_rinfo(ls, "dlm_recover_locks %u in",
                           ls->ls_recover_locks_in);
 
                 /*
@@ -186,7 +186,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
                 error = dlm_recover_locks_wait(ls);
                 if (error) {
-                        log_debug(ls, "dlm_recover_locks_wait error %d", error);
+                        log_rinfo(ls, "dlm_recover_locks_wait error %d", error);
                         goto fail;
                 }
         }
@@ -205,7 +205,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
         error = dlm_recover_done_wait(ls);
         if (error) {
-                log_debug(ls, "dlm_recover_done_wait error %d", error);
+                log_rinfo(ls, "dlm_recover_done_wait error %d", error);
                 goto fail;
         }
 
@@ -217,25 +217,25 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
         error = enable_locking(ls, rv->seq);
         if (error) {
-                log_debug(ls, "enable_locking error %d", error);
+                log_rinfo(ls, "enable_locking error %d", error);
                 goto fail;
         }
 
         error = dlm_process_requestqueue(ls);
         if (error) {
-                log_debug(ls, "dlm_process_requestqueue error %d", error);
+                log_rinfo(ls, "dlm_process_requestqueue error %d", error);
                 goto fail;
         }
 
         error = dlm_recover_waiters_post(ls);
         if (error) {
-                log_debug(ls, "dlm_recover_waiters_post error %d", error);
+                log_rinfo(ls, "dlm_recover_waiters_post error %d", error);
                 goto fail;
         }
 
         dlm_recover_grant(ls);
 
-        log_debug(ls, "dlm_recover %llu generation %u done: %u ms",
+        log_rinfo(ls, "dlm_recover %llu generation %u done: %u ms",
                   (unsigned long long)rv->seq, ls->ls_generation,
                   jiffies_to_msecs(jiffies - start));
         mutex_unlock(&ls->ls_recoverd_active);
@@ -245,7 +245,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
 
  fail:
         dlm_release_root_list(ls);
-        log_debug(ls, "dlm_recover %llu error %d",
+        log_rinfo(ls, "dlm_recover %llu error %d",
                   (unsigned long long)rv->seq, error);
         mutex_unlock(&ls->ls_recoverd_active);
         return error;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 9fd702f5bfb2..9280202e488c 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -59,10 +59,22 @@ int drop_caches_sysctl_handler(ctl_table *table, int write,
         if (ret)
                 return ret;
         if (write) {
-                if (sysctl_drop_caches & 1)
+                static int stfu;
+
+                if (sysctl_drop_caches & 1) {
                         iterate_supers(drop_pagecache_sb, NULL);
-                if (sysctl_drop_caches & 2)
+                        count_vm_event(DROP_PAGECACHE);
+                }
+                if (sysctl_drop_caches & 2) {
                         drop_slab();
+                        count_vm_event(DROP_SLAB);
+                }
+                if (!stfu) {
+                        pr_info("%s (%d): drop_caches: %d\n",
+                                current->comm, task_pid_nr(current),
+                                sysctl_drop_caches);
+                }
+                stfu |= sysctl_drop_caches & 4;
         }
         return 0;
 }
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index b167ca48b8ee..d4a9431ec73c 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         }
         rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
                         lower_new_dir_dentry->d_inode, lower_new_dentry,
-                        NULL);
+                        NULL, 0);
         if (rc)
                 goto out_lock;
         if (target_inode)
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index e879cf8ff0b1..afa1b81c3418 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -132,7 +132,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf)
  */
 static void ecryptfs_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         iput(ecryptfs_inode_to_lower(inode));
 }
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index 8dd524f32284..cdb2971192a5 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -21,7 +21,7 @@ static ssize_t efivarfs_file_write(struct file *file,
         u32 attributes;
         struct inode *inode = file->f_mapping->host;
         unsigned long datasize = count - sizeof(attributes);
-        ssize_t bytes = 0;
+        ssize_t bytes;
         bool set = false;
 
         if (count < sizeof(attributes))
@@ -33,14 +33,9 @@ static ssize_t efivarfs_file_write(struct file *file,
         if (attributes & ~(EFI_VARIABLE_MASK))
                 return -EINVAL;
 
-        data = kmalloc(datasize, GFP_KERNEL);
-        if (!data)
-                return -ENOMEM;
-
-        if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) {
-                bytes = -EFAULT;
-                goto out;
-        }
+        data = memdup_user(userbuf + sizeof(attributes), datasize);
+        if (IS_ERR(data))
+                return PTR_ERR(data);
 
         bytes = efivar_entry_set_get_size(var, attributes, &datasize,
                                           data, &set);
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 50215bbd6463..3befcc9f5d63 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -91,7 +91,7 @@ static void init_once(void *foo)
         inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
         efs_inode_cachep = kmem_cache_create("efs_inode_cache",
                                 sizeof(struct efs_inode_info),
@@ -114,6 +114,7 @@ static void destroy_inodecache(void)
 
 static int efs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_RDONLY;
         return 0;
 }
diff --git a/fs/exec.c b/fs/exec.c
index 3d78fccdd723..25dfeba6d55f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -97,6 +97,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
         module_put(fmt->module);
 }
 
+#ifdef CONFIG_USELIB
 /*
  * Note that a shared library must be both readable and executable due to
  * security reasons.
@@ -156,6 +157,7 @@ exit:
 out:
         return error;
 }
+#endif /* #ifdef CONFIG_USELIB */
 
 #ifdef CONFIG_MMU
 /*
@@ -1619,9 +1621,9 @@ SYSCALL_DEFINE3(execve,
         return do_execve(getname(filename), argv, envp);
 }
 #ifdef CONFIG_COMPAT
-asmlinkage long compat_sys_execve(const char __user * filename,
-        const compat_uptr_t __user * argv,
-        const compat_uptr_t __user * envp)
+COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
+        const compat_uptr_t __user *, argv,
+        const compat_uptr_t __user *, envp)
 {
         return compat_do_execve(getname(filename), argv, envp);
 }
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index ee4317faccb1..d1c244d67667 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1486,7 +1486,7 @@ void exofs_evict_inode(struct inode *inode)
         struct ore_io_state *ios;
         int ret;
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         /* TODO: should do better here */
         if (inode->i_nlink || is_bad_inode(inode))
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 94ed36849b71..b1d2a4675d42 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -78,7 +78,7 @@ void ext2_evict_inode(struct inode * inode)
                 dquot_drop(inode);
         }
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         if (want_delete) {
                 sb_start_intwrite(inode->i_sb);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 20d6697bd638..d260115c0350 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1254,6 +1254,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
         unsigned long old_sb_flags;
         int err;
 
+        sync_filesystem(sb);
         spin_lock(&sbi->s_lock);
 
         /* Store the old options */
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 384b6ebb655f..efce2bbfb5e5 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -228,7 +228,7 @@ void ext3_evict_inode (struct inode *inode)
                 log_wait_commit(journal, commit_tid);
                 filemap_write_and_wait(&inode->i_data);
         }
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         ext3_discard_reservation(inode);
         rsv = ei->i_block_alloc_info;
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 37fd31ed16e7..95c6c5a6d0c5 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2649,6 +2649,8 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
         int i;
 #endif
 
+        sync_filesystem(sb);
+
         /* Store the original options */
         old_sb_flags = sb->s_flags;
         old_opts.s_mount_opt = sbi->s_mount_opt;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index d3a534fdc5ff..f1c65dc7cc0a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -31,6 +31,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/ratelimit.h>
 #include <crypto/hash.h>
+#include <linux/falloc.h>
 #ifdef __KERNEL__
 #include <linux/compat.h>
 #endif
@@ -567,6 +568,8 @@ enum {
 #define EXT4_GET_BLOCKS_NO_LOCK                 0x0100
         /* Do not put hole in extent cache */
 #define EXT4_GET_BLOCKS_NO_PUT_HOLE             0x0200
+        /* Convert written extents to unwritten */
+#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN       0x0400
 
 /*
  * The bit position of these flags must not overlap with any of the
@@ -998,6 +1001,8 @@ struct ext4_inode_info {
 #define EXT4_MOUNT2_STD_GROUP_SIZE      0x00000002 /* We have standard group
                                                       size of blocksize * 8
                                                       blocks */
+#define EXT4_MOUNT2_HURD_COMPAT         0x00000004 /* Support HURD-castrated
+                                                      file systems */
 
 #define clear_opt(sb, opt)              EXT4_SB(sb)->s_mount_opt &= \
                                                 ~EXT4_MOUNT_##opt
@@ -1326,6 +1331,7 @@ struct ext4_sb_info {
         struct list_head s_es_lru;
         unsigned long s_es_last_sorted;
         struct percpu_counter s_extent_cache_cnt;
+        struct mb_cache *s_mb_cache;
         spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 
         /* Ratelimit ext4 messages. */
@@ -2133,8 +2139,6 @@ extern int ext4_writepage_trans_blocks(struct inode *);
 extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_block_truncate_page(handle_t *handle,
                 struct address_space *mapping, loff_t from);
-extern int ext4_block_zero_page_range(handle_t *handle,
-                struct address_space *mapping, loff_t from, loff_t length);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
                              loff_t lstart, loff_t lend);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
@@ -2757,6 +2761,7 @@ extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                         __u64 start, __u64 len);
 extern int ext4_ext_precache(struct inode *inode);
+extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
 
 /* move_extent.c */
 extern void ext4_double_down_write_data_sem(struct inode *first,
@@ -2766,6 +2771,8 @@ extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
                              __u64 start_orig, __u64 start_donor,
                              __u64 len, __u64 *moved_len);
+extern int mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
+                            struct ext4_extent **extent);
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 3fe29de832c8..c3fb607413ed 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -259,6 +259,16 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
                 if (WARN_ON_ONCE(err)) {
                         ext4_journal_abort_handle(where, line, __func__, bh,
                                                   handle, err);
+                        if (inode == NULL) {
+                                pr_err("EXT4: jbd2_journal_dirty_metadata "
+                                       "failed: handle type %u started at "
+                                       "line %u, credits %u/%u, errcode %d",
+                                       handle->h_type,
+                                       handle->h_line_no,
+                                       handle->h_requested_credits,
+                                       handle->h_buffer_credits, err);
+                                return err;
+                        }
                         ext4_error_inode(inode, where, line,
                                          bh->b_blocknr,
                                          "journal_dirty_metadata failed: "
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74bc2d549c58..82df3ce9874a 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -37,7 +37,6 @@
 #include <linux/quotaops.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <linux/falloc.h>
 #include <asm/uaccess.h>
 #include <linux/fiemap.h>
 #include "ext4_jbd2.h"
@@ -1691,7 +1690,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
          * the extent that was written properly split out and conversion to
          * initialized is trivial.
          */
-        if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
+        if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2))
                 return 0;
 
         ext1_ee_len = ext4_ext_get_actual_len(ex1);
@@ -1708,6 +1707,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
          */
         if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
                 return 0;
+        if (ext4_ext_is_uninitialized(ex1) &&
+            (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
+             atomic_read(&EXT4_I(inode)->i_unwritten) ||
+             (ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN)))
+                return 0;
 #ifdef AGGRESSIVE_TEST
         if (ext1_ee_len >= 4)
                 return 0;
@@ -1731,7 +1735,7 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
 {
         struct ext4_extent_header *eh;
         unsigned int depth, len;
-        int merge_done = 0;
+        int merge_done = 0, uninit;
 
         depth = ext_depth(inode);
         BUG_ON(path[depth].p_hdr == NULL);
@@ -1741,8 +1745,11 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
                 if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
                         break;
                 /* merge with next extent! */
+                uninit = ext4_ext_is_uninitialized(ex);
                 ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
                                 + ext4_ext_get_actual_len(ex + 1));
+                if (uninit)
+                        ext4_ext_mark_uninitialized(ex);
 
                 if (ex + 1 < EXT_LAST_EXTENT(eh)) {
                         len = (EXT_LAST_EXTENT(eh) - ex - 1)
@@ -1896,7 +1903,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
         struct ext4_ext_path *npath = NULL;
         int depth, len, err;
         ext4_lblk_t next;
-        int mb_flags = 0;
+        int mb_flags = 0, uninit;
 
         if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
                 EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1946,9 +1953,11 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
                                                   path + depth);
                         if (err)
                                 return err;
-
+                        uninit = ext4_ext_is_uninitialized(ex);
                         ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
                                         + ext4_ext_get_actual_len(newext));
+                        if (uninit)
+                                ext4_ext_mark_uninitialized(ex);
                         eh = path[depth].p_hdr;
                         nearex = ex;
                         goto merge;
@@ -1971,10 +1980,13 @@ prepend:
                         if (err)
                                 return err;
 
+                        uninit = ext4_ext_is_uninitialized(ex);
                         ex->ee_block = newext->ee_block;
                         ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
                         ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
                                         + ext4_ext_get_actual_len(newext));
+                        if (uninit)
+                                ext4_ext_mark_uninitialized(ex);
                         eh = path[depth].p_hdr;
                         nearex = ex;
                         goto merge;
@@ -2585,6 +2597,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
         ex_ee_block = le32_to_cpu(ex->ee_block);
         ex_ee_len = ext4_ext_get_actual_len(ex);
 
+        /*
+         * If we're starting with an extent other than the last one in the
+         * node, we need to see if it shares a cluster with the extent to
+         * the right (towards the end of the file). If its leftmost cluster
+         * is this extent's rightmost cluster and it is not cluster aligned,
+         * we'll mark it as a partial that is not to be deallocated.
+         */
+
+        if (ex != EXT_LAST_EXTENT(eh)) {
+                ext4_fsblk_t current_pblk, right_pblk;
+                long long current_cluster, right_cluster;
+
+                current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+                current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+                right_pblk = ext4_ext_pblock(ex + 1);
+                right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+                if (current_cluster == right_cluster &&
+                        EXT4_PBLK_COFF(sbi, right_pblk))
+                        *partial_cluster = -right_cluster;
+        }
+
         trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
 
         while (ex >= EXT_FIRST_EXTENT(eh) &&
@@ -2710,10 +2743,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
                 err = ext4_ext_correct_indexes(handle, inode, path);
 
         /*
-         * Free the partial cluster only if the current extent does not
-         * reference it. Otherwise we might free used cluster.
+         * If there's a partial cluster and at least one extent remains in
+         * the leaf, free the partial cluster if it isn't shared with the
+         * current extent.  If there's a partial cluster and no extents
+         * remain in the leaf, it can't be freed here.  It can only be
+         * freed when it's possible to determine if it's not shared with
+         * any other extent - when the next leaf is processed or when space
+         * removal is complete.
          */
-        if (*partial_cluster > 0 &&
+        if (*partial_cluster > 0 && eh->eh_entries &&
             (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
              *partial_cluster)) {
                 int flags = get_default_free_blocks_flags(inode);
@@ -3569,6 +3607,8 @@ out:
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
  *
+ * This works the same way in the case of initialized -> unwritten conversion.
+ *
  * One of more index blocks maybe needed if the extent tree grow after
  * the uninitialized extent split. To prevent ENOSPC occur at the IO
  * complete, we need to split the uninitialized extent before DIO submit
@@ -3579,7 +3619,7 @@ out:
  *
  * Returns the size of uninitialized extent to be written on success.
  */
-static int ext4_split_unwritten_extents(handle_t *handle,
+static int ext4_split_convert_extents(handle_t *handle,
                                         struct inode *inode,
                                         struct ext4_map_blocks *map,
                                         struct ext4_ext_path *path,
@@ -3591,9 +3631,9 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         unsigned int ee_len;
         int split_flag = 0, depth;
 
-        ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
-                "block %llu, max_blocks %u\n", inode->i_ino,
-                (unsigned long long)map->m_lblk, map->m_len);
+        ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n",
+                  __func__, inode->i_ino,
+                  (unsigned long long)map->m_lblk, map->m_len);
 
         eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
                 inode->i_sb->s_blocksize_bits;
@@ -3608,14 +3648,73 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         ee_block = le32_to_cpu(ex->ee_block);
         ee_len = ext4_ext_get_actual_len(ex);
 
-        split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
-        split_flag |= EXT4_EXT_MARK_UNINIT2;
-        if (flags & EXT4_GET_BLOCKS_CONVERT)
-                split_flag |= EXT4_EXT_DATA_VALID2;
+        /* Convert to unwritten */
+        if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) {
+                split_flag |= EXT4_EXT_DATA_VALID1;
+        /* Convert to initialized */
+        } else if (flags & EXT4_GET_BLOCKS_CONVERT) {
+                split_flag |= ee_block + ee_len <= eof_block ?
+                              EXT4_EXT_MAY_ZEROOUT : 0;
+                split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
+        }
         flags |= EXT4_GET_BLOCKS_PRE_IO;
         return ext4_split_extent(handle, inode, path, map, split_flag, flags);
 }
 
+static int ext4_convert_initialized_extents(handle_t *handle,
+                                            struct inode *inode,
+                                            struct ext4_map_blocks *map,
+                                            struct ext4_ext_path *path)
+{
+        struct ext4_extent *ex;
+        ext4_lblk_t ee_block;
+        unsigned int ee_len;
+        int depth;
+        int err = 0;
+
+        depth = ext_depth(inode);
+        ex = path[depth].p_ext;
+        ee_block = le32_to_cpu(ex->ee_block);
+        ee_len = ext4_ext_get_actual_len(ex);
+
+        ext_debug("%s: inode %lu, logical"
+                "block %llu, max_blocks %u\n", __func__, inode->i_ino,
+                  (unsigned long long)ee_block, ee_len);
+
+        if (ee_block != map->m_lblk || ee_len > map->m_len) {
+                err = ext4_split_convert_extents(handle, inode, map, path,
+                                EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
+                if (err < 0)
+                        goto out;
+                ext4_ext_drop_refs(path);
+                path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
+                if (IS_ERR(path)) {
+                        err = PTR_ERR(path);
+                        goto out;
+                }
+                depth = ext_depth(inode);
+                ex = path[depth].p_ext;
+        }
+
+        err = ext4_ext_get_access(handle, inode, path + depth);
+        if (err)
+                goto out;
+        /* first mark the extent as uninitialized */
+        ext4_ext_mark_uninitialized(ex);
+
+        /* note: ext4_ext_correct_indexes() isn't needed here because
+         * borders are not changed
+         */
+        ext4_ext_try_to_merge(handle, inode, path, ex);
+
+        /* Mark modified extent as dirty */
+        err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+out:
+        ext4_ext_show_leaf(inode, path);
+        return err;
+}
+
+
 static int ext4_convert_unwritten_extents_endio(handle_t *handle,
                                                 struct inode *inode,
                                                 struct ext4_map_blocks *map,
@@ -3649,8 +3748,8 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
                              inode->i_ino, (unsigned long long)ee_block, ee_len,
                              (unsigned long long)map->m_lblk, map->m_len);
 #endif
-                err = ext4_split_unwritten_extents(handle, inode, map, path,
-                                                   EXT4_GET_BLOCKS_CONVERT);
+                err = ext4_split_convert_extents(handle, inode, map, path,
+                                                 EXT4_GET_BLOCKS_CONVERT);
                 if (err < 0)
                         goto out;
                 ext4_ext_drop_refs(path);
@@ -3851,6 +3950,38 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 }
 
 static int
+ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
+                        struct ext4_map_blocks *map,
+                        struct ext4_ext_path *path, int flags,
+                        unsigned int allocated, ext4_fsblk_t newblock)
+{
+        int ret = 0;
+        int err = 0;
+
+        /*
+         * Make sure that the extent is no bigger than we support with
+         * uninitialized extent
+         */
+        if (map->m_len > EXT_UNINIT_MAX_LEN)
+                map->m_len = EXT_UNINIT_MAX_LEN / 2;
+
+        ret = ext4_convert_initialized_extents(handle, inode, map,
+                                                path);
+        if (ret >= 0) {
+                ext4_update_inode_fsync_trans(handle, inode, 1);
+                err = check_eofblocks_fl(handle, inode, map->m_lblk,
+                                         path, map->m_len);
+        } else
+                err = ret;
+        map->m_flags |= EXT4_MAP_UNWRITTEN;
+        if (allocated > map->m_len)
+                allocated = map->m_len;
+        map->m_len = allocated;
+
+        return err ? err : allocated;
+}
+
+static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
                         struct ext4_map_blocks *map,
                         struct ext4_ext_path *path, int flags,
@@ -3877,8 +4008,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 
         /* get_block() before submit the IO, split the extent */
         if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-                ret = ext4_split_unwritten_extents(handle, inode, map,
-                                                   path, flags);
+                ret = ext4_split_convert_extents(handle, inode, map,
+                                         path, flags | EXT4_GET_BLOCKS_CONVERT);
                 if (ret <= 0)
                         goto out;
                 /*
@@ -3993,10 +4124,6 @@ out1:
         map->m_pblk = newblock;
         map->m_len = allocated;
 out2:
-        if (path) {
-                ext4_ext_drop_refs(path);
-                kfree(path);
-        }
         return err ? err : allocated;
 }
 
@@ -4128,7 +4255,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
         struct ext4_extent newex, *ex, *ex2;
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
         ext4_fsblk_t newblock = 0;
-        int free_on_err = 0, err = 0, depth;
+        int free_on_err = 0, err = 0, depth, ret;
         unsigned int allocated = 0, offset = 0;
         unsigned int allocated_clusters = 0;
         struct ext4_allocation_request ar;
@@ -4170,6 +4297,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
                 ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
                 unsigned short ee_len;
 
+
                 /*
                  * Uninitialized extents are treated as holes, except that
                  * we split out initialized portions during a write.
@@ -4186,13 +4314,27 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
                         ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
                                   ee_block, ee_len, newblock);
 
-                        if (!ext4_ext_is_uninitialized(ex))
+                        /*
+                         * If the extent is initialized check whether the
+                         * caller wants to convert it to unwritten.
+                         */
+                        if ((!ext4_ext_is_uninitialized(ex)) &&
+                            (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
+                                allocated = ext4_ext_convert_initialized_extent(
+                                                handle, inode, map, path, flags,
+                                                allocated, newblock);
+                                goto out2;
+                        } else if (!ext4_ext_is_uninitialized(ex))
                                 goto out;
 
-                        allocated = ext4_ext_handle_uninitialized_extents(
+                        ret = ext4_ext_handle_uninitialized_extents(
                                 handle, inode, map, path, flags,
                                 allocated, newblock);
-                        goto out3;
+                        if (ret < 0)
+                                err = ret;
+                        else
+                                allocated = ret;
+                        goto out2;
                 }
         }
 
@@ -4473,7 +4615,6 @@ out2:
                 kfree(path);
         }
 
-out3:
         trace_ext4_ext_map_blocks_exit(inode, flags, map,
                                        err ? err : allocated);
         ext4_es_lru_add(inode);
@@ -4514,34 +4655,200 @@ retry:
         ext4_std_error(inode->i_sb, err);
 }
 
-static void ext4_falloc_update_inode(struct inode *inode,
-                                int mode, loff_t new_size, int update_ctime)
+static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
+                                  ext4_lblk_t len, int flags, int mode)
 {
-        struct timespec now;
+        struct inode *inode = file_inode(file);
+        handle_t *handle;
+        int ret = 0;
+        int ret2 = 0;
+        int retries = 0;
+        struct ext4_map_blocks map;
+        unsigned int credits;
 
-        if (update_ctime) {
-                now = current_fs_time(inode->i_sb);
-                if (!timespec_equal(&inode->i_ctime, &now))
-                        inode->i_ctime = now;
+        map.m_lblk = offset;
+        /*
+         * Don't normalize the request if it can fit in one extent so
+         * that it doesn't get unnecessarily split into multiple
+         * extents.
+         */
+        if (len <= EXT_UNINIT_MAX_LEN)
+                flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
+
+        /*
+         * credits to insert 1 extent into extent tree
+         */
+        credits = ext4_chunk_trans_blocks(inode, len);
+
+retry:
+        while (ret >= 0 && ret < len) {
+                map.m_lblk = map.m_lblk + ret;
+                map.m_len = len = len - ret;
+                handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+                                            credits);
+                if (IS_ERR(handle)) {
+                        ret = PTR_ERR(handle);
+                        break;
+                }
+                ret = ext4_map_blocks(handle, inode, &map, flags);
+                if (ret <= 0) {
+                        ext4_debug("inode #%lu: block %u: len %u: "
+                                   "ext4_ext_map_blocks returned %d",
+                                   inode->i_ino, map.m_lblk,
+                                   map.m_len, ret);
+                        ext4_mark_inode_dirty(handle, inode);
+                        ret2 = ext4_journal_stop(handle);
+                        break;
+                }
+                ret2 = ext4_journal_stop(handle);
+                if (ret2)
+                        break;
+        }
+        if (ret == -ENOSPC &&
+                        ext4_should_retry_alloc(inode->i_sb, &retries)) {
+                ret = 0;
+                goto retry;
         }
+
+        return ret > 0 ? ret2 : ret;
+}
+
+static long ext4_zero_range(struct file *file, loff_t offset,
+                            loff_t len, int mode)
+{
+        struct inode *inode = file_inode(file);
+        handle_t *handle = NULL;
+        unsigned int max_blocks;
+        loff_t new_size = 0;
+        int ret = 0;
+        int flags;
+        int partial;
+        loff_t start, end;
+        ext4_lblk_t lblk;
+        struct address_space *mapping = inode->i_mapping;
+        unsigned int blkbits = inode->i_blkbits;
+
+        trace_ext4_zero_range(inode, offset, len, mode);
+
+        /*
+         * Write out all dirty pages to avoid race conditions
+         * Then release them.
+         */
+        if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+                ret = filemap_write_and_wait_range(mapping, offset,
+                                                   offset + len - 1);
+                if (ret)
+                        return ret;
+        }
+
         /*
-         * Update only when preallocation was requested beyond
-         * the file size.
+         * Round up offset. This is not fallocate, we neet to zero out
+         * blocks, so convert interior block aligned part of the range to
+         * unwritten and possibly manually zero out unaligned parts of the
+         * range.
          */
-        if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+        start = round_up(offset, 1 << blkbits);
+        end = round_down((offset + len), 1 << blkbits);
+
+        if (start < offset || end > offset + len)
+                return -EINVAL;
+        partial = (offset + len) & ((1 << blkbits) - 1);
+
+        lblk = start >> blkbits;
+        max_blocks = (end >> blkbits);
+        if (max_blocks < lblk)
+                max_blocks = 0;
+        else
+                max_blocks -= lblk;
+
+        flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+                EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
+        if (mode & FALLOC_FL_KEEP_SIZE)
+                flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+
+        mutex_lock(&inode->i_mutex);
+
+        /*
+         * Indirect files do not support unwritten extnets
+         */
+        if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+                ret = -EOPNOTSUPP;
+                goto out_mutex;
+        }
+
+        if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+             offset + len > i_size_read(inode)) {
+                new_size = offset + len;
+                ret = inode_newsize_ok(inode, new_size);
+                if (ret)
+                        goto out_mutex;
+                /*
+                 * If we have a partial block after EOF we have to allocate
+                 * the entire block.
+                 */
+                if (partial)
+                        max_blocks += 1;
+        }
+
+        if (max_blocks > 0) {
+
+                /* Now release the pages and zero block aligned part of pages*/
+                truncate_pagecache_range(inode, start, end - 1);
+
+                /* Wait all existing dio workers, newcomers will block on i_mutex */
+                ext4_inode_block_unlocked_dio(inode);
+                inode_dio_wait(inode);
+
+                /*
+                 * Remove entire range from the extent status tree.
+                 */
+                ret = ext4_es_remove_extent(inode, lblk, max_blocks);
+                if (ret)
+                        goto out_dio;
+
+                ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags,
+                                             mode);
+                if (ret)
+                        goto out_dio;
+        }
+
+        handle = ext4_journal_start(inode, EXT4_HT_MISC, 4);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                ext4_std_error(inode->i_sb, ret);
+                goto out_dio;
+        }
+
+        inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+
+        if (new_size) {
                 if (new_size > i_size_read(inode))
                         i_size_write(inode, new_size);
                 if (new_size > EXT4_I(inode)->i_disksize)
                         ext4_update_i_disksize(inode, new_size);
         } else {
                 /*
-                 * Mark that we allocate beyond EOF so the subsequent truncate
-                 * can proceed even if the new size is the same as i_size.
-                 */
-                if (new_size > i_size_read(inode))
+                * Mark that we allocate beyond EOF so the subsequent truncate
+                * can proceed even if the new size is the same as i_size.
+                */
+                if ((offset + len) > i_size_read(inode))
                         ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
         }
 
+        ext4_mark_inode_dirty(handle, inode);
+
+        /* Zero out partial block at the edges of the range */
+        ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+
+        if (file->f_flags & O_SYNC)
+                ext4_handle_sync(handle);
+
+        ext4_journal_stop(handle);
+out_dio:
+        ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+        mutex_unlock(&inode->i_mutex);
+        return ret;
 }
 
 /*
@@ -4555,22 +4862,25 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
         struct inode *inode = file_inode(file);
         handle_t *handle;
-        loff_t new_size;
+        loff_t new_size = 0;
         unsigned int max_blocks;
         int ret = 0;
-        int ret2 = 0;
-        int retries = 0;
         int flags;
-        struct ext4_map_blocks map;
-        unsigned int credits, blkbits = inode->i_blkbits;
+        ext4_lblk_t lblk;
+        struct timespec tv;
+        unsigned int blkbits = inode->i_blkbits;
 
         /* Return error if mode is not supported */
-        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+                     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
                 return -EOPNOTSUPP;
 
         if (mode & FALLOC_FL_PUNCH_HOLE)
                 return ext4_punch_hole(inode, offset, len);
 
+        if (mode & FALLOC_FL_COLLAPSE_RANGE)
+                return ext4_collapse_range(inode, offset, len);
+
         ret = ext4_convert_inline_data(inode);
         if (ret)
                 return ret;
@@ -4582,83 +4892,66 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
         if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
                 return -EOPNOTSUPP;
 
+        if (mode & FALLOC_FL_ZERO_RANGE)
+                return ext4_zero_range(file, offset, len, mode);
+
         trace_ext4_fallocate_enter(inode, offset, len, mode);
-        map.m_lblk = offset >> blkbits;
+        lblk = offset >> blkbits;
         /*
          * We can't just convert len to max_blocks because
          * If blocksize = 4096 offset = 3072 and len = 2048
          */
         max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
-                - map.m_lblk;
-        /*
-         * credits to insert 1 extent into extent tree
-         */
-        credits = ext4_chunk_trans_blocks(inode, max_blocks);
-        mutex_lock(&inode->i_mutex);
-        ret = inode_newsize_ok(inode, (len + offset));
-        if (ret) {
-                mutex_unlock(&inode->i_mutex);
-                trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
-                return ret;
-        }
+                - lblk;
+
         flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
         if (mode & FALLOC_FL_KEEP_SIZE)
                 flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
-        /*
-         * Don't normalize the request if it can fit in one extent so
-         * that it doesn't get unnecessarily split into multiple
-         * extents.
-         */
-        if (len <= EXT_UNINIT_MAX_LEN << blkbits)
-                flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
-retry:
-        while (ret >= 0 && ret < max_blocks) {
-                map.m_lblk = map.m_lblk + ret;
-                map.m_len = max_blocks = max_blocks - ret;
-                handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
-                                            credits);
-                if (IS_ERR(handle)) {
-                        ret = PTR_ERR(handle);
-                        break;
-                }
-                ret = ext4_map_blocks(handle, inode, &map, flags);
-                if (ret <= 0) {
-#ifdef EXT4FS_DEBUG
-                        ext4_warning(inode->i_sb,
-                                     "inode #%lu: block %u: len %u: "
-                                     "ext4_ext_map_blocks returned %d",
-                                     inode->i_ino, map.m_lblk,
-                                     map.m_len, ret);
-#endif
-                        ext4_mark_inode_dirty(handle, inode);
-                        ret2 = ext4_journal_stop(handle);
-                        break;
-                }
-                if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
-                                                blkbits) >> blkbits))
-                        new_size = offset + len;
-                else
-                        new_size = ((loff_t) map.m_lblk + ret) << blkbits;
+        mutex_lock(&inode->i_mutex);
 
-                ext4_falloc_update_inode(inode, mode, new_size,
-                                         (map.m_flags & EXT4_MAP_NEW));
-                ext4_mark_inode_dirty(handle, inode);
-                if ((file->f_flags & O_SYNC) && ret >= max_blocks)
-                        ext4_handle_sync(handle);
-                ret2 = ext4_journal_stop(handle);
-                if (ret2)
-                        break;
+        if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+             offset + len > i_size_read(inode)) {
+                new_size = offset + len;
+                ret = inode_newsize_ok(inode, new_size);
+                if (ret)
+                        goto out;
         }
-        if (ret == -ENOSPC &&
-                        ext4_should_retry_alloc(inode->i_sb, &retries)) {
-                ret = 0;
-                goto retry;
+
+        ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, mode);
+        if (ret)
+                goto out;
+
+        handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+        if (IS_ERR(handle))
+                goto out;
+
+        tv = inode->i_ctime = ext4_current_time(inode);
+
+        if (new_size) {
+                if (new_size > i_size_read(inode)) {
+                        i_size_write(inode, new_size);
+                        inode->i_mtime = tv;
+                }
+                if (new_size > EXT4_I(inode)->i_disksize)
+                        ext4_update_i_disksize(inode, new_size);
+        } else {
+                /*
+                * Mark that we allocate beyond EOF so the subsequent truncate
+                * can proceed even if the new size is the same as i_size.
+                */
+                if ((offset + len) > i_size_read(inode))
+                        ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
         }
+        ext4_mark_inode_dirty(handle, inode);
+        if (file->f_flags & O_SYNC)
+                ext4_handle_sync(handle);
+
+        ext4_journal_stop(handle);
+out:
         mutex_unlock(&inode->i_mutex);
-        trace_ext4_fallocate_exit(inode, offset, max_blocks,
-                                ret > 0 ? ret2 : ret);
-        return ret > 0 ? ret2 : ret;
+        trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+        return ret;
 }
 
 /*
@@ -4869,3 +5162,304 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
         ext4_es_lru_add(inode);
         return error;
 }
+
+/*
+ * ext4_access_path:
+ * Function to access the path buffer for marking it dirty.
+ * It also checks if there are sufficient credits left in the journal handle
+ * to update path.
+ */
+static int
+ext4_access_path(handle_t *handle, struct inode *inode,
+                struct ext4_ext_path *path)
+{
+        int credits, err;
+
+        if (!ext4_handle_valid(handle))
+                return 0;
+
+        /*
+         * Check if need to extend journal credits
+         * 3 for leaf, sb, and inode plus 2 (bmap and group
+         * descriptor) for each block group; assume two block
+         * groups
+         */
+        if (handle->h_buffer_credits < 7) {
+                credits = ext4_writepage_trans_blocks(inode);
+                err = ext4_ext_truncate_extend_restart(handle, inode, credits);
+                /* EAGAIN is success */
+                if (err && err != -EAGAIN)
+                        return err;
+        }
+
+        err = ext4_ext_get_access(handle, inode, path);
+        return err;
+}
+
+/*
+ * ext4_ext_shift_path_extents:
+ * Shift the extents of a path structure lying between path[depth].p_ext
+ * and EXT_LAST_EXTENT(path[depth].p_hdr) downwards, by subtracting shift
+ * from starting block for each extent.
+ */
+static int
+ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
+                            struct inode *inode, handle_t *handle,
+                            ext4_lblk_t *start)
+{
+        int depth, err = 0;
+        struct ext4_extent *ex_start, *ex_last;
+        bool update = 0;
+        depth = path->p_depth;
+
+        while (depth >= 0) {
+                if (depth == path->p_depth) {
+                        ex_start = path[depth].p_ext;
+                        if (!ex_start)
+                                return -EIO;
+
+                        ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
+                        if (!ex_last)
+                                return -EIO;
+
+                        err = ext4_access_path(handle, inode, path + depth);
+                        if (err)
+                                goto out;
+
+                        if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
+                                update = 1;
+
+                        *start = ex_last->ee_block +
+                                ext4_ext_get_actual_len(ex_last);
+
+                        while (ex_start <= ex_last) {
+                                ex_start->ee_block -= shift;
+                                if (ex_start >
+                                        EXT_FIRST_EXTENT(path[depth].p_hdr)) {
+                                        if (ext4_ext_try_to_merge_right(inode,
+                                                path, ex_start - 1))
+                                                ex_last--;
+                                }
+                                ex_start++;
+                        }
+                        err = ext4_ext_dirty(handle, inode, path + depth);
+                        if (err)
+                                goto out;
+
+                        if (--depth < 0 || !update)
+                                break;
+                }
+
+                /* Update index too */
+                err = ext4_access_path(handle, inode, path + depth);
+                if (err)
+                        goto out;
+
+                path[depth].p_idx->ei_block -= shift;
+                err = ext4_ext_dirty(handle, inode, path + depth);
+                if (err)
+                        goto out;
+
+                /* we are done if current index is not a starting index */
+                if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr))
+                        break;
+
+                depth--;
+        }
+
+out:
+        return err;
+}
+
+/*
+ * ext4_ext_shift_extents:
+ * All the extents which lies in the range from start to the last allocated
+ * block for the file are shifted downwards by shift blocks.
+ * On success, 0 is returned, error otherwise.
+ */
+static int
+ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
+                       ext4_lblk_t start, ext4_lblk_t shift)
+{
+        struct ext4_ext_path *path;
+        int ret = 0, depth;
+        struct ext4_extent *extent;
+        ext4_lblk_t stop_block, current_block;
+        ext4_lblk_t ex_start, ex_end;
+
+        /* Let path point to the last extent */
+        path = ext4_ext_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+        if (IS_ERR(path))
+                return PTR_ERR(path);
+
+        depth = path->p_depth;
+        extent = path[depth].p_ext;
+        if (!extent) {
+                ext4_ext_drop_refs(path);
+                kfree(path);
+                return ret;
+        }
+
+        stop_block = extent->ee_block + ext4_ext_get_actual_len(extent);
+        ext4_ext_drop_refs(path);
+        kfree(path);
+
+        /* Nothing to shift, if hole is at the end of file */
+        if (start >= stop_block)
+                return ret;
+
+        /*
+         * Don't start shifting extents until we make sure the hole is big
+         * enough to accomodate the shift.
+         */
+        path = ext4_ext_find_extent(inode, start - 1, NULL, 0);
+        depth = path->p_depth;
+        extent =  path[depth].p_ext;
+        ex_start = extent->ee_block;
+        ex_end = extent->ee_block + ext4_ext_get_actual_len(extent);
+        ext4_ext_drop_refs(path);
+        kfree(path);
+
+        if ((start == ex_start && shift > ex_start) ||
+            (shift > start - ex_end))
+                return -EINVAL;
+
+        /* Its safe to start updating extents */
+        while (start < stop_block) {
+                path = ext4_ext_find_extent(inode, start, NULL, 0);
+                if (IS_ERR(path))
+                        return PTR_ERR(path);
+                depth = path->p_depth;
+                extent = path[depth].p_ext;
+                current_block = extent->ee_block;
+                if (start > current_block) {
+                        /* Hole, move to the next extent */
+                        ret = mext_next_extent(inode, path, &extent);
+                        if (ret != 0) {
+                                ext4_ext_drop_refs(path);
+                                kfree(path);
+                                if (ret == 1)
+                                        ret = 0;
+                                break;
+                        }
+                }
+                ret = ext4_ext_shift_path_extents(path, shift, inode,
+                                handle, &start);
+                ext4_ext_drop_refs(path);
+                kfree(path);
+                if (ret)
+                        break;
+        }
+
+        return ret;
+}
+
+/*
+ * ext4_collapse_range:
+ * This implements the fallocate's collapse range functionality for ext4
+ * Returns: 0 and non-zero on error.
+ */
+int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+{
+        struct super_block *sb = inode->i_sb;
+        ext4_lblk_t punch_start, punch_stop;
+        handle_t *handle;
+        unsigned int credits;
+        loff_t new_size;
+        int ret;
+
+        BUG_ON(offset + len > i_size_read(inode));
+
+        /* Collapse range works only on fs block size aligned offsets. */
+        if (offset & (EXT4_BLOCK_SIZE(sb) - 1) ||
+            len & (EXT4_BLOCK_SIZE(sb) - 1))
+                return -EINVAL;
+
+        if (!S_ISREG(inode->i_mode))
+                return -EOPNOTSUPP;
+
+        trace_ext4_collapse_range(inode, offset, len);
+
+        punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
+        punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+        /* Write out all dirty pages */
+        ret = filemap_write_and_wait_range(inode->i_mapping, offset, -1);
+        if (ret)
+                return ret;
+
+        /* Take mutex lock */
+        mutex_lock(&inode->i_mutex);
+
+        /* It's not possible punch hole on append only file */
+        if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+                ret = -EPERM;
+                goto out_mutex;
+        }
+
+        if (IS_SWAPFILE(inode)) {
+                ret = -ETXTBSY;
+                goto out_mutex;
+        }
+
+        /* Currently just for extent based files */
+        if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+                ret = -EOPNOTSUPP;
+                goto out_mutex;
+        }
+
+        truncate_pagecache_range(inode, offset, -1);
+
+        /* Wait for existing dio to complete */
+        ext4_inode_block_unlocked_dio(inode);
+        inode_dio_wait(inode);
+
+        credits = ext4_writepage_trans_blocks(inode);
+        handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                goto out_dio;
+        }
+
+        down_write(&EXT4_I(inode)->i_data_sem);
+        ext4_discard_preallocations(inode);
+
+        ret = ext4_es_remove_extent(inode, punch_start,
+                                    EXT_MAX_BLOCKS - punch_start - 1);
+        if (ret) {
+                up_write(&EXT4_I(inode)->i_data_sem);
+                goto out_stop;
+        }
+
+        ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
+        if (ret) {
+                up_write(&EXT4_I(inode)->i_data_sem);
+                goto out_stop;
+        }
+
+        ret = ext4_ext_shift_extents(inode, handle, punch_stop,
+                                     punch_stop - punch_start);
+        if (ret) {
+                up_write(&EXT4_I(inode)->i_data_sem);
+                goto out_stop;
+        }
+
+        new_size = i_size_read(inode) - len;
+        truncate_setsize(inode, new_size);
+        EXT4_I(inode)->i_disksize = new_size;
+
+        ext4_discard_preallocations(inode);
+        up_write(&EXT4_I(inode)->i_data_sem);
+        if (IS_SYNC(inode))
+                ext4_handle_sync(handle);
+        inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+        ext4_mark_inode_dirty(handle, inode);
+
+out_stop:
+        ext4_journal_stop(handle);
+out_dio:
+        ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+        mutex_unlock(&inode->i_mutex);
+        return ret;
+}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 3981ff783950..0a014a7194b2 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -184,7 +184,7 @@ static void ext4_es_print_tree(struct inode *inode)
         while (node) {
                 struct extent_status *es;
                 es = rb_entry(node, struct extent_status, rb_node);
-                printk(KERN_DEBUG " [%u/%u) %llu %llx",
+                printk(KERN_DEBUG " [%u/%u) %llu %x",
                        es->es_lblk, es->es_len,
                        ext4_es_pblock(es), ext4_es_status(es));
                 node = rb_next(node);
@@ -445,8 +445,8 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
                                 pr_warn("ES insert assertion failed for "
                                         "inode: %lu we can find an extent "
                                         "at block [%d/%d/%llu/%c], but we "
-                                        "want to add an delayed/hole extent "
-                                        "[%d/%d/%llu/%llx]\n",
+                                        "want to add a delayed/hole extent "
+                                        "[%d/%d/%llu/%x]\n",
                                         inode->i_ino, ee_block, ee_len,
                                         ee_start, ee_status ? 'u' : 'w',
                                         es->es_lblk, es->es_len,
@@ -486,8 +486,8 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
                 if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
                         pr_warn("ES insert assertion failed for inode: %lu "
                                 "can't find an extent at block %d but we want "
-                                "to add an written/unwritten extent "
-                                "[%d/%d/%llu/%llx]\n", inode->i_ino,
+                                "to add a written/unwritten extent "
+                                "[%d/%d/%llu/%x]\n", inode->i_ino,
                                 es->es_lblk, es->es_lblk, es->es_len,
                                 ext4_es_pblock(es), ext4_es_status(es));
                 }
@@ -524,7 +524,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode,
                          */
                         pr_warn("ES insert assertion failed for inode: %lu "
                                 "We can find blocks but we want to add a "
-                                "delayed/hole extent [%d/%d/%llu/%llx]\n",
+                                "delayed/hole extent [%d/%d/%llu/%x]\n",
                                 inode->i_ino, es->es_lblk, es->es_len,
                                 ext4_es_pblock(es), ext4_es_status(es));
                         return;
@@ -554,7 +554,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode,
                 if (ext4_es_is_written(es)) {
                         pr_warn("ES insert assertion failed for inode: %lu "
                                 "We can't find the block but we want to add "
-                                "an written extent [%d/%d/%llu/%llx]\n",
+                                "a written extent [%d/%d/%llu/%x]\n",
                                 inode->i_ino, es->es_lblk, es->es_len,
                                 ext4_es_pblock(es), ext4_es_status(es));
                         return;
@@ -658,8 +658,7 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 
         newes.es_lblk = lblk;
         newes.es_len = len;
-        ext4_es_store_pblock(&newes, pblk);
-        ext4_es_store_status(&newes, status);
+        ext4_es_store_pblock_status(&newes, pblk, status);
         trace_ext4_es_insert_extent(inode, &newes);
 
         ext4_es_insert_extent_check(inode, &newes);
@@ -699,8 +698,7 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
 
         newes.es_lblk = lblk;
         newes.es_len = len;
-        ext4_es_store_pblock(&newes, pblk);
-        ext4_es_store_status(&newes, status);
+        ext4_es_store_pblock_status(&newes, pblk, status);
         trace_ext4_es_cache_extent(inode, &newes);
 
         if (!len)
@@ -812,13 +810,13 @@ retry:
 
                         newes.es_lblk = end + 1;
                         newes.es_len = len2;
+                        block = 0x7FDEADBEEF;
                         if (ext4_es_is_written(&orig_es) ||
-                            ext4_es_is_unwritten(&orig_es)) {
+                            ext4_es_is_unwritten(&orig_es))
                                 block = ext4_es_pblock(&orig_es) +
                                         orig_es.es_len - len2;
-                                ext4_es_store_pblock(&newes, block);
-                        }
-                        ext4_es_store_status(&newes, ext4_es_status(&orig_es));
+                        ext4_es_store_pblock_status(&newes, block,
+                                                    ext4_es_status(&orig_es));
                         err = __es_insert_extent(inode, &newes);
                         if (err) {
                                 es->es_lblk = orig_es.es_lblk;
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 167f4ab8ecc3..f1b62a419920 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -129,6 +129,15 @@ static inline void ext4_es_store_status(struct extent_status *es,
                        (es->es_pblk & ~ES_MASK));
 }
 
+static inline void ext4_es_store_pblock_status(struct extent_status *es,
+                                               ext4_fsblk_t pb,
+                                               unsigned int status)
+{
+        es->es_pblk = (((ext4_fsblk_t)
+                        (status & EXTENT_STATUS_FLAGS) << ES_SHIFT) |
+                       (pb & ~ES_MASK));
+}
+
 extern void ext4_es_register_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_lru_add(struct inode *inode);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1a5073959f32..6db7f7db7777 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -153,7 +153,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
                 ssize_t err;
 
                 err = generic_write_sync(file, iocb->ki_pos - ret, ret);
-                if (err < 0 && ret > 0)
+                if (err < 0)
                         ret = err;
         }
         blk_finish_plug(&plug);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 24bfd7ff3049..5b0d2c7d5408 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -215,7 +215,7 @@ void ext4_evict_inode(struct inode *inode)
                         jbd2_complete_transaction(journal, commit_tid);
                         filemap_write_and_wait(&inode->i_data);
                 }
-                truncate_inode_pages(&inode->i_data, 0);
+                truncate_inode_pages_final(&inode->i_data);
 
                 WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
                 goto no_delete;
@@ -226,7 +226,7 @@ void ext4_evict_inode(struct inode *inode)
 
         if (ext4_should_order_data(inode))
                 ext4_begin_ordered_truncate(inode, 0);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
         if (is_bad_inode(inode))
@@ -504,6 +504,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 {
         struct extent_status es;
         int retval;
+        int ret = 0;
 #ifdef ES_AGGRESSIVE_TEST
         struct ext4_map_blocks orig_map;
 
@@ -515,6 +516,12 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
                   "logical block %lu\n", inode->i_ino, flags, map->m_len,
                   (unsigned long) map->m_lblk);
 
+        /*
+         * ext4_map_blocks returns an int, and m_len is an unsigned int
+         */
+        if (unlikely(map->m_len > INT_MAX))
+                map->m_len = INT_MAX;
+
         /* Lookup extent status tree firstly */
         if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
                 ext4_es_lru_add(inode);
@@ -553,7 +560,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
                                              EXT4_GET_BLOCKS_KEEP_SIZE);
         }
         if (retval > 0) {
-                int ret;
                 unsigned int status;
 
                 if (unlikely(retval != map->m_len)) {
@@ -580,7 +586,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 
 found:
         if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-                int ret = check_block_validity(inode, map);
+                ret = check_block_validity(inode, map);
                 if (ret != 0)
                         return ret;
         }
@@ -597,7 +603,13 @@ found:
          * with buffer head unmapped.
          */
         if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
-                return retval;
+                /*
+                 * If we need to convert extent to unwritten
+                 * we continue and do the actual work in
+                 * ext4_ext_map_blocks()
+                 */
+                if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
+                        return retval;
 
         /*
          * Here we clear m_flags because after allocating an new extent,
@@ -653,7 +665,6 @@ found:
                 ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
 
         if (retval > 0) {
-                int ret;
                 unsigned int status;
 
                 if (unlikely(retval != map->m_len)) {
@@ -688,7 +699,7 @@ found:
 has_zeroout:
         up_write((&EXT4_I(inode)->i_data_sem));
         if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-                int ret = check_block_validity(inode, map);
+                ret = check_block_validity(inode, map);
                 if (ret != 0)
                         return ret;
         }
@@ -3313,33 +3324,13 @@ void ext4_set_aops(struct inode *inode)
 }
 
 /*
- * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
- * up to the end of the block which corresponds to `from'.
- * This required during truncate. We need to physically zero the tail end
- * of that block so it doesn't yield old data if the file is later grown.
- */
-int ext4_block_truncate_page(handle_t *handle,
-                struct address_space *mapping, loff_t from)
-{
-        unsigned offset = from & (PAGE_CACHE_SIZE-1);
-        unsigned length;
-        unsigned blocksize;
-        struct inode *inode = mapping->host;
-
-        blocksize = inode->i_sb->s_blocksize;
-        length = blocksize - (offset & (blocksize - 1));
-
-        return ext4_block_zero_page_range(handle, mapping, from, length);
-}
-
-/*
  * ext4_block_zero_page_range() zeros out a mapping of length 'length'
  * starting from file offset 'from'.  The range to be zero'd must
  * be contained with in one block.  If the specified range exceeds
  * the end of the block it will be shortened to end of the block
  * that cooresponds to 'from'
  */
-int ext4_block_zero_page_range(handle_t *handle,
+static int ext4_block_zero_page_range(handle_t *handle,
                 struct address_space *mapping, loff_t from, loff_t length)
 {
         ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
@@ -3429,6 +3420,26 @@ unlock:
         return err;
 }
 
+/*
+ * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
+ * up to the end of the block which corresponds to `from'.
+ * This required during truncate. We need to physically zero the tail end
+ * of that block so it doesn't yield old data if the file is later grown.
+ */
+int ext4_block_truncate_page(handle_t *handle,
+                struct address_space *mapping, loff_t from)
+{
+        unsigned offset = from & (PAGE_CACHE_SIZE-1);
+        unsigned length;
+        unsigned blocksize;
+        struct inode *inode = mapping->host;
+
+        blocksize = inode->i_sb->s_blocksize;
+        length = blocksize - (offset & (blocksize - 1));
+
+        return ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
 int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
                              loff_t lstart, loff_t length)
 {
@@ -3502,7 +3513,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
         if (!S_ISREG(inode->i_mode))
                 return -EOPNOTSUPP;
 
-        trace_ext4_punch_hole(inode, offset, length);
+        trace_ext4_punch_hole(inode, offset, length, 0);
 
         /*
          * Write out all dirty pages to avoid race conditions
@@ -3609,6 +3620,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
         up_write(&EXT4_I(inode)->i_data_sem);
         if (IS_SYNC(inode))
                 ext4_handle_sync(handle);
+
+        /* Now release the pages again to reduce race window */
+        if (last_block_offset > first_block_offset)
+                truncate_pagecache_range(inode, first_block_offset,
+                                         last_block_offset);
+
         inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
         ext4_mark_inode_dirty(handle, inode);
 out_stop:
@@ -3682,7 +3699,7 @@ void ext4_truncate(struct inode *inode)
 
         /*
          * There is a possibility that we're either freeing the inode
-         * or it completely new indode. In those cases we might not
+         * or it's a completely new inode. In those cases we might not
          * have i_mutex locked because it's not necessary.
          */
         if (!(inode->i_state & (I_NEW|I_FREEING)))
@@ -3934,8 +3951,8 @@ void ext4_set_inode_flags(struct inode *inode)
                 new_fl |= S_NOATIME;
         if (flags & EXT4_DIRSYNC_FL)
                 new_fl |= S_DIRSYNC;
-        set_mask_bits(&inode->i_flags,
-                      S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
+        inode_set_flags(inode, new_fl,
+                        S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4154,11 +4171,13 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
         EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
         EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
 
-        inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
-        if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
-                if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
-                        inode->i_version |=
-                        (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+        if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+                inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+                if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+                        if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+                                inode->i_version |=
+                    (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+                }
         }
 
         ret = 0;
@@ -4328,8 +4347,7 @@ static int ext4_do_update_inode(handle_t *handle,
                 goto out_brelse;
         raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
         raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
-        if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
-            cpu_to_le32(EXT4_OS_HURD))
+        if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
                 raw_inode->i_file_acl_high =
                         cpu_to_le16(ei->i_file_acl >> 32);
         raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
@@ -4374,12 +4392,15 @@ static int ext4_do_update_inode(handle_t *handle,
                         raw_inode->i_block[block] = ei->i_data[block];
         }
 
-        raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
-        if (ei->i_extra_isize) {
-                if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
-                        raw_inode->i_version_hi =
-                        cpu_to_le32(inode->i_version >> 32);
-                raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
+        if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+                raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+                if (ei->i_extra_isize) {
+                        if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+                                raw_inode->i_version_hi =
+                                        cpu_to_le32(inode->i_version >> 32);
+                        raw_inode->i_extra_isize =
+                                cpu_to_le16(ei->i_extra_isize);
+                }
         }
 
         ext4_inode_csum_set(inode, raw_inode, ei);
@@ -4446,7 +4467,12 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
                         return -EIO;
                 }
 
-                if (wbc->sync_mode != WB_SYNC_ALL)
+                /*
+                 * No need to force transaction in WB_SYNC_NONE mode. Also
+                 * ext4_sync_fs() will force the commit after everything is
+                 * written.
+                 */
+                if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
                         return 0;
 
                 err = ext4_force_commit(inode->i_sb);
@@ -4456,7 +4482,11 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
                 err = __ext4_get_inode_loc(inode, &iloc, 0);
                 if (err)
                         return err;
-                if (wbc->sync_mode == WB_SYNC_ALL)
+                /*
+                 * sync(2) will flush the whole buffer cache. No need to do
+                 * it here separately for each inode.
+                 */
+                if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
                         sync_dirty_buffer(iloc.bh);
                 if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
                         EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index a2a837f00407..0f2252ec274d 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -104,21 +104,15 @@ static long swap_inode_boot_loader(struct super_block *sb,
         struct ext4_inode_info *ei_bl;
         struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-        if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
-                err = -EINVAL;
-                goto swap_boot_out;
-        }
+        if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode))
+                return -EINVAL;
 
-        if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
-                err = -EPERM;
-                goto swap_boot_out;
-        }
+        if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN))
+                return -EPERM;
 
         inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
-        if (IS_ERR(inode_bl)) {
-                err = PTR_ERR(inode_bl);
-                goto swap_boot_out;
-        }
+        if (IS_ERR(inode_bl))
+                return PTR_ERR(inode_bl);
         ei_bl = EXT4_I(inode_bl);
 
         filemap_flush(inode->i_mapping);
@@ -193,20 +187,14 @@ static long swap_inode_boot_loader(struct super_block *sb,
                         ext4_mark_inode_dirty(handle, inode);
                 }
         }
-
         ext4_journal_stop(handle);
-
         ext4_double_up_write_data_sem(inode, inode_bl);
 
 journal_err_out:
         ext4_inode_resume_unlocked_dio(inode);
         ext4_inode_resume_unlocked_dio(inode_bl);
-
         unlock_two_nondirectories(inode, inode_bl);
-
         iput(inode_bl);
-
-swap_boot_out:
         return err;
 }
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 04a5c7504be9..a888cac76e9c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1808,6 +1808,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
         ext4_lock_group(ac->ac_sb, group);
         max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
                              ac->ac_g_ex.fe_len, &ex);
+        ex.fe_logical = 0xDEADFA11; /* debug value */
 
         if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
                 ext4_fsblk_t start;
@@ -1936,7 +1937,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
                          */
                         break;
                 }
-
+                ex.fe_logical = 0xDEADC0DE; /* debug value */
                 ext4_mb_measure_extent(ac, &ex, e4b);
 
                 i += ex.fe_len;
@@ -1977,6 +1978,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
                         max = mb_find_extent(e4b, i, sbi->s_stripe, &ex);
                         if (max >= sbi->s_stripe) {
                                 ac->ac_found++;
+                                ex.fe_logical = 0xDEADF00D; /* debug value */
                                 ac->ac_b_ex = ex;
                                 ext4_mb_use_best_found(ac, e4b);
                                 break;
@@ -4006,8 +4008,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
                         (unsigned long)ac->ac_b_ex.fe_len,
                         (unsigned long)ac->ac_b_ex.fe_logical,
                         (int)ac->ac_criteria);
-        ext4_msg(ac->ac_sb, KERN_ERR, "%lu scanned, %d found",
-                 ac->ac_ex_scanned, ac->ac_found);
+        ext4_msg(ac->ac_sb, KERN_ERR, "%d found", ac->ac_found);
         ext4_msg(ac->ac_sb, KERN_ERR, "groups: ");
         ngroups = ext4_get_groups_count(sb);
         for (i = 0; i < ngroups; i++) {
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 08481ee84cd5..d634e183b4d4 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -48,7 +48,7 @@ extern ushort ext4_mballoc_debug;
                 }                                                       \
         } while (0)
 #else
-#define mb_debug(n, fmt, a...)
+#define mb_debug(n, fmt, a...)          no_printk(fmt, ## a)
 #endif
 
 #define EXT4_MB_HISTORY_ALLOC           1       /* allocation */
@@ -175,8 +175,6 @@ struct ext4_allocation_context {
         /* copy of the best found extent taken before preallocation efforts */
         struct ext4_free_extent ac_f_ex;
 
-        /* number of iterations done. we have to track to limit searching */
-        unsigned long ac_ex_scanned;
         __u16 ac_groups_scanned;
         __u16 ac_found;
         __u16 ac_tail;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 773b503bd18c..58ee7dc87669 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -76,7 +76,7 @@ copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
  * ext4_ext_path structure refers to the last extent, or a negative error
  * value on failure.
  */
-static int
+int
 mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
                       struct ext4_extent **extent)
 {
@@ -861,8 +861,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
                         }
                         if (!buffer_mapped(bh)) {
                                 zero_user(page, block_start, blocksize);
-                                if (!err)
-                                        set_buffer_uptodate(bh);
+                                set_buffer_uptodate(bh);
                                 continue;
                         }
                 }
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index d050e043e884..1cb84f78909e 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3000,6 +3000,154 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
         return ext4_get_first_inline_block(inode, parent_de, retval);
 }
 
+struct ext4_renament {
+        struct inode *dir;
+        struct dentry *dentry;
+        struct inode *inode;
+        bool is_dir;
+        int dir_nlink_delta;
+
+        /* entry for "dentry" */
+        struct buffer_head *bh;
+        struct ext4_dir_entry_2 *de;
+        int inlined;
+
+        /* entry for ".." in inode if it's a directory */
+        struct buffer_head *dir_bh;
+        struct ext4_dir_entry_2 *parent_de;
+        int dir_inlined;
+};
+
+static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent)
+{
+        int retval;
+
+        ent->dir_bh = ext4_get_first_dir_block(handle, ent->inode,
+                                              &retval, &ent->parent_de,
+                                              &ent->dir_inlined);
+        if (!ent->dir_bh)
+                return retval;
+        if (le32_to_cpu(ent->parent_de->inode) != ent->dir->i_ino)
+                return -EIO;
+        BUFFER_TRACE(ent->dir_bh, "get_write_access");
+        return ext4_journal_get_write_access(handle, ent->dir_bh);
+}
+
+static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent,
+                                  unsigned dir_ino)
+{
+        int retval;
+
+        ent->parent_de->inode = cpu_to_le32(dir_ino);
+        BUFFER_TRACE(ent->dir_bh, "call ext4_handle_dirty_metadata");
+        if (!ent->dir_inlined) {
+                if (is_dx(ent->inode)) {
+                        retval = ext4_handle_dirty_dx_node(handle,
+                                                           ent->inode,
+                                                           ent->dir_bh);
+                } else {
+                        retval = ext4_handle_dirty_dirent_node(handle,
+                                                               ent->inode,
+                                                               ent->dir_bh);
+                }
+        } else {
+                retval = ext4_mark_inode_dirty(handle, ent->inode);
+        }
+        if (retval) {
+                ext4_std_error(ent->dir->i_sb, retval);
+                return retval;
+        }
+        return 0;
+}
+
+static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
+                       unsigned ino, unsigned file_type)
+{
+        int retval;
+
+        BUFFER_TRACE(ent->bh, "get write access");
+        retval = ext4_journal_get_write_access(handle, ent->bh);
+        if (retval)
+                return retval;
+        ent->de->inode = cpu_to_le32(ino);
+        if (EXT4_HAS_INCOMPAT_FEATURE(ent->dir->i_sb,
+                                      EXT4_FEATURE_INCOMPAT_FILETYPE))
+                ent->de->file_type = file_type;
+        ent->dir->i_version++;
+        ent->dir->i_ctime = ent->dir->i_mtime =
+                ext4_current_time(ent->dir);
+        ext4_mark_inode_dirty(handle, ent->dir);
+        BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
+        if (!ent->inlined) {
+                retval = ext4_handle_dirty_dirent_node(handle,
+                                                       ent->dir, ent->bh);
+                if (unlikely(retval)) {
+                        ext4_std_error(ent->dir->i_sb, retval);
+                        return retval;
+                }
+        }
+        brelse(ent->bh);
+        ent->bh = NULL;
+
+        return 0;
+}
+
+static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
+                                  const struct qstr *d_name)
+{
+        int retval = -ENOENT;
+        struct buffer_head *bh;
+        struct ext4_dir_entry_2 *de;
+
+        bh = ext4_find_entry(dir, d_name, &de, NULL);
+        if (bh) {
+                retval = ext4_delete_entry(handle, dir, de, bh);
+                brelse(bh);
+        }
+        return retval;
+}
+
+static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent)
+{
+        int retval;
+        /*
+         * ent->de could have moved from under us during htree split, so make
+         * sure that we are deleting the right entry.  We might also be pointing
+         * to a stale entry in the unused part of ent->bh so just checking inum
+         * and the name isn't enough.
+         */
+        if (le32_to_cpu(ent->de->inode) != ent->inode->i_ino ||
+            ent->de->name_len != ent->dentry->d_name.len ||
+            strncmp(ent->de->name, ent->dentry->d_name.name,
+                    ent->de->name_len)) {
+                retval = ext4_find_delete_entry(handle, ent->dir,
+                                                &ent->dentry->d_name);
+        } else {
+                retval = ext4_delete_entry(handle, ent->dir, ent->de, ent->bh);
+                if (retval == -ENOENT) {
+                        retval = ext4_find_delete_entry(handle, ent->dir,
+                                                        &ent->dentry->d_name);
+                }
+        }
+
+        if (retval) {
+                ext4_warning(ent->dir->i_sb,
+                                "Deleting old file (%lu), %d, error=%d",
+                                ent->dir->i_ino, ent->dir->i_nlink, retval);
+        }
+}
+
+static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
+{
+        if (ent->dir_nlink_delta) {
+                if (ent->dir_nlink_delta == -1)
+                        ext4_dec_count(handle, ent->dir);
+                else
+                        ext4_inc_count(handle, ent->dir);
+                ext4_mark_inode_dirty(handle, ent->dir);
+        }
+}
+
 /*
  * Anybody can rename anything with this: the permission checks are left to the
  * higher-level routines.
@@ -3012,198 +3160,267 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
                        struct inode *new_dir, struct dentry *new_dentry)
 {
         handle_t *handle = NULL;
-        struct inode *old_inode, *new_inode;
-        struct buffer_head *old_bh, *new_bh, *dir_bh;
-        struct ext4_dir_entry_2 *old_de, *new_de;
+        struct ext4_renament old = {
+                .dir = old_dir,
+                .dentry = old_dentry,
+                .inode = old_dentry->d_inode,
+        };
+        struct ext4_renament new = {
+                .dir = new_dir,
+                .dentry = new_dentry,
+                .inode = new_dentry->d_inode,
+        };
         int retval;
-        int inlined = 0, new_inlined = 0;
-        struct ext4_dir_entry_2 *parent_de;
 
-        dquot_initialize(old_dir);
-        dquot_initialize(new_dir);
-
-        old_bh = new_bh = dir_bh = NULL;
+        dquot_initialize(old.dir);
+        dquot_initialize(new.dir);
 
         /* Initialize quotas before so that eventual writes go
          * in separate transaction */
-        if (new_dentry->d_inode)
-                dquot_initialize(new_dentry->d_inode);
+        if (new.inode)
+                dquot_initialize(new.inode);
 
-        old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de, NULL);
+        old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
         /*
          *  Check for inode number is _not_ due to possible IO errors.
          *  We might rmdir the source, keep it as pwd of some process
          *  and merrily kill the link to whatever was created under the
          *  same name. Goodbye sticky bit ;-<
          */
-        old_inode = old_dentry->d_inode;
         retval = -ENOENT;
-        if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino)
+        if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
                 goto end_rename;
 
-        new_inode = new_dentry->d_inode;
-        new_bh = ext4_find_entry(new_dir, &new_dentry->d_name,
-                                 &new_de, &new_inlined);
-        if (new_bh) {
-                if (!new_inode) {
-                        brelse(new_bh);
-                        new_bh = NULL;
+        new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
+                                 &new.de, &new.inlined);
+        if (new.bh) {
+                if (!new.inode) {
+                        brelse(new.bh);
+                        new.bh = NULL;
                 }
         }
-        if (new_inode && !test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC))
-                ext4_alloc_da_blocks(old_inode);
+        if (new.inode && !test_opt(new.dir->i_sb, NO_AUTO_DA_ALLOC))
+                ext4_alloc_da_blocks(old.inode);
 
-        handle = ext4_journal_start(old_dir, EXT4_HT_DIR,
-                (2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
+        handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
+                (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
                  EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
         if (IS_ERR(handle))
                 return PTR_ERR(handle);
 
-        if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
+        if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
                 ext4_handle_sync(handle);
 
