* 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
KVM: Prevent overflow in largepages calculation
KVM: Disable large pages on misaligned memory slots
KVM: Add VT-x machine check support
KVM: VMX: Rename rmode.active to rmode.vm86_active
KVM: Move "exit due to NMI" handling into vmx_complete_interrupts()
KVM: Disable CR8 intercept if tpr patching is active
KVM: Do not migrate pending software interrupts.
KVM: inject NMI after IRET from a previous NMI, not before.
KVM: Always request IRQ/NMI window if an interrupt is pending
KVM: Do not re-execute INTn instruction.
KVM: skip_emulated_instruction() decode instruction if size is not known
KVM: Remove irq_pending bitmap
KVM: Do not allow interrupt injection from userspace if there is a pending event.
KVM: Unprotect a page if #PF happens during NMI injection.
KVM: s390: Verify memory in kvm run
KVM: s390: Sanity check on validity intercept
KVM: s390: Unlink vcpu on destroy - v2
KVM: s390: optimize float int lock: spin_lock_bh --> spin_lock
KVM: s390: use hrtimer for clock wakeup from idle - v2
KVM: s390: Fix memory slot versus run - v3
...
--- /dev/null
+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
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
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):
--- /dev/null
+<?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>
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.
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
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:
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().
other than a letter or digit, are reserved for use by the Smack development
team. Smack labels are unstructured, case sensitive, and the only operation
ever performed on them is comparison for equality. Smack labels cannot
-contain unprintable characters or the "/" (slash) character. Smack labels
-cannot begin with a '-', which is reserved for special options.
+contain unprintable characters, the "/" (slash), the "\" (backslash), the "'"
+(quote) and '"' (double-quote) characters.
+Smack labels cannot begin with a '-', which is reserved for special options.
There are some predefined labels:
These mount options apply to all file system types.
+Smack auditing
+
+If you want Smack auditing of security events, you need to set CONFIG_AUDIT
+in your kernel configuration.
+By default, all denied events will be audited. You can change this behavior by
+writing a single character to the /smack/logging file :
+0 : no logging
+1 : log denied (default)
+2 : log accepted
+3 : log denied & accepted
+
+Events are logged as 'key=value' pairs, for each event you at least will get
+the subjet, the object, the rights requested, the action, the kernel function
+that triggered the event, plus other pairs depending on the type of event
+audited.
--- /dev/null
+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.
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.
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>
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]
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
Formt: { "sha1" | "md5" }
default: "sha1"
+ ima_tcb [IMA]
+ Load a policy which meets the needs of the Trusted
+ Computing Base. This means IMA will measure all
+ programs exec'd, files mmap'd for exec, and all files
+ opened for read by uid=0.
+
in2000= [HW,SCSI]
See header of drivers/scsi/in2000.c.
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)
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.
oprofile.timer= [HW]
Use timer interrupt instead of performance counters
+ oprofile.cpu_type= Force an oprofile cpu type
+ This might be useful if you have an older oprofile
+ userland or if you want common events.
+ Format: { archperfmon }
+ archperfmon: [X86] Force use of architectural
+ perfmon on Intel CPUs instead of the
+ CPU specific event set.
+
osst= [HW,SCSI] SCSI Tape Driver
Format: <buffer_size>,<write_threshold>
See also Documentation/scsi/st.txt.
- Locking functions.
- Interrupt disabling functions.
+ - Sleep and wake-up functions.
- Miscellaneous functions.
(*) Inter-CPU locking barrier effects.
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
-----------------------
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.
CONTENTS
========
+0. WARNING
1. Overview
1.1 The problem
1.2 The solution
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
===========
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).
- kstack_depth_to_print [ X86 only ]
- l2cr [ PPC only ]
- modprobe ==> Documentation/debugging-modules.txt
+- modules_disabled
- msgmax
- msgmnb
- msgmni
==============================================================
+modules_disabled:
+
+A toggle value indicating if modules are allowed to be loaded
+in an otherwise modular kernel. This toggle defaults to off
+(0), but can be set true (1). Once true, modules can be
+neither loaded nor unloaded, and the toggle cannot be set back
+to false.
+
+==============================================================
+
osrelease, ostype & version:
# cat osrelease
--- /dev/null
+ 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
+
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
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:
--- /dev/null
+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
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
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
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.
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:
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.
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
0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
Field name: kernel_alignment
-Type: read (reloc)
+Type: read/modify (reloc)
Offset/size: 0x230/4
-Protocol: 2.05+
+Protocol: 2.05+ (read), 2.10+ (modify)
+
+ Alignment unit required by the kernel (if relocatable_kernel is
+ true.) A relocatable kernel that is loaded at an alignment
+ incompatible with the value in this field will be realigned during
+ kernel initialization.
- Alignment unit required by the kernel (if relocatable_kernel is true.)
+ Starting with protocol version 2.10, this reflects the kernel
+ alignment preferred for optimal performance; it is possible for the
+ loader to modify this field to permit a lesser alignment. See the
+ min_alignment and pref_address field below.
Field name: relocatable_kernel
Type: read (reloc)
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
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
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
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
M: Mail patches to
L: Mailing list that is relevant to this area
W: Web-page with status/info
-T: SCM tree type and location. Type is one of: git, hg, quilt.
+T: SCM tree type and location. Type is one of: git, hg, quilt, stgit.
S: Status, one of the following:
Supported: Someone is actually paid to look after this.
8250/16?50 (AND CLONE UARTS) SERIAL DRIVER
L: linux-serial@vger.kernel.org
W: http://serial.sourceforge.net
-S: Orphan
+M: alan@lxorguk.ukuu.org.uk
+S: Odd Fixes
F: drivers/serial/8250*
F: include/linux/serial_8250.h
M: alan@lxorguk.ukuu.org.uk
L: linux-kernel@vger.kernel.org
S: Maintained
+T: stgit http://zeniv.linux.org.uk/~alan/ttydev/
TULIP NETWORK DRIVERS
P: Grant Grundler
}
}
-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 = {
}
-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
}
#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;
val |= 1 << (cpu + shift);
writel(val, reg);
spin_unlock(&irq_controller_lock);
+
+ return 0;
}
#endif
#define ASMARM_ARCH_UART_H
#define IMXUART_HAVE_RTSCTS (1<<0)
+#define IMXUART_IRDA (1<<1)
struct imxuart_platform_data {
int (*init)(struct platform_device *pdev);
int (*exit)(struct platform_device *pdev);
unsigned int flags;
+ void (*irda_enable)(int enable);
+ unsigned int irda_inv_rx:1;
+ unsigned int irda_inv_tx:1;
+ unsigned short transceiver_delay;
};
#endif
{
}
-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 = {
bool
default y
select HAVE_IDE
+ select HAVE_ARCH_TRACEHOOK
config ZONE_DMA
bool
#define atomic_clear_mask(mask, v) atomic_test_and_ANDNOT_mask((mask), (v))
#define atomic_set_mask(mask, v) atomic_test_and_OR_mask((mask), (v))
-static inline int test_and_clear_bit(int nr, volatile void *addr)
+static inline int test_and_clear_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *ptr = addr;
unsigned long mask = 1UL << (nr & 31);
return (atomic_test_and_ANDNOT_mask(mask, ptr) & mask) != 0;
}
-static inline int test_and_set_bit(int nr, volatile void *addr)
+static inline int test_and_set_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *ptr = addr;
unsigned long mask = 1UL << (nr & 31);
return (atomic_test_and_OR_mask(mask, ptr) & mask) != 0;
}
-static inline int test_and_change_bit(int nr, volatile void *addr)
+static inline int test_and_change_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *ptr = addr;
unsigned long mask = 1UL << (nr & 31);
return (atomic_test_and_XOR_mask(mask, ptr) & mask) != 0;
}
-static inline void clear_bit(int nr, volatile void *addr)
+static inline void clear_bit(unsigned long nr, volatile void *addr)
{
test_and_clear_bit(nr, addr);
}
-static inline void set_bit(int nr, volatile void *addr)
+static inline void set_bit(unsigned long nr, volatile void *addr)
{
test_and_set_bit(nr, addr);
}
-static inline void change_bit(int nr, volatile void * addr)
+static inline void change_bit(unsigned long nr, volatile void *addr)
{
test_and_change_bit(nr, addr);
}
-static inline void __clear_bit(int nr, volatile void * addr)
+static inline void __clear_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask;
*a &= ~mask;
}
-static inline void __set_bit(int nr, volatile void * addr)
+static inline void __set_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask;
*a |= mask;
}
-static inline void __change_bit(int nr, volatile void *addr)
+static inline void __change_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask;
*a ^= mask;
}
-static inline int __test_and_clear_bit(int nr, volatile void * addr)
+static inline int __test_and_clear_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask, retval;
return retval;
}
-static inline int __test_and_set_bit(int nr, volatile void * addr)
+static inline int __test_and_set_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask, retval;
return retval;
}
-static inline int __test_and_change_bit(int nr, volatile void * addr)
+static inline int __test_and_change_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask, retval;
/*
* This routine doesn't need to be atomic.
*/
-static inline int __constant_test_bit(int nr, const volatile void * addr)
+static inline int
+__constant_test_bit(unsigned long nr, const volatile void *addr)
{
return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
}
-static inline int __test_bit(int nr, const volatile void * addr)
+static inline int __test_bit(unsigned long nr, const volatile void *addr)
{
int * a = (int *) addr;
int mask;
} while(0)
#define USE_ELF_CORE_DUMP
+#define CORE_DUMP_USE_REGSET
#define ELF_FDPIC_CORE_EFLAGS EF_FRV_FDPIC
#define ELF_EXEC_PAGESIZE 16384
dma_addr_t dma_handle,
size_t size, int direction)
{
- if (direction == PCI_DMA_NONE)
- BUG();
+ BUG_ON(direction == PCI_DMA_NONE);
frv_cache_wback_inv((unsigned long)bus_to_virt(dma_handle),
(unsigned long)bus_to_virt(dma_handle) + size);
int nelems, int direction)
{
int i;
-
- if (direction == PCI_DMA_NONE)
- BUG();
+ BUG_ON(direction == PCI_DMA_NONE);
for (i = 0; i < nelems; i++)
frv_cache_wback_inv(sg_dma_address(&sg[i]),
#ifdef __KERNEL__
#ifndef __ASSEMBLY__
+struct task_struct;
+
/*
* we dedicate GR28 to keeping a pointer to the current exception frame
* - gr28 is destroyed on entry to the kernel from userspace
#define user_mode(regs) (!((regs)->psr & PSR_S))
#define instruction_pointer(regs) ((regs)->pc)
+#define user_stack_pointer(regs) ((regs)->sp)
extern unsigned long user_stack(const struct pt_regs *);
extern void show_regs(struct pt_regs *);
#define profile_pc(regs) ((regs)->pc)
-#endif
+
+#define task_pt_regs(task) ((task)->thread.frame0)
+
+#define arch_has_single_step() (1)
+extern void user_enable_single_step(struct task_struct *);
+extern void user_disable_single_step(struct task_struct *);
#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
#endif /* _ASM_PTRACE_H */
--- /dev/null
+/* syscall parameter access functions
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_SYSCALL_H
+#define _ASM_SYSCALL_H
+
+#include <linux/err.h>
+#include <asm/ptrace.h>
+
+/*
+ * Get the system call number or -1
+ */
+static inline long syscall_get_nr(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->syscallno;
+}
+
+/*
+ * Restore the clobbered GR8 register
+ * (1st syscall arg was overwritten with syscall return or error)
+ */
+static inline void syscall_rollback(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ regs->gr8 = regs->orig_gr8;
+}
+
+/*
+ * See if the syscall return value is an error, returning it if it is and 0 if
+ * not
+ */
+static inline long syscall_get_error(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return IS_ERR_VALUE(regs->gr8) ? regs->gr8 : 0;
+}
+
+/*
+ * Get the syscall return value
+ */
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->gr8;
+}
+
+/*
+ * Set the syscall return value
+ */
+static inline void syscall_set_return_value(struct task_struct *task,
+ struct pt_regs *regs,
+ int error, long val)
+{
+ if (error)
+ regs->gr8 = -error;
+ else
+ regs->gr8 = val;
+}
+
+/*
+ * Retrieve the system call arguments
+ */
+static inline void syscall_get_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ unsigned long *args)
+{
+ /*
+ * Do this simply for now. If we need to start supporting
+ * fetching arguments from arbitrary indices, this will need some
+ * extra logic. Presently there are no in-tree users that depend
+ * on this behaviour.
+ */
+ BUG_ON(i);
+
+ /* Argument pattern is: GR8, GR9, GR10, GR11, GR12, GR13 */
+ switch (n) {
+ case 6: args[5] = regs->gr13;
+ case 5: args[4] = regs->gr12;
+ case 4: args[3] = regs->gr11;
+ case 3: args[2] = regs->gr10;
+ case 2: args[1] = regs->gr9;
+ case 1: args[0] = regs->gr8;
+ break;
+ default:
+ BUG();
+ }
+}
+
+/*
+ * Alter the system call arguments
+ */
+static inline void syscall_set_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ unsigned int i, unsigned int n,
+ const unsigned long *args)
+{
+ /* Same note as above applies */
+ BUG_ON(i);
+
+ switch (n) {
+ case 6: regs->gr13 = args[5];
+ case 5: regs->gr12 = args[4];
+ case 4: regs->gr11 = args[3];
+ case 3: regs->gr10 = args[2];
+ case 2: regs->gr9 = args[1];
+ case 1: regs->gr8 = args[0];
+ break;
+ default:
+ BUG();
+ }
+}
+
+#endif /* _ASM_SYSCALL_H */
* - other flags in MSW
*/
#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
-#define TIF_SIGPENDING 1 /* signal pending */
-#define TIF_NEED_RESCHED 2 /* rescheduling necessary */
-#define TIF_SINGLESTEP 3 /* restore singlestep on return to user mode */
-#define TIF_IRET 4 /* return with iret */
+#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
+#define TIF_SIGPENDING 2 /* signal pending */
+#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
+#define TIF_SINGLESTEP 4 /* restore singlestep on return to user mode */
#define TIF_RESTORE_SIGMASK 5 /* restore signal mask in do_signal() */
#define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling TIF_NEED_RESCHED */
#define TIF_MEMDIE 17 /* OOM killer killed process */
#define TIF_FREEZE 18 /* freezing for suspend */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
-#define _TIF_IRET (1 << TIF_IRET)
#define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK)
#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG)
#define _TIF_FREEZE (1 << TIF_FREEZE)
bnc icc0,#0,__syscall_badsys
ldi @(gr15,#TI_FLAGS),gr4
- ori gr4,#_TIF_SYSCALL_TRACE,gr4
andicc gr4,#_TIF_SYSCALL_TRACE,gr0,icc0
bne icc0,#0,__syscall_trace_entry
# perform syscall entry tracing
__syscall_trace_entry:
LEDS 0x6320
- setlos.p #0,gr8
- call do_syscall_trace
+ call syscall_trace_entry
- ldi @(gr28,#REG_SYSCALLNO),gr7
- lddi @(gr28,#REG_GR(8)) ,gr8
+ lddi.p @(gr28,#REG_GR(8)) ,gr8
+ ori gr8,#0,gr7 ; syscall_trace_entry() returned new syscallno
lddi @(gr28,#REG_GR(10)),gr10
lddi.p @(gr28,#REG_GR(12)),gr12
beq icc0,#1,__entry_work_pending
movsg psr,gr23
- andi gr23,#~PSR_PIL,gr23 ; could let do_syscall_trace() call schedule()
+ andi gr23,#~PSR_PIL,gr23 ; could let syscall_trace_exit() call schedule()
movgs gr23,psr
- setlos.p #1,gr8
- call do_syscall_trace
+ call syscall_trace_exit
bra __entry_resume_userspace
__syscall_badsys:
#include <linux/user.h>
#include <linux/security.h>
#include <linux/signal.h>
+#include <linux/regset.h>
+#include <linux/elf.h>
+#include <linux/tracehook.h>
#include <asm/uaccess.h>
#include <asm/page.h>
* in exit.c or in signal.c.
*/
+/*
+ * retrieve the contents of FRV userspace general registers
+ */
+static int genregs_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ const struct user_int_regs *iregs = &target->thread.user->i;
+ int ret;
+
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ iregs, 0, sizeof(*iregs));
+ if (ret < 0)
+ return ret;
+
+ return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+ sizeof(*iregs), -1);
+}
+
+/*
+ * update the contents of the FRV userspace general registers
+ */
+static int genregs_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct user_int_regs *iregs = &target->thread.user->i;
+ unsigned int offs_gr0, offs_gr1;
+ int ret;
+
+ /* not allowed to set PSR or __status */
+ if (pos < offsetof(struct user_int_regs, psr) + sizeof(long) &&
+ pos + count > offsetof(struct user_int_regs, psr))
+ return -EIO;
+
+ if (pos < offsetof(struct user_int_regs, __status) + sizeof(long) &&
+ pos + count > offsetof(struct user_int_regs, __status))
+ return -EIO;
+
+ /* set the control regs */
+ offs_gr0 = offsetof(struct user_int_regs, gr[0]);
+ offs_gr1 = offsetof(struct user_int_regs, gr[1]);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ iregs, 0, offs_gr0);
+ if (ret < 0)
+ return ret;
+
+ /* skip GR0/TBR */
+ ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ offs_gr0, offs_gr1);
+ if (ret < 0)
+ return ret;
+
+ /* set the general regs */
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &iregs->gr[1], offs_gr1, sizeof(*iregs));
+ if (ret < 0)
+ return ret;
+
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ sizeof(*iregs), -1);
+}
+
+/*
+ * retrieve the contents of FRV userspace FP/Media registers
+ */
+static int fpmregs_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ const struct user_fpmedia_regs *fpregs = &target->thread.user->f;
+ int ret;
+
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ fpregs, 0, sizeof(*fpregs));
+ if (ret < 0)
+ return ret;
+
+ return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+ sizeof(*fpregs), -1);
+}
+
+/*
+ * update the contents of the FRV userspace FP/Media registers
+ */
+static int fpmregs_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct user_fpmedia_regs *fpregs = &target->thread.user->f;
+ int ret;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ fpregs, 0, sizeof(*fpregs));
+ if (ret < 0)
+ return ret;
+
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ sizeof(*fpregs), -1);
+}
+
+/*
+ * determine if the FP/Media registers have actually been used
+ */
+static int fpmregs_active(struct task_struct *target,
+ const struct user_regset *regset)
+{
+ return tsk_used_math(target) ? regset->n : 0;
+}
+
+/*
+ * Define the register sets available on the FRV under Linux
+ */
+enum frv_regset {
+ REGSET_GENERAL,
+ REGSET_FPMEDIA,
+};
+
+static const struct user_regset frv_regsets[] = {
+ /*
+ * General register format is:
+ * PSR, ISR, CCR, CCCR, LR, LCR, PC, (STATUS), SYSCALLNO, ORIG_G8
+ * GNER0-1, IACC0, TBR, GR1-63
+ */
+ [REGSET_GENERAL] = {
+ .core_note_type = NT_PRSTATUS,
+ .n = ELF_NGREG,
+ .size = sizeof(long),
+ .align = sizeof(long),
+ .get = genregs_get,
+ .set = genregs_set,
+ },
+ /*
+ * FPU/Media register format is:
+ * FR0-63, FNER0-1, MSR0-1, ACC0-7, ACCG0-8, FSR
+ */
+ [REGSET_FPMEDIA] = {
+ .core_note_type = NT_PRFPREG,
+ .n = sizeof(struct user_fpmedia_regs) / sizeof(long),
+ .size = sizeof(long),
+ .align = sizeof(long),
+ .get = fpmregs_get,
+ .set = fpmregs_set,
+ .active = fpmregs_active,
+ },
+};
+
+static const struct user_regset_view user_frv_native_view = {
+ .name = "frv",
+ .e_machine = EM_FRV,
+ .regsets = frv_regsets,
+ .n = ARRAY_SIZE(frv_regsets),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ return &user_frv_native_view;
+}
+
/*
* Get contents of register REGNO in task TASK.
*/
}
}
-/*
- * check that an address falls within the bounds of the target process's memory
- * mappings
- */
-static inline int is_user_addr_valid(struct task_struct *child,
- unsigned long start, unsigned long len)
-{
-#ifdef CONFIG_MMU
- if (start >= PAGE_OFFSET || len > PAGE_OFFSET - start)
- return -EIO;
- return 0;
-#else
- struct vm_area_struct *vma;
-
- vma = find_vma(child->mm, start);
- if (vma && start >= vma->vm_start && start + len <= vma->vm_end)
- return 0;
-
- return -EIO;
-#endif
-}
-
/*
* Called by kernel/ptrace.c when detaching..
*
* Control h/w single stepping
*/
-void ptrace_disable(struct task_struct *child)
+void user_enable_single_step(struct task_struct *child)
+{
+ child->thread.frame0->__status |= REG__STATUS_STEP;
+}
+
+void user_disable_single_step(struct task_struct *child)
{
child->thread.frame0->__status &= ~REG__STATUS_STEP;
}
-void ptrace_enable(struct task_struct *child)
+void ptrace_disable(struct task_struct *child)
{
- child->thread.frame0->__status |= REG__STATUS_STEP;
+ user_disable_single_step(child);
}
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
int ret;
switch (request) {
- /* when I and D space are separate, these will need to be fixed. */
- case PTRACE_PEEKTEXT: /* read word at location addr. */
- case PTRACE_PEEKDATA:
- ret = -EIO;
- if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
- break;
- ret = generic_ptrace_peekdata(child, addr, data);
- break;
-
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
tmp = 0;
break;
}
- /* when I and D space are separate, this will have to be fixed. */
- case PTRACE_POKETEXT: /* write the word at location addr. */
- case PTRACE_POKEDATA:
- ret = -EIO;
- if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
- break;
- ret = generic_ptrace_pokedata(child, addr, data);
- break;
-
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
ret = -EIO;
if ((addr & 3) || addr < 0)
ret = 0;
switch (addr >> 2) {
- case 0 ... PT__END-1:
+ case 0 ... PT__END - 1:
ret = put_reg(child, addr >> 2, data);
break;
}
break;
- case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
- case PTRACE_CONT: /* restart after signal. */
- ret = -EIO;
- if (!valid_signal(data))
- break;
- if (request == PTRACE_SYSCALL)
- set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
- else
- clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
- child->exit_code = data;
- ptrace_disable(child);
- wake_up_process(child);
- ret = 0;
- break;
-
- /* make the child exit. Best I can do is send it a sigkill.
- * perhaps it should be put in the status that it wants to
- * exit.
- */
- case PTRACE_KILL:
- ret = 0;
- if (child->exit_state == EXIT_ZOMBIE) /* already dead */
- break;
- child->exit_code = SIGKILL;
- clear_tsk_thread_flag(child, TIF_SINGLESTEP);
- ptrace_disable(child);
- wake_up_process(child);
- break;
-
- case PTRACE_SINGLESTEP: /* set the trap flag. */
- ret = -EIO;
- if (!valid_signal(data))
- break;
- clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
- ptrace_enable(child);
- child->exit_code = data;
- wake_up_process(child);
- ret = 0;
- break;
-
- case PTRACE_DETACH: /* detach a process that was attached. */
- ret = ptrace_detach(child, data);
- break;
-
- case PTRACE_GETREGS: { /* Get all integer regs from the child. */
- int i;
- for (i = 0; i < PT__GPEND; i++) {
- tmp = get_reg(child, i);
- if (put_user(tmp, (unsigned long *) data)) {
- ret = -EFAULT;
- break;
- }
- data += sizeof(long);
- }
- ret = 0;
- break;
- }
-
- case PTRACE_SETREGS: { /* Set all integer regs in the child. */
- int i;
- for (i = 0; i < PT__GPEND; i++) {
- if (get_user(tmp, (unsigned long *) data)) {
- ret = -EFAULT;
- break;
- }
- put_reg(child, i, tmp);
- data += sizeof(long);
- }
- ret = 0;
- break;
- }
-
- case PTRACE_GETFPREGS: { /* Get the child FP/Media state. */
- ret = 0;
- if (copy_to_user((void *) data,
- &child->thread.user->f,
- sizeof(child->thread.user->f)))
- ret = -EFAULT;
- break;
- }
-
- case PTRACE_SETFPREGS: { /* Set the child FP/Media state. */
- ret = 0;
- if (copy_from_user(&child->thread.user->f,
- (void *) data,
- sizeof(child->thread.user->f)))
- ret = -EFAULT;
- break;
- }
+ case PTRACE_GETREGS: /* Get all integer regs from the child. */
+ return copy_regset_to_user(child, &user_frv_native_view,
+ REGSET_GENERAL,
+ 0, sizeof(child->thread.user->i),
+ (void __user *)data);
+
+ case PTRACE_SETREGS: /* Set all integer regs in the child. */
+ return copy_regset_from_user(child, &user_frv_native_view,
+ REGSET_GENERAL,
+ 0, sizeof(child->thread.user->i),
+ (const void __user *)data);
+
+ case PTRACE_GETFPREGS: /* Get the child FP/Media state. */
+ return copy_regset_to_user(child, &user_frv_native_view,
+ REGSET_FPMEDIA,
+ 0, sizeof(child->thread.user->f),
+ (void __user *)data);
+
+ case PTRACE_SETFPREGS: /* Set the child FP/Media state. */
+ return copy_regset_from_user(child, &user_frv_native_view,
+ REGSET_FPMEDIA,
+ 0, sizeof(child->thread.user->f),
+ (const void __user *)data);
case PTRACE_GETFDPIC:
tmp = 0;
break;
default:
- ret = -EIO;
+ ret = ptrace_request(child, request, addr, data);
break;
}
return ret;
}
-int __nongprelbss kstrace;
-
-static const struct {
- const char *name;
- unsigned argmask;
-} __syscall_name_table[NR_syscalls] = {
- [0] = { "restart_syscall" },
- [1] = { "exit", 0x000001 },
- [2] = { "fork", 0xffffff },
- [3] = { "read", 0x000141 },
- [4] = { "write", 0x000141 },
- [5] = { "open", 0x000235 },
- [6] = { "close", 0x000001 },
- [7] = { "waitpid", 0x000141 },
- [8] = { "creat", 0x000025 },
- [9] = { "link", 0x000055 },
- [10] = { "unlink", 0x000005 },
- [11] = { "execve", 0x000445 },
- [12] = { "chdir", 0x000005 },
- [13] = { "time", 0x000004 },
- [14] = { "mknod", 0x000325 },
- [15] = { "chmod", 0x000025 },
- [16] = { "lchown", 0x000025 },
- [17] = { "break" },
- [18] = { "oldstat", 0x000045 },
- [19] = { "lseek", 0x000131 },
- [20] = { "getpid", 0xffffff },
- [21] = { "mount", 0x043555 },
- [22] = { "umount", 0x000005 },
- [23] = { "setuid", 0x000001 },
- [24] = { "getuid", 0xffffff },
- [25] = { "stime", 0x000004 },
- [26] = { "ptrace", 0x004413 },
- [27] = { "alarm", 0x000001 },
- [28] = { "oldfstat", 0x000041 },
- [29] = { "pause", 0xffffff },
- [30] = { "utime", 0x000045 },
- [31] = { "stty" },
- [32] = { "gtty" },
- [33] = { "access", 0x000025 },
- [34] = { "nice", 0x000001 },
- [35] = { "ftime" },
- [36] = { "sync", 0xffffff },
- [37] = { "kill", 0x000011 },
- [38] = { "rename", 0x000055 },
- [39] = { "mkdir", 0x000025 },
- [40] = { "rmdir", 0x000005 },
- [41] = { "dup", 0x000001 },
- [42] = { "pipe", 0x000004 },
- [43] = { "times", 0x000004 },
- [44] = { "prof" },
- [45] = { "brk", 0x000004 },
- [46] = { "setgid", 0x000001 },
- [47] = { "getgid", 0xffffff },
- [48] = { "signal", 0x000041 },
- [49] = { "geteuid", 0xffffff },
- [50] = { "getegid", 0xffffff },
- [51] = { "acct", 0x000005 },
- [52] = { "umount2", 0x000035 },
- [53] = { "lock" },
- [54] = { "ioctl", 0x000331 },
- [55] = { "fcntl", 0x000331 },
- [56] = { "mpx" },
- [57] = { "setpgid", 0x000011 },
- [58] = { "ulimit" },
- [60] = { "umask", 0x000002 },
- [61] = { "chroot", 0x000005 },
- [62] = { "ustat", 0x000043 },
- [63] = { "dup2", 0x000011 },
- [64] = { "getppid", 0xffffff },
- [65] = { "getpgrp", 0xffffff },
- [66] = { "setsid", 0xffffff },
- [67] = { "sigaction" },
- [68] = { "sgetmask" },
- [69] = { "ssetmask" },
- [70] = { "setreuid" },
- [71] = { "setregid" },
- [72] = { "sigsuspend" },
- [73] = { "sigpending" },
- [74] = { "sethostname" },
- [75] = { "setrlimit" },
- [76] = { "getrlimit" },
- [77] = { "getrusage" },
- [78] = { "gettimeofday" },
- [79] = { "settimeofday" },
- [80] = { "getgroups" },
- [81] = { "setgroups" },
- [82] = { "select" },
- [83] = { "symlink" },
- [84] = { "oldlstat" },
- [85] = { "readlink" },
- [86] = { "uselib" },
- [87] = { "swapon" },
- [88] = { "reboot" },
- [89] = { "readdir" },
- [91] = { "munmap", 0x000034 },
- [92] = { "truncate" },
- [93] = { "ftruncate" },
- [94] = { "fchmod" },
- [95] = { "fchown" },
- [96] = { "getpriority" },
- [97] = { "setpriority" },
- [99] = { "statfs" },
- [100] = { "fstatfs" },
- [102] = { "socketcall" },
- [103] = { "syslog" },
- [104] = { "setitimer" },
- [105] = { "getitimer" },
- [106] = { "stat" },
- [107] = { "lstat" },
- [108] = { "fstat" },
- [111] = { "vhangup" },
- [114] = { "wait4" },
- [115] = { "swapoff" },
- [116] = { "sysinfo" },
- [117] = { "ipc" },
- [118] = { "fsync" },
- [119] = { "sigreturn" },
- [120] = { "clone" },
- [121] = { "setdomainname" },
- [122] = { "uname" },
- [123] = { "modify_ldt" },
- [123] = { "cacheflush" },
- [124] = { "adjtimex" },
- [125] = { "mprotect" },
- [126] = { "sigprocmask" },
- [127] = { "create_module" },
- [128] = { "init_module" },
- [129] = { "delete_module" },
- [130] = { "get_kernel_syms" },
- [131] = { "quotactl" },
- [132] = { "getpgid" },
- [133] = { "fchdir" },
- [134] = { "bdflush" },
- [135] = { "sysfs" },
- [136] = { "personality" },
- [137] = { "afs_syscall" },
- [138] = { "setfsuid" },
- [139] = { "setfsgid" },
- [140] = { "_llseek", 0x014331 },
- [141] = { "getdents" },
- [142] = { "_newselect", 0x000141 },
- [143] = { "flock" },
- [144] = { "msync" },
- [145] = { "readv" },
- [146] = { "writev" },
- [147] = { "getsid", 0x000001 },
- [148] = { "fdatasync", 0x000001 },
- [149] = { "_sysctl", 0x000004 },
- [150] = { "mlock" },
- [151] = { "munlock" },
- [152] = { "mlockall" },
- [153] = { "munlockall" },
- [154] = { "sched_setparam" },
- [155] = { "sched_getparam" },
- [156] = { "sched_setscheduler" },
- [157] = { "sched_getscheduler" },
- [158] = { "sched_yield" },
- [159] = { "sched_get_priority_max" },
- [160] = { "sched_get_priority_min" },
- [161] = { "sched_rr_get_interval" },
- [162] = { "nanosleep", 0x000044 },
- [163] = { "mremap" },
- [164] = { "setresuid" },
- [165] = { "getresuid" },
- [166] = { "vm86" },
- [167] = { "query_module" },
- [168] = { "poll" },
- [169] = { "nfsservctl" },
- [170] = { "setresgid" },
- [171] = { "getresgid" },
- [172] = { "prctl", 0x333331 },
- [173] = { "rt_sigreturn", 0xffffff },
- [174] = { "rt_sigaction", 0x001441 },
- [175] = { "rt_sigprocmask", 0x001441 },
- [176] = { "rt_sigpending", 0x000014 },
- [177] = { "rt_sigtimedwait", 0x001444 },
- [178] = { "rt_sigqueueinfo", 0x000411 },
- [179] = { "rt_sigsuspend", 0x000014 },
- [180] = { "pread", 0x003341 },
- [181] = { "pwrite", 0x003341 },
- [182] = { "chown", 0x000115 },
- [183] = { "getcwd" },
- [184] = { "capget" },
- [185] = { "capset" },
- [186] = { "sigaltstack" },
- [187] = { "sendfile" },
- [188] = { "getpmsg" },
- [189] = { "putpmsg" },
- [190] = { "vfork", 0xffffff },
- [191] = { "ugetrlimit" },
- [192] = { "mmap2", 0x313314 },
- [193] = { "truncate64" },
- [194] = { "ftruncate64" },
- [195] = { "stat64", 0x000045 },
- [196] = { "lstat64", 0x000045 },
- [197] = { "fstat64", 0x000041 },
- [198] = { "lchown32" },
- [199] = { "getuid32", 0xffffff },
- [200] = { "getgid32", 0xffffff },
- [201] = { "geteuid32", 0xffffff },
- [202] = { "getegid32", 0xffffff },
- [203] = { "setreuid32" },
- [204] = { "setregid32" },
- [205] = { "getgroups32" },
- [206] = { "setgroups32" },
- [207] = { "fchown32" },
- [208] = { "setresuid32" },
- [209] = { "getresuid32" },
- [210] = { "setresgid32" },
- [211] = { "getresgid32" },
- [212] = { "chown32" },
- [213] = { "setuid32" },
- [214] = { "setgid32" },
- [215] = { "setfsuid32" },
- [216] = { "setfsgid32" },
- [217] = { "pivot_root" },
- [218] = { "mincore" },
- [219] = { "madvise" },
- [220] = { "getdents64" },
- [221] = { "fcntl64" },
- [223] = { "security" },
- [224] = { "gettid" },
- [225] = { "readahead" },
- [226] = { "setxattr" },
- [227] = { "lsetxattr" },
- [228] = { "fsetxattr" },
- [229] = { "getxattr" },
- [230] = { "lgetxattr" },
- [231] = { "fgetxattr" },
- [232] = { "listxattr" },
- [233] = { "llistxattr" },
- [234] = { "flistxattr" },
- [235] = { "removexattr" },
- [236] = { "lremovexattr" },
- [237] = { "fremovexattr" },
- [238] = { "tkill" },
- [239] = { "sendfile64" },
- [240] = { "futex" },
- [241] = { "sched_setaffinity" },
- [242] = { "sched_getaffinity" },
- [243] = { "set_thread_area" },
- [244] = { "get_thread_area" },
- [245] = { "io_setup" },
- [246] = { "io_destroy" },
- [247] = { "io_getevents" },
- [248] = { "io_submit" },
- [249] = { "io_cancel" },
- [250] = { "fadvise64" },
- [252] = { "exit_group", 0x000001 },
- [253] = { "lookup_dcookie" },
- [254] = { "epoll_create" },
- [255] = { "epoll_ctl" },
- [256] = { "epoll_wait" },
- [257] = { "remap_file_pages" },
- [258] = { "set_tid_address" },
- [259] = { "timer_create" },
- [260] = { "timer_settime" },
- [261] = { "timer_gettime" },
- [262] = { "timer_getoverrun" },
- [263] = { "timer_delete" },
- [264] = { "clock_settime" },
- [265] = { "clock_gettime" },
- [266] = { "clock_getres" },
- [267] = { "clock_nanosleep" },
- [268] = { "statfs64" },
- [269] = { "fstatfs64" },
- [270] = { "tgkill" },
- [271] = { "utimes" },
- [272] = { "fadvise64_64" },
- [273] = { "vserver" },
- [274] = { "mbind" },
- [275] = { "get_mempolicy" },
- [276] = { "set_mempolicy" },
- [277] = { "mq_open" },
- [278] = { "mq_unlink" },
- [279] = { "mq_timedsend" },
- [280] = { "mq_timedreceive" },
- [281] = { "mq_notify" },
- [282] = { "mq_getsetattr" },
- [283] = { "sys_kexec_load" },
-};
-
-asmlinkage void do_syscall_trace(int leaving)
+/*
+ * handle tracing of system call entry
+ * - return the revised system call number or ULONG_MAX to cause ENOSYS
+ */
+asmlinkage unsigned long syscall_trace_entry(void)
{
-#if 0
- unsigned long *argp;
- const char *name;
- unsigned argmask;
- char buffer[16];
-
- if (!kstrace)
- return;
-
- if (!current->mm)
- return;
-
- if (__frame->gr7 == __NR_close)
- return;
-
-#if 0
- if (__frame->gr7 != __NR_mmap2 &&
- __frame->gr7 != __NR_vfork &&
- __frame->gr7 != __NR_execve &&
- __frame->gr7 != __NR_exit)
- return;
-#endif
-
- argmask = 0;
- name = NULL;
- if (__frame->gr7 < NR_syscalls) {
- name = __syscall_name_table[__frame->gr7].name;
- argmask = __syscall_name_table[__frame->gr7].argmask;
- }
- if (!name) {
- sprintf(buffer, "sys_%lx", __frame->gr7);
- name = buffer;
- }
-
- if (!leaving) {
- if (!argmask) {
- printk(KERN_CRIT "[%d] %s(%lx,%lx,%lx,%lx,%lx,%lx)\n",
- current->pid,
- name,
- __frame->gr8,
- __frame->gr9,
- __frame->gr10,
- __frame->gr11,
- __frame->gr12,
- __frame->gr13);
- }
- else if (argmask == 0xffffff) {
- printk(KERN_CRIT "[%d] %s()\n",
- current->pid,
- name);
- }
- else {
- printk(KERN_CRIT "[%d] %s(",
- current->pid,
- name);
-
- argp = &__frame->gr8;
-
- do {
- switch (argmask & 0xf) {
- case 1:
- printk("%ld", (long) *argp);
- break;
- case 2:
- printk("%lo", *argp);
- break;
- case 3:
- printk("%lx", *argp);
- break;
- case 4:
- printk("%p", (void *) *argp);
- break;
- case 5:
- printk("\"%s\"", (char *) *argp);
- break;
- }
-
- argp++;
- argmask >>= 4;
- if (argmask)
- printk(",");
-
- } while (argmask);
-
- printk(")\n");
- }
- }
- else {
- if ((int)__frame->gr8 > -4096 && (int)__frame->gr8 < 4096)
- printk(KERN_CRIT "[%d] %s() = %ld\n", current->pid, name, __frame->gr8);
- else
- printk(KERN_CRIT "[%d] %s() = %lx\n", current->pid, name, __frame->gr8);
+ __frame->__status |= REG__STATUS_SYSC_ENTRY;
+ if (tracehook_report_syscall_entry(__frame)) {
+ /* tracing decided this syscall should not happen, so
+ * We'll return a bogus call number to get an ENOSYS
+ * error, but leave the original number in
+ * __frame->syscallno
+ */
+ return ULONG_MAX;
}
- return;
-#endif
-
- if (!test_thread_flag(TIF_SYSCALL_TRACE))
- return;
-
- if (!(current->ptrace & PT_PTRACED))
- return;
- /* we need to indicate entry or exit to strace */
- if (leaving)
- __frame->__status |= REG__STATUS_SYSC_EXIT;
- else
- __frame->__status |= REG__STATUS_SYSC_ENTRY;
-
- ptrace_notify(SIGTRAP);
+ return __frame->syscallno;
+}
- /*
- * this isn't the same as continuing with a signal, but it will do
- * for normal use. strace only continues with a signal if the
- * stopping signal is not SIGTRAP. -brl
- */
- if (current->exit_code) {
- send_sig(current->exit_code, current, 1);
- current->exit_code = 0;
- }
+/*
+ * handle tracing of system call exit
+ */
+asmlinkage void syscall_trace_exit(void)
+{
+ __frame->__status |= REG__STATUS_SYSC_EXIT;
+ tracehook_report_syscall_exit(__frame, 0);
}
#include <linux/unistd.h>
#include <linux/personality.h>
#include <linux/freezer.h>
+#include <linux/tracehook.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
* clear the TIF_RESTORE_SIGMASK flag */
if (test_thread_flag(TIF_RESTORE_SIGMASK))
clear_thread_flag(TIF_RESTORE_SIGMASK);
+
+ tracehook_signal_handler(signr, &info, &ka, __frame,
+ test_thread_flag(TIF_SINGLESTEP));
}
return;
if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK))
do_signal();
+ /* deal with notification on about to resume userspace execution */
+ if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(__frame);
+ }
+
} /* end do_notify_resume() */
char *p, ch;
long err = -EFAULT;
- if (count < 0)
- BUG();
+ BUG_ON(count < 0);
p = dst;
long err = 0;
char ch;
- if (count < 0)
- BUG();
+ BUG_ON(count < 0);
#ifndef CONFIG_MMU
if ((unsigned long) src < memory_start)
dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
enum dma_data_direction direction)
{
- if (direction == DMA_NONE)
- BUG();
+ BUG_ON(direction == DMA_NONE);
frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
frv_cache_wback_inv(sg_dma_address(&sg[i]),
sg_dma_address(&sg[i]) + sg_dma_len(&sg[i]));
- if (direction == DMA_NONE)
- BUG();
+ BUG_ON(direction == DMA_NONE);
return nents;
}
dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
enum dma_data_direction direction)
{
- if (direction == DMA_NONE)
- BUG();
+ BUG_ON(direction == DMA_NONE);
frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
void *vaddr;
int i;
- if (direction == DMA_NONE)
- BUG();
+ BUG_ON(direction == DMA_NONE);
dampr2 = __get_DAMPR(2);
{
}
-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 = {
* 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;
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;
}
}
-static void
+static int
iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
{
#ifdef CONFIG_SMP
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);
iosapic_write(iosapic, IOSAPIC_RTE_HIGH(rte_index), high32);
iosapic_write(iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
}
+
#endif
+ return 0;
}
/*
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;
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);
write_msi_msg(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
+
+ return 0;
}
#endif /* CONFIG_SMP */
#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);
dmar_msi_write(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, mask);
+
+ return 0;
}
#endif /* CONFIG_SMP */
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;
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
}
#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;
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
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
write_msi_msg(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, cpu_mask);
+
+ return 0;
}
#endif /* CONFIG_SMP */
}
#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 */
*/
cvmx_read_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2));
write_unlock(&octeon_irq_ciu0_rwlock);
+
+ return 0;
}
#endif
}
#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 */
*/
cvmx_read_csr(CVMX_CIU_INTX_EN1(cvmx_get_core_num() * 2 + 1));
write_unlock(&octeon_irq_ciu1_rwlock);
+
+ return 0;
}
#endif
#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);
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;
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);
cpumask_copy(irq_desc[irq].affinity, cpumask);
spin_unlock_irqrestore(&gic_lock, flags);
+ return 0;
}
#endif
*/
-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;
/* Do any generic SMTC IRQ affinity setup */
smtc_set_irq_affinity(irq, tmask);
+
+ return 0;
}
#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
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
}
#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;
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);
}
}
spin_unlock_irqrestore(&bcm1480_imr_lock, flags);
+
+ return 0;
}
#endif
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
}
#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;
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 */
R_IMR_INTERRUPT_MASK));
}
spin_unlock_irqrestore(&sb1250_imr_lock, flags);
+
+ return 0;
}
#endif
config MN10300
def_bool y
select HAVE_OPROFILE
+ select HAVE_ARCH_TRACEHOOK
config AM33
def_bool y
*/
typedef unsigned long elf_greg_t;
-#define ELF_NGREG (sizeof (struct pt_regs) / sizeof(elf_greg_t))
+#define ELF_NGREG ((sizeof(struct pt_regs) / sizeof(elf_greg_t)) - 1)
typedef elf_greg_t elf_gregset_t[ELF_NGREG];
#define ELF_NFPREG 32
} while (0)
#define USE_ELF_CORE_DUMP
+#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE 4096
/*
unsigned long get_wchan(struct task_struct *p);
-#define task_pt_regs(task) \
-({ \
- struct pt_regs *__regs__; \
- __regs__ = (struct pt_regs *) (KSTK_TOP(task_stack_page(task)) - 8); \
- __regs__ - 1; \
-})
-
+#define task_pt_regs(task) ((task)->thread.uregs)
#define KSTK_EIP(task) (task_pt_regs(task)->pc)
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#if defined(__KERNEL__)
#if !defined(__ASSEMBLY__)
+struct task_struct;
+
#define user_mode(regs) (((regs)->epsw & EPSW_nSL) == EPSW_nSL)
#define instruction_pointer(regs) ((regs)->pc)
+#define user_stack_pointer(regs) ((regs)->sp)
extern void show_regs(struct pt_regs *);
+
+#define arch_has_single_step() (1)
+extern void user_enable_single_step(struct task_struct *);
+extern void user_disable_single_step(struct task_struct *);
+
#endif /* !__ASSEMBLY */
#define profile_pc(regs) ((regs)->pc)
cmp nr_syscalls,d0
bcc syscall_badsys
btst _TIF_SYSCALL_TRACE,(TI_flags,a2)
- bne syscall_trace_entry
+ bne syscall_entry_trace
syscall_call:
add d0,d0,a1
add a1,a1
syscall_exit_work:
btst _TIF_SYSCALL_TRACE,d2
beq work_pending
- __sti # could let do_syscall_trace() call
+ __sti # could let syscall_trace_exit() call
# schedule() instead
mov fp,d0
- mov 1,d1
- call do_syscall_trace[],0 # do_syscall_trace(regs,entryexit)
+ call syscall_trace_exit[],0 # do_syscall_trace(regs)
jmp resume_userspace
ALIGN
jmp resume_userspace
# perform syscall entry tracing
-syscall_trace_entry:
+syscall_entry_trace:
mov -ENOSYS,d0
mov d0,(REG_D0,fp)
mov fp,d0
- clr d1
- call do_syscall_trace[],0
- mov (REG_ORIG_D0,fp),d0
+ call syscall_trace_entry[],0 # returns the syscall number to actually use
mov (REG_D1,fp),d1
cmp nr_syscalls,d0
bcs syscall_call
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/user.h>
+#include <linux/regset.h>
+#include <linux/elf.h>
+#include <linux/tracehook.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/system.h>
((unsigned long) task->thread.uregs + offset);
}
-/*
- * this routine will put a word on the processes privileged stack.
- * the offset is how far from the base addr as stored in the TSS.
- * this routine assumes that all the privileged stacks are in our
- * data space.
- */
static inline
int put_stack_long(struct task_struct *task, int offset, unsigned long data)
{
return 0;
}
-static inline unsigned long get_fpregs(struct fpu_state_struct *buf,
- struct task_struct *tsk)
+/*
+ * retrieve the contents of MN10300 userspace general registers
+ */
+static int genregs_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
{
- return __copy_to_user(buf, &tsk->thread.fpu_state,
- sizeof(struct fpu_state_struct));
+ const struct pt_regs *regs = task_pt_regs(target);
+ int ret;
+
+ /* we need to skip regs->next */
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ regs, 0, PT_ORIG_D0 * sizeof(long));
+ if (ret < 0)
+ return ret;
+
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ ®s->orig_d0, PT_ORIG_D0 * sizeof(long),
+ NR_PTREGS * sizeof(long));
+ if (ret < 0)
+ return ret;
+
+ return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+ NR_PTREGS * sizeof(long), -1);
}
-static inline unsigned long set_fpregs(struct task_struct *tsk,
- struct fpu_state_struct *buf)
+/*
+ * update the contents of the MN10300 userspace general registers
+ */
+static int genregs_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
{
- return __copy_from_user(&tsk->thread.fpu_state, buf,
- sizeof(struct fpu_state_struct));
+ struct pt_regs *regs = task_pt_regs(target);
+ unsigned long tmp;
+ int ret;
+
+ /* we need to skip regs->next */
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ regs, 0, PT_ORIG_D0 * sizeof(long));
+ if (ret < 0)
+ return ret;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ ®s->orig_d0, PT_ORIG_D0 * sizeof(long),
+ PT_EPSW * sizeof(long));
+ if (ret < 0)
+ return ret;
+
+ /* we need to mask off changes to EPSW */
+ tmp = regs->epsw;
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &tmp, PT_EPSW * sizeof(long),
+ PT_PC * sizeof(long));
+ tmp &= EPSW_FLAG_V | EPSW_FLAG_C | EPSW_FLAG_N | EPSW_FLAG_Z;
+ tmp |= regs->epsw & ~(EPSW_FLAG_V | EPSW_FLAG_C | EPSW_FLAG_N |
+ EPSW_FLAG_Z);
+ regs->epsw = tmp;
+
+ if (ret < 0)
+ return ret;
+
+ /* and finally load the PC */
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ ®s->pc, PT_PC * sizeof(long),
+ NR_PTREGS * sizeof(long));
+
+ if (ret < 0)
+ return ret;
+
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ NR_PTREGS * sizeof(long), -1);
}
-static inline void fpsave_init(struct task_struct *task)
+/*
+ * retrieve the contents of MN10300 userspace FPU registers
+ */
+static int fpuregs_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
{
- memset(&task->thread.fpu_state, 0, sizeof(struct fpu_state_struct));
+ const struct fpu_state_struct *fpregs = &target->thread.fpu_state;
+ int ret;
+
+ unlazy_fpu(target);
+
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ fpregs, 0, sizeof(*fpregs));
+ if (ret < 0)
+ return ret;
+
+ return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+ sizeof(*fpregs), -1);
}
/*
- * make sure the single step bit is not set
+ * update the contents of the MN10300 userspace FPU registers
*/
-void ptrace_disable(struct task_struct *child)
+static int fpuregs_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu_state_struct fpu_state = target->thread.fpu_state;
+ int ret;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &fpu_state, 0, sizeof(fpu_state));
+ if (ret < 0)
+ return ret;
+
+ fpu_kill_state(target);
+ target->thread.fpu_state = fpu_state;
+ set_using_fpu(target);
+
+ return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ sizeof(fpu_state), -1);
+}
+
+/*
+ * determine if the FPU registers have actually been used
+ */
+static int fpuregs_active(struct task_struct *target,
+ const struct user_regset *regset)
+{
+ return is_using_fpu(target) ? regset->n : 0;
+}
+
+/*
+ * Define the register sets available on the MN10300 under Linux
+ */
+enum mn10300_regset {
+ REGSET_GENERAL,
+ REGSET_FPU,
+};
+
+static const struct user_regset mn10300_regsets[] = {
+ /*
+ * General register format is:
+ * A3, A2, D3, D2, MCVF, MCRL, MCRH, MDRQ
+ * E1, E0, E7...E2, SP, LAR, LIR, MDR
+ * A1, A0, D1, D0, ORIG_D0, EPSW, PC
+ */
+ [REGSET_GENERAL] = {
+ .core_note_type = NT_PRSTATUS,
+ .n = ELF_NGREG,
+ .size = sizeof(long),
+ .align = sizeof(long),
+ .get = genregs_get,
+ .set = genregs_set,
+ },
+ /*
+ * FPU register format is:
+ * FS0-31, FPCR
+ */
+ [REGSET_FPU] = {
+ .core_note_type = NT_PRFPREG,
+ .n = sizeof(struct fpu_state_struct) / sizeof(long),
+ .size = sizeof(long),
+ .align = sizeof(long),
+ .get = fpuregs_get,
+ .set = fpuregs_set,
+ .active = fpuregs_active,
+ },
+};
+
+static const struct user_regset_view user_mn10300_native_view = {
+ .name = "mn10300",
+ .e_machine = EM_MN10300,
+ .regsets = mn10300_regsets,
+ .n = ARRAY_SIZE(mn10300_regsets),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ return &user_mn10300_native_view;
+}
+
+/*
+ * set the single-step bit
+ */
+void user_enable_single_step(struct task_struct *child)
{
#ifndef CONFIG_MN10300_USING_JTAG
struct user *dummy = NULL;
long tmp;
tmp = get_stack_long(child, (unsigned long) &dummy->regs.epsw);
- tmp &= ~EPSW_T;
+ tmp |= EPSW_T;
put_stack_long(child, (unsigned long) &dummy->regs.epsw, tmp);
#endif
}
/*
- * set the single step bit
+ * make sure the single-step bit is not set
*/
-void ptrace_enable(struct task_struct *child)
+void user_disable_single_step(struct task_struct *child)
{
#ifndef CONFIG_MN10300_USING_JTAG
struct user *dummy = NULL;
long tmp;
tmp = get_stack_long(child, (unsigned long) &dummy->regs.epsw);
- tmp |= EPSW_T;
+ tmp &= ~EPSW_T;
put_stack_long(child, (unsigned long) &dummy->regs.epsw, tmp);
#endif
}
+void ptrace_disable(struct task_struct *child)
+{
+ user_disable_single_step(child);
+}
+
/*
* handle the arch-specific side of process tracing
*/
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct fpu_state_struct fpu_state;
- int i, ret;
+ unsigned long tmp;
+ int ret;
switch (request) {
- /* read the word at location addr. */
- case PTRACE_PEEKTEXT: {
- unsigned long tmp;
- int copied;
-
- copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
- ret = -EIO;
- if (copied != sizeof(tmp))
- break;
- ret = put_user(tmp, (unsigned long *) data);
- break;
- }
-
- /* read the word at location addr. */
- case PTRACE_PEEKDATA: {
- unsigned long tmp;
- int copied;
-
- copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
- ret = -EIO;
- if (copied != sizeof(tmp))
- break;
- ret = put_user(tmp, (unsigned long *) data);
- break;
- }
-
/* read the word at location addr in the USER area. */
- case PTRACE_PEEKUSR: {
- unsigned long tmp;
-
+ case PTRACE_PEEKUSR:
ret = -EIO;
if ((addr & 3) || addr < 0 ||
addr > sizeof(struct user) - 3)
ptrace_regid_to_frame[addr]);
ret = put_user(tmp, (unsigned long *) data);
break;
- }
-
- /* write the word at location addr. */
- case PTRACE_POKETEXT:
- case PTRACE_POKEDATA:
- if (access_process_vm(child, addr, &data, sizeof(data), 1) ==
- sizeof(data))
- ret = 0;
- else
- ret = -EIO;
- break;
/* write the word at location addr in the USER area */
case PTRACE_POKEUSR:
data);
break;
- /* continue and stop at next (return from) syscall */
- case PTRACE_SYSCALL:
- /* restart after signal. */
- case PTRACE_CONT:
- ret = -EIO;
- if ((unsigned long) data > _NSIG)
- break;
- if (request == PTRACE_SYSCALL)
- set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
- else
- clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
- child->exit_code = data;
- ptrace_disable(child);
- wake_up_process(child);
- ret = 0;
- break;
-
- /*
- * make the child exit
- * - the best I can do is send it a sigkill
- * - perhaps it should be put in the status that it wants to
- * exit
- */
- case PTRACE_KILL:
- ret = 0;
- if (child->exit_state == EXIT_ZOMBIE) /* already dead */
- break;
- child->exit_code = SIGKILL;
- clear_tsk_thread_flag(child, TIF_SINGLESTEP);
- ptrace_disable(child);
- wake_up_process(child);
- break;
-
- case PTRACE_SINGLESTEP: /* set the trap flag. */
-#ifndef CONFIG_MN10300_USING_JTAG
- ret = -EIO;
- if ((unsigned long) data > _NSIG)
- break;
- clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
- ptrace_enable(child);
- child->exit_code = data;
- wake_up_process(child);
- ret = 0;
-#else
- ret = -EINVAL;
-#endif
- break;
-
- case PTRACE_DETACH: /* detach a process that was attached. */
- ret = ptrace_detach(child, data);
- break;
-
- /* Get all gp regs from the child. */
- case PTRACE_GETREGS: {
- unsigned long tmp;
-
- if (!access_ok(VERIFY_WRITE, (unsigned *) data, NR_PTREGS << 2)) {
- ret = -EIO;
- break;
- }
-
- for (i = 0; i < NR_PTREGS << 2; i += 4) {
- tmp = get_stack_long(child, ptrace_regid_to_frame[i]);
- __put_user(tmp, (unsigned long *) data);
- data += sizeof(tmp);
- }
- ret = 0;
- break;
- }
-
- case PTRACE_SETREGS: { /* Set all gp regs in the child. */
- unsigned long tmp;
-
- if (!access_ok(VERIFY_READ, (unsigned long *)data,
- sizeof(struct pt_regs))) {
- ret = -EIO;
- break;
- }
-
- for (i = 0; i < NR_PTREGS << 2; i += 4) {
- __get_user(tmp, (unsigned long *) data);
- put_stack_long(child, ptrace_regid_to_frame[i], tmp);
- data += sizeof(tmp);
- }
- ret = 0;
- break;
- }
-
- case PTRACE_GETFPREGS: { /* Get the child FPU state. */
- if (is_using_fpu(child)) {
- unlazy_fpu(child);
- fpu_state = child->thread.fpu_state;
- } else {
- memset(&fpu_state, 0, sizeof(fpu_state));
- }
-
- ret = -EIO;
- if (copy_to_user((void *) data, &fpu_state,
- sizeof(fpu_state)) == 0)
- ret = 0;
- break;
- }
-
- case PTRACE_SETFPREGS: { /* Set the child FPU state. */
- ret = -EFAULT;
- if (copy_from_user(&fpu_state, (const void *) data,
- sizeof(fpu_state)) == 0) {
- fpu_kill_state(child);
- child->thread.fpu_state = fpu_state;
- set_using_fpu(child);
- ret = 0;
- }
- break;
- }
-
- case PTRACE_SETOPTIONS: {
- if (data & PTRACE_O_TRACESYSGOOD)
- child->ptrace |= PT_TRACESYSGOOD;
- else
- child->ptrace &= ~PT_TRACESYSGOOD;
- ret = 0;
- break;
- }
+ case PTRACE_GETREGS: /* Get all integer regs from the child. */
+ return copy_regset_to_user(child, &user_mn10300_native_view,
+ REGSET_GENERAL,
+ 0, NR_PTREGS * sizeof(long),
+ (void __user *)data);
+
+ case PTRACE_SETREGS: /* Set all integer regs in the child. */
+ return copy_regset_from_user(child, &user_mn10300_native_view,
+ REGSET_GENERAL,
+ 0, NR_PTREGS * sizeof(long),
+ (const void __user *)data);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state. */
+ return copy_regset_to_user(child, &user_mn10300_native_view,
+ REGSET_FPU,
+ 0, sizeof(struct fpu_state_struct),
+ (void __user *)data);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state. */
+ return copy_regset_from_user(child, &user_mn10300_native_view,
+ REGSET_FPU,
+ 0, sizeof(struct fpu_state_struct),
+ (const void __user *)data);
default:
- ret = -EIO;
+ ret = ptrace_request(child, request, addr, data);
break;
}
}
/*
- * notification of system call entry/exit
- * - triggered by current->work.syscall_trace
+ * handle tracing of system call entry
+ * - return the revised system call number or ULONG_MAX to cause ENOSYS
*/
-asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
+asmlinkage unsigned long syscall_trace_entry(struct pt_regs *regs)
{
-#if 0
- /* just in case... */
- printk(KERN_DEBUG "[%d] syscall_%lu(%lx,%lx,%lx,%lx) = %lx\n",
- current->pid,
- regs->orig_d0,
- regs->a0,
- regs->d1,
- regs->a3,
- regs->a2,
- regs->d0);
- return;
-#endif
-
- if (!test_thread_flag(TIF_SYSCALL_TRACE) &&
- !test_thread_flag(TIF_SINGLESTEP))
- return;
- if (!(current->ptrace & PT_PTRACED))
- return;
+ if (tracehook_report_syscall_entry(regs))
+ /* tracing decided this syscall should not happen, so
+ * We'll return a bogus call number to get an ENOSYS
+ * error, but leave the original number in
+ * regs->orig_d0
+ */
+ return ULONG_MAX;
- /* the 0x80 provides a way for the tracing parent to distinguish
- between a syscall stop and SIGTRAP delivery */
- ptrace_notify(SIGTRAP |
- ((current->ptrace & PT_TRACESYSGOOD) &&
- !test_thread_flag(TIF_SINGLESTEP) ? 0x80 : 0));
+ return regs->orig_d0;
+}
- /*
- * this isn't the same as continuing with a signal, but it will do
- * for normal use. strace only continues with a signal if the
- * stopping signal is not SIGTRAP. -brl
- */
- if (current->exit_code) {
- send_sig(current->exit_code, current, 1);
- current->exit_code = 0;
- }
+/*
+ * handle tracing of system call exit
+ */
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+ tracehook_report_syscall_exit(regs, 0);
}
#include <linux/tty.h>
#include <linux/personality.h>
#include <linux/suspend.h>
+#include <linux/tracehook.h>
#include <asm/cacheflush.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
* clear the TIF_RESTORE_SIGMASK flag */
if (test_thread_flag(TIF_RESTORE_SIGMASK))
clear_thread_flag(TIF_RESTORE_SIGMASK);
+
+ tracehook_signal_handler(signr, &info, &ka, regs,
+ test_thread_flag(TIF_SINGLESTEP));
}
return;
/* deal with pending signal delivery */
if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK))
do_signal(regs);
+
+ if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(__frame);
+ }
}
ENTRY(dtlb_aerror)
and ~EPSW_NMID,epsw
add -4,sp
- mov d1,(sp)
-
- movhu (MMUFCR_DFC),d1 # is it the initial valid write
- # to this page?
- and MMUFCR_xFC_INITWR,d1
- beq dtlb_pagefault # jump if not
-
- mov (DPTEL),d1 # set the dirty bit
- # (don't replace with BSET!)
- or _PAGE_DIRTY,d1
- mov d1,(DPTEL)
- mov (sp),d1
- add 4,sp
- rti
-
- ALIGN
-dtlb_pagefault:
- mov (sp),d1
SAVE_ALL
add -4,sp # need to pass three params
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
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;
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;
}
/*
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,
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 = {
#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);
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)
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 */
#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 */
}
}
-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
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;
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)
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;
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)
--- /dev/null
+
+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/
+
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
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
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.
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.
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
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.
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
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
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
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-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
cpustr.h
mkcpustr
offsets.h
+voffset.h
+zoffset.h
setup
setup.bin
setup.elf
targets += fdimage fdimage144 fdimage288 image.iso mtools.conf
subdir- := compressed
-setup-y += a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o
+setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o edd.o
setup-y += header.o main.o mca.o memory.o pm.o pmjump.o
-setup-y += printf.o string.o tty.o video.o video-mode.o version.o
+setup-y += printf.o regs.o string.o tty.o video.o video-mode.o
+setup-y += version.o
setup-$(CONFIG_X86_APM_BOOT) += apm.o
# The link order of the video-*.o modules can matter. In particular,
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
*
* 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.
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)
*
* 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)
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));
-
- 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;
-
- if (err)
+ ireg.al = 0x03;
+ intcall(0x15, &ireg, &oreg);
+
+ 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 (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;
}
--- /dev/null
+/* -----------------------------------------------------------------------
+ *
+ * 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
*
* 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.
#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)]))
/* 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);
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);
relocs
vmlinux.bin.all
vmlinux.relocs
+vmlinux.lds
+mkpiggy
+piggy.S
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)
@:
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 $<
$(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)
-
-ifeq ($(CONFIG_X86_32),y)
+vmlinux.bin.all-$(CONFIG_X86_NEED_RELOCS) += $(obj)/vmlinux.relocs
-ifdef CONFIG_RELOCATABLE
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
- $(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin.all 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
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) 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)
-endif
-LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
-else
+suffix-$(CONFIG_KERNEL_GZIP) := gz
+suffix-$(CONFIG_KERNEL_BZIP2) := bz2
+suffix-$(CONFIG_KERNEL_LZMA) := lzma
-$(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)
-
-LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
-endif
+quiet_cmd_mkpiggy = MKPIGGY $@
+ cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
-suffix_$(CONFIG_KERNEL_GZIP) = gz
-suffix_$(CONFIG_KERNEL_BZIP2) = bz2
-suffix_$(CONFIG_KERNEL_LZMA) = lzma
-
-$(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)
* 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>
#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
-
-/* Copy the compressed kernel to the end of our buffer
+ /* Target address to relocate to for decompression */
+ addl $z_extract_offset, %ebx
+
+ /* 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
- */
- xorl %eax,%eax
- leal _edata(%ebx),%edi
- leal _end(%ebx), %ecx
- subl %edi,%ecx
- cld
- rep
- stosb
-
-/*
- * Setup the stack for the decompressor
+ * Clear BSS (stack is currently empty)
*/
- 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:
/*
* High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
*/
-.code32
-.text
+ .code32
+ .text
#include <linux/linkage.h>
#include <asm/segment.h>
#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
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
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
/*
* 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
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
#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.
.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.
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
-
-/* Copy the compressed kernel to the end of our buffer
+ /* Target address to relocate to for decompression */
+ leaq z_extract_offset(%rbp), %rbx
+
+ /* 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.
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
.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
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");
+#endif
#ifndef CONFIG_RELOCATABLE
- if ((u32)output != LOAD_PHYSICAL_ADDR)
+ if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
error("Wrong destination address");
-#endif
#endif
if (!quiet)
--- /dev/null
+/* ----------------------------------------------------------------------- *
+ *
+ * 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;
+}
--- /dev/null
+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
+ * 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 = . ;
+ }
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ .bss : {
+ _bss = . ;
+ *(.bss)
+ *(.bss.*)
+ *(COMMON)
+ . = ALIGN(8); /* For convenience during zeroing */
+ _ebss = .;
+ }
+#ifdef CONFIG_X86_64
+ . = ALIGN(PAGE_SIZE);
+ .pgtable : {
+ _pgtable = . ;
+ *(.pgtable)
+ _epgtable = . ;
+ }
+#endif
+ _end = .;
+}
+++ /dev/null
-SECTIONS
-{
- .rodata.compressed : {
- input_len = .;
- LONG(input_data_end - input_data) input_data = .;
- *(.data)
- output_len = . - 4;
- input_data_end = .;
- }
-}
+++ /dev/null
-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 = . ;
- }
-}
+++ /dev/null
-OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
-OUTPUT_ARCH(i386:x86-64)
-ENTRY(startup_64)
-SECTIONS
-{
- /* Be careful parts of head_64.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)
- . = ALIGN(8);
- _end_before_pgt = . ;
- . = ALIGN(4096);
- pgtable = . ;
- . = . + 4096 * 6;
- _ebss = .;
- }
-}
*
* 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.
*/
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)
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");
-
- 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;
+ ireg.ah = 0x08;
+ ireg.es = 0;
+ intcall(0x13, &ireg, &oreg);
+
+ 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;
#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 */
# 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
# 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.
#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,
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.
*
* 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.
*/
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);
}
/*
*/
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;
}
/*
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
}
*
* 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.
int query_mca(void)
{
- u8 err;
- u16 es, bx, len;
-
- asm("pushw %%es ; "
- "int $0x15 ; "
- "setc %0 ; "
- "movw %%es, %1 ; "
- "popw %%es"
- : "=acd" (err), "=acdSD" (es), "=b" (bx)
- : "a" (0xc000));
-
- if (err)
+ struct biosregs ireg, oreg;
+ u16 len;
+
+ initregs(&ireg);
+ ireg.ah = 0xc0;
+ intcall(0x15, &ireg, &oreg);
+
+ 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;
}
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
*/
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
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)
--- /dev/null
+/* -----------------------------------------------------------------------
+ *
+ * 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();
+}
. = 497;
.header : { *(.header) }
+ .entrytext : { *(.entrytext) }
.inittext : { *(.inittext) }
.initdata : { *(.initdata) }
+ __end_init = .;
+
.text : { *(.text) }
.text32 : { *(.text32) }
. = 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!");
+
}
*
* 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.
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++;
- }
}
/*
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;
}
/*
*/
int getchar(void)
{
- u16 ax = 0;
- asm volatile("int $0x16" : "+a" (ax));
+ struct biosregs ireg, oreg;
+
+ initregs(&ireg);
+ /* ireg.ah = 0x00; */
+ intcall(0x16, &ireg, &oreg);
- return ax & 0xff;
+ 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)
*
* 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.
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 */
/* 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;
*
* 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.
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;
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 */
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) {
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) {
}
- 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;
/* 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;
}
/*
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);
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 */
-
- /* 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");
+ 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);
- 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 */
}
*
* 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.
/* 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
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;
}
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();
}
*/
static int vga_probe(void)
{
- u16 ega_bx;
-
static const char *card_name[] = {
"CGA/MDA/HGC", "EGA", "VGA"
};
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;
*
* 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.
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;
}
/*
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 */
}
/* 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)
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)
{
#
# 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
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
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"
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
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
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
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
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
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
# 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
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
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
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
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
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
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
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
# 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
#
# Networking options
#
-CONFIG_COMPAT_NET_DEV_OPS=y
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=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
#
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
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
# 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
#
# 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
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
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
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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
#
# 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
# 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
# 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
#
# 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
#
# 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
# 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
# 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
#
# 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
# CONFIG_FUSE_FS is not set
CONFIG_GENERIC_ACL=y
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
#
# CD-ROM/DVD Filesystems
#
# 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
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
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
# 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
# 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
# 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
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_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
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
#
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
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
# CONFIG_CRYPTO_LZO is not set
#
# 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
# 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
#
# 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
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
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"
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
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
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
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
# 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
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
# 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
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
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
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
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
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
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
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
# 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
#
# Networking options
#
-CONFIG_COMPAT_NET_DEV_OPS=y
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=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
#
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
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
# 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
#
# 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
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
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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
# 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
#
# 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
# 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
# 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
#
# 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
#
# 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
# 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
# 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
#
# 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
# CONFIG_FUSE_FS is not set
CONFIG_GENERIC_ACL=y
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
#
# CD-ROM/DVD Filesystems
#
# 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
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
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
# 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
# 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
# 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
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
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
#
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
#
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
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
# CONFIG_CRYPTO_LZO is not set
#
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
# 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
.quad sys_inotify_init1
.quad compat_sys_preadv
.quad compat_sys_pwritev
+ .quad compat_sys_rt_tgsigqueueinfo /* 335 */
ia32_syscall_end:
#include <linux/types.h>
#include <linux/stddef.h>
+#include <linux/stringify.h>
#include <asm/asm.h>
/*
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.
*
* 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.
* 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
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) { }
#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
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
*/
unsigned long aperture_size;
/* address we start to search for free addresses */
- unsigned long next_bit;
-
- /* address allocation bitmap */
- unsigned long *bitmap;
+ unsigned long next_address;
- /*
- * 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;
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
/*
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)
{
return 1;
return 0;
}
+
+#define x2apic_supported() (cpu_has_x2apic)
#else
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 int get_physical_broadcast(void);
+extern void enable_IR_x2apic(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 int get_physical_broadcast(void);
+extern void apic_disable(void);
extern int lapic_get_maxlvt(void);
extern void clear_local_APIC(void);
extern void connect_bsp_APIC(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
{
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;
extern void default_setup_apic_routing(void);
#ifdef CONFIG_X86_32
+
+extern struct apic apic_default;
+
/*
* Set up the logical destination ID.
*
# 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
#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)
#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
#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 */
__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;
CPU_VALUE_BIT, /* value */
};
-#define CPU_FILE_VALUE (1 << CPU_VALUE_BIT)
-
-/*
- * DisplayFamily_DisplayModel Processor Families/Processor Number Series
- * -------------------------- ------------------------------------------
- * 05_01, 05_02, 05_04 Pentium, Pentium with MMX
- *
- * 06_01 Pentium Pro
- * 06_03, 06_05 Pentium II Xeon, Pentium II
- * 06_07, 06_08, 06_0A, 06_0B Pentium III Xeon, Pentum III
- *
- * 06_09, 060D Pentium M
- *
- * 06_0E Core Duo, Core Solo
- *
- * 06_0F Xeon 3000, 3200, 5100, 5300, 7300 series,
- * Core 2 Quad, Core 2 Extreme, Core 2 Duo,
- * Pentium dual-core
- * 06_17 Xeon 5200, 5400 series, Core 2 Quad Q9650
- *
- * 06_1C Atom
- *
- * 0F_00, 0F_01, 0F_02 Xeon, Xeon MP, Pentium 4
- * 0F_03, 0F_04 Xeon, Xeon MP, Pentium 4, Pentium D
- *
- * 0F_06 Xeon 7100, 5000 Series, Xeon MP,
- * Pentium 4, Pentium D
- */
-
-/* Register processors bits */
-enum cpu_processor_bit {
- CPU_NONE,
-/* Intel */
- CPU_INTEL_PENTIUM_BIT,
- CPU_INTEL_P6_BIT,
- CPU_INTEL_PENTIUM_M_BIT,
- CPU_INTEL_CORE_BIT,
- CPU_INTEL_CORE2_BIT,
- CPU_INTEL_ATOM_BIT,
- CPU_INTEL_XEON_P4_BIT,
- CPU_INTEL_XEON_MP_BIT,
-/* AMD */
- CPU_AMD_K6_BIT,
- CPU_AMD_K7_BIT,
- CPU_AMD_K8_BIT,
- CPU_AMD_0F_BIT,
- CPU_AMD_10_BIT,
- CPU_AMD_11_BIT,
-};
-
-#define CPU_INTEL_PENTIUM (1 << CPU_INTEL_PENTIUM_BIT)
-#define CPU_INTEL_P6 (1 << CPU_INTEL_P6_BIT)
-#define CPU_INTEL_PENTIUM_M (1 << CPU_INTEL_PENTIUM_M_BIT)
-#define CPU_INTEL_CORE (1 << CPU_INTEL_CORE_BIT)
-#define CPU_INTEL_CORE2 (1 << CPU_INTEL_CORE2_BIT)
-#define CPU_INTEL_ATOM (1 << CPU_INTEL_ATOM_BIT)
-#define CPU_INTEL_XEON_P4 (1 << CPU_INTEL_XEON_P4_BIT)
-#define CPU_INTEL_XEON_MP (1 << CPU_INTEL_XEON_MP_BIT)
-
-#define CPU_INTEL_PX (CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M)
-#define CPU_INTEL_COREX (CPU_INTEL_CORE | CPU_INTEL_CORE2)
-#define CPU_INTEL_XEON (CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP)
-#define CPU_CO_AT (CPU_INTEL_CORE | CPU_INTEL_ATOM)
-#define CPU_C2_AT (CPU_INTEL_CORE2 | CPU_INTEL_ATOM)
-#define CPU_CX_AT (CPU_INTEL_COREX | CPU_INTEL_ATOM)
-#define CPU_CX_XE (CPU_INTEL_COREX | CPU_INTEL_XEON)
-#define CPU_P6_XE (CPU_INTEL_P6 | CPU_INTEL_XEON)
-#define CPU_PM_CO_AT (CPU_INTEL_PENTIUM_M | CPU_CO_AT)
-#define CPU_C2_AT_XE (CPU_C2_AT | CPU_INTEL_XEON)
-#define CPU_CX_AT_XE (CPU_CX_AT | CPU_INTEL_XEON)
-#define CPU_P6_CX_AT (CPU_INTEL_P6 | CPU_CX_AT)
-#define CPU_P6_CX_XE (CPU_P6_XE | CPU_INTEL_COREX)
-#define CPU_P6_CX_AT_XE (CPU_INTEL_P6 | CPU_CX_AT_XE)
-#define CPU_PM_CX_AT_XE (CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE)
-#define CPU_PM_CX_AT (CPU_INTEL_PENTIUM_M | CPU_CX_AT)
-#define CPU_PM_CX_XE (CPU_INTEL_PENTIUM_M | CPU_CX_XE)
-#define CPU_PX_CX_AT (CPU_INTEL_PX | CPU_CX_AT)
-#define CPU_PX_CX_AT_XE (CPU_INTEL_PX | CPU_CX_AT_XE)
-
-/* Select all supported Intel CPUs */
-#define CPU_INTEL_ALL (CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE)
-
-#define CPU_AMD_K6 (1 << CPU_AMD_K6_BIT)
-#define CPU_AMD_K7 (1 << CPU_AMD_K7_BIT)
-#define CPU_AMD_K8 (1 << CPU_AMD_K8_BIT)
-#define CPU_AMD_0F (1 << CPU_AMD_0F_BIT)
-#define CPU_AMD_10 (1 << CPU_AMD_10_BIT)
-#define CPU_AMD_11 (1 << CPU_AMD_11_BIT)
-
-#define CPU_K10_PLUS (CPU_AMD_10 | CPU_AMD_11)
-#define CPU_K0F_PLUS (CPU_AMD_0F | CPU_K10_PLUS)
-#define CPU_K8_PLUS (CPU_AMD_K8 | CPU_K0F_PLUS)
-#define CPU_K7_PLUS (CPU_AMD_K7 | CPU_K8_PLUS)
-
-/* Select all supported AMD CPUs */
-#define CPU_AMD_ALL (CPU_AMD_K6 | CPU_K7_PLUS)
-
-/* Select all supported CPUs */
-#define CPU_ALL (CPU_INTEL_ALL | CPU_AMD_ALL)
+#define CPU_FILE_VALUE (1 << CPU_VALUE_BIT)
#define MAX_CPU_FILES 512
unsigned min; /* Register range min */
unsigned max; /* Register range max */
unsigned flag; /* Supported flags */
- unsigned model; /* Supported models */
};
#endif /* _ASM_X86_CPU_DEBUG_H */
#define X86_FEATURE_TSC (0*32+ 4) /* Time Stamp Counter */
#define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers */
#define X86_FEATURE_PAE (0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Exception */
#define X86_FEATURE_CX8 (0*32+ 8) /* CMPXCHG8 instruction */
#define X86_FEATURE_APIC (0*32+ 9) /* Onboard APIC */
#define X86_FEATURE_SEP (0*32+11) /* SYSENTER/SYSEXIT */
#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
#define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */
#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
#define clear_cpu_cap(c, bit) clear_bit(bit, (unsigned long *)((c)->x86_capability))
#define setup_clear_cpu_cap(bit) do { \
clear_cpu_cap(&boot_cpu_data, bit); \
- set_bit(bit, (unsigned long *)cleared_cpu_caps); \
+ set_bit(bit, (unsigned long *)cpu_caps_cleared); \
} while (0)
#define setup_force_cpu_cap(bit) do { \
set_cpu_cap(&boot_cpu_data, bit); \
- clear_bit(bit, (unsigned long *)cleared_cpu_caps); \
+ set_bit(bit, (unsigned long *)cpu_caps_set); \
} while (0)
#define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU)
* - buffer allocation (memory accounting)
*
*
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Copyright (C) 2007-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
*/
#ifndef _ASM_X86_DS_H
* The interrupt threshold is independent from the overflow callback
* to allow users to use their own overflow interrupt handling mechanism.
*
- * task: the task to request recording for;
- * NULL for per-cpu recording on the current cpu
+ * The function might sleep.
+ *
+ * task: the task to request recording for
+ * cpu: the cpu to request recording for
* base: the base pointer for the (non-pageable) buffer;
* size: the size of the provided buffer in bytes
* ovfl: pointer to a function to be called on buffer overflow;
* -1 if no interrupt threshold is requested.
* flags: a bit-mask of the above flags
*/
-extern struct bts_tracer *ds_request_bts(struct task_struct *task,
- void *base, size_t size,
- bts_ovfl_callback_t ovfl,
- size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs(struct task_struct *task,
- void *base, size_t size,
- pebs_ovfl_callback_t ovfl,
- size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
+ void *base, size_t size,
+ bts_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
+ bts_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
+ void *base, size_t size,
+ pebs_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
+ void *base, size_t size,
+ pebs_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags);
/*
* Release BTS or PEBS resources
* Suspend and resume BTS or PEBS tracing
*
+ * Must be called with irq's enabled.
+ *
* tracer: the tracer handle returned from ds_request_~()
*/
extern void ds_release_bts(struct bts_tracer *tracer);
extern void ds_suspend_pebs(struct pebs_tracer *tracer);
extern void ds_resume_pebs(struct pebs_tracer *tracer);
+/*
+ * Release BTS or PEBS resources
+ * Suspend and resume BTS or PEBS tracing
+ *
+ * Cpu tracers must call this on the traced cpu.
+ * Task tracers must call ds_release_~_noirq() for themselves.
+ *
+ * May be called with irq's disabled.
+ *
+ * Returns 0 if successful;
+ * -EPERM if the cpu tracer does not trace the current cpu.
+ * -EPERM if the task tracer does not trace itself.
+ *
+ * tracer: the tracer handle returned from ds_request_~()
+ */
+extern int ds_release_bts_noirq(struct bts_tracer *tracer);
+extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
+extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
+extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
+
/*
* The raw DS buffer state as it is used for BTS and PEBS recording.
} lbr;
/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
struct {
- __u64 jiffies;
+ __u64 clock;
pid_t pid;
- } timestamp;
+ } event;
} variant;
};
struct pebs_trace {
struct ds_trace ds;
- /* the PEBS reset value */
- unsigned long long reset_value;
+ /* the number of valid counters in the below array */
+ unsigned int counters;
+
+#define MAX_PEBS_COUNTERS 4
+ /* the counter reset value */
+ unsigned long long counter_reset[MAX_PEBS_COUNTERS];
};
* Returns 0 on success; -Eerrno on error
*
* tracer: the tracer handle returned from ds_request_pebs()
+ * counter: the index of the counter
* value: the new counter reset value
*/
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value);
+extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
+ unsigned int counter, u64 value);
/*
* Initialization
*/
extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
-/*
- * Task clone/init and cleanup work
- */
-extern void ds_copy_thread(struct task_struct *tsk, struct task_struct *father);
-extern void ds_exit_thread(struct task_struct *tsk);
-
#else /* CONFIG_X86_DS */
struct cpuinfo_x86;
static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
static inline void ds_switch_to(struct task_struct *prev,
struct task_struct *next) {}
-static inline void ds_copy_thread(struct task_struct *tsk,
- struct task_struct *father) {}
-static inline void ds_exit_thread(struct task_struct *tsk) {}
#endif /* CONFIG_X86_DS */
#endif /* _ASM_X86_DS_H */
extern void init_VISWS_APIC_irqs(void);
extern void setup_IO_APIC(void);
extern void disable_IO_APIC(void);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+
+struct io_apic_irq_attr {
+ int ioapic;
+ int ioapic_pin;
+ int trigger;
+ int polarity;
+};
+
+static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
+ int ioapic, int ioapic_pin,
+ int trigger, int polarity)
+{
+ irq_attr->ioapic = ioapic;
+ irq_attr->ioapic_pin = ioapic_pin;
+ irq_attr->trigger = trigger;
+ irq_attr->polarity = polarity;
+}
+
+extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin,
+ struct io_apic_irq_attr *irq_attr);
extern void setup_ioapic_dest(void);
extern void enable_IO_APIC(void);
/* SMP */
extern void smp_apic_timer_interrupt(struct pt_regs *);
extern void smp_spurious_interrupt(struct pt_regs *);
+extern void smp_generic_interrupt(struct pt_regs *);
extern void smp_error_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_IO_APIC
+extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
+#endif
#ifdef CONFIG_SMP
extern void smp_reschedule_interrupt(struct pt_regs *);
extern void smp_call_function_interrupt(struct pt_regs *);
".previous\n"
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err)
-#if 0 /* See comment in __save_init_fpu() below. */
+#if 0 /* See comment in fxsave() below. */
: [fx] "r" (fx), "m" (*fx), "0" (0));
#else
: [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
return err;
}
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
- if (task_thread_info(tsk)->status & TS_XSAVE)
- return xrstor_checking(&tsk->thread.xstate->xsave);
- else
- return fxrstor_checking(&tsk->thread.xstate->fxsave);
-}
-
/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
is pending. Clear the x87 state here by setting it to fixed
values. The kernel data segment can be sometimes 0 and sometimes
".previous\n"
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in __fxsave_clear() below. */
+#if 0 /* See comment in fxsave() below. */
: [fx] "r" (fx), "0" (0));
#else
: [fx] "cdaSDb" (fx), "0" (0));
asm volatile("fnclex ; fwait");
}
-static inline void restore_fpu(struct task_struct *tsk)
+/* perform fxrstor iff the processor has extended states, otherwise frstor */
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
{
- if (task_thread_info(tsk)->status & TS_XSAVE) {
- xrstor_checking(&tsk->thread.xstate->xsave);
- return;
- }
/*
* The "nop" is needed to make the instructions the same
* length.
"nop ; frstor %1",
"fxrstor %1",
X86_FEATURE_FXSR,
- "m" (tsk->thread.xstate->fxsave));
+ "m" (*fx));
+
+ return 0;
}
/* We need a safe address that is cheap to find and that is already
#endif /* CONFIG_X86_64 */
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+ if (task_thread_info(tsk)->status & TS_XSAVE)
+ return xrstor_checking(&tsk->thread.xstate->xsave);
+ else
+ return fxrstor_checking(&tsk->thread.xstate->fxsave);
+}
+
/*
* Signal frame handlers...
*/
/*
* Some instructions like VIA's padlock instructions generate a spurious
* DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context aswell. To prevent these kernel instructions
- * in interrupt context interact wrongly with other user/kernel fpu usage, we
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
* should use them only in the context of irq_ts_save/restore()
*/
static inline int irq_ts_save(void)
{
/*
- * If we are in process context, we are ok to take a spurious DNA fault.
- * Otherwise, doing clts() in process context require pre-emption to
- * be disabled or some heavy lifting like kernel_fpu_begin()
+ * If in process context and not atomic, we can take a spurious DNA fault.
+ * Otherwise, doing clts() in process context requires disabling preemption
+ * or some heavy lifting like kernel_fpu_begin()
*/
- if (!in_interrupt())
+ if (!in_atomic())
return 0;
if (read_cr0() & X86_CR0_TS) {
extern void mask_8259A(void);
extern void unmask_8259A(void);
-#ifdef CONFIG_X86_32
-extern void init_ISA_irqs(void);
-#endif
-
#endif /* _ASM_X86_I8259_H */
extern int io_apic_get_unique_id(int ioapic, int apic_id);
extern int io_apic_get_version(int ioapic);
extern int io_apic_get_redir_entries(int ioapic);
-extern int io_apic_set_pci_routing(int ioapic, int pin, int irq,
- int edge_level, int active_high_low);
#endif /* CONFIG_ACPI */
+struct io_apic_irq_attr;
+extern int io_apic_set_pci_routing(struct device *dev, int irq,
+ struct io_apic_irq_attr *irq_attr);
extern int (*ioapic_renumber_irq)(int ioapic, int irq);
extern void ioapic_init_mappings(void);
-#ifdef CONFIG_X86_64
extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
-extern void reinit_intr_remapped_IO_APIC(int intr_remapping,
- struct IO_APIC_route_entry **ioapic_entries);
-#endif
extern void probe_nr_irqs_gsi(void);
+#ifndef _ASM_X86_IOMAP_H
+#define _ASM_X86_IOMAP_H
+
/*
* Copyright © 2008 Ingo Molnar
*
void
iounmap_atomic(void *kvaddr, enum km_type type);
+
+#endif /* _ASM_X86_IOMAP_H */
#ifndef _ASM_X86_IRQ_REMAPPING_H
#define _ASM_X86_IRQ_REMAPPING_H
-#define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
+#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
#endif /* _ASM_X86_IRQ_REMAPPING_H */
#ifdef CONFIG_X86_32
# define SYSCALL_VECTOR 0x80
+# define IA32_SYSCALL_VECTOR 0x80
#else
# define IA32_SYSCALL_VECTOR 0x80
#endif
extern void k8_flush_garts(void);
extern int k8_scan_nodes(unsigned long start, unsigned long end);
+#ifdef CONFIG_K8_NB
+static inline struct pci_dev *node_to_k8_nb_misc(int node)
+{
+ return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
+}
+#else
+static inline struct pci_dev *node_to_k8_nb_misc(int node)
+{
+ return NULL;
+}
+#endif
+
+
#endif /* _ASM_X86_K8_H */
struct device;
+enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+
struct microcode_ops {
- int (*request_microcode_user) (int cpu, const void __user *buf, size_t size);
- int (*request_microcode_fw) (int cpu, struct device *device);
+ enum ucode_state (*request_microcode_user) (int cpu,
+ const void __user *buf, size_t size);
- void (*apply_microcode) (int cpu);
+ enum ucode_state (*request_microcode_fw) (int cpu,
+ struct device *device);
- int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
void (*microcode_fini_cpu) (int cpu);
+
+ /*
+ * The generic 'microcode_core' part guarantees that
+ * the callbacks below run on a target cpu when they
+ * are being called.
+ * See also the "Synchronization" section in microcode_core.c.
+ */
+ int (*apply_microcode) (int cpu);
+ int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
};
struct ucode_cpu_info {
- struct cpu_signature cpu_sig;
- int valid;
- void *mc;
+ struct cpu_signature cpu_sig;
+ int valid;
+ void *mc;
};
extern struct ucode_cpu_info ucode_cpu_info[];
#ifdef CONFIG_X86_MPPARSE
extern void find_smp_config(void);
extern void early_reserve_e820_mpc_new(void);
+extern int enable_update_mptable;
#else
static inline void find_smp_config(void) { }
static inline void early_reserve_e820_mpc_new(void) { }
+#define enable_update_mptable 0
#endif
void __cpuinit generic_processor_info(int apicid, int version);
extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
u32 gsi);
extern void mp_config_acpi_legacy_irqs(void);
-extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+struct device;
+extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level,
+ int active_high_low);
extern int acpi_probe_gsi(void);
#ifdef CONFIG_X86_IO_APIC
-extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
- u32 gsi, int triggering, int polarity);
extern int mp_find_ioapic(int gsi);
extern int mp_find_ioapic_pin(int ioapic, int gsi);
-#else
-static inline int
-mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
- u32 gsi, int triggering, int polarity)
-{
- return 0;
-}
#endif
#else /* !CONFIG_ACPI: */
static inline int acpi_probe_gsi(void)
#define MSR_K8_TOP_MEM1 0xc001001a
#define MSR_K8_TOP_MEM2 0xc001001d
#define MSR_K8_SYSCFG 0xc0010010
-#define MSR_K8_HWCR 0xc0010015
#define MSR_K8_INT_PENDING_MSG 0xc0010055
/* C1E active bits in int pending message */
#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
* but since they are power of two we could use a
* cheaper way --cvg
*/
- return nmi_watchdog & 0x3;
+ return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC);
}
#endif
extern void numa_init_array(void);
extern int numa_off;
-extern void srat_reserve_add_area(int nodeid);
-extern int hotadd_percent;
-
extern s16 apicid_to_node[MAX_LOCAL_APIC];
extern unsigned long numa_free_all_bootmem(void);
unsigned long end);
#ifdef CONFIG_NUMA
+/*
+ * Too small node sizes may confuse the VM badly. Usually they
+ * result from BIOS bugs. So dont recognize nodes as standalone
+ * NUMA entities that have less than this amount of RAM listed:
+ */
+#define NODE_MIN_SIZE (4*1024*1024)
+
extern void __init init_cpu_to_node(void);
extern void __cpuinit numa_set_node(int cpu, int node);
extern void __cpuinit numa_clear_node(int cpu);
extern int sysctl_legacy_va_layout;
extern void find_low_pfn_range(void);
-extern unsigned long init_memory_mapping(unsigned long start,
- unsigned long end);
-extern void initmem_init(unsigned long, unsigned long);
-extern void free_initmem(void);
extern void setup_bootmem_allocator(void);
#endif /* !__ASSEMBLY__ */
*/
#define __PAGE_OFFSET _AC(0xffff880000000000, UL)
-#define __PHYSICAL_START CONFIG_PHYSICAL_START
-#define __KERNEL_ALIGN 0x200000
-
-/*
- * Make sure kernel is aligned to 2MB address. Catching it at compile
- * time is better. Change your config file and compile the kernel
- * for a 2MB aligned address (CONFIG_PHYSICAL_START)
- */
-#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
-#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
-#endif
+#define __PHYSICAL_START ((CONFIG_PHYSICAL_START + \
+ (CONFIG_PHYSICAL_ALIGN - 1)) & \
+ ~(CONFIG_PHYSICAL_ALIGN - 1))
#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START)
#define __START_KERNEL_map _AC(0xffffffff80000000, UL)
-/* See Documentation/x86_64/mm.txt for a description of the memory map. */
+/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
#define __PHYSICAL_MASK_SHIFT 46
#define __VIRTUAL_MASK_SHIFT 48
#define vmemmap ((struct page *)VMEMMAP_START)
-extern unsigned long init_memory_mapping(unsigned long start,
- unsigned long end);
-
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
-extern void free_initmem(void);
-
extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
extern unsigned long max_low_pfn_mapped;
extern unsigned long max_pfn_mapped;
+extern unsigned long init_memory_mapping(unsigned long start,
+ unsigned long end);
+
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void free_initmem(void);
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_PAGE_DEFS_H */
struct tss_struct;
struct mm_struct;
struct desc_struct;
+struct task_struct;
/*
* Wrapper type for pointers to code which uses the non-standard
void (*swapgs)(void);
- struct pv_lazy_ops lazy_mode;
+ void (*start_context_switch)(struct task_struct *prev);
+ void (*end_context_switch)(struct task_struct *next);
};
struct pv_irq_ops {
};
enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
void paravirt_enter_lazy_mmu(void);
void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
-#define __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
+#define __HAVE_ARCH_START_CONTEXT_SWITCH
+static inline void arch_start_context_switch(struct task_struct *prev)
{
- PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+ PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
}
-static inline void arch_leave_lazy_cpu_mode(void)
+static inline void arch_end_context_switch(struct task_struct *next)
{
- PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+ PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
}
-void arch_flush_lazy_cpu_mode(void);
-
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
{
#define pte_val(x) native_pte_val(x)
#define __pte(x) native_make_pte(x)
+#define arch_end_context_switch(prev) do {} while(0)
+
#endif /* CONFIG_PARAVIRT */
/*
#ifndef __ASSEMBLY__
+extern int direct_gbpages;
+
/* local pte updates need not use xchg for locking */
static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
{
extern void paging_init(void);
-#endif /* !__ASSEMBLY__ */
-
-#ifndef __ASSEMBLY__
-
#define pte_ERROR(e) \
printk("%s:%d: bad pte %p(%016lx).\n", \
__FILE__, __LINE__, &(e), pte_val(e))
#define update_mmu_cache(vma, address, pte) do { } while (0)
-extern int direct_gbpages;
-
/* Encode and de-code a swap entry */
#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
-
+/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
-#define VMALLOC_START _AC(0xffffc20000000000, UL)
-#define VMALLOC_END _AC(0xffffe1ffffffffff, UL)
-#define VMEMMAP_START _AC(0xffffe20000000000, UL)
+#define VMALLOC_START _AC(0xffffc90000000000, UL)
+#define VMALLOC_END _AC(0xffffe8ffffffffff, UL)
+#define VMEMMAP_START _AC(0xffffea0000000000, UL)
#define MODULES_VADDR _AC(0xffffffffa0000000, UL)
#define MODULES_END _AC(0xffffffffff000000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
extern pteval_t __supported_pte_mask;
extern int nx_enabled;
-extern void set_nx(void);
#define pgprot_writecombine pgprot_writecombine
extern pgprot_t pgprot_writecombine(pgprot_t prot);
extern struct cpuinfo_x86 new_cpu_data;
extern struct tss_struct doublefault_tss;
-extern __u32 cleared_cpu_caps[NCAPINTS];
+extern __u32 cpu_caps_cleared[NCAPINTS];
+extern __u32 cpu_caps_set[NCAPINTS];
#ifdef CONFIG_SMP
DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
extern unsigned int xstate_size;
extern void free_thread_xstate(struct task_struct *);
extern struct kmem_cache *task_xstate_cachep;
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern unsigned short num_cache_leaves;
struct thread_struct {
/* Cached TLS descriptors: */
unsigned short fsindex;
unsigned short gsindex;
#endif
+#ifdef CONFIG_X86_32
unsigned long ip;
+#endif
+#ifdef CONFIG_X86_64
unsigned long fs;
+#endif
unsigned long gs;
/* Hardware debugging registers: */
unsigned long debugreg0;
unsigned io_bitmap_max;
/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set. */
unsigned long debugctlmsr;
-#ifdef CONFIG_X86_DS
-/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
+ /* Debug Store context; see asm/ds.h */
struct ds_context *ds_ctx;
-#endif /* CONFIG_X86_DS */
-#ifdef CONFIG_X86_PTRACE_BTS
-/* the signal to send on a bts buffer overflow */
- unsigned int bts_ovfl_signal;
-#endif /* CONFIG_X86_PTRACE_BTS */
};
static inline unsigned long native_get_debugreg(int regno)
return debugctlmsr;
}
+static inline unsigned long get_debugctlmsr_on_cpu(int cpu)
+{
+ u64 debugctlmsr = 0;
+ u32 val1, val2;
+
+#ifndef CONFIG_X86_DEBUGCTLMSR
+ if (boot_cpu_data.x86 < 6)
+ return 0;
+#endif
+ rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2);
+ debugctlmsr = val1 | ((u64)val2 << 32);
+
+ return debugctlmsr;
+}
+
static inline void update_debugctlmsr(unsigned long debugctlmsr)
{
#ifndef CONFIG_X86_DEBUGCTLMSR
wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
}
+static inline void update_debugctlmsr_on_cpu(int cpu,
+ unsigned long debugctlmsr)
+{
+#ifndef CONFIG_X86_DEBUGCTLMSR
+ if (boot_cpu_data.x86 < 6)
+ return;
+#endif
+ wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR,
+ (u32)((u64)debugctlmsr),
+ (u32)((u64)debugctlmsr >> 32));
+}
+
/*
* from system description table in BIOS. Mostly for MCA use, but
* others may find it useful:
/* Boot loader type from the setup header: */
extern int bootloader_type;
+extern int bootloader_version;
extern char ignore_fpu_irq;
.vm86_info = NULL, \
.sysenter_cs = __KERNEL_CS, \
.io_bitmap_ptr = NULL, \
- .fs = __KERNEL_PERCPU, \
}
/*
extern int do_set_thread_area(struct task_struct *p, int idx,
struct user_desc __user *info, int can_allocate);
-extern void x86_ptrace_untrace(struct task_struct *);
-extern void x86_ptrace_fork(struct task_struct *child,
- unsigned long clone_flags);
+#ifdef CONFIG_X86_PTRACE_BTS
+extern void ptrace_bts_untrace(struct task_struct *tsk);
-#define arch_ptrace_untrace(tsk) x86_ptrace_untrace(tsk)
-#define arch_ptrace_fork(child, flags) x86_ptrace_fork(child, flags)
+#define arch_ptrace_untrace(tsk) ptrace_bts_untrace(tsk)
+#endif /* CONFIG_X86_PTRACE_BTS */
#endif /* __KERNEL__ */
#endif
#ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT
+/* Paravirtualized systems may not have PSE or PGE available */
#define NEED_PSE 0
-#define NEED_MSR (1<<(X86_FEATURE_MSR & 31))
#define NEED_PGE 0
+#else
+#define NEED_PSE (1<<(X86_FEATURE_PSE) & 31)
+#define NEED_PGE (1<<(X86_FEATURE_PGE) & 31)
+#endif
+#define NEED_MSR (1<<(X86_FEATURE_MSR & 31))
#define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31))
#define NEED_XMM (1<<(X86_FEATURE_XMM & 31))
#define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31))
int (*setup_ioapic_ids)(void);
};
-extern void x86_quirk_pre_intr_init(void);
extern void x86_quirk_intr_init(void);
extern void x86_quirk_trap_init(void);
static inline int logical_smp_processor_id(void)
{
/* we don't want to mark this access volatile - bad code generation */
- return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
+ return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
}
#endif
#else /* CONFIG_X86_32 */
# define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */
# define MAX_PHYSADDR_BITS 44
-# define MAX_PHYSMEM_BITS 44 /* Can be max 45 bits */
+# define MAX_PHYSMEM_BITS 46
#endif
#endif /* CONFIG_SPARSEMEM */
/*
* syscalls.h - Linux syscall interfaces (arch-specific)
*
- * Copyright (c) 2008 Jaswinder Singh
+ * Copyright (c) 2008 Jaswinder Singh Rajput
*
* This file is released under the GPLv2.
* See the file COPYING for more details.
#include <linux/compiler.h>
#include <linux/linkage.h>
-#include <linux/types.h>
#include <linux/signal.h>
+#include <linux/types.h>
/* Common in X86_32 and X86_64 */
/* kernel/ioport.c */
asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
+/* kernel/process.c */
+int sys_fork(struct pt_regs *);
+int sys_vfork(struct pt_regs *);
+
/* kernel/ldt.c */
asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+/* kernel/signal.c */
+long sys_rt_sigreturn(struct pt_regs *);
+
/* kernel/tls.c */
asmlinkage int sys_set_thread_area(struct user_desc __user *);
asmlinkage int sys_get_thread_area(struct user_desc __user *);
/* X86_32 only */
#ifdef CONFIG_X86_32
+/* kernel/ioport.c */
+long sys_iopl(struct pt_regs *);
+
/* kernel/process_32.c */
-int sys_fork(struct pt_regs *);
int sys_clone(struct pt_regs *);
-int sys_vfork(struct pt_regs *);
int sys_execve(struct pt_regs *);
-/* kernel/signal_32.c */
+/* kernel/signal.c */
asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
struct old_sigaction __user *);
int sys_sigaltstack(struct pt_regs *);
unsigned long sys_sigreturn(struct pt_regs *);
-long sys_rt_sigreturn(struct pt_regs *);
-
-/* kernel/ioport.c */
-long sys_iopl(struct pt_regs *);
/* kernel/sys_i386_32.c */
+struct mmap_arg_struct;
+struct sel_arg_struct;
+struct oldold_utsname;
+struct old_utsname;
+
asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
unsigned long, unsigned long, unsigned long);
-struct mmap_arg_struct;
asmlinkage int old_mmap(struct mmap_arg_struct __user *);
-struct sel_arg_struct;
asmlinkage int old_select(struct sel_arg_struct __user *);
asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
-struct old_utsname;
asmlinkage int sys_uname(struct old_utsname __user *);
-struct oldold_utsname;
asmlinkage int sys_olduname(struct oldold_utsname __user *);
/* kernel/vm86_32.c */
#else /* CONFIG_X86_32 */
/* X86_64 only */
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
+
/* kernel/process_64.c */
-asmlinkage long sys_fork(struct pt_regs *);
asmlinkage long sys_clone(unsigned long, unsigned long,
void __user *, void __user *,
struct pt_regs *);
-asmlinkage long sys_vfork(struct pt_regs *);
asmlinkage long sys_execve(char __user *, char __user * __user *,
char __user * __user *,
struct pt_regs *);
long sys_arch_prctl(int, unsigned long);
-/* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
-
-/* kernel/signal_64.c */
+/* kernel/signal.c */
asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
struct pt_regs *);
-long sys_rt_sigreturn(struct pt_regs *);
/* kernel/sys_x86_64.c */
+struct new_utsname;
+
asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
unsigned long, unsigned long, unsigned long);
-struct new_utsname;
asmlinkage long sys_uname(struct new_utsname __user *);
#endif /* CONFIG_X86_32 */
SET_LOW_TERMIOS_BITS(termios, termio, c_oflag);
SET_LOW_TERMIOS_BITS(termios, termio, c_cflag);
SET_LOW_TERMIOS_BITS(termios, termio, c_lflag);
+ get_user(termios->c_line, &termio->c_line);
return copy_from_user(termios->c_cc, termio->c_cc, NCC);
}
#define TIF_FORCED_TF 24 /* true if TF in eflags artificially */
#define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */
#define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */
-#define TIF_SYSCALL_FTRACE 27 /* for ftrace syscall instrumentation */
+#define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */
+#define TIF_SYSCALL_FTRACE 28 /* for ftrace syscall instrumentation */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_FORCED_TF (1 << TIF_FORCED_TF)
#define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR)
#define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR)
+#define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES)
#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE)
/* work to do in syscall_trace_enter() */
static inline void __native_flush_tlb(void)
{
- write_cr3(read_cr3());
+ native_write_cr3(native_read_cr3());
}
static inline void __native_flush_tlb_global(void)
*/
raw_local_irq_save(flags);
- cr4 = read_cr4();
+ cr4 = native_read_cr4();
/* clear PGE */
- write_cr4(cr4 & ~X86_CR4_PGE);
+ native_write_cr4(cr4 & ~X86_CR4_PGE);
/* write old PGE again and flush TLBs */
- write_cr4(cr4);
+ native_write_cr4(cr4);
raw_local_irq_restore(flags);
}
void x86_pci_root_bus_res_quirks(struct pci_bus *b);
#ifdef CONFIG_SMP
-#define mc_capable() (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable() ((boot_cpu_data.x86_max_cores > 1) && \
+ (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
#define smt_capable() (smp_num_siblings > 1)
#endif
#define _ASM_X86_TRAPS_H
#include <asm/debugreg.h>
+#include <asm/siginfo.h> /* TRAP_TRACE, ... */
#ifdef CONFIG_X86_32
#define dotraplinkage
asmlinkage void debug(void);
asmlinkage void nmi(void);
asmlinkage void int3(void);
+asmlinkage void xen_debug(void);
+asmlinkage void xen_int3(void);
+asmlinkage void xen_stack_segment(void);
asmlinkage void overflow(void);
asmlinkage void bounds(void);
asmlinkage void invalid_op(void);
}
extern int panic_on_unrecovered_nmi;
-extern int kstack_depth_to_print;
void math_error(void __user *);
void math_emulate(struct math_emu_info *);
#define __NR_inotify_init1 332
#define __NR_preadv 333
#define __NR_pwritev 334
+#define __NR_rt_tgsigqueueinfo 335
#ifdef __KERNEL__
__SYSCALL(__NR_preadv, sys_preadv)
#define __NR_pwritev 296
__SYSCALL(__NR_pwritev, sys_pwritev)
+#define __NR_rt_tgsigqueueinfo 297
+__SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
#ifndef __NO_STUBS
#define UV_CPUS_PER_ACT_STATUS 32
#define UV_ACT_STATUS_MASK 0x3
#define UV_ACT_STATUS_SIZE 2
-#define UV_ACTIVATION_DESCRIPTOR_SIZE 32
+#define UV_ADP_SIZE 32
#define UV_DISTRIBUTION_SIZE 256
#define UV_SW_ACK_NPENDING 8
#define UV_NET_ENDPOINT_INTD 0x38
struct uv_hub_info_s {
unsigned long global_mmr_base;
unsigned long gpa_mask;
+ unsigned int gnode_extra;
unsigned long gnode_upper;
unsigned long lowmem_remap_top;
unsigned long lowmem_remap_base;
* p - PNODE (local part of nsids, right shifted 1)
*/
#define UV_NASID_TO_PNODE(n) (((n) >> 1) & uv_hub_info->pnode_mask)
-#define UV_PNODE_TO_NASID(p) (((p) << 1) | uv_hub_info->gnode_upper)
+#define UV_PNODE_TO_GNODE(p) ((p) |uv_hub_info->gnode_extra)
+#define UV_PNODE_TO_NASID(p) (UV_PNODE_TO_GNODE(p) << 1)
#define UV_LOCAL_MMR_BASE 0xf4000000UL
#define UV_GLOBAL_MMR32_BASE 0xf8000000UL
#define UV_GLOBAL_MMR32_PNODE_BITS(p) ((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
#define UV_GLOBAL_MMR64_PNODE_BITS(p) \
- ((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+ ((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
#define UV_APIC_PNODE_SHIFT 6
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y += setup.o i8259.o irqinit_$(BITS).o
+obj-y += setup.o i8259.o irqinit.o
obj-$(CONFIG_X86_VISWS) += visws_quirks.o
obj-$(CONFIG_X86_32) += probe_roms_32.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
obj-$(CONFIG_X86_DS) += ds.o
+obj-$(CONFIG_X86_DS_SELFTEST) += ds_selftest.o
obj-$(CONFIG_X86_32) += tls.o
obj-$(CONFIG_IA32_EMULATION) += tls.o
obj-y += step.o
#include <linux/irq.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
+#include <linux/pci.h>
#include <asm/pgtable.h>
#include <asm/io_apic.h>
* 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 trigger, int polarity)
{
unsigned int irq;
unsigned int plat_gsi = gsi;
* Make sure all (legacy) PCI IRQs are set as level-triggered.
*/
if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
- if (triggering == ACPI_LEVEL_SENSITIVE)
+ if (trigger == ACPI_LEVEL_SENSITIVE)
eisa_set_level_irq(gsi);
}
#endif
#ifdef CONFIG_X86_IO_APIC
if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) {
- plat_gsi = mp_register_gsi(gsi, triggering, polarity);
+ plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity);
}
#endif
acpi_gsi_to_irq(plat_gsi, &irq);
#endif
static struct {
- int apic_id;
int gsi_base;
int gsi_end;
- DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
} mp_ioapic_routing[MAX_IO_APICS];
int mp_find_ioapic(int gsi)
set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
mp_ioapics[idx].apicid = uniq_ioapic_id(id);
-#ifdef CONFIG_X86_32
mp_ioapics[idx].apicver = io_apic_get_version(idx);
-#else
- mp_ioapics[idx].apicver = 0;
-#endif
+
/*
* Build basic GSI lookup table to facilitate gsi->io_apic lookups
* and to prevent reprogramming of IOAPIC pins (PCI GSIs).
*/
- mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].apicid;
mp_ioapic_routing[idx].gsi_base = gsi_base;
mp_ioapic_routing[idx].gsi_end = gsi_base +
io_apic_get_redir_entries(idx);
}
}
-int mp_register_gsi(u32 gsi, int triggering, int polarity)
+static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
+ int polarity)
{
+#ifdef CONFIG_X86_MPPARSE
+ struct mpc_intsrc mp_irq;
+ struct pci_dev *pdev;
+ unsigned char number;
+ unsigned int devfn;
int ioapic;
- int ioapic_pin;
-#ifdef CONFIG_X86_32
-#define MAX_GSI_NUM 4096
-#define IRQ_COMPRESSION_START 64
+ u8 pin;
- static int pci_irq = IRQ_COMPRESSION_START;
- /*
- * Mapping between Global System Interrupts, which
- * represent all possible interrupts, and IRQs
- * assigned to actual devices.
- */
- static int gsi_to_irq[MAX_GSI_NUM];
-#else
+ if (!acpi_ioapic)
+ return 0;
+ if (!dev)
+ return 0;
+ if (dev->bus != &pci_bus_type)
+ return 0;
+
+ pdev = to_pci_dev(dev);
+ number = pdev->bus->number;
+ devfn = pdev->devfn;
+ pin = pdev->pin;
+ /* print the entry should happen on mptable identically */
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+ (polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+ mp_irq.srcbus = number;
+ mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+ ioapic = mp_find_ioapic(gsi);
+ mp_irq.dstapic = mp_ioapics[ioapic].apicid;
+ mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
+
+ save_mp_irq(&mp_irq);
+#endif
+ return 0;
+}
+
+int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
+{
+ int ioapic;
+ int ioapic_pin;
+ struct io_apic_irq_attr irq_attr;
if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
return gsi;
-#endif
/* Don't set up the ACPI SCI because it's already set up */
if (acpi_gbl_FADT.sci_interrupt == gsi)
gsi = ioapic_renumber_irq(ioapic, gsi);
#endif
- /*
- * Avoid pin reprogramming. PRTs typically include entries
- * with redundant pin->gsi mappings (but unique PCI devices);
- * we only program the IOAPIC on the first.
- */
if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
printk(KERN_ERR "Invalid reference to IOAPIC pin "
- "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+ "%d-%d\n", mp_ioapics[ioapic].apicid,
ioapic_pin);
return gsi;
}
- if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
- pr_debug("Pin %d-%d already programmed\n",
- mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-#ifdef CONFIG_X86_32
- return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
-#else
- return gsi;
-#endif
- }
-
- set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
-#ifdef CONFIG_X86_32
- /*
- * For GSI >= 64, use IRQ compression
- */
- if ((gsi >= IRQ_COMPRESSION_START)
- && (triggering == ACPI_LEVEL_SENSITIVE)) {
- /*
- * For PCI devices assign IRQs in order, avoiding gaps
- * due to unused I/O APIC pins.
- */
- int irq = gsi;
- if (gsi < MAX_GSI_NUM) {
- /*
- * Retain the VIA chipset work-around (gsi > 15), but
- * avoid a problem where the 8254 timer (IRQ0) is setup
- * via an override (so it's not on pin 0 of the ioapic),
- * and at the same time, the pin 0 interrupt is a PCI
- * type. The gsi > 15 test could cause these two pins
- * to be shared as IRQ0, and they are not shareable.
- * So test for this condition, and if necessary, avoid
- * the pin collision.
- */
- gsi = pci_irq++;
- /*
- * Don't assign IRQ used by ACPI SCI
- */
- if (gsi == acpi_gbl_FADT.sci_interrupt)
- gsi = pci_irq++;
- gsi_to_irq[irq] = gsi;
- } else {
- printk(KERN_ERR "GSI %u is too high\n", gsi);
- return gsi;
- }
- }
-#endif
- io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
- triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
- polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
- return gsi;
-}
-int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
- u32 gsi, int triggering, int polarity)
-{
-#ifdef CONFIG_X86_MPPARSE
- struct mpc_intsrc mp_irq;
- int ioapic;
+ if (enable_update_mptable)
+ mp_config_acpi_gsi(dev, gsi, trigger, polarity);
- if (!acpi_ioapic)
- return 0;
+ set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
+ trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
+ polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+ io_apic_set_pci_routing(dev, gsi, &irq_attr);
- /* print the entry should happen on mptable identically */
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
- mp_irq.irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
- (polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
- mp_irq.srcbus = number;
- mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
- ioapic = mp_find_ioapic(gsi);
- mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
- mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
-
- save_mp_irq(&mp_irq);
-#endif
- return 0;
+ return gsi;
}
/*
always := wakeup.bin
targets := wakeup.elf wakeup.lds
-wakeup-y += wakeup.o wakemain.o video-mode.o copy.o
+wakeup-y += wakeup.o wakemain.o video-mode.o copy.o bioscall.o regs.o
# The link order of the video-*.o modules can matter. In particular,
# video-vga.o *must* be listed first, followed by video-vesa.o.
--- /dev/null
+#include "../../../boot/bioscall.S"
--- /dev/null
+#include "../../../boot/regs.c"
static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
struct unity_map_entry *e);
static struct dma_ops_domain *find_protection_domain(u16 devid);
+static u64* alloc_pte(struct protection_domain *dom,
+ unsigned long address, u64
+ **pte_page, gfp_t gfp);
+static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
+ unsigned long start_page,
+ unsigned int pages);
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
#ifdef CONFIG_AMD_IOMMU_STATS
{
struct amd_iommu *iommu;
- list_for_each_entry(iommu, &amd_iommu_list, list)
+ for_each_iommu(iommu)
iommu_poll_events(iommu);
return IRQ_HANDLED;
__iommu_build_inv_iommu_pages(&cmd, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
domid, 1, 1);
- list_for_each_entry(iommu, &amd_iommu_list, list) {
+ for_each_iommu(iommu) {
spin_lock_irqsave(&iommu->lock, flags);
__iommu_queue_command(iommu, &cmd);
__iommu_completion_wait(iommu);
}
}
+void amd_iommu_flush_all_domains(void)
+{
+ int i;
+
+ for (i = 1; i < MAX_DOMAIN_ID; ++i) {
+ if (!test_bit(i, amd_iommu_pd_alloc_bitmap))
+ continue;
+ iommu_flush_domain(i);
+ }
+}
+
+void amd_iommu_flush_all_devices(void)
+{
+ struct amd_iommu *iommu;
+ int i;
+
+ for (i = 0; i <= amd_iommu_last_bdf; ++i) {
+ if (amd_iommu_pd_table[i] == NULL)
+ continue;
+
+ iommu = amd_iommu_rlookup_table[i];
+ if (!iommu)
+ continue;
+
+ iommu_queue_inv_dev_entry(iommu, i);
+ iommu_completion_wait(iommu);
+ }
+}
+
/****************************************************************************
*
* The functions below are used the create the page table mappings for
unsigned long phys_addr,
int prot)
{
- u64 __pte, *pte, *page;
+ u64 __pte, *pte;
bus_addr = PAGE_ALIGN(bus_addr);
phys_addr = PAGE_ALIGN(phys_addr);
if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
return -EINVAL;
- pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(bus_addr)];
-
- if (!IOMMU_PTE_PRESENT(*pte)) {
- page = (u64 *)get_zeroed_page(GFP_KERNEL);
- if (!page)
- return -ENOMEM;
- *pte = IOMMU_L2_PDE(virt_to_phys(page));
- }
-
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)];
-
- if (!IOMMU_PTE_PRESENT(*pte)) {
- page = (u64 *)get_zeroed_page(GFP_KERNEL);
- if (!page)
- return -ENOMEM;
- *pte = IOMMU_L1_PDE(virt_to_phys(page));
- }
-
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[IOMMU_PTE_L0_INDEX(bus_addr)];
+ pte = alloc_pte(dom, bus_addr, NULL, GFP_KERNEL);
if (IOMMU_PTE_PRESENT(*pte))
return -EBUSY;
* as allocated in the aperture
*/
if (addr < dma_dom->aperture_size)
- __set_bit(addr >> PAGE_SHIFT, dma_dom->bitmap);
+ __set_bit(addr >> PAGE_SHIFT,
+ dma_dom->aperture[0]->bitmap);
}
return 0;
****************************************************************************/
/*
- * The address allocator core function.
+ * The address allocator core functions.
*
* called with domain->lock held
*/
+
+/*
+ * This function checks if there is a PTE for a given dma address. If
+ * there is one, it returns the pointer to it.
+ */
+static u64* fetch_pte(struct protection_domain *domain,
+ unsigned long address)
+{
+ u64 *pte;
+
+ pte = &domain->pt_root[IOMMU_PTE_L2_INDEX(address)];
+
+ if (!IOMMU_PTE_PRESENT(*pte))
+ return NULL;
+
+ pte = IOMMU_PTE_PAGE(*pte);
+ pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+
+ if (!IOMMU_PTE_PRESENT(*pte))
+ return NULL;
+
+ pte = IOMMU_PTE_PAGE(*pte);
+ pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+
+ return pte;
+}
+
+/*
+ * This function is used to add a new aperture range to an existing
+ * aperture in case of dma_ops domain allocation or address allocation
+ * failure.
+ */
+static int alloc_new_range(struct amd_iommu *iommu,
+ struct dma_ops_domain *dma_dom,
+ bool populate, gfp_t gfp)
+{
+ int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
+ int i;
+
+#ifdef CONFIG_IOMMU_STRESS
+ populate = false;
+#endif
+
+ if (index >= APERTURE_MAX_RANGES)
+ return -ENOMEM;
+
+ dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range), gfp);
+ if (!dma_dom->aperture[index])
+ return -ENOMEM;
+
+ dma_dom->aperture[index]->bitmap = (void *)get_zeroed_page(gfp);
+ if (!dma_dom->aperture[index]->bitmap)
+ goto out_free;
+
+ dma_dom->aperture[index]->offset = dma_dom->aperture_size;
+
+ if (populate) {
+ unsigned long address = dma_dom->aperture_size;
+ int i, num_ptes = APERTURE_RANGE_PAGES / 512;
+ u64 *pte, *pte_page;
+
+ for (i = 0; i < num_ptes; ++i) {
+ pte = alloc_pte(&dma_dom->domain, address,
+ &pte_page, gfp);
+ if (!pte)
+ goto out_free;
+
+ dma_dom->aperture[index]->pte_pages[i] = pte_page;
+
+ address += APERTURE_RANGE_SIZE / 64;
+ }
+ }
+
+ dma_dom->aperture_size += APERTURE_RANGE_SIZE;
+
+ /* Intialize the exclusion range if necessary */
+ if (iommu->exclusion_start &&
+ iommu->exclusion_start >= dma_dom->aperture[index]->offset &&
+ iommu->exclusion_start < dma_dom->aperture_size) {
+ unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
+ int pages = iommu_num_pages(iommu->exclusion_start,
+ iommu->exclusion_length,
+ PAGE_SIZE);
+ dma_ops_reserve_addresses(dma_dom, startpage, pages);
+ }
+
+ /*
+ * Check for areas already mapped as present in the new aperture
+ * range and mark those pages as reserved in the allocator. Such
+ * mappings may already exist as a result of requested unity
+ * mappings for devices.
