---

yaml
---
r: 158147
b: refs/heads/master
c: fa08661
h: refs/heads/master
i:
  158145: fe91864
  158143: 9c145e6
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 240ebbf81f149b11a31e060ebe5ee51a3c775360
+refs/heads/master: fa08661af834875c9bd6f7f0b1b9388dc72a6585

trunk/.gitignore

@@ -27,6 +27,7 @@
 *.gz
 *.lzma
 *.patch
+*.gcno
 
 #
 # Top-level generic files

trunk/CREDITS

@@ -1856,7 +1856,7 @@ E: rfkoenig@immd4.informatik.uni-erlangen.de
 D: The Linux Support Team Erlangen
 
 N: Andreas Koensgen
-E: ajk@iehk.rwth-aachen.de
+E: ajk@comnets.uni-bremen.de
 D: 6pack driver for AX.25
 
 N: Harald Koerfgen
@@ -2006,6 +2006,9 @@ E: paul@laufernet.com
 D: Soundblaster driver fixes, ISAPnP quirk
 S: California, USA
 
+N: Jonathan Layes
+D: ARPD support
+
 N: Tom Lees
 E: tom@lpsg.demon.co.uk
 W: http://www.lpsg.demon.co.uk/
@@ -3802,6 +3805,9 @@ S: van Bronckhorststraat 12
 S: 2612 XV Delft
 S: The Netherlands
 
+N: Thomas Woller
+D: CS461x Cirrus Logic sound driver
+
 N: David Woodhouse
 E: dwmw2@infradead.org
 D: JFFS2 file system, Memory Technology Device subsystem,

trunk/Documentation/ABI/testing/sysfs-block

@@ -94,28 +94,37 @@ What:		/sys/block/<disk>/queue/physical_block_size
 Date:		May 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		This is the smallest unit the storage device can write
-		without resorting to read-modify-write operation.  It is
-		usually the same as the logical block size but may be
-		bigger.  One example is SATA drives with 4KB sectors
-		that expose a 512-byte logical block size to the
-		operating system.
+		This is the smallest unit a physical storage device can
+		write atomically.  It is usually the same as the logical
+		block size but may be bigger.  One example is SATA
+		drives with 4KB sectors that expose a 512-byte logical
+		block size to the operating system.  For stacked block
+		devices the physical_block_size variable contains the
+		maximum physical_block_size of the component devices.
 
 What:		/sys/block/<disk>/queue/minimum_io_size
 Date:		April 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		Storage devices may report a preferred minimum I/O size,
-		which is the smallest request the device can perform
-		without incurring a read-modify-write penalty.  For disk
-		drives this is often the physical block size.  For RAID
-		arrays it is often the stripe chunk size.
+		Storage devices may report a granularity or preferred
+		minimum I/O size which is the smallest request the
+		device can perform without incurring a performance
+		penalty.  For disk drives this is often the physical
+		block size.  For RAID arrays it is often the stripe
+		chunk size.  A properly aligned multiple of
+		minimum_io_size is the preferred request size for
+		workloads where a high number of I/O operations is
+		desired.
 
 What:		/sys/block/<disk>/queue/optimal_io_size
 Date:		April 2009
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
 		Storage devices may report an optimal I/O size, which is
-		the device's preferred unit of receiving I/O.  This is
-		rarely reported for disk drives.  For RAID devices it is
-		usually the stripe width or the internal block size.
+		the device's preferred unit for sustained I/O.  This is
+		rarely reported for disk drives.  For RAID arrays it is
+		usually the stripe width or the internal track size.  A
+		properly aligned multiple of optimal_io_size is the
+		preferred request size for workloads where sustained
+		throughput is desired.  If no optimal I/O size is
+		reported this file contains 0.

trunk/Documentation/DocBook/kernel-hacking.tmpl

@@ -449,8 +449,8 @@ printk(KERN_INFO "i = %u\n", i);
    </para>
 
    <programlisting>
-__u32 ipaddress;
-printk(KERN_INFO "my ip: %d.%d.%d.%d\n", NIPQUAD(ipaddress));
+__be32 ipaddress;
+printk(KERN_INFO "my ip: %pI4\n", &amp;ipaddress);
    </programlisting>
 
    <para>

trunk/Documentation/DocBook/mac80211.tmpl

@@ -184,8 +184,6 @@ usage should require reading the full document.
 !Finclude/net/mac80211.h ieee80211_ctstoself_get
 !Finclude/net/mac80211.h ieee80211_ctstoself_duration
 !Finclude/net/mac80211.h ieee80211_generic_frame_duration
-!Finclude/net/mac80211.h ieee80211_get_hdrlen_from_skb
-!Finclude/net/mac80211.h ieee80211_hdrlen
 !Finclude/net/mac80211.h ieee80211_wake_queue
 !Finclude/net/mac80211.h ieee80211_stop_queue
 !Finclude/net/mac80211.h ieee80211_wake_queues

trunk/Documentation/RCU/rculist_nulls.txt

@@ -83,11 +83,12 @@ not detect it missed following items in original chain.
 obj = kmem_cache_alloc(...);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
-atomic_inc(&obj->refcnt);
 /*
  * we need to make sure obj->key is updated before obj->next
+ * or obj->refcnt
  */
 smp_wmb();
+atomic_set(&obj->refcnt, 1);
 hlist_add_head_rcu(&obj->obj_node, list);
 unlock_chain(); // typically a spin_unlock()
 
