3565 files changed, 194524 insertions, 125153 deletions

diff --git a/.gitignore b/.gitignore
index d24ad506e79..869e1a3b64b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,6 +3,10 @@
 # subdirectories here. Add them in the ".gitignore" file
 # in that subdirectory instead.
 #
+# NOTE! Please use 'git-ls-files -i --exclude-standard'
+# command after changing this file, to see if there are
+# any tracked files which get ignored after the change.
+#
 # Normal rules
 #
 .*
@@ -18,18 +22,21 @@
 *.lst
 *.symtypes
 *.order
+*.elf
+*.bin
+*.gz
 
 #
 # Top-level generic files
 #
 tags
 TAGS
-vmlinux*
-!vmlinux.lds.S
+vmlinux
 System.map
 Module.markers
 Module.symvers
 !.gitignore
+!.mailmap
 
 #
 # Generated include files
diff --git a/CREDITS b/CREDITS
index 8fec7b3f96d..e97bea06b59 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2611,8 +2611,9 @@ S: Perth, Western Australia
 S: Australia
 
 N: Miguel Ojeda Sandonis
-E: maxextreme@gmail.com
-W: http://maxextreme.googlepages.com/
+E: miguel.ojeda.sandonis@gmail.com
+W: http://miguelojeda.es
+W: http://jair.lab.fi.uva.es/~migojed/
 D: Author of the ks0108, cfag12864b and cfag12864bfb auxiliary display drivers.
 D: Maintainer of the auxiliary display drivers tree (drivers/auxdisplay/*)
 S: C/ Mieses 20, 9-B
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 4bd9ea53912..44f52a4f590 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/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.
diff --git a/Documentation/ABI/testing/sysfs-bus-css b/Documentation/ABI/testing/sysfs-bus-css
new file mode 100644
index 00000000000..b585ec258a0
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-css
@@ -0,0 +1,35 @@
+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
diff --git a/Documentation/ABI/testing/sysfs-firmware-memmap b/Documentation/ABI/testing/sysfs-firmware-memmap
new file mode 100644
index 00000000000..0d99ee6ae02
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-memmap
@@ -0,0 +1,71 @@
+What:		/sys/firmware/memmap/
+Date:		June 2008
+Contact:	Bernhard Walle <bwalle@suse.de>
+Description:
+		On all platforms, the firmware provides a memory map which the
+		kernel reads. The resources from that memory map are registered
+		in the kernel resource tree and exposed to userspace via
+		/proc/iomem (together with other resources).
+
+		However, on most architectures that firmware-provided memory
+		map is modified afterwards by the kernel itself, either because
+		the kernel merges that memory map with other information or
+		just because the user overwrites that memory map via command
+		line.
+
+		kexec needs the raw firmware-provided memory map to setup the
+		parameter segment of the kernel that should be booted with
+		kexec. Also, the raw memory map is useful for debugging. For
+		that reason, /sys/firmware/memmap is an interface that provides
+		the raw memory map to userspace.
+
+		The structure is as follows: Under /sys/firmware/memmap there
+		are subdirectories with the number of the entry as their name:
+
+			/sys/firmware/memmap/0
+			/sys/firmware/memmap/1
+			/sys/firmware/memmap/2
+			/sys/firmware/memmap/3
+			...
+
+		The maximum depends on the number of memory map entries provided
+		by the firmware. The order is just the order that the firmware
+		provides.
+
+		Each directory contains three files:
+
+		start	: The start address (as hexadecimal number with the
+			  '0x' prefix).
+		end	: The end address, inclusive (regardless whether the
+			  firmware provides inclusive or exclusive ranges).
+		type	: Type of the entry as string. See below for a list of
+			  valid types.
+
+		So, for example:
+
+			/sys/firmware/memmap/0/start
+			/sys/firmware/memmap/0/end
+			/sys/firmware/memmap/0/type
+			/sys/firmware/memmap/1/start
+			...
+
+		Currently following types exist:
+
+		  - System RAM
+		  - ACPI Tables
+		  - ACPI Non-volatile Storage
+		  - reserved
+
+		Following shell snippet can be used to display that memory
+		map in a human-readable format:
+
+		-------------------- 8< ----------------------------------------
+		  #!/bin/bash
+		  cd /sys/firmware/memmap
+		  for dir in * ; do
+		      start=$(cat $dir/start)
+		      end=$(cat $dir/end)
+		      type=$(cat $dir/type)
+		      printf "%016x-%016x (%s)\n" $start $[ $end +1] "$type"
+		  done
+		-------------------- >8 ----------------------------------------
diff --git a/Documentation/DocBook/kgdb.tmpl b/Documentation/DocBook/kgdb.tmpl
index 028a8444d95..e8acd1f0345 100644
--- a/Documentation/DocBook/kgdb.tmpl
+++ b/Documentation/DocBook/kgdb.tmpl
@@ -84,10 +84,9 @@
     runs an instance of gdb against the vmlinux file which contains
     the symbols (not boot image such as bzImage, zImage, uImage...).
     In gdb the developer specifies the connection parameters and
-    connects to kgdb.  Depending on which kgdb I/O modules exist in
-    the kernel for a given architecture, it may be possible to debug
-    the test machine's kernel with the development machine using a
-    rs232 or ethernet connection.
+    connects to kgdb.  The type of connection a developer makes with
+    gdb depends on the availability of kgdb I/O modules compiled as
+    builtin's or kernel modules in the test machine's kernel.
     </para>
   </chapter>
   <chapter id="CompilingAKernel">
@@ -223,7 +222,7 @@
   </para>
   <para>
   IMPORTANT NOTE: Using this option with kgdb over the console
-  (kgdboc) or kgdb over ethernet (kgdboe) is not supported.
+  (kgdboc) is not supported.
   </para>
   </sect1>
   </chapter>
@@ -249,18 +248,11 @@
     (gdb) target remote /dev/ttyS0
     </programlisting>
     <para>
-    Example (kgdb to a terminal server):
+    Example (kgdb to a terminal server on tcp port 2012):
     </para>
     <programlisting>
     % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
-    </programlisting>
-    <para>
-    Example (kgdb over ethernet):
-    </para>
-    <programlisting>
-    % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
+    (gdb) target remote 192.168.2.2:2012
     </programlisting>
     <para>
     Once connected, you can debug a kernel the way you would debug an
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 0291ade44c1..619e8caf30d 100644
--- a/Documentation/HOWTO
+++ b/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
diff --git a/Documentation/IRQ-affinity.txt b/Documentation/IRQ-affinity.txt
index 938d7dd0549..b4a615b7840 100644
--- a/Documentation/IRQ-affinity.txt
+++ b/Documentation/IRQ-affinity.txt
@@ -1,17 +1,26 @@
+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.
 
diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index c64158ecde4..a6d32e65d22 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/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
 
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 39ad8f56783..9f711d2df91 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/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.
+"
+}
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 42b01bc2e1b..cf5562cbe35 100644
--- a/Documentation/RCU/checklist.txt
+++ b/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
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 2967a65269d..a342b6e1cc1 100644
--- a/Documentation/RCU/torture.txt
+++ b/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
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index e0d6d99b8f9..e04d643a9f5 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -1,3 +1,11 @@
+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
+
+	rcu_read_lock		synchronize_net		rcu_barrier
+	rcu_read_unlock		synchronize_rcu
+				call_rcu
+
+
+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
 
-	synchronize_net
-	synchronize_sched
-	synchronize_rcu
-	synchronize_srcu
-	call_rcu
-	call_rcu_bh
 
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 9c93a03ea33..118ca6e9404 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -327,6 +327,52 @@ Some people also put extra tags at the end.  They'll just be ignored for
 now, but you can do this to mark internal company procedures or just
 point out some special detail about the sign-off. 
 
+If you are a subsystem or branch maintainer, sometimes you need to slightly
+modify patches you receive in order to merge them, because the code is not
+exactly the same in your tree and the submitters'. If you stick strictly to
+rule (c), you should ask the submitter to rediff, but this is a totally
+counter-productive waste of time and energy. Rule (b) allows you to adjust
+the code, but then it is very impolite to change one submitter's code and
+make him endorse your bugs. To solve this problem, it is recommended that
+you add a line between the last Signed-off-by header and yours, indicating
+the nature of your changes. While there is nothing mandatory about this, it
+seems like prepending the description with your mail and/or name, all
+enclosed in square brackets, is noticeable enough to make it obvious that
+you are responsible for last-minute changes. Example :
+
+	Signed-off-by: Random J Developer <random@developer.example.org>
+	[lucky@maintainer.example.org: struct foo moved from foo.c to foo.h]
+	Signed-off-by: Lucky K Maintainer <lucky@maintainer.example.org>
+
+This practise is particularly helpful if you maintain a stable branch and
+want at the same time to credit the author, track changes, merge the fix,
+and protect the submitter from complaints. Note that under no circumstances
+can you change the author's identity (the From header), as it is the one
+which appears in the changelog.
+
+Special note to back-porters: It seems to be a common and useful practise
+to insert an indication of the origin of a patch at the top of the commit
+message (just after the subject line) to facilitate tracking. For instance,
+here's what we see in 2.6-stable :
+
+    Date:   Tue May 13 19:10:30 2008 +0000
+
+        SCSI: libiscsi regression in 2.6.25: fix nop timer handling
+
+        commit 4cf1043593db6a337f10e006c23c69e5fc93e722 upstream
+
+And here's what appears in 2.4 :
+
+    Date:   Tue May 13 22:12:27 2008 +0200
+
+        wireless, airo: waitbusy() won't delay
+
+        [backport of 2.6 commit b7acbdfbd1f277c1eb23f344f899cfa4cd0bf36a]
+
+Whatever the format, this information provides a valuable help to people
+tracking your trees, and to people trying to trouble-shoot bugs in your
+tree.
+
 
 13) When to use Acked-by: and Cc:
 
diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt
index 8aa7529f825..cd784f46bf8 100644
--- a/Documentation/accounting/taskstats-struct.txt
+++ b/Documentation/accounting/taskstats-struct.txt
@@ -24,6 +24,8 @@ There are three different groups of fields in the struct taskstats:
 
 4) Per-task and per-thread context switch count statistics
 
+5) Time accounting for SMT machines
+
 Future extension should add fields to the end of the taskstats struct, and
 should not change the relative position of each field within the struct.
 
@@ -164,4 +166,8 @@ struct taskstats {
 	__u64	nvcsw;			/* Context voluntary switch counter */
 	__u64	nivcsw;			/* Context involuntary switch counter */
 
+5) Time accounting for SMT machines
+	__u64	ac_utimescaled;		/* utime scaled on frequency etc */
+	__u64	ac_stimescaled;		/* stime scaled on frequency etc */
+	__u64	cpu_scaled_run_real_total; /* scaled cpu_run_real_total */
 }
diff --git a/Documentation/auxdisplay/cfag12864b b/Documentation/auxdisplay/cfag12864b
index b714183d412..eb7be393a51 100644
--- a/Documentation/auxdisplay/cfag12864b
+++ b/Documentation/auxdisplay/cfag12864b
@@ -3,7 +3,7 @@
 	===================================
 
 License:		GPLv2
-Author & Maintainer:	Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:	Miguel Ojeda Sandonis
 Date:			2006-10-27
 
 
@@ -22,7 +22,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
 
-This driver support one cfag12864b display at time.
+This driver supports a cfag12864b LCD.
 
 
 ---------------------
diff --git a/Documentation/auxdisplay/cfag12864b-example.c b/Documentation/auxdisplay/cfag12864b-example.c
index 7bfac354d4c..2caeea5e499 100644
--- a/Documentation/auxdisplay/cfag12864b-example.c
+++ b/Documentation/auxdisplay/cfag12864b-example.c
@@ -4,7 +4,7 @@
  * Description: cfag12864b LCD userspace example program
  *     License: GPLv2
  *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
  *        Date: 2006-10-31
  *
  *  This program is free software; you can redistribute it and/or modify
diff --git a/Documentation/auxdisplay/ks0108 b/Documentation/auxdisplay/ks0108
index 92b03b60c61..8ddda0c8cee 100644
--- a/Documentation/auxdisplay/ks0108
+++ b/Documentation/auxdisplay/ks0108
@@ -3,7 +3,7 @@
 	==========================================
 
 License:		GPLv2
-Author & Maintainer:	Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:	Miguel Ojeda Sandonis
 Date:			2006-10-27
 
 
@@ -21,7 +21,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
 
-This driver support the ks0108 LCD controller.
+This driver supports the ks0108 LCD controller.
 
 
 ---------------------
diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
new file mode 100644
index 00000000000..e9dc8d86adc
--- /dev/null
+++ b/Documentation/block/data-integrity.txt
@@ -0,0 +1,327 @@
+----------------------------------------------------------------------
+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>
diff --git a/Documentation/cciss.txt b/Documentation/cciss.txt
index e65736c6b8b..63e59b8847c 100644
--- a/Documentation/cciss.txt
+++ b/Documentation/cciss.txt
@@ -21,6 +21,11 @@ This driver is known to work with the following cards:
 	* SA E200
 	* SA E200i
 	* SA E500
+	* SA P212
+	* SA P410
+	* SA P410i
+	* SA P411
+	* SA P812
 
 Detecting drive failures:
 -------------------------
diff --git a/Documentation/cgroups.txt b/Documentation/cgroups.txt
index 824fc027447..d9014aa0eb6 100644
--- a/Documentation/cgroups.txt
+++ b/Documentation/cgroups.txt
@@ -390,6 +390,10 @@ If you have several tasks to attach, you have to do it one after another:
 	...
 # /bin/echo PIDn > tasks
 
+You can attach the current shell task by echoing 0:
+
+# echo 0 > tasks
+
 3. Kernel API
 =============
 
diff --git a/Documentation/controllers/devices.txt b/Documentation/controllers/devices.txt
index 4dcea42432c..7cc6e6a6067 100644
--- a/Documentation/controllers/devices.txt
+++ b/Documentation/controllers/devices.txt
@@ -13,7 +13,7 @@ either an integer or * for all.  Access is a composition of r
 The root device cgroup starts with rwm to 'all'.  A child device
 cgroup gets a copy of the parent.  Administrators can then remove
 devices from the whitelist or add new entries.  A child cgroup can
-never receive a device access which is denied its parent.  However
+never receive a device access which is denied by its parent.  However
 when a device access is removed from a parent it will not also be
 removed from the child(ren).
 
@@ -29,7 +29,11 @@ allows cgroup 1 to read and mknod the device usually known as
 
 	echo a > /cgroups/1/devices.deny
 
-will remove the default 'a *:* mrw' entry.
+will remove the default 'a *:* rwm' entry. Doing
+
+	echo a > /cgroups/1/devices.allow
+
+will add the 'a *:* rwm' entry to the whitelist.
 
 3. Security
 
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index fb7b361e6ee..1f5a924d1e5 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -154,13 +154,15 @@ browsing and modifying the cpusets presently known to the kernel.  No
 new system calls are added for cpusets - all support for querying and
 modifying cpusets is via this cpuset file system.
 
-The /proc/<pid>/status file for each task has two added lines,
+The /proc/<pid>/status file for each task has four added lines,
 displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
 and mems_allowed (on which Memory Nodes it may obtain memory),
-in the format seen in the following example:
+in the two formats seen in the following example:
 
   Cpus_allowed:   ffffffff,ffffffff,ffffffff,ffffffff
+  Cpus_allowed_list:      0-127
   Mems_allowed:   ffffffff,ffffffff
+  Mems_allowed_list:      0-63
 
 Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
@@ -199,7 +201,7 @@ using the sched_setaffinity, mbind and set_mempolicy system calls.
 The following rules apply to each cpuset:
 
  - Its CPUs and Memory Nodes must be a subset of its parents.
- - It can only be marked exclusive if its parent is.
+ - It can't be marked exclusive unless its parent is.
  - If its cpu or memory is exclusive, they may not overlap any sibling.
 
 These rules, and the natural hierarchy of cpusets, enable efficient
@@ -345,7 +347,7 @@ is modified to perform an inline check for this PF_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
 
-Similarly, setting 'memory_spread_cache' turns on the flag
+Similarly, setting 'memory_spread_slab' turns on the flag
 PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
 
@@ -542,7 +544,10 @@ otherwise initial value -1 that indicates the cpuset has no request.
    2  : search cores in a package.
    3  : search cpus in a node [= system wide on non-NUMA system]
  ( 4  : search nodes in a chunk of node [on NUMA system] )
- ( 5~ : search system wide [on NUMA system])
+ ( 5  : search system wide [on NUMA system] )
+
+The system default is architecture dependent.  The system default
+can be changed using the relax_domain_level= boot parameter.
 
 This file is per-cpuset and affect the sched domain where the cpuset
 belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
@@ -709,7 +714,10 @@ Now you want to do something with this cpuset.
 
 In this directory you can find several files:
 # ls
-cpus  cpu_exclusive  mems  mem_exclusive mem_hardwall  tasks
+cpu_exclusive  memory_migrate      mems                      tasks
+cpus           memory_pressure     notify_on_release
+mem_exclusive  memory_spread_page  sched_load_balance
+mem_hardwall   memory_spread_slab  sched_relax_domain_level
 
 Reading them will give you information about the state of this cpuset:
 the CPUs and Memory Nodes it can use, the processes that are using
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index b61cb956402..bd699da2466 100644
--- a/Documentation/cputopology.txt
+++ b/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
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 5b3f31faed5..65a1482457a 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/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)
@@ -312,3 +305,12 @@ When:	2.6.26
 Why:	Implementation became generic; users should now include
 	linux/semaphore.h instead.
 Who:	Matthew Wilcox <willy@linux.intel.com>
+
+---------------------------
+
+What:	CONFIG_THERMAL_HWMON
+When:	January 2009
+Why:	This option was introduced just to allow older lm-sensors userspace
+	to keep working over the upgrade to 2.6.26. At the scheduled time of
+	removal fixed lm-sensors (2.x or 3.x) should be readily available.
+Who:	Rene Herman <rene.herman@gmail.com>
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 560f88dc709..80e193d82e2 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/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
 ==========
@@ -139,8 +160,16 @@ commit=nrsec	(*)	Ext4 can be told to sync all its data and metadata
 			Setting it to very large values will improve
 			performance.
 
-barrier=1		This enables/disables barriers.  barrier=0 disables
-			it, barrier=1 enables it.
+barrier=<0|1(*)>	This enables/disables the use of write barriers in
+			the jbd code.  barrier=0 disables, barrier=1 enables.
+			This also requires an IO stack which can support
+			barriers, and if jbd gets an error on a barrier
+			write, it will disable again with a warning.
+			Write barriers enforce proper on-disk ordering
+			of journal commits, making volatile disk write caches
+			safe to use, at some performance penalty.  If
+			your disks are battery-backed in one way or another,
+			disabling barriers may safely improve performance.
 
 orlov		(*)	This enables the new Orlov block allocator. It is
 			enabled by default.
@@ -214,9 +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
@@ -228,10 +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
@@ -239,7 +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
 ==========
@@ -248,7 +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
diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
new file mode 100644
index 00000000000..4dae9a3840b
--- /dev/null
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -0,0 +1,114 @@
+                   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.
+
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index dbc3c6a3650..7f268f327d7 100644
--- a/Documentation/filesystems/proc.txt
+++ b/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:
 
-  > cat /proc/irq/0/smp_affinity 
-  ffffffff
+  > 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.
 
