33 files changed, 1655 insertions, 766 deletions

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 44f52a4f5903..cbbd3e069945 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -60,3 +60,62 @@ Description:
                 Indicates whether the block layer should automatically
                 generate checksums for write requests bound for
                 devices that support receiving integrity metadata.
+
+What:           /sys/block/<disk>/alignment_offset
+Date:           April 2009
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Storage devices may report a physical block size that is
+                bigger than the logical block size (for instance a drive
+                with 4KB physical sectors exposing 512-byte logical
+                blocks to the operating system).  This parameter
+                indicates how many bytes the beginning of the device is
+                offset from the disk's natural alignment.
+
+What:           /sys/block/<disk>/<partition>/alignment_offset
+Date:           April 2009
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Storage devices may report a physical block size that is
+                bigger than the logical block size (for instance a drive
+                with 4KB physical sectors exposing 512-byte logical
+                blocks to the operating system).  This parameter
+                indicates how many bytes the beginning of the partition
+                is offset from the disk's natural alignment.
+
+What:           /sys/block/<disk>/queue/logical_block_size
+Date:           May 2009
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                This is the smallest unit the storage device can
+                address.  It is typically 512 bytes.
+
+What:           /sys/block/<disk>/queue/physical_block_size
+Date:           May 2009
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                This is the smallest unit the storage device can write
+                without resorting to read-modify-write operation.  It is
+                usually the same as the logical block size but may be
+                bigger.  One example is SATA drives with 4KB sectors
+                that expose a 512-byte logical block size to the
+                operating system.
+
+What:           /sys/block/<disk>/queue/minimum_io_size
+Date:           April 2009
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Storage devices may report a preferred minimum I/O size,
+                which is the smallest request the device can perform
+                without incurring a read-modify-write penalty.  For disk
+                drives this is often the physical block size.  For RAID
+                arrays it is often the stripe chunk size.
+
+What:           /sys/block/<disk>/queue/optimal_io_size
+Date:           April 2009
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Storage devices may report an optimal I/O size, which is
+                the device's preferred unit of receiving I/O.  This is
+                rarely reported for disk drives.  For RAID devices it is
+                usually the stripe width or the internal block size.
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
new file mode 100644
index 000000000000..0a92a7c93a62
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
@@ -0,0 +1,33 @@
+Where:          /sys/bus/pci/devices/<dev>/ccissX/cXdY/model
+Date:           March 2009
+Kernel Version: 2.6.30
+Contact:        iss_storagedev@hp.com
+Description:    Displays the SCSI INQUIRY page 0 model for logical drive
+                Y of controller X.
+
+Where:          /sys/bus/pci/devices/<dev>/ccissX/cXdY/rev
+Date:           March 2009
+Kernel Version: 2.6.30
+Contact:        iss_storagedev@hp.com
+Description:    Displays the SCSI INQUIRY page 0 revision for logical
+                drive Y of controller X.
+
+Where:          /sys/bus/pci/devices/<dev>/ccissX/cXdY/unique_id
+Date:           March 2009
+Kernel Version: 2.6.30
+Contact:        iss_storagedev@hp.com
+Description:    Displays the SCSI INQUIRY page 83 serial number for logical
+                drive Y of controller X.
+
+Where:          /sys/bus/pci/devices/<dev>/ccissX/cXdY/vendor
+Date:           March 2009
+Kernel Version: 2.6.30
+Contact:        iss_storagedev@hp.com
+Description:    Displays the SCSI INQUIRY page 0 vendor for logical drive
+                Y of controller X.
+
+Where:          /sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY
+Date:           March 2009
+Kernel Version: 2.6.30
+Contact:        iss_storagedev@hp.com
+Description:    A symbolic link to /sys/block/cciss!cXdY
diff --git a/Documentation/ABI/testing/sysfs-devices-cache_disable b/Documentation/ABI/testing/sysfs-devices-cache_disable
new file mode 100644
index 000000000000..175bb4f70512
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-cache_disable
@@ -0,0 +1,18 @@
+What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
+Date:      August 2008
+KernelVersion:  2.6.27
+Contact:        mark.langsdorf@amd.com
+Description:    These files exist in every cpu's cache index directories.
+                There are currently 2 cache_disable_# files in each
+                directory.  Reading from these files on a supported
+                processor will return that cache disable index value
+                for that processor and node.  Writing to one of these
+                files will cause the specificed cache index to be disabled.
+
+                Currently, only AMD Family 10h Processors support cache index
+                disable, and only for their L3 caches.  See the BIOS and
+                Kernel Developer's Guide at
+                http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
+                for formatting information and other details on the
+                cache index disable.
+Users:    joachim.deguara@amd.com
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index d9aa43d78bcc..25fb8bcf32a2 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -704,12 +704,24 @@ this directory the following files can currently be found:
                                 The current number of free dma_debug_entries
                                 in the allocator.
 
+        dma-api/driver-filter
+                                You can write a name of a driver into this file
+                                to limit the debug output to requests from that
+                                particular driver. Write an empty string to
+                                that file to disable the filter and see
+                                all errors again.
+
 If you have this code compiled into your kernel it will be enabled by default.
 If you want to boot without the bookkeeping anyway you can provide
 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
 Notice that you can not enable it again at runtime. You have to reboot to do
 so.
 
+If you want to see debug messages only for a special device driver you can
+specify the dma_debug_driver=<drivername> parameter. This will enable the
+driver filter at boot time. The debug code will only print errors for that
+driver afterwards. This filter can be disabled or changed later using debugfs.
+
 When the code disables itself at runtime this is most likely because it ran
 out of dma_debug_entries. These entries are preallocated at boot. The number
 of preallocated entries is defined per architecture. If it is too low for you
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index b1eb661e6302..9632444f6c62 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -13,7 +13,8 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
             gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
             genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
             mac80211.xml debugobjects.xml sh.xml regulator.xml \
-            alsa-driver-api.xml writing-an-alsa-driver.xml
+            alsa-driver-api.xml writing-an-alsa-driver.xml \
+            tracepoint.xml
 
 ###
 # The build process is as follows (targets):
diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl
new file mode 100644
index 000000000000..b0756d0fd579
--- /dev/null
+++ b/Documentation/DocBook/tracepoint.tmpl
@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+        "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+
+<book id="Tracepoints">
+ <bookinfo>
+  <title>The Linux Kernel Tracepoint API</title>
+
+  <authorgroup>
+   <author>
+    <firstname>Jason</firstname>
+    <surname>Baron</surname>
+    <affiliation>
+     <address>
+      <email>jbaron@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+
+  <legalnotice>
+   <para>
+     This documentation is free software; you can redistribute
+     it and/or modify it under the terms of the GNU General Public
+     License as published by the Free Software Foundation; either
+     version 2 of the License, or (at your option) any later
+     version.
+   </para>
+
+   <para>
+     This program is distributed in the hope that it will be
+     useful, but WITHOUT ANY WARRANTY; without even the implied
+     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+     See the GNU General Public License for more details.
+   </para>
+
+   <para>
+     You should have received a copy of the GNU General Public
+     License along with this program; if not, write to the Free
+     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+     MA 02111-1307 USA
+   </para>
+
+   <para>
+     For more details see the file COPYING in the source
+     distribution of Linux.
+   </para>
+  </legalnotice>
+ </bookinfo>
+
+ <toc></toc>
+  <chapter id="intro">
+   <title>Introduction</title>
+   <para>
+     Tracepoints are static probe points that are located in strategic points
+     throughout the kernel. 'Probes' register/unregister with tracepoints
+     via a callback mechanism. The 'probes' are strictly typed functions that
+     are passed a unique set of parameters defined by each tracepoint.
+   </para>
+
+   <para>
+     From this simple callback mechanism, 'probes' can be used to profile, debug,
+     and understand kernel behavior. There are a number of tools that provide a
+     framework for using 'probes'. These tools include Systemtap, ftrace, and
+     LTTng.
+   </para>
+
+   <para>
+     Tracepoints are defined in a number of header files via various macros. Thus,
+     the purpose of this document is to provide a clear accounting of the available
+     tracepoints. The intention is to understand not only what tracepoints are
+     available but also to understand where future tracepoints might be added.
+   </para>
+
+   <para>
+     The API presented has functions of the form:
+     <function>trace_tracepointname(function parameters)</function>. These are the
+     tracepoints callbacks that are found throughout the code. Registering and
+     unregistering probes with these callback sites is covered in the
+     <filename>Documentation/trace/*</filename> directory.
+   </para>
+  </chapter>
+
+  <chapter id="irq">
+   <title>IRQ</title>
+!Iinclude/trace/events/irq.h
+  </chapter>
+
+</book>
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 068848240a8b..02cced183b2d 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -192,23 +192,24 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy).
 The output of "cat rcu/rcudata" looks as follows:
 
 rcu:
-  0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10
-  1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10
-  2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10
-  3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10
-  4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10
-  5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10
-  6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10
-  7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10
+rcu:
+  0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10
+  1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10
+  2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10
+  3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10
+  4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10
+  5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10
+  6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10
+  7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10
 rcu_bh:
-  0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10
-  1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10
-  2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10
-  3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10
-  4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
-  6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
+  0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10
+  1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10
+  2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10
+  4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
 
 The first section lists the rcu_data structures for rcu, the second for
 rcu_bh.  Each section has one line per CPU, or eight for this 8-CPU system.
@@ -253,12 +254,6 @@ o	"pqc" indicates which grace period the last-observed quiescent
 o       "qp" indicates that RCU still expects a quiescent state from
         this CPU.
 
-o       "rpfq" is the number of rcu_pending() calls on this CPU required
-        to induce this CPU to invoke force_quiescent_state().
-
-o       "rp" is low-order four hex digits of the count of how many times
-        rcu_pending() has been invoked on this CPU.
-
 o       "dt" is the current value of the dyntick counter that is incremented
         when entering or leaving dynticks idle state, either by the
         scheduler or by irq.  The number after the "/" is the interrupt
@@ -305,6 +300,9 @@ o	"b" is the batch limit for this CPU.  If more than this number
         of RCU callbacks is ready to invoke, then the remainder will
         be deferred.
 
+There is also an rcu/rcudata.csv file with the same information in
+comma-separated-variable spreadsheet format.
+
 
 The output of "cat rcu/rcugp" looks as follows:
 
@@ -411,3 +409,63 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
                 For example, the first entry at the lowest level shows
                 "^0", indicating that it corresponds to bit zero in
                 the first entry at the middle level.
+
+
+The output of "cat rcu/rcu_pending" looks as follows:
+
+rcu:
+  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+rcu_bh:
+  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+
+As always, this is once again split into "rcu" and "rcu_bh" portions.
+The fields are as follows:
+
+o       "np" is the number of times that __rcu_pending() has been invoked
+        for the corresponding flavor of RCU.
+
+o       "qsp" is the number of times that the RCU was waiting for a
+        quiescent state from this CPU.
+
+o       "cbr" is the number of times that this CPU had RCU callbacks
+        that had passed through a grace period, and were thus ready
+        to be invoked.
+
+o       "cng" is the number of times that this CPU needed another
+        grace period while RCU was idle.
+
+o       "gpc" is the number of times that an old grace period had
+        completed, but this CPU was not yet aware of it.
+
+o       "gps" is the number of times that a new grace period had started,
+        but this CPU was not yet aware of it.
+
+o       "nf" is the number of times that this CPU suspected that the
+        current grace period had run for too long, and thus needed to
+        be forced.
+
+        Please note that "forcing" consists of sending resched IPIs
+        to holdout CPUs.  If that CPU really still is in an old RCU
+        read-side critical section, then we really do have to wait for it.
+        The assumption behing "forcing" is that the CPU is not still in
+        an old RCU read-side critical section, but has not yet responded
+        for some other reason.
+
+o       "nn" is the number of times that this CPU needed nothing.  Alert
+        readers will note that the rcu "nn" number for a given CPU very
+        closely matches the rcu_bh "np" number for that same CPU.  This
+        is due to short-circuit evaluation in rcu_pending().
diff --git a/Documentation/Smack.txt b/Documentation/Smack.txt
index 629c92e99783..34614b4c708e 100644
--- a/Documentation/Smack.txt
+++ b/Documentation/Smack.txt
@@ -184,8 +184,9 @@ length. Single character labels using special characters, that being anything
 other than a letter or digit, are reserved for use by the Smack development
 team. Smack labels are unstructured, case sensitive, and the only operation
 ever performed on them is comparison for equality. Smack labels cannot
-contain unprintable characters or the "/" (slash) character. Smack labels
-cannot begin with a '-', which is reserved for special options.
+contain unprintable characters, the "/" (slash), the "\" (backslash), the "'"
+(quote) and '"' (double-quote) characters.
+Smack labels cannot begin with a '-', which is reserved for special options.
 
 There are some predefined labels:
 
@@ -523,3 +524,18 @@ Smack supports some mount options:
 
 These mount options apply to all file system types.
 
+Smack auditing
+
+If you want Smack auditing of security events, you need to set CONFIG_AUDIT
+in your kernel configuration.
+By default, all denied events will be audited. You can change this behavior by
+writing a single character to the /smack/logging file :
+0 : no logging
+1 : log denied (default)
+2 : log accepted
+3 : log denied & accepted
+
+Events are logged as 'key=value' pairs, for each event you at least will get
+the subjet, the object, the rights requested, the action, the kernel function
+that triggered the event, plus other pairs depending on the type of event
+audited.
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 6fab97ea7e6b..8d2158a1c6aa 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/DMA-mapping.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 
diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
index 4dae9a3840bf..0494f78d87e4 100644
--- a/Documentation/filesystems/gfs2-glocks.txt
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -60,7 +60,7 @@ 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_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
diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt
index 593004b6bbab..5e3ab8f3beff 100644
--- a/Documentation/filesystems/gfs2.txt
+++ b/Documentation/filesystems/gfs2.txt
@@ -11,18 +11,15 @@ their I/O so file system consistency is maintained.  One of the nifty
 features of GFS is perfect consistency -- changes made to the file system
 on one machine show up immediately on all other machines in the cluster.
 
-GFS uses interchangable inter-node locking mechanisms.  Different lock
-modules can plug into GFS and each file system selects the appropriate
-lock module at mount time.  Lock modules include:
+GFS uses interchangable inter-node locking mechanisms, the currently
+supported mechanisms are:
 
   lock_nolock -- allows gfs to be used as a local file system
 
   lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking
   The dlm is found at linux/fs/dlm/
 
-In addition to interfacing with an external locking manager, a gfs lock
-module is responsible for interacting with external cluster management
-systems.  Lock_dlm depends on user space cluster management systems found
+Lock_dlm depends on user space cluster management systems found
 at the URL above.
 
 To use gfs as a local file system, no external clustering systems are
@@ -31,13 +28,19 @@ needed, simply:
   $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device
   $ mount -t gfs2 /dev/block_device /dir
 
-GFS2 is not on-disk compatible with previous versions of GFS.
+If you are using Fedora, you need to install the gfs2-utils package
+and, for lock_dlm, you will also need to install the cman package
+and write a cluster.conf as per the documentation.
+
+GFS2 is not on-disk compatible with previous versions of GFS, but it
+is pretty close.
 
