Merge branch 'linus' into x86/x2apic

Documentation/ABI/testing/sysfs-block

@@ -26,3 +26,37 @@ Description:
 		I/O statistics of partition <part>. The format is the
 		same as the above-written /sys/block/<disk>/stat
 		format.
+
+
+What:		/sys/block/<disk>/integrity/format
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Metadata format for integrity capable block device.
+		E.g. T10-DIF-TYPE1-CRC.
+
+
+What:		/sys/block/<disk>/integrity/read_verify
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Indicates whether the block layer should verify the
+		integrity of read requests serviced by devices that
+		support sending integrity metadata.
+
+
+What:		/sys/block/<disk>/integrity/tag_size
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Number of bytes of integrity tag space available per
+		512 bytes of data.
+
+
+What:		/sys/block/<disk>/integrity/write_generate
+Date:		June 2008
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Indicates whether the block layer should automatically
+		generate checksums for write requests bound for
+		devices that support receiving integrity metadata.

Documentation/ABI/testing/sysfs-bus-css

+What:		/sys/bus/css/devices/.../type
+Date:		March 2008
+Contact:	Cornelia Huck <cornelia.huck@de.ibm.com>
+		linux-s390@vger.kernel.org
+Description:	Contains the subchannel type, as reported by the hardware.
+		This attribute is present for all subchannel types.
+
+What:		/sys/bus/css/devices/.../modalias
+Date:		March 2008
+Contact:	Cornelia Huck <cornelia.huck@de.ibm.com>
+		linux-s390@vger.kernel.org
+Description:	Contains the module alias as reported with uevents.
+		It is of the format css:t<type> and present for all
+		subchannel types.
+
+What:		/sys/bus/css/drivers/io_subchannel/.../chpids
+Date:		December 2002
+Contact:	Cornelia Huck <cornelia.huck@de.ibm.com>
+		linux-s390@vger.kernel.org
+Description:	Contains the ids of the channel paths used by this
+		subchannel, as reported by the channel subsystem
+		during subchannel recognition.
+		Note: This is an I/O-subchannel specific attribute.
+Users:		s390-tools, HAL
+
+What:		/sys/bus/css/drivers/io_subchannel/.../pimpampom
+Date:		December 2002
+Contact:	Cornelia Huck <cornelia.huck@de.ibm.com>
+		linux-s390@vger.kernel.org
+Description:	Contains the PIM/PAM/POM values, as reported by the
+		channel subsystem when last queried by the common I/O
+		layer (this implies that this attribute is not neccessarily
+		in sync with the values current in the channel subsystem).
+		Note: This is an I/O-subchannel specific attribute.
+Users:		s390-tools, HAL

Documentation/ABI/testing/sysfs-firmware-acpi

@@ -29,46 +29,46 @@ Description:
 
 		$ cd /sys/firmware/acpi/interrupts
 		$ grep . *
-		error:0
-		ff_gbl_lock:0
-		ff_pmtimer:0
-		ff_pwr_btn:0
-		ff_rt_clk:0
-		ff_slp_btn:0
-		gpe00:0
-		gpe01:0
-		gpe02:0
-		gpe03:0
-		gpe04:0
-		gpe05:0
-		gpe06:0
-		gpe07:0
-		gpe08:0
-		gpe09:174
-		gpe0A:0
-		gpe0B:0
-		gpe0C:0
-		gpe0D:0
-		gpe0E:0
-		gpe0F:0
-		gpe10:0
-		gpe11:60
-		gpe12:0
-		gpe13:0
-		gpe14:0
-		gpe15:0
-		gpe16:0
-		gpe17:0
-		gpe18:0
-		gpe19:7
-		gpe1A:0
-		gpe1B:0
-		gpe1C:0
-		gpe1D:0
-		gpe1E:0
-		gpe1F:0
-		gpe_all:241
-		sci:241
+		error:	     0
+		ff_gbl_lock:	   0   enable
+		ff_pmtimer:	  0  invalid
+		ff_pwr_btn:	  0   enable
+		ff_rt_clk:	 2  disable
+		ff_slp_btn:	  0  invalid
+		gpe00:	     0	invalid
+		gpe01:	     0	 enable
+		gpe02:	   108	 enable
+		gpe03:	     0	invalid
+		gpe04:	     0	invalid
+		gpe05:	     0	invalid
+		gpe06:	     0	 enable
+		gpe07:	     0	 enable
+		gpe08:	     0	invalid
+		gpe09:	     0	invalid
+		gpe0A:	     0	invalid
+		gpe0B:	     0	invalid
+		gpe0C:	     0	invalid
+		gpe0D:	     0	invalid
+		gpe0E:	     0	invalid
+		gpe0F:	     0	invalid
+		gpe10:	     0	invalid
+		gpe11:	     0	invalid
+		gpe12:	     0	invalid
+		gpe13:	     0	invalid
+		gpe14:	     0	invalid
+		gpe15:	     0	invalid
+		gpe16:	     0	invalid
+		gpe17:	  1084	 enable
+		gpe18:	     0	 enable
+		gpe19:	     0	invalid
+		gpe1A:	     0	invalid
+		gpe1B:	     0	invalid
+		gpe1C:	     0	invalid
+		gpe1D:	     0	invalid
+		gpe1E:	     0	invalid
+		gpe1F:	     0	invalid
+		gpe_all:    1192
+		sci:	1194
 
 		sci - The total number of times the ACPI SCI
 		has claimed an interrupt.
@@ -89,6 +89,13 @@ Description:
 
 		error - an interrupt that can't be accounted for above.
 
+		invalid: it's either a wakeup GPE or a GPE/Fixed Event that
+			doesn't have an event handler.
+
+		disable: the GPE/Fixed Event is valid but disabled.
+
+		enable: the GPE/Fixed Event is valid and enabled.
+
 		Root has permission to clear any of these counters.  Eg.
 		# echo 0 > gpe11
 
@@ -97,3 +104,43 @@ Description:
 
 		None of these counters has an effect on the function
 		of the system, they are simply statistics.
+
+		Besides this, user can also write specific strings to these files
+		to enable/disable/clear ACPI interrupts in user space, which can be
+		used to debug some ACPI interrupt storm issues.
+
+		Note that only writting to VALID GPE/Fixed Event is allowed,
+		i.e. user can only change the status of runtime GPE and
+		Fixed Event with event handler installed.
+
+		Let's take power button fixed event for example, please kill acpid
+		and other user space applications so that the machine won't shutdown
+		when pressing the power button.
+		# cat ff_pwr_btn
+		0
+		# press the power button for 3 times;
+		# cat ff_pwr_btn
+		3
+		# echo disable > ff_pwr_btn
+		# cat ff_pwr_btn
+		disable
+		# press the power button for 3 times;
+		# cat ff_pwr_btn
+		disable
+		# echo enable > ff_pwr_btn
+		# cat ff_pwr_btn
+		4
+		/*
+		 * this is because the status bit is set even if the enable bit is cleared,
+		 * and it triggers an ACPI fixed event when the enable bit is set again
+		 */
+		# press the power button for 3 times;
+		# cat ff_pwr_btn
+		7
+		# echo disable > ff_pwr_btn
+		# press the power button for 3 times;
+		# echo clear > ff_pwr_btn	/* clear the status bit */
+		# echo disable > ff_pwr_btn
+		# cat ff_pwr_btn
+		7
+

Documentation/HOWTO

@@ -377,7 +377,7 @@ Bug Reporting
 bugzilla.kernel.org is where the Linux kernel developers track kernel
 bugs.  Users are encouraged to report all bugs that they find in this
 tool.  For details on how to use the kernel bugzilla, please see:
-	http://test.kernel.org/bugzilla/faq.html
+	http://bugzilla.kernel.org/page.cgi?id=faq.html
 
 The file REPORTING-BUGS in the main kernel source directory has a good
 template for how to report a possible kernel bug, and details what kind

Documentation/IRQ-affinity.txt

+ChangeLog:
+	Started by Ingo Molnar <mingo@redhat.com>
+	Update by Max Krasnyansky <maxk@qualcomm.com>
 
-SMP IRQ affinity, started by Ingo Molnar <mingo@redhat.com>
-
+SMP IRQ affinity
 
 /proc/irq/IRQ#/smp_affinity specifies which target CPUs are permitted
 for a given IRQ source. It's a bitmask of allowed CPUs. It's not allowed
 to turn off all CPUs, and if an IRQ controller does not support IRQ
 affinity then the value will not change from the default 0xffffffff.
 
+/proc/irq/default_smp_affinity specifies default affinity mask that applies
+to all non-active IRQs. Once IRQ is allocated/activated its affinity bitmask
+will be set to the default mask. It can then be changed as described above.
+Default mask is 0xffffffff.
+
 Here is an example of restricting IRQ44 (eth1) to CPU0-3 then restricting
-the IRQ to CPU4-7 (this is an 8-CPU SMP box):
+it to CPU4-7 (this is an 8-CPU SMP box):
 
+[root@moon 44]# cd /proc/irq/44
 [root@moon 44]# cat smp_affinity
 ffffffff
+
 [root@moon 44]# echo 0f > smp_affinity
 [root@moon 44]# cat smp_affinity
 0000000f
@@ -21,17 +30,27 @@ PING hell (195.4.7.3): 56 data bytes
 --- hell ping statistics ---
 6029 packets transmitted, 6027 packets received, 0% packet loss
 round-trip min/avg/max = 0.1/0.1/0.4 ms
-[root@moon 44]# cat /proc/interrupts | grep 44:
- 44:          0       1785       1785       1783       1783          1
-1          0   IO-APIC-level  eth1
+[root@moon 44]# cat /proc/interrupts | grep 'CPU\|44:'
+           CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
+ 44:       1068       1785       1785       1783         0          0           0         0    IO-APIC-level  eth1
+
+As can be seen from the line above IRQ44 was delivered only to the first four
+processors (0-3).
+Now lets restrict that IRQ to CPU(4-7).
+
 [root@moon 44]# echo f0 > smp_affinity
+[root@moon 44]# cat smp_affinity
+000000f0
 [root@moon 44]# ping -f h
 PING hell (195.4.7.3): 56 data bytes
 ..
 --- hell ping statistics ---
 2779 packets transmitted, 2777 packets received, 0% packet loss
 round-trip min/avg/max = 0.1/0.5/585.4 ms
-[root@moon 44]# cat /proc/interrupts | grep 44:
- 44:       1068       1785       1785       1784       1784       1069       1070       1069   IO-APIC-level  eth1
-[root@moon 44]#
+[root@moon 44]# cat /proc/interrupts |  'CPU\|44:'
+           CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
+ 44:       1068       1785       1785       1783      1784       1069        1070       1069   IO-APIC-level  eth1
+
+This time around IRQ44 was delivered only to the last four processors.
+i.e counters for the CPU0-3 did not change.
 

Documentation/RCU/NMI-RCU.txt

@@ -93,6 +93,9 @@ Since NMI handlers disable preemption, synchronize_sched() is guaranteed
 not to return until all ongoing NMI handlers exit.  It is therefore safe
 to free up the handler's data as soon as synchronize_sched() returns.
 
+Important note: for this to work, the architecture in question must
+invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
+
 
 Answer to Quick Quiz
 

Documentation/RCU/RTFP.txt

@@ -52,6 +52,10 @@ of each iteration.  Unfortunately, chaotic relaxation requires highly
 structured data, such as the matrices used in scientific programs, and
 is thus inapplicable to most data structures in operating-system kernels.
 
+In 1992, Henry (now Alexia) Massalin completed a dissertation advising
+parallel programmers to defer processing when feasible to simplify
+synchronization.  RCU makes extremely heavy use of this advice.
+
 In 1993, Jacobson [Jacobson93] verbally described what is perhaps the
 simplest deferred-free technique: simply waiting a fixed amount of time
 before freeing blocks awaiting deferred free.  Jacobson did not describe
@@ -138,6 +142,13 @@ blocking in read-side critical sections appeared [PaulEMcKenney2006c],
 Robert Olsson described an RCU-protected trie-hash combination
 [RobertOlsson2006a].
 
+2007 saw the journal version of the award-winning RCU paper from 2006
+[ThomasEHart2007a], as well as a paper demonstrating use of Promela
+and Spin to mechanically verify an optimization to Oleg Nesterov's
+QRCU [PaulEMcKenney2007QRCUspin], a design document describing
+preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part
+LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally,
+PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI].
 
 Bibtex Entries
 
@@ -202,6 +213,20 @@ Bibtex Entries
 ,Year="1991"
 }
 
+@phdthesis{HMassalinPhD
+,author="H. Massalin"
+,title="Synthesis: An Efficient Implementation of Fundamental Operating
+System Services"
+,school="Columbia University"
+,address="New York, NY"
+,year="1992"
+,annotation="
+	Mondo optimizing compiler.
+	Wait-free stuff.
+	Good advice: defer work to avoid synchronization.
+"
+}
+
 @unpublished{Jacobson93
 ,author="Van Jacobson"
 ,title="Avoid Read-Side Locking Via Delayed Free"
@@ -635,3 +660,86 @@ Revised:
 "
 }
 
+@unpublished{PaulEMcKenney2007PreemptibleRCU
+,Author="Paul E. McKenney"
+,Title="The design of preemptible read-copy-update"
+,month="October"
+,day="8"
+,year="2007"
+,note="Available:
+\url{http://lwn.net/Articles/253651/}
+[Viewed October 25, 2007]"
+,annotation="
+	LWN article describing the design of preemptible RCU.
+"
+}
+
+########################################################################
+#
+#	"What is RCU?" LWN series.
+#
+
+@unpublished{PaulEMcKenney2007WhatIsRCUFundamentally
+,Author="Paul E. McKenney and Jonathan Walpole"
+,Title="What is {RCU}, Fundamentally?"
+,month="December"
+,day="17"
+,year="2007"
+,note="Available:
+\url{http://lwn.net/Articles/262464/}
+[Viewed December 27, 2007]"
+,annotation="
+	Lays out the three basic components of RCU: (1) publish-subscribe,
+	(2) wait for pre-existing readers to complete, and (2) maintain
+	multiple versions.
+"
+}
+
+@unpublished{PaulEMcKenney2008WhatIsRCUUsage
+,Author="Paul E. McKenney"
+,Title="What is {RCU}? Part 2: Usage"
+,month="January"
+,day="4"
+,year="2008"
+,note="Available:
+\url{http://lwn.net/Articles/263130/}
+[Viewed January 4, 2008]"
+,annotation="
+	Lays out six uses of RCU:
+	1. RCU is a Reader-Writer Lock Replacement
+	2. RCU is a Restricted Reference-Counting Mechanism
+	3. RCU is a Bulk Reference-Counting Mechanism
+	4. RCU is a Poor Man's Garbage Collector
+	5. RCU is a Way of Providing Existence Guarantees
+	6. RCU is a Way of Waiting for Things to Finish 
+"
+}
+
+@unpublished{PaulEMcKenney2008WhatIsRCUAPI
+,Author="Paul E. McKenney"
+,Title="{RCU} part 3: the {RCU} {API}"
+,month="January"
+,day="17"
+,year="2008"
+,note="Available:
+\url{http://lwn.net/Articles/264090/}
+[Viewed January 10, 2008]"
+,annotation="
+	Gives an overview of the Linux-kernel RCU API and a brief annotated RCU
+	bibliography.
+"
+}
+
+@article{DinakarGuniguntala2008IBMSysJ
+,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
+,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
+,Year="2008"
+,Month="April"
+,journal="IBM Systems Journal"
+,volume="47"
+,number="2"
+,pages="@@-@@"
+,annotation="
+	RCU, realtime RCU, sleepable RCU, performance.
+"
+}

Documentation/RCU/checklist.txt

@@ -13,10 +13,13 @@ over a rather long period of time, but improvements are always welcome!
 	detailed performance measurements show that RCU is nonetheless
 	the right tool for the job.
 
