UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge commit 'tip/perfcounters-for-linus' into oprofile/master 

Conflicts:
	arch/x86/oprofile/op_model_ppro.c

Signed-off-by: Robert Richter <robert.richter@amd.com>
This commit is contained in:
Robert Richter 2009-06-12 17:58:48 +02:00
parent 51563a0e56 940010c5a3
commit 1241eb8f13
506 changed files with 44855 additions and 8421 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
Documentation/ABI/testing/sysfs-devices-cache_disable Normal file
View File

@ -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

12
Documentation/DMA-API.txt
View File

@ -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

3
Documentation/DocBook/Makefile
View File

@ -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):

89
Documentation/DocBook/tracepoint.tmpl Normal file
View File

@ -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>

102
Documentation/RCU/trace.txt
View File

@ -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().

131
Documentation/futex-requeue-pi.txt Normal file
View File

@ -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.

42
Documentation/kernel-parameters.txt
View File

@ -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
@ -1054,15 +1068,6 @@ 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)
@ -1575,6 +1580,9 @@ 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.

129
Documentation/memory-barriers.txt
View File

@ -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.

20
Documentation/scheduler/sched-rt-group.txt
View File

@ -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).

90
Documentation/trace/events.txt Normal file
View File

@ -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

17
Documentation/trace/ftrace.txt
View File

@ -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:

17
Documentation/trace/power.txt Normal file
View File

@ -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

122
Documentation/x86/boot.txt
View File

@ -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.)
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.
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

5
Documentation/x86/x86_64/boot-options.txt
View File

@ -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

9
Documentation/x86/x86_64/mm.txt
View File

@ -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

10
MAINTAINERS
View File

@ -4392,6 +4392,16 @@ S: Maintained
F: include/linux/delayacct.h
F: kernel/delayacct.c
PERFORMANCE COUNTER SUBSYSTEM
P: Peter Zijlstra
M: a.p.zijlstra@chello.nl
P: Paul Mackerras
M: paulus@samba.org
P: Ingo Molnar
M: mingo@elte.hu
L: linux-kernel@vger.kernel.org
S: Supported
PERSONALITY HANDLING
P: Christoph Hellwig
M: hch@infradead.org

8
arch/alpha/kernel/sys_dp264.c
View File

@ -176,22 +176,26 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
}
}
static void
static int
dp264_set_affinity(unsigned int irq, const struct cpumask *affinity)
{
spin_lock(&dp264_irq_lock);
cpu_set_irq_affinity(irq, *affinity);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
return 0;
}
static void
static int
clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
{
spin_lock(&dp264_irq_lock);
cpu_set_irq_affinity(irq - 16, *affinity);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
return 0;
}
static struct hw_interrupt_type dp264_irq_type = {

4
arch/alpha/kernel/sys_titan.c
View File

@ -157,13 +157,15 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
}
static void
static int
titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
{
spin_lock(&titan_irq_lock);
titan_cpu_set_irq_affinity(irq - 16, *affinity);
titan_update_irq_hw(titan_cached_irq_mask);
spin_unlock(&titan_irq_lock);
return 0;
}
static void

4
arch/arm/common/gic.c
View File

@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq)
}
#ifdef CONFIG_SMP
static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
{
void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3);
unsigned int shift = (irq % 4) * 8;
@ -122,6 +122,8 @@ static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
val |= 1 << (cpu + shift);
writel(val, reg);
spin_unlock(&irq_controller_lock);
return 0;
}
#endif

4
arch/cris/arch-v32/kernel/irq.c
View File

@ -325,12 +325,14 @@ static void end_crisv32_irq(unsigned int irq)
{
}
void set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
int set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
{
unsigned long flags;
spin_lock_irqsave(&irq_lock, flags);
irq_allocations[irq - FIRST_IRQ].mask = *dest;
spin_unlock_irqrestore(&irq_lock, flags);
return 0;
}
static struct irq_chip crisv32_irq_type = {

3
arch/ia64/hp/sim/hpsim_irq.c
View File

@ -21,9 +21,10 @@ hpsim_irq_noop (unsigned int irq)
{
}
static void
static int
hpsim_set_affinity_noop(unsigned int a, const struct cpumask *b)
{
return 0;
}
static struct hw_interrupt_type irq_type_hp_sim = {

5
arch/ia64/kernel/acpi.c
View File

@ -636,7 +636,7 @@ void __init acpi_numa_arch_fixup(void)
* success: return IRQ number (>=0)
* failure: return < 0
*/
int acpi_register_gsi(u32 gsi, int triggering, int polarity)
int acpi_register_gsi(struct device *dev, u32 gsi, int triggering, int polarity)
{
if (acpi_irq_model == ACPI_IRQ_MODEL_PLATFORM)
return gsi;
@ -678,7 +678,8 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
fadt = (struct acpi_table_fadt *)fadt_header;
acpi_register_gsi(fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW);
acpi_register_gsi(NULL, fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE,
ACPI_ACTIVE_LOW);
return 0;
}

10
arch/ia64/kernel/iosapic.c
View File

@ -329,7 +329,7 @@ unmask_irq (unsigned int irq)
}
static void
static int
iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
{
#ifdef CONFIG_SMP
@ -343,15 +343,15 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
cpu = cpumask_first_and(cpu_online_mask, mask);
if (cpu >= nr_cpu_ids)
return;
return -1;
if (irq_prepare_move(irq, cpu))
return;
return -1;
dest = cpu_physical_id(cpu);
if (!iosapic_intr_info[irq].count)
return; /* not an IOSAPIC interrupt */
return -1; /* not an IOSAPIC interrupt */
set_irq_affinity_info(irq, dest, redir);
@ -376,7 +376,9 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
iosapic_write(iosapic, IOSAPIC_RTE_HIGH(rte_index), high32);
iosapic_write(iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
}
#endif
return 0;
}
/*

16
arch/ia64/kernel/msi_ia64.c
View File

@ -12,7 +12,7 @@
static struct irq_chip ia64_msi_chip;
#ifdef CONFIG_SMP
static void ia64_set_msi_irq_affinity(unsigned int irq,
static int ia64_set_msi_irq_affinity(unsigned int irq,
const cpumask_t *cpu_mask)
{
struct msi_msg msg;
@ -20,10 +20,10 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
int cpu = first_cpu(*cpu_mask);
if (!cpu_online(cpu))
return;
return -1;
if (irq_prepare_move(irq, cpu))
return;
return -1;
read_msi_msg(irq, &msg);
@ -39,6 +39,8 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
write_msi_msg(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
return 0;
}
#endif /* CONFIG_SMP */
@ -130,17 +132,17 @@ void arch_teardown_msi_irq(unsigned int irq)
#ifdef CONFIG_DMAR
#ifdef CONFIG_SMP
static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_cfg *cfg = irq_cfg + irq;
struct msi_msg msg;
int cpu = cpumask_first(mask);
if (!cpu_online(cpu))
return;
return -1;
if (irq_prepare_move(irq, cpu))
return;
return -1;
dmar_msi_read(irq, &msg);
@ -151,6 +153,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
dmar_msi_write(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, mask);
return 0;
}
#endif /* CONFIG_SMP */

4
arch/ia64/sn/kernel/irq.c
View File

@ -227,7 +227,7 @@ finish_up:
return new_irq_info;
}
static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
static int sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
{
struct sn_irq_info *sn_irq_info, *sn_irq_info_safe;
nasid_t nasid;
@ -239,6 +239,8 @@ static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe,
sn_irq_lh[irq], list)
(void)sn_retarget_vector(sn_irq_info, nasid, slice);
return 0;
}
#ifdef CONFIG_SMP

8
arch/ia64/sn/kernel/msi_sn.c
View File

@ -151,7 +151,7 @@ int sn_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *entry)
}
#ifdef CONFIG_SMP
static void sn_set_msi_irq_affinity(unsigned int irq,
static int sn_set_msi_irq_affinity(unsigned int irq,
const struct cpumask *cpu_mask)
{
struct msi_msg msg;
@ -168,7 +168,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
cpu = cpumask_first(cpu_mask);
sn_irq_info = sn_msi_info[irq].sn_irq_info;
if (sn_irq_info == NULL || sn_irq_info->irq_int_bit >= 0)
return;
return -1;
/*
* Release XIO resources for the old MSI PCI address
@ -189,7 +189,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
new_irq_info = sn_retarget_vector(sn_irq_info, nasid, slice);
sn_msi_info[irq].sn_irq_info = new_irq_info;
if (new_irq_info == NULL)
return;
return -1;
/*
* Map the xio address into bus space
@ -206,6 +206,8 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
write_msi_msg(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, cpu_mask);
return 0;
}
#endif /* CONFIG_SMP */

8
arch/mips/cavium-octeon/octeon-irq.c
View File

@ -177,7 +177,7 @@ static void octeon_irq_ciu0_disable(unsigned int irq)
}
#ifdef CONFIG_SMP
static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest)
static int octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest)
{
int cpu;
int bit = irq - OCTEON_IRQ_WORKQ0; /* Bit 0-63 of EN0 */
@ -199,6 +199,8 @@ static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask
*/
cvmx_read_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2));
write_unlock(&octeon_irq_ciu0_rwlock);
return 0;
}
#endif
@ -292,7 +294,7 @@ static void octeon_irq_ciu1_disable(unsigned int irq)
}
#ifdef CONFIG_SMP
static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest)
static int octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest)
{
int cpu;
int bit = irq - OCTEON_IRQ_WDOG0; /* Bit 0-63 of EN1 */
@ -315,6 +317,8 @@ static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask
*/
cvmx_read_csr(CVMX_CIU_INTX_EN1(cvmx_get_core_num() * 2 + 1));
write_unlock(&octeon_irq_ciu1_rwlock);
return 0;
}
#endif

2
arch/mips/include/asm/irq.h
View File

@ -49,7 +49,7 @@ static inline void smtc_im_ack_irq(unsigned int irq)
#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
#include <linux/cpumask.h>
extern void plat_set_irq_affinity(unsigned int irq,
extern int plat_set_irq_affinity(unsigned int irq,
const struct cpumask *affinity);
extern void smtc_forward_irq(unsigned int irq);

5
arch/mips/kernel/irq-gic.c
View File

@ -155,7 +155,7 @@ static void gic_unmask_irq(unsigned int irq)
static DEFINE_SPINLOCK(gic_lock);
static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
{
cpumask_t tmp = CPU_MASK_NONE;
unsigned long flags;
@ -166,7 +166,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
cpumask_and(&tmp, cpumask, cpu_online_mask);
if (cpus_empty(tmp))
return;
return -1;
/* Assumption : cpumask refers to a single CPU */
spin_lock_irqsave(&gic_lock, flags);
@ -190,6 +190,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
cpumask_copy(irq_desc[irq].affinity, cpumask);
spin_unlock_irqrestore(&gic_lock, flags);
return 0;
}
#endif

4
arch/mips/mti-malta/malta-smtc.c
View File

@ -114,7 +114,7 @@ struct plat_smp_ops msmtc_smp_ops = {
*/
void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
{
cpumask_t tmask;
int cpu = 0;
@ -156,5 +156,7 @@ void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
/* Do any generic SMTC IRQ affinity setup */
smtc_set_irq_affinity(irq, tmask);
return 0;
}
#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */

8
arch/mips/sibyte/bcm1480/irq.c
View File

@ -50,7 +50,7 @@ static void enable_bcm1480_irq(unsigned int irq);
static void disable_bcm1480_irq(unsigned int irq);
static void ack_bcm1480_irq(unsigned int irq);
#ifdef CONFIG_SMP
static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask);
static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask);
#endif
#ifdef CONFIG_PCI
@ -109,7 +109,7 @@ void bcm1480_unmask_irq(int cpu, int irq)
}
#ifdef CONFIG_SMP
static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
{
int i = 0, old_cpu, cpu, int_on, k;
u64 cur_ints;
@ -118,7 +118,7 @@ static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
if (cpumask_weight(mask) != 1) {
printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
return;
return -1;
}
i = cpumask_first(mask);
@ -152,6 +152,8 @@ static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
}
}
spin_unlock_irqrestore(&bcm1480_imr_lock, flags);
return 0;
}
#endif

8
arch/mips/sibyte/sb1250/irq.c
View File

@ -50,7 +50,7 @@ static void enable_sb1250_irq(unsigned int irq);
static void disable_sb1250_irq(unsigned int irq);
static void ack_sb1250_irq(unsigned int irq);
#ifdef CONFIG_SMP
static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask);
static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask);
#endif
#ifdef CONFIG_SIBYTE_HAS_LDT
@ -103,7 +103,7 @@ void sb1250_unmask_irq(int cpu, int irq)
}
#ifdef CONFIG_SMP
static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
{
int i = 0, old_cpu, cpu, int_on;
u64 cur_ints;
@ -113,7 +113,7 @@ static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
if (cpumask_weight(mask) > 1) {
printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
return;
return -1;
}
/* Convert logical CPU to physical CPU */
@ -143,6 +143,8 @@ static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
R_IMR_INTERRUPT_MASK));
}
spin_unlock_irqrestore(&sb1250_imr_lock, flags);
return 0;
}
#endif

6
arch/parisc/kernel/irq.c
View File

@ -130,15 +130,17 @@ int cpu_check_affinity(unsigned int irq, const struct cpumask *dest)
return cpu_dest;
}
static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
static int cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
{
int cpu_dest;
cpu_dest = cpu_check_affinity(irq, dest);
if (cpu_dest < 0)
return;
return -1;
cpumask_copy(&irq_desc[irq].affinity, dest);
return 0;
}
#endif

39
arch/powerpc/include/asm/hw_irq.h
View File

@ -131,5 +131,44 @@ static inline int irqs_disabled_flags(unsigned long flags)
*/
struct irq_chip;
#ifdef CONFIG_PERF_COUNTERS
static inline unsigned long test_perf_counter_pending(void)
{
unsigned long x;
asm volatile("lbz %0,%1(13)"
: "=r" (x)
: "i" (offsetof(struct paca_struct, perf_counter_pending)));
return x;
}
static inline void set_perf_counter_pending(void)
{
asm volatile("stb %0,%1(13)" : :
"r" (1),
"i" (offsetof(struct paca_struct, perf_counter_pending)));
}
static inline void clear_perf_counter_pending(void)
{
asm volatile("stb %0,%1(13)" : :
"r" (0),
"i" (offsetof(struct paca_struct, perf_counter_pending)));
}
extern void perf_counter_do_pending(void);
#else
static inline unsigned long test_perf_counter_pending(void)
{
return 0;
}
static inline void set_perf_counter_pending(void) {}
static inline void clear_perf_counter_pending(void) {}
static inline void perf_counter_do_pending(void) {}
#endif /* CONFIG_PERF_COUNTERS */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_HW_IRQ_H */

1
arch/powerpc/include/asm/paca.h
View File

@ -99,6 +99,7 @@ struct paca_struct {
u8 soft_enabled; /* irq soft-enable flag */
u8 hard_enabled; /* set if irqs are enabled in MSR */
u8 io_sync; /* writel() needs spin_unlock sync */
u8 perf_counter_pending; /* PM interrupt while soft-disabled */
/* Stuff for accurate time accounting */
u64 user_time; /* accumulated usermode TB ticks */

98
arch/powerpc/include/asm/perf_counter.h Normal file
View File

@ -0,0 +1,98 @@
/*
* Performance counter support - PowerPC-specific definitions.
*
* Copyright 2008-2009 Paul Mackerras, IBM Corporation.
*
* This program 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.
*/
#include <linux/types.h>
#define MAX_HWCOUNTERS 8
#define MAX_EVENT_ALTERNATIVES 8
#define MAX_LIMITED_HWCOUNTERS 2
/*
* This struct provides the constants and functions needed to
* describe the PMU on a particular POWER-family CPU.
*/
struct power_pmu {
int n_counter;
int max_alternatives;
u64 add_fields;
u64 test_adder;
int (*compute_mmcr)(u64 events[], int n_ev,
unsigned int hwc[], u64 mmcr[]);
int (*get_constraint)(u64 event, u64 *mskp, u64 *valp);
int (*get_alternatives)(u64 event, unsigned int flags,
u64 alt[]);
void (*disable_pmc)(unsigned int pmc, u64 mmcr[]);
int (*limited_pmc_event)(u64 event);
u32 flags;
int n_generic;
int *generic_events;
int (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
};
extern struct power_pmu *ppmu;
/*
* Values for power_pmu.flags
*/
#define PPMU_LIMITED_PMC5_6 1 /* PMC5/6 have limited function */
#define PPMU_ALT_SIPR 2 /* uses alternate posn for SIPR/HV */
/*
* Values for flags to get_alternatives()
*/
#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */
#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */
#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */
struct pt_regs;
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
/*
* The power_pmu.get_constraint function returns a 64-bit value and
* a 64-bit mask that express the constraints between this event and
* other events.
*
* The value and mask are divided up into (non-overlapping) bitfields
* of three different types:
*
* Select field: this expresses the constraint that some set of bits
* in MMCR* needs to be set to a specific value for this event. For a
* select field, the mask contains 1s in every bit of the field, and
* the value contains a unique value for each possible setting of the
* MMCR* bits. The constraint checking code will ensure that two events
* that set the same field in their masks have the same value in their
* value dwords.
*
* Add field: this expresses the constraint that there can be at most
* N events in a particular class. A field of k bits can be used for
* N <= 2^(k-1) - 1. The mask has the most significant bit of the field
* set (and the other bits 0), and the value has only the least significant
* bit of the field set. In addition, the 'add_fields' and 'test_adder'
* in the struct power_pmu for this processor come into play. The
* add_fields value contains 1 in the LSB of the field, and the
* test_adder contains 2^(k-1) - 1 - N in the field.
*
* NAND field: this expresses the constraint that you may not have events
* in all of a set of classes. (For example, on PPC970, you can't select
* events from the FPU, ISU and IDU simultaneously, although any two are
* possible.) For N classes, the field is N+1 bits wide, and each class
* is assigned one bit from the least-significant N bits. The mask has
* only the most-significant bit set, and the value has only the bit
* for the event's class set. The test_adder has the least significant
* bit set in the field.
*
* If an event is not subject to the constraint expressed by a particular
* field, then it will have 0 in both the mask and value for that field.
*/

2
arch/powerpc/include/asm/reg.h
View File

@ -492,11 +492,13 @@
#define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */
#define SPRN_MMCR1 798
#define SPRN_MMCRA 0x312
#define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */
#define MMCRA_SIHV 0x10000000UL /* state of MSR HV when SIAR set */
#define MMCRA_SIPR 0x08000000UL /* state of MSR PR when SIAR set */
#define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */
#define MMCRA_SLOT_SHIFT 24
#define MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */
#define POWER6_MMCRA_SDSYNC 0x0000080000000000ULL /* SDAR/SIAR synced */
#define POWER6_MMCRA_SIHV 0x0000040000000000ULL
#define POWER6_MMCRA_SIPR 0x0000020000000000ULL
#define POWER6_MMCRA_THRM 0x00000020UL

2
arch/powerpc/include/asm/systbl.h
View File

@ -322,6 +322,6 @@ SYSCALL_SPU(epoll_create1)
SYSCALL_SPU(dup3)
SYSCALL_SPU(pipe2)
SYSCALL(inotify_init1)
SYSCALL(ni_syscall)
SYSCALL_SPU(perf_counter_open)
COMPAT_SYS_SPU(preadv)
COMPAT_SYS_SPU(pwritev)

1
arch/powerpc/include/asm/unistd.h
View File

@ -341,6 +341,7 @@
#define __NR_dup3 316
#define __NR_pipe2 317
#define __NR_inotify_init1 318
#define __NR_perf_counter_open 319
#define __NR_preadv 320
#define __NR_pwritev 321

3
arch/powerpc/kernel/Makefile
View File

@ -94,6 +94,9 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o power4-pmu.o ppc970-pmu.o \
power5-pmu.o power5+-pmu.o power6-pmu.o \
power7-pmu.o
obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o

1
arch/powerpc/kernel/asm-offsets.c
View File

@ -131,6 +131,7 @@ int main(void)
DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending));
DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));

9
arch/powerpc/kernel/entry_64.S
View File

@ -526,6 +526,15 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
2:
TRACE_AND_RESTORE_IRQ(r5);
#ifdef CONFIG_PERF_COUNTERS
/* check paca->perf_counter_pending if we're enabling ints */
lbz r3,PACAPERFPEND(r13)
and. r3,r3,r5
beq 27f
bl .perf_counter_do_pending
27:
#endif /* CONFIG_PERF_COUNTERS */
/* extract EE bit and use it to restore paca->hard_enabled */
ld r3,_MSR(r1)
rldicl r4,r3,49,63 /* r0 = (r3 >> 15) & 1 */

5
arch/powerpc/kernel/irq.c
View File

@ -135,6 +135,11 @@ notrace void raw_local_irq_restore(unsigned long en)
iseries_handle_interrupts();
}
if (test_perf_counter_pending()) {
clear_perf_counter_pending();
perf_counter_do_pending();
}
/*
* if (get_paca()->hard_enabled) return;
* But again we need to take care that gcc gets hard_enabled directly

1263
arch/powerpc/kernel/perf_counter.c Normal file
View File

File diff suppressed because it is too large Load Diff

598
arch/powerpc/kernel/power4-pmu.c Normal file
View File

@ -0,0 +1,598 @@
/*
* Performance counter support for POWER4 (GP) and POWER4+ (GQ) processors.
*
* Copyright 2009 Paul Mackerras, IBM Corporation.
*
* This program 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.
*/
#include <linux/kernel.h>
#include <linux/perf_counter.h>
#include <asm/reg.h>
/*
* Bits in event code for POWER4
*/
#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */
#define PM_PMC_MSK 0xf
#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */
#define PM_UNIT_MSK 0xf
#define PM_LOWER_SH 6
#define PM_LOWER_MSK 1
#define PM_LOWER_MSKS 0x40
#define PM_BYTE_SH 4 /* Byte number of event bus to use */
#define PM_BYTE_MSK 3
#define PM_PMCSEL_MSK 7
/*
* Unit code values
*/
#define PM_FPU 1
#define PM_ISU1 2
#define PM_IFU 3
#define PM_IDU0 4
#define PM_ISU1_ALT 6
#define PM_ISU2 7
#define PM_IFU_ALT 8
#define PM_LSU0 9
#define PM_LSU1 0xc
#define PM_GPS 0xf
/*
* Bits in MMCR0 for POWER4
*/
#define MMCR0_PMC1SEL_SH 8
#define MMCR0_PMC2SEL_SH 1
#define MMCR_PMCSEL_MSK 0x1f
/*
* Bits in MMCR1 for POWER4
*/
#define MMCR1_TTM0SEL_SH 62
#define MMCR1_TTC0SEL_SH 61
#define MMCR1_TTM1SEL_SH 59
#define MMCR1_TTC1SEL_SH 58
#define MMCR1_TTM2SEL_SH 56
#define MMCR1_TTC2SEL_SH 55
#define MMCR1_TTM3SEL_SH 53
#define MMCR1_TTC3SEL_SH 52
#define MMCR1_TTMSEL_MSK 3
#define MMCR1_TD_CP_DBG0SEL_SH 50
#define MMCR1_TD_CP_DBG1SEL_SH 48
#define MMCR1_TD_CP_DBG2SEL_SH 46
#define MMCR1_TD_CP_DBG3SEL_SH 44
#define MMCR1_DEBUG0SEL_SH 43
#define MMCR1_DEBUG1SEL_SH 42
#define MMCR1_DEBUG2SEL_SH 41
#define MMCR1_DEBUG3SEL_SH 40
#define MMCR1_PMC1_ADDER_SEL_SH 39
#define MMCR1_PMC2_ADDER_SEL_SH 38
#define MMCR1_PMC6_ADDER_SEL_SH 37
#define MMCR1_PMC5_ADDER_SEL_SH 36
#define MMCR1_PMC8_ADDER_SEL_SH 35
#define MMCR1_PMC7_ADDER_SEL_SH 34
#define MMCR1_PMC3_ADDER_SEL_SH 33
#define MMCR1_PMC4_ADDER_SEL_SH 32
#define MMCR1_PMC3SEL_SH 27
#define MMCR1_PMC4SEL_SH 22
#define MMCR1_PMC5SEL_SH 17
#define MMCR1_PMC6SEL_SH 12
#define MMCR1_PMC7SEL_SH 7
#define MMCR1_PMC8SEL_SH 2 /* note bit 0 is in MMCRA for GP */
static short mmcr1_adder_bits[8] = {
MMCR1_PMC1_ADDER_SEL_SH,
MMCR1_PMC2_ADDER_SEL_SH,
MMCR1_PMC3_ADDER_SEL_SH,
MMCR1_PMC4_ADDER_SEL_SH,
MMCR1_PMC5_ADDER_SEL_SH,
MMCR1_PMC6_ADDER_SEL_SH,
MMCR1_PMC7_ADDER_SEL_SH,
MMCR1_PMC8_ADDER_SEL_SH
};
/*
* Bits in MMCRA
*/
#define MMCRA_PMC8SEL0_SH 17 /* PMC8SEL bit 0 for GP */
/*
* Layout of constraint bits:
* 6666555555555544444444443333333333222222222211111111110000000000
* 3210987654321098765432109876543210987654321098765432109876543210
* |[ >[ >[ >|||[ >[ >< >< >< >< ><><><><><><><><>
* | UC1 UC2 UC3 ||| PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8
* \SMPL ||\TTC3SEL
* |\TTC_IFU_SEL
* \TTM2SEL0
*
* SMPL - SAMPLE_ENABLE constraint
* 56: SAMPLE_ENABLE value 0x0100_0000_0000_0000
*
* UC1 - unit constraint 1: can't have all three of FPU/ISU1/IDU0|ISU2
* 55: UC1 error 0x0080_0000_0000_0000
* 54: FPU events needed 0x0040_0000_0000_0000
* 53: ISU1 events needed 0x0020_0000_0000_0000
* 52: IDU0|ISU2 events needed 0x0010_0000_0000_0000
*
* UC2 - unit constraint 2: can't have all three of FPU/IFU/LSU0
* 51: UC2 error 0x0008_0000_0000_0000
* 50: FPU events needed 0x0004_0000_0000_0000
* 49: IFU events needed 0x0002_0000_0000_0000
* 48: LSU0 events needed 0x0001_0000_0000_0000
*
* UC3 - unit constraint 3: can't have all four of LSU0/IFU/IDU0|ISU2/ISU1
* 47: UC3 error 0x8000_0000_0000
* 46: LSU0 events needed 0x4000_0000_0000
* 45: IFU events needed 0x2000_0000_0000
* 44: IDU0|ISU2 events needed 0x1000_0000_0000
* 43: ISU1 events needed 0x0800_0000_0000
*
* TTM2SEL0
* 42: 0 = IDU0 events needed
* 1 = ISU2 events needed 0x0400_0000_0000
*
* TTC_IFU_SEL
* 41: 0 = IFU.U events needed
* 1 = IFU.L events needed 0x0200_0000_0000
*
* TTC3SEL
* 40: 0 = LSU1.U events needed
* 1 = LSU1.L events needed 0x0100_0000_0000
*
* PS1
* 39: PS1 error 0x0080_0000_0000
* 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
*
* PS2
* 35: PS2 error 0x0008_0000_0000
* 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
*
* B0
* 28-31: Byte 0 event source 0xf000_0000
* 1 = FPU
* 2 = ISU1
* 3 = IFU
* 4 = IDU0
* 7 = ISU2
* 9 = LSU0
* c = LSU1
* f = GPS
*
* B1, B2, B3
* 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
*
* P8
* 15: P8 error 0x8000
* 14-15: Count of events needing PMC8
*
* P1..P7
* 0-13: Count of events needing PMC1..PMC7
*
* Note: this doesn't allow events using IFU.U to be combined with events
* using IFU.L, though that is feasible (using TTM0 and TTM2). However
* there are no listed events for IFU.L (they are debug events not
* verified for performance monitoring) so this shouldn't cause a
* problem.
*/
static struct unitinfo {
u64 value, mask;
int unit;
int lowerbit;
} p4_unitinfo[16] = {
[PM_FPU] = { 0x44000000000000ull, 0x88000000000000ull, PM_FPU, 0 },
[PM_ISU1] = { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 },
[PM_ISU1_ALT] =
{ 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 },
[PM_IFU] = { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 },
[PM_IFU_ALT] =
{ 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 },
[PM_IDU0] = { 0x10100000000000ull, 0x80840000000000ull, PM_IDU0, 1 },
[PM_ISU2] = { 0x10140000000000ull, 0x80840000000000ull, PM_ISU2, 0 },
[PM_LSU0] = { 0x01400000000000ull, 0x08800000000000ull, PM_LSU0, 0 },
[PM_LSU1] = { 0x00000000000000ull, 0x00010000000000ull, PM_LSU1, 40 },
[PM_GPS] = { 0x00000000000000ull, 0x00000000000000ull, PM_GPS, 0 }
};
static unsigned char direct_marked_event[8] = {
(1<<2) | (1<<3), /* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */
(1<<3) | (1<<5), /* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */
(1<<3), /* PMC3: PM_MRK_ST_CMPL_INT */
(1<<4) | (1<<5), /* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */
(1<<4) | (1<<5), /* PMC5: PM_MRK_GRP_TIMEO */
(1<<3) | (1<<4) | (1<<5),
/* PMC6: PM_MRK_ST_GPS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */
(1<<4) | (1<<5), /* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */
(1<<4), /* PMC8: PM_MRK_LSU_FIN */
};
/*
* Returns 1 if event counts things relating to marked instructions
* and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
*/
static int p4_marked_instr_event(u64 event)
{
int pmc, psel, unit, byte, bit;
unsigned int mask;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
psel = event & PM_PMCSEL_MSK;
if (pmc) {
if (direct_marked_event[pmc - 1] & (1 << psel))
return 1;
if (psel == 0) /* add events */
bit = (pmc <= 4)? pmc - 1: 8 - pmc;
else if (psel == 6) /* decode events */
bit = 4;
else
return 0;
} else
bit = psel;
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
mask = 0;
switch (unit) {
case PM_LSU1:
if (event & PM_LOWER_MSKS)
mask = 1 << 28; /* byte 7 bit 4 */
else
mask = 6 << 24; /* byte 3 bits 1 and 2 */
break;
case PM_LSU0:
/* byte 3, bit 3; byte 2 bits 0,2,3,4,5; byte 1 */
mask = 0x083dff00;
}
return (mask >> (byte * 8 + bit)) & 1;
}
static int p4_get_constraint(u64 event, u64 *maskp, u64 *valp)
{
int pmc, byte, unit, lower, sh;
u64 mask = 0, value = 0;
int grp = -1;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 8)
return -1;
sh = (pmc - 1) * 2;
mask |= 2 << sh;
value |= 1 << sh;
grp = ((pmc - 1) >> 1) & 1;
}
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
if (unit) {
lower = (event >> PM_LOWER_SH) & PM_LOWER_MSK;
/*
* Bus events on bytes 0 and 2 can be counted
* on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
*/
if (!pmc)
grp = byte & 1;
if (!p4_unitinfo[unit].unit)
return -1;
mask |= p4_unitinfo[unit].mask;
value |= p4_unitinfo[unit].value;
sh = p4_unitinfo[unit].lowerbit;
if (sh > 1)
value |= (u64)lower << sh;
else if (lower != sh)
return -1;
unit = p4_unitinfo[unit].unit;
/* Set byte lane select field */
mask |= 0xfULL << (28 - 4 * byte);
value |= (u64)unit << (28 - 4 * byte);
}
if (grp == 0) {
/* increment PMC1/2/5/6 field */
mask |= 0x8000000000ull;
value |= 0x1000000000ull;
} else {
/* increment PMC3/4/7/8 field */
mask |= 0x800000000ull;
value |= 0x100000000ull;
}
/* Marked instruction events need sample_enable set */
if (p4_marked_instr_event(event)) {
mask |= 1ull << 56;
value |= 1ull << 56;
}
/* PMCSEL=6 decode events on byte 2 need sample_enable clear */
if (pmc && (event & PM_PMCSEL_MSK) == 6 && byte == 2)
mask |= 1ull << 56;
*maskp = mask;
*valp = value;
return 0;
}
static unsigned int ppc_inst_cmpl[] = {
0x1001, 0x4001, 0x6001, 0x7001, 0x8001
};
static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[])
{
int i, j, na;
alt[0] = event;
na = 1;
/* 2 possibilities for PM_GRP_DISP_REJECT */
if (event == 0x8003 || event == 0x0224) {
alt[1] = event ^ (0x8003 ^ 0x0224);
return 2;
}
/* 2 possibilities for PM_ST_MISS_L1 */
if (event == 0x0c13 || event == 0x0c23) {
alt[1] = event ^ (0x0c13 ^ 0x0c23);
return 2;
}
/* several possibilities for PM_INST_CMPL */
for (i = 0; i < ARRAY_SIZE(ppc_inst_cmpl); ++i) {
if (event == ppc_inst_cmpl[i]) {
for (j = 0; j < ARRAY_SIZE(ppc_inst_cmpl); ++j)
if (j != i)
alt[na++] = ppc_inst_cmpl[j];
break;
}
}
return na;
}
static int p4_compute_mmcr(u64 event[], int n_ev,
unsigned int hwc[], u64 mmcr[])
{
u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0;
unsigned int pmc, unit, byte, psel, lower;
unsigned int ttm, grp;
unsigned int pmc_inuse = 0;
unsigned int pmc_grp_use[2];
unsigned char busbyte[4];
unsigned char unituse[16];
unsigned int unitlower = 0;
int i;
if (n_ev > 8)
return -1;
/* First pass to count resource use */
pmc_grp_use[0] = pmc_grp_use[1] = 0;
memset(busbyte, 0, sizeof(busbyte));
memset(unituse, 0, sizeof(unituse));
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc_inuse & (1 << (pmc - 1)))
return -1;
pmc_inuse |= 1 << (pmc - 1);
/* count 1/2/5/6 vs 3/4/7/8 use */
++pmc_grp_use[((pmc - 1) >> 1) & 1];
}
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
lower = (event[i] >> PM_LOWER_SH) & PM_LOWER_MSK;
if (unit) {
if (!pmc)
++pmc_grp_use[byte & 1];
if (unit == 6 || unit == 8)
/* map alt ISU1/IFU codes: 6->2, 8->3 */
unit = (unit >> 1) - 1;
if (busbyte[byte] && busbyte[byte] != unit)
return -1;
busbyte[byte] = unit;
lower <<= unit;
if (unituse[unit] && lower != (unitlower & lower))
return -1;
unituse[unit] = 1;
unitlower |= lower;
}
}
if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
return -1;
/*
* Assign resources and set multiplexer selects.
*
* Units 1,2,3 are on TTM0, 4,6,7 on TTM1, 8,10 on TTM2.
* Each TTMx can only select one unit, but since
* units 2 and 6 are both ISU1, and 3 and 8 are both IFU,
* we have some choices.
*/
if (unituse[2] & (unituse[1] | (unituse[3] & unituse[9]))) {
unituse[6] = 1; /* Move 2 to 6 */
unituse[2] = 0;
}
if (unituse[3] & (unituse[1] | unituse[2])) {
unituse[8] = 1; /* Move 3 to 8 */
unituse[3] = 0;
unitlower = (unitlower & ~8) | ((unitlower & 8) << 5);
}
/* Check only one unit per TTMx */
if (unituse[1] + unituse[2] + unituse[3] > 1 ||
unituse[4] + unituse[6] + unituse[7] > 1 ||
unituse[8] + unituse[9] > 1 ||
(unituse[5] | unituse[10] | unituse[11] |
unituse[13] | unituse[14]))
return -1;
/* Set TTMxSEL fields. Note, units 1-3 => TTM0SEL codes 0-2 */
mmcr1 |= (u64)(unituse[3] * 2 + unituse[2]) << MMCR1_TTM0SEL_SH;
mmcr1 |= (u64)(unituse[7] * 3 + unituse[6] * 2) << MMCR1_TTM1SEL_SH;
mmcr1 |= (u64)unituse[9] << MMCR1_TTM2SEL_SH;
/* Set TTCxSEL fields. */
if (unitlower & 0xe)
mmcr1 |= 1ull << MMCR1_TTC0SEL_SH;
if (unitlower & 0xf0)
mmcr1 |= 1ull << MMCR1_TTC1SEL_SH;
if (unitlower & 0xf00)
mmcr1 |= 1ull << MMCR1_TTC2SEL_SH;
if (unitlower & 0x7000)
mmcr1 |= 1ull << MMCR1_TTC3SEL_SH;
/* Set byte lane select fields. */
for (byte = 0; byte < 4; ++byte) {
unit = busbyte[byte];
if (!unit)
continue;
if (unit == 0xf) {
/* special case for GPS */
mmcr1 |= 1ull << (MMCR1_DEBUG0SEL_SH - byte);
} else {
if (!unituse[unit])
ttm = unit - 1; /* 2->1, 3->2 */
else
ttm = unit >> 2;
mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2*byte);
}
}
/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
psel = event[i] & PM_PMCSEL_MSK;
if (!pmc) {
/* Bus event or 00xxx direct event (off or cycles) */
if (unit)
psel |= 0x10 | ((byte & 2) << 2);
for (pmc = 0; pmc < 8; ++pmc) {
if (pmc_inuse & (1 << pmc))
continue;
grp = (pmc >> 1) & 1;
if (unit) {
if (grp == (byte & 1))
break;
} else if (pmc_grp_use[grp] < 4) {
++pmc_grp_use[grp];
break;
}
}
pmc_inuse |= 1 << pmc;
} else {
/* Direct event */
--pmc;
if (psel == 0 && (byte & 2))
/* add events on higher-numbered bus */
mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
else if (psel == 6 && byte == 3)
/* seem to need to set sample_enable here */
mmcra |= MMCRA_SAMPLE_ENABLE;
psel |= 8;
}
if (pmc <= 1)
mmcr0 |= psel << (MMCR0_PMC1SEL_SH - 7 * pmc);
else
mmcr1 |= psel << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
if (pmc == 7) /* PMC8 */
mmcra |= (psel & 1) << MMCRA_PMC8SEL0_SH;
hwc[i] = pmc;
if (p4_marked_instr_event(event[i]))
mmcra |= MMCRA_SAMPLE_ENABLE;
}
if (pmc_inuse & 1)
mmcr0 |= MMCR0_PMC1CE;
if (pmc_inuse & 0xfe)
mmcr0 |= MMCR0_PMCjCE;
mmcra |= 0x2000; /* mark only one IOP per PPC instruction */
/* Return MMCRx values */
mmcr[0] = mmcr0;
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
return 0;
}
static void p4_disable_pmc(unsigned int pmc, u64 mmcr[])
{
/*
* Setting the PMCxSEL field to 0 disables PMC x.
* (Note that pmc is 0-based here, not 1-based.)
*/
if (pmc <= 1) {
mmcr[0] &= ~(0x1fUL << (MMCR0_PMC1SEL_SH - 7 * pmc));
} else {
mmcr[1] &= ~(0x1fUL << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)));
if (pmc == 7)
mmcr[2] &= ~(1UL << MMCRA_PMC8SEL0_SH);
}
}
static int p4_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = 7,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x1001,
[PERF_COUNT_HW_CACHE_REFERENCES] = 0x8c10, /* PM_LD_REF_L1 */
[PERF_COUNT_HW_CACHE_MISSES] = 0x3c10, /* PM_LD_MISS_L1 */
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x330, /* PM_BR_ISSUED */
[PERF_COUNT_HW_BRANCH_MISSES] = 0x331, /* PM_BR_MPRED_CR */
};
#define C(x) PERF_COUNT_HW_CACHE_##x
/*
* Table of generalized cache-related events.
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x8c10, 0x3c10 },
[C(OP_WRITE)] = { 0x7c10, 0xc13 },
[C(OP_PREFETCH)] = { 0xc35, 0 },
},
[C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { 0, 0 },
},
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { 0, 0 },
[C(OP_PREFETCH)] = { 0xc34, 0 },
},
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x904 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x900 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x330, 0x331 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
};
struct power_pmu power4_pmu = {
.n_counter = 8,
.max_alternatives = 5,
.add_fields = 0x0000001100005555ull,
.test_adder = 0x0011083300000000ull,
.compute_mmcr = p4_compute_mmcr,
.get_constraint = p4_get_constraint,
.get_alternatives = p4_get_alternatives,
.disable_pmc = p4_disable_pmc,
.n_generic = ARRAY_SIZE(p4_generic_events),
.generic_events = p4_generic_events,
.cache_events = &power4_cache_events,
};

