summaryrefslogtreecommitdiffstats
path: root/Documentation
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/00-INDEX2
-rw-r--r--Documentation/DMA-API.txt2
-rw-r--r--Documentation/DocBook/kernel-api.tmpl5
-rw-r--r--Documentation/RCU/checklist.txt2
-rw-r--r--Documentation/RCU/rcuref.txt16
-rw-r--r--Documentation/RCU/whatisRCU.txt2
-rw-r--r--Documentation/SELinux.txt27
-rw-r--r--Documentation/block/deadline-iosched.txt14
-rw-r--r--Documentation/cdrom/ide-cd3
-rw-r--r--Documentation/cpu-freq/index.txt10
-rw-r--r--Documentation/hwmon/adt747318
-rw-r--r--Documentation/hwmon/sysfs-interface12
-rw-r--r--Documentation/kernel-doc-nano-HOWTO.txt4
-rw-r--r--Documentation/kernel-parameters.txt16
-rw-r--r--Documentation/s390/CommonIO11
-rw-r--r--Documentation/scheduler/sched-design-CFS.txt395
-rw-r--r--Documentation/scsi/scsi_fc_transport.txt36
-rw-r--r--Documentation/sound/alsa/ALSA-Configuration.txt62
-rw-r--r--Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl62
-rw-r--r--Documentation/x86/00-INDEX4
-rw-r--r--Documentation/x86/boot.txt (renamed from Documentation/x86/i386/boot.txt)2
-rw-r--r--Documentation/x86/mtrr.txt (renamed from Documentation/mtrr.txt)4
-rw-r--r--Documentation/x86/pat.txt54
-rw-r--r--Documentation/x86/usb-legacy-support.txt (renamed from Documentation/x86/i386/usb-legacy-support.txt)0
-rw-r--r--Documentation/x86/x86_64/boot-options.txt4
-rw-r--r--Documentation/x86/zero-page.txt (renamed from Documentation/x86/i386/zero-page.txt)0
26 files changed, 514 insertions, 253 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 5b5aba404aa..73060819ed9 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -251,8 +251,6 @@ mono.txt
- how to execute Mono-based .NET binaries with the help of BINFMT_MISC.
moxa-smartio
- file with info on installing/using Moxa multiport serial driver.
-mtrr.txt
- - how to use PPro Memory Type Range Registers to increase performance.
mutex-design.txt
- info on the generic mutex subsystem.
namespaces/
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index d8b63d164e4..b8e86460046 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -337,7 +337,7 @@ With scatterlists, you use the resulting mapping like this:
int i, count = dma_map_sg(dev, sglist, nents, direction);
struct scatterlist *sg;
- for (i = 0, sg = sglist; i < count; i++, sg++) {
+ for_each_sg(sglist, sg, count, i) {
hw_address[i] = sg_dma_address(sg);
hw_len[i] = sg_dma_len(sg);
}
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index b7b1482f6e0..9d0058e788e 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -283,6 +283,7 @@ X!Earch/x86/kernel/mca_32.c
<chapter id="security">
<title>Security Framework</title>
!Isecurity/security.c
+!Esecurity/inode.c
</chapter>
<chapter id="audit">
@@ -364,6 +365,10 @@ X!Edrivers/pnp/system.c
!Eblock/blk-barrier.c
!Eblock/blk-tag.c
!Iblock/blk-tag.c
+!Eblock/blk-integrity.c
+!Iblock/blktrace.c
+!Iblock/genhd.c
+!Eblock/genhd.c
</chapter>
<chapter id="chrdev">
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index cf5562cbe35..6e253407b3d 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -210,7 +210,7 @@ over a rather long period of time, but improvements are always welcome!
number of updates per grace period.
9. All RCU list-traversal primitives, which include
- rcu_dereference(), list_for_each_rcu(), list_for_each_entry_rcu(),
+ rcu_dereference(), list_for_each_entry_rcu(),
list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
must be either within an RCU read-side critical section or
must be protected by appropriate update-side locks. RCU
diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt
index 451de2ad832..4202ad09313 100644
--- a/Documentation/RCU/rcuref.txt
+++ b/Documentation/RCU/rcuref.txt
@@ -29,9 +29,9 @@ release_referenced() delete()
}
If this list/array is made lock free using RCU as in changing the
-write_lock() in add() and delete() to spin_lock and changing read_lock
-in search_and_reference to rcu_read_lock(), the atomic_get in
-search_and_reference could potentially hold reference to an element which
+write_lock() in add() and delete() to spin_lock() and changing read_lock()
+in search_and_reference() to rcu_read_lock(), the atomic_inc() in
+search_and_reference() could potentially hold reference to an element which
has already been deleted from the list/array. Use atomic_inc_not_zero()
in this scenario as follows:
@@ -40,20 +40,20 @@ add() search_and_reference()
{ {
alloc_object rcu_read_lock();
... search_for_element
- atomic_set(&el->rc, 1); if (atomic_inc_not_zero(&el->rc)) {
- write_lock(&list_lock); rcu_read_unlock();
+ atomic_set(&el->rc, 1); if (!atomic_inc_not_zero(&el->rc)) {
+ spin_lock(&list_lock); rcu_read_unlock();
return FAIL;
add_element }
... ...
- write_unlock(&list_lock); rcu_read_unlock();
+ spin_unlock(&list_lock); rcu_read_unlock();
} }
3. 4.
release_referenced() delete()
{ {
- ... write_lock(&list_lock);
+ ... spin_lock(&list_lock);
if (atomic_dec_and_test(&el->rc)) ...
call_rcu(&el->head, el_free); delete_element
- ... write_unlock(&list_lock);
+ ... spin_unlock(&list_lock);
} ...
if (atomic_dec_and_test(&el->rc))
call_rcu(&el->head, el_free);
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index e04d643a9f5..96170824a71 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -786,8 +786,6 @@ RCU pointer/list traversal:
list_for_each_entry_rcu
hlist_for_each_entry_rcu
- list_for_each_rcu (to be deprecated in favor of
- list_for_each_entry_rcu)
list_for_each_continue_rcu (to be deprecated in favor of new
list_for_each_entry_continue_rcu)
diff --git a/Documentation/SELinux.txt b/Documentation/SELinux.txt
new file mode 100644
index 00000000000..07eae00f331
--- /dev/null
+++ b/Documentation/SELinux.txt
@@ -0,0 +1,27 @@
+If you want to use SELinux, chances are you will want
+to use the distro-provided policies, or install the
+latest reference policy release from
+ http://oss.tresys.com/projects/refpolicy
+
+However, if you want to install a dummy policy for
+testing, you can do using 'mdp' provided under
+scripts/selinux. Note that this requires the selinux
+userspace to be installed - in particular you will
+need checkpolicy to compile a kernel, and setfiles and
+fixfiles to label the filesystem.