+ */
+ for (i = dma_dom->aperture[index]->offset;
+ i < dma_dom->aperture_size;
+ i += PAGE_SIZE) {
+ u64 *pte = fetch_pte(&dma_dom->domain, i);
+ if (!pte || !IOMMU_PTE_PRESENT(*pte))
+ continue;
+
+ dma_ops_reserve_addresses(dma_dom, i << PAGE_SHIFT, 1);
+ }
+
+ return 0;
+
+out_free:
+ free_page((unsigned long)dma_dom->aperture[index]->bitmap);
+
+ kfree(dma_dom->aperture[index]);
+ dma_dom->aperture[index] = NULL;
+
+ return -ENOMEM;
+}
+
+static unsigned long dma_ops_area_alloc(struct device *dev,
+ struct dma_ops_domain *dom,
+ unsigned int pages,
+ unsigned long align_mask,
+ u64 dma_mask,
+ unsigned long start)
+{
+ unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE;
+ int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
+ int i = start >> APERTURE_RANGE_SHIFT;
+ unsigned long boundary_size;
+ unsigned long address = -1;
+ unsigned long limit;
+
+ next_bit >>= PAGE_SHIFT;
+
+ boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+ PAGE_SIZE) >> PAGE_SHIFT;
+
+ for (;i < max_index; ++i) {
+ unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT;
+
+ if (dom->aperture[i]->offset >= dma_mask)
+ break;
+
+ limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset,
+ dma_mask >> PAGE_SHIFT);
+
+ address = iommu_area_alloc(dom->aperture[i]->bitmap,
+ limit, next_bit, pages, 0,
+ boundary_size, align_mask);
+ if (address != -1) {
+ address = dom->aperture[i]->offset +
+ (address << PAGE_SHIFT);
+ dom->next_address = address + (pages << PAGE_SHIFT);
+ break;
+ }
+
+ next_bit = 0;
+ }
+
+ return address;
+}
+
static unsigned long dma_ops_alloc_addresses(struct device *dev,
struct dma_ops_domain *dom,
unsigned int pages,
unsigned long align_mask,
u64 dma_mask)
{
- unsigned long limit;
unsigned long address;
- unsigned long boundary_size;
- boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
- PAGE_SIZE) >> PAGE_SHIFT;
- limit = iommu_device_max_index(dom->aperture_size >> PAGE_SHIFT, 0,
- dma_mask >> PAGE_SHIFT);
+#ifdef CONFIG_IOMMU_STRESS
+ dom->next_address = 0;
+ dom->need_flush = true;
+#endif
- if (dom->next_bit >= limit) {
- dom->next_bit = 0;
- dom->need_flush = true;
- }
+ address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+ dma_mask, dom->next_address);
- address = iommu_area_alloc(dom->bitmap, limit, dom->next_bit, pages,
- 0 , boundary_size, align_mask);
if (address == -1) {
- address = iommu_area_alloc(dom->bitmap, limit, 0, pages,
- 0, boundary_size, align_mask);
+ dom->next_address = 0;
+ address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+ dma_mask, 0);
dom->need_flush = true;
}
- if (likely(address != -1)) {
- dom->next_bit = address + pages;
- address <<= PAGE_SHIFT;
- } else
+ if (unlikely(address == -1))
address = bad_dma_address;
WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size);
unsigned long address,
unsigned int pages)
{
- address >>= PAGE_SHIFT;
- iommu_area_free(dom->bitmap, address, pages);
+ unsigned i = address >> APERTURE_RANGE_SHIFT;
+ struct aperture_range *range = dom->aperture[i];
- if (address >= dom->next_bit)
+ BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL);
+
+#ifdef CONFIG_IOMMU_STRESS
+ if (i < 4)
+ return;
+#endif
+
+ if (address >= dom->next_address)
dom->need_flush = true;
+
+ address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT;
+
+ iommu_area_free(range->bitmap, address, pages);
+
}
/****************************************************************************
unsigned long start_page,
unsigned int pages)
{
- unsigned int last_page = dom->aperture_size >> PAGE_SHIFT;
+ unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT;
if (start_page + pages > last_page)
pages = last_page - start_page;
- iommu_area_reserve(dom->bitmap, start_page, pages);
+ for (i = start_page; i < start_page + pages; ++i) {
+ int index = i / APERTURE_RANGE_PAGES;
+ int page = i % APERTURE_RANGE_PAGES;
+ __set_bit(page, dom->aperture[index]->bitmap);
+ }
}
static void free_pagetable(struct protection_domain *domain)
*/
static void dma_ops_domain_free(struct dma_ops_domain *dom)
{
+ int i;
+
if (!dom)
return;
free_pagetable(&dom->domain);
- kfree(dom->pte_pages);
-
- kfree(dom->bitmap);
+ for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
+ if (!dom->aperture[i])
+ continue;
+ free_page((unsigned long)dom->aperture[i]->bitmap);
+ kfree(dom->aperture[i]);
+ }
kfree(dom);
}
* It also intializes the page table and the address allocator data
* structures required for the dma_ops interface
*/
-static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
- unsigned order)
+static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu)
{
struct dma_ops_domain *dma_dom;
- unsigned i, num_pte_pages;
- u64 *l2_pde;
- u64 address;
-
- /*
- * Currently the DMA aperture must be between 32 MB and 1GB in size
- */
- if ((order < 25) || (order > 30))
- return NULL;
dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
if (!dma_dom)
dma_dom->domain.priv = dma_dom;
if (!dma_dom->domain.pt_root)
goto free_dma_dom;
- dma_dom->aperture_size = (1ULL << order);
- dma_dom->bitmap = kzalloc(dma_dom->aperture_size / (PAGE_SIZE * 8),
- GFP_KERNEL);
- if (!dma_dom->bitmap)
- goto free_dma_dom;
- /*
- * mark the first page as allocated so we never return 0 as
- * a valid dma-address. So we can use 0 as error value
- */
- dma_dom->bitmap[0] = 1;
- dma_dom->next_bit = 0;
dma_dom->need_flush = false;
dma_dom->target_dev = 0xffff;
- /* Intialize the exclusion range if necessary */
- if (iommu->exclusion_start &&
- iommu->exclusion_start < dma_dom->aperture_size) {
- unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
- int pages = iommu_num_pages(iommu->exclusion_start,
- iommu->exclusion_length,
- PAGE_SIZE);
- dma_ops_reserve_addresses(dma_dom, startpage, pages);
- }
+ if (alloc_new_range(iommu, dma_dom, true, GFP_KERNEL))
+ goto free_dma_dom;
/*
- * At the last step, build the page tables so we don't need to
- * allocate page table pages in the dma_ops mapping/unmapping
- * path.
+ * mark the first page as allocated so we never return 0 as
+ * a valid dma-address. So we can use 0 as error value
*/
- num_pte_pages = dma_dom->aperture_size / (PAGE_SIZE * 512);
- dma_dom->pte_pages = kzalloc(num_pte_pages * sizeof(void *),
- GFP_KERNEL);
- if (!dma_dom->pte_pages)
- goto free_dma_dom;
-
- l2_pde = (u64 *)get_zeroed_page(GFP_KERNEL);
- if (l2_pde == NULL)
- goto free_dma_dom;
+ dma_dom->aperture[0]->bitmap[0] = 1;
+ dma_dom->next_address = 0;
- dma_dom->domain.pt_root[0] = IOMMU_L2_PDE(virt_to_phys(l2_pde));
-
- for (i = 0; i < num_pte_pages; ++i) {
- dma_dom->pte_pages[i] = (u64 *)get_zeroed_page(GFP_KERNEL);
- if (!dma_dom->pte_pages[i])
- goto free_dma_dom;
- address = virt_to_phys(dma_dom->pte_pages[i]);
- l2_pde[i] = IOMMU_L1_PDE(address);
- }
return dma_dom;
struct protection_domain *domain;
struct dma_ops_domain *dma_domain;
struct amd_iommu *iommu;
- int order = amd_iommu_aperture_order;
unsigned long flags;
if (devid > amd_iommu_last_bdf)
"to a non-dma-ops domain\n", dev_name(dev));
switch (action) {
- case BUS_NOTIFY_BOUND_DRIVER:
- if (domain)
- goto out;
- dma_domain = find_protection_domain(devid);
- if (!dma_domain)
- dma_domain = iommu->default_dom;
- attach_device(iommu, &dma_domain->domain, devid);
- printk(KERN_INFO "AMD IOMMU: Using protection domain %d for "
- "device %s\n", dma_domain->domain.id, dev_name(dev));
- break;
- case BUS_NOTIFY_UNBIND_DRIVER:
+ case BUS_NOTIFY_UNBOUND_DRIVER:
if (!domain)
goto out;
detach_device(domain, devid);
dma_domain = find_protection_domain(devid);
if (dma_domain)
goto out;
- dma_domain = dma_ops_domain_alloc(iommu, order);
+ dma_domain = dma_ops_domain_alloc(iommu);
if (!dma_domain)
goto out;
dma_domain->target_dev = devid;
dma_dom = (*iommu)->default_dom;
*domain = &dma_dom->domain;
attach_device(*iommu, *domain, *bdf);
- printk(KERN_INFO "AMD IOMMU: Using protection domain %d for "
- "device %s\n", (*domain)->id, dev_name(dev));
+ DUMP_printk("Using protection domain %d for device %s\n",
+ (*domain)->id, dev_name(dev));
}
if (domain_for_device(_bdf) == NULL)
return 1;
}
+/*
+ * If the pte_page is not yet allocated this function is called
+ */
+static u64* alloc_pte(struct protection_domain *dom,
+ unsigned long address, u64 **pte_page, gfp_t gfp)
+{
+ u64 *pte, *page;
+
+ pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(address)];
+
+ if (!IOMMU_PTE_PRESENT(*pte)) {
+ page = (u64 *)get_zeroed_page(gfp);
+ if (!page)
+ return NULL;
+ *pte = IOMMU_L2_PDE(virt_to_phys(page));
+ }
+
+ pte = IOMMU_PTE_PAGE(*pte);
+ pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+
+ if (!IOMMU_PTE_PRESENT(*pte)) {
+ page = (u64 *)get_zeroed_page(gfp);
+ if (!page)
+ return NULL;
+ *pte = IOMMU_L1_PDE(virt_to_phys(page));
+ }
+
+ pte = IOMMU_PTE_PAGE(*pte);
+
+ if (pte_page)
+ *pte_page = pte;
+
+ pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+
+ return pte;
+}
+
+/*
+ * This function fetches the PTE for a given address in the aperture
+ */
+static u64* dma_ops_get_pte(struct dma_ops_domain *dom,
+ unsigned long address)
+{
+ struct aperture_range *aperture;
+ u64 *pte, *pte_page;
+
+ aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+ if (!aperture)
+ return NULL;
+
+ pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+ if (!pte) {
+ pte = alloc_pte(&dom->domain, address, &pte_page, GFP_ATOMIC);
+ aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page;
+ } else
+ pte += IOMMU_PTE_L0_INDEX(address);
+
+ return pte;
+}
+
/*
* This is the generic map function. It maps one 4kb page at paddr to
* the given address in the DMA address space for the domain.
paddr &= PAGE_MASK;
- pte = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
- pte += IOMMU_PTE_L0_INDEX(address);
+ pte = dma_ops_get_pte(dom, address);
+ if (!pte)
+ return bad_dma_address;
__pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC;
struct dma_ops_domain *dom,
unsigned long address)
{
+ struct aperture_range *aperture;
u64 *pte;
if (address >= dom->aperture_size)
return;
- WARN_ON(address & ~PAGE_MASK || address >= dom->aperture_size);
+ aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+ if (!aperture)
+ return;
+
+ pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+ if (!pte)
+ return;
- pte = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
pte += IOMMU_PTE_L0_INDEX(address);
WARN_ON(!*pte);
u64 dma_mask)
{
dma_addr_t offset = paddr & ~PAGE_MASK;
- dma_addr_t address, start;
+ dma_addr_t address, start, ret;
unsigned int pages;
unsigned long align_mask = 0;
int i;
if (align)
align_mask = (1UL << get_order(size)) - 1;
+retry:
address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask,
dma_mask);
- if (unlikely(address == bad_dma_address))
- goto out;
+ if (unlikely(address == bad_dma_address)) {
+ /*
+ * setting next_address here will let the address
+ * allocator only scan the new allocated range in the
+ * first run. This is a small optimization.
+ */
+ dma_dom->next_address = dma_dom->aperture_size;
+
+ if (alloc_new_range(iommu, dma_dom, false, GFP_ATOMIC))
+ goto out;
+
+ /*
+ * aperture was sucessfully enlarged by 128 MB, try
+ * allocation again
+ */
+ goto retry;
+ }
start = address;
for (i = 0; i < pages; ++i) {
- dma_ops_domain_map(iommu, dma_dom, start, paddr, dir);
+ ret = dma_ops_domain_map(iommu, dma_dom, start, paddr, dir);
+ if (ret == bad_dma_address)
+ goto out_unmap;
+
paddr += PAGE_SIZE;
start += PAGE_SIZE;
}
out:
return address;
+
+out_unmap:
+
+ for (--i; i >= 0; --i) {
+ start -= PAGE_SIZE;
+ dma_ops_domain_unmap(iommu, dma_dom, start);
+ }
+
+ dma_ops_free_addresses(dma_dom, address, pages);
+
+ return bad_dma_address;
}
/*
*dma_addr = __map_single(dev, iommu, domain->priv, paddr,
size, DMA_BIDIRECTIONAL, true, dma_mask);
- if (*dma_addr == bad_dma_address)
+ if (*dma_addr == bad_dma_address) {
+ spin_unlock_irqrestore(&domain->lock, flags);
goto out_free;
+ }
iommu_completion_wait(iommu);
struct pci_dev *dev = NULL;
struct dma_ops_domain *dma_dom;
struct amd_iommu *iommu;
- int order = amd_iommu_aperture_order;
u16 devid;
while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
iommu = amd_iommu_rlookup_table[devid];
if (!iommu)
continue;
- dma_dom = dma_ops_domain_alloc(iommu, order);
+ dma_dom = dma_ops_domain_alloc(iommu);
if (!dma_dom)
continue;
init_unity_mappings_for_device(dma_dom, devid);
int __init amd_iommu_init_dma_ops(void)
{
struct amd_iommu *iommu;
- int order = amd_iommu_aperture_order;
int ret;
/*
* found in the system. Devices not assigned to any other
* protection domain will be assigned to the default one.
*/
- list_for_each_entry(iommu, &amd_iommu_list, list) {
- iommu->default_dom = dma_ops_domain_alloc(iommu, order);
+ for_each_iommu(iommu) {
+ iommu->default_dom = dma_ops_domain_alloc(iommu);
if (iommu->default_dom == NULL)
return -ENOMEM;
iommu->default_dom->domain.flags |= PD_DEFAULT_MASK;
free_domains:
- list_for_each_entry(iommu, &amd_iommu_list, list) {
+ for_each_iommu(iommu) {
if (iommu->default_dom)
dma_ops_domain_free(iommu->default_dom);
}
old_domain = domain_for_device(devid);
if (old_domain)
- return -EBUSY;
+ detach_device(old_domain, devid);
attach_device(iommu, domain, devid);
u64 range_length;
} __attribute__((packed));
+bool amd_iommu_dump;
+
static int __initdata amd_iommu_detected;
u16 amd_iommu_last_bdf; /* largest PCI device id we have
to handle */
LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings
we find in ACPI */
-unsigned amd_iommu_aperture_order = 26; /* size of aperture in power of 2 */
+#ifdef CONFIG_IOMMU_STRESS
+bool amd_iommu_isolate = false;
+#else
bool amd_iommu_isolate = true; /* if true, device isolation is
enabled */
+#endif
+
bool amd_iommu_unmap_flush; /* if true, flush on every unmap */
LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the
static inline unsigned long tbl_size(int entry_size)
{
unsigned shift = PAGE_SHIFT +
- get_order(amd_iommu_last_bdf * entry_size);
+ get_order(((int)amd_iommu_last_bdf + 1) * entry_size);
return 1UL << shift;
}
* This function set the exclusion range in the IOMMU. DMA accesses to the
* exclusion range are passed through untranslated
*/
-static void __init iommu_set_exclusion_range(struct amd_iommu *iommu)
+static void iommu_set_exclusion_range(struct amd_iommu *iommu)
{
u64 start = iommu->exclusion_start & PAGE_MASK;
u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
}
/* Generic functions to enable/disable certain features of the IOMMU. */
-static void __init iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
+static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
{
u32 ctrl;
}
/* Function to enable the hardware */
-static void __init iommu_enable(struct amd_iommu *iommu)
+static void iommu_enable(struct amd_iommu *iommu)
{
printk(KERN_INFO "AMD IOMMU: Enabling IOMMU at %s cap 0x%hx\n",
dev_name(&iommu->dev->dev), iommu->cap_ptr);
iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
}
-/* Function to enable IOMMU event logging and event interrupts */
-static void __init iommu_enable_event_logging(struct amd_iommu *iommu)
+static void iommu_disable(struct amd_iommu *iommu)
{
- iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
- iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+ iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
}
/*
{
u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
get_order(CMD_BUFFER_SIZE));
- u64 entry;
if (cmd_buf == NULL)
return NULL;
iommu->cmd_buf_size = CMD_BUFFER_SIZE;
- entry = (u64)virt_to_phys(cmd_buf);
+ return cmd_buf;
+}
+
+/*
+ * This function writes the command buffer address to the hardware and
+ * enables it.
+ */
+static void iommu_enable_command_buffer(struct amd_iommu *iommu)
+{
+ u64 entry;
+
+ BUG_ON(iommu->cmd_buf == NULL);
+
+ entry = (u64)virt_to_phys(iommu->cmd_buf);
entry |= MMIO_CMD_SIZE_512;
+
memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
- &entry, sizeof(entry));
+ &entry, sizeof(entry));
/* set head and tail to zero manually */
writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
-
- return cmd_buf;
}
static void __init free_command_buffer(struct amd_iommu *iommu)
/* allocates the memory where the IOMMU will log its events to */
static u8 * __init alloc_event_buffer(struct amd_iommu *iommu)
{
- u64 entry;
iommu->evt_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
get_order(EVT_BUFFER_SIZE));
if (iommu->evt_buf == NULL)
return NULL;
+ return iommu->evt_buf;
+}
+
+static void iommu_enable_event_buffer(struct amd_iommu *iommu)
+{
+ u64 entry;
+
+ BUG_ON(iommu->evt_buf == NULL);
+
entry = (u64)virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
+
memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
&entry, sizeof(entry));
- iommu->evt_buf_size = EVT_BUFFER_SIZE;
-
- return iommu->evt_buf;
+ iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
}
static void __init free_event_buffer(struct amd_iommu *iommu)
p += sizeof(struct ivhd_header);
end += h->length;
+
while (p < end) {
e = (struct ivhd_entry *)p;
switch (e->type) {
case IVHD_DEV_ALL:
+
+ DUMP_printk(" DEV_ALL\t\t\t first devid: %02x:%02x.%x"
+ " last device %02x:%02x.%x flags: %02x\n",
+ PCI_BUS(iommu->first_device),
+ PCI_SLOT(iommu->first_device),
+ PCI_FUNC(iommu->first_device),
+ PCI_BUS(iommu->last_device),
+ PCI_SLOT(iommu->last_device),
+ PCI_FUNC(iommu->last_device),
+ e->flags);
+
for (dev_i = iommu->first_device;
dev_i <= iommu->last_device; ++dev_i)
set_dev_entry_from_acpi(iommu, dev_i,
e->flags, 0);
break;
case IVHD_DEV_SELECT:
+
+ DUMP_printk(" DEV_SELECT\t\t\t devid: %02x:%02x.%x "
+ "flags: %02x\n",
+ PCI_BUS(e->devid),
+ PCI_SLOT(e->devid),
+ PCI_FUNC(e->devid),
+ e->flags);
+
devid = e->devid;
set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
break;
case IVHD_DEV_SELECT_RANGE_START:
+
+ DUMP_printk(" DEV_SELECT_RANGE_START\t "
+ "devid: %02x:%02x.%x flags: %02x\n",
+ PCI_BUS(e->devid),
+ PCI_SLOT(e->devid),
+ PCI_FUNC(e->devid),
+ e->flags);
+
devid_start = e->devid;
flags = e->flags;
ext_flags = 0;
alias = false;
break;
case IVHD_DEV_ALIAS:
+
+ DUMP_printk(" DEV_ALIAS\t\t\t devid: %02x:%02x.%x "
+ "flags: %02x devid_to: %02x:%02x.%x\n",
+ PCI_BUS(e->devid),
+ PCI_SLOT(e->devid),
+ PCI_FUNC(e->devid),
+ e->flags,
+ PCI_BUS(e->ext >> 8),
+ PCI_SLOT(e->ext >> 8),
+ PCI_FUNC(e->ext >> 8));
+
devid = e->devid;
devid_to = e->ext >> 8;
- set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+ set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
amd_iommu_alias_table[devid] = devid_to;
break;
case IVHD_DEV_ALIAS_RANGE:
+
+ DUMP_printk(" DEV_ALIAS_RANGE\t\t "
+ "devid: %02x:%02x.%x flags: %02x "
+ "devid_to: %02x:%02x.%x\n",
+ PCI_BUS(e->devid),
+ PCI_SLOT(e->devid),
+ PCI_FUNC(e->devid),
+ e->flags,
+ PCI_BUS(e->ext >> 8),
+ PCI_SLOT(e->ext >> 8),
+ PCI_FUNC(e->ext >> 8));
+
devid_start = e->devid;
flags = e->flags;
devid_to = e->ext >> 8;
alias = true;
break;
case IVHD_DEV_EXT_SELECT:
+
+ DUMP_printk(" DEV_EXT_SELECT\t\t devid: %02x:%02x.%x "
+ "flags: %02x ext: %08x\n",
+ PCI_BUS(e->devid),
+ PCI_SLOT(e->devid),
+ PCI_FUNC(e->devid),
+ e->flags, e->ext);
+
devid = e->devid;
set_dev_entry_from_acpi(iommu, devid, e->flags,
e->ext);
break;
case IVHD_DEV_EXT_SELECT_RANGE:
+
+ DUMP_printk(" DEV_EXT_SELECT_RANGE\t devid: "
+ "%02x:%02x.%x flags: %02x ext: %08x\n",
+ PCI_BUS(e->devid),
+ PCI_SLOT(e->devid),
+ PCI_FUNC(e->devid),
+ e->flags, e->ext);
+
devid_start = e->devid;
flags = e->flags;
ext_flags = e->ext;
alias = false;
break;
case IVHD_DEV_RANGE_END:
+
+ DUMP_printk(" DEV_RANGE_END\t\t devid: %02x:%02x.%x\n",
+ PCI_BUS(e->devid),
+ PCI_SLOT(e->devid),
+ PCI_FUNC(e->devid));
+
devid = e->devid;
for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
if (alias)
{
struct amd_iommu *iommu, *next;
- list_for_each_entry_safe(iommu, next, &amd_iommu_list, list) {
+ for_each_iommu_safe(iommu, next) {
list_del(&iommu->list);
free_iommu_one(iommu);
kfree(iommu);
if (!iommu->mmio_base)
return -ENOMEM;
- iommu_set_device_table(iommu);
iommu->cmd_buf = alloc_command_buffer(iommu);
if (!iommu->cmd_buf)
return -ENOMEM;
h = (struct ivhd_header *)p;
switch (*p) {
case ACPI_IVHD_TYPE:
+
+ DUMP_printk("IOMMU: device: %02x:%02x.%01x cap: %04x "
+ "seg: %d flags: %01x info %04x\n",
+ PCI_BUS(h->devid), PCI_SLOT(h->devid),
+ PCI_FUNC(h->devid), h->cap_ptr,
+ h->pci_seg, h->flags, h->info);
+ DUMP_printk(" mmio-addr: %016llx\n",
+ h->mmio_phys);
+
iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
if (iommu == NULL)
return -ENOMEM;
*
****************************************************************************/
-static int __init iommu_setup_msix(struct amd_iommu *iommu)
-{
- struct amd_iommu *curr;
- struct msix_entry entries[32]; /* only 32 supported by AMD IOMMU */
- int nvec = 0, i;
-
- list_for_each_entry(curr, &amd_iommu_list, list) {
- if (curr->dev == iommu->dev) {
- entries[nvec].entry = curr->evt_msi_num;
- entries[nvec].vector = 0;
- curr->int_enabled = true;
- nvec++;
- }
- }
-
- if (pci_enable_msix(iommu->dev, entries, nvec)) {
- pci_disable_msix(iommu->dev);
- return 1;
- }
-
- for (i = 0; i < nvec; ++i) {
- int r = request_irq(entries->vector, amd_iommu_int_handler,
- IRQF_SAMPLE_RANDOM,
- "AMD IOMMU",
- NULL);
- if (r)
- goto out_free;
- }
-
- return 0;
-
-out_free:
- for (i -= 1; i >= 0; --i)
- free_irq(entries->vector, NULL);
-
- pci_disable_msix(iommu->dev);
-
- return 1;
-}
-
static int __init iommu_setup_msi(struct amd_iommu *iommu)
{
int r;
- struct amd_iommu *curr;
-
- list_for_each_entry(curr, &amd_iommu_list, list) {
- if (curr->dev == iommu->dev)
- curr->int_enabled = true;
- }
-
if (pci_enable_msi(iommu->dev))
return 1;
return 1;
}
+ iommu->int_enabled = true;
+ iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+
return 0;
}
-static int __init iommu_init_msi(struct amd_iommu *iommu)
+static int iommu_init_msi(struct amd_iommu *iommu)
{
if (iommu->int_enabled)
return 0;
- if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSIX))
- return iommu_setup_msix(iommu);
- else if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
+ if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
return iommu_setup_msi(iommu);
return 1;
static int __init init_unity_map_range(struct ivmd_header *m)
{
struct unity_map_entry *e = 0;
+ char *s;
e = kzalloc(sizeof(*e), GFP_KERNEL);
if (e == NULL)
switch (m->type) {
default:
+ kfree(e);
+ return 0;
case ACPI_IVMD_TYPE:
+ s = "IVMD_TYPEi\t\t\t";
e->devid_start = e->devid_end = m->devid;
break;
case ACPI_IVMD_TYPE_ALL:
+ s = "IVMD_TYPE_ALL\t\t";
e->devid_start = 0;
e->devid_end = amd_iommu_last_bdf;
break;
case ACPI_IVMD_TYPE_RANGE:
+ s = "IVMD_TYPE_RANGE\t\t";
e->devid_start = m->devid;
e->devid_end = m->aux;
break;
e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
e->prot = m->flags >> 1;
+ DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
+ " range_start: %016llx range_end: %016llx flags: %x\n", s,
+ PCI_BUS(e->devid_start), PCI_SLOT(e->devid_start),
+ PCI_FUNC(e->devid_start), PCI_BUS(e->devid_end),
+ PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end),
+ e->address_start, e->address_end, m->flags);
+
list_add_tail(&e->list, &amd_iommu_unity_map);
return 0;
* This function finally enables all IOMMUs found in the system after
* they have been initialized
*/
-static void __init enable_iommus(void)
+static void enable_iommus(void)
{
struct amd_iommu *iommu;
- list_for_each_entry(iommu, &amd_iommu_list, list) {
+ for_each_iommu(iommu) {
+ iommu_set_device_table(iommu);
+ iommu_enable_command_buffer(iommu);
+ iommu_enable_event_buffer(iommu);
iommu_set_exclusion_range(iommu);
iommu_init_msi(iommu);
- iommu_enable_event_logging(iommu);
iommu_enable(iommu);
}
}
+static void disable_iommus(void)
+{
+ struct amd_iommu *iommu;
+
+ for_each_iommu(iommu)
+ iommu_disable(iommu);
+}
+
/*
* Suspend/Resume support
* disable suspend until real resume implemented
static int amd_iommu_resume(struct sys_device *dev)
{
+ /*
+ * Disable IOMMUs before reprogramming the hardware registers.
+ * IOMMU is still enabled from the resume kernel.
+ */
+ disable_iommus();
+
+ /* re-load the hardware */
+ enable_iommus();
+
+ /*
+ * we have to flush after the IOMMUs are enabled because a
+ * disabled IOMMU will never execute the commands we send
+ */
+ amd_iommu_flush_all_domains();
+ amd_iommu_flush_all_devices();
+
return 0;
}
static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
{
- return -EINVAL;
+ /* disable IOMMUs to go out of the way for BIOS */
+ disable_iommus();
+
+ return 0;
}
static struct sysdev_class amd_iommu_sysdev_class = {
enable_iommus();
- printk(KERN_INFO "AMD IOMMU: aperture size is %d MB\n",
- (1 << (amd_iommu_aperture_order-20)));
-
printk(KERN_INFO "AMD IOMMU: device isolation ");
if (amd_iommu_isolate)
printk("enabled\n");
*
****************************************************************************/
+static int __init parse_amd_iommu_dump(char *str)
+{
+ amd_iommu_dump = true;
+
+ return 1;
+}
+
static int __init parse_amd_iommu_options(char *str)
{
for (; *str; ++str) {
return 1;
}
-static int __init parse_amd_iommu_size_options(char *str)
-{
- unsigned order = PAGE_SHIFT + get_order(memparse(str, &str));
-
- if ((order > 24) && (order < 31))
- amd_iommu_aperture_order = order;
-
- return 1;
-}
-
+__setup("amd_iommu_dump", parse_amd_iommu_dump);
__setup("amd_iommu=", parse_amd_iommu_options);
-__setup("amd_iommu_size=", parse_amd_iommu_size_options);
/* Local APIC was disabled by the BIOS and enabled by the kernel */
static int enabled_via_apicbase;
+/*
+ * Handle interrupt mode configuration register (IMCR).
+ * This register controls whether the interrupt signals
+ * that reach the BSP come from the master PIC or from the
+ * local APIC. Before entering Symmetric I/O Mode, either
+ * the BIOS or the operating system must switch out of
+ * PIC Mode by changing the IMCR.
+ */
+static inline void imcr_pic_to_apic(void)
+{
+ /* select IMCR register */
+ outb(0x70, 0x22);
+ /* NMI and 8259 INTR go through APIC */
+ outb(0x01, 0x23);
+}
+
+static inline void imcr_apic_to_pic(void)
+{
+ /* select IMCR register */
+ outb(0x70, 0x22);
+ /* NMI and 8259 INTR go directly to BSP */
+ outb(0x00, 0x23);
+}
#endif
#ifdef CONFIG_X86_64
__setup("apicpmtimer", setup_apicpmtimer);
#endif
+int x2apic_mode;
#ifdef CONFIG_X86_X2APIC
-int x2apic;
/* x2apic enabled before OS handover */
static int x2apic_preenabled;
static int disable_x2apic;
static __init int setup_nox2apic(char *str)
{
+ if (x2apic_enabled()) {
+ pr_warning("Bios already enabled x2apic, "
+ "can't enforce nox2apic");
+ return 0;
+ }
+
disable_x2apic = 1;
setup_clear_cpu_cap(X86_FEATURE_X2APIC);
return 0;
return lapic_get_version() >= 0x14;
}
+/*
+ * bare function to substitute write operation
+ * and it's _that_ fast :)
+ */
+static void native_apic_write_dummy(u32 reg, u32 v)
+{
+ WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+}
+
+static u32 native_apic_read_dummy(u32 reg)
+{
+ WARN_ON_ONCE((cpu_has_apic && !disable_apic));
+ return 0;
+}
+
+/*
+ * right after this call apic->write/read doesn't do anything
+ * note that there is no restore operation it works one way
+ */
+void apic_disable(void)
+{
+ apic->read = native_apic_read_dummy;
+ apic->write = native_apic_write_dummy;
+}
+
void native_apic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
{
- unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
+ unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
unsigned int v = (mask << 16) | (msg_type << 8) | vector;
apic_write(reg, v);
u32 v;
/* APIC hasn't been mapped yet */
- if (!x2apic && !apic_phys)
+ if (!x2apic_mode && !apic_phys)
return;
maxlvt = lapic_get_maxlvt();
{
if (x2apic_enabled()) {
pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
- x2apic_preenabled = x2apic = 1;
+ x2apic_preenabled = x2apic_mode = 1;
}
}
{
int msr, msr2;
- if (!x2apic)
+ if (!x2apic_mode)
return;
rdmsr(MSR_IA32_APICBASE, msr, msr2);
wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
}
}
+#endif /* CONFIG_X86_X2APIC */
void __init enable_IR_x2apic(void)
{
unsigned long flags;
struct IO_APIC_route_entry **ioapic_entries = NULL;
- if (!cpu_has_x2apic)
- return;
-
- if (!x2apic_preenabled && disable_x2apic) {
- pr_info("Skipped enabling x2apic and Interrupt-remapping "
- "because of nox2apic\n");
- return;
+ ret = dmar_table_init();
+ if (ret) {
+ pr_debug("dmar_table_init() failed with %d:\n", ret);
+ goto ir_failed;
}
- if (x2apic_preenabled && disable_x2apic)
- panic("Bios already enabled x2apic, can't enforce nox2apic");
-
- if (!x2apic_preenabled && skip_ioapic_setup) {
- pr_info("Skipped enabling x2apic and Interrupt-remapping "
- "because of skipping io-apic setup\n");
- return;
+ if (!intr_remapping_supported()) {
+ pr_debug("intr-remapping not supported\n");
+ goto ir_failed;
}
- ret = dmar_table_init();
- if (ret) {
- pr_info("dmar_table_init() failed with %d:\n", ret);
- if (x2apic_preenabled)
- panic("x2apic enabled by bios. But IR enabling failed");
- else
- pr_info("Not enabling x2apic,Intr-remapping\n");
+ if (!x2apic_preenabled && skip_ioapic_setup) {
+ pr_info("Skipped enabling intr-remap because of skipping "
+ "io-apic setup\n");
return;
}
mask_IO_APIC_setup(ioapic_entries);
mask_8259A();
- ret = enable_intr_remapping(EIM_32BIT_APIC_ID);
-
- if (ret && x2apic_preenabled) {
- local_irq_restore(flags);
- panic("x2apic enabled by bios. But IR enabling failed");
- }
-
+ ret = enable_intr_remapping(x2apic_supported());
if (ret)
goto end_restore;
- if (!x2apic) {
- x2apic = 1;
+ pr_info("Enabled Interrupt-remapping\n");
+
+ if (x2apic_supported() && !x2apic_mode) {
+ x2apic_mode = 1;
enable_x2apic();
+ pr_info("Enabled x2apic\n");
}
end_restore:
* IR enabling failed
*/
restore_IO_APIC_setup(ioapic_entries);
- else
- reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries);
unmask_8259A();
local_irq_restore(flags);
end:
- if (!ret) {
- if (!x2apic_preenabled)
- pr_info("Enabled x2apic and interrupt-remapping\n");
- else
- pr_info("Enabled Interrupt-remapping\n");
- } else
- pr_err("Failed to enable Interrupt-remapping and x2apic\n");
if (ioapic_entries)
free_ioapic_entries(ioapic_entries);
+
+ if (!ret)
+ return;
+
+ir_failed:
+ if (x2apic_preenabled)
+ panic("x2apic enabled by bios. But IR enabling failed");
+ else if (cpu_has_x2apic)
+ pr_info("Not enabling x2apic,Intr-remapping\n");
#else
if (!cpu_has_x2apic)
return;
if (x2apic_preenabled)
panic("x2apic enabled prior OS handover,"
- " enable CONFIG_INTR_REMAP");
-
- pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
- " and x2apic\n");
+ " enable CONFIG_X86_X2APIC, CONFIG_INTR_REMAP");
#endif
return;
}
-#endif /* CONFIG_X86_X2APIC */
+
#ifdef CONFIG_X86_64
/*
}
mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
- boot_cpu_physical_apicid = 0;
return 0;
}
#else
*/
void __init init_apic_mappings(void)
{
- if (x2apic) {
+ unsigned int new_apicid;
+
+ if (x2apic_mode) {
boot_cpu_physical_apicid = read_apic_id();
return;
}
- /*
- * If no local APIC can be found then set up a fake all
- * zeroes page to simulate the local APIC and another
- * one for the IO-APIC.
- */
+ /* If no local APIC can be found return early */
if (!smp_found_config && detect_init_APIC()) {
- apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
- apic_phys = __pa(apic_phys);
- } else
+ /* lets NOP'ify apic operations */
+ pr_info("APIC: disable apic facility\n");
+ apic_disable();
+ } else {
apic_phys = mp_lapic_addr;
- set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
- apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
- APIC_BASE, apic_phys);
+ /*
+ * acpi lapic path already maps that address in
+ * acpi_register_lapic_address()
+ */
+ if (!acpi_lapic)
+ set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+
+ apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
+ APIC_BASE, apic_phys);
+ }
/*
* Fetch the APIC ID of the BSP in case we have a
* default configuration (or the MP table is broken).
*/
- if (boot_cpu_physical_apicid == -1U)
- boot_cpu_physical_apicid = read_apic_id();
+ new_apicid = read_apic_id();
+ if (boot_cpu_physical_apicid != new_apicid) {
+ boot_cpu_physical_apicid = new_apicid;
+ /*
+ * yeah -- we lie about apic_version
+ * in case if apic was disabled via boot option
+ * but it's not a problem for SMP compiled kernel
+ * since smp_sanity_check is prepared for such a case
+ * and disable smp mode
+ */
+ apic_version[new_apicid] =
+ GET_APIC_VERSION(apic_read(APIC_LVR));
+ }
}
/*
*/
apic_printk(APIC_VERBOSE, "leaving PIC mode, "
"enabling APIC mode.\n");
- outb(0x70, 0x22);
- outb(0x01, 0x23);
+ imcr_pic_to_apic();
}
#endif
if (apic->enable_apic_mode)
*/
apic_printk(APIC_VERBOSE, "disabling APIC mode, "
"entering PIC mode.\n");
- outb(0x70, 0x22);
- outb(0x00, 0x23);
+ imcr_apic_to_pic();
return;
}
#endif
local_irq_save(flags);
disable_local_APIC();
-#ifdef CONFIG_INTR_REMAP
+
if (intr_remapping_enabled)
disable_intr_remapping();
-#endif
+
local_irq_restore(flags);
return 0;
}
unsigned int l, h;
unsigned long flags;
int maxlvt;
-
-#ifdef CONFIG_INTR_REMAP
- int ret;
+ int ret = 0;
struct IO_APIC_route_entry **ioapic_entries = NULL;
if (!apic_pm_state.active)
return 0;
local_irq_save(flags);
- if (x2apic) {
+ if (intr_remapping_enabled) {
ioapic_entries = alloc_ioapic_entries();
if (!ioapic_entries) {
WARN(1, "Alloc ioapic_entries in lapic resume failed.");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto restore;
}
ret = save_IO_APIC_setup(ioapic_entries);
if (ret) {
WARN(1, "Saving IO-APIC state failed: %d\n", ret);
free_ioapic_entries(ioapic_entries);
- return ret;
+ goto restore;
}
mask_IO_APIC_setup(ioapic_entries);
mask_8259A();
- enable_x2apic();
}
-#else
- if (!apic_pm_state.active)
- return 0;
- local_irq_save(flags);
- if (x2apic)
+ if (x2apic_mode)
enable_x2apic();
-#endif
-
else {
/*
* Make sure the APICBASE points to the right address
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
-#ifdef CONFIG_INTR_REMAP
- if (intr_remapping_enabled)
- reenable_intr_remapping(EIM_32BIT_APIC_ID);
-
- if (x2apic) {
+ if (intr_remapping_enabled) {
+ reenable_intr_remapping(x2apic_mode);
unmask_8259A();
restore_IO_APIC_setup(ioapic_entries);
free_ioapic_entries(ioapic_entries);
}
-#endif
-
+restore:
local_irq_restore(flags);
-
- return 0;
+ return ret;
}
/*
#endif /* CONFIG_PM */
#ifdef CONFIG_X86_64
-/*
- * apic_is_clustered_box() -- Check if we can expect good TSC
- *
- * Thus far, the major user of this is IBM's Summit2 series:
- *
- * Clustered boxes may have unsynced TSC problems if they are
- * multi-chassis. Use available data to take a good guess.
- * If in doubt, go HPET.
- */
-__cpuinit int apic_is_clustered_box(void)
+
+static int __cpuinit apic_cluster_num(void)
{
int i, clusters, zeros;
unsigned id;
u16 *bios_cpu_apicid;
DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
- /*
- * there is not this kind of box with AMD CPU yet.
- * Some AMD box with quadcore cpu and 8 sockets apicid
- * will be [4, 0x23] or [8, 0x27] could be thought to
- * vsmp box still need checking...
- */
- if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
- return 0;
-
bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
++zeros;
}
- /* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
- * not guaranteed to be synced between boards
- */
- if (is_vsmp_box() && clusters > 1)
+ return clusters;
+}
+
+static int __cpuinitdata multi_checked;
+static int __cpuinitdata multi;
+
+static int __cpuinit set_multi(const struct dmi_system_id *d)
+{
+ if (multi)
+ return 0;
+ pr_info("APIC: %s detected, Multi Chassis\n", d->ident);
+ multi = 1;
+ return 0;
+}
+
+static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+ {
+ .callback = set_multi,
+ .ident = "IBM System Summit2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Summit2"),
+ },
+ },
+ {}
+};
+
+static void __cpuinit dmi_check_multi(void)
+{
+ if (multi_checked)
+ return;
+
+ dmi_check_system(multi_dmi_table);
+ multi_checked = 1;
+}
+
+/*
+ * apic_is_clustered_box() -- Check if we can expect good TSC
+ *
+ * Thus far, the major user of this is IBM's Summit2 series:
+ * Clustered boxes may have unsynced TSC problems if they are
+ * multi-chassis.
+ * Use DMI to check them
+ */
+__cpuinit int apic_is_clustered_box(void)
+{
+ dmi_check_multi();
+ if (multi)
return 1;
+ if (!is_vsmp_box())
+ return 0;
+
/*
- * If clusters > 2, then should be multi-chassis.
- * May have to revisit this when multi-core + hyperthreaded CPUs come
- * out, but AFAIK this will work even for them.
+ * ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+ * not guaranteed to be synced between boards
*/
- return (clusters > 2);
+ if (apic_cluster_num() > 1)
+ return 1;
+
+ return 0;
}
#endif
static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
{
- return hard_smp_processor_id() >> index_msb;
+ return initial_apic_id >> index_msb;
}
struct apic apic_flat = {
* regardless of how many processors are present (x86_64 ES7000
* is an example).
*/
- if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+ if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
printk(KERN_DEBUG "system APIC only can use physical flat");
return 1;
return gsi;
}
-static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
{
unsigned long vect = 0, psaival = 0;
#include <asm/setup.h>
#include <asm/irq_remapping.h>
#include <asm/hpet.h>
+#include <asm/hw_irq.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/uv_irq.h>
struct irq_pin_list *next;
};
-static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
+static struct irq_pin_list *get_one_free_irq_2_pin(int node)
{
struct irq_pin_list *pin;
- int node;
-
- node = cpu_to_node(cpu);
pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
unsigned move_cleanup_count;
u8 vector;
u8 move_in_progress : 1;
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
- u8 move_desc_pending : 1;
-#endif
};
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
return cfg;
}
-static struct irq_cfg *get_one_free_irq_cfg(int cpu)
+static struct irq_cfg *get_one_free_irq_cfg(int node)
{
struct irq_cfg *cfg;
- int node;
-
- node = cpu_to_node(cpu);
cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
if (cfg) {
return cfg;
}
-int arch_init_chip_data(struct irq_desc *desc, int cpu)
+int arch_init_chip_data(struct irq_desc *desc, int node)
{
struct irq_cfg *cfg;
cfg = desc->chip_data;
if (!cfg) {
- desc->chip_data = get_one_free_irq_cfg(cpu);
+ desc->chip_data = get_one_free_irq_cfg(node);
if (!desc->chip_data) {
printk(KERN_ERR "can not alloc irq_cfg\n");
BUG_ON(1);
return 0;
}
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-
+/* for move_irq_desc */
static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
+init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
{
struct irq_pin_list *old_entry, *head, *tail, *entry;
if (!old_entry)
return;
- entry = get_one_free_irq_2_pin(cpu);
+ entry = get_one_free_irq_2_pin(node);
if (!entry)
return;
tail = entry;
old_entry = old_entry->next;
while (old_entry) {
- entry = get_one_free_irq_2_pin(cpu);
+ entry = get_one_free_irq_2_pin(node);
if (!entry) {
entry = head;
while (entry) {
}
void arch_init_copy_chip_data(struct irq_desc *old_desc,
- struct irq_desc *desc, int cpu)
+ struct irq_desc *desc, int node)
{
struct irq_cfg *cfg;
struct irq_cfg *old_cfg;
- cfg = get_one_free_irq_cfg(cpu);
+ cfg = get_one_free_irq_cfg(node);
if (!cfg)
return;
memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
- init_copy_irq_2_pin(old_cfg, cfg, cpu);
+ init_copy_irq_2_pin(old_cfg, cfg, node);
}
static void free_irq_cfg(struct irq_cfg *old_cfg)
old_desc->chip_data = NULL;
}
}
-
-static void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
- struct irq_cfg *cfg = desc->chip_data;
-
- if (!cfg->move_in_progress) {
- /* it means that domain is not changed */
- if (!cpumask_intersects(desc->affinity, mask))
- cfg->move_desc_pending = 1;
- }
-}
-#endif
+/* end for move_irq_desc */
#else
static struct irq_cfg *irq_cfg(unsigned int irq)
#endif
-#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC
-static inline void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-}
-#endif
-
struct io_apic {
unsigned int index;
unsigned int unused[3];
spin_unlock_irqrestore(&ioapic_lock, flags);
}
-#ifdef CONFIG_SMP
-static void send_cleanup_vector(struct irq_cfg *cfg)
-{
- cpumask_var_t cleanup_mask;
-
- if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
- unsigned int i;
- cfg->move_cleanup_count = 0;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
- cfg->move_cleanup_count++;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
- apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
- } else {
- cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
- cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
- apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
- free_cpumask_var(cleanup_mask);
- }
- cfg->move_in_progress = 0;
-}
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
- int apic, pin;
- struct irq_pin_list *entry;
- u8 vector = cfg->vector;
-
- entry = cfg->irq_2_pin;
- for (;;) {
- unsigned int reg;
-
- if (!entry)
- break;
-
- apic = entry->apic;
- pin = entry->pin;
- /*
- * With interrupt-remapping, destination information comes
- * from interrupt-remapping table entry.
- */
- if (!irq_remapped(irq))
- io_apic_write(apic, 0x11 + pin*2, dest);
- reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~IO_APIC_REDIR_VECTOR_MASK;
- reg |= vector;
- io_apic_modify(apic, 0x10 + pin*2, reg);
- if (!entry->next)
- break;
- entry = entry->next;
- }
-}
-
-static int
-assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
-
-/*
- * Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
- * leaves desc->affinity untouched.
- */
-static unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
-{
- struct irq_cfg *cfg;
- unsigned int irq;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return BAD_APICID;
-
- irq = desc->irq;
- cfg = desc->chip_data;
- if (assign_irq_vector(irq, cfg, mask))
- return BAD_APICID;
-
- /* check that before desc->addinity get updated */
- set_extra_move_desc(desc, mask);
-
- cpumask_copy(desc->affinity, mask);
-
- return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
-}
-
-static void
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- unsigned int dest;
- unsigned int irq;
-
- irq = desc->irq;
- cfg = desc->chip_data;
-
- spin_lock_irqsave(&ioapic_lock, flags);
- dest = set_desc_affinity(desc, mask);
- if (dest != BAD_APICID) {
- /* Only the high 8 bits are valid. */
- dest = SET_APIC_LOGICAL_ID(dest);
- __target_IO_APIC_irq(irq, dest, cfg);
- }
- spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
- struct irq_desc *desc;
-
- desc = irq_to_desc(irq);
-
- set_ioapic_affinity_irq_desc(desc, mask);
-}
-#endif /* CONFIG_SMP */
-
/*
* The common case is 1:1 IRQ<->pin mappings. Sometimes there are
* shared ISA-space IRQs, so we have to support them. We are super
* fast in the common case, and fast for shared ISA-space IRQs.
*/
-static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
+static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
{
struct irq_pin_list *entry;
entry = cfg->irq_2_pin;
if (!entry) {
- entry = get_one_free_irq_2_pin(cpu);
+ entry = get_one_free_irq_2_pin(node);
if (!entry) {
printk(KERN_ERR "can not alloc irq_2_pin to add %d - %d\n",
apic, pin);
entry = entry->next;
}
- entry->next = get_one_free_irq_2_pin(cpu);
+ entry->next = get_one_free_irq_2_pin(node);
entry = entry->next;
entry->apic = apic;
entry->pin = pin;
/*
* Reroute an IRQ to a different pin.
*/
-static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
+static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
int oldapic, int oldpin,
int newapic, int newpin)
{
/* why? call replace before add? */
if (!replaced)
- add_pin_to_irq_cpu(cfg, cpu, newapic, newpin);
+ add_pin_to_irq_node(cfg, node, newapic, newpin);
}
static inline void io_apic_modify_irq(struct irq_cfg *cfg,
__setup("pirq=", ioapic_pirq_setup);
#endif /* CONFIG_X86_32 */
-#ifdef CONFIG_INTR_REMAP
struct IO_APIC_route_entry **alloc_ioapic_entries(void)
{
int apic;
return 0;
}
-void reinit_intr_remapped_IO_APIC(int intr_remapping,
- struct IO_APIC_route_entry **ioapic_entries)
-
-{
- /*
- * for now plain restore of previous settings.
- * TBD: In the case of OS enabling interrupt-remapping,
- * IO-APIC RTE's need to be setup to point to interrupt-remapping
- * table entries. for now, do a plain restore, and wait for
- * the setup_IO_APIC_irqs() to do proper initialization.
- */
- restore_IO_APIC_setup(ioapic_entries);
-}
-
void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
{
int apic;
kfree(ioapic_entries);
}
-#endif
/*
* Find the IRQ entry number of a certain pin.
return -1;
}
-/*
- * Find a specific PCI IRQ entry.
- * Not an __init, possibly needed by modules
- */
-static int pin_2_irq(int idx, int apic, int pin);
-
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
-{
- int apic, i, best_guess = -1;
-
- apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
- bus, slot, pin);
- if (test_bit(bus, mp_bus_not_pci)) {
- apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
- return -1;
- }
- for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].srcbus;
-
- for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
- mp_irqs[i].dstapic == MP_APIC_ALL)
- break;
-
- if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].irqtype &&
- (bus == lbus) &&
- (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
-
- if (!(apic || IO_APIC_IRQ(irq)))
- continue;
-
- if (pin == (mp_irqs[i].srcbusirq & 3))
- return irq;
- /*
- * Use the first all-but-pin matching entry as a
- * best-guess fuzzy result for broken mptables.
- */
- if (best_guess < 0)
- best_guess = irq;
- }
- }
- return best_guess;
-}
-
-EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-
#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
/*
* EISA Edge/Level control register, ELCR
return irq;
}
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
+ struct io_apic_irq_attr *irq_attr)
+{
+ int apic, i, best_guess = -1;
+
+ apic_printk(APIC_DEBUG,
+ "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
+ bus, slot, pin);
+ if (test_bit(bus, mp_bus_not_pci)) {
+ apic_printk(APIC_VERBOSE,
+ "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
+ return -1;
+ }
+ for (i = 0; i < mp_irq_entries; i++) {
+ int lbus = mp_irqs[i].srcbus;
+
+ for (apic = 0; apic < nr_ioapics; apic++)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+ mp_irqs[i].dstapic == MP_APIC_ALL)
+ break;
+
+ if (!test_bit(lbus, mp_bus_not_pci) &&
+ !mp_irqs[i].irqtype &&
+ (bus == lbus) &&
+ (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
+
+ if (!(apic || IO_APIC_IRQ(irq)))
+ continue;
+
+ if (pin == (mp_irqs[i].srcbusirq & 3)) {
+ set_io_apic_irq_attr(irq_attr, apic,
+ mp_irqs[i].dstirq,
+ irq_trigger(i),
+ irq_polarity(i));
+ return irq;
+ }
+ /*
+ * Use the first all-but-pin matching entry as a
+ * best-guess fuzzy result for broken mptables.
+ */
+ if (best_guess < 0) {
+ set_io_apic_irq_attr(irq_attr, apic,
+ mp_irqs[i].dstirq,
+ irq_trigger(i),
+ irq_polarity(i));
+ best_guess = irq;
+ }
+ }
+ }
+ return best_guess;
+}
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+
void lock_vector_lock(void)
{
/* Used to the online set of cpus does not change
ioapic_write_entry(apic_id, pin, entry);
}
+static struct {
+ DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+} mp_ioapic_routing[MAX_IO_APICS];
+
static void __init setup_IO_APIC_irqs(void)
{
- int apic_id, pin, idx, irq;
+ int apic_id = 0, pin, idx, irq;
int notcon = 0;
struct irq_desc *desc;
struct irq_cfg *cfg;
- int cpu = boot_cpu_id;
+ int node = cpu_to_node(boot_cpu_id);
apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
- for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
- for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
-
- idx = find_irq_entry(apic_id, pin, mp_INT);
- if (idx == -1) {
- if (!notcon) {
- notcon = 1;
- apic_printk(APIC_VERBOSE,
- KERN_DEBUG " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
- } else
- apic_printk(APIC_VERBOSE, " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
- continue;
- }
- if (notcon) {
- apic_printk(APIC_VERBOSE,
- " (apicid-pin) not connected\n");
- notcon = 0;
- }
+#ifdef CONFIG_ACPI
+ if (!acpi_disabled && acpi_ioapic) {
+ apic_id = mp_find_ioapic(0);
+ if (apic_id < 0)
+ apic_id = 0;
+ }
+#endif
- irq = pin_2_irq(idx, apic_id, pin);
+ for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
+ idx = find_irq_entry(apic_id, pin, mp_INT);
+ if (idx == -1) {
+ if (!notcon) {
+ notcon = 1;
+ apic_printk(APIC_VERBOSE,
+ KERN_DEBUG " %d-%d",
+ mp_ioapics[apic_id].apicid, pin);
+ } else
+ apic_printk(APIC_VERBOSE, " %d-%d",
+ mp_ioapics[apic_id].apicid, pin);
+ continue;
+ }
+ if (notcon) {
+ apic_printk(APIC_VERBOSE,
+ " (apicid-pin) not connected\n");
+ notcon = 0;
+ }
- /*
- * Skip the timer IRQ if there's a quirk handler
- * installed and if it returns 1:
- */
- if (apic->multi_timer_check &&
- apic->multi_timer_check(apic_id, irq))
- continue;
+ irq = pin_2_irq(idx, apic_id, pin);
- desc = irq_to_desc_alloc_cpu(irq, cpu);
- if (!desc) {
- printk(KERN_INFO "can not get irq_desc for %d\n", irq);
- continue;
- }
- cfg = desc->chip_data;
- add_pin_to_irq_cpu(cfg, cpu, apic_id, pin);
+ /*
+ * Skip the timer IRQ if there's a quirk handler
+ * installed and if it returns 1:
+ */
+ if (apic->multi_timer_check &&
+ apic->multi_timer_check(apic_id, irq))
+ continue;
- setup_IO_APIC_irq(apic_id, pin, irq, desc,
- irq_trigger(idx), irq_polarity(idx));
+ desc = irq_to_desc_alloc_node(irq, node);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+ continue;
}
+ cfg = desc->chip_data;
+ add_pin_to_irq_node(cfg, node, apic_id, pin);
+ /*
+ * don't mark it in pin_programmed, so later acpi could
+ * set it correctly when irq < 16
+ */
+ setup_IO_APIC_irq(apic_id, pin, irq, desc,
+ irq_trigger(idx), irq_polarity(idx));
}
if (notcon)
__apicdebuginit(void) print_local_APIC(void *dummy)
{
- unsigned int v, ver, maxlvt;
+ unsigned int i, v, ver, maxlvt;
u64 icr;
if (apic_verbosity == APIC_QUIET)
printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
v = apic_read(APIC_TDCR);
printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+
+ if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+ v = apic_read(APIC_EFEAT);
+ maxlvt = (v >> 16) & 0xff;
+ printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v);
+ v = apic_read(APIC_ECTRL);
+ printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v);
+ for (i = 0; i < maxlvt; i++) {
+ v = apic_read(APIC_EILVTn(i));
+ printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v);
+ }
+ }
printk("\n");
}
__apicdebuginit(int) print_all_ICs(void)
{
print_PIC();
+
+ /* don't print out if apic is not there */
+ if (!cpu_has_apic || disable_apic)
+ return 0;
+
print_all_local_APICs();
print_IO_APIC();
*/
#ifdef CONFIG_SMP
+static void send_cleanup_vector(struct irq_cfg *cfg)
+{
+ cpumask_var_t cleanup_mask;
+
+ if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+ unsigned int i;
+ cfg->move_cleanup_count = 0;
+ for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ cfg->move_cleanup_count++;
+ for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+ } else {
+ cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+ cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
+ apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ free_cpumask_var(cleanup_mask);
+ }
+ cfg->move_in_progress = 0;
+}
+
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
+{
+ int apic, pin;
+ struct irq_pin_list *entry;
+ u8 vector = cfg->vector;
+
+ entry = cfg->irq_2_pin;
+ for (;;) {
+ unsigned int reg;
+
+ if (!entry)
+ break;
+
+ apic = entry->apic;
+ pin = entry->pin;
+ /*
+ * With interrupt-remapping, destination information comes
+ * from interrupt-remapping table entry.
+ */
+ if (!irq_remapped(irq))
+ io_apic_write(apic, 0x11 + pin*2, dest);
+ reg = io_apic_read(apic, 0x10 + pin*2);
+ reg &= ~IO_APIC_REDIR_VECTOR_MASK;
+ reg |= vector;
+ io_apic_modify(apic, 0x10 + pin*2, reg);
+ if (!entry->next)
+ break;
+ entry = entry->next;
+ }
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
+
+/*
+ * Either sets desc->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * leaves desc->affinity untouched.
+ */
+static unsigned int
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg;
+ unsigned int irq;
+
+ if (!cpumask_intersects(mask, cpu_online_mask))
+ return BAD_APICID;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
+ return BAD_APICID;
+
+ cpumask_copy(desc->affinity, mask);
+
+ return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+}
+
+static int
+set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ unsigned int dest;
+ unsigned int irq;
+ int ret = -1;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ dest = set_desc_affinity(desc, mask);
+ if (dest != BAD_APICID) {
+ /* Only the high 8 bits are valid. */
+ dest = SET_APIC_LOGICAL_ID(dest);
+ __target_IO_APIC_irq(irq, dest, cfg);
+ ret = 0;
+ }
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return ret;
+}
+
+static int
+set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
+{
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+
+ return set_ioapic_affinity_irq_desc(desc, mask);
+}
+
+#ifdef CONFIG_INTR_REMAP
-#ifdef CONFIG_INTR_REMAP
-
/*
* Migrate the IO-APIC irq in the presence of intr-remapping.
*
* Real vector that is used for interrupting cpu will be coming from
* the interrupt-remapping table entry.
*/
-static void
+static int
migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
{
struct irq_cfg *cfg;
struct irte irte;
unsigned int dest;
unsigned int irq;
+ int ret = -1;
if (!cpumask_intersects(mask, cpu_online_mask))
- return;
+ return ret;
irq = desc->irq;
if (get_irte(irq, &irte))
- return;
+ return ret;
cfg = desc->chip_data;
if (assign_irq_vector(irq, cfg, mask))
- return;
-
- set_extra_move_desc(desc, mask);
+ return ret;
dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
send_cleanup_vector(cfg);
cpumask_copy(desc->affinity, mask);
+
+ return 0;
}
/*
* Migrates the IRQ destination in the process context.
*/
-static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
const struct cpumask *mask)
{
- migrate_ioapic_irq_desc(desc, mask);
+ return migrate_ioapic_irq_desc(desc, mask);
}
-static void set_ir_ioapic_affinity_irq(unsigned int irq,
+static int set_ir_ioapic_affinity_irq(unsigned int irq,
const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
- set_ir_ioapic_affinity_irq_desc(desc, mask);
+ return set_ir_ioapic_affinity_irq_desc(desc, mask);
}
#else
-static inline void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
const struct cpumask *mask)
{
+ return 0;
}
#endif
struct irq_cfg *cfg = desc->chip_data;
unsigned vector, me;
- if (likely(!cfg->move_in_progress)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
- if (likely(!cfg->move_desc_pending))
- return;
-
- /* domain has not changed, but affinity did */
- me = smp_processor_id();
- if (cpumask_test_cpu(me, desc->affinity)) {
- *descp = desc = move_irq_desc(desc, me);
- /* get the new one */
- cfg = desc->chip_data;
- cfg->move_desc_pending = 0;
- }
-#endif
+ if (likely(!cfg->move_in_progress))
return;
- }
vector = ~get_irq_regs()->orig_ax;
me = smp_processor_id();
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
- *descp = desc = move_irq_desc(desc, me);
- /* get the new one */
- cfg = desc->chip_data;
-#endif
+ if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
send_cleanup_vector(cfg);
- }
}
#else
static inline void irq_complete_move(struct irq_desc **descp) {}
#endif
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
-{
- int apic, pin;
- struct irq_pin_list *entry;
-
- entry = cfg->irq_2_pin;
- for (;;) {
-
- if (!entry)
- break;
-
- apic = entry->apic;
- pin = entry->pin;
- io_apic_eoi(apic, pin);
- entry = entry->next;
- }
-}
-
-static void
-eoi_ioapic_irq(struct irq_desc *desc)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- unsigned int irq;
-
- irq = desc->irq;
- cfg = desc->chip_data;
-
- spin_lock_irqsave(&ioapic_lock, flags);
- __eoi_ioapic_irq(irq, cfg);
- spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-#ifdef CONFIG_X86_X2APIC
-static void ack_x2apic_level(unsigned int irq)
-{
- struct irq_desc *desc = irq_to_desc(irq);
- ack_x2APIC_irq();
- eoi_ioapic_irq(desc);
-}
-
-static void ack_x2apic_edge(unsigned int irq)
-{
- ack_x2APIC_irq();
-}
-#endif
-
static void ack_apic_edge(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
*/
ack_APIC_irq();
- if (irq_remapped(irq))
- eoi_ioapic_irq(desc);
-
/* Now we can move and renable the irq */
if (unlikely(do_unmask_irq)) {
/* Only migrate the irq if the ack has been received.
}
#ifdef CONFIG_INTR_REMAP
+static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+{
+ int apic, pin;
+ struct irq_pin_list *entry;
+
+ entry = cfg->irq_2_pin;
+ for (;;) {
+
+ if (!entry)
+ break;
+
+ apic = entry->apic;
+ pin = entry->pin;
+ io_apic_eoi(apic, pin);
+ entry = entry->next;
+ }
+}
+
+static void
+eoi_ioapic_irq(struct irq_desc *desc)
+{
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ unsigned int irq;
+
+ irq = desc->irq;
+ cfg = desc->chip_data;
+
+ spin_lock_irqsave(&ioapic_lock, flags);
+ __eoi_ioapic_irq(irq, cfg);
+ spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
static void ir_ack_apic_edge(unsigned int irq)
{
-#ifdef CONFIG_X86_X2APIC
- if (x2apic_enabled())
- return ack_x2apic_edge(irq);
-#endif
- return ack_apic_edge(irq);
+ ack_APIC_irq();
}
static void ir_ack_apic_level(unsigned int irq)
{
-#ifdef CONFIG_X86_X2APIC
- if (x2apic_enabled())
- return ack_x2apic_level(irq);
-#endif
- return ack_apic_level(irq);
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ ack_APIC_irq();
+ eoi_ioapic_irq(desc);
}
#endif /* CONFIG_INTR_REMAP */
{
struct irq_desc *desc = irq_to_desc(0);
struct irq_cfg *cfg = desc->chip_data;
- int cpu = boot_cpu_id;
+ int node = cpu_to_node(boot_cpu_id);
int apic1, pin1, apic2, pin2;
unsigned long flags;
int no_pin1 = 0;
* Ok, does IRQ0 through the IOAPIC work?
*/
if (no_pin1) {
- add_pin_to_irq_cpu(cfg, cpu, apic1, pin1);
+ add_pin_to_irq_node(cfg, node, apic1, pin1);
setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
} else {
/* for edge trigger, setup_IO_APIC_irq already
/*
* legacy devices should be connected to IO APIC #0
*/
- replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2);
+ replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
enable_8259A_irq(0);
if (timer_irq_works()) {
/*
* Dynamic irq allocate and deallocation
*/
-unsigned int create_irq_nr(unsigned int irq_want)
+unsigned int create_irq_nr(unsigned int irq_want, int node)
{
/* Allocate an unused irq */
unsigned int irq;
unsigned int new;
unsigned long flags;
struct irq_cfg *cfg_new = NULL;
- int cpu = boot_cpu_id;
struct irq_desc *desc_new = NULL;
irq = 0;
spin_lock_irqsave(&vector_lock, flags);
for (new = irq_want; new < nr_irqs; new++) {
- desc_new = irq_to_desc_alloc_cpu(new, cpu);
+ desc_new = irq_to_desc_alloc_node(new, node);
if (!desc_new) {
printk(KERN_INFO "can not get irq_desc for %d\n", new);
continue;
if (cfg_new->vector != 0)
continue;
+
+ desc_new = move_irq_desc(desc_new, node);
+
if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
irq = new;
break;
int create_irq(void)
{
+ int node = cpu_to_node(boot_cpu_id);
unsigned int irq_want;
int irq;
irq_want = nr_irqs_gsi;
- irq = create_irq_nr(irq_want);
+ irq = create_irq_nr(irq_want, node);
if (irq == 0)
irq = -1;
}
#ifdef CONFIG_SMP
-static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
write_msi_msg_desc(desc, &msg);
+
+ return 0;
}
#ifdef CONFIG_INTR_REMAP
/*
* Migrate the MSI irq to another cpumask. This migration is
* done in the process context using interrupt-remapping hardware.
*/
-static void
+static int
ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irte irte;
if (get_irte(irq, &irte))
- return;
+ return -1;
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
irte.vector = cfg->vector;
irte.dest_id = IRTE_DEST(dest);
*/
if (cfg->move_in_progress)
send_cleanup_vector(cfg);
+
+ return 0;
}
#endif
unsigned int irq_want;
struct intel_iommu *iommu = NULL;
int index = 0;
+ int node;
/* x86 doesn't support multiple MSI yet */
if (type == PCI_CAP_ID_MSI && nvec > 1)
return 1;
+ node = dev_to_node(&dev->dev);
irq_want = nr_irqs_gsi;
sub_handle = 0;
list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = create_irq_nr(irq_want);
+ irq = create_irq_nr(irq_want, node);
if (irq == 0)
return -1;
irq_want = irq + 1;
#if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
#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_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
dmar_msi_write(irq, &msg);
+
+ return 0;
}
#endif /* CONFIG_SMP */
#ifdef CONFIG_HPET_TIMER
#ifdef CONFIG_SMP
-static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
msg.address_lo |= MSI_ADDR_DEST_ID(dest);
hpet_msi_write(irq, &msg);
+
+ return 0;
}
#endif /* CONFIG_SMP */
write_ht_irq_msg(irq, &msg);
}
-static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
dest = set_desc_affinity(desc, mask);
if (dest == BAD_APICID)
- return;
+ return -1;
cfg = desc->chip_data;
target_ht_irq(irq, dest, cfg->vector);
+
+ return 0;
}
#endif
unsigned long flags;
int err;
+ BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
cfg = irq_cfg(irq);
err = assign_irq_vector(irq, cfg, eligible_cpu);
mmr_value = 0;
entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
- BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
+ entry->vector = cfg->vector;
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->polarity = 0;
+ entry->trigger = 0;
+ entry->mask = 0;
+ entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
mmr_pnode = uv_blade_to_pnode(mmr_blade);
uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
struct uv_IO_APIC_route_entry *entry;
int mmr_pnode;
+ BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
mmr_value = 0;
entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
- BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
entry->mask = 1;
mmr_pnode = uv_blade_to_pnode(mmr_blade);
}
#endif
+static int __io_apic_set_pci_routing(struct device *dev, int irq,
+ struct io_apic_irq_attr *irq_attr)
+{
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ int node;
+ int ioapic, pin;
+ int trigger, polarity;
+
+ ioapic = irq_attr->ioapic;
+ if (!IO_APIC_IRQ(irq)) {
+ apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+ ioapic);
+ return -EINVAL;
+ }
+
+ if (dev)
+ node = dev_to_node(dev);
+ else
+ node = cpu_to_node(boot_cpu_id);
+
+ desc = irq_to_desc_alloc_node(irq, node);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc %d\n", irq);
+ return 0;
+ }
+
+ pin = irq_attr->ioapic_pin;
+ trigger = irq_attr->trigger;
+ polarity = irq_attr->polarity;
+
+ /*
+ * IRQs < 16 are already in the irq_2_pin[] map
+ */
+ if (irq >= NR_IRQS_LEGACY) {
+ cfg = desc->chip_data;
+ add_pin_to_irq_node(cfg, node, ioapic, pin);
+ }
+
+ setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+
+ return 0;
+}
+
+int io_apic_set_pci_routing(struct device *dev, int irq,
+ struct io_apic_irq_attr *irq_attr)
+{
+ int ioapic, pin;
+ /*
+ * Avoid pin reprogramming. PRTs typically include entries
+ * with redundant pin->gsi mappings (but unique PCI devices);
+ * we only program the IOAPIC on the first.
+ */
+ ioapic = irq_attr->ioapic;
+ pin = irq_attr->ioapic_pin;
+ if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
+ pr_debug("Pin %d-%d already programmed\n",
+ mp_ioapics[ioapic].apicid, pin);
+ return 0;
+ }
+ set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
+
+ return __io_apic_set_pci_routing(dev, irq, irq_attr);
+}
+
/* --------------------------------------------------------------------------
ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
return apic_id;
}
+#endif
int __init io_apic_get_version(int ioapic)
{
return reg_01.bits.version;
}
-#endif
-
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
-{
- struct irq_desc *desc;
- struct irq_cfg *cfg;
- int cpu = boot_cpu_id;
-
- if (!IO_APIC_IRQ(irq)) {
- apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
- ioapic);
- return -EINVAL;
- }
-
- desc = irq_to_desc_alloc_cpu(irq, cpu);
- if (!desc) {
- printk(KERN_INFO "can not get irq_desc %d\n", irq);
- return 0;
- }
-
- /*
- * IRQs < 16 are already in the irq_2_pin[] map
- */
- if (irq >= NR_IRQS_LEGACY) {
- cfg = desc->chip_data;
- add_pin_to_irq_cpu(cfg, cpu, ioapic, pin);
- }
-
- setup_IO_APIC_irq(ioapic, pin, irq, desc, triggering, polarity);
-
- return 0;
-}
-
int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
{
#ifdef CONFIG_SMP
void __init setup_ioapic_dest(void)
{
- int pin, ioapic, irq, irq_entry;
+ int pin, ioapic = 0, irq, irq_entry;
struct irq_desc *desc;
- struct irq_cfg *cfg;
const struct cpumask *mask;
if (skip_ioapic_setup == 1)
return;
- for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
- for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
- irq_entry = find_irq_entry(ioapic, pin, mp_INT);
- if (irq_entry == -1)
- continue;
- irq = pin_2_irq(irq_entry, ioapic, pin);
-
- /* setup_IO_APIC_irqs could fail to get vector for some device
- * when you have too many devices, because at that time only boot
- * cpu is online.
- */
- desc = irq_to_desc(irq);
- cfg = desc->chip_data;
- if (!cfg->vector) {
- setup_IO_APIC_irq(ioapic, pin, irq, desc,
- irq_trigger(irq_entry),
- irq_polarity(irq_entry));
- continue;
+#ifdef CONFIG_ACPI
+ if (!acpi_disabled && acpi_ioapic) {
+ ioapic = mp_find_ioapic(0);
+ if (ioapic < 0)
+ ioapic = 0;
+ }
+#endif
- }
+ for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+ irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+ if (irq_entry == -1)
+ continue;
+ irq = pin_2_irq(irq_entry, ioapic, pin);
- /*
- * Honour affinities which have been set in early boot
- */
- if (desc->status &
- (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
- mask = desc->affinity;
- else
- mask = apic->target_cpus();
+ desc = irq_to_desc(irq);
- if (intr_remapping_enabled)
- set_ir_ioapic_affinity_irq_desc(desc, mask);
- else
- set_ioapic_affinity_irq_desc(desc, mask);
- }
+ /*
+ * Honour affinities which have been set in early boot
+ */
+ if (desc->status &
+ (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+ mask = desc->affinity;
+ else
+ mask = apic->target_cpus();
+ if (intr_remapping_enabled)
+ set_ir_ioapic_affinity_irq_desc(desc, mask);
+ else
+ set_ioapic_affinity_irq_desc(desc, mask);
}
+
}
#endif
}
#endif
-static void report_broken_nmi(int cpu, int *prev_nmi_count)
+static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
{
printk(KERN_CONT "\n");
extern struct apic apic_bigsmp;
extern struct apic apic_es7000;
extern struct apic apic_es7000_cluster;
-extern struct apic apic_default;
struct apic *apic = &apic_default;
EXPORT_SYMBOL_GPL(apic);
void __init default_setup_apic_routing(void)
{
#ifdef CONFIG_X86_X2APIC
- if (x2apic && (apic != &apic_x2apic_phys &&
+ if (x2apic_mode && (apic != &apic_x2apic_phys &&
#ifdef CONFIG_X86_UV
apic != &apic_x2apic_uv_x &&
#endif
rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
}
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT 4
-#define XAPIC_DEST_CPUS_MASK ((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
#define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER)
static const struct cpumask *summit_target_cpus(void)
#include <asm/apic.h>
#include <asm/ipi.h>
-DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
cpumask_set_cpu(cpu, retmask);
}
-static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
{
#ifdef CONFIG_SMP
unsigned long val;
union uvh_node_id_u node_id;
unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
- int max_pnode = 0;
+ int gnode_extra, max_pnode = 0;
unsigned long mmr_base, present, paddr;
unsigned short pnode_mask;
mmr_base =
uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
~UV_MMR_ENABLE;
+ pnode_mask = (1 << n_val) - 1;
+ node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+ gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
+ gnode_upper = ((unsigned long)gnode_extra << m_val);
+ printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
+ n_val, m_val, gnode_upper, gnode_extra);
+
printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+ BUG_ON(!uv_blade_info);
get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
+ BUG_ON(!uv_node_to_blade);
memset(uv_node_to_blade, 255, bytes);
bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
+ BUG_ON(!uv_cpu_to_blade);
memset(uv_cpu_to_blade, 255, bytes);
blade = 0;
}
}
- pnode_mask = (1 << n_val) - 1;
- node_id.v = uv_read_local_mmr(UVH_NODE_ID);
- gnode_upper = (((unsigned long)node_id.s.node_id) &
- ~((1 << n_val) - 1)) << m_val;
-
uv_bios_init();
uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
&sn_coherency_id, &sn_region_size);
uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
+ uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
+ OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
}
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
+ OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
BLANK();
DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cpu.h>
+#include <asm/pci-direct.h>
#ifdef CONFIG_X86_64
# include <asm/numa_64.h>
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
int cpu = smp_processor_id();
int node;
- unsigned apicid = hard_smp_processor_id();
+ unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
node = c->phys_proc_id;
if (apicid_to_node[apicid] != NUMA_NO_NODE)
(c->x86_model == 8 && c->x86_mask >= 8))
set_cpu_cap(c, X86_FEATURE_K6_MTRR);
#endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
+ /* check CPU config space for extended APIC ID */
+ if (c->x86 >= 0xf) {
+ unsigned int val;
+ val = read_pci_config(0, 24, 0, 0x68);
+ if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
+ set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+ }
+#endif
}
static void __cpuinit init_amd(struct cpuinfo_x86 *c)
return NULL; /* Not found */
}
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_cleared[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_set[NCAPINTS] __cpuinitdata;
void load_percpu_segment(int cpu)
{
if (this_cpu->c_identify)
this_cpu->c_identify(c);
+ /* Clear/Set all flags overriden by options, after probe */
+ for (i = 0; i < NCAPINTS; i++) {
+ c->x86_capability[i] &= ~cpu_caps_cleared[i];
+ c->x86_capability[i] |= cpu_caps_set[i];
+ }
+
#ifdef CONFIG_X86_64
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
#endif
#endif
init_hypervisor(c);
+
+ /*
+ * Clear/Set all flags overriden by options, need do it
+ * before following smp all cpus cap AND.
+ */
+ for (i = 0; i < NCAPINTS; i++) {
+ c->x86_capability[i] &= ~cpu_caps_cleared[i];
+ c->x86_capability[i] |= cpu_caps_set[i];
+ }
+
/*
* On SMP, boot_cpu_data holds the common feature set between
* all CPUs; so make sure that we indicate which features are
boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
}
- /* Clear all flags overriden by options */
- for (i = 0; i < NCAPINTS; i++)
- c->x86_capability[i] &= ~cleared_cpu_caps[i];
-
#ifdef CONFIG_X86_MCE
/* Init Machine Check Exception if available. */
mcheck_init(c);
static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
-static DEFINE_PER_CPU(unsigned, cpu_modelflag);
static DEFINE_PER_CPU(int, cpu_priv_count);
-static DEFINE_PER_CPU(unsigned, cpu_model);
static DEFINE_MUTEX(cpu_debug_lock);
{ "value", CPU_REG_ALL, 1 },
};
-/* Intel Registers Range */
-static struct cpu_debug_range cpu_intel_range[] = {
- { 0x00000000, 0x00000001, CPU_MC, CPU_INTEL_ALL },
- { 0x00000006, 0x00000007, CPU_MONITOR, CPU_CX_AT_XE },
- { 0x00000010, 0x00000010, CPU_TIME, CPU_INTEL_ALL },
- { 0x00000011, 0x00000013, CPU_PMC, CPU_INTEL_PENTIUM },
- { 0x00000017, 0x00000017, CPU_PLATFORM, CPU_PX_CX_AT_XE },
- { 0x0000001B, 0x0000001B, CPU_APIC, CPU_P6_CX_AT_XE },
-
- { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_PX_CX_AT_XE },
- { 0x0000002B, 0x0000002B, CPU_POWERON, CPU_INTEL_XEON },
- { 0x0000002C, 0x0000002C, CPU_FREQ, CPU_INTEL_XEON },
- { 0x0000003A, 0x0000003A, CPU_CONTROL, CPU_CX_AT_XE },
-
- { 0x00000040, 0x00000043, CPU_LBRANCH, CPU_PM_CX_AT_XE },
- { 0x00000044, 0x00000047, CPU_LBRANCH, CPU_PM_CO_AT },
- { 0x00000060, 0x00000063, CPU_LBRANCH, CPU_C2_AT },
- { 0x00000064, 0x00000067, CPU_LBRANCH, CPU_INTEL_ATOM },
-
- { 0x00000079, 0x00000079, CPU_BIOS, CPU_P6_CX_AT_XE },
- { 0x00000088, 0x0000008A, CPU_CACHE, CPU_INTEL_P6 },
- { 0x0000008B, 0x0000008B, CPU_BIOS, CPU_P6_CX_AT_XE },
- { 0x0000009B, 0x0000009B, CPU_MONITOR, CPU_INTEL_XEON },
-
- { 0x000000C1, 0x000000C2, CPU_PMC, CPU_P6_CX_AT },
- { 0x000000CD, 0x000000CD, CPU_FREQ, CPU_CX_AT },
- { 0x000000E7, 0x000000E8, CPU_PERF, CPU_CX_AT },
- { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_P6_CX_XE },
-
- { 0x00000116, 0x00000116, CPU_CACHE, CPU_INTEL_P6 },
- { 0x00000118, 0x00000118, CPU_CACHE, CPU_INTEL_P6 },
- { 0x00000119, 0x00000119, CPU_CACHE, CPU_INTEL_PX },
- { 0x0000011A, 0x0000011B, CPU_CACHE, CPU_INTEL_P6 },
- { 0x0000011E, 0x0000011E, CPU_CACHE, CPU_PX_CX_AT },
-
- { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_P6_CX_AT_XE },
- { 0x00000179, 0x0000017A, CPU_MC, CPU_PX_CX_AT_XE },
- { 0x0000017B, 0x0000017B, CPU_MC, CPU_P6_XE },
- { 0x00000186, 0x00000187, CPU_PMC, CPU_P6_CX_AT },
- { 0x00000198, 0x00000199, CPU_PERF, CPU_PM_CX_AT_XE },
- { 0x0000019A, 0x0000019A, CPU_TIME, CPU_PM_CX_AT_XE },
- { 0x0000019B, 0x0000019D, CPU_THERM, CPU_PM_CX_AT_XE },
- { 0x000001A0, 0x000001A0, CPU_MISC, CPU_PM_CX_AT_XE },
-
- { 0x000001C9, 0x000001C9, CPU_LBRANCH, CPU_PM_CX_AT },
- { 0x000001D7, 0x000001D8, CPU_LBRANCH, CPU_INTEL_XEON },
- { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_CX_AT_XE },
- { 0x000001DA, 0x000001DA, CPU_LBRANCH, CPU_INTEL_XEON },
- { 0x000001DB, 0x000001DB, CPU_LBRANCH, CPU_P6_XE },
- { 0x000001DC, 0x000001DC, CPU_LBRANCH, CPU_INTEL_P6 },
- { 0x000001DD, 0x000001DE, CPU_LBRANCH, CPU_PX_CX_AT_XE },
- { 0x000001E0, 0x000001E0, CPU_LBRANCH, CPU_INTEL_P6 },
-
- { 0x00000200, 0x0000020F, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000250, 0x00000250, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000258, 0x00000259, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000268, 0x0000026F, CPU_MTRR, CPU_P6_CX_XE },
- { 0x00000277, 0x00000277, CPU_PAT, CPU_C2_AT_XE },
- { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_P6_CX_XE },
-
- { 0x00000300, 0x00000308, CPU_PMC, CPU_INTEL_XEON },
- { 0x00000309, 0x0000030B, CPU_PMC, CPU_C2_AT_XE },
- { 0x0000030C, 0x00000311, CPU_PMC, CPU_INTEL_XEON },
- { 0x00000345, 0x00000345, CPU_PMC, CPU_C2_AT },
- { 0x00000360, 0x00000371, CPU_PMC, CPU_INTEL_XEON },
- { 0x0000038D, 0x00000390, CPU_PMC, CPU_C2_AT },
- { 0x000003A0, 0x000003BE, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003C0, 0x000003CD, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003E0, 0x000003E1, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003F0, 0x000003F0, CPU_PMC, CPU_INTEL_XEON },
- { 0x000003F1, 0x000003F1, CPU_PMC, CPU_C2_AT_XE },
- { 0x000003F2, 0x000003F2, CPU_PMC, CPU_INTEL_XEON },
-
- { 0x00000400, 0x00000402, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x00000403, 0x00000403, CPU_MC, CPU_INTEL_XEON },
- { 0x00000404, 0x00000406, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x00000407, 0x00000407, CPU_MC, CPU_INTEL_XEON },
- { 0x00000408, 0x0000040A, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x0000040B, 0x0000040B, CPU_MC, CPU_INTEL_XEON },
- { 0x0000040C, 0x0000040E, CPU_MC, CPU_PM_CX_XE },
- { 0x0000040F, 0x0000040F, CPU_MC, CPU_INTEL_XEON },
- { 0x00000410, 0x00000412, CPU_MC, CPU_PM_CX_AT_XE },
- { 0x00000413, 0x00000417, CPU_MC, CPU_CX_AT_XE },
- { 0x00000480, 0x0000048B, CPU_VMX, CPU_CX_AT_XE },
-
- { 0x00000600, 0x00000600, CPU_DEBUG, CPU_PM_CX_AT_XE },
- { 0x00000680, 0x0000068F, CPU_LBRANCH, CPU_INTEL_XEON },
- { 0x000006C0, 0x000006CF, CPU_LBRANCH, CPU_INTEL_XEON },
-
- { 0x000107CC, 0x000107D3, CPU_PMC, CPU_INTEL_XEON_MP },
-
- { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_INTEL_XEON },
- { 0xC0000081, 0xC0000082, CPU_CALL, CPU_INTEL_XEON },
- { 0xC0000084, 0xC0000084, CPU_CALL, CPU_INTEL_XEON },
- { 0xC0000100, 0xC0000102, CPU_BASE, CPU_INTEL_XEON },
+/* CPU Registers Range */
+static struct cpu_debug_range cpu_reg_range[] = {
+ { 0x00000000, 0x00000001, CPU_MC, },
+ { 0x00000006, 0x00000007, CPU_MONITOR, },
+ { 0x00000010, 0x00000010, CPU_TIME, },
+ { 0x00000011, 0x00000013, CPU_PMC, },
+ { 0x00000017, 0x00000017, CPU_PLATFORM, },
+ { 0x0000001B, 0x0000001B, CPU_APIC, },
+ { 0x0000002A, 0x0000002B, CPU_POWERON, },
+ { 0x0000002C, 0x0000002C, CPU_FREQ, },
+ { 0x0000003A, 0x0000003A, CPU_CONTROL, },
+ { 0x00000040, 0x00000047, CPU_LBRANCH, },
+ { 0x00000060, 0x00000067, CPU_LBRANCH, },
+ { 0x00000079, 0x00000079, CPU_BIOS, },
+ { 0x00000088, 0x0000008A, CPU_CACHE, },
+ { 0x0000008B, 0x0000008B, CPU_BIOS, },
+ { 0x0000009B, 0x0000009B, CPU_MONITOR, },
+ { 0x000000C1, 0x000000C4, CPU_PMC, },
+ { 0x000000CD, 0x000000CD, CPU_FREQ, },
+ { 0x000000E7, 0x000000E8, CPU_PERF, },
+ { 0x000000FE, 0x000000FE, CPU_MTRR, },
+
+ { 0x00000116, 0x0000011E, CPU_CACHE, },
+ { 0x00000174, 0x00000176, CPU_SYSENTER, },
+ { 0x00000179, 0x0000017B, CPU_MC, },
+ { 0x00000186, 0x00000189, CPU_PMC, },
+ { 0x00000198, 0x00000199, CPU_PERF, },
+ { 0x0000019A, 0x0000019A, CPU_TIME, },
+ { 0x0000019B, 0x0000019D, CPU_THERM, },
+ { 0x000001A0, 0x000001A0, CPU_MISC, },
+ { 0x000001C9, 0x000001C9, CPU_LBRANCH, },
+ { 0x000001D7, 0x000001D8, CPU_LBRANCH, },
+ { 0x000001D9, 0x000001D9, CPU_DEBUG, },
+ { 0x000001DA, 0x000001E0, CPU_LBRANCH, },
+
+ { 0x00000200, 0x0000020F, CPU_MTRR, },
+ { 0x00000250, 0x00000250, CPU_MTRR, },
+ { 0x00000258, 0x00000259, CPU_MTRR, },
+ { 0x00000268, 0x0000026F, CPU_MTRR, },
+ { 0x00000277, 0x00000277, CPU_PAT, },
+ { 0x000002FF, 0x000002FF, CPU_MTRR, },
+
+ { 0x00000300, 0x00000311, CPU_PMC, },
+ { 0x00000345, 0x00000345, CPU_PMC, },
+ { 0x00000360, 0x00000371, CPU_PMC, },
+ { 0x0000038D, 0x00000390, CPU_PMC, },
+ { 0x000003A0, 0x000003BE, CPU_PMC, },
+ { 0x000003C0, 0x000003CD, CPU_PMC, },
+ { 0x000003E0, 0x000003E1, CPU_PMC, },
+ { 0x000003F0, 0x000003F2, CPU_PMC, },
+
+ { 0x00000400, 0x00000417, CPU_MC, },
+ { 0x00000480, 0x0000048B, CPU_VMX, },
+
+ { 0x00000600, 0x00000600, CPU_DEBUG, },
+ { 0x00000680, 0x0000068F, CPU_LBRANCH, },
+ { 0x000006C0, 0x000006CF, CPU_LBRANCH, },
+
+ { 0x000107CC, 0x000107D3, CPU_PMC, },
+
+ { 0xC0000080, 0xC0000080, CPU_FEATURES, },
+ { 0xC0000081, 0xC0000084, CPU_CALL, },
+ { 0xC0000100, 0xC0000102, CPU_BASE, },
+ { 0xC0000103, 0xC0000103, CPU_TIME, },
+
+ { 0xC0010000, 0xC0010007, CPU_PMC, },
+ { 0xC0010010, 0xC0010010, CPU_CONF, },
+ { 0xC0010015, 0xC0010015, CPU_CONF, },
+ { 0xC0010016, 0xC001001A, CPU_MTRR, },
+ { 0xC001001D, 0xC001001D, CPU_MTRR, },
+ { 0xC001001F, 0xC001001F, CPU_CONF, },
+ { 0xC0010030, 0xC0010035, CPU_BIOS, },
+ { 0xC0010044, 0xC0010048, CPU_MC, },
+ { 0xC0010050, 0xC0010056, CPU_SMM, },
+ { 0xC0010058, 0xC0010058, CPU_CONF, },
+ { 0xC0010060, 0xC0010060, CPU_CACHE, },
+ { 0xC0010061, 0xC0010068, CPU_SMM, },
+ { 0xC0010069, 0xC001006B, CPU_SMM, },
+ { 0xC0010070, 0xC0010071, CPU_SMM, },
+ { 0xC0010111, 0xC0010113, CPU_SMM, },
+ { 0xC0010114, 0xC0010118, CPU_SVM, },
+ { 0xC0010140, 0xC0010141, CPU_OSVM, },
+ { 0xC0011022, 0xC0011023, CPU_CONF, },
};
-/* AMD Registers Range */
-static struct cpu_debug_range cpu_amd_range[] = {
- { 0x00000000, 0x00000001, CPU_MC, CPU_K10_PLUS, },
- { 0x00000010, 0x00000010, CPU_TIME, CPU_K8_PLUS, },
- { 0x0000001B, 0x0000001B, CPU_APIC, CPU_K8_PLUS, },
- { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_K7_PLUS },
- { 0x0000008B, 0x0000008B, CPU_VER, CPU_K8_PLUS },
- { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_K8_PLUS, },
-
- { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_K8_PLUS, },
- { 0x00000179, 0x0000017B, CPU_MC, CPU_K8_PLUS, },
- { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_K8_PLUS, },
- { 0x000001DB, 0x000001DE, CPU_LBRANCH, CPU_K8_PLUS, },
-
- { 0x00000200, 0x0000020F, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000250, 0x00000250, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000258, 0x00000259, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000268, 0x0000026F, CPU_MTRR, CPU_K8_PLUS, },
- { 0x00000277, 0x00000277, CPU_PAT, CPU_K8_PLUS, },
- { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_K8_PLUS, },
-
- { 0x00000400, 0x00000413, CPU_MC, CPU_K8_PLUS, },
-
- { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_AMD_ALL, },
- { 0xC0000081, 0xC0000084, CPU_CALL, CPU_K8_PLUS, },
- { 0xC0000100, 0xC0000102, CPU_BASE, CPU_K8_PLUS, },
- { 0xC0000103, 0xC0000103, CPU_TIME, CPU_K10_PLUS, },
-
- { 0xC0010000, 0xC0010007, CPU_PMC, CPU_K8_PLUS, },
- { 0xC0010010, 0xC0010010, CPU_CONF, CPU_K7_PLUS, },
- { 0xC0010015, 0xC0010015, CPU_CONF, CPU_K7_PLUS, },
- { 0xC0010016, 0xC001001A, CPU_MTRR, CPU_K8_PLUS, },
- { 0xC001001D, 0xC001001D, CPU_MTRR, CPU_K8_PLUS, },
- { 0xC001001F, 0xC001001F, CPU_CONF, CPU_K8_PLUS, },
- { 0xC0010030, 0xC0010035, CPU_BIOS, CPU_K8_PLUS, },
- { 0xC0010044, 0xC0010048, CPU_MC, CPU_K8_PLUS, },
- { 0xC0010050, 0xC0010056, CPU_SMM, CPU_K0F_PLUS, },
- { 0xC0010058, 0xC0010058, CPU_CONF, CPU_K10_PLUS, },
- { 0xC0010060, 0xC0010060, CPU_CACHE, CPU_AMD_11, },
- { 0xC0010061, 0xC0010068, CPU_SMM, CPU_K10_PLUS, },
- { 0xC0010069, 0xC001006B, CPU_SMM, CPU_AMD_11, },
- { 0xC0010070, 0xC0010071, CPU_SMM, CPU_K10_PLUS, },
- { 0xC0010111, 0xC0010113, CPU_SMM, CPU_K8_PLUS, },
- { 0xC0010114, 0xC0010118, CPU_SVM, CPU_K10_PLUS, },
- { 0xC0010140, 0xC0010141, CPU_OSVM, CPU_K10_PLUS, },
- { 0xC0011022, 0xC0011023, CPU_CONF, CPU_K10_PLUS, },
-};
-
-
-/* Intel */
-static int get_intel_modelflag(unsigned model)
-{
- int flag;
-
- switch (model) {
- case 0x0501:
- case 0x0502:
- case 0x0504:
- flag = CPU_INTEL_PENTIUM;
- break;
- case 0x0601:
- case 0x0603:
- case 0x0605:
- case 0x0607:
- case 0x0608:
- case 0x060A:
- case 0x060B:
- flag = CPU_INTEL_P6;
- break;
- case 0x0609:
- case 0x060D:
- flag = CPU_INTEL_PENTIUM_M;
- break;
- case 0x060E:
- flag = CPU_INTEL_CORE;
- break;
- case 0x060F:
- case 0x0617:
- flag = CPU_INTEL_CORE2;
- break;
- case 0x061C:
- flag = CPU_INTEL_ATOM;
- break;
- case 0x0F00:
- case 0x0F01:
- case 0x0F02:
- case 0x0F03:
- case 0x0F04:
- flag = CPU_INTEL_XEON_P4;
- break;
- case 0x0F06:
- flag = CPU_INTEL_XEON_MP;
- break;
- default:
- flag = CPU_NONE;
- break;
- }
-
- return flag;
-}
-
-/* AMD */
-static int get_amd_modelflag(unsigned model)
-{
- int flag;
-
- switch (model >> 8) {
- case 0x6:
- flag = CPU_AMD_K6;
- break;
- case 0x7:
- flag = CPU_AMD_K7;
- break;
- case 0x8:
- flag = CPU_AMD_K8;
- break;
- case 0xf:
- flag = CPU_AMD_0F;
- break;
- case 0x10:
- flag = CPU_AMD_10;
- break;
- case 0x11:
- flag = CPU_AMD_11;
- break;
- default:
- flag = CPU_NONE;
- break;
- }
-
- return flag;
-}
-
-static int get_cpu_modelflag(unsigned cpu)
-{
- int flag;
-
- flag = per_cpu(cpu_model, cpu);
-
- switch (flag >> 16) {
- case X86_VENDOR_INTEL:
- flag = get_intel_modelflag(flag);
- break;
- case X86_VENDOR_AMD:
- flag = get_amd_modelflag(flag & 0xffff);
- break;
- default:
- flag = CPU_NONE;
- break;
- }
-
- return flag;
-}
-
-static int get_cpu_range_count(unsigned cpu)
-{
- int index;
-
- switch (per_cpu(cpu_model, cpu) >> 16) {
- case X86_VENDOR_INTEL:
- index = ARRAY_SIZE(cpu_intel_range);
- break;
- case X86_VENDOR_AMD:
- index = ARRAY_SIZE(cpu_amd_range);
- break;
- default:
- index = 0;
- break;
- }
-
- return index;
-}
-
static int is_typeflag_valid(unsigned cpu, unsigned flag)
{
- unsigned vendor, modelflag;
- int i, index;
+ int i;
/* Standard Registers should be always valid */
if (flag >= CPU_TSS)
return 1;
- modelflag = per_cpu(cpu_modelflag, cpu);
- vendor = per_cpu(cpu_model, cpu) >> 16;
- index = get_cpu_range_count(cpu);
-
- for (i = 0; i < index; i++) {
- switch (vendor) {
- case X86_VENDOR_INTEL:
- if ((cpu_intel_range[i].model & modelflag) &&
- (cpu_intel_range[i].flag & flag))
- return 1;
- break;
- case X86_VENDOR_AMD:
- if ((cpu_amd_range[i].model & modelflag) &&
- (cpu_amd_range[i].flag & flag))
- return 1;
- break;
- }
+ for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
+ if (cpu_reg_range[i].flag == flag)
+ return 1;
}
/* Invalid */
static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max,
int index, unsigned flag)
{
- unsigned modelflag;
-
- modelflag = per_cpu(cpu_modelflag, cpu);
- *max = 0;
- switch (per_cpu(cpu_model, cpu) >> 16) {
- case X86_VENDOR_INTEL:
- if ((cpu_intel_range[index].model & modelflag) &&
- (cpu_intel_range[index].flag & flag)) {
- *min = cpu_intel_range[index].min;
- *max = cpu_intel_range[index].max;
- }
- break;
- case X86_VENDOR_AMD:
- if ((cpu_amd_range[index].model & modelflag) &&
- (cpu_amd_range[index].flag & flag)) {
- *min = cpu_amd_range[index].min;
- *max = cpu_amd_range[index].max;
- }
- break;
- }
+ if (cpu_reg_range[index].flag == flag) {
+ *min = cpu_reg_range[index].min;
+ *max = cpu_reg_range[index].max;
+ } else
+ *max = 0;
return *max;
}
unsigned msr, msr_min, msr_max;
struct cpu_private *priv;
u32 low, high;
- int i, range;
+ int i;
if (seq) {
priv = seq->private;
}
}
- range = get_cpu_range_count(cpu);
-
- for (i = 0; i < range; i++) {
+ for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag))
continue;
seq_printf(seq, " TMICT\t\t: %08x\n", apic_read(APIC_TMICT));
seq_printf(seq, " TMCCT\t\t: %08x\n", apic_read(APIC_TMCCT));
seq_printf(seq, " TDCR\t\t: %08x\n", apic_read(APIC_TDCR));
-#endif /* CONFIG_X86_LOCAL_APIC */
+ if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+ unsigned int i, v, maxeilvt;
+
+ v = apic_read(APIC_EFEAT);
+ maxeilvt = (v >> 16) & 0xff;
+ seq_printf(seq, " EFEAT\t\t: %08x\n", v);
+ seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL));
+ for (i = 0; i < maxeilvt; i++) {
+ v = apic_read(APIC_EILVTn(i));
+ seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v);
+ }
+ }
+#endif /* CONFIG_X86_LOCAL_APIC */
seq_printf(seq, "\n MSR\t:\n");
}
{
struct dentry *cpu_dentry = NULL;
unsigned reg, reg_min, reg_max;
- int i, range, err = 0;
+ int i, err = 0;
char reg_dir[12];
u32 low, high;
- range = get_cpu_range_count(cpu);
-
- for (i = 0; i < range; i++) {
+ for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
if (!get_cpu_range(cpu, ®_min, ®_max, i,
cpu_base[type].flag))
continue;
cpui = &cpu_data(cpu);
if (!cpu_has(cpui, X86_FEATURE_MSR))
continue;
- per_cpu(cpu_model, cpu) = ((cpui->x86_vendor << 16) |
- (cpui->x86 << 8) |
- (cpui->x86_model));
- per_cpu(cpu_modelflag, cpu) = get_cpu_modelflag(cpu);
sprintf(cpu_dir, "cpu%d", cpu);
cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir);
If in doubt, say N.
config X86_E_POWERSAVER
- tristate "VIA C7 Enhanced PowerSaver"
+ tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
select CPU_FREQ_TABLE
- depends on X86_32
+ depends on X86_32 && EXPERIMENTAL
help
- This adds the CPUFreq driver for VIA C7 processors.
+ This adds the CPUFreq driver for VIA C7 processors. However, this driver
+ does not have any safeguards to prevent operating the CPU out of spec
+ and is thus considered dangerous. Please use the regular ACPI cpufreq
+ driver, enabled by CONFIG_X86_ACPI_CPUFREQ.
If in doubt, say N.
{
struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
- if (cpu->x86_vendor != X86_VENDOR_INTEL ||
- !cpu_has(cpu, X86_FEATURE_EST))
- return 0;
-
- return 1;
+ return cpu_has(cpu, X86_FEATURE_EST);
}
static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
}
#endif
-static void __cpuinit srat_detect_node(void)
+static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
unsigned node;
int cpu = smp_processor_id();
- int apicid = hard_smp_processor_id();
+ int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
}
/* Work around errata */
- srat_detect_node();
+ srat_detect_node(c);
if (cpu_has(c, X86_FEATURE_VMX))
detect_vmx_virtcap(c);
#include <asm/processor.h>
#include <asm/smp.h>
+#include <asm/k8.h>
#define LVL_1_INST 1
#define LVL_1_DATA 2
unsigned long can_disable;
};
-#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS)
-static struct pci_device_id k8_nb_id[] = {
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
- {}
-};
-#endif
-
unsigned short num_cache_leaves;
/* AMD doesn't have CPUID4. Emulate it here to report the same
};
static const unsigned short __cpuinitconst assocs[] = {
- [1] = 1, [2] = 2, [4] = 4, [6] = 8,
- [8] = 16, [0xa] = 32, [0xb] = 48,
+ [1] = 1,
+ [2] = 2,
+ [4] = 4,
+ [6] = 8,
+ [8] = 16,
+ [0xa] = 32,
+ [0xb] = 48,
[0xc] = 64,
- [0xf] = 0xffff // ??
+ [0xd] = 96,
+ [0xe] = 128,
+ [0xf] = 0xffff /* fully associative - no way to show this currently */
};
static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 };
eax->split.type = types[leaf];
eax->split.level = levels[leaf];
if (leaf == 3)
- eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1;
+ eax->split.num_threads_sharing =
+ current_cpu_data.x86_max_cores - 1;
else
eax->split.num_threads_sharing = 0;
eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
{
if (index < 3)
return;
+
+ if (boot_cpu_data.x86 == 0x11)
+ return;
+
+ /* see erratum #382 */
+ if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8))
+ return;
+
this_leaf->can_disable = 1;
}
#define to_object(k) container_of(k, struct _index_kobject, kobj)
#define to_attr(a) container_of(a, struct _cache_attr, attr)
-#ifdef CONFIG_PCI
-static struct pci_dev *get_k8_northbridge(int node)
-{
- struct pci_dev *dev = NULL;
- int i;
-
- for (i = 0; i <= node; i++) {
- do {
- dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
- if (!dev)
- break;
- } while (!pci_match_id(&k8_nb_id[0], dev));
- if (!dev)
- break;
- }
- return dev;
-}
-#else
-static struct pci_dev *get_k8_northbridge(int node)
-{
- return NULL;
-}
-#endif
-
-static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int index)
{
- const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
- int node = cpu_to_node(cpumask_first(mask));
- struct pci_dev *dev = NULL;
- ssize_t ret = 0;
- int i;
+ int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+ int node = cpu_to_node(cpu);
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+ unsigned int reg = 0;
if (!this_leaf->can_disable)
- return sprintf(buf, "Feature not enabled\n");
-
- dev = get_k8_northbridge(node);
- if (!dev) {
- printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
return -EINVAL;
- }
- for (i = 0; i < 2; i++) {
- unsigned int reg;
+ if (!dev)
+ return -EINVAL;
- pci_read_config_dword(dev, 0x1BC + i * 4, ®);
+ pci_read_config_dword(dev, 0x1BC + index * 4, ®);
+ return sprintf(buf, "%x\n", reg);
+}
- ret += sprintf(buf, "%sEntry: %d\n", buf, i);
- ret += sprintf(buf, "%sReads: %s\tNew Entries: %s\n",
- buf,
- reg & 0x80000000 ? "Disabled" : "Allowed",
- reg & 0x40000000 ? "Disabled" : "Allowed");
- ret += sprintf(buf, "%sSubCache: %x\tIndex: %x\n",
- buf, (reg & 0x30000) >> 16, reg & 0xfff);
- }
- return ret;
+#define SHOW_CACHE_DISABLE(index) \
+static ssize_t \
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \
+{ \
+ return show_cache_disable(this_leaf, buf, index); \
}
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
-static ssize_t
-store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
- size_t count)
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+ const char *buf, size_t count, unsigned int index)
{
- const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
- int node = cpu_to_node(cpumask_first(mask));
- struct pci_dev *dev = NULL;
- unsigned int ret, index, val;
+ int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+ int node = cpu_to_node(cpu);
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+ unsigned long val = 0;
+ unsigned int scrubber = 0;
if (!this_leaf->can_disable)
- return 0;
-
- if (strlen(buf) > 15)
return -EINVAL;
- ret = sscanf(buf, "%x %x", &index, &val);
- if (ret != 2)
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!dev)
return -EINVAL;
- if (index > 1)
+
+ if (strict_strtoul(buf, 10, &val) < 0)
return -EINVAL;
val |= 0xc0000000;
- dev = get_k8_northbridge(node);
- if (!dev) {
- printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
- return -EINVAL;
- }
+
+ pci_read_config_dword(dev, 0x58, &scrubber);
+ scrubber &= ~0x1f000000;
+ pci_write_config_dword(dev, 0x58, scrubber);
pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
wbinvd();
pci_write_config_dword(dev, 0x1BC + index * 4, val);
+ return count;
+}
- return 1;
+#define STORE_CACHE_DISABLE(index) \
+static ssize_t \
+store_cache_disable_##index(struct _cpuid4_info *this_leaf, \
+ const char *buf, size_t count) \
+{ \
+ return store_cache_disable(this_leaf, buf, count, index); \
}
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
struct _cache_attr {
struct attribute attr;
define_one_ro(shared_cpu_map);
define_one_ro(shared_cpu_list);
-static struct _cache_attr cache_disable = __ATTR(cache_disable, 0644, show_cache_disable, store_cache_disable);
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+ show_cache_disable_0, store_cache_disable_0);
+static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
+ show_cache_disable_1, store_cache_disable_1);
static struct attribute * default_attrs[] = {
&type.attr,
&size.attr,
&shared_cpu_map.attr,
&shared_cpu_list.attr,
- &cache_disable.attr,
+ &cache_disable_0.attr,
+ &cache_disable_1.attr,
NULL
};
#include <asm/hw_irq.h>
#include <asm/idle.h>
#include <asm/therm_throt.h>
-#include <asm/apic.h>
asmlinkage void smp_thermal_interrupt(void)
{
if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
return 0;
- rdmsr(MTRRdefType_MSR, def, dummy);
+ rdmsr(MSR_MTRRdefType, def, dummy);
def &= 0xff;
if (def != MTRR_TYPE_UNCACHABLE)
return 0;
*/
if (!is_cpu(INTEL) || disable_mtrr_trim)
return 0;
- rdmsr(MTRRdefType_MSR, def, dummy);
+ rdmsr(MSR_MTRRdefType, def, dummy);
def &= 0xff;
if (def != MTRR_TYPE_UNCACHABLE)
return 0;
};
static struct fixed_range_block fixed_range_blocks[] = {
- { MTRRfix64K_00000_MSR, 1 }, /* one 64k MTRR */
- { MTRRfix16K_80000_MSR, 2 }, /* two 16k MTRRs */
- { MTRRfix4K_C0000_MSR, 8 }, /* eight 4k MTRRs */
+ { MSR_MTRRfix64K_00000, 1 }, /* one 64k MTRR */
+ { MSR_MTRRfix16K_80000, 2 }, /* two 16k MTRRs */
+ { MSR_MTRRfix4K_C0000, 8 }, /* eight 4k MTRRs */
{}
};
k8_check_syscfg_dram_mod_en();
- rdmsr(MTRRfix64K_00000_MSR, p[0], p[1]);
+ rdmsr(MSR_MTRRfix64K_00000, p[0], p[1]);
for (i = 0; i < 2; i++)
- rdmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2], p[3 + i * 2]);
+ rdmsr(MSR_MTRRfix16K_80000 + i, p[2 + i * 2], p[3 + i * 2]);
for (i = 0; i < 8; i++)
- rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]);
+ rdmsr(MSR_MTRRfix4K_C0000 + i, p[6 + i * 2], p[7 + i * 2]);
}
void mtrr_save_fixed_ranges(void *info)
vrs = mtrr_state.var_ranges;
- rdmsr(MTRRcap_MSR, lo, dummy);
+ rdmsr(MSR_MTRRcap, lo, dummy);
mtrr_state.have_fixed = (lo >> 8) & 1;
for (i = 0; i < num_var_ranges; i++)
if (mtrr_state.have_fixed)
get_fixed_ranges(mtrr_state.fixed_ranges);
- rdmsr(MTRRdefType_MSR, lo, dummy);
+ rdmsr(MSR_MTRRdefType, lo, dummy);
mtrr_state.def_type = (lo & 0xff);
mtrr_state.enabled = (lo & 0xc00) >> 10;
__flush_tlb();
/* Save MTRR state */
- rdmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+ rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
/* Disable MTRRs, and set the default type to uncached */
- mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & ~0xcff, deftype_hi);
+ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
}
static void post_set(void) __releases(set_atomicity_lock)
__flush_tlb();
/* Intel (P6) standard MTRRs */
- mtrr_wrmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
/* Enable caches */
write_cr0(read_cr0() & 0xbfffffff);
static int generic_have_wrcomb(void)
{
unsigned long config, dummy;
- rdmsr(MTRRcap_MSR, config, dummy);
+ rdmsr(MSR_MTRRcap, config, dummy);
return (config & (1 << 10));
}
unsigned long config = 0, dummy;
if (use_intel()) {
- rdmsr(MTRRcap_MSR, config, dummy);
+ rdmsr(MSR_MTRRcap, config, dummy);
} else if (is_cpu(AMD))
config = 2;
else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
#include <linux/types.h>
#include <linux/stddef.h>
-#define MTRRcap_MSR 0x0fe
-#define MTRRdefType_MSR 0x2ff
-
-#define MTRRfix64K_00000_MSR 0x250
-#define MTRRfix16K_80000_MSR 0x258
-#define MTRRfix16K_A0000_MSR 0x259
-#define MTRRfix4K_C0000_MSR 0x268
-#define MTRRfix4K_C8000_MSR 0x269
-#define MTRRfix4K_D0000_MSR 0x26a
-#define MTRRfix4K_D8000_MSR 0x26b
-#define MTRRfix4K_E0000_MSR 0x26c
-#define MTRRfix4K_E8000_MSR 0x26d
-#define MTRRfix4K_F0000_MSR 0x26e
-#define MTRRfix4K_F8000_MSR 0x26f
-
#define MTRR_CHANGE_MASK_FIXED 0x01
#define MTRR_CHANGE_MASK_VARIABLE 0x02
#define MTRR_CHANGE_MASK_DEFTYPE 0x04
if (use_intel())
/* Save MTRR state */
- rdmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+ rdmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
else
/* Cyrix ARRs - everything else were excluded at the top */
ctxt->ccr3 = getCx86(CX86_CCR3);
{
if (use_intel())
/* Disable MTRRs, and set the default type to uncached */
- mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo & 0xf300UL,
+ mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo & 0xf300UL,
ctxt->deftype_hi);
else if (is_cpu(CYRIX))
/* Cyrix ARRs - everything else were excluded at the top */
/* Restore MTRRdefType */
if (use_intel())
/* Intel (P6) standard MTRRs */
- mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+ mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
else
/* Cyrix ARRs - everything else was excluded at the top */
setCx86(CX86_CCR3, ctxt->ccr3);
* Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
*/
-
-#include <asm/ds.h>
-
-#include <linux/errno.h>
+#include <linux/kernel.h>
#include <linux/string.h>
-#include <linux/slab.h>
+#include <linux/errno.h>
#include <linux/sched.h>
+#include <linux/slab.h>
#include <linux/mm.h>
-#include <linux/kernel.h>
+#include <linux/trace_clock.h>
+
+#include <asm/ds.h>
+#include "ds_selftest.h"
/*
- * The configuration for a particular DS hardware implementation.
+ * The configuration for a particular DS hardware implementation:
*/
struct ds_configuration {
- /* the name of the configuration */
- const char *name;
- /* the size of one pointer-typed field in the DS structure and
- in the BTS and PEBS buffers in bytes;
- this covers the first 8 DS fields related to buffer management. */
- unsigned char sizeof_field;
- /* the size of a BTS/PEBS record in bytes */
- unsigned char sizeof_rec[2];
- /* a series of bit-masks to control various features indexed
- * by enum ds_feature */
- unsigned long ctl[dsf_ctl_max];
+ /* The name of the configuration: */
+ const char *name;
+
+ /* The size of pointer-typed fields in DS, BTS, and PEBS: */
+ unsigned char sizeof_ptr_field;
+
+ /* The size of a BTS/PEBS record in bytes: */
+ unsigned char sizeof_rec[2];
+
+ /* The number of pebs counter reset values in the DS structure. */
+ unsigned char nr_counter_reset;
+
+ /* Control bit-masks indexed by enum ds_feature: */
+ unsigned long ctl[dsf_ctl_max];
};
-static DEFINE_PER_CPU(struct ds_configuration, ds_cfg_array);
+static struct ds_configuration ds_cfg __read_mostly;
+
+
+/* Maximal size of a DS configuration: */
+#define MAX_SIZEOF_DS 0x80
-#define ds_cfg per_cpu(ds_cfg_array, smp_processor_id())
+/* Maximal size of a BTS record: */
+#define MAX_SIZEOF_BTS (3 * 8)
-#define MAX_SIZEOF_DS (12 * 8) /* maximal size of a DS configuration */
-#define MAX_SIZEOF_BTS (3 * 8) /* maximal size of a BTS record */
-#define DS_ALIGNMENT (1 << 3) /* BTS and PEBS buffer alignment */
+/* BTS and PEBS buffer alignment: */
+#define DS_ALIGNMENT (1 << 3)
-#define BTS_CONTROL \
- (ds_cfg.ctl[dsf_bts] | ds_cfg.ctl[dsf_bts_kernel] | ds_cfg.ctl[dsf_bts_user] |\
- ds_cfg.ctl[dsf_bts_overflow])
+/* Number of buffer pointers in DS: */
+#define NUM_DS_PTR_FIELDS 8
+/* Size of a pebs reset value in DS: */
+#define PEBS_RESET_FIELD_SIZE 8
+
+/* Mask of control bits in the DS MSR register: */
+#define BTS_CONTROL \
+ ( ds_cfg.ctl[dsf_bts] | \
+ ds_cfg.ctl[dsf_bts_kernel] | \
+ ds_cfg.ctl[dsf_bts_user] | \
+ ds_cfg.ctl[dsf_bts_overflow] )
/*
* A BTS or PEBS tracer.
* to identify tracers.
*/
struct ds_tracer {
- /* the DS context (partially) owned by this tracer */
- struct ds_context *context;
- /* the buffer provided on ds_request() and its size in bytes */
- void *buffer;
- size_t size;
+ /* The DS context (partially) owned by this tracer. */
+ struct ds_context *context;
+ /* The buffer provided on ds_request() and its size in bytes. */
+ void *buffer;
+ size_t size;
};
struct bts_tracer {
- /* the common DS part */
- struct ds_tracer ds;
- /* the trace including the DS configuration */
- struct bts_trace trace;
- /* buffer overflow notification function */
- bts_ovfl_callback_t ovfl;
+ /* The common DS part: */
+ struct ds_tracer ds;
+
+ /* The trace including the DS configuration: */
+ struct bts_trace trace;
+
+ /* Buffer overflow notification function: */
+ bts_ovfl_callback_t ovfl;
+
+ /* Active flags affecting trace collection. */
+ unsigned int flags;
};
struct pebs_tracer {
- /* the common DS part */
- struct ds_tracer ds;
- /* the trace including the DS configuration */
- struct pebs_trace trace;
- /* buffer overflow notification function */
- pebs_ovfl_callback_t ovfl;
+ /* The common DS part: */
+ struct ds_tracer ds;
+
+ /* The trace including the DS configuration: */
+ struct pebs_trace trace;
+
+ /* Buffer overflow notification function: */
+ pebs_ovfl_callback_t ovfl;
};
/*
*
* The DS configuration consists of the following fields; different
* architetures vary in the size of those fields.
+ *
* - double-word aligned base linear address of the BTS buffer
* - write pointer into the BTS buffer
* - end linear address of the BTS buffer (one byte beyond the end of
};
enum ds_qualifier {
- ds_bts = 0,
+ ds_bts = 0,
ds_pebs
};
-static inline unsigned long ds_get(const unsigned char *base,
- enum ds_qualifier qual, enum ds_field field)
+static inline unsigned long
+ds_get(const unsigned char *base, enum ds_qualifier qual, enum ds_field field)
{
- base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+ base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
return *(unsigned long *)base;
}
-static inline void ds_set(unsigned char *base, enum ds_qualifier qual,
- enum ds_field field, unsigned long value)
+static inline void
+ds_set(unsigned char *base, enum ds_qualifier qual, enum ds_field field,
+ unsigned long value)
{
- base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+ base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
(*(unsigned long *)base) = value;
}
*/
static DEFINE_SPINLOCK(ds_lock);
-
/*
* We either support (system-wide) per-cpu or per-thread allocation.
* We distinguish the two based on the task_struct pointer, where a
*/
static atomic_t tracers = ATOMIC_INIT(0);
-static inline void get_tracer(struct task_struct *task)
+static inline int get_tracer(struct task_struct *task)
{
- if (task)
+ int error;
+
+ spin_lock_irq(&ds_lock);
+
+ if (task) {
+ error = -EPERM;
+ if (atomic_read(&tracers) < 0)
+ goto out;
atomic_inc(&tracers);
- else
+ } else {
+ error = -EPERM;
+ if (atomic_read(&tracers) > 0)
+ goto out;
atomic_dec(&tracers);
+ }
+
+ error = 0;
+out:
+ spin_unlock_irq(&ds_lock);
+ return error;
}
static inline void put_tracer(struct task_struct *task)
atomic_inc(&tracers);
}
-static inline int check_tracer(struct task_struct *task)
-{
- return task ?
- (atomic_read(&tracers) >= 0) :
- (atomic_read(&tracers) <= 0);
-}
-
-
/*
* The DS context is either attached to a thread or to a cpu:
* - in the former case, the thread_struct contains a pointer to the
* deallocated when the last user puts the context.
*/
struct ds_context {
- /* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
- unsigned char ds[MAX_SIZEOF_DS];
- /* the owner of the BTS and PEBS configuration, respectively */
- struct bts_tracer *bts_master;
- struct pebs_tracer *pebs_master;
- /* use count */
- unsigned long count;
- /* a pointer to the context location inside the thread_struct
- * or the per_cpu context array */
- struct ds_context **this;
- /* a pointer to the task owning this context, or NULL, if the
- * context is owned by a cpu */
- struct task_struct *task;
-};
+ /* The DS configuration; goes into MSR_IA32_DS_AREA: */
+ unsigned char ds[MAX_SIZEOF_DS];
+
+ /* The owner of the BTS and PEBS configuration, respectively: */
+ struct bts_tracer *bts_master;
+ struct pebs_tracer *pebs_master;
-static DEFINE_PER_CPU(struct ds_context *, system_context_array);
+ /* Use count: */
+ unsigned long count;
-#define system_context per_cpu(system_context_array, smp_processor_id())
+ /* Pointer to the context pointer field: */
+ struct ds_context **this;
+
+ /* The traced task; NULL for cpu tracing: */
+ struct task_struct *task;
+
+ /* The traced cpu; only valid if task is NULL: */
+ int cpu;
+};
+static DEFINE_PER_CPU(struct ds_context *, cpu_context);
-static inline struct ds_context *ds_get_context(struct task_struct *task)
+
+static struct ds_context *ds_get_context(struct task_struct *task, int cpu)
{
struct ds_context **p_context =
- (task ? &task->thread.ds_ctx : &system_context);
+ (task ? &task->thread.ds_ctx : &per_cpu(cpu_context, cpu));
struct ds_context *context = NULL;
struct ds_context *new_context = NULL;
- unsigned long irq;
/* Chances are small that we already have a context. */
new_context = kzalloc(sizeof(*new_context), GFP_KERNEL);
if (!new_context)
return NULL;
- spin_lock_irqsave(&ds_lock, irq);
+ spin_lock_irq(&ds_lock);
context = *p_context;
- if (!context) {
+ if (likely(!context)) {
context = new_context;
context->this = p_context;
context->task = task;
+ context->cpu = cpu;
context->count = 0;
- if (task)
- set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
-
- if (!task || (task == current))
- wrmsrl(MSR_IA32_DS_AREA, (unsigned long)context->ds);
-
*p_context = context;
}
context->count++;
- spin_unlock_irqrestore(&ds_lock, irq);
+ spin_unlock_irq(&ds_lock);
if (context != new_context)
kfree(new_context);
return context;
}
-static inline void ds_put_context(struct ds_context *context)
+static void ds_put_context(struct ds_context *context)
{
+ struct task_struct *task;
unsigned long irq;
if (!context)
*(context->this) = NULL;
- if (context->task)
- clear_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+ task = context->task;
+
+ if (task)
+ clear_tsk_thread_flag(task, TIF_DS_AREA_MSR);
- if (!context->task || (context->task == current))
- wrmsrl(MSR_IA32_DS_AREA, 0);
+ /*
+ * We leave the (now dangling) pointer to the DS configuration in
+ * the DS_AREA msr. This is as good or as bad as replacing it with
+ * NULL - the hardware would crash if we enabled tracing.
