diff --git a/.gitignore b/.gitignore
index ce57b79670a5cf..9ac91060ea6437 100644
--- a/.gitignore
+++ b/.gitignore
@@ -52,6 +52,11 @@ Module.symvers
 #
 /debian/
 
+#
+# tar directory (make tar*-pkg)
+#
+/tar-install/
+
 #
 # git files that we don't want to ignore even it they are dot-files
 #
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 6f9157f16725af..2c4cc42006e8c9 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -74,3 +74,9 @@ Date:		March 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
 Description:
 		 Controls the memory footprint used by f2fs.
+
+What:		/sys/fs/f2fs/<disk>/trim_sections
+Date:		February 2015
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the trimming rate in batch mode.
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index e0950c483c2244..dac11d7fef2744 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -106,6 +106,8 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
                        Default value for this option is on. So garbage
                        collection is on by default.
 disable_roll_forward   Disable the roll-forward recovery routine
+norecovery             Disable the roll-forward recovery routine, mounted read-
+                       only (i.e., -o ro,disable_roll_forward)
 discard                Issue discard/TRIM commands when a segment is cleaned.
 no_heap                Disable heap-style segment allocation which finds free
                        segments for data from the beginning of main area, while
@@ -197,6 +199,10 @@ Files in /sys/fs/f2fs/<devname>
 			      checkpoint is triggered, and issued during the
 			      checkpoint. By default, it is disabled with 0.
 
+ trim_sections                This parameter controls the number of sections
+                              to be trimmed out in batch mode when FITRIM
+                              conducts. 32 sections is set by default.
+
  ipu_policy                   This parameter controls the policy of in-place
                               updates in f2fs. There are five policies:
                                0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index c49cd7e796e724..682a59fabe3fce 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -24,11 +24,6 @@ focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
 "exactly once" semantics and better control and throttling of the
 resources allocated for each client.
 
-Other NFSv4.1 features, Parallel NFS operations in particular,
-are still under development out of tree.
-See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
-for more information.
-
 The table below, taken from the NFSv4.1 document, lists
 the operations that are mandatory to implement (REQ), optional
 (OPT), and NFSv4.0 operations that are required not to implement (MNI)
@@ -43,9 +38,7 @@ The OPTIONAL features identified and their abbreviations are as follows:
 The following abbreviations indicate the linux server implementation status.
 	I	Implemented NFSv4.1 operations.
 	NS	Not Supported.
-	NS*	unimplemented optional feature.
-	P	pNFS features implemented out of tree.
-	PNS	pNFS features that are not supported yet (out of tree).
+	NS*	Unimplemented optional feature.
 
 Operations
 
@@ -70,13 +63,13 @@ I  | DESTROY_SESSION      | REQ        |              | Section 18.37  |
 I  | EXCHANGE_ID          | REQ        |              | Section 18.35  |
 I  | FREE_STATEID         | REQ        |              | Section 18.38  |
    | GETATTR              | REQ        |              | Section 18.7   |
-P  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
-P  | GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
+I  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
+NS*| GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
    | GETFH                | REQ        |              | Section 18.8   |
 NS*| GET_DIR_DELEGATION   | OPT        | DDELG (REQ)  | Section 18.39  |
-P  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
-P  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
-P  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
+I  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
+I  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
+I  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
    | LINK                 | OPT        |              | Section 18.9   |
    | LOCK                 | REQ        |              | Section 18.10  |
    | LOCKT                | REQ        |              | Section 18.11  |
@@ -122,9 +115,9 @@ Callback Operations
    |                         | MNI       | or OPT)     |               |
    +-------------------------+-----------+-------------+---------------+
    | CB_GETATTR              | OPT       | FDELG (REQ) | Section 20.1  |
-P  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
+I  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
 NS*| CB_NOTIFY               | OPT       | DDELG (REQ) | Section 20.4  |
-P  | CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
+NS*| CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
 NS*| CB_NOTIFY_LOCK          | OPT       |             | Section 20.11 |
 NS*| CB_PUSH_DELEG           | OPT       | FDELG (OPT) | Section 20.5  |
    | CB_RECALL               | OPT       | FDELG,      | Section 20.2  |
diff --git a/Documentation/filesystems/nfs/pnfs-block-server.txt b/Documentation/filesystems/nfs/pnfs-block-server.txt
new file mode 100644
index 00000000000000..2143673cf1544b
--- /dev/null
+++ b/Documentation/filesystems/nfs/pnfs-block-server.txt
@@ -0,0 +1,37 @@
+pNFS block layout server user guide
+
+The Linux NFS server now supports the pNFS block layout extension.  In this
+case the NFS server acts as Metadata Server (MDS) for pNFS, which in addition
+to handling all the metadata access to the NFS export also hands out layouts
+to the clients to directly access the underlying block devices that are
+shared with the client.
+
+To use pNFS block layouts with with the Linux NFS server the exported file
+system needs to support the pNFS block layouts (currently just XFS), and the
+file system must sit on shared storage (typically iSCSI) that is accessible
+to the clients in addition to the MDS.  As of now the file system needs to
+sit directly on the exported volume, striping or concatenation of
+volumes on the MDS and clients is not supported yet.
+
+On the server, pNFS block volume support is automatically if the file system
+support it.  On the client make sure the kernel has the CONFIG_PNFS_BLOCK
+option enabled, the blkmapd daemon from nfs-utils is running, and the
+file system is mounted using the NFSv4.1 protocol version (mount -o vers=4.1).
+
+If the nfsd server needs to fence a non-responding client it calls
+/sbin/nfsd-recall-failed with the first argument set to the IP address of
+the client, and the second argument set to the device node without the /dev
+prefix for the file system to be fenced. Below is an example file that shows
+how to translate the device into a serial number from SCSI EVPD 0x80:
+
+cat > /sbin/nfsd-recall-failed << EOF
+#!/bin/sh
+
+CLIENT="$1"
+DEV="/dev/$2"
+EVPD=`sg_inq --page=0x80 ${DEV} | \
+	grep "Unit serial number:" | \
+	awk -F ': ' '{print $2}'`
+
+echo "fencing client ${CLIENT} serial ${EVPD}" >> /var/log/pnfsd-fence.log
+EOF
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index cf8fc2f0b34bbb..a07ba61662ed79 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -145,6 +145,8 @@ Table 1-1: Process specific entries in /proc
  stack		Report full stack trace, enable via CONFIG_STACKTRACE
  smaps		a extension based on maps, showing the memory consumption of
 		each mapping and flags associated with it
+ numa_maps	an extension based on maps, showing the memory locality and
+		binding policy as well as mem usage (in pages) of each mapping.
 ..............................................................................
 
 For example, to get the status information of a process, all you have to do is
@@ -489,12 +491,47 @@ To clear the bits for the file mapped pages associated with the process
 To clear the soft-dirty bit
     > echo 4 > /proc/PID/clear_refs
 
+To reset the peak resident set size ("high water mark") to the process's
+current value:
+    > echo 5 > /proc/PID/clear_refs
+
 Any other value written to /proc/PID/clear_refs will have no effect.
 
 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
 using /proc/kpageflags and number of times a page is mapped using
 /proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 
+The /proc/pid/numa_maps is an extension based on maps, showing the memory
+locality and binding policy, as well as the memory usage (in pages) of
+each mapping. The output follows a general format where mapping details get
+summarized separated by blank spaces, one mapping per each file line:
+
+address   policy    mapping details
+
+00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
+00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
+320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
+320698b000 default file=/lib64/libc-2.12.so
+3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
+3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
+7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
+7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
+7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
+7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
+7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
+
+Where:
+"address" is the starting address for the mapping;
+"policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
+"mapping details" summarizes mapping data such as mapping type, page usage counters,
+node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
+size, in KB, that is backing the mapping up.
+
 1.2 Kernel data
 ---------------
 
diff --git a/Documentation/filesystems/xip.txt b/Documentation/filesystems/xip.txt
index 0466ee569278e4..b77472949ede03 100644
--- a/Documentation/filesystems/xip.txt
+++ b/Documentation/filesystems/xip.txt
@@ -28,12 +28,15 @@ Implementation
 Execute-in-place is implemented in three steps: block device operation,
 address space operation, and file operations.
 
-A block device operation named direct_access is used to retrieve a
-reference (pointer) to a block on-disk. The reference is supposed to be
-cpu-addressable, physical address and remain valid until the release operation
-is performed. A struct block_device reference is used to address the device,
-and a sector_t argument is used to identify the individual block. As an
-alternative, memory technology devices can be used for this.
+A block device operation named direct_access is used to translate the
+block device sector number to a page frame number (pfn) that identifies
+the physical page for the memory.  It also returns a kernel virtual
+address that can be used to access the memory.
+
+The direct_access method takes a 'size' parameter that indicates the
+number of bytes being requested.  The function should return the number
+of bytes that can be contiguously accessed at that offset.  It may also
+return a negative errno if an error occurs.
 
 The block device operation is optional, these block devices support it as of
 today:
diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt
index 8e1ddec2c78a2b..ae57b9ea0d4169 100644
--- a/Documentation/nommu-mmap.txt
+++ b/Documentation/nommu-mmap.txt
@@ -43,12 +43,12 @@ and it's also much more restricted in the latter case:
            even if this was created by another process.
 
          - If possible, the file mapping will be directly on the backing device
-           if the backing device has the BDI_CAP_MAP_DIRECT capability and
+           if the backing device has the NOMMU_MAP_DIRECT capability and
            appropriate mapping protection capabilities. Ramfs, romfs, cramfs
            and mtd might all permit this.
 
 	 - If the backing device device can't or won't permit direct sharing,
-           but does have the BDI_CAP_MAP_COPY capability, then a copy of the
+           but does have the NOMMU_MAP_COPY capability, then a copy of the
            appropriate bit of the file will be read into a contiguous bit of
            memory and any extraneous space beyond the EOF will be cleared
 
@@ -220,7 +220,7 @@ directly (can't be copied).
 
 The file->f_op->mmap() operation will be called to actually inaugurate the
 mapping. It can be rejected at that point. Returning the ENOSYS error will
-cause the mapping to be copied instead if BDI_CAP_MAP_COPY is specified.
+cause the mapping to be copied instead if NOMMU_MAP_COPY is specified.
 
 The vm_ops->close() routine will be invoked when the last mapping on a chardev
 is removed. An existing mapping will be shared, partially or not, if possible
@@ -232,7 +232,7 @@ want to handle it, despite the fact it's got an operation. For instance, it
 might try directing the call to a secondary driver which turns out not to
 implement it. Such is the case for the framebuffer driver which attempts to
 direct the call to the device-specific driver. Under such circumstances, the
-mapping request will be rejected if BDI_CAP_MAP_COPY is not specified, and a
+mapping request will be rejected if NOMMU_MAP_COPY is not specified, and a
 copy mapped otherwise.
 
 IMPORTANT NOTE:
diff --git a/MAINTAINERS b/MAINTAINERS
index 22999654195afb..482bfc55397d4a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6642,9 +6642,10 @@ F:	include/uapi/linux/netrom.h
 F:	net/netrom/
 
 NETWORK BLOCK DEVICE (NBD)
-M:	Paul Clements <Paul.Clements@steeleye.com>
+M:	Markus Pargmann <mpa@pengutronix.de>
 S:	Maintained
 L:	nbd-general@lists.sourceforge.net
+T:	git git://git.pengutronix.de/git/mpa/linux-nbd.git
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/linux/nbd.h
@@ -10690,6 +10691,7 @@ F:	drivers/pci/*xen*
 
 XEN BLOCK SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+M:	Roger Pau Monné <roger.pau@citrix.com>
 L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/block/xen-blkback/*
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 48bbea6898b30c..d5b98ab514bbda 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -27,8 +27,6 @@ struct thread_info {
 	int bpt_nsaved;
 	unsigned long bpt_addr[2];		/* breakpoint handling  */
 	unsigned int bpt_insn[2];
-
-	struct restart_block	restart_block;
 };
 
 /*
@@ -40,9 +38,6 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 6cec2881acbf2f..8dbfb15f174505 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -150,7 +150,7 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs)
 	struct switch_stack *sw = (struct switch_stack *)regs - 1;
 	long i, err = __get_user(regs->pc, &sc->sc_pc);
 
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sw->r26 = (unsigned long) ret_from_sys_call;
 
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 02bc5ec0fb2e4e..1163a1838ac1ae 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -46,7 +46,6 @@ struct thread_info {
 	struct exec_domain *exec_domain;/* execution domain */
 	__u32 cpu;			/* current CPU */
 	unsigned long thr_ptr;		/* TLS ptr */
-	struct restart_block restart_block;
 };
 
 /*
@@ -62,9 +61,6 @@ struct thread_info {
 	.cpu        = 0,			\
 	.preempt_count  = INIT_PREEMPT_COUNT,	\
 	.addr_limit = KERNEL_DS,		\
-	.restart_block  = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info    (init_thread_union.thread_info)
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index cb3142a2d40b2b..114234e83caa25 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -104,7 +104,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	struct pt_regs *regs = current_pt_regs();
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* Since we stacked the signal on a word boundary,
 	 * then 'sp' should be word aligned here.  If it's
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 18dbc82f85e55d..423a5ac09d3a77 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -257,7 +257,10 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 /* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
-#define pmd_mknotpresent(pmd)	(__pmd(0))
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return __pmd(0);
+}
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index d890e41f55207b..72812a1f3d1cc9 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -68,7 +68,6 @@ struct thread_info {
 #ifdef CONFIG_ARM_THUMBEE
 	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
@@ -81,9 +80,6 @@ struct thread_info {
 	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
 			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
 			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 8aa6f1b87c9e2b..023ac905e4c38c 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -191,7 +191,7 @@ asmlinkage int sys_sigreturn(struct pt_regs *regs)
 	struct sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
@@ -221,7 +221,7 @@ asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 459bf8e5320866..702e1e6a0d80f9 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -48,7 +48,6 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* address limit */
 	struct task_struct	*task;		/* main task structure */
 	struct exec_domain	*exec_domain;	/* execution domain */
-	struct restart_block	restart_block;
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
 	int			cpu;		/* cpu */
 };
@@ -60,9 +59,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 6fa792137eda6a..660ccf9f7524cb 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -131,7 +131,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 128-bit boundary, then 'sp' should
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index e299de396e9b33..c20a300e22137f 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -347,7 +347,7 @@ asmlinkage int compat_sys_sigreturn(struct pt_regs *regs)
 	struct compat_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
@@ -381,7 +381,7 @@ asmlinkage int compat_sys_rt_sigreturn(struct pt_regs *regs)
 	struct compat_rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
diff --git a/arch/avr32/include/asm/thread_info.h b/arch/avr32/include/asm/thread_info.h
index a978f3fe7c25a2..d56afa99a5149c 100644
--- a/arch/avr32/include/asm/thread_info.h
+++ b/arch/avr32/include/asm/thread_info.h
@@ -30,7 +30,6 @@ struct thread_info {
 						   saved by debug handler
 						   when setting up
 						   trampoline */
-	struct restart_block	restart_block;
 	__u8			supervisor_stack[0];
 };
 
@@ -41,9 +40,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.cpu		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall				\
-	}								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/avr32/kernel/asm-offsets.c b/arch/avr32/kernel/asm-offsets.c
index d6a8193a1d2f09..e41c84516e5d1e 100644
--- a/arch/avr32/kernel/asm-offsets.c
+++ b/arch/avr32/kernel/asm-offsets.c
@@ -18,7 +18,6 @@ void foo(void)
 	OFFSET(TI_preempt_count, thread_info, preempt_count);
 	OFFSET(TI_rar_saved, thread_info, rar_saved);
 	OFFSET(TI_rsr_saved, thread_info, rsr_saved);
-	OFFSET(TI_restart_block, thread_info, restart_block);
 	BLANK();
 	OFFSET(TSK_active_mm, task_struct, active_mm);
 	BLANK();
diff --git a/arch/avr32/kernel/signal.c b/arch/avr32/kernel/signal.c
index d309fbcc3bd641..8f1c63b9b9839b 100644
--- a/arch/avr32/kernel/signal.c
+++ b/arch/avr32/kernel/signal.c
@@ -69,7 +69,7 @@ asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
 	sigset_t set;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *)regs->sp;
 	pr_debug("SIG return: frame = %p\n", frame);
diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h
index 55f473bdad361a..57c3a8bd583d46 100644
--- a/arch/blackfin/include/asm/thread_info.h
+++ b/arch/blackfin/include/asm/thread_info.h
@@ -42,7 +42,6 @@ struct thread_info {
 	int cpu;		/* cpu we're on */
 	int preempt_count;	/* 0 => preemptable, <0 => BUG */
 	mm_segment_t addr_limit;	/* address limit */
-	struct restart_block restart_block;
 #ifndef CONFIG_SMP
 	struct l1_scratch_task_info l1_task_info;
 #endif
@@ -58,9 +57,6 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
diff --git a/arch/blackfin/kernel/signal.c b/arch/blackfin/kernel/signal.c
index ef275571d88533..f2a8b5493bd328 100644
--- a/arch/blackfin/kernel/signal.c
+++ b/arch/blackfin/kernel/signal.c
@@ -44,7 +44,7 @@ rt_restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *p
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 #define RESTORE(x) err |= __get_user(regs->x, &sc->sc_##x)
 
diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h
index d4e9ef87076dbe..584e253f321799 100644
--- a/arch/c6x/include/asm/thread_info.h
+++ b/arch/c6x/include/asm/thread_info.h
@@ -45,7 +45,6 @@ struct thread_info {
 	int			cpu;		/* cpu we're on */
 	int			preempt_count;	/* 0 = preemptable, <0 = BUG */
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block	restart_block;
 };
 
 /*
@@ -61,9 +60,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c
index fe68226f6c4d60..3c4bb5a5c3820a 100644
--- a/arch/c6x/kernel/signal.c
+++ b/arch/c6x/kernel/signal.c
@@ -68,7 +68,7 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs)
 	sigset_t set;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a dword boundary,
diff --git a/arch/cris/arch-v10/kernel/signal.c b/arch/cris/arch-v10/kernel/signal.c
index 9b32d338838b75..74d7ba35120d31 100644
--- a/arch/cris/arch-v10/kernel/signal.c
+++ b/arch/cris/arch-v10/kernel/signal.c
@@ -67,7 +67,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	unsigned long old_usp;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore the regs from &sc->regs (same as sc, since regs is first)
 	 * (sc is already checked for VERIFY_READ since the sigframe was
diff --git a/arch/cris/arch-v32/kernel/signal.c b/arch/cris/arch-v32/kernel/signal.c
index 78ce3b1c9bcb05..870e3e06931852 100644
--- a/arch/cris/arch-v32/kernel/signal.c
+++ b/arch/cris/arch-v32/kernel/signal.c
@@ -59,7 +59,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	unsigned long old_usp;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Restore the registers from &sc->regs. sc is already checked
diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h
index 55dede18c032e3..7286db5ed90e38 100644
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@@ -38,7 +38,6 @@ struct thread_info {
 					 	   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 };
 
@@ -56,9 +55,6 @@ struct thread_info {
 	.cpu		= 0,				\
 	.preempt_count	= INIT_PREEMPT_COUNT,		\
 	.addr_limit	= KERNEL_DS,			\
-	.restart_block = {				\
-		       .fn = do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/frv/include/asm/string.h b/arch/frv/include/asm/string.h
index 5ed310f64b7e95..1f6c3599043913 100644
--- a/arch/frv/include/asm/string.h
+++ b/arch/frv/include/asm/string.h
@@ -33,7 +33,6 @@ extern void *memcpy(void *, const void *, __kernel_size_t);
 #define __HAVE_ARCH_STRNCAT 1
 #define __HAVE_ARCH_STRCMP 1
 #define __HAVE_ARCH_STRNCMP 1
-#define __HAVE_ARCH_STRNICMP 1
 #define __HAVE_ARCH_STRCHR 1
 #define __HAVE_ARCH_STRRCHR 1
 #define __HAVE_ARCH_STRSTR 1
diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h
index af29e17c01814a..6b917f1c295543 100644
--- a/arch/frv/include/asm/thread_info.h
+++ b/arch/frv/include/asm/thread_info.h
@@ -41,7 +41,6 @@ struct thread_info {
 						 * 0-0xBFFFFFFF for user-thead
 						 * 0-0xFFFFFFFF for kernel-thread
 						 */
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -65,9 +64,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/frv/kernel/asm-offsets.c b/arch/frv/kernel/asm-offsets.c
index 9de96843a27808..446e89d500cc4f 100644
--- a/arch/frv/kernel/asm-offsets.c
+++ b/arch/frv/kernel/asm-offsets.c
@@ -40,7 +40,6 @@ void foo(void)
 	OFFSET(TI_CPU,			thread_info, cpu);
 	OFFSET(TI_PREEMPT_COUNT,	thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT,		thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK,	thread_info, restart_block);
 	BLANK();
 
 	/* offsets into register file storage */
diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c
index dc3d59de087046..336713ab47454f 100644
--- a/arch/frv/kernel/signal.c
+++ b/arch/frv/kernel/signal.c
@@ -62,7 +62,7 @@ static int restore_sigcontext(struct sigcontext __user *sc, int *_gr8)
 	unsigned long tbr, psr;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	tbr = user->i.tbr;
 	psr = user->i.psr;
diff --git a/arch/frv/mm/extable.c b/arch/frv/mm/extable.c
index 2fb9b3ab57b9d6..8863d6c1df6e40 100644
--- a/arch/frv/mm/extable.c
+++ b/arch/frv/mm/extable.c
@@ -10,29 +10,6 @@ extern const void __memset_end, __memset_user_error_lr, __memset_user_error_hand
 extern const void __memcpy_end, __memcpy_user_error_lr, __memcpy_user_error_handler;
 extern spinlock_t modlist_lock;
 
-/*****************************************************************************/
-/*
- *
- */
-static inline unsigned long search_one_table(const struct exception_table_entry *first,
-					     const struct exception_table_entry *last,
-					     unsigned long value)
-{
-        while (first <= last) {
-		const struct exception_table_entry __attribute__((aligned(8))) *mid;
-		long diff;
-
-		mid = (last - first) / 2 + first;
-		diff = mid->insn - value;
-                if (diff == 0)
-                        return mid->fixup;
-                else if (diff < 0)
-                        first = mid + 1;
-                else
-                        last = mid - 1;
-        }
-        return 0;
-} /* end search_one_table() */
 
 /*****************************************************************************/
 /*
diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h
index a59dad3b369511..bacd3d6030c576 100644
--- a/arch/hexagon/include/asm/thread_info.h
+++ b/arch/hexagon/include/asm/thread_info.h
@@ -56,7 +56,6 @@ struct thread_info {
 	 * used for syscalls somehow;
 	 * seems to have a function pointer and four arguments
 	 */
-	struct restart_block    restart_block;
 	/* Points to the current pt_regs frame  */
 	struct pt_regs		*regs;
 	/*
@@ -83,9 +82,6 @@ struct thread_info {
 	.cpu            = 0,                    \
 	.preempt_count  = 1,                    \
 	.addr_limit     = KERNEL_DS,            \
-	.restart_block = {                      \
-		.fn = do_no_restart_syscall,    \
-	},                                      \
 	.sp = 0,				\
 	.regs = NULL,			\
 }
diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c
index eadd70e47e7edd..b039a624c170a3 100644
--- a/arch/hexagon/kernel/signal.c
+++ b/arch/hexagon/kernel/signal.c
@@ -239,7 +239,7 @@ asmlinkage int sys_rt_sigreturn(void)
 	sigset_t blocked;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *)pt_psp(regs);
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index 5b17418b42239b..c16f21a068ff7e 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -27,7 +27,6 @@ struct thread_info {
 	__u32 status;			/* Thread synchronous flags */
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
-	struct restart_block restart_block;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	__u64 ac_stamp;
 	__u64 ac_leave;
@@ -46,9 +45,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #ifndef ASM_OFFSETS_C
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 6d92170be4579c..b3a124da71e5ec 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -46,7 +46,7 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr)
 	long err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore scratch that always needs gets updated during signal delivery: */
 	err  = __get_user(flags, &sc->sc_flags);
diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h
index 00171703402f19..32422d0211c3d5 100644
--- a/arch/m32r/include/asm/thread_info.h
+++ b/arch/m32r/include/asm/thread_info.h
@@ -34,7 +34,6 @@ struct thread_info {
 					 	   0-0xBFFFFFFF for user-thread
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -49,7 +48,6 @@ struct thread_info {
 #define TI_CPU		0x00000010
 #define TI_PRE_COUNT	0x00000014
 #define TI_ADDR_LIMIT	0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
@@ -68,9 +66,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c
index 95408b8f130af6..7736c6660a1580 100644
--- a/arch/m32r/kernel/signal.c
+++ b/arch/m32r/kernel/signal.c
@@ -48,7 +48,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 #define COPY(x)		err |= __get_user(regs->x, &sc->sc_##x)
 	COPY(r4);
diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h
index 21a4784ca5a186..c54256e69e642a 100644
--- a/arch/m68k/include/asm/thread_info.h
+++ b/arch/m68k/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
 	__u32			cpu;		/* should always be 0 on m68k */
 	unsigned long		tp_value;	/* thread pointer */
-	struct restart_block    restart_block;
 };
 #endif /* __ASSEMBLY__ */
 
@@ -41,9 +40,6 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_stack		(init_thread_union.stack)
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 967a8b7e152727..d7179281e74aff 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -655,7 +655,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* get previous context */
 	if (copy_from_user(&context, usc, sizeof(context)))
@@ -693,7 +693,7 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = __get_user(temp, &uc->uc_mcontext.version);
 	if (temp != MCONTEXT_VERSION)
diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h
index 47711336119e0f..afb3ca4776d1df 100644
--- a/arch/metag/include/asm/thread_info.h
+++ b/arch/metag/include/asm/thread_info.h
@@ -35,9 +35,8 @@ struct thread_info {
 	int preempt_count;	/* 0 => preemptable, <0 => BUG */
 
 	mm_segment_t addr_limit;	/* thread address space */
-	struct restart_block restart_block;
 
-	u8 supervisor_stack[0];
+	u8 supervisor_stack[0] __aligned(8);
 };
 
 #else /* !__ASSEMBLY__ */
@@ -74,9 +73,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/metag/kernel/signal.c b/arch/metag/kernel/signal.c
index 0d100d5c140713..ce49d429c74aa6 100644
--- a/arch/metag/kernel/signal.c
+++ b/arch/metag/kernel/signal.c
@@ -48,7 +48,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = metag_gp_regs_copyin(regs, 0, sizeof(struct user_gp_regs), NULL,
 				   &sc->regs);
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index 8c9d36591a031d..b699fbd7de4aca 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -71,7 +71,6 @@ struct thread_info {
 	__u32			cpu; /* current CPU */
 	__s32			preempt_count; /* 0 => preemptable,< 0 => BUG*/
 	mm_segment_t		addr_limit; /* thread address space */
-	struct restart_block	restart_block;
 
 	struct cpu_context	cpu_context;
 };
@@ -87,9 +86,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index 235706055b7fc6..a1cbaf90e2ea47 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -89,7 +89,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	int rval;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index e4440f92b366f7..9e1295f874f0c1 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -34,7 +34,6 @@ struct thread_info {
 						 * 0x7fffffff for user-thead
 						 * 0xffffffff for kernel-thread
 						 */
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 	long			syscall;	/* syscall number */
 };
@@ -50,9 +49,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index b1d84bd4efb3b4..3b2dfdb4865fd9 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -98,7 +98,6 @@ void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 545bf11bd2edb4..6a28c792d862c0 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -243,7 +243,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	int i;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
 
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index d69179c0d49d4f..19a7705f2a015e 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -220,7 +220,7 @@ static int restore_sigcontext32(struct pt_regs *regs,
 	int i;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
 	err |= __get_user(regs->hi, &sc->sc_mdhi);
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index bf280eaccd36fd..c1c374f0ec12ef 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -50,7 +50,6 @@ struct thread_info {
 						   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -80,9 +79,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/mn10300/kernel/asm-offsets.c b/arch/mn10300/kernel/asm-offsets.c
index 47b3bb0c04ffc4..d780670cbaf365 100644
--- a/arch/mn10300/kernel/asm-offsets.c
+++ b/arch/mn10300/kernel/asm-offsets.c
@@ -28,7 +28,6 @@ void foo(void)
 	OFFSET(TI_cpu,			thread_info, cpu);
 	OFFSET(TI_preempt_count,	thread_info, preempt_count);
 	OFFSET(TI_addr_limit,		thread_info, addr_limit);
-	OFFSET(TI_restart_block,	thread_info, restart_block);
 	BLANK();
 
 	OFFSET(REG_D0,			pt_regs, d0);
diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c
index a6c0858592c3be..8609845f12c581 100644
--- a/arch/mn10300/kernel/signal.c
+++ b/arch/mn10300/kernel/signal.c
@@ -40,7 +40,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (is_using_fpu(current))
 		fpu_kill_state(current);
diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h
index d797acc901e4c2..875f0845a70760 100644
--- a/arch/openrisc/include/asm/thread_info.h
+++ b/arch/openrisc/include/asm/thread_info.h
@@ -57,7 +57,6 @@ struct thread_info {
 					       0-0x7FFFFFFF for user-thead
 					       0-0xFFFFFFFF for kernel-thread
 					     */
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 
 	/* saved context data */
@@ -79,9 +78,6 @@ struct thread_info {
 	.cpu		= 0,				\
 	.preempt_count	= 1,				\
 	.addr_limit	= KERNEL_DS,			\
-	.restart_block  = {				\
-			  .fn = do_no_restart_syscall,	\
-	},						\
 	.ksp            = 0,                            \
 }
 
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index 7d1b8235bf90a9..4112175bf803b4 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -46,7 +46,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Restore the regs from &sc->regs.
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index a84611835549c2..fb13e3865563cd 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -14,7 +14,6 @@ struct thread_info {
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	__u32 cpu;			/* current CPU */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
-	struct restart_block restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -25,9 +24,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-  	.restart_block	= {			\
-		.fn = do_no_restart_syscall	\
-	}					\
 }
 
 #define init_thread_info        (init_thread_union.thread_info)
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 012d4fa63d9763..9b910a0251b8a0 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -99,7 +99,7 @@ sys_rt_sigreturn(struct pt_regs *regs, int in_syscall)
 		sigframe_size = PARISC_RT_SIGFRAME_SIZE32;
 #endif
 
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* Unwind the user stack to get the rt_sigframe structure. */
 	frame = (struct rt_sigframe __user *)
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 7e77f2ca51325a..79fee2eb8d56f1 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -40,63 +40,27 @@ static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK)
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_NUMA_BALANCING
-static inline int pte_present(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_NUMA_MASK;
-}
-
-#define pte_present_nonuma pte_present_nonuma
-static inline int pte_present_nonuma(pte_t pte)
-{
-	return pte_val(pte) & (_PAGE_PRESENT);
-}
-
-#define ptep_set_numa ptep_set_numa
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep)
-{
-	if ((pte_val(*ptep) & _PAGE_PRESENT) == 0)
-		VM_BUG_ON(1);
-
-	pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0);
-	return;
-}
-
-#define pmdp_set_numa pmdp_set_numa
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pmd_t *pmdp)
-{
-	if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0)
-		VM_BUG_ON(1);
-
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA);
-	return;
-}
-
 /*
- * Generic NUMA pte helpers expect pteval_t and pmdval_t types to exist
- * which was inherited from x86. For the purposes of powerpc pte_basic_t and
- * pmd_t are equivalent
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h . On powerpc, this will only
+ * work for user pages and always return true for kernel pages.
  */
-#define pteval_t pte_basic_t
-#define pmdval_t pmd_t
-static inline pteval_t ptenuma_flags(pte_t pte)
+static inline int pte_protnone(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_NUMA_MASK;
+	return (pte_val(pte) &
+		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
 }
 
-static inline pmdval_t pmdnuma_flags(pmd_t pmd)
+static inline int pmd_protnone(pmd_t pmd)
 {
-	return pmd_val(pmd) & _PAGE_NUMA_MASK;
+	return pte_protnone(pmd_pte(pmd));
 }
-
-# else
+#endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_PRESENT;
 }
-#endif /* CONFIG_NUMA_BALANCING */
 
 /* Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index 2aef9b7a0eb2af..c5a755ef7011ad 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -104,11 +104,6 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 			 _PAGE_USER | _PAGE_ACCESSED | _PAGE_RO | \
 			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
-#ifdef CONFIG_NUMA_BALANCING
-/* Mask of bits that distinguish present and numa ptes */
-#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PRESENT)
-#endif
-
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable
diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h
index 2505d8eab15cb9..55aea0caf95ebc 100644
--- a/arch/powerpc/include/asm/pte-hash64.h
+++ b/arch/powerpc/include/asm/pte-hash64.h
@@ -27,12 +27,6 @@
 #define _PAGE_RW		0x0200 /* software: user write access allowed */
 #define _PAGE_BUSY		0x0800 /* software: PTE & hash are busy */
 
-/*
- * Used for tracking numa faults
- */
-#define _PAGE_NUMA	0x00000010 /* Gather numa placement stats */
-
-
 /* No separate kernel read-only */
 #define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */
 #define _PAGE_KERNEL_RO		 _PAGE_KERNEL_RW
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index e8abc83e699fbe..72489799cf022f 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -43,7 +43,6 @@ struct thread_info {
 	int		cpu;			/* cpu we're on */
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
-	struct restart_block restart_block;
 	unsigned long	local_flags;		/* private flags for thread */
 
 	/* low level flags - has atomic operations done on it */
@@ -59,9 +58,6 @@ struct thread_info {
 	.exec_domain =	&default_exec_domain,	\
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 	.flags =	0,			\
 }
 
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index b171001698ff32..d3a831ac0f927e 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1231,7 +1231,7 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 	int tm_restore = 0;
 #endif
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	rt_sf = (struct rt_sigframe __user *)
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
@@ -1504,7 +1504,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
 	sc = &sf->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 2cb0c94cafa5ef..c7c24d2e2bdbc6 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -666,7 +666,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
 		goto badframe;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index fa7c4f12104fe4..7316dd15278a35 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -621,6 +621,38 @@ unsigned long long sched_clock(void)
 	return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
 }
 
+
+#ifdef CONFIG_PPC_PSERIES
+
+/*
+ * Running clock - attempts to give a view of time passing for a virtualised
+ * kernels.
+ * Uses the VTB register if available otherwise a next best guess.
+ */
+unsigned long long running_clock(void)
+{
+	/*
+	 * Don't read the VTB as a host since KVM does not switch in host
+	 * timebase into the VTB when it takes a guest off the CPU, reading the
+	 * VTB would result in reading 'last switched out' guest VTB.
+	 *
+	 * Host kernels are often compiled with CONFIG_PPC_PSERIES checked, it
+	 * would be unsafe to rely only on the #ifdef above.
+	 */
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
+	    cpu_has_feature(CPU_FTR_ARCH_207S))
+		return mulhdu(get_vtb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
+
+	/*
+	 * This is a next best approximation without a VTB.
+	 * On a host which is running bare metal there should never be any stolen
+	 * time and on a host which doesn't do any virtualisation TB *should* equal
+	 * VTB so it makes no difference anyway.
+	 */
+	return local_clock() - cputime_to_nsecs(kcpustat_this_cpu->cpustat[CPUTIME_STEAL]);
+}
+#endif
+
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 510bdfbc40734f..625407e4d3b0a7 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -212,7 +212,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	/* Look up the Linux PTE for the backing page */
 	pte_size = psize;
 	pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size);
-	if (pte_present(pte) && !pte_numa(pte)) {
+	if (pte_present(pte) && !pte_protnone(pte)) {
 		if (writing && !pte_write(pte))
 			/* make the actual HPTE be read-only */
 			ptel = hpte_make_readonly(ptel);
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 1b5305d4bdabe9..f031a47d7701e6 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -64,10 +64,14 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		if (!(vma->vm_flags & VM_WRITE))
 			goto out_unlock;
 	} else {
-		if (dsisr & DSISR_PROTFAULT)
-			goto out_unlock;
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto out_unlock;
+		/*
+		 * protfault should only happen due to us
+		 * mapping a region readonly temporarily. PROT_NONE
+		 * is also covered by the VMA check above.
+		 */
+		WARN_ON_ONCE(dsisr & DSISR_PROTFAULT);
 	}
 
 	ret = 0;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 6154b0a2b06331..b396868d2aa7c4 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -389,19 +389,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 #endif /* CONFIG_8xx */
 
 	if (is_exec) {
-#ifdef CONFIG_PPC_STD_MMU
-		/* Protection fault on exec go straight to failure on
-		 * Hash based MMUs as they either don't support per-page
-		 * execute permission, or if they do, it's handled already
-		 * at the hash level. This test would probably have to
-		 * be removed if we change the way this works to make hash
-		 * processors use the same I/D cache coherency mechanism
-		 * as embedded.
-		 */
-		if (error_code & DSISR_PROTFAULT)
-			goto bad_area;
-#endif /* CONFIG_PPC_STD_MMU */
-
 		/*
 		 * Allow execution from readable areas if the MMU does not
 		 * provide separate controls over reading and executing.
@@ -416,6 +403,14 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		    (cpu_has_feature(CPU_FTR_NOEXECUTE) ||
 		     !(vma->vm_flags & (VM_READ | VM_WRITE))))
 			goto bad_area;
+#ifdef CONFIG_PPC_STD_MMU
+		/*
+		 * protfault should only happen due to us
+		 * mapping a region readonly temporarily. PROT_NONE
+		 * is also covered by the VMA check above.
+		 */
+		WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
+#endif /* CONFIG_PPC_STD_MMU */
 	/* a write */
 	} else if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -423,11 +418,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
-		/* protection fault */
-		if (error_code & 0x08000000)
-			goto bad_area;
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 			goto bad_area;
+		WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
 	}
 
 	/*
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index c90e602677c94f..83dfcb55ffef69 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -172,9 +172,14 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 		pte_t pte)
 {
-#ifdef CONFIG_DEBUG_VM
-	WARN_ON(pte_val(*ptep) & _PAGE_PRESENT);
-#endif
+	/*
+	 * When handling numa faults, we already have the pte marked
+	 * _PAGE_PRESENT, but we can be sure that it is not in hpte.
+	 * Hence we can use set_pte_at for them.
+	 */
+	VM_WARN_ON((pte_val(*ptep) & (_PAGE_PRESENT | _PAGE_USER)) ==
+		(_PAGE_PRESENT | _PAGE_USER));
+
 	/* Note: mm->context.id might not yet have been assigned as
 	 * this context might not have been activated yet when this
 	 * is called.
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 4fe5f64cc1793e..91bb8836825a6f 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -718,7 +718,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(pmd_val(*pmdp) & _PAGE_PRESENT);
+	WARN_ON((pmd_val(*pmdp) & (_PAGE_PRESENT | _PAGE_USER)) ==
+		(_PAGE_PRESENT | _PAGE_USER));
 	assert_spin_locked(&mm->page_table_lock);
 	WARN_ON(!pmd_trans_huge(pmd));
 #endif
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index f532c92bf99dab..ee90db17b0972a 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -139,26 +139,17 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  * axon_ram_direct_access - direct_access() method for block device
  * @device, @sector, @data: see block_device_operations method
  */
-static int
+static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void **kaddr, unsigned long *pfn)
+		       void **kaddr, unsigned long *pfn, long size)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
-	loff_t offset;
-
-	offset = sector;
-	if (device->bd_part != NULL)
-		offset += device->bd_part->start_sect;
-	offset <<= AXON_RAM_SECTOR_SHIFT;
-	if (offset >= bank->size) {
-		dev_err(&bank->device->dev, "Access outside of address space\n");
-		return -ERANGE;
-	}
+	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
 
 	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return bank->size - offset;
 }
 
 static const struct block_device_operations axon_ram_devops = {
diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index 7e2dcd7c57efe2..8662f5c8e17f42 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -44,7 +44,6 @@ extern char *strstr(const char *, const char *);
 #undef __HAVE_ARCH_STRCHR
 #undef __HAVE_ARCH_STRNCHR
 #undef __HAVE_ARCH_STRNCMP
-#undef __HAVE_ARCH_STRNICMP
 #undef __HAVE_ARCH_STRPBRK
 #undef __HAVE_ARCH_STRSEP
 #undef __HAVE_ARCH_STRSPN
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 4d62fd5b56e5d1..ef1df718642d20 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -39,7 +39,6 @@ struct thread_info {
 	unsigned long		sys_call_table;	/* System call table address */
 	unsigned int		cpu;		/* current CPU */
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
-	struct restart_block	restart_block;
 	unsigned int		system_call;
 	__u64			user_timer;
 	__u64			system_timer;
@@ -56,9 +55,6 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 34d5fa7b01b50e..bc1df12dd4f816 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -209,7 +209,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	int i;
 
 	/* Alwys make any pending restarted system call return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (__copy_from_user(&user_sregs, &sregs->regs, sizeof(user_sregs)))
 		return -EFAULT;
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 6a2ac257d98f28..b3ae6f70c6d64b 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -162,7 +162,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	_sigregs user_sregs;
 
 	/* Alwys make any pending restarted system call return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (__copy_from_user(&user_sregs, sregs, sizeof(user_sregs)))
 		return -EFAULT;
diff --git a/arch/score/include/asm/thread_info.h b/arch/score/include/asm/thread_info.h
index 656b7ada9326ab..33864fa2a8d4cd 100644
--- a/arch/score/include/asm/thread_info.h
+++ b/arch/score/include/asm/thread_info.h
@@ -42,7 +42,6 @@ struct thread_info {
 	 * 0-0xFFFFFFFF for kernel-thread
 	 */
 	mm_segment_t		addr_limit;
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 };
 
@@ -58,9 +57,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= 1,			\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/score/kernel/asm-offsets.c b/arch/score/kernel/asm-offsets.c
index 57788f44c6fb09..b4d5214a7a7e26 100644
--- a/arch/score/kernel/asm-offsets.c
+++ b/arch/score/kernel/asm-offsets.c
@@ -106,7 +106,6 @@ void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
 	DEFINE(KERNEL_STACK_SIZE, THREAD_SIZE);
 	DEFINE(KERNEL_STACK_MASK, THREAD_MASK);
diff --git a/arch/score/kernel/signal.c b/arch/score/kernel/signal.c
index 1651807774ad10..e381c8c4ff65b6 100644
--- a/arch/score/kernel/signal.c
+++ b/arch/score/kernel/signal.c
@@ -141,7 +141,7 @@ score_rt_sigreturn(struct pt_regs *regs)
 	int sig;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *) regs->regs[0];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index ad27ffa65e2eaf..657c0391962761 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -33,7 +33,6 @@ struct thread_info {
 	__u32			cpu;
 	int			preempt_count; /* 0 => preemptable, <0 => BUG */
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block	restart_block;
 	unsigned long		previous_sp;	/* sp of previous stack in case
 						   of nested IRQ stacks */
 	__u8			supervisor_stack[0];
@@ -63,9 +62,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/sh/kernel/asm-offsets.c b/arch/sh/kernel/asm-offsets.c
index 08a2be775b6c79..542225fedb1120 100644
--- a/arch/sh/kernel/asm-offsets.c
+++ b/arch/sh/kernel/asm-offsets.c
@@ -25,7 +25,6 @@ int main(void)
 	DEFINE(TI_FLAGS,	offsetof(struct thread_info, flags));
 	DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
 	DEFINE(TI_PRE_COUNT,	offsetof(struct thread_info, preempt_count));
-	DEFINE(TI_RESTART_BLOCK,offsetof(struct thread_info, restart_block));
 	DEFINE(TI_SIZE,		sizeof(struct thread_info));
 
 #ifdef CONFIG_HIBERNATION
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 2f002b24fb92f4..0b34f2a704fe1d 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -156,7 +156,7 @@ asmlinkage int sys_sigreturn(void)
 	int r0;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -186,7 +186,7 @@ asmlinkage int sys_rt_sigreturn(void)
 	int r0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c
index 897abe7b871e2d..71993c6a7d94b0 100644
--- a/arch/sh/kernel/signal_64.c
+++ b/arch/sh/kernel/signal_64.c
@@ -260,7 +260,7 @@ asmlinkage int sys_sigreturn(unsigned long r2, unsigned long r3,
 	long long ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -294,7 +294,7 @@ asmlinkage int sys_rt_sigreturn(unsigned long r2, unsigned long r3,
 	long long ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index 025c98446b1ee1..fd7bd0a440ca71 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -47,8 +47,6 @@ struct thread_info {
 	struct reg_window32	reg_window[NSWINS];	/* align for ldd! */
 	unsigned long		rwbuf_stkptrs[NSWINS];
 	unsigned long		w_saved;
-
-	struct restart_block	restart_block;
 };
 
 /*
@@ -62,9 +60,6 @@ struct thread_info {
 	.flags		=	0,			\
 	.cpu		=	0,			\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
-	.restart_block	= {				\
-		.fn	=	do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
@@ -103,7 +98,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define TI_REG_WINDOW	0x30
 #define TI_RWIN_SPTRS	0x230
 #define TI_W_SAVED	0x250
-/* #define TI_RESTART_BLOCK 0x25n */ /* Nobody cares */
 
 /*
  * thread information flag bit numbers
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 798f0279a4b56a..ff455164732a9b 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -58,8 +58,6 @@ struct thread_info {
 	unsigned long		gsr[7];
 	unsigned long		xfsr[7];
 
-	struct restart_block	restart_block;
-
 	struct pt_regs		*kern_una_regs;
 	unsigned int		kern_una_insn;
 
@@ -92,10 +90,9 @@ struct thread_info {
 #define TI_RWIN_SPTRS	0x000003c8
 #define TI_GSR		0x00000400
 #define TI_XFSR		0x00000438
-#define TI_RESTART_BLOCK 0x00000470
-#define TI_KUNA_REGS	0x000004a0
-#define TI_KUNA_INSN	0x000004a8
-#define TI_FPREGS	0x000004c0
+#define TI_KUNA_REGS	0x00000470
+#define TI_KUNA_INSN	0x00000478
+#define TI_FPREGS	0x00000480
 
 /* We embed this in the uppermost byte of thread_info->flags */
 #define FAULT_CODE_WRITE	0x01	/* Write access, implies D-TLB	   */
@@ -124,9 +121,6 @@ struct thread_info {
 	.current_ds	=	ASI_P,			\
 	.exec_domain	=	&default_exec_domain,	\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
-	.restart_block	= {				\
-		.fn	=	do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 62deba7be1a9ed..4eed773a77358b 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -150,7 +150,7 @@ void do_sigreturn32(struct pt_regs *regs)
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 
@@ -235,7 +235,7 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 	regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 9ee72fc8e0e496..52aa5e4ce5e77c 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -70,7 +70,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 1a699986803158..d88beff47bab3e 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -254,7 +254,7 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack ();
 	sf = (struct rt_signal_frame __user *)
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 981a769b955802..a27651e866e7a1 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2730,8 +2730,6 @@ void __init trap_init(void)
 		     TI_NEW_CHILD != offsetof(struct thread_info, new_child) ||
 		     TI_CURRENT_DS != offsetof(struct thread_info,
 						current_ds) ||
-		     TI_RESTART_BLOCK != offsetof(struct thread_info,
-						  restart_block) ||
 		     TI_KUNA_REGS != offsetof(struct thread_info,
 					      kern_una_regs) ||
 		     TI_KUNA_INSN != offsetof(struct thread_info,
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 48e4fd0f38e49e..96c14c1430d8e7 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -36,7 +36,6 @@ struct thread_info {
 
 	mm_segment_t		addr_limit;	/* thread address space
 						   (KERNEL_DS or USER_DS) */
-	struct restart_block	restart_block;
 	struct single_step_state *step_state;	/* single step state
 						   (if non-zero) */
 	int			align_ctl;	/* controls unaligned access */
@@ -57,9 +56,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 	.step_state	= NULL,			\
 	.align_ctl	= 0,			\
 }
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index bb0a9ce7ae23f6..8a524e332c1a28 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -48,7 +48,7 @@ int restore_sigcontext(struct pt_regs *regs,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Enforce that sigcontext is like pt_regs, and doesn't mess
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 1c5b2a83046aab..e04114c4fcd9e5 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -22,7 +22,6 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* thread address space:
 					 	   0-0xBFFFFFFF for user
 						   0-0xFFFFFFFF for kernel */
-	struct restart_block    restart_block;
 	struct thread_info	*real_thread;    /* Points to non-IRQ stack */
 };
 
@@ -34,9 +33,6 @@ struct thread_info {
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit =	KERNEL_DS,		\
-	.restart_block =  {			\
-		.fn =  do_no_restart_syscall,	\
-	},					\
 	.real_thread = NULL,			\
 }
 
diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h
index af36d8eabdf1c1..63e2839dfeb8f8 100644
--- a/arch/unicore32/include/asm/thread_info.h
+++ b/arch/unicore32/include/asm/thread_info.h
@@ -79,7 +79,6 @@ struct thread_info {
 #ifdef CONFIG_UNICORE_FPU_F64
 	struct fp_state		fpstate __attribute__((aligned(8)));
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
@@ -89,9 +88,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/unicore32/kernel/signal.c b/arch/unicore32/kernel/signal.c
index 7c8fb7018dc6bf..d329f85766cc5c 100644
--- a/arch/unicore32/kernel/signal.c
+++ b/arch/unicore32/kernel/signal.c
@@ -105,7 +105,7 @@ asmlinkage int __sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 920e6160c5353c..5ba2d9ce82dcb8 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -148,6 +148,7 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
 
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
 asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index f9e181aaba9791..d0165c9a293241 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -169,7 +169,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	u32 tmp;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
 		/*
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0fe03f834fb123..67fc3d2b0aabe6 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -132,13 +132,7 @@ static inline int pte_exec(pte_t pte)
 
 static inline int pte_special(pte_t pte)
 {
-	/*
-	 * See CONFIG_NUMA_BALANCING pte_numa in include/asm-generic/pgtable.h.
-	 * On x86 we have _PAGE_BIT_NUMA == _PAGE_BIT_GLOBAL+1 ==
-	 * __PAGE_BIT_SOFTW1 == _PAGE_BIT_SPECIAL.
-	 */
-	return (pte_flags(pte) & _PAGE_SPECIAL) &&
-		(pte_flags(pte) & (_PAGE_PRESENT|_PAGE_PROTNONE));
+	return pte_flags(pte) & _PAGE_SPECIAL;
 }
 
 static inline unsigned long pte_pfn(pte_t pte)
@@ -300,7 +294,7 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {
-	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+	return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
@@ -442,13 +436,6 @@ static inline int pte_same(pte_t a, pte_t b)
 }
 
 static inline int pte_present(pte_t a)
-{
-	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
-			       _PAGE_NUMA);
-}
-
-#define pte_present_nonuma pte_present_nonuma
-static inline int pte_present_nonuma(pte_t a)
 {
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
@@ -459,7 +446,7 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 	if (pte_flags(a) & _PAGE_PRESENT)
 		return true;
 
-	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+	if ((pte_flags(a) & _PAGE_PROTNONE) &&
 			mm_tlb_flush_pending(mm))
 		return true;
 
@@ -479,10 +466,25 @@ static inline int pmd_present(pmd_t pmd)
 	 * the _PAGE_PSE flag will remain set at all times while the
 	 * _PAGE_PRESENT bit is clear).
 	 */
-	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE |
-				 _PAGE_NUMA);
+	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_PROTNONE;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_PROTNONE;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 static inline int pmd_none(pmd_t pmd)
 {
 	/* Only check low word on 32-bit platforms, since it might be
@@ -539,11 +541,6 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-#ifdef CONFIG_NUMA_BALANCING
-	/* pmd_numa check */
-	if ((pmd_flags(pmd) & (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA)
-		return 0;
-#endif
 	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
 }
 
@@ -862,19 +859,16 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
 
 static inline int pte_swp_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
 }
 
 static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
 #endif
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e227970f983ee0..2ee781114d3480 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -142,12 +142,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 
 /* Encode and de-code a swap entry */
 #define SWP_TYPE_BITS 5
-#ifdef CONFIG_NUMA_BALANCING
-/* Automatic NUMA balancing needs to be distinguishable from swap entries */
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2)
-#else
 #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
-#endif
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 3e0230c94cff1e..8c7c10802e9c68 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -27,14 +27,6 @@
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
-/*
- * Swap offsets on configurations that allow automatic NUMA balancing use the
- * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from
- * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the
- * maximum possible swap space from 16TB to 8TB.
- */
-#define _PAGE_BIT_NUMA		(_PAGE_BIT_GLOBAL+1)
-
 /* If _PAGE_BIT_PRESENT is clear, we use these: */
 /* - if the user mapped it with PROT_NONE; pte_present gives true */
 #define _PAGE_BIT_PROTNONE	_PAGE_BIT_GLOBAL
@@ -75,21 +67,6 @@
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
-/*
- * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page
- * that is not present. The hinting fault gathers numa placement statistics
- * (see pte_numa()). The bit is always zero when the PTE is not present.
- *
- * The bit picked must be always zero when the pmd is present and not
- * present, so that we don't lose information when we set it while
- * atomically clearing the present bit.
- */
-#ifdef CONFIG_NUMA_BALANCING
-#define _PAGE_NUMA	(_AT(pteval_t, 1) << _PAGE_BIT_NUMA)
-#else
-#define _PAGE_NUMA	(_AT(pteval_t, 0))
-#endif
-
 /*
  * Tracking soft dirty bit when a page goes to a swap is tricky.
  * We need a bit which can be stored in pte _and_ not conflict
@@ -122,8 +99,8 @@
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_NUMA)
-#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA)
+			 _PAGE_SOFT_DIRTY)
+#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*
  * The cache modes defined here are used to translate between pure SW usage
@@ -324,20 +301,6 @@ static inline pteval_t pte_flags(pte_t pte)
 	return native_pte_val(pte) & PTE_FLAGS_MASK;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-/* Set of bits that distinguishes present, prot_none and numa ptes */
-#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)
-static inline pteval_t ptenuma_flags(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_NUMA_MASK;
-}
-
-static inline pmdval_t pmdnuma_flags(pmd_t pmd)
-{
-	return pmd_flags(pmd) & _PAGE_NUMA_MASK;
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e82e95abc92bd5..1d4e4f279a3281 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
 	__u32			cpu;		/* current CPU */
 	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
-	struct restart_block    restart_block;
 	void __user		*sysenter_return;
 	unsigned int		sig_on_uaccess_error:1;
 	unsigned int		uaccess_err:1;	/* uaccess failed */
@@ -45,9 +44,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 319bcb9372fed3..3acbff4716b088 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -168,7 +168,7 @@ static void _hpet_print_config(const char *function, int line)
 #define hpet_print_config()					\
 do {								\
 	if (hpet_verbose)					\
-		_hpet_print_config(__FUNCTION__, __LINE__);	\
+		_hpet_print_config(__func__, __LINE__);	\
 } while (0)
 
 /*
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index fe3dbfe0c4a5ee..cd9685235df91b 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -49,11 +49,11 @@ int mach_set_rtc_mmss(const struct timespec *now)
 		retval = set_rtc_time(&tm);
 		if (retval)
 			printk(KERN_ERR "%s: RTC write failed with error %d\n",
-			       __FUNCTION__, retval);
+			       __func__, retval);
 	} else {
 		printk(KERN_ERR
 		       "%s: Invalid RTC value: write of %lx to RTC failed\n",
-			__FUNCTION__, nowtime);
+			__func__, nowtime);
 		retval = -EINVAL;
 	}
 	return retval;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 2a33c8f6831943..e5042463c1bca5 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -69,7 +69,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 89df70e0caa6b9..81bf3d2af3eb39 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -84,7 +84,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		struct page *page;
 
 		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_numa(pte)) {
+		if (pte_protnone(pte)) {
 			pte_unmap(ptep);
 			return 0;
 		}
@@ -178,7 +178,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 			 * slowpath for accounting purposes and so that they
 			 * can be serialised against THP migration.
 			 */
-			if (pmd_numa(pmd))
+			if (pmd_protnone(pmd))
 				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
index 4762cff7facd02..32947ba0f62dad 100644
--- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c
+++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
@@ -110,7 +110,7 @@ int vrtc_set_mmss(const struct timespec *now)
 		spin_unlock_irqrestore(&rtc_lock, flags);
 	} else {
 		pr_err("%s: Invalid vRTC value: write of %lx to vRTC failed\n",
-			__FUNCTION__, now->tv_sec);
+			__func__, now->tv_sec);
 		retval = -EINVAL;
 	}
 	return retval;
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 79d824551c1a56..0c8c32bfd7928e 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -157,7 +157,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
 	int err, pid;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = copy_from_user(&sc, from, sizeof(sc));
 	if (err)
diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index 470153e8547c19..a9b5d3ba196cd7 100644
--- a/arch/xtensa/include/asm/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
@@ -51,7 +51,6 @@ struct thread_info {
 	__s32			preempt_count;	/* 0 => preemptable,< 0 => BUG*/
 
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block    restart_block;
 
 	unsigned long		cpenable;
 
@@ -72,7 +71,6 @@ struct thread_info {
 #define TI_CPU		 0x00000010
 #define TI_PRE_COUNT	 0x00000014
 #define TI_ADDR_LIMIT	 0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
@@ -90,9 +88,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 4612321c73cc1d..3d733ba16f28a2 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -245,7 +245,7 @@ asmlinkage long xtensa_rt_sigreturn(long a0, long a1, long a2, long a3,
 	int ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (regs->depc > 64)
 		panic("rt_sigreturn in double exception!\n");
diff --git a/block/bio.c b/block/bio.c
index 471d7382c7d17b..f66a4eae16ee4a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -28,7 +28,6 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
-#include <scsi/sg.h>		/* for struct sg_iovec */
 
 #include <trace/events/block.h>
 
@@ -1022,21 +1021,11 @@ void bio_copy_data(struct bio *dst, struct bio *src)
 EXPORT_SYMBOL(bio_copy_data);
 
 struct bio_map_data {
-	int nr_sgvecs;
 	int is_our_pages;
-	struct sg_iovec sgvecs[];
+	struct iov_iter iter;
+	struct iovec iov[];
 };
 
-static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
-			     const struct sg_iovec *iov, int iov_count,
-			     int is_our_pages)
-{
-	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
-	bmd->nr_sgvecs = iov_count;
-	bmd->is_our_pages = is_our_pages;
-	bio->bi_private = bmd;
-}
-
 static struct bio_map_data *bio_alloc_map_data(unsigned int iov_count,
 					       gfp_t gfp_mask)
 {
@@ -1044,85 +1033,101 @@ static struct bio_map_data *bio_alloc_map_data(unsigned int iov_count,
 		return NULL;
 
 	return kmalloc(sizeof(struct bio_map_data) +
-		       sizeof(struct sg_iovec) * iov_count, gfp_mask);
+		       sizeof(struct iovec) * iov_count, gfp_mask);
 }
 
-static int __bio_copy_iov(struct bio *bio, const struct sg_iovec *iov, int iov_count,
-			  int to_user, int from_user, int do_free_page)
+/**
+ * bio_copy_from_iter - copy all pages from iov_iter to bio
+ * @bio: The &struct bio which describes the I/O as destination
+ * @iter: iov_iter as source
+ *
+ * Copy all pages from iov_iter to bio.
+ * Returns 0 on success, or error on failure.
+ */
+static int bio_copy_from_iter(struct bio *bio, struct iov_iter iter)
 {
-	int ret = 0, i;
+	int i;
 	struct bio_vec *bvec;
-	int iov_idx = 0;
-	unsigned int iov_off = 0;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		char *bv_addr = page_address(bvec->bv_page);
-		unsigned int bv_len = bvec->bv_len;
+		ssize_t ret;
 
-		while (bv_len && iov_idx < iov_count) {
-			unsigned int bytes;
-			char __user *iov_addr;
+		ret = copy_page_from_iter(bvec->bv_page,
+					  bvec->bv_offset,
+					  bvec->bv_len,
+					  &iter);
 
-			bytes = min_t(unsigned int,
-				      iov[iov_idx].iov_len - iov_off, bv_len);
-			iov_addr = iov[iov_idx].iov_base + iov_off;
+		if (!iov_iter_count(&iter))
+			break;
 
-			if (!ret) {
-				if (to_user)
-					ret = copy_to_user(iov_addr, bv_addr,
-							   bytes);
+		if (ret < bvec->bv_len)
+			return -EFAULT;
+	}
 
-				if (from_user)
-					ret = copy_from_user(bv_addr, iov_addr,
-							     bytes);
+	return 0;
+}
 
-				if (ret)
-					ret = -EFAULT;
-			}
+/**
+ * bio_copy_to_iter - copy all pages from bio to iov_iter
+ * @bio: The &struct bio which describes the I/O as source
+ * @iter: iov_iter as destination
+ *
+ * Copy all pages from bio to iov_iter.
+ * Returns 0 on success, or error on failure.
+ */
+static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
+{
+	int i;
+	struct bio_vec *bvec;
 
-			bv_len -= bytes;
-			bv_addr += bytes;
-			iov_addr += bytes;
-			iov_off += bytes;
+	bio_for_each_segment_all(bvec, bio, i) {
+		ssize_t ret;
 
-			if (iov[iov_idx].iov_len == iov_off) {
-				iov_idx++;
-				iov_off = 0;
-			}
-		}
+		ret = copy_page_to_iter(bvec->bv_page,
+					bvec->bv_offset,
+					bvec->bv_len,
+					&iter);
+
+		if (!iov_iter_count(&iter))
+			break;
 
-		if (do_free_page)
-			__free_page(bvec->bv_page);
+		if (ret < bvec->bv_len)
+			return -EFAULT;
 	}
 
-	return ret;
+	return 0;
+}
+
+static void bio_free_pages(struct bio *bio)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i)
+		__free_page(bvec->bv_page);
 }
 
 /**
  *	bio_uncopy_user	-	finish previously mapped bio
  *	@bio: bio being terminated
  *
- *	Free pages allocated from bio_copy_user() and write back data
+ *	Free pages allocated from bio_copy_user_iov() and write back data
  *	to user space in case of a read.
  */
 int bio_uncopy_user(struct bio *bio)
 {
 	struct bio_map_data *bmd = bio->bi_private;
-	struct bio_vec *bvec;
-	int ret = 0, i;
+	int ret = 0;
 
 	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
 		 * don't copy into a random user address space, just free.
 		 */
-		if (current->mm)
-			ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs,
-					     bio_data_dir(bio) == READ,
-					     0, bmd->is_our_pages);
-		else if (bmd->is_our_pages)
-			bio_for_each_segment_all(bvec, bio, i)
-				__free_page(bvec->bv_page);
+		if (current->mm && bio_data_dir(bio) == READ)
+			ret = bio_copy_to_iter(bio, bmd->iter);
+		if (bmd->is_our_pages)
+			bio_free_pages(bio);
 	}
 	kfree(bmd);
 	bio_put(bio);
@@ -1132,12 +1137,10 @@ EXPORT_SYMBOL(bio_uncopy_user);
 
 /**
  *	bio_copy_user_iov	-	copy user data to bio
- *	@q: destination block queue
- *	@map_data: pointer to the rq_map_data holding pages (if necessary)
- *	@iov:	the iovec.
- *	@iov_count: number of elements in the iovec
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
+ *	@q:		destination block queue
+ *	@map_data:	pointer to the rq_map_data holding pages (if necessary)
+ *	@iter:		iovec iterator
+ *	@gfp_mask:	memory allocation flags
  *
  *	Prepares and returns a bio for indirect user io, bouncing data
  *	to/from kernel pages as necessary. Must be paired with
@@ -1145,25 +1148,25 @@ EXPORT_SYMBOL(bio_uncopy_user);
  */
 struct bio *bio_copy_user_iov(struct request_queue *q,
 			      struct rq_map_data *map_data,
-			      const struct sg_iovec *iov, int iov_count,
-			      int write_to_vm, gfp_t gfp_mask)
+			      const struct iov_iter *iter,
+			      gfp_t gfp_mask)
 {
 	struct bio_map_data *bmd;
-	struct bio_vec *bvec;
 	struct page *page;
 	struct bio *bio;
 	int i, ret;
 	int nr_pages = 0;
-	unsigned int len = 0;
+	unsigned int len = iter->count;
 	unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0;
 
-	for (i = 0; i < iov_count; i++) {
+	for (i = 0; i < iter->nr_segs; i++) {
 		unsigned long uaddr;
 		unsigned long end;
 		unsigned long start;
 
-		uaddr = (unsigned long)iov[i].iov_base;
-		end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		uaddr = (unsigned long) iter->iov[i].iov_base;
+		end = (uaddr + iter->iov[i].iov_len + PAGE_SIZE - 1)
+			>> PAGE_SHIFT;
 		start = uaddr >> PAGE_SHIFT;
 
 		/*
@@ -1173,22 +1176,31 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 			return ERR_PTR(-EINVAL);
 
 		nr_pages += end - start;
-		len += iov[i].iov_len;
 	}
 
 	if (offset)
 		nr_pages++;
 
-	bmd = bio_alloc_map_data(iov_count, gfp_mask);
+	bmd = bio_alloc_map_data(iter->nr_segs, gfp_mask);
 	if (!bmd)
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * We need to do a deep copy of the iov_iter including the iovecs.
+	 * The caller provided iov might point to an on-stack or otherwise
+	 * shortlived one.
+	 */
+	bmd->is_our_pages = map_data ? 0 : 1;
+	memcpy(bmd->iov, iter->iov, sizeof(struct iovec) * iter->nr_segs);
+	iov_iter_init(&bmd->iter, iter->type, bmd->iov,
+			iter->nr_segs, iter->count);
+
 	ret = -ENOMEM;
 	bio = bio_kmalloc(gfp_mask, nr_pages);
 	if (!bio)
 		goto out_bmd;
 
-	if (!write_to_vm)
+	if (iter->type & WRITE)
 		bio->bi_rw |= REQ_WRITE;
 
 	ret = 0;
@@ -1236,20 +1248,18 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	/*
 	 * success
 	 */
-	if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
+	if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) ||
 	    (map_data && map_data->from_user)) {
-		ret = __bio_copy_iov(bio, iov, iov_count, 0, 1, 0);
+		ret = bio_copy_from_iter(bio, *iter);
 		if (ret)
 			goto cleanup;
 	}
 
-	bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
+	bio->bi_private = bmd;
 	return bio;
 cleanup:
 	if (!map_data)
-		bio_for_each_segment_all(bvec, bio, i)
-			__free_page(bvec->bv_page);
-
+		bio_free_pages(bio);
 	bio_put(bio);
 out_bmd:
 	kfree(bmd);
@@ -1257,46 +1267,30 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 }
 
 /**
- *	bio_copy_user	-	copy user data to bio
- *	@q: destination block queue
- *	@map_data: pointer to the rq_map_data holding pages (if necessary)
- *	@uaddr: start of user address
- *	@len: length in bytes
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
+ *	bio_map_user_iov - map user iovec into bio
+ *	@q:		the struct request_queue for the bio
+ *	@iter:		iovec iterator
+ *	@gfp_mask:	memory allocation flags
  *
- *	Prepares and returns a bio for indirect user io, bouncing data
- *	to/from kernel pages as necessary. Must be paired with
- *	call bio_uncopy_user() on io completion.
+ *	Map the user space address into a bio suitable for io to a block
+ *	device. Returns an error pointer in case of error.
  */
-struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
-			  unsigned long uaddr, unsigned int len,
-			  int write_to_vm, gfp_t gfp_mask)
+struct bio *bio_map_user_iov(struct request_queue *q,
+			     const struct iov_iter *iter,
+			     gfp_t gfp_mask)
 {
-	struct sg_iovec iov;
-
-	iov.iov_base = (void __user *)uaddr;
-	iov.iov_len = len;
-
-	return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
-}
-EXPORT_SYMBOL(bio_copy_user);
-
-static struct bio *__bio_map_user_iov(struct request_queue *q,
-				      struct block_device *bdev,
-				      const struct sg_iovec *iov, int iov_count,
-				      int write_to_vm, gfp_t gfp_mask)
-{
-	int i, j;
+	int j;
 	int nr_pages = 0;
 	struct page **pages;
 	struct bio *bio;
 	int cur_page = 0;
 	int ret, offset;
+	struct iov_iter i;
+	struct iovec iov;
 
-	for (i = 0; i < iov_count; i++) {
-		unsigned long uaddr = (unsigned long)iov[i].iov_base;
-		unsigned long len = iov[i].iov_len;
+	iov_for_each(iov, i, *iter) {
+		unsigned long uaddr = (unsigned long) iov.iov_base;
+		unsigned long len = iov.iov_len;
 		unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 		unsigned long start = uaddr >> PAGE_SHIFT;
 
@@ -1326,16 +1320,17 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
 	if (!pages)
 		goto out;
 
-	for (i = 0; i < iov_count; i++) {
-		unsigned long uaddr = (unsigned long)iov[i].iov_base;
-		unsigned long len = iov[i].iov_len;
+	iov_for_each(iov, i, *iter) {
+		unsigned long uaddr = (unsigned long) iov.iov_base;
+		unsigned long len = iov.iov_len;
 		unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 		unsigned long start = uaddr >> PAGE_SHIFT;
 		const int local_nr_pages = end - start;
 		const int page_limit = cur_page + local_nr_pages;
 
 		ret = get_user_pages_fast(uaddr, local_nr_pages,
-				write_to_vm, &pages[cur_page]);
+				(iter->type & WRITE) != WRITE,
+				&pages[cur_page]);
 		if (ret < local_nr_pages) {
 			ret = -EFAULT;
 			goto out_unmap;
@@ -1375,72 +1370,10 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
 	/*
 	 * set data direction, and check if mapped pages need bouncing
 	 */
-	if (!write_to_vm)
+	if (iter->type & WRITE)
 		bio->bi_rw |= REQ_WRITE;
 
-	bio->bi_bdev = bdev;
 	bio->bi_flags |= (1 << BIO_USER_MAPPED);
-	return bio;
-
- out_unmap:
-	for (i = 0; i < nr_pages; i++) {
-		if(!pages[i])
-			break;
-		page_cache_release(pages[i]);
-	}
- out:
-	kfree(pages);
-	bio_put(bio);
-	return ERR_PTR(ret);
-}
-
-/**
- *	bio_map_user	-	map user address into bio
- *	@q: the struct request_queue for the bio
- *	@bdev: destination block device
- *	@uaddr: start of user address
- *	@len: length in bytes
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
- *
- *	Map the user space address into a bio suitable for io to a block
- *	device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
-			 unsigned long uaddr, unsigned int len, int write_to_vm,
-			 gfp_t gfp_mask)
-{
-	struct sg_iovec iov;
-
-	iov.iov_base = (void __user *)uaddr;
-	iov.iov_len = len;
-
-	return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm, gfp_mask);
-}
-EXPORT_SYMBOL(bio_map_user);
-
-/**
- *	bio_map_user_iov - map user sg_iovec table into bio
- *	@q: the struct request_queue for the bio
- *	@bdev: destination block device
- *	@iov:	the iovec.
- *	@iov_count: number of elements in the iovec
- *	@write_to_vm: bool indicating writing to pages or not
- *	@gfp_mask: memory allocation flags
- *
- *	Map the user space address into a bio suitable for io to a block
- *	device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
-			     const struct sg_iovec *iov, int iov_count,
-			     int write_to_vm, gfp_t gfp_mask)
-{
-	struct bio *bio;
-
-	bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm,
-				 gfp_mask);
-	if (IS_ERR(bio))
-		return bio;
 
 	/*
 	 * subtle -- if __bio_map_user() ended up bouncing a bio,
@@ -1449,8 +1382,18 @@ struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
 	 * reference to it
 	 */
 	bio_get(bio);
-
 	return bio;
+
+ out_unmap:
+	for (j = 0; j < nr_pages; j++) {
+		if (!pages[j])
+			break;
+		page_cache_release(pages[j]);
+	}
+ out:
+	kfree(pages);
+	bio_put(bio);
+	return ERR_PTR(ret);
 }
 
 static void __bio_unmap_user(struct bio *bio)
@@ -1492,8 +1435,18 @@ static void bio_map_kern_endio(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-static struct bio *__bio_map_kern(struct request_queue *q, void *data,
-				  unsigned int len, gfp_t gfp_mask)
+/**
+ *	bio_map_kern	-	map kernel address into bio
+ *	@q: the struct request_queue for the bio
+ *	@data: pointer to buffer to map
+ *	@len: length in bytes
+ *	@gfp_mask: allocation flags for bio allocation
+ *
+ *	Map the kernel address into a bio suitable for io to a block
+ *	device. Returns an error pointer in case of error.
+ */
+struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
+			 gfp_t gfp_mask)
 {
 	unsigned long kaddr = (unsigned long)data;
 	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -1517,8 +1470,11 @@ static struct bio *__bio_map_kern(struct request_queue *q, void *data,
 			bytes = len;
 
 		if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
-				    offset) < bytes)
-			break;
+				    offset) < bytes) {
+			/* we don't support partial mappings */
+			bio_put(bio);
+			return ERR_PTR(-EINVAL);
+		}
 
 		data += bytes;
 		len -= bytes;
@@ -1528,57 +1484,26 @@ static struct bio *__bio_map_kern(struct request_queue *q, void *data,
 	bio->bi_end_io = bio_map_kern_endio;
 	return bio;
 }
+EXPORT_SYMBOL(bio_map_kern);
 
-/**
- *	bio_map_kern	-	map kernel address into bio
- *	@q: the struct request_queue for the bio
- *	@data: pointer to buffer to map
- *	@len: length in bytes
- *	@gfp_mask: allocation flags for bio allocation
- *
- *	Map the kernel address into a bio suitable for io to a block
- *	device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
-			 gfp_t gfp_mask)
+static void bio_copy_kern_endio(struct bio *bio, int err)
 {
-	struct bio *bio;
-
-	bio = __bio_map_kern(q, data, len, gfp_mask);
-	if (IS_ERR(bio))
-		return bio;
-
-	if (bio->bi_iter.bi_size == len)
-		return bio;
-
-	/*
-	 * Don't support partial mappings.
-	 */
+	bio_free_pages(bio);
 	bio_put(bio);
-	return ERR_PTR(-EINVAL);
 }
-EXPORT_SYMBOL(bio_map_kern);
 
-static void bio_copy_kern_endio(struct bio *bio, int err)
+static void bio_copy_kern_endio_read(struct bio *bio, int err)
 {
+	char *p = bio->bi_private;
 	struct bio_vec *bvec;
-	const int read = bio_data_dir(bio) == READ;
-	struct bio_map_data *bmd = bio->bi_private;
 	int i;
-	char *p = bmd->sgvecs[0].iov_base;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		char *addr = page_address(bvec->bv_page);
-
-		if (read)
-			memcpy(p, addr, bvec->bv_len);
-
-		__free_page(bvec->bv_page);
+		memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
 		p += bvec->bv_len;
 	}
 
-	kfree(bmd);
-	bio_put(bio);
+	bio_copy_kern_endio(bio, err);
 }
 
 /**
@@ -1595,28 +1520,59 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
 struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 			  gfp_t gfp_mask, int reading)
 {
+	unsigned long kaddr = (unsigned long)data;
+	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	unsigned long start = kaddr >> PAGE_SHIFT;
 	struct bio *bio;
-	struct bio_vec *bvec;
-	int i;
+	void *p = data;
+	int nr_pages = 0;
+
+	/*
+	 * Overflow, abort
+	 */
+	if (end < start)
+		return ERR_PTR(-EINVAL);
 
-	bio = bio_copy_user(q, NULL, (unsigned long)data, len, 1, gfp_mask);
-	if (IS_ERR(bio))
-		return bio;
+	nr_pages = end - start;
+	bio = bio_kmalloc(gfp_mask, nr_pages);
+	if (!bio)
+		return ERR_PTR(-ENOMEM);
 
-	if (!reading) {
-		void *p = data;
+	while (len) {
+		struct page *page;
+		unsigned int bytes = PAGE_SIZE;
 
-		bio_for_each_segment_all(bvec, bio, i) {
-			char *addr = page_address(bvec->bv_page);
+		if (bytes > len)
+			bytes = len;
 
-			memcpy(addr, p, bvec->bv_len);
-			p += bvec->bv_len;
-		}
+		page = alloc_page(q->bounce_gfp | gfp_mask);
+		if (!page)
+			goto cleanup;
+
+		if (!reading)
+			memcpy(page_address(page), p, bytes);
+
+		if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes)
+			break;
+
+		len -= bytes;
+		p += bytes;
 	}
 
-	bio->bi_end_io = bio_copy_kern_endio;
+	if (reading) {
+		bio->bi_end_io = bio_copy_kern_endio_read;
+		bio->bi_private = data;
+	} else {
+		bio->bi_end_io = bio_copy_kern_endio;
+		bio->bi_rw |= REQ_WRITE;
+	}
 
 	return bio;
+
+cleanup:
+	bio_free_pages(bio);
+	bio_put(bio);
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_copy_kern);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 3ad405571dcc51..794c3e7f01cf74 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -607,7 +607,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.state = 0;
-	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+	q->backing_dev_info.capabilities = 0;
 	q->backing_dev_info.name = "block";
 	q->node = node_id;
 
@@ -2048,6 +2048,13 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
 		return -EIO;
 
+	if (q->mq_ops) {
+		if (blk_queue_io_stat(q))
+			blk_account_io_start(rq, true);
+		blk_mq_insert_request(rq, false, true, true);
+		return 0;
+	}
+
 	spin_lock_irqsave(q->queue_lock, flags);
 	if (unlikely(blk_queue_dying(q))) {
 		spin_unlock_irqrestore(q->queue_lock, flags);
@@ -2907,7 +2914,7 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
@@ -2945,8 +2952,6 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	if (!bs)
 		bs = fs_bio_set;
 
-	blk_rq_init(NULL, rq);
-
 	__rq_for_each_bio(bio_src, rq_src) {
 		bio = bio_clone_fast(bio_src, gfp_mask, bs);
 		if (!bio)
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 8411be3c19d30c..7688ee3f5d729e 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -283,24 +283,34 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @discard:	whether to discard the block range
  *
  * Description:
- *  Generate and issue number of bios with zerofiled pages.
+ *  Zero-fill a block range.  If the discard flag is set and the block
+ *  device guarantees that subsequent READ operations to the block range
+ *  in question will return zeroes, the blocks will be discarded. Should
+ *  the discard request fail, if the discard flag is not set, or if
+ *  discard_zeroes_data is not supported, this function will resort to
+ *  zeroing the blocks manually, thus provisioning (allocating,
+ *  anchoring) them. If the block device supports the WRITE SAME command
+ *  blkdev_issue_zeroout() will use it to optimize the process of
+ *  clearing the block range. Otherwise the zeroing will be performed
+ *  using regular WRITE calls.
  */
 
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			 sector_t nr_sects, gfp_t gfp_mask)
+			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
 {
-	if (bdev_write_same(bdev)) {
-		unsigned char bdn[BDEVNAME_SIZE];
+	struct request_queue *q = bdev_get_queue(bdev);
 
-		if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
-					     ZERO_PAGE(0)))
-			return 0;
+	if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data &&
+	    blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0) == 0)
+		return 0;
 
-		bdevname(bdev, bdn);
-		pr_err("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
-	}
+	if (bdev_write_same(bdev) &&
+	    blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+				    ZERO_PAGE(0)) == 0)
+		return 0;
 
 	return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
 }
diff --git a/block/blk-map.c b/block/blk-map.c
index f890d4345b0cb6..b8d2725324a6b8 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -5,7 +5,7 @@
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <scsi/sg.h>		/* for struct sg_iovec */
+#include <linux/uio.h>
 
 #include "blk.h"
 
@@ -39,138 +39,12 @@ static int __blk_rq_unmap_user(struct bio *bio)
 	return ret;
 }
 
-static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
-			     struct rq_map_data *map_data, void __user *ubuf,
-			     unsigned int len, gfp_t gfp_mask)
-{
-	unsigned long uaddr;
-	struct bio *bio, *orig_bio;
-	int reading, ret;
-
-	reading = rq_data_dir(rq) == READ;
-
-	/*
-	 * if alignment requirement is satisfied, map in user pages for
-	 * direct dma. else, set up kernel bounce buffers
-	 */
-	uaddr = (unsigned long) ubuf;
-	if (blk_rq_aligned(q, uaddr, len) && !map_data)
-		bio = bio_map_user(q, NULL, uaddr, len, reading, gfp_mask);
-	else
-		bio = bio_copy_user(q, map_data, uaddr, len, reading, gfp_mask);
-
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	if (map_data && map_data->null_mapped)
-		bio->bi_flags |= (1 << BIO_NULL_MAPPED);
-
-	orig_bio = bio;
-	blk_queue_bounce(q, &bio);
-
-	/*
-	 * We link the bounce buffer in and could have to traverse it
-	 * later so we have to get a ref to prevent it from being freed
-	 */
-	bio_get(bio);
-
-	ret = blk_rq_append_bio(q, rq, bio);
-	if (!ret)
-		return bio->bi_iter.bi_size;
-
-	/* if it was boucned we must call the end io function */
-	bio_endio(bio, 0);
-	__blk_rq_unmap_user(orig_bio);
-	bio_put(bio);
-	return ret;
-}
-
-/**
- * blk_rq_map_user - map user data to a request, for REQ_TYPE_BLOCK_PC usage
- * @q:		request queue where request should be inserted
- * @rq:		request structure to fill
- * @map_data:   pointer to the rq_map_data holding pages (if necessary)
- * @ubuf:	the user buffer
- * @len:	length of user data
- * @gfp_mask:	memory allocation flags
- *
- * Description:
- *    Data will be mapped directly for zero copy I/O, if possible. Otherwise
- *    a kernel bounce buffer is used.
- *
- *    A matching blk_rq_unmap_user() must be issued at the end of I/O, while
- *    still in process context.
- *
- *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
- *    before being submitted to the device, as pages mapped may be out of
- *    reach. It's the callers responsibility to make sure this happens. The
- *    original bio must be passed back in to blk_rq_unmap_user() for proper
- *    unmapping.
- */
-int blk_rq_map_user(struct request_queue *q, struct request *rq,
-		    struct rq_map_data *map_data, void __user *ubuf,
-		    unsigned long len, gfp_t gfp_mask)
-{
-	unsigned long bytes_read = 0;
-	struct bio *bio = NULL;
-	int ret;
-
-	if (len > (queue_max_hw_sectors(q) << 9))
-		return -EINVAL;
-	if (!len)
-		return -EINVAL;
-
-	if (!ubuf && (!map_data || !map_data->null_mapped))
-		return -EINVAL;
-
-	while (bytes_read != len) {
-		unsigned long map_len, end, start;
-
-		map_len = min_t(unsigned long, len - bytes_read, BIO_MAX_SIZE);
-		end = ((unsigned long)ubuf + map_len + PAGE_SIZE - 1)
-								>> PAGE_SHIFT;
-		start = (unsigned long)ubuf >> PAGE_SHIFT;
-
-		/*
-		 * A bad offset could cause us to require BIO_MAX_PAGES + 1
-		 * pages. If this happens we just lower the requested
-		 * mapping len by a page so that we can fit
-		 */
-		if (end - start > BIO_MAX_PAGES)
-			map_len -= PAGE_SIZE;
-
-		ret = __blk_rq_map_user(q, rq, map_data, ubuf, map_len,
-					gfp_mask);
-		if (ret < 0)
-			goto unmap_rq;
-		if (!bio)
-			bio = rq->bio;
-		bytes_read += ret;
-		ubuf += ret;
-
-		if (map_data)
-			map_data->offset += ret;
-	}
-
-	if (!bio_flagged(bio, BIO_USER_MAPPED))
-		rq->cmd_flags |= REQ_COPY_USER;
-
-	return 0;
-unmap_rq:
-	blk_rq_unmap_user(bio);
-	rq->bio = NULL;
-	return ret;
-}
-EXPORT_SYMBOL(blk_rq_map_user);
-
 /**
  * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
  * @q:		request queue where request should be inserted
  * @rq:		request to map data to
  * @map_data:   pointer to the rq_map_data holding pages (if necessary)
- * @iov:	pointer to the iovec
- * @iov_count:	number of elements in the iovec
- * @len:	I/O byte count
+ * @iter:	iovec iterator
  * @gfp_mask:	memory allocation flags
  *
  * Description:
@@ -187,20 +61,21 @@ EXPORT_SYMBOL(blk_rq_map_user);
  *    unmapping.
  */
 int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
-			struct rq_map_data *map_data, const struct sg_iovec *iov,
-			int iov_count, unsigned int len, gfp_t gfp_mask)
+			struct rq_map_data *map_data,
+			const struct iov_iter *iter, gfp_t gfp_mask)
 {
 	struct bio *bio;
-	int i, read = rq_data_dir(rq) == READ;
 	int unaligned = 0;
+	struct iov_iter i;
+	struct iovec iov;
 
-	if (!iov || iov_count <= 0)
+	if (!iter || !iter->count)
 		return -EINVAL;
 
-	for (i = 0; i < iov_count; i++) {
-		unsigned long uaddr = (unsigned long)iov[i].iov_base;
+	iov_for_each(iov, i, *iter) {
+		unsigned long uaddr = (unsigned long) iov.iov_base;
 
-		if (!iov[i].iov_len)
+		if (!iov.iov_len)
 			return -EINVAL;
 
 		/*
@@ -210,16 +85,18 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			unaligned = 1;
 	}
 
-	if (unaligned || (q->dma_pad_mask & len) || map_data)
-		bio = bio_copy_user_iov(q, map_data, iov, iov_count, read,
-					gfp_mask);
+	if (unaligned || (q->dma_pad_mask & iter->count) || map_data)
+		bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
 	else
-		bio = bio_map_user_iov(q, NULL, iov, iov_count, read, gfp_mask);
+		bio = bio_map_user_iov(q, iter, gfp_mask);
 
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	if (bio->bi_iter.bi_size != len) {
+	if (map_data && map_data->null_mapped)
+		bio->bi_flags |= (1 << BIO_NULL_MAPPED);
+
+	if (bio->bi_iter.bi_size != iter->count) {
 		/*
 		 * Grab an extra reference to this bio, as bio_unmap_user()
 		 * expects to be able to drop it twice as it happens on the
@@ -241,6 +118,21 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
 
+int blk_rq_map_user(struct request_queue *q, struct request *rq,
+		    struct rq_map_data *map_data, void __user *ubuf,
+		    unsigned long len, gfp_t gfp_mask)
+{
+	struct iovec iov;
+	struct iov_iter i;
+
+	iov.iov_base = ubuf;
+	iov.iov_len = len;
+	iov_iter_init(&i, rq_data_dir(rq), &iov, 1, len);
+
+	return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask);
+}
+EXPORT_SYMBOL(blk_rq_map_user);
+
 /**
  * blk_rq_unmap_user - unmap a request with user data
  * @bio:	       start of bio list
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 89b97b5e088185..fc1ff3b1ea1f4a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -283,35 +283,6 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
-/**
- * blk_bio_map_sg - map a bio to a scatterlist
- * @q: request_queue in question
- * @bio: bio being mapped
- * @sglist: scatterlist being mapped
- *
- * Note:
- *    Caller must make sure sg can hold bio->bi_phys_segments entries
- *
- * Will return the number of sg entries setup
- */
-int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
-		   struct scatterlist *sglist)
-{
-	struct scatterlist *sg = NULL;
-	int nsegs;
-	struct bio *next = bio->bi_next;
-	bio->bi_next = NULL;
-
-	nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
-	bio->bi_next = next;
-	if (sg)
-		sg_mark_end(sg);
-
-	BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments);
-	return nsegs;
-}
-EXPORT_SYMBOL(blk_bio_map_sg);
-
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
@@ -385,6 +356,14 @@ static bool req_no_special_merge(struct request *req)
 	return !q->mq_ops && req->special;
 }
 
+static int req_gap_to_prev(struct request *req, struct request *next)
+{
+	struct bio *prev = req->biotail;
+
+	return bvec_gap_to_prev(&prev->bi_io_vec[prev->bi_vcnt - 1],
+				next->bio->bi_io_vec[0].bv_offset);
+}
+
 static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 				struct request *next)
 {
@@ -399,6 +378,10 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	if (req_no_special_merge(req) || req_no_special_merge(next))
 		return 0;
 
+	if (test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags) &&
+	    req_gap_to_prev(req, next))
+		return 0;
+
 	/*
 	 * Will it become too large?
 	 */
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 60c9d4a93fe470..d53a764b05eacd 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -140,35 +140,39 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	return atomic_read(&hctx->nr_active) < depth;
 }
 
-static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
+static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag,
+			 bool nowrap)
 {
-	int tag, org_last_tag, end;
-	bool wrap = last_tag != 0;
+	int tag, org_last_tag = last_tag;
 
-	org_last_tag = last_tag;
-	end = bm->depth;
-	do {
-restart:
-		tag = find_next_zero_bit(&bm->word, end, last_tag);
-		if (unlikely(tag >= end)) {
+	while (1) {
+		tag = find_next_zero_bit(&bm->word, bm->depth, last_tag);
+		if (unlikely(tag >= bm->depth)) {
 			/*
-			 * We started with an offset, start from 0 to
+			 * We started with an offset, and we didn't reset the
+			 * offset to 0 in a failure case, so start from 0 to
 			 * exhaust the map.
 			 */
-			if (wrap) {
-				wrap = false;
-				end = org_last_tag;
-				last_tag = 0;
-				goto restart;
+			if (org_last_tag && last_tag && !nowrap) {
+				last_tag = org_last_tag = 0;
+				continue;
 			}
 			return -1;
 		}
+
+		if (!test_and_set_bit(tag, &bm->word))
+			break;
+
 		last_tag = tag + 1;
-	} while (test_and_set_bit(tag, &bm->word));
+		if (last_tag >= bm->depth - 1)
+			last_tag = 0;
+	}
 
 	return tag;
 }
 
+#define BT_ALLOC_RR(tags) (tags->alloc_policy == BLK_TAG_ALLOC_RR)
+
 /*
  * Straight forward bitmap tag implementation, where each bit is a tag
  * (cleared == free, and set == busy). The small twist is using per-cpu
@@ -181,7 +185,7 @@ static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
  * until the map is exhausted.
  */
 static int __bt_get(struct blk_mq_hw_ctx *hctx, struct blk_mq_bitmap_tags *bt,
-		    unsigned int *tag_cache)
+		    unsigned int *tag_cache, struct blk_mq_tags *tags)
 {
 	unsigned int last_tag, org_last_tag;
 	int index, i, tag;
@@ -193,15 +197,24 @@ static int __bt_get(struct blk_mq_hw_ctx *hctx, struct blk_mq_bitmap_tags *bt,
 	index = TAG_TO_INDEX(bt, last_tag);
 
 	for (i = 0; i < bt->map_nr; i++) {
-		tag = __bt_get_word(&bt->map[index], TAG_TO_BIT(bt, last_tag));
+		tag = __bt_get_word(&bt->map[index], TAG_TO_BIT(bt, last_tag),
+				    BT_ALLOC_RR(tags));
 		if (tag != -1) {
 			tag += (index << bt->bits_per_word);
 			goto done;
 		}
 
-		last_tag = 0;
-		if (++index >= bt->map_nr)
+		/*
+		 * Jump to next index, and reset the last tag to be the
+		 * first tag of that index
+		 */
+		index++;
+		last_tag = (index << bt->bits_per_word);
+
+		if (index >= bt->map_nr) {
 			index = 0;
+			last_tag = 0;
+		}
 	}
 
 	*tag_cache = 0;
@@ -212,7 +225,7 @@ static int __bt_get(struct blk_mq_hw_ctx *hctx, struct blk_mq_bitmap_tags *bt,
 	 * up using the specific cached tag.
 	 */
 done:
-	if (tag == org_last_tag) {
+	if (tag == org_last_tag || unlikely(BT_ALLOC_RR(tags))) {
 		last_tag = tag + 1;
 		if (last_tag >= bt->depth - 1)
 			last_tag = 0;
@@ -241,13 +254,13 @@ static struct bt_wait_state *bt_wait_ptr(struct blk_mq_bitmap_tags *bt,
 static int bt_get(struct blk_mq_alloc_data *data,
 		struct blk_mq_bitmap_tags *bt,
 		struct blk_mq_hw_ctx *hctx,
-		unsigned int *last_tag)
+		unsigned int *last_tag, struct blk_mq_tags *tags)
 {
 	struct bt_wait_state *bs;
 	DEFINE_WAIT(wait);
 	int tag;
 
-	tag = __bt_get(hctx, bt, last_tag);
+	tag = __bt_get(hctx, bt, last_tag, tags);
 	if (tag != -1)
 		return tag;
 
@@ -258,7 +271,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 	do {
 		prepare_to_wait(&bs->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		tag = __bt_get(hctx, bt, last_tag);
+		tag = __bt_get(hctx, bt, last_tag, tags);
 		if (tag != -1)
 			break;
 
@@ -273,7 +286,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 		 * Retry tag allocation after running the hardware queue,
 		 * as running the queue may also have found completions.
 		 */
-		tag = __bt_get(hctx, bt, last_tag);
+		tag = __bt_get(hctx, bt, last_tag, tags);
 		if (tag != -1)
 			break;
 
@@ -304,7 +317,7 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	int tag;
 
 	tag = bt_get(data, &data->hctx->tags->bitmap_tags, data->hctx,
-			&data->ctx->last_tag);
+			&data->ctx->last_tag, data->hctx->tags);
 	if (tag >= 0)
 		return tag + data->hctx->tags->nr_reserved_tags;
 
@@ -320,7 +333,8 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_alloc_data *data)
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL, &zero);
+	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL, &zero,
+		data->hctx->tags);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 
@@ -392,7 +406,8 @@ void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
 
 		BUG_ON(real_tag >= tags->nr_tags);
 		bt_clear_tag(&tags->bitmap_tags, real_tag);
-		*last_tag = real_tag;
+		if (likely(tags->alloc_policy == BLK_TAG_ALLOC_FIFO))
+			*last_tag = real_tag;
 	} else {
 		BUG_ON(tag >= tags->nr_reserved_tags);
 		bt_clear_tag(&tags->breserved_tags, tag);
@@ -509,6 +524,7 @@ static int bt_alloc(struct blk_mq_bitmap_tags *bt, unsigned int depth,
 	bt->bs = kzalloc(BT_WAIT_QUEUES * sizeof(*bt->bs), GFP_KERNEL);
 	if (!bt->bs) {
 		kfree(bt->map);
+		bt->map = NULL;
 		return -ENOMEM;
 	}
 
@@ -529,10 +545,12 @@ static void bt_free(struct blk_mq_bitmap_tags *bt)
 }
 
 static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
-						   int node)
+						   int node, int alloc_policy)
 {
 	unsigned int depth = tags->nr_tags - tags->nr_reserved_tags;
 
+	tags->alloc_policy = alloc_policy;
+
 	if (bt_alloc(&tags->bitmap_tags, depth, node, false))
 		goto enomem;
 	if (bt_alloc(&tags->breserved_tags, tags->nr_reserved_tags, node, true))
@@ -546,7 +564,8 @@ static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
 }
 
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
-				     unsigned int reserved_tags, int node)
+				     unsigned int reserved_tags,
+				     int node, int alloc_policy)
 {
 	struct blk_mq_tags *tags;
 
@@ -562,7 +581,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
-	return blk_mq_init_bitmap_tags(tags, node);
+	return blk_mq_init_bitmap_tags(tags, node, alloc_policy);
 }
 
 void blk_mq_free_tags(struct blk_mq_tags *tags)
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index a6fa0fc9d41a2e..90767b370308da 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -42,10 +42,12 @@ struct blk_mq_tags {
 
 	struct request **rqs;
 	struct list_head page_list;
+
+	int alloc_policy;
 };
 
 
-extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node);
+extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2390c5541e71fb..4f4bea21052e41 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -33,6 +33,7 @@ static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);
+static void blk_mq_run_queues(struct request_queue *q);
 
 /*
  * Check if any of the ctx's have pending work in this hardware queue
@@ -117,7 +118,7 @@ void blk_mq_freeze_queue_start(struct request_queue *q)
 
 	if (freeze) {
 		percpu_ref_kill(&q->mq_usage_counter);
-		blk_mq_run_queues(q, false);
+		blk_mq_run_queues(q);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
@@ -136,6 +137,7 @@ void blk_mq_freeze_queue(struct request_queue *q)
 	blk_mq_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
@@ -902,7 +904,7 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 			&hctx->run_work, 0);
 }
 
-void blk_mq_run_queues(struct request_queue *q, bool async)
+static void blk_mq_run_queues(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
@@ -913,10 +915,9 @@ void blk_mq_run_queues(struct request_queue *q, bool async)
 		    test_bit(BLK_MQ_S_STOPPED, &hctx->state))
 			continue;
 
-		blk_mq_run_hw_queue(hctx, async);
+		blk_mq_run_hw_queue(hctx, false);
 	}
 }
-EXPORT_SYMBOL(blk_mq_run_queues);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
@@ -954,7 +955,6 @@ void blk_mq_start_hw_queues(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_start_hw_queues);
 
-
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
 {
 	struct blk_mq_hw_ctx *hctx;
@@ -1423,7 +1423,8 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 	size_t rq_size, left;
 
 	tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags,
-				set->numa_node);
+				set->numa_node,
+				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
 	if (!tags)
 		return NULL;
 
diff --git a/block/blk-tag.c b/block/blk-tag.c
index a185b86741e5ff..f0344e6939d537 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -119,7 +119,7 @@ init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
 }
 
 static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
-						   int depth)
+						int depth, int alloc_policy)
 {
 	struct blk_queue_tag *tags;
 