671
arch/powerpc/kernel/power5+-pmu.c Normal file
View File

@ -0,0 +1,671 @@
/*
* Performance counter support for POWER5+/++ (not POWER5) processors.
*
* Copyright 2009 Paul Mackerras, IBM Corporation.
*
* This program 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.
*/
#include <linux/kernel.h>
#include <linux/perf_counter.h>
#include <asm/reg.h>
/*
* Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3)
*/
#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */
#define PM_PMC_MSK 0xf
#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH)
#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */
#define PM_UNIT_MSK 0xf
#define PM_BYTE_SH 12 /* Byte number of event bus to use */
#define PM_BYTE_MSK 7
#define PM_GRS_SH 8 /* Storage subsystem mux select */
#define PM_GRS_MSK 7
#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */
#define PM_PMCSEL_MSK 0x7f
/* Values in PM_UNIT field */
#define PM_FPU 0
#define PM_ISU0 1
#define PM_IFU 2
#define PM_ISU1 3
#define PM_IDU 4
#define PM_ISU0_ALT 6
#define PM_GRS 7
#define PM_LSU0 8
#define PM_LSU1 0xc
#define PM_LASTUNIT 0xc
/*
* Bits in MMCR1 for POWER5+
*/
#define MMCR1_TTM0SEL_SH 62
#define MMCR1_TTM1SEL_SH 60
#define MMCR1_TTM2SEL_SH 58
#define MMCR1_TTM3SEL_SH 56
#define MMCR1_TTMSEL_MSK 3
#define MMCR1_TD_CP_DBG0SEL_SH 54
#define MMCR1_TD_CP_DBG1SEL_SH 52
#define MMCR1_TD_CP_DBG2SEL_SH 50
#define MMCR1_TD_CP_DBG3SEL_SH 48
#define MMCR1_GRS_L2SEL_SH 46
#define MMCR1_GRS_L2SEL_MSK 3
#define MMCR1_GRS_L3SEL_SH 44
#define MMCR1_GRS_L3SEL_MSK 3
#define MMCR1_GRS_MCSEL_SH 41
#define MMCR1_GRS_MCSEL_MSK 7
#define MMCR1_GRS_FABSEL_SH 39
#define MMCR1_GRS_FABSEL_MSK 3
#define MMCR1_PMC1_ADDER_SEL_SH 35
#define MMCR1_PMC2_ADDER_SEL_SH 34
#define MMCR1_PMC3_ADDER_SEL_SH 33
#define MMCR1_PMC4_ADDER_SEL_SH 32
#define MMCR1_PMC1SEL_SH 25
#define MMCR1_PMC2SEL_SH 17
#define MMCR1_PMC3SEL_SH 9
#define MMCR1_PMC4SEL_SH 1
#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8)
#define MMCR1_PMCSEL_MSK 0x7f
/*
* Bits in MMCRA
*/
/*
* Layout of constraint bits:
* 6666555555555544444444443333333333222222222211111111110000000000
* 3210987654321098765432109876543210987654321098765432109876543210
* [ ><><>< ><> <><>[ > < >< >< >< ><><><><><><>
* NC G0G1G2 G3 T0T1 UC B0 B1 B2 B3 P6P5P4P3P2P1
*
* NC - number of counters
* 51: NC error 0x0008_0000_0000_0000
* 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000
*
* G0..G3 - GRS mux constraints
* 46-47: GRS_L2SEL value
* 44-45: GRS_L3SEL value
* 41-44: GRS_MCSEL value
* 39-40: GRS_FABSEL value
* Note that these match up with their bit positions in MMCR1
*
* T0 - TTM0 constraint
* 36-37: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0x30_0000_0000
*
* T1 - TTM1 constraint
* 34-35: TTM1SEL value (0=IDU, 3=GRS) 0x0c_0000_0000
*
* UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS
* 33: UC3 error 0x02_0000_0000
* 32: FPU|IFU|ISU1 events needed 0x01_0000_0000
* 31: ISU0 events needed 0x01_8000_0000
* 30: IDU|GRS events needed 0x00_4000_0000
*
* B0
* 24-27: Byte 0 event source 0x0f00_0000
* Encoding as for the event code
*
* B1, B2, B3
* 20-23, 16-19, 12-15: Byte 1, 2, 3 event sources
*
* P6
* 11: P6 error 0x800
* 10-11: Count of events needing PMC6
*
* P1..P5
* 0-9: Count of events needing PMC1..PMC5
*/
static const int grsel_shift[8] = {
MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH,
MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH,
MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH
};
/* Masks and values for using events from the various units */
static u64 unit_cons[PM_LASTUNIT+1][2] = {
[PM_FPU] = { 0x3200000000ull, 0x0100000000ull },
[PM_ISU0] = { 0x0200000000ull, 0x0080000000ull },
[PM_ISU1] = { 0x3200000000ull, 0x3100000000ull },
[PM_IFU] = { 0x3200000000ull, 0x2100000000ull },
[PM_IDU] = { 0x0e00000000ull, 0x0040000000ull },
[PM_GRS] = { 0x0e00000000ull, 0x0c40000000ull },
};
static int power5p_get_constraint(u64 event, u64 *maskp, u64 *valp)
{
int pmc, byte, unit, sh;
int bit, fmask;
u64 mask = 0, value = 0;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 6)
return -1;
sh = (pmc - 1) * 2;
mask |= 2 << sh;
value |= 1 << sh;
if (pmc >= 5 && !(event == 0x500009 || event == 0x600005))
return -1;
}
if (event & PM_BUSEVENT_MSK) {
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
if (unit > PM_LASTUNIT)
return -1;
if (unit == PM_ISU0_ALT)
unit = PM_ISU0;
mask |= unit_cons[unit][0];
value |= unit_cons[unit][1];
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
if (byte >= 4) {
if (unit != PM_LSU1)
return -1;
/* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */
++unit;
byte &= 3;
}
if (unit == PM_GRS) {
bit = event & 7;
fmask = (bit == 6)? 7: 3;
sh = grsel_shift[bit];
mask |= (u64)fmask << sh;
value |= (u64)((event >> PM_GRS_SH) & fmask) << sh;
}
/* Set byte lane select field */
mask |= 0xfULL << (24 - 4 * byte);
value |= (u64)unit << (24 - 4 * byte);
}
if (pmc < 5) {
/* need a counter from PMC1-4 set */
mask |= 0x8000000000000ull;
value |= 0x1000000000000ull;
}
*maskp = mask;
*valp = value;
return 0;
}
static int power5p_limited_pmc_event(u64 event)
{
int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
return pmc == 5 || pmc == 6;
}
#define MAX_ALT 3 /* at most 3 alternatives for any event */
static const unsigned int event_alternatives[][MAX_ALT] = {
{ 0x100c0, 0x40001f }, /* PM_GCT_FULL_CYC */
{ 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */
{ 0x230e2, 0x323087 }, /* PM_BR_PRED_CR */
{ 0x230e3, 0x223087, 0x3230a0 }, /* PM_BR_PRED_TA */
{ 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */
{ 0x800c4, 0xc20e0 }, /* PM_DTLB_MISS */
{ 0xc50c6, 0xc60e0 }, /* PM_MRK_DTLB_MISS */
{ 0x100005, 0x600005 }, /* PM_RUN_CYC */
{ 0x100009, 0x200009 }, /* PM_INST_CMPL */
{ 0x200015, 0x300015 }, /* PM_LSU_LMQ_SRQ_EMPTY_CYC */
{ 0x300009, 0x400009 }, /* PM_INST_DISP */
};
/*
* Scan the alternatives table for a match and return the
* index into the alternatives table if found, else -1.
*/
static int find_alternative(unsigned int event)
{
int i, j;
for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
if (event < event_alternatives[i][0])
break;
for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
if (event == event_alternatives[i][j])
return i;
}
return -1;
}
static const unsigned char bytedecode_alternatives[4][4] = {
/* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 },
/* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e },
/* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 },
/* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e }
};
/*
* Some direct events for decodes of event bus byte 3 have alternative
* PMCSEL values on other counters. This returns the alternative
* event code for those that do, or -1 otherwise. This also handles
* alternative PCMSEL values for add events.
*/
static s64 find_alternative_bdecode(u64 event)
{
int pmc, altpmc, pp, j;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc == 0 || pmc > 4)
return -1;
altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */
pp = event & PM_PMCSEL_MSK;
for (j = 0; j < 4; ++j) {
if (bytedecode_alternatives[pmc - 1][j] == pp) {
return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) |
(altpmc << PM_PMC_SH) |
bytedecode_alternatives[altpmc - 1][j];
}
}
/* new decode alternatives for power5+ */
if (pmc == 1 && (pp == 0x0d || pp == 0x0e))
return event + (2 << PM_PMC_SH) + (0x2e - 0x0d);
if (pmc == 3 && (pp == 0x2e || pp == 0x2f))
return event - (2 << PM_PMC_SH) - (0x2e - 0x0d);
/* alternative add event encodings */
if (pp == 0x10 || pp == 0x28)
return ((event ^ (0x10 ^ 0x28)) & ~PM_PMC_MSKS) |
(altpmc << PM_PMC_SH);
return -1;
}
static int power5p_get_alternatives(u64 event, unsigned int flags, u64 alt[])
{
int i, j, nalt = 1;
int nlim;
s64 ae;
alt[0] = event;
nalt = 1;
nlim = power5p_limited_pmc_event(event);
i = find_alternative(event);
if (i >= 0) {
for (j = 0; j < MAX_ALT; ++j) {
ae = event_alternatives[i][j];
if (ae && ae != event)
alt[nalt++] = ae;
nlim += power5p_limited_pmc_event(ae);
}
} else {
ae = find_alternative_bdecode(event);
if (ae > 0)
alt[nalt++] = ae;
}
if (flags & PPMU_ONLY_COUNT_RUN) {
/*
* We're only counting in RUN state,
* so PM_CYC is equivalent to PM_RUN_CYC
* and PM_INST_CMPL === PM_RUN_INST_CMPL.
* This doesn't include alternatives that don't provide
* any extra flexibility in assigning PMCs (e.g.
* 0x100005 for PM_RUN_CYC vs. 0xf for PM_CYC).
* Note that even with these additional alternatives
* we never end up with more than 3 alternatives for any event.
*/
j = nalt;
for (i = 0; i < nalt; ++i) {
switch (alt[i]) {
case 0xf: /* PM_CYC */
alt[j++] = 0x600005; /* PM_RUN_CYC */
++nlim;
break;
case 0x600005: /* PM_RUN_CYC */
alt[j++] = 0xf;
break;
case 0x100009: /* PM_INST_CMPL */
alt[j++] = 0x500009; /* PM_RUN_INST_CMPL */
++nlim;
break;
case 0x500009: /* PM_RUN_INST_CMPL */
alt[j++] = 0x100009; /* PM_INST_CMPL */
alt[j++] = 0x200009;
break;
}
}
nalt = j;
}
if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) {
/* remove the limited PMC events */
j = 0;
for (i = 0; i < nalt; ++i) {
if (!power5p_limited_pmc_event(alt[i])) {
alt[j] = alt[i];
++j;
}
}
nalt = j;
} else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) {
/* remove all but the limited PMC events */
j = 0;
for (i = 0; i < nalt; ++i) {
if (power5p_limited_pmc_event(alt[i])) {
alt[j] = alt[i];
++j;
}
}
nalt = j;
}
return nalt;
}
/*
* Map of which direct events on which PMCs are marked instruction events.
* Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event.
* Bit 0 is set if it is marked for all PMCs.
* The 0x80 bit indicates a byte decode PMCSEL value.
*/
static unsigned char direct_event_is_marked[0x28] = {
0, /* 00 */
0x1f, /* 01 PM_IOPS_CMPL */
0x2, /* 02 PM_MRK_GRP_DISP */
0xe, /* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
0, /* 04 */
0x1c, /* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */
0x80, /* 06 */
0x80, /* 07 */
0, 0, 0,/* 08 - 0a */
0x18, /* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */
0, /* 0c */
0x80, /* 0d */
0x80, /* 0e */
0, /* 0f */
0, /* 10 */
0x14, /* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */
0, /* 12 */
0x10, /* 13 PM_MRK_GRP_CMPL */
0x1f, /* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */
0x2, /* 15 PM_MRK_GRP_ISSUED */
0x80, /* 16 */
0x80, /* 17 */
0, 0, 0, 0, 0,
0x80, /* 1d */
0x80, /* 1e */
0, /* 1f */
0x80, /* 20 */
0x80, /* 21 */
0x80, /* 22 */
0x80, /* 23 */
0x80, /* 24 */
0x80, /* 25 */
0x80, /* 26 */
0x80, /* 27 */
};
/*
* Returns 1 if event counts things relating to marked instructions
* and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
*/
static int power5p_marked_instr_event(u64 event)
{
int pmc, psel;
int bit, byte, unit;
u32 mask;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
psel = event & PM_PMCSEL_MSK;
if (pmc >= 5)
return 0;
bit = -1;
if (psel < sizeof(direct_event_is_marked)) {
if (direct_event_is_marked[psel] & (1 << pmc))
return 1;
if (direct_event_is_marked[psel] & 0x80)
bit = 4;
else if (psel == 0x08)
bit = pmc - 1;
else if (psel == 0x10)
bit = 4 - pmc;
else if (psel == 0x1b && (pmc == 1 || pmc == 3))
bit = 4;
} else if ((psel & 0x48) == 0x40) {
bit = psel & 7;
} else if (psel == 0x28) {
bit = pmc - 1;
} else if (pmc == 3 && (psel == 0x2e || psel == 0x2f)) {
bit = 4;
}
if (!(event & PM_BUSEVENT_MSK) || bit == -1)
return 0;
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
if (unit == PM_LSU0) {
/* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */
mask = 0x5dff00;
} else if (unit == PM_LSU1 && byte >= 4) {
byte -= 4;
/* byte 5 bits 6-7, byte 6 bits 0,4, byte 7 bits 0-4,6 */
mask = 0x5f11c000;
} else
return 0;
return (mask >> (byte * 8 + bit)) & 1;
}
static int power5p_compute_mmcr(u64 event[], int n_ev,
unsigned int hwc[], u64 mmcr[])
{
u64 mmcr1 = 0;
u64 mmcra = 0;
unsigned int pmc, unit, byte, psel;
unsigned int ttm;
int i, isbus, bit, grsel;
unsigned int pmc_inuse = 0;
unsigned char busbyte[4];
unsigned char unituse[16];
int ttmuse;
if (n_ev > 6)
return -1;
/* First pass to count resource use */
memset(busbyte, 0, sizeof(busbyte));
memset(unituse, 0, sizeof(unituse));
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 6)
return -1;
if (pmc_inuse & (1 << (pmc - 1)))
return -1;
pmc_inuse |= 1 << (pmc - 1);
}
if (event[i] & PM_BUSEVENT_MSK) {
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
if (unit > PM_LASTUNIT)
return -1;
if (unit == PM_ISU0_ALT)
unit = PM_ISU0;
if (byte >= 4) {
if (unit != PM_LSU1)
return -1;
++unit;
byte &= 3;
}
if (busbyte[byte] && busbyte[byte] != unit)
return -1;
busbyte[byte] = unit;
unituse[unit] = 1;
}
}
/*
* Assign resources and set multiplexer selects.
*
* PM_ISU0 can go either on TTM0 or TTM1, but that's the only
* choice we have to deal with.
*/
if (unituse[PM_ISU0] &
(unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) {
unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */
unituse[PM_ISU0] = 0;
}
/* Set TTM[01]SEL fields. */
ttmuse = 0;
for (i = PM_FPU; i <= PM_ISU1; ++i) {
if (!unituse[i])
continue;
if (ttmuse++)
return -1;
mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH;
}
ttmuse = 0;
for (; i <= PM_GRS; ++i) {
if (!unituse[i])
continue;
if (ttmuse++)
return -1;
mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH;
}
if (ttmuse > 1)
return -1;
/* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */
for (byte = 0; byte < 4; ++byte) {
unit = busbyte[byte];
if (!unit)
continue;
if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) {
/* get ISU0 through TTM1 rather than TTM0 */
unit = PM_ISU0_ALT;
} else if (unit == PM_LSU1 + 1) {
/* select lower word of LSU1 for this byte */
mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
}
ttm = unit >> 2;
mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
}
/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
psel = event[i] & PM_PMCSEL_MSK;
isbus = event[i] & PM_BUSEVENT_MSK;
if (!pmc) {
/* Bus event or any-PMC direct event */
for (pmc = 0; pmc < 4; ++pmc) {
if (!(pmc_inuse & (1 << pmc)))
break;
}
if (pmc >= 4)
return -1;
pmc_inuse |= 1 << pmc;
} else if (pmc <= 4) {
/* Direct event */
--pmc;
if (isbus && (byte & 2) &&
(psel == 8 || psel == 0x10 || psel == 0x28))
/* add events on higher-numbered bus */
mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
} else {
/* Instructions or run cycles on PMC5/6 */
--pmc;
}
if (isbus && unit == PM_GRS) {
bit = psel & 7;
grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
mmcr1 |= (u64)grsel << grsel_shift[bit];
}
if (power5p_marked_instr_event(event[i]))
mmcra |= MMCRA_SAMPLE_ENABLE;
if ((psel & 0x58) == 0x40 && (byte & 1) != ((pmc >> 1) & 1))
/* select alternate byte lane */
psel |= 0x10;
if (pmc <= 3)
mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
hwc[i] = pmc;
}
/* Return MMCRx values */
mmcr[0] = 0;
if (pmc_inuse & 1)
mmcr[0] = MMCR0_PMC1CE;
if (pmc_inuse & 0x3e)
mmcr[0] |= MMCR0_PMCjCE;
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
return 0;
}
static void power5p_disable_pmc(unsigned int pmc, u64 mmcr[])
{
if (pmc <= 3)
mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
}
static int power5p_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = 0xf,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x100009,
[PERF_COUNT_HW_CACHE_REFERENCES] = 0x1c10a8, /* LD_REF_L1 */
[PERF_COUNT_HW_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */
[PERF_COUNT_HW_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */
};
#define C(x) PERF_COUNT_HW_CACHE_##x
/*
* Table of generalized cache-related events.
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x1c10a8, 0x3c1088 },
[C(OP_WRITE)] = { 0x2c10a8, 0xc10c3 },
[C(OP_PREFETCH)] = { 0xc70e7, -1 },
},
[C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { 0, 0 },
},
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { 0, 0 },
[C(OP_PREFETCH)] = { 0xc50c3, 0 },
},
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0xc20e4, 0x800c4 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x800c0 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x230e4, 0x230e5 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
};
struct power_pmu power5p_pmu = {
.n_counter = 6,
.max_alternatives = MAX_ALT,
.add_fields = 0x7000000000055ull,
.test_adder = 0x3000040000000ull,
.compute_mmcr = power5p_compute_mmcr,
.get_constraint = power5p_get_constraint,
.get_alternatives = power5p_get_alternatives,
.disable_pmc = power5p_disable_pmc,
.limited_pmc_event = power5p_limited_pmc_event,
.flags = PPMU_LIMITED_PMC5_6,
.n_generic = ARRAY_SIZE(power5p_generic_events),
.generic_events = power5p_generic_events,
.cache_events = &power5p_cache_events,
};