 The following man pages can be found at the URL above:
-  gfs2_fsck     to repair a filesystem
+  fsck.gfs2     to repair a filesystem
   gfs2_grow     to expand a filesystem online
   gfs2_jadd     to add journals to a filesystem online
   gfs2_tool     to manipulate, examine and tune a filesystem
   gfs2_quota    to examine and change quota values in a filesystem
+  gfs2_convert  to convert a gfs filesystem to gfs2 in-place
   mount.gfs2    to help mount(8) mount a filesystem
   mkfs.gfs2     to make a filesystem
diff --git a/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt
new file mode 100644
index 000000000000..9dc1ff4fd536
--- /dev/null
+++ b/Documentation/futex-requeue-pi.txt
@@ -0,0 +1,131 @@
+Futex Requeue PI
+----------------
+
+Requeueing of tasks from a non-PI futex to a PI futex requires
+special handling in order to ensure the underlying rt_mutex is never
+left without an owner if it has waiters; doing so would break the PI
+boosting logic [see rt-mutex-desgin.txt] For the purposes of
+brevity, this action will be referred to as "requeue_pi" throughout
+this document.  Priority inheritance is abbreviated throughout as
+"PI".
+
+Motivation
+----------
+
+Without requeue_pi, the glibc implementation of
+pthread_cond_broadcast() must resort to waking all the tasks waiting
+on a pthread_condvar and letting them try to sort out which task
+gets to run first in classic thundering-herd formation.  An ideal
+implementation would wake the highest-priority waiter, and leave the
+rest to the natural wakeup inherent in unlocking the mutex
+associated with the condvar.
+
+Consider the simplified glibc calls:
+
+/* caller must lock mutex */
+pthread_cond_wait(cond, mutex)
+{
+        lock(cond->__data.__lock);
+        unlock(mutex);
+        do {
+           unlock(cond->__data.__lock);
+           futex_wait(cond->__data.__futex);
+           lock(cond->__data.__lock);
+        } while(...)
+        unlock(cond->__data.__lock);
+        lock(mutex);
+}
+
+pthread_cond_broadcast(cond)
+{
+        lock(cond->__data.__lock);
+        unlock(cond->__data.__lock);
+        futex_requeue(cond->data.__futex, cond->mutex);
+}
+
+Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
+has waiters. Note that pthread_cond_wait() attempts to lock the
+mutex only after it has returned to user space.  This will leave the
+underlying rt_mutex with waiters, and no owner, breaking the
+previously mentioned PI-boosting algorithms.
+
+In order to support PI-aware pthread_condvar's, the kernel needs to
+be able to requeue tasks to PI futexes.  This support implies that
+upon a successful futex_wait system call, the caller would return to
+user space already holding the PI futex.  The glibc implementation
+would be modified as follows:
+
+
+/* caller must lock mutex */
+pthread_cond_wait_pi(cond, mutex)
+{
+        lock(cond->__data.__lock);
+        unlock(mutex);
+        do {
+           unlock(cond->__data.__lock);
+           futex_wait_requeue_pi(cond->__data.__futex);
+           lock(cond->__data.__lock);
+        } while(...)
+        unlock(cond->__data.__lock);
+        /* the kernel acquired the the mutex for us */
+}
+
+pthread_cond_broadcast_pi(cond)
+{
+        lock(cond->__data.__lock);
+        unlock(cond->__data.__lock);
+        futex_requeue_pi(cond->data.__futex, cond->mutex);
+}
+
+The actual glibc implementation will likely test for PI and make the
+necessary changes inside the existing calls rather than creating new
+calls for the PI cases.  Similar changes are needed for
+pthread_cond_timedwait() and pthread_cond_signal().
+
+Implementation
+--------------
+
+In order to ensure the rt_mutex has an owner if it has waiters, it
+is necessary for both the requeue code, as well as the waiting code,
+to be able to acquire the rt_mutex before returning to user space.
+The requeue code cannot simply wake the waiter and leave it to
+acquire the rt_mutex as it would open a race window between the
+requeue call returning to user space and the waiter waking and
+starting to run.  This is especially true in the uncontended case.
+
+The solution involves two new rt_mutex helper routines,
+rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
+allow the requeue code to acquire an uncontended rt_mutex on behalf
+of the waiter and to enqueue the waiter on a contended rt_mutex.
+Two new system calls provide the kernel<->user interface to
+requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI.
+
+FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
+and pthread_cond_timedwait()) to block on the initial futex and wait
+to be requeued to a PI-aware futex.  The implementation is the
+result of a high-speed collision between futex_wait() and
+futex_lock_pi(), with some extra logic to check for the additional
+wake-up scenarios.
+
+FUTEX_REQUEUE_CMP_PI is called by the waker
+(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
+possibly wake the waiting tasks. Internally, this system call is
+still handled by futex_requeue (by passing requeue_pi=1).  Before
+requeueing, futex_requeue() attempts to acquire the requeue target
+PI futex on behalf of the top waiter.  If it can, this waiter is
+woken.  futex_requeue() then proceeds to requeue the remaining
+nr_wake+nr_requeue tasks to the PI futex, calling
+rt_mutex_start_proxy_lock() prior to each requeue to prepare the
+task as a waiter on the underlying rt_mutex.  It is possible that
+the lock can be acquired at this stage as well, if so, the next
+waiter is woken to finish the acquisition of the lock.
+
+FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
+their sum is all that really matters.  futex_requeue() will wake or
+requeue up to nr_wake + nr_requeue tasks.  It will wake only as many
+tasks as it can acquire the lock for, which in the majority of cases
+should be 0 as good programming practice dictates that the caller of
+either pthread_cond_broadcast() or pthread_cond_signal() acquire the
+mutex prior to making the call. FUTEX_REQUEUE_PI requires that
+nr_wake=1.  nr_requeue should be INT_MAX for broadcast and 0 for
+signal.
diff --git a/Documentation/ide/ide.txt b/Documentation/ide/ide.txt
index 0c78f4b1d9d9..e77bebfa7b0d 100644
--- a/Documentation/ide/ide.txt
+++ b/Documentation/ide/ide.txt
@@ -216,6 +216,8 @@ Other kernel parameters for ide_core are:
 
 * "noflush=[interface_number.device_number]" to disable flush requests
 
+* "nohpa=[interface_number.device_number]" to disable Host Protected Area
+
 * "noprobe=[interface_number.device_number]" to skip probing
 
 * "nowerr=[interface_number.device_number]" to ignore the WRERR_STAT bit
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index fd5cac013037..0bf8a882ee9e 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -56,7 +56,6 @@ parameter is applicable:
         ISAPNP  ISA PnP code is enabled.
         ISDN    Appropriate ISDN support is enabled.
         JOY     Appropriate joystick support is enabled.
-        KMEMTRACE kmemtrace is enabled.
         LIBATA  Libata driver is enabled
         LP      Printer support is enabled.
         LOOP    Loopback device support is enabled.
@@ -329,11 +328,6 @@ and is between 256 and 4096 characters. It is defined in the file
                                     flushed before they will be reused, which
                                     is a lot of faster
 
-        amd_iommu_size= [HW,X86-64]
-                        Define the size of the aperture for the AMD IOMMU
-                        driver. Possible values are:
-                        '32M', '64M' (default), '128M', '256M', '512M', '1G'
-
         amijoy.map=     [HW,JOY] Amiga joystick support
                         Map of devices attached to JOY0DAT and JOY1DAT
                         Format: <a>,<b>
@@ -646,6 +640,13 @@ and is between 256 and 4096 characters. It is defined in the file
                         DMA-API debugging code disables itself because the
                         architectural default is too low.
 
+        dma_debug_driver=<driver_name>
+                        With this option the DMA-API debugging driver
+                        filter feature can be enabled at boot time. Just
+                        pass the driver to filter for as the parameter.
+                        The filter can be disabled or changed to another
+                        driver later using sysfs.
+
         dscc4.setup=    [NET]
 
         dtc3181e=       [HW,SCSI]
@@ -752,12 +753,25 @@ and is between 256 and 4096 characters. It is defined in the file
                         ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
         ftrace=[tracer]
-                        [ftrace] will set and start the specified tracer
+                        [FTRACE] will set and start the specified tracer
                         as early as possible in order to facilitate early
                         boot debugging.
 
         ftrace_dump_on_oops
-                        [ftrace] will dump the trace buffers on oops.
+                        [FTRACE] will dump the trace buffers on oops.
+
+        ftrace_filter=[function-list]
+                        [FTRACE] Limit the functions traced by the function
+                        tracer at boot up. function-list is a comma separated
+                        list of functions. This list can be changed at run
+                        time by the set_ftrace_filter file in the debugfs
+                        tracing directory. 
+
+        ftrace_notrace=[function-list]
+                        [FTRACE] Do not trace the functions specified in
+                        function-list. This list can be changed at run time
+                        by the set_ftrace_notrace file in the debugfs
+                        tracing directory.
 
         gamecon.map[2|3]=
                         [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
@@ -873,11 +887,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
         ide-core.nodma= [HW] (E)IDE subsystem
                         Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc
-                        .vlb_clock .pci_clock .noflush .noprobe .nowerr .cdrom
-                        .chs .ignore_cable are additional options
-                        See Documentation/ide/ide.txt.
-
-        idebus=         [HW] (E)IDE subsystem - VLB/PCI bus speed
+                        .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr
+                        .cdrom .chs .ignore_cable are additional options
                         See Documentation/ide/ide.txt.
 
         ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
@@ -914,6 +925,12 @@ and is between 256 and 4096 characters. It is defined in the file
                         Formt: { "sha1" | "md5" }
                         default: "sha1"
 
+        ima_tcb         [IMA]
+                        Load a policy which meets the needs of the Trusted
+                        Computing Base.  This means IMA will measure all
+                        programs exec'd, files mmap'd for exec, and all files
+                        opened for read by uid=0.
+
         in2000=         [HW,SCSI]
                         See header of drivers/scsi/in2000.c.
 
@@ -1054,15 +1071,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         use the HighMem zone if it exists, and the Normal
                         zone if it does not.
 
-        kmemtrace.enable=       [KNL,KMEMTRACE] Format: { yes | no }
-                                Controls whether kmemtrace is enabled
-                                at boot-time.
-
-        kmemtrace.subbufs=n     [KNL,KMEMTRACE] Overrides the number of
-                        subbufs kmemtrace's relay channel has. Set this
-                        higher than default (KMEMTRACE_N_SUBBUFS in code) if
-                        you experience buffer overruns.
-
         kgdboc=         [HW] kgdb over consoles.
                         Requires a tty driver that supports console polling.
                         (only serial suported for now)
@@ -1072,6 +1080,10 @@ and is between 256 and 4096 characters. It is defined in the file
                         Configure the RouterBoard 532 series on-chip
                         Ethernet adapter MAC address.
 
+        kmemleak=       [KNL] Boot-time kmemleak enable/disable
+                        Valid arguments: on, off
+                        Default: on
+
         kstack=N        [X86] Print N words from the kernel stack
                         in oops dumps.
 
@@ -1575,6 +1587,9 @@ and is between 256 and 4096 characters. It is defined in the file
         noinitrd        [RAM] Tells the kernel not to load any configured
                         initial RAM disk.
 
+        nointremap      [X86-64, Intel-IOMMU] Do not enable interrupt
+                        remapping.
+
         nointroute      [IA-64]
 
         nojitter        [IA64] Disables jitter checking for ITC timers.
@@ -1660,6 +1675,14 @@ and is between 256 and 4096 characters. It is defined in the file
         oprofile.timer= [HW]
                         Use timer interrupt instead of performance counters
 
+        oprofile.cpu_type=      Force an oprofile cpu type
+                        This might be useful if you have an older oprofile
+                        userland or if you want common events.
+                        Format: { archperfmon }
+                        archperfmon: [X86] Force use of architectural
+                                perfmon on Intel CPUs instead of the
+                                CPU specific event set.
+
         osst=           [HW,SCSI] SCSI Tape Driver
                         Format: <buffer_size>,<write_threshold>
                         See also Documentation/scsi/st.txt.
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
new file mode 100644
index 000000000000..0112da3b9ab8
--- /dev/null
+++ b/Documentation/kmemleak.txt
@@ -0,0 +1,142 @@
+Kernel Memory Leak Detector
+===========================
+
+Introduction
+------------
+
+Kmemleak provides a way of detecting possible kernel memory leaks in a
+way similar to a tracing garbage collector
+(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
+with the difference that the orphan objects are not freed but only
+reported via /sys/kernel/debug/kmemleak. A similar method is used by the
+Valgrind tool (memcheck --leak-check) to detect the memory leaks in
+user-space applications.
+
+Usage
+-----
+
+CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel
+thread scans the memory every 10 minutes (by default) and prints any new
+unreferenced objects found. To trigger an intermediate scan and display
+all the possible memory leaks:
+
+  # mount -t debugfs nodev /sys/kernel/debug/
+  # cat /sys/kernel/debug/kmemleak
+
+Note that the orphan objects are listed in the order they were allocated
+and one object at the beginning of the list may cause other subsequent
+objects to be reported as orphan.
+
+Memory scanning parameters can be modified at run-time by writing to the
+/sys/kernel/debug/kmemleak file. The following parameters are supported:
+
+  off           - disable kmemleak (irreversible)
+  stack=on      - enable the task stacks scanning
+  stack=off     - disable the tasks stacks scanning
+  scan=on       - start the automatic memory scanning thread
+  scan=off      - stop the automatic memory scanning thread
+  scan=<secs>   - set the automatic memory scanning period in seconds (0
+                  to disable it)
+
+Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on
+the kernel command line.
+
+Basic Algorithm
+---------------
+
+The memory allocations via kmalloc, vmalloc, kmem_cache_alloc and
+friends are traced and the pointers, together with additional
+information like size and stack trace, are stored in a prio search tree.
+The corresponding freeing function calls are tracked and the pointers
+removed from the kmemleak data structures.
+
+An allocated block of memory is considered orphan if no pointer to its
+start address or to any location inside the block can be found by
+scanning the memory (including saved registers). This means that there
+might be no way for the kernel to pass the address of the allocated
+block to a freeing function and therefore the block is considered a
+memory leak.
+
+The scanning algorithm steps:
+
+  1. mark all objects as white (remaining white objects will later be
+     considered orphan)
+  2. scan the memory starting with the data section and stacks, checking
+     the values against the addresses stored in the prio search tree. If
+     a pointer to a white object is found, the object is added to the
+     gray list
+  3. scan the gray objects for matching addresses (some white objects
+     can become gray and added at the end of the gray list) until the
+     gray set is finished
+  4. the remaining white objects are considered orphan and reported via
+     /sys/kernel/debug/kmemleak
+
+Some allocated memory blocks have pointers stored in the kernel's
+internal data structures and they cannot be detected as orphans. To
+avoid this, kmemleak can also store the number of values pointing to an
+address inside the block address range that need to be found so that the
+block is not considered a leak. One example is __vmalloc().
+
+Kmemleak API
+------------
+
+See the include/linux/kmemleak.h header for the functions prototype.
+
+kmemleak_init            - initialize kmemleak
+kmemleak_alloc           - notify of a memory block allocation
+kmemleak_free            - notify of a memory block freeing
+kmemleak_not_leak        - mark an object as not a leak
+kmemleak_ignore          - do not scan or report an object as leak
+kmemleak_scan_area       - add scan areas inside a memory block
+kmemleak_no_scan         - do not scan a memory block
+kmemleak_erase           - erase an old value in a pointer variable
+kmemleak_alloc_recursive - as kmemleak_alloc but checks the recursiveness
+kmemleak_free_recursive  - as kmemleak_free but checks the recursiveness
+
+Dealing with false positives/negatives
+--------------------------------------
+
+The false negatives are real memory leaks (orphan objects) but not
+reported by kmemleak because values found during the memory scanning
+point to such objects. To reduce the number of false negatives, kmemleak
+provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and
+kmemleak_erase functions (see above). The task stacks also increase the
+amount of false negatives and their scanning is not enabled by default.
+
+The false positives are objects wrongly reported as being memory leaks
+(orphan). For objects known not to be leaks, kmemleak provides the
+kmemleak_not_leak function. The kmemleak_ignore could also be used if
+the memory block is known not to contain other pointers and it will no
+longer be scanned.
+
+Some of the reported leaks are only transient, especially on SMP
+systems, because of pointers temporarily stored in CPU registers or
+stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing
+the minimum age of an object to be reported as a memory leak.
+
+Limitations and Drawbacks
+-------------------------
+
+The main drawback is the reduced performance of memory allocation and
+freeing. To avoid other penalties, the memory scanning is only performed
+when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is
+intended for debugging purposes where the performance might not be the
+most important requirement.
+
+To keep the algorithm simple, kmemleak scans for values pointing to any
+address inside a block's address range. This may lead to an increased
+number of false negatives. However, it is likely that a real memory leak
+will eventually become visible.
+
+Another source of false negatives is the data stored in non-pointer
+values. In a future version, kmemleak could only scan the pointer
+members in the allocated structures. This feature would solve many of
+the false negative cases described above.
+
+The tool can report false positives. These are cases where an allocated
+block doesn't need to be freed (some cases in the init_call functions),
+the pointer is calculated by other methods than the usual container_of
+macro or the pointer is stored in a location not scanned by kmemleak.
+
+Page allocations and ioremap are not tracked. Only the ARM and x86
+architectures are currently supported.
diff --git a/Documentation/lguest/Makefile b/Documentation/lguest/Makefile
index 1f4f9e888bd1..28c8cdfcafd8 100644
--- a/Documentation/lguest/Makefile
+++ b/Documentation/lguest/Makefile
@@ -1,6 +1,5 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE
-LDLIBS:=-lz
+CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE
 
 all: lguest
 
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index d36fcc0f2715..9ebcd6ef361b 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -16,6 +16,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
+#include <sys/eventfd.h>
 #include <fcntl.h>
 #include <stdbool.h>
 #include <errno.h>
@@ -59,7 +60,6 @@ typedef uint8_t u8;
 /*:*/
 