-        if (S_ISDIR(old_inode->i_mode)) {
-                if (new_inode) {
+        if (S_ISDIR(old.inode->i_mode)) {
+                if (new.inode) {
                         retval = -ENOTEMPTY;
-                        if (!empty_dir(new_inode))
+                        if (!empty_dir(new.inode))
+                                goto end_rename;
+                } else {
+                        retval = -EMLINK;
+                        if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir))
                                 goto end_rename;
                 }
-                retval = -EIO;
-                dir_bh = ext4_get_first_dir_block(handle, old_inode,
-                                                  &retval, &parent_de,
-                                                  &inlined);
-                if (!dir_bh)
-                        goto end_rename;
-                if (le32_to_cpu(parent_de->inode) != old_dir->i_ino)
-                        goto end_rename;
-                retval = -EMLINK;
-                if (!new_inode && new_dir != old_dir &&
-                    EXT4_DIR_LINK_MAX(new_dir))
-                        goto end_rename;
-                BUFFER_TRACE(dir_bh, "get_write_access");
-                retval = ext4_journal_get_write_access(handle, dir_bh);
+                retval = ext4_rename_dir_prepare(handle, &old);
                 if (retval)
                         goto end_rename;
         }
-        if (!new_bh) {
-                retval = ext4_add_entry(handle, new_dentry, old_inode);
+        if (!new.bh) {
+                retval = ext4_add_entry(handle, new.dentry, old.inode);
                 if (retval)
                         goto end_rename;
         } else {
-                BUFFER_TRACE(new_bh, "get write access");
-                retval = ext4_journal_get_write_access(handle, new_bh);
+                retval = ext4_setent(handle, &new,
+                                     old.inode->i_ino, old.de->file_type);
                 if (retval)
                         goto end_rename;
-                new_de->inode = cpu_to_le32(old_inode->i_ino);
-                if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
-                                              EXT4_FEATURE_INCOMPAT_FILETYPE))
-                        new_de->file_type = old_de->file_type;
-                new_dir->i_version++;
-                new_dir->i_ctime = new_dir->i_mtime =
-                                        ext4_current_time(new_dir);
-                ext4_mark_inode_dirty(handle, new_dir);
-                BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
-                if (!new_inlined) {
-                        retval = ext4_handle_dirty_dirent_node(handle,
-                                                               new_dir, new_bh);
-                        if (unlikely(retval)) {
-                                ext4_std_error(new_dir->i_sb, retval);
-                                goto end_rename;
-                        }
-                }
-                brelse(new_bh);
-                new_bh = NULL;
         }
 
         /*
          * Like most other Unix systems, set the ctime for inodes on a
          * rename.
          */
-        old_inode->i_ctime = ext4_current_time(old_inode);
-        ext4_mark_inode_dirty(handle, old_inode);
+        old.inode->i_ctime = ext4_current_time(old.inode);
+        ext4_mark_inode_dirty(handle, old.inode);
 
         /*
          * ok, that's it
          */
-        if (le32_to_cpu(old_de->inode) != old_inode->i_ino ||
-            old_de->name_len != old_dentry->d_name.len ||
-            strncmp(old_de->name, old_dentry->d_name.name, old_de->name_len) ||
-            (retval = ext4_delete_entry(handle, old_dir,
-                                        old_de, old_bh)) == -ENOENT) {
-                /* old_de could have moved from under us during htree split, so
-                 * make sure that we are deleting the right entry.  We might
-                 * also be pointing to a stale entry in the unused part of
-                 * old_bh so just checking inum and the name isn't enough. */
-                struct buffer_head *old_bh2;
-                struct ext4_dir_entry_2 *old_de2;
-
-                old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name,
-                                          &old_de2, NULL);
-                if (old_bh2) {
-                        retval = ext4_delete_entry(handle, old_dir,
-                                                   old_de2, old_bh2);
-                        brelse(old_bh2);
-                }
+        ext4_rename_delete(handle, &old);
+
+        if (new.inode) {
+                ext4_dec_count(handle, new.inode);
+                new.inode->i_ctime = ext4_current_time(new.inode);
         }
-        if (retval) {
-                ext4_warning(old_dir->i_sb,
-                                "Deleting old file (%lu), %d, error=%d",
-                                old_dir->i_ino, old_dir->i_nlink, retval);
-        }
-
-        if (new_inode) {
-                ext4_dec_count(handle, new_inode);
-                new_inode->i_ctime = ext4_current_time(new_inode);
-        }
-        old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir);
-        ext4_update_dx_flag(old_dir);
-        if (dir_bh) {
-                parent_de->inode = cpu_to_le32(new_dir->i_ino);
-                BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-                if (!inlined) {
-                        if (is_dx(old_inode)) {
-                                retval = ext4_handle_dirty_dx_node(handle,
-                                                                   old_inode,
-                                                                   dir_bh);
-                        } else {
-                                retval = ext4_handle_dirty_dirent_node(handle,
-                                                        old_inode, dir_bh);
-                        }
-                } else {
-                        retval = ext4_mark_inode_dirty(handle, old_inode);
-                }
-                if (retval) {
-                        ext4_std_error(old_dir->i_sb, retval);
+        old.dir->i_ctime = old.dir->i_mtime = ext4_current_time(old.dir);
+        ext4_update_dx_flag(old.dir);
+        if (old.dir_bh) {
+                retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
+                if (retval)
                         goto end_rename;
-                }
-                ext4_dec_count(handle, old_dir);
-                if (new_inode) {
+
+                ext4_dec_count(handle, old.dir);
+                if (new.inode) {
                         /* checked empty_dir above, can't have another parent,
                          * ext4_dec_count() won't work for many-linked dirs */
-                        clear_nlink(new_inode);
+                        clear_nlink(new.inode);
                 } else {
-                        ext4_inc_count(handle, new_dir);
-                        ext4_update_dx_flag(new_dir);
-                        ext4_mark_inode_dirty(handle, new_dir);
+                        ext4_inc_count(handle, new.dir);
+                        ext4_update_dx_flag(new.dir);
+                        ext4_mark_inode_dirty(handle, new.dir);
                 }
         }
-        ext4_mark_inode_dirty(handle, old_dir);
-        if (new_inode) {
-                ext4_mark_inode_dirty(handle, new_inode);
-                if (!new_inode->i_nlink)
-                        ext4_orphan_add(handle, new_inode);
+        ext4_mark_inode_dirty(handle, old.dir);
+        if (new.inode) {
+                ext4_mark_inode_dirty(handle, new.inode);
+                if (!new.inode->i_nlink)
+                        ext4_orphan_add(handle, new.inode);
         }
         retval = 0;
 
 end_rename:
-        brelse(dir_bh);
-        brelse(old_bh);
-        brelse(new_bh);
+        brelse(old.dir_bh);
+        brelse(old.bh);
+        brelse(new.bh);
         if (handle)
                 ext4_journal_stop(handle);
         return retval;
 }
 
+static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
+                             struct inode *new_dir, struct dentry *new_dentry)
+{
+        handle_t *handle = NULL;
+        struct ext4_renament old = {
+                .dir = old_dir,
+                .dentry = old_dentry,
+                .inode = old_dentry->d_inode,
+        };
+        struct ext4_renament new = {
+                .dir = new_dir,
+                .dentry = new_dentry,
+                .inode = new_dentry->d_inode,
+        };
+        u8 new_file_type;
+        int retval;
+
+        dquot_initialize(old.dir);
+        dquot_initialize(new.dir);
+
+        old.bh = ext4_find_entry(old.dir, &old.dentry->d_name,
+                                 &old.de, &old.inlined);
+        /*
+         *  Check for inode number is _not_ due to possible IO errors.
+         *  We might rmdir the source, keep it as pwd of some process
+         *  and merrily kill the link to whatever was created under the
+         *  same name. Goodbye sticky bit ;-<
+         */
+        retval = -ENOENT;
+        if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
+                goto end_rename;
+
+        new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
+                                 &new.de, &new.inlined);
+
+        /* RENAME_EXCHANGE case: old *and* new must both exist */
+        if (!new.bh || le32_to_cpu(new.de->inode) != new.inode->i_ino)
+                goto end_rename;
+
+        handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
+                (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
+                 2 * EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
+        if (IS_ERR(handle))
+                return PTR_ERR(handle);
+
+        if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
+                ext4_handle_sync(handle);
+
+        if (S_ISDIR(old.inode->i_mode)) {
+                old.is_dir = true;
+                retval = ext4_rename_dir_prepare(handle, &old);
+                if (retval)
+                        goto end_rename;
+        }
+        if (S_ISDIR(new.inode->i_mode)) {
+                new.is_dir = true;
+                retval = ext4_rename_dir_prepare(handle, &new);
+                if (retval)
+                        goto end_rename;
+        }
+
+        /*
+         * Other than the special case of overwriting a directory, parents'
+         * nlink only needs to be modified if this is a cross directory rename.
+         */
+        if (old.dir != new.dir && old.is_dir != new.is_dir) {
+                old.dir_nlink_delta = old.is_dir ? -1 : 1;
+                new.dir_nlink_delta = -old.dir_nlink_delta;
+                retval = -EMLINK;
+                if ((old.dir_nlink_delta > 0 && EXT4_DIR_LINK_MAX(old.dir)) ||
+                    (new.dir_nlink_delta > 0 && EXT4_DIR_LINK_MAX(new.dir)))
+                        goto end_rename;
+        }
+
+        new_file_type = new.de->file_type;
+        retval = ext4_setent(handle, &new, old.inode->i_ino, old.de->file_type);
+        if (retval)
+                goto end_rename;
+
+        retval = ext4_setent(handle, &old, new.inode->i_ino, new_file_type);
+        if (retval)
+                goto end_rename;
+
+        /*
+         * Like most other Unix systems, set the ctime for inodes on a
+         * rename.
+         */
+        old.inode->i_ctime = ext4_current_time(old.inode);
+        new.inode->i_ctime = ext4_current_time(new.inode);
+        ext4_mark_inode_dirty(handle, old.inode);
+        ext4_mark_inode_dirty(handle, new.inode);
+
+        if (old.dir_bh) {
+                retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
+                if (retval)
+                        goto end_rename;
+        }
+        if (new.dir_bh) {
+                retval = ext4_rename_dir_finish(handle, &new, old.dir->i_ino);
+                if (retval)
+                        goto end_rename;
+        }
+        ext4_update_dir_count(handle, &old);
+        ext4_update_dir_count(handle, &new);
+        retval = 0;
+
+end_rename:
+        brelse(old.dir_bh);
+        brelse(new.dir_bh);
+        brelse(old.bh);
+        brelse(new.bh);
+        if (handle)
+                ext4_journal_stop(handle);
+        return retval;
+}
+
+static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
+                        struct inode *new_dir, struct dentry *new_dentry,
+                        unsigned int flags)
+{
+        if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+                return -EINVAL;
+
+        if (flags & RENAME_EXCHANGE) {
+                return ext4_cross_rename(old_dir, old_dentry,
+                                         new_dir, new_dentry);
+        }
+        /*
+         * Existence checking was done by the VFS, otherwise "RENAME_NOREPLACE"
+         * is equivalent to regular rename.
+         */
+        return ext4_rename(old_dir, old_dentry, new_dir, new_dentry);
+}
+
 /*
  * directories can handle most operations...
  */
@@ -3218,6 +3435,7 @@ const struct inode_operations ext4_dir_inode_operations = {
         .mknod          = ext4_mknod,
         .tmpfile        = ext4_tmpfile,
         .rename         = ext4_rename,
+        .rename2        = ext4_rename2,
         .setattr        = ext4_setattr,
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 710fed2377d4..f3c667091618 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -59,6 +59,7 @@ static struct kset *ext4_kset;
 static struct ext4_lazy_init *ext4_li_info;
 static struct mutex ext4_li_mtx;
 static struct ext4_features *ext4_feat;
+static int ext4_mballoc_ready;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
                              unsigned long journal_devnum);
@@ -845,6 +846,10 @@ static void ext4_put_super(struct super_block *sb)
                 invalidate_bdev(sbi->journal_bdev);
                 ext4_blkdev_remove(sbi);
         }
+        if (sbi->s_mb_cache) {
+                ext4_xattr_destroy_cache(sbi->s_mb_cache);
+                sbi->s_mb_cache = NULL;
+        }
         if (sbi->s_mmp_tsk)
                 kthread_stop(sbi->s_mmp_tsk);
         sb->s_fs_info = NULL;
@@ -940,7 +945,7 @@ static void init_once(void *foo)
         inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
         ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
                                              sizeof(struct ext4_inode_info),
@@ -3575,6 +3580,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                        "feature flags set on rev 0 fs, "
                        "running e2fsck is recommended");
 
+        if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) {
+                set_opt2(sb, HURD_COMPAT);
+                if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+                                              EXT4_FEATURE_INCOMPAT_64BIT)) {
+                        ext4_msg(sb, KERN_ERR,
+                                 "The Hurd can't support 64-bit file systems");
+                        goto failed_mount;
+                }
+        }
+
         if (IS_EXT2_SB(sb)) {
                 if (ext2_feature_set_ok(sb))
                         ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
@@ -4010,6 +4025,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
 
 no_journal:
+        if (ext4_mballoc_ready) {
+                sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id);
+                if (!sbi->s_mb_cache) {
+                        ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+                        goto failed_mount_wq;
+                }
+        }
+
         /*
          * Get the # of file system overhead blocks from the
          * superblock if present.
@@ -4835,6 +4858,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
                 }
 
                 if (*flags & MS_RDONLY) {
+                        err = sync_filesystem(sb);
+                        if (err < 0)
+                                goto restore_opts;
                         err = dquot_suspend(sb, -1);
                         if (err < 0)
                                 goto restore_opts;
@@ -5516,11 +5542,9 @@ static int __init ext4_init_fs(void)
 
         err = ext4_init_mballoc();
         if (err)
-                goto out3;
-
-        err = ext4_init_xattr();
-        if (err)
                 goto out2;
+        else
+                ext4_mballoc_ready = 1;
         err = init_inodecache();
         if (err)
                 goto out1;
@@ -5536,10 +5560,9 @@ out:
         unregister_as_ext3();
         destroy_inodecache();
 out1:
-        ext4_exit_xattr();
-out2:
+        ext4_mballoc_ready = 0;
         ext4_exit_mballoc();
-out3:
+out2:
         ext4_exit_feat_adverts();
 out4:
         if (ext4_proc_root)
@@ -5562,7 +5585,6 @@ static void __exit ext4_exit_fs(void)
         unregister_as_ext3();
         unregister_filesystem(&ext4_fs_type);
         destroy_inodecache();
-        ext4_exit_xattr();
         ext4_exit_mballoc();
         ext4_exit_feat_adverts();
         remove_proc_entry("fs/ext4", NULL);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index e175e94116ac..1f5cf5880718 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -81,7 +81,7 @@
 # define ea_bdebug(bh, fmt, ...)        no_printk(fmt, ##__VA_ARGS__)
 #endif
 
-static void ext4_xattr_cache_insert(struct buffer_head *);
+static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
 static struct buffer_head *ext4_xattr_cache_find(struct inode *,
                                                  struct ext4_xattr_header *,
                                                  struct mb_cache_entry **);
@@ -90,8 +90,6 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *,
 static int ext4_xattr_list(struct dentry *dentry, char *buffer,
                            size_t buffer_size);
 
-static struct mb_cache *ext4_xattr_cache;
-
 static const struct xattr_handler *ext4_xattr_handler_map[] = {
         [EXT4_XATTR_INDEX_USER]              = &ext4_xattr_user_handler,
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
@@ -117,6 +115,9 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
         NULL
 };
 
+#define EXT4_GET_MB_CACHE(inode)        (((struct ext4_sb_info *) \
+                                inode->i_sb->s_fs_info)->s_mb_cache)
+
 static __le32 ext4_xattr_block_csum(struct inode *inode,
                                     sector_t block_nr,
                                     struct ext4_xattr_header *hdr)
@@ -265,6 +266,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
         struct ext4_xattr_entry *entry;
         size_t size;
         int error;
+        struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
         ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
                   name_index, name, buffer, (long)buffer_size);
@@ -286,7 +288,7 @@ bad_block:
                 error = -EIO;
                 goto cleanup;
         }
-        ext4_xattr_cache_insert(bh);
+        ext4_xattr_cache_insert(ext4_mb_cache, bh);
         entry = BFIRST(bh);
         error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
         if (error == -EIO)
@@ -409,6 +411,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
         struct inode *inode = dentry->d_inode;
         struct buffer_head *bh = NULL;
         int error;
+        struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
         ea_idebug(inode, "buffer=%p, buffer_size=%ld",
                   buffer, (long)buffer_size);
@@ -430,7 +433,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
                 error = -EIO;
                 goto cleanup;
         }
-        ext4_xattr_cache_insert(bh);
+        ext4_xattr_cache_insert(ext4_mb_cache, bh);
         error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
 
 cleanup:
@@ -526,8 +529,9 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 {
         struct mb_cache_entry *ce = NULL;
         int error = 0;
+        struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
-        ce = mb_cache_entry_get(ext4_xattr_cache, bh->b_bdev, bh->b_blocknr);
+        ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
         error = ext4_journal_get_write_access(handle, bh);
         if (error)
                 goto out;
@@ -567,12 +571,13 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
                                     size_t *min_offs, void *base, int *total)
 {
         for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
-                *total += EXT4_XATTR_LEN(last->e_name_len);
                 if (!last->e_value_block && last->e_value_size) {
                         size_t offs = le16_to_cpu(last->e_value_offs);
                         if (offs < *min_offs)
                                 *min_offs = offs;
                 }
+                if (total)
+                        *total += EXT4_XATTR_LEN(last->e_name_len);
         }
         return (*min_offs - ((void *)last - base) - sizeof(__u32));
 }
@@ -745,13 +750,14 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
         struct ext4_xattr_search *s = &bs->s;
         struct mb_cache_entry *ce = NULL;
         int error = 0;
+        struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 #define header(x) ((struct ext4_xattr_header *)(x))
 
         if (i->value && i->value_len > sb->s_blocksize)
                 return -ENOSPC;
         if (s->base) {
-                ce = mb_cache_entry_get(ext4_xattr_cache, bs->bh->b_bdev,
+                ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
                                         bs->bh->b_blocknr);
                 error = ext4_journal_get_write_access(handle, bs->bh);
                 if (error)
@@ -769,7 +775,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
                                 if (!IS_LAST_ENTRY(s->first))
                                         ext4_xattr_rehash(header(s->base),
                                                           s->here);
-                                ext4_xattr_cache_insert(bs->bh);
+                                ext4_xattr_cache_insert(ext4_mb_cache,
+                                        bs->bh);
                         }
                         unlock_buffer(bs->bh);
                         if (error == -EIO)
@@ -905,7 +912,7 @@ getblk_failed:
                         memcpy(new_bh->b_data, s->base, new_bh->b_size);
                         set_buffer_uptodate(new_bh);
                         unlock_buffer(new_bh);
-                        ext4_xattr_cache_insert(new_bh);
+                        ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
                         error = ext4_handle_dirty_xattr_block(handle,
                                                               inode, new_bh);
                         if (error)
@@ -1228,7 +1235,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
         struct ext4_xattr_block_find *bs = NULL;
         char *buffer = NULL, *b_entry_name = NULL;
         size_t min_offs, free;
-        int total_ino, total_blk;
+        int total_ino;
         void *base, *start, *end;
         int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
         int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
@@ -1286,8 +1293,7 @@ retry:
                 first = BFIRST(bh);
                 end = bh->b_data + bh->b_size;
                 min_offs = end - base;
-                free = ext4_xattr_free_space(first, &min_offs, base,
-                                             &total_blk);
+                free = ext4_xattr_free_space(first, &min_offs, base, NULL);
                 if (free < new_extra_isize) {
                         if (!tried_min_extra_isize && s_min_extra_isize) {
                                 tried_min_extra_isize++;
@@ -1495,13 +1501,13 @@ ext4_xattr_put_super(struct super_block *sb)
  * Returns 0, or a negative error number on failure.
  */
 static void
-ext4_xattr_cache_insert(struct buffer_head *bh)
+ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
 {
         __u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
         struct mb_cache_entry *ce;
         int error;
 
-        ce = mb_cache_entry_alloc(ext4_xattr_cache, GFP_NOFS);
+        ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS);
         if (!ce) {
                 ea_bdebug(bh, "out of memory");
                 return;
@@ -1573,12 +1579,13 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
 {
         __u32 hash = le32_to_cpu(header->h_hash);
         struct mb_cache_entry *ce;
+        struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
         if (!header->h_hash)
                 return NULL;  /* never share */
         ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-        ce = mb_cache_entry_find_first(ext4_xattr_cache, inode->i_sb->s_bdev,
+        ce = mb_cache_entry_find_first(ext4_mb_cache, inode->i_sb->s_bdev,
                                        hash);
         while (ce) {
                 struct buffer_head *bh;
@@ -1676,19 +1683,17 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header,
 
 #undef BLOCK_HASH_SHIFT
 
-int __init
-ext4_init_xattr(void)
+#define HASH_BUCKET_BITS        10
+
+struct mb_cache *
+ext4_xattr_create_cache(char *name)
 {
-        ext4_xattr_cache = mb_cache_create("ext4_xattr", 6);
-        if (!ext4_xattr_cache)
-                return -ENOMEM;
-        return 0;
+        return mb_cache_create(name, HASH_BUCKET_BITS);
 }
 
-void
-ext4_exit_xattr(void)
+void ext4_xattr_destroy_cache(struct mb_cache *cache)
 {
-        if (ext4_xattr_cache)
-                mb_cache_destroy(ext4_xattr_cache);
-        ext4_xattr_cache = NULL;
+        if (cache)
+                mb_cache_destroy(cache);
 }
+
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 819d6398833f..29bedf5589f6 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -110,9 +110,6 @@ extern void ext4_xattr_put_super(struct super_block *);
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
                             struct ext4_inode *raw_inode, handle_t *handle);
 
-extern int __init ext4_init_xattr(void);
-extern void ext4_exit_xattr(void);
-
 extern const struct xattr_handler *ext4_xattr_handlers[];
 
 extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
@@ -124,6 +121,9 @@ extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
                                        struct ext4_xattr_info *i,
                                        struct ext4_xattr_ibody_find *is);
 
+extern struct mb_cache *ext4_xattr_create_cache(char *name);
+extern void ext4_xattr_destroy_cache(struct mb_cache *);
+
 #ifdef CONFIG_EXT4_FS_SECURITY
 extern int ext4_init_security(handle_t *handle, struct inode *inode,
                               struct inode *dir, const struct qstr *qstr);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 4d67ed736dca..28cea76d78c6 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -260,7 +260,7 @@ void f2fs_evict_inode(struct inode *inode)
         struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
         trace_f2fs_evict_inode(inode);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         if (inode->i_ino == F2FS_NODE_INO(sbi) ||
                         inode->i_ino == F2FS_META_INO(sbi))
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1a85f83abd53..856bdf994c0a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -568,6 +568,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
         struct f2fs_mount_info org_mount_opt;
         int err, active_logs;
 
+        sync_filesystem(sb);
+
         /*
          * Save the old mount options in case we
          * need to restore them.
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 854b578f6695..b3361fe2bcb5 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(fat_build_inode);
 
 static void fat_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         if (!inode->i_nlink) {
                 inode->i_size = 0;
                 fat_truncate_blocks(inode, 0);
@@ -635,6 +635,8 @@ static int fat_remount(struct super_block *sb, int *flags, char *data)
         struct msdos_sb_info *sbi = MSDOS_SB(sb);
         *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
 
+        sync_filesystem(sb);
+
         /* make sure we update state on remount. */
         new_rdonly = *flags & MS_RDONLY;
         if (new_rdonly != (sb->s_flags & MS_RDONLY)) {
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ef6866592a0f..9ead1596399a 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -272,9 +272,19 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
         case F_SETFL:
                 err = setfl(fd, filp, arg);
                 break;
+#if BITS_PER_LONG != 32
+        /* 32-bit arches must use fcntl64() */
+        case F_GETLKP:
+#endif
         case F_GETLK:
-                err = fcntl_getlk(filp, (struct flock __user *) arg);
+                err = fcntl_getlk(filp, cmd, (struct flock __user *) arg);
                 break;
+#if BITS_PER_LONG != 32
+        /* 32-bit arches must use fcntl64() */
+        case F_SETLKP:
+        case F_SETLKPW:
+#endif
+                /* Fallthrough */
         case F_SETLK:
         case F_SETLKW:
                 err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg);
@@ -388,17 +398,20 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
                 goto out1;
         
         switch (cmd) {
-                case F_GETLK64:
-                        err = fcntl_getlk64(f.file, (struct flock64 __user *) arg);
-                        break;
-                case F_SETLK64:
-                case F_SETLKW64:
-                        err = fcntl_setlk64(fd, f.file, cmd,
-                                        (struct flock64 __user *) arg);
-                        break;
-                default:
-                        err = do_fcntl(fd, cmd, arg, f.file);
-                        break;
+        case F_GETLK64:
+        case F_GETLKP:
+                err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg);
+                break;
+        case F_SETLK64:
+        case F_SETLKW64:
+        case F_SETLKP:
+        case F_SETLKPW:
+                err = fcntl_setlk64(fd, f.file, cmd,
+                                (struct flock64 __user *) arg);
+                break;
+        default:
+                err = do_fcntl(fd, cmd, arg, f.file);
+                break;
         }
 out1:
         fdput(f);
diff --git a/fs/file.c b/fs/file.c
index eb56a13dab3e..b61293badfb1 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -497,7 +497,7 @@ repeat:
         error = fd;
 #if 1
         /* Sanity check */
-        if (rcu_dereference_raw(fdt->fd[fd]) != NULL) {
+        if (rcu_access_pointer(fdt->fd[fd]) != NULL) {
                 printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
                 rcu_assign_pointer(fdt->fd[fd], NULL);
         }
diff --git a/fs/file_table.c b/fs/file_table.c
index 5b24008ea4f6..01071c4d752e 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -235,7 +235,7 @@ static void __fput(struct file *file)
          * in the file cleanup chain.
          */
         eventpoll_release(file);
-        locks_remove_flock(file);
+        locks_remove_file(file);
 
         if (unlikely(file->f_flags & FASYNC)) {
                 if (file->f_op->fasync)
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 92567d95ba6a..5797d45a78cb 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -121,6 +121,7 @@ int unregister_filesystem(struct file_system_type * fs)
 
 EXPORT_SYMBOL(unregister_filesystem);
 
+#ifdef CONFIG_SYSFS_SYSCALL
 static int fs_index(const char __user * __name)
 {
         struct file_system_type * tmp;
@@ -199,6 +200,7 @@ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2)
         }
         return retval;
 }
+#endif
 
 int __init get_filesystem_list(char *buf)
 {
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index f47df72cef17..363e3ae25f6b 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -354,7 +354,7 @@ static void vxfs_i_callback(struct rcu_head *head)
 void
 vxfs_evict_inode(struct inode *ip)
 {
-        truncate_inode_pages(&ip->i_data, 0);
+        truncate_inode_pages_final(&ip->i_data);
         clear_inode(ip);
         call_rcu(&ip->i_rcu, vxfs_i_callback);
 }
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index 25d4099a4aea..99c7f0a37af4 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -192,7 +192,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp)
  * vxfs_lookup - lookup pathname component
  * @dip:        dir in which we lookup
  * @dp:         dentry we lookup
- * @nd:         lookup nameidata
+ * @flags:      lookup flags
  *
  * Description:
  *   vxfs_lookup tries to lookup the pathname component described
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index e37eb274e492..7ca8c75d50d3 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -124,6 +124,7 @@ vxfs_statfs(struct dentry *dentry, struct kstatfs *bufp)
 
 static int vxfs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_RDONLY;
         return 0;
 }
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index d754e3cf99a8..be568b7311d6 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -89,16 +89,31 @@ static inline struct inode *wb_inode(struct list_head *head)
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
+
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+{
+        spin_lock_bh(&bdi->wb_lock);
+        if (test_bit(BDI_registered, &bdi->state))
+                mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+        spin_unlock_bh(&bdi->wb_lock);
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
                            struct wb_writeback_work *work)
 {
         trace_writeback_queue(bdi, work);
 
         spin_lock_bh(&bdi->wb_lock);
+        if (!test_bit(BDI_registered, &bdi->state)) {
+                if (work->done)
+                        complete(work->done);
+                goto out_unlock;
+        }
         list_add_tail(&work->list, &bdi->work_list);
-        spin_unlock_bh(&bdi->wb_lock);
-
         mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
+        spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -114,7 +129,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
         work = kzalloc(sizeof(*work), GFP_ATOMIC);
         if (!work) {
                 trace_writeback_nowork(bdi);
-                mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+                bdi_wakeup_thread(bdi);
                 return;
         }
 
@@ -161,7 +176,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
          * writeback as soon as there is no other work to do.
          */
         trace_writeback_wake_background(bdi);
-        mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+        bdi_wakeup_thread(bdi);
 }
 
 /*
@@ -1017,7 +1032,7 @@ void bdi_writeback_workfn(struct work_struct *work)
         current->flags |= PF_SWAPWRITE;
 
         if (likely(!current_is_workqueue_rescuer() ||
-                   list_empty(&bdi->bdi_list))) {
+                   !test_bit(BDI_registered, &bdi->state))) {
                 /*
                  * The normal path.  Keep writing back @bdi until its
                  * work_list is empty.  Note that this path is also taken
@@ -1039,10 +1054,10 @@ void bdi_writeback_workfn(struct work_struct *work)
                 trace_writeback_pages_written(pages_written);
         }
 
-        if (!list_empty(&bdi->work_list) ||
-            (wb_has_dirty_io(wb) && dirty_writeback_interval))
-                queue_delayed_work(bdi_wq, &wb->dwork,
-                        msecs_to_jiffies(dirty_writeback_interval * 10));
+        if (!list_empty(&bdi->work_list))
+                mod_delayed_work(bdi_wq, &wb->dwork, 0);
+        else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+                bdi_wakeup_thread_delayed(bdi);
 
         current->flags &= ~PF_SWAPWRITE;
 }
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index b96a49b37d66..23e363f38302 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -95,7 +95,7 @@ static ssize_t cuse_read(struct file *file, char __user *buf, size_t count,
         struct iovec iov = { .iov_base = buf, .iov_len = count };
         struct fuse_io_priv io = { .async = 0, .file = file };
 
-        return fuse_direct_io(&io, &iov, 1, count, &pos, 0);
+        return fuse_direct_io(&io, &iov, 1, count, &pos, FUSE_DIO_CUSE);
 }
 
 static ssize_t cuse_write(struct file *file, const char __user *buf,
@@ -109,7 +109,8 @@ static ssize_t cuse_write(struct file *file, const char __user *buf,
          * No locking or generic_write_checks(), the server is
          * responsible for locking and sanity checks.
          */
-        return fuse_direct_io(&io, &iov, 1, count, &pos, 1);
+        return fuse_direct_io(&io, &iov, 1, count, &pos,
+                              FUSE_DIO_WRITE | FUSE_DIO_CUSE);
 }
 
 static int cuse_open(struct inode *inode, struct file *file)
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 1d1292c581c3..5b4e035b364c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -839,6 +839,14 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr,
                           struct kstat *stat)
 {
         unsigned int blkbits;
+        struct fuse_conn *fc = get_fuse_conn(inode);
+
+        /* see the comment in fuse_change_attributes() */
+        if (fc->writeback_cache && S_ISREG(inode->i_mode)) {
+                attr->size = i_size_read(inode);
+                attr->mtime = inode->i_mtime.tv_sec;
+                attr->mtimensec = inode->i_mtime.tv_nsec;
+        }
 
         stat->dev = inode->i_sb->s_dev;
         stat->ino = attr->ino;
@@ -1477,12 +1485,16 @@ static long fuse_dir_compat_ioctl(struct file *file, unsigned int cmd,
                                  FUSE_IOCTL_COMPAT | FUSE_IOCTL_DIR);
 }
 
-static bool update_mtime(unsigned ivalid)
+static bool update_mtime(unsigned ivalid, bool trust_local_mtime)
 {
         /* Always update if mtime is explicitly set  */
         if (ivalid & ATTR_MTIME_SET)
                 return true;
 
+        /* Or if kernel i_mtime is the official one */
+        if (trust_local_mtime)
+                return true;
+
         /* If it's an open(O_TRUNC) or an ftruncate(), don't update */
         if ((ivalid & ATTR_SIZE) && (ivalid & (ATTR_OPEN | ATTR_FILE)))
                 return false;
@@ -1491,7 +1503,8 @@ static bool update_mtime(unsigned ivalid)
         return true;
 }
 
-static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg)
+static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg,
+                           bool trust_local_mtime)
 {
         unsigned ivalid = iattr->ia_valid;
 
@@ -1510,11 +1523,11 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg)
                 if (!(ivalid & ATTR_ATIME_SET))
                         arg->valid |= FATTR_ATIME_NOW;
         }
-        if ((ivalid & ATTR_MTIME) && update_mtime(ivalid)) {
+        if ((ivalid & ATTR_MTIME) && update_mtime(ivalid, trust_local_mtime)) {
                 arg->valid |= FATTR_MTIME;
                 arg->mtime = iattr->ia_mtime.tv_sec;
                 arg->mtimensec = iattr->ia_mtime.tv_nsec;
-                if (!(ivalid & ATTR_MTIME_SET))
+                if (!(ivalid & ATTR_MTIME_SET) && !trust_local_mtime)
                         arg->valid |= FATTR_MTIME_NOW;
         }
 }
@@ -1563,6 +1576,63 @@ void fuse_release_nowrite(struct inode *inode)
         spin_unlock(&fc->lock);
 }
 
+static void fuse_setattr_fill(struct fuse_conn *fc, struct fuse_req *req,
+                              struct inode *inode,
+                              struct fuse_setattr_in *inarg_p,
+                              struct fuse_attr_out *outarg_p)
+{
+        req->in.h.opcode = FUSE_SETATTR;
+        req->in.h.nodeid = get_node_id(inode);
+        req->in.numargs = 1;
+        req->in.args[0].size = sizeof(*inarg_p);
+        req->in.args[0].value = inarg_p;
+        req->out.numargs = 1;
+        if (fc->minor < 9)
+                req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
+        else
+                req->out.args[0].size = sizeof(*outarg_p);
+        req->out.args[0].value = outarg_p;
+}
+
+/*
+ * Flush inode->i_mtime to the server
+ */
+int fuse_flush_mtime(struct file *file, bool nofail)
+{
+        struct inode *inode = file->f_mapping->host;
+        struct fuse_inode *fi = get_fuse_inode(inode);
+        struct fuse_conn *fc = get_fuse_conn(inode);
+        struct fuse_req *req = NULL;
+        struct fuse_setattr_in inarg;
+        struct fuse_attr_out outarg;
+        int err;
+
+        if (nofail) {
+                req = fuse_get_req_nofail_nopages(fc, file);
+        } else {
+                req = fuse_get_req_nopages(fc);
+                if (IS_ERR(req))
+                        return PTR_ERR(req);
+        }
+
+        memset(&inarg, 0, sizeof(inarg));
+        memset(&outarg, 0, sizeof(outarg));
+
+        inarg.valid |= FATTR_MTIME;
+        inarg.mtime = inode->i_mtime.tv_sec;
+        inarg.mtimensec = inode->i_mtime.tv_nsec;
+
+        fuse_setattr_fill(fc, req, inode, &inarg, &outarg);
+        fuse_request_send(fc, req);
+        err = req->out.h.error;
+        fuse_put_request(fc, req);
+
+        if (!err)
+                clear_bit(FUSE_I_MTIME_DIRTY, &fi->state);
+
+        return err;
+}
+
 /*
  * Set attributes, and at the same time refresh them.
  *
@@ -1580,8 +1650,10 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
         struct fuse_setattr_in inarg;
         struct fuse_attr_out outarg;
         bool is_truncate = false;
+        bool is_wb = fc->writeback_cache;
         loff_t oldsize;
         int err;
+        bool trust_local_mtime = is_wb && S_ISREG(inode->i_mode);
 
         if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
                 attr->ia_valid |= ATTR_FORCE;
@@ -1610,7 +1682,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
 
         memset(&inarg, 0, sizeof(inarg));
         memset(&outarg, 0, sizeof(outarg));
-        iattr_to_fattr(attr, &inarg);
+        iattr_to_fattr(attr, &inarg, trust_local_mtime);
         if (file) {
                 struct fuse_file *ff = file->private_data;
                 inarg.valid |= FATTR_FH;
@@ -1621,17 +1693,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
                 inarg.valid |= FATTR_LOCKOWNER;
                 inarg.lock_owner = fuse_lock_owner_id(fc, current->files);
         }
-        req->in.h.opcode = FUSE_SETATTR;
-        req->in.h.nodeid = get_node_id(inode);
-        req->in.numargs = 1;
-        req->in.args[0].size = sizeof(inarg);
-        req->in.args[0].value = &inarg;
-        req->out.numargs = 1;
-        if (fc->minor < 9)
-                req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
-        else
-                req->out.args[0].size = sizeof(outarg);
-        req->out.args[0].value = &outarg;
+        fuse_setattr_fill(fc, req, inode, &inarg, &outarg);
         fuse_request_send(fc, req);
         err = req->out.h.error;
         fuse_put_request(fc, req);
@@ -1648,10 +1710,18 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
         }
 
         spin_lock(&fc->lock);
+        /* the kernel maintains i_mtime locally */
+        if (trust_local_mtime && (attr->ia_valid & ATTR_MTIME)) {
+                inode->i_mtime = attr->ia_mtime;
+                clear_bit(FUSE_I_MTIME_DIRTY, &fi->state);
+        }
+
         fuse_change_attributes_common(inode, &outarg.attr,
                                       attr_timeout(&outarg));
         oldsize = inode->i_size;
-        i_size_write(inode, outarg.attr.size);
+        /* see the comment in fuse_change_attributes() */
+        if (!is_wb || is_truncate || !S_ISREG(inode->i_mode))
+                i_size_write(inode, outarg.attr.size);
 
         if (is_truncate) {
                 /* NOTE: this may release/reacquire fc->lock */
@@ -1663,7 +1733,8 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
          * Only call invalidate_inode_pages2() after removing
          * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
          */
-        if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
+        if ((is_truncate || !is_wb) &&
+            S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
                 truncate_pagecache(inode, outarg.attr.size);
                 invalidate_inode_pages2(inode->i_mapping);
         }
@@ -1875,6 +1946,17 @@ static int fuse_removexattr(struct dentry *entry, const char *name)
         return err;
 }
 
+static int fuse_update_time(struct inode *inode, struct timespec *now,
+                            int flags)
+{
+        if (flags & S_MTIME) {
+                inode->i_mtime = *now;
+                set_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state);
+                BUG_ON(!S_ISREG(inode->i_mode));
+        }
+        return 0;
+}
+
 static const struct inode_operations fuse_dir_inode_operations = {
         .lookup         = fuse_lookup,
         .mkdir          = fuse_mkdir,
@@ -1914,6 +1996,7 @@ static const struct inode_operations fuse_common_inode_operations = {
         .getxattr       = fuse_getxattr,
         .listxattr      = fuse_listxattr,
         .removexattr    = fuse_removexattr,
+        .update_time    = fuse_update_time,
 };
 
 static const struct inode_operations fuse_symlink_inode_operations = {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 77bcc303c3ae..65df7d8be4f5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -188,6 +188,22 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 }
 EXPORT_SYMBOL_GPL(fuse_do_open);
 
+static void fuse_link_write_file(struct file *file)
+{
+        struct inode *inode = file_inode(file);
+        struct fuse_conn *fc = get_fuse_conn(inode);
+        struct fuse_inode *fi = get_fuse_inode(inode);
+        struct fuse_file *ff = file->private_data;
+        /*
+         * file may be written through mmap, so chain it onto the
+         * inodes's write_file list
+         */
+        spin_lock(&fc->lock);
+        if (list_empty(&ff->write_entry))
+                list_add(&ff->write_entry, &fi->write_files);
+        spin_unlock(&fc->lock);
+}
+
 void fuse_finish_open(struct inode *inode, struct file *file)
 {
         struct fuse_file *ff = file->private_data;
@@ -208,6 +224,8 @@ void fuse_finish_open(struct inode *inode, struct file *file)
                 spin_unlock(&fc->lock);
                 fuse_invalidate_attr(inode);
         }
+        if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache)
+                fuse_link_write_file(file);
 }
 
 int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
@@ -292,6 +310,15 @@ static int fuse_open(struct inode *inode, struct file *file)
 
 static int fuse_release(struct inode *inode, struct file *file)
 {
+        struct fuse_conn *fc = get_fuse_conn(inode);
+
+        /* see fuse_vma_close() for !writeback_cache case */
+        if (fc->writeback_cache)
+                filemap_write_and_wait(file->f_mapping);
+
+        if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state))
+                fuse_flush_mtime(file, true);
+
         fuse_release_common(file, FUSE_RELEASE);
 
         /* return value is ignored by VFS */
@@ -333,12 +360,13 @@ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
 }
 
 /*
- * Check if page is under writeback
+ * Check if any page in a range is under writeback
  *
  * This is currently done by walking the list of writepage requests
  * for the inode, which can be pretty inefficient.
  */
-static bool fuse_page_is_writeback(struct inode *inode, pgoff_t index)
+static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from,
+                                   pgoff_t idx_to)
 {
         struct fuse_conn *fc = get_fuse_conn(inode);
         struct fuse_inode *fi = get_fuse_inode(inode);
@@ -351,8 +379,8 @@ static bool fuse_page_is_writeback(struct inode *inode, pgoff_t index)
 
                 BUG_ON(req->inode != inode);
                 curr_index = req->misc.write.in.offset >> PAGE_CACHE_SHIFT;
-                if (curr_index <= index &&
-                    index < curr_index + req->num_pages) {
+                if (idx_from < curr_index + req->num_pages &&
+                    curr_index <= idx_to) {
                         found = true;
                         break;
                 }
@@ -362,6 +390,11 @@ static bool fuse_page_is_writeback(struct inode *inode, pgoff_t index)
         return found;
 }
 
+static inline bool fuse_page_is_writeback(struct inode *inode, pgoff_t index)
+{
+        return fuse_range_is_writeback(inode, index, index);
+}
+
 /*
  * Wait for page writeback to be completed.
  *
@@ -376,6 +409,21 @@ static int fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
         return 0;
 }
 
+/*
+ * Wait for all pending writepages on the inode to finish.
+ *
+ * This is currently done by blocking further writes with FUSE_NOWRITE
+ * and waiting for all sent writes to complete.
+ *
+ * This must be called under i_mutex, otherwise the FUSE_NOWRITE usage
+ * could conflict with truncation.
+ */
+static void fuse_sync_writes(struct inode *inode)
+{
+        fuse_set_nowrite(inode);
+        fuse_release_nowrite(inode);
+}
+
 static int fuse_flush(struct file *file, fl_owner_t id)
 {
         struct inode *inode = file_inode(file);
@@ -391,6 +439,14 @@ static int fuse_flush(struct file *file, fl_owner_t id)
         if (fc->no_flush)
                 return 0;
 
+        err = filemap_write_and_wait(file->f_mapping);
+        if (err)
+                return err;
+
+        mutex_lock(&inode->i_mutex);
+        fuse_sync_writes(inode);
+        mutex_unlock(&inode->i_mutex);
+
         req = fuse_get_req_nofail_nopages(fc, file);
         memset(&inarg, 0, sizeof(inarg));
         inarg.fh = ff->fh;
@@ -411,21 +467,6 @@ static int fuse_flush(struct file *file, fl_owner_t id)
         return err;
 }
 
-/*
- * Wait for all pending writepages on the inode to finish.
- *
- * This is currently done by blocking further writes with FUSE_NOWRITE
- * and waiting for all sent writes to complete.
- *
- * This must be called under i_mutex, otherwise the FUSE_NOWRITE usage
- * could conflict with truncation.
- */
-static void fuse_sync_writes(struct inode *inode)
-{
-        fuse_set_nowrite(inode);
-        fuse_release_nowrite(inode);
-}
-
 int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
                       int datasync, int isdir)
 {
@@ -459,6 +500,12 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
 
         fuse_sync_writes(inode);
 
+        if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state)) {
+                int err = fuse_flush_mtime(file, false);
+                if (err)
+                        goto out;
+        }
+
         req = fuse_get_req_nopages(fc);
         if (IS_ERR(req)) {
                 err = PTR_ERR(req);
@@ -655,7 +702,33 @@ static void fuse_read_update_size(struct inode *inode, loff_t size,
         spin_unlock(&fc->lock);
 }
 
-static int fuse_readpage(struct file *file, struct page *page)
+static void fuse_short_read(struct fuse_req *req, struct inode *inode,
+                            u64 attr_ver)
+{
+        size_t num_read = req->out.args[0].size;
+        struct fuse_conn *fc = get_fuse_conn(inode);
+
+        if (fc->writeback_cache) {
+                /*
+                 * A hole in a file. Some data after the hole are in page cache,
+                 * but have not reached the client fs yet. So, the hole is not
+                 * present there.
+                 */
+                int i;
+                int start_idx = num_read >> PAGE_CACHE_SHIFT;
+                size_t off = num_read & (PAGE_CACHE_SIZE - 1);
+
+                for (i = start_idx; i < req->num_pages; i++) {
+                        zero_user_segment(req->pages[i], off, PAGE_CACHE_SIZE);
+                        off = 0;
+                }
+        } else {
+                loff_t pos = page_offset(req->pages[0]) + num_read;
+                fuse_read_update_size(inode, pos, attr_ver);
+        }
+}
+
+static int fuse_do_readpage(struct file *file, struct page *page)
 {
         struct fuse_io_priv io = { .async = 0, .file = file };
         struct inode *inode = page->mapping->host;
@@ -667,10 +740,6 @@ static int fuse_readpage(struct file *file, struct page *page)
         u64 attr_ver;
         int err;
 
-        err = -EIO;
-        if (is_bad_inode(inode))
-                goto out;
-
         /*
          * Page writeback can extend beyond the lifetime of the
          * page-cache page, so make sure we read a properly synced
@@ -679,9 +748,8 @@ static int fuse_readpage(struct file *file, struct page *page)
         fuse_wait_on_page_writeback(inode, page->index);
 
         req = fuse_get_req(fc, 1);
-        err = PTR_ERR(req);
         if (IS_ERR(req))
-                goto out;
+                return PTR_ERR(req);
 
         attr_ver = fuse_get_attr_version(fc);
 
@@ -692,18 +760,32 @@ static int fuse_readpage(struct file *file, struct page *page)
         req->page_descs[0].length = count;
         num_read = fuse_send_read(req, &io, pos, count, NULL);
         err = req->out.h.error;
-        fuse_put_request(fc, req);
 
         if (!err) {
                 /*
                  * Short read means EOF.  If file size is larger, truncate it
                  */
                 if (num_read < count)
-                        fuse_read_update_size(inode, pos + num_read, attr_ver);
+                        fuse_short_read(req, inode, attr_ver);
 
                 SetPageUptodate(page);
         }
 
+        fuse_put_request(fc, req);
+
+        return err;
+}
+
+static int fuse_readpage(struct file *file, struct page *page)
+{
+        struct inode *inode = page->mapping->host;
+        int err;
+
+        err = -EIO;
+        if (is_bad_inode(inode))
+                goto out;
+
+        err = fuse_do_readpage(file, page);
         fuse_invalidate_atime(inode);
  out:
         unlock_page(page);
@@ -726,13 +808,9 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
                 /*
                  * Short read means EOF. If file size is larger, truncate it
                  */
-                if (!req->out.h.error && num_read < count) {
-                        loff_t pos;
+                if (!req->out.h.error && num_read < count)
+                        fuse_short_read(req, inode, req->misc.read.attr_ver);
 
-                        pos = page_offset(req->pages[0]) + num_read;
-                        fuse_read_update_size(inode, pos,
-                                              req->misc.read.attr_ver);
-                }
                 fuse_invalidate_atime(inode);
         }
 
@@ -922,16 +1000,21 @@ static size_t fuse_send_write(struct fuse_req *req, struct fuse_io_priv *io,
         return req->misc.write.out.size;
 }
 
-void fuse_write_update_size(struct inode *inode, loff_t pos)
+bool fuse_write_update_size(struct inode *inode, loff_t pos)
 {
         struct fuse_conn *fc = get_fuse_conn(inode);
         struct fuse_inode *fi = get_fuse_inode(inode);
+        bool ret = false;
 
         spin_lock(&fc->lock);
         fi->attr_version = ++fc->attr_version;
-        if (pos > inode->i_size)
+        if (pos > inode->i_size) {
                 i_size_write(inode, pos);
+                ret = true;
+        }
         spin_unlock(&fc->lock);
+
+        return ret;
 }
 
 static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
@@ -1116,6 +1199,15 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
         struct iov_iter i;
         loff_t endbyte = 0;
 
+        if (get_fuse_conn(inode)->writeback_cache) {
+                /* Update size (EOF optimization) and mode (SUID clearing) */
+                err = fuse_update_attributes(mapping->host, NULL, file, NULL);
+                if (err)
+                        return err;
+
+                return generic_file_aio_write(iocb, iov, nr_segs, pos);
+        }
+
         WARN_ON(iocb->ki_pos != pos);
 
         ocount = 0;
@@ -1289,13 +1381,18 @@ static inline int fuse_iter_npages(const struct iov_iter *ii_p)
 
 ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
                        unsigned long nr_segs, size_t count, loff_t *ppos,
-                       int write)
+                       int flags)
 {
+        int write = flags & FUSE_DIO_WRITE;
+        int cuse = flags & FUSE_DIO_CUSE;
         struct file *file = io->file;
+        struct inode *inode = file->f_mapping->host;
         struct fuse_file *ff = file->private_data;
         struct fuse_conn *fc = ff->fc;
         size_t nmax = write ? fc->max_write : fc->max_read;
         loff_t pos = *ppos;
+        pgoff_t idx_from = pos >> PAGE_CACHE_SHIFT;
+        pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT;
         ssize_t res = 0;
         struct fuse_req *req;
         struct iov_iter ii;
@@ -1309,6 +1406,14 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
         if (IS_ERR(req))
                 return PTR_ERR(req);
 
+        if (!cuse && fuse_range_is_writeback(inode, idx_from, idx_to)) {
+                if (!write)
+                        mutex_lock(&inode->i_mutex);
+                fuse_sync_writes(inode);
+                if (!write)
+                        mutex_unlock(&inode->i_mutex);
+        }
+
         while (count) {
                 size_t nres;
                 fl_owner_t owner = current->files;
@@ -1397,7 +1502,8 @@ static ssize_t __fuse_direct_write(struct fuse_io_priv *io,
 
         res = generic_write_checks(file, ppos, &count, 0);
         if (!res)
-                res = fuse_direct_io(io, iov, nr_segs, count, ppos, 1);
+                res = fuse_direct_io(io, iov, nr_segs, count, ppos,
+                                     FUSE_DIO_WRITE);
 
         fuse_invalidate_attr(inode);
 
@@ -1885,6 +1991,77 @@ out:
         return err;
 }
 
+/*
+ * It's worthy to make sure that space is reserved on disk for the write,
+ * but how to implement it without killing performance need more thinking.
+ */
+static int fuse_write_begin(struct file *file, struct address_space *mapping,
+                loff_t pos, unsigned len, unsigned flags,
+                struct page **pagep, void **fsdata)
+{
+        pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+        struct fuse_conn *fc = get_fuse_conn(file->f_dentry->d_inode);
+        struct page *page;
+        loff_t fsize;
+        int err = -ENOMEM;
+
+        WARN_ON(!fc->writeback_cache);
+
+        page = grab_cache_page_write_begin(mapping, index, flags);
+        if (!page)
+                goto error;
+
+        fuse_wait_on_page_writeback(mapping->host, page->index);
+
+        if (PageUptodate(page) || len == PAGE_CACHE_SIZE)
+                goto success;
+        /*
+         * Check if the start this page comes after the end of file, in which
+         * case the readpage can be optimized away.
+         */
+        fsize = i_size_read(mapping->host);
+        if (fsize <= (pos & PAGE_CACHE_MASK)) {
+                size_t off = pos & ~PAGE_CACHE_MASK;
+                if (off)
+                        zero_user_segment(page, 0, off);
+                goto success;
+        }
+        err = fuse_do_readpage(file, page);
+        if (err)
+                goto cleanup;
+success:
+        *pagep = page;
+        return 0;
+
+cleanup:
+        unlock_page(page);
+        page_cache_release(page);
+error:
+        return err;
+}
+
+static int fuse_write_end(struct file *file, struct address_space *mapping,
+                loff_t pos, unsigned len, unsigned copied,
+                struct page *page, void *fsdata)
+{
+        struct inode *inode = page->mapping->host;
+
+        if (!PageUptodate(page)) {
+                /* Zero any unwritten bytes at the end of the page */
+                size_t endoff = (pos + copied) & ~PAGE_CACHE_MASK;
+                if (endoff)
+                        zero_user_segment(page, endoff, PAGE_CACHE_SIZE);
+                SetPageUptodate(page);
+        }
+
+        fuse_write_update_size(inode, pos + copied);
+        set_page_dirty(page);
+        unlock_page(page);
+        page_cache_release(page);
+
+        return copied;
+}
+
 static int fuse_launder_page(struct page *page)
 {
         int err = 0;
@@ -1946,20 +2123,9 @@ static const struct vm_operations_struct fuse_file_vm_ops = {
 
 static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
-        if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) {
-                struct inode *inode = file_inode(file);
-                struct fuse_conn *fc = get_fuse_conn(inode);
-                struct fuse_inode *fi = get_fuse_inode(inode);
-                struct fuse_file *ff = file->private_data;
-                /*
-                 * file may be written through mmap, so chain it onto the
-                 * inodes's write_file list
-                 */
-                spin_lock(&fc->lock);
-                if (list_empty(&ff->write_entry))
-                        list_add(&ff->write_entry, &fi->write_files);
-                spin_unlock(&fc->lock);
-        }
+        if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
+                fuse_link_write_file(file);
+
         file_accessed(file);
         vma->vm_ops = &fuse_file_vm_ops;
         return 0;
@@ -2606,7 +2772,7 @@ static void fuse_register_polled_file(struct fuse_conn *fc,
 {
         spin_lock(&fc->lock);
         if (RB_EMPTY_NODE(&ff->polled_node)) {
-                struct rb_node **link, *parent;
+                struct rb_node **link, *uninitialized_var(parent);
 
                 link = fuse_find_polled_node(fc, ff->kh, &parent);
                 BUG_ON(*link);
@@ -2850,8 +3016,16 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
                 goto out;
 
         /* we could have extended the file */
-        if (!(mode & FALLOC_FL_KEEP_SIZE))
-                fuse_write_update_size(inode, offset + length);
+        if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+                bool changed = fuse_write_update_size(inode, offset + length);
+
+                if (changed && fc->writeback_cache) {
+                        struct fuse_inode *fi = get_fuse_inode(inode);
+
+                        inode->i_mtime = current_fs_time(inode->i_sb);
+                        set_bit(FUSE_I_MTIME_DIRTY, &fi->state);
+                }
+        }
 
         if (mode & FALLOC_FL_PUNCH_HOLE)
                 truncate_pagecache_range(inode, offset, offset + length - 1);
@@ -2915,6 +3089,8 @@ static const struct address_space_operations fuse_file_aops  = {
         .set_page_dirty = __set_page_dirty_nobuffers,
         .bmap           = fuse_bmap,
         .direct_IO      = fuse_direct_IO,
+        .write_begin    = fuse_write_begin,
+        .write_end      = fuse_write_end,
 };
 
 void fuse_init_file_inode(struct inode *inode)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 2da5db2c8bdb..a257ed8ebee6 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -119,6 +119,8 @@ enum {
         FUSE_I_INIT_RDPLUS,
         /** An operation changing file size is in progress  */
         FUSE_I_SIZE_UNSTABLE,
+        /** i_mtime has been updated locally; a flush to userspace needed */
+        FUSE_I_MTIME_DIRTY,
 };
 
 struct fuse_conn;
@@ -480,6 +482,9 @@ struct fuse_conn {
         /** Set if bdi is valid */
         unsigned bdi_initialized:1;
 
+        /** write-back cache policy (default is write-through) */
+        unsigned writeback_cache:1;
+
         /*
          * The following bitfields are only for optimization purposes
          * and hence races in setting them will not cause malfunction
@@ -863,9 +868,20 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
 
 int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
                  bool isdir);
+
+/**
+ * fuse_direct_io() flags
+ */
+
+/** If set, it is WRITE; otherwise - READ */
+#define FUSE_DIO_WRITE (1 << 0)
+
+/** CUSE pass fuse_direct_io() a file which f_mapping->host is not from FUSE */
+#define FUSE_DIO_CUSE  (1 << 1)
+
 ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
                        unsigned long nr_segs, size_t count, loff_t *ppos,
-                       int write);
+                       int flags);
 long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
                    unsigned int flags);
 long fuse_ioctl_common(struct file *file, unsigned int cmd,
@@ -873,7 +889,9 @@ long fuse_ioctl_common(struct file *file, unsigned int cmd,
 unsigned fuse_file_poll(struct file *file, poll_table *wait);
 int fuse_dev_release(struct inode *inode, struct file *file);
 
-void fuse_write_update_size(struct inode *inode, loff_t pos);
+bool fuse_write_update_size(struct inode *inode, loff_t pos);
+
+int fuse_flush_mtime(struct file *file, bool nofail);
 
 int fuse_do_setattr(struct inode *inode, struct iattr *attr,
                     struct file *file);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d468643a68b2..8d611696fcad 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -123,7 +123,7 @@ static void fuse_destroy_inode(struct inode *inode)
 
 static void fuse_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         if (inode->i_sb->s_flags & MS_ACTIVE) {
                 struct fuse_conn *fc = get_fuse_conn(inode);
@@ -135,6 +135,7 @@ static void fuse_evict_inode(struct inode *inode)
 
 static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         if (*flags & MS_MANDLOCK)
                 return -EINVAL;
 
@@ -170,8 +171,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
         inode->i_blocks  = attr->blocks;
         inode->i_atime.tv_sec   = attr->atime;
         inode->i_atime.tv_nsec  = attr->atimensec;
-        inode->i_mtime.tv_sec   = attr->mtime;
-        inode->i_mtime.tv_nsec  = attr->mtimensec;
+        /* mtime from server may be stale due to local buffered write */
+        if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) {
+                inode->i_mtime.tv_sec   = attr->mtime;
+                inode->i_mtime.tv_nsec  = attr->mtimensec;
+        }
         inode->i_ctime.tv_sec   = attr->ctime;
         inode->i_ctime.tv_nsec  = attr->ctimensec;
 
@@ -197,6 +201,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 {
         struct fuse_conn *fc = get_fuse_conn(inode);
         struct fuse_inode *fi = get_fuse_inode(inode);
+        bool is_wb = fc->writeback_cache;
         loff_t oldsize;
         struct timespec old_mtime;
 
@@ -211,10 +216,16 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
         fuse_change_attributes_common(inode, attr, attr_valid);
 
         oldsize = inode->i_size;
-        i_size_write(inode, attr->size);
+        /*
+         * In case of writeback_cache enabled, the cached writes beyond EOF
+         * extend local i_size without keeping userspace server in sync. So,
+         * attr->size coming from server can be stale. We cannot trust it.
+         */
+        if (!is_wb || !S_ISREG(inode->i_mode))
+                i_size_write(inode, attr->size);
         spin_unlock(&fc->lock);
 
-        if (S_ISREG(inode->i_mode)) {
+        if (!is_wb && S_ISREG(inode->i_mode)) {
                 bool inval = false;
 
                 if (oldsize != attr->size) {
@@ -243,6 +254,8 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
 {
         inode->i_mode = attr->mode & S_IFMT;
         inode->i_size = attr->size;
+        inode->i_mtime.tv_sec  = attr->mtime;
+        inode->i_mtime.tv_nsec = attr->mtimensec;
         if (S_ISREG(inode->i_mode)) {
                 fuse_init_common(inode);
                 fuse_init_file_inode(inode);
@@ -289,7 +302,9 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
                 return NULL;
 
         if ((inode->i_state & I_NEW)) {
-                inode->i_flags |= S_NOATIME|S_NOCMTIME;
+                inode->i_flags |= S_NOATIME;
+                if (!fc->writeback_cache || !S_ISREG(inode->i_mode))
+                        inode->i_flags |= S_NOCMTIME;
                 inode->i_generation = generation;
                 inode->i_data.backing_dev_info = &fc->bdi;
                 fuse_init_inode(inode, attr);
@@ -873,6 +888,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
                         }
                         if (arg->flags & FUSE_ASYNC_DIO)
                                 fc->async_dio = 1;
+                        if (arg->flags & FUSE_WRITEBACK_CACHE)
+                                fc->writeback_cache = 1;
                 } else {
                         ra_pages = fc->max_read / PAGE_CACHE_SIZE;
                         fc->no_lock = 1;
@@ -900,7 +917,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
                 FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
                 FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
                 FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
-                FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO;
+                FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
+                FUSE_WRITEBACK_CACHE;
         req->in.h.opcode = FUSE_INIT;
         req->in.numargs = 1;
         req->in.args[0].size = sizeof(*arg);
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index ba9456685f47..3088e2a38e30 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -64,18 +64,6 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
         return acl;
 }
 
-static int gfs2_set_mode(struct inode *inode, umode_t mode)
-{
-        int error = 0;
-
-        if (mode != inode->i_mode) {
-                inode->i_mode = mode;
-                mark_inode_dirty(inode);
-        }
-
-        return error;
-}
-
 int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
         int error;
@@ -85,8 +73,8 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 
         BUG_ON(name == NULL);
 
-        if (acl->a_count > GFS2_ACL_MAX_ENTRIES)
-                return -EINVAL;
+        if (acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
+                return -E2BIG;
 
         if (type == ACL_TYPE_ACCESS) {
                 umode_t mode = inode->i_mode;
@@ -98,9 +86,10 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
                 if (error == 0)
                         acl = NULL;
 
-                error = gfs2_set_mode(inode, mode);
-                if (error)
-                        return error;
+                if (mode != inode->i_mode) {
+                        inode->i_mode = mode;
+                        mark_inode_dirty(inode);
+                }
         }
 
         if (acl) {
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index 301260c999ba..2d65ec4cd4be 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -14,7 +14,7 @@
 
 #define GFS2_POSIX_ACL_ACCESS           "posix_acl_access"
 #define GFS2_POSIX_ACL_DEFAULT          "posix_acl_default"
-#define GFS2_ACL_MAX_ENTRIES            25
+#define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12)
 
 extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
 extern int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 49436fa7cd4f..ce62dcac90b6 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -21,6 +21,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/backing-dev.h>
 #include <linux/aio.h>
+#include <trace/events/writeback.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -230,13 +231,11 @@ static int gfs2_writepages(struct address_space *mapping,
 static int gfs2_write_jdata_pagevec(struct address_space *mapping,
                                     struct writeback_control *wbc,
                                     struct pagevec *pvec,
-                                    int nr_pages, pgoff_t end)
+                                    int nr_pages, pgoff_t end,
+                                    pgoff_t *done_index)
 {
         struct inode *inode = mapping->host;
         struct gfs2_sbd *sdp = GFS2_SB(inode);
-        loff_t i_size = i_size_read(inode);
-        pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
-        unsigned offset = i_size & (PAGE_CACHE_SIZE-1);
         unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
         int i;
         int ret;
@@ -248,40 +247,83 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping,
         for(i = 0; i < nr_pages; i++) {
                 struct page *page = pvec->pages[i];
 
+                /*
+                 * At this point, the page may be truncated or
+                 * invalidated (changing page->mapping to NULL), or
+                 * even swizzled back from swapper_space to tmpfs file
+                 * mapping. However, page->index will not change
+                 * because we have a reference on the page.
+                 */
+                if (page->index > end) {
+                        /*
+                         * can't be range_cyclic (1st pass) because
+                         * end == -1 in that case.
+                         */
+                        ret = 1;
+                        break;
+                }
+
+                *done_index = page->index;
+
                 lock_page(page);
 
                 if (unlikely(page->mapping != mapping)) {
+continue_unlock:
                         unlock_page(page);
                         continue;
                 }
 
-                if (!wbc->range_cyclic && page->index > end) {
-                        ret = 1;
-                        unlock_page(page);
-                        continue;
+                if (!PageDirty(page)) {
+                        /* someone wrote it for us */
+                        goto continue_unlock;
                 }
 
-                if (wbc->sync_mode != WB_SYNC_NONE)
-                        wait_on_page_writeback(page);
-
-                if (PageWriteback(page) ||
-                    !clear_page_dirty_for_io(page)) {
-                        unlock_page(page);
-                        continue;
+                if (PageWriteback(page)) {
+                        if (wbc->sync_mode != WB_SYNC_NONE)
+                                wait_on_page_writeback(page);
+                        else
+                                goto continue_unlock;
                 }
 
-                /* Is the page fully outside i_size? (truncate in progress) */
-                if (page->index > end_index || (page->index == end_index && !offset)) {
-                        page->mapping->a_ops->invalidatepage(page, 0,
-                                                             PAGE_CACHE_SIZE);
-                        unlock_page(page);
-                        continue;
-                }
+                BUG_ON(PageWriteback(page));
+                if (!clear_page_dirty_for_io(page))
+                        goto continue_unlock;
+
+                trace_wbc_writepage(wbc, mapping->backing_dev_info);
 
                 ret = __gfs2_jdata_writepage(page, wbc);
+                if (unlikely(ret)) {
+                        if (ret == AOP_WRITEPAGE_ACTIVATE) {
+                                unlock_page(page);
+                                ret = 0;
+                        } else {
+
+                                /*
+                                 * done_index is set past this page,
+                                 * so media errors will not choke
+                                 * background writeout for the entire
+                                 * file. This has consequences for
+                                 * range_cyclic semantics (ie. it may
+                                 * not be suitable for data integrity
+                                 * writeout).
+                                 */
+                                *done_index = page->index + 1;
+                                ret = 1;
+                                break;
+                        }
+                }
 
-                if (ret || (--(wbc->nr_to_write) <= 0))
+                /*
+                 * We stop writing back only if we are not doing
+                 * integrity sync. In case of integrity sync we have to
+                 * keep going until we have written all the pages
+                 * we tagged for writeback prior to entering this loop.
+                 */
+                if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) {
                         ret = 1;
+                        break;
+                }
+
         }
         gfs2_trans_end(sdp);
         return ret;
@@ -306,51 +348,69 @@ static int gfs2_write_cache_jdata(struct address_space *mapping,
         int done = 0;
         struct pagevec pvec;
         int nr_pages;
+        pgoff_t uninitialized_var(writeback_index);
         pgoff_t index;
         pgoff_t end;
-        int scanned = 0;
+        pgoff_t done_index;
+        int cycled;
         int range_whole = 0;
+        int tag;
 
         pagevec_init(&pvec, 0);
         if (wbc->range_cyclic) {
-                index = mapping->writeback_index; /* Start from prev offset */
+                writeback_index = mapping->writeback_index; /* prev offset */
+                index = writeback_index;
+                if (index == 0)
+                        cycled = 1;
+                else
+                        cycled = 0;
                 end = -1;
         } else {
                 index = wbc->range_start >> PAGE_CACHE_SHIFT;
                 end = wbc->range_end >> PAGE_CACHE_SHIFT;
                 if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
                         range_whole = 1;
-                scanned = 1;
+                cycled = 1; /* ignore range_cyclic tests */
         }
+        if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+                tag = PAGECACHE_TAG_TOWRITE;
+        else
+                tag = PAGECACHE_TAG_DIRTY;
 
 retry:
-         while (!done && (index <= end) &&
-                (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-                                               PAGECACHE_TAG_DIRTY,
-                                               min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
-                scanned = 1;
-                ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
+        if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+                tag_pages_for_writeback(mapping, index, end);
+        done_index = index;
+        while (!done && (index <= end)) {
+                nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
+                              min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+                if (nr_pages == 0)
+                        break;
+
+                ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end, &done_index);
                 if (ret)
                         done = 1;
                 if (ret > 0)
                         ret = 0;
-
                 pagevec_release(&pvec);
                 cond_resched();
         }
 