-	The other exception would be where performance is not an issue,
-	and RCU provides a simpler implementation.  An example of this
-	situation is the dynamic NMI code in the Linux 2.6 kernel,
-	at least on architectures where NMIs are rare.
+	Another exception is where performance is not an issue, and RCU
+	provides a simpler implementation.  An example of this situation
+	is the dynamic NMI code in the Linux 2.6 kernel, at least on
+	architectures where NMIs are rare.
+
+	Yet another exception is where the low real-time latency of RCU's
+	read-side primitives is critically important.
 
 1.	Does the update code have proper mutual exclusion?
 
@@ -39,9 +42,10 @@ over a rather long period of time, but improvements are always welcome!
 
 2.	Do the RCU read-side critical sections make proper use of
 	rcu_read_lock() and friends?  These primitives are needed
-	to suppress preemption (or bottom halves, in the case of
-	rcu_read_lock_bh()) in the read-side critical sections,
-	and are also an excellent aid to readability.
+	to prevent grace periods from ending prematurely, which
+	could result in data being unceremoniously freed out from
+	under your read-side code, which can greatly increase the
+	actuarial risk of your kernel.
 
 	As a rough rule of thumb, any dereference of an RCU-protected
 	pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
@@ -54,15 +58,30 @@ over a rather long period of time, but improvements are always welcome!
 	be running while updates are in progress.  There are a number
 	of ways to handle this concurrency, depending on the situation:
 
-	a.	Make updates appear atomic to readers.  For example,
+	a.	Use the RCU variants of the list and hlist update
+		primitives to add, remove, and replace elements on an
+		RCU-protected list.  Alternatively, use the RCU-protected
+		trees that have been added to the Linux kernel.
+
+		This is almost always the best approach.
+
+	b.	Proceed as in (a) above, but also maintain per-element
+		locks (that are acquired by both readers and writers)
+		that guard per-element state.  Of course, fields that
+		the readers refrain from accessing can be guarded by the
+		update-side lock.
+
+		This works quite well, also.
+
+	c.	Make updates appear atomic to readers.  For example,
 		pointer updates to properly aligned fields will appear
 		atomic, as will individual atomic primitives.  Operations
 		performed under a lock and sequences of multiple atomic
 		primitives will -not- appear to be atomic.
 
-		This is almost always the best approach.
+		This can work, but is starting to get a bit tricky.
 
-	b.	Carefully order the updates and the reads so that
+	d.	Carefully order the updates and the reads so that
 		readers see valid data at all phases of the update.
 		This is often more difficult than it sounds, especially
 		given modern CPUs' tendency to reorder memory references.
@@ -123,18 +142,22 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
-	is used, the callback function must be written to be called
-	from softirq context.  In particular, it cannot block.
+5.	If call_rcu(), or a related primitive such as call_rcu_bh() or
+	call_rcu_sched(), is used, the callback function must be
+	written to be called from softirq context.  In particular,
+	it cannot block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.
+	any sort of irq context.  Ditto for synchronize_sched() and
+	synchronize_srcu().
 
 7.	If the updater uses call_rcu(), then the corresponding readers
 	must use rcu_read_lock() and rcu_read_unlock().  If the updater
 	uses call_rcu_bh(), then the corresponding readers must use
-	rcu_read_lock_bh() and rcu_read_unlock_bh().  Mixing things up
-	will result in confusion and broken kernels.
+	rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
+	uses call_rcu_sched(), then the corresponding readers must
+	disable preemption.  Mixing things up will result in confusion
+	and broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -143,9 +166,9 @@ over a rather long period of time, but improvements are always welcome!
 	such cases is a must, of course!  And the jury is still out on
 	whether the increased speed is worth it.
 
-8.	Although synchronize_rcu() is a bit slower than is call_rcu(),
-	it usually results in simpler code.  So, unless update
-	performance is critically important or the updaters cannot block,
+8.	Although synchronize_rcu() is slower than is call_rcu(), it
+	usually results in simpler code.  So, unless update performance
+	is critically important or the updaters cannot block,
 	synchronize_rcu() should be used in preference to call_rcu().
 
 	An especially important property of the synchronize_rcu()
@@ -187,23 +210,23 @@ over a rather long period of time, but improvements are always welcome!
 		number of updates per grace period.
 
 9.	All RCU list-traversal primitives, which include
-	list_for_each_rcu(), list_for_each_entry_rcu(),
+	rcu_dereference(), list_for_each_rcu(), list_for_each_entry_rcu(),
 	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
-	must be within an RCU read-side critical section.  RCU
+	must be either within an RCU read-side critical section or
+	must be protected by appropriate update-side locks.  RCU
 	read-side critical sections are delimited by rcu_read_lock()
 	and rcu_read_unlock(), or by similar primitives such as
 	rcu_read_lock_bh() and rcu_read_unlock_bh().
 
-	Use of the _rcu() list-traversal primitives outside of an
-	RCU read-side critical section causes no harm other than
-	a slight performance degradation on Alpha CPUs.  It can
-	also be quite helpful in reducing code bloat when common
-	code is shared between readers and updaters.
+	The reason that it is permissible to use RCU list-traversal
+	primitives when the update-side lock is held is that doing so
+	can be quite helpful in reducing code bloat when common code is
+	shared between readers and updaters.
 
 10.	Conversely, if you are in an RCU read-side critical section,
-	you -must- use the "_rcu()" variants of the list macros.
-	Failing to do so will break Alpha and confuse people reading
-	your code.
+	and you don't hold the appropriate update-side lock, you -must-
+	use the "_rcu()" variants of the list macros.  Failing to do so
+	will break Alpha and confuse people reading your code.
 
 11.	Note that synchronize_rcu() -only- guarantees to wait until
 	all currently executing rcu_read_lock()-protected RCU read-side
@@ -230,6 +253,14 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
+	RCU callbacks are -usually- executed on the same CPU that executed
+	the corresponding call_rcu(), call_rcu_bh(), or call_rcu_sched(),
+	but are by -no- means guaranteed to be.  For example, if a given
+	CPU goes offline while having an RCU callback pending, then that
+	RCU callback will execute on some surviving CPU.  (If this was
+	not the case, a self-spawning RCU callback would prevent the
+	victim CPU from ever going offline.)
+
 14.	SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
 	may only be invoked from process context.  Unlike other forms of
 	RCU, it -is- permissible to block in an SRCU read-side critical

Documentation/RCU/torture.txt

@@ -10,23 +10,30 @@ status messages via printk(), which can be examined via the dmesg
 command (perhaps grepping for "torture").  The test is started
 when the module is loaded, and stops when the module is unloaded.
 
-However, actually setting this config option to "y" results in the system
-running the test immediately upon boot, and ending only when the system
-is taken down.  Normally, one will instead want to build the system
-with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
-the test, perhaps using a script similar to the one shown at the end of
-this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
-to be able to end the test.
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
+result in the tests being loaded into the base kernel.  In this case,
+the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
+whether the RCU torture tests are to be started immediately during
+boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
+to enable them.  This /proc file can be used to repeatedly pause and
+restart the tests, regardless of the initial state specified by the
+CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
+
+You will normally -not- want to start the RCU torture tests during boot
+(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
+this can sometimes be useful in finding boot-time bugs.
 
 
 MODULE PARAMETERS
 
 This module has the following parameters:
 
-nreaders	This is the number of RCU reading threads supported.
-		The default is twice the number of CPUs.  Why twice?
-		To properly exercise RCU implementations with preemptible
-		read-side critical sections.
+irqreaders	Says to invoke RCU readers from irq level.  This is currently
+		done via timers.  Defaults to "1" for variants of RCU that
+		permit this.  (Or, more accurately, variants of RCU that do
+		-not- permit this know to ignore this variable.)
 
 nfakewriters	This is the number of RCU fake writer threads to run.  Fake
 		writer threads repeatedly use the synchronous "wait for
@@ -37,6 +44,16 @@ nfakewriters	This is the number of RCU fake writer threads to run.  Fake
 		to trigger special cases caused by multiple writers, such as
 		the synchronize_srcu() early return optimization.
 
+nreaders	This is the number of RCU reading threads supported.
+		The default is twice the number of CPUs.  Why twice?
+		To properly exercise RCU implementations with preemptible
+		read-side critical sections.
+
+shuffle_interval
+		The number of seconds to keep the test threads affinitied
+		to a particular subset of the CPUs, defaults to 3 seconds.
+		Used in conjunction with test_no_idle_hz.
+
 stat_interval	The number of seconds between output of torture
 		statistics (via printk()).  Regardless of the interval,
 		statistics are printed when the module is unloaded.
@@ -44,10 +61,11 @@ stat_interval	The number of seconds between output of torture
 		be printed -only- when the module is unloaded, and this
 		is the default.
 
-shuffle_interval
-		The number of seconds to keep the test threads affinitied
-		to a particular subset of the CPUs, defaults to 5 seconds.
-		Used in conjunction with test_no_idle_hz.
+stutter		The length of time to run the test before pausing for this
+		same period of time.  Defaults to "stutter=5", so as
+		to run and pause for (roughly) five-second intervals.
+		Specifying "stutter=0" causes the test to run continuously
+		without pausing, which is the old default behavior.
 
 test_no_idle_hz	Whether or not to test the ability of RCU to operate in
 		a kernel that disables the scheduling-clock interrupt to

Documentation/RCU/whatisRCU.txt

+Please note that the "What is RCU?" LWN series is an excellent place
+to start learning about RCU:
+
+1.	What is RCU, Fundamentally?  http://lwn.net/Articles/262464/
+2.	What is RCU? Part 2: Usage   http://lwn.net/Articles/263130/
+3.	RCU part 3: the RCU API      http://lwn.net/Articles/264090/
+
+
 What is RCU?
 
 RCU is a synchronization mechanism that was added to the Linux kernel
@@ -772,26 +780,18 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
 
-Markers for RCU read-side critical sections:
-
-	rcu_read_lock
-	rcu_read_unlock
-	rcu_read_lock_bh
-	rcu_read_unlock_bh
-	srcu_read_lock
-	srcu_read_unlock
-
 RCU pointer/list traversal:
 
 	rcu_dereference
+	list_for_each_entry_rcu
+	hlist_for_each_entry_rcu
+
 	list_for_each_rcu		(to be deprecated in favor of
 					 list_for_each_entry_rcu)
-	list_for_each_entry_rcu
 	list_for_each_continue_rcu	(to be deprecated in favor of new
 					 list_for_each_entry_continue_rcu)
-	hlist_for_each_entry_rcu
 
-RCU pointer update:
+RCU pointer/list update:
 
 	rcu_assign_pointer
 	list_add_rcu
@@ -799,16 +799,36 @@ RCU pointer update:
 	list_del_rcu
 	list_replace_rcu
 	hlist_del_rcu
+	hlist_add_after_rcu
+	hlist_add_before_rcu
 	hlist_add_head_rcu
+	hlist_replace_rcu
+	list_splice_init_rcu()
 
-RCU grace period:
+RCU:	Critical sections	Grace period		Barrier
 
-	synchronize_net
-	synchronize_sched
-	synchronize_rcu
-	synchronize_srcu
+	rcu_read_lock		synchronize_net		rcu_barrier
+	rcu_read_unlock		synchronize_rcu
 				call_rcu
-	call_rcu_bh
+
+
+bh:	Critical sections	Grace period		Barrier
+
+	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
+	rcu_read_unlock_bh
+
+
+sched:	Critical sections	Grace period		Barrier
+
+	[preempt_disable]	synchronize_sched	rcu_barrier_sched
+	[and friends]		call_rcu_sched
+
+
+SRCU:	Critical sections	Grace period		Barrier
+
+	srcu_read_lock		synchronize_srcu	N/A
+	srcu_read_unlock
+
 
 See the comment headers in the source code (or the docbook generated
 from them) for more information.

