Sync up with Linus

.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
 #

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.

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,

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  |

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

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
 ---------------
 

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:

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:

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/*

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)

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;
 

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)

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

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)
 {

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)

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,

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)

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