-It's a bitmask, in which you can specify which CPUs can handle the IRQ, you can
-set it by doing:
+The contents of each smp_affinity file is the same by default:
+
+  > cat /proc/irq/0/smp_affinity
+  ffffffff
 
-  > 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
diff --git a/Documentation/filesystems/sysfs-pci.txt b/Documentation/filesystems/sysfs-pci.txt
index 5daa2aaec2c..68ef48839c0 100644
--- a/Documentation/filesystems/sysfs-pci.txt
+++ b/Documentation/filesystems/sysfs-pci.txt
@@ -36,6 +36,7 @@ files, each with their own function.
        local_cpus	   nearby CPU mask (cpumask, ro)
        resource		   PCI resource host addresses (ascii, ro)
        resource0..N	   PCI resource N, if present (binary, mmap)
+       resource0_wc..N_wc  PCI WC map resource N, if prefetchable (binary, mmap)
        rom		   PCI ROM resource, if present (binary, ro)
        subsystem_device	   PCI subsystem device (ascii, ro)
        subsystem_vendor	   PCI subsystem vendor (ascii, ro)
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
new file mode 100644
index 00000000000..f218f616ff6
--- /dev/null
+++ b/Documentation/ftrace.txt
@@ -0,0 +1,1360 @@
+		ftrace - Function Tracer
+		========================
+
+Copyright 2008 Red Hat Inc.
+   Author:   Steven Rostedt <srostedt@redhat.com>
+  License:   The GNU Free Documentation License, Version 1.2
+Reviewers:   Elias Oltmanns, Randy Dunlap, Andrew Morton,
+	     John Kacur, and David Teigland.
+
+Written for: 2.6.27-rc1
+
+Introduction
+------------
+
+Ftrace is an internal tracer designed to help out developers and
+designers of systems to find what is going on inside the kernel.
+It can be used for debugging or analyzing latencies and performance
+issues that take place outside of user-space.
+
+Although ftrace is the function tracer, it also includes an
+infrastructure that allows for other types of tracing. Some of the
+tracers that are currently in ftrace include a tracer to trace
+context switches, the time it takes for a high priority task to
+run after it was woken up, the time interrupts are disabled, and
+more (ftrace allows for tracer plugins, which means that the list of
+tracers can always grow).
+
+
+The File System
+---------------
+
+Ftrace uses the debugfs file system to hold the control files as well
+as the files to display output.
+
+To mount the debugfs system:
+
+  # mkdir /debug
+  # mount -t debugfs nodev /debug
+
+(Note: it is more common to mount at /sys/kernel/debug, but for simplicity
+ this document will use /debug)
+
+That's it! (assuming that you have ftrace configured into your kernel)
+
+After mounting the debugfs, you can see a directory called
+"tracing".  This directory contains the control and output files
+of ftrace. Here is a list of some of the key files:
+
+
+ Note: all time values are in microseconds.
+
+  current_tracer : This is used to set or display the current tracer
+		that is configured.
+
+  available_tracers : This holds the different types of tracers that
+		have been compiled into the kernel. The tracers
+		listed here can be configured by echoing their name
+		into current_tracer.
+
+  tracing_enabled : This sets or displays whether the current_tracer
+		is activated and tracing or not. Echo 0 into this
+		file to disable the tracer or 1 to enable it.
+
+  trace : This file holds the output of the trace in a human readable
+		format (described below).
+
+  latency_trace : This file shows the same trace but the information
+		is organized more to display possible latencies
+		in the system (described below).
+
+  trace_pipe : The output is the same as the "trace" file but this
+		file is meant to be streamed with live tracing.
+		Reads from this file will block until new data
+		is retrieved. Unlike the "trace" and "latency_trace"
+		files, this file is a consumer. This means reading
+		from this file causes sequential reads to display
+		more current data. Once data is read from this
+		file, it is consumed, and will not be read
+		again with a sequential read. The "trace" and
+		"latency_trace" files are static, and if the
+		tracer is not adding more data, they will display
+		the same information every time they are read.
+
+  iter_ctrl : This file lets the user control the amount of data
+		that is displayed in one of the above output
+		files.
+
+  trace_max_latency : Some of the tracers record the max latency.
+		For example, the time interrupts are disabled.
+		This time is saved in this file. The max trace
+		will also be stored, and displayed by either
+		"trace" or "latency_trace".  A new max trace will
+		only be recorded if the latency is greater than
+		the value in this file. (in microseconds)
+
+  trace_entries : This sets or displays the number of trace
+		entries each CPU buffer can hold. The tracer buffers
+		are the same size for each CPU. The displayed number
+		is the size of the CPU buffer and not total size. The
+		trace buffers are allocated in pages (blocks of memory
+		that the kernel uses for allocation, usually 4 KB in size).
+		Since each entry is smaller than a page, if the last
+		allocated page has room for more entries than were
+		requested, the rest of the page is used to allocate
+		entries.
+
+		This can only be updated when the current_tracer
+		is set to "none".
+
+		NOTE: It is planned on changing the allocated buffers
+		      from being the number of possible CPUS to
+		      the number of online CPUS.
+
+  tracing_cpumask : This is a mask that lets the user only trace
+		on specified CPUS. The format is a hex string
+		representing the CPUS.
+
+  set_ftrace_filter : When dynamic ftrace is configured in (see the
+		section below "dynamic ftrace"), the code is dynamically
+		modified (code text rewrite) to disable calling of the
+		function profiler (mcount). This lets tracing be configured
+		in with practically no overhead in performance.  This also
+		has a side effect of enabling or disabling specific functions
+		to be traced. Echoing names of functions into this file
+		will limit the trace to only those functions.
+
+  set_ftrace_notrace: This has an effect opposite to that of
+		set_ftrace_filter. Any function that is added here will not
+		be traced. If a function exists in both set_ftrace_filter
+		and set_ftrace_notrace,	the function will _not_ be traced.
+
+  available_filter_functions : When a function is encountered the first
+		time by the dynamic tracer, it is recorded and
+		later the call is converted into a nop. This file
+		lists the functions that have been recorded
+		by the dynamic tracer and these functions can
+		be used to set the ftrace filter by the above
+		"set_ftrace_filter" file. (See the section "dynamic ftrace"
+		below for more details).
+
+
+The Tracers
+-----------
+
+Here is the list of current tracers that may be configured.
+
+  ftrace - function tracer that uses mcount to trace all functions.
+
+  sched_switch - traces the context switches between tasks.
+
+  irqsoff - traces the areas that disable interrupts and saves
+  		the trace with the longest max latency.
+		See tracing_max_latency.  When a new max is recorded,
+		it replaces the old trace. It is best to view this
+		trace via the latency_trace file.
+
+  preemptoff - Similar to irqsoff but traces and records the amount of
+		time for which preemption is disabled.
+
+  preemptirqsoff - Similar to irqsoff and preemptoff, but traces and
+		 records the largest time for which irqs and/or preemption
+		 is disabled.
+
+  wakeup - Traces and records the max latency that it takes for
+		the highest priority task to get scheduled after
+		it has been woken up.
+
+  none - This is not a tracer. To remove all tracers from tracing
+		simply echo "none" into current_tracer.
+
+
+Examples of using the tracer
+----------------------------
+
+Here are typical examples of using the tracers when controlling them only
+with the debugfs interface (without using any user-land utilities).
+
+Output format:
+--------------
+
+Here is an example of the output format of the file "trace"
+
+                             --------
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4251  [01] 10152.583854: path_put <-path_walk
+            bash-4251  [01] 10152.583855: dput <-path_put
+            bash-4251  [01] 10152.583855: _atomic_dec_and_lock <-dput
+                             --------
+
+A header is printed with the tracer name that is represented by the trace.
+In this case the tracer is "ftrace". Then a header showing the format. Task
+name "bash", the task PID "4251", the CPU that it was running on
+"01", the timestamp in <secs>.<usecs> format, the function name that was
+traced "path_put" and the parent function that called this function
+"path_walk". The timestamp is the time at which the function was
+entered.
+
+The sched_switch tracer also includes tracing of task wakeups and
+context switches.
+
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +  2916:115:S
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +    10:115:S
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R ==>    10:115:R
+        events/1-10    [01]  1453.070013:     10:115:S ==>  2916:115:R
+     kondemand/1-2916  [01]  1453.070013:   2916:115:S ==>     7:115:R
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:S ==>     0:140:R
+
+Wake ups are represented by a "+" and the context switches are shown as
+"==>".  The format is:
+
+ Context switches:
+
+       Previous task              Next Task
+
+  <pid>:<prio>:<state>  ==>  <pid>:<prio>:<state>
+
+ Wake ups:
+
+       Current task               Task waking up
+
+  <pid>:<prio>:<state>    +  <pid>:<prio>:<state>
+
+The prio is the internal kernel priority, which is the inverse of the
+priority that is usually displayed by user-space tools. Zero represents
+the highest priority (99). Prio 100 starts the "nice" priorities with
+100 being equal to nice -20 and 139 being nice 19. The prio "140" is
+reserved for the idle task which is the lowest priority thread (pid 0).
+
+
+Latency trace format
+--------------------
+
+For traces that display latency times, the latency_trace file gives
+somewhat more information to see why a latency happened. Here is a typical
+trace.
+
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 97 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: apic_timer_interrupt
+ => ended at:   do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+  <idle>-0     0d..1    0us+: trace_hardirqs_off_thunk (apic_timer_interrupt)
+  <idle>-0     0d.s.   97us : __do_softirq (do_softirq)
+  <idle>-0     0d.s1   98us : trace_hardirqs_on (do_softirq)
+
+
+
+This shows that the current tracer is "irqsoff" tracing the time for which
+interrupts were disabled. It gives the trace version and the version
+of the kernel upon which this was executed on (2.6.26-rc8). Then it displays
+the max latency in microsecs (97 us). The number of trace entries displayed
+and the total number recorded (both are three: #3/3). The type of
+preemption that was used (PREEMPT). VP, KP, SP, and HP are always zero
+and are reserved for later use. #P is the number of online CPUS (#P:2).
+
+The task is the process that was running when the latency occurred.
+(swapper pid: 0).
+
+The start and stop (the functions in which the interrupts were disabled and
+enabled respectively) that caused the latencies:
+
+  apic_timer_interrupt is where the interrupts were disabled.
+  do_softirq is where they were enabled again.
+
+The next lines after the header are the trace itself. The header
+explains which is which.
+
+  cmd: The name of the process in the trace.
+
+  pid: The PID of that process.
+
+  CPU#: The CPU which the process was running on.
+
+  irqs-off: 'd' interrupts are disabled. '.' otherwise.
+
+  need-resched: 'N' task need_resched is set, '.' otherwise.
+
+  hardirq/softirq:
+	'H' - hard irq occurred inside a softirq.
+	'h' - hard irq is running
+	's' - soft irq is running
+	'.' - normal context.
+
+  preempt-depth: The level of preempt_disabled
+
+The above is mostly meaningful for kernel developers.
+
+  time: This differs from the trace file output. The trace file output
+	includes an absolute timestamp. The timestamp used by the
+	latency_trace file is relative to the start of the trace.
+
+  delay: This is just to help catch your eye a bit better. And
+	needs to be fixed to be only relative to the same CPU.
+	The marks are determined by the difference between this
+	current trace and the next trace.
+	 '!' - greater than preempt_mark_thresh (default 100)
+	 '+' - greater than 1 microsecond
+	 ' ' - less than or equal to 1 microsecond.
+
+  The rest is the same as the 'trace' file.
+
+
+iter_ctrl
+---------
+
+The iter_ctrl file is used to control what gets printed in the trace
+output. To see what is available, simply cat the file:
+
+  cat /debug/tracing/iter_ctrl
+  print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
+ noblock nostacktrace nosched-tree
+
+To disable one of the options, echo in the option prepended with "no".
+
+  echo noprint-parent > /debug/tracing/iter_ctrl
+
+To enable an option, leave off the "no".
+
+  echo sym-offset > /debug/tracing/iter_ctrl
+
+Here are the available options:
+
+  print-parent - On function traces, display the calling function
+		as well as the function being traced.
+
+  print-parent:
+   bash-4000  [01]  1477.606694: simple_strtoul <-strict_strtoul
+
+  noprint-parent:
+   bash-4000  [01]  1477.606694: simple_strtoul
+
+
+  sym-offset - Display not only the function name, but also the offset
+		in the function. For example, instead of seeing just
+		"ktime_get", you will see "ktime_get+0xb/0x20".
+
+  sym-offset:
+   bash-4000  [01]  1477.606694: simple_strtoul+0x6/0xa0
+
+  sym-addr - this will also display the function address as well as
+		the function name.
+
+  sym-addr:
+   bash-4000  [01]  1477.606694: simple_strtoul <c0339346>
+
+  verbose - This deals with the latency_trace file.
+
+    bash  4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \
+    (+0.000ms): simple_strtoul (strict_strtoul)
+
+  raw - This will display raw numbers. This option is best for use with
+	user applications that can translate the raw numbers better than
+	having it done in the kernel.
+
+  hex - Similar to raw, but the numbers will be in a hexadecimal format.
+
+  bin - This will print out the formats in raw binary.
+
+  block - TBD (needs update)
+
+  stacktrace - This is one of the options that changes the trace itself.
+		When a trace is recorded, so is the stack of functions.
+		This allows for back traces of trace sites.
+
+  sched-tree - TBD (any users??)
+
+
+sched_switch
+------------
+
+This tracer simply records schedule switches. Here is an example
+of how to use it.
+
+ # echo sched_switch > /debug/tracing/current_tracer
+ # echo 1 > /debug/tracing/tracing_enabled
+ # sleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+
+# tracer: sched_switch
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-3997  [01]   240.132281:   3997:120:R   +  4055:120:R
+            bash-3997  [01]   240.132284:   3997:120:R ==>  4055:120:R
+           sleep-4055  [01]   240.132371:   4055:120:S ==>  3997:120:R
+            bash-3997  [01]   240.132454:   3997:120:R   +  4055:120:S
+            bash-3997  [01]   240.132457:   3997:120:R ==>  4055:120:R
+           sleep-4055  [01]   240.132460:   4055:120:D ==>  3997:120:R
+            bash-3997  [01]   240.132463:   3997:120:R   +  4055:120:D
+            bash-3997  [01]   240.132465:   3997:120:R ==>  4055:120:R
+          <idle>-0     [00]   240.132589:      0:140:R   +     4:115:S
+          <idle>-0     [00]   240.132591:      0:140:R ==>     4:115:R
+     ksoftirqd/0-4     [00]   240.132595:      4:115:S ==>     0:140:R
+          <idle>-0     [00]   240.132598:      0:140:R   +     4:115:S
+          <idle>-0     [00]   240.132599:      0:140:R ==>     4:115:R
+     ksoftirqd/0-4     [00]   240.132603:      4:115:S ==>     0:140:R
+           sleep-4055  [01]   240.133058:   4055:120:S ==>  3997:120:R
+ [...]
+
+
+As we have discussed previously about this format, the header shows
+the name of the trace and points to the options. The "FUNCTION"
+is a misnomer since here it represents the wake ups and context
+switches.
+
+The sched_switch file only lists the wake ups (represented with '+')
+and context switches ('==>') with the previous task or current task
+first followed by the next task or task waking up. The format for both
+of these is PID:KERNEL-PRIO:TASK-STATE. Remember that the KERNEL-PRIO
+is the inverse of the actual priority with zero (0) being the highest
+priority and the nice values starting at 100 (nice -20). Below is
+a quick chart to map the kernel priority to user land priorities.
+
+  Kernel priority: 0 to 99    ==> user RT priority 99 to 0
+  Kernel priority: 100 to 139 ==> user nice -20 to 19
+  Kernel priority: 140        ==> idle task priority
+
+The task states are:
+
+ R - running : wants to run, may not actually be running
+ S - sleep   : process is waiting to be woken up (handles signals)
+ D - disk sleep (uninterruptible sleep) : process must be woken up
+					(ignores signals)
+ T - stopped : process suspended
+ t - traced  : process is being traced (with something like gdb)
+ Z - zombie  : process waiting to be cleaned up
+ X - unknown
+
+
+ftrace_enabled
+--------------
+
+The following tracers (listed below) give different output depending
+on whether or not the sysctl ftrace_enabled is set. To set ftrace_enabled,
+one can either use the sysctl function or set it via the proc
+file system interface.
+
+  sysctl kernel.ftrace_enabled=1
+
+ or
+
+  echo 1 > /proc/sys/kernel/ftrace_enabled
+
+To disable ftrace_enabled simply replace the '1' with '0' in
+the above commands.
+
+When ftrace_enabled is set the tracers will also record the functions
+that are within the trace. The descriptions of the tracers
+will also show an example with ftrace enabled.
+
+
+irqsoff
+-------
+
+When interrupts are disabled, the CPU can not react to any other
+external event (besides NMIs and SMIs). This prevents the timer
+interrupt from triggering or the mouse interrupt from letting the
+kernel know of a new mouse event. The result is a latency with the
+reaction time.
+
+The irqsoff tracer tracks the time for which interrupts are disabled.
+When a new maximum latency is hit, the tracer saves the trace leading up
+to that latency point so that every time a new maximum is reached, the old
+saved trace is discarded and the new trace is saved.
+
+To reset the maximum, echo 0 into tracing_max_latency. Here is an
+example:
+
+ # echo irqsoff > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26
+--------------------------------------------------------------------
+ latency: 12 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: bash-3730 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: sys_setpgid
+ => ended at:   sys_setpgid
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    bash-3730  1d...    0us : _write_lock_irq (sys_setpgid)
+    bash-3730  1d..1    1us+: _write_unlock_irq (sys_setpgid)
+    bash-3730  1d..2   14us : trace_hardirqs_on (sys_setpgid)
+
+
+Here we see that that we had a latency of 12 microsecs (which is
+very good). The _write_lock_irq in sys_setpgid disabled interrupts.
+The difference between the 12 and the displayed timestamp 14us occurred
+because the clock was incremented between the time of recording the max
+latency and the time of recording the function that had that latency.
+
+Note the above example had ftrace_enabled not set. If we set the
+ftrace_enabled, we get a much larger output:
+
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 50 us, #101/101, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: ls-4339 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: __alloc_pages_internal
+ => ended at:   __alloc_pages_internal
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+      ls-4339  0...1    0us+: get_page_from_freelist (__alloc_pages_internal)
+      ls-4339  0d..1    3us : rmqueue_bulk (get_page_from_freelist)
+      ls-4339  0d..1    3us : _spin_lock (rmqueue_bulk)
+      ls-4339  0d..1    4us : add_preempt_count (_spin_lock)
+      ls-4339  0d..2    4us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    5us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2    5us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2    6us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    6us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2    7us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2    7us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    8us : __rmqueue_smallest (__rmqueue)
+[...]
+      ls-4339  0d..2   46us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2   47us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2   47us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2   48us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2   48us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2   49us : _spin_unlock (rmqueue_bulk)
+      ls-4339  0d..2   49us : sub_preempt_count (_spin_unlock)
+      ls-4339  0d..1   50us : get_page_from_freelist (__alloc_pages_internal)
+      ls-4339  0d..2   51us : trace_hardirqs_on (__alloc_pages_internal)
+
+
+
+Here we traced a 50 microsecond latency. But we also see all the
+functions that were called during that time. Note that by enabling
+function tracing, we incur an added overhead. This overhead may
+extend the latency times. But nevertheless, this trace has provided
+some very helpful debugging information.
+
+
+preemptoff
+----------
+
+When preemption is disabled, we may be able to receive interrupts but
+the task cannot be preempted and a higher priority task must wait
+for preemption to be enabled again before it can preempt a lower
+priority task.
+
+The preemptoff tracer traces the places that disable preemption.
+Like the irqsoff tracer, it records the maximum latency for which preemption
+was disabled. The control of preemptoff tracer is much like the irqsoff
+tracer.
+
+ # echo preemptoff > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: preemptoff
+#
+preemptoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 29 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: do_IRQ
+ => ended at:   __do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    sshd-4261  0d.h.    0us+: irq_enter (do_IRQ)
+    sshd-4261  0d.s.   29us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s1   30us : trace_preempt_on (__do_softirq)
+
+
+This has some more changes. Preemption was disabled when an interrupt
+came in (notice the 'h'), and was enabled while doing a softirq.
+(notice the 's'). But we also see that interrupts have been disabled
+when entering the preempt off section and leaving it (the 'd').
+We do not know if interrupts were enabled in the mean time.
+
+# tracer: preemptoff
+#
+preemptoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 63 us, #87/87, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: remove_wait_queue
+ => ended at:   __do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    sshd-4261  0d..1    0us : _spin_lock_irqsave (remove_wait_queue)
+    sshd-4261  0d..1    1us : _spin_unlock_irqrestore (remove_wait_queue)
+    sshd-4261  0d..1    2us : do_IRQ (common_interrupt)
+    sshd-4261  0d..1    2us : irq_enter (do_IRQ)
+    sshd-4261  0d..1    2us : idle_cpu (irq_enter)
+    sshd-4261  0d..1    3us : add_preempt_count (irq_enter)
+    sshd-4261  0d.h1    3us : idle_cpu (irq_enter)
+    sshd-4261  0d.h.    4us : handle_fasteoi_irq (do_IRQ)
+[...]
+    sshd-4261  0d.h.   12us : add_preempt_count (_spin_lock)
+    sshd-4261  0d.h1   12us : ack_ioapic_quirk_irq (handle_fasteoi_irq)
+    sshd-4261  0d.h1   13us : move_native_irq (ack_ioapic_quirk_irq)
+    sshd-4261  0d.h1   13us : _spin_unlock (handle_fasteoi_irq)
+    sshd-4261  0d.h1   14us : sub_preempt_count (_spin_unlock)
+    sshd-4261  0d.h1   14us : irq_exit (do_IRQ)
+    sshd-4261  0d.h1   15us : sub_preempt_count (irq_exit)
+    sshd-4261  0d..2   15us : do_softirq (irq_exit)
+    sshd-4261  0d...   15us : __do_softirq (do_softirq)
+    sshd-4261  0d...   16us : __local_bh_disable (__do_softirq)
+    sshd-4261  0d...   16us+: add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s4   20us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s4   21us : sub_preempt_count (local_bh_enable)
+    sshd-4261  0d.s5   21us : sub_preempt_count (local_bh_enable)
+[...]
+    sshd-4261  0d.s6   41us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s6   42us : sub_preempt_count (local_bh_enable)
+    sshd-4261  0d.s7   42us : sub_preempt_count (local_bh_enable)
+    sshd-4261  0d.s5   43us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s5   43us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s6   44us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s5   44us : add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s5   45us : sub_preempt_count (local_bh_enable)
+[...]
+    sshd-4261  0d.s.   63us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s1   64us : trace_preempt_on (__do_softirq)
+
+
+The above is an example of the preemptoff trace with ftrace_enabled