+
+ 1. Compile the kernel with selinux enabled.
+ 2. Type 'make' to compile mdp.
+ 3. Make sure that you are not running with
+ SELinux enabled and a real policy. If
+ you are, reboot with selinux disabled
+ before continuing.
+ 4. Run install_policy.sh:
+ cd scripts/selinux
+ sh install_policy.sh
+
+Step 4 will create a new dummy policy valid for your
+kernel, with a single selinux user, role, and type.
+It will compile the policy, will set your SELINUXTYPE to
+dummy in /etc/selinux/config, install the compiled policy
+as 'dummy', and relabel your filesystem.
diff --git a/Documentation/block/deadline-iosched.txt b/Documentation/block/deadline-iosched.txt
index c23cab13c3d..72576769e0f 100644
--- a/Documentation/block/deadline-iosched.txt
+++ b/Documentation/block/deadline-iosched.txt
@@ -30,12 +30,18 @@ write_expire (in ms)
Similar to read_expire mentioned above, but for writes.
-fifo_batch
+fifo_batch (number of requests)
----------
-When a read request expires its deadline, we must move some requests from
-the sorted io scheduler list to the block device dispatch queue. fifo_batch
-controls how many requests we move.
+Requests are grouped into ``batches'' of a particular data direction (read or
+write) which are serviced in increasing sector order. To limit extra seeking,
+deadline expiries are only checked between batches. fifo_batch controls the
+maximum number of requests per batch.
+
+This parameter tunes the balance between per-request latency and aggregate
+throughput. When low latency is the primary concern, smaller is better (where
+a value of 1 yields first-come first-served behaviour). Increasing fifo_batch
+generally improves throughput, at the cost of latency variation.
writes_starved (number of dispatches)
diff --git a/Documentation/cdrom/ide-cd b/Documentation/cdrom/ide-cd
index 91c0dcc6fa5..2c558cd6c1e 100644
--- a/Documentation/cdrom/ide-cd
+++ b/Documentation/cdrom/ide-cd
@@ -145,8 +145,7 @@ useful for reading photocds.
To play an audio CD, you should first unmount and remove any data
CDROM. Any of the CDROM player programs should then work (workman,
-workbone, cdplayer, etc.). Lacking anything else, you could use the
-cdtester program in Documentation/cdrom/sbpcd.
+workbone, cdplayer, etc.).
On a few drives, you can read digital audio directly using a program
such as cdda2wav. The only types of drive which I've heard support
diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt
index ffdb5323df3..3d0b915035b 100644
--- a/Documentation/cpu-freq/index.txt
+++ b/Documentation/cpu-freq/index.txt
@@ -35,11 +35,9 @@ Mailing List
------------
There is a CPU frequency changing CVS commit and general list where
you can report bugs, problems or submit patches. To post a message,
-send an email to cpufreq@lists.linux.org.uk, to subscribe go to
-http://lists.linux.org.uk/mailman/listinfo/cpufreq. Previous post to the
-mailing list are available to subscribers at
-http://lists.linux.org.uk/mailman/private/cpufreq/.
-
+send an email to cpufreq@vger.kernel.org, to subscribe go to
+http://vger.kernel.org/vger-lists.html#cpufreq and follow the
+instructions there.
Links
-----
@@ -50,7 +48,7 @@ how to access the CVS repository:
* http://cvs.arm.linux.org.uk/
the CPUFreq Mailing list:
-* http://lists.linux.org.uk/mailman/listinfo/cpufreq
+* http://vger.kernel.org/vger-lists.html#cpufreq
Clock and voltage scaling for the SA-1100:
* http://www.lartmaker.nl/projects/scaling
diff --git a/Documentation/hwmon/adt7473 b/Documentation/hwmon/adt7473
index 2126de34c71..1cbf671822e 100644
--- a/Documentation/hwmon/adt7473
+++ b/Documentation/hwmon/adt7473
@@ -14,14 +14,14 @@ Description
This driver implements support for the Analog Devices ADT7473 chip family.
-The LM85 uses the 2-wire interface compatible with the SMBUS 2.0
+The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
specification. Using an analog to digital converter it measures three (3)
-temperatures and two (2) voltages. It has three (3) 16-bit counters for
+temperatures and two (2) voltages. It has four (4) 16-bit counters for
measuring fan speed. There are three (3) PWM outputs that can be used
to control fan speed.
A sophisticated control system for the PWM outputs is designed into the
-LM85 that allows fan speed to be adjusted automatically based on any of the
+ADT7473 that allows fan speed to be adjusted automatically based on any of the
three temperature sensors. Each PWM output is individually adjustable and
programmable. Once configured, the ADT7473 will adjust the PWM outputs in
response to the measured temperatures without further host intervention.
@@ -46,14 +46,6 @@ from the raw value to get the temperature value.
The Analog Devices datasheet is very detailed and describes a procedure for
determining an optimal configuration for the automatic PWM control.
-Hardware Configurations
------------------------
-
-The ADT7473 chips have an optional SMBALERT output that can be used to
-signal the chipset in case a limit is exceeded or the temperature sensors
-fail. Individual sensor interrupts can be masked so they won't trigger
-SMBALERT. The SMBALERT output if configured replaces the PWM2 function.
-
Configuration Notes
-------------------
@@ -61,8 +53,8 @@ Besides standard interfaces driver adds the following:
* PWM Control
-* pwm#_auto_point1_pwm and pwm#_auto_point1_temp and
-* pwm#_auto_point2_pwm and pwm#_auto_point2_temp -
+* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
+* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
point1: Set the pwm speed at a lower temperature bound.
point2: Set the pwm speed at a higher temperature bound.