+ *
+ * This saves us some problems with having to write an msr on a
+ * different cpu while preventing others from doing the same for the
+ * next context for that same cpu.
+ */
spin_unlock_irqrestore(&ds_lock, irq);
+ /* The context might still be in use for context switching. */
+ if (task && (task != current))
+ wait_task_context_switch(task);
+
kfree(context);
}
+static void ds_install_ds_area(struct ds_context *context)
+{
+ unsigned long ds;
+
+ ds = (unsigned long)context->ds;
+
+ /*
+ * There is a race between the bts master and the pebs master.
+ *
+ * The thread/cpu access is synchronized via get/put_cpu() for
+ * task tracing and via wrmsr_on_cpu for cpu tracing.
+ *
+ * If bts and pebs are collected for the same task or same cpu,
+ * the same confiuration is written twice.
+ */
+ if (context->task) {
+ get_cpu();
+ if (context->task == current)
+ wrmsrl(MSR_IA32_DS_AREA, ds);
+ set_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+ put_cpu();
+ } else
+ wrmsr_on_cpu(context->cpu, MSR_IA32_DS_AREA,
+ (u32)((u64)ds), (u32)((u64)ds >> 32));
+}
/*
* Call the tracer's callback on a buffer overflow.
* The remainder of any partially written record is zeroed out.
*
* context: the DS context
- * qual: the buffer type
- * record: the data to write
- * size: the size of the data
+ * qual: the buffer type
+ * record: the data to write
+ * size: the size of the data
*/
static int ds_write(struct ds_context *context, enum ds_qualifier qual,
const void *record, size_t size)
unsigned long write_size, adj_write_size;
/*
- * write as much as possible without producing an
+ * Write as much as possible without producing an
* overflow interrupt.
*
- * interrupt_threshold must either be
+ * Interrupt_threshold must either be
* - bigger than absolute_maximum or
* - point to a record between buffer_base and absolute_maximum
*
- * index points to a valid record.
+ * Index points to a valid record.
*/
base = ds_get(context->ds, qual, ds_buffer_base);
index = ds_get(context->ds, qual, ds_index);
write_end = min(end, int_th);
- /* if we are already beyond the interrupt threshold,
- * we fill the entire buffer */
+ /*
+ * If we are already beyond the interrupt threshold,
+ * we fill the entire buffer.
+ */
if (write_end <= index)
write_end = end;
adj_write_size = write_size / ds_cfg.sizeof_rec[qual];
adj_write_size *= ds_cfg.sizeof_rec[qual];
- /* zero out trailing bytes */
+ /* Zero out trailing bytes. */
memset((char *)index + write_size, 0,
adj_write_size - write_size);
index += adj_write_size;
* Later architectures use 64bit pointers throughout, whereas earlier
* architectures use 32bit pointers in 32bit mode.
*
- * We compute the base address for the first 8 fields based on:
+ * We compute the base address for the fields based on:
* - the field size stored in the DS configuration
* - the relative field position
*
bts_to,
bts_flags,
- bts_qual = bts_from,
- bts_jiffies = bts_to,
- bts_pid = bts_flags,
+ bts_qual = bts_from,
+ bts_clock = bts_to,
+ bts_pid = bts_flags,
- bts_qual_mask = (bts_qual_max - 1),
- bts_escape = ((unsigned long)-1 & ~bts_qual_mask)
+ bts_qual_mask = (bts_qual_max - 1),
+ bts_escape = ((unsigned long)-1 & ~bts_qual_mask)
};
static inline unsigned long bts_get(const char *base, enum bts_field field)
{
- base += (ds_cfg.sizeof_field * field);
+ base += (ds_cfg.sizeof_ptr_field * field);
return *(unsigned long *)base;
}
static inline void bts_set(char *base, enum bts_field field, unsigned long val)
{
- base += (ds_cfg.sizeof_field * field);;
+ base += (ds_cfg.sizeof_ptr_field * field);;
(*(unsigned long *)base) = val;
}
*
* return: bytes read/written on success; -Eerrno, otherwise
*/
-static int bts_read(struct bts_tracer *tracer, const void *at,
- struct bts_struct *out)
+static int
+bts_read(struct bts_tracer *tracer, const void *at, struct bts_struct *out)
{
if (!tracer)
return -EINVAL;
memset(out, 0, sizeof(*out));
if ((bts_get(at, bts_qual) & ~bts_qual_mask) == bts_escape) {
out->qualifier = (bts_get(at, bts_qual) & bts_qual_mask);
- out->variant.timestamp.jiffies = bts_get(at, bts_jiffies);
- out->variant.timestamp.pid = bts_get(at, bts_pid);
+ out->variant.event.clock = bts_get(at, bts_clock);
+ out->variant.event.pid = bts_get(at, bts_pid);
} else {
out->qualifier = bts_branch;
out->variant.lbr.from = bts_get(at, bts_from);
case bts_task_arrives:
case bts_task_departs:
bts_set(raw, bts_qual, (bts_escape | in->qualifier));
- bts_set(raw, bts_jiffies, in->variant.timestamp.jiffies);
- bts_set(raw, bts_pid, in->variant.timestamp.pid);
+ bts_set(raw, bts_clock, in->variant.event.clock);
+ bts_set(raw, bts_pid, in->variant.event.pid);
break;
default:
return -EINVAL;
unsigned int flags) {
unsigned long buffer, adj;
- /* adjust the buffer address and size to meet alignment
+ /*
+ * Adjust the buffer address and size to meet alignment
* constraints:
* - buffer is double-word aligned
* - size is multiple of record size
trace->begin = (void *)buffer;
trace->top = trace->begin;
trace->end = (void *)(buffer + size);
- /* The value for 'no threshold' is -1, which will set the
+ /*
+ * The value for 'no threshold' is -1, which will set the
* threshold outside of the buffer, just like we want it.
*/
+ ith *= ds_cfg.sizeof_rec[qual];
trace->ith = (void *)(buffer + size - ith);
trace->flags = flags;
static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace,
enum ds_qualifier qual, struct task_struct *task,
- void *base, size_t size, size_t th, unsigned int flags)
+ int cpu, void *base, size_t size, size_t th)
{
struct ds_context *context;
int error;
+ size_t req_size;
+
+ error = -EOPNOTSUPP;
+ if (!ds_cfg.sizeof_rec[qual])
+ goto out;
error = -EINVAL;
if (!base)
goto out;
- /* we require some space to do alignment adjustments below */
+ req_size = ds_cfg.sizeof_rec[qual];
+ /* We might need space for alignment adjustments. */
+ if (!IS_ALIGNED((unsigned long)base, DS_ALIGNMENT))
+ req_size += DS_ALIGNMENT;
+
error = -EINVAL;
- if (size < (DS_ALIGNMENT + ds_cfg.sizeof_rec[qual]))
+ if (size < req_size)
goto out;
if (th != (size_t)-1) {
tracer->size = size;
error = -ENOMEM;
- context = ds_get_context(task);
+ context = ds_get_context(task, cpu);
if (!context)
goto out;
tracer->context = context;
- ds_init_ds_trace(trace, qual, base, size, th, flags);
+ /*
+ * Defer any tracer-specific initialization work for the context until
+ * context ownership has been clarified.
+ */
error = 0;
out:
return error;
}
-struct bts_tracer *ds_request_bts(struct task_struct *task,
- void *base, size_t size,
- bts_ovfl_callback_t ovfl, size_t th,
- unsigned int flags)
+static struct bts_tracer *ds_request_bts(struct task_struct *task, int cpu,
+ void *base, size_t size,
+ bts_ovfl_callback_t ovfl, size_t th,
+ unsigned int flags)
{
struct bts_tracer *tracer;
- unsigned long irq;
int error;
+ /* Buffer overflow notification is not yet implemented. */
error = -EOPNOTSUPP;
- if (!ds_cfg.ctl[dsf_bts])
+ if (ovfl)
goto out;
- /* buffer overflow notification is not yet implemented */
- error = -EOPNOTSUPP;
- if (ovfl)
+ error = get_tracer(task);
+ if (error < 0)
goto out;
error = -ENOMEM;
tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
if (!tracer)
- goto out;
+ goto out_put_tracer;
tracer->ovfl = ovfl;
+ /* Do some more error checking and acquire a tracing context. */
error = ds_request(&tracer->ds, &tracer->trace.ds,
- ds_bts, task, base, size, th, flags);
+ ds_bts, task, cpu, base, size, th);
if (error < 0)
goto out_tracer;
-
- spin_lock_irqsave(&ds_lock, irq);
-
- error = -EPERM;
- if (!check_tracer(task))
- goto out_unlock;
- get_tracer(task);
+ /* Claim the bts part of the tracing context we acquired above. */
+ spin_lock_irq(&ds_lock);
error = -EPERM;
if (tracer->ds.context->bts_master)
- goto out_put_tracer;
+ goto out_unlock;
tracer->ds.context->bts_master = tracer;
- spin_unlock_irqrestore(&ds_lock, irq);
+ spin_unlock_irq(&ds_lock);
+ /*
+ * Now that we own the bts part of the context, let's complete the
+ * initialization for that part.
+ */
+ ds_init_ds_trace(&tracer->trace.ds, ds_bts, base, size, th, flags);
+ ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+ ds_install_ds_area(tracer->ds.context);
tracer->trace.read = bts_read;
tracer->trace.write = bts_write;
- ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+ /* Start tracing. */
ds_resume_bts(tracer);
return tracer;
- out_put_tracer:
- put_tracer(task);
out_unlock:
- spin_unlock_irqrestore(&ds_lock, irq);
+ spin_unlock_irq(&ds_lock);
ds_put_context(tracer->ds.context);
out_tracer:
kfree(tracer);
+ out_put_tracer:
+ put_tracer(task);
out:
return ERR_PTR(error);
}
-struct pebs_tracer *ds_request_pebs(struct task_struct *task,
- void *base, size_t size,
- pebs_ovfl_callback_t ovfl, size_t th,
- unsigned int flags)
+struct bts_tracer *ds_request_bts_task(struct task_struct *task,
+ void *base, size_t size,
+ bts_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags)
+{
+ return ds_request_bts(task, 0, base, size, ovfl, th, flags);
+}
+
+struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
+ bts_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags)
+{
+ return ds_request_bts(NULL, cpu, base, size, ovfl, th, flags);
+}
+
+static struct pebs_tracer *ds_request_pebs(struct task_struct *task, int cpu,
+ void *base, size_t size,
+ pebs_ovfl_callback_t ovfl, size_t th,
+ unsigned int flags)
{
struct pebs_tracer *tracer;
- unsigned long irq;
int error;
- /* buffer overflow notification is not yet implemented */
+ /* Buffer overflow notification is not yet implemented. */
error = -EOPNOTSUPP;
if (ovfl)
goto out;
+ error = get_tracer(task);
+ if (error < 0)
+ goto out;
+
error = -ENOMEM;
tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
if (!tracer)
- goto out;
+ goto out_put_tracer;
tracer->ovfl = ovfl;
+ /* Do some more error checking and acquire a tracing context. */
error = ds_request(&tracer->ds, &tracer->trace.ds,
- ds_pebs, task, base, size, th, flags);
+ ds_pebs, task, cpu, base, size, th);
if (error < 0)
goto out_tracer;
- spin_lock_irqsave(&ds_lock, irq);
-
- error = -EPERM;
- if (!check_tracer(task))
- goto out_unlock;
- get_tracer(task);
+ /* Claim the pebs part of the tracing context we acquired above. */
+ spin_lock_irq(&ds_lock);
error = -EPERM;
if (tracer->ds.context->pebs_master)
- goto out_put_tracer;
+ goto out_unlock;
tracer->ds.context->pebs_master = tracer;
- spin_unlock_irqrestore(&ds_lock, irq);
+ spin_unlock_irq(&ds_lock);
+ /*
+ * Now that we own the pebs part of the context, let's complete the
+ * initialization for that part.
+ */
+ ds_init_ds_trace(&tracer->trace.ds, ds_pebs, base, size, th, flags);
ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
+ ds_install_ds_area(tracer->ds.context);
+
+ /* Start tracing. */
ds_resume_pebs(tracer);
return tracer;
- out_put_tracer:
- put_tracer(task);
out_unlock:
- spin_unlock_irqrestore(&ds_lock, irq);
+ spin_unlock_irq(&ds_lock);
ds_put_context(tracer->ds.context);
out_tracer:
kfree(tracer);
+ out_put_tracer:
+ put_tracer(task);
out:
return ERR_PTR(error);
}
-void ds_release_bts(struct bts_tracer *tracer)
+struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
+ void *base, size_t size,
+ pebs_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags)
{
- if (!tracer)
- return;
+ return ds_request_pebs(task, 0, base, size, ovfl, th, flags);
+}
- ds_suspend_bts(tracer);
+struct pebs_tracer *ds_request_pebs_cpu(int cpu, void *base, size_t size,
+ pebs_ovfl_callback_t ovfl,
+ size_t th, unsigned int flags)
+{
+ return ds_request_pebs(NULL, cpu, base, size, ovfl, th, flags);
+}
+
+static void ds_free_bts(struct bts_tracer *tracer)
+{
+ struct task_struct *task;
+
+ task = tracer->ds.context->task;
WARN_ON_ONCE(tracer->ds.context->bts_master != tracer);
tracer->ds.context->bts_master = NULL;
- put_tracer(tracer->ds.context->task);
+ /* Make sure tracing stopped and the tracer is not in use. */
+ if (task && (task != current))
+ wait_task_context_switch(task);
+
ds_put_context(tracer->ds.context);
+ put_tracer(task);
kfree(tracer);
}
+void ds_release_bts(struct bts_tracer *tracer)
+{
+ might_sleep();
+
+ if (!tracer)
+ return;
+
+ ds_suspend_bts(tracer);
+ ds_free_bts(tracer);
+}
+
+int ds_release_bts_noirq(struct bts_tracer *tracer)
+{
+ struct task_struct *task;
+ unsigned long irq;
+ int error;
+
+ if (!tracer)
+ return 0;
+
+ task = tracer->ds.context->task;
+
+ local_irq_save(irq);
+
+ error = -EPERM;
+ if (!task &&
+ (tracer->ds.context->cpu != smp_processor_id()))
+ goto out;
+
+ error = -EPERM;
+ if (task && (task != current))
+ goto out;
+
+ ds_suspend_bts_noirq(tracer);
+ ds_free_bts(tracer);
+
+ error = 0;
+ out:
+ local_irq_restore(irq);
+ return error;
+}
+
+static void update_task_debugctlmsr(struct task_struct *task,
+ unsigned long debugctlmsr)
+{
+ task->thread.debugctlmsr = debugctlmsr;
+
+ get_cpu();
+ if (task == current)
+ update_debugctlmsr(debugctlmsr);
+ put_cpu();
+}
+
void ds_suspend_bts(struct bts_tracer *tracer)
{
struct task_struct *task;
+ unsigned long debugctlmsr;
+ int cpu;
if (!tracer)
return;
+ tracer->flags = 0;
+
task = tracer->ds.context->task;
+ cpu = tracer->ds.context->cpu;
- if (!task || (task == current))
- update_debugctlmsr(get_debugctlmsr() & ~BTS_CONTROL);
+ WARN_ON(!task && irqs_disabled());
- if (task) {
- task->thread.debugctlmsr &= ~BTS_CONTROL;
+ debugctlmsr = (task ?
+ task->thread.debugctlmsr :
+ get_debugctlmsr_on_cpu(cpu));
+ debugctlmsr &= ~BTS_CONTROL;
- if (!task->thread.debugctlmsr)
- clear_tsk_thread_flag(task, TIF_DEBUGCTLMSR);
- }
+ if (task)
+ update_task_debugctlmsr(task, debugctlmsr);
+ else
+ update_debugctlmsr_on_cpu(cpu, debugctlmsr);
}
-void ds_resume_bts(struct bts_tracer *tracer)
+int ds_suspend_bts_noirq(struct bts_tracer *tracer)
{
struct task_struct *task;
- unsigned long control;
+ unsigned long debugctlmsr, irq;
+ int cpu, error = 0;
if (!tracer)
- return;
+ return 0;
+
+ tracer->flags = 0;
task = tracer->ds.context->task;
+ cpu = tracer->ds.context->cpu;
+
+ local_irq_save(irq);
+
+ error = -EPERM;
+ if (!task && (cpu != smp_processor_id()))
+ goto out;
+
+ debugctlmsr = (task ?
+ task->thread.debugctlmsr :
+ get_debugctlmsr());
+ debugctlmsr &= ~BTS_CONTROL;
+
+ if (task)
+ update_task_debugctlmsr(task, debugctlmsr);
+ else
+ update_debugctlmsr(debugctlmsr);
+
+ error = 0;
+ out:
+ local_irq_restore(irq);
+ return error;
+}
+
+static unsigned long ds_bts_control(struct bts_tracer *tracer)
+{
+ unsigned long control;
control = ds_cfg.ctl[dsf_bts];
if (!(tracer->trace.ds.flags & BTS_KERNEL))
if (!(tracer->trace.ds.flags & BTS_USER))
control |= ds_cfg.ctl[dsf_bts_user];
- if (task) {
- task->thread.debugctlmsr |= control;
- set_tsk_thread_flag(task, TIF_DEBUGCTLMSR);
- }
-
- if (!task || (task == current))
- update_debugctlmsr(get_debugctlmsr() | control);
+ return control;
}
-void ds_release_pebs(struct pebs_tracer *tracer)
+void ds_resume_bts(struct bts_tracer *tracer)
{
+ struct task_struct *task;
+ unsigned long debugctlmsr;
+ int cpu;
+
if (!tracer)
return;
- ds_suspend_pebs(tracer);
+ tracer->flags = tracer->trace.ds.flags;
+
+ task = tracer->ds.context->task;
+ cpu = tracer->ds.context->cpu;
+
+ WARN_ON(!task && irqs_disabled());
+
+ debugctlmsr = (task ?
+ task->thread.debugctlmsr :
+ get_debugctlmsr_on_cpu(cpu));
+ debugctlmsr |= ds_bts_control(tracer);
+
+ if (task)
+ update_task_debugctlmsr(task, debugctlmsr);
+ else
+ update_debugctlmsr_on_cpu(cpu, debugctlmsr);
+}
+
+int ds_resume_bts_noirq(struct bts_tracer *tracer)
+{
+ struct task_struct *task;
+ unsigned long debugctlmsr, irq;
+ int cpu, error = 0;
+
+ if (!tracer)
+ return 0;
+
+ tracer->flags = tracer->trace.ds.flags;
+
+ task = tracer->ds.context->task;
+ cpu = tracer->ds.context->cpu;
+
+ local_irq_save(irq);
+
+ error = -EPERM;
+ if (!task && (cpu != smp_processor_id()))
+ goto out;
+
+ debugctlmsr = (task ?
+ task->thread.debugctlmsr :
+ get_debugctlmsr());
+ debugctlmsr |= ds_bts_control(tracer);
+
+ if (task)
+ update_task_debugctlmsr(task, debugctlmsr);
+ else
+ update_debugctlmsr(debugctlmsr);
+
+ error = 0;
+ out:
+ local_irq_restore(irq);
+ return error;
+}
+
+static void ds_free_pebs(struct pebs_tracer *tracer)
+{
+ struct task_struct *task;
+
+ task = tracer->ds.context->task;
WARN_ON_ONCE(tracer->ds.context->pebs_master != tracer);
tracer->ds.context->pebs_master = NULL;
- put_tracer(tracer->ds.context->task);
ds_put_context(tracer->ds.context);
+ put_tracer(task);
kfree(tracer);
}
+void ds_release_pebs(struct pebs_tracer *tracer)
+{
+ might_sleep();
+
+ if (!tracer)
+ return;
+
+ ds_suspend_pebs(tracer);
+ ds_free_pebs(tracer);
+}
+
+int ds_release_pebs_noirq(struct pebs_tracer *tracer)
+{
+ struct task_struct *task;
+ unsigned long irq;
+ int error;
+
+ if (!tracer)
+ return 0;
+
+ task = tracer->ds.context->task;
+
+ local_irq_save(irq);
+
+ error = -EPERM;
+ if (!task &&
+ (tracer->ds.context->cpu != smp_processor_id()))
+ goto out;
+
+ error = -EPERM;
+ if (task && (task != current))
+ goto out;
+
+ ds_suspend_pebs_noirq(tracer);
+ ds_free_pebs(tracer);
+
+ error = 0;
+ out:
+ local_irq_restore(irq);
+ return error;
+}
+
void ds_suspend_pebs(struct pebs_tracer *tracer)
{
}
+int ds_suspend_pebs_noirq(struct pebs_tracer *tracer)
+{
+ return 0;
+}
+
void ds_resume_pebs(struct pebs_tracer *tracer)
{
}
+int ds_resume_pebs_noirq(struct pebs_tracer *tracer)
+{
+ return 0;
+}
+
const struct bts_trace *ds_read_bts(struct bts_tracer *tracer)
{
if (!tracer)
return NULL;
ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
- tracer->trace.reset_value =
- *(u64 *)(tracer->ds.context->ds + (ds_cfg.sizeof_field * 8));
+
+ tracer->trace.counters = ds_cfg.nr_counter_reset;
+ memcpy(tracer->trace.counter_reset,
+ tracer->ds.context->ds +
+ (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field),
+ ds_cfg.nr_counter_reset * PEBS_RESET_FIELD_SIZE);
return &tracer->trace;
}
tracer->trace.ds.top = tracer->trace.ds.begin;
- ds_set(tracer->ds.context->ds, ds_bts, ds_index,
+ ds_set(tracer->ds.context->ds, ds_pebs, ds_index,
(unsigned long)tracer->trace.ds.top);
return 0;
}
-int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value)
+int ds_set_pebs_reset(struct pebs_tracer *tracer,
+ unsigned int counter, u64 value)
{
if (!tracer)
return -EINVAL;
- *(u64 *)(tracer->ds.context->ds + (ds_cfg.sizeof_field * 8)) = value;
+ if (ds_cfg.nr_counter_reset < counter)
+ return -EINVAL;
+
+ *(u64 *)(tracer->ds.context->ds +
+ (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field) +
+ (counter * PEBS_RESET_FIELD_SIZE)) = value;
return 0;
}
.ctl[dsf_bts] = (1 << 2) | (1 << 3),
.ctl[dsf_bts_kernel] = (1 << 5),
.ctl[dsf_bts_user] = (1 << 6),
-
- .sizeof_field = sizeof(long),
- .sizeof_rec[ds_bts] = sizeof(long) * 3,
-#ifdef __i386__
- .sizeof_rec[ds_pebs] = sizeof(long) * 10,
-#else
- .sizeof_rec[ds_pebs] = sizeof(long) * 18,
-#endif
+ .nr_counter_reset = 1,
};
static const struct ds_configuration ds_cfg_pentium_m = {
.name = "Pentium M",
.ctl[dsf_bts] = (1 << 6) | (1 << 7),
-
- .sizeof_field = sizeof(long),
- .sizeof_rec[ds_bts] = sizeof(long) * 3,
-#ifdef __i386__
- .sizeof_rec[ds_pebs] = sizeof(long) * 10,
-#else
- .sizeof_rec[ds_pebs] = sizeof(long) * 18,
-#endif
+ .nr_counter_reset = 1,
};
static const struct ds_configuration ds_cfg_core2_atom = {
.name = "Core 2/Atom",
.ctl[dsf_bts] = (1 << 6) | (1 << 7),
.ctl[dsf_bts_kernel] = (1 << 9),
.ctl[dsf_bts_user] = (1 << 10),
-
- .sizeof_field = 8,
- .sizeof_rec[ds_bts] = 8 * 3,
- .sizeof_rec[ds_pebs] = 8 * 18,
+ .nr_counter_reset = 1,
+};
+static const struct ds_configuration ds_cfg_core_i7 = {
+ .name = "Core i7",
+ .ctl[dsf_bts] = (1 << 6) | (1 << 7),
+ .ctl[dsf_bts_kernel] = (1 << 9),
+ .ctl[dsf_bts_user] = (1 << 10),
+ .nr_counter_reset = 4,
};
static void
-ds_configure(const struct ds_configuration *cfg)
+ds_configure(const struct ds_configuration *cfg,
+ struct cpuinfo_x86 *cpu)
{
+ unsigned long nr_pebs_fields = 0;
+
+ printk(KERN_INFO "[ds] using %s configuration\n", cfg->name);
+
+#ifdef __i386__
+ nr_pebs_fields = 10;
+#else
+ nr_pebs_fields = 18;
+#endif
+
+ /*
+ * Starting with version 2, architectural performance
+ * monitoring supports a format specifier.
+ */
+ if ((cpuid_eax(0xa) & 0xff) > 1) {
+ unsigned long perf_capabilities, format;
+
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
+
+ format = (perf_capabilities >> 8) & 0xf;
+
+ switch (format) {
+ case 0:
+ nr_pebs_fields = 18;
+ break;
+ case 1:
+ nr_pebs_fields = 22;
+ break;
+ default:
+ printk(KERN_INFO
+ "[ds] unknown PEBS format: %lu\n", format);
+ nr_pebs_fields = 0;
+ break;
+ }
+ }
+
memset(&ds_cfg, 0, sizeof(ds_cfg));
ds_cfg = *cfg;
- printk(KERN_INFO "[ds] using %s configuration\n", ds_cfg.name);
+ ds_cfg.sizeof_ptr_field =
+ (cpu_has(cpu, X86_FEATURE_DTES64) ? 8 : 4);
+
+ ds_cfg.sizeof_rec[ds_bts] = ds_cfg.sizeof_ptr_field * 3;
+ ds_cfg.sizeof_rec[ds_pebs] = ds_cfg.sizeof_ptr_field * nr_pebs_fields;
- if (!cpu_has_bts) {
- ds_cfg.ctl[dsf_bts] = 0;
+ if (!cpu_has(cpu, X86_FEATURE_BTS)) {
+ ds_cfg.sizeof_rec[ds_bts] = 0;
printk(KERN_INFO "[ds] bts not available\n");
}
- if (!cpu_has_pebs)
+ if (!cpu_has(cpu, X86_FEATURE_PEBS)) {
+ ds_cfg.sizeof_rec[ds_pebs] = 0;
printk(KERN_INFO "[ds] pebs not available\n");
+ }
+
+ printk(KERN_INFO "[ds] sizes: address: %u bit, ",
+ 8 * ds_cfg.sizeof_ptr_field);
+ printk("bts/pebs record: %u/%u bytes\n",
+ ds_cfg.sizeof_rec[ds_bts], ds_cfg.sizeof_rec[ds_pebs]);
- WARN_ON_ONCE(MAX_SIZEOF_DS < (12 * ds_cfg.sizeof_field));
+ WARN_ON_ONCE(MAX_PEBS_COUNTERS < ds_cfg.nr_counter_reset);
}
void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
{
+ /* Only configure the first cpu. Others are identical. */
+ if (ds_cfg.name)
+ return;
+
switch (c->x86) {
case 0x6:
switch (c->x86_model) {
case 0x9:
case 0xd: /* Pentium M */
- ds_configure(&ds_cfg_pentium_m);
+ ds_configure(&ds_cfg_pentium_m, c);
break;
case 0xf:
case 0x17: /* Core2 */
case 0x1c: /* Atom */
- ds_configure(&ds_cfg_core2_atom);
+ ds_configure(&ds_cfg_core2_atom, c);
+ break;
+ case 0x1a: /* Core i7 */
+ ds_configure(&ds_cfg_core_i7, c);
break;
- case 0x1a: /* i7 */
default:
- /* sorry, don't know about them */
+ /* Sorry, don't know about them. */
break;
}
break;
case 0x0:
case 0x1:
case 0x2: /* Netburst */
- ds_configure(&ds_cfg_netburst);
+ ds_configure(&ds_cfg_netburst, c);
break;
default:
- /* sorry, don't know about them */
+ /* Sorry, don't know about them. */
break;
}
break;
default:
- /* sorry, don't know about them */
+ /* Sorry, don't know about them. */
break;
}
}
+static inline void ds_take_timestamp(struct ds_context *context,
+ enum bts_qualifier qualifier,
+ struct task_struct *task)
+{
+ struct bts_tracer *tracer = context->bts_master;
+ struct bts_struct ts;
+
+ /* Prevent compilers from reading the tracer pointer twice. */
+ barrier();
+
+ if (!tracer || !(tracer->flags & BTS_TIMESTAMPS))
+ return;
+
+ memset(&ts, 0, sizeof(ts));
+ ts.qualifier = qualifier;
+ ts.variant.event.clock = trace_clock_global();
+ ts.variant.event.pid = task->pid;
+
+ bts_write(tracer, &ts);
+}
+
/*
* Change the DS configuration from tracing prev to tracing next.
*/
void ds_switch_to(struct task_struct *prev, struct task_struct *next)
{
- struct ds_context *prev_ctx = prev->thread.ds_ctx;
- struct ds_context *next_ctx = next->thread.ds_ctx;
+ struct ds_context *prev_ctx = prev->thread.ds_ctx;
+ struct ds_context *next_ctx = next->thread.ds_ctx;
+ unsigned long debugctlmsr = next->thread.debugctlmsr;
+
+ /* Make sure all data is read before we start. */
+ barrier();
if (prev_ctx) {
update_debugctlmsr(0);
- if (prev_ctx->bts_master &&
- (prev_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
- struct bts_struct ts = {
- .qualifier = bts_task_departs,
- .variant.timestamp.jiffies = jiffies_64,
- .variant.timestamp.pid = prev->pid
- };
- bts_write(prev_ctx->bts_master, &ts);
- }
+ ds_take_timestamp(prev_ctx, bts_task_departs, prev);
}
if (next_ctx) {
- if (next_ctx->bts_master &&
- (next_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
- struct bts_struct ts = {
- .qualifier = bts_task_arrives,
- .variant.timestamp.jiffies = jiffies_64,
- .variant.timestamp.pid = next->pid
- };
- bts_write(next_ctx->bts_master, &ts);
- }
+ ds_take_timestamp(next_ctx, bts_task_arrives, next);
wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds);
}
- update_debugctlmsr(next->thread.debugctlmsr);
+ update_debugctlmsr(debugctlmsr);
}
-void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
+static __init int ds_selftest(void)
{
- clear_tsk_thread_flag(tsk, TIF_DS_AREA_MSR);
- tsk->thread.ds_ctx = NULL;
-}
+ if (ds_cfg.sizeof_rec[ds_bts]) {
+ int error;
-void ds_exit_thread(struct task_struct *tsk)
-{
+ error = ds_selftest_bts();
+ if (error) {
+ WARN(1, "[ds] selftest failed. disabling bts.\n");
+ ds_cfg.sizeof_rec[ds_bts] = 0;
+ }
+ }
+
+ if (ds_cfg.sizeof_rec[ds_pebs]) {
+ int error;
+
+ error = ds_selftest_pebs();
+ if (error) {
+ WARN(1, "[ds] selftest failed. disabling pebs.\n");
+ ds_cfg.sizeof_rec[ds_pebs] = 0;
+ }
+ }
+
+ return 0;
}
+device_initcall(ds_selftest);
--- /dev/null
+/*
+ * Debug Store support - selftest
+ *
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2009
+ */
+
+#include "ds_selftest.h"
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+
+#include <asm/ds.h>
+
+
+#define BUFFER_SIZE 521 /* Intentionally chose an odd size. */
+#define SMALL_BUFFER_SIZE 24 /* A single bts entry. */
+
+struct ds_selftest_bts_conf {
+ struct bts_tracer *tracer;
+ int error;
+ int (*suspend)(struct bts_tracer *);
+ int (*resume)(struct bts_tracer *);
+};
+
+static int ds_selftest_bts_consistency(const struct bts_trace *trace)
+{
+ int error = 0;
+
+ if (!trace) {
+ printk(KERN_CONT "failed to access trace...");
+ /* Bail out. Other tests are pointless. */
+ return -1;
+ }
+
+ if (!trace->read) {
+ printk(KERN_CONT "bts read not available...");
+ error = -1;
+ }
+
+ /* Do some sanity checks on the trace configuration. */
+ if (!trace->ds.n) {
+ printk(KERN_CONT "empty bts buffer...");
+ error = -1;
+ }
+ if (!trace->ds.size) {
+ printk(KERN_CONT "bad bts trace setup...");
+ error = -1;
+ }
+ if (trace->ds.end !=
+ (char *)trace->ds.begin + (trace->ds.n * trace->ds.size)) {
+ printk(KERN_CONT "bad bts buffer setup...");
+ error = -1;
+ }
+ /*
+ * We allow top in [begin; end], since its not clear when the
+ * overflow adjustment happens: after the increment or before the
+ * write.
+ */
+ if ((trace->ds.top < trace->ds.begin) ||
+ (trace->ds.end < trace->ds.top)) {
+ printk(KERN_CONT "bts top out of bounds...");
+ error = -1;
+ }
+
+ return error;
+}
+
+static int ds_selftest_bts_read(struct bts_tracer *tracer,
+ const struct bts_trace *trace,
+ const void *from, const void *to)
+{
+ const unsigned char *at;
+
+ /*
+ * Check a few things which do not belong to this test.
+ * They should be covered by other tests.
+ */
+ if (!trace)
+ return -1;
+
+ if (!trace->read)
+ return -1;
+
+ if (to < from)
+ return -1;
+
+ if (from < trace->ds.begin)
+ return -1;
+
+ if (trace->ds.end < to)
+ return -1;
+
+ if (!trace->ds.size)
+ return -1;
+
+ /* Now to the test itself. */
+ for (at = from; (void *)at < to; at += trace->ds.size) {
+ struct bts_struct bts;
+ unsigned long index;
+ int error;
+
+ if (((void *)at - trace->ds.begin) % trace->ds.size) {
+ printk(KERN_CONT
+ "read from non-integer index...");
+ return -1;
+ }
+ index = ((void *)at - trace->ds.begin) / trace->ds.size;
+
+ memset(&bts, 0, sizeof(bts));
+ error = trace->read(tracer, at, &bts);
+ if (error < 0) {
+ printk(KERN_CONT
+ "error reading bts trace at [%lu] (0x%p)...",
+ index, at);
+ return error;
+ }
+
+ switch (bts.qualifier) {
+ case BTS_BRANCH:
+ break;
+ default:
+ printk(KERN_CONT
+ "unexpected bts entry %llu at [%lu] (0x%p)...",
+ bts.qualifier, index, at);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static void ds_selftest_bts_cpu(void *arg)
+{
+ struct ds_selftest_bts_conf *conf = arg;
+ const struct bts_trace *trace;
+ void *top;
+
+ if (IS_ERR(conf->tracer)) {
+ conf->error = PTR_ERR(conf->tracer);
+ conf->tracer = NULL;
+
+ printk(KERN_CONT
+ "initialization failed (err: %d)...", conf->error);
+ return;
+ }
+
+ /* We should meanwhile have enough trace. */
+ conf->error = conf->suspend(conf->tracer);
+ if (conf->error < 0)
+ return;
+
+ /* Let's see if we can access the trace. */
+ trace = ds_read_bts(conf->tracer);
+
+ conf->error = ds_selftest_bts_consistency(trace);
+ if (conf->error < 0)
+ return;
+
+ /* If everything went well, we should have a few trace entries. */
+ if (trace->ds.top == trace->ds.begin) {
+ /*
+ * It is possible but highly unlikely that we got a
+ * buffer overflow and end up at exactly the same
+ * position we started from.
+ * Let's issue a warning, but continue.
+ */
+ printk(KERN_CONT "no trace/overflow...");
+ }
+
+ /* Let's try to read the trace we collected. */
+ conf->error =
+ ds_selftest_bts_read(conf->tracer, trace,
+ trace->ds.begin, trace->ds.top);
+ if (conf->error < 0)
+ return;
+
+ /*
+ * Let's read the trace again.
+ * Since we suspended tracing, we should get the same result.
+ */
+ top = trace->ds.top;
+
+ trace = ds_read_bts(conf->tracer);
+ conf->error = ds_selftest_bts_consistency(trace);
+ if (conf->error < 0)
+ return;
+
+ if (top != trace->ds.top) {
+ printk(KERN_CONT "suspend not working...");
+ conf->error = -1;
+ return;
+ }
+
+ /* Let's collect some more trace - see if resume is working. */
+ conf->error = conf->resume(conf->tracer);
+ if (conf->error < 0)
+ return;
+
+ conf->error = conf->suspend(conf->tracer);
+ if (conf->error < 0)
+ return;
+
+ trace = ds_read_bts(conf->tracer);
+
+ conf->error = ds_selftest_bts_consistency(trace);
+ if (conf->error < 0)
+ return;
+
+ if (trace->ds.top == top) {
+ /*
+ * It is possible but highly unlikely that we got a
+ * buffer overflow and end up at exactly the same
+ * position we started from.
+ * Let's issue a warning and check the full trace.
+ */
+ printk(KERN_CONT
+ "no resume progress/overflow...");
+
+ conf->error =
+ ds_selftest_bts_read(conf->tracer, trace,
+ trace->ds.begin, trace->ds.end);
+ } else if (trace->ds.top < top) {
+ /*
+ * We had a buffer overflow - the entire buffer should
+ * contain trace records.
+ */
+ conf->error =
+ ds_selftest_bts_read(conf->tracer, trace,
+ trace->ds.begin, trace->ds.end);
+ } else {
+ /*
+ * It is quite likely that the buffer did not overflow.
+ * Let's just check the delta trace.
+ */
+ conf->error =
+ ds_selftest_bts_read(conf->tracer, trace, top,
+ trace->ds.top);
+ }
+ if (conf->error < 0)
+ return;
+
+ conf->error = 0;
+}
+
+static int ds_suspend_bts_wrap(struct bts_tracer *tracer)
+{
+ ds_suspend_bts(tracer);
+ return 0;
+}
+
+static int ds_resume_bts_wrap(struct bts_tracer *tracer)
+{
+ ds_resume_bts(tracer);
+ return 0;
+}
+
+static void ds_release_bts_noirq_wrap(void *tracer)
+{
+ (void)ds_release_bts_noirq(tracer);
+}
+
+static int ds_selftest_bts_bad_release_noirq(int cpu,
+ struct bts_tracer *tracer)
+{
+ int error = -EPERM;
+
+ /* Try to release the tracer on the wrong cpu. */
+ get_cpu();
+ if (cpu != smp_processor_id()) {
+ error = ds_release_bts_noirq(tracer);
+ if (error != -EPERM)
+ printk(KERN_CONT "release on wrong cpu...");
+ }
+ put_cpu();
+
+ return error ? 0 : -1;
+}
+
+static int ds_selftest_bts_bad_request_cpu(int cpu, void *buffer)
+{
+ struct bts_tracer *tracer;
+ int error;
+
+ /* Try to request cpu tracing while task tracing is active. */
+ tracer = ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, NULL,
+ (size_t)-1, BTS_KERNEL);
+ error = PTR_ERR(tracer);
+ if (!IS_ERR(tracer)) {
+ ds_release_bts(tracer);
+ error = 0;
+ }
+
+ if (error != -EPERM)
+ printk(KERN_CONT "cpu/task tracing overlap...");
+
+ return error ? 0 : -1;
+}
+
+static int ds_selftest_bts_bad_request_task(void *buffer)
+{
+ struct bts_tracer *tracer;
+ int error;
+
+ /* Try to request cpu tracing while task tracing is active. */
+ tracer = ds_request_bts_task(current, buffer, BUFFER_SIZE, NULL,
+ (size_t)-1, BTS_KERNEL);
+ error = PTR_ERR(tracer);
+ if (!IS_ERR(tracer)) {
+ error = 0;
+ ds_release_bts(tracer);
+ }
+
+ if (error != -EPERM)
+ printk(KERN_CONT "task/cpu tracing overlap...");
+
+ return error ? 0 : -1;
+}
+
+int ds_selftest_bts(void)
+{
+ struct ds_selftest_bts_conf conf;
+ unsigned char buffer[BUFFER_SIZE], *small_buffer;
+ unsigned long irq;
+ int cpu;
+
+ printk(KERN_INFO "[ds] bts selftest...");
+ conf.error = 0;
+
+ small_buffer = (unsigned char *)ALIGN((unsigned long)buffer, 8) + 8;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ conf.suspend = ds_suspend_bts_wrap;
+ conf.resume = ds_resume_bts_wrap;
+ conf.tracer =
+ ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
+ NULL, (size_t)-1, BTS_KERNEL);
+ ds_selftest_bts_cpu(&conf);
+ if (conf.error >= 0)
+ conf.error = ds_selftest_bts_bad_request_task(buffer);
+ ds_release_bts(conf.tracer);
+ if (conf.error < 0)
+ goto out;
+
+ conf.suspend = ds_suspend_bts_noirq;
+ conf.resume = ds_resume_bts_noirq;
+ conf.tracer =
+ ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
+ NULL, (size_t)-1, BTS_KERNEL);
+ smp_call_function_single(cpu, ds_selftest_bts_cpu, &conf, 1);
+ if (conf.error >= 0) {
+ conf.error =
+ ds_selftest_bts_bad_release_noirq(cpu,
+ conf.tracer);
+ /* We must not release the tracer twice. */
+ if (conf.error < 0)
+ conf.tracer = NULL;
+ }
+ if (conf.error >= 0)
+ conf.error = ds_selftest_bts_bad_request_task(buffer);
+ smp_call_function_single(cpu, ds_release_bts_noirq_wrap,
+ conf.tracer, 1);
+ if (conf.error < 0)
+ goto out;
+ }
+
+ conf.suspend = ds_suspend_bts_wrap;
+ conf.resume = ds_resume_bts_wrap;
+ conf.tracer =
+ ds_request_bts_task(current, buffer, BUFFER_SIZE,
+ NULL, (size_t)-1, BTS_KERNEL);
+ ds_selftest_bts_cpu(&conf);
+ if (conf.error >= 0)
+ conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
+ ds_release_bts(conf.tracer);
+ if (conf.error < 0)
+ goto out;
+
+ conf.suspend = ds_suspend_bts_noirq;
+ conf.resume = ds_resume_bts_noirq;
+ conf.tracer =
+ ds_request_bts_task(current, small_buffer, SMALL_BUFFER_SIZE,
+ NULL, (size_t)-1, BTS_KERNEL);
+ local_irq_save(irq);
+ ds_selftest_bts_cpu(&conf);
+ if (conf.error >= 0)
+ conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
+ ds_release_bts_noirq(conf.tracer);
+ local_irq_restore(irq);
+ if (conf.error < 0)
+ goto out;
+
+ conf.error = 0;
+ out:
+ put_online_cpus();
+ printk(KERN_CONT "%s.\n", (conf.error ? "failed" : "passed"));
+
+ return conf.error;
+}
+
+int ds_selftest_pebs(void)
+{
+ return 0;
+}
--- /dev/null
+/*
+ * Debug Store support - selftest
+ *
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2009
+ */
+
+#ifdef CONFIG_X86_DS_SELFTEST
+extern int ds_selftest_bts(void);
+extern int ds_selftest_pebs(void);
+#else
+static inline int ds_selftest_bts(void) { return 0; }
+static inline int ds_selftest_pebs(void) { return 0; }
+#endif
unsigned long *sp, unsigned long bp, char *log_lvl);
extern unsigned int code_bytes;
-extern int kstack_depth_to_print;
/* The form of the top of the frame on the stack */
struct stack_frame {
*/
__init void e820_setup_gap(void)
{
- unsigned long gapstart, gapsize, round;
+ unsigned long gapstart, gapsize;
int found;
gapstart = 0x10000000;
#endif
/*
- * See how much we want to round up: start off with
- * rounding to the next 1MB area.
+ * e820_reserve_resources_late protect stolen RAM already
*/
- round = 0x100000;
- while ((gapsize >> 4) > round)
- round += round;
- /* Fun with two's complement */
- pci_mem_start = (gapstart + round) & -round;
+ pci_mem_start = gapstart;
printk(KERN_INFO
"Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
}
}
+/* How much should we pad RAM ending depending on where it is? */
+static unsigned long ram_alignment(resource_size_t pos)
+{
+ unsigned long mb = pos >> 20;
+
+ /* To 64kB in the first megabyte */
+ if (!mb)
+ return 64*1024;
+
+ /* To 1MB in the first 16MB */
+ if (mb < 16)
+ return 1024*1024;
+
+ /* To 32MB for anything above that */
+ return 32*1024*1024;
+}
+
void __init e820_reserve_resources_late(void)
{
int i;
insert_resource_expand_to_fit(&iomem_resource, res);
res++;
}
+
+ /*
+ * Try to bump up RAM regions to reasonable boundaries to
+ * avoid stolen RAM:
+ */
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *entry = &e820_saved.map[i];
+ resource_size_t start, end;
+
+ if (entry->type != E820_RAM)
+ continue;
+ start = entry->addr + entry->size;
+ end = round_up(start, ram_alignment(start));
+ if (start == end)
+ continue;
+ reserve_region_with_split(&iomem_resource, start,
+ end - 1, "RAM buffer");
+ }
}
char *__init default_machine_specific_memory_setup(void)
}
+#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
{
d &= 0xff;
return d;
}
+#endif
static void __init ati_bugs(int num, int slot, int func)
{
GLOBAL(return_to_handler)
subq $80, %rsp
+ /* Save the return values */
movq %rax, (%rsp)
- movq %rcx, 8(%rsp)
- movq %rdx, 16(%rsp)
- movq %rsi, 24(%rsp)
- movq %rdi, 32(%rsp)
- movq %r8, 40(%rsp)
- movq %r9, 48(%rsp)
- movq %r10, 56(%rsp)
- movq %r11, 64(%rsp)
+ movq %rdx, 8(%rsp)
call ftrace_return_to_handler
movq %rax, 72(%rsp)
- movq 64(%rsp), %r11
- movq 56(%rsp), %r10
- movq 48(%rsp), %r9
- movq 40(%rsp), %r8
- movq 32(%rsp), %rdi
- movq 24(%rsp), %rsi
- movq 16(%rsp), %rdx
- movq 8(%rsp), %rcx
+ movq 8(%rsp), %rdx
movq (%rsp), %rax
addq $72, %rsp
retq
paranoidzeroentry_ist debug do_debug DEBUG_STACK
paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
paranoiderrorentry stack_segment do_stack_segment
+#ifdef CONFIG_XEN
+zeroentry xen_debug do_debug
+zeroentry xen_int3 do_int3
+errorentry xen_stack_segment do_stack_segment
+#endif
errorentry general_protection do_general_protection
errorentry page_fault do_page_fault
#ifdef CONFIG_X86_MCE
ENTRY(initial_code)
.long i386_start_kernel
-.section .text
-/*
- * Real beginning of normal "text" segment
- */
-ENTRY(stext)
-ENTRY(_stext)
-
/*
* BSS section
*/
#include <asm/io_apic.h>
#include <asm/irq.h>
#include <asm/idle.h>
+#include <asm/hw_irq.h>
atomic_t irq_err_count;
*/
void ack_bad_irq(unsigned int irq)
{
- printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq);
+ if (printk_ratelimit())
+ pr_err("unexpected IRQ trap at vector %02x\n", irq);
-#ifdef CONFIG_X86_LOCAL_APIC
/*
* Currently unexpected vectors happen only on SMP and APIC.
* We _must_ ack these because every local APIC has only N
* completely.
* But only ack when the APIC is enabled -AK
*/
- if (cpu_has_apic)
- ack_APIC_irq();
-#endif
+ ack_APIC_irq();
}
#define irq_stats(x) (&per_cpu(irq_stat, x))
sum += irq_stats(cpu)->irq_thermal_count;
# ifdef CONFIG_X86_64
sum += irq_stats(cpu)->irq_threshold_count;
-#endif
+# endif
#endif
return sum;
}
irq = __get_cpu_var(vector_irq)[vector];
if (!handle_irq(irq, regs)) {
-#ifdef CONFIG_X86_64
- if (!disable_apic)
- ack_APIC_irq();
-#endif
+ ack_APIC_irq();
if (printk_ratelimit())
- printk(KERN_EMERG "%s: %d.%d No irq handler for vector (irq %d)\n",
- __func__, smp_processor_id(), vector, irq);
+ pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
+ __func__, smp_processor_id(), vector, irq);
}
irq_exit();
--- /dev/null
+#include <linux/linkage.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/kprobes.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/timer.h>
+#include <asm/hw_irq.h>
+#include <asm/pgtable.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/setup.h>
+#include <asm/i8259.h>
+#include <asm/traps.h>
+
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
+
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+
+#ifdef CONFIG_X86_32
+/*
+ * Note that on a 486, we don't want to do a SIGFPE on an irq13
+ * as the irq is unreliable, and exception 16 works correctly
+ * (ie as explained in the intel literature). On a 386, you
+ * can't use exception 16 due to bad IBM design, so we have to
+ * rely on the less exact irq13.
+ *
+ * Careful.. Not only is IRQ13 unreliable, but it is also
+ * leads to races. IBM designers who came up with it should
+ * be shot.
+ */
+
+static irqreturn_t math_error_irq(int cpl, void *dev_id)
+{
+ outb(0, 0xF0);
+ if (ignore_fpu_irq || !boot_cpu_data.hard_math)
+ return IRQ_NONE;
+ math_error((void __user *)get_irq_regs()->ip);
+ return IRQ_HANDLED;
+}
+
+/*
+ * New motherboards sometimes make IRQ 13 be a PCI interrupt,
+ * so allow interrupt sharing.
+ */
+static struct irqaction fpu_irq = {
+ .handler = math_error_irq,
+ .name = "fpu",
+};
+#endif
+
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+static struct irqaction irq2 = {
+ .handler = no_action,
+ .name = "cascade",
+};
+
+DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
+ [0 ... IRQ0_VECTOR - 1] = -1,
+ [IRQ0_VECTOR] = 0,
+ [IRQ1_VECTOR] = 1,
+ [IRQ2_VECTOR] = 2,
+ [IRQ3_VECTOR] = 3,
+ [IRQ4_VECTOR] = 4,
+ [IRQ5_VECTOR] = 5,
+ [IRQ6_VECTOR] = 6,
+ [IRQ7_VECTOR] = 7,
+ [IRQ8_VECTOR] = 8,
+ [IRQ9_VECTOR] = 9,
+ [IRQ10_VECTOR] = 10,
+ [IRQ11_VECTOR] = 11,
+ [IRQ12_VECTOR] = 12,
+ [IRQ13_VECTOR] = 13,
+ [IRQ14_VECTOR] = 14,
+ [IRQ15_VECTOR] = 15,
+ [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
+};
+
+int vector_used_by_percpu_irq(unsigned int vector)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ if (per_cpu(vector_irq, cpu)[vector] != -1)
+ return 1;
+ }
+
+ return 0;
+}
+
+static void __init init_ISA_irqs(void)
+{
+ int i;
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ init_bsp_APIC();
+#endif
+ init_8259A(0);
+
+ /*
+ * 16 old-style INTA-cycle interrupts:
+ */
+ for (i = 0; i < NR_IRQS_LEGACY; i++) {
+ struct irq_desc *desc = irq_to_desc(i);
+
+ desc->status = IRQ_DISABLED;
+ desc->action = NULL;
+ desc->depth = 1;
+
+ set_irq_chip_and_handler_name(i, &i8259A_chip,
+ handle_level_irq, "XT");
+ }
+}
+
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+static void __init smp_intr_init(void)
+{
+#ifdef CONFIG_SMP
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ /*
+ * The reschedule interrupt is a CPU-to-CPU reschedule-helper
+ * IPI, driven by wakeup.
+ */
+ alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+
+ /* IPIs for invalidation */
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+
+ /* IPI for generic function call */
+ alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
+ /* IPI for generic single function call */
+ alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
+ call_function_single_interrupt);
+
+ /* Low priority IPI to cleanup after moving an irq */
+ set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
+ set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
+#endif
+#endif /* CONFIG_SMP */
+}
+
+static void __init apic_intr_init(void)
+{
+ smp_intr_init();
+
+#ifdef CONFIG_X86_64
+ alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+ alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+#endif
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ /* self generated IPI for local APIC timer */
+ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+
+ /* generic IPI for platform specific use */
+ alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
+
+ /* IPI vectors for APIC spurious and error interrupts */
+ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+ alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+ /* Performance monitoring interrupts: */
+# ifdef CONFIG_PERF_COUNTERS
+ alloc_intr_gate(LOCAL_PERF_VECTOR, perf_counter_interrupt);
+ alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
+# endif
+
+#endif
+
+#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_MCE_P4THERMAL)
+ /* thermal monitor LVT interrupt */
+ alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+#endif
+#endif
+}
+
+/**
+ * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
+ *
+ * Description:
+ * Perform any necessary interrupt initialisation prior to setting up
+ * the "ordinary" interrupt call gates. For legacy reasons, the ISA
+ * interrupts should be initialised here if the machine emulates a PC
+ * in any way.
+ **/
+static void __init x86_quirk_pre_intr_init(void)
+{
+#ifdef CONFIG_X86_32
+ if (x86_quirks->arch_pre_intr_init) {
+ if (x86_quirks->arch_pre_intr_init())
+ return;
+ }
+#endif
+ init_ISA_irqs();
+}
+
+void __init native_init_IRQ(void)
+{
+ int i;
+
+ /* Execute any quirks before the call gates are initialised: */
+ x86_quirk_pre_intr_init();
+
+ apic_intr_init();
+
+ /*
+ * Cover the whole vector space, no vector can escape
+ * us. (some of these will be overridden and become
+ * 'special' SMP interrupts)
+ */
+ for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
+ /* IA32_SYSCALL_VECTOR could be used in trap_init already. */
+ if (!test_bit(i, used_vectors))
+ set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
+ }
+
+ if (!acpi_ioapic)
+ setup_irq(2, &irq2);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Call quirks after call gates are initialised (usually add in
+ * the architecture specific gates):
+ */
+ x86_quirk_intr_init();
+
+ /*
+ * External FPU? Set up irq13 if so, for
+ * original braindamaged IBM FERR coupling.
+ */
+ if (boot_cpu_data.hard_math && !cpu_has_fpu)
+ setup_irq(FPU_IRQ, &fpu_irq);
+
+ irq_ctx_init(smp_processor_id());
+#endif
+}
+++ /dev/null
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/timer.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/setup.h>
-#include <asm/i8259.h>
-#include <asm/traps.h>
-
-
-/*
- * Note that on a 486, we don't want to do a SIGFPE on an irq13
- * as the irq is unreliable, and exception 16 works correctly
- * (ie as explained in the intel literature). On a 386, you
- * can't use exception 16 due to bad IBM design, so we have to
- * rely on the less exact irq13.
- *
- * Careful.. Not only is IRQ13 unreliable, but it is also
- * leads to races. IBM designers who came up with it should
- * be shot.
- */
-
-static irqreturn_t math_error_irq(int cpl, void *dev_id)
-{
- outb(0, 0xF0);
- if (ignore_fpu_irq || !boot_cpu_data.hard_math)
- return IRQ_NONE;
- math_error((void __user *)get_irq_regs()->ip);
- return IRQ_HANDLED;
-}
-
-/*
- * New motherboards sometimes make IRQ 13 be a PCI interrupt,
- * so allow interrupt sharing.
- */
-static struct irqaction fpu_irq = {
- .handler = math_error_irq,
- .name = "fpu",
-};
-
-void __init init_ISA_irqs(void)
-{
- int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
- init_bsp_APIC();
-#endif
- init_8259A(0);
-
- /*
- * 16 old-style INTA-cycle interrupts:
- */
- for (i = 0; i < NR_IRQS_LEGACY; i++) {
- struct irq_desc *desc = irq_to_desc(i);
-
- desc->status = IRQ_DISABLED;
- desc->action = NULL;
- desc->depth = 1;
-
- set_irq_chip_and_handler_name(i, &i8259A_chip,
- handle_level_irq, "XT");
- }
-}
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
- .handler = no_action,
- .name = "cascade",
-};
-
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
- [0 ... IRQ0_VECTOR - 1] = -1,
- [IRQ0_VECTOR] = 0,
- [IRQ1_VECTOR] = 1,
- [IRQ2_VECTOR] = 2,
- [IRQ3_VECTOR] = 3,
- [IRQ4_VECTOR] = 4,
- [IRQ5_VECTOR] = 5,
- [IRQ6_VECTOR] = 6,
- [IRQ7_VECTOR] = 7,
- [IRQ8_VECTOR] = 8,
- [IRQ9_VECTOR] = 9,
- [IRQ10_VECTOR] = 10,
- [IRQ11_VECTOR] = 11,
- [IRQ12_VECTOR] = 12,
- [IRQ13_VECTOR] = 13,
- [IRQ14_VECTOR] = 14,
- [IRQ15_VECTOR] = 15,
- [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-int vector_used_by_percpu_irq(unsigned int vector)
-{
- int cpu;
-
- for_each_online_cpu(cpu) {
- if (per_cpu(vector_irq, cpu)[vector] != -1)
- return 1;
- }
-
- return 0;
-}
-
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
-{
- int i;
-
- /* Execute any quirks before the call gates are initialised: */
- x86_quirk_pre_intr_init();
-
- /*
- * Cover the whole vector space, no vector can escape
- * us. (some of these will be overridden and become
- * 'special' SMP interrupts)
- */
- for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
- /* SYSCALL_VECTOR was reserved in trap_init. */
- if (i != SYSCALL_VECTOR)
- set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
- }
-
-
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
- /*
- * The reschedule interrupt is a CPU-to-CPU reschedule-helper
- * IPI, driven by wakeup.
- */
- alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
- /* IPIs for invalidation */
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
- /* IPI for generic function call */
- alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
- /* IPI for single call function */
- alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
- call_function_single_interrupt);
-
- /* Low priority IPI to cleanup after moving an irq */
- set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
- set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
- /* self generated IPI for local APIC timer */
- alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
- /* generic IPI for platform specific use */
- alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
-
- /* IPI vectors for APIC spurious and error interrupts */
- alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
- alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-#endif
-
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_MCE_P4THERMAL)
- /* thermal monitor LVT interrupt */
- alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-#endif
-
- if (!acpi_ioapic)
- setup_irq(2, &irq2);
-
- /*
- * Call quirks after call gates are initialised (usually add in
- * the architecture specific gates):
- */
- x86_quirk_intr_init();
-
- /*
- * External FPU? Set up irq13 if so, for
- * original braindamaged IBM FERR coupling.
- */
- if (boot_cpu_data.hard_math && !cpu_has_fpu)
- setup_irq(FPU_IRQ, &fpu_irq);
-
- irq_ctx_init(smp_processor_id());
-}
+++ /dev/null
-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-#include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
- .handler = no_action,
- .name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
- [0 ... IRQ0_VECTOR - 1] = -1,
- [IRQ0_VECTOR] = 0,
- [IRQ1_VECTOR] = 1,
- [IRQ2_VECTOR] = 2,
- [IRQ3_VECTOR] = 3,
- [IRQ4_VECTOR] = 4,
- [IRQ5_VECTOR] = 5,
- [IRQ6_VECTOR] = 6,
- [IRQ7_VECTOR] = 7,
- [IRQ8_VECTOR] = 8,
- [IRQ9_VECTOR] = 9,
- [IRQ10_VECTOR] = 10,
- [IRQ11_VECTOR] = 11,
- [IRQ12_VECTOR] = 12,
- [IRQ13_VECTOR] = 13,
- [IRQ14_VECTOR] = 14,
- [IRQ15_VECTOR] = 15,
- [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-int vector_used_by_percpu_irq(unsigned int vector)
-{
- int cpu;
-
- for_each_online_cpu(cpu) {
- if (per_cpu(vector_irq, cpu)[vector] != -1)
- return 1;
- }
-
- return 0;
-}
-
-static void __init init_ISA_irqs(void)
-{
- int i;
-
- init_bsp_APIC();
- init_8259A(0);
-
- for (i = 0; i < NR_IRQS_LEGACY; i++) {
- struct irq_desc *desc = irq_to_desc(i);
-
- desc->status = IRQ_DISABLED;
- desc->action = NULL;
- desc->depth = 1;
-
- /*
- * 16 old-style INTA-cycle interrupts:
- */
- set_irq_chip_and_handler_name(i, &i8259A_chip,
- handle_level_irq, "XT");
- }
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-static void __init smp_intr_init(void)
-{
-#ifdef CONFIG_SMP
- /*
- * The reschedule interrupt is a CPU-to-CPU reschedule-helper
- * IPI, driven by wakeup.
- */
- alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
- /* IPIs for invalidation */
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
- alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
- /* IPI for generic function call */
- alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
- /* IPI for generic single function call */
- alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
- call_function_single_interrupt);
-
- /* Low priority IPI to cleanup after moving an irq */
- set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
- set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
-#endif
-}
-
-static void __init apic_intr_init(void)
-{
- smp_intr_init();
-
- alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
- alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
- /* self generated IPI for local APIC timer */
- alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
- /* generic IPI for platform specific use */
- alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
-
- /* IPI vectors for APIC spurious and error interrupts */
- alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
- alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-}
-
-void __init native_init_IRQ(void)
-{
- int i;
-
- init_ISA_irqs();
- /*
- * Cover the whole vector space, no vector can escape
- * us. (some of these will be overridden and become
- * 'special' SMP interrupts)
- */
- for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
- int vector = FIRST_EXTERNAL_VECTOR + i;
- if (vector != IA32_SYSCALL_VECTOR)
- set_intr_gate(vector, interrupt[i]);
- }
-
- apic_intr_init();
-
- if (!acpi_ioapic)
- setup_irq(2, &irq2);
-}
gdb_regs32[GDB_PS] = *(unsigned long *)(p->thread.sp + 8);
gdb_regs32[GDB_CS] = __KERNEL_CS;
gdb_regs32[GDB_SS] = __KERNEL_DS;
- gdb_regs[GDB_PC] = p->thread.ip;
+ gdb_regs[GDB_PC] = 0;
gdb_regs[GDB_R8] = 0;
gdb_regs[GDB_R9] = 0;
gdb_regs[GDB_R10] = 0;
struct kvm_para_state *state = kvm_para_state();
mmu_queue_flush(state);
- paravirt_leave_lazy(paravirt_get_lazy_mode());
+ paravirt_leave_lazy_mmu();
state->mode = paravirt_get_lazy_mode();
}
* Licensed under the terms of the GNU General Public
* License version 2. See file COPYING for details.
*/
-#include <linux/platform_device.h>
-#include <linux/capability.h>
-#include <linux/miscdevice.h>
#include <linux/firmware.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
#include <linux/pci_ids.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
#include <linux/pci.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
#include <asm/microcode.h>
#include <asm/processor.h>
#define UCODE_CONTAINER_SECTION_HDR 8
#define UCODE_CONTAINER_HEADER_SIZE 12
-/* serialize access to the physical write */
-static DEFINE_SPINLOCK(microcode_update_lock);
-
static struct equiv_cpu_entry *equiv_cpu_table;
static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
return 1;
}
-static void apply_microcode_amd(int cpu)
+static int apply_microcode_amd(int cpu)
{
- unsigned long flags;
u32 rev, dummy;
int cpu_num = raw_smp_processor_id();
struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num;
BUG_ON(cpu_num != cpu);
if (mc_amd == NULL)
- return;
+ return 0;
- spin_lock_irqsave(µcode_update_lock, flags);
wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
/* get patch id after patching */
rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- spin_unlock_irqrestore(µcode_update_lock, flags);
/* check current patch id and patch's id for match */
if (rev != mc_amd->hdr.patch_id) {
printk(KERN_ERR "microcode: CPU%d: update failed "
"(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id);
- return;
+ return -1;
}
printk(KERN_INFO "microcode: CPU%d: updated (new patch_level=0x%x)\n",
cpu, rev);
uci->cpu_sig.rev = rev;
+
+ return 0;
}
static int get_ucode_data(void *to, const u8 *from, size_t n)
static void free_equiv_cpu_table(void)
{
- if (equiv_cpu_table) {
- vfree(equiv_cpu_table);
- equiv_cpu_table = NULL;
- }
+ vfree(equiv_cpu_table);
+ equiv_cpu_table = NULL;
}
-static int generic_load_microcode(int cpu, const u8 *data, size_t size)
+static enum ucode_state
+generic_load_microcode(int cpu, const u8 *data, size_t size)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
const u8 *ucode_ptr = data;
int new_rev = uci->cpu_sig.rev;
unsigned int leftover;
unsigned long offset;
+ enum ucode_state state = UCODE_OK;
offset = install_equiv_cpu_table(ucode_ptr);
if (!offset) {
printk(KERN_ERR "microcode: failed to create "
"equivalent cpu table\n");
- return -EINVAL;
+ return UCODE_ERROR;
}
ucode_ptr += offset;
mc_header = (struct microcode_header_amd *)mc;
if (get_matching_microcode(cpu, mc, new_rev)) {
- if (new_mc)
- vfree(new_mc);
+ vfree(new_mc);
new_rev = mc_header->patch_id;
new_mc = mc;
} else
if (new_mc) {
if (!leftover) {
- if (uci->mc)
- vfree(uci->mc);
+ vfree(uci->mc);
uci->mc = new_mc;
pr_debug("microcode: CPU%d found a matching microcode "
"update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
- } else
+ } else {
vfree(new_mc);
- }
+ state = UCODE_ERROR;
+ }
+ } else
+ state = UCODE_NFOUND;
free_equiv_cpu_table();
- return (int)leftover;
+ return state;
}
-static int request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device)
{
const char *fw_name = "amd-ucode/microcode_amd.bin";
const struct firmware *firmware;
- int ret;
-
- /* We should bind the task to the CPU */
- BUG_ON(cpu != raw_smp_processor_id());
+ enum ucode_state ret;
- ret = request_firmware(&firmware, fw_name, device);
- if (ret) {
+ if (request_firmware(&firmware, fw_name, device)) {
printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
- return ret;
+ return UCODE_NFOUND;
}
ret = generic_load_microcode(cpu, firmware->data, firmware->size);
return ret;
}
-static int request_microcode_user(int cpu, const void __user *buf, size_t size)
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
{
printk(KERN_INFO "microcode: AMD microcode update via "
"/dev/cpu/microcode not supported\n");
- return -1;
+ return UCODE_ERROR;
}
static void microcode_fini_cpu_amd(int cpu)
* Thanks to Stuart Swales for pointing out this bug.
*/
#include <linux/platform_device.h>
-#include <linux/capability.h>
#include <linux/miscdevice.h>
-#include <linux/firmware.h>
+#include <linux/capability.h>
#include <linux/smp_lock.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <asm/microcode.h>
#include <asm/processor.h>
-#include <asm/msr.h>
MODULE_DESCRIPTION("Microcode Update Driver");
MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
static struct microcode_ops *microcode_ops;
-/* no concurrent ->write()s are allowed on /dev/cpu/microcode */
+/*
+ * Synchronization.
+ *
+ * All non cpu-hotplug-callback call sites use:
+ *
+ * - microcode_mutex to synchronize with each other;
+ * - get/put_online_cpus() to synchronize with
+ * the cpu-hotplug-callback call sites.
+ *
+ * We guarantee that only a single cpu is being
+ * updated at any particular moment of time.
+ */
static DEFINE_MUTEX(microcode_mutex);
struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
EXPORT_SYMBOL_GPL(ucode_cpu_info);
+/*
+ * Operations that are run on a target cpu:
+ */
+
+struct cpu_info_ctx {
+ struct cpu_signature *cpu_sig;
+ int err;
+};
+
+static void collect_cpu_info_local(void *arg)
+{
+ struct cpu_info_ctx *ctx = arg;
+
+ ctx->err = microcode_ops->collect_cpu_info(smp_processor_id(),
+ ctx->cpu_sig);
+}
+
+static int collect_cpu_info_on_target(int cpu, struct cpu_signature *cpu_sig)
+{
+ struct cpu_info_ctx ctx = { .cpu_sig = cpu_sig, .err = 0 };
+ int ret;
+
+ ret = smp_call_function_single(cpu, collect_cpu_info_local, &ctx, 1);
+ if (!ret)
+ ret = ctx.err;
+
+ return ret;
+}
+
+static int collect_cpu_info(int cpu)
+{
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ int ret;
+
+ memset(uci, 0, sizeof(*uci));
+
+ ret = collect_cpu_info_on_target(cpu, &uci->cpu_sig);
+ if (!ret)
+ uci->valid = 1;
+
+ return ret;
+}
+
+struct apply_microcode_ctx {
+ int err;
+};
+
+static void apply_microcode_local(void *arg)
+{
+ struct apply_microcode_ctx *ctx = arg;
+
+ ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+}
+
+static int apply_microcode_on_target(int cpu)
+{
+ struct apply_microcode_ctx ctx = { .err = 0 };
+ int ret;
+
+ ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
+ if (!ret)
+ ret = ctx.err;
+
+ return ret;
+}
+
#ifdef CONFIG_MICROCODE_OLD_INTERFACE
static int do_microcode_update(const void __user *buf, size_t size)
{
- cpumask_t old;
int error = 0;
int cpu;
- old = current->cpus_allowed;
-
for_each_online_cpu(cpu) {
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ enum ucode_state ustate;
if (!uci->valid)
continue;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
- error = microcode_ops->request_microcode_user(cpu, buf, size);
- if (error < 0)
- goto out;
- if (!error)
- microcode_ops->apply_microcode(cpu);
+ ustate = microcode_ops->request_microcode_user(cpu, buf, size);
+ if (ustate == UCODE_ERROR) {
+ error = -1;
+ break;
+ } else if (ustate == UCODE_OK)
+ apply_microcode_on_target(cpu);
}
-out:
- set_cpus_allowed_ptr(current, &old);
+
return error;
}
static ssize_t microcode_write(struct file *file, const char __user *buf,
size_t len, loff_t *ppos)
{
- ssize_t ret;
+ ssize_t ret = -EINVAL;
if ((len >> PAGE_SHIFT) > num_physpages) {
- printk(KERN_ERR "microcode: too much data (max %ld pages)\n",
- num_physpages);
- return -EINVAL;
+ pr_err("microcode: too much data (max %ld pages)\n", num_physpages);
+ return ret;
}
get_online_cpus();
mutex_lock(µcode_mutex);
- ret = do_microcode_update(buf, len);
- if (!ret)
+ if (do_microcode_update(buf, len) == 0)
ret = (ssize_t)len;
mutex_unlock(µcode_mutex);
}
static const struct file_operations microcode_fops = {
- .owner = THIS_MODULE,
- .write = microcode_write,
- .open = microcode_open,
+ .owner = THIS_MODULE,
+ .write = microcode_write,
+ .open = microcode_open,
};
static struct miscdevice microcode_dev = {
- .minor = MICROCODE_MINOR,
- .name = "microcode",
- .fops = µcode_fops,
+ .minor = MICROCODE_MINOR,
+ .name = "microcode",
+ .fops = µcode_fops,
};
static int __init microcode_dev_init(void)
error = misc_register(µcode_dev);
if (error) {
- printk(KERN_ERR
- "microcode: can't misc_register on minor=%d\n",
- MICROCODE_MINOR);
+ pr_err("microcode: can't misc_register on minor=%d\n", MICROCODE_MINOR);
return error;
}
/* fake device for request_firmware */
static struct platform_device *microcode_pdev;
-static long reload_for_cpu(void *unused)
+static int reload_for_cpu(int cpu)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
int err = 0;
mutex_lock(µcode_mutex);
if (uci->valid) {
- err = microcode_ops->request_microcode_fw(smp_processor_id(),
- µcode_pdev->dev);
- if (!err)
- microcode_ops->apply_microcode(smp_processor_id());
+ enum ucode_state ustate;
+
+ ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev);
+ if (ustate == UCODE_OK)
+ apply_microcode_on_target(cpu);
+ else
+ if (ustate == UCODE_ERROR)
+ err = -EINVAL;
}
mutex_unlock(µcode_mutex);
+
return err;
}
static ssize_t reload_store(struct sys_device *dev,
struct sysdev_attribute *attr,
- const char *buf, size_t sz)
+ const char *buf, size_t size)
{
- char *end;
- unsigned long val = simple_strtoul(buf, &end, 0);
- int err = 0;
+ unsigned long val;
int cpu = dev->id;
+ int ret = 0;
+ char *end;
+ val = simple_strtoul(buf, &end, 0);
if (end == buf)
return -EINVAL;
+
if (val == 1) {
get_online_cpus();
if (cpu_online(cpu))
- err = work_on_cpu(cpu, reload_for_cpu, NULL);
+ ret = reload_for_cpu(cpu);
put_online_cpus();
}
- if (err)
- return err;
- return sz;
+
+ if (!ret)
+ ret = size;
+
+ return ret;
}
static ssize_t version_show(struct sys_device *dev,
};
static struct attribute_group mc_attr_group = {
- .attrs = mc_default_attrs,
- .name = "microcode",
+ .attrs = mc_default_attrs,
+ .name = "microcode",
};
-static void __microcode_fini_cpu(int cpu)
+static void microcode_fini_cpu(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
uci->valid = 0;
}
-static void microcode_fini_cpu(int cpu)
-{
- mutex_lock(µcode_mutex);
- __microcode_fini_cpu(cpu);
- mutex_unlock(µcode_mutex);
-}
-
-static void collect_cpu_info(int cpu)
+static enum ucode_state microcode_resume_cpu(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- memset(uci, 0, sizeof(*uci));
- if (!microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig))
- uci->valid = 1;
+ if (!uci->mc)
+ return UCODE_NFOUND;
+
+ pr_debug("microcode: CPU%d updated upon resume\n", cpu);
+ apply_microcode_on_target(cpu);
+
+ return UCODE_OK;
}
-static int microcode_resume_cpu(int cpu)
+static enum ucode_state microcode_init_cpu(int cpu)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- struct cpu_signature nsig;
+ enum ucode_state ustate;
- pr_debug("microcode: CPU%d resumed\n", cpu);
+ if (collect_cpu_info(cpu))
+ return UCODE_ERROR;
- if (!uci->mc)
- return 1;
+ /* --dimm. Trigger a delayed update? */
+ if (system_state != SYSTEM_RUNNING)
+ return UCODE_NFOUND;
- /*
- * Let's verify that the 'cached' ucode does belong
- * to this cpu (a bit of paranoia):
- */
- if (microcode_ops->collect_cpu_info(cpu, &nsig)) {
- __microcode_fini_cpu(cpu);
- printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n",
- cpu);
- return -1;
- }
+ ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev);
- if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) {
- __microcode_fini_cpu(cpu);
- printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n",
- cpu);
- /* Should we look for a new ucode here? */
- return 1;
+ if (ustate == UCODE_OK) {
+ pr_debug("microcode: CPU%d updated upon init\n", cpu);
+ apply_microcode_on_target(cpu);
}
- return 0;
+ return ustate;
}
-static long microcode_update_cpu(void *unused)
+static enum ucode_state microcode_update_cpu(int cpu)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
- int err = 0;
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ enum ucode_state ustate;
- /*
- * Check if the system resume is in progress (uci->valid != NULL),
- * otherwise just request a firmware:
- */
- if (uci->valid) {
- err = microcode_resume_cpu(smp_processor_id());
- } else {
- collect_cpu_info(smp_processor_id());
- if (uci->valid && system_state == SYSTEM_RUNNING)
- err = microcode_ops->request_microcode_fw(
- smp_processor_id(),
- µcode_pdev->dev);
- }
- if (!err)
- microcode_ops->apply_microcode(smp_processor_id());
- return err;
-}
+ if (uci->valid)
+ ustate = microcode_resume_cpu(cpu);
+ else
+ ustate = microcode_init_cpu(cpu);
-static int microcode_init_cpu(int cpu)
-{
- int err;
- mutex_lock(µcode_mutex);
- err = work_on_cpu(cpu, microcode_update_cpu, NULL);
- mutex_unlock(µcode_mutex);
-
- return err;
+ return ustate;
}
static int mc_sysdev_add(struct sys_device *sys_dev)
{
int err, cpu = sys_dev->id;
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
if (!cpu_online(cpu))
return 0;
pr_debug("microcode: CPU%d added\n", cpu);
- memset(uci, 0, sizeof(*uci));
err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
if (err)
return err;
- err = microcode_init_cpu(cpu);
+ if (microcode_init_cpu(cpu) == UCODE_ERROR)
+ err = -EINVAL;
return err;
}
static int mc_sysdev_resume(struct sys_device *dev)
{
int cpu = dev->id;
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
if (!cpu_online(cpu))
return 0;
- /* only CPU 0 will apply ucode here */
- microcode_update_cpu(NULL);
+ /*
+ * All non-bootup cpus are still disabled,
+ * so only CPU 0 will apply ucode here.
+ *
+ * Moreover, there can be no concurrent
+ * updates from any other places at this point.
+ */
+ WARN_ON(cpu != 0);
+
+ if (uci->valid && uci->mc)
+ microcode_ops->apply_microcode(cpu);
+
return 0;
}
static struct sysdev_driver mc_sysdev_driver = {
- .add = mc_sysdev_add,
- .remove = mc_sysdev_remove,
- .resume = mc_sysdev_resume,
+ .add = mc_sysdev_add,
+ .remove = mc_sysdev_remove,
+ .resume = mc_sysdev_resume,
};
static __cpuinit int
switch (action) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- if (microcode_init_cpu(cpu))
- printk(KERN_ERR "microcode: failed to init CPU%d\n",
- cpu);
+ microcode_update_cpu(cpu);
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
pr_debug("microcode: CPU%d added\n", cpu);
if (sysfs_create_group(&sys_dev->kobj, &mc_attr_group))
- printk(KERN_ERR "microcode: Failed to create the sysfs "
- "group for CPU%d\n", cpu);
+ pr_err("microcode: Failed to create group for CPU%d\n", cpu);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
microcode_ops = init_amd_microcode();
if (!microcode_ops) {
- printk(KERN_ERR "microcode: no support for this CPU vendor\n");
+ pr_err("microcode: no support for this CPU vendor\n");
return -ENODEV;
}
- error = microcode_dev_init();
- if (error)
- return error;
microcode_pdev = platform_device_register_simple("microcode", -1,
NULL, 0);
if (IS_ERR(microcode_pdev)) {
}
get_online_cpus();
+ mutex_lock(µcode_mutex);
+
error = sysdev_driver_register(&cpu_sysdev_class, &mc_sysdev_driver);
+
+ mutex_unlock(µcode_mutex);
put_online_cpus();
+
if (error) {
- microcode_dev_exit();
platform_device_unregister(microcode_pdev);
return error;
}
+ error = microcode_dev_init();
+ if (error)
+ return error;
+
register_hotcpu_notifier(&mc_cpu_notifier);
- printk(KERN_INFO
- "Microcode Update Driver: v" MICROCODE_VERSION
+ pr_info("Microcode Update Driver: v" MICROCODE_VERSION
" <tigran@aivazian.fsnet.co.uk>,"
" Peter Oruba\n");
return 0;
}
+module_init(microcode_init);
static void __exit microcode_exit(void)
{
unregister_hotcpu_notifier(&mc_cpu_notifier);
get_online_cpus();
+ mutex_lock(µcode_mutex);
+
sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver);
+
+ mutex_unlock(µcode_mutex);
put_online_cpus();
platform_device_unregister(microcode_pdev);
microcode_ops = NULL;
- printk(KERN_INFO
- "Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
+ pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
}
-
-module_init(microcode_init);
module_exit(microcode_exit);
* Fix sigmatch() macro to handle old CPUs with pf == 0.
* Thanks to Stuart Swales for pointing out this bug.
*/
-#include <linux/platform_device.h>
-#include <linux/capability.h>
-#include <linux/miscdevice.h>
#include <linux/firmware.h>
-#include <linux/smp_lock.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
+#include <linux/vmalloc.h>
#include <asm/microcode.h>
#include <asm/processor.h>
#define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
-/* serialize access to the physical write to MSR 0x79 */
-static DEFINE_SPINLOCK(microcode_update_lock);
-
static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
{
struct cpuinfo_x86 *c = &cpu_data(cpu_num);
- unsigned long flags;
unsigned int val[2];
memset(csig, 0, sizeof(*csig));
csig->pf = 1 << ((val[1] >> 18) & 7);
}
- /* serialize access to the physical write to MSR 0x79 */
- spin_lock_irqsave(µcode_update_lock, flags);
-
wrmsr(MSR_IA32_UCODE_REV, 0, 0);
/* see notes above for revision 1.07. Apparent chip bug */
sync_core();
/* get the current revision from MSR 0x8B */
rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
- spin_unlock_irqrestore(µcode_update_lock, flags);
- pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n",
- csig->sig, csig->pf, csig->rev);
+ printk(KERN_INFO "microcode: CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
+ cpu_num, csig->sig, csig->pf, csig->rev);
return 0;
}
return 0;
}
-static void apply_microcode(int cpu)
+static int apply_microcode(int cpu)
{
struct microcode_intel *mc_intel;
struct ucode_cpu_info *uci;
- unsigned long flags;
unsigned int val[2];
int cpu_num;
BUG_ON(cpu_num != cpu);
if (mc_intel == NULL)
- return;
-
- /* serialize access to the physical write to MSR 0x79 */
- spin_lock_irqsave(µcode_update_lock, flags);
+ return 0;
/* write microcode via MSR 0x79 */
wrmsr(MSR_IA32_UCODE_WRITE,
/* get the current revision from MSR 0x8B */
rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
- spin_unlock_irqrestore(µcode_update_lock, flags);
if (val[1] != mc_intel->hdr.rev) {
- printk(KERN_ERR "microcode: CPU%d update from revision "
- "0x%x to 0x%x failed\n",
- cpu_num, uci->cpu_sig.rev, val[1]);
- return;
+ printk(KERN_ERR "microcode: CPU%d update "
+ "to revision 0x%x failed\n",
+ cpu_num, mc_intel->hdr.rev);
+ return -1;
}
- printk(KERN_INFO "microcode: CPU%d updated from revision "
- "0x%x to 0x%x, date = %04x-%02x-%02x \n",
- cpu_num, uci->cpu_sig.rev, val[1],
+ printk(KERN_INFO "microcode: CPU%d updated to revision "
+ "0x%x, date = %04x-%02x-%02x \n",
+ cpu_num, val[1],
mc_intel->hdr.date & 0xffff,
mc_intel->hdr.date >> 24,
(mc_intel->hdr.date >> 16) & 0xff);
uci->cpu_sig.rev = val[1];
+
+ return 0;
}
-static int generic_load_microcode(int cpu, void *data, size_t size,
- int (*get_ucode_data)(void *, const void *, size_t))
+static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
+ int (*get_ucode_data)(void *, const void *, size_t))
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
u8 *ucode_ptr = data, *new_mc = NULL, *mc;
int new_rev = uci->cpu_sig.rev;
unsigned int leftover = size;
+ enum ucode_state state = UCODE_OK;
while (leftover) {
struct microcode_header_intel mc_header;
leftover -= mc_size;
}
- if (!new_mc)
+ if (leftover) {
+ if (new_mc)
+ vfree(new_mc);
+ state = UCODE_ERROR;
goto out;
+ }
- if (leftover) {
- vfree(new_mc);
+ if (!new_mc) {
+ state = UCODE_NFOUND;
goto out;
}
pr_debug("microcode: CPU%d found a matching microcode update with"
" version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
-
- out:
- return (int)leftover;
+out:
+ return state;
}
static int get_ucode_fw(void *to, const void *from, size_t n)
return 0;
}
-static int request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device)
{
char name[30];
struct cpuinfo_x86 *c = &cpu_data(cpu);
const struct firmware *firmware;
- int ret;
+ enum ucode_state ret;
- /* We should bind the task to the CPU */
- BUG_ON(cpu != raw_smp_processor_id());
sprintf(name, "intel-ucode/%02x-%02x-%02x",
c->x86, c->x86_model, c->x86_mask);
- ret = request_firmware(&firmware, name, device);
- if (ret) {
+
+ if (request_firmware(&firmware, name, device)) {
pr_debug("microcode: data file %s load failed\n", name);
- return ret;
+ return UCODE_NFOUND;
}
ret = generic_load_microcode(cpu, (void *)firmware->data,
return copy_from_user(to, from, n);
}
-static int request_microcode_user(int cpu, const void __user *buf, size_t size)
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
{
- /* We should bind the task to the CPU */
- BUG_ON(cpu != raw_smp_processor_id());
-
return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
}
#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/smp.h>
+#include <linux/pci.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
#endif /* CONFIG_X86_IO_APIC */
-static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length,
- int count)
+static int
+check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
{
- if (!mpc_new_phys) {
- pr_info("No spare slots, try to append...take your risk, "
- "new mpc_length %x\n", count);
- } else {
- if (count <= mpc_new_length)
- pr_info("No spare slots, try to append..., "
- "new mpc_length %x\n", count);
- else {
- pr_err("mpc_new_length %lx is too small\n",
- mpc_new_length);
- return -1;
- }
+ int ret = 0;
+
+ if (!mpc_new_phys || count <= mpc_new_length) {
+ WARN(1, "update_mptable: No spare slots (length: %x)\n", count);
+ return -1;
}
- return 0;
+ return ret;
}
static int __init replace_intsrc_all(struct mpc_table *mpc,
} else {
struct mpc_intsrc *m = (struct mpc_intsrc *)mpt;
count += sizeof(struct mpc_intsrc);
- if (!check_slot(mpc_new_phys, mpc_new_length, count))
+ if (check_slot(mpc_new_phys, mpc_new_length, count) < 0)
goto out;
assign_to_mpc_intsrc(&mp_irqs[i], m);
mpc->length = count;
return 0;
}
-static int __initdata enable_update_mptable;
+int enable_update_mptable;
static int __init update_mptable_setup(char *str)
{
enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+ pci_routeirq = 1;
+#endif
return 0;
}
early_param("update_mptable", update_mptable_setup);
static int __init parse_alloc_mptable_opt(char *p)
{
enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+ pci_routeirq = 1;
+#endif
alloc_mptable = 1;
if (!p)
return 0;
static inline void enter_lazy(enum paravirt_lazy_mode mode)
{
- BUG_ON(__get_cpu_var(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
- BUG_ON(preemptible());
+ BUG_ON(percpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
- __get_cpu_var(paravirt_lazy_mode) = mode;
+ percpu_write(paravirt_lazy_mode, mode);
}
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode)
+static void leave_lazy(enum paravirt_lazy_mode mode)
{
- BUG_ON(__get_cpu_var(paravirt_lazy_mode) != mode);
- BUG_ON(preemptible());
+ BUG_ON(percpu_read(paravirt_lazy_mode) != mode);
- __get_cpu_var(paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+ percpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
}
void paravirt_enter_lazy_mmu(void)
void paravirt_leave_lazy_mmu(void)
{
- paravirt_leave_lazy(PARAVIRT_LAZY_MMU);
+ leave_lazy(PARAVIRT_LAZY_MMU);
}
-void paravirt_enter_lazy_cpu(void)
+void paravirt_start_context_switch(struct task_struct *prev)
{
+ BUG_ON(preemptible());
+
+ if (percpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+ arch_leave_lazy_mmu_mode();
+ set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+ }
enter_lazy(PARAVIRT_LAZY_CPU);
}
-void paravirt_leave_lazy_cpu(void)
+void paravirt_end_context_switch(struct task_struct *next)
{
- paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+ BUG_ON(preemptible());
+
+ leave_lazy(PARAVIRT_LAZY_CPU);
+
+ if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+ arch_enter_lazy_mmu_mode();
}
enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
{
- return __get_cpu_var(paravirt_lazy_mode);
+ if (in_interrupt())
+ return PARAVIRT_LAZY_NONE;
+
+ return percpu_read(paravirt_lazy_mode);
}
void arch_flush_lazy_mmu_mode(void)
preempt_disable();
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
- WARN_ON(preempt_count() == 1);
arch_leave_lazy_mmu_mode();
arch_enter_lazy_mmu_mode();
}
preempt_enable();
}
-void arch_flush_lazy_cpu_mode(void)
-{
- preempt_disable();
-
- if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
- WARN_ON(preempt_count() == 1);
- arch_leave_lazy_cpu_mode();
- arch_enter_lazy_cpu_mode();
- }
-
- preempt_enable();
-}
-
struct pv_info pv_info = {
.name = "bare hardware",
.paravirt_enabled = 0,
.set_iopl_mask = native_set_iopl_mask,
.io_delay = native_io_delay,
- .lazy_mode = {
- .enter = paravirt_nop,
- .leave = paravirt_nop,
- },
+ .start_context_switch = paravirt_nop,
+ .end_context_switch = paravirt_nop,
};
struct pv_apic_ops pv_apic_ops = {
static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, };
-/* enable this to stress test the chip's TCE cache */
-#ifdef CONFIG_IOMMU_DEBUG
-static int debugging = 1;
-
-static inline unsigned long verify_bit_range(unsigned long* bitmap,
- int expected, unsigned long start, unsigned long end)
-{
- unsigned long idx = start;
-
- BUG_ON(start >= end);
-
- while (idx < end) {
- if (!!test_bit(idx, bitmap) != expected)
- return idx;
- ++idx;
- }
-
- /* all bits have the expected value */
- return ~0UL;
-}
-#else /* debugging is disabled */
-static int debugging;
-
-static inline unsigned long verify_bit_range(unsigned long* bitmap,
- int expected, unsigned long start, unsigned long end)
-{
- return ~0UL;
-}
-
-#endif /* CONFIG_IOMMU_DEBUG */
-
static inline int translation_enabled(struct iommu_table *tbl)
{
/* only PHBs with translation enabled have an IOMMU table */
{
unsigned long index;
unsigned long end;
- unsigned long badbit;
unsigned long flags;
index = start_addr >> PAGE_SHIFT;
spin_lock_irqsave(&tbl->it_lock, flags);
- badbit = verify_bit_range(tbl->it_map, 0, index, end);
- if (badbit != ~0UL) {
- if (printk_ratelimit())
- printk(KERN_ERR "Calgary: entry already allocated at "
- "0x%lx tbl %p dma 0x%lx npages %u\n",
- badbit, tbl, start_addr, npages);
- }
-
iommu_area_reserve(tbl->it_map, index, npages);
spin_unlock_irqrestore(&tbl->it_lock, flags);
unsigned int npages)
{
unsigned long entry;
- unsigned long badbit;
unsigned long badend;
unsigned long flags;
spin_lock_irqsave(&tbl->it_lock, flags);
- badbit = verify_bit_range(tbl->it_map, 1, entry, entry + npages);
- if (badbit != ~0UL) {
- if (printk_ratelimit())
- printk(KERN_ERR "Calgary: bit is off at 0x%lx "
- "tbl %p dma 0x%Lx entry 0x%lx npages %u\n",
- badbit, tbl, dma_addr, entry, npages);
- }
-
iommu_area_free(tbl->it_map, entry, npages);
spin_unlock_irqrestore(&tbl->it_lock, flags);
iommu_detected = 1;
calgary_detected = 1;
printk(KERN_INFO "PCI-DMA: Calgary IOMMU detected.\n");
- printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, "
- "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size,
- debugging ? "enabled" : "disabled");
+ printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d\n",
+ specified_table_size);
/* swiotlb for devices that aren't behind the Calgary. */
if (max_pfn > MAX_DMA32_PFN)
}
#ifdef CONFIG_IOMMU_LEAK
-
-#define SET_LEAK(x) \
- do { \
- if (iommu_leak_tab) \
- iommu_leak_tab[x] = __builtin_return_address(0);\
- } while (0)
-
-#define CLEAR_LEAK(x) \
- do { \
- if (iommu_leak_tab) \
- iommu_leak_tab[x] = NULL; \
- } while (0)
-
/* Debugging aid for drivers that don't free their IOMMU tables */
-static void **iommu_leak_tab;
static int leak_trace;
static int iommu_leak_pages = 20;
static void dump_leak(void)
{
- int i;
static int dump;
- if (dump || !iommu_leak_tab)
+ if (dump)
return;
dump = 1;
- show_stack(NULL, NULL);
- /* Very crude. dump some from the end of the table too */
- printk(KERN_DEBUG "Dumping %d pages from end of IOMMU:\n",
- iommu_leak_pages);
- for (i = 0; i < iommu_leak_pages; i += 2) {
- printk(KERN_DEBUG "%lu: ", iommu_pages-i);
- printk_address((unsigned long) iommu_leak_tab[iommu_pages-i],
- 0);
- printk(KERN_CONT "%c", (i+1)%2 == 0 ? '\n' : ' ');
- }
- printk(KERN_DEBUG "\n");
+ show_stack(NULL, NULL);
+ debug_dma_dump_mappings(NULL);
}
-#else
-# define SET_LEAK(x)
-# define CLEAR_LEAK(x)
#endif
static void iommu_full(struct device *dev, size_t size, int dir)
for (i = 0; i < npages; i++) {
iommu_gatt_base[iommu_page + i] = GPTE_ENCODE(phys_mem);
- SET_LEAK(iommu_page + i);
phys_mem += PAGE_SIZE;
}
return iommu_bus_base + iommu_page*PAGE_SIZE + (phys_mem & ~PAGE_MASK);
npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
for (i = 0; i < npages; i++) {
iommu_gatt_base[iommu_page + i] = gart_unmapped_entry;
- CLEAR_LEAK(iommu_page + i);
}
free_iommu(iommu_page, npages);
}
pages = iommu_num_pages(s->offset, s->length, PAGE_SIZE);
while (pages--) {
iommu_gatt_base[iommu_page] = GPTE_ENCODE(addr);
- SET_LEAK(iommu_page);
addr += PAGE_SIZE;
iommu_page++;
}
agp_gatt_table = gatt;
- enable_gart_translations();
-
error = sysdev_class_register(&gart_sysdev_class);
if (!error)
error = sysdev_register(&device_gart);
#ifdef CONFIG_IOMMU_LEAK
if (leak_trace) {
- iommu_leak_tab = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
- get_order(iommu_pages*sizeof(void *)));
- if (!iommu_leak_tab)
+ int ret;
+
+ ret = dma_debug_resize_entries(iommu_pages);
+ if (ret)
printk(KERN_DEBUG
- "PCI-DMA: Cannot allocate leak trace area\n");
+ "PCI-DMA: Cannot trace all the entries\n");
}
#endif
* the pages as Not-Present:
*/
wbinvd();
+
+ /*
+ * Now all caches are flushed and we can safely enable
+ * GART hardware. Doing it early leaves the possibility
+ * of stale cache entries that can lead to GART PTE
+ * errors.
+ */
+ enable_gart_translations();
/*
* Try to workaround a bug (thanks to BenH):
return paddr;
}
-phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr)
+phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
{
return baddr;
}
#include <linux/module.h>
#include <linux/pm.h>
#include <linux/clockchips.h>
+#include <linux/random.h>
#include <trace/power.h>
#include <asm/system.h>
#include <asm/apic.h>
+#include <asm/syscalls.h>
#include <asm/idle.h>
#include <asm/uaccess.h>
#include <asm/i387.h>
+#include <asm/ds.h>
unsigned long idle_halt;
EXPORT_SYMBOL(idle_halt);
kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
tsk->thread.xstate = NULL;
}
+
+ WARN(tsk->thread.ds_ctx, "leaking DS context\n");
}
void free_thread_info(struct thread_info *ti)
put_cpu();
kfree(bp);
}
-
- ds_exit_thread(current);
}
void flush_thread(void)
}
early_param("idle", idle_setup);
+unsigned long arch_align_stack(unsigned long sp)
+{
+ if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+ sp -= get_random_int() % 8192;
+ return sp & ~0xf;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+ unsigned long range_end = mm->brk + 0x02000000;
+ return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
+}
+
* This file handles the architecture-dependent parts of process handling..
*/
-#include <stdarg.h>
-
#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
-#include <linux/random.h>
#include <linux/personality.h>
#include <linux/tick.h>
#include <linux/percpu.h>
p->thread.io_bitmap_max = 0;
}
- ds_copy_thread(p, current);
+ clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
+ p->thread.ds_ctx = NULL;
clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
p->thread.debugctlmsr = 0;
* done before math_state_restore, so the TS bit is up
* to date.
*/
- arch_leave_lazy_cpu_mode();
+ arch_end_context_switch(next_p);
/* If the task has used fpu the last 5 timeslices, just do a full
* restore of the math state immediately to avoid the trap; the
return 0;
}
-unsigned long arch_align_stack(unsigned long sp)
-{
- if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
- sp -= get_random_int() % 8192;
- return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
- unsigned long range_end = mm->brk + 0x02000000;
- return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
* This file handles the architecture-dependent parts of process handling..
*/
-#include <stdarg.h>
-
#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
-#include <linux/random.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
goto out;
}
- ds_copy_thread(p, me);
+ clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
+ p->thread.ds_ctx = NULL;
clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
p->thread.debugctlmsr = 0;
* done before math_state_restore, so the TS bit is up
* to date.
*/
- arch_leave_lazy_cpu_mode();
+ arch_end_context_switch(next_p);
/*
* Switch FS and GS.
return do_arch_prctl(current, code, addr);
}
-unsigned long arch_align_stack(unsigned long sp)
-{
- if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
- sp -= get_random_int() % 8192;
- return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
- unsigned long range_end = mm->brk + 0x02000000;
- return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
+#include <linux/workqueue.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
}
#ifdef CONFIG_X86_PTRACE_BTS
+/*
+ * A branch trace store context.
+ *
+ * Contexts may only be installed by ptrace_bts_config() and only for
+ * ptraced tasks.
+ *
+ * Contexts are destroyed when the tracee is detached from the tracer.
+ * The actual destruction work requires interrupts enabled, so the
+ * work is deferred and will be scheduled during __ptrace_unlink().
+ *
+ * Contexts hold an additional task_struct reference on the traced
+ * task, as well as a reference on the tracer's mm.
+ *
+ * Ptrace already holds a task_struct for the duration of ptrace operations,
+ * but since destruction is deferred, it may be executed after both
+ * tracer and tracee exited.
+ */
+struct bts_context {
+ /* The branch trace handle. */
+ struct bts_tracer *tracer;
+
+ /* The buffer used to store the branch trace and its size. */
+ void *buffer;
+ unsigned int size;
+
+ /* The mm that paid for the above buffer. */
+ struct mm_struct *mm;
+
+ /* The task this context belongs to. */
+ struct task_struct *task;
+
+ /* The signal to send on a bts buffer overflow. */
+ unsigned int bts_ovfl_signal;
+
+ /* The work struct to destroy a context. */
+ struct work_struct work;
+};
+
+static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
+{
+ void *buffer = NULL;
+ int err = -ENOMEM;
+
+ err = account_locked_memory(current->mm, current->signal->rlim, size);
+ if (err < 0)
+ return err;
+
+ buffer = kzalloc(size, GFP_KERNEL);
+ if (!buffer)
+ goto out_refund;
+
+ context->buffer = buffer;
+ context->size = size;
+ context->mm = get_task_mm(current);
+
+ return 0;
+
+ out_refund:
+ refund_locked_memory(current->mm, size);
+ return err;
+}
+
+static inline void free_bts_buffer(struct bts_context *context)
+{
+ if (!context->buffer)
+ return;
+
+ kfree(context->buffer);
+ context->buffer = NULL;
+
+ refund_locked_memory(context->mm, context->size);
+ context->size = 0;
+
+ mmput(context->mm);
+ context->mm = NULL;
+}
+
+static void free_bts_context_work(struct work_struct *w)
+{
+ struct bts_context *context;
+
+ context = container_of(w, struct bts_context, work);
+
+ ds_release_bts(context->tracer);
+ put_task_struct(context->task);
+ free_bts_buffer(context);
+ kfree(context);
+}
+
+static inline void free_bts_context(struct bts_context *context)
+{
+ INIT_WORK(&context->work, free_bts_context_work);
+ schedule_work(&context->work);
+}
+
+static inline struct bts_context *alloc_bts_context(struct task_struct *task)
+{
+ struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL);
+ if (context) {
+ context->task = task;
+ task->bts = context;
+
+ get_task_struct(task);
+ }
+
+ return context;
+}
+
static int ptrace_bts_read_record(struct task_struct *child, size_t index,
struct bts_struct __user *out)
{
+ struct bts_context *context;
const struct bts_trace *trace;
struct bts_struct bts;
const unsigned char *at;
int error;
- trace = ds_read_bts(child->bts);
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
+ trace = ds_read_bts(context->tracer);
if (!trace)
- return -EPERM;
+ return -ESRCH;
at = trace->ds.top - ((index + 1) * trace->ds.size);
if ((void *)at < trace->ds.begin)
if (!trace->read)
return -EOPNOTSUPP;
- error = trace->read(child->bts, at, &bts);
+ error = trace->read(context->tracer, at, &bts);
if (error < 0)
return error;
long size,
struct bts_struct __user *out)
{
+ struct bts_context *context;
const struct bts_trace *trace;
const unsigned char *at;
int error, drained = 0;
- trace = ds_read_bts(child->bts);
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
+ trace = ds_read_bts(context->tracer);
if (!trace)
- return -EPERM;
+ return -ESRCH;
if (!trace->read)
return -EOPNOTSUPP;
for (at = trace->ds.begin; (void *)at < trace->ds.top;
out++, drained++, at += trace->ds.size) {
struct bts_struct bts;
- int error;
- error = trace->read(child->bts, at, &bts);
+ error = trace->read(context->tracer, at, &bts);
if (error < 0)
return error;
memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
- error = ds_reset_bts(child->bts);
+ error = ds_reset_bts(context->tracer);
if (error < 0)
return error;
return drained;
}
-static int ptrace_bts_allocate_buffer(struct task_struct *child, size_t size)
-{
- child->bts_buffer = alloc_locked_buffer(size);
- if (!child->bts_buffer)
- return -ENOMEM;
-
- child->bts_size = size;
-
- return 0;
-}
-
-static void ptrace_bts_free_buffer(struct task_struct *child)
-{
- free_locked_buffer(child->bts_buffer, child->bts_size);
- child->bts_buffer = NULL;
- child->bts_size = 0;
-}
-
static int ptrace_bts_config(struct task_struct *child,
long cfg_size,
const struct ptrace_bts_config __user *ucfg)
{
+ struct bts_context *context;
struct ptrace_bts_config cfg;
unsigned int flags = 0;
if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
return -EFAULT;
- if (child->bts) {
- ds_release_bts(child->bts);
- child->bts = NULL;
- }
+ context = child->bts;
+ if (!context)
+ context = alloc_bts_context(child);
+ if (!context)
+ return -ENOMEM;
if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
if (!cfg.signal)
return -EINVAL;
- child->thread.bts_ovfl_signal = cfg.signal;
return -EOPNOTSUPP;
+ context->bts_ovfl_signal = cfg.signal;
}
- if ((cfg.flags & PTRACE_BTS_O_ALLOC) &&
- (cfg.size != child->bts_size)) {
- int error;
+ ds_release_bts(context->tracer);
+ context->tracer = NULL;
- ptrace_bts_free_buffer(child);
+ if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
+ int err;
- error = ptrace_bts_allocate_buffer(child, cfg.size);
- if (error < 0)
- return error;
+ free_bts_buffer(context);
+ if (!cfg.size)
+ return 0;
+
+ err = alloc_bts_buffer(context, cfg.size);
+ if (err < 0)
+ return err;
}
if (cfg.flags & PTRACE_BTS_O_TRACE)
if (cfg.flags & PTRACE_BTS_O_SCHED)
flags |= BTS_TIMESTAMPS;
- child->bts = ds_request_bts(child, child->bts_buffer, child->bts_size,
- /* ovfl = */ NULL, /* th = */ (size_t)-1,
- flags);
- if (IS_ERR(child->bts)) {
- int error = PTR_ERR(child->bts);
-
- ptrace_bts_free_buffer(child);
- child->bts = NULL;
+ context->tracer =
+ ds_request_bts_task(child, context->buffer, context->size,
+ NULL, (size_t)-1, flags);
+ if (unlikely(IS_ERR(context->tracer))) {
+ int error = PTR_ERR(context->tracer);
+ free_bts_buffer(context);
+ context->tracer = NULL;
return error;
}
long cfg_size,
struct ptrace_bts_config __user *ucfg)
{
+ struct bts_context *context;
const struct bts_trace *trace;
struct ptrace_bts_config cfg;
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
if (cfg_size < sizeof(cfg))
return -EIO;
- trace = ds_read_bts(child->bts);
+ trace = ds_read_bts(context->tracer);
if (!trace)
- return -EPERM;
+ return -ESRCH;
memset(&cfg, 0, sizeof(cfg));
- cfg.size = trace->ds.end - trace->ds.begin;
- cfg.signal = child->thread.bts_ovfl_signal;
- cfg.bts_size = sizeof(struct bts_struct);
+ cfg.size = trace->ds.end - trace->ds.begin;
+ cfg.signal = context->bts_ovfl_signal;
+ cfg.bts_size = sizeof(struct bts_struct);
if (cfg.signal)
cfg.flags |= PTRACE_BTS_O_SIGNAL;
static int ptrace_bts_clear(struct task_struct *child)
{
+ struct bts_context *context;
const struct bts_trace *trace;
- trace = ds_read_bts(child->bts);
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
+ trace = ds_read_bts(context->tracer);
if (!trace)
- return -EPERM;
+ return -ESRCH;
memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
- return ds_reset_bts(child->bts);
+ return ds_reset_bts(context->tracer);
}
static int ptrace_bts_size(struct task_struct *child)
{
+ struct bts_context *context;
const struct bts_trace *trace;
- trace = ds_read_bts(child->bts);
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
+ trace = ds_read_bts(context->tracer);
if (!trace)
- return -EPERM;
+ return -ESRCH;
return (trace->ds.top - trace->ds.begin) / trace->ds.size;
}
-static void ptrace_bts_fork(struct task_struct *tsk)
-{
- tsk->bts = NULL;
- tsk->bts_buffer = NULL;
- tsk->bts_size = 0;
- tsk->thread.bts_ovfl_signal = 0;
-}
-
-static void ptrace_bts_untrace(struct task_struct *child)
+/*
+ * Called from __ptrace_unlink() after the child has been moved back
+ * to its original parent.
+ */
+void ptrace_bts_untrace(struct task_struct *child)
{
if (unlikely(child->bts)) {
- ds_release_bts(child->bts);
+ free_bts_context(child->bts);
child->bts = NULL;
-
- /* We cannot update total_vm and locked_vm since
- child's mm is already gone. But we can reclaim the
- memory. */
- kfree(child->bts_buffer);
- child->bts_buffer = NULL;
- child->bts_size = 0;
}
}
-
-static void ptrace_bts_detach(struct task_struct *child)
-{
- /*
- * Ptrace_detach() races with ptrace_untrace() in case
- * the child dies and is reaped by another thread.
- *
- * We only do the memory accounting at this point and
- * leave the buffer deallocation and the bts tracer
- * release to ptrace_bts_untrace() which will be called
- * later on with tasklist_lock held.
- */
- release_locked_buffer(child->bts_buffer, child->bts_size);
-}
-#else
-static inline void ptrace_bts_fork(struct task_struct *tsk) {}
-static inline void ptrace_bts_detach(struct task_struct *child) {}
-static inline void ptrace_bts_untrace(struct task_struct *child) {}
#endif /* CONFIG_X86_PTRACE_BTS */
-void x86_ptrace_fork(struct task_struct *child, unsigned long clone_flags)
-{
- ptrace_bts_fork(child);
-}
-
-void x86_ptrace_untrace(struct task_struct *child)
-{
- ptrace_bts_untrace(child);
-}
-
/*
* Called by kernel/ptrace.c when detaching..
*
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
#endif
- ptrace_bts_detach(child);
}
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
break;
}
}
+#endif
+
+#if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
+/* Set correct numa_node information for AMD NB functions */
+static void __init quirk_amd_nb_node(struct pci_dev *dev)
+{
+ struct pci_dev *nb_ht;
+ unsigned int devfn;
+ u32 val;
+
+ devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+ nb_ht = pci_get_slot(dev->bus, devfn);
+ if (!nb_ht)
+ return;
+
+ pci_read_config_dword(nb_ht, 0x60, &val);
+ set_dev_node(&dev->dev, val & 7);
+ pci_dev_put(dev);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MEMCTL,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_HT,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MAP,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_DRAM,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK,
+ quirk_amd_nb_node);
#endif
DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
},
},
+ { /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */
+ .callback = set_bios_reboot,
+ .ident = "Dell OptiPlex 360",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"),
+ DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
+ },
+ },
{ /* Handle problems with rebooting on Dell 2400's */
.callback = set_bios_reboot,
.ident = "Dell PowerEdge 2400",
#define ARCH_SETUP
#endif
+/*
+ * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
+ * The direct mapping extends to max_pfn_mapped, so that we can directly access
+ * apertures, ACPI and other tables without having to play with fixmaps.
+ */
+unsigned long max_low_pfn_mapped;
+unsigned long max_pfn_mapped;
+
RESERVE_BRK(dmi_alloc, 65536);
unsigned int boot_cpu_id __read_mostly;
unsigned long mmu_cr4_features = X86_CR4_PAE;
#endif
-/* Boot loader ID as an integer, for the benefit of proc_dointvec */
-int bootloader_type;
+/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
+int bootloader_type, bootloader_version;
/*
* Setup options
#endif
saved_video_mode = boot_params.hdr.vid_mode;
bootloader_type = boot_params.hdr.type_of_loader;
+ if ((bootloader_type >> 4) == 0xe) {
+ bootloader_type &= 0xf;
+ bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
+ }
+ bootloader_version = bootloader_type & 0xf;
+ bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
#ifdef CONFIG_BLK_DEV_RAM
rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
max_low_pfn = max_pfn;
high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+ max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
#endif
#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
setup_bios_corruption_check();
#endif
+ printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+ max_pfn_mapped<<PAGE_SHIFT);
+
reserve_brk();
/* max_pfn_mapped is updated here */
#ifdef CONFIG_X86_32
-/**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- * Perform any necessary interrupt initialisation prior to setting up
- * the "ordinary" interrupt call gates. For legacy reasons, the ISA
- * interrupts should be initialised here if the machine emulates a PC
- * in any way.
- **/
-void __init x86_quirk_pre_intr_init(void)
-{
- if (x86_quirks->arch_pre_intr_init) {
- if (x86_quirks->arch_pre_intr_init())
- return;
- }
- init_ISA_irqs();
-}
-
/**
* x86_quirk_intr_init - post gate setup interrupt initialisation
*
early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
#endif
+#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+ /*
+ * make sure boot cpu node_number is right, when boot cpu is on the
+ * node that doesn't have mem installed
+ */
+ per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id);
+#endif
+
/* Setup node to cpumask map */
setup_node_to_cpumask_map();
}
struct smp_ops smp_ops = {
- .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
- .smp_prepare_cpus = native_smp_prepare_cpus,
- .smp_cpus_done = native_smp_cpus_done,
+ .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
+ .smp_prepare_cpus = native_smp_prepare_cpus,
+ .smp_cpus_done = native_smp_cpus_done,
- .smp_send_stop = native_smp_send_stop,
- .smp_send_reschedule = native_smp_send_reschedule,
+ .smp_send_stop = native_smp_send_stop,
+ .smp_send_reschedule = native_smp_send_reschedule,
- .cpu_up = native_cpu_up,
- .cpu_die = native_cpu_die,
- .cpu_disable = native_cpu_disable,
- .play_dead = native_play_dead,
+ .cpu_up = native_cpu_up,
+ .cpu_die = native_cpu_die,
+ .cpu_disable = native_cpu_disable,
+ .play_dead = native_play_dead,
- .send_call_func_ipi = native_send_call_func_ipi,
+ .send_call_func_ipi = native_send_call_func_ipi,
.send_call_func_single_ipi = native_send_call_func_single_ipi,
};
EXPORT_SYMBOL_GPL(smp_ops);
* INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
* won't ... remember to clear down the APIC, etc later.
*/
-int __devinit
+int __cpuinit
wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
return (send_status | accept_status);
}
-int __devinit
+static int __cpuinit
wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
/* mark "stuck" area as not stuck */
*((volatile unsigned long *)trampoline_base) = 0;
- /*
- * Cleanup possible dangling ends...
- */
- smpboot_restore_warm_reset_vector();
+ if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+ /*
+ * Cleanup possible dangling ends...
+ */
+ smpboot_restore_warm_reset_vector();
+ }
return boot_error;
}
*/
if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
!cpu_has_apic) {
- printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
- boot_cpu_physical_apicid);
- printk(KERN_ERR "... forcing use of dummy APIC emulation."
+ if (!disable_apic) {
+ pr_err("BIOS bug, local APIC #%d not detected!...\n",
+ boot_cpu_physical_apicid);
+ pr_err("... forcing use of dummy APIC emulation."
"(tell your hw vendor)\n");
+ }
smpboot_clear_io_apic();
arch_disable_smp_support();
return -1;
static int save_stack_stack(void *data, char *name)
{
- return -1;
+ return 0;
}
static void save_stack_address(void *data, unsigned long addr, int reliable)
.long sys_inotify_init1
.long sys_preadv
.long sys_pwritev
+ .long sys_rt_tgsigqueueinfo /* 335 */
struct bau_desc *adp;
struct bau_desc *ad2;
- adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node);
+ /*
+ * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
+ * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per blade
+ */
+ adp = (struct bau_desc *)kmalloc_node(sizeof(struct bau_desc)*
+ UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
BUG_ON(!adp);
pa = uv_gpa(adp); /* need the real nasid*/
(n << UV_DESC_BASE_PNODE_SHIFT | m));
}
- for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) {
+ /*
+ * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+ * cpu even though we only use the first one; one descriptor can
+ * describe a broadcast to 256 nodes.
+ */
+ for (i = 0, ad2 = adp; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR);
+ i++, ad2++) {
memset(ad2, 0, sizeof(struct bau_desc));
ad2->header.sw_ack_flag = 1;
/*
}
clts(); /* Allow maths ops (or we recurse) */
-#ifdef CONFIG_X86_32
- restore_fpu(tsk);
-#else
/*
* Paranoid restore. send a SIGSEGV if we fail to restore the state.
*/
force_sig(SIGSEGV, tsk);
return;
}
-#endif
+
thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */
tsk->fpu_counter++;
}
for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
set_bit(i, used_vectors);
-#ifdef CONFIG_X86_64
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
-#else
- set_bit(SYSCALL_VECTOR, used_vectors);
-#endif
+
/*
* Should be a barrier for any external CPU state:
*/
{
u64 tsc1, tsc2, delta, ref1, ref2;
unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
- unsigned long flags, latch, ms, fast_calibrate, tsc_khz;
+ unsigned long flags, latch, ms, fast_calibrate, hv_tsc_khz;
int hpet = is_hpet_enabled(), i, loopmin;
- tsc_khz = get_hypervisor_tsc_freq();
- if (tsc_khz) {
+ hv_tsc_khz = get_hypervisor_tsc_freq();
+ if (hv_tsc_khz) {
printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
- return tsc_khz;
+ return hv_tsc_khz;
}
local_irq_save(flags);
#ifdef CONFIG_X86_64
static cycle_t __vsyscall_fn vread_tsc(void)
{
- cycle_t ret = (cycle_t)vget_cycles();
+ cycle_t ret;
+
+ /*
+ * Surround the RDTSC by barriers, to make sure it's not
+ * speculated to outside the seqlock critical section and
+ * does not cause time warps:
+ */
+ rdtsc_barrier();
+ ret = (cycle_t)vget_cycles();
+ rdtsc_barrier();
return ret >= __vsyscall_gtod_data.clock.cycle_last ?
ret : __vsyscall_gtod_data.clock.cycle_last;
* of a critical section, to be able to prove TSC time-warps:
*/
static __cpuinitdata raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED;
+
static __cpuinitdata cycles_t last_tsc;
static __cpuinitdata cycles_t max_warp;
static __cpuinitdata int nr_warps;
return;
if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
- printk(KERN_INFO
- "Skipping synchronization checks as TSC is reliable.\n");
+ pr_info("Skipping synchronization checks as TSC is reliable.\n");
return;
}
- printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
- smp_processor_id(), cpu);
+ pr_info("checking TSC synchronization [CPU#%d -> CPU#%d]:",
+ smp_processor_id(), cpu);
/*
* Reset it - in case this is a second bootup:
if (nr_warps) {
printk("\n");
- printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
- " turning off TSC clock.\n", max_warp);
+ pr_warning("Measured %Ld cycles TSC warp between CPUs, "
+ "turning off TSC clock.\n", max_warp);
mark_tsc_unstable("check_tsc_sync_source failed");
} else {
printk(" passed.\n");
while (atomic_read(&stop_count) != cpus)
cpu_relax();
}
-#undef NR_LOOPS
-
info->regs.pt.ds = 0;
info->regs.pt.es = 0;
info->regs.pt.fs = 0;
-
-/* we are clearing gs later just before "jmp resume_userspace",
- * because it is not saved/restored.
- */
+#ifndef CONFIG_X86_32_LAZY_GS
+ info->regs.pt.gs = 0;
+#endif
/*
* The flags register is also special: we cannot trust that the user
}
/*
- * Save old state, set default return value (%ax) to 0
+ * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL)
*/
- info->regs32->ax = 0;
+ info->regs32->ax = VM86_SIGNAL;
tsk->thread.saved_sp0 = tsk->thread.sp0;
tsk->thread.saved_fs = info->regs32->fs;
tsk->thread.saved_gs = get_user_gs(info->regs32);
__asm__ __volatile__(
"movl %0,%%esp\n\t"
"movl %1,%%ebp\n\t"
+#ifdef CONFIG_X86_32_LAZY_GS
"mov %2, %%gs\n\t"
+#endif
"jmp resume_userspace"
: /* no outputs */
:"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0));
}
#endif
-static void vmi_enter_lazy_cpu(void)
+static void vmi_start_context_switch(struct task_struct *prev)
{
- paravirt_enter_lazy_cpu();
+ paravirt_start_context_switch(prev);
vmi_ops.set_lazy_mode(2);
}
+static void vmi_end_context_switch(struct task_struct *next)
+{
+ vmi_ops.set_lazy_mode(0);
+ paravirt_end_context_switch(next);
+}
+
static void vmi_enter_lazy_mmu(void)
{
paravirt_enter_lazy_mmu();
vmi_ops.set_lazy_mode(1);
}
-static void vmi_leave_lazy(void)
+static void vmi_leave_lazy_mmu(void)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
vmi_ops.set_lazy_mode(0);
+ paravirt_leave_lazy_mmu();
}
static inline int __init check_vmi_rom(struct vrom_header *rom)
para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
para_fill(pv_cpu_ops.io_delay, IODelay);
- para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
+ para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
set_lazy_mode, SetLazyMode);
- para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+ para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
set_lazy_mode, SetLazyMode);
para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
set_lazy_mode, SetLazyMode);
- para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy,
+ para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
set_lazy_mode, SetLazyMode);
/* user and kernel flush are just handled with different flags to FlushTLB */
+/*
+ * ld script for the x86 kernel
+ *
+ * Historic 32-bit version written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *
+ * Modernisation, unification and other changes and fixes:
+ * Copyright (C) 2007-2009 Sam Ravnborg <sam@ravnborg.org>
+ *
+ *
+ * Don't define absolute symbols until and unless you know that symbol
+ * value is should remain constant even if kernel image is relocated
+ * at run time. Absolute symbols are not relocated. If symbol value should
+ * change if kernel is relocated, make the symbol section relative and
+ * put it inside the section definition.