611
arch/powerpc/kernel/power5-pmu.c Normal file
View File

@ -0,0 +1,611 @@
/*
* Performance counter support for POWER5 (not POWER5++) processors.
*
* Copyright 2009 Paul Mackerras, IBM Corporation.
*
* This program 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.
*/
#include <linux/kernel.h>
#include <linux/perf_counter.h>
#include <asm/reg.h>
/*
* Bits in event code for POWER5 (not POWER5++)
*/
#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */
#define PM_PMC_MSK 0xf
#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH)
#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */
#define PM_UNIT_MSK 0xf
#define PM_BYTE_SH 12 /* Byte number of event bus to use */
#define PM_BYTE_MSK 7
#define PM_GRS_SH 8 /* Storage subsystem mux select */
#define PM_GRS_MSK 7
#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */
#define PM_PMCSEL_MSK 0x7f
/* Values in PM_UNIT field */
#define PM_FPU 0
#define PM_ISU0 1
#define PM_IFU 2
#define PM_ISU1 3
#define PM_IDU 4
#define PM_ISU0_ALT 6
#define PM_GRS 7
#define PM_LSU0 8
#define PM_LSU1 0xc
#define PM_LASTUNIT 0xc
/*
* Bits in MMCR1 for POWER5
*/
#define MMCR1_TTM0SEL_SH 62
#define MMCR1_TTM1SEL_SH 60
#define MMCR1_TTM2SEL_SH 58
#define MMCR1_TTM3SEL_SH 56
#define MMCR1_TTMSEL_MSK 3
#define MMCR1_TD_CP_DBG0SEL_SH 54
#define MMCR1_TD_CP_DBG1SEL_SH 52
#define MMCR1_TD_CP_DBG2SEL_SH 50
#define MMCR1_TD_CP_DBG3SEL_SH 48
#define MMCR1_GRS_L2SEL_SH 46
#define MMCR1_GRS_L2SEL_MSK 3
#define MMCR1_GRS_L3SEL_SH 44
#define MMCR1_GRS_L3SEL_MSK 3
#define MMCR1_GRS_MCSEL_SH 41
#define MMCR1_GRS_MCSEL_MSK 7
#define MMCR1_GRS_FABSEL_SH 39
#define MMCR1_GRS_FABSEL_MSK 3
#define MMCR1_PMC1_ADDER_SEL_SH 35
#define MMCR1_PMC2_ADDER_SEL_SH 34
#define MMCR1_PMC3_ADDER_SEL_SH 33
#define MMCR1_PMC4_ADDER_SEL_SH 32
#define MMCR1_PMC1SEL_SH 25
#define MMCR1_PMC2SEL_SH 17
#define MMCR1_PMC3SEL_SH 9
#define MMCR1_PMC4SEL_SH 1
#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8)
#define MMCR1_PMCSEL_MSK 0x7f
/*
* Bits in MMCRA
*/
/*
* Layout of constraint bits:
* 6666555555555544444444443333333333222222222211111111110000000000
* 3210987654321098765432109876543210987654321098765432109876543210
* <><>[ ><><>< ><> [ >[ >[ >< >< >< >< ><><><><><><>
* T0T1 NC G0G1G2 G3 UC PS1PS2 B0 B1 B2 B3 P6P5P4P3P2P1
*
* T0 - TTM0 constraint
* 54-55: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0xc0_0000_0000_0000
*
* T1 - TTM1 constraint
* 52-53: TTM1SEL value (0=IDU, 3=GRS) 0x30_0000_0000_0000
*
* NC - number of counters
* 51: NC error 0x0008_0000_0000_0000
* 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000
*
* G0..G3 - GRS mux constraints
* 46-47: GRS_L2SEL value
* 44-45: GRS_L3SEL value
* 41-44: GRS_MCSEL value
* 39-40: GRS_FABSEL value
* Note that these match up with their bit positions in MMCR1
*
* UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS
* 37: UC3 error 0x20_0000_0000
* 36: FPU|IFU|ISU1 events needed 0x10_0000_0000
* 35: ISU0 events needed 0x08_0000_0000
* 34: IDU|GRS events needed 0x04_0000_0000
*
* PS1
* 33: PS1 error 0x2_0000_0000
* 31-32: count of events needing PMC1/2 0x1_8000_0000
*
* PS2
* 30: PS2 error 0x4000_0000
* 28-29: count of events needing PMC3/4 0x3000_0000
*
* B0
* 24-27: Byte 0 event source 0x0f00_0000
* Encoding as for the event code
*
* B1, B2, B3
* 20-23, 16-19, 12-15: Byte 1, 2, 3 event sources
*
* P1..P6
* 0-11: Count of events needing PMC1..PMC6
*/
static const int grsel_shift[8] = {
MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH,
MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH,
MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH
};
/* Masks and values for using events from the various units */
static u64 unit_cons[PM_LASTUNIT+1][2] = {
[PM_FPU] = { 0xc0002000000000ull, 0x00001000000000ull },
[PM_ISU0] = { 0x00002000000000ull, 0x00000800000000ull },
[PM_ISU1] = { 0xc0002000000000ull, 0xc0001000000000ull },
[PM_IFU] = { 0xc0002000000000ull, 0x80001000000000ull },
[PM_IDU] = { 0x30002000000000ull, 0x00000400000000ull },
[PM_GRS] = { 0x30002000000000ull, 0x30000400000000ull },
};
static int power5_get_constraint(u64 event, u64 *maskp, u64 *valp)
{
int pmc, byte, unit, sh;
int bit, fmask;
u64 mask = 0, value = 0;
int grp = -1;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 6)
return -1;
sh = (pmc - 1) * 2;
mask |= 2 << sh;
value |= 1 << sh;
if (pmc <= 4)
grp = (pmc - 1) >> 1;
else if (event != 0x500009 && event != 0x600005)
return -1;
}
if (event & PM_BUSEVENT_MSK) {
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
if (unit > PM_LASTUNIT)
return -1;
if (unit == PM_ISU0_ALT)
unit = PM_ISU0;
mask |= unit_cons[unit][0];
value |= unit_cons[unit][1];
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
if (byte >= 4) {
if (unit != PM_LSU1)
return -1;
/* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */
++unit;
byte &= 3;
}
if (unit == PM_GRS) {
bit = event & 7;
fmask = (bit == 6)? 7: 3;
sh = grsel_shift[bit];
mask |= (u64)fmask << sh;
value |= (u64)((event >> PM_GRS_SH) & fmask) << sh;
}
/*
* Bus events on bytes 0 and 2 can be counted
* on PMC1/2; bytes 1 and 3 on PMC3/4.
*/
if (!pmc)
grp = byte & 1;
/* Set byte lane select field */
mask |= 0xfULL << (24 - 4 * byte);
value |= (u64)unit << (24 - 4 * byte);
}
if (grp == 0) {
/* increment PMC1/2 field */
mask |= 0x200000000ull;
value |= 0x080000000ull;
} else if (grp == 1) {
/* increment PMC3/4 field */
mask |= 0x40000000ull;
value |= 0x10000000ull;
}
if (pmc < 5) {
/* need a counter from PMC1-4 set */
mask |= 0x8000000000000ull;
value |= 0x1000000000000ull;
}
*maskp = mask;
*valp = value;
return 0;
}
#define MAX_ALT 3 /* at most 3 alternatives for any event */
static const unsigned int event_alternatives[][MAX_ALT] = {
{ 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */
{ 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */
{ 0x100005, 0x600005 }, /* PM_RUN_CYC */
{ 0x100009, 0x200009, 0x500009 }, /* PM_INST_CMPL */
{ 0x300009, 0x400009 }, /* PM_INST_DISP */
};
/*
* Scan the alternatives table for a match and return the
* index into the alternatives table if found, else -1.
*/
static int find_alternative(u64 event)
{
int i, j;
for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
if (event < event_alternatives[i][0])
break;
for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
if (event == event_alternatives[i][j])
return i;
}
return -1;
}
static const unsigned char bytedecode_alternatives[4][4] = {
/* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 },
/* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e },
/* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 },
/* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e }
};
/*
* Some direct events for decodes of event bus byte 3 have alternative
* PMCSEL values on other counters. This returns the alternative
* event code for those that do, or -1 otherwise.
*/
static s64 find_alternative_bdecode(u64 event)
{
int pmc, altpmc, pp, j;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc == 0 || pmc > 4)
return -1;
altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */
pp = event & PM_PMCSEL_MSK;
for (j = 0; j < 4; ++j) {
if (bytedecode_alternatives[pmc - 1][j] == pp) {
return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) |
(altpmc << PM_PMC_SH) |
bytedecode_alternatives[altpmc - 1][j];
}
}
return -1;
}
static int power5_get_alternatives(u64 event, unsigned int flags, u64 alt[])
{
int i, j, nalt = 1;
s64 ae;
alt[0] = event;
nalt = 1;
i = find_alternative(event);
if (i >= 0) {
for (j = 0; j < MAX_ALT; ++j) {
ae = event_alternatives[i][j];
if (ae && ae != event)
alt[nalt++] = ae;
}
} else {
ae = find_alternative_bdecode(event);
if (ae > 0)
alt[nalt++] = ae;
}
return nalt;
}
/*
* Map of which direct events on which PMCs are marked instruction events.
* Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event.
* Bit 0 is set if it is marked for all PMCs.
* The 0x80 bit indicates a byte decode PMCSEL value.
*/
static unsigned char direct_event_is_marked[0x28] = {
0, /* 00 */
0x1f, /* 01 PM_IOPS_CMPL */
0x2, /* 02 PM_MRK_GRP_DISP */
0xe, /* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
0, /* 04 */
0x1c, /* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */
0x80, /* 06 */
0x80, /* 07 */
0, 0, 0,/* 08 - 0a */
0x18, /* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */
0, /* 0c */
0x80, /* 0d */
0x80, /* 0e */
0, /* 0f */
0, /* 10 */
0x14, /* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */
0, /* 12 */
0x10, /* 13 PM_MRK_GRP_CMPL */
0x1f, /* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */
0x2, /* 15 PM_MRK_GRP_ISSUED */
0x80, /* 16 */
0x80, /* 17 */
0, 0, 0, 0, 0,
0x80, /* 1d */
0x80, /* 1e */
0, /* 1f */
0x80, /* 20 */
0x80, /* 21 */
0x80, /* 22 */
0x80, /* 23 */
0x80, /* 24 */
0x80, /* 25 */
0x80, /* 26 */
0x80, /* 27 */
};
/*
* Returns 1 if event counts things relating to marked instructions
* and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
*/
static int power5_marked_instr_event(u64 event)
{
int pmc, psel;
int bit, byte, unit;
u32 mask;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
psel = event & PM_PMCSEL_MSK;
if (pmc >= 5)
return 0;
bit = -1;
if (psel < sizeof(direct_event_is_marked)) {
if (direct_event_is_marked[psel] & (1 << pmc))
return 1;
if (direct_event_is_marked[psel] & 0x80)
bit = 4;
else if (psel == 0x08)
bit = pmc - 1;
else if (psel == 0x10)
bit = 4 - pmc;
else if (psel == 0x1b && (pmc == 1 || pmc == 3))
bit = 4;
} else if ((psel & 0x58) == 0x40)
bit = psel & 7;
if (!(event & PM_BUSEVENT_MSK))
return 0;
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
if (unit == PM_LSU0) {
/* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */
mask = 0x5dff00;
} else if (unit == PM_LSU1 && byte >= 4) {
byte -= 4;
/* byte 4 bits 1,3,5,7, byte 5 bits 6-7, byte 7 bits 0-4,6 */
mask = 0x5f00c0aa;
} else
return 0;
return (mask >> (byte * 8 + bit)) & 1;
}
static int power5_compute_mmcr(u64 event[], int n_ev,
unsigned int hwc[], u64 mmcr[])
{
u64 mmcr1 = 0;
u64 mmcra = 0;
unsigned int pmc, unit, byte, psel;
unsigned int ttm, grp;
int i, isbus, bit, grsel;
unsigned int pmc_inuse = 0;
unsigned int pmc_grp_use[2];
unsigned char busbyte[4];
unsigned char unituse[16];
int ttmuse;
if (n_ev > 6)
return -1;
/* First pass to count resource use */
pmc_grp_use[0] = pmc_grp_use[1] = 0;
memset(busbyte, 0, sizeof(busbyte));
memset(unituse, 0, sizeof(unituse));
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 6)
return -1;
if (pmc_inuse & (1 << (pmc - 1)))
return -1;
pmc_inuse |= 1 << (pmc - 1);
/* count 1/2 vs 3/4 use */
if (pmc <= 4)
++pmc_grp_use[(pmc - 1) >> 1];
}
if (event[i] & PM_BUSEVENT_MSK) {
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
if (unit > PM_LASTUNIT)
return -1;
if (unit == PM_ISU0_ALT)
unit = PM_ISU0;
if (byte >= 4) {
if (unit != PM_LSU1)
return -1;
++unit;
byte &= 3;
}
if (!pmc)
++pmc_grp_use[byte & 1];
if (busbyte[byte] && busbyte[byte] != unit)
return -1;
busbyte[byte] = unit;
unituse[unit] = 1;
}
}
if (pmc_grp_use[0] > 2 || pmc_grp_use[1] > 2)
return -1;
/*
* Assign resources and set multiplexer selects.
*
* PM_ISU0 can go either on TTM0 or TTM1, but that's the only
* choice we have to deal with.
*/
if (unituse[PM_ISU0] &
(unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) {
unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */
unituse[PM_ISU0] = 0;
}
/* Set TTM[01]SEL fields. */
ttmuse = 0;
for (i = PM_FPU; i <= PM_ISU1; ++i) {
if (!unituse[i])
continue;
if (ttmuse++)
return -1;
mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH;
}
ttmuse = 0;
for (; i <= PM_GRS; ++i) {
if (!unituse[i])
continue;
if (ttmuse++)
return -1;
mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH;
}
if (ttmuse > 1)
return -1;
/* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */
for (byte = 0; byte < 4; ++byte) {
unit = busbyte[byte];
if (!unit)
continue;
if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) {
/* get ISU0 through TTM1 rather than TTM0 */
unit = PM_ISU0_ALT;
} else if (unit == PM_LSU1 + 1) {
/* select lower word of LSU1 for this byte */
mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
}
ttm = unit >> 2;
mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
}
/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
psel = event[i] & PM_PMCSEL_MSK;
isbus = event[i] & PM_BUSEVENT_MSK;
if (!pmc) {
/* Bus event or any-PMC direct event */
for (pmc = 0; pmc < 4; ++pmc) {
if (pmc_inuse & (1 << pmc))
continue;
grp = (pmc >> 1) & 1;
if (isbus) {
if (grp == (byte & 1))
break;
} else if (pmc_grp_use[grp] < 2) {
++pmc_grp_use[grp];
break;
}
}
pmc_inuse |= 1 << pmc;
} else if (pmc <= 4) {
/* Direct event */
--pmc;
if ((psel == 8 || psel == 0x10) && isbus && (byte & 2))
/* add events on higher-numbered bus */
mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
} else {
/* Instructions or run cycles on PMC5/6 */
--pmc;
}
if (isbus && unit == PM_GRS) {
bit = psel & 7;
grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
mmcr1 |= (u64)grsel << grsel_shift[bit];
}
if (power5_marked_instr_event(event[i]))
mmcra |= MMCRA_SAMPLE_ENABLE;
if (pmc <= 3)
mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
hwc[i] = pmc;
}
/* Return MMCRx values */
mmcr[0] = 0;
if (pmc_inuse & 1)
mmcr[0] = MMCR0_PMC1CE;
if (pmc_inuse & 0x3e)
mmcr[0] |= MMCR0_PMCjCE;
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
return 0;
}
static void power5_disable_pmc(unsigned int pmc, u64 mmcr[])
{
if (pmc <= 3)
mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
}
static int power5_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = 0xf,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x100009,
[PERF_COUNT_HW_CACHE_REFERENCES] = 0x4c1090, /* LD_REF_L1 */
[PERF_COUNT_HW_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */
[PERF_COUNT_HW_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */
};
#define C(x) PERF_COUNT_HW_CACHE_##x
/*
* Table of generalized cache-related events.
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x4c1090, 0x3c1088 },
[C(OP_WRITE)] = { 0x3c1090, 0xc10c3 },
[C(OP_PREFETCH)] = { 0xc70e7, 0 },
},
[C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { 0, 0 },
},
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x3c309b },
[C(OP_WRITE)] = { 0, 0 },
[C(OP_PREFETCH)] = { 0xc50c3, 0 },
},
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x2c4090, 0x800c4 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x800c0 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x230e4, 0x230e5 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
};
struct power_pmu power5_pmu = {
.n_counter = 6,
.max_alternatives = MAX_ALT,
.add_fields = 0x7000090000555ull,
.test_adder = 0x3000490000000ull,
.compute_mmcr = power5_compute_mmcr,
.get_constraint = power5_get_constraint,
.get_alternatives = power5_get_alternatives,
.disable_pmc = power5_disable_pmc,
.n_generic = ARRAY_SIZE(power5_generic_events),
.generic_events = power5_generic_events,
.cache_events = &power5_cache_events,
};

532
arch/powerpc/kernel/power6-pmu.c Normal file
View File

@ -0,0 +1,532 @@
/*
* Performance counter support for POWER6 processors.
*
* Copyright 2008-2009 Paul Mackerras, IBM Corporation.
*
* This program 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.
*/
#include <linux/kernel.h>
#include <linux/perf_counter.h>
#include <asm/reg.h>
/*
* Bits in event code for POWER6
*/
#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */
#define PM_PMC_MSK 0x7
#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH)
#define PM_UNIT_SH 16 /* Unit event comes (TTMxSEL encoding) */
#define PM_UNIT_MSK 0xf
#define PM_UNIT_MSKS (PM_UNIT_MSK << PM_UNIT_SH)
#define PM_LLAV 0x8000 /* Load lookahead match value */
#define PM_LLA 0x4000 /* Load lookahead match enable */
#define PM_BYTE_SH 12 /* Byte of event bus to use */
#define PM_BYTE_MSK 3
#define PM_SUBUNIT_SH 8 /* Subunit event comes from (NEST_SEL enc.) */
#define PM_SUBUNIT_MSK 7
#define PM_SUBUNIT_MSKS (PM_SUBUNIT_MSK << PM_SUBUNIT_SH)
#define PM_PMCSEL_MSK 0xff /* PMCxSEL value */
#define PM_BUSEVENT_MSK 0xf3700
/*
* Bits in MMCR1 for POWER6
*/
#define MMCR1_TTM0SEL_SH 60
#define MMCR1_TTMSEL_SH(n) (MMCR1_TTM0SEL_SH - (n) * 4)
#define MMCR1_TTMSEL_MSK 0xf
#define MMCR1_TTMSEL(m, n) (((m) >> MMCR1_TTMSEL_SH(n)) & MMCR1_TTMSEL_MSK)
#define MMCR1_NESTSEL_SH 45
#define MMCR1_NESTSEL_MSK 0x7
#define MMCR1_NESTSEL(m) (((m) >> MMCR1_NESTSEL_SH) & MMCR1_NESTSEL_MSK)
#define MMCR1_PMC1_LLA ((u64)1 << 44)
#define MMCR1_PMC1_LLA_VALUE ((u64)1 << 39)
#define MMCR1_PMC1_ADDR_SEL ((u64)1 << 35)
#define MMCR1_PMC1SEL_SH 24
#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8)
#define MMCR1_PMCSEL_MSK 0xff
/*
* Map of which direct events on which PMCs are marked instruction events.
* Indexed by PMCSEL value >> 1.
* Bottom 4 bits are a map of which PMCs are interesting,
* top 4 bits say what sort of event:
* 0 = direct marked event,
* 1 = byte decode event,
* 4 = add/and event (PMC1 -> bits 0 & 4),
* 5 = add/and event (PMC1 -> bits 1 & 5),
* 6 = add/and event (PMC1 -> bits 2 & 6),
* 7 = add/and event (PMC1 -> bits 3 & 7).
*/
static unsigned char direct_event_is_marked[0x60 >> 1] = {
0, /* 00 */
0, /* 02 */
0, /* 04 */
0x07, /* 06 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
0x04, /* 08 PM_MRK_DFU_FIN */
0x06, /* 0a PM_MRK_IFU_FIN, PM_MRK_INST_FIN */
0, /* 0c */
0, /* 0e */
0x02, /* 10 PM_MRK_INST_DISP */
0x08, /* 12 PM_MRK_LSU_DERAT_MISS */
0, /* 14 */
0, /* 16 */
0x0c, /* 18 PM_THRESH_TIMEO, PM_MRK_INST_FIN */
0x0f, /* 1a PM_MRK_INST_DISP, PM_MRK_{FXU,FPU,LSU}_FIN */
0x01, /* 1c PM_MRK_INST_ISSUED */
0, /* 1e */
0, /* 20 */
0, /* 22 */
0, /* 24 */
0, /* 26 */
0x15, /* 28 PM_MRK_DATA_FROM_L2MISS, PM_MRK_DATA_FROM_L3MISS */
0, /* 2a */
0, /* 2c */
0, /* 2e */
0x4f, /* 30 */
0x7f, /* 32 */
0x4f, /* 34 */
0x5f, /* 36 */
0x6f, /* 38 */
0x4f, /* 3a */
0, /* 3c */
0x08, /* 3e PM_MRK_INST_TIMEO */
0x1f, /* 40 */
0x1f, /* 42 */
0x1f, /* 44 */
0x1f, /* 46 */
0x1f, /* 48 */
0x1f, /* 4a */
0x1f, /* 4c */
0x1f, /* 4e */
0, /* 50 */
0x05, /* 52 PM_MRK_BR_TAKEN, PM_MRK_BR_MPRED */
0x1c, /* 54 PM_MRK_PTEG_FROM_L3MISS, PM_MRK_PTEG_FROM_L2MISS */
0x02, /* 56 PM_MRK_LD_MISS_L1 */
0, /* 58 */
0, /* 5a */
0, /* 5c */
0, /* 5e */
};
/*
* Masks showing for each unit which bits are marked events.
* These masks are in LE order, i.e. 0x00000001 is byte 0, bit 0.
*/
static u32 marked_bus_events[16] = {
0x01000000, /* direct events set 1: byte 3 bit 0 */
0x00010000, /* direct events set 2: byte 2 bit 0 */
0, 0, 0, 0, /* IDU, IFU, nest: nothing */
0x00000088, /* VMX set 1: byte 0 bits 3, 7 */
0x000000c0, /* VMX set 2: byte 0 bits 4-7 */
0x04010000, /* LSU set 1: byte 2 bit 0, byte 3 bit 2 */
0xff010000u, /* LSU set 2: byte 2 bit 0, all of byte 3 */
0, /* LSU set 3 */
0x00000010, /* VMX set 3: byte 0 bit 4 */
0, /* BFP set 1 */
0x00000022, /* BFP set 2: byte 0 bits 1, 5 */
0, 0
};
/*
* Returns 1 if event counts things relating to marked instructions
* and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
*/
static int power6_marked_instr_event(u64 event)
{
int pmc, psel, ptype;
int bit, byte, unit;
u32 mask;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
psel = (event & PM_PMCSEL_MSK) >> 1; /* drop edge/level bit */
if (pmc >= 5)
return 0;
bit = -1;
if (psel < sizeof(direct_event_is_marked)) {
ptype = direct_event_is_marked[psel];
if (pmc == 0 || !(ptype & (1 << (pmc - 1))))
return 0;
ptype >>= 4;
if (ptype == 0)
return 1;
if (ptype == 1)
bit = 0;
else
bit = ptype ^ (pmc - 1);
} else if ((psel & 0x48) == 0x40)
bit = psel & 7;
if (!(event & PM_BUSEVENT_MSK) || bit == -1)
return 0;
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
mask = marked_bus_events[unit];
return (mask >> (byte * 8 + bit)) & 1;
}
/*
* Assign PMC numbers and compute MMCR1 value for a set of events
*/
static int p6_compute_mmcr(u64 event[], int n_ev,
unsigned int hwc[], u64 mmcr[])
{
u64 mmcr1 = 0;
u64 mmcra = 0;
int i;
unsigned int pmc, ev, b, u, s, psel;
unsigned int ttmset = 0;
unsigned int pmc_inuse = 0;
if (n_ev > 6)
return -1;
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc_inuse & (1 << (pmc - 1)))
return -1; /* collision! */
pmc_inuse |= 1 << (pmc - 1);
}
}
for (i = 0; i < n_ev; ++i) {
ev = event[i];
pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
--pmc;
} else {
/* can go on any PMC; find a free one */
for (pmc = 0; pmc < 4; ++pmc)
if (!(pmc_inuse & (1 << pmc)))
break;
if (pmc >= 4)
return -1;
pmc_inuse |= 1 << pmc;
}
hwc[i] = pmc;
psel = ev & PM_PMCSEL_MSK;
if (ev & PM_BUSEVENT_MSK) {
/* this event uses the event bus */
b = (ev >> PM_BYTE_SH) & PM_BYTE_MSK;
u = (ev >> PM_UNIT_SH) & PM_UNIT_MSK;
/* check for conflict on this byte of event bus */
if ((ttmset & (1 << b)) && MMCR1_TTMSEL(mmcr1, b) != u)
return -1;
mmcr1 |= (u64)u << MMCR1_TTMSEL_SH(b);
ttmset |= 1 << b;
if (u == 5) {
/* Nest events have a further mux */
s = (ev >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK;
if ((ttmset & 0x10) &&
MMCR1_NESTSEL(mmcr1) != s)
return -1;
ttmset |= 0x10;
mmcr1 |= (u64)s << MMCR1_NESTSEL_SH;
}
if (0x30 <= psel && psel <= 0x3d) {
/* these need the PMCx_ADDR_SEL bits */
if (b >= 2)
mmcr1 |= MMCR1_PMC1_ADDR_SEL >> pmc;
}
/* bus select values are different for PMC3/4 */
if (pmc >= 2 && (psel & 0x90) == 0x80)
psel ^= 0x20;
}
if (ev & PM_LLA) {
mmcr1 |= MMCR1_PMC1_LLA >> pmc;
if (ev & PM_LLAV)
mmcr1 |= MMCR1_PMC1_LLA_VALUE >> pmc;
}
if (power6_marked_instr_event(event[i]))
mmcra |= MMCRA_SAMPLE_ENABLE;
if (pmc < 4)
mmcr1 |= (u64)psel << MMCR1_PMCSEL_SH(pmc);
}
mmcr[0] = 0;
if (pmc_inuse & 1)
mmcr[0] = MMCR0_PMC1CE;
if (pmc_inuse & 0xe)
mmcr[0] |= MMCR0_PMCjCE;
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
return 0;
}
/*
* Layout of constraint bits:
*
* 0-1 add field: number of uses of PMC1 (max 1)
* 2-3, 4-5, 6-7, 8-9, 10-11: ditto for PMC2, 3, 4, 5, 6
* 12-15 add field: number of uses of PMC1-4 (max 4)
* 16-19 select field: unit on byte 0 of event bus
* 20-23, 24-27, 28-31 ditto for bytes 1, 2, 3
* 32-34 select field: nest (subunit) event selector
*/
static int p6_get_constraint(u64 event, u64 *maskp, u64 *valp)
{
int pmc, byte, sh, subunit;
u64 mask = 0, value = 0;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 4 && !(event == 0x500009 || event == 0x600005))
return -1;
sh = (pmc - 1) * 2;
mask |= 2 << sh;
value |= 1 << sh;
}
if (event & PM_BUSEVENT_MSK) {
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
sh = byte * 4 + (16 - PM_UNIT_SH);
mask |= PM_UNIT_MSKS << sh;
value |= (u64)(event & PM_UNIT_MSKS) << sh;
if ((event & PM_UNIT_MSKS) == (5 << PM_UNIT_SH)) {
subunit = (event >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK;
mask |= (u64)PM_SUBUNIT_MSK << 32;
value |= (u64)subunit << 32;
}
}
if (pmc <= 4) {
mask |= 0x8000; /* add field for count of PMC1-4 uses */
value |= 0x1000;
}
*maskp = mask;
*valp = value;
return 0;
}
static int p6_limited_pmc_event(u64 event)
{
int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
return pmc == 5 || pmc == 6;
}
#define MAX_ALT 4 /* at most 4 alternatives for any event */
static const unsigned int event_alternatives[][MAX_ALT] = {
{ 0x0130e8, 0x2000f6, 0x3000fc }, /* PM_PTEG_RELOAD_VALID */
{ 0x080080, 0x10000d, 0x30000c, 0x4000f0 }, /* PM_LD_MISS_L1 */
{ 0x080088, 0x200054, 0x3000f0 }, /* PM_ST_MISS_L1 */
{ 0x10000a, 0x2000f4, 0x600005 }, /* PM_RUN_CYC */
{ 0x10000b, 0x2000f5 }, /* PM_RUN_COUNT */
{ 0x10000e, 0x400010 }, /* PM_PURR */
{ 0x100010, 0x4000f8 }, /* PM_FLUSH */
{ 0x10001a, 0x200010 }, /* PM_MRK_INST_DISP */
{ 0x100026, 0x3000f8 }, /* PM_TB_BIT_TRANS */
{ 0x100054, 0x2000f0 }, /* PM_ST_FIN */
{ 0x100056, 0x2000fc }, /* PM_L1_ICACHE_MISS */
{ 0x1000f0, 0x40000a }, /* PM_INST_IMC_MATCH_CMPL */
{ 0x1000f8, 0x200008 }, /* PM_GCT_EMPTY_CYC */
{ 0x1000fc, 0x400006 }, /* PM_LSU_DERAT_MISS_CYC */
{ 0x20000e, 0x400007 }, /* PM_LSU_DERAT_MISS */
{ 0x200012, 0x300012 }, /* PM_INST_DISP */
{ 0x2000f2, 0x3000f2 }, /* PM_INST_DISP */
{ 0x2000f8, 0x300010 }, /* PM_EXT_INT */
{ 0x2000fe, 0x300056 }, /* PM_DATA_FROM_L2MISS */
{ 0x2d0030, 0x30001a }, /* PM_MRK_FPU_FIN */
{ 0x30000a, 0x400018 }, /* PM_MRK_INST_FIN */
{ 0x3000f6, 0x40000e }, /* PM_L1_DCACHE_RELOAD_VALID */
{ 0x3000fe, 0x400056 }, /* PM_DATA_FROM_L3MISS */
};
/*
* This could be made more efficient with a binary search on
* a presorted list, if necessary
*/
static int find_alternatives_list(u64 event)
{
int i, j;
unsigned int alt;
for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
if (event < event_alternatives[i][0])
return -1;
for (j = 0; j < MAX_ALT; ++j) {
alt = event_alternatives[i][j];
if (!alt || event < alt)
break;
if (event == alt)
return i;
}
}
return -1;
}
static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[])
{
int i, j, nlim;
unsigned int psel, pmc;
unsigned int nalt = 1;
u64 aevent;
alt[0] = event;
nlim = p6_limited_pmc_event(event);
/* check the alternatives table */
i = find_alternatives_list(event);
if (i >= 0) {
/* copy out alternatives from list */
for (j = 0; j < MAX_ALT; ++j) {
aevent = event_alternatives[i][j];
if (!aevent)
break;
if (aevent != event)
alt[nalt++] = aevent;
nlim += p6_limited_pmc_event(aevent);
}
} else {
/* Check for alternative ways of computing sum events */
/* PMCSEL 0x32 counter N == PMCSEL 0x34 counter 5-N */
psel = event & (PM_PMCSEL_MSK & ~1); /* ignore edge bit */
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc && (psel == 0x32 || psel == 0x34))
alt[nalt++] = ((event ^ 0x6) & ~PM_PMC_MSKS) |
((5 - pmc) << PM_PMC_SH);
/* PMCSEL 0x38 counter N == PMCSEL 0x3a counter N+/-2 */
if (pmc && (psel == 0x38 || psel == 0x3a))
alt[nalt++] = ((event ^ 0x2) & ~PM_PMC_MSKS) |
((pmc > 2? pmc - 2: pmc + 2) << PM_PMC_SH);
}
if (flags & PPMU_ONLY_COUNT_RUN) {
/*
* We're only counting in RUN state,
* so PM_CYC is equivalent to PM_RUN_CYC,
* PM_INST_CMPL === PM_RUN_INST_CMPL, PM_PURR === PM_RUN_PURR.
* This doesn't include alternatives that don't provide
* any extra flexibility in assigning PMCs (e.g.
* 0x10000a for PM_RUN_CYC vs. 0x1e for PM_CYC).
* Note that even with these additional alternatives
* we never end up with more than 4 alternatives for any event.
*/
j = nalt;
for (i = 0; i < nalt; ++i) {
switch (alt[i]) {
case 0x1e: /* PM_CYC */
alt[j++] = 0x600005; /* PM_RUN_CYC */
++nlim;
break;
case 0x10000a: /* PM_RUN_CYC */
alt[j++] = 0x1e; /* PM_CYC */
break;
case 2: /* PM_INST_CMPL */
alt[j++] = 0x500009; /* PM_RUN_INST_CMPL */
++nlim;
break;
case 0x500009: /* PM_RUN_INST_CMPL */
alt[j++] = 2; /* PM_INST_CMPL */
break;
case 0x10000e: /* PM_PURR */
alt[j++] = 0x4000f4; /* PM_RUN_PURR */
break;
case 0x4000f4: /* PM_RUN_PURR */
alt[j++] = 0x10000e; /* PM_PURR */
break;
}
}
nalt = j;
}
if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) {
/* remove the limited PMC events */
j = 0;
for (i = 0; i < nalt; ++i) {
if (!p6_limited_pmc_event(alt[i])) {
alt[j] = alt[i];
++j;
}
}
nalt = j;
} else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) {
/* remove all but the limited PMC events */
j = 0;
for (i = 0; i < nalt; ++i) {
if (p6_limited_pmc_event(alt[i])) {
alt[j] = alt[i];
++j;
}
}
nalt = j;
}
return nalt;
}
static void p6_disable_pmc(unsigned int pmc, u64 mmcr[])
{
/* Set PMCxSEL to 0 to disable PMCx */
if (pmc <= 3)
mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
}
static int power6_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = 0x1e,
[PERF_COUNT_HW_INSTRUCTIONS] = 2,
[PERF_COUNT_HW_CACHE_REFERENCES] = 0x280030, /* LD_REF_L1 */
[PERF_COUNT_HW_CACHE_MISSES] = 0x30000c, /* LD_MISS_L1 */
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x410a0, /* BR_PRED */
[PERF_COUNT_HW_BRANCH_MISSES] = 0x400052, /* BR_MPRED */
};
#define C(x) PERF_COUNT_HW_CACHE_##x
/*
* Table of generalized cache-related events.
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
* The "DTLB" and "ITLB" events relate to the DERAT and IERAT.
*/
static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x80082, 0x80080 },
[C(OP_WRITE)] = { 0x80086, 0x80088 },
[C(OP_PREFETCH)] = { 0x810a4, 0 },
},
[C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x100056 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { 0x4008c, 0 },
},
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x150730, 0x250532 },
[C(OP_WRITE)] = { 0x250432, 0x150432 },
[C(OP_PREFETCH)] = { 0x810a6, 0 },
},
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x20000e },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x420ce },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x430e6, 0x400052 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
};
struct power_pmu power6_pmu = {
.n_counter = 6,
.max_alternatives = MAX_ALT,
.add_fields = 0x1555,
.test_adder = 0x3000,
.compute_mmcr = p6_compute_mmcr,
.get_constraint = p6_get_constraint,
.get_alternatives = p6_get_alternatives,
.disable_pmc = p6_disable_pmc,
.limited_pmc_event = p6_limited_pmc_event,
.flags = PPMU_LIMITED_PMC5_6 | PPMU_ALT_SIPR,
.n_generic = ARRAY_SIZE(power6_generic_events),
.generic_events = power6_generic_events,
.cache_events = &power6_cache_events,
};

357
arch/powerpc/kernel/power7-pmu.c Normal file
View File

@ -0,0 +1,357 @@
/*
* Performance counter support for POWER7 processors.
*
* Copyright 2009 Paul Mackerras, IBM Corporation.
*
* This program 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.
*/
#include <linux/kernel.h>
#include <linux/perf_counter.h>
#include <asm/reg.h>
/*
* Bits in event code for POWER7
*/
#define PM_PMC_SH 16 /* PMC number (1-based) for direct events */
#define PM_PMC_MSK 0xf
#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH)
#define PM_UNIT_SH 12 /* TTMMUX number and setting - unit select */
#define PM_UNIT_MSK 0xf
#define PM_COMBINE_SH 11 /* Combined event bit */
#define PM_COMBINE_MSK 1
#define PM_COMBINE_MSKS 0x800
#define PM_L2SEL_SH 8 /* L2 event select */
#define PM_L2SEL_MSK 7
#define PM_PMCSEL_MSK 0xff
/*
* Bits in MMCR1 for POWER7
*/
#define MMCR1_TTM0SEL_SH 60
#define MMCR1_TTM1SEL_SH 56
#define MMCR1_TTM2SEL_SH 52
#define MMCR1_TTM3SEL_SH 48
#define MMCR1_TTMSEL_MSK 0xf
#define MMCR1_L2SEL_SH 45
#define MMCR1_L2SEL_MSK 7
#define MMCR1_PMC1_COMBINE_SH 35
#define MMCR1_PMC2_COMBINE_SH 34
#define MMCR1_PMC3_COMBINE_SH 33
#define MMCR1_PMC4_COMBINE_SH 32
#define MMCR1_PMC1SEL_SH 24
#define MMCR1_PMC2SEL_SH 16
#define MMCR1_PMC3SEL_SH 8
#define MMCR1_PMC4SEL_SH 0
#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8)
#define MMCR1_PMCSEL_MSK 0xff
/*
* Bits in MMCRA
*/
/*
* Layout of constraint bits:
* 6666555555555544444444443333333333222222222211111111110000000000
* 3210987654321098765432109876543210987654321098765432109876543210
* [ ><><><><><><>
* NC P6P5P4P3P2P1
*
* NC - number of counters
* 15: NC error 0x8000
* 12-14: number of events needing PMC1-4 0x7000
*
* P6
* 11: P6 error 0x800
* 10-11: Count of events needing PMC6
*
* P1..P5
* 0-9: Count of events needing PMC1..PMC5
*/
static int power7_get_constraint(u64 event, u64 *maskp, u64 *valp)
{
int pmc, sh;
u64 mask = 0, value = 0;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 6)
return -1;
sh = (pmc - 1) * 2;
mask |= 2 << sh;
value |= 1 << sh;
if (pmc >= 5 && !(event == 0x500fa || event == 0x600f4))
return -1;
}
if (pmc < 5) {
/* need a counter from PMC1-4 set */
mask |= 0x8000;
value |= 0x1000;
}
*maskp = mask;
*valp = value;
return 0;
}
#define MAX_ALT 2 /* at most 2 alternatives for any event */
static const unsigned int event_alternatives[][MAX_ALT] = {
{ 0x200f2, 0x300f2 }, /* PM_INST_DISP */
{ 0x200f4, 0x600f4 }, /* PM_RUN_CYC */
{ 0x400fa, 0x500fa }, /* PM_RUN_INST_CMPL */
};
/*
* Scan the alternatives table for a match and return the
* index into the alternatives table if found, else -1.
*/
static int find_alternative(u64 event)
{
int i, j;
for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
if (event < event_alternatives[i][0])
break;
for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
if (event == event_alternatives[i][j])
return i;
}
return -1;
}
static s64 find_alternative_decode(u64 event)
{
int pmc, psel;
/* this only handles the 4x decode events */
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
psel = event & PM_PMCSEL_MSK;
if ((pmc == 2 || pmc == 4) && (psel & ~7) == 0x40)
return event - (1 << PM_PMC_SH) + 8;
if ((pmc == 1 || pmc == 3) && (psel & ~7) == 0x48)
return event + (1 << PM_PMC_SH) - 8;
return -1;
}
static int power7_get_alternatives(u64 event, unsigned int flags, u64 alt[])
{
int i, j, nalt = 1;
s64 ae;
alt[0] = event;
nalt = 1;
i = find_alternative(event);
if (i >= 0) {
for (j = 0; j < MAX_ALT; ++j) {
ae = event_alternatives[i][j];
if (ae && ae != event)
alt[nalt++] = ae;
}
} else {
ae = find_alternative_decode(event);
if (ae > 0)
alt[nalt++] = ae;
}
if (flags & PPMU_ONLY_COUNT_RUN) {
/*
* We're only counting in RUN state,
* so PM_CYC is equivalent to PM_RUN_CYC
* and PM_INST_CMPL === PM_RUN_INST_CMPL.
* This doesn't include alternatives that don't provide
* any extra flexibility in assigning PMCs.
*/
j = nalt;
for (i = 0; i < nalt; ++i) {
switch (alt[i]) {
case 0x1e: /* PM_CYC */
alt[j++] = 0x600f4; /* PM_RUN_CYC */
break;
case 0x600f4: /* PM_RUN_CYC */
alt[j++] = 0x1e;
break;
case 0x2: /* PM_PPC_CMPL */
alt[j++] = 0x500fa; /* PM_RUN_INST_CMPL */
break;
case 0x500fa: /* PM_RUN_INST_CMPL */
alt[j++] = 0x2; /* PM_PPC_CMPL */
break;
}
}
nalt = j;
}
return nalt;
}
/*
* Returns 1 if event counts things relating to marked instructions
* and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
*/
static int power7_marked_instr_event(u64 event)
{
int pmc, psel;
int unit;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
psel = event & PM_PMCSEL_MSK & ~1; /* trim off edge/level bit */
if (pmc >= 5)
return 0;
switch (psel >> 4) {
case 2:
return pmc == 2 || pmc == 4;
case 3:
if (psel == 0x3c)
return pmc == 1;
if (psel == 0x3e)
return pmc != 2;
return 1;
case 4:
case 5:
return unit == 0xd;
case 6:
if (psel == 0x64)
return pmc >= 3;
case 8:
return unit == 0xd;
}
return 0;
}
static int power7_compute_mmcr(u64 event[], int n_ev,
unsigned int hwc[], u64 mmcr[])
{
u64 mmcr1 = 0;
u64 mmcra = 0;
unsigned int pmc, unit, combine, l2sel, psel;
unsigned int pmc_inuse = 0;
int i;
/* First pass to count resource use */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 6)
return -1;
if (pmc_inuse & (1 << (pmc - 1)))
return -1;
pmc_inuse |= 1 << (pmc - 1);
}
}
/* Second pass: assign PMCs, set all MMCR1 fields */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
combine = (event[i] >> PM_COMBINE_SH) & PM_COMBINE_MSK;
l2sel = (event[i] >> PM_L2SEL_SH) & PM_L2SEL_MSK;
psel = event[i] & PM_PMCSEL_MSK;
if (!pmc) {
/* Bus event or any-PMC direct event */
for (pmc = 0; pmc < 4; ++pmc) {
if (!(pmc_inuse & (1 << pmc)))
break;
}
if (pmc >= 4)
return -1;
pmc_inuse |= 1 << pmc;
} else {
/* Direct or decoded event */
--pmc;
}
if (pmc <= 3) {
mmcr1 |= (u64) unit << (MMCR1_TTM0SEL_SH - 4 * pmc);
mmcr1 |= (u64) combine << (MMCR1_PMC1_COMBINE_SH - pmc);
mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
if (unit == 6) /* L2 events */
mmcr1 |= (u64) l2sel << MMCR1_L2SEL_SH;
}
if (power7_marked_instr_event(event[i]))
mmcra |= MMCRA_SAMPLE_ENABLE;
hwc[i] = pmc;
}
/* Return MMCRx values */
mmcr[0] = 0;
if (pmc_inuse & 1)
mmcr[0] = MMCR0_PMC1CE;
if (pmc_inuse & 0x3e)
mmcr[0] |= MMCR0_PMCjCE;
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
return 0;
}
static void power7_disable_pmc(unsigned int pmc, u64 mmcr[])
{
if (pmc <= 3)
mmcr[1] &= ~(0xffULL << MMCR1_PMCSEL_SH(pmc));
}
static int power7_generic_events[] = {
[PERF_COUNT_CPU_CYCLES] = 0x1e,
[PERF_COUNT_INSTRUCTIONS] = 2,
[PERF_COUNT_CACHE_REFERENCES] = 0xc880, /* LD_REF_L1_LSU */
[PERF_COUNT_CACHE_MISSES] = 0x400f0, /* LD_MISS_L1 */
[PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x10068, /* BRU_FIN */
[PERF_COUNT_BRANCH_MISSES] = 0x400f6, /* BR_MPRED */
};
#define C(x) PERF_COUNT_HW_CACHE_##x
/*
* Table of generalized cache-related events.
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x400f0, 0xc880 },
[C(OP_WRITE)] = { 0, 0x300f0 },
[C(OP_PREFETCH)] = { 0xd8b8, 0 },
},
[C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x200fc },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { 0x408a, 0 },
},
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x6080, 0x6084 },
[C(OP_WRITE)] = { 0x6082, 0x6086 },
[C(OP_PREFETCH)] = { 0, 0 },
},
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x300fc },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x400fc },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x10068, 0x400f6 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
};
struct power_pmu power7_pmu = {
.n_counter = 6,
.max_alternatives = MAX_ALT + 1,
.add_fields = 0x1555ull,
.test_adder = 0x3000ull,
.compute_mmcr = power7_compute_mmcr,
.get_constraint = power7_get_constraint,
.get_alternatives = power7_get_alternatives,
.disable_pmc = power7_disable_pmc,
.n_generic = ARRAY_SIZE(power7_generic_events),
.generic_events = power7_generic_events,
.cache_events = &power7_cache_events,
};