Documentation/block/data-integrity.txt

+----------------------------------------------------------------------
+1. INTRODUCTION
+
+Modern filesystems feature checksumming of data and metadata to
+protect against data corruption.  However, the detection of the
+corruption is done at read time which could potentially be months
+after the data was written.  At that point the original data that the
+application tried to write is most likely lost.
+
+The solution is to ensure that the disk is actually storing what the
+application meant it to.  Recent additions to both the SCSI family
+protocols (SBC Data Integrity Field, SCC protection proposal) as well
+as SATA/T13 (External Path Protection) try to remedy this by adding
+support for appending integrity metadata to an I/O.  The integrity
+metadata (or protection information in SCSI terminology) includes a
+checksum for each sector as well as an incrementing counter that
+ensures the individual sectors are written in the right order.  And
+for some protection schemes also that the I/O is written to the right
+place on disk.
+
+Current storage controllers and devices implement various protective
+measures, for instance checksumming and scrubbing.  But these
+technologies are working in their own isolated domains or at best
+between adjacent nodes in the I/O path.  The interesting thing about
+DIF and the other integrity extensions is that the protection format
+is well defined and every node in the I/O path can verify the
+integrity of the I/O and reject it if corruption is detected.  This
+allows not only corruption prevention but also isolation of the point
+of failure.
+
+----------------------------------------------------------------------
+2. THE DATA INTEGRITY EXTENSIONS
+
+As written, the protocol extensions only protect the path between
+controller and storage device.  However, many controllers actually
+allow the operating system to interact with the integrity metadata
+(IMD).  We have been working with several FC/SAS HBA vendors to enable
+the protection information to be transferred to and from their
+controllers.
+
+The SCSI Data Integrity Field works by appending 8 bytes of protection
+information to each sector.  The data + integrity metadata is stored
+in 520 byte sectors on disk.  Data + IMD are interleaved when
+transferred between the controller and target.  The T13 proposal is
+similar.
+
+Because it is highly inconvenient for operating systems to deal with
+520 (and 4104) byte sectors, we approached several HBA vendors and
+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
+host memory without changes to the page cache.
+
+Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs
+is somewhat heavy to compute in software.  Benchmarks found that
+calculating this checksum had a significant impact on system
+performance for a number of workloads.  Some controllers allow a
+lighter-weight checksum to be used when interfacing with the operating
+system.  Emulex, for instance, supports the TCP/IP checksum instead.
+The IP checksum received from the OS is converted to the 16-bit CRC
+when writing and vice versa.  This allows the integrity metadata to be
+generated by Linux or the application at very low cost (comparable to
+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
+match up for an I/O to complete.
+
+The separation of the data and integrity metadata buffers as well as
+the choice in checksums is referred to as the Data Integrity
+Extensions.  As these extensions are outside the scope of the protocol
+bodies (T10, T13), Oracle and its partners are trying to standardize
+them within the Storage Networking Industry Association.
+
+----------------------------------------------------------------------
+3. KERNEL CHANGES
+
+The data integrity framework in Linux enables protection information
+to be pinned to I/Os and sent to/received from controllers that
+support it.
+
+The advantage to the integrity extensions in SCSI and SATA is that
+they enable us to protect the entire path from application to storage
+device.  However, at the same time this is also the biggest
+disadvantage. It means that the protection information must be in a
+format that can be understood by the disk.
+
+Generally Linux/POSIX applications are agnostic to the intricacies of
+the storage devices they are accessing.  The virtual filesystem switch
+and the block layer make things like hardware sector size and
+transport protocols completely transparent to the application.
+
+However, this level of detail is required when preparing the
+protection information to send to a disk.  Consequently, the very
+concept of an end-to-end protection scheme is a layering violation.
+It is completely unreasonable for an application to be aware whether
+it is accessing a SCSI or SATA disk.
+
+The data integrity support implemented in Linux attempts to hide this
+from the application.  As far as the application (and to some extent
+the kernel) is concerned, the integrity metadata is opaque information
+that's attached to the I/O.
+
+The current implementation allows the block layer to automatically
+generate the protection information for any I/O.  Eventually the
+intent is to move the integrity metadata calculation to userspace for
+user data.  Metadata and other I/O that originates within the kernel
+will still use the automatic generation interface.
+
+Some storage devices allow each hardware sector to be tagged with a
+16-bit value.  The owner of this tag space is the owner of the block
+device.  I.e. the filesystem in most cases.  The filesystem can use
+this extra space to tag sectors as they see fit.  Because the tag
+space is limited, the block interface allows tagging bigger chunks by
+way of interleaving.  This way, 8*16 bits of information can be
+attached to a typical 4KB filesystem block.
+
+This also means that applications such as fsck and mkfs will need
+access to manipulate the tags from user space.  A passthrough
+interface for this is being worked on.
+
+
+----------------------------------------------------------------------
+4. BLOCK LAYER IMPLEMENTATION DETAILS
+
+4.1 BIO
+
+The data integrity patches add a new field to struct bio when
+CONFIG_BLK_DEV_INTEGRITY is enabled.  bio->bi_integrity is a pointer
+to a struct bip which contains the bio integrity payload.  Essentially
+a bip is a trimmed down struct bio which holds a bio_vec containing
+the integrity metadata and the required housekeeping information (bvec
+pool, vector count, etc.)
+
+A kernel subsystem can enable data integrity protection on a bio by
+calling bio_integrity_alloc(bio).  This will allocate and attach the
+bip to the bio.
+
+Individual pages containing integrity metadata can subsequently be
+attached using bio_integrity_add_page().
+
+bio_free() will automatically free the bip.
+
+
+4.2 BLOCK DEVICE
+
+Because the format of the protection data is tied to the physical
+disk, each block device has been extended with a block integrity
+profile (struct blk_integrity).  This optional profile is registered
+with the block layer using blk_integrity_register().
+
+The profile contains callback functions for generating and verifying
+the protection data, as well as getting and setting application tags.
+The profile also contains a few constants to aid in completing,
+merging and splitting the integrity metadata.
+
+Layered block devices will need to pick a profile that's appropriate
+for all subdevices.  blk_integrity_compare() can help with that.  DM
+and MD linear, RAID0 and RAID1 are currently supported.  RAID4/5/6
+will require extra work due to the application tag.
+
+
+----------------------------------------------------------------------
+5.0 BLOCK LAYER INTEGRITY API
+
+5.1 NORMAL FILESYSTEM
+
+    The normal filesystem is unaware that the underlying block device
+    is capable of sending/receiving integrity metadata.  The IMD will
+    be automatically generated by the block layer at submit_bio() time
+    in case of a WRITE.  A READ request will cause the I/O integrity
+    to be verified upon completion.
+
+    IMD generation and verification can be toggled using the
+
+      /sys/block/<bdev>/integrity/write_generate
+
+    and
+
+      /sys/block/<bdev>/integrity/read_verify
+
+    flags.
+
+
+5.2 INTEGRITY-AWARE FILESYSTEM
+
+    A filesystem that is integrity-aware can prepare I/Os with IMD
+    attached.  It can also use the application tag space if this is
+    supported by the block device.
+
+
+    int bdev_integrity_enabled(block_device, int rw);
+
+      bdev_integrity_enabled() will return 1 if the block device
+      supports integrity metadata transfer for the data direction
+      specified in 'rw'.
+
+      bdev_integrity_enabled() honors the write_generate and
+      read_verify flags in sysfs and will respond accordingly.
+
+
+    int bio_integrity_prep(bio);
+
+      To generate IMD for WRITE and to set up buffers for READ, the
+      filesystem must call bio_integrity_prep(bio).
+
+      Prior to calling this function, the bio data direction and start
+      sector must be set, and the bio should have all data pages
+      added.  It is up to the caller to ensure that the bio does not
+      change while I/O is in progress.
+
+      bio_integrity_prep() should only be called if
+      bio_integrity_enabled() returned 1.
+
+
+    int bio_integrity_tag_size(bio);
+
+      If the filesystem wants to use the application tag space it will
+      first have to find out how much storage space is available.
+      Because tag space is generally limited (usually 2 bytes per
+      sector regardless of sector size), the integrity framework
+      supports interleaving the information between the sectors in an
+      I/O.
+
+      Filesystems can call bio_integrity_tag_size(bio) to find out how
+      many bytes of storage are available for that particular bio.
+
+      Another option is bdev_get_tag_size(block_device) which will
+      return the number of available bytes per hardware sector.
+
+
+    int bio_integrity_set_tag(bio, void *tag_buf, len);
+
+      After a successful return from bio_integrity_prep(),
+      bio_integrity_set_tag() can be used to attach an opaque tag
+      buffer to a bio.  Obviously this only makes sense if the I/O is
+      a WRITE.
+
+
+    int bio_integrity_get_tag(bio, void *tag_buf, len);
+
+      Similarly, at READ I/O completion time the filesystem can
+      retrieve the tag buffer using bio_integrity_get_tag().
+
+
+6.3 PASSING EXISTING INTEGRITY METADATA
+
+    Filesystems that either generate their own integrity metadata or
+    are capable of transferring IMD from user space can use the
+    following calls:
+
+
+    struct bip * bio_integrity_alloc(bio, gfp_mask, nr_pages);
+
+      Allocates the bio integrity payload and hangs it off of the bio.
+      nr_pages indicate how many pages of protection data need to be
+      stored in the integrity bio_vec list (similar to bio_alloc()).
+
+      The integrity payload will be freed at bio_free() time.
+
+
+    int bio_integrity_add_page(bio, page, len, offset);
+
+      Attaches a page containing integrity metadata to an existing
+      bio.  The bio must have an existing bip,
+      i.e. bio_integrity_alloc() must have been called.  For a WRITE,
+      the integrity metadata in the pages must be in a format
+      understood by the target device with the notable exception that
+      the sector numbers will be remapped as the request traverses the
+      I/O stack.  This implies that the pages added using this call
+      will be modified during I/O!  The first reference tag in the
+      integrity metadata must have a value of bip->bip_sector.
+
+      Pages can be added using bio_integrity_add_page() as long as
+      there is room in the bip bio_vec array (nr_pages).
+
+      Upon completion of a READ operation, the attached pages will
+      contain the integrity metadata received from the storage device.
+      It is up to the receiver to process them and verify data
+      integrity upon completion.
+
+
+6.4 REGISTERING A BLOCK DEVICE AS CAPABLE OF EXCHANGING INTEGRITY
+    METADATA
+
+    To enable integrity exchange on a block device the gendisk must be
+    registered as capable:
+
+    int blk_integrity_register(gendisk, blk_integrity);
+
+      The blk_integrity struct is a template and should contain the
+      following:
+
+        static struct blk_integrity my_profile = {
+            .name                   = "STANDARDSBODY-TYPE-VARIANT-CSUM",
+            .generate_fn            = my_generate_fn,
+       	    .verify_fn              = my_verify_fn,
+       	    .get_tag_fn             = my_get_tag_fn,
+       	    .set_tag_fn             = my_set_tag_fn,
+	    .tuple_size             = sizeof(struct my_tuple_size),
+	    .tag_size               = <tag bytes per hw sector>,
+        };
+
+      'name' is a text string which will be visible in sysfs.  This is
+      part of the userland API so chose it carefully and never change
+      it.  The format is standards body-type-variant.
+      E.g. T10-DIF-TYPE1-IP or T13-EPP-0-CRC.
+
+      'generate_fn' generates appropriate integrity metadata (for WRITE).
+
+      'verify_fn' verifies that the data buffer matches the integrity
+      metadata.
+
+      'tuple_size' must be set to match the size of the integrity
+      metadata per sector.  I.e. 8 for DIF and EPP.
+
+      'tag_size' must be set to identify how many bytes of tag space
+      are available per hardware sector.  For DIF this is either 2 or
+      0 depending on the value of the Control Mode Page ATO bit.
+
+      See 6.2 for a description of get_tag_fn and set_tag_fn.
+
+----------------------------------------------------------------------
+2007-12-24 Martin K. Petersen <martin.petersen@oracle.com>

Documentation/cputopology.txt

@@ -14,9 +14,8 @@ represent the thread siblings to cpu X in the same physical package;
 To implement it in an architecture-neutral way, a new source file,
 drivers/base/topology.c, is to export the 4 attributes.
 
-If one architecture wants to support this feature, it just needs to
-implement 4 defines, typically in file include/asm-XXX/topology.h.
-The 4 defines are:
+For an architecture to support this feature, it must define some of
+these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
 #define topology_thread_siblings(cpu)
@@ -25,17 +24,10 @@ The 4 defines are:
 The type of **_id is int.
 The type of siblings is cpumask_t.
 
-To be consistent on all architectures, the 4 attributes should have
-default values if their values are unavailable. Below is the rule.
-1) physical_package_id: If cpu has no physical package id, -1 is the
-default value.
-2) core_id: If cpu doesn't support multi-core, its core id is 0.
-3) thread_siblings: Just include itself, if the cpu doesn't support
-HT/multi-thread.
-4) core_siblings: Just include itself, if the cpu doesn't support
-multi-core and HT/Multi-thread.
-
-So be careful when declaring the 4 defines in include/asm-XXX/topology.h.
-
-If an attribute isn't defined on an architecture, it won't be exported.
-
+To be consistent on all architectures, include/linux/topology.h
+provides default definitions for any of the above macros that are
+not defined by include/asm-XXX/topology.h:
+1) physical_package_id: -1
+2) core_id: 0
+3) thread_siblings: just the given CPU
+4) core_siblings: just the given CPU

Documentation/feature-removal-schedule.txt

@@ -222,13 +222,6 @@ Who:	Thomas Gleixner <tglx@linutronix.de>
 
 ---------------------------
 
-What:	i2c-i810, i2c-prosavage and i2c-savage4
-When:	May 2008
-Why:	These drivers are superseded by i810fb, intelfb and savagefb.
-Who:	Jean Delvare <khali@linux-fr.org>
-
----------------------------
-
 What (Why):
 	- include/linux/netfilter_ipv4/ipt_TOS.h ipt_tos.h header files
 	  (superseded by xt_TOS/xt_tos target & match)

Documentation/filesystems/configfs/configfs.txt

@@ -233,10 +233,12 @@ accomplished via the group operations specified on the group's
 config_item_type.
 
 	struct configfs_group_operations {
-		struct config_item *(*make_item)(struct config_group *group,
-						 const char *name);
-		struct config_group *(*make_group)(struct config_group *group,
-						   const char *name);
+		int (*make_item)(struct config_group *group,
+				 const char *name,
+				 struct config_item **new_item);
+		int (*make_group)(struct config_group *group,
+				  const char *name,
+				  struct config_group **new_group);
 		int (*commit_item)(struct config_item *item);
 		void (*disconnect_notify)(struct config_group *group,
 					  struct config_item *item);

Documentation/filesystems/configfs/configfs_example.c

@@ -273,13 +273,13 @@ static inline struct simple_children *to_simple_children(struct config_item *ite
 	return item ? container_of(to_config_group(item), struct simple_children, group) : NULL;
 }
 
-static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
+static int simple_children_make_item(struct config_group *group, const char *name, struct config_item **new_item)
 {
 	struct simple_child *simple_child;
 
 	simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL);
 	if (!simple_child)
-		return NULL;
+		return -ENOMEM;
 
 
 	config_item_init_type_name(&simple_child->item, name,
@@ -287,7 +287,8 @@ static struct config_item *simple_children_make_item(struct config_group *group,
 
 	simple_child->storeme = 0;
 
-	return &simple_child->item;
+	*new_item = &simple_child->item;
+	return 0;
 }
 
 static struct configfs_attribute simple_children_attr_description = {
@@ -359,20 +360,21 @@ static struct configfs_subsystem simple_children_subsys = {
  * children of its own.
  */
 
-static struct config_group *group_children_make_group(struct config_group *group, const char *name)
+static int group_children_make_group(struct config_group *group, const char *name, struct config_group **new_group)
 {
 	struct simple_children *simple_children;
 
 	simple_children = kzalloc(sizeof(struct simple_children),
 				  GFP_KERNEL);
 	if (!simple_children)
-		return NULL;
+		return -ENOMEM;
 
 
 	config_group_init_type_name(&simple_children->group, name,
 				    &simple_children_type);
 
-	return &simple_children->group;
+	*new_group = &simple_children->group;
+	return 0;
 }
 
 static struct configfs_attribute group_children_attr_description = {

Documentation/filesystems/ext4.txt

@@ -13,72 +13,93 @@ Mailing list: linux-ext4@vger.kernel.org
 1. Quick usage instructions:
 ===========================
 
-  - Grab updated e2fsprogs from
-    ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs-interim/
-    This is a patchset on top of e2fsprogs-1.39, which can be found at
+  - Compile and install the latest version of e2fsprogs (as of this
+    writing version 1.41) from:
+
+    http://sourceforge.net/project/showfiles.php?group_id=2406
+	
+	or
+
     ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
 
-  - It's still mke2fs -j /dev/hda1
+	or grab the latest git repository from:
+
+    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
+
+  - Create a new filesystem using the ext4dev filesystem type:
+
+    	# mke2fs -t ext4dev /dev/hda1
+
+    Or configure an existing ext3 filesystem to support extents and set
+    the test_fs flag to indicate that it's ok for an in-development
+    filesystem to touch this filesystem:
 
-  - mount /dev/hda1 /wherever -t ext4dev
+	# tune2fs -O extents -E test_fs /dev/hda1
 
-  - To enable extents,
+    If the filesystem was created with 128 byte inodes, it can be
+    converted to use 256 byte for greater efficiency via:
 
-	mount /dev/hda1 /wherever -t ext4dev -o extents
+        # tune2fs -I 256 /dev/hda1
 
-  - The filesystem is compatible with the ext3 driver until you add a file
-    which has extents (ie: `mount -o extents', then create a file).
+    (Note: we currently do not have tools to convert an ext4dev
+    filesystem back to ext3; so please do not do try this on production
+    filesystems.)
 