@@ -159,6 +160,10 @@ out:
 obj = kmem_cache_alloc(cachep);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
+/*
+ * changes to obj->key must be visible before refcnt one
+ */
+smp_wmb();
 atomic_set(&obj->refcnt, 1);
 /*
  * insert obj in RCU way (readers might be traversing chain)

trunk/Documentation/arm/memory.txt

@@ -21,6 +21,8 @@ ffff8000	ffffffff	copy_user_page / clear_user_page use.
 				For SA11xx and Xscale, this is used to
 				setup a minicache mapping.
 
+ffff4000	ffffffff	cache aliasing on ARMv6 and later CPUs.
+
 ffff1000	ffff7fff	Reserved.
 				Platforms must not use this address range.
 

trunk/Documentation/block/data-integrity.txt

@@ -50,7 +50,7 @@ encouraged them to allow separation of the data and integrity metadata
 scatter-gather lists.
 
 The controller will interleave the buffers on write and split them on
-read.  This means that the Linux can DMA the data buffers to and from
+read.  This means that Linux can DMA the data buffers to and from
 host memory without changes to the page cache.
 
 Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs
@@ -66,7 +66,7 @@ software RAID5).
 
 The IP checksum is weaker than the CRC in terms of detecting bit
 errors.  However, the strength is really in the separation of the data
-buffers and the integrity metadata.  These two distinct buffers much
+buffers and the integrity metadata.  These two distinct buffers must
 match up for an I/O to complete.
 
 The separation of the data and integrity metadata buffers as well as

trunk/Documentation/cgroups/cpusets.txt

@@ -777,6 +777,18 @@ in cpuset directories:
 # /bin/echo 1-4 > cpus		-> set cpus list to cpus 1,2,3,4
 # /bin/echo 1,2,3,4 > cpus	-> set cpus list to cpus 1,2,3,4
 
+To add a CPU to a cpuset, write the new list of CPUs including the
+CPU to be added. To add 6 to the above cpuset:
+
+# /bin/echo 1-4,6 > cpus	-> set cpus list to cpus 1,2,3,4,6
+
+Similarly to remove a CPU from a cpuset, write the new list of CPUs
+without the CPU to be removed.
+
+To remove all the CPUs:
+
+# /bin/echo "" > cpus		-> clear cpus list
+
 2.3 Setting flags
 -----------------
 

trunk/Documentation/connector/cn_test.c

@@ -1,7 +1,7 @@
 /*
  * 	cn_test.c
  * 
- * 2004-2005 Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * 2004+ Copyright (c) Evgeniy Polyakov <zbr@ioremap.net>
  * All rights reserved.
  * 
  * This program is free software; you can redistribute it and/or modify
@@ -194,5 +194,5 @@ module_init(cn_test_init);
 module_exit(cn_test_fini);
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Evgeniy Polyakov <johnpol@2ka.mipt.ru>");
+MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>");
 MODULE_DESCRIPTION("Connector's test module");

trunk/Documentation/connector/ucon.c

@@ -1,7 +1,7 @@
 /*
  * 	ucon.c
  *
- * Copyright (c) 2004+ Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * Copyright (c) 2004+ Evgeniy Polyakov <zbr@ioremap.net>
  *
  *
  * This program is free software; you can redistribute it and/or modify

trunk/Documentation/device-mapper/dm-log.txt

@@ -0,0 +1,54 @@
+Device-Mapper Logging
+=====================
+The device-mapper logging code is used by some of the device-mapper
+RAID targets to track regions of the disk that are not consistent.
+A region (or portion of the address space) of the disk may be
+inconsistent because a RAID stripe is currently being operated on or
+a machine died while the region was being altered.  In the case of
+mirrors, a region would be considered dirty/inconsistent while you
+are writing to it because the writes need to be replicated for all
+the legs of the mirror and may not reach the legs at the same time.
+Once all writes are complete, the region is considered clean again.
+
+There is a generic logging interface that the device-mapper RAID
+implementations use to perform logging operations (see
+dm_dirty_log_type in include/linux/dm-dirty-log.h).  Various different
+logging implementations are available and provide different
+capabilities.  The list includes:
+
+Type		Files
+====		=====
+disk		drivers/md/dm-log.c
+core		drivers/md/dm-log.c
+userspace	drivers/md/dm-log-userspace* include/linux/dm-log-userspace.h
+
+The "disk" log type
+-------------------
+This log implementation commits the log state to disk.  This way, the
+logging state survives reboots/crashes.
+
+The "core" log type
+-------------------
+This log implementation keeps the log state in memory.  The log state
+will not survive a reboot or crash, but there may be a small boost in
+performance.  This method can also be used if no storage device is
+available for storing log state.
+
+The "userspace" log type
+------------------------
+This log type simply provides a way to export the log API to userspace,
+so log implementations can be done there.  This is done by forwarding most
+logging requests to userspace, where a daemon receives and processes the
+request.
+
+The structure used for communication between kernel and userspace are
+located in include/linux/dm-log-userspace.h.  Due to the frequency,
+diversity, and 2-way communication nature of the exchanges between
+kernel and userspace, 'connector' is used as the interface for
+communication.
+
+There are currently two userspace log implementations that leverage this
+framework - "clustered_disk" and "clustered_core".  These implementations
+provide a cluster-coherent log for shared-storage.  Device-mapper mirroring
+can be used in a shared-storage environment when the cluster log implementations
+are employed.