482
arch/powerpc/kernel/ppc970-pmu.c Normal file
View File

@ -0,0 +1,482 @@
/*
* Performance counter support for PPC970-family processors.
*
* Copyright 2008-2009 Paul Mackerras, IBM Corporation.
*
* This program 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.
*/
#include <linux/string.h>
#include <linux/perf_counter.h>
#include <asm/reg.h>
/*
* Bits in event code for PPC970
*/
#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */
#define PM_PMC_MSK 0xf
#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */
#define PM_UNIT_MSK 0xf
#define PM_SPCSEL_SH 6
#define PM_SPCSEL_MSK 3
#define PM_BYTE_SH 4 /* Byte number of event bus to use */
#define PM_BYTE_MSK 3
#define PM_PMCSEL_MSK 0xf
/* Values in PM_UNIT field */
#define PM_NONE 0
#define PM_FPU 1
#define PM_VPU 2
#define PM_ISU 3
#define PM_IFU 4
#define PM_IDU 5
#define PM_STS 6
#define PM_LSU0 7
#define PM_LSU1U 8
#define PM_LSU1L 9
#define PM_LASTUNIT 9
/*
* Bits in MMCR0 for PPC970
*/
#define MMCR0_PMC1SEL_SH 8
#define MMCR0_PMC2SEL_SH 1
#define MMCR_PMCSEL_MSK 0x1f
/*
* Bits in MMCR1 for PPC970
*/
#define MMCR1_TTM0SEL_SH 62
#define MMCR1_TTM1SEL_SH 59
#define MMCR1_TTM3SEL_SH 53
#define MMCR1_TTMSEL_MSK 3
#define MMCR1_TD_CP_DBG0SEL_SH 50
#define MMCR1_TD_CP_DBG1SEL_SH 48
#define MMCR1_TD_CP_DBG2SEL_SH 46
#define MMCR1_TD_CP_DBG3SEL_SH 44
#define MMCR1_PMC1_ADDER_SEL_SH 39
#define MMCR1_PMC2_ADDER_SEL_SH 38
#define MMCR1_PMC6_ADDER_SEL_SH 37
#define MMCR1_PMC5_ADDER_SEL_SH 36
#define MMCR1_PMC8_ADDER_SEL_SH 35
#define MMCR1_PMC7_ADDER_SEL_SH 34
#define MMCR1_PMC3_ADDER_SEL_SH 33
#define MMCR1_PMC4_ADDER_SEL_SH 32
#define MMCR1_PMC3SEL_SH 27
#define MMCR1_PMC4SEL_SH 22
#define MMCR1_PMC5SEL_SH 17
#define MMCR1_PMC6SEL_SH 12
#define MMCR1_PMC7SEL_SH 7
#define MMCR1_PMC8SEL_SH 2
static short mmcr1_adder_bits[8] = {
MMCR1_PMC1_ADDER_SEL_SH,
MMCR1_PMC2_ADDER_SEL_SH,
MMCR1_PMC3_ADDER_SEL_SH,
MMCR1_PMC4_ADDER_SEL_SH,
MMCR1_PMC5_ADDER_SEL_SH,
MMCR1_PMC6_ADDER_SEL_SH,
MMCR1_PMC7_ADDER_SEL_SH,
MMCR1_PMC8_ADDER_SEL_SH
};
/*
* Bits in MMCRA
*/
/*
* Layout of constraint bits:
* 6666555555555544444444443333333333222222222211111111110000000000
* 3210987654321098765432109876543210987654321098765432109876543210
* <><><>[ >[ >[ >< >< >< >< ><><><><><><><><>
* SPT0T1 UC PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8
*
* SP - SPCSEL constraint
* 48-49: SPCSEL value 0x3_0000_0000_0000
*
* T0 - TTM0 constraint
* 46-47: TTM0SEL value (0=FPU, 2=IFU, 3=VPU) 0xC000_0000_0000
*
* T1 - TTM1 constraint
* 44-45: TTM1SEL value (0=IDU, 3=STS) 0x3000_0000_0000
*
* UC - unit constraint: can't have all three of FPU|IFU|VPU, ISU, IDU|STS
* 43: UC3 error 0x0800_0000_0000
* 42: FPU|IFU|VPU events needed 0x0400_0000_0000
* 41: ISU events needed 0x0200_0000_0000
* 40: IDU|STS events needed 0x0100_0000_0000
*
* PS1
* 39: PS1 error 0x0080_0000_0000
* 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
*
* PS2
* 35: PS2 error 0x0008_0000_0000
* 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
*
* B0
* 28-31: Byte 0 event source 0xf000_0000
* Encoding as for the event code
*
* B1, B2, B3
* 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
*
* P1
* 15: P1 error 0x8000
* 14-15: Count of events needing PMC1
*
* P2..P8
* 0-13: Count of events needing PMC2..PMC8
*/
static unsigned char direct_marked_event[8] = {
(1<<2) | (1<<3), /* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */
(1<<3) | (1<<5), /* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */
(1<<3) | (1<<5), /* PMC3: PM_MRK_ST_CMPL_INT, PM_MRK_VMX_FIN */
(1<<4) | (1<<5), /* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */
(1<<4) | (1<<5), /* PMC5: PM_GRP_MRK, PM_MRK_GRP_TIMEO */
(1<<3) | (1<<4) | (1<<5),
/* PMC6: PM_MRK_ST_STS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */
(1<<4) | (1<<5), /* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */
(1<<4) /* PMC8: PM_MRK_LSU_FIN */
};
/*
* Returns 1 if event counts things relating to marked instructions
* and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
*/
static int p970_marked_instr_event(u64 event)
{
int pmc, psel, unit, byte, bit;
unsigned int mask;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
psel = event & PM_PMCSEL_MSK;
if (pmc) {
if (direct_marked_event[pmc - 1] & (1 << psel))
return 1;
if (psel == 0) /* add events */
bit = (pmc <= 4)? pmc - 1: 8 - pmc;
else if (psel == 7 || psel == 13) /* decode events */
bit = 4;
else
return 0;
} else
bit = psel;
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
mask = 0;
switch (unit) {
case PM_VPU:
mask = 0x4c; /* byte 0 bits 2,3,6 */
case PM_LSU0:
/* byte 2 bits 0,2,3,4,6; all of byte 1 */
mask = 0x085dff00;
case PM_LSU1L:
mask = 0x50 << 24; /* byte 3 bits 4,6 */
break;
}
return (mask >> (byte * 8 + bit)) & 1;
}
/* Masks and values for using events from the various units */
static u64 unit_cons[PM_LASTUNIT+1][2] = {
[PM_FPU] = { 0xc80000000000ull, 0x040000000000ull },
[PM_VPU] = { 0xc80000000000ull, 0xc40000000000ull },
[PM_ISU] = { 0x080000000000ull, 0x020000000000ull },
[PM_IFU] = { 0xc80000000000ull, 0x840000000000ull },
[PM_IDU] = { 0x380000000000ull, 0x010000000000ull },
[PM_STS] = { 0x380000000000ull, 0x310000000000ull },
};
static int p970_get_constraint(u64 event, u64 *maskp, u64 *valp)
{
int pmc, byte, unit, sh, spcsel;
u64 mask = 0, value = 0;
int grp = -1;
pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc > 8)
return -1;
sh = (pmc - 1) * 2;
mask |= 2 << sh;
value |= 1 << sh;
grp = ((pmc - 1) >> 1) & 1;
}
unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
if (unit) {
if (unit > PM_LASTUNIT)
return -1;
mask |= unit_cons[unit][0];
value |= unit_cons[unit][1];
byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
/*
* Bus events on bytes 0 and 2 can be counted
* on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
*/
if (!pmc)
grp = byte & 1;
/* Set byte lane select field */
mask |= 0xfULL << (28 - 4 * byte);
value |= (u64)unit << (28 - 4 * byte);
}
if (grp == 0) {
/* increment PMC1/2/5/6 field */
mask |= 0x8000000000ull;
value |= 0x1000000000ull;
} else if (grp == 1) {
/* increment PMC3/4/7/8 field */
mask |= 0x800000000ull;
value |= 0x100000000ull;
}
spcsel = (event >> PM_SPCSEL_SH) & PM_SPCSEL_MSK;
if (spcsel) {
mask |= 3ull << 48;
value |= (u64)spcsel << 48;
}
*maskp = mask;
*valp = value;
return 0;
}
static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[])
{
alt[0] = event;
/* 2 alternatives for LSU empty */
if (event == 0x2002 || event == 0x3002) {
alt[1] = event ^ 0x1000;
return 2;
}
return 1;
}
static int p970_compute_mmcr(u64 event[], int n_ev,
unsigned int hwc[], u64 mmcr[])
{
u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0;
unsigned int pmc, unit, byte, psel;
unsigned int ttm, grp;
unsigned int pmc_inuse = 0;
unsigned int pmc_grp_use[2];
unsigned char busbyte[4];
unsigned char unituse[16];
unsigned char unitmap[] = { 0, 0<<3, 3<<3, 1<<3, 2<<3, 0|4, 3|4 };
unsigned char ttmuse[2];
unsigned char pmcsel[8];
int i;
int spcsel;
if (n_ev > 8)
return -1;
/* First pass to count resource use */
pmc_grp_use[0] = pmc_grp_use[1] = 0;
memset(busbyte, 0, sizeof(busbyte));
memset(unituse, 0, sizeof(unituse));
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
if (pmc) {
if (pmc_inuse & (1 << (pmc - 1)))
return -1;
pmc_inuse |= 1 << (pmc - 1);
/* count 1/2/5/6 vs 3/4/7/8 use */
++pmc_grp_use[((pmc - 1) >> 1) & 1];
}
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
if (unit) {
if (unit > PM_LASTUNIT)
return -1;
if (!pmc)
++pmc_grp_use[byte & 1];
if (busbyte[byte] && busbyte[byte] != unit)
return -1;
busbyte[byte] = unit;
unituse[unit] = 1;
}
}
if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
return -1;
/*
* Assign resources and set multiplexer selects.
*
* PM_ISU can go either on TTM0 or TTM1, but that's the only
* choice we have to deal with.
*/
if (unituse[PM_ISU] &
(unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_VPU]))
unitmap[PM_ISU] = 2 | 4; /* move ISU to TTM1 */
/* Set TTM[01]SEL fields. */
ttmuse[0] = ttmuse[1] = 0;
for (i = PM_FPU; i <= PM_STS; ++i) {
if (!unituse[i])
continue;
ttm = unitmap[i];
++ttmuse[(ttm >> 2) & 1];
mmcr1 |= (u64)(ttm & ~4) << MMCR1_TTM1SEL_SH;
}
/* Check only one unit per TTMx */
if (ttmuse[0] > 1 || ttmuse[1] > 1)
return -1;
/* Set byte lane select fields and TTM3SEL. */
for (byte = 0; byte < 4; ++byte) {
unit = busbyte[byte];
if (!unit)
continue;
if (unit <= PM_STS)
ttm = (unitmap[unit] >> 2) & 1;
else if (unit == PM_LSU0)
ttm = 2;
else {
ttm = 3;
if (unit == PM_LSU1L && byte >= 2)
mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
}
mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
}
/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
memset(pmcsel, 0x8, sizeof(pmcsel)); /* 8 means don't count */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
psel = event[i] & PM_PMCSEL_MSK;
if (!pmc) {
/* Bus event or any-PMC direct event */
if (unit)
psel |= 0x10 | ((byte & 2) << 2);
else
psel |= 8;
for (pmc = 0; pmc < 8; ++pmc) {
if (pmc_inuse & (1 << pmc))
continue;
grp = (pmc >> 1) & 1;
if (unit) {
if (grp == (byte & 1))
break;
} else if (pmc_grp_use[grp] < 4) {
++pmc_grp_use[grp];
break;
}
}
pmc_inuse |= 1 << pmc;
} else {
/* Direct event */
--pmc;
if (psel == 0 && (byte & 2))
/* add events on higher-numbered bus */
mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
}
pmcsel[pmc] = psel;
hwc[i] = pmc;
spcsel = (event[i] >> PM_SPCSEL_SH) & PM_SPCSEL_MSK;
mmcr1 |= spcsel;
if (p970_marked_instr_event(event[i]))
mmcra |= MMCRA_SAMPLE_ENABLE;
}
for (pmc = 0; pmc < 2; ++pmc)
mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc);
for (; pmc < 8; ++pmc)
mmcr1 |= (u64)pmcsel[pmc] << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
if (pmc_inuse & 1)
mmcr0 |= MMCR0_PMC1CE;
if (pmc_inuse & 0xfe)
mmcr0 |= MMCR0_PMCjCE;
mmcra |= 0x2000; /* mark only one IOP per PPC instruction */
/* Return MMCRx values */
mmcr[0] = mmcr0;
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
return 0;
}
static void p970_disable_pmc(unsigned int pmc, u64 mmcr[])
{
int shift, i;
if (pmc <= 1) {
shift = MMCR0_PMC1SEL_SH - 7 * pmc;
i = 0;
} else {
shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2);
i = 1;
}
/*
* Setting the PMCxSEL field to 0x08 disables PMC x.
*/
mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift);
}
static int ppc970_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = 7,
[PERF_COUNT_HW_INSTRUCTIONS] = 1,
[PERF_COUNT_HW_CACHE_REFERENCES] = 0x8810, /* PM_LD_REF_L1 */
[PERF_COUNT_HW_CACHE_MISSES] = 0x3810, /* PM_LD_MISS_L1 */
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x431, /* PM_BR_ISSUED */
[PERF_COUNT_HW_BRANCH_MISSES] = 0x327, /* PM_GRP_BR_MPRED */
};
#define C(x) PERF_COUNT_HW_CACHE_##x
/*
* Table of generalized cache-related events.
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x8810, 0x3810 },
[C(OP_WRITE)] = { 0x7810, 0x813 },
[C(OP_PREFETCH)] = { 0x731, 0 },
},
[C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { 0, 0 },
},
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { 0, 0 },
[C(OP_PREFETCH)] = { 0x733, 0 },
},
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x704 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x700 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x431, 0x327 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
};
struct power_pmu ppc970_pmu = {
.n_counter = 8,
.max_alternatives = 2,
.add_fields = 0x001100005555ull,
.test_adder = 0x013300000000ull,
.compute_mmcr = p970_compute_mmcr,
.get_constraint = p970_get_constraint,
.get_alternatives = p970_get_alternatives,
.disable_pmc = p970_disable_pmc,
.n_generic = ARRAY_SIZE(ppc970_generic_events),
.generic_events = ppc970_generic_events,
.cache_events = &ppc970_cache_events,
};

10
arch/powerpc/mm/fault.c
View File

@ -29,6 +29,7 @@
#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/perf_counter.h>
#include <asm/firmware.h>
#include <asm/page.h>
@ -170,6 +171,8 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
die("Weird page fault", regs, SIGSEGV);
}
perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@ -309,6 +312,8 @@ good_area:
}
if (ret & VM_FAULT_MAJOR) {
current->maj_flt++;
perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
regs, address);
#ifdef CONFIG_PPC_SMLPAR
if (firmware_has_feature(FW_FEATURE_CMO)) {
preempt_disable();
@ -316,8 +321,11 @@ good_area:
preempt_enable();
}
#endif
} else
} else {
current->min_flt++;
perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
regs, address);
}
up_read(&mm->mmap_sem);
return 0;

1
arch/powerpc/platforms/Kconfig.cputype
View File

@ -1,6 +1,7 @@
config PPC64
bool "64-bit kernel"
default n
select HAVE_PERF_COUNTERS
help
This option selects whether a 32-bit or a 64-bit kernel
will be built.

12
arch/powerpc/platforms/pseries/xics.c
View File

@ -333,7 +333,7 @@ static void xics_eoi_lpar(unsigned int virq)
lpar_xirr_info_set((0xff << 24) | irq);
}
static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
{
unsigned int irq;
int status;
@ -342,14 +342,14 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
irq = (unsigned int)irq_map[virq].hwirq;
if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
return;
return -1;
status = rtas_call(ibm_get_xive, 1, 3, xics_status, irq);
if (status) {
printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n",
__func__, irq, status);
return;
return -1;
}
/*
@ -363,7 +363,7 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
printk(KERN_WARNING
"%s: No online cpus in the mask %s for irq %d\n",
__func__, cpulist, virq);
return;
return -1;
}
status = rtas_call(ibm_set_xive, 3, 1, NULL,
@ -372,8 +372,10 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
if (status) {
printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n",
__func__, irq, status);
return;
return -1;
}
return 0;
}
static struct irq_chip xics_pic_direct = {

4
arch/powerpc/sysdev/mpic.c
View File

@ -807,7 +807,7 @@ static void mpic_end_ipi(unsigned int irq)
#endif /* CONFIG_SMP */
void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
{
struct mpic *mpic = mpic_from_irq(irq);
unsigned int src = mpic_irq_to_hw(irq);
@ -824,6 +824,8 @@ void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION),
mpic_physmask(cpus_addr(tmp)[0]));
}
return 0;
}
static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type)

2
arch/powerpc/sysdev/mpic.h
View File

@ -36,6 +36,6 @@ static inline int mpic_pasemi_msi_init(struct mpic *mpic)
extern int mpic_set_irq_type(unsigned int virq, unsigned int flow_type);
extern void mpic_set_vector(unsigned int virq, unsigned int vector);
extern void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask);
extern int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask);
#endif /* _POWERPC_SYSDEV_MPIC_H */

4
arch/sparc/include/asm/thread_info_64.h
View File

@ -102,8 +102,8 @@ struct thread_info {
#define TI_KERN_CNTD1 0x00000488
#define TI_PCR 0x00000490
#define TI_RESTART_BLOCK 0x00000498
#define TI_KUNA_REGS 0x000004c0
#define TI_KUNA_INSN 0x000004c8
#define TI_KUNA_REGS 0x000004c8
#define TI_KUNA_INSN 0x000004d0
#define TI_FPREGS 0x00000500
/* We embed this in the uppermost byte of thread_info->flags */

12
arch/sparc/kernel/irq_64.c
View File

@ -318,10 +318,12 @@ static void sun4u_irq_enable(unsigned int virt_irq)
}
}
static void sun4u_set_affinity(unsigned int virt_irq,
static int sun4u_set_affinity(unsigned int virt_irq,
const struct cpumask *mask)
{
sun4u_irq_enable(virt_irq);
return 0;
}
/* Don't do anything. The desc->status check for IRQ_DISABLED in
@ -377,7 +379,7 @@ static void sun4v_irq_enable(unsigned int virt_irq)
ino, err);
}
static void sun4v_set_affinity(unsigned int virt_irq,
static int sun4v_set_affinity(unsigned int virt_irq,
const struct cpumask *mask)
{
unsigned int ino = virt_irq_table[virt_irq].dev_ino;
@ -388,6 +390,8 @@ static void sun4v_set_affinity(unsigned int virt_irq,
if (err != HV_EOK)
printk(KERN_ERR "sun4v_intr_settarget(%x,%lu): "
"err(%d)\n", ino, cpuid, err);
return 0;
}
static void sun4v_irq_disable(unsigned int virt_irq)
@ -445,7 +449,7 @@ static void sun4v_virq_enable(unsigned int virt_irq)
dev_handle, dev_ino, err);
}
static void sun4v_virt_set_affinity(unsigned int virt_irq,
static int sun4v_virt_set_affinity(unsigned int virt_irq,
const struct cpumask *mask)
{
unsigned long cpuid, dev_handle, dev_ino;
@ -461,6 +465,8 @@ static void sun4v_virt_set_affinity(unsigned int virt_irq,
printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
"err(%d)\n",
dev_handle, dev_ino, cpuid, err);
return 0;
}
static void sun4v_virq_disable(unsigned int virt_irq)

16
arch/x86/Kbuild Normal file
View File

@ -0,0 +1,16 @@
obj-$(CONFIG_KVM) += kvm/
# Xen paravirtualization support
obj-$(CONFIG_XEN) += xen/
# lguest paravirtualization support
obj-$(CONFIG_LGUEST_GUEST) += lguest/
obj-y += kernel/
obj-y += mm/
obj-y += crypto/
obj-y += vdso/
obj-$(CONFIG_IA32_EMULATION) += ia32/

54
arch/x86/Kconfig
View File

@ -47,6 +47,11 @@ config X86
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_LZMA
config OUTPUT_FORMAT
string
default "elf32-i386" if X86_32
default "elf64-x86-64" if X86_64
config ARCH_DEFCONFIG
string
default "arch/x86/configs/i386_defconfig" if X86_32
@ -274,15 +279,9 @@ config SPARSE_IRQ
If you don't know what to do here, say N.
config NUMA_MIGRATE_IRQ_DESC
bool "Move irq desc when changing irq smp_affinity"
config NUMA_IRQ_DESC
def_bool y
depends on SPARSE_IRQ && NUMA
depends on BROKEN
default n
---help---
This enables moving irq_desc to cpu/node that irq will use handled.
If you don't know what to do here, say N.
config X86_MPPARSE
bool "Enable MPS table" if ACPI
@ -355,7 +354,7 @@ config X86_UV
depends on X86_64
depends on X86_EXTENDED_PLATFORM
depends on NUMA
select X86_X2APIC
depends on X86_X2APIC
---help---
This option is needed in order to support SGI Ultraviolet systems.
If you don't have one of these, you should say N here.
@ -740,6 +739,7 @@ config X86_UP_IOAPIC
config X86_LOCAL_APIC
def_bool y
depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
select HAVE_PERF_COUNTERS if (!M386 && !M486)
config X86_IO_APIC
def_bool y
@ -1466,9 +1466,7 @@ config KEXEC_JUMP
config PHYSICAL_START
hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
default "0x1000000" if X86_NUMAQ
default "0x200000" if X86_64
default "0x100000"
default "0x1000000"
---help---
This gives the physical address where the kernel is loaded.
@ -1487,15 +1485,15 @@ config PHYSICAL_START
to be specifically compiled to run from a specific memory area
(normally a reserved region) and this option comes handy.
So if you are using bzImage for capturing the crash dump, leave
the value here unchanged to 0x100000 and set CONFIG_RELOCATABLE=y.
Otherwise if you plan to use vmlinux for capturing the crash dump
change this value to start of the reserved region (Typically 16MB
0x1000000). In other words, it can be set based on the "X" value as
specified in the "crashkernel=YM@XM" command line boot parameter
passed to the panic-ed kernel. Typically this parameter is set as
crashkernel=64M@16M. Please take a look at
Documentation/kdump/kdump.txt for more details about crash dumps.
So if you are using bzImage for capturing the crash dump,
leave the value here unchanged to 0x1000000 and set
CONFIG_RELOCATABLE=y. Otherwise if you plan to use vmlinux
for capturing the crash dump change this value to start of
the reserved region. In other words, it can be set based on
the "X" value as specified in the "crashkernel=YM@XM"
command line boot parameter passed to the panic-ed
kernel. Please take a look at Documentation/kdump/kdump.txt
for more details about crash dumps.
Usage of bzImage for capturing the crash dump is recommended as
one does not have to build two kernels. Same kernel can be used
@ -1508,8 +1506,8 @@ config PHYSICAL_START
Don't change this unless you know what you are doing.
config RELOCATABLE
bool "Build a relocatable kernel (EXPERIMENTAL)"
depends on EXPERIMENTAL
bool "Build a relocatable kernel"
default y
---help---
This builds a kernel image that retains relocation information
so it can be loaded someplace besides the default 1MB.
@ -1524,12 +1522,16 @@ config RELOCATABLE
it has been loaded at and the compile time physical address
(CONFIG_PHYSICAL_START) is ignored.
# Relocation on x86-32 needs some additional build support
config X86_NEED_RELOCS
def_bool y
depends on X86_32 && RELOCATABLE
config PHYSICAL_ALIGN
hex
prompt "Alignment value to which kernel should be aligned" if X86_32
default "0x100000" if X86_32
default "0x200000" if X86_64
range 0x2000 0x400000
default "0x1000000"
range 0x2000 0x1000000
---help---
This value puts the alignment restrictions on physical address
where kernel is loaded and run from. Kernel is compiled for an

20
arch/x86/Kconfig.debug
View File

@ -159,14 +159,30 @@ config IOMMU_DEBUG
options. See Documentation/x86_64/boot-options.txt for more
details.
config IOMMU_STRESS
bool "Enable IOMMU stress-test mode"
---help---
This option disables various optimizations in IOMMU related
code to do real stress testing of the IOMMU code. This option
will cause a performance drop and should only be enabled for
testing.
config IOMMU_LEAK
bool "IOMMU leak tracing"
depends on DEBUG_KERNEL
depends on IOMMU_DEBUG
depends on IOMMU_DEBUG && DMA_API_DEBUG
---help---
Add a simple leak tracer to the IOMMU code. This is useful when you
are debugging a buggy device driver that leaks IOMMU mappings.
config X86_DS_SELFTEST
bool "DS selftest"
default y
depends on DEBUG_KERNEL
depends on X86_DS
---help---
Perform Debug Store selftests at boot time.
If in doubt, say "N".
config HAVE_MMIOTRACE_SUPPORT
def_bool y

19
arch/x86/Makefile
View File

@ -7,8 +7,6 @@ else
KBUILD_DEFCONFIG := $(ARCH)_defconfig
endif
core-$(CONFIG_KVM) += arch/x86/kvm/
# BITS is used as extension for files which are available in a 32 bit
# and a 64 bit version to simplify shared Makefiles.
# e.g.: obj-y += foo_$(BITS).o
@ -118,21 +116,8 @@ head-y += arch/x86/kernel/init_task.o
libs-y += arch/x86/lib/
# Sub architecture files that needs linking first
core-y += $(fcore-y)
# Xen paravirtualization support
core-$(CONFIG_XEN) += arch/x86/xen/
# lguest paravirtualization support
core-$(CONFIG_LGUEST_GUEST) += arch/x86/lguest/
core-y += arch/x86/kernel/
core-y += arch/x86/mm/
core-y += arch/x86/crypto/
core-y += arch/x86/vdso/
core-$(CONFIG_IA32_EMULATION) += arch/x86/ia32/
# See arch/x86/Kbuild for content of core part of the kernel
core-y += arch/x86/
# drivers-y are linked after core-y
drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/

2
arch/x86/boot/.gitignore vendored
View File

@ -3,6 +3,8 @@ bzImage
cpustr.h
mkcpustr
offsets.h
voffset.h
zoffset.h
setup
setup.bin
setup.elf

29
arch/x86/boot/Makefile
View File

@ -26,9 +26,10 @@ targets := vmlinux.bin setup.bin setup.elf bzImage
targets += fdimage fdimage144 fdimage288 image.iso mtools.conf
subdir- := compressed
setup-y += a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o
setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o edd.o
setup-y += header.o main.o mca.o memory.o pm.o pmjump.o
setup-y += printf.o string.o tty.o video.o video-mode.o version.o
setup-y += printf.o regs.o string.o tty.o video.o video-mode.o
setup-y += version.o
setup-$(CONFIG_X86_APM_BOOT) += apm.o
# The link order of the video-*.o modules can matter. In particular,
@ -86,19 +87,27 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
sed-offsets := -e 's/^00*/0/' \
-e 's/^\([0-9a-fA-F]*\) . \(input_data\|input_data_end\)$$/\#define \2 0x\1/p'
sed-voffset := -e 's/^\([0-9a-fA-F]*\) . \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
quiet_cmd_offsets = OFFSETS $@
cmd_offsets = $(NM) $< | sed -n $(sed-offsets) > $@
quiet_cmd_voffset = VOFFSET $@
cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
$(obj)/offsets.h: $(obj)/compressed/vmlinux FORCE
$(call if_changed,offsets)
targets += voffset.h
$(obj)/voffset.h: vmlinux FORCE
$(call if_changed,voffset)
sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
quiet_cmd_zoffset = ZOFFSET $@
cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
targets += zoffset.h
$(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
$(call if_changed,zoffset)
targets += offsets.h
AFLAGS_header.o += -I$(obj)
$(obj)/header.o: $(obj)/offsets.h
$(obj)/header.o: $(obj)/voffset.h $(obj)/zoffset.h
LDFLAGS_setup.elf := -T
$(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE

9
arch/x86/boot/a20.c
View File

@ -2,7 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007-2008 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -90,8 +90,11 @@ static int a20_test_long(void)
static void enable_a20_bios(void)
{
asm volatile("pushfl; int $0x15; popfl"
: : "a" ((u16)0x2401));
struct biosregs ireg;
initregs(&ireg);
ireg.ax = 0x2401;
intcall(0x15, &ireg, NULL);
}
static void enable_a20_kbc(void)

72
arch/x86/boot/apm.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* Original APM BIOS checking by Stephen Rothwell, May 1994
* (sfr@canb.auug.org.au)
@ -19,75 +20,56 @@
int query_apm_bios(void)
{
u16 ax, bx, cx, dx, di;
u32 ebx, esi;
u8 err;
struct biosregs ireg, oreg;
/* APM BIOS installation check */
ax = 0x5300;
bx = cx = 0;
asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %0"
: "=d" (err), "+a" (ax), "+b" (bx), "+c" (cx)
: : "esi", "edi");
initregs(&ireg);
ireg.ah = 0x53;
intcall(0x15, &ireg, &oreg);
if (err)
if (oreg.flags & X86_EFLAGS_CF)
return -1; /* No APM BIOS */
if (bx != 0x504d) /* "PM" signature */
if (oreg.bx != 0x504d) /* "PM" signature */
return -1;
if (!(cx & 0x02)) /* 32 bits supported? */
if (!(oreg.cx & 0x02)) /* 32 bits supported? */
return -1;
/* Disconnect first, just in case */
ax = 0x5304;
bx = 0;
asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp"
: "+a" (ax), "+b" (bx)
: : "ecx", "edx", "esi", "edi");
/* Paranoia */
ebx = esi = 0;
cx = dx = di = 0;
ireg.al = 0x04;
intcall(0x15, &ireg, NULL);
/* 32-bit connect */
asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %6"
: "=a" (ax), "+b" (ebx), "+c" (cx), "+d" (dx),
"+S" (esi), "+D" (di), "=m" (err)
: "a" (0x5303));
ireg.al = 0x03;
intcall(0x15, &ireg, &oreg);
boot_params.apm_bios_info.cseg = ax;
boot_params.apm_bios_info.offset = ebx;
boot_params.apm_bios_info.cseg_16 = cx;
boot_params.apm_bios_info.dseg = dx;
boot_params.apm_bios_info.cseg_len = (u16)esi;
boot_params.apm_bios_info.cseg_16_len = esi >> 16;
boot_params.apm_bios_info.dseg_len = di;
boot_params.apm_bios_info.cseg = oreg.ax;
boot_params.apm_bios_info.offset = oreg.ebx;
boot_params.apm_bios_info.cseg_16 = oreg.cx;
boot_params.apm_bios_info.dseg = oreg.dx;
boot_params.apm_bios_info.cseg_len = oreg.si;
boot_params.apm_bios_info.cseg_16_len = oreg.hsi;
boot_params.apm_bios_info.dseg_len = oreg.di;
if (err)
if (oreg.flags & X86_EFLAGS_CF)
return -1;
/* Redo the installation check as the 32-bit connect;
some BIOSes return different flags this way... */
ax = 0x5300;
bx = cx = 0;
asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %0"
: "=d" (err), "+a" (ax), "+b" (bx), "+c" (cx)
: : "esi", "edi");
ireg.al = 0x00;
intcall(0x15, &ireg, &oreg);
if (err || bx != 0x504d) {
if ((oreg.eflags & X86_EFLAGS_CF) || oreg.bx != 0x504d) {
/* Failure with 32-bit connect, try to disconect and ignore */
ax = 0x5304;
bx = 0;
asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp"
: "+a" (ax), "+b" (bx)
: : "ecx", "edx", "esi", "edi");
ireg.al = 0x04;
intcall(0x15, &ireg, NULL);
return -1;
}
boot_params.apm_bios_info.version = ax;
boot_params.apm_bios_info.flags = cx;
boot_params.apm_bios_info.version = oreg.ax;
boot_params.apm_bios_info.flags = oreg.cx;
return 0;
}