 #define PAGE_PRESENT 0x7        /* Present, RW, Execute */
-#define NET_PEERNUM 1
 #define BRIDGE_PFX "bridge:"
 #ifndef SIOCBRADDIF
 #define SIOCBRADDIF     0x89a2          /* add interface to bridge      */
@@ -76,19 +76,12 @@ static bool verbose;
         do { if (verbose) printf(args); } while(0)
 /*:*/
 
-/* File descriptors for the Waker. */
-struct {
-        int pipe[2];
-        int lguest_fd;
-} waker_fds;
-
 /* The pointer to the start of guest memory. */
 static void *guest_base;
 /* The maximum guest physical address allowed, and maximum possible. */
 static unsigned long guest_limit, guest_max;
-/* The pipe for signal hander to write to. */
-static int timeoutpipe[2];
-static unsigned int timeout_usec = 500;
+/* The /dev/lguest file descriptor. */
+static int lguest_fd;
 
 /* a per-cpu variable indicating whose vcpu is currently running */
 static unsigned int __thread cpu_id;
@@ -96,11 +89,6 @@ static unsigned int __thread cpu_id;
 /* This is our list of devices. */
 struct device_list
 {
-        /* Summary information about the devices in our list: ready to pass to
-         * select() to ask which need servicing.*/
-        fd_set infds;
-        int max_infd;
-
         /* Counter to assign interrupt numbers. */
         unsigned int next_irq;
 
@@ -126,22 +114,21 @@ struct device
         /* The linked-list pointer. */
         struct device *next;
 
-        /* The this device's descriptor, as mapped into the Guest. */
+        /* The device's descriptor, as mapped into the Guest. */
         struct lguest_device_desc *desc;
 
+        /* We can't trust desc values once Guest has booted: we use these. */
+        unsigned int feature_len;
+        unsigned int num_vq;
+
         /* The name of this device, for --verbose. */
         const char *name;
 
-        /* If handle_input is set, it wants to be called when this file
-         * descriptor is ready. */
-        int fd;
-        bool (*handle_input)(int fd, struct device *me);
-
         /* Any queues attached to this device */
         struct virtqueue *vq;
 
-        /* Handle status being finalized (ie. feature bits stable). */
-        void (*ready)(struct device *me);
+        /* Is it operational */
+        bool running;
 
         /* Device-specific data. */
         void *priv;
@@ -164,22 +151,28 @@ struct virtqueue
         /* Last available index we saw. */
         u16 last_avail_idx;
 
-        /* The routine to call when the Guest pings us, or timeout. */
-        void (*handle_output)(int fd, struct virtqueue *me, bool timeout);
+        /* How many are used since we sent last irq? */
+        unsigned int pending_used;
 
-        /* Outstanding buffers */
-        unsigned int inflight;
+        /* Eventfd where Guest notifications arrive. */
+        int eventfd;
 
-        /* Is this blocked awaiting a timer? */
-        bool blocked;
+        /* Function for the thread which is servicing this virtqueue. */
+        void (*service)(struct virtqueue *vq);
+        pid_t thread;
 };
 
 /* Remember the arguments to the program so we can "reboot" */
 static char **main_args;
 
-/* Since guest is UP and we don't run at the same time, we don't need barriers.
- * But I include them in the code in case others copy it. */
-#define wmb()
+/* The original tty settings to restore on exit. */
+static struct termios orig_term;
+
+/* We have to be careful with barriers: our devices are all run in separate
+ * threads and so we need to make sure that changes visible to the Guest happen
+ * in precise order. */
+#define wmb() __asm__ __volatile__("" : : : "memory")
+#define mb() __asm__ __volatile__("" : : : "memory")
 
 /* Convert an iovec element to the given type.
  *
@@ -245,7 +238,7 @@ static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len)
 static u8 *get_feature_bits(struct device *dev)
 {
         return (u8 *)(dev->desc + 1)
-                + dev->desc->num_vq * sizeof(struct lguest_vqconfig);
+                + dev->num_vq * sizeof(struct lguest_vqconfig);
 }
 
 /*L:100 The Launcher code itself takes us out into userspace, that scary place
@@ -505,99 +498,19 @@ static void concat(char *dst, char *args[])
  * saw the arguments it expects when we looked at initialize() in lguest_user.c:
  * the base of Guest "physical" memory, the top physical page to allow and the
  * entry point for the Guest. */
-static int tell_kernel(unsigned long start)
+static void tell_kernel(unsigned long start)
 {
         unsigned long args[] = { LHREQ_INITIALIZE,
                                  (unsigned long)guest_base,
                                  guest_limit / getpagesize(), start };
-        int fd;
-
         verbose("Guest: %p - %p (%#lx)\n",
                 guest_base, guest_base + guest_limit, guest_limit);
-        fd = open_or_die("/dev/lguest", O_RDWR);
-        if (write(fd, args, sizeof(args)) < 0)
+        lguest_fd = open_or_die("/dev/lguest", O_RDWR);
+        if (write(lguest_fd, args, sizeof(args)) < 0)
                 err(1, "Writing to /dev/lguest");
-
-        /* We return the /dev/lguest file descriptor to control this Guest */
-        return fd;
 }
 /*:*/
 
-static void add_device_fd(int fd)
-{
-        FD_SET(fd, &devices.infds);
-        if (fd > devices.max_infd)
-                devices.max_infd = fd;
-}
-
-/*L:200
- * The Waker.
- *
- * With console, block and network devices, we can have lots of input which we
- * need to process.  We could try to tell the kernel what file descriptors to
- * watch, but handing a file descriptor mask through to the kernel is fairly
- * icky.
- *
- * Instead, we clone off a thread which watches the file descriptors and writes
- * the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host
- * stop running the Guest.  This causes the Launcher to return from the
- * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
- * the LHREQ_BREAK and wake us up again.
- *
- * This, of course, is merely a different *kind* of icky.
- *
- * Given my well-known antipathy to threads, I'd prefer to use processes.  But
- * it's easier to share Guest memory with threads, and trivial to share the
- * devices.infds as the Launcher changes it.
- */
-static int waker(void *unused)
-{
-        /* Close the write end of the pipe: only the Launcher has it open. */
-        close(waker_fds.pipe[1]);
-
-        for (;;) {
-                fd_set rfds = devices.infds;
-                unsigned long args[] = { LHREQ_BREAK, 1 };
-                unsigned int maxfd = devices.max_infd;
-
-                /* We also listen to the pipe from the Launcher. */
-                FD_SET(waker_fds.pipe[0], &rfds);
-                if (waker_fds.pipe[0] > maxfd)
-                        maxfd = waker_fds.pipe[0];
-
-                /* Wait until input is ready from one of the devices. */
-                select(maxfd+1, &rfds, NULL, NULL, NULL);
-
-                /* Message from Launcher? */
-                if (FD_ISSET(waker_fds.pipe[0], &rfds)) {
-                        char c;
-                        /* If this fails, then assume Launcher has exited.
-                         * Don't do anything on exit: we're just a thread! */
-                        if (read(waker_fds.pipe[0], &c, 1) != 1)
-                                _exit(0);
-                        continue;
-                }
-
-                /* Send LHREQ_BREAK command to snap the Launcher out of it. */
-                pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id);
-        }
-        return 0;
-}
-
-/* This routine just sets up a pipe to the Waker process. */
-static void setup_waker(int lguest_fd)
-{
-        /* This pipe is closed when Launcher dies, telling Waker. */
-        if (pipe(waker_fds.pipe) != 0)
-                err(1, "Creating pipe for Waker");
-
-        /* Waker also needs to know the lguest fd */
-        waker_fds.lguest_fd = lguest_fd;
-
-        if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1)
-                err(1, "Creating Waker");
-}
-
 /*
  * Device Handling.
  *
@@ -623,49 +536,90 @@ static void *_check_pointer(unsigned long addr, unsigned int size,
 /* Each buffer in the virtqueues is actually a chain of descriptors.  This
  * function returns the next descriptor in the chain, or vq->vring.num if we're
  * at the end. */
-static unsigned next_desc(struct virtqueue *vq, unsigned int i)
+static unsigned next_desc(struct vring_desc *desc,
+                          unsigned int i, unsigned int max)
 {
         unsigned int next;
 
         /* If this descriptor says it doesn't chain, we're done. */
-        if (!(vq->vring.desc[i].flags & VRING_DESC_F_NEXT))
-                return vq->vring.num;
+        if (!(desc[i].flags & VRING_DESC_F_NEXT))
+                return max;
 
         /* Check they're not leading us off end of descriptors. */
-        next = vq->vring.desc[i].next;
+        next = desc[i].next;
         /* Make sure compiler knows to grab that: we don't want it changing! */
         wmb();
 
-        if (next >= vq->vring.num)
+        if (next >= max)
                 errx(1, "Desc next is %u", next);
 
         return next;
 }
 
+/* This actually sends the interrupt for this virtqueue */
+static void trigger_irq(struct virtqueue *vq)
+{
+        unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
+
+        /* Don't inform them if nothing used. */
+        if (!vq->pending_used)
+                return;
+        vq->pending_used = 0;
+
+        /* If they don't want an interrupt, don't send one, unless empty. */
+        if ((vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
+            && lg_last_avail(vq) != vq->vring.avail->idx)
+                return;
+
+        /* Send the Guest an interrupt tell them we used something up. */
+        if (write(lguest_fd, buf, sizeof(buf)) != 0)
+                err(1, "Triggering irq %i", vq->config.irq);
+}
+
 /* This looks in the virtqueue and for the first available buffer, and converts
  * it to an iovec for convenient access.  Since descriptors consist of some
  * number of output then some number of input descriptors, it's actually two
  * iovecs, but we pack them into one and note how many of each there were.
  *
- * This function returns the descriptor number found, or vq->vring.num (which
- * is never a valid descriptor number) if none was found. */
-static unsigned get_vq_desc(struct virtqueue *vq,
-                            struct iovec iov[],
-                            unsigned int *out_num, unsigned int *in_num)
+ * This function returns the descriptor number found. */
+static unsigned wait_for_vq_desc(struct virtqueue *vq,
+                                 struct iovec iov[],
+                                 unsigned int *out_num, unsigned int *in_num)
 {
-        unsigned int i, head;
-        u16 last_avail;
+        unsigned int i, head, max;
+        struct vring_desc *desc;
+        u16 last_avail = lg_last_avail(vq);
+
+        while (last_avail == vq->vring.avail->idx) {
+                u64 event;
+
+                /* OK, tell Guest about progress up to now. */
+                trigger_irq(vq);
+
+                /* OK, now we need to know about added descriptors. */
+                vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+
+                /* They could have slipped one in as we were doing that: make
+                 * sure it's written, then check again. */
+                mb();
+                if (last_avail != vq->vring.avail->idx) {
+                        vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+                        break;
+                }
+
+                /* Nothing new?  Wait for eventfd to tell us they refilled. */
+                if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event))
+                        errx(1, "Event read failed?");
+
+                /* We don't need to be notified again. */
+                vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+        }
 
         /* Check it isn't doing very strange things with descriptor numbers. */
-        last_avail = lg_last_avail(vq);
         if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
                 errx(1, "Guest moved used index from %u to %u",
                      last_avail, vq->vring.avail->idx);
 
-        /* If there's nothing new since last we looked, return invalid. */
-        if (vq->vring.avail->idx == last_avail)
-                return vq->vring.num;
-
         /* Grab the next descriptor number they're advertising, and increment
          * the index we've seen. */
         head = vq->vring.avail->ring[last_avail % vq->vring.num];
@@ -678,15 +632,28 @@ static unsigned get_vq_desc(struct virtqueue *vq,
         /* When we start there are none of either input nor output. */
         *out_num = *in_num = 0;
 
+        max = vq->vring.num;
+        desc = vq->vring.desc;
         i = head;
+
+        /* If this is an indirect entry, then this buffer contains a descriptor
+         * table which we handle as if it's any normal descriptor chain. */
+        if (desc[i].flags & VRING_DESC_F_INDIRECT) {
+                if (desc[i].len % sizeof(struct vring_desc))
+                        errx(1, "Invalid size for indirect buffer table");
+
+                max = desc[i].len / sizeof(struct vring_desc);
+                desc = check_pointer(desc[i].addr, desc[i].len);
+                i = 0;
+        }
+
         do {
                 /* Grab the first descriptor, and check it's OK. */
-                iov[*out_num + *in_num].iov_len = vq->vring.desc[i].len;
+                iov[*out_num + *in_num].iov_len = desc[i].len;
                 iov[*out_num + *in_num].iov_base
-                        = check_pointer(vq->vring.desc[i].addr,
-                                        vq->vring.desc[i].len);
+                        = check_pointer(desc[i].addr, desc[i].len);
                 /* If this is an input descriptor, increment that count. */
-                if (vq->vring.desc[i].flags & VRING_DESC_F_WRITE)
+                if (desc[i].flags & VRING_DESC_F_WRITE)
                         (*in_num)++;
                 else {
                         /* If it's an output descriptor, they're all supposed
@@ -697,11 +664,10 @@ static unsigned get_vq_desc(struct virtqueue *vq,
                 }
 
                 /* If we've got too many, that implies a descriptor loop. */
-                if (*out_num + *in_num > vq->vring.num)
+                if (*out_num + *in_num > max)
                         errx(1, "Looped descriptor");
-        } while ((i = next_desc(vq, i)) != vq->vring.num);
+        } while ((i = next_desc(desc, i, max)) != max);
 