-        if (!scanned && !done) {
+        if (!cycled && !done) {
                 /*
+                 * range_cyclic:
                  * We hit the last page and there is more work to be done: wrap
                  * back to the start of the file
                  */
-                scanned = 1;
+                cycled = 1;
                 index = 0;
+                end = writeback_index - 1;
                 goto retry;
         }
 
         if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-                mapping->writeback_index = index;
+                mapping->writeback_index = done_index;
+
         return ret;
 }
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index fe0500c0af7a..c62d4b9f51dc 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1328,6 +1328,121 @@ int gfs2_file_dealloc(struct gfs2_inode *ip)
 }
 
 /**
+ * gfs2_free_journal_extents - Free cached journal bmap info
+ * @jd: The journal
+ *
+ */
+
+void gfs2_free_journal_extents(struct gfs2_jdesc *jd)
+{
+        struct gfs2_journal_extent *jext;
+
+        while(!list_empty(&jd->extent_list)) {
+                jext = list_entry(jd->extent_list.next, struct gfs2_journal_extent, list);
+                list_del(&jext->list);
+                kfree(jext);
+        }
+}
+
+/**
+ * gfs2_add_jextent - Add or merge a new extent to extent cache
+ * @jd: The journal descriptor
+ * @lblock: The logical block at start of new extent
+ * @pblock: The physical block at start of new extent
+ * @blocks: Size of extent in fs blocks
+ *
+ * Returns: 0 on success or -ENOMEM
+ */
+
+static int gfs2_add_jextent(struct gfs2_jdesc *jd, u64 lblock, u64 dblock, u64 blocks)
+{
+        struct gfs2_journal_extent *jext;
+
+        if (!list_empty(&jd->extent_list)) {
+                jext = list_entry(jd->extent_list.prev, struct gfs2_journal_extent, list);
+                if ((jext->dblock + jext->blocks) == dblock) {
+                        jext->blocks += blocks;
+                        return 0;
+                }
+        }
+
+        jext = kzalloc(sizeof(struct gfs2_journal_extent), GFP_NOFS);
+        if (jext == NULL)
+                return -ENOMEM;
+        jext->dblock = dblock;
+        jext->lblock = lblock;
+        jext->blocks = blocks;
+        list_add_tail(&jext->list, &jd->extent_list);
+        jd->nr_extents++;
+        return 0;
+}
+
+/**
+ * gfs2_map_journal_extents - Cache journal bmap info
+ * @sdp: The super block
+ * @jd: The journal to map
+ *
+ * Create a reusable "extent" mapping from all logical
+ * blocks to all physical blocks for the given journal.  This will save
+ * us time when writing journal blocks.  Most journals will have only one
+ * extent that maps all their logical blocks.  That's because gfs2.mkfs
+ * arranges the journal blocks sequentially to maximize performance.
+ * So the extent would map the first block for the entire file length.
+ * However, gfs2_jadd can happen while file activity is happening, so
+ * those journals may not be sequential.  Less likely is the case where
+ * the users created their own journals by mounting the metafs and
+ * laying it out.  But it's still possible.  These journals might have
+ * several extents.
+ *
+ * Returns: 0 on success, or error on failure
+ */
+
+int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
+{
+        u64 lblock = 0;
+        u64 lblock_stop;
+        struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+        struct buffer_head bh;
+        unsigned int shift = sdp->sd_sb.sb_bsize_shift;
+        u64 size;
+        int rc;
+
+        lblock_stop = i_size_read(jd->jd_inode) >> shift;
+        size = (lblock_stop - lblock) << shift;
+        jd->nr_extents = 0;
+        WARN_ON(!list_empty(&jd->extent_list));
+
+        do {
+                bh.b_state = 0;
+                bh.b_blocknr = 0;
+                bh.b_size = size;
+                rc = gfs2_block_map(jd->jd_inode, lblock, &bh, 0);
+                if (rc || !buffer_mapped(&bh))
+                        goto fail;
+                rc = gfs2_add_jextent(jd, lblock, bh.b_blocknr, bh.b_size >> shift);
+                if (rc)
+                        goto fail;
+                size -= bh.b_size;
+                lblock += (bh.b_size >> ip->i_inode.i_blkbits);
+        } while(size > 0);
+
+        fs_info(sdp, "journal %d mapped with %u extents\n", jd->jd_jid,
+                jd->nr_extents);
+        return 0;
+
+fail:
+        fs_warn(sdp, "error %d mapping journal %u at offset %llu (extent %u)\n",
+                rc, jd->jd_jid,
+                (unsigned long long)(i_size_read(jd->jd_inode) - size),
+                jd->nr_extents);
+        fs_warn(sdp, "bmap=%d lblock=%llu block=%llu, state=0x%08lx, size=%llu\n",
+                rc, (unsigned long long)lblock, (unsigned long long)bh.b_blocknr,
+                bh.b_state, (unsigned long long)bh.b_size);
+        gfs2_free_journal_extents(jd);
+        return rc;
+}
+
+/**
  * gfs2_write_alloc_required - figure out if a write will require an allocation
  * @ip: the file being written to
  * @offset: the offset to write to
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index 42fea03e2bd9..81ded5e2aaa2 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -55,5 +55,7 @@ extern int gfs2_truncatei_resume(struct gfs2_inode *ip);
 extern int gfs2_file_dealloc(struct gfs2_inode *ip);
 extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
                                      unsigned int len);
+extern int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd);
+extern void gfs2_free_journal_extents(struct gfs2_jdesc *jd);
 
 #endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index fa32655449c8..1a349f9a9685 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -53,6 +53,8 @@
  * but never before the maximum hash table size has been reached.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/buffer_head.h>
@@ -507,8 +509,8 @@ static int gfs2_check_dirent(struct gfs2_dirent *dent, unsigned int offset,
                 goto error;
         return 0;
 error:
-        printk(KERN_WARNING "gfs2_check_dirent: %s (%s)\n", msg,
-               first ? "first in block" : "not first in block");
+        pr_warn("%s: %s (%s)\n",
+                __func__, msg, first ? "first in block" : "not first in block");
         return -EIO;
 }
 
@@ -531,8 +533,7 @@ static int gfs2_dirent_offset(const void *buf)
         }
         return offset;
 wrong_type:
-        printk(KERN_WARNING "gfs2_scan_dirent: wrong block type %u\n",
-               be32_to_cpu(h->mh_type));
+        pr_warn("%s: wrong block type %u\n", __func__, be32_to_cpu(h->mh_type));
         return -1;
 }
 
@@ -728,7 +729,7 @@ static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
 
         error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp);
         if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) {
-                /* printk(KERN_INFO "block num=%llu\n", leaf_no); */
+                /* pr_info("block num=%llu\n", leaf_no); */
                 error = -EIO;
         }
 
@@ -1006,7 +1007,8 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
         len = 1 << (dip->i_depth - be16_to_cpu(oleaf->lf_depth));
         half_len = len >> 1;
         if (!half_len) {
-                printk(KERN_WARNING "i_depth %u lf_depth %u index %u\n", dip->i_depth, be16_to_cpu(oleaf->lf_depth), index);
+                pr_warn("i_depth %u lf_depth %u index %u\n",
+                        dip->i_depth, be16_to_cpu(oleaf->lf_depth), index);
                 gfs2_consist_inode(dip);
                 error = -EIO;
                 goto fail_brelse;
@@ -1684,6 +1686,14 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name)
         return 0;
 }
 
+static u16 gfs2_inode_ra_len(const struct gfs2_inode *ip)
+{
+        u64 where = ip->i_no_addr + 1;
+        if (ip->i_eattr == where)
+                return 1;
+        return 0;
+}
+
 /**
  * gfs2_dir_add - Add new filename into directory
  * @inode: The directory inode
@@ -1721,6 +1731,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name,
                         dent = gfs2_init_dirent(inode, dent, name, bh);
                         gfs2_inum_out(nip, dent);
                         dent->de_type = cpu_to_be16(IF2DT(nip->i_inode.i_mode));
+                        dent->de_rahead = cpu_to_be16(gfs2_inode_ra_len(nip));
                         tv = CURRENT_TIME;
                         if (ip->i_diskflags & GFS2_DIF_EXHASH) {
                                 leaf = (struct gfs2_leaf *)bh->b_data;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index efc078f0ee4e..6c794085abac 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -811,6 +811,8 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
         loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1);
         loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
         loff_t max_chunk_size = UINT_MAX & bsize_mask;
+        struct gfs2_holder gh;
+
         next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
 
         /* We only support the FALLOC_FL_KEEP_SIZE mode */
@@ -831,8 +833,10 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
         if (error)
                 return error;
 
-        gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-        error = gfs2_glock_nq(&ip->i_gh);
+        mutex_lock(&inode->i_mutex);
+
+        gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+        error = gfs2_glock_nq(&gh);
         if (unlikely(error))
                 goto out_uninit;
 
@@ -900,9 +904,10 @@ out_trans_fail:
 out_qunlock:
         gfs2_quota_unlock(ip);
 out_unlock:
-        gfs2_glock_dq(&ip->i_gh);
+        gfs2_glock_dq(&gh);
 out_uninit:
-        gfs2_holder_uninit(&ip->i_gh);
+        gfs2_holder_uninit(&gh);
+        mutex_unlock(&inode->i_mutex);
         return error;
 }
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index ca0be6c69a26..aec7f73832f0 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -468,7 +470,7 @@ retry:
                         do_xmote(gl, gh, LM_ST_UNLOCKED);
                         break;
                 default: /* Everything else */
-                        printk(KERN_ERR "GFS2: wanted %u got %u\n", gl->gl_target, state);
+                        pr_err("wanted %u got %u\n", gl->gl_target, state);
                         GLOCK_BUG_ON(gl, 1);
                 }
                 spin_unlock(&gl->gl_spin);
@@ -542,7 +544,7 @@ __acquires(&gl->gl_spin)
                 /* lock_dlm */
                 ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
                 if (ret) {
-                        printk(KERN_ERR "GFS2: lm_lock ret %d\n", ret);
+                        pr_err("lm_lock ret %d\n", ret);
                         GLOCK_BUG_ON(gl, 1);
                 }
         } else { /* lock_nolock */
@@ -935,7 +937,7 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
                 vaf.fmt = fmt;
                 vaf.va = &args;
 
-                printk(KERN_ERR " %pV", &vaf);
+                pr_err("%pV", &vaf);
         }
 
         va_end(args);
@@ -1010,13 +1012,13 @@ do_cancel:
         return;
 
 trap_recursive:
-        printk(KERN_ERR "original: %pSR\n", (void *)gh2->gh_ip);
-        printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid));
-        printk(KERN_ERR "lock type: %d req lock state : %d\n",
+        pr_err("original: %pSR\n", (void *)gh2->gh_ip);
+        pr_err("pid: %d\n", pid_nr(gh2->gh_owner_pid));
+        pr_err("lock type: %d req lock state : %d\n",
                gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
-        printk(KERN_ERR "new: %pSR\n", (void *)gh->gh_ip);
-        printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid));
-        printk(KERN_ERR "lock type: %d req lock state : %d\n",
+        pr_err("new: %pSR\n", (void *)gh->gh_ip);
+        pr_err("pid: %d\n", pid_nr(gh->gh_owner_pid));
+        pr_err("lock type: %d req lock state : %d\n",
                gh->gh_gl->gl_name.ln_type, gh->gh_state);
         gfs2_dump_glock(NULL, gl);
         BUG();
@@ -1045,9 +1047,13 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 
         spin_lock(&gl->gl_spin);
         add_to_queue(gh);
-        if ((LM_FLAG_NOEXP & gh->gh_flags) &&
-            test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+        if (unlikely((LM_FLAG_NOEXP & gh->gh_flags) &&
+                     test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) {
                 set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+                gl->gl_lockref.count++;
+                if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+                        gl->gl_lockref.count--;
+        }
         run_queue(gl, 1);
         spin_unlock(&gl->gl_spin);
 
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 3bf0631b5d56..54b66809e818 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -82,6 +82,8 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
         struct gfs2_trans tr;
 
         memset(&tr, 0, sizeof(tr));
+        INIT_LIST_HEAD(&tr.tr_buf);
+        INIT_LIST_HEAD(&tr.tr_databuf);
         tr.tr_revokes = atomic_read(&gl->gl_ail_count);
 
         if (!tr.tr_revokes)
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index cf0e34400f71..bdf70c18610c 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -52,7 +52,7 @@ struct gfs2_log_header_host {
  */
 
 struct gfs2_log_operations {
-        void (*lo_before_commit) (struct gfs2_sbd *sdp);
+        void (*lo_before_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
         void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
         void (*lo_before_scan) (struct gfs2_jdesc *jd,
                                 struct gfs2_log_header_host *head, int pass);
@@ -371,6 +371,7 @@ enum {
         GIF_ALLOC_FAILED        = 2,
         GIF_SW_PAGED            = 3,
         GIF_ORDERED             = 4,
+        GIF_FREE_VFS_INODE      = 5,
 };
 
 struct gfs2_inode {
@@ -462,11 +463,11 @@ struct gfs2_trans {
         unsigned int tr_blocks;
         unsigned int tr_revokes;
         unsigned int tr_reserved;
+        unsigned int tr_touched:1;
+        unsigned int tr_attached:1;
 
         struct gfs2_holder tr_t_gh;
 
-        int tr_touched;
-        int tr_attached;
 
         unsigned int tr_num_buf_new;
         unsigned int tr_num_databuf_new;
@@ -476,6 +477,8 @@ struct gfs2_trans {
         unsigned int tr_num_revoke_rm;
 
         struct list_head tr_list;
+        struct list_head tr_databuf;
+        struct list_head tr_buf;
 
         unsigned int tr_first;
         struct list_head tr_ail1_list;
@@ -483,7 +486,7 @@ struct gfs2_trans {
 };
 
 struct gfs2_journal_extent {
-        struct list_head extent_list;
+        struct list_head list;
 
         unsigned int lblock; /* First logical block */
         u64 dblock; /* First disk block */
@@ -493,6 +496,7 @@ struct gfs2_journal_extent {
 struct gfs2_jdesc {
         struct list_head jd_list;
         struct list_head extent_list;
+        unsigned int nr_extents;
         struct work_struct jd_work;
         struct inode *jd_inode;
         unsigned long jd_flags;
@@ -500,6 +504,15 @@ struct gfs2_jdesc {
         unsigned int jd_jid;
         unsigned int jd_blocks;
         int jd_recover_error;
+        /* Replay stuff */
+
+        unsigned int jd_found_blocks;
+        unsigned int jd_found_revokes;
+        unsigned int jd_replayed_blocks;
+
+        struct list_head jd_revoke_list;
+        unsigned int jd_replay_tail;
+
 };
 
 struct gfs2_statfs_change_host {
@@ -746,19 +759,12 @@ struct gfs2_sbd {
 
         struct gfs2_trans *sd_log_tr;
         unsigned int sd_log_blks_reserved;
-        unsigned int sd_log_commited_buf;
-        unsigned int sd_log_commited_databuf;
         int sd_log_commited_revoke;
 
         atomic_t sd_log_pinned;
-        unsigned int sd_log_num_buf;
         unsigned int sd_log_num_revoke;
-        unsigned int sd_log_num_rg;
-        unsigned int sd_log_num_databuf;
 
-        struct list_head sd_log_le_buf;
         struct list_head sd_log_le_revoke;
-        struct list_head sd_log_le_databuf;
         struct list_head sd_log_le_ordered;
         spinlock_t sd_ordered_lock;
 
@@ -786,15 +792,6 @@ struct gfs2_sbd {
         struct list_head sd_ail1_list;
         struct list_head sd_ail2_list;
 
-        /* Replay stuff */
-
-        struct list_head sd_revoke_list;
-        unsigned int sd_replay_tail;
-
-        unsigned int sd_found_blocks;
-        unsigned int sd_found_revokes;
-        unsigned int sd_replayed_blocks;
-
         /* For quiescing the filesystem */
         struct gfs2_holder sd_freeze_gh;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 5c524180c98e..28cc7bf6575a 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -376,12 +376,11 @@ static void munge_mode_uid_gid(const struct gfs2_inode *dip,
                 inode->i_gid = current_fsgid();
 }
 
-static int alloc_dinode(struct gfs2_inode *ip, u32 flags)
+static int alloc_dinode(struct gfs2_inode *ip, u32 flags, unsigned *dblocks)
 {
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-        struct gfs2_alloc_parms ap = { .target = RES_DINODE, .aflags = flags, };
+        struct gfs2_alloc_parms ap = { .target = *dblocks, .aflags = flags, };
         int error;
-        int dblocks = 1;
 
         error = gfs2_quota_lock_check(ip);
         if (error)
@@ -391,11 +390,11 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags)
         if (error)
                 goto out_quota;
 
-        error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA, 0);
+        error = gfs2_trans_begin(sdp, (*dblocks * RES_RG_BIT) + RES_STATFS + RES_QUOTA, 0);
         if (error)
                 goto out_ipreserv;
 
-        error = gfs2_alloc_blocks(ip, &ip->i_no_addr, &dblocks, 1, &ip->i_generation);
+        error = gfs2_alloc_blocks(ip, &ip->i_no_addr, dblocks, 1, &ip->i_generation);
         ip->i_no_formal_ino = ip->i_generation;
         ip->i_inode.i_ino = ip->i_no_addr;
         ip->i_goal = ip->i_no_addr;
@@ -428,6 +427,33 @@ static void gfs2_init_dir(struct buffer_head *dibh,
 }
 
 /**
+ * gfs2_init_xattr - Initialise an xattr block for a new inode
+ * @ip: The inode in question
+ *
+ * This sets up an empty xattr block for a new inode, ready to
+ * take any ACLs, LSM xattrs, etc.
+ */
+
+static void gfs2_init_xattr(struct gfs2_inode *ip)
+{
+        struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+        struct buffer_head *bh;
+        struct gfs2_ea_header *ea;
+
+        bh = gfs2_meta_new(ip->i_gl, ip->i_eattr);
+        gfs2_trans_add_meta(ip->i_gl, bh);
+        gfs2_metatype_set(bh, GFS2_METATYPE_EA, GFS2_FORMAT_EA);
+        gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
+
+        ea = GFS2_EA_BH2FIRST(bh);
+        ea->ea_rec_len = cpu_to_be32(sdp->sd_jbsize);
+        ea->ea_type = GFS2_EATYPE_UNUSED;
+        ea->ea_flags = GFS2_EAFLAG_LAST;
+
+        brelse(bh);
+}
+
+/**
  * init_dinode - Fill in a new dinode structure
  * @dip: The directory this inode is being created in
  * @ip: The inode
@@ -545,13 +571,6 @@ static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
         return err;
 }
 
-static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
-                              const struct qstr *qstr)
-{
-        return security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr,
-                                            &gfs2_initxattrs, NULL);
-}
-
 /**
  * gfs2_create_inode - Create a new inode
  * @dir: The parent directory
@@ -578,8 +597,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
         struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
         struct gfs2_glock *io_gl;
         struct dentry *d;
-        int error;
+        int error, free_vfs_inode = 0;
         u32 aflags = 0;
+        unsigned blocks = 1;
         struct gfs2_diradd da = { .bh = NULL, };
 
         if (!name->len || name->len > GFS2_FNAMESIZE)
@@ -676,10 +696,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
             (dip->i_diskflags & GFS2_DIF_TOPDIR))
                 aflags |= GFS2_AF_ORLOV;
 
-        error = alloc_dinode(ip, aflags);
+        if (default_acl || acl)
+                blocks++;
+
+        error = alloc_dinode(ip, aflags, &blocks);
         if (error)
                 goto fail_free_inode;
 
+        gfs2_set_inode_blocks(inode, blocks);
+
         error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
         if (error)
                 goto fail_free_inode;
@@ -689,10 +714,14 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
         if (error)
                 goto fail_free_inode;
 
-        error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+        error = gfs2_trans_begin(sdp, blocks, 0);
         if (error)
                 goto fail_gunlock2;
 
+        if (blocks > 1) {
+                ip->i_eattr = ip->i_no_addr + 1;
+                gfs2_init_xattr(ip);
+        }
         init_dinode(dip, ip, symname);
         gfs2_trans_end(sdp);
 
@@ -722,7 +751,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
         if (error)
                 goto fail_gunlock3;
 
-        error = gfs2_security_init(dip, ip, name);
+        error = security_inode_init_security(&ip->i_inode, &dip->i_inode, name,
+                                             &gfs2_initxattrs, NULL);
         if (error)
                 goto fail_gunlock3;
 
@@ -758,15 +788,16 @@ fail_free_acls:
         if (acl)
                 posix_acl_release(acl);
 fail_free_vfs_inode:
-        free_inode_nonrcu(inode);
-        inode = NULL;
+        free_vfs_inode = 1;
 fail_gunlock:
         gfs2_dir_no_add(&da);
         gfs2_glock_dq_uninit(ghs);
         if (inode && !IS_ERR(inode)) {
                 clear_nlink(inode);
-                mark_inode_dirty(inode);
-                set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
+                if (!free_vfs_inode)
+                        mark_inode_dirty(inode);
+                set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED,
+                        &GFS2_I(inode)->i_flags);
                 iput(inode);
         }
 fail:
@@ -1263,6 +1294,10 @@ static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
                 }
 
                 tmp = gfs2_lookupi(dir, &gfs2_qdotdot, 1);
+                if (!tmp) {
+                        error = -ENOENT;
+                        break;
+                }
                 if (IS_ERR(tmp)) {
                         error = PTR_ERR(tmp);
                         break;
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 2a6ba06bee6f..c1eb555dc588 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/dlm.h>
 #include <linux/slab.h>
@@ -176,7 +178,7 @@ static void gdlm_bast(void *arg, int mode)
                 gfs2_glock_cb(gl, LM_ST_SHARED);
                 break;
         default:
-                printk(KERN_ERR "unknown bast mode %d", mode);
+                pr_err("unknown bast mode %d\n", mode);
                 BUG();
         }
 }
@@ -195,7 +197,7 @@ static int make_mode(const unsigned int lmstate)
         case LM_ST_SHARED:
                 return DLM_LOCK_PR;
         }
-        printk(KERN_ERR "unknown LM state %d", lmstate);
+        pr_err("unknown LM state %d\n", lmstate);
         BUG();
         return -1;
 }
@@ -308,7 +310,7 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
         error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK,
                            NULL, gl);
         if (error) {
-                printk(KERN_ERR "gdlm_unlock %x,%llx err=%d\n",
+                pr_err("gdlm_unlock %x,%llx err=%d\n",
                        gl->gl_name.ln_type,
                        (unsigned long long)gl->gl_name.ln_number, error);
                 return;
@@ -1102,7 +1104,7 @@ static void gdlm_recover_slot(void *arg, struct dlm_slot *slot)
         }
 
         if (ls->ls_recover_submit[jid]) {
-                fs_info(sdp, "recover_slot jid %d gen %u prev %u",
+                fs_info(sdp, "recover_slot jid %d gen %u prev %u\n",
                         jid, ls->ls_recover_block, ls->ls_recover_submit[jid]);
         }
         ls->ls_recover_submit[jid] = ls->ls_recover_block;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 9dcb9777a5f8..4a14d504ef83 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -18,6 +18,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/bio.h>
+#include <linux/blkdev.h>
 #include <linux/writeback.h>
 #include <linux/list_sort.h>
 
@@ -145,8 +146,10 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
 {
         struct list_head *head = &sdp->sd_ail1_list;
         struct gfs2_trans *tr;
+        struct blk_plug plug;
 
         trace_gfs2_ail_flush(sdp, wbc, 1);
+        blk_start_plug(&plug);
         spin_lock(&sdp->sd_ail_lock);
 restart:
         list_for_each_entry_reverse(tr, head, tr_list) {
@@ -156,6 +159,7 @@ restart:
                         goto restart;
         }
         spin_unlock(&sdp->sd_ail_lock);
+        blk_finish_plug(&plug);
         trace_gfs2_ail_flush(sdp, wbc, 0);
 }
 
@@ -410,24 +414,22 @@ static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer
 static unsigned int calc_reserved(struct gfs2_sbd *sdp)
 {
         unsigned int reserved = 0;
-        unsigned int mbuf_limit, metabufhdrs_needed;
-        unsigned int dbuf_limit, databufhdrs_needed;
-        unsigned int revokes = 0;
+        unsigned int mbuf;
+        unsigned int dbuf;
+        struct gfs2_trans *tr = sdp->sd_log_tr;
 
-        mbuf_limit = buf_limit(sdp);
-        metabufhdrs_needed = (sdp->sd_log_commited_buf +
-                              (mbuf_limit - 1)) / mbuf_limit;
-        dbuf_limit = databuf_limit(sdp);
-        databufhdrs_needed = (sdp->sd_log_commited_databuf +
-                              (dbuf_limit - 1)) / dbuf_limit;
+        if (tr) {
+                mbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
+                dbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
+                reserved = mbuf + dbuf;
+                /* Account for header blocks */
+                reserved += DIV_ROUND_UP(mbuf, buf_limit(sdp));
+                reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
+        }
 
         if (sdp->sd_log_commited_revoke > 0)
-                revokes = gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
+                reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
                                           sizeof(u64));
-
-        reserved = sdp->sd_log_commited_buf + metabufhdrs_needed +
-                sdp->sd_log_commited_databuf + databufhdrs_needed +
-                revokes;
         /* One for the overall header */
         if (reserved)
                 reserved++;
@@ -682,36 +684,25 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
         }
         trace_gfs2_log_flush(sdp, 1);
 
+        sdp->sd_log_flush_head = sdp->sd_log_head;
+        sdp->sd_log_flush_wrapped = 0;
         tr = sdp->sd_log_tr;
         if (tr) {
                 sdp->sd_log_tr = NULL;
                 INIT_LIST_HEAD(&tr->tr_ail1_list);
                 INIT_LIST_HEAD(&tr->tr_ail2_list);
+                tr->tr_first = sdp->sd_log_flush_head;
         }
 
-        if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) {
-                printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf,
-                       sdp->sd_log_commited_buf);
-                gfs2_assert_withdraw(sdp, 0);
-        }
-        if (sdp->sd_log_num_databuf != sdp->sd_log_commited_databuf) {
-                printk(KERN_INFO "GFS2: log databuf %u %u\n",
-                       sdp->sd_log_num_databuf, sdp->sd_log_commited_databuf);
-                gfs2_assert_withdraw(sdp, 0);
-        }
         gfs2_assert_withdraw(sdp,
                         sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
 
-        sdp->sd_log_flush_head = sdp->sd_log_head;
-        sdp->sd_log_flush_wrapped = 0;
-        if (tr)
-                tr->tr_first = sdp->sd_log_flush_head;
-
         gfs2_ordered_write(sdp);
-        lops_before_commit(sdp);
+        lops_before_commit(sdp, tr);
         gfs2_log_flush_bio(sdp, WRITE);
 
         if (sdp->sd_log_head != sdp->sd_log_flush_head) {
+                log_flush_wait(sdp);
                 log_write_header(sdp, 0);
         } else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
                 atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
@@ -723,8 +714,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
         gfs2_log_lock(sdp);
         sdp->sd_log_head = sdp->sd_log_flush_head;
         sdp->sd_log_blks_reserved = 0;
-        sdp->sd_log_commited_buf = 0;
-        sdp->sd_log_commited_databuf = 0;
         sdp->sd_log_commited_revoke = 0;
 
         spin_lock(&sdp->sd_ail_lock);
@@ -740,34 +729,54 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
         kfree(tr);
 }
 
+/**
+ * gfs2_merge_trans - Merge a new transaction into a cached transaction
+ * @old: Original transaction to be expanded
+ * @new: New transaction to be merged
+ */
+
+static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
+{
+        WARN_ON_ONCE(old->tr_attached != 1);
+
+        old->tr_num_buf_new     += new->tr_num_buf_new;
+        old->tr_num_databuf_new += new->tr_num_databuf_new;
+        old->tr_num_buf_rm      += new->tr_num_buf_rm;
+        old->tr_num_databuf_rm  += new->tr_num_databuf_rm;
+        old->tr_num_revoke      += new->tr_num_revoke;
+        old->tr_num_revoke_rm   += new->tr_num_revoke_rm;
+
+        list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
+        list_splice_tail_init(&new->tr_buf, &old->tr_buf);
+}
+
 static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
         unsigned int reserved;
         unsigned int unused;
+        unsigned int maxres;
 
         gfs2_log_lock(sdp);
 
-        sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
-        sdp->sd_log_commited_databuf += tr->tr_num_databuf_new -
-                tr->tr_num_databuf_rm;
-        gfs2_assert_withdraw(sdp, (((int)sdp->sd_log_commited_buf) >= 0) ||
-                             (((int)sdp->sd_log_commited_databuf) >= 0));
+        if (sdp->sd_log_tr) {
+                gfs2_merge_trans(sdp->sd_log_tr, tr);
+        } else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
+                gfs2_assert_withdraw(sdp, tr->tr_t_gh.gh_gl);
+                sdp->sd_log_tr = tr;
+                tr->tr_attached = 1;
+        }
+
         sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
         reserved = calc_reserved(sdp);
-        gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved);
-        unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved;
+        maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
+        gfs2_assert_withdraw(sdp, maxres >= reserved);
+        unused = maxres - reserved;
         atomic_add(unused, &sdp->sd_log_blks_free);
         trace_gfs2_log_blocks(sdp, unused);
         gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
                              sdp->sd_jdesc->jd_blocks);
         sdp->sd_log_blks_reserved = reserved;
 
-        if (sdp->sd_log_tr == NULL &&
-            (tr->tr_num_buf_new || tr->tr_num_databuf_new)) {
-                gfs2_assert_withdraw(sdp, tr->tr_t_gh.gh_gl);
-                sdp->sd_log_tr = tr;
-                tr->tr_attached = 1;
-        }
         gfs2_log_unlock(sdp);
 }
 
@@ -807,10 +816,7 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
         down_write(&sdp->sd_log_flush_lock);
 
         gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
-        gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
         gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
-        gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg);
-        gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf);
         gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
 
         sdp->sd_log_flush_head = sdp->sd_log_head;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 76693793cedd..a294d8d8bcd4 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -146,8 +146,8 @@ static u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
         struct gfs2_journal_extent *je;
         u64 block;
 
-        list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) {
-                if (lbn >= je->lblock && lbn < je->lblock + je->blocks) {
+        list_for_each_entry(je, &sdp->sd_jdesc->extent_list, list) {
+                if ((lbn >= je->lblock) && (lbn < (je->lblock + je->blocks))) {
                         block = je->dblock + lbn - je->lblock;
                         gfs2_log_incr_head(sdp);
                         return block;
@@ -491,44 +491,40 @@ static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit,
         gfs2_log_unlock(sdp);
 }
 
-static void buf_lo_before_commit(struct gfs2_sbd *sdp)
+static void buf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
         unsigned int limit = buf_limit(sdp); /* 503 for 4k blocks */
-
-        gfs2_before_commit(sdp, limit, sdp->sd_log_num_buf,
-                           &sdp->sd_log_le_buf, 0);
+        unsigned int nbuf;
+        if (tr == NULL)
+                return;
+        nbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
+        gfs2_before_commit(sdp, limit, nbuf, &tr->tr_buf, 0);
 }
 
 static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
-        struct list_head *head = &sdp->sd_log_le_buf;
+        struct list_head *head;
         struct gfs2_bufdata *bd;
 
-        if (tr == NULL) {
-                gfs2_assert(sdp, list_empty(head));
+        if (tr == NULL)
                 return;
-        }
 
+        head = &tr->tr_buf;
         while (!list_empty(head)) {
                 bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
                 list_del_init(&bd->bd_list);
-                sdp->sd_log_num_buf--;
-
                 gfs2_unpin(sdp, bd->bd_bh, tr);
         }
-        gfs2_assert_warn(sdp, !sdp->sd_log_num_buf);
 }
 
 static void buf_lo_before_scan(struct gfs2_jdesc *jd,
                                struct gfs2_log_header_host *head, int pass)
 {
-        struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
-
         if (pass != 0)
                 return;
 
-        sdp->sd_found_blocks = 0;
-        sdp->sd_replayed_blocks = 0;
+        jd->jd_found_blocks = 0;
+        jd->jd_replayed_blocks = 0;
 }
 
 static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
@@ -551,9 +547,9 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
         for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
                 blkno = be64_to_cpu(*ptr++);
 
-                sdp->sd_found_blocks++;
+                jd->jd_found_blocks++;
 
-                if (gfs2_revoke_check(sdp, blkno, start))
+                if (gfs2_revoke_check(jd, blkno, start))
                         continue;
 
                 error = gfs2_replay_read_block(jd, start, &bh_log);
@@ -574,7 +570,7 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
                 if (error)
                         break;
 
-                sdp->sd_replayed_blocks++;
+                jd->jd_replayed_blocks++;
         }
 
         return error;
@@ -617,10 +613,10 @@ static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
         gfs2_meta_sync(ip->i_gl);
 
         fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
-                jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+                jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
 }
 
-static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
+static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
         struct gfs2_meta_header *mh;
         unsigned int offset;
@@ -679,13 +675,11 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
                                   struct gfs2_log_header_host *head, int pass)
 {
-        struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
-
         if (pass != 0)
                 return;
 
-        sdp->sd_found_revokes = 0;
-        sdp->sd_replay_tail = head->lh_tail;
+        jd->jd_found_revokes = 0;
+        jd->jd_replay_tail = head->lh_tail;
 }
 
 static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
@@ -717,13 +711,13 @@ static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
                 while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
                         blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));
 
-                        error = gfs2_revoke_add(sdp, blkno, start);
+                        error = gfs2_revoke_add(jd, blkno, start);
                         if (error < 0) {
                                 brelse(bh);
                                 return error;
                         }
                         else if (error)
-                                sdp->sd_found_revokes++;
+                                jd->jd_found_revokes++;
 
                         if (!--revokes)
                                 break;
@@ -743,16 +737,16 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
         struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 
         if (error) {
-                gfs2_revoke_clean(sdp);
+                gfs2_revoke_clean(jd);
                 return;
         }
         if (pass != 1)
                 return;
 
         fs_info(sdp, "jid=%u: Found %u revoke tags\n",
-                jd->jd_jid, sdp->sd_found_revokes);
+                jd->jd_jid, jd->jd_found_revokes);
 
-        gfs2_revoke_clean(sdp);
+        gfs2_revoke_clean(jd);
 }
 
 /**
@@ -760,12 +754,14 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
  *
  */
 
-static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
+static void databuf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
-        unsigned int limit = buf_limit(sdp) / 2;
-
-        gfs2_before_commit(sdp, limit, sdp->sd_log_num_databuf,
-                           &sdp->sd_log_le_databuf, 1);
+        unsigned int limit = databuf_limit(sdp);
+        unsigned int nbuf;
+        if (tr == NULL)
+                return;
+        nbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
+        gfs2_before_commit(sdp, limit, nbuf, &tr->tr_databuf, 1);
 }
 
 static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
@@ -789,9 +785,9 @@ static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
                 blkno = be64_to_cpu(*ptr++);
                 esc = be64_to_cpu(*ptr++);
 
-                sdp->sd_found_blocks++;
+                jd->jd_found_blocks++;
 
-                if (gfs2_revoke_check(sdp, blkno, start))
+                if (gfs2_revoke_check(jd, blkno, start))
                         continue;
 
                 error = gfs2_replay_read_block(jd, start, &bh_log);
@@ -811,7 +807,7 @@ static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
                 brelse(bh_log);
                 brelse(bh_ip);
 
-                sdp->sd_replayed_blocks++;
+                jd->jd_replayed_blocks++;
         }
 
         return error;
@@ -835,26 +831,23 @@ static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
         gfs2_meta_sync(ip->i_gl);
 
         fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
-                jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+                jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
 }
 
 static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
-        struct list_head *head = &sdp->sd_log_le_databuf;
+        struct list_head *head;
         struct gfs2_bufdata *bd;
 
-        if (tr == NULL) {
-                gfs2_assert(sdp, list_empty(head));
+        if (tr == NULL)
                 return;
-        }
 
+        head = &tr->tr_databuf;
         while (!list_empty(head)) {
                 bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
                 list_del_init(&bd->bd_list);
-                sdp->sd_log_num_databuf--;
                 gfs2_unpin(sdp, bd->bd_bh, tr);
         }
-        gfs2_assert_warn(sdp, !sdp->sd_log_num_databuf);
 }
 
 
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 9ca2e6438419..a65a7ba32ffd 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -46,12 +46,13 @@ static inline unsigned int databuf_limit(struct gfs2_sbd *sdp)
         return limit;
 }
 
-static inline void lops_before_commit(struct gfs2_sbd *sdp)
+static inline void lops_before_commit(struct gfs2_sbd *sdp,
+                                      struct gfs2_trans *tr)
 {
         int x;
         for (x = 0; gfs2_log_ops[x]; x++)
                 if (gfs2_log_ops[x]->lo_before_commit)
-                        gfs2_log_ops[x]->lo_before_commit(sdp);
+                        gfs2_log_ops[x]->lo_before_commit(sdp, tr);
 }
 
 static inline void lops_after_commit(struct gfs2_sbd *sdp,
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index c272e73063de..82b6ac829656 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -165,7 +167,7 @@ static int __init init_gfs2_fs(void)
 
         gfs2_register_debugfs();
 
-        printk("GFS2 installed\n");
+        pr_info("GFS2 installed\n");
 
         return 0;
 
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index c7f24690ed05..2cf09b63a6b4 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -97,6 +97,11 @@ const struct address_space_operations gfs2_meta_aops = {
         .releasepage = gfs2_releasepage,
 };
 
+const struct address_space_operations gfs2_rgrp_aops = {
+        .writepage = gfs2_aspace_writepage,
+        .releasepage = gfs2_releasepage,
+};
+
 /**
  * gfs2_getbuf - Get a buffer with a given address space
  * @gl: the glock
@@ -267,15 +272,10 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
                 trace_gfs2_pin(bd, 0);
                 atomic_dec(&sdp->sd_log_pinned);
                 list_del_init(&bd->bd_list);
-                if (meta) {
-                        gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
-                        sdp->sd_log_num_buf--;
+                if (meta)
                         tr->tr_num_buf_rm++;
-                } else {
-                        gfs2_assert_warn(sdp, sdp->sd_log_num_databuf);
-                        sdp->sd_log_num_databuf--;
+                else
                         tr->tr_num_databuf_rm++;
-                }
                 tr->tr_touched = 1;
                 was_pinned = 1;
                 brelse(bh);
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 4823b934208a..ac5d8027d335 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -38,12 +38,15 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh,
 }
 
 extern const struct address_space_operations gfs2_meta_aops;
+extern const struct address_space_operations gfs2_rgrp_aops;
 
 static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
 {
         struct inode *inode = mapping->host;
         if (mapping->a_ops == &gfs2_meta_aops)
                 return (((struct gfs2_glock *)mapping) - 1)->gl_sbd;
+        else if (mapping->a_ops == &gfs2_rgrp_aops)
+                return container_of(mapping, struct gfs2_sbd, sd_aspace);
         else
                 return inode->i_sb->s_fs_info;
 }
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index c6872d09561a..22f954051bb8 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -104,7 +106,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
         mapping = &sdp->sd_aspace;
 
         address_space_init_once(mapping);
-        mapping->a_ops = &gfs2_meta_aops;
+        mapping->a_ops = &gfs2_rgrp_aops;
         mapping->host = sb->s_bdev->bd_inode;
         mapping->flags = 0;
         mapping_set_gfp_mask(mapping, GFP_NOFS);
@@ -114,9 +116,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
         spin_lock_init(&sdp->sd_log_lock);
         atomic_set(&sdp->sd_log_pinned, 0);
-        INIT_LIST_HEAD(&sdp->sd_log_le_buf);
         INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
-        INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
         INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
         spin_lock_init(&sdp->sd_ordered_lock);
 
@@ -130,8 +130,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
         atomic_set(&sdp->sd_log_in_flight, 0);
         init_waitqueue_head(&sdp->sd_log_flush_wait);
 
-        INIT_LIST_HEAD(&sdp->sd_revoke_list);
-
         return sdp;
 }
 
@@ -154,7 +152,7 @@ static int gfs2_check_sb(struct gfs2_sbd *sdp, int silent)
         if (sb->sb_magic != GFS2_MAGIC ||
             sb->sb_type != GFS2_METATYPE_SB) {
                 if (!silent)
-                        printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
+                        pr_warn("not a GFS2 filesystem\n");
                 return -EINVAL;
         }
 
@@ -176,7 +174,7 @@ static void end_bio_io_page(struct bio *bio, int error)
         if (!error)
                 SetPageUptodate(page);
         else
-                printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
+                pr_warn("error %d reading superblock\n", error);
         unlock_page(page);
 }
 
@@ -519,67 +517,6 @@ out:
         return ret;
 }
 
-/**
- * map_journal_extents - create a reusable "extent" mapping from all logical
- * blocks to all physical blocks for the given journal.  This will save
- * us time when writing journal blocks.  Most journals will have only one
- * extent that maps all their logical blocks.  That's because gfs2.mkfs
- * arranges the journal blocks sequentially to maximize performance.
- * So the extent would map the first block for the entire file length.
- * However, gfs2_jadd can happen while file activity is happening, so
- * those journals may not be sequential.  Less likely is the case where
- * the users created their own journals by mounting the metafs and
- * laying it out.  But it's still possible.  These journals might have
- * several extents.
- *
- * TODO: This should be done in bigger chunks rather than one block at a time,
- *       but since it's only done at mount time, I'm not worried about the
- *       time it takes.
- */
-static int map_journal_extents(struct gfs2_sbd *sdp)
-{
-        struct gfs2_jdesc *jd = sdp->sd_jdesc;
-        unsigned int lb;
-        u64 db, prev_db; /* logical block, disk block, prev disk block */
-        struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
-        struct gfs2_journal_extent *jext = NULL;
-        struct buffer_head bh;
-        int rc = 0;
-
-        prev_db = 0;
-
-        for (lb = 0; lb < i_size_read(jd->jd_inode) >> sdp->sd_sb.sb_bsize_shift; lb++) {
-                bh.b_state = 0;
-                bh.b_blocknr = 0;
-                bh.b_size = 1 << ip->i_inode.i_blkbits;
-                rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0);
-                db = bh.b_blocknr;
-                if (rc || !db) {
-                        printk(KERN_INFO "GFS2 journal mapping error %d: lb="
-                               "%u db=%llu\n", rc, lb, (unsigned long long)db);
-                        break;
-                }
-                if (!prev_db || db != prev_db + 1) {
-                        jext = kzalloc(sizeof(struct gfs2_journal_extent),
-                                       GFP_KERNEL);
-                        if (!jext) {
-                                printk(KERN_INFO "GFS2 error: out of memory "
-                                       "mapping journal extents.\n");
-                                rc = -ENOMEM;
-                                break;
-                        }
-                        jext->dblock = db;
-                        jext->lblock = lb;
-                        jext->blocks = 1;
-                        list_add_tail(&jext->extent_list, &jd->extent_list);
-                } else {
-                        jext->blocks++;
-                }
-                prev_db = db;
-        }
-        return rc;
-}
-
 static void gfs2_others_may_mount(struct gfs2_sbd *sdp)
 {
         char *message = "FIRSTMOUNT=Done";
@@ -638,6 +575,8 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
                         break;
 
                 INIT_LIST_HEAD(&jd->extent_list);
+                INIT_LIST_HEAD(&jd->jd_revoke_list);
+
                 INIT_WORK(&jd->jd_work, gfs2_recover_func);
                 jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
                 if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
@@ -781,7 +720,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
                 atomic_set(&sdp->sd_log_thresh2, 4*sdp->sd_jdesc->jd_blocks/5);
 
                 /* Map the extents for this journal's blocks */
-                map_journal_extents(sdp);
+                gfs2_map_journal_extents(sdp, sdp->sd_jdesc);
         }
         trace_gfs2_log_blocks(sdp, atomic_read(&sdp->sd_log_blks_free));
 
@@ -1008,7 +947,7 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
                 lm = &gfs2_dlm_ops;
 #endif
         } else {
-                printk(KERN_INFO "GFS2: can't find protocol %s\n", proto);
+                pr_info("can't find protocol %s\n", proto);
                 return -ENOENT;
         }
 
@@ -1115,7 +1054,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
 
         sdp = init_sbd(sb);
         if (!sdp) {
-                printk(KERN_WARNING "GFS2: can't alloc struct gfs2_sbd\n");
+                pr_warn("can't alloc struct gfs2_sbd\n");
                 return -ENOMEM;
         }
         sdp->sd_args = *args;
@@ -1363,7 +1302,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 
         error = gfs2_mount_args(&args, data);
         if (error) {
-                printk(KERN_WARNING "GFS2: can't parse mount arguments\n");
+                pr_warn("can't parse mount arguments\n");
                 goto error_super;
         }
 
@@ -1413,15 +1352,15 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type,
 
         error = kern_path(dev_name, LOOKUP_FOLLOW, &path);
         if (error) {
-                printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
-                       dev_name, error);
+                pr_warn("path_lookup on %s returned error %d\n",
+                        dev_name, error);
                 return ERR_PTR(error);
         }
         s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, flags,
                  path.dentry->d_inode->i_sb->s_bdev);
         path_put(&path);
         if (IS_ERR(s)) {
-                printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
+                pr_warn("gfs2 mount does not exist\n");
                 return ERR_CAST(s);
         }
         if ((flags ^ s->s_flags) & MS_RDONLY) {
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 8bec0e3192dd..c4effff7cf55 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -36,6 +36,8 @@
  * the quota file, so it is not being constantly read.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
@@ -330,6 +332,7 @@ static int slot_get(struct gfs2_quota_data *qd)
         if (bit < sdp->sd_quota_slots) {
                 set_bit(bit, sdp->sd_quota_bitmap);
                 qd->qd_slot = bit;
+                error = 0;
 out:
                 qd->qd_slot_count++;
         }
@@ -1081,10 +1084,10 @@ static int print_message(struct gfs2_quota_data *qd, char *type)
 {
         struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
 
-        printk(KERN_INFO "GFS2: fsid=%s: quota %s for %s %u\n",
-               sdp->sd_fsname, type,
-               (qd->qd_id.type == USRQUOTA) ? "user" : "group",
-               from_kqid(&init_user_ns, qd->qd_id));
+        fs_info(sdp, "quota %s for %s %u\n",
+                type,
+                (qd->qd_id.type == USRQUOTA) ? "user" : "group",
+                from_kqid(&init_user_ns, qd->qd_id));
 
         return 0;
 }
@@ -1242,14 +1245,13 @@ int gfs2_quota_init(struct gfs2_sbd *sdp)
         bm_size = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * sizeof(unsigned long));
         bm_size *= sizeof(unsigned long);
         error = -ENOMEM;
-        sdp->sd_quota_bitmap = kmalloc(bm_size, GFP_NOFS|__GFP_NOWARN);
+        sdp->sd_quota_bitmap = kzalloc(bm_size, GFP_NOFS | __GFP_NOWARN);
         if (sdp->sd_quota_bitmap == NULL)
-                sdp->sd_quota_bitmap = __vmalloc(bm_size, GFP_NOFS, PAGE_KERNEL);
+                sdp->sd_quota_bitmap = __vmalloc(bm_size, GFP_NOFS |
+                                                 __GFP_ZERO, PAGE_KERNEL);
         if (!sdp->sd_quota_bitmap)
                 return error;
 
-        memset(sdp->sd_quota_bitmap, 0, bm_size);
-
         for (x = 0; x < blocks; x++) {
                 struct buffer_head *bh;
                 const struct gfs2_quota_change *qc;
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 963b2d75200c..7ad4094d68c0 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -52,9 +52,9 @@ int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
         return error;
 }
 
-int gfs2_revoke_add(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
+int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where)
 {
-        struct list_head *head = &sdp->sd_revoke_list;
+        struct list_head *head = &jd->jd_revoke_list;
         struct gfs2_revoke_replay *rr;
         int found = 0;
 
@@ -81,13 +81,13 @@ int gfs2_revoke_add(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
         return 1;
 }
 
-int gfs2_revoke_check(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
+int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where)
 {
         struct gfs2_revoke_replay *rr;
         int wrap, a, b, revoke;
         int found = 0;
 
-        list_for_each_entry(rr, &sdp->sd_revoke_list, rr_list) {
+        list_for_each_entry(rr, &jd->jd_revoke_list, rr_list) {
                 if (rr->rr_blkno == blkno) {
                         found = 1;
                         break;
@@ -97,17 +97,17 @@ int gfs2_revoke_check(struct gfs2_sbd *sdp, u64 blkno, unsigned int where)
         if (!found)
                 return 0;
 
-        wrap = (rr->rr_where < sdp->sd_replay_tail);
-        a = (sdp->sd_replay_tail < where);
+        wrap = (rr->rr_where < jd->jd_replay_tail);
+        a = (jd->jd_replay_tail < where);
         b = (where < rr->rr_where);
         revoke = (wrap) ? (a || b) : (a && b);
 
         return revoke;
 }
 
-void gfs2_revoke_clean(struct gfs2_sbd *sdp)
+void gfs2_revoke_clean(struct gfs2_jdesc *jd)
 {
-        struct list_head *head = &sdp->sd_revoke_list;
+        struct list_head *head = &jd->jd_revoke_list;
         struct gfs2_revoke_replay *rr;
 
         while (!list_empty(head)) {
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
index 2226136c7647..6142836cce96 100644
--- a/fs/gfs2/recovery.h
+++ b/fs/gfs2/recovery.h
@@ -23,9 +23,9 @@ static inline void gfs2_replay_incr_blk(struct gfs2_sbd *sdp, unsigned int *blk)
 extern int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
                            struct buffer_head **bh);
 
-extern int gfs2_revoke_add(struct gfs2_sbd *sdp, u64 blkno, unsigned int where);
-extern int gfs2_revoke_check(struct gfs2_sbd *sdp, u64 blkno, unsigned int where);
-extern void gfs2_revoke_clean(struct gfs2_sbd *sdp);
+extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where);
+extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where);
+extern void gfs2_revoke_clean(struct gfs2_jdesc *jd);
 
 extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
                     struct gfs2_log_header_host *head);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index a1da21349235..281a7716e3f3 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -99,12 +101,12 @@ static inline void gfs2_setbit(const struct gfs2_rbm *rbm, bool do_clone,
         cur_state = (*byte1 >> bit) & GFS2_BIT_MASK;
 
         if (unlikely(!valid_change[new_state * 4 + cur_state])) {
-                printk(KERN_WARNING "GFS2: buf_blk = 0x%x old_state=%d, "
-                       "new_state=%d\n", rbm->offset, cur_state, new_state);
-                printk(KERN_WARNING "GFS2: rgrp=0x%llx bi_start=0x%x\n",
-                       (unsigned long long)rbm->rgd->rd_addr, bi->bi_start);
-                printk(KERN_WARNING "GFS2: bi_offset=0x%x bi_len=0x%x\n",
-                       bi->bi_offset, bi->bi_len);
+                pr_warn("buf_blk = 0x%x old_state=%d, new_state=%d\n",
+                        rbm->offset, cur_state, new_state);
+                pr_warn("rgrp=0x%llx bi_start=0x%x\n",
+                        (unsigned long long)rbm->rgd->rd_addr, bi->bi_start);
+                pr_warn("bi_offset=0x%x bi_len=0x%x\n",
+                        bi->bi_offset, bi->bi_len);
                 dump_stack();
                 gfs2_consist_rgrpd(rbm->rgd);
                 return;
@@ -736,11 +738,11 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
 
 static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd)
 {
-        printk(KERN_INFO "  ri_addr = %llu\n", (unsigned long long)rgd->rd_addr);
-        printk(KERN_INFO "  ri_length = %u\n", rgd->rd_length);
-        printk(KERN_INFO "  ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0);
-        printk(KERN_INFO "  ri_data = %u\n", rgd->rd_data);
-        printk(KERN_INFO "  ri_bitbytes = %u\n", rgd->rd_bitbytes);
+        pr_info("ri_addr = %llu\n", (unsigned long long)rgd->rd_addr);
+        pr_info("ri_length = %u\n", rgd->rd_length);
+        pr_info("ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0);
+        pr_info("ri_data = %u\n", rgd->rd_data);
+        pr_info("ri_bitbytes = %u\n", rgd->rd_bitbytes);
 }
 
 /**
@@ -1102,7 +1104,7 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd)
  * Returns: errno
  */
 
-int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
+static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 {
         struct gfs2_sbd *sdp = rgd->rd_sbd;
         struct gfs2_glock *gl = rgd->rd_gl;
@@ -1169,7 +1171,7 @@ fail:
         return error;
 }
 
-int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
+static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
 {
         u32 rl_flags;
 
@@ -2278,7 +2280,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
                 }
         }
         if (rbm.rgd->rd_free < *nblocks) {
-                printk(KERN_WARNING "nblocks=%u\n", *nblocks);
+                pr_warn("nblocks=%u\n", *nblocks);
                 goto rgrp_error;
         }
 
@@ -2296,7 +2298,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 
         gfs2_statfs_change(sdp, 0, -(s64)*nblocks, dinode ? 1 : 0);
         if (dinode)
-                gfs2_trans_add_unrevoke(sdp, block, 1);
+                gfs2_trans_add_unrevoke(sdp, block, *nblocks);
 
         gfs2_quota_change(ip, *nblocks, ip->i_inode.i_uid, ip->i_inode.i_gid);
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 60f60f6181f3..de8afad89e51 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/bio.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -175,8 +177,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         break;
                 case Opt_debug:
                         if (args->ar_errors == GFS2_ERRORS_PANIC) {
-                                printk(KERN_WARNING "GFS2: -o debug and -o errors=panic "
-                                       "are mutually exclusive.\n");
+                                pr_warn("-o debug and -o errors=panic are mutually exclusive\n");
                                 return -EINVAL;
                         }
                         args->ar_debug = 1;
@@ -228,21 +229,21 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                 case Opt_commit:
                         rv = match_int(&tmp[0], &args->ar_commit);
                         if (rv || args->ar_commit <= 0) {
-                                printk(KERN_WARNING "GFS2: commit mount option requires a positive numeric argument\n");
+                                pr_warn("commit mount option requires a positive numeric argument\n");
                                 return rv ? rv : -EINVAL;
                         }
                         break;
                 case Opt_statfs_quantum:
                         rv = match_int(&tmp[0], &args->ar_statfs_quantum);
                         if (rv || args->ar_statfs_quantum < 0) {
-                                printk(KERN_WARNING "GFS2: statfs_quantum mount option requires a non-negative numeric argument\n");
+                                pr_warn("statfs_quantum mount option requires a non-negative numeric argument\n");
                                 return rv ? rv : -EINVAL;
                         }
                         break;
                 case Opt_quota_quantum:
                         rv = match_int(&tmp[0], &args->ar_quota_quantum);
                         if (rv || args->ar_quota_quantum <= 0) {
-                                printk(KERN_WARNING "GFS2: quota_quantum mount option requires a positive numeric argument\n");
+                                pr_warn("quota_quantum mount option requires a positive numeric argument\n");
                                 return rv ? rv : -EINVAL;
                         }
                         break;
@@ -250,7 +251,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         rv = match_int(&tmp[0], &args->ar_statfs_percent);
                         if (rv || args->ar_statfs_percent < 0 ||
                             args->ar_statfs_percent > 100) {
-                                printk(KERN_WARNING "statfs_percent mount option requires a numeric argument between 0 and 100\n");
+                                pr_warn("statfs_percent mount option requires a numeric argument between 0 and 100\n");
                                 return rv ? rv : -EINVAL;
                         }
                         break;
@@ -259,8 +260,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         break;
                 case Opt_err_panic:
                         if (args->ar_debug) {
-                                printk(KERN_WARNING "GFS2: -o debug and -o errors=panic "
-                                        "are mutually exclusive.\n");
+                                pr_warn("-o debug and -o errors=panic are mutually exclusive\n");
                                 return -EINVAL;
                         }
                         args->ar_errors = GFS2_ERRORS_PANIC;
@@ -279,7 +279,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         break;
                 case Opt_error:
                 default:
-                        printk(KERN_WARNING "GFS2: invalid mount option: %s\n", o);
+                        pr_warn("invalid mount option: %s\n", o);
                         return -EINVAL;
                 }
         }
@@ -295,9 +295,8 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 
 void gfs2_jindex_free(struct gfs2_sbd *sdp)
 {
-        struct list_head list, *head;
+        struct list_head list;
         struct gfs2_jdesc *jd;
-        struct gfs2_journal_extent *jext;
 
         spin_lock(&sdp->sd_jindex_spin);
         list_add(&list, &sdp->sd_jindex_list);
@@ -307,14 +306,7 @@ void gfs2_jindex_free(struct gfs2_sbd *sdp)
 
         while (!list_empty(&list)) {
                 jd = list_entry(list.next, struct gfs2_jdesc, jd_list);
-                head = &jd->extent_list;
-                while (!list_empty(head)) {
-                        jext = list_entry(head->next,
-                                          struct gfs2_journal_extent,
-                                          extent_list);
-                        list_del(&jext->extent_list);
-                        kfree(jext);
-                }
+                gfs2_free_journal_extents(jd);
                 list_del(&jd->jd_list);
                 iput(jd->jd_inode);
                 kfree(jd);
@@ -1175,6 +1167,8 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
         struct gfs2_tune *gt = &sdp->sd_tune;
         int error;
 
+        sync_filesystem(sb);
+
         spin_lock(&gt->gt_spin);
         args.ar_commit = gt->gt_logd_secs;
         args.ar_quota_quantum = gt->gt_quota_quantum;
@@ -1256,7 +1250,7 @@ static int gfs2_drop_inode(struct inode *inode)
 {
         struct gfs2_inode *ip = GFS2_I(inode);
 
-        if (inode->i_nlink) {
+        if (!test_bit(GIF_FREE_VFS_INODE, &ip->i_flags) && inode->i_nlink) {
                 struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
                 if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
                         clear_nlink(inode);
@@ -1471,6 +1465,11 @@ static void gfs2_evict_inode(struct inode *inode)
         struct gfs2_holder gh;
         int error;
 
+        if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) {
+                clear_inode(inode);
+                return;
+        }
+
         if (inode->i_nlink || (sb->s_flags & MS_RDONLY))
                 goto out;
 
@@ -1558,7 +1557,7 @@ out_unlock:
                 fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
 out:
         /* Case 3 starts here */
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         gfs2_rs_delete(ip, NULL);
         gfs2_ordered_del_inode(ip);
         clear_inode(inode);
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index d09f6edda0ff..de25d5577e5d 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -138,9 +140,8 @@ static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
         if (simple_strtol(buf, NULL, 0) != 1)
                 return -EINVAL;
 
-        gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: withdrawing from cluster at user's request\n",
-                sdp->sd_fsname);
+        gfs2_lm_withdraw(sdp, "withdrawing from cluster at user's request\n");
+
         return len;
 }
 
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 2b20d7046bf3..bead90d27bad 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -51,6 +53,9 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
         if (revokes)
                 tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
                                                    sizeof(u64));
+        INIT_LIST_HEAD(&tr->tr_databuf);
+        INIT_LIST_HEAD(&tr->tr_buf);
+
         sb_start_intwrite(sdp->sd_vfs);
         gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh);
 
@@ -96,14 +101,13 @@ static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
 
 static void gfs2_print_trans(const struct gfs2_trans *tr)
 {
-        printk(KERN_WARNING "GFS2: Transaction created at: %pSR\n",
-               (void *)tr->tr_ip);
-        printk(KERN_WARNING "GFS2: blocks=%u revokes=%u reserved=%u touched=%d\n",
-               tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
-        printk(KERN_WARNING "GFS2: Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
-               tr->tr_num_buf_new, tr->tr_num_buf_rm,
-               tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
-               tr->tr_num_revoke, tr->tr_num_revoke_rm);
+        pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip);
+        pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n",
+                tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
+        pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
+                tr->tr_num_buf_new, tr->tr_num_buf_rm,
+                tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
+                tr->tr_num_revoke, tr->tr_num_revoke_rm);
 }
 
 void gfs2_trans_end(struct gfs2_sbd *sdp)
@@ -210,8 +214,7 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
                 set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
                 gfs2_pin(sdp, bd->bd_bh);
                 tr->tr_num_databuf_new++;
-                sdp->sd_log_num_databuf++;
-                list_add_tail(&bd->bd_list, &sdp->sd_log_le_databuf);
+                list_add_tail(&bd->bd_list, &tr->tr_databuf);
         }
         gfs2_log_unlock(sdp);
         unlock_buffer(bh);
@@ -230,16 +233,14 @@ static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
         set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
         mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
         if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
-                printk(KERN_ERR
-                       "Attempting to add uninitialised block to journal (inplace block=%lld)\n",
+                pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
                        (unsigned long long)bd->bd_bh->b_blocknr);
                 BUG();
         }
         gfs2_pin(sdp, bd->bd_bh);
         mh->__pad0 = cpu_to_be64(0);
         mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
-        sdp->sd_log_num_buf++;
-        list_add(&bd->bd_list, &sdp->sd_log_le_buf);
+        list_add(&bd->bd_list, &tr->tr_buf);
         tr->tr_num_buf_new++;
 }
 
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index f7109f689e61..86d2035ac669 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
@@ -30,22 +32,27 @@ mempool_t *gfs2_page_pool __read_mostly;
 
 void gfs2_assert_i(struct gfs2_sbd *sdp)
 {
-        printk(KERN_EMERG "GFS2: fsid=%s: fatal assertion failed\n",
-               sdp->sd_fsname);
+        fs_emerg(sdp, "fatal assertion failed\n");
 }
 
-int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 {
         struct lm_lockstruct *ls = &sdp->sd_lockstruct;
         const struct lm_lockops *lm = ls->ls_ops;
         va_list args;
+        struct va_format vaf;
 
         if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
             test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
                 return 0;
 
         va_start(args, fmt);
-        vprintk(fmt, args);
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        fs_err(sdp, "%pV", &vaf);
+
         va_end(args);
 
         if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW) {
@@ -66,7 +73,7 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
         }
 
         if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
-                panic("GFS2: fsid=%s: panic requested.\n", sdp->sd_fsname);
+                panic("GFS2: fsid=%s: panic requested\n", sdp->sd_fsname);
 
         return -1;
 }
@@ -82,10 +89,9 @@ int gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
 {
         int me;
         me = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: assertion \"%s\" failed\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname, assertion,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: assertion \"%s\" failed\n"
+                              "   function = %s, file = %s, line = %u\n",
+                              assertion, function, file, line);
         dump_stack();
         return (me) ? -1 : -2;
 }
@@ -105,11 +111,8 @@ int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
                 return -2;
 
         if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW)
-                printk(KERN_WARNING
-                       "GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
-                       "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                       sdp->sd_fsname, assertion,
-                       sdp->sd_fsname, function, file, line);
+                fs_warn(sdp, "warning: assertion \"%s\" failed at function = %s, file = %s, line = %u\n",
+                        assertion, function, file, line);
 
         if (sdp->sd_args.ar_debug)
                 BUG();
@@ -138,10 +141,8 @@ int gfs2_consist_i(struct gfs2_sbd *sdp, int cluster_wide, const char *function,
 {
         int rv;
         rv = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: filesystem consistency error\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: filesystem consistency error - function = %s, file = %s, line = %u\n",
+                              function, file, line);
         return rv;
 }
 
@@ -157,13 +158,12 @@ int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide,
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
         int rv;
         rv = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: filesystem consistency error\n"
-                "GFS2: fsid=%s:   inode = %llu %llu\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname,
-                sdp->sd_fsname, (unsigned long long)ip->i_no_formal_ino,
-                (unsigned long long)ip->i_no_addr,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: filesystem consistency error\n"
+                              "  inode = %llu %llu\n"
+                              "  function = %s, file = %s, line = %u\n",
+                              (unsigned long long)ip->i_no_formal_ino,
+                              (unsigned long long)ip->i_no_addr,
+                              function, file, line);
         return rv;
 }
 
@@ -179,12 +179,11 @@ int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide,
         struct gfs2_sbd *sdp = rgd->rd_sbd;
         int rv;
         rv = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: filesystem consistency error\n"
-                "GFS2: fsid=%s:   RG = %llu\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname,
-                sdp->sd_fsname, (unsigned long long)rgd->rd_addr,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: filesystem consistency error\n"
+                              "  RG = %llu\n"
+                              "  function = %s, file = %s, line = %u\n",
+                              (unsigned long long)rgd->rd_addr,
+                              function, file, line);
         return rv;
 }
 
@@ -200,12 +199,11 @@ int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
 {
         int me;
         me = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: invalid metadata block\n"
-                "GFS2: fsid=%s:   bh = %llu (%s)\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname,
-                sdp->sd_fsname, (unsigned long long)bh->b_blocknr, type,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: invalid metadata block\n"
+                              "  bh = %llu (%s)\n"
+                              "  function = %s, file = %s, line = %u\n",
+                              (unsigned long long)bh->b_blocknr, type,
+                              function, file, line);
         return (me) ? -1 : -2;
 }
 
@@ -221,12 +219,11 @@ int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
 {
         int me;
         me = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: invalid metadata block\n"
-                "GFS2: fsid=%s:   bh = %llu (type: exp=%u, found=%u)\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname,
-                sdp->sd_fsname, (unsigned long long)bh->b_blocknr, type, t,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: invalid metadata block\n"
+                              "  bh = %llu (type: exp=%u, found=%u)\n"
+                              "  function = %s, file = %s, line = %u\n",
+                              (unsigned long long)bh->b_blocknr, type, t,
+                              function, file, line);
         return (me) ? -1 : -2;
 }
 
@@ -241,10 +238,9 @@ int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
 {
         int rv;
         rv = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: I/O error\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: I/O error\n"
+                              "  function = %s, file = %s, line = %u\n",
+                              function, file, line);
         return rv;
 }
 
@@ -259,12 +255,11 @@ int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
 {
         int rv;
         rv = gfs2_lm_withdraw(sdp,
-                "GFS2: fsid=%s: fatal: I/O error\n"
-                "GFS2: fsid=%s:   block = %llu\n"
-                "GFS2: fsid=%s:   function = %s, file = %s, line = %u\n",
-                sdp->sd_fsname,
-                sdp->sd_fsname, (unsigned long long)bh->b_blocknr,
-                sdp->sd_fsname, function, file, line);
+                              "fatal: I/O error\n"
+                              "  block = %llu\n"
+                              "  function = %s, file = %s, line = %u\n",
+                              (unsigned long long)bh->b_blocknr,
+                              function, file, line);
         return rv;
 }
 
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index b7ffb09b99ea..cbdcbdf39614 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -10,22 +10,23 @@
 #ifndef __UTIL_DOT_H__
 #define __UTIL_DOT_H__
 
+#ifdef pr_fmt
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#endif
+
 #include <linux/mempool.h>
 
 #include "incore.h"
 
-#define fs_printk(level, fs, fmt, arg...) \
-        printk(level "GFS2: fsid=%s: " fmt , (fs)->sd_fsname , ## arg)
-
-#define fs_info(fs, fmt, arg...) \
-        fs_printk(KERN_INFO , fs , fmt , ## arg)
-
-#define fs_warn(fs, fmt, arg...) \
-        fs_printk(KERN_WARNING , fs , fmt , ## arg)
-
-#define fs_err(fs, fmt, arg...) \
-        fs_printk(KERN_ERR, fs , fmt , ## arg)
-
+#define fs_emerg(fs, fmt, ...)                                          \
+        pr_emerg("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
+#define fs_warn(fs, fmt, ...)                                           \
+        pr_warn("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
+#define fs_err(fs, fmt, ...)                                            \
+        pr_err("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
+#define fs_info(fs, fmt, ...)                                           \
+        pr_info("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
 
 void gfs2_assert_i(struct gfs2_sbd *sdp);
 