82
arch/x86/boot/bioscall.S Normal file
View File

@ -0,0 +1,82 @@
/* -----------------------------------------------------------------------
*
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2 or (at your
* option) any later version; incorporated herein by reference.
*
* ----------------------------------------------------------------------- */
/*
* "Glove box" for BIOS calls. Avoids the constant problems with BIOSes
* touching registers they shouldn't be.
*/
.code16
.text
.globl intcall
.type intcall, @function
intcall:
/* Self-modify the INT instruction. Ugly, but works. */
cmpb %al, 3f
je 1f
movb %al, 3f
jmp 1f /* Synchronize pipeline */
1:
/* Save state */
pushfl
pushw %fs
pushw %gs
pushal
/* Copy input state to stack frame */
subw $44, %sp
movw %dx, %si
movw %sp, %di
movw $11, %cx
rep; movsd
/* Pop full state from the stack */
popal
popw %gs
popw %fs
popw %es
popw %ds
popfl
/* Actual INT */
.byte 0xcd /* INT opcode */
3: .byte 0
/* Push full state to the stack */
pushfl
pushw %ds
pushw %es
pushw %fs
pushw %gs
pushal
/* Re-establish C environment invariants */
cld
movzwl %sp, %esp
movw %cs, %ax
movw %ax, %ds
movw %ax, %es
/* Copy output state from stack frame */
movw 68(%esp), %di /* Original %cx == 3rd argument */
andw %di, %di
jz 4f
movw %sp, %si
movw $11, %cx
rep; movsd
4: addw $44, %sp
/* Restore state and return */
popal
popw %gs
popw %fs
popfl
retl
.size intcall, .-intcall

48
arch/x86/boot/boot.h
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -26,6 +27,7 @@
#include <asm/setup.h>
#include "bitops.h"
#include <asm/cpufeature.h>
#include <asm/processor-flags.h>
/* Useful macros */
#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
@ -241,6 +243,49 @@ int enable_a20(void);
/* apm.c */
int query_apm_bios(void);
/* bioscall.c */
struct biosregs {
union {
struct {
u32 edi;
u32 esi;
u32 ebp;
u32 _esp;
u32 ebx;
u32 edx;
u32 ecx;
u32 eax;
u32 _fsgs;
u32 _dses;
u32 eflags;
};
struct {
u16 di, hdi;
u16 si, hsi;
u16 bp, hbp;
u16 _sp, _hsp;
u16 bx, hbx;
u16 dx, hdx;
u16 cx, hcx;
u16 ax, hax;
u16 gs, fs;
u16 es, ds;
u16 flags, hflags;
};
struct {
u8 dil, dih, edi2, edi3;
u8 sil, sih, esi2, esi3;
u8 bpl, bph, ebp2, ebp3;
u8 _spl, _sph, _esp2, _esp3;
u8 bl, bh, ebx2, ebx3;
u8 dl, dh, edx2, edx3;
u8 cl, ch, ecx2, ecx3;
u8 al, ah, eax2, eax3;
};
};
};
void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg);
/* cmdline.c */
int cmdline_find_option(const char *option, char *buffer, int bufsize);
int cmdline_find_option_bool(const char *option);
@ -279,6 +324,9 @@ int sprintf(char *buf, const char *fmt, ...);
int vsprintf(char *buf, const char *fmt, va_list args);
int printf(const char *fmt, ...);
/* regs.c */
void initregs(struct biosregs *regs);
/* string.c */
int strcmp(const char *str1, const char *str2);
size_t strnlen(const char *s, size_t maxlen);

3
arch/x86/boot/compressed/.gitignore vendored
View File

@ -1,3 +1,6 @@
relocs
vmlinux.bin.all
vmlinux.relocs
vmlinux.lds
mkpiggy
piggy.S

54
arch/x86/boot/compressed/Makefile
View File

@ -19,7 +19,9 @@ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
LDFLAGS := -m elf_$(UTS_MACHINE)
LDFLAGS_vmlinux := -T
$(obj)/vmlinux: $(src)/vmlinux_$(BITS).lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE
hostprogs-y := mkpiggy
$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE
$(call if_changed,ld)
@:
@ -29,7 +31,7 @@ $(obj)/vmlinux.bin: vmlinux FORCE
targets += vmlinux.bin.all vmlinux.relocs relocs
hostprogs-$(CONFIG_X86_32) += relocs
hostprogs-$(CONFIG_X86_NEED_RELOCS) += relocs
quiet_cmd_relocs = RELOCS $@
cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
@ -37,46 +39,22 @@ $(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
$(call if_changed,relocs)
vmlinux.bin.all-y := $(obj)/vmlinux.bin
vmlinux.bin.all-$(CONFIG_RELOCATABLE) += $(obj)/vmlinux.relocs
quiet_cmd_relocbin = BUILD $@
cmd_relocbin = cat $(filter-out FORCE,$^) > $@
$(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
$(call if_changed,relocbin)
vmlinux.bin.all-$(CONFIG_X86_NEED_RELOCS) += $(obj)/vmlinux.relocs
ifeq ($(CONFIG_X86_32),y)
ifdef CONFIG_RELOCATABLE
$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
$(call if_changed,gzip)
$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin.all FORCE
$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
$(call if_changed,bzip2)
$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin.all FORCE
$(call if_changed,lzma)
else
$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
$(call if_changed,gzip)
$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
$(call if_changed,bzip2)
$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
$(call if_changed,lzma)
endif
LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
else
$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
$(call if_changed,gzip)
$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
$(call if_changed,bzip2)
$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
$(call if_changed,lzma)
LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
endif
suffix-$(CONFIG_KERNEL_GZIP) := gz
suffix-$(CONFIG_KERNEL_BZIP2) := bz2
suffix-$(CONFIG_KERNEL_LZMA) := lzma
suffix_$(CONFIG_KERNEL_GZIP) = gz
suffix_$(CONFIG_KERNEL_BZIP2) = bz2
suffix_$(CONFIG_KERNEL_LZMA) = lzma
quiet_cmd_mkpiggy = MKPIGGY $@
cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE
$(call if_changed,ld)
targets += piggy.S
$(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
$(call if_changed,mkpiggy)

192
arch/x86/boot/compressed/head_32.S
View File

@ -12,16 +12,16 @@
* the page directory. [According to comments etc elsewhere on a compressed
* kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
*
* Page 0 is deliberately kept safe, since System Management Mode code in
* Page 0 is deliberately kept safe, since System Management Mode code in
* laptops may need to access the BIOS data stored there. This is also
* useful for future device drivers that either access the BIOS via VM86
* useful for future device drivers that either access the BIOS via VM86
* mode.
*/
/*
* High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
*/
.text
.text
#include <linux/linkage.h>
#include <asm/segment.h>
@ -29,161 +29,151 @@
#include <asm/boot.h>
#include <asm/asm-offsets.h>
.section ".text.head","ax",@progbits
.section ".text.head","ax",@progbits
ENTRY(startup_32)
cld
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments */
testb $(1<<6), BP_loadflags(%esi)
jnz 1f
/*
* Test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments
*/
testb $(1<<6), BP_loadflags(%esi)
jnz 1f
cli
movl $(__BOOT_DS),%eax
movl %eax,%ds
movl %eax,%es
movl %eax,%fs
movl %eax,%gs
movl %eax,%ss
movl $__BOOT_DS, %eax
movl %eax, %ds
movl %eax, %es
movl %eax, %fs
movl %eax, %gs
movl %eax, %ss
1:
/* Calculate the delta between where we were compiled to run
/*
* Calculate the delta between where we were compiled to run
* at and where we were actually loaded at. This can only be done
* with a short local call on x86. Nothing else will tell us what
* address we are running at. The reserved chunk of the real-mode
* data at 0x1e4 (defined as a scratch field) are used as the stack
* for this calculation. Only 4 bytes are needed.
*/
leal (0x1e4+4)(%esi), %esp
call 1f
1: popl %ebp
subl $1b, %ebp
leal (BP_scratch+4)(%esi), %esp
call 1f
1: popl %ebp
subl $1b, %ebp
/* %ebp contains the address we are loaded at by the boot loader and %ebx
/*
* %ebp contains the address we are loaded at by the boot loader and %ebx
* contains the address where we should move the kernel image temporarily
* for safe in-place decompression.
*/
#ifdef CONFIG_RELOCATABLE
movl %ebp, %ebx
addl $(CONFIG_PHYSICAL_ALIGN - 1), %ebx
andl $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebx
movl %ebp, %ebx
movl BP_kernel_alignment(%esi), %eax
decl %eax
addl %eax, %ebx
notl %eax
andl %eax, %ebx
#else
movl $LOAD_PHYSICAL_ADDR, %ebx
movl $LOAD_PHYSICAL_ADDR, %ebx
#endif
/* Replace the compressed data size with the uncompressed size */
subl input_len(%ebp), %ebx
movl output_len(%ebp), %eax
addl %eax, %ebx
/* Add 8 bytes for every 32K input block */
shrl $12, %eax
addl %eax, %ebx
/* Add 32K + 18 bytes of extra slack */
addl $(32768 + 18), %ebx
/* Align on a 4K boundary */
addl $4095, %ebx
andl $~4095, %ebx
/* Target address to relocate to for decompression */
addl $z_extract_offset, %ebx
/* Copy the compressed kernel to the end of our buffer
/* Set up the stack */
leal boot_stack_end(%ebx), %esp
/* Zero EFLAGS */
pushl $0
popfl
/*
* Copy the compressed kernel to the end of our buffer
* where decompression in place becomes safe.
*/
pushl %esi
leal _end(%ebp), %esi
leal _end(%ebx), %edi
movl $(_end - startup_32), %ecx
pushl %esi
leal (_bss-4)(%ebp), %esi
leal (_bss-4)(%ebx), %edi
movl $(_bss - startup_32), %ecx
shrl $2, %ecx
std
rep
movsb
rep movsl
cld
popl %esi
/* Compute the kernel start address.
*/
#ifdef CONFIG_RELOCATABLE
addl $(CONFIG_PHYSICAL_ALIGN - 1), %ebp
andl $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebp
#else
movl $LOAD_PHYSICAL_ADDR, %ebp
#endif
popl %esi
/*
* Jump to the relocated address.
*/
leal relocated(%ebx), %eax
jmp *%eax
leal relocated(%ebx), %eax
jmp *%eax
ENDPROC(startup_32)
.section ".text"
.text
relocated:
/*
* Clear BSS
* Clear BSS (stack is currently empty)
*/
xorl %eax,%eax
leal _edata(%ebx),%edi
leal _end(%ebx), %ecx
subl %edi,%ecx
cld
rep
stosb
/*
* Setup the stack for the decompressor
*/
leal boot_stack_end(%ebx), %esp
xorl %eax, %eax
leal _bss(%ebx), %edi
leal _ebss(%ebx), %ecx
subl %edi, %ecx
shrl $2, %ecx
rep stosl
/*
* Do the decompression, and jump to the new kernel..
*/
movl output_len(%ebx), %eax
pushl %eax
# push arguments for decompress_kernel:
pushl %ebp # output address
movl input_len(%ebx), %eax
pushl %eax # input_len
leal input_data(%ebx), %eax
pushl %eax # input_data
leal boot_heap(%ebx), %eax
pushl %eax # heap area
pushl %esi # real mode pointer
call decompress_kernel
addl $20, %esp
popl %ecx
leal z_extract_offset_negative(%ebx), %ebp
/* push arguments for decompress_kernel: */
pushl %ebp /* output address */
pushl $z_input_len /* input_len */
leal input_data(%ebx), %eax
pushl %eax /* input_data */
leal boot_heap(%ebx), %eax
pushl %eax /* heap area */
pushl %esi /* real mode pointer */
call decompress_kernel
addl $20, %esp
#if CONFIG_RELOCATABLE
/* Find the address of the relocations.
/*
* Find the address of the relocations.
*/
movl %ebp, %edi
addl %ecx, %edi
leal z_output_len(%ebp), %edi
/* Calculate the delta between where vmlinux was compiled to run
/*
* Calculate the delta between where vmlinux was compiled to run
* and where it was actually loaded.
*/
movl %ebp, %ebx
subl $LOAD_PHYSICAL_ADDR, %ebx
jz 2f /* Nothing to be done if loaded at compiled addr. */
movl %ebp, %ebx
subl $LOAD_PHYSICAL_ADDR, %ebx
jz 2f /* Nothing to be done if loaded at compiled addr. */
/*
* Process relocations.
*/
1: subl $4, %edi
movl 0(%edi), %ecx
testl %ecx, %ecx
jz 2f
addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
jmp 1b
1: subl $4, %edi
movl (%edi), %ecx
testl %ecx, %ecx
jz 2f
addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
jmp 1b
2:
#endif
/*
* Jump to the decompressed kernel.
*/
xorl %ebx,%ebx
jmp *%ebp
xorl %ebx, %ebx
jmp *%ebp
.bss
/* Stack and heap for uncompression */
.balign 4
/*
* Stack and heap for uncompression
*/
.bss
.balign 4
boot_heap:
.fill BOOT_HEAP_SIZE, 1, 0
boot_stack:

167
arch/x86/boot/compressed/head_64.S
View File

@ -21,8 +21,8 @@
/*
* High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
*/
.code32
.text
.code32
.text
#include <linux/linkage.h>
#include <asm/segment.h>
@ -33,12 +33,14 @@
#include <asm/processor-flags.h>
#include <asm/asm-offsets.h>
.section ".text.head"
.section ".text.head"
.code32
ENTRY(startup_32)
cld
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments */
/*
* Test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments
*/
testb $(1<<6), BP_loadflags(%esi)
jnz 1f
@ -49,14 +51,15 @@ ENTRY(startup_32)
movl %eax, %ss
1:
/* Calculate the delta between where we were compiled to run
/*
* Calculate the delta between where we were compiled to run
* at and where we were actually loaded at. This can only be done
* with a short local call on x86. Nothing else will tell us what
* address we are running at. The reserved chunk of the real-mode
* data at 0x1e4 (defined as a scratch field) are used as the stack
* for this calculation. Only 4 bytes are needed.
*/
leal (0x1e4+4)(%esi), %esp
leal (BP_scratch+4)(%esi), %esp
call 1f
1: popl %ebp
subl $1b, %ebp
@ -70,32 +73,28 @@ ENTRY(startup_32)
testl %eax, %eax
jnz no_longmode
/* Compute the delta between where we were compiled to run at
/*
* Compute the delta between where we were compiled to run at
* and where the code will actually run at.
*/
/* %ebp contains the address we are loaded at by the boot loader and %ebx
*
* %ebp contains the address we are loaded at by the boot loader and %ebx
* contains the address where we should move the kernel image temporarily
* for safe in-place decompression.
*/
#ifdef CONFIG_RELOCATABLE
movl %ebp, %ebx
addl $(PMD_PAGE_SIZE -1), %ebx
andl $PMD_PAGE_MASK, %ebx
movl BP_kernel_alignment(%esi), %eax
decl %eax
addl %eax, %ebx
notl %eax
andl %eax, %ebx
#else
movl $CONFIG_PHYSICAL_START, %ebx
movl $LOAD_PHYSICAL_ADDR, %ebx
#endif
/* Replace the compressed data size with the uncompressed size */
subl input_len(%ebp), %ebx
movl output_len(%ebp), %eax
addl %eax, %ebx
/* Add 8 bytes for every 32K input block */
shrl $12, %eax
addl %eax, %ebx
/* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
addl $(32768 + 18 + 4095), %ebx
andl $~4095, %ebx
/* Target address to relocate to for decompression */
addl $z_extract_offset, %ebx
/*
* Prepare for entering 64 bit mode
@ -114,7 +113,7 @@ ENTRY(startup_32)
/*
* Build early 4G boot pagetable
*/
/* Initialize Page tables to 0*/
/* Initialize Page tables to 0 */
leal pgtable(%ebx), %edi
xorl %eax, %eax
movl $((4096*6)/4), %ecx
@ -155,7 +154,8 @@ ENTRY(startup_32)
btsl $_EFER_LME, %eax
wrmsr
/* Setup for the jump to 64bit mode
/*
* Setup for the jump to 64bit mode
*
* When the jump is performend we will be in long mode but
* in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
@ -184,7 +184,8 @@ no_longmode:
#include "../../kernel/verify_cpu_64.S"
/* Be careful here startup_64 needs to be at a predictable
/*
* Be careful here startup_64 needs to be at a predictable
* address so I can export it in an ELF header. Bootloaders
* should look at the ELF header to find this address, as
* it may change in the future.
@ -192,7 +193,8 @@ no_longmode:
.code64
.org 0x200
ENTRY(startup_64)
/* We come here either from startup_32 or directly from a
/*
* We come here either from startup_32 or directly from a
* 64bit bootloader. If we come here from a bootloader we depend on
* an identity mapped page table being provied that maps our
* entire text+data+bss and hopefully all of memory.
@ -209,50 +211,54 @@ ENTRY(startup_64)
movl $0x20, %eax
ltr %ax
/* Compute the decompressed kernel start address. It is where
/*
* Compute the decompressed kernel start address. It is where
* we were loaded at aligned to a 2M boundary. %rbp contains the
* decompressed kernel start address.
*
* If it is a relocatable kernel then decompress and run the kernel
* from load address aligned to 2MB addr, otherwise decompress and
* run the kernel from CONFIG_PHYSICAL_START
* run the kernel from LOAD_PHYSICAL_ADDR
*
* We cannot rely on the calculation done in 32-bit mode, since we
* may have been invoked via the 64-bit entry point.
*/
/* Start with the delta to where the kernel will run at. */
#ifdef CONFIG_RELOCATABLE
leaq startup_32(%rip) /* - $startup_32 */, %rbp
addq $(PMD_PAGE_SIZE - 1), %rbp
andq $PMD_PAGE_MASK, %rbp
movq %rbp, %rbx
movl BP_kernel_alignment(%rsi), %eax
decl %eax
addq %rax, %rbp
notq %rax
andq %rax, %rbp
#else
movq $CONFIG_PHYSICAL_START, %rbp
movq %rbp, %rbx
movq $LOAD_PHYSICAL_ADDR, %rbp
#endif
/* Replace the compressed data size with the uncompressed size */
movl input_len(%rip), %eax
subq %rax, %rbx
movl output_len(%rip), %eax
addq %rax, %rbx
/* Add 8 bytes for every 32K input block */
shrq $12, %rax
addq %rax, %rbx
/* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
addq $(32768 + 18 + 4095), %rbx
andq $~4095, %rbx
/* Target address to relocate to for decompression */
leaq z_extract_offset(%rbp), %rbx
/* Copy the compressed kernel to the end of our buffer
/* Set up the stack */
leaq boot_stack_end(%rbx), %rsp
/* Zero EFLAGS */
pushq $0
popfq
/*
* Copy the compressed kernel to the end of our buffer
* where decompression in place becomes safe.
*/
leaq _end_before_pgt(%rip), %r8
leaq _end_before_pgt(%rbx), %r9
movq $_end_before_pgt /* - $startup_32 */, %rcx
1: subq $8, %r8
subq $8, %r9
movq 0(%r8), %rax
movq %rax, 0(%r9)
subq $8, %rcx
jnz 1b
pushq %rsi
leaq (_bss-8)(%rip), %rsi
leaq (_bss-8)(%rbx), %rdi
movq $_bss /* - $startup_32 */, %rcx
shrq $3, %rcx
std
rep movsq
cld
popq %rsi
/*
* Jump to the relocated address.
@ -260,37 +266,28 @@ ENTRY(startup_64)
leaq relocated(%rbx), %rax
jmp *%rax
.section ".text"
.text
relocated:
/*
* Clear BSS
* Clear BSS (stack is currently empty)
*/
xorq %rax, %rax
leaq _edata(%rbx), %rdi
leaq _end_before_pgt(%rbx), %rcx
xorl %eax, %eax
leaq _bss(%rip), %rdi
leaq _ebss(%rip), %rcx
subq %rdi, %rcx
cld
rep
stosb
/* Setup the stack */
leaq boot_stack_end(%rip), %rsp
/* zero EFLAGS after setting rsp */
pushq $0
popfq
shrq $3, %rcx
rep stosq
/*
* Do the decompression, and jump to the new kernel..
*/
pushq %rsi # Save the real mode argument
movq %rsi, %rdi # real mode address
leaq boot_heap(%rip), %rsi # malloc area for uncompression
leaq input_data(%rip), %rdx # input_data
movl input_len(%rip), %eax
movq %rax, %rcx # input_len
movq %rbp, %r8 # output
pushq %rsi /* Save the real mode argument */
movq %rsi, %rdi /* real mode address */
leaq boot_heap(%rip), %rsi /* malloc area for uncompression */
leaq input_data(%rip), %rdx /* input_data */
movl $z_input_len, %ecx /* input_len */
movq %rbp, %r8 /* output target address */
call decompress_kernel
popq %rsi
@ -311,11 +308,21 @@ gdt:
.quad 0x0000000000000000 /* TS continued */
gdt_end:
.bss
/* Stack and heap for uncompression */
.balign 4
/*
* Stack and heap for uncompression
*/
.bss
.balign 4
boot_heap:
.fill BOOT_HEAP_SIZE, 1, 0
boot_stack:
.fill BOOT_STACK_SIZE, 1, 0
boot_stack_end:
/*
* Space for page tables (not in .bss so not zeroed)
*/
.section ".pgtable","a",@nobits
.balign 4096
pgtable:
.fill 6*4096, 1, 0

14
arch/x86/boot/compressed/misc.c
View File

@ -325,20 +325,18 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
free_mem_ptr = heap; /* Heap */
free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
error("Destination address inappropriately aligned");
#ifdef CONFIG_X86_64
if ((unsigned long)output & (__KERNEL_ALIGN - 1))
error("Destination address not 2M aligned");
if ((unsigned long)output >= 0xffffffffffUL)
if (heap > 0x3fffffffffffUL)
error("Destination address too large");
#else
if ((u32)output & (CONFIG_PHYSICAL_ALIGN - 1))
error("Destination address not CONFIG_PHYSICAL_ALIGN aligned");
if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
error("Destination address too large");
#ifndef CONFIG_RELOCATABLE
if ((u32)output != LOAD_PHYSICAL_ADDR)
error("Wrong destination address");
#endif
#ifndef CONFIG_RELOCATABLE
if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
error("Wrong destination address");
#endif
if (!quiet)

97
arch/x86/boot/compressed/mkpiggy.c Normal file
View File

@ -0,0 +1,97 @@
/* ----------------------------------------------------------------------- *
*
* Copyright (C) 2009 Intel Corporation. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version
* 2 as published by the Free Software Foundation.
*
* 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.
*
* 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., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA.
*
* H. Peter Anvin <hpa@linux.intel.com>
*
* ----------------------------------------------------------------------- */
/*
* Compute the desired load offset from a compressed program; outputs
* a small assembly wrapper with the appropriate symbols defined.
*/
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <inttypes.h>
static uint32_t getle32(const void *p)
{
const uint8_t *cp = p;
return (uint32_t)cp[0] + ((uint32_t)cp[1] << 8) +
((uint32_t)cp[2] << 16) + ((uint32_t)cp[3] << 24);
}
int main(int argc, char *argv[])
{
uint32_t olen;
long ilen;
unsigned long offs;
FILE *f;
if (argc < 2) {
fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
return 1;
}
/* Get the information for the compressed kernel image first */
f = fopen(argv[1], "r");
if (!f) {
perror(argv[1]);
return 1;
}
if (fseek(f, -4L, SEEK_END)) {
perror(argv[1]);
}
fread(&olen, sizeof olen, 1, f);
ilen = ftell(f);
olen = getle32(&olen);
fclose(f);
/*
* Now we have the input (compressed) and output (uncompressed)
* sizes, compute the necessary decompression offset...
*/
offs = (olen > ilen) ? olen - ilen : 0;
offs += olen >> 12; /* Add 8 bytes for each 32K block */
offs += 32*1024 + 18; /* Add 32K + 18 bytes slack */
offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
printf(".section \".rodata.compressed\",\"a\",@progbits\n");
printf(".globl z_input_len\n");
printf("z_input_len = %lu\n", ilen);
printf(".globl z_output_len\n");
printf("z_output_len = %lu\n", (unsigned long)olen);
printf(".globl z_extract_offset\n");
printf("z_extract_offset = 0x%lx\n", offs);
/* z_extract_offset_negative allows simplification of head_32.S */
printf(".globl z_extract_offset_negative\n");
printf("z_extract_offset_negative = -0x%lx\n", offs);
printf(".globl input_data, input_data_end\n");
printf("input_data:\n");
printf(".incbin \"%s\"\n", argv[1]);
printf("input_data_end:\n");
return 0;
}

29
arch/x86/boot/compressed/vmlinux_64.lds → arch/x86/boot/compressed/vmlinux.lds.S
View File

@ -1,6 +1,17 @@
OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
#undef i386
#include <asm/page_types.h>
#ifdef CONFIG_X86_64
OUTPUT_ARCH(i386:x86-64)
ENTRY(startup_64)
#else
OUTPUT_ARCH(i386)
ENTRY(startup_32)
#endif
SECTIONS
{
/* Be careful parts of head_64.S assume startup_32 is at
@ -33,16 +44,22 @@ SECTIONS
*(.data.*)
_edata = . ;
}
. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
.bss : {
_bss = . ;
*(.bss)
*(.bss.*)
*(COMMON)
. = ALIGN(8);
_end_before_pgt = . ;
. = ALIGN(4096);
pgtable = . ;
. = . + 4096 * 6;
. = ALIGN(8); /* For convenience during zeroing */
_ebss = .;
}
#ifdef CONFIG_X86_64
. = ALIGN(PAGE_SIZE);
.pgtable : {
_pgtable = . ;
*(.pgtable)
_epgtable = . ;
}
#endif
_end = .;
}

10
arch/x86/boot/compressed/vmlinux.scr
View File

@ -1,10 +0,0 @@
SECTIONS
{
.rodata.compressed : {
input_len = .;
LONG(input_data_end - input_data) input_data = .;
*(.data)
output_len = . - 4;
input_data_end = .;
}
}

43
arch/x86/boot/compressed/vmlinux_32.lds
View File

@ -1,43 +0,0 @@
OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
OUTPUT_ARCH(i386)
ENTRY(startup_32)
SECTIONS
{
/* Be careful parts of head_32.S assume startup_32 is at
* address 0.
*/
. = 0;
.text.head : {
_head = . ;
*(.text.head)
_ehead = . ;
}
.rodata.compressed : {
*(.rodata.compressed)
}
.text : {
_text = .; /* Text */
*(.text)
*(.text.*)
_etext = . ;
}
.rodata : {
_rodata = . ;
*(.rodata) /* read-only data */
*(.rodata.*)
_erodata = . ;
}
.data : {
_data = . ;
*(.data)
*(.data.*)
_edata = . ;
}
.bss : {
_bss = . ;
*(.bss)
*(.bss.*)
*(COMMON)
_end = . ;
}
}

69
arch/x86/boot/edd.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -22,17 +23,17 @@
*/
static int read_mbr(u8 devno, void *buf)
{
u16 ax, bx, cx, dx;
struct biosregs ireg, oreg;
ax = 0x0201; /* Legacy Read, one sector */
cx = 0x0001; /* Sector 0-0-1 */
dx = devno;
bx = (size_t)buf;
asm volatile("pushfl; stc; int $0x13; setc %%al; popfl"
: "+a" (ax), "+c" (cx), "+d" (dx), "+b" (bx)
: : "esi", "edi", "memory");
initregs(&ireg);
ireg.ax = 0x0201; /* Legacy Read, one sector */
ireg.cx = 0x0001; /* Sector 0-0-1 */
ireg.dl = devno;
ireg.bx = (size_t)buf;
return -(u8)ax; /* 0 or -1 */
intcall(0x13, &ireg, &oreg);
return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
}
static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
@ -72,56 +73,46 @@ static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
static int get_edd_info(u8 devno, struct edd_info *ei)
{
u16 ax, bx, cx, dx, di;
struct biosregs ireg, oreg;
memset(ei, 0, sizeof *ei);
/* Check Extensions Present */
ax = 0x4100;
bx = EDDMAGIC1;
dx = devno;
asm("pushfl; stc; int $0x13; setc %%al; popfl"
: "+a" (ax), "+b" (bx), "=c" (cx), "+d" (dx)
: : "esi", "edi");
initregs(&ireg);
ireg.ah = 0x41;
ireg.bx = EDDMAGIC1;
ireg.dl = devno;
intcall(0x13, &ireg, &oreg);
if ((u8)ax)
if (oreg.eflags & X86_EFLAGS_CF)
return -1; /* No extended information */
if (bx != EDDMAGIC2)
if (oreg.bx != EDDMAGIC2)
return -1;
ei->device = devno;
ei->version = ax >> 8; /* EDD version number */
ei->interface_support = cx; /* EDD functionality subsets */
ei->version = oreg.ah; /* EDD version number */
ei->interface_support = oreg.cx; /* EDD functionality subsets */
/* Extended Get Device Parameters */
ei->params.length = sizeof(ei->params);
ax = 0x4800;
dx = devno;
asm("pushfl; int $0x13; popfl"
: "+a" (ax), "+d" (dx), "=m" (ei->params)
: "S" (&ei->params)
: "ebx", "ecx", "edi");
ireg.ah = 0x48;
ireg.si = (size_t)&ei->params;
intcall(0x13, &ireg, &oreg);
/* Get legacy CHS parameters */
/* Ralf Brown recommends setting ES:DI to 0:0 */
ax = 0x0800;
dx = devno;
di = 0;
asm("pushw %%es; "
"movw %%di,%%es; "
"pushfl; stc; int $0x13; setc %%al; popfl; "
"popw %%es"
: "+a" (ax), "=b" (bx), "=c" (cx), "+d" (dx), "+D" (di)
: : "esi");
ireg.ah = 0x08;
ireg.es = 0;
intcall(0x13, &ireg, &oreg);
if ((u8)ax == 0) {
ei->legacy_max_cylinder = (cx >> 8) + ((cx & 0xc0) << 2);
ei->legacy_max_head = dx >> 8;
ei->legacy_sectors_per_track = cx & 0x3f;
if (!(oreg.eflags & X86_EFLAGS_CF)) {
ei->legacy_max_cylinder = oreg.ch + ((oreg.cl & 0xc0) << 2);
ei->legacy_max_head = oreg.dh;
ei->legacy_sectors_per_track = oreg.cl & 0x3f;
}
return 0;

30
arch/x86/boot/header.S
View File

@ -22,7 +22,8 @@
#include <asm/page_types.h>
#include <asm/setup.h>
#include "boot.h"
#include "offsets.h"
#include "voffset.h"
#include "zoffset.h"
BOOTSEG = 0x07C0 /* original address of boot-sector */
SYSSEG = 0x1000 /* historical load address >> 4 */
@ -115,7 +116,7 @@ _start:
# Part 2 of the header, from the old setup.S
.ascii "HdrS" # header signature
.word 0x0209 # header version number (>= 0x0105)
.word 0x020a # header version number (>= 0x0105)
# or else old loadlin-1.5 will fail)
.globl realmode_swtch
realmode_swtch: .word 0, 0 # default_switch, SETUPSEG
@ -168,7 +169,11 @@ heap_end_ptr: .word _end+STACK_SIZE-512
# end of setup code can be used by setup
# for local heap purposes.
pad1: .word 0
ext_loader_ver:
.byte 0 # Extended boot loader version
ext_loader_type:
.byte 0 # Extended boot loader type
cmd_line_ptr: .long 0 # (Header version 0x0202 or later)
# If nonzero, a 32-bit pointer
# to the kernel command line.
@ -200,7 +205,7 @@ relocatable_kernel: .byte 1
#else
relocatable_kernel: .byte 0
#endif
pad2: .byte 0
min_alignment: .byte MIN_KERNEL_ALIGN_LG2 # minimum alignment
pad3: .word 0
cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line,
@ -212,16 +217,27 @@ hardware_subarch: .long 0 # subarchitecture, added with 2.07
hardware_subarch_data: .quad 0
payload_offset: .long input_data
payload_length: .long input_data_end-input_data
payload_offset: .long ZO_input_data
payload_length: .long ZO_z_input_len
setup_data: .quad 0 # 64-bit physical pointer to
# single linked list of
# struct setup_data
pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr
#define ZO_INIT_SIZE (ZO__end - ZO_startup_32 + ZO_z_extract_offset)
#define VO_INIT_SIZE (VO__end - VO__text)
#if ZO_INIT_SIZE > VO_INIT_SIZE
#define INIT_SIZE ZO_INIT_SIZE
#else
#define INIT_SIZE VO_INIT_SIZE
#endif
init_size: .long INIT_SIZE # kernel initialization size
# End of setup header #####################################################
.section ".inittext", "ax"
.section ".entrytext", "ax"
start_of_setup:
#ifdef SAFE_RESET_DISK_CONTROLLER
# Reset the disk controller.