trunk/Documentation/device-mapper/dm-queue-length.txt

@@ -0,0 +1,39 @@
+dm-queue-length
+===============
+
+dm-queue-length is a path selector module for device-mapper targets,
+which selects a path with the least number of in-flight I/Os.
+The path selector name is 'queue-length'.
+
+Table parameters for each path: [<repeat_count>]
+	<repeat_count>: The number of I/Os to dispatch using the selected
+			path before switching to the next path.
+			If not given, internal default is used. To check
+			the default value, see the activated table.
+
+Status for each path: <status> <fail-count> <in-flight>
+	<status>: 'A' if the path is active, 'F' if the path is failed.
+	<fail-count>: The number of path failures.
+	<in-flight>: The number of in-flight I/Os on the path.
+
+
+Algorithm
+=========
+
+dm-queue-length increments/decrements 'in-flight' when an I/O is
+dispatched/completed respectively.
+dm-queue-length selects a path with the minimum 'in-flight'.
+
+
+Examples
+========
+In case that 2 paths (sda and sdb) are used with repeat_count == 128.
+
+# echo "0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 1 8:0 A 0 0 8:16 A 0 0

trunk/Documentation/device-mapper/dm-service-time.txt

@@ -0,0 +1,91 @@
+dm-service-time
+===============
+
+dm-service-time is a path selector module for device-mapper targets,
+which selects a path with the shortest estimated service time for
+the incoming I/O.
+
+The service time for each path is estimated by dividing the total size
+of in-flight I/Os on a path with the performance value of the path.
+The performance value is a relative throughput value among all paths
+in a path-group, and it can be specified as a table argument.
+
+The path selector name is 'service-time'.
+
+Table parameters for each path: [<repeat_count> [<relative_throughput>]]
+	<repeat_count>: The number of I/Os to dispatch using the selected
+			path before switching to the next path.
+			If not given, internal default is used.  To check
+			the default value, see the activated table.
+	<relative_throughput>: The relative throughput value of the path
+			among all paths in the path-group.
+			The valid range is 0-100.
+			If not given, minimum value '1' is used.
+			If '0' is given, the path isn't selected while
+			other paths having a positive value are available.
+
+Status for each path: <status> <fail-count> <in-flight-size> \
+		      <relative_throughput>
+	<status>: 'A' if the path is active, 'F' if the path is failed.
+	<fail-count>: The number of path failures.
+	<in-flight-size>: The size of in-flight I/Os on the path.
+	<relative_throughput>: The relative throughput value of the path
+			among all paths in the path-group.
+
+
+Algorithm
+=========
+
+dm-service-time adds the I/O size to 'in-flight-size' when the I/O is
+dispatched and substracts when completed.
+Basically, dm-service-time selects a path having minimum service time
+which is calculated by:
+
+	('in-flight-size' + 'size-of-incoming-io') / 'relative_throughput'
+
+However, some optimizations below are used to reduce the calculation
+as much as possible.
+
+	1. If the paths have the same 'relative_throughput', skip
+	   the division and just compare the 'in-flight-size'.
+
+	2. If the paths have the same 'in-flight-size', skip the division
+	   and just compare the 'relative_throughput'.
+
+	3. If some paths have non-zero 'relative_throughput' and others
+	   have zero 'relative_throughput', ignore those paths with zero
+	   'relative_throughput'.
+
+If such optimizations can't be applied, calculate service time, and
+compare service time.
+If calculated service time is equal, the path having maximum
+'relative_throughput' may be better.  So compare 'relative_throughput'
+then.
+
+
+Examples
+========
+In case that 2 paths (sda and sdb) are used with repeat_count == 128
+and sda has an average throughput 1GB/s and sdb has 4GB/s,
+'relative_throughput' value may be '1' for sda and '4' for sdb.
+
+# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 1 8:16 A 0 0 4
+
+
+Or '2' for sda and '8' for sdb would be also true.
+
+# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 2 8:16 A 0 0 8