@@ -131,6 +131,8 @@ static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
 		goto fail;
 
 	atomic_set(&tags->refcnt, 1);
+	tags->alloc_policy = alloc_policy;
+	tags->next_tag = 0;
 	return tags;
 fail:
 	kfree(tags);
@@ -140,10 +142,11 @@ static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
 /**
  * blk_init_tags - initialize the tag info for an external tag map
  * @depth:	the maximum queue depth supported
+ * @alloc_policy: tag allocation policy
  **/
-struct blk_queue_tag *blk_init_tags(int depth)
+struct blk_queue_tag *blk_init_tags(int depth, int alloc_policy)
 {
-	return __blk_queue_init_tags(NULL, depth);
+	return __blk_queue_init_tags(NULL, depth, alloc_policy);
 }
 EXPORT_SYMBOL(blk_init_tags);
 
@@ -152,19 +155,20 @@ EXPORT_SYMBOL(blk_init_tags);
  * @q:  the request queue for the device
  * @depth:  the maximum queue depth supported
  * @tags: the tag to use
+ * @alloc_policy: tag allocation policy
  *
  * Queue lock must be held here if the function is called to resize an
  * existing map.
  **/
 int blk_queue_init_tags(struct request_queue *q, int depth,
-			struct blk_queue_tag *tags)
+			struct blk_queue_tag *tags, int alloc_policy)
 {
 	int rc;
 
 	BUG_ON(tags && q->queue_tags && tags != q->queue_tags);
 
 	if (!tags && !q->queue_tags) {
-		tags = __blk_queue_init_tags(q, depth);
+		tags = __blk_queue_init_tags(q, depth, alloc_policy);
 
 		if (!tags)
 			return -ENOMEM;
@@ -344,9 +348,21 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	}
 
 	do {
-		tag = find_first_zero_bit(bqt->tag_map, max_depth);
-		if (tag >= max_depth)
-			return 1;
+		if (bqt->alloc_policy == BLK_TAG_ALLOC_FIFO) {
+			tag = find_first_zero_bit(bqt->tag_map, max_depth);
+			if (tag >= max_depth)
+				return 1;
+		} else {
+			int start = bqt->next_tag;
+			int size = min_t(int, bqt->max_depth, max_depth + start);
+			tag = find_next_zero_bit(bqt->tag_map, size, start);
+			if (tag >= size && start + size > bqt->max_depth) {
+				size = start + size - bqt->max_depth;
+				tag = find_first_zero_bit(bqt->tag_map, size);
+			}
+			if (tag >= size)
+				return 1;
+		}
 
 	} while (test_and_set_bit_lock(tag, bqt->tag_map));
 	/*
@@ -354,6 +370,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	 * See blk_queue_end_tag for details.
 	 */
 
+	bqt->next_tag = (tag + 1) % bqt->max_depth;
 	rq->cmd_flags |= REQ_QUEUED;
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;
diff --git a/block/bsg.c b/block/bsg.c
index 276e869e686cbb..d214e929ce1855 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -136,42 +136,6 @@ static inline struct hlist_head *bsg_dev_idx_hash(int index)
 	return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)];
 }
 
-static int bsg_io_schedule(struct bsg_device *bd)
-{
-	DEFINE_WAIT(wait);
-	int ret = 0;
-
-	spin_lock_irq(&bd->lock);
-
-	BUG_ON(bd->done_cmds > bd->queued_cmds);
-
-	/*
-	 * -ENOSPC or -ENODATA?  I'm going for -ENODATA, meaning "I have no
-	 * work to do", even though we return -ENOSPC after this same test
-	 * during bsg_write() -- there, it means our buffer can't have more
-	 * bsg_commands added to it, thus has no space left.
-	 */
-	if (bd->done_cmds == bd->queued_cmds) {
-		ret = -ENODATA;
-		goto unlock;
-	}
-
-	if (!test_bit(BSG_F_BLOCK, &bd->flags)) {
-		ret = -EAGAIN;
-		goto unlock;
-	}
-
-	prepare_to_wait(&bd->wq_done, &wait, TASK_UNINTERRUPTIBLE);
-	spin_unlock_irq(&bd->lock);
-	io_schedule();
-	finish_wait(&bd->wq_done, &wait);
-
-	return ret;
-unlock:
-	spin_unlock_irq(&bd->lock);
-	return ret;
-}
-
 static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
 				fmode_t has_write_perm)
@@ -482,6 +446,30 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	return ret;
 }
 
+static bool bsg_complete(struct bsg_device *bd)
+{
+	bool ret = false;
+	bool spin;
+
+	do {
+		spin_lock_irq(&bd->lock);
+
+		BUG_ON(bd->done_cmds > bd->queued_cmds);
+
+		/*
+		 * All commands consumed.
+		 */
+		if (bd->done_cmds == bd->queued_cmds)
+			ret = true;
+
+		spin = !test_bit(BSG_F_BLOCK, &bd->flags);
+
+		spin_unlock_irq(&bd->lock);
+	} while (!ret && spin);
+
+	return ret;
+}
+
 static int bsg_complete_all_commands(struct bsg_device *bd)
 {
 	struct bsg_command *bc;
@@ -492,17 +480,7 @@ static int bsg_complete_all_commands(struct bsg_device *bd)
 	/*
 	 * wait for all commands to complete
 	 */
-	ret = 0;
-	do {
-		ret = bsg_io_schedule(bd);
-		/*
-		 * look for -ENODATA specifically -- we'll sometimes get
-		 * -ERESTARTSYS when we've taken a signal, but we can't
-		 * return until we're done freeing the queue, so ignore
-		 * it.  The signal will get handled when we're done freeing
-		 * the bsg_device.
-		 */
-	} while (ret != -ENODATA);
+	io_wait_event(bd->wq_done, bsg_complete(bd));
 
 	/*
 	 * discard done commands
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 6f2751d305dede..5da8e6e9ab4bfd 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3590,6 +3590,11 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 
 	blkcg = bio_blkcg(bio);
 	cfqg = cfq_lookup_create_cfqg(cfqd, blkcg);
+	if (!cfqg) {
+		cfqq = &cfqd->oom_cfqq;
+		goto out;
+	}
+
 	cfqq = cic_to_cfqq(cic, is_sync);
 
 	/*
@@ -3626,7 +3631,7 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 		} else
 			cfqq = &cfqd->oom_cfqq;
 	}
-
+out:
 	if (new_cfqq)
 		kmem_cache_free(cfq_pool, new_cfqq);
 
@@ -3656,12 +3661,17 @@ static struct cfq_queue *
 cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 	      struct bio *bio, gfp_t gfp_mask)
 {
-	const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
-	const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
+	int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
+	int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
 	struct cfq_queue **async_cfqq = NULL;
 	struct cfq_queue *cfqq = NULL;
 
 	if (!is_sync) {
+		if (!ioprio_valid(cic->ioprio)) {
+			struct task_struct *tsk = current;
+			ioprio = task_nice_ioprio(tsk);
+			ioprio_class = task_nice_ioclass(tsk);
+		}
 		async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
 		cfqq = *async_cfqq;
 	}
diff --git a/block/ioctl.c b/block/ioctl.c
index 6c7bf903742f92..7d8befde2aca7a 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -198,7 +198,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
 	if (start + len > (i_size_read(bdev->bd_inode) >> 9))
 		return -EINVAL;
 
-	return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL);
+	return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL, false);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)
diff --git a/block/partitions/check.c b/block/partitions/check.c
index 9ac1df74f69940..16118d11dbfc00 100644
--- a/block/partitions/check.c
+++ b/block/partitions/check.c
@@ -184,12 +184,12 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
 	if (err)
 	/* The partition is unrecognized. So report I/O errors if there were any */
 		res = err;
-	if (!res)
-		strlcat(state->pp_buf, " unknown partition table\n", PAGE_SIZE);
-	else if (warn_no_part)
-		strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE);
-
-	printk(KERN_INFO "%s", state->pp_buf);
+	if (res) {
+		if (warn_no_part)
+			strlcat(state->pp_buf,
+				" unable to read partition table\n", PAGE_SIZE);
+		printk(KERN_INFO "%s", state->pp_buf);
+	}
 
 	free_page((unsigned long)state->pp_buf);
 	free_partitions(state);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 28163fad3c5d88..e1f71c3961934b 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -332,7 +332,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 
 	ret = 0;
 	if (hdr->iovec_count) {
-		size_t iov_data_len;
+		struct iov_iter i;
 		struct iovec *iov = NULL;
 
 		ret = rw_copy_check_uvector(-1, hdr->dxferp, hdr->iovec_count,
@@ -342,20 +342,11 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 			goto out_free_cdb;
 		}
 
-		iov_data_len = ret;
-		ret = 0;
-
 		/* SG_IO howto says that the shorter of the two wins */
-		if (hdr->dxfer_len < iov_data_len) {
-			hdr->iovec_count = iov_shorten(iov,
-						       hdr->iovec_count,
-						       hdr->dxfer_len);
-			iov_data_len = hdr->dxfer_len;
-		}
+		iov_iter_init(&i, rq_data_dir(rq), iov, hdr->iovec_count,
+			      min_t(unsigned, ret, hdr->dxfer_len));
 
-		ret = blk_rq_map_user_iov(q, rq, NULL, (struct sg_iovec *) iov,
-					  hdr->iovec_count,
-					  iov_data_len, GFP_KERNEL);
+		ret = blk_rq_map_user_iov(q, rq, NULL, &i, GFP_KERNEL);
 		kfree(iov);
 	} else if (hdr->dxfer_len)
 		ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len,
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index 57078e3ea9b746..4f3f888d33bb18 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -111,8 +111,8 @@ void acpi_ut_track_stack_ptr(void)
  * RETURN:      Updated pointer to the function name
  *
  * DESCRIPTION: Remove the "Acpi" prefix from the function name, if present.
- *              This allows compiler macros such as __FUNCTION__ to be used
- *              with no change to the debug output.
+ *              This allows compiler macros such as __func__ to be used with no
+ *              change to the debug output.
  *
  ******************************************************************************/
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 4b0d5e71858e28..4c35f0822d06e5 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1585,8 +1585,6 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
 	else
 		tag = 0;
 
-	if (test_and_set_bit(tag, &ap->qc_allocated))
-		BUG();
 	qc = __ata_qc_from_tag(ap, tag);
 
 	qc->tag = tag;
@@ -4722,69 +4720,36 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 }
 
 /**
- *	ata_qc_new - Request an available ATA command, for queueing
- *	@ap: target port
- *
- *	Some ATA host controllers may implement a queue depth which is less
- *	than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
- *	the hardware limitation.
+ *	ata_qc_new_init - Request an available ATA command, and initialize it
+ *	@dev: Device from whom we request an available command structure
  *
  *	LOCKING:
  *	None.
  */
 
-static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
+struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag)
 {
-	struct ata_queued_cmd *qc = NULL;
-	unsigned int max_queue = ap->host->n_tags;
-	unsigned int i, tag;
+	struct ata_port *ap = dev->link->ap;
+	struct ata_queued_cmd *qc;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
-		if (ap->flags & ATA_FLAG_LOWTAG)
-			tag = i;
-		else
-			tag = tag < max_queue ? tag : 0;
-
-		/* the last tag is reserved for internal command. */
-		if (tag == ATA_TAG_INTERNAL)
-			continue;
-
-		if (!test_and_set_bit(tag, &ap->qc_allocated)) {
-			qc = __ata_qc_from_tag(ap, tag);
-			qc->tag = tag;
-			ap->last_tag = tag;
-			break;
-		}
+	/* libsas case */
+	if (!ap->scsi_host) {
+		tag = ata_sas_allocate_tag(ap);
+		if (tag < 0)
+			return NULL;
 	}
 
-	return qc;
-}
-
-/**
- *	ata_qc_new_init - Request an available ATA command, and initialize it
- *	@dev: Device from whom we request an available command structure
- *
- *	LOCKING:
- *	None.
- */
-
-struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev)
-{
-	struct ata_port *ap = dev->link->ap;
-	struct ata_queued_cmd *qc;
-
-	qc = ata_qc_new(ap);
-	if (qc) {
-		qc->scsicmd = NULL;
-		qc->ap = ap;
-		qc->dev = dev;
+	qc = __ata_qc_from_tag(ap, tag);
+	qc->tag = tag;
+	qc->scsicmd = NULL;
+	qc->ap = ap;
+	qc->dev = dev;
 
-		ata_qc_reinit(qc);
-	}
+	ata_qc_reinit(qc);
 
 	return qc;
 }
@@ -4811,7 +4776,8 @@ void ata_qc_free(struct ata_queued_cmd *qc)
 	tag = qc->tag;
 	if (likely(ata_tag_valid(tag))) {
 		qc->tag = ATA_TAG_POISON;
-		clear_bit(tag, &ap->qc_allocated);
+		if (!ap->scsi_host)
+			ata_sas_free_tag(tag, ap);
 	}
 }
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 280729325ebda9..b061ba2c31d8f5 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -756,7 +756,7 @@ static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev,
 {
 	struct ata_queued_cmd *qc;
 
-	qc = ata_qc_new_init(dev);
+	qc = ata_qc_new_init(dev, cmd->request->tag);
 	if (qc) {
 		qc->scsicmd = cmd;
 		qc->scsidone = cmd->scsi_done;
@@ -3668,6 +3668,9 @@ int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht)
 		 */
 		shost->max_host_blocked = 1;
 
+		if (scsi_init_shared_tag_map(shost, host->n_tags))
+			goto err_add;
+
 		rc = scsi_add_host_with_dma(ap->scsi_host,
 						&ap->tdev, ap->host->dev);
 		if (rc)
@@ -4230,3 +4233,31 @@ int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap)
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ata_sas_queuecmd);
+
+int ata_sas_allocate_tag(struct ata_port *ap)
+{
+	unsigned int max_queue = ap->host->n_tags;
+	unsigned int i, tag;
+
+	for (i = 0, tag = ap->sas_last_tag + 1; i < max_queue; i++, tag++) {
+		if (ap->flags & ATA_FLAG_LOWTAG)
+			tag = 1;
+		else
+			tag = tag < max_queue ? tag : 0;
+
+		/* the last tag is reserved for internal command. */
+		if (tag == ATA_TAG_INTERNAL)
+			continue;
+
+		if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) {
+			ap->sas_last_tag = tag;
+			return tag;
+		}
+	}
+	return -1;
+}
+
+void ata_sas_free_tag(unsigned int tag, struct ata_port *ap)
+{
+	clear_bit(tag, &ap->sas_tag_allocated);
+}
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 82ebe263d2f161..f840ca18a7c014 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -63,7 +63,7 @@ extern struct ata_link *ata_dev_phys_link(struct ata_device *dev);
 extern void ata_force_cbl(struct ata_port *ap);
 extern u64 ata_tf_to_lba(const struct ata_taskfile *tf);
 extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf);
-extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev);
+extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag);
 extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
 			   u64 block, u32 n_block, unsigned int tf_flags,
 			   unsigned int tag);
@@ -144,6 +144,8 @@ extern void ata_scsi_dev_rescan(struct work_struct *work);
 extern int ata_bus_probe(struct ata_port *ap);
 extern int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
 			      unsigned int id, u64 lun);
+int ata_sas_allocate_tag(struct ata_port *ap);
+void ata_sas_free_tag(unsigned int tag, struct ata_port *ap);
 
 
 /* libata-eh.c */
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index ea655949023f4a..ba2667fa0528ff 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -388,6 +388,7 @@ static struct scsi_host_template sil24_sht = {
 	.can_queue		= SIL24_MAX_CMDS,
 	.sg_tablesize		= SIL24_MAX_SGE,
 	.dma_boundary		= ATA_DMA_BOUNDARY,
+	.tag_alloc_policy	= BLK_TAG_ALLOC_FIFO,
 };
 
 static struct ata_port_operations sil24_ops = {
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 3598110d2cefcf..c01b921b1b4a8a 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -370,25 +370,25 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 }
 
 #ifdef CONFIG_BLK_DEV_XIP
-static int brd_direct_access(struct block_device *bdev, sector_t sector,
-			void **kaddr, unsigned long *pfn)
+static long brd_direct_access(struct block_device *bdev, sector_t sector,
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
 
 	if (!brd)
 		return -ENODEV;
-	if (sector & (PAGE_SECTORS-1))
-		return -EINVAL;
-	if (sector + PAGE_SECTORS > get_capacity(bdev->bd_disk))
-		return -ERANGE;
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);
 	*pfn = page_to_pfn(page);
 
-	return 0;
+	/*
+	 * TODO: If size > PAGE_SIZE, we could look to see if the next page in
+	 * the file happens to be mapped to the next page of physical RAM.
+	 */
+	return PAGE_SIZE;
 }
 #endif
 
@@ -438,19 +438,18 @@ static const struct block_device_operations brd_fops = {
 /*
  * And now the modules code and kernel interface.
  */
-static int rd_nr;
-int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
-static int max_part;
-static int part_shift;
-static int part_show = 0;
+static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
 module_param(rd_nr, int, S_IRUGO);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
+
+int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
 module_param(rd_size, int, S_IRUGO);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
+
+static int max_part = 1;
 module_param(max_part, int, S_IRUGO);
-MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
-module_param(part_show, int, S_IRUGO);
-MODULE_PARM_DESC(part_show, "Control RAM disk visibility in /proc/partitions");
+MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 MODULE_ALIAS("rd");
@@ -487,25 +486,33 @@ static struct brd_device *brd_alloc(int i)
 	brd->brd_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!brd->brd_queue)
 		goto out_free_dev;
+
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
+	/* This is so fdisk will align partitions on 4k, because of
+	 * direct_access API needing 4k alignment, returning a PFN
+	 * (This is only a problem on very small devices <= 4M,
+	 *  otherwise fdisk will align on 1M. Regardless this call
+	 *  is harmless)
+	 */
+	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
+
 	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
 	brd->brd_queue->limits.max_discard_sectors = UINT_MAX;
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 
-	disk = brd->brd_disk = alloc_disk(1 << part_shift);
+	disk = brd->brd_disk = alloc_disk(max_part);
 	if (!disk)
 		goto out_free_queue;
 	disk->major		= RAMDISK_MAJOR;
-	disk->first_minor	= i << part_shift;
+	disk->first_minor	= i * max_part;
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
 	disk->queue		= brd->brd_queue;
-	if (!part_show)
-		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
+	disk->flags		= GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
 
@@ -527,10 +534,11 @@ static void brd_free(struct brd_device *brd)
 	kfree(brd);
 }
 
-static struct brd_device *brd_init_one(int i)
+static struct brd_device *brd_init_one(int i, bool *new)
 {
 	struct brd_device *brd;
 
+	*new = false;
 	list_for_each_entry(brd, &brd_devices, brd_list) {
 		if (brd->brd_number == i)
 			goto out;
@@ -541,6 +549,7 @@ static struct brd_device *brd_init_one(int i)
 		add_disk(brd->brd_disk);
 		list_add_tail(&brd->brd_list, &brd_devices);
 	}
+	*new = true;
 out:
 	return brd;
 }
@@ -556,70 +565,46 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 {
 	struct brd_device *brd;
 	struct kobject *kobj;
+	bool new;
 
 	mutex_lock(&brd_devices_mutex);
-	brd = brd_init_one(MINOR(dev) >> part_shift);
+	brd = brd_init_one(MINOR(dev) / max_part, &new);
 	kobj = brd ? get_disk(brd->brd_disk) : NULL;
 	mutex_unlock(&brd_devices_mutex);
 
-	*part = 0;
+	if (new)
+		*part = 0;
+
 	return kobj;
 }
 
 static int __init brd_init(void)
 {
-	int i, nr;
-	unsigned long range;
 	struct brd_device *brd, *next;
+	int i;
 
 	/*
 	 * brd module now has a feature to instantiate underlying device
 	 * structure on-demand, provided that there is an access dev node.
-	 * However, this will not work well with user space tool that doesn't
-	 * know about such "feature".  In order to not break any existing
-	 * tool, we do the following:
 	 *
-	 * (1) if rd_nr is specified, create that many upfront, and this
-	 *     also becomes a hard limit.
-	 * (2) if rd_nr is not specified, create CONFIG_BLK_DEV_RAM_COUNT
-	 *     (default 16) rd device on module load, user can further
-	 *     extend brd device by create dev node themselves and have
-	 *     kernel automatically instantiate actual device on-demand.
+	 * (1) if rd_nr is specified, create that many upfront. else
+	 *     it defaults to CONFIG_BLK_DEV_RAM_COUNT
+	 * (2) User can further extend brd devices by create dev node themselves
+	 *     and have kernel automatically instantiate actual device
+	 *     on-demand. Example:
+	 *		mknod /path/devnod_name b 1 X	# 1 is the rd major
+	 *		fdisk -l /path/devnod_name
+	 *	If (X / max_part) was not already created it will be created
+	 *	dynamically.
 	 */
 
-	part_shift = 0;
-	if (max_part > 0) {
-		part_shift = fls(max_part);
-
-		/*
-		 * Adjust max_part according to part_shift as it is exported
-		 * to user space so that user can decide correct minor number
-		 * if [s]he want to create more devices.
-		 *
-		 * Note that -1 is required because partition 0 is reserved
-		 * for the whole disk.
-		 */
-		max_part = (1UL << part_shift) - 1;
-	}
-
-	if ((1UL << part_shift) > DISK_MAX_PARTS)
-		return -EINVAL;
-
-	if (rd_nr > 1UL << (MINORBITS - part_shift))
-		return -EINVAL;
-
-	if (rd_nr) {
-		nr = rd_nr;
-		range = rd_nr << part_shift;
-	} else {
-		nr = CONFIG_BLK_DEV_RAM_COUNT;
-		range = 1UL << MINORBITS;
-	}
-
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
 		return -EIO;
 
-	for (i = 0; i < nr; i++) {
+	if (unlikely(!max_part))
+		max_part = 1;
+
+	for (i = 0; i < rd_nr; i++) {
 		brd = brd_alloc(i);
 		if (!brd)
 			goto out_free;
@@ -631,10 +616,10 @@ static int __init brd_init(void)
 	list_for_each_entry(brd, &brd_devices, brd_list)
 		add_disk(brd->brd_disk);
 
-	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), range,
+	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS,
 				  THIS_MODULE, brd_probe, NULL, NULL);
 
-	printk(KERN_INFO "brd: module loaded\n");
+	pr_info("brd: module loaded\n");
 	return 0;
 
 out_free:
@@ -644,21 +629,21 @@ static int __init brd_init(void)
 	}
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
 
+	pr_info("brd: module NOT loaded !!!\n");
 	return -ENOMEM;
 }
 
 static void __exit brd_exit(void)
 {
-	unsigned long range;
 	struct brd_device *brd, *next;
 
-	range = rd_nr ? rd_nr << part_shift : 1UL << MINORBITS;
-
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
 
-	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), range);
+	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS);
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
+
+	pr_info("brd: module unloaded\n");
 }
 
 module_init(brd_init);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index d169b4a7926700..cee20354ac37b8 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1388,7 +1388,7 @@ int drbd_submit_peer_request(struct drbd_device *device,
 		list_add_tail(&peer_req->w.list, &device->active_ee);
 		spin_unlock_irq(&device->resource->req_lock);
 		if (blkdev_issue_zeroout(device->ldev->backing_bdev,
-			sector, data_size >> 9, GFP_NOIO))
+			sector, data_size >> 9, GFP_NOIO, false))
 			peer_req->flags |= EE_WAS_ERROR;
 		drbd_endio_write_sec_final(peer_req);
 		return 0;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 56d46ffb08e151..a08cda95528503 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4112,6 +4112,13 @@ static ssize_t floppy_cmos_show(struct device *dev,
 
 static DEVICE_ATTR(cmos, S_IRUGO, floppy_cmos_show, NULL);
 
+static struct attribute *floppy_dev_attrs[] = {
+	&dev_attr_cmos.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(floppy_dev);
+
 static void floppy_device_release(struct device *dev)
 {
 }
@@ -4324,16 +4331,12 @@ static int __init do_floppy_init(void)
 		floppy_device[drive].name = floppy_device_name;
 		floppy_device[drive].id = drive;
 		floppy_device[drive].dev.release = floppy_device_release;
+		floppy_device[drive].dev.groups = floppy_dev_groups;
 
 		err = platform_device_register(&floppy_device[drive]);
 		if (err)
 			goto out_remove_drives;
 
-		err = device_create_file(&floppy_device[drive].dev,
-					 &dev_attr_cmos);
-		if (err)
-			goto out_unreg_platform_dev;
-
 		/* to be cleaned up... */
 		disks[drive]->private_data = (void *)(long)drive;
 		disks[drive]->flags |= GENHD_FL_REMOVABLE;
@@ -4343,13 +4346,10 @@ static int __init do_floppy_init(void)
 
 	return 0;
 
-out_unreg_platform_dev:
-	platform_device_unregister(&floppy_device[drive]);
 out_remove_drives:
 	while (drive--) {
 		if (floppy_available(drive)) {
 			del_gendisk(disks[drive]);
-			device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
 			platform_device_unregister(&floppy_device[drive]);
 		}
 	}
@@ -4594,7 +4594,6 @@ static void __exit floppy_module_exit(void)
 
 		if (floppy_available(drive)) {
 			del_gendisk(disks[drive]);
-			device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
 			platform_device_unregister(&floppy_device[drive]);
 		}
 		blk_cleanup_queue(disks[drive]->queue);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 6cb1beb47c25d1..d1f168b7363432 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -85,6 +85,8 @@ static DEFINE_MUTEX(loop_index_mutex);
 static int max_part;
 static int part_shift;
 
+static struct workqueue_struct *loop_wq;
+
 /*
  * Transfer functions
  */
@@ -284,12 +286,12 @@ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
 	return ret;
 }
 
-static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
+static int lo_send(struct loop_device *lo, struct request *rq, loff_t pos)
 {
 	int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
 			struct page *page);
 	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct req_iterator iter;
 	struct page *page = NULL;
 	int ret = 0;
 
@@ -303,7 +305,7 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 		do_lo_send = do_lo_send_direct_write;
 	}
 
-	bio_for_each_segment(bvec, bio, iter) {
+	rq_for_each_segment(bvec, rq, iter) {
 		ret = do_lo_send(lo, &bvec, pos, page);
 		if (ret < 0)
 			break;
@@ -391,19 +393,22 @@ do_lo_receive(struct loop_device *lo,
 }
 
 static int
-lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
+lo_receive(struct loop_device *lo, struct request *rq, int bsize, loff_t pos)
 {
 	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct req_iterator iter;
 	ssize_t s;
 
-	bio_for_each_segment(bvec, bio, iter) {
+	rq_for_each_segment(bvec, rq, iter) {
 		s = do_lo_receive(lo, &bvec, bsize, pos);
 		if (s < 0)
 			return s;
 
 		if (s != bvec.bv_len) {
-			zero_fill_bio(bio);
+			struct bio *bio;
+
+			__rq_for_each_bio(bio, rq)
+				zero_fill_bio(bio);
 			break;
 		}
 		pos += bvec.bv_len;
@@ -411,106 +416,58 @@ lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
 	return 0;
 }
 
-static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
+static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
 {
-	loff_t pos;
+	/*
+	 * We use punch hole to reclaim the free space used by the
+	 * image a.k.a. discard. However we do not support discard if
+	 * encryption is enabled, because it may give an attacker
+	 * useful information.
+	 */
+	struct file *file = lo->lo_backing_file;
+	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	int ret;
 
-	pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset;
-
-	if (bio_rw(bio) == WRITE) {
-		struct file *file = lo->lo_backing_file;
-
-		if (bio->bi_rw & REQ_FLUSH) {
-			ret = vfs_fsync(file, 0);
-			if (unlikely(ret && ret != -EINVAL)) {
-				ret = -EIO;
-				goto out;
-			}
-		}
-
-		/*
-		 * We use punch hole to reclaim the free space used by the
-		 * image a.k.a. discard. However we do not support discard if
-		 * encryption is enabled, because it may give an attacker
-		 * useful information.
-		 */
-		if (bio->bi_rw & REQ_DISCARD) {
-			struct file *file = lo->lo_backing_file;
-			int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
-
-			if ((!file->f_op->fallocate) ||
-			    lo->lo_encrypt_key_size) {
-				ret = -EOPNOTSUPP;
-				goto out;
-			}
-			ret = file->f_op->fallocate(file, mode, pos,
-						    bio->bi_iter.bi_size);
-			if (unlikely(ret && ret != -EINVAL &&
-				     ret != -EOPNOTSUPP))
-				ret = -EIO;
-			goto out;
-		}
-
-		ret = lo_send(lo, bio, pos);
-
-		if ((bio->bi_rw & REQ_FUA) && !ret) {
-			ret = vfs_fsync(file, 0);
-			if (unlikely(ret && ret != -EINVAL))
-				ret = -EIO;
-		}
-	} else
-		ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
+	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
 
-out:
+	ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
+	if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
+		ret = -EIO;
+ out:
 	return ret;
 }
 
-/*
- * Add bio to back of pending list
- */
-static void loop_add_bio(struct loop_device *lo, struct bio *bio)
+static int lo_req_flush(struct loop_device *lo, struct request *rq)
 {
-	lo->lo_bio_count++;
-	bio_list_add(&lo->lo_bio_list, bio);
-}
+	struct file *file = lo->lo_backing_file;
+	int ret = vfs_fsync(file, 0);
+	if (unlikely(ret && ret != -EINVAL))
+		ret = -EIO;
 
-/*
- * Grab first pending buffer
- */
-static struct bio *loop_get_bio(struct loop_device *lo)
-{
-	lo->lo_bio_count--;
-	return bio_list_pop(&lo->lo_bio_list);
+	return ret;
 }
 
-static void loop_make_request(struct request_queue *q, struct bio *old_bio)
+static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 {
-	struct loop_device *lo = q->queuedata;
-	int rw = bio_rw(old_bio);
-
-	if (rw == READA)
-		rw = READ;
+	loff_t pos;
+	int ret;
 
-	BUG_ON(!lo || (rw != READ && rw != WRITE));
+	pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
-	spin_lock_irq(&lo->lo_lock);
-	if (lo->lo_state != Lo_bound)
-		goto out;
-	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
-		goto out;
-	if (lo->lo_bio_count >= q->nr_congestion_on)
-		wait_event_lock_irq(lo->lo_req_wait,
-				    lo->lo_bio_count < q->nr_congestion_off,
-				    lo->lo_lock);
-	loop_add_bio(lo, old_bio);
-	wake_up(&lo->lo_event);
-	spin_unlock_irq(&lo->lo_lock);
-	return;
+	if (rq->cmd_flags & REQ_WRITE) {
+		if (rq->cmd_flags & REQ_FLUSH)
+			ret = lo_req_flush(lo, rq);
+		else if (rq->cmd_flags & REQ_DISCARD)
+			ret = lo_discard(lo, rq, pos);
+		else
+			ret = lo_send(lo, rq, pos);
+	} else
+		ret = lo_receive(lo, rq, lo->lo_blocksize, pos);
 
-out:
-	spin_unlock_irq(&lo->lo_lock);
-	bio_io_error(old_bio);
+	return ret;
 }
 
 struct switch_request {
@@ -518,57 +475,26 @@ struct switch_request {
 	struct completion wait;
 };
 
-static void do_loop_switch(struct loop_device *, struct switch_request *);
-
-static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio)
-{
-	if (unlikely(!bio->bi_bdev)) {
-		do_loop_switch(lo, bio->bi_private);
-		bio_put(bio);
-	} else {
-		int ret = do_bio_filebacked(lo, bio);
-		bio_endio(bio, ret);
-	}
-}
-
 /*
- * worker thread that handles reads/writes to file backed loop devices,
- * to avoid blocking in our make_request_fn. it also does loop decrypting
- * on reads for block backed loop, as that is too heavy to do from
- * b_end_io context where irqs may be disabled.
- *
- * Loop explanation:  loop_clr_fd() sets lo_state to Lo_rundown before
- * calling kthread_stop().  Therefore once kthread_should_stop() is
- * true, make_request will not place any more requests.  Therefore
- * once kthread_should_stop() is true and lo_bio is NULL, we are
- * done with the loop.
+ * Do the actual switch; called from the BIO completion routine
  */
-static int loop_thread(void *data)
+static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
 {
-	struct loop_device *lo = data;
-	struct bio *bio;
-
-	set_user_nice(current, MIN_NICE);
-
-	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
-
-		wait_event_interruptible(lo->lo_event,
-				!bio_list_empty(&lo->lo_bio_list) ||
-				kthread_should_stop());
-
-		if (bio_list_empty(&lo->lo_bio_list))
-			continue;
-		spin_lock_irq(&lo->lo_lock);
-		bio = loop_get_bio(lo);
-		if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
-			wake_up(&lo->lo_req_wait);
-		spin_unlock_irq(&lo->lo_lock);
+	struct file *file = p->file;
+	struct file *old_file = lo->lo_backing_file;
+	struct address_space *mapping;
 
-		BUG_ON(!bio);
-		loop_handle_bio(lo, bio);
-	}
+	/* if no new file, only flush of queued bios requested */
+	if (!file)
+		return;
 
-	return 0;
+	mapping = file->f_mapping;
+	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
+	lo->lo_backing_file = file;
+	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
+		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
+	lo->old_gfp_mask = mapping_gfp_mask(mapping);
+	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 }
 
 /*
@@ -579,15 +505,18 @@ static int loop_thread(void *data)
 static int loop_switch(struct loop_device *lo, struct file *file)
 {
 	struct switch_request w;
-	struct bio *bio = bio_alloc(GFP_KERNEL, 0);
-	if (!bio)
-		return -ENOMEM;
-	init_completion(&w.wait);
+
 	w.file = file;
-	bio->bi_private = &w;
-	bio->bi_bdev = NULL;
-	loop_make_request(lo->lo_queue, bio);
-	wait_for_completion(&w.wait);
+
+	/* freeze queue and wait for completion of scheduled requests */
+	blk_mq_freeze_queue(lo->lo_queue);
+
+	/* do the switch action */
+	do_loop_switch(lo, &w);
+
+	/* unfreeze */
+	blk_mq_unfreeze_queue(lo->lo_queue);
+
 	return 0;
 }
 
@@ -596,38 +525,9 @@ static int loop_switch(struct loop_device *lo, struct file *file)
  */
 static int loop_flush(struct loop_device *lo)
 {
-	/* loop not yet configured, no running thread, nothing to flush */
-	if (!lo->lo_thread)
-		return 0;
-
 	return loop_switch(lo, NULL);
 }
 
-/*
- * Do the actual switch; called from the BIO completion routine
- */
-static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
-{
-	struct file *file = p->file;
-	struct file *old_file = lo->lo_backing_file;
-	struct address_space *mapping;
-
-	/* if no new file, only flush of queued bios requested */
-	if (!file)
-		goto out;
-
-	mapping = file->f_mapping;
-	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
-	lo->lo_backing_file = file;
-	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
-		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
-	lo->old_gfp_mask = mapping_gfp_mask(mapping);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
-out:
-	complete(&p->wait);
-}
-
-
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -889,12 +789,9 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->transfer = transfer_none;
 	lo->ioctl = NULL;
 	lo->lo_sizelimit = 0;
-	lo->lo_bio_count = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	bio_list_init(&lo->lo_bio_list);
-
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
@@ -906,14 +803,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 
 	set_blocksize(bdev, lo_blocksize);
 
-	lo->lo_thread = kthread_create(loop_thread, lo, "loop%d",
-						lo->lo_number);
-	if (IS_ERR(lo->lo_thread)) {
-		error = PTR_ERR(lo->lo_thread);
-		goto out_clr;
-	}
 	lo->lo_state = Lo_bound;
-	wake_up_process(lo->lo_thread);
 	if (part_shift)
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
@@ -925,18 +815,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	bdgrab(bdev);
 	return 0;
 
-out_clr:
-	loop_sysfs_exit(lo);
-	lo->lo_thread = NULL;
-	lo->lo_device = NULL;
-	lo->lo_backing_file = NULL;
-	lo->lo_flags = 0;
-	set_capacity(lo->lo_disk, 0);
-	invalidate_bdev(bdev);
-	bd_set_size(bdev, 0);
-	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask);
-	lo->lo_state = Lo_unbound;
  out_putf:
 	fput(file);
  out:
@@ -1012,11 +890,6 @@ static int loop_clr_fd(struct loop_device *lo)
 
 	spin_lock_irq(&lo->lo_lock);
 	lo->lo_state = Lo_rundown;
-	spin_unlock_irq(&lo->lo_lock);
-
-	kthread_stop(lo->lo_thread);
-
-	spin_lock_irq(&lo->lo_lock);
 	lo->lo_backing_file = NULL;
 	spin_unlock_irq(&lo->lo_lock);
 
@@ -1028,7 +901,6 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	lo->lo_encrypt_key_size = 0;
-	lo->lo_thread = NULL;
 	memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
 	memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
@@ -1601,6 +1473,105 @@ int loop_unregister_transfer(int number)
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
+static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+
+	blk_mq_start_request(bd->rq);
+
+	if (cmd->rq->cmd_flags & REQ_WRITE) {
+		struct loop_device *lo = cmd->rq->q->queuedata;
+		bool need_sched = true;
+
+		spin_lock_irq(&lo->lo_lock);
+		if (lo->write_started)
+			need_sched = false;
+		else
+			lo->write_started = true;
+		list_add_tail(&cmd->list, &lo->write_cmd_head);
+		spin_unlock_irq(&lo->lo_lock);
+
+		if (need_sched)
+			queue_work(loop_wq, &lo->write_work);
+	} else {
+		queue_work(loop_wq, &cmd->read_work);
+	}
+
+	return BLK_MQ_RQ_QUEUE_OK;
+}
+
+static void loop_handle_cmd(struct loop_cmd *cmd)
+{
+	const bool write = cmd->rq->cmd_flags & REQ_WRITE;
+	struct loop_device *lo = cmd->rq->q->queuedata;
+	int ret = -EIO;
+
+	if (lo->lo_state != Lo_bound)
+		goto failed;
+
+	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY))
+		goto failed;
+
+	ret = do_req_filebacked(lo, cmd->rq);
+
+ failed:
+	if (ret)
+		cmd->rq->errors = -EIO;
+	blk_mq_complete_request(cmd->rq);
+}
+
+static void loop_queue_write_work(struct work_struct *work)
+{
+	struct loop_device *lo =
+		container_of(work, struct loop_device, write_work);
+	LIST_HEAD(cmd_list);
+
+	spin_lock_irq(&lo->lo_lock);
+ repeat:
+	list_splice_init(&lo->write_cmd_head, &cmd_list);
+	spin_unlock_irq(&lo->lo_lock);
+
+	while (!list_empty(&cmd_list)) {
+		struct loop_cmd *cmd = list_first_entry(&cmd_list,
+				struct loop_cmd, list);
+		list_del_init(&cmd->list);
+		loop_handle_cmd(cmd);
+	}
+
+	spin_lock_irq(&lo->lo_lock);
+	if (!list_empty(&lo->write_cmd_head))
+		goto repeat;
+	lo->write_started = false;
+	spin_unlock_irq(&lo->lo_lock);
+}
+
+static void loop_queue_read_work(struct work_struct *work)
+{
+	struct loop_cmd *cmd =
+		container_of(work, struct loop_cmd, read_work);
+
+	loop_handle_cmd(cmd);
+}
+
+static int loop_init_request(void *data, struct request *rq,
+		unsigned int hctx_idx, unsigned int request_idx,
+		unsigned int numa_node)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	cmd->rq = rq;
+	INIT_WORK(&cmd->read_work, loop_queue_read_work);
+
+	return 0;
+}
+
+static struct blk_mq_ops loop_mq_ops = {
+	.queue_rq       = loop_queue_rq,
+	.map_queue      = blk_mq_map_queue,
+	.init_request	= loop_init_request,
+};
+
 static int loop_add(struct loop_device **l, int i)
 {
 	struct loop_device *lo;
@@ -1627,16 +1598,28 @@ static int loop_add(struct loop_device **l, int i)
 	i = err;
 
 	err = -ENOMEM;
-	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
-	if (!lo->lo_queue)
+	lo->tag_set.ops = &loop_mq_ops;
+	lo->tag_set.nr_hw_queues = 1;
+	lo->tag_set.queue_depth = 128;
+	lo->tag_set.numa_node = NUMA_NO_NODE;
+	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
+	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	lo->tag_set.driver_data = lo;
+
+	err = blk_mq_alloc_tag_set(&lo->tag_set);
+	if (err)
 		goto out_free_idr;
 
-	/*
-	 * set queue make_request_fn
-	 */
-	blk_queue_make_request(lo->lo_queue, loop_make_request);
+	lo->lo_queue = blk_mq_init_queue(&lo->tag_set);
+	if (IS_ERR_OR_NULL(lo->lo_queue)) {
+		err = PTR_ERR(lo->lo_queue);
+		goto out_cleanup_tags;
+	}
 	lo->lo_queue->queuedata = lo;
 
+	INIT_LIST_HEAD(&lo->write_cmd_head);
+	INIT_WORK(&lo->write_work, loop_queue_write_work);
+
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
@@ -1664,9 +1647,6 @@ static int loop_add(struct loop_device **l, int i)
 	disk->flags |= GENHD_FL_EXT_DEVT;
 	mutex_init(&lo->lo_ctl_mutex);
 	lo->lo_number		= i;
-	lo->lo_thread		= NULL;
-	init_waitqueue_head(&lo->lo_event);
-	init_waitqueue_head(&lo->lo_req_wait);
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
 	disk->first_minor	= i << part_shift;
@@ -1680,6 +1660,8 @@ static int loop_add(struct loop_device **l, int i)
 
 out_free_queue:
 	blk_cleanup_queue(lo->lo_queue);
+out_cleanup_tags:
+	blk_mq_free_tag_set(&lo->tag_set);
 out_free_idr:
 	idr_remove(&loop_index_idr, i);
 out_free_dev:
@@ -1692,6 +1674,7 @@ static void loop_remove(struct loop_device *lo)
 {
 	del_gendisk(lo->lo_disk);
 	blk_cleanup_queue(lo->lo_queue);
+	blk_mq_free_tag_set(&lo->tag_set);
 	put_disk(lo->lo_disk);
 	kfree(lo);
 }
@@ -1875,6 +1858,13 @@ static int __init loop_init(void)
 		goto misc_out;
 	}
 
+	loop_wq = alloc_workqueue("kloopd",
+			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 0);
+	if (!loop_wq) {
+		err = -ENOMEM;
+		goto misc_out;
+	}
+
 	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
 				  THIS_MODULE, loop_probe, NULL, NULL);
 
@@ -1912,6 +1902,8 @@ static void __exit loop_exit(void)
 	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
 	unregister_blkdev(LOOP_MAJOR, "loop");
 
+	destroy_workqueue(loop_wq);
+
 	misc_deregister(&loop_misc);
 }
 
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 90df5d6485b696..301c27f8323ffd 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -11,8 +11,10 @@
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 #include <uapi/linux/loop.h>
 
 /* Possible states of device */
@@ -52,19 +54,23 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
-	struct bio_list		lo_bio_list;
-	unsigned int		lo_bio_count;
+	struct list_head	write_cmd_head;
+	struct work_struct	write_work;
+	bool			write_started;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
-	struct task_struct	*lo_thread;
-	wait_queue_head_t	lo_event;
-	/* wait queue for incoming requests */
-	wait_queue_head_t	lo_req_wait;
 
 	struct request_queue	*lo_queue;
+	struct blk_mq_tag_set	tag_set;
 	struct gendisk		*lo_disk;
 };
 
+struct loop_cmd {
+	struct work_struct read_work;
+	struct request *rq;
+	struct list_head list;
+};
+
 /* Support for loadable transfer modules */
 struct loop_func_table {
 	int number;	/* filter type */ 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index aa2224aa7caa34..65cd61a4145ed2 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -579,7 +579,7 @@ static int null_add_dev(void)
 	sector_div(size, bs);
 	set_capacity(disk, size);
 
-	disk->flags |= GENHD_FL_EXT_DEVT;
+	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
 	disk->major		= null_major;
 	disk->first_minor	= nullb->index;
 	disk->fops		= &null_fops;
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index d826bf3e62c862..cbdfbbf983927e 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -144,8 +144,37 @@ struct nvme_cmd_info {
 	void *ctx;
 	int aborted;
 	struct nvme_queue *nvmeq;
+	struct nvme_iod iod[0];
 };
 
+/*
+ * Max size of iod being embedded in the request payload
+ */
+#define NVME_INT_PAGES		2
+#define NVME_INT_BYTES(dev)	(NVME_INT_PAGES * (dev)->page_size)
+
+/*
+ * Will slightly overestimate the number of pages needed.  This is OK
+ * as it only leads to a small amount of wasted memory for the lifetime of
+ * the I/O.
+ */
+static int nvme_npages(unsigned size, struct nvme_dev *dev)
+{
+	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
+	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+}
+
+static unsigned int nvme_cmd_size(struct nvme_dev *dev)
+{
+	unsigned int ret = sizeof(struct nvme_cmd_info);
+
+	ret += sizeof(struct nvme_iod);
+	ret += sizeof(__le64 *) * nvme_npages(NVME_INT_BYTES(dev), dev);
+	ret += sizeof(struct scatterlist) * NVME_INT_PAGES;
+
+	return ret;
+}
+
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 				unsigned int hctx_idx)
 {
@@ -218,6 +247,19 @@ static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
 	blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
 }
 
+static void *iod_get_private(struct nvme_iod *iod)
+{
+	return (void *) (iod->private & ~0x1UL);
+}
+
+/*
+ * If bit 0 is set, the iod is embedded in the request payload.
+ */
+static bool iod_should_kfree(struct nvme_iod *iod)
+{
+	return (iod->private & 0x01) == 0;
+}
+
 /* Special values must be less than 0x1000 */
 #define CMD_CTX_BASE		((void *)POISON_POINTER_DELTA)
 #define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
@@ -361,35 +403,53 @@ static __le64 **iod_list(struct nvme_iod *iod)
 	return ((void *)iod) + iod->offset;
 }
 
-/*
- * Will slightly overestimate the number of pages needed.  This is OK
- * as it only leads to a small amount of wasted memory for the lifetime of
- * the I/O.
- */
-static int nvme_npages(unsigned size, struct nvme_dev *dev)
+static inline void iod_init(struct nvme_iod *iod, unsigned nbytes,
+			    unsigned nseg, unsigned long private)
 {
-	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
-	return DIV_ROUND_UP(8 * nprps, dev->page_size - 8);
+	iod->private = private;
+	iod->offset = offsetof(struct nvme_iod, sg[nseg]);
+	iod->npages = -1;
+	iod->length = nbytes;
+	iod->nents = 0;
 }
 
 static struct nvme_iod *
-nvme_alloc_iod(unsigned nseg, unsigned nbytes, struct nvme_dev *dev, gfp_t gfp)
+__nvme_alloc_iod(unsigned nseg, unsigned bytes, struct nvme_dev *dev,
+		 unsigned long priv, gfp_t gfp)
 {
 	struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
-				sizeof(__le64 *) * nvme_npages(nbytes, dev) +
+				sizeof(__le64 *) * nvme_npages(bytes, dev) +
 				sizeof(struct scatterlist) * nseg, gfp);
 
-	if (iod) {
-		iod->offset = offsetof(struct nvme_iod, sg[nseg]);
-		iod->npages = -1;
-		iod->length = nbytes;
-		iod->nents = 0;
-		iod->first_dma = 0ULL;
-	}
+	if (iod)
+		iod_init(iod, bytes, nseg, priv);
 
 	return iod;
 }
 
+static struct nvme_iod *nvme_alloc_iod(struct request *rq, struct nvme_dev *dev,
+			               gfp_t gfp)
+{
+	unsigned size = !(rq->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(rq) :
+                                                sizeof(struct nvme_dsm_range);
+	unsigned long mask = 0;
+	struct nvme_iod *iod;
+
+	if (rq->nr_phys_segments <= NVME_INT_PAGES &&
+	    size <= NVME_INT_BYTES(dev)) {
+		struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(rq);
+
+		iod = cmd->iod;
+		mask = 0x01;
+		iod_init(iod, size, rq->nr_phys_segments,
+				(unsigned long) rq | 0x01);
+		return iod;
+	}
+
+	return __nvme_alloc_iod(rq->nr_phys_segments, size, dev,
+				(unsigned long) rq, gfp);
+}
+
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 {
 	const int last_prp = dev->page_size / 8 - 1;
@@ -405,7 +465,9 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 		dma_pool_free(dev->prp_page_pool, prp_list, prp_dma);
 		prp_dma = next_prp_dma;
 	}
-	kfree(iod);
+
+	if (iod_should_kfree(iod))
+		kfree(iod);
 }
 
 static int nvme_error_status(u16 status)
@@ -424,7 +486,7 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct nvme_iod *iod = ctx;
-	struct request *req = iod->private;
+	struct request *req = iod_get_private(iod);
 	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
 
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
@@ -585,7 +647,7 @@ static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 							struct nvme_ns *ns)
 {
-	struct request *req = iod->private;
+	struct request *req = iod_get_private(iod);
 	struct nvme_command *cmnd;
 	u16 control = 0;
 	u32 dsmgmt = 0;
@@ -626,17 +688,12 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_iod *iod;
-	int psegs = req->nr_phys_segments;
 	enum dma_data_direction dma_dir;
-	unsigned size = !(req->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(req) :
-						sizeof(struct nvme_dsm_range);
 
-	iod = nvme_alloc_iod(psegs, size, ns->dev, GFP_ATOMIC);
+	iod = nvme_alloc_iod(req, ns->dev, GFP_ATOMIC);
 	if (!iod)
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
-	iod->private = req;
-
 	if (req->cmd_flags & REQ_DISCARD) {
 		void *range;
 		/*
@@ -651,10 +708,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 			goto retry_cmd;
 		iod_list(iod)[0] = (__le64 *)range;
 		iod->npages = 0;
-	} else if (psegs) {
+	} else if (req->nr_phys_segments) {
 		dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 
-		sg_init_table(iod->sg, psegs);
+		sg_init_table(iod->sg, req->nr_phys_segments);
 		iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
 		if (!iod->nents)
 			goto error_cmd;
@@ -1137,21 +1194,14 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
 
 static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 {
-	LLIST_HEAD(q_list);
-	struct nvme_queue *nvmeq, *next;
-	struct llist_node *entry;
 	int i;
 
 	for (i = dev->queue_count - 1; i >= lowest; i--) {
 		struct nvme_queue *nvmeq = dev->queues[i];
-		llist_add(&nvmeq->node, &q_list);
 		dev->queue_count--;
 		dev->queues[i] = NULL;
-	}
-	synchronize_rcu();
-	entry = llist_del_all(&q_list);
-	llist_for_each_entry_safe(nvmeq, next, entry, node)
 		nvme_free_queue(nvmeq);
+	}
 }
 
 /**
@@ -1408,7 +1458,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
-		dev->admin_tagset.cmd_size = sizeof(struct nvme_cmd_info);
+		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
@@ -1522,7 +1572,7 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 	}
 
 	err = -ENOMEM;
-	iod = nvme_alloc_iod(count, length, dev, GFP_KERNEL);
+	iod = __nvme_alloc_iod(count, length, dev, 0, GFP_KERNEL);
 	if (!iod)
 		goto put_pages;
 
@@ -2148,7 +2198,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	dev->tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
 	dev->tagset.queue_depth =
 				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
-	dev->tagset.cmd_size = sizeof(struct nvme_cmd_info);
+	dev->tagset.cmd_size = nvme_cmd_size(dev);
 	dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
 	dev->tagset.driver_data = dev;
 
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 79aa179305b5e6..e229425962074c 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -423,7 +423,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev)
 	}
 
 	/* switch queue to TCQ mode; allocate tag map */
-	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL);
+	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL, BLK_TAG_ALLOC_FIFO);
 	if (rc) {
 		blk_cleanup_queue(q);
 		put_disk(disk);
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index cc90a840e6166e..375d28851860fd 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -214,6 +214,15 @@ enum blkif_protocol {
 	BLKIF_PROTOCOL_X86_64 = 3,
 };
 
+/*
+ * Default protocol if the frontend doesn't specify one.
+ */
+#ifdef CONFIG_X86
+#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_X86_32
+#else
+#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_NATIVE
+#endif
+
 struct xen_vbd {
 	/* What the domain refers to this vbd as. */
 	blkif_vdev_t		handle;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 630a489e757d61..e3afe97280b189 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -868,11 +868,11 @@ static int connect_ring(struct backend_info *be)
 		return err;
 	}
 
-	be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
+	be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT;
 	err = xenbus_gather(XBT_NIL, dev->otherend, "protocol",
 			    "%63s", protocol, NULL);
 	if (err)
-		strcpy(protocol, "unspecified, assuming native");
+		strcpy(protocol, "unspecified, assuming default");
 	else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_NATIVE))
 		be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
 	else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_32))
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 2236c6f3160897..37779e4c4585ea 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1391,7 +1391,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 			if (major != XENVBD_MAJOR) {
 				printk(KERN_INFO
 						"%s: HVM does not support vbd %d as xen block device\n",
-						__FUNCTION__, vdevice);
+						__func__, vdevice);
 				return -ENODEV;
 			}
 		}
@@ -1511,7 +1511,7 @@ static int blkif_recover(struct blkfront_info *info)
 		merge_bio.tail = copy[i].request->biotail;
 		bio_list_merge(&bio_list, &merge_bio);
 		copy[i].request->bio = NULL;
-		blk_put_request(copy[i].request);
+		blk_end_request_all(copy[i].request, 0);
 	}
 
 	kfree(copy);
@@ -1534,7 +1534,7 @@ static int blkif_recover(struct blkfront_info *info)
 		req->bio = NULL;
 		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
 			pr_alert("diskcache flush request found!\n");
-		__blk_put_request(info->rq, req);
+		__blk_end_request_all(req, 0);
 	}
 	spin_unlock_irq(&info->io_lock);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index bd8bda386e0218..8e233edd7a097a 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -53,9 +53,9 @@ static ssize_t name##_show(struct device *d,		\
 }									\
 static DEVICE_ATTR_RO(name);
 
-static inline int init_done(struct zram *zram)
+static inline bool init_done(struct zram *zram)
 {
-	return zram->meta != NULL;
+	return zram->disksize;
 }
 
 static inline struct zram *dev_to_zram(struct device *dev)
@@ -307,42 +307,67 @@ static inline int valid_io_request(struct zram *zram,
 	return 1;
 }
 
-static void zram_meta_free(struct zram_meta *meta)
+static void zram_meta_free(struct zram_meta *meta, u64 disksize)
 {
+	size_t num_pages = disksize >> PAGE_SHIFT;
+	size_t index;
+
+	/* Free all pages that are still in this zram device */
+	for (index = 0; index < num_pages; index++) {
+		unsigned long handle = meta->table[index].handle;
+
+		if (!handle)
+			continue;
+
+		zs_free(meta->mem_pool, handle);
+	}
+
 	zs_destroy_pool(meta->mem_pool);
 	vfree(meta->table);
 	kfree(meta);
 }
 
-static struct zram_meta *zram_meta_alloc(u64 disksize)
+static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
 {
 	size_t num_pages;
+	char pool_name[8];
 	struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
+
 	if (!meta)
-		goto out;
+		return NULL;
 
 	num_pages = disksize >> PAGE_SHIFT;
 	meta->table = vzalloc(num_pages * sizeof(*meta->table));
 	if (!meta->table) {
 		pr_err("Error allocating zram address table\n");
-		goto free_meta;
+		goto out_error;
 	}
 
-	meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
+	snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
+	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
 	if (!meta->mem_pool) {
 		pr_err("Error creating memory pool\n");
-		goto free_table;
+		goto out_error;
 	}
 
 	return meta;
 
-free_table:
+out_error:
 	vfree(meta->table);
-free_meta:
 	kfree(meta);
-	meta = NULL;
-out:
-	return meta;
+	return NULL;
+}
+
+static inline bool zram_meta_get(struct zram *zram)
+{
+	if (atomic_inc_not_zero(&zram->refcount))
+		return true;
+	return false;
+}
+
+static inline void zram_meta_put(struct zram *zram)
+{
+	atomic_dec(&zram->refcount);
 }
 
 static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
@@ -704,10 +729,11 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 	}
 }
 
-static void zram_reset_device(struct zram *zram, bool reset_capacity)
+static void zram_reset_device(struct zram *zram)
 {
-	size_t index;
 	struct zram_meta *meta;
+	struct zcomp *comp;
+	u64 disksize;
 
 	down_write(&zram->init_lock);
 
@@ -719,36 +745,30 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	}
 
 	meta = zram->meta;
-	/* Free all pages that are still in this zram device */
-	for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
-		unsigned long handle = meta->table[index].handle;
-		if (!handle)
-			continue;
-
-		zs_free(meta->mem_pool, handle);
-	}
-
-	zcomp_destroy(zram->comp);
-	zram->max_comp_streams = 1;
+	comp = zram->comp;
+	disksize = zram->disksize;
+	/*
+	 * Refcount will go down to 0 eventually and r/w handler
+	 * cannot handle further I/O so it will bail out by
+	 * check zram_meta_get.
+	 */
+	zram_meta_put(zram);
+	/*
+	 * We want to free zram_meta in process context to avoid
+	 * deadlock between reclaim path and any other locks.
+	 */
+	wait_event(zram->io_done, atomic_read(&zram->refcount) == 0);
 
-	zram_meta_free(zram->meta);
-	zram->meta = NULL;
 	/* Reset stats */
 	memset(&zram->stats, 0, sizeof(zram->stats));
-
 	zram->disksize = 0;
-	if (reset_capacity)
-		set_capacity(zram->disk, 0);
+	zram->max_comp_streams = 1;
+	set_capacity(zram->disk, 0);
 
 	up_write(&zram->init_lock);
-
-	/*
-	 * Revalidate disk out of the init_lock to avoid lockdep splat.
-	 * It's okay because disk's capacity is protected by init_lock
-	 * so that revalidate_disk always sees up-to-date capacity.
-	 */
-	if (reset_capacity)
-		revalidate_disk(zram->disk);
+	/* I/O operation under all of CPU are done so let's free */
+	zram_meta_free(meta, disksize);
+	zcomp_destroy(comp);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -765,7 +785,7 @@ static ssize_t disksize_store(struct device *dev,
 		return -EINVAL;
 
 	disksize = PAGE_ALIGN(disksize);
-	meta = zram_meta_alloc(disksize);
+	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
 	if (!meta)
 		return -ENOMEM;
 
@@ -784,6 +804,8 @@ static ssize_t disksize_store(struct device *dev,
 		goto out_destroy_comp;
 	}
 
+	init_waitqueue_head(&zram->io_done);
+	atomic_set(&zram->refcount, 1);
 	zram->meta = meta;
 	zram->comp = comp;
 	zram->disksize = disksize;
@@ -803,7 +825,7 @@ static ssize_t disksize_store(struct device *dev,
 	up_write(&zram->init_lock);
 	zcomp_destroy(comp);
 out_free_meta:
-	zram_meta_free(meta);
+	zram_meta_free(meta, disksize);
 	return err;
 }
 
@@ -821,8 +843,9 @@ static ssize_t reset_store(struct device *dev,
 	if (!bdev)
 		return -ENOMEM;
 
+	mutex_lock(&bdev->bd_mutex);
 	/* Do not reset an active device! */
-	if (bdev->bd_holders) {
+	if (bdev->bd_openers) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -838,12 +861,16 @@ static ssize_t reset_store(struct device *dev,
 
 	/* Make sure all pending I/O is finished */
 	fsync_bdev(bdev);
+	zram_reset_device(zram);
+
+	mutex_unlock(&bdev->bd_mutex);
+	revalidate_disk(zram->disk);
 	bdput(bdev);
 
-	zram_reset_device(zram, true);
 	return len;
 
 out:
+	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	return ret;
 }
@@ -909,23 +936,21 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct zram *zram = queue->queuedata;
 
-	down_read(&zram->init_lock);
-	if (unlikely(!init_done(zram)))
+	if (unlikely(!zram_meta_get(zram)))
 		goto error;
 
 	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
 					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		goto error;
+		goto put_zram;
 	}
 
 	__zram_make_request(zram, bio);
-	up_read(&zram->init_lock);
-
+	zram_meta_put(zram);
 	return;
-
+put_zram:
+	zram_meta_put(zram);
 error:
-	up_read(&zram->init_lock);
 	bio_io_error(bio);
 }
 
@@ -947,21 +972,19 @@ static void zram_slot_free_notify(struct block_device *bdev,
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
 		       struct page *page, int rw)
 {
-	int offset, err;
+	int offset, err = -EIO;
 	u32 index;
 	struct zram *zram;
 	struct bio_vec bv;
 
 	zram = bdev->bd_disk->private_data;
+	if (unlikely(!zram_meta_get(zram)))
+		goto out;
+
 	if (!valid_io_request(zram, sector, PAGE_SIZE)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		return -EINVAL;
-	}
-
-	down_read(&zram->init_lock);
-	if (unlikely(!init_done(zram))) {
-		err = -EIO;
-		goto out_unlock;
+		err = -EINVAL;
+		goto put_zram;
 	}
 
 	index = sector >> SECTORS_PER_PAGE_SHIFT;
@@ -972,8 +995,9 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_offset = 0;
 
 	err = zram_bvec_rw(zram, &bv, index, offset, rw);
-out_unlock:
-	up_read(&zram->init_lock);
+put_zram:
+	zram_meta_put(zram);
+out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
 	 * calling page_endio.
@@ -1039,19 +1063,19 @@ static struct attribute_group zram_disk_attr_group = {
 
 static int create_device(struct zram *zram, int device_id)
 {
+	struct request_queue *queue;
 	int ret = -ENOMEM;
 
 	init_rwsem(&zram->init_lock);
 
-	zram->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!zram->queue) {
+	queue = blk_alloc_queue(GFP_KERNEL);
+	if (!queue) {
 		pr_err("Error allocating disk queue for device %d\n",
 			device_id);
 		goto out;
 	}
 
-	blk_queue_make_request(zram->queue, zram_make_request);
-	zram->queue->queuedata = zram;
+	blk_queue_make_request(queue, zram_make_request);
 
 	 /* gendisk structure */
 	zram->disk = alloc_disk(1);
@@ -1064,7 +1088,8 @@ static int create_device(struct zram *zram, int device_id)
 	zram->disk->major = zram_major;
 	zram->disk->first_minor = device_id;
 	zram->disk->fops = &zram_devops;
-	zram->disk->queue = zram->queue;
+	zram->disk->queue = queue;
+	zram->disk->queue->queuedata = zram;
 	zram->disk->private_data = zram;
 	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
 
@@ -1115,20 +1140,35 @@ static int create_device(struct zram *zram, int device_id)
 	del_gendisk(zram->disk);
 	put_disk(zram->disk);
 out_free_queue:
-	blk_cleanup_queue(zram->queue);
+	blk_cleanup_queue(queue);
 out:
 	return ret;
 }
 
-static void destroy_device(struct zram *zram)
+static void destroy_devices(unsigned int nr)
 {
-	sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
-			&zram_disk_attr_group);
+	struct zram *zram;
+	unsigned int i;
 
-	del_gendisk(zram->disk);
-	put_disk(zram->disk);
+	for (i = 0; i < nr; i++) {
+		zram = &zram_devices[i];
+		/*
+		 * Remove sysfs first, so no one will perform a disksize
+		 * store while we destroy the devices
+		 */
+		sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
+				&zram_disk_attr_group);
+
+		zram_reset_device(zram);
 
-	blk_cleanup_queue(zram->queue);
+		blk_cleanup_queue(zram->disk->queue);
+		del_gendisk(zram->disk);
+		put_disk(zram->disk);
+	}
+
+	kfree(zram_devices);
+	unregister_blkdev(zram_major, "zram");
+	pr_info("Destroyed %u device(s)\n", nr);
 }
 
 static int __init zram_init(void)
@@ -1138,64 +1178,39 @@ static int __init zram_init(void)
 	if (num_devices > max_num_devices) {
 		pr_warn("Invalid value for num_devices: %u\n",
 				num_devices);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	zram_major = register_blkdev(0, "zram");
 	if (zram_major <= 0) {
 		pr_warn("Unable to get major number\n");
-		ret = -EBUSY;
-		goto out;
+		return -EBUSY;
 	}
 
 	/* Allocate the device array and initialize each one */
 	zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
 	if (!zram_devices) {
-		ret = -ENOMEM;
-		goto unregister;
+		unregister_blkdev(zram_major, "zram");
+		return -ENOMEM;
 	}
 
 	for (dev_id = 0; dev_id < num_devices; dev_id++) {
 		ret = create_device(&zram_devices[dev_id], dev_id);
 		if (ret)
-			goto free_devices;
+			goto out_error;
 	}
 
-	pr_info("Created %u device(s) ...\n", num_devices);
-
+	pr_info("Created %u device(s)\n", num_devices);
 	return 0;
 
-free_devices:
-	while (dev_id)
-		destroy_device(&zram_devices[--dev_id]);
-	kfree(zram_devices);
-unregister:
-	unregister_blkdev(zram_major, "zram");
-out:
+out_error:
+	destroy_devices(dev_id);
 	return ret;
 }
 
 static void __exit zram_exit(void)
 {
-	int i;
-	struct zram *zram;
-
-	for (i = 0; i < num_devices; i++) {
-		zram = &zram_devices[i];
-
-		destroy_device(zram);
-		/*
-		 * Shouldn't access zram->disk after destroy_device
-		 * because destroy_device already released zram->disk.
-		 */
-		zram_reset_device(zram, false);
-	}
-
-	unregister_blkdev(zram_major, "zram");
-
-	kfree(zram_devices);
-	pr_debug("Cleanup done!\n");
+	destroy_devices(num_devices);
 }
 
 module_init(zram_init);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index b05a816b09acbf..17056e5891467c 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -100,24 +100,25 @@ struct zram_meta {
 
 struct zram {
 	struct zram_meta *meta;
-	struct request_queue *queue;
-	struct gendisk *disk;
 	struct zcomp *comp;
-
-	/* Prevent concurrent execution of device init, reset and R/W request */
+	struct gendisk *disk;
+	/* Prevent concurrent execution of device init */
 	struct rw_semaphore init_lock;
 	/*
-	 * This is the limit on amount of *uncompressed* worth of data
-	 * we can store in a disk.
+	 * the number of pages zram can consume for storing compressed data
 	 */
-	u64 disksize;	/* bytes */
+	unsigned long limit_pages;
 	int max_comp_streams;
+
 	struct zram_stats stats;
+	atomic_t refcount; /* refcount for zram_meta */
+	/* wait all IO under all of cpu are done */
+	wait_queue_head_t io_done;
 	/*
-	 * the number of pages zram can consume for storing compressed data
+	 * This is the limit on amount of *uncompressed* worth of data
+	 * we can store in a disk.
 	 */
-	unsigned long limit_pages;
-
+	u64 disksize;	/* bytes */
 	char compressor[10];
 };
 #endif
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 4c58333b42570d..9a6b63783a94dd 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -287,13 +287,24 @@ static unsigned long get_unmapped_area_mem(struct file *file,
 	return pgoff << PAGE_SHIFT;
 }
 
+/* permit direct mmap, for read, write or exec */
+static unsigned memory_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_DIRECT |
+		NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
+static unsigned zero_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_COPY;
+}
+
 /* can't do an in-place private mapping if there's no MMU */
 static inline int private_mapping_ok(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & VM_MAYSHARE;
 }
 #else
-#define get_unmapped_area_mem	NULL
 
 static inline int private_mapping_ok(struct vm_area_struct *vma)
 {
@@ -721,7 +732,10 @@ static const struct file_operations mem_fops = {
 	.write		= write_mem,
 	.mmap		= mmap_mem,
 	.open		= open_mem,
+#ifndef CONFIG_MMU
 	.get_unmapped_area = get_unmapped_area_mem,
+	.mmap_capabilities = memory_mmap_capabilities,
+#endif
 };
 
 #ifdef CONFIG_DEVKMEM
@@ -731,7 +745,10 @@ static const struct file_operations kmem_fops = {
 	.write		= write_kmem,
 	.mmap		= mmap_kmem,
 	.open		= open_kmem,
+#ifndef CONFIG_MMU
 	.get_unmapped_area = get_unmapped_area_mem,
+	.mmap_capabilities = memory_mmap_capabilities,
+#endif
 };
 #endif
 
@@ -760,16 +777,9 @@ static const struct file_operations zero_fops = {
 	.read_iter	= read_iter_zero,
 	.aio_write	= aio_write_zero,
 	.mmap		= mmap_zero,
-};
-
-/*
- * capabilities for /dev/zero
- * - permits private mappings, "copies" are taken of the source of zeros
- * - no writeback happens
- */
-static struct backing_dev_info zero_bdi = {
-	.name		= "char/mem",
-	.capabilities	= BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK,
+#ifndef CONFIG_MMU
+	.mmap_capabilities = zero_mmap_capabilities,
+#endif
 };
 
 static const struct file_operations full_fops = {
@@ -783,22 +793,22 @@ static const struct memdev {
 	const char *name;
 	umode_t mode;
 	const struct file_operations *fops;
-	struct backing_dev_info *dev_info;
+	fmode_t fmode;
 } devlist[] = {
-	 [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
+	 [1] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
 #ifdef CONFIG_DEVKMEM
-	 [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
+	 [2] = { "kmem", 0, &kmem_fops, FMODE_UNSIGNED_OFFSET },
 #endif
-	 [3] = { "null", 0666, &null_fops, NULL },
+	 [3] = { "null", 0666, &null_fops, 0 },
 #ifdef CONFIG_DEVPORT
-	 [4] = { "port", 0, &port_fops, NULL },
+	 [4] = { "port", 0, &port_fops, 0 },
 #endif
-	 [5] = { "zero", 0666, &zero_fops, &zero_bdi },
-	 [7] = { "full", 0666, &full_fops, NULL },
-	 [8] = { "random", 0666, &random_fops, NULL },
-	 [9] = { "urandom", 0666, &urandom_fops, NULL },
+	 [5] = { "zero", 0666, &zero_fops, 0 },
+	 [7] = { "full", 0666, &full_fops, 0 },
+	 [8] = { "random", 0666, &random_fops, 0 },
+	 [9] = { "urandom", 0666, &urandom_fops, 0 },
 #ifdef CONFIG_PRINTK
-	[11] = { "kmsg", 0644, &kmsg_fops, NULL },
+	[11] = { "kmsg", 0644, &kmsg_fops, 0 },
 #endif
 };
 
@@ -816,12 +826,7 @@ static int memory_open(struct inode *inode, struct file *filp)
 		return -ENXIO;
 
 	filp->f_op = dev->fops;
-	if (dev->dev_info)
-		filp->f_mapping->backing_dev_info = dev->dev_info;
-
-	/* Is /dev/mem or /dev/kmem ? */
-	if (dev->dev_info == &directly_mappable_cdev_bdi)
-		filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+	filp->f_mode |= dev->fmode;
 
 	if (dev->fops->open)
 		return dev->fops->open(inode, filp);
@@ -846,11 +851,6 @@ static struct class *mem_class;
 static int __init chr_dev_init(void)
 {
 	int minor;
-	int err;
-
-	err = bdi_init(&zero_bdi);
-	if (err)
-		return err;
 
 	if (register_chrdev(MEM_MAJOR, "mem", &memory_fops))
 		printk("unable to get major %d for memory devs\n", MEM_MAJOR);
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index a24891b97547dc..6e29bf2db53677 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -104,11 +104,9 @@ static int raw_release(struct inode *inode, struct file *filp)
 
 	mutex_lock(&raw_mutex);
 	bdev = raw_devices[minor].binding;
-	if (--raw_devices[minor].inuse == 0) {
+	if (--raw_devices[minor].inuse == 0)
 		/* Here  inode->i_mapping == bdev->bd_inode->i_mapping  */
 		inode->i_mapping = &inode->i_data;
-		inode->i_mapping->backing_dev_info = &default_backing_dev_info;
-	}
 	mutex_unlock(&raw_mutex);
 
 	blkdev_put(bdev, filp->f_mode | FMODE_EXCL);
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index c355a226a0247c..c39644478aa4e6 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -231,9 +231,8 @@ config DM_CRYPT
 	  transparently encrypts the data on it. You'll need to activate
 	  the ciphers you're going to use in the cryptoapi configuration.
 
-	  Information on how to use dm-crypt can be found on
-
-	  <http://www.saout.de/misc/dm-crypt/>
+	  For further information on dm-crypt and userspace tools see:
+	  <http://code.google.com/p/cryptsetup/wiki/DMCrypt>
 
 	  To compile this code as a module, choose M here: the module will
 	  be called dm-crypt.
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 1695ee5f3ffc30..3a5767968ba06c 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1619,7 +1619,9 @@ void bitmap_destroy(struct mddev *mddev)
 		return;
 
 	mutex_lock(&mddev->bitmap_info.mutex);
+	spin_lock(&mddev->lock);
 	mddev->bitmap = NULL; /* disconnect from the md device */
+	spin_unlock(&mddev->lock);
 	mutex_unlock(&mddev->bitmap_info.mutex);
 	if (mddev->thread)
 		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
@@ -2209,11 +2211,13 @@ __ATTR(metadata, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
 static ssize_t can_clear_show(struct mddev *mddev, char *page)
 {
 	int len;
+	spin_lock(&mddev->lock);
 	if (mddev->bitmap)
 		len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ?
 					     "false" : "true"));
 	else
 		len = sprintf(page, "\n");
+	spin_unlock(&mddev->lock);
 	return len;
 }
 
@@ -2238,10 +2242,15 @@ __ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store);
 static ssize_t
 behind_writes_used_show(struct mddev *mddev, char *page)
 {
+	ssize_t ret;
+	spin_lock(&mddev->lock);
 	if (mddev->bitmap == NULL)
-		return sprintf(page, "0\n");
-	return sprintf(page, "%lu\n",
-		       mddev->bitmap->behind_writes_used);
+		ret = sprintf(page, "0\n");
+	else
+		ret = sprintf(page, "%lu\n",
+			      mddev->bitmap->behind_writes_used);
+	spin_unlock(&mddev->lock);
+	return ret;
 }
 
 static ssize_t
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index c33b49792b8730..86dbbc73740222 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -11,6 +11,7 @@
 #include <linux/device-mapper.h>
 #include <linux/dm-io.h>
 #include <linux/slab.h>
+#include <linux/jiffies.h>
 #include <linux/vmalloc.h>
 #include <linux/shrinker.h>
 #include <linux/module.h>
@@ -1739,7 +1740,7 @@ static unsigned get_max_age_hz(void)
 
 static bool older_than(struct dm_buffer *b, unsigned long age_hz)
 {
-	return (jiffies - b->last_accessed) >= age_hz;
+	return time_after_eq(jiffies, b->last_accessed + age_hz);
 }
 
 static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index e1650539cc2f82..7755af35186762 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -11,6 +11,7 @@
 
 #include <linux/dm-io.h>
 #include <linux/dm-kcopyd.h>
+#include <linux/jiffies.h>
 #include <linux/init.h>
 #include <linux/mempool.h>
 #include <linux/module.h>
@@ -1562,8 +1563,8 @@ static void process_bio(struct cache *cache, struct prealloc *structs,
 
 static int need_commit_due_to_time(struct cache *cache)
 {
-	return jiffies < cache->last_commit_jiffies ||
-	       jiffies > cache->last_commit_jiffies + COMMIT_PERIOD;
+	return !time_in_range(jiffies, cache->last_commit_jiffies,
+			      cache->last_commit_jiffies + COMMIT_PERIOD);
 }
 
 static int commit_if_needed(struct cache *cache)
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 73f791bb9ea4f0..c8a18e4ee9dce2 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -639,8 +639,8 @@ static int check_name(const char *name)
 
 /*
  * On successful return, the caller must not attempt to acquire
- * _hash_lock without first calling dm_table_put, because dm_table_destroy
- * waits for this dm_table_put and could be called under this lock.
+ * _hash_lock without first calling dm_put_live_table, because dm_table_destroy
+ * waits for this dm_put_live_table and could be called under this lock.
  */
 static struct dm_table *dm_get_inactive_table(struct mapped_device *md, int *srcu_idx)
 {
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index b953db6cc229ae..03177ca0b00904 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -6,6 +6,7 @@
 
 #include <linux/bio.h>
 #include <linux/slab.h>
+#include <linux/jiffies.h>
 #include <linux/dm-dirty-log.h>
 #include <linux/device-mapper.h>
 #include <linux/dm-log-userspace.h>
@@ -829,7 +830,7 @@ static int userspace_is_remote_recovering(struct dm_dirty_log *log,
 	int r;
 	uint64_t region64 = region;
 	struct log_c *lc = log->context;
-	static unsigned long long limit;
+	static unsigned long limit;
 	struct {
 		int64_t is_recovering;
 		uint64_t in_sync_hint;
@@ -845,7 +846,7 @@ static int userspace_is_remote_recovering(struct dm_dirty_log *log,
 	 */
 	if (region < lc->in_sync_hint)
 		return 0;
-	else if (jiffies < limit)
+	else if (time_after(limit, jiffies))
 		return 1;
 
 	limit = jiffies + (HZ / 4);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 7b6b0f0f831a44..d376dc87716ebb 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -11,6 +11,7 @@
 #include "dm-path-selector.h"
 #include "dm-uevent.h"
 
+#include <linux/blkdev.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/mempool.h>
@@ -378,18 +379,18 @@ static int __must_push_back(struct multipath *m)
 /*
  * Map cloned requests
  */
-static int multipath_map(struct dm_target *ti, struct request *clone,
-			 union map_info *map_context)
+static int __multipath_map(struct dm_target *ti, struct request *clone,
+			   union map_info *map_context,
+			   struct request *rq, struct request **__clone)
 {
 	struct multipath *m = (struct multipath *) ti->private;
 	int r = DM_MAPIO_REQUEUE;
-	size_t nr_bytes = blk_rq_bytes(clone);
-	unsigned long flags;
+	size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq);
 	struct pgpath *pgpath;
 	struct block_device *bdev;
 	struct dm_mpath_io *mpio;
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
 
 	/* Do we need to select a new pgpath? */
 	if (!m->current_pgpath ||
@@ -411,25 +412,61 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
 		/* ENOMEM, requeue */
 		goto out_unlock;
 
-	bdev = pgpath->path.dev->bdev;
-	clone->q = bdev_get_queue(bdev);
-	clone->rq_disk = bdev->bd_disk;
-	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
 	mpio = map_context->ptr;
 	mpio->pgpath = pgpath;
 	mpio->nr_bytes = nr_bytes;
+
+	bdev = pgpath->path.dev->bdev;
+
+	spin_unlock_irq(&m->lock);
+
+	if (clone) {
+		/* Old request-based interface: allocated clone is passed in */
+		clone->q = bdev_get_queue(bdev);
+		clone->rq_disk = bdev->bd_disk;
+		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	} else {
+		/* blk-mq request-based interface */
+		*__clone = blk_get_request(bdev_get_queue(bdev),
+					   rq_data_dir(rq), GFP_KERNEL);
+		if (IS_ERR(*__clone))
+			/* ENOMEM, requeue */
+			return r;
+		(*__clone)->bio = (*__clone)->biotail = NULL;
+		(*__clone)->rq_disk = bdev->bd_disk;
+		(*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	}
+
 	if (pgpath->pg->ps.type->start_io)
 		pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
 					      &pgpath->path,
 					      nr_bytes);
-	r = DM_MAPIO_REMAPPED;
+	return DM_MAPIO_REMAPPED;
 
 out_unlock:
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 
 	return r;
 }
 
+static int multipath_map(struct dm_target *ti, struct request *clone,
+			 union map_info *map_context)
+{
+	return __multipath_map(ti, clone, map_context, NULL, NULL);
+}
+
+static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
+				   union map_info *map_context,
+				   struct request **clone)
+{
+	return __multipath_map(ti, NULL, map_context, rq, clone);
+}
+
+static void multipath_release_clone(struct request *clone)
+{
+	blk_put_request(clone);
+}
+
 /*
  * If we run out of usable paths, should we queue I/O or error it?
  */
@@ -1666,11 +1703,13 @@ static int multipath_busy(struct dm_target *ti)
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 7, 0},
+	.version = {1, 8, 0},
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
 	.map_rq = multipath_map,
+	.clone_and_map_rq = multipath_clone_and_map,
+	.release_clone_rq = multipath_release_clone,
 	.rq_end_io = multipath_end_io,
 	.presuspend = multipath_presuspend,
 	.postsuspend = multipath_postsuspend,
@@ -1694,16 +1733,15 @@ static int __init dm_multipath_init(void)
 	r = dm_register_target(&multipath_target);
 	if (r < 0) {
 		DMERR("register failed %d", r);
-		kmem_cache_destroy(_mpio_cache);
-		return -EINVAL;
+		r = -EINVAL;
+		goto bad_register_target;
 	}
 
 	kmultipathd = alloc_workqueue("kmpathd", WQ_MEM_RECLAIM, 0);
 	if (!kmultipathd) {
 		DMERR("failed to create workqueue kmpathd");
-		dm_unregister_target(&multipath_target);
-		kmem_cache_destroy(_mpio_cache);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto bad_alloc_kmultipathd;
 	}
 
 	/*
@@ -1716,16 +1754,23 @@ static int __init dm_multipath_init(void)
 						  WQ_MEM_RECLAIM);
 	if (!kmpath_handlerd) {
 		DMERR("failed to create workqueue kmpath_handlerd");
-		destroy_workqueue(kmultipathd);
-		dm_unregister_target(&multipath_target);
-		kmem_cache_destroy(_mpio_cache);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto bad_alloc_kmpath_handlerd;
 	}
 
 	DMINFO("version %u.%u.%u loaded",
 	       multipath_target.version[0], multipath_target.version[1],
 	       multipath_target.version[2]);
 
+	return 0;
+
+bad_alloc_kmpath_handlerd:
+	destroy_workqueue(kmultipathd);
+bad_alloc_kmultipathd:
+	dm_unregister_target(&multipath_target);
+bad_register_target:
+	kmem_cache_destroy(_mpio_cache);
+
 	return r;
 }
 
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 07c0fa0fa284fb..88e4c7f249864e 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -746,13 +746,7 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
 {
 	struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
 
-	if (rs->raid_type->level == 1)
-		return md_raid1_congested(&rs->md, bits);
-
-	if (rs->raid_type->level == 10)
-		return md_raid10_congested(&rs->md, bits);
-
-	return md_raid5_congested(&rs->md, bits);
+	return mddev_congested(&rs->md, bits);
 }
 
 /*
@@ -1243,7 +1237,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	argv++;
 
 	/* Skip over RAID params for now and find out # of devices */
-	if (num_raid_params + 1 > argc) {
+	if (num_raid_params >= argc) {
 		ti->error = "Arguments do not agree with counts given";
 		return -EINVAL;
 	}
@@ -1254,6 +1248,12 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		return -EINVAL;
 	}
 
+	argc -= num_raid_params + 1; /* +1: we already have num_raid_devs */
+	if (argc != (num_raid_devs * 2)) {
+		ti->error = "Supplied RAID devices does not match the count given";
+		return -EINVAL;
+	}
+
 	rs = context_alloc(ti, rt, (unsigned)num_raid_devs);
 	if (IS_ERR(rs))
 		return PTR_ERR(rs);
@@ -1262,16 +1262,8 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (ret)
 		goto bad;
 
-	ret = -EINVAL;
-
-	argc -= num_raid_params + 1; /* +1: we already have num_raid_devs */
 	argv += num_raid_params + 1;
 
-	if (argc != (num_raid_devs * 2)) {
-		ti->error = "Supplied RAID devices does not match the count given";
-		goto bad;
-	}
-
 	ret = dev_parms(rs, argv);
 	if (ret)
 		goto bad;
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index d6e88178d22cff..808b8419bc48d4 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -200,16 +200,11 @@ static int alloc_area(struct pstore *ps)
 
 static void free_area(struct pstore *ps)
 {
-	if (ps->area)
-		vfree(ps->area);
+	vfree(ps->area);
 	ps->area = NULL;
-
-	if (ps->zero_area)
-		vfree(ps->zero_area);
+	vfree(ps->zero_area);
 	ps->zero_area = NULL;
-
-	if (ps->header_area)
-		vfree(ps->header_area);
+	vfree(ps->header_area);
 	ps->header_area = NULL;
 }
 
@@ -605,8 +600,7 @@ static void persistent_dtr(struct dm_exception_store *store)
 	free_area(ps);
 
 	/* Allocated in persistent_read_metadata */
-	if (ps->callbacks)
-		vfree(ps->callbacks);
+	vfree(ps->callbacks);
 
 	kfree(ps);
 }
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3afae9e062f842..6554d914892777 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -827,10 +827,11 @@ static int dm_table_set_type(struct dm_table *t)
 {
 	unsigned i;
 	unsigned bio_based = 0, request_based = 0, hybrid = 0;
+	bool use_blk_mq = false;
 	struct dm_target *tgt;
 	struct dm_dev_internal *dd;
 	struct list_head *devices;
-	unsigned live_md_type;
+	unsigned live_md_type = dm_get_md_type(t->md);
 
 	for (i = 0; i < t->num_targets; i++) {
 		tgt = t->targets + i;
@@ -854,8 +855,8 @@ static int dm_table_set_type(struct dm_table *t)
 		 * Determine the type from the live device.
 		 * Default to bio-based if device is new.
 		 */
-		live_md_type = dm_get_md_type(t->md);
-		if (live_md_type == DM_TYPE_REQUEST_BASED)
+		if (live_md_type == DM_TYPE_REQUEST_BASED ||
+		    live_md_type == DM_TYPE_MQ_REQUEST_BASED)
 			request_based = 1;
 		else
 			bio_based = 1;
@@ -869,16 +870,6 @@ static int dm_table_set_type(struct dm_table *t)
 
 	BUG_ON(!request_based); /* No targets in this table */
 
-	/* Non-request-stackable devices can't be used for request-based dm */
-	devices = dm_table_get_devices(t);
-	list_for_each_entry(dd, devices, list) {
-		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev->bdev))) {
-			DMWARN("table load rejected: including"
-			       " non-request-stackable devices");
-			return -EINVAL;
-		}
-	}
-
 	/*
 	 * Request-based dm supports only tables that have a single target now.
 	 * To support multiple targets, request splitting support is needed,
@@ -890,7 +881,37 @@ static int dm_table_set_type(struct dm_table *t)
 		return -EINVAL;
 	}
 
-	t->type = DM_TYPE_REQUEST_BASED;
+	/* Non-request-stackable devices can't be used for request-based dm */
+	devices = dm_table_get_devices(t);
+	list_for_each_entry(dd, devices, list) {
+		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
+
+		if (!blk_queue_stackable(q)) {
+			DMERR("table load rejected: including"
+			      " non-request-stackable devices");
+			return -EINVAL;
+		}
+
+		if (q->mq_ops)
+			use_blk_mq = true;
+	}
+
+	if (use_blk_mq) {
+		/* verify _all_ devices in the table are blk-mq devices */
+		list_for_each_entry(dd, devices, list)
+			if (!bdev_get_queue(dd->dm_dev->bdev)->mq_ops) {
+				DMERR("table load rejected: not all devices"
+				      " are blk-mq request-stackable");
+				return -EINVAL;
+			}
+		t->type = DM_TYPE_MQ_REQUEST_BASED;
+
+	} else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) {
+		/* inherit live MD type */
+		t->type = live_md_type;
+
+	} else
+		t->type = DM_TYPE_REQUEST_BASED;
 
 	return 0;
 }
@@ -907,7 +928,15 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
 
 bool dm_table_request_based(struct dm_table *t)
 {
-	return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED;
+	unsigned table_type = dm_table_get_type(t);
+
+	return (table_type == DM_TYPE_REQUEST_BASED ||
+		table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
+bool dm_table_mq_request_based(struct dm_table *t)
+{
+	return dm_table_get_type(t) == DM_TYPE_MQ_REQUEST_BASED;
 }
 
 static int dm_table_alloc_md_mempools(struct dm_table *t)
@@ -1360,6 +1389,14 @@ static int queue_supports_sg_merge(struct dm_target *ti, struct dm_dev *dev,
 	return q && !test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
 }
 
+static int queue_supports_sg_gaps(struct dm_target *ti, struct dm_dev *dev,
+				  sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags);
+}
+
 static bool dm_table_all_devices_attribute(struct dm_table *t,
 					   iterate_devices_callout_fn func)
 {
@@ -1480,6 +1517,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
 
+	if (dm_table_all_devices_attribute(t, queue_supports_sg_gaps))
+		queue_flag_clear_unlocked(QUEUE_FLAG_SG_GAPS, q);
+	else
+		queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, q);
+
 	dm_table_set_integrity(t);
 
 	/*
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 242e3cec397a5c..925ec1b15e75ed 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -137,13 +137,26 @@ static int io_err_map_rq(struct dm_target *ti, struct request *clone,
 	return -EIO;
 }
 
+static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
+				   union map_info *map_context,
+				   struct request **clone)
+{
+	return -EIO;
+}
+
+static void io_err_release_clone_rq(struct request *clone)
+{
+}
+
 static struct target_type error_target = {
 	.name = "error",
-	.version = {1, 2, 0},
+	.version = {1, 3, 0},
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
 	.map_rq = io_err_map_rq,
+	.clone_and_map_rq = io_err_clone_and_map_rq,
+	.release_clone_rq = io_err_release_clone_rq,
 };
 
 int __init dm_target_init(void)
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 43adbb863f5a9e..79f694120ddf06 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1635,15 +1635,6 @@ int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd,
 	return r;
 }
 
-int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result)
-{
-	down_read(&pmd->root_lock);
-	*result = pmd->data_block_size;
-	up_read(&pmd->root_lock);
-
-	return 0;
-}
-
 int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result)
 {
 	int r = -EINVAL;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 921d15ee56a0c6..fac01a96d30311 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -182,8 +182,6 @@ int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd,
 int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd,
 				  dm_block_t *result);
 
-int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result);
-
 int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
 
 int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 07705ee181e3d2..654773cb1eeea2 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -11,6 +11,7 @@
 #include <linux/device-mapper.h>
 #include <linux/dm-io.h>
 #include <linux/dm-kcopyd.h>
+#include <linux/jiffies.h>
 #include <linux/log2.h>
 #include <linux/list.h>
 #include <linux/rculist.h>
@@ -1700,8 +1701,8 @@ static void process_cell_fail(struct thin_c *tc, struct dm_bio_prison_cell *cell
  */
 static int need_commit_due_to_time(struct pool *pool)
 {
-	return jiffies < pool->last_commit_jiffies ||
-	       jiffies > pool->last_commit_jiffies + COMMIT_PERIOD;
+	return !time_in_range(jiffies, pool->last_commit_jiffies,
+			      pool->last_commit_jiffies + COMMIT_PERIOD);
 }
 
 #define thin_pbd(node) rb_entry((node), struct dm_thin_endio_hook, rb_node)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2caf5b374649af..ec1444f49de14a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -20,6 +20,7 @@
 #include <linux/hdreg.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
+#include <linux/kthread.h>
 
 #include <trace/events/block.h>
 
@@ -78,7 +79,8 @@ struct dm_io {
 struct dm_rq_target_io {
 	struct mapped_device *md;
 	struct dm_target *ti;
-	struct request *orig, clone;
+	struct request *orig, *clone;
+	struct kthread_work work;
 	int error;
 	union map_info info;
 };
@@ -179,6 +181,7 @@ struct mapped_device {
 	 * io objects are allocated from here.
 	 */
 	mempool_t *io_pool;
+	mempool_t *rq_pool;
 
 	struct bio_set *bs;
 
@@ -210,6 +213,9 @@ struct mapped_device {
 	unsigned internal_suspend_count;
 
 	struct dm_stats stats;
+
+	struct kthread_worker kworker;
+	struct task_struct *kworker_task;
 };
 
 /*
@@ -217,6 +223,7 @@ struct mapped_device {
  */
 struct dm_md_mempools {
 	mempool_t *io_pool;
+	mempool_t *rq_pool;
 	struct bio_set *bs;
 };
 
@@ -231,6 +238,7 @@ struct table_device {
 #define RESERVED_MAX_IOS		1024
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_rq_tio_cache;
+static struct kmem_cache *_rq_cache;
 
 /*
  * Bio-based DM's mempools' reserved IOs set by the user.
@@ -288,9 +296,14 @@ static int __init local_init(void)
 	if (!_rq_tio_cache)
 		goto out_free_io_cache;
 
+	_rq_cache = kmem_cache_create("dm_clone_request", sizeof(struct request),
+				      __alignof__(struct request), 0, NULL);
+	if (!_rq_cache)
+		goto out_free_rq_tio_cache;
+
 	r = dm_uevent_init();
 	if (r)
-		goto out_free_rq_tio_cache;
+		goto out_free_rq_cache;
 
 	deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1);
 	if (!deferred_remove_workqueue) {
@@ -312,6 +325,8 @@ static int __init local_init(void)
 	destroy_workqueue(deferred_remove_workqueue);
 out_uevent_exit:
 	dm_uevent_exit();
+out_free_rq_cache:
+	kmem_cache_destroy(_rq_cache);
 out_free_rq_tio_cache:
 	kmem_cache_destroy(_rq_tio_cache);
 out_free_io_cache:
@@ -325,6 +340,7 @@ static void local_exit(void)
 	flush_scheduled_work();
 	destroy_workqueue(deferred_remove_workqueue);
 
+	kmem_cache_destroy(_rq_cache);
 	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_io_cache);
 	unregister_blkdev(_major, _name);
@@ -577,6 +593,17 @@ static void free_rq_tio(struct dm_rq_target_io *tio)
 	mempool_free(tio, tio->md->io_pool);
 }
 
+static struct request *alloc_clone_request(struct mapped_device *md,
+					   gfp_t gfp_mask)
+{
+	return mempool_alloc(md->rq_pool, gfp_mask);
+}
+
+static void free_clone_request(struct mapped_device *md, struct request *rq)
+{
+	mempool_free(rq, md->rq_pool);
+}
+
 static int md_in_flight(struct mapped_device *md)
 {
 	return atomic_read(&md->pending[READ]) +
@@ -992,7 +1019,7 @@ static void end_clone_bio(struct bio *clone, int error)
  * the md may be freed in dm_put() at the end of this function.
  * Or do dm_get() before calling this function and dm_put() later.
  */
-static void rq_completed(struct mapped_device *md, int rw, int run_queue)
+static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 {
 	atomic_dec(&md->pending[rw]);
 
@@ -1020,12 +1047,17 @@ static void free_rq_clone(struct request *clone)
 	struct dm_rq_target_io *tio = clone->end_io_data;
 
 	blk_rq_unprep_clone(clone);
+	if (clone->q && clone->q->mq_ops)
+		tio->ti->type->release_clone_rq(clone);
+	else
+		free_clone_request(tio->md, clone);
 	free_rq_tio(tio);
 }
 
 /*
  * Complete the clone and the original request.
- * Must be called without queue lock.
+ * Must be called without clone's queue lock held,
+ * see end_clone_request() for more details.
  */
 static void dm_end_request(struct request *clone, int error)
 {
@@ -1054,23 +1086,23 @@ static void dm_end_request(struct request *clone, int error)
 
 static void dm_unprep_request(struct request *rq)
 {
-	struct request *clone = rq->special;
+	struct dm_rq_target_io *tio = rq->special;
+	struct request *clone = tio->clone;
 
 	rq->special = NULL;
 	rq->cmd_flags &= ~REQ_DONTPREP;
 
-	free_rq_clone(clone);
+	if (clone)
+		free_rq_clone(clone);
 }
 
 /*
  * Requeue the original request of a clone.
  */
-void dm_requeue_unmapped_request(struct request *clone)
+static void dm_requeue_unmapped_original_request(struct mapped_device *md,
+						 struct request *rq)
 {
-	int rw = rq_data_dir(clone);
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct mapped_device *md = tio->md;
-	struct request *rq = tio->orig;
+	int rw = rq_data_dir(rq);
 	struct request_queue *q = rq->q;
 	unsigned long flags;
 
@@ -1080,9 +1112,15 @@ void dm_requeue_unmapped_request(struct request *clone)
 	blk_requeue_request(q, rq);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
-	rq_completed(md, rw, 0);
+	rq_completed(md, rw, false);
+}
+
+static void dm_requeue_unmapped_request(struct request *clone)
+{
+	struct dm_rq_target_io *tio = clone->end_io_data;
+
+	dm_requeue_unmapped_original_request(tio->md, tio->orig);
 }
-EXPORT_SYMBOL_GPL(dm_requeue_unmapped_request);
 
 static void __stop_queue(struct request_queue *q)
 {
@@ -1151,8 +1189,15 @@ static void dm_done(struct request *clone, int error, bool mapped)
 static void dm_softirq_done(struct request *rq)
 {
 	bool mapped = true;
-	struct request *clone = rq->completion_data;
-	struct dm_rq_target_io *tio = clone->end_io_data;
+	struct dm_rq_target_io *tio = rq->special;
+	struct request *clone = tio->clone;
+
+	if (!clone) {
+		blk_end_request_all(rq, tio->error);
+		rq_completed(tio->md, rq_data_dir(rq), false);
+		free_rq_tio(tio);
+		return;
+	}
 
 	if (rq->cmd_flags & REQ_FAILED)
 		mapped = false;
@@ -1164,13 +1209,11 @@ static void dm_softirq_done(struct request *rq)
  * Complete the clone and the original request with the error status
  * through softirq context.
  */
-static void dm_complete_request(struct request *clone, int error)
+static void dm_complete_request(struct request *rq, int error)
 {
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct request *rq = tio->orig;
+	struct dm_rq_target_io *tio = rq->special;
 
 	tio->error = error;
-	rq->completion_data = clone;
 	blk_complete_request(rq);
 }
 
@@ -1178,40 +1221,40 @@ static void dm_complete_request(struct request *clone, int error)
  * Complete the not-mapped clone and the original request with the error status
  * through softirq context.
  * Target's rq_end_io() function isn't called.
- * This may be used when the target's map_rq() function fails.
+ * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
  */
-void dm_kill_unmapped_request(struct request *clone, int error)
+static void dm_kill_unmapped_request(struct request *rq, int error)
 {
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct request *rq = tio->orig;
-
 	rq->cmd_flags |= REQ_FAILED;
-	dm_complete_request(clone, error);
+	dm_complete_request(rq, error);
 }
-EXPORT_SYMBOL_GPL(dm_kill_unmapped_request);
 