@@ -85,7 +86,7 @@ static inline int gfs2_meta_check(struct gfs2_sbd *sdp,
         struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
         u32 magic = be32_to_cpu(mh->mh_magic);
         if (unlikely(magic != GFS2_MAGIC)) {
-                printk(KERN_ERR "GFS2: Magic number missing at %llu\n",
+                pr_err("Magic number missing at %llu\n",
                        (unsigned long long)bh->b_blocknr);
                 return -EIO;
         }
@@ -164,7 +165,7 @@ static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
 #define gfs2_tune_get(sdp, field) \
 gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field)
 
-int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...);
+__printf(2, 3)
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...);
 
 #endif /* __UTIL_DOT_H__ */
-
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 380ab31b5e0f..9e2fecd62f62 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -547,7 +547,7 @@ out:
 
 void hfs_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         if (HFS_IS_RSRC(inode) && HFS_I(inode)->rsrc_inode) {
                 HFS_I(HFS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 2d2039e754cd..eee7206c38d1 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -112,6 +112,7 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static int hfs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_NODIRATIME;
         if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
                 return 0;
diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c
index 0f47890299c4..caf89a7be0a1 100644
--- a/fs/hfsplus/attributes.c
+++ b/fs/hfsplus/attributes.c
@@ -11,7 +11,7 @@
 
 static struct kmem_cache *hfsplus_attr_tree_cachep;
 
-int hfsplus_create_attr_tree_cache(void)
+int __init hfsplus_create_attr_tree_cache(void)
 {
         if (hfsplus_attr_tree_cachep)
                 return -EEXIST;
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index fbb212fbb1ef..a7aafb35b624 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -227,10 +227,8 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
         u32 ablock, dblock, mask;
         sector_t sector;
         int was_dirty = 0;
-        int shift;
 
         /* Convert inode block to disk allocation block */
-        shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
         ablock = iblock >> sbi->fs_shift;
 
         if (iblock >= hip->fs_blocks) {
@@ -498,11 +496,13 @@ int hfsplus_file_extend(struct inode *inode)
                         goto insert_extent;
         }
 out:
-        mutex_unlock(&hip->extents_lock);
         if (!res) {
                 hip->alloc_blocks += len;
+                mutex_unlock(&hip->extents_lock);
                 hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY);
+                return 0;
         }
+        mutex_unlock(&hip->extents_lock);
         return res;
 
 insert_extent:
@@ -556,11 +556,13 @@ void hfsplus_file_truncate(struct inode *inode)
 
         blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >>
                         HFSPLUS_SB(sb)->alloc_blksz_shift;
+
+        mutex_lock(&hip->extents_lock);
+
         alloc_cnt = hip->alloc_blocks;
         if (blk_cnt == alloc_cnt)
-                goto out;
+                goto out_unlock;
 
-        mutex_lock(&hip->extents_lock);
         res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
         if (res) {
                 mutex_unlock(&hip->extents_lock);
@@ -592,10 +594,10 @@ void hfsplus_file_truncate(struct inode *inode)
                 hfs_brec_remove(&fd);
         }
         hfs_find_exit(&fd);
-        mutex_unlock(&hip->extents_lock);
 
         hip->alloc_blocks = blk_cnt;
-out:
+out_unlock:
+        mutex_unlock(&hip->extents_lock);
         hip->phys_size = inode->i_size;
         hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >>
                 sb->s_blocksize_bits;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 62d571eb69ba..83dc29286b10 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -367,7 +367,7 @@ typedef int (*search_strategy_t)(struct hfs_bnode *,
  */
 
 /* attributes.c */
-int hfsplus_create_attr_tree_cache(void);
+int __init hfsplus_create_attr_tree_cache(void);
 void hfsplus_destroy_attr_tree_cache(void);
 hfsplus_attr_entry *hfsplus_alloc_attr_entry(void);
 void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 80875aa640ef..a513d2d36be9 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -161,7 +161,7 @@ static int hfsplus_write_inode(struct inode *inode,
 static void hfsplus_evict_inode(struct inode *inode)
 {
         hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         if (HFSPLUS_IS_RSRC(inode)) {
                 HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
@@ -323,6 +323,7 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
                 return 0;
         if (!(*flags & MS_RDONLY)) {
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index fe649d325b1f..9c470fde9878 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -230,7 +230,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb)
 
 static void hostfs_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         if (HOSTFS_I(inode)->fd != -1) {
                 close_file(&HOSTFS_I(inode)->fd);
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 9edeeb0ea97e..50a427313835 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -304,7 +304,7 @@ void hpfs_write_if_changed(struct inode *inode)
 
 void hpfs_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         if (!inode->i_nlink) {
                 hpfs_lock(inode->i_sb);
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 4534ff688b76..fe3463a43236 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -421,6 +421,8 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
         struct hpfs_sb_info *sbi = hpfs_sb(s);
         char *new_opts = kstrdup(data, GFP_KERNEL);
         
+        sync_filesystem(s);
+
         *flags |= MS_NOATIME;
         
         hpfs_lock(s);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d19b30ababf1..204027520937 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -366,7 +366,13 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
 
 static void hugetlbfs_evict_inode(struct inode *inode)
 {
+        struct resv_map *resv_map;
+
         truncate_hugepages(inode, 0);
+        resv_map = (struct resv_map *)inode->i_mapping->private_data;
+        /* root inode doesn't have the resv_map, so we should check it */
+        if (resv_map)
+                resv_map_release(&resv_map->refs);
         clear_inode(inode);
 }
 
@@ -476,6 +482,11 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
                                         umode_t mode, dev_t dev)
 {
         struct inode *inode;
+        struct resv_map *resv_map;
+
+        resv_map = resv_map_alloc();
+        if (!resv_map)
+                return NULL;
 
         inode = new_inode(sb);
         if (inode) {
@@ -487,7 +498,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
                 inode->i_mapping->a_ops = &hugetlbfs_aops;
                 inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
                 inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-                INIT_LIST_HEAD(&inode->i_mapping->private_list);
+                inode->i_mapping->private_data = resv_map;
                 info = HUGETLBFS_I(inode);
                 /*
                  * The policy is initialized here even if we are creating a
@@ -517,7 +528,9 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
                         break;
                 }
                 lockdep_annotate_inode_mutex_key(inode);
-        }
+        } else
+                kref_put(&resv_map->refs, resv_map_release);
+
         return inode;
 }
 
diff --git a/fs/inode.c b/fs/inode.c
index 4bcdad3c9361..f96d2a6f88cc 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -503,6 +503,7 @@ void clear_inode(struct inode *inode)
          */
         spin_lock_irq(&inode->i_data.tree_lock);
         BUG_ON(inode->i_data.nrpages);
+        BUG_ON(inode->i_data.nrshadows);
         spin_unlock_irq(&inode->i_data.tree_lock);
         BUG_ON(!list_empty(&inode->i_data.private_list));
         BUG_ON(!(inode->i_state & I_FREEING));
@@ -548,8 +549,7 @@ static void evict(struct inode *inode)
         if (op->evict_inode) {
                 op->evict_inode(inode);
         } else {
-                if (inode->i_data.nrpages)
-                        truncate_inode_pages(&inode->i_data, 0);
+                truncate_inode_pages_final(&inode->i_data);
                 clear_inode(inode);
         }
         if (S_ISBLK(inode->i_mode) && inode->i_bdev)
@@ -944,24 +944,22 @@ EXPORT_SYMBOL(unlock_new_inode);
 
 /**
  * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ *
+ * Lock any non-NULL argument that is not a directory.
+ * Zero, one or two objects may be locked by this function.
+ *
  * @inode1: first inode to lock
  * @inode2: second inode to lock
  */
 void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 {
-        WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
-        if (inode1 == inode2 || !inode2) {
-                mutex_lock(&inode1->i_mutex);
-                return;
-        }
-        WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
-        if (inode1 < inode2) {
+        if (inode1 > inode2)
+                swap(inode1, inode2);
+
+        if (inode1 && !S_ISDIR(inode1->i_mode))
                 mutex_lock(&inode1->i_mutex);
+        if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
                 mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
-        } else {
-                mutex_lock(&inode2->i_mutex);
-                mutex_lock_nested(&inode1->i_mutex, I_MUTEX_NONDIR2);
-        }
 }
 EXPORT_SYMBOL(lock_two_nondirectories);
 
@@ -972,8 +970,9 @@ EXPORT_SYMBOL(lock_two_nondirectories);
  */
 void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 {
-        mutex_unlock(&inode1->i_mutex);
-        if (inode2 && inode2 != inode1)
+        if (inode1 && !S_ISDIR(inode1->i_mode))
+                mutex_unlock(&inode1->i_mutex);
+        if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
                 mutex_unlock(&inode2->i_mutex);
 }
 EXPORT_SYMBOL(unlock_two_nondirectories);
@@ -1899,3 +1898,34 @@ void inode_dio_done(struct inode *inode)
                 wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
 }
 EXPORT_SYMBOL(inode_dio_done);
+
+/*
+ * inode_set_flags - atomically set some inode flags
+ *
+ * Note: the caller should be holding i_mutex, or else be sure that
+ * they have exclusive access to the inode structure (i.e., while the
+ * inode is being instantiated).  The reason for the cmpxchg() loop
+ * --- which wouldn't be necessary if all code paths which modify
+ * i_flags actually followed this rule, is that there is at least one
+ * code path which doesn't today --- for example,
+ * __generic_file_aio_write() calls file_remove_suid() without holding
+ * i_mutex --- so we use cmpxchg() out of an abundance of caution.
+ *
+ * In the long run, i_mutex is overkill, and we should probably look
+ * at using the i_lock spinlock to protect i_flags, and then make sure
+ * it is so documented in include/linux/fs.h and that all code follows
+ * the locking convention!!
+ */
+void inode_set_flags(struct inode *inode, unsigned int flags,
+                     unsigned int mask)
+{
+        unsigned int old_flags, new_flags;
+
+        WARN_ON_ONCE(flags & ~mask);
+        do {
+                old_flags = ACCESS_ONCE(inode->i_flags);
+                new_flags = (old_flags & ~mask) | flags;
+        } while (unlikely(cmpxchg(&inode->i_flags, old_flags,
+                                  new_flags) != old_flags));
+}
+EXPORT_SYMBOL(inode_set_flags);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 4a9e10ea13f2..6af66ee56390 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -117,6 +117,7 @@ static void destroy_inodecache(void)
 
 static int isofs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         if (!(*flags & MS_RDONLY))
                 return -EROFS;
         return 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index cf2fc0594063..5f26139a165a 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -555,7 +555,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         blk_start_plug(&plug);
         jbd2_journal_write_revoke_records(journal, commit_transaction,
                                           &log_bufs, WRITE_SYNC);
-        blk_finish_plug(&plug);
 
         jbd_debug(3, "JBD2: commit phase 2b\n");
 
@@ -582,7 +581,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         err = 0;
         bufs = 0;
         descriptor = NULL;
-        blk_start_plug(&plug);
         while (commit_transaction->t_buffers) {
 
                 /* Find the next buffer to be journaled... */
@@ -1067,6 +1065,25 @@ restart_loop:
                 goto restart_loop;
         }
 
+        /* Add the transaction to the checkpoint list
+         * __journal_remove_checkpoint() can not destroy transaction
+         * under us because it is not marked as T_FINISHED yet */
+        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;
+        }
+        spin_unlock(&journal->j_list_lock);
+
         /* Done with this transaction! */
 
         jbd_debug(3, "JBD2: commit phase 7\n");
@@ -1085,24 +1102,7 @@ restart_loop:
                 atomic_read(&commit_transaction->t_handle_count);
         trace_jbd2_run_stats(journal->j_fs_dev->bd_dev,
                              commit_transaction->t_tid, &stats.run);
-
-        /*
-         * Calculate overall stats
-         */
-        spin_lock(&journal->j_history_lock);
-        journal->j_stats.ts_tid++;
-        if (commit_transaction->t_requested)
-                journal->j_stats.ts_requested++;
-        journal->j_stats.run.rs_wait += stats.run.rs_wait;
-        journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
-        journal->j_stats.run.rs_running += stats.run.rs_running;
-        journal->j_stats.run.rs_locked += stats.run.rs_locked;
-        journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
-        journal->j_stats.run.rs_logging += stats.run.rs_logging;
-        journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
-        journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
-        journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
-        spin_unlock(&journal->j_history_lock);
+        stats.ts_requested = (commit_transaction->t_requested) ? 1 : 0;
 
         commit_transaction->t_state = T_COMMIT_CALLBACK;
         J_ASSERT(commit_transaction == journal->j_committing_transaction);
@@ -1122,24 +1122,6 @@ restart_loop:
 
         write_unlock(&journal->j_state_lock);
 
-        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;
-        }
-        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);
 
@@ -1150,7 +1132,7 @@ restart_loop:
         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 */
+        /* Check if the transaction can be dropped now that we are finished */
         if (commit_transaction->t_checkpoint_list == NULL &&
             commit_transaction->t_checkpoint_io_list == NULL) {
                 __jbd2_journal_drop_transaction(journal, commit_transaction);
@@ -1159,4 +1141,21 @@ restart_loop:
         spin_unlock(&journal->j_list_lock);
         write_unlock(&journal->j_state_lock);
         wake_up(&journal->j_wait_done_commit);
+
+        /*
+         * Calculate overall stats
+         */
+        spin_lock(&journal->j_history_lock);
+        journal->j_stats.ts_tid++;
+        journal->j_stats.ts_requested += stats.ts_requested;
+        journal->j_stats.run.rs_wait += stats.run.rs_wait;
+        journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
+        journal->j_stats.run.rs_running += stats.run.rs_running;
+        journal->j_stats.run.rs_locked += stats.run.rs_locked;
+        journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
+        journal->j_stats.run.rs_logging += stats.run.rs_logging;
+        journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
+        journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
+        journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
+        spin_unlock(&journal->j_history_lock);
 }
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 5fa344afb49a..67b8e303946c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -122,7 +122,7 @@ EXPORT_SYMBOL(__jbd2_debug);
 #endif
 
 /* Checksumming functions */
-int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
+static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
         if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
                 return 1;
@@ -143,7 +143,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
         return cpu_to_be32(csum);
 }
 
-int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
+static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 {
         if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
                 return 1;
@@ -151,7 +151,7 @@ int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
         return sb->s_checksum == jbd2_superblock_csum(j, sb);
 }
 
-void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
+static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
 {
         if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
                 return;
@@ -302,8 +302,8 @@ static void journal_kill_thread(journal_t *journal)
         journal->j_flags |= JBD2_UNMOUNT;
 
         while (journal->j_task) {
-                wake_up(&journal->j_wait_commit);
                 write_unlock(&journal->j_state_lock);
+                wake_up(&journal->j_wait_commit);
                 wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
                 write_lock(&journal->j_state_lock);
         }
@@ -710,8 +710,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
         while (tid_gt(tid, journal->j_commit_sequence)) {
                 jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
                                   tid, journal->j_commit_sequence);
-                wake_up(&journal->j_wait_commit);
                 read_unlock(&journal->j_state_lock);
+                wake_up(&journal->j_wait_commit);
                 wait_event(journal->j_wait_done_commit,
                                 !tid_gt(tid, journal->j_commit_sequence));
                 read_lock(&journal->j_state_lock);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 60bb365f54a5..38cfcf5f6fce 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1073,7 +1073,6 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
          * reused here.
          */
         jbd_lock_bh_state(bh);
-        spin_lock(&journal->j_list_lock);
         J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
                 jh->b_transaction == NULL ||
                 (jh->b_transaction == journal->j_committing_transaction &&
@@ -1096,12 +1095,14 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
                 jh->b_modified = 0;
 
                 JBUFFER_TRACE(jh, "file as BJ_Reserved");
+                spin_lock(&journal->j_list_lock);
                 __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
         } else if (jh->b_transaction == journal->j_committing_transaction) {
                 /* first access by this transaction */
                 jh->b_modified = 0;
 
                 JBUFFER_TRACE(jh, "set next transaction");
+                spin_lock(&journal->j_list_lock);
                 jh->b_next_transaction = transaction;
         }
         spin_unlock(&journal->j_list_lock);
@@ -1312,7 +1313,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
                              journal->j_running_transaction)) {
                         printk(KERN_ERR "JBD2: %s: "
                                "jh->b_transaction (%llu, %p, %u) != "
-                               "journal->j_running_transaction (%p, %u)",
+                               "journal->j_running_transaction (%p, %u)\n",
                                journal->j_devname,
                                (unsigned long long) bh->b_blocknr,
                                jh->b_transaction,
@@ -1335,30 +1336,25 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
          */
         if (jh->b_transaction != transaction) {
                 JBUFFER_TRACE(jh, "already on other transaction");
-                if (unlikely(jh->b_transaction !=
-                             journal->j_committing_transaction)) {
-                        printk(KERN_ERR "JBD2: %s: "
-                               "jh->b_transaction (%llu, %p, %u) != "
-                               "journal->j_committing_transaction (%p, %u)",
+                if (unlikely(((jh->b_transaction !=
+                               journal->j_committing_transaction)) ||
+                             (jh->b_next_transaction != transaction))) {
+                        printk(KERN_ERR "jbd2_journal_dirty_metadata: %s: "
+                               "bad jh for block %llu: "
+                               "transaction (%p, %u), "
+                               "jh->b_transaction (%p, %u), "
+                               "jh->b_next_transaction (%p, %u), jlist %u\n",
                                journal->j_devname,
                                (unsigned long long) bh->b_blocknr,
+                               transaction, transaction->t_tid,
                                jh->b_transaction,
-                               jh->b_transaction ? jh->b_transaction->t_tid : 0,
-                               journal->j_committing_transaction,
-                               journal->j_committing_transaction ?
-                               journal->j_committing_transaction->t_tid : 0);
-                        ret = -EINVAL;
-                }
-                if (unlikely(jh->b_next_transaction != transaction)) {
-                        printk(KERN_ERR "JBD2: %s: "
-                               "jh->b_next_transaction (%llu, %p, %u) != "
-                               "transaction (%p, %u)",
-                               journal->j_devname,
-                               (unsigned long long) bh->b_blocknr,
+                               jh->b_transaction ?
+                               jh->b_transaction->t_tid : 0,
                                jh->b_next_transaction,
                                jh->b_next_transaction ?
                                jh->b_next_transaction->t_tid : 0,
-                               transaction, transaction->t_tid);
+                               jh->b_jlist);
+                        WARN_ON(1);
                         ret = -EINVAL;
                 }
                 /* And this case is illegal: we can't reuse another
@@ -1415,7 +1411,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
         BUFFER_TRACE(bh, "entry");
 
         jbd_lock_bh_state(bh);
-        spin_lock(&journal->j_list_lock);
 
         if (!buffer_jbd(bh))
                 goto not_jbd;
@@ -1468,6 +1463,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
                  * we know to remove the checkpoint after we commit.
                  */
 
+                spin_lock(&journal->j_list_lock);
                 if (jh->b_cp_transaction) {
                         __jbd2_journal_temp_unlink_buffer(jh);
                         __jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
@@ -1480,6 +1476,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
                                 goto drop;
                         }
                 }
+                spin_unlock(&journal->j_list_lock);
         } else if (jh->b_transaction) {
                 J_ASSERT_JH(jh, (jh->b_transaction ==
                                  journal->j_committing_transaction));
@@ -1491,7 +1488,9 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 
                 if (jh->b_next_transaction) {
                         J_ASSERT(jh->b_next_transaction == transaction);
+                        spin_lock(&journal->j_list_lock);
                         jh->b_next_transaction = NULL;
+                        spin_unlock(&journal->j_list_lock);
 
                         /*
                          * only drop a reference if this transaction modified
@@ -1503,7 +1502,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
         }
 
 not_jbd:
-        spin_unlock(&journal->j_list_lock);
         jbd_unlock_bh_state(bh);
         __brelse(bh);
 drop:
@@ -1821,11 +1819,11 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
         if (buffer_locked(bh) || buffer_dirty(bh))
                 goto out;
 
-        if (jh->b_next_transaction != NULL)
+        if (jh->b_next_transaction != NULL || jh->b_transaction != NULL)
                 goto out;
 
         spin_lock(&journal->j_list_lock);
-        if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
+        if (jh->b_cp_transaction != NULL) {
                 /* written-back checkpointed metadata buffer */
                 JBUFFER_TRACE(jh, "remove from checkpoint list");
                 __jbd2_journal_remove_checkpoint(jh);
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index a69e426435dd..f73991522672 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -242,7 +242,7 @@ void jffs2_evict_inode (struct inode *inode)
 
         jffs2_dbg(1, "%s(): ino #%lu mode %o\n",
                   __func__, inode->i_ino, inode->i_mode);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         jffs2_do_clear_inode(c, f);
 }
@@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c,
         struct inode *inode = OFNI_EDONI_2SFFJ(f);
         struct page *pg;
 
-        pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
+        pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
                              (void *)jffs2_do_readpage_unlock, inode);
         if (IS_ERR(pg))
                 return (void *)pg;
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 0defb1cc2a35..0918f0e2e266 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -243,6 +243,7 @@ static int jffs2_remount_fs(struct super_block *sb, int *flags, char *data)
         struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
         int err;
 
+        sync_filesystem(sb);
         err = jffs2_parse_options(c, data);
         if (err)
                 return -EINVAL;
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index f4aab719add5..6f8fe72c2a7a 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -154,7 +154,7 @@ void jfs_evict_inode(struct inode *inode)
                 dquot_initialize(inode);
 
                 if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
-                        truncate_inode_pages(&inode->i_data, 0);
+                        truncate_inode_pages_final(&inode->i_data);
 
                         if (test_cflag(COMMIT_Freewmap, inode))
                                 jfs_free_zero_link(inode);
@@ -168,7 +168,7 @@ void jfs_evict_inode(struct inode *inode)
                         dquot_free_inode(inode);
                 }
         } else {
-                truncate_inode_pages(&inode->i_data, 0);
+                truncate_inode_pages_final(&inode->i_data);
         }
         clear_inode(inode);
         dquot_drop(inode);
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index e2b7483444fd..97f7fda51890 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -418,6 +418,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
         int flag = JFS_SBI(sb)->flag;
         int ret;
 
+        sync_filesystem(sb);
         if (!parse_options(data, sb, &newLVSize, &flag)) {
                 return -EINVAL;
         }
diff --git a/fs/kernfs/Kconfig b/fs/kernfs/Kconfig
new file mode 100644
index 000000000000..397b5f7a7a16
--- /dev/null
+++ b/fs/kernfs/Kconfig
@@ -0,0 +1,7 @@
+#
+# KERNFS should be selected by its users
+#
+
+config KERNFS
+        bool
+        default n
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index bd6e18be6e1a..78f3403300af 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -8,6 +8,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/idr.h>
@@ -18,9 +19,162 @@
 #include "kernfs-internal.h"
 
 DEFINE_MUTEX(kernfs_mutex);
+static DEFINE_SPINLOCK(kernfs_rename_lock);     /* kn->parent and ->name */
+static char kernfs_pr_cont_buf[PATH_MAX];       /* protected by rename_lock */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
+static bool kernfs_active(struct kernfs_node *kn)
+{
+        lockdep_assert_held(&kernfs_mutex);
+        return atomic_read(&kn->active) >= 0;
+}
+
+static bool kernfs_lockdep(struct kernfs_node *kn)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        return kn->flags & KERNFS_LOCKDEP;
+#else
+        return false;
+#endif
+}
+
+static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+        return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+}
+
+static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf,
+                                              size_t buflen)
+{
+        char *p = buf + buflen;
+        int len;
+
+        *--p = '\0';
+
+        do {
+                len = strlen(kn->name);
+                if (p - buf < len + 1) {
+                        buf[0] = '\0';
+                        p = NULL;
+                        break;
+                }
+                p -= len;
+                memcpy(p, kn->name, len);
+                *--p = '/';
+                kn = kn->parent;
+        } while (kn && kn->parent);
+
+        return p;
+}
+
+/**
+ * kernfs_name - obtain the name of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
+ * similar to strlcpy().  It returns the length of @kn's name and if @buf
+ * isn't long enough, it's filled upto @buflen-1 and nul terminated.
+ *
+ * This function can be called from any context.
+ */
+int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+        unsigned long flags;
+        int ret;
+
+        spin_lock_irqsave(&kernfs_rename_lock, flags);
+        ret = kernfs_name_locked(kn, buf, buflen);
+        spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+        return ret;
+}
+
+/**
+ * kernfs_path - build full path of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Builds and returns the full path of @kn in @buf of @buflen bytes.  The
+ * path is built from the end of @buf so the returned pointer usually
+ * doesn't match @buf.  If @buf isn't long enough, @buf is nul terminated
+ * and %NULL is returned.
+ */
+char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+        unsigned long flags;
+        char *p;
+
+        spin_lock_irqsave(&kernfs_rename_lock, flags);
+        p = kernfs_path_locked(kn, buf, buflen);
+        spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+        return p;
+}
+EXPORT_SYMBOL_GPL(kernfs_path);
+
+/**
+ * pr_cont_kernfs_name - pr_cont name of a kernfs_node
+ * @kn: kernfs_node of interest
+ *
+ * This function can be called from any context.
+ */
+void pr_cont_kernfs_name(struct kernfs_node *kn)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&kernfs_rename_lock, flags);
+
+        kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+        pr_cont("%s", kernfs_pr_cont_buf);
+
+        spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+}
+
+/**
+ * pr_cont_kernfs_path - pr_cont path of a kernfs_node
+ * @kn: kernfs_node of interest
+ *
+ * This function can be called from any context.
+ */
+void pr_cont_kernfs_path(struct kernfs_node *kn)
+{
+        unsigned long flags;
+        char *p;
+
+        spin_lock_irqsave(&kernfs_rename_lock, flags);
+
+        p = kernfs_path_locked(kn, kernfs_pr_cont_buf,
+                               sizeof(kernfs_pr_cont_buf));
+        if (p)
+                pr_cont("%s", p);
+        else
+                pr_cont("<name too long>");
+
+        spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+}
+
+/**
+ * kernfs_get_parent - determine the parent node and pin it
+ * @kn: kernfs_node of interest
+ *
+ * Determines @kn's parent, pins and returns it.  This function can be
+ * called from any context.
+ */
+struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
+{
+        struct kernfs_node *parent;
+        unsigned long flags;
+
+        spin_lock_irqsave(&kernfs_rename_lock, flags);
+        parent = kn->parent;
+        kernfs_get(parent);
+        spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+
+        return parent;
+}
+
 /**
  *      kernfs_name_hash
  *      @name: Null terminated string to hash
@@ -37,7 +191,7 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns)
         hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
         hash &= 0x7fffffffU;
         /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
-        if (hash < 1)
+        if (hash < 2)
                 hash += 2;
         if (hash >= INT_MAX)
                 hash = INT_MAX - 1;
@@ -105,18 +259,24 @@ static int kernfs_link_sibling(struct kernfs_node *kn)
  *      kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree
  *      @kn: kernfs_node of interest
  *
- *      Unlink @kn from its sibling rbtree which starts from
- *      kn->parent->dir.children.
+ *      Try to unlink @kn from its sibling rbtree which starts from
+ *      kn->parent->dir.children.  Returns %true if @kn was actually
+ *      removed, %false if @kn wasn't on the rbtree.
  *
  *      Locking:
  *      mutex_lock(kernfs_mutex)
  */
-static void kernfs_unlink_sibling(struct kernfs_node *kn)
+static bool kernfs_unlink_sibling(struct kernfs_node *kn)
 {
+        if (RB_EMPTY_NODE(&kn->rb))
+                return false;
+
         if (kernfs_type(kn) == KERNFS_DIR)
                 kn->parent->dir.subdirs--;
 
         rb_erase(&kn->rb, &kn->parent->dir.children);
+        RB_CLEAR_NODE(&kn->rb);
+        return true;
 }
 
 /**
@@ -137,7 +297,7 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
         if (!atomic_inc_unless_negative(&kn->active))
                 return NULL;
 
-        if (kn->flags & KERNFS_LOCKDEP)
+        if (kernfs_lockdep(kn))
                 rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_);
         return kn;
 }
@@ -151,59 +311,57 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
  */
 void kernfs_put_active(struct kernfs_node *kn)
 {
+        struct kernfs_root *root = kernfs_root(kn);
         int v;
 
         if (unlikely(!kn))
                 return;
 
-        if (kn->flags & KERNFS_LOCKDEP)
+        if (kernfs_lockdep(kn))
                 rwsem_release(&kn->dep_map, 1, _RET_IP_);
         v = atomic_dec_return(&kn->active);
         if (likely(v != KN_DEACTIVATED_BIAS))
                 return;
 
-        /*
-         * atomic_dec_return() is a mb(), we'll always see the updated
-         * kn->u.completion.
-         */
-        complete(kn->u.completion);
+        wake_up_all(&root->deactivate_waitq);
 }
 
 /**
- *      kernfs_deactivate - deactivate kernfs_node
- *      @kn: kernfs_node to deactivate
+ * kernfs_drain - drain kernfs_node
+ * @kn: kernfs_node to drain
  *
- *      Deny new active references and drain existing ones.
+ * Drain existing usages and nuke all existing mmaps of @kn.  Mutiple
+ * removers may invoke this function concurrently on @kn and all will
+ * return after draining is complete.
  */
-static void kernfs_deactivate(struct kernfs_node *kn)
+static void kernfs_drain(struct kernfs_node *kn)
+        __releases(&kernfs_mutex) __acquires(&kernfs_mutex)
 {
-        DECLARE_COMPLETION_ONSTACK(wait);
-        int v;
+        struct kernfs_root *root = kernfs_root(kn);
 
-        BUG_ON(!(kn->flags & KERNFS_REMOVED));
-
-        if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF))
-                return;
+        lockdep_assert_held(&kernfs_mutex);
+        WARN_ON_ONCE(kernfs_active(kn));
 
-        kn->u.completion = (void *)&wait;
+        mutex_unlock(&kernfs_mutex);
 
-        if (kn->flags & KERNFS_LOCKDEP)
+        if (kernfs_lockdep(kn)) {
                 rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
-        /* atomic_add_return() is a mb(), put_active() will always see
-         * the updated kn->u.completion.
-         */
-        v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
-
-        if (v != KN_DEACTIVATED_BIAS) {
-                if (kn->flags & KERNFS_LOCKDEP)
+                if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS)
                         lock_contended(&kn->dep_map, _RET_IP_);
-                wait_for_completion(&wait);
         }
 
-        if (kn->flags & KERNFS_LOCKDEP) {
+        /* but everyone should wait for draining */
+        wait_event(root->deactivate_waitq,
+                   atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);
+
+        if (kernfs_lockdep(kn)) {
                 lock_acquired(&kn->dep_map, _RET_IP_);
                 rwsem_release(&kn->dep_map, 1, _RET_IP_);
         }
+
+        kernfs_unmap_bin_file(kn);
+
+        mutex_lock(&kernfs_mutex);
 }
 
 /**
@@ -234,13 +392,15 @@ void kernfs_put(struct kernfs_node *kn)
                 return;
         root = kernfs_root(kn);
  repeat:
-        /* Moving/renaming is always done while holding reference.
+        /*
+         * Moving/renaming is always done while holding reference.
          * kn->parent won't change beneath us.
          */
         parent = kn->parent;
 
-        WARN(!(kn->flags & KERNFS_REMOVED), "kernfs: free using entry: %s/%s\n",
-             parent ? parent->name : "", kn->name);
+        WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS,
+                  "kernfs_put: %s/%s: released with incorrect active_ref %d\n",
+                  parent ? parent->name : "", kn->name, atomic_read(&kn->active));
 
         if (kernfs_type(kn) == KERNFS_LINK)
                 kernfs_put(kn->symlink.target_kn);
@@ -282,8 +442,8 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
         kn = dentry->d_fsdata;
         mutex_lock(&kernfs_mutex);
 
-        /* The kernfs node has been deleted */
-        if (kn->flags & KERNFS_REMOVED)
+        /* The kernfs node has been deactivated */
+        if (!kernfs_active(kn))
                 goto out_bad;
 
         /* The kernfs node has been moved? */
@@ -328,6 +488,24 @@ const struct dentry_operations kernfs_dops = {
         .d_release      = kernfs_dop_release,
 };
 
+/**
+ * kernfs_node_from_dentry - determine kernfs_node associated with a dentry
+ * @dentry: the dentry in question
+ *
+ * Return the kernfs_node associated with @dentry.  If @dentry is not a
+ * kernfs one, %NULL is returned.
+ *
+ * While the returned kernfs_node will stay accessible as long as @dentry
+ * is accessible, the returned node can be in any state and the caller is
+ * fully responsible for determining what's accessible.
+ */
+struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
+{
+        if (dentry->d_sb->s_op == &kernfs_sops)
+                return dentry->d_fsdata;
+        return NULL;
+}
+
 static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
                                              const char *name, umode_t mode,
                                              unsigned flags)
@@ -352,11 +530,12 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
         kn->ino = ret;
 
         atomic_set(&kn->count, 1);
-        atomic_set(&kn->active, 0);
+        atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
+        RB_CLEAR_NODE(&kn->rb);
 
         kn->name = name;
         kn->mode = mode;
-        kn->flags = flags | KERNFS_REMOVED;
+        kn->flags = flags;
 
         return kn;
 
@@ -382,69 +561,44 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 }
 
 /**
- *      kernfs_addrm_start - prepare for kernfs_node add/remove
- *      @acxt: pointer to kernfs_addrm_cxt to be used
- *
- *      This function is called when the caller is about to add or remove
- *      kernfs_node.  This function acquires kernfs_mutex.  @acxt is used
- *      to keep and pass context to other addrm functions.
- *
- *      LOCKING:
- *      Kernel thread context (may sleep).  kernfs_mutex is locked on
- *      return.
- */
-void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt)
-        __acquires(kernfs_mutex)
-{
-        memset(acxt, 0, sizeof(*acxt));
-
-        mutex_lock(&kernfs_mutex);
-}
-
-/**
  *      kernfs_add_one - add kernfs_node to parent without warning
- *      @acxt: addrm context to use
  *      @kn: kernfs_node to be added
  *
  *      The caller must already have initialized @kn->parent.  This
  *      function increments nlink of the parent's inode if @kn is a
  *      directory and link into the children list of the parent.
  *
- *      This function should be called between calls to
- *      kernfs_addrm_start() and kernfs_addrm_finish() and should be passed
- *      the same @acxt as passed to kernfs_addrm_start().
- *
- *      LOCKING:
- *      Determined by kernfs_addrm_start().
- *
  *      RETURNS:
  *      0 on success, -EEXIST if entry with the given name already
  *      exists.
  */
-int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
+int kernfs_add_one(struct kernfs_node *kn)
 {
         struct kernfs_node *parent = kn->parent;
-        bool has_ns = kernfs_ns_enabled(parent);
         struct kernfs_iattrs *ps_iattr;
+        bool has_ns;
         int ret;
 
-        if (has_ns != (bool)kn->ns) {
-                WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
-                     has_ns ? "required" : "invalid", parent->name, kn->name);
-                return -EINVAL;
-        }
+        mutex_lock(&kernfs_mutex);
+
+        ret = -EINVAL;
+        has_ns = kernfs_ns_enabled(parent);
+        if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
+                 has_ns ? "required" : "invalid", parent->name, kn->name))
+                goto out_unlock;
 
         if (kernfs_type(parent) != KERNFS_DIR)
-                return -EINVAL;
+                goto out_unlock;
 
-        if (parent->flags & KERNFS_REMOVED)
-                return -ENOENT;
+        ret = -ENOENT;
+        if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent))
+                goto out_unlock;
 
         kn->hash = kernfs_name_hash(kn->name, kn->ns);
 
         ret = kernfs_link_sibling(kn);
         if (ret)
-                return ret;
+                goto out_unlock;
 
         /* Update timestamps on the parent */
         ps_iattr = parent->iattr;
@@ -453,82 +607,22 @@ int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
                 ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
         }
 
-        /* Mark the entry added into directory tree */
-        kn->flags &= ~KERNFS_REMOVED;
-
-        return 0;
-}
-
-/**
- *      kernfs_remove_one - remove kernfs_node from parent
- *      @acxt: addrm context to use
- *      @kn: kernfs_node to be removed
- *
- *      Mark @kn removed and drop nlink of parent inode if @kn is a
- *      directory.  @kn is unlinked from the children list.
- *
- *      This function should be called between calls to
- *      kernfs_addrm_start() and kernfs_addrm_finish() and should be
- *      passed the same @acxt as passed to kernfs_addrm_start().
- *
- *      LOCKING:
- *      Determined by kernfs_addrm_start().
- */
-static void kernfs_remove_one(struct kernfs_addrm_cxt *acxt,
-                              struct kernfs_node *kn)
-{
-        struct kernfs_iattrs *ps_iattr;
+        mutex_unlock(&kernfs_mutex);
 
         /*
-         * Removal can be called multiple times on the same node.  Only the
-         * first invocation is effective and puts the base ref.
+         * Activate the new node unless CREATE_DEACTIVATED is requested.
+         * If not activated here, the kernfs user is responsible for
+         * activating the node with kernfs_activate().  A node which hasn't
+         * been activated is not visible to userland and its removal won't
+         * trigger deactivation.
          */
-        if (kn->flags & KERNFS_REMOVED)
-                return;
-
-        if (kn->parent) {
-                kernfs_unlink_sibling(kn);
-
-                /* Update timestamps on the parent */
-                ps_iattr = kn->parent->iattr;
-                if (ps_iattr) {
-                        ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
-                        ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
-                }
-        }
-
-        kn->flags |= KERNFS_REMOVED;
-        kn->u.removed_list = acxt->removed;
-        acxt->removed = kn;
-}
+        if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED))
+                kernfs_activate(kn);
+        return 0;
 
-/**
- *      kernfs_addrm_finish - finish up kernfs_node add/remove
- *      @acxt: addrm context to finish up
- *
- *      Finish up kernfs_node add/remove.  Resources acquired by
- *      kernfs_addrm_start() are released and removed kernfs_nodes are
- *      cleaned up.
- *
- *      LOCKING:
- *      kernfs_mutex is released.
- */
-void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt)
-        __releases(kernfs_mutex)
-{
-        /* release resources acquired by kernfs_addrm_start() */
+out_unlock:
         mutex_unlock(&kernfs_mutex);
-
-        /* kill removed kernfs_nodes */
-        while (acxt->removed) {
-                struct kernfs_node *kn = acxt->removed;
-
-                acxt->removed = kn->u.removed_list;
-
-                kernfs_deactivate(kn);
-                kernfs_unmap_bin_file(kn);
-                kernfs_put(kn);
-        }
+        return ret;
 }
 
 /**
@@ -599,13 +693,15 @@ EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
 
 /**
  * kernfs_create_root - create a new kernfs hierarchy
- * @kdops: optional directory syscall operations for the hierarchy
+ * @scops: optional syscall operations for the hierarchy
+ * @flags: KERNFS_ROOT_* flags
  * @priv: opaque data associated with the new directory
  *
  * Returns the root of the new hierarchy on success, ERR_PTR() value on
  * failure.
  */
-struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
+                                       unsigned int flags, void *priv)
 {
         struct kernfs_root *root;
         struct kernfs_node *kn;
@@ -624,12 +720,16 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
                 return ERR_PTR(-ENOMEM);
         }
 
-        kn->flags &= ~KERNFS_REMOVED;
         kn->priv = priv;
         kn->dir.root = root;
 
-        root->dir_ops = kdops;
+        root->syscall_ops = scops;
+        root->flags = flags;
         root->kn = kn;
+        init_waitqueue_head(&root->deactivate_waitq);
+
+        if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED))
+                kernfs_activate(kn);
 
         return root;
 }
@@ -660,7 +760,6 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
                                          const char *name, umode_t mode,
                                          void *priv, const void *ns)
 {
-        struct kernfs_addrm_cxt acxt;
         struct kernfs_node *kn;
         int rc;
 
@@ -674,10 +773,7 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
         kn->priv = priv;
 
         /* link in */
-        kernfs_addrm_start(&acxt);
-        rc = kernfs_add_one(&acxt, kn);
-        kernfs_addrm_finish(&acxt);
-
+        rc = kernfs_add_one(kn);
         if (!rc)
                 return kn;
 
@@ -703,7 +799,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
         kn = kernfs_find_ns(parent, dentry->d_name.name, ns);
 
         /* no such entry */
-        if (!kn) {
+        if (!kn || !kernfs_active(kn)) {
                 ret = NULL;
                 goto out_unlock;
         }
@@ -728,23 +824,37 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
                             umode_t mode)
 {
         struct kernfs_node *parent = dir->i_private;
-        struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops;
+        struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops;
+        int ret;
 
-        if (!kdops || !kdops->mkdir)
+        if (!scops || !scops->mkdir)
                 return -EPERM;
 
-        return kdops->mkdir(parent, dentry->d_name.name, mode);
+        if (!kernfs_get_active(parent))
+                return -ENODEV;
+
+        ret = scops->mkdir(parent, dentry->d_name.name, mode);
+
+        kernfs_put_active(parent);
+        return ret;
 }
 
 static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
 {
         struct kernfs_node *kn  = dentry->d_fsdata;
-        struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+        struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
+        int ret;
 
-        if (!kdops || !kdops->rmdir)
+        if (!scops || !scops->rmdir)
                 return -EPERM;
 
-        return kdops->rmdir(kn);
+        if (!kernfs_get_active(kn))
+                return -ENODEV;
+
+        ret = scops->rmdir(kn);
+
+        kernfs_put_active(kn);
+        return ret;
 }
 
 static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
@@ -752,12 +862,25 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
         struct kernfs_node *kn  = old_dentry->d_fsdata;
         struct kernfs_node *new_parent = new_dir->i_private;
-        struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+        struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
+        int ret;
 
-        if (!kdops || !kdops->rename)
+        if (!scops || !scops->rename)
                 return -EPERM;
 
-        return kdops->rename(kn, new_parent, new_dentry->d_name.name);
+        if (!kernfs_get_active(kn))
+                return -ENODEV;
+
+        if (!kernfs_get_active(new_parent)) {
+                kernfs_put_active(kn);
+                return -ENODEV;
+        }
+
+        ret = scops->rename(kn, new_parent, new_dentry->d_name.name);
+
+        kernfs_put_active(new_parent);
+        kernfs_put_active(kn);
+        return ret;
 }
 
 const struct inode_operations kernfs_dir_iops = {
@@ -830,23 +953,104 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
         return pos->parent;
 }
 
-static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
-                            struct kernfs_node *kn)
+/**
+ * kernfs_activate - activate a node which started deactivated
+ * @kn: kernfs_node whose subtree is to be activated
+ *
+ * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node
+ * needs to be explicitly activated.  A node which hasn't been activated
+ * isn't visible to userland and deactivation is skipped during its
+ * removal.  This is useful to construct atomic init sequences where
+ * creation of multiple nodes should either succeed or fail atomically.
+ *
+ * The caller is responsible for ensuring that this function is not called
+ * after kernfs_remove*() is invoked on @kn.
+ */
+void kernfs_activate(struct kernfs_node *kn)
 {
-        struct kernfs_node *pos, *next;
+        struct kernfs_node *pos;
 
-        if (!kn)
+        mutex_lock(&kernfs_mutex);
+
+        pos = NULL;
+        while ((pos = kernfs_next_descendant_post(pos, kn))) {
+                if (!pos || (pos->flags & KERNFS_ACTIVATED))
+                        continue;
+
+                WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb));
+                WARN_ON_ONCE(atomic_read(&pos->active) != KN_DEACTIVATED_BIAS);
+
+                atomic_sub(KN_DEACTIVATED_BIAS, &pos->active);
+                pos->flags |= KERNFS_ACTIVATED;
+        }
+
+        mutex_unlock(&kernfs_mutex);
+}
+
+static void __kernfs_remove(struct kernfs_node *kn)
+{
+        struct kernfs_node *pos;
+
+        lockdep_assert_held(&kernfs_mutex);
+
+        /*
+         * Short-circuit if non-root @kn has already finished removal.
+         * This is for kernfs_remove_self() which plays with active ref
+         * after removal.
+         */
+        if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb)))
                 return;
 
         pr_debug("kernfs %s: removing\n", kn->name);
 
-        next = NULL;
+        /* prevent any new usage under @kn by deactivating all nodes */
+        pos = NULL;
+        while ((pos = kernfs_next_descendant_post(pos, kn)))
+                if (kernfs_active(pos))
+                        atomic_add(KN_DEACTIVATED_BIAS, &pos->active);
+
+        /* deactivate and unlink the subtree node-by-node */
         do {
-                pos = next;
-                next = kernfs_next_descendant_post(pos, kn);
-                if (pos)
-                        kernfs_remove_one(acxt, pos);
-        } while (next);
+                pos = kernfs_leftmost_descendant(kn);
+
+                /*
+                 * kernfs_drain() drops kernfs_mutex temporarily and @pos's
+                 * base ref could have been put by someone else by the time
+                 * the function returns.  Make sure it doesn't go away
+                 * underneath us.
+                 */
+                kernfs_get(pos);
+
+                /*
+                 * Drain iff @kn was activated.  This avoids draining and
+                 * its lockdep annotations for nodes which have never been
+                 * activated and allows embedding kernfs_remove() in create
+                 * error paths without worrying about draining.
+                 */
+                if (kn->flags & KERNFS_ACTIVATED)
+                        kernfs_drain(pos);
+                else
+                        WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
+
+                /*
+                 * kernfs_unlink_sibling() succeeds once per node.  Use it
+                 * to decide who's responsible for cleanups.
+                 */
+                if (!pos->parent || kernfs_unlink_sibling(pos)) {
+                        struct kernfs_iattrs *ps_iattr =
+                                pos->parent ? pos->parent->iattr : NULL;
+
+                        /* update timestamps on the parent */
+                        if (ps_iattr) {
+                                ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
+                                ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
+                        }
+
+                        kernfs_put(pos);
+                }
+
+                kernfs_put(pos);
+        } while (pos != kn);
 }
 
 /**
@@ -857,11 +1061,140 @@ static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
  */
 void kernfs_remove(struct kernfs_node *kn)
 {
-        struct kernfs_addrm_cxt acxt;
+        mutex_lock(&kernfs_mutex);
+        __kernfs_remove(kn);
+        mutex_unlock(&kernfs_mutex);
+}
 
-        kernfs_addrm_start(&acxt);
-        __kernfs_remove(&acxt, kn);
-        kernfs_addrm_finish(&acxt);
+/**
+ * kernfs_break_active_protection - break out of active protection
+ * @kn: the self kernfs_node
+ *
+ * The caller must be running off of a kernfs operation which is invoked
+ * with an active reference - e.g. one of kernfs_ops.  Each invocation of
+ * this function must also be matched with an invocation of
+ * kernfs_unbreak_active_protection().
+ *
+ * This function releases the active reference of @kn the caller is
+ * holding.  Once this function is called, @kn may be removed at any point
+ * and the caller is solely responsible for ensuring that the objects it
+ * dereferences are accessible.
+ */
+void kernfs_break_active_protection(struct kernfs_node *kn)
+{
+        /*
+         * Take out ourself out of the active ref dependency chain.  If
+         * we're called without an active ref, lockdep will complain.
+         */
+        kernfs_put_active(kn);
+}
+
+/**
+ * kernfs_unbreak_active_protection - undo kernfs_break_active_protection()
+ * @kn: the self kernfs_node
+ *
+ * If kernfs_break_active_protection() was called, this function must be
+ * invoked before finishing the kernfs operation.  Note that while this
+ * function restores the active reference, it doesn't and can't actually
+ * restore the active protection - @kn may already or be in the process of
+ * being removed.  Once kernfs_break_active_protection() is invoked, that
+ * protection is irreversibly gone for the kernfs operation instance.
+ *
+ * While this function may be called at any point after
+ * kernfs_break_active_protection() is invoked, its most useful location
+ * would be right before the enclosing kernfs operation returns.
+ */
+void kernfs_unbreak_active_protection(struct kernfs_node *kn)
+{
+        /*
+         * @kn->active could be in any state; however, the increment we do
+         * here will be undone as soon as the enclosing kernfs operation
+         * finishes and this temporary bump can't break anything.  If @kn
+         * is alive, nothing changes.  If @kn is being deactivated, the
+         * soon-to-follow put will either finish deactivation or restore
+         * deactivated state.  If @kn is already removed, the temporary
+         * bump is guaranteed to be gone before @kn is released.
+         */
+        atomic_inc(&kn->active);
+        if (kernfs_lockdep(kn))
+                rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_);
+}
+
+/**
+ * kernfs_remove_self - remove a kernfs_node from its own method
+ * @kn: the self kernfs_node to remove
+ *
+ * The caller must be running off of a kernfs operation which is invoked
+ * with an active reference - e.g. one of kernfs_ops.  This can be used to
+ * implement a file operation which deletes itself.
+ *
+ * For example, the "delete" file for a sysfs device directory can be
+ * implemented by invoking kernfs_remove_self() on the "delete" file
+ * itself.  This function breaks the circular dependency of trying to
+ * deactivate self while holding an active ref itself.  It isn't necessary
+ * to modify the usual removal path to use kernfs_remove_self().  The
+ * "delete" implementation can simply invoke kernfs_remove_self() on self
+ * before proceeding with the usual removal path.  kernfs will ignore later
+ * kernfs_remove() on self.
+ *
+ * kernfs_remove_self() can be called multiple times concurrently on the
+ * same kernfs_node.  Only the first one actually performs removal and
+ * returns %true.  All others will wait until the kernfs operation which
+ * won self-removal finishes and return %false.  Note that the losers wait
+ * for the completion of not only the winning kernfs_remove_self() but also
+ * the whole kernfs_ops which won the arbitration.  This can be used to
+ * guarantee, for example, all concurrent writes to a "delete" file to
+ * finish only after the whole operation is complete.
+ */
+bool kernfs_remove_self(struct kernfs_node *kn)
+{
+        bool ret;
+
+        mutex_lock(&kernfs_mutex);
+        kernfs_break_active_protection(kn);
+
+        /*
+         * SUICIDAL is used to arbitrate among competing invocations.  Only
+         * the first one will actually perform removal.  When the removal
+         * is complete, SUICIDED is set and the active ref is restored
+         * while holding kernfs_mutex.  The ones which lost arbitration
+         * waits for SUICDED && drained which can happen only after the
+         * enclosing kernfs operation which executed the winning instance
+         * of kernfs_remove_self() finished.
+         */
+        if (!(kn->flags & KERNFS_SUICIDAL)) {
+                kn->flags |= KERNFS_SUICIDAL;
+                __kernfs_remove(kn);
+                kn->flags |= KERNFS_SUICIDED;
+                ret = true;
+        } else {
+                wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq;
+                DEFINE_WAIT(wait);
+
+                while (true) {
+                        prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE);
+
+                        if ((kn->flags & KERNFS_SUICIDED) &&
+                            atomic_read(&kn->active) == KN_DEACTIVATED_BIAS)
+                                break;
+
+                        mutex_unlock(&kernfs_mutex);
+                        schedule();
+                        mutex_lock(&kernfs_mutex);
+                }
+                finish_wait(waitq, &wait);
+                WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb));
+                ret = false;
+        }
+
+        /*
+         * This must be done while holding kernfs_mutex; otherwise, waiting
+         * for SUICIDED && deactivated could finish prematurely.
+         */
+        kernfs_unbreak_active_protection(kn);
+
+        mutex_unlock(&kernfs_mutex);
+        return ret;
 }
 
 /**
@@ -876,7 +1209,6 @@ void kernfs_remove(struct kernfs_node *kn)
 int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
                              const void *ns)
 {
-        struct kernfs_addrm_cxt acxt;
         struct kernfs_node *kn;
 
         if (!parent) {
@@ -885,13 +1217,13 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
                 return -ENOENT;
         }
 
-        kernfs_addrm_start(&acxt);
+        mutex_lock(&kernfs_mutex);
 
         kn = kernfs_find_ns(parent, name, ns);
         if (kn)
-                __kernfs_remove(&acxt, kn);
+                __kernfs_remove(kn);
 
-        kernfs_addrm_finish(&acxt);
+        mutex_unlock(&kernfs_mutex);
 
         if (kn)
                 return 0;
@@ -909,12 +1241,18 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
                      const char *new_name, const void *new_ns)
 {
+        struct kernfs_node *old_parent;
+        const char *old_name = NULL;
         int error;
 
+        /* can't move or rename root */
+        if (!kn->parent)
+                return -EINVAL;
+
         mutex_lock(&kernfs_mutex);
 
         error = -ENOENT;
-        if ((kn->flags | new_parent->flags) & KERNFS_REMOVED)
+        if (!kernfs_active(kn) || !kernfs_active(new_parent))
                 goto out;
 
         error = 0;
@@ -932,13 +1270,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
                 new_name = kstrdup(new_name, GFP_KERNEL);
                 if (!new_name)
                         goto out;
-
-                if (kn->flags & KERNFS_STATIC_NAME)
-                        kn->flags &= ~KERNFS_STATIC_NAME;
-                else
-                        kfree(kn->name);
-
-                kn->name = new_name;
+        } else {
+                new_name = NULL;
         }
 
         /*
@@ -946,12 +1279,29 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
          */
         kernfs_unlink_sibling(kn);
         kernfs_get(new_parent);
-        kernfs_put(kn->parent);
+
+        /* rename_lock protects ->parent and ->name accessors */
+        spin_lock_irq(&kernfs_rename_lock);
+
+        old_parent = kn->parent;
+        kn->parent = new_parent;
+
         kn->ns = new_ns;
+        if (new_name) {
+                if (!(kn->flags & KERNFS_STATIC_NAME))
+                        old_name = kn->name;
+                kn->flags &= ~KERNFS_STATIC_NAME;
+                kn->name = new_name;
+        }
+
+        spin_unlock_irq(&kernfs_rename_lock);
+
         kn->hash = kernfs_name_hash(kn->name, kn->ns);
-        kn->parent = new_parent;
         kernfs_link_sibling(kn);
 
+        kernfs_put(old_parent);
+        kfree(old_name);
+
         error = 0;
  out:
         mutex_unlock(&kernfs_mutex);
@@ -974,7 +1324,7 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns,
         struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
 {
         if (pos) {
-                int valid = !(pos->flags & KERNFS_REMOVED) &&
+                int valid = kernfs_active(pos) &&
                         pos->parent == parent && hash == pos->hash;
                 kernfs_put(pos);
                 if (!valid)
@@ -993,8 +1343,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns,
                                 break;
                 }
         }
-        /* Skip over entries in the wrong namespace */
-        while (pos && pos->ns != ns) {
+        /* Skip over entries which are dying/dead or in the wrong namespace */
+        while (pos && (!kernfs_active(pos) || pos->ns != ns)) {
                 struct rb_node *node = rb_next(&pos->rb);
                 if (!node)
                         pos = NULL;
@@ -1008,14 +1358,15 @@ static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
         struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos)
 {
         pos = kernfs_dir_pos(ns, parent, ino, pos);
-        if (pos)
+        if (pos) {
                 do {
                         struct rb_node *node = rb_next(&pos->rb);
                         if (!node)
                                 pos = NULL;
                         else
                                 pos = rb_to_kn(node);
-                } while (pos && pos->ns != ns);
+                } while (pos && (!kernfs_active(pos) || pos->ns != ns));
+        }
         return pos;
 }
 
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index dbf397bfdff2..8034706a7af8 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -252,10 +252,18 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
                                 size_t count, loff_t *ppos)
 {
         struct kernfs_open_file *of = kernfs_of(file);
-        ssize_t len = min_t(size_t, count, PAGE_SIZE);
         const struct kernfs_ops *ops;
+        size_t len;
         char *buf;
 
+        if (of->atomic_write_len) {
+                len = count;
+                if (len > of->atomic_write_len)
+                        return -E2BIG;
+        } else {
+                len = min_t(size_t, count, PAGE_SIZE);
+        }
+
         buf = kmalloc(len + 1, GFP_KERNEL);
         if (!buf)
                 return -ENOMEM;
@@ -653,6 +661,12 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
         of->file = file;
 
         /*
+         * Write path needs to atomic_write_len outside active reference.
+         * Cache it in open_file.  See kernfs_fop_write() for details.
+         */
+        of->atomic_write_len = ops->atomic_write_len;
+
+        /*
          * Always instantiate seq_file even if read access doesn't use
          * seq_file or is not requested.  This unifies private data access
          * and readable regular files are the vast majority anyway.
@@ -820,7 +834,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
                                          bool name_is_static,
                                          struct lock_class_key *key)
 {
-        struct kernfs_addrm_cxt acxt;
         struct kernfs_node *kn;
         unsigned flags;
         int rc;
@@ -855,10 +868,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
         if (ops->mmap)
                 kn->flags |= KERNFS_HAS_MMAP;
 
-        kernfs_addrm_start(&acxt);
-        rc = kernfs_add_one(&acxt, kn);
-        kernfs_addrm_finish(&acxt);
-
+        rc = kernfs_add_one(kn);
         if (rc) {
                 kernfs_put(kn);
                 return ERR_PTR(rc);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index e55126f85bd2..abb0f1f53d93 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -355,7 +355,7 @@ void kernfs_evict_inode(struct inode *inode)
 {
         struct kernfs_node *kn = inode->i_private;
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         kernfs_put(kn);
 }
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index eb536b76374a..8be13b2a079b 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -26,7 +26,8 @@ struct kernfs_iattrs {
         struct simple_xattrs    xattrs;
 };
 
-#define KN_DEACTIVATED_BIAS             INT_MIN
+/* +1 to avoid triggering overflow warning when negating it */
+#define KN_DEACTIVATED_BIAS             (INT_MIN + 1)
 
 /* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */
 
@@ -45,13 +46,6 @@ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
 }
 
 /*
- * Context structure to be used while adding/removing nodes.
- */
-struct kernfs_addrm_cxt {
-        struct kernfs_node      *removed;
-};
-
-/*
  * mount.c
  */
 struct kernfs_super_info {
@@ -71,6 +65,7 @@ struct kernfs_super_info {
 };
 #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
 
+extern const struct super_operations kernfs_sops;
 extern struct kmem_cache *kernfs_node_cache;
 
 /*
@@ -100,9 +95,7 @@ extern const struct inode_operations kernfs_dir_iops;
 
 struct kernfs_node *kernfs_get_active(struct kernfs_node *kn);
 void kernfs_put_active(struct kernfs_node *kn);
-void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt);
-int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn);
-void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt);
+int kernfs_add_one(struct kernfs_node *kn);
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
                                     const char *name, umode_t mode,
                                     unsigned flags);
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0f4152defe7b..6a5f04ac8704 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -19,12 +19,49 @@
 
 struct kmem_cache *kernfs_node_cache;
 
-static const struct super_operations kernfs_sops = {
+static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+        struct kernfs_root *root = kernfs_info(sb)->root;
+        struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+        if (scops && scops->remount_fs)
+                return scops->remount_fs(root, flags, data);
+        return 0;
+}
+
+static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
+{
+        struct kernfs_root *root = kernfs_root(dentry->d_fsdata);
+        struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+        if (scops && scops->show_options)
+                return scops->show_options(sf, root);
+        return 0;
+}
+
+const struct super_operations kernfs_sops = {
         .statfs         = simple_statfs,
         .drop_inode     = generic_delete_inode,
         .evict_inode    = kernfs_evict_inode,
+
+        .remount_fs     = kernfs_sop_remount_fs,
+        .show_options   = kernfs_sop_show_options,
 };
 
+/**
+ * kernfs_root_from_sb - determine kernfs_root associated with a super_block
+ * @sb: the super_block in question
+ *
+ * Return the kernfs_root associated with @sb.  If @sb is not a kernfs one,
+ * %NULL is returned.
+ */
+struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
+{
+        if (sb->s_op == &kernfs_sops)
+                return kernfs_info(sb)->root;
+        return NULL;
+}
+
 static int kernfs_fill_super(struct super_block *sb)
 {
         struct kernfs_super_info *info = kernfs_info(sb);
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index 4d457055acb9..8a198898e39a 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -27,7 +27,6 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
                                        struct kernfs_node *target)
 {
         struct kernfs_node *kn;
-        struct kernfs_addrm_cxt acxt;
         int error;
 
         kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK);
@@ -39,10 +38,7 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
         kn->symlink.target_kn = target;
         kernfs_get(target);     /* ref owned by symlink */
 
-        kernfs_addrm_start(&acxt);
-        error = kernfs_add_one(&acxt, kn);
-        kernfs_addrm_finish(&acxt);
-
+        error = kernfs_add_one(kn);
         if (!error)
                 return kn;
 
diff --git a/fs/locks.c b/fs/locks.c
index 92a0f0a52b06..13fc7a6d380a 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -135,6 +135,7 @@
 #define IS_POSIX(fl)    (fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)    (fl->fl_flags & FL_FLOCK)
 #define IS_LEASE(fl)    (fl->fl_flags & (FL_LEASE|FL_DELEG))
+#define IS_FILE_PVT(fl) (fl->fl_flags & FL_FILE_PVT)
 
 static bool lease_breaking(struct file_lock *fl)
 {
@@ -344,48 +345,43 @@ static int assign_type(struct file_lock *fl, long type)
         return 0;
 }
 
-/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
- * style lock.
- */
-static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
-                               struct flock *l)
+static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
+                                 struct flock64 *l)
 {
-        off_t start, end;
-
         switch (l->l_whence) {
         case SEEK_SET:
-                start = 0;
+                fl->fl_start = 0;
                 break;
         case SEEK_CUR:
-                start = filp->f_pos;
+                fl->fl_start = filp->f_pos;
                 break;
         case SEEK_END:
-                start = i_size_read(file_inode(filp));
+                fl->fl_start = i_size_read(file_inode(filp));
                 break;
         default:
                 return -EINVAL;
         }
+        if (l->l_start > OFFSET_MAX - fl->fl_start)
+                return -EOVERFLOW;
+        fl->fl_start += l->l_start;
+        if (fl->fl_start < 0)
+                return -EINVAL;
 
         /* POSIX-1996 leaves the case l->l_len < 0 undefined;
            POSIX-2001 defines it. */
-        start += l->l_start;
-        if (start < 0)
-                return -EINVAL;
-        fl->fl_end = OFFSET_MAX;
         if (l->l_len > 0) {
-                end = start + l->l_len - 1;
-                fl->fl_end = end;
+                if (l->l_len - 1 > OFFSET_MAX - fl->fl_start)
+                        return -EOVERFLOW;
+                fl->fl_end = fl->fl_start + l->l_len - 1;
+
         } else if (l->l_len < 0) {
-                end = start - 1;
-                fl->fl_end = end;
-                start += l->l_len;
-                if (start < 0)
+                if (fl->fl_start + l->l_len < 0)
                         return -EINVAL;
-        }
-        fl->fl_start = start;   /* we record the absolute position */
-        if (fl->fl_end < fl->fl_start)
-                return -EOVERFLOW;
-        
+                fl->fl_end = fl->fl_start - 1;
+                fl->fl_start += l->l_len;
+        } else
+                fl->fl_end = OFFSET_MAX;
+
         fl->fl_owner = current->files;
         fl->fl_pid = current->tgid;
         fl->fl_file = filp;
@@ -393,55 +389,36 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
         fl->fl_ops = NULL;
         fl->fl_lmops = NULL;
 
-        return assign_type(fl, l->l_type);
-}
-
-#if BITS_PER_LONG == 32
-static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
-                                 struct flock64 *l)
-{
-        loff_t start;
-
-        switch (l->l_whence) {
-        case SEEK_SET:
-                start = 0;
-                break;
-        case SEEK_CUR:
-                start = filp->f_pos;
+        /* Ensure that fl->fl_filp has compatible f_mode */
+        switch (l->l_type) {
+        case F_RDLCK:
+                if (!(filp->f_mode & FMODE_READ))
+                        return -EBADF;
                 break;
-        case SEEK_END:
-                start = i_size_read(file_inode(filp));
+        case F_WRLCK:
+                if (!(filp->f_mode & FMODE_WRITE))
+                        return -EBADF;
                 break;
-        default:
-                return -EINVAL;
         }
 
-        start += l->l_start;
-        if (start < 0)
-                return -EINVAL;
-        fl->fl_end = OFFSET_MAX;
-        if (l->l_len > 0) {
-                fl->fl_end = start + l->l_len - 1;
-        } else if (l->l_len < 0) {
-                fl->fl_end = start - 1;
-                start += l->l_len;
-                if (start < 0)
-                        return -EINVAL;
-        }
-        fl->fl_start = start;   /* we record the absolute position */
-        if (fl->fl_end < fl->fl_start)
-                return -EOVERFLOW;
-        
-        fl->fl_owner = current->files;
-        fl->fl_pid = current->tgid;
-        fl->fl_file = filp;
-        fl->fl_flags = FL_POSIX;
-        fl->fl_ops = NULL;
-        fl->fl_lmops = NULL;
-
         return assign_type(fl, l->l_type);
 }
-#endif
+
+/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
+ * style lock.
+ */
+static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
+                               struct flock *l)
+{
+        struct flock64 ll = {
+                .l_type = l->l_type,
+                .l_whence = l->l_whence,
+                .l_start = l->l_start,
+                .l_len = l->l_len,
+        };
+
+        return flock64_to_posix_lock(filp, fl, &ll);
+}
 
 /* default lease lock manager operations */
 static void lease_break_callback(struct file_lock *fl)
@@ -511,8 +488,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
 }
 
 /* Must be called with the i_lock held! */
-static inline void
-locks_insert_global_locks(struct file_lock *fl)
+static void locks_insert_global_locks(struct file_lock *fl)
 {
         lg_local_lock(&file_lock_lglock);
         fl->fl_link_cpu = smp_processor_id();
@@ -521,8 +497,7 @@ locks_insert_global_locks(struct file_lock *fl)
 }
 
 /* Must be called with the i_lock held! */
-static inline void
-locks_delete_global_locks(struct file_lock *fl)
+static void locks_delete_global_locks(struct file_lock *fl)
 {
         /*
          * Avoid taking lock if already unhashed. This is safe since this check
@@ -544,14 +519,12 @@ posix_owner_key(struct file_lock *fl)
         return (unsigned long)fl->fl_owner;
 }
 
-static inline void
-locks_insert_global_blocked(struct file_lock *waiter)
+static void locks_insert_global_blocked(struct file_lock *waiter)
 {
         hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter));
 }
 
-static inline void
-locks_delete_global_blocked(struct file_lock *waiter)
+static void locks_delete_global_blocked(struct file_lock *waiter)
 {
         hash_del(&waiter->fl_link);
 }
@@ -581,7 +554,7 @@ static void locks_delete_block(struct file_lock *waiter)
  * it seems like the reasonable thing to do.
  *
  * Must be called with both the i_lock and blocked_lock_lock held. The fl_block
- * list itself is protected by the file_lock_list, but by ensuring that the
+ * list itself is protected by the blocked_lock_lock, but by ensuring that the
  * i_lock is also held on insertions we can avoid taking the blocked_lock_lock
  * in some cases when we see that the fl_block list is empty.
  */
@@ -591,7 +564,7 @@ static void __locks_insert_block(struct file_lock *blocker,
         BUG_ON(!list_empty(&waiter->fl_block));
         waiter->fl_next = blocker;
         list_add_tail(&waiter->fl_block, &blocker->fl_block);
-        if (IS_POSIX(blocker))
+        if (IS_POSIX(blocker) && !IS_FILE_PVT(blocker))
                 locks_insert_global_blocked(waiter);
 }
 
@@ -652,15 +625,18 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
         locks_insert_global_locks(fl);
 }
 