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 2d845730d4e..6dbfd5efd99 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -329,6 +329,10 @@ power[1-*]_average Average power use
Unit: microWatt
RO
+power[1-*]_average_interval Power use averaging interval
+ Unit: milliseconds
+ RW
+
power[1-*]_average_highest Historical average maximum power use
Unit: microWatt
RO
@@ -354,6 +358,14 @@ power[1-*]_reset_history Reset input_highest, input_lowest,
WO
**********
+* Energy *
+**********
+
+energy[1-*]_input Cumulative energy use
+ Unit: microJoule
+ RO
+
+**********
* Alarms *
**********
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index 0bd32748a46..c6841eee959 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -168,10 +168,10 @@ if ($#ARGV < 0) {
mkdir $ARGV[0],0777;
$state = 0;
while (<STDIN>) {
- if (/^\.TH \"[^\"]*\" 4 \"([^\"]*)\"/) {
+ if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) {
if ($state == 1) { close OUT }
$state = 1;
- $fn = "$ARGV[0]/$1.4";
+ $fn = "$ARGV[0]/$1.9";
print STDERR "Creating $fn\n";
open OUT, ">$fn" or die "can't open $fn: $!\n";
print OUT $_;
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1150444a21a..d0fff6302f6 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -463,12 +463,6 @@ and is between 256 and 4096 characters. It is defined in the file
Range: 0 - 8192
Default: 64
- disable_8254_timer
- enable_8254_timer
- [IA32/X86_64] Disable/Enable interrupt 0 timer routing
- over the 8254 in addition to over the IO-APIC. The
- kernel tries to set a sensible default.
-
hpet= [X86-32,HPET] option to control HPET usage
Format: { enable (default) | disable | force }
disable: disable HPET and use PIT instead
@@ -1020,6 +1014,10 @@ and is between 256 and 4096 characters. It is defined in the file
(only serial suported for now)
Format: <serial_device>[,baud]
+ kmac= [MIPS] korina ethernet MAC address.
+ Configure the RouterBoard 532 series on-chip
+ Ethernet adapter MAC address.
+
l2cr= [PPC]
l3cr= [PPC]
@@ -1882,6 +1880,12 @@ and is between 256 and 4096 characters. It is defined in the file
shapers= [NET]
Maximal number of shapers.
+ show_msr= [x86] show boot-time MSR settings
+ Format: { <integer> }
+ Show boot-time (BIOS-initialized) MSR settings.
+ The parameter means the number of CPUs to show,
+ for example 1 means boot CPU only.
+
sim710= [SCSI,HW]
See header of drivers/scsi/sim710.c.
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index bf0baa19ec2..339207d11d9 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -70,13 +70,19 @@ Command line parameters
Note: While already known devices can be added to the list of devices to be
ignored, there will be no effect on then. However, if such a device
- disappears and then reappears, it will then be ignored.
+ disappears and then reappears, it will then be ignored. To make
+ known devices go away, you need the "purge" command (see below).
For example,
"echo add 0.0.a000-0.0.accc, 0.0.af00-0.0.afff > /proc/cio_ignore"
will add 0.0.a000-0.0.accc and 0.0.af00-0.0.afff to the list of ignored
devices.
+ You can remove already known but now ignored devices via
+ "echo purge > /proc/cio_ignore"
+ All devices ignored but still registered and not online (= not in use)
+ will be deregistered and thus removed from the system.
+
The devices can be specified either by bus id (0.x.abcd) or, for 2.4 backward
compatibility, by the device number in hexadecimal (0xabcd or abcd). Device
numbers given as 0xabcd will be interpreted as 0.0.abcd.
@@ -98,8 +104,7 @@ debugfs entries
handling).
- /sys/kernel/debug/s390dbf/cio_msg/sprintf
- Various debug messages from the common I/O-layer, including messages
- printed when cio_msg=yes.
+ Various debug messages from the common I/O-layer.
- /sys/kernel/debug/s390dbf/cio_trace/hex_ascii
Logs the calling of functions in the common I/O-layer and, if applicable,
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 88bcb876733..9d8eb553884 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -1,151 +1,242 @@
+ =============
+ CFS Scheduler
+ =============
-This is the CFS scheduler.
-
-80% of CFS's design can be summed up in a single sentence: CFS basically
-models an "ideal, precise multi-tasking CPU" on real hardware.
-
-"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100%
-physical power and which can run each task at precise equal speed, in
-parallel, each at 1/nr_running speed. For example: if there are 2 tasks
-running then it runs each at 50% physical power - totally in parallel.
-
-On real hardware, we can run only a single task at once, so while that
-one task runs, the other tasks that are waiting for the CPU are at a
-disadvantage - the current task gets an unfair amount of CPU time. In
-CFS this fairness imbalance is expressed and tracked via the per-task
-p->wait_runtime (nanosec-unit) value. "wait_runtime" is the amount of
-time the task should now run on the CPU for it to become completely fair
-and balanced.
-
-( small detail: on 'ideal' hardware, the p->wait_runtime value would
- always be zero - no task would ever get 'out of balance' from the
- 'ideal' share of CPU time. )
-
-CFS's task picking logic is based on this p->wait_runtime value and it
-is thus very simple: it always tries to run the task with the largest
-p->wait_runtime value. In other words, CFS tries to run the task with
-the 'gravest need' for more CPU time. So CFS always tries to split up
-CPU time between runnable tasks as close to 'ideal multitasking
-hardware' as possible.
-
-Most of the rest of CFS's design just falls out of this really simple
-concept, with a few add-on embellishments like nice levels,
-multiprocessing and various algorithm variants to recognize sleepers.
-
-In practice it works like this: the system runs a task a bit, and when
-the task schedules (or a scheduler tick happens) the task's CPU usage is
-'accounted for': the (small) time it just spent using the physical CPU
-is deducted from p->wait_runtime. [minus the 'fair share' it would have
-gotten anyway]. Once p->wait_runtime gets low enough so that another
-task becomes the 'leftmost task' of the time-ordered rbtree it maintains
-(plus a small amount of 'granularity' distance relative to the leftmost
-task so that we do not over-schedule tasks and trash the cache) then the
-new leftmost task is picked and the current task is preempted.
-
-The rq->fair_clock value tracks the 'CPU time a runnable task would have
-fairly gotten, had it been runnable during that time'. So by using
-rq->fair_clock values we can accurately timestamp and measure the
-'expected CPU time' a task should have gotten. All runnable tasks are
-sorted in the rbtree by the "rq->fair_clock - p->wait_runtime" key, and
-CFS picks the 'leftmost' task and sticks to it. As the system progresses
-forwards, newly woken tasks are put into the tree more and more to the
-right - slowly but surely giving a chance for every task to become the
-'leftmost task' and thus get on the CPU within a deterministic amount of
-time.