+ */
+
#ifdef CONFIG_X86_32
-# include "vmlinux_32.lds.S"
+#define LOAD_OFFSET __PAGE_OFFSET
#else
-# include "vmlinux_64.lds.S"
+#define LOAD_OFFSET __START_KERNEL_map
#endif
+
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page_types.h>
+#include <asm/cache.h>
+#include <asm/boot.h>
+
+#undef i386 /* in case the preprocessor is a 32bit one */
+
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+
+#ifdef CONFIG_X86_32
+OUTPUT_ARCH(i386)
+ENTRY(phys_startup_32)
+jiffies = jiffies_64;
+#else
+OUTPUT_ARCH(i386:x86-64)
+ENTRY(phys_startup_64)
+jiffies_64 = jiffies;
+#endif
+
+PHDRS {
+ text PT_LOAD FLAGS(5); /* R_E */
+ data PT_LOAD FLAGS(7); /* RWE */
+#ifdef CONFIG_X86_64
+ user PT_LOAD FLAGS(7); /* RWE */
+ data.init PT_LOAD FLAGS(7); /* RWE */
+#ifdef CONFIG_SMP
+ percpu PT_LOAD FLAGS(7); /* RWE */
+#endif
+ data.init2 PT_LOAD FLAGS(7); /* RWE */
+#endif
+ note PT_NOTE FLAGS(0); /* ___ */
+}
+
+SECTIONS
+{
+#ifdef CONFIG_X86_32
+ . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
+ phys_startup_32 = startup_32 - LOAD_OFFSET;
+#else
+ . = __START_KERNEL;
+ phys_startup_64 = startup_64 - LOAD_OFFSET;
+#endif
+
+ /* Text and read-only data */
+
+ /* bootstrapping code */
+ .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
+ _text = .;
+ *(.text.head)
+ } :text = 0x9090
+
+ /* The rest of the text */
+ .text : AT(ADDR(.text) - LOAD_OFFSET) {
+#ifdef CONFIG_X86_32
+ /* not really needed, already page aligned */
+ . = ALIGN(PAGE_SIZE);
+ *(.text.page_aligned)
+#endif
+ . = ALIGN(8);
+ _stext = .;
+ TEXT_TEXT
+ SCHED_TEXT
+ LOCK_TEXT
+ KPROBES_TEXT
+ IRQENTRY_TEXT
+ *(.fixup)
+ *(.gnu.warning)
+ /* End of text section */
+ _etext = .;
+ } :text = 0x9090
+
+ NOTES :text :note
+
+ /* Exception table */
+ . = ALIGN(16);
+ __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
+ __start___ex_table = .;
+ *(__ex_table)
+ __stop___ex_table = .;
+ } :text = 0x9090
+
+ RODATA
+
+ /* Data */
+ . = ALIGN(PAGE_SIZE);
+ .data : AT(ADDR(.data) - LOAD_OFFSET) {
+ DATA_DATA
+ CONSTRUCTORS
+
+#ifdef CONFIG_X86_64
+ /* End of data section */
+ _edata = .;
+#endif
+ } :data
+
+#ifdef CONFIG_X86_32
+ /* 32 bit has nosave before _edata */
+ . = ALIGN(PAGE_SIZE);
+ .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+ __nosave_begin = .;
+ *(.data.nosave)
+ . = ALIGN(PAGE_SIZE);
+ __nosave_end = .;
+ }
+#endif
+
+ . = ALIGN(PAGE_SIZE);
+ .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
+ *(.data.page_aligned)
+ *(.data.idt)
+ }
+
+#ifdef CONFIG_X86_32
+ . = ALIGN(32);
+#else
+ . = ALIGN(PAGE_SIZE);
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+#endif
+ .data.cacheline_aligned :
+ AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
+ *(.data.cacheline_aligned)
+ }
+
+ /* rarely changed data like cpu maps */
+#ifdef CONFIG_X86_32
+ . = ALIGN(32);
+#else
+ . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
+#endif
+ .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
+ *(.data.read_mostly)
+
+#ifdef CONFIG_X86_32
+ /* End of data section */
+ _edata = .;
+#endif
+ }
+
+#ifdef CONFIG_X86_64
+
+#define VSYSCALL_ADDR (-10*1024*1024)
+#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + \
+ SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + \
+ SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+
+#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
+#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
+
+#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
+#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
+
+ . = VSYSCALL_ADDR;
+ .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) {
+ *(.vsyscall_0)
+ } :user
+
+ __vsyscall_0 = VSYSCALL_VIRT_ADDR;
+
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
+ *(.vsyscall_fn)
+ }
+
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
+ *(.vsyscall_gtod_data)
+ }
+
+ vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
+ .vsyscall_clock : AT(VLOAD(.vsyscall_clock)) {
+ *(.vsyscall_clock)
+ }
+ vsyscall_clock = VVIRT(.vsyscall_clock);
+
+
+ .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) {
+ *(.vsyscall_1)
+ }
+ .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) {
+ *(.vsyscall_2)
+ }
+
+ .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) {
+ *(.vgetcpu_mode)
+ }
+ vgetcpu_mode = VVIRT(.vgetcpu_mode);
+
+ . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ .jiffies : AT(VLOAD(.jiffies)) {
+ *(.jiffies)
+ }
+ jiffies = VVIRT(.jiffies);
+
+ .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
+ *(.vsyscall_3)
+ }
+
+ . = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
+
+#undef VSYSCALL_ADDR
+#undef VSYSCALL_PHYS_ADDR
+#undef VSYSCALL_VIRT_ADDR
+#undef VLOAD_OFFSET
+#undef VLOAD
+#undef VVIRT_OFFSET
+#undef VVIRT
+
+#endif /* CONFIG_X86_64 */
+
+ /* init_task */
+ . = ALIGN(THREAD_SIZE);
+ .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
+ *(.data.init_task)
+ }
+#ifdef CONFIG_X86_64
+ :data.init
+#endif
+
+ /*
+ * smp_locks might be freed after init
+ * start/end must be page aligned
+ */
+ . = ALIGN(PAGE_SIZE);
+ .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+ __smp_locks = .;
+ *(.smp_locks)
+ __smp_locks_end = .;
+ . = ALIGN(PAGE_SIZE);
+ }
+
+ /* Init code and data - will be freed after init */
+ . = ALIGN(PAGE_SIZE);
+ .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+ __init_begin = .; /* paired with __init_end */
+ _sinittext = .;
+ INIT_TEXT
+ _einittext = .;
+ }
+
+ .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
+ INIT_DATA
+ }
+
+ . = ALIGN(16);
+ .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
+ __setup_start = .;
+ *(.init.setup)
+ __setup_end = .;
+ }
+ .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
+ __initcall_start = .;
+ INITCALLS
+ __initcall_end = .;
+ }
+
+ .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
+ __con_initcall_start = .;
+ *(.con_initcall.init)
+ __con_initcall_end = .;
+ }
+
+ .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
+ __x86_cpu_dev_start = .;
+ *(.x86_cpu_dev.init)
+ __x86_cpu_dev_end = .;
+ }
+
+ SECURITY_INIT
+
+ . = ALIGN(8);
+ .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
+ __parainstructions = .;
+ *(.parainstructions)
+ __parainstructions_end = .;
+ }
+
+ . = ALIGN(8);
+ .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
+ __alt_instructions = .;
+ *(.altinstructions)
+ __alt_instructions_end = .;
+ }
+
+ .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
+ *(.altinstr_replacement)
+ }
+
+ /*
+ * .exit.text is discard at runtime, not link time, to deal with
+ * references from .altinstructions and .eh_frame
+ */
+ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+ EXIT_TEXT
+ }
+
+ .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
+ EXIT_DATA
+ }
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ . = ALIGN(PAGE_SIZE);
+ .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
+ __initramfs_start = .;
+ *(.init.ramfs)
+ __initramfs_end = .;
+ }
+#endif
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
+ /*
+ * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
+ * output PHDR, so the next output section - __data_nosave - should
+ * start another section data.init2. Also, pda should be at the head of
+ * percpu area. Preallocate it and define the percpu offset symbol
+ * so that it can be accessed as a percpu variable.
+ */
+ . = ALIGN(PAGE_SIZE);
+ PERCPU_VADDR(0, :percpu)
+#else
+ PERCPU(PAGE_SIZE)
+#endif
+
+ . = ALIGN(PAGE_SIZE);
+
+ /* freed after init ends here */
+ .init.end : AT(ADDR(.init.end) - LOAD_OFFSET) {
+ __init_end = .;
+ }
+
+#ifdef CONFIG_X86_64
+ .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+ . = ALIGN(PAGE_SIZE);
+ __nosave_begin = .;
+ *(.data.nosave)
+ . = ALIGN(PAGE_SIZE);
+ __nosave_end = .;
+ } :data.init2
+ /* use another section data.init2, see PERCPU_VADDR() above */
+#endif
+
+ /* BSS */
+ . = ALIGN(PAGE_SIZE);
+ .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
+ __bss_start = .;
+ *(.bss.page_aligned)
+ *(.bss)
+ . = ALIGN(4);
+ __bss_stop = .;
+ }
+
+ . = ALIGN(PAGE_SIZE);
+ .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
+ __brk_base = .;
+ . += 64 * 1024; /* 64k alignment slop space */
+ *(.brk_reservation) /* areas brk users have reserved */
+ __brk_limit = .;
+ }
+
+ .end : AT(ADDR(.end) - LOAD_OFFSET) {
+ _end = .;
+ }
+
+ /* Sections to be discarded */
+ /DISCARD/ : {
+ *(.exitcall.exit)
+ *(.eh_frame)
+ *(.discard)
+ }
+
+ STABS_DEBUG
+ DWARF_DEBUG
+}
+
+
+#ifdef CONFIG_X86_32
+ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE")
+#else
+/*
+ * Per-cpu symbols which need to be offset from __per_cpu_load
+ * for the boot processor.
+ */
+#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+INIT_PER_CPU(gdt_page);
+INIT_PER_CPU(irq_stack_union);
+
+/*
+ * Build-time check on the image size:
+ */
+ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE")
+
+#ifdef CONFIG_SMP
+ASSERT((per_cpu__irq_stack_union == 0),
+ "irq_stack_union is not at start of per-cpu area");
+#endif
+
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_KEXEC
+#include <asm/kexec.h>
+
+ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+ "kexec control code size is too big")
+#endif
+
+++ /dev/null
-/* ld script to make i386 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- *
- * Don't define absolute symbols until and unless you know that symbol
- * value is should remain constant even if kernel image is relocated
- * at run time. Absolute symbols are not relocated. If symbol value should
- * change if kernel is relocated, make the symbol section relative and
- * put it inside the section definition.
- */
-
-#define LOAD_OFFSET __PAGE_OFFSET
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/thread_info.h>
-#include <asm/page_types.h>
-#include <asm/cache.h>
-#include <asm/boot.h>
-
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(phys_startup_32)
-jiffies = jiffies_64;
-
-PHDRS {
- text PT_LOAD FLAGS(5); /* R_E */
- data PT_LOAD FLAGS(7); /* RWE */
- note PT_NOTE FLAGS(0); /* ___ */
-}
-SECTIONS
-{
- . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
- phys_startup_32 = startup_32 - LOAD_OFFSET;
-
- .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
- _text = .; /* Text and read-only data */
- *(.text.head)
- } :text = 0x9090
-
- /* read-only */
- .text : AT(ADDR(.text) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE); /* not really needed, already page aligned */
- *(.text.page_aligned)
- TEXT_TEXT
- SCHED_TEXT
- LOCK_TEXT
- KPROBES_TEXT
- IRQENTRY_TEXT
- *(.fixup)
- *(.gnu.warning)
- _etext = .; /* End of text section */
- } :text = 0x9090
-
- NOTES :text :note
-
- . = ALIGN(16); /* Exception table */
- __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
- __start___ex_table = .;
- *(__ex_table)
- __stop___ex_table = .;
- } :text = 0x9090
-
- RODATA
-
- /* writeable */
- . = ALIGN(PAGE_SIZE);
- .data : AT(ADDR(.data) - LOAD_OFFSET) { /* Data */
- DATA_DATA
- CONSTRUCTORS
- } :data
-
- . = ALIGN(PAGE_SIZE);
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- }
-
- . = ALIGN(PAGE_SIZE);
- .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
- *(.data.page_aligned)
- *(.data.idt)
- }
-
- . = ALIGN(32);
- .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
- *(.data.cacheline_aligned)
- }
-
- /* rarely changed data like cpu maps */
- . = ALIGN(32);
- .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
- *(.data.read_mostly)
- _edata = .; /* End of data section */
- }
-
- . = ALIGN(THREAD_SIZE); /* init_task */
- .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
- *(.data.init_task)
- }
-
- /* might get freed after init */
- . = ALIGN(PAGE_SIZE);
- .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
- __smp_locks = .;
- *(.smp_locks)
- __smp_locks_end = .;
- }
- /* will be freed after init
- * Following ALIGN() is required to make sure no other data falls on the
- * same page where __smp_alt_end is pointing as that page might be freed
- * after boot. Always make sure that ALIGN() directive is present after
- * the section which contains __smp_alt_end.
- */
- . = ALIGN(PAGE_SIZE);
-
- /* will be freed after init */
- . = ALIGN(PAGE_SIZE); /* Init code and data */
- .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
- __init_begin = .;
- _sinittext = .;
- INIT_TEXT
- _einittext = .;
- }
- .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
- INIT_DATA
- }
- . = ALIGN(16);
- .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
- __setup_start = .;
- *(.init.setup)
- __setup_end = .;
- }
- .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
- __initcall_start = .;
- INITCALLS
- __initcall_end = .;
- }
- .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
- __con_initcall_start = .;
- *(.con_initcall.init)
- __con_initcall_end = .;
- }
- .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
- __x86_cpu_dev_start = .;
- *(.x86_cpu_dev.init)
- __x86_cpu_dev_end = .;
- }
- SECURITY_INIT
- . = ALIGN(4);
- .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
- __alt_instructions = .;
- *(.altinstructions)
- __alt_instructions_end = .;
- }
- .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
- *(.altinstr_replacement)
- }
- . = ALIGN(4);
- .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
- __parainstructions = .;
- *(.parainstructions)
- __parainstructions_end = .;
- }
- /* .exit.text is discard at runtime, not link time, to deal with references
- from .altinstructions and .eh_frame */
- .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
- EXIT_TEXT
- }
- .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
- EXIT_DATA
- }
-#if defined(CONFIG_BLK_DEV_INITRD)
- . = ALIGN(PAGE_SIZE);
- .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
- __initramfs_start = .;
- *(.init.ramfs)
- __initramfs_end = .;
- }
-#endif
- PERCPU(PAGE_SIZE)
- . = ALIGN(PAGE_SIZE);
- /* freed after init ends here */
-
- .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
- __init_end = .;
- __bss_start = .; /* BSS */
- *(.bss.page_aligned)
- *(.bss)
- . = ALIGN(4);
- __bss_stop = .;
- }
-
- .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __brk_base = . ;
- . += 64 * 1024 ; /* 64k alignment slop space */
- *(.brk_reservation) /* areas brk users have reserved */
- __brk_limit = . ;
- }
-
- .end : AT(ADDR(.end) - LOAD_OFFSET) {
- _end = . ;
- }
-
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.exitcall.exit)
- *(.discard)
- }
-
- STABS_DEBUG
-
- DWARF_DEBUG
-}
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_KEXEC
-/* Link time checks */
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
- "kexec control code size is too big")
-#endif
+++ /dev/null
-/* ld script to make x86-64 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- */
-
-#define LOAD_OFFSET __START_KERNEL_map
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/asm-offsets.h>
-#include <asm/page_types.h>
-
-#undef i386 /* in case the preprocessor is a 32bit one */
-
-OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
-OUTPUT_ARCH(i386:x86-64)
-ENTRY(phys_startup_64)
-jiffies_64 = jiffies;
-PHDRS {
- text PT_LOAD FLAGS(5); /* R_E */
- data PT_LOAD FLAGS(7); /* RWE */
- user PT_LOAD FLAGS(7); /* RWE */
- data.init PT_LOAD FLAGS(7); /* RWE */
-#ifdef CONFIG_SMP
- percpu PT_LOAD FLAGS(7); /* RWE */
-#endif
- data.init2 PT_LOAD FLAGS(7); /* RWE */
- note PT_NOTE FLAGS(0); /* ___ */
-}
-SECTIONS
-{
- . = __START_KERNEL;
- phys_startup_64 = startup_64 - LOAD_OFFSET;
- .text : AT(ADDR(.text) - LOAD_OFFSET) {
- _text = .; /* Text and read-only data */
- /* First the code that has to be first for bootstrapping */
- *(.text.head)
- _stext = .;
- /* Then the rest */
- TEXT_TEXT
- SCHED_TEXT
- LOCK_TEXT
- KPROBES_TEXT
- IRQENTRY_TEXT
- *(.fixup)
- *(.gnu.warning)
- _etext = .; /* End of text section */
- } :text = 0x9090
-
- NOTES :text :note
-
- . = ALIGN(16); /* Exception table */
- __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
- __start___ex_table = .;
- *(__ex_table)
- __stop___ex_table = .;
- } :text = 0x9090
-
- RODATA
-
- . = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */
- /* Data */
- .data : AT(ADDR(.data) - LOAD_OFFSET) {
- DATA_DATA
- CONSTRUCTORS
- _edata = .; /* End of data section */
- } :data
-
-
- .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- *(.data.cacheline_aligned)
- }
- . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
- .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
- *(.data.read_mostly)
- }
-
-#define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
- . = VSYSCALL_ADDR;
- .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { *(.vsyscall_0) } :user
- __vsyscall_0 = VSYSCALL_VIRT_ADDR;
-
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) }
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))
- { *(.vsyscall_gtod_data) }
- vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
- .vsyscall_clock : AT(VLOAD(.vsyscall_clock))
- { *(.vsyscall_clock) }
- vsyscall_clock = VVIRT(.vsyscall_clock);
-
-
- .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
- { *(.vsyscall_1) }
- .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
- { *(.vsyscall_2) }
-
- .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
- vgetcpu_mode = VVIRT(.vgetcpu_mode);
-
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
- jiffies = VVIRT(.jiffies);
-
- .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3))
- { *(.vsyscall_3) }
-
- . = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
-
-#undef VSYSCALL_ADDR
-#undef VSYSCALL_PHYS_ADDR
-#undef VSYSCALL_VIRT_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
- .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
- . = ALIGN(THREAD_SIZE); /* init_task */
- *(.data.init_task)
- }:data.init
-
- .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- *(.data.page_aligned)
- }
-
- .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
- /* might get freed after init */
- . = ALIGN(PAGE_SIZE);
- __smp_alt_begin = .;
- __smp_locks = .;
- *(.smp_locks)
- __smp_locks_end = .;
- . = ALIGN(PAGE_SIZE);
- __smp_alt_end = .;
- }
-
- . = ALIGN(PAGE_SIZE); /* Init code and data */
- __init_begin = .; /* paired with __init_end */
- .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
- _sinittext = .;
- INIT_TEXT
- _einittext = .;
- }
- .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
- __initdata_begin = .;
- INIT_DATA
- __initdata_end = .;
- }
-
- .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
- . = ALIGN(16);
- __setup_start = .;
- *(.init.setup)
- __setup_end = .;
- }
- .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
- __initcall_start = .;
- INITCALLS
- __initcall_end = .;
- }
- .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
- __con_initcall_start = .;
- *(.con_initcall.init)
- __con_initcall_end = .;
- }
- .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
- __x86_cpu_dev_start = .;
- *(.x86_cpu_dev.init)
- __x86_cpu_dev_end = .;
- }
- SECURITY_INIT
-
- . = ALIGN(8);
- .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
- __parainstructions = .;
- *(.parainstructions)
- __parainstructions_end = .;
- }
-
- .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
- . = ALIGN(8);
- __alt_instructions = .;
- *(.altinstructions)
- __alt_instructions_end = .;
- }
- .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
- *(.altinstr_replacement)
- }
- /* .exit.text is discard at runtime, not link time, to deal with references
- from .altinstructions and .eh_frame */
- .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
- EXIT_TEXT
- }
- .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
- EXIT_DATA
- }
-
-#ifdef CONFIG_BLK_DEV_INITRD
- . = ALIGN(PAGE_SIZE);
- .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
- __initramfs_start = .;
- *(.init.ramfs)
- __initramfs_end = .;
- }
-#endif
-
-#ifdef CONFIG_SMP
- /*
- * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
- * output PHDR, so the next output section - __data_nosave - should
- * start another section data.init2. Also, pda should be at the head of
- * percpu area. Preallocate it and define the percpu offset symbol
- * so that it can be accessed as a percpu variable.
- */
- . = ALIGN(PAGE_SIZE);
- PERCPU_VADDR(0, :percpu)
-#else
- PERCPU(PAGE_SIZE)
-#endif
-
- . = ALIGN(PAGE_SIZE);
- __init_end = .;
-
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */
-
- .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __bss_start = .; /* BSS */
- *(.bss.page_aligned)
- *(.bss)
- __bss_stop = .;
- }
-
- .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __brk_base = . ;
- . += 64 * 1024 ; /* 64k alignment slop space */
- *(.brk_reservation) /* areas brk users have reserved */
- __brk_limit = . ;
- }
-
- _end = . ;
-
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.exitcall.exit)
- *(.eh_frame)
- *(.discard)
- }
-
- STABS_DEBUG
-
- DWARF_DEBUG
-}
-
- /*
- * Per-cpu symbols which need to be offset from __per_cpu_load
- * for the boot processor.
- */
-#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_SMP
-ASSERT((per_cpu__irq_stack_union == 0),
- "irq_stack_union is not at start of per-cpu area");
-#endif
-
-#ifdef CONFIG_KEXEC
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
- "kexec control code size is too big")
-#endif
return;
}
- /*
- * Surround the RDTSC by barriers, to make sure it's not
- * speculated to outside the seqlock critical section and
- * does not cause time warps:
- */
- rdtsc_barrier();
now = vread();
- rdtsc_barrier();
-
base = __vsyscall_gtod_data.clock.cycle_last;
mask = __vsyscall_gtod_data.clock.mask;
mult = __vsyscall_gtod_data.clock.mult;
/* When lazy mode is turned off reset the per-cpu lazy mode variable and then
* issue the do-nothing hypercall to flush any stored calls. */
-static void lguest_leave_lazy_mode(void)
+static void lguest_leave_lazy_mmu_mode(void)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+ paravirt_leave_lazy_mmu();
+}
+
+static void lguest_end_context_switch(struct task_struct *next)
+{
+ kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+ paravirt_end_context_switch(next);
}
/*G:033
void lguest_setup_irq(unsigned int irq)
{
- irq_to_desc_alloc_cpu(irq, 0);
+ irq_to_desc_alloc_node(irq, 0);
set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
handle_level_irq, "level");
}
pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
pv_cpu_ops.wbinvd = lguest_wbinvd;
- pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
- pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+ pv_cpu_ops.start_context_switch = paravirt_start_context_switch;
+ pv_cpu_ops.end_context_switch = lguest_end_context_switch;
/* pagetable management */
pv_mmu_ops.write_cr3 = lguest_write_cr3;
pv_mmu_ops.read_cr2 = lguest_read_cr2;
pv_mmu_ops.read_cr3 = lguest_read_cr3;
pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
- pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+ pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
pv_mmu_ops.pte_update = lguest_pte_update;
pv_mmu_ops.pte_update_defer = lguest_pte_update;
st->current_address >= st->marker[1].start_address) {
const char *unit = units;
unsigned long delta;
+ int width = sizeof(unsigned long) * 2;
/*
* Now print the actual finished series
*/
- seq_printf(m, "0x%p-0x%p ",
- (void *)st->start_address,
- (void *)st->current_address);
+ seq_printf(m, "0x%0*lx-0x%0*lx ",
+ width, st->start_address,
+ width, st->current_address);
delta = (st->current_address - st->start_address) >> 10;
while (!(delta & 1023) && unit[1]) {
* Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
* Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
*/
-#include <linux/interrupt.h>
-#include <linux/mmiotrace.h>
-#include <linux/bootmem.h>
-#include <linux/compiler.h>
-#include <linux/highmem.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/vt_kern.h>
-#include <linux/signal.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/errno.h>
-#include <linux/magic.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mman.h>
-#include <linux/tty.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
-
-#include <asm-generic/sections.h>
-
-#include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
-#include <asm/segment.h>
-#include <asm/system.h>
-#include <asm/proto.h>
-#include <asm/traps.h>
-#include <asm/desc.h>
+#include <linux/magic.h> /* STACK_END_MAGIC */
+#include <linux/sched.h> /* test_thread_flag(), ... */
+#include <linux/kdebug.h> /* oops_begin/end, ... */
+#include <linux/module.h> /* search_exception_table */
+#include <linux/bootmem.h> /* max_low_pfn */
+#include <linux/kprobes.h> /* __kprobes, ... */
+#include <linux/mmiotrace.h> /* kmmio_handler, ... */
+
+#include <asm/traps.h> /* dotraplinkage, ... */
+#include <asm/pgalloc.h> /* pgd_*(), ... */
/*
* Page fault error code bits:
if (!pmd_present(*pmd_k))
return NULL;
- if (!pmd_present(*pmd)) {
+ if (!pmd_present(*pmd))
set_pmd(pmd, *pmd_k);
- arch_flush_lazy_mmu_mode();
- } else {
+ else
BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
- }
return pmd_k;
}
static int is_errata93(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
- static int once;
-
if (address != regs->ip)
return 0;
address |= 0xffffffffUL << 32;
if ((address >= (u64)_stext && address <= (u64)_etext) ||
(address >= MODULES_VADDR && address <= MODULES_END)) {
- if (!once) {
- printk(errata93_warning);
- once = 1;
- }
+ printk_once(errata93_warning);
regs->ip = address;
return 1;
}
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
BUG_ON(!pte_none(*(kmap_pte-idx)));
set_pte(kmap_pte-idx, mk_pte(page, prot));
- arch_flush_lazy_mmu_mode();
return (void *)vaddr;
}
#endif
}
- arch_flush_lazy_mmu_mode();
pagefault_enable();
}
+#include <linux/initrd.h>
#include <linux/ioport.h>
#include <linux/swap.h>
#include <asm/setup.h>
#include <asm/system.h>
#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
unsigned long __initdata e820_table_start;
unsigned long __meminitdata e820_table_end;
#endif
;
+int nx_enabled;
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+static int disable_nx __cpuinitdata;
+
+/*
+ * noexec = on|off
+ *
+ * Control non-executable mappings for processes.
+ *
+ * on Enable
+ * off Disable
+ */
+static int __init noexec_setup(char *str)
+{
+ if (!str)
+ return -EINVAL;
+ if (!strncmp(str, "on", 2)) {
+ __supported_pte_mask |= _PAGE_NX;
+ disable_nx = 0;
+ } else if (!strncmp(str, "off", 3)) {
+ disable_nx = 1;
+ __supported_pte_mask &= ~_PAGE_NX;
+ }
+ return 0;
+}
+early_param("noexec", noexec_setup);
+#endif
+
+#ifdef CONFIG_X86_PAE
+static void __init set_nx(void)
+{
+ unsigned int v[4], l, h;
+
+ if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
+ cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
+
+ if ((v[3] & (1 << 20)) && !disable_nx) {
+ rdmsr(MSR_EFER, l, h);
+ l |= EFER_NX;
+ wrmsr(MSR_EFER, l, h);
+ nx_enabled = 1;
+ __supported_pte_mask |= _PAGE_NX;
+ }
+ }
+}
+#else
+static inline void set_nx(void)
+{
+}
+#endif
+
+#ifdef CONFIG_X86_64
+void __cpuinit check_efer(void)
+{
+ unsigned long efer;
+
+ rdmsrl(MSR_EFER, efer);
+ if (!(efer & EFER_NX) || disable_nx)
+ __supported_pte_mask &= ~_PAGE_NX;
+}
+#endif
+
static void __init find_early_table_space(unsigned long end, int use_pse,
int use_gbpages)
{
*/
#ifdef CONFIG_X86_32
start = 0x7000;
- e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
- tables, PAGE_SIZE);
-#else /* CONFIG_X86_64 */
+#else
start = 0x8000;
- e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE);
#endif
+ e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+ tables, PAGE_SIZE);
if (e820_table_start == -1UL)
panic("Cannot find space for the kernel page tables");
use_gbpages = direct_gbpages;
#endif
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_PAE
set_nx();
if (nx_enabled)
printk(KERN_INFO "NX (Execute Disable) protection: active\n");
-#endif
/* Enable PSE if available */
if (cpu_has_pse)
set_in_cr4(X86_CR4_PGE);
__supported_pte_mask |= _PAGE_GLOBAL;
}
-#endif
if (use_gbpages)
page_size_mask |= 1 << PG_LEVEL_1G;
#include <asm/paravirt.h>
#include <asm/setup.h>
#include <asm/cacheflush.h>
+#include <asm/page_types.h>
#include <asm/init.h>
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
unsigned long highstart_pfn, highend_pfn;
static noinline int do_test_wp_bit(void);
flush_tlb_all();
}
-int nx_enabled;
-
pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
EXPORT_SYMBOL_GPL(__supported_pte_mask);
-#ifdef CONFIG_X86_PAE
-
-static int disable_nx __initdata;
-
-/*
- * noexec = on|off
- *
- * Control non executable mappings.
- *
- * on Enable
- * off Disable
- */
-static int __init noexec_setup(char *str)
-{
- if (!str || !strcmp(str, "on")) {
- if (cpu_has_nx) {
- __supported_pte_mask |= _PAGE_NX;
- disable_nx = 0;
- }
- } else {
- if (!strcmp(str, "off")) {
- disable_nx = 1;
- __supported_pte_mask &= ~_PAGE_NX;
- } else {
- return -EINVAL;
- }
- }
-
- return 0;
-}
-early_param("noexec", noexec_setup);
-
-void __init set_nx(void)
-{
- unsigned int v[4], l, h;
-
- if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
- cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
-
- if ((v[3] & (1 << 20)) && !disable_nx) {
- rdmsr(MSR_EFER, l, h);
- l |= EFER_NX;
- wrmsr(MSR_EFER, l, h);
- nx_enabled = 1;
- __supported_pte_mask |= _PAGE_NX;
- }
- }
-}
-#endif
-
/* user-defined highmem size */
static unsigned int highmem_pages = -1;
highstart_pfn = highend_pfn = max_pfn;
if (max_pfn > max_low_pfn)
highstart_pfn = max_low_pfn;
- memory_present(0, 0, highend_pfn);
e820_register_active_regions(0, 0, highend_pfn);
+ sparse_memory_present_with_active_regions(0);
printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
pages_to_mb(highend_pfn - highstart_pfn));
num_physpages = highend_pfn;
high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
- memory_present(0, 0, max_low_pfn);
e820_register_active_regions(0, 0, max_low_pfn);
+ sparse_memory_present_with_active_regions(0);
num_physpages = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
#include <asm/cacheflush.h>
#include <asm/init.h>
-/*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
- */
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
static unsigned long dma_reserve __initdata;
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
static int __init parse_direct_gbpages_off(char *arg)
{
direct_gbpages = 0;
pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
-static int disable_nx __cpuinitdata;
-
-/*
- * noexec=on|off
- * Control non-executable mappings for 64-bit processes.
- *
- * on Enable (default)
- * off Disable
- */
-static int __init nonx_setup(char *str)
-{
- if (!str)
- return -EINVAL;
- if (!strncmp(str, "on", 2)) {
- __supported_pte_mask |= _PAGE_NX;
- disable_nx = 0;
- } else if (!strncmp(str, "off", 3)) {
- disable_nx = 1;
- __supported_pte_mask &= ~_PAGE_NX;
- }
- return 0;
-}
-early_param("noexec", nonx_setup);
-
-void __cpuinit check_efer(void)
-{
- unsigned long efer;
-
- rdmsrl(MSR_EFER, efer);
- if (!(efer & EFER_NX) || disable_nx)
- __supported_pte_mask &= ~_PAGE_NX;
-}
-
int force_personality32;
/*
early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
}
+#endif
void __init paging_init(void)
{
max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
max_zone_pfns[ZONE_NORMAL] = max_pfn;
- memory_present(0, 0, max_pfn);
+ sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
free_area_init_nodes(max_zone_pfns);
}
-#endif
/*
* Memory hotplug specific functions
if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
kpte_clear_flush(kmap_pte-idx, vaddr);
- arch_flush_lazy_mmu_mode();
pagefault_enable();
}
EXPORT_SYMBOL_GPL(iounmap_atomic);
struct list_head list;
struct kmmio_fault_page *release_next;
unsigned long page; /* location of the fault page */
- bool old_presence; /* page presence prior to arming */
+ pteval_t old_presence; /* page presence prior to arming */
bool armed;
/*
static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
{
struct list_head *head;
- struct kmmio_fault_page *p;
+ struct kmmio_fault_page *f;
page &= PAGE_MASK;
head = kmmio_page_list(page);
- list_for_each_entry_rcu(p, head, list) {
- if (p->page == page)
- return p;
+ list_for_each_entry_rcu(f, head, list) {
+ if (f->page == page)
+ return f;
}
return NULL;
}
-static void set_pmd_presence(pmd_t *pmd, bool present, bool *old)
+static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
{
pmdval_t v = pmd_val(*pmd);
- *old = !!(v & _PAGE_PRESENT);
- v &= ~_PAGE_PRESENT;
- if (present)
- v |= _PAGE_PRESENT;
+ if (clear) {
+ *old = v & _PAGE_PRESENT;
+ v &= ~_PAGE_PRESENT;
+ } else /* presume this has been called with clear==true previously */
+ v |= *old;
set_pmd(pmd, __pmd(v));
}
-static void set_pte_presence(pte_t *pte, bool present, bool *old)
+static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
{
pteval_t v = pte_val(*pte);
- *old = !!(v & _PAGE_PRESENT);
- v &= ~_PAGE_PRESENT;
- if (present)
- v |= _PAGE_PRESENT;
+ if (clear) {
+ *old = v & _PAGE_PRESENT;
+ v &= ~_PAGE_PRESENT;
+ } else /* presume this has been called with clear==true previously */
+ v |= *old;
set_pte_atomic(pte, __pte(v));
}
-static int set_page_presence(unsigned long addr, bool present, bool *old)
+static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
{
unsigned int level;
- pte_t *pte = lookup_address(addr, &level);
+ pte_t *pte = lookup_address(f->page, &level);
if (!pte) {
- pr_err("kmmio: no pte for page 0x%08lx\n", addr);
+ pr_err("kmmio: no pte for page 0x%08lx\n", f->page);
return -1;
}
switch (level) {
case PG_LEVEL_2M:
- set_pmd_presence((pmd_t *)pte, present, old);
+ clear_pmd_presence((pmd_t *)pte, clear, &f->old_presence);
break;
case PG_LEVEL_4K:
- set_pte_presence(pte, present, old);
+ clear_pte_presence(pte, clear, &f->old_presence);
break;
default:
pr_err("kmmio: unexpected page level 0x%x.\n", level);
return -1;
}
- __flush_tlb_one(addr);
+ __flush_tlb_one(f->page);
return 0;
}
WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n");
if (f->armed) {
pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n",
- f->page, f->count, f->old_presence);
+ f->page, f->count, !!f->old_presence);
}
- ret = set_page_presence(f->page, false, &f->old_presence);
+ ret = clear_page_presence(f, true);
WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page);
f->armed = true;
return ret;
/** Restore the given page to saved presence state. */
static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
{
- bool tmp;
- int ret = set_page_presence(f->page, f->old_presence, &tmp);
+ int ret = clear_page_presence(f, false);
WARN_ONCE(ret < 0,
KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
f->armed = false;
struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
if (!ctx->active) {
- pr_debug("kmmio: spurious debug trap on CPU %d.\n",
+ /*
+ * debug traps without an active context are due to either
+ * something external causing them (f.e. using a debugger while
+ * mmio tracing enabled), or erroneous behaviour
+ */
+ pr_warning("kmmio: unexpected debug trap on CPU %d.\n",
smp_processor_id());
goto out;
}
head,
struct kmmio_delayed_release,
rcu);
- struct kmmio_fault_page *p = dr->release_list;
- while (p) {
- struct kmmio_fault_page *next = p->release_next;
- BUG_ON(p->count);
- kfree(p);
- p = next;
+ struct kmmio_fault_page *f = dr->release_list;
+ while (f) {
+ struct kmmio_fault_page *next = f->release_next;
+ BUG_ON(f->count);
+ kfree(f);
+ f = next;
}
kfree(dr);
}
{
struct kmmio_delayed_release *dr =
container_of(head, struct kmmio_delayed_release, rcu);
- struct kmmio_fault_page *p = dr->release_list;
+ struct kmmio_fault_page *f = dr->release_list;
struct kmmio_fault_page **prevp = &dr->release_list;
unsigned long flags;
spin_lock_irqsave(&kmmio_lock, flags);
- while (p) {
- if (!p->count) {
- list_del_rcu(&p->list);
- prevp = &p->release_next;
+ while (f) {
+ if (!f->count) {
+ list_del_rcu(&f->list);
+ prevp = &f->release_next;
} else {
- *prevp = p->release_next;
+ *prevp = f->release_next;
}
- p = p->release_next;
+ f = f->release_next;
}
spin_unlock_irqrestore(&kmmio_lock, flags);
}
EXPORT_SYMBOL(unregister_kmmio_probe);
-static int kmmio_die_notifier(struct notifier_block *nb, unsigned long val,
- void *args)
+static int
+kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
{
struct die_args *arg = args;
.notifier_call = kmmio_die_notifier
};
-static int __init init_kmmio(void)
+int kmmio_init(void)
{
int i;
+
for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++)
INIT_LIST_HEAD(&kmmio_page_table[i]);
+
return register_die_notifier(&nb_die);
}
-fs_initcall(init_kmmio); /* should be before device_initcall() */
+
+void kmmio_cleanup(void)
+{
+ int i;
+
+ unregister_die_notifier(&nb_die);
+ for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++) {
+ WARN_ONCE(!list_empty(&kmmio_page_table[i]),
+ KERN_ERR "kmmio_page_table not empty at cleanup, any further tracing will leak memory.\n");
+ }
+}
static void __init memtest(u64 pattern, u64 start_phys, u64 size)
{
- u64 i, count;
- u64 *start;
+ u64 *p;
+ void *start, *end;
u64 start_bad, last_bad;
u64 start_phys_aligned;
size_t incr;
incr = sizeof(pattern);
start_phys_aligned = ALIGN(start_phys, incr);
- count = (size - (start_phys_aligned - start_phys))/incr;
start = __va(start_phys_aligned);
+ end = start + size - (start_phys_aligned - start_phys);
start_bad = 0;
last_bad = 0;
- for (i = 0; i < count; i++)
- start[i] = pattern;
- for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
- if (*start == pattern)
+ for (p = start; p < end; p++)
+ *p = pattern;
+ for (p = start; p < end; p++, start_phys_aligned += incr) {
+ if (*p == pattern)
continue;
if (start_phys_aligned == last_bad + incr) {
last_bad += incr;
if (nommiotrace)
pr_info(NAME "MMIO tracing disabled.\n");
+ kmmio_init();
enter_uniprocessor();
spin_lock_irq(&trace_lock);
atomic_inc(&mmiotrace_enabled);
clear_trace_list(); /* guarantees: no more kmmio callbacks */
leave_uniprocessor();
+ kmmio_cleanup();
pr_info(NAME "disabled.\n");
out:
mutex_unlock(&mmiotrace_mutex);
}
/* Initialize bootmem allocator for a node */
-void __init setup_node_bootmem(int nodeid, unsigned long start,
- unsigned long end)
+void __init
+setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
{
unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+ const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
unsigned long bootmap_start, nodedata_phys;
void *bootmap;
- const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
int nid;
if (!end)
return;
+ /*
+ * Don't confuse VM with a node that doesn't have the
+ * minimum amount of memory:
+ */
+ if (end && (end - start) < NODE_MIN_SIZE)
+ return;
+
start = roundup(start, ZONE_ALIGN);
printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
-#ifdef CONFIG_ACPI_NUMA
- srat_reserve_add_area(nodeid);
-#endif
node_set_online(nodeid);
}
return pages;
}
-void __init paging_init(void)
-{
- unsigned long max_zone_pfns[MAX_NR_ZONES];
-
- memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
- max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
- max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
- max_zone_pfns[ZONE_NORMAL] = max_pfn;
-
- sparse_memory_present_with_active_regions(MAX_NUMNODES);
- sparse_init();
-
- free_area_init_nodes(max_zone_pfns);
-}
-
static __init int numa_setup(char *opt)
{
if (!opt)
#ifdef CONFIG_ACPI_NUMA
if (!strncmp(opt, "noacpi", 6))
acpi_numa = -1;
- if (!strncmp(opt, "hotadd=", 7))
- hotadd_percent = simple_strtoul(opt+7, NULL, 10);
#endif
return 0;
}
vm_unmap_aliases();
- /*
- * If we're called with lazy mmu updates enabled, the
- * in-memory pte state may be stale. Flush pending updates to
- * bring them up to date.
- */
- arch_flush_lazy_mmu_mode();
-
cpa.vaddr = addr;
cpa.pages = pages;
cpa.numpages = numpages;
} else
cpa_flush_all(cache);
- /*
- * If we've been called with lazy mmu updates enabled, then
- * make sure that everything gets flushed out before we
- * return.
- */
- arch_flush_lazy_mmu_mode();
-
out:
return ret;
}
static nodemask_t cpu_nodes_parsed __initdata;
static struct bootnode nodes[MAX_NUMNODES] __initdata;
static struct bootnode nodes_add[MAX_NUMNODES];
-static int found_add_area __initdata;
-int hotadd_percent __initdata = 0;
static int num_node_memblks __initdata;
static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;
-/* Too small nodes confuse the VM badly. Usually they result
- from BIOS bugs. */
-#define NODE_MIN_SIZE (4*1024*1024)
-
static __init int setup_node(int pxm)
{
return acpi_map_pxm_to_node(pxm);
{
struct bootnode *nd = &nodes[i];
- if (found_add_area)
- return;
-
if (nd->start < start) {
nd->start = start;
if (nd->end < nd->start)
int i;
printk(KERN_ERR "SRAT: SRAT not used.\n");
acpi_numa = -1;
- found_add_area = 0;
for (i = 0; i < MAX_LOCAL_APIC; i++)
apicid_to_node[i] = NUMA_NO_NODE;
for (i = 0; i < MAX_NUMNODES; i++)
pxm, apic_id, node);
}
-static int update_end_of_memory(unsigned long end) {return -1;}
-static int hotadd_enough_memory(struct bootnode *nd) {return 1;}
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
static inline int save_add_info(void) {return 1;}
#else
static inline int save_add_info(void) {return 0;}
#endif
/*
- * Update nodes_add and decide if to include add are in the zone.
- * Both SPARSE and RESERVE need nodes_add information.
- * This code supports one contiguous hot add area per node.
+ * Update nodes_add[]
+ * This code supports one contiguous hot add area per node
*/
-static int __init
-reserve_hotadd(int node, unsigned long start, unsigned long end)
+static void __init
+update_nodes_add(int node, unsigned long start, unsigned long end)
{
unsigned long s_pfn = start >> PAGE_SHIFT;
unsigned long e_pfn = end >> PAGE_SHIFT;
- int ret = 0, changed = 0;
+ int changed = 0;
struct bootnode *nd = &nodes_add[node];
/* I had some trouble with strange memory hotadd regions breaking
mistakes */
if ((signed long)(end - start) < NODE_MIN_SIZE) {
printk(KERN_ERR "SRAT: Hotplug area too small\n");
- return -1;
+ return;
}
/* This check might be a bit too strict, but I'm keeping it for now. */
printk(KERN_ERR
"SRAT: Hotplug area %lu -> %lu has existing memory\n",
s_pfn, e_pfn);
- return -1;
- }
-
- if (!hotadd_enough_memory(&nodes_add[node])) {
- printk(KERN_ERR "SRAT: Hotplug area too large\n");
- return -1;
+ return;
}
/* Looks good */
printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
}
- ret = update_end_of_memory(nd->end);
-
if (changed)
- printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end);
- return ret;
+ printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n",
+ nd->start, nd->end);
}
/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
start, end);
e820_register_active_regions(node, start >> PAGE_SHIFT,
end >> PAGE_SHIFT);
- push_node_boundaries(node, nd->start >> PAGE_SHIFT,
- nd->end >> PAGE_SHIFT);
- if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) &&
- (reserve_hotadd(node, start, end) < 0)) {
- /* Ignore hotadd region. Undo damage */
- printk(KERN_NOTICE "SRAT: Hotplug region ignored\n");
+ if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) {
+ update_nodes_add(node, start, end);
+ /* restore nodes[node] */
*nd = oldnode;
if ((nd->start | nd->end) == 0)
node_clear(node, nodes_parsed);
pxmram = 0;
}
- e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
- /* We seem to lose 3 pages somewhere. Allow a bit of slack. */
- if ((long)(e820ram - pxmram) >= 1*1024*1024) {
+ e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+ /* We seem to lose 3 pages somewhere. Allow 1M of slack. */
+ if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
printk(KERN_ERR
"SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n",
(pxmram << PAGE_SHIFT) >> 20,
return 1;
}
-static void __init unparse_node(int node)
-{
- int i;
- node_clear(node, nodes_parsed);
- node_clear(node, cpu_nodes_parsed);
- for (i = 0; i < MAX_LOCAL_APIC; i++) {
- if (apicid_to_node[i] == node)
- apicid_to_node[i] = NUMA_NO_NODE;
- }
-}
-
void __init acpi_numa_arch_fixup(void) {}
/* Use the information discovered above to actually set up the nodes. */
return -1;
/* First clean up the node list */
- for (i = 0; i < MAX_NUMNODES; i++) {
+ for (i = 0; i < MAX_NUMNODES; i++)
cutoff_node(i, start, end);
- /*
- * don't confuse VM with a node that doesn't have the
- * minimum memory.
- */
- if (nodes[i].end &&
- (nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) {
- unparse_node(i);
- node_set_offline(i);
- }
- }
if (!nodes_cover_memory(nodes)) {
bad_srat();
if (node == NUMA_NO_NODE)
continue;
- if (!node_isset(node, node_possible_map))
+ if (!node_online(node))
numa_clear_node(i);
}
numa_init_array();
}
#endif /* CONFIG_NUMA_EMU */
-void __init srat_reserve_add_area(int nodeid)
-{
- if (found_add_area && nodes_add[nodeid].end) {
- u64 total_mb;
-
- printk(KERN_INFO "SRAT: Reserving hot-add memory space "
- "for node %d at %Lx-%Lx\n",
- nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end);
- total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start)
- >> PAGE_SHIFT;
- total_mb *= sizeof(struct page);
- total_mb >>= 20;
- printk(KERN_INFO "SRAT: This will cost you %Lu MB of "
- "pre-allocated memory.\n", (unsigned long long)total_mb);
- reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start,
- nodes_add[nodeid].end - nodes_add[nodeid].start,
- BOOTMEM_DEFAULT);
- }
-}
-
int __node_distance(int a, int b)
{
int index;
#define exit_sysfs() do { } while (0)
#endif /* CONFIG_PM */
-static int p4force;
-module_param(p4force, int, 0);
-
static int __init p4_init(char **cpu_type)
{
__u8 cpu_model = boot_cpu_data.x86_model;
- if (!p4force && (cpu_model > 6 || cpu_model == 5))
+ if (cpu_model > 6 || cpu_model == 5)
return 0;
#ifndef CONFIG_SMP
return 0;
}
+static int force_arch_perfmon;
+static int force_cpu_type(const char *str, struct kernel_param *kp)
+{
+ if (!strcmp(str, "archperfmon")) {
+ force_arch_perfmon = 1;
+ printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
+ }
+
+ return 0;
+}
+module_param_call(cpu_type, force_cpu_type, NULL, NULL, 0);
+
static int __init ppro_init(char **cpu_type)
{
__u8 cpu_model = boot_cpu_data.x86_model;
+ if (force_arch_perfmon && cpu_has_arch_perfmon)
+ return 0;
+
switch (cpu_model) {
case 0 ... 2:
*cpu_type = "i386/ppro";
case 15: case 23:
*cpu_type = "i386/core_2";
break;
+ case 26:
+ arch_perfmon_setup_counters();
+ *cpu_type = "i386/core_i7";
+ break;
+ case 28:
+ *cpu_type = "i386/atom";
+ break;
default:
/* Unknown */
return 0;
return 0;
}
+ if (io_apic_assign_pci_irqs)
+ return 0;
+
/* Find IRQ routing entry */
if (!pirq_table)
pirq_penalty[dev->irq]++;
}
+ if (io_apic_assign_pci_irqs)
+ return;
+
dev = NULL;
while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
if (!pin)
continue;
-#ifdef CONFIG_X86_IO_APIC
- /*
- * Recalculate IRQ numbers if we use the I/O APIC.
- */
- if (io_apic_assign_pci_irqs) {
- int irq;
-
- /*
- * interrupt pins are numbered starting from 1
- */
- irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
- PCI_SLOT(dev->devfn), pin - 1);
- /*
- * Busses behind bridges are typically not listed in the
- * MP-table. In this case we have to look up the IRQ
- * based on the parent bus, parent slot, and pin number.
- * The SMP code detects such bridged busses itself so we
- * should get into this branch reliably.
- */
- if (irq < 0 && dev->bus->parent) {
- /* go back to the bridge */
- struct pci_dev *bridge = dev->bus->self;
- int bus;
-
- pin = pci_swizzle_interrupt_pin(dev, pin);
- bus = bridge->bus->number;
- irq = IO_APIC_get_PCI_irq_vector(bus,
- PCI_SLOT(bridge->devfn), pin - 1);
- if (irq >= 0)
- dev_warn(&dev->dev,
- "using bridge %s INT %c to "
- "get IRQ %d\n",
- pci_name(bridge),
- 'A' + pin - 1, irq);
- }
- if (irq >= 0) {
- dev_info(&dev->dev,
- "PCI->APIC IRQ transform: INT %c "
- "-> IRQ %d\n",
- 'A' + pin - 1, irq);
- dev->irq = irq;
- }
- }
-#endif
/*
* Still no IRQ? Try to lookup one...
*/
pcibios_enable_irq = pirq_enable_irq;
pcibios_fixup_irqs();
+
+ if (io_apic_assign_pci_irqs && pci_routeirq) {
+ struct pci_dev *dev = NULL;
+ /*
+ * PCI IRQ routing is set up by pci_enable_device(), but we
+ * also do it here in case there are still broken drivers that
+ * don't use pci_enable_device().
+ */
+ printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
+ for_each_pci_dev(dev)
+ pirq_enable_irq(dev);
+ }
+
return 0;
}
static int pirq_enable_irq(struct pci_dev *dev)
{
u8 pin;
- struct pci_dev *temp_dev;
pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
- if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) {
+ if (pin && !pcibios_lookup_irq(dev, 1)) {
char *msg = "";
+ if (!io_apic_assign_pci_irqs && dev->irq)
+ return 0;
+
if (io_apic_assign_pci_irqs) {
+#ifdef CONFIG_X86_IO_APIC
+ struct pci_dev *temp_dev;
int irq;
+ struct io_apic_irq_attr irq_attr;
- irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin - 1);
+ irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
+ PCI_SLOT(dev->devfn),
+ pin - 1, &irq_attr);
/*
* Busses behind bridges are typically not listed in the MP-table.
* In this case we have to look up the IRQ based on the parent bus,
pin = pci_swizzle_interrupt_pin(dev, pin);
irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
- PCI_SLOT(bridge->devfn), pin - 1);
+ PCI_SLOT(bridge->devfn),
+ pin - 1, &irq_attr);
if (irq >= 0)
dev_warn(&dev->dev, "using bridge %s "
"INT %c to get IRQ %d\n",
}
dev = temp_dev;
if (irq >= 0) {
+ io_apic_set_pci_routing(&dev->dev, irq,
+ &irq_attr);
+ dev->irq = irq;
dev_info(&dev->dev, "PCI->APIC IRQ transform: "
"INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
- dev->irq = irq;
return 0;
} else
msg = "; probably buggy MP table";
+#endif
} else if (pci_probe & PCI_BIOS_IRQ_SCAN)
msg = "";
else
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/random.h>
+#include <linux/elf.h>
#include <asm/vsyscall.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <linux/delay.h>
#include <linux/start_kernel.h>
#include <linux/sched.h>
+#include <linux/kprobes.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <asm/processor.h>
#include <asm/proto.h>
#include <asm/msr-index.h>
+#include <asm/traps.h>
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
return HYPERVISOR_get_debugreg(reg);
}
-void xen_leave_lazy(void)
+static void xen_end_context_switch(struct task_struct *next)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
xen_mc_flush();
+ paravirt_end_context_switch(next);
}
static unsigned long xen_store_tr(void)
static int cvt_gate_to_trap(int vector, const gate_desc *val,
struct trap_info *info)
{
+ unsigned long addr;
+
if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
return 0;
info->vector = vector;
- info->address = gate_offset(*val);
+
+ addr = gate_offset(*val);
+#ifdef CONFIG_X86_64
+ /*
+ * Look for known traps using IST, and substitute them
+ * appropriately. The debugger ones are the only ones we care
+ * about. Xen will handle faults like double_fault and
+ * machine_check, so we should never see them. Warn if
+ * there's an unexpected IST-using fault handler.
+ */
+ if (addr == (unsigned long)debug)
+ addr = (unsigned long)xen_debug;
+ else if (addr == (unsigned long)int3)
+ addr = (unsigned long)xen_int3;
+ else if (addr == (unsigned long)stack_segment)
+ addr = (unsigned long)xen_stack_segment;
+ else if (addr == (unsigned long)double_fault ||
+ addr == (unsigned long)nmi) {
+ /* Don't need to handle these */
+ return 0;
+#ifdef CONFIG_X86_MCE
+ } else if (addr == (unsigned long)machine_check) {
+ return 0;
+#endif
+ } else {
+ /* Some other trap using IST? */
+ if (WARN_ON(val->ist != 0))
+ return 0;
+ }
+#endif /* CONFIG_X86_64 */
+ info->address = addr;
+
info->cs = gate_segment(*val);
info->flags = val->dpl;
/* interrupt gates clear IF */
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+ unsigned long cr0 = percpu_read(xen_cr0_value);
+
+ if (unlikely(cr0 == 0)) {
+ cr0 = native_read_cr0();
+ percpu_write(xen_cr0_value, cr0);
+ }
+
+ return cr0;
+}
+
static void xen_write_cr0(unsigned long cr0)
{
struct multicall_space mcs;
+ percpu_write(xen_cr0_value, cr0);
+
/* Only pay attention to cr0.TS; everything else is
ignored. */
mcs = xen_mc_entry(0);
.clts = xen_clts,
- .read_cr0 = native_read_cr0,
+ .read_cr0 = xen_read_cr0,
.write_cr0 = xen_write_cr0,
.read_cr4 = native_read_cr4,
/* Xen takes care of %gs when switching to usermode for us */
.swapgs = paravirt_nop,
- .lazy_mode = {
- .enter = paravirt_enter_lazy_cpu,
- .leave = xen_leave_lazy,
- },
+ .start_context_switch = paravirt_start_context_switch,
+ .end_context_switch = xen_end_context_switch,
};
static const struct pv_apic_ops xen_apic_ops __initdata = {
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
- /* updates to init_mm may be done without lock */
- if (mm == &init_mm)
- preempt_disable();
-
ADD_STATS(set_pte_at, 1);
// ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
ADD_STATS(set_pte_at_current, mm == current->mm);
}
xen_set_pte(ptep, pteval);
-out:
- if (mm == &init_mm)
- preempt_enable();
+out: return;
}
pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
/* If this cpu still has a stale cr3 reference, then make sure
it has been flushed. */
- if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
+ if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
load_cr3(swapper_pg_dir);
- arch_flush_lazy_cpu_mode();
- }
}
static void xen_drop_mm_ref(struct mm_struct *mm)
load_cr3(swapper_pg_dir);
else
leave_mm(smp_processor_id());
- arch_flush_lazy_cpu_mode();
}
/* Get the "official" set of cpus referring to our pagetable. */
xen_mark_init_mm_pinned();
}
+static void xen_leave_lazy_mmu(void)
+{
+ preempt_disable();
+ xen_mc_flush();
+ paravirt_leave_lazy_mmu();
+ preempt_enable();
+}
+
const struct pv_mmu_ops xen_mmu_ops __initdata = {
.pagetable_setup_start = xen_pagetable_setup_start,
.pagetable_setup_done = xen_pagetable_setup_done,
.lazy_mode = {
.enter = paravirt_enter_lazy_mmu,
- .leave = xen_leave_lazy,
+ .leave = xen_leave_lazy_mmu,
},
.set_fixmap = xen_set_fixmap,
* - xen_start_info
* See comment above "struct start_info" in <xen/interface/xen.h>
*/
- e820_add_region(__pa(xen_start_info->mfn_list),
- xen_start_info->pt_base - xen_start_info->mfn_list,
- E820_RESERVED);
+ reserve_early(__pa(xen_start_info->mfn_list),
+ __pa(xen_start_info->pt_base),
+ "XEN START INFO");
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
void xen_ident_map_ISA(void);
void xen_reserve_top(void);
-void xen_leave_lazy(void);
void xen_post_allocator_init(void);
char * __init xen_memory_setup(void);
#include <linux/task_io_accounting_ops.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
-#include <trace/block.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/block.h>
#include "blk.h"
-DEFINE_TRACE(block_plug);
-DEFINE_TRACE(block_unplug_io);
-DEFINE_TRACE(block_unplug_timer);
-DEFINE_TRACE(block_getrq);
-DEFINE_TRACE(block_sleeprq);
-DEFINE_TRACE(block_rq_requeue);
-DEFINE_TRACE(block_bio_backmerge);
-DEFINE_TRACE(block_bio_frontmerge);
-DEFINE_TRACE(block_bio_queue);
-DEFINE_TRACE(block_rq_complete);
-DEFINE_TRACE(block_remap); /* Also used in drivers/md/dm.c */
EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
static int __make_request(struct request_queue *q, struct bio *bio);
bio->bi_bdev = bdev->bd_contains;
trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
- bdev->bd_dev, bio->bi_sector,
+ bdev->bd_dev,
bio->bi_sector - p->start_sect);
}
}
goto end_io;
if (old_sector != -1)
- trace_block_remap(q, bio, old_dev, bio->bi_sector,
- old_sector);
+ trace_block_remap(q, bio, old_dev, old_sector);
trace_block_bio_queue(q, bio);
trace_block_rq_complete(req->q, req);
/*
- * for a REQ_TYPE_BLOCK_PC request, we want to carry any eventual
- * sense key with us all the way through
+ * For fs requests, rq is just carrier of independent bio's
+ * and each partial completion should be handled separately.
+ * Reset per-request error on each partial completion.
+ *
+ * TODO: tj: This is too subtle. It would be better to let
+ * low level drivers do what they see fit.
*/
- if (!blk_pc_request(req))
+ if (blk_fs_request(req))
req->errors = 0;
if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) {
int blk_register_queue(struct gendisk *disk)
{
int ret;
+ struct device *dev = disk_to_dev(disk);
struct request_queue *q = disk->queue;
if (WARN_ON(!q))
return -ENXIO;
+ ret = blk_trace_init_sysfs(dev);
+ if (ret)
+ return ret;
+
if (!q->request_fn)
return 0;
- ret = kobject_add(&q->kobj, kobject_get(&disk_to_dev(disk)->kobj),
+ ret = kobject_add(&q->kobj, kobject_get(&dev->kobj),
"%s", "queue");
if (ret < 0)
return ret;
memcpy(&buts.name, &cbuts.name, 32);
mutex_lock(&bdev->bd_mutex);
- ret = do_blk_trace_setup(q, b, bdev->bd_dev, &buts);
+ ret = do_blk_trace_setup(q, b, bdev->bd_dev, bdev, &buts);
mutex_unlock(&bdev->bd_mutex);
if (ret)
return ret;
#include <linux/compiler.h>
#include <linux/delay.h>
#include <linux/blktrace_api.h>
-#include <trace/block.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
+#include <trace/events/block.h>
+
#include "blk.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
-DEFINE_TRACE(block_rq_abort);
-
/*
* Merge hash stuff.
*/
#define rq_hash_key(rq) ((rq)->sector + (rq)->nr_sectors)
#define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash))
-DEFINE_TRACE(block_rq_insert);
-DEFINE_TRACE(block_rq_issue);
-
/*
* Query io scheduler to see if the current process issuing bio may be
* merged with rq.
/* Interrupt Line values above 0xF are forbidden */
if (dev->irq > 0 && (dev->irq <= 0xF)) {
printk(" - using IRQ %d\n", dev->irq);
- acpi_register_gsi(dev->irq, ACPI_LEVEL_SENSITIVE,
+ acpi_register_gsi(&dev->dev, dev->irq,
+ ACPI_LEVEL_SENSITIVE,
ACPI_ACTIVE_LOW);
return 0;
} else {
}
}
- rc = acpi_register_gsi(gsi, triggering, polarity);
+ rc = acpi_register_gsi(&dev->dev, gsi, triggering, polarity);
if (rc < 0) {
dev_warn(&dev->dev, "PCI INT %c: failed to register GSI\n",
pin_name(pin));
/* FIXME: why is this needed. Note don't use ldisc_ref here as the
open path is before the ldisc is referencable */
- if (tty->ldisc.ops->flush_buffer)
- tty->ldisc.ops->flush_buffer(tty);
+ if (tty->ldisc->ops->flush_buffer)
+ tty->ldisc->ops->flush_buffer(tty);
tty_driver_flush_buffer(tty);
return 0;
clear_bit(HCI_UART_PROTO_SET, &hu->flags);
return err;
}
- tty->low_latency = 1;
} else
return -EBUSY;
break;
kind of kernel debugging operations.
When in doubt, say "N".
+config BFIN_JTAG_COMM
+ tristate "Blackfin JTAG Communication"
+ depends on BLACKFIN
+ help
+ Add support for emulating a TTY device over the Blackfin JTAG.
+
+ To compile this driver as a module, choose M here: the
+ module will be called bfin_jtag_comm.
+
+config BFIN_JTAG_COMM_CONSOLE
+ bool "Console on Blackfin JTAG"
+ depends on BFIN_JTAG_COMM=y
+
config SERIAL_NONSTANDARD
bool "Non-standard serial port support"
depends on HAS_IOMEM
obj-$(CONFIG_UNIX98_PTYS) += pty.o
obj-y += misc.o
obj-$(CONFIG_VT) += vt_ioctl.o vc_screen.o selection.o keyboard.o
+obj-$(CONFIG_BFIN_JTAG_COMM) += bfin_jtag_comm.o
obj-$(CONFIG_CONSOLE_TRANSLATIONS) += consolemap.o consolemap_deftbl.o
obj-$(CONFIG_HW_CONSOLE) += vt.o defkeymap.o
obj-$(CONFIG_AUDIT) += tty_audit.o
--- /dev/null
+/*
+ * TTY over Blackfin JTAG Communication
+ *
+ * Copyright 2008-2009 Analog Devices Inc.
+ *
+ * Enter bugs at http://blackfin.uclinux.org/
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/circ_buf.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <asm/atomic.h>
+
+/* See the Debug/Emulation chapter in the HRM */
+#define EMUDOF 0x00000001 /* EMUDAT_OUT full & valid */
+#define EMUDIF 0x00000002 /* EMUDAT_IN full & valid */
+#define EMUDOOVF 0x00000004 /* EMUDAT_OUT overflow */
+#define EMUDIOVF 0x00000008 /* EMUDAT_IN overflow */
+
+#define DRV_NAME "bfin-jtag-comm"
+#define DEV_NAME "ttyBFJC"
+
+#define pr_init(fmt, args...) ({ static const __initdata char __fmt[] = fmt; printk(__fmt, ## args); })
+#define debug(fmt, args...) pr_debug(DRV_NAME ": " fmt, ## args)
+
+static inline uint32_t bfin_write_emudat(uint32_t emudat)
+{
+ __asm__ __volatile__("emudat = %0;" : : "d"(emudat));
+ return emudat;
+}
+
+static inline uint32_t bfin_read_emudat(void)
+{
+ uint32_t emudat;
+ __asm__ __volatile__("%0 = emudat;" : "=d"(emudat));
+ return emudat;
+}
+
+static inline uint32_t bfin_write_emudat_chars(char a, char b, char c, char d)
+{
+ return bfin_write_emudat((a << 0) | (b << 8) | (c << 16) | (d << 24));
+}
+
+#define CIRC_SIZE 2048 /* see comment in tty_io.c:do_tty_write() */
+#define CIRC_MASK (CIRC_SIZE - 1)
+#define circ_empty(circ) ((circ)->head == (circ)->tail)
+#define circ_free(circ) CIRC_SPACE((circ)->head, (circ)->tail, CIRC_SIZE)
+#define circ_cnt(circ) CIRC_CNT((circ)->head, (circ)->tail, CIRC_SIZE)
+#define circ_byte(circ, idx) ((circ)->buf[(idx) & CIRC_MASK])
+
+static struct tty_driver *bfin_jc_driver;
+static struct task_struct *bfin_jc_kthread;
+static struct tty_struct * volatile bfin_jc_tty;
+static unsigned long bfin_jc_count;
+static DEFINE_MUTEX(bfin_jc_tty_mutex);
+static volatile struct circ_buf bfin_jc_write_buf;
+
+static int
+bfin_jc_emudat_manager(void *arg)
+{
+ uint32_t inbound_len = 0, outbound_len = 0;
+
+ while (!kthread_should_stop()) {
+ /* no one left to give data to, so sleep */
+ if (bfin_jc_tty == NULL && circ_empty(&bfin_jc_write_buf)) {
+ debug("waiting for readers\n");
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+
+ /* no data available, so just chill */
+ if (!(bfin_read_DBGSTAT() & EMUDIF) && circ_empty(&bfin_jc_write_buf)) {
+ debug("waiting for data (in_len = %i) (circ: %i %i)\n",
+ inbound_len, bfin_jc_write_buf.tail, bfin_jc_write_buf.head);
+ if (inbound_len)
+ schedule();
+ else
+ schedule_timeout_interruptible(HZ);
+ continue;
+ }
+
+ /* if incoming data is ready, eat it */
+ if (bfin_read_DBGSTAT() & EMUDIF) {
+ struct tty_struct *tty;
+ mutex_lock(&bfin_jc_tty_mutex);
+ tty = (struct tty_struct *)bfin_jc_tty;
+ if (tty != NULL) {
+ uint32_t emudat = bfin_read_emudat();
+ if (inbound_len == 0) {
+ debug("incoming length: 0x%08x\n", emudat);
+ inbound_len = emudat;
+ } else {
+ size_t num_chars = (4 <= inbound_len ? 4 : inbound_len);
+ debug(" incoming data: 0x%08x (pushing %zu)\n", emudat, num_chars);
+ inbound_len -= num_chars;
+ tty_insert_flip_string(tty, (unsigned char *)&emudat, num_chars);
+ tty_flip_buffer_push(tty);
+ }
+ }
+ mutex_unlock(&bfin_jc_tty_mutex);
+ }
+
+ /* if outgoing data is ready, post it */
+ if (!(bfin_read_DBGSTAT() & EMUDOF) && !circ_empty(&bfin_jc_write_buf)) {
+ if (outbound_len == 0) {
+ outbound_len = circ_cnt(&bfin_jc_write_buf);
+ bfin_write_emudat(outbound_len);
+ debug("outgoing length: 0x%08x\n", outbound_len);
+ } else {
+ struct tty_struct *tty;
+ int tail = bfin_jc_write_buf.tail;
+ size_t ate = (4 <= outbound_len ? 4 : outbound_len);
+ uint32_t emudat =
+ bfin_write_emudat_chars(
+ circ_byte(&bfin_jc_write_buf, tail + 0),
+ circ_byte(&bfin_jc_write_buf, tail + 1),
+ circ_byte(&bfin_jc_write_buf, tail + 2),
+ circ_byte(&bfin_jc_write_buf, tail + 3)
+ );
+ bfin_jc_write_buf.tail += ate;
+ outbound_len -= ate;
+ mutex_lock(&bfin_jc_tty_mutex);
+ tty = (struct tty_struct *)bfin_jc_tty;
+ if (tty)
+ tty_wakeup(tty);
+ mutex_unlock(&bfin_jc_tty_mutex);
+ debug(" outgoing data: 0x%08x (pushing %zu)\n", emudat, ate);
+ }
+ }
+ }
+
+ __set_current_state(TASK_RUNNING);
+ return 0;
+}
+
+static int
+bfin_jc_open(struct tty_struct *tty, struct file *filp)
+{
+ mutex_lock(&bfin_jc_tty_mutex);
+ debug("open %lu\n", bfin_jc_count);
+ ++bfin_jc_count;
+ bfin_jc_tty = tty;
+ wake_up_process(bfin_jc_kthread);
+ mutex_unlock(&bfin_jc_tty_mutex);
+ return 0;
+}
+
+static void
+bfin_jc_close(struct tty_struct *tty, struct file *filp)
+{
+ mutex_lock(&bfin_jc_tty_mutex);
+ debug("close %lu\n", bfin_jc_count);
+ if (--bfin_jc_count == 0)
+ bfin_jc_tty = NULL;
+ wake_up_process(bfin_jc_kthread);
+ mutex_unlock(&bfin_jc_tty_mutex);
+}
+
+/* XXX: we dont handle the put_char() case where we must handle count = 1 */
+static int
+bfin_jc_circ_write(const unsigned char *buf, int count)
+{
+ int i;
+ count = min(count, circ_free(&bfin_jc_write_buf));
+ debug("going to write chunk of %i bytes\n", count);
+ for (i = 0; i < count; ++i)
+ circ_byte(&bfin_jc_write_buf, bfin_jc_write_buf.head + i) = buf[i];
+ bfin_jc_write_buf.head += i;
+ return i;
+}
+
+#ifndef CONFIG_BFIN_JTAG_COMM_CONSOLE
+# define acquire_console_sem()
+# define release_console_sem()
+#endif
+static int
+bfin_jc_write(struct tty_struct *tty, const unsigned char *buf, int count)
+{
+ int i;
+ acquire_console_sem();
+ i = bfin_jc_circ_write(buf, count);
+ release_console_sem();
+ wake_up_process(bfin_jc_kthread);
+ return i;
+}
+
+static void
+bfin_jc_flush_chars(struct tty_struct *tty)
+{
+ wake_up_process(bfin_jc_kthread);
+}
+
+static int
+bfin_jc_write_room(struct tty_struct *tty)
+{
+ return circ_free(&bfin_jc_write_buf);
+}
+
+static int
+bfin_jc_chars_in_buffer(struct tty_struct *tty)
+{
+ return circ_cnt(&bfin_jc_write_buf);
+}
+
+static void
+bfin_jc_wait_until_sent(struct tty_struct *tty, int timeout)
+{
+ unsigned long expire = jiffies + timeout;
+ while (!circ_empty(&bfin_jc_write_buf)) {
+ if (signal_pending(current))
+ break;
+ if (time_after(jiffies, expire))
+ break;
+ }
+}
+
+static struct tty_operations bfin_jc_ops = {
+ .open = bfin_jc_open,
+ .close = bfin_jc_close,
+ .write = bfin_jc_write,
+ /*.put_char = bfin_jc_put_char,*/
+ .flush_chars = bfin_jc_flush_chars,
+ .write_room = bfin_jc_write_room,
+ .chars_in_buffer = bfin_jc_chars_in_buffer,
+ .wait_until_sent = bfin_jc_wait_until_sent,
+};
+
+static int __init bfin_jc_init(void)
+{
+ int ret;
+
+ bfin_jc_kthread = kthread_create(bfin_jc_emudat_manager, NULL, DRV_NAME);
+ if (IS_ERR(bfin_jc_kthread))
+ return PTR_ERR(bfin_jc_kthread);
+
+ ret = -ENOMEM;
+
+ bfin_jc_write_buf.head = bfin_jc_write_buf.tail = 0;
+ bfin_jc_write_buf.buf = kmalloc(CIRC_SIZE, GFP_KERNEL);
+ if (!bfin_jc_write_buf.buf)
+ goto err;
+
+ bfin_jc_driver = alloc_tty_driver(1);
+ if (!bfin_jc_driver)
+ goto err;
+
+ bfin_jc_driver->owner = THIS_MODULE;
+ bfin_jc_driver->driver_name = DRV_NAME;
+ bfin_jc_driver->name = DEV_NAME;
+ bfin_jc_driver->type = TTY_DRIVER_TYPE_SERIAL;
+ bfin_jc_driver->subtype = SERIAL_TYPE_NORMAL;
+ bfin_jc_driver->init_termios = tty_std_termios;
+ tty_set_operations(bfin_jc_driver, &bfin_jc_ops);
+
+ ret = tty_register_driver(bfin_jc_driver);
+ if (ret)
+ goto err;
+
+ pr_init(KERN_INFO DRV_NAME ": initialized\n");
+
+ return 0;
+
+ err:
+ put_tty_driver(bfin_jc_driver);
+ kfree(bfin_jc_write_buf.buf);
+ kthread_stop(bfin_jc_kthread);
+ return ret;
+}
+module_init(bfin_jc_init);
+
+static void __exit bfin_jc_exit(void)
+{
+ kthread_stop(bfin_jc_kthread);
+ kfree(bfin_jc_write_buf.buf);
+ tty_unregister_driver(bfin_jc_driver);
+ put_tty_driver(bfin_jc_driver);
+}
+module_exit(bfin_jc_exit);
+
+#if defined(CONFIG_BFIN_JTAG_COMM_CONSOLE) || defined(CONFIG_EARLY_PRINTK)
+static void
+bfin_jc_straight_buffer_write(const char *buf, unsigned count)
+{
+ unsigned ate = 0;
+ while (bfin_read_DBGSTAT() & EMUDOF)
+ continue;
+ bfin_write_emudat(count);
+ while (ate < count) {
+ while (bfin_read_DBGSTAT() & EMUDOF)
+ continue;
+ bfin_write_emudat_chars(buf[ate], buf[ate+1], buf[ate+2], buf[ate+3]);
+ ate += 4;
+ }
+}
+#endif
+
+#ifdef CONFIG_BFIN_JTAG_COMM_CONSOLE
+static void
+bfin_jc_console_write(struct console *co, const char *buf, unsigned count)
+{
+ if (bfin_jc_kthread == NULL)
+ bfin_jc_straight_buffer_write(buf, count);
+ else
+ bfin_jc_circ_write(buf, count);
+}
+
+static struct tty_driver *
+bfin_jc_console_device(struct console *co, int *index)
+{
+ *index = co->index;
+ return bfin_jc_driver;
+}
+
+static struct console bfin_jc_console = {
+ .name = DEV_NAME,
+ .write = bfin_jc_console_write,
+ .device = bfin_jc_console_device,
+ .flags = CON_ANYTIME | CON_PRINTBUFFER,
+ .index = -1,
+};
+
+static int __init bfin_jc_console_init(void)
+{
+ register_console(&bfin_jc_console);
+ return 0;
+}
+console_initcall(bfin_jc_console_init);
+#endif
+
+#ifdef CONFIG_EARLY_PRINTK
+static void __init
+bfin_jc_early_write(struct console *co, const char *buf, unsigned int count)
+{
+ bfin_jc_straight_buffer_write(buf, count);
+}
+
+static struct __initdata console bfin_jc_early_console = {
+ .name = "early_BFJC",
+ .write = bfin_jc_early_write,
+ .flags = CON_ANYTIME | CON_PRINTBUFFER,
+ .index = -1,
+};
+
+struct console * __init
+bfin_jc_early_init(unsigned int port, unsigned int cflag)
+{
+ return &bfin_jc_early_console;
+}
+#endif
+
+MODULE_AUTHOR("Mike Frysinger <vapier@gentoo.org>");
+MODULE_DESCRIPTION("TTY over Blackfin JTAG Communication");
+MODULE_LICENSE("GPL");
#define NR_PORTS 256
-#define ZE_V1_NPORTS 64
#define ZO_V1 0
#define ZO_V2 1
#define ZE_V1 2
static void cy_throttle(struct tty_struct *tty);
static void cy_send_xchar(struct tty_struct *tty, char ch);
-#define IS_CYC_Z(card) ((card).num_chips == (unsigned int)-1)
-
-#define Z_FPGA_CHECK(card) \
- ((readl(&((struct RUNTIME_9060 __iomem *) \
- ((card).ctl_addr))->init_ctrl) & (1<<17)) != 0)
-
-#define ISZLOADED(card) (((ZO_V1 == readl(&((struct RUNTIME_9060 __iomem *) \
- ((card).ctl_addr))->mail_box_0)) || \
- Z_FPGA_CHECK(card)) && \
- (ZFIRM_ID == readl(&((struct FIRM_ID __iomem *) \
- ((card).base_addr+ID_ADDRESS))->signature)))
-
#ifndef SERIAL_XMIT_SIZE
#define SERIAL_XMIT_SIZE (min(PAGE_SIZE, 4096))
#endif
#define DRIVER_VERSION 0x02010203
#define RAM_SIZE 0x80000
-#define Z_FPGA_LOADED(X) ((readl(&(X)->init_ctrl) & (1<<17)) != 0)
-
enum zblock_type {
ZBLOCK_PRG = 0,
ZBLOCK_FPGA = 1
static struct timer_list cyz_rx_full_timer[NR_PORTS];
#endif /* CONFIG_CYZ_INTR */
+static inline bool cy_is_Z(struct cyclades_card *card)
+{
+ return card->num_chips == (unsigned int)-1;
+}
+
+static inline bool __cyz_fpga_loaded(struct RUNTIME_9060 __iomem *ctl_addr)
+{
+ return readl(&ctl_addr->init_ctrl) & (1 << 17);
+}
+
+static inline bool cyz_fpga_loaded(struct cyclades_card *card)
+{
+ return __cyz_fpga_loaded(card->ctl_addr.p9060);
+}
+
+static inline bool cyz_is_loaded(struct cyclades_card *card)
+{
+ struct FIRM_ID __iomem *fw_id = card->base_addr + ID_ADDRESS;
+
+ return (card->hw_ver == ZO_V1 || cyz_fpga_loaded(card)) &&
+ readl(&fw_id->signature) == ZFIRM_ID;
+}
+
static inline int serial_paranoia_check(struct cyclades_port *info,
char *name, const char *routine)
{
unsigned long loc_doorbell;
firm_id = cinfo->base_addr + ID_ADDRESS;
- if (!ISZLOADED(*cinfo))
- return -1;
zfw_ctrl = cinfo->base_addr + (readl(&firm_id->zfwctrl_addr) & 0xfffff);
board_ctrl = &zfw_ctrl->board_ctrl;
- loc_doorbell = readl(&((struct RUNTIME_9060 __iomem *)
- (cinfo->ctl_addr))->loc_doorbell);
+ loc_doorbell = readl(&cinfo->ctl_addr.p9060->loc_doorbell);
if (loc_doorbell) {
*cmd = (char)(0xff & loc_doorbell);
*channel = readl(&board_ctrl->fwcmd_channel);
*param = (__u32) readl(&board_ctrl->fwcmd_param);
- cy_writel(&((struct RUNTIME_9060 __iomem *)(cinfo->ctl_addr))->
- loc_doorbell, 0xffffffff);
+ cy_writel(&cinfo->ctl_addr.p9060->loc_doorbell, 0xffffffff);
return 1;
}
return 0;
unsigned int index;
firm_id = cinfo->base_addr + ID_ADDRESS;
- if (!ISZLOADED(*cinfo))
+ if (!cyz_is_loaded(cinfo))
return -1;
zfw_ctrl = cinfo->base_addr + (readl(&firm_id->zfwctrl_addr) & 0xfffff);
board_ctrl = &zfw_ctrl->board_ctrl;
index = 0;
- pci_doorbell =
- &((struct RUNTIME_9060 __iomem *)(cinfo->ctl_addr))->pci_doorbell;
+ pci_doorbell = &cinfo->ctl_addr.p9060->pci_doorbell;
while ((readl(pci_doorbell) & 0xff) != 0) {
if (index++ == 1000)
return (int)(readl(pci_doorbell) & 0xff);
static struct BOARD_CTRL __iomem *board_ctrl;
static struct CH_CTRL __iomem *ch_ctrl;
static struct BUF_CTRL __iomem *buf_ctrl;
- __u32 channel;
+ __u32 channel, param, fw_ver;
__u8 cmd;
- __u32 param;
- __u32 hw_ver, fw_ver;
int special_count;
int delta_count;
zfw_ctrl = cinfo->base_addr + (readl(&firm_id->zfwctrl_addr) & 0xfffff);
board_ctrl = &zfw_ctrl->board_ctrl;
fw_ver = readl(&board_ctrl->fw_version);
- hw_ver = readl(&((struct RUNTIME_9060 __iomem *)(cinfo->ctl_addr))->
- mail_box_0);
while (cyz_fetch_msg(cinfo, &channel, &cmd, ¶m) == 1) {
special_count = 0;
{
struct cyclades_card *cinfo = dev_id;
- if (unlikely(cinfo == NULL)) {
-#ifdef CY_DEBUG_INTERRUPTS
- printk(KERN_DEBUG "cyz_interrupt: spurious interrupt %d\n",
- irq);
-#endif
- return IRQ_NONE; /* spurious interrupt */
- }
-
- if (unlikely(!ISZLOADED(*cinfo))) {
+ if (unlikely(!cyz_is_loaded(cinfo))) {
#ifdef CY_DEBUG_INTERRUPTS
printk(KERN_DEBUG "cyz_interrupt: board not yet loaded "
"(IRQ%d).\n", irq);
struct tty_struct *tty;
struct FIRM_ID __iomem *firm_id;
struct ZFW_CTRL __iomem *zfw_ctrl;
- struct BOARD_CTRL __iomem *board_ctrl;
struct BUF_CTRL __iomem *buf_ctrl;
unsigned long expires = jiffies + HZ;
unsigned int port, card;
for (card = 0; card < NR_CARDS; card++) {
cinfo = &cy_card[card];
- if (!IS_CYC_Z(*cinfo))
+ if (!cy_is_Z(cinfo))
continue;
- if (!ISZLOADED(*cinfo))
+ if (!cyz_is_loaded(cinfo))
continue;
firm_id = cinfo->base_addr + ID_ADDRESS;
zfw_ctrl = cinfo->base_addr +
(readl(&firm_id->zfwctrl_addr) & 0xfffff);
- board_ctrl = &(zfw_ctrl->board_ctrl);
/* Skip first polling cycle to avoid racing conditions with the FW */
if (!cinfo->intr_enabled) {
- cinfo->nports = (int)readl(&board_ctrl->n_channel);
cinfo->intr_enabled = 1;
continue;
}
set_line_char(info);
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
base_addr = card->base_addr;
firm_id = base_addr + ID_ADDRESS;
- if (!ISZLOADED(*card))
+ if (!cyz_is_loaded(card))
return -ENODEV;
zfw_ctrl = card->base_addr +
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
#endif
firm_id = base_addr + ID_ADDRESS;
- if (!ISZLOADED(*card))
+ if (!cyz_is_loaded(card))
return;
zfw_ctrl = card->base_addr +
#endif
info->port.blocked_open++;
- if (!IS_CYC_Z(*cinfo)) {
+ if (!cy_is_Z(cinfo)) {
chip = channel >> 2;
channel &= 0x03;
index = cinfo->bus_index;
base_addr = cinfo->base_addr;
firm_id = base_addr + ID_ADDRESS;
- if (!ISZLOADED(*cinfo)) {
+ if (!cyz_is_loaded(cinfo)) {
__set_current_state(TASK_RUNNING);
remove_wait_queue(&info->port.open_wait, &wait);
return -EINVAL;
treat it as absent from the system. This
will make the user pay attention.
*/
- if (IS_CYC_Z(*info->card)) {
+ if (cy_is_Z(info->card)) {
struct cyclades_card *cinfo = info->card;
struct FIRM_ID __iomem *firm_id = cinfo->base_addr + ID_ADDRESS;
- if (!ISZLOADED(*cinfo)) {
- if (((ZE_V1 == readl(&((struct RUNTIME_9060 __iomem *)
- (cinfo->ctl_addr))->mail_box_0)) &&
- Z_FPGA_CHECK(*cinfo)) &&
- (ZFIRM_HLT == readl(
- &firm_id->signature))) {
+ if (!cyz_is_loaded(cinfo)) {
+ if (cinfo->hw_ver == ZE_V1 && cyz_fpga_loaded(cinfo) &&
+ readl(&firm_id->signature) ==
+ ZFIRM_HLT) {
printk(KERN_ERR "cyc:Cyclades-Z Error: you "
"need an external power supply for "
"this number of ports.\nFirmware "
interrupts should be enabled as soon as the first open
happens to one of its ports. */
if (!cinfo->intr_enabled) {
- struct ZFW_CTRL __iomem *zfw_ctrl;
- struct BOARD_CTRL __iomem *board_ctrl;
-
- zfw_ctrl = cinfo->base_addr +
- (readl(&firm_id->zfwctrl_addr) &
- 0xfffff);
-
- board_ctrl = &zfw_ctrl->board_ctrl;
+ u16 intr;
/* Enable interrupts on the PLX chip */
- cy_writew(cinfo->ctl_addr + 0x68,
- readw(cinfo->ctl_addr + 0x68) | 0x0900);
+ intr = readw(&cinfo->ctl_addr.p9060->
+ intr_ctrl_stat) | 0x0900;
+ cy_writew(&cinfo->ctl_addr.p9060->
+ intr_ctrl_stat, intr);
/* Enable interrupts on the FW */
retval = cyz_issue_cmd(cinfo, 0,
C_CM_IRQ_ENBL, 0L);
printk(KERN_ERR "cyc:IRQ enable retval "
"was %x\n", retval);
}
- cinfo->nports =
- (int)readl(&board_ctrl->n_channel);
cinfo->intr_enabled = 1;
}
}
#endif
card = info->card;
channel = (info->line) - (card->first_line);
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
info->xmit_cnt = info->xmit_head = info->xmit_tail = 0;
spin_unlock_irqrestore(&card->card_lock, flags);
- if (IS_CYC_Z(*card)) { /* If it is a Z card, flush the on-board
+ if (cy_is_Z(card)) { /* If it is a Z card, flush the on-board
buffers as well */
spin_lock_irqsave(&card->card_lock, flags);
retval = cyz_issue_cmd(card, channel, C_CM_FLUSH_TX, 0L);
spin_lock_irqsave(&card->card_lock, flags);
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
int channel = info->line - card->first_line;
int index = card->bus_index;
void __iomem *base_addr = card->base_addr +
channel = (info->line) - (card->first_line);
#ifdef Z_EXT_CHARS_IN_BUFFER
- if (!IS_CYC_Z(cy_card[card])) {
+ if (!cy_is_Z(card)) {
#endif /* Z_EXT_CHARS_IN_BUFFER */
#ifdef CY_DEBUG_IO
printk(KERN_DEBUG "cyc:cy_chars_in_buffer ttyC%d %d\n",
void __iomem *base_addr;
int chip, channel, index;
unsigned cflag, iflag;
- unsigned short chip_number;
int baud, baud_rate = 0;
int i;
card = info->card;
channel = info->line - card->first_line;
- chip_number = channel / 4;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
index = card->bus_index;
} else {
struct FIRM_ID __iomem *firm_id;
struct ZFW_CTRL __iomem *zfw_ctrl;
- struct BOARD_CTRL __iomem *board_ctrl;
struct CH_CTRL __iomem *ch_ctrl;
- struct BUF_CTRL __iomem *buf_ctrl;
__u32 sw_flow;
int retval;
firm_id = card->base_addr + ID_ADDRESS;
- if (!ISZLOADED(*card))
+ if (!cyz_is_loaded(card))
return;
zfw_ctrl = card->base_addr +
(readl(&firm_id->zfwctrl_addr) & 0xfffff);
- board_ctrl = &zfw_ctrl->board_ctrl;
ch_ctrl = &(zfw_ctrl->ch_ctrl[channel]);
- buf_ctrl = &zfw_ctrl->buf_ctrl[channel];
/* baud rate */
baud = tty_get_baud_rate(info->port.tty);
card = info->card;
channel = (info->line) - (card->first_line);
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
} else {
base_addr = card->base_addr;
firm_id = card->base_addr + ID_ADDRESS;
- if (ISZLOADED(*card)) {
+ if (cyz_is_loaded(card)) {
zfw_ctrl = card->base_addr +
(readl(&firm_id->zfwctrl_addr) & 0xfffff);
board_ctrl = &zfw_ctrl->board_ctrl;
card = info->card;
channel = (info->line) - (card->first_line);
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
base_addr = card->base_addr;
firm_id = card->base_addr + ID_ADDRESS;
- if (ISZLOADED(*card)) {
+ if (cyz_is_loaded(card)) {
zfw_ctrl = card->base_addr +
(readl(&firm_id->zfwctrl_addr) & 0xfffff);
board_ctrl = &zfw_ctrl->board_ctrl;
card = info->card;
spin_lock_irqsave(&card->card_lock, flags);
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
/* Let the transmit ISR take care of this (since it
requires stuffing characters into the output stream).
*/
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
card = info->card;
channel = info->line - card->first_line;
- if (IS_CYC_Z(*card)) {
+ if (cy_is_Z(card)) {
if (ch == STOP_CHAR(tty))
cyz_issue_cmd(card, channel, C_CM_SENDXOFF, 0L);
else if (ch == START_CHAR(tty))
card = info->card;
if (I_IXOFF(tty)) {
- if (!IS_CYC_Z(*card))
+ if (!cy_is_Z(card))
cy_send_xchar(tty, STOP_CHAR(tty));
else
info->throttle = 1;
if (tty->termios->c_cflag & CRTSCTS) {
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
if (tty->termios->c_cflag & CRTSCTS) {
card = info->card;
channel = info->line - card->first_line;
- if (!IS_CYC_Z(*card)) {
+ if (!cy_is_Z(card)) {
chip = channel >> 2;
channel &= 0x03;
index = card->bus_index;
cinfo = info->card;
channel = info->line - cinfo->first_line;
- if (!IS_CYC_Z(*cinfo)) {
+ if (!cy_is_Z(cinfo)) {
index = cinfo->bus_index;
chip = channel >> 2;
channel &= 0x03;
cinfo = info->card;
channel = info->line - cinfo->first_line;
index = cinfo->bus_index;
- if (!IS_CYC_Z(*cinfo)) {
+ if (!cy_is_Z(cinfo)) {
chip = channel >> 2;
channel &= 0x03;
base_addr = cinfo->base_addr + (cy_chip_offset[chip] << index);
static int __devinit cy_init_card(struct cyclades_card *cinfo)
{
struct cyclades_port *info;
- u32 uninitialized_var(mailbox);
- unsigned int nports, port;
+ unsigned int port;
unsigned short chip_number;
- int uninitialized_var(index);
spin_lock_init(&cinfo->card_lock);
+ cinfo->intr_enabled = 0;
- if (IS_CYC_Z(*cinfo)) { /* Cyclades-Z */
- mailbox = readl(&((struct RUNTIME_9060 __iomem *)
- cinfo->ctl_addr)->mail_box_0);
- nports = (mailbox == ZE_V1) ? ZE_V1_NPORTS : 8;
- cinfo->intr_enabled = 0;
- cinfo->nports = 0; /* Will be correctly set later, after
- Z FW is loaded */
- } else {
- index = cinfo->bus_index;
- nports = cinfo->nports = CyPORTS_PER_CHIP * cinfo->num_chips;
- }
-
- cinfo->ports = kzalloc(sizeof(*cinfo->ports) * nports, GFP_KERNEL);
+ cinfo->ports = kcalloc(cinfo->nports, sizeof(*cinfo->ports),
+ GFP_KERNEL);
if (cinfo->ports == NULL) {
printk(KERN_ERR "Cyclades: cannot allocate ports\n");
- cinfo->nports = 0;
return -ENOMEM;
}
- for (port = cinfo->first_line; port < cinfo->first_line + nports;
+ for (port = cinfo->first_line; port < cinfo->first_line + cinfo->nports;
port++) {
info = &cinfo->ports[port - cinfo->first_line];
tty_port_init(&info->port);
init_completion(&info->shutdown_wait);
init_waitqueue_head(&info->delta_msr_wait);
- if (IS_CYC_Z(*cinfo)) {
+ if (cy_is_Z(cinfo)) {
info->type = PORT_STARTECH;
- if (mailbox == ZO_V1)
+ if (cinfo->hw_ver == ZO_V1)
info->xmit_fifo_size = CYZ_FIFO_SIZE;
else
info->xmit_fifo_size = 4 * CYZ_FIFO_SIZE;
cyz_rx_restart, (unsigned long)info);
#endif
} else {
+ int index = cinfo->bus_index;
info->type = PORT_CIRRUS;
info->xmit_fifo_size = CyMAX_CHAR_FIFO;
info->cor1 = CyPARITY_NONE | Cy_1_STOP | Cy_8_BITS;
}
#ifndef CONFIG_CYZ_INTR
- if (IS_CYC_Z(*cinfo) && !timer_pending(&cyz_timerlist)) {
+ if (cy_is_Z(cinfo) && !timer_pending(&cyz_timerlist)) {
mod_timer(&cyz_timerlist, jiffies + 1);
#ifdef CY_PCI_DEBUG
printk(KERN_DEBUG "Cyclades-Z polling initialized\n");
/* set cy_card */
cy_card[j].base_addr = cy_isa_address;
- cy_card[j].ctl_addr = NULL;
+ cy_card[j].ctl_addr.p9050 = NULL;
cy_card[j].irq = (int)cy_isa_irq;
cy_card[j].bus_index = 0;
cy_card[j].first_line = cy_next_channel;
- cy_card[j].num_chips = cy_isa_nchan / 4;
+ cy_card[j].num_chips = cy_isa_nchan / CyPORTS_PER_CHIP;
+ cy_card[j].nports = cy_isa_nchan;
if (cy_init_card(&cy_card[j])) {
cy_card[j].base_addr = NULL;
free_irq(cy_isa_irq, &cy_card[j]);
struct CUSTOM_REG __iomem *cust = base_addr;
struct ZFW_CTRL __iomem *pt_zfwctrl;
void __iomem *tmp;
- u32 mailbox, status;
+ u32 mailbox, status, nchan;
unsigned int i;
int retval;
/* Check whether the firmware is already loaded and running. If
positive, skip this board */
- if (Z_FPGA_LOADED(ctl_addr) && readl(&fid->signature) == ZFIRM_ID) {
+ if (__cyz_fpga_loaded(ctl_addr) && readl(&fid->signature) == ZFIRM_ID) {
u32 cntval = readl(base_addr + 0x190);
udelay(100);
mailbox = readl(&ctl_addr->mail_box_0);
- if (mailbox == 0 || Z_FPGA_LOADED(ctl_addr)) {
+ if (mailbox == 0 || __cyz_fpga_loaded(ctl_addr)) {
/* stops CPU and set window to beginning of RAM */
cy_writel(&ctl_addr->loc_addr_base, WIN_CREG);
cy_writel(&cust->cpu_stop, 0);
base_addr);
if (retval)
goto err_rel;
- if (!Z_FPGA_LOADED(ctl_addr)) {
+ if (!__cyz_fpga_loaded(ctl_addr)) {
dev_err(&pdev->dev, "fw upload successful, but fw is "
"not loaded\n");
goto err_rel;
"system before loading the new FW to the "
"Cyclades-Z.\n");
- if (Z_FPGA_LOADED(ctl_addr))
+ if (__cyz_fpga_loaded(ctl_addr))
plx_init(pdev, irq, ctl_addr);
retval = -EIO;
base_addr + ID_ADDRESS, readl(&fid->zfwctrl_addr),
base_addr + readl(&fid->zfwctrl_addr));
+ nchan = readl(&pt_zfwctrl->board_ctrl.n_channel);
dev_info(&pdev->dev, "Cyclades-Z FW loaded: version = %x, ports = %u\n",
- readl(&pt_zfwctrl->board_ctrl.fw_version),
- readl(&pt_zfwctrl->board_ctrl.n_channel));
+ readl(&pt_zfwctrl->board_ctrl.fw_version), nchan);
- if (readl(&pt_zfwctrl->board_ctrl.n_channel) == 0) {
+ if (nchan == 0) {
dev_warn(&pdev->dev, "no Cyclades-Z ports were found. Please "
"check the connection between the Z host card and the "
"serial expanders.\n");
- if (Z_FPGA_LOADED(ctl_addr))
+ if (__cyz_fpga_loaded(ctl_addr))
plx_init(pdev, irq, ctl_addr);
dev_info(&pdev->dev, "Null number of ports detected. Board "
cy_writel(&ctl_addr->intr_ctrl_stat, readl(&ctl_addr->intr_ctrl_stat) |
0x00030800UL);
- plx_init(pdev, irq, ctl_addr);
-
- return 0;
+ return nchan;
err_rel:
release_firmware(fw);
err:
{
void __iomem *addr0 = NULL, *addr2 = NULL;
char *card_name = NULL;
- u32 mailbox;
+ u32 uninitialized_var(mailbox);
unsigned int device_id, nchan = 0, card_no, i;
unsigned char plx_ver;
int retval, irq;
}
/* Disable interrupts on the PLX before resetting it */
- cy_writew(addr0 + 0x68, readw(addr0 + 0x68) & ~0x0900);
+ cy_writew(&ctl_addr->intr_ctrl_stat,
+ readw(&ctl_addr->intr_ctrl_stat) & ~0x0900);
plx_init(pdev, irq, addr0);
- mailbox = (u32)readl(&ctl_addr->mail_box_0);
+ mailbox = readl(&ctl_addr->mail_box_0);
addr2 = ioremap_nocache(pci_resource_start(pdev, 2),
mailbox == ZE_V1 ? CyPCI_Ze_win : CyPCI_Zwin);
if (mailbox == ZE_V1) {
card_name = "Cyclades-Ze";
-
- readl(&ctl_addr->mail_box_0);
- nchan = ZE_V1_NPORTS;
} else {
card_name = "Cyclades-8Zo";
-
#ifdef CY_PCI_DEBUG
if (mailbox == ZO_V1) {
cy_writel(&ctl_addr->loc_addr_base, WIN_CREG);
*/
if ((mailbox == ZO_V1) || (mailbox == ZO_V2))
cy_writel(addr2 + ID_ADDRESS, 0L);
-
- retval = cyz_load_fw(pdev, addr2, addr0, irq);
- if (retval)
- goto err_unmap;
- /* This must be a Cyclades-8Zo/PCI. The extendable
- version will have a different device_id and will
- be allocated its maximum number of ports. */
- nchan = 8;
}
+
+ retval = cyz_load_fw(pdev, addr2, addr0, irq);
+ if (retval <= 0)
+ goto err_unmap;
+ nchan = retval;
}
if ((cy_next_channel + nchan) > NR_PORTS) {
dev_err(&pdev->dev, "could not allocate IRQ\n");
goto err_unmap;
}
- cy_card[card_no].num_chips = nchan / 4;
+ cy_card[card_no].num_chips = nchan / CyPORTS_PER_CHIP;
} else {
+ cy_card[card_no].hw_ver = mailbox;
+ cy_card[card_no].num_chips = (unsigned int)-1;
#ifdef CONFIG_CYZ_INTR
/* allocate IRQ only if board has an IRQ */
if (irq != 0 && irq != 255) {
}
}
#endif /* CONFIG_CYZ_INTR */
- cy_card[card_no].num_chips = (unsigned int)-1;
}
/* set cy_card */
cy_card[card_no].base_addr = addr2;
- cy_card[card_no].ctl_addr = addr0;
+ cy_card[card_no].ctl_addr.p9050 = addr0;
cy_card[card_no].irq = irq;
cy_card[card_no].bus_index = 1;
cy_card[card_no].first_line = cy_next_channel;
+ cy_card[card_no].nports = nchan;
retval = cy_init_card(&cy_card[card_no]);
if (retval)
goto err_null;
plx_ver = readb(addr2 + CyPLX_VER) & 0x0f;
switch (plx_ver) {
case PLX_9050:
-
cy_writeb(addr0 + 0x4c, 0x43);
break;
case PLX_9060:
case PLX_9080:
default: /* Old boards, use PLX_9060 */
- plx_init(pdev, irq, addr0);
- cy_writew(addr0 + 0x68, readw(addr0 + 0x68) | 0x0900);
+ {
+ struct RUNTIME_9060 __iomem *ctl_addr = addr0;
+ plx_init(pdev, irq, ctl_addr);
+ cy_writew(&ctl_addr->intr_ctrl_stat,
+ readw(&ctl_addr->intr_ctrl_stat) | 0x0900);
break;
}
+ }
}
dev_info(&pdev->dev, "%s/PCI #%d found: %d channels starting from "
unsigned int i;
/* non-Z with old PLX */
- if (!IS_CYC_Z(*cinfo) && (readb(cinfo->base_addr + CyPLX_VER) & 0x0f) ==
+ if (!cy_is_Z(cinfo) && (readb(cinfo->base_addr + CyPLX_VER) & 0x0f) ==
PLX_9050)
- cy_writeb(cinfo->ctl_addr + 0x4c, 0);
+ cy_writeb(cinfo->ctl_addr.p9050 + 0x4c, 0);
else
#ifndef CONFIG_CYZ_INTR
- if (!IS_CYC_Z(*cinfo))
+ if (!cy_is_Z(cinfo))
#endif
- cy_writew(cinfo->ctl_addr + 0x68,
- readw(cinfo->ctl_addr + 0x68) & ~0x0900);
+ cy_writew(&cinfo->ctl_addr.p9060->intr_ctrl_stat,
+ readw(&cinfo->ctl_addr.p9060->intr_ctrl_stat) &
+ ~0x0900);
iounmap(cinfo->base_addr);
- if (cinfo->ctl_addr)
- iounmap(cinfo->ctl_addr);
+ if (cinfo->ctl_addr.p9050)
+ iounmap(cinfo->ctl_addr.p9050);
if (cinfo->irq
#ifndef CONFIG_CYZ_INTR
- && !IS_CYC_Z(*cinfo)
+ && !cy_is_Z(cinfo)
#endif /* CONFIG_CYZ_INTR */
)
free_irq(cinfo->irq, cinfo);
(cur_jifs - info->idle_stats.recv_idle)/
HZ, info->idle_stats.overruns,
/* FIXME: double check locking */
- (long)info->port.tty->ldisc.ops->num);
+ (long)info->port.tty->ldisc->ops->num);
else
seq_printf(m, "%3d %8lu %10lu %8lu "
"%10lu %8lu %9lu %6ld\n",
/* clear interrupt */
cy_writeb(card->base_addr + Cy_ClrIntr, 0);
iounmap(card->base_addr);
- if (card->ctl_addr)
- iounmap(card->ctl_addr);
+ if (card->ctl_addr.p9050)
+ iounmap(card->ctl_addr.p9050);
if (card->irq
#ifndef CONFIG_CYZ_INTR
- && !IS_CYC_Z(*card)
+ && !cy_is_Z(card)
#endif /* CONFIG_CYZ_INTR */
)
free_irq(card->irq, card);
return 0;
}
-static void epca_raise_dtr_rts(struct tty_port *port)
+static void epca_dtr_rts(struct tty_port *port, int onoff)
{
}
static const struct tty_port_operations epca_port_ops = {
.carrier_raised = epca_carrier_raised,
- .raise_dtr_rts = epca_raise_dtr_rts,
+ .dtr_rts = epca_dtr_rts,
};
static int info_open(struct tty_struct *tty, struct file *filp)
if (event & MODEMCHG_IND) {
/* A modem signal change has been indicated */
ch->imodem = mstat;
- if (test_bit(ASYNC_CHECK_CD, &ch->port.flags)) {
+ if (test_bit(ASYNCB_CHECK_CD, &ch->port.flags)) {
/* We are now receiving dcd */
if (mstat & ch->dcd)
wake_up_interruptible(&ch->port.open_wait);
* that the driver will wait on carrier detect.
*/
if (ts->c_cflag & CLOCAL)
- clear_bit(ASYNC_CHECK_CD, &ch->port.flags);
+ clear_bit(ASYNCB_CHECK_CD, &ch->port.flags);
else
- set_bit(ASYNC_CHECK_CD, &ch->port.flags);
+ set_bit(ASYNCB_CHECK_CD, &ch->port.flags);
mval = ch->m_dtr | ch->m_rts;
} /* End CBAUD not detected */
iflag = termios2digi_i(ch, ts->c_iflag);
tty_wait_until_sent(tty, 0);
} else {
/* ldisc lock already held in ioctl */
- if (tty->ldisc.ops->flush_buffer)
- tty->ldisc.ops->flush_buffer(tty);
+ if (tty->ldisc->ops->flush_buffer)
+ tty->ldisc->ops->flush_buffer(tty);
}
unlock_kernel();
/* Fall Thru */
if (test_and_clear_bit(EPCA_EVENT_HANGUP, &ch->event)) {
tty_hangup(tty);
wake_up_interruptible(&ch->port.open_wait);
- clear_bit(ASYNC_NORMAL_ACTIVE, &ch->port.flags);
+ clear_bit(ASYNCB_NORMAL_ACTIVE,
+ &ch->port.flags);
}
}
tty_kref_put(tty);
break;
}
- gsi = acpi_register_gsi(irq, ACPI_LEVEL_SENSITIVE,
+ gsi = acpi_register_gsi(NULL, irq, ACPI_LEVEL_SENSITIVE,
ACPI_ACTIVE_LOW);
if (gsi > 0)
break;
irqp = &res->data.extended_irq;
for (i = 0; i < irqp->interrupt_count; i++) {
- irq = acpi_register_gsi(irqp->interrupts[i],
+ irq = acpi_register_gsi(NULL, irqp->interrupts[i],
irqp->triggering, irqp->polarity);
if (irq < 0)
return AE_ERROR;
amountToMove = count;
}
// Move the first block
- pCh->pTTY->ldisc.ops->receive_buf( pCh->pTTY,
+ pCh->pTTY->ldisc->ops->receive_buf( pCh->pTTY,
&(pCh->Ibuf[stripIndex]), NULL, amountToMove );
// If we needed to wrap, do the second data move
if (count > amountToMove) {
- pCh->pTTY->ldisc.ops->receive_buf( pCh->pTTY,
+ pCh->pTTY->ldisc->ops->receive_buf( pCh->pTTY,
pCh->Ibuf, NULL, count - amountToMove );
}
// Bump and wrap the stripIndex all at once by the amount of data read. This
if (tty->pgrp)
kill_pgrp(tty->pgrp, sig, 1);
if (flush || !L_NOFLSH(tty)) {
- if ( tty->ldisc.ops->flush_buffer )
- tty->ldisc.ops->flush_buffer(tty);
+ if ( tty->ldisc->ops->flush_buffer )
+ tty->ldisc->ops->flush_buffer(tty);
i2InputFlush( tty->driver_data );
}
}
/* card->lock MUST NOT be held */
-static void isicom_raise_dtr_rts(struct tty_port *port)
+static void isicom_dtr_rts(struct tty_port *port, int on)
{
struct isi_port *ip = container_of(port, struct isi_port, port);
struct isi_board *card = ip->card;
if (!lock_card(card))
return;
- outw(0x8000 | (channel << card->shift_count) | 0x02, base);
- outw(0x0f04, base);
- InterruptTheCard(base);
- ip->status |= (ISI_DTR | ISI_RTS);
+ if (on) {
+ outw(0x8000 | (channel << card->shift_count) | 0x02, base);
+ outw(0x0f04, base);
+ InterruptTheCard(base);
+ ip->status |= (ISI_DTR | ISI_RTS);
+ } else {
+ outw(0x8000 | (channel << card->shift_count) | 0x02, base);
+ outw(0x0C04, base);
+ InterruptTheCard(base);
+ ip->status &= ~(ISI_DTR | ISI_RTS);
+ }
unlock_card(card);
}
static const struct tty_port_operations isicom_port_ops = {
.carrier_raised = isicom_carrier_raised,
- .raise_dtr_rts = isicom_raise_dtr_rts,
+ .dtr_rts = isicom_dtr_rts,
};
static int __devinit reset_card(struct pci_dev *pdev,
return (portp->sigs & TIOCM_CD) ? 1 : 0;
}
-static void stli_raise_dtr_rts(struct tty_port *port)
+static void stli_dtr_rts(struct tty_port *port, int on)
{
struct stliport *portp = container_of(port, struct stliport, port);
struct stlibrd *brdp = stli_brds[portp->brdnr];
- stli_mkasysigs(&portp->asig, 1, 1);
+ stli_mkasysigs(&portp->asig, on, on);
if (stli_cmdwait(brdp, portp, A_SETSIGNALS, &portp->asig,
sizeof(asysigs_t), 0) < 0)
- printk(KERN_WARNING "istallion: dtr raise failed.\n");
+ printk(KERN_WARNING "istallion: dtr set failed.\n");
}
static const struct tty_port_operations stli_port_ops = {
.carrier_raised = stli_carrier_raised,
- .raise_dtr_rts = stli_raise_dtr_rts,
+ .dtr_rts = stli_dtr_rts,
};
/*****************************************************************************/
written += chunk - unwritten;
if (unwritten)
break;
- /* Consider changing this to just 'signal_pending()' with lots of testing */
- if (fatal_signal_pending(current))
- return written ? written : -EINTR;
+ if (signal_pending(current))
+ return written ? written : -ERESTARTSYS;
buf += chunk;
count -= chunk;
cond_resched();
return -ENODEV;
}
+ if (port % MAX_PORTS_PER_BOARD >= brd->numPorts) {
+ mutex_unlock(&moxa_openlock);
+ return -ENODEV;
+ }
+
ch = &brd->ports[port % MAX_PORTS_PER_BOARD];
ch->port.count++;
tty->driver_data = ch;
return (inb(mp->ioaddr + UART_MSR) & UART_MSR_DCD)?1:0;
}
-static void mxser_raise_dtr_rts(struct tty_port *port)
+static void mxser_dtr_rts(struct tty_port *port, int on)
{
struct mxser_port *mp = container_of(port, struct mxser_port, port);
unsigned long flags;
spin_lock_irqsave(&mp->slock, flags);
- outb(inb(mp->ioaddr + UART_MCR) |
- UART_MCR_DTR | UART_MCR_RTS, mp->ioaddr + UART_MCR);
+ if (on)
+ outb(inb(mp->ioaddr + UART_MCR) |
+ UART_MCR_DTR | UART_MCR_RTS, mp->ioaddr + UART_MCR);
+ else
+ outb(inb(mp->ioaddr + UART_MCR)&~(UART_MCR_DTR | UART_MCR_RTS),
+ mp->ioaddr + UART_MCR);
spin_unlock_irqrestore(&mp->slock, flags);
}
struct tty_port_operations mxser_port_ops = {
.carrier_raised = mxser_carrier_raised,
- .raise_dtr_rts = mxser_raise_dtr_rts,
+ .dtr_rts = mxser_dtr_rts,
};
/*
#endif
/* Flush any pending characters in the driver and discipline. */
- if (tty->ldisc.ops->flush_buffer)
- tty->ldisc.ops->flush_buffer(tty);
+ if (tty->ldisc->ops->flush_buffer)
+ tty->ldisc->ops->flush_buffer(tty);
tty_driver_flush_buffer(tty);
#define ECHO_OP_SET_CANON_COL 0x81
#define ECHO_OP_ERASE_TAB 0x82
-static inline unsigned char *alloc_buf(void)
-{
- gfp_t prio = in_interrupt() ? GFP_ATOMIC : GFP_KERNEL;
-
- if (PAGE_SIZE != N_TTY_BUF_SIZE)
- return kmalloc(N_TTY_BUF_SIZE, prio);
- else
- return (unsigned char *)__get_free_page(prio);
-}
-
-static inline void free_buf(unsigned char *buf)
-{
- if (PAGE_SIZE != N_TTY_BUF_SIZE)
- kfree(buf);
- else
- free_page((unsigned long) buf);
-}
-
static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
unsigned char __user *ptr)
{
{
n_tty_flush_buffer(tty);
if (tty->read_buf) {
- free_buf(tty->read_buf);
+ kfree(tty->read_buf);
tty->read_buf = NULL;
}
if (tty->echo_buf) {
- free_buf(tty->echo_buf);
+ kfree(tty->echo_buf);
tty->echo_buf = NULL;
}
}
/* These are ugly. Currently a malloc failure here can panic */
if (!tty->read_buf) {
- tty->read_buf = alloc_buf();
+ tty->read_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
if (!tty->read_buf)
return -ENOMEM;
}
if (!tty->echo_buf) {
- tty->echo_buf = alloc_buf();
+ tty->echo_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
+
if (!tty->echo_buf)
return -ENOMEM;
}
- memset(tty->read_buf, 0, N_TTY_BUF_SIZE);
- memset(tty->echo_buf, 0, N_TTY_BUF_SIZE);
reset_buffer_flags(tty);
tty->column = 0;
n_tty_set_termios(tty, NULL);
static void tx_timeout(unsigned long context);
static int carrier_raised(struct tty_port *port);
-static void raise_dtr_rts(struct tty_port *port);
+static void dtr_rts(struct tty_port *port, int onoff);
#if SYNCLINK_GENERIC_HDLC
#define dev_to_port(D) (dev_to_hdlc(D)->priv)
static const struct tty_port_operations mgslpc_port_ops = {
.carrier_raised = carrier_raised,
- .raise_dtr_rts = raise_dtr_rts
+ .dtr_rts = dtr_rts
};
static int mgslpc_probe(struct pcmcia_device *link)
return 0;
}
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int onoff)
{
MGSLPC_INFO *info = container_of(port, MGSLPC_INFO, port);
unsigned long flags;
spin_lock_irqsave(&info->lock,flags);
- info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+ if (onoff)
+ info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+ else
+ info->serial_signals &= ~SerialSignal_RTS + SerialSignal_DTR;
set_signals(info);
spin_unlock_irqrestore(&info->lock,flags);
}
#include <asm/system.h>
-/* These are global because they are accessed in tty_io.c */
#ifdef CONFIG_UNIX98_PTYS
static struct tty_driver *ptm_driver;
static struct tty_driver *pts_driver;
c = to->receive_room;
if (c > count)
c = count;
- to->ldisc.ops->receive_buf(to, buf, NULL, c);
+ to->ldisc->ops->receive_buf(to, buf, NULL, c);
return c;
}
int count;
/* We should get the line discipline lock for "tty->link" */
- if (!to || !to->ldisc.ops->chars_in_buffer)
+ if (!to || !to->ldisc->ops->chars_in_buffer)
return 0;
/* The ldisc must report 0 if no characters available to be read */
- count = to->ldisc.ops->chars_in_buffer(to);
+ count = to->ldisc->ops->chars_in_buffer(to);
if (tty->driver->subtype == PTY_TYPE_SLAVE)
return count;
if (!to)
return;
- if (to->ldisc.ops->flush_buffer)
- to->ldisc.ops->flush_buffer(to);
+ if (to->ldisc->ops->flush_buffer)
+ to->ldisc->ops->flush_buffer(to);
if (to->packet) {
spin_lock_irqsave(&tty->ctrl_lock, flags);
return (sGetChanStatusLo(&info->channel) & CD_ACT) ? 1 : 0;
}
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
{
struct r_port *info = container_of(port, struct r_port, port);
- sSetDTR(&info->channel);
- sSetRTS(&info->channel);
+ if (on) {
+ sSetDTR(&info->channel);
+ sSetRTS(&info->channel);
+ } else {
+ sClrDTR(&info->channel);
+ sClrRTS(&info->channel);
+ }
}
/*
/*
* Info->count is now 1; so it's safe to sleep now.