-        vq->inflight++;
         return head;
 }
 
@@ -719,44 +685,20 @@ static void add_used(struct virtqueue *vq, unsigned int head, int len)
         /* Make sure buffer is written before we update index. */
         wmb();
         vq->vring.used->idx++;
-        vq->inflight--;
-}
-
-/* This actually sends the interrupt for this virtqueue */
-static void trigger_irq(int fd, struct virtqueue *vq)
-{
-        unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
-
-        /* If they don't want an interrupt, don't send one, unless empty. */
-        if ((vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
-            && vq->inflight)
-                return;
-
-        /* Send the Guest an interrupt tell them we used something up. */
-        if (write(fd, buf, sizeof(buf)) != 0)
-                err(1, "Triggering irq %i", vq->config.irq);
+        vq->pending_used++;
 }
 
 /* And here's the combo meal deal.  Supersize me! */
-static void add_used_and_trigger(int fd, struct virtqueue *vq,
-                                 unsigned int head, int len)
+static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len)
 {
         add_used(vq, head, len);
-        trigger_irq(fd, vq);
+        trigger_irq(vq);
 }
 
 /*
  * The Console
  *
- * Here is the input terminal setting we save, and the routine to restore them
- * on exit so the user gets their terminal back. */
-static struct termios orig_term;
-static void restore_term(void)
-{
-        tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
-}
-
-/* We associate some data with the console for our exit hack. */
+ * We associate some data with the console for our exit hack. */
 struct console_abort
 {
         /* How many times have they hit ^C? */
@@ -766,276 +708,275 @@ struct console_abort
 };
 
 /* This is the routine which handles console input (ie. stdin). */
-static bool handle_console_input(int fd, struct device *dev)
+static void console_input(struct virtqueue *vq)
 {
         int len;
         unsigned int head, in_num, out_num;
-        struct iovec iov[dev->vq->vring.num];
-        struct console_abort *abort = dev->priv;
-
-        /* First we need a console buffer from the Guests's input virtqueue. */
-        head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-
-        /* If they're not ready for input, stop listening to this file
-         * descriptor.  We'll start again once they add an input buffer. */
-        if (head == dev->vq->vring.num)
-                return false;
+        struct console_abort *abort = vq->dev->priv;
+        struct iovec iov[vq->vring.num];
 
+        /* Make sure there's a descriptor waiting. */
+        head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
         if (out_num)
                 errx(1, "Output buffers in console in queue?");
 
-        /* This is why we convert to iovecs: the readv() call uses them, and so
-         * it reads straight into the Guest's buffer. */
-        len = readv(dev->fd, iov, in_num);
+        /* Read it in. */
+        len = readv(STDIN_FILENO, iov, in_num);
         if (len <= 0) {
-                /* This implies that the console is closed, is /dev/null, or
-                 * something went terribly wrong. */
+                /* Ran out of input? */
                 warnx("Failed to get console input, ignoring console.");
-                /* Put the input terminal back. */
-                restore_term();
-                /* Remove callback from input vq, so it doesn't restart us. */
-                dev->vq->handle_output = NULL;
-                /* Stop listening to this fd: don't call us again. */
-                return false;
+                /* For simplicity, dying threads kill the whole Launcher.  So
+                 * just nap here. */
+                for (;;)
+                        pause();
         }
 
-        /* Tell the Guest about the new input. */
-        add_used_and_trigger(fd, dev->vq, head, len);
+        add_used_and_trigger(vq, head, len);
 
         /* Three ^C within one second?  Exit.
          *
-         * This is such a hack, but works surprisingly well.  Each ^C has to be
-         * in a buffer by itself, so they can't be too fast.  But we check that
-         * we get three within about a second, so they can't be too slow. */
-        if (len == 1 && ((char *)iov[0].iov_base)[0] == 3) {
-                if (!abort->count++)
-                        gettimeofday(&abort->start, NULL);
-                else if (abort->count == 3) {
-                        struct timeval now;
-                        gettimeofday(&now, NULL);
-                        if (now.tv_sec <= abort->start.tv_sec+1) {
-                                unsigned long args[] = { LHREQ_BREAK, 0 };
-                                /* Close the fd so Waker will know it has to
-                                 * exit. */
-                                close(waker_fds.pipe[1]);
-                                /* Just in case Waker is blocked in BREAK, send
-                                 * unbreak now. */
-                                write(fd, args, sizeof(args));
-                                exit(2);
-                        }
-                        abort->count = 0;
-                }
-        } else
-                /* Any other key resets the abort counter. */
+         * This is such a hack, but works surprisingly well.  Each ^C has to
+         * be in a buffer by itself, so they can't be too fast.  But we check
+         * that we get three within about a second, so they can't be too
+         * slow. */
+        if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) {
                 abort->count = 0;
+                return;
+        }
 
-        /* Everything went OK! */
-        return true;
+        abort->count++;
+        if (abort->count == 1)
+                gettimeofday(&abort->start, NULL);
+        else if (abort->count == 3) {
+                struct timeval now;
+                gettimeofday(&now, NULL);
+                /* Kill all Launcher processes with SIGINT, like normal ^C */
+                if (now.tv_sec <= abort->start.tv_sec+1)
+                        kill(0, SIGINT);
+                abort->count = 0;
+        }
 }
 
-/* Handling output for console is simple: we just get all the output buffers
- * and write them to stdout. */
-static void handle_console_output(int fd, struct virtqueue *vq, bool timeout)
+/* This is the routine which handles console output (ie. stdout). */
+static void console_output(struct virtqueue *vq)
 {
         unsigned int head, out, in;
-        int len;
         struct iovec iov[vq->vring.num];
 
-        /* Keep getting output buffers from the Guest until we run out. */
-        while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
-                if (in)
-                        errx(1, "Input buffers in output queue?");
-                len = writev(STDOUT_FILENO, iov, out);
-                add_used_and_trigger(fd, vq, head, len);
+        head = wait_for_vq_desc(vq, iov, &out, &in);
+        if (in)
+                errx(1, "Input buffers in console output queue?");
+        while (!iov_empty(iov, out)) {
+                int len = writev(STDOUT_FILENO, iov, out);
+                if (len <= 0)
+                        err(1, "Write to stdout gave %i", len);
+                iov_consume(iov, out, len);
         }
-}
-
-/* This is called when we no longer want to hear about Guest changes to a
- * virtqueue.  This is more efficient in high-traffic cases, but it means we
- * have to set a timer to check if any more changes have occurred. */
-static void block_vq(struct virtqueue *vq)
-{
-        struct itimerval itm;
-
-        vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
-        vq->blocked = true;
-
-        itm.it_interval.tv_sec = 0;
-        itm.it_interval.tv_usec = 0;
-        itm.it_value.tv_sec = 0;
-        itm.it_value.tv_usec = timeout_usec;
-
-        setitimer(ITIMER_REAL, &itm, NULL);
+        add_used(vq, head, 0);
 }
 
 /*
  * The Network
  *
  * Handling output for network is also simple: we get all the output buffers
- * and write them (ignoring the first element) to this device's file descriptor
- * (/dev/net/tun).
+ * and write them to /dev/net/tun.
  */
-static void handle_net_output(int fd, struct virtqueue *vq, bool timeout)
+struct net_info {
+        int tunfd;
+};
+
+static void net_output(struct virtqueue *vq)
 {
-        unsigned int head, out, in, num = 0;
-        int len;
+        struct net_info *net_info = vq->dev->priv;
+        unsigned int head, out, in;
         struct iovec iov[vq->vring.num];
-        static int last_timeout_num;
-
-        /* Keep getting output buffers from the Guest until we run out. */
-        while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
-                if (in)
-                        errx(1, "Input buffers in output queue?");
-                len = writev(vq->dev->fd, iov, out);
-                if (len < 0)
-                        err(1, "Writing network packet to tun");
-                add_used_and_trigger(fd, vq, head, len);
-                num++;
-        }
 
-        /* Block further kicks and set up a timer if we saw anything. */
-        if (!timeout && num)
-                block_vq(vq);
-
-        /* We never quite know how long should we wait before we check the
-         * queue again for more packets.  We start at 500 microseconds, and if
-         * we get fewer packets than last time, we assume we made the timeout
-         * too small and increase it by 10 microseconds.  Otherwise, we drop it
-         * by one microsecond every time.  It seems to work well enough. */
-        if (timeout) {
-                if (num < last_timeout_num)
-                        timeout_usec += 10;
-                else if (timeout_usec > 1)
-                        timeout_usec--;
-                last_timeout_num = num;
-        }
+        head = wait_for_vq_desc(vq, iov, &out, &in);
+        if (in)
+                errx(1, "Input buffers in net output queue?");
+        if (writev(net_info->tunfd, iov, out) < 0)
+                errx(1, "Write to tun failed?");
+        add_used(vq, head, 0);
+}
+
+/* Will reading from this file descriptor block? */
+static bool will_block(int fd)
+{
+        fd_set fdset;
+        struct timeval zero = { 0, 0 };
+        FD_ZERO(&fdset);
+        FD_SET(fd, &fdset);
+        return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
 }
 
-/* This is where we handle a packet coming in from the tun device to our
+/* This is where we handle packets coming in from the tun device to our
  * Guest. */
-static bool handle_tun_input(int fd, struct device *dev)
+static void net_input(struct virtqueue *vq)
 {
-        unsigned int head, in_num, out_num;
         int len;
-        struct iovec iov[dev->vq->vring.num];
-
-        /* First we need a network buffer from the Guests's recv virtqueue. */
-        head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-        if (head == dev->vq->vring.num) {
-                /* Now, it's expected that if we try to send a packet too
-                 * early, the Guest won't be ready yet.  Wait until the device
-                 * status says it's ready. */
-                /* FIXME: Actually want DRIVER_ACTIVE here. */
-
-                /* Now tell it we want to know if new things appear. */
-                dev->vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
-                wmb();
-
-                /* We'll turn this back on if input buffers are registered. */
-                return false;
-        } else if (out_num)
-                errx(1, "Output buffers in network recv queue?");
-
-        /* Read the packet from the device directly into the Guest's buffer. */
-        len = readv(dev->fd, iov, in_num);
-        if (len <= 0)
-                err(1, "reading network");
+        unsigned int head, out, in;
+        struct iovec iov[vq->vring.num];
+        struct net_info *net_info = vq->dev->priv;
 
-        /* Tell the Guest about the new packet. */
-        add_used_and_trigger(fd, dev->vq, head, len);
+        head = wait_for_vq_desc(vq, iov, &out, &in);
+        if (out)
+                errx(1, "Output buffers in net input queue?");
 
-        verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
-                ((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
-                head != dev->vq->vring.num ? "sent" : "discarded");
+        /* Deliver interrupt now, since we're about to sleep. */
+        if (vq->pending_used && will_block(net_info->tunfd))
+                trigger_irq(vq);
 
-        /* All good. */
-        return true;
+        len = readv(net_info->tunfd, iov, in);
+        if (len <= 0)
+                err(1, "Failed to read from tun.");
+        add_used(vq, head, len);
 }
 
-/*L:215 This is the callback attached to the network and console input
- * virtqueues: it ensures we try again, in case we stopped console or net
- * delivery because Guest didn't have any buffers. */
-static void enable_fd(int fd, struct virtqueue *vq, bool timeout)
+/* This is the helper to create threads. */
+static int do_thread(void *_vq)
 {
-        add_device_fd(vq->dev->fd);
-        /* Snap the Waker out of its select loop. */
-        write(waker_fds.pipe[1], "", 1);
+        struct virtqueue *vq = _vq;
+
+        for (;;)
+                vq->service(vq);
+        return 0;
 }
 
-static void net_enable_fd(int fd, struct virtqueue *vq, bool timeout)
+/* When a child dies, we kill our entire process group with SIGTERM.  This
+ * also has the side effect that the shell restores the console for us! */
+static void kill_launcher(int signal)
 {
-        /* We don't need to know again when Guest refills receive buffer. */
-        vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
-        enable_fd(fd, vq, timeout);
+        kill(0, SIGTERM);
 }
 
-/* When the Guest tells us they updated the status field, we handle it. */
-static void update_device_status(struct device *dev)
+static void reset_device(struct device *dev)
 {
         struct virtqueue *vq;
 
-        /* This is a reset. */
-        if (dev->desc->status == 0) {
-                verbose("Resetting device %s\n", dev->name);
+        verbose("Resetting device %s\n", dev->name);
 
-                /* Clear any features they've acked. */
-                memset(get_feature_bits(dev) + dev->desc->feature_len, 0,
-                       dev->desc->feature_len);
+        /* Clear any features they've acked. */
+        memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len);
 
-                /* Zero out the virtqueues. */
-                for (vq = dev->vq; vq; vq = vq->next) {
-                        memset(vq->vring.desc, 0,
-                               vring_size(vq->config.num, LGUEST_VRING_ALIGN));
-                        lg_last_avail(vq) = 0;
+        /* We're going to be explicitly killing threads, so ignore them. */
+        signal(SIGCHLD, SIG_IGN);
+
+        /* Zero out the virtqueues, get rid of their threads */
+        for (vq = dev->vq; vq; vq = vq->next) {
+                if (vq->thread != (pid_t)-1) {
+                        kill(vq->thread, SIGTERM);
+                        waitpid(vq->thread, NULL, 0);
+                        vq->thread = (pid_t)-1;
                 }
-        } else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
+                memset(vq->vring.desc, 0,
+                       vring_size(vq->config.num, LGUEST_VRING_ALIGN));
+                lg_last_avail(vq) = 0;
+        }
+        dev->running = false;
+
+        /* Now we care if threads die. */
+        signal(SIGCHLD, (void *)kill_launcher);
+}
+
+static void create_thread(struct virtqueue *vq)
+{
+        /* Create stack for thread and run it.  Since stack grows
+         * upwards, we point the stack pointer to the end of this
+         * region. */
+        char *stack = malloc(32768);
+        unsigned long args[] = { LHREQ_EVENTFD,
+                                 vq->config.pfn*getpagesize(), 0 };
+
+        /* Create a zero-initialized eventfd. */
+        vq->eventfd = eventfd(0, 0);
+        if (vq->eventfd < 0)
+                err(1, "Creating eventfd");
+        args[2] = vq->eventfd;
+
+        /* Attach an eventfd to this virtqueue: it will go off
+         * when the Guest does an LHCALL_NOTIFY for this vq. */
+        if (write(lguest_fd, &args, sizeof(args)) != 0)
+                err(1, "Attaching eventfd");
+
+        /* CLONE_VM: because it has to access the Guest memory, and
+         * SIGCHLD so we get a signal if it dies. */
+        vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
+        if (vq->thread == (pid_t)-1)
+                err(1, "Creating clone");
+        /* We close our local copy, now the child has it. */
+        close(vq->eventfd);
+}
+
+static void start_device(struct device *dev)
+{
+        unsigned int i;
+        struct virtqueue *vq;
+
+        verbose("Device %s OK: offered", dev->name);
+        for (i = 0; i < dev->feature_len; i++)
+                verbose(" %02x", get_feature_bits(dev)[i]);
+        verbose(", accepted");
+        for (i = 0; i < dev->feature_len; i++)
+                verbose(" %02x", get_feature_bits(dev)
+                        [dev->feature_len+i]);
+
+        for (vq = dev->vq; vq; vq = vq->next) {
+                if (vq->service)
+                        create_thread(vq);
+        }
+        dev->running = true;
+}
+
+static void cleanup_devices(void)
+{
+        struct device *dev;
+
+        for (dev = devices.dev; dev; dev = dev->next)
+                reset_device(dev);
+
+        /* If we saved off the original terminal settings, restore them now. */
+        if (orig_term.c_lflag & (ISIG|ICANON|ECHO))
+                tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
+}
+
+/* When the Guest tells us they updated the status field, we handle it. */
+static void update_device_status(struct device *dev)
+{
+        /* A zero status is a reset, otherwise it's a set of flags. */
+        if (dev->desc->status == 0)
+                reset_device(dev);
+        else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
                 warnx("Device %s configuration FAILED", dev->name);
+                if (dev->running)
+                        reset_device(dev);
         } else if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
-                unsigned int i;
-
-                verbose("Device %s OK: offered", dev->name);
-                for (i = 0; i < dev->desc->feature_len; i++)
-                        verbose(" %02x", get_feature_bits(dev)[i]);
-                verbose(", accepted");
-                for (i = 0; i < dev->desc->feature_len; i++)
-                        verbose(" %02x", get_feature_bits(dev)
-                                [dev->desc->feature_len+i]);
-
-                if (dev->ready)
-                        dev->ready(dev);
+                if (!dev->running)
+                        start_device(dev);
         }
 }
 