-
-Some implementation details:
-
- - the introduction of Scheduling Classes: an extensible hierarchy of
- scheduler modules. These modules encapsulate scheduling policy
- details and are handled by the scheduler core without the core
- code assuming about them too much.
-
- - sched_fair.c implements the 'CFS desktop scheduler': it is a
- replacement for the vanilla scheduler's SCHED_OTHER interactivity
- code.
-
- I'd like to give credit to Con Kolivas for the general approach here:
- he has proven via RSDL/SD that 'fair scheduling' is possible and that
- it results in better desktop scheduling. Kudos Con!
-
- The CFS patch uses a completely different approach and implementation
- from RSDL/SD. My goal was to make CFS's interactivity quality exceed
- that of RSDL/SD, which is a high standard to meet :-) Testing
- feedback is welcome to decide this one way or another. [ and, in any
- case, all of SD's logic could be added via a kernel/sched_sd.c module
- as well, if Con is interested in such an approach. ]
-
- CFS's design is quite radical: it does not use runqueues, it uses a
- time-ordered rbtree to build a 'timeline' of future task execution,
- and thus has no 'array switch' artifacts (by which both the vanilla
- scheduler and RSDL/SD are affected).
-
- CFS uses nanosecond granularity accounting and does not rely on any
- jiffies or other HZ detail. Thus the CFS scheduler has no notion of
- 'timeslices' and has no heuristics whatsoever. There is only one
- central tunable (you have to switch on CONFIG_SCHED_DEBUG):
-
- /proc/sys/kernel/sched_granularity_ns
-
- which can be used to tune the scheduler from 'desktop' (low
- latencies) to 'server' (good batching) workloads. It defaults to a
- setting suitable for desktop workloads. SCHED_BATCH is handled by the
- CFS scheduler module too.
-
- Due to its design, the CFS scheduler is not prone to any of the
- 'attacks' that exist today against the heuristics of the stock
- scheduler: fiftyp.c, thud.c, chew.c, ring-test.c, massive_intr.c all
- work fine and do not impact interactivity and produce the expected
- behavior.
-
- the CFS scheduler has a much stronger handling of nice levels and
- SCHED_BATCH: both types of workloads should be isolated much more
- agressively than under the vanilla scheduler.
-
- ( another detail: due to nanosec accounting and timeline sorting,
- sched_yield() support is very simple under CFS, and in fact under
- CFS sched_yield() behaves much better than under any other
- scheduler i have tested so far. )
-
- - sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler
- way than the vanilla scheduler does. It uses 100 runqueues (for all
- 100 RT priority levels, instead of 140 in the vanilla scheduler)
- and it needs no expired array.
-
- - reworked/sanitized SMP load-balancing: the runqueue-walking
- assumptions are gone from the load-balancing code now, and
- iterators of the scheduling modules are used. The balancing code got
- quite a bit simpler as a result.
-
-
-Group scheduler extension to CFS
-================================
-
-Normally the scheduler operates on individual tasks and strives to provide
-fair CPU time to each task. Sometimes, it may be desirable to group tasks
-and provide fair CPU time to each such task group. For example, it may
-be desirable to first provide fair CPU time to each user on the system
-and then to each task belonging to a user.
-
-CONFIG_FAIR_GROUP_SCHED strives to achieve exactly that. It lets
-SCHED_NORMAL/BATCH tasks be be grouped and divides CPU time fairly among such
-groups. At present, there are two (mutually exclusive) mechanisms to group
-tasks for CPU bandwidth control purpose:
-
- - Based on user id (CONFIG_FAIR_USER_SCHED)
- In this option, tasks are grouped according to their user id.
- - Based on "cgroup" pseudo filesystem (CONFIG_FAIR_CGROUP_SCHED)
- This options lets the administrator create arbitrary groups
- of tasks, using the "cgroup" pseudo filesystem. See
- Documentation/cgroups.txt for more information about this
- filesystem.
-Only one of these options to group tasks can be chosen and not both.
+1. OVERVIEW
+
+CFS stands for "Completely Fair Scheduler," and is the new "desktop" process
+scheduler implemented by Ingo Molnar and merged in Linux 2.6.23. It is the
+replacement for the previous vanilla scheduler's SCHED_OTHER interactivity
+code.
+
+80% of CFS's design can be summed up in a single sentence: CFS basically models
+an "ideal, precise multi-tasking CPU" on real hardware.
+
+"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100% physical
+power and which can run each task at precise equal speed, in parallel, each at
+1/nr_running speed. For example: if there are 2 tasks running, then it runs
+each at 50% physical power --- i.e., actually in parallel.
+
+On real hardware, we can run only a single task at once, so we have to
+introduce the concept of "virtual runtime." The virtual runtime of a task
+specifies when its next timeslice would start execution on the ideal
+multi-tasking CPU described above. In practice, the virtual runtime of a task
+is its actual runtime normalized to the total number of running tasks.
+
+
+
+2. FEW IMPLEMENTATION DETAILS
+
+In CFS the virtual runtime is expressed and tracked via the per-task
+p->se.vruntime (nanosec-unit) value. This way, it's possible to accurately
+timestamp and measure the "expected CPU time" a task should have gotten.
+
+[ small detail: on "ideal" hardware, at any time all tasks would have the same
+ p->se.vruntime value --- i.e., tasks would execute simultaneously and no task
+ would ever get "out of balance" from the "ideal" share of CPU time. ]
+
+CFS's task picking logic is based on this p->se.vruntime value and it is thus
+very simple: it always tries to run the task with the smallest p->se.vruntime
+value (i.e., the task which executed least so far). CFS always tries to split
+up CPU time between runnable tasks as close to "ideal multitasking hardware" as
+possible.
+
+Most of the rest of CFS's design just falls out of this really simple concept,
+with a few add-on embellishments like nice levels, multiprocessing and various
+algorithm variants to recognize sleepers.
+
+
+
+3. THE RBTREE
+
+CFS's design is quite radical: it does not use the old data structures for the
+runqueues, but it uses a time-ordered rbtree to build a "timeline" of future
+task execution, and thus has no "array switch" artifacts (by which both the
+previous vanilla scheduler and RSDL/SD are affected).
+
+CFS also maintains the rq->cfs.min_vruntime value, which is a monotonic
+increasing value tracking the smallest vruntime among all tasks in the
+runqueue. The total amount of work done by the system is tracked using
+min_vruntime; that value is used to place newly activated entities on the left
+side of the tree as much as possible.