+set. Here we see that interrupts were disabled the entire time.
+The irq_enter code lets us know that we entered an interrupt 'h'.
+Before that, the functions being traced still show that it is not
+in an interrupt, but we can see from the functions themselves that
+this is not the case.
+
+Notice that __do_softirq when called does not have a preempt_count.
+It may seem that we missed a preempt enabling. What really happened
+is that the preempt count is held on the thread's stack and we
+switched to the softirq stack (4K stacks in effect). The code
+does not copy the preempt count, but because interrupts are disabled,
+we do not need to worry about it. Having a tracer like this is good
+for letting people know what really happens inside the kernel.
+
+
+preemptirqsoff
+--------------
+
+Knowing the locations that have interrupts disabled or preemption
+disabled for the longest times is helpful. But sometimes we would
+like to know when either preemption and/or interrupts are disabled.
+
+Consider the following code:
+
+    local_irq_disable();
+    call_function_with_irqs_off();
+    preempt_disable();
+    call_function_with_irqs_and_preemption_off();
+    local_irq_enable();
+    call_function_with_preemption_off();
+    preempt_enable();
+
+The irqsoff tracer will record the total length of
+call_function_with_irqs_off() and
+call_function_with_irqs_and_preemption_off().
+
+The preemptoff tracer will record the total length of
+call_function_with_irqs_and_preemption_off() and
+call_function_with_preemption_off().
+
+But neither will trace the time that interrupts and/or preemption
+is disabled. This total time is the time that we can not schedule.
+To record this time, use the preemptirqsoff tracer.
+
+Again, using this trace is much like the irqsoff and preemptoff tracers.
+
+ # echo preemptirqsoff > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: preemptirqsoff
+#
+preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 293 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: ls-4860 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: apic_timer_interrupt
+ => ended at:   __do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+      ls-4860  0d...    0us!: trace_hardirqs_off_thunk (apic_timer_interrupt)
+      ls-4860  0d.s.  294us : _local_bh_enable (__do_softirq)
+      ls-4860  0d.s1  294us : trace_preempt_on (__do_softirq)
+
+
+
+The trace_hardirqs_off_thunk is called from assembly on x86 when
+interrupts are disabled in the assembly code. Without the function
+tracing, we do not know if interrupts were enabled within the preemption
+points. We do see that it started with preemption enabled.
+
+Here is a trace with ftrace_enabled set:
+
+
+# tracer: preemptirqsoff
+#
+preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 105 us, #183/183, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: write_chan
+ => ended at:   __do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+      ls-4473  0.N..    0us : preempt_schedule (write_chan)
+      ls-4473  0dN.1    1us : _spin_lock (schedule)
+      ls-4473  0dN.1    2us : add_preempt_count (_spin_lock)
+      ls-4473  0d..2    2us : put_prev_task_fair (schedule)
+[...]
+      ls-4473  0d..2   13us : set_normalized_timespec (ktime_get_ts)
+      ls-4473  0d..2   13us : __switch_to (schedule)
+    sshd-4261  0d..2   14us : finish_task_switch (schedule)
+    sshd-4261  0d..2   14us : _spin_unlock_irq (finish_task_switch)
+    sshd-4261  0d..1   15us : add_preempt_count (_spin_lock_irqsave)
+    sshd-4261  0d..2   16us : _spin_unlock_irqrestore (hrtick_set)
+    sshd-4261  0d..2   16us : do_IRQ (common_interrupt)
+    sshd-4261  0d..2   17us : irq_enter (do_IRQ)
+    sshd-4261  0d..2   17us : idle_cpu (irq_enter)
+    sshd-4261  0d..2   18us : add_preempt_count (irq_enter)
+    sshd-4261  0d.h2   18us : idle_cpu (irq_enter)
+    sshd-4261  0d.h.   18us : handle_fasteoi_irq (do_IRQ)
+    sshd-4261  0d.h.   19us : _spin_lock (handle_fasteoi_irq)
+    sshd-4261  0d.h.   19us : add_preempt_count (_spin_lock)
+    sshd-4261  0d.h1   20us : _spin_unlock (handle_fasteoi_irq)
+    sshd-4261  0d.h1   20us : sub_preempt_count (_spin_unlock)
+[...]
+    sshd-4261  0d.h1   28us : _spin_unlock (handle_fasteoi_irq)
+    sshd-4261  0d.h1   29us : sub_preempt_count (_spin_unlock)
+    sshd-4261  0d.h2   29us : irq_exit (do_IRQ)
+    sshd-4261  0d.h2   29us : sub_preempt_count (irq_exit)
+    sshd-4261  0d..3   30us : do_softirq (irq_exit)
+    sshd-4261  0d...   30us : __do_softirq (do_softirq)
+    sshd-4261  0d...   31us : __local_bh_disable (__do_softirq)
+    sshd-4261  0d...   31us+: add_preempt_count (__local_bh_disable)
+    sshd-4261  0d.s4   34us : add_preempt_count (__local_bh_disable)
+[...]
+    sshd-4261  0d.s3   43us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s4   44us : sub_preempt_count (local_bh_enable_ip)
+    sshd-4261  0d.s3   44us : smp_apic_timer_interrupt (apic_timer_interrupt)
+    sshd-4261  0d.s3   45us : irq_enter (smp_apic_timer_interrupt)
+    sshd-4261  0d.s3   45us : idle_cpu (irq_enter)
+    sshd-4261  0d.s3   46us : add_preempt_count (irq_enter)
+    sshd-4261  0d.H3   46us : idle_cpu (irq_enter)
+    sshd-4261  0d.H3   47us : hrtimer_interrupt (smp_apic_timer_interrupt)
+    sshd-4261  0d.H3   47us : ktime_get (hrtimer_interrupt)
+[...]
+    sshd-4261  0d.H3   81us : tick_program_event (hrtimer_interrupt)
+    sshd-4261  0d.H3   82us : ktime_get (tick_program_event)
+    sshd-4261  0d.H3   82us : ktime_get_ts (ktime_get)
+    sshd-4261  0d.H3   83us : getnstimeofday (ktime_get_ts)
+    sshd-4261  0d.H3   83us : set_normalized_timespec (ktime_get_ts)
+    sshd-4261  0d.H3   84us : clockevents_program_event (tick_program_event)
+    sshd-4261  0d.H3   84us : lapic_next_event (clockevents_program_event)
+    sshd-4261  0d.H3   85us : irq_exit (smp_apic_timer_interrupt)
+    sshd-4261  0d.H3   85us : sub_preempt_count (irq_exit)
+    sshd-4261  0d.s4   86us : sub_preempt_count (irq_exit)
+    sshd-4261  0d.s3   86us : add_preempt_count (__local_bh_disable)
+[...]
+    sshd-4261  0d.s1   98us : sub_preempt_count (net_rx_action)
+    sshd-4261  0d.s.   99us : add_preempt_count (_spin_lock_irq)
+    sshd-4261  0d.s1   99us+: _spin_unlock_irq (run_timer_softirq)
+    sshd-4261  0d.s.  104us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s.  104us : sub_preempt_count (_local_bh_enable)
+    sshd-4261  0d.s.  105us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s1  105us : trace_preempt_on (__do_softirq)
+
+
+This is a very interesting trace. It started with the preemption of
+the ls task. We see that the task had the "need_resched" bit set
+via the 'N' in the trace.  Interrupts were disabled before the spin_lock
+at the beginning of the trace. We see that a schedule took place to run
+sshd.  When the interrupts were enabled, we took an interrupt.
+On return from the interrupt handler, the softirq ran. We took another
+interrupt while running the softirq as we see from the capital 'H'.
+
+
+wakeup
+------
+
+In a Real-Time environment it is very important to know the wakeup
+time it takes for the highest priority task that is woken up to the
+time that it executes. This is also known as "schedule latency".
+I stress the point that this is about RT tasks. It is also important
+to know the scheduling latency of non-RT tasks, but the average
+schedule latency is better for non-RT tasks. Tools like
+LatencyTop are more appropriate for such measurements.
+
+Real-Time environments are interested in the worst case latency.
+That is the longest latency it takes for something to happen, and
+not the average. We can have a very fast scheduler that may only
+have a large latency once in a while, but that would not work well
+with Real-Time tasks.  The wakeup tracer was designed to record
+the worst case wakeups of RT tasks. Non-RT tasks are not recorded
+because the tracer only records one worst case and tracing non-RT
+tasks that are unpredictable will overwrite the worst case latency
+of RT tasks.
+
+Since this tracer only deals with RT tasks, we will run this slightly
+differently than we did with the previous tracers. Instead of performing
+an 'ls', we will run 'sleep 1' under 'chrt' which changes the
+priority of the task.
+
+ # echo wakeup > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # chrt -f 5 sleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: wakeup
+#
+wakeup latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 4 us, #2/2, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sleep-4901 (uid:0 nice:0 policy:1 rt_prio:5)
+    -----------------
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+  <idle>-0     1d.h4    0us+: try_to_wake_up (wake_up_process)
+  <idle>-0     1d..4    4us : schedule (cpu_idle)
+
+
+
+Running this on an idle system, we see that it only took 4 microseconds
+to perform the task switch.  Note, since the trace marker in the
+schedule is before the actual "switch", we stop the tracing when
+the recorded task is about to schedule in. This may change if
+we add a new marker at the end of the scheduler.
+
+Notice that the recorded task is 'sleep' with the PID of 4901 and it
+has an rt_prio of 5. This priority is user-space priority and not
+the internal kernel priority. The policy is 1 for SCHED_FIFO and 2
+for SCHED_RR.
+
+Doing the same with chrt -r 5 and ftrace_enabled set.
+
+# tracer: wakeup
+#
+wakeup latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 50 us, #60/60, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sleep-4068 (uid:0 nice:0 policy:2 rt_prio:5)
+    -----------------
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+ksoftirq-7     1d.H3    0us : try_to_wake_up (wake_up_process)
+ksoftirq-7     1d.H4    1us : sub_preempt_count (marker_probe_cb)
+ksoftirq-7     1d.H3    2us : check_preempt_wakeup (try_to_wake_up)
+ksoftirq-7     1d.H3    3us : update_curr (check_preempt_wakeup)
+ksoftirq-7     1d.H3    4us : calc_delta_mine (update_curr)
+ksoftirq-7     1d.H3    5us : __resched_task (check_preempt_wakeup)
+ksoftirq-7     1d.H3    6us : task_wake_up_rt (try_to_wake_up)
+ksoftirq-7     1d.H3    7us : _spin_unlock_irqrestore (try_to_wake_up)
+[...]
+ksoftirq-7     1d.H2   17us : irq_exit (smp_apic_timer_interrupt)
+ksoftirq-7     1d.H2   18us : sub_preempt_count (irq_exit)
+ksoftirq-7     1d.s3   19us : sub_preempt_count (irq_exit)
+ksoftirq-7     1..s2   20us : rcu_process_callbacks (__do_softirq)
+[...]
+ksoftirq-7     1..s2   26us : __rcu_process_callbacks (rcu_process_callbacks)
+ksoftirq-7     1d.s2   27us : _local_bh_enable (__do_softirq)
+ksoftirq-7     1d.s2   28us : sub_preempt_count (_local_bh_enable)
+ksoftirq-7     1.N.3   29us : sub_preempt_count (ksoftirqd)
+ksoftirq-7     1.N.2   30us : _cond_resched (ksoftirqd)
+ksoftirq-7     1.N.2   31us : __cond_resched (_cond_resched)
+ksoftirq-7     1.N.2   32us : add_preempt_count (__cond_resched)
+ksoftirq-7     1.N.2   33us : schedule (__cond_resched)
+ksoftirq-7     1.N.2   33us : add_preempt_count (schedule)
+ksoftirq-7     1.N.3   34us : hrtick_clear (schedule)
+ksoftirq-7     1dN.3   35us : _spin_lock (schedule)
+ksoftirq-7     1dN.3   36us : add_preempt_count (_spin_lock)
+ksoftirq-7     1d..4   37us : put_prev_task_fair (schedule)
+ksoftirq-7     1d..4   38us : update_curr (put_prev_task_fair)
+[...]
+ksoftirq-7     1d..5   47us : _spin_trylock (tracing_record_cmdline)
+ksoftirq-7     1d..5   48us : add_preempt_count (_spin_trylock)
+ksoftirq-7     1d..6   49us : _spin_unlock (tracing_record_cmdline)
+ksoftirq-7     1d..6   49us : sub_preempt_count (_spin_unlock)
+ksoftirq-7     1d..4   50us : schedule (__cond_resched)
+
+The interrupt went off while running ksoftirqd. This task runs at
+SCHED_OTHER. Why did not we see the 'N' set early? This may be
+a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K stacks
+configured, the interrupt and softirq run with their own stack.
+Some information is held on the top of the task's stack (need_resched
+and preempt_count are both stored there). The setting of the NEED_RESCHED
+bit is done directly to the task's stack, but the reading of the
+NEED_RESCHED is done by looking at the current stack, which in this case
+is the stack for the hard interrupt. This hides the fact that NEED_RESCHED
+has been set. We do not see the 'N' until we switch back to the task's
+assigned stack.
+
+ftrace
+------
+
+ftrace is not only the name of the tracing infrastructure, but it
+is also a name of one of the tracers. The tracer is the function
+tracer. Enabling the function tracer can be done from the
+debug file system. Make sure the ftrace_enabled is set otherwise
+this tracer is a nop.
+
+ # sysctl kernel.ftrace_enabled=1
+ # echo ftrace > /debug/tracing/current_tracer
+ # echo 1 > /debug/tracing/tracing_enabled
+ # usleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4003  [00]   123.638713: finish_task_switch <-schedule
+            bash-4003  [00]   123.638714: _spin_unlock_irq <-finish_task_switch
+            bash-4003  [00]   123.638714: sub_preempt_count <-_spin_unlock_irq
+            bash-4003  [00]   123.638715: hrtick_set <-schedule
+            bash-4003  [00]   123.638715: _spin_lock_irqsave <-hrtick_set
+            bash-4003  [00]   123.638716: add_preempt_count <-_spin_lock_irqsave
+            bash-4003  [00]   123.638716: _spin_unlock_irqrestore <-hrtick_set
+            bash-4003  [00]   123.638717: sub_preempt_count <-_spin_unlock_irqrestore
+            bash-4003  [00]   123.638717: hrtick_clear <-hrtick_set
+            bash-4003  [00]   123.638718: sub_preempt_count <-schedule
+            bash-4003  [00]   123.638718: sub_preempt_count <-preempt_schedule
+            bash-4003  [00]   123.638719: wait_for_completion <-__stop_machine_run
+            bash-4003  [00]   123.638719: wait_for_common <-wait_for_completion
+            bash-4003  [00]   123.638720: _spin_lock_irq <-wait_for_common
+            bash-4003  [00]   123.638720: add_preempt_count <-_spin_lock_irq
+[...]
+
+
+Note: ftrace uses ring buffers to store the above entries. The newest data
+may overwrite the oldest data. Sometimes using echo to stop the trace
+is not sufficient because the tracing could have overwritten the data
+that you wanted to record. For this reason, it is sometimes better to
+disable tracing directly from a program. This allows you to stop the
+tracing at the point that you hit the part that you are interested in.
+To disable the tracing directly from a C program, something like following
+code snippet can be used:
+
+int trace_fd;
+[...]
+int main(int argc, char *argv[]) {
+	[...]
+	trace_fd = open("/debug/tracing/tracing_enabled", O_WRONLY);
+	[...]
+	if (condition_hit()) {
+		write(trace_fd, "0", 1);
+	}
+	[...]
+}
+
+Note: Here we hard coded the path name. The debugfs mount is not
+guaranteed to be at /debug (and is more commonly at /sys/kernel/debug).
+For simple one time traces, the above is sufficent. For anything else,
+a search through /proc/mounts may be needed to find where the debugfs
+file-system is mounted.
+
+dynamic ftrace
+--------------
+
+If CONFIG_DYNAMIC_FTRACE is set, the system will run with
+virtually no overhead when function tracing is disabled. The way
+this works is the mcount function call (placed at the start of
+every kernel function, produced by the -pg switch in gcc), starts
+of pointing to a simple return. (Enabling FTRACE will include the
+-pg switch in the compiling of the kernel.)
+
+When dynamic ftrace is initialized, it calls kstop_machine to make
+the machine act like a uniprocessor so that it can freely modify code
+without worrying about other processors executing that same code.  At
+initialization, the mcount calls are changed to call a "record_ip"
+function.  After this, the first time a kernel function is called,
+it has the calling address saved in a hash table.
+
+Later on the ftraced kernel thread is awoken and will again call
+kstop_machine if new functions have been recorded. The ftraced thread
+will change all calls to mcount to "nop".  Just calling mcount
+and having mcount return has shown a 10% overhead. By converting
+it to a nop, there is no measurable overhead to the system.
+
+One special side-effect to the recording of the functions being
+traced is that we can now selectively choose which functions we
+wish to trace and which ones we want the mcount calls to remain as
+nops.
+
+Two files are used, one for enabling and one for disabling the tracing
+of specified functions. They are:
+
+  set_ftrace_filter
+
+and
+
+  set_ftrace_notrace
+
+A list of available functions that you can add to these files is listed
+in:
+
+   available_filter_functions
+
+ # cat /debug/tracing/available_filter_functions
+put_prev_task_idle
+kmem_cache_create
+pick_next_task_rt
+get_online_cpus
+pick_next_task_fair
+mutex_lock
+[...]
+
+If I am only interested in sys_nanosleep and hrtimer_interrupt:
+
+ # echo sys_nanosleep hrtimer_interrupt \
+		> /debug/tracing/set_ftrace_filter
+ # echo ftrace > /debug/tracing/current_tracer
+ # echo 1 > /debug/tracing/tracing_enabled
+ # usleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+          usleep-4134  [00]  1317.070017: hrtimer_interrupt <-smp_apic_timer_interrupt
+          usleep-4134  [00]  1317.070111: sys_nanosleep <-syscall_call
+          <idle>-0     [00]  1317.070115: hrtimer_interrupt <-smp_apic_timer_interrupt
+
+To see which functions are being traced, you can cat the file:
+
+ # cat /debug/tracing/set_ftrace_filter
+hrtimer_interrupt
+sys_nanosleep
+
+
+Perhaps this is not enough. The filters also allow simple wild cards.
+Only the following are currently available
+
+  <match>*  - will match functions that begin with <match>
+  *<match>  - will match functions that end with <match>
+  *<match>* - will match functions that have <match> in it
+
+These are the only wild cards which are supported.
+
+  <match>*<match> will not work.
+
+ # echo hrtimer_* > /debug/tracing/set_ftrace_filter
+
+Produces:
+
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4003  [00]  1480.611794: hrtimer_init <-copy_process
+            bash-4003  [00]  1480.611941: hrtimer_start <-hrtick_set
+            bash-4003  [00]  1480.611956: hrtimer_cancel <-hrtick_clear
+            bash-4003  [00]  1480.611956: hrtimer_try_to_cancel <-hrtimer_cancel
+          <idle>-0     [00]  1480.612019: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612025: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612032: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612037: hrtimer_get_next_event <-get_next_timer_interrupt
+          <idle>-0     [00]  1480.612382: hrtimer_get_next_event <-get_next_timer_interrupt
+
+
+Notice that we lost the sys_nanosleep.
+
+ # cat /debug/tracing/set_ftrace_filter
+hrtimer_run_queues
+hrtimer_run_pending
+hrtimer_init
+hrtimer_cancel
+hrtimer_try_to_cancel
+hrtimer_forward
+hrtimer_start
+hrtimer_reprogram
+hrtimer_force_reprogram
+hrtimer_get_next_event
+hrtimer_interrupt
+hrtimer_nanosleep
+hrtimer_wakeup
+hrtimer_get_remaining
+hrtimer_get_res
+hrtimer_init_sleeper
+
+
+This is because the '>' and '>>' act just like they do in bash.
+To rewrite the filters, use '>'
+To append to the filters, use '>>'
+
+To clear out a filter so that all functions will be recorded again:
+
+ # echo > /debug/tracing/set_ftrace_filter
+ # cat /debug/tracing/set_ftrace_filter
+ #
+
+Again, now we want to append.
+
+ # echo sys_nanosleep > /debug/tracing/set_ftrace_filter
+ # cat /debug/tracing/set_ftrace_filter
+sys_nanosleep
+ # echo hrtimer_* >> /debug/tracing/set_ftrace_filter
+ # cat /debug/tracing/set_ftrace_filter
+hrtimer_run_queues
+hrtimer_run_pending
+hrtimer_init
+hrtimer_cancel
+hrtimer_try_to_cancel
+hrtimer_forward
+hrtimer_start
+hrtimer_reprogram
+hrtimer_force_reprogram
+hrtimer_get_next_event
+hrtimer_interrupt
+sys_nanosleep
+hrtimer_nanosleep
+hrtimer_wakeup
+hrtimer_get_remaining
+hrtimer_get_res
+hrtimer_init_sleeper
+
+
+The set_ftrace_notrace prevents those functions from being traced.
+
+ # echo '*preempt*' '*lock*' > /debug/tracing/set_ftrace_notrace
+
+Produces:
+
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4043  [01]   115.281644: finish_task_switch <-schedule
+            bash-4043  [01]   115.281645: hrtick_set <-schedule
+            bash-4043  [01]   115.281645: hrtick_clear <-hrtick_set
+            bash-4043  [01]   115.281646: wait_for_completion <-__stop_machine_run
+            bash-4043  [01]   115.281647: wait_for_common <-wait_for_completion
+            bash-4043  [01]   115.281647: kthread_stop <-stop_machine_run
+            bash-4043  [01]   115.281648: init_waitqueue_head <-kthread_stop
+            bash-4043  [01]   115.281648: wake_up_process <-kthread_stop
+            bash-4043  [01]   115.281649: try_to_wake_up <-wake_up_process
+
+We can see that there's no more lock or preempt tracing.
+
+ftraced
+-------
+
+As mentioned above, when dynamic ftrace is configured in, a kernel
+thread wakes up once a second and checks to see if there are mcount
+calls that need to be converted into nops. If there are not any, then
+it simply goes back to sleep. But if there are some, it will call
+kstop_machine to convert the calls to nops.
+
+There may be a case in which you do not want this added latency.
+Perhaps you are doing some audio recording and this activity might
+cause skips in the playback. There is an interface to disable
+and enable the "ftraced" kernel thread.
+
+ # echo 0 > /debug/tracing/ftraced_enabled
+
+This will disable the calling of kstop_machine to update the
+mcount calls to nops. Remember that there is a large overhead
+to calling mcount. Without this kernel thread, that overhead will
+exist.
+
+If there are recorded calls to mcount, any write to the ftraced_enabled
+file will cause the kstop_machine to run. This means that a
+user can manually perform the updates when they want to by simply
+echoing a '0' into the ftraced_enabled file.
+
+The updates are also done at the beginning of enabling a tracer
+that uses ftrace function recording.
+
+
+trace_pipe
+----------
+
+The trace_pipe outputs the same content as the trace file, but the effect
+on the tracing is different. Every read from trace_pipe is consumed.
+This means that subsequent reads will be different. The trace
+is live.
+
+ # echo ftrace > /debug/tracing/current_tracer
+ # cat /debug/tracing/trace_pipe > /tmp/trace.out &
+[1] 4153
+ # echo 1 > /debug/tracing/tracing_enabled
+ # usleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+
+ #
+ # cat /tmp/trace.out
+            bash-4043  [00] 41.267106: finish_task_switch <-schedule
+            bash-4043  [00] 41.267106: hrtick_set <-schedule
+            bash-4043  [00] 41.267107: hrtick_clear <-hrtick_set
+            bash-4043  [00] 41.267108: wait_for_completion <-__stop_machine_run
+            bash-4043  [00] 41.267108: wait_for_common <-wait_for_completion
+            bash-4043  [00] 41.267109: kthread_stop <-stop_machine_run
+            bash-4043  [00] 41.267109: init_waitqueue_head <-kthread_stop
+            bash-4043  [00] 41.267110: wake_up_process <-kthread_stop
+            bash-4043  [00] 41.267110: try_to_wake_up <-wake_up_process
+            bash-4043  [00] 41.267111: select_task_rq_rt <-try_to_wake_up
+
+
+Note, reading the trace_pipe file will block until more input is added.
+By changing the tracer, trace_pipe will issue an EOF. We needed
+to set the ftrace tracer _before_ cating the trace_pipe file.
+
+
+trace entries
+-------------
+
+Having too much or not enough data can be troublesome in diagnosing
+an issue in the kernel. The file trace_entries is used to modify
+the size of the internal trace buffers. The number listed
+is the number of entries that can be recorded per CPU. To know
+the full size, multiply the number of possible CPUS with the
+number of entries.
+
+ # cat /debug/tracing/trace_entries
+65620
+
+Note, to modify this, you must have tracing completely disabled. To do that,
+echo "none" into the current_tracer. If the current_tracer is not set
+to "none", an EINVAL error will be returned.
+
+ # echo none > /debug/tracing/current_tracer
+ # echo 100000 > /debug/tracing/trace_entries
+ # cat /debug/tracing/trace_entries
+100045
+
+
+Notice that we echoed in 100,000 but the size is 100,045. The entries
+are held in individual pages. It allocates the number of pages it takes
+to fulfill the request. If more entries may fit on the last page
+then they will be added.
+
+ # echo 1 > /debug/tracing/trace_entries
+ # cat /debug/tracing/trace_entries
+85
+
+This shows us that 85 entries can fit in a single page.
+
+The number of pages which will be allocated is limited to a percentage
+of available memory. Allocating too much will produce an error.
+
+ # echo 1000000000000 > /debug/tracing/trace_entries
+-bash: echo: write error: Cannot allocate memory
+ # cat /debug/tracing/trace_entries
+85
+
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index f4a8ebc1ef1..2d845730d4e 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -2,17 +2,12 @@ Naming and data format standards for sysfs files
 ------------------------------------------------
 