39
arch/x86/boot/main.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -61,11 +62,10 @@ static void copy_boot_params(void)
*/
static void keyboard_set_repeat(void)
{
u16 ax = 0x0305;
u16 bx = 0;
asm volatile("int $0x16"
: "+a" (ax), "+b" (bx)
: : "ecx", "edx", "esi", "edi");
struct biosregs ireg;
initregs(&ireg);
ireg.ax = 0x0305;
intcall(0x16, &ireg, NULL);
}
/*
@ -73,18 +73,22 @@ static void keyboard_set_repeat(void)
*/
static void query_ist(void)
{
struct biosregs ireg, oreg;
/* Some older BIOSes apparently crash on this call, so filter
it from machines too old to have SpeedStep at all. */
if (cpu.level < 6)
return;
asm("int $0x15"
: "=a" (boot_params.ist_info.signature),
"=b" (boot_params.ist_info.command),
"=c" (boot_params.ist_info.event),
"=d" (boot_params.ist_info.perf_level)
: "a" (0x0000e980), /* IST Support */
"d" (0x47534943)); /* Request value */
initregs(&ireg);
ireg.ax = 0xe980; /* IST Support */
ireg.edx = 0x47534943; /* Request value */
intcall(0x15, &ireg, &oreg);
boot_params.ist_info.signature = oreg.eax;
boot_params.ist_info.command = oreg.ebx;
boot_params.ist_info.event = oreg.ecx;
boot_params.ist_info.perf_level = oreg.edx;
}
/*
@ -93,13 +97,12 @@ static void query_ist(void)
static void set_bios_mode(void)
{
#ifdef CONFIG_X86_64
u32 eax, ebx;
struct biosregs ireg;
eax = 0xec00;
ebx = 2;
asm volatile("int $0x15"
: "+a" (eax), "+b" (ebx)
: : "ecx", "edx", "esi", "edi");
initregs(&ireg);
ireg.ax = 0xec00;
ireg.bx = 2;
intcall(0x15, &ireg, NULL);
#endif
}

23
arch/x86/boot/mca.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -16,26 +17,22 @@
int query_mca(void)
{
u8 err;
u16 es, bx, len;
struct biosregs ireg, oreg;
u16 len;
asm("pushw %%es ; "
"int $0x15 ; "
"setc %0 ; "
"movw %%es, %1 ; "
"popw %%es"
: "=acd" (err), "=acdSD" (es), "=b" (bx)
: "a" (0xc000));
initregs(&ireg);
ireg.ah = 0xc0;
intcall(0x15, &ireg, &oreg);
if (err)
if (oreg.eflags & X86_EFLAGS_CF)
return -1; /* No MCA present */
set_fs(es);
len = rdfs16(bx);
set_fs(oreg.es);
len = rdfs16(oreg.bx);
if (len > sizeof(boot_params.sys_desc_table))
len = sizeof(boot_params.sys_desc_table);
copy_from_fs(&boot_params.sys_desc_table, bx, len);
copy_from_fs(&boot_params.sys_desc_table, oreg.bx, len);
return 0;
}

79
arch/x86/boot/memory.c
View File

@ -20,12 +20,16 @@
static int detect_memory_e820(void)
{
int count = 0;
u32 next = 0;
u32 size, id, edi;
u8 err;
struct biosregs ireg, oreg;
struct e820entry *desc = boot_params.e820_map;
static struct e820entry buf; /* static so it is zeroed */
initregs(&ireg);
ireg.ax = 0xe820;
ireg.cx = sizeof buf;
ireg.edx = SMAP;
ireg.di = (size_t)&buf;
/*
* Note: at least one BIOS is known which assumes that the
* buffer pointed to by one e820 call is the same one as
@ -41,22 +45,13 @@ static int detect_memory_e820(void)
*/
do {
size = sizeof buf;
/* Important: %edx and %esi are clobbered by some BIOSes,
so they must be either used for the error output
or explicitly marked clobbered. Given that, assume there
is something out there clobbering %ebp and %edi, too. */
asm("pushl %%ebp; int $0x15; popl %%ebp; setc %0"
: "=d" (err), "+b" (next), "=a" (id), "+c" (size),
"=D" (edi), "+m" (buf)
: "D" (&buf), "d" (SMAP), "a" (0xe820)
: "esi");
intcall(0x15, &ireg, &oreg);
ireg.ebx = oreg.ebx; /* for next iteration... */
/* BIOSes which terminate the chain with CF = 1 as opposed
to %ebx = 0 don't always report the SMAP signature on
the final, failing, probe. */
if (err)
if (oreg.eflags & X86_EFLAGS_CF)
break;
/* Some BIOSes stop returning SMAP in the middle of
@ -64,60 +59,64 @@ static int detect_memory_e820(void)
screwed up the map at that point, we might have a
partial map, the full map, or complete garbage, so
just return failure. */
if (id != SMAP) {
if (oreg.eax != SMAP) {
count = 0;
break;
}
*desc++ = buf;
count++;
} while (next && count < ARRAY_SIZE(boot_params.e820_map));
} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));
return boot_params.e820_entries = count;
}
static int detect_memory_e801(void)
{
u16 ax, bx, cx, dx;
u8 err;
struct biosregs ireg, oreg;
bx = cx = dx = 0;
ax = 0xe801;
asm("stc; int $0x15; setc %0"
: "=m" (err), "+a" (ax), "+b" (bx), "+c" (cx), "+d" (dx));
initregs(&ireg);
ireg.ax = 0xe801;
intcall(0x15, &ireg, &oreg);
if (err)
if (oreg.eflags & X86_EFLAGS_CF)
return -1;
/* Do we really need to do this? */
if (cx || dx) {
ax = cx;
bx = dx;
if (oreg.cx || oreg.dx) {
oreg.ax = oreg.cx;
oreg.bx = oreg.dx;
}
if (ax > 15*1024)
if (oreg.ax > 15*1024) {
return -1; /* Bogus! */
/* This ignores memory above 16MB if we have a memory hole
there. If someone actually finds a machine with a memory
hole at 16MB and no support for 0E820h they should probably
generate a fake e820 map. */
boot_params.alt_mem_k = (ax == 15*1024) ? (dx << 6)+ax : ax;
} else if (oreg.ax == 15*1024) {
boot_params.alt_mem_k = (oreg.dx << 6) + oreg.ax;
} else {
/*
* This ignores memory above 16MB if we have a memory
* hole there. If someone actually finds a machine
* with a memory hole at 16MB and no support for
* 0E820h they should probably generate a fake e820
* map.
*/
boot_params.alt_mem_k = oreg.ax;
}
return 0;
}
static int detect_memory_88(void)
{
u16 ax;
u8 err;
struct biosregs ireg, oreg;
ax = 0x8800;
asm("stc; int $0x15; setc %0" : "=bcdm" (err), "+a" (ax));
initregs(&ireg);
ireg.ah = 0x88;
intcall(0x15, &ireg, &oreg);
boot_params.screen_info.ext_mem_k = ax;
boot_params.screen_info.ext_mem_k = oreg.ax;
return -err;
return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
}
int detect_memory(void)

29
arch/x86/boot/regs.c Normal file
View File

@ -0,0 +1,29 @@
/* -----------------------------------------------------------------------
*
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2 or (at your
* option) any later version; incorporated herein by reference.
*
* ----------------------------------------------------------------------- */
/*
* Simple helper function for initializing a register set.
*
* Note that this sets EFLAGS_CF in the input register set; this
* makes it easier to catch functions which do nothing but don't
* explicitly set CF.
*/
#include "boot.h"
void initregs(struct biosregs *reg)
{
memset(reg, 0, sizeof *reg);
reg->eflags |= X86_EFLAGS_CF;
reg->ds = ds();
reg->es = ds();
reg->fs = fs();
reg->gs = gs();
}

6
arch/x86/boot/setup.ld
View File

@ -15,8 +15,11 @@ SECTIONS
. = 497;
.header : { *(.header) }
.entrytext : { *(.entrytext) }
.inittext : { *(.inittext) }
.initdata : { *(.initdata) }
__end_init = .;
.text : { *(.text) }
.text32 : { *(.text32) }
@ -52,4 +55,7 @@ SECTIONS
. = ASSERT(_end <= 0x8000, "Setup too big!");
. = ASSERT(hdr == 0x1f1, "The setup header has the wrong offset!");
/* Necessary for the very-old-loader check to work... */
. = ASSERT(__end_init <= 5*512, "init sections too big!");
}

52
arch/x86/boot/tty.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -22,24 +23,23 @@
void __attribute__((section(".inittext"))) putchar(int ch)
{
unsigned char c = ch;
struct biosregs ireg;
if (c == '\n')
if (ch == '\n')
putchar('\r'); /* \n -> \r\n */
/* int $0x10 is known to have bugs involving touching registers
it shouldn't. Be extra conservative... */
asm volatile("pushal; pushw %%ds; int $0x10; popw %%ds; popal"
: : "b" (0x0007), "c" (0x0001), "a" (0x0e00|ch));
initregs(&ireg);
ireg.bx = 0x0007;
ireg.cx = 0x0001;
ireg.ah = 0x0e;
ireg.al = ch;
intcall(0x10, &ireg, NULL);
}
void __attribute__((section(".inittext"))) puts(const char *str)
{
int n = 0;
while (*str) {
while (*str)
putchar(*str++);
n++;
}
}
/*
@ -49,14 +49,13 @@ void __attribute__((section(".inittext"))) puts(const char *str)
static u8 gettime(void)
{
u16 ax = 0x0200;
u16 cx, dx;
struct biosregs ireg, oreg;
asm volatile("int $0x1a"
: "+a" (ax), "=c" (cx), "=d" (dx)
: : "ebx", "esi", "edi");
initregs(&ireg);
ireg.ah = 0x02;
intcall(0x1a, &ireg, &oreg);
return dx >> 8;
return oreg.dh;
}
/*
@ -64,19 +63,24 @@ static u8 gettime(void)
*/
int getchar(void)
{
u16 ax = 0;
asm volatile("int $0x16" : "+a" (ax));
struct biosregs ireg, oreg;
return ax & 0xff;
initregs(&ireg);
/* ireg.ah = 0x00; */
intcall(0x16, &ireg, &oreg);
return oreg.al;
}
static int kbd_pending(void)
{
u8 pending;
asm volatile("int $0x16; setnz %0"
: "=qm" (pending)
: "a" (0x0100));
return pending;
struct biosregs ireg, oreg;
initregs(&ireg);
ireg.ah = 0x01;
intcall(0x16, &ireg, &oreg);
return !(oreg.eflags & X86_EFLAGS_ZF);
}
void kbd_flush(void)

27
arch/x86/boot/video-bios.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -29,21 +30,21 @@ static int bios_set_mode(struct mode_info *mi)
static int set_bios_mode(u8 mode)
{
u16 ax;
struct biosregs ireg, oreg;
u8 new_mode;
ax = mode; /* AH=0x00 Set Video Mode */
asm volatile(INT10
: "+a" (ax)
: : "ebx", "ecx", "edx", "esi", "edi");
initregs(&ireg);
ireg.al = mode; /* AH=0x00 Set Video Mode */
intcall(0x10, &ireg, NULL);
ax = 0x0f00; /* Get Current Video Mode */
asm volatile(INT10
: "+a" (ax)
: : "ebx", "ecx", "edx", "esi", "edi");
ireg.ah = 0x0f; /* Get Current Video Mode */
intcall(0x10, &ireg, &oreg);
do_restore = 1; /* Assume video contents were lost */
new_mode = ax & 0x7f; /* Not all BIOSes are clean with the top bit */
/* Not all BIOSes are clean with the top bit */
new_mode = ireg.al & 0x7f;
if (new_mode == mode)
return 0; /* Mode change OK */
@ -53,10 +54,8 @@ static int set_bios_mode(u8 mode)
/* Mode setting failed, but we didn't end up where we
started. That's bad. Try to revert to the original
video mode. */
ax = boot_params.screen_info.orig_video_mode;
asm volatile(INT10
: "+a" (ax)
: : "ebx", "ecx", "edx", "esi", "edi");
ireg.ax = boot_params.screen_info.orig_video_mode;
intcall(0x10, &ireg, NULL);
}
#endif
return -1;

137
arch/x86/boot/video-vesa.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -31,7 +32,7 @@ static inline void vesa_store_mode_params_graphics(void) {}
static int vesa_probe(void)
{
#if defined(CONFIG_VIDEO_VESA) || defined(CONFIG_FIRMWARE_EDID)
u16 ax, cx, di;
struct biosregs ireg, oreg;
u16 mode;
addr_t mode_ptr;
struct mode_info *mi;
@ -39,13 +40,12 @@ static int vesa_probe(void)
video_vesa.modes = GET_HEAP(struct mode_info, 0);
ax = 0x4f00;
di = (size_t)&vginfo;
asm(INT10
: "+a" (ax), "+D" (di), "=m" (vginfo)
: : "ebx", "ecx", "edx", "esi");
initregs(&ireg);
ireg.ax = 0x4f00;
ireg.di = (size_t)&vginfo;
intcall(0x10, &ireg, &oreg);
if (ax != 0x004f ||
if (ireg.ax != 0x004f ||
vginfo.signature != VESA_MAGIC ||
vginfo.version < 0x0102)
return 0; /* Not present */
@ -65,14 +65,12 @@ static int vesa_probe(void)
memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
ax = 0x4f01;
cx = mode;
di = (size_t)&vminfo;
asm(INT10
: "+a" (ax), "+c" (cx), "+D" (di), "=m" (vminfo)
: : "ebx", "edx", "esi");
ireg.ax = 0x4f01;
ireg.cx = mode;
ireg.di = (size_t)&vminfo;
intcall(0x10, &ireg, &oreg);
if (ax != 0x004f)
if (ireg.ax != 0x004f)
continue;
if ((vminfo.mode_attr & 0x15) == 0x05) {
@ -111,20 +109,19 @@ static int vesa_probe(void)
static int vesa_set_mode(struct mode_info *mode)
{
u16 ax, bx, cx, di;
struct biosregs ireg, oreg;
int is_graphic;
u16 vesa_mode = mode->mode - VIDEO_FIRST_VESA;
memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
ax = 0x4f01;
cx = vesa_mode;
di = (size_t)&vminfo;
asm(INT10
: "+a" (ax), "+c" (cx), "+D" (di), "=m" (vminfo)
: : "ebx", "edx", "esi");
initregs(&ireg);
ireg.ax = 0x4f01;
ireg.cx = vesa_mode;
ireg.di = (size_t)&vminfo;
intcall(0x10, &ireg, &oreg);
if (ax != 0x004f)
if (oreg.ax != 0x004f)
return -1;
if ((vminfo.mode_attr & 0x15) == 0x05) {
@ -141,14 +138,12 @@ static int vesa_set_mode(struct mode_info *mode)
}
ax = 0x4f02;
bx = vesa_mode;
di = 0;
asm volatile(INT10
: "+a" (ax), "+b" (bx), "+D" (di)
: : "ecx", "edx", "esi");
initregs(&ireg);
ireg.ax = 0x4f02;
ireg.bx = vesa_mode;
intcall(0x10, &ireg, &oreg);
if (ax != 0x004f)
if (oreg.ax != 0x004f)
return -1;
graphic_mode = is_graphic;
@ -171,50 +166,45 @@ static int vesa_set_mode(struct mode_info *mode)
/* Switch DAC to 8-bit mode */
static void vesa_dac_set_8bits(void)
{
struct biosregs ireg, oreg;
u8 dac_size = 6;
/* If possible, switch the DAC to 8-bit mode */
if (vginfo.capabilities & 1) {
u16 ax, bx;
ax = 0x4f08;
bx = 0x0800;
asm volatile(INT10
: "+a" (ax), "+b" (bx)
: : "ecx", "edx", "esi", "edi");
if (ax == 0x004f)
dac_size = bx >> 8;
initregs(&ireg);
ireg.ax = 0x4f08;
ireg.bh = 0x08;
intcall(0x10, &ireg, &oreg);
if (oreg.ax == 0x004f)
dac_size = oreg.bh;
}
/* Set the color sizes to the DAC size, and offsets to 0 */
boot_params.screen_info.red_size = dac_size;
boot_params.screen_info.red_size = dac_size;
boot_params.screen_info.green_size = dac_size;
boot_params.screen_info.blue_size = dac_size;
boot_params.screen_info.rsvd_size = dac_size;
boot_params.screen_info.blue_size = dac_size;
boot_params.screen_info.rsvd_size = dac_size;
boot_params.screen_info.red_pos = 0;
boot_params.screen_info.green_pos = 0;
boot_params.screen_info.blue_pos = 0;
boot_params.screen_info.rsvd_pos = 0;
boot_params.screen_info.red_pos = 0;
boot_params.screen_info.green_pos = 0;
boot_params.screen_info.blue_pos = 0;
boot_params.screen_info.rsvd_pos = 0;
}
/* Save the VESA protected mode info */
static void vesa_store_pm_info(void)
{
u16 ax, bx, di, es;
struct biosregs ireg, oreg;
ax = 0x4f0a;
bx = di = 0;
asm("pushw %%es; "INT10"; movw %%es,%0; popw %%es"
: "=d" (es), "+a" (ax), "+b" (bx), "+D" (di)
: : "ecx", "esi");
initregs(&ireg);
ireg.ax = 0x4f0a;
intcall(0x10, &ireg, &oreg);
if (ax != 0x004f)
if (oreg.ax != 0x004f)
return;
boot_params.screen_info.vesapm_seg = es;
boot_params.screen_info.vesapm_off = di;
boot_params.screen_info.vesapm_seg = oreg.es;
boot_params.screen_info.vesapm_off = oreg.di;
}
/*
@ -252,7 +242,7 @@ static void vesa_store_mode_params_graphics(void)
void vesa_store_edid(void)
{
#ifdef CONFIG_FIRMWARE_EDID
u16 ax, bx, cx, dx, di;
struct biosregs ireg, oreg;
/* Apparently used as a nonsense token... */
memset(&boot_params.edid_info, 0x13, sizeof boot_params.edid_info);
@ -260,33 +250,26 @@ void vesa_store_edid(void)
if (vginfo.version < 0x0200)
return; /* EDID requires VBE 2.0+ */
ax = 0x4f15; /* VBE DDC */
bx = 0x0000; /* Report DDC capabilities */
cx = 0; /* Controller 0 */
di = 0; /* ES:DI must be 0 by spec */
initregs(&ireg);
ireg.ax = 0x4f15; /* VBE DDC */
/* ireg.bx = 0x0000; */ /* Report DDC capabilities */
/* ireg.cx = 0; */ /* Controller 0 */
ireg.es = 0; /* ES:DI must be 0 by spec */
intcall(0x10, &ireg, &oreg);
/* Note: The VBE DDC spec is different from the main VESA spec;
we genuinely have to assume all registers are destroyed here. */
asm("pushw %%es; movw %2,%%es; "INT10"; popw %%es"
: "+a" (ax), "+b" (bx), "+c" (cx), "+D" (di)
: : "esi", "edx");
if (ax != 0x004f)
if (oreg.ax != 0x004f)
return; /* No EDID */
/* BH = time in seconds to transfer EDD information */
/* BL = DDC level supported */
ax = 0x4f15; /* VBE DDC */
bx = 0x0001; /* Read EDID */
cx = 0; /* Controller 0 */
dx = 0; /* EDID block number */
di =(size_t) &boot_params.edid_info; /* (ES:)Pointer to block */
asm(INT10
: "+a" (ax), "+b" (bx), "+d" (dx), "=m" (boot_params.edid_info),
"+c" (cx), "+D" (di)
: : "esi");
ireg.ax = 0x4f15; /* VBE DDC */
ireg.bx = 0x0001; /* Read EDID */
/* ireg.cx = 0; */ /* Controller 0 */
/* ireg.dx = 0; */ /* EDID block number */
ireg.es = ds();
ireg.di =(size_t)&boot_params.edid_info; /* (ES:)Pointer to block */
intcall(0x10, &ireg, &oreg);
#endif /* CONFIG_FIRMWARE_EDID */
}

95
arch/x86/boot/video-vga.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -39,30 +40,30 @@ static __videocard video_vga;
/* Set basic 80x25 mode */
static u8 vga_set_basic_mode(void)
{
struct biosregs ireg, oreg;
u16 ax;
u8 rows;
u8 mode;
initregs(&ireg);
#ifdef CONFIG_VIDEO_400_HACK
if (adapter >= ADAPTER_VGA) {
asm volatile(INT10
: : "a" (0x1202), "b" (0x0030)
: "ecx", "edx", "esi", "edi");
ireg.ax = 0x1202;
ireg.bx = 0x0030;
intcall(0x10, &ireg, NULL);
}
#endif
ax = 0x0f00;
asm volatile(INT10
: "+a" (ax)
: : "ebx", "ecx", "edx", "esi", "edi");
mode = (u8)ax;
intcall(0x10, &ireg, &oreg);
mode = oreg.al;
set_fs(0);
rows = rdfs8(0x484); /* rows minus one */
#ifndef CONFIG_VIDEO_400_HACK
if ((ax == 0x5003 || ax == 0x5007) &&
if ((oreg.ax == 0x5003 || oreg.ax == 0x5007) &&
(rows == 0 || rows == 24))
return mode;
#endif
@ -71,10 +72,8 @@ static u8 vga_set_basic_mode(void)
mode = 3;
/* Set the mode */
ax = mode;
asm volatile(INT10
: "+a" (ax)
: : "ebx", "ecx", "edx", "esi", "edi");
ireg.ax = mode; /* AH=0: set mode */
intcall(0x10, &ireg, NULL);
do_restore = 1;
return mode;
}
@ -82,43 +81,69 @@ static u8 vga_set_basic_mode(void)
static void vga_set_8font(void)
{
/* Set 8x8 font - 80x43 on EGA, 80x50 on VGA */
struct biosregs ireg;
initregs(&ireg);
/* Set 8x8 font */
asm volatile(INT10 : : "a" (0x1112), "b" (0));
ireg.ax = 0x1112;
/* ireg.bl = 0; */
intcall(0x10, &ireg, NULL);
/* Use alternate print screen */
asm volatile(INT10 : : "a" (0x1200), "b" (0x20));
ireg.ax = 0x1200;
ireg.bl = 0x20;
intcall(0x10, &ireg, NULL);
/* Turn off cursor emulation */
asm volatile(INT10 : : "a" (0x1201), "b" (0x34));
ireg.ax = 0x1201;
ireg.bl = 0x34;
intcall(0x10, &ireg, NULL);
/* Cursor is scan lines 6-7 */
asm volatile(INT10 : : "a" (0x0100), "c" (0x0607));
ireg.ax = 0x0100;
ireg.cx = 0x0607;
intcall(0x10, &ireg, NULL);
}
static void vga_set_14font(void)
{
/* Set 9x14 font - 80x28 on VGA */
struct biosregs ireg;
initregs(&ireg);
/* Set 9x14 font */
asm volatile(INT10 : : "a" (0x1111), "b" (0));
ireg.ax = 0x1111;
/* ireg.bl = 0; */
intcall(0x10, &ireg, NULL);
/* Turn off cursor emulation */
asm volatile(INT10 : : "a" (0x1201), "b" (0x34));
ireg.ax = 0x1201;
ireg.bl = 0x34;
intcall(0x10, &ireg, NULL);
/* Cursor is scan lines 11-12 */
asm volatile(INT10 : : "a" (0x0100), "c" (0x0b0c));
ireg.ax = 0x0100;
ireg.cx = 0x0b0c;
intcall(0x10, &ireg, NULL);
}
static void vga_set_80x43(void)
{
/* Set 80x43 mode on VGA (not EGA) */
struct biosregs ireg;
initregs(&ireg);
/* Set 350 scans */
asm volatile(INT10 : : "a" (0x1201), "b" (0x30));
ireg.ax = 0x1201;
ireg.bl = 0x30;
intcall(0x10, &ireg, NULL);
/* Reset video mode */
asm volatile(INT10 : : "a" (0x0003));
ireg.ax = 0x0003;
intcall(0x10, &ireg, NULL);
vga_set_8font();
}
@ -225,8 +250,6 @@ static int vga_set_mode(struct mode_info *mode)
*/
static int vga_probe(void)
{
u16 ega_bx;
static const char *card_name[] = {
"CGA/MDA/HGC", "EGA", "VGA"
};
@ -240,26 +263,26 @@ static int vga_probe(void)
sizeof(ega_modes)/sizeof(struct mode_info),
sizeof(vga_modes)/sizeof(struct mode_info),
};
u8 vga_flag;
asm(INT10
: "=b" (ega_bx)
: "a" (0x1200), "b" (0x10) /* Check EGA/VGA */
: "ecx", "edx", "esi", "edi");
struct biosregs ireg, oreg;
initregs(&ireg);
ireg.ax = 0x1200;
ireg.bl = 0x10; /* Check EGA/VGA */
intcall(0x10, &ireg, &oreg);
#ifndef _WAKEUP
boot_params.screen_info.orig_video_ega_bx = ega_bx;
boot_params.screen_info.orig_video_ega_bx = oreg.bx;
#endif
/* If we have MDA/CGA/HGC then BL will be unchanged at 0x10 */
if ((u8)ega_bx != 0x10) {
if (oreg.bl != 0x10) {
/* EGA/VGA */
asm(INT10
: "=a" (vga_flag)
: "a" (0x1a00)
: "ebx", "ecx", "edx", "esi", "edi");
ireg.ax = 0x1a00;
intcall(0x10, &ireg, &oreg);
if (vga_flag == 0x1a) {
if (oreg.al == 0x1a) {
adapter = ADAPTER_VGA;
#ifndef _WAKEUP
boot_params.screen_info.orig_video_isVGA = 1;

42
arch/x86/boot/video.c
View File

@ -2,6 +2,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
@ -18,33 +19,29 @@
static void store_cursor_position(void)
{
u16 curpos;
u16 ax, bx;
struct biosregs ireg, oreg;
ax = 0x0300;
bx = 0;
asm(INT10
: "=d" (curpos), "+a" (ax), "+b" (bx)
: : "ecx", "esi", "edi");
initregs(&ireg);
ireg.ah = 0x03;
intcall(0x10, &ireg, &oreg);
boot_params.screen_info.orig_x = curpos;
boot_params.screen_info.orig_y = curpos >> 8;
boot_params.screen_info.orig_x = oreg.dl;
boot_params.screen_info.orig_y = oreg.dh;
}
static void store_video_mode(void)
{
u16 ax, page;
struct biosregs ireg, oreg;
/* N.B.: the saving of the video page here is a bit silly,
since we pretty much assume page 0 everywhere. */
ax = 0x0f00;
asm(INT10
: "+a" (ax), "=b" (page)
: : "ecx", "edx", "esi", "edi");
initregs(&ireg);
ireg.ah = 0x0f;
intcall(0x10, &ireg, &oreg);
/* Not all BIOSes are clean with respect to the top bit */
boot_params.screen_info.orig_video_mode = ax & 0x7f;
boot_params.screen_info.orig_video_page = page >> 8;
boot_params.screen_info.orig_video_mode = oreg.al & 0x7f;
boot_params.screen_info.orig_video_page = oreg.bh;
}
/*
@ -257,7 +254,7 @@ static void restore_screen(void)
int y;
addr_t dst = 0;
u16 *src = saved.data;
u16 ax, bx, dx;
struct biosregs ireg;
if (graphic_mode)
return; /* Can't restore onto a graphic mode */
@ -296,12 +293,11 @@ static void restore_screen(void)
}
/* Restore cursor position */
ax = 0x0200; /* Set cursor position */
bx = 0; /* Page number (<< 8) */
dx = (saved.cury << 8)+saved.curx;
asm volatile(INT10
: "+a" (ax), "+b" (bx), "+d" (dx)
: : "ecx", "esi", "edi");
initregs(&ireg);
ireg.ah = 0x02; /* Set cursor position */
ireg.dh = saved.cury;
ireg.dl = saved.curx;
intcall(0x10, &ireg, NULL);
}
#else
#define save_screen() ((void)0)

14
arch/x86/boot/video.h
View File

@ -112,20 +112,6 @@ extern int force_x, force_y; /* Don't query the BIOS for cols/rows */
extern int do_restore; /* Restore screen contents */
extern int graphic_mode; /* Graphics mode with linear frame buffer */
/*
* int $0x10 is notorious for touching registers it shouldn't.
* gcc doesn't like %ebp being clobbered, so define it as a push/pop
* sequence here.
*
* A number of systems, including the original PC can clobber %bp in
* certain circumstances, like when scrolling. There exists at least
* one Trident video card which could clobber DS under a set of
* circumstances that we are unlikely to encounter (scrolling when
* using an extended graphics mode of more than 800x600 pixels), but
* it's cheap insurance to deal with that here.
*/
#define INT10 "pushl %%ebp; pushw %%ds; int $0x10; popw %%ds; popl %%ebp"
/* Accessing VGA indexed registers */
static inline u8 in_idx(u16 port, u8 index)
{