 /* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
-static void handle_output(int fd, unsigned long addr)
+static void handle_output(unsigned long addr)
 {
         struct device *i;
-        struct virtqueue *vq;
 
-        /* Check each device and virtqueue. */
+        /* Check each device. */
         for (i = devices.dev; i; i = i->next) {
+                struct virtqueue *vq;
+
                 /* Notifications to device descriptors update device status. */
                 if (from_guest_phys(addr) == i->desc) {
                         update_device_status(i);
                         return;
                 }
 
-                /* Notifications to virtqueues mean output has occurred. */
+                /* Devices *can* be used before status is set to DRIVER_OK. */
                 for (vq = i->vq; vq; vq = vq->next) {
-                        if (vq->config.pfn != addr/getpagesize())
+                        if (addr != vq->config.pfn*getpagesize())
                                 continue;
-
-                        /* Guest should acknowledge (and set features!)  before
-                         * using the device. */
-                        if (i->desc->status == 0) {
-                                warnx("%s gave early output", i->name);
-                                return;
-                        }
-
-                        if (strcmp(vq->dev->name, "console") != 0)
-                                verbose("Output to %s\n", vq->dev->name);
-                        if (vq->handle_output)
-                                vq->handle_output(fd, vq, false);
+                        if (i->running)
+                                errx(1, "Notification on running %s", i->name);
+                        start_device(i);
                         return;
                 }
         }
@@ -1049,71 +990,6 @@ static void handle_output(int fd, unsigned long addr)
               strnlen(from_guest_phys(addr), guest_limit - addr));
 }
 
-static void handle_timeout(int fd)
-{
-        char buf[32];
-        struct device *i;
-        struct virtqueue *vq;
-
-        /* Clear the pipe */
-        read(timeoutpipe[0], buf, sizeof(buf));
-
-        /* Check each device and virtqueue: flush blocked ones. */
-        for (i = devices.dev; i; i = i->next) {
-                for (vq = i->vq; vq; vq = vq->next) {
-                        if (!vq->blocked)
-                                continue;
-
-                        vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
-                        vq->blocked = false;
-                        if (vq->handle_output)
-                                vq->handle_output(fd, vq, true);
-                }
-        }
-}
-
-/* This is called when the Waker wakes us up: check for incoming file
- * descriptors. */
-static void handle_input(int fd)
-{
-        /* select() wants a zeroed timeval to mean "don't wait". */
-        struct timeval poll = { .tv_sec = 0, .tv_usec = 0 };
-
-        for (;;) {
-                struct device *i;
-                fd_set fds = devices.infds;
-                int num;
-
-                num = select(devices.max_infd+1, &fds, NULL, NULL, &poll);
-                /* Could get interrupted */
-                if (num < 0)
-                        continue;
-                /* If nothing is ready, we're done. */
-                if (num == 0)
-                        break;
-
-                /* Otherwise, call the device(s) which have readable file
-                 * descriptors and a method of handling them.  */
-                for (i = devices.dev; i; i = i->next) {
-                        if (i->handle_input && FD_ISSET(i->fd, &fds)) {
-                                if (i->handle_input(fd, i))
-                                        continue;
-
-                                /* If handle_input() returns false, it means we
-                                 * should no longer service it.  Networking and
-                                 * console do this when there's no input
-                                 * buffers to deliver into.  Console also uses
-                                 * it when it discovers that stdin is closed. */
-                                FD_CLR(i->fd, &devices.infds);
-                        }
-                }
-
-                /* Is this the timeout fd? */
-                if (FD_ISSET(timeoutpipe[0], &fds))
-                        handle_timeout(fd);
-        }
-}
-
 /*L:190
  * Device Setup
  *
@@ -1129,8 +1005,8 @@ static void handle_input(int fd)
 static u8 *device_config(const struct device *dev)
 {
         return (void *)(dev->desc + 1)
-                + dev->desc->num_vq * sizeof(struct lguest_vqconfig)
-                + dev->desc->feature_len * 2;
+                + dev->num_vq * sizeof(struct lguest_vqconfig)
+                + dev->feature_len * 2;
 }
 
 /* This routine allocates a new "struct lguest_device_desc" from descriptor
@@ -1159,7 +1035,7 @@ static struct lguest_device_desc *new_dev_desc(u16 type)
 /* Each device descriptor is followed by the description of its virtqueues.  We
  * specify how many descriptors the virtqueue is to have. */
 static void add_virtqueue(struct device *dev, unsigned int num_descs,
-                          void (*handle_output)(int, struct virtqueue *, bool))
+                          void (*service)(struct virtqueue *))
 {
         unsigned int pages;
         struct virtqueue **i, *vq = malloc(sizeof(*vq));
@@ -1174,8 +1050,8 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
         vq->next = NULL;
         vq->last_avail_idx = 0;
         vq->dev = dev;
-        vq->inflight = 0;
-        vq->blocked = false;
+        vq->service = service;
+        vq->thread = (pid_t)-1;
 
         /* Initialize the configuration. */
         vq->config.num = num_descs;
@@ -1191,6 +1067,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
          * yet, otherwise we'd be overwriting them. */
         assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
         memcpy(device_config(dev), &vq->config, sizeof(vq->config));
+        dev->num_vq++;
         dev->desc->num_vq++;
 
         verbose("Virtqueue page %#lx\n", to_guest_phys(p));
@@ -1199,15 +1076,6 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
          * second.  */
         for (i = &dev->vq; *i; i = &(*i)->next);
         *i = vq;
-
-        /* Set the routine to call when the Guest does something to this
-         * virtqueue. */
-        vq->handle_output = handle_output;
-
-        /* As an optimization, set the advisory "Don't Notify Me" flag if we
-         * don't have a handler */
-        if (!handle_output)
-                vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;
 }
 
 /* The first half of the feature bitmask is for us to advertise features.  The
@@ -1219,7 +1087,7 @@ static void add_feature(struct device *dev, unsigned bit)
         /* We can't extend the feature bits once we've added config bytes */
         if (dev->desc->feature_len <= bit / CHAR_BIT) {
                 assert(dev->desc->config_len == 0);
-                dev->desc->feature_len = (bit / CHAR_BIT) + 1;
+                dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1;
         }
 
         features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
@@ -1243,22 +1111,17 @@ static void set_config(struct device *dev, unsigned len, const void *conf)
  * calling new_dev_desc() to allocate the descriptor and device memory.
  *
  * See what I mean about userspace being boring? */
-static struct device *new_device(const char *name, u16 type, int fd,
-                                 bool (*handle_input)(int, struct device *))
+static struct device *new_device(const char *name, u16 type)
 {
         struct device *dev = malloc(sizeof(*dev));
 
         /* Now we populate the fields one at a time. */
-        dev->fd = fd;
-        /* If we have an input handler for this file descriptor, then we add it
-         * to the device_list's fdset and maxfd. */
-        if (handle_input)
-                add_device_fd(dev->fd);
         dev->desc = new_dev_desc(type);
-        dev->handle_input = handle_input;
         dev->name = name;
         dev->vq = NULL;
-        dev->ready = NULL;
+        dev->feature_len = 0;
+        dev->num_vq = 0;
+        dev->running = false;
 
         /* Append to device list.  Prepending to a single-linked list is
          * easier, but the user expects the devices to be arranged on the bus
@@ -1286,13 +1149,10 @@ static void setup_console(void)
                  * raw input stream to the Guest. */
                 term.c_lflag &= ~(ISIG|ICANON|ECHO);
                 tcsetattr(STDIN_FILENO, TCSANOW, &term);
-                /* If we exit gracefully, the original settings will be
-                 * restored so the user can see what they're typing. */
-                atexit(restore_term);
         }
 
-        dev = new_device("console", VIRTIO_ID_CONSOLE,
-                         STDIN_FILENO, handle_console_input);
+        dev = new_device("console", VIRTIO_ID_CONSOLE);
+
         /* We store the console state in dev->priv, and initialize it. */
         dev->priv = malloc(sizeof(struct console_abort));
         ((struct console_abort *)dev->priv)->count = 0;
@@ -1301,31 +1161,13 @@ static void setup_console(void)
          * they put something the input queue, we make sure we're listening to
          * stdin.  When they put something in the output queue, we write it to
          * stdout. */
-        add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
-        add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output);
+        add_virtqueue(dev, VIRTQUEUE_NUM, console_input);
+        add_virtqueue(dev, VIRTQUEUE_NUM, console_output);
 
-        verbose("device %u: console\n", devices.device_num++);
+        verbose("device %u: console\n", ++devices.device_num);
 }
 /*:*/
 
-static void timeout_alarm(int sig)
-{
-        write(timeoutpipe[1], "", 1);
-}
-
-static void setup_timeout(void)
-{
-        if (pipe(timeoutpipe) != 0)
-                err(1, "Creating timeout pipe");
-
-        if (fcntl(timeoutpipe[1], F_SETFL,
-                  fcntl(timeoutpipe[1], F_GETFL) | O_NONBLOCK) != 0)
-                err(1, "Making timeout pipe nonblocking");
-
-        add_device_fd(timeoutpipe[0]);
-        signal(SIGALRM, timeout_alarm);
-}
-
 /*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
  * --sharenet=<name> option which opens or creates a named pipe.  This can be
  * used to send packets to another guest in a 1:1 manner.
@@ -1447,21 +1289,23 @@ static int get_tun_device(char tapif[IFNAMSIZ])
 static void setup_tun_net(char *arg)
 {
         struct device *dev;
-        int netfd, ipfd;
+        struct net_info *net_info = malloc(sizeof(*net_info));
+        int ipfd;
         u32 ip = INADDR_ANY;
         bool bridging = false;
         char tapif[IFNAMSIZ], *p;
         struct virtio_net_config conf;
 
-        netfd = get_tun_device(tapif);
+        net_info->tunfd = get_tun_device(tapif);
 
         /* First we create a new network device. */
-        dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);
+        dev = new_device("net", VIRTIO_ID_NET);
+        dev->priv = net_info;
 
         /* Network devices need a receive and a send queue, just like
          * console. */
-        add_virtqueue(dev, VIRTQUEUE_NUM, net_enable_fd);
-        add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);
+        add_virtqueue(dev, VIRTQUEUE_NUM, net_input);
+        add_virtqueue(dev, VIRTQUEUE_NUM, net_output);
 
         /* We need a socket to perform the magic network ioctls to bring up the
          * tap interface, connect to the bridge etc.  Any socket will do! */
@@ -1502,6 +1346,8 @@ static void setup_tun_net(char *arg)
         add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
         add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
         add_feature(dev, VIRTIO_NET_F_HOST_ECN);
+        /* We handle indirect ring entries */
+        add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC);
         set_config(dev, sizeof(conf), &conf);
 
         /* We don't need the socket any more; setup is done. */
@@ -1550,20 +1396,18 @@ struct vblk_info
  * Remember that the block device is handled by a separate I/O thread.  We head
  * straight into the core of that thread here:
  */
-static bool service_io(struct device *dev)
+static void blk_request(struct virtqueue *vq)
 {
-        struct vblk_info *vblk = dev->priv;
+        struct vblk_info *vblk = vq->dev->priv;
         unsigned int head, out_num, in_num, wlen;
         int ret;
         u8 *in;
         struct virtio_blk_outhdr *out;
-        struct iovec iov[dev->vq->vring.num];
+        struct iovec iov[vq->vring.num];
         off64_t off;
 
-        /* See if there's a request waiting.  If not, nothing to do. */
-        head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-        if (head == dev->vq->vring.num)
-                return false;
+        /* Get the next request. */
+        head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 
         /* Every block request should contain at least one output buffer
          * (detailing the location on disk and the type of request) and one
@@ -1637,83 +1481,21 @@ static bool service_io(struct device *dev)
         if (out->type & VIRTIO_BLK_T_BARRIER)
                 fdatasync(vblk->fd);
 
-        /* We can't trigger an IRQ, because we're not the Launcher.  It does
-         * that when we tell it we're done. */
-        add_used(dev->vq, head, wlen);
-        return true;
-}
-
-/* This is the thread which actually services the I/O. */
-static int io_thread(void *_dev)
-{
-        struct device *dev = _dev;
-        struct vblk_info *vblk = dev->priv;
-        char c;
-
-        /* Close other side of workpipe so we get 0 read when main dies. */
-        close(vblk->workpipe[1]);
-        /* Close the other side of the done_fd pipe. */
-        close(dev->fd);
-
-        /* When this read fails, it means Launcher died, so we follow. */
-        while (read(vblk->workpipe[0], &c, 1) == 1) {
-                /* We acknowledge each request immediately to reduce latency,
-                 * rather than waiting until we've done them all.  I haven't
-                 * measured to see if it makes any difference.
-                 *
-                 * That would be an interesting test, wouldn't it?  You could
-                 * also try having more than one I/O thread. */
-                while (service_io(dev))
-                        write(vblk->done_fd, &c, 1);
-        }
-        return 0;
-}
-
-/* Now we've seen the I/O thread, we return to the Launcher to see what happens
- * when that thread tells us it's completed some I/O. */
-static bool handle_io_finish(int fd, struct device *dev)
-{
-        char c;
-
-        /* If the I/O thread died, presumably it printed the error, so we
-         * simply exit. */
-        if (read(dev->fd, &c, 1) != 1)
-                exit(1);
-
-        /* It did some work, so trigger the irq. */
-        trigger_irq(fd, dev->vq);
-        return true;
-}
-
-/* When the Guest submits some I/O, we just need to wake the I/O thread. */
-static void handle_virtblk_output(int fd, struct virtqueue *vq, bool timeout)
-{
-        struct vblk_info *vblk = vq->dev->priv;
-        char c = 0;
-
-        /* Wake up I/O thread and tell it to go to work! */
-        if (write(vblk->workpipe[1], &c, 1) != 1)
-                /* Presumably it indicated why it died. */
-                exit(1);
+        add_used(vq, head, wlen);
 }
 
 /*L:198 This actually sets up a virtual block device. */
 static void setup_block_file(const char *filename)
 {
-        int p[2];
         struct device *dev;
         struct vblk_info *vblk;
-        void *stack;
         struct virtio_blk_config conf;
 
-        /* This is the pipe the I/O thread will use to tell us I/O is done. */
-        pipe(p);
-
         /* The device responds to return from I/O thread. */
-        dev = new_device("block", VIRTIO_ID_BLOCK, p[0], handle_io_finish);
+        dev = new_device("block", VIRTIO_ID_BLOCK);
 