 The libsensors library offers an interface to the raw sensors data
-through the sysfs interface. See libsensors documentation and source for
-further information. As of writing this document, libsensors
-(from lm_sensors 2.8.3) is heavily chip-dependent. Adding or updating
-support for any given chip requires modifying the library's code.
-This is because libsensors was written for the procfs interface
-older kernel modules were using, which wasn't standardized enough.
-Recent versions of libsensors (from lm_sensors 2.8.2 and later) have
-support for the sysfs interface, though.
-
-The new sysfs interface was designed to be as chip-independent as
-possible.
+through the sysfs interface. Since lm-sensors 3.0.0, libsensors is
+completely chip-independent. It assumes that all the kernel drivers
+implement the standard sysfs interface described in this document.
+This makes adding or updating support for any given chip very easy, as
+libsensors, and applications using it, do not need to be modified.
+This is a major improvement compared to lm-sensors 2.
 
 Note that motherboards vary widely in the connections to sensor chips.
 There is no standard that ensures, for example, that the second
@@ -35,19 +30,17 @@ access this data in a simple and consistent way. That said, such programs
 will have to implement conversion, labeling and hiding of inputs. For
 this reason, it is still not recommended to bypass the library.
 
-If you are developing a userspace application please send us feedback on
-this standard.
-
-Note that this standard isn't completely established yet, so it is subject
-to changes. If you are writing a new hardware monitoring driver those
-features can't seem to fit in this interface, please contact us with your
-extension proposal. Keep in mind that backward compatibility must be
-preserved.
-
 Each chip gets its own directory in the sysfs /sys/devices tree.  To
 find all sensor chips, it is easier to follow the device symlinks from
 /sys/class/hwmon/hwmon*.
 
+Up to lm-sensors 3.0.0, libsensors looks for hardware monitoring attributes
+in the "physical" device directory. Since lm-sensors 3.0.1, attributes found
+in the hwmon "class" device directory are also supported. Complex drivers
+(e.g. drivers for multifunction chips) may want to use this possibility to
+avoid namespace pollution. The only drawback will be that older versions of
+libsensors won't support the driver in question.
+
 All sysfs values are fixed point numbers.
 
 There is only one value per file, unlike the older /proc specification.
diff --git a/Documentation/i2c/busses/i2c-i810 b/Documentation/i2c/busses/i2c-i810
deleted file mode 100644
index 778210ee158..00000000000
--- a/Documentation/i2c/busses/i2c-i810
+++ /dev/null
@@ -1,47 +0,0 @@
-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.
diff --git a/Documentation/i2c/busses/i2c-prosavage b/Documentation/i2c/busses/i2c-prosavage
deleted file mode 100644
index 70368790251..00000000000
--- a/Documentation/i2c/busses/i2c-prosavage
+++ /dev/null
@@ -1,23 +0,0 @@
-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.
-
diff --git a/Documentation/i2c/busses/i2c-savage4 b/Documentation/i2c/busses/i2c-savage4
deleted file mode 100644
index 6ecceab618d..00000000000
--- a/Documentation/i2c/busses/i2c-savage4
+++ /dev/null
@@ -1,26 +0,0 @@
-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.
-
diff --git a/Documentation/i2c/fault-codes b/Documentation/i2c/fault-codes
new file mode 100644
index 00000000000..045765c0b9b
--- /dev/null
+++ b/Documentation/i2c/fault-codes
@@ -0,0 +1,127 @@
+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.
+
diff --git a/Documentation/i2c/smbus-protocol b/Documentation/i2c/smbus-protocol
index 03f08fb491c..24bfb65da17 100644
--- a/Documentation/i2c/smbus-protocol
+++ b/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.
 
diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index ee75cbace28..6b61b3a2e90 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -25,14 +25,29 @@ routines, and should be zero-initialized except for fields with data you
 provide.  A client structure holds device-specific information like the
 driver model device node, and its I2C address.
 
+/* iff driver uses driver model ("new style") binding model: */
+
+static struct i2c_device_id foo_idtable[] = {
+	{ "foo", my_id_for_foo },
+	{ "bar", my_id_for_bar },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(i2c, foo_idtable);
+
 static struct i2c_driver foo_driver = {
 	.driver = {
 		.name	= "foo",
 	},
 
 	/* iff driver uses driver model ("new style") binding model: */
+	.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,
@@ -173,10 +188,9 @@ handle may be used during foo_probe().  If foo_probe() reports success
 (zero not a negative status code) it may save the handle and use it until
 foo_remove() returns.  That binding model is used by most Linux drivers.
 
-Drivers match devices when i2c_client.driver_name and the driver name are
-the same; this approach is used in several other busses that don't have
-device typing support in the hardware.  The driver and module name should
-match, so hotplug/coldplug mechanisms will modprobe the driver.
+The probe function is called when an entry in the id_table name field
+matches the device's name. It is passed the entry that was matched so
+the driver knows which one in the table matched.
 
 
 Device Creation (Standard driver model)
@@ -207,6 +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)
 ---------------------------------------
 
@@ -559,7 +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);
@@ -568,30 +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.
diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt
index 240ce7a56c4..3bb5f466a90 100644
--- a/Documentation/ioctl-number.txt
+++ b/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
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index b8e52c0355d..9691c7f5166 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -109,7 +109,7 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
    only with the architecutres which support a relocatable kernel. As
-   of today i386 and ia64 architectures support relocatable kernel.
+   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
 
 Building a relocatable kernel is advantageous from the point of view that
 one does not have to build a second kernel for capturing the dump. But
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index 2075c0658bf..0bd32748a46 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -1,6 +1,105 @@
 kernel-doc nano-HOWTO
 =====================
 
+How to format kernel-doc comments
+---------------------------------
+
+In order to provide embedded, 'C' friendly, easy to maintain,
+but consistent and extractable documentation of the functions and
+data structures in the Linux kernel, the Linux kernel has adopted
+a consistent style for documenting functions and their parameters,
+and structures and their members.
+
+The format for this documentation is called the kernel-doc format.
+It is documented in this Documentation/kernel-doc-nano-HOWTO.txt file.
+
+This style embeds the documentation within the source files, using
+a few simple conventions.  The scripts/kernel-doc perl script, some
+SGML templates in Documentation/DocBook, and other tools understand
+these conventions, and are used to extract this embedded documentation
+into various documents.
+
+In order to provide good documentation of kernel functions and data
+structures, please use the following conventions to format your
+kernel-doc comments in Linux kernel source.
+
+We definitely need kernel-doc formatted documentation for functions
+that are exported to loadable modules using EXPORT_SYMBOL.
+
+We also look to provide kernel-doc formatted documentation for
+functions externally visible to other kernel files (not marked
+"static").
+
+We also recommend providing kernel-doc formatted documentation
+for private (file "static") routines, for consistency of kernel
+source code layout.  But this is lower priority and at the
+discretion of the MAINTAINER of that kernel source file.
+
+Data structures visible in kernel include files should also be
+documented using kernel-doc formatted comments.
+
+The opening comment mark "/**" is reserved for kernel-doc comments.
+Only comments so marked will be considered by the kernel-doc scripts,
+and any comment so marked must be in kernel-doc format.  Do not use
+"/**" to be begin a comment block unless the comment block contains
+kernel-doc formatted comments.  The closing comment marker for
+kernel-doc comments can be either "*/" or "**/".
+
+Kernel-doc comments should be placed just before the function
+or data structure being described.
+
+Example kernel-doc function comment:
+
+/**
+ * foobar() - short function description of foobar
+ * @arg1:	Describe the first argument to foobar.
+ * @arg2:	Describe the second argument to foobar.
+ *		One can provide multiple line descriptions
+ *		for arguments.
+ *
+ * A longer description, with more discussion of the function foobar()
+ * that might be useful to those using or modifying it.  Begins with
+ * empty comment line, and may include additional embedded empty
+ * comment lines.
+ *
+ * The longer description can have multiple paragraphs.
+ **/
+
+The first line, with the short description, must be on a single line.
+
+The @argument descriptions must begin on the very next line following
+this opening short function description line, with no intervening
+empty comment lines.
+
+Example kernel-doc data structure comment.
+
+/**
+ * struct blah - the basic blah structure
+ * @mem1:	describe the first member of struct blah
+ * @mem2:	describe the second member of struct blah,
+ *		perhaps with more lines and words.
+ *
+ * Longer description of this structure.
+ **/
+
+The kernel-doc function comments describe each parameter to the
+function, in order, with the @name lines.
+
+The kernel-doc data structure comments describe each structure member
+in the data structure, with the @name lines.
+
+The longer description formatting is "reflowed", losing your line
+breaks.  So presenting carefully formatted lists within these
+descriptions won't work so well; derived documentation will lose
+the formatting.
+
+See the section below "How to add extractable documentation to your
+source files" for more details and notes on how to format kernel-doc
+comments.
+
+Components of the kernel-doc system
+-----------------------------------
+
 Many places in the source tree have extractable documentation in the
 form of block comments above functions.  The components of this system
 are:
diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt

path: root/lib/Frontend/CompilerInvocation.cpp

//===--- CompilerInvocation.cpp -------------------------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//