*/
- if (!test_bit(ASYNC_INITIALIZED, &port->flags)) {
+ if (!test_bit(ASYNCB_INITIALIZED, &port->flags)) {
cp = &info->channel;
sSetRxTrigger(cp, TRIG_1);
if (sGetChanStatus(cp) & CD_ACT)
sEnRxFIFO(cp);
sEnTransmit(cp);
- set_bit(ASYNC_INITIALIZED, &info->port.flags);
+ set_bit(ASYNCB_INITIALIZED, &info->port.flags);
/*
* Set up the tty->alt_speed kludge
/* Write remaining data into the port's xmit_buf */
while (1) {
/* Hung up ? */
- if (!test_bit(ASYNC_NORMAL_ACTIVE, &info->port.flags))
+ if (!test_bit(ASYNCB_NORMAL_ACTIVE, &info->port.flags))
goto end;
c = min(count, XMIT_BUF_SIZE - info->xmit_cnt - 1);
c = min(c, XMIT_BUF_SIZE - info->xmit_head);
static const struct tty_port_operations rocket_port_ops = {
.carrier_raised = carrier_raised,
- .raise_dtr_rts = raise_dtr_rts,
+ .dtr_rts = dtr_rts,
};
/*
}
count = sel_buffer_lth - pasted;
count = min(count, tty->receive_room);
- tty->ldisc.ops->receive_buf(tty, sel_buffer + pasted,
+ tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
NULL, count);
pasted += count;
}
return (portp->sigs & TIOCM_CD) ? 1 : 0;
}
-static void stl_raise_dtr_rts(struct tty_port *port)
+static void stl_dtr_rts(struct tty_port *port, int on)
{
struct stlport *portp = container_of(port, struct stlport, port);
/* Takes brd_lock internally */
- stl_setsignals(portp, 1, 1);
+ stl_setsignals(portp, on, on);
}
/*****************************************************************************/
static const struct tty_port_operations stl_port_ops = {
.carrier_raised = stl_carrier_raised,
- .raise_dtr_rts = stl_raise_dtr_rts,
+ .dtr_rts = stl_dtr_rts,
};
/*****************************************************************************/
return (info->serial_signals & SerialSignal_DCD) ? 1 : 0;
}
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
{
struct mgsl_struct *info = container_of(port, struct mgsl_struct, port);
unsigned long flags;
spin_lock_irqsave(&info->irq_spinlock,flags);
- info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+ if (on)
+ info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+ else
+ info->serial_signals &= ~(SerialSignal_RTS + SerialSignal_DTR);
usc_set_serial_signals(info);
spin_unlock_irqrestore(&info->irq_spinlock,flags);
}
static const struct tty_port_operations mgsl_port_ops = {
.carrier_raised = carrier_raised,
- .raise_dtr_rts = raise_dtr_rts,
+ .dtr_rts = dtr_rts,
};
#define set_desc_next(a,b) (a).next = cpu_to_le32((unsigned int)(b))
#define set_desc_count(a,b)(a).count = cpu_to_le16((unsigned short)(b))
#define set_desc_eof(a,b) (a).status = cpu_to_le16((b) ? (le16_to_cpu((a).status) | BIT0) : (le16_to_cpu((a).status) & ~BIT0))
+#define set_desc_status(a, b) (a).status = cpu_to_le16((unsigned short)(b))
#define desc_count(a) (le16_to_cpu((a).count))
#define desc_status(a) (le16_to_cpu((a).status))
#define desc_complete(a) (le16_to_cpu((a).status) & BIT15)
u32 max_frame_size; /* as set by device config */
unsigned int rbuf_fill_level;
+ unsigned int rx_pio;
unsigned int if_mode;
unsigned int base_clock;
struct slgt_desc *rbufs;
unsigned int rbuf_current;
unsigned int rbuf_index;
+ unsigned int rbuf_fill_index;
+ unsigned short rbuf_fill_count;
unsigned int tbuf_count;
struct slgt_desc *tbufs;
info->pending_bh |= BH_STATUS;
}
+static void isr_rxdata(struct slgt_info *info)
+{
+ unsigned int count = info->rbuf_fill_count;
+ unsigned int i = info->rbuf_fill_index;
+ unsigned short reg;
+
+ while (rd_reg16(info, SSR) & IRQ_RXDATA) {
+ reg = rd_reg16(info, RDR);
+ DBGISR(("isr_rxdata %s RDR=%04X\n", info->device_name, reg));
+ if (desc_complete(info->rbufs[i])) {
+ /* all buffers full */
+ rx_stop(info);
+ info->rx_restart = 1;
+ continue;
+ }
+ info->rbufs[i].buf[count++] = (unsigned char)reg;
+ /* async mode saves status byte to buffer for each data byte */
+ if (info->params.mode == MGSL_MODE_ASYNC)
+ info->rbufs[i].buf[count++] = (unsigned char)(reg >> 8);
+ if (count == info->rbuf_fill_level || (reg & BIT10)) {
+ /* buffer full or end of frame */
+ set_desc_count(info->rbufs[i], count);
+ set_desc_status(info->rbufs[i], BIT15 | (reg >> 8));
+ info->rbuf_fill_count = count = 0;
+ if (++i == info->rbuf_count)
+ i = 0;
+ info->pending_bh |= BH_RECEIVE;
+ }
+ }
+
+ info->rbuf_fill_index = i;
+ info->rbuf_fill_count = count;
+}
+
static void isr_serial(struct slgt_info *info)
{
unsigned short status = rd_reg16(info, SSR);
if (info->tx_count)
isr_txeom(info, status);
}
+ if (info->rx_pio && (status & IRQ_RXDATA))
+ isr_rxdata(info);
if ((status & IRQ_RXBREAK) && (status & RXBREAK)) {
info->icount.brk++;
/* process break detection if tty control allows */
} else {
if (status & (IRQ_TXIDLE + IRQ_TXUNDER))
isr_txeom(info, status);
-
+ if (info->rx_pio && (status & IRQ_RXDATA))
+ isr_rxdata(info);
if (status & IRQ_RXIDLE) {
if (status & RXIDLE)
info->icount.rxidle++;
return -EINVAL;
}
info->rbuf_fill_level = rbuf_fill_level;
+ if (rbuf_fill_level < 128)
+ info->rx_pio = 1; /* PIO mode */
+ else
+ info->rx_pio = 0; /* DMA mode */
rx_stop(info); /* restart receiver to use new fill level */
}
return (info->signals & SerialSignal_DCD) ? 1 : 0;
}
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
{
unsigned long flags;
struct slgt_info *info = container_of(port, struct slgt_info, port);
spin_lock_irqsave(&info->lock,flags);
- info->signals |= SerialSignal_RTS + SerialSignal_DTR;
+ if (on)
+ info->signals |= SerialSignal_RTS + SerialSignal_DTR;
+ else
+ info->signals &= ~(SerialSignal_RTS + SerialSignal_DTR);
set_signals(info);
spin_unlock_irqrestore(&info->lock,flags);
}
static const struct tty_port_operations slgt_port_ops = {
.carrier_raised = carrier_raised,
- .raise_dtr_rts = raise_dtr_rts,
+ .dtr_rts = dtr_rts,
};
/*
rdma_reset(info);
reset_rbufs(info);
- /* set 1st descriptor address */
- wr_reg32(info, RDDAR, info->rbufs[0].pdesc);
-
- if (info->params.mode != MGSL_MODE_ASYNC) {
- /* enable rx DMA and DMA interrupt */
- wr_reg32(info, RDCSR, (BIT2 + BIT0));
+ if (info->rx_pio) {
+ /* rx request when rx FIFO not empty */
+ wr_reg16(info, SCR, (unsigned short)(rd_reg16(info, SCR) & ~BIT14));
+ slgt_irq_on(info, IRQ_RXDATA);
+ if (info->params.mode == MGSL_MODE_ASYNC) {
+ /* enable saving of rx status */
+ wr_reg32(info, RDCSR, BIT6);
+ }
} else {
- /* enable saving of rx status, rx DMA and DMA interrupt */
- wr_reg32(info, RDCSR, (BIT6 + BIT2 + BIT0));
+ /* rx request when rx FIFO half full */
+ wr_reg16(info, SCR, (unsigned short)(rd_reg16(info, SCR) | BIT14));
+ /* set 1st descriptor address */
+ wr_reg32(info, RDDAR, info->rbufs[0].pdesc);
+
+ if (info->params.mode != MGSL_MODE_ASYNC) {
+ /* enable rx DMA and DMA interrupt */
+ wr_reg32(info, RDCSR, (BIT2 + BIT0));
+ } else {
+ /* enable saving of rx status, rx DMA and DMA interrupt */
+ wr_reg32(info, RDCSR, (BIT6 + BIT2 + BIT0));
+ }
}
slgt_irq_on(info, IRQ_RXOVER);
static void reset_rbufs(struct slgt_info *info)
{
free_rbufs(info, 0, info->rbuf_count - 1);
+ info->rbuf_fill_index = 0;
+ info->rbuf_fill_count = 0;
}
/*
return (info->serial_signals & SerialSignal_DCD) ? 1 : 0;
}
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
{
SLMP_INFO *info = container_of(port, SLMP_INFO, port);
unsigned long flags;
spin_lock_irqsave(&info->lock,flags);
- info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+ if (on)
+ info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+ else
+ info->serial_signals &= ~(SerialSignal_RTS + SerialSignal_DTR);
set_signals(info);
spin_unlock_irqrestore(&info->lock,flags);
}
static const struct tty_port_operations port_ops = {
.carrier_raised = carrier_raised,
- .raise_dtr_rts = raise_dtr_rts,
+ .dtr_rts = dtr_rts,
};
/* Allocate and initialize a device instance structure
buf = kmalloc(sizeof(*buf), GFP_KERNEL);
if (!buf)
goto err;
- if (PAGE_SIZE != N_TTY_BUF_SIZE)
- buf->data = kmalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
- else
- buf->data = (unsigned char *)__get_free_page(GFP_KERNEL);
+ buf->data = kmalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
if (!buf->data)
goto err_buf;
atomic_set(&buf->count, 1);
static void tty_audit_buf_free(struct tty_audit_buf *buf)
{
WARN_ON(buf->valid != 0);
- if (PAGE_SIZE != N_TTY_BUF_SIZE)
- kfree(buf->data);
- else
- free_page((unsigned long)buf->data);
+ kfree(buf->data);
kfree(buf);
}
struct tty_driver *p, *res = NULL;
int tty_line = 0;
int len;
- char *str;
+ char *str, *stp;
for (str = name; *str; str++)
if ((*str >= '0' && *str <= '9') || *str == ',')
list_for_each_entry(p, &tty_drivers, tty_drivers) {
if (strncmp(name, p->name, len) != 0)
continue;
- if (*str == ',')
- str++;
- if (*str == '\0')
- str = NULL;
+ stp = str;
+ if (*stp == ',')
+ stp++;
+ if (*stp == '\0')
+ stp = NULL;
if (tty_line >= 0 && tty_line <= p->num && p->ops &&
- p->ops->poll_init && !p->ops->poll_init(p, tty_line, str)) {
+ p->ops->poll_init && !p->ops->poll_init(p, tty_line, stp)) {
res = tty_driver_kref_get(p);
*line = tty_line;
break;
EXPORT_SYMBOL_GPL(tty_wakeup);
-/**
- * tty_ldisc_flush - flush line discipline queue
- * @tty: tty
- *
- * Flush the line discipline queue (if any) for this tty. If there
- * is no line discipline active this is a no-op.
- */
-
-void tty_ldisc_flush(struct tty_struct *tty)
-{
- struct tty_ldisc *ld = tty_ldisc_ref(tty);
- if (ld) {
- if (ld->ops->flush_buffer)
- ld->ops->flush_buffer(tty);
- tty_ldisc_deref(ld);
- }
- tty_buffer_flush(tty);
-}
-
-EXPORT_SYMBOL_GPL(tty_ldisc_flush);
-
-/**
- * tty_reset_termios - reset terminal state
- * @tty: tty to reset
- *
- * Restore a terminal to the driver default state
- */
-
-static void tty_reset_termios(struct tty_struct *tty)
-{
- mutex_lock(&tty->termios_mutex);
- *tty->termios = tty->driver->init_termios;
- tty->termios->c_ispeed = tty_termios_input_baud_rate(tty->termios);
- tty->termios->c_ospeed = tty_termios_baud_rate(tty->termios);
- mutex_unlock(&tty->termios_mutex);
-}
-
/**
* do_tty_hangup - actual handler for hangup events
* @work: tty device
struct file *cons_filp = NULL;
struct file *filp, *f = NULL;
struct task_struct *p;
- struct tty_ldisc *ld;
int closecount = 0, n;
unsigned long flags;
int refs = 0;
filp->f_op = &hung_up_tty_fops;
}
file_list_unlock();
- /*
- * FIXME! What are the locking issues here? This may me overdoing
- * things... This question is especially important now that we've
- * removed the irqlock.
- */
- ld = tty_ldisc_ref(tty);
- if (ld != NULL) {
- /* We may have no line discipline at this point */
- if (ld->ops->flush_buffer)
- ld->ops->flush_buffer(tty);
- tty_driver_flush_buffer(tty);
- if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
- ld->ops->write_wakeup)
- ld->ops->write_wakeup(tty);
- if (ld->ops->hangup)
- ld->ops->hangup(tty);
- }
- /*
- * FIXME: Once we trust the LDISC code better we can wait here for
- * ldisc completion and fix the driver call race
- */
- wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
- wake_up_interruptible_poll(&tty->read_wait, POLLIN);
- /*
- * Shutdown the current line discipline, and reset it to
- * N_TTY.
- */
- if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS)
- tty_reset_termios(tty);
- /* Defer ldisc switch */
- /* tty_deferred_ldisc_switch(N_TTY);
- This should get done automatically when the port closes and
- tty_release is called */
+ tty_ldisc_hangup(tty);
read_lock(&tasklist_lock);
if (tty->session) {
read_unlock(&tasklist_lock);
spin_lock_irqsave(&tty->ctrl_lock, flags);
- tty->flags = 0;
+ clear_bit(TTY_THROTTLED, &tty->flags);
+ clear_bit(TTY_PUSH, &tty->flags);
+ clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
put_pid(tty->session);
put_pid(tty->pgrp);
tty->session = NULL;
tty->pgrp = NULL;
tty->ctrl_status = 0;
+ set_bit(TTY_HUPPED, &tty->flags);
spin_unlock_irqrestore(&tty->ctrl_lock, flags);
/* Account for the p->signal references we killed */
* can't yet guarantee all that.
*/
set_bit(TTY_HUPPED, &tty->flags);
- if (ld) {
- tty_ldisc_enable(tty);
- tty_ldisc_deref(ld);
- }
+ tty_ldisc_enable(tty);
unlock_kernel();
if (f)
fput(f);
return tty->ops->tiocmset(tty, file, set, clear);
}
+struct tty_struct *tty_pair_get_tty(struct tty_struct *tty)
+{
+ if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver->subtype == PTY_TYPE_MASTER)
+ tty = tty->link;
+ return tty;
+}
+EXPORT_SYMBOL(tty_pair_get_tty);
+
+struct tty_struct *tty_pair_get_pty(struct tty_struct *tty)
+{
+ if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+ tty->driver->subtype == PTY_TYPE_MASTER)
+ return tty;
+ return tty->link;
+}
+EXPORT_SYMBOL(tty_pair_get_pty);
+
/*
* Split this up, as gcc can choke on it otherwise..
*/
if (tty_paranoia_check(tty, inode, "tty_ioctl"))
return -EINVAL;
- real_tty = tty;
- if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
- tty->driver->subtype == PTY_TYPE_MASTER)
- real_tty = tty->link;
-
+ real_tty = tty_pair_get_tty(tty);
/*
* Factor out some common prep work
case TIOCGSID:
return tiocgsid(tty, real_tty, p);
case TIOCGETD:
- return put_user(tty->ldisc.ops->num, (int __user *)p);
+ return put_user(tty->ldisc->ops->num, (int __user *)p);
case TIOCSETD:
return tiocsetd(tty, p);
/*
tty->buf.head = tty->buf.tail = NULL;
tty_buffer_init(tty);
mutex_init(&tty->termios_mutex);
+ mutex_init(&tty->ldisc_mutex);
init_waitqueue_head(&tty->write_wait);
init_waitqueue_head(&tty->read_wait);
INIT_WORK(&tty->hangup_work, do_tty_hangup);
* @tty: terminal
*
* Indicate that a tty should stop transmitting data down the stack.
+ * Takes the termios mutex to protect against parallel throttle/unthrottle
+ * and also to ensure the driver can consistently reference its own
+ * termios data at this point when implementing software flow control.
*/
void tty_throttle(struct tty_struct *tty)
{
+ mutex_lock(&tty->termios_mutex);
/* check TTY_THROTTLED first so it indicates our state */
if (!test_and_set_bit(TTY_THROTTLED, &tty->flags) &&
tty->ops->throttle)
tty->ops->throttle(tty);
+ mutex_unlock(&tty->termios_mutex);
}
EXPORT_SYMBOL(tty_throttle);
* @tty: terminal
*
* Indicate that a tty may continue transmitting data down the stack.
+ * Takes the termios mutex to protect against parallel throttle/unthrottle
+ * and also to ensure the driver can consistently reference its own
+ * termios data at this point when implementing software flow control.
+ *
+ * Drivers should however remember that the stack can issue a throttle,
+ * then change flow control method, then unthrottle.
*/
void tty_unthrottle(struct tty_struct *tty)
{
+ mutex_lock(&tty->termios_mutex);
if (test_and_clear_bit(TTY_THROTTLED, &tty->flags) &&
tty->ops->unthrottle)
tty->ops->unthrottle(tty);
+ mutex_unlock(&tty->termios_mutex);
}
EXPORT_SYMBOL(tty_unthrottle);
return 0;
}
+static void copy_termios(struct tty_struct *tty, struct ktermios *kterm)
+{
+ mutex_lock(&tty->termios_mutex);
+ memcpy(kterm, tty->termios, sizeof(struct ktermios));
+ mutex_unlock(&tty->termios_mutex);
+}
+
+static void copy_termios_locked(struct tty_struct *tty, struct ktermios *kterm)
+{
+ mutex_lock(&tty->termios_mutex);
+ memcpy(kterm, tty->termios_locked, sizeof(struct ktermios));
+ mutex_unlock(&tty->termios_mutex);
+}
+
static int get_termio(struct tty_struct *tty, struct termio __user *termio)
{
- if (kernel_termios_to_user_termio(termio, tty->termios))
+ struct ktermios kterm;
+ copy_termios(tty, &kterm);
+ if (kernel_termios_to_user_termio(termio, &kterm))
return -EFAULT;
return 0;
}
struct tty_struct *real_tty;
void __user *p = (void __user *)arg;
int ret = 0;
+ struct ktermios kterm;
+ struct termiox ktermx;
if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
tty->driver->subtype == PTY_TYPE_MASTER)
return set_termios(real_tty, p, TERMIOS_OLD);
#ifndef TCGETS2
case TCGETS:
- mutex_lock(&real_tty->termios_mutex);
- if (kernel_termios_to_user_termios((struct termios __user *)arg, real_tty->termios))
+ copy_termios(real_tty, &kterm);
+ if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm))
ret = -EFAULT;
- mutex_unlock(&real_tty->termios_mutex);
return ret;
#else
case TCGETS:
- mutex_lock(&real_tty->termios_mutex);
- if (kernel_termios_to_user_termios_1((struct termios __user *)arg, real_tty->termios))
+ copy_termios(real_tty, &kterm);
+ if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm))
ret = -EFAULT;
- mutex_unlock(&real_tty->termios_mutex);
return ret;
case TCGETS2:
- mutex_lock(&real_tty->termios_mutex);
- if (kernel_termios_to_user_termios((struct termios2 __user *)arg, real_tty->termios))
+ copy_termios(real_tty, &kterm);
+ if (kernel_termios_to_user_termios((struct termios2 __user *)arg, &kterm))
ret = -EFAULT;
- mutex_unlock(&real_tty->termios_mutex);
return ret;
case TCSETSF2:
return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT);
return set_termios(real_tty, p, TERMIOS_TERMIO);
#ifndef TCGETS2
case TIOCGLCKTRMIOS:
- mutex_lock(&real_tty->termios_mutex);
- if (kernel_termios_to_user_termios((struct termios __user *)arg, real_tty->termios_locked))
+ copy_termios_locked(real_tty, &kterm);
+ if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm))
ret = -EFAULT;
- mutex_unlock(&real_tty->termios_mutex);
return ret;
case TIOCSLCKTRMIOS:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- mutex_lock(&real_tty->termios_mutex);
- if (user_termios_to_kernel_termios(real_tty->termios_locked,
+ copy_termios_locked(real_tty, &kterm);
+ if (user_termios_to_kernel_termios(&kterm,
(struct termios __user *) arg))
- ret = -EFAULT;
+ return -EFAULT;
+ mutex_lock(&real_tty->termios_mutex);
+ memcpy(real_tty->termios_locked, &kterm, sizeof(struct ktermios));
mutex_unlock(&real_tty->termios_mutex);
- return ret;
+ return 0;
#else
case TIOCGLCKTRMIOS:
- mutex_lock(&real_tty->termios_mutex);
- if (kernel_termios_to_user_termios_1((struct termios __user *)arg, real_tty->termios_locked))
+ copy_termios_locked(real_tty, &kterm);
+ if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm))
ret = -EFAULT;
- mutex_unlock(&real_tty->termios_mutex);
return ret;
case TIOCSLCKTRMIOS:
if (!capable(CAP_SYS_ADMIN))
- ret = -EPERM;
- mutex_lock(&real_tty->termios_mutex);
- if (user_termios_to_kernel_termios_1(real_tty->termios_locked,
+ return -EPERM;
+ copy_termios_locked(real_tty, &kterm);
+ if (user_termios_to_kernel_termios_1(&kterm,
(struct termios __user *) arg))
- ret = -EFAULT;
+ return -EFAULT;
+ mutex_lock(&real_tty->termios_mutex);
+ memcpy(real_tty->termios_locked, &kterm, sizeof(struct ktermios));
mutex_unlock(&real_tty->termios_mutex);
return ret;
#endif
if (real_tty->termiox == NULL)
return -EINVAL;
mutex_lock(&real_tty->termios_mutex);
- if (copy_to_user(p, real_tty->termiox, sizeof(struct termiox)))
- ret = -EFAULT;
+ memcpy(&ktermx, real_tty->termiox, sizeof(struct termiox));
mutex_unlock(&real_tty->termios_mutex);
+ if (copy_to_user(p, &ktermx, sizeof(struct termiox)))
+ ret = -EFAULT;
return ret;
case TCSETX:
return set_termiox(real_tty, p, 0);
return set_termiox(real_tty, p, TERMIOS_FLUSH);
#endif
case TIOCGSOFTCAR:
- mutex_lock(&real_tty->termios_mutex);
- ret = put_user(C_CLOCAL(real_tty) ? 1 : 0,
+ copy_termios(real_tty, &kterm);
+ ret = put_user((kterm.c_cflag & CLOCAL) ? 1 : 0,
(int __user *)arg);
- mutex_unlock(&real_tty->termios_mutex);
return ret;
case TIOCSSOFTCAR:
if (get_user(arg, (unsigned int __user *) arg))
/**
* tty_ldisc_try_get - try and reference an ldisc
* @disc: ldisc number
- * @ld: tty ldisc structure to complete
*
* Attempt to open and lock a line discipline into place. Return
- * the line discipline refcounted and assigned in ld. On an error
- * report the error code back
+ * the line discipline refcounted or an error.
*/
-static int tty_ldisc_try_get(int disc, struct tty_ldisc *ld)
+static struct tty_ldisc *tty_ldisc_try_get(int disc)
{
unsigned long flags;
+ struct tty_ldisc *ld;
struct tty_ldisc_ops *ldops;
int err = -EINVAL;
-
+
+ ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL);
+ if (ld == NULL)
+ return ERR_PTR(-ENOMEM);
+
spin_lock_irqsave(&tty_ldisc_lock, flags);
ld->ops = NULL;
ldops = tty_ldiscs[disc];
/* lock it */
ldops->refcount++;
ld->ops = ldops;
+ ld->refcount = 0;
err = 0;
}
}
spin_unlock_irqrestore(&tty_ldisc_lock, flags);
- return err;
+ if (err)
+ return ERR_PTR(err);
+ return ld;
}
/**
* tty_ldisc_get - take a reference to an ldisc
* @disc: ldisc number
- * @ld: tty line discipline structure to use
*
* Takes a reference to a line discipline. Deals with refcounts and
* module locking counts. Returns NULL if the discipline is not available.
* takes tty_ldisc_lock to guard against ldisc races
*/
-static int tty_ldisc_get(int disc, struct tty_ldisc *ld)
+static struct tty_ldisc *tty_ldisc_get(int disc)
{
- int err;
+ struct tty_ldisc *ld;
if (disc < N_TTY || disc >= NR_LDISCS)
- return -EINVAL;
- err = tty_ldisc_try_get(disc, ld);
- if (err < 0) {
+ return ERR_PTR(-EINVAL);
+ ld = tty_ldisc_try_get(disc);
+ if (IS_ERR(ld)) {
request_module("tty-ldisc-%d", disc);
- err = tty_ldisc_try_get(disc, ld);
+ ld = tty_ldisc_try_get(disc);
}
- return err;
+ return ld;
}
/**
* tty_ldisc_put - drop ldisc reference
- * @disc: ldisc number
+ * @ld: ldisc
*
* Drop a reference to a line discipline. Manage refcounts and
- * module usage counts
+ * module usage counts. Free the ldisc once the recount hits zero.
*
* Locking:
* takes tty_ldisc_lock to guard against ldisc races
*/
-static void tty_ldisc_put(struct tty_ldisc_ops *ld)
+static void tty_ldisc_put(struct tty_ldisc *ld)
{
unsigned long flags;
- int disc = ld->num;
+ int disc = ld->ops->num;
+ struct tty_ldisc_ops *ldo;
BUG_ON(disc < N_TTY || disc >= NR_LDISCS);
spin_lock_irqsave(&tty_ldisc_lock, flags);
- ld = tty_ldiscs[disc];
- BUG_ON(ld->refcount == 0);
- ld->refcount--;
- module_put(ld->owner);
+ ldo = tty_ldiscs[disc];
+ BUG_ON(ldo->refcount == 0);
+ ldo->refcount--;
+ module_put(ldo->owner);
spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ kfree(ld);
}
-static void * tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
+static void *tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
{
return (*pos < NR_LDISCS) ? pos : NULL;
}
-static void * tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
+static void *tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
{
(*pos)++;
return (*pos < NR_LDISCS) ? pos : NULL;
static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
{
int i = *(loff_t *)v;
- struct tty_ldisc ld;
-
- if (tty_ldisc_get(i, &ld) < 0)
+ struct tty_ldisc *ld;
+
+ ld = tty_ldisc_try_get(i);
+ if (IS_ERR(ld))
return 0;
- seq_printf(m, "%-10s %2d\n", ld.ops->name ? ld.ops->name : "???", i);
- tty_ldisc_put(ld.ops);
+ seq_printf(m, "%-10s %2d\n", ld->ops->name ? ld->ops->name : "???", i);
+ tty_ldisc_put(ld);
return 0;
}
static void tty_ldisc_assign(struct tty_struct *tty, struct tty_ldisc *ld)
{
- ld->refcount = 0;
- tty->ldisc = *ld;
+ tty->ldisc = ld;
}
/**
int ret = 0;
spin_lock_irqsave(&tty_ldisc_lock, flags);
- ld = &tty->ldisc;
+ ld = tty->ldisc;
if (test_bit(TTY_LDISC, &tty->flags)) {
ld->refcount++;
ret = 1;
{
/* wait_event is a macro */
wait_event(tty_ldisc_wait, tty_ldisc_try(tty));
- WARN_ON(tty->ldisc.refcount == 0);
- return &tty->ldisc;
+ WARN_ON(tty->ldisc->refcount == 0);
+ return tty->ldisc;
}
-
EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait);
/**
struct tty_ldisc *tty_ldisc_ref(struct tty_struct *tty)
{
if (tty_ldisc_try(tty))
- return &tty->ldisc;
+ return tty->ldisc;
return NULL;
}
-
EXPORT_SYMBOL_GPL(tty_ldisc_ref);
/**
wake_up(&tty_ldisc_wait);
spin_unlock_irqrestore(&tty_ldisc_lock, flags);
}
-
EXPORT_SYMBOL_GPL(tty_ldisc_deref);
/**
wake_up(&tty_ldisc_wait);
}
+/**
+ * tty_ldisc_flush - flush line discipline queue
+ * @tty: tty
+ *
+ * Flush the line discipline queue (if any) for this tty. If there
+ * is no line discipline active this is a no-op.
+ */
+
+void tty_ldisc_flush(struct tty_struct *tty)
+{
+ struct tty_ldisc *ld = tty_ldisc_ref(tty);
+ if (ld) {
+ if (ld->ops->flush_buffer)
+ ld->ops->flush_buffer(tty);
+ tty_ldisc_deref(ld);
+ }
+ tty_buffer_flush(tty);
+}
+EXPORT_SYMBOL_GPL(tty_ldisc_flush);
+
/**
* tty_set_termios_ldisc - set ldisc field
* @tty: tty structure
mutex_unlock(&tty->termios_mutex);
}
+/**
+ * tty_ldisc_open - open a line discipline
+ * @tty: tty we are opening the ldisc on
+ * @ld: discipline to open
+ *
+ * A helper opening method. Also a convenient debugging and check
+ * point.
+ */
+
+static int tty_ldisc_open(struct tty_struct *tty, struct tty_ldisc *ld)
+{
+ WARN_ON(test_and_set_bit(TTY_LDISC_OPEN, &tty->flags));
+ if (ld->ops->open)
+ return ld->ops->open(tty);
+ return 0;
+}
+
+/**
+ * tty_ldisc_close - close a line discipline
+ * @tty: tty we are opening the ldisc on
+ * @ld: discipline to close
+ *
+ * A helper close method. Also a convenient debugging and check
+ * point.
+ */
+
+static void tty_ldisc_close(struct tty_struct *tty, struct tty_ldisc *ld)
+{
+ WARN_ON(!test_bit(TTY_LDISC_OPEN, &tty->flags));
+ clear_bit(TTY_LDISC_OPEN, &tty->flags);
+ if (ld->ops->close)
+ ld->ops->close(tty);
+}
/**
* tty_ldisc_restore - helper for tty ldisc change
static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
{
char buf[64];
- struct tty_ldisc new_ldisc;
+ struct tty_ldisc *new_ldisc;
+ int r;
/* There is an outstanding reference here so this is safe */
- tty_ldisc_get(old->ops->num, old);
+ old = tty_ldisc_get(old->ops->num);
+ WARN_ON(IS_ERR(old));
tty_ldisc_assign(tty, old);
tty_set_termios_ldisc(tty, old->ops->num);
- if (old->ops->open && (old->ops->open(tty) < 0)) {
- tty_ldisc_put(old->ops);
+ if (tty_ldisc_open(tty, old) < 0) {
+ tty_ldisc_put(old);
/* This driver is always present */
- if (tty_ldisc_get(N_TTY, &new_ldisc) < 0)
+ new_ldisc = tty_ldisc_get(N_TTY);
+ if (IS_ERR(new_ldisc))
panic("n_tty: get");
- tty_ldisc_assign(tty, &new_ldisc);
+ tty_ldisc_assign(tty, new_ldisc);
tty_set_termios_ldisc(tty, N_TTY);
- if (new_ldisc.ops->open) {
- int r = new_ldisc.ops->open(tty);
- if (r < 0)
- panic("Couldn't open N_TTY ldisc for "
- "%s --- error %d.",
- tty_name(tty, buf), r);
- }
+ r = tty_ldisc_open(tty, new_ldisc);
+ if (r < 0)
+ panic("Couldn't open N_TTY ldisc for "
+ "%s --- error %d.",
+ tty_name(tty, buf), r);
}
}
+/**
+ * tty_ldisc_halt - shut down the line discipline
+ * @tty: tty device
+ *
+ * Shut down the line discipline and work queue for this tty device.
+ * The TTY_LDISC flag being cleared ensures no further references can
+ * be obtained while the delayed work queue halt ensures that no more
+ * data is fed to the ldisc.
+ *
+ * In order to wait for any existing references to complete see
+ * tty_ldisc_wait_idle.
+ */
+
+static int tty_ldisc_halt(struct tty_struct *tty)
+{
+ clear_bit(TTY_LDISC, &tty->flags);
+ return cancel_delayed_work(&tty->buf.work);
+}
+
+/**
+ * tty_ldisc_wait_idle - wait for the ldisc to become idle
+ * @tty: tty to wait for
+ *
+ * Wait for the line discipline to become idle. The discipline must
+ * have been halted for this to guarantee it remains idle.
+ *
+ * tty_ldisc_lock protects the ref counts currently.
+ */
+
+static int tty_ldisc_wait_idle(struct tty_struct *tty)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ while (tty->ldisc->refcount) {
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ if (wait_event_timeout(tty_ldisc_wait,
+ tty->ldisc->refcount == 0, 5 * HZ) == 0)
+ return -EBUSY;
+ spin_lock_irqsave(&tty_ldisc_lock, flags);
+ }
+ spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+ return 0;
+}
+
/**
* tty_set_ldisc - set line discipline
* @tty: the terminal to set
* @ldisc: the line discipline
*
* Set the discipline of a tty line. Must be called from a process
- * context.
+ * context. The ldisc change logic has to protect itself against any
+ * overlapping ldisc change (including on the other end of pty pairs),
+ * the close of one side of a tty/pty pair, and eventually hangup.
*
- * Locking: takes tty_ldisc_lock.
- * called functions take termios_mutex
+ * Locking: takes tty_ldisc_lock, termios_mutex
*/
int tty_set_ldisc(struct tty_struct *tty, int ldisc)
{
int retval;
- struct tty_ldisc o_ldisc, new_ldisc;
- int work;
- unsigned long flags;
+ struct tty_ldisc *o_ldisc, *new_ldisc;
+ int work, o_work = 0;
struct tty_struct *o_tty;
-restart:
- /* This is a bit ugly for now but means we can break the 'ldisc
- is part of the tty struct' assumption later */
- retval = tty_ldisc_get(ldisc, &new_ldisc);
- if (retval)
- return retval;
+ new_ldisc = tty_ldisc_get(ldisc);
+ if (IS_ERR(new_ldisc))
+ return PTR_ERR(new_ldisc);
+
+ /*
+ * We need to look at the tty locking here for pty/tty pairs
+ * when both sides try to change in parallel.
+ */
+
+ o_tty = tty->link; /* o_tty is the pty side or NULL */
+
+
+ /*
+ * Check the no-op case
+ */
+
+ if (tty->ldisc->ops->num == ldisc) {
+ tty_ldisc_put(new_ldisc);
+ return 0;
+ }
/*
* Problem: What do we do if this blocks ?
+ * We could deadlock here
*/
tty_wait_until_sent(tty, 0);
- if (tty->ldisc.ops->num == ldisc) {
- tty_ldisc_put(new_ldisc.ops);
- return 0;
+ mutex_lock(&tty->ldisc_mutex);
+
+ /*
+ * We could be midstream of another ldisc change which has
+ * dropped the lock during processing. If so we need to wait.
+ */
+
+ while (test_bit(TTY_LDISC_CHANGING, &tty->flags)) {
+ mutex_unlock(&tty->ldisc_mutex);
+ wait_event(tty_ldisc_wait,
+ test_bit(TTY_LDISC_CHANGING, &tty->flags) == 0);
+ mutex_lock(&tty->ldisc_mutex);
}
+ set_bit(TTY_LDISC_CHANGING, &tty->flags);
/*
* No more input please, we are switching. The new ldisc
tty->receive_room = 0;
o_ldisc = tty->ldisc;
- o_tty = tty->link;
-
/*
* Make sure we don't change while someone holds a
* reference to the line discipline. The TTY_LDISC bit
* with a userspace app continually trying to use the tty in
* parallel to the change and re-referencing the tty.
*/
- clear_bit(TTY_LDISC, &tty->flags);
- if (o_tty)
- clear_bit(TTY_LDISC, &o_tty->flags);
- spin_lock_irqsave(&tty_ldisc_lock, flags);
- if (tty->ldisc.refcount || (o_tty && o_tty->ldisc.refcount)) {
- if (tty->ldisc.refcount) {
- /* Free the new ldisc we grabbed. Must drop the lock
- first. */
- spin_unlock_irqrestore(&tty_ldisc_lock, flags);
- tty_ldisc_put(o_ldisc.ops);
- /*
- * There are several reasons we may be busy, including
- * random momentary I/O traffic. We must therefore
- * retry. We could distinguish between blocking ops
- * and retries if we made tty_ldisc_wait() smarter.
- * That is up for discussion.
- */
- if (wait_event_interruptible(tty_ldisc_wait, tty->ldisc.refcount == 0) < 0)
- return -ERESTARTSYS;
- goto restart;
- }
- if (o_tty && o_tty->ldisc.refcount) {
- spin_unlock_irqrestore(&tty_ldisc_lock, flags);
- tty_ldisc_put(o_tty->ldisc.ops);
- if (wait_event_interruptible(tty_ldisc_wait, o_tty->ldisc.refcount == 0) < 0)
- return -ERESTARTSYS;
- goto restart;
- }
- }
- /*
- * If the TTY_LDISC bit is set, then we are racing against
- * another ldisc change
- */
- if (test_bit(TTY_LDISC_CHANGING, &tty->flags)) {
- struct tty_ldisc *ld;
- spin_unlock_irqrestore(&tty_ldisc_lock, flags);
- tty_ldisc_put(new_ldisc.ops);
- ld = tty_ldisc_ref_wait(tty);
- tty_ldisc_deref(ld);
- goto restart;
- }
- /*
- * This flag is used to avoid two parallel ldisc changes. Once
- * open and close are fine grained locked this may work better
- * as a mutex shared with the open/close/hup paths
- */
- set_bit(TTY_LDISC_CHANGING, &tty->flags);
+ work = tty_ldisc_halt(tty);
if (o_tty)
- set_bit(TTY_LDISC_CHANGING, &o_tty->flags);
- spin_unlock_irqrestore(&tty_ldisc_lock, flags);
-
- /*
- * From this point on we know nobody has an ldisc
- * usage reference, nor can they obtain one until
- * we say so later on.
- */
+ o_work = tty_ldisc_halt(o_tty);
- work = cancel_delayed_work(&tty->buf.work);
/*
- * Wait for ->hangup_work and ->buf.work handlers to terminate
- * MUST NOT hold locks here.
+ * Wait for ->hangup_work and ->buf.work handlers to terminate.
+ * We must drop the mutex here in case a hangup is also in process.
*/
+
+ mutex_unlock(&tty->ldisc_mutex);
+
flush_scheduled_work();
+
+ /* Let any existing reference holders finish */
+ retval = tty_ldisc_wait_idle(tty);
+ if (retval < 0) {
+ clear_bit(TTY_LDISC_CHANGING, &tty->flags);
+ tty_ldisc_put(new_ldisc);
+ return retval;
+ }
+
+ mutex_lock(&tty->ldisc_mutex);
+ if (test_bit(TTY_HUPPED, &tty->flags)) {
+ /* We were raced by the hangup method. It will have stomped
+ the ldisc data and closed the ldisc down */
+ clear_bit(TTY_LDISC_CHANGING, &tty->flags);
+ mutex_unlock(&tty->ldisc_mutex);
+ tty_ldisc_put(new_ldisc);
+ return -EIO;
+ }
+
/* Shutdown the current discipline. */
- if (o_ldisc.ops->close)
- (o_ldisc.ops->close)(tty);
+ tty_ldisc_close(tty, o_ldisc);
/* Now set up the new line discipline. */
- tty_ldisc_assign(tty, &new_ldisc);
+ tty_ldisc_assign(tty, new_ldisc);
tty_set_termios_ldisc(tty, ldisc);
- if (new_ldisc.ops->open)
- retval = (new_ldisc.ops->open)(tty);
+
+ retval = tty_ldisc_open(tty, new_ldisc);
if (retval < 0) {
- tty_ldisc_put(new_ldisc.ops);
- tty_ldisc_restore(tty, &o_ldisc);
+ /* Back to the old one or N_TTY if we can't */
+ tty_ldisc_put(new_ldisc);
+ tty_ldisc_restore(tty, o_ldisc);
}
+
/* At this point we hold a reference to the new ldisc and a
a reference to the old ldisc. If we ended up flipping back
to the existing ldisc we have two references to it */
- if (tty->ldisc.ops->num != o_ldisc.ops->num && tty->ops->set_ldisc)
+ if (tty->ldisc->ops->num != o_ldisc->ops->num && tty->ops->set_ldisc)
tty->ops->set_ldisc(tty);
- tty_ldisc_put(o_ldisc.ops);
+ tty_ldisc_put(o_ldisc);
/*
- * Allow ldisc referencing to occur as soon as the driver
- * ldisc callback completes.
+ * Allow ldisc referencing to occur again
*/
tty_ldisc_enable(tty);
if (o_tty)
tty_ldisc_enable(o_tty);
- /* Restart it in case no characters kick it off. Safe if
+ /* Restart the work queue in case no characters kick it off. Safe if
already running */
if (work)
schedule_delayed_work(&tty->buf.work, 1);
+ if (o_work)
+ schedule_delayed_work(&o_tty->buf.work, 1);
+ mutex_unlock(&tty->ldisc_mutex);
return retval;
}
+/**
+ * tty_reset_termios - reset terminal state
+ * @tty: tty to reset
+ *
+ * Restore a terminal to the driver default state.
+ */
+
+static void tty_reset_termios(struct tty_struct *tty)
+{
+ mutex_lock(&tty->termios_mutex);
+ *tty->termios = tty->driver->init_termios;
+ tty->termios->c_ispeed = tty_termios_input_baud_rate(tty->termios);
+ tty->termios->c_ospeed = tty_termios_baud_rate(tty->termios);
+ mutex_unlock(&tty->termios_mutex);
+}
+
+
+/**
+ * tty_ldisc_reinit - reinitialise the tty ldisc
+ * @tty: tty to reinit
+ *
+ * Switch the tty back to N_TTY line discipline and leave the
+ * ldisc state closed
+ */
+
+static void tty_ldisc_reinit(struct tty_struct *tty)
+{
+ struct tty_ldisc *ld;
+
+ tty_ldisc_close(tty, tty->ldisc);
+ tty_ldisc_put(tty->ldisc);
+ tty->ldisc = NULL;
+ /*
+ * Switch the line discipline back
+ */
+ ld = tty_ldisc_get(N_TTY);
+ BUG_ON(IS_ERR(ld));
+ tty_ldisc_assign(tty, ld);
+ tty_set_termios_ldisc(tty, N_TTY);
+}
+
+/**
+ * tty_ldisc_hangup - hangup ldisc reset
+ * @tty: tty being hung up
+ *
+ * Some tty devices reset their termios when they receive a hangup
+ * event. In that situation we must also switch back to N_TTY properly
+ * before we reset the termios data.
+ *
+ * Locking: We can take the ldisc mutex as the rest of the code is
+ * careful to allow for this.
+ *
+ * In the pty pair case this occurs in the close() path of the
+ * tty itself so we must be careful about locking rules.
+ */
+
+void tty_ldisc_hangup(struct tty_struct *tty)
+{
+ struct tty_ldisc *ld;
+
+ /*
+ * FIXME! What are the locking issues here? This may me overdoing
+ * things... This question is especially important now that we've
+ * removed the irqlock.
+ */
+ ld = tty_ldisc_ref(tty);
+ if (ld != NULL) {
+ /* We may have no line discipline at this point */
+ if (ld->ops->flush_buffer)
+ ld->ops->flush_buffer(tty);
+ tty_driver_flush_buffer(tty);
+ if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
+ ld->ops->write_wakeup)
+ ld->ops->write_wakeup(tty);
+ if (ld->ops->hangup)
+ ld->ops->hangup(tty);
+ tty_ldisc_deref(ld);
+ }
+ /*
+ * FIXME: Once we trust the LDISC code better we can wait here for
+ * ldisc completion and fix the driver call race
+ */
+ wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
+ wake_up_interruptible_poll(&tty->read_wait, POLLIN);
+ /*
+ * Shutdown the current line discipline, and reset it to
+ * N_TTY.
+ */
+ if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS) {
+ /* Avoid racing set_ldisc */
+ mutex_lock(&tty->ldisc_mutex);
+ /* Switch back to N_TTY */
+ tty_ldisc_reinit(tty);
+ /* At this point we have a closed ldisc and we want to
+ reopen it. We could defer this to the next open but
+ it means auditing a lot of other paths so this is a FIXME */
+ WARN_ON(tty_ldisc_open(tty, tty->ldisc));
+ tty_ldisc_enable(tty);
+ mutex_unlock(&tty->ldisc_mutex);
+ tty_reset_termios(tty);
+ }
+}
/**
* tty_ldisc_setup - open line discipline
* @o_tty: pair tty for pty/tty pairs
*
* Called during the initial open of a tty/pty pair in order to set up the
- * line discplines and bind them to the tty.
+ * line disciplines and bind them to the tty. This has no locking issues
+ * as the device isn't yet active.
*/
int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty)
{
- struct tty_ldisc *ld = &tty->ldisc;
+ struct tty_ldisc *ld = tty->ldisc;
int retval;
- if (ld->ops->open) {
- retval = (ld->ops->open)(tty);
- if (retval)
- return retval;
- }
- if (o_tty && o_tty->ldisc.ops->open) {
- retval = (o_tty->ldisc.ops->open)(o_tty);
+ retval = tty_ldisc_open(tty, ld);
+ if (retval)
+ return retval;
+
+ if (o_tty) {
+ retval = tty_ldisc_open(o_tty, o_tty->ldisc);
if (retval) {
- if (ld->ops->close)
- (ld->ops->close)(tty);
+ tty_ldisc_close(tty, ld);
return retval;
}
tty_ldisc_enable(o_tty);
tty_ldisc_enable(tty);
return 0;
}
-
/**
* tty_ldisc_release - release line discipline
* @tty: tty being shut down
* @o_tty: pair tty for pty/tty pairs
*
- * Called during the final close of a tty/pty pair in order to shut down the
- * line discpline layer.
+ * Called during the final close of a tty/pty pair in order to shut down
+ * the line discpline layer. On exit the ldisc assigned is N_TTY and the
+ * ldisc has not been opened.
*/
void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty)
{
- unsigned long flags;
- struct tty_ldisc ld;
/*
* Prevent flush_to_ldisc() from rescheduling the work for later. Then
* kill any delayed work. As this is the final close it does not
* race with the set_ldisc code path.
*/
- clear_bit(TTY_LDISC, &tty->flags);
- cancel_delayed_work(&tty->buf.work);
-
- /*
- * Wait for ->hangup_work and ->buf.work handlers to terminate
- */
+ tty_ldisc_halt(tty);
flush_scheduled_work();
/*
* side waiters as the file is closing so user count on the file
* side is zero.
*/
- spin_lock_irqsave(&tty_ldisc_lock, flags);
- while (tty->ldisc.refcount) {
- spin_unlock_irqrestore(&tty_ldisc_lock, flags);
- wait_event(tty_ldisc_wait, tty->ldisc.refcount == 0);
- spin_lock_irqsave(&tty_ldisc_lock, flags);
- }
- spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+
+ tty_ldisc_wait_idle(tty);
+
/*
* Shutdown the current line discipline, and reset it to N_TTY.
*
* FIXME: this MUST get fixed for the new reflocking
*/
- if (tty->ldisc.ops->close)
- (tty->ldisc.ops->close)(tty);
- tty_ldisc_put(tty->ldisc.ops);
- /*
- * Switch the line discipline back
- */
- WARN_ON(tty_ldisc_get(N_TTY, &ld));
- tty_ldisc_assign(tty, &ld);
- tty_set_termios_ldisc(tty, N_TTY);
- if (o_tty) {
- /* FIXME: could o_tty be in setldisc here ? */
- clear_bit(TTY_LDISC, &o_tty->flags);
- if (o_tty->ldisc.ops->close)
- (o_tty->ldisc.ops->close)(o_tty);
- tty_ldisc_put(o_tty->ldisc.ops);
- WARN_ON(tty_ldisc_get(N_TTY, &ld));
- tty_ldisc_assign(o_tty, &ld);
- tty_set_termios_ldisc(o_tty, N_TTY);
- }
+ tty_ldisc_reinit(tty);
+ /* This will need doing differently if we need to lock */
+ if (o_tty)
+ tty_ldisc_release(o_tty, NULL);
}
/**
void tty_ldisc_init(struct tty_struct *tty)
{
- struct tty_ldisc ld;
- if (tty_ldisc_get(N_TTY, &ld) < 0)
+ struct tty_ldisc *ld = tty_ldisc_get(N_TTY);
+ if (IS_ERR(ld))
panic("n_tty: init_tty");
- tty_ldisc_assign(tty, &ld);
+ tty_ldisc_assign(tty, ld);
}
void tty_ldisc_begin(void)
EXPORT_SYMBOL(tty_port_carrier_raised);
/**
- * tty_port_raise_dtr_rts - Riase DTR/RTS
+ * tty_port_raise_dtr_rts - Raise DTR/RTS
* @port: tty port
*
* Wrapper for the DTR/RTS raise logic. For the moment this is used
void tty_port_raise_dtr_rts(struct tty_port *port)
{
- if (port->ops->raise_dtr_rts)
- port->ops->raise_dtr_rts(port);
+ if (port->ops->dtr_rts)
+ port->ops->dtr_rts(port, 1);
}
EXPORT_SYMBOL(tty_port_raise_dtr_rts);
+/**
+ * tty_port_lower_dtr_rts - Lower DTR/RTS
+ * @port: tty port
+ *
+ * Wrapper for the DTR/RTS raise logic. For the moment this is used
+ * to hide some internal details. This will eventually become entirely
+ * internal to the tty port.
+ */
+
+void tty_port_lower_dtr_rts(struct tty_port *port)
+{
+ if (port->ops->dtr_rts)
+ port->ops->dtr_rts(port, 0);
+}
+EXPORT_SYMBOL(tty_port_lower_dtr_rts);
+
/**
* tty_port_block_til_ready - Waiting logic for tty open
* @port: the tty port being opened
* - port flags and counts
*
* The passed tty_port must implement the carrier_raised method if it can
- * do carrier detect and the raise_dtr_rts method if it supports software
+ * do carrier detect and the dtr_rts method if it supports software
* management of these lines. Note that the dtr/rts raise is done each
* iteration as a hangup may have previously dropped them while we wait.
*/
/* block if port is in the process of being closed */
if (tty_hung_up_p(filp) || port->flags & ASYNC_CLOSING) {
- interruptible_sleep_on(&port->close_wait);
+ wait_event_interruptible(port->close_wait,
+ !(port->flags & ASYNC_CLOSING));
if (port->flags & ASYNC_HUP_NOTIFY)
return -EAGAIN;
else
before the next open may complete */
retval = 0;
- add_wait_queue(&port->open_wait, &wait);
/* The port lock protects the port counts */
spin_lock_irqsave(&port->lock, flags);
if (tty->termios->c_cflag & CBAUD)
tty_port_raise_dtr_rts(port);
- set_current_state(TASK_INTERRUPTIBLE);
+ prepare_to_wait(&port->open_wait, &wait, TASK_INTERRUPTIBLE);
/* Check for a hangup or uninitialised port. Return accordingly */
if (tty_hung_up_p(filp) || !(port->flags & ASYNC_INITIALIZED)) {
if (port->flags & ASYNC_HUP_NOTIFY)
}
schedule();
}
- set_current_state(TASK_RUNNING);
- remove_wait_queue(&port->open_wait, &wait);
+ finish_wait(&port->open_wait, &wait);
/* Update counts. A parallel hangup will have set count to zero and
we must not mess that up further */
if (port->flags & ASYNC_INITIALIZED &&
port->closing_wait != ASYNC_CLOSING_WAIT_NONE)
tty_wait_until_sent(tty, port->closing_wait);
+ if (port->drain_delay) {
+ unsigned int bps = tty_get_baud_rate(tty);
+ long timeout;
+
+ if (bps > 1200)
+ timeout = max_t(long, (HZ * 10 * port->drain_delay) / bps,
+ HZ / 10);
+ else
+ timeout = 2 * HZ;
+ schedule_timeout_interruptible(timeout);
+ }
return 1;
}
EXPORT_SYMBOL(tty_port_close_start);
tty_ldisc_flush(tty);
+ if (tty->termios->c_cflag & HUPCL)
+ tty_port_lower_dtr_rts(port);
+
spin_lock_irqsave(&port->lock, flags);
tty->closing = 0;
return cbl;
}
-#if !defined(CONFIG_SPARC64) && !defined(CONFIG_PPC)
+#ifndef CONFIG_SPARC64
/**
* init_hwif_ali15x3 - Initialize the ALI IDE x86 stuff
* @hwif: interface to configure
*
* Obtain the IRQ tables for an ALi based IDE solution on the PC
* class platforms. This part of the code isn't applicable to the
- * Sparc and PowerPC systems.
+ * Sparc systems.
*/
static void __devinit init_hwif_ali15x3 (ide_hwif_t *hwif)
{
- struct pci_dev *dev = to_pci_dev(hwif->dev);
u8 ideic, inmir;
s8 irq_routing_table[] = { -1, 9, 3, 10, 4, 5, 7, 6,
1, 11, 0, 12, 0, 14, 0, 15 };
int irq = -1;
- if (dev->device == PCI_DEVICE_ID_AL_M5229)
- hwif->irq = hwif->channel ? 15 : 14;
-
if (isa_dev) {
/*
* read IDE interface control
}
#else
#define init_hwif_ali15x3 NULL
-#endif /* !defined(CONFIG_SPARC64) && !defined(CONFIG_PPC) */
+#endif /* CONFIG_SPARC64 */
/**
* init_dma_ali15x3 - set up DMA on ALi15x3
}
EXPORT_SYMBOL_GPL(ide_init_pc);
-/*
- * Generate a new packet command request in front of the request queue, before
- * the current request, so that it will be processed immediately, on the next
- * pass through the driver.
- */
-static void ide_queue_pc_head(ide_drive_t *drive, struct gendisk *disk,
- struct ide_atapi_pc *pc, struct request *rq)
-{
- blk_rq_init(NULL, rq);
- rq->cmd_type = REQ_TYPE_SPECIAL;
- rq->cmd_flags |= REQ_PREEMPT;
- rq->buffer = (char *)pc;
- rq->rq_disk = disk;
-
- if (pc->req_xfer) {
- rq->data = pc->buf;
- rq->data_len = pc->req_xfer;
- }
-
- memcpy(rq->cmd, pc->c, 12);
- if (drive->media == ide_tape)
- rq->cmd[13] = REQ_IDETAPE_PC1;
-
- drive->hwif->rq = NULL;
-
- elv_add_request(drive->queue, rq, ELEVATOR_INSERT_FRONT, 0);
-}
-
/*
* Add a special packet command request to the tail of the request queue,
* and wait for it to be serviced.
rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
rq->cmd_type = REQ_TYPE_SPECIAL;
- rq->buffer = (char *)pc;
+ rq->special = (char *)pc;
if (pc->req_xfer) {
- rq->data = pc->buf;
- rq->data_len = pc->req_xfer;
+ error = blk_rq_map_kern(drive->queue, rq, pc->buf, pc->req_xfer,
+ GFP_NOIO);
+ if (error)
+ goto put_req;
}
memcpy(rq->cmd, pc->c, 12);
if (drive->media == ide_tape)
rq->cmd[13] = REQ_IDETAPE_PC1;
error = blk_execute_rq(drive->queue, disk, rq, 0);
+put_req:
blk_put_request(rq);
-
return error;
}
EXPORT_SYMBOL_GPL(ide_queue_pc_tail);
}
EXPORT_SYMBOL_GPL(ide_create_request_sense_cmd);
+void ide_prep_sense(ide_drive_t *drive, struct request *rq)
+{
+ struct request_sense *sense = &drive->sense_data;
+ struct request *sense_rq = &drive->sense_rq;
+ unsigned int cmd_len, sense_len;
+ int err;
+
+ debug_log("%s: enter\n", __func__);
+
+ switch (drive->media) {
+ case ide_floppy:
+ cmd_len = 255;
+ sense_len = 18;
+ break;
+ case ide_tape:
+ cmd_len = 20;
+ sense_len = 20;
+ break;
+ default:
+ cmd_len = 18;
+ sense_len = 18;
+ }
+
+ BUG_ON(sense_len > sizeof(*sense));
+
+ if (blk_sense_request(rq) || drive->sense_rq_armed)
+ return;
+
+ memset(sense, 0, sizeof(*sense));
+
+ blk_rq_init(rq->q, sense_rq);
+
+ err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
+ GFP_NOIO);
+ if (unlikely(err)) {
+ if (printk_ratelimit())
+ printk(KERN_WARNING "%s: failed to map sense buffer\n",
+ drive->name);
+ return;
+ }
+
+ sense_rq->rq_disk = rq->rq_disk;
+ sense_rq->cmd[0] = GPCMD_REQUEST_SENSE;
+ sense_rq->cmd[4] = cmd_len;
+ sense_rq->cmd_type = REQ_TYPE_SENSE;
+ sense_rq->cmd_flags |= REQ_PREEMPT;
+
+ if (drive->media == ide_tape)
+ sense_rq->cmd[13] = REQ_IDETAPE_PC1;
+
+ drive->sense_rq_armed = true;
+}
+EXPORT_SYMBOL_GPL(ide_prep_sense);
+
+int ide_queue_sense_rq(ide_drive_t *drive, void *special)
+{
+ /* deferred failure from ide_prep_sense() */
+ if (!drive->sense_rq_armed) {
+ printk(KERN_WARNING "%s: failed queue sense request\n",
+ drive->name);
+ return -ENOMEM;
+ }
+
+ drive->sense_rq.special = special;
+ drive->sense_rq_armed = false;
+
+ drive->hwif->rq = NULL;
+
+ elv_add_request(drive->queue, &drive->sense_rq,
+ ELEVATOR_INSERT_FRONT, 0);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
+
/*
* Called when an error was detected during the last packet command.
- * We queue a request sense packet command in the head of the request list.
+ * We queue a request sense packet command at the head of the request
+ * queue.
*/
-void ide_retry_pc(ide_drive_t *drive, struct gendisk *disk)
+void ide_retry_pc(ide_drive_t *drive)
{
- struct request *rq = &drive->request_sense_rq;
+ struct request *sense_rq = &drive->sense_rq;
struct ide_atapi_pc *pc = &drive->request_sense_pc;
(void)ide_read_error(drive);
- ide_create_request_sense_cmd(drive, pc);
+
+ /* init pc from sense_rq */
+ ide_init_pc(pc);
+ memcpy(pc->c, sense_rq->cmd, 12);
+ pc->buf = bio_data(sense_rq->bio); /* pointer to mapped address */
+ pc->req_xfer = sense_rq->data_len;
+
if (drive->media == ide_tape)
set_bit(IDE_AFLAG_IGNORE_DSC, &drive->atapi_flags);
- ide_queue_pc_head(drive, disk, pc, rq);
+
+ if (ide_queue_sense_rq(drive, pc))
+ ide_complete_rq(drive, -EIO, blk_rq_bytes(drive->hwif->rq));
}
EXPORT_SYMBOL_GPL(ide_retry_pc);
struct ide_cmd *cmd = &hwif->cmd;
struct request *rq = hwif->rq;
const struct ide_tp_ops *tp_ops = hwif->tp_ops;
- xfer_func_t *xferfunc;
unsigned int timeout, done;
u16 bcount;
u8 stat, ireason, dsc = 0;
drive->name, rq_data_dir(pc->rq)
? "write" : "read");
pc->flags |= PC_FLAG_DMA_ERROR;
- } else {
+ } else
pc->xferred = pc->req_xfer;
- if (drive->pc_update_buffers)
- drive->pc_update_buffers(drive, pc);
- }
debug_log("%s: DMA finished\n", drive->name);
}
debug_log("[cmd %x]: check condition\n", rq->cmd[0]);
/* Retry operation */
- ide_retry_pc(drive, rq->rq_disk);
+ ide_retry_pc(drive);
/* queued, but not started */
return ide_stopped;
if ((pc->flags & PC_FLAG_WAIT_FOR_DSC) && (stat & ATA_DSC) == 0)
dsc = 1;
+ /*
+ * ->pc_callback() might change rq->data_len for
+ * residual count, cache total length.
+ */
+ done = blk_rq_bytes(rq);
+
/* Command finished - Call the callback function */
uptodate = drive->pc_callback(drive, dsc);
if (blk_special_request(rq)) {
rq->errors = 0;
- done = blk_rq_bytes(rq);
error = 0;
} else {
rq->errors = -EIO;
}
- if (drive->media == ide_tape)
- done = ide_rq_bytes(rq); /* FIXME */
- else
- done = blk_rq_bytes(rq);
-
error = uptodate ? 0 : -EIO;
}
return ide_do_reset(drive);
}
- xferfunc = write ? tp_ops->output_data : tp_ops->input_data;
-
- if (drive->media == ide_floppy && pc->buf == NULL) {
- done = min_t(unsigned int, bcount, cmd->nleft);
- ide_pio_bytes(drive, cmd, write, done);
- } else if (drive->media == ide_tape && pc->bh) {
- done = drive->pc_io_buffers(drive, pc, bcount, write);
- } else {
- done = min_t(unsigned int, bcount, pc->req_xfer - pc->xferred);
- xferfunc(drive, NULL, pc->cur_pos, done);
- }
+ done = min_t(unsigned int, bcount, cmd->nleft);
+ ide_pio_bytes(drive, cmd, write, done);
- /* Update the current position */
+ /* Update transferred byte count */
pc->xferred += done;
- pc->cur_pos += done;
bcount -= done;
/* We haven't transferred any data yet */
pc->xferred = 0;
- pc->cur_pos = pc->buf;
valid_tf = IDE_VALID_DEVICE;
bcount = ((drive->media == ide_tape) ?
ide_cd_log_error(drive->name, failed_command, sense);
}
-static void cdrom_queue_request_sense(ide_drive_t *drive, void *sense,
- struct request *failed_command)
-{
- struct cdrom_info *info = drive->driver_data;
- struct request *rq = &drive->request_sense_rq;
-
- ide_debug_log(IDE_DBG_SENSE, "enter");
-
- if (sense == NULL)
- sense = &info->sense_data;
-
- /* stuff the sense request in front of our current request */
- blk_rq_init(NULL, rq);
- rq->cmd_type = REQ_TYPE_ATA_PC;
- rq->rq_disk = info->disk;
-
- rq->data = sense;
- rq->cmd[0] = GPCMD_REQUEST_SENSE;
- rq->cmd[4] = 18;
- rq->data_len = 18;
-
- rq->cmd_type = REQ_TYPE_SENSE;
- rq->cmd_flags |= REQ_PREEMPT;
-
- /* NOTE! Save the failed command in "rq->buffer" */
- rq->buffer = (void *) failed_command;
-
- if (failed_command)
- ide_debug_log(IDE_DBG_SENSE, "failed_cmd: 0x%x",
- failed_command->cmd[0]);
-
- drive->hwif->rq = NULL;
-
- elv_add_request(drive->queue, rq, ELEVATOR_INSERT_FRONT, 0);
-}
-
static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
{
/*
- * For REQ_TYPE_SENSE, "rq->buffer" points to the original
- * failed request
+ * For REQ_TYPE_SENSE, "rq->special" points to the original
+ * failed request. Also, the sense data should be read
+ * directly from rq which might be different from the original
+ * sense buffer if it got copied during mapping.
*/
- struct request *failed = (struct request *)rq->buffer;
- struct cdrom_info *info = drive->driver_data;
- void *sense = &info->sense_data;
+ struct request *failed = (struct request *)rq->special;
+ void *sense = bio_data(rq->bio);
if (failed) {
if (failed->sense) {
+ /*
+ * Sense is always read into drive->sense_data.
+ * Copy back if the failed request has its
+ * sense pointer set.
+ */
+ memcpy(failed->sense, sense, 18);
sense = failed->sense;
failed->sense_len = rq->sense_len;
}
/* if we got a CHECK_CONDITION status, queue a request sense command */
if (stat & ATA_ERR)
- cdrom_queue_request_sense(drive, NULL, NULL);
+ return ide_queue_sense_rq(drive, NULL) ? 2 : 1;
return 1;
end_request:
hwif->rq = NULL;
- cdrom_queue_request_sense(drive, rq->sense, rq);
- return 1;
+ return ide_queue_sense_rq(drive, rq) ? 2 : 1;
} else
return 2;
}
* and some drives don't send them. Sigh.
*/
if (rq->cmd[0] == GPCMD_REQUEST_SENSE &&
- cmd->nleft > 0 && cmd->nleft <= 5) {
- unsigned int ofs = cmd->nbytes - cmd->nleft;
-
- while (cmd->nleft > 0) {
- *((u8 *)rq->data + ofs++) = 0;
- cmd->nleft--;
- }
- }
+ cmd->nleft > 0 && cmd->nleft <= 5)
+ cmd->nleft = 0;
}
int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
rq->cmd_flags |= cmd_flags;
rq->timeout = timeout;
if (buffer) {
- rq->data = buffer;
- rq->data_len = *bufflen;
+ error = blk_rq_map_kern(drive->queue, rq, buffer,
+ *bufflen, GFP_NOIO);
+ if (error) {
+ blk_put_request(rq);
+ return error;
+ }
}
error = blk_execute_rq(drive->queue, info->disk, rq, 0);
drive->dma = 0;
/* sg request */
- if (rq->bio || ((rq->cmd_type == REQ_TYPE_ATA_PC) && rq->data_len)) {
+ if (rq->bio) {
struct request_queue *q = drive->queue;
+ char *buf = bio_data(rq->bio);
unsigned int alignment;
- char *buf;
-
- if (rq->bio)
- buf = bio_data(rq->bio);
- else
- buf = rq->data;
drive->dma = !!(drive->dev_flags & IDE_DFLAG_USING_DMA);
goto out_end;
}
+ /* prepare sense request for this command */
+ ide_prep_sense(drive, rq);
+
memset(&cmd, 0, sizeof(cmd));
if (rq_data_dir(rq))
struct atapi_toc *toc;
- /* The result of the last successful request sense command
- on this device. */
- struct request_sense sense_data;
-
u8 max_speed; /* Max speed of the drive. */
u8 current_speed; /* Current speed of the drive. */
cmd->protocol = ATA_PROT_NODATA;
rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
- rq->cmd_flags |= REQ_SOFTBARRIER;
rq->special = cmd;
}
/*
* un-busy drive etc and make sure request is sane
*/
-
rq = hwif->rq;
- if (!rq)
- goto out;
-
- hwif->rq = NULL;
-
- rq->errors = 0;
-
- if (!rq->bio)
- goto out;
-
- rq->sector = rq->bio->bi_sector;
- rq->current_nr_sectors = bio_iovec(rq->bio)->bv_len >> 9;
- rq->hard_cur_sectors = rq->current_nr_sectors;
- rq->buffer = bio_data(rq->bio);
-out:
+ if (rq) {
+ hwif->rq = NULL;
+ rq->errors = 0;
+ }
return ret;
}
drive->pc = pc;
if (pc->retries > IDEFLOPPY_MAX_PC_RETRIES) {
+ unsigned int done = blk_rq_bytes(drive->hwif->rq);
+
if (!(pc->flags & PC_FLAG_SUPPRESS_ERROR))
ide_floppy_report_error(floppy, pc);
+
/* Giving up */
pc->error = IDE_DRV_ERROR_GENERAL;
drive->failed_pc = NULL;
drive->pc_callback(drive, 0);
+ ide_complete_rq(drive, -EIO, done);
return ide_stopped;
}
ide_init_pc(pc);
memcpy(pc->c, rq->cmd, sizeof(pc->c));
pc->rq = rq;
- if (rq->data_len && rq_data_dir(rq) == WRITE)
- pc->flags |= PC_FLAG_WRITING;
- pc->buf = rq->data;
- if (rq->bio)
+ if (rq->data_len) {
pc->flags |= PC_FLAG_DMA_OK;
- /*
- * possibly problematic, doesn't look like ide-floppy correctly
- * handled scattered requests if dma fails...
- */
+ if (rq_data_dir(rq) == WRITE)
+ pc->flags |= PC_FLAG_WRITING;
+ }
+ /* pio will be performed by ide_pio_bytes() which handles sg fine */
+ pc->buf = NULL;
pc->req_xfer = pc->buf_size = rq->data_len;
}
}
pc = &floppy->queued_pc;
idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block);
- } else if (blk_special_request(rq)) {
- pc = (struct ide_atapi_pc *) rq->buffer;
+ } else if (blk_special_request(rq) || blk_sense_request(rq)) {
+ pc = (struct ide_atapi_pc *)rq->special;
} else if (blk_pc_request(rq)) {
pc = &floppy->queued_pc;
idefloppy_blockpc_cmd(floppy, pc, rq);
goto out_end;
}
+ ide_prep_sense(drive, rq);
+
memset(&cmd, 0, sizeof(cmd));
if (rq_data_dir(rq))
struct scatterlist *sg = hwif->sg_table;
struct request *rq = cmd->rq;
- if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE) {
- sg_init_one(sg, rq->buffer, rq->nr_sectors * SECTOR_SIZE);
- cmd->sg_nents = 1;
- } else if (!rq->bio) {
- sg_init_one(sg, rq->data, rq->data_len);
- cmd->sg_nents = 1;
- } else
- cmd->sg_nents = blk_rq_map_sg(drive->queue, rq, sg);
+ cmd->sg_nents = blk_rq_map_sg(drive->queue, rq, sg);
}
EXPORT_SYMBOL_GPL(ide_map_sg);
if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE)
return execute_drive_cmd(drive, rq);
else if (blk_pm_request(rq)) {
- struct request_pm_state *pm = rq->data;
+ struct request_pm_state *pm = rq->special;
#ifdef DEBUG_PM
printk("%s: start_power_step(step: %d)\n",
drive->name, pm->pm_step);
spin_unlock_irq(q->queue_lock);
+ /* HLD do_request() callback might sleep, make sure it's okay */
+ might_sleep();
+
if (ide_lock_host(host, hwif))
goto plug_device_2;
rq->cmd_type = REQ_TYPE_SPECIAL;
rq->cmd_len = 1;
rq->cmd[0] = REQ_DRIVE_RESET;
- rq->cmd_flags |= REQ_SOFTBARRIER;
if (blk_execute_rq(drive->queue, NULL, rq, 1))
ret = rq->errors;
blk_put_request(rq);
start_queue = 1;
spin_unlock_irq(&hwif->lock);
- if (start_queue) {
- spin_lock_irq(q->queue_lock);
- blk_start_queueing(q);
- spin_unlock_irq(q->queue_lock);
- }
+ if (start_queue)
+ blk_run_queue(q);
return;
}
spin_unlock_irq(&hwif->lock);
ide_hwif_t *hwif = drive->hwif;
struct request *rq;
struct request_pm_state rqpm;
- struct ide_cmd cmd;
int ret;
/* call ACPI _GTM only once */
ide_acpi_get_timing(hwif);
memset(&rqpm, 0, sizeof(rqpm));
- memset(&cmd, 0, sizeof(cmd));
rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
rq->cmd_type = REQ_TYPE_PM_SUSPEND;
- rq->special = &cmd;
- rq->data = &rqpm;
+ rq->special = &rqpm;
rqpm.pm_step = IDE_PM_START_SUSPEND;
if (mesg.event == PM_EVENT_PRETHAW)
mesg.event = PM_EVENT_FREEZE;
ide_hwif_t *hwif = drive->hwif;
struct request *rq;
struct request_pm_state rqpm;
- struct ide_cmd cmd;
int err;
/* call ACPI _PS0 / _STM only once */
ide_acpi_exec_tfs(drive);
memset(&rqpm, 0, sizeof(rqpm));
- memset(&cmd, 0, sizeof(cmd));
rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
rq->cmd_type = REQ_TYPE_PM_RESUME;
rq->cmd_flags |= REQ_PREEMPT;
- rq->special = &cmd;
- rq->data = &rqpm;
+ rq->special = &rqpm;
rqpm.pm_step = IDE_PM_START_RESUME;
rqpm.pm_state = PM_EVENT_ON;
void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
{
- struct request_pm_state *pm = rq->data;
+ struct request_pm_state *pm = rq->special;
#ifdef DEBUG_PM
printk(KERN_INFO "%s: complete_power_step(step: %d)\n",
ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
{
- struct request_pm_state *pm = rq->data;
- struct ide_cmd *cmd = rq->special;
-
- memset(cmd, 0, sizeof(*cmd));
+ struct request_pm_state *pm = rq->special;
+ struct ide_cmd cmd = { };
switch (pm->pm_step) {
case IDE_PM_FLUSH_CACHE: /* Suspend step 1 (flush cache) */
return ide_stopped;
}
if (ata_id_flush_ext_enabled(drive->id))
- cmd->tf.command = ATA_CMD_FLUSH_EXT;
+ cmd.tf.command = ATA_CMD_FLUSH_EXT;
else
- cmd->tf.command = ATA_CMD_FLUSH;
+ cmd.tf.command = ATA_CMD_FLUSH;
goto out_do_tf;
case IDE_PM_STANDBY: /* Suspend step 2 (standby) */
- cmd->tf.command = ATA_CMD_STANDBYNOW1;
+ cmd.tf.command = ATA_CMD_STANDBYNOW1;
goto out_do_tf;
case IDE_PM_RESTORE_PIO: /* Resume step 1 (restore PIO) */
ide_set_max_pio(drive);
ide_complete_power_step(drive, rq);
return ide_stopped;
case IDE_PM_IDLE: /* Resume step 2 (idle) */
- cmd->tf.command = ATA_CMD_IDLEIMMEDIATE;
+ cmd.tf.command = ATA_CMD_IDLEIMMEDIATE;
goto out_do_tf;
case IDE_PM_RESTORE_DMA: /* Resume step 3 (restore DMA) */
/*
return ide_stopped;
out_do_tf:
- cmd->valid.out.tf = IDE_VALID_OUT_TF | IDE_VALID_DEVICE;
- cmd->valid.in.tf = IDE_VALID_IN_TF | IDE_VALID_DEVICE;
- cmd->protocol = ATA_PROT_NODATA;
+ cmd.valid.out.tf = IDE_VALID_OUT_TF | IDE_VALID_DEVICE;
+ cmd.valid.in.tf = IDE_VALID_IN_TF | IDE_VALID_DEVICE;
+ cmd.protocol = ATA_PROT_NODATA;
- return do_rw_taskfile(drive, cmd);
+ return do_rw_taskfile(drive, &cmd);
}
/**
void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
{
struct request_queue *q = drive->queue;
- struct request_pm_state *pm = rq->data;
+ struct request_pm_state *pm = rq->special;
unsigned long flags;
ide_complete_power_step(drive, rq);
void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
{
- struct request_pm_state *pm = rq->data;
+ struct request_pm_state *pm = rq->special;
if (blk_pm_suspend_request(rq) &&
pm->pm_step == IDE_PM_START_SUSPEND)
IDETAPE_DIR_WRITE = (1 << 2),
};
-struct idetape_bh {
- u32 b_size;
- atomic_t b_count;
- struct idetape_bh *b_reqnext;
- char *b_data;
-};
-
/* Tape door status */
#define DOOR_UNLOCKED 0
#define DOOR_LOCKED 1
/* Data buffer size chosen based on the tape's recommendation */
int buffer_size;
- /* merge buffer */
- struct idetape_bh *merge_bh;
- /* size of the merge buffer */
- int merge_bh_size;
- /* pointer to current buffer head within the merge buffer */
- struct idetape_bh *bh;
- char *b_data;
- int b_count;
-
- int pages_per_buffer;
- /* Wasted space in each stage */
- int excess_bh_size;
+ /* Staging buffer of buffer_size bytes */
+ void *buf;
+ /* The read/write cursor */
+ void *cur;
+ /* The number of valid bytes in buf */
+ size_t valid;
/* Measures average tape speed */
unsigned long avg_time;
return tape;
}
-static int idetape_input_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
- unsigned int bcount)
-{
- struct idetape_bh *bh = pc->bh;
- int count;
-
- while (bcount) {
- if (bh == NULL)
- break;
- count = min(
- (unsigned int)(bh->b_size - atomic_read(&bh->b_count)),
- bcount);
- drive->hwif->tp_ops->input_data(drive, NULL, bh->b_data +
- atomic_read(&bh->b_count), count);
- bcount -= count;
- atomic_add(count, &bh->b_count);
- if (atomic_read(&bh->b_count) == bh->b_size) {
- bh = bh->b_reqnext;
- if (bh)
- atomic_set(&bh->b_count, 0);
- }
- }
-
- pc->bh = bh;
-
- return bcount;
-}
-
-static int idetape_output_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
- unsigned int bcount)
-{
- struct idetape_bh *bh = pc->bh;
- int count;
-
- while (bcount) {
- if (bh == NULL)
- break;
- count = min((unsigned int)pc->b_count, (unsigned int)bcount);
- drive->hwif->tp_ops->output_data(drive, NULL, pc->b_data, count);
- bcount -= count;
- pc->b_data += count;
- pc->b_count -= count;
- if (!pc->b_count) {
- bh = bh->b_reqnext;
- pc->bh = bh;
- if (bh) {
- pc->b_data = bh->b_data;
- pc->b_count = atomic_read(&bh->b_count);
- }
- }
- }
-
- return bcount;
-}
-
-static void idetape_update_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc)
-{
- struct idetape_bh *bh = pc->bh;
- int count;
- unsigned int bcount = pc->xferred;
-
- if (pc->flags & PC_FLAG_WRITING)
- return;
- while (bcount) {
- if (bh == NULL) {
- printk(KERN_ERR "ide-tape: bh == NULL in %s\n",
- __func__);
- return;
- }
- count = min((unsigned int)bh->b_size, (unsigned int)bcount);
- atomic_set(&bh->b_count, count);
- if (atomic_read(&bh->b_count) == bh->b_size)
- bh = bh->b_reqnext;
- bcount -= count;
- }
- pc->bh = bh;
-}
-
/*
* called on each failed packet command retry to analyze the request sense. We
* currently do not utilize this information.
pc->c[0], tape->sense_key, tape->asc, tape->ascq);
/* Correct pc->xferred by asking the tape. */
- if (pc->flags & PC_FLAG_DMA_ERROR) {
+ if (pc->flags & PC_FLAG_DMA_ERROR)
pc->xferred = pc->req_xfer -
tape->blk_size *
get_unaligned_be32(&sense[3]);
- idetape_update_buffers(drive, pc);
- }
/*
* If error was the result of a zero-length read or write command,
}
}
-/* Free data buffers completely. */
-static void ide_tape_kfree_buffer(idetape_tape_t *tape)
-{
- struct idetape_bh *prev_bh, *bh = tape->merge_bh;
-
- while (bh) {
- u32 size = bh->b_size;
-
- while (size) {
- unsigned int order = fls(size >> PAGE_SHIFT)-1;
-
- if (bh->b_data)
- free_pages((unsigned long)bh->b_data, order);
-
- size &= (order-1);
- bh->b_data += (1 << order) * PAGE_SIZE;
- }
- prev_bh = bh;
- bh = bh->b_reqnext;
- kfree(prev_bh);
- }
-}
-
static void ide_tape_handle_dsc(ide_drive_t *);
static int ide_tape_callback(ide_drive_t *drive, int dsc)
}
tape->first_frame += blocks;
- rq->current_nr_sectors -= blocks;
+ rq->data_len -= blocks * tape->blk_size;
if (pc->error) {
uptodate = 0;
idetape_postpone_request(drive);
}
-static int ide_tape_io_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
- unsigned int bcount, int write)
-{
- unsigned int bleft;
-
- if (write)
- bleft = idetape_output_buffers(drive, pc, bcount);
- else
- bleft = idetape_input_buffers(drive, pc, bcount);
-
- return bcount - bleft;
-}
-
/*
* Packet Command Interface
*
if (pc->retries > IDETAPE_MAX_PC_RETRIES ||
(pc->flags & PC_FLAG_ABORT)) {
+ unsigned int done = blk_rq_bytes(drive->hwif->rq);
+
/*
* We will "abort" retrying a packet command in case legitimate
* error code was received (crossing a filemark, or end of the
/* Giving up */
pc->error = IDE_DRV_ERROR_GENERAL;
}
+
drive->failed_pc = NULL;
drive->pc_callback(drive, 0);
+ ide_complete_rq(drive, -EIO, done);
return ide_stopped;
}
debug_log(DBG_SENSE, "Retry #%d, cmd = %02X\n", pc->retries, pc->c[0]);
printk(KERN_ERR "ide-tape: %s: I/O error, ",
tape->name);
/* Retry operation */
- ide_retry_pc(drive, tape->disk);
+ ide_retry_pc(drive);
return ide_stopped;
}
pc->error = 0;
struct ide_atapi_pc *pc, struct request *rq,
u8 opcode)
{
- struct idetape_bh *bh = (struct idetape_bh *)rq->special;
- unsigned int length = rq->current_nr_sectors;
+ unsigned int length = rq->nr_sectors;
ide_init_pc(pc);
put_unaligned(cpu_to_be32(length), (unsigned int *) &pc->c[1]);
pc->c[1] = 1;
- pc->bh = bh;
pc->buf = NULL;
pc->buf_size = length * tape->blk_size;
pc->req_xfer = pc->buf_size;
if (pc->req_xfer == tape->buffer_size)
pc->flags |= PC_FLAG_DMA_OK;
- if (opcode == READ_6) {
+ if (opcode == READ_6)
pc->c[0] = READ_6;
- atomic_set(&bh->b_count, 0);
- } else if (opcode == WRITE_6) {
+ else if (opcode == WRITE_6) {
pc->c[0] = WRITE_6;
pc->flags |= PC_FLAG_WRITING;
- pc->b_data = bh->b_data;
- pc->b_count = atomic_read(&bh->b_count);
}
memcpy(rq->cmd, pc->c, 12);
struct ide_cmd cmd;
u8 stat;
- debug_log(DBG_SENSE, "sector: %llu, nr_sectors: %lu,"
- " current_nr_sectors: %u\n",
- (unsigned long long)rq->sector, rq->nr_sectors,
- rq->current_nr_sectors);
+ debug_log(DBG_SENSE, "sector: %llu, nr_sectors: %lu\n",
+ (unsigned long long)rq->sector, rq->nr_sectors);
- if (!blk_special_request(rq)) {
+ if (!(blk_special_request(rq) || blk_sense_request(rq))) {
/* We do not support buffer cache originated requests. */
printk(KERN_NOTICE "ide-tape: %s: Unsupported request in "
"request queue (%d)\n", drive->name, rq->cmd_type);
goto out;
}
if (rq->cmd[13] & REQ_IDETAPE_PC1) {
- pc = (struct ide_atapi_pc *) rq->buffer;
+ pc = (struct ide_atapi_pc *)rq->special;
rq->cmd[13] &= ~(REQ_IDETAPE_PC1);
rq->cmd[13] |= REQ_IDETAPE_PC2;
goto out;
BUG();
out:
+ /* prepare sense request for this command */
+ ide_prep_sense(drive, rq);
+
memset(&cmd, 0, sizeof(cmd));
if (rq_data_dir(rq))
cmd.rq = rq;
- return ide_tape_issue_pc(drive, &cmd, pc);
-}
-
-/*
- * The function below uses __get_free_pages to allocate a data buffer of size
- * tape->buffer_size (or a bit more). We attempt to combine sequential pages as
- * much as possible.
- *
- * It returns a pointer to the newly allocated buffer, or NULL in case of
- * failure.
- */
-static struct idetape_bh *ide_tape_kmalloc_buffer(idetape_tape_t *tape,
- int full, int clear)
-{
- struct idetape_bh *prev_bh, *bh, *merge_bh;
- int pages = tape->pages_per_buffer;
- unsigned int order, b_allocd;
- char *b_data = NULL;
-
- merge_bh = kmalloc(sizeof(struct idetape_bh), GFP_KERNEL);
- bh = merge_bh;
- if (bh == NULL)
- goto abort;
-
- order = fls(pages) - 1;
- bh->b_data = (char *) __get_free_pages(GFP_KERNEL, order);
- if (!bh->b_data)
- goto abort;
- b_allocd = (1 << order) * PAGE_SIZE;
- pages &= (order-1);
-
- if (clear)
- memset(bh->b_data, 0, b_allocd);
- bh->b_reqnext = NULL;
- bh->b_size = b_allocd;
- atomic_set(&bh->b_count, full ? bh->b_size : 0);
-
- while (pages) {
- order = fls(pages) - 1;
- b_data = (char *) __get_free_pages(GFP_KERNEL, order);
- if (!b_data)
- goto abort;
- b_allocd = (1 << order) * PAGE_SIZE;
-
- if (clear)
- memset(b_data, 0, b_allocd);
-
- /* newly allocated page frames below buffer header or ...*/
- if (bh->b_data == b_data + b_allocd) {
- bh->b_size += b_allocd;
- bh->b_data -= b_allocd;
- if (full)
- atomic_add(b_allocd, &bh->b_count);
- continue;
- }
- /* they are above the header */
- if (b_data == bh->b_data + bh->b_size) {
- bh->b_size += b_allocd;
- if (full)
- atomic_add(b_allocd, &bh->b_count);
- continue;
- }
- prev_bh = bh;
- bh = kmalloc(sizeof(struct idetape_bh), GFP_KERNEL);
- if (!bh) {
- free_pages((unsigned long) b_data, order);
- goto abort;
- }
- bh->b_reqnext = NULL;
- bh->b_data = b_data;
- bh->b_size = b_allocd;
- atomic_set(&bh->b_count, full ? bh->b_size : 0);
- prev_bh->b_reqnext = bh;
-
- pages &= (order-1);
- }
-
- bh->b_size -= tape->excess_bh_size;
- if (full)
- atomic_sub(tape->excess_bh_size, &bh->b_count);
- return merge_bh;
-abort:
- ide_tape_kfree_buffer(tape);
- return NULL;
-}
+ ide_init_sg_cmd(&cmd, pc->req_xfer);
+ ide_map_sg(drive, &cmd);
-static int idetape_copy_stage_from_user(idetape_tape_t *tape,
- const char __user *buf, int n)
-{
- struct idetape_bh *bh = tape->bh;
- int count;
- int ret = 0;
-
- while (n) {
- if (bh == NULL) {
- printk(KERN_ERR "ide-tape: bh == NULL in %s\n",
- __func__);
- return 1;
- }
- count = min((unsigned int)
- (bh->b_size - atomic_read(&bh->b_count)),
- (unsigned int)n);
- if (copy_from_user(bh->b_data + atomic_read(&bh->b_count), buf,
- count))
- ret = 1;
- n -= count;
- atomic_add(count, &bh->b_count);
- buf += count;
- if (atomic_read(&bh->b_count) == bh->b_size) {
- bh = bh->b_reqnext;
- if (bh)
- atomic_set(&bh->b_count, 0);
- }
- }
- tape->bh = bh;
- return ret;
-}
-
-static int idetape_copy_stage_to_user(idetape_tape_t *tape, char __user *buf,
- int n)
-{
- struct idetape_bh *bh = tape->bh;
- int count;
- int ret = 0;
-
- while (n) {
- if (bh == NULL) {
- printk(KERN_ERR "ide-tape: bh == NULL in %s\n",
- __func__);
- return 1;
- }
- count = min(tape->b_count, n);
- if (copy_to_user(buf, tape->b_data, count))
- ret = 1;
- n -= count;
- tape->b_data += count;
- tape->b_count -= count;
- buf += count;
- if (!tape->b_count) {
- bh = bh->b_reqnext;
- tape->bh = bh;
- if (bh) {
- tape->b_data = bh->b_data;
- tape->b_count = atomic_read(&bh->b_count);
- }
- }
- }
- return ret;
-}
-
-static void idetape_init_merge_buffer(idetape_tape_t *tape)
-{
- struct idetape_bh *bh = tape->merge_bh;
- tape->bh = tape->merge_bh;
-
- if (tape->chrdev_dir == IDETAPE_DIR_WRITE)
- atomic_set(&bh->b_count, 0);
- else {
- tape->b_data = bh->b_data;
- tape->b_count = atomic_read(&bh->b_count);
- }
+ return ide_tape_issue_pc(drive, &cmd, pc);
}
/*
return;
clear_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags);
- tape->merge_bh_size = 0;
- if (tape->merge_bh != NULL) {
- ide_tape_kfree_buffer(tape);
- tape->merge_bh = NULL;
+ tape->valid = 0;
+ if (tape->buf != NULL) {
+ kfree(tape->buf);
+ tape->buf = NULL;
}
tape->chrdev_dir = IDETAPE_DIR_NONE;
* Generate a read/write request for the block device interface and wait for it
* to be serviced.
*/
-static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int blocks,
- struct idetape_bh *bh)
+static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
{
idetape_tape_t *tape = drive->driver_data;
struct request *rq;
- int ret, errors;
+ int ret;
debug_log(DBG_SENSE, "%s: cmd=%d\n", __func__, cmd);
+ BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE);
+ BUG_ON(size < 0 || size % tape->blk_size);
rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
rq->cmd_type = REQ_TYPE_SPECIAL;
rq->cmd[13] = cmd;
rq->rq_disk = tape->disk;
- rq->special = (void *)bh;
rq->sector = tape->first_frame;
- rq->nr_sectors = blocks;
- rq->current_nr_sectors = blocks;
- blk_execute_rq(drive->queue, tape->disk, rq, 0);
- errors = rq->errors;
- ret = tape->blk_size * (blocks - rq->current_nr_sectors);
- blk_put_request(rq);
+ if (size) {
+ ret = blk_rq_map_kern(drive->queue, rq, tape->buf, size,
+ __GFP_WAIT);
+ if (ret)
+ goto out_put;
+ }
- if ((cmd & (REQ_IDETAPE_READ | REQ_IDETAPE_WRITE)) == 0)
- return 0;
+ blk_execute_rq(drive->queue, tape->disk, rq, 0);
- if (tape->merge_bh)
- idetape_init_merge_buffer(tape);
- if (errors == IDE_DRV_ERROR_GENERAL)
- return -EIO;
+ /* calculate the number of transferred bytes and update buffer state */
+ size -= rq->data_len;
+ tape->cur = tape->buf;
+ if (cmd == REQ_IDETAPE_READ)
+ tape->valid = size;
+ else
+ tape->valid = 0;
+
+ ret = size;
+ if (rq->errors == IDE_DRV_ERROR_GENERAL)
+ ret = -EIO;
+out_put:
+ blk_put_request(rq);
return ret;
}
pc->flags |= PC_FLAG_WAIT_FOR_DSC;
}
-/* Queue up a character device originated write request. */
-static int idetape_add_chrdev_write_request(ide_drive_t *drive, int blocks)
-{
- idetape_tape_t *tape = drive->driver_data;
-
- debug_log(DBG_CHRDEV, "Enter %s\n", __func__);
-
- return idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE,
- blocks, tape->merge_bh);
-}
-
static void ide_tape_flush_merge_buffer(ide_drive_t *drive)
{
idetape_tape_t *tape = drive->driver_data;
- int blocks, min;
- struct idetape_bh *bh;
if (tape->chrdev_dir != IDETAPE_DIR_WRITE) {
printk(KERN_ERR "ide-tape: bug: Trying to empty merge buffer"
" but we are not writing.\n");
return;
}
- if (tape->merge_bh_size > tape->buffer_size) {
- printk(KERN_ERR "ide-tape: bug: merge_buffer too big\n");
- tape->merge_bh_size = tape->buffer_size;
- }
- if (tape->merge_bh_size) {
- blocks = tape->merge_bh_size / tape->blk_size;
- if (tape->merge_bh_size % tape->blk_size) {
- unsigned int i;
-
- blocks++;
- i = tape->blk_size - tape->merge_bh_size %
- tape->blk_size;
- bh = tape->bh->b_reqnext;
- while (bh) {
- atomic_set(&bh->b_count, 0);
- bh = bh->b_reqnext;
- }
- bh = tape->bh;
- while (i) {
- if (bh == NULL) {
- printk(KERN_INFO "ide-tape: bug,"
- " bh NULL\n");
- break;
- }
- min = min(i, (unsigned int)(bh->b_size -
- atomic_read(&bh->b_count)));
- memset(bh->b_data + atomic_read(&bh->b_count),
- 0, min);
- atomic_add(min, &bh->b_count);
- i -= min;
- bh = bh->b_reqnext;
- }
- }
- (void) idetape_add_chrdev_write_request(drive, blocks);
- tape->merge_bh_size = 0;
- }
- if (tape->merge_bh != NULL) {
- ide_tape_kfree_buffer(tape);
- tape->merge_bh = NULL;
+ if (tape->buf) {
+ size_t aligned = roundup(tape->valid, tape->blk_size);
+
+ memset(tape->cur, 0, aligned - tape->valid);
+ idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE, aligned);
+ kfree(tape->buf);
+ tape->buf = NULL;
}
tape->chrdev_dir = IDETAPE_DIR_NONE;
}
-static int idetape_init_read(ide_drive_t *drive)
+static int idetape_init_rw(ide_drive_t *drive, int dir)
{
idetape_tape_t *tape = drive->driver_data;
- int bytes_read;
+ int rc;
- /* Initialize read operation */
- if (tape->chrdev_dir != IDETAPE_DIR_READ) {
- if (tape->chrdev_dir == IDETAPE_DIR_WRITE) {
- ide_tape_flush_merge_buffer(drive);
- idetape_flush_tape_buffers(drive);
- }
- if (tape->merge_bh || tape->merge_bh_size) {
- printk(KERN_ERR "ide-tape: merge_bh_size should be"
- " 0 now\n");
- tape->merge_bh_size = 0;
- }
- tape->merge_bh = ide_tape_kmalloc_buffer(tape, 0, 0);
- if (!tape->merge_bh)
- return -ENOMEM;
- tape->chrdev_dir = IDETAPE_DIR_READ;
+ BUG_ON(dir != IDETAPE_DIR_READ && dir != IDETAPE_DIR_WRITE);
- /*
- * Issue a read 0 command to ensure that DSC handshake is
- * switched from completion mode to buffer available mode.
- * No point in issuing this if DSC overlap isn't supported, some
- * drives (Seagate STT3401A) will return an error.
- */
- if (drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) {
- bytes_read = idetape_queue_rw_tail(drive,
- REQ_IDETAPE_READ, 0,
- tape->merge_bh);
- if (bytes_read < 0) {
- ide_tape_kfree_buffer(tape);
- tape->merge_bh = NULL;
- tape->chrdev_dir = IDETAPE_DIR_NONE;
- return bytes_read;
- }
- }
- }
+ if (tape->chrdev_dir == dir)
+ return 0;
- return 0;
-}
+ if (tape->chrdev_dir == IDETAPE_DIR_READ)
+ ide_tape_discard_merge_buffer(drive, 1);
+ else if (tape->chrdev_dir == IDETAPE_DIR_WRITE) {
+ ide_tape_flush_merge_buffer(drive);
+ idetape_flush_tape_buffers(drive);
+ }
-/* called from idetape_chrdev_read() to service a chrdev read request. */
-static int idetape_add_chrdev_read_request(ide_drive_t *drive, int blocks)
-{
- idetape_tape_t *tape = drive->driver_data;
+ if (tape->buf || tape->valid) {
+ printk(KERN_ERR "ide-tape: valid should be 0 now\n");
+ tape->valid = 0;
+ }
- debug_log(DBG_PROCS, "Enter %s, %d blocks\n", __func__, blocks);
+ tape->buf = kmalloc(tape->buffer_size, GFP_KERNEL);
+ if (!tape->buf)
+ return -ENOMEM;
+ tape->chrdev_dir = dir;
+ tape->cur = tape->buf;
- /* If we are at a filemark, return a read length of 0 */
- if (test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags))
- return 0;
-
- idetape_init_read(drive);
+ /*
+ * Issue a 0 rw command to ensure that DSC handshake is
+ * switched from completion mode to buffer available mode. No
+ * point in issuing this if DSC overlap isn't supported, some
+ * drives (Seagate STT3401A) will return an error.
+ */
+ if (drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) {
+ int cmd = dir == IDETAPE_DIR_READ ? REQ_IDETAPE_READ
+ : REQ_IDETAPE_WRITE;
+
+ rc = idetape_queue_rw_tail(drive, cmd, 0);
+ if (rc < 0) {
+ kfree(tape->buf);
+ tape->buf = NULL;
+ tape->chrdev_dir = IDETAPE_DIR_NONE;
+ return rc;
+ }
+ }
- return idetape_queue_rw_tail(drive, REQ_IDETAPE_READ, blocks,
- tape->merge_bh);
+ return 0;
}
static void idetape_pad_zeros(ide_drive_t *drive, int bcount)
{
idetape_tape_t *tape = drive->driver_data;
- struct idetape_bh *bh;
- int blocks;
+
+ memset(tape->buf, 0, tape->buffer_size);
while (bcount) {
- unsigned int count;
+ unsigned int count = min(tape->buffer_size, bcount);
- bh = tape->merge_bh;
- count = min(tape->buffer_size, bcount);
+ idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE, count);
bcount -= count;
- blocks = count / tape->blk_size;
- while (count) {
- atomic_set(&bh->b_count,
- min(count, (unsigned int)bh->b_size));
- memset(bh->b_data, 0, atomic_read(&bh->b_count));
- count -= atomic_read(&bh->b_count);
- bh = bh->b_reqnext;
- }
- idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE, blocks,
- tape->merge_bh);
}
}
}
if (tape->chrdev_dir == IDETAPE_DIR_READ) {
- tape->merge_bh_size = 0;
+ tape->valid = 0;
if (test_and_clear_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags))
++count;
ide_tape_discard_merge_buffer(drive, 0);
{
struct ide_tape_obj *tape = file->private_data;
ide_drive_t *drive = tape->drive;
- ssize_t bytes_read, temp, actually_read = 0, rc;
+ size_t done = 0;
ssize_t ret = 0;
- u16 ctl = *(u16 *)&tape->caps[12];
+ int rc;
debug_log(DBG_CHRDEV, "Enter %s, count %Zd\n", __func__, count);
(count % tape->blk_size) == 0)
tape->user_bs_factor = count / tape->blk_size;
}
- rc = idetape_init_read(drive);
+
+ rc = idetape_init_rw(drive, IDETAPE_DIR_READ);
if (rc < 0)
return rc;
- if (count == 0)
- return (0);
- if (tape->merge_bh_size) {
- actually_read = min((unsigned int)(tape->merge_bh_size),
- (unsigned int)count);
- if (idetape_copy_stage_to_user(tape, buf, actually_read))
- ret = -EFAULT;
- buf += actually_read;
- tape->merge_bh_size -= actually_read;
- count -= actually_read;
- }
- while (count >= tape->buffer_size) {
- bytes_read = idetape_add_chrdev_read_request(drive, ctl);
- if (bytes_read <= 0)
- goto finish;
- if (idetape_copy_stage_to_user(tape, buf, bytes_read))
- ret = -EFAULT;
- buf += bytes_read;
- count -= bytes_read;
- actually_read += bytes_read;
- }
- if (count) {
- bytes_read = idetape_add_chrdev_read_request(drive, ctl);
- if (bytes_read <= 0)
- goto finish;
- temp = min((unsigned long)count, (unsigned long)bytes_read);
- if (idetape_copy_stage_to_user(tape, buf, temp))
+
+ while (done < count) {
+ size_t todo;
+
+ /* refill if staging buffer is empty */
+ if (!tape->valid) {
+ /* If we are at a filemark, nothing more to read */
+ if (test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags))
+ break;
+ /* read */
+ if (idetape_queue_rw_tail(drive, REQ_IDETAPE_READ,
+ tape->buffer_size) <= 0)
+ break;
+ }
+
+ /* copy out */
+ todo = min_t(size_t, count - done, tape->valid);
+ if (copy_to_user(buf + done, tape->cur, todo))
ret = -EFAULT;
- actually_read += temp;
- tape->merge_bh_size = bytes_read-temp;
+
+ tape->cur += todo;
+ tape->valid -= todo;
+ done += todo;
}
-finish:
- if (!actually_read && test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags)) {
+
+ if (!done && test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags)) {
debug_log(DBG_SENSE, "%s: spacing over filemark\n", tape->name);
idetape_space_over_filemarks(drive, MTFSF, 1);
return 0;
}
- return ret ? ret : actually_read;
+ return ret ? ret : done;
}
static ssize_t idetape_chrdev_write(struct file *file, const char __user *buf,
{
struct ide_tape_obj *tape = file->private_data;
ide_drive_t *drive = tape->drive;
- ssize_t actually_written = 0;
+ size_t done = 0;
ssize_t ret = 0;
- u16 ctl = *(u16 *)&tape->caps[12];
+ int rc;
/* The drive is write protected. */
if (tape->write_prot)
debug_log(DBG_CHRDEV, "Enter %s, count %Zd\n", __func__, count);
/* Initialize write operation */
- if (tape->chrdev_dir != IDETAPE_DIR_WRITE) {
- if (tape->chrdev_dir == IDETAPE_DIR_READ)
- ide_tape_discard_merge_buffer(drive, 1);
- if (tape->merge_bh || tape->merge_bh_size) {
- printk(KERN_ERR "ide-tape: merge_bh_size "
- "should be 0 now\n");
- tape->merge_bh_size = 0;
- }
- tape->merge_bh = ide_tape_kmalloc_buffer(tape, 0, 0);
- if (!tape->merge_bh)
- return -ENOMEM;
- tape->chrdev_dir = IDETAPE_DIR_WRITE;
- idetape_init_merge_buffer(tape);
+ rc = idetape_init_rw(drive, IDETAPE_DIR_WRITE);
+ if (rc < 0)
+ return rc;
- /*
- * Issue a write 0 command to ensure that DSC handshake is
- * switched from completion mode to buffer available mode. No
- * point in issuing this if DSC overlap isn't supported, some
- * drives (Seagate STT3401A) will return an error.
- */
- if (drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) {
- ssize_t retval = idetape_queue_rw_tail(drive,
- REQ_IDETAPE_WRITE, 0,
- tape->merge_bh);
- if (retval < 0) {
- ide_tape_kfree_buffer(tape);
- tape->merge_bh = NULL;
- tape->chrdev_dir = IDETAPE_DIR_NONE;
- return retval;
- }
- }
- }
- if (count == 0)
- return (0);
- if (tape->merge_bh_size) {
- if (tape->merge_bh_size >= tape->buffer_size) {
- printk(KERN_ERR "ide-tape: bug: merge buf too big\n");
- tape->merge_bh_size = 0;
- }
- actually_written = min((unsigned int)
- (tape->buffer_size - tape->merge_bh_size),
- (unsigned int)count);
- if (idetape_copy_stage_from_user(tape, buf, actually_written))
- ret = -EFAULT;
- buf += actually_written;
- tape->merge_bh_size += actually_written;
- count -= actually_written;
-
- if (tape->merge_bh_size == tape->buffer_size) {
- ssize_t retval;
- tape->merge_bh_size = 0;
- retval = idetape_add_chrdev_write_request(drive, ctl);
- if (retval <= 0)
- return (retval);
- }
- }
- while (count >= tape->buffer_size) {
- ssize_t retval;
- if (idetape_copy_stage_from_user(tape, buf, tape->buffer_size))
- ret = -EFAULT;
- buf += tape->buffer_size;
- count -= tape->buffer_size;
- retval = idetape_add_chrdev_write_request(drive, ctl);
- actually_written += tape->buffer_size;
- if (retval <= 0)
- return (retval);
- }
- if (count) {
- actually_written += count;
- if (idetape_copy_stage_from_user(tape, buf, count))
+ while (done < count) {
+ size_t todo;
+
+ /* flush if staging buffer is full */
+ if (tape->valid == tape->buffer_size &&
+ idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE,
+ tape->buffer_size) <= 0)
+ return rc;
+
+ /* copy in */
+ todo = min_t(size_t, count - done,
+ tape->buffer_size - tape->valid);
+ if (copy_from_user(tape->cur, buf + done, todo))
ret = -EFAULT;
- tape->merge_bh_size += count;
+
+ tape->cur += todo;
+ tape->valid += todo;
+ done += todo;
}
- return ret ? ret : actually_written;
+
+ return ret ? ret : done;
}
static int idetape_write_filemark(ide_drive_t *drive)
idetape_flush_tape_buffers(drive);
}
if (cmd == MTIOCGET || cmd == MTIOCPOS) {
- block_offset = tape->merge_bh_size /
+ block_offset = tape->valid /
(tape->blk_size * tape->user_bs_factor);
position = idetape_read_position(drive);
if (position < 0)
idetape_tape_t *tape = drive->driver_data;
ide_tape_flush_merge_buffer(drive);
- tape->merge_bh = ide_tape_kmalloc_buffer(tape, 1, 0);
- if (tape->merge_bh != NULL) {
+ tape->buf = kmalloc(tape->buffer_size, GFP_KERNEL);
+ if (tape->buf != NULL) {
idetape_pad_zeros(drive, tape->blk_size *
(tape->user_bs_factor - 1));
- ide_tape_kfree_buffer(tape);
- tape->merge_bh = NULL;
+ kfree(tape->buf);
+ tape->buf = NULL;
}
idetape_write_filemark(drive);
idetape_flush_tape_buffers(drive);
u16 *ctl = (u16 *)&tape->caps[12];
drive->pc_callback = ide_tape_callback;
- drive->pc_update_buffers = idetape_update_buffers;
- drive->pc_io_buffers = ide_tape_io_buffers;
drive->dev_flags |= IDE_DFLAG_DSC_OVERLAP;
tape->buffer_size = *ctl * tape->blk_size;
}
buffer_size = tape->buffer_size;
- tape->pages_per_buffer = buffer_size / PAGE_SIZE;
- if (buffer_size % PAGE_SIZE) {
- tape->pages_per_buffer++;
- tape->excess_bh_size = PAGE_SIZE - buffer_size % PAGE_SIZE;
- }
/* select the "best" DSC read/write polling freq */
speed = max(*(u16 *)&tape->caps[14], *(u16 *)&tape->caps[8]);
ide_drive_t *drive = tape->drive;
struct gendisk *g = tape->disk;
- BUG_ON(tape->merge_bh_size);
+ BUG_ON(tape->valid);
drive->dev_flags &= ~IDE_DFLAG_DSC_OVERLAP;
drive->driver_data = NULL;
rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
- rq->buffer = buf;
+
+ if (cmd->tf_flags & IDE_TFLAG_WRITE)
+ rq->cmd_flags |= REQ_RW;
/*
* (ks) We transfer currently only whole sectors.
* if we would find a solution to transfer any size.
* To support special commands like READ LONG.
*/
- rq->hard_nr_sectors = rq->nr_sectors = nsect;
- rq->hard_cur_sectors = rq->current_nr_sectors = nsect;
-
- if (cmd->tf_flags & IDE_TFLAG_WRITE)
- rq->cmd_flags |= REQ_RW;
+ if (nsect) {
+ error = blk_rq_map_kern(drive->queue, rq, buf,
+ nsect * SECTOR_SIZE, __GFP_WAIT);
+ if (error)
+ goto put_req;
+ }
rq->special = cmd;
cmd->rq = rq;
error = blk_execute_rq(drive->queue, NULL, rq, 0);
- blk_put_request(rq);
+put_req:
+ blk_put_request(rq);
return error;
}
#include <linux/idr.h>
#include <linux/hdreg.h>
#include <linux/blktrace_api.h>
-#include <trace/block.h>
+
+#include <trace/events/block.h>
#define DM_MSG_PREFIX "core"
union map_info info;
};
-DEFINE_TRACE(block_bio_complete);
-
/*
* For request-based dm.
* One of these is allocated per request.
/* the bio has been remapped so dispatch it */
trace_block_remap(bdev_get_queue(clone->bi_bdev), clone,
- tio->io->bio->bi_bdev->bd_dev,
- clone->bi_sector, sector);
+ tio->io->bio->bi_bdev->bd_dev, sector);
generic_make_request(clone);
} else if (r < 0 || r == DM_MAPIO_REQUEUE) {
}
#ifdef CONFIG_SMP
-static void iosapic_set_affinity_irq(unsigned int irq,
+static int iosapic_set_affinity_irq(unsigned int irq,
const struct cpumask *dest)
{
struct vector_info *vi = iosapic_get_vector(irq);
dest_cpu = cpu_check_affinity(irq, dest);
if (dest_cpu < 0)
- return;
+ return -1;
cpumask_copy(irq_desc[irq].affinity, cpumask_of(dest_cpu));
vi->txn_addr = txn_affinity_addr(irq, dest_cpu);
iosapic_set_irt_data(vi, &dummy_d0, &d1);
iosapic_wr_irt_entry(vi, d0, d1);
spin_unlock_irqrestore(&iosapic_lock, flags);
+
+ return 0;
}
#endif
/* Low-level parallel-port routines for 8255-based PC-style hardware.
- *
+ *
* Authors: Phil Blundell <philb@gnu.org>
* Tim Waugh <tim@cyberelk.demon.co.uk>
* Jose Renau <renau@acm.org>
* Cleaned up include files - Russell King <linux@arm.uk.linux.org>
* DMA support - Bert De Jonghe <bert@sophis.be>
* Many ECP bugs fixed. Fred Barnes & Jamie Lokier, 1999
- * More PCI support now conditional on CONFIG_PCI, 03/2001, Paul G.
+ * More PCI support now conditional on CONFIG_PCI, 03/2001, Paul G.
* Various hacks, Fred Barnes, 04/2001
* Updated probing logic - Adam Belay <ambx1@neo.rr.com>
*/
#include <linux/pnp.h>
#include <linux/platform_device.h>
#include <linux/sysctl.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
-#include <asm/io.h>
#include <asm/dma.h>
-#include <asm/uaccess.h>
#include <linux/parport.h>
#include <linux/parport_pc.h>
#define ECR_TST 06
#define ECR_CNF 07
#define ECR_MODE_MASK 0xe0
-#define ECR_WRITE(p,v) frob_econtrol((p),0xff,(v))
+#define ECR_WRITE(p, v) frob_econtrol((p), 0xff, (v))
#undef DEBUG
static int pnp_registered_parport;
/* frob_control, but for ECR */
-static void frob_econtrol (struct parport *pb, unsigned char m,
+static void frob_econtrol(struct parport *pb, unsigned char m,
unsigned char v)
{
unsigned char ectr = 0;
if (m != 0xff)
- ectr = inb (ECONTROL (pb));
+ ectr = inb(ECONTROL(pb));
- DPRINTK (KERN_DEBUG "frob_econtrol(%02x,%02x): %02x -> %02x\n",
+ DPRINTK(KERN_DEBUG "frob_econtrol(%02x,%02x): %02x -> %02x\n",
m, v, ectr, (ectr & ~m) ^ v);
- outb ((ectr & ~m) ^ v, ECONTROL (pb));
+ outb((ectr & ~m) ^ v, ECONTROL(pb));
}
-static __inline__ void frob_set_mode (struct parport *p, int mode)
+static inline void frob_set_mode(struct parport *p, int mode)
{
- frob_econtrol (p, ECR_MODE_MASK, mode << 5);
+ frob_econtrol(p, ECR_MODE_MASK, mode << 5);
}
#ifdef CONFIG_PARPORT_PC_FIFO
-/* Safely change the mode bits in the ECR
+/* Safely change the mode bits in the ECR
Returns:
0 : Success
-EBUSY: Could not drain FIFO in some finite amount of time,
unsigned char oecr;
int mode;
- DPRINTK(KERN_INFO "parport change_mode ECP-ISA to mode 0x%02x\n",m);
+ DPRINTK(KERN_INFO "parport change_mode ECP-ISA to mode 0x%02x\n", m);
if (!priv->ecr) {
- printk (KERN_DEBUG "change_mode: but there's no ECR!\n");
+ printk(KERN_DEBUG "change_mode: but there's no ECR!\n");
return 0;
}
/* Bits <7:5> contain the mode. */
- oecr = inb (ECONTROL (p));
+ oecr = inb(ECONTROL(p));
mode = (oecr >> 5) & 0x7;
- if (mode == m) return 0;
+ if (mode == m)
+ return 0;
if (mode >= 2 && !(priv->ctr & 0x20)) {
/* This mode resets the FIFO, so we may
case ECR_ECP: /* ECP Parallel Port mode */
/* Busy wait for 200us */
for (counter = 0; counter < 40; counter++) {
- if (inb (ECONTROL (p)) & 0x01)
+ if (inb(ECONTROL(p)) & 0x01)
+ break;
+ if (signal_pending(current))
break;
- if (signal_pending (current)) break;
- udelay (5);
+ udelay(5);
}
/* Poll slowly. */
- while (!(inb (ECONTROL (p)) & 0x01)) {
- if (time_after_eq (jiffies, expire))
+ while (!(inb(ECONTROL(p)) & 0x01)) {
+ if (time_after_eq(jiffies, expire))
/* The FIFO is stuck. */
return -EBUSY;
- schedule_timeout_interruptible(msecs_to_jiffies(10));
- if (signal_pending (current))
+ schedule_timeout_interruptible(
+ msecs_to_jiffies(10));
+ if (signal_pending(current))
break;
}
}
/* We have to go through mode 001 */
oecr &= ~(7 << 5);
oecr |= ECR_PS2 << 5;
- ECR_WRITE (p, oecr);
+ ECR_WRITE(p, oecr);
}
/* Set the mode. */
oecr &= ~(7 << 5);
oecr |= m << 5;
- ECR_WRITE (p, oecr);
+ ECR_WRITE(p, oecr);
return 0;
}
#ifdef CONFIG_PARPORT_1284
/* Find FIFO lossage; FIFO is reset */
#if 0
-static int get_fifo_residue (struct parport *p)
+static int get_fifo_residue(struct parport *p)
{
int residue;
int cnfga;
/* Adjust for the contents of the FIFO. */
for (residue = priv->fifo_depth; ; residue--) {
- if (inb (ECONTROL (p)) & 0x2)
+ if (inb(ECONTROL(p)) & 0x2)
/* Full up. */
break;
- outb (0, FIFO (p));
+ outb(0, FIFO(p));
}
- printk (KERN_DEBUG "%s: %d PWords were left in FIFO\n", p->name,
+ printk(KERN_DEBUG "%s: %d PWords were left in FIFO\n", p->name,
residue);
/* Reset the FIFO. */
- frob_set_mode (p, ECR_PS2);
+ frob_set_mode(p, ECR_PS2);
/* Now change to config mode and clean up. FIXME */
- frob_set_mode (p, ECR_CNF);
- cnfga = inb (CONFIGA (p));
- printk (KERN_DEBUG "%s: cnfgA contains 0x%02x\n", p->name, cnfga);
+ frob_set_mode(p, ECR_CNF);
+ cnfga = inb(CONFIGA(p));
+ printk(KERN_DEBUG "%s: cnfgA contains 0x%02x\n", p->name, cnfga);
if (!(cnfga & (1<<2))) {
- printk (KERN_DEBUG "%s: Accounting for extra byte\n", p->name);
+ printk(KERN_DEBUG "%s: Accounting for extra byte\n", p->name);
residue++;
}
* PWord != 1 byte. */
/* Back to PS2 mode. */
- frob_set_mode (p, ECR_PS2);
+ frob_set_mode(p, ECR_PS2);
- DPRINTK (KERN_DEBUG "*** get_fifo_residue: done residue collecting (ecr = 0x%2.2x)\n", inb (ECONTROL (p)));
+ DPRINTK(KERN_DEBUG
+ "*** get_fifo_residue: done residue collecting (ecr = 0x%2.2x)\n",
+ inb(ECONTROL(p)));
return residue;
}
#endif /* 0 */
/* To clear timeout some chips require double read */
parport_pc_read_status(pb);
r = parport_pc_read_status(pb);
- outb (r | 0x01, STATUS (pb)); /* Some reset by writing 1 */
- outb (r & 0xfe, STATUS (pb)); /* Others by writing 0 */
+ outb(r | 0x01, STATUS(pb)); /* Some reset by writing 1 */
+ outb(r & 0xfe, STATUS(pb)); /* Others by writing 0 */
r = parport_pc_read_status(pb);
return !(r & 0x01);
* of these are in parport_pc.h.
*/
-static void parport_pc_init_state(struct pardevice *dev, struct parport_state *s)
+static void parport_pc_init_state(struct pardevice *dev,
+ struct parport_state *s)
{
s->u.pc.ctr = 0xc;
if (dev->irq_func &&
const struct parport_pc_private *priv = p->physport->private_data;
s->u.pc.ctr = priv->ctr;
if (priv->ecr)
- s->u.pc.ecr = inb (ECONTROL (p));
+ s->u.pc.ecr = inb(ECONTROL(p));
}
-static void parport_pc_restore_state(struct parport *p, struct parport_state *s)
+static void parport_pc_restore_state(struct parport *p,
+ struct parport_state *s)
{
struct parport_pc_private *priv = p->physport->private_data;
register unsigned char c = s->u.pc.ctr & priv->ctr_writable;
- outb (c, CONTROL (p));
+ outb(c, CONTROL(p));
priv->ctr = c;
if (priv->ecr)
- ECR_WRITE (p, s->u.pc.ecr);
+ ECR_WRITE(p, s->u.pc.ecr);
}
#ifdef CONFIG_PARPORT_1284
-static size_t parport_pc_epp_read_data (struct parport *port, void *buf,
- size_t length, int flags)
+static size_t parport_pc_epp_read_data(struct parport *port, void *buf,
+ size_t length, int flags)
{
size_t got = 0;
* nFault is 0 if there is at least 1 byte in the Warp's FIFO
* pError is 1 if there are 16 bytes in the Warp's FIFO
*/
- status = inb (STATUS (port));
+ status = inb(STATUS(port));
- while (!(status & 0x08) && (got < length)) {
- if ((left >= 16) && (status & 0x20) && !(status & 0x08)) {
+ while (!(status & 0x08) && got < length) {
+ if (left >= 16 && (status & 0x20) && !(status & 0x08)) {
/* can grab 16 bytes from warp fifo */
- if (!((long)buf & 0x03)) {
- insl (EPPDATA (port), buf, 4);
- } else {
- insb (EPPDATA (port), buf, 16);
- }
+ if (!((long)buf & 0x03))
+ insl(EPPDATA(port), buf, 4);
+ else
+ insb(EPPDATA(port), buf, 16);
buf += 16;
got += 16;
left -= 16;
} else {
/* grab single byte from the warp fifo */
- *((char *)buf) = inb (EPPDATA (port));
+ *((char *)buf) = inb(EPPDATA(port));
buf++;
got++;
left--;
}
- status = inb (STATUS (port));
+ status = inb(STATUS(port));
if (status & 0x01) {
/* EPP timeout should never occur... */
- printk (KERN_DEBUG "%s: EPP timeout occurred while talking to "
- "w91284pic (should not have done)\n", port->name);
- clear_epp_timeout (port);
+ printk(KERN_DEBUG
+"%s: EPP timeout occurred while talking to w91284pic (should not have done)\n", port->name);
+ clear_epp_timeout(port);
}
}
return got;
}
if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
- if (!(((long)buf | length) & 0x03)) {
- insl (EPPDATA (port), buf, (length >> 2));
- } else {
- insb (EPPDATA (port), buf, length);
- }
- if (inb (STATUS (port)) & 0x01) {
- clear_epp_timeout (port);
+ if (!(((long)buf | length) & 0x03))
+ insl(EPPDATA(port), buf, (length >> 2));
+ else
+ insb(EPPDATA(port), buf, length);
+ if (inb(STATUS(port)) & 0x01) {
+ clear_epp_timeout(port);
return -EIO;
}
return length;
}
for (; got < length; got++) {
- *((char*)buf) = inb (EPPDATA(port));
+ *((char *)buf) = inb(EPPDATA(port));
buf++;
- if (inb (STATUS (port)) & 0x01) {
+ if (inb(STATUS(port)) & 0x01) {
/* EPP timeout */
- clear_epp_timeout (port);
+ clear_epp_timeout(port);
break;
}
}
return got;
}
-static size_t parport_pc_epp_write_data (struct parport *port, const void *buf,
- size_t length, int flags)
+static size_t parport_pc_epp_write_data(struct parport *port, const void *buf,
+ size_t length, int flags)
{
size_t written = 0;
if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
- if (!(((long)buf | length) & 0x03)) {
- outsl (EPPDATA (port), buf, (length >> 2));
- } else {
- outsb (EPPDATA (port), buf, length);
- }
- if (inb (STATUS (port)) & 0x01) {
- clear_epp_timeout (port);
+ if (!(((long)buf | length) & 0x03))
+ outsl(EPPDATA(port), buf, (length >> 2));
+ else
+ outsb(EPPDATA(port), buf, length);
+ if (inb(STATUS(port)) & 0x01) {
+ clear_epp_timeout(port);
return -EIO;
}
return length;
}
for (; written < length; written++) {
- outb (*((char*)buf), EPPDATA(port));
+ outb(*((char *)buf), EPPDATA(port));
buf++;
- if (inb (STATUS(port)) & 0x01) {
- clear_epp_timeout (port);
+ if (inb(STATUS(port)) & 0x01) {
+ clear_epp_timeout(port);
break;
}
}
return written;
}
-static size_t parport_pc_epp_read_addr (struct parport *port, void *buf,
+static size_t parport_pc_epp_read_addr(struct parport *port, void *buf,
size_t length, int flags)
{
size_t got = 0;
if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
- insb (EPPADDR (port), buf, length);
- if (inb (STATUS (port)) & 0x01) {
- clear_epp_timeout (port);
+ insb(EPPADDR(port), buf, length);
+ if (inb(STATUS(port)) & 0x01) {
+ clear_epp_timeout(port);
return -EIO;
}
return length;
}
for (; got < length; got++) {
- *((char*)buf) = inb (EPPADDR (port));
+ *((char *)buf) = inb(EPPADDR(port));
buf++;
- if (inb (STATUS (port)) & 0x01) {
- clear_epp_timeout (port);
+ if (inb(STATUS(port)) & 0x01) {
+ clear_epp_timeout(port);
break;
}
}
return got;
}
-static size_t parport_pc_epp_write_addr (struct parport *port,
+static size_t parport_pc_epp_write_addr(struct parport *port,
const void *buf, size_t length,
int flags)
{
size_t written = 0;
if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
- outsb (EPPADDR (port), buf, length);
- if (inb (STATUS (port)) & 0x01) {
- clear_epp_timeout (port);
+ outsb(EPPADDR(port), buf, length);
+ if (inb(STATUS(port)) & 0x01) {
+ clear_epp_timeout(port);
return -EIO;
}
return length;
}
for (; written < length; written++) {
- outb (*((char*)buf), EPPADDR (port));
+ outb(*((char *)buf), EPPADDR(port));
buf++;
- if (inb (STATUS (port)) & 0x01) {
- clear_epp_timeout (port);
+ if (inb(STATUS(port)) & 0x01) {
+ clear_epp_timeout(port);
break;
}
}
return written;
}
-static size_t parport_pc_ecpepp_read_data (struct parport *port, void *buf,
- size_t length, int flags)
+static size_t parport_pc_ecpepp_read_data(struct parport *port, void *buf,
+ size_t length, int flags)
{
size_t got;
- frob_set_mode (port, ECR_EPP);
- parport_pc_data_reverse (port);
- parport_pc_write_control (port, 0x4);
- got = parport_pc_epp_read_data (port, buf, length, flags);
- frob_set_mode (port, ECR_PS2);
+ frob_set_mode(port, ECR_EPP);
+ parport_pc_data_reverse(port);
+ parport_pc_write_control(port, 0x4);
+ got = parport_pc_epp_read_data(port, buf, length, flags);
+ frob_set_mode(port, ECR_PS2);
return got;
}
-static size_t parport_pc_ecpepp_write_data (struct parport *port,
- const void *buf, size_t length,
- int flags)
+static size_t parport_pc_ecpepp_write_data(struct parport *port,
+ const void *buf, size_t length,
+ int flags)
{
size_t written;
- frob_set_mode (port, ECR_EPP);
- parport_pc_write_control (port, 0x4);
- parport_pc_data_forward (port);
- written = parport_pc_epp_write_data (port, buf, length, flags);
- frob_set_mode (port, ECR_PS2);
+ frob_set_mode(port, ECR_EPP);
+ parport_pc_write_control(port, 0x4);
+ parport_pc_data_forward(port);
+ written = parport_pc_epp_write_data(port, buf, length, flags);
+ frob_set_mode(port, ECR_PS2);
return written;
}
-static size_t parport_pc_ecpepp_read_addr (struct parport *port, void *buf,
- size_t length, int flags)
+static size_t parport_pc_ecpepp_read_addr(struct parport *port, void *buf,
+ size_t length, int flags)
{
size_t got;
- frob_set_mode (port, ECR_EPP);
- parport_pc_data_reverse (port);
- parport_pc_write_control (port, 0x4);
- got = parport_pc_epp_read_addr (port, buf, length, flags);
- frob_set_mode (port, ECR_PS2);
+ frob_set_mode(port, ECR_EPP);
+ parport_pc_data_reverse(port);
+ parport_pc_write_control(port, 0x4);
+ got = parport_pc_epp_read_addr(port, buf, length, flags);
+ frob_set_mode(port, ECR_PS2);
return got;
}
-static size_t parport_pc_ecpepp_write_addr (struct parport *port,
+static size_t parport_pc_ecpepp_write_addr(struct parport *port,
const void *buf, size_t length,
int flags)
{
size_t written;
- frob_set_mode (port, ECR_EPP);
- parport_pc_write_control (port, 0x4);
- parport_pc_data_forward (port);
- written = parport_pc_epp_write_addr (port, buf, length, flags);
- frob_set_mode (port, ECR_PS2);
+ frob_set_mode(port, ECR_EPP);
+ parport_pc_write_control(port, 0x4);
+ parport_pc_data_forward(port);
+ written = parport_pc_epp_write_addr(port, buf, length, flags);
+ frob_set_mode(port, ECR_PS2);
return written;
}
#endif /* IEEE 1284 support */
#ifdef CONFIG_PARPORT_PC_FIFO
-static size_t parport_pc_fifo_write_block_pio (struct parport *port,
+static size_t parport_pc_fifo_write_block_pio(struct parport *port,
const void *buf, size_t length)
{
int ret = 0;
const unsigned char *bufp = buf;
size_t left = length;
unsigned long expire = jiffies + port->physport->cad->timeout;
- const int fifo = FIFO (port);
+ const int fifo = FIFO(port);
int poll_for = 8; /* 80 usecs */
const struct parport_pc_private *priv = port->physport->private_data;
const int fifo_depth = priv->fifo_depth;
port = port->physport;
/* We don't want to be interrupted every character. */
- parport_pc_disable_irq (port);
+ parport_pc_disable_irq(port);
/* set nErrIntrEn and serviceIntr */
- frob_econtrol (port, (1<<4) | (1<<2), (1<<4) | (1<<2));
+ frob_econtrol(port, (1<<4) | (1<<2), (1<<4) | (1<<2));
/* Forward mode. */
- parport_pc_data_forward (port); /* Must be in PS2 mode */
+ parport_pc_data_forward(port); /* Must be in PS2 mode */
while (left) {
unsigned char byte;
- unsigned char ecrval = inb (ECONTROL (port));
+ unsigned char ecrval = inb(ECONTROL(port));
int i = 0;
- if (need_resched() && time_before (jiffies, expire))
+ if (need_resched() && time_before(jiffies, expire))
/* Can't yield the port. */
- schedule ();
+ schedule();
/* Anyone else waiting for the port? */
if (port->waithead) {
- printk (KERN_DEBUG "Somebody wants the port\n");
+ printk(KERN_DEBUG "Somebody wants the port\n");
break;
}
/* FIFO is full. Wait for interrupt. */
/* Clear serviceIntr */
- ECR_WRITE (port, ecrval & ~(1<<2));
- false_alarm:
- ret = parport_wait_event (port, HZ);
- if (ret < 0) break;
+ ECR_WRITE(port, ecrval & ~(1<<2));
+false_alarm:
+ ret = parport_wait_event(port, HZ);
+ if (ret < 0)
+ break;
ret = 0;
- if (!time_before (jiffies, expire)) {
+ if (!time_before(jiffies, expire)) {
/* Timed out. */
- printk (KERN_DEBUG "FIFO write timed out\n");
+ printk(KERN_DEBUG "FIFO write timed out\n");
break;
}
- ecrval = inb (ECONTROL (port));
+ ecrval = inb(ECONTROL(port));
if (!(ecrval & (1<<2))) {
if (need_resched() &&
- time_before (jiffies, expire))
- schedule ();
+ time_before(jiffies, expire))
+ schedule();
goto false_alarm;
}
/* Can't fail now. */
expire = jiffies + port->cad->timeout;
- poll:
- if (signal_pending (current))
+poll:
+ if (signal_pending(current))
break;
if (ecrval & 0x01) {
/* FIFO is empty. Blast it full. */
const int n = left < fifo_depth ? left : fifo_depth;
- outsb (fifo, bufp, n);
+ outsb(fifo, bufp, n);
bufp += n;
left -= n;
/* Adjust the poll time. */
- if (i < (poll_for - 2)) poll_for--;
+ if (i < (poll_for - 2))
+ poll_for--;
continue;
} else if (i++ < poll_for) {
- udelay (10);
- ecrval = inb (ECONTROL (port));
+ udelay(10);
+ ecrval = inb(ECONTROL(port));
goto poll;
}
- /* Half-full (call me an optimist) */
+ /* Half-full(call me an optimist) */
byte = *bufp++;
- outb (byte, fifo);
+ outb(byte, fifo);
left--;
- }
-
-dump_parport_state ("leave fifo_write_block_pio", port);
+ }
+ dump_parport_state("leave fifo_write_block_pio", port);
return length - left;
}
#ifdef HAS_DMA
-static size_t parport_pc_fifo_write_block_dma (struct parport *port,
+static size_t parport_pc_fifo_write_block_dma(struct parport *port,
const void *buf, size_t length)
{
int ret = 0;
unsigned long start = (unsigned long) buf;
unsigned long end = (unsigned long) buf + length - 1;
-dump_parport_state ("enter fifo_write_block_dma", port);
+ dump_parport_state("enter fifo_write_block_dma", port);
if (end < MAX_DMA_ADDRESS) {
/* If it would cross a 64k boundary, cap it at the end. */
if ((start ^ end) & ~0xffffUL)
dma_addr = dma_handle = dma_map_single(dev, (void *)buf, length,
DMA_TO_DEVICE);
- } else {
- /* above 16 MB we use a bounce buffer as ISA-DMA is not possible */
+ } else {
+ /* above 16 MB we use a bounce buffer as ISA-DMA
+ is not possible */
maxlen = PAGE_SIZE; /* sizeof(priv->dma_buf) */
dma_addr = priv->dma_handle;
dma_handle = 0;
port = port->physport;
/* We don't want to be interrupted every character. */
- parport_pc_disable_irq (port);
+ parport_pc_disable_irq(port);
/* set nErrIntrEn and serviceIntr */
- frob_econtrol (port, (1<<4) | (1<<2), (1<<4) | (1<<2));
+ frob_econtrol(port, (1<<4) | (1<<2), (1<<4) | (1<<2));
/* Forward mode. */
- parport_pc_data_forward (port); /* Must be in PS2 mode */
+ parport_pc_data_forward(port); /* Must be in PS2 mode */
while (left) {
unsigned long expire = jiffies + port->physport->cad->timeout;
set_dma_count(port->dma, count);
/* Set DMA mode */
- frob_econtrol (port, 1<<3, 1<<3);
+ frob_econtrol(port, 1<<3, 1<<3);
/* Clear serviceIntr */
- frob_econtrol (port, 1<<2, 0);
+ frob_econtrol(port, 1<<2, 0);
enable_dma(port->dma);
release_dma_lock(dmaflag);
/* assume DMA will be successful */
left -= count;
buf += count;
- if (dma_handle) dma_addr += count;
+ if (dma_handle)
+ dma_addr += count;
/* Wait for interrupt. */
- false_alarm:
- ret = parport_wait_event (port, HZ);
- if (ret < 0) break;
+false_alarm:
+ ret = parport_wait_event(port, HZ);
+ if (ret < 0)
+ break;
ret = 0;
- if (!time_before (jiffies, expire)) {
+ if (!time_before(jiffies, expire)) {
/* Timed out. */
- printk (KERN_DEBUG "DMA write timed out\n");
+ printk(KERN_DEBUG "DMA write timed out\n");
break;
}
/* Is serviceIntr set? */
- if (!(inb (ECONTROL (port)) & (1<<2))) {
+ if (!(inb(ECONTROL(port)) & (1<<2))) {
cond_resched();
goto false_alarm;
/* Anyone else waiting for the port? */
if (port->waithead) {
- printk (KERN_DEBUG "Somebody wants the port\n");
+ printk(KERN_DEBUG "Somebody wants the port\n");
break;
}
/* update for possible DMA residue ! */
buf -= count;
left += count;
- if (dma_handle) dma_addr -= count;
+ if (dma_handle)
+ dma_addr -= count;
}
/* Maybe got here through break, so adjust for DMA residue! */
release_dma_lock(dmaflag);
/* Turn off DMA mode */
- frob_econtrol (port, 1<<3, 0);
+ frob_econtrol(port, 1<<3, 0);
if (dma_handle)
dma_unmap_single(dev, dma_handle, length, DMA_TO_DEVICE);
-dump_parport_state ("leave fifo_write_block_dma", port);
+ dump_parport_state("leave fifo_write_block_dma", port);
return length - left;
}
#endif
{
#ifdef HAS_DMA
if (port->dma != PARPORT_DMA_NONE)
- return parport_pc_fifo_write_block_dma (port, buf, length);
+ return parport_pc_fifo_write_block_dma(port, buf, length);
#endif
- return parport_pc_fifo_write_block_pio (port, buf, length);
+ return parport_pc_fifo_write_block_pio(port, buf, length);
}
/* Parallel Port FIFO mode (ECP chipsets) */
-static size_t parport_pc_compat_write_block_pio (struct parport *port,
+static size_t parport_pc_compat_write_block_pio(struct parport *port,
const void *buf, size_t length,
int flags)
{
/* Special case: a timeout of zero means we cannot call schedule().