+
+The total number of running tasks in the runqueue is accounted through the
+rq->cfs.load value, which is the sum of the weights of the tasks queued on the
+runqueue.
+
+CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the
+p->se.vruntime key (there is a subtraction using rq->cfs.min_vruntime to
+account for possible wraparounds). CFS picks the "leftmost" task from this
+tree and sticks to it.
+As the system progresses forwards, the executed tasks are put into the tree
+more and more to the right --- slowly but surely giving a chance for every task
+to become the "leftmost task" and thus get on the CPU within a deterministic
+amount of time.
+
+Summing up, CFS works like this: it runs a task a bit, and when the task
+schedules (or a scheduler tick happens) the task's CPU usage is "accounted
+for": the (small) time it just spent using the physical CPU is added to
+p->se.vruntime. Once p->se.vruntime gets high enough so that another task
+becomes the "leftmost task" of the time-ordered rbtree it maintains (plus a
+small amount of "granularity" distance relative to the leftmost task so that we
+do not over-schedule tasks and trash the cache), then the new leftmost task is
+picked and the current task is preempted.
+
+
+
+4. SOME FEATURES OF CFS
+
+CFS uses nanosecond granularity accounting and does not rely on any jiffies or
+other HZ detail. Thus the CFS scheduler has no notion of "timeslices" in the
+way the previous scheduler had, and has no heuristics whatsoever. There is
+only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
+
+ /proc/sys/kernel/sched_granularity_ns
+
+which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
+"server" (i.e., good batching) workloads. It defaults to a setting suitable
+for desktop workloads. SCHED_BATCH is handled by the CFS scheduler module too.
+
+Due to its design, the CFS scheduler is not prone to any of the "attacks" that
+exist today against the heuristics of the stock scheduler: fiftyp.c, thud.c,
+chew.c, ring-test.c, massive_intr.c all work fine and do not impact
+interactivity and produce the expected behavior.
+
+The CFS scheduler has a much stronger handling of nice levels and SCHED_BATCH
+than the previous vanilla scheduler: both types of workloads are isolated much
+more aggressively.
+
+SMP load-balancing has been reworked/sanitized: the runqueue-walking
+assumptions are gone from the load-balancing code now, and iterators of the
+scheduling modules are used. The balancing code got quite a bit simpler as a
+result.
+
+
+
+5. Scheduling policies
+
+CFS implements three scheduling policies:
+
+ - SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling
+ policy that is used for regular tasks.
+
+ - SCHED_BATCH: Does not preempt nearly as often as regular tasks
+ would, thereby allowing tasks to run longer and make better use of
+ caches but at the cost of interactivity. This is well suited for
+ batch jobs.
+
+ - SCHED_IDLE: This is even weaker than nice 19, but its not a true
+ idle timer scheduler in order to avoid to get into priority
+ inversion problems which would deadlock the machine.
+
+SCHED_FIFO/_RR are implemented in sched_rt.c and are as specified by
+POSIX.
+
+The command chrt from util-linux-ng 2.13.1.1 can set all of these except
+SCHED_IDLE.
-Group scheduler tunables:
-When CONFIG_FAIR_USER_SCHED is defined, a directory is created in sysfs for
-each new user and a "cpu_share" file is added in that directory.
+
+6. SCHEDULING CLASSES
+
+The new CFS scheduler has been designed in such a way to introduce "Scheduling
+Classes," an extensible hierarchy of scheduler modules. These modules
+encapsulate scheduling policy details and are handled by the scheduler core
+without the core code assuming too much about them.
+
+sched_fair.c implements the CFS scheduler described above.
+
+sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than
+the previous vanilla scheduler did. It uses 100 runqueues (for all 100 RT
+priority levels, instead of 140 in the previous scheduler) and it needs no
+expired array.
+
+Scheduling classes are implemented through the sched_class structure, which
+contains hooks to functions that must be called whenever an interesting event
+occurs.
+
+This is the (partial) list of the hooks:
+
+ - enqueue_task(...)
+
+ Called when a task enters a runnable state.
+ It puts the scheduling entity (task) into the red-black tree and
+ increments the nr_running variable.
+
+ - dequeue_tree(...)
+
+ When a task is no longer runnable, this function is called to keep the
+ corresponding scheduling entity out of the red-black tree. It decrements
+ the nr_running variable.
+
+ - yield_task(...)
+
+ This function is basically just a dequeue followed by an enqueue, unless the
+ compat_yield sysctl is turned on; in that case, it places the scheduling
+ entity at the right-most end of the red-black tree.
+
+ - check_preempt_curr(...)
+
+ This function checks if a task that entered the runnable state should
+ preempt the currently running task.
+
+ - pick_next_task(...)
+
+ This function chooses the most appropriate task eligible to run next.
+
+ - set_curr_task(...)
+
+ This function is called when a task changes its scheduling class or changes
+ its task group.
+
+ - task_tick(...)
+
+ This function is mostly called from time tick functions; it might lead to
+ process switch. This drives the running preemption.
+
+ - task_new(...)
+
+ The core scheduler gives the scheduling module an opportunity to manage new
+ task startup. The CFS scheduling module uses it for group scheduling, while
+ the scheduling module for a real-time task does not use it.
+
+
+
+7. GROUP SCHEDULER EXTENSIONS TO CFS
+
+Normally, the scheduler operates on individual tasks and strives to provide
+fair CPU time to each task. Sometimes, it may be desirable to group tasks and
+provide fair CPU time to each such task group. For example, it may be
+desirable to first provide fair CPU time to each user on the system and then to
+each task belonging to a user.
+
+CONFIG_GROUP_SCHED strives to achieve exactly that. It lets tasks to be
+grouped and divides CPU time fairly among such groups.
+
+CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
+SCHED_RR) tasks.
+
+CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
+SCHED_BATCH) tasks.
+
+At present, there are two (mutually exclusive) mechanisms to group tasks for
+CPU bandwidth control purposes:
+
+ - Based on user id (CONFIG_USER_SCHED)
+
+ With this option, tasks are grouped according to their user id.
+
+ - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED)
+
+ This options needs CONFIG_CGROUPS to be defined, and lets the administrator
+ create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See
+ Documentation/cgroups.txt for more information about this filesystem.
+
+Only one of these options to group tasks can be chosen and not both.
+
+When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
+user and a "cpu_share" file is added in that directory.
# cd /sys/kernel/uids
# cat 512/cpu_share # Display user 512's CPU share
@@ -155,16 +246,14 @@ each new user and a "cpu_share" file is added in that directory.