 /*
- * Called with the queue lock held
+ * Called with the clone's queue lock held
  */
 static void end_clone_request(struct request *clone, int error)
 {
-	/*
-	 * For just cleaning up the information of the queue in which
-	 * the clone was dispatched.
-	 * The clone is *NOT* freed actually here because it is alloced from
-	 * dm own mempool and REQ_ALLOCED isn't set in clone->cmd_flags.
-	 */
-	__blk_put_request(clone->q, clone);
+	struct dm_rq_target_io *tio = clone->end_io_data;
+
+	if (!clone->q->mq_ops) {
+		/*
+		 * For just cleaning up the information of the queue in which
+		 * the clone was dispatched.
+		 * The clone is *NOT* freed actually here because it is alloced
+		 * from dm own mempool (REQ_ALLOCED isn't set).
+		 */
+		__blk_put_request(clone->q, clone);
+	}
 
 	/*
 	 * Actual request completion is done in a softirq context which doesn't
-	 * hold the queue lock.  Otherwise, deadlock could occur because:
+	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
 	 *     - another request may be submitted by the upper level driver
 	 *       of the stacking during the completion
 	 *     - the submission which requires queue lock may be done
-	 *       against this queue
+	 *       against this clone's queue
 	 */
-	dm_complete_request(clone, error);
+	dm_complete_request(tio->orig, error);
 }
 
 /*
@@ -1689,19 +1732,19 @@ static void dm_request(struct request_queue *q, struct bio *bio)
 		_dm_request(q, bio);
 }
 
-void dm_dispatch_request(struct request *rq)
+static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
 {
 	int r;
 
-	if (blk_queue_io_stat(rq->q))
-		rq->cmd_flags |= REQ_IO_STAT;
+	if (blk_queue_io_stat(clone->q))
+		clone->cmd_flags |= REQ_IO_STAT;
 
-	rq->start_time = jiffies;
-	r = blk_insert_cloned_request(rq->q, rq);
+	clone->start_time = jiffies;
+	r = blk_insert_cloned_request(clone->q, clone);
 	if (r)
+		/* must complete clone in terms of original request */
 		dm_complete_request(rq, r);
 }
-EXPORT_SYMBOL_GPL(dm_dispatch_request);
 
 static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
 				 void *data)
@@ -1718,11 +1761,11 @@ static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
 }
 
 static int setup_clone(struct request *clone, struct request *rq,
-		       struct dm_rq_target_io *tio)
+		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
 {
 	int r;
 
-	r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
+	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
 			      dm_rq_bio_constructor, tio);
 	if (r)
 		return r;
@@ -1733,14 +1776,37 @@ static int setup_clone(struct request *clone, struct request *rq,
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
 
+	tio->clone = clone;
+
 	return 0;
 }
 
 static struct request *clone_rq(struct request *rq, struct mapped_device *md,
-				gfp_t gfp_mask)
+				struct dm_rq_target_io *tio, gfp_t gfp_mask)
+{
+	struct request *clone = alloc_clone_request(md, gfp_mask);
+
+	if (!clone)
+		return NULL;
+
+	blk_rq_init(NULL, clone);
+	if (setup_clone(clone, rq, tio, gfp_mask)) {
+		/* -ENOMEM */
+		free_clone_request(md, clone);
+		return NULL;
+	}
+
+	return clone;
+}
+
+static void map_tio_request(struct kthread_work *work);
+
+static struct dm_rq_target_io *prep_tio(struct request *rq,
+					struct mapped_device *md, gfp_t gfp_mask)
 {
-	struct request *clone;
 	struct dm_rq_target_io *tio;
+	int srcu_idx;
+	struct dm_table *table;
 
 	tio = alloc_rq_tio(md, gfp_mask);
 	if (!tio)
@@ -1748,18 +1814,23 @@ static struct request *clone_rq(struct request *rq, struct mapped_device *md,
 
 	tio->md = md;
 	tio->ti = NULL;
+	tio->clone = NULL;
 	tio->orig = rq;
 	tio->error = 0;
 	memset(&tio->info, 0, sizeof(tio->info));
-
-	clone = &tio->clone;
-	if (setup_clone(clone, rq, tio)) {
-		/* -ENOMEM */
-		free_rq_tio(tio);
-		return NULL;
+	init_kthread_work(&tio->work, map_tio_request);
+
+	table = dm_get_live_table(md, &srcu_idx);
+	if (!dm_table_mq_request_based(table)) {
+		if (!clone_rq(rq, md, tio, gfp_mask)) {
+			dm_put_live_table(md, srcu_idx);
+			free_rq_tio(tio);
+			return NULL;
+		}
 	}
+	dm_put_live_table(md, srcu_idx);
 
-	return clone;
+	return tio;
 }
 
 /*
@@ -1768,18 +1839,18 @@ static struct request *clone_rq(struct request *rq, struct mapped_device *md,
 static int dm_prep_fn(struct request_queue *q, struct request *rq)
 {
 	struct mapped_device *md = q->queuedata;
-	struct request *clone;
+	struct dm_rq_target_io *tio;
 
 	if (unlikely(rq->special)) {
 		DMWARN("Already has something in rq->special.");
 		return BLKPREP_KILL;
 	}
 
-	clone = clone_rq(rq, md, GFP_ATOMIC);
-	if (!clone)
+	tio = prep_tio(rq, md, GFP_ATOMIC);
+	if (!tio)
 		return BLKPREP_DEFER;
 
-	rq->special = clone;
+	rq->special = tio;
 	rq->cmd_flags |= REQ_DONTPREP;
 
 	return BLKPREP_OK;
@@ -1787,17 +1858,36 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
 
 /*
  * Returns:
- * 0  : the request has been processed (not requeued)
- * !0 : the request has been requeued
+ * 0                : the request has been processed
+ * DM_MAPIO_REQUEUE : the original request needs to be requeued
+ * < 0              : the request was completed due to failure
  */
-static int map_request(struct dm_target *ti, struct request *clone,
+static int map_request(struct dm_target *ti, struct request *rq,
 		       struct mapped_device *md)
 {
-	int r, requeued = 0;
-	struct dm_rq_target_io *tio = clone->end_io_data;
+	int r;
+	struct dm_rq_target_io *tio = rq->special;
+	struct request *clone = NULL;
+
+	if (tio->clone) {
+		clone = tio->clone;
+		r = ti->type->map_rq(ti, clone, &tio->info);
+	} else {
+		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
+		if (r < 0) {
+			/* The target wants to complete the I/O */
+			dm_kill_unmapped_request(rq, r);
+			return r;
+		}
+		if (IS_ERR(clone))
+			return DM_MAPIO_REQUEUE;
+		if (setup_clone(clone, rq, tio, GFP_KERNEL)) {
+			/* -ENOMEM */
+			ti->type->release_clone_rq(clone);
+			return DM_MAPIO_REQUEUE;
+		}
+	}
 
-	tio->ti = ti;
-	r = ti->type->map_rq(ti, clone, &tio->info);
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
 		/* The target has taken the I/O to submit by itself later */
@@ -1805,13 +1895,12 @@ static int map_request(struct dm_target *ti, struct request *clone,
 	case DM_MAPIO_REMAPPED:
 		/* The target has remapped the I/O so dispatch it */
 		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
-				     blk_rq_pos(tio->orig));
-		dm_dispatch_request(clone);
+				     blk_rq_pos(rq));
+		dm_dispatch_clone_request(clone, rq);
 		break;
 	case DM_MAPIO_REQUEUE:
 		/* The target wants to requeue the I/O */
 		dm_requeue_unmapped_request(clone);
-		requeued = 1;
 		break;
 	default:
 		if (r > 0) {
@@ -1820,20 +1909,27 @@ static int map_request(struct dm_target *ti, struct request *clone,
 		}
 
 		/* The target wants to complete the I/O */
-		dm_kill_unmapped_request(clone, r);
-		break;
+		dm_kill_unmapped_request(rq, r);
+		return r;
 	}
 
-	return requeued;
+	return 0;
 }
 
-static struct request *dm_start_request(struct mapped_device *md, struct request *orig)
+static void map_tio_request(struct kthread_work *work)
 {
-	struct request *clone;
+	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
+	struct request *rq = tio->orig;
+	struct mapped_device *md = tio->md;
 
+	if (map_request(tio->ti, rq, md) == DM_MAPIO_REQUEUE)
+		dm_requeue_unmapped_original_request(md, rq);
+}
+
+static void dm_start_request(struct mapped_device *md, struct request *orig)
+{
 	blk_start_request(orig);
-	clone = orig->special;
-	atomic_inc(&md->pending[rq_data_dir(clone)]);
+	atomic_inc(&md->pending[rq_data_dir(orig)]);
 
 	/*
 	 * Hold the md reference here for the in-flight I/O.
@@ -1843,8 +1939,6 @@ static struct request *dm_start_request(struct mapped_device *md, struct request
 	 * See the comment in rq_completed() too.
 	 */
 	dm_get(md);
-
-	return clone;
 }
 
 /*
@@ -1857,7 +1951,8 @@ static void dm_request_fn(struct request_queue *q)
 	int srcu_idx;
 	struct dm_table *map = dm_get_live_table(md, &srcu_idx);
 	struct dm_target *ti;
-	struct request *rq, *clone;
+	struct request *rq;
+	struct dm_rq_target_io *tio;
 	sector_t pos;
 
 	/*
@@ -1879,34 +1974,29 @@ static void dm_request_fn(struct request_queue *q)
 		ti = dm_table_find_target(map, pos);
 		if (!dm_target_is_valid(ti)) {
 			/*
-			 * Must perform setup, that dm_done() requires,
+			 * Must perform setup, that rq_completed() requires,
 			 * before calling dm_kill_unmapped_request
 			 */
 			DMERR_LIMIT("request attempted access beyond the end of device");
-			clone = dm_start_request(md, rq);
-			dm_kill_unmapped_request(clone, -EIO);
+			dm_start_request(md, rq);
+			dm_kill_unmapped_request(rq, -EIO);
 			continue;
 		}
 
 		if (ti->type->busy && ti->type->busy(ti))
 			goto delay_and_out;
 
-		clone = dm_start_request(md, rq);
-
-		spin_unlock(q->queue_lock);
-		if (map_request(ti, clone, md))
-			goto requeued;
+		dm_start_request(md, rq);
 
+		tio = rq->special;
+		/* Establish tio->ti before queuing work (map_tio_request) */
+		tio->ti = ti;
+		queue_kthread_work(&md->kworker, &tio->work);
 		BUG_ON(!irqs_disabled());
-		spin_lock(q->queue_lock);
 	}
 
 	goto out;
 
-requeued:
-	BUG_ON(!irqs_disabled());
-	spin_lock(q->queue_lock);
-
 delay_and_out:
 	blk_delay_queue(q, HZ / 10);
 out:
@@ -2092,6 +2182,7 @@ static struct mapped_device *alloc_dev(int minor)
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
 	init_completion(&md->kobj_holder.completion);
+	md->kworker_task = NULL;
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
@@ -2152,8 +2243,13 @@ static void free_dev(struct mapped_device *md)
 	unlock_fs(md);
 	bdput(md->bdev);
 	destroy_workqueue(md->wq);
+
+	if (md->kworker_task)
+		kthread_stop(md->kworker_task);
 	if (md->io_pool)
 		mempool_destroy(md->io_pool);
+	if (md->rq_pool)
+		mempool_destroy(md->rq_pool);
 	if (md->bs)
 		bioset_free(md->bs);
 	blk_integrity_unregister(md->disk);
@@ -2187,23 +2283,24 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 			bioset_free(md->bs);
 			md->bs = p->bs;
 			p->bs = NULL;
-		} else if (dm_table_get_type(t) == DM_TYPE_REQUEST_BASED) {
-			/*
-			 * There's no need to reload with request-based dm
-			 * because the size of front_pad doesn't change.
-			 * Note for future: If you are to reload bioset,
-			 * prep-ed requests in the queue may refer
-			 * to bio from the old bioset, so you must walk
-			 * through the queue to unprep.
-			 */
 		}
+		/*
+		 * There's no need to reload with request-based dm
+		 * because the size of front_pad doesn't change.
+		 * Note for future: If you are to reload bioset,
+		 * prep-ed requests in the queue may refer
+		 * to bio from the old bioset, so you must walk
+		 * through the queue to unprep.
+		 */
 		goto out;
 	}
 
-	BUG_ON(!p || md->io_pool || md->bs);
+	BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
 
 	md->io_pool = p->io_pool;
 	p->io_pool = NULL;
+	md->rq_pool = p->rq_pool;
+	p->rq_pool = NULL;
 	md->bs = p->bs;
 	p->bs = NULL;
 
@@ -2406,6 +2503,14 @@ unsigned dm_get_md_type(struct mapped_device *md)
 	return md->type;
 }
 
+static bool dm_md_type_request_based(struct mapped_device *md)
+{
+	unsigned table_type = dm_get_md_type(md);
+
+	return (table_type == DM_TYPE_REQUEST_BASED ||
+		table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
 struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
 {
 	return md->immutable_target_type;
@@ -2443,6 +2548,11 @@ static int dm_init_request_based_queue(struct mapped_device *md)
 	blk_queue_prep_rq(md->queue, dm_prep_fn);
 	blk_queue_lld_busy(md->queue, dm_lld_busy);
 
+	/* Also initialize the request-based DM worker thread */
+	init_kthread_worker(&md->kworker);
+	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
+				       "kdmwork-%s", dm_device_name(md));
+
 	elv_register_queue(md->queue);
 
 	return 1;
@@ -2453,8 +2563,7 @@ static int dm_init_request_based_queue(struct mapped_device *md)
  */
 int dm_setup_md_queue(struct mapped_device *md)
 {
-	if ((dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) &&
-	    !dm_init_request_based_queue(md)) {
+	if (dm_md_type_request_based(md) && !dm_init_request_based_queue(md)) {
 		DMWARN("Cannot initialize queue for request-based mapped device");
 		return -EINVAL;
 	}
@@ -2533,6 +2642,9 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	set_bit(DMF_FREEING, &md->flags);
 	spin_unlock(&_minor_lock);
 
+	if (dm_request_based(md))
+		flush_kthread_worker(&md->kworker);
+
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
 		dm_table_postsuspend_targets(map);
@@ -2776,8 +2888,10 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
 	 * Stop md->queue before flushing md->wq in case request-based
 	 * dm defers requests to md->wq from md->queue.
 	 */
-	if (dm_request_based(md))
+	if (dm_request_based(md)) {
 		stop_queue(md->queue);
+		flush_kthread_worker(&md->kworker);
+	}
 
 	flush_workqueue(md->wq);
 
@@ -3123,24 +3237,35 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u
 {
 	struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL);
 	struct kmem_cache *cachep;
-	unsigned int pool_size;
+	unsigned int pool_size = 0;
 	unsigned int front_pad;
 
 	if (!pools)
 		return NULL;
 
-	if (type == DM_TYPE_BIO_BASED) {
+	switch (type) {
+	case DM_TYPE_BIO_BASED:
 		cachep = _io_cache;
 		pool_size = dm_get_reserved_bio_based_ios();
 		front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
-	} else if (type == DM_TYPE_REQUEST_BASED) {
-		cachep = _rq_tio_cache;
+		break;
+	case DM_TYPE_REQUEST_BASED:
 		pool_size = dm_get_reserved_rq_based_ios();
+		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
+		if (!pools->rq_pool)
+			goto out;
+		/* fall through to setup remaining rq-based pools */
+	case DM_TYPE_MQ_REQUEST_BASED:
+		cachep = _rq_tio_cache;
+		if (!pool_size)
+			pool_size = dm_get_reserved_rq_based_ios();
 		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
 		/* per_bio_data_size is not used. See __bind_mempools(). */
 		WARN_ON(per_bio_data_size != 0);
-	} else
+		break;
+	default:
 		goto out;
+	}
 
 	pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
 	if (!pools->io_pool)
@@ -3169,6 +3294,9 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
 	if (pools->io_pool)
 		mempool_destroy(pools->io_pool);
 
+	if (pools->rq_pool)
+		mempool_destroy(pools->rq_pool);
+
 	if (pools->bs)
 		bioset_free(pools->bs);
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 84b0f9e4ba6ca1..59f53e79db8264 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -34,9 +34,10 @@
 /*
  * Type of table and mapped_device's mempool
  */
-#define DM_TYPE_NONE		0
-#define DM_TYPE_BIO_BASED	1
-#define DM_TYPE_REQUEST_BASED	2
+#define DM_TYPE_NONE			0
+#define DM_TYPE_BIO_BASED		1
+#define DM_TYPE_REQUEST_BASED		2
+#define DM_TYPE_MQ_REQUEST_BASED	3
 
 /*
  * List of devices that a metadevice uses and should open/close.
@@ -73,6 +74,7 @@ int dm_table_any_busy_target(struct dm_table *t);
 unsigned dm_table_get_type(struct dm_table *t);
 struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
+bool dm_table_mq_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
 
@@ -99,7 +101,8 @@ int dm_setup_md_queue(struct mapped_device *md);
 /*
  * To check whether the target type is request-based or not (bio-based).
  */
-#define dm_target_request_based(t) ((t)->type->map_rq != NULL)
+#define dm_target_request_based(t) (((t)->type->map_rq != NULL) || \
+				    ((t)->type->clone_and_map_rq != NULL))
 
 /*
  * To check whether the target type is a hybrid (capable of being
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index e8b4574956c73e..1277eb26b58ac6 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -332,13 +332,11 @@ static int run(struct mddev *mddev)
 	return 0;
 }
 
-static int stop(struct mddev *mddev)
+static void faulty_free(struct mddev *mddev, void *priv)
 {
-	struct faulty_conf *conf = mddev->private;
+	struct faulty_conf *conf = priv;
 
 	kfree(conf);
-	mddev->private = NULL;
-	return 0;
 }
 
 static struct md_personality faulty_personality =
@@ -348,7 +346,7 @@ static struct md_personality faulty_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= faulty_free,
 	.status		= status,
 	.check_reshape	= reshape,
 	.size		= faulty_size,
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 64713b77df1c5c..fa7d577f3d1257 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -34,7 +34,7 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 
 	lo = 0;
 	hi = mddev->raid_disks - 1;
-	conf = rcu_dereference(mddev->private);
+	conf = mddev->private;
 
 	/*
 	 * Binary Search
@@ -60,18 +60,16 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
  *
  *	Return amount of bytes we can take at this offset
  */
-static int linear_mergeable_bvec(struct request_queue *q,
+static int linear_mergeable_bvec(struct mddev *mddev,
 				 struct bvec_merge_data *bvm,
 				 struct bio_vec *biovec)
 {
-	struct mddev *mddev = q->queuedata;
 	struct dev_info *dev0;
 	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int maxbytes = biovec->bv_len;
 	struct request_queue *subq;
 
-	rcu_read_lock();
 	dev0 = which_dev(mddev, sector);
 	maxsectors = dev0->end_sector - sector;
 	subq = bdev_get_queue(dev0->rdev->bdev);
@@ -81,7 +79,6 @@ static int linear_mergeable_bvec(struct request_queue *q,
 		maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
 							     biovec));
 	}
-	rcu_read_unlock();
 
 	if (maxsectors < bio_sectors)
 		maxsectors = 0;
@@ -97,24 +94,18 @@ static int linear_mergeable_bvec(struct request_queue *q,
 		return maxsectors << 9;
 }
 
-static int linear_congested(void *data, int bits)
+static int linear_congested(struct mddev *mddev, int bits)
 {
-	struct mddev *mddev = data;
 	struct linear_conf *conf;
 	int i, ret = 0;
 
-	if (mddev_congested(mddev, bits))
-		return 1;
-
-	rcu_read_lock();
-	conf = rcu_dereference(mddev->private);
+	conf = mddev->private;
 
 	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(&q->backing_dev_info, bits);
 	}
 
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -123,12 +114,10 @@ static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disk
 	struct linear_conf *conf;
 	sector_t array_sectors;
 
-	rcu_read_lock();
-	conf = rcu_dereference(mddev->private);
+	conf = mddev->private;
 	WARN_ONCE(sectors || raid_disks,
 		  "%s does not support generic reshape\n", __func__);
 	array_sectors = conf->array_sectors;
-	rcu_read_unlock();
 
 	return array_sectors;
 }
@@ -217,10 +206,6 @@ static int linear_run (struct mddev *mddev)
 	mddev->private = conf;
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 
-	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
-	mddev->queue->backing_dev_info.congested_fn = linear_congested;
-	mddev->queue->backing_dev_info.congested_data = mddev;
-
 	ret =  md_integrity_register(mddev);
 	if (ret) {
 		kfree(conf);
@@ -252,38 +237,23 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	if (!newconf)
 		return -ENOMEM;
 
-	oldconf = rcu_dereference_protected(mddev->private,
-					    lockdep_is_held(
-						    &mddev->reconfig_mutex));
+	mddev_suspend(mddev);
+	oldconf = mddev->private;
 	mddev->raid_disks++;
-	rcu_assign_pointer(mddev->private, newconf);
+	mddev->private = newconf;
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
+	mddev_resume(mddev);
 	revalidate_disk(mddev->gendisk);
-	kfree_rcu(oldconf, rcu);
+	kfree(oldconf);
 	return 0;
 }
 
-static int linear_stop (struct mddev *mddev)
+static void linear_free(struct mddev *mddev, void *priv)
 {
-	struct linear_conf *conf =
-		rcu_dereference_protected(mddev->private,
-					  lockdep_is_held(
-						  &mddev->reconfig_mutex));
+	struct linear_conf *conf = priv;
 
-	/*
-	 * We do not require rcu protection here since
-	 * we hold reconfig_mutex for both linear_add and
-	 * linear_stop, so they cannot race.
-	 * We should make sure any old 'conf's are properly
-	 * freed though.
-	 */
-	rcu_barrier();
-	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	kfree(conf);
-	mddev->private = NULL;
-
-	return 0;
 }
 
 static void linear_make_request(struct mddev *mddev, struct bio *bio)
@@ -299,16 +269,12 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 	}
 
 	do {
-		rcu_read_lock();
-
 		tmp_dev = which_dev(mddev, bio->bi_iter.bi_sector);
 		start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
 		end_sector = tmp_dev->end_sector;
 		data_offset = tmp_dev->rdev->data_offset;
 		bio->bi_bdev = tmp_dev->rdev->bdev;
 
-		rcu_read_unlock();
-
 		if (unlikely(bio->bi_iter.bi_sector >= end_sector ||
 			     bio->bi_iter.bi_sector < start_sector))
 			goto out_of_bounds;
@@ -355,6 +321,10 @@ static void linear_status (struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
 }
 
+static void linear_quiesce(struct mddev *mddev, int state)
+{
+}
+
 static struct md_personality linear_personality =
 {
 	.name		= "linear",
@@ -362,10 +332,13 @@ static struct md_personality linear_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= linear_make_request,
 	.run		= linear_run,
-	.stop		= linear_stop,
+	.free		= linear_free,
 	.status		= linear_status,
 	.hot_add_disk	= linear_add,
 	.size		= linear_size,
+	.quiesce	= linear_quiesce,
+	.congested	= linear_congested,
+	.mergeable_bvec	= linear_mergeable_bvec,
 };
 
 static int __init linear_init (void)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 709755fb6d7b62..c8d2bac4e28be4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -72,6 +72,7 @@ static struct workqueue_struct *md_misc_wq;
 
 static int remove_and_add_spares(struct mddev *mddev,
 				 struct md_rdev *this);
+static void mddev_detach(struct mddev *mddev);
 
 /*
  * Default number of read corrections we'll attempt on an rdev
@@ -292,8 +293,8 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
 /* mddev_suspend makes sure no new requests are submitted
  * to the device, and that any requests that have been submitted
  * are completely handled.
- * Once ->stop is called and completes, the module will be completely
- * unused.
+ * Once mddev_detach() is called and completes, the module will be
+ * completely unused.
  */
 void mddev_suspend(struct mddev *mddev)
 {
@@ -321,10 +322,47 @@ EXPORT_SYMBOL_GPL(mddev_resume);
 
 int mddev_congested(struct mddev *mddev, int bits)
 {
-	return mddev->suspended;
+	struct md_personality *pers = mddev->pers;
+	int ret = 0;
+
+	rcu_read_lock();
+	if (mddev->suspended)
+		ret = 1;
+	else if (pers && pers->congested)
+		ret = pers->congested(mddev, bits);
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mddev_congested);
+static int md_congested(void *data, int bits)
+{
+	struct mddev *mddev = data;
+	return mddev_congested(mddev, bits);
 }
-EXPORT_SYMBOL(mddev_congested);
 
+static int md_mergeable_bvec(struct request_queue *q,
+			     struct bvec_merge_data *bvm,
+			     struct bio_vec *biovec)
+{
+	struct mddev *mddev = q->queuedata;
+	int ret;
+	rcu_read_lock();
+	if (mddev->suspended) {
+		/* Must always allow one vec */
+		if (bvm->bi_size == 0)
+			ret = biovec->bv_len;
+		else
+			ret = 0;
+	} else {
+		struct md_personality *pers = mddev->pers;
+		if (pers && pers->mergeable_bvec)
+			ret = pers->mergeable_bvec(mddev, bvm, biovec);
+		else
+			ret = biovec->bv_len;
+	}
+	rcu_read_unlock();
+	return ret;
+}
 /*
  * Generic flush handling for md
  */
@@ -397,12 +435,12 @@ static void md_submit_flush_data(struct work_struct *ws)
 
 void md_flush_request(struct mddev *mddev, struct bio *bio)
 {
-	spin_lock_irq(&mddev->write_lock);
+	spin_lock_irq(&mddev->lock);
 	wait_event_lock_irq(mddev->sb_wait,
 			    !mddev->flush_bio,
-			    mddev->write_lock);
+			    mddev->lock);
 	mddev->flush_bio = bio;
-	spin_unlock_irq(&mddev->write_lock);
+	spin_unlock_irq(&mddev->lock);
 
 	INIT_WORK(&mddev->flush_work, submit_flushes);
 	queue_work(md_wq, &mddev->flush_work);
@@ -465,7 +503,7 @@ void mddev_init(struct mddev *mddev)
 	atomic_set(&mddev->active, 1);
 	atomic_set(&mddev->openers, 0);
 	atomic_set(&mddev->active_io, 0);
-	spin_lock_init(&mddev->write_lock);
+	spin_lock_init(&mddev->lock);
 	atomic_set(&mddev->flush_pending, 0);
 	init_waitqueue_head(&mddev->sb_wait);
 	init_waitqueue_head(&mddev->recovery_wait);
@@ -552,32 +590,9 @@ static struct mddev *mddev_find(dev_t unit)
 	goto retry;
 }
 
-static inline int __must_check mddev_lock(struct mddev *mddev)
-{
-	return mutex_lock_interruptible(&mddev->reconfig_mutex);
-}
-
-/* Sometimes we need to take the lock in a situation where
- * failure due to interrupts is not acceptable.
- */
-static inline void mddev_lock_nointr(struct mddev *mddev)
-{
-	mutex_lock(&mddev->reconfig_mutex);
-}
-
-static inline int mddev_is_locked(struct mddev *mddev)
-{
-	return mutex_is_locked(&mddev->reconfig_mutex);
-}
-
-static inline int mddev_trylock(struct mddev *mddev)
-{
-	return mutex_trylock(&mddev->reconfig_mutex);
-}
-
 static struct attribute_group md_redundancy_group;
 
-static void mddev_unlock(struct mddev *mddev)
+void mddev_unlock(struct mddev *mddev)
 {
 	if (mddev->to_remove) {
 		/* These cannot be removed under reconfig_mutex as
@@ -619,6 +634,7 @@ static void mddev_unlock(struct mddev *mddev)
 	md_wakeup_thread(mddev->thread);
 	spin_unlock(&pers_lock);
 }
+EXPORT_SYMBOL_GPL(mddev_unlock);
 
 static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr)
 {
@@ -2230,7 +2246,7 @@ static void md_update_sb(struct mddev *mddev, int force_change)
 		return;
 	}
 
-	spin_lock_irq(&mddev->write_lock);
+	spin_lock(&mddev->lock);
 
 	mddev->utime = get_seconds();
 
@@ -2287,7 +2303,7 @@ static void md_update_sb(struct mddev *mddev, int force_change)
 	}
 
 	sync_sbs(mddev, nospares);
-	spin_unlock_irq(&mddev->write_lock);
+	spin_unlock(&mddev->lock);
 
 	pr_debug("md: updating %s RAID superblock on device (in sync %d)\n",
 		 mdname(mddev), mddev->in_sync);
@@ -2326,15 +2342,15 @@ static void md_update_sb(struct mddev *mddev, int force_change)
 	md_super_wait(mddev);
 	/* if there was a failure, MD_CHANGE_DEVS was set, and we re-write super */
 
-	spin_lock_irq(&mddev->write_lock);
+	spin_lock(&mddev->lock);
 	if (mddev->in_sync != sync_req ||
 	    test_bit(MD_CHANGE_DEVS, &mddev->flags)) {
 		/* have to write it out again */
-		spin_unlock_irq(&mddev->write_lock);
+		spin_unlock(&mddev->lock);
 		goto repeat;
 	}
 	clear_bit(MD_CHANGE_PENDING, &mddev->flags);
-	spin_unlock_irq(&mddev->write_lock);
+	spin_unlock(&mddev->lock);
 	wake_up(&mddev->sb_wait);
 	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
@@ -2381,40 +2397,41 @@ state_show(struct md_rdev *rdev, char *page)
 {
 	char *sep = "";
 	size_t len = 0;
+	unsigned long flags = ACCESS_ONCE(rdev->flags);
 
-	if (test_bit(Faulty, &rdev->flags) ||
+	if (test_bit(Faulty, &flags) ||
 	    rdev->badblocks.unacked_exist) {
 		len+= sprintf(page+len, "%sfaulty",sep);
 		sep = ",";
 	}
-	if (test_bit(In_sync, &rdev->flags)) {
+	if (test_bit(In_sync, &flags)) {
 		len += sprintf(page+len, "%sin_sync",sep);
 		sep = ",";
 	}
-	if (test_bit(WriteMostly, &rdev->flags)) {
+	if (test_bit(WriteMostly, &flags)) {
 		len += sprintf(page+len, "%swrite_mostly",sep);
 		sep = ",";
 	}
-	if (test_bit(Blocked, &rdev->flags) ||
+	if (test_bit(Blocked, &flags) ||
 	    (rdev->badblocks.unacked_exist
-	     && !test_bit(Faulty, &rdev->flags))) {
+	     && !test_bit(Faulty, &flags))) {
 		len += sprintf(page+len, "%sblocked", sep);
 		sep = ",";
 	}
-	if (!test_bit(Faulty, &rdev->flags) &&
-	    !test_bit(In_sync, &rdev->flags)) {
+	if (!test_bit(Faulty, &flags) &&
+	    !test_bit(In_sync, &flags)) {
 		len += sprintf(page+len, "%sspare", sep);
 		sep = ",";
 	}
-	if (test_bit(WriteErrorSeen, &rdev->flags)) {
+	if (test_bit(WriteErrorSeen, &flags)) {
 		len += sprintf(page+len, "%swrite_error", sep);
 		sep = ",";
 	}
-	if (test_bit(WantReplacement, &rdev->flags)) {
+	if (test_bit(WantReplacement, &flags)) {
 		len += sprintf(page+len, "%swant_replacement", sep);
 		sep = ",";
 	}
-	if (test_bit(Replacement, &rdev->flags)) {
+	if (test_bit(Replacement, &flags)) {
 		len += sprintf(page+len, "%sreplacement", sep);
 		sep = ",";
 	}
@@ -2927,21 +2944,12 @@ rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
 	struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
 	struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj);
-	struct mddev *mddev = rdev->mddev;
-	ssize_t rv;
 
 	if (!entry->show)
 		return -EIO;
-
-	rv = mddev ? mddev_lock(mddev) : -EBUSY;
-	if (!rv) {
-		if (rdev->mddev == NULL)
-			rv = -EBUSY;
-		else
-			rv = entry->show(rdev, page);
-		mddev_unlock(mddev);
-	}
-	return rv;
+	if (!rdev->mddev)
+		return -EBUSY;
+	return entry->show(rdev, page);
 }
 
 static ssize_t
@@ -3212,11 +3220,13 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len)
 		mddev->safemode_delay = 0;
 	else {
 		unsigned long old_delay = mddev->safemode_delay;
-		mddev->safemode_delay = (msec*HZ)/1000;
-		if (mddev->safemode_delay == 0)
-			mddev->safemode_delay = 1;
-		if (mddev->safemode_delay < old_delay || old_delay == 0)
-			md_safemode_timeout((unsigned long)mddev);
+		unsigned long new_delay = (msec*HZ)/1000;
+
+		if (new_delay == 0)
+			new_delay = 1;
+		mddev->safemode_delay = new_delay;
+		if (new_delay < old_delay || old_delay == 0)
+			mod_timer(&mddev->safemode_timer, jiffies+1);
 	}
 	return len;
 }
@@ -3226,41 +3236,52 @@ __ATTR(safe_mode_delay, S_IRUGO|S_IWUSR,safe_delay_show, safe_delay_store);
 static ssize_t
 level_show(struct mddev *mddev, char *page)
 {
-	struct md_personality *p = mddev->pers;
+	struct md_personality *p;
+	int ret;
+	spin_lock(&mddev->lock);
+	p = mddev->pers;
 	if (p)
-		return sprintf(page, "%s\n", p->name);
+		ret = sprintf(page, "%s\n", p->name);
 	else if (mddev->clevel[0])
-		return sprintf(page, "%s\n", mddev->clevel);
+		ret = sprintf(page, "%s\n", mddev->clevel);
 	else if (mddev->level != LEVEL_NONE)
-		return sprintf(page, "%d\n", mddev->level);
+		ret = sprintf(page, "%d\n", mddev->level);
 	else
-		return 0;
+		ret = 0;
+	spin_unlock(&mddev->lock);
+	return ret;
 }
 
 static ssize_t
 level_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	char clevel[16];
-	ssize_t rv = len;
-	struct md_personality *pers;
+	ssize_t rv;
+	size_t slen = len;
+	struct md_personality *pers, *oldpers;
 	long level;
-	void *priv;
+	void *priv, *oldpriv;
 	struct md_rdev *rdev;
 
+	if (slen == 0 || slen >= sizeof(clevel))
+		return -EINVAL;
+
+	rv = mddev_lock(mddev);
+	if (rv)
+		return rv;
+
 	if (mddev->pers == NULL) {
-		if (len == 0)
-			return 0;
-		if (len >= sizeof(mddev->clevel))
-			return -ENOSPC;
-		strncpy(mddev->clevel, buf, len);
-		if (mddev->clevel[len-1] == '\n')
-			len--;
-		mddev->clevel[len] = 0;
+		strncpy(mddev->clevel, buf, slen);
+		if (mddev->clevel[slen-1] == '\n')
+			slen--;
+		mddev->clevel[slen] = 0;
 		mddev->level = LEVEL_NONE;
-		return rv;
+		rv = len;
+		goto out_unlock;
 	}
+	rv = -EROFS;
 	if (mddev->ro)
-		return  -EROFS;
+		goto out_unlock;
 
 	/* request to change the personality.  Need to ensure:
 	 *  - array is not engaged in resync/recovery/reshape
@@ -3268,25 +3289,25 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	 *  - new personality will access other array.
 	 */
 
+	rv = -EBUSY;
 	if (mddev->sync_thread ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector ||
 	    mddev->sysfs_active)
-		return -EBUSY;
+		goto out_unlock;
 
+	rv = -EINVAL;
 	if (!mddev->pers->quiesce) {
 		printk(KERN_WARNING "md: %s: %s does not support online personality change\n",
 		       mdname(mddev), mddev->pers->name);
-		return -EINVAL;
+		goto out_unlock;
 	}
 
 	/* Now find the new personality */
-	if (len == 0 || len >= sizeof(clevel))
-		return -EINVAL;
-	strncpy(clevel, buf, len);
-	if (clevel[len-1] == '\n')
-		len--;
-	clevel[len] = 0;
+	strncpy(clevel, buf, slen);
+	if (clevel[slen-1] == '\n')
+		slen--;
+	clevel[slen] = 0;
 	if (kstrtol(clevel, 10, &level))
 		level = LEVEL_NONE;
 
@@ -3297,20 +3318,23 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	if (!pers || !try_module_get(pers->owner)) {
 		spin_unlock(&pers_lock);
 		printk(KERN_WARNING "md: personality %s not loaded\n", clevel);
-		return -EINVAL;
+		rv = -EINVAL;
+		goto out_unlock;
 	}
 	spin_unlock(&pers_lock);
 
 	if (pers == mddev->pers) {
 		/* Nothing to do! */
 		module_put(pers->owner);
-		return rv;
+		rv = len;
+		goto out_unlock;
 	}
 	if (!pers->takeover) {
 		module_put(pers->owner);
 		printk(KERN_WARNING "md: %s: %s does not support personality takeover\n",
 		       mdname(mddev), clevel);
-		return -EINVAL;
+		rv = -EINVAL;
+		goto out_unlock;
 	}
 
 	rdev_for_each(rdev, mddev)
@@ -3330,30 +3354,29 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		module_put(pers->owner);
 		printk(KERN_WARNING "md: %s: %s would not accept array\n",
 		       mdname(mddev), clevel);
-		return PTR_ERR(priv);
+		rv = PTR_ERR(priv);
+		goto out_unlock;
 	}
 
 	/* Looks like we have a winner */
 	mddev_suspend(mddev);
-	mddev->pers->stop(mddev);
+	mddev_detach(mddev);
 
-	if (mddev->pers->sync_request == NULL &&
-	    pers->sync_request != NULL) {
-		/* need to add the md_redundancy_group */
-		if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
-			printk(KERN_WARNING
-			       "md: cannot register extra attributes for %s\n",
-			       mdname(mddev));
-		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
-	}
-	if (mddev->pers->sync_request != NULL &&
-	    pers->sync_request == NULL) {
-		/* need to remove the md_redundancy_group */
-		if (mddev->to_remove == NULL)
-			mddev->to_remove = &md_redundancy_group;
-	}
+	spin_lock(&mddev->lock);
+	oldpers = mddev->pers;
+	oldpriv = mddev->private;
+	mddev->pers = pers;
+	mddev->private = priv;
+	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+	mddev->level = mddev->new_level;
+	mddev->layout = mddev->new_layout;
+	mddev->chunk_sectors = mddev->new_chunk_sectors;
+	mddev->delta_disks = 0;
+	mddev->reshape_backwards = 0;
+	mddev->degraded = 0;
+	spin_unlock(&mddev->lock);
 
-	if (mddev->pers->sync_request == NULL &&
+	if (oldpers->sync_request == NULL &&
 	    mddev->external) {
 		/* We are converting from a no-redundancy array
 		 * to a redundancy array and metadata is managed
@@ -3367,6 +3390,24 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->safemode = 0;
 	}
 
+	oldpers->free(mddev, oldpriv);
+
+	if (oldpers->sync_request == NULL &&
+	    pers->sync_request != NULL) {
+		/* need to add the md_redundancy_group */
+		if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+			printk(KERN_WARNING
+			       "md: cannot register extra attributes for %s\n",
+			       mdname(mddev));
+		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
+	}
+	if (oldpers->sync_request != NULL &&
+	    pers->sync_request == NULL) {
+		/* need to remove the md_redundancy_group */
+		if (mddev->to_remove == NULL)
+			mddev->to_remove = &md_redundancy_group;
+	}
+
 	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk < 0)
 			continue;
@@ -3392,17 +3433,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		}
 	}
 
-	module_put(mddev->pers->owner);
-	mddev->pers = pers;
-	mddev->private = priv;
-	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
-	mddev->level = mddev->new_level;
-	mddev->layout = mddev->new_layout;
-	mddev->chunk_sectors = mddev->new_chunk_sectors;
-	mddev->delta_disks = 0;
-	mddev->reshape_backwards = 0;
-	mddev->degraded = 0;
-	if (mddev->pers->sync_request == NULL) {
+	if (pers->sync_request == NULL) {
 		/* this is now an array without redundancy, so
 		 * it must always be in_sync
 		 */
@@ -3417,6 +3448,9 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		md_update_sb(mddev, 1);
 	sysfs_notify(&mddev->kobj, NULL, "level");
 	md_new_event(mddev);
+	rv = len;
+out_unlock:
+	mddev_unlock(mddev);
 	return rv;
 }
 
@@ -3439,28 +3473,32 @@ layout_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	char *e;
 	unsigned long n = simple_strtoul(buf, &e, 10);
+	int err;
 
 	if (!*buf || (*e && *e != '\n'))
 		return -EINVAL;
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 
 	if (mddev->pers) {
-		int err;
 		if (mddev->pers->check_reshape == NULL)
-			return -EBUSY;
-		if (mddev->ro)
-			return -EROFS;
-		mddev->new_layout = n;
-		err = mddev->pers->check_reshape(mddev);
-		if (err) {
-			mddev->new_layout = mddev->layout;
-			return err;
+			err = -EBUSY;
+		else if (mddev->ro)
+			err = -EROFS;
+		else {
+			mddev->new_layout = n;
+			err = mddev->pers->check_reshape(mddev);
+			if (err)
+				mddev->new_layout = mddev->layout;
 		}
 	} else {
 		mddev->new_layout = n;
 		if (mddev->reshape_position == MaxSector)
 			mddev->layout = n;
 	}
-	return len;
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 static struct md_sysfs_entry md_layout =
 __ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);
@@ -3483,32 +3521,39 @@ static ssize_t
 raid_disks_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	char *e;
-	int rv = 0;
+	int err;
 	unsigned long n = simple_strtoul(buf, &e, 10);
 
 	if (!*buf || (*e && *e != '\n'))
 		return -EINVAL;
 
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 	if (mddev->pers)
-		rv = update_raid_disks(mddev, n);
+		err = update_raid_disks(mddev, n);
 	else if (mddev->reshape_position != MaxSector) {
 		struct md_rdev *rdev;
 		int olddisks = mddev->raid_disks - mddev->delta_disks;
 
+		err = -EINVAL;
 		rdev_for_each(rdev, mddev) {
 			if (olddisks < n &&
 			    rdev->data_offset < rdev->new_data_offset)
-				return -EINVAL;
+				goto out_unlock;
 			if (olddisks > n &&
 			    rdev->data_offset > rdev->new_data_offset)
-				return -EINVAL;
+				goto out_unlock;
 		}
+		err = 0;
 		mddev->delta_disks = n - olddisks;
 		mddev->raid_disks = n;
 		mddev->reshape_backwards = (mddev->delta_disks < 0);
 	} else
 		mddev->raid_disks = n;
-	return rv ? rv : len;
+out_unlock:
+	mddev_unlock(mddev);
+	return err ? err : len;
 }
 static struct md_sysfs_entry md_raid_disks =
 __ATTR(raid_disks, S_IRUGO|S_IWUSR, raid_disks_show, raid_disks_store);
@@ -3527,30 +3572,34 @@ chunk_size_show(struct mddev *mddev, char *page)
 static ssize_t
 chunk_size_store(struct mddev *mddev, const char *buf, size_t len)
 {
+	int err;
 	char *e;
 	unsigned long n = simple_strtoul(buf, &e, 10);
 
 	if (!*buf || (*e && *e != '\n'))
 		return -EINVAL;
 
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 	if (mddev->pers) {
-		int err;
 		if (mddev->pers->check_reshape == NULL)
-			return -EBUSY;
-		if (mddev->ro)
-			return -EROFS;
-		mddev->new_chunk_sectors = n >> 9;
-		err = mddev->pers->check_reshape(mddev);
-		if (err) {
-			mddev->new_chunk_sectors = mddev->chunk_sectors;
-			return err;
+			err = -EBUSY;
+		else if (mddev->ro)
+			err = -EROFS;
+		else {
+			mddev->new_chunk_sectors = n >> 9;
+			err = mddev->pers->check_reshape(mddev);
+			if (err)
+				mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
 	} else {
 		mddev->new_chunk_sectors = n >> 9;
 		if (mddev->reshape_position == MaxSector)
 			mddev->chunk_sectors = n >> 9;
 	}
-	return len;
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 static struct md_sysfs_entry md_chunk_size =
 __ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store);
@@ -3566,20 +3615,27 @@ resync_start_show(struct mddev *mddev, char *page)
 static ssize_t
 resync_start_store(struct mddev *mddev, const char *buf, size_t len)
 {
+	int err;
 	char *e;
 	unsigned long long n = simple_strtoull(buf, &e, 10);
 
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 	if (mddev->pers && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
-		return -EBUSY;
-	if (cmd_match(buf, "none"))
+		err = -EBUSY;
+	else if (cmd_match(buf, "none"))
 		n = MaxSector;
 	else if (!*buf || (*e && *e != '\n'))
-		return -EINVAL;
+		err = -EINVAL;
 
-	mddev->recovery_cp = n;
-	if (mddev->pers)
-		set_bit(MD_CHANGE_CLEAN, &mddev->flags);
-	return len;
+	if (!err) {
+		mddev->recovery_cp = n;
+		if (mddev->pers)
+			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+	}
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 static struct md_sysfs_entry md_resync_start =
 __ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store);
@@ -3677,8 +3733,39 @@ static int restart_array(struct mddev *mddev);
 static ssize_t
 array_state_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	int err = -EINVAL;
+	int err;
 	enum array_state st = match_word(buf, array_states);
+
+	if (mddev->pers && (st == active || st == clean) && mddev->ro != 1) {
+		/* don't take reconfig_mutex when toggling between
+		 * clean and active
+		 */
+		spin_lock(&mddev->lock);
+		if (st == active) {
+			restart_array(mddev);
+			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+			wake_up(&mddev->sb_wait);
+			err = 0;
+		} else /* st == clean */ {
+			restart_array(mddev);
+			if (atomic_read(&mddev->writes_pending) == 0) {
+				if (mddev->in_sync == 0) {
+					mddev->in_sync = 1;
+					if (mddev->safemode == 1)
+						mddev->safemode = 0;
+					set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+				}
+				err = 0;
+			} else
+				err = -EBUSY;
+		}
+		spin_unlock(&mddev->lock);
+		return err;
+	}
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	err = -EINVAL;
 	switch(st) {
 	case bad_word:
 		break;
@@ -3722,7 +3809,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case clean:
 		if (mddev->pers) {
 			restart_array(mddev);
-			spin_lock_irq(&mddev->write_lock);
+			spin_lock(&mddev->lock);
 			if (atomic_read(&mddev->writes_pending) == 0) {
 				if (mddev->in_sync == 0) {
 					mddev->in_sync = 1;
@@ -3733,7 +3820,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 				err = 0;
 			} else
 				err = -EBUSY;
-			spin_unlock_irq(&mddev->write_lock);
+			spin_unlock(&mddev->lock);
 		} else
 			err = -EINVAL;
 		break;
@@ -3754,14 +3841,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		/* these cannot be set */
 		break;
 	}
-	if (err)
-		return err;
-	else {
+
+	if (!err) {
 		if (mddev->hold_active == UNTIL_IOCTL)
 			mddev->hold_active = 0;
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
-		return len;
 	}
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 static struct md_sysfs_entry md_array_state =
 __ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
@@ -3822,6 +3909,11 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 	    minor != MINOR(dev))
 		return -EOVERFLOW;
 
+	flush_workqueue(md_misc_wq);
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 	if (mddev->persistent) {
 		rdev = md_import_device(dev, mddev->major_version,
 					mddev->minor_version);
@@ -3845,6 +3937,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
  out:
 	if (err)
 		export_rdev(rdev);
+	mddev_unlock(mddev);
 	return err ? err : len;
 }
 
@@ -3856,7 +3949,11 @@ bitmap_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	char *end;
 	unsigned long chunk, end_chunk;
+	int err;
 
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 	if (!mddev->bitmap)
 		goto out;
 	/* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */
@@ -3874,6 +3971,7 @@ bitmap_store(struct mddev *mddev, const char *buf, size_t len)
 	}
 	bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
 out:
+	mddev_unlock(mddev);
 	return len;
 }
 
@@ -3901,6 +3999,9 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
 
 	if (err < 0)
 		return err;
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 	if (mddev->pers) {
 		err = update_size(mddev, sectors);
 		md_update_sb(mddev, 1);
@@ -3911,6 +4012,7 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
 		else
 			err = -ENOSPC;
 	}
+	mddev_unlock(mddev);
 	return err ? err : len;
 }
 
@@ -3940,21 +4042,28 @@ metadata_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	int major, minor;
 	char *e;
+	int err;
 	/* Changing the details of 'external' metadata is
 	 * always permitted.  Otherwise there must be
 	 * no devices attached to the array.
 	 */
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	err = -EBUSY;
 	if (mddev->external && strncmp(buf, "external:", 9) == 0)
 		;
 	else if (!list_empty(&mddev->disks))
-		return -EBUSY;
+		goto out_unlock;
 
+	err = 0;
 	if (cmd_match(buf, "none")) {
 		mddev->persistent = 0;
 		mddev->external = 0;
 		mddev->major_version = 0;
 		mddev->minor_version = 90;
-		return len;
+		goto out_unlock;
 	}
 	if (strncmp(buf, "external:", 9) == 0) {
 		size_t namelen = len-9;
@@ -3968,22 +4077,27 @@ metadata_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->external = 1;
 		mddev->major_version = 0;
 		mddev->minor_version = 90;
-		return len;
+		goto out_unlock;
 	}
 	major = simple_strtoul(buf, &e, 10);
+	err = -EINVAL;
 	if (e==buf || *e != '.')
-		return -EINVAL;
+		goto out_unlock;
 	buf = e+1;
 	minor = simple_strtoul(buf, &e, 10);
 	if (e==buf || (*e && *e != '\n') )
-		return -EINVAL;
+		goto out_unlock;
+	err = -ENOENT;
 	if (major >= ARRAY_SIZE(super_types) || super_types[major].name == NULL)
-		return -ENOENT;
+		goto out_unlock;
 	mddev->major_version = major;
 	mddev->minor_version = minor;
 	mddev->persistent = 1;
 	mddev->external = 0;
-	return len;
+	err = 0;
+out_unlock:
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry md_metadata =
@@ -3993,20 +4107,21 @@ static ssize_t
 action_show(struct mddev *mddev, char *page)
 {
 	char *type = "idle";
-	if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+	unsigned long recovery = mddev->recovery;
+	if (test_bit(MD_RECOVERY_FROZEN, &recovery))
 		type = "frozen";
-	else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-	    (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
-		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+	else if (test_bit(MD_RECOVERY_RUNNING, &recovery) ||
+	    (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery))) {
+		if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
 			type = "reshape";
-		else if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
-			if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+		else if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
+			if (!test_bit(MD_RECOVERY_REQUESTED, &recovery))
 				type = "resync";
-			else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+			else if (test_bit(MD_RECOVERY_CHECK, &recovery))
 				type = "check";
 			else
 				type = "repair";
-		} else if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
+		} else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
 			type = "recover";
 	}
 	return sprintf(page, "%s\n", type);
@@ -4027,7 +4142,10 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 		flush_workqueue(md_misc_wq);
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
+			if (mddev_lock(mddev) == 0) {
+				md_reap_sync_thread(mddev);
+				mddev_unlock(mddev);
+			}
 		}
 	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
@@ -4041,7 +4159,11 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 		int err;
 		if (mddev->pers->start_reshape == NULL)
 			return -EINVAL;
-		err = mddev->pers->start_reshape(mddev);
+		err = mddev_lock(mddev);
+		if (!err) {
+			err = mddev->pers->start_reshape(mddev);
+			mddev_unlock(mddev);
+		}
 		if (err)
 			return err;
 		sysfs_notify(&mddev->kobj, NULL, "degraded");
@@ -4225,22 +4347,36 @@ static ssize_t
 min_sync_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	unsigned long long min;
+	int err;
+	int chunk;
+
 	if (kstrtoull(buf, 10, &min))
 		return -EINVAL;
+
+	spin_lock(&mddev->lock);
+	err = -EINVAL;
 	if (min > mddev->resync_max)
-		return -EINVAL;
+		goto out_unlock;
+
+	err = -EBUSY;
 	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		return -EBUSY;
+		goto out_unlock;
 
 	/* Must be a multiple of chunk_size */
-	if (mddev->chunk_sectors) {
+	chunk = mddev->chunk_sectors;
+	if (chunk) {
 		sector_t temp = min;
-		if (sector_div(temp, mddev->chunk_sectors))
-			return -EINVAL;
+
+		err = -EINVAL;
+		if (sector_div(temp, chunk))
+			goto out_unlock;
 	}
 	mddev->resync_min = min;
+	err = 0;
 
-	return len;
+out_unlock:
+	spin_unlock(&mddev->lock);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry md_min_sync =
@@ -4258,29 +4394,42 @@ max_sync_show(struct mddev *mddev, char *page)
 static ssize_t
 max_sync_store(struct mddev *mddev, const char *buf, size_t len)
 {
+	int err;
+	spin_lock(&mddev->lock);
 	if (strncmp(buf, "max", 3) == 0)
 		mddev->resync_max = MaxSector;
 	else {
 		unsigned long long max;
+		int chunk;
+
+		err = -EINVAL;
 		if (kstrtoull(buf, 10, &max))
-			return -EINVAL;
+			goto out_unlock;
 		if (max < mddev->resync_min)
-			return -EINVAL;
+			goto out_unlock;
+
+		err = -EBUSY;
 		if (max < mddev->resync_max &&
 		    mddev->ro == 0 &&
 		    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-			return -EBUSY;
+			goto out_unlock;
 
 		/* Must be a multiple of chunk_size */
-		if (mddev->chunk_sectors) {
+		chunk = mddev->chunk_sectors;
+		if (chunk) {
 			sector_t temp = max;
-			if (sector_div(temp, mddev->chunk_sectors))
-				return -EINVAL;
+
+			err = -EINVAL;
+			if (sector_div(temp, chunk))
+				goto out_unlock;
 		}
 		mddev->resync_max = max;
 	}
 	wake_up(&mddev->recovery_wait);
-	return len;
+	err = 0;
+out_unlock:
+	spin_unlock(&mddev->lock);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry md_max_sync =
@@ -4297,14 +4446,20 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	char *e;
 	unsigned long long new = simple_strtoull(buf, &e, 10);
-	unsigned long long old = mddev->suspend_lo;
+	unsigned long long old;
+	int err;
 
-	if (mddev->pers == NULL ||
-	    mddev->pers->quiesce == NULL)
-		return -EINVAL;
 	if (buf == e || (*e && *e != '\n'))
 		return -EINVAL;
 
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	err = -EINVAL;
+	if (mddev->pers == NULL ||
+	    mddev->pers->quiesce == NULL)
+		goto unlock;
+	old = mddev->suspend_lo;
 	mddev->suspend_lo = new;
 	if (new >= old)
 		/* Shrinking suspended region */
@@ -4314,7 +4469,10 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
 	}
-	return len;
+	err = 0;
+unlock:
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 static struct md_sysfs_entry md_suspend_lo =
 __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
@@ -4330,14 +4488,20 @@ suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	char *e;
 	unsigned long long new = simple_strtoull(buf, &e, 10);
-	unsigned long long old = mddev->suspend_hi;
+	unsigned long long old;
+	int err;
 
-	if (mddev->pers == NULL ||
-	    mddev->pers->quiesce == NULL)
-		return -EINVAL;
 	if (buf == e || (*e && *e != '\n'))
 		return -EINVAL;
 
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	err = -EINVAL;
+	if (mddev->pers == NULL ||
+	    mddev->pers->quiesce == NULL)
+		goto unlock;
+	old = mddev->suspend_hi;
 	mddev->suspend_hi = new;
 	if (new <= old)
 		/* Shrinking suspended region */
@@ -4347,7 +4511,10 @@ suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
 	}
-	return len;
+	err = 0;
+unlock:
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 static struct md_sysfs_entry md_suspend_hi =
 __ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
@@ -4367,11 +4534,17 @@ reshape_position_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	struct md_rdev *rdev;
 	char *e;
+	int err;
 	unsigned long long new = simple_strtoull(buf, &e, 10);
-	if (mddev->pers)
-		return -EBUSY;
+
 	if (buf == e || (*e && *e != '\n'))
 		return -EINVAL;
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	err = -EBUSY;
+	if (mddev->pers)
+		goto unlock;
 	mddev->reshape_position = new;
 	mddev->delta_disks = 0;
 	mddev->reshape_backwards = 0;
@@ -4380,7 +4553,10 @@ reshape_position_store(struct mddev *mddev, const char *buf, size_t len)
 	mddev->new_chunk_sectors = mddev->chunk_sectors;
 	rdev_for_each(rdev, mddev)
 		rdev->new_data_offset = rdev->data_offset;
-	return len;
+	err = 0;
+unlock:
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry md_reshape_position =
@@ -4398,6 +4574,8 @@ static ssize_t
 reshape_direction_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	int backwards = 0;
+	int err;
+
 	if (cmd_match(buf, "forwards"))
 		backwards = 0;
 	else if (cmd_match(buf, "backwards"))
@@ -4407,16 +4585,19 @@ reshape_direction_store(struct mddev *mddev, const char *buf, size_t len)
 	if (mddev->reshape_backwards == backwards)
 		return len;
 
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 	/* check if we are allowed to change */
 	if (mddev->delta_disks)
-		return -EBUSY;
-
-	if (mddev->persistent &&
+		err = -EBUSY;
+	else if (mddev->persistent &&
 	    mddev->major_version == 0)
-		return -EINVAL;
-
-	mddev->reshape_backwards = backwards;
-	return len;
+		err =  -EINVAL;
+	else
+		mddev->reshape_backwards = backwards;
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry md_reshape_direction =
@@ -4437,6 +4618,11 @@ static ssize_t
 array_size_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	sector_t sectors;
+	int err;
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
 
 	if (strncmp(buf, "default", 7) == 0) {
 		if (mddev->pers)
@@ -4447,19 +4633,22 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->external_size = 0;
 	} else {
 		if (strict_blocks_to_sectors(buf, &sectors) < 0)
-			return -EINVAL;
-		if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
-			return -E2BIG;
-
-		mddev->external_size = 1;
+			err = -EINVAL;
+		else if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
+			err = -E2BIG;
+		else
+			mddev->external_size = 1;
 	}
 
-	mddev->array_sectors = sectors;
-	if (mddev->pers) {
-		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
+	if (!err) {
+		mddev->array_sectors = sectors;
+		if (mddev->pers) {
+			set_capacity(mddev->gendisk, mddev->array_sectors);
+			revalidate_disk(mddev->gendisk);
+		}
 	}
-	return len;
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry md_array_size =
@@ -4523,11 +4712,7 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 	mddev_get(mddev);
 	spin_unlock(&all_mddevs_lock);
 
-	rv = mddev_lock(mddev);
-	if (!rv) {
-		rv = entry->show(mddev, page);
-		mddev_unlock(mddev);
-	}
+	rv = entry->show(mddev, page);
 	mddev_put(mddev);
 	return rv;
 }
@@ -4551,13 +4736,7 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
 	}
 	mddev_get(mddev);
 	spin_unlock(&all_mddevs_lock);
-	if (entry->store == new_dev_store)
-		flush_workqueue(md_misc_wq);
-	rv = mddev_lock(mddev);
-	if (!rv) {
-		rv = entry->store(mddev, page, length);
-		mddev_unlock(mddev);
-	}
+	rv = entry->store(mddev, page, length);
 	mddev_put(mddev);
 	return rv;
 }
@@ -4825,7 +5004,6 @@ int md_run(struct mddev *mddev)
 			       mddev->clevel);
 		return -EINVAL;
 	}
-	mddev->pers = pers;
 	spin_unlock(&pers_lock);
 	if (mddev->level != pers->level) {
 		mddev->level = pers->level;
@@ -4836,7 +5014,6 @@ int md_run(struct mddev *mddev)
 	if (mddev->reshape_position != MaxSector &&
 	    pers->start_reshape == NULL) {
 		/* This personality cannot handle reshaping... */
-		mddev->pers = NULL;
 		module_put(pers->owner);
 		return -EINVAL;
 	}
@@ -4880,35 +5057,38 @@ int md_run(struct mddev *mddev)
 	if (start_readonly && mddev->ro == 0)
 		mddev->ro = 2; /* read-only, but switch on first write */
 
-	err = mddev->pers->run(mddev);
+	err = pers->run(mddev);
 	if (err)
 		printk(KERN_ERR "md: pers->run() failed ...\n");
-	else if (mddev->pers->size(mddev, 0, 0) < mddev->array_sectors) {
+	else if (pers->size(mddev, 0, 0) < mddev->array_sectors) {
 		WARN_ONCE(!mddev->external_size, "%s: default size too small,"
 			  " but 'external_size' not in effect?\n", __func__);
 		printk(KERN_ERR
 		       "md: invalid array_size %llu > default size %llu\n",
 		       (unsigned long long)mddev->array_sectors / 2,
-		       (unsigned long long)mddev->pers->size(mddev, 0, 0) / 2);
+		       (unsigned long long)pers->size(mddev, 0, 0) / 2);
 		err = -EINVAL;
-		mddev->pers->stop(mddev);
 	}
-	if (err == 0 && mddev->pers->sync_request &&
+	if (err == 0 && pers->sync_request &&
 	    (mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
 		err = bitmap_create(mddev);
-		if (err) {
+		if (err)
 			printk(KERN_ERR "%s: failed to create bitmap (%d)\n",
 			       mdname(mddev), err);
-			mddev->pers->stop(mddev);
-		}
 	}
 	if (err) {
-		module_put(mddev->pers->owner);
-		mddev->pers = NULL;
+		mddev_detach(mddev);
+		pers->free(mddev, mddev->private);
+		module_put(pers->owner);
 		bitmap_destroy(mddev);
 		return err;
 	}
-	if (mddev->pers->sync_request) {
+	if (mddev->queue) {
+		mddev->queue->backing_dev_info.congested_data = mddev;
+		mddev->queue->backing_dev_info.congested_fn = md_congested;
+		blk_queue_merge_bvec(mddev->queue, md_mergeable_bvec);
+	}
+	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
 		    sysfs_create_group(&mddev->kobj, &md_redundancy_group))
 			printk(KERN_WARNING
@@ -4927,7 +5107,10 @@ int md_run(struct mddev *mddev)
 	mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
 	mddev->in_sync = 1;
 	smp_wmb();
+	spin_lock(&mddev->lock);
+	mddev->pers = pers;
 	mddev->ready = 1;
+	spin_unlock(&mddev->lock);
 	rdev_for_each(rdev, mddev)
 		if (rdev->raid_disk >= 0)
 			if (sysfs_link_rdev(mddev, rdev))
@@ -5070,14 +5253,38 @@ void md_stop_writes(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(md_stop_writes);
 
+static void mddev_detach(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+	/* wait for behind writes to complete */
+	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+		printk(KERN_INFO "md:%s: behind writes in progress - waiting to stop.\n",
+		       mdname(mddev));
+		/* need to kick something here to make sure I/O goes? */
+		wait_event(bitmap->behind_wait,
+			   atomic_read(&bitmap->behind_writes) == 0);
+	}
+	if (mddev->pers && mddev->pers->quiesce) {
+		mddev->pers->quiesce(mddev, 1);
+		mddev->pers->quiesce(mddev, 0);
+	}
+	md_unregister_thread(&mddev->thread);
+	if (mddev->queue)
+		blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+}
+
 static void __md_stop(struct mddev *mddev)
 {
+	struct md_personality *pers = mddev->pers;
+	mddev_detach(mddev);
+	spin_lock(&mddev->lock);
 	mddev->ready = 0;
-	mddev->pers->stop(mddev);
-	if (mddev->pers->sync_request && mddev->to_remove == NULL)
-		mddev->to_remove = &md_redundancy_group;
-	module_put(mddev->pers->owner);
 	mddev->pers = NULL;
+	spin_unlock(&mddev->lock);
+	pers->free(mddev, mddev->private);
+	if (pers->sync_request && mddev->to_remove == NULL)
+		mddev->to_remove = &md_redundancy_group;
+	module_put(pers->owner);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 }
 
@@ -5226,8 +5433,11 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		bitmap_destroy(mddev);
 		if (mddev->bitmap_info.file) {
-			fput(mddev->bitmap_info.file);
+			struct file *f = mddev->bitmap_info.file;
+			spin_lock(&mddev->lock);
 			mddev->bitmap_info.file = NULL;
+			spin_unlock(&mddev->lock);
+			fput(f);
 		}
 		mddev->bitmap_info.offset = 0;
 
@@ -5436,37 +5646,31 @@ static int get_array_info(struct mddev *mddev, void __user *arg)
 static int get_bitmap_file(struct mddev *mddev, void __user * arg)
 {
 	mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */
-	char *ptr, *buf = NULL;
-	int err = -ENOMEM;
+	char *ptr;
+	int err;
 
 	file = kmalloc(sizeof(*file), GFP_NOIO);
-
 	if (!file)
-		goto out;
+		return -ENOMEM;
 
+	err = 0;
+	spin_lock(&mddev->lock);
 	/* bitmap disabled, zero the first byte and copy out */
-	if (!mddev->bitmap || !mddev->bitmap->storage.file) {
+	if (!mddev->bitmap_info.file)
 		file->pathname[0] = '\0';
-		goto copy_out;
-	}
-
-	buf = kmalloc(sizeof(file->pathname), GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	ptr = d_path(&mddev->bitmap->storage.file->f_path,
-		     buf, sizeof(file->pathname));
-	if (IS_ERR(ptr))
-		goto out;
-
-	strcpy(file->pathname, ptr);
+	else if ((ptr = d_path(&mddev->bitmap_info.file->f_path,
+			       file->pathname, sizeof(file->pathname))),
+		 IS_ERR(ptr))
+		err = PTR_ERR(ptr);
+	else
+		memmove(file->pathname, ptr,
+			sizeof(file->pathname)-(ptr-file->pathname));
+	spin_unlock(&mddev->lock);
 
-copy_out:
-	err = 0;
-	if (copy_to_user(arg, file, sizeof(*file)))
+	if (err == 0 &&
+	    copy_to_user(arg, file, sizeof(*file)))
 		err = -EFAULT;
-out:
-	kfree(buf);
+
 	kfree(file);
 	return err;
 }
@@ -5789,22 +5993,24 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 
 	if (fd >= 0) {
 		struct inode *inode;
-		if (mddev->bitmap)
+		struct file *f;
+
+		if (mddev->bitmap || mddev->bitmap_info.file)
 			return -EEXIST; /* cannot add when bitmap is present */
-		mddev->bitmap_info.file = fget(fd);
+		f = fget(fd);
 
-		if (mddev->bitmap_info.file == NULL) {
+		if (f == NULL) {
 			printk(KERN_ERR "%s: error: failed to get bitmap file\n",
 			       mdname(mddev));
 			return -EBADF;
 		}
 
-		inode = mddev->bitmap_info.file->f_mapping->host;
+		inode = f->f_mapping->host;
 		if (!S_ISREG(inode->i_mode)) {
 			printk(KERN_ERR "%s: error: bitmap file must be a regular file\n",
 			       mdname(mddev));
 			err = -EBADF;
-		} else if (!(mddev->bitmap_info.file->f_mode & FMODE_WRITE)) {
+		} else if (!(f->f_mode & FMODE_WRITE)) {
 			printk(KERN_ERR "%s: error: bitmap file must open for write\n",
 			       mdname(mddev));
 			err = -EBADF;
@@ -5814,10 +6020,10 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 			err = -EBUSY;
 		}
 		if (err) {
-			fput(mddev->bitmap_info.file);
-			mddev->bitmap_info.file = NULL;
+			fput(f);
 			return err;
 		}
+		mddev->bitmap_info.file = f;
 		mddev->bitmap_info.offset = 0; /* file overrides offset */
 	} else if (mddev->bitmap == NULL)
 		return -ENOENT; /* cannot remove what isn't there */
@@ -5836,9 +6042,13 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 		mddev->pers->quiesce(mddev, 0);
 	}
 	if (fd < 0) {
-		if (mddev->bitmap_info.file)
-			fput(mddev->bitmap_info.file);
-		mddev->bitmap_info.file = NULL;
+		struct file *f = mddev->bitmap_info.file;
+		if (f) {
+			spin_lock(&mddev->lock);
+			mddev->bitmap_info.file = NULL;
+			spin_unlock(&mddev->lock);
+			fput(f);
+		}
 	}
 
 	return err;
@@ -6251,6 +6461,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	case SET_DISK_FAULTY:
 		err = set_disk_faulty(mddev, new_decode_dev(arg));
 		goto out;
+
+	case GET_BITMAP_FILE:
+		err = get_bitmap_file(mddev, argp);
+		goto out;
+
 	}
 
 	if (cmd == ADD_NEW_DISK)
@@ -6342,10 +6557,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	 * Commands even a read-only array can execute:
 	 */
 	switch (cmd) {
-	case GET_BITMAP_FILE:
-		err = get_bitmap_file(mddev, argp);
-		goto unlock;
-
 	case RESTART_ARRAY_RW:
 		err = restart_array(mddev);
 		goto unlock;
@@ -6873,9 +7084,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		return 0;
 	}
 
-	if (mddev_lock(mddev) < 0)
-		return -EINTR;
-
+	spin_lock(&mddev->lock);
 	if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
 		seq_printf(seq, "%s : %sactive", mdname(mddev),
 						mddev->pers ? "" : "in");
@@ -6888,7 +7097,8 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		}
 
 		sectors = 0;
-		rdev_for_each(rdev, mddev) {
+		rcu_read_lock();
+		rdev_for_each_rcu(rdev, mddev) {
 			char b[BDEVNAME_SIZE];
 			seq_printf(seq, " %s[%d]",
 				bdevname(rdev->bdev,b), rdev->desc_nr);
@@ -6904,6 +7114,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 				seq_printf(seq, "(R)");
 			sectors += rdev->sectors;
 		}
+		rcu_read_unlock();
 
 		if (!list_empty(&mddev->disks)) {
 			if (mddev->pers)
@@ -6946,7 +7157,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 
 		seq_printf(seq, "\n");
 	}
-	mddev_unlock(mddev);
+	spin_unlock(&mddev->lock);
 
 	return 0;
 }
@@ -7102,7 +7313,7 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
 	if (mddev->safemode == 1)
 		mddev->safemode = 0;
 	if (mddev->in_sync) {
-		spin_lock_irq(&mddev->write_lock);
+		spin_lock(&mddev->lock);
 		if (mddev->in_sync) {
 			mddev->in_sync = 0;
 			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
@@ -7110,7 +7321,7 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
 			md_wakeup_thread(mddev->thread);
 			did_change = 1;
 		}
-		spin_unlock_irq(&mddev->write_lock);
+		spin_unlock(&mddev->lock);
 	}
 	if (did_change)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -7148,7 +7359,7 @@ int md_allow_write(struct mddev *mddev)
 	if (!mddev->pers->sync_request)
 		return 0;
 
-	spin_lock_irq(&mddev->write_lock);
+	spin_lock(&mddev->lock);
 	if (mddev->in_sync) {
 		mddev->in_sync = 0;
 		set_bit(MD_CHANGE_CLEAN, &mddev->flags);
@@ -7156,11 +7367,11 @@ int md_allow_write(struct mddev *mddev)
 		if (mddev->safemode_delay &&
 		    mddev->safemode == 0)
 			mddev->safemode = 1;
-		spin_unlock_irq(&mddev->write_lock);
+		spin_unlock(&mddev->lock);
 		md_update_sb(mddev, 0);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	} else
-		spin_unlock_irq(&mddev->write_lock);
+		spin_unlock(&mddev->lock);
 
 	if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
 		return -EAGAIN;
@@ -7513,6 +7724,7 @@ void md_do_sync(struct md_thread *thread)
  skip:
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
+	spin_lock(&mddev->lock);
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 		/* We completed so min/max setting can be forgotten if used. */
 		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
@@ -7521,6 +7733,8 @@ void md_do_sync(struct md_thread *thread)
 	} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 		mddev->resync_min = mddev->curr_resync_completed;
 	mddev->curr_resync = 0;
+	spin_unlock(&mddev->lock);
+
 	wake_up(&resync_wait);
 	set_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
@@ -7688,7 +7902,7 @@ void md_check_recovery(struct mddev *mddev)
 
 		if (!mddev->external) {
 			int did_change = 0;
-			spin_lock_irq(&mddev->write_lock);
+			spin_lock(&mddev->lock);
 			if (mddev->safemode &&
 			    !atomic_read(&mddev->writes_pending) &&
 			    !mddev->in_sync &&
@@ -7699,7 +7913,7 @@ void md_check_recovery(struct mddev *mddev)
 			}
 			if (mddev->safemode == 1)
 				mddev->safemode = 0;
-			spin_unlock_irq(&mddev->write_lock);
+			spin_unlock(&mddev->lock);
 			if (did_change)
 				sysfs_notify_dirent_safe(mddev->sysfs_state);
 		}
@@ -7721,7 +7935,9 @@ void md_check_recovery(struct mddev *mddev)
 		 * any transients in the value of "sync_action".
 		 */
 		mddev->curr_resync_completed = 0;
+		spin_lock(&mddev->lock);
 		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+		spin_unlock(&mddev->lock);
 		/* Clear some bits that don't mean anything, but
 		 * might be left set
 		 */
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 03cec5bdcaae75..318ca8fd430f1f 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -386,7 +386,18 @@ struct mddev {
 
 	struct work_struct del_work;	/* used for delayed sysfs removal */
 
-	spinlock_t			write_lock;
+	/* "lock" protects:
+	 *   flush_bio transition from NULL to !NULL
+	 *   rdev superblocks, events
+	 *   clearing MD_CHANGE_*
+	 *   in_sync - and related safemode and MD_CHANGE changes
+	 *   pers (also protected by reconfig_mutex and pending IO).
+	 *   clearing ->bitmap
+	 *   clearing ->bitmap_info.file
+	 *   changing ->resync_{min,max}
+	 *   setting MD_RECOVERY_RUNNING (which interacts with resync_{min,max})
+	 */
+	spinlock_t			lock;
 	wait_queue_head_t		sb_wait;	/* for waiting on superblock updates */
 	atomic_t			pending_writes;	/* number of active superblock writes */
 
@@ -439,13 +450,30 @@ struct mddev {
 	void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);
 };
 
-static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
+static inline int __must_check mddev_lock(struct mddev *mddev)
 {
-	int faulty = test_bit(Faulty, &rdev->flags);
-	if (atomic_dec_and_test(&rdev->nr_pending) && faulty)
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	return mutex_lock_interruptible(&mddev->reconfig_mutex);
+}
+
+/* Sometimes we need to take the lock in a situation where
+ * failure due to interrupts is not acceptable.
+ */
+static inline void mddev_lock_nointr(struct mddev *mddev)
+{
+	mutex_lock(&mddev->reconfig_mutex);
+}
+
+static inline int mddev_is_locked(struct mddev *mddev)
+{
+	return mutex_is_locked(&mddev->reconfig_mutex);
 }
 
+static inline int mddev_trylock(struct mddev *mddev)
+{
+	return mutex_trylock(&mddev->reconfig_mutex);
+}
+extern void mddev_unlock(struct mddev *mddev);
+
 static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
 {
 	atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
@@ -459,7 +487,7 @@ struct md_personality
 	struct module *owner;
 	void (*make_request)(struct mddev *mddev, struct bio *bio);
 	int (*run)(struct mddev *mddev);
-	int (*stop)(struct mddev *mddev);
+	void (*free)(struct mddev *mddev, void *priv);
 	void (*status)(struct seq_file *seq, struct mddev *mddev);
 	/* error_handler must set ->faulty and clear ->in_sync
 	 * if appropriate, and should abort recovery if needed
@@ -490,6 +518,13 @@ struct md_personality
 	 * array.
 	 */
 	void *(*takeover) (struct mddev *mddev);
+	/* congested implements bdi.congested_fn().
+	 * Will not be called while array is 'suspended' */
+	int (*congested)(struct mddev *mddev, int bits);
+	/* mergeable_bvec is use to implement ->merge_bvec_fn */
+	int (*mergeable_bvec)(struct mddev *mddev,
+			      struct bvec_merge_data *bvm,
+			      struct bio_vec *biovec);
 };
 
 struct md_sysfs_entry {
@@ -624,4 +659,14 @@ static inline int mddev_check_plugged(struct mddev *mddev)
 	return !!blk_check_plugged(md_unplug, mddev,
 				   sizeof(struct blk_plug_cb));
 }
+
+static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
+{
+	int faulty = test_bit(Faulty, &rdev->flags);
+	if (atomic_dec_and_test(&rdev->nr_pending) && faulty) {
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		md_wakeup_thread(mddev->thread);
+	}
+}
+
 #endif /* _MD_MD_H */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 399272f9c0425a..ac3ede2bd00e62 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -153,15 +153,11 @@ static void multipath_status (struct seq_file *seq, struct mddev *mddev)
 	seq_printf (seq, "]");
 }
 
-static int multipath_congested(void *data, int bits)
+static int multipath_congested(struct mddev *mddev, int bits)
 {
-	struct mddev *mddev = data;
 	struct mpconf *conf = mddev->private;
 	int i, ret = 0;
 
-	if (mddev_congested(mddev, bits))
-		return 1;
-
 	rcu_read_lock();
 	for (i = 0; i < mddev->raid_disks ; i++) {
 		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
@@ -403,7 +399,7 @@ static int multipath_run (struct mddev *mddev)
 	/*
 	 * copy the already verified devices into our private MULTIPATH
 	 * bookkeeping area. [whatever we allocate in multipath_run(),
-	 * should be freed in multipath_stop()]
+	 * should be freed in multipath_free()]
 	 */
 
 	conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
@@ -489,9 +485,6 @@ static int multipath_run (struct mddev *mddev)
 	 */
 	md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
 
-	mddev->queue->backing_dev_info.congested_fn = multipath_congested;
-	mddev->queue->backing_dev_info.congested_data = mddev;
-
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
 
@@ -507,17 +500,13 @@ static int multipath_run (struct mddev *mddev)
 	return -EIO;
 }
 
-static int multipath_stop (struct mddev *mddev)
+static void multipath_free(struct mddev *mddev, void *priv)
 {
-	struct mpconf *conf = mddev->private;
+	struct mpconf *conf = priv;
 
-	md_unregister_thread(&mddev->thread);
-	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	mempool_destroy(conf->pool);
 	kfree(conf->multipaths);
 	kfree(conf);
-	mddev->private = NULL;
-	return 0;
 }
 
 static struct md_personality multipath_personality =
@@ -527,12 +516,13 @@ static struct md_personality multipath_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= multipath_make_request,
 	.run		= multipath_run,
-	.stop		= multipath_stop,
+	.free		= multipath_free,
 	.status		= multipath_status,
 	.error_handler	= multipath_error,
 	.hot_add_disk	= multipath_add_disk,
 	.hot_remove_disk= multipath_remove_disk,
 	.size		= multipath_size,
+	.congested	= multipath_congested,
 };
 
 static int __init multipath_init (void)
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index ba6b85de96d209..a13f738a7b39f6 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -25,17 +25,13 @@
 #include "raid0.h"
 #include "raid5.h"
 
-static int raid0_congested(void *data, int bits)
+static int raid0_congested(struct mddev *mddev, int bits)
 {
-	struct mddev *mddev = data;
 	struct r0conf *conf = mddev->private;
 	struct md_rdev **devlist = conf->devlist;
 	int raid_disks = conf->strip_zone[0].nb_dev;
 	int i, ret = 0;
 
-	if (mddev_congested(mddev, bits))
-		return 1;
-
 	for (i = 0; i < raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
 
@@ -263,8 +259,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 			 mdname(mddev),
 			 (unsigned long long)smallest->sectors);
 	}
-	mddev->queue->backing_dev_info.congested_fn = raid0_congested;
-	mddev->queue->backing_dev_info.congested_data = mddev;
 
 	/*
 	 * now since we have the hard sector sizes, we can make sure
@@ -356,17 +350,16 @@ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
 
 /**
  *	raid0_mergeable_bvec -- tell bio layer if two requests can be merged
- *	@q: request queue
+ *	@mddev: the md device
  *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
  */
-static int raid0_mergeable_bvec(struct request_queue *q,
+static int raid0_mergeable_bvec(struct mddev *mddev,
 				struct bvec_merge_data *bvm,
 				struct bio_vec *biovec)
 {
-	struct mddev *mddev = q->queuedata;
 	struct r0conf *conf = mddev->private;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	sector_t sector_offset = sector;
@@ -422,7 +415,7 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	return array_sectors;
 }
 
-static int raid0_stop(struct mddev *mddev);
+static void raid0_free(struct mddev *mddev, void *priv);
 
 static int raid0_run(struct mddev *mddev)
 {
@@ -471,26 +464,22 @@ static int raid0_run(struct mddev *mddev)
 			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
 	}
 
-	blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
 	dump_zones(mddev);
 
 	ret = md_integrity_register(mddev);
 	if (ret)
-		raid0_stop(mddev);
+		raid0_free(mddev, conf);
 
 	return ret;
 }
 
-static int raid0_stop(struct mddev *mddev)
+static void raid0_free(struct mddev *mddev, void *priv)
 {
-	struct r0conf *conf = mddev->private;
+	struct r0conf *conf = priv;
 
-	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	kfree(conf->strip_zone);
 	kfree(conf->devlist);
 	kfree(conf);
-	mddev->private = NULL;
-	return 0;
 }
 
 /*
@@ -724,11 +713,13 @@ static struct md_personality raid0_personality=
 	.owner		= THIS_MODULE,
 	.make_request	= raid0_make_request,
 	.run		= raid0_run,
-	.stop		= raid0_stop,
+	.free		= raid0_free,
 	.status		= raid0_status,
 	.size		= raid0_size,
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
+	.congested	= raid0_congested,
+	.mergeable_bvec	= raid0_mergeable_bvec,
 };
 
 static int __init raid0_init (void)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 40b35be34f8d84..5dd0c2e59ab98c 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -701,11 +701,10 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
-static int raid1_mergeable_bvec(struct request_queue *q,
+static int raid1_mergeable_bvec(struct mddev *mddev,
 				struct bvec_merge_data *bvm,
 				struct bio_vec *biovec)
 {
-	struct mddev *mddev = q->queuedata;
 	struct r1conf *conf = mddev->private;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max = biovec->bv_len;
@@ -734,7 +733,7 @@ static int raid1_mergeable_bvec(struct request_queue *q,
 
 }
 
-int md_raid1_congested(struct mddev *mddev, int bits)
+static int raid1_congested(struct mddev *mddev, int bits)
 {
 	struct r1conf *conf = mddev->private;
 	int i, ret = 0;
@@ -763,15 +762,6 @@ int md_raid1_congested(struct mddev *mddev, int bits)
 	rcu_read_unlock();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(md_raid1_congested);
-
-static int raid1_congested(void *data, int bits)
-{
-	struct mddev *mddev = data;
-
-	return mddev_congested(mddev, bits) ||
-		md_raid1_congested(mddev, bits);
-}
 
 static void flush_pending_writes(struct r1conf *conf)
 {
@@ -2882,7 +2872,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
-static int stop(struct mddev *mddev);
+static void raid1_free(struct mddev *mddev, void *priv);
 static int run(struct mddev *mddev)
 {
 	struct r1conf *conf;
@@ -2904,7 +2894,7 @@ static int run(struct mddev *mddev)
 	/*
 	 * copy the already verified devices into our private RAID1
 	 * bookkeeping area. [whatever we allocate in run(),
-	 * should be freed in stop()]
+	 * should be freed in raid1_free()]
 	 */
 	if (mddev->private == NULL)
 		conf = setup_conf(mddev);
@@ -2955,10 +2945,6 @@ static int run(struct mddev *mddev)
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
 	if (mddev->queue) {
-		mddev->queue->backing_dev_info.congested_fn = raid1_congested;
-		mddev->queue->backing_dev_info.congested_data = mddev;
-		blk_queue_merge_bvec(mddev->queue, raid1_mergeable_bvec);
-
 		if (discard_supported)
 			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
 						mddev->queue);
@@ -2968,37 +2954,23 @@ static int run(struct mddev *mddev)
 	}
 
 	ret =  md_integrity_register(mddev);
-	if (ret)
-		stop(mddev);
+	if (ret) {
+		md_unregister_thread(&mddev->thread);
+		raid1_free(mddev, conf);
+	}
 	return ret;
 }
 
-static int stop(struct mddev *mddev)
+static void raid1_free(struct mddev *mddev, void *priv)
 {
-	struct r1conf *conf = mddev->private;
-	struct bitmap *bitmap = mddev->bitmap;
+	struct r1conf *conf = priv;
 
-	/* wait for behind writes to complete */
-	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
-		printk(KERN_INFO "md/raid1:%s: behind writes in progress - waiting to stop.\n",
-		       mdname(mddev));
-		/* need to kick something here to make sure I/O goes? */
-		wait_event(bitmap->behind_wait,
-			   atomic_read(&bitmap->behind_writes) == 0);
-	}
-
-	freeze_array(conf, 0);
-	unfreeze_array(conf);
-
-	md_unregister_thread(&mddev->thread);
 	if (conf->r1bio_pool)
 		mempool_destroy(conf->r1bio_pool);
 	kfree(conf->mirrors);
 	safe_put_page(conf->tmppage);
 	kfree(conf->poolinfo);
 	kfree(conf);
-	mddev->private = NULL;
-	return 0;
 }
 
 static int raid1_resize(struct mddev *mddev, sector_t sectors)
@@ -3181,7 +3153,7 @@ static struct md_personality raid1_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= raid1_free,
 	.status		= status,
 	.error_handler	= error,
 	.hot_add_disk	= raid1_add_disk,
@@ -3193,6 +3165,8 @@ static struct md_personality raid1_personality =
 	.check_reshape	= raid1_reshape,
 	.quiesce	= raid1_quiesce,
 	.takeover	= raid1_takeover,
+	.congested	= raid1_congested,
+	.mergeable_bvec	= raid1_mergeable_bvec,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 33bda55ef9f783..14ebb288c1ef94 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -170,7 +170,4 @@ struct r1bio {
  */
 #define	R1BIO_MadeGood 7
 #define	R1BIO_WriteError 8
-
-extern int md_raid1_congested(struct mddev *mddev, int bits);
-
 #endif
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 32e282f4c83c3a..b8d76b1fba6457 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -674,7 +674,7 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
 
 /**
  *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
- *	@q: request queue
+ *	@mddev: the md device
  *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
@@ -682,11 +682,10 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
  *	This requires checking for end-of-chunk if near_copies != raid_disks,
  *	and for subordinate merge_bvec_fns if merge_check_needed.
  */
-static int raid10_mergeable_bvec(struct request_queue *q,
+static int raid10_mergeable_bvec(struct mddev *mddev,
 				 struct bvec_merge_data *bvm,
 				 struct bio_vec *biovec)
 {
-	struct mddev *mddev = q->queuedata;
 	struct r10conf *conf = mddev->private;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
@@ -910,7 +909,7 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	return rdev;
 }
 
-int md_raid10_congested(struct mddev *mddev, int bits)
+static int raid10_congested(struct mddev *mddev, int bits)
 {
 	struct r10conf *conf = mddev->private;
 	int i, ret = 0;
@@ -934,15 +933,6 @@ int md_raid10_congested(struct mddev *mddev, int bits)
 	rcu_read_unlock();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(md_raid10_congested);
-
-static int raid10_congested(void *data, int bits)
-{
-	struct mddev *mddev = data;
-
-	return mddev_congested(mddev, bits) ||
-		md_raid10_congested(mddev, bits);
-}
 
 static void flush_pending_writes(struct r10conf *conf)
 {
@@ -3757,8 +3747,6 @@ static int run(struct mddev *mddev)
 	if (mddev->queue) {
 		int stripe = conf->geo.raid_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		mddev->queue->backing_dev_info.congested_fn = raid10_congested;
-		mddev->queue->backing_dev_info.congested_data = mddev;
 
 		/* Calculate max read-ahead size.
 		 * We need to readahead at least twice a whole stripe....
@@ -3767,7 +3755,6 @@ static int run(struct mddev *mddev)
 		stripe /= conf->geo.near_copies;
 		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
-		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
 	}
 
 	if (md_integrity_register(mddev))
@@ -3811,17 +3798,9 @@ static int run(struct mddev *mddev)
 	return -EIO;
 }
 
-static int stop(struct mddev *mddev)
+static void raid10_free(struct mddev *mddev, void *priv)
 {
-	struct r10conf *conf = mddev->private;
-
-	raise_barrier(conf, 0);
-	lower_barrier(conf);
-
-	md_unregister_thread(&mddev->thread);
-	if (mddev->queue)
-		/* the unplug fn references 'conf'*/
-		blk_sync_queue(mddev->queue);
+	struct r10conf *conf = priv;
 
 	if (conf->r10bio_pool)
 		mempool_destroy(conf->r10bio_pool);
@@ -3830,8 +3809,6 @@ static int stop(struct mddev *mddev)
 	kfree(conf->mirrors_old);
 	kfree(conf->mirrors_new);
 	kfree(conf);
-	mddev->private = NULL;
-	return 0;
 }
 
 static void raid10_quiesce(struct mddev *mddev, int state)
@@ -3895,7 +3872,7 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 	return 0;
 }
 
-static void *raid10_takeover_raid0(struct mddev *mddev)
+static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs)
 {
 	struct md_rdev *rdev;
 	struct r10conf *conf;
@@ -3905,6 +3882,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev)
 		       mdname(mddev));
 		return ERR_PTR(-EINVAL);
 	}
+	sector_div(size, devs);
 
 	/* Set new parameters */
 	mddev->new_level = 10;
@@ -3915,12 +3893,15 @@ static void *raid10_takeover_raid0(struct mddev *mddev)
 	mddev->raid_disks *= 2;
 	/* make sure it will be not marked as dirty */
 	mddev->recovery_cp = MaxSector;
+	mddev->dev_sectors = size;
 
 	conf = setup_conf(mddev);
 	if (!IS_ERR(conf)) {
 		rdev_for_each(rdev, mddev)
-			if (rdev->raid_disk >= 0)
+			if (rdev->raid_disk >= 0) {
 				rdev->new_raid_disk = rdev->raid_disk * 2;
+				rdev->sectors = size;
+			}
 		conf->barrier = 1;
 	}
 
@@ -3943,7 +3924,9 @@ static void *raid10_takeover(struct mddev *mddev)
 			       mdname(mddev));
 			return ERR_PTR(-EINVAL);
 		}
-		return raid10_takeover_raid0(mddev);
+		return raid10_takeover_raid0(mddev,
+			raid0_conf->strip_zone->zone_end,
+			raid0_conf->strip_zone->nb_dev);
 	}
 	return ERR_PTR(-EINVAL);
 }
@@ -4713,7 +4696,7 @@ static struct md_personality raid10_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= raid10_free,
 	.status		= status,
 	.error_handler	= error,
 	.hot_add_disk	= raid10_add_disk,
@@ -4727,6 +4710,8 @@ static struct md_personality raid10_personality =
 	.check_reshape	= raid10_check_reshape,
 	.start_reshape	= raid10_start_reshape,
 	.finish_reshape	= raid10_finish_reshape,
+	.congested	= raid10_congested,
+	.mergeable_bvec	= raid10_mergeable_bvec,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 157d69e83ff401..5ee6473ddc2c01 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -150,7 +150,4 @@ enum r10bio_state {
  */
 	R10BIO_Previous,
 };
-
-extern int md_raid10_congested(struct mddev *mddev, int bits);
-
 #endif
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b98765f6f77fd9..aa76865b804b41 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -296,12 +296,9 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 	BUG_ON(atomic_read(&conf->active_stripes)==0);
 	if (test_bit(STRIPE_HANDLE, &sh->state)) {
 		if (test_bit(STRIPE_DELAYED, &sh->state) &&
-		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 			list_add_tail(&sh->lru, &conf->delayed_list);
-			if (atomic_read(&conf->preread_active_stripes)
-			    < IO_THRESHOLD)
-				md_wakeup_thread(conf->mddev->thread);
-		} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+		else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
 			   sh->bm_seq - conf->seq_write > 0)
 			list_add_tail(&sh->lru, &conf->bitmap_list);
 		else {
@@ -2898,31 +2895,102 @@ static int want_replace(struct stripe_head *sh, int disk_idx)
  * Returns 1 when no more member devices need to be checked, otherwise returns
  * 0 to tell the loop in handle_stripe_fill to continue
  */
-static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
-		       int disk_idx, int disks)
+
+static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
+			   int disk_idx, int disks)
 {
 	struct r5dev *dev = &sh->dev[disk_idx];
 	struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]],
 				  &sh->dev[s->failed_num[1]] };
+	int i;
+
+
+	if (test_bit(R5_LOCKED, &dev->flags) ||
+	    test_bit(R5_UPTODATE, &dev->flags))
+		/* No point reading this as we already have it or have
+		 * decided to get it.
+		 */
+		return 0;
+
+	if (dev->toread ||
+	    (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)))
+		/* We need this block to directly satisfy a request */
+		return 1;
+
+	if (s->syncing || s->expanding ||
+	    (s->replacing && want_replace(sh, disk_idx)))
+		/* When syncing, or expanding we read everything.
+		 * When replacing, we need the replaced block.
+		 */
+		return 1;
+
+	if ((s->failed >= 1 && fdev[0]->toread) ||
+	    (s->failed >= 2 && fdev[1]->toread))
+		/* If we want to read from a failed device, then
+		 * we need to actually read every other device.
+		 */
+		return 1;
+
+	/* Sometimes neither read-modify-write nor reconstruct-write
+	 * cycles can work.  In those cases we read every block we
+	 * can.  Then the parity-update is certain to have enough to
+	 * work with.
+	 * This can only be a problem when we need to write something,
+	 * and some device has failed.  If either of those tests
+	 * fail we need look no further.
+	 */
+	if (!s->failed || !s->to_write)
+		return 0;
+
+	if (test_bit(R5_Insync, &dev->flags) &&
+	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+		/* Pre-reads at not permitted until after short delay
+		 * to gather multiple requests.  However if this
+		 * device is no Insync, the block could only be be computed
+		 * and there is no need to delay that.
+		 */
+		return 0;
+
+	for (i = 0; i < s->failed; i++) {
+		if (fdev[i]->towrite &&
+		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
+		    !test_bit(R5_OVERWRITE, &fdev[i]->flags))
+			/* If we have a partial write to a failed
+			 * device, then we will need to reconstruct
+			 * the content of that device, so all other
+			 * devices must be read.
+			 */
+			return 1;
+	}
+
+	/* If we are forced to do a reconstruct-write, either because
+	 * the current RAID6 implementation only supports that, or
+	 * or because parity cannot be trusted and we are currently
+	 * recovering it, there is extra need to be careful.
+	 * If one of the devices that we would need to read, because
+	 * it is not being overwritten (and maybe not written at all)
+	 * is missing/faulty, then we need to read everything we can.
+	 */
+	if (sh->raid_conf->level != 6 &&
+	    sh->sector < sh->raid_conf->mddev->recovery_cp)
+		/* reconstruct-write isn't being forced */
+		return 0;
+	for (i = 0; i < s->failed; i++) {
+		if (!test_bit(R5_UPTODATE, &fdev[i]->flags) &&
+		    !test_bit(R5_OVERWRITE, &fdev[i]->flags))
+			return 1;
+	}
+
+	return 0;
+}
+
+static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
+		       int disk_idx, int disks)
+{
+	struct r5dev *dev = &sh->dev[disk_idx];
 
 	/* is the data in this block needed, and can we get it? */
-	if (!test_bit(R5_LOCKED, &dev->flags) &&
-	    !test_bit(R5_UPTODATE, &dev->flags) &&
-	    (dev->toread ||
-	     (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
-	     s->syncing || s->expanding ||
-	     (s->replacing && want_replace(sh, disk_idx)) ||
-	     (s->failed >= 1 && fdev[0]->toread) ||
-	     (s->failed >= 2 && fdev[1]->toread) ||
-	     (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
-	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) &&
-	      !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
-	     ((sh->raid_conf->level == 6 ||
-	       sh->sector >= sh->raid_conf->mddev->recovery_cp)
-	      && s->failed && s->to_write &&
-	      (s->to_write - s->non_overwrite <
-	       sh->raid_conf->raid_disks - sh->raid_conf->max_degraded) &&
-	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) {
+	if (need_this_block(sh, s, disk_idx, disks)) {
 		/* we would like to get this block, possibly by computing it,
 		 * otherwise read it if the backing disk is insync
 		 */
@@ -4081,7 +4149,7 @@ static void activate_bit_delay(struct r5conf *conf,
 	}
 }
 
-int md_raid5_congested(struct mddev *mddev, int bits)
+static int raid5_congested(struct mddev *mddev, int bits)
 {
 	struct r5conf *conf = mddev->private;
 
@@ -4098,24 +4166,14 @@ int md_raid5_congested(struct mddev *mddev, int bits)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(md_raid5_congested);
-
-static int raid5_congested(void *data, int bits)
-{
-	struct mddev *mddev = data;
-
-	return mddev_congested(mddev, bits) ||
-		md_raid5_congested(mddev, bits);
-}
 
 /* We want read requests to align with chunks where possible,
  * but write requests don't need to.
  */
-static int raid5_mergeable_bvec(struct request_queue *q,
+static int raid5_mergeable_bvec(struct mddev *mddev,
 				struct bvec_merge_data *bvm,
 				struct bio_vec *biovec)
 {
-	struct mddev *mddev = q->queuedata;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_sectors;
@@ -5296,11 +5354,14 @@ static void raid5d(struct md_thread *thread)
 static ssize_t
 raid5_show_stripe_cache_size(struct mddev *mddev, char *page)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
+	int ret = 0;
+	spin_lock(&mddev->lock);
+	conf = mddev->private;
 	if (conf)
-		return sprintf(page, "%d\n", conf->max_nr_stripes);
-	else
-		return 0;
+		ret = sprintf(page, "%d\n", conf->max_nr_stripes);
+	spin_unlock(&mddev->lock);
+	return ret;
 }
 
 int
@@ -5339,21 +5400,25 @@ EXPORT_SYMBOL(raid5_set_cache_size);
 static ssize_t
 raid5_store_stripe_cache_size(struct mddev *mddev, const char *page, size_t len)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
 	unsigned long new;
 	int err;
 