         /* The device has one virtqueue, where the Guest places requests. */
-        add_virtqueue(dev, VIRTQUEUE_NUM, handle_virtblk_output);
+        add_virtqueue(dev, VIRTQUEUE_NUM, blk_request);
 
         /* Allocate the room for our own bookkeeping */
         vblk = dev->priv = malloc(sizeof(*vblk));
@@ -1735,49 +1517,29 @@ static void setup_block_file(const char *filename)
 
         set_config(dev, sizeof(conf), &conf);
 
-        /* The I/O thread writes to this end of the pipe when done. */
-        vblk->done_fd = p[1];
-
-        /* This is the second pipe, which is how we tell the I/O thread about
-         * more work. */
-        pipe(vblk->workpipe);
-
-        /* Create stack for thread and run it.  Since stack grows upwards, we
-         * point the stack pointer to the end of this region. */
-        stack = malloc(32768);
-        /* SIGCHLD - We dont "wait" for our cloned thread, so prevent it from
-         * becoming a zombie. */
-        if (clone(io_thread, stack + 32768, CLONE_VM | SIGCHLD, dev) == -1)
-                err(1, "Creating clone");
-
-        /* We don't need to keep the I/O thread's end of the pipes open. */
-        close(vblk->done_fd);
-        close(vblk->workpipe[0]);
-
         verbose("device %u: virtblock %llu sectors\n",
-                devices.device_num, le64_to_cpu(conf.capacity));
+                ++devices.device_num, le64_to_cpu(conf.capacity));
 }
 
+struct rng_info {
+        int rfd;
+};
+
 /* Our random number generator device reads from /dev/random into the Guest's
  * input buffers.  The usual case is that the Guest doesn't want random numbers
  * and so has no buffers although /dev/random is still readable, whereas
  * console is the reverse.
  *
  * The same logic applies, however. */
-static bool handle_rng_input(int fd, struct device *dev)
+static void rng_input(struct virtqueue *vq)
 {
         int len;
         unsigned int head, in_num, out_num, totlen = 0;
-        struct iovec iov[dev->vq->vring.num];
+        struct rng_info *rng_info = vq->dev->priv;
+        struct iovec iov[vq->vring.num];
 
         /* First we need a buffer from the Guests's virtqueue. */
-        head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-
-        /* If they're not ready for input, stop listening to this file
-         * descriptor.  We'll start again once they add an input buffer. */
-        if (head == dev->vq->vring.num)
-                return false;
-
+        head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
         if (out_num)
                 errx(1, "Output buffers in rng?");
 
@@ -1785,7 +1547,7 @@ static bool handle_rng_input(int fd, struct device *dev)
          * it reads straight into the Guest's buffer.  We loop to make sure we
          * fill it. */
         while (!iov_empty(iov, in_num)) {
-                len = readv(dev->fd, iov, in_num);
+                len = readv(rng_info->rfd, iov, in_num);
                 if (len <= 0)
                         err(1, "Read from /dev/random gave %i", len);
                 iov_consume(iov, in_num, len);
@@ -1793,25 +1555,23 @@ static bool handle_rng_input(int fd, struct device *dev)
         }
 
         /* Tell the Guest about the new input. */
-        add_used_and_trigger(fd, dev->vq, head, totlen);
-
-        /* Everything went OK! */
-        return true;
+        add_used(vq, head, totlen);
 }
 
 /* And this creates a "hardware" random number device for the Guest. */
 static void setup_rng(void)
 {
         struct device *dev;
-        int fd;
+        struct rng_info *rng_info = malloc(sizeof(*rng_info));
 
-        fd = open_or_die("/dev/random", O_RDONLY);
+        rng_info->rfd = open_or_die("/dev/random", O_RDONLY);
 
         /* The device responds to return from I/O thread. */
-        dev = new_device("rng", VIRTIO_ID_RNG, fd, handle_rng_input);
+        dev = new_device("rng", VIRTIO_ID_RNG);
+        dev->priv = rng_info;
 
         /* The device has one virtqueue, where the Guest places inbufs. */
-        add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
+        add_virtqueue(dev, VIRTQUEUE_NUM, rng_input);
 
         verbose("device %u: rng\n", devices.device_num++);
 }
@@ -1827,17 +1587,18 @@ static void __attribute__((noreturn)) restart_guest(void)
         for (i = 3; i < FD_SETSIZE; i++)
                 close(i);
 
-        /* The exec automatically gets rid of the I/O and Waker threads. */
+        /* Reset all the devices (kills all threads). */
+        cleanup_devices();
+
         execv(main_args[0], main_args);
         err(1, "Could not exec %s", main_args[0]);
 }
 
 /*L:220 Finally we reach the core of the Launcher which runs the Guest, serves
  * its input and output, and finally, lays it to rest. */
-static void __attribute__((noreturn)) run_guest(int lguest_fd)
+static void __attribute__((noreturn)) run_guest(void)
 {
         for (;;) {
-                unsigned long args[] = { LHREQ_BREAK, 0 };
                 unsigned long notify_addr;
                 int readval;
 
@@ -1848,8 +1609,7 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
                 /* One unsigned long means the Guest did HCALL_NOTIFY */
                 if (readval == sizeof(notify_addr)) {
                         verbose("Notify on address %#lx\n", notify_addr);
-                        handle_output(lguest_fd, notify_addr);
-                        continue;
+                        handle_output(notify_addr);
                 /* ENOENT means the Guest died.  Reading tells us why. */
                 } else if (errno == ENOENT) {
                         char reason[1024] = { 0 };
@@ -1858,19 +1618,9 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
                 /* ERESTART means that we need to reboot the guest */
                 } else if (errno == ERESTART) {
                         restart_guest();
-                /* EAGAIN means a signal (timeout).
-                 * Anything else means a bug or incompatible change. */
-                } else if (errno != EAGAIN)
+                /* Anything else means a bug or incompatible change. */
+                } else
                         err(1, "Running guest failed");
-
-                /* Only service input on thread for CPU 0. */
-                if (cpu_id != 0)
-                        continue;
-
-                /* Service input, then unset the BREAK to release the Waker. */
-                handle_input(lguest_fd);
-                if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
-                        err(1, "Resetting break");
         }
 }
 /*L:240
@@ -1904,8 +1654,8 @@ int main(int argc, char *argv[])
         /* Memory, top-level pagetable, code startpoint and size of the
          * (optional) initrd. */
         unsigned long mem = 0, start, initrd_size = 0;
-        /* Two temporaries and the /dev/lguest file descriptor. */
-        int i, c, lguest_fd;
+        /* Two temporaries. */
+        int i, c;
         /* The boot information for the Guest. */
         struct boot_params *boot;
         /* If they specify an initrd file to load. */
@@ -1913,18 +1663,10 @@ int main(int argc, char *argv[])
 
         /* Save the args: we "reboot" by execing ourselves again. */
         main_args = argv;
-        /* We don't "wait" for the children, so prevent them from becoming
-         * zombies. */
-        signal(SIGCHLD, SIG_IGN);
 
-        /* First we initialize the device list.  Since console and network
-         * device receive input from a file descriptor, we keep an fdset
-         * (infds) and the maximum fd number (max_infd) with the head of the
-         * list.  We also keep a pointer to the last device.  Finally, we keep
-         * the next interrupt number to use for devices (1: remember that 0 is
-         * used by the timer). */
-        FD_ZERO(&devices.infds);
-        devices.max_infd = -1;
+        /* First we initialize the device list.  We keep a pointer to the last
+         * device, and the next interrupt number to use for devices (1:
+         * remember that 0 is used by the timer). */
         devices.lastdev = NULL;
         devices.next_irq = 1;
 
@@ -1982,9 +1724,6 @@ int main(int argc, char *argv[])
         /* We always have a console device */
         setup_console();
 
-        /* We can timeout waiting for Guest network transmit. */
-        setup_timeout();
-
         /* Now we load the kernel */
         start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));
 
@@ -2023,15 +1762,16 @@ int main(int argc, char *argv[])
 
         /* We tell the kernel to initialize the Guest: this returns the open
          * /dev/lguest file descriptor. */
-        lguest_fd = tell_kernel(start);
+        tell_kernel(start);
+
+        /* Ensure that we terminate if a child dies. */
+        signal(SIGCHLD, kill_launcher);
 
-        /* We clone off a thread, which wakes the Launcher whenever one of the
-         * input file descriptors needs attention.  We call this the Waker, and
-         * we'll cover it in a moment. */
-        setup_waker(lguest_fd);
+        /* If we exit via err(), this kills all the threads, restores tty. */
+        atexit(cleanup_devices);
 
         /* Finally, run the Guest.  This doesn't return. */
-        run_guest(lguest_fd);
+        run_guest();
 }
 /*:*/
 
diff --git a/Documentation/lguest/lguest.txt b/Documentation/lguest/lguest.txt
index 28c747362f95..efb3a6a045a2 100644
--- a/Documentation/lguest/lguest.txt
+++ b/Documentation/lguest/lguest.txt
@@ -37,7 +37,6 @@ Running Lguest:
      "Paravirtualized guest support" = Y
         "Lguest guest support" = Y
      "High Memory Support" = off/4GB
-     "PAE (Physical Address Extension) Support" = N
      "Alignment value to which kernel should be aligned" = 0x100000
         (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and
          CONFIG_PHYSICAL_ALIGN=0x100000)
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f5b7127f54ac..7f5809eddee6 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -31,6 +31,7 @@ Contents:
 
      - Locking functions.
      - Interrupt disabling functions.
+     - Sleep and wake-up functions.
      - Miscellaneous functions.
 
  (*) Inter-CPU locking barrier effects.
@@ -1217,6 +1218,132 @@ barriers are required in such a situation, they must be provided from some
 other means.
 
 
+SLEEP AND WAKE-UP FUNCTIONS
+---------------------------
+
+Sleeping and waking on an event flagged in global data can be viewed as an
+interaction between two pieces of data: the task state of the task waiting for
+the event and the global data used to indicate the event.  To make sure that
+these appear to happen in the right order, the primitives to begin the process
+of going to sleep, and the primitives to initiate a wake up imply certain
+barriers.
+
+Firstly, the sleeper normally follows something like this sequence of events:
+
+        for (;;) {
+                set_current_state(TASK_UNINTERRUPTIBLE);
+                if (event_indicated)
+                        break;
+                schedule();
+        }
+
+A general memory barrier is interpolated automatically by set_current_state()
+after it has altered the task state:
+
+        CPU 1
+        ===============================
+        set_current_state();
+          set_mb();
+            STORE current->state
+            <general barrier>
+        LOAD event_indicated
+
+set_current_state() may be wrapped by:
+
+        prepare_to_wait();
+        prepare_to_wait_exclusive();
+
+which therefore also imply a general memory barrier after setting the state.
+The whole sequence above is available in various canned forms, all of which
+interpolate the memory barrier in the right place:
+
+        wait_event();
+        wait_event_interruptible();
+        wait_event_interruptible_exclusive();
+        wait_event_interruptible_timeout();
+        wait_event_killable();
+        wait_event_timeout();
+        wait_on_bit();
+        wait_on_bit_lock();
+
+
+Secondly, code that performs a wake up normally follows something like this:
+
+        event_indicated = 1;
+        wake_up(&event_wait_queue);
+
+or:
+
+        event_indicated = 1;
+        wake_up_process(event_daemon);
+
+A write memory barrier is implied by wake_up() and co. if and only if they wake
+something up.  The barrier occurs before the task state is cleared, and so sits
+between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+
+        CPU 1                           CPU 2
+        =============================== ===============================
+        set_current_state();            STORE event_indicated
+          set_mb();                     wake_up();
+            STORE current->state          <write barrier>
+            <general barrier>             STORE current->state
+        LOAD event_indicated
+
+The available waker functions include:
+
+        complete();
+        wake_up();
+        wake_up_all();
+        wake_up_bit();
+        wake_up_interruptible();
+        wake_up_interruptible_all();
+        wake_up_interruptible_nr();
+        wake_up_interruptible_poll();
+        wake_up_interruptible_sync();
+        wake_up_interruptible_sync_poll();
+        wake_up_locked();
+        wake_up_locked_poll();
+        wake_up_nr();
+        wake_up_poll();
+        wake_up_process();
+
+
+[!] Note that the memory barriers implied by the sleeper and the waker do _not_
+order multiple stores before the wake-up with respect to loads of those stored
+values after the sleeper has called set_current_state().  For instance, if the
+sleeper does:
+
+        set_current_state(TASK_INTERRUPTIBLE);
+        if (event_indicated)
+                break;
+        __set_current_state(TASK_RUNNING);
+        do_something(my_data);
+
+and the waker does:
+
+        my_data = value;
+        event_indicated = 1;
+        wake_up(&event_wait_queue);
+
+there's no guarantee that the change to event_indicated will be perceived by
+the sleeper as coming after the change to my_data.  In such a circumstance, the
+code on both sides must interpolate its own memory barriers between the
+separate data accesses.  Thus the above sleeper ought to do:
+
+        set_current_state(TASK_INTERRUPTIBLE);
+        if (event_indicated) {
+                smp_rmb();
+                do_something(my_data);
+        }
+
+and the waker should do:
+
+        my_data = value;
+        smp_wmb();
+        event_indicated = 1;
+        wake_up(&event_wait_queue);
+
+
 MISCELLANEOUS FUNCTIONS
 -----------------------
 
@@ -1366,7 +1493,7 @@ WHERE ARE MEMORY BARRIERS NEEDED?
 
 Under normal operation, memory operation reordering is generally not going to
 be a problem as a single-threaded linear piece of code will still appear to
-work correctly, even if it's in an SMP kernel.  There are, however, three
+work correctly, even if it's in an SMP kernel.  There are, however, four
 circumstances in which reordering definitely _could_ be a problem:
 
  (*) Interprocessor interaction.
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 421e7d00ffd0..c9abbd86bc18 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -75,9 +75,6 @@ may need to apply in domain-specific ways to their devices:
 struct bus_type {
         ...
         int  (*suspend)(struct device *dev, pm_message_t state);
-        int  (*suspend_late)(struct device *dev, pm_message_t state);
-
-        int  (*resume_early)(struct device *dev);
         int  (*resume)(struct device *dev);
 };
 
@@ -226,20 +223,7 @@ The phases are seen by driver notifications issued in this order:
 
         This call should handle parts of device suspend logic that require
         sleeping.  It probably does work to quiesce the device which hasn't
-        been abstracted into class.suspend() or bus.suspend_late().
-
-   3    bus.suspend_late(dev, message) is called with IRQs disabled, and
-        with only one CPU active.  Until the bus.resume_early() phase
-        completes (see later), IRQs are not enabled again.  This method
-        won't be exposed by all busses; for message based busses like USB,
-        I2C, or SPI, device interactions normally require IRQs.  This bus
-        call may be morphed into a driver call with bus-specific parameters.
-
-        This call might save low level hardware state that might otherwise
-        be lost in the upcoming low power state, and actually put the
-        device into a low power state ... so that in some cases the device
-        may stay partly usable until this late.  This "late" call may also
-        help when coping with hardware that behaves badly.
+        been abstracted into class.suspend().
 
 The pm_message_t parameter is currently used to refine those semantics
 (described later).
@@ -351,19 +335,11 @@ devices processing each phase's calls before the next phase begins.
 