#include "clang/Frontend/CompilerInvocation.h"
#include "clang/Basic/Diagnostic.h"
#include "clang/Basic/Version.h"
#include "clang/Basic/FileManager.h"
#include "clang/Driver/Arg.h"
#include "clang/Driver/ArgList.h"
#include "clang/Driver/CC1Options.h"
#include "clang/Driver/DriverDiagnostic.h"
#include "clang/Driver/OptTable.h"
#include "clang/Driver/Option.h"
#include "clang/Frontend/CompilerInvocation.h"
#include "clang/Frontend/LangStandard.h"
#include "clang/Serialization/ASTReader.h"
#include "llvm/ADT/OwningPtr.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/ADT/Triple.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/Host.h"
#include "llvm/Support/Path.h"
using namespace clang;

static const char *getAnalysisStoreName(AnalysisStores Kind) {
  switch (Kind) {
  default:
    llvm_unreachable("Unknown analysis store!");
#define ANALYSIS_STORE(NAME, CMDFLAG, DESC, CREATFN) \
  case NAME##Model: return CMDFLAG;
#include "clang/Frontend/Analyses.def"
  }
}

static const char *getAnalysisConstraintName(AnalysisConstraints Kind) {
  switch (Kind) {
  default:
    llvm_unreachable("Unknown analysis constraints!");
#define ANALYSIS_CONSTRAINTS(NAME, CMDFLAG, DESC, CREATFN) \
  case NAME##Model: return CMDFLAG;
#include "clang/Frontend/Analyses.def"
  }
}

static const char *getAnalysisDiagClientName(AnalysisDiagClients Kind) {
  switch (Kind) {
  default:
    llvm_unreachable("Unknown analysis client!");
#define ANALYSIS_DIAGNOSTICS(NAME, CMDFLAG, DESC, CREATFN, AUTOCREATE) \
  case PD_##NAME: return CMDFLAG;
#include "clang/Frontend/Analyses.def"
  }
}

//===----------------------------------------------------------------------===//
// Serialization (to args)
//===----------------------------------------------------------------------===//

static void AnalyzerOptsToArgs(const AnalyzerOptions &Opts,
                               std::vector<std::string> &Res) {
  if (Opts.ShowCheckerHelp)
    Res.push_back("-analyzer-checker-help");
  if (Opts.AnalysisStoreOpt != BasicStoreModel) {
    Res.push_back("-analyzer-store");
    Res.push_back(getAnalysisStoreName(Opts.AnalysisStoreOpt));
  }
  if (Opts.AnalysisConstraintsOpt != RangeConstraintsModel) {
    Res.push_back("-analyzer-constraints");
    Res.push_back(getAnalysisConstraintName(Opts.AnalysisConstraintsOpt));
  }
  if (Opts.AnalysisDiagOpt != PD_HTML) {
    Res.push_back("-analyzer-output");
    Res.push_back(getAnalysisDiagClientName(Opts.AnalysisDiagOpt));
  }
  if (!Opts.AnalyzeSpecificFunction.empty()) {
    Res.push_back("-analyze-function");
    Res.push_back(Opts.AnalyzeSpecificFunction);
  }
  if (Opts.AnalyzeAll)
    Res.push_back("-analyzer-opt-analyze-headers");
  if (Opts.AnalyzerDisplayProgress)
    Res.push_back("-analyzer-display-progress");
  if (Opts.AnalyzeNestedBlocks)
    Res.push_back("-analyzer-opt-analyze-nested-blocks");
  if (Opts.EagerlyAssume)
    Res.push_back("-analyzer-eagerly-assume");
  if (!Opts.PurgeDead)
    Res.push_back("-analyzer-no-purge-dead");
  if (Opts.TrimGraph)
    Res.push_back("-trim-egraph");
  if (Opts.VisualizeEGDot)
    Res.push_back("-analyzer-viz-egraph-graphviz");
  if (Opts.VisualizeEGDot)
    Res.push_back("-analyzer-viz-egraph-ubigraph");

  for (unsigned i = 0, e = Opts.CheckersControlList.size(); i != e; ++i) {
    const std::pair<std::string, bool> &opt = Opts.CheckersControlList[i];
    if (opt.second)
      Res.push_back("-analyzer-disable-checker");
    else
      Res.push_back("-analyzer-checker");
    Res.push_back(opt.first);
  }
}

static void CodeGenOptsToArgs(const CodeGenOptions &Opts,
                              std::vector<std::string> &Res) {
  if (Opts.DebugInfo)
    Res.push_back("-g");
  if (Opts.DisableLLVMOpts)
    Res.push_back("-disable-llvm-optzns");
  if (Opts.DisableRedZone)
    Res.push_back("-disable-red-zone");
  if (!Opts.DwarfDebugFlags.empty()) {
    Res.push_back("-dwarf-debug-flags");
    Res.push_back(Opts.DwarfDebugFlags);
  }
  if (!Opts.MergeAllConstants)
    Res.push_back("-fno-merge-all-constants");
  if (Opts.NoCommon)
    Res.push_back("-fno-common");
  if (Opts.NoImplicitFloat)
    Res.push_back("-no-implicit-float");
  if (Opts.OmitLeafFramePointer)
    Res.push_back("-momit-leaf-frame-pointer");
  if (Opts.OptimizeSize) {
    assert(Opts.OptimizationLevel == 2 && "Invalid options!");
    Res.push_back("-Os");
  } else if (Opts.OptimizationLevel != 0)
    Res.push_back("-O" + llvm::utostr(Opts.OptimizationLevel));
  if (!Opts.MainFileName.empty()) {
    Res.push_back("-main-file-name");
    Res.push_back(Opts.MainFileName);
  }
  // SimplifyLibCalls is only derived.
  // TimePasses is only derived.
  // UnitAtATime is unused.
  // Inlining is only derived.

  // UnrollLoops is derived, but also accepts an option, no
  // harm in pushing it back here.
  if (Opts.UnrollLoops)
    Res.push_back("-funroll-loops");
  if (Opts.DataSections)
    Res.push_back("-fdata-sections");
  if (Opts.FunctionSections)
    Res.push_back("-ffunction-sections");
  if (Opts.AsmVerbose)
    Res.push_back("-masm-verbose");
  if (!Opts.CodeModel.empty()) {
    Res.push_back("-mcode-model");
    Res.push_back(Opts.CodeModel);
  }
  if (!Opts.CXAAtExit)
    Res.push_back("-fno-use-cxa-atexit");
  if (Opts.CXXCtorDtorAliases)
    Res.push_back("-mconstructor-aliases");
  if (!Opts.DebugPass.empty()) {
    Res.push_back("-mdebug-pass");
    Res.push_back(Opts.DebugPass);
  }
  if (Opts.DisableFPElim)
    Res.push_back("-mdisable-fp-elim");
  if (!Opts.FloatABI.empty()) {
    Res.push_back("-mfloat-abi");
    Res.push_back(Opts.FloatABI);
  }
  if (!Opts.LimitFloatPrecision.empty()) {
    Res.push_back("-mlimit-float-precision");
    Res.push_back(Opts.LimitFloatPrecision);
  }
  if (Opts.NoZeroInitializedInBSS)
    Res.push_back("-mno-zero-initialized-bss");
  switch (Opts.getObjCDispatchMethod()) {
  case CodeGenOptions::Legacy:
    break;
  case CodeGenOptions::Mixed:
    Res.push_back("-fobjc-dispatch-method=mixed");
    break;
  case CodeGenOptions::NonLegacy:
    Res.push_back("-fobjc-dispatch-method=non-legacy");
    break;
  }
  if (Opts.NumRegisterParameters) {
    Res.push_back("-mregparm");
    Res.push_back(llvm::utostr(Opts.NumRegisterParameters));
  }
  if (Opts.RelaxAll)
    Res.push_back("-mrelax-all");
  if (Opts.SoftFloat)
    Res.push_back("-msoft-float");
  if (Opts.UnwindTables)
    Res.push_back("-munwind-tables");
  if (Opts.RelocationModel != "pic") {
    Res.push_back("-mrelocation-model");
    Res.push_back(Opts.RelocationModel);
  }
  if (!Opts.VerifyModule)
    Res.push_back("-disable-llvm-verifier");
}

static void DependencyOutputOptsToArgs(const DependencyOutputOptions &Opts,
                                       std::vector<std::string> &Res) {
  if (Opts.IncludeSystemHeaders)
    Res.push_back("-sys-header-deps");
  if (Opts.ShowHeaderIncludes)
    Res.push_back("-H");
  if (!Opts.HeaderIncludeOutputFile.empty()) {
    Res.push_back("-header-include-file");
    Res.push_back(Opts.HeaderIncludeOutputFile);
  }
  if (Opts.UsePhonyTargets)
    Res.push_back("-MP");
  if (!Opts.OutputFile.empty()) {
    Res.push_back("-dependency-file");
    Res.push_back(Opts.OutputFile);
  }
  for (unsigned i = 0, e = Opts.Targets.size(); i != e; ++i) {
    Res.push_back("-MT");
    Res.push_back(Opts.Targets[i]);
  }
}

static void DiagnosticOptsToArgs(const DiagnosticOptions &Opts,
                                 std::vector<std::string> &Res) {
  if (Opts.IgnoreWarnings)
    Res.push_back("-w");
  if (Opts.NoRewriteMacros)
    Res.push_back("-Wno-rewrite-macros");
  if (Opts.Pedantic)
    Res.push_back("-pedantic");
  if (Opts.PedanticErrors)
    Res.push_back("-pedantic-errors");
  if (!Opts.ShowColumn)
    Res.push_back("-fno-show-column");
  if (!Opts.ShowLocation)
    Res.push_back("-fno-show-source-location");
  if (!Opts.ShowCarets)
    Res.push_back("-fno-caret-diagnostics");
  if (!Opts.ShowFixits)
    Res.push_back("-fno-diagnostics-fixit-info");
  if (Opts.ShowSourceRanges)
    Res.push_back("-fdiagnostics-print-source-range-info");
  if (Opts.ShowParseableFixits)
    Res.push_back("-fdiagnostics-parseable-fixits");
  if (Opts.ShowColors)
    Res.push_back("-fcolor-diagnostics");
  if (Opts.VerifyDiagnostics)
    Res.push_back("-verify");
  if (Opts.ShowOptionNames)
    Res.push_back("-fdiagnostics-show-option");
  if (Opts.ShowCategories == 1)
    Res.push_back("-fdiagnostics-show-category=id");
  else if (Opts.ShowCategories == 2)
    Res.push_back("-fdiagnostics-show-category=name");
  if (Opts.ErrorLimit) {
    Res.push_back("-ferror-limit");
    Res.push_back(llvm::utostr(Opts.ErrorLimit));
  }
  if (Opts.MacroBacktraceLimit
                        != DiagnosticOptions::DefaultMacroBacktraceLimit) {
    Res.push_back("-fmacro-backtrace-limit");
    Res.push_back(llvm::utostr(Opts.MacroBacktraceLimit));
  }
  if (Opts.TemplateBacktraceLimit
                        != DiagnosticOptions::DefaultTemplateBacktraceLimit) {
    Res.push_back("-ftemplate-backtrace-limit");
    Res.push_back(llvm::utostr(Opts.TemplateBacktraceLimit));
  }

  if (Opts.TabStop != DiagnosticOptions::DefaultTabStop) {
    Res.push_back("-ftabstop");
    Res.push_back(llvm::utostr(Opts.TabStop));
  }
  if (Opts.MessageLength) {
    Res.push_back("-fmessage-length");
    Res.push_back(llvm::utostr(Opts.MessageLength));
  }
  if (!Opts.DumpBuildInformation.empty()) {
    Res.push_back("-dump-build-information");
    Res.push_back(Opts.DumpBuildInformation);
  }
  for (unsigned i = 0, e = Opts.Warnings.size(); i != e; ++i)
    Res.push_back("-W" + Opts.Warnings[i]);
}

static const char *getInputKindName(InputKind Kind) {
  switch (Kind) {
  case IK_None:              break;
  case IK_AST:               return "ast";
  case IK_Asm:               return "assembler-with-cpp";
  case IK_C:                 return "c";
  case IK_CXX:               return "c++";
  case IK_LLVM_IR:           return "ir";
  case IK_ObjC:              return "objective-c";
  case IK_ObjCXX:            return "objective-c++";
  case IK_OpenCL:            return "cl";
  case IK_CUDA:              return "cuda";
  case IK_PreprocessedC:     return "cpp-output";
  case IK_PreprocessedCXX:   return "c++-cpp-output";
  case IK_PreprocessedObjC:  return "objective-c-cpp-output";
  case IK_PreprocessedObjCXX:return "objective-c++-cpp-output";
  }

  llvm_unreachable("Unexpected language kind!");
  return 0;
}

static const char *getActionName(frontend::ActionKind Kind) {
  switch (Kind) {
  case frontend::PluginAction:
    llvm_unreachable("Invalid kind!");

  case frontend::ASTDump:                return "-ast-dump";
  case frontend::ASTDumpXML:             return "-ast-dump-xml";
  case frontend::ASTPrint:               return "-ast-print";
  case frontend::ASTView:                return "-ast-view";
  case frontend::BoostCon:               return "-boostcon";
  case frontend::CreateModule:           return "-create-module";
  case frontend::DumpRawTokens:          return "-dump-raw-tokens";
  case frontend::DumpTokens:             return "-dump-tokens";
  case frontend::EmitAssembly:           return "-S";
  case frontend::EmitBC:                 return "-emit-llvm-bc";
  case frontend::EmitHTML:               return "-emit-html";
  case frontend::EmitLLVM:               return "-emit-llvm";
  case frontend::EmitLLVMOnly:           return "-emit-llvm-only";
  case frontend::EmitCodeGenOnly:        return "-emit-codegen-only";
  case frontend::EmitObj:                return "-emit-obj";
  case frontend::FixIt:                  return "-fixit";
  case frontend::GeneratePCH:            return "-emit-pch";
  case frontend::GeneratePTH:            return "-emit-pth";
  case frontend::InitOnly:               return "-init-only";
  case frontend::ParseSyntaxOnly:        return "-fsyntax-only";
  case frontend::PrintDeclContext:       return "-print-decl-contexts";
  case frontend::PrintPreamble:          return "-print-preamble";
  case frontend::PrintPreprocessedInput: return "-E";
  case frontend::RewriteMacros:          return "-rewrite-macros";
  case frontend::RewriteObjC:            return "-rewrite-objc";
  case frontend::RewriteTest:            return "-rewrite-test";
  case frontend::RunAnalysis:            return "-analyze";
  case frontend::RunPreprocessorOnly:    return "-Eonly";
  }

  llvm_unreachable("Unexpected language kind!");
  return 0;
}

static void FileSystemOptsToArgs(const FileSystemOptions &Opts,
                                 std::vector<std::string> &Res) {
  if (!Opts.WorkingDir.empty()) {
    Res.push_back("-working-directory");
    Res.push_back(Opts.WorkingDir);
  }
}

static void FrontendOptsToArgs(const FrontendOptions &Opts,
                               std::vector<std::string> &Res) {
  if (Opts.DisableFree)
    Res.push_back("-disable-free");
  if (Opts.RelocatablePCH)
    Res.push_back("-relocatable-pch");
  if (Opts.ChainedPCH)
    Res.push_back("-chained-pch");
  if (Opts.ShowHelp)
    Res.push_back("-help");
  if (Opts.ShowMacrosInCodeCompletion)
    Res.push_back("-code-completion-macros");
  if (Opts.ShowCodePatternsInCodeCompletion)
    Res.push_back("-code-completion-patterns");
  if (!Opts.ShowGlobalSymbolsInCodeCompletion)
    Res.push_back("-no-code-completion-globals");
  if (Opts.ShowStats)
    Res.push_back("-print-stats");
  if (Opts.ShowTimers)
    Res.push_back("-ftime-report");
  if (Opts.ShowVersion)
    Res.push_back("-version");
  if (Opts.FixWhatYouCan)
    Res.push_back("-fix-what-you-can");

  bool NeedLang = false;
  for (unsigned i = 0, e = Opts.Inputs.size(); i != e; ++i)
    if (FrontendOptions::getInputKindForExtension(Opts.Inputs[i].second) !=
        Opts.Inputs[i].first)
      NeedLang = true;
  if (NeedLang) {
    Res.push_back("-x");
    Res.push_back(getInputKindName(Opts.Inputs[0].first));
  }
  for (unsigned i = 0, e = Opts.Inputs.size(); i != e; ++i) {
    assert((!NeedLang || Opts.Inputs[i].first == Opts.Inputs[0].first) &&
           "Unable to represent this input vector!");
    Res.push_back(Opts.Inputs[i].second);
  }

  if (!Opts.OutputFile.empty()) {
    Res.push_back("-o");
    Res.push_back(Opts.OutputFile);
  }
  if (!Opts.CodeCompletionAt.FileName.empty()) {
    Res.push_back("-code-completion-at");
    Res.push_back(Opts.CodeCompletionAt.FileName + ":" +
                  llvm::utostr(Opts.CodeCompletionAt.Line) + ":" +
                  llvm::utostr(Opts.CodeCompletionAt.Column));
  }
  if (Opts.ProgramAction != frontend::PluginAction)
    Res.push_back(getActionName(Opts.ProgramAction));
  if (!Opts.ActionName.empty()) {
    Res.push_back("-plugin");
    Res.push_back(Opts.ActionName);
    for(unsigned i = 0, e = Opts.PluginArgs.size(); i != e; ++i) {
      Res.push_back("-plugin-arg-" + Opts.ActionName);
      Res.push_back(Opts.PluginArgs[i]);
    }
  }
  for (unsigned i = 0, e = Opts.Plugins.size(); i != e; ++i) {
    Res.push_back("-load");
    Res.push_back(Opts.Plugins[i]);
  }
  for (unsigned i = 0, e = Opts.AddPluginActions.size(); i != e; ++i) {
    Res.push_back("-add-plugin");
    Res.push_back(Opts.AddPluginActions[i]);
    for(unsigned ai = 0, ae = Opts.AddPluginArgs.size(); ai != ae; ++ai) {
      Res.push_back("-plugin-arg-" + Opts.AddPluginActions[i]);
      Res.push_back(Opts.AddPluginArgs[i][ai]);
    }
  }
  for (unsigned i = 0, e = Opts.ASTMergeFiles.size(); i != e; ++i) {
    Res.push_back("-ast-merge");
    Res.push_back(Opts.ASTMergeFiles[i]);
  }
  for (unsigned i = 0, e = Opts.Modules.size(); i != e; ++i) {
    Res.push_back("-import-module");
    Res.push_back(Opts.Modules[i]);
  }
  for (unsigned i = 0, e = Opts.LLVMArgs.size(); i != e; ++i) {
    Res.push_back("-mllvm");
    Res.push_back(Opts.LLVMArgs[i]);
  }
}

static void HeaderSearchOptsToArgs(const HeaderSearchOptions &Opts,
                                   std::vector<std::string> &Res) {
  if (Opts.Sysroot != "/") {
    Res.push_back("-isysroot");
    Res.push_back(Opts.Sysroot);
  }

  /// User specified include entries.
  for (unsigned i = 0, e = Opts.UserEntries.size(); i != e; ++i) {
    const HeaderSearchOptions::Entry &E = Opts.UserEntries[i];
    if (E.IsFramework && (E.Group != frontend::Angled || !E.IsUserSupplied))
      llvm::report_fatal_error("Invalid option set!");
    if (E.IsUserSupplied) {
      if (E.Group == frontend::After) {
        Res.push_back("-idirafter");
      } else if (E.Group == frontend::Quoted) {
        Res.push_back("-iquote");
      } else if (E.Group == frontend::System) {
        Res.push_back("-isystem");
      } else if (E.Group == frontend::CXXSystem) {
        Res.push_back("-cxx-isystem");
      } else {
        assert(E.Group == frontend::Angled && "Invalid group!");
        Res.push_back(E.IsFramework ? "-F" : "-I");
      }
    } else {
      if (E.Group != frontend::Angled && E.Group != frontend::System)
        llvm::report_fatal_error("Invalid option set!");
      Res.push_back(E.Group == frontend::Angled ? "-iwithprefixbefore" :
                    "-iwithprefix");
    }
    Res.push_back(E.Path);
  }

  if (!Opts.EnvIncPath.empty()) {
    // FIXME: Provide an option for this, and move env detection to driver.
    llvm::report_fatal_error("Not yet implemented!");
  }
  if (!Opts.CEnvIncPath.empty()) {
    // FIXME: Provide an option for this, and move env detection to driver.
    llvm::report_fatal_error("Not yet implemented!");
  }
  if (!Opts.ObjCEnvIncPath.empty()) {
    // FIXME: Provide an option for this, and move env detection to driver.
    llvm::report_fatal_error("Not yet implemented!");
  }
  if (!Opts.CXXEnvIncPath.empty()) {
    // FIXME: Provide an option for this, and move env detection to driver.
    llvm::report_fatal_error("Not yet implemented!");
  }
  if (!Opts.ObjCXXEnvIncPath.empty()) {
    // FIXME: Provide an option for this, and move env detection to driver.
    llvm::report_fatal_error("Not yet implemented!");
  }
  if (!Opts.ResourceDir.empty()) {
    Res.push_back("-resource-dir");
    Res.push_back(Opts.ResourceDir);
  }
  if (!Opts.UseStandardIncludes)
    Res.push_back("-nostdinc");
  if (!Opts.UseStandardCXXIncludes)
    Res.push_back("-nostdinc++");
  if (Opts.Verbose)
    Res.push_back("-v");
}

static void LangOptsToArgs(const LangOptions &Opts,
                           std::vector<std::string> &Res) {
  LangOptions DefaultLangOpts;

  // FIXME: Need to set -std to get all the implicit options.