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
-	if (!conf)
-		return -ENODEV;
-
 	if (kstrtoul(page, 10, &new))
 		return -EINVAL;
-	err = raid5_set_cache_size(mddev, new);
+	err = mddev_lock(mddev);
 	if (err)
 		return err;
-	return len;
+	conf = mddev->private;
+	if (!conf)
+		err = -ENODEV;
+	else
+		err = raid5_set_cache_size(mddev, new);
+	mddev_unlock(mddev);
+
+	return err ?: len;
 }
 
 static struct md_sysfs_entry
@@ -5364,29 +5429,40 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR,
 static ssize_t
 raid5_show_preread_threshold(struct mddev *mddev, char *page)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
+	int ret = 0;
+	spin_lock(&mddev->lock);
+	conf = mddev->private;
 	if (conf)
-		return sprintf(page, "%d\n", conf->bypass_threshold);
-	else
-		return 0;
+		ret = sprintf(page, "%d\n", conf->bypass_threshold);
+	spin_unlock(&mddev->lock);
+	return ret;
 }
 
 static ssize_t
 raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
 	unsigned long new;
+	int err;
+
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
-	if (!conf)
-		return -ENODEV;
-
 	if (kstrtoul(page, 10, &new))
 		return -EINVAL;
-	if (new > conf->max_nr_stripes)
-		return -EINVAL;
-	conf->bypass_threshold = new;
-	return len;
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	conf = mddev->private;
+	if (!conf)
+		err = -ENODEV;
+	else if (new > conf->max_nr_stripes)
+		err = -EINVAL;
+	else
+		conf->bypass_threshold = new;
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry
@@ -5398,39 +5474,48 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
 static ssize_t
 raid5_show_skip_copy(struct mddev *mddev, char *page)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
+	int ret = 0;
+	spin_lock(&mddev->lock);
+	conf = mddev->private;
 	if (conf)
-		return sprintf(page, "%d\n", conf->skip_copy);
-	else
-		return 0;
+		ret = sprintf(page, "%d\n", conf->skip_copy);
+	spin_unlock(&mddev->lock);
+	return ret;
 }
 
 static ssize_t
 raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
 	unsigned long new;
+	int err;
+
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
-	if (!conf)
-		return -ENODEV;
-
 	if (kstrtoul(page, 10, &new))
 		return -EINVAL;
 	new = !!new;
-	if (new == conf->skip_copy)
-		return len;
 
-	mddev_suspend(mddev);
-	conf->skip_copy = new;
-	if (new)
-		mddev->queue->backing_dev_info.capabilities |=
-						BDI_CAP_STABLE_WRITES;
-	else
-		mddev->queue->backing_dev_info.capabilities &=
-						~BDI_CAP_STABLE_WRITES;
-	mddev_resume(mddev);
-	return len;
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	conf = mddev->private;
+	if (!conf)
+		err = -ENODEV;
+	else if (new != conf->skip_copy) {
+		mddev_suspend(mddev);
+		conf->skip_copy = new;
+		if (new)
+			mddev->queue->backing_dev_info.capabilities |=
+				BDI_CAP_STABLE_WRITES;
+		else
+			mddev->queue->backing_dev_info.capabilities &=
+				~BDI_CAP_STABLE_WRITES;
+		mddev_resume(mddev);
+	}
+	mddev_unlock(mddev);
+	return err ?: len;
 }
 
 static struct md_sysfs_entry
@@ -5454,11 +5539,14 @@ raid5_stripecache_active = __ATTR_RO(stripe_cache_active);
 static ssize_t
 raid5_show_group_thread_cnt(struct mddev *mddev, char *page)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
+	int ret = 0;
+	spin_lock(&mddev->lock);
+	conf = mddev->private;
 	if (conf)
-		return sprintf(page, "%d\n", conf->worker_cnt_per_group);
-	else
-		return 0;
+		ret = sprintf(page, "%d\n", conf->worker_cnt_per_group);
+	spin_unlock(&mddev->lock);
+	return ret;
 }
 
 static int alloc_thread_groups(struct r5conf *conf, int cnt,
@@ -5468,7 +5556,7 @@ static int alloc_thread_groups(struct r5conf *conf, int cnt,
 static ssize_t
 raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf;
 	unsigned long new;
 	int err;
 	struct r5worker_group *new_groups, *old_groups;
@@ -5476,41 +5564,41 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
 
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
-	if (!conf)
-		return -ENODEV;
-
 	if (kstrtoul(page, 10, &new))
 		return -EINVAL;
 
-	if (new == conf->worker_cnt_per_group)
-		return len;
-
-	mddev_suspend(mddev);
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	conf = mddev->private;
+	if (!conf)
+		err = -ENODEV;
+	else if (new != conf->worker_cnt_per_group) {
+		mddev_suspend(mddev);
 
-	old_groups = conf->worker_groups;
-	if (old_groups)
-		flush_workqueue(raid5_wq);
+		old_groups = conf->worker_groups;
+		if (old_groups)
+			flush_workqueue(raid5_wq);
 
-	err = alloc_thread_groups(conf, new,
-				  &group_cnt, &worker_cnt_per_group,
-				  &new_groups);
-	if (!err) {
-		spin_lock_irq(&conf->device_lock);
-		conf->group_cnt = group_cnt;
-		conf->worker_cnt_per_group = worker_cnt_per_group;
-		conf->worker_groups = new_groups;
-		spin_unlock_irq(&conf->device_lock);
+		err = alloc_thread_groups(conf, new,
+					  &group_cnt, &worker_cnt_per_group,
+					  &new_groups);
+		if (!err) {
+			spin_lock_irq(&conf->device_lock);
+			conf->group_cnt = group_cnt;
+			conf->worker_cnt_per_group = worker_cnt_per_group;
+			conf->worker_groups = new_groups;
+			spin_unlock_irq(&conf->device_lock);
 
-		if (old_groups)
-			kfree(old_groups[0].workers);
-		kfree(old_groups);
+			if (old_groups)
+				kfree(old_groups[0].workers);
+			kfree(old_groups);
+		}
+		mddev_resume(mddev);
 	}
+	mddev_unlock(mddev);
 
-	mddev_resume(mddev);
-
-	if (err)
-		return err;
-	return len;
+	return err ?: len;
 }
 
 static struct md_sysfs_entry
@@ -6178,11 +6266,6 @@ static int run(struct mddev *mddev)
 		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
 
-		blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
-
-		mddev->queue->backing_dev_info.congested_data = mddev;
-		mddev->queue->backing_dev_info.congested_fn = raid5_congested;
-
 		chunk_size = mddev->chunk_sectors << 9;
 		blk_queue_io_min(mddev->queue, chunk_size);
 		blk_queue_io_opt(mddev->queue, chunk_size *
@@ -6260,17 +6343,12 @@ static int run(struct mddev *mddev)
 	return -EIO;
 }
 
-static int stop(struct mddev *mddev)
+static void raid5_free(struct mddev *mddev, void *priv)
 {
-	struct r5conf *conf = mddev->private;
+	struct r5conf *conf = priv;
 
-	md_unregister_thread(&mddev->thread);
-	if (mddev->queue)
-		mddev->queue->backing_dev_info.congested_fn = NULL;
 	free_conf(conf);
-	mddev->private = NULL;
 	mddev->to_remove = &raid5_attrs_group;
-	return 0;
 }
 
 static void status(struct seq_file *seq, struct mddev *mddev)
@@ -7044,7 +7122,7 @@ static struct md_personality raid6_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= raid5_free,
 	.status		= status,
 	.error_handler	= error,
 	.hot_add_disk	= raid5_add_disk,
@@ -7058,6 +7136,8 @@ static struct md_personality raid6_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
+	.congested	= raid5_congested,
+	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 static struct md_personality raid5_personality =
 {
@@ -7066,7 +7146,7 @@ static struct md_personality raid5_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= raid5_free,
 	.status		= status,
 	.error_handler	= error,
 	.hot_add_disk	= raid5_add_disk,
@@ -7080,6 +7160,8 @@ static struct md_personality raid5_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
+	.congested	= raid5_congested,
+	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 
 static struct md_personality raid4_personality =
@@ -7089,7 +7171,7 @@ static struct md_personality raid4_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= raid5_free,
 	.status		= status,
 	.error_handler	= error,
 	.hot_add_disk	= raid5_add_disk,
@@ -7103,6 +7185,8 @@ static struct md_personality raid4_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
+	.congested	= raid5_congested,
+	.mergeable_bvec	= raid5_mergeable_bvec,
 };
 
 static int __init raid5_init(void)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index d59f5ca743cdc0..983e18a83db138 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -558,7 +558,6 @@ static inline int algorithm_is_DDF(int layout)
 	return layout >= 8 && layout <= 10;
 }
 
-extern int md_raid5_congested(struct mddev *mddev, int bits);
 extern void md_raid5_kick_device(struct r5conf *conf);
 extern int raid5_set_cache_size(struct mddev *mddev, int size);
 #endif
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 53563955931b4e..55fa27ecf4e152 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -49,7 +49,6 @@ static DEFINE_MUTEX(mtd_mutex);
  */
 struct mtd_file_info {
 	struct mtd_info *mtd;
-	struct inode *ino;
 	enum mtd_file_modes mode;
 };
 
@@ -59,10 +58,6 @@ static loff_t mtdchar_lseek(struct file *file, loff_t offset, int orig)
 	return fixed_size_llseek(file, offset, orig, mfi->mtd->size);
 }
 
-static int count;
-static struct vfsmount *mnt;
-static struct file_system_type mtd_inodefs_type;
-
 static int mtdchar_open(struct inode *inode, struct file *file)
 {
 	int minor = iminor(inode);
@@ -70,7 +65,6 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 	int ret = 0;
 	struct mtd_info *mtd;
 	struct mtd_file_info *mfi;
-	struct inode *mtd_ino;
 
 	pr_debug("MTD_open\n");
 
@@ -78,10 +72,6 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 	if ((file->f_mode & FMODE_WRITE) && (minor & 1))
 		return -EACCES;
 
-	ret = simple_pin_fs(&mtd_inodefs_type, &mnt, &count);
-	if (ret)
-		return ret;
-
 	mutex_lock(&mtd_mutex);
 	mtd = get_mtd_device(NULL, devnum);
 
@@ -95,43 +85,26 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 		goto out1;
 	}
 
-	mtd_ino = iget_locked(mnt->mnt_sb, devnum);
-	if (!mtd_ino) {
-		ret = -ENOMEM;
-		goto out1;
-	}
-	if (mtd_ino->i_state & I_NEW) {
-		mtd_ino->i_private = mtd;
-		mtd_ino->i_mode = S_IFCHR;
-		mtd_ino->i_data.backing_dev_info = mtd->backing_dev_info;
-		unlock_new_inode(mtd_ino);
-	}
-	file->f_mapping = mtd_ino->i_mapping;
-
 	/* You can't open it RW if it's not a writeable device */
 	if ((file->f_mode & FMODE_WRITE) && !(mtd->flags & MTD_WRITEABLE)) {
 		ret = -EACCES;
-		goto out2;
+		goto out1;
 	}
 
 	mfi = kzalloc(sizeof(*mfi), GFP_KERNEL);
 	if (!mfi) {
 		ret = -ENOMEM;
-		goto out2;
+		goto out1;
 	}
-	mfi->ino = mtd_ino;
 	mfi->mtd = mtd;
 	file->private_data = mfi;
 	mutex_unlock(&mtd_mutex);
 	return 0;
 
-out2:
-	iput(mtd_ino);
 out1:
 	put_mtd_device(mtd);
 out:
 	mutex_unlock(&mtd_mutex);
-	simple_release_fs(&mnt, &count);
 	return ret;
 } /* mtdchar_open */
 
@@ -148,12 +121,9 @@ static int mtdchar_close(struct inode *inode, struct file *file)
 	if ((file->f_mode & FMODE_WRITE))
 		mtd_sync(mtd);
 
-	iput(mfi->ino);
-
 	put_mtd_device(mtd);
 	file->private_data = NULL;
 	kfree(mfi);
-	simple_release_fs(&mnt, &count);
 
 	return 0;
 } /* mtdchar_close */
@@ -1117,6 +1087,13 @@ static unsigned long mtdchar_get_unmapped_area(struct file *file,
 	ret = mtd_get_unmapped_area(mtd, len, offset, flags);
 	return ret == -EOPNOTSUPP ? -ENODEV : ret;
 }
+
+static unsigned mtdchar_mmap_capabilities(struct file *file)
+{
+	struct mtd_file_info *mfi = file->private_data;
+
+	return mtd_mmap_capabilities(mfi->mtd);
+}
 #endif
 
 /*
@@ -1160,27 +1137,10 @@ static const struct file_operations mtd_fops = {
 	.mmap		= mtdchar_mmap,
 #ifndef CONFIG_MMU
 	.get_unmapped_area = mtdchar_get_unmapped_area,
+	.mmap_capabilities = mtdchar_mmap_capabilities,
 #endif
 };
 
-static const struct super_operations mtd_ops = {
-	.drop_inode = generic_delete_inode,
-	.statfs = simple_statfs,
-};
-
-static struct dentry *mtd_inodefs_mount(struct file_system_type *fs_type,
-				int flags, const char *dev_name, void *data)
-{
-	return mount_pseudo(fs_type, "mtd_inode:", &mtd_ops, NULL, MTD_INODE_FS_MAGIC);
-}
-
-static struct file_system_type mtd_inodefs_type = {
-       .name = "mtd_inodefs",
-       .mount = mtd_inodefs_mount,
-       .kill_sb = kill_anon_super,
-};
-MODULE_ALIAS_FS("mtd_inodefs");
-
 int __init init_mtdchar(void)
 {
 	int ret;
@@ -1193,23 +1153,11 @@ int __init init_mtdchar(void)
 		return ret;
 	}
 
-	ret = register_filesystem(&mtd_inodefs_type);
-	if (ret) {
-		pr_err("Can't register mtd_inodefs filesystem, error %d\n",
-		       ret);
-		goto err_unregister_chdev;
-	}
-
-	return ret;
-
-err_unregister_chdev:
-	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 	return ret;
 }
 
 void __exit cleanup_mtdchar(void)
 {
-	unregister_filesystem(&mtd_inodefs_type);
 	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 }
 
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index b9000563b9f431..eacc3aac732789 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -732,8 +732,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 
 	concat->mtd.ecc_stats.badblocks = subdev[0]->ecc_stats.badblocks;
 
-	concat->mtd.backing_dev_info = subdev[0]->backing_dev_info;
-
 	concat->subdev[0] = subdev[0];
 
 	for (i = 1; i < num_devs; i++) {
@@ -761,14 +759,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 				    subdev[i]->flags & MTD_WRITEABLE;
 		}
 
-		/* only permit direct mapping if the BDIs are all the same
-		 * - copy-mapping is still permitted
-		 */
-		if (concat->mtd.backing_dev_info !=
-		    subdev[i]->backing_dev_info)
-			concat->mtd.backing_dev_info =
-				&default_backing_dev_info;
-
 		concat->mtd.size += subdev[i]->size;
 		concat->mtd.ecc_stats.badblocks +=
 			subdev[i]->ecc_stats.badblocks;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 4c611871d7e6b4..0ec4d6ea1e4b8d 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -43,33 +43,7 @@
 
 #include "mtdcore.h"
 
-/*
- * backing device capabilities for non-mappable devices (such as NAND flash)
- * - permits private mappings, copies are taken of the data
- */
-static struct backing_dev_info mtd_bdi_unmappable = {
-	.capabilities	= BDI_CAP_MAP_COPY,
-};
-
-/*
- * backing device capabilities for R/O mappable devices (such as ROM)
- * - permits private mappings, copies are taken of the data
- * - permits non-writable shared mappings
- */
-static struct backing_dev_info mtd_bdi_ro_mappable = {
-	.capabilities	= (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT |
-			   BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP),
-};
-
-/*
- * backing device capabilities for writable mappable devices (such as RAM)
- * - permits private mappings, copies are taken of the data
- * - permits non-writable shared mappings
- */
-static struct backing_dev_info mtd_bdi_rw_mappable = {
-	.capabilities	= (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT |
-			   BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP |
-			   BDI_CAP_WRITE_MAP),
+static struct backing_dev_info mtd_bdi = {
 };
 
 static int mtd_cls_suspend(struct device *dev, pm_message_t state);
@@ -365,6 +339,23 @@ static struct device_type mtd_devtype = {
 	.release	= mtd_release,
 };
 
+#ifndef CONFIG_MMU
+unsigned mtd_mmap_capabilities(struct mtd_info *mtd)
+{
+	switch (mtd->type) {
+	case MTD_RAM:
+		return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
+			NOMMU_MAP_READ | NOMMU_MAP_WRITE;
+	case MTD_ROM:
+		return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
+			NOMMU_MAP_READ;
+	default:
+		return NOMMU_MAP_COPY;
+	}
+}
+EXPORT_SYMBOL_GPL(mtd_mmap_capabilities);
+#endif
+
 /**
  *	add_mtd_device - register an MTD device
  *	@mtd: pointer to new MTD device info structure
@@ -380,19 +371,7 @@ int add_mtd_device(struct mtd_info *mtd)
 	struct mtd_notifier *not;
 	int i, error;
 
-	if (!mtd->backing_dev_info) {
-		switch (mtd->type) {
-		case MTD_RAM:
-			mtd->backing_dev_info = &mtd_bdi_rw_mappable;
-			break;
-		case MTD_ROM:
-			mtd->backing_dev_info = &mtd_bdi_ro_mappable;
-			break;
-		default:
-			mtd->backing_dev_info = &mtd_bdi_unmappable;
-			break;
-		}
-	}
+	mtd->backing_dev_info = &mtd_bdi;
 
 	BUG_ON(mtd->writesize == 0);
 	mutex_lock(&mtd_table_mutex);
@@ -1237,17 +1216,9 @@ static int __init init_mtd(void)
 	if (ret)
 		goto err_reg;
 
-	ret = mtd_bdi_init(&mtd_bdi_unmappable, "mtd-unmap");
-	if (ret)
-		goto err_bdi1;
-
-	ret = mtd_bdi_init(&mtd_bdi_ro_mappable, "mtd-romap");
-	if (ret)
-		goto err_bdi2;
-
-	ret = mtd_bdi_init(&mtd_bdi_rw_mappable, "mtd-rwmap");
+	ret = mtd_bdi_init(&mtd_bdi, "mtd");
 	if (ret)
-		goto err_bdi3;
+		goto err_bdi;
 
 	proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops);
 
@@ -1260,11 +1231,7 @@ static int __init init_mtd(void)
 out_procfs:
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
-err_bdi3:
-	bdi_destroy(&mtd_bdi_ro_mappable);
-err_bdi2:
-	bdi_destroy(&mtd_bdi_unmappable);
-err_bdi1:
+err_bdi:
 	class_unregister(&mtd_class);
 err_reg:
 	pr_err("Error registering mtd class or bdi: %d\n", ret);
@@ -1277,9 +1244,7 @@ static void __exit cleanup_mtd(void)
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
 	class_unregister(&mtd_class);
-	bdi_destroy(&mtd_bdi_unmappable);
-	bdi_destroy(&mtd_bdi_ro_mappable);
-	bdi_destroy(&mtd_bdi_rw_mappable);
+	bdi_destroy(&mtd_bdi);
 }
 
 module_init(init_mtd);
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index a3e3a7d074d5c7..e779de315ade50 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -378,7 +378,6 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 
 	slave->mtd.name = name;
 	slave->mtd.owner = master->owner;
-	slave->mtd.backing_dev_info = master->backing_dev_info;
 
 	/* NOTE:  we don't arrange MTDs as a tree; it'd be error-prone
 	 * to have the same data be in two different partitions.
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 7f900229404dfd..96128cb009f352 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -28,8 +28,8 @@
 static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
-static int dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-				 void **kaddr, unsigned long *pfn);
+static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
+				 void **kaddr, unsigned long *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -877,25 +877,22 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 	bio_io_error(bio);
 }
 
-static int
+static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void **kaddr, unsigned long *pfn)
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct dcssblk_dev_info *dev_info;
-	unsigned long pgoff;
+	unsigned long offset, dev_sz;
 
 	dev_info = bdev->bd_disk->private_data;
 	if (!dev_info)
 		return -ENODEV;
-	if (secnum % (PAGE_SIZE/512))
-		return -EINVAL;
-	pgoff = secnum / (PAGE_SIZE / 512);
-	if ((pgoff+1)*PAGE_SIZE-1 > dev_info->end - dev_info->start)
-		return -ERANGE;
-	*kaddr = (void *) (dev_info->start+pgoff*PAGE_SIZE);
+	dev_sz = dev_info->end - dev_info->start;
+	offset = secnum * 512;
+	*kaddr = (void *) (dev_info->start + offset);
 	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
-	return 0;
+	return dev_sz - offset;
 }
 
 static void
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 17bb541f7cc259..54d7a6cbb98a48 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2197,6 +2197,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 	shost->tag_set.cmd_size = cmd_size;
 	shost->tag_set.numa_node = NUMA_NO_NODE;
 	shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	shost->tag_set.flags |=
+		BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
 	shost->tag_set.driver_data = shost;
 
 	return blk_mq_alloc_tag_set(&shost->tag_set);
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 0deb385ad4d66e..9c0a520d933c91 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -277,7 +277,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	if (!shost_use_blk_mq(sdev->host) &&
 	    (shost->bqt || shost->hostt->use_blk_tags)) {
 		blk_queue_init_tags(sdev->request_queue,
-				    sdev->host->cmd_per_lun, shost->bqt);
+				    sdev->host->cmd_per_lun, shost->bqt,
+				    shost->hostt->tag_alloc_policy);
 	}
 	scsi_change_queue_depth(sdev, sdev->host->cmd_per_lun);
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index a668c88ea150f7..0cbc1fb45f10eb 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1719,22 +1719,19 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 	}
 
 	if (iov_count) {
-		int len, size = sizeof(struct sg_iovec) * iov_count;
+		int size = sizeof(struct iovec) * iov_count;
 		struct iovec *iov;
+		struct iov_iter i;
 
 		iov = memdup_user(hp->dxferp, size);
 		if (IS_ERR(iov))
 			return PTR_ERR(iov);
 
-		len = iov_length(iov, iov_count);
-		if (hp->dxfer_len < len) {
-			iov_count = iov_shorten(iov, iov_count, hp->dxfer_len);
-			len = hp->dxfer_len;
-		}
+		iov_iter_init(&i, rw, iov, iov_count,
+			      min_t(size_t, hp->dxfer_len,
+				    iov_length(iov, iov_count)));
 
-		res = blk_rq_map_user_iov(q, rq, md, (struct sg_iovec *)iov,
-					  iov_count,
-					  len, GFP_ATOMIC);
+		res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
 		kfree(iov);
 	} else
 		res = blk_rq_map_user(q, rq, md, hp->dxferp,
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index a3367bfb1456a3..45aaa1cc56bc7a 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -987,7 +987,7 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
 	if (err)
 		goto out_free;
 	lsi->lsi_flags |= LSI_BDI_INITIALIZED;
-	lsi->lsi_bdi.capabilities = BDI_CAP_MAP_COPY;
+	lsi->lsi_bdi.capabilities = 0;
 	err = ll_bdi_register(&lsi->lsi_bdi);
 	if (err)
 		goto out_free;
@@ -1812,10 +1812,6 @@ void ll_read_inode2(struct inode *inode, void *opaque)
 
 	/* OIDEBUG(inode); */
 
-	/* initializing backing dev info. */
-	inode->i_mapping->backing_dev_info = &s2lsi(inode->i_sb)->lsi_bdi;
-
-
 	if (S_ISREG(inode->i_mode)) {
 		struct ll_sb_info *sbi = ll_i2sbi(inode);
 
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 6894b085f0ee0f..620d9348953983 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -335,7 +335,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	}
 	init_rwsem(&v9ses->rename_sem);
 
-	rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
 	if (rc) {
 		kfree(v9ses->aname);
 		kfree(v9ses->uname);
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 2b607257820c8e..d142a2449e65a9 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -106,7 +106,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 	volume->cell		= params->cell;
 	volume->vid		= vlocation->vldb.vid[params->type];
 
-	ret = bdi_setup_and_register(&volume->bdi, "afs", BDI_CAP_MAP_COPY);
+	ret = bdi_setup_and_register(&volume->bdi, "afs");
 	if (ret)
 		goto error_bdi;
 
diff --git a/fs/aio.c b/fs/aio.c
index c428871f10934a..118a2e0088d8fd 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -165,15 +165,6 @@ static struct vfsmount *aio_mnt;
 static const struct file_operations aio_ring_fops;
 static const struct address_space_operations aio_ctx_aops;
 
-/* Backing dev info for aio fs.
- * -no dirty page accounting or writeback happens
- */
-static struct backing_dev_info aio_fs_backing_dev_info = {
-	.name           = "aiofs",
-	.state          = 0,
-	.capabilities   = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY,
-};
-
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
 	struct qstr this = QSTR_INIT("[aio]", 5);
@@ -185,7 +176,6 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
 	inode->i_mapping->private_data = ctx;
-	inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
@@ -230,9 +220,6 @@ static int __init aio_setup(void)
 	if (IS_ERR(aio_mnt))
 		panic("Failed to create aio fs mount.");
 
-	if (bdi_init(&aio_fs_backing_dev_info))
-		panic("Failed to init aio fs backing dev info.");
-
 	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b48c41bf0f8675..975266be67d319 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -49,23 +49,15 @@ inline struct block_device *I_BDEV(struct inode *inode)
 }
 EXPORT_SYMBOL(I_BDEV);
 
-/*
- * Move the inode from its current bdi to a new bdi.  Make sure the inode
- * is clean before moving so that it doesn't linger on the old bdi.
- */
-static void bdev_inode_switch_bdi(struct inode *inode,
-			struct backing_dev_info *dst)
+static void bdev_write_inode(struct inode *inode)
 {
-	while (true) {
-		spin_lock(&inode->i_lock);
-		if (!(inode->i_state & I_DIRTY)) {
-			inode->i_data.backing_dev_info = dst;
-			spin_unlock(&inode->i_lock);
-			return;
-		}
+	spin_lock(&inode->i_lock);
+	while (inode->i_state & I_DIRTY) {
 		spin_unlock(&inode->i_lock);
 		WARN_ON_ONCE(write_inode_now(inode, true));
+		spin_lock(&inode->i_lock);
 	}
+	spin_unlock(&inode->i_lock);
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
@@ -429,6 +421,46 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
 
+/**
+ * bdev_direct_access() - Get the address for directly-accessibly memory
+ * @bdev: The device containing the memory
+ * @sector: The offset within the device
+ * @addr: Where to put the address of the memory
+ * @pfn: The Page Frame Number for the memory
+ * @size: The number of bytes requested
+ *
+ * If a block device is made up of directly addressable memory, this function
+ * will tell the caller the PFN and the address of the memory.  The address
+ * may be directly dereferenced within the kernel without the need to call
+ * ioremap(), kmap() or similar.  The PFN is suitable for inserting into
+ * page tables.
+ *
+ * Return: negative errno if an error occurs, otherwise the number of bytes
+ * accessible at this address.
+ */
+long bdev_direct_access(struct block_device *bdev, sector_t sector,
+			void **addr, unsigned long *pfn, long size)
+{
+	long avail;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+
+	if (size < 0)
+		return size;
+	if (!ops->direct_access)
+		return -EOPNOTSUPP;
+	if ((sector + DIV_ROUND_UP(size, 512)) >
+					part_nr_sects_read(bdev->bd_part))
+		return -ERANGE;
+	sector += get_start_sect(bdev);
+	if (sector % (PAGE_SIZE / 512))
+		return -EINVAL;
+	avail = ops->direct_access(bdev, sector, addr, pfn, size);
+	if (!avail)
+		return -ERANGE;
+	return min(avail, size);
+}
+EXPORT_SYMBOL_GPL(bdev_direct_access);
+
 /*
  * pseudo-fs
  */
@@ -584,7 +616,6 @@ struct block_device *bdget(dev_t dev)
 		inode->i_bdev = bdev;
 		inode->i_data.a_ops = &def_blk_aops;
 		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
-		inode->i_data.backing_dev_info = &default_backing_dev_info;
 		spin_lock(&bdev_lock);
 		list_add(&bdev->bd_list, &all_bdevs);
 		spin_unlock(&bdev_lock);
@@ -1145,8 +1176,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
 		if (!partno) {
-			struct backing_dev_info *bdi;
-
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!bdev->bd_part)
@@ -1172,11 +1201,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				}
 			}
 
-			if (!ret) {
+			if (!ret)
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
-				bdi = blk_get_backing_dev_info(bdev);
-				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
-			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1203,8 +1229,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (ret)
 				goto out_clear;
 			bdev->bd_contains = whole;
-			bdev_inode_switch_bdi(bdev->bd_inode,
-				whole->bd_inode->i_data.backing_dev_info);
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
 			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
@@ -1244,7 +1268,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_queue = NULL;
-	bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
@@ -1464,11 +1487,11 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		WARN_ON_ONCE(bdev->bd_holders);
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
-		/* ->release can cause the old bdi to disappear,
-		 * so must switch it out first
+		/*
+		 * ->release can cause the queue to disappear, so flush all
+		 * dirty data before.
 		 */
-		bdev_inode_switch_bdi(bdev->bd_inode,
-					&default_backing_dev_info);
+		bdev_write_inode(bdev->bd_inode);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8c63419a7f70de..1afb18226da82c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1715,12 +1715,11 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 {
 	int err;
 
-	bdi->capabilities = BDI_CAP_MAP_COPY;
-	err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY);
+	err = bdi_setup_and_register(bdi, "btrfs");
 	if (err)
 		return err;
 
-	bdi->ra_pages	= default_backing_dev_info.ra_pages;
+	bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
 	bdi->congested_fn	= btrfs_congested_fn;
 	bdi->congested_data	= info;
 	return 0;
@@ -2319,7 +2318,6 @@ int open_ctree(struct super_block *sb,
 	 */
 	fs_info->btree_inode->i_size = OFFSET_MAX;
 	fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
-	fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
 
 	RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
 	extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a606ab551296e1..b78bbbac900db8 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1746,7 +1746,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 
 	mutex_lock(&inode->i_mutex);
 
-	current->backing_dev_info = inode->i_mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err) {
 		mutex_unlock(&inode->i_mutex);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8bf326affb9440..54bcf639d1cf1f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3608,7 +3608,6 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_mapping->a_ops = &btrfs_aops;
-		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 		inode->i_fop = &btrfs_file_operations;
 		inode->i_op = &btrfs_file_inode_operations;
@@ -3623,7 +3622,6 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	case S_IFLNK:
 		inode->i_op = &btrfs_symlink_inode_operations;
 		inode->i_mapping->a_ops = &btrfs_symlink_aops;
-		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 		break;
 	default:
 		inode->i_op = &btrfs_special_inode_operations;
@@ -6088,7 +6086,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
@@ -9203,7 +9200,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
@@ -9247,7 +9243,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 
 	inode->i_op = &btrfs_symlink_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_symlink_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	inode_set_bytes(inode, name_len);
 	btrfs_i_size_write(inode, name_len);
 	err = btrfs_update_inode(trans, root, inode);
@@ -9459,7 +9454,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_op = &btrfs_file_inode_operations;
 
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
 	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ce74b394b49dd4..905986dd4c3c9d 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -945,7 +945,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = file->f_mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f61a74115bebbe..6b51736051541e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -783,8 +783,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	}
 
 	inode->i_mapping->a_ops = &ceph_aops;
-	inode->i_mapping->backing_dev_info =
-		&ceph_sb_to_client(inode->i_sb)->backing_dev_info;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFIFO:
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 50f06cddc94b7d..5ae62587a71d5c 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -40,17 +40,6 @@ static void ceph_put_super(struct super_block *s)
 
 	dout("put_super\n");
 	ceph_mdsc_close_sessions(fsc->mdsc);
-
-	/*
-	 * ensure we release the bdi before put_anon_super releases
-	 * the device name.
-	 */
-	if (s->s_bdi == &fsc->backing_dev_info) {
-		bdi_unregister(&fsc->backing_dev_info);
-		s->s_bdi = NULL;
-	}
-
-	return;
 }
 
 static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -910,7 +899,7 @@ static int ceph_register_bdi(struct super_block *sb,
 			>> PAGE_SHIFT;
 	else
 		fsc->backing_dev_info.ra_pages =
-			default_backing_dev_info.ra_pages;
+			VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
 
 	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
 			   atomic_long_inc_return(&bdi_seq));
@@ -1002,11 +991,16 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 static void ceph_kill_sb(struct super_block *s)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
+	dev_t dev = s->s_dev;
+
 	dout("kill_sb %p\n", s);
+
 	ceph_mdsc_pre_umount(fsc->mdsc);
-	kill_anon_super(s);    /* will call put_super after sb is r/o */
+	generic_shutdown_super(s);
 	ceph_mdsc_destroy(fsc);
+
 	destroy_fs_client(fsc);
+	free_anon_bdev(dev);
 }
 
 static struct file_system_type ceph_fs_type = {
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 67b2007f10fe65..ea06a3d0364cc2 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -24,27 +24,6 @@
 
 #include "internal.h"
 
-/*
- * capabilities for /dev/mem, /dev/kmem and similar directly mappable character
- * devices
- * - permits shared-mmap for read, write and/or exec
- * - does not permit private mmap in NOMMU mode (can't do COW)
- * - no readahead or I/O queue unplugging required
- */
-struct backing_dev_info directly_mappable_cdev_bdi = {
-	.name = "char",
-	.capabilities	= (
-#ifdef CONFIG_MMU
-		/* permit private copies of the data to be taken */
-		BDI_CAP_MAP_COPY |
-#endif
-		/* permit direct mmap, for read, write or exec */
-		BDI_CAP_MAP_DIRECT |
-		BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP |
-		/* no writeback happens */
-		BDI_CAP_NO_ACCT_AND_WRITEBACK),
-};
-
 static struct kobj_map *cdev_map;
 
 static DEFINE_MUTEX(chrdevs_lock);
@@ -575,8 +554,6 @@ static struct kobject *base_probe(dev_t dev, int *part, void *data)
 void __init chrdev_init(void)
 {
 	cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
-	if (bdi_init(&directly_mappable_cdev_bdi))
-		panic("Failed to init directly mappable cdev bdi");
 }
 
 
@@ -590,4 +567,3 @@ EXPORT_SYMBOL(cdev_del);
 EXPORT_SYMBOL(cdev_add);
 EXPORT_SYMBOL(__register_chrdev);
 EXPORT_SYMBOL(__unregister_chrdev);
-EXPORT_SYMBOL(directly_mappable_cdev_bdi);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2a772da16b839f..d3aa999ab78520 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3446,7 +3446,7 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 	int referral_walks_count = 0;
 #endif
 
-	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs");
 	if (rc)
 		return rc;
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 0c3ce464cae469..2d4f37235ed0fa 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -937,8 +937,6 @@ cifs_iget(struct super_block *sb, struct cifs_fattr *fattr)
 			inode->i_flags |= S_NOATIME | S_NOCMTIME;
 		if (inode->i_state & I_NEW) {
 			inode->i_ino = hash;
-			if (S_ISREG(inode->i_mode))
-				inode->i_data.backing_dev_info = sb->s_bdi;
 #ifdef CONFIG_CIFS_FSCACHE
 			/* initialize per-inode cache cookie pointer */
 			CIFS_I(inode)->fscache = NULL;
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index b945410bfcd58d..82ec68b5920828 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -183,7 +183,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 		goto unlock_out;
 	}
 
-	error = bdi_setup_and_register(&vc->bdi, "coda", BDI_CAP_MAP_COPY);
+	error = bdi_setup_and_register(&vc->bdi, "coda");
 	if (error)
 		goto unlock_out;
 
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index bd4a3c16709134..a315677e44d34d 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -70,8 +70,6 @@ extern int configfs_is_root(struct config_item *item);
 
 extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *);
 extern int configfs_create(struct dentry *, umode_t mode, int (*init)(struct inode *));
-extern int configfs_inode_init(void);
-extern void configfs_inode_exit(void);
 
 extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
 extern int configfs_make_dirent(struct configfs_dirent *,
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 5946ad98053fa0..65af8614715419 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -50,12 +50,6 @@ static const struct address_space_operations configfs_aops = {
 	.write_end	= simple_write_end,
 };
 
-static struct backing_dev_info configfs_backing_dev_info = {
-	.name		= "configfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 static const struct inode_operations configfs_inode_operations ={
 	.setattr	= configfs_setattr,
 };
@@ -137,7 +131,6 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode->i_mapping->a_ops = &configfs_aops;
-		inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
 		inode->i_op = &configfs_inode_operations;
 
 		if (sd->s_iattr) {
@@ -283,13 +276,3 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
 	}
 	mutex_unlock(&dir->d_inode->i_mutex);
 }
-
-int __init configfs_inode_init(void)
-{
-	return bdi_init(&configfs_backing_dev_info);
-}
-
-void configfs_inode_exit(void)
-{
-	bdi_destroy(&configfs_backing_dev_info);
-}
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index f6c28583339016..da94e41bdbf685 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -145,19 +145,13 @@ static int __init configfs_init(void)
 	if (!config_kobj)
 		goto out2;
 
-	err = configfs_inode_init();
-	if (err)
-		goto out3;
-
 	err = register_filesystem(&configfs_fs_type);
 	if (err)
-		goto out4;
+		goto out3;
 
 	return 0;
-out4:
-	pr_err("Unable to register filesystem!\n");
-	configfs_inode_exit();
 out3:
+	pr_err("Unable to register filesystem!\n");
 	kobject_put(config_kobj);
 out2:
 	kmem_cache_destroy(configfs_dir_cachep);
@@ -172,7 +166,6 @@ static void __exit configfs_exit(void)
 	kobject_put(config_kobj);
 	kmem_cache_destroy(configfs_dir_cachep);
 	configfs_dir_cachep = NULL;
-	configfs_inode_exit();
 }
 
 MODULE_AUTHOR("Oracle");
diff --git a/fs/dcache.c b/fs/dcache.c
index e368d4f412f97e..d04be762b216e5 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -400,19 +400,20 @@ static void d_shrink_add(struct dentry *dentry, struct list_head *list)
  * LRU lists entirely, while shrink_move moves it to the indicated
  * private list.
  */
-static void d_lru_isolate(struct dentry *dentry)
+static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry)
 {
 	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
 	dentry->d_flags &= ~DCACHE_LRU_LIST;
 	this_cpu_dec(nr_dentry_unused);
-	list_del_init(&dentry->d_lru);
+	list_lru_isolate(lru, &dentry->d_lru);
 }
 
-static void d_lru_shrink_move(struct dentry *dentry, struct list_head *list)
+static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry,
+			      struct list_head *list)
 {
 	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
 	dentry->d_flags |= DCACHE_SHRINK_LIST;
-	list_move_tail(&dentry->d_lru, list);
+	list_lru_isolate_move(lru, &dentry->d_lru, list);
 }
 
 /*
@@ -869,8 +870,8 @@ static void shrink_dentry_list(struct list_head *list)
 	}
 }
 
-static enum lru_status
-dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+static enum lru_status dentry_lru_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
@@ -890,7 +891,7 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 	 * another pass through the LRU.
 	 */
 	if (dentry->d_lockref.count) {
-		d_lru_isolate(dentry);
+		d_lru_isolate(lru, dentry);
 		spin_unlock(&dentry->d_lock);
 		return LRU_REMOVED;
 	}
@@ -921,7 +922,7 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 		return LRU_ROTATE;
 	}
 
-	d_lru_shrink_move(dentry, freeable);
+	d_lru_shrink_move(lru, dentry, freeable);
 	spin_unlock(&dentry->d_lock);
 
 	return LRU_REMOVED;
@@ -930,30 +931,28 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 /**
  * prune_dcache_sb - shrink the dcache
  * @sb: superblock
- * @nr_to_scan : number of entries to try to free
- * @nid: which node to scan for freeable entities
+ * @sc: shrink control, passed to list_lru_shrink_walk()
  *
- * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
- * done when we need more memory an called from the superblock shrinker
+ * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This
+ * is done when we need more memory and called from the superblock shrinker
  * function.
  *
  * This function may fail to free any resources if all the dentries are in
  * use.
  */
-long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-		     int nid)
+long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(dispose);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc,
+				     dentry_lru_isolate, &dispose);
 	shrink_dentry_list(&dispose);
 	return freed;
 }
 
 static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
-						spinlock_t *lru_lock, void *arg)
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
@@ -966,7 +965,7 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
 	if (!spin_trylock(&dentry->d_lock))
 		return LRU_SKIP;
 
-	d_lru_shrink_move(dentry, freeable);
+	d_lru_shrink_move(lru, dentry, freeable);
 	spin_unlock(&dentry->d_lock);
 
 	return LRU_REMOVED;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 2bc2c87f35e7a2..5718cb9f7273e8 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -37,20 +37,6 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	iput(toput_inode);
 }
 
-static void drop_slab(void)
-{
-	int nr_objects;
-
-	do {
-		int nid;
-
-		nr_objects = 0;
-		for_each_online_node(nid)
-			nr_objects += shrink_node_slabs(GFP_KERNEL, nid,
-							1000, 1000);
-	} while (nr_objects > 10);
-}
-
 int drop_caches_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1686dc2da9fd76..34b36a5040593e 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -67,7 +67,6 @@ static int ecryptfs_inode_set(struct inode *inode, void *opaque)
 	inode->i_ino = lower_inode->i_ino;
 	inode->i_version++;
 	inode->i_mapping->a_ops = &ecryptfs_aops;
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	if (S_ISLNK(inode->i_mode))
 		inode->i_op = &ecryptfs_symlink_iops;
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index d9eb84bda5591a..1895d60f4122c2 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -520,7 +520,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs");
 	if (rc)
 		goto out1;
 
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index f1d3d4eb8c4ff1..6fc91df99ff8aa 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1214,7 +1214,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 		memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
 	}
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &exofs_file_inode_operations;
 		inode->i_fop = &exofs_file_operations;
@@ -1314,7 +1313,6 @@ struct inode *exofs_new_inode(struct inode *dir, umode_t mode)
 
 	set_obj_2bcreated(oi);
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	inode_init_owner(inode, dir, mode);
 	inode->i_ino = sbi->s_nextid++;
 	inode->i_blkbits = EXOFS_BLKSHIFT;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 95965503afcbe5..fcc2e565f540c3 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -836,7 +836,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
-	ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY);
+	ret = bdi_setup_and_register(&sbi->bdi, "exofs");
 	if (ret) {
 		EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
 		dput(sb->s_root);
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 7d66fb0e4cca87..6c14bb8322fabe 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -170,7 +170,7 @@ static void ext2_preread_inode(struct inode *inode)
 	struct ext2_group_desc * gdp;
 	struct backing_dev_info *bdi;
 
-	bdi = inode->i_mapping->backing_dev_info;
+	bdi = inode_to_bdi(inode);
 	if (bdi_read_congested(bdi))
 		return;
 	if (bdi_write_congested(bdi))
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index e98171a11cfe19..bbc5fec6ff7f69 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -13,18 +13,12 @@
 #include "ext2.h"
 #include "xip.h"
 
-static inline int
-__inode_direct_access(struct inode *inode, sector_t block,
-		      void **kaddr, unsigned long *pfn)
+static inline long __inode_direct_access(struct inode *inode, sector_t block,
+				void **kaddr, unsigned long *pfn, long size)
 {
 	struct block_device *bdev = inode->i_sb->s_bdev;
-	const struct block_device_operations *ops = bdev->bd_disk->fops;
-	sector_t sector;
-
-	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
-
-	BUG_ON(!ops->direct_access);
-	return ops->direct_access(bdev, sector, kaddr, pfn);
+	sector_t sector = block * (PAGE_SIZE / 512);
+	return bdev_direct_access(bdev, sector, kaddr, pfn, size);
 }
 
 static inline int
@@ -53,12 +47,13 @@ ext2_clear_xip_target(struct inode *inode, sector_t block)
 {
 	void *kaddr;
 	unsigned long pfn;
-	int rc;
+	long size;
 
-	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
-	if (!rc)
-		clear_page(kaddr);
-	return rc;
+	size = __inode_direct_access(inode, block, &kaddr, &pfn, PAGE_SIZE);
+	if (size < 0)
+		return size;
+	clear_page(kaddr);
+	return 0;
 }
 
 void ext2_xip_verify_sb(struct super_block *sb)
@@ -77,7 +72,7 @@ void ext2_xip_verify_sb(struct super_block *sb)
 int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
 				void **kmem, unsigned long *pfn)
 {
-	int rc;
+	long rc;
 	sector_t block;
 
 	/* first, retrieve the sector number */
@@ -86,6 +81,6 @@ int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
 		return rc;
 
 	/* retrieve address of the target data */
-	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
-	return rc;
+	rc = __inode_direct_access(mapping->host, block, kmem, pfn, PAGE_SIZE);
+	return (rc < 0) ? rc : 0;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ac64edbe501d9f..64c39c7c594f72 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -334,7 +334,7 @@ static void save_error_info(struct super_block *sb, const char *func,
 static int block_device_ejected(struct super_block *sb)
 {
 	struct inode *bd_inode = sb->s_bdev->bd_inode;
-	struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
 
 	return bdi->dev == NULL;
 }
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 736a348509f7d6..94e2d2ffabe1a1 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -71,3 +71,13 @@ config F2FS_CHECK_FS
 	  Enables BUG_ONs which check the filesystem consistency in runtime.
 
 	  If you want to improve the performance, say N.
+
+config F2FS_IO_TRACE
+	bool "F2FS IO tracer"
+	depends on F2FS_FS
+	depends on FUNCTION_TRACER
+	help
+	  F2FS IO trace is based on a function trace, which gathers process
+	  information and block IO patterns in the filesystem level.
+
+	  If unsure, say N.
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 2e35da12d292e4..d92397731db846 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -5,3 +5,4 @@ f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
 f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
+f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 1ccb26bc2a0b5c..742202779bd517 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
 	if (count == 0)
 		return NULL;
 
-	acl = posix_acl_alloc(count, GFP_KERNEL);
+	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -116,7 +116,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
 	int i;
 
 	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
-			sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+			sizeof(struct f2fs_acl_entry), GFP_NOFS);
 	if (!f2fs_acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -396,7 +396,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
 		posix_acl_release(default_acl);
 	}
 	if (acl) {
-		if (error)
+		if (!error)
 			error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl,
 					       ipage);
 		posix_acl_release(acl);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index e6c271fefacae5..7f794b72b3b7d2 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -20,10 +20,11 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static struct kmem_cache *ino_entry_slab;
-static struct kmem_cache *inode_entry_slab;
+struct kmem_cache *inode_entry_slab;
 
 /*
  * We guarantee no failure on the returned page.
@@ -50,6 +51,11 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page;
+	struct f2fs_io_info fio = {
+		.type = META,
+		.rw = READ_SYNC | REQ_META | REQ_PRIO,
+		.blk_addr = index,
+	};
 repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page) {
@@ -59,8 +65,7 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	if (PageUptodate(page))
 		goto out;
 
-	if (f2fs_submit_page_bio(sbi, page, index,
-				READ_SYNC | REQ_META | REQ_PRIO))
+	if (f2fs_submit_page_bio(sbi, page, &fio))
 		goto repeat;
 
 	lock_page(page);
@@ -112,14 +117,12 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 	block_t prev_blk_addr = 0;
 	struct page *page;
 	block_t blkno = start;
-
 	struct f2fs_io_info fio = {
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO
 	};
 
 	for (; nrpages-- > 0; blkno++) {
-		block_t blk_addr;
 
 		if (!is_valid_blkaddr(sbi, blkno, type))
 			goto out;
@@ -130,27 +133,27 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 					NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
 				blkno = 0;
 			/* get nat block addr */
-			blk_addr = current_nat_addr(sbi,
+			fio.blk_addr = current_nat_addr(sbi,
 					blkno * NAT_ENTRY_PER_BLOCK);
 			break;
 		case META_SIT:
 			/* get sit block addr */
-			blk_addr = current_sit_addr(sbi,
+			fio.blk_addr = current_sit_addr(sbi,
 					blkno * SIT_ENTRY_PER_BLOCK);
-			if (blkno != start && prev_blk_addr + 1 != blk_addr)
+			if (blkno != start && prev_blk_addr + 1 != fio.blk_addr)
 				goto out;
-			prev_blk_addr = blk_addr;
+			prev_blk_addr = fio.blk_addr;
 			break;
 		case META_SSA:
 		case META_CP:
 		case META_POR:
-			blk_addr = blkno;
+			fio.blk_addr = blkno;
 			break;
 		default:
 			BUG();
 		}
 
-		page = grab_cache_page(META_MAPPING(sbi), blk_addr);
+		page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -158,7 +161,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 			continue;
 		}
 
-		f2fs_submit_page_mbio(sbi, page, blk_addr, &fio);
+		f2fs_submit_page_mbio(sbi, page, &fio);
 		f2fs_put_page(page, 0);
 	}
 out:
@@ -187,7 +190,7 @@ static int f2fs_write_meta_page(struct page *page,
 
 	trace_f2fs_writepage(page, META);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
 		goto redirty_out;
@@ -299,6 +302,8 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
+		SetPagePrivate(page);
+		f2fs_trace_pid(page);
 		return 1;
 	}
 	return 0;
@@ -308,6 +313,8 @@ const struct address_space_operations f2fs_meta_aops = {
 	.writepage	= f2fs_write_meta_page,
 	.writepages	= f2fs_write_meta_pages,
 	.set_page_dirty	= f2fs_set_meta_page_dirty,
+	.invalidatepage = f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 };
 
 static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -462,7 +469,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
 		return;
 
-	sbi->por_doing = true;
+	set_sbi_flag(sbi, SBI_POR_DOING);
 
 	start_blk = __start_cp_addr(sbi) + 1 +
 		le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
@@ -483,7 +490,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	}
 	/* clear Orphan Flag */
 	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	return;
 }
 
@@ -567,7 +574,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp1;
 
-	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
@@ -582,7 +589,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp2;
 
-	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
@@ -669,7 +676,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	return -EINVAL;
 }
 
-static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
+static int __add_dirty_inode(struct inode *inode, struct inode_entry *new)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
@@ -686,7 +693,7 @@ static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
 void update_dirty_page(struct inode *inode, struct page *page)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *new;
+	struct inode_entry *new;
 	int ret = 0;
 
 	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
@@ -710,12 +717,13 @@ void update_dirty_page(struct inode *inode, struct page *page)
 		kmem_cache_free(inode_entry_slab, new);
 out:
 	SetPagePrivate(page);
+	f2fs_trace_pid(page);
 }
 
 void add_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *new =
+	struct inode_entry *new =
 			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
 	int ret = 0;
 
@@ -733,7 +741,7 @@ void add_dirty_dir_inode(struct inode *inode)
 void remove_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *entry;
+	struct inode_entry *entry;
 
 	if (!S_ISDIR(inode->i_mode))
 		return;
@@ -763,7 +771,7 @@ void remove_dirty_dir_inode(struct inode *inode)
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
 {
 	struct list_head *head;
-	struct dir_inode_entry *entry;
+	struct inode_entry *entry;
 	struct inode *inode;
 retry:
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -776,7 +784,7 @@ void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
 		spin_unlock(&sbi->dir_inode_lock);
 		return;
 	}
-	entry = list_entry(head->next, struct dir_inode_entry, list);
+	entry = list_entry(head->next, struct inode_entry, list);
 	inode = igrab(entry->inode);
 	spin_unlock(&sbi->dir_inode_lock);
 	if (inode) {
@@ -922,7 +930,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->next_free_nid = cpu_to_le32(last_nid);
 
 	/* 2 cp  + n data seg summary + orphan inode blocks */
-	data_sum_blocks = npages_for_summary_flush(sbi);
+	data_sum_blocks = npages_for_summary_flush(sbi, false);
 	if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
 		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
@@ -932,24 +940,31 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
 			orphan_blocks);
 
-	if (cpc->reason == CP_UMOUNT) {
-		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	if (__remain_node_summaries(cpc->reason))
 		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks + NR_CURSEG_NODE_TYPE);
-	} else {
-		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	else
 		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks);
-	}
+
+	if (cpc->reason == CP_UMOUNT)
+		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+
+	if (cpc->reason == CP_FASTBOOT)
+		set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
 
 	if (orphan_num)
 		set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 	else
 		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 
-	if (sbi->need_fsck)
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
 		set_ckpt_flags(ckpt, CP_FSCK_FLAG);
 
 	/* update SIT/NAT bitmap */
@@ -966,15 +981,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* write out checkpoint buffer at block 0 */
 	cp_page = grab_meta_page(sbi, start_blk++);
 	kaddr = page_address(cp_page);
-	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	memcpy(kaddr, ckpt, F2FS_BLKSIZE);
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
 	for (i = 1; i < 1 + cp_payload_blks; i++) {
 		cp_page = grab_meta_page(sbi, start_blk++);
 		kaddr = page_address(cp_page);
-		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
-				(1 << sbi->log_blocksize));
+		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE, F2FS_BLKSIZE);
 		set_page_dirty(cp_page);
 		f2fs_put_page(cp_page, 1);
 	}
@@ -986,7 +1000,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	write_data_summaries(sbi, start_blk);
 	start_blk += data_sum_blocks;
-	if (cpc->reason == CP_UMOUNT) {
+	if (__remain_node_summaries(cpc->reason)) {
 		write_node_summaries(sbi, start_blk);
 		start_blk += NR_CURSEG_NODE_TYPE;
 	}
@@ -994,7 +1008,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* writeout checkpoint block */
 	cp_page = grab_meta_page(sbi, start_blk);
 	kaddr = page_address(cp_page);
-	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	memcpy(kaddr, ckpt, F2FS_BLKSIZE);
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
@@ -1023,7 +1037,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		return;
 
 	clear_prefree_segments(sbi);
-	F2FS_RESET_SB_DIRT(sbi);
+	clear_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
 /*
@@ -1038,10 +1052,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	mutex_lock(&sbi->cp_mutex);
 
-	if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
+	if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
+			cpc->reason != CP_DISCARD && cpc->reason != CP_UMOUNT)
 		goto out;
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto out;
+	if (f2fs_readonly(sbi->sb))
+		goto out;
 	if (block_operations(sbi))
 		goto out;
 
@@ -1102,8 +1119,8 @@ int __init create_checkpoint_caches(void)
 			sizeof(struct ino_entry));
 	if (!ino_entry_slab)
 		return -ENOMEM;
-	inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry",
-			sizeof(struct dir_inode_entry));
+	inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
+			sizeof(struct inode_entry));
 	if (!inode_entry_slab) {
 		kmem_cache_destroy(ino_entry_slab);
 		return -ENOMEM;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7ec697b37f1931..985ed023a75017 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -22,6 +22,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static void f2fs_read_end_io(struct bio *bio, int err)
@@ -95,11 +96,9 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 		return;
 
 	if (is_read_io(fio->rw))
-		trace_f2fs_submit_read_bio(io->sbi->sb, fio->rw,
-							fio->type, io->bio);
+		trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
 	else
-		trace_f2fs_submit_write_bio(io->sbi->sb, fio->rw,
-							fio->type, io->bio);
+		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
 
 	submit_bio(fio->rw, io->bio);
 	io->bio = NULL;
@@ -132,14 +131,15 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
  * Return unlocked page.
  */
 int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
-					block_t blk_addr, int rw)
+					struct f2fs_io_info *fio)
 {
 	struct bio *bio;
 
-	trace_f2fs_submit_page_bio(page, blk_addr, rw);
+	trace_f2fs_submit_page_bio(page, fio);
+	f2fs_trace_ios(page, fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw));
+	bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw));
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
 		bio_put(bio);
@@ -147,12 +147,12 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
 		return -EFAULT;
 	}
 
-	submit_bio(rw, bio);
+	submit_bio(fio->rw, bio);
 	return 0;
 }
 
 void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
-			block_t blk_addr, struct f2fs_io_info *fio)
+					struct f2fs_io_info *fio)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
 	struct f2fs_bio_info *io;
@@ -160,21 +160,21 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
-	verify_block_addr(sbi, blk_addr);
+	verify_block_addr(sbi, fio->blk_addr);
 
 	down_write(&io->io_rwsem);
 
 	if (!is_read)
 		inc_page_count(sbi, F2FS_WRITEBACK);
 
-	if (io->bio && (io->last_block_in_bio != blk_addr - 1 ||
+	if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
 						io->fio.rw != fio->rw))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
 		int bio_blocks = MAX_BIO_BLOCKS(sbi);
 
-		io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
+		io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read);
 		io->fio = *fio;
 	}
 
@@ -184,10 +184,11 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
 		goto alloc_new;
 	}
 
-	io->last_block_in_bio = blk_addr;
+	io->last_block_in_bio = fio->blk_addr;
+	f2fs_trace_ios(page, fio, 0);
 
 	up_write(&io->io_rwsem);
-	trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr);
+	trace_f2fs_submit_page_mbio(page, fio);
 }
 
 /*
@@ -196,7 +197,7 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
  *  ->node_page
  *    update block addresses in the node page
  */
-static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
+static void __set_data_blkaddr(struct dnode_of_data *dn)
 {
 	struct f2fs_node *rn;
 	__le32 *addr_array;
@@ -209,7 +210,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
 
 	/* Get physical address of data block */
 	addr_array = blkaddr_in_node(rn);
-	addr_array[ofs_in_node] = cpu_to_le32(new_addr);
+	addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
 	set_page_dirty(node_page);
 }
 
@@ -224,8 +225,8 @@ int reserve_new_block(struct dnode_of_data *dn)
 
 	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
 
-	__set_data_blkaddr(dn, NEW_ADDR);
 	dn->data_blkaddr = NEW_ADDR;
+	__set_data_blkaddr(dn);
 	mark_inode_dirty(dn->inode);
 	sync_inode_page(dn);
 	return 0;
@@ -273,7 +274,7 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 		unsigned int blkbits = inode->i_sb->s_blocksize_bits;
 		size_t count;
 
-		clear_buffer_new(bh_result);
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb,
 				start_blkaddr + pgofs - start_fofs);
 		count = end_fofs - pgofs + 1;
@@ -290,23 +291,24 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 	return 0;
 }
 
-void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
+void update_extent_cache(struct dnode_of_data *dn)
 {
 	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	pgoff_t fofs, start_fofs, end_fofs;
 	block_t start_blkaddr, end_blkaddr;
 	int need_update = true;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), blk_addr == NEW_ADDR);
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
-							dn->ofs_in_node;
+	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
 
 	/* Update the page address in the parent node */
-	__set_data_blkaddr(dn, blk_addr);
+	__set_data_blkaddr(dn);
 
 	if (is_inode_flag_set(fi, FI_NO_EXTENT))
 		return;
 
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+							dn->ofs_in_node;
+
 	write_lock(&fi->ext.ext_lock);
 
 	start_fofs = fi->ext.fofs;
@@ -320,16 +322,16 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 
 	/* Initial extent */
 	if (fi->ext.len == 0) {
-		if (blk_addr != NULL_ADDR) {
+		if (dn->data_blkaddr != NULL_ADDR) {
 			fi->ext.fofs = fofs;
-			fi->ext.blk_addr = blk_addr;
+			fi->ext.blk_addr = dn->data_blkaddr;
 			fi->ext.len = 1;
 		}
 		goto end_update;
 	}
 
 	/* Front merge */
-	if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
+	if (fofs == start_fofs - 1 && dn->data_blkaddr == start_blkaddr - 1) {
 		fi->ext.fofs--;
 		fi->ext.blk_addr--;
 		fi->ext.len++;
@@ -337,7 +339,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 	}
 
 	/* Back merge */
-	if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) {
+	if (fofs == end_fofs + 1 && dn->data_blkaddr == end_blkaddr + 1) {
 		fi->ext.len++;
 		goto end_update;
 	}
@@ -376,6 +378,10 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	struct dnode_of_data dn;
 	struct page *page;
 	int err;
+	struct f2fs_io_info fio = {
+		.type = DATA,
+		.rw = sync ? READ_SYNC : READA,
+	};
 
 	page = find_get_page(mapping, index);
 	if (page && PageUptodate(page))
@@ -404,8 +410,8 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 		return page;
 	}
 
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, dn.data_blkaddr,
-					sync ? READ_SYNC : READA);
+	fio.blk_addr = dn.data_blkaddr;
+	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -430,7 +436,10 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	struct dnode_of_data dn;
 	struct page *page;
 	int err;
-
+	struct f2fs_io_info fio = {
+		.type = DATA,
+		.rw = READ_SYNC,
+	};
 repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page)
@@ -464,8 +473,8 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 		return page;
 	}
 
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
-					dn.data_blkaddr, READ_SYNC);
+	fio.blk_addr = dn.data_blkaddr;
+	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -515,8 +524,12 @@ struct page *get_new_data_page(struct inode *inode,
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 		SetPageUptodate(page);
 	} else {
-		err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
-						dn.data_blkaddr, READ_SYNC);
+		struct f2fs_io_info fio = {
+			.type = DATA,
+			.rw = READ_SYNC,
+			.blk_addr = dn.data_blkaddr,
+		};
+		err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 		if (err)
 			goto put_err;
 
@@ -550,30 +563,25 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	struct f2fs_summary sum;
-	block_t new_blkaddr;
 	struct node_info ni;
+	int seg = CURSEG_WARM_DATA;
 	pgoff_t fofs;
-	int type;
 
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
 	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
 		return -ENOSPC;
 
-	__set_data_blkaddr(dn, NEW_ADDR);
-	dn->data_blkaddr = NEW_ADDR;
-
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
-	type = CURSEG_WARM_DATA;
+	if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
+		seg = CURSEG_DIRECT_IO;
 
-	allocate_data_block(sbi, NULL, NULL_ADDR, &new_blkaddr, &sum, type);
+	allocate_data_block(sbi, NULL, NULL_ADDR, &dn->data_blkaddr, &sum, seg);
 
 	/* direct IO doesn't use extent cache to maximize the performance */
-	set_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
-	update_extent_cache(new_blkaddr, dn);
-	clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
+	__set_data_blkaddr(dn);
 
 	/* update i_size */
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
@@ -581,10 +589,59 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
 		i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
 
-	dn->data_blkaddr = new_blkaddr;
 	return 0;
 }
 
+static void __allocate_data_blocks(struct inode *inode, loff_t offset,
+							size_t count)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct dnode_of_data dn;
+	u64 start = F2FS_BYTES_TO_BLK(offset);
+	u64 len = F2FS_BYTES_TO_BLK(count);
+	bool allocated;
+	u64 end_offset;
+
+	while (len) {
+		f2fs_balance_fs(sbi);
+		f2fs_lock_op(sbi);
+
+		/* When reading holes, we need its node page */
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		if (get_dnode_of_data(&dn, start, ALLOC_NODE))
+			goto out;
+
+		allocated = false;
+		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+
+		while (dn.ofs_in_node < end_offset && len) {
+			if (dn.data_blkaddr == NULL_ADDR) {
+				if (__allocate_data_block(&dn))
+					goto sync_out;
+				allocated = true;
+			}
+			len--;
+			start++;
+			dn.ofs_in_node++;
+		}
+
+		if (allocated)
+			sync_inode_page(&dn);
+
+		f2fs_put_dnode(&dn);
+		f2fs_unlock_op(sbi);
+	}
+	return;
+
+sync_out:
+	if (allocated)
+		sync_inode_page(&dn);
+	f2fs_put_dnode(&dn);
+out:
+	f2fs_unlock_op(sbi);
+	return;
+}
+
 /*
  * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh.
  * If original data blocks are allocated, then give them to blockdev.
@@ -610,10 +667,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	if (check_extent_cache(inode, pgofs, bh_result))
 		goto out;
 
-	if (create) {
-		f2fs_balance_fs(F2FS_I_SB(inode));
+	if (create)
 		f2fs_lock_op(F2FS_I_SB(inode));
-	}
 
 	/* When reading holes, we need its node page */
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -627,12 +682,14 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 		goto put_out;
 
 	if (dn.data_blkaddr != NULL_ADDR) {
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
 	} else if (create) {
 		err = __allocate_data_block(&dn);
 		if (err)
 			goto put_out;
 		allocated = true;
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
 	} else {
 		goto put_out;
@@ -745,7 +802,6 @@ static int f2fs_read_data_pages(struct file *file,
 int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 {
 	struct inode *inode = page->mapping->host;
-	block_t old_blkaddr, new_blkaddr;
 	struct dnode_of_data dn;
 	int err = 0;
 
@@ -754,10 +810,10 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	if (err)
 		return err;
 
-	old_blkaddr = dn.data_blkaddr;
+	fio->blk_addr = dn.data_blkaddr;
 
 	/* This page is already truncated */
-	if (old_blkaddr == NULL_ADDR)
+	if (fio->blk_addr == NULL_ADDR)
 		goto out_writepage;
 
 	set_page_writeback(page);
@@ -766,14 +822,14 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (unlikely(old_blkaddr != NEW_ADDR &&
+	if (unlikely(fio->blk_addr != NEW_ADDR &&
 			!is_cold_data(page) &&
 			need_inplace_update(inode))) {
-		rewrite_data_page(page, old_blkaddr, fio);
+		rewrite_data_page(page, fio);
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
 	} else {
-		write_data_page(page, &dn, &new_blkaddr, fio);
-		update_extent_cache(new_blkaddr, &dn);
+		write_data_page(page, &dn, fio);
+		update_extent_cache(&dn);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	}
 out_writepage:
@@ -812,7 +868,12 @@ static int f2fs_write_data_page(struct page *page,
 
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
 write:
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto redirty_out;
+	if (f2fs_is_drop_cache(inode))
+		goto out;
+	if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
+			available_free_memory(sbi, BASE_CHECK))
 		goto redirty_out;
 
 	/* Dentry blocks are controlled by checkpoint */
@@ -826,7 +887,6 @@ static int f2fs_write_data_page(struct page *page,
 	/* we should bypass data pages to proceed the kworkder jobs */
 	if (unlikely(f2fs_cp_error(sbi))) {
 		SetPageError(page);
-		unlock_page(page);
 		goto out;
 	}
 
@@ -1002,8 +1062,12 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
-		err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
-					   READ_SYNC);
+		struct f2fs_io_info fio = {
+			.type = DATA,
+			.rw = READ_SYNC,
+			.blk_addr = dn.data_blkaddr,
+		};
+		err = f2fs_submit_page_bio(sbi, page, &fio);
 		if (err)
 			goto fail;
 
@@ -1092,6 +1156,9 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
 
+	if (rw & WRITE)
+		__allocate_data_blocks(inode, offset, count);
+
 	err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block);
 	if (err < 0 && (rw & WRITE))
 		f2fs_write_failed(mapping, offset + count);
@@ -1101,24 +1168,33 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 	return err;
 }
 
-static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
-				      unsigned int length)
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+							unsigned int length)
 {
 	struct inode *inode = page->mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
-	if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)
+	if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
+		(offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE))
 		return;
 
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
-		invalidate_inmem_page(inode, page);
-
-	if (PageDirty(page))
-		inode_dec_dirty_pages(inode);
+	if (PageDirty(page)) {
+		if (inode->i_ino == F2FS_META_INO(sbi))
+			dec_page_count(sbi, F2FS_DIRTY_META);
+		else if (inode->i_ino == F2FS_NODE_INO(sbi))
+			dec_page_count(sbi, F2FS_DIRTY_NODES);
+		else
+			inode_dec_dirty_pages(inode);
+	}
 	ClearPagePrivate(page);
 }
 
-static int f2fs_release_data_page(struct page *page, gfp_t wait)
+int f2fs_release_page(struct page *page, gfp_t wait)
 {
+	/* If this is dirty page, keep PagePrivate */
+	if (PageDirty(page))
+		return 0;
+
 	ClearPagePrivate(page);
 	return 1;
 }
@@ -1132,7 +1208,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
 
 	SetPageUptodate(page);
 
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode)) {
+	if (f2fs_is_atomic_file(inode)) {
 		register_inmem_page(inode, page);
 		return 1;
 	}
@@ -1168,8 +1244,8 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.write_begin	= f2fs_write_begin,
 	.write_end	= f2fs_write_end,
 	.set_page_dirty	= f2fs_set_data_page_dirty,
-	.invalidatepage	= f2fs_invalidate_data_page,
-	.releasepage	= f2fs_release_data_page,
+	.invalidatepage	= f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 	.direct_IO	= f2fs_direct_IO,
 	.bmap		= f2fs_bmap,
 };
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 91e8f699ab3071..e671373cc8ab89 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -40,6 +40,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_dirs = sbi->n_dirty_dirs;
 	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
+	si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
@@ -57,7 +58,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->node_pages = NODE_MAPPING(sbi)->nrpages;
 	si->meta_pages = META_MAPPING(sbi)->nrpages;
 	si->nats = NM_I(sbi)->nat_cnt;
-	si->sits = SIT_I(sbi)->dirty_sentries;
+	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+	si->sits = MAIN_SEGS(sbi);
+	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
 	si->fnids = NM_I(sbi)->fcnt;
 	si->bg_gc = sbi->bg_gc;
 	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
@@ -79,6 +82,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->segment_count[i] = sbi->segment_count[i];
 		si->block_count[i] = sbi->block_count[i];
 	}
+
+	si->inplace_count = atomic_read(&sbi->inplace_count);
 }
 
 /*
@@ -137,6 +142,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
 	si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
 	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += SIT_VBLOCK_MAP_SIZE;
 	if (sbi->segs_per_sec > 1)
 		si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
 	si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
@@ -159,20 +165,32 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
 
+get_cache:
+	si->cache_mem = 0;
+
 	/* build gc */
-	si->base_mem += sizeof(struct f2fs_gc_kthread);
+	if (sbi->gc_thread)
+		si->cache_mem += sizeof(struct f2fs_gc_kthread);
+
+	/* build merge flush thread */
+	if (SM_I(sbi)->cmd_control_info)
+		si->cache_mem += sizeof(struct flush_cmd_control);
 
-get_cache:
 	/* free nids */
-	si->cache_mem = NM_I(sbi)->fcnt;
-	si->cache_mem += NM_I(sbi)->nat_cnt;
-	npages = NODE_MAPPING(sbi)->nrpages;
-	si->cache_mem += npages << PAGE_CACHE_SHIFT;
-	npages = META_MAPPING(sbi)->nrpages;
-	si->cache_mem += npages << PAGE_CACHE_SHIFT;
-	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry);
+	si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid);
+	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
+	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
+					sizeof(struct nat_entry_set);
+	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
+	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry);
 	for (i = 0; i <= UPDATE_INO; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
+
+	si->page_mem = 0;
+	npages = NODE_MAPPING(sbi)->nrpages;
+	si->page_mem += npages << PAGE_CACHE_SHIFT;
+	npages = META_MAPPING(sbi)->nrpages;
+	si->page_mem += npages << PAGE_CACHE_SHIFT;
 }
 
 static int stat_show(struct seq_file *s, void *v)
@@ -250,16 +268,16 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "\nExtent Hit Ratio: %d / %d\n",
 			   si->hit_ext, si->total_ext);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4d\n",
-			   si->inmem_pages);
+		seq_printf(s, "  - inmem: %4d, wb: %4d\n",
+			   si->inmem_pages, si->wb_pages);
 		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d\n",
 			   si->ndirty_dent, si->ndirty_dirs);
 		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
-		seq_printf(s, "  - NATs: %9d\n  - SITs: %9d\n",
-			   si->nats, si->sits);
+		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
+			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);
 		seq_printf(s, "  - free_nids: %9d\n",
 			   si->fnids);
 		seq_puts(s, "\nDistribution of User Blocks:");
@@ -277,6 +295,7 @@ static int stat_show(struct seq_file *s, void *v)
 		for (j = 0; j < si->util_free; j++)
 			seq_putc(s, '-');
 		seq_puts(s, "]\n\n");
+		seq_printf(s, "IPU: %u blocks\n", si->inplace_count);
 		seq_printf(s, "SSR: %u blocks in %u segments\n",
 			   si->block_count[SSR], si->segment_count[SSR]);
 		seq_printf(s, "LFS: %u blocks in %u segments\n",
@@ -289,9 +308,14 @@ static int stat_show(struct seq_file *s, void *v)
 
 		/* memory footprint */
 		update_mem_info(si->sbi);
-		seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
-				(si->base_mem + si->cache_mem) >> 10,
-				si->base_mem >> 10, si->cache_mem >> 10);
+		seq_printf(s, "\nMemory: %u KB\n",
+			(si->base_mem + si->cache_mem + si->page_mem) >> 10);
+		seq_printf(s, "  - static: %u KB\n",
+				si->base_mem >> 10);
+		seq_printf(s, "  - cached: %u KB\n",
+				si->cache_mem >> 10);
+		seq_printf(s, "  - paged : %u KB\n",
+				si->page_mem >> 10);
 	}
 	mutex_unlock(&f2fs_stat_mutex);
 	return 0;
@@ -331,6 +355,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 
 	atomic_set(&sbi->inline_inode, 0);
 	atomic_set(&sbi->inline_dir, 0);
+	atomic_set(&sbi->inplace_count, 0);
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index b1a7d5737cd05a..b74097a7f6d904 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -286,8 +286,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	f2fs_wait_on_page_writeback(page, type);
 	de->ino = cpu_to_le32(inode->i_ino);
 	set_de_type(de, inode);
-	if (!f2fs_has_inline_dentry(dir))
-		kunmap(page);
+	f2fs_dentry_kunmap(dir, page);
 	set_page_dirty(page);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	mark_inode_dirty(dir);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ec58bb2373fc86..7fa3313ab0e273 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -28,7 +28,7 @@
 	do {								\
 		if (unlikely(condition)) {				\
 			WARN_ON(1);					\
-			sbi->need_fsck = true;				\
+			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
 		}							\
 	} while (0)
 #define f2fs_down_write(x, y)	down_write(x)
@@ -100,10 +100,15 @@ enum {
 
 enum {
 	CP_UMOUNT,
+	CP_FASTBOOT,
 	CP_SYNC,
 	CP_DISCARD,
 };
 
+#define DEF_BATCHED_TRIM_SECTIONS	32
+#define BATCHED_TRIM_SEGMENTS(sbi)	\
+		(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+
 struct cp_control {
 	int reason;
 	__u64 trim_start;
@@ -136,8 +141,14 @@ struct ino_entry {
 	nid_t ino;		/* inode number */
 };
 
-/* for the list of directory inodes */
-struct dir_inode_entry {
+/*
+ * for the list of directory inodes or gc inodes.
+ * NOTE: there are two slab users for this structure, if we add/modify/delete
+ * fields in structure for one of slab users, it may affect fields or size of
+ * other one, in this condition, it's better to split both of slab and related
+ * data structure.
+ */
+struct inode_entry {
 	struct list_head list;	/* list head */
 	struct inode *inode;	/* vfs inode pointer */
 };
@@ -196,11 +207,14 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
  */
 #define F2FS_IOC_GETFLAGS		FS_IOC_GETFLAGS
 #define F2FS_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define F2FS_IOC_GETVERSION		FS_IOC_GETVERSION
 
 #define F2FS_IOCTL_MAGIC		0xf5
 #define F2FS_IOC_START_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 1)
 #define F2FS_IOC_COMMIT_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 2)
 #define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
+#define F2FS_IOC_RELEASE_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 4)
+#define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
@@ -295,7 +309,7 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
 	struct extent_info ext;		/* in-memory extent cache entry */
-	struct dir_inode_entry *dirty_dir;	/* the pointer of dirty dir */
+	struct inode_entry *dirty_dir;	/* the pointer of dirty dir */
 
 	struct radix_tree_root inmem_root;	/* radix tree for inmem pages */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
@@ -398,7 +412,8 @@ enum {
 	CURSEG_HOT_NODE,	/* direct node blocks of directory files */
 	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
 	CURSEG_COLD_NODE,	/* indirect node blocks */
-	NO_CHECK_TYPE
+	NO_CHECK_TYPE,
+	CURSEG_DIRECT_IO,	/* to use for the direct IO path */
 };
 
 struct flush_cmd {
@@ -437,6 +452,9 @@ struct f2fs_sm_info {
 	int nr_discards;			/* # of discards in the list */
 	int max_discards;			/* max. discards to be issued */
 
+	/* for batched trimming */
+	unsigned int trim_sections;		/* # of sections to trim */
+
 	struct list_head sit_entry_set;	/* sit entry set list */
 
 	unsigned int ipu_policy;	/* in-place-update policy */
@@ -489,6 +507,7 @@ enum page_type {
 struct f2fs_io_info {
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	int rw;			/* contains R/RS/W/WS with REQ_META/REQ_PRIO */
+	block_t blk_addr;	/* block address to be written */
 };
 
 #define is_read_io(rw)	(((rw) & 1) == READ)
@@ -508,13 +527,20 @@ struct inode_management {
 	unsigned long ino_num;			/* number of entries */
 };
 
+/* For s_flag in struct f2fs_sb_info */
+enum {
+	SBI_IS_DIRTY,				/* dirty flag for checkpoint */
+	SBI_IS_CLOSE,				/* specify unmounting */
+	SBI_NEED_FSCK,				/* need fsck.f2fs to fix */
+	SBI_POR_DOING,				/* recovery is doing or not */
+};
+
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
 	struct buffer_head *raw_super_buf;	/* buffer head of raw sb */
 	struct f2fs_super_block *raw_super;	/* raw super block pointer */
-	int s_dirty;				/* dirty flag for checkpoint */
-	bool need_fsck;				/* need fsck.f2fs to fix */
+	int s_flag;				/* flags for sbi */
 
 	/* for node-related operations */
 	struct f2fs_nm_info *nm_info;		/* node manager */
@@ -534,7 +560,6 @@ struct f2fs_sb_info {
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
 	struct mutex writepages;		/* mutex for writepages() */
-	bool por_doing;				/* recovery is doing or not */
 	wait_queue_head_t cp_wait;
 
 	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
@@ -589,6 +614,7 @@ struct f2fs_sb_info {
 	struct f2fs_stat_info *stat_info;	/* FS status information */
 	unsigned int segment_count[2];		/* # of allocated segments */
 	unsigned int block_count[2];		/* # of allocated blocks */
+	atomic_t inplace_count;		/* # of inplace update */
 	int total_hit_ext, read_hit_ext;	/* extent cache hit ratio */
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
@@ -686,14 +712,19 @@ static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
 	return sbi->node_inode->i_mapping;
 }
 
-static inline void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
 {
-	sbi->s_dirty = 1;
+	return sbi->s_flag & (0x01 << type);
 }
 
-static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
 {
-	sbi->s_dirty = 0;
+	sbi->s_flag |= (0x01 << type);
+}
+
+static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
+{
+	sbi->s_flag &= ~(0x01 << type);
 }
 
 static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
@@ -741,6 +772,28 @@ static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
 	up_write(&sbi->cp_rwsem);
 }
 
+static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
+{
+	int reason = CP_SYNC;
+
+	if (test_opt(sbi, FASTBOOT))
+		reason = CP_FASTBOOT;
+	if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
+		reason = CP_UMOUNT;
+	return reason;
+}
+
+static inline bool __remain_node_summaries(int reason)
+{
+	return (reason == CP_UMOUNT || reason == CP_FASTBOOT);
+}
+
+static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
+{
+	return (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) ||
+			is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FASTBOOT_FLAG));
+}
+
 /*
  * Check whether the given nid is within node id range.
  */
@@ -805,7 +858,7 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
 {
 	atomic_inc(&sbi->nr_pages[count_type]);
-	F2FS_SET_SB_DIRT(sbi);
+	set_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
 static inline void inode_inc_dirty_pages(struct inode *inode)
@@ -1113,6 +1166,7 @@ enum {
 	FI_NEED_IPU,		/* used for ipu per file */
 	FI_ATOMIC_FILE,		/* indicate atomic file */
 	FI_VOLATILE_FILE,	/* indicate volatile file */
+	FI_DROP_CACHE,		/* drop dirty page cache */
 	FI_DATA_EXIST,		/* indicate data exists */
 };
 
@@ -1220,6 +1274,11 @@ static inline bool f2fs_is_volatile_file(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
 }
 
+static inline bool f2fs_is_drop_cache(struct inode *inode)
+{
+	return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE);
+}
+
 static inline void *inline_data_addr(struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
@@ -1389,7 +1448,6 @@ void destroy_node_manager_caches(void);
  * segment.c
  */
 void register_inmem_page(struct inode *, struct page *);
-void invalidate_inmem_page(struct inode *, struct page *);
 void commit_inmem_pages(struct inode *, bool);
 void f2fs_balance_fs(struct f2fs_sb_info *);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
@@ -1401,16 +1459,16 @@ void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
 void clear_prefree_segments(struct f2fs_sb_info *);
 void release_discard_addrs(struct f2fs_sb_info *);
 void discard_next_dnode(struct f2fs_sb_info *, block_t);
-int npages_for_summary_flush(struct f2fs_sb_info *);
+int npages_for_summary_flush(struct f2fs_sb_info *, bool);
 void allocate_new_segments(struct f2fs_sb_info *);
 int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
 void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(struct f2fs_sb_info *, struct page *,
-		struct f2fs_io_info *, unsigned int, block_t, block_t *);
-void write_data_page(struct page *, struct dnode_of_data *, block_t *,
-					struct f2fs_io_info *);
-void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *);
+				unsigned int, struct f2fs_io_info *);
+void write_data_page(struct page *, struct dnode_of_data *,
+			struct f2fs_io_info *);
+void rewrite_data_page(struct page *, struct f2fs_io_info *);
 void recover_data_page(struct f2fs_sb_info *, struct page *,
 				struct f2fs_summary *, block_t, block_t);
 void allocate_data_block(struct f2fs_sb_info *, struct page *,
@@ -1457,17 +1515,20 @@ void destroy_checkpoint_caches(void);
  * data.c
  */
 void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, block_t, int);
-void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, block_t,
+int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *,
+						struct f2fs_io_info *);
+void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *,
 						struct f2fs_io_info *);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-void update_extent_cache(block_t, struct dnode_of_data *);
+void update_extent_cache(struct dnode_of_data *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct page *, struct f2fs_io_info *);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
+int f2fs_release_page(struct page *, gfp_t);
 
 /*
  * gc.c
@@ -1477,8 +1538,6 @@ void stop_gc_thread(struct f2fs_sb_info *);
 block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
 int f2fs_gc(struct f2fs_sb_info *);
 void build_gc_manager(struct f2fs_sb_info *);
-int __init create_gc_caches(void);
-void destroy_gc_caches(void);
 
 /*
  * recovery.c
@@ -1497,9 +1556,9 @@ struct f2fs_stat_info {
 	int main_area_segs, main_area_sections, main_area_zones;
 	int hit_ext, total_ext;
 	int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
-	int nats, sits, fnids;
+	int nats, dirty_nats, sits, dirty_sits, fnids;
 	int total_count, utilization;
-	int bg_gc, inline_inode, inline_dir, inmem_pages;
+	int bg_gc, inline_inode, inline_dir, inmem_pages, wb_pages;
 	unsigned int valid_count, valid_node_count, valid_inode_count;
 	unsigned int bimodal, avg_vblocks;
 	int util_free, util_valid, util_invalid;
@@ -1514,7 +1573,8 @@ struct f2fs_stat_info {
 
 	unsigned int segment_count[2];
 	unsigned int block_count[2];
-	unsigned base_mem, cache_mem;
+	unsigned int inplace_count;
+	unsigned base_mem, cache_mem, page_mem;
 };
 
 static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
@@ -1553,7 +1613,8 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		((sbi)->segment_count[(curseg)->alloc_type]++)
 #define stat_inc_block_count(sbi, curseg)				\
 		((sbi)->block_count[(curseg)->alloc_type]++)
-
+#define stat_inc_inplace_blocks(sbi)					\
+		(atomic_inc(&(sbi)->inplace_count))
 #define stat_inc_seg_count(sbi, type)					\
 	do {								\
 		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
@@ -1599,6 +1660,7 @@ void f2fs_destroy_root_stats(void);
 #define stat_dec_inline_dir(inode)
 #define stat_inc_seg_type(sbi, curseg)
 #define stat_inc_block_count(sbi, curseg)
+#define stat_inc_inplace_blocks(sbi)
 #define stat_inc_seg_count(si, type)
 #define stat_inc_tot_blk_count(si, blks)
 #define stat_inc_data_blk_count(si, blks)
@@ -1619,6 +1681,7 @@ extern const struct address_space_operations f2fs_meta_aops;
 extern const struct inode_operations f2fs_dir_inode_operations;
 extern const struct inode_operations f2fs_symlink_inode_operations;
 extern const struct inode_operations f2fs_special_inode_operations;
+extern struct kmem_cache *inode_entry_slab;
 
 /*
  * inline.c
@@ -1629,7 +1692,6 @@ int f2fs_read_inline_data(struct inode *, struct page *);
 int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
 int f2fs_convert_inline_inode(struct inode *);
 int f2fs_write_inline_data(struct inode *, struct page *);
-void truncate_inline_data(struct page *, u64);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *,
 							struct page **);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5674ba13102be9..98dac27bc3f733 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -26,6 +26,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "acl.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
@@ -245,6 +246,10 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 sync_nodes:
 	sync_node_pages(sbi, ino, &wbc);
 
+	/* if cp_error was enabled, we should avoid infinite loop */
+	if (unlikely(f2fs_cp_error(sbi)))
+		goto out;
+
 	if (need_inode_block_update(sbi, ino)) {
 		mark_inode_dirty_sync(inode);
 		f2fs_write_inode(inode, NULL);
@@ -264,6 +269,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	ret = f2fs_issue_flush(sbi);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+	f2fs_trace_ios(NULL, NULL, 1);
 	return ret;
 }
 
@@ -350,7 +356,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
 				dn.ofs_in_node++, pgofs++,
-				data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+				data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
 			block_t blkaddr;
 			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
 
@@ -426,7 +432,8 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		if (blkaddr == NULL_ADDR)
 			continue;
 
-		update_extent_cache(NULL_ADDR, dn);
+		dn->data_blkaddr = NULL_ADDR;
+		update_extent_cache(dn);
 		invalidate_blocks(sbi, blkaddr);
 		nr_free++;
 	}
@@ -483,8 +490,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
-	free_from = (pgoff_t)
-		((from + blocksize - 1) >> (sbi->log_blocksize));
+	free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
 
 	if (lock)
 		f2fs_lock_op(sbi);
@@ -835,6 +841,19 @@ static long f2fs_fallocate(struct file *file, int mode,
 	return ret;
 }
 
+static int f2fs_release_file(struct inode *inode, struct file *filp)
+{
+	/* some remained atomic pages should discarded */
+	if (f2fs_is_atomic_file(inode))
+		commit_inmem_pages(inode, true);
+	if (f2fs_is_volatile_file(inode)) {
+		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+		filemap_fdatawrite(inode->i_mapping);
+		clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+	}
+	return 0;
+}
+
 #define F2FS_REG_FLMASK		(~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
 #define F2FS_OTHER_FLMASK	(FS_NODUMP_FL | FS_NOATIME_FL)
 
@@ -905,29 +924,30 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 	return ret;
 }
 
+static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+
+	return put_user(inode->i_generation, (int __user *)arg);
+}
+
 static int f2fs_ioc_start_atomic_write(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(F2FS_I_SB(inode));
+
+	if (f2fs_is_atomic_file(inode))
+		return 0;
 
 	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 
 	return f2fs_convert_inline_inode(inode);
 }
 
-static int f2fs_release_file(struct inode *inode, struct file *filp)
-{
-	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
-		commit_inmem_pages(inode, true);
-	return 0;
-}
-
 static int f2fs_ioc_commit_atomic_write(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
@@ -948,6 +968,7 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 
 	ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
 	mnt_drop_write_file(filp);
+	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 	return ret;
 }
 
@@ -958,11 +979,56 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	if (f2fs_is_volatile_file(inode))
+		return 0;
+
 	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
 
 	return f2fs_convert_inline_inode(inode);
 }
 
+static int f2fs_ioc_release_volatile_write(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (!f2fs_is_volatile_file(inode))
+		return 0;
+
+	punch_hole(inode, 0, F2FS_BLKSIZE);
+	return 0;
+}
+
+static int f2fs_ioc_abort_volatile_write(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	int ret;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	f2fs_balance_fs(F2FS_I_SB(inode));
+
+	if (f2fs_is_atomic_file(inode)) {
+		commit_inmem_pages(inode, false);
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	}
+
+	if (f2fs_is_volatile_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+		filemap_fdatawrite(inode->i_mapping);
+		set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+	}
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
 static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -1000,12 +1066,18 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_getflags(filp, arg);
 	case F2FS_IOC_SETFLAGS:
 		return f2fs_ioc_setflags(filp, arg);
+	case F2FS_IOC_GETVERSION:
+		return f2fs_ioc_getversion(filp, arg);
 	case F2FS_IOC_START_ATOMIC_WRITE:
 		return f2fs_ioc_start_atomic_write(filp);
 	case F2FS_IOC_COMMIT_ATOMIC_WRITE:
 		return f2fs_ioc_commit_atomic_write(filp);
 	case F2FS_IOC_START_VOLATILE_WRITE:
 		return f2fs_ioc_start_volatile_write(filp);
+	case F2FS_IOC_RELEASE_VOLATILE_WRITE:
+		return f2fs_ioc_release_volatile_write(filp);
+	case F2FS_IOC_ABORT_VOLATILE_WRITE:
+		return f2fs_ioc_abort_volatile_write(filp);
 	case FITRIM:
 		return f2fs_ioc_fitrim(filp, arg);
 	default:
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index eec0933a481977..76adbc3641f153 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -24,8 +24,6 @@
 #include "gc.h"
 #include <trace/events/f2fs.h>
 
-static struct kmem_cache *winode_slab;
-
 static int gc_thread_func(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
@@ -46,7 +44,7 @@ static int gc_thread_func(void *data)
 			break;
 
 		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			continue;
 		}
 
@@ -67,15 +65,15 @@ static int gc_thread_func(void *data)
 			continue;
 
 		if (!is_idle(sbi)) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			mutex_unlock(&sbi->gc_mutex);
 			continue;
 		}
 
 		if (has_enough_invalid_blocks(sbi))
-			wait_ms = decrease_sleep_time(gc_th, wait_ms);
+			decrease_sleep_time(gc_th, &wait_ms);
 		else
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 
 		stat_inc_bggc_count(sbi);
 
@@ -356,13 +354,10 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
 		iput(inode);
 		return;
 	}
-	new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS);
+	new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
 	new_ie->inode = inode;
-retry:
-	if (radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie)) {
-		cond_resched();
-		goto retry;
-	}
+
+	f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
 	list_add_tail(&new_ie->list, &gc_list->ilist);
 }
 
@@ -373,7 +368,7 @@ static void put_gc_inode(struct gc_inode_list *gc_list)
 		radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
 		iput(ie->inode);
 		list_del(&ie->list);
-		kmem_cache_free(winode_slab, ie);
+		kmem_cache_free(inode_entry_slab, ie);
 	}
 }
 
@@ -703,8 +698,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
 		.iroot = RADIX_TREE_INIT(GFP_NOFS),
 	};
 
-	cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC;
-
+	cpc.reason = __get_cp_reason(sbi);
 gc_more:
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
@@ -750,17 +744,3 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
 {
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
 }
-
-int __init create_gc_caches(void)
-{
-	winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
-			sizeof(struct inode_entry));
-	if (!winode_slab)
-		return -ENOMEM;
-	return 0;
-}
-
-void destroy_gc_caches(void)
-{
-	kmem_cache_destroy(winode_slab);
-}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 6ff7ad38463e1d..b4a65be9f7d3fc 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -35,11 +35,6 @@ struct f2fs_gc_kthread {
 	unsigned int gc_idle;
 };
 
-struct inode_entry {
-	struct list_head list;
-	struct inode *inode;
-};
-
 struct gc_inode_list {
 	struct list_head ilist;
 	struct radix_tree_root iroot;
@@ -69,26 +64,26 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
 	return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
 }
 
-static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		return wait;
+	if (*wait == gc_th->no_gc_sleep_time)
+		return;
 
-	wait += gc_th->min_sleep_time;
-	if (wait > gc_th->max_sleep_time)
-		wait = gc_th->max_sleep_time;
-	return wait;
+	*wait += gc_th->min_sleep_time;
+	if (*wait > gc_th->max_sleep_time)
+		*wait = gc_th->max_sleep_time;
 }
 
-static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		wait = gc_th->max_sleep_time;
+	if (*wait == gc_th->no_gc_sleep_time)
+		*wait = gc_th->max_sleep_time;
 
-	wait -= gc_th->min_sleep_time;
-	if (wait <= gc_th->min_sleep_time)
-		wait = gc_th->min_sleep_time;
-	return wait;
+	*wait -= gc_th->min_sleep_time;
+	if (*wait <= gc_th->min_sleep_time)
+		*wait = gc_th->min_sleep_time;
 }
 
 static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index f2d3c581e7761b..1484c00133cd8e 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -50,6 +50,12 @@ void read_inline_data(struct page *page, struct page *ipage)
 	SetPageUptodate(page);
 }
 
+static void truncate_inline_data(struct page *ipage)
+{
+	f2fs_wait_on_page_writeback(ipage, NODE);
+	memset(inline_data_addr(ipage), 0, MAX_INLINE_DATA);
+}
+
 int f2fs_read_inline_data(struct inode *inode, struct page *page)
 {
 	struct page *ipage;
@@ -79,7 +85,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
 	void *src_addr, *dst_addr;
-	block_t new_blk_addr;
 	struct f2fs_io_info fio = {
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
@@ -115,9 +120,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
-
-	write_data_page(page, dn, &new_blk_addr, &fio);
-	update_extent_cache(new_blk_addr, dn);
+	fio.blk_addr = dn->data_blkaddr;
+	write_data_page(page, dn, &fio);
+	update_extent_cache(dn);
 	f2fs_wait_on_page_writeback(page, DATA);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
@@ -126,7 +131,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
 
 	/* clear inline data and flag after data writeback */
-	truncate_inline_data(dn->inode_page, 0);
+	truncate_inline_data(dn->inode_page);
 clear_out:
 	stat_dec_inline_inode(dn->inode);
 	f2fs_clear_inline_inode(dn->inode);
@@ -199,19 +204,6 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 	return 0;
 }
 
-void truncate_inline_data(struct page *ipage, u64 from)
-{
-	void *addr;
-
-	if (from >= MAX_INLINE_DATA)
-		return;
-
-	f2fs_wait_on_page_writeback(ipage, NODE);
-
-	addr = inline_data_addr(ipage);
-	memset(addr + from, 0, MAX_INLINE_DATA - from);
-}
-
 bool recover_inline_data(struct inode *inode, struct page *npage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -253,7 +245,7 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
-		truncate_inline_data(ipage, 0);
+		truncate_inline_data(ipage);
 		f2fs_clear_inline_inode(inode);
 		update_inode(inode, ipage);
 		f2fs_put_page(ipage, 1);
@@ -371,7 +363,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	set_page_dirty(page);
 
 	/* clear inline dir and flag after data writeback */
-	truncate_inline_data(ipage, 0);
+	truncate_inline_data(ipage);
 
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 196cc7843aaff5..2d002e3738a77b 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -67,29 +67,23 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
-static int __recover_inline_status(struct inode *inode, struct page *ipage)
+static void __recover_inline_status(struct inode *inode, struct page *ipage)
 {
 	void *inline_data = inline_data_addr(ipage);
-	struct f2fs_inode *ri;
-	void *zbuf;
+	__le32 *start = inline_data;
+	__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
 
-	zbuf = kzalloc(MAX_INLINE_DATA, GFP_NOFS);
-	if (!zbuf)
-		return -ENOMEM;
+	while (start < end) {
+		if (*start++) {
+			f2fs_wait_on_page_writeback(ipage, NODE);
 
-	if (!memcmp(zbuf, inline_data, MAX_INLINE_DATA)) {
-		kfree(zbuf);
-		return 0;
+			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
+			set_page_dirty(ipage);
+			return;
+		}
 	}
-	kfree(zbuf);
-
-	f2fs_wait_on_page_writeback(ipage, NODE);
-	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-
-	ri = F2FS_INODE(ipage);
-	set_raw_inline(F2FS_I(inode), ri);
-	set_page_dirty(ipage);
-	return 0;
+	return;
 }
 
 static int do_read_inode(struct inode *inode)
@@ -98,7 +92,6 @@ static int do_read_inode(struct inode *inode)
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct page *node_page;
 	struct f2fs_inode *ri;
-	int err = 0;
 
 	/* Check if ino is within scope */
 	if (check_nid_range(sbi, inode->i_ino)) {
@@ -142,7 +135,7 @@ static int do_read_inode(struct inode *inode)
 
 	/* check data exist */
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
-		err = __recover_inline_status(inode, node_page);
+		__recover_inline_status(inode, node_page);
 
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
@@ -152,7 +145,7 @@ static int do_read_inode(struct inode *inode)
 	stat_inc_inline_inode(inode);
 	stat_inc_inline_dir(inode);
 
-	return err;
+	return 0;
 }
 
 struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
@@ -304,7 +297,7 @@ void f2fs_evict_inode(struct inode *inode)
 	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 
 	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
+	if (f2fs_is_atomic_file(inode))
 		commit_inmem_pages(inode, true);
 
 	trace_f2fs_evict_inode(inode);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 547a2deeb1acaa..e79639a9787aab 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -299,7 +299,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_op = &f2fs_dir_inode_operations;
 	inode->i_fop = &f2fs_dir_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 
 	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
 	f2fs_lock_op(sbi);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index f83326ca32eff4..97bd9d3db88285 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -19,6 +19,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 #define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock)
@@ -57,12 +58,13 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	} else if (type == INO_ENTRIES) {
 		int i;
 