2048
#
-CPU bandwidth between two users are divided in the ratio of their CPU shares.
-For ex: if you would like user "root" to get twice the bandwidth of user
-"guest", then set the cpu_share for both the users such that "root"'s
-cpu_share is twice "guest"'s cpu_share
-
+CPU bandwidth between two users is divided in the ratio of their CPU shares.
+For example: if you would like user "root" to get twice the bandwidth of user
+"guest," then set the cpu_share for both the users such that "root"'s cpu_share
+is twice "guest"'s cpu_share.
-When CONFIG_FAIR_CGROUP_SCHED is defined, a "cpu.shares" file is created
-for each group created using the pseudo filesystem. See example steps
-below to create task groups and modify their CPU share using the "cgroups"
-pseudo filesystem
+When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
+group created using the pseudo filesystem. See example steps below to create
+task groups and modify their CPU share using the "cgroups" pseudo filesystem.
# mkdir /dev/cpuctl
# mount -t cgroup -ocpu none /dev/cpuctl
diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt
index 75143f0c23b..38d324d62b2 100644
--- a/Documentation/scsi/scsi_fc_transport.txt
+++ b/Documentation/scsi/scsi_fc_transport.txt
@@ -436,6 +436,42 @@ Other:
was updated to remove all vports for the fc_host as well.
+Transport supplied functions
+----------------------------
+
+The following functions are supplied by the FC-transport for use by LLDs.
+
+ fc_vport_create - create a vport
+ fc_vport_terminate - detach and remove a vport
+
+Details:
+
+/**
+ * fc_vport_create - Admin App or LLDD requests creation of a vport
+ * @shost: scsi host the virtual port is connected to.
+ * @ids: The world wide names, FC4 port roles, etc for
+ * the virtual port.
+ *
+ * Notes:
+ * This routine assumes no locks are held on entry.
+ */
+struct fc_vport *
+fc_vport_create(struct Scsi_Host *shost, struct fc_vport_identifiers *ids)
+
+/**
+ * fc_vport_terminate - Admin App or LLDD requests termination of a vport
+ * @vport: fc_vport to be terminated
+ *
+ * Calls the LLDD vport_delete() function, then deallocates and removes
+ * the vport from the shost and object tree.
+ *
+ * Notes:
+ * This routine assumes no locks are held on entry.
+ */
+int
+fc_vport_terminate(struct fc_vport *vport)
+
+
Credits
=======
The following people have contributed to this document:
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index b117e42a616..e0e54a27fc1 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -746,8 +746,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
Module snd-hda-intel
--------------------
- Module for Intel HD Audio (ICH6, ICH6M, ESB2, ICH7, ICH8),
- ATI SB450, SB600, RS600,
+ Module for Intel HD Audio (ICH6, ICH6M, ESB2, ICH7, ICH8, ICH9, ICH10,
+ PCH, SCH),
+ ATI SB450, SB600, R600, RS600, RS690, RS780, RV610, RV620,
+ RV630, RV635, RV670, RV770,
VIA VT8251/VT8237A,
SIS966, ULI M5461
@@ -807,6 +809,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
ALC260
hp HP machines
hp-3013 HP machines (3013-variant)
+ hp-dc7600 HP DC7600
fujitsu Fujitsu S7020
acer Acer TravelMate
will Will laptops (PB V7900)
@@ -828,8 +831,11 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
hippo Hippo (ATI) with jack detection, Sony UX-90s
hippo_1 Hippo (Benq) with jack detection
sony-assamd Sony ASSAMD
+ toshiba-s06 Toshiba S06
+ toshiba-rx1 Toshiba RX1
ultra Samsung Q1 Ultra Vista model
lenovo-3000 Lenovo 3000 y410
+ nec NEC Versa S9100
basic fixed pin assignment w/o SPDIF
auto auto-config reading BIOS (default)
@@ -838,6 +844,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
3stack 3-stack model
toshiba Toshiba A205
acer Acer laptops
+ acer-aspire Acer Aspire One
dell Dell OEM laptops (Vostro 1200)
zepto Zepto laptops
test for testing/debugging purpose, almost all controls can
@@ -847,6 +854,9 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
ALC269
basic Basic preset
+ quanta Quanta FL1
+ eeepc-p703 ASUS Eeepc P703 P900A
+ eeepc-p901 ASUS Eeepc P901 S101
ALC662/663
3stack-dig 3-stack (2-channel) with SPDIF
@@ -856,10 +866,17 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
lenovo-101e Lenovo laptop
eeepc-p701 ASUS Eeepc P701
eeepc-ep20 ASUS Eeepc EP20
+ ecs ECS/Foxconn mobo
m51va ASUS M51VA
g71v ASUS G71V
h13 ASUS H13
g50v ASUS G50V
+ asus-mode1 ASUS
+ asus-mode2 ASUS
+ asus-mode3 ASUS
+ asus-mode4 ASUS
+ asus-mode5 ASUS
+ asus-mode6 ASUS
auto auto-config reading BIOS (default)
ALC882/885
@@ -891,12 +908,14 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
lenovo-101e Lenovo 101E
lenovo-nb0763 Lenovo NB0763
lenovo-ms7195-dig Lenovo MS7195
+ lenovo-sky Lenovo Sky
haier-w66 Haier W66
3stack-hp HP machines with 3stack (Lucknow, Samba boards)
6stack-dell Dell machines with 6stack (Inspiron 530)
mitac Mitac 8252D
clevo-m720 Clevo M720 laptop series
fujitsu-pi2515 Fujitsu AMILO Pi2515
+ 3stack-6ch-intel Intel DG33* boards
auto auto-config reading BIOS (default)
ALC861/660
@@ -929,7 +948,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
allout 5-jack in back, 2-jack in front, SPDIF out
auto auto-config reading BIOS (default)
- AD1882
+ AD1882 / AD1882A
3stack 3-stack mode (default)
6stack 6-stack mode
@@ -1079,7 +1098,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
register value without FIFO size correction as the current
DMA pointer. position_fix=2 will make the driver to use
the position buffer instead of reading SD_LPIB register.
- (Usually SD_LPLIB register is more accurate than the
+ (Usually SD_LPIB register is more accurate than the
position buffer.)