  // FIXME: We want to only pass options relative to the defaults, which
  // requires constructing a target. :(
  //
  // It would be better to push the all target specific choices into the driver,
  // so that everything below that was more uniform.

  if (Opts.Trigraphs)
    Res.push_back("-trigraphs");
  // Implicit based on the input kind:
  //   AsmPreprocessor, CPlusPlus, ObjC1, ObjC2, OpenCL
  // Implicit based on the input language standard:
  //   BCPLComment, C99, CPlusPlus0x, Digraphs, GNUInline, ImplicitInt, GNUMode
  if (Opts.DollarIdents)
    Res.push_back("-fdollars-in-identifiers");
  if (Opts.GNUMode && !Opts.GNUKeywords)
    Res.push_back("-fno-gnu-keywords");
  if (!Opts.GNUMode && Opts.GNUKeywords)
    Res.push_back("-fgnu-keywords");
  if (Opts.Microsoft)
    Res.push_back("-fms-extensions");
  if (Opts.MSCVersion != 0)
    Res.push_back("-fmsc-version=" + llvm::utostr(Opts.MSCVersion));
  if (Opts.Borland)
    Res.push_back("-fborland-extensions");
  if (Opts.ObjCNonFragileABI)
    Res.push_back("-fobjc-nonfragile-abi");
  if (Opts.ObjCNonFragileABI2)
    Res.push_back("-fobjc-nonfragile-abi");
  if (Opts.ObjCDefaultSynthProperties)
    Res.push_back("-fobjc-default-synthesize-properties");
  // NoInline is implicit.
  if (!Opts.CXXOperatorNames)
    Res.push_back("-fno-operator-names");
  if (Opts.PascalStrings)
    Res.push_back("-fpascal-strings");
  if (Opts.CatchUndefined)
    Res.push_back("-fcatch-undefined-behavior");
  if (Opts.WritableStrings)
    Res.push_back("-fwritable-strings");
  if (Opts.ConstStrings)
    Res.push_back("-Wwrite-strings");
  if (!Opts.LaxVectorConversions)
    Res.push_back("-fno-lax-vector-conversions");
  if (Opts.AltiVec)
    Res.push_back("-faltivec");
  if (Opts.Exceptions)
    Res.push_back("-fexceptions");
  if (Opts.ObjCExceptions)
    Res.push_back("-fobjc-exceptions");
  if (Opts.CXXExceptions)
    Res.push_back("-fcxx-exceptions");
  if (Opts.SjLjExceptions)
    Res.push_back("-fsjlj-exceptions");
  if (!Opts.RTTI)
    Res.push_back("-fno-rtti");
  if (Opts.MSBitfields)
    Res.push_back("-mms-bitfields");
  if (!Opts.NeXTRuntime)
    Res.push_back("-fgnu-runtime");
  if (Opts.Freestanding)
    Res.push_back("-ffreestanding");
  if (Opts.NoBuiltin)
    Res.push_back("-fno-builtin");
  if (!Opts.AssumeSaneOperatorNew)
    Res.push_back("-fno-assume-sane-operator-new");
  if (!Opts.ThreadsafeStatics)
    Res.push_back("-fno-threadsafe-statics");
  if (Opts.POSIXThreads)
    Res.push_back("-pthread");
  if (Opts.Blocks)
    Res.push_back("-fblocks");
  if (Opts.EmitAllDecls)
    Res.push_back("-femit-all-decls");
  if (Opts.MathErrno)
    Res.push_back("-fmath-errno");
  switch (Opts.getSignedOverflowBehavior()) {
  case LangOptions::SOB_Undefined: break;
  case LangOptions::SOB_Defined:   Res.push_back("-fwrapv"); break;
  case LangOptions::SOB_Trapping:
    Res.push_back("-ftrapv"); break;
    if (!Opts.OverflowHandler.empty()) {
      Res.push_back("-ftrapv-handler");
      Res.push_back(Opts.OverflowHandler);
    }
  }
  if (Opts.HeinousExtensions)
    Res.push_back("-fheinous-gnu-extensions");
  // Optimize is implicit.
  // OptimizeSize is implicit.
  if (Opts.Static)
    Res.push_back("-static-define");
  if (Opts.DumpRecordLayouts)
    Res.push_back("-fdump-record-layouts");
  if (Opts.DumpVTableLayouts)
    Res.push_back("-fdump-vtable-layouts");
  if (Opts.NoBitFieldTypeAlign)
    Res.push_back("-fno-bitfield-type-alignment");
  if (Opts.PICLevel) {
    Res.push_back("-pic-level");
    Res.push_back(llvm::utostr(Opts.PICLevel));
  }
  if (Opts.ObjCGCBitmapPrint)
    Res.push_back("-print-ivar-layout");
  if (Opts.NoConstantCFStrings)
    Res.push_back("-fno-constant-cfstrings");
  if (!Opts.AccessControl)
    Res.push_back("-fno-access-control");
  if (!Opts.CharIsSigned)
    Res.push_back("-fno-signed-char");
  if (Opts.ShortWChar)
    Res.push_back("-fshort-wchar");
  if (!Opts.ElideConstructors)
    Res.push_back("-fno-elide-constructors");
  if (Opts.getGCMode() != LangOptions::NonGC) {
    if (Opts.getGCMode() == LangOptions::HybridGC) {
      Res.push_back("-fobjc-gc");
    } else {
      assert(Opts.getGCMode() == LangOptions::GCOnly && "Invalid GC mode!");
      Res.push_back("-fobjc-gc-only");
    }
  }
  if (Opts.AppleKext)
    Res.push_back("-fapple-kext");
  
  if (Opts.getVisibilityMode() != DefaultVisibility) {
    Res.push_back("-fvisibility");
    if (Opts.getVisibilityMode() == HiddenVisibility) {
      Res.push_back("hidden");
    } else {
      assert(Opts.getVisibilityMode() == ProtectedVisibility &&
             "Invalid visibility!");
      Res.push_back("protected");
    }
  }
  if (Opts.InlineVisibilityHidden)
    Res.push_back("-fvisibility-inlines-hidden");

  if (Opts.getStackProtectorMode() != 0) {
    Res.push_back("-stack-protector");
    Res.push_back(llvm::utostr(Opts.getStackProtectorMode()));
  }
  if (Opts.InstantiationDepth != DefaultLangOpts.InstantiationDepth) {
    Res.push_back("-ftemplate-depth");
    Res.push_back(llvm::utostr(Opts.InstantiationDepth));
  }
  if (!Opts.ObjCConstantStringClass.empty()) {
    Res.push_back("-fconstant-string-class");
    Res.push_back(Opts.ObjCConstantStringClass);
  }
}

static void PreprocessorOptsToArgs(const PreprocessorOptions &Opts,
                                   std::vector<std::string> &Res) {
  for (unsigned i = 0, e = Opts.Macros.size(); i != e; ++i)
    Res.push_back(std::string(Opts.Macros[i].second ? "-U" : "-D") +
                  Opts.Macros[i].first);
  for (unsigned i = 0, e = Opts.Includes.size(); i != e; ++i) {
    // FIXME: We need to avoid reincluding the implicit PCH and PTH includes.
    Res.push_back("-include");
    Res.push_back(Opts.Includes[i]);
  }
  for (unsigned i = 0, e = Opts.MacroIncludes.size(); i != e; ++i) {
    Res.push_back("-imacros");
    Res.push_back(Opts.MacroIncludes[i]);
  }
  if (!Opts.UsePredefines)
    Res.push_back("-undef");
  if (Opts.DetailedRecord)
    Res.push_back("-detailed-preprocessing-record");
  if (!Opts.ImplicitPCHInclude.empty()) {
    Res.push_back("-include-pch");
    Res.push_back(Opts.ImplicitPCHInclude);
  }
  if (!Opts.ImplicitPTHInclude.empty()) {
    Res.push_back("-include-pth");
    Res.push_back(Opts.ImplicitPTHInclude);
  }
  if (!Opts.TokenCache.empty()) {
    if (Opts.ImplicitPTHInclude.empty()) {
      Res.push_back("-token-cache");
      Res.push_back(Opts.TokenCache);
    } else
      assert(Opts.ImplicitPTHInclude == Opts.TokenCache &&
             "Unsupported option combination!");
  }
  for (unsigned i = 0, e = Opts.ChainedIncludes.size(); i != e; ++i) {
    Res.push_back("-chain-include");
    Res.push_back(Opts.ChainedIncludes[i]);
  }
  for (unsigned i = 0, e = Opts.RemappedFiles.size(); i != e; ++i) {
    Res.push_back("-remap-file");
    Res.push_back(Opts.RemappedFiles[i].first + ";" +
                  Opts.RemappedFiles[i].second);
  }
}

static void PreprocessorOutputOptsToArgs(const PreprocessorOutputOptions &Opts,
                                         std::vector<std::string> &Res) {
  if (!Opts.ShowCPP && !Opts.ShowMacros)
    llvm::report_fatal_error("Invalid option combination!");

  if (Opts.ShowCPP && Opts.ShowMacros)
    Res.push_back("-dD");
  else if (!Opts.ShowCPP && Opts.ShowMacros)
    Res.push_back("-dM");

  if (!Opts.ShowLineMarkers)
    Res.push_back("-P");
  if (Opts.ShowComments)
    Res.push_back("-C");
  if (Opts.ShowMacroComments)
    Res.push_back("-CC");
}

static void TargetOptsToArgs(const TargetOptions &Opts,
                             std::vector<std::string> &Res) {
  Res.push_back("-triple");
  Res.push_back(Opts.Triple);
  if (!Opts.CPU.empty()) {
    Res.push_back("-target-cpu");
    Res.push_back(Opts.CPU);
  }
  if (!Opts.ABI.empty()) {
    Res.push_back("-target-abi");
    Res.push_back(Opts.ABI);
  }
  if (!Opts.LinkerVersion.empty()) {
    Res.push_back("-target-linker-version");
    Res.push_back(Opts.LinkerVersion);
  }
  if (!Opts.CXXABI.empty()) {
    Res.push_back("-cxx-abi");
    Res.push_back(Opts.CXXABI);
  }
  for (unsigned i = 0, e = Opts.Features.size(); i != e; ++i) {
    Res.push_back("-target-feature");
    Res.push_back(Opts.Features[i]);
  }
}

void CompilerInvocation::toArgs(std::vector<std::string> &Res) {
  AnalyzerOptsToArgs(getAnalyzerOpts(), Res);
  CodeGenOptsToArgs(getCodeGenOpts(), Res);
  DependencyOutputOptsToArgs(getDependencyOutputOpts(), Res);
  DiagnosticOptsToArgs(getDiagnosticOpts(), Res);
  FileSystemOptsToArgs(getFileSystemOpts(), Res);
  FrontendOptsToArgs(getFrontendOpts(), Res);
  HeaderSearchOptsToArgs(getHeaderSearchOpts(), Res);
  LangOptsToArgs(getLangOpts(), Res);
  PreprocessorOptsToArgs(getPreprocessorOpts(), Res);
  PreprocessorOutputOptsToArgs(getPreprocessorOutputOpts(), Res);
  TargetOptsToArgs(getTargetOpts(), Res);
}

//===----------------------------------------------------------------------===//
// Deserialization (to args)
//===----------------------------------------------------------------------===//

using namespace clang::driver;
using namespace clang::driver::cc1options;

//

static unsigned getOptimizationLevel(ArgList &Args, InputKind IK,
                                     Diagnostic &Diags) {
  unsigned DefaultOpt = 0;
  if (IK == IK_OpenCL && !Args.hasArg(OPT_cl_opt_disable))
    DefaultOpt = 2;
  // -Os implies -O2
  return Args.hasArg(OPT_Os) ? 2 :
    Args.getLastArgIntValue(OPT_O, DefaultOpt, Diags);
}

static void ParseAnalyzerArgs(AnalyzerOptions &Opts, ArgList &Args,
                              Diagnostic &Diags) {
  using namespace cc1options;

  if (Arg *A = Args.getLastArg(OPT_analyzer_store)) {
    llvm::StringRef Name = A->getValue(Args);
    AnalysisStores Value = llvm::StringSwitch<AnalysisStores>(Name)
#define ANALYSIS_STORE(NAME, CMDFLAG, DESC, CREATFN) \
      .Case(CMDFLAG, NAME##Model)
#include "clang/Frontend/Analyses.def"
      .Default(NumStores);
    // FIXME: Error handling.
    if (Value == NumStores)
      Diags.Report(diag::err_drv_invalid_value)
        << A->getAsString(Args) << Name;
    else
      Opts.AnalysisStoreOpt = Value;
  }

  if (Arg *A = Args.getLastArg(OPT_analyzer_constraints)) {
    llvm::StringRef Name = A->getValue(Args);
    AnalysisConstraints Value = llvm::StringSwitch<AnalysisConstraints>(Name)
#define ANALYSIS_CONSTRAINTS(NAME, CMDFLAG, DESC, CREATFN) \
      .Case(CMDFLAG, NAME##Model)
#include "clang/Frontend/Analyses.def"
      .Default(NumConstraints);
    // FIXME: Error handling.
    if (Value == NumConstraints)
      Diags.Report(diag::err_drv_invalid_value)
        << A->getAsString(Args) << Name;
    else
      Opts.AnalysisConstraintsOpt = Value;
  }

  if (Arg *A = Args.getLastArg(OPT_analyzer_output)) {
    llvm::StringRef Name = A->getValue(Args);
    AnalysisDiagClients Value = llvm::StringSwitch<AnalysisDiagClients>(Name)
#define ANALYSIS_DIAGNOSTICS(NAME, CMDFLAG, DESC, CREATFN, AUTOCREAT) \
      .Case(CMDFLAG, PD_##NAME)
#include "clang/Frontend/Analyses.def"
      .Default(NUM_ANALYSIS_DIAG_CLIENTS);
    // FIXME: Error handling.
    if (Value == NUM_ANALYSIS_DIAG_CLIENTS)
      Diags.Report(diag::err_drv_invalid_value)
        << A->getAsString(Args) << Name;
    else
      Opts.AnalysisDiagOpt = Value;
  }

  Opts.ShowCheckerHelp = Args.hasArg(OPT_analyzer_checker_help);
  Opts.VisualizeEGDot = Args.hasArg(OPT_analyzer_viz_egraph_graphviz);
  Opts.VisualizeEGUbi = Args.hasArg(OPT_analyzer_viz_egraph_ubigraph);
  Opts.AnalyzeAll = Args.hasArg(OPT_analyzer_opt_analyze_headers);
  Opts.AnalyzerDisplayProgress = Args.hasArg(OPT_analyzer_display_progress);
  Opts.AnalyzeNestedBlocks =
    Args.hasArg(OPT_analyzer_opt_analyze_nested_blocks);
  Opts.PurgeDead = !Args.hasArg(OPT_analyzer_no_purge_dead);
  Opts.EagerlyAssume = Args.hasArg(OPT_analyzer_eagerly_assume);
  Opts.AnalyzeSpecificFunction = Args.getLastArgValue(OPT_analyze_function);
  Opts.UnoptimizedCFG = Args.hasArg(OPT_analysis_UnoptimizedCFG);
  Opts.CFGAddImplicitDtors = Args.hasArg(OPT_analysis_CFGAddImplicitDtors);
  Opts.CFGAddInitializers = Args.hasArg(OPT_analysis_CFGAddInitializers);
  Opts.TrimGraph = Args.hasArg(OPT_trim_egraph);
  Opts.MaxNodes = Args.getLastArgIntValue(OPT_analyzer_max_nodes, 150000,Diags);
  Opts.MaxLoop = Args.getLastArgIntValue(OPT_analyzer_max_loop, 4, Diags);
  Opts.EagerlyTrimEGraph = !Args.hasArg(OPT_analyzer_no_eagerly_trim_egraph);
  Opts.InlineCall = Args.hasArg(OPT_analyzer_inline_call);

  Opts.CheckersControlList.clear();
  for (arg_iterator it = Args.filtered_begin(OPT_analyzer_checker,
                                             OPT_analyzer_disable_checker),
         ie = Args.filtered_end(); it != ie; ++it) {
    const Arg *A = *it;
    A->claim();
    bool enable = (A->getOption().getID() == OPT_analyzer_checker);
    // We can have a list of comma separated checker names, e.g:
    // '-analyzer-checker=cocoa,unix'
    llvm::StringRef checkerList = A->getValue(Args);
    llvm::SmallVector<llvm::StringRef, 4> checkers;
    checkerList.split(checkers, ",");
    for (unsigned i = 0, e = checkers.size(); i != e; ++i)
      Opts.CheckersControlList.push_back(std::make_pair(checkers[i], enable));
  }
}

static void ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
                             Diagnostic &Diags) {
  using namespace cc1options;

  Opts.OptimizationLevel = getOptimizationLevel(Args, IK, Diags);
  if (Opts.OptimizationLevel > 3) {
    Diags.Report(diag::err_drv_invalid_value)
      << Args.getLastArg(OPT_O)->getAsString(Args) << Opts.OptimizationLevel;
    Opts.OptimizationLevel = 3;
  }

  // We must always run at least the always inlining pass.
  Opts.Inlining = (Opts.OptimizationLevel > 1) ? CodeGenOptions::NormalInlining
    : CodeGenOptions::OnlyAlwaysInlining;

  Opts.DebugInfo = Args.hasArg(OPT_g);
  Opts.LimitDebugInfo = Args.hasArg(OPT_flimit_debug_info);
  Opts.DisableLLVMOpts = Args.hasArg(OPT_disable_llvm_optzns);
  Opts.DisableRedZone = Args.hasArg(OPT_disable_red_zone);
  Opts.RelaxedAliasing = Args.hasArg(OPT_relaxed_aliasing);
  Opts.DwarfDebugFlags = Args.getLastArgValue(OPT_dwarf_debug_flags);
  Opts.MergeAllConstants = !Args.hasArg(OPT_fno_merge_all_constants);
  Opts.NoCommon = Args.hasArg(OPT_fno_common);
  Opts.NoImplicitFloat = Args.hasArg(OPT_no_implicit_float);
  Opts.OptimizeSize = Args.hasArg(OPT_Os);
  Opts.SimplifyLibCalls = !(Args.hasArg(OPT_fno_builtin) ||
                            Args.hasArg(OPT_ffreestanding));
  Opts.UnrollLoops = Args.hasArg(OPT_funroll_loops) ||
                     (Opts.OptimizationLevel > 1 && !Opts.OptimizeSize);