* Also if O_NONBLOCK is set then use the default implementation. */
if (port->physport->cad->timeout <= PARPORT_INACTIVITY_O_NONBLOCK)
- return parport_ieee1284_write_compat (port, buf,
+ return parport_ieee1284_write_compat(port, buf,
length, flags);
/* Set up parallel port FIFO mode.*/
- parport_pc_data_forward (port); /* Must be in PS2 mode */
- parport_pc_frob_control (port, PARPORT_CONTROL_STROBE, 0);
- r = change_mode (port, ECR_PPF); /* Parallel port FIFO */
- if (r) printk (KERN_DEBUG "%s: Warning change_mode ECR_PPF failed\n", port->name);
+ parport_pc_data_forward(port); /* Must be in PS2 mode */
+ parport_pc_frob_control(port, PARPORT_CONTROL_STROBE, 0);
+ r = change_mode(port, ECR_PPF); /* Parallel port FIFO */
+ if (r)
+ printk(KERN_DEBUG "%s: Warning change_mode ECR_PPF failed\n",
+ port->name);
port->physport->ieee1284.phase = IEEE1284_PH_FWD_DATA;
* the FIFO is empty, so allow 4 seconds for each position
* in the fifo.
*/
- expire = jiffies + (priv->fifo_depth * HZ * 4);
+ expire = jiffies + (priv->fifo_depth * HZ * 4);
do {
/* Wait for the FIFO to empty */
- r = change_mode (port, ECR_PS2);
- if (r != -EBUSY) {
+ r = change_mode(port, ECR_PS2);
+ if (r != -EBUSY)
break;
- }
- } while (time_before (jiffies, expire));
+ } while (time_before(jiffies, expire));
if (r == -EBUSY) {
- printk (KERN_DEBUG "%s: FIFO is stuck\n", port->name);
+ printk(KERN_DEBUG "%s: FIFO is stuck\n", port->name);
/* Prevent further data transfer. */
- frob_set_mode (port, ECR_TST);
+ frob_set_mode(port, ECR_TST);
/* Adjust for the contents of the FIFO. */
for (written -= priv->fifo_depth; ; written++) {
- if (inb (ECONTROL (port)) & 0x2) {
+ if (inb(ECONTROL(port)) & 0x2) {
/* Full up. */
break;
}
- outb (0, FIFO (port));
+ outb(0, FIFO(port));
}
/* Reset the FIFO and return to PS2 mode. */
- frob_set_mode (port, ECR_PS2);
+ frob_set_mode(port, ECR_PS2);
}
- r = parport_wait_peripheral (port,
+ r = parport_wait_peripheral(port,
PARPORT_STATUS_BUSY,
PARPORT_STATUS_BUSY);
if (r)
- printk (KERN_DEBUG
- "%s: BUSY timeout (%d) in compat_write_block_pio\n",
+ printk(KERN_DEBUG
+ "%s: BUSY timeout (%d) in compat_write_block_pio\n",
port->name, r);
port->physport->ieee1284.phase = IEEE1284_PH_FWD_IDLE;
/* ECP */
#ifdef CONFIG_PARPORT_1284
-static size_t parport_pc_ecp_write_block_pio (struct parport *port,
+static size_t parport_pc_ecp_write_block_pio(struct parport *port,
const void *buf, size_t length,
int flags)
{
/* Special case: a timeout of zero means we cannot call schedule().
* Also if O_NONBLOCK is set then use the default implementation. */
if (port->physport->cad->timeout <= PARPORT_INACTIVITY_O_NONBLOCK)
- return parport_ieee1284_ecp_write_data (port, buf,
+ return parport_ieee1284_ecp_write_data(port, buf,
length, flags);
/* Switch to forward mode if necessary. */
if (port->physport->ieee1284.phase != IEEE1284_PH_FWD_IDLE) {
/* Event 47: Set nInit high. */
- parport_frob_control (port,
+ parport_frob_control(port,
PARPORT_CONTROL_INIT
| PARPORT_CONTROL_AUTOFD,
PARPORT_CONTROL_INIT
| PARPORT_CONTROL_AUTOFD);
/* Event 49: PError goes high. */
- r = parport_wait_peripheral (port,
+ r = parport_wait_peripheral(port,
PARPORT_STATUS_PAPEROUT,
PARPORT_STATUS_PAPEROUT);
if (r) {
- printk (KERN_DEBUG "%s: PError timeout (%d) "
+ printk(KERN_DEBUG "%s: PError timeout (%d) "
"in ecp_write_block_pio\n", port->name, r);
}
}
/* Set up ECP parallel port mode.*/
- parport_pc_data_forward (port); /* Must be in PS2 mode */
- parport_pc_frob_control (port,
+ parport_pc_data_forward(port); /* Must be in PS2 mode */
+ parport_pc_frob_control(port,
PARPORT_CONTROL_STROBE |
PARPORT_CONTROL_AUTOFD,
0);
- r = change_mode (port, ECR_ECP); /* ECP FIFO */
- if (r) printk (KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n", port->name);
+ r = change_mode(port, ECR_ECP); /* ECP FIFO */
+ if (r)
+ printk(KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n",
+ port->name);
port->physport->ieee1284.phase = IEEE1284_PH_FWD_DATA;
/* Write the data to the FIFO. */
expire = jiffies + (priv->fifo_depth * (HZ * 4));
do {
/* Wait for the FIFO to empty */
- r = change_mode (port, ECR_PS2);
- if (r != -EBUSY) {
+ r = change_mode(port, ECR_PS2);
+ if (r != -EBUSY)
break;
- }
- } while (time_before (jiffies, expire));
+ } while (time_before(jiffies, expire));
if (r == -EBUSY) {
- printk (KERN_DEBUG "%s: FIFO is stuck\n", port->name);
+ printk(KERN_DEBUG "%s: FIFO is stuck\n", port->name);
/* Prevent further data transfer. */
- frob_set_mode (port, ECR_TST);
+ frob_set_mode(port, ECR_TST);
/* Adjust for the contents of the FIFO. */
for (written -= priv->fifo_depth; ; written++) {
- if (inb (ECONTROL (port)) & 0x2) {
+ if (inb(ECONTROL(port)) & 0x2) {
/* Full up. */
break;
}
- outb (0, FIFO (port));
+ outb(0, FIFO(port));
}
/* Reset the FIFO and return to PS2 mode. */
- frob_set_mode (port, ECR_PS2);
+ frob_set_mode(port, ECR_PS2);
/* Host transfer recovery. */
- parport_pc_data_reverse (port); /* Must be in PS2 mode */
- udelay (5);
- parport_frob_control (port, PARPORT_CONTROL_INIT, 0);
- r = parport_wait_peripheral (port, PARPORT_STATUS_PAPEROUT, 0);
+ parport_pc_data_reverse(port); /* Must be in PS2 mode */
+ udelay(5);
+ parport_frob_control(port, PARPORT_CONTROL_INIT, 0);
+ r = parport_wait_peripheral(port, PARPORT_STATUS_PAPEROUT, 0);
if (r)
- printk (KERN_DEBUG "%s: PE,1 timeout (%d) "
+ printk(KERN_DEBUG "%s: PE,1 timeout (%d) "
"in ecp_write_block_pio\n", port->name, r);
- parport_frob_control (port,
+ parport_frob_control(port,
PARPORT_CONTROL_INIT,
PARPORT_CONTROL_INIT);
- r = parport_wait_peripheral (port,
+ r = parport_wait_peripheral(port,
PARPORT_STATUS_PAPEROUT,
PARPORT_STATUS_PAPEROUT);
- if (r)
- printk (KERN_DEBUG "%s: PE,2 timeout (%d) "
+ if (r)
+ printk(KERN_DEBUG "%s: PE,2 timeout (%d) "
"in ecp_write_block_pio\n", port->name, r);
}
- r = parport_wait_peripheral (port,
- PARPORT_STATUS_BUSY,
+ r = parport_wait_peripheral(port,
+ PARPORT_STATUS_BUSY,
PARPORT_STATUS_BUSY);
- if(r)
- printk (KERN_DEBUG
+ if (r)
+ printk(KERN_DEBUG
"%s: BUSY timeout (%d) in ecp_write_block_pio\n",
port->name, r);
}
#if 0
-static size_t parport_pc_ecp_read_block_pio (struct parport *port,
+static size_t parport_pc_ecp_read_block_pio(struct parport *port,
void *buf, size_t length,
int flags)
{
char *bufp = buf;
port = port->physport;
-DPRINTK (KERN_DEBUG "parport_pc: parport_pc_ecp_read_block_pio\n");
-dump_parport_state ("enter fcn", port);
+ DPRINTK(KERN_DEBUG "parport_pc: parport_pc_ecp_read_block_pio\n");
+ dump_parport_state("enter fcn", port);
/* Special case: a timeout of zero means we cannot call schedule().
* Also if O_NONBLOCK is set then use the default implementation. */
if (port->cad->timeout <= PARPORT_INACTIVITY_O_NONBLOCK)
- return parport_ieee1284_ecp_read_data (port, buf,
+ return parport_ieee1284_ecp_read_data(port, buf,
length, flags);
if (port->ieee1284.mode == IEEE1284_MODE_ECPRLE) {
* go through software emulation. Otherwise we may have to throw
* away data. */
if (length < fifofull)
- return parport_ieee1284_ecp_read_data (port, buf,
+ return parport_ieee1284_ecp_read_data(port, buf,
length, flags);
if (port->ieee1284.phase != IEEE1284_PH_REV_IDLE) {
/* change to reverse-idle phase (must be in forward-idle) */
/* Event 38: Set nAutoFd low (also make sure nStrobe is high) */
- parport_frob_control (port,
+ parport_frob_control(port,
PARPORT_CONTROL_AUTOFD
| PARPORT_CONTROL_STROBE,
PARPORT_CONTROL_AUTOFD);
- parport_pc_data_reverse (port); /* Must be in PS2 mode */
- udelay (5);
+ parport_pc_data_reverse(port); /* Must be in PS2 mode */
+ udelay(5);
/* Event 39: Set nInit low to initiate bus reversal */
- parport_frob_control (port,
+ parport_frob_control(port,
PARPORT_CONTROL_INIT,
0);
/* Event 40: Wait for nAckReverse (PError) to go low */
- r = parport_wait_peripheral (port, PARPORT_STATUS_PAPEROUT, 0);
- if (r) {
- printk (KERN_DEBUG "%s: PE timeout Event 40 (%d) "
+ r = parport_wait_peripheral(port, PARPORT_STATUS_PAPEROUT, 0);
+ if (r) {
+ printk(KERN_DEBUG "%s: PE timeout Event 40 (%d) "
"in ecp_read_block_pio\n", port->name, r);
return 0;
}
}
/* Set up ECP FIFO mode.*/
-/* parport_pc_frob_control (port,
+/* parport_pc_frob_control(port,
PARPORT_CONTROL_STROBE |
PARPORT_CONTROL_AUTOFD,
PARPORT_CONTROL_AUTOFD); */
- r = change_mode (port, ECR_ECP); /* ECP FIFO */
- if (r) printk (KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n", port->name);
+ r = change_mode(port, ECR_ECP); /* ECP FIFO */
+ if (r)
+ printk(KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n",
+ port->name);
port->ieee1284.phase = IEEE1284_PH_REV_DATA;
/* the first byte must be collected manually */
-dump_parport_state ("pre 43", port);
+ dump_parport_state("pre 43", port);
/* Event 43: Wait for nAck to go low */
- r = parport_wait_peripheral (port, PARPORT_STATUS_ACK, 0);
+ r = parport_wait_peripheral(port, PARPORT_STATUS_ACK, 0);
if (r) {
/* timed out while reading -- no data */
- printk (KERN_DEBUG "PIO read timed out (initial byte)\n");
+ printk(KERN_DEBUG "PIO read timed out (initial byte)\n");
goto out_no_data;
}
/* read byte */
- *bufp++ = inb (DATA (port));
+ *bufp++ = inb(DATA(port));
left--;
-dump_parport_state ("43-44", port);
+ dump_parport_state("43-44", port);
/* Event 44: nAutoFd (HostAck) goes high to acknowledge */
- parport_pc_frob_control (port,
+ parport_pc_frob_control(port,
PARPORT_CONTROL_AUTOFD,
0);
-dump_parport_state ("pre 45", port);
+ dump_parport_state("pre 45", port);
/* Event 45: Wait for nAck to go high */
-/* r = parport_wait_peripheral (port, PARPORT_STATUS_ACK, PARPORT_STATUS_ACK); */
-dump_parport_state ("post 45", port);
-r = 0;
+ /* r = parport_wait_peripheral(port, PARPORT_STATUS_ACK,
+ PARPORT_STATUS_ACK); */
+ dump_parport_state("post 45", port);
+ r = 0;
if (r) {
/* timed out while waiting for peripheral to respond to ack */
- printk (KERN_DEBUG "ECP PIO read timed out (waiting for nAck)\n");
+ printk(KERN_DEBUG "ECP PIO read timed out (waiting for nAck)\n");
/* keep hold of the byte we've got already */
goto out_no_data;
}
/* Event 46: nAutoFd (HostAck) goes low to accept more data */
- parport_pc_frob_control (port,
+ parport_pc_frob_control(port,
PARPORT_CONTROL_AUTOFD,
PARPORT_CONTROL_AUTOFD);
-dump_parport_state ("rev idle", port);
+ dump_parport_state("rev idle", port);
/* Do the transfer. */
while (left > fifofull) {
int ret;
unsigned long expire = jiffies + port->cad->timeout;
- unsigned char ecrval = inb (ECONTROL (port));
+ unsigned char ecrval = inb(ECONTROL(port));
- if (need_resched() && time_before (jiffies, expire))
+ if (need_resched() && time_before(jiffies, expire))
/* Can't yield the port. */
- schedule ();
+ schedule();
/* At this point, the FIFO may already be full. In
- * that case ECP is already holding back the
- * peripheral (assuming proper design) with a delayed
- * handshake. Work fast to avoid a peripheral
- * timeout. */
+ * that case ECP is already holding back the
+ * peripheral (assuming proper design) with a delayed
+ * handshake. Work fast to avoid a peripheral
+ * timeout. */
if (ecrval & 0x01) {
/* FIFO is empty. Wait for interrupt. */
-dump_parport_state ("FIFO empty", port);
+ dump_parport_state("FIFO empty", port);
/* Anyone else waiting for the port? */
if (port->waithead) {
- printk (KERN_DEBUG "Somebody wants the port\n");
+ printk(KERN_DEBUG "Somebody wants the port\n");
break;
}
/* Clear serviceIntr */
- ECR_WRITE (port, ecrval & ~(1<<2));
- false_alarm:
-dump_parport_state ("waiting", port);
- ret = parport_wait_event (port, HZ);
-DPRINTK (KERN_DEBUG "parport_wait_event returned %d\n", ret);
+ ECR_WRITE(port, ecrval & ~(1<<2));
+false_alarm:
+ dump_parport_state("waiting", port);
+ ret = parport_wait_event(port, HZ);
+ DPRINTK(KERN_DEBUG "parport_wait_event returned %d\n",
+ ret);
if (ret < 0)
break;
ret = 0;
- if (!time_before (jiffies, expire)) {
+ if (!time_before(jiffies, expire)) {
/* Timed out. */
-dump_parport_state ("timeout", port);
- printk (KERN_DEBUG "PIO read timed out\n");
+ dump_parport_state("timeout", port);
+ printk(KERN_DEBUG "PIO read timed out\n");
break;
}
- ecrval = inb (ECONTROL (port));
+ ecrval = inb(ECONTROL(port));
if (!(ecrval & (1<<2))) {
if (need_resched() &&
- time_before (jiffies, expire)) {
- schedule ();
+ time_before(jiffies, expire)) {
+ schedule();
}
goto false_alarm;
}
/* Depending on how the FIFO threshold was
- * set, how long interrupt service took, and
- * how fast the peripheral is, we might be
- * lucky and have a just filled FIFO. */
+ * set, how long interrupt service took, and
+ * how fast the peripheral is, we might be
+ * lucky and have a just filled FIFO. */
continue;
}
if (ecrval & 0x02) {
/* FIFO is full. */
-dump_parport_state ("FIFO full", port);
- insb (fifo, bufp, fifo_depth);
+ dump_parport_state("FIFO full", port);
+ insb(fifo, bufp, fifo_depth);
bufp += fifo_depth;
left -= fifo_depth;
continue;
}
-DPRINTK (KERN_DEBUG "*** ecp_read_block_pio: reading one byte from the FIFO\n");
+ DPRINTK(KERN_DEBUG
+ "*** ecp_read_block_pio: reading one byte from the FIFO\n");
/* FIFO not filled. We will cycle this loop for a while
- * and either the peripheral will fill it faster,
- * tripping a fast empty with insb, or we empty it. */
- *bufp++ = inb (fifo);
+ * and either the peripheral will fill it faster,
+ * tripping a fast empty with insb, or we empty it. */
+ *bufp++ = inb(fifo);
left--;
}
/* scoop up anything left in the FIFO */
- while (left && !(inb (ECONTROL (port) & 0x01))) {
- *bufp++ = inb (fifo);
+ while (left && !(inb(ECONTROL(port) & 0x01))) {
+ *bufp++ = inb(fifo);
left--;
}
port->ieee1284.phase = IEEE1284_PH_REV_IDLE;
-dump_parport_state ("rev idle2", port);
+ dump_parport_state("rev idle2", port);
out_no_data:
/* Go to forward idle mode to shut the peripheral up (event 47). */
- parport_frob_control (port, PARPORT_CONTROL_INIT, PARPORT_CONTROL_INIT);
+ parport_frob_control(port, PARPORT_CONTROL_INIT, PARPORT_CONTROL_INIT);
/* event 49: PError goes high */
- r = parport_wait_peripheral (port,
+ r = parport_wait_peripheral(port,
PARPORT_STATUS_PAPEROUT,
PARPORT_STATUS_PAPEROUT);
if (r) {
- printk (KERN_DEBUG
+ printk(KERN_DEBUG
"%s: PE timeout FWDIDLE (%d) in ecp_read_block_pio\n",
port->name, r);
}
/* Finish up. */
{
- int lost = get_fifo_residue (port);
+ int lost = get_fifo_residue(port);
if (lost)
/* Shouldn't happen with compliant peripherals. */
- printk (KERN_DEBUG "%s: DATA LOSS (%d bytes)!\n",
+ printk(KERN_DEBUG "%s: DATA LOSS (%d bytes)!\n",
port->name, lost);
}
-dump_parport_state ("fwd idle", port);
+ dump_parport_state("fwd idle", port);
return length - left;
}
#endif /* 0 */
/* GCC is not inlining extern inline function later overwriten to non-inline,
so we use outlined_ variants here. */
-static const struct parport_operations parport_pc_ops =
-{
+static const struct parport_operations parport_pc_ops = {
.write_data = parport_pc_write_data,
.read_data = parport_pc_read_data,
};
#ifdef CONFIG_PARPORT_PC_SUPERIO
+
+static struct superio_struct *find_free_superio(void)
+{
+ int i;
+ for (i = 0; i < NR_SUPERIOS; i++)
+ if (superios[i].io == 0)
+ return &superios[i];
+ return NULL;
+}
+
+
/* Super-IO chipset detection, Winbond, SMSC */
static void __devinit show_parconfig_smsc37c669(int io, int key)
{
- int cr1,cr4,cra,cr23,cr26,cr27,i=0;
- static const char *const modes[]={
+ int cr1, cr4, cra, cr23, cr26, cr27;
+ struct superio_struct *s;
+
+ static const char *const modes[] = {
"SPP and Bidirectional (PS/2)",
"EPP and SPP",
"ECP",
"ECP and EPP" };
- outb(key,io);
- outb(key,io);
- outb(1,io);
- cr1=inb(io+1);
- outb(4,io);
- cr4=inb(io+1);
- outb(0x0a,io);
- cra=inb(io+1);
- outb(0x23,io);
- cr23=inb(io+1);
- outb(0x26,io);
- cr26=inb(io+1);
- outb(0x27,io);
- cr27=inb(io+1);
- outb(0xaa,io);
+ outb(key, io);
+ outb(key, io);
+ outb(1, io);
+ cr1 = inb(io + 1);
+ outb(4, io);
+ cr4 = inb(io + 1);
+ outb(0x0a, io);
+ cra = inb(io + 1);
+ outb(0x23, io);
+ cr23 = inb(io + 1);
+ outb(0x26, io);
+ cr26 = inb(io + 1);
+ outb(0x27, io);
+ cr27 = inb(io + 1);
+ outb(0xaa, io);
if (verbose_probing) {
- printk (KERN_INFO "SMSC 37c669 LPT Config: cr_1=0x%02x, 4=0x%02x, "
+ printk(KERN_INFO
+ "SMSC 37c669 LPT Config: cr_1=0x%02x, 4=0x%02x, "
"A=0x%2x, 23=0x%02x, 26=0x%02x, 27=0x%02x\n",
- cr1,cr4,cra,cr23,cr26,cr27);
-
+ cr1, cr4, cra, cr23, cr26, cr27);
+
/* The documentation calls DMA and IRQ-Lines by letters, so
the board maker can/will wire them
appropriately/randomly... G=reserved H=IDE-irq, */
- printk (KERN_INFO "SMSC LPT Config: io=0x%04x, irq=%c, dma=%c, "
- "fifo threshold=%d\n", cr23*4,
- (cr27 &0x0f) ? 'A'-1+(cr27 &0x0f): '-',
- (cr26 &0x0f) ? 'A'-1+(cr26 &0x0f): '-', cra & 0x0f);
+ printk(KERN_INFO
+ "SMSC LPT Config: io=0x%04x, irq=%c, dma=%c, fifo threshold=%d\n",
+ cr23 * 4,
+ (cr27 & 0x0f) ? 'A' - 1 + (cr27 & 0x0f) : '-',
+ (cr26 & 0x0f) ? 'A' - 1 + (cr26 & 0x0f) : '-',
+ cra & 0x0f);
printk(KERN_INFO "SMSC LPT Config: enabled=%s power=%s\n",
- (cr23*4 >=0x100) ?"yes":"no", (cr1 & 4) ? "yes" : "no");
- printk(KERN_INFO "SMSC LPT Config: Port mode=%s, EPP version =%s\n",
- (cr1 & 0x08 ) ? "Standard mode only (SPP)" : modes[cr4 & 0x03],
- (cr4 & 0x40) ? "1.7" : "1.9");
+ (cr23 * 4 >= 0x100) ? "yes" : "no",
+ (cr1 & 4) ? "yes" : "no");
+ printk(KERN_INFO
+ "SMSC LPT Config: Port mode=%s, EPP version =%s\n",
+ (cr1 & 0x08) ? "Standard mode only (SPP)"
+ : modes[cr4 & 0x03],
+ (cr4 & 0x40) ? "1.7" : "1.9");
}
-
+
/* Heuristics ! BIOS setup for this mainboard device limits
the choices to standard settings, i.e. io-address and IRQ
are related, however DMA can be 1 or 3, assume DMA_A=DMA1,
DMA_C=DMA3 (this is true e.g. for TYAN 1564D Tomcat IV) */
- if(cr23*4 >=0x100) { /* if active */
- while((superios[i].io!= 0) && (i<NR_SUPERIOS))
- i++;
- if(i==NR_SUPERIOS)
+ if (cr23 * 4 >= 0x100) { /* if active */
+ s = find_free_superio();
+ if (s == NULL)
printk(KERN_INFO "Super-IO: too many chips!\n");
else {
int d;
- switch (cr23*4) {
- case 0x3bc:
- superios[i].io = 0x3bc;
- superios[i].irq = 7;
- break;
- case 0x378:
- superios[i].io = 0x378;
- superios[i].irq = 7;
- break;
- case 0x278:
- superios[i].io = 0x278;
- superios[i].irq = 5;
+ switch (cr23 * 4) {
+ case 0x3bc:
+ s->io = 0x3bc;
+ s->irq = 7;
+ break;
+ case 0x378:
+ s->io = 0x378;
+ s->irq = 7;
+ break;
+ case 0x278:
+ s->io = 0x278;
+ s->irq = 5;
}
- d=(cr26 &0x0f);
- if((d==1) || (d==3))
- superios[i].dma= d;
+ d = (cr26 & 0x0f);
+ if (d == 1 || d == 3)
+ s->dma = d;
else
- superios[i].dma= PARPORT_DMA_NONE;
+ s->dma = PARPORT_DMA_NONE;
}
- }
+ }
}
static void __devinit show_parconfig_winbond(int io, int key)
{
- int cr30,cr60,cr61,cr70,cr74,crf0,i=0;
+ int cr30, cr60, cr61, cr70, cr74, crf0;
+ struct superio_struct *s;
static const char *const modes[] = {
"Standard (SPP) and Bidirectional(PS/2)", /* 0 */
"EPP-1.9 and SPP",
static char *const irqtypes[] = {
"pulsed low, high-Z",
"follows nACK" };
-
+
/* The registers are called compatible-PnP because the
- register layout is modelled after ISA-PnP, the access
- method is just another ... */
- outb(key,io);
- outb(key,io);
- outb(0x07,io); /* Register 7: Select Logical Device */
- outb(0x01,io+1); /* LD1 is Parallel Port */
- outb(0x30,io);
- cr30=inb(io+1);
- outb(0x60,io);
- cr60=inb(io+1);
- outb(0x61,io);
- cr61=inb(io+1);
- outb(0x70,io);
- cr70=inb(io+1);
- outb(0x74,io);
- cr74=inb(io+1);
- outb(0xf0,io);
- crf0=inb(io+1);
- outb(0xaa,io);
+ register layout is modelled after ISA-PnP, the access
+ method is just another ... */
+ outb(key, io);
+ outb(key, io);
+ outb(0x07, io); /* Register 7: Select Logical Device */
+ outb(0x01, io + 1); /* LD1 is Parallel Port */
+ outb(0x30, io);
+ cr30 = inb(io + 1);
+ outb(0x60, io);
+ cr60 = inb(io + 1);
+ outb(0x61, io);
+ cr61 = inb(io + 1);
+ outb(0x70, io);
+ cr70 = inb(io + 1);
+ outb(0x74, io);
+ cr74 = inb(io + 1);
+ outb(0xf0, io);
+ crf0 = inb(io + 1);
+ outb(0xaa, io);
if (verbose_probing) {
- printk(KERN_INFO "Winbond LPT Config: cr_30=%02x 60,61=%02x%02x "
- "70=%02x 74=%02x, f0=%02x\n", cr30,cr60,cr61,cr70,cr74,crf0);
- printk(KERN_INFO "Winbond LPT Config: active=%s, io=0x%02x%02x irq=%d, ",
- (cr30 & 0x01) ? "yes":"no", cr60,cr61,cr70&0x0f );
+ printk(KERN_INFO
+ "Winbond LPT Config: cr_30=%02x 60,61=%02x%02x 70=%02x 74=%02x, f0=%02x\n",
+ cr30, cr60, cr61, cr70, cr74, crf0);
+ printk(KERN_INFO "Winbond LPT Config: active=%s, io=0x%02x%02x irq=%d, ",
+ (cr30 & 0x01) ? "yes" : "no", cr60, cr61, cr70 & 0x0f);
if ((cr74 & 0x07) > 3)
printk("dma=none\n");
else
- printk("dma=%d\n",cr74 & 0x07);
- printk(KERN_INFO "Winbond LPT Config: irqtype=%s, ECP fifo threshold=%d\n",
- irqtypes[crf0>>7], (crf0>>3)&0x0f);
- printk(KERN_INFO "Winbond LPT Config: Port mode=%s\n", modes[crf0 & 0x07]);
+ printk("dma=%d\n", cr74 & 0x07);
+ printk(KERN_INFO
+ "Winbond LPT Config: irqtype=%s, ECP fifo threshold=%d\n",
+ irqtypes[crf0>>7], (crf0>>3)&0x0f);
+ printk(KERN_INFO "Winbond LPT Config: Port mode=%s\n",
+ modes[crf0 & 0x07]);
}
- if(cr30 & 0x01) { /* the settings can be interrogated later ... */
- while((superios[i].io!= 0) && (i<NR_SUPERIOS))
- i++;
- if(i==NR_SUPERIOS)
+ if (cr30 & 0x01) { /* the settings can be interrogated later ... */
+ s = find_free_superio();
+ if (s == NULL)
printk(KERN_INFO "Super-IO: too many chips!\n");
else {
- superios[i].io = (cr60<<8)|cr61;
- superios[i].irq = cr70&0x0f;
- superios[i].dma = (((cr74 & 0x07) > 3) ?
+ s->io = (cr60 << 8) | cr61;
+ s->irq = cr70 & 0x0f;
+ s->dma = (((cr74 & 0x07) > 3) ?
PARPORT_DMA_NONE : (cr74 & 0x07));
}
}
}
-static void __devinit decode_winbond(int efer, int key, int devid, int devrev, int oldid)
+static void __devinit decode_winbond(int efer, int key, int devid,
+ int devrev, int oldid)
{
const char *type = "unknown";
- int id,progif=2;
+ int id, progif = 2;
if (devid == devrev)
/* simple heuristics, we happened to read some
- non-winbond register */
+ non-winbond register */
return;
- id=(devid<<8) | devrev;
+ id = (devid << 8) | devrev;
/* Values are from public data sheets pdf files, I can just
- confirm 83977TF is correct :-) */
- if (id == 0x9771) type="83977F/AF";
- else if (id == 0x9773) type="83977TF / SMSC 97w33x/97w34x";
- else if (id == 0x9774) type="83977ATF";
- else if ((id & ~0x0f) == 0x5270) type="83977CTF / SMSC 97w36x";
- else if ((id & ~0x0f) == 0x52f0) type="83977EF / SMSC 97w35x";
- else if ((id & ~0x0f) == 0x5210) type="83627";
- else if ((id & ~0x0f) == 0x6010) type="83697HF";
- else if ((oldid &0x0f ) == 0x0a) { type="83877F"; progif=1;}
- else if ((oldid &0x0f ) == 0x0b) { type="83877AF"; progif=1;}
- else if ((oldid &0x0f ) == 0x0c) { type="83877TF"; progif=1;}
- else if ((oldid &0x0f ) == 0x0d) { type="83877ATF"; progif=1;}
- else progif=0;
+ confirm 83977TF is correct :-) */
+ if (id == 0x9771)
+ type = "83977F/AF";
+ else if (id == 0x9773)
+ type = "83977TF / SMSC 97w33x/97w34x";
+ else if (id == 0x9774)
+ type = "83977ATF";
+ else if ((id & ~0x0f) == 0x5270)
+ type = "83977CTF / SMSC 97w36x";
+ else if ((id & ~0x0f) == 0x52f0)
+ type = "83977EF / SMSC 97w35x";
+ else if ((id & ~0x0f) == 0x5210)
+ type = "83627";
+ else if ((id & ~0x0f) == 0x6010)
+ type = "83697HF";
+ else if ((oldid & 0x0f) == 0x0a) {
+ type = "83877F";
+ progif = 1;
+ } else if ((oldid & 0x0f) == 0x0b) {
+ type = "83877AF";
+ progif = 1;
+ } else if ((oldid & 0x0f) == 0x0c) {
+ type = "83877TF";
+ progif = 1;
+ } else if ((oldid & 0x0f) == 0x0d) {
+ type = "83877ATF";
+ progif = 1;
+ } else
+ progif = 0;
if (verbose_probing)
printk(KERN_INFO "Winbond chip at EFER=0x%x key=0x%02x "
- "devid=%02x devrev=%02x oldid=%02x type=%s\n",
+ "devid=%02x devrev=%02x oldid=%02x type=%s\n",
efer, key, devid, devrev, oldid, type);
if (progif == 2)
- show_parconfig_winbond(efer,key);
+ show_parconfig_winbond(efer, key);
}
static void __devinit decode_smsc(int efer, int key, int devid, int devrev)
{
- const char *type = "unknown";
+ const char *type = "unknown";
void (*func)(int io, int key);
- int id;
+ int id;
- if (devid == devrev)
+ if (devid == devrev)
/* simple heuristics, we happened to read some
- non-smsc register */
+ non-smsc register */
return;
- func=NULL;
- id=(devid<<8) | devrev;
+ func = NULL;
+ id = (devid << 8) | devrev;
- if (id==0x0302) {type="37c669"; func=show_parconfig_smsc37c669;}
- else if (id==0x6582) type="37c665IR";
- else if (devid==0x65) type="37c665GT";
- else if (devid==0x66) type="37c666GT";
+ if (id == 0x0302) {
+ type = "37c669";
+ func = show_parconfig_smsc37c669;
+ } else if (id == 0x6582)
+ type = "37c665IR";
+ else if (devid == 0x65)
+ type = "37c665GT";
+ else if (devid == 0x66)
+ type = "37c666GT";
if (verbose_probing)
printk(KERN_INFO "SMSC chip at EFER=0x%x "
efer, key, devid, devrev, type);
if (func)
- func(efer,key);
+ func(efer, key);
}
static void __devinit winbond_check(int io, int key)
{
- int devid,devrev,oldid,x_devid,x_devrev,x_oldid;
+ int devid, devrev, oldid, x_devid, x_devrev, x_oldid;
if (!request_region(io, 3, __func__))
return;
/* First probe without key */
- outb(0x20,io);
- x_devid=inb(io+1);
- outb(0x21,io);
- x_devrev=inb(io+1);
- outb(0x09,io);
- x_oldid=inb(io+1);
-
- outb(key,io);
- outb(key,io); /* Write Magic Sequence to EFER, extended
- funtion enable register */
- outb(0x20,io); /* Write EFIR, extended function index register */
- devid=inb(io+1); /* Read EFDR, extended function data register */
- outb(0x21,io);
- devrev=inb(io+1);
- outb(0x09,io);
- oldid=inb(io+1);
- outb(0xaa,io); /* Magic Seal */
+ outb(0x20, io);
+ x_devid = inb(io + 1);
+ outb(0x21, io);
+ x_devrev = inb(io + 1);
+ outb(0x09, io);
+ x_oldid = inb(io + 1);
+
+ outb(key, io);
+ outb(key, io); /* Write Magic Sequence to EFER, extended
+ funtion enable register */
+ outb(0x20, io); /* Write EFIR, extended function index register */
+ devid = inb(io + 1); /* Read EFDR, extended function data register */
+ outb(0x21, io);
+ devrev = inb(io + 1);
+ outb(0x09, io);
+ oldid = inb(io + 1);
+ outb(0xaa, io); /* Magic Seal */
if ((x_devid == devid) && (x_devrev == devrev) && (x_oldid == oldid))
goto out; /* protection against false positives */
- decode_winbond(io,key,devid,devrev,oldid);
+ decode_winbond(io, key, devid, devrev, oldid);
out:
release_region(io, 3);
}
-static void __devinit winbond_check2(int io,int key)
+static void __devinit winbond_check2(int io, int key)
{
- int devid,devrev,oldid,x_devid,x_devrev,x_oldid;
+ int devid, devrev, oldid, x_devid, x_devrev, x_oldid;
if (!request_region(io, 3, __func__))
return;
/* First probe without the key */
- outb(0x20,io+2);
- x_devid=inb(io+2);
- outb(0x21,io+1);
- x_devrev=inb(io+2);
- outb(0x09,io+1);
- x_oldid=inb(io+2);
-
- outb(key,io); /* Write Magic Byte to EFER, extended
- funtion enable register */
- outb(0x20,io+2); /* Write EFIR, extended function index register */
- devid=inb(io+2); /* Read EFDR, extended function data register */
- outb(0x21,io+1);
- devrev=inb(io+2);
- outb(0x09,io+1);
- oldid=inb(io+2);
- outb(0xaa,io); /* Magic Seal */
-
- if ((x_devid == devid) && (x_devrev == devrev) && (x_oldid == oldid))
+ outb(0x20, io + 2);
+ x_devid = inb(io + 2);
+ outb(0x21, io + 1);
+ x_devrev = inb(io + 2);
+ outb(0x09, io + 1);
+ x_oldid = inb(io + 2);
+
+ outb(key, io); /* Write Magic Byte to EFER, extended
+ funtion enable register */
+ outb(0x20, io + 2); /* Write EFIR, extended function index register */
+ devid = inb(io + 2); /* Read EFDR, extended function data register */
+ outb(0x21, io + 1);
+ devrev = inb(io + 2);
+ outb(0x09, io + 1);
+ oldid = inb(io + 2);
+ outb(0xaa, io); /* Magic Seal */
+
+ if (x_devid == devid && x_devrev == devrev && x_oldid == oldid)
goto out; /* protection against false positives */
- decode_winbond(io,key,devid,devrev,oldid);
+ decode_winbond(io, key, devid, devrev, oldid);
out:
release_region(io, 3);
}
static void __devinit smsc_check(int io, int key)
{
- int id,rev,oldid,oldrev,x_id,x_rev,x_oldid,x_oldrev;
+ int id, rev, oldid, oldrev, x_id, x_rev, x_oldid, x_oldrev;
if (!request_region(io, 3, __func__))
return;
/* First probe without the key */
- outb(0x0d,io);
- x_oldid=inb(io+1);
- outb(0x0e,io);
- x_oldrev=inb(io+1);
- outb(0x20,io);
- x_id=inb(io+1);
- outb(0x21,io);
- x_rev=inb(io+1);
-
- outb(key,io);
- outb(key,io); /* Write Magic Sequence to EFER, extended
- funtion enable register */
- outb(0x0d,io); /* Write EFIR, extended function index register */
- oldid=inb(io+1); /* Read EFDR, extended function data register */
- outb(0x0e,io);
- oldrev=inb(io+1);
- outb(0x20,io);
- id=inb(io+1);
- outb(0x21,io);
- rev=inb(io+1);
- outb(0xaa,io); /* Magic Seal */
-
- if ((x_id == id) && (x_oldrev == oldrev) &&
- (x_oldid == oldid) && (x_rev == rev))
+ outb(0x0d, io);
+ x_oldid = inb(io + 1);
+ outb(0x0e, io);
+ x_oldrev = inb(io + 1);
+ outb(0x20, io);
+ x_id = inb(io + 1);
+ outb(0x21, io);
+ x_rev = inb(io + 1);
+
+ outb(key, io);
+ outb(key, io); /* Write Magic Sequence to EFER, extended
+ funtion enable register */
+ outb(0x0d, io); /* Write EFIR, extended function index register */
+ oldid = inb(io + 1); /* Read EFDR, extended function data register */
+ outb(0x0e, io);
+ oldrev = inb(io + 1);
+ outb(0x20, io);
+ id = inb(io + 1);
+ outb(0x21, io);
+ rev = inb(io + 1);
+ outb(0xaa, io); /* Magic Seal */
+
+ if (x_id == id && x_oldrev == oldrev &&
+ x_oldid == oldid && x_rev == rev)
goto out; /* protection against false positives */
- decode_smsc(io,key,oldid,oldrev);
+ decode_smsc(io, key, oldid, oldrev);
out:
release_region(io, 3);
}
-static void __devinit detect_and_report_winbond (void)
-{
+static void __devinit detect_and_report_winbond(void)
+{
if (verbose_probing)
printk(KERN_DEBUG "Winbond Super-IO detection, now testing ports 3F0,370,250,4E,2E ...\n");
- winbond_check(0x3f0,0x87);
- winbond_check(0x370,0x87);
- winbond_check(0x2e ,0x87);
- winbond_check(0x4e ,0x87);
- winbond_check(0x3f0,0x86);
- winbond_check2(0x250,0x88);
- winbond_check2(0x250,0x89);
+ winbond_check(0x3f0, 0x87);
+ winbond_check(0x370, 0x87);
+ winbond_check(0x2e , 0x87);
+ winbond_check(0x4e , 0x87);
+ winbond_check(0x3f0, 0x86);
+ winbond_check2(0x250, 0x88);
+ winbond_check2(0x250, 0x89);
}
-static void __devinit detect_and_report_smsc (void)
+static void __devinit detect_and_report_smsc(void)
{
if (verbose_probing)
printk(KERN_DEBUG "SMSC Super-IO detection, now testing Ports 2F0, 370 ...\n");
- smsc_check(0x3f0,0x55);
- smsc_check(0x370,0x55);
- smsc_check(0x3f0,0x44);
- smsc_check(0x370,0x44);
+ smsc_check(0x3f0, 0x55);
+ smsc_check(0x370, 0x55);
+ smsc_check(0x3f0, 0x44);
+ smsc_check(0x370, 0x44);
}
static void __devinit detect_and_report_it87(void)
}
#endif /* CONFIG_PARPORT_PC_SUPERIO */
-static int get_superio_dma (struct parport *p)
+static struct superio_struct *find_superio(struct parport *p)
{
- int i=0;
- while( (superios[i].io != p->base) && (i<NR_SUPERIOS))
- i++;
- if (i!=NR_SUPERIOS)
- return superios[i].dma;
+ int i;
+ for (i = 0; i < NR_SUPERIOS; i++)
+ if (superios[i].io != p->base)
+ return &superios[i];
+ return NULL;
+}
+
+static int get_superio_dma(struct parport *p)
+{
+ struct superio_struct *s = find_superio(p);
+ if (s)
+ return s->dma;
return PARPORT_DMA_NONE;
}
-static int get_superio_irq (struct parport *p)
+static int get_superio_irq(struct parport *p)
{
- int i=0;
- while( (superios[i].io != p->base) && (i<NR_SUPERIOS))
- i++;
- if (i!=NR_SUPERIOS)
- return superios[i].irq;
- return PARPORT_IRQ_NONE;
+ struct superio_struct *s = find_superio(p);
+ if (s)
+ return s->irq;
+ return PARPORT_IRQ_NONE;
}
-
+
/* --- Mode detection ------------------------------------- */
/*
* Checks for port existence, all ports support SPP MODE
- * Returns:
+ * Returns:
* 0 : No parallel port at this address
- * PARPORT_MODE_PCSPP : SPP port detected
+ * PARPORT_MODE_PCSPP : SPP port detected
* (if the user specified an ioport himself,
* this shall always be the case!)
*
unsigned char r, w;
/*
- * first clear an eventually pending EPP timeout
+ * first clear an eventually pending EPP timeout
* I (sailer@ife.ee.ethz.ch) have an SMSC chipset
* that does not even respond to SPP cycles if an EPP
* timeout is pending
/* Do a simple read-write test to make sure the port exists. */
w = 0xc;
- outb (w, CONTROL (pb));
+ outb(w, CONTROL(pb));
/* Is there a control register that we can read from? Some
* ports don't allow reads, so read_control just returns a
* software copy. Some ports _do_ allow reads, so bypass the
* software copy here. In addition, some bits aren't
* writable. */
- r = inb (CONTROL (pb));
+ r = inb(CONTROL(pb));
if ((r & 0xf) == w) {
w = 0xe;
- outb (w, CONTROL (pb));
- r = inb (CONTROL (pb));
- outb (0xc, CONTROL (pb));
+ outb(w, CONTROL(pb));
+ r = inb(CONTROL(pb));
+ outb(0xc, CONTROL(pb));
if ((r & 0xf) == w)
return PARPORT_MODE_PCSPP;
}
if (user_specified)
/* That didn't work, but the user thinks there's a
* port here. */
- printk (KERN_INFO "parport 0x%lx (WARNING): CTR: "
+ printk(KERN_INFO "parport 0x%lx (WARNING): CTR: "
"wrote 0x%02x, read 0x%02x\n", pb->base, w, r);
/* Try the data register. The data lines aren't tri-stated at
* this stage, so we expect back what we wrote. */
w = 0xaa;
- parport_pc_write_data (pb, w);
- r = parport_pc_read_data (pb);
+ parport_pc_write_data(pb, w);
+ r = parport_pc_read_data(pb);
if (r == w) {
w = 0x55;
- parport_pc_write_data (pb, w);
- r = parport_pc_read_data (pb);
+ parport_pc_write_data(pb, w);
+ r = parport_pc_read_data(pb);
if (r == w)
return PARPORT_MODE_PCSPP;
}
if (user_specified) {
/* Didn't work, but the user is convinced this is the
* place. */
- printk (KERN_INFO "parport 0x%lx (WARNING): DATA: "
+ printk(KERN_INFO "parport 0x%lx (WARNING): DATA: "
"wrote 0x%02x, read 0x%02x\n", pb->base, w, r);
- printk (KERN_INFO "parport 0x%lx: You gave this address, "
+ printk(KERN_INFO "parport 0x%lx: You gave this address, "
"but there is probably no parallel port there!\n",
pb->base);
}
struct parport_pc_private *priv = pb->private_data;
unsigned char r = 0xc;
- outb (r, CONTROL (pb));
- if ((inb (ECONTROL (pb)) & 0x3) == (r & 0x3)) {
- outb (r ^ 0x2, CONTROL (pb)); /* Toggle bit 1 */
+ outb(r, CONTROL(pb));
+ if ((inb(ECONTROL(pb)) & 0x3) == (r & 0x3)) {
+ outb(r ^ 0x2, CONTROL(pb)); /* Toggle bit 1 */
- r = inb (CONTROL (pb));
- if ((inb (ECONTROL (pb)) & 0x2) == (r & 0x2))
+ r = inb(CONTROL(pb));
+ if ((inb(ECONTROL(pb)) & 0x2) == (r & 0x2))
goto no_reg; /* Sure that no ECR register exists */
}
-
- if ((inb (ECONTROL (pb)) & 0x3 ) != 0x1)
+
+ if ((inb(ECONTROL(pb)) & 0x3) != 0x1)
goto no_reg;
- ECR_WRITE (pb, 0x34);
- if (inb (ECONTROL (pb)) != 0x35)
+ ECR_WRITE(pb, 0x34);
+ if (inb(ECONTROL(pb)) != 0x35)
goto no_reg;
priv->ecr = 1;
- outb (0xc, CONTROL (pb));
-
+ outb(0xc, CONTROL(pb));
+
/* Go to mode 000 */
- frob_set_mode (pb, ECR_SPP);
+ frob_set_mode(pb, ECR_SPP);
return 1;
no_reg:
- outb (0xc, CONTROL (pb));
- return 0;
+ outb(0xc, CONTROL(pb));
+ return 0;
}
#ifdef CONFIG_PARPORT_1284
* allows us to read data from the data lines. In theory we would get back
* 0xff but any peripheral attached to the port may drag some or all of the
* lines down to zero. So if we get back anything that isn't the contents
- * of the data register we deem PS/2 support to be present.
+ * of the data register we deem PS/2 support to be present.
*
* Some SPP ports have "half PS/2" ability - you can't turn off the line
* drivers, but an external peripheral with sufficiently beefy drivers of
* where they can then be read back as normal. Ports with this property
* and the right type of device attached are likely to fail the SPP test,
* (as they will appear to have stuck bits) and so the fact that they might
- * be misdetected here is rather academic.
+ * be misdetected here is rather academic.
*/
static int parport_PS2_supported(struct parport *pb)
{
int ok = 0;
-
+
clear_epp_timeout(pb);
/* try to tri-state the buffer */
- parport_pc_data_reverse (pb);
-
+ parport_pc_data_reverse(pb);
+
parport_pc_write_data(pb, 0x55);
- if (parport_pc_read_data(pb) != 0x55) ok++;
+ if (parport_pc_read_data(pb) != 0x55)
+ ok++;
parport_pc_write_data(pb, 0xaa);
- if (parport_pc_read_data(pb) != 0xaa) ok++;
+ if (parport_pc_read_data(pb) != 0xaa)
+ ok++;
/* cancel input mode */
- parport_pc_data_forward (pb);
+ parport_pc_data_forward(pb);
if (ok) {
pb->modes |= PARPORT_MODE_TRISTATE;
int config, configb;
int pword;
struct parport_pc_private *priv = pb->private_data;
- /* Translate ECP intrLine to ISA irq value */
- static const int intrline[]= { 0, 7, 9, 10, 11, 14, 15, 5 };
+ /* Translate ECP intrLine to ISA irq value */
+ static const int intrline[] = { 0, 7, 9, 10, 11, 14, 15, 5 };
/* If there is no ECR, we have no hope of supporting ECP. */
if (!priv->ecr)
return 0;
/* Find out FIFO depth */
- ECR_WRITE (pb, ECR_SPP << 5); /* Reset FIFO */
- ECR_WRITE (pb, ECR_TST << 5); /* TEST FIFO */
- for (i=0; i < 1024 && !(inb (ECONTROL (pb)) & 0x02); i++)
- outb (0xaa, FIFO (pb));
+ ECR_WRITE(pb, ECR_SPP << 5); /* Reset FIFO */
+ ECR_WRITE(pb, ECR_TST << 5); /* TEST FIFO */
+ for (i = 0; i < 1024 && !(inb(ECONTROL(pb)) & 0x02); i++)
+ outb(0xaa, FIFO(pb));
/*
* Using LGS chipset it uses ECR register, but
* it doesn't support ECP or FIFO MODE
*/
if (i == 1024) {
- ECR_WRITE (pb, ECR_SPP << 5);
+ ECR_WRITE(pb, ECR_SPP << 5);
return 0;
}
priv->fifo_depth = i;
if (verbose_probing)
- printk (KERN_DEBUG "0x%lx: FIFO is %d bytes\n", pb->base, i);
+ printk(KERN_DEBUG "0x%lx: FIFO is %d bytes\n", pb->base, i);
/* Find out writeIntrThreshold */
- frob_econtrol (pb, 1<<2, 1<<2);
- frob_econtrol (pb, 1<<2, 0);
+ frob_econtrol(pb, 1<<2, 1<<2);
+ frob_econtrol(pb, 1<<2, 0);
for (i = 1; i <= priv->fifo_depth; i++) {
- inb (FIFO (pb));
- udelay (50);
- if (inb (ECONTROL (pb)) & (1<<2))
+ inb(FIFO(pb));
+ udelay(50);
+ if (inb(ECONTROL(pb)) & (1<<2))
break;
}
if (i <= priv->fifo_depth) {
if (verbose_probing)
- printk (KERN_DEBUG "0x%lx: writeIntrThreshold is %d\n",
+ printk(KERN_DEBUG "0x%lx: writeIntrThreshold is %d\n",
pb->base, i);
} else
/* Number of bytes we know we can write if we get an
- interrupt. */
+ interrupt. */
i = 0;
priv->writeIntrThreshold = i;
/* Find out readIntrThreshold */
- frob_set_mode (pb, ECR_PS2); /* Reset FIFO and enable PS2 */
- parport_pc_data_reverse (pb); /* Must be in PS2 mode */
- frob_set_mode (pb, ECR_TST); /* Test FIFO */
- frob_econtrol (pb, 1<<2, 1<<2);
- frob_econtrol (pb, 1<<2, 0);
+ frob_set_mode(pb, ECR_PS2); /* Reset FIFO and enable PS2 */
+ parport_pc_data_reverse(pb); /* Must be in PS2 mode */
+ frob_set_mode(pb, ECR_TST); /* Test FIFO */
+ frob_econtrol(pb, 1<<2, 1<<2);
+ frob_econtrol(pb, 1<<2, 0);
for (i = 1; i <= priv->fifo_depth; i++) {
- outb (0xaa, FIFO (pb));
- if (inb (ECONTROL (pb)) & (1<<2))
+ outb(0xaa, FIFO(pb));
+ if (inb(ECONTROL(pb)) & (1<<2))
break;
}
if (i <= priv->fifo_depth) {
if (verbose_probing)
- printk (KERN_INFO "0x%lx: readIntrThreshold is %d\n",
+ printk(KERN_INFO "0x%lx: readIntrThreshold is %d\n",
pb->base, i);
} else
/* Number of bytes we can read if we get an interrupt. */
priv->readIntrThreshold = i;
- ECR_WRITE (pb, ECR_SPP << 5); /* Reset FIFO */
- ECR_WRITE (pb, 0xf4); /* Configuration mode */
- config = inb (CONFIGA (pb));
+ ECR_WRITE(pb, ECR_SPP << 5); /* Reset FIFO */
+ ECR_WRITE(pb, 0xf4); /* Configuration mode */
+ config = inb(CONFIGA(pb));
pword = (config >> 4) & 0x7;
switch (pword) {
case 0:
pword = 2;
- printk (KERN_WARNING "0x%lx: Unsupported pword size!\n",
+ printk(KERN_WARNING "0x%lx: Unsupported pword size!\n",
pb->base);
break;
case 2:
pword = 4;
- printk (KERN_WARNING "0x%lx: Unsupported pword size!\n",
+ printk(KERN_WARNING "0x%lx: Unsupported pword size!\n",
pb->base);
break;
default:
- printk (KERN_WARNING "0x%lx: Unknown implementation ID\n",
+ printk(KERN_WARNING "0x%lx: Unknown implementation ID\n",
pb->base);
/* Assume 1 */
case 1:
priv->pword = pword;
if (verbose_probing) {
- printk (KERN_DEBUG "0x%lx: PWord is %d bits\n", pb->base, 8 * pword);
-
- printk (KERN_DEBUG "0x%lx: Interrupts are ISA-%s\n", pb->base,
+ printk(KERN_DEBUG "0x%lx: PWord is %d bits\n",
+ pb->base, 8 * pword);
+
+ printk(KERN_DEBUG "0x%lx: Interrupts are ISA-%s\n", pb->base,
config & 0x80 ? "Level" : "Pulses");
- configb = inb (CONFIGB (pb));
- printk (KERN_DEBUG "0x%lx: ECP port cfgA=0x%02x cfgB=0x%02x\n",
+ configb = inb(CONFIGB(pb));
+ printk(KERN_DEBUG "0x%lx: ECP port cfgA=0x%02x cfgB=0x%02x\n",
pb->base, config, configb);
- printk (KERN_DEBUG "0x%lx: ECP settings irq=", pb->base);
- if ((configb >>3) & 0x07)
- printk("%d",intrline[(configb >>3) & 0x07]);
+ printk(KERN_DEBUG "0x%lx: ECP settings irq=", pb->base);
+ if ((configb >> 3) & 0x07)
+ printk("%d", intrline[(configb >> 3) & 0x07]);
else
printk("<none or set by other means>");
- printk (" dma=");
- if( (configb & 0x03 ) == 0x00)
+ printk(" dma=");
+ if ((configb & 0x03) == 0x00)
printk("<none or set by other means>\n");
else
- printk("%d\n",configb & 0x07);
+ printk("%d\n", configb & 0x07);
}
/* Go back to mode 000 */
- frob_set_mode (pb, ECR_SPP);
+ frob_set_mode(pb, ECR_SPP);
return 1;
}
if (!priv->ecr)
return 0;
- oecr = inb (ECONTROL (pb));
- ECR_WRITE (pb, ECR_PS2 << 5);
+ oecr = inb(ECONTROL(pb));
+ ECR_WRITE(pb, ECR_PS2 << 5);
result = parport_PS2_supported(pb);
- ECR_WRITE (pb, oecr);
+ ECR_WRITE(pb, oecr);
return result;
}
*/
/* If EPP timeout bit clear then EPP available */
- if (!clear_epp_timeout(pb)) {
+ if (!clear_epp_timeout(pb))
return 0; /* No way to clear timeout */
- }
/* Check for Intel bug. */
if (priv->ecr) {
unsigned char i;
for (i = 0x00; i < 0x80; i += 0x20) {
- ECR_WRITE (pb, i);
- if (clear_epp_timeout (pb)) {
+ ECR_WRITE(pb, i);
+ if (clear_epp_timeout(pb)) {
/* Phony EPP in ECP. */
return 0;
}
int result;
unsigned char oecr;
- if (!priv->ecr) {
+ if (!priv->ecr)
return 0;
- }
- oecr = inb (ECONTROL (pb));
+ oecr = inb(ECONTROL(pb));
/* Search for SMC style EPP+ECP mode */
- ECR_WRITE (pb, 0x80);
- outb (0x04, CONTROL (pb));
+ ECR_WRITE(pb, 0x80);
+ outb(0x04, CONTROL(pb));
result = parport_EPP_supported(pb);
- ECR_WRITE (pb, oecr);
+ ECR_WRITE(pb, oecr);
if (result) {
/* Set up access functions to use ECP+EPP hardware. */
/* Don't bother probing for modes we know we won't use. */
static int __devinit parport_PS2_supported(struct parport *pb) { return 0; }
#ifdef CONFIG_PARPORT_PC_FIFO
-static int parport_ECP_supported(struct parport *pb) { return 0; }
+static int parport_ECP_supported(struct parport *pb)
+{
+ return 0;
+}
#endif
-static int __devinit parport_EPP_supported(struct parport *pb) { return 0; }
-static int __devinit parport_ECPEPP_supported(struct parport *pb){return 0;}
-static int __devinit parport_ECPPS2_supported(struct parport *pb){return 0;}
+static int __devinit parport_EPP_supported(struct parport *pb)
+{
+ return 0;
+}
+
+static int __devinit parport_ECPEPP_supported(struct parport *pb)
+{
+ return 0;
+}
+
+static int __devinit parport_ECPPS2_supported(struct parport *pb)
+{
+ return 0;
+}
#endif /* No IEEE 1284 support */
static int programmable_irq_support(struct parport *pb)
{
int irq, intrLine;
- unsigned char oecr = inb (ECONTROL (pb));
+ unsigned char oecr = inb(ECONTROL(pb));
static const int lookup[8] = {
PARPORT_IRQ_NONE, 7, 9, 10, 11, 14, 15, 5
};
- ECR_WRITE (pb, ECR_CNF << 5); /* Configuration MODE */
+ ECR_WRITE(pb, ECR_CNF << 5); /* Configuration MODE */
- intrLine = (inb (CONFIGB (pb)) >> 3) & 0x07;
+ intrLine = (inb(CONFIGB(pb)) >> 3) & 0x07;
irq = lookup[intrLine];
- ECR_WRITE (pb, oecr);
+ ECR_WRITE(pb, oecr);
return irq;
}
unsigned long irqs;
irqs = probe_irq_on();
-
- ECR_WRITE (pb, ECR_SPP << 5); /* Reset FIFO */
- ECR_WRITE (pb, (ECR_TST << 5) | 0x04);
- ECR_WRITE (pb, ECR_TST << 5);
+
+ ECR_WRITE(pb, ECR_SPP << 5); /* Reset FIFO */
+ ECR_WRITE(pb, (ECR_TST << 5) | 0x04);
+ ECR_WRITE(pb, ECR_TST << 5);
/* If Full FIFO sure that writeIntrThreshold is generated */
- for (i=0; i < 1024 && !(inb (ECONTROL (pb)) & 0x02) ; i++)
- outb (0xaa, FIFO (pb));
-
+ for (i = 0; i < 1024 && !(inb(ECONTROL(pb)) & 0x02) ; i++)
+ outb(0xaa, FIFO(pb));
+
pb->irq = probe_irq_off(irqs);
- ECR_WRITE (pb, ECR_SPP << 5);
+ ECR_WRITE(pb, ECR_SPP << 5);
if (pb->irq <= 0)
pb->irq = PARPORT_IRQ_NONE;
/*
* This detection seems that only works in National Semiconductors
- * This doesn't work in SMC, LGS, and Winbond
+ * This doesn't work in SMC, LGS, and Winbond
*/
static int irq_probe_EPP(struct parport *pb)
{
unsigned char oecr;
if (pb->modes & PARPORT_MODE_PCECR)
- oecr = inb (ECONTROL (pb));
+ oecr = inb(ECONTROL(pb));
irqs = probe_irq_on();
if (pb->modes & PARPORT_MODE_PCECR)
- frob_econtrol (pb, 0x10, 0x10);
-
+ frob_econtrol(pb, 0x10, 0x10);
+
clear_epp_timeout(pb);
- parport_pc_frob_control (pb, 0x20, 0x20);
- parport_pc_frob_control (pb, 0x10, 0x10);
+ parport_pc_frob_control(pb, 0x20, 0x20);
+ parport_pc_frob_control(pb, 0x10, 0x10);
clear_epp_timeout(pb);
/* Device isn't expecting an EPP read
parport_pc_read_epp(pb);
udelay(20);
- pb->irq = probe_irq_off (irqs);
+ pb->irq = probe_irq_off(irqs);
if (pb->modes & PARPORT_MODE_PCECR)
- ECR_WRITE (pb, oecr);
+ ECR_WRITE(pb, oecr);
parport_pc_write_control(pb, 0xc);
if (pb->irq <= 0)
/* --- DMA detection -------------------------------------- */
/* Only if chipset conforms to ECP ISA Interface Standard */
-static int programmable_dma_support (struct parport *p)
+static int programmable_dma_support(struct parport *p)
{
- unsigned char oecr = inb (ECONTROL (p));
+ unsigned char oecr = inb(ECONTROL(p));
int dma;
- frob_set_mode (p, ECR_CNF);
-
- dma = inb (CONFIGB(p)) & 0x07;
+ frob_set_mode(p, ECR_CNF);
+
+ dma = inb(CONFIGB(p)) & 0x07;
/* 000: Indicates jumpered 8-bit DMA if read-only.
100: Indicates jumpered 16-bit DMA if read-only. */
if ((dma & 0x03) == 0)
dma = PARPORT_DMA_NONE;
- ECR_WRITE (p, oecr);
+ ECR_WRITE(p, oecr);
return dma;
}
-static int parport_dma_probe (struct parport *p)
+static int parport_dma_probe(struct parport *p)
{
const struct parport_pc_private *priv = p->private_data;
- if (priv->ecr)
- p->dma = programmable_dma_support(p); /* ask ECP chipset first */
+ if (priv->ecr) /* ask ECP chipset first */
+ p->dma = programmable_dma_support(p);
if (p->dma == PARPORT_DMA_NONE) {
/* ask known Super-IO chips proper, although these
claim ECP compatible, some don't report their DMA
if (!base_res)
goto out4;
- memcpy(ops, &parport_pc_ops, sizeof (struct parport_operations));
+ memcpy(ops, &parport_pc_ops, sizeof(struct parport_operations));
priv->ctr = 0xc;
priv->ctr_writable = ~0x10;
priv->ecr = 0;
if (!parport_EPP_supported(p))
parport_ECPEPP_supported(p);
}
- if (!parport_SPP_supported (p))
+ if (!parport_SPP_supported(p))
/* No port. */
goto out5;
if (priv->ecr)
else
parport_PS2_supported(p);
- p->size = (p->modes & PARPORT_MODE_EPP)?8:3;
+ p->size = (p->modes & PARPORT_MODE_EPP) ? 8 : 3;
printk(KERN_INFO "%s: PC-style at 0x%lx", p->name, p->base);
if (p->base_hi && priv->ecr)
}
}
if (p->dma == PARPORT_DMA_AUTO) /* To use DMA, giving the irq
- is mandatory (see above) */
+ is mandatory (see above) */
p->dma = PARPORT_DMA_NONE;
#ifdef CONFIG_PARPORT_PC_FIFO
if (p->dma != PARPORT_DMA_NONE) {
printk(", dma %d", p->dma);
p->modes |= PARPORT_MODE_DMA;
- }
- else printk(", using FIFO");
- }
- else
+ } else
+ printk(", using FIFO");
+ } else
/* We can't use the DMA channel after all. */
p->dma = PARPORT_DMA_NONE;
#endif /* Allowed to use FIFO/DMA */
printk(" [");
-#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}}
+
+#define printmode(x) \
+ {\
+ if (p->modes & PARPORT_MODE_##x) {\
+ printk("%s%s", f ? "," : "", #x);\
+ f++;\
+ } \
+ }
+
{
int f = 0;
printmode(PCSPP);
}
#undef printmode
#ifndef CONFIG_PARPORT_1284
- printk ("(,...)");
+ printk("(,...)");
#endif /* CONFIG_PARPORT_1284 */
printk("]\n");
- if (probedirq != PARPORT_IRQ_NONE)
+ if (probedirq != PARPORT_IRQ_NONE)
printk(KERN_INFO "%s: irq %d detected\n", p->name, probedirq);
/* If No ECP release the ports grabbed above. */
if (p->irq != PARPORT_IRQ_NONE) {
if (request_irq(p->irq, parport_irq_handler,
irqflags, p->name, p)) {
- printk (KERN_WARNING "%s: irq %d in use, "
+ printk(KERN_WARNING "%s: irq %d in use, "
"resorting to polled operation\n",
p->name, p->irq);
p->irq = PARPORT_IRQ_NONE;
#ifdef CONFIG_PARPORT_PC_FIFO
#ifdef HAS_DMA
if (p->dma != PARPORT_DMA_NONE) {
- if (request_dma (p->dma, p->name)) {
- printk (KERN_WARNING "%s: dma %d in use, "
+ if (request_dma(p->dma, p->name)) {
+ printk(KERN_WARNING "%s: dma %d in use, "
"resorting to PIO operation\n",
p->name, p->dma);
p->dma = PARPORT_DMA_NONE;
PAGE_SIZE,
&priv->dma_handle,
GFP_KERNEL);
- if (! priv->dma_buf) {
- printk (KERN_WARNING "%s: "
+ if (!priv->dma_buf) {
+ printk(KERN_WARNING "%s: "
"cannot get buffer for DMA, "
"resorting to PIO operation\n",
p->name);
* Put the ECP detected port in PS2 mode.
* Do this also for ports that have ECR but don't do ECP.
*/
- ECR_WRITE (p, 0x34);
+ ECR_WRITE(p, 0x34);
parport_pc_write_data(p, 0);
- parport_pc_data_forward (p);
+ parport_pc_data_forward(p);
/* Now that we've told the sharing engine about the port, and
found out its characteristics, let the high-level drivers
spin_lock(&ports_lock);
list_add(&priv->list, &ports_list);
spin_unlock(&ports_lock);
- parport_announce_port (p);
+ parport_announce_port(p);
return p;
out4:
parport_put_port(p);
out3:
- kfree (priv);
+ kfree(priv);
out2:
- kfree (ops);
+ kfree(ops);
out1:
if (pdev)
platform_device_unregister(pdev);
return NULL;
}
+EXPORT_SYMBOL(parport_pc_probe_port);
-EXPORT_SYMBOL (parport_pc_probe_port);
-
-void parport_pc_unregister_port (struct parport *p)
+void parport_pc_unregister_port(struct parport *p)
{
struct parport_pc_private *priv = p->private_data;
struct parport_operations *ops = p->ops;
priv->dma_buf,
priv->dma_handle);
#endif
- kfree (p->private_data);
+ kfree(p->private_data);
parport_put_port(p);
- kfree (ops); /* hope no-one cached it */
+ kfree(ops); /* hope no-one cached it */
}
-
-EXPORT_SYMBOL (parport_pc_unregister_port);
+EXPORT_SYMBOL(parport_pc_unregister_port);
#ifdef CONFIG_PCI
/* ITE support maintained by Rich Liu <richliu@poorman.org> */
-static int __devinit sio_ite_8872_probe (struct pci_dev *pdev, int autoirq,
+static int __devinit sio_ite_8872_probe(struct pci_dev *pdev, int autoirq,
int autodma,
const struct parport_pc_via_data *via)
{
int irq;
int i;
- DPRINTK (KERN_DEBUG "sio_ite_8872_probe()\n");
-
- // make sure which one chip
- for(i = 0; i < 5; i++) {
+ DPRINTK(KERN_DEBUG "sio_ite_8872_probe()\n");
+
+ /* make sure which one chip */
+ for (i = 0; i < 5; i++) {
base_res = request_region(inta_addr[i], 32, "it887x");
if (base_res) {
int test;
- pci_write_config_dword (pdev, 0x60,
+ pci_write_config_dword(pdev, 0x60,
0xe5000000 | inta_addr[i]);
- pci_write_config_dword (pdev, 0x78,
+ pci_write_config_dword(pdev, 0x78,
0x00000000 | inta_addr[i]);
- test = inb (inta_addr[i]);
- if (test != 0xff) break;
+ test = inb(inta_addr[i]);
+ if (test != 0xff)
+ break;
release_region(inta_addr[i], 0x8);
}
}
- if(i >= 5) {
- printk (KERN_INFO "parport_pc: cannot find ITE8872 INTA\n");
+ if (i >= 5) {
+ printk(KERN_INFO "parport_pc: cannot find ITE8872 INTA\n");
return 0;
}
- type = inb (inta_addr[i] + 0x18);
+ type = inb(inta_addr[i] + 0x18);
type &= 0x0f;
switch (type) {
case 0x2:
- printk (KERN_INFO "parport_pc: ITE8871 found (1P)\n");
+ printk(KERN_INFO "parport_pc: ITE8871 found (1P)\n");
ite8872set = 0x64200000;
break;
case 0xa:
- printk (KERN_INFO "parport_pc: ITE8875 found (1P)\n");
+ printk(KERN_INFO "parport_pc: ITE8875 found (1P)\n");
ite8872set = 0x64200000;
break;
case 0xe:
- printk (KERN_INFO "parport_pc: ITE8872 found (2S1P)\n");
+ printk(KERN_INFO "parport_pc: ITE8872 found (2S1P)\n");
ite8872set = 0x64e00000;
break;
case 0x6:
- printk (KERN_INFO "parport_pc: ITE8873 found (1S)\n");
+ printk(KERN_INFO "parport_pc: ITE8873 found (1S)\n");
return 0;
case 0x8:
- DPRINTK (KERN_DEBUG "parport_pc: ITE8874 found (2S)\n");
+ DPRINTK(KERN_DEBUG "parport_pc: ITE8874 found (2S)\n");
return 0;
default:
- printk (KERN_INFO "parport_pc: unknown ITE887x\n");
- printk (KERN_INFO "parport_pc: please mail 'lspci -nvv' "
+ printk(KERN_INFO "parport_pc: unknown ITE887x\n");
+ printk(KERN_INFO "parport_pc: please mail 'lspci -nvv' "
"output to Rich.Liu@ite.com.tw\n");
return 0;
}
- pci_read_config_byte (pdev, 0x3c, &ite8872_irq);
- pci_read_config_dword (pdev, 0x1c, &ite8872_lpt);
+ pci_read_config_byte(pdev, 0x3c, &ite8872_irq);
+ pci_read_config_dword(pdev, 0x1c, &ite8872_lpt);
ite8872_lpt &= 0x0000ff00;
- pci_read_config_dword (pdev, 0x20, &ite8872_lpthi);
+ pci_read_config_dword(pdev, 0x20, &ite8872_lpthi);
ite8872_lpthi &= 0x0000ff00;
- pci_write_config_dword (pdev, 0x6c, 0xe3000000 | ite8872_lpt);
- pci_write_config_dword (pdev, 0x70, 0xe3000000 | ite8872_lpthi);
- pci_write_config_dword (pdev, 0x80, (ite8872_lpthi<<16) | ite8872_lpt);
- // SET SPP&EPP , Parallel Port NO DMA , Enable All Function
- // SET Parallel IRQ
- pci_write_config_dword (pdev, 0x9c,
+ pci_write_config_dword(pdev, 0x6c, 0xe3000000 | ite8872_lpt);
+ pci_write_config_dword(pdev, 0x70, 0xe3000000 | ite8872_lpthi);
+ pci_write_config_dword(pdev, 0x80, (ite8872_lpthi<<16) | ite8872_lpt);
+ /* SET SPP&EPP , Parallel Port NO DMA , Enable All Function */
+ /* SET Parallel IRQ */
+ pci_write_config_dword(pdev, 0x9c,
ite8872set | (ite8872_irq * 0x11111));
- DPRINTK (KERN_DEBUG "ITE887x: The IRQ is %d.\n", ite8872_irq);
- DPRINTK (KERN_DEBUG "ITE887x: The PARALLEL I/O port is 0x%x.\n",
+ DPRINTK(KERN_DEBUG "ITE887x: The IRQ is %d.\n", ite8872_irq);
+ DPRINTK(KERN_DEBUG "ITE887x: The PARALLEL I/O port is 0x%x.\n",
ite8872_lpt);
- DPRINTK (KERN_DEBUG "ITE887x: The PARALLEL I/O porthi is 0x%x.\n",
+ DPRINTK(KERN_DEBUG "ITE887x: The PARALLEL I/O porthi is 0x%x.\n",
ite8872_lpthi);
/* Let the user (or defaults) steer us away from interrupts */
* Release the resource so that parport_pc_probe_port can get it.
*/
release_resource(base_res);
- if (parport_pc_probe_port (ite8872_lpt, ite8872_lpthi,
+ if (parport_pc_probe_port(ite8872_lpt, ite8872_lpthi,
irq, PARPORT_DMA_NONE, &pdev->dev, 0)) {
- printk (KERN_INFO
+ printk(KERN_INFO
"parport_pc: ITE 8872 parallel port: io=0x%X",
- ite8872_lpt);
+ ite8872_lpt);
if (irq != PARPORT_IRQ_NONE)
- printk (", irq=%d", irq);
- printk ("\n");
+ printk(", irq=%d", irq);
+ printk("\n");
return 1;
}
/* VIA 8231 support by Pavel Fedin <sonic_amiga@rambler.ru>
based on VIA 686a support code by Jeff Garzik <jgarzik@pobox.com> */
-static int __devinitdata parport_init_mode = 0;
+static int __devinitdata parport_init_mode;
/* Data for two known VIA chips */
static struct parport_pc_via_data via_686a_data __devinitdata = {
0xF6
};
-static int __devinit sio_via_probe (struct pci_dev *pdev, int autoirq,
+static int __devinit sio_via_probe(struct pci_dev *pdev, int autoirq,
int autodma,
const struct parport_pc_via_data *via)
{
printk(KERN_DEBUG "parport_pc: VIA 686A/8231 detected\n");
- switch(parport_init_mode)
- {
+ switch (parport_init_mode) {
case 1:
- printk(KERN_DEBUG "parport_pc: setting SPP mode\n");
- siofunc = VIA_FUNCTION_PARPORT_SPP;
- break;
+ printk(KERN_DEBUG "parport_pc: setting SPP mode\n");
+ siofunc = VIA_FUNCTION_PARPORT_SPP;
+ break;
case 2:
- printk(KERN_DEBUG "parport_pc: setting PS/2 mode\n");
- siofunc = VIA_FUNCTION_PARPORT_SPP;
- ppcontrol = VIA_PARPORT_BIDIR;
- break;
+ printk(KERN_DEBUG "parport_pc: setting PS/2 mode\n");
+ siofunc = VIA_FUNCTION_PARPORT_SPP;
+ ppcontrol = VIA_PARPORT_BIDIR;
+ break;
case 3:
- printk(KERN_DEBUG "parport_pc: setting EPP mode\n");
- siofunc = VIA_FUNCTION_PARPORT_EPP;
- ppcontrol = VIA_PARPORT_BIDIR;
- have_epp = 1;
- break;
+ printk(KERN_DEBUG "parport_pc: setting EPP mode\n");
+ siofunc = VIA_FUNCTION_PARPORT_EPP;
+ ppcontrol = VIA_PARPORT_BIDIR;
+ have_epp = 1;
+ break;
case 4:
- printk(KERN_DEBUG "parport_pc: setting ECP mode\n");
- siofunc = VIA_FUNCTION_PARPORT_ECP;
- ppcontrol = VIA_PARPORT_BIDIR;
- break;
+ printk(KERN_DEBUG "parport_pc: setting ECP mode\n");
+ siofunc = VIA_FUNCTION_PARPORT_ECP;
+ ppcontrol = VIA_PARPORT_BIDIR;
+ break;
case 5:
- printk(KERN_DEBUG "parport_pc: setting EPP+ECP mode\n");
- siofunc = VIA_FUNCTION_PARPORT_ECP;
- ppcontrol = VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP;
- have_epp = 1;
- break;
- default:
- printk(KERN_DEBUG "parport_pc: probing current configuration\n");
- siofunc = VIA_FUNCTION_PROBE;
- break;
+ printk(KERN_DEBUG "parport_pc: setting EPP+ECP mode\n");
+ siofunc = VIA_FUNCTION_PARPORT_ECP;
+ ppcontrol = VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP;
+ have_epp = 1;
+ break;
+ default:
+ printk(KERN_DEBUG
+ "parport_pc: probing current configuration\n");
+ siofunc = VIA_FUNCTION_PROBE;
+ break;
}
/*
* unlock super i/o configuration
/* Bits 1-0: Parallel Port Mode / Enable */
outb(via->viacfg_function, VIA_CONFIG_INDEX);
- tmp = inb (VIA_CONFIG_DATA);
+ tmp = inb(VIA_CONFIG_DATA);
/* Bit 5: EPP+ECP enable; bit 7: PS/2 bidirectional port enable */
outb(via->viacfg_parport_control, VIA_CONFIG_INDEX);
- tmp2 = inb (VIA_CONFIG_DATA);
- if (siofunc == VIA_FUNCTION_PROBE)
- {
- siofunc = tmp & VIA_FUNCTION_PARPORT_DISABLE;
- ppcontrol = tmp2;
+ tmp2 = inb(VIA_CONFIG_DATA);
+ if (siofunc == VIA_FUNCTION_PROBE) {
+ siofunc = tmp & VIA_FUNCTION_PARPORT_DISABLE;
+ ppcontrol = tmp2;
+ } else {
+ tmp &= ~VIA_FUNCTION_PARPORT_DISABLE;
+ tmp |= siofunc;
+ outb(via->viacfg_function, VIA_CONFIG_INDEX);
+ outb(tmp, VIA_CONFIG_DATA);
+ tmp2 &= ~(VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP);
+ tmp2 |= ppcontrol;
+ outb(via->viacfg_parport_control, VIA_CONFIG_INDEX);
+ outb(tmp2, VIA_CONFIG_DATA);
}
- else
- {
- tmp &= ~VIA_FUNCTION_PARPORT_DISABLE;
- tmp |= siofunc;
- outb(via->viacfg_function, VIA_CONFIG_INDEX);
- outb(tmp, VIA_CONFIG_DATA);
- tmp2 &= ~(VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP);
- tmp2 |= ppcontrol;
- outb(via->viacfg_parport_control, VIA_CONFIG_INDEX);
- outb(tmp2, VIA_CONFIG_DATA);
- }
-
+
/* Parallel Port I/O Base Address, bits 9-2 */
outb(via->viacfg_parport_base, VIA_CONFIG_INDEX);
port1 = inb(VIA_CONFIG_DATA) << 2;
-
- printk (KERN_DEBUG "parport_pc: Current parallel port base: 0x%X\n",port1);
- if ((port1 == 0x3BC) && have_epp)
- {
- outb(via->viacfg_parport_base, VIA_CONFIG_INDEX);
- outb((0x378 >> 2), VIA_CONFIG_DATA);
- printk(KERN_DEBUG "parport_pc: Parallel port base changed to 0x378\n");
- port1 = 0x378;
+
+ printk(KERN_DEBUG "parport_pc: Current parallel port base: 0x%X\n",
+ port1);
+ if (port1 == 0x3BC && have_epp) {
+ outb(via->viacfg_parport_base, VIA_CONFIG_INDEX);
+ outb((0x378 >> 2), VIA_CONFIG_DATA);
+ printk(KERN_DEBUG
+ "parport_pc: Parallel port base changed to 0x378\n");
+ port1 = 0x378;
}
/*
printk(KERN_INFO "parport_pc: VIA parallel port disabled in BIOS\n");
return 0;
}
-
+
/* Bits 7-4: PnP Routing for Parallel Port IRQ */
pci_read_config_byte(pdev, via->via_pci_parport_irq_reg, &tmp);
irq = ((tmp & VIA_IRQCONTROL_PARALLEL) >> 4);
- if (siofunc == VIA_FUNCTION_PARPORT_ECP)
- {
- /* Bits 3-2: PnP Routing for Parallel Port DMA */
- pci_read_config_byte(pdev, via->via_pci_parport_dma_reg, &tmp);
- dma = ((tmp & VIA_DMACONTROL_PARALLEL) >> 2);
- }
- else
- /* if ECP not enabled, DMA is not enabled, assumed bogus 'dma' value */
- dma = PARPORT_DMA_NONE;
+ if (siofunc == VIA_FUNCTION_PARPORT_ECP) {
+ /* Bits 3-2: PnP Routing for Parallel Port DMA */
+ pci_read_config_byte(pdev, via->via_pci_parport_dma_reg, &tmp);
+ dma = ((tmp & VIA_DMACONTROL_PARALLEL) >> 2);
+ } else
+ /* if ECP not enabled, DMA is not enabled, assumed
+ bogus 'dma' value */
+ dma = PARPORT_DMA_NONE;
/* Let the user (or defaults) steer us away from interrupts and DMA */
if (autoirq == PARPORT_IRQ_NONE) {
- irq = PARPORT_IRQ_NONE;
- dma = PARPORT_DMA_NONE;
+ irq = PARPORT_IRQ_NONE;
+ dma = PARPORT_DMA_NONE;
}
if (autodma == PARPORT_DMA_NONE)
- dma = PARPORT_DMA_NONE;
+ dma = PARPORT_DMA_NONE;
switch (port1) {
- case 0x3bc: port2 = 0x7bc; break;
- case 0x378: port2 = 0x778; break;
- case 0x278: port2 = 0x678; break;
+ case 0x3bc:
+ port2 = 0x7bc; break;
+ case 0x378:
+ port2 = 0x778; break;
+ case 0x278:
+ port2 = 0x678; break;
default:
- printk(KERN_INFO "parport_pc: Weird VIA parport base 0x%X, ignoring\n",
- port1);
+ printk(KERN_INFO
+ "parport_pc: Weird VIA parport base 0x%X, ignoring\n",
+ port1);
return 0;
}
}
/* finally, do the probe with values obtained */
- if (parport_pc_probe_port (port1, port2, irq, dma, &pdev->dev, 0)) {
- printk (KERN_INFO
+ if (parport_pc_probe_port(port1, port2, irq, dma, &pdev->dev, 0)) {
+ printk(KERN_INFO
"parport_pc: VIA parallel port: io=0x%X", port1);
if (irq != PARPORT_IRQ_NONE)
- printk (", irq=%d", irq);
+ printk(", irq=%d", irq);
if (dma != PARPORT_DMA_NONE)
- printk (", dma=%d", dma);
- printk ("\n");
+ printk(", dma=%d", dma);
+ printk("\n");
return 1;
}
-
+
printk(KERN_WARNING "parport_pc: Strange, can't probe VIA parallel port: io=0x%X, irq=%d, dma=%d\n",
port1, irq, dma);
return 0;
enum parport_pc_sio_types {
- sio_via_686a = 0, /* Via VT82C686A motherboard Super I/O */
- sio_via_8231, /* Via VT8231 south bridge integrated Super IO */
+ sio_via_686a = 0, /* Via VT82C686A motherboard Super I/O */
+ sio_via_8231, /* Via VT8231 south bridge integrated Super IO */
sio_ite_8872,
last_sio
};
};
-/* each element directly indexed from enum list, above
+/* each element directly indexed from enum list, above
* (but offset by last_sio) */
static struct parport_pc_pci {
int numports;
struct { /* BAR (base address registers) numbers in the config
- space header */
+ space header */
int lo;
- int hi; /* -1 if not there, >6 for offset-method (max
- BAR is 6) */
+ int hi;
+ /* -1 if not there, >6 for offset-method (max BAR is 6) */
} addr[4];
/* If set, this is called immediately after pci_enable_device.
/* timedia_4018 */ { 2, { { 0, 1 }, { 2, 3 }, } },
/* timedia_9018a */ { 2, { { 0, 1 }, { 2, 3 }, } },
/* SYBA uses fixed offsets in
- a 1K io window */
+ a 1K io window */
/* syba_2p_epp AP138B */ { 2, { { 0, 0x078 }, { 0, 0x178 }, } },
/* syba_1p_ecp W83787 */ { 1, { { 0, 0x078 }, } },
/* titan_010l */ { 1, { { 3, -1 }, } },
/* oxsemi_pcie_pport */ { 1, { { 0, 1 }, } },
/* aks_0100 */ { 1, { { 0, -1 }, } },
/* mobility_pp */ { 1, { { 0, 1 }, } },
- /* netmos_9705 */ { 1, { { 0, -1 }, } }, /* untested */
- /* netmos_9715 */ { 2, { { 0, 1 }, { 2, 3 },} }, /* untested */
- /* netmos_9755 */ { 2, { { 0, 1 }, { 2, 3 },} }, /* untested */
- /* netmos_9805 */ { 1, { { 0, -1 }, } }, /* untested */
- /* netmos_9815 */ { 2, { { 0, -1 }, { 2, -1 }, } }, /* untested */
+
+ /* The netmos entries below are untested */
+ /* netmos_9705 */ { 1, { { 0, -1 }, } },
+ /* netmos_9715 */ { 2, { { 0, 1 }, { 2, 3 },} },
+ /* netmos_9755 */ { 2, { { 0, 1 }, { 2, 3 },} },
+ /* netmos_9805 */ { 1, { { 0, -1 }, } },
+ /* netmos_9815 */ { 2, { { 0, -1 }, { 2, -1 }, } },
+
/* quatech_sppxp100 */ { 1, { { 0, 1 }, } },
};
{ PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_BOCA_IOPPAR,
PCI_ANY_ID, PCI_ANY_ID, 0, 0, boca_ioppar },
{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050,
- PCI_SUBVENDOR_ID_EXSYS, PCI_SUBDEVICE_ID_EXSYS_4014, 0,0, plx_9050 },
+ PCI_SUBVENDOR_ID_EXSYS, PCI_SUBDEVICE_ID_EXSYS_4014, 0, 0, plx_9050 },
/* PCI_VENDOR_ID_TIMEDIA/SUNIX has many differing cards ...*/
{ 0x1409, 0x7168, 0x1409, 0x4078, 0, 0, timedia_4078a },
{ 0x1409, 0x7168, 0x1409, 0x4079, 0, 0, timedia_4079h },
{ 0x9710, 0x9805, 0x1000, 0x0010, 0, 0, titan_1284p1 },
{ 0x9710, 0x9815, 0x1000, 0x0020, 0, 0, titan_1284p2 },
/* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
- { 0x14db, 0x2120, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_1p}, /* AFAVLAB_TK9902 */
+ /* AFAVLAB_TK9902 */
+ { 0x14db, 0x2120, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_1p},
{ 0x14db, 0x2121, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_2p},
{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_16PCI952PP,
PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_952 },
PCI_ANY_ID, PCI_ANY_ID, 0, 0, quatech_sppxp100 },
{ 0, } /* terminate list */
};
-MODULE_DEVICE_TABLE(pci,parport_pc_pci_tbl);
+MODULE_DEVICE_TABLE(pci, parport_pc_pci_tbl);
struct pci_parport_data {
int num;
struct parport *ports[2];
};
-static int parport_pc_pci_probe (struct pci_dev *dev,
+static int parport_pc_pci_probe(struct pci_dev *dev,
const struct pci_device_id *id)
{
int err, count, n, i = id->driver_data;
/* This is a PCI card */
i -= last_sio;
count = 0;
- if ((err = pci_enable_device (dev)) != 0)
+ err = pci_enable_device(dev);
+ if (err)
return err;
data = kmalloc(sizeof(struct pci_parport_data), GFP_KERNEL);
return -ENOMEM;
if (cards[i].preinit_hook &&
- cards[i].preinit_hook (dev, PARPORT_IRQ_NONE, PARPORT_DMA_NONE)) {
+ cards[i].preinit_hook(dev, PARPORT_IRQ_NONE, PARPORT_DMA_NONE)) {
kfree(data);
return -ENODEV;
}
int hi = cards[i].addr[n].hi;
int irq;
unsigned long io_lo, io_hi;
- io_lo = pci_resource_start (dev, lo);
+ io_lo = pci_resource_start(dev, lo);
io_hi = 0;
if ((hi >= 0) && (hi <= 6))
- io_hi = pci_resource_start (dev, hi);
+ io_hi = pci_resource_start(dev, hi);
else if (hi > 6)
io_lo += hi; /* Reinterpret the meaning of
- "hi" as an offset (see SYBA
- def.) */
+ "hi" as an offset (see SYBA
+ def.) */
/* TODO: test if sharing interrupts works */
irq = dev->irq;
if (irq == IRQ_NONE) {
- printk (KERN_DEBUG
+ printk(KERN_DEBUG
"PCI parallel port detected: %04x:%04x, I/O at %#lx(%#lx)\n",
parport_pc_pci_tbl[i + last_sio].vendor,
parport_pc_pci_tbl[i + last_sio].device,
io_lo, io_hi);
irq = PARPORT_IRQ_NONE;
} else {
- printk (KERN_DEBUG
+ printk(KERN_DEBUG
"PCI parallel port detected: %04x:%04x, I/O at %#lx(%#lx), IRQ %d\n",
parport_pc_pci_tbl[i + last_sio].vendor,
parport_pc_pci_tbl[i + last_sio].device,
data->num = count;
if (cards[i].postinit_hook)
- cards[i].postinit_hook (dev, count == 0);
+ cards[i].postinit_hook(dev, count == 0);
if (count) {
pci_set_drvdata(dev, data);
.remove = __devexit_p(parport_pc_pci_remove),
};
-static int __init parport_pc_init_superio (int autoirq, int autodma)
+static int __init parport_pc_init_superio(int autoirq, int autodma)
{
const struct pci_device_id *id;
struct pci_dev *pdev = NULL;
if (id == NULL || id->driver_data >= last_sio)
continue;
- if (parport_pc_superio_info[id->driver_data].probe
- (pdev, autoirq, autodma,parport_pc_superio_info[id->driver_data].via)) {
+ if (parport_pc_superio_info[id->driver_data].probe(
+ pdev, autoirq, autodma,
+ parport_pc_superio_info[id->driver_data].via)) {
ret++;
}
}
}
#else
static struct pci_driver parport_pc_pci_driver;
-static int __init parport_pc_init_superio(int autoirq, int autodma) {return 0;}
+static int __init parport_pc_init_superio(int autoirq, int autodma)
+{
+ return 0;
+}
#endif /* CONFIG_PCI */
#ifdef CONFIG_PNP
{ }
};
-MODULE_DEVICE_TABLE(pnp,parport_pc_pnp_tbl);
+MODULE_DEVICE_TABLE(pnp, parport_pc_pnp_tbl);
-static int parport_pc_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *id)
+static int parport_pc_pnp_probe(struct pnp_dev *dev,
+ const struct pnp_device_id *id)
{
struct parport *pdata;
unsigned long io_lo, io_hi;
int dma, irq;
- if (pnp_port_valid(dev,0) &&
- !(pnp_port_flags(dev,0) & IORESOURCE_DISABLED)) {
- io_lo = pnp_port_start(dev,0);
+ if (pnp_port_valid(dev, 0) &&
+ !(pnp_port_flags(dev, 0) & IORESOURCE_DISABLED)) {
+ io_lo = pnp_port_start(dev, 0);
} else
return -EINVAL;
- if (pnp_port_valid(dev,1) &&
- !(pnp_port_flags(dev,1) & IORESOURCE_DISABLED)) {
- io_hi = pnp_port_start(dev,1);
+ if (pnp_port_valid(dev, 1) &&
+ !(pnp_port_flags(dev, 1) & IORESOURCE_DISABLED)) {
+ io_hi = pnp_port_start(dev, 1);
} else
io_hi = 0;
- if (pnp_irq_valid(dev,0) &&
- !(pnp_irq_flags(dev,0) & IORESOURCE_DISABLED)) {
- irq = pnp_irq(dev,0);
+ if (pnp_irq_valid(dev, 0) &&
+ !(pnp_irq_flags(dev, 0) & IORESOURCE_DISABLED)) {
+ irq = pnp_irq(dev, 0);
} else
irq = PARPORT_IRQ_NONE;
- if (pnp_dma_valid(dev,0) &&
- !(pnp_dma_flags(dev,0) & IORESOURCE_DISABLED)) {
- dma = pnp_dma(dev,0);
+ if (pnp_dma_valid(dev, 0) &&
+ !(pnp_dma_flags(dev, 0) & IORESOURCE_DISABLED)) {
+ dma = pnp_dma(dev, 0);
} else
dma = PARPORT_DMA_NONE;
dev_info(&dev->dev, "reported by %s\n", dev->protocol->name);
- if (!(pdata = parport_pc_probe_port(io_lo, io_hi,
- irq, dma, &dev->dev, 0)))
+ pdata = parport_pc_probe_port(io_lo, io_hi, irq, dma, &dev->dev, 0);
+ if (pdata == NULL)
return -ENODEV;
- pnp_set_drvdata(dev,pdata);
+ pnp_set_drvdata(dev, pdata);
return 0;
}
/* This is called by parport_pc_find_nonpci_ports (in asm/parport.h) */
static int __devinit __attribute__((unused))
-parport_pc_find_isa_ports (int autoirq, int autodma)
+parport_pc_find_isa_ports(int autoirq, int autodma)
{
int count = 0;
* autoirq is PARPORT_IRQ_NONE, PARPORT_IRQ_AUTO, or PARPORT_IRQ_PROBEONLY
* autodma is PARPORT_DMA_NONE or PARPORT_DMA_AUTO
*/
-static void __init parport_pc_find_ports (int autoirq, int autodma)
+static void __init parport_pc_find_ports(int autoirq, int autodma)
{
int count = 0, err;
* syntax and keep in mind that code below is a cleaned up version.
*/
-static int __initdata io[PARPORT_PC_MAX_PORTS+1] = { [0 ... PARPORT_PC_MAX_PORTS] = 0 };
-static int __initdata io_hi[PARPORT_PC_MAX_PORTS+1] =
- { [0 ... PARPORT_PC_MAX_PORTS] = PARPORT_IOHI_AUTO };
-static int __initdata dmaval[PARPORT_PC_MAX_PORTS] = { [0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_DMA_NONE };
-static int __initdata irqval[PARPORT_PC_MAX_PORTS] = { [0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_IRQ_PROBEONLY };
+static int __initdata io[PARPORT_PC_MAX_PORTS+1] = {
+ [0 ... PARPORT_PC_MAX_PORTS] = 0
+};
+static int __initdata io_hi[PARPORT_PC_MAX_PORTS+1] = {
+ [0 ... PARPORT_PC_MAX_PORTS] = PARPORT_IOHI_AUTO
+};
+static int __initdata dmaval[PARPORT_PC_MAX_PORTS] = {
+ [0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_DMA_NONE
+};
+static int __initdata irqval[PARPORT_PC_MAX_PORTS] = {
+ [0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_IRQ_PROBEONLY
+};
static int __init parport_parse_param(const char *s, int *val,
int automatic, int none, int nofifo)
#ifdef CONFIG_PCI
static int __init parport_init_mode_setup(char *str)
{
- printk(KERN_DEBUG "parport_pc.c: Specified parameter parport_init_mode=%s\n", str);
-
- if (!strcmp (str, "spp"))
- parport_init_mode=1;
- if (!strcmp (str, "ps2"))
- parport_init_mode=2;
- if (!strcmp (str, "epp"))
- parport_init_mode=3;
- if (!strcmp (str, "ecp"))
- parport_init_mode=4;
- if (!strcmp (str, "ecpepp"))
- parport_init_mode=5;
+ printk(KERN_DEBUG
+ "parport_pc.c: Specified parameter parport_init_mode=%s\n", str);
+
+ if (!strcmp(str, "spp"))
+ parport_init_mode = 1;
+ if (!strcmp(str, "ps2"))
+ parport_init_mode = 2;
+ if (!strcmp(str, "epp"))
+ parport_init_mode = 3;
+ if (!strcmp(str, "ecp"))
+ parport_init_mode = 4;
+ if (!strcmp(str, "ecpepp"))
+ parport_init_mode = 5;
return 1;
}
#endif
#endif
#ifdef CONFIG_PCI
static char *init_mode;
-MODULE_PARM_DESC(init_mode, "Initialise mode for VIA VT8231 port (spp, ps2, epp, ecp or ecpepp)");
+MODULE_PARM_DESC(init_mode,
+ "Initialise mode for VIA VT8231 port (spp, ps2, epp, ecp or ecpepp)");
module_param(init_mode, charp, 0);
#endif
irqval[0] = val;
break;
default:
- printk (KERN_WARNING
+ printk(KERN_WARNING
"parport_pc: irq specified "
"without base address. Use 'io=' "
"to specify one\n");
dmaval[0] = val;
break;
default:
- printk (KERN_WARNING
+ printk(KERN_WARNING
"parport_pc: dma specified "
"without base address. Use 'io=' "
"to specify one\n");
#else
-static int parport_setup_ptr __initdata = 0;
+static int parport_setup_ptr __initdata;
/*
* Acceptable parameters:
*
* IRQ/DMA may be numeric or 'auto' or 'none'
*/
-static int __init parport_setup (char *str)
+static int __init parport_setup(char *str)
{
char *endptr;
char *sep;
return 1;
}
- if (!strncmp (str, "auto", 4)) {
+ if (!strncmp(str, "auto", 4)) {
irqval[0] = PARPORT_IRQ_AUTO;
dmaval[0] = PARPORT_DMA_AUTO;
return 1;
}
- val = simple_strtoul (str, &endptr, 0);
+ val = simple_strtoul(str, &endptr, 0);
if (endptr == str) {
- printk (KERN_WARNING "parport=%s not understood\n", str);
+ printk(KERN_WARNING "parport=%s not understood\n", str);
return 1;
}
return io[0] == PARPORT_DISABLE;
}
-__setup ("parport=", parport_setup);
+__setup("parport=", parport_setup);
/*
* Acceptable parameters:
* parport_init_mode=[spp|ps2|epp|ecp|ecpepp]
*/
#ifdef CONFIG_PCI
-__setup("parport_init_mode=",parport_init_mode_setup);
+__setup("parport_init_mode=", parport_init_mode_setup);
#endif
#endif
for (i = 0; i < PARPORT_PC_MAX_PORTS; i++) {
if (!io[i])
break;
- if ((io_hi[i]) == PARPORT_IOHI_AUTO)
- io_hi[i] = 0x400 + io[i];
+ if (io_hi[i] == PARPORT_IOHI_AUTO)
+ io_hi[i] = 0x400 + io[i];
parport_pc_probe_port(io[i], io_hi[i],
- irqval[i], dmaval[i], NULL, 0);
+ irqval[i], dmaval[i], NULL, 0);
}
} else
- parport_pc_find_ports (irqval[0], dmaval[0]);
+ parport_pc_find_ports(irqval[0], dmaval[0]);
return 0;
}
static void __exit parport_pc_exit(void)
{
if (pci_registered_parport)
- pci_unregister_driver (&parport_pc_pci_driver);
+ pci_unregister_driver(&parport_pc_pci_driver);
if (pnp_registered_parport)
- pnp_unregister_driver (&parport_pc_pnp_driver);
+ pnp_unregister_driver(&parport_pc_pnp_driver);
platform_driver_unregister(&parport_pc_platform_driver);
while (!list_empty(&ports_list)) {
return -1;
}
for (loop = 0; loop < len; loop++) {
- if ((*cur_slot)->number == rtable->slots[loop].slot) {
- if ((*cur_slot)->bus == rtable->slots[loop].bus) {
+ if ((*cur_slot)->number == rtable->slots[loop].slot &&
+ (*cur_slot)->bus == rtable->slots[loop].bus) {
+ struct io_apic_irq_attr irq_attr;
+
(*cur_slot)->device = PCI_SLOT(rtable->slots[loop].devfn);
for (i = 0; i < 4; i++)
(*cur_slot)->irq[i] = IO_APIC_get_PCI_irq_vector((int) (*cur_slot)->bus,
- (int) (*cur_slot)->device, i);
-
- debug("(*cur_slot)->irq[0] = %x\n",
- (*cur_slot)->irq[0]);
- debug("(*cur_slot)->irq[1] = %x\n",
- (*cur_slot)->irq[1]);
- debug("(*cur_slot)->irq[2] = %x\n",
- (*cur_slot)->irq[2]);
- debug("(*cur_slot)->irq[3] = %x\n",
- (*cur_slot)->irq[3]);
-
- debug("rtable->exlusive_irqs = %x\n",
+ (int) (*cur_slot)->device, i,
+ &irq_attr);
+
+ debug("(*cur_slot)->irq[0] = %x\n",
+ (*cur_slot)->irq[0]);
+ debug("(*cur_slot)->irq[1] = %x\n",
+ (*cur_slot)->irq[1]);
+ debug("(*cur_slot)->irq[2] = %x\n",
+ (*cur_slot)->irq[2]);
+ debug("(*cur_slot)->irq[3] = %x\n",
+ (*cur_slot)->irq[3]);
+
+ debug("rtable->exlusive_irqs = %x\n",
rtable->exclusive_irqs);
- debug("rtable->slots[loop].irq[0].bitmap = %x\n",
+ debug("rtable->slots[loop].irq[0].bitmap = %x\n",
rtable->slots[loop].irq[0].bitmap);
- debug("rtable->slots[loop].irq[1].bitmap = %x\n",
+ debug("rtable->slots[loop].irq[1].bitmap = %x\n",
rtable->slots[loop].irq[1].bitmap);
- debug("rtable->slots[loop].irq[2].bitmap = %x\n",
+ debug("rtable->slots[loop].irq[2].bitmap = %x\n",
rtable->slots[loop].irq[2].bitmap);
- debug("rtable->slots[loop].irq[3].bitmap = %x\n",
+ debug("rtable->slots[loop].irq[3].bitmap = %x\n",
rtable->slots[loop].irq[3].bitmap);
- debug("rtable->slots[loop].irq[0].link = %x\n",
+ debug("rtable->slots[loop].irq[0].link = %x\n",
rtable->slots[loop].irq[0].link);
- debug("rtable->slots[loop].irq[1].link = %x\n",
+ debug("rtable->slots[loop].irq[1].link = %x\n",
rtable->slots[loop].irq[1].link);
- debug("rtable->slots[loop].irq[2].link = %x\n",
+ debug("rtable->slots[loop].irq[2].link = %x\n",
rtable->slots[loop].irq[2].link);
- debug("rtable->slots[loop].irq[3].link = %x\n",
+ debug("rtable->slots[loop].irq[3].link = %x\n",
rtable->slots[loop].irq[3].link);
- debug("end of init_devno\n");
- kfree(rtable);
- return 0;
- }
+ debug("end of init_devno\n");
+ kfree(rtable);
+ return 0;
}
}
int max_irq;
int pos;
int irq;
+ int node;
pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
if (!pos)
cfg->msg.address_lo = 0xffffffff;
cfg->msg.address_hi = 0xffffffff;
- irq = create_irq();
+ node = dev_to_node(&dev->dev);
+ irq = create_irq_nr(0, node);
if (irq <= 0) {
kfree(cfg);
}
}
-#ifdef CONFIG_INTR_REMAP
- if (!intr_remapping_enabled) {
- ret = enable_intr_remapping(0);
- if (ret)
- printk(KERN_ERR
- "IOMMU: enable interrupt remapping failed\n");
- }
-#endif
-
/*
* For each rmrr
* for each dev attached to rmrr
static int ir_ioapic_num;
int intr_remapping_enabled;
+static int disable_intremap;
+static __init int setup_nointremap(char *str)
+{
+ disable_intremap = 1;
+ return 0;
+}
+early_param("nointremap", setup_nointremap);
+
struct irq_2_iommu {
struct intel_iommu *iommu;
u16 irte_index;
};
#ifdef CONFIG_GENERIC_HARDIRQS
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int cpu)
+static struct irq_2_iommu *get_one_free_irq_2_iommu(int node)
{
struct irq_2_iommu *iommu;
- int node;
-
- node = cpu_to_node(cpu);
iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
- printk(KERN_DEBUG "alloc irq_2_iommu on cpu %d node %d\n", cpu, node);
+ printk(KERN_DEBUG "alloc irq_2_iommu on node %d\n", node);
return iommu;
}
return desc->irq_2_iommu;
}
-static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
+static struct irq_2_iommu *irq_2_iommu_alloc_node(unsigned int irq, int node)
{
struct irq_desc *desc;
struct irq_2_iommu *irq_iommu;
/*
* alloc irq desc if not allocated already.
*/
- desc = irq_to_desc_alloc_cpu(irq, cpu);
+ desc = irq_to_desc_alloc_node(irq, node);
if (!desc) {
printk(KERN_INFO "can not get irq_desc for %d\n", irq);
return NULL;
irq_iommu = desc->irq_2_iommu;
if (!irq_iommu)
- desc->irq_2_iommu = get_one_free_irq_2_iommu(cpu);
+ desc->irq_2_iommu = get_one_free_irq_2_iommu(node);
return desc->irq_2_iommu;
}
static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
{
- return irq_2_iommu_alloc_cpu(irq, boot_cpu_id);
+ return irq_2_iommu_alloc_node(irq, cpu_to_node(boot_cpu_id));
}
#else /* !CONFIG_SPARSE_IRQ */
readl, (sts & DMA_GSTS_IRTPS), sts);
spin_unlock_irqrestore(&iommu->register_lock, flags);
- if (mode == 0) {
- spin_lock_irqsave(&iommu->register_lock, flags);
-
- /* enable comaptiblity format interrupt pass through */
- cmd = iommu->gcmd | DMA_GCMD_CFI;
- iommu->gcmd |= DMA_GCMD_CFI;
- writel(cmd, iommu->reg + DMAR_GCMD_REG);
-
- IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
- readl, (sts & DMA_GSTS_CFIS), sts);
-
- spin_unlock_irqrestore(&iommu->register_lock, flags);
- }
-
/*
* global invalidation of interrupt entry cache before enabling
* interrupt-remapping.
spin_unlock_irqrestore(&iommu->register_lock, flags);
}
+int __init intr_remapping_supported(void)
+{
+ struct dmar_drhd_unit *drhd;
+
+ if (disable_intremap)
+ return 0;
+
+ for_each_drhd_unit(drhd) {
+ struct intel_iommu *iommu = drhd->iommu;
+
+ if (!ecap_ir_support(iommu->ecap))
+ return 0;
+ }
+
+ return 1;
+}
+
int __init enable_intr_remapping(int eim)
{
struct dmar_drhd_unit *drhd;
}
flags = irq_flags(triggering, polarity, shareable);
- irq = acpi_register_gsi(gsi, triggering, polarity);
+ irq = acpi_register_gsi(&dev->dev, gsi, triggering, polarity);
if (irq >= 0)
pcibios_penalize_isa_irq(irq, 1);
else
return blk_trace_setup(sdp->device->request_queue,
sdp->disk->disk_name,
MKDEV(SCSI_GENERIC_MAJOR, sdp->index),
+ NULL,
(char *)arg);
case BLKTRACESTART:
return blk_trace_startstop(sdp->device->request_queue, 1);
.fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
.flags = UART_CAP_FIFO,
},
+ [PORT_AR7] = {
+ .name = "AR7",
+ .fifo_size = 16,
+ .tx_loadsz = 16,
+ .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00,
+ .flags = UART_CAP_FIFO | UART_CAP_AFE,
+ },
};
#if defined (CONFIG_SERIAL_8250_AU1X00)
{ PCI_VENDOR_ID_OXSEMI, 0x950a,
PCI_ANY_ID, PCI_ANY_ID, 0, 0,
pbn_b0_2_1130000 },
+ { PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_C950,
+ PCI_VENDOR_ID_OXSEMI, PCI_SUBDEVICE_ID_OXSEMI_C950, 0, 0,
+ pbn_b0_1_921600 },
{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_16PCI954,
PCI_ANY_ID, PCI_ANY_ID, 0, 0,
pbn_b0_4_115200 },
bool "IMX serial port support"
depends on ARM && (ARCH_IMX || ARCH_MXC)
select SERIAL_CORE
+ select RATIONAL
help
If you have a machine based on a Motorola IMX CPU you
can enable its onboard serial port by enabling this option.
default 19200 if (SERIAL_SPORT_BAUD_RATE_19200)
default 9600 if (SERIAL_SPORT_BAUD_RATE_9600)
+config SERIAL_TIMBERDALE
+ tristate "Support for timberdale UART"
+ depends on MFD_TIMBERDALE
+ select SERIAL_CORE
+ ---help---
+ Add support for UART controller on timberdale.
+
endmenu
obj-$(CONFIG_SERIAL_KS8695) += serial_ks8695.o
obj-$(CONFIG_KGDB_SERIAL_CONSOLE) += kgdboc.o
obj-$(CONFIG_SERIAL_QE) += ucc_uart.o
+obj-$(CONFIG_SERIAL_TIMBERDALE) += timbuart.o
/* Clear TFI bit */
UART_PUT_LSR(uart, TFI);
#endif
+ /* Anomaly notes:
+ * 05000215 - we always clear ETBEI within last UART TX
+ * interrupt to end a string. It is always set
+ * when start a new tx.
+ */
UART_CLEAR_IER(uart, ETBEI);
return;
}
set_dma_start_addr(uart->tx_dma_channel, (unsigned long)(xmit->buf+xmit->tail));
set_dma_x_count(uart->tx_dma_channel, uart->tx_count);
set_dma_x_modify(uart->tx_dma_channel, 1);
+ SSYNC();
enable_dma(uart->tx_dma_channel);
UART_SET_IER(uart, ETBEI);
void bfin_serial_rx_dma_timeout(struct bfin_serial_port *uart)
{
int x_pos, pos;
- unsigned long flags;
-
- spin_lock_irqsave(&uart->port.lock, flags);
+ dma_disable_irq(uart->rx_dma_channel);
+ spin_lock_bh(&uart->port.lock);
+
+ /* 2D DMA RX buffer ring is used. Because curr_y_count and
+ * curr_x_count can't be read as an atomic operation,
+ * curr_y_count should be read before curr_x_count. When
+ * curr_x_count is read, curr_y_count may already indicate
+ * next buffer line. But, the position calculated here is
+ * still indicate the old line. The wrong position data may
+ * be smaller than current buffer tail, which cause garbages
+ * are received if it is not prohibit.
+ */
uart->rx_dma_nrows = get_dma_curr_ycount(uart->rx_dma_channel);
x_pos = get_dma_curr_xcount(uart->rx_dma_channel);
uart->rx_dma_nrows = DMA_RX_YCOUNT - uart->rx_dma_nrows;
- if (uart->rx_dma_nrows == DMA_RX_YCOUNT)
+ if (uart->rx_dma_nrows == DMA_RX_YCOUNT || x_pos == 0)
uart->rx_dma_nrows = 0;
x_pos = DMA_RX_XCOUNT - x_pos;
if (x_pos == DMA_RX_XCOUNT)
x_pos = 0;
pos = uart->rx_dma_nrows * DMA_RX_XCOUNT + x_pos;
- if (pos != uart->rx_dma_buf.tail) {
+ /* Ignore receiving data if new position is in the same line of
+ * current buffer tail and small.
+ */
+ if (pos > uart->rx_dma_buf.tail ||
+ uart->rx_dma_nrows < (uart->rx_dma_buf.tail/DMA_RX_XCOUNT)) {
uart->rx_dma_buf.head = pos;
bfin_serial_dma_rx_chars(uart);
uart->rx_dma_buf.tail = uart->rx_dma_buf.head;
}
- spin_unlock_irqrestore(&uart->port.lock, flags);
+ spin_unlock_bh(&uart->port.lock);
+ dma_enable_irq(uart->rx_dma_channel);
mod_timer(&(uart->rx_dma_timer), jiffies + DMA_RX_FLUSH_JIFFIES);
}
if (!(get_dma_curr_irqstat(uart->tx_dma_channel)&DMA_RUN)) {
disable_dma(uart->tx_dma_channel);
clear_dma_irqstat(uart->tx_dma_channel);
+ /* Anomaly notes:
+ * 05000215 - we always clear ETBEI within last UART TX
+ * interrupt to end a string. It is always set
+ * when start a new tx.
+ */
UART_CLEAR_IER(uart, ETBEI);
xmit->tail = (xmit->tail + uart->tx_count) & (UART_XMIT_SIZE - 1);
uart->port.icount.tx += uart->tx_count;
{
struct bfin_serial_port *uart = dev_id;
unsigned short irqstat;
+ int x_pos, pos;
spin_lock(&uart->port.lock);
irqstat = get_dma_curr_irqstat(uart->rx_dma_channel);
clear_dma_irqstat(uart->rx_dma_channel);
- bfin_serial_dma_rx_chars(uart);
+
+ uart->rx_dma_nrows = get_dma_curr_ycount(uart->rx_dma_channel);
+ x_pos = get_dma_curr_xcount(uart->rx_dma_channel);
+ uart->rx_dma_nrows = DMA_RX_YCOUNT - uart->rx_dma_nrows;
+ if (uart->rx_dma_nrows == DMA_RX_YCOUNT || x_pos == 0)
+ uart->rx_dma_nrows = 0;
+
+ pos = uart->rx_dma_nrows * DMA_RX_XCOUNT;
+ if (pos > uart->rx_dma_buf.tail ||
+ uart->rx_dma_nrows < (uart->rx_dma_buf.tail/DMA_RX_XCOUNT)) {
+ uart->rx_dma_buf.head = pos;
+ bfin_serial_dma_rx_chars(uart);
+ uart->rx_dma_buf.tail = uart->rx_dma_buf.head;
+ }
+
spin_unlock(&uart->port.lock);
return IRQ_HANDLED;
__func__);
}
- if (termios->c_cflag & CSTOPB)
- lcr |= STB;
+ /* Anomaly notes:
+ * 05000231 - STOP bit is always set to 1 whatever the user is set.