 The phases are seen by driver notifications issued in this order:
 
-   1    bus.resume_early(dev) is called with IRQs disabled, and with
-        only one CPU active.  As with bus.suspend_late(), this method
-        won't be supported on busses that require IRQs in order to
-        interact with devices.
-
-        This reverses the effects of bus.suspend_late().
-
-   2    bus.resume(dev) is called next.  This may be morphed into a device
-        driver call with bus-specific parameters; implementations may sleep.
-
-        This reverses the effects of bus.suspend().
+   1    bus.resume(dev) reverses the effects of bus.suspend().  This may
+        be morphed into a device driver call with bus-specific parameters;
+        implementations may sleep.
 
-   3    class.resume(dev) is called for devices associated with a class
+   2    class.resume(dev) is called for devices associated with a class
         that has such a method.  Implementations may sleep.
 
         This reverses the effects of class.suspend(), and would usually
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 5ba4d3fc625a..1df7f9cdab05 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -4,6 +4,7 @@
 CONTENTS
 ========
 
+0. WARNING
 1. Overview
   1.1 The problem
   1.2 The solution
@@ -14,6 +15,23 @@ CONTENTS
 3. Future plans
 
 
+0. WARNING
+==========
+
+ Fiddling with these settings can result in an unstable system, the knobs are
+ root only and assumes root knows what he is doing.
+
+Most notable:
+
+ * very small values in sched_rt_period_us can result in an unstable
+   system when the period is smaller than either the available hrtimer
+   resolution, or the time it takes to handle the budget refresh itself.
+
+ * very small values in sched_rt_runtime_us can result in an unstable
+   system when the runtime is so small the system has difficulty making
+   forward progress (NOTE: the migration thread and kstopmachine both
+   are real-time processes).
+
 1. Overview
 ===========
 
@@ -169,7 +187,7 @@ get their allocated time.
 
 Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
-the limited static priority levels 0-139. With deadline scheduling you need to
+the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
 deadline delta (deadline - now).
 
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 012858d2b119..5c08d96f407c 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -460,6 +460,25 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     The power-management is supported.
 
+  Module snd-ctxfi
+  ----------------
+
+    Module for Creative Sound Blaster X-Fi boards (20k1 / 20k2 chips)
+        * Creative Sound Blaster X-Fi Titanium Fatal1ty Champion Series
+        * Creative Sound Blaster X-Fi Titanium Fatal1ty Professional Series
+        * Creative Sound Blaster X-Fi Titanium Professional Audio
+        * Creative Sound Blaster X-Fi Titanium
+        * Creative Sound Blaster X-Fi Elite Pro
+        * Creative Sound Blaster X-Fi Platinum
+        * Creative Sound Blaster X-Fi Fatal1ty
+        * Creative Sound Blaster X-Fi XtremeGamer
+        * Creative Sound Blaster X-Fi XtremeMusic
+
+    reference_rate      - reference sample rate, 44100 or 48000 (default)
+    multiple            - multiple to ref. sample rate, 1 or 2 (default)
+
+    This module supports multiple cards.
+
   Module snd-darla20
   ------------------
 
@@ -925,6 +944,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
                         * Onkyo SE-90PCI
                         * Onkyo SE-200PCI
                         * ESI Juli@
+                        * ESI Maya44
                         * Hercules Fortissimo IV
                         * EGO-SYS WaveTerminal 192M
 
@@ -933,7 +953,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
                   prodigy71xt, prodigy71hifi, prodigyhd2, prodigy192,
                   juli, aureon51, aureon71, universe, ap192, k8x800,
                   phase22, phase28, ms300, av710, se200pci, se90pci,
-                  fortissimo4, sn25p, WT192M
+                  fortissimo4, sn25p, WT192M, maya44
 
     This module supports multiple cards and autoprobe.
 
@@ -1093,6 +1113,13 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     This module supports multiple cards.
     The driver requires the firmware loader support on kernel.
 
+  Module snd-lx6464es
+  -------------------
+
+    Module for Digigram LX6464ES boards
+
+    This module supports multiple cards.
+
   Module snd-maestro3
   -------------------
 
@@ -1543,13 +1570,15 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   Module snd-sc6000
   -----------------
 
-    Module for Gallant SC-6000 soundcard.
+    Module for Gallant SC-6000 soundcard and later models: SC-6600
+    and SC-7000.
 
     port        - Port # (0x220 or 0x240)
     mss_port    - MSS Port # (0x530 or 0xe80)
     irq         - IRQ # (5,7,9,10,11)
     mpu_irq     - MPU-401 IRQ # (5,7,9,10) ,0 - no MPU-401 irq
     dma         - DMA # (1,3,0)
+    joystick    - Enable gameport - 0 = disable (default), 1 = enable
 
     This module supports multiple cards.
 
@@ -1859,7 +1888,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), and Essence STX.
+    i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), Essence ST
+    (Deluxe) and Essence STX.
 
     This module supports autoprobe and multiple cards.
 
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index 322869fc8a9e..de8e10a94103 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -36,6 +36,7 @@ ALC260
   acer          Acer TravelMate
   will          Will laptops (PB V7900)
   replacer      Replacer 672V
+  favorit100    Maxdata Favorit 100XS
   basic         fixed pin assignment (old default model)
   test          for testing/debugging purpose, almost all controls can
                 adjusted.  Appearing only when compiled with
@@ -85,10 +86,11 @@ ALC269
   eeepc-p703    ASUS Eeepc P703 P900A
   eeepc-p901    ASUS Eeepc P901 S101
   fujitsu       FSC Amilo
+  lifebook      Fujitsu Lifebook S6420
   auto          auto-config reading BIOS (default)
 
-ALC662/663
-==========
+ALC662/663/272
+==============
   3stack-dig    3-stack (2-channel) with SPDIF
   3stack-6ch     3-stack (6-channel)
   3stack-6ch-dig 3-stack (6-channel) with SPDIF
@@ -107,6 +109,9 @@ ALC662/663
   asus-mode4    ASUS
   asus-mode5    ASUS
   asus-mode6    ASUS
+  dell          Dell with ALC272
+  dell-zm1      Dell ZM1 with ALC272
+  samsung-nc10  Samsung NC10 mini notebook
   auto          auto-config reading BIOS (default)
 
 ALC882/885
@@ -118,6 +123,7 @@ ALC882/885
   asus-a7j      ASUS A7J
   asus-a7m      ASUS A7M
   macpro        MacPro support
+  mb5           Macbook 5,1
   mbp3          Macbook Pro rev3
   imac24        iMac 24'' with jack detection
   w2jc          ASUS W2JC
@@ -133,10 +139,12 @@ ALC883/888
   acer          Acer laptops (Travelmate 3012WTMi, Aspire 5600, etc)
   acer-aspire   Acer Aspire 9810
   acer-aspire-4930g Acer Aspire 4930G
+  acer-aspire-8930g Acer Aspire 8930G
   medion        Medion Laptops
   medion-md2    Medion MD2
   targa-dig     Targa/MSI
-  targa-2ch-dig Targs/MSI with 2-channel
+  targa-2ch-dig Targa/MSI with 2-channel
+  targa-8ch-dig Targa/MSI with 8-channel (MSI GX620)
   laptop-eapd   3-jack with SPDIF I/O and EAPD (Clevo M540JE, M550JE)
   lenovo-101e   Lenovo 101E
   lenovo-nb0763 Lenovo NB0763
@@ -150,6 +158,9 @@ ALC883/888
   fujitsu-pi2515 Fujitsu AMILO Pi2515
   fujitsu-xa3530 Fujitsu AMILO XA3530
   3stack-6ch-intel Intel DG33* boards
+  asus-p5q      ASUS P5Q-EM boards
+  mb31          MacBook 3,1
+  sony-vaio-tt  Sony VAIO TT
   auto          auto-config reading BIOS (default)
 
 ALC861/660
@@ -348,6 +359,7 @@ STAC92HD71B*
   hp-m4         HP mini 1000
   hp-dv5        HP dv series
   hp-hdx        HP HDX series
+  hp-dv4-1222nr HP dv4-1222nr (with LED support)
   auto          BIOS setup (default)
 
 STAC92HD73*
diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt
index cfac20cf9e33..381908d8ca42 100644
--- a/Documentation/sound/alsa/Procfile.txt
+++ b/Documentation/sound/alsa/Procfile.txt
@@ -88,26 +88,34 @@ card*/pcm*/info
         substreams, etc.
 
 card*/pcm*/xrun_debug
-        This file appears when CONFIG_SND_DEBUG=y.
-        This shows the status of xrun (= buffer overrun/xrun) debug of
-        ALSA PCM middle layer, as an integer from 0 to 2.  The value
-        can be changed by writing to this file, such as
-
-                 # cat 2 > /proc/asound/card0/pcm0p/xrun_debug
-
-        When this value is greater than 0, the driver will show the
-        messages to kernel log when an xrun is detected.  The debug
-        message is shown also when the invalid H/W pointer is detected
-        at the update of periods (usually called from the interrupt
+        This file appears when CONFIG_SND_DEBUG=y and
+        CONFIG_PCM_XRUN_DEBUG=y.
+        This shows the status of xrun (= buffer overrun/xrun) and
+        invalid PCM position debug/check of ALSA PCM middle layer.
+        It takes an integer value, can be changed by writing to this
+        file, such as
+
+                 # cat 5 > /proc/asound/card0/pcm0p/xrun_debug
+
+        The value consists of the following bit flags:
+          bit 0 = Enable XRUN/jiffies debug messages
+          bit 1 = Show stack trace at XRUN / jiffies check
+          bit 2 = Enable additional jiffies check
+
+        When the bit 0 is set, the driver will show the messages to
+        kernel log when an xrun is detected.  The debug message is
+        shown also when the invalid H/W pointer is detected at the
+        update of periods (usually called from the interrupt
         handler).
 
-        When this value is greater than 1, the driver will show the
-        stack trace additionally.  This may help the debugging.
+        When the bit 1 is set, the driver will show the stack trace
+        additionally.  This may help the debugging.
 
-        Since 2.6.30, this option also enables the hwptr check using
+        Since 2.6.30, this option can enable the hwptr check using
         jiffies.  This detects spontaneous invalid pointer callback
         values, but can be lead to too much corrections for a (mostly
         buggy) hardware that doesn't give smooth pointer updates.
+        This feature is enabled via the bit 2.
 
 card*/pcm*/sub*/info
         The general information of this PCM sub-stream.
diff --git a/Documentation/sound/alsa/README.maya44 b/Documentation/sound/alsa/README.maya44
new file mode 100644
index 000000000000..0e41576fa13e
--- /dev/null
+++ b/Documentation/sound/alsa/README.maya44
@@ -0,0 +1,163 @@
+NOTE: The following is the original document of Rainer's patch that the
+current maya44 code based on.  Some contents might be obsoleted, but I
+keep here as reference -- tiwai
+
+----------------------------------------------------------------
+ 
+STATE OF DEVELOPMENT:
+
+This driver is being developed on the initiative of Piotr Makowski (oponek@gmail.com) and financed by Lars Bergmann.
+Development is carried out by Rainer Zimmermann (mail@lightshed.de).
+
+ESI provided a sample Maya44 card for the development work.
+
+However, unfortunately it has turned out difficult to get detailed programming information, so I (Rainer Zimmermann) had to find out some card-specific information by experiment and conjecture. Some information (in particular, several GPIO bits) is still missing.
+
+This is the first testing version of the Maya44 driver released to the alsa-devel mailing list (Feb 5, 2008).
+
+
+The following functions work, as tested by Rainer Zimmermann and Piotr Makowski:
+
+- playback and capture at all sampling rates
+- input/output level
+- crossmixing
+- line/mic switch
+- phantom power switch
+- analogue monitor a.k.a bypass
+
+
+The following functions *should* work, but are not fully tested:
+
+- Channel 3+4 analogue - S/PDIF input switching
+- S/PDIF output
+- all inputs/outputs on the M/IO/DIO extension card
+- internal/external clock selection
+
+
+*In particular, we would appreciate testing of these functions by anyone who has access to an M/IO/DIO extension card.*
+
+
+Things that do not seem to work:
+
+- The level meters ("multi track") in 'alsamixer' do not seem to react to signals in (if this is a bug, it would probably be in the existing ICE1724 code).
+
+- Ardour 2.1 seems to work only via JACK, not using ALSA directly or via OSS. This still needs to be tracked down.
+
+
+DRIVER DETAILS:
+
+the following files were added:
+
+pci/ice1724/maya44.c        - Maya44 specific code
+pci/ice1724/maya44.h
+pci/ice1724/ice1724.patch
+pci/ice1724/ice1724.h.patch - PROPOSED patch to ice1724.h (see SAMPLING RATES)
+i2c/other/wm8776.c  - low-level access routines for Wolfson WM8776 codecs 
+include/wm8776.h
+
+
+Note that the wm8776.c code is meant to be card-independent and does not actually register the codec with the ALSA infrastructure.
+This is done in maya44.c, mainly because some of the WM8776 controls are used in Maya44-specific ways, and should be named appropriately.
+
+
+the following files were created in pci/ice1724, simply #including the corresponding file from the alsa-kernel tree:
+
+wtm.h
+vt1720_mobo.h
+revo.h
+prodigy192.h
+pontis.h
+phase.h
+maya44.h
+juli.h
+aureon.h
+amp.h
+envy24ht.h
+se.h
+prodigy_hifi.h
+
+
+*I hope this is the correct way to do things.*
+
+
+SAMPLING RATES:
+
+The Maya44 card (or more exactly, the Wolfson WM8776 codecs) allow a maximum sampling rate of 192 kHz for playback and 92 kHz for capture.
+
+As the ICE1724 chip only allows one global sampling rate, this is handled as follows:
+
+* setting the sampling rate on any open PCM device on the maya44 card will always set the *global* sampling rate for all playback and capture channels.
+
+* In the current state of the driver, setting rates of up to 192 kHz is permitted even for capture devices.
+
+*AVOID CAPTURING AT RATES ABOVE 96kHz*, even though it may appear to work. The codec cannot actually capture at such rates, meaning poor quality.
+
+
+I propose some additional code for limiting the sampling rate when setting on a capture pcm device. However because of the global sampling rate, this logic would be somewhat problematic.
+
+The proposed code (currently deactivated) is in ice1712.h.patch, ice1724.c and maya44.c (in pci/ice1712).
+
+
+SOUND DEVICES:
+
+PCM devices correspond to inputs/outputs as follows (assuming Maya44 is card #0):
+
+hw:0,0 input - stereo, analog input 1+2
+hw:0,0 output - stereo, analog output 1+2
+hw:0,1 input - stereo, analog input 3+4 OR S/PDIF input
+hw:0,1 output - stereo, analog output 3+4 (and SPDIF out)
+
+
+NAMING OF MIXER CONTROLS:
+
+(for more information about the signal flow, please refer to the block diagram on p.24 of the ESI Maya44 manual, or in the ESI windows software).
+
+
+PCM: (digital) output level for channel 1+2
+PCM 1: same for channel 3+4
+
+Mic Phantom+48V: switch for +48V phantom power for electrostatic microphones on input 1/2.
+    Make sure this is not turned on while any other source is connected to input 1/2.
+    It might damage the source and/or the maya44 card.
+
+Mic/Line input: if switch is is on, input jack 1/2 is microphone input (mono), otherwise line input (stereo).
+
+Bypass: analogue bypass from ADC input to output for channel 1+2. Same as "Monitor" in the windows driver.
+Bypass 1: same for channel 3+4.
+
+Crossmix: cross-mixer from channels 1+2 to channels 3+4
+Crossmix 1: cross-mixer from channels 3+4 to channels 1+2
+
+IEC958 Output: switch for S/PDIF output.
+    This is not supported by the ESI windows driver.
+    S/PDIF should output the same signal as channel 3+4. [untested!]
+
+
+Digitial output selectors:
+
+    These switches allow a direct digital routing from the ADCs to the DACs.
+    Each switch determines where the digital input data to one of the DACs comes from.
+    They are not supported by the ESI windows driver.
+    For normal operation, they should all be set to "PCM out".
+
+H/W: Output source channel 1
+H/W 1: Output source channel 2
+H/W 2: Output source channel 3
+H/W 3: Output source channel 4
+
+H/W 4 ... H/W 9: unknown function, left in to enable testing.
+    Possibly some of these control S/PDIF output(s).
+    If these turn out to be unused, they will go away in later driver versions.
+
+Selectable values for each of the digital output selectors are:
+   "PCM out" -> DAC output of the corresponding channel (default setting)
+   "Input 1"...
+   "Input 4" -> direct routing from ADC output of the selected input channel
+
+
+--------
+
+Feb 14, 2008
+Rainer Zimmermann
+mail@lightshed.de
+
diff --git a/Documentation/sound/alsa/soc/dapm.txt b/Documentation/sound/alsa/soc/dapm.txt
index 9e6763264a2e..9ac842be9b4f 100644
--- a/Documentation/sound/alsa/soc/dapm.txt
+++ b/Documentation/sound/alsa/soc/dapm.txt
@@ -62,6 +62,7 @@ Audio DAPM widgets fall into a number of types:-
  o Mic        - Mic (and optional Jack)
  o Line       - Line Input/Output (and optional Jack)
  o Speaker    - Speaker
+ o Supply     - Power or clock supply widget used by other widgets.
  o Pre        - Special PRE widget (exec before all others)
  o Post       - Special POST widget (exec after all others)
 
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index f11ca7979fa6..322a00bb99d9 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -32,6 +32,7 @@ show up in /proc/sys/kernel:
 - kstack_depth_to_print       [ X86 only ]
 - l2cr                        [ PPC only ]
 - modprobe                    ==> Documentation/debugging-modules.txt
+- modules_disabled
 - msgmax
 - msgmnb
 - msgmni
@@ -184,6 +185,16 @@ kernel stack.
 