-		if (sbi->sb->s_bdi->dirty_exceeded)
-			return false;
 		for (i = 0; i <= UPDATE_INO; i++)
 			mem_size += (sbi->im[i].ino_num *
 				sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+	} else {
+		if (sbi->sb->s_bdi->dirty_exceeded)
+			return false;
 	}
 	return res;
 }
@@ -268,7 +270,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 	e = __lookup_nat_cache(nm_i, ni->nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, ni->nid);
-		e->ni = *ni;
+		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
 	} else if (new_blkaddr == NEW_ADDR) {
 		/*
@@ -276,7 +278,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 		 * previous nat entry can be remained in nat cache.
 		 * So, reinitialize it with new information.
 		 */
-		e->ni = *ni;
+		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
 	}
 
@@ -346,7 +348,6 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	struct nat_entry *e;
 	int i;
 
-	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 	ni->nid = nid;
 
 	/* Check nat cache */
@@ -361,6 +362,8 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	if (e)
 		return;
 
+	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
+
 	/* Check current segment summary */
 	mutex_lock(&curseg->curseg_mutex);
 	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
@@ -471,7 +474,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct page *npage[4];
-	struct page *parent;
+	struct page *parent = NULL;
 	int offset[4];
 	unsigned int noffset[4];
 	nid_t nids[4];
@@ -488,6 +491,14 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 		if (IS_ERR(npage[0]))
 			return PTR_ERR(npage[0]);
 	}
+
+	/* if inline_data is set, should not report any block indices */
+	if (f2fs_has_inline_data(dn->inode) && index) {
+		err = -EINVAL;
+		f2fs_put_page(npage[0], 1);
+		goto release_out;
+	}
+
 	parent = npage[0];
 	if (level != 0)
 		nids[1] = get_nid(parent, offset[0], true);
@@ -585,7 +596,7 @@ static void truncate_node(struct dnode_of_data *dn)
 	}
 invalidate:
 	clear_node_page_dirty(dn->node_page);
-	F2FS_SET_SB_DIRT(sbi);
+	set_sbi_flag(sbi, SBI_IS_DIRTY);
 
 	f2fs_put_page(dn->node_page, 1);
 
@@ -976,6 +987,10 @@ static int read_node_page(struct page *page, int rw)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	struct node_info ni;
+	struct f2fs_io_info fio = {
+		.type = NODE,
+		.rw = rw,
+	};
 
 	get_node_info(sbi, page->index, &ni);
 
@@ -987,7 +1002,8 @@ static int read_node_page(struct page *page, int rw)
 	if (PageUptodate(page))
 		return LOCKED_PAGE;
 
-	return f2fs_submit_page_bio(sbi, page, ni.blk_addr, rw);
+	fio.blk_addr = ni.blk_addr;
+	return f2fs_submit_page_bio(sbi, page, &fio);
 }
 
 /*
@@ -1028,11 +1044,11 @@ struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
 	err = read_node_page(page, READ_SYNC);
 	if (err < 0)
 		return ERR_PTR(err);
-	else if (err == LOCKED_PAGE)
-		goto got_it;
+	else if (err != LOCKED_PAGE)
+		lock_page(page);
 
-	lock_page(page);
 	if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) {
+		ClearPageUptodate(page);
 		f2fs_put_page(page, 1);
 		return ERR_PTR(-EIO);
 	}
@@ -1040,7 +1056,6 @@ struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
-got_it:
 	return page;
 }
 
@@ -1268,7 +1283,6 @@ static int f2fs_write_node_page(struct page *page,
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	nid_t nid;
-	block_t new_addr;
 	struct node_info ni;
 	struct f2fs_io_info fio = {
 		.type = NODE,
@@ -1277,7 +1291,7 @@ static int f2fs_write_node_page(struct page *page,
 
 	trace_f2fs_writepage(page, NODE);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
@@ -1303,9 +1317,11 @@ static int f2fs_write_node_page(struct page *page,
 	} else {
 		down_read(&sbi->node_write);
 	}
+
 	set_page_writeback(page);
-	write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr);
-	set_node_addr(sbi, &ni, new_addr, is_fsync_dnode(page));
+	fio.blk_addr = ni.blk_addr;
+	write_node_page(sbi, page, nid, &fio);
+	set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
 	up_read(&sbi->node_write);
 	unlock_page(page);
@@ -1355,26 +1371,12 @@ static int f2fs_set_node_page_dirty(struct page *page)
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
 		SetPagePrivate(page);
+		f2fs_trace_pid(page);
 		return 1;
 	}
 	return 0;
 }
 
-static void f2fs_invalidate_node_page(struct page *page, unsigned int offset,
-				      unsigned int length)
-{
-	struct inode *inode = page->mapping->host;
-	if (PageDirty(page))
-		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_NODES);
-	ClearPagePrivate(page);
-}
-
-static int f2fs_release_node_page(struct page *page, gfp_t wait)
-{
-	ClearPagePrivate(page);
-	return 1;
-}
-
 /*
  * Structure of the f2fs node operations
  */
@@ -1382,8 +1384,8 @@ const struct address_space_operations f2fs_node_aops = {
 	.writepage	= f2fs_write_node_page,
 	.writepages	= f2fs_write_node_pages,
 	.set_page_dirty	= f2fs_set_node_page_dirty,
-	.invalidatepage	= f2fs_invalidate_node_page,
-	.releasepage	= f2fs_release_node_page,
+	.invalidatepage	= f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 };
 
 static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
@@ -1726,80 +1728,41 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	return 0;
 }
 
-/*
- * ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-read pages are allocated in bd_inode's mapping tree.
- */
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
-				int start, int nrpages)
-{
-	struct inode *inode = sbi->sb->s_bdev->bd_inode;
-	struct address_space *mapping = inode->i_mapping;
-	int i, page_idx = start;
-	struct f2fs_io_info fio = {
-		.type = META,
-		.rw = READ_SYNC | REQ_META | REQ_PRIO
-	};
-
-	for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
-		/* alloc page in bd_inode for reading node summary info */
-		pages[i] = grab_cache_page(mapping, page_idx);
-		if (!pages[i])
-			break;
-		f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
-	}
-
-	f2fs_submit_merged_bio(sbi, META, READ);
-	return i;
-}
-
 int restore_node_summary(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct f2fs_summary_block *sum)
 {
 	struct f2fs_node *rn;
 	struct f2fs_summary *sum_entry;
-	struct inode *inode = sbi->sb->s_bdev->bd_inode;
 	block_t addr;
 	int bio_blocks = MAX_BIO_BLOCKS(sbi);
-	struct page *pages[bio_blocks];
-	int i, idx, last_offset, nrpages, err = 0;
+	int i, idx, last_offset, nrpages;
 
 	/* scan the node segment */
 	last_offset = sbi->blocks_per_seg;
 	addr = START_BLOCK(sbi, segno);
 	sum_entry = &sum->entries[0];
 
-	for (i = 0; !err && i < last_offset; i += nrpages, addr += nrpages) {
+	for (i = 0; i < last_offset; i += nrpages, addr += nrpages) {
 		nrpages = min(last_offset - i, bio_blocks);
 
 		/* readahead node pages */
-		nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
-		if (!nrpages)
-			return -ENOMEM;
+		ra_meta_pages(sbi, addr, nrpages, META_POR);
 
-		for (idx = 0; idx < nrpages; idx++) {
-			if (err)
-				goto skip;
+		for (idx = addr; idx < addr + nrpages; idx++) {
+			struct page *page = get_meta_page(sbi, idx);
 
-			lock_page(pages[idx]);
-			if (unlikely(!PageUptodate(pages[idx]))) {
-				err = -EIO;
-			} else {
-				rn = F2FS_NODE(pages[idx]);
-				sum_entry->nid = rn->footer.nid;
-				sum_entry->version = 0;
-				sum_entry->ofs_in_node = 0;
-				sum_entry++;
-			}
-			unlock_page(pages[idx]);
-skip:
-			page_cache_release(pages[idx]);
+			rn = F2FS_NODE(page);
+			sum_entry->nid = rn->footer.nid;
+			sum_entry->version = 0;
+			sum_entry->ofs_in_node = 0;
+			sum_entry++;
+			f2fs_put_page(page, 1);
 		}
 
-		invalidate_mapping_pages(inode->i_mapping, addr,
+		invalidate_mapping_pages(META_MAPPING(sbi), addr,
 							addr + nrpages);
 	}
-	return err;
+	return 0;
 }
 
 static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
@@ -1923,7 +1886,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
 	struct f2fs_summary_block *sum = curseg->sum_blk;
-	struct nat_entry_set *setvec[NATVEC_SIZE];
+	struct nat_entry_set *setvec[SETVEC_SIZE];
 	struct nat_entry_set *set, *tmp;
 	unsigned int found;
 	nid_t set_idx = 0;
@@ -1940,7 +1903,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
-					set_idx, NATVEC_SIZE, setvec))) {
+					set_idx, SETVEC_SIZE, setvec))) {
 		unsigned idx;
 		set_idx = setvec[found - 1]->set + 1;
 		for (idx = 0; idx < found; idx++)
@@ -2020,6 +1983,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i, *next_i;
 	struct nat_entry *natvec[NATVEC_SIZE];
+	struct nat_entry_set *setvec[SETVEC_SIZE];
 	nid_t nid = 0;
 	unsigned int found;
 
@@ -2044,11 +2008,27 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	while ((found = __gang_lookup_nat_cache(nm_i,
 					nid, NATVEC_SIZE, natvec))) {
 		unsigned idx;
+
 		nid = nat_get_nid(natvec[found - 1]) + 1;
 		for (idx = 0; idx < found; idx++)
 			__del_from_nat_cache(nm_i, natvec[idx]);
 	}
 	f2fs_bug_on(sbi, nm_i->nat_cnt);
+
+	/* destroy nat set cache */
+	nid = 0;
+	while ((found = __gang_lookup_nat_set(nm_i,
+					nid, SETVEC_SIZE, setvec))) {
+		unsigned idx;
+
+		nid = setvec[found - 1]->set + 1;
+		for (idx = 0; idx < found; idx++) {
+			/* entry_cnt is not zero, when cp_error was occurred */
+			f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list));
+			radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set);
+			kmem_cache_free(nat_entry_set_slab, setvec[idx]);
+		}
+	}
 	up_write(&nm_i->nat_tree_lock);
 
 	kfree(nm_i->nat_bitmap);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index d10b6448a671fc..f405bbf2435a50 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -25,10 +25,19 @@
 
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
+#define SETVEC_SIZE	32
 
 /* return value for read_node_page */
 #define LOCKED_PAGE	1
 
+/* For flag in struct node_info */
+enum {
+	IS_CHECKPOINTED,	/* is it checkpointed before? */
+	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
+	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
+	IS_DIRTY,		/* this nat entry is dirty? */
+};
+
 /*
  * For node information
  */
@@ -37,18 +46,11 @@ struct node_info {
 	nid_t ino;		/* inode number of the node's owner */
 	block_t	blk_addr;	/* block address of the node */
 	unsigned char version;	/* version of the node */
-};
-
-enum {
-	IS_CHECKPOINTED,	/* is it checkpointed before? */
-	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
-	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
-	IS_DIRTY,		/* this nat entry is dirty? */
+	unsigned char flag;	/* for node information bits */
 };
 
 struct nat_entry {
 	struct list_head list;	/* for clean or dirty nat list */
-	unsigned char flag;	/* for node information bits */
 	struct node_info ni;	/* in-memory node information */
 };
 
@@ -63,20 +65,30 @@ struct nat_entry {
 
 #define inc_node_version(version)	(++version)
 
+static inline void copy_node_info(struct node_info *dst,
+						struct node_info *src)
+{
+	dst->nid = src->nid;
+	dst->ino = src->ino;
+	dst->blk_addr = src->blk_addr;
+	dst->version = src->version;
+	/* should not copy flag here */
+}
+
 static inline void set_nat_flag(struct nat_entry *ne,
 				unsigned int type, bool set)
 {
 	unsigned char mask = 0x01 << type;
 	if (set)
-		ne->flag |= mask;
+		ne->ni.flag |= mask;
 	else
-		ne->flag &= ~mask;
+		ne->ni.flag &= ~mask;
 }
 
 static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
 {
 	unsigned char mask = 0x01 << type;
-	return ne->flag & mask;
+	return ne->ni.flag & mask;
 }
 
 static inline void nat_reset_flag(struct nat_entry *ne)
@@ -108,6 +120,7 @@ enum mem_type {
 	NAT_ENTRIES,	/* indicates the cached nat entry */
 	DIRTY_DENTS,	/* indicates dirty dentry pages */
 	INO_ENTRIES,	/* indicates inode entries */
+	BASE_CHECK,	/* check kernel status */
 };
 
 struct nat_entry_set {
@@ -200,11 +213,19 @@ static inline void fill_node_footer(struct page *page, nid_t nid,
 				nid_t ino, unsigned int ofs, bool reset)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);
+	unsigned int old_flag = 0;
+
 	if (reset)
 		memset(rn, 0, sizeof(*rn));
+	else
+		old_flag = le32_to_cpu(rn->footer.flag);
+
 	rn->footer.nid = cpu_to_le32(nid);
 	rn->footer.ino = cpu_to_le32(ino);
-	rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
+
+	/* should remain old flag bits such as COLD_BIT_SHIFT */
+	rn->footer.flag = cpu_to_le32((ofs << OFFSET_BIT_SHIFT) |
+					(old_flag & OFFSET_BIT_MASK));
 }
 
 static inline void copy_node_footer(struct page *dst, struct page *src)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 9160a37e1c7a40..41afb9534bbdcb 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -346,6 +346,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
+		/*
+		 * Deprecated; xattr blocks should be found from cold log.
+		 * But, we should remain this for backward compatibility.
+		 */
 		recover_xattr_data(inode, page, blkaddr);
 		goto out;
 	}
@@ -396,7 +400,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			/* write dummy data page */
 			recover_data_page(sbi, NULL, &sum, src, dest);
-			update_extent_cache(dest, &dn);
+			dn.data_blkaddr = dest;
+			update_extent_cache(&dn);
 			recovered++;
 		}
 		dn.ofs_in_node++;
@@ -503,7 +508,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 	INIT_LIST_HEAD(&inode_list);
 
 	/* step #1: find fsynced inode numbers */
-	sbi->por_doing = true;
+	set_sbi_flag(sbi, SBI_POR_DOING);
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
@@ -536,7 +541,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 		truncate_inode_pages_final(META_MAPPING(sbi));
 	}
 
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	if (err) {
 		discard_next_dnode(sbi, blkaddr);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 42607a67992335..daee4ab913daf2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -20,6 +20,7 @@
 #include "f2fs.h"
 #include "segment.h"
 #include "node.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 #define __reverse_ffz(x) __reverse_ffs(~(x))
@@ -181,6 +182,7 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	int err;
 
 	SetPagePrivate(page);
+	f2fs_trace_pid(page);
 
 	new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
 
@@ -205,23 +207,6 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	mutex_unlock(&fi->inmem_lock);
 }
 
-void invalidate_inmem_page(struct inode *inode, struct page *page)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct inmem_pages *cur;
-
-	mutex_lock(&fi->inmem_lock);
-	cur = radix_tree_lookup(&fi->inmem_root, page->index);
-	if (cur) {
-		radix_tree_delete(&fi->inmem_root, cur->page->index);
-		f2fs_put_page(cur->page, 0);
-		list_del(&cur->list);
-		kmem_cache_free(inmem_entry_slab, cur);
-		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
-	}
-	mutex_unlock(&fi->inmem_lock);
-}
-
 void commit_inmem_pages(struct inode *inode, bool abort)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -230,7 +215,7 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	bool submit_bio = false;
 	struct f2fs_io_info fio = {
 		.type = DATA,
-		.rw = WRITE_SYNC,
+		.rw = WRITE_SYNC | REQ_PRIO,
 	};
 
 	/*
@@ -240,33 +225,38 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	 * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
 	 * inode becomes free by iget_locked in f2fs_iget.
 	 */
-	if (!abort)
+	if (!abort) {
 		f2fs_balance_fs(sbi);
-
-	f2fs_lock_op(sbi);
+		f2fs_lock_op(sbi);
+	}
 
 	mutex_lock(&fi->inmem_lock);
 	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
-		lock_page(cur->page);
-		if (!abort && cur->page->mapping == inode->i_mapping) {
-			f2fs_wait_on_page_writeback(cur->page, DATA);
-			if (clear_page_dirty_for_io(cur->page))
-				inode_dec_dirty_pages(inode);
-			do_write_data_page(cur->page, &fio);
-			submit_bio = true;
+		if (!abort) {
+			lock_page(cur->page);
+			if (cur->page->mapping == inode->i_mapping) {
+				f2fs_wait_on_page_writeback(cur->page, DATA);
+				if (clear_page_dirty_for_io(cur->page))
+					inode_dec_dirty_pages(inode);
+				do_write_data_page(cur->page, &fio);
+				submit_bio = true;
+			}
+			f2fs_put_page(cur->page, 1);
+		} else {
+			put_page(cur->page);
 		}
 		radix_tree_delete(&fi->inmem_root, cur->page->index);
-		f2fs_put_page(cur->page, 1);
 		list_del(&cur->list);
 		kmem_cache_free(inmem_entry_slab, cur);
 		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
 	}
-	if (submit_bio)
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
 	mutex_unlock(&fi->inmem_lock);
 
-	filemap_fdatawait_range(inode->i_mapping, 0, LLONG_MAX);
-	f2fs_unlock_op(sbi);
+	if (!abort) {
+		f2fs_unlock_op(sbi);
+		if (submit_bio)
+			f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	}
 }
 
 /*
@@ -290,7 +280,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	/* check the # of cached NAT entries and prefree segments */
 	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
 			excess_prefree_segs(sbi) ||
-			available_free_memory(sbi, INO_ENTRIES))
+			!available_free_memory(sbi, INO_ENTRIES))
 		f2fs_sync_fs(sbi->sb, true);
 }
 
@@ -515,12 +505,13 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
-	unsigned long dmap[entries];
+	unsigned long *dmap = SIT_I(sbi)->tmp_map;
 	unsigned int start = 0, end = -1;
 	bool force = (cpc->reason == CP_DISCARD);
 	int i;
 
-	if (!force && !test_opt(sbi, DISCARD))
+	if (!force && (!test_opt(sbi, DISCARD) ||
+			SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards))
 		return;
 
 	if (force && !se->valid_blocks) {
@@ -548,7 +539,8 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
 	for (i = 0; i < entries; i++)
-		dmap[i] = ~(cur_map[i] | ckpt_map[i]);
+		dmap[i] = force ? ~ckpt_map[i] :
+				(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
 	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
 		start = __find_rev_next_bit(dmap, max_blocks, end + 1);
@@ -735,7 +727,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
 /*
  * Calculate the number of current summary pages for writing
  */
-int npages_for_summary_flush(struct f2fs_sb_info *sbi)
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
 {
 	int valid_sum_count = 0;
 	int i, sum_in_page;
@@ -743,8 +735,13 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi)
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		if (sbi->ckpt->alloc_type[i] == SSR)
 			valid_sum_count += sbi->blocks_per_seg;
-		else
-			valid_sum_count += curseg_blkoff(sbi, i);
+		else {
+			if (for_ra)
+				valid_sum_count += le16_to_cpu(
+					F2FS_CKPT(sbi)->cur_data_blkoff[i]);
+			else
+				valid_sum_count += curseg_blkoff(sbi, i);
+		}
 	}
 
 	sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
@@ -803,7 +800,7 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	int go_left = 0;
 	int i;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
@@ -876,7 +873,7 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
 	__set_inuse(sbi, segno);
 	*newseg = segno;
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
@@ -927,7 +924,7 @@ static void __next_free_blkoff(struct f2fs_sb_info *sbi,
 {
 	struct seg_entry *se = get_seg_entry(sbi, seg->segno);
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
-	unsigned long target_map[entries];
+	unsigned long *target_map = SIT_I(sbi)->tmp_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	int i, pos;
@@ -1027,18 +1024,22 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	stat_inc_seg_type(sbi, curseg);
 }
 
+static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned int old_segno;
+
+	old_segno = curseg->segno;
+	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
+	locate_dirty_segment(sbi, old_segno);
+}
+
 void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
-	struct curseg_info *curseg;
-	unsigned int old_curseg;
 	int i;
 
-	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
-		curseg = CURSEG_I(sbi, i);
-		old_curseg = curseg->segno;
-		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
-		locate_dirty_segment(sbi, old_curseg);
-	}
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
+		__allocate_new_segments(sbi, i);
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -1047,8 +1048,8 @@ static const struct segment_allocation default_salloc_ops = {
 
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 {
-	__u64 start = range->start >> sbi->log_blocksize;
-	__u64 end = start + (range->len >> sbi->log_blocksize) - 1;
+	__u64 start = F2FS_BYTES_TO_BLK(range->start);
+	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
 
@@ -1065,16 +1066,21 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
 						GET_SEGNO(sbi, end);
 	cpc.reason = CP_DISCARD;
-	cpc.trim_start = start_segno;
-	cpc.trim_end = end_segno;
-	cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
+	cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen);
 
 	/* do checkpoint to issue discard commands safely */
-	mutex_lock(&sbi->gc_mutex);
-	write_checkpoint(sbi, &cpc);
-	mutex_unlock(&sbi->gc_mutex);
+	for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
+		cpc.trim_start = start_segno;
+		cpc.trim_end = min_t(unsigned int, rounddown(start_segno +
+				BATCHED_TRIM_SEGMENTS(sbi),
+				sbi->segs_per_sec) - 1, end_segno);
+
+		mutex_lock(&sbi->gc_mutex);
+		write_checkpoint(sbi, &cpc);
+		mutex_unlock(&sbi->gc_mutex);
+	}
 out:
-	range->len = cpc.trimmed << sbi->log_blocksize;
+	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
 	return 0;
 }
 
@@ -1151,11 +1157,18 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
+	bool direct_io = (type == CURSEG_DIRECT_IO);
+
+	type = direct_io ? CURSEG_WARM_DATA : type;
 
 	curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
 
+	/* direct_io'ed data is aligned to the segment for better performance */
+	if (direct_io && curseg->next_blkoff)
+		__allocate_new_segments(sbi, type);
+
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	/*
@@ -1187,39 +1200,39 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 }
 
 static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
-			block_t old_blkaddr, block_t *new_blkaddr,
-			struct f2fs_summary *sum, struct f2fs_io_info *fio)
+			struct f2fs_summary *sum,
+			struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(page, fio->type);
 
-	allocate_data_block(sbi, page, old_blkaddr, new_blkaddr, sum, type);
+	allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type);
 
 	/* writeout dirty page into bdev */
-	f2fs_submit_page_mbio(sbi, page, *new_blkaddr, fio);
+	f2fs_submit_page_mbio(sbi, page, fio);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 {
 	struct f2fs_io_info fio = {
 		.type = META,
-		.rw = WRITE_SYNC | REQ_META | REQ_PRIO
+		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
+		.blk_addr = page->index,
 	};
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(sbi, page, page->index, &fio);
+	f2fs_submit_page_mbio(sbi, page, &fio);
 }
 
 void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
-		struct f2fs_io_info *fio,
-		unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
+			unsigned int nid, struct f2fs_io_info *fio)
 {
 	struct f2fs_summary sum;
 	set_summary(&sum, nid, 0, 0);
-	do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, fio);
+	do_write_page(sbi, page, &sum, fio);
 }
 
 void write_data_page(struct page *page, struct dnode_of_data *dn,
-		block_t *new_blkaddr, struct f2fs_io_info *fio)
+				struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
@@ -1228,14 +1241,14 @@ void write_data_page(struct page *page, struct dnode_of_data *dn,
 	f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
-
-	do_write_page(sbi, page, dn->data_blkaddr, new_blkaddr, &sum, fio);
+	do_write_page(sbi, page, &sum, fio);
+	dn->data_blkaddr = fio->blk_addr;
 }
 
-void rewrite_data_page(struct page *page, block_t old_blkaddr,
-					struct f2fs_io_info *fio)
+void rewrite_data_page(struct page *page, struct f2fs_io_info *fio)
 {
-	f2fs_submit_page_mbio(F2FS_P_SB(page), page, old_blkaddr, fio);
+	stat_inc_inplace_blocks(F2FS_P_SB(page));
+	f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio);
 }
 
 void recover_data_page(struct f2fs_sb_info *sbi,
@@ -1393,7 +1406,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 		segno = le32_to_cpu(ckpt->cur_data_segno[type]);
 		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
 							CURSEG_HOT_DATA]);
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+		if (__exist_node_summaries(sbi))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
 		else
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
@@ -1402,7 +1415,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 							CURSEG_HOT_NODE]);
 		blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
 							CURSEG_HOT_NODE]);
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+		if (__exist_node_summaries(sbi))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
 							type - CURSEG_HOT_NODE);
 		else
@@ -1413,7 +1426,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	sum = (struct f2fs_summary_block *)page_address(new);
 
 	if (IS_NODESEG(type)) {
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
+		if (__exist_node_summaries(sbi)) {
 			struct f2fs_summary *ns = &sum->entries[0];
 			int i;
 			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
@@ -1450,12 +1463,22 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 	int err;
 
 	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
+		int npages = npages_for_summary_flush(sbi, true);
+
+		if (npages >= 2)
+			ra_meta_pages(sbi, start_sum_block(sbi), npages,
+								META_CP);
+
 		/* restore for compacted data summary */
 		if (read_compacted_summaries(sbi))
 			return -EINVAL;
 		type = CURSEG_HOT_NODE;
 	}
 
+	if (__exist_node_summaries(sbi))
+		ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
+					NR_CURSEG_TYPE - type, META_CP);
+
 	for (; type <= CURSEG_COLD_NODE; type++) {
 		err = read_normal_summaries(sbi, type);
 		if (err)
@@ -1549,8 +1572,7 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 
 void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 {
-	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
-		write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
+	write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 }
 
 int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
@@ -1754,7 +1776,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			se = get_seg_entry(sbi, segno);
 
 			/* add discard candidates */
-			if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards) {
+			if (cpc->reason != CP_DISCARD) {
 				cpc->trim_start = segno;
 				add_discard_addrs(sbi, cpc);
 			}
@@ -1833,6 +1855,10 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 			return -ENOMEM;
 	}
 
+	sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+	if (!sit_i->tmp_map)
+		return -ENOMEM;
+
 	if (sbi->segs_per_sec > 1) {
 		sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) *
 					sizeof(struct sec_entry));
@@ -1897,7 +1923,7 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
 	free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi));
 	free_i->free_segments = 0;
 	free_i->free_sections = 0;
-	rwlock_init(&free_i->segmap_lock);
+	spin_lock_init(&free_i->segmap_lock);
 	return 0;
 }
 
@@ -2110,6 +2136,8 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->nr_discards = 0;
 	sm_info->max_discards = 0;
 
+	sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
+
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
 	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
@@ -2212,6 +2240,8 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 			kfree(sit_i->sentries[start].ckpt_valid_map);
 		}
 	}
+	kfree(sit_i->tmp_map);
+
 	vfree(sit_i->sentries);
 	vfree(sit_i->sec_entries);
 	kfree(sit_i->dirty_sentries_bitmap);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 7f327c0ba4e32c..7fd35111cf6241 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -189,6 +189,7 @@ struct sit_info {
 	char *sit_bitmap;		/* SIT bitmap pointer */
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
+	unsigned long *tmp_map;			/* bitmap for temporal use */
 	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
 	unsigned int dirty_sentries;		/* # of dirty sentries */
 	unsigned int sents_per_block;		/* # of SIT entries per block */
@@ -207,7 +208,7 @@ struct free_segmap_info {
 	unsigned int start_segno;	/* start segment number logically */
 	unsigned int free_segments;	/* # of free segments */
 	unsigned int free_sections;	/* # of free sections */
-	rwlock_t segmap_lock;		/* free segmap lock */
+	spinlock_t segmap_lock;		/* free segmap lock */
 	unsigned long *free_segmap;	/* free segment bitmap */
 	unsigned long *free_secmap;	/* free section bitmap */
 };
@@ -318,9 +319,9 @@ static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
 		unsigned int max, unsigned int segno)
 {
 	unsigned int ret;
-	read_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	ret = find_next_bit(free_i->free_segmap, max, segno);
-	read_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 	return ret;
 }
 
@@ -331,7 +332,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
 	free_i->free_segments++;
 
@@ -340,7 +341,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_inuse(struct f2fs_sb_info *sbi,
@@ -362,7 +363,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (test_and_clear_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments++;
 
@@ -373,7 +374,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 				free_i->free_sections++;
 		}
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
@@ -381,13 +382,13 @@ static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int secno = segno / sbi->segs_per_sec;
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (!test_and_set_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments--;
 		if (!test_and_set_bit(secno, free_i->free_secmap))
 			free_i->free_sections--;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
@@ -460,7 +461,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
 	return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
@@ -599,13 +600,13 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
 {
 	if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi))
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 /*
@@ -616,11 +617,11 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 {
 	/* check segment usage */
 	if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	/* check boundary of a given segment number */
 	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 #endif
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f71421d7047525..f2fe666a6ea995 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -30,6 +30,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "gc.h"
+#include "trace.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/f2fs.h>
@@ -41,6 +42,7 @@ static struct kset *f2fs_kset;
 enum {
 	Opt_gc_background,
 	Opt_disable_roll_forward,
+	Opt_norecovery,
 	Opt_discard,
 	Opt_noheap,
 	Opt_user_xattr,
@@ -61,6 +63,7 @@ enum {
 static match_table_t f2fs_tokens = {
 	{Opt_gc_background, "background_gc=%s"},
 	{Opt_disable_roll_forward, "disable_roll_forward"},
+	{Opt_norecovery, "norecovery"},
 	{Opt_discard, "discard"},
 	{Opt_noheap, "no_heap"},
 	{Opt_user_xattr, "user_xattr"},
@@ -192,6 +195,7 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
@@ -207,6 +211,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(gc_idle),
 	ATTR_LIST(reclaim_segments),
 	ATTR_LIST(max_small_discards),
+	ATTR_LIST(batched_trim_sections),
 	ATTR_LIST(ipu_policy),
 	ATTR_LIST(min_ipu_util),
 	ATTR_LIST(min_fsync_blocks),
@@ -286,6 +291,12 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_disable_roll_forward:
 			set_opt(sbi, DISABLE_ROLL_FORWARD);
 			break;
+		case Opt_norecovery:
+			/* this option mounts f2fs with ro */
+			set_opt(sbi, DISABLE_ROLL_FORWARD);
+			if (!f2fs_readonly(sb))
+				return -EINVAL;
+			break;
 		case Opt_discard:
 			set_opt(sbi, DISCARD);
 			break;
@@ -446,8 +457,13 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_stats(sbi);
 	stop_gc_thread(sbi);
 
-	/* We don't need to do checkpoint when it's clean */
-	if (sbi->s_dirty) {
+	/*
+	 * We don't need to do checkpoint when superblock is clean.
+	 * But, the previous checkpoint was not done by umount, it needs to do
+	 * clean checkpoint again.
+	 */
+	if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+			!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) {
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT,
 		};
@@ -486,13 +502,15 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 	if (sync) {
 		struct cp_control cpc;
 
-		cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC;
+		cpc.reason = __get_cp_reason(sbi);
+
 		mutex_lock(&sbi->gc_mutex);
 		write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
 	} else {
 		f2fs_balance_fs(sbi);
 	}
+	f2fs_trace_ios(NULL, NULL, 1);
 
 	return 0;
 }
@@ -887,7 +905,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 		atomic_set(&sbi->nr_pages[i], 0);
 
 	sbi->dir_level = DEF_DIR_LEVEL;
-	sbi->need_fsck = false;
+	clear_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 /*
@@ -942,6 +960,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *root;
 	long err = -EINVAL;
 	bool retry = true;
+	char *options = NULL;
 	int i;
 
 try_onemore:
@@ -973,9 +992,15 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	set_opt(sbi, POSIX_ACL);
 #endif
 	/* parse mount options */
-	err = parse_options(sb, (char *)data);
-	if (err)
+	options = kstrdup((const char *)data, GFP_KERNEL);
+	if (data && !options) {
+		err = -ENOMEM;
 		goto free_sb_buf;
+	}
+
+	err = parse_options(sb, options);
+	if (err)
+		goto free_options;
 
 	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
 	sb->s_max_links = F2FS_LINK_MAX;
@@ -998,7 +1023,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	spin_lock_init(&sbi->stat_lock);
 
 	init_rwsem(&sbi->read_io.io_rwsem);
@@ -1019,7 +1044,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (IS_ERR(sbi->meta_inode)) {
 		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
 		err = PTR_ERR(sbi->meta_inode);
-		goto free_sb_buf;
+		goto free_options;
 	}
 
 	err = get_valid_checkpoint(sbi);
@@ -1122,10 +1147,19 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_proc;
 
 	if (!retry)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	/* recover fsynced data */
 	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+		/*
+		 * mount should be failed, when device has readonly mode, and
+		 * previous checkpoint was not done by clean system shutdown.
+		 */
+		if (bdev_read_only(sb->s_bdev) &&
+				!is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
+			err = -EROFS;
+			goto free_kobj;
+		}
 		err = recover_fsync_data(sbi);
 		if (err) {
 			f2fs_msg(sb, KERN_ERR,
@@ -1144,6 +1178,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		if (err)
 			goto free_kobj;
 	}
+	kfree(options);
 	return 0;
 
 free_kobj:
@@ -1168,6 +1203,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
+free_options:
+	kfree(options);
 free_sb_buf:
 	brelse(raw_super_buf);
 free_sbi:
@@ -1188,11 +1225,18 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
 	return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
 }
 
+static void kill_f2fs_super(struct super_block *sb)
+{
+	if (sb->s_root)
+		set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+	kill_block_super(sb);
+}
+
 static struct file_system_type f2fs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "f2fs",
 	.mount		= f2fs_mount,
-	.kill_sb	= kill_block_super,
+	.kill_sb	= kill_f2fs_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 MODULE_ALIAS_FS("f2fs");
@@ -1220,6 +1264,8 @@ static int __init init_f2fs_fs(void)
 {
 	int err;
 
+	f2fs_build_trace_ios();
+
 	err = init_inodecache();
 	if (err)
 		goto fail;
@@ -1229,12 +1275,9 @@ static int __init init_f2fs_fs(void)
 	err = create_segment_manager_caches();
 	if (err)
 		goto free_node_manager_caches;
-	err = create_gc_caches();
-	if (err)
-		goto free_segment_manager_caches;
 	err = create_checkpoint_caches();
 	if (err)
-		goto free_gc_caches;
+		goto free_segment_manager_caches;
 	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
 	if (!f2fs_kset) {
 		err = -ENOMEM;
@@ -1251,8 +1294,6 @@ static int __init init_f2fs_fs(void)
 	kset_unregister(f2fs_kset);
 free_checkpoint_caches:
 	destroy_checkpoint_caches();
-free_gc_caches:
-	destroy_gc_caches();
 free_segment_manager_caches:
 	destroy_segment_manager_caches();
 free_node_manager_caches:
@@ -1269,11 +1310,11 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	destroy_checkpoint_caches();
-	destroy_gc_caches();
 	destroy_segment_manager_caches();
 	destroy_node_manager_caches();
 	destroy_inodecache();
 	kset_unregister(f2fs_kset);
+	f2fs_destroy_trace_ios();
 }
 
 module_init(init_f2fs_fs)
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
new file mode 100644
index 00000000000000..875aa8179bc173
--- /dev/null
+++ b/fs/f2fs/trace.c
@@ -0,0 +1,159 @@
+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/sched.h>
+#include <linux/radix-tree.h>
+
+#include "f2fs.h"
+#include "trace.h"
+
+static RADIX_TREE(pids, GFP_ATOMIC);
+static spinlock_t pids_lock;
+static struct last_io_info last_io;
+
+static inline void __print_last_io(void)
+{
+	if (!last_io.len)
+		return;
+
+	trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n",
+			last_io.major, last_io.minor,
+			last_io.pid, "----------------",
+			last_io.type,
+			last_io.fio.rw, last_io.fio.blk_addr,
+			last_io.len);
+	memset(&last_io, 0, sizeof(last_io));
+}
+
+static int __file_type(struct inode *inode, pid_t pid)
+{
+	if (f2fs_is_atomic_file(inode))
+		return __ATOMIC_FILE;
+	else if (f2fs_is_volatile_file(inode))
+		return __VOLATILE_FILE;
+	else if (S_ISDIR(inode->i_mode))
+		return __DIR_FILE;
+	else if (inode->i_ino == F2FS_NODE_INO(F2FS_I_SB(inode)))
+		return __NODE_FILE;
+	else if (inode->i_ino == F2FS_META_INO(F2FS_I_SB(inode)))
+		return __META_FILE;
+	else if (pid)
+		return __NORMAL_FILE;
+	else
+		return __MISC_FILE;
+}
+
+void f2fs_trace_pid(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	pid_t pid = task_pid_nr(current);
+	void *p;
+
+	page->private = pid;
+
+	if (radix_tree_preload(GFP_NOFS))
+		return;
+
+	spin_lock(&pids_lock);
+	p = radix_tree_lookup(&pids, pid);
+	if (p == current)
+		goto out;
+	if (p)
+		radix_tree_delete(&pids, pid);
+
+	f2fs_radix_tree_insert(&pids, pid, current);
+
+	trace_printk("%3x:%3x %4x %-16s\n",
+			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
+			pid, current->comm);
+out:
+	spin_unlock(&pids_lock);
+	radix_tree_preload_end();
+}
+
+void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush)
+{
+	struct inode *inode;
+	pid_t pid;
+	int major, minor;
+
+	if (flush) {
+		__print_last_io();
+		return;
+	}
+
+	inode = page->mapping->host;
+	pid = page_private(page);
+
+	major = MAJOR(inode->i_sb->s_dev);
+	minor = MINOR(inode->i_sb->s_dev);
+
+	if (last_io.major == major && last_io.minor == minor &&
+			last_io.pid == pid &&
+			last_io.type == __file_type(inode, pid) &&
+			last_io.fio.rw == fio->rw &&
+			last_io.fio.blk_addr + last_io.len == fio->blk_addr) {
+		last_io.len++;
+		return;
+	}
+
+	__print_last_io();
+
+	last_io.major = major;
+	last_io.minor = minor;
+	last_io.pid = pid;
+	last_io.type = __file_type(inode, pid);
+	last_io.fio = *fio;
+	last_io.len = 1;
+	return;
+}
+
+void f2fs_build_trace_ios(void)
+{
+	spin_lock_init(&pids_lock);
+}
+
+#define PIDVEC_SIZE	128
+static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
+							unsigned int max_items)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
+
+	if (unlikely(!max_items))
+		return 0;
+
+	radix_tree_for_each_slot(slot, &pids, &iter, first_index) {
+		results[ret] = iter.index;
+		if (++ret == PIDVEC_SIZE)
+			break;
+	}
+	return ret;
+}
+
+void f2fs_destroy_trace_ios(void)
+{
+	pid_t pid[PIDVEC_SIZE];
+	pid_t next_pid = 0;
+	unsigned int found;
+
+	spin_lock(&pids_lock);
+	while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
+		unsigned idx;
+
+		next_pid = pid[found - 1] + 1;
+		for (idx = 0; idx < found; idx++)
+			radix_tree_delete(&pids, pid[idx]);
+	}
+	spin_unlock(&pids_lock);
+}
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
new file mode 100644
index 00000000000000..1041dbeb52ae4f
--- /dev/null
+++ b/fs/f2fs/trace.h
@@ -0,0 +1,46 @@
+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __F2FS_TRACE_H__
+#define __F2FS_TRACE_H__
+
+#ifdef CONFIG_F2FS_IO_TRACE
+#include <trace/events/f2fs.h>
+
+enum file_type {
+	__NORMAL_FILE,
+	__DIR_FILE,
+	__NODE_FILE,
+	__META_FILE,
+	__ATOMIC_FILE,
+	__VOLATILE_FILE,
+	__MISC_FILE,
+};
+
+struct last_io_info {
+	int major, minor;
+	pid_t pid;
+	enum file_type type;
+	struct f2fs_io_info fio;
+	block_t len;
+};
+
+extern void f2fs_trace_pid(struct page *);
+extern void f2fs_trace_ios(struct page *, struct f2fs_io_info *, int);
+extern void f2fs_build_trace_ios(void);
+extern void f2fs_destroy_trace_ios(void);
+#else
+#define f2fs_trace_pid(p)
+#define f2fs_trace_ios(p, i, n)
+#define f2fs_build_trace_ios()
+#define f2fs_destroy_trace_ios()
+
+#endif
+#endif /* __F2FS_TRACE_H__ */
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 2d609a5fbfea96..c399152de397b7 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -66,15 +66,21 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(writeback_in_progress);
 
-static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
+struct backing_dev_info *inode_to_bdi(struct inode *inode)
 {
-	struct super_block *sb = inode->i_sb;
+	struct super_block *sb;
 
-	if (sb_is_blkdev_sb(sb))
-		return inode->i_mapping->backing_dev_info;
+	if (!inode)
+		return &noop_backing_dev_info;
 
+	sb = inode->i_sb;
+#ifdef CONFIG_BLOCK
+	if (sb_is_blkdev_sb(sb))
+		return blk_get_backing_dev_info(I_BDEV(inode));
+#endif
 	return sb->s_bdi;
 }
+EXPORT_SYMBOL_GPL(inode_to_bdi);
 
 static inline struct inode *wb_inode(struct list_head *head)
 {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index d769e594855b0a..c01ec3bdcfd810 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1159,7 +1159,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
@@ -1464,7 +1464,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct inode *inode = req->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
 	int i;
 
 	list_del(&req->writepages_entry);
@@ -1658,7 +1658,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->end = fuse_writepage_end;
 	req->inode = inode;
 
-	inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
+	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);
@@ -1768,7 +1768,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 
 	if (old_req->num_pages == 1 && (old_req->state == FUSE_REQ_INIT ||
 					old_req->state == FUSE_REQ_PENDING)) {
-		struct backing_dev_info *bdi = page->mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(page->mapping->host);
 
 		copy_highpage(old_req->pages[0], page);
 		spin_unlock(&fc->lock);
@@ -1872,7 +1872,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].offset = 0;
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
-	inc_bdi_stat(page->mapping->backing_dev_info, BDI_WRITEBACK);
+	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f38256e4476ed2..e8799c11424b93 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -308,7 +308,6 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 		if (!fc->writeback_cache || !S_ISREG(attr->mode))
 			inode->i_flags |= S_NOCMTIME;
 		inode->i_generation = generation;
-		inode->i_data.backing_dev_info = &fc->bdi;
 		fuse_init_inode(inode, attr);
 		unlock_new_inode(inode);
 	} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 805b37fed6383f..4ad4f94edebe25 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -289,7 +289,7 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping,
 		if (!clear_page_dirty_for_io(page))
 			goto continue_unlock;
 
-		trace_wbc_writepage(wbc, mapping->backing_dev_info);
+		trace_wbc_writepage(wbc, inode_to_bdi(inode));
 
 		ret = __gfs2_jdata_writepage(page, wbc);
 		if (unlikely(ret)) {
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index aeb7bc958a18a1..f42dffba056ab0 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -768,7 +768,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_NOFS);
 		mapping->private_data = NULL;
-		mapping->backing_dev_info = s->s_bdi;
 		mapping->writeback_index = 0;
 	}
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 8633ad328ee2a3..efc8e254787cb3 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -112,7 +112,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = sb->s_bdi;
 	mapping->writeback_index = 0;
 
 	spin_lock_init(&sdp->sd_log_lock);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3e193cb36996d0..3aa17d4d1cfcbf 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -145,7 +145,8 @@ static void gfs2_qd_dispose(struct list_head *list)
 }
 
 
-static enum lru_status gfs2_qd_isolate(struct list_head *item, spinlock_t *lock, void *arg)
+static enum lru_status gfs2_qd_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *dispose = arg;
 	struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru);
@@ -155,7 +156,7 @@ static enum lru_status gfs2_qd_isolate(struct list_head *item, spinlock_t *lock,
 
 	if (qd->qd_lockref.count == 0) {
 		lockref_mark_dead(&qd->qd_lockref);
-		list_move(&qd->qd_lru, dispose);
+		list_lru_isolate_move(lru, &qd->qd_lru, dispose);
 	}
 
 	spin_unlock(&qd->qd_lockref.lock);
@@ -171,8 +172,8 @@ static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
 	if (!(sc->gfp_mask & __GFP_FS))
 		return SHRINK_STOP;
 
-	freed = list_lru_walk_node(&gfs2_qd_lru, sc->nid, gfs2_qd_isolate,
-				   &dispose, &sc->nr_to_scan);
+	freed = list_lru_shrink_walk(&gfs2_qd_lru, sc,
+				     gfs2_qd_isolate, &dispose);
 
 	gfs2_qd_dispose(&dispose);
 
@@ -182,7 +183,7 @@ static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
 static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
 					  struct shrink_control *sc)
 {
-	return vfs_pressure_ratio(list_lru_count_node(&gfs2_qd_lru, sc->nid));
+	return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc));
 }
 
 struct shrinker gfs2_qd_shrinker = {
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 5b327f837de718..1666382b198db6 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -743,7 +743,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
-	struct backing_dev_info *bdi = metamapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
 	int ret = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 5eba47f593f8f8..c274aca8e8dc23 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -62,12 +62,6 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
 	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
 }
 
-static struct backing_dev_info hugetlbfs_backing_dev_info = {
-	.name		= "hugetlbfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 int sysctl_hugetlb_shm_group;
 
 enum {
@@ -498,7 +492,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		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;
 		inode->i_mapping->private_data = resv_map;
 		info = HUGETLBFS_I(inode);
@@ -1032,10 +1025,6 @@ static int __init init_hugetlbfs_fs(void)
 		return -ENOTSUPP;
 	}
 
-	error = bdi_init(&hugetlbfs_backing_dev_info);
-	if (error)
-		return error;
-
 	error = -ENOMEM;
 	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
 					sizeof(struct hugetlbfs_inode_info),
@@ -1071,7 +1060,6 @@ static int __init init_hugetlbfs_fs(void)
  out:
 	kmem_cache_destroy(hugetlbfs_inode_cachep);
  out2:
-	bdi_destroy(&hugetlbfs_backing_dev_info);
 	return error;
 }
 
@@ -1091,7 +1079,6 @@ static void __exit exit_hugetlbfs_fs(void)
 	for_each_hstate(h)
 		kern_unmount(hugetlbfs_vfsmount[i++]);
 	unregister_filesystem(&hugetlbfs_fs_type);
-	bdi_destroy(&hugetlbfs_backing_dev_info);
 }
 
 module_init(init_hugetlbfs_fs)
diff --git a/fs/inode.c b/fs/inode.c
index 3a53b1da3fb8da..86bfaca724dbdb 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -170,20 +170,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	atomic_set(&mapping->i_mmap_writable, 0);
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = &default_backing_dev_info;
 	mapping->writeback_index = 0;
-
-	/*
-	 * If the block_device provides a backing_dev_info for client
-	 * inodes then use that.  Otherwise the inode share the bdev's
-	 * backing_dev_info.
-	 */
-	if (sb->s_bdev) {
-		struct backing_dev_info *bdi;
-
-		bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
-		mapping->backing_dev_info = bdi;
-	}
 	inode->i_private = NULL;
 	inode->i_mapping = mapping;
 	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */
@@ -685,8 +672,8 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
  * LRU does not have strict ordering. Hence we don't want to reclaim inodes
  * with this flag set because they are the inodes that are out of order.
  */
-static enum lru_status
-inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+static enum lru_status inode_lru_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct inode	*inode = container_of(item, struct inode, i_lru);
@@ -704,7 +691,7 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 	 */
 	if (atomic_read(&inode->i_count) ||
 	    (inode->i_state & ~I_REFERENCED)) {
-		list_del_init(&inode->i_lru);
+		list_lru_isolate(lru, &inode->i_lru);
 		spin_unlock(&inode->i_lock);
 		this_cpu_dec(nr_unused);
 		return LRU_REMOVED;
@@ -738,7 +725,7 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
-	list_move(&inode->i_lru, freeable);
+	list_lru_isolate_move(lru, &inode->i_lru, freeable);
 	spin_unlock(&inode->i_lock);
 
 	this_cpu_dec(nr_unused);
@@ -751,14 +738,13 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
  * to trim from the LRU. Inodes to be freed are moved to a temporary list and
  * then are freed outside inode_lock by dispose_list().
  */
-long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
-		     int nid)
+long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(freeable);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
-				       &freeable, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
+				     inode_lru_isolate, &freeable);
 	dispose_list(&freeable);
 	return freed;
 }
diff --git a/fs/internal.h b/fs/internal.h
index e9a61fe67575fb..d92c346a793ddc 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -14,6 +14,7 @@ struct file_system_type;
 struct linux_binprm;
 struct path;
 struct mount;
+struct shrink_control;
 
 /*
  * block_dev.c
@@ -111,8 +112,7 @@ extern int open_check_o_direct(struct file *f);
  * inode.c
  */
 extern spinlock_t inode_sb_list_lock;
-extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
 extern void inode_add_lru(struct inode *inode);
 
 /*
@@ -129,8 +129,7 @@ extern int invalidate_inodes(struct super_block *, bool);
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
 extern int d_set_mounted(struct dentry *dentry);
-extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
 
 /*
  * read_write.c
diff --git a/fs/jfs/endian24.h b/fs/jfs/endian24.h
deleted file mode 100644
index fa92f7f1d0d0d7..00000000000000
--- a/fs/jfs/endian24.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- *   Copyright (C) International Business Machines Corp., 2001
- *
- *   This program is free software;  you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-#ifndef _H_ENDIAN24
-#define	_H_ENDIAN24
-
-/*
- *	endian24.h:
- *
- * Endian conversion for 24-byte data
- *
- */
-#define __swab24(x) \
-({ \
-	__u32 __x = (x); \
-	((__u32)( \
-		((__x & (__u32)0x000000ffUL) << 16) | \
-		 (__x & (__u32)0x0000ff00UL)	    | \
-		((__x & (__u32)0x00ff0000UL) >> 16) )); \
-})
-
-#if (defined(__KERNEL__) && defined(__LITTLE_ENDIAN)) || (defined(__BYTE_ORDER) && (__BYTE_ORDER == __LITTLE_ENDIAN))
-	#define __cpu_to_le24(x) ((__u32)(x))
-	#define __le24_to_cpu(x) ((__u32)(x))
-#else
-	#define __cpu_to_le24(x) __swab24(x)
-	#define __le24_to_cpu(x) __swab24(x)
-#endif
-
-#ifdef __KERNEL__
-	#define cpu_to_le24 __cpu_to_le24
-	#define le24_to_cpu __le24_to_cpu
-#endif
-
-#endif				/* !_H_ENDIAN24 */
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 984c2bbf4f6143..d88576e23fe4c4 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -1040,8 +1040,8 @@ static int dtSplitUp(tid_t tid,
 		pxdlist.maxnpxd = 1;
 		pxdlist.npxd = 0;
 		pxd = &pxdlist.pxd[0];
-		PXDaddress(pxd, nxaddr)
-		    PXDlength(pxd, xlen + n);
+		PXDaddress(pxd, nxaddr);
+		PXDlength(pxd, xlen + n);
 		split->pxdlist = &pxdlist;
 		if ((rc = dtExtendPage(tid, ip, split, btstack))) {
 			nxaddr = addressPXD(pxd);
diff --git a/fs/jfs/jfs_types.h b/fs/jfs/jfs_types.h
index 43ea3713c083fe..8f602dcb51fab6 100644
--- a/fs/jfs/jfs_types.h
+++ b/fs/jfs/jfs_types.h
@@ -30,8 +30,6 @@
 #include <linux/types.h>
 #include <linux/nls.h>
 
-#include "endian24.h"
-
 /*
  * transaction and lock id's
  *
@@ -59,26 +57,42 @@ struct timestruc_t {
 
 /*
  *	physical xd (pxd)
+ *
+ *	The leftmost 24 bits of len_addr are the extent length.
+ *	The rightmost 8 bits of len_addr are the most signficant bits of
+ *	the extent address
  */
 typedef struct {
-	unsigned len:24;
-	unsigned addr1:8;
+	__le32 len_addr;
 	__le32 addr2;
 } pxd_t;
 
 /* xd_t field construction */
 
-#define	PXDlength(pxd, length32)	((pxd)->len = __cpu_to_le24(length32))
-#define	PXDaddress(pxd, address64)\
-{\
-	(pxd)->addr1 = ((s64)address64) >> 32;\
-	(pxd)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\
+static inline void PXDlength(pxd_t *pxd, __u32 len)
+{
+	pxd->len_addr = (pxd->len_addr & cpu_to_le32(~0xffffff)) |
+			cpu_to_le32(len & 0xffffff);
+}
+
+static inline void PXDaddress(pxd_t *pxd, __u64 addr)
+{
+	pxd->len_addr = (pxd->len_addr & cpu_to_le32(0xffffff)) |
+			cpu_to_le32((addr >> 32)<<24);
+	pxd->addr2 = cpu_to_le32(addr & 0xffffffff);
 }
 
 /* xd_t field extraction */
-#define	lengthPXD(pxd)	__le24_to_cpu((pxd)->len)
-#define	addressPXD(pxd)\
-	( ((s64)((pxd)->addr1)) << 32 | __le32_to_cpu((pxd)->addr2))
+static inline __u32 lengthPXD(pxd_t *pxd)
+{
+	return le32_to_cpu((pxd)->len_addr) & 0xffffff;
+}
+
+static inline __u64 addressPXD(pxd_t *pxd)
+{
+	__u64 n = le32_to_cpu(pxd->len_addr) & ~0xffffff;
+	return (n << 8) + le32_to_cpu(pxd->addr2);
+}
 
 #define MAXTREEHEIGHT 8
 /* pxd list */
@@ -93,12 +107,10 @@ struct pxdlist {
  *	data extent descriptor (dxd)
  */
 typedef struct {
-	unsigned flag:8;	/* 1: flags */
-	unsigned rsrvd:24;
+	__u8 flag;	/* 1: flags */
+	__u8 rsrvd[3];
 	__le32 size;		/* 4: size in byte */
-	unsigned len:24;	/* 3: length in unit of fsblksize */
-	unsigned addr1:8;	/* 1: address in unit of fsblksize */
-	__le32 addr2;		/* 4: address in unit of fsblksize */
+	pxd_t loc;		/* 8: address and length in unit of fsblksize */
 } dxd_t;			/* - 16 - */
 
 /* dxd_t flags */
@@ -109,12 +121,11 @@ typedef struct {
 #define DXD_CORRUPT	0x08	/* Inconsistency detected */
 
 /* dxd_t field construction
- *	Conveniently, the PXD macros work for DXD
  */
-#define	DXDlength	PXDlength
-#define	DXDaddress	PXDaddress
-#define	lengthDXD	lengthPXD
-#define	addressDXD	addressPXD
+#define	DXDlength(dxd, len)	PXDlength(&(dxd)->loc, len)
+#define	DXDaddress(dxd, addr)	PXDaddress(&(dxd)->loc, addr)
+#define	lengthDXD(dxd)	lengthPXD(&(dxd)->loc)
+#define	addressDXD(dxd)	addressPXD(&(dxd)->loc)
 #define DXDsize(dxd, size32) ((dxd)->size = cpu_to_le32(size32))
 #define sizeDXD(dxd)	le32_to_cpu((dxd)->size)
 
diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h
index 08c0c749b986bd..1e0987986d5f96 100644
--- a/fs/jfs/jfs_xtree.h
+++ b/fs/jfs/jfs_xtree.h
@@ -29,13 +29,11 @@
  *	extent allocation descriptor (xad)
  */
 typedef struct xad {
-	unsigned flag:8;	/* 1: flag */
-	unsigned rsvrd:16;	/* 2: reserved */
-	unsigned off1:8;	/* 1: offset in unit of fsblksize */
-	__le32 off2;		/* 4: offset in unit of fsblksize */
-	unsigned len:24;	/* 3: length in unit of fsblksize */
-	unsigned addr1:8;	/* 1: address in unit of fsblksize */
-	__le32 addr2;		/* 4: address in unit of fsblksize */
+	__u8 flag;	/* 1: flag */
+	__u8 rsvrd[2];	/* 2: reserved */
+	__u8 off1;	/* 1: offset in unit of fsblksize */
+	__le32 off2;	/* 4: offset in unit of fsblksize */
+	pxd_t loc;	/* 8: length and address in unit of fsblksize */
 } xad_t;			/* (16) */
 
 #define MAXXLEN		((1 << 24) - 1)
@@ -49,19 +47,14 @@ typedef struct xad {
 	(xad)->off1 = ((u64)offset64) >> 32;\
 	(xad)->off2 = __cpu_to_le32((offset64) & 0xffffffff);\
 }
-#define XADaddress(xad, address64)\
-{\
-	(xad)->addr1 = ((u64)address64) >> 32;\
-	(xad)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\
-}
-#define XADlength(xad, length32)	(xad)->len = __cpu_to_le24(length32)
+#define XADaddress(xad, address64) PXDaddress(&(xad)->loc, address64)
+#define XADlength(xad, length32) PXDlength(&(xad)->loc, length32)
 
 /* xad_t field extraction */
 #define offsetXAD(xad)\
 	( ((s64)((xad)->off1)) << 32 | __le32_to_cpu((xad)->off2))
-#define addressXAD(xad)\
-	( ((s64)((xad)->addr1)) << 32 | __le32_to_cpu((xad)->addr2))
-#define lengthXAD(xad)	__le24_to_cpu((xad)->len)
+#define addressXAD(xad) addressPXD(&(xad)->loc)
+#define lengthXAD(xad) lengthPXD(&(xad)->loc)
 
 /* xad list */
 struct xadlist {
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 16c3a9556634dd..5d30c56ae07506 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -619,8 +619,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	iput(sbi->direct_inode);
 	sbi->direct_inode = NULL;
 out_unload:
-	if (sbi->nls_tab)
-		unload_nls(sbi->nls_tab);
+	unload_nls(sbi->nls_tab);
 out_kfree:
 	kfree(sbi);
 	return ret;
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 985217626e663f..9000874a945b62 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -24,12 +24,6 @@ static const struct address_space_operations kernfs_aops = {
 	.write_end	= simple_write_end,
 };
 
-static struct backing_dev_info kernfs_bdi = {
-	.name		= "kernfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 static const struct inode_operations kernfs_iops = {
 	.permission	= kernfs_iop_permission,
 	.setattr	= kernfs_iop_setattr,
@@ -40,12 +34,6 @@ static const struct inode_operations kernfs_iops = {
 	.listxattr	= kernfs_iop_listxattr,
 };
 
-void __init kernfs_inode_init(void)
-{
-	if (bdi_init(&kernfs_bdi))
-		panic("failed to init kernfs_bdi");
-}
-
 static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
 {
 	static DEFINE_MUTEX(iattr_mutex);
@@ -298,7 +286,6 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
 	kernfs_get(kn);
 	inode->i_private = kn;
 	inode->i_mapping->a_ops = &kernfs_aops;
-	inode->i_mapping->backing_dev_info = &kernfs_bdi;
 	inode->i_op = &kernfs_iops;
 
 	set_default_inode_attr(inode, kn->mode);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index dc84a3ef9ca204..af9fa7499919c5 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -88,7 +88,6 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
 ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
 			    size_t size);
 ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
-void kernfs_inode_init(void);
 
 /*
  * dir.c
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index f973ae9b05f15d..8eaf417187f11b 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -246,5 +246,4 @@ void __init kernfs_init(void)
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
 					      sizeof(struct kernfs_node),
 					      0, SLAB_PANIC, NULL);
-	kernfs_inode_init();
 }
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 56598742dde473..5581e020644bda 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -57,8 +57,8 @@ static DEFINE_SPINLOCK(nlm_blocked_lock);
 static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
 {
 	/*
-	 * We can get away with a static buffer because we're only
-	 * called with BKL held.
+	 * We can get away with a static buffer because this is only called
+	 * from lockd, which is single-threaded.
 	 */
 	static char buf[2*NLM_MAXCOOKIELEN+1];
 	unsigned int i, len = sizeof(buf);
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 9340e7e10ef60b..5b651daad5183c 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -95,14 +95,6 @@ nlm_decode_fh(__be32 *p, struct nfs_fh *f)
 	return p + XDR_QUADLEN(NFS2_FHSIZE);
 }
 
-static inline __be32 *
-nlm_encode_fh(__be32 *p, struct nfs_fh *f)
-{
-	*p++ = htonl(NFS2_FHSIZE);
-	memcpy(p, f->data, NFS2_FHSIZE);
-	return p + XDR_QUADLEN(NFS2_FHSIZE);
-}
-
 /*
  * Encode and decode owner handle
  */
diff --git a/fs/locks.c b/fs/locks.c
index 4d0d41163a50fe..4753218f308ed3 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -137,7 +137,7 @@
 
 #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_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
 #define IS_OFDLCK(fl)	(fl->fl_flags & FL_OFDLCK)
 
 static bool lease_breaking(struct file_lock *fl)
@@ -1371,6 +1371,8 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
 
 static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 {
+	if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT))
+		return false;
 	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
 		return false;
 	return locks_conflict(breaker, lease);
@@ -1594,11 +1596,14 @@ int fcntl_getlease(struct file *filp)
  * conflict with the lease we're trying to set.
  */
 static int
-check_conflicting_open(const struct dentry *dentry, const long arg)
+check_conflicting_open(const struct dentry *dentry, const long arg, int flags)
 {
 	int ret = 0;
 	struct inode *inode = dentry->d_inode;
 
+	if (flags & FL_LAYOUT)
+		return 0;
+
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
 		return -EAGAIN;
 
@@ -1647,7 +1652,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 
 	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
-	error = check_conflicting_open(dentry, arg);
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
 	if (error)
 		goto out;
 
@@ -1661,7 +1666,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 */
 	error = -EAGAIN;
 	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp) {
+		if (fl->fl_file == filp &&
+		    fl->fl_owner == lease->fl_owner) {
 			my_fl = fl;
 			continue;
 		}
@@ -1702,7 +1708,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * precedes these checks.
 	 */
 	smp_mb();
-	error = check_conflicting_open(dentry, arg);
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
 	if (error) {
 		locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt);
 		goto out;
@@ -1721,7 +1727,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	return error;
 }
 
-static int generic_delete_lease(struct file *filp)
+static int generic_delete_lease(struct file *filp, void *owner)
 {
 	int error = -EAGAIN;
 	struct file_lock *fl, *victim = NULL;
@@ -1737,7 +1743,8 @@ static int generic_delete_lease(struct file *filp)
 
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp) {
+		if (fl->fl_file == filp &&
+		    fl->fl_owner == owner) {
 			victim = fl;
 			break;
 		}
@@ -1778,13 +1785,14 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
 
 	switch (arg) {
 	case F_UNLCK:
-		return generic_delete_lease(filp);
+		return generic_delete_lease(filp, *priv);
 	case F_RDLCK:
 	case F_WRLCK:
 		if (!(*flp)->fl_lmops->lm_break) {
 			WARN_ON_ONCE(1);
 			return -ENOLCK;
 		}
+
 		return generic_add_lease(filp, arg, flp, priv);
 	default:
 		return -EINVAL;
@@ -1857,7 +1865,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
 	if (arg == F_UNLCK)
-		return vfs_setlease(filp, F_UNLCK, NULL, NULL);
+		return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp);
 	return do_fcntl_add_lease(fd, filp, arg);
 }
 
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index e31e589369a49a..01a9e16e97825e 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -267,7 +267,6 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 	if (inode) {
 		atomic_set(&NCP_FINFO(inode)->opened, info->opened);
 
-		inode->i_mapping->backing_dev_info = sb->s_bdi;
 		inode->i_ino = info->ino;
 		ncp_set_attr(inode, info);
 		if (S_ISREG(inode->i_mode)) {
@@ -560,7 +559,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	server = NCP_SBP(sb);
 	memset(server, 0, sizeof(*server));
 
-	error = bdi_setup_and_register(&server->bdi, "ncpfs", BDI_CAP_MAP_COPY);
+	error = bdi_setup_and_register(&server->bdi, "ncpfs");
 	if (error)
 		goto out_fput;
 
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 3c9769441f3641..7ae1c263c5cf03 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -1002,7 +1002,7 @@ filelayout_mark_request_commit(struct nfs_page *req,
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+		inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index f29fb7d7e8f84a..c22ecaa86c1c27 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1366,7 +1366,7 @@ ff_layout_mark_request_commit(struct nfs_page *req,
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+		inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index d2398c193bdaab..e4f0dcef8f5455 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -388,7 +388,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		if (S_ISREG(inode->i_mode)) {
 			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
-			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
 			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 21469e6e383427..212b8c883d2288 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -430,7 +430,6 @@ int  nfs_show_options(struct seq_file *, struct dentry *);
 int  nfs_show_devname(struct seq_file *, struct dentry *);
 int  nfs_show_path(struct seq_file *, struct dentry *);
 int  nfs_show_stats(struct seq_file *, struct dentry *);
-void nfs_put_super(struct super_block *);
 int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
 /* write.c */
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 48cea3c30e5de0..75090feeafade9 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -53,7 +53,6 @@ static const struct super_operations nfs4_sops = {
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs4_write_inode,
 	.drop_inode	= nfs_drop_inode,
-	.put_super	= nfs_put_super,
 	.statfs		= nfs_statfs,
 	.evict_inode	= nfs4_evict_inode,
 	.umount_begin	= nfs_umount_begin,
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 368d9395d2e7f0..322b2de02988fa 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -311,7 +311,6 @@ const struct super_operations nfs_sops = {
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs_write_inode,
 	.drop_inode	= nfs_drop_inode,
-	.put_super	= nfs_put_super,
 	.statfs		= nfs_statfs,
 	.evict_inode	= nfs_evict_inode,
 	.umount_begin	= nfs_umount_begin,
@@ -2572,7 +2571,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 		error = nfs_bdi_register(server);
 		if (error) {
 			mntroot = ERR_PTR(error);
-			goto error_splat_bdi;
+			goto error_splat_super;
 		}
 		server->super = s;
 	}
@@ -2604,9 +2603,6 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 	dput(mntroot);
 	mntroot = ERR_PTR(error);
 error_splat_super:
-	if (server && !s->s_root)
-		bdi_unregister(&server->backing_dev_info);
-error_splat_bdi:
 	deactivate_locked_super(s);
 	goto out;
 }
@@ -2653,28 +2649,20 @@ struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 }
 EXPORT_SYMBOL_GPL(nfs_fs_mount);
 
-/*
- * Ensure that we unregister the bdi before kill_anon_super
- * releases the device name
- */
-void nfs_put_super(struct super_block *s)
-{
-	struct nfs_server *server = NFS_SB(s);
-
-	bdi_unregister(&server->backing_dev_info);
-}
-EXPORT_SYMBOL_GPL(nfs_put_super);
-
 /*
  * Destroy an NFS2/3 superblock
  */
 void nfs_kill_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
+	dev_t dev = s->s_dev;
+
+	generic_shutdown_super(s);
 
-	kill_anon_super(s);
 	nfs_fscache_release_super_cookie(s);
+
 	nfs_free_server(server);
+	free_anon_bdev(dev);
 }
 EXPORT_SYMBOL_GPL(nfs_kill_super);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index bcf83e535f29a0..88a6d2196ece3b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -791,7 +791,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+		inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
@@ -858,7 +858,7 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
+	dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
 }
 
 /* Called holding inode (/cinfo) lock */
@@ -1607,7 +1607,7 @@ void nfs_retry_commit(struct list_head *page_list,
 		nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx);
 		if (!cinfo->dreq) {
 			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+			dec_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
 				     BDI_RECLAIMABLE);
 		}
 		nfs_unlock_and_release_request(req);
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 73395156bdb4c4..683bf718aead54 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -82,6 +82,16 @@ config NFSD_V4
 
 	  If unsure, say N.
 
+config NFSD_PNFS
+	bool "NFSv4.1 server support for Parallel NFS (pNFS)"
+	depends on NFSD_V4
+	help
+	  This option enables support for the parallel NFS features of the
+	  minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS
+	  server.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index af32ef06b4fec7..9a6028e120c68b 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -2,9 +2,14 @@
 # Makefile for the Linux nfs server
 #
 
+ccflags-y += -I$(src)			# needed for trace events
+
 obj-$(CONFIG_NFSD)	+= nfsd.o
 
-nfsd-y 			:= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
+# this one should be compiled first, as the tracing macros can easily blow up
+nfsd-y			+= trace.o
+
+nfsd-y 			+= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
 			   export.o auth.o lockd.o nfscache.o nfsxdr.o stats.o
 nfsd-$(CONFIG_NFSD_FAULT_INJECTION) += fault_inject.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
@@ -12,3 +17,4 @@ nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 			   nfs4acl.o nfs4callback.o nfs4recover.o
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o blocklayout.o blocklayoutxdr.o
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
new file mode 100644
index 00000000000000..cdbc78c7254218
--- /dev/null
+++ b/fs/nfsd/blocklayout.c
@@ -0,0 +1,189 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/exportfs.h>
+#include <linux/genhd.h>
+#include <linux/slab.h>
+
+#include <linux/nfsd/debug.h>
+
+#include "blocklayoutxdr.h"
+#include "pnfs.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+static int
+nfsd4_block_get_device_info_simple(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+
+	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
+		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	gdp->gd_device = dev;
+
+	dev->nr_volumes = 1;
+	b = &dev->volumes[0];
+
+	b->type = PNFS_BLOCK_VOLUME_SIMPLE;
+	b->simple.sig_len = PNFS_BLOCK_UUID_LEN;
+	return sb->s_export_op->get_uuid(sb, b->simple.sig, &b->simple.sig_len,
+			&b->simple.offset);
+}
+
+static __be32
+nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (sb->s_bdev != sb->s_bdev->bd_contains)
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
+}
+
+static __be32
+nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
+		struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	struct super_block *sb = inode->i_sb;
+	u32 block_size = (1 << inode->i_blkbits);
+	struct pnfs_block_extent *bex;
+	struct iomap iomap;
+	u32 device_generation = 0;
+	int error;
+
+	/*
+	 * We do not attempt to support I/O smaller than the fs block size,
+	 * or not aligned to it.
+	 */
+	if (args->lg_minlength < block_size) {
+		dprintk("pnfsd: I/O too small\n");
+		goto out_layoutunavailable;
+	}
+	if (seg->offset & (block_size - 1)) {
+		dprintk("pnfsd: I/O misaligned\n");
+		goto out_layoutunavailable;
+	}
+
+	/*
+	 * Some clients barf on non-zero block numbers for NONE or INVALID
+	 * layouts, so make sure to zero the whole structure.
+	 */
+	error = -ENOMEM;
+	bex = kzalloc(sizeof(*bex), GFP_KERNEL);
+	if (!bex)
+		goto out_error;
+	args->lg_content = bex;
+
+	error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length,
+					    &iomap, seg->iomode != IOMODE_READ,
+					    &device_generation);
+	if (error) {
+		if (error == -ENXIO)
+			goto out_layoutunavailable;
+		goto out_error;
+	}
+
+	if (iomap.length < args->lg_minlength) {
+		dprintk("pnfsd: extent smaller than minlength\n");
+		goto out_layoutunavailable;
+	}
+
+	switch (iomap.type) {
+	case IOMAP_MAPPED:
+		if (seg->iomode == IOMODE_READ)
+			bex->es = PNFS_BLOCK_READ_DATA;
+		else
+			bex->es = PNFS_BLOCK_READWRITE_DATA;
+		bex->soff = (iomap.blkno << 9);
+		break;
+	case IOMAP_UNWRITTEN:
+		if (seg->iomode & IOMODE_RW) {
+			/*
+			 * Crack monkey special case from section 2.3.1.
+			 */
+			if (args->lg_minlength == 0) {
+				dprintk("pnfsd: no soup for you!\n");
+				goto out_layoutunavailable;
+			}
+
+			bex->es = PNFS_BLOCK_INVALID_DATA;
+			bex->soff = (iomap.blkno << 9);
+			break;
+		}
+		/*FALLTHRU*/
+	case IOMAP_HOLE:
+		if (seg->iomode == IOMODE_READ) {
+			bex->es = PNFS_BLOCK_NONE_DATA;
+			break;
+		}
+		/*FALLTHRU*/
+	case IOMAP_DELALLOC:
+	default:
+		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
+		goto out_layoutunavailable;
+	}
+
+	error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation);
+	if (error)
+		goto out_error;
+	bex->foff = iomap.offset;
+	bex->len = iomap.length;
+
+	seg->offset = iomap.offset;
+	seg->length = iomap.length;
+
+	dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es);
+	return 0;
+
+out_error:
+	seg->length = 0;
+	return nfserrno(error);
+out_layoutunavailable:
+	seg->length = 0;
+	return nfserr_layoutunavailable;
+}
+
+static __be32
+nfsd4_block_proc_layoutcommit(struct inode *inode,
+		struct nfsd4_layoutcommit *lcp)
+{
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct iattr iattr = { .ia_valid = 0 };
+	struct iomap *iomaps;
+	int nr_iomaps;
+	int error;
+
+	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
+			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+	if (nr_iomaps < 0)
+		return nfserrno(nr_iomaps);
+
+	if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
+	    timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
+		lcp->lc_mtime = current_fs_time(inode->i_sb);
+	iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
+	iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
+
+	if (new_size > i_size_read(inode)) {
+		iattr.ia_valid |= ATTR_SIZE;
+		iattr.ia_size = new_size;
+	}
+
+	error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
+			nr_iomaps, &iattr);
+	kfree(iomaps);
+	return nfserrno(error);
+}
+
+const struct nfsd4_layout_ops bl_layout_ops = {
+	.proc_getdeviceinfo	= nfsd4_block_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_block_proc_layoutget,
+	.encode_layoutget	= nfsd4_block_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_block_proc_layoutcommit,
+};
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
new file mode 100644
index 00000000000000..9da89fddab338f
--- /dev/null
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -0,0 +1,157 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/exportfs.h>
+#include <linux/nfs4.h>
+
+#include "nfsd.h"
+#include "blocklayoutxdr.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+__be32
+nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct pnfs_block_extent *b = lgp->lg_content;
+	int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32);
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (!p)
+		return nfserr_toosmall;
+
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(1);		/* we always return a single extent */
+
+	p = xdr_encode_opaque_fixed(p, &b->vol_id,
+			sizeof(struct nfsd4_deviceid));
+	p = xdr_encode_hyper(p, b->foff);
+	p = xdr_encode_hyper(p, b->len);
+	p = xdr_encode_hyper(p, b->soff);
+	*p++ = cpu_to_be32(b->es);
+	return 0;
+}
+
+static int
+nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
+{
+	__be32 *p;
+	int len;
+
+	switch (b->type) {
+	case PNFS_BLOCK_VOLUME_SIMPLE:
+		len = 4 + 4 + 8 + 4 + b->simple.sig_len;
+		p = xdr_reserve_space(xdr, len);
+		if (!p)
+			return -ETOOSMALL;
+
+		*p++ = cpu_to_be32(b->type);
+		*p++ = cpu_to_be32(1);	/* single signature */
+		p = xdr_encode_hyper(p, b->simple.offset);
+		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return len;
+}
+
+__be32
+nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev = gdp->gd_device;
+	int len = sizeof(__be32), ret, i;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, len + sizeof(__be32));
+	if (!p)
+		return nfserr_resource;
+
+	for (i = 0; i < dev->nr_volumes; i++) {
+		ret = nfsd4_block_encode_volume(xdr, &dev->volumes[i]);
+		if (ret < 0)
+			return nfserrno(ret);
+		len += ret;
+	}
+
+	/*
+	 * Fill in the overall length and number of volumes at the beginning
+	 * of the layout.
+	 */
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(dev->nr_volumes);
+	return 0;
+}
+
+int
+nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size)
+{
+	struct iomap *iomaps;
+	u32 nr_iomaps, expected, i;
+
+	if (len < sizeof(u32)) {
+		dprintk("%s: extent array too small: %u\n", __func__, len);
+		return -EINVAL;
+	}
+
+	nr_iomaps = be32_to_cpup(p++);
+	expected = sizeof(__be32) + nr_iomaps * NFS4_BLOCK_EXTENT_SIZE;
+	if (len != expected) {
+		dprintk("%s: extent array size mismatch: %u/%u\n",
+			__func__, len, expected);
+		return -EINVAL;
+	}
+
+	iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL);
+	if (!iomaps) {
+		dprintk("%s: failed to allocate extent array\n", __func__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nr_iomaps; i++) {
+		struct pnfs_block_extent bex;
+
+		memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid));
+		p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid));
+
+		p = xdr_decode_hyper(p, &bex.foff);
+		if (bex.foff & (block_size - 1)) {
+			dprintk("%s: unaligned offset %lld\n",
+				__func__, bex.foff);
+			goto fail;
+		}
+		p = xdr_decode_hyper(p, &bex.len);
+		if (bex.len & (block_size - 1)) {
+			dprintk("%s: unaligned length %lld\n",
+				__func__, bex.foff);
+			goto fail;
+		}
+		p = xdr_decode_hyper(p, &bex.soff);
+		if (bex.soff & (block_size - 1)) {
+			dprintk("%s: unaligned disk offset %lld\n",
+				__func__, bex.soff);
+			goto fail;
+		}
+		bex.es = be32_to_cpup(p++);
+		if (bex.es != PNFS_BLOCK_READWRITE_DATA) {
+			dprintk("%s: incorrect extent state %d\n",
+				__func__, bex.es);
+			goto fail;
+		}
+
+		iomaps[i].offset = bex.foff;
+		iomaps[i].length = bex.len;
+	}
+
+	*iomapp = iomaps;
+	return nr_iomaps;
+fail:
+	kfree(iomaps);
+	return -EINVAL;
+}
diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h
new file mode 100644
index 00000000000000..fdc79037c0e781
--- /dev/null
+++ b/fs/nfsd/blocklayoutxdr.h
@@ -0,0 +1,62 @@
+#ifndef _NFSD_BLOCKLAYOUTXDR_H
+#define _NFSD_BLOCKLAYOUTXDR_H 1
+
+#include <linux/blkdev.h>
+#include "xdr4.h"
+
+struct iomap;
+struct xdr_stream;
+
+enum pnfs_block_extent_state {
+	PNFS_BLOCK_READWRITE_DATA	= 0,
+	PNFS_BLOCK_READ_DATA		= 1,
+	PNFS_BLOCK_INVALID_DATA		= 2,
+	PNFS_BLOCK_NONE_DATA		= 3,
+};
+
+struct pnfs_block_extent {
+	struct nfsd4_deviceid		vol_id;
+	u64				foff;
+	u64				len;
+	u64				soff;
+	enum pnfs_block_extent_state	es;
+};
+#define NFS4_BLOCK_EXTENT_SIZE		44
+
+enum pnfs_block_volume_type {
+	PNFS_BLOCK_VOLUME_SIMPLE	= 0,
+	PNFS_BLOCK_VOLUME_SLICE		= 1,
+	PNFS_BLOCK_VOLUME_CONCAT	= 2,
+	PNFS_BLOCK_VOLUME_STRIPE	= 3,
+};
+
+/*
+ * Random upper cap for the uuid length to avoid unbounded allocation.
+ * Not actually limited by the protocol.
+ */
+#define PNFS_BLOCK_UUID_LEN	128
+
+struct pnfs_block_volume {
+	enum pnfs_block_volume_type	type;
+	union {
+		struct {
+			u64		offset;
+			u32		sig_len;
+			u8		sig[PNFS_BLOCK_UUID_LEN];
+		} simple;
+	};
+};
+
+struct pnfs_block_deviceaddr {
+	u32				nr_volumes;
+	struct pnfs_block_volume	volumes[];
+};
+
+__be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp);
+__be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp);
+int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size);
+
+#endif /* _NFSD_BLOCKLAYOUTXDR_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 30a739d896ffca..c3e3b6e55ae28d 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -20,6 +20,7 @@
 #include "nfsd.h"
 #include "nfsfh.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
@@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 
 	exp.ex_client = dom;
 	exp.cd = cd;
+	exp.ex_devid_map = NULL;
 
 	/* expiry */
 	err = -EINVAL;
@@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		if (!gid_valid(exp.ex_anon_gid))
 			goto out4;
 		err = 0;
+
+		nfsd4_setup_layout_type(&exp);
 	}
 
 	expp = svc_export_lookup(&exp);
@@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_fslocs.locations = NULL;
 	new->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = 0;
+	new->ex_layout_type = 0;
 	new->ex_uuid = NULL;
 	new->cd = item->cd;
 }
@@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_anon_uid = item->ex_anon_uid;
 	new->ex_anon_gid = item->ex_anon_gid;
 	new->ex_fsid = item->ex_fsid;
+	new->ex_devid_map = item->ex_devid_map;
+	item->ex_devid_map = NULL;
 	new->ex_uuid = item->ex_uuid;
 	item->ex_uuid = NULL;
 	new->ex_fslocs.locations = item->ex_fslocs.locations;
@@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	item->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = item->ex_fslocs.migrated;
 	item->ex_fslocs.migrated = 0;
+	new->ex_layout_type = item->ex_layout_type;
 	new->ex_nflavors = item->ex_nflavors;
 	for (i = 0; i < MAX_SECINFO_LIST; i++) {
 		new->ex_flavors[i] = item->ex_flavors[i];
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 04dc8c167b0c19..1f52bfcc436f21 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -56,6 +56,8 @@ struct svc_export {
 	struct nfsd4_fs_locations ex_fslocs;
 	uint32_t		ex_nflavors;
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
+	enum pnfs_layouttype	ex_layout_type;
+	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 };
 
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7cbdf1b2e4abd7..58277859a467d8 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -546,6 +546,102 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 	return status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * CB_LAYOUTRECALL4args
+ *
+ *	struct layoutrecall_file4 {
+ *		nfs_fh4         lor_fh;
+ *		offset4         lor_offset;
+ *		length4         lor_length;
+ *		stateid4        lor_stateid;
+ *	};
+ *
+ *	union layoutrecall4 switch(layoutrecall_type4 lor_recalltype) {
+ *	case LAYOUTRECALL4_FILE:
+ *		layoutrecall_file4 lor_layout;
+ *	case LAYOUTRECALL4_FSID:
+ *		fsid4              lor_fsid;
+ *	case LAYOUTRECALL4_ALL:
+ *		void;
+ *	};
+ *
+ *	struct CB_LAYOUTRECALL4args {
+ *		layouttype4             clora_type;
+ *		layoutiomode4           clora_iomode;
+ *		bool                    clora_changed;
+ *		layoutrecall4           clora_recall;
+ *	};
+ */
+static void encode_cb_layout4args(struct xdr_stream *xdr,
+				  const struct nfs4_layout_stateid *ls,
+				  struct nfs4_cb_compound_hdr *hdr)
+{
+	__be32 *p;
+
+	BUG_ON(hdr->minorversion == 0);
+
+	p = xdr_reserve_space(xdr, 5 * 4);
+	*p++ = cpu_to_be32(OP_CB_LAYOUTRECALL);
+	*p++ = cpu_to_be32(ls->ls_layout_type);
+	*p++ = cpu_to_be32(IOMODE_ANY);
+	*p++ = cpu_to_be32(1);
+	*p = cpu_to_be32(RETURN_FILE);
+
+	encode_nfs_fh4(xdr, &ls->ls_stid.sc_file->fi_fhandle);
+
+	p = xdr_reserve_space(xdr, 2 * 8);
+	p = xdr_encode_hyper(p, 0);
+	xdr_encode_hyper(p, NFS4_MAX_UINT64);
+
+	encode_stateid4(xdr, &ls->ls_recall_sid);
+
+	hdr->nops++;
+}
+
+static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const struct nfsd4_callback *cb)
+{
+	const struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = 0,
+		.minorversion = cb->cb_minorversion,
+	};
+
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+	encode_cb_layout4args(xdr, ls, &hdr);
+	encode_cb_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  struct nfsd4_callback *cb)
+{
+	struct nfs4_cb_compound_hdr hdr;
+	enum nfsstat4 nfserr;
+	int status;
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		goto out;
+	if (cb) {
+		status = decode_cb_sequence4res(xdr, cb);
+		if (unlikely(status))
+			goto out;
+	}
+	status = decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &nfserr);
+	if (unlikely(status))
+		goto out;
+	if (unlikely(nfserr != NFS4_OK))
+		status = nfs_cb_stat_to_errno(nfserr);
+out:
+	return status;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * RPC procedure tables
  */
@@ -563,6 +659,9 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 static struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NULL,	NULL,		cb_null,	cb_null),
 	PROC(CB_RECALL,	COMPOUND,	cb_recall,	cb_recall),
+#ifdef CONFIG_NFSD_PNFS
+	PROC(CB_LAYOUT,	COMPOUND,	cb_layout,	cb_layout),
+#endif
 };
 
 static struct rpc_version nfs_cb_version4 = {
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
new file mode 100644
index 00000000000000..3c1bfa15557116
--- /dev/null
+++ b/fs/nfsd/nfs4layouts.c
@@ -0,0 +1,721 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/kmod.h>
+#include <linux/file.h>
+#include <linux/jhash.h>
+#include <linux/sched.h>
+#include <linux/sunrpc/addr.h>
+
+#include "pnfs.h"
+#include "netns.h"
+#include "trace.h"
+
+#define NFSDDBG_FACILITY                NFSDDBG_PNFS
+
+struct nfs4_layout {
+	struct list_head		lo_perstate;
+	struct nfs4_layout_stateid	*lo_state;
+	struct nfsd4_layout_seg		lo_seg;
+};
+
+static struct kmem_cache *nfs4_layout_cache;
+static struct kmem_cache *nfs4_layout_stateid_cache;
+
+static struct nfsd4_callback_ops nfsd4_cb_layout_ops;
+static const struct lock_manager_operations nfsd4_layouts_lm_ops;
+
+const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
+};
+
+/* pNFS device ID to export fsid mapping */
+#define DEVID_HASH_BITS	8
+#define DEVID_HASH_SIZE	(1 << DEVID_HASH_BITS)
+#define DEVID_HASH_MASK	(DEVID_HASH_SIZE - 1)
+static u64 nfsd_devid_seq = 1;
+static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfsd_devid_lock);
+
+static inline u32 devid_hashfn(u64 idx)
+{
+	return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK;
+}
+
+static void
+nfsd4_alloc_devid_map(const struct svc_fh *fhp)
+{
+	const struct knfsd_fh *fh = &fhp->fh_handle;
+	size_t fsid_len = key_len(fh->fh_fsid_type);
+	struct nfsd4_deviceid_map *map, *old;
+	int i;
+
+	map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL);
+	if (!map)
+		return;
+
+	map->fsid_type = fh->fh_fsid_type;
+	memcpy(&map->fsid, fh->fh_fsid, fsid_len);
+
+	spin_lock(&nfsd_devid_lock);
+	if (fhp->fh_export->ex_devid_map)
+		goto out_unlock;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		list_for_each_entry(old, &nfsd_devid_hash[i], hash) {
+			if (old->fsid_type != fh->fh_fsid_type)
+				continue;
+			if (memcmp(old->fsid, fh->fh_fsid,
+					key_len(old->fsid_type)))
+				continue;
+
+			fhp->fh_export->ex_devid_map = old;
+			goto out_unlock;
+		}
+	}
+
+	map->idx = nfsd_devid_seq++;
+	list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]);
+	fhp->fh_export->ex_devid_map = map;
+	map = NULL;
+
+out_unlock:
+	spin_unlock(&nfsd_devid_lock);
+	kfree(map);
+}
+
+struct nfsd4_deviceid_map *
+nfsd4_find_devid_map(int idx)
+{
+	struct nfsd4_deviceid_map *map, *ret = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash)
+		if (map->idx == idx)
+			ret = map;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int
+nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation)
+{
+	if (!fhp->fh_export->ex_devid_map) {
+		nfsd4_alloc_devid_map(fhp);
+		if (!fhp->fh_export->ex_devid_map)
+			return -ENOMEM;
+	}
+
+	id->fsid_idx = fhp->fh_export->ex_devid_map->idx;
+	id->generation = device_generation;
+	id->pad = 0;
+	return 0;
+}
+
+void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
+
+	if (exp->ex_flags & NFSEXP_NOPNFS)
+		return;
+
+	if (sb->s_export_op->get_uuid &&
+	    sb->s_export_op->map_blocks &&
+	    sb->s_export_op->commit_blocks)
+		exp->ex_layout_type = LAYOUT_BLOCK_VOLUME;
+}
+
+static void
+nfsd4_free_layout_stateid(struct nfs4_stid *stid)
+{
+	struct nfs4_layout_stateid *ls = layoutstateid(stid);
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+
+	trace_layoutstate_free(&ls->ls_stid.sc_stateid);
+
+	spin_lock(&clp->cl_lock);
+	list_del_init(&ls->ls_perclnt);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_del_init(&ls->ls_perfile);
+	spin_unlock(&fp->fi_lock);
+
+	vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls);
+	fput(ls->ls_file);
+
+	if (ls->ls_recalled)
+		atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls);
+
+	kmem_cache_free(nfs4_layout_stateid_cache, ls);
+}
+
+static int
+nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
+{
+	struct file_lock *fl;
+	int status;
+
+	fl = locks_alloc_lock();
+	if (!fl)
+		return -ENOMEM;
+	locks_init_lock(fl);
+	fl->fl_lmops = &nfsd4_layouts_lm_ops;
+	fl->fl_flags = FL_LAYOUT;
+	fl->fl_type = F_RDLCK;
+	fl->fl_end = OFFSET_MAX;
+	fl->fl_owner = ls;
+	fl->fl_pid = current->tgid;
+	fl->fl_file = ls->ls_file;
+
+	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL);
+	if (status) {
+		locks_free_lock(fl);
+		return status;
+	}
+	BUG_ON(fl != NULL);
+	return 0;
+}
+
+static struct nfs4_layout_stateid *
+nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
+		struct nfs4_stid *parent, u32 layout_type)
+{
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_file *fp = parent->sc_file;
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stp;
+
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+	if (!stp)
+		return NULL;
+	stp->sc_free = nfsd4_free_layout_stateid;
+	get_nfs4_file(fp);
+	stp->sc_file = fp;
+
+	ls = layoutstateid(stp);
+	INIT_LIST_HEAD(&ls->ls_perclnt);
+	INIT_LIST_HEAD(&ls->ls_perfile);
+	spin_lock_init(&ls->ls_lock);
+	INIT_LIST_HEAD(&ls->ls_layouts);
+	ls->ls_layout_type = layout_type;
+	nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops,
+			NFSPROC4_CLNT_CB_LAYOUT);
+
+	if (parent->sc_type == NFS4_DELEG_STID)
+		ls->ls_file = get_file(fp->fi_deleg_file);
+	else
+		ls->ls_file = find_any_file(fp);
+	BUG_ON(!ls->ls_file);
+
+	if (nfsd4_layout_setlease(ls)) {
+		put_nfs4_file(fp);
+		kmem_cache_free(nfs4_layout_stateid_cache, ls);
+		return NULL;
+	}
+
+	spin_lock(&clp->cl_lock);
+	stp->sc_type = NFS4_LAYOUT_STID;
+	list_add(&ls->ls_perclnt, &clp->cl_lo_states);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_add(&ls->ls_perfile, &fp->fi_lo_states);
+	spin_unlock(&fp->fi_lock);
+
+	trace_layoutstate_alloc(&ls->ls_stid.sc_stateid);
+	return ls;
+}
+
+__be32
+nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stid;
+	unsigned char typemask = NFS4_LAYOUT_STID;
+	__be32 status;
+
+	if (create)
+		typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID);
+
+	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid,
+			net_generic(SVC_NET(rqstp), nfsd_net_id));
+	if (status)
+		goto out;
+
+	if (!fh_match(&cstate->current_fh.fh_handle,
+		      &stid->sc_file->fi_fhandle)) {
+		status = nfserr_bad_stateid;
+		goto out_put_stid;
+	}
+
+	if (stid->sc_type != NFS4_LAYOUT_STID) {
+		ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type);
+		nfs4_put_stid(stid);
+
+		status = nfserr_jukebox;
+		if (!ls)
+			goto out;
+	} else {
+		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
+
+		status = nfserr_bad_stateid;
+		if (stateid->si_generation > stid->sc_stateid.si_generation)
+			goto out_put_stid;
+		if (layout_type != ls->ls_layout_type)
+			goto out_put_stid;
+	}
+
+	*lsp = ls;
+	return 0;
+
+out_put_stid:
+	nfs4_put_stid(stid);
+out:
+	return status;
+}
+
+static void
+nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls)
+{
+	spin_lock(&ls->ls_lock);
+	if (ls->ls_recalled)
+		goto out_unlock;
+
+	ls->ls_recalled = true;
+	atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls);
+	if (list_empty(&ls->ls_layouts))
+		goto out_unlock;
+
+	trace_layout_recall(&ls->ls_stid.sc_stateid);
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	nfsd4_run_cb(&ls->ls_recall);
+
+out_unlock:
+	spin_unlock(&ls->ls_lock);
+}
+
+static inline u64
+layout_end(struct nfsd4_layout_seg *seg)
+{
+	u64 end = seg->offset + seg->length;
+	return end >= seg->offset ? end : NFS4_MAX_UINT64;
+}
+
+static void
+layout_update_len(struct nfsd4_layout_seg *lo, u64 end)
+{
+	if (end == NFS4_MAX_UINT64)
+		lo->length = NFS4_MAX_UINT64;
+	else
+		lo->length = end - lo->offset;
+}
+
+static bool
+layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s)
+{
+	if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode)
+		return false;
+	if (layout_end(&lo->lo_seg) <= s->offset)
+		return false;
+	if (layout_end(s) <= lo->lo_seg.offset)
+		return false;
+	return true;
+}
+
+static bool
+layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new)
+{
+	if (lo->iomode != new->iomode)
+		return false;
+	if (layout_end(new) < lo->offset)
+		return false;
+	if (layout_end(lo) < new->offset)
+		return false;
+
+	lo->offset = min(lo->offset, new->offset);
+	layout_update_len(lo, max(layout_end(lo), layout_end(new)));
+	return true;
+}
+
+static __be32
+nfsd4_recall_conflict(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout_stateid *l, *n;
+	__be32 nfserr = nfs_ok;
+
+	assert_spin_locked(&fp->fi_lock);
+
+	list_for_each_entry_safe(l, n, &fp->fi_lo_states, ls_perfile) {
+		if (l != ls) {
+			nfsd4_recall_file_layout(l);
+			nfserr = nfserr_recallconflict;
+		}
+	}
+
+	return nfserr;
+}
+
+__be32
+nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls)
+{
+	struct nfsd4_layout_seg *seg = &lgp->lg_seg;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout *lp, *new = NULL;
+	__be32 nfserr;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+	spin_unlock(&ls->ls_lock);
+	spin_unlock(&fp->fi_lock);
+
+	new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL);
+	if (!new)
+		return nfserr_jukebox;
+	memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg));
+	new->lo_state = ls;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	list_add_tail(&new->lo_perstate, &ls->ls_layouts);
+	new = NULL;
+done:
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	spin_unlock(&ls->ls_lock);
+out:
+	spin_unlock(&fp->fi_lock);
+	if (new)
+		kmem_cache_free(nfs4_layout_cache, new);
+	return nfserr;
+}
+
+static void
+nfsd4_free_layouts(struct list_head *reaplist)
+{
+	while (!list_empty(reaplist)) {
+		struct nfs4_layout *lp = list_first_entry(reaplist,
+				struct nfs4_layout, lo_perstate);
+
+		list_del(&lp->lo_perstate);
+		nfs4_put_stid(&lp->lo_state->ls_stid);
+		kmem_cache_free(nfs4_layout_cache, lp);
+	}
+}
+
+static void
+nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
+		struct list_head *reaplist)
+{
+	struct nfsd4_layout_seg *lo = &lp->lo_seg;
+	u64 end = layout_end(lo);
+
+	if (seg->offset <= lo->offset) {
+		if (layout_end(seg) >= end) {
+			list_move_tail(&lp->lo_perstate, reaplist);
+			return;
+		}
+		end = seg->offset;
+	} else {
+		/* retain the whole layout segment on a split. */
+		if (layout_end(seg) < end) {
+			dprintk("%s: split not supported\n", __func__);
+			return;
+		}
+
+		lo->offset = layout_end(seg);
+	}
+
+	layout_update_len(lo, end);
+}
+
+__be32
+nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_layout *lp, *n;
+	LIST_HEAD(reaplist);
+	__be32 nfserr;
+	int found = 0;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid,
+						false, lrp->lr_layout_type,
+						&ls);
+	if (nfserr) {
+		trace_layout_return_lookup_fail(&lrp->lr_sid);
+		return nfserr;
+	}
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) {
+		if (layouts_overlapping(lp, &lrp->lr_seg)) {
+			nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist);
+			found++;
+		}
+	}
+	if (!list_empty(&ls->ls_layouts)) {
+		if (found) {
+			update_stateid(&ls->ls_stid.sc_stateid);
+			memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid,
+				sizeof(stateid_t));
+		}
+		lrp->lrs_present = 1;
+	} else {
+		trace_layoutstate_unhash(&ls->ls_stid.sc_stateid);
+		nfs4_unhash_stid(&ls->ls_stid);
+		lrp->lrs_present = 0;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	nfs4_put_stid(&ls->ls_stid);
+	nfsd4_free_layouts(&reaplist);
+	return nfs_ok;
+}
+
+__be32
+nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_layout *lp, *t;
+	LIST_HEAD(reaplist);
+
+	lrp->lrs_present = 0;
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+		if (lrp->lr_return_type == RETURN_FSID &&
+		    !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
+				   &cstate->current_fh.fh_handle))
+			continue;
+
+		spin_lock(&ls->ls_lock);
+		list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) {
+			if (lrp->lr_seg.iomode == IOMODE_ANY ||
+			    lrp->lr_seg.iomode == lp->lo_seg.iomode)
+				list_move_tail(&lp->lo_perstate, &reaplist);
+		}
+		spin_unlock(&ls->ls_lock);
+	}
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+	return 0;
+}
+
+static void
+nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls,
+		struct list_head *reaplist)
+{
+	spin_lock(&ls->ls_lock);
+	list_splice_init(&ls->ls_layouts, reaplist);
+	spin_unlock(&ls->ls_lock);
+}
+
+void
+nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt)
+		nfsd4_return_all_layouts(ls, &reaplist);
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+void
+nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) {
+		if (ls->ls_stid.sc_client == clp)
+			nfsd4_return_all_layouts(ls, &reaplist);
+	}
+	spin_unlock(&fp->fi_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+static void
+nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	char addr_str[INET6_ADDRSTRLEN];
+	static char *envp[] = {
+		"HOME=/",
+		"TERM=linux",
+		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+		NULL
+	};
+	char *argv[8];
+	int error;
+
+	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
+
+	nfsd4_cb_layout_fail(ls);
+
+	printk(KERN_WARNING
+		"nfsd: client %s failed to respond to layout recall. "
+		"  Fencing..\n", addr_str);
+
+	argv[0] = "/sbin/nfsd-recall-failed";
+	argv[1] = addr_str;
+	argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id;
+	argv[3] = NULL;
+
+	error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+	if (error) {
+		printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n",
+			addr_str, error);
+	}
+}
+
+static int
+nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	LIST_HEAD(reaplist);
+
+	switch (task->tk_status) {
+	case 0:
+		return 1;
+	case -NFS4ERR_NOMATCHING_LAYOUT:
+		trace_layout_recall_done(&ls->ls_stid.sc_stateid);
+		task->tk_status = 0;
+		return 1;
+	case -NFS4ERR_DELAY:
+		/* Poll the client until it's done with the layout */
+		/* FIXME: cap number of retries.
+		 * The pnfs standard states that we need to only expire
+		 * the client after at-least "lease time" .eg lease-time * 2
+		 * when failing to communicate a recall
+		 */
+		rpc_delay(task, HZ/100); /* 10 mili-seconds */
+		return 0;
+	default:
+		/*
+		 * Unknown error or non-responding client, we'll need to fence.
+		 */
+		nfsd4_cb_layout_fail(ls);
+		return -1;
+	}
+}
+
+static void
+nfsd4_cb_layout_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	LIST_HEAD(reaplist);
+
+	trace_layout_recall_release(&ls->ls_stid.sc_stateid);
+
+	nfsd4_return_all_layouts(ls, &reaplist);
+	nfsd4_free_layouts(&reaplist);
+	nfs4_put_stid(&ls->ls_stid);
+}
+
+static struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+	.done		= nfsd4_cb_layout_done,
+	.release	= nfsd4_cb_layout_release,
+};
+
+static bool
+nfsd4_layout_lm_break(struct file_lock *fl)
+{
+	/*
+	 * We don't want the locks code to timeout the lease for us;
+	 * we'll remove it ourself if a layout isn't returned
+	 * in time:
+	 */
+	fl->fl_break_time = 0;
+	nfsd4_recall_file_layout(fl->fl_owner);
+	return false;
+}
+
+static int
+nfsd4_layout_lm_change(struct file_lock *onlist, int arg,
+		struct list_head *dispose)
+{
+	BUG_ON(!(arg & F_UNLCK));
+	return lease_modify(onlist, arg, dispose);
+}
+
+static const struct lock_manager_operations nfsd4_layouts_lm_ops = {
+	.lm_break	= nfsd4_layout_lm_break,
+	.lm_change	= nfsd4_layout_lm_change,
+};
+
+int
+nfsd4_init_pnfs(void)
+{
+	int i;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&nfsd_devid_hash[i]);
+
+	nfs4_layout_cache = kmem_cache_create("nfs4_layout",
+			sizeof(struct nfs4_layout), 0, 0, NULL);
+	if (!nfs4_layout_cache)
+		return -ENOMEM;
+
+	nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid",
+			sizeof(struct nfs4_layout_stateid), 0, 0, NULL);
+	if (!nfs4_layout_stateid_cache) {
+		kmem_cache_destroy(nfs4_layout_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void
+nfsd4_exit_pnfs(void)
+{
+	int i;
+
+	kmem_cache_destroy(nfs4_layout_cache);
+	kmem_cache_destroy(nfs4_layout_stateid_cache);
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		struct nfsd4_deviceid_map *map, *n;
+
+		list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash)
+			kfree(map);
+	}
+}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ac71d13c69ef37..d30bea8d0277ab 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -43,6 +43,8 @@
 #include "current_stateid.h"
 #include "netns.h"
 #include "acl.h"
+#include "pnfs.h"
+#include "trace.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1178,6 +1180,259 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status == nfserr_same ? nfs_ok : status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static const struct nfsd4_layout_ops *
+nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
+{
+	if (!exp->ex_layout_type) {
+		dprintk("%s: export does not support pNFS\n", __func__);
+		return NULL;
+	}
+
+	if (exp->ex_layout_type != layout_type) {
+		dprintk("%s: layout type %d not supported\n",
+			__func__, layout_type);
+		return NULL;
+	}
+
+	return nfsd4_layout_ops[layout_type];
+}
+
+static __be32
+nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	const struct nfsd4_layout_ops *ops;
+	struct nfsd4_deviceid_map *map;
+	struct svc_export *exp;
+	__be32 nfserr;
+
+	dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n",
+	       __func__,
+	       gdp->gd_layout_type,
+	       gdp->gd_devid.fsid_idx, gdp->gd_devid.generation,
+	       gdp->gd_maxcount);
+
+	map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx);
+	if (!map) {
+		dprintk("%s: couldn't find device ID to export mapping!\n",
+			__func__);
+		return nfserr_noent;
+	}
+
+	exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid);
+	if (IS_ERR(exp)) {
+		dprintk("%s: could not find device id\n", __func__);
+		return nfserr_noent;
+	}
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(exp, gdp->gd_layout_type);
+	if (!ops)
+		goto out;
+
+	nfserr = nfs_ok;
+	if (gdp->gd_maxcount != 0)
+		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
+
+	gdp->gd_notify_types &= ops->notify_types;
+	exp_put(exp);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutget(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutget *lgp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+	int accmode;
+
+	switch (lgp->lg_seg.iomode) {
+	case IOMODE_READ:
+		accmode = NFSD_MAY_READ;
+		break;
+	case IOMODE_RW:
+		accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n",
+			__func__, lgp->lg_seg.iomode);
+		nfserr = nfserr_badiomode;
+		goto out;
+	}
+
+	nfserr = fh_verify(rqstp, current_fh, 0, accmode);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type);
+	if (!ops)
+		goto out;
+
+	/*
+	 * Verify minlength and range as per RFC5661:
+	 *  o  If loga_length is less than loga_minlength,
+	 *     the metadata server MUST return NFS4ERR_INVAL.
+	 *  o  If the sum of loga_offset and loga_minlength exceeds
+	 *     NFS4_UINT64_MAX, and loga_minlength is not
+	 *     NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result.
+	 *  o  If the sum of loga_offset and loga_length exceeds
+	 *     NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX,
+	 *     the error NFS4ERR_INVAL MUST result.
+	 */
+	nfserr = nfserr_inval;
+	if (lgp->lg_seg.length < lgp->lg_minlength ||
+	    (lgp->lg_minlength != NFS4_MAX_UINT64 &&
+	     lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) ||
+	    (lgp->lg_seg.length != NFS4_MAX_UINT64 &&
+	     lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset))
+		goto out;
+	if (lgp->lg_seg.length == 0)
+		goto out;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
+						true, lgp->lg_layout_type, &ls);
+	if (nfserr) {
+		trace_layout_get_lookup_fail(&lgp->lg_sid);
+		goto out;
+	}
+
+	nfserr = nfserr_recallconflict;
+	if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls))
+		goto out_put_stid;
+
+	nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode,
+				     current_fh, lgp);
+	if (nfserr)
+		goto out_put_stid;
+
+	nfserr = nfsd4_insert_layout(lgp, ls);
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutcommit(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutcommit *lcp)
+{
+	const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct inode *inode;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type);
+	if (!ops)
+		goto out;
+	inode = current_fh->fh_dentry->d_inode;
+
+	nfserr = nfserr_inval;
+	if (new_size <= seg->offset) {
+		dprintk("pnfsd: last write before layout segment\n");
+		goto out;
+	}
+	if (new_size > seg->offset + seg->length) {
+		dprintk("pnfsd: last write beyond layout segment\n");
+		goto out;
+	}
+	if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
+		dprintk("pnfsd: layoutcommit beyond EOF\n");
+		goto out;
+	}
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
+						false, lcp->lc_layout_type,
+						&ls);
+	if (nfserr) {
+		trace_layout_commit_lookup_fail(&lcp->lc_sid);
+		/* fixup error code as per RFC5661 */
+		if (nfserr == nfserr_bad_stateid)
+			nfserr = nfserr_badlayout;
+		goto out;
+	}
+
+	nfserr = ops->proc_layoutcommit(inode, lcp);
+	if (nfserr)
+		goto out_put_stid;
+
+	if (new_size > i_size_read(inode)) {
+		lcp->lc_size_chg = 1;
+		lcp->lc_newsize = new_size;
+	} else {
+		lcp->lc_size_chg = 0;
+	}
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutreturn(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type))
+		goto out;
+
+	switch (lrp->lr_seg.iomode) {
+	case IOMODE_READ:
+	case IOMODE_RW:
+	case IOMODE_ANY:
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n", __func__,
+			lrp->lr_seg.iomode);
+		nfserr = nfserr_inval;
+		goto out;
+	}
+
+	switch (lrp->lr_return_type) {
+	case RETURN_FILE:
+		nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp);
+		break;
+	case RETURN_FSID:
+	case RETURN_ALL:
+		nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp);
+		break;
+	default:
+		dprintk("%s: invalid return_type %d\n", __func__,
+			lrp->lr_return_type);
+		nfserr = nfserr_inval;
+		break;
+	}
+out:
+	return nfserr;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * NULL call.
  */
@@ -1679,6 +1934,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
 		op_encode_channel_attrs_maxsz) * sizeof(__be32);
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * At this stage we don't really know what layout driver will handle the request,
+ * so we need to define an arbitrary upper bound here.
+ */
+#define MAX_LAYOUT_SIZE		128
+static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* logr_return_on_close */ +
+		op_encode_stateid_maxsz +
+		1 /* nr of layouts */ +
+		MAX_LAYOUT_SIZE) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* locr_newsize */ +
+		2 /* ns_size */) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* lrs_stateid */ +
+		op_encode_stateid_maxsz) * sizeof(__be32);
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = (nfsd4op_func)nfsd4_access,
@@ -1966,6 +2251,31 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO] = {
+		.op_func = (nfsd4op_func)nfsd4_getdeviceinfo,
+		.op_flags = ALLOWED_WITHOUT_FH,
+		.op_name = "OP_GETDEVICEINFO",
+	},
+	[OP_LAYOUTGET] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutget,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTGET",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize,
+	},
+	[OP_LAYOUTCOMMIT] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutcommit,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTCOMMIT",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize,
+	},
+	[OP_LAYOUTRETURN] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutreturn,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTRETURN",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize,
+	},
+#endif /* CONFIG_NFSD_PNFS */
 