-    NOTE: The "extents" mount flag is temporary.  It will soon go away and
-    extents will be enabled by the "-o extents" flag to mke2fs or tune2fs
+  - Mounting:
+
+	# mount -t ext4dev /dev/hda1 /wherever
 
   - When comparing performance with other filesystems, remember that
-    ext3/4 by default offers higher data integrity guarantees than most.  So
-    when comparing with a metadata-only journalling filesystem, use `mount -o
-    data=writeback'.  And you might as well use `mount -o nobh' too along
-    with it.  Making the journal larger than the mke2fs default often helps
-    performance with metadata-intensive workloads.
+    ext3/4 by default offers higher data integrity guarantees than most.
+    So when comparing with a metadata-only journalling filesystem, such
+    as ext3, use `mount -o data=writeback'.  And you might as well use
+    `mount -o nobh' too along with it.  Making the journal larger than
+    the mke2fs default often helps performance with metadata-intensive
+    workloads.
 
 2. Features
 ===========
 
 2.1 Currently available
 
-* ability to use filesystems > 16TB
+* ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
 * extent format more robust in face of on-disk corruption due to magics,
 * internal redunancy in tree
-
-2.1 Previously available, soon to be enabled by default by "mkefs.ext4":
-
-* dir_index and resize inode will be on by default
-* large inodes will be used by default for fast EAs, nsec timestamps, etc
+* improved file allocation (multi-block alloc)
+* fix 32000 subdirectory limit
+* nsec timestamps for mtime, atime, ctime, create time
+* inode version field on disk (NFSv4, Lustre)
+* reduced e2fsck time via uninit_bg feature
+* journal checksumming for robustness, performance
+* persistent file preallocation (e.g for streaming media, databases)
+* ability to pack bitmaps and inode tables into larger virtual groups via the
+  flex_bg feature
+* large file support
+* Inode allocation using large virtual block groups via flex_bg
+* delayed allocation
+* large block (up to pagesize) support
+* efficent new ordered mode in JBD2 and ext4(avoid using buffer head to force
+  the ordering)
 
 2.2 Candidate features for future inclusion
 
-There are several under discussion, whether they all make it in is
-partly a function of how much time everyone has to work on them:
+* Online defrag (patches available but not well tested)
+* reduced mke2fs time via lazy itable initialization in conjuction with
+  the uninit_bg feature (capability to do this is available in e2fsprogs
+  but a kernel thread to do lazy zeroing of unused inode table blocks
+  after filesystem is first mounted is required for safety)
 
-* improved file allocation (multi-block alloc, delayed alloc; basically done)
-* fix 32000 subdirectory limit (patch exists, needs some e2fsck work)
-* nsec timestamps for mtime, atime, ctime, create time (patch exists,
-  needs some e2fsck work)
-* inode version field on disk (NFSv4, Lustre; prototype exists)
-* reduced mke2fs/e2fsck time via uninitialized groups (prototype exists)
-* journal checksumming for robustness, performance (prototype exists)
-* persistent file preallocation (e.g for streaming media, databases)
+There are several others under discussion, whether they all make it in is
+partly a function of how much time everyone has to work on them. Features like
+metadata checksumming have been discussed and planned for a bit but no patches
+exist yet so I'm not sure they're in the near-term roadmap.
 
-Features like metadata checksumming have been discussed and planned for
-a bit but no patches exist yet so I'm not sure they're in the near-term
-roadmap.
+The big performance win will come with mballoc, delalloc and flex_bg
+grouping of bitmaps and inode tables.  Some test results available here:
 
-The big performance win will come with mballoc and delalloc.  CFS has
-been using mballoc for a few years already with Lustre, and IBM + Bull
-did a lot of benchmarking on it.  The reason it isn't in the first set of
-patches is partly a manageability issue, and partly because it doesn't
-directly affect the on-disk format (outside of much better allocation)
-so it isn't critical to get into the first round of changes.  I believe
-Alex is working on a new set of patches right now.
+ - http://www.bullopensource.org/ext4/20080530/ffsb-write-2.6.26-rc2.html
+ - http://www.bullopensource.org/ext4/20080530/ffsb-readwrite-2.6.26-rc2.html
 
 3. Options
 ==========
@@ -222,9 +243,11 @@ stripe=n		Number of filesystem blocks that mballoc will try
 			to use for allocation size and alignment. For RAID5/6
 			systems this should be the number of data
 			disks *  RAID chunk size in file system blocks.
-
+delalloc	(*)	Deferring block allocation until write-out time.
+nodelalloc		Disable delayed allocation. Blocks are allocation
+			when data is copied from user to page cache.
 Data Mode
----------
+=========
 There are 3 different data modes:
 
 * writeback mode
@@ -236,10 +259,10 @@ typically provide the best ext4 performance.
 
 * ordered mode
 In data=ordered mode, ext4 only officially journals metadata, but it logically
-groups metadata and data blocks into a single unit called a transaction.  When
-it's time to write the new metadata out to disk, the associated data blocks
-are written first.  In general, this mode performs slightly slower than
-writeback but significantly faster than journal mode.
+groups metadata information related to data changes with the data blocks into a
+single unit called a transaction.  When it's time to write the new metadata
+out to disk, the associated data blocks are written first.  In general,
+this mode performs slightly slower than writeback but significantly faster than journal mode.
 
 * journal mode
 data=journal mode provides full data and metadata journaling.  All new data is
@@ -247,7 +270,8 @@ written to the journal first, and then to its final location.
 In the event of a crash, the journal can be replayed, bringing both data and
 metadata into a consistent state.  This mode is the slowest except when data
 needs to be read from and written to disk at the same time where it
-outperforms all others modes.
+outperforms all others modes.  Curently ext4 does not have delayed
+allocation support if this data journalling mode is selected.
 
 References
 ==========
@@ -256,7 +280,8 @@ kernel source:	<file:fs/ext4/>
 		<file:fs/jbd2/>
 
 programs:	http://e2fsprogs.sourceforge.net/
-		http://ext2resize.sourceforge.net
 
 useful links:	http://fedoraproject.org/wiki/ext3-devel
 		http://www.bullopensource.org/ext4/
+		http://ext4.wiki.kernel.org/index.php/Main_Page
+		http://fedoraproject.org/wiki/Features/Ext4

Documentation/filesystems/gfs2-glocks.txt

+                   Glock internal locking rules
+                  ------------------------------
+
+This documents the basic principles of the glock state machine
+internals. Each glock (struct gfs2_glock in fs/gfs2/incore.h)
+has two main (internal) locks:
+
+ 1. A spinlock (gl_spin) which protects the internal state such
+    as gl_state, gl_target and the list of holders (gl_holders)
+ 2. A non-blocking bit lock, GLF_LOCK, which is used to prevent other
+    threads from making calls to the DLM, etc. at the same time. If a
+    thread takes this lock, it must then call run_queue (usually via the
+    workqueue) when it releases it in order to ensure any pending tasks
+    are completed.
+
+The gl_holders list contains all the queued lock requests (not
+just the holders) associated with the glock. If there are any
+held locks, then they will be contiguous entries at the head
+of the list. Locks are granted in strictly the order that they
+are queued, except for those marked LM_FLAG_PRIORITY which are
+used only during recovery, and even then only for journal locks.
+
+There are three lock states that users of the glock layer can request,
+namely shared (SH), deferred (DF) and exclusive (EX). Those translate
+to the following DLM lock modes:
+
+Glock mode    | DLM lock mode
+------------------------------
+    UN        |    IV/NL  Unlocked (no DLM lock associated with glock) or NL
+    SH        |    PR     (Protected read)
+    DF        |    CW     (Concurrent write)
+    EX        |    EX     (Exclusive)
+
+Thus DF is basically a shared mode which is incompatible with the "normal"
+shared lock mode, SH. In GFS2 the DF mode is used exclusively for direct I/O
+operations. The glocks are basically a lock plus some routines which deal
+with cache management. The following rules apply for the cache:
+
+Glock mode   |  Cache data | Cache Metadata | Dirty Data | Dirty Metadata
+--------------------------------------------------------------------------
+    UN       |     No      |       No       |     No     |      No
+    SH       |     Yes     |       Yes      |     No     |      No
+    DF       |     No      |       Yes      |     No     |      No
+    EX       |     Yes     |       Yes      |     Yes    |      Yes
+
+These rules are implemented using the various glock operations which
+are defined for each type of glock. Not all types of glocks use
+all the modes. Only inode glocks use the DF mode for example.
+
+Table of glock operations and per type constants:
+
+Field            | Purpose
+----------------------------------------------------------------------------
+go_xmote_th      | Called before remote state change (e.g. to sync dirty data)
+go_xmote_bh      | Called after remote state change (e.g. to refill cache)
+go_inval         | Called if remote state change requires invalidating the cache
+go_demote_ok     | Returns boolean value of whether its ok to demote a glock
+                 | (e.g. checks timeout, and that there is no cached data)
+go_lock          | Called for the first local holder of a lock
+go_unlock        | Called on the final local unlock of a lock
+go_dump          | Called to print content of object for debugfs file, or on
+                 | error to dump glock to the log.
+go_type;         | The type of the glock, LM_TYPE_.....
+go_min_hold_time | The minimum hold time
+
+The minimum hold time for each lock is the time after a remote lock
+grant for which we ignore remote demote requests. This is in order to
+prevent a situation where locks are being bounced around the cluster
+from node to node with none of the nodes making any progress. This
+tends to show up most with shared mmaped files which are being written
+to by multiple nodes. By delaying the demotion in response to a
+remote callback, that gives the userspace program time to make
+some progress before the pages are unmapped.
+
+There is a plan to try and remove the go_lock and go_unlock callbacks
+if possible, in order to try and speed up the fast path though the locking.
+Also, eventually we hope to make the glock "EX" mode locally shared
+such that any local locking will be done with the i_mutex as required
+rather than via the glock.
+
+Locking rules for glock operations:
+
+Operation     |  GLF_LOCK bit lock held |  gl_spin spinlock held
+-----------------------------------------------------------------
+go_xmote_th   |       Yes               |       No
+go_xmote_bh   |       Yes               |       No
+go_inval      |       Yes               |       No
+go_demote_ok  |       Sometimes         |       Yes
+go_lock       |       Yes               |       No
+go_unlock     |       Yes               |       No
+go_dump       |       Sometimes         |       Yes
+
+N.B. Operations must not drop either the bit lock or the spinlock
+if its held on entry. go_dump and do_demote_ok must never block.
+Note that go_dump will only be called if the glock's state
+indicates that it is caching uptodate data.
+
+Glock locking order within GFS2:
+
+ 1. i_mutex (if required)
+ 2. Rename glock (for rename only)
+ 3. Inode glock(s)
+    (Parents before children, inodes at "same level" with same parent in
+     lock number order)
+ 4. Rgrp glock(s) (for (de)allocation operations)
+ 5. Transaction glock (via gfs2_trans_begin) for non-read operations
+ 6. Page lock  (always last, very important!)
+
+There are two glocks per inode. One deals with access to the inode
+itself (locking order as above), and the other, known as the iopen
+glock is used in conjunction with the i_nlink field in the inode to
+determine the lifetime of the inode in question. Locking of inodes
+is on a per-inode basis. Locking of rgrps is on a per rgrp basis.
+

Documentation/filesystems/proc.txt

@@ -380,28 +380,35 @@ i386 and x86_64 platforms support the new IRQ vector displays.
 Of some interest is the introduction of the /proc/irq directory to 2.4.
 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
-irq subdir is one subdir for each IRQ, and one file; prof_cpu_mask
+irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
+prof_cpu_mask.
 
 For example 
   > ls /proc/irq/
   0  10  12  14  16  18  2  4  6  8  prof_cpu_mask
-  1  11  13  15  17  19  3  5  7  9
+  1  11  13  15  17  19  3  5  7  9  default_smp_affinity
   > ls /proc/irq/0/
   smp_affinity
 
-The contents of the prof_cpu_mask file and each smp_affinity file for each IRQ
-is the same by default:
+smp_affinity is a bitmask, in which you can specify which CPUs can handle the
+IRQ, you can set it by doing:
+
+  > echo 1 > /proc/irq/10/smp_affinity
+
+This means that only the first CPU will handle the IRQ, but you can also echo
+5 which means that only the first and fourth CPU can handle the IRQ.
+
+The contents of each smp_affinity file is the same by default:
 
   > cat /proc/irq/0/smp_affinity
   ffffffff
 
-It's a bitmask, in which you can specify which CPUs can handle the IRQ, you can
-set it by doing:
-
-  > echo 1 > /proc/irq/prof_cpu_mask
+The default_smp_affinity mask applies to all non-active IRQs, which are the
+IRQs which have not yet been allocated/activated, and hence which lack a
+/proc/irq/[0-9]* directory.
 
-This means that only the first CPU will handle the IRQ, but you can also echo 5
-which means that only the first and fourth CPU can handle the IRQ.
+prof_cpu_mask specifies which CPUs are to be profiled by the system wide
+profiler. Default value is ffffffff (all cpus).
 