 ==============================================================
 
+modules_disabled:
+
+A toggle value indicating if modules are allowed to be loaded
+in an otherwise modular kernel.  This toggle defaults to off
+(0), but can be set true (1).  Once true, modules can be
+neither loaded nor unloaded, and the toggle cannot be set back
+to false.
+
+==============================================================
+
 osrelease, ostype & version:
 
 # cat osrelease
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
new file mode 100644
index 000000000000..f157d7594ea7
--- /dev/null
+++ b/Documentation/trace/events.txt
@@ -0,0 +1,90 @@
+                             Event Tracing
+
+                Documentation written by Theodore Ts'o
+                        Updated by Li Zefan
+
+1. Introduction
+===============
+
+Tracepoints (see Documentation/trace/tracepoints.txt) can be used
+without creating custom kernel modules to register probe functions
+using the event tracing infrastructure.
+
+Not all tracepoints can be traced using the event tracing system;
+the kernel developer must provide code snippets which define how the
+tracing information is saved into the tracing buffer, and how the
+tracing information should be printed.
+
+2. Using Event Tracing
+======================
+
+2.1 Via the 'set_event' interface
+---------------------------------
+
+The events which are available for tracing can be found in the file
+/debug/tracing/available_events.
+
+To enable a particular event, such as 'sched_wakeup', simply echo it
+to /debug/tracing/set_event. For example:
+
+        # echo sched_wakeup >> /debug/tracing/set_event
+
+[ Note: '>>' is necessary, otherwise it will firstly disable
+  all the events. ]
+
+To disable an event, echo the event name to the set_event file prefixed
+with an exclamation point:
+
+        # echo '!sched_wakeup' >> /debug/tracing/set_event
+
+To disable all events, echo an empty line to the set_event file:
+
+        # echo > /debug/tracing/set_event
+
+To enable all events, echo '*:*' or '*:' to the set_event file:
+
+        # echo *:* > /debug/tracing/set_event
+
+The events are organized into subsystems, such as ext4, irq, sched,
+etc., and a full event name looks like this: <subsystem>:<event>.  The
+subsystem name is optional, but it is displayed in the available_events
+file.  All of the events in a subsystem can be specified via the syntax
+"<subsystem>:*"; for example, to enable all irq events, you can use the
+command:
+
+        # echo 'irq:*' > /debug/tracing/set_event
+
+2.2 Via the 'enable' toggle
+---------------------------
+
+The events available are also listed in /debug/tracing/events/ hierarchy
+of directories.
+
+To enable event 'sched_wakeup':
+
+        # echo 1 > /debug/tracing/events/sched/sched_wakeup/enable
+
+To disable it:
+
+        # echo 0 > /debug/tracing/events/sched/sched_wakeup/enable
+
+To enable all events in sched subsystem:
+
+        # echo 1 > /debug/tracing/events/sched/enable
+
+To eanble all events:
+
+        # echo 1 > /debug/tracing/events/enable
+
+When reading one of these enable files, there are four results:
+
+ 0 - all events this file affects are disabled
+ 1 - all events this file affects are enabled
+ X - there is a mixture of events enabled and disabled
+ ? - this file does not affect any event
+
+3. Defining an event-enabled tracepoint
+=======================================
+
+See The example provided in samples/trace_events
+
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index fd9a3e693813..2a82d8602944 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -179,7 +179,7 @@ Here is the list of current tracers that may be configured.
 
         Function call tracer to trace all kernel functions.
 
-  "function_graph_tracer"
+  "function_graph"
 
         Similar to the function tracer except that the
         function tracer probes the functions on their entry
@@ -518,9 +518,18 @@ 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
+   Kernel Space                     User Space
+ ===============================================================
+   0(high) to  98(low)     user RT priority 99(high) to 1(low)
+                           with SCHED_RR or SCHED_FIFO
+ ---------------------------------------------------------------
+  99                       sched_priority is not used in scheduling
+                           decisions(it must be specified as 0)
+ ---------------------------------------------------------------
+ 100(high) to 139(low)     user nice -20(high) to 19(low)
+ ---------------------------------------------------------------
+ 140                       idle task priority
+ ---------------------------------------------------------------
 
 The task states are:
 
diff --git a/Documentation/trace/power.txt b/Documentation/trace/power.txt
new file mode 100644
index 000000000000..cd805e16dc27
--- /dev/null
+++ b/Documentation/trace/power.txt
@@ -0,0 +1,17 @@
+The power tracer collects detailed information about C-state and P-state
+transitions, instead of just looking at the high-level "average"
+information.
+
+There is a helper script found in scrips/tracing/power.pl in the kernel
+sources which can be used to parse this information and create a
+Scalable Vector Graphics (SVG) picture from the trace data.
+
+To use this tracer:
+
+        echo 0 > /sys/kernel/debug/tracing/tracing_enabled
+        echo power > /sys/kernel/debug/tracing/current_tracer
+        echo 1 > /sys/kernel/debug/tracing/tracing_enabled
+        sleep 1
+        echo 0 > /sys/kernel/debug/tracing/tracing_enabled
+        cat /sys/kernel/debug/tracing/trace | \
+                perl scripts/tracing/power.pl > out.sv
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index e0203662f9e9..8da3a795083f 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -50,6 +50,10 @@ Protocol 2.08:	(Kernel 2.6.26) Added crc32 checksum and ELF format
 Protocol 2.09:  (Kernel 2.6.26) Added a field of 64-bit physical
                 pointer to single linked list of struct setup_data.
 
+Protocol 2.10:  (Kernel 2.6.31) Added a protocol for relaxed alignment
+                beyond the kernel_alignment added, new init_size and
+                pref_address fields.  Added extended boot loader IDs.
+
 **** MEMORY LAYOUT
 
 The traditional memory map for the kernel loader, used for Image or
@@ -168,12 +172,13 @@ Offset	Proto	Name		Meaning
 021C/4  2.00+   ramdisk_size    initrd size (set by boot loader)
 0220/4  2.00+   bootsect_kludge DO NOT USE - for bootsect.S use only
 0224/2  2.01+   heap_end_ptr    Free memory after setup end
-0226/2  N/A     pad1            Unused
+0226/1  2.02+(3 ext_loader_ver  Extended boot loader version
+0227/1  2.02+(3 ext_loader_type Extended boot loader ID
 0228/4  2.02+   cmd_line_ptr    32-bit pointer to the kernel command line
 022C/4  2.03+   ramdisk_max     Highest legal initrd address
 0230/4  2.05+   kernel_alignment Physical addr alignment required for kernel
 0234/1  2.05+   relocatable_kernel Whether kernel is relocatable or not
-0235/1  N/A     pad2            Unused
+0235/1  2.10+   min_alignment   Minimum alignment, as a power of two
 0236/2  N/A     pad3            Unused
 0238/4  2.06+   cmdline_size    Maximum size of the kernel command line
 023C/4  2.07+   hardware_subarch Hardware subarchitecture
@@ -182,6 +187,8 @@ Offset	Proto	Name		Meaning
 024C/4  2.08+   payload_length  Length of kernel payload
 0250/8  2.09+   setup_data      64-bit physical pointer to linked list
                                 of struct setup_data
+0258/8  2.10+   pref_address    Preferred loading address
+0260/4  2.10+   init_size       Linear memory required during initialization
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.
@@ -190,6 +197,8 @@ Offset	Proto	Name		Meaning
     field are unusable, which means the size of a bzImage kernel
     cannot be determined.
 
+(3) Ignored, but safe to set, for boot protocols 2.02-2.09.
+
 If the "HdrS" (0x53726448) magic number is not found at offset 0x202,
 the boot protocol version is "old".  Loading an old kernel, the
 following parameters should be assumed:
@@ -343,18 +352,32 @@ Protocol:	2.00+
   0xTV here, where T is an identifier for the boot loader and V is
   a version number.  Otherwise, enter 0xFF here.
 
+  For boot loader IDs above T = 0xD, write T = 0xE to this field and
+  write the extended ID minus 0x10 to the ext_loader_type field.
+  Similarly, the ext_loader_ver field can be used to provide more than
+  four bits for the bootloader version.
+
+  For example, for T = 0x15, V = 0x234, write:
+
+  type_of_loader  <- 0xE4
+  ext_loader_type <- 0x05
+  ext_loader_ver  <- 0x23
+
   Assigned boot loader ids:
         0  LILO                 (0x00 reserved for pre-2.00 bootloader)
         1  Loadlin
         2  bootsect-loader      (0x20, all other values reserved)
-        3  SYSLINUX
-        4  EtherBoot
+        3  Syslinux
+        4  Etherboot/gPXE
         5  ELILO
         7  GRUB
-        8  U-BOOT
+        8  U-Boot
         9  Xen
         A  Gujin
         B  Qemu
+        C  Arcturus Networks uCbootloader
+        E  Extended             (see ext_loader_type)
+        F  Special              (0xFF = undefined)
 
   Please contact <hpa@zytor.com> if you need a bootloader ID
   value assigned.
@@ -453,6 +476,35 @@ Protocol:	2.01+
   Set this field to the offset (from the beginning of the real-mode
   code) of the end of the setup stack/heap, minus 0x0200.
 
+Field name:     ext_loader_ver
+Type:           write (optional)
+Offset/size:    0x226/1
+Protocol:       2.02+
+
+  This field is used as an extension of the version number in the
+  type_of_loader field.  The total version number is considered to be
+  (type_of_loader & 0x0f) + (ext_loader_ver << 4).
+
+  The use of this field is boot loader specific.  If not written, it
+  is zero.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
+Field name:     ext_loader_type
+Type:           write (obligatory if (type_of_loader & 0xf0) == 0xe0)
+Offset/size:    0x227/1
+Protocol:       2.02+
+
+  This field is used as an extension of the type number in
+  type_of_loader field.  If the type in type_of_loader is 0xE, then
+  the actual type is (ext_loader_type + 0x10).
+
+  This field is ignored if the type in type_of_loader is not 0xE.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
 Field name:     cmd_line_ptr
 Type:           write (obligatory)
 Offset/size:    0x228/4
@@ -482,11 +534,19 @@ Protocol:	2.03+
   0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
 
 Field name:     kernel_alignment
-Type:           read (reloc)
+Type:           read/modify (reloc)
 Offset/size:    0x230/4
-Protocol:       2.05+
+Protocol:       2.05+ (read), 2.10+ (modify)
+
+  Alignment unit required by the kernel (if relocatable_kernel is
+  true.)  A relocatable kernel that is loaded at an alignment
+  incompatible with the value in this field will be realigned during
+  kernel initialization.
 
-  Alignment unit required by the kernel (if relocatable_kernel is true.)
+  Starting with protocol version 2.10, this reflects the kernel
+  alignment preferred for optimal performance; it is possible for the
+  loader to modify this field to permit a lesser alignment.  See the
+  min_alignment and pref_address field below.
 
 Field name:     relocatable_kernel
 Type:           read (reloc)
@@ -498,6 +558,22 @@ Protocol:	2.05+
   After loading, the boot loader must set the code32_start field to
   point to the loaded code, or to a boot loader hook.
 
+Field name:     min_alignment
+Type:           read (reloc)
+Offset/size:    0x235/1
+Protocol:       2.10+
+
+  This field, if nonzero, indicates as a power of two the minimum
+  alignment required, as opposed to preferred, by the kernel to boot.
+  If a boot loader makes use of this field, it should update the
+  kernel_alignment field with the alignment unit desired; typically:
+
+        kernel_alignment = 1 << min_alignment
+
+  There may be a considerable performance cost with an excessively
+  misaligned kernel.  Therefore, a loader should typically try each
+  power-of-two alignment from kernel_alignment down to this alignment.
+
 Field name:     cmdline_size
 Type:           read
 Offset/size:    0x238/4
@@ -582,6 +658,36 @@ Protocol:	2.09+
   sure to consider the case where the linked list already contains
   entries.
 
+Field name:     pref_address
+Type:           read (reloc)
+Offset/size:    0x258/8
+Protocol:       2.10+
+
+  This field, if nonzero, represents a preferred load address for the
+  kernel.  A relocating bootloader should attempt to load at this
+  address if possible.
+
+  A non-relocatable kernel will unconditionally move itself and to run
+  at this address.
+
+Field name:     init_size
+Type:           read
+Offset/size:    0x25c/4
+
+  This field indicates the amount of linear contiguous memory starting
+  at the kernel runtime start address that the kernel needs before it
+  is capable of examining its memory map.  This is not the same thing
+  as the total amount of memory the kernel needs to boot, but it can
+  be used by a relocating boot loader to help select a safe load
+  address for the kernel.
+
+  The kernel runtime start address is determined by the following algorithm:
+
+  if (relocatable_kernel)
+        runtime_start = align_up(load_address, kernel_alignment)
+  else
+        runtime_start = pref_address
+
 
 **** THE IMAGE CHECKSUM
 
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 34c13040a718..2db5893d6c97 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -150,11 +150,6 @@ NUMA
                 Otherwise, the remaining system RAM is allocated to an
                 additional node.
 
-  numa=hotadd=percent
-                Only allow hotadd memory to preallocate page structures upto
-                percent of already available memory.
-                numa=hotadd=0 will disable hotadd memory.
-
 ACPI
 
   acpi=off      Don't enable ACPI
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 29b52b14d0b4..d6498e3cd713 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -6,10 +6,11 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
-ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
-ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
-ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
-ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
+ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
+ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
+ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
+ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
+ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space