+ */
+ if (termios->c_cflag & CSTOPB) {
+ if (ANOMALY_05000231)
+ printk(KERN_WARNING "STOP bits other than 1 is not "
+ "supported in case of anomaly 05000231.\n");
+ else
+ lcr |= STB;
+ }
if (termios->c_cflag & PARENB)
lcr |= PEN;
if (!(termios->c_cflag & PARODD))
}
#ifdef CONFIG_CONSOLE_POLL
+/* Anomaly notes:
+ * 05000099 - Because we only use THRE in poll_put and DR in poll_get,
+ * losing other bits of UART_LSR is not a problem here.
+ */
static void bfin_serial_poll_put_char(struct uart_port *port, unsigned char chr)
{
struct bfin_serial_port *uart = (struct bfin_serial_port *)port;
}
}
+/*
+ * This should have a .setup or .early_setup in it, but then things get called
+ * without the command line options, and the baud rate gets messed up - so
+ * don't let the common infrastructure play with things. (see calls to setup
+ * & earlysetup in ./kernel/printk.c:register_console()
+ */
static struct __initdata console bfin_early_serial_console = {
.name = "early_BFuart",
.write = early_serial_write,
.device = uart_console_device,
.flags = CON_PRINTBUFFER,
- .setup = bfin_serial_console_setup,
.index = -1,
.data = &bfin_serial_reg,
};
{
pr_debug("%s value:%x\n", __func__, value);
/* Place a Start and Stop bit */
- __asm__ volatile (
- "R2 = b#01111111100;\n\t"
- "R3 = b#10000000001;\n\t"
- "%0 <<= 2;\n\t"
- "%0 = %0 & R2;\n\t"
- "%0 = %0 | R3;\n\t"
- :"=r"(value)
- :"0"(value)
- :"R2", "R3");
+ __asm__ __volatile__ (
+ "R2 = b#01111111100;"
+ "R3 = b#10000000001;"
+ "%0 <<= 2;"
+ "%0 = %0 & R2;"
+ "%0 = %0 | R3;"
+ : "=d"(value)
+ : "d"(value)
+ : "ASTAT", "R2", "R3"
+ );
pr_debug("%s value:%x\n", __func__, value);
SPORT_PUT_TX(up, value);
static inline unsigned int rx_one_byte(struct sport_uart_port *up)
{
unsigned int value, extract;
+ u32 tmp_mask1, tmp_mask2, tmp_shift, tmp;
value = SPORT_GET_RX32(up);
pr_debug("%s value:%x\n", __func__, value);
/* Extract 8 bits data */
- __asm__ volatile (
- "R5 = 0;\n\t"
- "P0 = 8;\n\t"
- "R1 = 0x1801(Z);\n\t"
- "R3 = 0x0300(Z);\n\t"
- "R4 = 0;\n\t"
- "LSETUP(loop_s, loop_e) LC0 = P0;\nloop_s:\t"
- "R2 = extract(%1, R1.L)(Z);\n\t"
- "R2 <<= R4;\n\t"
- "R5 = R5 | R2;\n\t"
- "R1 = R1 - R3;\nloop_e:\t"
- "R4 += 1;\n\t"
- "%0 = R5;\n\t"
- :"=r"(extract)
- :"r"(value)
- :"P0", "R1", "R2","R3","R4", "R5");
+ __asm__ __volatile__ (
+ "%[extr] = 0;"
+ "%[mask1] = 0x1801(Z);"
+ "%[mask2] = 0x0300(Z);"
+ "%[shift] = 0;"
+ "LSETUP(.Lloop_s, .Lloop_e) LC0 = %[lc];"
+ ".Lloop_s:"
+ "%[tmp] = extract(%[val], %[mask1].L)(Z);"
+ "%[tmp] <<= %[shift];"
+ "%[extr] = %[extr] | %[tmp];"
+ "%[mask1] = %[mask1] - %[mask2];"
+ ".Lloop_e:"
+ "%[shift] += 1;"
+ : [val]"=d"(value), [extr]"=d"(extract), [shift]"=d"(tmp_shift), [tmp]"=d"(tmp),
+ [mask1]"=d"(tmp_mask1), [mask2]"=d"(tmp_mask2)
+ : "d"(value), [lc]"a"(8)
+ : "ASTAT", "LB0", "LC0", "LT0"
+ );
pr_debug(" extract:%x\n", extract);
return extract;
int tclkdiv, tfsdiv, rclkdiv;
/* Set TCR1 and TCR2 */
- SPORT_PUT_TCR1(up, (LTFS | ITFS | TFSR | TLSBIT | ITCLK));
+ SPORT_PUT_TCR1(up, (LATFS | ITFS | TFSR | TLSBIT | ITCLK));
SPORT_PUT_TCR2(up, 10);
pr_debug("%s TCR1:%x, TCR2:%x\n", __func__, SPORT_GET_TCR1(up), SPORT_GET_TCR2(up));
}
static void sport_set_termios(struct uart_port *port,
- struct termios *termios, struct termios *old)
+ struct ktermios *termios, struct ktermios *old)
{
pr_debug("%s enter, c_cflag:%08x\n", __func__, termios->c_cflag);
uart_update_timeout(port, CS8 ,port->uartclk);
static spinlock_t icom_lock;
#ifdef ICOM_TRACE
-static inline void trace(struct icom_port *, char *, unsigned long) {};
+static inline void trace(struct icom_port *icom_port, char *trace_pt,
+ unsigned long trace_data)
+{
+ dev_info(&icom_port->adapter->pci_dev->dev, ":%d:%s - %lx\n",
+ icom_port->port, trace_pt, trace_data);
+}
#else
static inline void trace(struct icom_port *icom_port, char *trace_pt, unsigned long trace_data) {};
#endif
release_firmware(fw);
/* Set Hardware level */
- if ((icom_port->adapter->version | ADAPTER_V2) == ADAPTER_V2)
+ if (icom_port->adapter->version == ADAPTER_V2)
writeb(V2_HARDWARE, &(icom_port->dram->misc_flags));
/* Start the processor in Adapter */
/* find icom_port for this interrupt */
icom_adapter = (struct icom_adapter *) dev_id;
- if ((icom_adapter->version | ADAPTER_V2) == ADAPTER_V2) {
+ if (icom_adapter->version == ADAPTER_V2) {
int_reg = icom_adapter->base_addr + 0x8024;
adapter_interrupts = readl(int_reg);
module_init(icom_init);
module_exit(icom_exit);
-#ifdef ICOM_TRACE
-static inline void trace(struct icom_port *icom_port, char *trace_pt,
- unsigned long trace_data)
-{
- dev_info(&icom_port->adapter->pci_dev->dev, ":%d:%s - %lx\n",
- icom_port->port, trace_pt, trace_data);
-}
-#endif
-
MODULE_AUTHOR("Michael Anderson <mjanders@us.ibm.com>");
MODULE_DESCRIPTION("IBM iSeries Serial IOA driver");
MODULE_SUPPORTED_DEVICE
* Author: Sascha Hauer <sascha@saschahauer.de>
* Copyright (C) 2004 Pengutronix
*
+ * Copyright (C) 2009 emlix GmbH
+ * Author: Fabian Godehardt (added IrDA support for iMX)
+ *
* 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
#include <linux/serial_core.h>
#include <linux/serial.h>
#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/rational.h>
#include <asm/io.h>
#include <asm/irq.h>
#define UCR4_DREN (1<<0) /* Recv data ready interrupt enable */
#define UFCR_RXTL_SHF 0 /* Receiver trigger level shift */
#define UFCR_RFDIV (7<<7) /* Reference freq divider mask */
+#define UFCR_RFDIV_REG(x) (((x) < 7 ? 6 - (x) : 6) << 7)
#define UFCR_TXTL_SHF 10 /* Transmitter trigger level shift */
#define USR1_PARITYERR (1<<15) /* Parity error interrupt flag */
#define USR1_RTSS (1<<14) /* RTS pin status */
struct timer_list timer;
unsigned int old_status;
int txirq,rxirq,rtsirq;
- int have_rtscts:1;
+ unsigned int have_rtscts:1;
+ unsigned int use_irda:1;
+ unsigned int irda_inv_rx:1;
+ unsigned int irda_inv_tx:1;
+ unsigned short trcv_delay; /* transceiver delay */
struct clk *clk;
};
+#ifdef CONFIG_IRDA
+#define USE_IRDA(sport) ((sport)->use_irda)
+#else
+#define USE_IRDA(sport) (0)
+#endif
+
/*
* Handle any change of modem status signal since we were last called.
*/
struct imx_port *sport = (struct imx_port *)port;
unsigned long temp;
+ if (USE_IRDA(sport)) {
+ /* half duplex - wait for end of transmission */
+ int n = 256;
+ while ((--n > 0) &&
+ !(readl(sport->port.membase + USR2) & USR2_TXDC)) {
+ udelay(5);
+ barrier();
+ }
+ /*
+ * irda transceiver - wait a bit more to avoid
+ * cutoff, hardware dependent
+ */
+ udelay(sport->trcv_delay);
+
+ /*
+ * half duplex - reactivate receive mode,
+ * flush receive pipe echo crap
+ */
+ if (readl(sport->port.membase + USR2) & USR2_TXDC) {
+ temp = readl(sport->port.membase + UCR1);
+ temp &= ~(UCR1_TXMPTYEN | UCR1_TRDYEN);
+ writel(temp, sport->port.membase + UCR1);
+
+ temp = readl(sport->port.membase + UCR4);
+ temp &= ~(UCR4_TCEN);
+ writel(temp, sport->port.membase + UCR4);
+
+ while (readl(sport->port.membase + URXD0) &
+ URXD_CHARRDY)
+ barrier();
+
+ temp = readl(sport->port.membase + UCR1);
+ temp |= UCR1_RRDYEN;
+ writel(temp, sport->port.membase + UCR1);
+
+ temp = readl(sport->port.membase + UCR4);
+ temp |= UCR4_DREN;
+ writel(temp, sport->port.membase + UCR4);
+ }
+ return;
+ }
+
temp = readl(sport->port.membase + UCR1);
writel(temp & ~UCR1_TXMPTYEN, sport->port.membase + UCR1);
}
/* send xmit->buf[xmit->tail]
* out the port here */
writel(xmit->buf[xmit->tail], sport->port.membase + URTX0);
- xmit->tail = (xmit->tail + 1) &
- (UART_XMIT_SIZE - 1);
+ xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
sport->port.icount.tx++;
if (uart_circ_empty(xmit))
break;
}
+ if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+ uart_write_wakeup(&sport->port);
+
if (uart_circ_empty(xmit))
imx_stop_tx(&sport->port);
}
struct imx_port *sport = (struct imx_port *)port;
unsigned long temp;
+ if (USE_IRDA(sport)) {
+ /* half duplex in IrDA mode; have to disable receive mode */
+ temp = readl(sport->port.membase + UCR4);
+ temp &= ~(UCR4_DREN);
+ writel(temp, sport->port.membase + UCR4);
+
+ temp = readl(sport->port.membase + UCR1);
+ temp &= ~(UCR1_RRDYEN);
+ writel(temp, sport->port.membase + UCR1);
+ }
+
temp = readl(sport->port.membase + UCR1);
writel(temp | UCR1_TXMPTYEN, sport->port.membase + UCR1);
+ if (USE_IRDA(sport)) {
+ temp = readl(sport->port.membase + UCR1);
+ temp |= UCR1_TRDYEN;
+ writel(temp, sport->port.membase + UCR1);
+
+ temp = readl(sport->port.membase + UCR4);
+ temp |= UCR4_TCEN;
+ writel(temp, sport->port.membase + UCR4);
+ }
+
if (readl(sport->port.membase + UTS) & UTS_TXEMPTY)
imx_transmit_buffer(sport);
}
continue;
}
- if (uart_handle_sysrq_char
- (&sport->port, (unsigned char)rx))
+ if (uart_handle_sysrq_char(&sport->port, (unsigned char)rx))
continue;
if (rx & (URXD_PRERR | URXD_OVRRUN | URXD_FRMERR) ) {
*/
static unsigned int imx_get_mctrl(struct uart_port *port)
{
- struct imx_port *sport = (struct imx_port *)port;
- unsigned int tmp = TIOCM_DSR | TIOCM_CAR;
+ struct imx_port *sport = (struct imx_port *)port;
+ unsigned int tmp = TIOCM_DSR | TIOCM_CAR;
- if (readl(sport->port.membase + USR1) & USR1_RTSS)
- tmp |= TIOCM_CTS;
+ if (readl(sport->port.membase + USR1) & USR1_RTSS)
+ tmp |= TIOCM_CTS;
- if (readl(sport->port.membase + UCR2) & UCR2_CTS)
- tmp |= TIOCM_RTS;
+ if (readl(sport->port.membase + UCR2) & UCR2_CTS)
+ tmp |= TIOCM_RTS;
- return tmp;
+ return tmp;
}
static void imx_set_mctrl(struct uart_port *port, unsigned int mctrl)
{
- struct imx_port *sport = (struct imx_port *)port;
+ struct imx_port *sport = (struct imx_port *)port;
unsigned long temp;
temp = readl(sport->port.membase + UCR2) & ~UCR2_CTS;
- if (mctrl & TIOCM_RTS)
+ if (mctrl & TIOCM_RTS)
temp |= UCR2_CTS;
writel(temp, sport->port.membase + UCR2);
if(!ufcr_rfdiv)
ufcr_rfdiv = 1;
- if(ufcr_rfdiv >= 7)
- ufcr_rfdiv = 6;
- else
- ufcr_rfdiv = 6 - ufcr_rfdiv;
-
- val |= UFCR_RFDIV & (ufcr_rfdiv << 7);
+ val |= UFCR_RFDIV_REG(ufcr_rfdiv);
writel(val, sport->port.membase + UFCR);
* requesting IRQs
*/
temp = readl(sport->port.membase + UCR4);
+
+ if (USE_IRDA(sport))
+ temp |= UCR4_IRSC;
+
writel(temp & ~UCR4_DREN, sport->port.membase + UCR4);
+ if (USE_IRDA(sport)) {
+ /* reset fifo's and state machines */
+ int i = 100;
+ temp = readl(sport->port.membase + UCR2);
+ temp &= ~UCR2_SRST;
+ writel(temp, sport->port.membase + UCR2);
+ while (!(readl(sport->port.membase + UCR2) & UCR2_SRST) &&
+ (--i > 0)) {
+ udelay(1);
+ }
+ }
+
/*
* Allocate the IRQ(s) i.MX1 has three interrupts whereas later
* chips only have one interrupt.
if (retval)
goto error_out2;
- retval = request_irq(sport->rtsirq, imx_rtsint,
- (sport->rtsirq < MAX_INTERNAL_IRQ) ? 0 :
- IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
- DRIVER_NAME, sport);
- if (retval)
- goto error_out3;
+ /* do not use RTS IRQ on IrDA */
+ if (!USE_IRDA(sport)) {
+ retval = request_irq(sport->rtsirq, imx_rtsint,
+ (sport->rtsirq < MAX_INTERNAL_IRQ) ? 0 :
+ IRQF_TRIGGER_FALLING |
+ IRQF_TRIGGER_RISING,
+ DRIVER_NAME, sport);
+ if (retval)
+ goto error_out3;
+ }
} else {
retval = request_irq(sport->port.irq, imx_int, 0,
DRIVER_NAME, sport);
temp = readl(sport->port.membase + UCR1);
temp |= UCR1_RRDYEN | UCR1_RTSDEN | UCR1_UARTEN;
+
+ if (USE_IRDA(sport)) {
+ temp |= UCR1_IREN;
+ temp &= ~(UCR1_RTSDEN);
+ }
+
writel(temp, sport->port.membase + UCR1);
temp = readl(sport->port.membase + UCR2);
temp |= (UCR2_RXEN | UCR2_TXEN);
writel(temp, sport->port.membase + UCR2);
+ if (USE_IRDA(sport)) {
+ /* clear RX-FIFO */
+ int i = 64;
+ while ((--i > 0) &&
+ (readl(sport->port.membase + URXD0) & URXD_CHARRDY)) {
+ barrier();
+ }
+ }
+
#if defined CONFIG_ARCH_MX2 || defined CONFIG_ARCH_MX3
temp = readl(sport->port.membase + UCR3);
temp |= UCR3_RXDMUXSEL;
writel(temp, sport->port.membase + UCR3);
#endif
+ if (USE_IRDA(sport)) {
+ temp = readl(sport->port.membase + UCR4);
+ if (sport->irda_inv_rx)
+ temp |= UCR4_INVR;
+ else
+ temp &= ~(UCR4_INVR);
+ writel(temp | UCR4_DREN, sport->port.membase + UCR4);
+
+ temp = readl(sport->port.membase + UCR3);
+ if (sport->irda_inv_tx)
+ temp |= UCR3_INVT;
+ else
+ temp &= ~(UCR3_INVT);
+ writel(temp, sport->port.membase + UCR3);
+ }
+
/*
* Enable modem status interrupts
*/
imx_enable_ms(&sport->port);
spin_unlock_irqrestore(&sport->port.lock,flags);
+ if (USE_IRDA(sport)) {
+ struct imxuart_platform_data *pdata;
+ pdata = sport->port.dev->platform_data;
+ sport->irda_inv_rx = pdata->irda_inv_rx;
+ sport->irda_inv_tx = pdata->irda_inv_tx;
+ sport->trcv_delay = pdata->transceiver_delay;
+ if (pdata->irda_enable)
+ pdata->irda_enable(1);
+ }
+
return 0;
error_out3:
struct imx_port *sport = (struct imx_port *)port;
unsigned long temp;
+ temp = readl(sport->port.membase + UCR2);
+ temp &= ~(UCR2_TXEN);
+ writel(temp, sport->port.membase + UCR2);
+
+ if (USE_IRDA(sport)) {
+ struct imxuart_platform_data *pdata;
+ pdata = sport->port.dev->platform_data;
+ if (pdata->irda_enable)
+ pdata->irda_enable(0);
+ }
+
/*
* Stop our timer.
*/
* Free the interrupts
*/
if (sport->txirq > 0) {
- free_irq(sport->rtsirq, sport);
+ if (!USE_IRDA(sport))
+ free_irq(sport->rtsirq, sport);
free_irq(sport->txirq, sport);
free_irq(sport->rxirq, sport);
} else
temp = readl(sport->port.membase + UCR1);
temp &= ~(UCR1_TXMPTYEN | UCR1_RRDYEN | UCR1_RTSDEN | UCR1_UARTEN);
+ if (USE_IRDA(sport))
+ temp &= ~(UCR1_IREN);
+
writel(temp, sport->port.membase + UCR1);
}
unsigned long flags;
unsigned int ucr2, old_ucr1, old_txrxen, baud, quot;
unsigned int old_csize = old ? old->c_cflag & CSIZE : CS8;
- unsigned int div, num, denom, ufcr;
+ unsigned int div, ufcr;
+ unsigned long num, denom;
+ uint64_t tdiv64;
/*
* If we don't support modem control lines, don't allow
sport->port.membase + UCR2);
old_txrxen &= (UCR2_TXEN | UCR2_RXEN);
- div = sport->port.uartclk / (baud * 16);
- if (div > 7)
- div = 7;
- if (!div)
+ if (USE_IRDA(sport)) {
+ /*
+ * use maximum available submodule frequency to
+ * avoid missing short pulses due to low sampling rate
+ */
div = 1;
-
- num = baud;
- denom = port->uartclk / div / 16;
-
- /* shift num and denom right until they fit into 16 bits */
- while (num > 0x10000 || denom > 0x10000) {
- num >>= 1;
- denom >>= 1;
+ } else {
+ div = sport->port.uartclk / (baud * 16);
+ if (div > 7)
+ div = 7;
+ if (!div)
+ div = 1;
}
- if (num > 0)
- num -= 1;
- if (denom > 0)
- denom -= 1;
- writel(num, sport->port.membase + UBIR);
- writel(denom, sport->port.membase + UBMR);
+ rational_best_approximation(16 * div * baud, sport->port.uartclk,
+ 1 << 16, 1 << 16, &num, &denom);
- if (div == 7)
- div = 6; /* 6 in RFDIV means divide by 7 */
- else
- div = 6 - div;
+ tdiv64 = sport->port.uartclk;
+ tdiv64 *= num;
+ do_div(tdiv64, denom * 16 * div);
+ tty_encode_baud_rate(sport->port.info->port.tty,
+ (speed_t)tdiv64, (speed_t)tdiv64);
+
+ num -= 1;
+ denom -= 1;
ufcr = readl(sport->port.membase + UFCR);
- ufcr = (ufcr & (~UFCR_RFDIV)) |
- (div << 7);
+ ufcr = (ufcr & (~UFCR_RFDIV)) | UFCR_RFDIV_REG(div);
writel(ufcr, sport->port.membase + UFCR);
+ writel(num, sport->port.membase + UBIR);
+ writel(denom, sport->port.membase + UBMR);
+
#ifdef ONEMS
writel(sport->port.uartclk / div / 1000, sport->port.membase + ONEMS);
#endif
static int serial_imx_suspend(struct platform_device *dev, pm_message_t state)
{
- struct imx_port *sport = platform_get_drvdata(dev);
+ struct imx_port *sport = platform_get_drvdata(dev);
- if (sport)
- uart_suspend_port(&imx_reg, &sport->port);
+ if (sport)
+ uart_suspend_port(&imx_reg, &sport->port);
- return 0;
+ return 0;
}
static int serial_imx_resume(struct platform_device *dev)
{
- struct imx_port *sport = platform_get_drvdata(dev);
+ struct imx_port *sport = platform_get_drvdata(dev);
- if (sport)
- uart_resume_port(&imx_reg, &sport->port);
+ if (sport)
+ uart_resume_port(&imx_reg, &sport->port);
- return 0;
+ return 0;
}
static int serial_imx_probe(struct platform_device *pdev)
imx_ports[pdev->id] = sport;
pdata = pdev->dev.platform_data;
- if(pdata && (pdata->flags & IMXUART_HAVE_RTSCTS))
+ if (pdata && (pdata->flags & IMXUART_HAVE_RTSCTS))
sport->have_rtscts = 1;
+#ifdef CONFIG_IRDA
+ if (pdata && (pdata->flags & IMXUART_IRDA))
+ sport->use_irda = 1;
+#endif
+
if (pdata->init) {
ret = pdata->init(pdev);
if (ret)
goto clkput;
}
- uart_add_one_port(&imx_reg, &sport->port);
+ ret = uart_add_one_port(&imx_reg, &sport->port);
+ if (ret)
+ goto deinit;
platform_set_drvdata(pdev, &sport->port);
return 0;
+deinit:
+ if (pdata->exit)
+ pdata->exit(pdev);
clkput:
clk_put(sport->clk);
clk_disable(sport->clk);
}
static struct platform_driver serial_imx_driver = {
- .probe = serial_imx_probe,
- .remove = serial_imx_remove,
+ .probe = serial_imx_probe,
+ .remove = serial_imx_remove,
.suspend = serial_imx_suspend,
.resume = serial_imx_resume,
.driver = {
- .name = "imx-uart",
+ .name = "imx-uart",
.owner = THIS_MODULE,
},
};
if ((DBG_##nlevel & jsm_debug)) \
dev_printk(KERN_##klevel, pdev->dev, fmt, ## args)
+#define MAXLINES 256
#define MAXPORTS 8
#define MAX_STOPS_SENT 5
#include "jsm.h"
+static DECLARE_BITMAP(linemap, MAXLINES);
+
static void jsm_carrier(struct jsm_channel *ch);
static inline int jsm_get_mstat(struct jsm_channel *ch)
int __devinit jsm_uart_port_init(struct jsm_board *brd)
{
int i;
+ unsigned int line;
struct jsm_channel *ch;
if (!brd)
brd->channels[i]->uart_port.membase = brd->re_map_membase;
brd->channels[i]->uart_port.fifosize = 16;
brd->channels[i]->uart_port.ops = &jsm_ops;
- brd->channels[i]->uart_port.line = brd->channels[i]->ch_portnum + brd->boardnum * 2;
+ line = find_first_zero_bit(linemap, MAXLINES);
+ if (line >= MAXLINES) {
+ printk(KERN_INFO "jsm: linemap is full, added device failed\n");
+ continue;
+ } else
+ set_bit((int)line, linemap);
+ brd->channels[i]->uart_port.line = line;
if (uart_add_one_port (&jsm_uart_driver, &brd->channels[i]->uart_port))
- printk(KERN_INFO "Added device failed\n");
+ printk(KERN_INFO "jsm: add device failed\n");
else
printk(KERN_INFO "Added device \n");
}
ch = brd->channels[i];
+ clear_bit((int)(ch->uart_port.line), linemap);
uart_remove_one_port(&jsm_uart_driver, &brd->channels[i]->uart_port);
}
--- /dev/null
+/*
+ * timbuart.c timberdale FPGA UART driver
+ * Copyright (c) 2009 Intel Corporation
+ *
+ * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/* Supports:
+ * Timberdale FPGA UART
+ */
+
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/serial_core.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/ioport.h>
+
+#include "timbuart.h"
+
+struct timbuart_port {
+ struct uart_port port;
+ struct tasklet_struct tasklet;
+ int usedma;
+ u8 last_ier;
+ struct platform_device *dev;
+};
+
+static int baudrates[] = {9600, 19200, 38400, 57600, 115200, 230400, 460800,
+ 921600, 1843200, 3250000};
+
+static void timbuart_mctrl_check(struct uart_port *port, u8 isr, u8 *ier);
+
+static irqreturn_t timbuart_handleinterrupt(int irq, void *devid);
+
+static void timbuart_stop_rx(struct uart_port *port)
+{
+ /* spin lock held by upper layer, disable all RX interrupts */
+ u8 ier = ioread8(port->membase + TIMBUART_IER) & ~RXFLAGS;
+ iowrite8(ier, port->membase + TIMBUART_IER);
+}
+
+static void timbuart_stop_tx(struct uart_port *port)
+{
+ /* spinlock held by upper layer, disable TX interrupt */
+ u8 ier = ioread8(port->membase + TIMBUART_IER) & ~TXBAE;
+ iowrite8(ier, port->membase + TIMBUART_IER);
+}
+
+static void timbuart_start_tx(struct uart_port *port)
+{
+ struct timbuart_port *uart =
+ container_of(port, struct timbuart_port, port);
+
+ /* do not transfer anything here -> fire off the tasklet */
+ tasklet_schedule(&uart->tasklet);
+}
+
+static void timbuart_flush_buffer(struct uart_port *port)
+{
+ u8 ctl = ioread8(port->membase + TIMBUART_CTRL) | TIMBUART_CTRL_FLSHTX;
+
+ iowrite8(ctl, port->membase + TIMBUART_CTRL);
+ iowrite8(TXBF, port->membase + TIMBUART_ISR);
+}
+
+static void timbuart_rx_chars(struct uart_port *port)
+{
+ struct tty_struct *tty = port->info->port.tty;
+
+ while (ioread8(port->membase + TIMBUART_ISR) & RXDP) {
+ u8 ch = ioread8(port->membase + TIMBUART_RXFIFO);
+ port->icount.rx++;
+ tty_insert_flip_char(tty, ch, TTY_NORMAL);
+ }
+
+ spin_unlock(&port->lock);
+ tty_flip_buffer_push(port->info->port.tty);
+ spin_lock(&port->lock);
+
+ dev_dbg(port->dev, "%s - total read %d bytes\n",
+ __func__, port->icount.rx);
+}
+
+static void timbuart_tx_chars(struct uart_port *port)
+{
+ struct circ_buf *xmit = &port->info->xmit;
+
+ while (!(ioread8(port->membase + TIMBUART_ISR) & TXBF) &&
+ !uart_circ_empty(xmit)) {
+ iowrite8(xmit->buf[xmit->tail],
+ port->membase + TIMBUART_TXFIFO);
+ xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
+ port->icount.tx++;
+ }
+
+ dev_dbg(port->dev,
+ "%s - total written %d bytes, CTL: %x, RTS: %x, baud: %x\n",
+ __func__,
+ port->icount.tx,
+ ioread8(port->membase + TIMBUART_CTRL),
+ port->mctrl & TIOCM_RTS,
+ ioread8(port->membase + TIMBUART_BAUDRATE));
+}
+
+static void timbuart_handle_tx_port(struct uart_port *port, u8 isr, u8 *ier)
+{
+ struct timbuart_port *uart =
+ container_of(port, struct timbuart_port, port);
+ struct circ_buf *xmit = &port->info->xmit;
+
+ if (uart_circ_empty(xmit) || uart_tx_stopped(port))
+ return;
+
+ if (port->x_char)
+ return;
+
+ if (isr & TXFLAGS) {
+ timbuart_tx_chars(port);
+ /* clear all TX interrupts */
+ iowrite8(TXFLAGS, port->membase + TIMBUART_ISR);
+
+ if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+ uart_write_wakeup(port);
+ } else
+ /* Re-enable any tx interrupt */
+ *ier |= uart->last_ier & TXFLAGS;
+
+ /* enable interrupts if there are chars in the transmit buffer,
+ * Or if we delivered some bytes and want the almost empty interrupt
+ * we wake up the upper layer later when we got the interrupt
+ * to give it some time to go out...
+ */
+ if (!uart_circ_empty(xmit))
+ *ier |= TXBAE;
+
+ dev_dbg(port->dev, "%s - leaving\n", __func__);
+}
+
+void timbuart_handle_rx_port(struct uart_port *port, u8 isr, u8 *ier)
+{
+ if (isr & RXFLAGS) {
+ /* Some RX status is set */
+ if (isr & RXBF) {
+ u8 ctl = ioread8(port->membase + TIMBUART_CTRL) |
+ TIMBUART_CTRL_FLSHRX;
+ iowrite8(ctl, port->membase + TIMBUART_CTRL);
+ port->icount.overrun++;
+ } else if (isr & (RXDP))
+ timbuart_rx_chars(port);
+
+ /* ack all RX interrupts */
+ iowrite8(RXFLAGS, port->membase + TIMBUART_ISR);
+ }
+
+ /* always have the RX interrupts enabled */
+ *ier |= RXBAF | RXBF | RXTT;
+
+ dev_dbg(port->dev, "%s - leaving\n", __func__);
+}
+
+void timbuart_tasklet(unsigned long arg)
+{
+ struct timbuart_port *uart = (struct timbuart_port *)arg;
+ u8 isr, ier = 0;
+
+ spin_lock(&uart->port.lock);
+
+ isr = ioread8(uart->port.membase + TIMBUART_ISR);
+ dev_dbg(uart->port.dev, "%s ISR: %x\n", __func__, isr);
+
+ if (!uart->usedma)
+ timbuart_handle_tx_port(&uart->port, isr, &ier);
+
+ timbuart_mctrl_check(&uart->port, isr, &ier);
+
+ if (!uart->usedma)
+ timbuart_handle_rx_port(&uart->port, isr, &ier);
+
+ iowrite8(ier, uart->port.membase + TIMBUART_IER);
+
+ spin_unlock(&uart->port.lock);
+ dev_dbg(uart->port.dev, "%s leaving\n", __func__);
+}
+
+static unsigned int timbuart_tx_empty(struct uart_port *port)
+{
+ u8 isr = ioread8(port->membase + TIMBUART_ISR);
+
+ return (isr & TXBAE) ? TIOCSER_TEMT : 0;
+}
+
+static unsigned int timbuart_get_mctrl(struct uart_port *port)
+{
+ u8 cts = ioread8(port->membase + TIMBUART_CTRL);
+ dev_dbg(port->dev, "%s - cts %x\n", __func__, cts);
+
+ if (cts & TIMBUART_CTRL_CTS)
+ return TIOCM_CTS | TIOCM_DSR | TIOCM_CAR;
+ else
+ return TIOCM_DSR | TIOCM_CAR;
+}
+
+static void timbuart_set_mctrl(struct uart_port *port, unsigned int mctrl)
+{
+ dev_dbg(port->dev, "%s - %x\n", __func__, mctrl);
+
+ if (mctrl & TIOCM_RTS)
+ iowrite8(TIMBUART_CTRL_RTS, port->membase + TIMBUART_CTRL);
+ else
+ iowrite8(TIMBUART_CTRL_RTS, port->membase + TIMBUART_CTRL);
+}
+
+static void timbuart_mctrl_check(struct uart_port *port, u8 isr, u8 *ier)
+{
+ unsigned int cts;
+
+ if (isr & CTS_DELTA) {
+ /* ack */
+ iowrite8(CTS_DELTA, port->membase + TIMBUART_ISR);
+ cts = timbuart_get_mctrl(port);
+ uart_handle_cts_change(port, cts & TIOCM_CTS);
+ wake_up_interruptible(&port->info->delta_msr_wait);
+ }
+
+ *ier |= CTS_DELTA;
+}
+
+static void timbuart_enable_ms(struct uart_port *port)
+{
+ /* N/A */
+}
+
+static void timbuart_break_ctl(struct uart_port *port, int ctl)
+{
+ /* N/A */
+}
+
+static int timbuart_startup(struct uart_port *port)
+{
+ struct timbuart_port *uart =
+ container_of(port, struct timbuart_port, port);
+
+ dev_dbg(port->dev, "%s\n", __func__);
+
+ iowrite8(TIMBUART_CTRL_FLSHRX, port->membase + TIMBUART_CTRL);
+ iowrite8(0xff, port->membase + TIMBUART_ISR);
+ /* Enable all but TX interrupts */
+ iowrite8(RXBAF | RXBF | RXTT | CTS_DELTA,
+ port->membase + TIMBUART_IER);
+
+ return request_irq(port->irq, timbuart_handleinterrupt, IRQF_SHARED,
+ "timb-uart", uart);
+}
+
+static void timbuart_shutdown(struct uart_port *port)
+{
+ struct timbuart_port *uart =
+ container_of(port, struct timbuart_port, port);
+ dev_dbg(port->dev, "%s\n", __func__);
+ free_irq(port->irq, uart);
+ iowrite8(0, port->membase + TIMBUART_IER);
+}
+
+static int get_bindex(int baud)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(baudrates); i++)
+ if (baud <= baudrates[i])
+ return i;
+
+ return -1;
+}
+
+static void timbuart_set_termios(struct uart_port *port,
+ struct ktermios *termios,
+ struct ktermios *old)
+{
+ unsigned int baud;
+ short bindex;
+ unsigned long flags;
+
+ baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk / 16);
+ bindex = get_bindex(baud);
+ dev_dbg(port->dev, "%s - bindex %d\n", __func__, bindex);
+
+ if (bindex < 0)
+ bindex = 0;
+ baud = baudrates[bindex];
+
+ /* The serial layer calls into this once with old = NULL when setting
+ up initially */
+ if (old)
+ tty_termios_copy_hw(termios, old);
+ tty_termios_encode_baud_rate(termios, baud, baud);
+
+ spin_lock_irqsave(&port->lock, flags);
+ iowrite8((u8)bindex, port->membase + TIMBUART_BAUDRATE);
+ uart_update_timeout(port, termios->c_cflag, baud);
+ spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static const char *timbuart_type(struct uart_port *port)
+{
+ return port->type == PORT_UNKNOWN ? "timbuart" : NULL;
+}
+
+/* We do not request/release mappings of the registers here,
+ * currently it's done in the proble function.
+ */
+static void timbuart_release_port(struct uart_port *port)
+{
+ struct platform_device *pdev = to_platform_device(port->dev);
+ int size =
+ resource_size(platform_get_resource(pdev, IORESOURCE_MEM, 0));
+
+ if (port->flags & UPF_IOREMAP) {
+ iounmap(port->membase);
+ port->membase = NULL;
+ }
+
+ release_mem_region(port->mapbase, size);
+}
+
+static int timbuart_request_port(struct uart_port *port)
+{
+ struct platform_device *pdev = to_platform_device(port->dev);
+ int size =
+ resource_size(platform_get_resource(pdev, IORESOURCE_MEM, 0));
+
+ if (!request_mem_region(port->mapbase, size, "timb-uart"))
+ return -EBUSY;
+
+ if (port->flags & UPF_IOREMAP) {
+ port->membase = ioremap(port->mapbase, size);
+ if (port->membase == NULL) {
+ release_mem_region(port->mapbase, size);
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+static irqreturn_t timbuart_handleinterrupt(int irq, void *devid)
+{
+ struct timbuart_port *uart = (struct timbuart_port *)devid;
+
+ if (ioread8(uart->port.membase + TIMBUART_IPR)) {
+ uart->last_ier = ioread8(uart->port.membase + TIMBUART_IER);
+
+ /* disable interrupts, the tasklet enables them again */
+ iowrite8(0, uart->port.membase + TIMBUART_IER);
+
+ /* fire off bottom half */
+ tasklet_schedule(&uart->tasklet);
+
+ return IRQ_HANDLED;
+ } else
+ return IRQ_NONE;
+}
+
+/*
+ * Configure/autoconfigure the port.
+ */
+static void timbuart_config_port(struct uart_port *port, int flags)
+{
+ if (flags & UART_CONFIG_TYPE) {
+ port->type = PORT_TIMBUART;
+ timbuart_request_port(port);
+ }
+}
+
+static int timbuart_verify_port(struct uart_port *port,
+ struct serial_struct *ser)
+{
+ /* we don't want the core code to modify any port params */
+ return -EINVAL;
+}
+
+static struct uart_ops timbuart_ops = {
+ .tx_empty = timbuart_tx_empty,
+ .set_mctrl = timbuart_set_mctrl,
+ .get_mctrl = timbuart_get_mctrl,
+ .stop_tx = timbuart_stop_tx,
+ .start_tx = timbuart_start_tx,
+ .flush_buffer = timbuart_flush_buffer,
+ .stop_rx = timbuart_stop_rx,
+ .enable_ms = timbuart_enable_ms,
+ .break_ctl = timbuart_break_ctl,
+ .startup = timbuart_startup,
+ .shutdown = timbuart_shutdown,
+ .set_termios = timbuart_set_termios,
+ .type = timbuart_type,
+ .release_port = timbuart_release_port,
+ .request_port = timbuart_request_port,
+ .config_port = timbuart_config_port,
+ .verify_port = timbuart_verify_port
+};
+
+static struct uart_driver timbuart_driver = {
+ .owner = THIS_MODULE,
+ .driver_name = "timberdale_uart",
+ .dev_name = "ttyTU",
+ .major = TIMBUART_MAJOR,
+ .minor = TIMBUART_MINOR,
+ .nr = 1
+};
+
+static int timbuart_probe(struct platform_device *dev)
+{
+ int err;
+ struct timbuart_port *uart;
+ struct resource *iomem;
+
+ dev_dbg(&dev->dev, "%s\n", __func__);
+
+ uart = kzalloc(sizeof(*uart), GFP_KERNEL);
+ if (!uart) {
+ err = -EINVAL;
+ goto err_mem;
+ }
+
+ uart->usedma = 0;
+
+ uart->port.uartclk = 3250000 * 16;
+ uart->port.fifosize = TIMBUART_FIFO_SIZE;
+ uart->port.regshift = 2;
+ uart->port.iotype = UPIO_MEM;
+ uart->port.ops = &timbuart_ops;
+ uart->port.irq = 0;
+ uart->port.flags = UPF_BOOT_AUTOCONF | UPF_IOREMAP;
+ uart->port.line = 0;
+ uart->port.dev = &dev->dev;
+
+ iomem = platform_get_resource(dev, IORESOURCE_MEM, 0);
+ if (!iomem) {
+ err = -ENOMEM;
+ goto err_register;
+ }
+ uart->port.mapbase = iomem->start;
+ uart->port.membase = NULL;
+
+ uart->port.irq = platform_get_irq(dev, 0);
+ if (uart->port.irq < 0) {
+ err = -EINVAL;
+ goto err_register;
+ }
+
+ tasklet_init(&uart->tasklet, timbuart_tasklet, (unsigned long)uart);
+
+ err = uart_register_driver(&timbuart_driver);
+ if (err)
+ goto err_register;
+
+ err = uart_add_one_port(&timbuart_driver, &uart->port);
+ if (err)
+ goto err_add_port;
+
+ platform_set_drvdata(dev, uart);
+
+ return 0;
+
+err_add_port:
+ uart_unregister_driver(&timbuart_driver);
+err_register:
+ kfree(uart);
+err_mem:
+ printk(KERN_ERR "timberdale: Failed to register Timberdale UART: %d\n",
+ err);
+
+ return err;
+}
+
+static int timbuart_remove(struct platform_device *dev)
+{
+ struct timbuart_port *uart = platform_get_drvdata(dev);
+
+ tasklet_kill(&uart->tasklet);
+ uart_remove_one_port(&timbuart_driver, &uart->port);
+ uart_unregister_driver(&timbuart_driver);
+ kfree(uart);
+
+ return 0;
+}
+
+static struct platform_driver timbuart_platform_driver = {
+ .driver = {
+ .name = "timb-uart",
+ .owner = THIS_MODULE,
+ },
+ .probe = timbuart_probe,
+ .remove = timbuart_remove,
+};
+
+/*--------------------------------------------------------------------------*/
+
+static int __init timbuart_init(void)
+{
+ return platform_driver_register(&timbuart_platform_driver);
+}
+
+static void __exit timbuart_exit(void)
+{
+ platform_driver_unregister(&timbuart_platform_driver);
+}
+
+module_init(timbuart_init);
+module_exit(timbuart_exit);
+
+MODULE_DESCRIPTION("Timberdale UART driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:timb-uart");
+
--- /dev/null
+/*
+ * timbuart.c timberdale FPGA GPIO driver
+ * Copyright (c) 2009 Intel Corporation
+ *
+ * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/* Supports:
+ * Timberdale FPGA UART
+ */
+
+#ifndef _TIMBUART_H
+#define _TIMBUART_H
+
+#define TIMBUART_FIFO_SIZE 2048
+
+#define TIMBUART_RXFIFO 0x08
+#define TIMBUART_TXFIFO 0x0c
+#define TIMBUART_IER 0x10
+#define TIMBUART_IPR 0x14
+#define TIMBUART_ISR 0x18
+#define TIMBUART_CTRL 0x1c
+#define TIMBUART_BAUDRATE 0x20
+
+#define TIMBUART_CTRL_RTS 0x01
+#define TIMBUART_CTRL_CTS 0x02
+#define TIMBUART_CTRL_FLSHTX 0x40
+#define TIMBUART_CTRL_FLSHRX 0x80
+
+#define TXBF 0x01
+#define TXBAE 0x02
+#define CTS_DELTA 0x04
+#define RXDP 0x08
+#define RXBAF 0x10
+#define RXBF 0x20
+#define RXTT 0x40
+#define RXBNAE 0x80
+#define TXBE 0x100
+
+#define RXFLAGS (RXDP | RXBAF | RXBF | RXTT | RXBNAE)
+#define TXFLAGS (TXBF | TXBAE)
+
+#define TIMBUART_MAJOR 204
+#define TIMBUART_MINOR 192
+
+#endif /* _TIMBUART_H */
+
* v0.9 - thorough cleaning, URBification, almost a rewrite
* v0.10 - some more cleanups
* v0.11 - fixed flow control, read error doesn't stop reads
- * v0.12 - added TIOCM ioctls, added break handling, made struct acm kmalloced
+ * v0.12 - added TIOCM ioctls, added break handling, made struct acm
+ * kmalloced
* v0.13 - added termios, added hangup
* v0.14 - sized down struct acm
* v0.15 - fixed flow control again - characters could be lost
#include <linux/tty_flip.h>
#include <linux/module.h>
#include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <linux/usb.h>
#include <linux/usb/cdc.h>
#include <asm/byteorder.h>
static DEFINE_MUTEX(open_mutex);
-#define ACM_READY(acm) (acm && acm->dev && acm->used)
+#define ACM_READY(acm) (acm && acm->dev && acm->port.count)
+
+static const struct tty_port_operations acm_port_ops = {
+};
#ifdef VERBOSE_DEBUG
#define verbose 1
* Functions for ACM control messages.
*/
-static int acm_ctrl_msg(struct acm *acm, int request, int value, void *buf, int len)
+static int acm_ctrl_msg(struct acm *acm, int request, int value,
+ void *buf, int len)
{
int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
request, USB_RT_ACM, value,
acm->control->altsetting[0].desc.bInterfaceNumber,
buf, len, 5000);
- dbg("acm_control_msg: rq: 0x%02x val: %#x len: %#x result: %d", request, value, len, retval);
+ dbg("acm_control_msg: rq: 0x%02x val: %#x len: %#x result: %d",
+ request, value, len, retval);
return retval < 0 ? retval : 0;
}
n = ACM_NW;
spin_lock_irqsave(&acm->write_lock, flags);
- for (i = 0; i < ACM_NW; i++) {
+ for (i = 0; i < ACM_NW; i++)
n -= acm->wb[i].use;
- }
spin_unlock_irqrestore(&acm->write_lock, flags);
return n;
}
wb->urb->transfer_buffer_length = wb->len;
wb->urb->dev = acm->dev;
- if ((rc = usb_submit_urb(wb->urb, GFP_ATOMIC)) < 0) {
+ rc = usb_submit_urb(wb->urb, GFP_ATOMIC);
+ if (rc < 0) {
dbg("usb_submit_urb(write bulk) failed: %d", rc);
acm_write_done(acm, wb);
}
{
struct acm *acm = urb->context;
struct usb_cdc_notification *dr = urb->transfer_buffer;
+ struct tty_struct *tty;
unsigned char *data;
int newctrl;
int retval;
data = (unsigned char *)(dr + 1);
switch (dr->bNotificationType) {
+ case USB_CDC_NOTIFY_NETWORK_CONNECTION:
+ dbg("%s network", dr->wValue ?
+ "connected to" : "disconnected from");
+ break;
- case USB_CDC_NOTIFY_NETWORK_CONNECTION:
-
- dbg("%s network", dr->wValue ? "connected to" : "disconnected from");
- break;
-
- case USB_CDC_NOTIFY_SERIAL_STATE:
-
- newctrl = get_unaligned_le16(data);
+ case USB_CDC_NOTIFY_SERIAL_STATE:
+ tty = tty_port_tty_get(&acm->port);
+ newctrl = get_unaligned_le16(data);
- if (acm->tty && !acm->clocal && (acm->ctrlin & ~newctrl & ACM_CTRL_DCD)) {
+ if (tty) {
+ if (!acm->clocal &&
+ (acm->ctrlin & ~newctrl & ACM_CTRL_DCD)) {
dbg("calling hangup");
- tty_hangup(acm->tty);
+ tty_hangup(tty);
}
+ tty_kref_put(tty);
+ }
- acm->ctrlin = newctrl;
-
- dbg("input control lines: dcd%c dsr%c break%c ring%c framing%c parity%c overrun%c",
- acm->ctrlin & ACM_CTRL_DCD ? '+' : '-', acm->ctrlin & ACM_CTRL_DSR ? '+' : '-',
- acm->ctrlin & ACM_CTRL_BRK ? '+' : '-', acm->ctrlin & ACM_CTRL_RI ? '+' : '-',
- acm->ctrlin & ACM_CTRL_FRAMING ? '+' : '-', acm->ctrlin & ACM_CTRL_PARITY ? '+' : '-',
- acm->ctrlin & ACM_CTRL_OVERRUN ? '+' : '-');
+ acm->ctrlin = newctrl;
+ dbg("input control lines: dcd%c dsr%c break%c ring%c framing%c parity%c overrun%c",
+ acm->ctrlin & ACM_CTRL_DCD ? '+' : '-',
+ acm->ctrlin & ACM_CTRL_DSR ? '+' : '-',
+ acm->ctrlin & ACM_CTRL_BRK ? '+' : '-',
+ acm->ctrlin & ACM_CTRL_RI ? '+' : '-',
+ acm->ctrlin & ACM_CTRL_FRAMING ? '+' : '-',
+ acm->ctrlin & ACM_CTRL_PARITY ? '+' : '-',
+ acm->ctrlin & ACM_CTRL_OVERRUN ? '+' : '-');
break;
- default:
- dbg("unknown notification %d received: index %d len %d data0 %d data1 %d",
- dr->bNotificationType, dr->wIndex,
- dr->wLength, data[0], data[1]);
- break;
+ default:
+ dbg("unknown notification %d received: index %d len %d data0 %d data1 %d",
+ dr->bNotificationType, dr->wIndex,
+ dr->wLength, data[0], data[1]);
+ break;
}
exit:
usb_mark_last_busy(acm->dev);
- retval = usb_submit_urb (urb, GFP_ATOMIC);
+ retval = usb_submit_urb(urb, GFP_ATOMIC);
if (retval)
dev_err(&urb->dev->dev, "%s - usb_submit_urb failed with "
"result %d", __func__, retval);
{
struct acm *acm = (void *)_acm;
struct acm_rb *buf;
- struct tty_struct *tty = acm->tty;
+ struct tty_struct *tty;
struct acm_ru *rcv;
unsigned long flags;
unsigned char throttled;
dbg("Entering acm_rx_tasklet");
- if (!ACM_READY(acm))
- {
+ if (!ACM_READY(acm)) {
dbg("acm_rx_tasklet: ACM not ready");
return;
}
spin_lock_irqsave(&acm->throttle_lock, flags);
throttled = acm->throttle;
spin_unlock_irqrestore(&acm->throttle_lock, flags);
- if (throttled)
- {
+ if (throttled) {
dbg("acm_rx_tasklet: throttled");
return;
}
+ tty = tty_port_tty_get(&acm->port);
+
next_buffer:
spin_lock_irqsave(&acm->read_lock, flags);
if (list_empty(&acm->filled_read_bufs)) {
dbg("acm_rx_tasklet: procesing buf 0x%p, size = %d", buf, buf->size);
- tty_buffer_request_room(tty, buf->size);
- spin_lock_irqsave(&acm->throttle_lock, flags);
- throttled = acm->throttle;
- spin_unlock_irqrestore(&acm->throttle_lock, flags);
- if (!throttled)
- tty_insert_flip_string(tty, buf->base, buf->size);
- tty_flip_buffer_push(tty);
-
- if (throttled) {
- dbg("Throttling noticed");
- spin_lock_irqsave(&acm->read_lock, flags);
- list_add(&buf->list, &acm->filled_read_bufs);
- spin_unlock_irqrestore(&acm->read_lock, flags);
- return;
+ if (tty) {
+ spin_lock_irqsave(&acm->throttle_lock, flags);
+ throttled = acm->throttle;
+ spin_unlock_irqrestore(&acm->throttle_lock, flags);
+ if (!throttled) {
+ tty_buffer_request_room(tty, buf->size);
+ tty_insert_flip_string(tty, buf->base, buf->size);
+ tty_flip_buffer_push(tty);
+ } else {
+ tty_kref_put(tty);
+ dbg("Throttling noticed");
+ spin_lock_irqsave(&acm->read_lock, flags);
+ list_add(&buf->list, &acm->filled_read_bufs);
+ spin_unlock_irqrestore(&acm->read_lock, flags);
+ return;
+ }
}
spin_lock_irqsave(&acm->read_lock, flags);
goto next_buffer;
urbs:
+ tty_kref_put(tty);
+
while (!list_empty(&acm->spare_read_bufs)) {
spin_lock_irqsave(&acm->read_lock, flags);
if (list_empty(&acm->spare_read_urbs)) {
rcv->urb->transfer_dma = buf->dma;
rcv->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
- /* This shouldn't kill the driver as unsuccessful URBs are returned to the
- free-urbs-pool and resubmited ASAP */
+ /* This shouldn't kill the driver as unsuccessful URBs are
+ returned to the free-urbs-pool and resubmited ASAP */
spin_lock_irqsave(&acm->read_lock, flags);
- if (acm->susp_count || usb_submit_urb(rcv->urb, GFP_ATOMIC) < 0) {
+ if (acm->susp_count ||
+ usb_submit_urb(rcv->urb, GFP_ATOMIC) < 0) {
list_add(&buf->list, &acm->spare_read_bufs);
list_add(&rcv->list, &acm->spare_read_urbs);
acm->processing = 0;
static void acm_softint(struct work_struct *work)
{
struct acm *acm = container_of(work, struct acm, work);
+ struct tty_struct *tty;
dev_vdbg(&acm->data->dev, "tx work\n");
if (!ACM_READY(acm))
return;
- tty_wakeup(acm->tty);
+ tty = tty_port_tty_get(&acm->port);
+ tty_wakeup(tty);
+ tty_kref_put(tty);
}
static void acm_waker(struct work_struct *waker)
rv = 0;
set_bit(TTY_NO_WRITE_SPLIT, &tty->flags);
+
tty->driver_data = acm;
- acm->tty = tty;
+ tty_port_tty_set(&acm->port, tty);
if (usb_autopm_get_interface(acm->control) < 0)
goto early_bail;
acm->control->needs_remote_wakeup = 1;
mutex_lock(&acm->mutex);
- if (acm->used++) {
+ if (acm->port.count++) {
usb_autopm_put_interface(acm->control);
goto done;
- }
-
+ }
acm->ctrlurb->dev = acm->dev;
if (usb_submit_urb(acm->ctrlurb, GFP_KERNEL)) {
if (0 > acm_set_control(acm, acm->ctrlout = ACM_CTRL_DTR | ACM_CTRL_RTS) &&
(acm->ctrl_caps & USB_CDC_CAP_LINE))
goto full_bailout;
+
usb_autopm_put_interface(acm->control);
INIT_LIST_HEAD(&acm->spare_read_urbs);
INIT_LIST_HEAD(&acm->spare_read_bufs);
INIT_LIST_HEAD(&acm->filled_read_bufs);
- for (i = 0; i < acm->rx_buflimit; i++) {
+
+ for (i = 0; i < acm->rx_buflimit; i++)
list_add(&(acm->ru[i].list), &acm->spare_read_urbs);
- }
- for (i = 0; i < acm->rx_buflimit; i++) {
+ for (i = 0; i < acm->rx_buflimit; i++)
list_add(&(acm->rb[i].list), &acm->spare_read_bufs);
- }
acm->throttle = 0;
tasklet_schedule(&acm->urb_task);
-
+ rv = tty_port_block_til_ready(&acm->port, tty, filp);
done:
mutex_unlock(&acm->mutex);
err_out:
usb_kill_urb(acm->ctrlurb);
bail_out:
usb_autopm_put_interface(acm->control);
- acm->used--;
+ acm->port.count--;
mutex_unlock(&acm->mutex);
early_bail:
mutex_unlock(&open_mutex);
+ tty_port_tty_set(&acm->port, NULL);
return -EIO;
}
static void acm_tty_unregister(struct acm *acm)
{
- int i,nr;
+ int i, nr;
nr = acm->rx_buflimit;
tty_unregister_device(acm_tty_driver, acm->minor);
static int acm_tty_chars_in_buffer(struct tty_struct *tty);
+static void acm_port_down(struct acm *acm, int drain)
+{
+ int i, nr = acm->rx_buflimit;
+ mutex_lock(&open_mutex);
+ if (acm->dev) {
+ usb_autopm_get_interface(acm->control);
+ acm_set_control(acm, acm->ctrlout = 0);
+ /* try letting the last writes drain naturally */
+ if (drain) {
+ wait_event_interruptible_timeout(acm->drain_wait,
+ (ACM_NW == acm_wb_is_avail(acm)) || !acm->dev,
+ ACM_CLOSE_TIMEOUT * HZ);
+ }
+ usb_kill_urb(acm->ctrlurb);
+ for (i = 0; i < ACM_NW; i++)
+ usb_kill_urb(acm->wb[i].urb);
+ for (i = 0; i < nr; i++)
+ usb_kill_urb(acm->ru[i].urb);
+ acm->control->needs_remote_wakeup = 0;
+ usb_autopm_put_interface(acm->control);
+ }
+ mutex_unlock(&open_mutex);
+}
+
+static void acm_tty_hangup(struct tty_struct *tty)
+{
+ struct acm *acm = tty->driver_data;
+ tty_port_hangup(&acm->port);
+ acm_port_down(acm, 0);
+}
+
static void acm_tty_close(struct tty_struct *tty, struct file *filp)
{
struct acm *acm = tty->driver_data;
- int i,nr;
- if (!acm || !acm->used)
+ /* Perform the closing process and see if we need to do the hardware
+ shutdown */
+ if (tty_port_close_start(&acm->port, tty, filp) == 0)
return;
-
- nr = acm->rx_buflimit;
+ acm_port_down(acm, 0);
+ tty_port_close_end(&acm->port, tty);
mutex_lock(&open_mutex);
- if (!--acm->used) {
- if (acm->dev) {
- usb_autopm_get_interface(acm->control);
- acm_set_control(acm, acm->ctrlout = 0);
-
- /* try letting the last writes drain naturally */
- wait_event_interruptible_timeout(acm->drain_wait,
- (ACM_NW == acm_wb_is_avail(acm))
- || !acm->dev,
- ACM_CLOSE_TIMEOUT * HZ);
-
- usb_kill_urb(acm->ctrlurb);
- for (i = 0; i < ACM_NW; i++)
- usb_kill_urb(acm->wb[i].urb);
- for (i = 0; i < nr; i++)
- usb_kill_urb(acm->ru[i].urb);
- acm->control->needs_remote_wakeup = 0;
- usb_autopm_put_interface(acm->control);
- } else
- acm_tty_unregister(acm);
- }
+ tty_port_tty_set(&acm->port, NULL);
+ if (!acm->dev)
+ acm_tty_unregister(acm);
mutex_unlock(&open_mutex);
}
-static int acm_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
+static int acm_tty_write(struct tty_struct *tty,
+ const unsigned char *buf, int count)
{
struct acm *acm = tty->driver_data;
int stat;
return 0;
spin_lock_irqsave(&acm->write_lock, flags);
- if ((wbn = acm_wb_alloc(acm)) < 0) {
+ wbn = acm_wb_alloc(acm);
+ if (wbn < 0) {
spin_unlock_irqrestore(&acm->write_lock, flags);
return 0;
}
wb->len = count;
spin_unlock_irqrestore(&acm->write_lock, flags);
- if ((stat = acm_write_start(acm, wbn)) < 0)
+ stat = acm_write_start(acm, wbn);
+ if (stat < 0)
return stat;
return count;
}
return -EINVAL;
newctrl = acm->ctrlout;
- set = (set & TIOCM_DTR ? ACM_CTRL_DTR : 0) | (set & TIOCM_RTS ? ACM_CTRL_RTS : 0);
- clear = (clear & TIOCM_DTR ? ACM_CTRL_DTR : 0) | (clear & TIOCM_RTS ? ACM_CTRL_RTS : 0);
+ set = (set & TIOCM_DTR ? ACM_CTRL_DTR : 0) |
+ (set & TIOCM_RTS ? ACM_CTRL_RTS : 0);
+ clear = (clear & TIOCM_DTR ? ACM_CTRL_DTR : 0) |
+ (clear & TIOCM_RTS ? ACM_CTRL_RTS : 0);
newctrl = (newctrl & ~clear) | set;
return acm_set_control(acm, acm->ctrlout = newctrl);
}
-static int acm_tty_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg)
+static int acm_tty_ioctl(struct tty_struct *tty, struct file *file,
+ unsigned int cmd, unsigned long arg)
{
struct acm *acm = tty->driver_data;
5, 6, 7, 8
};
-static void acm_tty_set_termios(struct tty_struct *tty, struct ktermios *termios_old)
+static void acm_tty_set_termios(struct tty_struct *tty,
+ struct ktermios *termios_old)
{
struct acm *acm = tty->driver_data;
struct ktermios *termios = tty->termios;
if (!ACM_READY(acm))
return;
+ /* FIXME: Needs to support the tty_baud interface */
+ /* FIXME: Broken on sparc */
newline.dwDTERate = cpu_to_le32p(acm_tty_speed +
(termios->c_cflag & CBAUD & ~CBAUDEX) + (termios->c_cflag & CBAUDEX ? 15 : 0));
newline.bCharFormat = termios->c_cflag & CSTOPB ? 2 : 0;
newline.bParityType = termios->c_cflag & PARENB ?
- (termios->c_cflag & PARODD ? 1 : 2) + (termios->c_cflag & CMSPAR ? 2 : 0) : 0;
+ (termios->c_cflag & PARODD ? 1 : 2) +
+ (termios->c_cflag & CMSPAR ? 2 : 0) : 0;
newline.bDataBits = acm_tty_size[(termios->c_cflag & CSIZE) >> 4];
-
+ /* FIXME: Needs to clear unsupported bits in the termios */
acm->clocal = ((termios->c_cflag & CLOCAL) != 0);
if (!newline.dwDTERate) {
newline.dwDTERate = acm->line.dwDTERate;
newctrl &= ~ACM_CTRL_DTR;
- } else newctrl |= ACM_CTRL_DTR;
+ } else
+ newctrl |= ACM_CTRL_DTR;
if (newctrl != acm->ctrlout)
acm_set_control(acm, acm->ctrlout = newctrl);
struct acm_wb *wb;
struct usb_device *usb_dev = interface_to_usbdev(acm->control);
- for (wb = &acm->wb[0], i = 0; i < ACM_NW; i++, wb++) {
+ for (wb = &acm->wb[0], i = 0; i < ACM_NW; i++, wb++)
usb_buffer_free(usb_dev, acm->writesize, wb->buf, wb->dmah);
- }
}
static void acm_read_buffers_free(struct acm *acm)
int i, n = acm->rx_buflimit;
for (i = 0; i < n; i++)
- usb_buffer_free(usb_dev, acm->readsize, acm->rb[i].base, acm->rb[i].dma);
+ usb_buffer_free(usb_dev, acm->readsize,
+ acm->rb[i].base, acm->rb[i].dma);
}
/* Little helper: write buffers allocate */
return 0;
}
-static int acm_probe (struct usb_interface *intf,
- const struct usb_device_id *id)
+static int acm_probe(struct usb_interface *intf,
+ const struct usb_device_id *id)
{
struct usb_cdc_union_desc *union_header = NULL;
struct usb_cdc_country_functional_desc *cfd = NULL;
struct usb_device *usb_dev = interface_to_usbdev(intf);
struct acm *acm;
int minor;
- int ctrlsize,readsize;
+ int ctrlsize, readsize;
u8 *buf;
u8 ac_management_function = 0;
u8 call_management_function = 0;
control_interface = usb_ifnum_to_if(usb_dev, 0);
goto skip_normal_probe;
}
-
+
/* normal probing*/
if (!buffer) {
dev_err(&intf->dev, "Weird descriptor references\n");
}
if (!buflen) {
- if (intf->cur_altsetting->endpoint->extralen && intf->cur_altsetting->endpoint->extra) {
- dev_dbg(&intf->dev,"Seeking extra descriptors on endpoint\n");
+ if (intf->cur_altsetting->endpoint->extralen &&
+ intf->cur_altsetting->endpoint->extra) {
+ dev_dbg(&intf->dev,
+ "Seeking extra descriptors on endpoint\n");
buflen = intf->cur_altsetting->endpoint->extralen;
buffer = intf->cur_altsetting->endpoint->extra;
} else {
}
while (buflen > 0) {
- if (buffer [1] != USB_DT_CS_INTERFACE) {
+ if (buffer[1] != USB_DT_CS_INTERFACE) {
dev_err(&intf->dev, "skipping garbage\n");
goto next_desc;
}
- switch (buffer [2]) {
- case USB_CDC_UNION_TYPE: /* we've found it */
- if (union_header) {
- dev_err(&intf->dev, "More than one "
- "union descriptor, "
- "skipping ...\n");
- goto next_desc;
- }
- union_header = (struct usb_cdc_union_desc *)
- buffer;
- break;
- case USB_CDC_COUNTRY_TYPE: /* export through sysfs*/
- cfd = (struct usb_cdc_country_functional_desc *)buffer;
- break;
- case USB_CDC_HEADER_TYPE: /* maybe check version */
- break; /* for now we ignore it */
- case USB_CDC_ACM_TYPE:
- ac_management_function = buffer[3];
- break;
- case USB_CDC_CALL_MANAGEMENT_TYPE:
- call_management_function = buffer[3];
- call_interface_num = buffer[4];
- if ((call_management_function & 3) != 3)
- dev_err(&intf->dev, "This device "
- "cannot do calls on its own. "
- "It is no modem.\n");
- break;
- default:
- /* there are LOTS more CDC descriptors that
- * could legitimately be found here.
- */
- dev_dbg(&intf->dev, "Ignoring descriptor: "
- "type %02x, length %d\n",
- buffer[2], buffer[0]);
- break;
+ switch (buffer[2]) {
+ case USB_CDC_UNION_TYPE: /* we've found it */
+ if (union_header) {
+ dev_err(&intf->dev, "More than one "
+ "union descriptor, skipping ...\n");
+ goto next_desc;
}
+ union_header = (struct usb_cdc_union_desc *)buffer;
+ break;
+ case USB_CDC_COUNTRY_TYPE: /* export through sysfs*/
+ cfd = (struct usb_cdc_country_functional_desc *)buffer;
+ break;
+ case USB_CDC_HEADER_TYPE: /* maybe check version */
+ break; /* for now we ignore it */
+ case USB_CDC_ACM_TYPE:
+ ac_management_function = buffer[3];
+ break;
+ case USB_CDC_CALL_MANAGEMENT_TYPE:
+ call_management_function = buffer[3];
+ call_interface_num = buffer[4];
+ if ((call_management_function & 3) != 3)
+ dev_err(&intf->dev, "This device cannot do calls on its own. It is not a modem.\n");
+ break;
+ default:
+ /* there are LOTS more CDC descriptors that
+ * could legitimately be found here.
+ */
+ dev_dbg(&intf->dev, "Ignoring descriptor: "
+ "type %02x, length %d\n",
+ buffer[2], buffer[0]);
+ break;
+ }
next_desc:
buflen -= buffer[0];
buffer += buffer[0];
if (!union_header) {
if (call_interface_num > 0) {
- dev_dbg(&intf->dev,"No union descriptor, using call management descriptor\n");
+ dev_dbg(&intf->dev, "No union descriptor, using call management descriptor\n");
data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = call_interface_num));
control_interface = intf;
} else {
- dev_dbg(&intf->dev,"No union descriptor, giving up\n");
+ dev_dbg(&intf->dev,
+ "No union descriptor, giving up\n");
return -ENODEV;
}
} else {
control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0);
data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0));
if (!control_interface || !data_interface) {
- dev_dbg(&intf->dev,"no interfaces\n");
+ dev_dbg(&intf->dev, "no interfaces\n");
return -ENODEV;
}
}
-
+
if (data_interface_num != call_interface_num)
- dev_dbg(&intf->dev,"Separate call control interface. That is not fully supported.\n");
+ dev_dbg(&intf->dev, "Separate call control interface. That is not fully supported.\n");
skip_normal_probe:
/*workaround for switched interfaces */
- if (data_interface->cur_altsetting->desc.bInterfaceClass != CDC_DATA_INTERFACE_TYPE) {
- if (control_interface->cur_altsetting->desc.bInterfaceClass == CDC_DATA_INTERFACE_TYPE) {
+ if (data_interface->cur_altsetting->desc.bInterfaceClass
+ != CDC_DATA_INTERFACE_TYPE) {
+ if (control_interface->cur_altsetting->desc.bInterfaceClass
+ == CDC_DATA_INTERFACE_TYPE) {
struct usb_interface *t;
- dev_dbg(&intf->dev,"Your device has switched interfaces.\n");
-
+ dev_dbg(&intf->dev,
+ "Your device has switched interfaces.\n");
t = control_interface;
control_interface = data_interface;
data_interface = t;
/* Accept probe requests only for the control interface */
if (intf != control_interface)
return -ENODEV;
-
+
if (usb_interface_claimed(data_interface)) { /* valid in this context */
- dev_dbg(&intf->dev,"The data interface isn't available\n");
+ dev_dbg(&intf->dev, "The data interface isn't available\n");
return -EBUSY;
}
if (!usb_endpoint_dir_in(epread)) {
/* descriptors are swapped */
struct usb_endpoint_descriptor *t;
- dev_dbg(&intf->dev,"The data interface has switched endpoints\n");
-
+ dev_dbg(&intf->dev,
+ "The data interface has switched endpoints\n");
t = epread;
epread = epwrite;
epwrite = t;
return -ENODEV;
}
- if (!(acm = kzalloc(sizeof(struct acm), GFP_KERNEL))) {
+ acm = kzalloc(sizeof(struct acm), GFP_KERNEL);
+ if (acm == NULL) {
dev_dbg(&intf->dev, "out of memory (acm kzalloc)\n");
goto alloc_fail;
}
ctrlsize = le16_to_cpu(epctrl->wMaxPacketSize);
- readsize = le16_to_cpu(epread->wMaxPacketSize)* ( quirks == SINGLE_RX_URB ? 1 : 2);
+ readsize = le16_to_cpu(epread->wMaxPacketSize) *
+ (quirks == SINGLE_RX_URB ? 1 : 2);
acm->writesize = le16_to_cpu(epwrite->wMaxPacketSize) * 20;
acm->control = control_interface;
acm->data = data_interface;
spin_lock_init(&acm->read_lock);
mutex_init(&acm->mutex);
acm->rx_endpoint = usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress);
+ tty_port_init(&acm->port);
+ acm->port.ops = &acm_port_ops;
buf = usb_buffer_alloc(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
if (!buf) {
for (i = 0; i < num_rx_buf; i++) {
struct acm_ru *rcv = &(acm->ru[i]);
- if (!(rcv->urb = usb_alloc_urb(0, GFP_KERNEL))) {
- dev_dbg(&intf->dev, "out of memory (read urbs usb_alloc_urb)\n");
+ rcv->urb = usb_alloc_urb(0, GFP_KERNEL);
+ if (rcv->urb == NULL) {
+ dev_dbg(&intf->dev,
+ "out of memory (read urbs usb_alloc_urb)\n");
goto alloc_fail7;
}
rb->base = usb_buffer_alloc(acm->dev, readsize,
GFP_KERNEL, &rb->dma);
if (!rb->base) {
- dev_dbg(&intf->dev, "out of memory (read bufs usb_buffer_alloc)\n");
+ dev_dbg(&intf->dev,
+ "out of memory (read bufs usb_buffer_alloc)\n");
goto alloc_fail7;
}
}
- for(i = 0; i < ACM_NW; i++)
- {
+ for (i = 0; i < ACM_NW; i++) {
struct acm_wb *snd = &(acm->wb[i]);
- if (!(snd->urb = usb_alloc_urb(0, GFP_KERNEL))) {
- dev_dbg(&intf->dev, "out of memory (write urbs usb_alloc_urb)");
+ snd->urb = usb_alloc_urb(0, GFP_KERNEL);
+ if (snd->urb == NULL) {
+ dev_dbg(&intf->dev,
+ "out of memory (write urbs usb_alloc_urb)");
goto alloc_fail7;
}
- usb_fill_bulk_urb(snd->urb, usb_dev, usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress),
- NULL, acm->writesize, acm_write_bulk, snd);
+ usb_fill_bulk_urb(snd->urb, usb_dev,
+ usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress),
+ NULL, acm->writesize, acm_write_bulk, snd);
snd->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
snd->instance = acm;
}
- usb_set_intfdata (intf, acm);
+ usb_set_intfdata(intf, acm);
i = device_create_file(&intf->dev, &dev_attr_bmCapabilities);
if (i < 0)
if (!acm->country_codes)
goto skip_countries;
acm->country_code_size = cfd->bLength - 4;
- memcpy(acm->country_codes, (u8 *)&cfd->wCountyCode0, cfd->bLength - 4);
+ memcpy(acm->country_codes, (u8 *)&cfd->wCountyCode0,
+ cfd->bLength - 4);
acm->country_rel_date = cfd->iCountryCodeRelDate;
i = device_create_file(&intf->dev, &dev_attr_wCountryCodes);
goto skip_countries;
}
- i = device_create_file(&intf->dev, &dev_attr_iCountryCodeRelDate);
+ i = device_create_file(&intf->dev,
+ &dev_attr_iCountryCodeRelDate);
if (i < 0) {
kfree(acm->country_codes);
goto skip_countries;
}
skip_countries:
- usb_fill_int_urb(acm->ctrlurb, usb_dev, usb_rcvintpipe(usb_dev, epctrl->bEndpointAddress),
- acm->ctrl_buffer, ctrlsize, acm_ctrl_irq, acm, epctrl->bInterval);
+ usb_fill_int_urb(acm->ctrlurb, usb_dev,
+ usb_rcvintpipe(usb_dev, epctrl->bEndpointAddress),
+ acm->ctrl_buffer, ctrlsize, acm_ctrl_irq, acm,
+ epctrl->bInterval);
acm->ctrlurb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
acm->ctrlurb->transfer_dma = acm->ctrl_dma;
tasklet_disable(&acm->urb_task);
usb_kill_urb(acm->ctrlurb);
- for(i = 0; i < ACM_NW; i++)
+ for (i = 0; i < ACM_NW; i++)
usb_kill_urb(acm->wb[i].urb);
for (i = 0; i < acm->rx_buflimit; i++)
usb_kill_urb(acm->ru[i].urb);
{
struct acm *acm = usb_get_intfdata(intf);
struct usb_device *usb_dev = interface_to_usbdev(intf);
+ struct tty_struct *tty;
/* sibling interface is already cleaning up */
if (!acm)
return;
mutex_lock(&open_mutex);
- if (acm->country_codes){
+ if (acm->country_codes) {
device_remove_file(&acm->control->dev,
&dev_attr_wCountryCodes);
device_remove_file(&acm->control->dev,
stop_data_traffic(acm);
acm_write_buffers_free(acm);
- usb_buffer_free(usb_dev, acm->ctrlsize, acm->ctrl_buffer, acm->ctrl_dma);
+ usb_buffer_free(usb_dev, acm->ctrlsize, acm->ctrl_buffer,
+ acm->ctrl_dma);
acm_read_buffers_free(acm);
usb_driver_release_interface(&acm_driver, intf == acm->control ?
acm->data : acm->control);
- if (!acm->used) {
+ if (acm->port.count == 0) {
acm_tty_unregister(acm);
mutex_unlock(&open_mutex);
return;
}
mutex_unlock(&open_mutex);
-
- if (acm->tty)
- tty_hangup(acm->tty);
+ tty = tty_port_tty_get(&acm->port);
+ if (tty) {
+ tty_hangup(tty);
+ tty_kref_put(tty);
+ }
}
#ifdef CONFIG_PM
*/
mutex_lock(&acm->mutex);
- if (acm->used)
+ if (acm->port.count)
stop_data_traffic(acm);
mutex_unlock(&acm->mutex);
return 0;
mutex_lock(&acm->mutex);
- if (acm->used) {
+ if (acm->port.count) {
rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO);
if (rv < 0)
goto err_out;
{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
USB_CDC_ACM_PROTO_AT_GSM) },
{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
- USB_CDC_ACM_PROTO_AT_3G ) },
+ USB_CDC_ACM_PROTO_AT_3G) },
{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
USB_CDC_ACM_PROTO_AT_CDMA) },
{ }
};
-MODULE_DEVICE_TABLE (usb, acm_ids);
+MODULE_DEVICE_TABLE(usb, acm_ids);
static struct usb_driver acm_driver = {
.name = "cdc_acm",
static const struct tty_operations acm_ops = {
.open = acm_tty_open,
.close = acm_tty_close,
+ .hangup = acm_tty_hangup,
.write = acm_tty_write,
.write_room = acm_tty_write_room,
.ioctl = acm_tty_ioctl,
acm_tty_driver->subtype = SERIAL_TYPE_NORMAL,
acm_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV;
acm_tty_driver->init_termios = tty_std_termios;
- acm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL;
+ acm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD |
+ HUPCL | CLOCAL;
tty_set_operations(acm_tty_driver, &acm_ops);
retval = tty_register_driver(acm_tty_driver);
module_init(acm_init);
module_exit(acm_exit);
-MODULE_AUTHOR( DRIVER_AUTHOR );
-MODULE_DESCRIPTION( DRIVER_DESC );
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_LICENSE("GPL");
MODULE_ALIAS_CHARDEV_MAJOR(ACM_TTY_MAJOR);
struct usb_device *dev; /* the corresponding usb device */
struct usb_interface *control; /* control interface */
struct usb_interface *data; /* data interface */
- struct tty_struct *tty; /* the corresponding tty */
- struct urb *ctrlurb; /* urbs */
+ struct tty_port port; /* our tty port data */
+ struct urb *ctrlurb; /* urbs */
u8 *ctrl_buffer; /* buffers of urbs */
dma_addr_t ctrl_dma; /* dma handles of buffers */
u8 *country_codes; /* country codes from device */
unsigned int ctrlout; /* output control lines (DTR, RTS) */
unsigned int writesize; /* max packet size for the output bulk endpoint */
unsigned int readsize,ctrlsize; /* buffer sizes for freeing */
- unsigned int used; /* someone has this acm's device open */
unsigned int minor; /* acm minor number */
unsigned char throttle; /* throttled by tty layer */
unsigned char clocal; /* termios CLOCAL */
static void belkin_sa_shutdown(struct usb_serial *serial);
static int belkin_sa_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void belkin_sa_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void belkin_sa_close(struct usb_serial_port *port);
static void belkin_sa_read_int_callback(struct urb *urb);
static void belkin_sa_set_termios(struct tty_struct *tty,
struct usb_serial_port *port, struct ktermios * old);
} /* belkin_sa_open */
-static void belkin_sa_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void belkin_sa_close(struct usb_serial_port *port)
{
dbg("%s port %d", __func__, port->number);
return r;
}
-static void ch341_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp)
+static int ch341_carrier_raised(struct usb_serial_port *port)
+{
+ struct ch341_private *priv = usb_get_serial_port_data(port);
+ if (priv->line_status & CH341_BIT_DCD)
+ return 1;
+ return 0;
+}
+
+static void ch341_dtr_rts(struct usb_serial_port *port, int on)
{
struct ch341_private *priv = usb_get_serial_port_data(port);
unsigned long flags;
- unsigned int c_cflag;
+ dbg("%s - port %d", __func__, port->number);
+ /* drop DTR and RTS */
+ spin_lock_irqsave(&priv->lock, flags);
+ if (on)
+ priv->line_control |= CH341_BIT_RTS | CH341_BIT_DTR;
+ else
+ priv->line_control &= ~(CH341_BIT_RTS | CH341_BIT_DTR);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ ch341_set_handshake(port->serial->dev, priv->line_control);
+ wake_up_interruptible(&priv->delta_msr_wait);
+}
+
+static void ch341_close(struct usb_serial_port *port)
+{
dbg("%s - port %d", __func__, port->number);
/* shutdown our urbs */
usb_kill_urb(port->write_urb);
usb_kill_urb(port->read_urb);
usb_kill_urb(port->interrupt_in_urb);
-
- if (tty) {
- c_cflag = tty->termios->c_cflag;
- if (c_cflag & HUPCL) {
- /* drop DTR and RTS */
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_control = 0;
- spin_unlock_irqrestore(&priv->lock, flags);
- ch341_set_handshake(port->serial->dev, 0);
- }
- }
- wake_up_interruptible(&priv->delta_msr_wait);
}
dbg("ch341_open()");
priv->baud_rate = DEFAULT_BAUD_RATE;
- priv->line_control = CH341_BIT_RTS | CH341_BIT_DTR;
r = ch341_configure(serial->dev, priv);
if (r)
if (r) {
dev_err(&port->dev, "%s - failed submitting interrupt urb,"
" error %d\n", __func__, r);
- ch341_close(tty, port, NULL);
+ ch341_close(port);
return -EPROTO;
}
dbg("ch341_set_termios()");
- if (!tty || !tty->termios)
- return;
-
baud_rate = tty_get_baud_rate(tty);
priv->baud_rate = baud_rate;
.usb_driver = &ch341_driver,
.num_ports = 1,
.open = ch341_open,
+ .dtr_rts = ch341_dtr_rts,
+ .carrier_raised = ch341_carrier_raised,
.close = ch341_close,
.ioctl = ch341_ioctl,
.set_termios = ch341_set_termios,
kfree(tty);
}
}
-
+ /* So we know not to kill the hardware on a hangup on this
+ port. We have also bumped the use count by one so it won't go
+ idle */
port->console = 1;
retval = 0;
kfree(tty);
reset_open_count:
port->port.count = 0;
-goto out;
+ goto out;
}
static void usb_console_write(struct console *co,
/*
- * Silicon Laboratories CP2101/CP2102 USB to RS232 serial adaptor driver
+ * Silicon Laboratories CP210x USB to RS232 serial adaptor driver
*
* Copyright (C) 2005 Craig Shelley (craig@microtron.org.uk)
*
/*
* Version Information
*/
-#define DRIVER_VERSION "v0.08"
-#define DRIVER_DESC "Silicon Labs CP2101/CP2102 RS232 serial adaptor driver"
+#define DRIVER_VERSION "v0.09"
+#define DRIVER_DESC "Silicon Labs CP210x RS232 serial adaptor driver"
/*
* Function Prototypes
*/
-static int cp2101_open(struct tty_struct *, struct usb_serial_port *,
+static int cp210x_open(struct tty_struct *, struct usb_serial_port *,
struct file *);
-static void cp2101_cleanup(struct usb_serial_port *);
-static void cp2101_close(struct tty_struct *, struct usb_serial_port *,
- struct file*);
-static void cp2101_get_termios(struct tty_struct *,
+static void cp210x_cleanup(struct usb_serial_port *);
+static void cp210x_close(struct usb_serial_port *);
+static void cp210x_get_termios(struct tty_struct *,
struct usb_serial_port *port);
-static void cp2101_get_termios_port(struct usb_serial_port *port,
+static void cp210x_get_termios_port(struct usb_serial_port *port,
unsigned int *cflagp, unsigned int *baudp);
-static void cp2101_set_termios(struct tty_struct *, struct usb_serial_port *,
+static void cp210x_set_termios(struct tty_struct *, struct usb_serial_port *,
struct ktermios*);
-static int cp2101_tiocmget(struct tty_struct *, struct file *);
-static int cp2101_tiocmset(struct tty_struct *, struct file *,
+static int cp210x_tiocmget(struct tty_struct *, struct file *);
+static int cp210x_tiocmset(struct tty_struct *, struct file *,
unsigned int, unsigned int);
-static int cp2101_tiocmset_port(struct usb_serial_port *port, struct file *,
+static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *,
unsigned int, unsigned int);
-static void cp2101_break_ctl(struct tty_struct *, int);
-static int cp2101_startup(struct usb_serial *);
-static void cp2101_shutdown(struct usb_serial *);
+static void cp210x_break_ctl(struct tty_struct *, int);
+static int cp210x_startup(struct usb_serial *);
+static void cp210x_shutdown(struct usb_serial *);
static int debug;
static struct usb_device_id id_table [] = {
{ USB_DEVICE(0x0471, 0x066A) }, /* AKTAKOM ACE-1001 cable */
{ USB_DEVICE(0x0489, 0xE000) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */
+ { USB_DEVICE(0x0745, 0x1000) }, /* CipherLab USB CCD Barcode Scanner 1000 */
{ USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */
+ { USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */
{ USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */
{ USB_DEVICE(0x0FCF, 0x1004) }, /* Dynastream ANT2USB */
{ USB_DEVICE(0x0FCF, 0x1006) }, /* Dynastream ANT development board */
{ USB_DEVICE(0x10A6, 0xAA26) }, /* Knock-off DCU-11 cable */
{ USB_DEVICE(0x10AB, 0x10C5) }, /* Siemens MC60 Cable */
{ USB_DEVICE(0x10B5, 0xAC70) }, /* Nokia CA-42 USB */
+ { USB_DEVICE(0x10C4, 0x0F91) }, /* Vstabi */
{ USB_DEVICE(0x10C4, 0x800A) }, /* SPORTident BSM7-D-USB main station */
{ USB_DEVICE(0x10C4, 0x803B) }, /* Pololu USB-serial converter */
{ USB_DEVICE(0x10C4, 0x8053) }, /* Enfora EDG1228 */
{ USB_DEVICE(0x10C4, 0x81C8) }, /* Lipowsky Industrie Elektronik GmbH, Baby-JTAG */
{ USB_DEVICE(0x10C4, 0x81E2) }, /* Lipowsky Industrie Elektronik GmbH, Baby-LIN */
{ USB_DEVICE(0x10C4, 0x81E7) }, /* Aerocomm Radio */
+ { USB_DEVICE(0x10C4, 0x81F2) }, /* C1007 HF band RFID controller */
{ USB_DEVICE(0x10C4, 0x8218) }, /* Lipowsky Industrie Elektronik GmbH, HARP-1 */
{ USB_DEVICE(0x10C4, 0x822B) }, /* Modem EDGE(GSM) Comander 2 */
{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demostration module */
{ USB_DEVICE(0x10c4, 0x8293) }, /* Telegesys ETRX2USB */
+ { USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
{ USB_DEVICE(0x10C4, 0x83A8) }, /* Amber Wireless AMB2560 */
{ USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */
{ USB_DEVICE(0x10C4, 0xF003) }, /* Elan Digital Systems USBpulse100 */
{ USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */
{ USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */
+ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */
{ USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */
+ { USB_DEVICE(0x1555, 0x0004) }, /* Owen AC4 USB-RS485 Converter */
{ USB_DEVICE(0x166A, 0x0303) }, /* Clipsal 5500PCU C-Bus USB interface */
{ USB_DEVICE(0x16D6, 0x0001) }, /* Jablotron serial interface */
{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
MODULE_DEVICE_TABLE(usb, id_table);
-static struct usb_driver cp2101_driver = {
- .name = "cp2101",
+static struct usb_driver cp210x_driver = {
+ .name = "cp210x",
.probe = usb_serial_probe,
.disconnect = usb_serial_disconnect,
.id_table = id_table,
.no_dynamic_id = 1,
};
-static struct usb_serial_driver cp2101_device = {
+static struct usb_serial_driver cp210x_device = {
.driver = {
.owner = THIS_MODULE,
- .name = "cp2101",
+ .name = "cp210x",
},
- .usb_driver = &cp2101_driver,
+ .usb_driver = &cp210x_driver,
.id_table = id_table,
.num_ports = 1,
- .open = cp2101_open,
- .close = cp2101_close,
- .break_ctl = cp2101_break_ctl,
- .set_termios = cp2101_set_termios,
- .tiocmget = cp2101_tiocmget,
- .tiocmset = cp2101_tiocmset,
- .attach = cp2101_startup,
- .shutdown = cp2101_shutdown,
+ .open = cp210x_open,
+ .close = cp210x_close,
+ .break_ctl = cp210x_break_ctl,
+ .set_termios = cp210x_set_termios,
+ .tiocmget = cp210x_tiocmget,
+ .tiocmset = cp210x_tiocmset,
+ .attach = cp210x_startup,
+ .shutdown = cp210x_shutdown,
};
/* Config request types */
#define REQTYPE_HOST_TO_DEVICE 0x41
#define REQTYPE_DEVICE_TO_HOST 0xc1
-/* Config SET requests. To GET, add 1 to the request number */
-#define CP2101_UART 0x00 /* Enable / Disable */
-#define CP2101_BAUDRATE 0x01 /* (BAUD_RATE_GEN_FREQ / baudrate) */
-#define CP2101_BITS 0x03 /* 0x(0)(databits)(parity)(stopbits) */
-#define CP2101_BREAK 0x05 /* On / Off */
-#define CP2101_CONTROL 0x07 /* Flow control line states */
-#define CP2101_MODEMCTL 0x13 /* Modem controls */
-#define CP2101_CONFIG_6 0x19 /* 6 bytes of config data ??? */
-
-/* CP2101_UART */
+/* Config request codes */
+#define CP210X_IFC_ENABLE 0x00
+#define CP210X_SET_BAUDDIV 0x01
+#define CP210X_GET_BAUDDIV 0x02
+#define CP210X_SET_LINE_CTL 0x03
+#define CP210X_GET_LINE_CTL 0x04
+#define CP210X_SET_BREAK 0x05
+#define CP210X_IMM_CHAR 0x06
+#define CP210X_SET_MHS 0x07
+#define CP210X_GET_MDMSTS 0x08
+#define CP210X_SET_XON 0x09
+#define CP210X_SET_XOFF 0x0A
+#define CP210X_SET_EVENTMASK 0x0B
+#define CP210X_GET_EVENTMASK 0x0C
+#define CP210X_SET_CHAR 0x0D
+#define CP210X_GET_CHARS 0x0E
+#define CP210X_GET_PROPS 0x0F
+#define CP210X_GET_COMM_STATUS 0x10
+#define CP210X_RESET 0x11
+#define CP210X_PURGE 0x12
+#define CP210X_SET_FLOW 0x13
+#define CP210X_GET_FLOW 0x14
+#define CP210X_EMBED_EVENTS 0x15
+#define CP210X_GET_EVENTSTATE 0x16
+#define CP210X_SET_CHARS 0x19
+
+/* CP210X_IFC_ENABLE */
#define UART_ENABLE 0x0001
#define UART_DISABLE 0x0000
-/* CP2101_BAUDRATE */
+/* CP210X_(SET|GET)_BAUDDIV */
#define BAUD_RATE_GEN_FREQ 0x384000
-/* CP2101_BITS */
+/* CP210X_(SET|GET)_LINE_CTL */
#define BITS_DATA_MASK 0X0f00
#define BITS_DATA_5 0X0500
#define BITS_DATA_6 0X0600
#define BITS_STOP_1_5 0x0001
#define BITS_STOP_2 0x0002
-/* CP2101_BREAK */
+/* CP210X_SET_BREAK */
#define BREAK_ON 0x0000
#define BREAK_OFF 0x0001
-/* CP2101_CONTROL */
+/* CP210X_(SET_MHS|GET_MDMSTS) */
#define CONTROL_DTR 0x0001
#define CONTROL_RTS 0x0002
#define CONTROL_CTS 0x0010
#define CONTROL_WRITE_RTS 0x0200
/*
- * cp2101_get_config
- * Reads from the CP2101 configuration registers
+ * cp210x_get_config
+ * Reads from the CP210x configuration registers
* 'size' is specified in bytes.
* 'data' is a pointer to a pre-allocated array of integers large
* enough to hold 'size' bytes (with 4 bytes to each integer)
*/
-static int cp2101_get_config(struct usb_serial_port *port, u8 request,
+static int cp210x_get_config(struct usb_serial_port *port, u8 request,
unsigned int *data, int size)
{
struct usb_serial *serial = port->serial;
return -ENOMEM;
}
- /* For get requests, the request number must be incremented */
- request++;
-
/* Issue the request, attempting to read 'size' bytes */
result = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
request, REQTYPE_DEVICE_TO_HOST, 0x0000,
}
/*
- * cp2101_set_config
- * Writes to the CP2101 configuration registers
+ * cp210x_set_config
+ * Writes to the CP210x configuration registers
* Values less than 16 bits wide are sent directly
* 'size' is specified in bytes.
*/
-static int cp2101_set_config(struct usb_serial_port *port, u8 request,
+static int cp210x_set_config(struct usb_serial_port *port, u8 request,
unsigned int *data, int size)
{
struct usb_serial *serial = port->serial;
}
/*
- * cp2101_set_config_single
- * Convenience function for calling cp2101_set_config on single data values
+ * cp210x_set_config_single
+ * Convenience function for calling cp210x_set_config on single data values
* without requiring an integer pointer
*/
-static inline int cp2101_set_config_single(struct usb_serial_port *port,
+static inline int cp210x_set_config_single(struct usb_serial_port *port,
u8 request, unsigned int data)
{
- return cp2101_set_config(port, request, &data, 2);
+ return cp210x_set_config(port, request, &data, 2);
}
/*
- * cp2101_quantise_baudrate
+ * cp210x_quantise_baudrate
* Quantises the baud rate as per AN205 Table 1
*/
-static unsigned int cp2101_quantise_baudrate(unsigned int baud) {
+static unsigned int cp210x_quantise_baudrate(unsigned int baud) {
if (baud <= 56) baud = 0;
else if (baud <= 300) baud = 300;
else if (baud <= 600) baud = 600;
return baud;
}
-static int cp2101_open(struct tty_struct *tty, struct usb_serial_port *port,
+static int cp210x_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp)
{
struct usb_serial *serial = port->serial;
dbg("%s - port %d", __func__, port->number);
- if (cp2101_set_config_single(port, CP2101_UART, UART_ENABLE)) {
+ if (cp210x_set_config_single(port, CP210X_IFC_ENABLE, UART_ENABLE)) {
dev_err(&port->dev, "%s - Unable to enable UART\n",
__func__);
return -EPROTO;
}
/* Configure the termios structure */
- cp2101_get_termios(tty, port);
+ cp210x_get_termios(tty, port);
/* Set the DTR and RTS pins low */
- cp2101_tiocmset_port(tty ? (struct usb_serial_port *) tty->driver_data
+ cp210x_tiocmset_port(tty ? (struct usb_serial_port *) tty->driver_data
: port,
NULL, TIOCM_DTR | TIOCM_RTS, 0);
return 0;
}
-static void cp2101_cleanup(struct usb_serial_port *port)
+static void cp210x_cleanup(struct usb_serial_port *port)
{
struct usb_serial *serial = port->serial;
}
}
-static void cp2101_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp)
+static void cp210x_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
mutex_lock(&port->serial->disc_mutex);
if (!port->serial->disconnected)
- cp2101_set_config_single(port, CP2101_UART, UART_DISABLE);
+ cp210x_set_config_single(port, CP210X_IFC_ENABLE, UART_DISABLE);
mutex_unlock(&port->serial->disc_mutex);
}
/*
- * cp2101_get_termios
+ * cp210x_get_termios
* Reads the baud rate, data bits, parity, stop bits and flow control mode
* from the device, corrects any unsupported values, and configures the
* termios structure to reflect the state of the device
*/
-static void cp2101_get_termios(struct tty_struct *tty,
+static void cp210x_get_termios(struct tty_struct *tty,
struct usb_serial_port *port)
{
unsigned int baud;
if (tty) {
- cp2101_get_termios_port(tty->driver_data,
+ cp210x_get_termios_port(tty->driver_data,
&tty->termios->c_cflag, &baud);
tty_encode_baud_rate(tty, baud, baud);
}
else {
unsigned int cflag;
cflag = 0;
- cp2101_get_termios_port(port, &cflag, &baud);
+ cp210x_get_termios_port(port, &cflag, &baud);
}
}
/*
- * cp2101_get_termios_port
- * This is the heart of cp2101_get_termios which always uses a &usb_serial_port.
+ * cp210x_get_termios_port
+ * This is the heart of cp210x_get_termios which always uses a &usb_serial_port.