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE] = {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 532a60cca2fbd6..f6b2a09f793f45 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -48,6 +48,7 @@
 #include "current_stateid.h"
 
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -150,16 +151,6 @@ renew_client_locked(struct nfs4_client *clp)
 	clp->cl_time = get_seconds();
 }
 
-static inline void
-renew_client(struct nfs4_client *clp)
-{
-	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-
-	spin_lock(&nn->client_lock);
-	renew_client_locked(clp);
-	spin_unlock(&nn->client_lock);
-}
-
 static void put_client_renew_locked(struct nfs4_client *clp)
 {
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
@@ -282,7 +273,7 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu)
 	kmem_cache_free(file_slab, fp);
 }
 
-static inline void
+void
 put_nfs4_file(struct nfs4_file *fi)
 {
 	might_lock(&state_lock);
@@ -295,12 +286,6 @@ put_nfs4_file(struct nfs4_file *fi)
 	}
 }
 
-static inline void
-get_nfs4_file(struct nfs4_file *fi)
-{
-	atomic_inc(&fi->fi_ref);
-}
-
 static struct file *
 __nfs4_get_fd(struct nfs4_file *f, int oflag)
 {
@@ -358,7 +343,7 @@ find_readable_file(struct nfs4_file *f)
 	return ret;
 }
 
-static struct file *
+struct file *
 find_any_file(struct nfs4_file *f)
 {
 	struct file *ret;
@@ -408,14 +393,6 @@ static unsigned int file_hashval(struct knfsd_fh *fh)
 	return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1);
 }
 
-static bool nfsd_fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
-{
-	return fh1->fh_size == fh2->fh_size &&
-		!memcmp(fh1->fh_base.fh_pad,
-				fh2->fh_base.fh_pad,
-				fh1->fh_size);
-}
-
 static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
 
 static void
@@ -494,7 +471,7 @@ static void nfs4_file_put_access(struct nfs4_file *fp, u32 access)
 		__nfs4_file_put_access(fp, O_RDONLY);
 }
 
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 					 struct kmem_cache *slab)
 {
 	struct nfs4_stid *stid;
@@ -688,17 +665,17 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 	struct file *filp = NULL;
 
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_deleg_file && atomic_dec_and_test(&fp->fi_delegees))
+	if (fp->fi_deleg_file && --fp->fi_delegees == 0)
 		swap(filp, fp->fi_deleg_file);
 	spin_unlock(&fp->fi_lock);
 
 	if (filp) {
-		vfs_setlease(filp, F_UNLCK, NULL, NULL);
+		vfs_setlease(filp, F_UNLCK, NULL, (void **)&fp);
 		fput(filp);
 	}
 }
 
-static void unhash_stid(struct nfs4_stid *s)
+void nfs4_unhash_stid(struct nfs4_stid *s)
 {
 	s->sc_type = 0;
 }
@@ -1006,7 +983,7 @@ static void unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 
 	list_del_init(&stp->st_locks);
 	unhash_ol_stateid(stp);
-	unhash_stid(&stp->st_stid);
+	nfs4_unhash_stid(&stp->st_stid);
 }
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -1518,7 +1495,12 @@ unhash_session(struct nfsd4_session *ses)
 static int
 STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
 {
-	if (clid->cl_boot == nn->boot_time)
+	/*
+	 * We're assuming the clid was not given out from a boot
+	 * precisely 2^32 (about 136 years) before this one.  That seems
+	 * a safe assumption:
+	 */
+	if (clid->cl_boot == (u32)nn->boot_time)
 		return 0;
 	dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
 		clid->cl_boot, clid->cl_id, nn->boot_time);
@@ -1558,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 	INIT_LIST_HEAD(&clp->cl_lru);
 	INIT_LIST_HEAD(&clp->cl_callbacks);
 	INIT_LIST_HEAD(&clp->cl_revoked);
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&clp->cl_lo_states);
+#endif
 	spin_lock_init(&clp->cl_lock);
 	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
@@ -1662,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
+	nfsd4_return_all_client_layouts(clp);
 	nfsd4_shutdown_callback(clp);
 	if (clp->cl_cb_conn.cb_xprt)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@@ -2145,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 static void
 nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
 {
-	/* pNFS is not supported */
+#ifdef CONFIG_NFSD_PNFS
+	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
+#else
 	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
+#endif
 
 	/* Referrals are supported, Migration is not. */
 	new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;
@@ -3074,6 +3063,10 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&fp->fi_lo_states);
+	atomic_set(&fp->fi_lo_recalls, 0);
+#endif
 	hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
 }
 
@@ -3300,7 +3293,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 	struct nfs4_file *fp;
 
 	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) {
-		if (nfsd_fh_match(&fp->fi_fhandle, fh)) {
+		if (fh_match(&fp->fi_fhandle, fh)) {
 			if (atomic_inc_not_zero(&fp->fi_ref))
 				return fp;
 		}
@@ -3308,7 +3301,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 	return NULL;
 }
 
-static struct nfs4_file *
+struct nfs4_file *
 find_file(struct knfsd_fh *fh)
 {
 	struct nfs4_file *fp;
@@ -3856,12 +3849,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	/* Race breaker */
 	if (fp->fi_deleg_file) {
 		status = 0;
-		atomic_inc(&fp->fi_delegees);
+		++fp->fi_delegees;
 		hash_delegation_locked(dp, fp);
 		goto out_unlock;
 	}
 	fp->fi_deleg_file = filp;
-	atomic_set(&fp->fi_delegees, 1);
+	fp->fi_delegees = 1;
 	hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
@@ -3902,7 +3895,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		status = -EAGAIN;
 		goto out_unlock;
 	}
-	atomic_inc(&fp->fi_delegees);
+	++fp->fi_delegees;
 	hash_delegation_locked(dp, fp);
 	status = 0;
 out_unlock:
@@ -4295,7 +4288,7 @@ laundromat_main(struct work_struct *laundry)
 
 static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
 {
-	if (!nfsd_fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
+	if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
 		return nfserr_bad_stateid;
 	return nfs_ok;
 }
@@ -4446,7 +4439,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	return status;
 }
 
-static __be32
+__be32
 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn)
@@ -4860,6 +4853,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
+	nfsd4_return_all_file_layouts(stp->st_stateowner->so_client,
+				      stp->st_stid.sc_file);
+
 	nfsd4_close_open_stateid(stp);
 
 	/* put reference from nfs4_preprocess_seqid_op */
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 15f7b73e0c0fd8..df5e66caf100ca 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -47,6 +47,7 @@
 #include "state.h"
 #include "cache.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -234,6 +235,26 @@ static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes)
 	return ret;
 }
 
+/*
+ * We require the high 32 bits of 'seconds' to be 0, and
+ * we ignore all 32 bits of 'nseconds'.
+ */
+static __be32
+nfsd4_decode_time(struct nfsd4_compoundargs *argp, struct timespec *tv)
+{
+	DECODE_HEAD;
+	u64 sec;
+
+	READ_BUF(12);
+	p = xdr_decode_hyper(p, &sec);
+	tv->tv_sec = sec;
+	tv->tv_nsec = be32_to_cpup(p++);
+	if (tv->tv_nsec >= (u32)1000000000)
+		return nfserr_inval;
+
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
 {
@@ -267,7 +288,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 {
 	int expected_len, len = 0;
 	u32 dummy32;
-	u64 sec;
 	char *buf;
 
 	DECODE_HEAD;
@@ -358,15 +378,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
-			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
-			   all 32 bits of 'nseconds'. */
-			READ_BUF(12);
 			len += 12;
-			p = xdr_decode_hyper(p, &sec);
-			iattr->ia_atime.tv_sec = (time_t)sec;
-			iattr->ia_atime.tv_nsec = be32_to_cpup(p++);
-			if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
-				return nfserr_inval;
+			status = nfsd4_decode_time(argp, &iattr->ia_atime);
+			if (status)
+				return status;
 			iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET);
 			break;
 		case NFS4_SET_TO_SERVER_TIME:
@@ -382,15 +397,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
-			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
-			   all 32 bits of 'nseconds'. */
-			READ_BUF(12);
 			len += 12;
-			p = xdr_decode_hyper(p, &sec);
-			iattr->ia_mtime.tv_sec = sec;
-			iattr->ia_mtime.tv_nsec = be32_to_cpup(p++);
-			if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
-				return nfserr_inval;
+			status = nfsd4_decode_time(argp, &iattr->ia_mtime);
+			if (status)
+				return status;
 			iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET);
 			break;
 		case NFS4_SET_TO_SERVER_TIME:
@@ -1513,6 +1523,127 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	DECODE_HEAD;
+	u32 num, i;
+
+	READ_BUF(sizeof(struct nfsd4_deviceid) + 3 * 4);
+	COPYMEM(&gdev->gd_devid, sizeof(struct nfsd4_deviceid));
+	gdev->gd_layout_type = be32_to_cpup(p++);
+	gdev->gd_maxcount = be32_to_cpup(p++);
+	num = be32_to_cpup(p++);
+	if (num) {
+		READ_BUF(4 * num);
+		gdev->gd_notify_types = be32_to_cpup(p++);
+		for (i = 1; i < num; i++) {
+			if (be32_to_cpup(p++)) {
+				status = nfserr_inval;
+				goto out;
+			}
+		}
+	}
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutget *lgp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(36);
+	lgp->lg_signal = be32_to_cpup(p++);
+	lgp->lg_layout_type = be32_to_cpup(p++);
+	lgp->lg_seg.iomode = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.offset);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.length);
+	p = xdr_decode_hyper(p, &lgp->lg_minlength);
+	nfsd4_decode_stateid(argp, &lgp->lg_sid);
+	READ_BUF(4);
+	lgp->lg_maxcount = be32_to_cpup(p++);
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	DECODE_HEAD;
+	u32 timechange;
+
+	READ_BUF(20);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.offset);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.length);
+	lcp->lc_reclaim = be32_to_cpup(p++);
+	nfsd4_decode_stateid(argp, &lcp->lc_sid);
+	READ_BUF(4);
+	lcp->lc_newoffset = be32_to_cpup(p++);
+	if (lcp->lc_newoffset) {
+		READ_BUF(8);
+		p = xdr_decode_hyper(p, &lcp->lc_last_wr);
+	} else
+		lcp->lc_last_wr = 0;
+	READ_BUF(4);
+	timechange = be32_to_cpup(p++);
+	if (timechange) {
+		status = nfsd4_decode_time(argp, &lcp->lc_mtime);
+		if (status)
+			return status;
+	} else {
+		lcp->lc_mtime.tv_nsec = UTIME_NOW;
+	}
+	READ_BUF(8);
+	lcp->lc_layout_type = be32_to_cpup(p++);
+
+	/*
+	 * Save the layout update in XDR format and let the layout driver deal
+	 * with it later.
+	 */
+	lcp->lc_up_len = be32_to_cpup(p++);
+	if (lcp->lc_up_len > 0) {
+		READ_BUF(lcp->lc_up_len);
+		READMEM(lcp->lc_up_layout, lcp->lc_up_len);
+	}
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutreturn *lrp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(16);
+	lrp->lr_reclaim = be32_to_cpup(p++);
+	lrp->lr_layout_type = be32_to_cpup(p++);
+	lrp->lr_seg.iomode = be32_to_cpup(p++);
+	lrp->lr_return_type = be32_to_cpup(p++);
+	if (lrp->lr_return_type == RETURN_FILE) {
+		READ_BUF(16);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.offset);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.length);
+		nfsd4_decode_stateid(argp, &lrp->lr_sid);
+		READ_BUF(4);
+		lrp->lrf_body_len = be32_to_cpup(p++);
+		if (lrp->lrf_body_len > 0) {
+			READ_BUF(lrp->lrf_body_len);
+			READMEM(lrp->lrf_body, lrp->lrf_body_len);
+		}
+	} else {
+		lrp->lr_seg.offset = 0;
+		lrp->lr_seg.length = NFS4_MAX_UINT64;
+	}
+
+	DECODE_TAIL;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp,
 		       struct nfsd4_fallocate *fallocate)
@@ -1607,11 +1738,19 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_dec)nfsd4_decode_destroy_session,
 	[OP_FREE_STATEID]	= (nfsd4_dec)nfsd4_decode_free_stateid,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_dec)nfsd4_decode_sequence,
 	[OP_SET_SSV]		= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2539,6 +2678,30 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 			get_parent_attributes(exp, &stat);
 		p = xdr_encode_hyper(p, stat.ino);
 	}
+#ifdef CONFIG_NFSD_PNFS
+	if ((bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) ||
+	    (bmval2 & FATTR4_WORD2_LAYOUT_TYPES)) {
+		if (exp->ex_layout_type) {
+			p = xdr_reserve_space(xdr, 8);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(1);
+			*p++ = cpu_to_be32(exp->ex_layout_type);
+		} else {
+			p = xdr_reserve_space(xdr, 4);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(0);
+		}
+	}
+
+	if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out_resource;
+		*p++ = cpu_to_be32(stat.blksize);
+	}
+#endif /* CONFIG_NFSD_PNFS */
 	if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
 		status = nfsd4_encode_security_label(xdr, rqstp, context,
 								contextlen);
@@ -2768,16 +2931,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 	if (entry_bytes > cd->rd_maxcount)
 		goto fail;
 	cd->rd_maxcount -= entry_bytes;
-	if (!cd->rd_dircount)
-		goto fail;
 	/*
 	 * RFC 3530 14.2.24 describes rd_dircount as only a "hint", so
 	 * let's always let through the first entry, at least:
 	 */
-	name_and_cookie = 4 * XDR_QUADLEN(namlen) + 8;
+	if (!cd->rd_dircount)
+		goto fail;
+	name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8;
 	if (name_and_cookie > cd->rd_dircount && cd->cookie_offset)
 		goto fail;
 	cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie);
+
 	cd->cookie_offset = cookie_offset;
 skip_entry:
 	cd->common.err = nfs_ok;
@@ -3814,6 +3978,156 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	return nfserr;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[gdev->gd_layout_type];
+	u32 starting_len = xdr->buf->len, needed_len;
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(gdev->gd_layout_type);
+
+	/* If maxcount is 0 then just update notifications */
+	if (gdev->gd_maxcount != 0) {
+		nfserr = ops->encode_getdeviceinfo(xdr, gdev);
+		if (nfserr) {
+			/*
+			 * We don't bother to burden the layout drivers with
+			 * enforcing gd_maxcount, just tell the client to
+			 * come back with a bigger buffer if it's not enough.
+			 */
+			if (xdr->buf->len + 4 > gdev->gd_maxcount)
+				goto toosmall;
+			goto out;
+		}
+	}
+
+	nfserr = nfserr_resource;
+	if (gdev->gd_notify_types) {
+		p = xdr_reserve_space(xdr, 4 + 4);
+		if (!p)
+			goto out;
+		*p++ = cpu_to_be32(1);			/* bitmap length */
+		*p++ = cpu_to_be32(gdev->gd_notify_types);
+	} else {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out;
+		*p++ = 0;
+	}
+
+	nfserr = 0;
+out:
+	kfree(gdev->gd_device);
+	dprintk("%s: done: %d\n", __func__, be32_to_cpu(nfserr));
+	return nfserr;
+
+toosmall:
+	dprintk("%s: maxcount too small\n", __func__);
+	needed_len = xdr->buf->len + 4 /* notifications */;
+	xdr_truncate_encode(xdr, starting_len);
+	p = xdr_reserve_space(xdr, 4);
+	if (!p) {
+		nfserr = nfserr_resource;
+	} else {
+		*p++ = cpu_to_be32(needed_len);
+		nfserr = nfserr_toosmall;
+	}
+	goto out;
+}
+
+static __be32
+nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[lgp->lg_layout_type];
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t));
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(1);	/* we always set return-on-close */
+	*p++ = cpu_to_be32(lgp->lg_sid.si_generation);
+	p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque,
+				    sizeof(stateid_opaque_t));
+
+	*p++ = cpu_to_be32(1);	/* we always return a single layout */
+	p = xdr_encode_hyper(p, lgp->lg_seg.offset);
+	p = xdr_encode_hyper(p, lgp->lg_seg.length);
+	*p++ = cpu_to_be32(lgp->lg_seg.iomode);
+	*p++ = cpu_to_be32(lgp->lg_layout_type);
+
+	nfserr = ops->encode_layoutget(xdr, lgp);
+out:
+	kfree(lgp->lg_content);
+	return nfserr;
+}
+
+static __be32
+nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr,
+			  struct nfsd4_layoutcommit *lcp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lcp->lc_size_chg);
+	if (lcp->lc_size_chg) {
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_hyper(p, lcp->lc_newsize);
+	}
+
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lrp->lrs_present);
+	if (lrp->lrs_present)
+		nfsd4_encode_stateid(xdr, &lrp->lr_sid);
+	return nfs_ok;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_seek *seek)
@@ -3890,11 +4204,19 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_FREE_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_noop,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_enc)nfsd4_encode_sequence,
 	[OP_SET_SSV]		= (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 19ace74d35f6f2..aa47d75ddb2631 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -21,6 +21,7 @@
 #include "cache.h"
 #include "state.h"
 #include "netns.h"
+#include "pnfs.h"
 
 /*
  *	We have a single directory with several nodes in it.
@@ -1258,9 +1259,12 @@ static int __init init_nfsd(void)
 	retval = nfsd4_init_slabs();
 	if (retval)
 		goto out_unregister_pernet;
-	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	retval = nfsd4_init_pnfs();
 	if (retval)
 		goto out_free_slabs;
+	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	if (retval)
+		goto out_exit_pnfs;
 	nfsd_stat_init();	/* Statistics */
 	retval = nfsd_reply_cache_init();
 	if (retval)
@@ -1282,6 +1286,8 @@ static int __init init_nfsd(void)
 out_free_stat:
 	nfsd_stat_shutdown();
 	nfsd_fault_inject_cleanup();
+out_exit_pnfs:
+	nfsd4_exit_pnfs();
 out_free_slabs:
 	nfsd4_free_slabs();
 out_unregister_pernet:
@@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void)
 	nfsd_stat_shutdown();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();
+	nfsd4_exit_pnfs();
 	nfsd_fault_inject_cleanup();
 	unregister_filesystem(&nfsd_fs_type);
 	unregister_pernet_subsys(&nfsd_net_ops);
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 33a46a8dfaf73a..565c4da1a9eb9d 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -325,15 +325,27 @@ void		nfsd_lockd_shutdown(void);
 
 #define NFSD4_SUPPORTED_ATTRS_WORD2 0
 
+/* 4.1 */
+#ifdef CONFIG_NFSD_PNFS
+#define PNFSD_SUPPORTED_ATTRS_WORD1	FATTR4_WORD1_FS_LAYOUT_TYPES
+#define PNFSD_SUPPORTED_ATTRS_WORD2 \
+(FATTR4_WORD2_LAYOUT_BLKSIZE	| FATTR4_WORD2_LAYOUT_TYPES)
+#else
+#define PNFSD_SUPPORTED_ATTRS_WORD1	0
+#define PNFSD_SUPPORTED_ATTRS_WORD2	0
+#endif /* CONFIG_NFSD_PNFS */
+
 #define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
 	NFSD4_SUPPORTED_ATTRS_WORD0
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
-	NFSD4_SUPPORTED_ATTRS_WORD1
+	(NFSD4_SUPPORTED_ATTRS_WORD1	| PNFSD_SUPPORTED_ATTRS_WORD1)
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
-	(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+	(NFSD4_SUPPORTED_ATTRS_WORD2	| PNFSD_SUPPORTED_ATTRS_WORD2 | \
+	 FATTR4_WORD2_SUPPATTR_EXCLCREAT)
 
+/* 4.2 */
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
 #else
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 08236d70c667e7..84cae2079d21bb 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -187,6 +187,24 @@ fh_init(struct svc_fh *fhp, int maxsize)
 	return fhp;
 }
 
+static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+{
+	if (fh1->fh_size != fh2->fh_size)
+		return false;
+	if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0)
+		return false;
+	return true;
+}
+
+static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+{
+	if (fh1->fh_fsid_type != fh2->fh_fsid_type)
+		return false;
+	if (memcmp(fh1->fh_fsid, fh2->fh_fsid, key_len(fh1->fh_fsid_type) != 0))
+		return false;
+	return true;
+}
+
 #ifdef CONFIG_NFSD_V3
 /*
  * The wcc data stored in current_fh should be cleared
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 314f5c8f8f1a9c..9277cc91c21b05 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -119,6 +119,7 @@ struct svc_program		nfsd_program = {
 static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = {
 	[0] = 1,
 	[1] = 1,
+	[2] = 1,
 };
 
 int nfsd_vers(int vers, enum vers_op change)
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
new file mode 100644
index 00000000000000..fedb4d620a81f0
--- /dev/null
+++ b/fs/nfsd/pnfs.h
@@ -0,0 +1,81 @@
+#ifndef _FS_NFSD_PNFS_H
+#define _FS_NFSD_PNFS_H 1
+
+#include <linux/exportfs.h>
+#include <linux/nfsd/export.h>
+
+#include "state.h"
+#include "xdr4.h"
+
+struct xdr_stream;
+
+struct nfsd4_deviceid_map {
+	struct list_head	hash;
+	u64			idx;
+	int			fsid_type;
+	u32			fsid[];
+};
+
+struct nfsd4_layout_ops {
+	u32		notify_types;
+
+	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct nfsd4_getdeviceinfo *gdevp);
+	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
+			struct nfsd4_getdeviceinfo *gdevp);
+
+	__be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp,
+			struct nfsd4_layoutget *lgp);
+	__be32 (*encode_layoutget)(struct xdr_stream *,
+			struct nfsd4_layoutget *lgp);
+
+	__be32 (*proc_layoutcommit)(struct inode *inode,
+			struct nfsd4_layoutcommit *lcp);
+};
+
+extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
+extern const struct nfsd4_layout_ops bl_layout_ops;
+
+__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp);
+__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp,
+		struct nfs4_layout_stateid *ls);
+__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation);
+struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx);
+
+#ifdef CONFIG_NFSD_PNFS
+void nfsd4_setup_layout_type(struct svc_export *exp);
+void nfsd4_return_all_client_layouts(struct nfs4_client *);
+void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp);
+int nfsd4_init_pnfs(void);
+void nfsd4_exit_pnfs(void);
+#else
+static inline void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+}
+
+static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+}
+static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp)
+{
+}
+static inline void nfsd4_exit_pnfs(void)
+{
+}
+static inline int nfsd4_init_pnfs(void)
+{
+	return 0;
+}
+#endif /* CONFIG_NFSD_PNFS */
+#endif /* _FS_NFSD_PNFS_H */
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 9d3be371240a58..4f3bfeb1176662 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -92,6 +92,7 @@ struct nfs4_stid {
 /* For a deleg stateid kept around only to process free_stateid's: */
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
+#define NFS4_LAYOUT_STID 64
 	unsigned char sc_type;
 	stateid_t sc_stateid;
 	struct nfs4_client *sc_client;
@@ -297,6 +298,9 @@ struct nfs4_client {
 	struct list_head	cl_delegations;
 	struct list_head	cl_revoked;	/* unacknowledged, revoked 4.1 state */
 	struct list_head        cl_lru;         /* tail queue */
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	cl_lo_states;	/* outstanding layout states */
+#endif
 	struct xdr_netobj	cl_name; 	/* id generated by client */
 	nfs4_verifier		cl_verifier; 	/* generated by client */
 	time_t                  cl_time;        /* time of last lease renewal */
@@ -493,9 +497,13 @@ struct nfs4_file {
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
 	struct file		*fi_deleg_file;
-	atomic_t		fi_delegees;
+	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	fi_lo_states;
+	atomic_t		fi_lo_recalls;
+#endif
 };
 
 /*
@@ -528,6 +536,24 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 	return container_of(s, struct nfs4_ol_stateid, st_stid);
 }
 
+struct nfs4_layout_stateid {
+	struct nfs4_stid		ls_stid;
+	struct list_head		ls_perclnt;
+	struct list_head		ls_perfile;
+	spinlock_t			ls_lock;
+	struct list_head		ls_layouts;
+	u32				ls_layout_type;
+	struct file			*ls_file;
+	struct nfsd4_callback		ls_recall;
+	stateid_t			ls_recall_sid;
+	bool				ls_recalled;
+};
+
+static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_layout_stateid, ls_stid);
+}
+
 /* flags for preprocess_seqid_op() */
 #define RD_STATE	        0x00000010
 #define WR_STATE	        0x00000020
@@ -535,6 +561,7 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_NULL = 0,
 	NFSPROC4_CLNT_CB_RECALL,
+	NFSPROC4_CLNT_CB_LAYOUT,
 	NFSPROC4_CLNT_CB_SEQUENCE,
 };
 
@@ -545,6 +572,12 @@ struct nfsd_net;
 extern __be32 nfs4_preprocess_stateid_op(struct net *net,
 		struct nfsd4_compound_state *cstate,
 		stateid_t *stateid, int flags, struct file **filp);
+__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
+		     stateid_t *stateid, unsigned char typemask,
+		     struct nfs4_stid **s, struct nfsd_net *nn);
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
+		struct kmem_cache *slab);
+void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
 extern void nfs4_release_reclaim(struct nfsd_net *);
@@ -567,6 +600,14 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
 							struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
 
+struct nfs4_file *find_file(struct knfsd_fh *fh);
+void put_nfs4_file(struct nfs4_file *fi);
+static inline void get_nfs4_file(struct nfs4_file *fi)
+{
+	atomic_inc(&fi->fi_ref);
+}
+struct file *find_any_file(struct nfs4_file *f);
+
 /* grace period management */
 void nfsd4_end_grace(struct nfsd_net *nn);
 
diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c
new file mode 100644
index 00000000000000..82f89070594c76
--- /dev/null
+++ b/fs/nfsd/trace.c
@@ -0,0 +1,5 @@
+
+#include "state.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
new file mode 100644
index 00000000000000..c668520c344b52
--- /dev/null
+++ b/fs/nfsd/trace.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nfsd
+
+#if !defined(_NFSD_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _NFSD_TRACE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(nfsd_stateid_class,
+	TP_PROTO(stateid_t *stp),
+	TP_ARGS(stp),
+	TP_STRUCT__entry(
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, si_id)
+		__field(u32, si_generation)
+	),
+	TP_fast_assign(
+		__entry->cl_boot = stp->si_opaque.so_clid.cl_boot;
+		__entry->cl_id = stp->si_opaque.so_clid.cl_id;
+		__entry->si_id = stp->si_opaque.so_id;
+		__entry->si_generation = stp->si_generation;
+	),
+	TP_printk("client %08x:%08x stateid %08x:%08x",
+		__entry->cl_boot,
+		__entry->cl_id,
+		__entry->si_id,
+		__entry->si_generation)
+)
+
+#define DEFINE_STATEID_EVENT(name) \
+DEFINE_EVENT(nfsd_stateid_class, name, \
+	TP_PROTO(stateid_t *stp), \
+	TP_ARGS(stp))
+DEFINE_STATEID_EVENT(layoutstate_alloc);
+DEFINE_STATEID_EVENT(layoutstate_unhash);
+DEFINE_STATEID_EVENT(layoutstate_free);
+DEFINE_STATEID_EVENT(layout_get_lookup_fail);
+DEFINE_STATEID_EVENT(layout_commit_lookup_fail);
+DEFINE_STATEID_EVENT(layout_return_lookup_fail);
+DEFINE_STATEID_EVENT(layout_recall);
+DEFINE_STATEID_EVENT(layout_recall_done);
+DEFINE_STATEID_EVENT(layout_recall_fail);
+DEFINE_STATEID_EVENT(layout_recall_release);
+
+#endif /* _NFSD_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 90a5925bd6ab49..0bda93e58e1b78 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete {
 	u32 rca_one_fs;
 };
 
+struct nfsd4_deviceid {
+	u64			fsid_idx;
+	u32			generation;
+	u32			pad;
+};
+
+struct nfsd4_layout_seg {
+	u32			iomode;
+	u64			offset;
+	u64			length;
+};
+
+struct nfsd4_getdeviceinfo {
+	struct nfsd4_deviceid	gd_devid;	/* request */
+	u32			gd_layout_type;	/* request */
+	u32			gd_maxcount;	/* request */
+	u32			gd_notify_types;/* request - response */
+	void			*gd_device;	/* response */
+};
+
+struct nfsd4_layoutget {
+	u64			lg_minlength;	/* request */
+	u32			lg_signal;	/* request */
+	u32			lg_layout_type;	/* request */
+	u32			lg_maxcount;	/* request */
+	stateid_t		lg_sid;		/* request/response */
+	struct nfsd4_layout_seg	lg_seg;		/* request/response */
+	void			*lg_content;	/* response */
+};
+
+struct nfsd4_layoutcommit {
+	stateid_t		lc_sid;		/* request */
+	struct nfsd4_layout_seg	lc_seg;		/* request */
+	u32			lc_reclaim;	/* request */
+	u32			lc_newoffset;	/* request */
+	u64			lc_last_wr;	/* request */
+	struct timespec		lc_mtime;	/* request */
+	u32			lc_layout_type;	/* request */
+	u32			lc_up_len;	/* layout length */
+	void			*lc_up_layout;	/* decoded by callback */
+	u32			lc_size_chg;	/* boolean for response */
+	u64			lc_newsize;	/* response */
+};
+
+struct nfsd4_layoutreturn {
+	u32			lr_return_type;	/* request */
+	u32			lr_layout_type;	/* request */
+	struct nfsd4_layout_seg	lr_seg;		/* request */
+	u32			lr_reclaim;	/* request */
+	u32			lrf_body_len;	/* request */
+	void			*lrf_body;	/* request */
+	stateid_t		lr_sid;		/* request/response */
+	u32			lrs_present;	/* response */
+};
+
 struct nfsd4_fallocate {
 	/* request */
 	stateid_t	falloc_stateid;
@@ -491,6 +546,10 @@ struct nfsd4_op {
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
 		struct nfsd4_free_stateid	free_stateid;
+		struct nfsd4_getdeviceinfo	getdeviceinfo;
+		struct nfsd4_layoutget		layoutget;
+		struct nfsd4_layoutcommit	layoutcommit;
+		struct nfsd4_layoutreturn	layoutreturn;
 
 		/* NFSv4.2 */
 		struct nfsd4_fallocate		allocate;
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index c5c55dfb91a92d..c47f6fdb111aaf 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -21,3 +21,10 @@
 #define NFS4_dec_cb_recall_sz		(cb_compound_dec_hdr_sz  +      \
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
+#define NFS4_enc_cb_layout_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + 3 +                         \
+					enc_nfs4_fh_sz + 4)
+#define NFS4_dec_cb_layout_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 57ceaf33d1773e..748ca238915a43 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -172,7 +172,6 @@ int nilfs_init_gcinode(struct inode *inode)
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 	inode->i_mapping->a_ops = &empty_aops;
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	ii->i_flags = 0;
 	nilfs_bmap_init_gc(ii->i_bmap);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index c4dcd1db57ee9c..892cf5ffdb8e16 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -429,7 +429,6 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz)
 
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, gfp_mask);
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	inode->i_op = &def_mdt_iops;
 	inode->i_fop = &def_mdt_fops;
@@ -457,13 +456,12 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
 			       struct nilfs_shadow_map *shadow)
 {
 	struct nilfs_mdt_info *mi = NILFS_MDT(inode);
-	struct backing_dev_info *bdi = inode->i_sb->s_bdi;
 
 	INIT_LIST_HEAD(&shadow->frozen_buffers);
 	address_space_init_once(&shadow->frozen_data);
-	nilfs_mapping_init(&shadow->frozen_data, inode, bdi);
+	nilfs_mapping_init(&shadow->frozen_data, inode);
 	address_space_init_once(&shadow->frozen_btnodes);
-	nilfs_mapping_init(&shadow->frozen_btnodes, inode, bdi);
+	nilfs_mapping_init(&shadow->frozen_btnodes, inode);
 	mi->mi_shadow = shadow;
 	return 0;
 }
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index da276640f7763d..700ecbcca55d56 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -461,14 +461,12 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
 	return nc;
 }
 
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
-			struct backing_dev_info *bdi)
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode)
 {
 	mapping->host = inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = bdi;
 	mapping->a_ops = &empty_aops;
 }
 
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index ef30c5c2426f47..a43b8287d012a9 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -57,8 +57,7 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
 void nilfs_clear_dirty_page(struct page *, bool);
 void nilfs_clear_dirty_pages(struct address_space *, bool);
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
-			struct backing_dev_info *bdi);
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode);
 unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
 unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 2e5b3ec85b8f62..5bc2a1cf73c353 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -166,7 +166,7 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
 	ii->i_state = 0;
 	ii->i_cno = 0;
 	ii->vfs_inode.i_version = 1;
-	nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode, sb->s_bdi);
+	nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode);
 	return &ii->vfs_inode;
 }
 
@@ -1057,7 +1057,6 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct the_nilfs *nilfs;
 	struct nilfs_root *fsroot;
-	struct backing_dev_info *bdi;
 	__u64 cno;
 	int err;
 
@@ -1077,8 +1076,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran = 1;
 	sb->s_max_links = NILFS_LINK_MAX;
 
-	bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
-	sb->s_bdi = bdi ? : &default_backing_dev_info;
+	sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
 
 	err = load_nilfs(nilfs, sb);
 	if (err)
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 643faa44f22b0b..1da9b2d184dc4e 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -19,6 +19,7 @@
  * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include <linux/gfp.h>
 #include <linux/pagemap.h>
@@ -2091,7 +2092,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
 	count = iov_length(iov, nr_segs);
 	pos = *ppos;
 	/* We can write back this queue in page reclaim. */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	written = 0;
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 57c40e34f56feb..061ba6a91bf2fa 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -390,12 +390,6 @@ static void dlmfs_evict_inode(struct inode *inode)
 	ip->ip_conn = NULL;
 }
 
-static struct backing_dev_info dlmfs_backing_dev_info = {
-	.name		= "ocfs2-dlmfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -404,7 +398,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, NULL, mode);
-		inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inc_nlink(inode);
 
@@ -428,7 +421,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
 
 	inode->i_ino = get_next_ino();
 	inode_init_owner(inode, parent, mode);
-	inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 
 	ip = DLMFS_I(inode);
@@ -643,10 +635,6 @@ static int __init init_dlmfs_fs(void)
 	int status;
 	int cleanup_inode = 0, cleanup_worker = 0;
 
-	status = bdi_init(&dlmfs_backing_dev_info);
-	if (status)
-		return status;
-
 	dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache",
 				sizeof(struct dlmfs_inode_private),
 				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
@@ -673,7 +661,6 @@ static int __init init_dlmfs_fs(void)
 			kmem_cache_destroy(dlmfs_inode_cache);
 		if (cleanup_worker)
 			destroy_workqueue(user_dlm_worker);
-		bdi_destroy(&dlmfs_backing_dev_info);
 	} else
 		printk("OCFS2 User DLM kernel interface loaded\n");
 	return status;
@@ -693,7 +680,6 @@ static void __exit exit_dlmfs_fs(void)
 	rcu_barrier();
 	kmem_cache_destroy(dlmfs_inode_cache);
 
-	bdi_destroy(&dlmfs_backing_dev_info);
 }
 
 MODULE_AUTHOR("Oracle");
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 245db4f504dab4..e0f04d55fd0531 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2363,7 +2363,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 			goto out_dio;
 		}
 	} else {
-		current->backing_dev_info = file->f_mapping->backing_dev_info;
+		current->backing_dev_info = inode_to_bdi(inode);
 		written = generic_perform_write(file, from, *ppos);
 		if (likely(written >= 0))
 			iocb->ki_pos = *ppos + written;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index bd117d065b822f..a3ccf4c4ce70b7 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -81,6 +81,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
+#include <linux/string_helpers.h>
 #include <linux/user_namespace.h>
 
 #include <asm/pgtable.h>
@@ -89,39 +90,18 @@
 
 static inline void task_name(struct seq_file *m, struct task_struct *p)
 {
-	int i;
-	char *buf, *end;
-	char *name;
+	char *buf;
 	char tcomm[sizeof(p->comm)];
 
 	get_task_comm(tcomm, p);
 
 	seq_puts(m, "Name:\t");
-	end = m->buf + m->size;
 	buf = m->buf + m->count;
-	name = tcomm;
-	i = sizeof(tcomm);
-	while (i && (buf < end)) {
-		unsigned char c = *name;
-		name++;
-		i--;
-		*buf = c;
-		if (!c)
-			break;
-		if (c == '\\') {
-			buf++;
-			if (buf < end)
-				*buf++ = c;
-			continue;
-		}
-		if (c == '\n') {
-			*buf++ = '\\';
-			if (buf < end)
-				*buf++ = 'n';
-			continue;
-		}
-		buf++;
-	}
+
+	/* Ignore error for now */
+	string_escape_str(tcomm, &buf, m->size - m->count,
+			  ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+
 	m->count = buf - m->buf;
 	seq_putc(m, '\n');
 }
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 7fea13229f3370..de14e46fd80794 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -122,7 +122,7 @@ static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
 			struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
-	struct proc_dir_entry *de = PROC_I(inode)->pde;
+	struct proc_dir_entry *de = PDE(inode);
 	if (de && de->nlink)
 		set_nlink(inode, de->nlink);
 
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 8420a2f8081182..13a50a32652dc8 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -40,7 +40,7 @@ static void proc_evict_inode(struct inode *inode)
 	put_pid(PROC_I(inode)->pid);
 
 	/* Let go of any associated proc directory entry */
-	de = PROC_I(inode)->pde;
+	de = PDE(inode);
 	if (de)
 		pde_put(de);
 	head = PROC_I(inode)->sysctl;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 0e36c1e49fe30b..956b75d61809f0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -732,6 +732,7 @@ enum clear_refs_types {
 	CLEAR_REFS_ANON,
 	CLEAR_REFS_MAPPED,
 	CLEAR_REFS_SOFT_DIRTY,
+	CLEAR_REFS_MM_HIWATER_RSS,
 	CLEAR_REFS_LAST,
 };
 
@@ -907,6 +908,18 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.mm = mm,
 			.private = &cp,
 		};
+
+		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+			/*
+			 * Writing 5 to /proc/pid/clear_refs resets the peak
+			 * resident set size to this mm's current rss value.
+			 */
+			down_write(&mm->mmap_sem);
+			reset_mm_hiwater_rss(mm);
+			up_write(&mm->mmap_sem);
+			goto out_mm;
+		}
+
 		down_read(&mm->mmap_sem);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
@@ -928,6 +941,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);
 		up_read(&mm->mmap_sem);
+out_mm:
 		mmput(mm);
 	}
 	put_task_struct(task);
@@ -1543,6 +1557,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	for_each_node_state(nid, N_MEMORY)
 		if (md->node[nid])
 			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
+
+	seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10);
 out:
 	seq_putc(m, '\n');
 	m_cache_vma(m, vma);
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index bbafbde3471a65..f6ab41b39612bd 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -34,7 +34,14 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 						   unsigned long flags);
 static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
 
+static unsigned ramfs_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_DIRECT | NOMMU_MAP_COPY | NOMMU_MAP_READ |
+		NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
 const struct file_operations ramfs_file_operations = {
+	.mmap_capabilities	= ramfs_mmap_capabilities,
 	.mmap			= ramfs_nommu_mmap,
 	.get_unmapped_area	= ramfs_nommu_get_unmapped_area,
 	.read			= new_sync_read,
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index d365b1c4eb3cbe..889d558b4e0551 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -50,14 +50,6 @@ static const struct address_space_operations ramfs_aops = {
 	.set_page_dirty	= __set_page_dirty_no_writeback,
 };
 
-static struct backing_dev_info ramfs_backing_dev_info = {
-	.name		= "ramfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK |
-			  BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
-			  BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP,
-};
-
 struct inode *ramfs_get_inode(struct super_block *sb,
 				const struct inode *dir, umode_t mode, dev_t dev)
 {
@@ -67,7 +59,6 @@ struct inode *ramfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_mapping->a_ops = &ramfs_aops;
-		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
 		mapping_set_unevictable(inode->i_mapping);
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -267,19 +258,9 @@ static struct file_system_type ramfs_fs_type = {
 int __init init_ramfs_fs(void)
 {
 	static unsigned long once;
-	int err;
 
 	if (test_and_set_bit(0, &once))
 		return 0;
-
-	err = bdi_init(&ramfs_backing_dev_info);
-	if (err)
-		return err;
-
-	err = register_filesystem(&ramfs_fs_type);
-	if (err)
-		bdi_destroy(&ramfs_backing_dev_info);
-
-	return err;
+	return register_filesystem(&ramfs_fs_type);
 }
 fs_initcall(init_ramfs_fs);
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index ea06c7554860d7..7da9e2153953eb 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -70,6 +70,15 @@ static int romfs_mmap(struct file *file, struct vm_area_struct *vma)
 	return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS;
 }
 
+static unsigned romfs_mmap_capabilities(struct file *file)
+{
+	struct mtd_info *mtd = file_inode(file)->i_sb->s_mtd;
+
+	if (!mtd)
+		return NOMMU_MAP_COPY;
+	return mtd_mmap_capabilities(mtd);
+}
+
 const struct file_operations romfs_ro_fops = {
 	.llseek			= generic_file_llseek,
 	.read			= new_sync_read,
@@ -77,4 +86,5 @@ const struct file_operations romfs_ro_fops = {
 	.splice_read		= generic_file_splice_read,
 	.mmap			= romfs_mmap,
 	.get_unmapped_area	= romfs_get_unmapped_area,
+	.mmap_capabilities	= romfs_mmap_capabilities,
 };
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index e98dd88197d502..268733cda397eb 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -355,9 +355,6 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
 	case ROMFH_REG:
 		i->i_fop = &romfs_ro_fops;
 		i->i_data.a_ops = &romfs_aops;
-		if (i->i_sb->s_mtd)
-			i->i_data.backing_dev_info =
-				i->i_sb->s_mtd->backing_dev_info;
 		if (nextfh & ROMFH_EXEC)
 			mode |= S_IXUGO;
 		break;
diff --git a/fs/select.c b/fs/select.c
index 467bb1cb3ea5e0..f684c750e08a54 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -971,7 +971,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 	if (ret == -EINTR) {
 		struct restart_block *restart_block;
 
-		restart_block = &current_thread_info()->restart_block;
+		restart_block = &current->restart_block;
 		restart_block->fn = do_restart_poll;
 		restart_block->poll.ufds = ufds;
 		restart_block->poll.nfds = nfds;
diff --git a/fs/super.c b/fs/super.c
index eae088f6aaaeb6..1facd2c282e5ae 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -36,8 +36,8 @@
 #include "internal.h"
 
 
-LIST_HEAD(super_blocks);
-DEFINE_SPINLOCK(sb_lock);
+static LIST_HEAD(super_blocks);
+static DEFINE_SPINLOCK(sb_lock);
 
 static char *sb_writers_name[SB_FREEZE_LEVELS] = {
 	"sb_writers",
@@ -75,10 +75,10 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 		return SHRINK_STOP;
 
 	if (sb->s_op->nr_cached_objects)
-		fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
+		fs_objects = sb->s_op->nr_cached_objects(sb, sc);
 
-	inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
-	dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
+	inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
+	dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
 	total_objects = dentries + inodes + fs_objects + 1;
 	if (!total_objects)
 		total_objects = 1;
@@ -86,19 +86,23 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
 	inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+	fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);
 
 	/*
 	 * prune the dcache first as the icache is pinned by it, then
 	 * prune the icache, followed by the filesystem specific caches
+	 *
+	 * Ensure that we always scan at least one object - memcg kmem
+	 * accounting uses this to fully empty the caches.
 	 */
-	freed = prune_dcache_sb(sb, dentries, sc->nid);
-	freed += prune_icache_sb(sb, inodes, sc->nid);
+	sc->nr_to_scan = dentries + 1;
+	freed = prune_dcache_sb(sb, sc);
+	sc->nr_to_scan = inodes + 1;
+	freed += prune_icache_sb(sb, sc);
 
 	if (fs_objects) {
-		fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
-								total_objects);
-		freed += sb->s_op->free_cached_objects(sb, fs_objects,
-						       sc->nid);
+		sc->nr_to_scan = fs_objects + 1;
+		freed += sb->s_op->free_cached_objects(sb, sc);
 	}
 
 	drop_super(sb);
@@ -118,17 +122,14 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	 * scalability bottleneck. The counts could get updated
 	 * between super_cache_count and super_cache_scan anyway.
 	 * Call to super_cache_count with shrinker_rwsem held
-	 * ensures the safety of call to list_lru_count_node() and
+	 * ensures the safety of call to list_lru_shrink_count() and
 	 * s_op->nr_cached_objects().
 	 */
 	if (sb->s_op && sb->s_op->nr_cached_objects)
-		total_objects = sb->s_op->nr_cached_objects(sb,
-						 sc->nid);
+		total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
-	total_objects += list_lru_count_node(&sb->s_dentry_lru,
-						 sc->nid);
-	total_objects += list_lru_count_node(&sb->s_inode_lru,
-						 sc->nid);
+	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
+	total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
 
 	total_objects = vfs_pressure_ratio(total_objects);
 	return total_objects;
@@ -185,15 +186,15 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	}
 	init_waitqueue_head(&s->s_writers.wait);
 	init_waitqueue_head(&s->s_writers.wait_unfrozen);
+	s->s_bdi = &noop_backing_dev_info;
 	s->s_flags = flags;
-	s->s_bdi = &default_backing_dev_info;
 	INIT_HLIST_NODE(&s->s_instances);
 	INIT_HLIST_BL_HEAD(&s->s_anon);
 	INIT_LIST_HEAD(&s->s_inodes);
 
-	if (list_lru_init(&s->s_dentry_lru))
+	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;
-	if (list_lru_init(&s->s_inode_lru))
+	if (list_lru_init_memcg(&s->s_inode_lru))
 		goto fail;
 
 	init_rwsem(&s->s_umount);
@@ -229,7 +230,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	s->s_shrink.scan_objects = super_cache_scan;
 	s->s_shrink.count_objects = super_cache_count;
 	s->s_shrink.batch = 1024;
-	s->s_shrink.flags = SHRINKER_NUMA_AWARE;
+	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
 	return s;
 
 fail:
@@ -284,6 +285,14 @@ void deactivate_locked_super(struct super_block *s)
 		unregister_shrinker(&s->s_shrink);
 		fs->kill_sb(s);
 
+		/*
+		 * Since list_lru_destroy() may sleep, we cannot call it from
+		 * put_super(), where we hold the sb_lock. Therefore we destroy
+		 * the lru lists right now.
+		 */
+		list_lru_destroy(&s->s_dentry_lru);
+		list_lru_destroy(&s->s_inode_lru);
+
 		put_filesystem(fs);
 		put_super(s);
 	} else {
@@ -863,10 +872,7 @@ EXPORT_SYMBOL(free_anon_bdev);
 
 int set_anon_super(struct super_block *s, void *data)
 {
-	int error = get_anon_bdev(&s->s_dev);
-	if (!error)
-		s->s_bdi = &noop_backing_dev_info;
-	return error;
+	return get_anon_bdev(&s->s_dev);
 }
 
 EXPORT_SYMBOL(set_anon_super);
@@ -1111,7 +1117,6 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
 	sb = root->d_sb;
 	BUG_ON(!sb);
 	WARN_ON(!sb->s_bdi);
-	WARN_ON(sb->s_bdi == &default_backing_dev_info);
 	sb->s_flags |= MS_BORN;
 
 	error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index ea41649e4ca55e..c49b1981ac95f6 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -108,8 +108,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir,
 	inode->i_mtime = inode->i_atime = inode->i_ctime =
 			 ubifs_current_time(inode);
 	inode->i_mapping->nrpages = 0;
-	/* Disable readahead */
-	inode->i_mapping->backing_dev_info = &c->bdi;
 
 	switch (mode & S_IFMT) {
 	case S_IFREG:
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 106bf20629ce6d..6197154f36ca40 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -156,9 +156,6 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
 	if (err)
 		goto out_invalid;
 
-	/* Disable read-ahead */
-	inode->i_mapping->backing_dev_info = &c->bdi;
-
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_mapping->a_ops = &ubifs_file_address_operations;
@@ -2017,7 +2014,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
 	 */
 	c->bdi.name = "ubifs",
-	c->bdi.capabilities = BDI_CAP_MAP_COPY;
+	c->bdi.capabilities = 0;
 	err  = bdi_init(&c->bdi);
 	if (err)
 		goto out_close;
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index bb502a39179210..1790b00bea7a7b 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1488,6 +1488,7 @@ xfs_buf_iomove(
 static enum lru_status
 xfs_buftarg_wait_rele(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 
@@ -1509,7 +1510,7 @@ xfs_buftarg_wait_rele(
 	 */
 	atomic_set(&bp->b_lru_ref, 0);
 	bp->b_state |= XFS_BSTATE_DISPOSE;
-	list_move(item, dispose);
+	list_lru_isolate_move(lru, item, dispose);
 	spin_unlock(&bp->b_lock);
 	return LRU_REMOVED;
 }
@@ -1546,6 +1547,7 @@ xfs_wait_buftarg(
 static enum lru_status
 xfs_buftarg_isolate(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 {
@@ -1569,7 +1571,7 @@ xfs_buftarg_isolate(
 	}
 
 	bp->b_state |= XFS_BSTATE_DISPOSE;
-	list_move(item, dispose);
+	list_lru_isolate_move(lru, item, dispose);
 	spin_unlock(&bp->b_lock);
 	return LRU_REMOVED;
 }
@@ -1583,10 +1585,9 @@ xfs_buftarg_shrink_scan(
 					struct xfs_buftarg, bt_shrinker);
 	LIST_HEAD(dispose);
 	unsigned long		freed;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
-	freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&btp->bt_lru, sc,
+				     xfs_buftarg_isolate, &dispose);
 
 	while (!list_empty(&dispose)) {
 		struct xfs_buf *bp;
@@ -1605,7 +1606,7 @@ xfs_buftarg_shrink_count(
 {
 	struct xfs_buftarg	*btp = container_of(shrink,
 					struct xfs_buftarg, bt_shrinker);
-	return list_lru_count_node(&btp->bt_lru, sc->nid);
+	return list_lru_shrink_count(&btp->bt_lru, sc);
 }
 
 void
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f2d05a19d68cab..1cdba95c78cb3e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -735,7 +735,7 @@ xfs_file_buffered_aio_write(
 
 	iov_iter_truncate(from, count);
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 3e81862795411e..53cc2aaf8d2bdf 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -430,6 +430,7 @@ struct xfs_qm_isolate {
 static enum lru_status
 xfs_qm_dquot_isolate(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 		__releases(lru_lock) __acquires(lru_lock)
@@ -450,7 +451,7 @@ xfs_qm_dquot_isolate(
 		XFS_STATS_INC(xs_qm_dqwants);
 
 		trace_xfs_dqreclaim_want(dqp);
-		list_del_init(&dqp->q_lru);
+		list_lru_isolate(lru, &dqp->q_lru);
 		XFS_STATS_DEC(xs_qm_dquot_unused);
 		return LRU_REMOVED;
 	}
@@ -494,7 +495,7 @@ xfs_qm_dquot_isolate(
 	xfs_dqunlock(dqp);
 
 	ASSERT(dqp->q_nrefs == 0);
-	list_move_tail(&dqp->q_lru, &isol->dispose);
+	list_lru_isolate_move(lru, &dqp->q_lru, &isol->dispose);
 	XFS_STATS_DEC(xs_qm_dquot_unused);
 	trace_xfs_dqreclaim_done(dqp);
 	XFS_STATS_INC(xs_qm_dqreclaims);
@@ -523,7 +524,6 @@ xfs_qm_shrink_scan(
 	struct xfs_qm_isolate	isol;
 	unsigned long		freed;
 	int			error;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
 	if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
 		return 0;
@@ -531,8 +531,8 @@ xfs_qm_shrink_scan(
 	INIT_LIST_HEAD(&isol.buffers);
 	INIT_LIST_HEAD(&isol.dispose);
 
-	freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol,
-					&nr_to_scan);
+	freed = list_lru_shrink_walk(&qi->qi_lru, sc,
+				     xfs_qm_dquot_isolate, &isol);
 
 	error = xfs_buf_delwri_submit(&isol.buffers);
 	if (error)
@@ -557,7 +557,7 @@ xfs_qm_shrink_count(
 	struct xfs_quotainfo	*qi = container_of(shrink,
 					struct xfs_quotainfo, qi_shrinker);
 
-	return list_lru_count_node(&qi->qi_lru, sc->nid);
+	return list_lru_shrink_count(&qi->qi_lru, sc);
 }
 
 /*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f2449fd869263b..8fcc4ccc5c7912 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1537,7 +1537,7 @@ xfs_fs_mount(
 static long
 xfs_fs_nr_cached_objects(
 	struct super_block	*sb,
-	int			nid)
+	struct shrink_control	*sc)
 {
 	return xfs_reclaim_inodes_count(XFS_M(sb));
 }
@@ -1545,10 +1545,9 @@ xfs_fs_nr_cached_objects(
 static long
 xfs_fs_free_cached_objects(
 	struct super_block	*sb,
-	long			nr_to_scan,
-	int			nid)
+	struct shrink_control	*sc)
 {
-	return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
+	return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
 }
 
 static const struct super_operations xfs_super_operations = {
diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
index 9318a87ee39ab9..a8f344363e7737 100644
--- a/include/acpi/acoutput.h
+++ b/include/acpi/acoutput.h
@@ -240,7 +240,7 @@
 /*
  * If ACPI_GET_FUNCTION_NAME was not defined in the compiler-dependent header,
  * define it now. This is the case where there the compiler does not support
- * a __FUNCTION__ macro or equivalent.
+ * a __func__ macro or equivalent.
  */
 #ifndef ACPI_GET_FUNCTION_NAME
 #define ACPI_GET_FUNCTION_NAME          _acpi_function_name
@@ -249,12 +249,12 @@
  * The Name parameter should be the procedure name as a quoted string.
  * The function name is also used by the function exit macros below.
  * Note: (const char) is used to be compatible with the debug interfaces
- * and macros such as __FUNCTION__.
+ * and macros such as __func__.
  */
 #define ACPI_FUNCTION_NAME(name)        static const char _acpi_function_name[] = #name;
 
 #else
-/* Compiler supports __FUNCTION__ (or equivalent) -- Ignore this macro */
+/* Compiler supports __func__ (or equivalent) -- Ignore this macro */
 
 #define ACPI_FUNCTION_NAME(name)
 #endif				/* ACPI_GET_FUNCTION_NAME */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 129de9204d18e6..4d46085c1b901c 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -244,10 +244,6 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 # define pte_accessible(mm, pte)	((void)(pte), 1)
 #endif
 
-#ifndef pte_present_nonuma
-#define pte_present_nonuma(pte) pte_present(pte)
-#endif
-
 #ifndef flush_tlb_fix_spurious_fault
 #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
 #endif
@@ -673,155 +669,24 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #endif
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-/*
- * _PAGE_NUMA distinguishes between an unmapped page table entry, an entry that
- * is protected for PROT_NONE and a NUMA hinting fault entry. If the
- * architecture defines __PAGE_PROTNONE then it should take that into account
- * but those that do not can rely on the fact that the NUMA hinting scanner
- * skips inaccessible VMAs.
- *
- * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
- * fault triggers on those regions if pte/pmd_numa returns true
- * (because _PAGE_PRESENT is not set).
- */
-#ifndef pte_numa
-static inline int pte_numa(pte_t pte)
-{
-	return ptenuma_flags(pte) == _PAGE_NUMA;
-}
-#endif
-
-#ifndef pmd_numa
-static inline int pmd_numa(pmd_t pmd)
-{
-	return pmdnuma_flags(pmd) == _PAGE_NUMA;
-}
-#endif
-
+#ifndef CONFIG_NUMA_BALANCING
 /*
- * pte/pmd_mknuma sets the _PAGE_ACCESSED bitflag automatically
- * because they're called by the NUMA hinting minor page fault. If we
- * wouldn't set the _PAGE_ACCESSED bitflag here, the TLB miss handler
- * would be forced to set it later while filling the TLB after we
- * return to userland. That would trigger a second write to memory
- * that we optimize away by setting _PAGE_ACCESSED here.
+ * Technically a PTE can be PROTNONE even when not doing NUMA balancing but
+ * the only case the kernel cares is for NUMA balancing and is only ever set
+ * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
+ * _PAGE_PROTNONE so by by default, implement the helper as "always no". It
+ * is the responsibility of the caller to distinguish between PROT_NONE
+ * protections and NUMA hinting fault protections.
  */
-#ifndef pte_mknonnuma
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
-	pteval_t val = pte_val(pte);
-
-	val &= ~_PAGE_NUMA;
-	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
-	return __pte(val);
-}
-#endif
-
-#ifndef pmd_mknonnuma
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
-{
-	pmdval_t val = pmd_val(pmd);
-
-	val &= ~_PAGE_NUMA;
-	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
-
-	return __pmd(val);
-}
-#endif
-
-#ifndef pte_mknuma
-static inline pte_t pte_mknuma(pte_t pte)
-{
-	pteval_t val = pte_val(pte);
-
-	VM_BUG_ON(!(val & _PAGE_PRESENT));
-
-	val &= ~_PAGE_PRESENT;
-	val |= _PAGE_NUMA;
-
-	return __pte(val);
-}
-#endif
-
-#ifndef ptep_set_numa
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep)
-{
-	pte_t ptent = *ptep;
-
-	ptent = pte_mknuma(ptent);
-	set_pte_at(mm, addr, ptep, ptent);
-	return;
-}
-#endif
-
-#ifndef pmd_mknuma
-static inline pmd_t pmd_mknuma(pmd_t pmd)
-{
-	pmdval_t val = pmd_val(pmd);
-
-	val &= ~_PAGE_PRESENT;
-	val |= _PAGE_NUMA;
-
-	return __pmd(val);
-}
-#endif
-
-#ifndef pmdp_set_numa
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pmd_t *pmdp)
-{
-	pmd_t pmd = *pmdp;
-
-	pmd = pmd_mknuma(pmd);
-	set_pmd_at(mm, addr, pmdp, pmd);
-	return;
-}
-#endif
-#else
-static inline int pmd_numa(pmd_t pmd)
+static inline int pte_protnone(pte_t pte)
 {
 	return 0;
 }
 
-static inline int pte_numa(pte_t pte)
+static inline int pmd_protnone(pmd_t pmd)
 {
 	return 0;
 }
-
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
-	return pte;
-}
-
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline pte_t pte_mknuma(pte_t pte)
-{
-	return pte;
-}
-
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep)
-{
-	return;
-}
-
-
-static inline pmd_t pmd_mknuma(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pmd_t *pmdp)
-{
-	return ;
-}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #endif /* CONFIG_MMU */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5da6012b7a141e..d94077fea1f8a2 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -106,6 +106,8 @@ struct backing_dev_info {
 #endif
 };
 
+struct backing_dev_info *inode_to_bdi(struct inode *inode);
+
 int __must_check bdi_init(struct backing_dev_info *bdi);
 void bdi_destroy(struct backing_dev_info *bdi);
 
@@ -114,7 +116,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
-int __must_check bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
+int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 			enum wb_reason reason);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
@@ -228,46 +230,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
  * BDI_CAP_NO_WRITEBACK:   Don't write pages back
  * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
- *
- * These flags let !MMU mmap() govern direct device mapping vs immediate
- * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
- *
- * BDI_CAP_MAP_COPY:       Copy can be mapped (MAP_PRIVATE)
- * BDI_CAP_MAP_DIRECT:     Can be mapped directly (MAP_SHARED)
- * BDI_CAP_READ_MAP:       Can be mapped for reading
- * BDI_CAP_WRITE_MAP:      Can be mapped for writing
- * BDI_CAP_EXEC_MAP:       Can be mapped for execution
- *
- * BDI_CAP_SWAP_BACKED:    Count shmem/tmpfs objects as swap-backed.
- *
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
-#define BDI_CAP_MAP_COPY	0x00000004
-#define BDI_CAP_MAP_DIRECT	0x00000008
-#define BDI_CAP_READ_MAP	0x00000010
-#define BDI_CAP_WRITE_MAP	0x00000020
-#define BDI_CAP_EXEC_MAP	0x00000040
-#define BDI_CAP_NO_ACCT_WB	0x00000080
-#define BDI_CAP_SWAP_BACKED	0x00000100
-#define BDI_CAP_STABLE_WRITES	0x00000200
-#define BDI_CAP_STRICTLIMIT	0x00000400
-
-#define BDI_CAP_VMFLAGS \
-	(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
+#define BDI_CAP_NO_ACCT_WB	0x00000004
+#define BDI_CAP_STABLE_WRITES	0x00000008
+#define BDI_CAP_STRICTLIMIT	0x00000010
 
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
 	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
 
-#if defined(VM_MAYREAD) && \
-	(BDI_CAP_READ_MAP != VM_MAYREAD || \
-	 BDI_CAP_WRITE_MAP != VM_MAYWRITE || \
-	 BDI_CAP_EXEC_MAP != VM_MAYEXEC)
-#error please change backing_dev_info::capabilities flags
-#endif
-
-extern struct backing_dev_info default_backing_dev_info;
 extern struct backing_dev_info noop_backing_dev_info;
 
 int writeback_in_progress(struct backing_dev_info *bdi);
@@ -329,24 +302,14 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
 				      BDI_CAP_NO_WRITEBACK));
 }
 
-static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
-{
-	return bdi->capabilities & BDI_CAP_SWAP_BACKED;
-}
-
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
-	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
+	return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
 }
 
 static inline bool mapping_cap_account_dirty(struct address_space *mapping)
 {
-	return bdi_cap_account_dirty(mapping->backing_dev_info);
-}
-
-static inline bool mapping_cap_swap_backed(struct address_space *mapping)
-{
-	return bdi_cap_swap_backed(mapping->backing_dev_info);
+	return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
 }
 
 static inline int bdi_sched_wait(void *word)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index efead0b532c472..da3a127c99583b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -428,13 +428,9 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 extern int bio_get_nr_vecs(struct block_device *);
-extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
-				unsigned long, unsigned int, int, gfp_t);
-struct sg_iovec;
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
-				    struct block_device *,
-				    const struct sg_iovec *, int, int, gfp_t);
+				    const struct iov_iter *, gfp_t);
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
@@ -462,12 +458,10 @@ static inline void bio_flush_dcache_pages(struct bio *bi)
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
 
-extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
-				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
 				     struct rq_map_data *,
-				     const struct sg_iovec *,
-				     int, int, gfp_t);
+				     const struct iov_iter *,
+				     gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
 extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 202e4034fe26c4..5f5c00de39f026 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -160,18 +160,18 @@ extern int bitmap_parselist(const char *buf, unsigned long *maskp,
 extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
 			unsigned long *dst, int nbits);
 extern void bitmap_remap(unsigned long *dst, const unsigned long *src,
-		const unsigned long *old, const unsigned long *new, int bits);
+		const unsigned long *old, const unsigned long *new, unsigned int nbits);
 extern int bitmap_bitremap(int oldbit,
 		const unsigned long *old, const unsigned long *new, int bits);
 extern void bitmap_onto(unsigned long *dst, const unsigned long *orig,
-		const unsigned long *relmap, int bits);
+		const unsigned long *relmap, unsigned int bits);
 extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
-		int sz, int bits);
+		unsigned int sz, unsigned int nbits);
 extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order);
 extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order);
 extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
 extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
-extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits);
+extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits);
 extern int bitmap_print_to_pagebuf(bool list, char *buf,
 				   const unsigned long *maskp, int nmaskbits);
 
@@ -185,33 +185,33 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf,
 #define small_const_nbits(nbits) \
 	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
 
-static inline void bitmap_zero(unsigned long *dst, int nbits)
+static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = 0UL;
 	else {
-		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
 		memset(dst, 0, len);
 	}
 }
 
-static inline void bitmap_fill(unsigned long *dst, int nbits)
+static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
-	size_t nlongs = BITS_TO_LONGS(nbits);
+	unsigned int nlongs = BITS_TO_LONGS(nbits);
 	if (!small_const_nbits(nbits)) {
-		int len = (nlongs - 1) * sizeof(unsigned long);
+		unsigned int len = (nlongs - 1) * sizeof(unsigned long);
 		memset(dst, 0xff,  len);
 	}
 	dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
 }
 
 static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
-			int nbits)
+			unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src;
 	else {
-		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
 		memcpy(dst, src, len);
 	}
 }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 5735e7130d630f..7aec861273357d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -146,6 +146,8 @@ enum {
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_SYSFS_UP	= 1 << 3,
 	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
+	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
+	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
@@ -154,6 +156,12 @@ enum {
 
 	BLK_MQ_CPU_WORK_BATCH	= 8,
 };
+#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
+	((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
+		((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
+#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
+	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
+		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
 void blk_mq_finish_init(struct request_queue *q);
@@ -166,7 +174,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
 void blk_mq_insert_request(struct request *, bool, bool, bool);
-void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
@@ -214,6 +221,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 92f4b4b288dd57..7f9a516f24dec5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -272,7 +272,11 @@ struct blk_queue_tag {
 	int max_depth;			/* what we will send to device */
 	int real_max_depth;		/* what the array can hold */
 	atomic_t refcnt;		/* map can be shared */
+	int alloc_policy;		/* tag allocation policy */
+	int next_tag;			/* next tag */
 };
+#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
+#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
 
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
@@ -516,6 +520,7 @@ struct request_queue {
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
+				 (1 << QUEUE_FLAG_STACKABLE)	|	\
 				 (1 << QUEUE_FLAG_SAME_COMP))
 
 static inline void queue_lockdep_assert_held(struct request_queue *q)
@@ -850,8 +855,8 @@ extern int blk_rq_map_user(struct request_queue *, struct request *,
 extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct rq_map_data *, const struct sg_iovec *,
-			       int, unsigned int, gfp_t);
+			       struct rq_map_data *, const struct iov_iter *,
+			       gfp_t);
 extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
@@ -1044,8 +1049,6 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
-extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
-			  struct scatterlist *sglist);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
 
@@ -1139,11 +1142,11 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 extern int blk_queue_start_tag(struct request_queue *, struct request *);
 extern struct request *blk_queue_find_tag(struct request_queue *, int);
 extern void blk_queue_end_tag(struct request_queue *, struct request *);
-extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *);
+extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int);
 extern void blk_queue_free_tags(struct request_queue *);
 extern int blk_queue_resize_tags(struct request_queue *, int);
 extern void blk_queue_invalidate_tags(struct request_queue *);
-extern struct blk_queue_tag *blk_init_tags(int);
+extern struct blk_queue_tag *blk_init_tags(int, int);
 extern void blk_free_tags(struct blk_queue_tag *);
 
 static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
@@ -1162,7 +1165,7 @@ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			sector_t nr_sects, gfp_t gfp_mask);
+		sector_t nr_sects, gfp_t gfp_mask, bool discard);
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
@@ -1176,7 +1179,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 	return blkdev_issue_zeroout(sb->s_bdev,
 				    block << (sb->s_blocksize_bits - 9),
 				    nr_blocks << (sb->s_blocksize_bits - 9),
-				    gfp_mask);
+				    gfp_mask, true);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
@@ -1601,8 +1604,8 @@ struct block_device_operations {
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t,
-						void **, unsigned long *);
+	long (*direct_access)(struct block_device *, sector_t,
+					void **, unsigned long *pfn, long size);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1620,6 +1623,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
+extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
+						unsigned long *pfn, long size);
 #else /* CONFIG_BLOCK */
 
 struct block_device;
diff --git a/include/linux/cdev.h b/include/linux/cdev.h
index fb4591977b039a..f8763615a5f2dc 100644
--- a/include/linux/cdev.h
+++ b/include/linux/cdev.h
@@ -30,6 +30,4 @@ void cdev_del(struct cdev *);
 
 void cd_forget(struct inode *);
 
-extern struct backing_dev_info directly_mappable_cdev_bdi;
-
 #endif
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index b950e9d6008b1e..ff9044286d8808 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -905,13 +905,13 @@ static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp)
 }
 
 #define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS)
-static inline void __cpus_setall(cpumask_t *dstp, int nbits)
+static inline void __cpus_setall(cpumask_t *dstp, unsigned int nbits)
 {
 	bitmap_fill(dstp->bits, nbits);
 }
 
 #define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS)
-static inline void __cpus_clear(cpumask_t *dstp, int nbits)
+static inline void __cpus_clear(cpumask_t *dstp, unsigned int nbits)
 {
 	bitmap_zero(dstp->bits, nbits);
 }
@@ -927,21 +927,21 @@ static inline int __cpu_test_and_set(int cpu, cpumask_t *addr)
 
 #define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS)
 static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS)
 static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS)
 static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
@@ -949,40 +949,40 @@ static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
 #define cpus_andnot(dst, src1, src2) \
 				__cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS)
 static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS)
 static inline int __cpus_equal(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS)
 static inline int __cpus_intersects(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS)
 static inline int __cpus_subset(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
+					const cpumask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_empty(src) __cpus_empty(&(src), NR_CPUS)
-static inline int __cpus_empty(const cpumask_t *srcp, int nbits)
+static inline int __cpus_empty(const cpumask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS)
-static inline int __cpus_weight(const cpumask_t *srcp, int nbits)
+static inline int __cpus_weight(const cpumask_t *srcp, unsigned int nbits)
 {
 	return bitmap_weight(srcp->bits, nbits);
 }
diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h
index 2cd9f1cf9fa366..f4754282c9c2a1 100644
--- a/include/linux/cryptohash.h
+++ b/include/linux/cryptohash.h
@@ -1,6 +1,8 @@
 #ifndef __CRYPTOHASH_H
 #define __CRYPTOHASH_H
 
+#include <uapi/linux/types.h>
+
 #define SHA_DIGEST_WORDS 5
 #define SHA_MESSAGE_BYTES (512 /*bits*/ / 8)
 #define SHA_WORKSPACE_WORDS 16
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ca6d2acc5eb76f..2646aed1d3feda 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -48,6 +48,11 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti);
 typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio);
 typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
 				  union map_info *map_context);
+typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti,
+					    struct request *rq,
+					    union map_info *map_context,
+					    struct request **clone);
+typedef void (*dm_release_clone_request_fn) (struct request *clone);
 
 /*
  * Returns:
@@ -143,6 +148,8 @@ struct target_type {
 	dm_dtr_fn dtr;
 	dm_map_fn map;
 	dm_map_request_fn map_rq;
+	dm_clone_and_map_request_fn clone_and_map_rq;
+	dm_release_clone_request_fn release_clone_rq;
 	dm_endio_fn end_io;
 	dm_request_endio_fn rq_end_io;
 	dm_presuspend_fn presuspend;
@@ -600,9 +607,6 @@ static inline unsigned long to_bytes(sector_t n)
 /*-----------------------------------------------------------------
  * Helper for block layer and dm core operations
  *---------------------------------------------------------------*/
-void dm_dispatch_request(struct request *rq);
-void dm_requeue_unmapped_request(struct request *rq);
-void dm_kill_unmapped_request(struct request *rq, int error);
 int dm_underlying_device_busy(struct request_queue *q);
 
 #endif	/* _LINUX_DEVICE_MAPPER_H */
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 41b223a59a636c..fa05e04c5531ce 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 
 struct dentry;
+struct iattr;
 struct inode;
 struct super_block;
 struct vfsmount;
@@ -180,6 +181,21 @@ struct fid {
  *    get_name is not (which is possibly inconsistent)
  */
 
+/* types of block ranges for multipage write mappings. */
+#define IOMAP_HOLE	0x01	/* no blocks allocated, need allocation */
+#define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
+#define IOMAP_MAPPED	0x03	/* blocks allocated @blkno */
+#define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
+
+#define IOMAP_NULL_BLOCK -1LL	/* blkno is not valid */
+
+struct iomap {
+	sector_t	blkno;	/* first sector of mapping */
+	loff_t		offset;	/* file offset of mapping, bytes */
+	u64		length;	/* length of mapping, bytes */
+	int		type;	/* type of mapping */
+};
+
 struct export_operations {
 	int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len,
 			struct inode *parent);
@@ -191,6 +207,13 @@ struct export_operations {
 			struct dentry *child);
 	struct dentry * (*get_parent)(struct dentry *child);
 	int (*commit_metadata)(struct inode *inode);
+
+	int (*get_uuid)(struct super_block *sb, u8 *buf, u32 *len, u64 *offset);
+	int (*map_blocks)(struct inode *inode, loff_t offset,
+			  u64 len, struct iomap *iomap,
+			  bool write, u32 *device_generation);
+	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
+			     int nr_iomaps, struct iattr *iattr);
 };
 
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 87f14e90e98489..a23556c32703aa 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -19,12 +19,16 @@
 #define F2FS_MAX_LOG_SECTOR_SIZE	12	/* 12 bits for 4096 bytes */
 #define F2FS_LOG_SECTORS_PER_BLOCK	3	/* log number for sector/blk */
 #define F2FS_BLKSIZE			4096	/* support only 4KB block */
+#define F2FS_BLKSIZE_BITS		12	/* bits for F2FS_BLKSIZE */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
 #define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
 
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
 
+#define F2FS_BYTES_TO_BLK(bytes)	((bytes) >> F2FS_BLKSIZE_BITS)
+#define F2FS_BLK_TO_BYTES(blk)		((blk) << F2FS_BLKSIZE_BITS)
+
 /* 0, 1(node nid), 2(meta nid) are reserved node id */
 #define F2FS_RESERVED_NODE_NUM		3
 
@@ -87,6 +91,7 @@ struct f2fs_super_block {
 /*
  * For checkpoint
  */
+#define CP_FASTBOOT_FLAG	0x00000020
 #define CP_FSCK_FLAG		0x00000010
 #define CP_ERROR_FLAG		0x00000008
 #define CP_COMPACT_SUM_FLAG	0x00000004
@@ -224,6 +229,8 @@ enum {
 	OFFSET_BIT_SHIFT
 };
 
+#define OFFSET_BIT_MASK		(0x07)	/* (0x01 << OFFSET_BIT_SHIFT) - 1 */
+
 struct node_footer {
 	__le32 nid;		/* node id */
 	__le32 ino;		/* inode nunmber */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f125b88443bd7c..e49f10cc8a7383 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -34,6 +34,7 @@
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
 
+struct backing_dev_info;
 struct export_operations;
 struct hd_geometry;
 struct iovec;
@@ -394,7 +395,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct page *page, void *fsdata);
 
-struct backing_dev_info;
 struct address_space {
 	struct inode		*host;		/* owner: inode, block_device */
 	struct radix_tree_root	page_tree;	/* radix tree of all pages */
@@ -408,7 +408,6 @@ struct address_space {
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
 	unsigned long		flags;		/* error bits/gfp mask */
-	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
 	spinlock_t		private_lock;	/* for use by the address_space */
 	struct list_head	private_list;	/* ditto */
 	void			*private_data;	/* ditto */
@@ -873,6 +872,7 @@ static inline struct file *get_file(struct file *f)
 #define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
 #define FL_UNLOCK_PENDING	512 /* Lease is being broken */
 #define FL_OFDLCK	1024	/* lock is "owned" by struct file */
+#define FL_LAYOUT	2048	/* outstanding pNFS layout */
 
 /*
  * Special return value from posix_lock_file() and vfs_lock_file() for
@@ -1200,8 +1200,6 @@ struct mm_struct;
 #define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
 #define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
 
-extern struct list_head super_blocks;
-extern spinlock_t sb_lock;
 
 /* Possible states of 'frozen' field */
 enum {
@@ -1518,6 +1516,26 @@ struct block_device_operations;
 #define HAVE_COMPAT_IOCTL 1
 #define HAVE_UNLOCKED_IOCTL 1
 
+/*
+ * These flags let !MMU mmap() govern direct device mapping vs immediate
+ * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
+ *
+ * NOMMU_MAP_COPY:	Copy can be mapped (MAP_PRIVATE)
+ * NOMMU_MAP_DIRECT:	Can be mapped directly (MAP_SHARED)
+ * NOMMU_MAP_READ:	Can be mapped for reading
+ * NOMMU_MAP_WRITE:	Can be mapped for writing
+ * NOMMU_MAP_EXEC:	Can be mapped for execution
+ */
+#define NOMMU_MAP_COPY		0x00000001
+#define NOMMU_MAP_DIRECT	0x00000008
+#define NOMMU_MAP_READ		VM_MAYREAD
+#define NOMMU_MAP_WRITE		VM_MAYWRITE
+#define NOMMU_MAP_EXEC		VM_MAYEXEC
+
+#define NOMMU_VMFLAGS \
+	(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
+
+
 struct iov_iter;
 
 struct file_operations {
@@ -1552,6 +1570,9 @@ struct file_operations {
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	void (*show_fdinfo)(struct seq_file *m, struct file *f);
+#ifndef CONFIG_MMU
+	unsigned (*mmap_capabilities)(struct file *);
+#endif
 };
 
 struct inode_operations {
@@ -1634,8 +1655,10 @@ struct super_operations {
 	struct dquot **(*get_dquots)(struct inode *);
 #endif
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
-	long (*nr_cached_objects)(struct super_block *, int);
-	long (*free_cached_objects)(struct super_block *, long, int);
+	long (*nr_cached_objects)(struct super_block *,
+				  struct shrink_control *);
+	long (*free_cached_objects)(struct super_block *,
+				    struct shrink_control *);
 };
 
 /*
@@ -2035,6 +2058,16 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 	return ret;
 }
 
+static inline int break_layout(struct inode *inode, bool wait)
+{
+	smp_mb();
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
+		return __break_lease(inode,
+				wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
+				FL_LAYOUT);
+	return 0;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct file *file)
 {
@@ -2090,6 +2123,11 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 	return 0;
 }
 
+static inline int break_layout(struct inode *inode, bool wait)
+{
+	return 0;
+}
+
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 3037fc085e8e16..d3d43ecf148cd9 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -193,6 +193,9 @@ extern struct task_group root_task_group;
 	.nr_cpus_allowed= NR_CPUS,					\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
+	.restart_block = {						\
+		.fn = do_no_restart_syscall,				\
+	},								\
 	.se		= {						\
 		.group_node 	= LIST_HEAD_INIT(tsk.se.group_node),	\
 	},								\
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e42e7dc34c6861..d6d630d31ef308 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -800,9 +800,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
 	(type *)( (char *)__mptr - offsetof(type,member) );})
 
-/* Trap pasters of __FUNCTION__ at compile-time */
-#define __FUNCTION__ (__func__)
-
 /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 61df823ac86a24..fc03efa64ffe58 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -823,10 +823,10 @@ struct ata_port {
 	unsigned int		cbl;	/* cable type; ATA_CBL_xxx */
 
 	struct ata_queued_cmd	qcmd[ATA_MAX_QUEUE];
-	unsigned long		qc_allocated;
+	unsigned long		sas_tag_allocated; /* for sas tag allocation only */
 	unsigned int		qc_active;
 	int			nr_active_links; /* #links with active qcs */
-	unsigned int		last_tag;	/* track next tag hw expects */
+	unsigned int		sas_last_tag;	/* track next tag hw expects */
 
 	struct ata_link		link;		/* host default link */
 	struct ata_link		*slave_link;	/* see ata_slave_link_init() */
@@ -1352,6 +1352,7 @@ extern struct device_attribute *ata_common_sdev_attrs[];
 	.ioctl			= ata_scsi_ioctl,		\
 	.queuecommand		= ata_scsi_queuecmd,		\
 	.can_queue		= ATA_DEF_QUEUE,		\
+	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
 	.this_id		= ATA_SHT_THIS_ID,		\
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,		\
 	.emulated		= ATA_SHT_EMULATED,		\
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index f3434533fbf88e..2a6b9947aaa319 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -9,6 +9,9 @@
 
 #include <linux/list.h>
 #include <linux/nodemask.h>
+#include <linux/shrinker.h>
+
+struct mem_cgroup;
 
 /* list_lru_walk_cb has to always return one of those */
 enum lru_status {
@@ -21,24 +24,45 @@ enum lru_status {
 				   internally, but has to return locked. */
 };
 
-struct list_lru_node {
-	spinlock_t		lock;
+struct list_lru_one {
 	struct list_head	list;
-	/* kept as signed so we can catch imbalance bugs */
+	/* may become negative during memcg reparenting */
 	long			nr_items;
+};
+
+struct list_lru_memcg {
+	/* array of per cgroup lists, indexed by memcg_cache_id */
+	struct list_lru_one	*lru[0];
+};
+
+struct list_lru_node {
+	/* protects all lists on the node, including per cgroup */
+	spinlock_t		lock;
+	/* global list, used for the root cgroup in cgroup aware lrus */
+	struct list_lru_one	lru;
+#ifdef CONFIG_MEMCG_KMEM
+	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
+	struct list_lru_memcg	*memcg_lrus;
+#endif
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
 	struct list_lru_node	*node;
-	nodemask_t		active_nodes;
+#ifdef CONFIG_MEMCG_KMEM
+	struct list_head	list;
+#endif
 };
 
 void list_lru_destroy(struct list_lru *lru);
-int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
-static inline int list_lru_init(struct list_lru *lru)
-{
-	return list_lru_init_key(lru, NULL);
-}
+int __list_lru_init(struct list_lru *lru, bool memcg_aware,
+		    struct lock_class_key *key);
+
+#define list_lru_init(lru)		__list_lru_init((lru), false, NULL)
+#define list_lru_init_key(lru, key)	__list_lru_init((lru), false, (key))
+#define list_lru_init_memcg(lru)	__list_lru_init((lru), true, NULL)
+
+int memcg_update_all_list_lrus(int num_memcgs);
+void memcg_drain_all_list_lrus(int src_idx, int dst_idx);
 
 /**
  * list_lru_add: add an element to the lru list's tail
@@ -72,32 +96,48 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item);
 bool list_lru_del(struct list_lru *lru, struct list_head *item);
 
 /**
- * list_lru_count_node: return the number of objects currently held by @lru
+ * list_lru_count_one: return the number of objects currently held by @lru
  * @lru: the lru pointer.
  * @nid: the node id to count from.
+ * @memcg: the cgroup to count from.
  *
  * Always return a non-negative number, 0 for empty lists. There is no
  * guarantee that the list is not updated while the count is being computed.
  * Callers that want such a guarantee need to provide an outer lock.
  */
+unsigned long list_lru_count_one(struct list_lru *lru,
+				 int nid, struct mem_cgroup *memcg);
 unsigned long list_lru_count_node(struct list_lru *lru, int nid);
+
+static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
+						  struct shrink_control *sc)
+{
+	return list_lru_count_one(lru, sc->nid, sc->memcg);
+}
+
 static inline unsigned long list_lru_count(struct list_lru *lru)
 {
 	long count = 0;
 	int nid;
 
-	for_each_node_mask(nid, lru->active_nodes)
+	for_each_node_state(nid, N_NORMAL_MEMORY)
 		count += list_lru_count_node(lru, nid);
 
 	return count;
 }
 
-typedef enum lru_status
-(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
+void list_lru_isolate(struct list_lru_one *list, struct list_head *item);
+void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
+			   struct list_head *head);
+
+typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
+		struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
+
 /**
- * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
+ * @memcg: the cgroup to scan from.
  * @isolate: callback function that is resposible for deciding what to do with
  *  the item currently being scanned
  * @cb_arg: opaque type that will be passed to @isolate
@@ -115,10 +155,22 @@ typedef enum lru_status
  *
  * Return value: the number of objects effectively removed from the LRU.
  */
+unsigned long list_lru_walk_one(struct list_lru *lru,
+				int nid, struct mem_cgroup *memcg,
+				list_lru_walk_cb isolate, void *cb_arg,
+				unsigned long *nr_to_walk);
 unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
 				 list_lru_walk_cb isolate, void *cb_arg,
 				 unsigned long *nr_to_walk);
 
+static inline unsigned long
+list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
+		     list_lru_walk_cb isolate, void *cb_arg)
+{
+	return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg,
+				 &sc->nr_to_scan);
+}
+
 static inline unsigned long
 list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
 	      void *cb_arg, unsigned long nr_to_walk)
@@ -126,7 +178,7 @@ list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
 	long isolated = 0;
 	int nid;
 
-	for_each_node_mask(nid, lru->active_nodes) {
+	for_each_node_state(nid, N_NORMAL_MEMORY) {
 		isolated += list_lru_walk_node(lru, nid, isolate,
 					       cb_arg, &nr_to_walk);
 		if (nr_to_walk <= 0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6cfd934c7c9b3e..72dff5fb0d0cea 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -398,7 +398,9 @@ static inline void sock_release_memcg(struct sock *sk)
 #ifdef CONFIG_MEMCG_KMEM
 extern struct static_key memcg_kmem_enabled_key;
 
-extern int memcg_limited_groups_array_size;
+extern int memcg_nr_cache_ids;
+extern void memcg_get_cache_ids(void);
+extern void memcg_put_cache_ids(void);
 
 /*
  * Helper macro to loop through all memcg-specific caches. Callers must still
@@ -406,13 +408,15 @@ extern int memcg_limited_groups_array_size;
  * the slab_mutex must be held when looping through those caches
  */
 #define for_each_memcg_cache_index(_idx)	\
-	for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++)
+	for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
 
 static inline bool memcg_kmem_enabled(void)
 {
 	return static_key_false(&memcg_kmem_enabled_key);
 }
 
+bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+
 /*
  * In general, we'll do everything in our power to not incur in any overhead
  * for non-memcg users for the kmem functions. Not even a function call, if we
@@ -432,11 +436,11 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
 
-void memcg_update_array_size(int num_groups);
-
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
 
+struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr);
+
 int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 		      unsigned long nr_pages);
 void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
@@ -533,6 +537,13 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 	if (memcg_kmem_enabled())
 		__memcg_kmem_put_cache(cachep);
 }
+
+static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+	if (!memcg_kmem_enabled())
+		return NULL;
+	return __mem_cgroup_from_kmem(ptr);
+}
 #else
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
@@ -542,6 +553,11 @@ static inline bool memcg_kmem_enabled(void)
 	return false;
 }
 