-/*
- * Delete a lock and then free it.
- * Wake up processes that are blocked waiting for this lock,
- * notify the FS that the lock has been cleared and
- * finally free the lock.
+/**
+ * locks_delete_lock - Delete a lock and then free it.
+ * @thisfl_p: pointer that points to the fl_next field of the previous
+ *            inode->i_flock list entry
+ *
+ * Unlink a lock from all lists and free the namespace reference, but don't
+ * free it yet. Wake up processes that are blocked waiting for this lock and
+ * notify the FS that the lock has been cleared.
  *
  * Must be called with the i_lock held!
  */
-static void locks_delete_lock(struct file_lock **thisfl_p)
+static void locks_unlink_lock(struct file_lock **thisfl_p)
 {
         struct file_lock *fl = *thisfl_p;
 
@@ -675,6 +651,18 @@ static void locks_delete_lock(struct file_lock **thisfl_p)
         }
 
         locks_wake_up_blocks(fl);
+}
+
+/*
+ * Unlink a lock from all lists and free it.
+ *
+ * Must be called with i_lock held!
+ */
+static void locks_delete_lock(struct file_lock **thisfl_p)
+{
+        struct file_lock *fl = *thisfl_p;
+
+        locks_unlink_lock(thisfl_p);
         locks_free_lock(fl);
 }
 
@@ -769,8 +757,16 @@ EXPORT_SYMBOL(posix_test_lock);
  * Note: the above assumption may not be true when handling lock
  * requests from a broken NFS client. It may also fail in the presence
  * of tasks (such as posix threads) sharing the same open file table.
- *
  * To handle those cases, we just bail out after a few iterations.
+ *
+ * For FL_FILE_PVT locks, the owner is the filp, not the files_struct.
+ * Because the owner is not even nominally tied to a thread of
+ * execution, the deadlock detection below can't reasonably work well. Just
+ * skip it for those.
+ *
+ * In principle, we could do a more limited deadlock detection on FL_FILE_PVT
+ * locks that just checks for the case where two tasks are attempting to
+ * upgrade from read to write locks on the same inode.
  */
 
 #define MAX_DEADLK_ITERATIONS 10
@@ -793,6 +789,13 @@ static int posix_locks_deadlock(struct file_lock *caller_fl,
 {
         int i = 0;
 
+        /*
+         * This deadlock detector can't reasonably detect deadlocks with
+         * FL_FILE_PVT locks, since they aren't owned by a process, per-se.
+         */
+        if (IS_FILE_PVT(caller_fl))
+                return 0;
+
         while ((block_fl = what_owner_is_waiting_for(block_fl))) {
                 if (i++ > MAX_DEADLK_ITERATIONS)
                         return 0;
@@ -1152,13 +1155,14 @@ EXPORT_SYMBOL(posix_lock_file_wait);
 
 /**
  * locks_mandatory_locked - Check for an active lock
- * @inode: the file to check
+ * @file: the file to check
  *
  * Searches the inode's list of locks to find any POSIX locks which conflict.
  * This function is called from locks_verify_locked() only.
  */
-int locks_mandatory_locked(struct inode *inode)
+int locks_mandatory_locked(struct file *file)
 {
+        struct inode *inode = file_inode(file);
         fl_owner_t owner = current->files;
         struct file_lock *fl;
 
@@ -1169,7 +1173,7 @@ int locks_mandatory_locked(struct inode *inode)
         for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
                 if (!IS_POSIX(fl))
                         continue;
-                if (fl->fl_owner != owner)
+                if (fl->fl_owner != owner && fl->fl_owner != (fl_owner_t)file)
                         break;
         }
         spin_unlock(&inode->i_lock);
@@ -1195,19 +1199,30 @@ int locks_mandatory_area(int read_write, struct inode *inode,
 {
         struct file_lock fl;
         int error;
+        bool sleep = false;
 
         locks_init_lock(&fl);
-        fl.fl_owner = current->files;
         fl.fl_pid = current->tgid;
         fl.fl_file = filp;
         fl.fl_flags = FL_POSIX | FL_ACCESS;
         if (filp && !(filp->f_flags & O_NONBLOCK))
-                fl.fl_flags |= FL_SLEEP;
+                sleep = true;
         fl.fl_type = (read_write == FLOCK_VERIFY_WRITE) ? F_WRLCK : F_RDLCK;
         fl.fl_start = offset;
         fl.fl_end = offset + count - 1;
 
         for (;;) {
+                if (filp) {
+                        fl.fl_owner = (fl_owner_t)filp;
+                        fl.fl_flags &= ~FL_SLEEP;
+                        error = __posix_lock_file(inode, &fl, NULL);
+                        if (!error)
+                                break;
+                }
+
+                if (sleep)
+                        fl.fl_flags |= FL_SLEEP;
+                fl.fl_owner = current->files;
                 error = __posix_lock_file(inode, &fl, NULL);
                 if (error != FILE_LOCK_DEFERRED)
                         break;
@@ -1472,6 +1487,32 @@ int fcntl_getlease(struct file *filp)
         return type;
 }
 
+/**
+ * check_conflicting_open - see if the given dentry points to a file that has
+ *                          an existing open that would conflict with the
+ *                          desired lease.
+ * @dentry:     dentry to check
+ * @arg:        type of lease that we're trying to acquire
+ *
+ * Check to see if there's an existing open fd on this file that would
+ * conflict with the lease we're trying to set.
+ */
+static int
+check_conflicting_open(const struct dentry *dentry, const long arg)
+{
+        int ret = 0;
+        struct inode *inode = dentry->d_inode;
+
+        if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
+                return -EAGAIN;
+
+        if ((arg == F_WRLCK) && ((d_count(dentry) > 1) ||
+            (atomic_read(&inode->i_count) > 1)))
+                ret = -EAGAIN;
+
+        return ret;
+}
+
 static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp)
 {
         struct file_lock *fl, **before, **my_before = NULL, *lease;
@@ -1499,12 +1540,8 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
                 return -EINVAL;
         }
 
-        error = -EAGAIN;
-        if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
-                goto out;
-        if ((arg == F_WRLCK)
-            && ((d_count(dentry) > 1)
-                || (atomic_read(&inode->i_count) > 1)))
+        error = check_conflicting_open(dentry, arg);
+        if (error)
                 goto out;
 
         /*
@@ -1549,7 +1586,19 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
                 goto out;
 
         locks_insert_lock(before, lease);
-        error = 0;
+        /*
+         * The check in break_lease() is lockless. It's possible for another
+         * open to race in after we did the earlier check for a conflicting
+         * open but before the lease was inserted. Check again for a
+         * conflicting open and cancel the lease if there is one.
+         *
+         * We also add a barrier here to ensure that the insertion of the lock
+         * precedes these checks.
+         */
+        smp_mb();
+        error = check_conflicting_open(dentry, arg);
+        if (error)
+                locks_unlink_lock(flp);
 out:
         if (is_deleg)
                 mutex_unlock(&inode->i_mutex);
@@ -1842,7 +1891,7 @@ EXPORT_SYMBOL_GPL(vfs_test_lock);
 
 static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
 {
-        flock->l_pid = fl->fl_pid;
+        flock->l_pid = IS_FILE_PVT(fl) ? -1 : fl->fl_pid;
 #if BITS_PER_LONG == 32
         /*
          * Make sure we can represent the posix lock via
@@ -1864,7 +1913,7 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
 #if BITS_PER_LONG == 32
 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
 {
-        flock->l_pid = fl->fl_pid;
+        flock->l_pid = IS_FILE_PVT(fl) ? -1 : fl->fl_pid;
         flock->l_start = fl->fl_start;
         flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
                 fl->fl_end - fl->fl_start + 1;
@@ -1876,7 +1925,7 @@ static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
 /* Report the first existing lock that would conflict with l.
  * This implements the F_GETLK command of fcntl().
  */
-int fcntl_getlk(struct file *filp, struct flock __user *l)
+int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l)
 {
         struct file_lock file_lock;
         struct flock flock;
@@ -1893,6 +1942,16 @@ int fcntl_getlk(struct file *filp, struct flock __user *l)
         if (error)
                 goto out;
 
+        if (cmd == F_GETLKP) {
+                error = -EINVAL;
+                if (flock.l_pid != 0)
+                        goto out;
+
+                cmd = F_GETLK;
+                file_lock.fl_flags |= FL_FILE_PVT;
+                file_lock.fl_owner = (fl_owner_t)filp;
+        }
+
         error = vfs_test_lock(filp, &file_lock);
         if (error)
                 goto out;
@@ -2012,25 +2071,32 @@ again:
         error = flock_to_posix_lock(filp, file_lock, &flock);
         if (error)
                 goto out;
-        if (cmd == F_SETLKW) {
-                file_lock->fl_flags |= FL_SLEEP;
-        }
-        
-        error = -EBADF;
-        switch (flock.l_type) {
-        case F_RDLCK:
-                if (!(filp->f_mode & FMODE_READ))
-                        goto out;
-                break;
-        case F_WRLCK:
-                if (!(filp->f_mode & FMODE_WRITE))
+
+        /*
+         * If the cmd is requesting file-private locks, then set the
+         * FL_FILE_PVT flag and override the owner.
+         */
+        switch (cmd) {
+        case F_SETLKP:
+                error = -EINVAL;
+                if (flock.l_pid != 0)
                         goto out;
+
+                cmd = F_SETLK;
+                file_lock->fl_flags |= FL_FILE_PVT;
+                file_lock->fl_owner = (fl_owner_t)filp;
                 break;
-        case F_UNLCK:
-                break;
-        default:
+        case F_SETLKPW:
                 error = -EINVAL;
-                goto out;
+                if (flock.l_pid != 0)
+                        goto out;
+
+                cmd = F_SETLKW;
+                file_lock->fl_flags |= FL_FILE_PVT;
+                file_lock->fl_owner = (fl_owner_t)filp;
+                /* Fallthrough */
+        case F_SETLKW:
+                file_lock->fl_flags |= FL_SLEEP;
         }
 
         error = do_lock_file_wait(filp, cmd, file_lock);
@@ -2061,7 +2127,7 @@ out:
 /* Report the first existing lock that would conflict with l.
  * This implements the F_GETLK command of fcntl().
  */
-int fcntl_getlk64(struct file *filp, struct flock64 __user *l)
+int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
 {
         struct file_lock file_lock;
         struct flock64 flock;
@@ -2078,6 +2144,16 @@ int fcntl_getlk64(struct file *filp, struct flock64 __user *l)
         if (error)
                 goto out;
 
+        if (cmd == F_GETLKP) {
+                error = -EINVAL;
+                if (flock.l_pid != 0)
+                        goto out;
+
+                cmd = F_GETLK64;
+                file_lock.fl_flags |= FL_FILE_PVT;
+                file_lock.fl_owner = (fl_owner_t)filp;
+        }
+
         error = vfs_test_lock(filp, &file_lock);
         if (error)
                 goto out;
@@ -2130,25 +2206,32 @@ again:
         error = flock64_to_posix_lock(filp, file_lock, &flock);
         if (error)
                 goto out;
-        if (cmd == F_SETLKW64) {
-                file_lock->fl_flags |= FL_SLEEP;
-        }
-        
-        error = -EBADF;
-        switch (flock.l_type) {
-        case F_RDLCK:
-                if (!(filp->f_mode & FMODE_READ))
-                        goto out;
-                break;
-        case F_WRLCK:
-                if (!(filp->f_mode & FMODE_WRITE))
+
+        /*
+         * If the cmd is requesting file-private locks, then set the
+         * FL_FILE_PVT flag and override the owner.
+         */
+        switch (cmd) {
+        case F_SETLKP:
+                error = -EINVAL;
+                if (flock.l_pid != 0)
                         goto out;
+
+                cmd = F_SETLK64;
+                file_lock->fl_flags |= FL_FILE_PVT;
+                file_lock->fl_owner = (fl_owner_t)filp;
                 break;
-        case F_UNLCK:
-                break;
-        default:
+        case F_SETLKPW:
                 error = -EINVAL;
-                goto out;
+                if (flock.l_pid != 0)
+                        goto out;
+
+                cmd = F_SETLKW64;
+                file_lock->fl_flags |= FL_FILE_PVT;
+                file_lock->fl_owner = (fl_owner_t)filp;
+                /* Fallthrough */
+        case F_SETLKW64:
+                file_lock->fl_flags |= FL_SLEEP;
         }
 
         error = do_lock_file_wait(filp, cmd, file_lock);
@@ -2209,7 +2292,7 @@ EXPORT_SYMBOL(locks_remove_posix);
 /*
  * This function is called on the last close of an open file.
  */
-void locks_remove_flock(struct file *filp)
+void locks_remove_file(struct file *filp)
 {
         struct inode * inode = file_inode(filp);
         struct file_lock *fl;
@@ -2218,6 +2301,8 @@ void locks_remove_flock(struct file *filp)
         if (!inode->i_flock)
                 return;
 
+        locks_remove_posix(filp, (fl_owner_t)filp);
+
         if (filp->f_op->flock) {
                 struct file_lock fl = {
                         .fl_pid = current->tgid,
@@ -2236,16 +2321,28 @@ void locks_remove_flock(struct file *filp)
 
         while ((fl = *before) != NULL) {
                 if (fl->fl_file == filp) {
-                        if (IS_FLOCK(fl)) {
-                                locks_delete_lock(before);
-                                continue;
-                        }
                         if (IS_LEASE(fl)) {
                                 lease_modify(before, F_UNLCK);
                                 continue;
                         }
-                        /* What? */
-                        BUG();
+
+                        /*
+                         * There's a leftover lock on the list of a type that
+                         * we didn't expect to see. Most likely a classic
+                         * POSIX lock that ended up not getting released
+                         * properly, or that raced onto the list somehow. Log
+                         * some info about it and then just remove it from
+                         * the list.
+                         */
+                        WARN(!IS_FLOCK(fl),
+                                "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n",
+                                MAJOR(inode->i_sb->s_dev),
+                                MINOR(inode->i_sb->s_dev), inode->i_ino,
+                                fl->fl_type, fl->fl_flags,
+                                fl->fl_start, fl->fl_end);
+
+                        locks_delete_lock(before);
+                        continue;
                 }
                 before = &fl->fl_next;
         }
@@ -2314,8 +2411,14 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 
         seq_printf(f, "%lld:%s ", id, pfx);
         if (IS_POSIX(fl)) {
-                seq_printf(f, "%6s %s ",
-                             (fl->fl_flags & FL_ACCESS) ? "ACCESS" : "POSIX ",
+                if (fl->fl_flags & FL_ACCESS)
+                        seq_printf(f, "ACCESS");
+                else if (IS_FILE_PVT(fl))
+                        seq_printf(f, "FLPVT ");
+                else
+                        seq_printf(f, "POSIX ");
+
+                seq_printf(f, " %s ",
                              (inode == NULL) ? "*NOINODE*" :
                              mandatory_lock(inode) ? "MANDATORY" : "ADVISORY ");
         } else if (IS_FLOCK(fl)) {
@@ -2385,6 +2488,7 @@ static int locks_show(struct seq_file *f, void *v)
 }
 
 static void *locks_start(struct seq_file *f, loff_t *pos)
+        __acquires(&blocked_lock_lock)
 {
         struct locks_iterator *iter = f->private;
 
@@ -2403,6 +2507,7 @@ static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
 }
 
 static void locks_stop(struct seq_file *f, void *v)
+        __releases(&blocked_lock_lock)
 {
         spin_unlock(&blocked_lock_lock);
         lg_global_unlock(&file_lock_lglock);
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 9a59cbade2fb..48140315f627 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -2180,7 +2180,7 @@ void logfs_evict_inode(struct inode *inode)
                         do_delete_inode(inode);
                 }
         }
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
 
         /* Cheaper version of write_inode.  All changes are concealed in
diff --git a/fs/mbcache.c b/fs/mbcache.c
index e519e45bf673..bf166e388f0d 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -26,6 +26,41 @@
  * back on the lru list.
  */
 
+/*
+ * Lock descriptions and usage:
+ *
+ * Each hash chain of both the block and index hash tables now contains
+ * a built-in lock used to serialize accesses to the hash chain.
+ *
+ * Accesses to global data structures mb_cache_list and mb_cache_lru_list
+ * are serialized via the global spinlock mb_cache_spinlock.
+ *
+ * Each mb_cache_entry contains a spinlock, e_entry_lock, to serialize
+ * accesses to its local data, such as e_used and e_queued.
+ *
+ * Lock ordering:
+ *
+ * Each block hash chain's lock has the highest lock order, followed by an
+ * index hash chain's lock, mb_cache_bg_lock (used to implement mb_cache_entry's
+ * lock), and mb_cach_spinlock, with the lowest order.  While holding
+ * either a block or index hash chain lock, a thread can acquire an
+ * mc_cache_bg_lock, which in turn can also acquire mb_cache_spinlock.
+ *
+ * Synchronization:
+ *
+ * Since both mb_cache_entry_get and mb_cache_entry_find scan the block and
+ * index hash chian, it needs to lock the corresponding hash chain.  For each
+ * mb_cache_entry within the chain, it needs to lock the mb_cache_entry to
+ * prevent either any simultaneous release or free on the entry and also
+ * to serialize accesses to either the e_used or e_queued member of the entry.
+ *
+ * To avoid having a dangling reference to an already freed
+ * mb_cache_entry, an mb_cache_entry is only freed when it is not on a
+ * block hash chain and also no longer being referenced, both e_used,
+ * and e_queued are 0's.  When an mb_cache_entry is explicitly freed it is
+ * first removed from a block hash chain.
+ */
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 
@@ -34,9 +69,10 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/init.h>
+#include <linux/list_bl.h>
 #include <linux/mbcache.h>
-
+#include <linux/init.h>
+#include <linux/blockgroup_lock.h>
 
 #ifdef MB_CACHE_DEBUG
 # define mb_debug(f...) do { \
@@ -57,8 +93,14 @@
 
 #define MB_CACHE_WRITER ((unsigned short)~0U >> 1)
 
+#define MB_CACHE_ENTRY_LOCK_BITS        __builtin_log2(NR_BG_LOCKS)
+#define MB_CACHE_ENTRY_LOCK_INDEX(ce)                   \
+        (hash_long((unsigned long)ce, MB_CACHE_ENTRY_LOCK_BITS))
+
 static DECLARE_WAIT_QUEUE_HEAD(mb_cache_queue);
-                
+static struct blockgroup_lock *mb_cache_bg_lock;
+static struct kmem_cache *mb_cache_kmem_cache;
+
 MODULE_AUTHOR("Andreas Gruenbacher <a.gruenbacher@computer.org>");
 MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
 MODULE_LICENSE("GPL");
@@ -86,58 +128,110 @@ static LIST_HEAD(mb_cache_list);
 static LIST_HEAD(mb_cache_lru_list);
 static DEFINE_SPINLOCK(mb_cache_spinlock);
 
+static inline void
+__spin_lock_mb_cache_entry(struct mb_cache_entry *ce)
+{
+        spin_lock(bgl_lock_ptr(mb_cache_bg_lock,
+                MB_CACHE_ENTRY_LOCK_INDEX(ce)));
+}
+
+static inline void
+__spin_unlock_mb_cache_entry(struct mb_cache_entry *ce)
+{
+        spin_unlock(bgl_lock_ptr(mb_cache_bg_lock,
+                MB_CACHE_ENTRY_LOCK_INDEX(ce)));
+}
+
 static inline int
-__mb_cache_entry_is_hashed(struct mb_cache_entry *ce)
+__mb_cache_entry_is_block_hashed(struct mb_cache_entry *ce)
 {
-        return !list_empty(&ce->e_block_list);
+        return !hlist_bl_unhashed(&ce->e_block_list);
 }
 
 
-static void
-__mb_cache_entry_unhash(struct mb_cache_entry *ce)
+static inline void
+__mb_cache_entry_unhash_block(struct mb_cache_entry *ce)
 {
-        if (__mb_cache_entry_is_hashed(ce)) {
-                list_del_init(&ce->e_block_list);
-                list_del(&ce->e_index.o_list);
-        }
+        if (__mb_cache_entry_is_block_hashed(ce))
+                hlist_bl_del_init(&ce->e_block_list);
 }
 
+static inline int
+__mb_cache_entry_is_index_hashed(struct mb_cache_entry *ce)
+{
+        return !hlist_bl_unhashed(&ce->e_index.o_list);
+}
+
+static inline void
+__mb_cache_entry_unhash_index(struct mb_cache_entry *ce)
+{
+        if (__mb_cache_entry_is_index_hashed(ce))
+                hlist_bl_del_init(&ce->e_index.o_list);
+}
+
+/*
+ * __mb_cache_entry_unhash_unlock()
+ *
+ * This function is called to unhash both the block and index hash
+ * chain.
+ * It assumes both the block and index hash chain is locked upon entry.
+ * It also unlock both hash chains both exit
+ */
+static inline void
+__mb_cache_entry_unhash_unlock(struct mb_cache_entry *ce)
+{
+        __mb_cache_entry_unhash_index(ce);
+        hlist_bl_unlock(ce->e_index_hash_p);
+        __mb_cache_entry_unhash_block(ce);
+        hlist_bl_unlock(ce->e_block_hash_p);
+}
 
 static void
 __mb_cache_entry_forget(struct mb_cache_entry *ce, gfp_t gfp_mask)
 {
         struct mb_cache *cache = ce->e_cache;
 
-        mb_assert(!(ce->e_used || ce->e_queued));
+        mb_assert(!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt)));
         kmem_cache_free(cache->c_entry_cache, ce);
         atomic_dec(&cache->c_entry_count);
 }
 
-
 static void
-__mb_cache_entry_release_unlock(struct mb_cache_entry *ce)
-        __releases(mb_cache_spinlock)
+__mb_cache_entry_release(struct mb_cache_entry *ce)
 {
+        /* First lock the entry to serialize access to its local data. */
+        __spin_lock_mb_cache_entry(ce);
         /* Wake up all processes queuing for this cache entry. */
         if (ce->e_queued)
                 wake_up_all(&mb_cache_queue);
         if (ce->e_used >= MB_CACHE_WRITER)
                 ce->e_used -= MB_CACHE_WRITER;
+        /*
+         * Make sure that all cache entries on lru_list have
+         * both e_used and e_qued of 0s.
+         */
         ce->e_used--;
-        if (!(ce->e_used || ce->e_queued)) {
-                if (!__mb_cache_entry_is_hashed(ce))
+        if (!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))) {
+                if (!__mb_cache_entry_is_block_hashed(ce)) {
+                        __spin_unlock_mb_cache_entry(ce);
                         goto forget;
-                mb_assert(list_empty(&ce->e_lru_list));
-                list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
+                }
+                /*
+                 * Need access to lru list, first drop entry lock,
+                 * then reacquire the lock in the proper order.
+                 */
+                spin_lock(&mb_cache_spinlock);
+                if (list_empty(&ce->e_lru_list))
+                        list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
+                spin_unlock(&mb_cache_spinlock);
         }
-        spin_unlock(&mb_cache_spinlock);
+        __spin_unlock_mb_cache_entry(ce);
         return;
 forget:
-        spin_unlock(&mb_cache_spinlock);
+        mb_assert(list_empty(&ce->e_lru_list));
         __mb_cache_entry_forget(ce, GFP_KERNEL);
 }
 
-
 /*
  * mb_cache_shrink_scan()  memory pressure callback
  *
@@ -160,17 +254,34 @@ mb_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 
         mb_debug("trying to free %d entries", nr_to_scan);
         spin_lock(&mb_cache_spinlock);
-        while (nr_to_scan-- && !list_empty(&mb_cache_lru_list)) {
+        while ((nr_to_scan-- > 0) && !list_empty(&mb_cache_lru_list)) {
                 struct mb_cache_entry *ce =
                         list_entry(mb_cache_lru_list.next,
-                                   struct mb_cache_entry, e_lru_list);
-                list_move_tail(&ce->e_lru_list, &free_list);
-                __mb_cache_entry_unhash(ce);
-                freed++;
+                                struct mb_cache_entry, e_lru_list);
+                list_del_init(&ce->e_lru_list);
+                if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))
+                        continue;
+                spin_unlock(&mb_cache_spinlock);
+                /* Prevent any find or get operation on the entry */
+                hlist_bl_lock(ce->e_block_hash_p);
+                hlist_bl_lock(ce->e_index_hash_p);
+                /* Ignore if it is touched by a find/get */
+                if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt) ||
+                        !list_empty(&ce->e_lru_list)) {
+                        hlist_bl_unlock(ce->e_index_hash_p);
+                        hlist_bl_unlock(ce->e_block_hash_p);
+                        spin_lock(&mb_cache_spinlock);
+                        continue;
+                }
+                __mb_cache_entry_unhash_unlock(ce);
+                list_add_tail(&ce->e_lru_list, &free_list);
+                spin_lock(&mb_cache_spinlock);
         }
         spin_unlock(&mb_cache_spinlock);
+
         list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
                 __mb_cache_entry_forget(entry, gfp_mask);
+                freed++;
         }
         return freed;
 }
@@ -215,29 +326,40 @@ mb_cache_create(const char *name, int bucket_bits)
         int n, bucket_count = 1 << bucket_bits;
         struct mb_cache *cache = NULL;
 
+        if (!mb_cache_bg_lock) {
+                mb_cache_bg_lock = kmalloc(sizeof(struct blockgroup_lock),
+                        GFP_KERNEL);
+                if (!mb_cache_bg_lock)
+                        return NULL;
+                bgl_lock_init(mb_cache_bg_lock);
+        }
+
         cache = kmalloc(sizeof(struct mb_cache), GFP_KERNEL);
         if (!cache)
                 return NULL;
         cache->c_name = name;
         atomic_set(&cache->c_entry_count, 0);
         cache->c_bucket_bits = bucket_bits;
-        cache->c_block_hash = kmalloc(bucket_count * sizeof(struct list_head),
-                                      GFP_KERNEL);
+        cache->c_block_hash = kmalloc(bucket_count *
+                sizeof(struct hlist_bl_head), GFP_KERNEL);
         if (!cache->c_block_hash)
                 goto fail;
         for (n=0; n<bucket_count; n++)
-                INIT_LIST_HEAD(&cache->c_block_hash[n]);
-        cache->c_index_hash = kmalloc(bucket_count * sizeof(struct list_head),
-                                      GFP_KERNEL);
+                INIT_HLIST_BL_HEAD(&cache->c_block_hash[n]);
+        cache->c_index_hash = kmalloc(bucket_count *
+                sizeof(struct hlist_bl_head), GFP_KERNEL);
         if (!cache->c_index_hash)
                 goto fail;
         for (n=0; n<bucket_count; n++)
-                INIT_LIST_HEAD(&cache->c_index_hash[n]);
-        cache->c_entry_cache = kmem_cache_create(name,
-                sizeof(struct mb_cache_entry), 0,
-                SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
-        if (!cache->c_entry_cache)
-                goto fail2;
+                INIT_HLIST_BL_HEAD(&cache->c_index_hash[n]);
+        if (!mb_cache_kmem_cache) {
+                mb_cache_kmem_cache = kmem_cache_create(name,
+                        sizeof(struct mb_cache_entry), 0,
+                        SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+                if (!mb_cache_kmem_cache)
+                        goto fail2;
+        }
+        cache->c_entry_cache = mb_cache_kmem_cache;
 
         /*
          * Set an upper limit on the number of cache entries so that the hash
@@ -273,21 +395,47 @@ void
 mb_cache_shrink(struct block_device *bdev)
 {
         LIST_HEAD(free_list);
-        struct list_head *l, *ltmp;
+        struct list_head *l;
+        struct mb_cache_entry *ce, *tmp;
 
+        l = &mb_cache_lru_list;
         spin_lock(&mb_cache_spinlock);
-        list_for_each_safe(l, ltmp, &mb_cache_lru_list) {
-                struct mb_cache_entry *ce =
-                        list_entry(l, struct mb_cache_entry, e_lru_list);
+        while (!list_is_last(l, &mb_cache_lru_list)) {
+                l = l->next;
+                ce = list_entry(l, struct mb_cache_entry, e_lru_list);
                 if (ce->e_bdev == bdev) {
-                        list_move_tail(&ce->e_lru_list, &free_list);
-                        __mb_cache_entry_unhash(ce);
+                        list_del_init(&ce->e_lru_list);
+                        if (ce->e_used || ce->e_queued ||
+                                atomic_read(&ce->e_refcnt))
+                                continue;
+                        spin_unlock(&mb_cache_spinlock);
+                        /*
+                         * Prevent any find or get operation on the entry.
+                         */
+                        hlist_bl_lock(ce->e_block_hash_p);
+                        hlist_bl_lock(ce->e_index_hash_p);
+                        /* Ignore if it is touched by a find/get */
+                        if (ce->e_used || ce->e_queued ||
+                                atomic_read(&ce->e_refcnt) ||
+                                !list_empty(&ce->e_lru_list)) {
+                                hlist_bl_unlock(ce->e_index_hash_p);
+                                hlist_bl_unlock(ce->e_block_hash_p);
+                                l = &mb_cache_lru_list;
+                                spin_lock(&mb_cache_spinlock);
+                                continue;
+                        }
+                        __mb_cache_entry_unhash_unlock(ce);
+                        mb_assert(!(ce->e_used || ce->e_queued ||
+                                atomic_read(&ce->e_refcnt)));
+                        list_add_tail(&ce->e_lru_list, &free_list);
+                        l = &mb_cache_lru_list;
+                        spin_lock(&mb_cache_spinlock);
                 }
         }
         spin_unlock(&mb_cache_spinlock);
-        list_for_each_safe(l, ltmp, &free_list) {
-                __mb_cache_entry_forget(list_entry(l, struct mb_cache_entry,
-                                                   e_lru_list), GFP_KERNEL);
+
+        list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
+                __mb_cache_entry_forget(ce, GFP_KERNEL);
         }
 }
 
@@ -303,23 +451,27 @@ void
 mb_cache_destroy(struct mb_cache *cache)
 {
         LIST_HEAD(free_list);
-        struct list_head *l, *ltmp;
+        struct mb_cache_entry *ce, *tmp;
 
         spin_lock(&mb_cache_spinlock);
-        list_for_each_safe(l, ltmp, &mb_cache_lru_list) {
-                struct mb_cache_entry *ce =
-                        list_entry(l, struct mb_cache_entry, e_lru_list);
-                if (ce->e_cache == cache) {
+        list_for_each_entry_safe(ce, tmp, &mb_cache_lru_list, e_lru_list) {
+                if (ce->e_cache == cache)
                         list_move_tail(&ce->e_lru_list, &free_list);
-                        __mb_cache_entry_unhash(ce);
-                }
         }
         list_del(&cache->c_cache_list);
         spin_unlock(&mb_cache_spinlock);
 
-        list_for_each_safe(l, ltmp, &free_list) {
-                __mb_cache_entry_forget(list_entry(l, struct mb_cache_entry,
-                                                   e_lru_list), GFP_KERNEL);
+        list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
+                list_del_init(&ce->e_lru_list);
+                /*
+                 * Prevent any find or get operation on the entry.
+                 */
+                hlist_bl_lock(ce->e_block_hash_p);
+                hlist_bl_lock(ce->e_index_hash_p);
+                mb_assert(!(ce->e_used || ce->e_queued ||
+                        atomic_read(&ce->e_refcnt)));
+                __mb_cache_entry_unhash_unlock(ce);
+                __mb_cache_entry_forget(ce, GFP_KERNEL);
         }
 
         if (atomic_read(&cache->c_entry_count) > 0) {
@@ -328,8 +480,10 @@ mb_cache_destroy(struct mb_cache *cache)
                           atomic_read(&cache->c_entry_count));
         }
 
-        kmem_cache_destroy(cache->c_entry_cache);
-
+        if (list_empty(&mb_cache_list)) {
+                kmem_cache_destroy(mb_cache_kmem_cache);
+                mb_cache_kmem_cache = NULL;
+        }
         kfree(cache->c_index_hash);
         kfree(cache->c_block_hash);
         kfree(cache);
@@ -346,28 +500,61 @@ mb_cache_destroy(struct mb_cache *cache)
 struct mb_cache_entry *
 mb_cache_entry_alloc(struct mb_cache *cache, gfp_t gfp_flags)
 {
-        struct mb_cache_entry *ce = NULL;
+        struct mb_cache_entry *ce;
 
         if (atomic_read(&cache->c_entry_count) >= cache->c_max_entries) {
+                struct list_head *l;
+
+                l = &mb_cache_lru_list;
                 spin_lock(&mb_cache_spinlock);
-                if (!list_empty(&mb_cache_lru_list)) {
-                        ce = list_entry(mb_cache_lru_list.next,
-                                        struct mb_cache_entry, e_lru_list);
-                        list_del_init(&ce->e_lru_list);
-                        __mb_cache_entry_unhash(ce);
+                while (!list_is_last(l, &mb_cache_lru_list)) {
+                        l = l->next;
+                        ce = list_entry(l, struct mb_cache_entry, e_lru_list);
+                        if (ce->e_cache == cache) {
+                                list_del_init(&ce->e_lru_list);
+                                if (ce->e_used || ce->e_queued ||
+                                        atomic_read(&ce->e_refcnt))
+                                        continue;
+                                spin_unlock(&mb_cache_spinlock);
+                                /*
+                                 * Prevent any find or get operation on the
+                                 * entry.
+                                 */
+                                hlist_bl_lock(ce->e_block_hash_p);
+                                hlist_bl_lock(ce->e_index_hash_p);
+                                /* Ignore if it is touched by a find/get */
+                                if (ce->e_used || ce->e_queued ||
+                                        atomic_read(&ce->e_refcnt) ||
+                                        !list_empty(&ce->e_lru_list)) {
+                                        hlist_bl_unlock(ce->e_index_hash_p);
+                                        hlist_bl_unlock(ce->e_block_hash_p);
+                                        l = &mb_cache_lru_list;
+                                        spin_lock(&mb_cache_spinlock);
+                                        continue;
+                                }
+                                mb_assert(list_empty(&ce->e_lru_list));
+                                mb_assert(!(ce->e_used || ce->e_queued ||
+                                        atomic_read(&ce->e_refcnt)));
+                                __mb_cache_entry_unhash_unlock(ce);
+                                goto found;
+                        }
                 }
                 spin_unlock(&mb_cache_spinlock);
         }
-        if (!ce) {
-                ce = kmem_cache_alloc(cache->c_entry_cache, gfp_flags);
-                if (!ce)
-                        return NULL;
-                atomic_inc(&cache->c_entry_count);
-                INIT_LIST_HEAD(&ce->e_lru_list);
-                INIT_LIST_HEAD(&ce->e_block_list);
-                ce->e_cache = cache;
-                ce->e_queued = 0;
-        }
+
+        ce = kmem_cache_alloc(cache->c_entry_cache, gfp_flags);
+        if (!ce)
+                return NULL;
+        atomic_inc(&cache->c_entry_count);
+        INIT_LIST_HEAD(&ce->e_lru_list);
+        INIT_HLIST_BL_NODE(&ce->e_block_list);
+        INIT_HLIST_BL_NODE(&ce->e_index.o_list);
+        ce->e_cache = cache;
+        ce->e_queued = 0;
+        atomic_set(&ce->e_refcnt, 0);
+found:
+        ce->e_block_hash_p = &cache->c_block_hash[0];
+        ce->e_index_hash_p = &cache->c_index_hash[0];
         ce->e_used = 1 + MB_CACHE_WRITER;
         return ce;
 }
@@ -393,29 +580,38 @@ mb_cache_entry_insert(struct mb_cache_entry *ce, struct block_device *bdev,
 {
         struct mb_cache *cache = ce->e_cache;
         unsigned int bucket;
-        struct list_head *l;
-        int error = -EBUSY;
+        struct hlist_bl_node *l;
+        struct hlist_bl_head *block_hash_p;
+        struct hlist_bl_head *index_hash_p;
+        struct mb_cache_entry *lce;
 
+        mb_assert(ce);
         bucket = hash_long((unsigned long)bdev + (block & 0xffffffff), 
                            cache->c_bucket_bits);
-        spin_lock(&mb_cache_spinlock);
-        list_for_each_prev(l, &cache->c_block_hash[bucket]) {
-                struct mb_cache_entry *ce =
-                        list_entry(l, struct mb_cache_entry, e_block_list);
-                if (ce->e_bdev == bdev && ce->e_block == block)
-                        goto out;
+        block_hash_p = &cache->c_block_hash[bucket];
+        hlist_bl_lock(block_hash_p);
+        hlist_bl_for_each_entry(lce, l, block_hash_p, e_block_list) {
+                if (lce->e_bdev == bdev && lce->e_block == block) {
+                        hlist_bl_unlock(block_hash_p);
+                        return -EBUSY;
+                }
         }
-        __mb_cache_entry_unhash(ce);
+        mb_assert(!__mb_cache_entry_is_block_hashed(ce));
+        __mb_cache_entry_unhash_block(ce);
+        __mb_cache_entry_unhash_index(ce);
         ce->e_bdev = bdev;
         ce->e_block = block;
-        list_add(&ce->e_block_list, &cache->c_block_hash[bucket]);
+        ce->e_block_hash_p = block_hash_p;
         ce->e_index.o_key = key;
+        hlist_bl_add_head(&ce->e_block_list, block_hash_p);
+        hlist_bl_unlock(block_hash_p);
         bucket = hash_long(key, cache->c_bucket_bits);
-        list_add(&ce->e_index.o_list, &cache->c_index_hash[bucket]);
-        error = 0;
-out:
-        spin_unlock(&mb_cache_spinlock);
-        return error;
+        index_hash_p = &cache->c_index_hash[bucket];
+        hlist_bl_lock(index_hash_p);
+        ce->e_index_hash_p = index_hash_p;
+        hlist_bl_add_head(&ce->e_index.o_list, index_hash_p);
+        hlist_bl_unlock(index_hash_p);
+        return 0;
 }
 
 
@@ -429,24 +625,26 @@ out:
 void
 mb_cache_entry_release(struct mb_cache_entry *ce)
 {
-        spin_lock(&mb_cache_spinlock);
-        __mb_cache_entry_release_unlock(ce);
+        __mb_cache_entry_release(ce);
 }
 
 
 /*
  * mb_cache_entry_free()
  *
- * This is equivalent to the sequence mb_cache_entry_takeout() --
- * mb_cache_entry_release().
  */
 void
 mb_cache_entry_free(struct mb_cache_entry *ce)
 {
-        spin_lock(&mb_cache_spinlock);
+        mb_assert(ce);
         mb_assert(list_empty(&ce->e_lru_list));
-        __mb_cache_entry_unhash(ce);
-        __mb_cache_entry_release_unlock(ce);
+        hlist_bl_lock(ce->e_index_hash_p);
+        __mb_cache_entry_unhash_index(ce);
+        hlist_bl_unlock(ce->e_index_hash_p);
+        hlist_bl_lock(ce->e_block_hash_p);
+        __mb_cache_entry_unhash_block(ce);
+        hlist_bl_unlock(ce->e_block_hash_p);
+        __mb_cache_entry_release(ce);
 }
 
 
@@ -463,84 +661,110 @@ mb_cache_entry_get(struct mb_cache *cache, struct block_device *bdev,
                    sector_t block)
 {
         unsigned int bucket;
-        struct list_head *l;
+        struct hlist_bl_node *l;
         struct mb_cache_entry *ce;
+        struct hlist_bl_head *block_hash_p;
 
         bucket = hash_long((unsigned long)bdev + (block & 0xffffffff),
                            cache->c_bucket_bits);
-        spin_lock(&mb_cache_spinlock);
-        list_for_each(l, &cache->c_block_hash[bucket]) {
-                ce = list_entry(l, struct mb_cache_entry, e_block_list);
+        block_hash_p = &cache->c_block_hash[bucket];
+        /* First serialize access to the block corresponding hash chain. */
+        hlist_bl_lock(block_hash_p);
+        hlist_bl_for_each_entry(ce, l, block_hash_p, e_block_list) {
+                mb_assert(ce->e_block_hash_p == block_hash_p);
                 if (ce->e_bdev == bdev && ce->e_block == block) {
-                        DEFINE_WAIT(wait);
+                        /*
+                         * Prevent a free from removing the entry.
+                         */
+                        atomic_inc(&ce->e_refcnt);
+                        hlist_bl_unlock(block_hash_p);
+                        __spin_lock_mb_cache_entry(ce);
+                        atomic_dec(&ce->e_refcnt);
+                        if (ce->e_used > 0) {
+                                DEFINE_WAIT(wait);
+                                while (ce->e_used > 0) {
+                                        ce->e_queued++;
+                                        prepare_to_wait(&mb_cache_queue, &wait,
+                                                        TASK_UNINTERRUPTIBLE);
+                                        __spin_unlock_mb_cache_entry(ce);
+                                        schedule();
+                                        __spin_lock_mb_cache_entry(ce);
+                                        ce->e_queued--;
+                                }
+                                finish_wait(&mb_cache_queue, &wait);
+                        }
+                        ce->e_used += 1 + MB_CACHE_WRITER;
+                        __spin_unlock_mb_cache_entry(ce);
 
-                        if (!list_empty(&ce->e_lru_list))
+                        if (!list_empty(&ce->e_lru_list)) {
+                                spin_lock(&mb_cache_spinlock);
                                 list_del_init(&ce->e_lru_list);
-
-                        while (ce->e_used > 0) {
-                                ce->e_queued++;
-                                prepare_to_wait(&mb_cache_queue, &wait,
-                                                TASK_UNINTERRUPTIBLE);
                                 spin_unlock(&mb_cache_spinlock);
-                                schedule();
-                                spin_lock(&mb_cache_spinlock);
-                                ce->e_queued--;
                         }
-                        finish_wait(&mb_cache_queue, &wait);
-                        ce->e_used += 1 + MB_CACHE_WRITER;
-
-                        if (!__mb_cache_entry_is_hashed(ce)) {
-                                __mb_cache_entry_release_unlock(ce);
+                        if (!__mb_cache_entry_is_block_hashed(ce)) {
+                                __mb_cache_entry_release(ce);
                                 return NULL;
                         }
-                        goto cleanup;
+                        return ce;
                 }
         }
-        ce = NULL;
-
-cleanup:
-        spin_unlock(&mb_cache_spinlock);
-        return ce;
+        hlist_bl_unlock(block_hash_p);
+        return NULL;
 }
 
 #if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
 
 static struct mb_cache_entry *
-__mb_cache_entry_find(struct list_head *l, struct list_head *head,
+__mb_cache_entry_find(struct hlist_bl_node *l, struct hlist_bl_head *head,
                       struct block_device *bdev, unsigned int key)
 {
-        while (l != head) {
+
+        /* The index hash chain is alredy acquire by caller. */
+        while (l != NULL) {
                 struct mb_cache_entry *ce =
-                        list_entry(l, struct mb_cache_entry, e_index.o_list);
+                        hlist_bl_entry(l, struct mb_cache_entry,
+                                e_index.o_list);
+                mb_assert(ce->e_index_hash_p == head);
                 if (ce->e_bdev == bdev && ce->e_index.o_key == key) {
-                        DEFINE_WAIT(wait);
-
-                        if (!list_empty(&ce->e_lru_list))
-                                list_del_init(&ce->e_lru_list);
-
+                        /*
+                         * Prevent a free from removing the entry.
+                         */
+                        atomic_inc(&ce->e_refcnt);
+                        hlist_bl_unlock(head);
+                        __spin_lock_mb_cache_entry(ce);
+                        atomic_dec(&ce->e_refcnt);
+                        ce->e_used++;
                         /* Incrementing before holding the lock gives readers
                            priority over writers. */
-                        ce->e_used++;
-                        while (ce->e_used >= MB_CACHE_WRITER) {
-                                ce->e_queued++;
-                                prepare_to_wait(&mb_cache_queue, &wait,
-                                                TASK_UNINTERRUPTIBLE);
-                                spin_unlock(&mb_cache_spinlock);
-                                schedule();
-                                spin_lock(&mb_cache_spinlock);
-                                ce->e_queued--;
+                        if (ce->e_used >= MB_CACHE_WRITER) {
+                                DEFINE_WAIT(wait);
+
+                                while (ce->e_used >= MB_CACHE_WRITER) {
+                                        ce->e_queued++;
+                                        prepare_to_wait(&mb_cache_queue, &wait,
+                                                        TASK_UNINTERRUPTIBLE);
+                                        __spin_unlock_mb_cache_entry(ce);
+                                        schedule();
+                                        __spin_lock_mb_cache_entry(ce);
+                                        ce->e_queued--;
+                                }
+                                finish_wait(&mb_cache_queue, &wait);
                         }
-                        finish_wait(&mb_cache_queue, &wait);
-
-                        if (!__mb_cache_entry_is_hashed(ce)) {
-                                __mb_cache_entry_release_unlock(ce);
+                        __spin_unlock_mb_cache_entry(ce);
+                        if (!list_empty(&ce->e_lru_list)) {
                                 spin_lock(&mb_cache_spinlock);
+                                list_del_init(&ce->e_lru_list);
+                                spin_unlock(&mb_cache_spinlock);
+                        }
+                        if (!__mb_cache_entry_is_block_hashed(ce)) {
+                                __mb_cache_entry_release(ce);
                                 return ERR_PTR(-EAGAIN);
                         }
                         return ce;
                 }
                 l = l->next;
         }
+        hlist_bl_unlock(head);
         return NULL;
 }
 
@@ -562,13 +786,17 @@ mb_cache_entry_find_first(struct mb_cache *cache, struct block_device *bdev,
                           unsigned int key)
 {
         unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-        struct list_head *l;
-        struct mb_cache_entry *ce;
-
-        spin_lock(&mb_cache_spinlock);
-        l = cache->c_index_hash[bucket].next;
-        ce = __mb_cache_entry_find(l, &cache->c_index_hash[bucket], bdev, key);
-        spin_unlock(&mb_cache_spinlock);
+        struct hlist_bl_node *l;
+        struct mb_cache_entry *ce = NULL;
+        struct hlist_bl_head *index_hash_p;
+
+        index_hash_p = &cache->c_index_hash[bucket];
+        hlist_bl_lock(index_hash_p);
+        if (!hlist_bl_empty(index_hash_p)) {
+                l = hlist_bl_first(index_hash_p);
+                ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
+        } else
+                hlist_bl_unlock(index_hash_p);
         return ce;
 }
 
@@ -597,13 +825,17 @@ mb_cache_entry_find_next(struct mb_cache_entry *prev,
 {
         struct mb_cache *cache = prev->e_cache;
         unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-        struct list_head *l;
+        struct hlist_bl_node *l;
         struct mb_cache_entry *ce;
+        struct hlist_bl_head *index_hash_p;
 
-        spin_lock(&mb_cache_spinlock);
+        index_hash_p = &cache->c_index_hash[bucket];
+        mb_assert(prev->e_index_hash_p == index_hash_p);
+        hlist_bl_lock(index_hash_p);
+        mb_assert(!hlist_bl_empty(index_hash_p));
         l = prev->e_index.o_list.next;
-        ce = __mb_cache_entry_find(l, &cache->c_index_hash[bucket], bdev, key);
-        __mb_cache_entry_release_unlock(prev);
+        ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
+        __mb_cache_entry_release(prev);
         return ce;
 }
 
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 0332109162a5..f007a3355570 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -26,7 +26,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data);
 
 static void minix_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         if (!inode->i_nlink) {
                 inode->i_size = 0;
                 minix_truncate(inode);
@@ -86,7 +86,7 @@ static void init_once(void *foo)
         inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
         minix_inode_cachep = kmem_cache_create("minix_inode_cache",
                                              sizeof(struct minix_inode_info),
@@ -123,6 +123,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data)
         struct minix_sb_info * sbi = minix_sb(sb);
         struct minix_super_block * ms;
 
+        sync_filesystem(sb);
         ms = sbi->s_ms;
         if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
                 return 0;
diff --git a/fs/namei.c b/fs/namei.c
index 4b491b431990..88339f59efb5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1796,7 +1796,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
                         if (err)
                                 return err;
                 }
-                if (!d_is_directory(nd->path.dentry)) {
+                if (!d_can_lookup(nd->path.dentry)) {
                         err = -ENOTDIR; 
                         break;
                 }
@@ -1817,7 +1817,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
                 struct dentry *root = nd->root.dentry;
                 struct inode *inode = root->d_inode;
                 if (*name) {
-                        if (!d_is_directory(root))
+                        if (!d_can_lookup(root))
                                 return -ENOTDIR;
                         retval = inode_permission(inode, MAY_EXEC);
                         if (retval)
@@ -1873,7 +1873,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
                 dentry = f.file->f_path.dentry;
 
                 if (*name) {
-                        if (!d_is_directory(dentry)) {
+                        if (!d_can_lookup(dentry)) {
                                 fdput(f);
                                 return -ENOTDIR;
                         }
@@ -1955,7 +1955,7 @@ static int path_lookupat(int dfd, const char *name,
                 err = complete_walk(nd);
 
         if (!err && nd->flags & LOOKUP_DIRECTORY) {
-                if (!d_is_directory(nd->path.dentry)) {
+                if (!d_can_lookup(nd->path.dentry)) {
                         path_put(&nd->path);
                         err = -ENOTDIR;
                 }
@@ -2414,11 +2414,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
             IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
                 return -EPERM;
         if (isdir) {
-                if (!d_is_directory(victim) && !d_is_autodir(victim))
+                if (!d_is_dir(victim))
                         return -ENOTDIR;
                 if (IS_ROOT(victim))
                         return -EBUSY;
-        } else if (d_is_directory(victim) || d_is_autodir(victim))
+        } else if (d_is_dir(victim))
                 return -EISDIR;
         if (IS_DEADDIR(dir))
                 return -ENOENT;
@@ -2569,7 +2569,7 @@ static int handle_truncate(struct file *filp)
         /*
          * Refuse to truncate files with mandatory locks held on them.
          */
-        error = locks_verify_locked(inode);
+        error = locks_verify_locked(filp);
         if (!error)
                 error = security_path_truncate(path);
         if (!error) {
@@ -3016,11 +3016,10 @@ finish_open:
         }
         audit_inode(name, nd->path.dentry, 0);
         error = -EISDIR;
-        if ((open_flag & O_CREAT) &&
-            (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry)))
+        if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
                 goto out;
         error = -ENOTDIR;
-        if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry))
+        if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
                 goto out;
         if (!S_ISREG(nd->inode->i_mode))
                 will_truncate = false;
@@ -3744,7 +3743,7 @@ exit1:
 slashes:
         if (d_is_negative(dentry))
                 error = -ENOENT;
-        else if (d_is_directory(dentry) || d_is_autodir(dentry))
+        else if (d_is_dir(dentry))
                 error = -EISDIR;
         else
                 error = -ENOTDIR;
@@ -3974,7 +3973,28 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
         return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-/*
+/**
+ * vfs_rename - rename a filesystem object
+ * @old_dir:    parent of source
+ * @old_dentry: source
+ * @new_dir:    parent of destination
+ * @new_dentry: destination
+ * @delegated_inode: returns an inode needing a delegation break
+ * @flags:      rename flags
+ *
+ * The caller must hold multiple mutexes--see lock_rename()).
+ *
+ * If vfs_rename discovers a delegation in need of breaking at either
+ * the source or destination, it will return -EWOULDBLOCK and return a
+ * reference to the inode in delegated_inode.  The caller should then
+ * break the delegation and retry.  Because breaking a delegation may
+ * take a long time, the caller should drop all locks before doing
+ * so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ *
  * The worst of all namespace operations - renaming directory. "Perverted"
  * doesn't even start to describe it. Somebody in UCB had a heck of a trip...
  * Problems:
@@ -4002,163 +4022,139 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *         ->i_mutex on parents, which works but leads to some truly excessive
  *         locking].
  */
-static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
-                          struct inode *new_dir, struct dentry *new_dentry)
+int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+               struct inode *new_dir, struct dentry *new_dentry,
+               struct inode **delegated_inode, unsigned int flags)
 {
-        int error = 0;
+        int error;
+        bool is_dir = d_is_dir(old_dentry);
+        const unsigned char *old_name;
+        struct inode *source = old_dentry->d_inode;
         struct inode *target = new_dentry->d_inode;
+        bool new_is_dir = false;
         unsigned max_links = new_dir->i_sb->s_max_links;
 
+        if (source == target)
+                return 0;
+
+        error = may_delete(old_dir, old_dentry, is_dir);
+        if (error)
+                return error;
+
+        if (!target) {
+                error = may_create(new_dir, new_dentry);
+        } else {
+                new_is_dir = d_is_dir(new_dentry);
+
+                if (!(flags & RENAME_EXCHANGE))
+                        error = may_delete(new_dir, new_dentry, is_dir);
+                else
+                        error = may_delete(new_dir, new_dentry, new_is_dir);
+        }
+        if (error)
+                return error;
+
+        if (!old_dir->i_op->rename)
+                return -EPERM;
+
+        if (flags && !old_dir->i_op->rename2)
+                return -EINVAL;
+
         /*
          * If we are going to change the parent - check write permissions,
          * we'll need to flip '..'.
          */
         if (new_dir != old_dir) {
-                error = inode_permission(old_dentry->d_inode, MAY_WRITE);
-                if (error)
-                        return error;
+                if (is_dir) {
+                        error = inode_permission(source, MAY_WRITE);
+                        if (error)
+                                return error;
+                }
+                if ((flags & RENAME_EXCHANGE) && new_is_dir) {
+                        error = inode_permission(target, MAY_WRITE);
+                        if (error)
+                                return error;
+                }
         }
 
-        error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
+        error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
+                                      flags);
         if (error)
                 return error;
 
+        old_name = fsnotify_oldname_init(old_dentry->d_name.name);
         dget(new_dentry);
-        if (target)
+        if (!is_dir || (flags & RENAME_EXCHANGE))
+                lock_two_nondirectories(source, target);
+        else if (target)
                 mutex_lock(&target->i_mutex);
 
         error = -EBUSY;
         if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
                 goto out;
 
-        error = -EMLINK;
-        if (max_links && !target && new_dir != old_dir &&
-            new_dir->i_nlink >= max_links)
-                goto out;
-
-        if (target)
+        if (max_links && new_dir != old_dir) {
+                error = -EMLINK;
+                if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links)
+                        goto out;
+                if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir &&
+                    old_dir->i_nlink >= max_links)
+                        goto out;
+        }
+        if (is_dir && !(flags & RENAME_EXCHANGE) && target)
                 shrink_dcache_parent(new_dentry);
-        error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
-        if (error)
-                goto out;
-
-        if (target) {
-                target->i_flags |= S_DEAD;
-                dont_mount(new_dentry);
+        if (!is_dir) {
+                error = try_break_deleg(source, delegated_inode);
+                if (error)
+                        goto out;
         }
-out:
-        if (target)
-                mutex_unlock(&target->i_mutex);
-        dput(new_dentry);
-        if (!error)
-                if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
-                        d_move(old_dentry,new_dentry);
-        return error;
-}
-
-static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
-                            struct inode *new_dir, struct dentry *new_dentry,
-                            struct inode **delegated_inode)
-{
-        struct inode *target = new_dentry->d_inode;
-        struct inode *source = old_dentry->d_inode;
-        int error;
-
-        error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
-        if (error)
-                return error;
-
-        dget(new_dentry);
-        lock_two_nondirectories(source, target);
-
-        error = -EBUSY;
-        if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
-                goto out;
-
-        error = try_break_deleg(source, delegated_inode);
-        if (error)
-                goto out;
-        if (target) {
+        if (target && !new_is_dir) {
                 error = try_break_deleg(target, delegated_inode);
                 if (error)
                         goto out;
         }
-        error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
+        if (!flags) {
+                error = old_dir->i_op->rename(old_dir, old_dentry,
+                                              new_dir, new_dentry);
+        } else {
+                error = old_dir->i_op->rename2(old_dir, old_dentry,
+                                               new_dir, new_dentry, flags);
+        }
         if (error)
                 goto out;
 
-        if (target)
+        if (!(flags & RENAME_EXCHANGE) && target) {
+                if (is_dir)
+                        target->i_flags |= S_DEAD;
                 dont_mount(new_dentry);
-        if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
-                d_move(old_dentry, new_dentry);
+        }
+        if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
+                if (!(flags & RENAME_EXCHANGE))
+                        d_move(old_dentry, new_dentry);
+                else
+                        d_exchange(old_dentry, new_dentry);
+        }
 out:
-        unlock_two_nondirectories(source, target);
+        if (!is_dir || (flags & RENAME_EXCHANGE))
+                unlock_two_nondirectories(source, target);
+        else if (target)
+                mutex_unlock(&target->i_mutex);
         dput(new_dentry);
-        return error;
-}
-
-/**
- * vfs_rename - rename a filesystem object
- * @old_dir:    parent of source
- * @old_dentry: source
- * @new_dir:    parent of destination
- * @new_dentry: destination
- * @delegated_inode: returns an inode needing a delegation break
- *
- * The caller must hold multiple mutexes--see lock_rename()).
- *
- * If vfs_rename discovers a delegation in need of breaking at either
- * the source or destination, it will return -EWOULDBLOCK and return a
- * reference to the inode in delegated_inode.  The caller should then
- * break the delegation and retry.  Because breaking a delegation may
- * take a long time, the caller should drop all locks before doing
- * so.
- *
- * Alternatively, a caller may pass NULL for delegated_inode.  This may
- * be appropriate for callers that expect the underlying filesystem not
- * to be NFS exported.
- */
-int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
-               struct inode *new_dir, struct dentry *new_dentry,
-               struct inode **delegated_inode)
-{
-        int error;
-        int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry);
-        const unsigned char *old_name;
-
-        if (old_dentry->d_inode == new_dentry->d_inode)
-                return 0;
- 
-        error = may_delete(old_dir, old_dentry, is_dir);
-        if (error)
-                return error;
-
-        if (!new_dentry->d_inode)
-                error = may_create(new_dir, new_dentry);
-        else
-                error = may_delete(new_dir, new_dentry, is_dir);
-        if (error)
-                return error;
-
-        if (!old_dir->i_op->rename)
-                return -EPERM;
-
-        old_name = fsnotify_oldname_init(old_dentry->d_name.name);
-
-        if (is_dir)
-                error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
-        else
-                error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,delegated_inode);
-        if (!error)
+        if (!error) {
                 fsnotify_move(old_dir, new_dir, old_name, is_dir,
-                              new_dentry->d_inode, old_dentry);
+                              !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
+                if (flags & RENAME_EXCHANGE) {
+                        fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
+                                      new_is_dir, NULL, new_dentry);
+                }
+        }
         fsnotify_oldname_free(old_name);
 
         return error;
 }
 
-SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
-                int, newdfd, const char __user *, newname)
+SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
+                int, newdfd, const char __user *, newname, unsigned int, flags)
 {
         struct dentry *old_dir, *new_dir;
         struct dentry *old_dentry, *new_dentry;
@@ -4170,6 +4166,13 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
         unsigned int lookup_flags = 0;
         bool should_retry = false;
         int error;
+
+        if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+                return -EINVAL;
+
+        if ((flags & RENAME_NOREPLACE) && (flags & RENAME_EXCHANGE))
+                return -EINVAL;
+
 retry:
         from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
         if (IS_ERR(from)) {
@@ -4193,6 +4196,8 @@ retry:
                 goto exit2;
 
         new_dir = newnd.path.dentry;
+        if (flags & RENAME_NOREPLACE)
+                error = -EEXIST;
         if (newnd.last_type != LAST_NORM)
                 goto exit2;
 
@@ -4202,7 +4207,8 @@ retry:
 
         oldnd.flags &= ~LOOKUP_PARENT;
         newnd.flags &= ~LOOKUP_PARENT;
-        newnd.flags |= LOOKUP_RENAME_TARGET;
+        if (!(flags & RENAME_EXCHANGE))
+                newnd.flags |= LOOKUP_RENAME_TARGET;
 
 retry_deleg:
         trap = lock_rename(new_dir, old_dir);
@@ -4215,34 +4221,49 @@ retry_deleg:
         error = -ENOENT;
         if (d_is_negative(old_dentry))
                 goto exit4;
+        new_dentry = lookup_hash(&newnd);
+        error = PTR_ERR(new_dentry);
+        if (IS_ERR(new_dentry))
+                goto exit4;
+        error = -EEXIST;
+        if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry))
+                goto exit5;
+        if (flags & RENAME_EXCHANGE) {
+                error = -ENOENT;
+                if (d_is_negative(new_dentry))
+                        goto exit5;
+
+                if (!d_is_dir(new_dentry)) {
+                        error = -ENOTDIR;
+                        if (newnd.last.name[newnd.last.len])
+                                goto exit5;
+                }
+        }
         /* unless the source is a directory trailing slashes give -ENOTDIR */
-        if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) {
+        if (!d_is_dir(old_dentry)) {
                 error = -ENOTDIR;
                 if (oldnd.last.name[oldnd.last.len])
-                        goto exit4;
-                if (newnd.last.name[newnd.last.len])
-                        goto exit4;
+                        goto exit5;
+                if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len])
+                        goto exit5;
         }
         /* source should not be ancestor of target */
         error = -EINVAL;
         if (old_dentry == trap)
-                goto exit4;
-        new_dentry = lookup_hash(&newnd);
-        error = PTR_ERR(new_dentry);
-        if (IS_ERR(new_dentry))
-                goto exit4;
+                goto exit5;
         /* target should not be an ancestor of source */
-        error = -ENOTEMPTY;
+        if (!(flags & RENAME_EXCHANGE))
+                error = -ENOTEMPTY;
         if (new_dentry == trap)
                 goto exit5;
 
         error = security_path_rename(&oldnd.path, old_dentry,
-                                     &newnd.path, new_dentry);
+                                     &newnd.path, new_dentry, flags);
         if (error)
                 goto exit5;
         error = vfs_rename(old_dir->d_inode, old_dentry,
-                                   new_dir->d_inode, new_dentry,
-                                   &delegated_inode);
+                           new_dir->d_inode, new_dentry,
+                           &delegated_inode, flags);
 exit5:
         dput(new_dentry);
 exit4:
@@ -4272,9 +4293,15 @@ exit:
         return error;
 }
 
+SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
+                int, newdfd, const char __user *, newname)
+{
+        return sys_renameat2(olddfd, oldname, newdfd, newname, 0);
+}
+
 SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
 {
-        return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
+        return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
 int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 2cf2ebecb55f..647d86d2db39 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -99,6 +99,7 @@ static void destroy_inodecache(void)
 
 static int ncp_remount(struct super_block *sb, int *flags, char* data)
 {
+        sync_filesystem(sb);
         *flags |= MS_NODIRATIME;
         return 0;
 }
@@ -296,7 +297,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 static void
 ncp_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
 
         if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 56ff823ca82e..65d849bdf77a 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
         end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
         if (end != NFS_I(inode)->npages) {
                 rcu_read_lock();
-                end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+                end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
                 rcu_read_unlock();
         }
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 360114ae8b82..c4702baa22b8 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(nfs_clear_inode);
 
 void nfs_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         nfs_clear_inode(inode);
 }
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 808f29574412..6f340f02f2ba 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -90,7 +90,7 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
  */
 static void nfs4_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         pnfs_return_layout(inode);
         pnfs_destroy_layout(NFS_I(inode));
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 910ed906eb82..2cb56943e232 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2215,6 +2215,8 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
         struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data;
         u32 nfsvers = nfss->nfs_client->rpc_ops->version;
 
+        sync_filesystem(sb);
+
         /*
          * Userspace mount programs that send binary options generally send
          * them populated with default values. We have no way to know which
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 06cddd572264..2645be435e75 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -71,10 +71,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
         if (gid_eq(new->fsgid, INVALID_GID))
                 new->fsgid = exp->ex_anon_gid;
 
-        ret = set_groups(new, gi);
+        set_groups(new, gi);
         put_group_info(gi);
-        if (ret < 0)
-                goto error;
 
         if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID))
                 new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
@@ -89,7 +87,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 
 oom:
         ret = -ENOMEM;
-error:
         abort_creds(new);
         return ret;
 }
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 6d7be3f80356..915808b36df7 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1694,7 +1694,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
         if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
                 goto out_dput_new;
 
-        host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
+        host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
         if (!host_err) {
                 host_err = commit_metadata(tfhp);
                 if (!host_err)
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index deaa3d33a0aa..0d58075f34e2 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -942,6 +942,18 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
         struct inode *cpfile;
         int err;
 
+        if (cpsize > sb->s_blocksize) {
+                printk(KERN_ERR
+                       "NILFS: too large checkpoint size: %zu bytes.\n",
+                       cpsize);
+                return -EINVAL;
+        } else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) {
+                printk(KERN_ERR
+                       "NILFS: too small checkpoint size: %zu bytes.\n",
+                       cpsize);
+                return -EINVAL;
+        }
+
         cpfile = nilfs_iget_locked(sb, NULL, NILFS_CPFILE_INO);
         if (unlikely(!cpfile))
                 return -ENOMEM;
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index fa0f80308c2d..0d5fada91191 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -484,6 +484,18 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size,
         struct nilfs_dat_info *di;
         int err;
 
+        if (entry_size > sb->s_blocksize) {
+                printk(KERN_ERR
+                       "NILFS: too large DAT entry size: %zu bytes.\n",
+                       entry_size);
+                return -EINVAL;
+        } else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) {
+                printk(KERN_ERR
+                       "NILFS: too small DAT entry size: %zu bytes.\n",
+                       entry_size);
+                return -EINVAL;
+        }
+
         dat = nilfs_iget_locked(sb, NULL, NILFS_DAT_INO);
         if (unlikely(!dat))
                 return -ENOMEM;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 7e350c562e0e..b9c5726120e3 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -783,16 +783,14 @@ void nilfs_evict_inode(struct inode *inode)
         int ret;
 
         if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
-                if (inode->i_data.nrpages)
-                        truncate_inode_pages(&inode->i_data, 0);
+                truncate_inode_pages_final(&inode->i_data);
                 clear_inode(inode);
                 nilfs_clear_inode(inode);
                 return;
         }
         nilfs_transaction_begin(sb, &ti, 0); /* never fails */
 
-        if (inode->i_data.nrpages)
-                truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         /* TODO: some of the following operations may fail.  */
         nilfs_truncate_bmap(ii, 0);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 2b34021948e4..422fb54b7377 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1072,6 +1072,48 @@ out:
 }
 
 /**
+ * nilfs_ioctl_trim_fs() - trim ioctl handle function
+ * @inode: inode object
+ * @argp: pointer on argument from userspace
+ *
+ * Decription: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
+ * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
+ * performs the actual trim operation.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
+{
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+        struct request_queue *q = bdev_get_queue(nilfs->ns_bdev);
+        struct fstrim_range range;
+        int ret;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        if (!blk_queue_discard(q))
+                return -EOPNOTSUPP;
+
+        if (copy_from_user(&range, argp, sizeof(range)))
+                return -EFAULT;
+
+        range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity);
+
+        down_read(&nilfs->ns_segctor_sem);
+        ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range);
+        up_read(&nilfs->ns_segctor_sem);
+
+        if (ret < 0)
+                return ret;
+
+        if (copy_to_user(argp, &range, sizeof(range)))
+                return -EFAULT;
+
+        return 0;
+}
+
+/**
  * nilfs_ioctl_set_alloc_range - limit range of segments to be allocated
  * @inode: inode object
  * @argp: pointer on argument from userspace
@@ -1163,6 +1205,95 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
         return ret;
 }
 