NB: If you get many "azx_get_response timeout" messages at
@@ -1166,6 +1185,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* Event Electronics, EZ8
* Digigram VX442
* Lionstracs, Mediastaton
+ * Terrasoniq TS 88
model - Use the given board model, one of the following:
delta1010, dio2496, delta66, delta44, audiophile, delta410,
@@ -1200,7 +1220,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* TerraTec Phase 22
* TerraTec Phase 28
* AudioTrak Prodigy 7.1
- * AudioTrak Prodigy 7.1LT
+ * AudioTrak Prodigy 7.1 LT
+ * AudioTrak Prodigy 7.1 XT
+ * AudioTrak Prodigy 7.1 HIFI
+ * AudioTrak Prodigy 7.1 HD2
* AudioTrak Prodigy 192
* Pontis MS300
* Albatron K8X800 Pro II
@@ -1211,12 +1234,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* Shuttle SN25P
* Onkyo SE-90PCI
* Onkyo SE-200PCI
+ * ESI Juli@
+ * Hercules Fortissimo IV
+ * EGO-SYS WaveTerminal 192M
model - Use the given board model, one of the following:
revo51, revo71, amp2000, prodigy71, prodigy71lt,
- prodigy192, aureon51, aureon71, universe, ap192,
- k8x800, phase22, phase28, ms300, av710, se200pci,
- se90pci
+ prodigy71xt, prodigy71hifi, prodigyhd2, prodigy192,
+ juli, aureon51, aureon71, universe, ap192, k8x800,
+ phase22, phase28, ms300, av710, se200pci, se90pci,
+ fortissimo4, sn25p, WT192M
This module supports multiple cards and autoprobe.
@@ -1255,7 +1282,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
Module for AC'97 motherboards from Intel and compatibles.
* Intel i810/810E, i815, i820, i830, i84x, MX440
- ICH5, ICH6, ICH7, ESB2
+ ICH5, ICH6, ICH7, 6300ESB, ESB2
* SiS 7012 (SiS 735)
* NVidia NForce, NForce2, NForce3, MCP04, CK804
CK8, CK8S, MCP501
@@ -1951,6 +1978,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* CHIC True Sound 4Dwave
* Shark Predator4D-PCI
* Jaton SonicWave 4D
+ * SiS SI7018 PCI Audio
+ * Hoontech SoundTrack Digital 4DWave NX
pcm_channels - max channels (voices) reserved for PCM
wavetable_size - max wavetable size in kB (4-?kb)
@@ -1966,12 +1995,25 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
vid - Vendor ID for the device (optional)
pid - Product ID for the device (optional)
+ nrpacks - Max. number of packets per URB (default: 8)
+ async_unlink - Use async unlink mode (default: yes)
device_setup - Device specific magic number (optional)
- Influence depends on the device
- Default: 0x0000
+ ignore_ctl_error - Ignore any USB-controller regarding mixer
+ interface (default: no)
This module supports multiple devices, autoprobe and hotplugging.
+ NB: nrpacks parameter can be modified dynamically via sysfs.
+ Don't put the value over 20. Changing via sysfs has no sanity
+ check.
+ NB: async_unlink=0 would cause Oops. It remains just for
+ debugging purpose (if any).
+ NB: ignore_ctl_error=1 may help when you get an error at accessing
+ the mixer element such as URB error -22. This happens on some
+ buggy USB device or the controller.
+
Module snd-usb-caiaq
--------------------
@@ -2078,7 +2120,7 @@ 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 and D2X.
+ i.e., Xonar D1, DX, D2, D2X and HDAV1.3 (Deluxe).
This module supports autoprobe and multiple cards.
diff --git a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
index e13c4e67029..b54cb5048df 100644
--- a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
@@ -6135,44 +6135,58 @@ struct _snd_pcm_runtime {
</para>
</section>
- <section id="useful-functions-snd-assert">
- <title><function>snd_assert()</function></title>
+ <section id="useful-functions-snd-bug">
+ <title><function>snd_BUG()</function></title>
<para>
- <function>snd_assert()</function> macro is similar with the
- normal <function>assert()</function> macro. For example,
+ It shows the <computeroutput>BUG?</computeroutput> message and
+ stack trace as well as <function>snd_BUG_ON</function> at the point.
+ It's useful to show that a fatal error happens there.
+ </para>
+ <para>
+ When no debug flag is set, this macro is ignored.
+ </para>
+ </section>
+
+ <section id="useful-functions-snd-bug-on">
+ <title><function>snd_BUG_ON()</function></title>
+ <para>
+ <function>snd_BUG_ON()</function> macro is similar with
+ <function>WARN_ON()</function> macro. For example,
<informalexample>
<programlisting>
<![CDATA[
- snd_assert(pointer != NULL, return -EINVAL);
+ snd_BUG_ON(!pointer);
]]>
</programlisting>
</informalexample>
- </para>
- <para>
- The first argument is the expression to evaluate, and the
- second argument is the action if it fails. When
- <constant>CONFIG_SND_DEBUG</constant>, is set, it will show an
- error message such as <computeroutput>BUG? (xxx)</computeroutput>
- together with stack trace.
- </para>
- <para>
- When no debug flag is set, this macro is ignored.
- </para>
- </section>
+ or it can be used as the condition,
+ <informalexample>
+ <programlisting>
+<![CDATA[
+ if (snd_BUG_ON(non_zero_is_bug))
+ return -EINVAL;
+]]>
+ </programlisting>
+ </informalexample>
- <section id="useful-functions-snd-bug">
- <title><function>snd_BUG()</function></title>
- <para>
- It shows the <computeroutput>BUG?</computeroutput> message and
- stack trace as well as <function>snd_assert</function> at the point.
- It's useful to show that a fatal error happens there.
</para>
+
<para>
- When no debug flag is set, this macro is ignored.
+ The macro takes an conditional expression to evaluate.
+ When <constant>CONFIG_SND_DEBUG</constant>, is set, the
+ expression is actually evaluated. If it's non-zero, it shows
+ the warning message such as
+ <computeroutput>BUG? (xxx)</computeroutput>
+ normally followed by stack trace. It returns the evaluated
+ value.
+ When no <constant>CONFIG_SND_DEBUG</constant> is set, this
+ macro always returns zero.