148
arch/x86/configs/i386_defconfig
View File

@ -1,12 +1,13 @@
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.29-rc4
# Tue Feb 24 15:50:58 2009
# Linux kernel version: 2.6.30-rc2
# Mon May 11 16:21:55 2009
#
# CONFIG_64BIT is not set
CONFIG_X86_32=y
# CONFIG_X86_64 is not set
CONFIG_X86=y
CONFIG_OUTPUT_FORMAT="elf32-i386"
CONFIG_ARCH_DEFCONFIG="arch/x86/configs/i386_defconfig"
CONFIG_GENERIC_TIME=y
CONFIG_GENERIC_CMOS_UPDATE=y
@ -33,6 +34,7 @@ CONFIG_ARCH_HAS_CPU_RELAX=y
CONFIG_ARCH_HAS_DEFAULT_IDLE=y
CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
CONFIG_HAVE_SETUP_PER_CPU_AREA=y
CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
# CONFIG_HAVE_CPUMASK_OF_CPU_MAP is not set
CONFIG_ARCH_HIBERNATION_POSSIBLE=y
CONFIG_ARCH_SUSPEND_POSSIBLE=y
@ -40,15 +42,16 @@ CONFIG_ARCH_SUSPEND_POSSIBLE=y
CONFIG_ARCH_POPULATES_NODE_MAP=y
# CONFIG_AUDIT_ARCH is not set
CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_PENDING_IRQ=y
CONFIG_X86_SMP=y
CONFIG_USE_GENERIC_SMP_HELPERS=y
CONFIG_X86_32_SMP=y
CONFIG_X86_HT=y
CONFIG_X86_BIOS_REBOOT=y
CONFIG_X86_TRAMPOLINE=y
CONFIG_X86_32_LAZY_GS=y
CONFIG_KTIME_SCALAR=y
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
@ -60,10 +63,17 @@ CONFIG_LOCK_KERNEL=y
CONFIG_INIT_ENV_ARG_LIMIT=32
CONFIG_LOCALVERSION=""
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_KERNEL_GZIP=y
# CONFIG_KERNEL_BZIP2 is not set
# CONFIG_KERNEL_LZMA is not set
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSVIPC_SYSCTL=y
CONFIG_POSIX_MQUEUE=y
CONFIG_POSIX_MQUEUE_SYSCTL=y
CONFIG_BSD_PROCESS_ACCT=y
# CONFIG_BSD_PROCESS_ACCT_V3 is not set
CONFIG_TASKSTATS=y
@ -113,23 +123,26 @@ CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_RD_GZIP=y
CONFIG_RD_BZIP2=y
CONFIG_RD_LZMA=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_SYSCTL=y
CONFIG_ANON_INODES=y
# CONFIG_EMBEDDED is not set
CONFIG_UID16=y
CONFIG_SYSCTL_SYSCALL=y
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
CONFIG_KALLSYMS_EXTRA_PASS=y
# CONFIG_STRIP_ASM_SYMS is not set
CONFIG_HOTPLUG=y
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_PCSPKR_PLATFORM=y
# CONFIG_COMPAT_BRK is not set
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_ANON_INODES=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
CONFIG_TIMERFD=y
@ -139,6 +152,7 @@ CONFIG_AIO=y
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_PCI_QUIRKS=y
CONFIG_SLUB_DEBUG=y
# CONFIG_COMPAT_BRK is not set
# CONFIG_SLAB is not set
CONFIG_SLUB=y
# CONFIG_SLOB is not set
@ -154,6 +168,8 @@ CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_API_DEBUG=y
# CONFIG_SLOW_WORK is not set
CONFIG_HAVE_GENERIC_DMA_COHERENT=y
CONFIG_SLABINFO=y
CONFIG_RT_MUTEXES=y
@ -167,7 +183,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_STOP_MACHINE=y
CONFIG_BLOCK=y
# CONFIG_LBD is not set
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_BLK_DEV_BSG=y
# CONFIG_BLK_DEV_INTEGRITY is not set
@ -194,12 +209,12 @@ CONFIG_HIGH_RES_TIMERS=y
CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
CONFIG_SMP=y
CONFIG_SPARSE_IRQ=y
CONFIG_X86_FIND_SMP_CONFIG=y
CONFIG_X86_MPPARSE=y
# CONFIG_X86_BIGSMP is not set
CONFIG_X86_EXTENDED_PLATFORM=y
# CONFIG_X86_ELAN is not set
# CONFIG_X86_GENERICARCH is not set
# CONFIG_X86_VSMP is not set
# CONFIG_X86_RDC321X is not set
# CONFIG_X86_32_NON_STANDARD is not set
CONFIG_SCHED_OMIT_FRAME_POINTER=y
# CONFIG_PARAVIRT_GUEST is not set
# CONFIG_MEMTEST is not set
@ -230,8 +245,10 @@ CONFIG_M686=y
# CONFIG_GENERIC_CPU is not set
CONFIG_X86_GENERIC=y
CONFIG_X86_CPU=y
CONFIG_X86_L1_CACHE_BYTES=64
CONFIG_X86_INTERNODE_CACHE_BYTES=64
CONFIG_X86_CMPXCHG=y
CONFIG_X86_L1_CACHE_SHIFT=7
CONFIG_X86_L1_CACHE_SHIFT=5
CONFIG_X86_XADD=y
# CONFIG_X86_PPRO_FENCE is not set
CONFIG_X86_WP_WORKS_OK=y
@ -247,7 +264,7 @@ CONFIG_X86_DEBUGCTLMSR=y
CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_CYRIX_32=y
CONFIG_CPU_SUP_AMD=y
CONFIG_CPU_SUP_CENTAUR_32=y
CONFIG_CPU_SUP_CENTAUR=y
CONFIG_CPU_SUP_TRANSMETA_32=y
CONFIG_CPU_SUP_UMC_32=y
CONFIG_X86_DS=y
@ -279,6 +296,7 @@ CONFIG_MICROCODE_AMD=y
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=y
CONFIG_X86_CPUID=y
# CONFIG_X86_CPU_DEBUG is not set
# CONFIG_NOHIGHMEM is not set
CONFIG_HIGHMEM4G=y
# CONFIG_HIGHMEM64G is not set
@ -302,6 +320,8 @@ CONFIG_ZONE_DMA_FLAG=1
CONFIG_BOUNCE=y
CONFIG_VIRT_TO_BUS=y
CONFIG_UNEVICTABLE_LRU=y
CONFIG_HAVE_MLOCK=y
CONFIG_HAVE_MLOCKED_PAGE_BIT=y
CONFIG_HIGHPTE=y
CONFIG_X86_CHECK_BIOS_CORRUPTION=y
CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
@ -312,6 +332,7 @@ CONFIG_MTRR=y
CONFIG_X86_PAT=y
CONFIG_EFI=y
CONFIG_SECCOMP=y
# CONFIG_CC_STACKPROTECTOR is not set
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
@ -322,8 +343,9 @@ CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
# CONFIG_KEXEC_JUMP is not set
CONFIG_PHYSICAL_START=0x1000000
# CONFIG_RELOCATABLE is not set
CONFIG_PHYSICAL_ALIGN=0x200000
CONFIG_RELOCATABLE=y
CONFIG_X86_NEED_RELOCS=y
CONFIG_PHYSICAL_ALIGN=0x1000000
CONFIG_HOTPLUG_CPU=y
# CONFIG_COMPAT_VDSO is not set
# CONFIG_CMDLINE_BOOL is not set
@ -363,7 +385,6 @@ CONFIG_ACPI_THERMAL=y
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
# CONFIG_ACPI_PCI_SLOT is not set
CONFIG_ACPI_SYSTEM=y
CONFIG_X86_PM_TIMER=y
CONFIG_ACPI_CONTAINER=y
# CONFIG_ACPI_SBS is not set
@ -425,6 +446,7 @@ CONFIG_PCI_BIOS=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
CONFIG_PCI_DOMAINS=y
# CONFIG_DMAR is not set
CONFIG_PCIEPORTBUS=y
# CONFIG_HOTPLUG_PCI_PCIE is not set
CONFIG_PCIEAER=y
@ -435,6 +457,7 @@ CONFIG_PCI_MSI=y
# CONFIG_PCI_DEBUG is not set
# CONFIG_PCI_STUB is not set
CONFIG_HT_IRQ=y
# CONFIG_PCI_IOV is not set
CONFIG_ISA_DMA_API=y
# CONFIG_ISA is not set
# CONFIG_MCA is not set
@ -481,7 +504,6 @@ CONFIG_NET=y
#
# Networking options
#
CONFIG_COMPAT_NET_DEV_OPS=y
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
@ -639,6 +661,7 @@ CONFIG_LLC=y
# CONFIG_LAPB is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set
# CONFIG_PHONET is not set
CONFIG_NET_SCHED=y
#
@ -696,6 +719,7 @@ CONFIG_NET_SCH_FIFO=y
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_NET_TCPPROBE is not set
# CONFIG_NET_DROP_MONITOR is not set
CONFIG_HAMRADIO=y
#
@ -706,12 +730,10 @@ CONFIG_HAMRADIO=y
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_AF_RXRPC is not set
# CONFIG_PHONET is not set
CONFIG_FIB_RULES=y
CONFIG_WIRELESS=y
CONFIG_CFG80211=y
# CONFIG_CFG80211_REG_DEBUG is not set
CONFIG_NL80211=y
CONFIG_WIRELESS_OLD_REGULATORY=y
CONFIG_WIRELESS_EXT=y
CONFIG_WIRELESS_EXT_SYSFS=y
@ -789,6 +811,7 @@ CONFIG_MISC_DEVICES=y
# CONFIG_ICS932S401 is not set
# CONFIG_ENCLOSURE_SERVICES is not set
# CONFIG_HP_ILO is not set
# CONFIG_ISL29003 is not set
# CONFIG_C2PORT is not set
#
@ -842,6 +865,7 @@ CONFIG_SCSI_SPI_ATTRS=y
# CONFIG_SCSI_LOWLEVEL is not set
# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
# CONFIG_SCSI_DH is not set
# CONFIG_SCSI_OSD_INITIATOR is not set
CONFIG_ATA=y
# CONFIG_ATA_NONSTANDARD is not set
CONFIG_ATA_ACPI=y
@ -940,6 +964,7 @@ CONFIG_DM_ZERO=y
CONFIG_MACINTOSH_DRIVERS=y
CONFIG_MAC_EMUMOUSEBTN=y
CONFIG_NETDEVICES=y
CONFIG_COMPAT_NET_DEV_OPS=y
# CONFIG_IFB is not set
# CONFIG_DUMMY is not set
# CONFIG_BONDING is not set
@ -977,6 +1002,8 @@ CONFIG_MII=y
CONFIG_NET_VENDOR_3COM=y
# CONFIG_VORTEX is not set
# CONFIG_TYPHOON is not set
# CONFIG_ETHOC is not set
# CONFIG_DNET is not set
CONFIG_NET_TULIP=y
# CONFIG_DE2104X is not set
# CONFIG_TULIP is not set
@ -1026,6 +1053,7 @@ CONFIG_E1000=y
CONFIG_E1000E=y
# CONFIG_IP1000 is not set
# CONFIG_IGB is not set
# CONFIG_IGBVF is not set
# CONFIG_NS83820 is not set
# CONFIG_HAMACHI is not set
# CONFIG_YELLOWFIN is not set
@ -1040,6 +1068,7 @@ CONFIG_BNX2=y
# CONFIG_QLA3XXX is not set
# CONFIG_ATL1 is not set
# CONFIG_ATL1E is not set
# CONFIG_ATL1C is not set
# CONFIG_JME is not set
CONFIG_NETDEV_10000=y
# CONFIG_CHELSIO_T1 is not set
@ -1049,6 +1078,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
# CONFIG_IXGBE is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set
# CONFIG_VXGE is not set
# CONFIG_MYRI10GE is not set
# CONFIG_NETXEN_NIC is not set
# CONFIG_NIU is not set
@ -1058,6 +1088,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
# CONFIG_BNX2X is not set
# CONFIG_QLGE is not set
# CONFIG_SFC is not set
# CONFIG_BE2NET is not set
CONFIG_TR=y
# CONFIG_IBMOL is not set
# CONFIG_IBMLS is not set
@ -1073,8 +1104,8 @@ CONFIG_WLAN_80211=y
# CONFIG_LIBERTAS is not set
# CONFIG_LIBERTAS_THINFIRM is not set
# CONFIG_AIRO is not set
# CONFIG_HERMES is not set
# CONFIG_ATMEL is not set
# CONFIG_AT76C50X_USB is not set
# CONFIG_AIRO_CS is not set
# CONFIG_PCMCIA_WL3501 is not set
# CONFIG_PRISM54 is not set
@ -1084,21 +1115,21 @@ CONFIG_WLAN_80211=y
# CONFIG_RTL8187 is not set
# CONFIG_ADM8211 is not set
# CONFIG_MAC80211_HWSIM is not set
# CONFIG_MWL8K is not set
# CONFIG_P54_COMMON is not set
CONFIG_ATH5K=y
# CONFIG_ATH5K_DEBUG is not set
# CONFIG_ATH9K is not set
# CONFIG_AR9170_USB is not set
# CONFIG_IPW2100 is not set
# CONFIG_IPW2200 is not set
# CONFIG_IWLCORE is not set
# CONFIG_IWLWIFI_LEDS is not set
# CONFIG_IWLAGN is not set
# CONFIG_IWL3945 is not set
# CONFIG_IWLWIFI is not set
# CONFIG_HOSTAP is not set
# CONFIG_B43 is not set
# CONFIG_B43LEGACY is not set
# CONFIG_ZD1211RW is not set
# CONFIG_RT2X00 is not set
# CONFIG_HERMES is not set
#
# Enable WiMAX (Networking options) to see the WiMAX drivers
@ -1209,6 +1240,8 @@ CONFIG_INPUT_TABLET=y
# CONFIG_TABLET_USB_KBTAB is not set
# CONFIG_TABLET_USB_WACOM is not set
CONFIG_INPUT_TOUCHSCREEN=y
# CONFIG_TOUCHSCREEN_AD7879_I2C is not set
# CONFIG_TOUCHSCREEN_AD7879 is not set
# CONFIG_TOUCHSCREEN_FUJITSU is not set
# CONFIG_TOUCHSCREEN_GUNZE is not set
# CONFIG_TOUCHSCREEN_ELO is not set
@ -1303,6 +1336,7 @@ CONFIG_UNIX98_PTYS=y
# CONFIG_LEGACY_PTYS is not set
# CONFIG_IPMI_HANDLER is not set
CONFIG_HW_RANDOM=y
# CONFIG_HW_RANDOM_TIMERIOMEM is not set
CONFIG_HW_RANDOM_INTEL=y
CONFIG_HW_RANDOM_AMD=y
CONFIG_HW_RANDOM_GEODE=y
@ -1390,7 +1424,6 @@ CONFIG_I2C_I801=y
# CONFIG_SENSORS_PCF8574 is not set
# CONFIG_PCF8575 is not set
# CONFIG_SENSORS_PCA9539 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_MAX6875 is not set
# CONFIG_SENSORS_TSL2550 is not set
# CONFIG_I2C_DEBUG_CORE is not set
@ -1424,6 +1457,7 @@ CONFIG_HWMON=y
# CONFIG_SENSORS_ADT7475 is not set
# CONFIG_SENSORS_K8TEMP is not set
# CONFIG_SENSORS_ASB100 is not set
# CONFIG_SENSORS_ATK0110 is not set
# CONFIG_SENSORS_ATXP1 is not set
# CONFIG_SENSORS_DS1621 is not set
# CONFIG_SENSORS_I5K_AMB is not set
@ -1433,6 +1467,7 @@ CONFIG_HWMON=y
# CONFIG_SENSORS_FSCHER is not set
# CONFIG_SENSORS_FSCPOS is not set
# CONFIG_SENSORS_FSCHMD is not set
# CONFIG_SENSORS_G760A is not set
# CONFIG_SENSORS_GL518SM is not set
# CONFIG_SENSORS_GL520SM is not set
# CONFIG_SENSORS_CORETEMP is not set
@ -1448,11 +1483,14 @@ CONFIG_HWMON=y
# CONFIG_SENSORS_LM90 is not set
# CONFIG_SENSORS_LM92 is not set
# CONFIG_SENSORS_LM93 is not set
# CONFIG_SENSORS_LTC4215 is not set
# CONFIG_SENSORS_LTC4245 is not set
# CONFIG_SENSORS_LM95241 is not set
# CONFIG_SENSORS_MAX1619 is not set
# CONFIG_SENSORS_MAX6650 is not set
# CONFIG_SENSORS_PC87360 is not set
# CONFIG_SENSORS_PC87427 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_SIS5595 is not set
# CONFIG_SENSORS_DME1737 is not set
# CONFIG_SENSORS_SMSC47M1 is not set
@ -1643,7 +1681,6 @@ CONFIG_FB_EFI=y
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_VT8623 is not set
# CONFIG_FB_CYBLA is not set
# CONFIG_FB_TRIDENT is not set
# CONFIG_FB_ARK is not set
# CONFIG_FB_PM3 is not set
@ -1652,6 +1689,7 @@ CONFIG_FB_EFI=y
# CONFIG_FB_VIRTUAL is not set
# CONFIG_FB_METRONOME is not set
# CONFIG_FB_MB862XX is not set
# CONFIG_FB_BROADSHEET is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
# CONFIG_LCD_CLASS_DEVICE is not set
CONFIG_BACKLIGHT_CLASS_DEVICE=y
@ -1738,6 +1776,8 @@ CONFIG_SND_PCI=y
# CONFIG_SND_INDIGO is not set
# CONFIG_SND_INDIGOIO is not set
# CONFIG_SND_INDIGODJ is not set
# CONFIG_SND_INDIGOIOX is not set
# CONFIG_SND_INDIGODJX is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_ENS1370 is not set
@ -1811,15 +1851,17 @@ CONFIG_USB_HIDDEV=y
#
# Special HID drivers
#
CONFIG_HID_COMPAT=y
CONFIG_HID_A4TECH=y
CONFIG_HID_APPLE=y
CONFIG_HID_BELKIN=y
CONFIG_HID_CHERRY=y
CONFIG_HID_CHICONY=y
CONFIG_HID_CYPRESS=y
# CONFIG_DRAGONRISE_FF is not set
CONFIG_HID_EZKEY=y
CONFIG_HID_KYE=y
CONFIG_HID_GYRATION=y
CONFIG_HID_KENSINGTON=y
CONFIG_HID_LOGITECH=y
CONFIG_LOGITECH_FF=y
# CONFIG_LOGIRUMBLEPAD2_FF is not set
@ -1885,11 +1927,11 @@ CONFIG_USB_PRINTER=y
# CONFIG_USB_TMC is not set
#
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
#
#
# see USB_STORAGE Help for more information
# also be needed; see USB_STORAGE Help for more info
#
CONFIG_USB_STORAGE=y
# CONFIG_USB_STORAGE_DEBUG is not set
@ -1931,7 +1973,6 @@ CONFIG_USB_LIBUSUAL=y
# CONFIG_USB_LED is not set
# CONFIG_USB_CYPRESS_CY7C63 is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_PHIDGET is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_FTDI_ELAN is not set
# CONFIG_USB_APPLEDISPLAY is not set
@ -1947,6 +1988,7 @@ CONFIG_USB_LIBUSUAL=y
#
# OTG and related infrastructure
#
# CONFIG_NOP_USB_XCEIV is not set
# CONFIG_UWB is not set
# CONFIG_MMC is not set
# CONFIG_MEMSTICK is not set
@ -1958,8 +2000,10 @@ CONFIG_LEDS_CLASS=y
#
# CONFIG_LEDS_ALIX2 is not set
# CONFIG_LEDS_PCA9532 is not set
# CONFIG_LEDS_LP5521 is not set
# CONFIG_LEDS_CLEVO_MAIL is not set
# CONFIG_LEDS_PCA955X is not set
# CONFIG_LEDS_BD2802 is not set
#
# LED Triggers
@ -1969,6 +2013,10 @@ CONFIG_LEDS_TRIGGERS=y
# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
# CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
#
# iptables trigger is under Netfilter config (LED target)
#
# CONFIG_ACCESSIBILITY is not set
# CONFIG_INFINIBAND is not set
CONFIG_EDAC=y
@ -2037,6 +2085,7 @@ CONFIG_DMADEVICES=y
# DMA Devices
#
# CONFIG_INTEL_IOATDMA is not set
# CONFIG_AUXDISPLAY is not set
# CONFIG_UIO is not set
# CONFIG_STAGING is not set
CONFIG_X86_PLATFORM_DEVICES=y
@ -2071,6 +2120,7 @@ CONFIG_DMIID=y
#
# CONFIG_EXT2_FS is not set
CONFIG_EXT3_FS=y
# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
CONFIG_EXT3_FS_XATTR=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
@ -2100,6 +2150,11 @@ CONFIG_AUTOFS4_FS=y
# CONFIG_FUSE_FS is not set
CONFIG_GENERIC_ACL=y
#
# Caches
#
# CONFIG_FSCACHE is not set
#
# CD-ROM/DVD Filesystems
#
@ -2151,6 +2206,7 @@ CONFIG_MISC_FILESYSTEMS=y
# CONFIG_ROMFS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set
# CONFIG_NILFS2_FS is not set
CONFIG_NETWORK_FILESYSTEMS=y
CONFIG_NFS_FS=y
CONFIG_NFS_V3=y
@ -2164,7 +2220,6 @@ CONFIG_NFS_ACL_SUPPORT=y
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=y
CONFIG_SUNRPC_GSS=y
# CONFIG_SUNRPC_REGISTER_V4 is not set
CONFIG_RPCSEC_GSS_KRB5=y
# CONFIG_RPCSEC_GSS_SPKM3 is not set
# CONFIG_SMB_FS is not set
@ -2251,6 +2306,7 @@ CONFIG_DEBUG_FS=y
CONFIG_DEBUG_KERNEL=y
# CONFIG_DEBUG_SHIRQ is not set
# CONFIG_DETECT_SOFTLOCKUP is not set
# CONFIG_DETECT_HUNG_TASK is not set
# CONFIG_SCHED_DEBUG is not set
CONFIG_SCHEDSTATS=y
CONFIG_TIMER_STATS=y
@ -2266,6 +2322,7 @@ CONFIG_TIMER_STATS=y
# CONFIG_LOCK_STAT is not set
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
CONFIG_STACKTRACE=y
# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_HIGHMEM is not set
CONFIG_DEBUG_BUGVERBOSE=y
@ -2289,13 +2346,19 @@ CONFIG_FRAME_POINTER=y
# CONFIG_FAULT_INJECTION is not set
# CONFIG_LATENCYTOP is not set
CONFIG_SYSCTL_SYSCALL_CHECK=y
# CONFIG_DEBUG_PAGEALLOC is not set
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_NOP_TRACER=y
CONFIG_HAVE_FUNCTION_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
CONFIG_HAVE_DYNAMIC_FTRACE=y
CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
CONFIG_HAVE_HW_BRANCH_TRACER=y
CONFIG_HAVE_FTRACE_SYSCALLS=y
CONFIG_RING_BUFFER=y
CONFIG_TRACING=y
CONFIG_TRACING_SUPPORT=y
#
# Tracers
@ -2305,13 +2368,21 @@ CONFIG_HAVE_HW_BRANCH_TRACER=y
# CONFIG_SYSPROF_TRACER is not set
# CONFIG_SCHED_TRACER is not set
# CONFIG_CONTEXT_SWITCH_TRACER is not set
# CONFIG_EVENT_TRACER is not set
# CONFIG_FTRACE_SYSCALLS is not set
# CONFIG_BOOT_TRACER is not set
# CONFIG_TRACE_BRANCH_PROFILING is not set
# CONFIG_POWER_TRACER is not set
# CONFIG_STACK_TRACER is not set
# CONFIG_HW_BRANCH_TRACER is not set
# CONFIG_KMEMTRACE is not set
# CONFIG_WORKQUEUE_TRACER is not set
CONFIG_BLK_DEV_IO_TRACE=y
# CONFIG_FTRACE_STARTUP_TEST is not set
# CONFIG_MMIOTRACE is not set
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
# CONFIG_DYNAMIC_DEBUG is not set
# CONFIG_DMA_API_DEBUG is not set
# CONFIG_SAMPLES is not set
CONFIG_HAVE_ARCH_KGDB=y
# CONFIG_KGDB is not set
@ -2321,7 +2392,6 @@ CONFIG_EARLY_PRINTK=y
CONFIG_EARLY_PRINTK_DBGP=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_DEBUG_STACK_USAGE=y
# CONFIG_DEBUG_PAGEALLOC is not set
# CONFIG_DEBUG_PER_CPU_MAPS is not set
# CONFIG_X86_PTDUMP is not set
CONFIG_DEBUG_RODATA=y
@ -2329,7 +2399,7 @@ CONFIG_DEBUG_RODATA=y
CONFIG_DEBUG_NX_TEST=m
# CONFIG_4KSTACKS is not set
CONFIG_DOUBLEFAULT=y
# CONFIG_MMIOTRACE is not set
CONFIG_HAVE_MMIOTRACE_SUPPORT=y
CONFIG_IO_DELAY_TYPE_0X80=0
CONFIG_IO_DELAY_TYPE_0XED=1
CONFIG_IO_DELAY_TYPE_UDELAY=2
@ -2365,6 +2435,8 @@ CONFIG_SECURITY_SELINUX_AVC_STATS=y
CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
# CONFIG_SECURITY_SMACK is not set
# CONFIG_SECURITY_TOMOYO is not set
# CONFIG_IMA is not set
CONFIG_CRYPTO=y
#
@ -2380,10 +2452,12 @@ CONFIG_CRYPTO_BLKCIPHER2=y
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_HASH2=y
CONFIG_CRYPTO_RNG2=y
CONFIG_CRYPTO_PCOMP=y
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_MANAGER2=y
# CONFIG_CRYPTO_GF128MUL is not set
# CONFIG_CRYPTO_NULL is not set
CONFIG_CRYPTO_WORKQUEUE=y
# CONFIG_CRYPTO_CRYPTD is not set
CONFIG_CRYPTO_AUTHENC=y
# CONFIG_CRYPTO_TEST is not set
@ -2456,6 +2530,7 @@ CONFIG_CRYPTO_DES=y
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
# CONFIG_CRYPTO_ZLIB is not set
# CONFIG_CRYPTO_LZO is not set
#
@ -2467,11 +2542,13 @@ CONFIG_CRYPTO_HW=y
# CONFIG_CRYPTO_DEV_GEODE is not set
# CONFIG_CRYPTO_DEV_HIFN_795X is not set
CONFIG_HAVE_KVM=y
CONFIG_HAVE_KVM_IRQCHIP=y
CONFIG_VIRTUALIZATION=y
# CONFIG_KVM is not set
# CONFIG_LGUEST is not set
# CONFIG_VIRTIO_PCI is not set
# CONFIG_VIRTIO_BALLOON is not set
CONFIG_BINARY_PRINTF=y
#
# Library routines
@ -2489,7 +2566,10 @@ CONFIG_CRC32=y
# CONFIG_LIBCRC32C is not set
CONFIG_AUDIT_GENERIC=y
CONFIG_ZLIB_INFLATE=y
CONFIG_PLIST=y
CONFIG_DECOMPRESS_GZIP=y
CONFIG_DECOMPRESS_BZIP2=y
CONFIG_DECOMPRESS_LZMA=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT=y
CONFIG_HAS_DMA=y
CONFIG_NLATTR=y