+/**
+ * nilfs_ioctl_set_suinfo - set segment usage info
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: Expects an array of nilfs_suinfo_update structures
+ * encapsulated in nilfs_argv and updates the segment usage info
+ * according to the flags in nilfs_suinfo_update.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EPERM - Not enough permissions
+ *
+ * %-EFAULT - Error copying input data
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ */
+static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp,
+                                unsigned int cmd, void __user *argp)
+{
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+        struct nilfs_transaction_info ti;
+        struct nilfs_argv argv;
+        size_t len;
+        void __user *base;
+        void *kbuf;
+        int ret;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        ret = mnt_want_write_file(filp);
+        if (ret)
+                return ret;
+
+        ret = -EFAULT;
+        if (copy_from_user(&argv, argp, sizeof(argv)))
+                goto out;
+
+        ret = -EINVAL;
+        if (argv.v_size < sizeof(struct nilfs_suinfo_update))
+                goto out;
+
+        if (argv.v_nmembs > nilfs->ns_nsegments)
+                goto out;
+
+        if (argv.v_nmembs >= UINT_MAX / argv.v_size)
+                goto out;
+
+        len = argv.v_size * argv.v_nmembs;
+        if (!len) {
+                ret = 0;
+                goto out;
+        }
+
+        base = (void __user *)(unsigned long)argv.v_base;
+        kbuf = vmalloc(len);
+        if (!kbuf) {
+                ret = -ENOMEM;
+                goto out;
+        }
+
+        if (copy_from_user(kbuf, base, len)) {
+                ret = -EFAULT;
+                goto out_free;
+        }
+
+        nilfs_transaction_begin(inode->i_sb, &ti, 0);
+        ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size,
+                        argv.v_nmembs);
+        if (unlikely(ret < 0))
+                nilfs_transaction_abort(inode->i_sb);
+        else
+                nilfs_transaction_commit(inode->i_sb); /* never fails */
+
+out_free:
+        vfree(kbuf);
+out:
+        mnt_drop_write_file(filp);
+        return ret;
+}
+
 long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
         struct inode *inode = file_inode(filp);
@@ -1189,6 +1320,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 return nilfs_ioctl_get_info(inode, filp, cmd, argp,
                                             sizeof(struct nilfs_suinfo),
                                             nilfs_ioctl_do_get_suinfo);
+        case NILFS_IOCTL_SET_SUINFO:
+                return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp);
         case NILFS_IOCTL_GET_SUSTAT:
                 return nilfs_ioctl_get_sustat(inode, filp, cmd, argp);
         case NILFS_IOCTL_GET_VINFO:
@@ -1205,6 +1338,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 return nilfs_ioctl_resize(inode, filp, argp);
         case NILFS_IOCTL_SET_ALLOC_RANGE:
                 return nilfs_ioctl_set_alloc_range(inode, argp);
+        case FITRIM:
+                return nilfs_ioctl_trim_fs(inode, argp);
         default:
                 return -ENOTTY;
         }
@@ -1228,6 +1363,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
         case NILFS_IOCTL_GET_CPINFO:
         case NILFS_IOCTL_GET_CPSTAT:
         case NILFS_IOCTL_GET_SUINFO:
+        case NILFS_IOCTL_SET_SUINFO:
         case NILFS_IOCTL_GET_SUSTAT:
         case NILFS_IOCTL_GET_VINFO:
         case NILFS_IOCTL_GET_BDESCS:
@@ -1235,6 +1371,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
         case NILFS_IOCTL_SYNC:
         case NILFS_IOCTL_RESIZE:
         case NILFS_IOCTL_SET_ALLOC_RANGE:
+        case FITRIM:
                 break;
         default:
                 return -ENOIOCTLCMD;
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 3127e9f438a7..2a869c35c362 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -870,6 +870,289 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
 }
 
 /**
+ * nilfs_sufile_set_suinfo - sets segment usage info
+ * @sufile: inode of segment usage file
+ * @buf: array of suinfo_update
+ * @supsz: byte size of suinfo_update
+ * @nsup: size of suinfo_update array
+ *
+ * Description: Takes an array of nilfs_suinfo_update structs and updates
+ * segment usage accordingly. Only the fields indicated by the sup_flags
+ * are updated.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ */
+ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
+                                unsigned supsz, size_t nsup)
+{
+        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+        struct buffer_head *header_bh, *bh;
+        struct nilfs_suinfo_update *sup, *supend = buf + supsz * nsup;
+        struct nilfs_segment_usage *su;
+        void *kaddr;
+        unsigned long blkoff, prev_blkoff;
+        int cleansi, cleansu, dirtysi, dirtysu;
+        long ncleaned = 0, ndirtied = 0;
+        int ret = 0;
+
+        if (unlikely(nsup == 0))
+                return ret;
+
+        for (sup = buf; sup < supend; sup = (void *)sup + supsz) {
+                if (sup->sup_segnum >= nilfs->ns_nsegments
+                        || (sup->sup_flags &
+                                (~0UL << __NR_NILFS_SUINFO_UPDATE_FIELDS))
+                        || (nilfs_suinfo_update_nblocks(sup) &&
+                                sup->sup_sui.sui_nblocks >
+                                nilfs->ns_blocks_per_segment))
+                        return -EINVAL;
+        }
+
+        down_write(&NILFS_MDT(sufile)->mi_sem);
+
+        ret = nilfs_sufile_get_header_block(sufile, &header_bh);
+        if (ret < 0)
+                goto out_sem;
+
+        sup = buf;
+        blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
+        ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
+        if (ret < 0)
+                goto out_header;
+
+        for (;;) {
+                kaddr = kmap_atomic(bh->b_page);
+                su = nilfs_sufile_block_get_segment_usage(
+                        sufile, sup->sup_segnum, bh, kaddr);
+
+                if (nilfs_suinfo_update_lastmod(sup))
+                        su->su_lastmod = cpu_to_le64(sup->sup_sui.sui_lastmod);
+
+                if (nilfs_suinfo_update_nblocks(sup))
+                        su->su_nblocks = cpu_to_le32(sup->sup_sui.sui_nblocks);
+
+                if (nilfs_suinfo_update_flags(sup)) {
+                        /*
+                         * Active flag is a virtual flag projected by running
+                         * nilfs kernel code - drop it not to write it to
+                         * disk.
+                         */
+                        sup->sup_sui.sui_flags &=
+                                        ~(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
+
+                        cleansi = nilfs_suinfo_clean(&sup->sup_sui);
+                        cleansu = nilfs_segment_usage_clean(su);
+                        dirtysi = nilfs_suinfo_dirty(&sup->sup_sui);
+                        dirtysu = nilfs_segment_usage_dirty(su);
+
+                        if (cleansi && !cleansu)
+                                ++ncleaned;
+                        else if (!cleansi && cleansu)
+                                --ncleaned;
+
+                        if (dirtysi && !dirtysu)
+                                ++ndirtied;
+                        else if (!dirtysi && dirtysu)
+                                --ndirtied;
+
+                        su->su_flags = cpu_to_le32(sup->sup_sui.sui_flags);
+                }
+
+                kunmap_atomic(kaddr);
+
+                sup = (void *)sup + supsz;
+                if (sup >= supend)
+                        break;
+
+                prev_blkoff = blkoff;
+                blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
+                if (blkoff == prev_blkoff)
+                        continue;
+
+                /* get different block */
+                mark_buffer_dirty(bh);
+                put_bh(bh);
+                ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
+                if (unlikely(ret < 0))
+                        goto out_mark;
+        }
+        mark_buffer_dirty(bh);
+        put_bh(bh);
+
+ out_mark:
+        if (ncleaned || ndirtied) {
+                nilfs_sufile_mod_counter(header_bh, (u64)ncleaned,
+                                (u64)ndirtied);
+                NILFS_SUI(sufile)->ncleansegs += ncleaned;
+        }
+        nilfs_mdt_mark_dirty(sufile);
+ out_header:
+        put_bh(header_bh);
+ out_sem:
+        up_write(&NILFS_MDT(sufile)->mi_sem);
+        return ret;
+}
+
+/**
+ * nilfs_sufile_trim_fs() - trim ioctl handle function
+ * @sufile: inode of segment usage file
+ * @range: fstrim_range structure
+ *
+ * start:       First Byte to trim
+ * len:         number of Bytes to trim from start
+ * minlen:      minimum extent length in Bytes
+ *
+ * Decription: nilfs_sufile_trim_fs goes through all segments containing bytes
+ * from start to start+len. start is rounded up to the next block boundary
+ * and start+len is rounded down. For each clean segment blkdev_issue_discard
+ * function is invoked.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
+{
+        struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+        struct buffer_head *su_bh;
+        struct nilfs_segment_usage *su;
+        void *kaddr;
+        size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
+        sector_t seg_start, seg_end, start_block, end_block;
+        sector_t start = 0, nblocks = 0;
+        u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0;
+        int ret = 0;
+        unsigned int sects_per_block;
+
+        sects_per_block = (1 << nilfs->ns_blocksize_bits) /
+                        bdev_logical_block_size(nilfs->ns_bdev);
+        len = range->len >> nilfs->ns_blocksize_bits;
+        minlen = range->minlen >> nilfs->ns_blocksize_bits;
+        max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment);
+
+        if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits)
+                return -EINVAL;
+
+        start_block = (range->start + nilfs->ns_blocksize - 1) >>
+                        nilfs->ns_blocksize_bits;
+
+        /*
+         * range->len can be very large (actually, it is set to
+         * ULLONG_MAX by default) - truncate upper end of the range
+         * carefully so as not to overflow.
+         */
+        if (max_blocks - start_block < len)
+                end_block = max_blocks - 1;
+        else
+                end_block = start_block + len - 1;
+
+        segnum = nilfs_get_segnum_of_block(nilfs, start_block);
+        segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);
+
+        down_read(&NILFS_MDT(sufile)->mi_sem);
+
+        while (segnum <= segnum_end) {
+                n = nilfs_sufile_segment_usages_in_block(sufile, segnum,
+                                segnum_end);
+
+                ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
+                                                           &su_bh);
+                if (ret < 0) {
+                        if (ret != -ENOENT)
+                                goto out_sem;
+                        /* hole */
+                        segnum += n;
+                        continue;
+                }
+
+                kaddr = kmap_atomic(su_bh->b_page);
+                su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
+                                su_bh, kaddr);
+                for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
+                        if (!nilfs_segment_usage_clean(su))
+                                continue;
+
+                        nilfs_get_segment_range(nilfs, segnum, &seg_start,
+                                                &seg_end);
+
+                        if (!nblocks) {
+                                /* start new extent */
+                                start = seg_start;
+                                nblocks = seg_end - seg_start + 1;
+                                continue;
+                        }
+
+                        if (start + nblocks == seg_start) {
+                                /* add to previous extent */
+                                nblocks += seg_end - seg_start + 1;
+                                continue;
+                        }
+
+                        /* discard previous extent */
+                        if (start < start_block) {
+                                nblocks -= start_block - start;
+                                start = start_block;
+                        }
+
+                        if (nblocks >= minlen) {
+                                kunmap_atomic(kaddr);
+
+                                ret = blkdev_issue_discard(nilfs->ns_bdev,
+                                                start * sects_per_block,
+                                                nblocks * sects_per_block,
+                                                GFP_NOFS, 0);
+                                if (ret < 0) {
+                                        put_bh(su_bh);
+                                        goto out_sem;
+                                }
+
+                                ndiscarded += nblocks;
+                                kaddr = kmap_atomic(su_bh->b_page);
+                                su = nilfs_sufile_block_get_segment_usage(
+                                        sufile, segnum, su_bh, kaddr);
+                        }
+
+                        /* start new extent */
+                        start = seg_start;
+                        nblocks = seg_end - seg_start + 1;
+                }
+                kunmap_atomic(kaddr);
+                put_bh(su_bh);
+        }
+
+
+        if (nblocks) {
+                /* discard last extent */
+                if (start < start_block) {
+                        nblocks -= start_block - start;
+                        start = start_block;
+                }
+                if (start + nblocks > end_block + 1)
+                        nblocks = end_block - start + 1;
+
+                if (nblocks >= minlen) {
+                        ret = blkdev_issue_discard(nilfs->ns_bdev,
+                                        start * sects_per_block,
+                                        nblocks * sects_per_block,
+                                        GFP_NOFS, 0);
+                        if (!ret)
+                                ndiscarded += nblocks;
+                }
+        }
+
+out_sem:
+        up_read(&NILFS_MDT(sufile)->mi_sem);
+
+        range->len = ndiscarded << nilfs->ns_blocksize_bits;
+        return ret;
+}
+
+/**
  * nilfs_sufile_read - read or get sufile inode
  * @sb: super block instance
  * @susize: size of a segment usage entry
@@ -886,6 +1169,18 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
         void *kaddr;
         int err;
 
+        if (susize > sb->s_blocksize) {
+                printk(KERN_ERR
+                       "NILFS: too large segment usage size: %zu bytes.\n",
+                       susize);
+                return -EINVAL;
+        } else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) {
+                printk(KERN_ERR
+                       "NILFS: too small segment usage size: %zu bytes.\n",
+                       susize);
+                return -EINVAL;
+        }
+
         sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO);
         if (unlikely(!sufile))
                 return -ENOMEM;
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index e84bc5b51fc1..b8afd72f2379 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -44,6 +44,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *);
 ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned,
                                 size_t);
+ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned , size_t);
 
 int nilfs_sufile_updatev(struct inode *, __u64 *, size_t, int, size_t *,
                          void (*dofunc)(struct inode *, __u64,
@@ -65,6 +66,7 @@ void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *,
 int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs);
 int nilfs_sufile_read(struct super_block *sb, size_t susize,
                       struct nilfs_inode *raw_inode, struct inode **inodep);
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range);
 
 /**
  * nilfs_sufile_scrap - make a segment garbage
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 7ac2a122ca1d..8c532b2ca3ab 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1129,6 +1129,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
         unsigned long old_mount_opt;
         int err;
 
+        sync_filesystem(sb);
         old_sb_flags = sb->s_flags;
         old_mount_opt = nilfs->ns_mount_opt;
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 94c451ce6d24..8ba8229ba076 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -399,6 +399,16 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
                 return -EINVAL;
 
         nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size);
+        if (nilfs->ns_inode_size > nilfs->ns_blocksize) {
+                printk(KERN_ERR "NILFS: too large inode size: %d bytes.\n",
+                       nilfs->ns_inode_size);
+                return -EINVAL;
+        } else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) {
+                printk(KERN_ERR "NILFS: too small inode size: %d bytes.\n",
+                       nilfs->ns_inode_size);
+                return -EINVAL;
+        }
+
         nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino);
 
         nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index dc638f786d5c..ee9cb3795c2b 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -60,8 +60,8 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-static int fanotify_get_response_from_access(struct fsnotify_group *group,
-                                             struct fanotify_event_info *event)
+static int fanotify_get_response(struct fsnotify_group *group,
+                                 struct fanotify_perm_event_info *event)
 {
         int ret;
 
@@ -142,6 +142,40 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
         return false;
 }
 
+struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+                                                 struct path *path)
+{
+        struct fanotify_event_info *event;
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+        if (mask & FAN_ALL_PERM_EVENTS) {
+                struct fanotify_perm_event_info *pevent;
+
+                pevent = kmem_cache_alloc(fanotify_perm_event_cachep,
+                                          GFP_KERNEL);
+                if (!pevent)
+                        return NULL;
+                event = &pevent->fae;
+                pevent->response = 0;
+                goto init;
+        }
+#endif
+        event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+        if (!event)
+                return NULL;
+init: __maybe_unused
+        fsnotify_init_event(&event->fse, inode, mask);
+        event->tgid = get_pid(task_tgid(current));
+        if (path) {
+                event->path = *path;
+                path_get(&event->path);
+        } else {
+                event->path.mnt = NULL;
+                event->path.dentry = NULL;
+        }
+        return event;
+}
+
 static int fanotify_handle_event(struct fsnotify_group *group,
                                  struct inode *inode,
                                  struct fsnotify_mark *inode_mark,
@@ -171,25 +205,11 @@ static int fanotify_handle_event(struct fsnotify_group *group,
         pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
                  mask);
 
-        event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+        event = fanotify_alloc_event(inode, mask, data);
         if (unlikely(!event))
                 return -ENOMEM;
 
         fsn_event = &event->fse;
-        fsnotify_init_event(fsn_event, inode, mask);
-        event->tgid = get_pid(task_tgid(current));
-        if (data_type == FSNOTIFY_EVENT_PATH) {
-                struct path *path = data;
-                event->path = *path;
-                path_get(&event->path);
-        } else {
-                event->path.mnt = NULL;
-                event->path.dentry = NULL;
-        }
-#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-        event->response = 0;
-#endif
-
         ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
         if (ret) {
                 /* Permission events shouldn't be merged */
@@ -202,7 +222,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
         if (mask & FAN_ALL_PERM_EVENTS) {
-                ret = fanotify_get_response_from_access(group, event);
+                ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event));
                 fsnotify_destroy_event(group, fsn_event);
         }
 #endif
@@ -225,6 +245,13 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
         event = FANOTIFY_E(fsn_event);
         path_put(&event->path);
         put_pid(event->tgid);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+        if (fsn_event->mask & FAN_ALL_PERM_EVENTS) {
+                kmem_cache_free(fanotify_perm_event_cachep,
+                                FANOTIFY_PE(fsn_event));
+                return;
+        }
+#endif
         kmem_cache_free(fanotify_event_cachep, event);
 }
 
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 32a2f034fb94..2a5fb14115df 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -3,13 +3,12 @@
 #include <linux/slab.h>
 
 extern struct kmem_cache *fanotify_event_cachep;
+extern struct kmem_cache *fanotify_perm_event_cachep;
 
 /*
- * Lifetime of the structure differs for normal and permission events. In both
- * cases the structure is allocated in fanotify_handle_event(). For normal
- * events the structure is freed immediately after reporting it to userspace.
- * For permission events we free it only after we receive response from
- * userspace.
+ * Structure for normal fanotify events. It gets allocated in
+ * fanotify_handle_event() and freed when the information is retrieved by
+ * userspace
  */
 struct fanotify_event_info {
         struct fsnotify_event fse;
@@ -19,12 +18,33 @@ struct fanotify_event_info {
          */
         struct path path;
         struct pid *tgid;
+};
+
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-        u32 response;   /* userspace answer to question */
-#endif
+/*
+ * Structure for permission fanotify events. It gets allocated and freed in
+ * fanotify_handle_event() since we wait there for user response. When the
+ * information is retrieved by userspace the structure is moved from
+ * group->notification_list to group->fanotify_data.access_list to wait for
+ * user response.
+ */
+struct fanotify_perm_event_info {
+        struct fanotify_event_info fae;
+        int response;   /* userspace answer to question */
+        int fd;         /* fd we passed to userspace for this event */
 };
 
+static inline struct fanotify_perm_event_info *
+FANOTIFY_PE(struct fsnotify_event *fse)
+{
+        return container_of(fse, struct fanotify_perm_event_info, fae.fse);
+}
+#endif
+
 static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse)
 {
         return container_of(fse, struct fanotify_event_info, fse);
 }
+
+struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+                                                 struct path *path);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 287a22c04149..4e565c814309 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -28,14 +28,8 @@
 extern const struct fsnotify_ops fanotify_fsnotify_ops;
 
 static struct kmem_cache *fanotify_mark_cache __read_mostly;
-static struct kmem_cache *fanotify_response_event_cache __read_mostly;
 struct kmem_cache *fanotify_event_cachep __read_mostly;
-
-struct fanotify_response_event {
-        struct list_head list;
-        __s32 fd;
-        struct fanotify_event_info *event;
-};
+struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
 
 /*
  * Get an fsnotify notification event if one exists and is small
@@ -135,33 +129,34 @@ static int fill_event_metadata(struct fsnotify_group *group,
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-static struct fanotify_response_event *dequeue_re(struct fsnotify_group *group,
-                                                  __s32 fd)
+static struct fanotify_perm_event_info *dequeue_event(
+                                struct fsnotify_group *group, int fd)
 {
-        struct fanotify_response_event *re, *return_re = NULL;
+        struct fanotify_perm_event_info *event, *return_e = NULL;
 
-        mutex_lock(&group->fanotify_data.access_mutex);
-        list_for_each_entry(re, &group->fanotify_data.access_list, list) {
-                if (re->fd != fd)
+        spin_lock(&group->fanotify_data.access_lock);
+        list_for_each_entry(event, &group->fanotify_data.access_list,
+                            fae.fse.list) {
+                if (event->fd != fd)
                         continue;
 
-                list_del_init(&re->list);
-                return_re = re;
+                list_del_init(&event->fae.fse.list);
+                return_e = event;
                 break;
         }
-        mutex_unlock(&group->fanotify_data.access_mutex);
+        spin_unlock(&group->fanotify_data.access_lock);
 
-        pr_debug("%s: found return_re=%p\n", __func__, return_re);
+        pr_debug("%s: found return_re=%p\n", __func__, return_e);
 
-        return return_re;
+        return return_e;
 }
 
 static int process_access_response(struct fsnotify_group *group,
                                    struct fanotify_response *response_struct)
 {
-        struct fanotify_response_event *re;
-        __s32 fd = response_struct->fd;
-        __u32 response = response_struct->response;
+        struct fanotify_perm_event_info *event;
+        int fd = response_struct->fd;
+        int response = response_struct->response;
 
         pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
                  fd, response);
@@ -181,58 +176,15 @@ static int process_access_response(struct fsnotify_group *group,
         if (fd < 0)
                 return -EINVAL;
 
-        re = dequeue_re(group, fd);
-        if (!re)
+        event = dequeue_event(group, fd);
+        if (!event)
                 return -ENOENT;
 
-        re->event->response = response;
-
+        event->response = response;
         wake_up(&group->fanotify_data.access_waitq);
 
-        kmem_cache_free(fanotify_response_event_cache, re);
-
-        return 0;
-}
-
-static int prepare_for_access_response(struct fsnotify_group *group,
-                                       struct fsnotify_event *event,
-                                       __s32 fd)
-{
-        struct fanotify_response_event *re;
-
-        if (!(event->mask & FAN_ALL_PERM_EVENTS))
-                return 0;
-
-        re = kmem_cache_alloc(fanotify_response_event_cache, GFP_KERNEL);
-        if (!re)
-                return -ENOMEM;
-
-        re->event = FANOTIFY_E(event);
-        re->fd = fd;
-
-        mutex_lock(&group->fanotify_data.access_mutex);
-
-        if (atomic_read(&group->fanotify_data.bypass_perm)) {
-                mutex_unlock(&group->fanotify_data.access_mutex);
-                kmem_cache_free(fanotify_response_event_cache, re);
-                FANOTIFY_E(event)->response = FAN_ALLOW;
-                return 0;
-        }
-                
-        list_add_tail(&re->list, &group->fanotify_data.access_list);
-        mutex_unlock(&group->fanotify_data.access_mutex);
-
-        return 0;
-}
-
-#else
-static int prepare_for_access_response(struct fsnotify_group *group,
-                                       struct fsnotify_event *event,
-                                       __s32 fd)
-{
         return 0;
 }
-
 #endif
 
 static ssize_t copy_event_to_user(struct fsnotify_group *group,
@@ -247,7 +199,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 
         ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
         if (ret < 0)
-                goto out;
+                return ret;
 
         fd = fanotify_event_metadata.fd;
         ret = -EFAULT;
@@ -255,9 +207,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
                          fanotify_event_metadata.event_len))
                 goto out_close_fd;
 
-        ret = prepare_for_access_response(group, event, fd);
-        if (ret)
-                goto out_close_fd;
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+        if (event->mask & FAN_ALL_PERM_EVENTS)
+                FANOTIFY_PE(event)->fd = fd;
+#endif
 
         if (fd != FAN_NOFD)
                 fd_install(fd, f);
@@ -268,13 +221,6 @@ out_close_fd:
                 put_unused_fd(fd);
                 fput(f);
         }
-out:
-#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-        if (event->mask & FAN_ALL_PERM_EVENTS) {
-                FANOTIFY_E(event)->response = FAN_DENY;
-                wake_up(&group->fanotify_data.access_waitq);
-        }
-#endif
         return ret;
 }
 
@@ -314,35 +260,50 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
                 kevent = get_one_event(group, count);
                 mutex_unlock(&group->notification_mutex);
 
-                if (kevent) {
+                if (IS_ERR(kevent)) {
                         ret = PTR_ERR(kevent);
-                        if (IS_ERR(kevent))
+                        break;
+                }
+
+                if (!kevent) {
+                        ret = -EAGAIN;
+                        if (file->f_flags & O_NONBLOCK)
                                 break;
-                        ret = copy_event_to_user(group, kevent, buf);
-                        /*
-                         * Permission events get destroyed after we
-                         * receive response
-                         */
-                        if (!(kevent->mask & FAN_ALL_PERM_EVENTS))
-                                fsnotify_destroy_event(group, kevent);
-                        if (ret < 0)
+
+                        ret = -ERESTARTSYS;
+                        if (signal_pending(current))
+                                break;
+
+                        if (start != buf)
                                 break;
-                        buf += ret;
-                        count -= ret;
+                        schedule();
                         continue;
                 }
 
-                ret = -EAGAIN;
-                if (file->f_flags & O_NONBLOCK)
-                        break;
-                ret = -ERESTARTSYS;
-                if (signal_pending(current))
-                        break;
-
-                if (start != buf)
-                        break;
-
-                schedule();
+                ret = copy_event_to_user(group, kevent, buf);
+                /*
+                 * Permission events get queued to wait for response.  Other
+                 * events can be destroyed now.
+                 */
+                if (!(kevent->mask & FAN_ALL_PERM_EVENTS)) {
+                        fsnotify_destroy_event(group, kevent);
+                        if (ret < 0)
+                                break;
+                } else {
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+                        if (ret < 0) {
+                                FANOTIFY_PE(kevent)->response = FAN_DENY;
+                                wake_up(&group->fanotify_data.access_waitq);
+                                break;
+                        }
+                        spin_lock(&group->fanotify_data.access_lock);
+                        list_add_tail(&kevent->list,
+                                      &group->fanotify_data.access_list);
+                        spin_unlock(&group->fanotify_data.access_lock);
+#endif
+                }
+                buf += ret;
+                count -= ret;
         }
 
         finish_wait(&group->notification_waitq, &wait);
@@ -383,22 +344,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
         struct fsnotify_group *group = file->private_data;
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-        struct fanotify_response_event *re, *lre;
+        struct fanotify_perm_event_info *event, *next;
 
-        mutex_lock(&group->fanotify_data.access_mutex);
+        spin_lock(&group->fanotify_data.access_lock);
 
         atomic_inc(&group->fanotify_data.bypass_perm);
 
-        list_for_each_entry_safe(re, lre, &group->fanotify_data.access_list, list) {
-                pr_debug("%s: found group=%p re=%p event=%p\n", __func__, group,
-                         re, re->event);
+        list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
+                                 fae.fse.list) {
+                pr_debug("%s: found group=%p event=%p\n", __func__, group,
+                         event);
 
-                list_del_init(&re->list);
-                re->event->response = FAN_ALLOW;
-
-                kmem_cache_free(fanotify_response_event_cache, re);
+                list_del_init(&event->fae.fse.list);
+                event->response = FAN_ALLOW;
         }
-        mutex_unlock(&group->fanotify_data.access_mutex);
+        spin_unlock(&group->fanotify_data.access_lock);
 
         wake_up(&group->fanotify_data.access_waitq);
 #endif
@@ -731,21 +691,16 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
         group->fanotify_data.user = user;
         atomic_inc(&user->fanotify_listeners);
 
-        oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+        oevent = fanotify_alloc_event(NULL, FS_Q_OVERFLOW, NULL);
         if (unlikely(!oevent)) {
                 fd = -ENOMEM;
                 goto out_destroy_group;
         }
         group->overflow_event = &oevent->fse;
-        fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
-        oevent->tgid = get_pid(task_tgid(current));
-        oevent->path.mnt = NULL;
-        oevent->path.dentry = NULL;
 
         group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-        oevent->response = 0;
-        mutex_init(&group->fanotify_data.access_mutex);
+        spin_lock_init(&group->fanotify_data.access_lock);
         init_waitqueue_head(&group->fanotify_data.access_waitq);
         INIT_LIST_HEAD(&group->fanotify_data.access_list);
         atomic_set(&group->fanotify_data.bypass_perm, 0);
@@ -920,9 +875,11 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
 static int __init fanotify_user_setup(void)
 {
         fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC);
-        fanotify_response_event_cache = KMEM_CACHE(fanotify_response_event,
-                                                   SLAB_PANIC);
         fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+        fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event_info,
+                                                SLAB_PANIC);
+#endif
 
         return 0;
 }
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index ffb9b3675736..9d8153ebacfb 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -2259,7 +2259,7 @@ void ntfs_evict_big_inode(struct inode *vi)
 {
         ntfs_inode *ni = NTFS_I(vi);
 
-        truncate_inode_pages(&vi->i_data, 0);
+        truncate_inode_pages_final(&vi->i_data);
         clear_inode(vi);
 
 #ifdef NTFS_RW
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 82650d52d916..bd5610d48242 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -468,6 +468,8 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 
         ntfs_debug("Entering with remount options string: %s", opt);
 
+        sync_filesystem(sb);
+
 #ifndef NTFS_RW
         /* For read-only compiled driver, enforce read-only flag. */
         *flags |= MS_RDONLY;
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 555f4cddefe3..7e8282dcea2a 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -205,6 +205,7 @@ static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
         di->i_mode = cpu_to_le16(inode->i_mode);
         di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
         di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
         ocfs2_journal_dirty(handle, di_bh);
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index e2edff38be52..b4deb5f750d9 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5728,6 +5728,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
         }
 
         ocfs2_et_update_clusters(et, -len);
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
 
         ocfs2_journal_dirty(handle, et->et_root_bh);
 
@@ -6932,6 +6933,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
         di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
         spin_unlock(&oi->ip_lock);
 
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
         ocfs2_dinode_new_extent_list(inode, di);
 
         ocfs2_journal_dirty(handle, di_bh);
@@ -7208,6 +7210,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
         di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec);
         di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
 
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
         ocfs2_journal_dirty(handle, di_bh);
 
 out_commit:
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index aeb44e879c51..d310d12a9adc 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -571,7 +571,6 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 {
         struct inode *inode = file_inode(iocb->ki_filp);
         int level;
-        wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
 
         /* this io's submitter should not have unlocked this before we could */
         BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
@@ -582,10 +581,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
         if (ocfs2_iocb_is_unaligned_aio(iocb)) {
                 ocfs2_iocb_clear_unaligned_aio(iocb);
 
-                if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) &&
-                    waitqueue_active(wq)) {
-                        wake_up_all(wq);
-                }
+                mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
         }
 
         ocfs2_iocb_clear_rw_locked(iocb);
@@ -2043,6 +2039,7 @@ out_write_size:
         inode->i_mtime = inode->i_ctime = CURRENT_TIME;
         di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
         di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
         ocfs2_journal_dirty(handle, wc->w_di_bh);
 
         ocfs2_commit_trans(osb, handle);
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index f671e49beb34..6cae155d54df 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -102,9 +102,4 @@ enum ocfs2_iocb_lock_bits {
 #define ocfs2_iocb_is_unaligned_aio(iocb) \
         test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
 
-#define OCFS2_IOEND_WQ_HASH_SZ  37
-#define ocfs2_ioend_wq(v)   (&ocfs2__ioend_wq[((unsigned long)(v)) %\
-                                            OCFS2_IOEND_WQ_HASH_SZ])
-extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
-
 #endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 5b704c63a103..1edcb141f639 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -90,7 +90,6 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
                  * information for this bh as it's not marked locally
                  * uptodate. */
                 ret = -EIO;
-                put_bh(bh);
                 mlog_errno(ret);
         }
 
@@ -420,7 +419,6 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 
         if (!buffer_uptodate(bh)) {
                 ret = -EIO;
-                put_bh(bh);
                 mlog_errno(ret);
         }
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 2cd2406b4140..eb649d23a4de 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -262,17 +262,17 @@ static void o2net_update_recv_stats(struct o2net_sock_container *sc)
 
 #endif /* CONFIG_OCFS2_FS_STATS */
 
-static inline int o2net_reconnect_delay(void)
+static inline unsigned int o2net_reconnect_delay(void)
 {
         return o2nm_single_cluster->cl_reconnect_delay_ms;
 }
 
-static inline int o2net_keepalive_delay(void)
+static inline unsigned int o2net_keepalive_delay(void)
 {
         return o2nm_single_cluster->cl_keepalive_delay_ms;
 }
 
-static inline int o2net_idle_timeout(void)
+static inline unsigned int o2net_idle_timeout(void)
 {
         return o2nm_single_cluster->cl_idle_timeout_ms;
 }
@@ -1964,18 +1964,30 @@ static void o2net_listen_data_ready(struct sock *sk, int bytes)
                 goto out;
         }
 
-        /* ->sk_data_ready is also called for a newly established child socket
-         * before it has been accepted and the acceptor has set up their
-         * data_ready.. we only want to queue listen work for our listening
-         * socket */
+        /* This callback may called twice when a new connection
+         * is  being established as a child socket inherits everything
+         * from a parent LISTEN socket, including the data_ready cb of
+         * the parent. This leads to a hazard. In o2net_accept_one()
+         * we are still initializing the child socket but have not
+         * changed the inherited data_ready callback yet when
+         * data starts arriving.
+         * We avoid this hazard by checking the state.
+         * For the listening socket,  the state will be TCP_LISTEN; for the new
+         * socket, will be  TCP_ESTABLISHED. Also, in this case,
+         * sk->sk_user_data is not a valid function pointer.
+         */
+
         if (sk->sk_state == TCP_LISTEN) {
                 mlog(ML_TCP, "bytes: %d\n", bytes);
                 queue_work(o2net_wq, &o2net_listen_work);
+        } else {
+                ready = NULL;
         }
 
 out:
         read_unlock(&sk->sk_callback_lock);
-        ready(sk, bytes);
+        if (ready != NULL)
+                ready(sk, bytes);
 }
 
 static int o2net_open_listening_sock(__be32 addr, __be16 port)
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 0d3a97d2d5f6..e2e05a106beb 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -37,7 +37,6 @@
 #include "dlmglue.h"
 #include "file.h"
 #include "inode.h"
-#include "super.h"
 #include "ocfs2_trace.h"
 
 void ocfs2_dentry_attach_gen(struct dentry *dentry)
@@ -346,52 +345,6 @@ out_attach:
         return ret;
 }
 
-DEFINE_SPINLOCK(dentry_list_lock);
-
-/* We limit the number of dentry locks to drop in one go. We have
- * this limit so that we don't starve other users of ocfs2_wq. */
-#define DL_INODE_DROP_COUNT 64
-
-/* Drop inode references from dentry locks */
-static void __ocfs2_drop_dl_inodes(struct ocfs2_super *osb, int drop_count)
-{
-        struct ocfs2_dentry_lock *dl;
-
-        spin_lock(&dentry_list_lock);
-        while (osb->dentry_lock_list && (drop_count < 0 || drop_count--)) {
-                dl = osb->dentry_lock_list;
-                osb->dentry_lock_list = dl->dl_next;
-                spin_unlock(&dentry_list_lock);
-                iput(dl->dl_inode);
-                kfree(dl);
-                spin_lock(&dentry_list_lock);
-        }
-        spin_unlock(&dentry_list_lock);
-}
-
-void ocfs2_drop_dl_inodes(struct work_struct *work)
-{
-        struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
-                                               dentry_lock_work);
-
-        __ocfs2_drop_dl_inodes(osb, DL_INODE_DROP_COUNT);
-        /*
-         * Don't queue dropping if umount is in progress. We flush the
-         * list in ocfs2_dismount_volume
-         */
-        spin_lock(&dentry_list_lock);
-        if (osb->dentry_lock_list &&
-            !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
-                queue_work(ocfs2_wq, &osb->dentry_lock_work);
-        spin_unlock(&dentry_list_lock);
-}
-
-/* Flush the whole work queue */
-void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb)
-{
-        __ocfs2_drop_dl_inodes(osb, -1);
-}
-
 /*
  * ocfs2_dentry_iput() and friends.
  *
@@ -416,24 +369,16 @@ void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb)
 static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb,
                                    struct ocfs2_dentry_lock *dl)
 {
+        iput(dl->dl_inode);
         ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
         ocfs2_lock_res_free(&dl->dl_lockres);
-
-        /* We leave dropping of inode reference to ocfs2_wq as that can
-         * possibly lead to inode deletion which gets tricky */
-        spin_lock(&dentry_list_lock);
-        if (!osb->dentry_lock_list &&
-            !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
-                queue_work(ocfs2_wq, &osb->dentry_lock_work);
-        dl->dl_next = osb->dentry_lock_list;
-        osb->dentry_lock_list = dl;
-        spin_unlock(&dentry_list_lock);
+        kfree(dl);
 }
 
 void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
                            struct ocfs2_dentry_lock *dl)
 {
-        int unlock;
+        int unlock = 0;
 
         BUG_ON(dl->dl_count == 0);
 
diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h
index b79eff709958..55f58892b153 100644
--- a/fs/ocfs2/dcache.h
+++ b/fs/ocfs2/dcache.h
@@ -29,13 +29,8 @@
 extern const struct dentry_operations ocfs2_dentry_ops;
 
 struct ocfs2_dentry_lock {
-        /* Use count of dentry lock */
         unsigned int            dl_count;
-        union {
-                /* Linked list of dentry locks to release */
-                struct ocfs2_dentry_lock *dl_next;
-                u64                     dl_parent_blkno;
-        };
+        u64                     dl_parent_blkno;
 
         /*
          * The ocfs2_dentry_lock keeps an inode reference until
@@ -49,14 +44,9 @@ struct ocfs2_dentry_lock {
 int ocfs2_dentry_attach_lock(struct dentry *dentry, struct inode *inode,
                              u64 parent_blkno);
 
-extern spinlock_t dentry_list_lock;
-
 void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
                            struct ocfs2_dentry_lock *dl);
 
-void ocfs2_drop_dl_inodes(struct work_struct *work);
-void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb);
-
 struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno,
                                       int skip_unhashed);
 
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 91a7e85ac8fd..0717662b4aef 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2957,6 +2957,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
                 ocfs2_init_dir_trailer(dir, dirdata_bh, i);
         }
 
+        ocfs2_update_inode_fsync_trans(handle, dir, 1);
         ocfs2_journal_dirty(handle, dirdata_bh);
 
         if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) {
@@ -3005,6 +3006,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
         di->i_size = cpu_to_le64(sb->s_blocksize);
         di->i_ctime = di->i_mtime = cpu_to_le64(dir->i_ctime.tv_sec);
         di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(dir->i_ctime.tv_nsec);
+        ocfs2_update_inode_fsync_trans(handle, dir, 1);
 
         /*
          * This should never fail as our extent list is empty and all
@@ -3338,6 +3340,7 @@ do_extend:
         } else {
                 de->rec_len = cpu_to_le16(sb->s_blocksize);
         }
+        ocfs2_update_inode_fsync_trans(handle, dir, 1);
         ocfs2_journal_dirty(handle, new_bh);
 
         dir_i_size += dir->i_sb->s_blocksize;
@@ -3896,6 +3899,7 @@ out_commit:
                 dquot_free_space_nodirty(dir,
                                 ocfs2_clusters_to_bytes(dir->i_sb, 1));
 
+        ocfs2_update_inode_fsync_trans(handle, dir, 1);
         ocfs2_commit_trans(osb, handle);
 
 out:
@@ -4134,6 +4138,7 @@ static int ocfs2_expand_inline_dx_root(struct inode *dir,
                 mlog_errno(ret);
         did_quota = 0;
 
+        ocfs2_update_inode_fsync_trans(handle, dir, 1);
         ocfs2_journal_dirty(handle, dx_root_bh);
 
 out_commit:
@@ -4401,6 +4406,7 @@ static int ocfs2_dx_dir_remove_index(struct inode *dir,
         di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features);
         spin_unlock(&OCFS2_I(dir)->ip_lock);
         di->i_dx_root = cpu_to_le64(0ULL);
+        ocfs2_update_inode_fsync_trans(handle, dir, 1);
 
         ocfs2_journal_dirty(handle, di_bh);
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 33660a4a52fa..c973690dc0bc 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1123,7 +1123,6 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
         struct dlm_ctxt *dlm = NULL;
         char *local = NULL;
         int status = 0;
-        int locked = 0;
 
         qr = (struct dlm_query_region *) msg->buf;
 
@@ -1132,10 +1131,8 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
 
         /* buffer used in dlm_mast_regions() */
         local = kmalloc(sizeof(qr->qr_regions), GFP_KERNEL);
-        if (!local) {
-                status = -ENOMEM;
-                goto bail;
-        }
+        if (!local)
+                return -ENOMEM;
 
         status = -EINVAL;
 
@@ -1144,16 +1141,15 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
         if (!dlm) {
                 mlog(ML_ERROR, "Node %d queried hb regions on domain %s "
                      "before join domain\n", qr->qr_node, qr->qr_domain);
-                goto bail;
+                goto out_domain_lock;
         }
 
         spin_lock(&dlm->spinlock);
-        locked = 1;
         if (dlm->joining_node != qr->qr_node) {
                 mlog(ML_ERROR, "Node %d queried hb regions on domain %s "
                      "but joining node is %d\n", qr->qr_node, qr->qr_domain,
                      dlm->joining_node);
-                goto bail;
+                goto out_dlm_lock;
         }
 
         /* Support for global heartbeat was added in 1.1 */
@@ -1163,14 +1159,15 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
                      "but active dlm protocol is %d.%d\n", qr->qr_node,
                      qr->qr_domain, dlm->dlm_locking_proto.pv_major,
                      dlm->dlm_locking_proto.pv_minor);
-                goto bail;
+                goto out_dlm_lock;
         }
 
         status = dlm_match_regions(dlm, qr, local, sizeof(qr->qr_regions));
 
-bail:
-        if (locked)
-                spin_unlock(&dlm->spinlock);
+out_dlm_lock:
+        spin_unlock(&dlm->spinlock);
+
+out_domain_lock:
         spin_unlock(&dlm_domain_lock);
 
         kfree(local);
@@ -1877,19 +1874,19 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
                 goto bail;
         }
 
-        status = dlm_debug_init(dlm);
+        status = dlm_launch_thread(dlm);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
         }
 
-        status = dlm_launch_thread(dlm);
+        status = dlm_launch_recovery_thread(dlm);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
         }
 
-        status = dlm_launch_recovery_thread(dlm);
+        status = dlm_debug_init(dlm);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 7035af09cc03..fe29f7978f81 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -537,7 +537,10 @@ master_here:
                 /* success!  see if any other nodes need recovery */
                 mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
                      dlm->name, dlm->reco.dead_node, dlm->node_num);
-                dlm_reset_recovery(dlm);
+                spin_lock(&dlm->spinlock);
+                __dlm_reset_recovery(dlm);
+                dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+                spin_unlock(&dlm->spinlock);
         }
         dlm_end_recovery(dlm);
 
@@ -695,6 +698,14 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
                 if (all_nodes_done) {
                         int ret;
 
+                        /* Set this flag on recovery master to avoid
+                         * a new recovery for another dead node start
+                         * before the recovery is not done. That may
+                         * cause recovery hung.*/
+                        spin_lock(&dlm->spinlock);
+                        dlm->reco.state |= DLM_RECO_STATE_FINALIZE;
+                        spin_unlock(&dlm->spinlock);
+
                         /* all nodes are now in DLM_RECO_NODE_DATA_DONE state
                          * just send a finalize message to everyone and
                          * clean up */
@@ -1750,13 +1761,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
                                      struct dlm_migratable_lockres *mres)
 {
         struct dlm_migratable_lock *ml;
-        struct list_head *queue;
+        struct list_head *queue, *iter;
         struct list_head *tmpq = NULL;
         struct dlm_lock *newlock = NULL;
         struct dlm_lockstatus *lksb = NULL;
         int ret = 0;
         int i, j, bad;
-        struct dlm_lock *lock = NULL;
+        struct dlm_lock *lock;
         u8 from = O2NM_MAX_NODES;
         unsigned int added = 0;
         __be64 c;
@@ -1791,14 +1802,16 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
                         /* MIGRATION ONLY! */
                         BUG_ON(!(mres->flags & DLM_MRES_MIGRATION));
 
+                        lock = NULL;
                         spin_lock(&res->spinlock);
                         for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
                                 tmpq = dlm_list_idx_to_ptr(res, j);
-                                list_for_each_entry(lock, tmpq, list) {
-                                        if (lock->ml.cookie != ml->cookie)
-                                                lock = NULL;
-                                        else
+                                list_for_each(iter, tmpq) {
+                                        lock = list_entry(iter,
+                                                  struct dlm_lock, list);
+                                        if (lock->ml.cookie == ml->cookie)
                                                 break;
+                                        lock = NULL;
                                 }
                                 if (lock)
                                         break;
@@ -2882,8 +2895,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data,
                                 BUG();
                         }
                         dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+                        __dlm_reset_recovery(dlm);
                         spin_unlock(&dlm->spinlock);
-                        dlm_reset_recovery(dlm);
                         dlm_kick_recovery_thread(dlm);
                         break;
                 default:
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 19986959d149..6bd690b5a061 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3144,22 +3144,60 @@ out:
         return 0;
 }
 
+static void ocfs2_process_blocked_lock(struct ocfs2_super *osb,
+                                       struct ocfs2_lock_res *lockres);
+
 /* Mark the lockres as being dropped. It will no longer be
  * queued if blocking, but we still may have to wait on it
  * being dequeued from the downconvert thread before we can consider
  * it safe to drop.
  *
  * You can *not* attempt to call cluster_lock on this lockres anymore. */
-void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres)
+void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb,
+                                struct ocfs2_lock_res *lockres)
 {
         int status;
         struct ocfs2_mask_waiter mw;
-        unsigned long flags;
+        unsigned long flags, flags2;
 
         ocfs2_init_mask_waiter(&mw);
 
         spin_lock_irqsave(&lockres->l_lock, flags);
         lockres->l_flags |= OCFS2_LOCK_FREEING;
+        if (lockres->l_flags & OCFS2_LOCK_QUEUED && current == osb->dc_task) {
+                /*
+                 * We know the downconvert is queued but not in progress
+                 * because we are the downconvert thread and processing
+                 * different lock. So we can just remove the lock from the
+                 * queue. This is not only an optimization but also a way
+                 * to avoid the following deadlock:
+                 *   ocfs2_dentry_post_unlock()
+                 *     ocfs2_dentry_lock_put()
+                 *       ocfs2_drop_dentry_lock()
+                 *         iput()
+                 *           ocfs2_evict_inode()
+                 *             ocfs2_clear_inode()
+                 *               ocfs2_mark_lockres_freeing()
+                 *                 ... blocks waiting for OCFS2_LOCK_QUEUED
+                 *                 since we are the downconvert thread which
+                 *                 should clear the flag.
+                 */
+                spin_unlock_irqrestore(&lockres->l_lock, flags);
+                spin_lock_irqsave(&osb->dc_task_lock, flags2);
+                list_del_init(&lockres->l_blocked_list);
+                osb->blocked_lock_count--;
+                spin_unlock_irqrestore(&osb->dc_task_lock, flags2);
+                /*
+                 * Warn if we recurse into another post_unlock call.  Strictly
+                 * speaking it isn't a problem but we need to be careful if
+                 * that happens (stack overflow, deadlocks, ...) so warn if
+                 * ocfs2 grows a path for which this can happen.
+                 */
+                WARN_ON_ONCE(lockres->l_ops->post_unlock);
+                /* Since the lock is freeing we don't do much in the fn below */
+                ocfs2_process_blocked_lock(osb, lockres);
+                return;
+        }
         while (lockres->l_flags & OCFS2_LOCK_QUEUED) {
                 lockres_add_mask_waiter(lockres, &mw, OCFS2_LOCK_QUEUED, 0);
                 spin_unlock_irqrestore(&lockres->l_lock, flags);
@@ -3180,7 +3218,7 @@ void ocfs2_simple_drop_lockres(struct ocfs2_super *osb,
 {
         int ret;
 
-        ocfs2_mark_lockres_freeing(lockres);
+        ocfs2_mark_lockres_freeing(osb, lockres);
         ret = ocfs2_drop_lock(osb, lockres);
         if (ret)
                 mlog_errno(ret);
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index 1d596d8c4a4a..d293a22c32c5 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -157,7 +157,8 @@ int ocfs2_refcount_lock(struct ocfs2_refcount_tree *ref_tree, int ex);
 void ocfs2_refcount_unlock(struct ocfs2_refcount_tree *ref_tree, int ex);
 
 
-void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres);
+void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb,
+                                struct ocfs2_lock_res *lockres);
 void ocfs2_simple_drop_lockres(struct ocfs2_super *osb,
                                struct ocfs2_lock_res *lockres);
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 51632c40e896..ff33c5ef87f2 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -175,9 +175,13 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
                            int datasync)
 {
         int err = 0;
-        journal_t *journal;
         struct inode *inode = file->f_mapping->host;
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        journal_t *journal = osb->journal->j_journal;
+        int ret;
+        tid_t commit_tid;
+        bool needs_barrier = false;
 
         trace_ocfs2_sync_file(inode, file, file->f_path.dentry,
                               OCFS2_I(inode)->ip_blkno,
@@ -192,29 +196,19 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
         if (err)
                 return err;
 
-        /*
-         * Probably don't need the i_mutex at all in here, just putting it here
-         * to be consistent with how fsync used to be called, someone more
-         * familiar with the fs could possibly remove it.
-         */
-        mutex_lock(&inode->i_mutex);
-        if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) {
-                /*
-                 * We still have to flush drive's caches to get data to the
-                 * platter
-                 */
-                if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER)
-                        blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
-                goto bail;
+        commit_tid = datasync ? oi->i_datasync_tid : oi->i_sync_tid;
+        if (journal->j_flags & JBD2_BARRIER &&
+            !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+                needs_barrier = true;
+        err = jbd2_complete_transaction(journal, commit_tid);
+        if (needs_barrier) {
+                ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+                if (!err)
+                        err = ret;
         }
 
-        journal = osb->journal->j_journal;
-        err = jbd2_journal_force_commit(journal);
-
-bail:
         if (err)
                 mlog_errno(err);
-        mutex_unlock(&inode->i_mutex);
 
         return (err < 0) ? -EIO : 0;
 }
@@ -292,6 +286,7 @@ int ocfs2_update_inode_atime(struct inode *inode,
         inode->i_atime = CURRENT_TIME;
         di->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
         di->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
         ocfs2_journal_dirty(handle, bh);
 
 out_commit:
@@ -341,6 +336,7 @@ int ocfs2_simple_size_update(struct inode *inode,
         if (ret < 0)
                 mlog_errno(ret);
 
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
         ocfs2_commit_trans(osb, handle);
 out:
         return ret;
@@ -435,6 +431,7 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb,
         di->i_size = cpu_to_le64(new_i_size);
         di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec);
         di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
         ocfs2_journal_dirty(handle, fe_bh);
 
@@ -650,7 +647,7 @@ restarted_transaction:
                         mlog_errno(status);
                 goto leave;
         }
-
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
         ocfs2_journal_dirty(handle, bh);
 
         spin_lock(&OCFS2_I(inode)->ip_lock);
@@ -743,6 +740,7 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
                                       OCFS2_JOURNAL_ACCESS_WRITE);
         if (ret)
                 mlog_errno(ret);
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
 
 out:
         if (ret) {
@@ -840,6 +838,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
                 di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
                 di->i_mtime_nsec = di->i_ctime_nsec;
                 ocfs2_journal_dirty(handle, di_bh);
+                ocfs2_update_inode_fsync_trans(handle, inode, 1);
                 ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
         }
 
@@ -1344,6 +1343,7 @@ static int __ocfs2_write_remove_suid(struct inode *inode,
 
         di = (struct ocfs2_dinode *) bh->b_data;
         di->i_mode = cpu_to_le16(inode->i_mode);
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
         ocfs2_journal_dirty(handle, bh);
 
@@ -1576,6 +1576,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
                 if (ret)
                         mlog_errno(ret);
         }
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
 
         ocfs2_commit_trans(osb, handle);
 out:
@@ -2061,13 +2062,6 @@ out:
         return ret;
 }
 
-static void ocfs2_aiodio_wait(struct inode *inode)
-{
-        wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
-
-        wait_event(*wq, (atomic_read(&OCFS2_I(inode)->ip_unaligned_aio) == 0));
-}
-
 static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
 {
         int blockmask = inode->i_sb->s_blocksize - 1;
@@ -2345,10 +2339,8 @@ relock:
                  * Wait on previous unaligned aio to complete before
                  * proceeding.
                  */
-                ocfs2_aiodio_wait(inode);
-
-                /* Mark the iocb as needing a decrement in ocfs2_dio_end_io */
-                atomic_inc(&OCFS2_I(inode)->ip_unaligned_aio);
+                mutex_lock(&OCFS2_I(inode)->ip_unaligned_aio);
+                /* Mark the iocb as needing an unlock in ocfs2_dio_end_io */
                 ocfs2_iocb_set_unaligned_aio(iocb);
         }
 
@@ -2428,7 +2420,7 @@ out_dio:
 
         if (unaligned_dio) {
                 ocfs2_iocb_clear_unaligned_aio(iocb);
-                atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio);
+                mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
         }
 
 out:
@@ -2645,7 +2637,16 @@ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
         case SEEK_SET:
                 break;
         case SEEK_END:
-                offset += inode->i_size;
+                /* SEEK_END requires the OCFS2 inode lock for the file
+                 * because it references the file's size.
+                 */
+                ret = ocfs2_inode_lock(inode, NULL, 0);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+                offset += i_size_read(inode);
+                ocfs2_inode_unlock(inode, 0);
                 break;
         case SEEK_CUR:
                 if (offset == 0) {
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index f29a90fde619..437de7f768c6 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -130,6 +130,7 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
         struct inode *inode = NULL;
         struct super_block *sb = osb->sb;
         struct ocfs2_find_inode_args args;
+        journal_t *journal = OCFS2_SB(sb)->journal->j_journal;
 
         trace_ocfs2_iget_begin((unsigned long long)blkno, flags,
                                sysfile_type);
@@ -169,6 +170,32 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
                 goto bail;
         }
 
+        /*
+         * Set transaction id's of transactions that have to be committed
+         * to finish f[data]sync. We set them to currently running transaction
+         * as we cannot be sure that the inode or some of its metadata isn't
+         * part of the transaction - the inode could have been reclaimed and
+         * now it is reread from disk.
+         */
+        if (journal) {
+                transaction_t *transaction;
+                tid_t tid;
+                struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+                read_lock(&journal->j_state_lock);
+                if (journal->j_running_transaction)
+                        transaction = journal->j_running_transaction;
+                else
+                        transaction = journal->j_committing_transaction;
+                if (transaction)
+                        tid = transaction->t_tid;
+                else
+                        tid = journal->j_commit_sequence;
+                read_unlock(&journal->j_state_lock);
+                oi->i_sync_tid = tid;
+                oi->i_datasync_tid = tid;
+        }
+
 bail:
         if (!IS_ERR(inode)) {
                 trace_ocfs2_iget_end(inode, 
@@ -804,11 +831,13 @@ static int ocfs2_inode_is_valid_to_delete(struct inode *inode)
                 goto bail;
         }
 
-        /* If we're coming from downconvert_thread we can't go into our own
-         * voting [hello, deadlock city!], so unforuntately we just
-         * have to skip deleting this guy. That's OK though because
-         * the node who's doing the actual deleting should handle it
-         * anyway. */
+        /*
+         * If we're coming from downconvert_thread we can't go into our own
+         * voting [hello, deadlock city!] so we cannot delete the inode. But
+         * since we dropped last inode ref when downconverting dentry lock,
+         * we cannot have the file open and thus the node doing unlink will
+         * take care of deleting the inode.
+         */
         if (current == osb->dc_task)
                 goto bail;
 
@@ -822,12 +851,6 @@ static int ocfs2_inode_is_valid_to_delete(struct inode *inode)
                 goto bail_unlock;
         }
 
-        /* If we have allowd wipe of this inode for another node, it
-         * will be marked here so we can safely skip it. Recovery will
-         * cleanup any inodes we might inadvertently skip here. */
-        if (oi->ip_flags & OCFS2_INODE_SKIP_DELETE)
-                goto bail_unlock;
-
         ret = 1;
 bail_unlock:
         spin_unlock(&oi->ip_lock);
@@ -941,7 +964,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode,
                 (unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data);
         if (sync_data)
                 filemap_write_and_wait(inode->i_mapping);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 }
 
 static void ocfs2_delete_inode(struct inode *inode)
@@ -960,8 +983,6 @@ static void ocfs2_delete_inode(struct inode *inode)
         if (is_bad_inode(inode) || !OCFS2_I(inode)->ip_blkno)
                 goto bail;
 
-        dquot_initialize(inode);
-
         if (!ocfs2_inode_is_valid_to_delete(inode)) {
                 /* It's probably not necessary to truncate_inode_pages
                  * here but we do it for safety anyway (it will most
@@ -970,6 +991,8 @@ static void ocfs2_delete_inode(struct inode *inode)
                 goto bail;
         }
 
+        dquot_initialize(inode);
+
         /* We want to block signals in delete_inode as the lock and
          * messaging paths may return us -ERESTARTSYS. Which would
          * cause us to exit early, resulting in inodes being orphaned
@@ -1057,6 +1080,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 {
         int status;
         struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
         clear_inode(inode);
         trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno,
@@ -1073,9 +1097,9 @@ static void ocfs2_clear_inode(struct inode *inode)
 
         /* Do these before all the other work so that we don't bounce
          * the downconvert thread while waiting to destroy the locks. */
-        ocfs2_mark_lockres_freeing(&oi->ip_rw_lockres);
-        ocfs2_mark_lockres_freeing(&oi->ip_inode_lockres);
-        ocfs2_mark_lockres_freeing(&oi->ip_open_lockres);
+        ocfs2_mark_lockres_freeing(osb, &oi->ip_rw_lockres);
+        ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres);
+        ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres);
 
         ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap,
                            &oi->ip_la_data_resv);
@@ -1157,7 +1181,7 @@ void ocfs2_evict_inode(struct inode *inode)
             (OCFS2_I(inode)->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)) {
                 ocfs2_delete_inode(inode);
         } else {
-                truncate_inode_pages(&inode->i_data, 0);
+                truncate_inode_pages_final(&inode->i_data);
         }
         ocfs2_clear_inode(inode);
 }
@@ -1260,6 +1284,7 @@ int ocfs2_mark_inode_dirty(handle_t *handle,
         fe->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
 
         ocfs2_journal_dirty(handle, bh);
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
 leave:
         return status;
 }
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 621fc73bf23d..a6c991c0fc98 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -44,7 +44,7 @@ struct ocfs2_inode_info
         struct rw_semaphore             ip_xattr_sem;
 
         /* Number of outstanding AIO's which are not page aligned */
-        atomic_t                        ip_unaligned_aio;
+        struct mutex                    ip_unaligned_aio;
 
         /* These fields are protected by ip_lock */
         spinlock_t                      ip_lock;
@@ -73,6 +73,13 @@ struct ocfs2_inode_info
         u32                             ip_dir_lock_gen;
 
         struct ocfs2_alloc_reservation  ip_la_data_resv;
+
+        /*
+         * Transactions that contain inode's metadata needed to complete
+         * fsync and fdatasync, respectively.
+         */
+        tid_t i_sync_tid;
+        tid_t i_datasync_tid;
 };
 
 /*
@@ -84,8 +91,6 @@ struct ocfs2_inode_info
 #define OCFS2_INODE_BITMAP              0x00000004
 /* This inode has been wiped from disk */
 #define OCFS2_INODE_DELETED             0x00000008
-/* Another node is deleting, so our delete is a nop */
-#define OCFS2_INODE_SKIP_DELETE         0x00000010
 /* Has the inode been orphaned on another node?
  *
  * This hints to ocfs2_drop_inode that it should clear i_nlink before
@@ -100,11 +105,11 @@ struct ocfs2_inode_info
  * rely on ocfs2_delete_inode to sort things out under the proper
  * cluster locks.
  */
-#define OCFS2_INODE_MAYBE_ORPHANED      0x00000020
+#define OCFS2_INODE_MAYBE_ORPHANED      0x00000010
 /* Does someone have the file open O_DIRECT */
-#define OCFS2_INODE_OPEN_DIRECT         0x00000040
+#define OCFS2_INODE_OPEN_DIRECT         0x00000020
 /* Tell the inode wipe code it's not in orphan dir */
-#define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000080
+#define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000040
 
 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode)
 {
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 8ca3c29accbf..490229f43731 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -413,11 +413,12 @@ int ocfs2_info_handle_freeinode(struct inode *inode,
                 }
 
                 status = ocfs2_info_scan_inode_alloc(osb, inode_alloc, blkno, oifi, i);
-                if (status < 0)
-                        goto bail;
 
                 iput(inode_alloc);
                 inode_alloc = NULL;
+
+                if (status < 0)
+                        goto bail;
         }
 
         o2info_set_request_filled(&oifi->ifi_req);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 44fc3e530c3d..03ea9314fecd 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -2132,12 +2132,6 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
                 iter = oi->ip_next_orphan;
 
                 spin_lock(&oi->ip_lock);
-                /* The remote delete code may have set these on the
-                 * assumption that the other node would wipe them
-                 * successfully.  If they are still in the node's
-                 * orphan dir, we need to reset that state. */
-                oi->ip_flags &= ~(OCFS2_INODE_DELETED|OCFS2_INODE_SKIP_DELETE);
-
                 /* Set the proper information to get us going into
                  * ocfs2_delete_inode. */
                 oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 9ff4e8cf9d97..7f8cde94abfe 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -626,4 +626,15 @@ static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
                                 new_size);
 }
 
+static inline void ocfs2_update_inode_fsync_trans(handle_t *handle,
+                                                  struct inode *inode,
+                                                  int datasync)
+{
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+        oi->i_sync_tid = handle->h_transaction->t_tid;
+        if (datasync)
+                oi->i_datasync_tid = handle->h_transaction->t_tid;
+}
+
 #endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index e57c804069ea..6b6d092b0998 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -82,6 +82,8 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
         }
 
         ret = flock_lock_file_wait(file, fl);
+        if (ret)
+                ocfs2_file_unlock(file);
 
 out:
         mutex_unlock(&fp->fp_mutex);
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 64c304d668f0..599eb4c4c8be 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -151,6 +151,7 @@ static int __ocfs2_move_extent(handle_t *handle,
                                                         old_blkno, len);
         }
 
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
 out:
         ocfs2_free_path(path);
         return ret;
@@ -690,8 +691,11 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 
         ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
                                          goal_bit, len);
-        if (ret)
+        if (ret) {
+                ocfs2_rollback_alloc_dinode_counts(gb_inode, gb_bh, len,
+                                               le16_to_cpu(gd->bg_chain));
                 mlog_errno(ret);
+        }
 
         /*
          * Here we should write the new page out first if we are
@@ -957,6 +961,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
         inode->i_ctime = CURRENT_TIME;
         di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
         di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
         ocfs2_journal_dirty(handle, di_bh);
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3683643f3f0e..2060fc398445 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -450,7 +450,6 @@ leave:
 
         brelse(new_fe_bh);
         brelse(parent_fe_bh);
-        kfree(si.name);
         kfree(si.value);
 
         ocfs2_free_dir_lookup_result(&lookup);
@@ -495,6 +494,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
         struct ocfs2_dinode *fe = NULL;
         struct ocfs2_extent_list *fel;
         u16 feat;
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
         *new_fe_bh = NULL;
 
@@ -576,8 +576,8 @@ static int __ocfs2_mknod_locked(struct inode *dir,
                         mlog_errno(status);
         }
 
-        status = 0; /* error in ocfs2_create_new_inode_locks is not
-                     * critical */
+        oi->i_sync_tid = handle->h_transaction->t_tid;
+        oi->i_datasync_tid = handle->h_transaction->t_tid;
 
 leave:
         if (status < 0) {
@@ -1855,7 +1855,6 @@ bail:
 
         brelse(new_fe_bh);
         brelse(parent_fe_bh);
-        kfree(si.name);
         kfree(si.value);
         ocfs2_free_dir_lookup_result(&lookup);
         if (inode_ac)
@@ -2481,6 +2480,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
         di->i_orphaned_slot = 0;
         set_nlink(inode, 1);
         ocfs2_set_links_count(di, inode->i_nlink);
+        ocfs2_update_inode_fsync_trans(handle, inode, 1);
         ocfs2_journal_dirty(handle, di_bh);
 
         status = ocfs2_add_entry(handle, dentry, inode,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 553f53cc73ae..8d64a97a9d5e 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -30,6 +30,7 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/rbtree.h>
 #include <linux/workqueue.h>
 #include <linux/kref.h>
@@ -274,19 +275,16 @@ enum ocfs2_mount_options
         OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */
 };
 
-#define OCFS2_OSB_SOFT_RO                       0x0001
-#define OCFS2_OSB_HARD_RO                       0x0002
-#define OCFS2_OSB_ERROR_FS                      0x0004
-#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED        0x0008
-
-#define OCFS2_DEFAULT_ATIME_QUANTUM             60
+#define OCFS2_OSB_SOFT_RO       0x0001
+#define OCFS2_OSB_HARD_RO       0x0002
+#define OCFS2_OSB_ERROR_FS      0x0004
+#define OCFS2_DEFAULT_ATIME_QUANTUM     60
 
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
 struct ocfs2_replay_map;
 struct ocfs2_quota_recovery;
-struct ocfs2_dentry_lock;
 struct ocfs2_super
 {
         struct task_struct *commit_task;
@@ -414,10 +412,9 @@ struct ocfs2_super
         struct list_head blocked_lock_list;
         unsigned long blocked_lock_count;
 
-        /* List of dentry locks to release. Anyone can add locks to
-         * the list, ocfs2_wq processes the list  */
-        struct ocfs2_dentry_lock *dentry_lock_list;
-        struct work_struct dentry_lock_work;
+        /* List of dquot structures to drop last reference to */
+        struct llist_head dquot_drop_list;
+        struct work_struct dquot_drop_work;
 
         wait_queue_head_t               osb_mount_event;
 
@@ -449,6 +446,8 @@ struct ocfs2_super
         /* rb tree root for refcount lock. */
         struct rb_root  osb_rf_lock_tree;
         struct ocfs2_refcount_tree *osb_ref_tree_lru;
+
+        struct mutex system_file_mutex;
 };
 
 #define OCFS2_SB(sb)        ((struct ocfs2_super *)(sb)->s_fs_info)
@@ -579,18 +578,6 @@ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb,
         spin_unlock(&osb->osb_lock);
 }
 
-
-static inline unsigned long  ocfs2_test_osb_flag(struct ocfs2_super *osb,
-                                                 unsigned long flag)
-{
-        unsigned long ret;
-
-        spin_lock(&osb->osb_lock);
-        ret = osb->osb_flags & flag;
-        spin_unlock(&osb->osb_lock);
-        return ret;
-}
-
 static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb,
                                      int hard)
 {
diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index d5ab56cbe5c5..f266d67df3c6 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -28,6 +28,7 @@ struct ocfs2_dquot {
         unsigned int dq_use_count;      /* Number of nodes having reference to this entry in global quota file */
         s64 dq_origspace;       /* Last globally synced space usage */
         s64 dq_originodes;      /* Last globally synced inode usage */
+        struct llist_node list; /* Member of list of dquots to drop */
 };
 
 /* Description of one chunk to recover in memory */
@@ -110,6 +111,7 @@ int ocfs2_read_quota_phys_block(struct inode *inode, u64 p_block,
 int ocfs2_create_local_dquot(struct dquot *dquot);
 int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot);
 int ocfs2_local_write_dquot(struct dquot *dquot);
+void ocfs2_drop_dquot_refs(struct work_struct *work);
 
 extern const struct dquot_operations ocfs2_quota_operations;
 extern struct quota_format_type ocfs2_quota_format;
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index d7b5108789e2..b990a62cff50 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -10,6 +10,7 @@
 #include <linux/jiffies.h>
 #include <linux/writeback.h>
 #include <linux/workqueue.h>
+#include <linux/llist.h>
 
 #include <cluster/masklog.h>
 
@@ -679,6 +680,27 @@ static int ocfs2_calc_qdel_credits(struct super_block *sb, int type)
                OCFS2_INODE_UPDATE_CREDITS;
 }
 