 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
 between all the CPUs which are allowed to handle it. As usual the kernel has

Documentation/filesystems/ubifs.txt

+Introduction
+=============
+
+UBIFS file-system stands for UBI File System. UBI stands for "Unsorted
+Block Images". UBIFS is a flash file system, which means it is designed
+to work with flash devices. It is important to understand, that UBIFS
+is completely different to any traditional file-system in Linux, like
+Ext2, XFS, JFS, etc. UBIFS represents a separate class of file-systems
+which work with MTD devices, not block devices. The other Linux
+file-system of this class is JFFS2.
+
+To make it more clear, here is a small comparison of MTD devices and
+block devices.
+
+1 MTD devices represent flash devices and they consist of eraseblocks of
+  rather large size, typically about 128KiB. Block devices consist of
+  small blocks, typically 512 bytes.
+2 MTD devices support 3 main operations - read from some offset within an
+  eraseblock, write to some offset within an eraseblock, and erase a whole
+  eraseblock. Block  devices support 2 main operations - read a whole
+  block and write a whole block.
+3 The whole eraseblock has to be erased before it becomes possible to
+  re-write its contents. Blocks may be just re-written.
+4 Eraseblocks become worn out after some number of erase cycles -
+  typically 100K-1G for SLC NAND and NOR flashes, and 1K-10K for MLC
+  NAND flashes. Blocks do not have the wear-out property.
+5 Eraseblocks may become bad (only on NAND flashes) and software should
+  deal with this. Blocks on hard drives typically do not become bad,
+  because hardware has mechanisms to substitute bad blocks, at least in
+  modern LBA disks.
+
+It should be quite obvious why UBIFS is very different to traditional
+file-systems.
+
+UBIFS works on top of UBI. UBI is a separate software layer which may be
+found in drivers/mtd/ubi. UBI is basically a volume management and
+wear-leveling layer. It provides so called UBI volumes which is a higher
+level abstraction than a MTD device. The programming model of UBI devices
+is very similar to MTD devices - they still consist of large eraseblocks,
+they have read/write/erase operations, but UBI devices are devoid of
+limitations like wear and bad blocks (items 4 and 5 in the above list).
+
+In a sense, UBIFS is a next generation of JFFS2 file-system, but it is
+very different and incompatible to JFFS2. The following are the main
+differences.
+
+* JFFS2 works on top of MTD devices, UBIFS depends on UBI and works on
+  top of UBI volumes.
+* JFFS2 does not have on-media index and has to build it while mounting,
+  which requires full media scan. UBIFS maintains the FS indexing
+  information on the flash media and does not require full media scan,
+  so it mounts many times faster than JFFS2.
+* JFFS2 is a write-through file-system, while UBIFS supports write-back,
+  which makes UBIFS much faster on writes.
+
+Similarly to JFFS2, UBIFS supports on-the-flight compression which makes
+it possible to fit quite a lot of data to the flash.
+
+Similarly to JFFS2, UBIFS is tolerant of unclean reboots and power-cuts.
+It does not need stuff like ckfs.ext2. UBIFS automatically replays its
+journal and recovers from crashes, ensuring that the on-flash data
+structures are consistent.
+
+UBIFS scales logarithmically (most of the data structures it uses are
+trees), so the mount time and memory consumption do not linearly depend
+on the flash size, like in case of JFFS2. This is because UBIFS
+maintains the FS index on the flash media. However, UBIFS depends on
+UBI, which scales linearly. So overall UBI/UBIFS stack scales linearly.
+Nevertheless, UBI/UBIFS scales considerably better than JFFS2.
+
+The authors of UBIFS believe, that it is possible to develop UBI2 which
+would scale logarithmically as well. UBI2 would support the same API as UBI,
+but it would be binary incompatible to UBI. So UBIFS would not need to be
+changed to use UBI2
+
+
+Mount options
+=============
+
+(*) == default.
+
+norm_unmount (*)	commit on unmount; the journal is committed
+			when the file-system is unmounted so that the
+			next mount does not have to replay the journal
+			and it becomes very fast;
+fast_unmount		do not commit on unmount; this option makes
+			unmount faster, but the next mount slower
+			because of the need to replay the journal.
+
+
+Quick usage instructions
+========================
+
+The UBI volume to mount is specified using "ubiX_Y" or "ubiX:NAME" syntax,
+where "X" is UBI device number, "Y" is UBI volume number, and "NAME" is
+UBI volume name.
+
+Mount volume 0 on UBI device 0 to /mnt/ubifs:
+$ mount -t ubifs ubi0_0 /mnt/ubifs
+
+Mount "rootfs" volume of UBI device 0 to /mnt/ubifs ("rootfs" is volume
+name):
+$ mount -t ubifs ubi0:rootfs /mnt/ubifs
+
+The following is an example of the kernel boot arguments to attach mtd0
+to UBI and mount volume "rootfs":
+ubi.mtd=0 root=ubi0:rootfs rootfstype=ubifs
+
+
+Module Parameters for Debugging
+===============================
+
+When UBIFS has been compiled with debugging enabled, there are 3 module
+parameters that are available to control aspects of testing and debugging.
+The parameters are unsigned integers where each bit controls an option.
+The parameters are:
+
+debug_msgs	Selects which debug messages to display, as follows:
+
+		Message Type				Flag value
+
+		General messages			1
+		Journal messages			2
+		Mount messages				4
+		Commit messages				8
+		LEB search messages			16
+		Budgeting messages			32
+		Garbage collection messages		64
+		Tree Node Cache (TNC) messages		128
+		LEB properties (lprops) messages	256
+		Input/output messages			512
+		Log messages				1024
+		Scan messages				2048
+		Recovery messages			4096
+
+debug_chks	Selects extra checks that UBIFS can do while running:
+
+		Check					Flag value
+
+		General checks				1
+		Check Tree Node Cache (TNC)		2
+		Check indexing tree size		4
+		Check orphan area			8
+		Check old indexing tree			16
+		Check LEB properties (lprops)		32
+		Check leaf nodes and inodes		64
+
+debug_tsts	Selects a mode of testing, as follows:
+
+		Test mode				Flag value
+
+		Force in-the-gaps method		2
+		Failure mode for recovery testing	4
+
+For example, set debug_msgs to 5 to display General messages and Mount
+messages.
+
+
+References
+==========
+
+UBIFS documentation and FAQ/HOWTO at the MTD web site:
+http://www.linux-mtd.infradead.org/doc/ubifs.html
+http://www.linux-mtd.infradead.org/faq/ubifs.html

Documentation/i2c/busses/i2c-i810

-Kernel driver i2c-i810
-
-Supported adapters:
-  * Intel 82810, 82810-DC100, 82810E, and 82815 (GMCH)
-  * Intel 82845G (GMCH)
-
-Authors: 
-	Frodo Looijaard <frodol@dds.nl>, 
-	Philip Edelbrock <phil@netroedge.com>,
-        Kyösti Mälkki <kmalkki@cc.hut.fi>,
-	Ralph Metzler <rjkm@thp.uni-koeln.de>,
-	Mark D. Studebaker <mdsxyz123@yahoo.com>
-
-Main contact: Mark Studebaker <mdsxyz123@yahoo.com>
-
-Description 
------------ 
-
-WARNING: If you have an '810' or '815' motherboard, your standard I2C
-temperature sensors are most likely on the 801's I2C bus. You want the
-i2c-i801 driver for those, not this driver.
-
-Now for the i2c-i810...
-
-The GMCH chip contains two I2C interfaces.
-
-The first interface is used for DDC (Data Display Channel) which is a
-serial channel through the VGA monitor connector to a DDC-compliant
-monitor. This interface is defined by the Video Electronics Standards
-Association (VESA). The standards are available for purchase at
-http://www.vesa.org .
-
-The second interface is a general-purpose I2C bus. It may be connected to a
-TV-out chip such as the BT869 or possibly to a digital flat-panel display.
-
-Features
--------- 
-
-Both busses use the i2c-algo-bit driver for 'bit banging'
-and support for specific transactions is provided by i2c-algo-bit.
-
-Issues
-------
-
-If you enable bus testing in i2c-algo-bit (insmod i2c-algo-bit bit_test=1),
-the test may fail; if so, the i2c-i810 driver won't be inserted. However,
-we think this has been fixed.

Documentation/i2c/busses/i2c-prosavage

-Kernel driver i2c-prosavage
-
-Supported adapters:
-	
-	S3/VIA KM266/VT8375 aka ProSavage8 
-	S3/VIA KM133/VT8365 aka Savage4 
-
-Author: Henk Vergonet <henk@god.dyndns.org>
-
-Description
------------
-
-The Savage4 chips contain two I2C interfaces (aka a I2C 'master' or
-'host'). 
-
-The first interface is used for DDC (Data Display Channel) which is a
-serial channel through the VGA monitor connector to a DDC-compliant
-monitor. This interface is defined by the Video Electronics Standards
-Association (VESA). The standards are available for purchase at
-http://www.vesa.org . The second interface is a general-purpose I2C bus.
-
-Usefull for gaining access to the TV Encoder chips.
-

Documentation/i2c/busses/i2c-savage4

-Kernel driver i2c-savage4
-
-Supported adapters:
-  * Savage4
-  * Savage2000
-
-Authors: 
-	Alexander Wold <awold@bigfoot.com>,
-	Mark D. Studebaker <mdsxyz123@yahoo.com> 
-
-Description
------------
-
-The Savage4 chips contain two I2C interfaces (aka a I2C 'master'
-or 'host'). 
-
-The first interface is used for DDC (Data Display Channel) which is a
-serial channel through the VGA monitor connector to a DDC-compliant
-monitor. This interface is defined by the Video Electronics Standards
-Association (VESA). The standards are available for purchase at
-http://www.vesa.org . The DDC bus is not yet supported because its register
-is not directly memory-mapped.
-
-The second interface is a general-purpose I2C bus. This is the only
-interface supported by the driver at the moment.
-

Documentation/i2c/chips/max6875

@@ -49,7 +49,7 @@ $ modprobe max6875 force=0,0x50
 
 The MAX6874/MAX6875 ignores address bit 0, so this driver attaches to multiple
 addresses.  For example, for address 0x50, it also reserves 0x51.
-The even-address instance is called 'max6875', the odd one is 'max6875 subclient'.
+The even-address instance is called 'max6875', the odd one is 'dummy'.
 
 
 Programming the chip using i2c-dev

Documentation/i2c/chips/pca9539

@@ -7,7 +7,7 @@ drivers/gpio/pca9539.c instead.
 Supported chips:
   * Philips PCA9539
     Prefix: 'pca9539'
-    Addresses scanned: 0x74 - 0x77
+    Addresses scanned: none
     Datasheet:
         http://www.semiconductors.philips.com/acrobat/datasheets/PCA9539_2.pdf
 
@@ -23,6 +23,14 @@ The input sense can also be inverted.
 The 16 lines are split between two bytes.
 
 
+Detection
+---------
+
+The PCA9539 is difficult to detect and not commonly found in PC machines,
+so you have to pass the I2C bus and address of the installed PCA9539
+devices explicitly to the driver at load time via the force=... parameter.
+
+
 Sysfs entries
 -------------
 

Documentation/i2c/chips/pcf8574

@@ -4,13 +4,13 @@ Kernel driver pcf8574
 Supported chips:
   * Philips PCF8574
     Prefix: 'pcf8574'
-    Addresses scanned: I2C 0x20 - 0x27
+    Addresses scanned: none
     Datasheet: Publicly available at the Philips Semiconductors website
                http://www.semiconductors.philips.com/pip/PCF8574P.html
 
  * Philips PCF8574A
     Prefix: 'pcf8574a'
-    Addresses scanned: I2C 0x38 - 0x3f
+    Addresses scanned: none
     Datasheet: Publicly available at the Philips Semiconductors website
                http://www.semiconductors.philips.com/pip/PCF8574P.html
 
@@ -38,12 +38,10 @@ For more informations see the datasheet.
 Accessing PCF8574(A) via /sys interface
 -------------------------------------
 
-! Be careful !
 The PCF8574(A) is plainly impossible to detect ! Stupid chip.
-So every chip with address in the interval [20..27] and [38..3f] are
-detected as PCF8574(A). If you have other chips in this address
-range, the workaround is to load this module after the one
-for your others chips.
+So, you have to pass the I2C bus and address of the installed PCF857A
+and PCF8574A devices explicitly to the driver at load time via the
+force=... parameter.
 
 On detection (i.e. insmod, modprobe et al.), directories are being
 created for each detected PCF8574(A):

Documentation/i2c/chips/pcf8575

@@ -40,12 +40,9 @@ Detection
 ---------
 
 There is no method known to detect whether a chip on a given I2C address is
-a PCF8575 or whether it is any other I2C device. So there are two alternatives
-to let the driver find the installed PCF8575 devices:
-- Load this driver after any other I2C driver for I2C devices with addresses
-  in the range 0x20 .. 0x27.
-- Pass the I2C bus and address of the installed PCF8575 devices explicitly to
-  the driver at load time via the probe=... or force=... parameters.
+a PCF8575 or whether it is any other I2C device, so you have to pass the I2C
+bus and address of the installed PCF8575 devices explicitly to the driver at
+load time via the force=... parameter.
 