  Opts.AsmVerbose = Args.hasArg(OPT_masm_verbose);
  Opts.CXAAtExit = !Args.hasArg(OPT_fno_use_cxa_atexit);
  Opts.CXXCtorDtorAliases = Args.hasArg(OPT_mconstructor_aliases);
  Opts.CodeModel = Args.getLastArgValue(OPT_mcode_model);
  Opts.DebugPass = Args.getLastArgValue(OPT_mdebug_pass);
  Opts.DisableFPElim = Args.hasArg(OPT_mdisable_fp_elim);
  Opts.FloatABI = Args.getLastArgValue(OPT_mfloat_abi);
  Opts.HiddenWeakVTables = Args.hasArg(OPT_fhidden_weak_vtables);
  Opts.LessPreciseFPMAD = Args.hasArg(OPT_cl_mad_enable);
  Opts.LimitFloatPrecision = Args.getLastArgValue(OPT_mlimit_float_precision);
  Opts.NoInfsFPMath = Opts.NoNaNsFPMath = Args.hasArg(OPT_cl_finite_math_only)||
                                          Args.hasArg(OPT_cl_fast_relaxed_math);
  Opts.NoZeroInitializedInBSS = Args.hasArg(OPT_mno_zero_initialized_in_bss);
  Opts.NumRegisterParameters = Args.getLastArgIntValue(OPT_mregparm, 0, Diags);
  Opts.RelaxAll = Args.hasArg(OPT_mrelax_all);
  Opts.OmitLeafFramePointer = Args.hasArg(OPT_momit_leaf_frame_pointer);
  Opts.SoftFloat = Args.hasArg(OPT_msoft_float);
  Opts.UnsafeFPMath = Args.hasArg(OPT_cl_unsafe_math_optimizations) ||
                      Args.hasArg(OPT_cl_fast_relaxed_math);
  Opts.UnwindTables = Args.hasArg(OPT_munwind_tables);
  Opts.RelocationModel = Args.getLastArgValue(OPT_mrelocation_model, "pic");

  Opts.FunctionSections = Args.hasArg(OPT_ffunction_sections);
  Opts.DataSections = Args.hasArg(OPT_fdata_sections);

  Opts.MainFileName = Args.getLastArgValue(OPT_main_file_name);
  Opts.VerifyModule = !Args.hasArg(OPT_disable_llvm_verifier);

  Opts.InstrumentFunctions = Args.hasArg(OPT_finstrument_functions);
  Opts.InstrumentForProfiling = Args.hasArg(OPT_pg);

  if (Arg *A = Args.getLastArg(OPT_fobjc_dispatch_method_EQ)) {
    llvm::StringRef Name = A->getValue(Args);
    unsigned Method = llvm::StringSwitch<unsigned>(Name)
      .Case("legacy", CodeGenOptions::Legacy)
      .Case("non-legacy", CodeGenOptions::NonLegacy)
      .Case("mixed", CodeGenOptions::Mixed)
      .Default(~0U);
    if (Method == ~0U)
      Diags.Report(diag::err_drv_invalid_value) << A->getAsString(Args) << Name;
    else
      Opts.ObjCDispatchMethod = Method;
  }
}

static void ParseDependencyOutputArgs(DependencyOutputOptions &Opts,
                                      ArgList &Args) {
  using namespace cc1options;
  Opts.OutputFile = Args.getLastArgValue(OPT_dependency_file);
  Opts.Targets = Args.getAllArgValues(OPT_MT);
  Opts.IncludeSystemHeaders = Args.hasArg(OPT_sys_header_deps);
  Opts.UsePhonyTargets = Args.hasArg(OPT_MP);
  Opts.ShowHeaderIncludes = Args.hasArg(OPT_H);
  Opts.HeaderIncludeOutputFile = Args.getLastArgValue(OPT_header_include_file);
}

static void ParseDiagnosticArgs(DiagnosticOptions &Opts, ArgList &Args,
                                Diagnostic &Diags) {
  using namespace cc1options;
  Opts.IgnoreWarnings = Args.hasArg(OPT_w);
  Opts.NoRewriteMacros = Args.hasArg(OPT_Wno_rewrite_macros);
  Opts.Pedantic = Args.hasArg(OPT_pedantic);
  Opts.PedanticErrors = Args.hasArg(OPT_pedantic_errors);
  Opts.ShowCarets = !Args.hasArg(OPT_fno_caret_diagnostics);
  Opts.ShowColors = Args.hasArg(OPT_fcolor_diagnostics);
  Opts.ShowColumn = !Args.hasArg(OPT_fno_show_column);
  Opts.ShowFixits = !Args.hasArg(OPT_fno_diagnostics_fixit_info);
  Opts.ShowLocation = !Args.hasArg(OPT_fno_show_source_location);
  Opts.ShowOptionNames = Args.hasArg(OPT_fdiagnostics_show_option);

  llvm::StringRef ShowOverloads =
    Args.getLastArgValue(OPT_fshow_overloads_EQ, "all");
  if (ShowOverloads == "best")
    Opts.ShowOverloads = Diagnostic::Ovl_Best;
  else if (ShowOverloads == "all")
    Opts.ShowOverloads = Diagnostic::Ovl_All;
  else
    Diags.Report(diag::err_drv_invalid_value)
      << Args.getLastArg(OPT_fshow_overloads_EQ)->getAsString(Args)
      << ShowOverloads;

  llvm::StringRef ShowCategory =
    Args.getLastArgValue(OPT_fdiagnostics_show_category, "none");
  if (ShowCategory == "none")
    Opts.ShowCategories = 0;
  else if (ShowCategory == "id")
    Opts.ShowCategories = 1;
  else if (ShowCategory == "name")
    Opts.ShowCategories = 2;
  else
    Diags.Report(diag::err_drv_invalid_value)
      << Args.getLastArg(OPT_fdiagnostics_show_category)->getAsString(Args)
      << ShowCategory;

  Opts.ShowSourceRanges = Args.hasArg(OPT_fdiagnostics_print_source_range_info);
  Opts.ShowParseableFixits = Args.hasArg(OPT_fdiagnostics_parseable_fixits);
  Opts.VerifyDiagnostics = Args.hasArg(OPT_verify);
  Opts.ErrorLimit = Args.getLastArgIntValue(OPT_ferror_limit, 0, Diags);
  Opts.MacroBacktraceLimit
    = Args.getLastArgIntValue(OPT_fmacro_backtrace_limit,
                         DiagnosticOptions::DefaultMacroBacktraceLimit, Diags);
  Opts.TemplateBacktraceLimit
    = Args.getLastArgIntValue(OPT_ftemplate_backtrace_limit,
                         DiagnosticOptions::DefaultTemplateBacktraceLimit,
                         Diags);
  Opts.TabStop = Args.getLastArgIntValue(OPT_ftabstop,
                                    DiagnosticOptions::DefaultTabStop, Diags);
  if (Opts.TabStop == 0 || Opts.TabStop > DiagnosticOptions::MaxTabStop) {
    Diags.Report(diag::warn_ignoring_ftabstop_value)
      << Opts.TabStop << DiagnosticOptions::DefaultTabStop;
    Opts.TabStop = DiagnosticOptions::DefaultTabStop;
  }
  Opts.MessageLength = Args.getLastArgIntValue(OPT_fmessage_length, 0, Diags);
  Opts.DumpBuildInformation = Args.getLastArgValue(OPT_dump_build_information);
  Opts.Warnings = Args.getAllArgValues(OPT_W);
}

static void ParseFileSystemArgs(FileSystemOptions &Opts, ArgList &Args) {
  Opts.WorkingDir = Args.getLastArgValue(OPT_working_directory);
}

static InputKind ParseFrontendArgs(FrontendOptions &Opts, ArgList &Args,
                                   Diagnostic &Diags) {
  using namespace cc1options;
  Opts.ProgramAction = frontend::ParseSyntaxOnly;
  if (const Arg *A = Args.getLastArg(OPT_Action_Group)) {
    switch (A->getOption().getID()) {
    default:
      assert(0 && "Invalid option in group!");
    case OPT_ast_dump:
      Opts.ProgramAction = frontend::ASTDump; break;
    case OPT_ast_dump_xml:
      Opts.ProgramAction = frontend::ASTDumpXML; break;
    case OPT_ast_print:
      Opts.ProgramAction = frontend::ASTPrint; break;
    case OPT_ast_view:
      Opts.ProgramAction = frontend::ASTView; break;
    case OPT_boostcon:
      Opts.ProgramAction = frontend::BoostCon; break;
    case OPT_dump_raw_tokens:
      Opts.ProgramAction = frontend::DumpRawTokens; break;
    case OPT_dump_tokens:
      Opts.ProgramAction = frontend::DumpTokens; break;
    case OPT_S:
      Opts.ProgramAction = frontend::EmitAssembly; break;
    case OPT_emit_llvm_bc:
      Opts.ProgramAction = frontend::EmitBC; break;
    case OPT_emit_html:
      Opts.ProgramAction = frontend::EmitHTML; break;
    case OPT_emit_llvm:
      Opts.ProgramAction = frontend::EmitLLVM; break;
    case OPT_emit_llvm_only:
      Opts.ProgramAction = frontend::EmitLLVMOnly; break;
    case OPT_emit_codegen_only:
      Opts.ProgramAction = frontend::EmitCodeGenOnly; break;
    case OPT_emit_obj:
      Opts.ProgramAction = frontend::EmitObj; break;
    case OPT_fixit_EQ:
      Opts.FixItSuffix = A->getValue(Args);
      // fall-through!
    case OPT_fixit:
      Opts.ProgramAction = frontend::FixIt; break;
    case OPT_emit_pch:
      Opts.ProgramAction = frontend::GeneratePCH; break;
    case OPT_emit_pth:
      Opts.ProgramAction = frontend::GeneratePTH; break;
    case OPT_init_only:
      Opts.ProgramAction = frontend::InitOnly; break;
    case OPT_fsyntax_only:
      Opts.ProgramAction = frontend::ParseSyntaxOnly; break;
    case OPT_print_decl_contexts:
      Opts.ProgramAction = frontend::PrintDeclContext; break;
    case OPT_print_preamble:
      Opts.ProgramAction = frontend::PrintPreamble; break;
    case OPT_E:
      Opts.ProgramAction = frontend::PrintPreprocessedInput; break;
    case OPT_rewrite_macros:
      Opts.ProgramAction = frontend::RewriteMacros; break;
    case OPT_rewrite_objc:
      Opts.ProgramAction = frontend::RewriteObjC; break;
    case OPT_rewrite_test:
      Opts.ProgramAction = frontend::RewriteTest; break;
    case OPT_analyze:
      Opts.ProgramAction = frontend::RunAnalysis; break;
    case OPT_Eonly:
      Opts.ProgramAction = frontend::RunPreprocessorOnly; break;
    case OPT_create_module:
      Opts.ProgramAction = frontend::CreateModule; break;
    }
  }

  if (const Arg* A = Args.getLastArg(OPT_plugin)) {
    Opts.Plugins.push_back(A->getValue(Args,0));
    Opts.ProgramAction = frontend::PluginAction;
    Opts.ActionName = A->getValue(Args);

    for (arg_iterator it = Args.filtered_begin(OPT_plugin_arg),
           end = Args.filtered_end(); it != end; ++it) {
      if ((*it)->getValue(Args, 0) == Opts.ActionName)
        Opts.PluginArgs.push_back((*it)->getValue(Args, 1));
    }
  }

  Opts.AddPluginActions = Args.getAllArgValues(OPT_add_plugin);
  Opts.AddPluginArgs.resize(Opts.AddPluginActions.size());
  for (int i = 0, e = Opts.AddPluginActions.size(); i != e; ++i) {
    for (arg_iterator it = Args.filtered_begin(OPT_plugin_arg),
           end = Args.filtered_end(); it != end; ++it) {
      if ((*it)->getValue(Args, 0) == Opts.AddPluginActions[i])
        Opts.AddPluginArgs[i].push_back((*it)->getValue(Args, 1));
    }
  }

  if (const Arg *A = Args.getLastArg(OPT_code_completion_at)) {
    Opts.CodeCompletionAt =
      ParsedSourceLocation::FromString(A->getValue(Args));
    if (Opts.CodeCompletionAt.FileName.empty())
      Diags.Report(diag::err_drv_invalid_value)
        << A->getAsString(Args) << A->getValue(Args);
  }
  Opts.DisableFree = Args.hasArg(OPT_disable_free);

  Opts.OutputFile = Args.getLastArgValue(OPT_o);
  Opts.Plugins = Args.getAllArgValues(OPT_load);
  Opts.RelocatablePCH = Args.hasArg(OPT_relocatable_pch);
  Opts.ChainedPCH = Args.hasArg(OPT_chained_pch);
  Opts.ShowHelp = Args.hasArg(OPT_help);
  Opts.ShowMacrosInCodeCompletion = Args.hasArg(OPT_code_completion_macros);
  Opts.ShowCodePatternsInCodeCompletion
    = Args.hasArg(OPT_code_completion_patterns);
  Opts.ShowGlobalSymbolsInCodeCompletion
    = !Args.hasArg(OPT_no_code_completion_globals);
  Opts.ShowStats = Args.hasArg(OPT_print_stats);
  Opts.ShowTimers = Args.hasArg(OPT_ftime_report);
  Opts.ShowVersion = Args.hasArg(OPT_version);
  Opts.ASTMergeFiles = Args.getAllArgValues(OPT_ast_merge);
  Opts.LLVMArgs = Args.getAllArgValues(OPT_mllvm);
  Opts.FixWhatYouCan = Args.hasArg(OPT_fix_what_you_can);
  Opts.Modules = Args.getAllArgValues(OPT_import_module);

  InputKind DashX = IK_None;
  if (const Arg *A = Args.getLastArg(OPT_x)) {
    DashX = llvm::StringSwitch<InputKind>(A->getValue(Args))
      .Case("c", IK_C)
      .Case("cl", IK_OpenCL)
      .Case("c", IK_C)
      .Case("cl", IK_OpenCL)
      .Case("cuda", IK_CUDA)
      .Case("c++", IK_CXX)
      .Case("objective-c", IK_ObjC)
      .Case("objective-c++", IK_ObjCXX)
      .Case("cpp-output", IK_PreprocessedC)
      .Case("assembler-with-cpp", IK_Asm)
      .Case("c++-cpp-output", IK_PreprocessedCXX)
      .Case("objective-c-cpp-output", IK_PreprocessedObjC)
      .Case("objective-c++-cpp-output", IK_PreprocessedObjCXX)
      .Case("c-header", IK_C)
      .Case("objective-c-header", IK_ObjC)
      .Case("c++-header", IK_CXX)
      .Case("objective-c++-header", IK_ObjCXX)
      .Case("ast", IK_AST)
      .Case("ir", IK_LLVM_IR)
      .Default(IK_None);
    if (DashX == IK_None)
      Diags.Report(diag::err_drv_invalid_value)
        << A->getAsString(Args) << A->getValue(Args);
  }

  // '-' is the default input if none is given.
  std::vector<std::string> Inputs = Args.getAllArgValues(OPT_INPUT);
  Opts.Inputs.clear();
  if (Inputs.empty())
    Inputs.push_back("-");
  for (unsigned i = 0, e = Inputs.size(); i != e; ++i) {
    InputKind IK = DashX;
    if (IK == IK_None) {
      IK = FrontendOptions::getInputKindForExtension(
        llvm::StringRef(Inputs[i]).rsplit('.').second);
      // FIXME: Remove this hack.
      if (i == 0)
        DashX = IK;
    }
    Opts.Inputs.push_back(std::make_pair(IK, Inputs[i]));
  }

  return DashX;
}

std::string CompilerInvocation::GetResourcesPath(const char *Argv0,
                                                 void *MainAddr) {
  llvm::sys::Path P = llvm::sys::Path::GetMainExecutable(Argv0, MainAddr);

  if (!P.isEmpty()) {
    P.eraseComponent();  // Remove /clang from foo/bin/clang
    P.eraseComponent();  // Remove /bin   from foo/bin

    // Get foo/lib/clang/<version>/include
    P.appendComponent("lib");
    P.appendComponent("clang");
    P.appendComponent(CLANG_VERSION_STRING);
  }

  return P.str();
}

static void ParseHeaderSearchArgs(HeaderSearchOptions &Opts, ArgList &Args) {
  using namespace cc1options;
  Opts.Sysroot = Args.getLastArgValue(OPT_isysroot, "/");
  Opts.Verbose = Args.hasArg(OPT_v);
  Opts.UseBuiltinIncludes = !Args.hasArg(OPT_nobuiltininc);
  Opts.UseStandardIncludes = !Args.hasArg(OPT_nostdinc);
  Opts.UseStandardCXXIncludes = !Args.hasArg(OPT_nostdincxx);
  Opts.ResourceDir = Args.getLastArgValue(OPT_resource_dir);

  // Add -I... and -F... options in order.
  for (arg_iterator it = Args.filtered_begin(OPT_I, OPT_F),
         ie = Args.filtered_end(); it != ie; ++it)
    Opts.AddPath((*it)->getValue(Args), frontend::Angled, true,
                 /*IsFramework=*/ (*it)->getOption().matches(OPT_F), true);

  // Add -iprefix/-iwith-prefix/-iwithprefixbefore options.
  llvm::StringRef Prefix = ""; // FIXME: This isn't the correct default prefix.
  for (arg_iterator it = Args.filtered_begin(OPT_iprefix, OPT_iwithprefix,
                                             OPT_iwithprefixbefore),
         ie = Args.filtered_end(); it != ie; ++it) {
    const Arg *A = *it;
    if (A->getOption().matches(OPT_iprefix))
      Prefix = A->getValue(Args);
    else if (A->getOption().matches(OPT_iwithprefix))
      Opts.AddPath(Prefix.str() + A->getValue(Args),
                   frontend::System, false, false, true);
    else
      Opts.AddPath(Prefix.str() + A->getValue(Args),
                   frontend::Angled, false, false, true);
  }

  for (arg_iterator it = Args.filtered_begin(OPT_idirafter),
         ie = Args.filtered_end(); it != ie; ++it)
    Opts.AddPath((*it)->getValue(Args), frontend::After, true, false, true);
  for (arg_iterator it = Args.filtered_begin(OPT_iquote),
         ie = Args.filtered_end(); it != ie; ++it)
    Opts.AddPath((*it)->getValue(Args), frontend::Quoted, true, false, true);
  for (arg_iterator it = Args.filtered_begin(OPT_cxx_isystem, OPT_isystem,
         OPT_iwithsysroot), ie = Args.filtered_end(); it != ie; ++it)
    Opts.AddPath((*it)->getValue(Args),
                 ((*it)->getOption().matches(OPT_cxx_isystem) ?
                   frontend::CXXSystem : frontend::System),
                 true, false, (*it)->getOption().matches(OPT_iwithsysroot));