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+	return false;
+}
+
 static inline bool
 memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 {
@@ -562,6 +578,14 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
+static inline void memcg_get_cache_ids(void)
+{
+}
+
+static inline void memcg_put_cache_ids(void)
+{
+}
+
 static inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
@@ -571,6 +595,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 }
+
+static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+	return NULL;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index fab9b32ace8e2c..78baed5f29522e 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -67,7 +67,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 #ifdef CONFIG_NUMA_BALANCING
 extern bool pmd_trans_migrating(pmd_t pmd);
-extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
 extern int migrate_misplaced_page(struct page *page,
 				  struct vm_area_struct *vma, int node);
 extern bool migrate_ratelimited(int node);
@@ -76,9 +75,6 @@ static inline bool pmd_trans_migrating(pmd_t pmd)
 {
 	return false;
 }
-static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
-{
-}
 static inline int migrate_misplaced_page(struct page *page,
 					 struct vm_area_struct *vma, int node)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a4d24f3c5430fe..9bee7ec0c31f6c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1408,6 +1408,11 @@ static inline void update_hiwater_vm(struct mm_struct *mm)
 		mm->hiwater_vm = mm->total_vm;
 }
 
+static inline void reset_mm_hiwater_rss(struct mm_struct *mm)
+{
+	mm->hiwater_rss = get_mm_rss(mm);
+}
+
 static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
 					 struct mm_struct *mm)
 {
@@ -1447,13 +1452,15 @@ static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
 int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
 #endif
 
-#ifdef __PAGETABLE_PMD_FOLDED
+#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
 static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
 						unsigned long address)
 {
 	return 0;
 }
 
+static inline void mm_nr_pmds_init(struct mm_struct *mm) {}
+
 static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
 {
 	return 0;
@@ -1465,6 +1472,11 @@ static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}
 #else
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 
+static inline void mm_nr_pmds_init(struct mm_struct *mm)
+{
+	atomic_long_set(&mm->nr_pmds, 0);
+}
+
 static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
 {
 	return atomic_long_read(&mm->nr_pmds);
@@ -2168,9 +2180,8 @@ int drop_caches_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 #endif
 
-unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
-				unsigned long nr_scanned,
-				unsigned long nr_eligible);
+void drop_slab(void);
+void drop_slab_node(int nid);
 
 #ifndef CONFIG_MMU
 #define randomize_va_space 0
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 031ff3a9a0bdff..3301c4c289d625 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -408,4 +408,6 @@ static inline int mtd_is_bitflip_or_eccerr(int err) {
 	return mtd_is_bitflip(err) || mtd_is_eccerr(err);
 }
 
+unsigned mtd_mmap_capabilities(struct mtd_info *mtd);
+
 #endif /* __MTD_MTD_H__ */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index de7c91ca427e6e..ed43cb74b11d75 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -411,6 +411,7 @@ enum lock_type4 {
 #define FATTR4_WORD1_TIME_MODIFY_SET    (1UL << 22)
 #define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
 #define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
+#define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
@@ -517,6 +518,7 @@ enum pnfs_layouttype {
 	LAYOUT_OSD2_OBJECTS = 2,
 	LAYOUT_BLOCK_VOLUME = 3,
 	LAYOUT_FLEX_FILES = 4,
+	LAYOUT_TYPE_MAX
 };
 
 /* used for both layout return and recall */
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 83a6aeda899d56..21cef483dc1bf1 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -120,13 +120,13 @@ static inline void __node_clear(int node, volatile nodemask_t *dstp)
 }
 
 #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
-static inline void __nodes_setall(nodemask_t *dstp, int nbits)
+static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_fill(dstp->bits, nbits);
 }
 
 #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
-static inline void __nodes_clear(nodemask_t *dstp, int nbits)
+static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_zero(dstp->bits, nbits);
 }
@@ -144,7 +144,7 @@ static inline int __node_test_and_set(int node, nodemask_t *addr)
 #define nodes_and(dst, src1, src2) \
 			__nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
@@ -152,7 +152,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
 #define nodes_or(dst, src1, src2) \
 			__nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
@@ -160,7 +160,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
 #define nodes_xor(dst, src1, src2) \
 			__nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
@@ -168,7 +168,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
 #define nodes_andnot(dst, src1, src2) \
 			__nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
 static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
@@ -176,7 +176,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
 #define nodes_complement(dst, src) \
 			__nodes_complement(&(dst), &(src), MAX_NUMNODES)
 static inline void __nodes_complement(nodemask_t *dstp,
-					const nodemask_t *srcp, int nbits)
+					const nodemask_t *srcp, unsigned int nbits)
 {
 	bitmap_complement(dstp->bits, srcp->bits, nbits);
 }
@@ -184,7 +184,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
 static inline int __nodes_equal(const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
 }
@@ -192,7 +192,7 @@ static inline int __nodes_equal(const nodemask_t *src1p,
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
 static inline int __nodes_intersects(const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
 }
@@ -200,25 +200,25 @@ static inline int __nodes_intersects(const nodemask_t *src1p,
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
 static inline int __nodes_subset(const nodemask_t *src1p,
-					const nodemask_t *src2p, int nbits)
+					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline int __nodes_empty(const nodemask_t *srcp, int nbits)
+static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_full(const nodemask_t *srcp, int nbits)
+static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }
 
 #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_weight(const nodemask_t *srcp, int nbits)
+static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_weight(srcp->bits, nbits);
 }
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 258945fcabf17c..19a5d4b2320930 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -132,13 +132,12 @@ struct nvme_ns {
  * allocated to store the PRP list.
  */
 struct nvme_iod {
-	void *private;		/* For the use of the submitter of the I/O */
+	unsigned long private;	/* For the use of the submitter of the I/O */
 	int npages;		/* In the PRP list. 0 means small pool in use */
 	int offset;		/* Of PRP list */
 	int nents;		/* Used in scatterlist */
 	int length;		/* Of data, in bytes */
 	dma_addr_t first_dma;
-	struct list_head node;
 	struct scatterlist sg[0];
 };
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 4d5bf5726578c5..baa3f97d8ce87b 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -417,9 +417,9 @@ enum {
 	DUMP_PREFIX_ADDRESS,
 	DUMP_PREFIX_OFFSET
 };
-extern void hex_dump_to_buffer(const void *buf, size_t len,
-			       int rowsize, int groupsize,
-			       char *linebuf, size_t linebuflen, bool ascii);
+extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
+			      int groupsize, char *linebuf, size_t linebuflen,
+			      bool ascii);
 #ifdef CONFIG_PRINTK
 extern void print_hex_dump(const char *level, const char *prefix_str,
 			   int prefix_type, int rowsize, int groupsize,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8db31ef98d2f4b..048b91b983ed39 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1370,6 +1370,8 @@ struct task_struct {
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
+	struct restart_block restart_block;
+
 	pid_t pid;
 	pid_t tgid;
 
@@ -2145,6 +2147,7 @@ extern unsigned long long notrace sched_clock(void);
  */
 extern u64 cpu_clock(int cpu);
 extern u64 local_clock(void);
+extern u64 running_clock(void);
 extern u64 sched_clock_cpu(int cpu);
 
 
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index f4aee75f00b194..4fcacd915d45ad 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -20,6 +20,9 @@ struct shrink_control {
 
 	/* current node being shrunk (for NUMA aware shrinkers) */
 	int nid;
+
+	/* current memcg being shrunk (for memcg aware shrinkers) */
+	struct mem_cgroup *memcg;
 };
 
 #define SHRINK_STOP (~0UL)
@@ -61,7 +64,8 @@ struct shrinker {
 #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
 
 /* Flags */
-#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_NUMA_AWARE	(1 << 0)
+#define SHRINKER_MEMCG_AWARE	(1 << 1)
 
 extern int register_shrinker(struct shrinker *);
 extern void unregister_shrinker(struct shrinker *);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 2e3b448cfa2d8b..ed2ffaab59ea5e 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -115,13 +115,12 @@ int slab_is_available(void);
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
 			void (*)(void *));
-#ifdef CONFIG_MEMCG_KMEM
-void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
-void memcg_destroy_kmem_caches(struct mem_cgroup *);
-#endif
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
-void kmem_cache_free(struct kmem_cache *, void *);
+
+void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
+void memcg_deactivate_kmem_caches(struct mem_cgroup *);
+void memcg_destroy_kmem_caches(struct mem_cgroup *);
 
 /*
  * Please use this macro to create slab caches. Simply specify the
@@ -288,6 +287,7 @@ static __always_inline int kmalloc_index(size_t size)
 
 void *__kmalloc(size_t size, gfp_t flags);
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags);
+void kmem_cache_free(struct kmem_cache *, void *);
 
 #ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node);
@@ -473,14 +473,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 #ifndef ARCH_SLAB_MINALIGN
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
+
+struct memcg_cache_array {
+	struct rcu_head rcu;
+	struct kmem_cache *entries[0];
+};
+
 /*
  * This is the main placeholder for memcg-related information in kmem caches.
- * struct kmem_cache will hold a pointer to it, so the memory cost while
- * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it
- * would otherwise be if that would be bundled in kmem_cache: we'll need an
- * extra pointer chase. But the trade off clearly lays in favor of not
- * penalizing non-users.
- *
  * Both the root cache and the child caches will have it. For the root cache,
  * this will hold a dynamically allocated array large enough to hold
  * information about the currently limited memcgs in the system. To allow the
@@ -491,14 +491,15 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
  *
  * @memcg: pointer to the memcg this cache belongs to
  * @root_cache: pointer to the global, root cache, this cache was derived from
+ *
+ * Both root and child caches of the same kind are linked into a list chained
+ * through @list.
  */
 struct memcg_cache_params {
 	bool is_root_cache;
+	struct list_head list;
 	union {
-		struct {
-			struct rcu_head rcu_head;
-			struct kmem_cache *memcg_caches[0];
-		};
+		struct memcg_cache_array __rcu *memcg_caches;
 		struct {
 			struct mem_cgroup *memcg;
 			struct kmem_cache *root_cache;
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index b869d1662ba346..33d049066c3d43 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -70,7 +70,7 @@ struct kmem_cache {
 	int obj_offset;
 #endif /* CONFIG_DEBUG_SLAB */
 #ifdef CONFIG_MEMCG_KMEM
-	struct memcg_cache_params *memcg_params;
+	struct memcg_cache_params memcg_params;
 #endif
 
 	struct kmem_cache_node *node[MAX_NUMNODES];
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index d82abd40a3c061..9abf04ed0999ce 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -85,7 +85,7 @@ struct kmem_cache {
 	struct kobject kobj;	/* For sysfs */
 #endif
 #ifdef CONFIG_MEMCG_KMEM
-	struct memcg_cache_params *memcg_params;
+	struct memcg_cache_params memcg_params;
 	int max_attr_size; /* for propagation, maximum size of a stored attr */
 #ifdef CONFIG_SYSFS
 	struct kset *memcg_kset;
diff --git a/include/linux/string.h b/include/linux/string.h
index 2e22a2e58f3af5..b9bc9a5d9e217f 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -40,9 +40,6 @@ extern int strcmp(const char *,const char *);
 #ifndef __HAVE_ARCH_STRNCMP
 extern int strncmp(const char *,const char *,__kernel_size_t);
 #endif
-#ifndef __HAVE_ARCH_STRNICMP
-#define strnicmp strncasecmp
-#endif
 #ifndef __HAVE_ARCH_STRCASECMP
 extern int strcasecmp(const char *s1, const char *s2);
 #endif
diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 6eb567ac56bc10..657571817260ab 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -10,8 +10,8 @@ enum string_size_units {
 	STRING_UNITS_2,		/* use binary powers of 2^10 */
 };
 
-int string_get_size(u64 size, enum string_size_units units,
-		    char *buf, int len);
+void string_get_size(u64 size, enum string_size_units units,
+		     char *buf, int len);
 
 #define UNESCAPE_SPACE		0x01
 #define UNESCAPE_OCTAL		0x02
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 6f22cfeef5e3c5..fae6fb947fc867 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -110,7 +110,7 @@ struct svc_serv {
  * We use sv_nrthreads as a reference count.  svc_destroy() drops
  * this refcount, so we need to bump it up around operations that
  * change the number of threads.  Horrible, but there it is.
- * Should be called with the BKL held.
+ * Should be called with the "service mutex" held.
  */
 static inline void svc_get(struct svc_serv *serv)
 {
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index ddfe88f522199c..df8edf8ec914d9 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -77,6 +77,7 @@ struct svc_rdma_op_ctxt {
 	enum ib_wr_opcode wr_op;
 	enum ib_wc_status wc_status;
 	u32 byte_len;
+	u32 position;
 	struct svcxprt_rdma *xprt;
 	unsigned long flags;
 	enum dma_data_direction direction;
@@ -148,6 +149,10 @@ struct svcxprt_rdma {
 	struct ib_cq         *sc_rq_cq;
 	struct ib_cq         *sc_sq_cq;
 	struct ib_mr         *sc_phys_mr;	/* MR for server memory */
+	int		     (*sc_reader)(struct svcxprt_rdma *,
+					  struct svc_rqst *,
+					  struct svc_rdma_op_ctxt *,
+					  int *, u32 *, u32, u32, u64, bool);
 	u32		     sc_dev_caps;	/* distilled device caps */
 	u32		     sc_dma_lkey;	/* local dma key */
 	unsigned int	     sc_frmr_pg_list_len;
@@ -176,8 +181,6 @@ struct svcxprt_rdma {
 #define RPCRDMA_MAX_REQ_SIZE    4096
 
 /* svc_rdma_marshal.c */
-extern void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *,
-				      int *, int *);
 extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *);
 extern int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *);
 extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
@@ -195,6 +198,12 @@ extern int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *);
 
 /* svc_rdma_recvfrom.c */
 extern int svc_rdma_recvfrom(struct svc_rqst *);
+extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *,
+			       struct svc_rdma_op_ctxt *, int *, u32 *,
+			       u32, u32, u64, bool);
+extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
+				struct svc_rdma_op_ctxt *, int *, u32 *,
+				u32, u32, u64, bool);
 
 /* svc_rdma_sendto.c */
 extern int svc_rdma_sendto(struct svc_rqst *);
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 831a3168ab35a6..cedf3d3c373f16 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry)
 /* check whether a pte points to a swap entry */
 static inline int is_swap_pte(pte_t pte)
 {
-	return !pte_none(pte) && !pte_present_nonuma(pte);
+	return !pte_none(pte) && !pte_present(pte);
 }
 #endif
 
diff --git a/include/linux/types.h b/include/linux/types.h
index 62323825cff943..6747247e3f9fd5 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -135,12 +135,9 @@ typedef unsigned long blkcnt_t;
 #endif
 
 /*
- * The type of an index into the pagecache.  Use a #define so asm/types.h
- * can override it.
+ * The type of an index into the pagecache.
  */
-#ifndef pgoff_t
 #define pgoff_t unsigned long
-#endif
 
 /* A dma_addr_t can hold any valid DMA or bus address for the platform */
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 537d58eea8a084..2db83349865bb7 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -267,6 +267,21 @@ do {									\
 	__wait_event(wq, condition);					\
 } while (0)
 
+#define __io_wait_event(wq, condition)					\
+	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			    io_schedule())
+
+/*
+ * io_wait_event() -- like wait_event() but with io_schedule()
+ */
+#define io_wait_event(wq, condition)					\
+do {									\
+	might_sleep();							\
+	if (condition)							\
+		break;							\
+	__io_wait_event(wq, condition);					\
+} while (0)
+
 #define __wait_event_freezable(wq, condition)				\
 	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 			    schedule(); try_to_freeze())
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index f14bd75f08b395..56529b34dc6353 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -36,7 +36,8 @@ enum zpool_mapmode {
 	ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
 };
 
-struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops);
+struct zpool *zpool_create_pool(char *type, char *name,
+			gfp_t gfp, struct zpool_ops *ops);
 
 char *zpool_get_type(struct zpool *pool);
 
@@ -80,7 +81,7 @@ struct zpool_driver {
 	atomic_t refcount;
 	struct list_head list;
 
-	void *(*create)(gfp_t gfp, struct zpool_ops *ops);
+	void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops);
 	void (*destroy)(void *pool);
 
 	int (*malloc)(void *pool, size_t size, gfp_t gfp,
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 05c21476097796..3283c6a55425d6 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -36,7 +36,7 @@ enum zs_mapmode {
 
 struct zs_pool;
 
-struct zs_pool *zs_create_pool(gfp_t flags);
+struct zs_pool *zs_create_pool(char *name, gfp_t flags);
 void zs_destroy_pool(struct zs_pool *pool);
 
 unsigned long zs_malloc(struct zs_pool *pool, size_t size);
diff --git a/include/net/sock.h b/include/net/sock.h
index e13824570b0fdc..ab186b1d31fffe 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1077,11 +1077,6 @@ static inline bool memcg_proto_active(struct cg_proto *cg_proto)
 	return test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
 }
 
-static inline bool memcg_proto_activated(struct cg_proto *cg_proto)
-{
-	return test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags);
-}
-
 #ifdef SOCK_REFCNT_DEBUG
 static inline void sk_refcnt_debug_inc(struct sock *sk)
 {
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 019e66858ce64a..e113c757d555ef 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -402,6 +402,9 @@ struct scsi_host_template {
 	 */
 	unsigned char present;
 
+	/* If use block layer to manage tags, this is tag allocation policy */
+	int tag_alloc_policy;
+
 	/*
 	 * Let the block layer assigns tags to all commands.
 	 */
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 9708b28bd2aa1b..b27977e8aaed9b 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -66,7 +66,8 @@ static inline int scsi_init_shared_tag_map(struct Scsi_Host *shost, int depth)
 	 * devices on the shared host (for libata)
 	 */
 	if (!shost->bqt) {
-		shost->bqt = blk_init_tags(depth);
+		shost->bqt = blk_init_tags(depth,
+			shost->hostt->tag_alloc_policy);
 		if (!shost->bqt)
 			return -ENOMEM;
 	}
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index bbc4de9baef765..5422dbfaf97d65 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -72,6 +72,7 @@
 #define show_cpreason(type)						\
 	__print_symbolic(type,						\
 		{ CP_UMOUNT,	"Umount" },				\
+		{ CP_FASTBOOT,	"Fastboot" },				\
 		{ CP_SYNC,	"Sync" },				\
 		{ CP_DISCARD,	"Discard" })
 
@@ -148,14 +149,14 @@ DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
 
 TRACE_EVENT(f2fs_sync_file_exit,
 
-	TP_PROTO(struct inode *inode, bool need_cp, int datasync, int ret),
+	TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret),
 
 	TP_ARGS(inode, need_cp, datasync, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(bool,	need_cp)
+		__field(int,	need_cp)
 		__field(int,	datasync)
 		__field(int,	ret)
 	),
@@ -190,7 +191,7 @@ TRACE_EVENT(f2fs_sync_fs,
 
 	TP_fast_assign(
 		__entry->dev	= sb->s_dev;
-		__entry->dirty	= F2FS_SB(sb)->s_dirty;
+		__entry->dirty	= is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY);
 		__entry->wait	= wait;
 	),
 
@@ -440,38 +441,6 @@ TRACE_EVENT(f2fs_truncate_partial_nodes,
 		__entry->err)
 );
 
-TRACE_EVENT_CONDITION(f2fs_submit_page_bio,
-
-	TP_PROTO(struct page *page, sector_t blkaddr, int type),
-
-	TP_ARGS(page, blkaddr, type),
-
-	TP_CONDITION(page->mapping),
-
-	TP_STRUCT__entry(
-		__field(dev_t,	dev)
-		__field(ino_t,	ino)
-		__field(pgoff_t,	index)
-		__field(sector_t,	blkaddr)
-		__field(int,	type)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= page->mapping->host->i_sb->s_dev;
-		__entry->ino		= page->mapping->host->i_ino;
-		__entry->index		= page->index;
-		__entry->blkaddr	= blkaddr;
-		__entry->type		= type;
-	),
-
-	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
-		"blkaddr = 0x%llx, bio_type = %s%s",
-		show_dev_ino(__entry),
-		(unsigned long)__entry->index,
-		(unsigned long long)__entry->blkaddr,
-		show_bio_type(__entry->type))
-);
-
 TRACE_EVENT(f2fs_get_data_block,
 	TP_PROTO(struct inode *inode, sector_t iblock,
 				struct buffer_head *bh, int ret),
@@ -680,11 +649,63 @@ TRACE_EVENT(f2fs_reserve_new_block,
 		__entry->ofs_in_node)
 );
 
+DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(ino_t, ino)
+		__field(pgoff_t, index)
+		__field(block_t, blkaddr)
+		__field(int, rw)
+		__field(int, type)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= page->mapping->host->i_sb->s_dev;
+		__entry->ino		= page->mapping->host->i_ino;
+		__entry->index		= page->index;
+		__entry->blkaddr	= fio->blk_addr;
+		__entry->rw		= fio->rw;
+		__entry->type		= fio->type;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
+		"blkaddr = 0x%llx, rw = %s%s, type = %s",
+		show_dev_ino(__entry),
+		(unsigned long)__entry->index,
+		(unsigned long long)__entry->blkaddr,
+		show_bio_type(__entry->rw),
+		show_block_type(__entry->type))
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_CONDITION(page->mapping)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_CONDITION(page->mapping)
+);
+
 DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+						struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
@@ -696,8 +717,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->rw		= rw;
-		__entry->type		= type;
+		__entry->rw		= fio->rw;
+		__entry->type		= fio->type;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->size		= bio->bi_iter.bi_size;
 	),
@@ -712,18 +733,20 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+							struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_CONDITION(bio)
 );
 
 DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+							struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_CONDITION(bio)
 );
@@ -916,38 +939,6 @@ TRACE_EVENT(f2fs_writepages,
 		__entry->for_sync)
 );
 
-TRACE_EVENT(f2fs_submit_page_mbio,
-
-	TP_PROTO(struct page *page, int rw, int type, block_t blk_addr),
-
-	TP_ARGS(page, rw, type, blk_addr),
-
-	TP_STRUCT__entry(
-		__field(dev_t,	dev)
-		__field(ino_t,	ino)
-		__field(int, rw)
-		__field(int, type)
-		__field(pgoff_t, index)
-		__field(block_t, block)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= page->mapping->host->i_sb->s_dev;
-		__entry->ino	= page->mapping->host->i_ino;
-		__entry->rw	= rw;
-		__entry->type	= type;
-		__entry->index	= page->index;
-		__entry->block	= blk_addr;
-	),
-
-	TP_printk("dev = (%d,%d), ino = %lu, %s%s, %s, index = %lu, blkaddr = 0x%llx",
-		show_dev_ino(__entry),
-		show_bio_type(__entry->rw),
-		show_block_type(__entry->type),
-		(unsigned long)__entry->index,
-		(unsigned long long)__entry->block)
-);
-
 TRACE_EVENT(f2fs_write_checkpoint,
 
 	TP_PROTO(struct super_block *sb, int reason, char *msg),
@@ -998,14 +989,15 @@ TRACE_EVENT(f2fs_issue_discard,
 
 TRACE_EVENT(f2fs_issue_flush,
 
-	TP_PROTO(struct super_block *sb, bool nobarrier, bool flush_merge),
+	TP_PROTO(struct super_block *sb, unsigned int nobarrier,
+					unsigned int flush_merge),
 
 	TP_ARGS(sb, nobarrier, flush_merge),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
-		__field(bool, nobarrier)
-		__field(bool, flush_merge)
+		__field(unsigned int, nobarrier)
+		__field(unsigned int, flush_merge)
 	),
 
 	TP_fast_assign(
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index cee02d65ab3f17..0e9310905413ff 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -47,7 +47,7 @@ TRACE_EVENT(writeback_dirty_page,
 
 	TP_fast_assign(
 		strncpy(__entry->name,
-			mapping ? dev_name(mapping->backing_dev_info->dev) : "(unknown)", 32);
+			mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", 32);
 		__entry->ino = mapping ? mapping->host->i_ino : 0;
 		__entry->index = page->index;
 	),
@@ -72,7 +72,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 	),
 
 	TP_fast_assign(
-		struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(inode);
 
 		/* may be called for files on pseudo FSes w/ unregistered bdi */
 		strncpy(__entry->name,
@@ -116,7 +116,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 
 	TP_fast_assign(
 		strncpy(__entry->name,
-			dev_name(inode->i_mapping->backing_dev_info->dev), 32);
+			dev_name(inode_to_bdi(inode)->dev), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->sync_mode	= wbc->sync_mode;
 	),
@@ -156,10 +156,8 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(int, reason)
 	),
 	TP_fast_assign(
-		struct device *dev = bdi->dev;
-		if (!dev)
-			dev = default_backing_dev_info.dev;
-		strncpy(__entry->name, dev_name(dev), 32);
+		strncpy(__entry->name,
+			bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
 		__entry->nr_pages = work->nr_pages;
 		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
 		__entry->sync_mode = work->sync_mode;
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index a570d7b5796c58..889f3a5b7b1826 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	29
+#define DM_VERSION_MINOR	30
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2014-10-28)"
+#define DM_VERSION_EXTRA	"-ioctl (2014-12-22)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 0d11c3dcd3a18e..9cd8b21dddbe66 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -67,7 +67,7 @@ enum mpol_rebind_step {
 #define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
 #define MPOL_F_REBINDING (1 << 2)	/* identify policies in rebinding */
 #define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
-#define MPOL_F_MORON	(1 << 4) /* Migrate On pte_numa Reference On Node */
+#define MPOL_F_MORON	(1 << 4) /* Migrate On protnone Reference On Node */
 
 
 #endif /* _UAPI_LINUX_MEMPOLICY_H */
diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h
index 1fdc95bb2375c5..0bf130a1c58df4 100644
--- a/include/uapi/linux/nfsd/debug.h
+++ b/include/uapi/linux/nfsd/debug.h
@@ -32,6 +32,7 @@
 #define NFSDDBG_REPCACHE	0x0080
 #define NFSDDBG_XDR		0x0100
 #define NFSDDBG_LOCKD		0x0200
+#define NFSDDBG_PNFS		0x0400
 #define NFSDDBG_ALL		0x7FFF
 #define NFSDDBG_NOCHANGE	0xFFFF
 
diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h
index 584b6ef3a5e8c0..4742f2cb42f2bd 100644
--- a/include/uapi/linux/nfsd/export.h
+++ b/include/uapi/linux/nfsd/export.h
@@ -47,8 +47,10 @@
  * exported filesystem.
  */
 #define	NFSEXP_V4ROOT		0x10000
+#define NFSEXP_NOPNFS		0x20000
+
 /* All flags that we claim to support.  (Note we don't support NOACL.) */
-#define NFSEXP_ALLFLAGS		0x1FE7F
+#define NFSEXP_ALLFLAGS		0x3FE7F
 
 /* The flags that may vary depending on security flavor: */
 #define NFSEXP_SECINFO_FLAGS	(NFSEXP_READONLY | NFSEXP_ROOTSQUASH \
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 04cfe8ace52088..d5f6ec251fb2bc 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4373,16 +4373,20 @@ static void css_free_work_fn(struct work_struct *work)
 {
 	struct cgroup_subsys_state *css =
 		container_of(work, struct cgroup_subsys_state, destroy_work);
+	struct cgroup_subsys *ss = css->ss;
 	struct cgroup *cgrp = css->cgroup;
 
 	percpu_ref_exit(&css->refcnt);
 
-	if (css->ss) {
+	if (ss) {
 		/* css free path */
+		int id = css->id;
+
 		if (css->parent)
 			css_put(css->parent);
 
-		css->ss->css_free(css);
+		ss->css_free(css);
+		cgroup_idr_remove(&ss->css_idr, id);
 		cgroup_put(cgrp);
 	} else {
 		/* cgroup free path */
@@ -4434,7 +4438,7 @@ static void css_release_work_fn(struct work_struct *work)
 
 	if (ss) {
 		/* css release path */
-		cgroup_idr_remove(&ss->css_idr, css->id);
+		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
 		if (ss->css_released)
 			ss->css_released(css);
 	} else {
diff --git a/kernel/compat.c b/kernel/compat.c
index ebb3c369d03d59..24f00610c575fd 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -276,8 +276,7 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
 	 * core implementation decides to return random nonsense.
 	 */
 	if (ret == -ERESTART_RESTARTBLOCK) {
-		struct restart_block *restart
-			= &current_thread_info()->restart_block;
+		struct restart_block *restart = &current->restart_block;
 
 		restart->fn = compat_nanosleep_restart;
 		restart->nanosleep.compat_rmtp = rmtp;
@@ -860,7 +859,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 		return -EFAULT;
 
 	if (err == -ERESTART_RESTARTBLOCK) {
-		restart = &current_thread_info()->restart_block;
+		restart = &current->restart_block;
 		restart->fn = compat_clock_nanosleep_restart;
 		restart->nanosleep.compat_rmtp = rmtp;
 	}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 64b257f6bca2e2..c54a1dae6c1136 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2400,7 +2400,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	 */
 }
 
-void cpuset_init_current_mems_allowed(void)
+void __init cpuset_init_current_mems_allowed(void)
 {
 	nodes_setall(current->mems_allowed);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 66e19c251581d1..cf65139615a0d3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -555,9 +555,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
 	atomic_long_set(&mm->nr_ptes, 0);
-#ifndef __PAGETABLE_PMD_FOLDED
-	atomic_long_set(&mm->nr_pmds, 0);
-#endif
+	mm_nr_pmds_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
 	mm->pinned_vm = 0;
diff --git a/kernel/futex.c b/kernel/futex.c
index 4eeb63de7e54e8..2a5e3830e953b7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2217,7 +2217,7 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 	if (!abs_time)
 		goto out;
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 02d6b6d2879699..c06df7de0963a3 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -935,8 +935,8 @@ static int __init ignore_loglevel_setup(char *str)
 
 early_param("ignore_loglevel", ignore_loglevel_setup);
 module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to"
-	"print all kernel messages to the console.");
+MODULE_PARM_DESC(ignore_loglevel,
+		 "ignore loglevel setting (prints all kernel messages to the console)");
 
 #ifdef CONFIG_BOOT_PRINTK_DELAY
 
@@ -1419,16 +1419,16 @@ static void call_console_drivers(int level, const char *text, size_t len)
 }
 
 /*
- * Zap console related locks when oopsing. Only zap at most once
- * every 10 seconds, to leave time for slow consoles to print a
- * full oops.
+ * Zap console related locks when oopsing.
+ * To leave time for slow consoles to print a full oops,
+ * only zap at most once every 30 seconds.
  */
 static void zap_locks(void)
 {
 	static unsigned long oops_timestamp;
 
 	if (time_after_eq(jiffies, oops_timestamp) &&
-			!time_after(jiffies, oops_timestamp + 30 * HZ))
+	    !time_after(jiffies, oops_timestamp + 30 * HZ))
 		return;
 
 	oops_timestamp = jiffies;
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c27e4f8f4879eb..c0a205101c231a 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -420,3 +420,16 @@ u64 local_clock(void)
 
 EXPORT_SYMBOL_GPL(cpu_clock);
 EXPORT_SYMBOL_GPL(local_clock);
+
+/*
+ * Running clock - returns the time that has elapsed while a guest has been
+ * running.
+ * On a guest this value should be local_clock minus the time the guest was
+ * suspended by the hypervisor (for any reason).
+ * On bare metal this function should return the same as local_clock.
+ * Architectures and sub-architectures can override this.
+ */
+u64 __weak running_clock(void)
+{
+	return local_clock();
+}
diff --git a/kernel/signal.c b/kernel/signal.c
index 16a305295256dd..33a52759cc0edf 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2501,7 +2501,7 @@ EXPORT_SYMBOL(unblock_all_signals);
  */
 SYSCALL_DEFINE0(restart_syscall)
 {
-	struct restart_block *restart = &current_thread_info()->restart_block;
+	struct restart_block *restart = &current->restart_block;
 	return restart->fn(restart);
 }
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index a7077d3ae52fe2..1b001ed1edb945 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -788,7 +788,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp.tv64;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3f5e183c3d9727..bee0c1f780911a 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1583,7 +1583,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.rmtp = rmtp;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index a16b67859e2a79..0075da74abf0c5 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1334,8 +1334,7 @@ static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
 static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
-	struct restart_block *restart_block =
-		&current_thread_info()->restart_block;
+	struct restart_block *restart_block = &current->restart_block;
 	struct itimerspec it;
 	int error;
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 70bf11815f8445..3174bf8e353852 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -154,7 +154,7 @@ static int get_softlockup_thresh(void)
  */
 static unsigned long get_timestamp(void)
 {
-	return local_clock() >> 30LL;  /* 2^30 ~= 10^9 */
+	return running_clock() >> 30LL;  /* 2^30 ~= 10^9 */
 }
 
 static void set_sample_period(void)
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e5ea3ab856bf51..79a9bb67aeaf28 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1580,6 +1580,9 @@ config ASYNC_RAID6_TEST
 
 	  If unsure, say N.
 
+config TEST_HEXDUMP
+	tristate "Test functions located in the hexdump module at runtime"
+
 config TEST_STRING_HELPERS
 	tristate "Test functions located in the string_helpers module at runtime"
 
diff --git a/lib/Makefile b/lib/Makefile
index 25c061f77df799..e456defd102145 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -23,12 +23,14 @@ lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
-	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
+	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
 	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
+obj-y += hexdump.o
+obj-$(CONFIG_TEST_HEXDUMP) += test-hexdump.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_LKM) += test_module.o
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 324ea9eab8c1c6..ad161a6c82db69 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -744,10 +744,10 @@ EXPORT_SYMBOL(bitmap_parselist_user);
 /**
  * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
  *	@buf: pointer to a bitmap
- *	@pos: a bit position in @buf (0 <= @pos < @bits)
- *	@bits: number of valid bit positions in @buf
+ *	@pos: a bit position in @buf (0 <= @pos < @nbits)
+ *	@nbits: number of valid bit positions in @buf
  *
- * Map the bit at position @pos in @buf (of length @bits) to the
+ * Map the bit at position @pos in @buf (of length @nbits) to the
  * ordinal of which set bit it is.  If it is not set or if @pos
  * is not a valid bit position, map to -1.
  *
@@ -759,56 +759,40 @@ EXPORT_SYMBOL(bitmap_parselist_user);
  *
  * The bit positions 0 through @bits are valid positions in @buf.
  */
-static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
+static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits)
 {
-	int i, ord;
-
-	if (pos < 0 || pos >= bits || !test_bit(pos, buf))
+	if (pos >= nbits || !test_bit(pos, buf))
 		return -1;
 
-	i = find_first_bit(buf, bits);
-	ord = 0;
-	while (i < pos) {
-		i = find_next_bit(buf, bits, i + 1);
-	     	ord++;
-	}
-	BUG_ON(i != pos);
-
-	return ord;
+	return __bitmap_weight(buf, pos);
 }
 
 /**
  * bitmap_ord_to_pos - find position of n-th set bit in bitmap
  *	@buf: pointer to bitmap
  *	@ord: ordinal bit position (n-th set bit, n >= 0)
- *	@bits: number of valid bit positions in @buf
+ *	@nbits: number of valid bit positions in @buf
  *
  * Map the ordinal offset of bit @ord in @buf to its position in @buf.
- * Value of @ord should be in range 0 <= @ord < weight(buf), else
- * results are undefined.
+ * Value of @ord should be in range 0 <= @ord < weight(buf). If @ord
+ * >= weight(buf), returns @nbits.
  *
  * If for example, just bits 4 through 7 are set in @buf, then @ord
  * values 0 through 3 will get mapped to 4 through 7, respectively,
- * and all other @ord values return undefined values.  When @ord value 3
+ * and all other @ord values returns @nbits.  When @ord value 3
  * gets mapped to (returns) @pos value 7 in this example, that means
  * that the 3rd set bit (starting with 0th) is at position 7 in @buf.
  *
- * The bit positions 0 through @bits are valid positions in @buf.
+ * The bit positions 0 through @nbits-1 are valid positions in @buf.
  */
-int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
+unsigned int bitmap_ord_to_pos(const unsigned long *buf, unsigned int ord, unsigned int nbits)
 {
-	int pos = 0;
-
-	if (ord >= 0 && ord < bits) {
-		int i;
+	unsigned int pos;
 
-		for (i = find_first_bit(buf, bits);
-		     i < bits && ord > 0;
-		     i = find_next_bit(buf, bits, i + 1))
-	     		ord--;
-		if (i < bits && ord == 0)
-			pos = i;
-	}
+	for (pos = find_first_bit(buf, nbits);
+	     pos < nbits && ord;
+	     pos = find_next_bit(buf, nbits, pos + 1))
+		ord--;
 
 	return pos;
 }
@@ -819,7 +803,7 @@ int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
  *	@src: subset to be remapped
  *	@old: defines domain of map
  *	@new: defines range of map
- *	@bits: number of bits in each of these bitmaps
+ *	@nbits: number of bits in each of these bitmaps
  *
  * Let @old and @new define a mapping of bit positions, such that
  * whatever position is held by the n-th set bit in @old is mapped
@@ -847,22 +831,22 @@ int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
  */
 void bitmap_remap(unsigned long *dst, const unsigned long *src,
 		const unsigned long *old, const unsigned long *new,
-		int bits)
+		unsigned int nbits)
 {
-	int oldbit, w;
+	unsigned int oldbit, w;
 
 	if (dst == src)		/* following doesn't handle inplace remaps */
 		return;
-	bitmap_zero(dst, bits);
+	bitmap_zero(dst, nbits);
 
-	w = bitmap_weight(new, bits);
-	for_each_set_bit(oldbit, src, bits) {
-	     	int n = bitmap_pos_to_ord(old, oldbit, bits);
+	w = bitmap_weight(new, nbits);
+	for_each_set_bit(oldbit, src, nbits) {
+		int n = bitmap_pos_to_ord(old, oldbit, nbits);
 
 		if (n < 0 || w == 0)
 			set_bit(oldbit, dst);	/* identity map */
 		else
-			set_bit(bitmap_ord_to_pos(new, n % w, bits), dst);
+			set_bit(bitmap_ord_to_pos(new, n % w, nbits), dst);
 	}
 }
 EXPORT_SYMBOL(bitmap_remap);
@@ -1006,9 +990,9 @@ EXPORT_SYMBOL(bitmap_bitremap);
  * All bits in @dst not set by the above rule are cleared.
  */
 void bitmap_onto(unsigned long *dst, const unsigned long *orig,
-			const unsigned long *relmap, int bits)
+			const unsigned long *relmap, unsigned int bits)
 {
-	int n, m;       	/* same meaning as in above comment */
+	unsigned int n, m;	/* same meaning as in above comment */
 
 	if (dst == orig)	/* following doesn't handle inplace mappings */
 		return;
@@ -1039,22 +1023,22 @@ EXPORT_SYMBOL(bitmap_onto);
  *	@dst: resulting smaller bitmap
  *	@orig: original larger bitmap
  *	@sz: specified size
- *	@bits: number of bits in each of these bitmaps
+ *	@nbits: number of bits in each of these bitmaps
  *
  * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst.
  * Clear all other bits in @dst.  See further the comment and
  * Example [2] for bitmap_onto() for why and how to use this.
  */
 void bitmap_fold(unsigned long *dst, const unsigned long *orig,
-			int sz, int bits)
+			unsigned int sz, unsigned int nbits)
 {
-	int oldbit;
+	unsigned int oldbit;
 
 	if (dst == orig)	/* following doesn't handle inplace mappings */
 		return;
-	bitmap_zero(dst, bits);
+	bitmap_zero(dst, nbits);
 
-	for_each_set_bit(oldbit, orig, bits)
+	for_each_set_bit(oldbit, orig, nbits)
 		set_bit(oldbit % sz, dst);
 }
 EXPORT_SYMBOL(bitmap_fold);
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index 0777c5a45fa04f..f346715e225575 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -3,12 +3,12 @@
  *
  * Copyright (c) 2011, Tom Herbert <therbert@google.com>
  */
-#include <linux/module.h>
 #include <linux/types.h>
-#include <linux/ctype.h>
 #include <linux/kernel.h>
 #include <linux/jiffies.h>
 #include <linux/dynamic_queue_limits.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 
 #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
 #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 2e65d206b01c13..0fe1cbe8770028 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -34,7 +34,6 @@
 #include <linux/rculist.h>
 #include <linux/interrupt.h>
 #include <linux/genalloc.h>
-#include <linux/of_address.h>
 #include <linux/of_device.h>
 
 static inline size_t chunk_size(const struct gen_pool_chunk *chunk)
@@ -415,7 +414,7 @@ bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
 			size_t size)
 {
 	bool found = false;
-	unsigned long end = start + size;
+	unsigned long end = start + size - 1;
 	struct gen_pool_chunk *chunk;
 
 	rcu_read_lock();
diff --git a/lib/halfmd4.c b/lib/halfmd4.c
index 66d0ee8b777652..a8fe6274a13cfe 100644
--- a/lib/halfmd4.c
+++ b/lib/halfmd4.c
@@ -1,4 +1,4 @@
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/cryptohash.h>
 
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 270773b91923ce..7ea09699855d98 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -97,63 +97,79 @@ EXPORT_SYMBOL(bin2hex);
  *
  * example output buffer:
  * 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f  @ABCDEFGHIJKLMNO
+ *
+ * Return:
+ * The amount of bytes placed in the buffer without terminating NUL. If the
+ * output was truncated, then the return value is the number of bytes
+ * (excluding the terminating NUL) which would have been written to the final
+ * string if enough space had been available.
  */
-void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
-			int groupsize, char *linebuf, size_t linebuflen,
-			bool ascii)
+int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize,
+		       char *linebuf, size_t linebuflen, bool ascii)
 {
 	const u8 *ptr = buf;
+	int ngroups;
 	u8 ch;
 	int j, lx = 0;
 	int ascii_column;
+	int ret;
 
 	if (rowsize != 16 && rowsize != 32)
 		rowsize = 16;
 
-	if (!len)
-		goto nil;
 	if (len > rowsize)		/* limit to one line at a time */
 		len = rowsize;
+	if (!is_power_of_2(groupsize) || groupsize > 8)
+		groupsize = 1;
 	if ((len % groupsize) != 0)	/* no mixed size output */
 		groupsize = 1;
 
-	switch (groupsize) {
-	case 8: {
-		const u64 *ptr8 = buf;
-		int ngroups = len / groupsize;
+	ngroups = len / groupsize;
+	ascii_column = rowsize * 2 + rowsize / groupsize + 1;
 
-		for (j = 0; j < ngroups; j++)
-			lx += scnprintf(linebuf + lx, linebuflen - lx,
-					"%s%16.16llx", j ? " " : "",
-					(unsigned long long)*(ptr8 + j));
-		ascii_column = 17 * ngroups + 2;
-		break;
-	}
+	if (!linebuflen)
+		goto overflow1;
 
-	case 4: {
-		const u32 *ptr4 = buf;
-		int ngroups = len / groupsize;
+	if (!len)
+		goto nil;
 
-		for (j = 0; j < ngroups; j++)
-			lx += scnprintf(linebuf + lx, linebuflen - lx,
-					"%s%8.8x", j ? " " : "", *(ptr4 + j));
-		ascii_column = 9 * ngroups + 2;
-		break;
-	}
+	if (groupsize == 8) {
+		const u64 *ptr8 = buf;
 
-	case 2: {
-		const u16 *ptr2 = buf;
-		int ngroups = len / groupsize;
+		for (j = 0; j < ngroups; j++) {
+			ret = snprintf(linebuf + lx, linebuflen - lx,
+				       "%s%16.16llx", j ? " " : "",
+				       (unsigned long long)*(ptr8 + j));
+			if (ret >= linebuflen - lx)
+				goto overflow1;
+			lx += ret;
+		}
+	} else if (groupsize == 4) {
+		const u32 *ptr4 = buf;
 
-		for (j = 0; j < ngroups; j++)
-			lx += scnprintf(linebuf + lx, linebuflen - lx,
-					"%s%4.4x", j ? " " : "", *(ptr2 + j));
-		ascii_column = 5 * ngroups + 2;
-		break;
-	}
+		for (j = 0; j < ngroups; j++) {
+			ret = snprintf(linebuf + lx, linebuflen - lx,
+				       "%s%8.8x", j ? " " : "",
+				       *(ptr4 + j));
+			if (ret >= linebuflen - lx)
+				goto overflow1;
+			lx += ret;
+		}
+	} else if (groupsize == 2) {
+		const u16 *ptr2 = buf;
 
-	default:
-		for (j = 0; (j < len) && (lx + 3) <= linebuflen; j++) {
+		for (j = 0; j < ngroups; j++) {
+			ret = snprintf(linebuf + lx, linebuflen - lx,
+				       "%s%4.4x", j ? " " : "",
+				       *(ptr2 + j));
+			if (ret >= linebuflen - lx)
+				goto overflow1;
+			lx += ret;
+		}
+	} else {
+		for (j = 0; j < len; j++) {
+			if (linebuflen < lx + 3)
+				goto overflow2;
 			ch = ptr[j];
 			linebuf[lx++] = hex_asc_hi(ch);
 			linebuf[lx++] = hex_asc_lo(ch);
@@ -161,21 +177,28 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 		}
 		if (j)
 			lx--;
-
-		ascii_column = 3 * rowsize + 2;
-		break;
 	}
 	if (!ascii)
 		goto nil;
 
-	while (lx < (linebuflen - 1) && lx < (ascii_column - 1))
+	while (lx < ascii_column) {
+		if (linebuflen < lx + 2)
+			goto overflow2;
 		linebuf[lx++] = ' ';
-	for (j = 0; (j < len) && (lx + 2) < linebuflen; j++) {
+	}
+	for (j = 0; j < len; j++) {
+		if (linebuflen < lx + 2)
+			goto overflow2;
 		ch = ptr[j];
 		linebuf[lx++] = (isascii(ch) && isprint(ch)) ? ch : '.';
 	}
 nil:
+	linebuf[lx] = '\0';
+	return lx;
+overflow2:
 	linebuf[lx++] = '\0';
+overflow1:
+	return ascii ? ascii_column + len : (groupsize * 2 + 1) * ngroups - 1;
 }
 EXPORT_SYMBOL(hex_dump_to_buffer);
 
diff --git a/lib/idr.c b/lib/idr.c
index e654aebd5f807d..5335c43adf46af 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -30,7 +30,6 @@
 #include <linux/idr.h>
 #include <linux/spinlock.h>
 #include <linux/percpu.h>
-#include <linux/hardirq.h>
 
 #define MAX_IDR_SHIFT		(sizeof(int) * 8 - 1)
 #define MAX_IDR_BIT		(1U << MAX_IDR_SHIFT)
diff --git a/lib/interval_tree.c b/lib/interval_tree.c
index f367f9ad544c39..c85f6600a5f8de 100644
--- a/lib/interval_tree.c
+++ b/lib/interval_tree.c
@@ -1,7 +1,7 @@
-#include <linux/init.h>
 #include <linux/interval_tree.h>
 #include <linux/interval_tree_generic.h>
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 
 #define START(node) ((node)->start)
 #define LAST(node)  ((node)->last)
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 9ebf9e20de53db..f6c2c1e7779c9c 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -20,7 +20,6 @@
 #include <linux/export.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
-#include <linux/user_namespace.h>
 #include <linux/socket.h>
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
diff --git a/lib/lcm.c b/lib/lcm.c
index 51cc6b13cd52d3..e97dbd51e7569f 100644
--- a/lib/lcm.c
+++ b/lib/lcm.c
@@ -1,4 +1,4 @@
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <linux/gcd.h>
 #include <linux/export.h>
 #include <linux/lcm.h>
diff --git a/lib/list_sort.c b/lib/list_sort.c
index 12bcba1c8612bc..b29015102698b3 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -2,9 +2,11 @@
 #define pr_fmt(fmt) "list_sort_test: " fmt
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <linux/string.h>
 #include <linux/list_sort.h>
-#include <linux/slab.h>
 #include <linux/list.h>
 
 #define MAX_LIST_LENGTH_BITS 20
@@ -146,6 +148,7 @@ EXPORT_SYMBOL(list_sort);
 
 #ifdef CONFIG_TEST_LIST_SORT
 
+#include <linux/slab.h>
 #include <linux/random.h>
 
 /*
diff --git a/lib/llist.c b/lib/llist.c
index f76196d0740976..0b0e9779d6753b 100644
--- a/lib/llist.c
+++ b/lib/llist.c
@@ -24,7 +24,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/export.h>
-#include <linux/interrupt.h>
 #include <linux/llist.h>
 
 
diff --git a/lib/md5.c b/lib/md5.c
index 958a3c15923c8a..bb0cd01d356d42 100644
--- a/lib/md5.c
+++ b/lib/md5.c
@@ -1,4 +1,4 @@
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/cryptohash.h>
 
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 9c3e85ff0a6c56..76a1b59523ab05 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/jiffies.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/string.h>
 #include <linux/types.h>
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 93d145e5539c2e..f75715131f2094 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -19,13 +19,10 @@
 #include <linux/bug.h>
 #include <linux/err.h>
 #include <linux/export.h>
-#include <linux/hardirq.h>
-#include <linux/idr.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/percpu_ida.h>
diff --git a/lib/plist.c b/lib/plist.c
index d408e774b74624..3a30c53db06158 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -25,7 +25,6 @@
 
 #include <linux/bug.h>
 #include <linux/plist.h>
-#include <linux/spinlock.h>
 
 #ifdef CONFIG_DEBUG_PI_LIST
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3291a8e37490ec..3d2aa27b845b53 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -33,7 +33,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/rcupdate.h>
-#include <linux/hardirq.h>		/* in_interrupt() */
+#include <linux/preempt_mask.h>		/* in_interrupt() */
 
 
 /*
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 7d0e5cd7b570c3..dbef2314901ed3 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -89,10 +89,10 @@ void (*raid6_datap_recov)(int, size_t, int, void **);
 EXPORT_SYMBOL_GPL(raid6_datap_recov);
 
 const struct raid6_recov_calls *const raid6_recov_algos[] = {
-#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
 #ifdef CONFIG_AS_AVX2
 	&raid6_recov_avx2,
 #endif
+#ifdef CONFIG_AS_SSSE3
 	&raid6_recov_ssse3,
 #endif
 	&raid6_recov_intx1,
diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c
index e1eea433a49395..53fe3d7bdfb3b4 100644
--- a/lib/raid6/recov_avx2.c
+++ b/lib/raid6/recov_avx2.c
@@ -8,7 +8,7 @@
  * of the License.
  */
 
-#if CONFIG_AS_AVX2
+#ifdef CONFIG_AS_AVX2
 
 #include <linux/raid/pq.h>
 #include "x86.h"
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
index a9168328f03b3d..cda33e56a5e346 100644
--- a/lib/raid6/recov_ssse3.c
+++ b/lib/raid6/recov_ssse3.c
@@ -7,6 +7,8 @@
  * of the License.
  */
 
+#ifdef CONFIG_AS_SSSE3
+
 #include <linux/raid/pq.h>
 #include "x86.h"
 
@@ -330,3 +332,7 @@ const struct raid6_recov_calls raid6_recov_ssse3 = {
 #endif
 	.priority = 1,
 };
+
+#else
+#warning "your version of binutils lacks SSSE3 support"
+#endif
diff --git a/lib/show_mem.c b/lib/show_mem.c
index 7de89f4a36cfa5..adc98e1825ba0d 100644
--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/mm.h>
-#include <linux/nmi.h>
 #include <linux/quicklist.h>
 #include <linux/cma.h>
 
diff --git a/lib/sort.c b/lib/sort.c
index 926d00429ed239..43c9fe73ae2e2f 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -4,10 +4,9 @@
  * Jan 23 2005  Matt Mackall <mpm@selenic.com>
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/export.h>
 #include <linux/sort.h>
-#include <linux/slab.h>
 
 static void u32_swap(void *a, void *b, int size)
 {
@@ -85,6 +84,7 @@ void sort(void *base, size_t num, size_t size,
 EXPORT_SYMBOL(sort);
 
 #if 0
+#include <linux/slab.h>
 /* a simple boot-time regression test */
 
 int cmpint(const void *a, const void *b)
diff --git a/lib/stmp_device.c b/lib/stmp_device.c
index 8ac9bcc4289a65..a904656f4fd7c5 100644
--- a/lib/stmp_device.c
+++ b/lib/stmp_device.c
@@ -15,7 +15,8 @@
 #include <linux/io.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 #include <linux/stmp_device.h>
 
 #define STMP_MODULE_CLKGATE	(1 << 30)
diff --git a/lib/string.c b/lib/string.c
index 10063300b83009..3206d017829696 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -58,14 +58,6 @@ int strncasecmp(const char *s1, const char *s2, size_t len)
 }
 EXPORT_SYMBOL(strncasecmp);
 #endif
-#ifndef __HAVE_ARCH_STRNICMP
-#undef strnicmp
-int strnicmp(const char *s1, const char *s2, size_t len)
-{
-	return strncasecmp(s1, s2, len);
-}
-EXPORT_SYMBOL(strnicmp);
-#endif
 
 #ifndef __HAVE_ARCH_STRCASECMP
 int strcasecmp(const char *s1, const char *s2)
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 58b78ba57439c7..8f8c4417f22865 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -20,19 +20,18 @@
  * @len:	length of buffer
  *
  * This function returns a string formatted to 3 significant figures
- * giving the size in the required units.  Returns 0 on success or
- * error on failure.  @buf is always zero terminated.
+ * giving the size in the required units.  @buf should have room for
+ * at least 9 bytes and will always be zero terminated.
  *
  */
-int string_get_size(u64 size, const enum string_size_units units,
-		    char *buf, int len)
+void string_get_size(u64 size, const enum string_size_units units,
+		     char *buf, int len)
 {
 	static const char *const units_10[] = {
-		"B", "kB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB", NULL
+		"B", "kB", "MB", "GB", "TB", "PB", "EB"
 	};
 	static const char *const units_2[] = {
-		"B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB", "ZiB", "YiB",
-		NULL
+		"B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB"
 	};
 	static const char *const *const units_str[] = {
 		[STRING_UNITS_10] = units_10,
@@ -43,13 +42,13 @@ int string_get_size(u64 size, const enum string_size_units units,
 		[STRING_UNITS_2] = 1024,
 	};
 	int i, j;
-	u64 remainder = 0, sf_cap;
+	u32 remainder = 0, sf_cap;
 	char tmp[8];
 
 	tmp[0] = '\0';
 	i = 0;
 	if (size >= divisor[units]) {
-		while (size >= divisor[units] && units_str[units][i]) {
+		while (size >= divisor[units]) {
 			remainder = do_div(size, divisor[units]);
 			i++;
 		}
@@ -60,17 +59,14 @@ int string_get_size(u64 size, const enum string_size_units units,
 
 		if (j) {
 			remainder *= 1000;
-			do_div(remainder, divisor[units]);
-			snprintf(tmp, sizeof(tmp), ".%03lld",
-				 (unsigned long long)remainder);
+			remainder /= divisor[units];
+			snprintf(tmp, sizeof(tmp), ".%03u", remainder);
 			tmp[j+1] = '\0';
 		}
 	}
 
-	snprintf(buf, len, "%lld%s %s", (unsigned long long)size,
+	snprintf(buf, len, "%u%s %s", (u32)size,
 		 tmp, units_str[units][i]);
-
-	return 0;
 }
 EXPORT_SYMBOL(string_get_size);
 
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index bb2b201d6ad039..e0af6ff73d146c 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -1,4 +1,5 @@
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/lib/test-hexdump.c b/lib/test-hexdump.c
new file mode 100644
index 00000000000000..daf29a390a89d1
--- /dev/null
+++ b/lib/test-hexdump.c
@@ -0,0 +1,180 @@
+/*
+ * Test cases for lib/hexdump.c module.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/string.h>
+
+static const unsigned char data_b[] = {
+	'\xbe', '\x32', '\xdb', '\x7b', '\x0a', '\x18', '\x93', '\xb2',	/* 00 - 07 */
+	'\x70', '\xba', '\xc4', '\x24', '\x7d', '\x83', '\x34', '\x9b',	/* 08 - 0f */
+	'\xa6', '\x9c', '\x31', '\xad', '\x9c', '\x0f', '\xac', '\xe9',	/* 10 - 17 */
+	'\x4c', '\xd1', '\x19', '\x99', '\x43', '\xb1', '\xaf', '\x0c',	/* 18 - 1f */
+};
+
+static const unsigned char data_a[] = ".2.{....p..$}.4...1.....L...C...";
+
+static const char *test_data_1_le[] __initconst = {
+	"be", "32", "db", "7b", "0a", "18", "93", "b2",
+	"70", "ba", "c4", "24", "7d", "83", "34", "9b",
+	"a6", "9c", "31", "ad", "9c", "0f", "ac", "e9",
+	"4c", "d1", "19", "99", "43", "b1", "af", "0c",
+};
+
+static const char *test_data_2_le[] __initconst = {
+	"32be", "7bdb", "180a", "b293",
+	"ba70", "24c4", "837d", "9b34",
+	"9ca6", "ad31", "0f9c", "e9ac",
+	"d14c", "9919", "b143", "0caf",
+};
+
+static const char *test_data_4_le[] __initconst = {
+	"7bdb32be", "b293180a", "24c4ba70", "9b34837d",
+	"ad319ca6", "e9ac0f9c", "9919d14c", "0cafb143",
+};
+
+static const char *test_data_8_le[] __initconst = {
+	"b293180a7bdb32be", "9b34837d24c4ba70",
+	"e9ac0f9cad319ca6", "0cafb1439919d14c",
+};
+
+static void __init test_hexdump(size_t len, int rowsize, int groupsize,
+				bool ascii)
+{
+	char test[32 * 3 + 2 + 32 + 1];
+	char real[32 * 3 + 2 + 32 + 1];
+	char *p;
+	const char **result;
+	size_t l = len;
+	int gs = groupsize, rs = rowsize;
+	unsigned int i;
+
+	hex_dump_to_buffer(data_b, l, rs, gs, real, sizeof(real), ascii);
+
+	if (rs != 16 && rs != 32)
+		rs = 16;
+
+	if (l > rs)
+		l = rs;
+
+	if (!is_power_of_2(gs) || gs > 8 || (len % gs != 0))
+		gs = 1;
+
+	if (gs == 8)
+		result = test_data_8_le;
+	else if (gs == 4)
+		result = test_data_4_le;
+	else if (gs == 2)
+		result = test_data_2_le;
+	else
+		result = test_data_1_le;
+
+	memset(test, ' ', sizeof(test));
+
+	/* hex dump */
+	p = test;
+	for (i = 0; i < l / gs; i++) {
+		const char *q = *result++;
+		size_t amount = strlen(q);
+
+		strncpy(p, q, amount);
+		p += amount + 1;
+	}
+	if (i)
+		p--;
+
+	/* ASCII part */
+	if (ascii) {
+		p = test + rs * 2 + rs / gs + 1;
+		strncpy(p, data_a, l);
+		p += l;
+	}
+
+	*p = '\0';
+
+	if (strcmp(test, real)) {
+		pr_err("Len: %zu row: %d group: %d\n", len, rowsize, groupsize);
+		pr_err("Result: '%s'\n", real);
+		pr_err("Expect: '%s'\n", test);
+	}
+}
+
+static void __init test_hexdump_set(int rowsize, bool ascii)
+{
+	size_t d = min_t(size_t, sizeof(data_b), rowsize);
+	size_t len = get_random_int() % d + 1;
+
+	test_hexdump(len, rowsize, 4, ascii);
+	test_hexdump(len, rowsize, 2, ascii);
+	test_hexdump(len, rowsize, 8, ascii);
+	test_hexdump(len, rowsize, 1, ascii);
+}
+
+static void __init test_hexdump_overflow(bool ascii)
+{
+	char buf[56];
+	const char *t = test_data_1_le[0];
+	size_t l = get_random_int() % sizeof(buf);
+	bool a;
+	int e, r;
+
+	memset(buf, ' ', sizeof(buf));
+
+	r = hex_dump_to_buffer(data_b, 1, 16, 1, buf, l, ascii);
+
+	if (ascii)
+		e = 50;
+	else
+		e = 2;
+	buf[e + 2] = '\0';
+
+	if (!l) {
+		a = r == e && buf[0] == ' ';
+	} else if (l < 3) {
+		a = r == e && buf[0] == '\0';
+	} else if (l < 4) {
+		a = r == e && !strcmp(buf, t);
+	} else if (ascii) {
+		if (l < 51)
+			a = r == e && buf[l - 1] == '\0' && buf[l - 2] == ' ';
+		else
+			a = r == e && buf[50] == '\0' && buf[49] == '.';
+	} else {
+		a = r == e && buf[e] == '\0';
+	}
+
+	if (!a) {
+		pr_err("Len: %zu rc: %u strlen: %zu\n", l, r, strlen(buf));
+		pr_err("Result: '%s'\n", buf);
+	}
+}
+
+static int __init test_hexdump_init(void)
+{
+	unsigned int i;
+	int rowsize;
+
+	pr_info("Running tests...\n");
+
+	rowsize = (get_random_int() % 2 + 1) * 16;
+	for (i = 0; i < 16; i++)
+		test_hexdump_set(rowsize, false);
+
+	rowsize = (get_random_int() % 2 + 1) * 16;
+	for (i = 0; i < 16; i++)
+		test_hexdump_set(rowsize, true);
+
+	for (i = 0; i < 16; i++)
+		test_hexdump_overflow(false);
+
+	for (i = 0; i < 16; i++)
+		test_hexdump_overflow(true);
+
+	return -EINVAL;
+}
+module_init(test_hexdump_init);
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index ec337f64f52dda..602d2081e713c8 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -114,8 +114,9 @@ int skip_atoi(const char **s)
 {
 	int i = 0;
 
-	while (isdigit(**s))
+	do {
 		i = i*10 + *((*s)++) - '0';
+	} while (isdigit(**s));
 
 	return i;
 }
@@ -1604,8 +1605,7 @@ int format_decode(const char *fmt, struct printf_spec *spec)
 
 	case 'p':
 		spec->type = FORMAT_TYPE_PTR;
-		return fmt - start;
-		/* skip alnum */
+		return ++fmt - start;
 
 	case '%':
 		spec->type = FORMAT_TYPE_PERCENT_CHAR;
@@ -1728,7 +1728,7 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 
 	/* Reject out-of-range values early.  Large positive sizes are
 	   used for unknown buffer sizes. */
-	if (WARN_ON_ONCE((int) size < 0))
+	if (WARN_ON_ONCE(size > INT_MAX))
 		return 0;
 
 	str = buf;
@@ -1794,7 +1794,7 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 			break;
 
 		case FORMAT_TYPE_PTR:
-			str = pointer(fmt+1, str, end, va_arg(args, void *),
+			str = pointer(fmt, str, end, va_arg(args, void *),
 				      spec);
 			while (isalnum(*fmt))
 				fmt++;
@@ -2232,7 +2232,7 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
 		}
 
 		case FORMAT_TYPE_PTR:
-			str = pointer(fmt+1, str, end, get_arg(void *), spec);
+			str = pointer(fmt, str, end, get_arg(void *), spec);
 			while (isalnum(*fmt))
 				fmt++;
 			break;
diff --git a/mm/Kconfig b/mm/Kconfig
index 4395b12869c832..de5239c152f9fb 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -602,6 +602,16 @@ config PGTABLE_MAPPING
 	  You can check speed with zsmalloc benchmark:
 	  https://github.com/spartacus06/zsmapbench
 
+config ZSMALLOC_STAT
+	bool "Export zsmalloc statistics"
+	depends on ZSMALLOC
+	select DEBUG_FS
+	help
+	  This option enables code in the zsmalloc to collect various
+	  statistics about whats happening in zsmalloc and exports that
+	  information to userspace via debugfs.
+	  If unsure, say N.
+
 config GENERIC_EARLY_IOREMAP
 	bool
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0ae0df55000bb0..7690ec77c72297 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -14,19 +14,10 @@
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-struct backing_dev_info default_backing_dev_info = {
-	.name		= "default",
-	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
-	.state		= 0,
-	.capabilities	= BDI_CAP_MAP_COPY,
-};
-EXPORT_SYMBOL_GPL(default_backing_dev_info);
-
 struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
-EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
 
@@ -40,17 +31,6 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
-static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
-{
-	if (wb1 < wb2) {
-		spin_lock(&wb1->list_lock);
-		spin_lock_nested(&wb2->list_lock, 1);
-	} else {
-		spin_lock(&wb2->list_lock);
-		spin_lock_nested(&wb1->list_lock, 1);
-	}
-}
-
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -264,9 +244,6 @@ static int __init default_bdi_init(void)
 	if (!bdi_wq)
 		return -ENOMEM;
 
-	err = bdi_init(&default_backing_dev_info);
-	if (!err)
-		bdi_register(&default_backing_dev_info, NULL, "default");
 	err = bdi_init(&noop_backing_dev_info);
 
 	return err;
@@ -355,19 +332,19 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
-	if (!bdi_cap_writeback_dirty(bdi))
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	if (!test_and_clear_bit(BDI_registered, &bdi->state)) {
+		spin_unlock_bh(&bdi->wb_lock);
 		return;
+	}
+	spin_unlock_bh(&bdi->wb_lock);
 
 	/*
 	 * Make sure nobody finds us on the bdi_list anymore
 	 */
 	bdi_remove_from_list(bdi);
 
-	/* Make sure nobody queues further work */
-	spin_lock_bh(&bdi->wb_lock);
-	clear_bit(BDI_registered, &bdi->state);
-	spin_unlock_bh(&bdi->wb_lock);
-
 	/*
 	 * Drain work list and shutdown the delayed_work.  At this point,
 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
@@ -375,37 +352,22 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 */
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 	flush_delayed_work(&bdi->wb.dwork);
-	WARN_ON(!list_empty(&bdi->work_list));
-	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 }
 
 /*
- * This bdi is going away now, make sure that no super_blocks point to it
+ * Called when the device behind @bdi has been removed or ejected.
+ *
+ * We can't really do much here except for reducing the dirty ratio at
+ * the moment.  In the future we should be able to set a flag so that
+ * the filesystem can handle errors at mark_inode_dirty time instead
+ * of only at writeback time.
  */
-static void bdi_prune_sb(struct backing_dev_info *bdi)
-{
-	struct super_block *sb;
-
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_bdi == bdi)
-			sb->s_bdi = &default_backing_dev_info;
-	}
-	spin_unlock(&sb_lock);
-}
-
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	if (bdi->dev) {
-		bdi_set_min_ratio(bdi, 0);
-		trace_writeback_bdi_unregister(bdi);
-		bdi_prune_sb(bdi);
+	if (WARN_ON_ONCE(!bdi->dev))
+		return;
 
-		bdi_wb_shutdown(bdi);
-		bdi_debug_unregister(bdi);
-		device_unregister(bdi->dev);
-		bdi->dev = NULL;
-	}
+	bdi_set_min_ratio(bdi, 0);
 }
 EXPORT_SYMBOL(bdi_unregister);
 
@@ -474,37 +436,19 @@ void bdi_destroy(struct backing_dev_info *bdi)
 {
 	int i;
 
-	/*
-	 * Splice our entries to the default_backing_dev_info.  This
-	 * condition shouldn't happen.  @wb must be empty at this point and
-	 * dirty inodes on it might cause other issues.  This workaround is
-	 * added by ce5f8e779519 ("writeback: splice dirty inode entries to
-	 * default bdi on bdi_destroy()") without root-causing the issue.
-	 *
-	 * http://lkml.kernel.org/g/1253038617-30204-11-git-send-email-jens.axboe@oracle.com
-	 * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350
-	 *
-	 * We should probably add WARN_ON() to find out whether it still
-	 * happens and track it down if so.
-	 */
-	if (bdi_has_dirty_io(bdi)) {
-		struct bdi_writeback *dst = &default_backing_dev_info.wb;
-
-		bdi_lock_two(&bdi->wb, dst);
-		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
-		list_splice(&bdi->wb.b_io, &dst->b_io);
-		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&bdi->wb.list_lock);
-		spin_unlock(&dst->list_lock);
-	}
-
-	bdi_unregister(bdi);
+	bdi_wb_shutdown(bdi);
 
+	WARN_ON(!list_empty(&bdi->work_list));
 	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 
+	if (bdi->dev) {
+		bdi_debug_unregister(bdi);
+		device_unregister(bdi->dev);
+		bdi->dev = NULL;
+	}
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
-
 	fprop_local_destroy_percpu(&bdi->completions);
 }
 EXPORT_SYMBOL(bdi_destroy);
@@ -513,13 +457,12 @@ EXPORT_SYMBOL(bdi_destroy);
  * For use from filesystems to quickly init and register a bdi associated
  * with dirty writeback
  */
-int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
-			   unsigned int cap)
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
 {
 	int err;
 
 	bdi->name = name;
-	bdi->capabilities = cap;
+	bdi->capabilities = 0;
 	err = bdi_init(bdi);
 	if (err)
 		return err;
diff --git a/mm/compaction.c b/mm/compaction.c
index b68736c8a1ce0d..d50d6de6f1b68a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -490,6 +490,13 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* If a page was split, advance to the end of it */
 		if (isolated) {
+			cc->nr_freepages += isolated;
+			if (!strict &&
+				cc->nr_migratepages <= cc->nr_freepages) {
+				blockpfn += isolated;
+				break;
+			}
+
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
 			continue;
@@ -899,7 +906,6 @@ static void isolate_freepages(struct compact_control *cc)
 	unsigned long isolate_start_pfn; /* exact pfn we start at */
 	unsigned long block_end_pfn;	/* end of current pageblock */
 	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
-	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
 	/*
@@ -924,11 +930,11 @@ static void isolate_freepages(struct compact_control *cc)
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
+	for (; block_start_pfn >= low_pfn &&
+			cc->nr_migratepages > cc->nr_freepages;
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
-		unsigned long isolated;
 
 		/*
 		 * This can iterate a massively long zone without finding any
@@ -953,9 +959,8 @@ static void isolate_freepages(struct compact_control *cc)
 			continue;
 
 		/* Found a block suitable for isolating free pages from. */
-		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+		isolate_freepages_block(cc, &isolate_start_pfn,
 					block_end_pfn, freelist, false);
-		nr_freepages += isolated;
 
 		/*
 		 * Remember where the free scanner should restart next time,
@@ -987,8 +992,6 @@ static void isolate_freepages(struct compact_control *cc)
 	 */
 	if (block_start_pfn < low_pfn)
 		cc->free_pfn = cc->migrate_pfn;
-
-	cc->nr_freepages = nr_freepages;
 }
 
 /*
@@ -1100,8 +1103,10 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
 								isolate_mode);
 
-		if (!low_pfn || cc->contended)
+		if (!low_pfn || cc->contended) {
+			acct_isolated(zone, cc);
 			return ISOLATE_ABORT;
+		}
 
 		/*
 		 * Either we isolated something and proceed with migration. Or
@@ -1173,7 +1178,7 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc,
 			return COMPACT_PARTIAL;
 
 		/* Job done if allocation would set block type */
-		if (cc->order >= pageblock_order && area->nr_free)
+		if (order >= pageblock_order && area->nr_free)
 			return COMPACT_PARTIAL;
 	}
 
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 2ad7adf4f0a459..fac23ecf8d7229 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -73,7 +73,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 	else
 		endbyte--;		/* inclusive */
 
-	bdi = mapping->backing_dev_info;
+	bdi = inode_to_bdi(mapping->host);
 
 	switch (advice) {
 	case POSIX_FADV_NORMAL:
@@ -113,7 +113,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 	case POSIX_FADV_NOREUSE:
 		break;
 	case POSIX_FADV_DONTNEED:
-		if (!bdi_write_congested(mapping->backing_dev_info))
+		if (!bdi_write_congested(bdi))
 			__filemap_fdatawrite_range(mapping, offset, endbyte,
 						   WB_SYNC_NONE);
 
diff --git a/mm/filemap.c b/mm/filemap.c
index bf7a2714270413..d9f5336552d7b1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -211,7 +211,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
 	 */
 	if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
 		dec_zone_page_state(page, NR_FILE_DIRTY);
-		dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+		dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE);
 	}
 }
 
@@ -2564,7 +2564,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	size_t		count = iov_iter_count(from);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
 		goto out;
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 70c09da1a4198c..c175f9f25210a6 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/backing-dev.h>
 #include <linux/pagemap.h>
 #include <linux/export.h>
 #include <linux/uio.h>
@@ -409,7 +410,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
 	count = len;
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
 	if (ret)
diff --git a/mm/gup.c b/mm/gup.c
index c2da1163986aa5..51bf0b06ca7bd7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -64,7 +64,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		migration_entry_wait(mm, pmd, address);
 		goto retry;
 	}
-	if ((flags & FOLL_NUMA) && pte_numa(pte))
+	if ((flags & FOLL_NUMA) && pte_protnone(pte))
 		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte)) {
 		pte_unmap_unlock(ptep, ptl);
@@ -184,7 +184,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 			return page;
 		return no_page_table(vma, flags);
 	}
-	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
 		return no_page_table(vma, flags);
 	if (pmd_trans_huge(*pmd)) {
 		if (flags & FOLL_SPLIT) {
@@ -906,10 +906,10 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 		/*
 		 * Similar to the PMD case below, NUMA hinting must take slow
-		 * path
+		 * path using the pte_protnone check.
 		 */
 		if (!pte_present(pte) || pte_special(pte) ||
-			pte_numa(pte) || (write && !pte_write(pte)))
+			pte_protnone(pte) || (write && !pte_write(pte)))
 			goto pte_unmap;
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
@@ -1104,7 +1104,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 			 * slowpath for accounting purposes and so that they
 			 * can be serialised against THP migration.
 			 */
-			if (pmd_numa(pmd))
+			if (pmd_protnone(pmd))
 				return 0;
 
 			if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cb7be110cad33a..fc00c8cb5a82ee 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1211,7 +1211,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 		return ERR_PTR(-EFAULT);
 
 	/* Full NUMA hinting faults to serialise migration in fault paths */
-	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
 		goto out;
 
 	page = pmd_page(*pmd);
@@ -1262,6 +1262,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	bool migrated = false;
 	int flags = 0;
 
+	/* A PROT_NONE fault should not end up here */
+	BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
+
 	ptl = pmd_lock(mm, pmdp);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
@@ -1272,8 +1275,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * check_same as the page may no longer be mapped.
 	 */
 	if (unlikely(pmd_trans_migrating(*pmdp))) {
+		page = pmd_page(*pmdp);
 		spin_unlock(ptl);
-		wait_migrate_huge_page(vma->anon_vma, pmdp);
+		wait_on_page_locked(page);
 		goto out;
 	}
 
@@ -1341,7 +1345,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/*
 	 * Migrate the THP to the requested node, returns with page unlocked
-	 * and pmd_numa cleared.
+	 * and access rights restored.
 	 */
 	spin_unlock(ptl);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
@@ -1354,9 +1358,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	goto out;
 clear_pmdnuma:
 	BUG_ON(!PageLocked(page));
-	pmd = pmd_mknonnuma(pmd);
+	pmd = pmd_modify(pmd, vma->vm_page_prot);
 	set_pmd_at(mm, haddr, pmdp, pmd);
-	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
 	unlock_page(page);
 out_unlock:
@@ -1479,29 +1482,24 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 
 	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pmd_t entry;
-		ret = 1;
-		if (!prot_numa) {
+
+		/*
+		 * Avoid trapping faults against the zero page. The read-only
+		 * data is likely to be read-cached on the local CPU and
+		 * local/remote hits to the zero page are not interesting.
+		 */
+		if (prot_numa && is_huge_zero_pmd(*pmd)) {
+			spin_unlock(ptl);
+			return 0;
+		}
+
+		if (!prot_numa || !pmd_protnone(*pmd)) {
+			ret = 1;
 			entry = pmdp_get_and_clear_notify(mm, addr, pmd);
-			if (pmd_numa(entry))
-				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
 			set_pmd_at(mm, addr, pmd, entry);
 			BUG_ON(pmd_write(entry));
-		} else {
-			struct page *page = pmd_page(*pmd);
-
-			/*
-			 * Do not trap faults against the zero page. The
-			 * read-only data is likely to be read-cached on the
-			 * local CPU cache and it is less useful to know about
-			 * local vs remote hits on the zero page.
-			 */
-			if (!is_huge_zero_page(page) &&
-			    !pmd_numa(*pmd)) {
-				pmdp_set_numa(mm, addr, pmd);
-				ret = HPAGE_PMD_NR;
-			}
 		}
 		spin_unlock(ptl);
 	}
@@ -1766,9 +1764,9 @@ static int __split_huge_page_map(struct page *page,
 			pte_t *pte, entry;
 			BUG_ON(PageCompound(page+i));
 			/*
-			 * Note that pmd_numa is not transferred deliberately
-			 * to avoid any possibility that pte_numa leaks to
-			 * a PROT_NONE VMA by accident.
+			 * Note that NUMA hinting access restrictions are not
+			 * transferred to avoid any possibility of altering
+			 * permissions across VMAs.
 			 */
 			entry = mk_pte(page + i, vma->vm_page_prot);
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
diff --git a/mm/internal.h b/mm/internal.h
index c4d6c9b43491d5..a96da5b0029dc4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -351,8 +351,10 @@ extern int mminit_loglevel;
 #define mminit_dprintk(level, prefix, fmt, arg...) \
 do { \
 	if (level < mminit_loglevel) { \
-		printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \
-		printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \
+		if (level <= MMINIT_WARNING) \
+			printk(KERN_WARNING "mminit::" prefix " " fmt, ##arg); \
+		else \
+			printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
 	} \
 } while (0)
 
diff --git a/mm/list_lru.c b/mm/list_lru.c
index f1a0db1941735e..909eca2c820e4a 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -9,18 +9,100 @@
 #include <linux/mm.h>
 #include <linux/list_lru.h>
 #include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/memcontrol.h>
+
+#ifdef CONFIG_MEMCG_KMEM
+static LIST_HEAD(list_lrus);
+static DEFINE_MUTEX(list_lrus_mutex);
+
+static void list_lru_register(struct list_lru *lru)
+{
+	mutex_lock(&list_lrus_mutex);
+	list_add(&lru->list, &list_lrus);
+	mutex_unlock(&list_lrus_mutex);
+}
+
+static void list_lru_unregister(struct list_lru *lru)
+{
+	mutex_lock(&list_lrus_mutex);
+	list_del(&lru->list);
+	mutex_unlock(&list_lrus_mutex);
+}
+#else
+static void list_lru_register(struct list_lru *lru)
+{
+}
+
+static void list_lru_unregister(struct list_lru *lru)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool list_lru_memcg_aware(struct list_lru *lru)
+{
+	return !!lru->node[0].memcg_lrus;
+}
+
+static inline struct list_lru_one *
+list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
+{
+	/*
+	 * The lock protects the array of per cgroup lists from relocation
+	 * (see memcg_update_list_lru_node).
+	 */
+	lockdep_assert_held(&nlru->lock);
+	if (nlru->memcg_lrus && idx >= 0)
+		return nlru->memcg_lrus->lru[idx];
+
+	return &nlru->lru;
+}
+
+static inline struct list_lru_one *
+list_lru_from_kmem(struct list_lru_node *nlru, void *ptr)
+{
+	struct mem_cgroup *memcg;
+
+	if (!nlru->memcg_lrus)
+		return &nlru->lru;
+
+	memcg = mem_cgroup_from_kmem(ptr);
+	if (!memcg)
+		return &nlru->lru;
+
+	return list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg));
+}
+#else
+static inline bool list_lru_memcg_aware(struct list_lru *lru)
+{
+	return false;
+}
+
+static inline struct list_lru_one *
+list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
+{
+	return &nlru->lru;
+}
+
+static inline struct list_lru_one *
+list_lru_from_kmem(struct list_lru_node *nlru, void *ptr)
+{
+	return &nlru->lru;
+}
+#endif /* CONFIG_MEMCG_KMEM */
 
 bool list_lru_add(struct list_lru *lru, struct list_head *item)
 {
 	int nid = page_to_nid(virt_to_page(item));
 	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
-	WARN_ON_ONCE(nlru->nr_items < 0);
+	l = list_lru_from_kmem(nlru, item);
 	if (list_empty(item)) {
-		list_add_tail(item, &nlru->list);
-		if (nlru->nr_items++ == 0)
-			node_set(nid, lru->active_nodes);
+		list_add_tail(item, &l->list);
+		l->nr_items++;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
@@ -33,13 +115,13 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 {
 	int nid = page_to_nid(virt_to_page(item));
 	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
+	l = list_lru_from_kmem(nlru, item);
 	if (!list_empty(item)) {
 		list_del_init(item);
-		if (--nlru->nr_items == 0)
-			node_clear(nid, lru->active_nodes);
-		WARN_ON_ONCE(nlru->nr_items < 0);
+		l->nr_items--;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
@@ -48,33 +130,72 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 }
 EXPORT_SYMBOL_GPL(list_lru_del);
 
-unsigned long
-list_lru_count_node(struct list_lru *lru, int nid)
+void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
+{
+	list_del_init(item);
+	list->nr_items--;
+}
+EXPORT_SYMBOL_GPL(list_lru_isolate);
+
+void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
+			   struct list_head *head)
+{
+	list_move(item, head);
+	list->nr_items--;
+}
+EXPORT_SYMBOL_GPL(list_lru_isolate_move);
+
+static unsigned long __list_lru_count_one(struct list_lru *lru,
+					  int nid, int memcg_idx)
 {
-	unsigned long count = 0;
 	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
+	unsigned long count;
 
 	spin_lock(&nlru->lock);
-	WARN_ON_ONCE(nlru->nr_items < 0);
-	count += nlru->nr_items;
+	l = list_lru_from_memcg_idx(nlru, memcg_idx);
+	count = l->nr_items;
 	spin_unlock(&nlru->lock);
 
 	return count;
 }
+
+unsigned long list_lru_count_one(struct list_lru *lru,
+				 int nid, struct mem_cgroup *memcg)
+{
+	return __list_lru_count_one(lru, nid, memcg_cache_id(memcg));
+}
+EXPORT_SYMBOL_GPL(list_lru_count_one);
+
+unsigned long list_lru_count_node(struct list_lru *lru, int nid)
+{
+	long count = 0;
+	int memcg_idx;
+
+	count += __list_lru_count_one(lru, nid, -1);
+	if (list_lru_memcg_aware(lru)) {
+		for_each_memcg_cache_index(memcg_idx)
+			count += __list_lru_count_one(lru, nid, memcg_idx);
+	}
+	return count;
+}
 EXPORT_SYMBOL_GPL(list_lru_count_node);
 
-unsigned long
-list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
-		   void *cb_arg, unsigned long *nr_to_walk)
+static unsigned long
+__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx,
+		    list_lru_walk_cb isolate, void *cb_arg,
+		    unsigned long *nr_to_walk)
 {
 
-	struct list_lru_node	*nlru = &lru->node[nid];
+	struct list_lru_node *nlru = &lru->node[nid];
+	struct list_lru_one *l;
 	struct list_head *item, *n;
 	unsigned long isolated = 0;
 
 	spin_lock(&nlru->lock);
+	l = list_lru_from_memcg_idx(nlru, memcg_idx);
 restart:
-	list_for_each_safe(item, n, &nlru->list) {
+	list_for_each_safe(item, n, &l->list) {
 		enum lru_status ret;
 
 		/*
@@ -85,14 +206,11 @@ list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
 			break;
 		--*nr_to_walk;
 
-		ret = isolate(item, &nlru->lock, cb_arg);
+		ret = isolate(item, l, &nlru->lock, cb_arg);
 		switch (ret) {
 		case LRU_REMOVED_RETRY:
 			assert_spin_locked(&nlru->lock);
 		case LRU_REMOVED:
-			if (--nlru->nr_items == 0)
-				node_clear(nid, lru->active_nodes);
-			WARN_ON_ONCE(nlru->nr_items < 0);
 			isolated++;
 			/*
 			 * If the lru lock has been dropped, our list
@@ -103,7 +221,7 @@ list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
 				goto restart;
 			break;
 		case LRU_ROTATE:
-			list_move_tail(item, &nlru->list);
+			list_move_tail(item, &l->list);
 			break;
 		case LRU_SKIP:
 			break;
@@ -122,31 +240,322 @@ list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
 	spin_unlock(&nlru->lock);
 	return isolated;
 }
+
+unsigned long
+list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
+		  list_lru_walk_cb isolate, void *cb_arg,
+		  unsigned long *nr_to_walk)
+{
+	return __list_lru_walk_one(lru, nid, memcg_cache_id(memcg),
+				   isolate, cb_arg, nr_to_walk);
+}
+EXPORT_SYMBOL_GPL(list_lru_walk_one);
+
+unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
+				 list_lru_walk_cb isolate, void *cb_arg,
+				 unsigned long *nr_to_walk)
+{
+	long isolated = 0;
+	int memcg_idx;
+
+	isolated += __list_lru_walk_one(lru, nid, -1, isolate, cb_arg,
+					nr_to_walk);
+	if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) {
+		for_each_memcg_cache_index(memcg_idx) {
+			isolated += __list_lru_walk_one(lru, nid, memcg_idx,
+						isolate, cb_arg, nr_to_walk);
+			if (*nr_to_walk <= 0)
+				break;
+		}
+	}
+	return isolated;
+}
 EXPORT_SYMBOL_GPL(list_lru_walk_node);
 
-int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
+static void init_one_lru(struct list_lru_one *l)
+{
+	INIT_LIST_HEAD(&l->list);
+	l->nr_items = 0;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus,
+					  int begin, int end)
+{
+	int i;
+
+	for (i = begin; i < end; i++)
+		kfree(memcg_lrus->lru[i]);
+}
+
+static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus,
+				      int begin, int end)
+{
+	int i;
+
+	for (i = begin; i < end; i++) {
+		struct list_lru_one *l;
+
+		l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL);
+		if (!l)
+			goto fail;
+
+		init_one_lru(l);
+		memcg_lrus->lru[i] = l;
+	}
+	return 0;
+fail:
+	__memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1);
+	return -ENOMEM;
+}
+
+static int memcg_init_list_lru_node(struct list_lru_node *nlru)
+{
+	int size = memcg_nr_cache_ids;
+
+	nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL);
+	if (!nlru->memcg_lrus)
+		return -ENOMEM;
+
+	if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) {
+		kfree(nlru->memcg_lrus);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
+{
+	__memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids);
+	kfree(nlru->memcg_lrus);
+}
+
+static int memcg_update_list_lru_node(struct list_lru_node *nlru,
+				      int old_size, int new_size)
+{
+	struct list_lru_memcg *old, *new;
+
+	BUG_ON(old_size > new_size);
+
+	old = nlru->memcg_lrus;
+	new = kmalloc(new_size * sizeof(void *), GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	if (__memcg_init_list_lru_node(new, old_size, new_size)) {
+		kfree(new);
+		return -ENOMEM;
+	}
+
+	memcpy(new, old, old_size * sizeof(void *));
+
+	/*
+	 * The lock guarantees that we won't race with a reader
+	 * (see list_lru_from_memcg_idx).
+	 *
+	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
+	 * we have to use IRQ-safe primitives here to avoid deadlock.
+	 */
+	spin_lock_irq(&nlru->lock);
+	nlru->memcg_lrus = new;
+	spin_unlock_irq(&nlru->lock);
+
+	kfree(old);
+	return 0;
+}
+
+static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru,
+					      int old_size, int new_size)
+{
+	/* do not bother shrinking the array back to the old size, because we
+	 * cannot handle allocation failures here */
+	__memcg_destroy_list_lru_node(nlru->memcg_lrus, old_size, new_size);
+}
+
+static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
+{
+	int i;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		if (!memcg_aware)
+			lru->node[i].memcg_lrus = NULL;
+		else if (memcg_init_list_lru_node(&lru->node[i]))
+			goto fail;
+	}
+	return 0;
+fail:
+	for (i = i - 1; i >= 0; i--)
+		memcg_destroy_list_lru_node(&lru->node[i]);
+	return -ENOMEM;
+}
+
+static void memcg_destroy_list_lru(struct list_lru *lru)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	for (i = 0; i < nr_node_ids; i++)
+		memcg_destroy_list_lru_node(&lru->node[i]);
+}
+
+static int memcg_update_list_lru(struct list_lru *lru,
+				 int old_size, int new_size)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return 0;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		if (memcg_update_list_lru_node(&lru->node[i],
+					       old_size, new_size))
+			goto fail;
+	}
+	return 0;
+fail:
+	for (i = i - 1; i >= 0; i--)
+		memcg_cancel_update_list_lru_node(&lru->node[i],
+						  old_size, new_size);
+	return -ENOMEM;
+}
+
+static void memcg_cancel_update_list_lru(struct list_lru *lru,
+					 int old_size, int new_size)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	for (i = 0; i < nr_node_ids; i++)
+		memcg_cancel_update_list_lru_node(&lru->node[i],
+						  old_size, new_size);
+}
+
+int memcg_update_all_list_lrus(int new_size)
+{
+	int ret = 0;
+	struct list_lru *lru;
+	int old_size = memcg_nr_cache_ids;
+
+	mutex_lock(&list_lrus_mutex);
+	list_for_each_entry(lru, &list_lrus, list) {
+		ret = memcg_update_list_lru(lru, old_size, new_size);
+		if (ret)
+			goto fail;
+	}
+out:
+	mutex_unlock(&list_lrus_mutex);
+	return ret;
+fail:
+	list_for_each_entry_continue_reverse(lru, &list_lrus, list)
+		memcg_cancel_update_list_lru(lru, old_size, new_size);
+	goto out;
+}
+
+static void memcg_drain_list_lru_node(struct list_lru_node *nlru,
+				      int src_idx, int dst_idx)
+{
+	struct list_lru_one *src, *dst;
+
+	/*
+	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
+	 * we have to use IRQ-safe primitives here to avoid deadlock.
+	 */
+	spin_lock_irq(&nlru->lock);
+
+	src = list_lru_from_memcg_idx(nlru, src_idx);
+	dst = list_lru_from_memcg_idx(nlru, dst_idx);
+
+	list_splice_init(&src->list, &dst->list);
+	dst->nr_items += src->nr_items;
+	src->nr_items = 0;
+
+	spin_unlock_irq(&nlru->lock);
+}
+
+static void memcg_drain_list_lru(struct list_lru *lru,
+				 int src_idx, int dst_idx)
+{
+	int i;
+
+	if (!list_lru_memcg_aware(lru))
+		return;
+
+	for (i = 0; i < nr_node_ids; i++)
+		memcg_drain_list_lru_node(&lru->node[i], src_idx, dst_idx);
+}
+
+void memcg_drain_all_list_lrus(int src_idx, int dst_idx)
+{
+	struct list_lru *lru;
+
+	mutex_lock(&list_lrus_mutex);
+	list_for_each_entry(lru, &list_lrus, list)
+		memcg_drain_list_lru(lru, src_idx, dst_idx);
+	mutex_unlock(&list_lrus_mutex);
+}
+#else
+static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
+{
+	return 0;
+}
+
+static void memcg_destroy_list_lru(struct list_lru *lru)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+int __list_lru_init(struct list_lru *lru, bool memcg_aware,
+		    struct lock_class_key *key)
 {
 	int i;
 	size_t size = sizeof(*lru->node) * nr_node_ids;
+	int err = -ENOMEM;
+
+	memcg_get_cache_ids();
 
 	lru->node = kzalloc(size, GFP_KERNEL);
 	if (!lru->node)
-		return -ENOMEM;
+		goto out;
 
-	nodes_clear(lru->active_nodes);
 	for (i = 0; i < nr_node_ids; i++) {
 		spin_lock_init(&lru->node[i].lock);
 		if (key)
 			lockdep_set_class(&lru->node[i].lock, key);
-		INIT_LIST_HEAD(&lru->node[i].list);
-		lru->node[i].nr_items = 0;
+		init_one_lru(&lru->node[i].lru);
 	}
-	return 0;
+
+	err = memcg_init_list_lru(lru, memcg_aware);
+	if (err) {
+		kfree(lru->node);
+		goto out;
+	}
+
+	list_lru_register(lru);
+out:
+	memcg_put_cache_ids();
+	return err;
 }
-EXPORT_SYMBOL_GPL(list_lru_init_key);
+EXPORT_SYMBOL_GPL(__list_lru_init);
 
 void list_lru_destroy(struct list_lru *lru)
 {
+	/* Already destroyed or not yet initialized? */
+	if (!lru->node)
+		return;
+
+	memcg_get_cache_ids();
+
+	list_lru_unregister(lru);
+
+	memcg_destroy_list_lru(lru);
 	kfree(lru->node);
+	lru->node = NULL;
+
+	memcg_put_cache_ids();
 }
 EXPORT_SYMBOL_GPL(list_lru_destroy);
diff --git a/mm/madvise.c b/mm/madvise.c
index d79fb5e8f80a0b..1077cbdc8b5207 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -222,19 +222,22 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	struct file *file = vma->vm_file;
 
 #ifdef CONFIG_SWAP
-	if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+	if (!file) {
 		*prev = vma;
-		if (!file)
-			force_swapin_readahead(vma, start, end);
-		else
-			force_shm_swapin_readahead(vma, start, end,
-						file->f_mapping);
+		force_swapin_readahead(vma, start, end);
 		return 0;
 	}
-#endif
 
+	if (shmem_mapping(file->f_mapping)) {
+		*prev = vma;
+		force_shm_swapin_readahead(vma, start, end,
+					file->f_mapping);
+		return 0;
+	}
+#else
 	if (!file)
 		return -EBADF;
+#endif
 
 	if (file->f_mapping->a_ops->get_xip_mem) {
 		/* no bad return value, but ignore advice */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 095c1f96fbecf3..d18d3a6e7337d9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -332,8 +332,10 @@ struct mem_cgroup {
 	struct cg_proto tcp_mem;
 #endif
 #if defined(CONFIG_MEMCG_KMEM)
-        /* Index in the kmem_cache->memcg_params->memcg_caches array */
+        /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
+	bool kmem_acct_activated;
+	bool kmem_acct_active;
 #endif
 
 	int last_scanned_node;
@@ -352,9 +354,9 @@ struct mem_cgroup {
 };
 
 #ifdef CONFIG_MEMCG_KMEM
-static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 {
-	return memcg->kmemcg_id >= 0;
+	return memcg->kmem_acct_active;
 }
 #endif
 
@@ -517,33 +519,35 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(tcp_proto_cgroup);
 
-static void disarm_sock_keys(struct mem_cgroup *memcg)
-{
-	if (!memcg_proto_activated(&memcg->tcp_mem))
-		return;
-	static_key_slow_dec(&memcg_socket_limit_enabled);
-}
-#else
-static void disarm_sock_keys(struct mem_cgroup *memcg)
-{
-}
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
 /*
- * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
+ * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
  * The main reason for not using cgroup id for this:
  *  this works better in sparse environments, where we have a lot of memcgs,
  *  but only a few kmem-limited. Or also, if we have, for instance, 200
  *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
  *  200 entry array for that.
  *
- * The current size of the caches array is stored in
- * memcg_limited_groups_array_size.  It will double each time we have to
- * increase it.
+ * The current size of the caches array is stored in memcg_nr_cache_ids. It
+ * will double each time we have to increase it.
  */
-static DEFINE_IDA(kmem_limited_groups);
-int memcg_limited_groups_array_size;
+static DEFINE_IDA(memcg_cache_ida);
+int memcg_nr_cache_ids;
+
+/* Protects memcg_nr_cache_ids */
+static DECLARE_RWSEM(memcg_cache_ids_sem);
+
+void memcg_get_cache_ids(void)
+{
+	down_read(&memcg_cache_ids_sem);
+}
+
+void memcg_put_cache_ids(void)
+{
+	up_read(&memcg_cache_ids_sem);
+}
 
 /*
  * MIN_SIZE is different than 1, because we would like to avoid going through
@@ -569,32 +573,8 @@ int memcg_limited_groups_array_size;
 struct static_key memcg_kmem_enabled_key;
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
-static void memcg_free_cache_id(int id);
-
-static void disarm_kmem_keys(struct mem_cgroup *memcg)
-{
-	if (memcg_kmem_is_active(memcg)) {
-		static_key_slow_dec(&memcg_kmem_enabled_key);
-		memcg_free_cache_id(memcg->kmemcg_id);
-	}
-	/*
-	 * This check can't live in kmem destruction function,
-	 * since the charges will outlive the cgroup
-	 */
-	WARN_ON(page_counter_read(&memcg->kmem));
-}
-#else
-static void disarm_kmem_keys(struct mem_cgroup *memcg)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 
-static void disarm_static_keys(struct mem_cgroup *memcg)
-{
-	disarm_sock_keys(memcg);
-	disarm_kmem_keys(memcg);
-}
-
 static struct mem_cgroup_per_zone *
 mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
 {
@@ -2538,18 +2518,19 @@ static int memcg_alloc_cache_id(void)
 	int id, size;
 	int err;
 
-	id = ida_simple_get(&kmem_limited_groups,
+	id = ida_simple_get(&memcg_cache_ida,
 			    0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
 	if (id < 0)
 		return id;
 
-	if (id < memcg_limited_groups_array_size)
+	if (id < memcg_nr_cache_ids)
 		return id;
 
 	/*
 	 * There's no space for the new id in memcg_caches arrays,
 	 * so we have to grow them.
 	 */
+	down_write(&memcg_cache_ids_sem);
 
 	size = 2 * (id + 1);
 	if (size < MEMCG_CACHES_MIN_SIZE)
@@ -2558,8 +2539,15 @@ static int memcg_alloc_cache_id(void)
 		size = MEMCG_CACHES_MAX_SIZE;
 
 	err = memcg_update_all_caches(size);
+	if (!err)
+		err = memcg_update_all_list_lrus(size);
+	if (!err)
+		memcg_nr_cache_ids = size;
+
+	up_write(&memcg_cache_ids_sem);
+
 	if (err) {
-		ida_simple_remove(&kmem_limited_groups, id);
+		ida_simple_remove(&memcg_cache_ida, id);
 		return err;
 	}
 	return id;
@@ -2567,17 +2555,7 @@ static int memcg_alloc_cache_id(void)
 
 static void memcg_free_cache_id(int id)
 {
-	ida_simple_remove(&kmem_limited_groups, id);
-}
-
-/*
- * We should update the current array size iff all caches updates succeed. This
- * can only be done from the slab side. The slab mutex needs to be held when
- * calling this.
- */
-void memcg_update_array_size(int num)
-{
-	memcg_limited_groups_array_size = num;
+	ida_simple_remove(&memcg_cache_ida, id);
 }
 
 struct memcg_kmem_cache_create_work {
@@ -2656,18 +2634,19 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
+	int kmemcg_id;
 