+void ocfs2_drop_dquot_refs(struct work_struct *work)
+{
+        struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
+                                               dquot_drop_work);
+        struct llist_node *list;
+        struct ocfs2_dquot *odquot, *next_odquot;
+
+        list = llist_del_all(&osb->dquot_drop_list);
+        llist_for_each_entry_safe(odquot, next_odquot, list, list) {
+                /* Drop the reference we acquired in ocfs2_dquot_release() */
+                dqput(&odquot->dq_dquot);
+        }
+}
+
+/*
+ * Called when the last reference to dquot is dropped. If we are called from
+ * downconvert thread, we cannot do all the handling here because grabbing
+ * quota lock could deadlock (the node holding the quota lock could need some
+ * other cluster lock to proceed but with blocked downconvert thread we cannot
+ * release any lock).
+ */
 static int ocfs2_release_dquot(struct dquot *dquot)
 {
         handle_t *handle;
@@ -694,6 +716,19 @@ static int ocfs2_release_dquot(struct dquot *dquot)
         /* Check whether we are not racing with some other dqget() */
         if (atomic_read(&dquot->dq_count) > 1)
                 goto out;
+        /* Running from downconvert thread? Postpone quota processing to wq */
+        if (current == osb->dc_task) {
+                /*
+                 * Grab our own reference to dquot and queue it for delayed
+                 * dropping.  Quota code rechecks after calling
+                 * ->release_dquot() and won't free dquot structure.
+                 */
+                dqgrab(dquot);
+                /* First entry on list -> queue work */
+                if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list))
+                        queue_work(ocfs2_wq, &osb->dquot_drop_work);
+                goto out;
+        }
         status = ocfs2_lock_global_qf(oinfo, 1);
         if (status < 0)
                 goto out;
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index ca5ce14cbddc..5c8343fe7438 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -603,11 +603,25 @@ static struct kobj_attribute ocfs2_attr_cluster_stack =
                ocfs2_cluster_stack_show,
                ocfs2_cluster_stack_store);
 
+
+
+static ssize_t ocfs2_dlm_recover_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr,
+                                        char *buf)
+{
+        return snprintf(buf, PAGE_SIZE, "1\n");
+}
+
+static struct kobj_attribute ocfs2_attr_dlm_recover_support =
+        __ATTR(dlm_recover_callback_support, S_IRUGO,
+               ocfs2_dlm_recover_show, NULL);
+
 static struct attribute *ocfs2_attrs[] = {
         &ocfs2_attr_max_locking_protocol.attr,
         &ocfs2_attr_loaded_cluster_plugins.attr,
         &ocfs2_attr_active_cluster_plugin.attr,
         &ocfs2_attr_cluster_stack.attr,
+        &ocfs2_attr_dlm_recover_support.attr,
         NULL,
 };
 
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 47ae2663a6f5..0cb889a17ae1 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -771,6 +771,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
         spin_unlock(&OCFS2_I(alloc_inode)->ip_lock);
         i_size_write(alloc_inode, le64_to_cpu(fe->i_size));
         alloc_inode->i_blocks = ocfs2_inode_sector_count(alloc_inode);
+        ocfs2_update_inode_fsync_trans(handle, alloc_inode, 0);
 
         status = 0;
 
@@ -1607,6 +1608,21 @@ out:
         return ret;
 }
 
+void ocfs2_rollback_alloc_dinode_counts(struct inode *inode,
+                                       struct buffer_head *di_bh,
+                                       u32 num_bits,
+                                       u16 chain)
+{
+        u32 tmp_used;
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
+        struct ocfs2_chain_list *cl;
+
+        cl = (struct ocfs2_chain_list *)&di->id2.i_chain;
+        tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
+        di->id1.bitmap1.i_used = cpu_to_le32(tmp_used - num_bits);
+        le32_add_cpu(&cl->cl_recs[chain].c_free, num_bits);
+}
+
 static int ocfs2_bg_discontig_fix_by_rec(struct ocfs2_suballoc_result *res,
                                          struct ocfs2_extent_rec *rec,
                                          struct ocfs2_chain_list *cl)
@@ -1707,8 +1723,12 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
 
         ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh,
                                          res->sr_bit_offset, res->sr_bits);
-        if (ret < 0)
+        if (ret < 0) {
+                ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh,
+                                               res->sr_bits,
+                                               le16_to_cpu(gd->bg_chain));
                 mlog_errno(ret);
+        }
 
 out_loc_only:
         *bits_left = le16_to_cpu(gd->bg_free_bits_count);
@@ -1838,6 +1858,8 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
                                             res->sr_bit_offset,
                                             res->sr_bits);
         if (status < 0) {
+                ocfs2_rollback_alloc_dinode_counts(alloc_inode,
+                                        ac->ac_bh, res->sr_bits, chain);
                 mlog_errno(status);
                 goto bail;
         }
@@ -2091,7 +2113,7 @@ int ocfs2_find_new_inode_loc(struct inode *dir,
 
         ac->ac_find_loc_priv = res;
         *fe_blkno = res->sr_blkno;
-
+        ocfs2_update_inode_fsync_trans(handle, dir, 0);
 out:
         if (handle)
                 ocfs2_commit_trans(OCFS2_SB(dir->i_sb), handle);
@@ -2149,6 +2171,8 @@ int ocfs2_claim_new_inode_at_loc(handle_t *handle,
                                          res->sr_bit_offset,
                                          res->sr_bits);
         if (ret < 0) {
+                ocfs2_rollback_alloc_dinode_counts(ac->ac_inode,
+                                               ac->ac_bh, res->sr_bits, chain);
                 mlog_errno(ret);
                 goto out;
         }
@@ -2870,6 +2894,7 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
         status = ocfs2_inode_lock(inode_alloc_inode, &alloc_bh, 0);
         if (status < 0) {
                 mutex_unlock(&inode_alloc_inode->i_mutex);
+                iput(inode_alloc_inode);
                 mlog(ML_ERROR, "lock on alloc inode on slot %u failed %d\n",
                      (u32)suballoc_slot, status);
                 goto bail;
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 218d8036b3e7..2d2501767c0c 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -91,6 +91,10 @@ int ocfs2_alloc_dinode_update_counts(struct inode *inode,
                          struct buffer_head *di_bh,
                          u32 num_bits,
                          u16 chain);
+void ocfs2_rollback_alloc_dinode_counts(struct inode *inode,
+                         struct buffer_head *di_bh,
+                         u32 num_bits,
+                         u16 chain);
 int ocfs2_block_group_set_bits(handle_t *handle,
                          struct inode *alloc_inode,
                          struct ocfs2_group_desc *bg,
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 49d84f80f36c..a7cdd56f4c79 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -561,6 +561,9 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb)
         if (!oi)
                 return NULL;
 
+        oi->i_sync_tid = 0;
+        oi->i_datasync_tid = 0;
+
         jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode);
         return &oi->vfs_inode;
 }
@@ -631,6 +634,8 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
         struct ocfs2_super *osb = OCFS2_SB(sb);
         u32 tmp;
 
+        sync_filesystem(sb);
+
         if (!ocfs2_parse_options(sb, data, &parsed_options, 1) ||
             !ocfs2_check_set_options(sb, &parsed_options)) {
                 ret = -EINVAL;
@@ -1238,30 +1243,11 @@ static struct dentry *ocfs2_mount(struct file_system_type *fs_type,
         return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super);
 }
 
-static void ocfs2_kill_sb(struct super_block *sb)
-{
-        struct ocfs2_super *osb = OCFS2_SB(sb);
-
-        /* Failed mount? */
-        if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED)
-                goto out;
-
-        /* Prevent further queueing of inode drop events */
-        spin_lock(&dentry_list_lock);
-        ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
-        spin_unlock(&dentry_list_lock);
-        /* Wait for work to finish and/or remove it */
-        cancel_work_sync(&osb->dentry_lock_work);
-out:
-        kill_block_super(sb);
-}
-
 static struct file_system_type ocfs2_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "ocfs2",
         .mount          = ocfs2_mount,
-        .kill_sb        = ocfs2_kill_sb,
-
+        .kill_sb        = kill_block_super,
         .fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
         .next           = NULL
 };
@@ -1612,14 +1598,9 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
         return 0;
 }
 
-wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
-
 static int __init ocfs2_init(void)
 {
-        int status, i;
-
-        for (i = 0; i < OCFS2_IOEND_WQ_HASH_SZ; i++)
-                init_waitqueue_head(&ocfs2__ioend_wq[i]);
+        int status;
 
         status = init_ocfs2_uptodate_cache();
         if (status < 0)
@@ -1761,7 +1742,7 @@ static void ocfs2_inode_init_once(void *data)
         ocfs2_extent_map_init(&oi->vfs_inode);
         INIT_LIST_HEAD(&oi->ip_io_markers);
         oi->ip_dir_start_lookup = 0;
-        atomic_set(&oi->ip_unaligned_aio, 0);
+        mutex_init(&oi->ip_unaligned_aio);
         init_rwsem(&oi->ip_alloc_sem);
         init_rwsem(&oi->ip_xattr_sem);
         mutex_init(&oi->ip_io_mutex);
@@ -1932,17 +1913,16 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
         debugfs_remove(osb->osb_ctxt);
 
-        /*
-         * Flush inode dropping work queue so that deletes are
-         * performed while the filesystem is still working
-         */
-        ocfs2_drop_all_dl_inodes(osb);
-
         /* Orphan scan should be stopped as early as possible */
         ocfs2_orphan_scan_stop(osb);
 
         ocfs2_disable_quotas(osb);
 
+        /* All dquots should be freed by now */
+        WARN_ON(!llist_empty(&osb->dquot_drop_list));
+        /* Wait for worker to be done with the work structure in osb */
+        cancel_work_sync(&osb->dquot_drop_work);
+
         ocfs2_shutdown_local_alloc(osb);
 
         /* This will disable recovery and flush any recovery work. */
@@ -2077,7 +2057,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
         struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
         struct inode *inode = NULL;
         struct ocfs2_journal *journal;
-        __le32 uuid_net_key;
         struct ocfs2_super *osb;
         u64 total_blocks;
 
@@ -2123,6 +2102,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
         spin_lock_init(&osb->osb_xattr_lock);
         ocfs2_init_steal_slots(osb);
 
+        mutex_init(&osb->system_file_mutex);
+
         atomic_set(&osb->alloc_stats.moves, 0);
         atomic_set(&osb->alloc_stats.local_data, 0);
         atomic_set(&osb->alloc_stats.bitmap_data, 0);
@@ -2276,8 +2257,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
         INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
         journal->j_state = OCFS2_JOURNAL_FREE;
 
-        INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes);
-        osb->dentry_lock_list = NULL;
+        INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
+        init_llist_head(&osb->dquot_drop_list);
 
         /* get some pseudo constants for clustersize bits */
         osb->s_clustersize_bits =
@@ -2311,8 +2292,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
                 goto bail;
         }
 
-        memcpy(&uuid_net_key, di->id2.i_super.s_uuid, sizeof(uuid_net_key));
-
         strncpy(osb->vol_label, di->id2.i_super.s_label, 63);
         osb->vol_label[63] = '\0';
         osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno);
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index f053688d22a3..af155c183123 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -113,9 +113,11 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
         } else
                 arr = get_local_system_inode(osb, type, slot);
 
+        mutex_lock(&osb->system_file_mutex);
         if (arr && ((inode = *arr) != NULL)) {
                 /* get a ref in addition to the array ref */
                 inode = igrab(inode);
+                mutex_unlock(&osb->system_file_mutex);
                 BUG_ON(!inode);
 
                 return inode;
@@ -129,6 +131,7 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
                 *arr = igrab(inode);
                 BUG_ON(!*arr);
         }
+        mutex_unlock(&osb->system_file_mutex);
         return inode;
 }
 
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 185fa3b7f962..016f01df3825 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -369,7 +369,7 @@ static void ocfs2_xattr_bucket_free(struct ocfs2_xattr_bucket *bucket)
  * them fully.
  */
 static int ocfs2_init_xattr_bucket(struct ocfs2_xattr_bucket *bucket,
-                                   u64 xb_blkno)
+                                   u64 xb_blkno, int new)
 {
         int i, rc = 0;
 
@@ -383,9 +383,16 @@ static int ocfs2_init_xattr_bucket(struct ocfs2_xattr_bucket *bucket,
                 }
 
                 if (!ocfs2_buffer_uptodate(INODE_CACHE(bucket->bu_inode),
-                                           bucket->bu_bhs[i]))
-                        ocfs2_set_new_buffer_uptodate(INODE_CACHE(bucket->bu_inode),
-                                                      bucket->bu_bhs[i]);
+                                           bucket->bu_bhs[i])) {
+                        if (new)
+                                ocfs2_set_new_buffer_uptodate(INODE_CACHE(bucket->bu_inode),
+                                                              bucket->bu_bhs[i]);
+                        else {
+                                set_buffer_uptodate(bucket->bu_bhs[i]);
+                                ocfs2_set_buffer_uptodate(INODE_CACHE(bucket->bu_inode),
+                                                          bucket->bu_bhs[i]);
+                        }
+                }
         }
 
         if (rc)
@@ -2602,6 +2609,7 @@ int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh)
         oi->ip_dyn_features &= ~(OCFS2_INLINE_XATTR_FL | OCFS2_HAS_XATTR_FL);
         di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
         spin_unlock(&oi->ip_lock);
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
         ocfs2_journal_dirty(handle, di_bh);
 out_commit:
@@ -3200,8 +3208,15 @@ meta_guess:
                         clusters_add += 1;
                 }
         } else {
-                meta_add += 1;
                 credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS;
+                if (xi->xi_value_len > OCFS2_XATTR_INLINE_SIZE) {
+                        struct ocfs2_extent_list *el = &def_xv.xv.xr_list;
+                        meta_add += ocfs2_extend_meta_needed(el);
+                        credits += ocfs2_calc_extend_credits(inode->i_sb,
+                                                             el);
+                } else {
+                        meta_add += 1;
+                }
         }
 out:
         if (clusters_need)
@@ -3614,6 +3629,7 @@ int ocfs2_xattr_set(struct inode *inode,
         }
 
         ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt);
+        ocfs2_update_inode_fsync_trans(ctxt.handle, inode, 0);
 
         ocfs2_commit_trans(osb, ctxt.handle);
 
@@ -4294,7 +4310,7 @@ static int ocfs2_xattr_create_index_block(struct inode *inode,
 
         trace_ocfs2_xattr_create_index_block((unsigned long long)blkno);
 
-        ret = ocfs2_init_xattr_bucket(xs->bucket, blkno);
+        ret = ocfs2_init_xattr_bucket(xs->bucket, blkno, 1);
         if (ret) {
                 mlog_errno(ret);
                 goto out;
@@ -4638,7 +4654,7 @@ static int ocfs2_divide_xattr_bucket(struct inode *inode,
          * Even if !new_bucket_head, we're overwriting t_bucket.  Thus,
          * there's no need to read it.
          */
-        ret = ocfs2_init_xattr_bucket(t_bucket, new_blk);
+        ret = ocfs2_init_xattr_bucket(t_bucket, new_blk, new_bucket_head);
         if (ret) {
                 mlog_errno(ret);
                 goto out;
@@ -4804,7 +4820,7 @@ static int ocfs2_cp_xattr_bucket(struct inode *inode,
          * Even if !t_is_new, we're overwriting t_bucket.  Thus,
          * there's no need to read it.
          */
-        ret = ocfs2_init_xattr_bucket(t_bucket, t_blkno);
+        ret = ocfs2_init_xattr_bucket(t_bucket, t_blkno, t_is_new);
         if (ret)
                 goto out;
 
@@ -5476,6 +5492,7 @@ static int ocfs2_rm_xattr_cluster(struct inode *inode,
         ret = ocfs2_truncate_log_append(osb, handle, blkno, len);
         if (ret)
                 mlog_errno(ret);
+        ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
 out_commit:
         ocfs2_commit_trans(osb, handle);
@@ -6830,7 +6847,7 @@ static int ocfs2_reflink_xattr_bucket(handle_t *handle,
                         break;
                 }
 
-                ret = ocfs2_init_xattr_bucket(args->new_bucket, new_blkno);
+                ret = ocfs2_init_xattr_bucket(args->new_bucket, new_blkno, 1);
                 if (ret) {
                         mlog_errno(ret);
                         break;
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index d8b0afde2179..ec58c7659183 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -183,7 +183,7 @@ int omfs_sync_inode(struct inode *inode)
  */
 static void omfs_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
 
         if (inode->i_nlink)
diff --git a/fs/open.c b/fs/open.c
index b9ed8b25c108..631aea815def 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -231,7 +231,13 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
                 return -EINVAL;
 
         /* Return error if mode is not supported */
-        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+                     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
+                return -EOPNOTSUPP;
+
+        /* Punch hole and zero range are mutually exclusive */
+        if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
+            (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
                 return -EOPNOTSUPP;
 
         /* Punch hole must have keep size set */
@@ -239,11 +245,20 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
             !(mode & FALLOC_FL_KEEP_SIZE))
                 return -EOPNOTSUPP;
 
+        /* Collapse range should only be used exclusively. */
+        if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
+            (mode & ~FALLOC_FL_COLLAPSE_RANGE))
+                return -EINVAL;
+
         if (!(file->f_mode & FMODE_WRITE))
                 return -EBADF;
 
-        /* It's not possible punch hole on append only file */
-        if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode))
+        /*
+         * It's not possible to punch hole or perform collapse range
+         * on append only file
+         */
+        if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE)
+            && IS_APPEND(inode))
                 return -EPERM;
 
         if (IS_IMMUTABLE(inode))
@@ -271,6 +286,14 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
         if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
                 return -EFBIG;
 
+        /*
+         * There is no need to overlap collapse range with EOF, in which case
+         * it is effectively a truncate operation
+         */
+        if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
+            (offset + len >= i_size_read(inode)))
+                return -EINVAL;
+
         if (!file->f_op->fallocate)
                 return -EOPNOTSUPP;
 
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 8c0ceb8dd1f7..15e4500cda3e 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -368,6 +368,7 @@ static struct inode *openprom_iget(struct super_block *sb, ino_t ino)
 
 static int openprom_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_NOATIME;
         return 0;
 }
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 11c54fd51e16..9e363e41dacc 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -723,7 +723,7 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
                    void *buffer, size_t size)
 {
         posix_acl_xattr_header *ext_acl = (posix_acl_xattr_header *)buffer;
-        posix_acl_xattr_entry *ext_entry = ext_acl->a_entries;
+        posix_acl_xattr_entry *ext_entry;
         int real_size, n;
 
         real_size = posix_acl_xattr_size(acl->a_count);
@@ -731,7 +731,8 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
                 return real_size;
         if (real_size > size)
                 return -ERANGE;
-        
+
+        ext_entry = ext_acl->a_entries;
         ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
 
         for (n=0; n < acl->a_count; n++, ext_entry++) {
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index ab30716584f5..239493ec718e 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -27,6 +27,5 @@ proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
 proc-$(CONFIG_NET)              += proc_net.o
 proc-$(CONFIG_PROC_KCORE)       += kcore.o
 proc-$(CONFIG_PROC_VMCORE)      += vmcore.o
-proc-$(CONFIG_PROC_DEVICETREE)  += proc_devtree.o
 proc-$(CONFIG_PRINTK)   += kmsg.o
 proc-$(CONFIG_PROC_PAGE_MONITOR)        += page.o
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 124fc43c7090..8f20e3404fd2 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -35,7 +35,7 @@ static void proc_evict_inode(struct inode *inode)
         const struct proc_ns_operations *ns_ops;
         void *ns;
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
 
         /* Stop tracking associated processes */
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 651d09a11dde..3ab6d14e71c5 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -211,13 +211,6 @@ extern int proc_fill_super(struct super_block *);
 extern void proc_entry_rundown(struct proc_dir_entry *);
 
 /*
- * proc_devtree.c
- */
-#ifdef CONFIG_PROC_DEVICETREE
-extern void proc_device_tree_init(void);
-#endif
-
-/*
  * proc_namespaces.c
  */
 extern const struct inode_operations proc_ns_dir_inode_operations;
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
deleted file mode 100644
index c82dd5147845..000000000000
--- a/fs/proc/proc_devtree.c
+++ /dev/null
@@ -1,241 +0,0 @@
-/*
- * proc_devtree.c - handles /proc/device-tree
- *
- * Copyright 1997 Paul Mackerras
- */
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/time.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/printk.h>
-#include <linux/stat.h>
-#include <linux/string.h>
-#include <linux/of.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <asm/uaccess.h>
-#include "internal.h"
-
-static inline void set_node_proc_entry(struct device_node *np,
-                                       struct proc_dir_entry *de)
-{
-        np->pde = de;
-}
-
-static struct proc_dir_entry *proc_device_tree;
-
-/*
- * Supply data on a read from /proc/device-tree/node/property.
- */
-static int property_proc_show(struct seq_file *m, void *v)
-{
-        struct property *pp = m->private;
-
-        seq_write(m, pp->value, pp->length);
-        return 0;
-}
-
-static int property_proc_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, property_proc_show, __PDE_DATA(inode));
-}
-
-static const struct file_operations property_proc_fops = {
-        .owner          = THIS_MODULE,
-        .open           = property_proc_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-
-/*
- * For a node with a name like "gc@10", we make symlinks called "gc"
- * and "@10" to it.
- */
-
-/*
- * Add a property to a node
- */
-static struct proc_dir_entry *
-__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp,
-                const char *name)
-{
-        struct proc_dir_entry *ent;
-
-        /*
-         * Unfortunately proc_register puts each new entry
-         * at the beginning of the list.  So we rearrange them.
-         */
-        ent = proc_create_data(name,
-                               strncmp(name, "security-", 9) ? S_IRUGO : S_IRUSR,
-                               de, &property_proc_fops, pp);
-        if (ent == NULL)
-                return NULL;
-
-        if (!strncmp(name, "security-", 9))
-                proc_set_size(ent, 0); /* don't leak number of password chars */
-        else
-                proc_set_size(ent, pp->length);
-
-        return ent;
-}
-
-
-void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop)
-{
-        __proc_device_tree_add_prop(pde, prop, prop->name);
-}
-
-void proc_device_tree_remove_prop(struct proc_dir_entry *pde,
-                                  struct property *prop)
-{
-        remove_proc_entry(prop->name, pde);
-}
-
-void proc_device_tree_update_prop(struct proc_dir_entry *pde,
-                                  struct property *newprop,
-                                  struct property *oldprop)
-{
-        struct proc_dir_entry *ent;
-
-        if (!oldprop) {
-                proc_device_tree_add_prop(pde, newprop);
-                return;
-        }
-
-        for (ent = pde->subdir; ent != NULL; ent = ent->next)
-                if (ent->data == oldprop)
-                        break;
-        if (ent == NULL) {
-                pr_warn("device-tree: property \"%s\" does not exist\n",
-                        oldprop->name);
-        } else {
-                ent->data = newprop;
-                ent->size = newprop->length;
-        }
-}
-
-/*
- * Various dodgy firmware might give us nodes and/or properties with
- * conflicting names. That's generally ok, except for exporting via /proc,
- * so munge names here to ensure they're unique.
- */
-
-static int duplicate_name(struct proc_dir_entry *de, const char *name)
-{
-        struct proc_dir_entry *ent;
-        int found = 0;
-
-        spin_lock(&proc_subdir_lock);
-
-        for (ent = de->subdir; ent != NULL; ent = ent->next) {
-                if (strcmp(ent->name, name) == 0) {
-                        found = 1;
-                        break;
-                }
-        }
-
-        spin_unlock(&proc_subdir_lock);
-
-        return found;
-}
-
-static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de,
-                const char *name)
-{
-        char *fixed_name;
-        int fixup_len = strlen(name) + 2 + 1; /* name + #x + \0 */
-        int i = 1, size;
-
-realloc:
-        fixed_name = kmalloc(fixup_len, GFP_KERNEL);
-        if (fixed_name == NULL) {
-                pr_err("device-tree: Out of memory trying to fixup "
-                       "name \"%s\"\n", name);
-                return name;
-        }
-
-retry:
-        size = snprintf(fixed_name, fixup_len, "%s#%d", name, i);
-        size++; /* account for NULL */
-
-        if (size > fixup_len) {
-                /* We ran out of space, free and reallocate. */
-                kfree(fixed_name);
-                fixup_len = size;
-                goto realloc;
-        }
-
-        if (duplicate_name(de, fixed_name)) {
-                /* Multiple duplicates. Retry with a different offset. */
-                i++;
-                goto retry;
-        }
-
-        pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
-                np->full_name, fixed_name);
-
-        return fixed_name;
-}
-
-/*
- * Process a node, adding entries for its children and its properties.
- */
-void proc_device_tree_add_node(struct device_node *np,
-                               struct proc_dir_entry *de)
-{
-        struct property *pp;
-        struct proc_dir_entry *ent;
-        struct device_node *child;
-        const char *p;
-
-        set_node_proc_entry(np, de);
-        for (child = NULL; (child = of_get_next_child(np, child));) {
-                /* Use everything after the last slash, or the full name */
-                p = kbasename(child->full_name);
-
-                if (duplicate_name(de, p))
-                        p = fixup_name(np, de, p);
-
-                ent = proc_mkdir(p, de);
-                if (ent == NULL)
-                        break;
-                proc_device_tree_add_node(child, ent);
-        }
-        of_node_put(child);
-
-        for (pp = np->properties; pp != NULL; pp = pp->next) {
-                p = pp->name;
-
-                if (strchr(p, '/'))
-                        continue;
-
-                if (duplicate_name(de, p))
-                        p = fixup_name(np, de, p);
-
-                ent = __proc_device_tree_add_prop(de, pp, p);
-                if (ent == NULL)
-                        break;
-        }
-}
-
-/*
- * Called on initialization to set up the /proc/device-tree subtree
- */
-void __init proc_device_tree_init(void)
-{
-        struct device_node *root;
-
-        proc_device_tree = proc_mkdir("device-tree", NULL);
-        if (proc_device_tree == NULL)
-                return;
-        root = of_find_node_by_path("/");
-        if (root == NULL) {
-                remove_proc_entry("device-tree", NULL);
-                pr_debug("/proc/device-tree: can't find root\n");
-                return;
-        }
-        proc_device_tree_add_node(root, proc_device_tree);
-        of_node_put(root);
-}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 87dbcbef7fe4..5dbadecb234d 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -92,6 +92,8 @@ static int proc_parse_options(char *options, struct pid_namespace *pid)
 int proc_remount(struct super_block *sb, int *flags, char *data)
 {
         struct pid_namespace *pid = sb->s_fs_info;
+
+        sync_filesystem(sb);
         return !proc_parse_options(data, pid);
 }
 
@@ -183,9 +185,6 @@ void __init proc_root_init(void)
         proc_mkdir("openprom", NULL);
 #endif
         proc_tty_init();
-#ifdef CONFIG_PROC_DEVICETREE
-        proc_device_tree_init();
-#endif
         proc_mkdir("bus", NULL);
         proc_sys_init();
 }
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 6f599c62f0cc..9d231e9e5f0e 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/irqnr.h>
-#include <asm/cputime.h>
+#include <linux/cputime.h>
 #include <linux/tick.h>
 
 #ifndef arch_irq_stat_cpu
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 7141b8d0ca9e..33de567c25af 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -5,7 +5,7 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 #include <linux/kernel_stat.h>
-#include <asm/cputime.h>
+#include <linux/cputime.h>
 
 static int uptime_proc_show(struct seq_file *m, void *v)
 {
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 12823845d324..192297b0090d 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -249,6 +249,7 @@ static void parse_options(char *options)
 
 static int pstore_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         parse_options(data);
 
         return 0;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 78c3c2097787..46d269e38706 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -497,6 +497,7 @@ void pstore_get_records(int quiet)
                                                         big_oops_buf_sz);
 
                         if (unzipped_len > 0) {
+                                kfree(buf);
                                 buf = big_oops_buf;
                                 size = unzipped_len;
                                 compressed = false;
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index fa8cef2cca3a..3b5744306ed8 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -86,6 +86,7 @@ struct ramoops_context {
         struct persistent_ram_ecc_info ecc_info;
         unsigned int max_dump_cnt;
         unsigned int dump_write_cnt;
+        /* _read_cnt need clear on ramoops_pstore_open */
         unsigned int dump_read_cnt;
         unsigned int console_read_cnt;
         unsigned int ftrace_read_cnt;
@@ -101,6 +102,7 @@ static int ramoops_pstore_open(struct pstore_info *psi)
 
         cxt->dump_read_cnt = 0;
         cxt->console_read_cnt = 0;
+        cxt->ftrace_read_cnt = 0;
         return 0;
 }
 
@@ -117,13 +119,15 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max,
                 return NULL;
 
         prz = przs[i];
+        if (!prz)
+                return NULL;
 
-        if (update) {
-                /* Update old/shadowed buffer. */
+        /* Update old/shadowed buffer. */
+        if (update)
                 persistent_ram_save_old(prz);
-                if (!persistent_ram_old_size(prz))
-                        return NULL;
-        }
+
+        if (!persistent_ram_old_size(prz))
+                return NULL;
 
         *typep = type;
         *id = i;
@@ -316,6 +320,7 @@ static void ramoops_free_przs(struct ramoops_context *cxt)
 {
         int i;
 
+        cxt->max_dump_cnt = 0;
         if (!cxt->przs)
                 return;
 
@@ -346,7 +351,7 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
                              GFP_KERNEL);
         if (!cxt->przs) {
                 dev_err(dev, "failed to initialize a prz array for dumps\n");
-                return -ENOMEM;
+                goto fail_prz;
         }
 
         for (i = 0; i < cxt->max_dump_cnt; i++) {
@@ -428,7 +433,6 @@ static int ramoops_probe(struct platform_device *pdev)
         if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size))
                 pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size);
 
-        cxt->dump_read_cnt = 0;
         cxt->size = pdata->mem_size;
         cxt->phys_addr = pdata->mem_address;
         cxt->record_size = pdata->record_size;
@@ -505,7 +509,6 @@ fail_buf:
         kfree(cxt->pstore.buf);
 fail_clear:
         cxt->pstore.bufsize = 0;
-        cxt->max_dump_cnt = 0;
 fail_cnt:
         kfree(cxt->fprz);
 fail_init_fprz:
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index de272d426763..ff7e3d4df5a1 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -54,7 +54,7 @@ static size_t buffer_start_add_atomic(struct persistent_ram_zone *prz, size_t a)
         do {
                 old = atomic_read(&prz->buffer->start);
                 new = old + a;
-                while (unlikely(new > prz->buffer_size))
+                while (unlikely(new >= prz->buffer_size))
                         new -= prz->buffer_size;
         } while (atomic_cmpxchg(&prz->buffer->start, old, new) != old);
 
@@ -91,7 +91,7 @@ static size_t buffer_start_add_locked(struct persistent_ram_zone *prz, size_t a)
 
         old = atomic_read(&prz->buffer->start);
         new = old + a;
-        while (unlikely(new > prz->buffer_size))
+        while (unlikely(new >= prz->buffer_size))
                 new -= prz->buffer_size;
         atomic_set(&prz->buffer->start, new);
 
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 89558810381c..c4bcb778886e 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -44,6 +44,7 @@ static int qnx4_remount(struct super_block *sb, int *flags, char *data)
 {
         struct qnx4_sb_info *qs;
 
+        sync_filesystem(sb);
         qs = qnx4_sb(sb);
         qs->Version = QNX4_VERSION;
         *flags |= MS_RDONLY;
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 8d941edfefa1..65cdaab3ed49 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -55,6 +55,7 @@ static int qnx6_show_options(struct seq_file *seq, struct dentry *root)
 
 static int qnx6_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_RDONLY;
         return 0;
 }
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index cfc8dcc16043..9cd5f63715c0 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -528,7 +528,7 @@ restart:
                 if (atomic_read(&dquot->dq_count)) {
                         DEFINE_WAIT(wait);
 
-                        atomic_inc(&dquot->dq_count);
+                        dqgrab(dquot);
                         prepare_to_wait(&dquot->dq_wait_unused, &wait,
                                         TASK_UNINTERRUPTIBLE);
                         spin_unlock(&dq_list_lock);
@@ -632,7 +632,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
                         /* Now we have active dquot from which someone is
                          * holding reference so we can safely just increase
                          * use count */
-                        atomic_inc(&dquot->dq_count);
+                        dqgrab(dquot);
                         spin_unlock(&dq_list_lock);
                         dqstats_inc(DQST_LOOKUPS);
                         err = sb->dq_op->write_dquot(dquot);
diff --git a/fs/read_write.c b/fs/read_write.c
index 28cc9c810744..31c6efa43183 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -994,9 +994,9 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
         return ret;
 }
 
-COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
-                const struct compat_iovec __user *,vec,
-                unsigned long, vlen, loff_t, pos)
+static long __compat_sys_preadv64(unsigned long fd,
+                                  const struct compat_iovec __user *vec,
+                                  unsigned long vlen, loff_t pos)
 {
         struct fd f;
         ssize_t ret;
@@ -1013,12 +1013,22 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
         return ret;
 }
 
+#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
+COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
+                const struct compat_iovec __user *,vec,
+                unsigned long, vlen, loff_t, pos)
+{
+        return __compat_sys_preadv64(fd, vec, vlen, pos);
+}
+#endif
+
 COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
                 const struct compat_iovec __user *,vec,
                 compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
         loff_t pos = ((loff_t)pos_high << 32) | pos_low;
-        return compat_sys_preadv64(fd, vec, vlen, pos);
+
+        return __compat_sys_preadv64(fd, vec, vlen, pos);
 }
 
 static size_t compat_writev(struct file *file,
@@ -1061,9 +1071,9 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
         return ret;
 }
 
-COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
-                const struct compat_iovec __user *,vec,
-                unsigned long, vlen, loff_t, pos)
+static long __compat_sys_pwritev64(unsigned long fd,
+                                   const struct compat_iovec __user *vec,
+                                   unsigned long vlen, loff_t pos)
 {
         struct fd f;
         ssize_t ret;
@@ -1080,12 +1090,22 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
         return ret;
 }
 
+#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
+COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
+                const struct compat_iovec __user *,vec,
+                unsigned long, vlen, loff_t, pos)
+{
+        return __compat_sys_pwritev64(fd, vec, vlen, pos);
+}
+#endif
+
 COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
                 const struct compat_iovec __user *,vec,
                 compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
         loff_t pos = ((loff_t)pos_high << 32) | pos_low;
-        return compat_sys_pwritev64(fd, vec, vlen, pos);
+
+        return __compat_sys_pwritev64(fd, vec, vlen, pos);
 }
 #endif
 
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ad62bdbb451e..bc8b8009897d 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -35,7 +35,7 @@ void reiserfs_evict_inode(struct inode *inode)
         if (!inode->i_nlink && !is_bad_inode(inode))
                 dquot_initialize(inode);
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         if (inode->i_nlink)
                 goto no_delete;
 
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 8d06adf89948..83d4eac8059a 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -2831,6 +2831,7 @@ void reiserfs_init_alloc_options(struct super_block *s);
  */
 __le32 reiserfs_choose_packing(struct inode *dir);
 
+void show_alloc_options(struct seq_file *seq, struct super_block *s);
 int reiserfs_init_bitmap_cache(struct super_block *sb);
 void reiserfs_free_bitmap_cache(struct super_block *sb);
 void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 2c803353f8ac..9fb20426005e 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -62,7 +62,6 @@ static int is_any_reiserfs_magic_string(struct reiserfs_super_block *rs)
 
 static int reiserfs_remount(struct super_block *s, int *flags, char *data);
 static int reiserfs_statfs(struct dentry *dentry, struct kstatfs *buf);
-void show_alloc_options(struct seq_file *seq, struct super_block *s);
 
 static int reiserfs_sync_fs(struct super_block *s, int wait)
 {
@@ -597,7 +596,7 @@ static void init_once(void *foo)
         inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
         reiserfs_inode_cachep = kmem_cache_create("reiser_inode_cache",
                                                   sizeof(struct
@@ -1319,6 +1318,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
         int i;
 #endif
 
+        sync_filesystem(s);
         reiserfs_write_lock(s);
 
 #ifdef CONFIG_QUOTA
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index d8418782862b..ef90e8bca95a 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -432,6 +432,7 @@ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
  */
 static int romfs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_RDONLY;
         return 0;
 }
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 202df6312d4e..031c8d67fd51 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -371,6 +371,7 @@ static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static int squashfs_remount(struct super_block *sb, int *flags, char *data)
 {
+        sync_filesystem(sb);
         *flags |= MS_RDONLY;
         return 0;
 }
diff --git a/fs/super.c b/fs/super.c
index 80d5cf2ca765..e9dc3c3fe159 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -719,8 +719,6 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
                 }
         }
 
-        sync_filesystem(sb);
-
         if (sb->s_op->remount_fs) {
                 retval = sb->s_op->remount_fs(sb, &flags, data);
                 if (retval) {
diff --git a/fs/sysfs/Kconfig b/fs/sysfs/Kconfig
index 8c41feacbac5..b2756014508c 100644
--- a/fs/sysfs/Kconfig
+++ b/fs/sysfs/Kconfig
@@ -1,6 +1,7 @@
 config SYSFS
         bool "sysfs file system support" if EXPERT
         default y
+        select KERNFS
         help
         The sysfs filesystem is a virtual filesystem that the kernel uses to
         export internal kernel objects, their attributes, and their
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index ee0d761c3179..0b45ff42f374 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -19,39 +19,18 @@
 
 DEFINE_SPINLOCK(sysfs_symlink_target_lock);
 
-/**
- *      sysfs_pathname - return full path to sysfs dirent
- *      @kn: kernfs_node whose path we want
- *      @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.
- */
-static char *sysfs_pathname(struct kernfs_node *kn, char *path)
-{
-        if (kn->parent) {
-                sysfs_pathname(kn->parent, path);
-                strlcat(path, "/", PATH_MAX);
-        }
-        strlcat(path, kn->name, PATH_MAX);
-        return path;
-}
-
 void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
 {
-        char *path;
+        char *buf, *path = NULL;
 
-        path = kzalloc(PATH_MAX, GFP_KERNEL);
-        if (path) {
-                sysfs_pathname(parent, path);
-                strlcat(path, "/", PATH_MAX);
-                strlcat(path, name, PATH_MAX);
-        }
+        buf = kzalloc(PATH_MAX, GFP_KERNEL);
+        if (buf)
+                path = kernfs_path(parent, buf, PATH_MAX);
 
-        WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s'\n",
-             path ? path : name);
+        WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s/%s'\n",
+             path, name);
 
-        kfree(path);
+        kfree(buf);
 }
 
 /**
@@ -122,9 +101,13 @@ void sysfs_remove_dir(struct kobject *kobj)
 int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
                         const void *new_ns)
 {
-        struct kernfs_node *parent = kobj->sd->parent;
+        struct kernfs_node *parent;
+        int ret;
 
-        return kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
+        parent = kernfs_get_parent(kobj->sd);
+        ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
+        kernfs_put(parent);
+        return ret;
 }
 
 int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
@@ -133,7 +116,6 @@ int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
         struct kernfs_node *kn = kobj->sd;
         struct kernfs_node *new_parent;
 
-        BUG_ON(!kn->parent);
         new_parent = new_parent_kobj && new_parent_kobj->sd ?
                 new_parent_kobj->sd : sysfs_root_kn;
 
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 810cf6e613e5..1b8b91b67fdb 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -372,6 +372,29 @@ void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
 
+/**
+ * sysfs_remove_file_self - remove an object attribute from its own method
+ * @kobj: object we're acting for
+ * @attr: attribute descriptor
+ *
+ * See kernfs_remove_self() for details.
+ */
+bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr)
+{
+        struct kernfs_node *parent = kobj->sd;
+        struct kernfs_node *kn;
+        bool ret;
+
+        kn = kernfs_find_and_get(parent, attr->name);
+        if (WARN_ON_ONCE(!kn))
+                return false;
+
+        ret = kernfs_remove_self(kn);
+
+        kernfs_put(kn);
+        return ret;
+}
+
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
 {
         int i;
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 6b579387c67a..aa0406895b53 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -70,8 +70,11 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
         if (grp->bin_attrs) {
                 for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) {
                         if (update)
-                                sysfs_remove_bin_file(kobj, *bin_attr);
-                        error = sysfs_create_bin_file(kobj, *bin_attr);
+                                kernfs_remove_by_name(parent,
+                                                (*bin_attr)->attr.name);
+                        error = sysfs_add_file_mode_ns(parent,
+                                        &(*bin_attr)->attr, true,
+                                        (*bin_attr)->attr.mode, NULL);
                         if (error)
                                 break;
                 }
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 3eaf5c6622eb..a66ad6196f59 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -63,7 +63,7 @@ int __init sysfs_init(void)
 {
         int err;
 
-        sysfs_root = kernfs_create_root(NULL, NULL);
+        sysfs_root = kernfs_create_root(NULL, 0, NULL);
         if (IS_ERR(sysfs_root))
                 return PTR_ERR(sysfs_root);
 
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index c327d4ee1235..88956309cc86 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -60,6 +60,7 @@ static int sysv_remount(struct super_block *sb, int *flags, char *data)
 {
         struct sysv_sb_info *sbi = SYSV_SB(sb);
 
+        sync_filesystem(sb);
         if (sbi->s_forced_ro)
                 *flags |= MS_RDONLY;
         return 0;
@@ -295,7 +296,7 @@ int sysv_sync_inode(struct inode *inode)
 
 static void sysv_evict_inode(struct inode *inode)
 {
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         if (!inode->i_nlink) {
                 inode->i_size = 0;
                 sysv_truncate(inode);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 929312180dd0..0013142c0475 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -317,6 +317,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
             (clockid != CLOCK_MONOTONIC &&
              clockid != CLOCK_REALTIME &&
              clockid != CLOCK_REALTIME_ALARM &&
+             clockid != CLOCK_BOOTTIME &&
              clockid != CLOCK_BOOTTIME_ALARM))
                 return -EINVAL;
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 5ded8490c0c6..a1266089eca1 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -351,7 +351,7 @@ static void ubifs_evict_inode(struct inode *inode)
         dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
         ubifs_assert(!atomic_read(&inode->i_count));
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         if (inode->i_nlink)
                 goto done;
@@ -1827,6 +1827,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
         int err;
         struct ubifs_info *c = sb->s_fs_info;
 
+        sync_filesystem(sb);
         dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, *flags);
 
         err = ubifs_parse_options(c, data, 1);
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 982ce05c87ed..5d643706212f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -146,8 +146,8 @@ void udf_evict_inode(struct inode *inode)
                 want_delete = 1;
                 udf_setsize(inode, 0);
                 udf_update_inode(inode, IS_SYNC(inode));
-        } else
-                truncate_inode_pages(&inode->i_data, 0);
+        }
+        truncate_inode_pages_final(&inode->i_data);
         invalidate_inode_buffers(inode);
         clear_inode(inode);
         if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB &&
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 3306b9f69bed..64f2b7334d08 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -646,6 +646,7 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
         int error = 0;
         struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb);
 
+        sync_filesystem(sb);
         if (lvidiu) {
                 int write_rev = le16_to_cpu(lvidiu->minUDFWriteRev);
                 if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY))
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index c8ca96086784..61e8a9b021dd 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -885,7 +885,7 @@ void ufs_evict_inode(struct inode * inode)
         if (!inode->i_nlink && !is_bad_inode(inode))
                 want_delete = 1;
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         if (want_delete) {
                 loff_t old_i_size;
                 /*UFS_I(inode)->i_dtime = CURRENT_TIME;*/
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 329f2f53b7ed..b8c6791f046f 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1280,6 +1280,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
         unsigned new_mount_opt, ufstype;
         unsigned flags;
 
+        sync_filesystem(sb);
         lock_ufs(sb);
         mutex_lock(&UFS_SB(sb)->s_lock);
         uspi = UFS_SB(sb)->s_uspi;
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 66a36befc5c0..844e288b9576 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -65,12 +65,31 @@ kmem_alloc(size_t size, xfs_km_flags_t flags)
 void *
 kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 {
+        unsigned noio_flag = 0;
         void    *ptr;
+        gfp_t   lflags;
 
         ptr = kmem_zalloc(size, flags | KM_MAYFAIL);
         if (ptr)
                 return ptr;
-        return vzalloc(size);
+
+        /*
+         * __vmalloc() will allocate data pages and auxillary structures (e.g.
+         * pagetables) with GFP_KERNEL, yet we may be under GFP_NOFS context
+         * here. Hence we need to tell memory reclaim that we are in such a
+         * context via PF_MEMALLOC_NOIO to prevent memory reclaim re-entering
+         * the filesystem here and potentially deadlocking.
+         */
+        if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+                noio_flag = memalloc_noio_save();
+
+        lflags = kmem_flags_convert(flags);
+        ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
+
+        if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+                memalloc_noio_restore(noio_flag);
+
+        return ptr;
 }
 
 void
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 0ecec1896f25..6888ad886ff6 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -281,7 +281,7 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
         if (!acl)
                 goto set_acl;
 
-        error = -EINVAL;
+        error = -E2BIG;
         if (acl->a_count > XFS_ACL_MAX_ENTRIES(XFS_M(inode->i_sb)))
                 return error;
 
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 3fc109819c34..0fdd4109c624 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -89,6 +89,8 @@ typedef struct xfs_agf {
         /* structure must be padded to 64 bit alignment */
 } xfs_agf_t;
 
+#define XFS_AGF_CRC_OFF         offsetof(struct xfs_agf, agf_crc)
+
 #define XFS_AGF_MAGICNUM        0x00000001
 #define XFS_AGF_VERSIONNUM      0x00000002
 #define XFS_AGF_SEQNO           0x00000004
@@ -167,6 +169,8 @@ typedef struct xfs_agi {
         /* structure must be padded to 64 bit alignment */
 } xfs_agi_t;
 
+#define XFS_AGI_CRC_OFF         offsetof(struct xfs_agi, agi_crc)
+
 #define XFS_AGI_MAGICNUM        0x00000001
 #define XFS_AGI_VERSIONNUM      0x00000002
 #define XFS_AGI_SEQNO           0x00000004
@@ -222,6 +226,8 @@ typedef struct xfs_agfl {
         __be32          agfl_bno[];     /* actually XFS_AGFL_SIZE(mp) */
 } xfs_agfl_t;
 
+#define XFS_AGFL_CRC_OFF        offsetof(struct xfs_agfl, agfl_crc)
+
 /*
  * tags for inode radix tree
  */
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 9eab2dfdcbb5..c1cf6a336a72 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -474,7 +474,6 @@ xfs_agfl_read_verify(
         struct xfs_buf  *bp)
 {
         struct xfs_mount *mp = bp->b_target->bt_mount;
-        int             agfl_ok = 1;
 
         /*
          * There is no verification of non-crc AGFLs because mkfs does not
@@ -485,15 +484,13 @@ xfs_agfl_read_verify(
         if (!xfs_sb_version_hascrc(&mp->m_sb))
                 return;
 
-        agfl_ok = xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                   offsetof(struct xfs_agfl, agfl_crc));
-
-        agfl_ok = agfl_ok && xfs_agfl_verify(bp);
-
-        if (!agfl_ok) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (!xfs_buf_verify_cksum(bp, XFS_AGFL_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_agfl_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -508,16 +505,15 @@ xfs_agfl_write_verify(
                 return;
 
         if (!xfs_agfl_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
         if (bip)
                 XFS_BUF_TO_AGFL(bp)->agfl_lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-                         offsetof(struct xfs_agfl, agfl_crc));
+        xfs_buf_update_cksum(bp, XFS_AGFL_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_agfl_buf_ops = {
@@ -2238,19 +2234,17 @@ xfs_agf_read_verify(
         struct xfs_buf  *bp)
 {
         struct xfs_mount *mp = bp->b_target->bt_mount;
-        int             agf_ok = 1;
-
-        if (xfs_sb_version_hascrc(&mp->m_sb))
-                agf_ok = xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                          offsetof(struct xfs_agf, agf_crc));
 
-        agf_ok = agf_ok && xfs_agf_verify(mp, bp);
-
-        if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
-                        XFS_RANDOM_ALLOC_READ_AGF))) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (xfs_sb_version_hascrc(&mp->m_sb) &&
+            !xfs_buf_verify_cksum(bp, XFS_AGF_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (XFS_TEST_ERROR(!xfs_agf_verify(mp, bp), mp,
+                                XFS_ERRTAG_ALLOC_READ_AGF,
+                                XFS_RANDOM_ALLOC_READ_AGF))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -2261,8 +2255,8 @@ xfs_agf_write_verify(
         struct xfs_buf_log_item *bip = bp->b_fspriv;
 
         if (!xfs_agf_verify(mp, bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -2272,8 +2266,7 @@ xfs_agf_write_verify(
         if (bip)
                 XFS_BUF_TO_AGF(bp)->agf_lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-                         offsetof(struct xfs_agf, agf_crc));
+        xfs_buf_update_cksum(bp, XFS_AGF_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_agf_buf_ops = {
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index 13085429e523..cc1eadcbb049 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -355,12 +355,14 @@ static void
 xfs_allocbt_read_verify(
         struct xfs_buf  *bp)
 {
-        if (!(xfs_btree_sblock_verify_crc(bp) &&
-              xfs_allocbt_verify(bp))) {
-                trace_xfs_btree_corrupt(bp, _RET_IP_);
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                     bp->b_target->bt_mount, bp->b_addr);
+        if (!xfs_btree_sblock_verify_crc(bp))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_allocbt_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+        if (bp->b_error) {
+                trace_xfs_btree_corrupt(bp, _RET_IP_);
+                xfs_verifier_error(bp);
         }
 }
 
@@ -370,9 +372,9 @@ xfs_allocbt_write_verify(
 {
         if (!xfs_allocbt_verify(bp)) {
                 trace_xfs_btree_corrupt(bp, _RET_IP_);
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                     bp->b_target->bt_mount, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
+                return;
         }
         xfs_btree_sblock_calc_crc(bp);
 
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index db2cfb067d0b..75df77d09f75 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -632,38 +632,46 @@ xfs_map_at_offset(
 }
 
 /*
- * Test if a given page is suitable for writing as part of an unwritten
- * or delayed allocate extent.
+ * Test if a given page contains at least one buffer of a given @type.
+ * If @check_all_buffers is true, then we walk all the buffers in the page to
+ * try to find one of the type passed in. If it is not set, then the caller only
+ * needs to check the first buffer on the page for a match.
  */
-STATIC int
+STATIC bool
 xfs_check_page_type(
         struct page             *page,
-        unsigned int            type)
+        unsigned int            type,
+        bool                    check_all_buffers)
 {
-        if (PageWriteback(page))
-                return 0;
+        struct buffer_head      *bh;
+        struct buffer_head      *head;
 
-        if (page->mapping && page_has_buffers(page)) {
-                struct buffer_head      *bh, *head;
-                int                     acceptable = 0;
+        if (PageWriteback(page))
+                return false;
+        if (!page->mapping)
+                return false;
+        if (!page_has_buffers(page))
+                return false;
 
-                bh = head = page_buffers(page);
-                do {
-                        if (buffer_unwritten(bh))
-                                acceptable += (type == XFS_IO_UNWRITTEN);
-                        else if (buffer_delay(bh))
-                                acceptable += (type == XFS_IO_DELALLOC);
-                        else if (buffer_dirty(bh) && buffer_mapped(bh))
-                                acceptable += (type == XFS_IO_OVERWRITE);
-                        else
-                                break;
-                } while ((bh = bh->b_this_page) != head);
+        bh = head = page_buffers(page);
+        do {
+                if (buffer_unwritten(bh)) {
+                        if (type == XFS_IO_UNWRITTEN)
+                                return true;
+                } else if (buffer_delay(bh)) {
+                        if (type == XFS_IO_DELALLOC)
+                                return true;
+                } else if (buffer_dirty(bh) && buffer_mapped(bh)) {
+                        if (type == XFS_IO_OVERWRITE)
+                                return true;
+                }
 
-                if (acceptable)
-                        return 1;
-        }
+                /* If we are only checking the first buffer, we are done now. */
+                if (!check_all_buffers)
+                        break;
+        } while ((bh = bh->b_this_page) != head);
 
-        return 0;
+        return false;
 }
 
 /*
@@ -697,7 +705,7 @@ xfs_convert_page(
                 goto fail_unlock_page;
         if (page->mapping != inode->i_mapping)
                 goto fail_unlock_page;
-        if (!xfs_check_page_type(page, (*ioendp)->io_type))
+        if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
                 goto fail_unlock_page;
 
         /*
@@ -742,6 +750,15 @@ xfs_convert_page(
         p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
         page_dirty = p_offset / len;
 
+        /*
+         * The moment we find a buffer that doesn't match our current type
+         * specification or can't be written, abort the loop and start
+         * writeback. As per the above xfs_imap_valid() check, only
+         * xfs_vm_writepage() can handle partial page writeback fully - we are
+         * limited here to the buffers that are contiguous with the current
+         * ioend, and hence a buffer we can't write breaks that contiguity and
+         * we have to defer the rest of the IO to xfs_vm_writepage().
+         */
         bh = head = page_buffers(page);
         do {
                 if (offset >= end_offset)
@@ -750,7 +767,7 @@ xfs_convert_page(
                         uptodate = 0;
                 if (!(PageUptodate(page) || buffer_uptodate(bh))) {
                         done = 1;
-                        continue;
+                        break;
                 }
 
                 if (buffer_unwritten(bh) || buffer_delay(bh) ||
@@ -762,10 +779,11 @@ xfs_convert_page(
                         else
                                 type = XFS_IO_OVERWRITE;
 
-                        if (!xfs_imap_valid(inode, imap, offset)) {
-                                done = 1;
-                                continue;
-                        }
+                        /*
+                         * imap should always be valid because of the above
+                         * partial page end_offset check on the imap.
+                         */
+                        ASSERT(xfs_imap_valid(inode, imap, offset));
 
                         lock_buffer(bh);
                         if (type != XFS_IO_OVERWRITE)
@@ -777,6 +795,7 @@ xfs_convert_page(
                         count++;
                 } else {
                         done = 1;
+                        break;
                 }
         } while (offset += len, (bh = bh->b_this_page) != head);
 
@@ -868,7 +887,7 @@ xfs_aops_discard_page(
         struct buffer_head      *bh, *head;
         loff_t                  offset = page_offset(page);
 
-        if (!xfs_check_page_type(page, XFS_IO_DELALLOC))
+        if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
                 goto out_invalidate;
 
         if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -1441,7 +1460,8 @@ xfs_vm_direct_IO(
                 ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
                                             offset, nr_segs,
                                             xfs_get_blocks_direct,
-                                            xfs_end_io_direct_write, NULL, 0);
+                                            xfs_end_io_direct_write, NULL,
+                                            DIO_ASYNC_EXTEND);
                 if (ret != -EIOCBQUEUED && iocb->private)
                         goto out_destroy_ioend;
         } else {
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 7b126f46a2f9..fe9587fab17a 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -213,8 +213,8 @@ xfs_attr3_leaf_write_verify(
         struct xfs_attr3_leaf_hdr *hdr3 = bp->b_addr;
 
         if (!xfs_attr3_leaf_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -224,7 +224,7 @@ xfs_attr3_leaf_write_verify(
         if (bip)
                 hdr3->info.lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_ATTR3_LEAF_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_ATTR3_LEAF_CRC_OFF);
 }
 
 /*
@@ -239,13 +239,14 @@ xfs_attr3_leaf_read_verify(
 {
         struct xfs_mount        *mp = bp->b_target->bt_mount;
 
-        if ((xfs_sb_version_hascrc(&mp->m_sb) &&
-             !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                          XFS_ATTR3_LEAF_CRC_OFF)) ||
-            !xfs_attr3_leaf_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (xfs_sb_version_hascrc(&mp->m_sb) &&
+             !xfs_buf_verify_cksum(bp, XFS_ATTR3_LEAF_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_attr3_leaf_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = {
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index 5549d69ddb45..6e37823e2932 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -125,7 +125,6 @@ xfs_attr3_rmt_read_verify(
         struct xfs_mount *mp = bp->b_target->bt_mount;
         char            *ptr;
         int             len;
-        bool            corrupt = false;
         xfs_daddr_t     bno;
 
         /* no verification of non-crc buffers */
@@ -140,11 +139,11 @@ xfs_attr3_rmt_read_verify(
         while (len > 0) {
                 if (!xfs_verify_cksum(ptr, XFS_LBSIZE(mp),
                                       XFS_ATTR3_RMT_CRC_OFF)) {
-                        corrupt = true;
+                        xfs_buf_ioerror(bp, EFSBADCRC);
                         break;
                 }
                 if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
-                        corrupt = true;
+                        xfs_buf_ioerror(bp, EFSCORRUPTED);
                         break;
                 }
                 len -= XFS_LBSIZE(mp);
@@ -152,10 +151,9 @@ xfs_attr3_rmt_read_verify(
                 bno += mp->m_bsize;
         }
 
-        if (corrupt) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
-                xfs_buf_ioerror(bp, EFSCORRUPTED);
-        } else
+        if (bp->b_error)
+                xfs_verifier_error(bp);
+        else
                 ASSERT(len == 0);
 }
 
@@ -180,9 +178,8 @@ xfs_attr3_rmt_write_verify(
 
         while (len > 0) {
                 if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
-                        XFS_CORRUPTION_ERROR(__func__,
-                                            XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                         xfs_buf_ioerror(bp, EFSCORRUPTED);
+                        xfs_verifier_error(bp);
                         return;
                 }
                 if (bip) {
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 152543c4ca70..5b6092ef51ef 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -5378,3 +5378,196 @@ error0:
         }
         return error;
 }
+
+/*
+ * Shift extent records to the left to cover a hole.
+ *
+ * The maximum number of extents to be shifted in a single operation
+ * is @num_exts, and @current_ext keeps track of the current extent
+ * index we have shifted. @offset_shift_fsb is the length by which each
+ * extent is shifted. If there is no hole to shift the extents
+ * into, this will be considered invalid operation and we abort immediately.
+ */
+int
+xfs_bmap_shift_extents(
+        struct xfs_trans        *tp,
+        struct xfs_inode        *ip,
+        int                     *done,
+        xfs_fileoff_t           start_fsb,
+        xfs_fileoff_t           offset_shift_fsb,
+        xfs_extnum_t            *current_ext,
+        xfs_fsblock_t           *firstblock,
+        struct xfs_bmap_free    *flist,
+        int                     num_exts)
+{
+        struct xfs_btree_cur            *cur;
+        struct xfs_bmbt_rec_host        *gotp;
+        struct xfs_bmbt_irec            got;
+        struct xfs_bmbt_irec            left;
+        struct xfs_mount                *mp = ip->i_mount;
+        struct xfs_ifork                *ifp;
+        xfs_extnum_t                    nexts = 0;
+        xfs_fileoff_t                   startoff;
+        int                             error = 0;
+        int                             i;
+        int                             whichfork = XFS_DATA_FORK;
+        int                             logflags;
+        xfs_filblks_t                   blockcount = 0;
+
+        if (unlikely(XFS_TEST_ERROR(
+            (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
+             XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
+             mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+                XFS_ERROR_REPORT("xfs_bmap_shift_extents",
+                                 XFS_ERRLEVEL_LOW, mp);
+                return XFS_ERROR(EFSCORRUPTED);
+        }
+
+        if (XFS_FORCED_SHUTDOWN(mp))
+                return XFS_ERROR(EIO);
+
+        ASSERT(current_ext != NULL);
+
+        ifp = XFS_IFORK_PTR(ip, whichfork);
+
+        if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+                /* Read in all the extents */
+                error = xfs_iread_extents(tp, ip, whichfork);
+                if (error)
+                        return error;
+        }
+
+        /*
+         * If *current_ext is 0, we would need to lookup the extent
+         * from where we would start shifting and store it in gotp.
+         */
+        if (!*current_ext) {
+                gotp = xfs_iext_bno_to_ext(ifp, start_fsb, current_ext);
+                /*
+                 * gotp can be null in 2 cases: 1) if there are no extents
+                 * or 2) start_fsb lies in a hole beyond which there are
+                 * no extents. Either way, we are done.
+                 */
+                if (!gotp) {
+                        *done = 1;
+                        return 0;
+                }
+        }
+
+        /* We are going to change core inode */
+        logflags = XFS_ILOG_CORE;
+
+        if (ifp->if_flags & XFS_IFBROOT) {
+                cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
+                cur->bc_private.b.firstblock = *firstblock;
+                cur->bc_private.b.flist = flist;
+                cur->bc_private.b.flags = 0;
+        } else {
+                cur = NULL;
+                logflags |= XFS_ILOG_DEXT;
+        }
+
+        while (nexts++ < num_exts &&
+               *current_ext <  XFS_IFORK_NEXTENTS(ip, whichfork)) {
+
+                gotp = xfs_iext_get_ext(ifp, *current_ext);
+                xfs_bmbt_get_all(gotp, &got);
+                startoff = got.br_startoff - offset_shift_fsb;
+
+                /*
+                 * Before shifting extent into hole, make sure that the hole
+                 * is large enough to accomodate the shift.
+                 */
+                if (*current_ext) {
+                        xfs_bmbt_get_all(xfs_iext_get_ext(ifp,
+                                                *current_ext - 1), &left);
+
+                        if (startoff < left.br_startoff + left.br_blockcount)
+                                error = XFS_ERROR(EINVAL);
+                } else if (offset_shift_fsb > got.br_startoff) {
+                        /*
+                         * When first extent is shifted, offset_shift_fsb
+                         * should be less than the stating offset of
+                         * the first extent.
+                         */
+                        error = XFS_ERROR(EINVAL);
+                }
+
+                if (error)
+                        goto del_cursor;
+
+                if (cur) {
+                        error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
+                                                   got.br_startblock,
+                                                   got.br_blockcount,
+                                                   &i);
+                        if (error)
+                                goto del_cursor;
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
+                }
+
+                /* Check if we can merge 2 adjacent extents */
+                if (*current_ext &&
+                    left.br_startoff + left.br_blockcount == startoff &&
+                    left.br_startblock + left.br_blockcount ==
+                                got.br_startblock &&
+                    left.br_state == got.br_state &&
+                    left.br_blockcount + got.br_blockcount <= MAXEXTLEN) {
+                        blockcount = left.br_blockcount +
+                                got.br_blockcount;
+                        xfs_iext_remove(ip, *current_ext, 1, 0);
+                        if (cur) {
+                                error = xfs_btree_delete(cur, &i);
+                                if (error)
+                                        goto del_cursor;
+                                XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
+                        }
+                        XFS_IFORK_NEXT_SET(ip, whichfork,
+                                XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
+                        gotp = xfs_iext_get_ext(ifp, --*current_ext);
+                        xfs_bmbt_get_all(gotp, &got);
+
+                        /* Make cursor point to the extent we will update */
+                        if (cur) {
+                                error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
+                                                           got.br_startblock,
+                                                           got.br_blockcount,
+                                                           &i);
+                                if (error)
+                                        goto del_cursor;
+                                XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
+                        }
+
+                        xfs_bmbt_set_blockcount(gotp, blockcount);
+                        got.br_blockcount = blockcount;
+                } else {
+                        /* We have to update the startoff */
+                        xfs_bmbt_set_startoff(gotp, startoff);
+                        got.br_startoff = startoff;
+                }
+
+                if (cur) {
+                        error = xfs_bmbt_update(cur, got.br_startoff,
+                                                got.br_startblock,
+                                                got.br_blockcount,
+                                                got.br_state);
+                        if (error)
+                                goto del_cursor;
+                }
+
+                (*current_ext)++;
+        }
+
+        /* Check if we are done */
+        if (*current_ext ==  XFS_IFORK_NEXTENTS(ip, whichfork))
+                *done = 1;
+
+del_cursor:
+        if (cur)
+                xfs_btree_del_cursor(cur,
+                        error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+
+        xfs_trans_log_inode(tp, ip, logflags);
+
+        return error;
+}
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 33b41f351225..f84bd7af43be 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -127,6 +127,16 @@ static inline void xfs_bmap_init(xfs_bmap_free_t *flp, xfs_fsblock_t *fbp)
         { BMAP_RIGHT_FILLING,   "RF" }, \
         { BMAP_ATTRFORK,        "ATTR" }
 
+
+/*
+ * This macro is used to determine how many extents will be shifted
+ * in one write transaction. We could require two splits,
+ * an extent move on the first and an extent merge on the second,
+ * So it is proper that one extent is shifted inside write transaction
+ * at a time.
+ */
+#define XFS_BMAP_MAX_SHIFT_EXTENTS      1
+
 #ifdef DEBUG
 void    xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
                 int whichfork, unsigned long caller_ip);
@@ -169,5 +179,10 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 int     xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
                 xfs_extnum_t num);
 uint    xfs_default_attroffset(struct xfs_inode *ip);
+int     xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip,
+                int *done, xfs_fileoff_t start_fsb,
+                xfs_fileoff_t offset_shift_fsb, xfs_extnum_t *current_ext,
+                xfs_fsblock_t *firstblock, struct xfs_bmap_free *flist,
+                int num_exts);
 
 #endif  /* __XFS_BMAP_H__ */
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index 706bc3f777cb..818d546664e7 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -780,12 +780,14 @@ static void
 xfs_bmbt_read_verify(
         struct xfs_buf  *bp)
 {
-        if (!(xfs_btree_lblock_verify_crc(bp) &&
-              xfs_bmbt_verify(bp))) {
-                trace_xfs_btree_corrupt(bp, _RET_IP_);
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                     bp->b_target->bt_mount, bp->b_addr);
+        if (!xfs_btree_lblock_verify_crc(bp))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_bmbt_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+        if (bp->b_error) {
+                trace_xfs_btree_corrupt(bp, _RET_IP_);
+                xfs_verifier_error(bp);
         }
 }
 
@@ -794,11 +796,9 @@ xfs_bmbt_write_verify(
         struct xfs_buf  *bp)
 {
         if (!xfs_bmbt_verify(bp)) {
-                xfs_warn(bp->b_target->bt_mount, "bmbt daddr 0x%llx failed", bp->b_bn);
                 trace_xfs_btree_corrupt(bp, _RET_IP_);
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                     bp->b_target->bt_mount, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
         xfs_btree_lblock_calc_crc(bp);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index f264616080ca..01f6a646caa1 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1349,7 +1349,6 @@ xfs_free_file_space(
                  * the freeing of the space succeeds at ENOSPC.
                  */
                 tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
-                tp->t_flags |= XFS_TRANS_RESERVE;
                 error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);
 
                 /*
@@ -1468,6 +1467,102 @@ out:
 }
 
 /*
+ * xfs_collapse_file_space()
+ *      This routine frees disk space and shift extent for the given file.
+ *      The first thing we do is to free data blocks in the specified range
+ *      by calling xfs_free_file_space(). It would also sync dirty data
+ *      and invalidate page cache over the region on which collapse range
+ *      is working. And Shift extent records to the left to cover a hole.
+ * RETURNS:
+ *      0 on success
+ *      errno on error
+ *
+ */
+int
+xfs_collapse_file_space(
+        struct xfs_inode        *ip,
+        xfs_off_t               offset,
+        xfs_off_t               len)
+{
+        int                     done = 0;
+        struct xfs_mount        *mp = ip->i_mount;
+        struct xfs_trans        *tp;
+        int                     error;
+        xfs_extnum_t            current_ext = 0;
+        struct xfs_bmap_free    free_list;
+        xfs_fsblock_t           first_block;
+        int                     committed;
+        xfs_fileoff_t           start_fsb;
+        xfs_fileoff_t           shift_fsb;
+
+        ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+        trace_xfs_collapse_file_space(ip);
+
+        start_fsb = XFS_B_TO_FSB(mp, offset + len);
+        shift_fsb = XFS_B_TO_FSB(mp, len);
+
+        error = xfs_free_file_space(ip, offset, len);
+        if (error)
+                return error;
+
+        while (!error && !done) {
+                tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+                tp->t_flags |= XFS_TRANS_RESERVE;
+                /*
+                 * We would need to reserve permanent block for transaction.
+                 * This will come into picture when after shifting extent into
+                 * hole we found that adjacent extents can be merged which
+                 * may lead to freeing of a block during record update.
+                 */
+                error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
+                                XFS_DIOSTRAT_SPACE_RES(mp, 0), 0);
+                if (error) {
+                        ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
+                        xfs_trans_cancel(tp, 0);
+                        break;
+                }
+
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+                error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
+                                ip->i_gdquot, ip->i_pdquot,
+                                XFS_DIOSTRAT_SPACE_RES(mp, 0), 0,
+                                XFS_QMOPT_RES_REGBLKS);
+                if (error)
+                        goto out;
+
+                xfs_trans_ijoin(tp, ip, 0);
+
+                xfs_bmap_init(&free_list, &first_block);
+
+                /*
+                 * We are using the write transaction in which max 2 bmbt
+                 * updates are allowed
+                 */
+                error = xfs_bmap_shift_extents(tp, ip, &done, start_fsb,
+                                               shift_fsb, &current_ext,
+                                               &first_block, &free_list,
+                                               XFS_BMAP_MAX_SHIFT_EXTENTS);
+                if (error)
+                        goto out;
+
+                error = xfs_bmap_finish(&tp, &free_list, &committed);
+                if (error)
+                        goto out;
+
+                error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        }
+
+        return error;
+
+out:
+        xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+        xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        return error;
+}
+
+/*
  * We need to check that the format of the data fork in the temporary inode is
  * valid for the target inode before doing the swap. This is not a problem with
  * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 900747b25772..935ed2b24edf 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -99,6 +99,8 @@ int	xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset,
                             xfs_off_t len);
 int     xfs_zero_file_space(struct xfs_inode *ip, xfs_off_t offset,
                             xfs_off_t len);
+int     xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset,
+                                xfs_off_t len);
 