151
arch/x86/configs/x86_64_defconfig
View File

@ -1,12 +1,13 @@
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.29-rc4
# Tue Feb 24 15:44:16 2009
# Linux kernel version: 2.6.30-rc2
# Mon May 11 16:22:00 2009
#
CONFIG_64BIT=y
# CONFIG_X86_32 is not set
CONFIG_X86_64=y
CONFIG_X86=y
CONFIG_OUTPUT_FORMAT="elf64-x86-64"
CONFIG_ARCH_DEFCONFIG="arch/x86/configs/x86_64_defconfig"
CONFIG_GENERIC_TIME=y
CONFIG_GENERIC_CMOS_UPDATE=y
@ -34,6 +35,7 @@ CONFIG_ARCH_HAS_CPU_RELAX=y
CONFIG_ARCH_HAS_DEFAULT_IDLE=y
CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
CONFIG_HAVE_SETUP_PER_CPU_AREA=y
CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
CONFIG_HAVE_CPUMASK_OF_CPU_MAP=y
CONFIG_ARCH_HIBERNATION_POSSIBLE=y
CONFIG_ARCH_SUSPEND_POSSIBLE=y
@ -41,14 +43,14 @@ CONFIG_ZONE_DMA32=y
CONFIG_ARCH_POPULATES_NODE_MAP=y
CONFIG_AUDIT_ARCH=y
CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_PENDING_IRQ=y
CONFIG_X86_SMP=y
CONFIG_USE_GENERIC_SMP_HELPERS=y
CONFIG_X86_64_SMP=y
CONFIG_X86_HT=y
CONFIG_X86_BIOS_REBOOT=y
CONFIG_X86_TRAMPOLINE=y
# CONFIG_KTIME_SCALAR is not set
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
@ -61,10 +63,17 @@ CONFIG_LOCK_KERNEL=y
CONFIG_INIT_ENV_ARG_LIMIT=32
CONFIG_LOCALVERSION=""
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_KERNEL_GZIP=y
# CONFIG_KERNEL_BZIP2 is not set
# CONFIG_KERNEL_LZMA is not set
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSVIPC_SYSCTL=y
CONFIG_POSIX_MQUEUE=y
CONFIG_POSIX_MQUEUE_SYSCTL=y
CONFIG_BSD_PROCESS_ACCT=y
# CONFIG_BSD_PROCESS_ACCT_V3 is not set
CONFIG_TASKSTATS=y
@ -114,23 +123,26 @@ CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_RD_GZIP=y
CONFIG_RD_BZIP2=y
CONFIG_RD_LZMA=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_SYSCTL=y
CONFIG_ANON_INODES=y
# CONFIG_EMBEDDED is not set
CONFIG_UID16=y
CONFIG_SYSCTL_SYSCALL=y
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
CONFIG_KALLSYMS_EXTRA_PASS=y
# CONFIG_STRIP_ASM_SYMS is not set
CONFIG_HOTPLUG=y
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_PCSPKR_PLATFORM=y
# CONFIG_COMPAT_BRK is not set
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_ANON_INODES=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
CONFIG_TIMERFD=y
@ -140,6 +152,7 @@ CONFIG_AIO=y
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_PCI_QUIRKS=y
CONFIG_SLUB_DEBUG=y
# CONFIG_COMPAT_BRK is not set
# CONFIG_SLAB is not set
CONFIG_SLUB=y
# CONFIG_SLOB is not set
@ -155,6 +168,8 @@ CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_API_DEBUG=y
# CONFIG_SLOW_WORK is not set
# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
CONFIG_SLABINFO=y
CONFIG_RT_MUTEXES=y
@ -167,7 +182,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_STOP_MACHINE=y
CONFIG_BLOCK=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_BLK_DEV_BSG=y
# CONFIG_BLK_DEV_INTEGRITY is not set
CONFIG_BLOCK_COMPAT=y
@ -195,12 +209,10 @@ CONFIG_HIGH_RES_TIMERS=y
CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
CONFIG_SMP=y
CONFIG_SPARSE_IRQ=y
# CONFIG_NUMA_MIGRATE_IRQ_DESC is not set
CONFIG_X86_FIND_SMP_CONFIG=y
CONFIG_X86_MPPARSE=y
# CONFIG_X86_ELAN is not set
# CONFIG_X86_GENERICARCH is not set
CONFIG_X86_EXTENDED_PLATFORM=y
# CONFIG_X86_VSMP is not set
# CONFIG_X86_UV is not set
CONFIG_SCHED_OMIT_FRAME_POINTER=y
# CONFIG_PARAVIRT_GUEST is not set
# CONFIG_MEMTEST is not set
@ -230,10 +242,10 @@ CONFIG_SCHED_OMIT_FRAME_POINTER=y
# CONFIG_MCORE2 is not set
CONFIG_GENERIC_CPU=y
CONFIG_X86_CPU=y
CONFIG_X86_L1_CACHE_BYTES=128
CONFIG_X86_INTERNODE_CACHE_BYTES=128
CONFIG_X86_L1_CACHE_BYTES=64
CONFIG_X86_INTERNODE_CACHE_BYTES=64
CONFIG_X86_CMPXCHG=y
CONFIG_X86_L1_CACHE_SHIFT=7
CONFIG_X86_L1_CACHE_SHIFT=6
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_TSC=y
CONFIG_X86_CMPXCHG64=y
@ -242,7 +254,7 @@ CONFIG_X86_MINIMUM_CPU_FAMILY=64
CONFIG_X86_DEBUGCTLMSR=y
CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_AMD=y
CONFIG_CPU_SUP_CENTAUR_64=y
CONFIG_CPU_SUP_CENTAUR=y
CONFIG_X86_DS=y
CONFIG_X86_PTRACE_BTS=y
CONFIG_HPET_TIMER=y
@ -269,6 +281,7 @@ CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
CONFIG_X86_MCE=y
CONFIG_X86_MCE_INTEL=y
CONFIG_X86_MCE_AMD=y
CONFIG_X86_MCE_THRESHOLD=y
# CONFIG_I8K is not set
CONFIG_MICROCODE=y
CONFIG_MICROCODE_INTEL=y
@ -276,6 +289,7 @@ CONFIG_MICROCODE_AMD=y
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=y
CONFIG_X86_CPUID=y
# CONFIG_X86_CPU_DEBUG is not set
CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
CONFIG_DIRECT_GBPAGES=y
CONFIG_NUMA=y
@ -309,6 +323,8 @@ CONFIG_ZONE_DMA_FLAG=1
CONFIG_BOUNCE=y
CONFIG_VIRT_TO_BUS=y
CONFIG_UNEVICTABLE_LRU=y
CONFIG_HAVE_MLOCK=y
CONFIG_HAVE_MLOCKED_PAGE_BIT=y
CONFIG_X86_CHECK_BIOS_CORRUPTION=y
CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
CONFIG_X86_RESERVE_LOW_64K=y
@ -317,6 +333,7 @@ CONFIG_MTRR=y
CONFIG_X86_PAT=y
CONFIG_EFI=y
CONFIG_SECCOMP=y
# CONFIG_CC_STACKPROTECTOR is not set
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
@ -325,9 +342,10 @@ CONFIG_HZ=1000
CONFIG_SCHED_HRTICK=y
CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
# CONFIG_KEXEC_JUMP is not set
CONFIG_PHYSICAL_START=0x1000000
# CONFIG_RELOCATABLE is not set
CONFIG_PHYSICAL_ALIGN=0x200000
CONFIG_RELOCATABLE=y
CONFIG_PHYSICAL_ALIGN=0x1000000
CONFIG_HOTPLUG_CPU=y
# CONFIG_COMPAT_VDSO is not set
# CONFIG_CMDLINE_BOOL is not set
@ -370,7 +388,6 @@ CONFIG_ACPI_NUMA=y
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
# CONFIG_ACPI_PCI_SLOT is not set
CONFIG_ACPI_SYSTEM=y
CONFIG_X86_PM_TIMER=y
CONFIG_ACPI_CONTAINER=y
# CONFIG_ACPI_SBS is not set
@ -436,6 +453,7 @@ CONFIG_PCI_MSI=y
# CONFIG_PCI_DEBUG is not set
# CONFIG_PCI_STUB is not set
CONFIG_HT_IRQ=y
# CONFIG_PCI_IOV is not set
CONFIG_ISA_DMA_API=y
CONFIG_K8_NB=y
CONFIG_PCCARD=y
@ -481,7 +499,6 @@ CONFIG_NET=y
#
# Networking options
#
CONFIG_COMPAT_NET_DEV_OPS=y
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
@ -639,6 +656,7 @@ CONFIG_LLC=y
# CONFIG_LAPB is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set
# CONFIG_PHONET is not set
CONFIG_NET_SCHED=y
#
@ -696,6 +714,7 @@ CONFIG_NET_SCH_FIFO=y
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_NET_TCPPROBE is not set
# CONFIG_NET_DROP_MONITOR is not set
CONFIG_HAMRADIO=y
#
@ -706,12 +725,10 @@ CONFIG_HAMRADIO=y
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_AF_RXRPC is not set
# CONFIG_PHONET is not set
CONFIG_FIB_RULES=y
CONFIG_WIRELESS=y
CONFIG_CFG80211=y
# CONFIG_CFG80211_REG_DEBUG is not set
CONFIG_NL80211=y
CONFIG_WIRELESS_OLD_REGULATORY=y
CONFIG_WIRELESS_EXT=y
CONFIG_WIRELESS_EXT_SYSFS=y
@ -788,9 +805,8 @@ CONFIG_MISC_DEVICES=y
# CONFIG_TIFM_CORE is not set
# CONFIG_ICS932S401 is not set
# CONFIG_ENCLOSURE_SERVICES is not set
# CONFIG_SGI_XP is not set
# CONFIG_HP_ILO is not set
# CONFIG_SGI_GRU is not set
# CONFIG_ISL29003 is not set
# CONFIG_C2PORT is not set
#
@ -844,6 +860,7 @@ CONFIG_SCSI_SPI_ATTRS=y
# CONFIG_SCSI_LOWLEVEL is not set
# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
# CONFIG_SCSI_DH is not set
# CONFIG_SCSI_OSD_INITIATOR is not set
CONFIG_ATA=y
# CONFIG_ATA_NONSTANDARD is not set
CONFIG_ATA_ACPI=y
@ -940,6 +957,7 @@ CONFIG_DM_ZERO=y
CONFIG_MACINTOSH_DRIVERS=y
CONFIG_MAC_EMUMOUSEBTN=y
CONFIG_NETDEVICES=y
CONFIG_COMPAT_NET_DEV_OPS=y
# CONFIG_IFB is not set
# CONFIG_DUMMY is not set
# CONFIG_BONDING is not set
@ -977,6 +995,8 @@ CONFIG_MII=y
CONFIG_NET_VENDOR_3COM=y
# CONFIG_VORTEX is not set
# CONFIG_TYPHOON is not set
# CONFIG_ETHOC is not set
# CONFIG_DNET is not set
CONFIG_NET_TULIP=y
# CONFIG_DE2104X is not set
# CONFIG_TULIP is not set
@ -1026,6 +1046,7 @@ CONFIG_E1000=y
# CONFIG_E1000E is not set
# CONFIG_IP1000 is not set
# CONFIG_IGB is not set
# CONFIG_IGBVF is not set
# CONFIG_NS83820 is not set
# CONFIG_HAMACHI is not set
# CONFIG_YELLOWFIN is not set
@ -1040,6 +1061,7 @@ CONFIG_TIGON3=y
# CONFIG_QLA3XXX is not set
# CONFIG_ATL1 is not set
# CONFIG_ATL1E is not set
# CONFIG_ATL1C is not set
# CONFIG_JME is not set
CONFIG_NETDEV_10000=y
# CONFIG_CHELSIO_T1 is not set
@ -1049,6 +1071,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
# CONFIG_IXGBE is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set
# CONFIG_VXGE is not set
# CONFIG_MYRI10GE is not set
# CONFIG_NETXEN_NIC is not set
# CONFIG_NIU is not set
@ -1058,6 +1081,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
# CONFIG_BNX2X is not set
# CONFIG_QLGE is not set
# CONFIG_SFC is not set
# CONFIG_BE2NET is not set
CONFIG_TR=y
# CONFIG_IBMOL is not set
# CONFIG_3C359 is not set
@ -1072,8 +1096,8 @@ CONFIG_WLAN_80211=y
# CONFIG_LIBERTAS is not set
# CONFIG_LIBERTAS_THINFIRM is not set
# CONFIG_AIRO is not set
# CONFIG_HERMES is not set
# CONFIG_ATMEL is not set
# CONFIG_AT76C50X_USB is not set
# CONFIG_AIRO_CS is not set
# CONFIG_PCMCIA_WL3501 is not set
# CONFIG_PRISM54 is not set
@ -1083,21 +1107,21 @@ CONFIG_WLAN_80211=y
# CONFIG_RTL8187 is not set
# CONFIG_ADM8211 is not set
# CONFIG_MAC80211_HWSIM is not set
# CONFIG_MWL8K is not set
# CONFIG_P54_COMMON is not set
CONFIG_ATH5K=y
# CONFIG_ATH5K_DEBUG is not set
# CONFIG_ATH9K is not set
# CONFIG_AR9170_USB is not set
# CONFIG_IPW2100 is not set
# CONFIG_IPW2200 is not set
# CONFIG_IWLCORE is not set
# CONFIG_IWLWIFI_LEDS is not set
# CONFIG_IWLAGN is not set
# CONFIG_IWL3945 is not set
# CONFIG_IWLWIFI is not set
# CONFIG_HOSTAP is not set
# CONFIG_B43 is not set
# CONFIG_B43LEGACY is not set
# CONFIG_ZD1211RW is not set
# CONFIG_RT2X00 is not set
# CONFIG_HERMES is not set
#
# Enable WiMAX (Networking options) to see the WiMAX drivers
@ -1208,6 +1232,8 @@ CONFIG_INPUT_TABLET=y
# CONFIG_TABLET_USB_KBTAB is not set
# CONFIG_TABLET_USB_WACOM is not set
CONFIG_INPUT_TOUCHSCREEN=y
# CONFIG_TOUCHSCREEN_AD7879_I2C is not set
# CONFIG_TOUCHSCREEN_AD7879 is not set
# CONFIG_TOUCHSCREEN_FUJITSU is not set
# CONFIG_TOUCHSCREEN_GUNZE is not set
# CONFIG_TOUCHSCREEN_ELO is not set
@ -1301,6 +1327,7 @@ CONFIG_UNIX98_PTYS=y
# CONFIG_LEGACY_PTYS is not set
# CONFIG_IPMI_HANDLER is not set
CONFIG_HW_RANDOM=y
# CONFIG_HW_RANDOM_TIMERIOMEM is not set
# CONFIG_HW_RANDOM_INTEL is not set
# CONFIG_HW_RANDOM_AMD is not set
CONFIG_NVRAM=y
@ -1382,7 +1409,6 @@ CONFIG_I2C_I801=y
# CONFIG_SENSORS_PCF8574 is not set
# CONFIG_PCF8575 is not set
# CONFIG_SENSORS_PCA9539 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_MAX6875 is not set
# CONFIG_SENSORS_TSL2550 is not set
# CONFIG_I2C_DEBUG_CORE is not set
@ -1416,6 +1442,7 @@ CONFIG_HWMON=y
# CONFIG_SENSORS_ADT7475 is not set
# CONFIG_SENSORS_K8TEMP is not set
# CONFIG_SENSORS_ASB100 is not set
# CONFIG_SENSORS_ATK0110 is not set
# CONFIG_SENSORS_ATXP1 is not set
# CONFIG_SENSORS_DS1621 is not set
# CONFIG_SENSORS_I5K_AMB is not set
@ -1425,6 +1452,7 @@ CONFIG_HWMON=y
# CONFIG_SENSORS_FSCHER is not set
# CONFIG_SENSORS_FSCPOS is not set
# CONFIG_SENSORS_FSCHMD is not set
# CONFIG_SENSORS_G760A is not set
# CONFIG_SENSORS_GL518SM is not set
# CONFIG_SENSORS_GL520SM is not set
# CONFIG_SENSORS_CORETEMP is not set
@ -1440,11 +1468,14 @@ CONFIG_HWMON=y
# CONFIG_SENSORS_LM90 is not set
# CONFIG_SENSORS_LM92 is not set
# CONFIG_SENSORS_LM93 is not set
# CONFIG_SENSORS_LTC4215 is not set
# CONFIG_SENSORS_LTC4245 is not set
# CONFIG_SENSORS_LM95241 is not set
# CONFIG_SENSORS_MAX1619 is not set
# CONFIG_SENSORS_MAX6650 is not set
# CONFIG_SENSORS_PC87360 is not set
# CONFIG_SENSORS_PC87427 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_SIS5595 is not set
# CONFIG_SENSORS_DME1737 is not set
# CONFIG_SENSORS_SMSC47M1 is not set
@ -1635,6 +1666,7 @@ CONFIG_FB_EFI=y
# CONFIG_FB_VIRTUAL is not set
# CONFIG_FB_METRONOME is not set
# CONFIG_FB_MB862XX is not set
# CONFIG_FB_BROADSHEET is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
# CONFIG_LCD_CLASS_DEVICE is not set
CONFIG_BACKLIGHT_CLASS_DEVICE=y
@ -1720,6 +1752,8 @@ CONFIG_SND_PCI=y
# CONFIG_SND_INDIGO is not set
# CONFIG_SND_INDIGOIO is not set
# CONFIG_SND_INDIGODJ is not set
# CONFIG_SND_INDIGOIOX is not set
# CONFIG_SND_INDIGODJX is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_ENS1370 is not set
@ -1792,15 +1826,17 @@ CONFIG_USB_HIDDEV=y
#
# Special HID drivers
#
CONFIG_HID_COMPAT=y
CONFIG_HID_A4TECH=y
CONFIG_HID_APPLE=y
CONFIG_HID_BELKIN=y
CONFIG_HID_CHERRY=y
CONFIG_HID_CHICONY=y
CONFIG_HID_CYPRESS=y
# CONFIG_DRAGONRISE_FF is not set
CONFIG_HID_EZKEY=y
CONFIG_HID_KYE=y
CONFIG_HID_GYRATION=y
CONFIG_HID_KENSINGTON=y
CONFIG_HID_LOGITECH=y
CONFIG_LOGITECH_FF=y
# CONFIG_LOGIRUMBLEPAD2_FF is not set
@ -1866,11 +1902,11 @@ CONFIG_USB_PRINTER=y
# CONFIG_USB_TMC is not set
#
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
#
#
# see USB_STORAGE Help for more information
# also be needed; see USB_STORAGE Help for more info
#
CONFIG_USB_STORAGE=y
# CONFIG_USB_STORAGE_DEBUG is not set
@ -1912,7 +1948,6 @@ CONFIG_USB_LIBUSUAL=y
# CONFIG_USB_LED is not set
# CONFIG_USB_CYPRESS_CY7C63 is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_PHIDGET is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_FTDI_ELAN is not set
# CONFIG_USB_APPLEDISPLAY is not set
@ -1928,6 +1963,7 @@ CONFIG_USB_LIBUSUAL=y
#
# OTG and related infrastructure
#
# CONFIG_NOP_USB_XCEIV is not set
# CONFIG_UWB is not set
# CONFIG_MMC is not set
# CONFIG_MEMSTICK is not set
@ -1939,8 +1975,10 @@ CONFIG_LEDS_CLASS=y
#
# CONFIG_LEDS_ALIX2 is not set
# CONFIG_LEDS_PCA9532 is not set
# CONFIG_LEDS_LP5521 is not set
# CONFIG_LEDS_CLEVO_MAIL is not set
# CONFIG_LEDS_PCA955X is not set
# CONFIG_LEDS_BD2802 is not set
#
# LED Triggers
@ -1950,6 +1988,10 @@ CONFIG_LEDS_TRIGGERS=y
# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
# CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
#
# iptables trigger is under Netfilter config (LED target)
#
# CONFIG_ACCESSIBILITY is not set
# CONFIG_INFINIBAND is not set
CONFIG_EDAC=y
@ -2018,6 +2060,7 @@ CONFIG_DMADEVICES=y
# DMA Devices
#
# CONFIG_INTEL_IOATDMA is not set
# CONFIG_AUXDISPLAY is not set
# CONFIG_UIO is not set
# CONFIG_STAGING is not set
CONFIG_X86_PLATFORM_DEVICES=y
@ -2051,6 +2094,7 @@ CONFIG_DMIID=y
#
# CONFIG_EXT2_FS is not set
CONFIG_EXT3_FS=y
# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
CONFIG_EXT3_FS_XATTR=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
@ -2081,6 +2125,11 @@ CONFIG_AUTOFS4_FS=y
# CONFIG_FUSE_FS is not set
CONFIG_GENERIC_ACL=y
#
# Caches
#
# CONFIG_FSCACHE is not set
#
# CD-ROM/DVD Filesystems
#
@ -2132,6 +2181,7 @@ CONFIG_MISC_FILESYSTEMS=y
# CONFIG_ROMFS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set
# CONFIG_NILFS2_FS is not set
CONFIG_NETWORK_FILESYSTEMS=y
CONFIG_NFS_FS=y
CONFIG_NFS_V3=y
@ -2145,7 +2195,6 @@ CONFIG_NFS_ACL_SUPPORT=y
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=y
CONFIG_SUNRPC_GSS=y
# CONFIG_SUNRPC_REGISTER_V4 is not set
CONFIG_RPCSEC_GSS_KRB5=y
# CONFIG_RPCSEC_GSS_SPKM3 is not set
# CONFIG_SMB_FS is not set
@ -2232,6 +2281,7 @@ CONFIG_DEBUG_FS=y
CONFIG_DEBUG_KERNEL=y
# CONFIG_DEBUG_SHIRQ is not set
# CONFIG_DETECT_SOFTLOCKUP is not set
# CONFIG_DETECT_HUNG_TASK is not set
# CONFIG_SCHED_DEBUG is not set
CONFIG_SCHEDSTATS=y
CONFIG_TIMER_STATS=y
@ -2247,6 +2297,7 @@ CONFIG_TIMER_STATS=y
# CONFIG_LOCK_STAT is not set
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
CONFIG_STACKTRACE=y
# CONFIG_DEBUG_KOBJECT is not set
CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_INFO is not set
@ -2269,13 +2320,19 @@ CONFIG_FRAME_POINTER=y
# CONFIG_FAULT_INJECTION is not set
# CONFIG_LATENCYTOP is not set
CONFIG_SYSCTL_SYSCALL_CHECK=y
# CONFIG_DEBUG_PAGEALLOC is not set
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_NOP_TRACER=y
CONFIG_HAVE_FUNCTION_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
CONFIG_HAVE_DYNAMIC_FTRACE=y
CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
CONFIG_HAVE_HW_BRANCH_TRACER=y
CONFIG_HAVE_FTRACE_SYSCALLS=y
CONFIG_RING_BUFFER=y
CONFIG_TRACING=y
CONFIG_TRACING_SUPPORT=y
#
# Tracers
@ -2285,13 +2342,21 @@ CONFIG_HAVE_HW_BRANCH_TRACER=y
# CONFIG_SYSPROF_TRACER is not set
# CONFIG_SCHED_TRACER is not set
# CONFIG_CONTEXT_SWITCH_TRACER is not set
# CONFIG_EVENT_TRACER is not set
# CONFIG_FTRACE_SYSCALLS is not set
# CONFIG_BOOT_TRACER is not set
# CONFIG_TRACE_BRANCH_PROFILING is not set
# CONFIG_POWER_TRACER is not set
# CONFIG_STACK_TRACER is not set
# CONFIG_HW_BRANCH_TRACER is not set
# CONFIG_KMEMTRACE is not set
# CONFIG_WORKQUEUE_TRACER is not set
CONFIG_BLK_DEV_IO_TRACE=y
# CONFIG_FTRACE_STARTUP_TEST is not set
# CONFIG_MMIOTRACE is not set
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
# CONFIG_DYNAMIC_DEBUG is not set
# CONFIG_DMA_API_DEBUG is not set
# CONFIG_SAMPLES is not set
CONFIG_HAVE_ARCH_KGDB=y
# CONFIG_KGDB is not set
@ -2301,14 +2366,13 @@ CONFIG_EARLY_PRINTK=y
CONFIG_EARLY_PRINTK_DBGP=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_DEBUG_STACK_USAGE=y
# CONFIG_DEBUG_PAGEALLOC is not set
# CONFIG_DEBUG_PER_CPU_MAPS is not set
# CONFIG_X86_PTDUMP is not set
CONFIG_DEBUG_RODATA=y
# CONFIG_DEBUG_RODATA_TEST is not set
CONFIG_DEBUG_NX_TEST=m
# CONFIG_IOMMU_DEBUG is not set
# CONFIG_MMIOTRACE is not set
CONFIG_HAVE_MMIOTRACE_SUPPORT=y
CONFIG_IO_DELAY_TYPE_0X80=0
CONFIG_IO_DELAY_TYPE_0XED=1
CONFIG_IO_DELAY_TYPE_UDELAY=2
@ -2344,6 +2408,8 @@ CONFIG_SECURITY_SELINUX_AVC_STATS=y
CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
# CONFIG_SECURITY_SMACK is not set
# CONFIG_SECURITY_TOMOYO is not set
# CONFIG_IMA is not set
CONFIG_CRYPTO=y
#
@ -2359,10 +2425,12 @@ CONFIG_CRYPTO_BLKCIPHER2=y
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_HASH2=y
CONFIG_CRYPTO_RNG2=y
CONFIG_CRYPTO_PCOMP=y
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_MANAGER2=y
# CONFIG_CRYPTO_GF128MUL is not set
# CONFIG_CRYPTO_NULL is not set
CONFIG_CRYPTO_WORKQUEUE=y
# CONFIG_CRYPTO_CRYPTD is not set
CONFIG_CRYPTO_AUTHENC=y
# CONFIG_CRYPTO_TEST is not set
@ -2414,6 +2482,7 @@ CONFIG_CRYPTO_SHA1=y
#
CONFIG_CRYPTO_AES=y
# CONFIG_CRYPTO_AES_X86_64 is not set
# CONFIG_CRYPTO_AES_NI_INTEL is not set
# CONFIG_CRYPTO_ANUBIS is not set
CONFIG_CRYPTO_ARC4=y
# CONFIG_CRYPTO_BLOWFISH is not set
@ -2435,6 +2504,7 @@ CONFIG_CRYPTO_DES=y
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
# CONFIG_CRYPTO_ZLIB is not set
# CONFIG_CRYPTO_LZO is not set
#
@ -2444,10 +2514,12 @@ CONFIG_CRYPTO_DES=y
CONFIG_CRYPTO_HW=y
# CONFIG_CRYPTO_DEV_HIFN_795X is not set
CONFIG_HAVE_KVM=y
CONFIG_HAVE_KVM_IRQCHIP=y
CONFIG_VIRTUALIZATION=y
# CONFIG_KVM is not set
# CONFIG_VIRTIO_PCI is not set
# CONFIG_VIRTIO_BALLOON is not set
CONFIG_BINARY_PRINTF=y
#
# Library routines
@ -2464,7 +2536,10 @@ CONFIG_CRC32=y
# CONFIG_CRC7 is not set
# CONFIG_LIBCRC32C is not set
CONFIG_ZLIB_INFLATE=y
CONFIG_PLIST=y
CONFIG_DECOMPRESS_GZIP=y
CONFIG_DECOMPRESS_BZIP2=y
CONFIG_DECOMPRESS_LZMA=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT=y
CONFIG_HAS_DMA=y
CONFIG_NLATTR=y

4
arch/x86/ia32/ia32entry.S
View File

@ -825,9 +825,11 @@ ia32_sys_call_table:
.quad compat_sys_signalfd4
.quad sys_eventfd2
.quad sys_epoll_create1
.quad sys_dup3 /* 330 */
.quad sys_dup3 /* 330 */
.quad sys_pipe2
.quad sys_inotify_init1
.quad compat_sys_preadv
.quad compat_sys_pwritev
.quad compat_sys_rt_tgsigqueueinfo /* 335 */
.quad sys_perf_counter_open
ia32_syscall_end:

59
arch/x86/include/asm/alternative.h
View File

@ -3,6 +3,7 @@
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/stringify.h>
#include <asm/asm.h>
/*
@ -74,6 +75,22 @@ static inline void alternatives_smp_switch(int smp) {}
const unsigned char *const *find_nop_table(void);
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
\
"661:\n\t" oldinstr "\n662:\n" \
".section .altinstructions,\"a\"\n" \
_ASM_ALIGN "\n" \
_ASM_PTR "661b\n" /* label */ \
_ASM_PTR "663f\n" /* new instruction */ \
" .byte " __stringify(feature) "\n" /* feature bit */ \
" .byte 662b-661b\n" /* sourcelen */ \
" .byte 664f-663f\n" /* replacementlen */ \
".previous\n" \
".section .altinstr_replacement, \"ax\"\n" \
"663:\n\t" newinstr "\n664:\n" /* replacement */ \
".previous"
/*
* Alternative instructions for different CPU types or capabilities.
*
@ -87,18 +104,7 @@ const unsigned char *const *find_nop_table(void);
* without volatile and memory clobber.
*/
#define alternative(oldinstr, newinstr, feature) \
asm volatile ("661:\n\t" oldinstr "\n662:\n" \
".section .altinstructions,\"a\"\n" \
_ASM_ALIGN "\n" \
_ASM_PTR "661b\n" /* label */ \
_ASM_PTR "663f\n" /* new instruction */ \
" .byte %c0\n" /* feature bit */ \
" .byte 662b-661b\n" /* sourcelen */ \
" .byte 664f-663f\n" /* replacementlen */ \
".previous\n" \
".section .altinstr_replacement,\"ax\"\n" \
"663:\n\t" newinstr "\n664:\n" /* replacement */ \
".previous" :: "i" (feature) : "memory")
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
/*
* Alternative inline assembly with input.
@ -109,35 +115,16 @@ const unsigned char *const *find_nop_table(void);
* Best is to use constraints that are fixed size (like (%1) ... "r")
* If you use variable sized constraints like "m" or "g" in the
* replacement make sure to pad to the worst case length.
* Leaving an unused argument 0 to keep API compatibility.
*/
#define alternative_input(oldinstr, newinstr, feature, input...) \
asm volatile ("661:\n\t" oldinstr "\n662:\n" \
".section .altinstructions,\"a\"\n" \
_ASM_ALIGN "\n" \
_ASM_PTR "661b\n" /* label */ \
_ASM_PTR "663f\n" /* new instruction */ \
" .byte %c0\n" /* feature bit */ \
" .byte 662b-661b\n" /* sourcelen */ \
" .byte 664f-663f\n" /* replacementlen */ \
".previous\n" \
".section .altinstr_replacement,\"ax\"\n" \
"663:\n\t" newinstr "\n664:\n" /* replacement */ \
".previous" :: "i" (feature), ##input)
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
: : "i" (0), ## input)
/* Like alternative_input, but with a single output argument */
#define alternative_io(oldinstr, newinstr, feature, output, input...) \
asm volatile ("661:\n\t" oldinstr "\n662:\n" \
".section .altinstructions,\"a\"\n" \
_ASM_ALIGN "\n" \
_ASM_PTR "661b\n" /* label */ \
_ASM_PTR "663f\n" /* new instruction */ \
" .byte %c[feat]\n" /* feature bit */ \
" .byte 662b-661b\n" /* sourcelen */ \
" .byte 664f-663f\n" /* replacementlen */ \
".previous\n" \
".section .altinstr_replacement,\"ax\"\n" \
"663:\n\t" newinstr "\n664:\n" /* replacement */ \
".previous" : output : [feat] "i" (feature), ##input)
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
: output : "i" (0), ## input)
/*
* use this macro(s) if you need more than one output parameter

2
arch/x86/include/asm/amd_iommu.h
View File

@ -27,6 +27,8 @@ extern int amd_iommu_init(void);
extern int amd_iommu_init_dma_ops(void);
extern void amd_iommu_detect(void);
extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
extern void amd_iommu_flush_all_domains(void);
extern void amd_iommu_flush_all_devices(void);
#else
static inline int amd_iommu_init(void) { return -ENODEV; }
static inline void amd_iommu_detect(void) { }

55
arch/x86/include/asm/amd_iommu_types.h
View File

@ -194,6 +194,27 @@
#define PD_DMA_OPS_MASK (1UL << 0) /* domain used for dma_ops */
#define PD_DEFAULT_MASK (1UL << 1) /* domain is a default dma_ops
domain for an IOMMU */
extern bool amd_iommu_dump;
#define DUMP_printk(format, arg...) \
do { \
if (amd_iommu_dump) \
printk(KERN_INFO "AMD IOMMU: " format, ## arg); \
} while(0);
/*
* Make iterating over all IOMMUs easier
*/
#define for_each_iommu(iommu) \
list_for_each_entry((iommu), &amd_iommu_list, list)
#define for_each_iommu_safe(iommu, next) \
list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
#define APERTURE_RANGE_SHIFT 27 /* 128 MB */
#define APERTURE_RANGE_SIZE (1ULL << APERTURE_RANGE_SHIFT)
#define APERTURE_RANGE_PAGES (APERTURE_RANGE_SIZE >> PAGE_SHIFT)
#define APERTURE_MAX_RANGES 32 /* allows 4GB of DMA address space */
#define APERTURE_RANGE_INDEX(a) ((a) >> APERTURE_RANGE_SHIFT)
#define APERTURE_PAGE_INDEX(a) (((a) >> 21) & 0x3fULL)
/*
* This structure contains generic data for IOMMU protection domains
@ -209,6 +230,26 @@ struct protection_domain {
void *priv; /* private data */
};
/*
* For dynamic growth the aperture size is split into ranges of 128MB of
* DMA address space each. This struct represents one such range.
*/
struct aperture_range {
/* address allocation bitmap */
unsigned long *bitmap;
/*
* Array of PTE pages for the aperture. In this array we save all the
* leaf pages of the domain page table used for the aperture. This way
* we don't need to walk the page table to find a specific PTE. We can
* just calculate its address in constant time.
*/
u64 *pte_pages[64];
unsigned long offset;
};
/*
* Data container for a dma_ops specific protection domain
*/
@ -222,18 +263,10 @@ struct dma_ops_domain {
unsigned long aperture_size;
/* address we start to search for free addresses */
unsigned long next_bit;
unsigned long next_address;
/* address allocation bitmap */
unsigned long *bitmap;
/*
* Array of PTE pages for the aperture. In this array we save all the
* leaf pages of the domain page table used for the aperture. This way
* we don't need to walk the page table to find a specific PTE. We can
* just calculate its address in constant time.
*/
u64 **pte_pages;
/* address space relevant data */
struct aperture_range *aperture[APERTURE_MAX_RANGES];
/* This will be set to true when TLB needs to be flushed */
bool need_flush;

33
arch/x86/include/asm/apic.h
View File

@ -107,8 +107,7 @@ extern u32 native_safe_apic_wait_icr_idle(void);
extern void native_apic_icr_write(u32 low, u32 id);
extern u64 native_apic_icr_read(void);
#define EIM_8BIT_APIC_ID 0
#define EIM_32BIT_APIC_ID 1
extern int x2apic_mode;
#ifdef CONFIG_X86_X2APIC
/*
@ -166,10 +165,9 @@ static inline u64 native_x2apic_icr_read(void)
return val;
}
extern int x2apic, x2apic_phys;
extern int x2apic_phys;
extern void check_x2apic(void);
extern void enable_x2apic(void);
extern void enable_IR_x2apic(void);
extern void x2apic_icr_write(u32 low, u32 id);
static inline int x2apic_enabled(void)
{
@ -183,6 +181,8 @@ static inline int x2apic_enabled(void)
return 1;
return 0;
}
#define x2apic_supported() (cpu_has_x2apic)
#else
static inline void check_x2apic(void)
{
@ -190,28 +190,20 @@ static inline void check_x2apic(void)
static inline void enable_x2apic(void)
{
}
static inline void enable_IR_x2apic(void)
{
}
static inline int x2apic_enabled(void)
{
return 0;
}
#define x2apic 0
#define x2apic_preenabled 0
#define x2apic_supported() 0
#endif
extern void enable_IR_x2apic(void);
extern int get_physical_broadcast(void);
#ifdef CONFIG_X86_X2APIC
static inline void ack_x2APIC_irq(void)
{
/* Docs say use 0 for future compatibility */
native_apic_msr_write(APIC_EOI, 0);
}
#endif
extern void apic_disable(void);
extern int lapic_get_maxlvt(void);
extern void clear_local_APIC(void);
extern void connect_bsp_APIC(void);
@ -252,7 +244,7 @@ static inline void lapic_shutdown(void) { }
#define local_apic_timer_c2_ok 1
static inline void init_apic_mappings(void) { }
static inline void disable_local_APIC(void) { }
static inline void apic_disable(void) { }
#endif /* !CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_64
@ -410,7 +402,7 @@ static inline unsigned default_get_apic_id(unsigned long x)
{
unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
if (APIC_XAPIC(ver))
if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
return (x >> 24) & 0xFF;
else
return (x >> 24) & 0x0F;
@ -478,6 +470,9 @@ static inline unsigned int read_apic_id(void)
extern void default_setup_apic_routing(void);
#ifdef CONFIG_X86_32
extern struct apic apic_default;
/*
* Set up the logical destination ID.
*

8
arch/x86/include/asm/apicdef.h
View File

@ -22,6 +22,7 @@
# define APIC_INTEGRATED(x) (1)
#endif
#define APIC_XAPIC(x) ((x) >= 0x14)
#define APIC_EXT_SPACE(x) ((x) & 0x80000000)
#define APIC_TASKPRI 0x80
#define APIC_TPRI_MASK 0xFFu
#define APIC_ARBPRI 0x90
@ -116,7 +117,9 @@
#define APIC_TDR_DIV_32 0x8
#define APIC_TDR_DIV_64 0x9
#define APIC_TDR_DIV_128 0xA
#define APIC_EILVT0 0x500
#define APIC_EFEAT 0x400
#define APIC_ECTRL 0x410
#define APIC_EILVTn(n) (0x500 + 0x10 * n)
#define APIC_EILVT_NR_AMD_K8 1 /* # of extended interrupts */
#define APIC_EILVT_NR_AMD_10H 4
#define APIC_EILVT_LVTOFF(x) (((x) >> 4) & 0xF)
@ -125,9 +128,6 @@
#define APIC_EILVT_MSG_NMI 0x4
#define APIC_EILVT_MSG_EXT 0x7
#define APIC_EILVT_MASKED (1 << 16)
#define APIC_EILVT1 0x510
#define APIC_EILVT2 0x520
#define APIC_EILVT3 0x530
#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
#define APIC_BASE_MSR 0x800

236
arch/x86/include/asm/atomic_32.h
View File

@ -247,5 +247,241 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
#define smp_mb__before_atomic_inc() barrier()
#define smp_mb__after_atomic_inc() barrier()
/* An 64bit atomic type */
typedef struct {
unsigned long long counter;
} atomic64_t;
#define ATOMIC64_INIT(val) { (val) }
/**
* atomic64_read - read atomic64 variable
* @v: pointer of type atomic64_t
*
* Atomically reads the value of @v.
* Doesn't imply a read memory barrier.
*/
#define __atomic64_read(ptr) ((ptr)->counter)
static inline unsigned long long
cmpxchg8b(unsigned long long *ptr, unsigned long long old, unsigned long long new)
{
asm volatile(
LOCK_PREFIX "cmpxchg8b (%[ptr])\n"
: "=A" (old)
: [ptr] "D" (ptr),
"A" (old),
"b" (ll_low(new)),
"c" (ll_high(new))
: "memory");
return old;
}
static inline unsigned long long
atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
unsigned long long new_val)
{
return cmpxchg8b(&ptr->counter, old_val, new_val);
}
/**
* atomic64_xchg - xchg atomic64 variable
* @ptr: pointer to type atomic64_t
* @new_val: value to assign
* @old_val: old value that was there
*
* Atomically xchgs the value of @ptr to @new_val and returns
* the old value.
*/
static inline unsigned long long
atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
{
unsigned long long old_val;
do {
old_val = atomic_read(ptr);
} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
return old_val;
}
/**
* atomic64_set - set atomic64 variable
* @ptr: pointer to type atomic64_t
* @new_val: value to assign
*
* Atomically sets the value of @ptr to @new_val.
*/
static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
{
atomic64_xchg(ptr, new_val);
}
/**
* atomic64_read - read atomic64 variable
* @ptr: pointer to type atomic64_t
*
* Atomically reads the value of @ptr and returns it.
*/
static inline unsigned long long atomic64_read(atomic64_t *ptr)
{
unsigned long long curr_val;
do {
curr_val = __atomic64_read(ptr);
} while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val);
return curr_val;
}
/**
* atomic64_add_return - add and return
* @delta: integer value to add
* @ptr: pointer to type atomic64_t
*
* Atomically adds @delta to @ptr and returns @delta + *@ptr
*/
static inline unsigned long long
atomic64_add_return(unsigned long long delta, atomic64_t *ptr)
{
unsigned long long old_val, new_val;
do {
old_val = atomic_read(ptr);
new_val = old_val + delta;
} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
return new_val;
}
static inline long atomic64_sub_return(unsigned long long delta, atomic64_t *ptr)
{
return atomic64_add_return(-delta, ptr);
}
static inline long atomic64_inc_return(atomic64_t *ptr)
{
return atomic64_add_return(1, ptr);
}
static inline long atomic64_dec_return(atomic64_t *ptr)
{
return atomic64_sub_return(1, ptr);
}
/**
* atomic64_add - add integer to atomic64 variable
* @delta: integer value to add
* @ptr: pointer to type atomic64_t
*
* Atomically adds @delta to @ptr.
*/
static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
{
atomic64_add_return(delta, ptr);
}
/**
* atomic64_sub - subtract the atomic64 variable
* @delta: integer value to subtract
* @ptr: pointer to type atomic64_t
*
* Atomically subtracts @delta from @ptr.
*/
static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
{
atomic64_add(-delta, ptr);
}
/**
* atomic64_sub_and_test - subtract value from variable and test result
* @delta: integer value to subtract
* @ptr: pointer to type atomic64_t
*
* Atomically subtracts @delta from @ptr and returns
* true if the result is zero, or false for all
* other cases.
*/
static inline int
atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
{
unsigned long long old_val = atomic64_sub_return(delta, ptr);
return old_val == 0;
}
/**
* atomic64_inc - increment atomic64 variable
* @ptr: pointer to type atomic64_t
*
* Atomically increments @ptr by 1.
*/
static inline void atomic64_inc(atomic64_t *ptr)
{
atomic64_add(1, ptr);
}
/**
* atomic64_dec - decrement atomic64 variable
* @ptr: pointer to type atomic64_t
*
* Atomically decrements @ptr by 1.
*/
static inline void atomic64_dec(atomic64_t *ptr)
{
atomic64_sub(1, ptr);
}
/**
* atomic64_dec_and_test - decrement and test
* @ptr: pointer to type atomic64_t
*
* Atomically decrements @ptr by 1 and
* returns true if the result is 0, or false for all other
* cases.
*/
static inline int atomic64_dec_and_test(atomic64_t *ptr)
{
return atomic64_sub_and_test(1, ptr);
}
/**
* atomic64_inc_and_test - increment and test
* @ptr: pointer to type atomic64_t
*
* Atomically increments @ptr by 1
* and returns true if the result is zero, or false for all
* other cases.
*/
static inline int atomic64_inc_and_test(atomic64_t *ptr)
{
return atomic64_sub_and_test(-1, ptr);
}
/**
* atomic64_add_negative - add and test if negative
* @delta: integer value to add
* @ptr: pointer to type atomic64_t
*
* Atomically adds @delta to @ptr and returns true
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
static inline int
atomic64_add_negative(unsigned long long delta, atomic64_t *ptr)
{
long long old_val = atomic64_add_return(delta, ptr);
return old_val < 0;
}
#include <asm-generic/atomic.h>
#endif /* _ASM_X86_ATOMIC_32_H */

15
arch/x86/include/asm/boot.h
View File

@ -8,11 +8,26 @@
#ifdef __KERNEL__
#include <asm/page_types.h>
/* Physical address where kernel should be loaded. */
#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
+ (CONFIG_PHYSICAL_ALIGN - 1)) \
& ~(CONFIG_PHYSICAL_ALIGN - 1))
/* Minimum kernel alignment, as a power of two */
#ifdef CONFIG_x86_64
#define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT
#else
#define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT+1)
#endif
#define MIN_KERNEL_ALIGN (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
#if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \
(CONFIG_PHYSICAL_ALIGN < (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2))
#error "Invalid value for CONFIG_PHYSICAL_ALIGN"
#endif
#ifdef CONFIG_KERNEL_BZIP2
#define BOOT_HEAP_SIZE 0x400000
#else /* !CONFIG_KERNEL_BZIP2 */

3
arch/x86/include/asm/bootparam.h
View File

@ -50,7 +50,8 @@ struct setup_header {
__u32 ramdisk_size;
__u32 bootsect_kludge;
__u16 heap_end_ptr;
__u16 _pad1;
__u8 ext_loader_ver;
__u8 ext_loader_type;
__u32 cmd_line_ptr;
__u32 initrd_addr_max;
__u32 kernel_alignment;

Some files were not shown because too many files have changed in this diff Show More