-	VM_BUG_ON(!cachep->memcg_params);
-	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
+	VM_BUG_ON(!is_root_cache(cachep));
 
 	if (current->memcg_kmem_skip_account)
 		return cachep;
 
 	memcg = get_mem_cgroup_from_mm(current->mm);
-	if (!memcg_kmem_is_active(memcg))
+	kmemcg_id = ACCESS_ONCE(memcg->kmemcg_id);
+	if (kmemcg_id < 0)
 		goto out;
 
-	memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg));
+	memcg_cachep = cache_from_memcg_idx(cachep, kmemcg_id);
 	if (likely(memcg_cachep))
 		return memcg_cachep;
 
@@ -2692,7 +2671,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 void __memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 	if (!is_root_cache(cachep))
-		css_put(&cachep->memcg_params->memcg->css);
+		css_put(&cachep->memcg_params.memcg->css);
 }
 
 /*
@@ -2757,6 +2736,24 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 	memcg_uncharge_kmem(memcg, 1 << order);
 	page->mem_cgroup = NULL;
 }
+
+struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
+{
+	struct mem_cgroup *memcg = NULL;
+	struct kmem_cache *cachep;
+	struct page *page;
+
+	page = virt_to_head_page(ptr);
+	if (PageSlab(page)) {
+		cachep = page->slab_cache;
+		if (!is_root_cache(cachep))
+			memcg = cachep->memcg_params.memcg;
+	} else
+		/* page allocated by alloc_kmem_pages */
+		memcg = page->mem_cgroup;
+
+	return memcg;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -3291,8 +3288,9 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg,
 	int err = 0;
 	int memcg_id;
 
-	if (memcg_kmem_is_active(memcg))
-		return 0;
+	BUG_ON(memcg->kmemcg_id >= 0);
+	BUG_ON(memcg->kmem_acct_activated);
+	BUG_ON(memcg->kmem_acct_active);
 
 	/*
 	 * For simplicity, we won't allow this to be disabled.  It also can't
@@ -3335,6 +3333,8 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg,
 	 * patched.
 	 */
 	memcg->kmemcg_id = memcg_id;
+	memcg->kmem_acct_activated = true;
+	memcg->kmem_acct_active = true;
 out:
 	return err;
 }
@@ -4014,9 +4014,59 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 	return mem_cgroup_sockets_init(memcg, ss);
 }
 
+static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
+{
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *parent, *child;
+	int kmemcg_id;
+
+	if (!memcg->kmem_acct_active)
+		return;
+
+	/*
+	 * Clear the 'active' flag before clearing memcg_caches arrays entries.
+	 * Since we take the slab_mutex in memcg_deactivate_kmem_caches(), it
+	 * guarantees no cache will be created for this cgroup after we are
+	 * done (see memcg_create_kmem_cache()).
+	 */
+	memcg->kmem_acct_active = false;
+
+	memcg_deactivate_kmem_caches(memcg);
+
+	kmemcg_id = memcg->kmemcg_id;
+	BUG_ON(kmemcg_id < 0);
+
+	parent = parent_mem_cgroup(memcg);
+	if (!parent)
+		parent = root_mem_cgroup;
+
+	/*
+	 * Change kmemcg_id of this cgroup and all its descendants to the
+	 * parent's id, and then move all entries from this cgroup's list_lrus
+	 * to ones of the parent. After we have finished, all list_lrus
+	 * corresponding to this cgroup are guaranteed to remain empty. The
+	 * ordering is imposed by list_lru_node->lock taken by
+	 * memcg_drain_all_list_lrus().
+	 */
+	css_for_each_descendant_pre(css, &memcg->css) {
+		child = mem_cgroup_from_css(css);
+		BUG_ON(child->kmemcg_id != kmemcg_id);
+		child->kmemcg_id = parent->kmemcg_id;
+		if (!memcg->use_hierarchy)
+			break;
+	}
+	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
+
+	memcg_free_cache_id(kmemcg_id);
+}
+
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
-	memcg_destroy_kmem_caches(memcg);
+	if (memcg->kmem_acct_activated) {
+		memcg_destroy_kmem_caches(memcg);
+		static_key_slow_dec(&memcg_kmem_enabled_key);
+		WARN_ON(page_counter_read(&memcg->kmem));
+	}
 	mem_cgroup_sockets_destroy(memcg);
 }
 #else
@@ -4025,6 +4075,10 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 	return 0;
 }
 
+static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
+{
+}
+
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
 }
@@ -4443,8 +4497,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 		free_mem_cgroup_per_zone_info(memcg, node);
 
 	free_percpu(memcg->stat);
-
-	disarm_static_keys(memcg);
 	kfree(memcg);
 }
 
@@ -4581,6 +4633,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	spin_unlock(&memcg->event_list_lock);
 
 	vmpressure_cleanup(&memcg->vmpressure);
+
+	memcg_deactivate_kmem(memcg);
 }
 
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index feb803bf344364..d487f8dc6d392a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -242,15 +242,8 @@ void shake_page(struct page *p, int access)
 	 * Only call shrink_node_slabs here (which would also shrink
 	 * other caches) if access is not potentially fatal.
 	 */
-	if (access) {
-		int nr;
-		int nid = page_to_nid(p);
-		do {
-			nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000);
-			if (page_count(p) == 1)
-				break;
-		} while (nr > 10);
-	}
+	if (access)
+		drop_slab_node(page_to_nid(p));
 }
 EXPORT_SYMBOL_GPL(shake_page);
 
@@ -1653,8 +1646,6 @@ static int __soft_offline_page(struct page *page, int flags)
 			 * source page should be freed back to buddy before
 			 * setting PG_hwpoison.
 			 */
-			if (!is_free_buddy_page(page))
-				lru_add_drain_all();
 			if (!is_free_buddy_page(page))
 				drain_all_pages(page_zone(page));
 			SetPageHWPoison(page);
diff --git a/mm/memory.c b/mm/memory.c
index bbe6a73a899d2b..99275325f30368 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3013,14 +3013,17 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	bool migrated = false;
 	int flags = 0;
 
+	/* A PROT_NONE fault should not end up here */
+	BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
+
 	/*
 	* The "pte" at this point cannot be used safely without
 	* validation through pte_unmap_same(). It's of NUMA type but
 	* the pfn may be screwed if the read is non atomic.
 	*
-	* ptep_modify_prot_start is not called as this is clearing
-	* the _PAGE_NUMA bit and it is not really expected that there
-	* would be concurrent hardware modifications to the PTE.
+	* We can safely just do a "set_pte_at()", because the old
+	* page table entry is not accessible, so there would be no
+	* concurrent hardware modifications to the PTE.
 	*/
 	ptl = pte_lockptr(mm, pmd);
 	spin_lock(ptl);
@@ -3029,7 +3032,9 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out;
 	}
 
-	pte = pte_mknonnuma(pte);
+	/* Make it present again */
+	pte = pte_modify(pte, vma->vm_page_prot);
+	pte = pte_mkyoung(pte);
 	set_pte_at(mm, addr, ptep, pte);
 	update_mmu_cache(vma, addr, ptep);
 
@@ -3038,7 +3043,6 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte_unmap_unlock(ptep, ptl);
 		return 0;
 	}
-	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
 	/*
 	 * Avoid grouping on DSO/COW pages in specific and RO pages
@@ -3124,7 +3128,7 @@ static int handle_pte_fault(struct mm_struct *mm,
 					pte, pmd, flags, entry);
 	}
 
-	if (pte_numa(entry))
+	if (pte_protnone(entry))
 		return do_numa_page(mm, vma, address, entry, pte, pmd);
 
 	ptl = pte_lockptr(mm, pmd);
@@ -3202,7 +3206,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			if (pmd_trans_splitting(orig_pmd))
 				return 0;
 
-			if (pmd_numa(orig_pmd))
+			if (pmd_protnone(orig_pmd))
 				return do_huge_pmd_numa_page(mm, vma, address,
 							     orig_pmd, pmd);
 
@@ -3458,7 +3462,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 	if (follow_phys(vma, addr, write, &prot, &phys_addr))
 		return -EINVAL;
 
-	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
+	maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
 	if (write)
 		memcpy_toio(maddr + offset, buf, len);
 	else
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f1bd23803576fe..c75f4dcec80865 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -569,7 +569,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 {
 	int nr_updated;
 
-	nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
+	nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index f98067e5d35338..85e04268603143 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1654,12 +1654,6 @@ bool pmd_trans_migrating(pmd_t pmd)
 	return PageLocked(page);
 }
 
-void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
-{
-	struct page *page = pmd_page(*pmd);
-	wait_on_page_locked(page);
-}
-
 /*
  * Attempt to migrate a misplaced page to the specified destination
  * node. Caller is expected to have an elevated reference count on
@@ -1853,7 +1847,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 out_dropref:
 	ptl = pmd_lock(mm, pmd);
 	if (pmd_same(*pmd, entry)) {
-		entry = pmd_mknonnuma(entry);
+		entry = pmd_modify(entry, vma->vm_page_prot);
 		set_pmd_at(mm, mmun_start, pmd, entry);
 		update_mmu_cache_pmd(vma, address, &entry);
 	}
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 4074caf9936bf3..5f420f7fafa1c6 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -14,14 +14,14 @@
 #include "internal.h"
 
 #ifdef CONFIG_DEBUG_MEMORY_INIT
-int mminit_loglevel;
+int __meminitdata mminit_loglevel;
 
 #ifndef SECTIONS_SHIFT
 #define SECTIONS_SHIFT	0
 #endif
 
 /* The zonelists are simply reported, validation is manual. */
-void mminit_verify_zonelist(void)
+void __init mminit_verify_zonelist(void)
 {
 	int nid;
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 33121662f08b50..44727811bf4cf6 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -75,36 +75,34 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		oldpte = *pte;
 		if (pte_present(oldpte)) {
 			pte_t ptent;
-			bool updated = false;
 
-			if (!prot_numa) {
-				ptent = ptep_modify_prot_start(mm, addr, pte);
-				if (pte_numa(ptent))
-					ptent = pte_mknonnuma(ptent);
-				ptent = pte_modify(ptent, newprot);
-				/*
-				 * Avoid taking write faults for pages we
-				 * know to be dirty.
-				 */
-				if (dirty_accountable && pte_dirty(ptent) &&
-				    (pte_soft_dirty(ptent) ||
-				     !(vma->vm_flags & VM_SOFTDIRTY)))
-					ptent = pte_mkwrite(ptent);
-				ptep_modify_prot_commit(mm, addr, pte, ptent);
-				updated = true;
-			} else {
+			/*
+			 * Avoid trapping faults against the zero or KSM
+			 * pages. See similar comment in change_huge_pmd.
+			 */
+			if (prot_numa) {
 				struct page *page;
 
 				page = vm_normal_page(vma, addr, oldpte);
-				if (page && !PageKsm(page)) {
-					if (!pte_numa(oldpte)) {
-						ptep_set_numa(mm, addr, pte);
-						updated = true;
-					}
-				}
+				if (!page || PageKsm(page))
+					continue;
+
+				/* Avoid TLB flush if possible */
+				if (pte_protnone(oldpte))
+					continue;
 			}
-			if (updated)
-				pages++;
+
+			ptent = ptep_modify_prot_start(mm, addr, pte);
+			ptent = pte_modify(ptent, newprot);
+
+			/* Avoid taking write faults for known dirty pages */
+			if (dirty_accountable && pte_dirty(ptent) &&
+					(pte_soft_dirty(ptent) ||
+					 !(vma->vm_flags & VM_SOFTDIRTY))) {
+				ptent = pte_mkwrite(ptent);
+			}
+			ptep_modify_prot_commit(mm, addr, pte, ptent);
+			pages++;
 		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 1a19fb3b046355..7296360fc057e5 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -980,9 +980,6 @@ static int validate_mmap_request(struct file *file,
 		return -EOVERFLOW;
 
 	if (file) {
-		/* validate file mapping requests */
-		struct address_space *mapping;
-
 		/* files must support mmap */
 		if (!file->f_op->mmap)
 			return -ENODEV;
@@ -991,28 +988,22 @@ static int validate_mmap_request(struct file *file,
 		 * - we support chardevs that provide their own "memory"
 		 * - we support files/blockdevs that are memory backed
 		 */
-		mapping = file->f_mapping;
-		if (!mapping)
-			mapping = file_inode(file)->i_mapping;
-
-		capabilities = 0;
-		if (mapping && mapping->backing_dev_info)
-			capabilities = mapping->backing_dev_info->capabilities;
-
-		if (!capabilities) {
+		if (file->f_op->mmap_capabilities) {
+			capabilities = file->f_op->mmap_capabilities(file);
+		} else {
 			/* no explicit capabilities set, so assume some
 			 * defaults */
 			switch (file_inode(file)->i_mode & S_IFMT) {
 			case S_IFREG:
 			case S_IFBLK:
-				capabilities = BDI_CAP_MAP_COPY;
+				capabilities = NOMMU_MAP_COPY;
 				break;
 
 			case S_IFCHR:
 				capabilities =
-					BDI_CAP_MAP_DIRECT |
-					BDI_CAP_READ_MAP |
-					BDI_CAP_WRITE_MAP;
+					NOMMU_MAP_DIRECT |
+					NOMMU_MAP_READ |
+					NOMMU_MAP_WRITE;
 				break;
 
 			default:
@@ -1023,9 +1014,9 @@ static int validate_mmap_request(struct file *file,
 		/* eliminate any capabilities that we can't support on this
 		 * device */
 		if (!file->f_op->get_unmapped_area)
-			capabilities &= ~BDI_CAP_MAP_DIRECT;
+			capabilities &= ~NOMMU_MAP_DIRECT;
 		if (!file->f_op->read)
-			capabilities &= ~BDI_CAP_MAP_COPY;
+			capabilities &= ~NOMMU_MAP_COPY;
 
 		/* The file shall have been opened with read permission. */
 		if (!(file->f_mode & FMODE_READ))
@@ -1044,29 +1035,29 @@ static int validate_mmap_request(struct file *file,
 			if (locks_verify_locked(file))
 				return -EAGAIN;
 
-			if (!(capabilities & BDI_CAP_MAP_DIRECT))
+			if (!(capabilities & NOMMU_MAP_DIRECT))
 				return -ENODEV;
 
 			/* we mustn't privatise shared mappings */
-			capabilities &= ~BDI_CAP_MAP_COPY;
+			capabilities &= ~NOMMU_MAP_COPY;
 		} else {
 			/* we're going to read the file into private memory we
 			 * allocate */
-			if (!(capabilities & BDI_CAP_MAP_COPY))
+			if (!(capabilities & NOMMU_MAP_COPY))
 				return -ENODEV;
 
 			/* we don't permit a private writable mapping to be
 			 * shared with the backing device */
 			if (prot & PROT_WRITE)
-				capabilities &= ~BDI_CAP_MAP_DIRECT;
+				capabilities &= ~NOMMU_MAP_DIRECT;
 		}
 
-		if (capabilities & BDI_CAP_MAP_DIRECT) {
-			if (((prot & PROT_READ)  && !(capabilities & BDI_CAP_READ_MAP))  ||
-			    ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
-			    ((prot & PROT_EXEC)  && !(capabilities & BDI_CAP_EXEC_MAP))
+		if (capabilities & NOMMU_MAP_DIRECT) {
+			if (((prot & PROT_READ)  && !(capabilities & NOMMU_MAP_READ))  ||
+			    ((prot & PROT_WRITE) && !(capabilities & NOMMU_MAP_WRITE)) ||
+			    ((prot & PROT_EXEC)  && !(capabilities & NOMMU_MAP_EXEC))
 			    ) {
-				capabilities &= ~BDI_CAP_MAP_DIRECT;
+				capabilities &= ~NOMMU_MAP_DIRECT;
 				if (flags & MAP_SHARED) {
 					printk(KERN_WARNING
 					       "MAP_SHARED not completely supported on !MMU\n");
@@ -1083,21 +1074,21 @@ static int validate_mmap_request(struct file *file,
 		} else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
 			/* handle implication of PROT_EXEC by PROT_READ */
 			if (current->personality & READ_IMPLIES_EXEC) {
-				if (capabilities & BDI_CAP_EXEC_MAP)
+				if (capabilities & NOMMU_MAP_EXEC)
 					prot |= PROT_EXEC;
 			}
 		} else if ((prot & PROT_READ) &&
 			 (prot & PROT_EXEC) &&
-			 !(capabilities & BDI_CAP_EXEC_MAP)
+			 !(capabilities & NOMMU_MAP_EXEC)
 			 ) {
 			/* backing file is not executable, try to copy */
-			capabilities &= ~BDI_CAP_MAP_DIRECT;
+			capabilities &= ~NOMMU_MAP_DIRECT;
 		}
 	} else {
 		/* anonymous mappings are always memory backed and can be
 		 * privately mapped
 		 */
-		capabilities = BDI_CAP_MAP_COPY;
+		capabilities = NOMMU_MAP_COPY;
 
 		/* handle PROT_EXEC implication by PROT_READ */
 		if ((prot & PROT_READ) &&
@@ -1129,7 +1120,7 @@ static unsigned long determine_vm_flags(struct file *file,
 	vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags);
 	/* vm_flags |= mm->def_flags; */
 
-	if (!(capabilities & BDI_CAP_MAP_DIRECT)) {
+	if (!(capabilities & NOMMU_MAP_DIRECT)) {
 		/* attempt to share read-only copies of mapped file chunks */
 		vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
 		if (file && !(prot & PROT_WRITE))
@@ -1138,7 +1129,7 @@ static unsigned long determine_vm_flags(struct file *file,
 		/* overlay a shareable mapping on the backing device or inode
 		 * if possible - used for chardevs, ramfs/tmpfs/shmfs and
 		 * romfs/cramfs */
-		vm_flags |= VM_MAYSHARE | (capabilities & BDI_CAP_VMFLAGS);
+		vm_flags |= VM_MAYSHARE | (capabilities & NOMMU_VMFLAGS);
 		if (flags & MAP_SHARED)
 			vm_flags |= VM_SHARED;
 	}
@@ -1191,7 +1182,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 	 * shared mappings on devices or memory
 	 * - VM_MAYSHARE will be set if it may attempt to share
 	 */
-	if (capabilities & BDI_CAP_MAP_DIRECT) {
+	if (capabilities & NOMMU_MAP_DIRECT) {
 		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
 		if (ret == 0) {
 			/* shouldn't return success if we're not sharing */
@@ -1380,7 +1371,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 			if ((pregion->vm_pgoff != pgoff || rpglen != pglen) &&
 			    !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) {
 				/* new mapping is not a subset of the region */
-				if (!(capabilities & BDI_CAP_MAP_DIRECT))
+				if (!(capabilities & NOMMU_MAP_DIRECT))
 					goto sharing_violation;
 				continue;
 			}
@@ -1419,7 +1410,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 		 * - this is the hook for quasi-memory character devices to
 		 *   tell us the location of a shared mapping
 		 */
-		if (capabilities & BDI_CAP_MAP_DIRECT) {
+		if (capabilities & NOMMU_MAP_DIRECT) {
 			addr = file->f_op->get_unmapped_area(file, addr, len,
 							     pgoff, flags);
 			if (IS_ERR_VALUE(addr)) {
@@ -1431,10 +1422,10 @@ unsigned long do_mmap_pgoff(struct file *file,
 				 * the mapping so we'll have to attempt to copy
 				 * it */
 				ret = -ENODEV;
-				if (!(capabilities & BDI_CAP_MAP_COPY))
+				if (!(capabilities & NOMMU_MAP_COPY))
 					goto error_just_free;
 
-				capabilities &= ~BDI_CAP_MAP_DIRECT;
+				capabilities &= ~NOMMU_MAP_DIRECT;
 			} else {
 				vma->vm_start = region->vm_start = addr;
 				vma->vm_end = region->vm_end = addr + len;
@@ -1445,7 +1436,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 	vma->vm_region = region;
 
 	/* set up the mapping
-	 * - the region is filled in if BDI_CAP_MAP_DIRECT is still set
+	 * - the region is filled in if NOMMU_MAP_DIRECT is still set
 	 */
 	if (file && vma->vm_flags & VM_SHARED)
 		ret = do_mmap_shared_file(vma);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6a73e47e81c67f..45e187b2d97183 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1351,7 +1351,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 	unsigned long task_ratelimit;
 	unsigned long dirty_ratelimit;
 	unsigned long pos_ratio;
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
 	unsigned long start_time = jiffies;
 
@@ -1574,7 +1574,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
  */
 void balance_dirty_pages_ratelimited(struct address_space *mapping)
 {
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	int ratelimit;
 	int *p;
 
@@ -1929,7 +1929,7 @@ int write_cache_pages(struct address_space *mapping,
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			trace_wbc_writepage(wbc, mapping->backing_dev_info);
+			trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
 			ret = (*writepage)(page, wbc, data);
 			if (unlikely(ret)) {
 				if (ret == AOP_WRITEPAGE_ACTIVATE) {
@@ -2094,10 +2094,12 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 	trace_writeback_dirty_page(page, mapping);
 
 	if (mapping_cap_account_dirty(mapping)) {
+		struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+
 		__inc_zone_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_DIRTIED);
-		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
-		__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+		__inc_bdi_stat(bdi, BDI_RECLAIMABLE);
+		__inc_bdi_stat(bdi, BDI_DIRTIED);
 		task_io_account_write(PAGE_CACHE_SIZE);
 		current->nr_dirtied++;
 		this_cpu_inc(bdp_ratelimits);
@@ -2156,7 +2158,7 @@ void account_page_redirty(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		current->nr_dirtied--;
 		dec_zone_page_state(page, NR_DIRTIED);
-		dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+		dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED);
 	}
 }
 EXPORT_SYMBOL(account_page_redirty);
@@ -2298,7 +2300,7 @@ int clear_page_dirty_for_io(struct page *page)
 		 */
 		if (TestClearPageDirty(page)) {
 			dec_zone_page_state(page, NR_FILE_DIRTY);
-			dec_bdi_stat(mapping->backing_dev_info,
+			dec_bdi_stat(inode_to_bdi(mapping->host),
 					BDI_RECLAIMABLE);
 			return 1;
 		}
@@ -2316,7 +2318,7 @@ int test_clear_page_writeback(struct page *page)
 
 	memcg = mem_cgroup_begin_page_stat(page);
 	if (mapping) {
-		struct backing_dev_info *bdi = mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 		unsigned long flags;
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
@@ -2351,7 +2353,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 
 	memcg = mem_cgroup_begin_page_stat(page);
 	if (mapping) {
-		struct backing_dev_info *bdi = mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 		unsigned long flags;
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
@@ -2405,12 +2407,7 @@ EXPORT_SYMBOL(mapping_tagged);
  */
 void wait_for_stable_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
-
-	if (!bdi_cap_stable_pages_required(bdi))
-		return;
-
-	wait_on_page_writeback(page);
+	if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
+		wait_on_page_writeback(page);
 }
 EXPORT_SYMBOL_GPL(wait_for_stable_page);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8d52ab18fe0dac..cb4758263f6b8a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -172,7 +172,7 @@ static void __free_pages_ok(struct page *page, unsigned int order);
  *	1G machine -> (16M dma, 784M normal, 224M high)
  *	NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
  *	HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
- *	HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
+ *	HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA
  *
  * TBD: should special case ZONE_DMA32 machines here - in those we normally
  * don't need any ZONE_NORMAL reservation
@@ -3871,18 +3871,29 @@ static int __build_all_zonelists(void *data)
 	return 0;
 }
 
+static noinline void __init
+build_all_zonelists_init(void)
+{
+	__build_all_zonelists(NULL);
+	mminit_verify_zonelist();
+	cpuset_init_current_mems_allowed();
+}
+
 /*
  * Called with zonelists_mutex held always
  * unless system_state == SYSTEM_BOOTING.
+ *
+ * __ref due to (1) call of __meminit annotated setup_zone_pageset
+ * [we're only called with non-NULL zone through __meminit paths] and
+ * (2) call of __init annotated helper build_all_zonelists_init
+ * [protected by SYSTEM_BOOTING].
  */
 void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 {
 	set_zonelist_order();
 
 	if (system_state == SYSTEM_BOOTING) {
-		__build_all_zonelists(NULL);
-		mminit_verify_zonelist();
-		cpuset_init_current_mems_allowed();
+		build_all_zonelists_init();
 	} else {
 #ifdef CONFIG_MEMORY_HOTPLUG
 		if (zone)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index dfb79e028ecbf2..c25f94b338115a 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -193,8 +193,6 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
 	pmd_t entry = *pmdp;
-	if (pmd_numa(entry))
-		entry = pmd_mknonnuma(entry);
 	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }
diff --git a/mm/readahead.c b/mm/readahead.c
index 17b9172ec37f1e..935675844b2ee4 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -27,7 +27,7 @@
 void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
 {
-	ra->ra_pages = mapping->backing_dev_info->ra_pages;
+	ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages;
 	ra->prev_pos = -1;
 }
 EXPORT_SYMBOL_GPL(file_ra_state_init);
@@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping,
 	/*
 	 * Defer asynchronous read-ahead on IO congestion.
 	 */
-	if (bdi_read_congested(mapping->backing_dev_info))
+	if (bdi_read_congested(inode_to_bdi(mapping->host)))
 		return;
 
 	/* do read-ahead */
diff --git a/mm/shmem.c b/mm/shmem.c
index 864c878401e66a..a63031fa3e0c1e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -191,11 +191,6 @@ static const struct inode_operations shmem_dir_inode_operations;
 static const struct inode_operations shmem_special_inode_operations;
 static const struct vm_operations_struct shmem_vm_ops;
 
-static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-};
-
 static LIST_HEAD(shmem_swaplist);
 static DEFINE_MUTEX(shmem_swaplist_mutex);
 
@@ -765,11 +760,11 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		goto redirty;
 
 	/*
-	 * shmem_backing_dev_info's capabilities prevent regular writeback or
-	 * sync from ever calling shmem_writepage; but a stacking filesystem
-	 * might use ->writepage of its underlying filesystem, in which case
-	 * tmpfs should write out to swap only in response to memory pressure,
-	 * and not for the writeback threads or sync.
+	 * Our capabilities prevent regular writeback or sync from ever calling
+	 * shmem_writepage; but a stacking filesystem might use ->writepage of
+	 * its underlying filesystem, in which case tmpfs should write out to
+	 * swap only in response to memory pressure, and not for the writeback
+	 * threads or sync.
 	 */
 	if (!wbc->for_reclaim) {
 		WARN_ON_ONCE(1);	/* Still happens? Tell us about it! */
@@ -1415,7 +1410,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_blocks = 0;
-		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_generation = get_seconds();
 		info = SHMEM_I(inode);
@@ -1461,7 +1455,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 
 bool shmem_mapping(struct address_space *mapping)
 {
-	return mapping->backing_dev_info == &shmem_backing_dev_info;
+	return mapping->host->i_sb->s_op == &shmem_ops;
 }
 
 #ifdef CONFIG_TMPFS
@@ -3225,10 +3219,6 @@ int __init shmem_init(void)
 	if (shmem_inode_cachep)
 		return 0;
 
-	error = bdi_init(&shmem_backing_dev_info);
-	if (error)
-		goto out4;
-
 	error = shmem_init_inodecache();
 	if (error)
 		goto out3;
@@ -3252,8 +3242,6 @@ int __init shmem_init(void)
 out2:
 	shmem_destroy_inodecache();
 out3:
-	bdi_destroy(&shmem_backing_dev_info);
-out4:
 	shm_mnt = ERR_PTR(error);
 	return error;
 }
diff --git a/mm/slab.c b/mm/slab.c
index 65b5dcb6f67107..c4b89eaf4c9641 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2382,7 +2382,7 @@ static int drain_freelist(struct kmem_cache *cache,
 	return nr_freed;
 }
 
-int __kmem_cache_shrink(struct kmem_cache *cachep)
+int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
 {
 	int ret = 0;
 	int node;
@@ -2404,7 +2404,7 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
 {
 	int i;
 	struct kmem_cache_node *n;
-	int rc = __kmem_cache_shrink(cachep);
+	int rc = __kmem_cache_shrink(cachep, false);
 
 	if (rc)
 		return rc;
@@ -3708,8 +3708,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 				int batchcount, int shared, gfp_t gfp)
 {
 	int ret;
-	struct kmem_cache *c = NULL;
-	int i = 0;
+	struct kmem_cache *c;
 
 	ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
 
@@ -3719,12 +3718,10 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 	if ((ret < 0) || !is_root_cache(cachep))
 		return ret;
 
-	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg_idx(cachep, i);
-		if (c)
-			/* return value determined by the parent cache only */
-			__do_tune_cpucache(c, limit, batchcount, shared, gfp);
+	lockdep_assert_held(&slab_mutex);
+	for_each_memcg_cache(c, cachep) {
+		/* return value determined by the root cache only */
+		__do_tune_cpucache(c, limit, batchcount, shared, gfp);
 	}
 
 	return ret;
diff --git a/mm/slab.h b/mm/slab.h
index 90430d6f665e62..4c3ac12dd64405 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -86,8 +86,6 @@ extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
 extern void create_boot_cache(struct kmem_cache *, const char *name,
 			size_t size, unsigned long flags);
 
-struct mem_cgroup;
-
 int slab_unmergeable(struct kmem_cache *s);
 struct kmem_cache *find_mergeable(size_t size, size_t align,
 		unsigned long flags, const char *name, void (*ctor)(void *));
@@ -140,7 +138,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
 
 int __kmem_cache_shutdown(struct kmem_cache *);
-int __kmem_cache_shrink(struct kmem_cache *);
+int __kmem_cache_shrink(struct kmem_cache *, bool);
 void slab_kmem_cache_release(struct kmem_cache *);
 
 struct seq_file;
@@ -165,16 +163,27 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 		       size_t count, loff_t *ppos);
 
 #ifdef CONFIG_MEMCG_KMEM
+/*
+ * Iterate over all memcg caches of the given root cache. The caller must hold
+ * slab_mutex.
+ */
+#define for_each_memcg_cache(iter, root) \
+	list_for_each_entry(iter, &(root)->memcg_params.list, \
+			    memcg_params.list)
+
+#define for_each_memcg_cache_safe(iter, tmp, root) \
+	list_for_each_entry_safe(iter, tmp, &(root)->memcg_params.list, \
+				 memcg_params.list)
+
 static inline bool is_root_cache(struct kmem_cache *s)
 {
-	return !s->memcg_params || s->memcg_params->is_root_cache;
+	return s->memcg_params.is_root_cache;
 }
 
 static inline bool slab_equal_or_root(struct kmem_cache *s,
-					struct kmem_cache *p)
+				      struct kmem_cache *p)
 {
-	return (p == s) ||
-		(s->memcg_params && (p == s->memcg_params->root_cache));
+	return p == s || p == s->memcg_params.root_cache;
 }
 
 /*
@@ -185,37 +194,30 @@ static inline bool slab_equal_or_root(struct kmem_cache *s,
 static inline const char *cache_name(struct kmem_cache *s)
 {
 	if (!is_root_cache(s))
-		return s->memcg_params->root_cache->name;
+		s = s->memcg_params.root_cache;
 	return s->name;
 }
 
 /*
  * Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
- * That said the caller must assure the memcg's cache won't go away. Since once
- * created a memcg's cache is destroyed only along with the root cache, it is
- * true if we are going to allocate from the cache or hold a reference to the
- * root cache by other means. Otherwise, we should hold either the slab_mutex
- * or the memcg's slab_caches_mutex while calling this function and accessing
- * the returned value.
+ * That said the caller must assure the memcg's cache won't go away by either
+ * taking a css reference to the owner cgroup, or holding the slab_mutex.
  */
 static inline struct kmem_cache *
 cache_from_memcg_idx(struct kmem_cache *s, int idx)
 {
 	struct kmem_cache *cachep;
-	struct memcg_cache_params *params;
-
-	if (!s->memcg_params)
-		return NULL;
+	struct memcg_cache_array *arr;
 
 	rcu_read_lock();
-	params = rcu_dereference(s->memcg_params);
+	arr = rcu_dereference(s->memcg_params.memcg_caches);
 
 	/*
 	 * Make sure we will access the up-to-date value. The code updating
 	 * memcg_caches issues a write barrier to match this (see
-	 * memcg_register_cache()).
+	 * memcg_create_kmem_cache()).
 	 */
-	cachep = lockless_dereference(params->memcg_caches[idx]);
+	cachep = lockless_dereference(arr->entries[idx]);
 	rcu_read_unlock();
 
 	return cachep;
@@ -225,7 +227,7 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 {
 	if (is_root_cache(s))
 		return s;
-	return s->memcg_params->root_cache;
+	return s->memcg_params.root_cache;
 }
 
 static __always_inline int memcg_charge_slab(struct kmem_cache *s,
@@ -235,7 +237,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s,
 		return 0;
 	if (is_root_cache(s))
 		return 0;
-	return memcg_charge_kmem(s->memcg_params->memcg, gfp, 1 << order);
+	return memcg_charge_kmem(s->memcg_params.memcg, gfp, 1 << order);
 }
 
 static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
@@ -244,9 +246,18 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
 		return;
 	if (is_root_cache(s))
 		return;
-	memcg_uncharge_kmem(s->memcg_params->memcg, 1 << order);
+	memcg_uncharge_kmem(s->memcg_params.memcg, 1 << order);
 }
-#else
+
+extern void slab_init_memcg_params(struct kmem_cache *);
+
+#else /* !CONFIG_MEMCG_KMEM */
+
+#define for_each_memcg_cache(iter, root) \
+	for ((void)(iter), (void)(root); 0; )
+#define for_each_memcg_cache_safe(iter, tmp, root) \
+	for ((void)(iter), (void)(tmp), (void)(root); 0; )
+
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return true;
@@ -282,7 +293,11 @@ static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order)
 static inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
 {
 }
-#endif
+
+static inline void slab_init_memcg_params(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 6e1e4cf65836cb..1a1cc89acaa3c8 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -106,62 +106,67 @@ static inline int kmem_cache_sanity_check(const char *name, size_t size)
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
-static int memcg_alloc_cache_params(struct mem_cgroup *memcg,
-		struct kmem_cache *s, struct kmem_cache *root_cache)
+void slab_init_memcg_params(struct kmem_cache *s)
 {
-	size_t size;
+	s->memcg_params.is_root_cache = true;
+	INIT_LIST_HEAD(&s->memcg_params.list);
+	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
+}
+
+static int init_memcg_params(struct kmem_cache *s,
+		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+{
+	struct memcg_cache_array *arr;
 
-	if (!memcg_kmem_enabled())
+	if (memcg) {
+		s->memcg_params.is_root_cache = false;
+		s->memcg_params.memcg = memcg;
+		s->memcg_params.root_cache = root_cache;
 		return 0;
+	}
 
-	if (!memcg) {
-		size = offsetof(struct memcg_cache_params, memcg_caches);
-		size += memcg_limited_groups_array_size * sizeof(void *);
-	} else
-		size = sizeof(struct memcg_cache_params);
+	slab_init_memcg_params(s);
 
-	s->memcg_params = kzalloc(size, GFP_KERNEL);
-	if (!s->memcg_params)
-		return -ENOMEM;
+	if (!memcg_nr_cache_ids)
+		return 0;
 
-	if (memcg) {
-		s->memcg_params->memcg = memcg;
-		s->memcg_params->root_cache = root_cache;
-	} else
-		s->memcg_params->is_root_cache = true;
+	arr = kzalloc(sizeof(struct memcg_cache_array) +
+		      memcg_nr_cache_ids * sizeof(void *),
+		      GFP_KERNEL);
+	if (!arr)
+		return -ENOMEM;
 
+	RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr);
 	return 0;
 }
 
-static void memcg_free_cache_params(struct kmem_cache *s)
+static void destroy_memcg_params(struct kmem_cache *s)
 {
-	kfree(s->memcg_params);
+	if (is_root_cache(s))
+		kfree(rcu_access_pointer(s->memcg_params.memcg_caches));
 }
 
-static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs)
+static int update_memcg_params(struct kmem_cache *s, int new_array_size)
 {
-	int size;
-	struct memcg_cache_params *new_params, *cur_params;
-
-	BUG_ON(!is_root_cache(s));
+	struct memcg_cache_array *old, *new;
 
-	size = offsetof(struct memcg_cache_params, memcg_caches);
-	size += num_memcgs * sizeof(void *);
+	if (!is_root_cache(s))
+		return 0;
 
-	new_params = kzalloc(size, GFP_KERNEL);
-	if (!new_params)
+	new = kzalloc(sizeof(struct memcg_cache_array) +
+		      new_array_size * sizeof(void *), GFP_KERNEL);
+	if (!new)
 		return -ENOMEM;
 
-	cur_params = s->memcg_params;
-	memcpy(new_params->memcg_caches, cur_params->memcg_caches,
-	       memcg_limited_groups_array_size * sizeof(void *));
-
-	new_params->is_root_cache = true;
-
-	rcu_assign_pointer(s->memcg_params, new_params);
-	if (cur_params)
-		kfree_rcu(cur_params, rcu_head);
+	old = rcu_dereference_protected(s->memcg_params.memcg_caches,
+					lockdep_is_held(&slab_mutex));
+	if (old)
+		memcpy(new->entries, old->entries,
+		       memcg_nr_cache_ids * sizeof(void *));
 
+	rcu_assign_pointer(s->memcg_params.memcg_caches, new);
+	if (old)
+		kfree_rcu(old, rcu);
 	return 0;
 }
 
@@ -169,34 +174,28 @@ int memcg_update_all_caches(int num_memcgs)
 {
 	struct kmem_cache *s;
 	int ret = 0;
-	mutex_lock(&slab_mutex);
 
+	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list) {
-		if (!is_root_cache(s))
-			continue;
-
-		ret = memcg_update_cache_params(s, num_memcgs);
+		ret = update_memcg_params(s, num_memcgs);
 		/*
 		 * Instead of freeing the memory, we'll just leave the caches
 		 * up to this point in an updated state.
 		 */
 		if (ret)
-			goto out;
+			break;
 	}
-
-	memcg_update_array_size(num_memcgs);
-out:
 	mutex_unlock(&slab_mutex);
 	return ret;
 }
 #else
-static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
-		struct kmem_cache *s, struct kmem_cache *root_cache)
+static inline int init_memcg_params(struct kmem_cache *s,
+		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
 {
 	return 0;
 }
 
-static inline void memcg_free_cache_params(struct kmem_cache *s)
+static inline void destroy_memcg_params(struct kmem_cache *s)
 {
 }
 #endif /* CONFIG_MEMCG_KMEM */
@@ -314,7 +313,7 @@ do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align,
 	s->align = align;
 	s->ctor = ctor;
 
-	err = memcg_alloc_cache_params(memcg, s, root_cache);
+	err = init_memcg_params(s, memcg, root_cache);
 	if (err)
 		goto out_free_cache;
 
@@ -330,7 +329,7 @@ do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align,
 	return s;
 
 out_free_cache:
-	memcg_free_cache_params(s);
+	destroy_memcg_params(s);
 	kmem_cache_free(kmem_cache, s);
 	goto out;
 }
@@ -369,6 +368,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
 
 	get_online_cpus();
 	get_online_mems();
+	memcg_get_cache_ids();
 
 	mutex_lock(&slab_mutex);
 
@@ -407,6 +407,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
 out_unlock:
 	mutex_unlock(&slab_mutex);
 
+	memcg_put_cache_ids();
 	put_online_mems();
 	put_online_cpus();
 
@@ -439,13 +440,8 @@ static int do_kmem_cache_shutdown(struct kmem_cache *s,
 		*need_rcu_barrier = true;
 
 #ifdef CONFIG_MEMCG_KMEM
-	if (!is_root_cache(s)) {
-		struct kmem_cache *root_cache = s->memcg_params->root_cache;
-		int memcg_id = memcg_cache_id(s->memcg_params->memcg);
-
-		BUG_ON(root_cache->memcg_params->memcg_caches[memcg_id] != s);
-		root_cache->memcg_params->memcg_caches[memcg_id] = NULL;
-	}
+	if (!is_root_cache(s))
+		list_del(&s->memcg_params.list);
 #endif
 	list_move(&s->list, release);
 	return 0;
@@ -482,27 +478,39 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 			     struct kmem_cache *root_cache)
 {
 	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
-	int memcg_id = memcg_cache_id(memcg);
+	struct cgroup_subsys_state *css = mem_cgroup_css(memcg);
+	struct memcg_cache_array *arr;
 	struct kmem_cache *s = NULL;
 	char *cache_name;
+	int idx;
 
 	get_online_cpus();
 	get_online_mems();
 
 	mutex_lock(&slab_mutex);
 
+	/*
+	 * The memory cgroup could have been deactivated while the cache
+	 * creation work was pending.
+	 */
+	if (!memcg_kmem_is_active(memcg))
+		goto out_unlock;
+
+	idx = memcg_cache_id(memcg);
+	arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches,
+					lockdep_is_held(&slab_mutex));
+
 	/*
 	 * Since per-memcg caches are created asynchronously on first
 	 * allocation (see memcg_kmem_get_cache()), several threads can try to
 	 * create the same cache, but only one of them may succeed.
 	 */
-	if (cache_from_memcg_idx(root_cache, memcg_id))
+	if (arr->entries[idx])
 		goto out_unlock;
 
-	cgroup_name(mem_cgroup_css(memcg)->cgroup,
-		    memcg_name_buf, sizeof(memcg_name_buf));
+	cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
 	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
-			       memcg_cache_id(memcg), memcg_name_buf);
+			       css->id, memcg_name_buf);
 	if (!cache_name)
 		goto out_unlock;
 
@@ -520,13 +528,15 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 		goto out_unlock;
 	}
 
+	list_add(&s->memcg_params.list, &root_cache->memcg_params.list);
+
 	/*
 	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
 	 * barrier here to ensure nobody will see the kmem_cache partially
 	 * initialized.
 	 */
 	smp_wmb();
-	root_cache->memcg_params->memcg_caches[memcg_id] = s;
+	arr->entries[idx] = s;
 
 out_unlock:
 	mutex_unlock(&slab_mutex);
@@ -535,6 +545,37 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	put_online_cpus();
 }
 
+void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
+{
+	int idx;
+	struct memcg_cache_array *arr;
+	struct kmem_cache *s, *c;
+
+	idx = memcg_cache_id(memcg);
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
+						lockdep_is_held(&slab_mutex));
+		c = arr->entries[idx];
+		if (!c)
+			continue;
+
+		__kmem_cache_shrink(c, true);
+		arr->entries[idx] = NULL;
+	}
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+}
+
 void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
 {
 	LIST_HEAD(release);
@@ -546,7 +587,7 @@ void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
 
 	mutex_lock(&slab_mutex);
 	list_for_each_entry_safe(s, s2, &slab_caches, list) {
-		if (is_root_cache(s) || s->memcg_params->memcg != memcg)
+		if (is_root_cache(s) || s->memcg_params.memcg != memcg)
 			continue;
 		/*
 		 * The cgroup is about to be freed and therefore has no charges
@@ -565,18 +606,20 @@ void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
-	memcg_free_cache_params(s);
+	destroy_memcg_params(s);
 	kfree(s->name);
 	kmem_cache_free(kmem_cache, s);
 }
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-	int i;
+	struct kmem_cache *c, *c2;
 	LIST_HEAD(release);
 	bool need_rcu_barrier = false;
 	bool busy = false;
 
+	BUG_ON(!is_root_cache(s));
+
 	get_online_cpus();
 	get_online_mems();
 
@@ -586,10 +629,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (s->refcount)
 		goto out_unlock;
 
-	for_each_memcg_cache_index(i) {
-		struct kmem_cache *c = cache_from_memcg_idx(s, i);
-
-		if (c && do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
+	for_each_memcg_cache_safe(c, c2, s) {
+		if (do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
 			busy = true;
 	}
 
@@ -619,7 +660,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
 
 	get_online_cpus();
 	get_online_mems();
-	ret = __kmem_cache_shrink(cachep);
+	ret = __kmem_cache_shrink(cachep, false);
 	put_online_mems();
 	put_online_cpus();
 	return ret;
@@ -641,6 +682,9 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz
 	s->name = name;
 	s->size = s->object_size = size;
 	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+
+	slab_init_memcg_params(s);
+
 	err = __kmem_cache_create(s, flags);
 
 	if (err)
@@ -920,16 +964,11 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 {
 	struct kmem_cache *c;
 	struct slabinfo sinfo;
-	int i;
 
 	if (!is_root_cache(s))
 		return;
 
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg_idx(s, i);
-		if (!c)
-			continue;
-
+	for_each_memcg_cache(c, s) {
 		memset(&sinfo, 0, sizeof(sinfo));
 		get_slabinfo(c, &sinfo);
 
@@ -981,7 +1020,7 @@ int memcg_slab_show(struct seq_file *m, void *p)
 
 	if (p == slab_caches.next)
 		print_slabinfo_header(m);
-	if (!is_root_cache(s) && s->memcg_params->memcg == memcg)
+	if (!is_root_cache(s) && s->memcg_params.memcg == memcg)
 		cache_show(s, m);
 	return 0;
 }
diff --git a/mm/slob.c b/mm/slob.c
index 96a86206a26b2c..94a7fede6d4878 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -618,7 +618,7 @@ int __kmem_cache_shutdown(struct kmem_cache *c)
 	return 0;
 }
 
-int __kmem_cache_shrink(struct kmem_cache *d)
+int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
 {
 	return 0;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 8b8508adf9c240..06cdb1829dc972 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2007,6 +2007,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 	int pages;
 	int pobjects;
 
+	preempt_disable();
 	do {
 		pages = 0;
 		pobjects = 0;
@@ -2040,6 +2041,14 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page)
 								!= oldpage);
+	if (unlikely(!s->cpu_partial)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
+		local_irq_restore(flags);
+	}
+	preempt_enable();
 #endif
 }
 
@@ -3358,69 +3367,92 @@ void kfree(const void *x)
 }
 EXPORT_SYMBOL(kfree);
 
+#define SHRINK_PROMOTE_MAX 32
+
 /*
- * kmem_cache_shrink removes empty slabs from the partial lists and sorts
- * the remaining slabs by the number of items in use. The slabs with the
- * most items in use come first. New allocations will then fill those up
- * and thus they can be removed from the partial lists.
+ * kmem_cache_shrink discards empty slabs and promotes the slabs filled
+ * up most to the head of the partial lists. New allocations will then
+ * fill those up and thus they can be removed from the partial lists.
  *
  * The slabs with the least items are placed last. This results in them
  * being allocated from last increasing the chance that the last objects
  * are freed in them.
  */
-int __kmem_cache_shrink(struct kmem_cache *s)
+int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
 {
 	int node;
 	int i;
 	struct kmem_cache_node *n;
 	struct page *page;
 	struct page *t;
-	int objects = oo_objects(s->max);
-	struct list_head *slabs_by_inuse =
-		kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL);
+	struct list_head discard;
+	struct list_head promote[SHRINK_PROMOTE_MAX];
 	unsigned long flags;
+	int ret = 0;
 
-	if (!slabs_by_inuse)
-		return -ENOMEM;
+	if (deactivate) {
+		/*
+		 * Disable empty slabs caching. Used to avoid pinning offline
+		 * memory cgroups by kmem pages that can be freed.
+		 */
+		s->cpu_partial = 0;
+		s->min_partial = 0;
+
+		/*
+		 * s->cpu_partial is checked locklessly (see put_cpu_partial),
+		 * so we have to make sure the change is visible.
+		 */
+		kick_all_cpus_sync();
+	}
 
 	flush_all(s);
 	for_each_kmem_cache_node(s, node, n) {
-		if (!n->nr_partial)
-			continue;
-
-		for (i = 0; i < objects; i++)
-			INIT_LIST_HEAD(slabs_by_inuse + i);
+		INIT_LIST_HEAD(&discard);
+		for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
+			INIT_LIST_HEAD(promote + i);
 
 		spin_lock_irqsave(&n->list_lock, flags);
 
 		/*
-		 * Build lists indexed by the items in use in each slab.
+		 * Build lists of slabs to discard or promote.
 		 *
 		 * Note that concurrent frees may occur while we hold the
 		 * list_lock. page->inuse here is the upper limit.
 		 */
 		list_for_each_entry_safe(page, t, &n->partial, lru) {
-			list_move(&page->lru, slabs_by_inuse + page->inuse);
-			if (!page->inuse)
+			int free = page->objects - page->inuse;
+
+			/* Do not reread page->inuse */
+			barrier();
+
+			/* We do not keep full slabs on the list */
+			BUG_ON(free <= 0);
+
+			if (free == page->objects) {
+				list_move(&page->lru, &discard);
 				n->nr_partial--;
+			} else if (free <= SHRINK_PROMOTE_MAX)
+				list_move(&page->lru, promote + free - 1);
 		}
 
 		/*
-		 * Rebuild the partial list with the slabs filled up most
-		 * first and the least used slabs at the end.
+		 * Promote the slabs filled up most to the head of the
+		 * partial list.
 		 */
-		for (i = objects - 1; i > 0; i--)
-			list_splice(slabs_by_inuse + i, n->partial.prev);
+		for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--)
+			list_splice(promote + i, &n->partial);
 
 		spin_unlock_irqrestore(&n->list_lock, flags);
 
 		/* Release empty slabs */
-		list_for_each_entry_safe(page, t, slabs_by_inuse, lru)
+		list_for_each_entry_safe(page, t, &discard, lru)
 			discard_slab(s, page);
+
+		if (slabs_node(s, node))
+			ret = 1;
 	}
 
-	kfree(slabs_by_inuse);
-	return 0;
+	return ret;
 }
 
 static int slab_mem_going_offline_callback(void *arg)
@@ -3429,7 +3461,7 @@ static int slab_mem_going_offline_callback(void *arg)
 
 	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list)
-		__kmem_cache_shrink(s);
+		__kmem_cache_shrink(s, false);
 	mutex_unlock(&slab_mutex);
 
 	return 0;
@@ -3577,6 +3609,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 			p->slab_cache = s;
 #endif
 	}
+	slab_init_memcg_params(s);
 	list_add(&s->list, &slab_caches);
 	return s;
 }
@@ -3635,13 +3668,10 @@ struct kmem_cache *
 __kmem_cache_alias(const char *name, size_t size, size_t align,
 		   unsigned long flags, void (*ctor)(void *))
 {
-	struct kmem_cache *s;
+	struct kmem_cache *s, *c;
 
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
-		int i;
-		struct kmem_cache *c;
-
 		s->refcount++;
 
 		/*
@@ -3651,10 +3681,7 @@ __kmem_cache_alias(const char *name, size_t size, size_t align,
 		s->object_size = max(s->object_size, (int)size);
 		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
 
-		for_each_memcg_cache_index(i) {
-			c = cache_from_memcg_idx(s, i);
-			if (!c)
-				continue;
+		for_each_memcg_cache(c, s) {
 			c->object_size = s->object_size;
 			c->inuse = max_t(int, c->inuse,
 					 ALIGN(size, sizeof(void *)));
@@ -4691,12 +4718,9 @@ static ssize_t shrink_show(struct kmem_cache *s, char *buf)
 static ssize_t shrink_store(struct kmem_cache *s,
 			const char *buf, size_t length)
 {
-	if (buf[0] == '1') {
-		int rc = kmem_cache_shrink(s);
-
-		if (rc)
-			return rc;
-	} else
+	if (buf[0] == '1')
+		kmem_cache_shrink(s);
+	else
 		return -EINVAL;
 	return length;
 }
@@ -4920,7 +4944,7 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 	err = attribute->store(s, buf, len);
 #ifdef CONFIG_MEMCG_KMEM
 	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
-		int i;
+		struct kmem_cache *c;
 
 		mutex_lock(&slab_mutex);
 		if (s->max_attr_size < len)
@@ -4943,11 +4967,8 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		 * directly either failed or succeeded, in which case we loop
 		 * through the descendants with best-effort propagation.
 		 */
-		for_each_memcg_cache_index(i) {
-			struct kmem_cache *c = cache_from_memcg_idx(s, i);
-			if (c)
-				attribute->store(c, buf, len);
-		}
+		for_each_memcg_cache(c, s)
+			attribute->store(c, buf, len);
 		mutex_unlock(&slab_mutex);
 	}
 #endif
@@ -4964,7 +4985,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 	if (is_root_cache(s))
 		return;
 
-	root_cache = s->memcg_params->root_cache;
+	root_cache = s->memcg_params.root_cache;
 
 	/*
 	 * This mean this cache had no attribute written. Therefore, no point
@@ -5044,7 +5065,7 @@ static inline struct kset *cache_kset(struct kmem_cache *s)
 {
 #ifdef CONFIG_MEMCG_KMEM
 	if (!is_root_cache(s))
-		return s->memcg_params->root_cache->memcg_kset;
+		return s->memcg_params.root_cache->memcg_kset;
 #endif
 	return slab_kset;
 }
diff --git a/mm/swap.c b/mm/swap.c
index 5b3087228b99c2..cd3a5e64cea9be 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1138,8 +1138,6 @@ void __init swap_setup(void)
 #ifdef CONFIG_SWAP
 	int i;
 
-	if (bdi_init(swapper_spaces[0].backing_dev_info))
-		panic("Failed to init swap bdi");
 	for (i = 0; i < MAX_SWAPFILES; i++)
 		spin_lock_init(&swapper_spaces[i].tree_lock);
 #endif
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 9711342987a05f..405923f773340c 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -32,17 +32,11 @@ static const struct address_space_operations swap_aops = {
 #endif
 };
 
-static struct backing_dev_info swap_backing_dev_info = {
-	.name		= "swap",
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-};
-
 struct address_space swapper_spaces[MAX_SWAPFILES] = {
 	[0 ... MAX_SWAPFILES - 1] = {
 		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
 		.i_mmap_writable = ATOMIC_INIT(0),
 		.a_ops		= &swap_aops,
-		.backing_dev_info = &swap_backing_dev_info,
 	}
 };
 
diff --git a/mm/truncate.c b/mm/truncate.c
index f1e4d60523694e..ddec5a5966d74a 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -112,7 +112,7 @@ void cancel_dirty_page(struct page *page, unsigned int account_size)
 		struct address_space *mapping = page->mapping;
 		if (mapping && mapping_cap_account_dirty(mapping)) {
 			dec_zone_page_state(page, NR_FILE_DIRTY);
-			dec_bdi_stat(mapping->backing_dev_info,
+			dec_bdi_stat(inode_to_bdi(mapping->host),
 					BDI_RECLAIMABLE);
 			if (account_size)
 				task_io_account_cancelled_write(account_size);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8e645ee5204554..5e8eadd71bac71 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -232,10 +232,10 @@ EXPORT_SYMBOL(unregister_shrinker);
 
 #define SHRINK_BATCH 128
 
-static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
-				  struct shrinker *shrinker,
-				  unsigned long nr_scanned,
-				  unsigned long nr_eligible)
+static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
+				    struct shrinker *shrinker,
+				    unsigned long nr_scanned,
+				    unsigned long nr_eligible)
 {
 	unsigned long freed = 0;
 	unsigned long long delta;
@@ -344,9 +344,10 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
 }
 
 /**
- * shrink_node_slabs - shrink slab caches of a given node
+ * shrink_slab - shrink slab caches
  * @gfp_mask: allocation context
  * @nid: node whose slab caches to target
+ * @memcg: memory cgroup whose slab caches to target
  * @nr_scanned: pressure numerator
  * @nr_eligible: pressure denominator
  *
@@ -355,6 +356,12 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
  * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
  * unaware shrinkers will receive a node id of 0 instead.
  *
+ * @memcg specifies the memory cgroup to target. If it is not NULL,
+ * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan
+ * objects from the memory cgroup specified. Otherwise all shrinkers
+ * are called, and memcg aware shrinkers are supposed to scan the
+ * global list then.
+ *
  * @nr_scanned and @nr_eligible form a ratio that indicate how much of
  * the available objects should be scanned.  Page reclaim for example
  * passes the number of pages scanned and the number of pages on the
@@ -365,13 +372,17 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
  *
  * Returns the number of reclaimed slab objects.
  */
-unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
-				unsigned long nr_scanned,
-				unsigned long nr_eligible)
+static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
+				 struct mem_cgroup *memcg,
+				 unsigned long nr_scanned,
+				 unsigned long nr_eligible)
 {
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
 
+	if (memcg && !memcg_kmem_is_active(memcg))
+		return 0;
+
 	if (nr_scanned == 0)
 		nr_scanned = SWAP_CLUSTER_MAX;
 
@@ -390,12 +401,16 @@ unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
 		struct shrink_control sc = {
 			.gfp_mask = gfp_mask,
 			.nid = nid,
+			.memcg = memcg,
 		};
 
+		if (memcg && !(shrinker->flags & SHRINKER_MEMCG_AWARE))
+			continue;
+
 		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
 			sc.nid = 0;
 
-		freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible);
+		freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
 	}
 
 	up_read(&shrinker_rwsem);
@@ -404,6 +419,29 @@ unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
 	return freed;
 }
 
+void drop_slab_node(int nid)
+{
+	unsigned long freed;
+
+	do {
+		struct mem_cgroup *memcg = NULL;
+
+		freed = 0;
+		do {
+			freed += shrink_slab(GFP_KERNEL, nid, memcg,
+					     1000, 1000);
+		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
+	} while (freed > 10);
+}
+
+void drop_slab(void)
+{
+	int nid;
+
+	for_each_online_node(nid)
+		drop_slab_node(nid);
+}
+
 static inline int is_page_cache_freeable(struct page *page)
 {
 	/*
@@ -500,7 +538,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 	}
 	if (mapping->a_ops->writepage == NULL)
 		return PAGE_ACTIVATE;
-	if (!may_write_to_queue(mapping->backing_dev_info, sc))
+	if (!may_write_to_queue(inode_to_bdi(mapping->host), sc))
 		return PAGE_KEEP;
 
 	if (clear_page_dirty_for_io(page)) {
@@ -879,7 +917,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 */
 		mapping = page_mapping(page);
 		if (((dirty || writeback) && mapping &&
-		     bdi_write_congested(mapping->backing_dev_info)) ||
+		     bdi_write_congested(inode_to_bdi(mapping->host))) ||
 		    (writeback && PageReclaim(page)))
 			nr_congested++;
 
@@ -2276,6 +2314,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
 static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 			bool is_classzone)
 {
+	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long nr_reclaimed, nr_scanned;
 	bool reclaimable = false;
 
@@ -2294,6 +2333,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 		memcg = mem_cgroup_iter(root, NULL, &reclaim);
 		do {
 			unsigned long lru_pages;
+			unsigned long scanned;
 			struct lruvec *lruvec;
 			int swappiness;
 
@@ -2305,10 +2345,16 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 			swappiness = mem_cgroup_swappiness(memcg);
+			scanned = sc->nr_scanned;
 
 			shrink_lruvec(lruvec, swappiness, sc, &lru_pages);
 			zone_lru_pages += lru_pages;
 
+			if (memcg && is_classzone)
+				shrink_slab(sc->gfp_mask, zone_to_nid(zone),
+					    memcg, sc->nr_scanned - scanned,
+					    lru_pages);
+
 			/*
 			 * Direct reclaim and kswapd have to scan all memory
 			 * cgroups to fulfill the overall scan target for the
@@ -2330,19 +2376,14 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 		 * Shrink the slab caches in the same proportion that
 		 * the eligible LRU pages were scanned.
 		 */
-		if (global_reclaim(sc) && is_classzone) {
-			struct reclaim_state *reclaim_state;
-
-			shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone),
-					  sc->nr_scanned - nr_scanned,
-					  zone_lru_pages);
-
-			reclaim_state = current->reclaim_state;
-			if (reclaim_state) {
-				sc->nr_reclaimed +=
-					reclaim_state->reclaimed_slab;
-				reclaim_state->reclaimed_slab = 0;
-			}
+		if (global_reclaim(sc) && is_classzone)
+			shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
+				    sc->nr_scanned - nr_scanned,
+				    zone_lru_pages);
+
+		if (reclaim_state) {
+			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+			reclaim_state->reclaimed_slab = 0;
 		}
 
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
diff --git a/mm/workingset.c b/mm/workingset.c
index f7216fa7da273b..aa017133744b22 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -275,7 +275,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+	shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
 	local_irq_enable();
 
 	pages = node_present_pages(sc->nid);
@@ -302,6 +302,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 }
 
 static enum lru_status shadow_lru_isolate(struct list_head *item,
+					  struct list_lru_one *lru,
 					  spinlock_t *lru_lock,
 					  void *arg)
 {
@@ -332,7 +333,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 		goto out;
 	}
 
-	list_del_init(item);
+	list_lru_isolate(lru, item);
 	spin_unlock(lru_lock);
 
 	/*
@@ -376,8 +377,8 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	ret =  list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
-				  shadow_lru_isolate, NULL, &sc->nr_to_scan);
+	ret =  list_lru_shrink_walk(&workingset_shadow_nodes, sc,
+				    shadow_lru_isolate, NULL);
 	local_irq_enable();
 	return ret;
 }
diff --git a/mm/zbud.c b/mm/zbud.c
index 4e387bea702eca..2ee4e45204936e 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -130,7 +130,8 @@ static struct zbud_ops zbud_zpool_ops = {
 	.evict =	zbud_zpool_evict
 };
 
-static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
+static void *zbud_zpool_create(char *name, gfp_t gfp,
+			struct zpool_ops *zpool_ops)
 {
 	return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL);
 }
diff --git a/mm/zpool.c b/mm/zpool.c
index 739cdf0d183ac0..bacdab6e47de33 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -129,6 +129,7 @@ static void zpool_put_driver(struct zpool_driver *driver)
 /**
  * zpool_create_pool() - Create a new zpool
  * @type	The type of the zpool to create (e.g. zbud, zsmalloc)
+ * @name	The name of the zpool (e.g. zram0, zswap)
  * @gfp		The GFP flags to use when allocating the pool.
  * @ops		The optional ops callback.
  *
@@ -140,7 +141,8 @@ static void zpool_put_driver(struct zpool_driver *driver)
  *
  * Returns: New zpool on success, NULL on failure.
  */
-struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops)
+struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
+		struct zpool_ops *ops)
 {
 	struct zpool_driver *driver;
 	struct zpool *zpool;
@@ -168,7 +170,7 @@ struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops)
 
 	zpool->type = driver->type;
 	zpool->driver = driver;
-	zpool->pool = driver->create(gfp, ops);
+	zpool->pool = driver->create(name, gfp, ops);
 	zpool->ops = ops;
 
 	if (!zpool->pool) {
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b72403927aa4b0..0dec1fa5f6565d 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -91,6 +91,7 @@
 #include <linux/hardirq.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/debugfs.h>
 #include <linux/zsmalloc.h>
 #include <linux/zpool.h>
 
@@ -168,6 +169,22 @@ enum fullness_group {
 	ZS_FULL
 };
 
+enum zs_stat_type {
+	OBJ_ALLOCATED,
+	OBJ_USED,
+	NR_ZS_STAT_TYPE,
+};
+
+#ifdef CONFIG_ZSMALLOC_STAT
+
+static struct dentry *zs_stat_root;
+
+struct zs_size_stat {
+	unsigned long objs[NR_ZS_STAT_TYPE];
+};
+
+#endif
+
 /*
  * number of size_classes
  */
@@ -200,6 +217,10 @@ struct size_class {
 	/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
 	int pages_per_zspage;
 
+#ifdef CONFIG_ZSMALLOC_STAT
+	struct zs_size_stat stats;
+#endif
+
 	spinlock_t lock;
 
 	struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
@@ -217,10 +238,16 @@ struct link_free {
 };
 
 struct zs_pool {
+	char *name;
+
 	struct size_class **size_class;
 
 	gfp_t flags;	/* allocation flags used when growing pool */
 	atomic_long_t pages_allocated;
+
+#ifdef CONFIG_ZSMALLOC_STAT
+	struct dentry *stat_dentry;
+#endif
 };
 
 /*
@@ -246,9 +273,9 @@ struct mapping_area {
 
 #ifdef CONFIG_ZPOOL
 
-static void *zs_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
+static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops)
 {
-	return zs_create_pool(gfp);
+	return zs_create_pool(name, gfp);
 }
 
 static void zs_zpool_destroy(void *pool)
@@ -942,6 +969,166 @@ static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
 	return true;
 }
 
+#ifdef CONFIG_ZSMALLOC_STAT
+
+static inline void zs_stat_inc(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+	class->stats.objs[type] += cnt;
+}
+
+static inline void zs_stat_dec(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+	class->stats.objs[type] -= cnt;
+}
+
+static inline unsigned long zs_stat_get(struct size_class *class,
+				enum zs_stat_type type)
+{
+	return class->stats.objs[type];
+}
+
+static int __init zs_stat_init(void)
+{
+	if (!debugfs_initialized())
+		return -ENODEV;
+
+	zs_stat_root = debugfs_create_dir("zsmalloc", NULL);
+	if (!zs_stat_root)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit zs_stat_exit(void)
+{
+	debugfs_remove_recursive(zs_stat_root);
+}
+
+static int zs_stats_size_show(struct seq_file *s, void *v)
+{
+	int i;
+	struct zs_pool *pool = s->private;
+	struct size_class *class;
+	int objs_per_zspage;
+	unsigned long obj_allocated, obj_used, pages_used;
+	unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0;
+
+	seq_printf(s, " %5s %5s %13s %10s %10s\n", "class", "size",
+				"obj_allocated", "obj_used", "pages_used");
+
+	for (i = 0; i < zs_size_classes; i++) {
+		class = pool->size_class[i];
+
+		if (class->index != i)
+			continue;
+
+		spin_lock(&class->lock);
+		obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
+		obj_used = zs_stat_get(class, OBJ_USED);
+		spin_unlock(&class->lock);
+
+		objs_per_zspage = get_maxobj_per_zspage(class->size,
+				class->pages_per_zspage);
+		pages_used = obj_allocated / objs_per_zspage *
+				class->pages_per_zspage;
+
+		seq_printf(s, " %5u %5u    %10lu %10lu %10lu\n", i,
+			class->size, obj_allocated, obj_used, pages_used);
+
+		total_objs += obj_allocated;
+		total_used_objs += obj_used;
+		total_pages += pages_used;
+	}
+
+	seq_puts(s, "\n");
+	seq_printf(s, " %5s %5s    %10lu %10lu %10lu\n", "Total", "",
+			total_objs, total_used_objs, total_pages);
+
+	return 0;
+}
+
+static int zs_stats_size_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, zs_stats_size_show, inode->i_private);
+}
+
+static const struct file_operations zs_stat_size_ops = {
+	.open           = zs_stats_size_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = single_release,
+};
+
+static int zs_pool_stat_create(char *name, struct zs_pool *pool)
+{
+	struct dentry *entry;
+
+	if (!zs_stat_root)
+		return -ENODEV;
+
+	entry = debugfs_create_dir(name, zs_stat_root);
+	if (!entry) {
+		pr_warn("debugfs dir <%s> creation failed\n", name);
+		return -ENOMEM;
+	}
+	pool->stat_dentry = entry;
+
+	entry = debugfs_create_file("obj_in_classes", S_IFREG | S_IRUGO,
+			pool->stat_dentry, pool, &zs_stat_size_ops);
+	if (!entry) {
+		pr_warn("%s: debugfs file entry <%s> creation failed\n",
+				name, "obj_in_classes");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void zs_pool_stat_destroy(struct zs_pool *pool)
+{
+	debugfs_remove_recursive(pool->stat_dentry);
+}
+
+#else /* CONFIG_ZSMALLOC_STAT */
+
+static inline void zs_stat_inc(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+}
+
+static inline void zs_stat_dec(struct size_class *class,
+				enum zs_stat_type type, unsigned long cnt)
+{
+}
+
+static inline unsigned long zs_stat_get(struct size_class *class,
+				enum zs_stat_type type)
+{
+	return 0;
+}
+
+static int __init zs_stat_init(void)
+{
+	return 0;
+}
+
+static void __exit zs_stat_exit(void)
+{
+}
+
+static inline int zs_pool_stat_create(char *name, struct zs_pool *pool)
+{
+	return 0;
+}
+
+static inline void zs_pool_stat_destroy(struct zs_pool *pool)
+{
+}
+
+#endif
+
 unsigned long zs_get_total_pages(struct zs_pool *pool)
 {
 	return atomic_long_read(&pool->pages_allocated);
@@ -1074,7 +1261,10 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 		set_zspage_mapping(first_page, class->index, ZS_EMPTY);
 		atomic_long_add(class->pages_per_zspage,
 					&pool->pages_allocated);
+
 		spin_lock(&class->lock);
+		zs_stat_inc(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
+				class->size, class->pages_per_zspage));
 	}
 
 	obj = (unsigned long)first_page->freelist;
@@ -1088,6 +1278,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 	kunmap_atomic(vaddr);
 
 	first_page->inuse++;
+	zs_stat_inc(class, OBJ_USED, 1);
 	/* Now move the zspage to another fullness group, if required */
 	fix_fullness_group(pool, first_page);
 	spin_unlock(&class->lock);
@@ -1128,6 +1319,12 @@ void zs_free(struct zs_pool *pool, unsigned long obj)
 
 	first_page->inuse--;
 	fullness = fix_fullness_group(pool, first_page);
+
+	zs_stat_dec(class, OBJ_USED, 1);
+	if (fullness == ZS_EMPTY)
+		zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
+				class->size, class->pages_per_zspage));
+
 	spin_unlock(&class->lock);
 
 	if (fullness == ZS_EMPTY) {
@@ -1148,7 +1345,7 @@ EXPORT_SYMBOL_GPL(zs_free);
  * On success, a pointer to the newly created pool is returned,
  * otherwise NULL.
  */
-struct zs_pool *zs_create_pool(gfp_t flags)
+struct zs_pool *zs_create_pool(char *name, gfp_t flags)
 {
 	int i;
 	struct zs_pool *pool;
@@ -1158,9 +1355,16 @@ struct zs_pool *zs_create_pool(gfp_t flags)
 	if (!pool)
 		return NULL;
 
+	pool->name = kstrdup(name, GFP_KERNEL);
+	if (!pool->name) {
+		kfree(pool);
+		return NULL;
+	}
+
 	pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *),
 			GFP_KERNEL);
 	if (!pool->size_class) {
+		kfree(pool->name);
 		kfree(pool);
 		return NULL;
 	}
@@ -1210,6 +1414,9 @@ struct zs_pool *zs_create_pool(gfp_t flags)
 
 	pool->flags = flags;
 
+	if (zs_pool_stat_create(name, pool))
+		goto err;
+
 	return pool;
 
 err:
@@ -1222,6 +1429,8 @@ void zs_destroy_pool(struct zs_pool *pool)
 {
 	int i;
 
+	zs_pool_stat_destroy(pool);
+
 	for (i = 0; i < zs_size_classes; i++) {
 		int fg;
 		struct size_class *class = pool->size_class[i];
@@ -1242,6 +1451,7 @@ void zs_destroy_pool(struct zs_pool *pool)
 	}
 
 	kfree(pool->size_class);
+	kfree(pool->name);
 	kfree(pool);
 }
 EXPORT_SYMBOL_GPL(zs_destroy_pool);
@@ -1250,17 +1460,30 @@ static int __init zs_init(void)
 {
 	int ret = zs_register_cpu_notifier();
 
-	if (ret) {
-		zs_unregister_cpu_notifier();
-		return ret;
-	}
+	if (ret)
+		goto notifier_fail;
 
 	init_zs_size_classes();
 
 #ifdef CONFIG_ZPOOL
 	zpool_register_driver(&zs_zpool_driver);
 #endif
+
+	ret = zs_stat_init();
+	if (ret) {
+		pr_err("zs stat initialization failed\n");
+		goto stat_fail;
+	}
 	return 0;
+
+stat_fail:
+#ifdef CONFIG_ZPOOL
+	zpool_unregister_driver(&zs_zpool_driver);
+#endif
+notifier_fail:
+	zs_unregister_cpu_notifier();
+
+	return ret;
 }
 
 static void __exit zs_exit(void)
@@ -1269,6 +1492,8 @@ static void __exit zs_exit(void)
 	zpool_unregister_driver(&zs_zpool_driver);
 #endif
 	zs_unregister_cpu_notifier();
+
+	zs_stat_exit();
 }
 
 module_init(zs_init);
diff --git a/mm/zswap.c b/mm/zswap.c
index 0cfce9bc51e494..4249e82ff934d9 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -906,11 +906,12 @@ static int __init init_zswap(void)
 
 	pr_info("loading zswap\n");
 
-	zswap_pool = zpool_create_pool(zswap_zpool_type, gfp, &zswap_zpool_ops);
+	zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
+					&zswap_zpool_ops);
 	if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
 		pr_info("%s zpool not available\n", zswap_zpool_type);
 		zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
-		zswap_pool = zpool_create_pool(zswap_zpool_type, gfp,
+		zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
 					&zswap_zpool_ops);
 	}
 	if (!zswap_pool) {
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index c2a75c6957a183..2379c1b4efb245 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -47,6 +47,10 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 		return;
 
 	percpu_counter_destroy(&cg_proto->sockets_allocated);
+
+	if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
+		static_key_slow_dec(&memcg_socket_limit_enabled);
+
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 91eaef1844c8f0..78974e4d9ad2a3 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -768,8 +768,8 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
 /*
- * Called from a server thread as it's exiting. Caller must hold the BKL or
- * the "service mutex", whichever is appropriate for the service.
+ * Called from a server thread as it's exiting. Caller must hold the "service
+ * mutex" for the service.
  */
 void
 svc_exit_thread(struct svc_rqst *rqstp)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c69358b3cf7f3b..163ac45c36394f 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -42,7 +42,7 @@ static LIST_HEAD(svc_xprt_class_list);
  *	svc_pool->sp_lock protects most of the fields of that pool.
  *	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
  *	when both need to be taken (rare), svc_serv->sv_lock is first.
- *	BKL protects svc_serv->sv_nrthread.
+ *	The "service mutex" protects svc_serv->sv_nrthread.
  *	svc_sock->sk_lock protects the svc_sock->sk_deferred list
  *             and the ->sk_info_authunix cache.
  *
@@ -67,7 +67,6 @@ static LIST_HEAD(svc_xprt_class_list);
  *		  that no other thread will be using the transport or will
  *		  try to set XPT_DEAD.
  */
-
 int svc_reg_xprt_class(struct svc_xprt_class *xcl)
 {
 	struct svc_xprt_class *cl;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 65b146297f5acf..b681855cf97016 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -70,22 +70,6 @@ static u32 *decode_read_list(u32 *va, u32 *vaend)
 	return (u32 *)&ch->rc_position;
 }
 
-/*
- * Determine number of chunks and total bytes in chunk list. The chunk
- * list has already been verified to fit within the RPCRDMA header.
- */
-void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
-			       int *ch_count, int *byte_count)
-{
-	/* compute the number of bytes represented by read chunks */
-	*byte_count = 0;
-	*ch_count = 0;
-	for (; ch->rc_discrim != 0; ch++) {
-		*byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
-		*ch_count = *ch_count + 1;
-	}
-}
-
 /*
  * Decodes a write chunk list. The expected format is as follows:
  *    descrim  : xdr_one
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index e0110270d650cf..f9f13a32ddb828 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -43,7 +43,6 @@
 #include <linux/sunrpc/debug.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/spinlock.h>
-#include <linux/highmem.h>
 #include <asm/unaligned.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
@@ -60,6 +59,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 			       struct svc_rdma_op_ctxt *ctxt,
 			       u32 byte_count)
 {
+	struct rpcrdma_msg *rmsgp;
 	struct page *page;
 	u32 bc;
 	int sge_no;
@@ -82,7 +82,14 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	/* If data remains, store it in the pagelist */
 	rqstp->rq_arg.page_len = bc;
 	rqstp->rq_arg.page_base = 0;
-	rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
+	if (be32_to_cpu(rmsgp->rm_type) == RDMA_NOMSG)
+		rqstp->rq_arg.pages = &rqstp->rq_pages[0];
+	else
+		rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
 	sge_no = 1;
 	while (bc && sge_no < ctxt->count) {
 		page = ctxt->pages[sge_no];
@@ -95,14 +102,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	rqstp->rq_respages = &rqstp->rq_pages[sge_no];
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
-	/* We should never run out of SGE because the limit is defined to
-	 * support the max allowed RPC data length
-	 */
-	BUG_ON(bc && (sge_no == ctxt->count));
-	BUG_ON((rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len)
-	       != byte_count);
-	BUG_ON(rqstp->rq_arg.len != byte_count);
-
 	/* If not all pages were used from the SGL, free the remaining ones */
 	bc = sge_no;
 	while (sge_no < ctxt->count) {
@@ -125,26 +124,16 @@ static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
 		return min_t(int, sge_count, xprt->sc_max_sge);
 }
 
-typedef int (*rdma_reader_fn)(struct svcxprt_rdma *xprt,
-			      struct svc_rqst *rqstp,
-			      struct svc_rdma_op_ctxt *head,
-			      int *page_no,
-			      u32 *page_offset,
-			      u32 rs_handle,
-			      u32 rs_length,
-			      u64 rs_offset,
-			      int last);
-
 /* Issue an RDMA_READ using the local lkey to map the data sink */
-static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
-			       struct svc_rqst *rqstp,
-			       struct svc_rdma_op_ctxt *head,
-			       int *page_no,
-			       u32 *page_offset,
-			       u32 rs_handle,
-			       u32 rs_length,
-			       u64 rs_offset,
-			       int last)
+int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
+			struct svc_rqst *rqstp,
+			struct svc_rdma_op_ctxt *head,
+			int *page_no,
+			u32 *page_offset,
+			u32 rs_handle,
+			u32 rs_length,
+			u64 rs_offset,
+			bool last)
 {
 	struct ib_send_wr read_wr;
 	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
@@ -229,15 +218,15 @@ static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
 }
 
 /* Issue an RDMA_READ using an FRMR to map the data sink */
-static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
-				struct svc_rqst *rqstp,
-				struct svc_rdma_op_ctxt *head,
-				int *page_no,
-				u32 *page_offset,
-				u32 rs_handle,
-				u32 rs_length,
-				u64 rs_offset,
-				int last)
+int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
+			 struct svc_rqst *rqstp,
+			 struct svc_rdma_op_ctxt *head,
+			 int *page_no,
+			 u32 *page_offset,
+			 u32 rs_handle,
+			 u32 rs_length,
+			 u64 rs_offset,
+			 bool last)
 {
 	struct ib_send_wr read_wr;
 	struct ib_send_wr inv_wr;
@@ -365,24 +354,84 @@ static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	return ret;
 }
 
+static unsigned int
+rdma_rcl_chunk_count(struct rpcrdma_read_chunk *ch)
+{
+	unsigned int count;
+
+	for (count = 0; ch->rc_discrim != xdr_zero; ch++)
+		count++;
+	return count;
+}
+
+/* If there was additional inline content, append it to the end of arg.pages.
+ * Tail copy has to be done after the reader function has determined how many
+ * pages are needed for RDMA READ.
+ */
+static int
+rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head,
+	       u32 position, u32 byte_count, u32 page_offset, int page_no)
+{
+	char *srcp, *destp;
+	int ret;
+
+	ret = 0;
+	srcp = head->arg.head[0].iov_base + position;
+	byte_count = head->arg.head[0].iov_len - position;
+	if (byte_count > PAGE_SIZE) {
+		dprintk("svcrdma: large tail unsupported\n");
+		return 0;
+	}
+
+	/* Fit as much of the tail on the current page as possible */
+	if (page_offset != PAGE_SIZE) {
+		destp = page_address(rqstp->rq_arg.pages[page_no]);
+		destp += page_offset;
+		while (byte_count--) {
+			*destp++ = *srcp++;
+			page_offset++;
+			if (page_offset == PAGE_SIZE && byte_count)
+				goto more;
+		}
+		goto done;
+	}
+
+more:
+	/* Fit the rest on the next page */
+	page_no++;
+	destp = page_address(rqstp->rq_arg.pages[page_no]);
+	while (byte_count--)
+		*destp++ = *srcp++;
+
+	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+done:
+	byte_count = head->arg.head[0].iov_len - position;
+	head->arg.page_len += byte_count;
+	head->arg.len += byte_count;
+	head->arg.buflen += byte_count;
+	return 1;
+}
+
 static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			    struct rpcrdma_msg *rmsgp,
 			    struct svc_rqst *rqstp,
 			    struct svc_rdma_op_ctxt *head)
 {
-	int page_no, ch_count, ret;
+	int page_no, ret;
 	struct rpcrdma_read_chunk *ch;
-	u32 page_offset, byte_count;
+	u32 handle, page_offset, byte_count;
+	u32 position;
 	u64 rs_offset;
-	rdma_reader_fn reader;
+	bool last;
 
 	/* If no read list is present, return 0 */
 	ch = svc_rdma_get_read_chunk(rmsgp);
 	if (!ch)
 		return 0;
 
-	svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count);
-	if (ch_count > RPCSVC_MAXPAGES)
+	if (rdma_rcl_chunk_count(ch) > RPCSVC_MAXPAGES)
 		return -EINVAL;
 
 	/* The request is completed when the RDMA_READs complete. The
@@ -391,34 +440,41 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	 */
 	head->arg.head[0] = rqstp->rq_arg.head[0];
 	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->arg.pages = &head->pages[head->count];
 	head->hdr_count = head->count;
 	head->arg.page_base = 0;
 	head->arg.page_len = 0;
 	head->arg.len = rqstp->rq_arg.len;
 	head->arg.buflen = rqstp->rq_arg.buflen;
 
-	/* Use FRMR if supported */
-	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)
-		reader = rdma_read_chunk_frmr;
-	else
-		reader = rdma_read_chunk_lcl;
+	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
+	position = be32_to_cpu(ch->rc_position);
+
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	if (position == 0) {
+		head->arg.pages = &head->pages[0];
+		page_offset = head->byte_len;
+	} else {
+		head->arg.pages = &head->pages[head->count];
+		page_offset = 0;
+	}
 
-	page_no = 0; page_offset = 0;
-	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	     ch->rc_discrim != 0; ch++) {
+	ret = 0;
+	page_no = 0;
+	for (; ch->rc_discrim != xdr_zero; ch++) {
+		if (be32_to_cpu(ch->rc_position) != position)
+			goto err;
 
+		handle = be32_to_cpu(ch->rc_target.rs_handle),
+		byte_count = be32_to_cpu(ch->rc_target.rs_length);
 		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
 				 &rs_offset);
-		byte_count = ntohl(ch->rc_target.rs_length);
 
 		while (byte_count > 0) {
-			ret = reader(xprt, rqstp, head,
-				     &page_no, &page_offset,
-				     ntohl(ch->rc_target.rs_handle),
-				     byte_count, rs_offset,
-				     ((ch+1)->rc_discrim == 0) /* last */
-				     );
+			last = (ch + 1)->rc_discrim == xdr_zero;
+			ret = xprt->sc_reader(xprt, rqstp, head,
+					      &page_no, &page_offset,
+					      handle, byte_count,
+					      rs_offset, last);
 			if (ret < 0)
 				goto err;
 			byte_count -= ret;
@@ -426,7 +482,24 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			head->arg.buflen += ret;
 		}
 	}
+
+	/* Read list may need XDR round-up (see RFC 5666, s. 3.7) */
+	if (page_offset & 3) {
+		u32 pad = 4 - (page_offset & 3);
+
+		head->arg.page_len += pad;
+		head->arg.len += pad;
+		head->arg.buflen += pad;
+		page_offset += pad;
+	}
+
 	ret = 1;
+	if (position && position < head->arg.head[0].iov_len)
+		ret = rdma_copy_tail(rqstp, head, position,
+				     byte_count, page_offset, page_no);
+	head->arg.head[0].iov_len = position;
+	head->position = position;
+
  err:
 	/* Detach arg pages. svc_recv will replenish them */
 	for (page_no = 0;
@@ -436,47 +509,33 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	return ret;
 }
 
-/*
- * To avoid a separate RDMA READ just for a handful of zero bytes,
- * RFC 5666 section 3.7 allows the client to omit the XDR zero pad
- * in chunk lists.
- */
-static void
-rdma_fix_xdr_pad(struct xdr_buf *buf)
-{
-	unsigned int page_len = buf->page_len;
-	unsigned int size = (XDR_QUADLEN(page_len) << 2) - page_len;
-	unsigned int offset, pg_no;
-	char *p;
-
-	if (size == 0)
-		return;
-
-	pg_no = page_len >> PAGE_SHIFT;
-	offset = page_len & ~PAGE_MASK;
-	p = page_address(buf->pages[pg_no]);
-	memset(p + offset, 0, size);
-
-	buf->page_len += size;
-	buf->buflen += size;
-	buf->len += size;
-}
-
 static int rdma_read_complete(struct svc_rqst *rqstp,
 			      struct svc_rdma_op_ctxt *head)
 {
 	int page_no;
 	int ret;
 
-	BUG_ON(!head);
-
 	/* Copy RPC pages */
 	for (page_no = 0; page_no < head->count; page_no++) {
 		put_page(rqstp->rq_pages[page_no]);
 		rqstp->rq_pages[page_no] = head->pages[page_no];
 	}
+
+	/* Adjustments made for RDMA_NOMSG type requests */
+	if (head->position == 0) {
+		if (head->arg.len <= head->sge[0].length) {
+			head->arg.head[0].iov_len = head->arg.len -
+							head->byte_len;
+			head->arg.page_len = 0;
+		} else {
+			head->arg.head[0].iov_len = head->sge[0].length -
+								head->byte_len;
+			head->arg.page_len = head->arg.len -
+						head->sge[0].length;
+		}
+	}
+
 	/* Point rq_arg.pages past header */
-	rdma_fix_xdr_pad(&head->arg);
 	rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count];
 	rqstp->rq_arg.page_len = head->arg.page_len;
 	rqstp->rq_arg.page_base = head->arg.page_base;
@@ -501,8 +560,8 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
 	ret = rqstp->rq_arg.head[0].iov_len
 		+ rqstp->rq_arg.page_len
 		+ rqstp->rq_arg.tail[0].iov_len;
-	dprintk("svcrdma: deferred read ret=%d, rq_arg.len =%d, "
-		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len = %zd\n",
+	dprintk("svcrdma: deferred read ret=%d, rq_arg.len=%u, "
+		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zu\n",
 		ret, rqstp->rq_arg.len,	rqstp->rq_arg.head[0].iov_base,
 		rqstp->rq_arg.head[0].iov_len);
 
@@ -558,7 +617,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	}
 	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p, status=%d\n",
 		ctxt, rdma_xprt, rqstp, ctxt->wc_status);
-	BUG_ON(ctxt->wc_status != IB_WC_SUCCESS);
 	atomic_inc(&rdma_stat_recv);
 
 	/* Build up the XDR from the receive buffers. */
@@ -591,8 +649,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		+ rqstp->rq_arg.tail[0].iov_len;
 	svc_rdma_put_context(ctxt, 0);
  out:
-	dprintk("svcrdma: ret = %d, rq_arg.len =%d, "
-		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len = %zd\n",
+	dprintk("svcrdma: ret=%d, rq_arg.len=%u, "
+		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zd\n",
 		ret, rqstp->rq_arg.len,
 		rqstp->rq_arg.head[0].iov_base,
 		rqstp->rq_arg.head[0].iov_len);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 9f1b50689c0f06..7de33d1af9b6d6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -60,8 +60,11 @@ static int map_xdr(struct svcxprt_rdma *xprt,
 	u32 page_off;
 	int page_no;
 
-	BUG_ON(xdr->len !=
-	       (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len));
+	if (xdr->len !=
+	    (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)) {
+		pr_err("svcrdma: map_xdr: XDR buffer length error\n");
+		return -EIO;
+	}
 
 	/* Skip the first sge, this is for the RPCRDMA header */
 	sge_no = 1;
@@ -150,7 +153,11 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 	int bc;
 	struct svc_rdma_op_ctxt *ctxt;
 
-	BUG_ON(vec->count > RPCSVC_MAXPAGES);
+	if (vec->count > RPCSVC_MAXPAGES) {
+		pr_err("svcrdma: Too many pages (%lu)\n", vec->count);
+		return -EIO;
+	}
+
 	dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, "
 		"write_len=%d, vec->sge=%p, vec->count=%lu\n",
 		rmr, (unsigned long long)to, xdr_off,
@@ -190,7 +197,10 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 		sge_off = 0;
 		sge_no++;
 		xdr_sge_no++;
-		BUG_ON(xdr_sge_no > vec->count);
+		if (xdr_sge_no > vec->count) {
+			pr_err("svcrdma: Too many sges (%d)\n", xdr_sge_no);
+			goto err;
+		}
 		bc -= sge_bytes;
 		if (sge_no == xprt->sc_max_sge)
 			break;
@@ -421,7 +431,10 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
 		ctxt->sge[sge_no].length = sge_bytes;
 	}
-	BUG_ON(byte_count != 0);
+	if (byte_count != 0) {
+		pr_err("svcrdma: Could not map %d bytes\n", byte_count);
+		goto err;
+	}
 
 	/* Save all respages in the ctxt and remove them from the
 	 * respages array. They are our pages until the I/O
@@ -442,7 +455,10 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	}
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
-	BUG_ON(sge_no > rdma->sc_max_sge);
+	if (sge_no > rdma->sc_max_sge) {
+		pr_err("svcrdma: Too many sges (%d)\n", sge_no);
+		goto err;
+	}
 	memset(&send_wr, 0, sizeof send_wr);
 	ctxt->wr_op = IB_WR_SEND;
 	send_wr.wr_id = (unsigned long)ctxt;
@@ -467,18 +483,6 @@ void svc_rdma_prep_reply_hdr(struct svc_rqst *rqstp)
 {
 }
 
-/*
- * Return the start of an xdr buffer.
- */
-static void *xdr_start(struct xdr_buf *xdr)
-{
-	return xdr->head[0].iov_base -
-		(xdr->len -
-		 xdr->page_len -
-		 xdr->tail[0].iov_len -
-		 xdr->head[0].iov_len);
-}
-
 int svc_rdma_sendto(struct svc_rqst *rqstp)
 {
 	struct svc_xprt *xprt = rqstp->rq_xprt;
@@ -496,8 +500,10 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 
 	dprintk("svcrdma: sending response for rqstp=%p\n", rqstp);
 
-	/* Get the RDMA request header. */
-	rdma_argp = xdr_start(&rqstp->rq_arg);
+	/* Get the RDMA request header. The receive logic always
+	 * places this at the start of page 0.
+	 */
+	rdma_argp = page_address(rqstp->rq_pages[0]);
 
 	/* Build an req vec for the XDR */
 	ctxt = svc_rdma_get_context(rdma);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 4e618808bc98d2..f609c1c2d38ddf 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -139,7 +139,6 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
 	struct svcxprt_rdma *xprt;
 	int i;
 
-	BUG_ON(!ctxt);
 	xprt = ctxt->xprt;
 	if (free_pages)
 		for (i = 0; i < ctxt->count; i++)
@@ -339,12 +338,14 @@ static void process_context(struct svcxprt_rdma *xprt,
 
 	switch (ctxt->wr_op) {
 	case IB_WR_SEND:
-		BUG_ON(ctxt->frmr);
+		if (ctxt->frmr)
+			pr_err("svcrdma: SEND: ctxt->frmr != NULL\n");
 		svc_rdma_put_context(ctxt, 1);
 		break;
 
 	case IB_WR_RDMA_WRITE:
-		BUG_ON(ctxt->frmr);
+		if (ctxt->frmr)
+			pr_err("svcrdma: WRITE: ctxt->frmr != NULL\n");
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
@@ -353,19 +354,21 @@ static void process_context(struct svcxprt_rdma *xprt,
 		svc_rdma_put_frmr(xprt, ctxt->frmr);
 		if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) {
 			struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr;
-			BUG_ON(!read_hdr);
-			spin_lock_bh(&xprt->sc_rq_dto_lock);
-			set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
-			list_add_tail(&read_hdr->dto_q,
-				      &xprt->sc_read_complete_q);
-			spin_unlock_bh(&xprt->sc_rq_dto_lock);
+			if (read_hdr) {
+				spin_lock_bh(&xprt->sc_rq_dto_lock);
+				set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
+				list_add_tail(&read_hdr->dto_q,
+					      &xprt->sc_read_complete_q);
+				spin_unlock_bh(&xprt->sc_rq_dto_lock);
+			} else {
+				pr_err("svcrdma: ctxt->read_hdr == NULL\n");
+			}
 			svc_xprt_enqueue(&xprt->sc_xprt);
 		}
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
 	default:
-		BUG_ON(1);
 		printk(KERN_ERR "svcrdma: unexpected completion type, "
 		       "opcode=%d\n",
 		       ctxt->wr_op);
@@ -513,7 +516,10 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
 	buflen = 0;
 	ctxt->direction = DMA_FROM_DEVICE;
 	for (sge_no = 0; buflen < xprt->sc_max_req_size; sge_no++) {
-		BUG_ON(sge_no >= xprt->sc_max_sge);
+		if (sge_no >= xprt->sc_max_sge) {
+			pr_err("svcrdma: Too many sges (%d)\n", sge_no);
+			goto err_put_ctxt;
+		}
 		page = svc_rdma_get_page();
 		ctxt->pages[sge_no] = page;
 		pa = ib_dma_map_page(xprt->sc_cm_id->device,
@@ -687,7 +693,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 {
 	struct rdma_cm_id *listen_id;
 	struct svcxprt_rdma *cma_xprt;
-	struct svc_xprt *xprt;
 	int ret;
 
 	dprintk("svcrdma: Creating RDMA socket\n");
@@ -698,7 +703,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 	cma_xprt = rdma_create_xprt(serv, 1);
 	if (!cma_xprt)
 		return ERR_PTR(-ENOMEM);
-	xprt = &cma_xprt->sc_xprt;
 
 	listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP,
 				   IB_QPT_RC);
@@ -822,7 +826,7 @@ void svc_rdma_put_frmr(struct svcxprt_rdma *rdma,
 	if (frmr) {
 		frmr_unmap_dma(rdma, frmr);
 		spin_lock_bh(&rdma->sc_frmr_q_lock);
-		BUG_ON(!list_empty(&frmr->frmr_list));
+		WARN_ON_ONCE(!list_empty(&frmr->frmr_list));
 		list_add(&frmr->frmr_list, &rdma->sc_frmr_q);
 		spin_unlock_bh(&rdma->sc_frmr_q_lock);
 	}
@@ -970,10 +974,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	 * NB:	iWARP requires remote write access for the data sink
 	 *	of an RDMA_READ. IB does not.
 	 */
+	newxprt->sc_reader = rdma_read_chunk_lcl;
 	if (devattr.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
 		newxprt->sc_frmr_pg_list_len =
 			devattr.max_fast_reg_page_list_len;
 		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
+		newxprt->sc_reader = rdma_read_chunk_frmr;
 	}
 
 	/*
@@ -1125,7 +1131,9 @@ static void __svc_rdma_free(struct work_struct *work)
 	dprintk("svcrdma: svc_rdma_free(%p)\n", rdma);
 
 	/* We should only be called from kref_put */
-	BUG_ON(atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0);
+	if (atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0)
+		pr_err("svcrdma: sc_xprt still in use? (%d)\n",
+		       atomic_read(&rdma->sc_xprt.xpt_ref.refcount));
 
 	/*
 	 * Destroy queued, but not processed read completions. Note
@@ -1153,8 +1161,12 @@ static void __svc_rdma_free(struct work_struct *work)
 	}
 
 	/* Warn if we leaked a resource or under-referenced */
-	WARN_ON(atomic_read(&rdma->sc_ctxt_used) != 0);
-	WARN_ON(atomic_read(&rdma->sc_dma_used) != 0);
+	if (atomic_read(&rdma->sc_ctxt_used) != 0)
+		pr_err("svcrdma: ctxt still in use? (%d)\n",
+		       atomic_read(&rdma->sc_ctxt_used));
+	if (atomic_read(&rdma->sc_dma_used) != 0)
+		pr_err("svcrdma: dma still in use? (%d)\n",
+		       atomic_read(&rdma->sc_dma_used));
 
 	/* De-allocate fastreg mr */
 	rdma_dealloc_frmr_q(rdma);
@@ -1254,7 +1266,6 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
 	if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
 		return -ENOTCONN;
 
-	BUG_ON(wr->send_flags != IB_SEND_SIGNALED);
 	wr_count = 1;
 	for (n_wr = wr->next; n_wr; n_wr = n_wr->next)
 		wr_count++;
diff --git a/security/security.c b/security/security.c
index 18b35c63fc0c80..a0442b20f001b8 100644
--- a/security/security.c
+++ b/security/security.c
@@ -726,16 +726,15 @@ static inline unsigned long mmap_prot(struct file *file, unsigned long prot)
 		return prot | PROT_EXEC;
 	/*
 	 * ditto if it's not on noexec mount, except that on !MMU we need
-	 * BDI_CAP_EXEC_MMAP (== VM_MAYEXEC) in this case
+	 * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case
 	 */
 	if (!(file->f_path.mnt->mnt_flags & MNT_NOEXEC)) {
 #ifndef CONFIG_MMU
-		unsigned long caps = 0;
-		struct address_space *mapping = file->f_mapping;
-		if (mapping && mapping->backing_dev_info)
-			caps = mapping->backing_dev_info->capabilities;
-		if (!(caps & BDI_CAP_EXEC_MAP))
-			return prot;
+		if (file->f_op->mmap_capabilities) {
+			unsigned caps = file->f_op->mmap_capabilities(file);
+			if (!(caps & NOMMU_MAP_EXEC))
+				return prot;
+		}
 #endif
 		return prot | PROT_EXEC;
 	}