 /* EOF block manipulation functions */
 bool    xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index 9adaae4f3e2f..e80d59fdf89a 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -234,8 +234,7 @@ xfs_btree_lblock_calc_crc(
                 return;
         if (bip)
                 block->bb_u.l.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-                         XFS_BTREE_LBLOCK_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF);
 }
 
 bool
@@ -243,8 +242,8 @@ xfs_btree_lblock_verify_crc(
         struct xfs_buf          *bp)
 {
         if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
-                return xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                        XFS_BTREE_LBLOCK_CRC_OFF);
+                return xfs_buf_verify_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF);
+
         return true;
 }
 
@@ -267,8 +266,7 @@ xfs_btree_sblock_calc_crc(
                 return;
         if (bip)
                 block->bb_u.s.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-                         XFS_BTREE_SBLOCK_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF);
 }
 
 bool
@@ -276,8 +274,8 @@ xfs_btree_sblock_verify_crc(
         struct xfs_buf          *bp)
 {
         if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
-                return xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                        XFS_BTREE_SBLOCK_CRC_OFF);
+                return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF);
+
         return true;
 }
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 9c061ef2b0d9..107f2fdfe41f 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -396,7 +396,17 @@ _xfs_buf_map_pages(
                 bp->b_addr = NULL;
         } else {
                 int retried = 0;
+                unsigned noio_flag;
 
+                /*
+                 * vm_map_ram() will allocate auxillary structures (e.g.
+                 * pagetables) with GFP_KERNEL, yet we are likely to be under
+                 * GFP_NOFS context here. Hence we need to tell memory reclaim
+                 * that we are in such a context via PF_MEMALLOC_NOIO to prevent
+                 * memory reclaim re-entering the filesystem here and
+                 * potentially deadlocking.
+                 */
+                noio_flag = memalloc_noio_save();
                 do {
                         bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
                                                 -1, PAGE_KERNEL);
@@ -404,6 +414,7 @@ _xfs_buf_map_pages(
                                 break;
                         vm_unmap_aliases();
                 } while (retried++ <= 1);
+                memalloc_noio_restore(noio_flag);
 
                 if (!bp->b_addr)
                         return -ENOMEM;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 995339534db6..b8a3abf6cf47 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -369,6 +369,20 @@ static inline void xfs_buf_relse(xfs_buf_t *bp)
         xfs_buf_rele(bp);
 }
 
+static inline int
+xfs_buf_verify_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
+{
+        return xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
+                                cksum_offset);
+}
+
+static inline void
+xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
+{
+        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
+                         cksum_offset);
+}
+
 /*
  *      Handling of buftargs.
  */
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 33149113e333..8752821443be 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -796,20 +796,6 @@ xfs_buf_item_init(
                 bip->bli_formats[i].blf_map_size = map_size;
         }
 
-#ifdef XFS_TRANS_DEBUG
-        /*
-         * Allocate the arrays for tracking what needs to be logged
-         * and what our callers request to be logged.  bli_orig
-         * holds a copy of the original, clean buffer for comparison
-         * against, and bli_logged keeps a 1 bit flag per byte in
-         * the buffer to indicate which bytes the callers have asked
-         * to have logged.
-         */
-        bip->bli_orig = kmem_alloc(BBTOB(bp->b_length), KM_SLEEP);
-        memcpy(bip->bli_orig, bp->b_addr, BBTOB(bp->b_length));
-        bip->bli_logged = kmem_zalloc(BBTOB(bp->b_length) / NBBY, KM_SLEEP);
-#endif
-
         /*
          * Put the buf item into the list of items attached to the
          * buffer at the front.
@@ -957,11 +943,6 @@ 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 */
-
         xfs_buf_item_free_format(bip);
         kmem_zone_free(xfs_buf_item_zone, bip);
 }
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 796272a2e129..6cc5f6785a77 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -185,8 +185,8 @@ xfs_da3_node_write_verify(
         struct xfs_da3_node_hdr *hdr3 = bp->b_addr;
 
         if (!xfs_da3_node_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -196,7 +196,7 @@ xfs_da3_node_write_verify(
         if (bip)
                 hdr3->info.lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DA3_NODE_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_DA3_NODE_CRC_OFF);
 }
 
 /*
@@ -209,18 +209,20 @@ static void
 xfs_da3_node_read_verify(
         struct xfs_buf          *bp)
 {
-        struct xfs_mount        *mp = bp->b_target->bt_mount;
         struct xfs_da_blkinfo   *info = bp->b_addr;
 
         switch (be16_to_cpu(info->magic)) {
                 case XFS_DA3_NODE_MAGIC:
-                        if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                              XFS_DA3_NODE_CRC_OFF))
+                        if (!xfs_buf_verify_cksum(bp, XFS_DA3_NODE_CRC_OFF)) {
+                                xfs_buf_ioerror(bp, EFSBADCRC);
                                 break;
+                        }
                         /* fall through */
                 case XFS_DA_NODE_MAGIC:
-                        if (!xfs_da3_node_verify(bp))
+                        if (!xfs_da3_node_verify(bp)) {
+                                xfs_buf_ioerror(bp, EFSCORRUPTED);
                                 break;
+                        }
                         return;
                 case XFS_ATTR_LEAF_MAGIC:
                 case XFS_ATTR3_LEAF_MAGIC:
@@ -237,8 +239,7 @@ xfs_da3_node_read_verify(
         }
 
         /* corrupt block */
-        XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
-        xfs_buf_ioerror(bp, EFSCORRUPTED);
+        xfs_verifier_error(bp);
 }
 
 const struct xfs_buf_ops xfs_da3_node_buf_ops = {
@@ -1295,7 +1296,7 @@ xfs_da3_fixhashpath(
                 node = blk->bp->b_addr;
                 dp->d_ops->node_hdr_from_disk(&nodehdr, node);
                 btree = dp->d_ops->node_tree_p(node);
-                if (be32_to_cpu(btree->hashval) == lasthash)
+                if (be32_to_cpu(btree[blk->index].hashval) == lasthash)
                         break;
                 blk->hashval = lasthash;
                 btree[blk->index].hashval = cpu_to_be32(lasthash);
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index e5869b50dc41..623bbe8fd921 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -89,6 +89,8 @@ typedef struct xfs_dinode {
         /* structure must be padded to 64 bit alignment */
 } xfs_dinode_t;
 
+#define XFS_DINODE_CRC_OFF      offsetof(struct xfs_dinode, di_crc)
+
 #define DI_MAX_FLUSH 0xffff
 
 /*
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index ce16ef02997a..fda46253966a 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -180,16 +180,23 @@ xfs_dir_init(
         xfs_inode_t     *dp,
         xfs_inode_t     *pdp)
 {
-        xfs_da_args_t   args;
+        struct xfs_da_args *args;
         int             error;
 
-        memset((char *)&args, 0, sizeof(args));
-        args.dp = dp;
-        args.trans = tp;
         ASSERT(S_ISDIR(dp->i_d.di_mode));
-        if ((error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino)))
+        error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino);
+        if (error)
                 return error;
-        return xfs_dir2_sf_create(&args, pdp->i_ino);
+
+        args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+        if (!args)
+                return ENOMEM;
+
+        args->dp = dp;
+        args->trans = tp;
+        error = xfs_dir2_sf_create(args, pdp->i_ino);
+        kmem_free(args);
+        return error;
 }
 
 /*
@@ -205,41 +212,56 @@ xfs_dir_createname(
         xfs_bmap_free_t         *flist,         /* bmap's freeblock list */
         xfs_extlen_t            total)          /* bmap's total block count */
 {
-        xfs_da_args_t           args;
+        struct xfs_da_args      *args;
         int                     rval;
         int                     v;              /* type-checking value */
 
         ASSERT(S_ISDIR(dp->i_d.di_mode));
-        if ((rval = xfs_dir_ino_validate(tp->t_mountp, inum)))
+        rval = xfs_dir_ino_validate(tp->t_mountp, inum);
+        if (rval)
                 return rval;
         XFS_STATS_INC(xs_dir_create);
 
-        memset(&args, 0, sizeof(xfs_da_args_t));
-        args.name = name->name;
-        args.namelen = name->len;
-        args.filetype = name->type;
-        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
-        args.inumber = inum;
-        args.dp = dp;
-        args.firstblock = first;
-        args.flist = flist;
-        args.total = total;
-        args.whichfork = XFS_DATA_FORK;
-        args.trans = tp;
-        args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
-
-        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
-                rval = xfs_dir2_sf_addname(&args);
-        else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_block_addname(&args);
-        else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_leaf_addname(&args);
+        args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+        if (!args)
+                return ENOMEM;
+
+        args->name = name->name;
+        args->namelen = name->len;
+        args->filetype = name->type;
+        args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+        args->inumber = inum;
+        args->dp = dp;
+        args->firstblock = first;
+        args->flist = flist;
+        args->total = total;
+        args->whichfork = XFS_DATA_FORK;
+        args->trans = tp;
+        args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+
+        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+                rval = xfs_dir2_sf_addname(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isblock(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v) {
+                rval = xfs_dir2_block_addname(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isleaf(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v)
+                rval = xfs_dir2_leaf_addname(args);
         else
-                rval = xfs_dir2_node_addname(&args);
+                rval = xfs_dir2_node_addname(args);
+
+out_free:
+        kmem_free(args);
         return rval;
 }
 
@@ -282,46 +304,66 @@ xfs_dir_lookup(
         xfs_ino_t       *inum,          /* out: inode number */
         struct xfs_name *ci_name)       /* out: actual name if CI match */
 {
-        xfs_da_args_t   args;
+        struct xfs_da_args *args;
         int             rval;
         int             v;              /* type-checking value */
 
         ASSERT(S_ISDIR(dp->i_d.di_mode));
         XFS_STATS_INC(xs_dir_lookup);
 
-        memset(&args, 0, sizeof(xfs_da_args_t));
-        args.name = name->name;
-        args.namelen = name->len;
-        args.filetype = name->type;
-        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
-        args.dp = dp;
-        args.whichfork = XFS_DATA_FORK;
-        args.trans = tp;
-        args.op_flags = XFS_DA_OP_OKNOENT;
+        /*
+         * We need to use KM_NOFS here so that lockdep will not throw false
+         * positive deadlock warnings on a non-transactional lookup path. It is
+         * safe to recurse into inode recalim in that case, but lockdep can't
+         * easily be taught about it. Hence KM_NOFS avoids having to add more
+         * lockdep Doing this avoids having to add a bunch of lockdep class
+         * annotations into the reclaim path for the ilock.
+         */
+        args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+        args->name = name->name;
+        args->namelen = name->len;
+        args->filetype = name->type;
+        args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+        args->dp = dp;
+        args->whichfork = XFS_DATA_FORK;
+        args->trans = tp;
+        args->op_flags = XFS_DA_OP_OKNOENT;
         if (ci_name)
-                args.op_flags |= XFS_DA_OP_CILOOKUP;
+                args->op_flags |= XFS_DA_OP_CILOOKUP;
 
-        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
-                rval = xfs_dir2_sf_lookup(&args);
-        else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_block_lookup(&args);
-        else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_leaf_lookup(&args);
+        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+                rval = xfs_dir2_sf_lookup(args);
+                goto out_check_rval;
+        }
+
+        rval = xfs_dir2_isblock(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v) {
+                rval = xfs_dir2_block_lookup(args);
+                goto out_check_rval;
+        }
+
+        rval = xfs_dir2_isleaf(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v)
+                rval = xfs_dir2_leaf_lookup(args);
         else
-                rval = xfs_dir2_node_lookup(&args);
+                rval = xfs_dir2_node_lookup(args);
+
+out_check_rval:
         if (rval == EEXIST)
                 rval = 0;
         if (!rval) {
-                *inum = args.inumber;
+                *inum = args->inumber;
                 if (ci_name) {
-                        ci_name->name = args.value;
-                        ci_name->len = args.valuelen;
+                        ci_name->name = args->value;
+                        ci_name->len = args->valuelen;
                 }
         }
+out_free:
+        kmem_free(args);
         return rval;
 }
 
@@ -338,38 +380,51 @@ xfs_dir_removename(
         xfs_bmap_free_t *flist,         /* bmap's freeblock list */
         xfs_extlen_t    total)          /* bmap's total block count */
 {
-        xfs_da_args_t   args;
+        struct xfs_da_args *args;
         int             rval;
         int             v;              /* type-checking value */
 
         ASSERT(S_ISDIR(dp->i_d.di_mode));
         XFS_STATS_INC(xs_dir_remove);
 
-        memset(&args, 0, sizeof(xfs_da_args_t));
-        args.name = name->name;
-        args.namelen = name->len;
-        args.filetype = name->type;
-        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
-        args.inumber = ino;
-        args.dp = dp;
-        args.firstblock = first;
-        args.flist = flist;
-        args.total = total;
-        args.whichfork = XFS_DATA_FORK;
-        args.trans = tp;
-
-        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
-                rval = xfs_dir2_sf_removename(&args);
-        else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_block_removename(&args);
-        else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_leaf_removename(&args);
+        args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+        if (!args)
+                return ENOMEM;
+
+        args->name = name->name;
+        args->namelen = name->len;
+        args->filetype = name->type;
+        args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+        args->inumber = ino;
+        args->dp = dp;
+        args->firstblock = first;
+        args->flist = flist;
+        args->total = total;
+        args->whichfork = XFS_DATA_FORK;
+        args->trans = tp;
+
+        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+                rval = xfs_dir2_sf_removename(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isblock(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v) {
+                rval = xfs_dir2_block_removename(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isleaf(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v)
+                rval = xfs_dir2_leaf_removename(args);
         else
-                rval = xfs_dir2_node_removename(&args);
+                rval = xfs_dir2_node_removename(args);
+out_free:
+        kmem_free(args);
         return rval;
 }
 
@@ -386,40 +441,54 @@ xfs_dir_replace(
         xfs_bmap_free_t *flist,         /* bmap's freeblock list */
         xfs_extlen_t    total)          /* bmap's total block count */
 {
-        xfs_da_args_t   args;
+        struct xfs_da_args *args;
         int             rval;
         int             v;              /* type-checking value */
 
         ASSERT(S_ISDIR(dp->i_d.di_mode));
 
-        if ((rval = xfs_dir_ino_validate(tp->t_mountp, inum)))
+        rval = xfs_dir_ino_validate(tp->t_mountp, inum);
+        if (rval)
                 return rval;
 
-        memset(&args, 0, sizeof(xfs_da_args_t));
-        args.name = name->name;
-        args.namelen = name->len;
-        args.filetype = name->type;
-        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
-        args.inumber = inum;
-        args.dp = dp;
-        args.firstblock = first;
-        args.flist = flist;
-        args.total = total;
-        args.whichfork = XFS_DATA_FORK;
-        args.trans = tp;
-
-        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
-                rval = xfs_dir2_sf_replace(&args);
-        else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_block_replace(&args);
-        else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_leaf_replace(&args);
+        args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+        if (!args)
+                return ENOMEM;
+
+        args->name = name->name;
+        args->namelen = name->len;
+        args->filetype = name->type;
+        args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+        args->inumber = inum;
+        args->dp = dp;
+        args->firstblock = first;
+        args->flist = flist;
+        args->total = total;
+        args->whichfork = XFS_DATA_FORK;
+        args->trans = tp;
+
+        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+                rval = xfs_dir2_sf_replace(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isblock(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v) {
+                rval = xfs_dir2_block_replace(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isleaf(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v)
+                rval = xfs_dir2_leaf_replace(args);
         else
-                rval = xfs_dir2_node_replace(&args);
+                rval = xfs_dir2_node_replace(args);
+out_free:
+        kmem_free(args);
         return rval;
 }
 
@@ -434,7 +503,7 @@ xfs_dir_canenter(
         struct xfs_name *name,          /* name of entry to add */
         uint            resblks)
 {
-        xfs_da_args_t   args;
+        struct xfs_da_args *args;
         int             rval;
         int             v;              /* type-checking value */
 
@@ -443,29 +512,42 @@ xfs_dir_canenter(
 
         ASSERT(S_ISDIR(dp->i_d.di_mode));
 
-        memset(&args, 0, sizeof(xfs_da_args_t));
-        args.name = name->name;
-        args.namelen = name->len;
-        args.filetype = name->type;
-        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
-        args.dp = dp;
-        args.whichfork = XFS_DATA_FORK;
-        args.trans = tp;
-        args.op_flags = XFS_DA_OP_JUSTCHECK | XFS_DA_OP_ADDNAME |
+        args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+        if (!args)
+                return ENOMEM;
+
+        args->name = name->name;
+        args->namelen = name->len;
+        args->filetype = name->type;
+        args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+        args->dp = dp;
+        args->whichfork = XFS_DATA_FORK;
+        args->trans = tp;
+        args->op_flags = XFS_DA_OP_JUSTCHECK | XFS_DA_OP_ADDNAME |
                                                         XFS_DA_OP_OKNOENT;
 
-        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
-                rval = xfs_dir2_sf_addname(&args);
-        else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_block_addname(&args);
-        else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
-                return rval;
-        else if (v)
-                rval = xfs_dir2_leaf_addname(&args);
+        if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+                rval = xfs_dir2_sf_addname(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isblock(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v) {
+                rval = xfs_dir2_block_addname(args);
+                goto out_free;
+        }
+
+        rval = xfs_dir2_isleaf(tp, dp, &v);
+        if (rval)
+                goto out_free;
+        if (v)
+                rval = xfs_dir2_leaf_addname(args);
         else
-                rval = xfs_dir2_node_addname(&args);
+                rval = xfs_dir2_node_addname(args);
+out_free:
+        kmem_free(args);
         return rval;
 }
 
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 90cdbf4b5f19..4f6a38cb83a4 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -89,13 +89,14 @@ xfs_dir3_block_read_verify(
 {
         struct xfs_mount        *mp = bp->b_target->bt_mount;
 
-        if ((xfs_sb_version_hascrc(&mp->m_sb) &&
-             !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                          XFS_DIR3_DATA_CRC_OFF)) ||
-            !xfs_dir3_block_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (xfs_sb_version_hascrc(&mp->m_sb) &&
+             !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_dir3_block_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -107,8 +108,8 @@ xfs_dir3_block_write_verify(
         struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
 
         if (!xfs_dir3_block_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -118,7 +119,7 @@ xfs_dir3_block_write_verify(
         if (bip)
                 hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DIR3_DATA_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index 70acff4ee173..afa4ad523f3f 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -241,7 +241,6 @@ static void
 xfs_dir3_data_reada_verify(
         struct xfs_buf          *bp)
 {
-        struct xfs_mount        *mp = bp->b_target->bt_mount;
         struct xfs_dir2_data_hdr *hdr = bp->b_addr;
 
         switch (hdr->magic) {
@@ -255,8 +254,8 @@ xfs_dir3_data_reada_verify(
                 xfs_dir3_data_verify(bp);
                 return;
         default:
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, hdr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 break;
         }
 }
@@ -267,13 +266,14 @@ xfs_dir3_data_read_verify(
 {
         struct xfs_mount        *mp = bp->b_target->bt_mount;
 
-        if ((xfs_sb_version_hascrc(&mp->m_sb) &&
-             !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                          XFS_DIR3_DATA_CRC_OFF)) ||
-            !xfs_dir3_data_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (xfs_sb_version_hascrc(&mp->m_sb) &&
+             !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
+                 xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_dir3_data_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -285,8 +285,8 @@ xfs_dir3_data_write_verify(
         struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
 
         if (!xfs_dir3_data_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -296,7 +296,7 @@ xfs_dir3_data_write_verify(
         if (bip)
                 hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DIR3_DATA_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_dir3_data_buf_ops = {
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index ae47ec6e16c4..d36e97df1187 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -179,13 +179,14 @@ __read_verify(
 {
         struct xfs_mount        *mp = bp->b_target->bt_mount;
 
-        if ((xfs_sb_version_hascrc(&mp->m_sb) &&
-             !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                          XFS_DIR3_LEAF_CRC_OFF)) ||
-            !xfs_dir3_leaf_verify(bp, magic)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (xfs_sb_version_hascrc(&mp->m_sb) &&
+             !xfs_buf_verify_cksum(bp, XFS_DIR3_LEAF_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_dir3_leaf_verify(bp, magic))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -198,8 +199,8 @@ __write_verify(
         struct xfs_dir3_leaf_hdr *hdr3 = bp->b_addr;
 
         if (!xfs_dir3_leaf_verify(bp, magic)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -209,7 +210,7 @@ __write_verify(
         if (bip)
                 hdr3->info.lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DIR3_LEAF_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_DIR3_LEAF_CRC_OFF);
 }
 
 static void
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index 48c7d18f68c3..cb434d732681 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -115,13 +115,14 @@ xfs_dir3_free_read_verify(
 {
         struct xfs_mount        *mp = bp->b_target->bt_mount;
 
-        if ((xfs_sb_version_hascrc(&mp->m_sb) &&
-             !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                          XFS_DIR3_FREE_CRC_OFF)) ||
-            !xfs_dir3_free_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (xfs_sb_version_hascrc(&mp->m_sb) &&
+            !xfs_buf_verify_cksum(bp, XFS_DIR3_FREE_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_dir3_free_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -133,8 +134,8 @@ xfs_dir3_free_write_verify(
         struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
 
         if (!xfs_dir3_free_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -144,7 +145,7 @@ xfs_dir3_free_write_verify(
         if (bip)
                 hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DIR3_FREE_CRC_OFF);
+        xfs_buf_update_cksum(bp, XFS_DIR3_FREE_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 7aeb4c895b32..868b19f096bf 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -615,7 +615,7 @@ xfs_qm_dqread(
 
         if (flags & XFS_QMOPT_DQALLOC) {
                 tp = xfs_trans_alloc(mp, XFS_TRANS_QM_DQALLOC);
-                error = xfs_trans_reserve(tp, &M_RES(mp)->tr_attrsetm,
+                error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_dqalloc,
                                           XFS_QM_DQALLOC_SPACE_RES(mp), 0);
                 if (error)
                         goto error1;
diff --git a/fs/xfs/xfs_dquot_buf.c b/fs/xfs/xfs_dquot_buf.c
index d401457d2f25..610da8177737 100644
--- a/fs/xfs/xfs_dquot_buf.c
+++ b/fs/xfs/xfs_dquot_buf.c
@@ -257,10 +257,13 @@ xfs_dquot_buf_read_verify(
 {
         struct xfs_mount        *mp = bp->b_target->bt_mount;
 
-        if (!xfs_dquot_buf_verify_crc(mp, bp) || !xfs_dquot_buf_verify(mp, bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (!xfs_dquot_buf_verify_crc(mp, bp))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_dquot_buf_verify(mp, bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 /*
@@ -275,8 +278,8 @@ xfs_dquot_buf_write_verify(
         struct xfs_mount        *mp = bp->b_target->bt_mount;
 
         if (!xfs_dquot_buf_verify(mp, bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 }
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 9995b807d627..edac5b057d28 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -156,7 +156,7 @@ xfs_error_report(
 {
         if (level <= xfs_error_level) {
                 xfs_alert_tag(mp, XFS_PTAG_ERROR_REPORT,
-                "Internal error %s at line %d of file %s.  Caller 0x%p",
+                "Internal error %s at line %d of file %s.  Caller %pF",
                             tag, linenum, filename, ra);
 
                 xfs_stack_trace();
@@ -178,3 +178,28 @@ xfs_corruption_error(
         xfs_error_report(tag, level, mp, filename, linenum, ra);
         xfs_alert(mp, "Corruption detected. Unmount and run xfs_repair");
 }
+
+/*
+ * Warnings specifically for verifier errors.  Differentiate CRC vs. invalid
+ * values, and omit the stack trace unless the error level is tuned high.
+ */
+void
+xfs_verifier_error(
+        struct xfs_buf          *bp)
+{
+        struct xfs_mount *mp = bp->b_target->bt_mount;
+
+        xfs_alert(mp, "Metadata %s detected at %pF, block 0x%llx",
+                  bp->b_error == EFSBADCRC ? "CRC error" : "corruption",
+                  __return_address, bp->b_bn);
+
+        xfs_alert(mp, "Unmount and run xfs_repair");
+
+        if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
+                xfs_alert(mp, "First 64 bytes of corrupted metadata buffer:");
+                xfs_hex_dump(xfs_buf_offset(bp, 0), 64);
+        }
+
+        if (xfs_error_level >= XFS_ERRLEVEL_HIGH)
+                xfs_stack_trace();
+}
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 079a367f44ee..c1c57d4a4b5d 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -34,6 +34,7 @@ extern void xfs_error_report(const char *tag, int level, struct xfs_mount *mp,
 extern void xfs_corruption_error(const char *tag, int level,
                         struct xfs_mount *mp, void *p, const char *filename,
                         int linenum, inst_t *ra);
+extern void xfs_verifier_error(struct xfs_buf *bp);
 
 #define XFS_ERROR_REPORT(e, lvl, mp)    \
         xfs_error_report(e, lvl, mp, __FILE__, __LINE__, __return_address)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 64b48eade91d..f7abff8c16ca 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -823,7 +823,8 @@ xfs_file_fallocate(
 
         if (!S_ISREG(inode->i_mode))
                 return -EINVAL;
-        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+                     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
                 return -EOPNOTSUPP;
 
         xfs_ilock(ip, XFS_IOLOCK_EXCL);
@@ -831,6 +832,20 @@ xfs_file_fallocate(
                 error = xfs_free_file_space(ip, offset, len);
                 if (error)
                         goto out_unlock;
+        } else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+                unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+
+                if (offset & blksize_mask || len & blksize_mask) {
+                        error = -EINVAL;
+                        goto out_unlock;
+                }
+
+                ASSERT(offset + len < i_size_read(inode));
+                new_size = i_size_read(inode) - len;
+
+                error = xfs_collapse_file_space(ip, offset, len);
+                if (error)
+                        goto out_unlock;
         } else {
                 if (!(mode & FALLOC_FL_KEEP_SIZE) &&
                     offset + len > i_size_read(inode)) {
@@ -840,8 +855,11 @@ xfs_file_fallocate(
                                 goto out_unlock;
                 }
 
-                error = xfs_alloc_file_space(ip, offset, len,
-                                             XFS_BMAPI_PREALLOC);
+                if (mode & FALLOC_FL_ZERO_RANGE)
+                        error = xfs_zero_file_space(ip, offset, len);
+                else
+                        error = xfs_alloc_file_space(ip, offset, len,
+                                                     XFS_BMAPI_PREALLOC);
                 if (error)
                         goto out_unlock;
         }
@@ -859,7 +877,7 @@ xfs_file_fallocate(
         if (ip->i_d.di_mode & S_IXGRP)
                 ip->i_d.di_mode &= ~S_ISGID;
 
-        if (!(mode & FALLOC_FL_PUNCH_HOLE))
+        if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE)))
                 ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
 
         xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
diff --git a/fs/xfs/xfs_format.h b/fs/xfs/xfs_format.h
index b6ab5a3cfa12..9898f31d05d8 100644
--- a/fs/xfs/xfs_format.h
+++ b/fs/xfs/xfs_format.h
@@ -145,6 +145,8 @@ struct xfs_dsymlink_hdr {
         __be64  sl_lsn;
 };
 
+#define XFS_SYMLINK_CRC_OFF     offsetof(struct xfs_dsymlink_hdr, sl_crc)
+
 /*
  * The maximum pathlen is 1024 bytes. Since the minimum file system
  * blocksize is 512 bytes, we can get a max of 3 extents back from
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 5d7f105a1c82..8f711db61a0c 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -363,6 +363,18 @@ xfs_ialloc_ag_alloc(
                 args.minleft = args.mp->m_in_maxlevels - 1;
                 if ((error = xfs_alloc_vextent(&args)))
                         return error;
+
+                /*
+                 * This request might have dirtied the transaction if the AG can
+                 * satisfy the request, but the exact block was not available.
+                 * If the allocation did fail, subsequent requests will relax
+                 * the exact agbno requirement and increase the alignment
+                 * instead. It is critical that the total size of the request
+                 * (len + alignment + slop) does not increase from this point
+                 * on, so reset minalignslop to ensure it is not included in
+                 * subsequent requests.
+                 */
+                args.minalignslop = 0;
         } else
                 args.fsbno = NULLFSBLOCK;
 
@@ -1568,18 +1580,17 @@ xfs_agi_read_verify(
         struct xfs_buf  *bp)
 {
         struct xfs_mount *mp = bp->b_target->bt_mount;
-        int             agi_ok = 1;
-
-        if (xfs_sb_version_hascrc(&mp->m_sb))
-                agi_ok = xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                          offsetof(struct xfs_agi, agi_crc));
-        agi_ok = agi_ok && xfs_agi_verify(bp);
 
-        if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IALLOC_READ_AGI,
-                        XFS_RANDOM_IALLOC_READ_AGI))) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (xfs_sb_version_hascrc(&mp->m_sb) &&
+            !xfs_buf_verify_cksum(bp, XFS_AGI_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (XFS_TEST_ERROR(!xfs_agi_verify(bp), mp,
+                                XFS_ERRTAG_IALLOC_READ_AGI,
+                                XFS_RANDOM_IALLOC_READ_AGI))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -1590,8 +1601,8 @@ xfs_agi_write_verify(
         struct xfs_buf_log_item *bip = bp->b_fspriv;
 
         if (!xfs_agi_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -1600,8 +1611,7 @@ xfs_agi_write_verify(
 
         if (bip)
                 XFS_BUF_TO_AGI(bp)->agi_lsn = cpu_to_be64(bip->bli_item.li_lsn);
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-                         offsetof(struct xfs_agi, agi_crc));
+        xfs_buf_update_cksum(bp, XFS_AGI_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_agi_buf_ops = {
diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c
index c8fa5bbb36de..7e309b11e87d 100644
--- a/fs/xfs/xfs_ialloc_btree.c
+++ b/fs/xfs/xfs_ialloc_btree.c
@@ -243,12 +243,14 @@ static void
 xfs_inobt_read_verify(
         struct xfs_buf  *bp)
 {
-        if (!(xfs_btree_sblock_verify_crc(bp) &&
-              xfs_inobt_verify(bp))) {
-                trace_xfs_btree_corrupt(bp, _RET_IP_);
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                     bp->b_target->bt_mount, bp->b_addr);
+        if (!xfs_btree_sblock_verify_crc(bp))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_inobt_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+        if (bp->b_error) {
+                trace_xfs_btree_corrupt(bp, _RET_IP_);
+                xfs_verifier_error(bp);
         }
 }
 
@@ -258,9 +260,9 @@ xfs_inobt_write_verify(
 {
         if (!xfs_inobt_verify(bp)) {
                 trace_xfs_btree_corrupt(bp, _RET_IP_);
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                     bp->b_target->bt_mount, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
+                return;
         }
         xfs_btree_sblock_calc_crc(bp);
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 3a137e9f9a7d..5e7a38fa6ee6 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -42,7 +42,6 @@
 #include "xfs_bmap_util.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
-#include "xfs_dinode.h"
 #include "xfs_filestream.h"
 #include "xfs_cksum.h"
 #include "xfs_trace.h"
@@ -62,6 +61,8 @@ kmem_zone_t *xfs_inode_zone;
 
 STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
 
+STATIC int xfs_iunlink_remove(xfs_trans_t *, xfs_inode_t *);
+
 /*
  * helper function to extract extent size hint from inode
  */
@@ -1115,7 +1116,7 @@ xfs_bumplink(
 {
         xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-        ASSERT(ip->i_d.di_nlink > 0);
+        ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE));
         ip->i_d.di_nlink++;
         inc_nlink(VFS_I(ip));
         if ((ip->i_d.di_version == 1) &&
@@ -1165,10 +1166,7 @@ xfs_create(
         if (XFS_FORCED_SHUTDOWN(mp))
                 return XFS_ERROR(EIO);
 
-        if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-                prid = xfs_get_projid(dp);
-        else
-                prid = XFS_PROJID_DEFAULT;
+        prid = xfs_get_initial_prid(dp);
 
         /*
          * Make sure that we have allocated dquot(s) on disk.
@@ -1333,6 +1331,113 @@ xfs_create(
 }
 
 int
+xfs_create_tmpfile(
+        struct xfs_inode        *dp,
+        struct dentry           *dentry,
+        umode_t                 mode)
+{
+        struct xfs_mount        *mp = dp->i_mount;
+        struct xfs_inode        *ip = NULL;
+        struct xfs_trans        *tp = NULL;
+        int                     error;
+        uint                    cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
+        prid_t                  prid;
+        struct xfs_dquot        *udqp = NULL;
+        struct xfs_dquot        *gdqp = NULL;
+        struct xfs_dquot        *pdqp = NULL;
+        struct xfs_trans_res    *tres;
+        uint                    resblks;
+
+        if (XFS_FORCED_SHUTDOWN(mp))
+                return XFS_ERROR(EIO);
+
+        prid = xfs_get_initial_prid(dp);
+
+        /*
+         * Make sure that we have allocated dquot(s) on disk.
+         */
+        error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()),
+                                xfs_kgid_to_gid(current_fsgid()), prid,
+                                XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+                                &udqp, &gdqp, &pdqp);
+        if (error)
+                return error;
+
+        resblks = XFS_IALLOC_SPACE_RES(mp);
+        tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE_TMPFILE);
+
+        tres = &M_RES(mp)->tr_create_tmpfile;
+        error = xfs_trans_reserve(tp, tres, resblks, 0);
+        if (error == ENOSPC) {
+                /* No space at all so try a "no-allocation" reservation */
+                resblks = 0;
+                error = xfs_trans_reserve(tp, tres, 0, 0);
+        }
+        if (error) {
+                cancel_flags = 0;
+                goto out_trans_cancel;
+        }
+
+        error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
+                                                pdqp, resblks, 1, 0);
+        if (error)
+                goto out_trans_cancel;
+
+        error = xfs_dir_ialloc(&tp, dp, mode, 1, 0,
+                                prid, resblks > 0, &ip, NULL);
+        if (error) {
+                if (error == ENOSPC)
+                        goto out_trans_cancel;
+                goto out_trans_abort;
+        }
+
+        if (mp->m_flags & XFS_MOUNT_WSYNC)
+                xfs_trans_set_sync(tp);
+
+        /*
+         * Attach the dquot(s) to the inodes and modify them incore.
+         * These ids of the inode couldn't have changed since the new
+         * inode has been locked ever since it was created.
+         */
+        xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
+
+        ip->i_d.di_nlink--;
+        d_tmpfile(dentry, VFS_I(ip));
+        error = xfs_iunlink(tp, ip);
+        if (error)
+                goto out_trans_abort;
+
+        error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+        if (error)
+                goto out_release_inode;
+
+        xfs_qm_dqrele(udqp);
+        xfs_qm_dqrele(gdqp);
+        xfs_qm_dqrele(pdqp);
+
+        return 0;
+
+ out_trans_abort:
+        cancel_flags |= XFS_TRANS_ABORT;
+ out_trans_cancel:
+        xfs_trans_cancel(tp, cancel_flags);
+ out_release_inode:
+        /*
+         * Wait until after the current transaction is aborted to
+         * release the inode.  This prevents recursive transactions
+         * and deadlocks from xfs_inactive.
+         */
+        if (ip)
+                IRELE(ip);
+
+        xfs_qm_dqrele(udqp);
+        xfs_qm_dqrele(gdqp);
+        xfs_qm_dqrele(pdqp);
+
+        return error;
+}
+
+int
 xfs_link(
         xfs_inode_t             *tdp,
         xfs_inode_t             *sip,
@@ -1397,6 +1502,12 @@ xfs_link(
 
         xfs_bmap_init(&free_list, &first_block);
 
+        if (sip->i_d.di_nlink == 0) {
+                error = xfs_iunlink_remove(tp, sip);
+                if (error)
+                        goto abort_return;
+        }
+
         error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
                                         &first_block, &free_list, resblks);
         if (error)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 65e2350f449c..396cc1fafd0d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -20,6 +20,7 @@
 
 #include "xfs_inode_buf.h"
 #include "xfs_inode_fork.h"
+#include "xfs_dinode.h"
 
 /*
  * Kernel only inode definitions
@@ -192,6 +193,15 @@ xfs_set_projid(struct xfs_inode *ip,
         ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff);
 }
 
+static inline prid_t
+xfs_get_initial_prid(struct xfs_inode *dp)
+{
+        if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+                return xfs_get_projid(dp);
+
+        return XFS_PROJID_DEFAULT;
+}
+
 /*
  * In-core inode flags.
  */
@@ -323,6 +333,8 @@ int		xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
                            struct xfs_inode **ipp, struct xfs_name *ci_name);
 int             xfs_create(struct xfs_inode *dp, struct xfs_name *name,
                            umode_t mode, xfs_dev_t rdev, struct xfs_inode **ipp);
+int             xfs_create_tmpfile(struct xfs_inode *dp, struct dentry *dentry,
+                           umode_t mode);
 int             xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
                            struct xfs_inode *ip);
 int             xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
diff --git a/fs/xfs/xfs_inode_buf.c b/fs/xfs/xfs_inode_buf.c
index 4fc9f39dd89e..24e993996bdc 100644
--- a/fs/xfs/xfs_inode_buf.c
+++ b/fs/xfs/xfs_inode_buf.c
@@ -102,8 +102,7 @@ xfs_inode_buf_verify(
                         }
 
                         xfs_buf_ioerror(bp, EFSCORRUPTED);
-                        XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
-                                             mp, dip);
+                        xfs_verifier_error(bp);
 #ifdef DEBUG
                         xfs_alert(mp,
                                 "bad inode magic/vsn daddr %lld #%d (magic=%x)",
@@ -306,7 +305,7 @@ xfs_dinode_verify(
         if (!xfs_sb_version_hascrc(&mp->m_sb))
                 return false;
         if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
-                              offsetof(struct xfs_dinode, di_crc)))
+                              XFS_DINODE_CRC_OFF))
                 return false;
         if (be64_to_cpu(dip->di_ino) != ip->i_ino)
                 return false;
@@ -327,7 +326,7 @@ xfs_dinode_calc_crc(
 
         ASSERT(xfs_sb_version_hascrc(&mp->m_sb));
         crc = xfs_start_cksum((char *)dip, mp->m_sb.sb_inodesize,
-                              offsetof(struct xfs_dinode, di_crc));
+                              XFS_DINODE_CRC_OFF);
         dip->di_crc = xfs_end_cksum(crc);
 }
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 22d1cbea283d..3b80ebae05f5 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -128,7 +128,6 @@ xfs_iomap_write_direct(
         xfs_fsblock_t   firstfsb;
         xfs_extlen_t    extsz, temp;
         int             nimaps;
-        int             bmapi_flag;
         int             quota_flag;
         int             rt;
         xfs_trans_t     *tp;
@@ -200,18 +199,15 @@ xfs_iomap_write_direct(
 
         xfs_trans_ijoin(tp, ip, 0);
 
-        bmapi_flag = 0;
-        if (offset < XFS_ISIZE(ip) || extsz)
-                bmapi_flag |= XFS_BMAPI_PREALLOC;
-
         /*
          * From this point onwards we overwrite the imap pointer that the
          * caller gave to us.
          */
         xfs_bmap_init(&free_list, &firstfsb);
         nimaps = 1;
-        error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flag,
-                                &firstfsb, 0, imap, &nimaps, &free_list);
+        error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
+                                XFS_BMAPI_PREALLOC, &firstfsb, 0,
+                                imap, &nimaps, &free_list);
         if (error)
                 goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 9ddfb8190ca1..89b07e43ca28 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -39,6 +39,7 @@
 #include "xfs_da_btree.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_dinode.h"
+#include "xfs_trans_space.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -48,6 +49,18 @@
 #include <linux/fiemap.h>
 #include <linux/slab.h>
 
+/*
+ * Directories have different lock order w.r.t. mmap_sem compared to regular
+ * files. This is due to readdir potentially triggering page faults on a user
+ * buffer inside filldir(), and this happens with the ilock on the directory
+ * held. For regular files, the lock order is the other way around - the
+ * mmap_sem is taken during the page fault, and then we lock the ilock to do
+ * block mapping. Hence we need a different class for the directory ilock so
+ * that lockdep can tell them apart.
+ */
+static struct lock_class_key xfs_nondir_ilock_class;
+static struct lock_class_key xfs_dir_ilock_class;
+
 static int
 xfs_initxattrs(
         struct inode            *inode,
@@ -1034,6 +1047,19 @@ xfs_vn_fiemap(
         return 0;
 }
 
+STATIC int
+xfs_vn_tmpfile(
+        struct inode    *dir,
+        struct dentry   *dentry,
+        umode_t         mode)
+{
+        int             error;
+
+        error = xfs_create_tmpfile(XFS_I(dir), dentry, mode);
+
+        return -error;
+}
+
 static const struct inode_operations xfs_inode_operations = {
         .get_acl                = xfs_get_acl,
         .set_acl                = xfs_set_acl,
@@ -1072,6 +1098,7 @@ static const struct inode_operations xfs_dir_inode_operations = {
         .removexattr            = generic_removexattr,
         .listxattr              = xfs_vn_listxattr,
         .update_time            = xfs_vn_update_time,
+        .tmpfile                = xfs_vn_tmpfile,
 };
 
 static const struct inode_operations xfs_dir_ci_inode_operations = {
@@ -1099,6 +1126,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
         .removexattr            = generic_removexattr,
         .listxattr              = xfs_vn_listxattr,
         .update_time            = xfs_vn_update_time,
+        .tmpfile                = xfs_vn_tmpfile,
 };
 
 static const struct inode_operations xfs_symlink_inode_operations = {
@@ -1191,6 +1219,7 @@ xfs_setup_inode(
         xfs_diflags_to_iflags(inode, ip);
 
         ip->d_ops = ip->i_mount->m_nondir_inode_ops;
+        lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
         switch (inode->i_mode & S_IFMT) {
         case S_IFREG:
                 inode->i_op = &xfs_inode_operations;
@@ -1198,6 +1227,7 @@ xfs_setup_inode(
                 inode->i_mapping->a_ops = &xfs_address_space_operations;
                 break;
         case S_IFDIR:
+                lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
                 if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
                         inode->i_op = &xfs_dir_ci_inode_operations;
                 else
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index f9bb590acc0e..825249d2dfc1 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -119,6 +119,7 @@ typedef __uint64_t __psunsigned_t;
 #include "xfs_iops.h"
 #include "xfs_aops.h"
 #include "xfs_super.h"
+#include "xfs_cksum.h"
 #include "xfs_buf.h"
 #include "xfs_message.h"
 
@@ -178,6 +179,7 @@ typedef __uint64_t __psunsigned_t;
 #define ENOATTR         ENODATA         /* Attribute not found */
 #define EWRONGFS        EINVAL          /* Mount with wrong filesystem type */
 #define EFSCORRUPTED    EUCLEAN         /* Filesystem is corrupted */
+#define EFSBADCRC       EBADMSG         /* Bad CRC detected */
 
 #define SYNCHRONIZE()   barrier()
 #define __return_address __builtin_return_address(0)
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index b0f4ef77fa70..2c4004475e71 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -175,7 +175,7 @@ void	  xlog_iodone(struct xfs_buf *);
 struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket);
 void      xfs_log_ticket_put(struct xlog_ticket *ticket);
 
-int     xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
+void    xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
                                 xfs_lsn_t *commit_lsn, int flags);
 bool    xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 4ef6fdbced78..7e5455391176 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -499,13 +499,6 @@ xlog_cil_push(
         cil->xc_ctx = new_ctx;
 
         /*
-         * mirror the new sequence into the cil structure so that we can do
-         * unlocked checks against the current sequence in log forces without
-         * risking deferencing a freed context pointer.
-         */
-        cil->xc_current_sequence = new_ctx->sequence;
-
-        /*
          * The switch is now done, so we can drop the context lock and move out
          * of a shared context. We can't just go straight to the commit record,
          * though - we need to synchronise with previous and future commits so
@@ -523,8 +516,15 @@ xlog_cil_push(
          * Hence we need to add this context to the committing context list so
          * that higher sequences will wait for us to write out a commit record
          * before they do.
+         *
+         * xfs_log_force_lsn requires us to mirror the new sequence into the cil
+         * structure atomically with the addition of this sequence to the
+         * committing list. This also ensures that we can do unlocked checks
+         * against the current sequence in log forces without risking
+         * deferencing a freed context pointer.
          */
         spin_lock(&cil->xc_push_lock);
+        cil->xc_current_sequence = new_ctx->sequence;
         list_add(&ctx->committing, &cil->xc_committing);
         spin_unlock(&cil->xc_push_lock);
         up_write(&cil->xc_ctx_lock);
@@ -662,8 +662,14 @@ xlog_cil_push_background(
 
 }
 
+/*
+ * xlog_cil_push_now() is used to trigger an immediate CIL push to the sequence
+ * number that is passed. When it returns, the work will be queued for
+ * @push_seq, but it won't be completed. The caller is expected to do any
+ * waiting for push_seq to complete if it is required.
+ */
 static void
-xlog_cil_push_foreground(
+xlog_cil_push_now(
         struct xlog     *log,
         xfs_lsn_t       push_seq)
 {
@@ -688,10 +694,8 @@ xlog_cil_push_foreground(
         }
 
         cil->xc_push_seq = push_seq;
+        queue_work(log->l_mp->m_cil_workqueue, &cil->xc_push_work);
         spin_unlock(&cil->xc_push_lock);
-
-        /* do the push now */
-        xlog_cil_push(log);
 }
 
 bool
@@ -721,7 +725,7 @@ xlog_cil_empty(
  * background commit, returns without it held once background commits are
  * allowed again.
  */
-int
+void
 xfs_log_commit_cil(
         struct xfs_mount        *mp,
         struct xfs_trans        *tp,
@@ -767,7 +771,6 @@ xfs_log_commit_cil(
         xlog_cil_push_background(log);
 
         up_read(&cil->xc_ctx_lock);
-        return 0;
 }
 
 /*
@@ -796,7 +799,8 @@ xlog_cil_force_lsn(
          * xlog_cil_push() handles racing pushes for the same sequence,
          * so no need to deal with it here.
          */
-        xlog_cil_push_foreground(log, sequence);
+restart:
+        xlog_cil_push_now(log, sequence);
 
         /*
          * See if we can find a previous sequence still committing.
@@ -804,7 +808,6 @@ xlog_cil_force_lsn(
          * before allowing the force of push_seq to go ahead. Hence block
          * on commits for those as well.
          */
-restart:
         spin_lock(&cil->xc_push_lock);
         list_for_each_entry(ctx, &cil->xc_committing, committing) {
                 if (ctx->sequence > sequence)
@@ -822,6 +825,28 @@ restart:
                 /* found it! */
                 commit_lsn = ctx->commit_lsn;
         }
+
+        /*
+         * The call to xlog_cil_push_now() executes the push in the background.
+         * Hence by the time we have got here it our sequence may not have been
+         * pushed yet. This is true if the current sequence still matches the
+         * push sequence after the above wait loop and the CIL still contains
+         * dirty objects.
+         *
+         * When the push occurs, it will empty the CIL and
+         * atomically increment the currect sequence past the push sequence and
+         * move it into the committing list. Of course, if the CIL is clean at
+         * the time of the push, it won't have pushed the CIL at all, so in that
+         * case we should try the push for this sequence again from the start
+         * just in case.
+         */
+
+        if (sequence == cil->xc_current_sequence &&
+            !list_empty(&cil->xc_cil)) {
+                spin_unlock(&cil->xc_push_lock);
+                goto restart;
+        }
+
         spin_unlock(&cil->xc_push_lock);
         return commit_lsn;
 }
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index f96c05669a9e..993cb19e7d39 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -314,6 +314,9 @@ reread:
                 error = bp->b_error;
                 if (loud)
                         xfs_warn(mp, "SB validate failed with error %d.", error);
+                /* bad CRC means corrupted metadata */
+                if (error == EFSBADCRC)
+                        error = EFSCORRUPTED;
                 goto release_buf;
         }
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index a6a76b2b6a85..ec5ca65c6211 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -842,7 +842,7 @@ xfs_growfs_rt_alloc(
                 /*
                  * Reserve space & log for one extent added to the file.
                  */
-                error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growdata,
+                error = xfs_trans_reserve(tp, &M_RES(mp)->tr_growrtalloc,
                                           resblks, 0);
                 if (error)
                         goto error_cancel;
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index 1e116794bb66..0c0e41bbe4e3 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -288,6 +288,7 @@ xfs_mount_validate_sb(
             sbp->sb_inodelog < XFS_DINODE_MIN_LOG                       ||
             sbp->sb_inodelog > XFS_DINODE_MAX_LOG                       ||
             sbp->sb_inodesize != (1 << sbp->sb_inodelog)                ||
+            sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
             (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog)   ||
             (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)  ||
             (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)  ||
@@ -610,12 +611,11 @@ xfs_sb_read_verify(
                                                 XFS_SB_VERSION_5) ||
              dsb->sb_crc != 0)) {
 
-                if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                      offsetof(struct xfs_sb, sb_crc))) {
+                if (!xfs_buf_verify_cksum(bp, XFS_SB_CRC_OFF)) {
                         /* Only fail bad secondaries on a known V5 filesystem */
                         if (bp->b_bn == XFS_SB_DADDR ||
                             xfs_sb_version_hascrc(&mp->m_sb)) {
-                                error = EFSCORRUPTED;
+                                error = EFSBADCRC;
                                 goto out_error;
                         }
                 }
@@ -624,10 +624,9 @@ xfs_sb_read_verify(
 
 out_error:
         if (error) {
-                if (error == EFSCORRUPTED)
-                        XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                             mp, bp->b_addr);
                 xfs_buf_ioerror(bp, error);
+                if (error == EFSCORRUPTED || error == EFSBADCRC)
+                        xfs_verifier_error(bp);
         }
 }
 
@@ -662,9 +661,8 @@ xfs_sb_write_verify(
 
         error = xfs_sb_verify(bp, false);
         if (error) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
-                                     mp, bp->b_addr);
                 xfs_buf_ioerror(bp, error);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -674,8 +672,7 @@ xfs_sb_write_verify(
         if (bip)
                 XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-                         offsetof(struct xfs_sb, sb_crc));
+        xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_sb_buf_ops = {
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index 35061d4b614c..f7b2fe77c5a5 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -182,6 +182,8 @@ typedef struct xfs_sb {
         /* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
+#define XFS_SB_CRC_OFF          offsetof(struct xfs_sb, sb_crc)
+
 /*
  * Superblock - on disk version.  Must match the in core version above.
  * Must be padded to 64 bit alignment.
diff --git a/fs/xfs/xfs_shared.h b/fs/xfs/xfs_shared.h
index 8c5035a13df1..4484e5151395 100644
--- a/fs/xfs/xfs_shared.h
+++ b/fs/xfs/xfs_shared.h
@@ -104,7 +104,8 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 #define XFS_TRANS_SB_COUNT              41
 #define XFS_TRANS_CHECKPOINT            42
 #define XFS_TRANS_ICREATE               43
-#define XFS_TRANS_TYPE_MAX              43
+#define XFS_TRANS_CREATE_TMPFILE        44
+#define XFS_TRANS_TYPE_MAX              44
 /* new transaction types need to be reflected in xfs_logprint(8) */
 
 #define XFS_TRANS_TYPES \
@@ -112,6 +113,7 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;
         { XFS_TRANS_SETATTR_SIZE,       "SETATTR_SIZE" }, \
         { XFS_TRANS_INACTIVE,           "INACTIVE" }, \
         { XFS_TRANS_CREATE,             "CREATE" }, \
+        { XFS_TRANS_CREATE_TMPFILE,     "CREATE_TMPFILE" }, \
         { XFS_TRANS_CREATE_TRUNC,       "CREATE_TRUNC" }, \
         { XFS_TRANS_TRUNCATE_FILE,      "TRUNCATE_FILE" }, \
         { XFS_TRANS_REMOVE,             "REMOVE" }, \
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d971f4932b5d..205376776377 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -996,7 +996,7 @@ xfs_fs_evict_inode(
 
         trace_xfs_evict_inode(ip);
 
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
         XFS_STATS_INC(vn_rele);
         XFS_STATS_INC(vn_remove);
@@ -1197,6 +1197,7 @@ xfs_fs_remount(
         char                    *p;
         int                     error;
 
+        sync_filesystem(sb);
         while ((p = strsep(&options, ",")) != NULL) {
                 int token;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 14e58f2c96bd..52979aa90986 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -80,6 +80,10 @@ xfs_readlink_bmap(
                 if (error) {
                         xfs_buf_ioerror_alert(bp, __func__);
                         xfs_buf_relse(bp);
+
+                        /* bad CRC means corrupted metadata */
+                        if (error == EFSBADCRC)
+                                error = EFSCORRUPTED;
                         goto out;
                 }
                 byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
@@ -208,10 +212,7 @@ xfs_symlink(
                 return XFS_ERROR(ENAMETOOLONG);
 
         udqp = gdqp = NULL;
-        if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-                prid = xfs_get_projid(dp);
-        else
-                prid = XFS_PROJID_DEFAULT;
+        prid = xfs_get_initial_prid(dp);
 
         /*
          * Make sure that we have allocated dquot(s) on disk.
diff --git a/fs/xfs/xfs_symlink_remote.c b/fs/xfs/xfs_symlink_remote.c
index bf59a2b45f8c..9b32052ff65e 100644
--- a/fs/xfs/xfs_symlink_remote.c
+++ b/fs/xfs/xfs_symlink_remote.c
@@ -133,12 +133,13 @@ xfs_symlink_read_verify(
         if (!xfs_sb_version_hascrc(&mp->m_sb))
                 return;
 
-        if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
-                                  offsetof(struct xfs_dsymlink_hdr, sl_crc)) ||
-            !xfs_symlink_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
+        if (!xfs_buf_verify_cksum(bp, XFS_SYMLINK_CRC_OFF))
+                xfs_buf_ioerror(bp, EFSBADCRC);
+        else if (!xfs_symlink_verify(bp))
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
-        }
+
+        if (bp->b_error)
+                xfs_verifier_error(bp);
 }
 
 static void
@@ -153,8 +154,8 @@ xfs_symlink_write_verify(
                 return;
 
         if (!xfs_symlink_verify(bp)) {
-                XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
                 xfs_buf_ioerror(bp, EFSCORRUPTED);
+                xfs_verifier_error(bp);
                 return;
         }
 
@@ -162,8 +163,7 @@ xfs_symlink_write_verify(
                 struct xfs_dsymlink_hdr *dsl = bp->b_addr;
                 dsl->sl_lsn = cpu_to_be64(bip->bli_item.li_lsn);
         }
-        xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
-                         offsetof(struct xfs_dsymlink_hdr, sl_crc));
+        xfs_buf_update_cksum(bp, XFS_SYMLINK_CRC_OFF);
 }
 
 const struct xfs_buf_ops xfs_symlink_buf_ops = {
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 425dfa45b9a0..a4ae41c179a8 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -603,6 +603,7 @@ DEFINE_INODE_EVENT(xfs_readlink);
 DEFINE_INODE_EVENT(xfs_inactive_symlink);
 DEFINE_INODE_EVENT(xfs_alloc_file_space);
 DEFINE_INODE_EVENT(xfs_free_file_space);
+DEFINE_INODE_EVENT(xfs_collapse_file_space);
 DEFINE_INODE_EVENT(xfs_readdir);
 #ifdef CONFIG_XFS_POSIX_ACL
 DEFINE_INODE_EVENT(xfs_get_acl);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index c812c5c060de..54a57326d85b 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -887,12 +887,7 @@ xfs_trans_commit(
                 xfs_trans_apply_sb_deltas(tp);
         xfs_trans_apply_dquot_deltas(tp);
 
-        error = xfs_log_commit_cil(mp, tp, &commit_lsn, flags);
-        if (error == ENOMEM) {
-                xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
-                error = XFS_ERROR(EIO);
-                goto out_unreserve;
-        }
+        xfs_log_commit_cil(mp, tp, &commit_lsn, flags);
 
         current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
         xfs_trans_free(tp);
@@ -902,10 +897,7 @@ xfs_trans_commit(
          * log out now and wait for it.
          */
         if (sync) {
-                if (!error) {
-                        error = _xfs_log_force_lsn(mp, commit_lsn,
-                                      XFS_LOG_SYNC, NULL);
-                }
+                error = _xfs_log_force_lsn(mp, commit_lsn, XFS_LOG_SYNC, NULL);
                 XFS_STATS_INC(xs_trans_sync);
         } else {
                 XFS_STATS_INC(xs_trans_async);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 647b6f1d8923..b8eef0549f3f 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -275,6 +275,10 @@ xfs_trans_read_buf_map(
                         XFS_BUF_UNDONE(bp);
                         xfs_buf_stale(bp);
                         xfs_buf_relse(bp);
+
+                        /* bad CRC means corrupted metadata */
+                        if (error == EFSBADCRC)
+                                error = EFSCORRUPTED;
                         return error;
                 }
 #ifdef DEBUG
@@ -338,6 +342,9 @@ xfs_trans_read_buf_map(
                                 if (tp->t_flags & XFS_TRANS_DIRTY)
                                         xfs_force_shutdown(tp->t_mountp,
                                                         SHUTDOWN_META_IO_ERROR);
+                                /* bad CRC means corrupted metadata */
+                                if (error == EFSBADCRC)
+                                        error = EFSCORRUPTED;
                                 return error;
                         }
                 }
@@ -375,6 +382,10 @@ xfs_trans_read_buf_map(
                 if (tp->t_flags & XFS_TRANS_DIRTY)
                         xfs_force_shutdown(tp->t_mountp, SHUTDOWN_META_IO_ERROR);
                 xfs_buf_relse(bp);
+
+                /* bad CRC means corrupted metadata */
+                if (error == EFSBADCRC)
+                        error = EFSCORRUPTED;
                 return error;
         }
 #ifdef DEBUG
diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c
index 2ffd3e331b49..ae368165244d 100644
--- a/fs/xfs/xfs_trans_resv.c
+++ b/fs/xfs/xfs_trans_resv.c
@@ -81,20 +81,28 @@ xfs_calc_buf_res(
  * on disk. Hence we need an inode reservation function that calculates all this
  * correctly. So, we log:
  *
- * - log op headers for object
+ * - 4 log op headers for object
+ *      - for the ilf, the inode core and 2 forks
  * - inode log format object
- * - the entire inode contents (core + 2 forks)
- * - two bmap btree block headers
+ * - the inode core
+ * - two inode forks containing bmap btree root blocks.
+ *      - the btree data contained by both forks will fit into the inode size,
+ *        hence when combined with the inode core above, we have a total of the
+ *        actual inode size.
+ *      - the BMBT headers need to be accounted separately, as they are
+ *        additional to the records and pointers that fit inside the inode
+ *        forks.
  */
 STATIC uint
 xfs_calc_inode_res(
         struct xfs_mount        *mp,
         uint                    ninodes)
 {
-        return ninodes * (sizeof(struct xlog_op_header) +
-                          sizeof(struct xfs_inode_log_format) +
-                          mp->m_sb.sb_inodesize +
-                          2 * XFS_BMBT_BLOCK_LEN(mp));
+        return ninodes *
+                (4 * sizeof(struct xlog_op_header) +
+                 sizeof(struct xfs_inode_log_format) +
+                 mp->m_sb.sb_inodesize +
+                 2 * XFS_BMBT_BLOCK_LEN(mp));
 }
 
 /*
@@ -204,6 +212,19 @@ xfs_calc_rename_reservation(
 }
 
 /*
+ * For removing an inode from unlinked list at first, we can modify:
+ *    the agi hash list and counters: sector size
+ *    the on disk inode before ours in the agi hash list: inode cluster size
+ */
+STATIC uint
+xfs_calc_iunlink_remove_reservation(
+        struct xfs_mount        *mp)
+{
+        return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+               max_t(uint, XFS_FSB_TO_B(mp, 1), mp->m_inode_cluster_size);
+}
+
+/*
  * For creating a link to an inode:
  *    the parent directory inode: inode size
  *    the linked inode: inode size
@@ -220,6 +241,7 @@ xfs_calc_link_reservation(
         struct xfs_mount        *mp)
 {
         return XFS_DQUOT_LOGRES(mp) +
+                xfs_calc_iunlink_remove_reservation(mp) +
                 MAX((xfs_calc_inode_res(mp, 2) +
                      xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
                                       XFS_FSB_TO_B(mp, 1))),
@@ -229,6 +251,18 @@ xfs_calc_link_reservation(
 }
 
 /*
+ * For adding an inode to unlinked list we can modify:
+ *    the agi hash list: sector size
+ *    the unlinked inode: inode size
+ */
+STATIC uint
+xfs_calc_iunlink_add_reservation(xfs_mount_t *mp)
+{
+        return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+                xfs_calc_inode_res(mp, 1);
+}
+
+/*
  * For removing a directory entry we can modify:
  *    the parent directory inode: inode size
  *    the removed inode: inode size
@@ -245,10 +279,11 @@ xfs_calc_remove_reservation(
         struct xfs_mount        *mp)
 {
         return XFS_DQUOT_LOGRES(mp) +
-                MAX((xfs_calc_inode_res(mp, 2) +
+                xfs_calc_iunlink_add_reservation(mp) +
+                MAX((xfs_calc_inode_res(mp, 1) +
                      xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
                                       XFS_FSB_TO_B(mp, 1))),
-                    (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
+                    (xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
                      xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 2),
                                       XFS_FSB_TO_B(mp, 1))));
 }
@@ -343,6 +378,20 @@ xfs_calc_create_reservation(
 
 }
 
+STATIC uint
+xfs_calc_create_tmpfile_reservation(
+        struct xfs_mount        *mp)
+{
+        uint    res = XFS_DQUOT_LOGRES(mp);
+
+        if (xfs_sb_version_hascrc(&mp->m_sb))
+                res += xfs_calc_icreate_resv_alloc(mp);
+        else
+                res += xfs_calc_create_resv_alloc(mp);
+
+        return res + xfs_calc_iunlink_add_reservation(mp);
+}
+
 /*
  * Making a new directory is the same as creating a new file.
  */
@@ -383,9 +432,9 @@ xfs_calc_ifree_reservation(
 {
         return XFS_DQUOT_LOGRES(mp) +
                 xfs_calc_inode_res(mp, 1) +
-                xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+                xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
                 xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
-                max_t(uint, XFS_FSB_TO_B(mp, 1), mp->m_inode_cluster_size) +
+                xfs_calc_iunlink_remove_reservation(mp) +
                 xfs_calc_buf_res(1, 0) +
                 xfs_calc_buf_res(2 + mp->m_ialloc_blks +
                                  mp->m_in_maxlevels, 0) +
@@ -644,15 +693,14 @@ xfs_calc_qm_setqlim_reservation(
 
 /*
  * Allocating quota on disk if needed.
- *      the write transaction log space: M_RES(mp)->tr_write.tr_logres
+ *      the write transaction log space for quota file extent allocation
  *      the unit of quota allocation: one system block size
  */
 STATIC uint
 xfs_calc_qm_dqalloc_reservation(
         struct xfs_mount        *mp)
 {
-        ASSERT(M_RES(mp)->tr_write.tr_logres);
-        return M_RES(mp)->tr_write.tr_logres +
+        return xfs_calc_write_reservation(mp) +
                 xfs_calc_buf_res(1,
                         XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) - 1);
 }
@@ -729,6 +777,11 @@ xfs_trans_resv_calc(
         resp->tr_create.tr_logcount = XFS_CREATE_LOG_COUNT;
         resp->tr_create.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
 
+        resp->tr_create_tmpfile.tr_logres =
+                        xfs_calc_create_tmpfile_reservation(mp);
+        resp->tr_create_tmpfile.tr_logcount = XFS_CREATE_TMPFILE_LOG_COUNT;
+        resp->tr_create_tmpfile.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
+
         resp->tr_mkdir.tr_logres = xfs_calc_mkdir_reservation(mp);
         resp->tr_mkdir.tr_logcount = XFS_MKDIR_LOG_COUNT;
         resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
@@ -784,7 +837,6 @@ xfs_trans_resv_calc(
         /* The following transaction are logged in logical format */
         resp->tr_ichange.tr_logres = xfs_calc_ichange_reservation(mp);
         resp->tr_growdata.tr_logres = xfs_calc_growdata_reservation(mp);
-        resp->tr_swrite.tr_logres = xfs_calc_swrite_reservation(mp);
         resp->tr_fsyncts.tr_logres = xfs_calc_swrite_reservation(mp);
         resp->tr_writeid.tr_logres = xfs_calc_writeid_reservation(mp);
         resp->tr_attrsetrt.tr_logres = xfs_calc_attrsetrt_reservation(mp);
diff --git a/fs/xfs/xfs_trans_resv.h b/fs/xfs/xfs_trans_resv.h
index de7de9aaad8a..1097d14cd583 100644
--- a/fs/xfs/xfs_trans_resv.h
+++ b/fs/xfs/xfs_trans_resv.h
@@ -38,11 +38,11 @@ struct xfs_trans_resv {
         struct xfs_trans_res    tr_remove;      /* unlink trans */
         struct xfs_trans_res    tr_symlink;     /* symlink trans */
         struct xfs_trans_res    tr_create;      /* create trans */
+        struct xfs_trans_res    tr_create_tmpfile; /* create O_TMPFILE trans */
         struct xfs_trans_res    tr_mkdir;       /* mkdir trans */
         struct xfs_trans_res    tr_ifree;       /* inode free trans */
         struct xfs_trans_res    tr_ichange;     /* inode update trans */
         struct xfs_trans_res    tr_growdata;    /* fs data section grow trans */
-        struct xfs_trans_res    tr_swrite;      /* sync write inode trans */
         struct xfs_trans_res    tr_addafork;    /* add inode attr fork trans */
         struct xfs_trans_res    tr_writeid;     /* write setuid/setgid file */
         struct xfs_trans_res    tr_attrinval;   /* attr fork buffer
@@ -100,6 +100,7 @@ struct xfs_trans_resv {
 #define XFS_ITRUNCATE_LOG_COUNT         2
 #define XFS_INACTIVE_LOG_COUNT          2
 #define XFS_CREATE_LOG_COUNT            2
+#define XFS_CREATE_TMPFILE_LOG_COUNT    2
 #define XFS_MKDIR_LOG_COUNT             3
 #define XFS_SYMLINK_LOG_COUNT           3
 #define XFS_REMOVE_LOG_COUNT            2