 /sys interface
 --------------

Documentation/i2c/fault-codes

+This is a summary of the most important conventions for use of fault
+codes in the I2C/SMBus stack.
+
+
+A "Fault" is not always an "Error"
+----------------------------------
+Not all fault reports imply errors; "page faults" should be a familiar
+example.  Software often retries idempotent operations after transient
+faults.  There may be fancier recovery schemes that are appropriate in
+some cases, such as re-initializing (and maybe resetting).  After such
+recovery, triggered by a fault report, there is no error.
+
+In a similar way, sometimes a "fault" code just reports one defined
+result for an operation ... it doesn't indicate that anything is wrong
+at all, just that the outcome wasn't on the "golden path".
+
+In short, your I2C driver code may need to know these codes in order
+to respond correctly.  Other code may need to rely on YOUR code reporting
+the right fault code, so that it can (in turn) behave correctly.
+
+
+I2C and SMBus fault codes
+-------------------------
+These are returned as negative numbers from most calls, with zero or
+some positive number indicating a non-fault return.  The specific
+numbers associated with these symbols differ between architectures,
+though most Linux systems use <asm-generic/errno*.h> numbering.
+
+Note that the descriptions here are not exhaustive.  There are other
+codes that may be returned, and other cases where these codes should
+be returned.  However, drivers should not return other codes for these
+cases (unless the hardware doesn't provide unique fault reports).
+
+Also, codes returned by adapter probe methods follow rules which are
+specific to their host bus (such as PCI, or the platform bus).
+
+
+EAGAIN
+	Returned by I2C adapters when they lose arbitration in master
+	transmit mode:  some other master was transmitting different
+	data at the same time.
+
+	Also returned when trying to invoke an I2C operation in an
+	atomic context, when some task is already using that I2C bus
+	to execute some other operation.
+
+EBADMSG
+	Returned by SMBus logic when an invalid Packet Error Code byte
+	is received.  This code is a CRC covering all bytes in the
+	transaction, and is sent before the terminating STOP.  This
+	fault is only reported on read transactions; the SMBus slave
+	may have a way to report PEC mismatches on writes from the
+	host.  Note that even if PECs are in use, you should not rely
+	on these as the only way to detect incorrect data transfers.
+
+EBUSY
+	Returned by SMBus adapters when the bus was busy for longer
+	than allowed.  This usually indicates some device (maybe the
+	SMBus adapter) needs some fault recovery (such as resetting),
+	or that the reset was attempted but failed.
+
+EINVAL
+	This rather vague error means an invalid parameter has been
+	detected before any I/O operation was started.  Use a more
+	specific fault code when you can.
+
+	One example would be a driver trying an SMBus Block Write
+	with block size outside the range of 1-32 bytes.
+
+EIO
+	This rather vague error means something went wrong when
+	performing an I/O operation.  Use a more specific fault
+	code when you can.
+
+ENODEV
+	Returned by driver probe() methods.  This is a bit more
+	specific than ENXIO, implying the problem isn't with the
+	address, but with the device found there.  Driver probes
+	may verify the device returns *correct* responses, and
+	return this as appropriate.  (The driver core will warn
+	about probe faults other than ENXIO and ENODEV.)
+
+ENOMEM
+	Returned by any component that can't allocate memory when
+	it needs to do so.
+
+ENXIO
+	Returned by I2C adapters to indicate that the address phase
+	of a transfer didn't get an ACK.  While it might just mean
+	an I2C device was temporarily not responding, usually it
+	means there's nothing listening at that address.
+
+	Returned by driver probe() methods to indicate that they
+	found no device to bind to.  (ENODEV may also be used.)
+
+EOPNOTSUPP
+	Returned by an adapter when asked to perform an operation
+	that it doesn't, or can't, support.
+
+	For example, this would be returned when an adapter that
+	doesn't support SMBus block transfers is asked to execute
+	one.  In that case, the driver making that request should
+	have verified that functionality was supported before it
+	made that block transfer request.
+
+	Similarly, if an I2C adapter can't execute all legal I2C
+	messages, it should return this when asked to perform a
+	transaction it can't.  (These limitations can't be seen in
+	the adapter's functionality mask, since the assumption is
+	that if an adapter supports I2C it supports all of I2C.)
+
+EPROTO
+	Returned when slave does not conform to the relevant I2C
+	or SMBus (or chip-specific) protocol specifications.  One
+	case is when the length of an SMBus block data response
+	(from the SMBus slave) is outside the range 1-32 bytes.
+
+ETIMEDOUT
+	This is returned by drivers when an operation took too much
+	time, and was aborted before it completed.
+
+	SMBus adapters may return it when an operation took more
+	time than allowed by the SMBus specification; for example,
+	when a slave stretches clocks too far.  I2C has no such
+	timeouts, but it's normal for I2C adapters to impose some
+	arbitrary limits (much longer than SMBus!) too.
+

Documentation/i2c/smbus-protocol

@@ -42,8 +42,8 @@ Count (8 bits): A data byte containing the length of a block operation.
 [..]: Data sent by I2C device, as opposed to data sent by the host adapter.
 
 
-SMBus Quick Command:  i2c_smbus_write_quick()
-=============================================
+SMBus Quick Command
+===================
 
 This sends a single bit to the device, at the place of the Rd/Wr bit.
 

Documentation/i2c/writing-clients

@@ -44,6 +44,10 @@ static struct i2c_driver foo_driver = {
 	.id_table	= foo_ids,
 	.probe		= foo_probe,
 	.remove		= foo_remove,
+	/* if device autodetection is needed: */
+	.class		= I2C_CLASS_SOMETHING,
+	.detect		= foo_detect,
+	.address_data	= &addr_data,
 
 	/* else, driver uses "legacy" binding model: */
 	.attach_adapter	= foo_attach_adapter,
@@ -217,6 +221,31 @@ in the I2C bus driver. You may want to save the returned i2c_client
 reference for later use.
 
 
+Device Detection (Standard driver model)
+----------------------------------------
+
+Sometimes you do not know in advance which I2C devices are connected to
+a given I2C bus.  This is for example the case of hardware monitoring
+devices on a PC's SMBus.  In that case, you may want to let your driver
+detect supported devices automatically.  This is how the legacy model
+was working, and is now available as an extension to the standard
+driver model (so that we can finally get rid of the legacy model.)
+
+You simply have to define a detect callback which will attempt to
+identify supported devices (returning 0 for supported ones and -ENODEV
+for unsupported ones), a list of addresses to probe, and a device type
+(or class) so that only I2C buses which may have that type of device
+connected (and not otherwise enumerated) will be probed.  The i2c
+core will then call you back as needed and will instantiate a device
+for you for every successful detection.
+
+Note that this mechanism is purely optional and not suitable for all
+devices.  You need some reliable way to identify the supported devices
+(typically using device-specific, dedicated identification registers),
+otherwise misdetections are likely to occur and things can get wrong
+quickly.
+
+
 Device Deletion (Standard driver model)
 ---------------------------------------
 
@@ -569,7 +598,6 @@ SMBus communication
   in terms of it. Never use this function directly!
 
 
-  extern s32 i2c_smbus_write_quick(struct i2c_client * client, u8 value);
   extern s32 i2c_smbus_read_byte(struct i2c_client * client);
   extern s32 i2c_smbus_write_byte(struct i2c_client * client, u8 value);
   extern s32 i2c_smbus_read_byte_data(struct i2c_client * client, u8 command);
@@ -578,30 +606,31 @@ SMBus communication
   extern s32 i2c_smbus_read_word_data(struct i2c_client * client, u8 command);
   extern s32 i2c_smbus_write_word_data(struct i2c_client * client,
                                        u8 command, u16 value);
+  extern s32 i2c_smbus_read_block_data(struct i2c_client * client,
+                                       u8 command, u8 *values);
   extern s32 i2c_smbus_write_block_data(struct i2c_client * client,
                                         u8 command, u8 length,
                                         u8 *values);
   extern s32 i2c_smbus_read_i2c_block_data(struct i2c_client * client,
                                            u8 command, u8 length, u8 *values);
-
-These ones were removed in Linux 2.6.10 because they had no users, but could
-be added back later if needed:
-
-  extern s32 i2c_smbus_read_block_data(struct i2c_client * client,
-                                       u8 command, u8 *values);
   extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client * client,
                                             u8 command, u8 length,
                                             u8 *values);
+
+These ones were removed from i2c-core because they had no users, but could
+be added back later if needed:
+
+  extern s32 i2c_smbus_write_quick(struct i2c_client * client, u8 value);
   extern s32 i2c_smbus_process_call(struct i2c_client * client,
                                     u8 command, u16 value);
   extern s32 i2c_smbus_block_process_call(struct i2c_client *client,
                                           u8 command, u8 length,
                                           u8 *values)
 
-All these transactions return -1 on failure. The 'write' transactions 
-return 0 on success; the 'read' transactions return the read value, except 
-for read_block, which returns the number of values read. The block buffers 
-need not be longer than 32 bytes.
+All these transactions return a negative errno value on failure. The 'write'
+transactions return 0 on success; the 'read' transactions return the read
+value, except for block transactions, which return the number of values
+read. The block buffers need not be longer than 32 bytes.
 
 You can read the file `smbus-protocol' for more information about the
 actual SMBus protocol.

Documentation/ioctl-number.txt

@@ -117,6 +117,7 @@ Code	Seq#	Include File		Comments
 					<mailto:natalia@nikhefk.nikhef.nl>
 'c'	00-7F	linux/comstats.h	conflict!
 'c'	00-7F	linux/coda.h		conflict!
+'c'	80-9F	asm-s390/chsc.h
 'd'	00-FF	linux/char/drm/drm/h	conflict!
 'd'	00-DF	linux/video_decoder.h	conflict!
 'd'	F0-FF	linux/digi1.h

Documentation/ioctl/hdio.txt

@@ -508,12 +508,13 @@ HDIO_DRIVE_RESET		execute a device reset
 
 	error returns:
 	  EACCES	Access denied:  requires CAP_SYS_ADMIN
+	  ENXIO		No such device:	phy dead or ctl_addr == 0
+	  EIO		I/O error:	reset timed out or hardware error
 
 	notes:
 
-	  Abort any current command, prevent anything else from being
-	  queued, execute a reset on the device, and issue BLKRRPART
-	  ioctl on the block device.
+	  Execute a reset on the device as soon as the current IO
+	  operation has completed.
 
 	  Executes an ATAPI soft reset if applicable, otherwise
 	  executes an ATA soft reset on the controller.

Documentation/kernel-parameters.txt

@@ -147,10 +147,14 @@ and is between 256 and 4096 characters. It is defined in the file
 			default: 0
 
 	acpi_sleep=	[HW,ACPI] Sleep options
-			Format: { s3_bios, s3_mode, s3_beep }
+			Format: { s3_bios, s3_mode, s3_beep, old_ordering }
 			See Documentation/power/video.txt for s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
 			as soon as the kernel's real-mode entry point is called.
+			old_ordering causes the ACPI 1.0 ordering of the _PTS
+			control method, wrt putting devices into low power
+			states, to be enforced (the ACPI 2.0 ordering of _PTS is
+			used by default).
 
 	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
 			Format: { level | edge | high | low }
@@ -571,6 +575,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	debug_objects	[KNL] Enable object debugging
 
+	debugpat	[X86] Enable PAT debugging
+
 	decnet.addr=	[HW,NET]
 			Format: <area>[,<node>]
 			See also Documentation/networking/decnet.txt.
@@ -756,9 +762,6 @@ and is between 256 and 4096 characters. It is defined in the file
 	hd=		[EIDE] (E)IDE hard drive subsystem geometry
 			Format: <cyl>,<head>,<sect>
 
-	hd?=		[HW] (E)IDE subsystem
-	hd?lun=		See Documentation/ide/ide.txt.
-
 	highmem=nn[KMG]	[KNL,BOOT] forces the highmem zone to have an exact
 			size of <nn>. This works even on boxes that have no
 			highmem otherwise. This also works to reduce highmem
@@ -819,7 +822,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			See Documentation/ide/ide.txt.
 
 	idle=		[X86]
-			Format: idle=poll or idle=mwait
+			Format: idle=poll or idle=mwait, idle=halt, idle=nomwait
 			Poll forces a polling idle loop that can slightly improves the performance
 			of waking up a idle CPU, but will use a lot of power and make the system
 			run hot. Not recommended.
@@ -827,6 +830,9 @@ and is between 256 and 4096 characters. It is defined in the file
 			to not use it because it doesn't save as much power as a normal idle
 			loop use the MONITOR/MWAIT idle loop anyways. Performance should be the same
 			as idle=poll.
+			idle=halt. Halt is forced to be used for CPU idle.
+			In such case C2/C3 won't be used again.
+			idle=nomwait. Disable mwait for CPU C-states
 
 	ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
 			Claim all unknown PCI IDE storage controllers.
@@ -1242,6 +1248,11 @@ and is between 256 and 4096 characters. It is defined in the file
 	mtdparts=	[MTD]
 			See drivers/mtd/cmdlinepart.c.
 
+	mtdset=		[ARM]
+			ARM/S3C2412 JIVE boot control
+
+			See arch/arm/mach-s3c2412/mach-jive.c
+
 	mtouchusb.raw_coordinates=
 			[HW] Make the MicroTouch USB driver use raw coordinates
 			('y', default) or cooked coordinates ('n')
@@ -1536,6 +1547,9 @@ and is between 256 and 4096 characters. It is defined in the file
 				Use with caution as certain devices share
 				address decoders between ROMs and other
 				resources.
+		norom		[X86-32,X86_64] Do not assign address space to
+				expansion ROMs that do not already have
+				BIOS assigned address ranges.
 		irqmask=0xMMMM	[X86-32] Set a bit mask of IRQs allowed to be
 				assigned automatically to PCI devices. You can
 				make the kernel exclude IRQs of your ISA cards
@@ -1611,6 +1625,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format: { parport<nr> | timid | 0 }
 			See also Documentation/parport.txt.
 
+	pmtmr=		[X86] Manual setup of pmtmr I/O Port. 
+			Override pmtimer IOPort with a hex value.
+			e.g. pmtmr=0x508
+
 	pnpacpi=	[ACPI]
 			{ off }
 

Documentation/kprobes.txt

@@ -172,6 +172,7 @@ architectures:
 - ia64 (Does not support probes on instruction slot1.)
 - sparc64 (Return probes not yet implemented.)
 - arm
+- ppc
 
 3. Configuring Kprobes
 

Documentation/laptops/acer-wmi.txt

@@ -174,8 +174,6 @@ The LED is exposed through the LED subsystem, and can be found in:
 The mail LED is autodetected, so if you don't have one, the LED device won't
 be registered.
 
-If you have a mail LED that is not green, please report this to me.
-
 Backlight
 *********
 