  // FIXME: Need options for the various environment variables!
}

void CompilerInvocation::setLangDefaults(LangOptions &Opts, InputKind IK,
                                         LangStandard::Kind LangStd) {
  // Set some properties which depend soley on the input kind; it would be nice
  // to move these to the language standard, and have the driver resolve the
  // input kind + language standard.
  if (IK == IK_Asm) {
    Opts.AsmPreprocessor = 1;
  } else if (IK == IK_ObjC ||
             IK == IK_ObjCXX ||
             IK == IK_PreprocessedObjC ||
             IK == IK_PreprocessedObjCXX) {
    Opts.ObjC1 = Opts.ObjC2 = 1;
  }

  if (LangStd == LangStandard::lang_unspecified) {
    // Based on the base language, pick one.
    switch (IK) {
    case IK_None:
    case IK_AST:
    case IK_LLVM_IR:
      assert(0 && "Invalid input kind!");
    case IK_OpenCL:
      LangStd = LangStandard::lang_opencl;
      break;
    case IK_CUDA:
      LangStd = LangStandard::lang_cuda;
      break;
    case IK_Asm:
    case IK_C:
    case IK_PreprocessedC:
    case IK_ObjC:
    case IK_PreprocessedObjC:
      LangStd = LangStandard::lang_gnu99;
      break;
    case IK_CXX:
    case IK_PreprocessedCXX:
    case IK_ObjCXX:
    case IK_PreprocessedObjCXX:
      LangStd = LangStandard::lang_gnucxx98;
      break;
    }
  }

  const LangStandard &Std = LangStandard::getLangStandardForKind(LangStd);
  Opts.BCPLComment = Std.hasBCPLComments();
  Opts.C99 = Std.isC99();
  Opts.CPlusPlus = Std.isCPlusPlus();
  Opts.CPlusPlus0x = Std.isCPlusPlus0x();
  Opts.Digraphs = Std.hasDigraphs();
  Opts.GNUMode = Std.isGNUMode();
  Opts.GNUInline = !Std.isC99();
  Opts.HexFloats = Std.hasHexFloats();
  Opts.ImplicitInt = Std.hasImplicitInt();

  // OpenCL has some additional defaults.
  if (LangStd == LangStandard::lang_opencl) {
    Opts.OpenCL = 1;
    Opts.AltiVec = 1;
    Opts.CXXOperatorNames = 1;
    Opts.LaxVectorConversions = 1;
    Opts.DefaultFPContract = 1;
  }

  if (LangStd == LangStandard::lang_cuda)
    Opts.CUDA = 1;

  // OpenCL and C++ both have bool, true, false keywords.
  Opts.Bool = Opts.OpenCL || Opts.CPlusPlus;

  Opts.GNUKeywords = Opts.GNUMode;
  Opts.CXXOperatorNames = Opts.CPlusPlus;

  // Mimicing gcc's behavior, trigraphs are only enabled if -trigraphs
  // is specified, or -std is set to a conforming mode.
  Opts.Trigraphs = !Opts.GNUMode;

  Opts.DollarIdents = !Opts.AsmPreprocessor;
}

static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
                          Diagnostic &Diags) {
  // FIXME: Cleanup per-file based stuff.
  LangStandard::Kind LangStd = LangStandard::lang_unspecified;
  if (const Arg *A = Args.getLastArg(OPT_std_EQ)) {
    LangStd = llvm::StringSwitch<LangStandard::Kind>(A->getValue(Args))
#define LANGSTANDARD(id, name, desc, features) \
      .Case(name, LangStandard::lang_##id)
#include "clang/Frontend/LangStandards.def"
      .Default(LangStandard::lang_unspecified);
    if (LangStd == LangStandard::lang_unspecified)
      Diags.Report(diag::err_drv_invalid_value)
        << A->getAsString(Args) << A->getValue(Args);
  }

  if (const Arg *A = Args.getLastArg(OPT_cl_std_EQ)) {
    if (strcmp(A->getValue(Args), "CL1.1") != 0) {
      Diags.Report(diag::err_drv_invalid_value)
        << A->getAsString(Args) << A->getValue(Args);
    }
  }

  CompilerInvocation::setLangDefaults(Opts, IK, LangStd);

  // We abuse '-f[no-]gnu-keywords' to force overriding all GNU-extension
  // keywords. This behavior is provided by GCC's poorly named '-fasm' flag,
  // while a subset (the non-C++ GNU keywords) is provided by GCC's
  // '-fgnu-keywords'. Clang conflates the two for simplicity under the single
  // name, as it doesn't seem a useful distinction.
  Opts.GNUKeywords = Args.hasFlag(OPT_fgnu_keywords, OPT_fno_gnu_keywords,
                                  Opts.GNUKeywords);

  if (Args.hasArg(OPT_fno_operator_names))
    Opts.CXXOperatorNames = 0;

  if (Args.hasArg(OPT_fobjc_gc_only))
    Opts.setGCMode(LangOptions::GCOnly);
  else if (Args.hasArg(OPT_fobjc_gc))
    Opts.setGCMode(LangOptions::HybridGC);
  
  if (Args.hasArg(OPT_fapple_kext)) {
    if (!Opts.CPlusPlus)
      Diags.Report(diag::warn_c_kext);
    else
      Opts.AppleKext = 1;
  }

  if (Args.hasArg(OPT_print_ivar_layout))
    Opts.ObjCGCBitmapPrint = 1;
  if (Args.hasArg(OPT_fno_constant_cfstrings))
    Opts.NoConstantCFStrings = 1;

  if (Args.hasArg(OPT_faltivec))
    Opts.AltiVec = 1;

  if (Args.hasArg(OPT_pthread))
    Opts.POSIXThreads = 1;

  llvm::StringRef Vis = Args.getLastArgValue(OPT_fvisibility, "default");
  if (Vis == "default")
    Opts.setVisibilityMode(DefaultVisibility);
  else if (Vis == "hidden")
    Opts.setVisibilityMode(HiddenVisibility);
  else if (Vis == "protected")
    Opts.setVisibilityMode(ProtectedVisibility);
  else
    Diags.Report(diag::err_drv_invalid_value)
      << Args.getLastArg(OPT_fvisibility)->getAsString(Args) << Vis;

  if (Args.hasArg(OPT_fvisibility_inlines_hidden))
    Opts.InlineVisibilityHidden = 1;

  if (Args.hasArg(OPT_ftrapv)) {
    Opts.setSignedOverflowBehavior(LangOptions::SOB_Trapping);
    // Set the handler, if one is specified.
    Opts.OverflowHandler =
        Args.getLastArgValue(OPT_ftrapv_handler);
  }
  else if (Args.hasArg(OPT_fwrapv))
    Opts.setSignedOverflowBehavior(LangOptions::SOB_Defined);

  if (Args.hasArg(OPT_trigraphs))
    Opts.Trigraphs = 1;

  Opts.DollarIdents = Args.hasFlag(OPT_fdollars_in_identifiers,
                                   OPT_fno_dollars_in_identifiers,
                                   Opts.DollarIdents);
  Opts.PascalStrings = Args.hasArg(OPT_fpascal_strings);
  Opts.Microsoft = Args.hasArg(OPT_fms_extensions);
  Opts.MSCVersion = Args.getLastArgIntValue(OPT_fmsc_version, 0, Diags);
  Opts.Borland = Args.hasArg(OPT_fborland_extensions);
  Opts.WritableStrings = Args.hasArg(OPT_fwritable_strings);
  Opts.ConstStrings = Args.hasArg(OPT_Wwrite_strings);
  if (Args.hasArg(OPT_fno_lax_vector_conversions))
    Opts.LaxVectorConversions = 0;
  if (Args.hasArg(OPT_fno_threadsafe_statics))
    Opts.ThreadsafeStatics = 0;
  Opts.Exceptions = Args.hasArg(OPT_fexceptions);
  Opts.ObjCExceptions = Args.hasArg(OPT_fobjc_exceptions);
  Opts.CXXExceptions = Args.hasArg(OPT_fcxx_exceptions);
  Opts.SjLjExceptions = Args.hasArg(OPT_fsjlj_exceptions);

  Opts.RTTI = !Args.hasArg(OPT_fno_rtti);
  Opts.Blocks = Args.hasArg(OPT_fblocks);
  Opts.CharIsSigned = !Args.hasArg(OPT_fno_signed_char);
  Opts.ShortWChar = Args.hasArg(OPT_fshort_wchar);
  Opts.ShortEnums = Args.hasArg(OPT_fshort_enums);
  Opts.Freestanding = Args.hasArg(OPT_ffreestanding);
  Opts.NoBuiltin = Args.hasArg(OPT_fno_builtin) || Opts.Freestanding;
  Opts.AssumeSaneOperatorNew = !Args.hasArg(OPT_fno_assume_sane_operator_new);
  Opts.HeinousExtensions = Args.hasArg(OPT_fheinous_gnu_extensions);
  Opts.AccessControl = !Args.hasArg(OPT_fno_access_control);
  Opts.ElideConstructors = !Args.hasArg(OPT_fno_elide_constructors);
  Opts.MathErrno = Args.hasArg(OPT_fmath_errno);
  Opts.InstantiationDepth = Args.getLastArgIntValue(OPT_ftemplate_depth, 1024,
                                               Diags);
  Opts.NumLargeByValueCopy = Args.getLastArgIntValue(OPT_Wlarge_by_value_copy,
                                                    0, Diags);
  Opts.MSBitfields = Args.hasArg(OPT_mms_bitfields);
  Opts.NeXTRuntime = !Args.hasArg(OPT_fgnu_runtime);
  Opts.ObjCConstantStringClass =
    Args.getLastArgValue(OPT_fconstant_string_class);
  Opts.ObjCNonFragileABI = Args.hasArg(OPT_fobjc_nonfragile_abi);
  if (Opts.ObjCNonFragileABI)
    Opts.ObjCNonFragileABI2 = true;
  Opts.ObjCDefaultSynthProperties =
    Args.hasArg(OPT_fobjc_default_synthesize_properties);
  Opts.CatchUndefined = Args.hasArg(OPT_fcatch_undefined_behavior);
  Opts.EmitAllDecls = Args.hasArg(OPT_femit_all_decls);
  Opts.PICLevel = Args.getLastArgIntValue(OPT_pic_level, 0, Diags);
  Opts.Static = Args.hasArg(OPT_static_define);
  Opts.DumpRecordLayouts = Args.hasArg(OPT_fdump_record_layouts);
  Opts.DumpVTableLayouts = Args.hasArg(OPT_fdump_vtable_layouts);
  Opts.SpellChecking = !Args.hasArg(OPT_fno_spell_checking);
  Opts.NoBitFieldTypeAlign = Args.hasArg(OPT_fno_bitfield_type_align);
  Opts.SinglePrecisionConstants = Args.hasArg(OPT_cl_single_precision_constant);
  Opts.FastRelaxedMath = Args.hasArg(OPT_cl_fast_relaxed_math);
  Opts.OptimizeSize = 0;
  Opts.MRTD = Args.hasArg(OPT_mrtd);

  // FIXME: Eliminate this dependency.
  unsigned Opt = getOptimizationLevel(Args, IK, Diags);
  Opts.Optimize = Opt != 0;

  // This is the __NO_INLINE__ define, which just depends on things like the
  // optimization level and -fno-inline, not actually whether the backend has
  // inlining enabled.
  //
  // FIXME: This is affected by other options (-fno-inline).
  Opts.NoInline = !Opt;

  unsigned SSP = Args.getLastArgIntValue(OPT_stack_protector, 0, Diags);
  switch (SSP) {
  default:
    Diags.Report(diag::err_drv_invalid_value)
      << Args.getLastArg(OPT_stack_protector)->getAsString(Args) << SSP;
    break;
  case 0: Opts.setStackProtectorMode(LangOptions::SSPOff); break;
  case 1: Opts.setStackProtectorMode(LangOptions::SSPOn);  break;
  case 2: Opts.setStackProtectorMode(LangOptions::SSPReq); break;
  }
}

static void ParsePreprocessorArgs(PreprocessorOptions &Opts, ArgList &Args,
                                  FileManager &FileMgr,
                                  Diagnostic &Diags) {
  using namespace cc1options;
  Opts.ImplicitPCHInclude = Args.getLastArgValue(OPT_include_pch);
  Opts.ImplicitPTHInclude = Args.getLastArgValue(OPT_include_pth);
  if (const Arg *A = Args.getLastArg(OPT_token_cache))
      Opts.TokenCache = A->getValue(Args);
  else
    Opts.TokenCache = Opts.ImplicitPTHInclude;
  Opts.UsePredefines = !Args.hasArg(OPT_undef);
  Opts.DetailedRecord = Args.hasArg(OPT_detailed_preprocessing_record);
  Opts.DisablePCHValidation = Args.hasArg(OPT_fno_validate_pch);

  Opts.DumpDeserializedPCHDecls = Args.hasArg(OPT_dump_deserialized_pch_decls);
  for (arg_iterator it = Args.filtered_begin(OPT_error_on_deserialized_pch_decl),
         ie = Args.filtered_end(); it != ie; ++it) {
    const Arg *A = *it;
    Opts.DeserializedPCHDeclsToErrorOn.insert(A->getValue(Args));
  }

  if (const Arg *A = Args.getLastArg(OPT_preamble_bytes_EQ)) {
    llvm::StringRef Value(A->getValue(Args));
    size_t Comma = Value.find(',');
    unsigned Bytes = 0;
    unsigned EndOfLine = 0;

    if (Comma == llvm::StringRef::npos ||
        Value.substr(0, Comma).getAsInteger(10, Bytes) ||
        Value.substr(Comma + 1).getAsInteger(10, EndOfLine))
      Diags.Report(diag::err_drv_preamble_format);
    else {
      Opts.PrecompiledPreambleBytes.first = Bytes;
      Opts.PrecompiledPreambleBytes.second = (EndOfLine != 0);
    }
  }

  // Add macros from the command line.
  for (arg_iterator it = Args.filtered_begin(OPT_D, OPT_U),
         ie = Args.filtered_end(); it != ie; ++it) {
    if ((*it)->getOption().matches(OPT_D))
      Opts.addMacroDef((*it)->getValue(Args));
    else
      Opts.addMacroUndef((*it)->getValue(Args));
  }

  Opts.MacroIncludes = Args.getAllArgValues(OPT_imacros);

  // Add the ordered list of -includes.
  for (arg_iterator it = Args.filtered_begin(OPT_include, OPT_include_pch,
                                             OPT_include_pth),
         ie = Args.filtered_end(); it != ie; ++it) {
    const Arg *A = *it;
    // PCH is handled specially, we need to extra the original include path.
    if (A->getOption().matches(OPT_include_pch)) {
      std::string OriginalFile =
        ASTReader::getOriginalSourceFile(A->getValue(Args), FileMgr, Diags);
      if (OriginalFile.empty())
        continue;

      Opts.Includes.push_back(OriginalFile);
    } else
      Opts.Includes.push_back(A->getValue(Args));
  }

  for (arg_iterator it = Args.filtered_begin(OPT_chain_include),
         ie = Args.filtered_end(); it != ie; ++it) {
    const Arg *A = *it;
    Opts.ChainedIncludes.push_back(A->getValue(Args));
  }

  // Include 'altivec.h' if -faltivec option present
  if (Args.hasArg(OPT_faltivec))
    Opts.Includes.push_back("altivec.h");

  for (arg_iterator it = Args.filtered_begin(OPT_remap_file),
         ie = Args.filtered_end(); it != ie; ++it) {
    const Arg *A = *it;
    std::pair<llvm::StringRef,llvm::StringRef> Split =
      llvm::StringRef(A->getValue(Args)).split(';');

    if (Split.second.empty()) {
      Diags.Report(diag::err_drv_invalid_remap_file) << A->getAsString(Args);
      continue;
    }

    Opts.addRemappedFile(Split.first, Split.second);
  }
}

static void ParsePreprocessorOutputArgs(PreprocessorOutputOptions &Opts,
                                        ArgList &Args) {
  using namespace cc1options;
  Opts.ShowCPP = !Args.hasArg(OPT_dM);
  Opts.ShowComments = Args.hasArg(OPT_C);
  Opts.ShowLineMarkers = !Args.hasArg(OPT_P);
  Opts.ShowMacroComments = Args.hasArg(OPT_CC);
  Opts.ShowMacros = Args.hasArg(OPT_dM) || Args.hasArg(OPT_dD);
}

static void ParseTargetArgs(TargetOptions &Opts, ArgList &Args) {
  using namespace cc1options;
  Opts.ABI = Args.getLastArgValue(OPT_target_abi);
  Opts.CXXABI = Args.getLastArgValue(OPT_cxx_abi);
  Opts.CPU = Args.getLastArgValue(OPT_target_cpu);
  Opts.Features = Args.getAllArgValues(OPT_target_feature);
  Opts.LinkerVersion = Args.getLastArgValue(OPT_target_linker_version);
  Opts.Triple = llvm::Triple::normalize(Args.getLastArgValue(OPT_triple));

  // Use the host triple if unspecified.
  if (Opts.Triple.empty())
    Opts.Triple = llvm::sys::getHostTriple();
}

//

void CompilerInvocation::CreateFromArgs(CompilerInvocation &Res,
                                        const char *const *ArgBegin,
                                        const char *const *ArgEnd,
                                        Diagnostic &Diags) {
  // Parse the arguments.
  llvm::OwningPtr<OptTable> Opts(createCC1OptTable());
  unsigned MissingArgIndex, MissingArgCount;
  llvm::OwningPtr<InputArgList> Args(
    Opts->ParseArgs(ArgBegin, ArgEnd,MissingArgIndex, MissingArgCount));

  // Check for missing argument error.
  if (MissingArgCount)
    Diags.Report(diag::err_drv_missing_argument)
      << Args->getArgString(MissingArgIndex) << MissingArgCount;

  // Issue errors on unknown arguments.
  for (arg_iterator it = Args->filtered_begin(OPT_UNKNOWN),
         ie = Args->filtered_end(); it != ie; ++it)
    Diags.Report(diag::err_drv_unknown_argument) << (*it)->getAsString(*Args);

  ParseAnalyzerArgs(Res.getAnalyzerOpts(), *Args, Diags);
  ParseDependencyOutputArgs(Res.getDependencyOutputOpts(), *Args);
  ParseDiagnosticArgs(Res.getDiagnosticOpts(), *Args, Diags);
  ParseFileSystemArgs(Res.getFileSystemOpts(), *Args);
  // FIXME: We shouldn't have to pass the DashX option around here
  InputKind DashX = ParseFrontendArgs(Res.getFrontendOpts(), *Args, Diags);
  ParseCodeGenArgs(Res.getCodeGenOpts(), *Args, DashX, Diags);
  ParseHeaderSearchArgs(Res.getHeaderSearchOpts(), *Args);
  if (DashX != IK_AST && DashX != IK_LLVM_IR) {
    ParseLangArgs(Res.getLangOpts(), *Args, DashX, Diags);
    if (Res.getFrontendOpts().ProgramAction == frontend::RewriteObjC)
      Res.getLangOpts().ObjCExceptions = 1;
  }
  // FIXME: ParsePreprocessorArgs uses the FileManager to read the contents of
  // PCH file and find the original header name. Remove the need to do that in
  // ParsePreprocessorArgs and remove the FileManager 
  // parameters from the function and the "FileManager.h" #include.
  FileManager FileMgr(Res.getFileSystemOpts());
  ParsePreprocessorArgs(Res.getPreprocessorOpts(), *Args, FileMgr, Diags);
  ParsePreprocessorOutputArgs(Res.getPreprocessorOutputOpts(), *Args);
  ParseTargetArgs(Res.getTargetOpts(), *Args);
}