</para>
+
</section>
+
</chapter>
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
new file mode 100644
index 00000000000..dbe3377754a
--- /dev/null
+++ b/Documentation/x86/00-INDEX
@@ -0,0 +1,4 @@
+00-INDEX
+ - this file
+mtrr.txt
+ - how to use x86 Memory Type Range Registers to increase performance
diff --git a/Documentation/x86/i386/boot.txt b/Documentation/x86/boot.txt
index 147bfe511cd..83c0033ee9e 100644
--- a/Documentation/x86/i386/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -308,7 +308,7 @@ Protocol: 2.00+
Field name: start_sys
Type: read
-Offset/size: 0x20c/4
+Offset/size: 0x20c/2
Protocol: 2.00+
The load low segment (0x1000). Obsolete.
diff --git a/Documentation/mtrr.txt b/Documentation/x86/mtrr.txt
index c39ac395970..cc071dc333c 100644
--- a/Documentation/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -18,7 +18,7 @@ Richard Gooch
The AMD K6-2 (stepping 8 and above) and K6-3 processors have two
MTRRs. These are supported. The AMD Athlon family provide 8 Intel
style MTRRs.
-
+
The Centaur C6 (WinChip) has 8 MCRs, allowing write-combining. These
are supported.
@@ -87,7 +87,7 @@ reg00: base=0x00000000 ( 0MB), size= 64MB: write-back, count=1
reg01: base=0xfb000000 (4016MB), size= 16MB: write-combining, count=1
reg02: base=0xfb000000 (4016MB), size= 4kB: uncachable, count=1
-Some cards (especially Voodoo Graphics boards) need this 4 kB area
+Some cards (especially Voodoo Graphics boards) need this 4 kB area
excluded from the beginning of the region because it is used for
registers.
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 17965f927c1..c93ff5f4c0d 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -14,6 +14,10 @@ PAT allows for different types of memory attributes. The most commonly used
ones that will be supported at this time are Write-back, Uncached,
Write-combined and Uncached Minus.
+
+PAT APIs
+--------
+
There are many different APIs in the kernel that allows setting of memory
attributes at the page level. In order to avoid aliasing, these interfaces
should be used thoughtfully. Below is a table of interfaces available,
@@ -26,38 +30,38 @@ address range to avoid any aliasing.
API | RAM | ACPI,... | Reserved/Holes |
-----------------------|----------|------------|------------------|
| | | |
-ioremap | -- | UC | UC |
+ioremap | -- | UC- | UC- |
| | | |
ioremap_cache | -- | WB | WB |
| | | |
-ioremap_nocache | -- | UC | UC |
+ioremap_nocache | -- | UC- | UC- |
| | | |
ioremap_wc | -- | -- | WC |
| | | |
-set_memory_uc | UC | -- | -- |
+set_memory_uc | UC- | -- | -- |
set_memory_wb | | | |
| | | |
set_memory_wc | WC | -- | -- |
set_memory_wb | | | |
| | | |
-pci sysfs resource | -- | -- | UC |
+pci sysfs resource | -- | -- | UC- |
| | | |
pci sysfs resource_wc | -- | -- | WC |
is IORESOURCE_PREFETCH| | | |
| | | |
-pci proc | -- | -- | UC |
+pci proc | -- | -- | UC- |
!PCIIOC_WRITE_COMBINE | | | |
| | | |
pci proc | -- | -- | WC |
PCIIOC_WRITE_COMBINE | | | |
| | | |
-/dev/mem | -- | UC | UC |
+/dev/mem | -- | WB/WC/UC- | WB/WC/UC- |
read-write | | | |
| | | |
-/dev/mem | -- | UC | UC |
+/dev/mem | -- | UC- | UC- |
mmap SYNC flag | | | |
| | | |
-/dev/mem | -- | WB/WC/UC | WB/WC/UC |
+/dev/mem | -- | WB/WC/UC- | WB/WC/UC- |
mmap !SYNC flag | |(from exist-| (from exist- |
and | | ing alias)| ing alias) |
any alias to this area| | | |
@@ -68,7 +72,7 @@ pci proc | -- | -- | WC |
and | | | |
MTRR says WB | | | |
| | | |
-/dev/mem | -- | -- | UC_MINUS |
+/dev/mem | -- | -- | UC- |
mmap !SYNC flag | | | |
no alias to this area | | | |
and | | | |
@@ -98,3 +102,35 @@ types.
Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
+
+PAT debugging
+-------------
+
+With CONFIG_DEBUG_FS enabled, PAT memtype list can be examined by
+
+# mount -t debugfs debugfs /sys/kernel/debug
+# cat /sys/kernel/debug/x86/pat_memtype_list
+PAT memtype list:
+uncached-minus @ 0x7fadf000-0x7fae0000
+uncached-minus @ 0x7fb19000-0x7fb1a000
+uncached-minus @ 0x7fb1a000-0x7fb1b000
+uncached-minus @ 0x7fb1b000-0x7fb1c000
+uncached-minus @ 0x7fb1c000-0x7fb1d000
+uncached-minus @ 0x7fb1d000-0x7fb1e000
+uncached-minus @ 0x7fb1e000-0x7fb25000
+uncached-minus @ 0x7fb25000-0x7fb26000
+uncached-minus @ 0x7fb26000-0x7fb27000
+uncached-minus @ 0x7fb27000-0x7fb28000
+uncached-minus @ 0x7fb28000-0x7fb2e000
+uncached-minus @ 0x7fb2e000-0x7fb2f000
+uncached-minus @ 0x7fb2f000-0x7fb30000
+uncached-minus @ 0x7fb31000-0x7fb32000
+uncached-minus @ 0x80000000-0x90000000
+
+This list shows physical address ranges and various PAT settings used to
+access those physical address ranges.
+
+Another, more verbose way of getting PAT related debug messages is with
+"debugpat" boot parameter. With this parameter, various debug messages are
+printed to dmesg log.
+
diff --git a/Documentation/x86/i386/usb-legacy-support.txt b/Documentation/x86/usb-legacy-support.txt
index 1894cdfc69d..1894cdfc69d 100644
--- a/Documentation/x86/i386/usb-legacy-support.txt
+++ b/Documentation/x86/usb-legacy-support.txt
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index b0c7b6c4abd..72ffb5373ec 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -54,10 +54,6 @@ APICs
apicmaintimer. Useful when your PIT timer is totally
broken.
- disable_8254_timer / enable_8254_timer
- Enable interrupt 0 timer routing over the 8254 in addition to over
- the IO-APIC. The kernel tries to set a sensible default.
-
Early Console
syntax: earlyprintk=vga
diff --git a/Documentation/x86/i386/zero-page.txt b/Documentation/x86/zero-page.txt
index 169ad423a3d..169ad423a3d 100644
--- a/Documentation/x86/i386/zero-page.txt
+++ b/Documentation/x86/zero-page.txt