Documentation/powerpc/bootwrapper.txt

+The PowerPC boot wrapper
+------------------------
+Copyright (C) Secret Lab Technologies Ltd.
+
+PowerPC image targets compresses and wraps the kernel image (vmlinux) with
+a boot wrapper to make it usable by the system firmware.  There is no
+standard PowerPC firmware interface, so the boot wrapper is designed to
+be adaptable for each kind of image that needs to be built.
+
+The boot wrapper can be found in the arch/powerpc/boot/ directory.  The
+Makefile in that directory has targets for all the available image types.
+The different image types are used to support all of the various firmware
+interfaces found on PowerPC platforms.  OpenFirmware is the most commonly
+used firmware type on general purpose PowerPC systems from Apple, IBM and
+others.  U-Boot is typically found on embedded PowerPC hardware, but there
+are a handful of other firmware implementations which are also popular.  Each
+firmware interface requires a different image format.
+
+The boot wrapper is built from the makefile in arch/powerpc/boot/Makefile and
+it uses the wrapper script (arch/powerpc/boot/wrapper) to generate target
+image.  The details of the build system is discussed in the next section.
+Currently, the following image format targets exist:
+
+   cuImage.%:		Backwards compatible uImage for older version of
+			U-Boot (for versions that don't understand the device
+			tree).  This image embeds a device tree blob inside
+			the image.  The boot wrapper, kernel and device tree
+			are all embedded inside the U-Boot uImage file format
+			with boot wrapper code that extracts data from the old
+			bd_info structure and loads the data into the device
+			tree before jumping into the kernel.
+			  Because of the series of #ifdefs found in the
+			bd_info structure used in the old U-Boot interfaces,
+			cuImages are platform specific.  Each specific
+			U-Boot platform has a different platform init file
+			which populates the embedded device tree with data
+			from the platform specific bd_info file.  The platform
+			specific cuImage platform init code can be found in
+			arch/powerpc/boot/cuboot.*.c.  Selection of the correct
+			cuImage init code for a specific board can be found in
+			the wrapper structure.
+   dtbImage.%:		Similar to zImage, except device tree blob is embedded
+			inside the image instead of provided by firmware.  The
+			output image file can be either an elf file or a flat
+			binary depending on the platform.
+			  dtbImages are used on systems which do not have an
+			interface for passing a device tree directly.
+			dtbImages are similar to simpleImages except that
+			dtbImages have platform specific code for extracting
+			data from the board firmware, but simpleImages do not
+			talk to the firmware at all.
+			  PlayStation 3 support uses dtbImage.  So do Embedded
+			Planet boards using the PlanetCore firmware.  Board
+			specific initialization code is typically found in a
+			file named arch/powerpc/boot/<platform>.c; but this
+			can be overridden by the wrapper script.
+   simpleImage.%:	Firmware independent compressed image that does not
+			depend on any particular firmware interface and embeds
+			a device tree blob.  This image is a flat binary that
+			can be loaded to any location in RAM and jumped to.
+			Firmware cannot pass any configuration data to the
+			kernel with this image type and it depends entirely on
+			the embedded device tree for all information.
+			  The simpleImage is useful for booting systems with
+			an unknown firmware interface or for booting from
+			a debugger when no firmware is present (such as on
+			the Xilinx Virtex platform).  The only assumption that
+			simpleImage makes is that RAM is correctly initialized
+			and that the MMU is either off or has RAM mapped to
+			base address 0.
+			  simpleImage also supports inserting special platform
+			specific initialization code to the start of the bootup
+			sequence.  The virtex405 platform uses this feature to
+			ensure that the cache is invalidated before caching
+			is enabled.  Platform specific initialization code is
+			added as part of the wrapper script and is keyed on
+			the image target name.  For example, all
+			simpleImage.virtex405-* targets will add the
+			virtex405-head.S initialization code (This also means
+			that the dts file for virtex405 targets should be
+			named (virtex405-<board>.dts).  Search the wrapper
+			script for 'virtex405' and see the file
+			arch/powerpc/boot/virtex405-head.S for details.
+   treeImage.%;		Image format for used with OpenBIOS firmware found
+			on some ppc4xx hardware.  This image embeds a device
+			tree blob inside the image.
+   uImage:		Native image format used by U-Boot.  The uImage target
+			does not add any boot code.  It just wraps a compressed
+			vmlinux in the uImage data structure.  This image
+			requires a version of U-Boot that is able to pass
+			a device tree to the kernel at boot.  If using an older
+			version of U-Boot, then you need to use a cuImage
+			instead.
+   zImage.%:		Image format which does not embed a device tree.
+			Used by OpenFirmware and other firmware interfaces
+			which are able to supply a device tree.  This image
+			expects firmware to provide the device tree at boot.
+			Typically, if you have general purpose PowerPC
+			hardware then you want this image format.
+
+Image types which embed a device tree blob (simpleImage, dtbImage, treeImage,
+and cuImage) all generate the device tree blob from a file in the
+arch/powerpc/boot/dts/ directory.  The Makefile selects the correct device
+tree source based on the name of the target.  Therefore, if the kernel is
+built with 'make treeImage.walnut simpleImage.virtex405-ml403', then the
+build system will use arch/powerpc/boot/dts/walnut.dts to build
+treeImage.walnut and arch/powerpc/boot/dts/virtex405-ml403.dts to build
+the simpleImage.virtex405-ml403.
+
+Two special targets called 'zImage' and 'zImage.initrd' also exist.  These
+targets build all the default images as selected by the kernel configuration.
+Default images are selected by the boot wrapper Makefile
+(arch/powerpc/boot/Makefile) by adding targets to the $image-y variable.  Look
+at the Makefile to see which default image targets are available.
+
+How it is built
+---------------
+arch/powerpc is designed to support multiplatform kernels, which means
+that a single vmlinux image can be booted on many different target boards.
+It also means that the boot wrapper must be able to wrap for many kinds of
+images on a single build.  The design decision was made to not use any
+conditional compilation code (#ifdef, etc) in the boot wrapper source code.
+All of the boot wrapper pieces are buildable at any time regardless of the
+kernel configuration.  Building all the wrapper bits on every kernel build
+also ensures that obscure parts of the wrapper are at the very least compile
+tested in a large variety of environments.
+
+The wrapper is adapted for different image types at link time by linking in
+just the wrapper bits that are appropriate for the image type.  The 'wrapper
+script' (found in arch/powerpc/boot/wrapper) is called by the Makefile and
+is responsible for selecting the correct wrapper bits for the image type.
+The arguments are well documented in the script's comment block, so they
+are not repeated here.  However, it is worth mentioning that the script
+uses the -p (platform) argument as the main method of deciding which wrapper
+bits to compile in.  Look for the large 'case "$platform" in' block in the
+middle of the script.  This is also the place where platform specific fixups
+can be selected by changing the link order.
+
+In particular, care should be taken when working with cuImages.  cuImage
+wrapper bits are very board specific and care should be taken to make sure
+the target you are trying to build is supported by the wrapper bits.

Documentation/powerpc/dts-bindings/fsl/board.txt

+* Board Control and Status (BCSR)
+
+Required properties:
+
+ - device_type : Should be "board-control"
+ - reg : Offset and length of the register set for the device
+
+Example:
+
+	bcsr@f8000000 {
+		device_type = "board-control";
+		reg = <f8000000 8000>;
+	};
+
+* Freescale on board FPGA
+
+This is the memory-mapped registers for on board FPGA.
+
+Required properities:
+- compatible : should be "fsl,fpga-pixis".
+- reg : should contain the address and the lenght of the FPPGA register
+  set.
+
+Example (MPC8610HPCD):
+
+	board-control@e8000000 {
+		compatible = "fsl,fpga-pixis";
+		reg = <0xe8000000 32>;
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt

+* Freescale Communications Processor Module
+
+NOTE: This is an interim binding, and will likely change slightly,
+as more devices are supported.  The QE bindings especially are
+incomplete.
+
+* Root CPM node
+
+Properties:
+- compatible : "fsl,cpm1", "fsl,cpm2", or "fsl,qe".
+- reg : A 48-byte region beginning with CPCR.
+
+Example:
+     cpm@119c0 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	#interrupt-cells = <2>;
+	compatible = "fsl,mpc8272-cpm", "fsl,cpm2";
+	reg = <119c0 30>;
+     }
+
+* Properties common to mulitple CPM/QE devices
+
+- fsl,cpm-command : This value is ORed with the opcode and command flag
+                    to specify the device on which a CPM command operates.
+
+- fsl,cpm-brg : Indicates which baud rate generator the device
+                is associated with.  If absent, an unused BRG
+                should be dynamically allocated.  If zero, the
+                device uses an external clock rather than a BRG.
+
+- reg : Unless otherwise specified, the first resource represents the
+        scc/fcc/ucc registers, and the second represents the device's
+        parameter RAM region (if it has one).
+
+* Multi-User RAM (MURAM)
+
+The multi-user/dual-ported RAM is expressed as a bus under the CPM node.
+
+Ranges must be set up subject to the following restrictions:
+
+- Children's reg nodes must be offsets from the start of all muram, even
+  if the user-data area does not begin at zero.
+- If multiple range entries are used, the difference between the parent
+  address and the child address must be the same in all, so that a single
+  mapping can cover them all while maintaining the ability to determine
+  CPM-side offsets with pointer subtraction.  It is recommended that
+  multiple range entries not be used.
+- A child address of zero must be translatable, even if no reg resources
+  contain it.
+
+A child "data" node must exist, compatible with "fsl,cpm-muram-data", to
+indicate the portion of muram that is usable by the OS for arbitrary
+purposes.  The data node may have an arbitrary number of reg resources,
+all of which contribute to the allocatable muram pool.
+
+Example, based on mpc8272:
+	muram@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0 10000>;
+
+		data@0 {
+			compatible = "fsl,cpm-muram-data";
+			reg = <0 2000 9800 800>;
+		};
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/brg.txt

+* Baud Rate Generators
+
+Currently defined compatibles:
+fsl,cpm-brg
+fsl,cpm1-brg
+fsl,cpm2-brg
+
+Properties:
+- reg : There may be an arbitrary number of reg resources; BRG
+  numbers are assigned to these in order.
+- clock-frequency : Specifies the base frequency driving
+  the BRG.
+
+Example:
+	brg@119f0 {
+		compatible = "fsl,mpc8272-brg",
+			     "fsl,cpm2-brg",
+			     "fsl,cpm-brg";
+		reg = <119f0 10 115f0 10>;
+		clock-frequency = <d#25000000>;
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/i2c.txt

+* I2C
+
+The I2C controller is expressed as a bus under the CPM node.
+
+Properties:
+- compatible : "fsl,cpm1-i2c", "fsl,cpm2-i2c"
+- reg : On CPM2 devices, the second resource doesn't specify the I2C
+  Parameter RAM itself, but the I2C_BASE field of the CPM2 Parameter RAM
+  (typically 0x8afc 0x2).
+- #address-cells : Should be one. The cell is the i2c device address with
+  the r/w bit set to zero.
+- #size-cells : Should be zero.
+- clock-frequency : Can be used to set the i2c clock frequency. If
+  unspecified, a default frequency of 60kHz is being used.
+The following two properties are deprecated. They are only used by legacy
+i2c drivers to find the bus to probe:
+- linux,i2c-index : Can be used to hard code an i2c bus number. By default,
+  the bus number is dynamically assigned by the i2c core.
+- linux,i2c-class : Can be used to override the i2c class. The class is used
+  by legacy i2c device drivers to find a bus in a specific context like
+  system management, video or sound. By default, I2C_CLASS_HWMON (1) is
+  being used. The definition of the classes can be found in
+  include/i2c/i2c.h
+
+Example, based on mpc823:
+
+	i2c@860 {
+		compatible = "fsl,mpc823-i2c",
+			     "fsl,cpm1-i2c";
+		reg = <0x860 0x20 0x3c80 0x30>;
+		interrupts = <16>;
+		interrupt-parent = <&CPM_PIC>;
+		fsl,cpm-command = <0x10>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		rtc@68 {
+			compatible = "dallas,ds1307";
+			reg = <0x68>;
+		};
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/pic.txt

+* Interrupt Controllers
+
+Currently defined compatibles:
+- fsl,cpm1-pic
+  - only one interrupt cell
+- fsl,pq1-pic
+- fsl,cpm2-pic
+  - second interrupt cell is level/sense:
+    - 2 is falling edge
+    - 8 is active low
+
+Example:
+	interrupt-controller@10c00 {
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <10c00 80>;
+		compatible = "mpc8272-pic", "fsl,cpm2-pic";
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/usb.txt

+* USB (Universal Serial Bus Controller)
+
+Properties:
+- compatible : "fsl,cpm1-usb", "fsl,cpm2-usb", "fsl,qe-usb"
+
+Example:
+	usb@11bc0 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,cpm2-usb";
+		reg = <11b60 18 8b00 100>;
+		interrupts = <b 8>;
+		interrupt-parent = <&PIC>;
+		fsl,cpm-command = <2e600000>;
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/network.txt

+* Network
+
+Currently defined compatibles:
+- fsl,cpm1-scc-enet
+- fsl,cpm2-scc-enet
+- fsl,cpm1-fec-enet
+- fsl,cpm2-fcc-enet (third resource is GFEMR)
+- fsl,qe-enet
+
+Example:
+
+	ethernet@11300 {
+		device_type = "network";
+		compatible = "fsl,mpc8272-fcc-enet",
+			     "fsl,cpm2-fcc-enet";
+		reg = <11300 20 8400 100 11390 1>;
+		local-mac-address = [ 00 00 00 00 00 00 ];
+		interrupts = <20 8>;
+		interrupt-parent = <&PIC>;
+		phy-handle = <&PHY0>;
+		fsl,cpm-command = <12000300>;
+	};
+
+* MDIO
+
+Currently defined compatibles:
+fsl,pq1-fec-mdio (reg is same as first resource of FEC device)
+fsl,cpm2-mdio-bitbang (reg is port C registers)
+
+Properties for fsl,cpm2-mdio-bitbang:
+fsl,mdio-pin : pin of port C controlling mdio data
+fsl,mdc-pin : pin of port C controlling mdio clock
+
+Example:
+	mdio@10d40 {
+		device_type = "mdio";
+		compatible = "fsl,mpc8272ads-mdio-bitbang",
+			     "fsl,mpc8272-mdio-bitbang",
+			     "fsl,cpm2-mdio-bitbang";
+		reg = <10d40 14>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		fsl,mdio-pin = <12>;
+		fsl,mdc-pin = <13>;
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt

+* Freescale QUICC Engine module (QE)
+This represents qe module that is installed on PowerQUICC II Pro.
+
+NOTE:  This is an interim binding; it should be updated to fit
+in with the CPM binding later in this document.
+
+Basically, it is a bus of devices, that could act more or less
+as a complete entity (UCC, USB etc ). All of them should be siblings on
+the "root" qe node, using the common properties from there.
+The description below applies to the qe of MPC8360 and
+more nodes and properties would be extended in the future.
+
+i) Root QE device
+
+Required properties:
+- compatible : should be "fsl,qe";
+- model : precise model of the QE, Can be "QE", "CPM", or "CPM2"
+- reg : offset and length of the device registers.
+- bus-frequency : the clock frequency for QUICC Engine.
+
+Recommended properties
+- brg-frequency : the internal clock source frequency for baud-rate
+  generators in Hz.
+
+Example:
+     qe@e0100000 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	#interrupt-cells = <2>;
+	compatible = "fsl,qe";
+	ranges = <0 e0100000 00100000>;
+	reg = <e0100000 480>;
+	brg-frequency = <0>;
+	bus-frequency = <179A7B00>;
+     }
+
+* Multi-User RAM (MURAM)
+
+Required properties:
+- compatible : should be "fsl,qe-muram", "fsl,cpm-muram".
+- mode : the could be "host" or "slave".
+- ranges : Should be defined as specified in 1) to describe the
+   translation of MURAM addresses.
+- data-only : sub-node which defines the address area under MURAM
+   bus that can be allocated as data/parameter
+
+Example:
+
+     muram@10000 {
+	compatible = "fsl,qe-muram", "fsl,cpm-muram";
+	ranges = <0 00010000 0000c000>;
+
+	data-only@0{
+		compatible = "fsl,qe-muram-data",
+			     "fsl,cpm-muram-data";
+		reg = <0 c000>;
+	};
+     };

Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt

+* Uploaded QE firmware
+
+      If a new firwmare has been uploaded to the QE (usually by the
+      boot loader), then a 'firmware' child node should be added to the QE
+      node.  This node provides information on the uploaded firmware that
+      device drivers may need.
+
+      Required properties:
+      - id: The string name of the firmware.  This is taken from the 'id'
+            member of the qe_firmware structure of the uploaded firmware.
+            Device drivers can search this string to determine if the
+            firmware they want is already present.
+      - extended-modes: The Extended Modes bitfield, taken from the
+		   firmware binary.  It is a 64-bit number represented
+		   as an array of two 32-bit numbers.
+      - virtual-traps: The virtual traps, taken from the firmware binary.
+		  It is an array of 8 32-bit numbers.
+
+Example:
+	firmware {
+		id = "Soft-UART";
+		extended-modes = <0 0>;
+		virtual-traps = <0 0 0 0 0 0 0 0>;
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/par_io.txt

+* Parallel I/O Ports
+
+This node configures Parallel I/O ports for CPUs with QE support.
+The node should reside in the "soc" node of the tree.  For each
+device that using parallel I/O ports, a child node should be created.
+See the definition of the Pin configuration nodes below for more
+information.
+
+Required properties:
+- device_type : should be "par_io".
+- reg : offset to the register set and its length.
+- num-ports : number of Parallel I/O ports
+
+Example:
+par_io@1400 {
+	reg = <1400 100>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	device_type = "par_io";
+	num-ports = <7>;
+	ucc_pin@01 {
+		......
+	};
+
+Note that "par_io" nodes are obsolete, and should not be used for
+the new device trees. Instead, each Par I/O bank should be represented
+via its own gpio-controller node:
+
+Required properties:
+- #gpio-cells : should be "2".
+- compatible : should be "fsl,<chip>-qe-pario-bank",
+  "fsl,mpc8323-qe-pario-bank".
+- reg : offset to the register set and its length.
+- gpio-controller : node to identify gpio controllers.
+
+Example:
+	qe_pio_a: gpio-controller@1400 {
+		#gpio-cells = <2>;
+		compatible = "fsl,mpc8360-qe-pario-bank",
+		"fsl,mpc8323-qe-pario-bank";
+		reg = <0x1400 0x18>;
+		gpio-controller;
+	  };
+
+	qe_pio_e: gpio-controller@1460 {
+		#gpio-cells = <2>;
+		compatible = "fsl,mpc8360-qe-pario-bank",
+			     "fsl,mpc8323-qe-pario-bank";
+		reg = <0x1460 0x18>;
+		gpio-controller;
+	  };

Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/pincfg.txt

+* Pin configuration nodes
+
+Required properties:
+- linux,phandle : phandle of this node; likely referenced by a QE
+  device.
+- pio-map : array of pin configurations.  Each pin is defined by 6
+  integers.  The six numbers are respectively: port, pin, dir,
+  open_drain, assignment, has_irq.
+  - port : port number of the pin; 0-6 represent port A-G in UM.
+  - pin : pin number in the port.
+  - dir : direction of the pin, should encode as follows:
+
+     0 = The pin is disabled
+     1 = The pin is an output
+     2 = The pin is an input
+     3 = The pin is I/O
+
+  - open_drain : indicates the pin is normal or wired-OR:
+
+     0 = The pin is actively driven as an output
+     1 = The pin is an open-drain driver. As an output, the pin is
+         driven active-low, otherwise it is three-stated.
+
+  - assignment : function number of the pin according to the Pin Assignment
+    tables in User Manual.  Each pin can have up to 4 possible functions in
+    QE and two options for CPM.
+  - has_irq : indicates if the pin is used as source of external
+    interrupts.
+
+Example:
+     ucc_pin@01 {
+	linux,phandle = <140001>;
+	pio-map = <
+	/* port  pin  dir  open_drain  assignment  has_irq */
+		0  3  1  0  1  0 	/* TxD0 */
+		0  4  1  0  1  0 	/* TxD1 */
+		0  5  1  0  1  0 	/* TxD2 */
+		0  6  1  0  1  0 	/* TxD3 */
+		1  6  1  0  3  0 	/* TxD4 */
+		1  7  1  0  1  0 	/* TxD5 */
+		1  9  1  0  2  0 	/* TxD6 */
+		1  a  1  0  2  0 	/* TxD7 */
+		0  9  2  0  1  0 	/* RxD0 */
+		0  a  2  0  1  0 	/* RxD1 */
+		0  b  2  0  1  0 	/* RxD2 */
+		0  c  2  0  1  0 	/* RxD3 */
+		0  d  2  0  1  0 	/* RxD4 */
+		1  1  2  0  2  0 	/* RxD5 */
+		1  0  2  0  2  0 	/* RxD6 */
+		1  4  2  0  2  0 	/* RxD7 */
+		0  7  1  0  1  0 	/* TX_EN */
+		0  8  1  0  1  0 	/* TX_ER */
+		0  f  2  0  1  0 	/* RX_DV */
+		0  10 2  0  1  0 	/* RX_ER */
+		0  0  2  0  1  0 	/* RX_CLK */
+		2  9  1  0  3  0 	/* GTX_CLK - CLK10 */
+		2  8  2  0  1  0>;	/* GTX125 - CLK9 */
+     };
+
+

Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/ucc.txt

+* UCC (Unified Communications Controllers)
+
+Required properties:
+- device_type : should be "network", "hldc", "uart", "transparent"
+  "bisync", "atm", or "serial".
+- compatible : could be "ucc_geth" or "fsl_atm" and so on.
+- cell-index : the ucc number(1-8), corresponding to UCCx in UM.
+- reg : Offset and length of the register set for the device
+- interrupts : <a b> where a is the interrupt number and b is a
+  field that represents an encoding of the sense and level
+  information for the interrupt.  This should be encoded based on
+  the information in section 2) depending on the type of interrupt
+  controller you have.
+- interrupt-parent : the phandle for the interrupt controller that
+  services interrupts for this device.
+- pio-handle : The phandle for the Parallel I/O port configuration.
+- port-number : for UART drivers, the port number to use, between 0 and 3.
+  This usually corresponds to the /dev/ttyQE device, e.g. <0> = /dev/ttyQE0.
+  The port number is added to the minor number of the device.  Unlike the
+  CPM UART driver, the port-number is required for the QE UART driver.
+- soft-uart : for UART drivers, if specified this means the QE UART device
+  driver should use "Soft-UART" mode, which is needed on some SOCs that have
+  broken UART hardware.  Soft-UART is provided via a microcode upload.
+- rx-clock-name: the UCC receive clock source
+  "none": clock source is disabled
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- tx-clock-name: the UCC transmit clock source
+  "none": clock source is disabled
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+The following two properties are deprecated.  rx-clock has been replaced
+with rx-clock-name, and tx-clock has been replaced with tx-clock-name.
+Drivers that currently use the deprecated properties should continue to
+do so, in order to support older device trees, but they should be updated
+to check for the new properties first.
+- rx-clock : represents the UCC receive clock source.
+  0x00 : clock source is disabled;
+  0x1~0x10 : clock source is BRG1~BRG16 respectively;
+  0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
+- tx-clock: represents the UCC transmit clock source;
+  0x00 : clock source is disabled;
+  0x1~0x10 : clock source is BRG1~BRG16 respectively;
+  0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
+
+Required properties for network device_type:
+- mac-address : list of bytes representing the ethernet address.
+- phy-handle : The phandle for the PHY connected to this controller.
+
+Recommended properties:
+- phy-connection-type : a string naming the controller/PHY interface type,
+  i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id" (Internal
+  Delay), "rgmii-txid" (delay on TX only), "rgmii-rxid" (delay on RX only),
+  "tbi", or "rtbi".
+
+Example:
+	ucc@2000 {
+		device_type = "network";
+		compatible = "ucc_geth";
+		cell-index = <1>;
+		reg = <2000 200>;
+		interrupts = <a0 0>;
+		interrupt-parent = <700>;
+		mac-address = [ 00 04 9f 00 23 23 ];
+		rx-clock = "none";
+		tx-clock = "clk9";
+		phy-handle = <212000>;
+		phy-connection-type = "gmii";
+		pio-handle = <140001>;
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt

+* USB (Universal Serial Bus Controller)
+
+Required properties:
+- compatible : could be "qe_udc" or "fhci-hcd".
+- mode : the could be "host" or "slave".
+- reg : Offset and length of the register set for the device
+- interrupts : <a b> where a is the interrupt number and b is a
+  field that represents an encoding of the sense and level
+  information for the interrupt.  This should be encoded based on
+  the information in section 2) depending on the type of interrupt
+  controller you have.
+- interrupt-parent : the phandle for the interrupt controller that
+  services interrupts for this device.
+
+Example(slave):
+	usb@6c0 {
+		compatible = "qe_udc";
+		reg = <6c0 40>;
+		interrupts = <8b 0>;
+		interrupt-parent = <700>;
+		mode = "slave";
+	};

Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt

+* Serial
+
+Currently defined compatibles:
+- fsl,cpm1-smc-uart
+- fsl,cpm2-smc-uart
+- fsl,cpm1-scc-uart
+- fsl,cpm2-scc-uart
+- fsl,qe-uart
+
+Example:
+
+	serial@11a00 {
+		device_type = "serial";
+		compatible = "fsl,mpc8272-scc-uart",
+			     "fsl,cpm2-scc-uart";
+		reg = <11a00 20 8000 100>;
+		interrupts = <28 8>;
+		interrupt-parent = <&PIC>;
+		fsl,cpm-brg = <1>;
+		fsl,cpm-command = <00800000>;
+	};

Documentation/powerpc/dts-bindings/fsl/diu.txt

+* Freescale Display Interface Unit
+
+The Freescale DIU is a LCD controller, with proper hardware, it can also
+drive DVI monitors.
+
+Required properties:
+- compatible : should be "fsl-diu".
+- reg : should contain at least address and length of the DIU register
+  set.
+- Interrupts : one DIU interrupt should be describe here.
+
+Example (MPC8610HPCD):
+	display@2c000 {
+		compatible = "fsl,diu";
+		reg = <0x2c000 100>;
+		interrupts = <72 2>;
+		interrupt-parent = <&mpic>;
+	};

Documentation/powerpc/dts-bindings/fsl/dma.txt

+* Freescale 83xx DMA Controller
+
+Freescale PowerPC 83xx have on chip general purpose DMA controllers.
+
+Required properties:
+
+- compatible        : compatible list, contains 2 entries, first is
+		 "fsl,CHIP-dma", where CHIP is the processor
+		 (mpc8349, mpc8360, etc.) and the second is
+		 "fsl,elo-dma"
+- reg               : <registers mapping for DMA general status reg>
+- ranges		: Should be defined as specified in 1) to describe the
+		  DMA controller channels.
+- cell-index        : controller index.  0 for controller @ 0x8100
+- interrupts        : <interrupt mapping for DMA IRQ>
+- interrupt-parent  : optional, if needed for interrupt mapping
+
+
+- DMA channel nodes:
+        - compatible        : compatible list, contains 2 entries, first is
+			 "fsl,CHIP-dma-channel", where CHIP is the processor
+			 (mpc8349, mpc8350, etc.) and the second is
+			 "fsl,elo-dma-channel"
+        - reg               : <registers mapping for channel>
+        - cell-index        : dma channel index starts at 0.
+
+Optional properties:
+        - interrupts        : <interrupt mapping for DMA channel IRQ>
+			  (on 83xx this is expected to be identical to
+			   the interrupts property of the parent node)
+        - interrupt-parent  : optional, if needed for interrupt mapping
+
+Example:
+	dma@82a8 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,mpc8349-dma", "fsl,elo-dma";
+		reg = <82a8 4>;
+		ranges = <0 8100 1a4>;
+		interrupt-parent = <&ipic>;
+		interrupts = <47 8>;
+		cell-index = <0>;
+		dma-channel@0 {
+			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+			cell-index = <0>;
+			reg = <0 80>;
+		};
+		dma-channel@80 {
+			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+			cell-index = <1>;
+			reg = <80 80>;
+		};
+		dma-channel@100 {
+			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+			cell-index = <2>;
+			reg = <100 80>;
+		};
+		dma-channel@180 {
+			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+			cell-index = <3>;
+			reg = <180 80>;
+		};
+	};
+
+* Freescale 85xx/86xx DMA Controller
+
+Freescale PowerPC 85xx/86xx have on chip general purpose DMA controllers.
+
+Required properties:
+
+- compatible        : compatible list, contains 2 entries, first is
+		 "fsl,CHIP-dma", where CHIP is the processor
+		 (mpc8540, mpc8540, etc.) and the second is
+		 "fsl,eloplus-dma"
+- reg               : <registers mapping for DMA general status reg>
+- cell-index        : controller index.  0 for controller @ 0x21000,
+                                         1 for controller @ 0xc000
+- ranges		: Should be defined as specified in 1) to describe the
+		  DMA controller channels.
+
+- DMA channel nodes:
+        - compatible        : compatible list, contains 2 entries, first is
+			 "fsl,CHIP-dma-channel", where CHIP is the processor
+			 (mpc8540, mpc8560, etc.) and the second is
+			 "fsl,eloplus-dma-channel"
+        - cell-index        : dma channel index starts at 0.
+        - reg               : <registers mapping for channel>
+        - interrupts        : <interrupt mapping for DMA channel IRQ>
+        - interrupt-parent  : optional, if needed for interrupt mapping
+
+Example:
+	dma@21300 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,mpc8540-dma", "fsl,eloplus-dma";
+		reg = <21300 4>;
+		ranges = <0 21100 200>;
+		cell-index = <0>;
+		dma-channel@0 {
+			compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+			reg = <0 80>;
+			cell-index = <0>;
+			interrupt-parent = <&mpic>;
+			interrupts = <14 2>;
+		};
+		dma-channel@80 {
+			compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+			reg = <80 80>;
+			cell-index = <1>;
+			interrupt-parent = <&mpic>;
+			interrupts = <15 2>;
+		};
+		dma-channel@100 {
+			compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+			reg = <100 80>;
+			cell-index = <2>;
+			interrupt-parent = <&mpic>;
+			interrupts = <16 2>;
+		};
+		dma-channel@180 {
+			compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+			reg = <180 80>;
+			cell-index = <3>;
+			interrupt-parent = <&mpic>;
+			interrupts = <17 2>;
+		};
+	};

Documentation/scheduler/sched-domains.txt

@@ -61,10 +61,7 @@ builder by #define'ing ARCH_HASH_SCHED_DOMAIN, and exporting your
 arch_init_sched_domains function. This function will attach domains to all
 CPUs using cpu_attach_domain.
 
-Implementors should change the line
-#undef SCHED_DOMAIN_DEBUG
-to
-#define SCHED_DOMAIN_DEBUG
-in kernel/sched.c as this enables an error checking parse of the sched domains
+The sched-domains debugging infrastructure can be enabled by enabling
+CONFIG_SCHED_DEBUG. This enables an error checking parse of the sched domains
 which should catch most possible errors (described above). It also prints out
 the domain structure in a visual format.

arch/Kconfig

@@ -39,3 +39,6 @@ config HAVE_KRETPROBES
 
 config HAVE_DMA_ATTRS
 	def_bool n
+
+config USE_GENERIC_SMP_HELPERS
+	def_bool n