*/
-static void cp2101_get_termios_port(struct usb_serial_port *port,
+static void cp210x_get_termios_port(struct usb_serial_port *port,
unsigned int *cflagp, unsigned int *baudp)
{
unsigned int cflag, modem_ctl[4];
dbg("%s - port %d", __func__, port->number);
- cp2101_get_config(port, CP2101_BAUDRATE, &baud, 2);
+ cp210x_get_config(port, CP210X_GET_BAUDDIV, &baud, 2);
/* Convert to baudrate */
if (baud)
- baud = cp2101_quantise_baudrate((BAUD_RATE_GEN_FREQ + baud/2)/ baud);
+ baud = cp210x_quantise_baudrate((BAUD_RATE_GEN_FREQ + baud/2)/ baud);
dbg("%s - baud rate = %d", __func__, baud);
*baudp = baud;
cflag = *cflagp;
- cp2101_get_config(port, CP2101_BITS, &bits, 2);
+ cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
cflag &= ~CSIZE;
switch (bits & BITS_DATA_MASK) {
case BITS_DATA_5:
cflag |= CS8;
bits &= ~BITS_DATA_MASK;
bits |= BITS_DATA_8;
- cp2101_set_config(port, CP2101_BITS, &bits, 2);
+ cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
break;
default:
dbg("%s - Unknown number of data bits, using 8", __func__);
cflag |= CS8;
bits &= ~BITS_DATA_MASK;
bits |= BITS_DATA_8;
- cp2101_set_config(port, CP2101_BITS, &bits, 2);
+ cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
break;
}
__func__);
cflag &= ~PARENB;
bits &= ~BITS_PARITY_MASK;
- cp2101_set_config(port, CP2101_BITS, &bits, 2);
+ cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
break;
case BITS_PARITY_SPACE:
dbg("%s - parity = SPACE (not supported, disabling parity)",
__func__);
cflag &= ~PARENB;
bits &= ~BITS_PARITY_MASK;
- cp2101_set_config(port, CP2101_BITS, &bits, 2);
+ cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
break;
default:
dbg("%s - Unknown parity mode, disabling parity", __func__);
cflag &= ~PARENB;
bits &= ~BITS_PARITY_MASK;
- cp2101_set_config(port, CP2101_BITS, &bits, 2);
+ cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
break;
}
dbg("%s - stop bits = 1.5 (not supported, using 1 stop bit)",
__func__);
bits &= ~BITS_STOP_MASK;
- cp2101_set_config(port, CP2101_BITS, &bits, 2);
+ cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
break;
case BITS_STOP_2:
dbg("%s - stop bits = 2", __func__);
dbg("%s - Unknown number of stop bits, using 1 stop bit",
__func__);
bits &= ~BITS_STOP_MASK;
- cp2101_set_config(port, CP2101_BITS, &bits, 2);
+ cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
break;
}
- cp2101_get_config(port, CP2101_MODEMCTL, modem_ctl, 16);
+ cp210x_get_config(port, CP210X_GET_FLOW, modem_ctl, 16);
if (modem_ctl[0] & 0x0008) {
dbg("%s - flow control = CRTSCTS", __func__);
cflag |= CRTSCTS;
*cflagp = cflag;
}
-static void cp2101_set_termios(struct tty_struct *tty,
+static void cp210x_set_termios(struct tty_struct *tty,
struct usb_serial_port *port, struct ktermios *old_termios)
{
unsigned int cflag, old_cflag;
tty->termios->c_cflag &= ~CMSPAR;
cflag = tty->termios->c_cflag;
old_cflag = old_termios->c_cflag;
- baud = cp2101_quantise_baudrate(tty_get_baud_rate(tty));
+ baud = cp210x_quantise_baudrate(tty_get_baud_rate(tty));
/* If the baud rate is to be updated*/
if (baud != tty_termios_baud_rate(old_termios) && baud != 0) {
dbg("%s - Setting baud rate to %d baud", __func__,
baud);
- if (cp2101_set_config_single(port, CP2101_BAUDRATE,
+ if (cp210x_set_config_single(port, CP210X_SET_BAUDDIV,
((BAUD_RATE_GEN_FREQ + baud/2) / baud))) {
dbg("Baud rate requested not supported by device\n");
baud = tty_termios_baud_rate(old_termios);
/* If the number of data bits is to be updated */
if ((cflag & CSIZE) != (old_cflag & CSIZE)) {
- cp2101_get_config(port, CP2101_BITS, &bits, 2);
+ cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
bits &= ~BITS_DATA_MASK;
switch (cflag & CSIZE) {
case CS5:
dbg("%s - data bits = 9", __func__);
break;*/
default:
- dbg("cp2101 driver does not "
+ dbg("cp210x driver does not "
"support the number of bits requested,"
" using 8 bit mode\n");
bits |= BITS_DATA_8;
break;
}
- if (cp2101_set_config(port, CP2101_BITS, &bits, 2))
+ if (cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2))
dbg("Number of data bits requested "
"not supported by device\n");
}
if ((cflag & (PARENB|PARODD)) != (old_cflag & (PARENB|PARODD))) {
- cp2101_get_config(port, CP2101_BITS, &bits, 2);
+ cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
bits &= ~BITS_PARITY_MASK;
if (cflag & PARENB) {
if (cflag & PARODD) {
dbg("%s - parity = EVEN", __func__);
}
}
- if (cp2101_set_config(port, CP2101_BITS, &bits, 2))
+ if (cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2))
dbg("Parity mode not supported "
"by device\n");
}
if ((cflag & CSTOPB) != (old_cflag & CSTOPB)) {
- cp2101_get_config(port, CP2101_BITS, &bits, 2);
+ cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
bits &= ~BITS_STOP_MASK;
if (cflag & CSTOPB) {
bits |= BITS_STOP_2;
bits |= BITS_STOP_1;
dbg("%s - stop bits = 1", __func__);
}
- if (cp2101_set_config(port, CP2101_BITS, &bits, 2))
+ if (cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2))
dbg("Number of stop bits requested "
"not supported by device\n");
}
if ((cflag & CRTSCTS) != (old_cflag & CRTSCTS)) {
- cp2101_get_config(port, CP2101_MODEMCTL, modem_ctl, 16);
+ cp210x_get_config(port, CP210X_GET_FLOW, modem_ctl, 16);
dbg("%s - read modem controls = 0x%.4x 0x%.4x 0x%.4x 0x%.4x",
__func__, modem_ctl[0], modem_ctl[1],
modem_ctl[2], modem_ctl[3]);
dbg("%s - write modem controls = 0x%.4x 0x%.4x 0x%.4x 0x%.4x",
__func__, modem_ctl[0], modem_ctl[1],
modem_ctl[2], modem_ctl[3]);
- cp2101_set_config(port, CP2101_MODEMCTL, modem_ctl, 16);
+ cp210x_set_config(port, CP210X_SET_FLOW, modem_ctl, 16);
}
}
-static int cp2101_tiocmset (struct tty_struct *tty, struct file *file,
+static int cp210x_tiocmset (struct tty_struct *tty, struct file *file,
unsigned int set, unsigned int clear)
{
struct usb_serial_port *port = tty->driver_data;
- return cp2101_tiocmset_port(port, file, set, clear);
+ return cp210x_tiocmset_port(port, file, set, clear);
}
-static int cp2101_tiocmset_port(struct usb_serial_port *port, struct file *file,
+static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *file,
unsigned int set, unsigned int clear)
{
unsigned int control = 0;
dbg("%s - control = 0x%.4x", __func__, control);
- return cp2101_set_config(port, CP2101_CONTROL, &control, 2);
+ return cp210x_set_config(port, CP210X_SET_MHS, &control, 2);
}
-static int cp2101_tiocmget (struct tty_struct *tty, struct file *file)
+static int cp210x_tiocmget (struct tty_struct *tty, struct file *file)
{
struct usb_serial_port *port = tty->driver_data;
unsigned int control;
dbg("%s - port %d", __func__, port->number);
- cp2101_get_config(port, CP2101_CONTROL, &control, 1);
+ cp210x_get_config(port, CP210X_GET_MDMSTS, &control, 1);
result = ((control & CONTROL_DTR) ? TIOCM_DTR : 0)
|((control & CONTROL_RTS) ? TIOCM_RTS : 0)
return result;
}
-static void cp2101_break_ctl (struct tty_struct *tty, int break_state)
+static void cp210x_break_ctl (struct tty_struct *tty, int break_state)
{
struct usb_serial_port *port = tty->driver_data;
unsigned int state;
state = BREAK_ON;
dbg("%s - turning break %s", __func__,
state == BREAK_OFF ? "off" : "on");
- cp2101_set_config(port, CP2101_BREAK, &state, 2);
+ cp210x_set_config(port, CP210X_SET_BREAK, &state, 2);
}
-static int cp2101_startup(struct usb_serial *serial)
+static int cp210x_startup(struct usb_serial *serial)
{
- /* CP2101 buffers behave strangely unless device is reset */
+ /* cp210x buffers behave strangely unless device is reset */
usb_reset_device(serial->dev);
return 0;
}
-static void cp2101_shutdown(struct usb_serial *serial)
+static void cp210x_shutdown(struct usb_serial *serial)
{
int i;
/* Stop reads and writes on all ports */
for (i = 0; i < serial->num_ports; ++i)
- cp2101_cleanup(serial->port[i]);
+ cp210x_cleanup(serial->port[i]);
}
-static int __init cp2101_init(void)
+static int __init cp210x_init(void)
{
int retval;
- retval = usb_serial_register(&cp2101_device);
+ retval = usb_serial_register(&cp210x_device);
if (retval)
return retval; /* Failed to register */
- retval = usb_register(&cp2101_driver);
+ retval = usb_register(&cp210x_driver);
if (retval) {
/* Failed to register */
- usb_serial_deregister(&cp2101_device);
+ usb_serial_deregister(&cp210x_device);
return retval;
}
return 0;
}
-static void __exit cp2101_exit(void)
+static void __exit cp210x_exit(void)
{
- usb_deregister(&cp2101_driver);
- usb_serial_deregister(&cp2101_device);
+ usb_deregister(&cp210x_driver);
+ usb_serial_deregister(&cp210x_device);
}
-module_init(cp2101_init);
-module_exit(cp2101_exit);
+module_init(cp210x_init);
+module_exit(cp210x_exit);
MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_VERSION(DRIVER_VERSION);
static void cyberjack_shutdown(struct usb_serial *serial);
static int cyberjack_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void cyberjack_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void cyberjack_close(struct usb_serial_port *port);
static int cyberjack_write(struct tty_struct *tty,
struct usb_serial_port *port, const unsigned char *buf, int count);
static int cyberjack_write_room(struct tty_struct *tty);
return result;
}
-static void cyberjack_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void cyberjack_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
static void cypress_shutdown(struct usb_serial *serial);
static int cypress_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void cypress_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void cypress_close(struct usb_serial_port *port);
+static void cypress_dtr_rts(struct usb_serial_port *port, int on);
static int cypress_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf, int count);
static void cypress_send(struct usb_serial_port *port);
.shutdown = cypress_shutdown,
.open = cypress_open,
.close = cypress_close,
+ .dtr_rts = cypress_dtr_rts,
.write = cypress_write,
.write_room = cypress_write_room,
.ioctl = cypress_ioctl,
.shutdown = cypress_shutdown,
.open = cypress_open,
.close = cypress_close,
+ .dtr_rts = cypress_dtr_rts,
.write = cypress_write,
.write_room = cypress_write_room,
.ioctl = cypress_ioctl,
.shutdown = cypress_shutdown,
.open = cypress_open,
.close = cypress_close,
+ .dtr_rts = cypress_dtr_rts,
.write = cypress_write,
.write_room = cypress_write_room,
.ioctl = cypress_ioctl,
priv->rx_flags = 0;
spin_unlock_irqrestore(&priv->lock, flags);
- /* raise both lines and set termios */
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_control = CONTROL_DTR | CONTROL_RTS;
- priv->cmd_ctrl = 1;
- spin_unlock_irqrestore(&priv->lock, flags);
+ /* Set termios */
result = cypress_write(tty, port, NULL, 0);
if (result) {
__func__, result);
cypress_set_dead(port);
}
-
+ port->port.drain_delay = 256;
return result;
} /* cypress_open */
+static void cypress_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct cypress_private *priv = usb_get_serial_port_data(port);
+ /* drop dtr and rts */
+ priv = usb_get_serial_port_data(port);
+ spin_lock_irq(&priv->lock);
+ if (on == 0)
+ priv->line_control = 0;
+ else
+ priv->line_control = CONTROL_DTR | CONTROL_RTS;
+ priv->cmd_ctrl = 1;
+ spin_unlock_irq(&priv->lock);
+ cypress_write(NULL, port, NULL, 0);
+}
-static void cypress_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void cypress_close(struct usb_serial_port *port)
{
struct cypress_private *priv = usb_get_serial_port_data(port);
- unsigned int c_cflag;
- int bps;
- long timeout;
- wait_queue_t wait;
dbg("%s - port %d", __func__, port->number);
- /* wait for data to drain from buffer */
- spin_lock_irq(&priv->lock);
- timeout = CYPRESS_CLOSING_WAIT;
- init_waitqueue_entry(&wait, current);
- add_wait_queue(&tty->write_wait, &wait);
- for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (cypress_buf_data_avail(priv->buf) == 0
- || timeout == 0 || signal_pending(current)
- /* without mutex, allowed due to harmless failure mode */
- || port->serial->disconnected)
- break;
- spin_unlock_irq(&priv->lock);
- timeout = schedule_timeout(timeout);
- spin_lock_irq(&priv->lock);
- }
- set_current_state(TASK_RUNNING);
- remove_wait_queue(&tty->write_wait, &wait);
- /* clear out any remaining data in the buffer */
- cypress_buf_clear(priv->buf);
- spin_unlock_irq(&priv->lock);
-
/* writing is potentially harmful, lock must be taken */
mutex_lock(&port->serial->disc_mutex);
if (port->serial->disconnected) {
mutex_unlock(&port->serial->disc_mutex);
return;
}
- /* wait for characters to drain from device */
- if (tty) {
- bps = tty_get_baud_rate(tty);
- if (bps > 1200)
- timeout = max((HZ * 2560) / bps, HZ / 10);
- else
- timeout = 2 * HZ;
- schedule_timeout_interruptible(timeout);
- }
-
+ cypress_buf_clear(priv->buf);
dbg("%s - stopping urbs", __func__);
usb_kill_urb(port->interrupt_in_urb);
usb_kill_urb(port->interrupt_out_urb);
- if (tty) {
- c_cflag = tty->termios->c_cflag;
- if (c_cflag & HUPCL) {
- /* drop dtr and rts */
- priv = usb_get_serial_port_data(port);
- spin_lock_irq(&priv->lock);
- priv->line_control = 0;
- priv->cmd_ctrl = 1;
- spin_unlock_irq(&priv->lock);
- cypress_write(tty, port, NULL, 0);
- }
- }
if (stats)
dev_info(&port->dev, "Statistics: %d Bytes In | %d Bytes Out | %d Commands Issued\n",
int dp_throttled;
int dp_throttle_restart;
wait_queue_head_t dp_flush_wait;
- int dp_in_close; /* close in progress */
wait_queue_head_t dp_close_wait; /* wait queue for close */
struct work_struct dp_wakeup_work;
struct usb_serial_port *dp_port;
static int digi_chars_in_buffer(struct tty_struct *tty);
static int digi_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp);
-static void digi_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp);
+static void digi_close(struct usb_serial_port *port);
+static int digi_carrier_raised(struct usb_serial_port *port);
+static void digi_dtr_rts(struct usb_serial_port *port, int on);
static int digi_startup_device(struct usb_serial *serial);
static int digi_startup(struct usb_serial *serial);
static void digi_shutdown(struct usb_serial *serial);
.num_ports = 3,
.open = digi_open,
.close = digi_close,
+ .dtr_rts = digi_dtr_rts,
+ .carrier_raised = digi_carrier_raised,
.write = digi_write,
.write_room = digi_write_room,
.write_bulk_callback = digi_write_bulk_callback,
}
+static void digi_dtr_rts(struct usb_serial_port *port, int on)
+{
+ /* Adjust DTR and RTS */
+ digi_set_modem_signals(port, on * (TIOCM_DTR|TIOCM_RTS), 1);
+}
+
+static int digi_carrier_raised(struct usb_serial_port *port)
+{
+ struct digi_port *priv = usb_get_serial_port_data(port);
+ if (priv->dp_modem_signals & TIOCM_CD)
+ return 1;
+ return 0;
+}
static int digi_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp)
unsigned char buf[32];
struct digi_port *priv = usb_get_serial_port_data(port);
struct ktermios not_termios;
- unsigned long flags = 0;
dbg("digi_open: TOP: port=%d, open_count=%d",
priv->dp_port_num, port->port.count);
if (digi_startup_device(port->serial) != 0)
return -ENXIO;
- spin_lock_irqsave(&priv->dp_port_lock, flags);
-
- /* don't wait on a close in progress for non-blocking opens */
- if (priv->dp_in_close && (filp->f_flags&(O_NDELAY|O_NONBLOCK)) == 0) {
- spin_unlock_irqrestore(&priv->dp_port_lock, flags);
- return -EAGAIN;
- }
-
- /* wait for a close in progress to finish */
- while (priv->dp_in_close) {
- cond_wait_interruptible_timeout_irqrestore(
- &priv->dp_close_wait, DIGI_RETRY_TIMEOUT,
- &priv->dp_port_lock, flags);
- if (signal_pending(current))
- return -EINTR;
- spin_lock_irqsave(&priv->dp_port_lock, flags);
- }
-
- spin_unlock_irqrestore(&priv->dp_port_lock, flags);
-
/* read modem signals automatically whenever they change */
buf[0] = DIGI_CMD_READ_INPUT_SIGNALS;
buf[1] = priv->dp_port_num;
not_termios.c_iflag = ~tty->termios->c_iflag;
digi_set_termios(tty, port, ¬_termios);
}
-
- /* set DTR and RTS */
- digi_set_modem_signals(port, TIOCM_DTR|TIOCM_RTS, 1);
-
return 0;
}
-static void digi_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp)
+static void digi_close(struct usb_serial_port *port)
{
DEFINE_WAIT(wait);
int ret;
if (port->serial->disconnected)
goto exit;
- /* do cleanup only after final close on this port */
- spin_lock_irq(&priv->dp_port_lock);
- priv->dp_in_close = 1;
- spin_unlock_irq(&priv->dp_port_lock);
-
- /* tell line discipline to process only XON/XOFF */
- tty->closing = 1;
-
- /* wait for output to drain */
- if ((filp->f_flags&(O_NDELAY|O_NONBLOCK)) == 0)
- tty_wait_until_sent(tty, DIGI_CLOSE_TIMEOUT);
-
- /* flush driver and line discipline buffers */
- tty_driver_flush_buffer(tty);
- tty_ldisc_flush(tty);
-
if (port->serial->dev) {
- /* wait for transmit idle */
- if ((filp->f_flags&(O_NDELAY|O_NONBLOCK)) == 0)
- digi_transmit_idle(port, DIGI_CLOSE_TIMEOUT);
- /* drop DTR and RTS */
- digi_set_modem_signals(port, 0, 0);
+ /* FIXME: Transmit idle belongs in the wait_unti_sent path */
+ digi_transmit_idle(port, DIGI_CLOSE_TIMEOUT);
/* disable input flow control */
buf[0] = DIGI_CMD_SET_INPUT_FLOW_CONTROL;
/* shutdown any outstanding bulk writes */
usb_kill_urb(port->write_urb);
}
- tty->closing = 0;
exit:
spin_lock_irq(&priv->dp_port_lock);
priv->dp_write_urb_in_use = 0;
- priv->dp_in_close = 0;
wake_up_interruptible(&priv->dp_close_wait);
spin_unlock_irq(&priv->dp_port_lock);
mutex_unlock(&port->serial->disc_mutex);
priv->dp_throttled = 0;
priv->dp_throttle_restart = 0;
init_waitqueue_head(&priv->dp_flush_wait);
- priv->dp_in_close = 0;
init_waitqueue_head(&priv->dp_close_wait);
INIT_WORK(&priv->dp_wakeup_work, digi_wakeup_write_lock);
priv->dp_port = serial->port[i];
/* function prototypes for an empeg-car player */
static int empeg_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp);
-static void empeg_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp);
+static void empeg_close(struct usb_serial_port *port);
static int empeg_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf,
int count);
}
-static void empeg_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp)
+static void empeg_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
int force_rtscts; /* if non-zero, force RTS-CTS to always
be enabled */
+ unsigned int latency; /* latency setting in use */
spinlock_t tx_lock; /* spinlock for transmit state */
unsigned long tx_bytes;
unsigned long tx_outstanding_bytes;
static int ftdi_sio_port_remove(struct usb_serial_port *port);
static int ftdi_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void ftdi_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void ftdi_close(struct usb_serial_port *port);
+static void ftdi_dtr_rts(struct usb_serial_port *port, int on);
static int ftdi_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf, int count);
static int ftdi_write_room(struct tty_struct *tty);
.port_remove = ftdi_sio_port_remove,
.open = ftdi_open,
.close = ftdi_close,
+ .dtr_rts = ftdi_dtr_rts,
.throttle = ftdi_throttle,
.unthrottle = ftdi_unthrottle,
.write = ftdi_write,
return rv;
}
+static int write_latency_timer(struct usb_serial_port *port)
+{
+ struct ftdi_private *priv = usb_get_serial_port_data(port);
+ struct usb_device *udev = port->serial->dev;
+ char buf[1];
+ int rv = 0;
+ int l = priv->latency;
+
+ if (priv->flags & ASYNC_LOW_LATENCY)
+ l = 1;
+
+ dbg("%s: setting latency timer = %i", __func__, l);
+
+ rv = usb_control_msg(udev,
+ usb_sndctrlpipe(udev, 0),
+ FTDI_SIO_SET_LATENCY_TIMER_REQUEST,
+ FTDI_SIO_SET_LATENCY_TIMER_REQUEST_TYPE,
+ l, priv->interface,
+ buf, 0, WDR_TIMEOUT);
+
+ if (rv < 0)
+ dev_err(&port->dev, "Unable to write latency timer: %i\n", rv);
+ return rv;
+}
+
+static int read_latency_timer(struct usb_serial_port *port)
+{
+ struct ftdi_private *priv = usb_get_serial_port_data(port);
+ struct usb_device *udev = port->serial->dev;
+ unsigned short latency = 0;
+ int rv = 0;
+
+ dbg("%s", __func__);
+
+ rv = usb_control_msg(udev,
+ usb_rcvctrlpipe(udev, 0),
+ FTDI_SIO_GET_LATENCY_TIMER_REQUEST,
+ FTDI_SIO_GET_LATENCY_TIMER_REQUEST_TYPE,
+ 0, priv->interface,
+ (char *) &latency, 1, WDR_TIMEOUT);
+
+ if (rv < 0) {
+ dev_err(&port->dev, "Unable to read latency timer: %i\n", rv);
+ return -EIO;
+ }
+ return latency;
+}
static int get_serial_info(struct usb_serial_port *port,
struct serial_struct __user *retinfo)
priv->custom_divisor = new_serial.custom_divisor;
tty->low_latency = (priv->flags & ASYNC_LOW_LATENCY) ? 1 : 0;
+ write_latency_timer(port);
check_and_exit:
if ((old_priv.flags & ASYNC_SPD_MASK) !=
{
struct usb_serial_port *port = to_usb_serial_port(dev);
struct ftdi_private *priv = usb_get_serial_port_data(port);
- struct usb_device *udev = port->serial->dev;
- unsigned short latency = 0;
- int rv = 0;
-
-
- dbg("%s", __func__);
-
- rv = usb_control_msg(udev,
- usb_rcvctrlpipe(udev, 0),
- FTDI_SIO_GET_LATENCY_TIMER_REQUEST,
- FTDI_SIO_GET_LATENCY_TIMER_REQUEST_TYPE,
- 0, priv->interface,
- (char *) &latency, 1, WDR_TIMEOUT);
-
- if (rv < 0) {
- dev_err(dev, "Unable to read latency timer: %i\n", rv);
- return -EIO;
- }
- return sprintf(buf, "%i\n", latency);
+ if (priv->flags & ASYNC_LOW_LATENCY)
+ return sprintf(buf, "1\n");
+ else
+ return sprintf(buf, "%i\n", priv->latency);
}
+
/* Write a new value of the latency timer, in units of milliseconds. */
static ssize_t store_latency_timer(struct device *dev,
struct device_attribute *attr, const char *valbuf,
{
struct usb_serial_port *port = to_usb_serial_port(dev);
struct ftdi_private *priv = usb_get_serial_port_data(port);
- struct usb_device *udev = port->serial->dev;
- char buf[1];
int v = simple_strtoul(valbuf, NULL, 10);
int rv = 0;
- dbg("%s: setting latency timer = %i", __func__, v);
-
- rv = usb_control_msg(udev,
- usb_sndctrlpipe(udev, 0),
- FTDI_SIO_SET_LATENCY_TIMER_REQUEST,
- FTDI_SIO_SET_LATENCY_TIMER_REQUEST_TYPE,
- v, priv->interface,
- buf, 0, WDR_TIMEOUT);
-
- if (rv < 0) {
- dev_err(dev, "Unable to write latency timer: %i\n", rv);
+ priv->latency = v;
+ rv = write_latency_timer(port);
+ if (rv < 0)
return -EIO;
- }
-
return count;
}
usb_set_serial_port_data(port, priv);
ftdi_determine_type(port);
+ read_latency_timer(port);
create_sysfs_attrs(port);
return 0;
}
if (tty)
tty->low_latency = (priv->flags & ASYNC_LOW_LATENCY) ? 1 : 0;
+ write_latency_timer(port);
+
/* No error checking for this (will get errors later anyway) */
/* See ftdi_sio.h for description of what is reset */
usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
if (tty)
ftdi_set_termios(tty, port, tty->termios);
- /* FIXME: Flow control might be enabled, so it should be checked -
- we have no control of defaults! */
- /* Turn on RTS and DTR since we are not flow controlling by default */
- set_mctrl(port, TIOCM_DTR | TIOCM_RTS);
-
/* Not throttled */
spin_lock_irqsave(&priv->rx_lock, flags);
priv->rx_flags &= ~(THROTTLED | ACTUALLY_THROTTLED);
} /* ftdi_open */
+static void ftdi_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct ftdi_private *priv = usb_get_serial_port_data(port);
+ char buf[1];
+
+ mutex_lock(&port->serial->disc_mutex);
+ if (!port->serial->disconnected) {
+ /* Disable flow control */
+ if (!on && usb_control_msg(port->serial->dev,
+ usb_sndctrlpipe(port->serial->dev, 0),
+ FTDI_SIO_SET_FLOW_CTRL_REQUEST,
+ FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
+ 0, priv->interface, buf, 0,
+ WDR_TIMEOUT) < 0) {
+ dev_err(&port->dev, "error from flowcontrol urb\n");
+ }
+ /* drop RTS and DTR */
+ if (on)
+ set_mctrl(port, TIOCM_DTR | TIOCM_RTS);
+ else
+ clear_mctrl(port, TIOCM_DTR | TIOCM_RTS);
+ }
+ mutex_unlock(&port->serial->disc_mutex);
+}
/*
* usbserial:__serial_close only calls ftdi_close if the point is open
*
*/
-static void ftdi_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void ftdi_close(struct usb_serial_port *port)
{ /* ftdi_close */
- unsigned int c_cflag = tty->termios->c_cflag;
struct ftdi_private *priv = usb_get_serial_port_data(port);
- char buf[1];
dbg("%s", __func__);
- mutex_lock(&port->serial->disc_mutex);
- if (c_cflag & HUPCL && !port->serial->disconnected) {
- /* Disable flow control */
- if (usb_control_msg(port->serial->dev,
- usb_sndctrlpipe(port->serial->dev, 0),
- FTDI_SIO_SET_FLOW_CTRL_REQUEST,
- FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
- 0, priv->interface, buf, 0,
- WDR_TIMEOUT) < 0) {
- dev_err(&port->dev, "error from flowcontrol urb\n");
- }
-
- /* drop RTS and DTR */
- clear_mctrl(port, TIOCM_DTR | TIOCM_RTS);
- } /* Note change no line if hupcl is off */
- mutex_unlock(&port->serial->disc_mutex);
/* cancel any scheduled reading */
cancel_delayed_work_sync(&priv->rx_work);
}
-static void garmin_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void garmin_close(struct usb_serial_port *port)
{
struct usb_serial *serial = port->serial;
struct garmin_data *garmin_data_p = usb_get_serial_port_data(port);
}
EXPORT_SYMBOL_GPL(usb_serial_generic_resume);
-void usb_serial_generic_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+void usb_serial_generic_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
generic_cleanup(port);
/* function prototypes for the usbserial callbacks */
static int edge_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp);
-static void edge_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp);
+static void edge_close(struct usb_serial_port *port);
static int edge_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf, int count);
static int edge_write_room(struct tty_struct *tty);
if (!edge_port->txfifo.fifo) {
dbg("%s - no memory", __func__);
- edge_close(tty, port, filp);
+ edge_close(port);
return -ENOMEM;
}
if (!edge_port->write_urb) {
dbg("%s - no memory", __func__);
- edge_close(tty, port, filp);
+ edge_close(port);
return -ENOMEM;
}
* edge_close
* this function is called by the tty driver when a port is closed
*****************************************************************************/
-static void edge_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void edge_close(struct usb_serial_port *port)
{
struct edgeport_serial *edge_serial;
struct edgeport_port *edge_port;
return status;
}
-static void edge_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void edge_close(struct usb_serial_port *port)
{
struct edgeport_serial *edge_serial;
struct edgeport_port *edge_port;
/* Function prototypes for an ipaq */
static int ipaq_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void ipaq_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void ipaq_close(struct usb_serial_port *port);
static int ipaq_calc_num_ports(struct usb_serial *serial);
static int ipaq_startup(struct usb_serial *serial);
static void ipaq_shutdown(struct usb_serial *serial);
}
-static void ipaq_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void ipaq_close(struct usb_serial_port *port)
{
struct ipaq_private *priv = usb_get_serial_port_data(port);
return 0;
}
-static void ipw_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void ipw_dtr_rts(struct usb_serial_port *port, int on)
{
struct usb_device *dev = port->serial->dev;
int result;
- if (tty_hung_up_p(filp)) {
- dbg("%s: tty_hung_up_p ...", __func__);
- return;
- }
-
/*--1: drop the dtr */
dbg("%s:dropping dtr", __func__);
result = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
IPW_SIO_SET_PIN,
USB_TYPE_VENDOR | USB_RECIP_INTERFACE | USB_DIR_OUT,
- IPW_PIN_CLRDTR,
+ on ? IPW_PIN_SETDTR : IPW_PIN_CLRDTR,
0,
NULL,
0,
result = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
IPW_SIO_SET_PIN, USB_TYPE_VENDOR |
USB_RECIP_INTERFACE | USB_DIR_OUT,
- IPW_PIN_CLRRTS,
+ on ? IPW_PIN_SETRTS : IPW_PIN_CLRRTS,
0,
NULL,
0,
if (result < 0)
dev_err(&port->dev,
"dropping rts failed (error = %d)\n", result);
+}
+static void ipw_close(struct usb_serial_port *port)
+{
+ struct usb_device *dev = port->serial->dev;
+ int result;
/*--3: purge */
dbg("%s:sending purge", __func__);
.num_ports = 1,
.open = ipw_open,
.close = ipw_close,
+ .dtr_rts = ipw_dtr_rts,
.port_probe = ipw_probe,
.port_remove = ipw_disconnect,
.write = ipw_write,
static int ir_startup (struct usb_serial *serial);
static int ir_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filep);
-static void ir_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filep);
+static void ir_close(struct usb_serial_port *port);
static int ir_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf, int count);
static void ir_write_bulk_callback (struct urb *urb);
return result;
}
-static void ir_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file * filp)
+static void ir_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
/*
* Version Information
*/
-#define DRIVER_VERSION "v0.5"
+#define DRIVER_VERSION "v0.10"
#define DRIVER_DESC "Infinity USB Unlimited Phoenix driver"
static struct usb_device_id id_table[] = {
struct iuu_private {
spinlock_t lock; /* store irq state */
wait_queue_head_t delta_msr_wait;
- u8 line_control;
u8 line_status;
u8 termios_initialized;
int tiostatus; /* store IUART SIGNAL for tiocmget call */
unsigned long flags;
int result;
int i;
+ int buf_len;
char *buf_ptr = port->write_urb->transfer_buffer;
dbg("%s - enter", __func__);
+ spin_lock_irqsave(&priv->lock, flags);
*buf_ptr++ = IUU_UART_ESC;
*buf_ptr++ = IUU_UART_TX;
*buf_ptr++ = priv->writelen;
- memcpy(buf_ptr, priv->writebuf,
- priv->writelen);
+ memcpy(buf_ptr, priv->writebuf, priv->writelen);
+ buf_len = priv->writelen;
+ priv->writelen = 0;
+ spin_unlock_irqrestore(&priv->lock, flags);
if (debug == 1) {
- for (i = 0; i < priv->writelen; i++)
+ for (i = 0; i < buf_len; i++)
sprintf(priv->dbgbuf + i*2 ,
"%02X", priv->writebuf[i]);
- priv->dbgbuf[priv->writelen+i*2] = 0;
+ priv->dbgbuf[buf_len+i*2] = 0;
dbg("%s - writing %i chars : %s", __func__,
- priv->writelen, priv->dbgbuf);
+ buf_len, priv->dbgbuf);
}
usb_fill_bulk_urb(port->write_urb, port->serial->dev,
usb_sndbulkpipe(port->serial->dev,
port->bulk_out_endpointAddress),
- port->write_urb->transfer_buffer, priv->writelen + 3,
+ port->write_urb->transfer_buffer, buf_len + 3,
iuu_rxcmd, port);
result = usb_submit_urb(port->write_urb, GFP_ATOMIC);
- spin_lock_irqsave(&priv->lock, flags);
- priv->writelen = 0;
- spin_unlock_irqrestore(&priv->lock, flags);
usb_serial_port_softint(port);
return result;
}
return -ENOMEM;
spin_lock_irqsave(&priv->lock, flags);
- if (priv->writelen > 0) {
- /* buffer already filled but not commited */
- spin_unlock_irqrestore(&priv->lock, flags);
- return 0;
- }
+
/* fill the buffer */
- memcpy(priv->writebuf, buf, count);
- priv->writelen = count;
+ memcpy(priv->writebuf + priv->writelen, buf, count);
+ priv->writelen += count;
spin_unlock_irqrestore(&priv->lock, flags);
return count;
buf[0] = IUU_UART_ENABLE;
buf[1] = (u8) ((IUU_BAUD_9600 >> 8) & 0x00FF);
buf[2] = (u8) (0x00FF & IUU_BAUD_9600);
- buf[3] = (u8) (0x0F0 & IUU_TWO_STOP_BITS) | (0x07 & IUU_PARITY_EVEN);
+ buf[3] = (u8) (0x0F0 & IUU_ONE_STOP_BIT) | (0x07 & IUU_PARITY_EVEN);
status = bulk_immediate(port, buf, 4);
if (status != IUU_OPERATION_OK) {
return status;
}
-static int set_control_lines(struct usb_device *dev, u8 value)
+static void iuu_set_termios(struct tty_struct *tty,
+ struct usb_serial_port *port, struct ktermios *old_termios)
{
- return 0;
+ const u32 supported_mask = CMSPAR|PARENB|PARODD;
+
+ unsigned int cflag = tty->termios->c_cflag;
+ int status;
+ u32 actual;
+ u32 parity;
+ int csize = CS7;
+ int baud = 9600; /* Fixed for the moment */
+ u32 newval = cflag & supported_mask;
+
+ /* compute the parity parameter */
+ parity = 0;
+ if (cflag & CMSPAR) { /* Using mark space */
+ if (cflag & PARODD)
+ parity |= IUU_PARITY_SPACE;
+ else
+ parity |= IUU_PARITY_MARK;
+ } else if (!(cflag & PARENB)) {
+ parity |= IUU_PARITY_NONE;
+ csize = CS8;
+ } else if (cflag & PARODD)
+ parity |= IUU_PARITY_ODD;
+ else
+ parity |= IUU_PARITY_EVEN;
+
+ parity |= (cflag & CSTOPB ? IUU_TWO_STOP_BITS : IUU_ONE_STOP_BIT);
+
+ /* set it */
+ status = iuu_uart_baud(port,
+ (clockmode == 2) ? 16457 : 9600 * boost / 100,
+ &actual, parity);
+
+ /* set the termios value to the real one, so the user now what has
+ * changed. We support few fields so its easies to copy the old hw
+ * settings back over and then adjust them
+ */
+ if (old_termios)
+ tty_termios_copy_hw(tty->termios, old_termios);
+ if (status != 0) /* Set failed - return old bits */
+ return;
+ /* Re-encode speed, parity and csize */
+ tty_encode_baud_rate(tty, baud, baud);
+ tty->termios->c_cflag &= ~(supported_mask|CSIZE);
+ tty->termios->c_cflag |= newval | csize;
}
-static void iuu_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void iuu_close(struct usb_serial_port *port)
{
/* iuu_led (port,255,0,0,0); */
struct usb_serial *serial;
- struct iuu_private *priv = usb_get_serial_port_data(port);
- unsigned long flags;
- unsigned int c_cflag;
serial = port->serial;
if (!serial)
iuu_uart_off(port);
if (serial->dev) {
- if (tty) {
- c_cflag = tty->termios->c_cflag;
- if (c_cflag & HUPCL) {
- /* drop DTR and RTS */
- priv = usb_get_serial_port_data(port);
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_control = 0;
- spin_unlock_irqrestore(&priv->lock, flags);
- set_control_lines(port->serial->dev, 0);
- }
- }
/* free writebuf */
/* shutdown our urbs */
dbg("%s - shutting down urbs", __func__);
if (result) {
dev_err(&port->dev, "%s - failed submitting read urb,"
" error %d\n", __func__, result);
- iuu_close(tty, port, NULL);
+ iuu_close(port);
return -EPROTO;
} else {
dbg("%s - rxcmd OK", __func__);
.read_bulk_callback = iuu_uart_read_callback,
.tiocmget = iuu_tiocmget,
.tiocmset = iuu_tiocmset,
+ .set_termios = iuu_set_termios,
.attach = iuu_startup,
.shutdown = iuu_shutdown,
};
usb_kill_urb(urb);
}
-static void keyspan_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void keyspan_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct keyspan_port_private *p_priv = usb_get_serial_port_data(port);
+
+ p_priv->rts_state = on;
+ p_priv->dtr_state = on;
+ keyspan_send_setup(port, 0);
+}
+
+static void keyspan_close(struct usb_serial_port *port)
{
int i;
struct usb_serial *serial = port->serial;
stop_urb(p_priv->out_urbs[i]);
}
}
- tty_port_tty_set(&port->port, NULL);
}
/* download the firmware to a pre-renumeration device */
static int keyspan_open (struct tty_struct *tty,
struct usb_serial_port *port,
struct file *filp);
-static void keyspan_close (struct tty_struct *tty,
- struct usb_serial_port *port,
- struct file *filp);
+static void keyspan_close (struct usb_serial_port *port);
+static void keyspan_dtr_rts (struct usb_serial_port *port, int on);
static int keyspan_startup (struct usb_serial *serial);
static void keyspan_shutdown (struct usb_serial *serial);
static int keyspan_write_room (struct tty_struct *tty);
.num_ports = 1,
.open = keyspan_open,
.close = keyspan_close,
+ .dtr_rts = keyspan_dtr_rts,
.write = keyspan_write,
.write_room = keyspan_write_room,
.set_termios = keyspan_set_termios,
.num_ports = 2,
.open = keyspan_open,
.close = keyspan_close,
+ .dtr_rts = keyspan_dtr_rts,
.write = keyspan_write,
.write_room = keyspan_write_room,
.set_termios = keyspan_set_termios,
.num_ports = 4,
.open = keyspan_open,
.close = keyspan_close,
+ .dtr_rts = keyspan_dtr_rts,
.write = keyspan_write,
.write_room = keyspan_write_room,
.set_termios = keyspan_set_termios,
}
+static void keyspan_pda_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct usb_serial *serial = port->serial;
+
+ if (serial->dev) {
+ if (on)
+ keyspan_pda_set_modem_info(serial, (1<<7) | (1<< 2));
+ else
+ keyspan_pda_set_modem_info(serial, 0);
+ }
+}
+
+static int keyspan_pda_carrier_raised(struct usb_serial_port *port)
+{
+ struct usb_serial *serial = port->serial;
+ unsigned char modembits;
+
+ /* If we can read the modem status and the DCD is low then
+ carrier is not raised yet */
+ if (keyspan_pda_get_modem_info(serial, &modembits) >= 0) {
+ if (!(modembits & (1>>6)))
+ return 0;
+ }
+ /* Carrier raised, or we failed (eg disconnected) so
+ progress accordingly */
+ return 1;
+}
+
+
static int keyspan_pda_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp)
{
priv->tx_room = room;
priv->tx_throttled = room ? 0 : 1;
- /* the normal serial device seems to always turn on DTR and RTS here,
- so do the same */
- if (tty && (tty->termios->c_cflag & CBAUD))
- keyspan_pda_set_modem_info(serial, (1<<7) | (1<<2));
- else
- keyspan_pda_set_modem_info(serial, 0);
-
/*Start reading from the device*/
port->interrupt_in_urb->dev = serial->dev;
rc = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
error:
return rc;
}
-
-
-static void keyspan_pda_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void keyspan_pda_close(struct usb_serial_port *port)
{
struct usb_serial *serial = port->serial;
if (serial->dev) {
- /* the normal serial device seems to always shut
- off DTR and RTS now */
- if (tty->termios->c_cflag & HUPCL)
- keyspan_pda_set_modem_info(serial, 0);
-
/* shutdown our bulk reads and writes */
usb_kill_urb(port->write_urb);
usb_kill_urb(port->interrupt_in_urb);
.usb_driver = &keyspan_pda_driver,
.id_table = id_table_std,
.num_ports = 1,
+ .dtr_rts = keyspan_pda_dtr_rts,
+ .carrier_raised = keyspan_pda_carrier_raised,
.open = keyspan_pda_open,
.close = keyspan_pda_close,
.write = keyspan_pda_write,
static void klsi_105_shutdown(struct usb_serial *serial);
static int klsi_105_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void klsi_105_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void klsi_105_close(struct usb_serial_port *port);
static int klsi_105_write(struct tty_struct *tty,
struct usb_serial_port *port, const unsigned char *buf, int count);
static void klsi_105_write_bulk_callback(struct urb *urb);
} /* klsi_105_open */
-static void klsi_105_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void klsi_105_close(struct usb_serial_port *port)
{
struct klsi_105_private *priv = usb_get_serial_port_data(port);
int rc;
static void kobil_shutdown(struct usb_serial *serial);
static int kobil_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void kobil_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp);
+static void kobil_close(struct usb_serial_port *port);
static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf, int count);
static int kobil_write_room(struct tty_struct *tty);
for (i = 0; i < serial->num_ports; ++i) {
while (serial->port[i]->port.count > 0)
- kobil_close(NULL, serial->port[i], NULL);
+ kobil_close(serial->port[i]);
kfree(usb_get_serial_port_data(serial->port[i]));
usb_set_serial_port_data(serial->port[i], NULL);
}
}
-static void kobil_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void kobil_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
+ /* FIXME: Add rts/dtr methods */
if (port->write_urb) {
usb_kill_urb(port->write_urb);
usb_free_urb(port->write_urb);
static void mct_u232_shutdown(struct usb_serial *serial);
static int mct_u232_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void mct_u232_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void mct_u232_close(struct usb_serial_port *port);
+static void mct_u232_dtr_rts(struct usb_serial_port *port, int on);
static void mct_u232_read_int_callback(struct urb *urb);
static void mct_u232_set_termios(struct tty_struct *tty,
struct usb_serial_port *port, struct ktermios *old);
.num_ports = 1,
.open = mct_u232_open,
.close = mct_u232_close,
+ .dtr_rts = mct_u232_dtr_rts,
.throttle = mct_u232_throttle,
.unthrottle = mct_u232_unthrottle,
.read_int_callback = mct_u232_read_int_callback,
return retval;
} /* mct_u232_open */
-
-static void mct_u232_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void mct_u232_dtr_rts(struct usb_serial_port *port, int on)
{
- unsigned int c_cflag;
unsigned int control_state;
struct mct_u232_private *priv = usb_get_serial_port_data(port);
- dbg("%s port %d", __func__, port->number);
- if (tty) {
- c_cflag = tty->termios->c_cflag;
- mutex_lock(&port->serial->disc_mutex);
- if (c_cflag & HUPCL && !port->serial->disconnected) {
- /* drop DTR and RTS */
- spin_lock_irq(&priv->lock);
+ mutex_lock(&port->serial->disc_mutex);
+ if (!port->serial->disconnected) {
+ /* drop DTR and RTS */
+ spin_lock_irq(&priv->lock);
+ if (on)
+ priv->control_state |= TIOCM_DTR | TIOCM_RTS;
+ else
priv->control_state &= ~(TIOCM_DTR | TIOCM_RTS);
- control_state = priv->control_state;
- spin_unlock_irq(&priv->lock);
- mct_u232_set_modem_ctrl(port->serial, control_state);
- }
- mutex_unlock(&port->serial->disc_mutex);
+ control_state = priv->control_state;
+ spin_unlock_irq(&priv->lock);
+ mct_u232_set_modem_ctrl(port->serial, control_state);
}
+ mutex_unlock(&port->serial->disc_mutex);
+}
+static void mct_u232_close(struct usb_serial_port *port)
+{
+ dbg("%s port %d", __func__, port->number);
if (port->serial->dev) {
/* shutdown our urbs */
return chars;
}
-static void mos7720_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void mos7720_close(struct usb_serial_port *port)
{
struct usb_serial *serial;
struct moschip_port *mos7720_port;
}
-/************************************************************************
- *
- * mos7840_block_until_tx_empty
- *
- * This function will block the close until one of the following:
- * 1. TX count are 0
- * 2. The mos7840 has stopped
- * 3. A timeout of 3 seconds without activity has expired
- *
- ************************************************************************/
-static void mos7840_block_until_tx_empty(struct tty_struct *tty,
- struct moschip_port *mos7840_port)
-{
- int timeout = HZ / 10;
- int wait = 30;
- int count;
-
- while (1) {
-
- count = mos7840_chars_in_buffer(tty);
-
- /* Check for Buffer status */
- if (count <= 0)
- return;
-
- /* Block the thread for a while */
- interruptible_sleep_on_timeout(&mos7840_port->wait_chase,
- timeout);
-
- /* No activity.. count down section */
- wait--;
- if (wait == 0) {
- dbg("%s - TIMEOUT", __func__);
- return;
- } else {
- /* Reset timeout value back to seconds */
- wait = 30;
- }
- }
-}
-
/*****************************************************************************
* mos7840_close
* this function is called by the tty driver when a port is closed
*****************************************************************************/
-static void mos7840_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void mos7840_close(struct usb_serial_port *port)
{
struct usb_serial *serial;
struct moschip_port *mos7840_port;
}
}
- if (serial->dev)
- /* flush and block until tx is empty */
- mos7840_block_until_tx_empty(tty, mos7840_port);
-
/* While closing port, shutdown all bulk read, write *
* and interrupt read if they exists */
if (serial->dev) {
return result;
}
-static void navman_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void navman_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
/* function prototypes */
static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp);
-static void omninet_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp);
+static void omninet_close(struct usb_serial_port *port);
static void omninet_read_bulk_callback(struct urb *urb);
static void omninet_write_bulk_callback(struct urb *urb);
static int omninet_write(struct tty_struct *tty, struct usb_serial_port *port,
return result;
}
-static void omninet_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void omninet_close(struct usb_serial_port *port)
{
dbg("%s - port %d", __func__, port->number);
usb_kill_urb(port->read_urb);
return result;
}
-static void opticon_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp)
+static void opticon_close(struct usb_serial_port *port)
{
struct opticon_private *priv = usb_get_serial_data(port->serial);
/* Function prototypes */
static int option_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp);
-static void option_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp);
+static void option_close(struct usb_serial_port *port);
+static void option_dtr_rts(struct usb_serial_port *port, int on);
+
static int option_startup(struct usb_serial *serial);
static void option_shutdown(struct usb_serial *serial);
static int option_write_room(struct tty_struct *tty);
static int option_tiocmget(struct tty_struct *tty, struct file *file);
static int option_tiocmset(struct tty_struct *tty, struct file *file,
unsigned int set, unsigned int clear);
-static int option_send_setup(struct tty_struct *tty, struct usb_serial_port *port);
+static int option_send_setup(struct usb_serial_port *port);
static int option_suspend(struct usb_serial *serial, pm_message_t message);
static int option_resume(struct usb_serial *serial);
.num_ports = 1,
.open = option_open,
.close = option_close,
+ .dtr_rts = option_dtr_rts,
.write = option_write,
.write_room = option_write_room,
.chars_in_buffer = option_chars_in_buffer,
dbg("%s", __func__);
/* Doesn't support option setting */
tty_termios_copy_hw(tty->termios, old_termios);
- option_send_setup(tty, port);
+ option_send_setup(port);
}
static int option_tiocmget(struct tty_struct *tty, struct file *file)
portdata->rts_state = 0;
if (clear & TIOCM_DTR)
portdata->dtr_state = 0;
- return option_send_setup(tty, port);
+ return option_send_setup(port);
}
/* Write */
dbg("%s", __func__);
- /* Set some sane defaults */
- portdata->rts_state = 1;
- portdata->dtr_state = 1;
-
/* Reset low level data toggle and start reading from endpoints */
for (i = 0; i < N_IN_URB; i++) {
urb = portdata->in_urbs[i];
usb_pipeout(urb->pipe), 0); */
}
- option_send_setup(tty, port);
+ option_send_setup(port);
return 0;
}
-static void option_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void option_dtr_rts(struct usb_serial_port *port, int on)
{
- int i;
struct usb_serial *serial = port->serial;
struct option_port_private *portdata;
dbg("%s", __func__);
portdata = usb_get_serial_port_data(port);
+ mutex_lock(&serial->disc_mutex);
+ portdata->rts_state = on;
+ portdata->dtr_state = on;
+ if (serial->dev)
+ option_send_setup(port);
+ mutex_unlock(&serial->disc_mutex);
+}
- portdata->rts_state = 0;
- portdata->dtr_state = 0;
- if (serial->dev) {
- mutex_lock(&serial->disc_mutex);
- if (!serial->disconnected)
- option_send_setup(tty, port);
- mutex_unlock(&serial->disc_mutex);
+static void option_close(struct usb_serial_port *port)
+{
+ int i;
+ struct usb_serial *serial = port->serial;
+ struct option_port_private *portdata;
+
+ dbg("%s", __func__);
+ portdata = usb_get_serial_port_data(port);
+ if (serial->dev) {
/* Stop reading/writing urbs */
for (i = 0; i < N_IN_URB; i++)
usb_kill_urb(portdata->in_urbs[i]);
for (i = 0; i < N_OUT_URB; i++)
usb_kill_urb(portdata->out_urbs[i]);
}
- tty_port_tty_set(&port->port, NULL);
}
/* Helper functions used by option_setup_urbs */
* This is exactly the same as SET_CONTROL_LINE_STATE from the PSTN
* CDC.
*/
-static int option_send_setup(struct tty_struct *tty,
- struct usb_serial_port *port)
+static int option_send_setup(struct usb_serial_port *port)
{
struct usb_serial *serial = port->serial;
struct option_port_private *portdata;
int ifNum = serial->interface->cur_altsetting->desc.bInterfaceNumber;
+ int val = 0;
dbg("%s", __func__);
portdata = usb_get_serial_port_data(port);
- if (tty) {
- int val = 0;
- if (portdata->dtr_state)
- val |= 0x01;
- if (portdata->rts_state)
- val |= 0x02;
+ if (portdata->dtr_state)
+ val |= 0x01;
+ if (portdata->rts_state)
+ val |= 0x02;
- return usb_control_msg(serial->dev,
- usb_rcvctrlpipe(serial->dev, 0),
- 0x22, 0x21, val, ifNum, NULL, 0, USB_CTRL_SET_TIMEOUT);
- }
- return 0;
+ return usb_control_msg(serial->dev,
+ usb_rcvctrlpipe(serial->dev, 0),
+ 0x22, 0x21, val, ifNum, NULL, 0, USB_CTRL_SET_TIMEOUT);
}
static int option_startup(struct usb_serial *serial)
/* function prototypes */
static int oti6858_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void oti6858_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void oti6858_close(struct usb_serial_port *port);
static void oti6858_set_termios(struct tty_struct *tty,
struct usb_serial_port *port, struct ktermios *old);
static int oti6858_ioctl(struct tty_struct *tty, struct file *file,
if (result != 0) {
dev_err(&port->dev, "%s(): usb_submit_urb() failed"
" with error %d\n", __func__, result);
- oti6858_close(tty, port, NULL);
+ oti6858_close(port);
return -EPROTO;
}
/* setup termios */
if (tty)
oti6858_set_termios(tty, port, &tmp_termios);
-
+ port->port.drain_delay = 256; /* FIXME: check the FIFO length */
return 0;
}
-static void oti6858_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void oti6858_close(struct usb_serial_port *port)
{
struct oti6858_private *priv = usb_get_serial_port_data(port);
unsigned long flags;
- long timeout;
- wait_queue_t wait;
dbg("%s(port = %d)", __func__, port->number);
- /* wait for data to drain from the buffer */
spin_lock_irqsave(&priv->lock, flags);
- timeout = 30 * HZ; /* PL2303_CLOSING_WAIT */
- init_waitqueue_entry(&wait, current);
- add_wait_queue(&tty->write_wait, &wait);
- dbg("%s(): entering wait loop", __func__);
- for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (oti6858_buf_data_avail(priv->buf) == 0
- || timeout == 0 || signal_pending(current)
- || port->serial->disconnected)
- break;
- spin_unlock_irqrestore(&priv->lock, flags);
- timeout = schedule_timeout(timeout);
- spin_lock_irqsave(&priv->lock, flags);
- }
- set_current_state(TASK_RUNNING);
- remove_wait_queue(&tty->write_wait, &wait);
- dbg("%s(): after wait loop", __func__);
-
/* clear out any remaining data in the buffer */
oti6858_buf_clear(priv->buf);
spin_unlock_irqrestore(&priv->lock, flags);
- /* wait for characters to drain from the device */
- /* (this is long enough for the entire 256 byte */
- /* pl2303 hardware buffer to drain with no flow */
- /* control for data rates of 1200 bps or more, */
- /* for lower rates we should really know how much */
- /* data is in the buffer to compute a delay */
- /* that is not unnecessarily long) */
- /* FIXME
- bps = tty_get_baud_rate(tty);
- if (bps > 1200)
- timeout = max((HZ*2560)/bps,HZ/10);
- else
- */
- timeout = 2*HZ;
- schedule_timeout_interruptible(timeout);
- dbg("%s(): after schedule_timeout_interruptible()", __func__);
+ dbg("%s(): after buf_clear()", __func__);
/* cancel scheduled setup */
cancel_delayed_work(&priv->delayed_setup_work);
usb_kill_urb(port->write_urb);
usb_kill_urb(port->read_urb);
usb_kill_urb(port->interrupt_in_urb);
-
- /*
- if (tty && (tty->termios->c_cflag) & HUPCL) {
- // drop DTR and RTS
- spin_lock_irqsave(&priv->lock, flags);
- priv->pending_setup.control &= ~CONTROL_MASK;
- spin_unlock_irqrestore(&priv->lock, flags);
- }
- */
}
static int oti6858_tiocmset(struct tty_struct *tty, struct file *file,
kfree(buf);
}
-static void pl2303_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void pl2303_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct pl2303_private *priv = usb_get_serial_port_data(port);
+ unsigned long flags;
+ u8 control;
+
+ spin_lock_irqsave(&priv->lock, flags);
+ /* Change DTR and RTS */
+ if (on)
+ priv->line_control |= (CONTROL_DTR | CONTROL_RTS);
+ else
+ priv->line_control &= ~(CONTROL_DTR | CONTROL_RTS);
+ control = priv->line_control;
+ spin_unlock_irqrestore(&priv->lock, flags);
+ set_control_lines(port->serial->dev, control);
+}
+
+static void pl2303_close(struct usb_serial_port *port)
{
struct pl2303_private *priv = usb_get_serial_port_data(port);
unsigned long flags;
- unsigned int c_cflag;
- int bps;
- long timeout;
- wait_queue_t wait;
dbg("%s - port %d", __func__, port->number);
- /* wait for data to drain from the buffer */
spin_lock_irqsave(&priv->lock, flags);
- timeout = PL2303_CLOSING_WAIT;
- init_waitqueue_entry(&wait, current);
- add_wait_queue(&tty->write_wait, &wait);
- for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (pl2303_buf_data_avail(priv->buf) == 0 ||
- timeout == 0 || signal_pending(current) ||
- port->serial->disconnected)
- break;
- spin_unlock_irqrestore(&priv->lock, flags);
- timeout = schedule_timeout(timeout);
- spin_lock_irqsave(&priv->lock, flags);
- }
- set_current_state(TASK_RUNNING);
- remove_wait_queue(&tty->write_wait, &wait);
/* clear out any remaining data in the buffer */
pl2303_buf_clear(priv->buf);
spin_unlock_irqrestore(&priv->lock, flags);
- /* wait for characters to drain from the device */
- /* (this is long enough for the entire 256 byte */
- /* pl2303 hardware buffer to drain with no flow */
- /* control for data rates of 1200 bps or more, */
- /* for lower rates we should really know how much */
- /* data is in the buffer to compute a delay */
- /* that is not unnecessarily long) */
- bps = tty_get_baud_rate(tty);
- if (bps > 1200)
- timeout = max((HZ*2560)/bps, HZ/10);
- else
- timeout = 2*HZ;
- schedule_timeout_interruptible(timeout);
-
/* shutdown our urbs */
dbg("%s - shutting down urbs", __func__);
usb_kill_urb(port->write_urb);
usb_kill_urb(port->read_urb);
usb_kill_urb(port->interrupt_in_urb);
- if (tty) {
- c_cflag = tty->termios->c_cflag;
- if (c_cflag & HUPCL) {
- /* drop DTR and RTS */
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_control = 0;
- spin_unlock_irqrestore(&priv->lock, flags);
- set_control_lines(port->serial->dev, 0);
- }
- }
}
static int pl2303_open(struct tty_struct *tty,
if (result) {
dev_err(&port->dev, "%s - failed submitting read urb,"
" error %d\n", __func__, result);
- pl2303_close(tty, port, NULL);
+ pl2303_close(port);
return -EPROTO;
}
if (result) {
dev_err(&port->dev, "%s - failed submitting interrupt urb,"
" error %d\n", __func__, result);
- pl2303_close(tty, port, NULL);
+ pl2303_close(port);
return -EPROTO;
}
+ port->port.drain_delay = 256;
return 0;
}
return result;
}
+static int pl2303_carrier_raised(struct usb_serial_port *port)
+{
+ struct pl2303_private *priv = usb_get_serial_port_data(port);
+ if (priv->line_status & UART_DCD)
+ return 1;
+ return 0;
+}
+
static int wait_modem_info(struct usb_serial_port *port, unsigned int arg)
{
struct pl2303_private *priv = usb_get_serial_port_data(port);
.num_ports = 1,
.open = pl2303_open,
.close = pl2303_close,
+ .dtr_rts = pl2303_dtr_rts,
+ .carrier_raised = pl2303_carrier_raised,
.write = pl2303_write,
.ioctl = pl2303_ioctl,
.break_ctl = pl2303_break_ctl,
#include <linux/module.h>
#include <linux/usb.h>
#include <linux/usb/serial.h>
-#include <linux/usb/ch9.h>
#define SWIMS_USB_REQUEST_SetPower 0x00
#define SWIMS_USB_REQUEST_SetNmea 0x07
-/* per port private data */
#define N_IN_URB 4
#define N_OUT_URB 4
#define IN_BUFLEN 4096
static int debug;
static int nmea;
+/* Used in interface blacklisting */
+struct sierra_iface_info {
+ const u32 infolen; /* number of interface numbers on blacklist */
+ const u8 *ifaceinfo; /* pointer to the array holding the numbers */
+};
+
static int sierra_set_power_state(struct usb_device *udev, __u16 swiState)
{
int result;
return result;
}
+static int is_blacklisted(const u8 ifnum,
+ const struct sierra_iface_info *blacklist)
+{
+ const u8 *info;
+ int i;
+
+ if (blacklist) {
+ info = blacklist->ifaceinfo;
+
+ for (i = 0; i < blacklist->infolen; i++) {
+ if (info[i] == ifnum)
+ return 1;
+ }
+ }
+ return 0;
+}
+
static int sierra_calc_interface(struct usb_serial *serial)
{
int interface;
*/
usb_set_serial_data(serial, (void *)num_ports);
+ /* ifnum could have changed - by calling usb_set_interface */
+ ifnum = sierra_calc_interface(serial);
+
+ if (is_blacklisted(ifnum,
+ (struct sierra_iface_info *)id->driver_info)) {
+ dev_dbg(&serial->dev->dev,
+ "Ignoring blacklisted interface #%d\n", ifnum);
+ return -ENODEV;
+ }
+
return result;
}
+static const u8 direct_ip_non_serial_ifaces[] = { 7, 8, 9, 10, 11 };
+static const struct sierra_iface_info direct_ip_interface_blacklist = {
+ .infolen = ARRAY_SIZE(direct_ip_non_serial_ifaces),
+ .ifaceinfo = direct_ip_non_serial_ifaces,
+};
+
static struct usb_device_id id_table [] = {
{ USB_DEVICE(0x1199, 0x0017) }, /* Sierra Wireless EM5625 */
{ USB_DEVICE(0x1199, 0x0018) }, /* Sierra Wireless MC5720 */
{ USB_DEVICE(0x1199, 0x6833) }, /* Sierra Wireless MC8781 */
{ USB_DEVICE(0x1199, 0x683A) }, /* Sierra Wireless MC8785 */
{ USB_DEVICE(0x1199, 0x683B) }, /* Sierra Wireless MC8785 Composite */
- { USB_DEVICE(0x1199, 0x683C) }, /* Sierra Wireless MC8790 */
- { USB_DEVICE(0x1199, 0x683D) }, /* Sierra Wireless MC8790 */
- { USB_DEVICE(0x1199, 0x683E) }, /* Sierra Wireless MC8790 */
+ /* Sierra Wireless MC8790, MC8791, MC8792 Composite */
+ { USB_DEVICE(0x1199, 0x683C) },
+ { USB_DEVICE(0x1199, 0x683D) }, /* Sierra Wireless MC8791 Composite */
+ /* Sierra Wireless MC8790, MC8791, MC8792 */
+ { USB_DEVICE(0x1199, 0x683E) },
{ USB_DEVICE(0x1199, 0x6850) }, /* Sierra Wireless AirCard 880 */
{ USB_DEVICE(0x1199, 0x6851) }, /* Sierra Wireless AirCard 881 */
{ USB_DEVICE(0x1199, 0x6852) }, /* Sierra Wireless AirCard 880 E */
{ USB_DEVICE(0x1199, 0x0112) }, /* Sierra Wireless AirCard 580 */
{ USB_DEVICE(0x0F3D, 0x0112) }, /* Airprime/Sierra PC 5220 */
+ { USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */
+ .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
+ },
+
{ }
};
MODULE_DEVICE_TABLE(usb, id_table);
/* Input endpoints and buffers for this port */
struct urb *in_urbs[N_IN_URB];
- char *in_buffer[N_IN_URB];
/* Settings for the port */
int rts_state; /* Handshaking pins (outputs) */
int ri_state;
};
-static int sierra_send_setup(struct tty_struct *tty,
- struct usb_serial_port *port)
+static int sierra_send_setup(struct usb_serial_port *port)
{
struct usb_serial *serial = port->serial;
struct sierra_port_private *portdata;
__u16 interface = 0;
+ int val = 0;
dev_dbg(&port->dev, "%s", __func__);
portdata = usb_get_serial_port_data(port);
- if (tty) {
- int val = 0;
- if (portdata->dtr_state)
- val |= 0x01;
- if (portdata->rts_state)
- val |= 0x02;
-
- /* If composite device then properly report interface */
- if (serial->num_ports == 1) {
- interface = sierra_calc_interface(serial);
-
- /* Control message is sent only to interfaces with
- * interrupt_in endpoints
- */
- if (port->interrupt_in_urb) {
- /* send control message */
- return usb_control_msg(serial->dev,
- usb_rcvctrlpipe(serial->dev, 0),
- 0x22, 0x21, val, interface,
- NULL, 0, USB_CTRL_SET_TIMEOUT);
- }
- }
-
- /* Otherwise the need to do non-composite mapping */
- else {
- if (port->bulk_out_endpointAddress == 2)
- interface = 0;
- else if (port->bulk_out_endpointAddress == 4)
- interface = 1;
- else if (port->bulk_out_endpointAddress == 5)
- interface = 2;
+ if (portdata->dtr_state)
+ val |= 0x01;
+ if (portdata->rts_state)
+ val |= 0x02;
+ /* If composite device then properly report interface */
+ if (serial->num_ports == 1) {
+ interface = sierra_calc_interface(serial);
+ /* Control message is sent only to interfaces with
+ * interrupt_in endpoints
+ */
+ if (port->interrupt_in_urb) {
+ /* send control message */
return usb_control_msg(serial->dev,
usb_rcvctrlpipe(serial->dev, 0),
0x22, 0x21, val, interface,
NULL, 0, USB_CTRL_SET_TIMEOUT);
-
}
}
+ /* Otherwise the need to do non-composite mapping */
+ else {
+ if (port->bulk_out_endpointAddress == 2)
+ interface = 0;
+ else if (port->bulk_out_endpointAddress == 4)
+ interface = 1;
+ else if (port->bulk_out_endpointAddress == 5)
+ interface = 2;
+ return usb_control_msg(serial->dev,
+ usb_rcvctrlpipe(serial->dev, 0),
+ 0x22, 0x21, val, interface,
+ NULL, 0, USB_CTRL_SET_TIMEOUT);
+ }
return 0;
}
{
dev_dbg(&port->dev, "%s", __func__);
tty_termios_copy_hw(tty->termios, old_termios);
- sierra_send_setup(tty, port);
+ sierra_send_setup(port);
}
static int sierra_tiocmget(struct tty_struct *tty, struct file *file)
portdata->rts_state = 0;
if (clear & TIOCM_DTR)
portdata->dtr_state = 0;
- return sierra_send_setup(tty, port);
+ return sierra_send_setup(port);
+}
+
+static void sierra_release_urb(struct urb *urb)
+{
+ struct usb_serial_port *port;
+ if (urb) {
+ port = urb->context;
+ dev_dbg(&port->dev, "%s: %p\n", __func__, urb);
+ kfree(urb->transfer_buffer);
+ usb_free_urb(urb);
+ }
}
static void sierra_outdat_callback(struct urb *urb)
" received", __func__);
/* Resubmit urb so we continue receiving */
- if (port->port.count && status != -ESHUTDOWN) {
+ if (port->port.count && status != -ESHUTDOWN && status != -EPERM) {
err = usb_submit_urb(urb, GFP_ATOMIC);
if (err)
dev_err(&port->dev, "resubmit read urb failed."
return 2048;
}
-static int sierra_open(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void sierra_stop_rx_urbs(struct usb_serial_port *port)
{
- struct sierra_port_private *portdata;
- struct usb_serial *serial = port->serial;
int i;
- struct urb *urb;
- int result;
+ struct sierra_port_private *portdata = usb_get_serial_port_data(port);
- portdata = usb_get_serial_port_data(port);
+ for (i = 0; i < ARRAY_SIZE(portdata->in_urbs); i++)
+ usb_kill_urb(portdata->in_urbs[i]);
- dev_dbg(&port->dev, "%s", __func__);
+ usb_kill_urb(port->interrupt_in_urb);
+}
- /* Set some sane defaults */
- portdata->rts_state = 1;
- portdata->dtr_state = 1;
+static int sierra_submit_rx_urbs(struct usb_serial_port *port, gfp_t mem_flags)
+{
+ int ok_cnt;
+ int err = -EINVAL;
+ int i;
+ struct urb *urb;
+ struct sierra_port_private *portdata = usb_get_serial_port_data(port);
- /* Reset low level data toggle and start reading from endpoints */
- for (i = 0; i < N_IN_URB; i++) {
+ ok_cnt = 0;
+ for (i = 0; i < ARRAY_SIZE(portdata->in_urbs); i++) {
urb = portdata->in_urbs[i];
if (!urb)
continue;
- if (urb->dev != serial->dev) {
- dev_dbg(&port->dev, "%s: dev %p != %p",
- __func__, urb->dev, serial->dev);
- continue;
+ err = usb_submit_urb(urb, mem_flags);
+ if (err) {
+ dev_err(&port->dev, "%s: submit urb failed: %d\n",
+ __func__, err);
+ } else {
+ ok_cnt++;
}
+ }
- /*
- * make sure endpoint data toggle is synchronized with the
- * device
- */
- usb_clear_halt(urb->dev, urb->pipe);
-
- result = usb_submit_urb(urb, GFP_KERNEL);
- if (result) {
- dev_err(&port->dev, "submit urb %d failed (%d) %d\n",
- i, result, urb->transfer_buffer_length);
+ if (ok_cnt && port->interrupt_in_urb) {
+ err = usb_submit_urb(port->interrupt_in_urb, mem_flags);
+ if (err) {
+ dev_err(&port->dev, "%s: submit intr urb failed: %d\n",
+ __func__, err);
}
}
- sierra_send_setup(tty, port);
+ if (ok_cnt > 0) /* at least one rx urb submitted */
+ return 0;
+ else
+ return err;
+}
+
+static struct urb *sierra_setup_urb(struct usb_serial *serial, int endpoint,
+ int dir, void *ctx, int len,
+ gfp_t mem_flags,
+ usb_complete_t callback)
+{
+ struct urb *urb;
+ u8 *buf;
+
+ if (endpoint == -1)
+ return NULL;
- /* start up the interrupt endpoint if we have one */
- if (port->interrupt_in_urb) {
- result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
- if (result)
- dev_err(&port->dev, "submit irq_in urb failed %d\n",
- result);
+ urb = usb_alloc_urb(0, mem_flags);
+ if (urb == NULL) {
+ dev_dbg(&serial->dev->dev, "%s: alloc for endpoint %d failed\n",
+ __func__, endpoint);
+ return NULL;
}
- return 0;
+
+ buf = kmalloc(len, mem_flags);
+ if (buf) {
+ /* Fill URB using supplied data */
+ usb_fill_bulk_urb(urb, serial->dev,
+ usb_sndbulkpipe(serial->dev, endpoint) | dir,
+ buf, len, callback, ctx);
+
+ /* debug */
+ dev_dbg(&serial->dev->dev, "%s %c u : %p d:%p\n", __func__,
+ dir == USB_DIR_IN ? 'i' : 'o', urb, buf);
+ } else {
+ dev_dbg(&serial->dev->dev, "%s %c u:%p d:%p\n", __func__,
+ dir == USB_DIR_IN ? 'i' : 'o', urb, buf);
+
+ sierra_release_urb(urb);
+ urb = NULL;
+ }
+
+ return urb;
}
-static void sierra_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void sierra_close(struct usb_serial_port *port)
{
int i;
struct usb_serial *serial = port->serial;
struct sierra_port_private *portdata;
- dev_dbg(&port->dev, "%s", __func__);
+ dev_dbg(&port->dev, "%s\n", __func__);
portdata = usb_get_serial_port_data(port);
portdata->rts_state = 0;
if (serial->dev) {
mutex_lock(&serial->disc_mutex);
if (!serial->disconnected)
- sierra_send_setup(tty, port);
+ sierra_send_setup(port);
mutex_unlock(&serial->disc_mutex);
- /* Stop reading/writing urbs */
- for (i = 0; i < N_IN_URB; i++)
- usb_kill_urb(portdata->in_urbs[i]);
+ /* Stop reading urbs */
+ sierra_stop_rx_urbs(port);
+ /* .. and release them */
+ for (i = 0; i < N_IN_URB; i++) {
+ sierra_release_urb(portdata->in_urbs[i]);
+ portdata->in_urbs[i] = NULL;
+ }
}
+}
- usb_kill_urb(port->interrupt_in_urb);
- tty_port_tty_set(&port->port, NULL);
+static int sierra_open(struct tty_struct *tty,
+ struct usb_serial_port *port, struct file *filp)
+{
+ struct sierra_port_private *portdata;
+ struct usb_serial *serial = port->serial;
+ int i;
+ int err;
+ int endpoint;
+ struct urb *urb;
+
+ portdata = usb_get_serial_port_data(port);
+
+ dev_dbg(&port->dev, "%s", __func__);
+
+ /* Set some sane defaults */
+ portdata->rts_state = 1;
+ portdata->dtr_state = 1;
+
+
+ endpoint = port->bulk_in_endpointAddress;
+ for (i = 0; i < ARRAY_SIZE(portdata->in_urbs); i++) {
+ urb = sierra_setup_urb(serial, endpoint, USB_DIR_IN, port,
+ IN_BUFLEN, GFP_KERNEL,
+ sierra_indat_callback);
+ portdata->in_urbs[i] = urb;
+ }
+ /* clear halt condition */
+ usb_clear_halt(serial->dev,
+ usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN);
+
+ err = sierra_submit_rx_urbs(port, GFP_KERNEL);
+ if (err) {
+ /* get rid of everything as in close */
+ sierra_close(port);
+ return err;
+ }
+ sierra_send_setup(port);
+
+ return 0;
+}
+
+
+static void sierra_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct usb_serial *serial = port->serial;
+ struct sierra_port_private *portdata;
+
+ portdata = usb_get_serial_port_data(port);
+ portdata->rts_state = on;
+ portdata->dtr_state = on;
+
+ if (serial->dev) {
+ mutex_lock(&serial->disc_mutex);
+ if (!serial->disconnected)
+ sierra_send_setup(port);
+ mutex_unlock(&serial->disc_mutex);
+ }
}
static int sierra_startup(struct usb_serial *serial)
{
struct usb_serial_port *port;
struct sierra_port_private *portdata;
- struct urb *urb;
int i;
- int j;
dev_dbg(&serial->dev->dev, "%s", __func__);
return -ENOMEM;
}
spin_lock_init(&portdata->lock);
- for (j = 0; j < N_IN_URB; j++) {
- portdata->in_buffer[j] = kmalloc(IN_BUFLEN, GFP_KERNEL);
- if (!portdata->in_buffer[j]) {
- for (--j; j >= 0; j--)
- kfree(portdata->in_buffer[j]);
- kfree(portdata);
- return -ENOMEM;
- }
- }
-
+ /* Set the port private data pointer */
usb_set_serial_port_data(port, portdata);
-
- /* initialize the in urbs */
- for (j = 0; j < N_IN_URB; ++j) {
- urb = usb_alloc_urb(0, GFP_KERNEL);
- if (urb == NULL) {
- dev_dbg(&port->dev, "%s: alloc for in "
- "port failed.", __func__);
- continue;
- }
- /* Fill URB using supplied data. */
- usb_fill_bulk_urb(urb, serial->dev,
- usb_rcvbulkpipe(serial->dev,
- port->bulk_in_endpointAddress),
- portdata->in_buffer[j], IN_BUFLEN,
- sierra_indat_callback, port);
- portdata->in_urbs[j] = urb;
- }
}
return 0;
static void sierra_shutdown(struct usb_serial *serial)
{
- int i, j;
+ int i;
struct usb_serial_port *port;
struct sierra_port_private *portdata;
portdata = usb_get_serial_port_data(port);
if (!portdata)
continue;
-
- for (j = 0; j < N_IN_URB; j++) {
- usb_kill_urb(portdata->in_urbs[j]);
- usb_free_urb(portdata->in_urbs[j]);
- kfree(portdata->in_buffer[j]);
- }
kfree(portdata);
usb_set_serial_port_data(port, NULL);
}
.probe = sierra_probe,
.open = sierra_open,
.close = sierra_close,
+ .dtr_rts = sierra_dtr_rts,
.write = sierra_write,
.write_room = sierra_write_room,
.set_termios = sierra_set_termios,
"RTSCTS usb_control_msg(enable flowctrl) = %d\n", ret);
}
+static int spcp8x5_carrier_raised(struct usb_serial_port *port)
+{
+ struct spcp8x5_private *priv = usb_get_serial_port_data(port);
+ if (priv->line_status & MSR_STATUS_LINE_DCD)
+ return 1;
+ return 0;
+}
+
+static void spcp8x5_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct spcp8x5_private *priv = usb_get_serial_port_data(port);
+ unsigned long flags;
+ u8 control;
+
+ spin_lock_irqsave(&priv->lock, flags);
+ if (on)
+ priv->line_control = MCR_CONTROL_LINE_DTR
+ | MCR_CONTROL_LINE_RTS;
+ else
+ priv->line_control &= ~ (MCR_CONTROL_LINE_DTR
+ | MCR_CONTROL_LINE_RTS);
+ control = priv->line_control;
+ spin_unlock_irqrestore(&priv->lock, flags);
+ spcp8x5_set_ctrlLine(port->serial->dev, control , priv->type);
+}
+
/* close the serial port. We should wait for data sending to device 1st and
* then kill all urb. */
-static void spcp8x5_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void spcp8x5_close(struct usb_serial_port *port)
{
struct spcp8x5_private *priv = usb_get_serial_port_data(port);
unsigned long flags;
- unsigned int c_cflag;
- int bps;
- long timeout;
- wait_queue_t wait;
int result;
dbg("%s - port %d", __func__, port->number);
- /* wait for data to drain from the buffer */
spin_lock_irqsave(&priv->lock, flags);
- timeout = SPCP8x5_CLOSING_WAIT;
- init_waitqueue_entry(&wait, current);
- add_wait_queue(&tty->write_wait, &wait);
- for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (ringbuf_avail_data(priv->buf) == 0 ||
- timeout == 0 || signal_pending(current))
- break;
- spin_unlock_irqrestore(&priv->lock, flags);
- timeout = schedule_timeout(timeout);
- spin_lock_irqsave(&priv->lock, flags);
- }
- set_current_state(TASK_RUNNING);
- remove_wait_queue(&tty->write_wait, &wait);
-
/* clear out any remaining data in the buffer */
clear_ringbuf(priv->buf);
spin_unlock_irqrestore(&priv->lock, flags);
- /* wait for characters to drain from the device (this is long enough
- * for the entire all byte spcp8x5 hardware buffer to drain with no
- * flow control for data rates of 1200 bps or more, for lower rates we
- * should really know how much data is in the buffer to compute a delay
- * that is not unnecessarily long) */
- bps = tty_get_baud_rate(tty);
- if (bps > 1200)
- timeout = max((HZ*2560) / bps, HZ/10);
- else
- timeout = 2*HZ;
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(timeout);
-
- /* clear control lines */
- if (tty) {
- c_cflag = tty->termios->c_cflag;
- if (c_cflag & HUPCL) {
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_control = 0;
- spin_unlock_irqrestore(&priv->lock, flags);
- spcp8x5_set_ctrlLine(port->serial->dev, 0 , priv->type);
- }
- }
-
/* kill urb */
if (port->write_urb != NULL) {
result = usb_unlink_urb(port->write_urb);
if (ret)
return ret;
- spin_lock_irqsave(&priv->lock, flags);
- if (tty && (tty->termios->c_cflag & CBAUD))
- priv->line_control = MCR_DTR | MCR_RTS;
- else
- priv->line_control = 0;
- spin_unlock_irqrestore(&priv->lock, flags);
-
spcp8x5_set_ctrlLine(serial->dev, priv->line_control , priv->type);
/* Setup termios */
port->read_urb->dev = serial->dev;
ret = usb_submit_urb(port->read_urb, GFP_KERNEL);
if (ret) {
- spcp8x5_close(tty, port, NULL);
+ spcp8x5_close(port);
return -EPROTO;
}
+ port->port.drain_delay = 256;
return 0;
}
.num_ports = 1,
.open = spcp8x5_open,
.close = spcp8x5_close,
+ .dtr_rts = spcp8x5_dtr_rts,
+ .carrier_raised = spcp8x5_carrier_raised,
.write = spcp8x5_write,
.set_termios = spcp8x5_set_termios,
.ioctl = spcp8x5_ioctl,
return result;
}
-static void symbol_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp)
+static void symbol_close(struct usb_serial_port *port)
{
struct symbol_private *priv = usb_get_serial_data(port->serial);
static void ti_shutdown(struct usb_serial *serial);
static int ti_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *file);
-static void ti_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *file);
+static void ti_close(struct usb_serial_port *port);
static int ti_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *data, int count);
static int ti_write_room(struct tty_struct *tty);
}
-static void ti_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *file)
+static void ti_close(struct usb_serial_port *port)
{
struct ti_device *tdev;
struct ti_port *tport;
goto bailout_interface_put;
mutex_unlock(&serial->disc_mutex);
}
-
mutex_unlock(&port->mutex);
- return 0;
+ /* Now do the correct tty layer semantics */
+ retval = tty_port_block_til_ready(&port->port, tty, filp);
+ if (retval == 0)
+ return 0;
bailout_interface_put:
usb_autopm_put_interface(serial->interface);
return retval;
}
-static void serial_close(struct tty_struct *tty, struct file *filp)
+/**
+ * serial_do_down - shut down hardware
+ * @port: port to shut down
+ *
+ * Shut down a USB port unless it is the console. We never shut down the
+ * console hardware as it will always be in use.
+ *
+ * Don't free any resources at this point
+ */
+static void serial_do_down(struct usb_serial_port *port)
{
- struct usb_serial_port *port = tty->driver_data;
+ struct usb_serial_driver *drv = port->serial->type;
struct usb_serial *serial;
struct module *owner;
- int count;
- if (!port)
+ /* The console is magical, do not hang up the console hardware
+ or there will be tears */
+ if (port->console)
return;
- dbg("%s - port %d", __func__, port->number);
-
mutex_lock(&port->mutex);
serial = port->serial;
owner = serial->type->driver.owner;
- if (port->port.count == 0) {
- mutex_unlock(&port->mutex);
- return;
- }
-
- if (port->port.count == 1)
- /* only call the device specific close if this
- * port is being closed by the last owner. Ensure we do
- * this before we drop the port count. The call is protected
- * by the port mutex
- */
- serial->type->close(tty, port, filp);
-
- if (port->port.count == (port->console ? 2 : 1)) {
- struct tty_struct *tty = tty_port_tty_get(&port->port);
- if (tty) {
- /* We must do this before we drop the port count to
- zero. */
- if (tty->driver_data)
- tty->driver_data = NULL;
- tty_port_tty_set(&port->port, NULL);
- tty_kref_put(tty);
- }
- }
+ if (drv->close)
+ drv->close(port);
- --port->port.count;
- count = port->port.count;
mutex_unlock(&port->mutex);
- put_device(&port->dev);
+}
+
+/**
+ * serial_do_free - free resources post close/hangup
+ * @port: port to free up
+ *
+ * Do the resource freeing and refcount dropping for the port. We must
+ * be careful about ordering and we must avoid freeing up the console.
+ */
+static void serial_do_free(struct usb_serial_port *port)
+{
+ struct usb_serial *serial;
+ struct module *owner;
+
+ /* The console is magical, do not hang up the console hardware
+ or there will be tears */
+ if (port->console)
+ return;
+
+ serial = port->serial;
+ owner = serial->type->driver.owner;
+ put_device(&port->dev);
/* Mustn't dereference port any more */
- if (count == 0) {
- mutex_lock(&serial->disc_mutex);
- if (!serial->disconnected)
- usb_autopm_put_interface(serial->interface);
- mutex_unlock(&serial->disc_mutex);
- }
+ mutex_lock(&serial->disc_mutex);
+ if (!serial->disconnected)
+ usb_autopm_put_interface(serial->interface);
+ mutex_unlock(&serial->disc_mutex);
usb_serial_put(serial);
-
/* Mustn't dereference serial any more */
- if (count == 0)
- module_put(owner);
+ module_put(owner);
+}
+
+static void serial_close(struct tty_struct *tty, struct file *filp)
+{
+ struct usb_serial_port *port = tty->driver_data;
+
+ dbg("%s - port %d", __func__, port->number);
+
+
+ if (tty_port_close_start(&port->port, tty, filp) == 0)
+ return;
+
+ serial_do_down(port);
+ tty_port_close_end(&port->port, tty);
+ tty_port_tty_set(&port->port, NULL);
+ serial_do_free(port);
+}
+
+static void serial_hangup(struct tty_struct *tty)
+{
+ struct usb_serial_port *port = tty->driver_data;
+ serial_do_down(port);
+ tty_port_hangup(&port->port);
+ serial_do_free(port);
}
static int serial_write(struct tty_struct *tty, const unsigned char *buf,
return NULL;
}
+static int serial_carrier_raised(struct tty_port *port)
+{
+ struct usb_serial_port *p = container_of(port, struct usb_serial_port, port);
+ struct usb_serial_driver *drv = p->serial->type;
+ if (drv->carrier_raised)
+ return drv->carrier_raised(p);
+ /* No carrier control - don't block */
+ return 1;
+}
+
+static void serial_dtr_rts(struct tty_port *port, int on)
+{
+ struct usb_serial_port *p = container_of(port, struct usb_serial_port, port);
+ struct usb_serial_driver *drv = p->serial->type;
+ if (drv->dtr_rts)
+ drv->dtr_rts(p, on);
+}
+
+static const struct tty_port_operations serial_port_ops = {
+ .carrier_raised = serial_carrier_raised,
+ .dtr_rts = serial_dtr_rts,
+};
+
int usb_serial_probe(struct usb_interface *interface,
const struct usb_device_id *id)
{
if (!port)
goto probe_error;
tty_port_init(&port->port);
+ port->port.ops = &serial_port_ops;
port->serial = serial;
spin_lock_init(&port->lock);
mutex_init(&port->mutex);
if (port) {
struct tty_struct *tty = tty_port_tty_get(&port->port);
if (tty) {
+ /* The hangup will occur asynchronously but
+ the object refcounts will sort out all the
+ cleanup */
tty_hangup(tty);
tty_kref_put(tty);
}
.open = serial_open,
.close = serial_close,
.write = serial_write,
+ .hangup = serial_hangup,
.write_room = serial_write_room,
.ioctl = serial_ioctl,
.set_termios = serial_set_termios,
.proc_fops = &serial_proc_fops,
};
+
struct tty_driver *usb_serial_tty_driver;
static int __init usb_serial_init(void)
/* function prototypes for a handspring visor */
static int visor_open(struct tty_struct *tty, struct usb_serial_port *port,
struct file *filp);
-static void visor_close(struct tty_struct *tty, struct usb_serial_port *port,
- struct file *filp);
+static void visor_close(struct usb_serial_port *port);
static int visor_write(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf, int count);
static int visor_write_room(struct tty_struct *tty);
}
-static void visor_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void visor_close(struct usb_serial_port *port)
{
struct visor_private *priv = usb_get_serial_port_data(port);
unsigned char *transfer_buffer;
static void whiteheat_shutdown(struct usb_serial *serial);
static int whiteheat_open(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
-static void whiteheat_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+static void whiteheat_close(struct usb_serial_port *port);
static int whiteheat_write(struct tty_struct *tty,
struct usb_serial_port *port,
const unsigned char *buf, int count);
}
-static void whiteheat_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp)
+static void whiteheat_close(struct usb_serial_port *port)
{
struct whiteheat_private *info = usb_get_serial_port_data(port);
struct whiteheat_urb_wrap *wrap;
dbg("%s - port %d", __func__, port->number);
- mutex_lock(&port->serial->disc_mutex);
- /* filp is NULL when called from usb_serial_disconnect */
- if ((filp && (tty_hung_up_p(filp))) || port->serial->disconnected) {
- mutex_unlock(&port->serial->disc_mutex);
- return;
- }
- mutex_unlock(&port->serial->disc_mutex);
-
- tty->closing = 1;
-
-/*
- * Not currently in use; tty_wait_until_sent() calls
- * serial_chars_in_buffer() which deadlocks on the second semaphore
- * acquisition. This should be fixed at some point. Greg's been
- * notified.
- if ((filp->f_flags & (O_NDELAY | O_NONBLOCK)) == 0) {
- tty_wait_until_sent(tty, CLOSING_DELAY);
- }
-*/
-
- tty_driver_flush_buffer(tty);
- tty_ldisc_flush(tty);
-
firm_report_tx_done(port);
-
firm_close(port);
/* shutdown our bulk reads and writes */
}
spin_unlock_irq(&info->lock);
mutex_unlock(&info->deathwarrant);
-
stop_command_port(port->serial);
-
- tty->closing = 0;
}
secure, but slightly less efficient.
If in doubt, say yes.
+config XEN_DEV_EVTCHN
+ tristate "Xen /dev/xen/evtchn device"
+ depends on XEN
+ default y
+ help
+ The evtchn driver allows a userspace process to triger event
+ channels and to receive notification of an event channel
+ firing.
+ If in doubt, say yes.
+
config XENFS
tristate "Xen filesystem"
depends on XEN
a xen platform.
If in doubt, say yes.
+config XEN_SYS_HYPERVISOR
+ bool "Create xen entries under /sys/hypervisor"
+ depends on XEN && SYSFS
+ select SYS_HYPERVISOR
+ default y
+ help
+ Create entries under /sys/hypervisor describing the Xen
+ hypervisor environment. When running native or in another
+ virtual environment, /sys/hypervisor will still be present,
+ but will have no xen contents.
\ No newline at end of file
obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o
obj-$(CONFIG_XEN_XENCOMM) += xencomm.o
obj-$(CONFIG_XEN_BALLOON) += balloon.o
-obj-$(CONFIG_XENFS) += xenfs/
\ No newline at end of file
+obj-$(CONFIG_XEN_DEV_EVTCHN) += evtchn.o
+obj-$(CONFIG_XENFS) += xenfs/
+obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
\ No newline at end of file
return info_for_irq(irq)->evtchn;
}
+unsigned irq_from_evtchn(unsigned int evtchn)
+{
+ return evtchn_to_irq[evtchn];
+}
+EXPORT_SYMBOL_GPL(irq_from_evtchn);
+
static enum ipi_vector ipi_from_irq(unsigned irq)
{
struct irq_info *info = info_for_irq(irq);
if (irq == nr_irqs)
panic("No available IRQ to bind to: increase nr_irqs!\n");
- desc = irq_to_desc_alloc_cpu(irq, 0);
+ desc = irq_to_desc_alloc_node(irq, 0);
if (WARN_ON(desc == NULL))
return -1;
}
/* Rebind an evtchn so that it gets delivered to a specific cpu */
-static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
+static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
{
struct evtchn_bind_vcpu bind_vcpu;
int evtchn = evtchn_from_irq(irq);
if (!VALID_EVTCHN(evtchn))
- return;
+ return -1;
/* Send future instances of this interrupt to other vcpu. */
bind_vcpu.port = evtchn;
*/
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
bind_evtchn_to_cpu(evtchn, tcpu);
-}
+ return 0;
+}
-static void set_affinity_irq(unsigned irq, const struct cpumask *dest)
+static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
{
unsigned tcpu = cpumask_first(dest);
- rebind_irq_to_cpu(irq, tcpu);
+
+ return rebind_irq_to_cpu(irq, tcpu);
}
int resend_irq_on_evtchn(unsigned int irq)
--- /dev/null
+/******************************************************************************
+ * evtchn.c
+ *
+ * Driver for receiving and demuxing event-channel signals.
+ *
+ * Copyright (c) 2004-2005, K A Fraser
+ * Multi-process extensions Copyright (c) 2004, Steven Smith
+ *
+ * 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; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/errno.h>
+#include <linux/miscdevice.h>
+#include <linux/major.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/poll.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+#include <xen/events.h>
+#include <xen/evtchn.h>
+#include <asm/xen/hypervisor.h>
+
+struct per_user_data {
+ struct mutex bind_mutex; /* serialize bind/unbind operations */
+
+ /* Notification ring, accessed via /dev/xen/evtchn. */
+#define EVTCHN_RING_SIZE (PAGE_SIZE / sizeof(evtchn_port_t))
+#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+ evtchn_port_t *ring;
+ unsigned int ring_cons, ring_prod, ring_overflow;
+ struct mutex ring_cons_mutex; /* protect against concurrent readers */
+
+ /* Processes wait on this queue when ring is empty. */
+ wait_queue_head_t evtchn_wait;
+ struct fasync_struct *evtchn_async_queue;
+ const char *name;
+};
+
+/* Who's bound to each port? */
+static struct per_user_data *port_user[NR_EVENT_CHANNELS];
+static DEFINE_SPINLOCK(port_user_lock); /* protects port_user[] and ring_prod */
+
+irqreturn_t evtchn_interrupt(int irq, void *data)
+{
+ unsigned int port = (unsigned long)data;
+ struct per_user_data *u;
+
+ spin_lock(&port_user_lock);
+
+ u = port_user[port];
+
+ disable_irq_nosync(irq);
+
+ if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
+ u->ring[EVTCHN_RING_MASK(u->ring_prod)] = port;
+ wmb(); /* Ensure ring contents visible */
+ if (u->ring_cons == u->ring_prod++) {
+ wake_up_interruptible(&u->evtchn_wait);
+ kill_fasync(&u->evtchn_async_queue,
+ SIGIO, POLL_IN);
+ }
+ } else {
+ u->ring_overflow = 1;
+ }
+
+ spin_unlock(&port_user_lock);
+
+ return IRQ_HANDLED;
+}
+
+static ssize_t evtchn_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int rc;
+ unsigned int c, p, bytes1 = 0, bytes2 = 0;
+ struct per_user_data *u = file->private_data;
+
+ /* Whole number of ports. */
+ count &= ~(sizeof(evtchn_port_t)-1);
+
+ if (count == 0)
+ return 0;
+
+ if (count > PAGE_SIZE)
+ count = PAGE_SIZE;
+
+ for (;;) {
+ mutex_lock(&u->ring_cons_mutex);
+
+ rc = -EFBIG;
+ if (u->ring_overflow)
+ goto unlock_out;
+
+ c = u->ring_cons;
+ p = u->ring_prod;
+ if (c != p)
+ break;
+
+ mutex_unlock(&u->ring_cons_mutex);
+
+ if (file->f_flags & O_NONBLOCK)
+ return -EAGAIN;
+
+ rc = wait_event_interruptible(u->evtchn_wait,
+ u->ring_cons != u->ring_prod);
+ if (rc)
+ return rc;
+ }
+
+ /* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
+ if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
+ bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+ sizeof(evtchn_port_t);
+ bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+ } else {
+ bytes1 = (p - c) * sizeof(evtchn_port_t);
+ bytes2 = 0;
+ }
+
+ /* Truncate chunks according to caller's maximum byte count. */
+ if (bytes1 > count) {
+ bytes1 = count;
+ bytes2 = 0;
+ } else if ((bytes1 + bytes2) > count) {
+ bytes2 = count - bytes1;
+ }
+
+ rc = -EFAULT;
+ rmb(); /* Ensure that we see the port before we copy it. */
+ if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+ ((bytes2 != 0) &&
+ copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
+ goto unlock_out;
+
+ u->ring_cons += (bytes1 + bytes2) / sizeof(evtchn_port_t);
+ rc = bytes1 + bytes2;
+
+ unlock_out:
+ mutex_unlock(&u->ring_cons_mutex);
+ return rc;
+}
+
+static ssize_t evtchn_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int rc, i;
+ evtchn_port_t *kbuf = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+ struct per_user_data *u = file->private_data;
+
+ if (kbuf == NULL)
+ return -ENOMEM;
+
+ /* Whole number of ports. */
+ count &= ~(sizeof(evtchn_port_t)-1);
+
+ rc = 0;
+ if (count == 0)
+ goto out;
+
+ if (count > PAGE_SIZE)
+ count = PAGE_SIZE;
+
+ rc = -EFAULT;
+ if (copy_from_user(kbuf, buf, count) != 0)
+ goto out;
+
+ spin_lock_irq(&port_user_lock);
+ for (i = 0; i < (count/sizeof(evtchn_port_t)); i++)
+ if ((kbuf[i] < NR_EVENT_CHANNELS) && (port_user[kbuf[i]] == u))
+ enable_irq(irq_from_evtchn(kbuf[i]));
+ spin_unlock_irq(&port_user_lock);
+
+ rc = count;
+
+ out:
+ free_page((unsigned long)kbuf);
+ return rc;
+}
+
+static int evtchn_bind_to_user(struct per_user_data *u, int port)
+{
+ int rc = 0;
+
+ /*
+ * Ports are never reused, so every caller should pass in a
+ * unique port.
+ *
+ * (Locking not necessary because we haven't registered the
+ * interrupt handler yet, and our caller has already
+ * serialized bind operations.)
+ */
+ BUG_ON(port_user[port] != NULL);
+ port_user[port] = u;
+
+ rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
+ u->name, (void *)(unsigned long)port);
+ if (rc >= 0)
+ rc = 0;
+
+ return rc;
+}
+
+static void evtchn_unbind_from_user(struct per_user_data *u, int port)
+{
+ int irq = irq_from_evtchn(port);
+
+ unbind_from_irqhandler(irq, (void *)(unsigned long)port);
+
+ /* make sure we unbind the irq handler before clearing the port */
+ barrier();
+
+ port_user[port] = NULL;
+}
+
+static long evtchn_ioctl(struct file *file,
+ unsigned int cmd, unsigned long arg)
+{
+ int rc;
+ struct per_user_data *u = file->private_data;
+ void __user *uarg = (void __user *) arg;
+
+ /* Prevent bind from racing with unbind */
+ mutex_lock(&u->bind_mutex);
+
+ switch (cmd) {
+ case IOCTL_EVTCHN_BIND_VIRQ: {
+ struct ioctl_evtchn_bind_virq bind;
+ struct evtchn_bind_virq bind_virq;
+
+ rc = -EFAULT;
+ if (copy_from_user(&bind, uarg, sizeof(bind)))
+ break;
+
+ bind_virq.virq = bind.virq;
+ bind_virq.vcpu = 0;
+ rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+ &bind_virq);
+ if (rc != 0)
+ break;
+
+ rc = evtchn_bind_to_user(u, bind_virq.port);
+ if (rc == 0)
+ rc = bind_virq.port;
+ break;
+ }
+
+ case IOCTL_EVTCHN_BIND_INTERDOMAIN: {
+ struct ioctl_evtchn_bind_interdomain bind;
+ struct evtchn_bind_interdomain bind_interdomain;
+
+ rc = -EFAULT;
+ if (copy_from_user(&bind, uarg, sizeof(bind)))
+ break;
+
+ bind_interdomain.remote_dom = bind.remote_domain;
+ bind_interdomain.remote_port = bind.remote_port;
+ rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+ &bind_interdomain);
+ if (rc != 0)
+ break;
+
+ rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
+ if (rc == 0)
+ rc = bind_interdomain.local_port;
+ break;
+ }
+
+ case IOCTL_EVTCHN_BIND_UNBOUND_PORT: {
+ struct ioctl_evtchn_bind_unbound_port bind;
+ struct evtchn_alloc_unbound alloc_unbound;
+
+ rc = -EFAULT;
+ if (copy_from_user(&bind, uarg, sizeof(bind)))
+ break;
+
+ alloc_unbound.dom = DOMID_SELF;
+ alloc_unbound.remote_dom = bind.remote_domain;
+ rc = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+ &alloc_unbound);
+ if (rc != 0)
+ break;
+
+ rc = evtchn_bind_to_user(u, alloc_unbound.port);
+ if (rc == 0)
+ rc = alloc_unbound.port;
+ break;
+ }
+
+ case IOCTL_EVTCHN_UNBIND: {
+ struct ioctl_evtchn_unbind unbind;
+
+ rc = -EFAULT;
+ if (copy_from_user(&unbind, uarg, sizeof(unbind)))
+ break;
+
+ rc = -EINVAL;
+ if (unbind.port >= NR_EVENT_CHANNELS)
+ break;
+
+ spin_lock_irq(&port_user_lock);
+
+ rc = -ENOTCONN;
+ if (port_user[unbind.port] != u) {
+ spin_unlock_irq(&port_user_lock);
+ break;
+ }
+
+ evtchn_unbind_from_user(u, unbind.port);
+
+ spin_unlock_irq(&port_user_lock);
+
+ rc = 0;
+ break;
+ }
+
+ case IOCTL_EVTCHN_NOTIFY: {
+ struct ioctl_evtchn_notify notify;
+
+ rc = -EFAULT;
+ if (copy_from_user(¬ify, uarg, sizeof(notify)))
+ break;
+
+ if (notify.port >= NR_EVENT_CHANNELS) {
+ rc = -EINVAL;
+ } else if (port_user[notify.port] != u) {
+ rc = -ENOTCONN;
+ } else {
+ notify_remote_via_evtchn(notify.port);
+ rc = 0;
+ }
+ break;
+ }
+
+ case IOCTL_EVTCHN_RESET: {
+ /* Initialise the ring to empty. Clear errors. */
+ mutex_lock(&u->ring_cons_mutex);
+ spin_lock_irq(&port_user_lock);
+ u->ring_cons = u->ring_prod = u->ring_overflow = 0;
+ spin_unlock_irq(&port_user_lock);
+ mutex_unlock(&u->ring_cons_mutex);
+ rc = 0;
+ break;
+ }
+
+ default:
+ rc = -ENOSYS;
+ break;
+ }
+ mutex_unlock(&u->bind_mutex);
+
+ return rc;
+}
+
+static unsigned int evtchn_poll(struct file *file, poll_table *wait)
+{
+ unsigned int mask = POLLOUT | POLLWRNORM;
+ struct per_user_data *u = file->private_data;
+
+ poll_wait(file, &u->evtchn_wait, wait);
+ if (u->ring_cons != u->ring_prod)
+ mask |= POLLIN | POLLRDNORM;
+ if (u->ring_overflow)
+ mask = POLLERR;
+ return mask;
+}
+
+static int evtchn_fasync(int fd, struct file *filp, int on)
+{
+ struct per_user_data *u = filp->private_data;
+ return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
+}
+
+static int evtchn_open(struct inode *inode, struct file *filp)
+{
+ struct per_user_data *u;
+
+ u = kzalloc(sizeof(*u), GFP_KERNEL);
+ if (u == NULL)
+ return -ENOMEM;
+
+ u->name = kasprintf(GFP_KERNEL, "evtchn:%s", current->comm);
+ if (u->name == NULL) {
+ kfree(u);
+ return -ENOMEM;
+ }
+
+ init_waitqueue_head(&u->evtchn_wait);
+
+ u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+ if (u->ring == NULL) {
+ kfree(u->name);
+ kfree(u);
+ return -ENOMEM;
+ }
+
+ mutex_init(&u->bind_mutex);
+ mutex_init(&u->ring_cons_mutex);
+
+ filp->private_data = u;
+
+ return 0;
+}
+
+static int evtchn_release(struct inode *inode, struct file *filp)
+{
+ int i;
+ struct per_user_data *u = filp->private_data;
+
+ spin_lock_irq(&port_user_lock);
+
+ free_page((unsigned long)u->ring);
+
+ for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+ if (port_user[i] != u)
+ continue;
+
+ evtchn_unbind_from_user(port_user[i], i);
+ }
+
+ spin_unlock_irq(&port_user_lock);
+
+ kfree(u->name);
+ kfree(u);
+
+ return 0;
+}
+
+static const struct file_operations evtchn_fops = {
+ .owner = THIS_MODULE,
+ .read = evtchn_read,
+ .write = evtchn_write,
+ .unlocked_ioctl = evtchn_ioctl,
+ .poll = evtchn_poll,
+ .fasync = evtchn_fasync,
+ .open = evtchn_open,
+ .release = evtchn_release,
+};
+
+static struct miscdevice evtchn_miscdev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "evtchn",
+ .fops = &evtchn_fops,
+};
+static int __init evtchn_init(void)
+{
+ int err;
+
+ if (!xen_domain())
+ return -ENODEV;
+
+ spin_lock_init(&port_user_lock);
+ memset(port_user, 0, sizeof(port_user));
+
+ /* Create '/dev/misc/evtchn'. */
+ err = misc_register(&evtchn_miscdev);
+ if (err != 0) {
+ printk(KERN_ALERT "Could not register /dev/misc/evtchn\n");
+ return err;
+ }
+
+ printk(KERN_INFO "Event-channel device installed.\n");
+
+ return 0;
+}
+
+static void __exit evtchn_cleanup(void)
+{
+ misc_deregister(&evtchn_miscdev);
+}
+
+module_init(evtchn_init);
+module_exit(evtchn_cleanup);
+
+MODULE_LICENSE("GPL");
goto out;
}
- printk("suspending xenbus...\n");
- /* XXX use normal device tree? */
- xenbus_suspend();
+ printk(KERN_DEBUG "suspending xenstore...\n");
+ xs_suspend();
err = device_power_down(PMSG_SUSPEND);
if (err) {
if (!cancelled) {
xen_arch_resume();
- xenbus_resume();
+ xs_resume();
} else
- xenbus_suspend_cancel();
+ xs_suspend_cancel();
device_power_up(PMSG_RESUME);
--- /dev/null
+/*
+ * copyright (c) 2006 IBM Corporation
+ * Authored by: Mike D. Day <ncmike@us.ibm.com>
+ *
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xenbus.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+
+#define HYPERVISOR_ATTR_RO(_name) \
+static struct hyp_sysfs_attr _name##_attr = __ATTR_RO(_name)
+
+#define HYPERVISOR_ATTR_RW(_name) \
+static struct hyp_sysfs_attr _name##_attr = \
+ __ATTR(_name, 0644, _name##_show, _name##_store)
+
+struct hyp_sysfs_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct hyp_sysfs_attr *, char *);
+ ssize_t (*store)(struct hyp_sysfs_attr *, const char *, size_t);
+ void *hyp_attr_data;
+};
+
+static ssize_t type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ return sprintf(buffer, "xen\n");
+}
+
+HYPERVISOR_ATTR_RO(type);
+
+static int __init xen_sysfs_type_init(void)
+{
+ return sysfs_create_file(hypervisor_kobj, &type_attr.attr);
+}
+
+static void xen_sysfs_type_destroy(void)
+{
+ sysfs_remove_file(hypervisor_kobj, &type_attr.attr);
+}
+
+/* xen version attributes */
+static ssize_t major_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+ if (version)
+ return sprintf(buffer, "%d\n", version >> 16);
+ return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(major);
+
+static ssize_t minor_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+ if (version)
+ return sprintf(buffer, "%d\n", version & 0xff);
+ return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(minor);
+
+static ssize_t extra_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret = -ENOMEM;
+ char *extra;
+
+ extra = kmalloc(XEN_EXTRAVERSION_LEN, GFP_KERNEL);
+ if (extra) {
+ ret = HYPERVISOR_xen_version(XENVER_extraversion, extra);
+ if (!ret)
+ ret = sprintf(buffer, "%s\n", extra);
+ kfree(extra);
+ }
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(extra);
+
+static struct attribute *version_attrs[] = {
+ &major_attr.attr,
+ &minor_attr.attr,
+ &extra_attr.attr,
+ NULL
+};
+
+static struct attribute_group version_group = {
+ .name = "version",
+ .attrs = version_attrs,
+};
+
+static int __init xen_sysfs_version_init(void)
+{
+ return sysfs_create_group(hypervisor_kobj, &version_group);
+}
+
+static void xen_sysfs_version_destroy(void)
+{
+ sysfs_remove_group(hypervisor_kobj, &version_group);
+}
+
+/* UUID */
+
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ char *vm, *val;
+ int ret;
+ extern int xenstored_ready;
+
+ if (!xenstored_ready)
+ return -EBUSY;
+
+ vm = xenbus_read(XBT_NIL, "vm", "", NULL);
+ if (IS_ERR(vm))
+ return PTR_ERR(vm);
+ val = xenbus_read(XBT_NIL, vm, "uuid", NULL);
+ kfree(vm);
+ if (IS_ERR(val))
+ return PTR_ERR(val);
+ ret = sprintf(buffer, "%s\n", val);
+ kfree(val);
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(uuid);
+
+static int __init xen_sysfs_uuid_init(void)
+{
+ return sysfs_create_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+static void xen_sysfs_uuid_destroy(void)
+{
+ sysfs_remove_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+/* xen compilation attributes */
+
+static ssize_t compiler_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret = -ENOMEM;
+ struct xen_compile_info *info;
+
+ info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+ if (info) {
+ ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+ if (!ret)
+ ret = sprintf(buffer, "%s\n", info->compiler);
+ kfree(info);
+ }
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiler);
+
+static ssize_t compiled_by_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret = -ENOMEM;
+ struct xen_compile_info *info;
+
+ info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+ if (info) {
+ ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+ if (!ret)
+ ret = sprintf(buffer, "%s\n", info->compile_by);
+ kfree(info);
+ }
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiled_by);
+
+static ssize_t compile_date_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret = -ENOMEM;
+ struct xen_compile_info *info;
+
+ info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+ if (info) {
+ ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+ if (!ret)
+ ret = sprintf(buffer, "%s\n", info->compile_date);
+ kfree(info);
+ }
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(compile_date);
+
+static struct attribute *xen_compile_attrs[] = {
+ &compiler_attr.attr,
+ &compiled_by_attr.attr,
+ &compile_date_attr.attr,
+ NULL
+};
+
+static struct attribute_group xen_compilation_group = {
+ .name = "compilation",
+ .attrs = xen_compile_attrs,
+};
+
+int __init static xen_compilation_init(void)
+{
+ return sysfs_create_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+static void xen_compilation_destroy(void)
+{
+ sysfs_remove_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+/* xen properties info */
+
+static ssize_t capabilities_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret = -ENOMEM;
+ char *caps;
+
+ caps = kmalloc(XEN_CAPABILITIES_INFO_LEN, GFP_KERNEL);
+ if (caps) {
+ ret = HYPERVISOR_xen_version(XENVER_capabilities, caps);
+ if (!ret)
+ ret = sprintf(buffer, "%s\n", caps);
+ kfree(caps);
+ }
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(capabilities);
+
+static ssize_t changeset_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret = -ENOMEM;
+ char *cset;
+
+ cset = kmalloc(XEN_CHANGESET_INFO_LEN, GFP_KERNEL);
+ if (cset) {
+ ret = HYPERVISOR_xen_version(XENVER_changeset, cset);
+ if (!ret)
+ ret = sprintf(buffer, "%s\n", cset);
+ kfree(cset);
+ }
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(changeset);
+
+static ssize_t virtual_start_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret = -ENOMEM;
+ struct xen_platform_parameters *parms;
+
+ parms = kmalloc(sizeof(struct xen_platform_parameters), GFP_KERNEL);
+ if (parms) {
+ ret = HYPERVISOR_xen_version(XENVER_platform_parameters,
+ parms);
+ if (!ret)
+ ret = sprintf(buffer, "%lx\n", parms->virt_start);
+ kfree(parms);
+ }
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(virtual_start);
+
+static ssize_t pagesize_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ int ret;
+
+ ret = HYPERVISOR_xen_version(XENVER_pagesize, NULL);
+ if (ret > 0)
+ ret = sprintf(buffer, "%x\n", ret);
+
+ return ret;
+}
+
+HYPERVISOR_ATTR_RO(pagesize);
+
+static ssize_t xen_feature_show(int index, char *buffer)
+{
+ ssize_t ret;
+ struct xen_feature_info info;
+
+ info.submap_idx = index;
+ ret = HYPERVISOR_xen_version(XENVER_get_features, &info);
+ if (!ret)
+ ret = sprintf(buffer, "%08x", info.submap);
+
+ return ret;
+}
+
+static ssize_t features_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+ ssize_t len;
+ int i;
+
+ len = 0;
+ for (i = XENFEAT_NR_SUBMAPS-1; i >= 0; i--) {
+ int ret = xen_feature_show(i, buffer + len);
+ if (ret < 0) {
+ if (len == 0)
+ len = ret;
+ break;
+ }
+ len += ret;
+ }
+ if (len > 0)
+ buffer[len++] = '\n';
+
+ return len;
+}
+
+HYPERVISOR_ATTR_RO(features);
+
+static struct attribute *xen_properties_attrs[] = {
+ &capabilities_attr.attr,
+ &changeset_attr.attr,
+ &virtual_start_attr.attr,
+ &pagesize_attr.attr,
+ &features_attr.attr,
+ NULL
+};
+
+static struct attribute_group xen_properties_group = {
+ .name = "properties",
+ .attrs = xen_properties_attrs,
+};
+
+static int __init xen_properties_init(void)
+{
+ return sysfs_create_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static void xen_properties_destroy(void)
+{
+ sysfs_remove_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static int __init hyper_sysfs_init(void)
+{
+ int ret;
+
+ if (!xen_domain())
+ return -ENODEV;
+
+ ret = xen_sysfs_type_init();
+ if (ret)
+ goto out;
+ ret = xen_sysfs_version_init();
+ if (ret)
+ goto version_out;
+ ret = xen_compilation_init();
+ if (ret)
+ goto comp_out;
+ ret = xen_sysfs_uuid_init();
+ if (ret)
+ goto uuid_out;
+ ret = xen_properties_init();
+ if (ret)
+ goto prop_out;
+
+ goto out;
+
+prop_out:
+ xen_sysfs_uuid_destroy();
+uuid_out:
+ xen_compilation_destroy();
+comp_out:
+ xen_sysfs_version_destroy();
+version_out:
+ xen_sysfs_type_destroy();
+out:
+ return ret;
+}
+
+static void __exit hyper_sysfs_exit(void)
+{
+ xen_properties_destroy();
+ xen_compilation_destroy();
+ xen_sysfs_uuid_destroy();
+ xen_sysfs_version_destroy();
+ xen_sysfs_type_destroy();
+
+}
+module_init(hyper_sysfs_init);
+module_exit(hyper_sysfs_exit);
+
+static ssize_t hyp_sysfs_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buffer)
+{
+ struct hyp_sysfs_attr *hyp_attr;
+ hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+ if (hyp_attr->show)
+ return hyp_attr->show(hyp_attr, buffer);
+ return 0;
+}
+
+static ssize_t hyp_sysfs_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer,
+ size_t len)
+{
+ struct hyp_sysfs_attr *hyp_attr;
+ hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+ if (hyp_attr->store)
+ return hyp_attr->store(hyp_attr, buffer, len);
+ return 0;
+}
+
+static struct sysfs_ops hyp_sysfs_ops = {
+ .show = hyp_sysfs_show,
+ .store = hyp_sysfs_store,
+};
+
+static struct kobj_type hyp_sysfs_kobj_type = {
+ .sysfs_ops = &hyp_sysfs_ops,
+};
+
+static int __init hypervisor_subsys_init(void)
+{
+ if (!xen_domain())
+ return -ENODEV;
+
+ hypervisor_kobj->ktype = &hyp_sysfs_kobj_type;
+ return 0;
+}
+device_initcall(hypervisor_subsys_init);
static void xenbus_dev_shutdown(struct device *_dev);
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state);
+static int xenbus_dev_resume(struct device *dev);
+
/* If something in array of ids matches this device, return it. */
static const struct xenbus_device_id *
match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev)
.remove = xenbus_dev_remove,
.shutdown = xenbus_dev_shutdown,
.dev_attrs = xenbus_dev_attrs,
+
+ .suspend = xenbus_dev_suspend,
+ .resume = xenbus_dev_resume,
},
};
kfree(root);
}
+EXPORT_SYMBOL_GPL(xenbus_dev_changed);
static void frontend_changed(struct xenbus_watch *watch,
const char **vec, unsigned int len)
.callback = frontend_changed,
};
-static int suspend_dev(struct device *dev, void *data)
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state)
{
int err = 0;
struct xenbus_driver *drv;
drv = to_xenbus_driver(dev->driver);
xdev = container_of(dev, struct xenbus_device, dev);
if (drv->suspend)
- err = drv->suspend(xdev);
+ err = drv->suspend(xdev, state);
if (err)
printk(KERN_WARNING
"xenbus: suspend %s failed: %i\n", dev_name(dev), err);
return 0;
}
-static int suspend_cancel_dev(struct device *dev, void *data)
-{
- int err = 0;
- struct xenbus_driver *drv;
- struct xenbus_device *xdev;
-
- DPRINTK("");
-
- if (dev->driver == NULL)
- return 0;
- drv = to_xenbus_driver(dev->driver);
- xdev = container_of(dev, struct xenbus_device, dev);
- if (drv->suspend_cancel)
- err = drv->suspend_cancel(xdev);
- if (err)
- printk(KERN_WARNING
- "xenbus: suspend_cancel %s failed: %i\n",
- dev_name(dev), err);
- return 0;
-}
-
-static int resume_dev(struct device *dev, void *data)
+static int xenbus_dev_resume(struct device *dev)
{
int err;
struct xenbus_driver *drv;
return 0;
}
-void xenbus_suspend(void)
-{
- DPRINTK("");
-
- bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_dev);
- xenbus_backend_suspend(suspend_dev);
- xs_suspend();
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend);
-
-void xenbus_resume(void)
-{
- xb_init_comms();
- xs_resume();
- bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, resume_dev);
- xenbus_backend_resume(resume_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_resume);
-
-void xenbus_suspend_cancel(void)
-{
- xs_suspend_cancel();
- bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_cancel_dev);
- xenbus_backend_resume(suspend_cancel_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend_cancel);
-
/* A flag to determine if xenstored is 'ready' (i.e. has started) */
int xenstored_ready = 0;
struct xenbus_watch *watch;
char token[sizeof(watch) * 2 + 1];
+ xb_init_comms();
+
mutex_unlock(&xs_state.response_mutex);
mutex_unlock(&xs_state.request_mutex);
up_write(&xs_state.transaction_mutex);
MODULE_DESCRIPTION("Xen filesystem");
MODULE_LICENSE("GPL");
+static ssize_t capabilities_read(struct file *file, char __user *buf,
+ size_t size, loff_t *off)
+{
+ char *tmp = "";
+
+ if (xen_initial_domain())
+ tmp = "control_d\n";
+
+ return simple_read_from_buffer(buf, size, off, tmp, strlen(tmp));
+}
+
+static const struct file_operations capabilities_file_ops = {
+ .read = capabilities_read,
+};
+
static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
{
static struct tree_descr xenfs_files[] = {
- [2] = {"xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR},
+ [1] = {},
+ { "xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR },
+ { "capabilities", &capabilities_file_ops, S_IRUGO },
{""},
};
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <linux/blktrace_api.h>
-#include <trace/block.h>
#include <scsi/sg.h> /* for struct sg_iovec */
-DEFINE_TRACE(block_split);
+#include <trace/events/block.h>
/*
* Test patch to inline a certain number of bi_io_vec's inside the bio
BUG_ON(!buffer_locked(bh));
BUG_ON(!buffer_mapped(bh));
BUG_ON(!bh->b_end_io);
+ BUG_ON(buffer_delay(bh));
+ BUG_ON(buffer_unwritten(bh));
/*
* Mask in barrier bit for a write (could be either a WRITE or a
+Version 1.59
+------------
+Client uses server inode numbers (which are persistent) rather than
+client generated ones by default (mount option "serverino" turned
+on by default if server supports it). Add forceuid and forcegid
+mount options (so that when negotiating unix extensions specifying
+which uid mounted does not immediately force the server's reported
+uids to be overridden).
+
Version 1.58
------------
Guard against buffer overruns in various UCS-2 to UTF-8 string conversions
session setup to distinguish multiple mounts to same server from different
userids. Raw NTLMSSP fixed (it requires /proc/fs/cifs/experimental
flag to be set to 2, and mount must enable krb5 to turn on extended security).
+Performance of file create to Samba improved (posix create on lookup
+removes 1 of 2 network requests sent on file create)
Version 1.57
------------
mount.
domain Set the SMB/CIFS workgroup name prepended to the
username during CIFS session establishment
- uid Set the default uid for inodes. For mounts to servers
+ forceuid Set the default uid for inodes based on the uid
+ passed in. For mounts to servers
which do support the CIFS Unix extensions, such as a
properly configured Samba server, the server provides
the uid, gid and mode so this parameter should not be
the client. Note that the mount.cifs helper must be
at version 1.10 or higher to support specifying the uid
(or gid) in non-numeric form.
+ forcegid (similar to above but for the groupid instead of uid)
+ uid Set the default uid for inodes, and indicate to the
+ cifs kernel driver which local user mounted . If the server
+ supports the unix extensions the default uid is
+ not used to fill in the owner fields of inodes (files)
+ unless the "forceuid" parameter is specified.
gid Set the default gid for inodes (similar to above).
file_mode If CIFS Unix extensions are not supported by the server
this overrides the default mode for file inodes.
or the CIFS Unix Extensions equivalent and for those
this mount option will have no effect. Exporting cifs mounts
under nfsd requires this mount option on the cifs mount.
+ This is now the default if server supports the
+ required network operation.
noserverino Client generates inode numbers (rather than using the actual one
- from the server) by default.
+ from the server). These inode numbers will vary after
+ unmount or reboot which can confuse some applications,
+ but not all server filesystems support unique inode
+ numbers.
setuids If the CIFS Unix extensions are negotiated with the server
the client will attempt to set the effective uid and gid of
the local process on newly created files, directories, and
#include <linux/string.h>
#include <keys/user-type.h>
#include <linux/key-type.h>
+#include <linux/inet.h>
#include "cifsglob.h"
#include "cifs_spnego.h"
#include "cifs_debug.h"
* strlen(";sec=ntlmsspi") */
#define MAX_MECH_STR_LEN 13
-/* max possible addr len eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/128 */
-#define MAX_IPV6_ADDR_LEN 43
-
/* strlen of "host=" */
#define HOST_KEY_LEN 5
host=hostname sec=mechanism uid=0xFF user=username */
desc_len = MAX_VER_STR_LEN +
HOST_KEY_LEN + strlen(hostname) +
- IP_KEY_LEN + MAX_IPV6_ADDR_LEN +
+ IP_KEY_LEN + INET6_ADDRSTRLEN +
MAX_MECH_STR_LEN +
UID_KEY_LEN + (sizeof(uid_t) * 2) +
USER_KEY_LEN + strlen(sesInfo->userName) + 1;
return rc;
}
-
-/* Retrieve an ACL from the server */
-static struct cifs_ntsd *get_cifs_acl(u32 *pacllen, struct inode *inode,
- const char *path, const __u16 *pfid)
+static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
+ __u16 fid, u32 *pacllen)
{
- struct cifsFileInfo *open_file = NULL;
- bool unlock_file = false;
- int xid;
- int rc = -EIO;
- __u16 fid;
- struct super_block *sb;
- struct cifs_sb_info *cifs_sb;
struct cifs_ntsd *pntsd = NULL;
+ int xid, rc;
+
+ xid = GetXid();
+ rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen);
+ FreeXid(xid);
- cFYI(1, ("get mode from ACL for %s", path));
- if (inode == NULL)
- return NULL;
+ cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen));
+ return pntsd;
+}
+
+static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
+ const char *path, u32 *pacllen)
+{
+ struct cifs_ntsd *pntsd = NULL;
+ int oplock = 0;
+ int xid, rc;
+ __u16 fid;
xid = GetXid();
- if (pfid == NULL)
- open_file = find_readable_file(CIFS_I(inode));
- else
- fid = *pfid;
- sb = inode->i_sb;
- if (sb == NULL) {
- FreeXid(xid);
- return NULL;
- }
- cifs_sb = CIFS_SB(sb);
-
- if (open_file) {
- unlock_file = true;
- fid = open_file->netfid;
- } else if (pfid == NULL) {
- int oplock = 0;
- /* open file */
- rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN,
- READ_CONTROL, 0, &fid, &oplock, NULL,
- cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
- if (rc != 0) {
- cERROR(1, ("Unable to open file to get ACL"));
- FreeXid(xid);
- return NULL;
- }
+ rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, READ_CONTROL, 0,
+ &fid, &oplock, NULL, cifs_sb->local_nls,
+ cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (rc) {
+ cERROR(1, ("Unable to open file to get ACL"));
+ goto out;
}
rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen);
cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen));
- if (unlock_file == true) /* find_readable_file increments ref count */
- atomic_dec(&open_file->wrtPending);
- else if (pfid == NULL) /* if opened above we have to close the handle */
- CIFSSMBClose(xid, cifs_sb->tcon, fid);
- /* else handle was passed in by caller */
+ CIFSSMBClose(xid, cifs_sb->tcon, fid);
+ out:
FreeXid(xid);
return pntsd;
}
-/* Set an ACL on the server */
-static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
- struct inode *inode, const char *path)
+/* Retrieve an ACL from the server */
+static struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
+ struct inode *inode, const char *path,
+ u32 *pacllen)
{
- struct cifsFileInfo *open_file;
- bool unlock_file = false;
- int xid;
- int rc = -EIO;
- __u16 fid;
- struct super_block *sb;
- struct cifs_sb_info *cifs_sb;
+ struct cifs_ntsd *pntsd = NULL;
+ struct cifsFileInfo *open_file = NULL;
- cFYI(DBG2, ("set ACL for %s from mode 0x%x", path, inode->i_mode));
+ if (inode)
+ open_file = find_readable_file(CIFS_I(inode));
+ if (!open_file)
+ return get_cifs_acl_by_path(cifs_sb, path, pacllen);
- if (!inode)
- return rc;
+ pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->netfid, pacllen);
+ atomic_dec(&open_file->wrtPending);
+ return pntsd;
+}
- sb = inode->i_sb;
- if (sb == NULL)
- return rc;
+static int set_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, __u16 fid,
+ struct cifs_ntsd *pnntsd, u32 acllen)
+{
+ int xid, rc;
- cifs_sb = CIFS_SB(sb);
xid = GetXid();
+ rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen);
+ FreeXid(xid);
- open_file = find_readable_file(CIFS_I(inode));
- if (open_file) {
- unlock_file = true;
- fid = open_file->netfid;
- } else {
- int oplock = 0;
- /* open file */
- rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN,
- WRITE_DAC, 0, &fid, &oplock, NULL,
- cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
- if (rc != 0) {
- cERROR(1, ("Unable to open file to set ACL"));
- FreeXid(xid);
- return rc;
- }
+ cFYI(DBG2, ("SetCIFSACL rc = %d", rc));
+ return rc;
+}
+
+static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path,
+ struct cifs_ntsd *pnntsd, u32 acllen)
+{
+ int oplock = 0;
+ int xid, rc;
+ __u16 fid;
+
+ xid = GetXid();
+
+ rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, WRITE_DAC, 0,
+ &fid, &oplock, NULL, cifs_sb->local_nls,
+ cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (rc) {
+ cERROR(1, ("Unable to open file to set ACL"));
+ goto out;
}
rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen);
cFYI(DBG2, ("SetCIFSACL rc = %d", rc));
- if (unlock_file)
- atomic_dec(&open_file->wrtPending);
- else
- CIFSSMBClose(xid, cifs_sb->tcon, fid);
+ CIFSSMBClose(xid, cifs_sb->tcon, fid);
+ out:
FreeXid(xid);
+ return rc;
+}
+/* Set an ACL on the server */
+static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
+ struct inode *inode, const char *path)
+{
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct cifsFileInfo *open_file;
+ int rc;
+
+ cFYI(DBG2, ("set ACL for %s from mode 0x%x", path, inode->i_mode));
+
+ open_file = find_readable_file(CIFS_I(inode));
+ if (!open_file)
+ return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
+
+ rc = set_cifs_acl_by_fid(cifs_sb, open_file->netfid, pnntsd, acllen);
+ atomic_dec(&open_file->wrtPending);
return rc;
}
/* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
-void acl_to_uid_mode(struct inode *inode, const char *path, const __u16 *pfid)
+void acl_to_uid_mode(struct cifs_sb_info *cifs_sb, struct inode *inode,
+ const char *path, const __u16 *pfid)
{
struct cifs_ntsd *pntsd = NULL;
u32 acllen = 0;
int rc = 0;
cFYI(DBG2, ("converting ACL to mode for %s", path));
- pntsd = get_cifs_acl(&acllen, inode, path, pfid);
+
+ if (pfid)
+ pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen);
+ else
+ pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen);
/* if we can retrieve the ACL, now parse Access Control Entries, ACEs */
if (pntsd)
cFYI(DBG2, ("set ACL from mode for %s", path));
/* Get the security descriptor */
- pntsd = get_cifs_acl(&secdesclen, inode, path, NULL);
+ pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
/* Add three ACEs for owner, group, everyone getting rid of
other ACEs as chmod disables ACEs and set the security descriptor */
#endif
sb->s_blocksize = CIFS_MAX_MSGSIZE;
sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */
- inode = cifs_iget(sb, ROOT_I);
+ inode = cifs_root_iget(sb, ROOT_I);
if (IS_ERR(inode)) {
rc = PTR_ERR(inode);
/* Functions related to inodes */
extern const struct inode_operations cifs_dir_inode_ops;
-extern struct inode *cifs_iget(struct super_block *, unsigned long);
+extern struct inode *cifs_root_iget(struct super_block *, unsigned long);
extern int cifs_create(struct inode *, struct dentry *, int,
struct nameidata *);
extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
extern const struct export_operations cifs_export_ops;
#endif /* EXPERIMENTAL */
-#define CIFS_VERSION "1.58"
+#define CIFS_VERSION "1.59"
#endif /* _CIFSFS_H */
struct cifsTconInfo *);
extern void DeleteOplockQEntry(struct oplock_q_entry *);
extern void DeleteTconOplockQEntries(struct cifsTconInfo *);
-extern struct timespec cifs_NTtimeToUnix(u64 utc_nanoseconds_since_1601);
+extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
extern u64 cifs_UnixTimeToNT(struct timespec);
-extern __le64 cnvrtDosCifsTm(__u16 date, __u16 time);
-extern struct timespec cnvrtDosUnixTm(__u16 date, __u16 time);
+extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
+ int offset);
extern int cifs_posix_open(char *full_path, struct inode **pinode,
struct super_block *sb, int mode, int oflags,
extern int cifs_get_inode_info_unix(struct inode **pinode,
const unsigned char *search_path,
struct super_block *sb, int xid);
-extern void acl_to_uid_mode(struct inode *inode, const char *path,
- const __u16 *pfid);
+extern void acl_to_uid_mode(struct cifs_sb_info *cifs_sb, struct inode *inode,
+ const char *path, const __u16 *pfid);
extern int mode_to_acl(struct inode *inode, const char *path, __u64);
extern int cifs_mount(struct super_block *, struct cifs_sb_info *, char *,
int val, seconds, remain, result;
struct timespec ts, utc;
utc = CURRENT_TIME;
- ts = cnvrtDosUnixTm(le16_to_cpu(rsp->SrvTime.Date),
- le16_to_cpu(rsp->SrvTime.Time));
+ ts = cnvrtDosUnixTm(rsp->SrvTime.Date,
+ rsp->SrvTime.Time, 0);
cFYI(1, ("SrvTime %d sec since 1970 (utc: %d) diff: %d",
(int)ts.tv_sec, (int)utc.tv_sec,
(int)(utc.tv_sec - ts.tv_sec)));
params = 2 /* level */ + 4 /* rsrvd */ + name_len /* incl null */ ;
pSMB->TotalDataCount = 0;
pSMB->MaxParameterCount = cpu_to_le16(2);
- /* BB find exact max data count below from sess structure BB */
- pSMB->MaxDataCount = cpu_to_le16(4000);
+ pSMB->MaxDataCount = cpu_to_le16(CIFSMaxBufSize);
pSMB->MaxSetupCount = 0;
pSMB->Reserved = 0;
pSMB->Flags = 0;
#include <linux/namei.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
+#include <linux/inet.h>
#include <net/ipv6.h>
#include "cifspdu.h"
#include "cifsglob.h"
char *domainname;
char *UNC;
char *UNCip;
- char *in6_addr; /* ipv6 address as human readable form of in6_addr */
char *iocharset; /* local code page for mapping to and from Unicode */
char source_rfc1001_name[16]; /* netbios name of client */
char target_rfc1001_name[16]; /* netbios name of server for Win9x/ME */
vol->target_rfc1001_name[0] = 0;
vol->linux_uid = current_uid(); /* use current_euid() instead? */
vol->linux_gid = current_gid();
- vol->dir_mode = S_IRWXUGO;
- /* 2767 perms indicate mandatory locking support */
- vol->file_mode = (S_IRWXUGO | S_ISGID) & (~S_IXGRP);
+
+ /* default to only allowing write access to owner of the mount */
+ vol->dir_mode = vol->file_mode = S_IRUGO | S_IXUGO | S_IWUSR;
/* vol->retry default is 0 (i.e. "soft" limited retry not hard retry) */
vol->rw = true;
/* default is always to request posix paths. */
vol->posix_paths = 1;
+ /* default to using server inode numbers where available */
+ vol->server_ino = 1;
if (!options)
return 1;
}
strcpy(vol->password, value);
}
- } else if (strnicmp(data, "ip", 2) == 0) {
+ } else if (!strnicmp(data, "ip", 2) ||
+ !strnicmp(data, "addr", 4)) {
if (!value || !*value) {
vol->UNCip = NULL;
- } else if (strnlen(value, 35) < 35) {
+ } else if (strnlen(value, INET6_ADDRSTRLEN) <
+ INET6_ADDRSTRLEN) {
vol->UNCip = value;
} else {
printk(KERN_WARNING "CIFS: ip address "
return 1;
}
} else if (strnicmp(data, "uid", 3) == 0) {
- if (value && *value) {
+ if (value && *value)
vol->linux_uid =
simple_strtoul(value, &value, 0);
+ } else if (strnicmp(data, "forceuid", 8) == 0) {
vol->override_uid = 1;
- }
} else if (strnicmp(data, "gid", 3) == 0) {
- if (value && *value) {
+ if (value && *value)
vol->linux_gid =
simple_strtoul(value, &value, 0);
+ } else if (strnicmp(data, "forcegid", 8) == 0) {
vol->override_gid = 1;
- }
} else if (strnicmp(data, "file_mode", 4) == 0) {
if (value && *value) {
vol->file_mode =
vol->direct_io = 1;
} else if (strnicmp(data, "forcedirectio", 13) == 0) {
vol->direct_io = 1;
- } else if (strnicmp(data, "in6_addr", 8) == 0) {
- if (!value || !*value) {
- vol->in6_addr = NULL;
- } else if (strnlen(value, 49) == 48) {
- vol->in6_addr = value;
- } else {
- printk(KERN_WARNING "CIFS: ip v6 address not "
- "48 characters long\n");
- return 1;
- }
} else if (strnicmp(data, "noac", 4) == 0) {
printk(KERN_WARNING "CIFS: Mount option noac not "
"supported. Instead set "
/* BB need same check in cifs_create too? */
/* if not oplocked, invalidate inode pages if mtime or file
size changed */
- temp = cifs_NTtimeToUnix(le64_to_cpu(buf->LastWriteTime));
+ temp = cifs_NTtimeToUnix(buf->LastWriteTime);
if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) &&
(file->f_path.dentry->d_inode->i_size ==
(loff_t)le64_to_cpu(buf->EndOfFile))) {
__u64 num_of_bytes = le64_to_cpu(info->NumOfBytes);
__u64 end_of_file = le64_to_cpu(info->EndOfFile);
- inode->i_atime = cifs_NTtimeToUnix(le64_to_cpu(info->LastAccessTime));
+ inode->i_atime = cifs_NTtimeToUnix(info->LastAccessTime);
inode->i_mtime =
- cifs_NTtimeToUnix(le64_to_cpu(info->LastModificationTime));
- inode->i_ctime = cifs_NTtimeToUnix(le64_to_cpu(info->LastStatusChange));
+ cifs_NTtimeToUnix(info->LastModificationTime);
+ inode->i_ctime = cifs_NTtimeToUnix(info->LastStatusChange);
inode->i_mode = le64_to_cpu(info->Permissions);
/*
/* Linux can not store file creation time so ignore it */
if (pfindData->LastAccessTime)
- inode->i_atime = cifs_NTtimeToUnix
- (le64_to_cpu(pfindData->LastAccessTime));
+ inode->i_atime = cifs_NTtimeToUnix(pfindData->LastAccessTime);
else /* do not need to use current_fs_time - time not stored */
inode->i_atime = CURRENT_TIME;
- inode->i_mtime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime));
- inode->i_ctime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime));
+ inode->i_mtime = cifs_NTtimeToUnix(pfindData->LastWriteTime);
+ inode->i_ctime = cifs_NTtimeToUnix(pfindData->ChangeTime);
cFYI(DBG2, ("Attributes came in as 0x%x", attr));
if (adjustTZ && (pTcon->ses) && (pTcon->ses->server)) {
inode->i_ctime.tv_sec += pTcon->ses->server->timeAdj;
/* fill in 0777 bits from ACL */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
cFYI(1, ("Getting mode bits from ACL"));
- acl_to_uid_mode(inode, full_path, pfid);
+ acl_to_uid_mode(cifs_sb, inode, full_path, pfid);
}
#endif
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
}
/* gets root inode */
-struct inode *cifs_iget(struct super_block *sb, unsigned long ino)
+struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino)
{
int xid;
struct cifs_sb_info *cifs_sb;
#define NTFS_TIME_OFFSET ((u64)(369*365 + 89) * 24 * 3600 * 10000000)
- /*
- * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units)
- * into Unix UTC (based 1970-01-01, in seconds).
- */
+/*
+ * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units)
+ * into Unix UTC (based 1970-01-01, in seconds).
+ */
struct timespec
-cifs_NTtimeToUnix(u64 ntutc)
+cifs_NTtimeToUnix(__le64 ntutc)
{
struct timespec ts;
/* BB what about the timezone? BB */
/* Subtract the NTFS time offset, then convert to 1s intervals. */
u64 t;
- t = ntutc - NTFS_TIME_OFFSET;
+ t = le64_to_cpu(ntutc) - NTFS_TIME_OFFSET;
ts.tv_nsec = do_div(t, 10000000) * 100;
ts.tv_sec = t;
return ts;
static int total_days_of_prev_months[] =
{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334};
-
-__le64 cnvrtDosCifsTm(__u16 date, __u16 time)
-{
- return cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(date, time)));
-}
-
-struct timespec cnvrtDosUnixTm(__u16 date, __u16 time)
+struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
{
struct timespec ts;
int sec, min, days, month, year;
+ u16 date = le16_to_cpu(le_date);
+ u16 time = le16_to_cpu(le_time);
SMB_TIME *st = (SMB_TIME *)&time;
SMB_DATE *sd = (SMB_DATE *)&date;
days -= ((year & 0x03) == 0) && (month < 2 ? 1 : 0);
sec += 24 * 60 * 60 * days;
- ts.tv_sec = sec;
+ ts.tv_sec = sec + offset;
/* cFYI(1,("sec after cnvrt dos to unix time %d",sec)); */
return rc;
}
-static void AdjustForTZ(struct cifsTconInfo *tcon, struct inode *inode)
-{
- if ((tcon) && (tcon->ses) && (tcon->ses->server)) {
- inode->i_ctime.tv_sec += tcon->ses->server->timeAdj;
- inode->i_mtime.tv_sec += tcon->ses->server->timeAdj;
- inode->i_atime.tv_sec += tcon->ses->server->timeAdj;
- }
- return;
-}
-
-
static void fill_in_inode(struct inode *tmp_inode, int new_buf_type,
char *buf, unsigned int *pobject_type, int isNewInode)
{
allocation_size = le64_to_cpu(pfindData->AllocationSize);
end_of_file = le64_to_cpu(pfindData->EndOfFile);
tmp_inode->i_atime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime));
+ cifs_NTtimeToUnix(pfindData->LastAccessTime);
tmp_inode->i_mtime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime));
+ cifs_NTtimeToUnix(pfindData->LastWriteTime);
tmp_inode->i_ctime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime));
+ cifs_NTtimeToUnix(pfindData->ChangeTime);
} else { /* legacy, OS2 and DOS style */
-/* struct timespec ts;*/
+ int offset = cifs_sb->tcon->ses->server->timeAdj;
FIND_FILE_STANDARD_INFO *pfindData =
(FIND_FILE_STANDARD_INFO *)buf;
- tmp_inode->i_mtime = cnvrtDosUnixTm(
- le16_to_cpu(pfindData->LastWriteDate),
- le16_to_cpu(pfindData->LastWriteTime));
- tmp_inode->i_atime = cnvrtDosUnixTm(
- le16_to_cpu(pfindData->LastAccessDate),
- le16_to_cpu(pfindData->LastAccessTime));
- tmp_inode->i_ctime = cnvrtDosUnixTm(
- le16_to_cpu(pfindData->LastWriteDate),
- le16_to_cpu(pfindData->LastWriteTime));
- AdjustForTZ(cifs_sb->tcon, tmp_inode);
+ tmp_inode->i_mtime = cnvrtDosUnixTm(pfindData->LastWriteDate,
+ pfindData->LastWriteTime,
+ offset);
+ tmp_inode->i_atime = cnvrtDosUnixTm(pfindData->LastAccessDate,
+ pfindData->LastAccessTime,
+ offset);
+ tmp_inode->i_ctime = cnvrtDosUnixTm(pfindData->LastWriteDate,
+ pfindData->LastWriteTime,
+ offset);
attr = le16_to_cpu(pfindData->Attributes);
allocation_size = le32_to_cpu(pfindData->AllocationSize);
end_of_file = le32_to_cpu(pfindData->DataSize);
local_size = tmp_inode->i_size;
tmp_inode->i_atime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime));
+ cifs_NTtimeToUnix(pfindData->LastAccessTime);
tmp_inode->i_mtime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastModificationTime));
+ cifs_NTtimeToUnix(pfindData->LastModificationTime);
tmp_inode->i_ctime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastStatusChange));
+ cifs_NTtimeToUnix(pfindData->LastStatusChange);
tmp_inode->i_mode = le64_to_cpu(pfindData->Permissions);
/* since we set the inode type below we need to mask off type
if (!bprm)
goto out_files;
- retval = mutex_lock_interruptible(¤t->cred_exec_mutex);
+ retval = mutex_lock_interruptible(¤t->cred_guard_mutex);
if (retval < 0)
goto out_free;
current->in_execve = 1;
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
- mutex_unlock(¤t->cred_exec_mutex);
+ mutex_unlock(¤t->cred_guard_mutex);
acct_update_integrals(current);
free_bprm(bprm);
if (displaced)
out_unlock:
current->in_execve = 0;
- mutex_unlock(¤t->cred_exec_mutex);
+ mutex_unlock(¤t->cred_guard_mutex);
out_free:
free_bprm(bprm);
int err = register_filesystem(&devpts_fs_type);
if (!err) {
devpts_mnt = kern_mount(&devpts_fs_type);
- if (IS_ERR(devpts_mnt))
+ if (IS_ERR(devpts_mnt)) {
err = PTR_ERR(devpts_mnt);
+ unregister_filesystem(&devpts_fs_type);
+ }
}
return err;
}
commit_creds(bprm->cred);
bprm->cred = NULL;
- /* cred_exec_mutex must be held at least to this point to prevent
+ /* cred_guard_mutex must be held at least to this point to prevent
* ptrace_attach() from altering our determination of the task's
* credentials; any time after this it may be unlocked */
/*
* determine how safe it is to execute the proposed program
- * - the caller must hold current->cred_exec_mutex to protect against
+ * - the caller must hold current->cred_guard_mutex to protect against
* PTRACE_ATTACH
*/
int check_unsafe_exec(struct linux_binprm *bprm)
if (!bprm)
goto out_files;
- retval = mutex_lock_interruptible(¤t->cred_exec_mutex);
+ retval = mutex_lock_interruptible(¤t->cred_guard_mutex);
if (retval < 0)
goto out_free;
current->in_execve = 1;
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
- mutex_unlock(¤t->cred_exec_mutex);
+ mutex_unlock(¤t->cred_guard_mutex);
acct_update_integrals(current);
free_bprm(bprm);
if (displaced)
out_unlock:
current->in_execve = 0;
- mutex_unlock(¤t->cred_exec_mutex);
+ mutex_unlock(¤t->cred_guard_mutex);
out_free:
free_bprm(bprm);
brelse(bh);
failed_sbi:
sb->s_fs_info = NULL;
+ kfree(sbi->s_blockgroup_lock);
kfree(sbi);
return ret;
}
brelse(bh);
out_fail:
sb->s_fs_info = NULL;
+ kfree(sbi->s_blockgroup_lock);
kfree(sbi);
lock_kernel();
return ret;
obj-$(CONFIG_EXT4_FS) += ext4.o
ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
- ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
- ext4_jbd2.o migrate.o mballoc.o
+ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
+ ext4_jbd2.o migrate.o mballoc.o block_validity.o
ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
#include <linux/buffer_head.h>
#include "ext4.h"
#include "ext4_jbd2.h"
-#include "group.h"
#include "mballoc.h"
/*
ext4_group_t block_group, struct ext4_group_desc *gdp)
{
int bit, bit_max;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
unsigned free_blocks, group_blocks;
struct ext4_sb_info *sbi = EXT4_SB(sb);
bit_max += ext4_bg_num_gdb(sb, block_group);
}
- if (block_group == sbi->s_groups_count - 1) {
+ if (block_group == ngroups - 1) {
/*
* Even though mke2fs always initialize first and last group
* if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
le32_to_cpu(sbi->s_es->s_first_data_block) -
- (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1));
+ (EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
{
unsigned int group_desc;
unsigned int offset;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (block_group >= sbi->s_groups_count) {
+ if (block_group >= ngroups) {
ext4_error(sb, "ext4_get_group_desc",
"block_group >= groups_count - "
"block_group = %u, groups_count = %u",
- block_group, sbi->s_groups_count);
+ block_group, ngroups);
return NULL;
}
- smp_rmb();
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
unlock_buffer(bh);
return bh;
}
- spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_lock_group(sb, block_group);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
ext4_init_block_bitmap(sb, bh, block_group, desc);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
return bh;
}
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_unlock_group(sb, block_group);
if (buffer_uptodate(bh)) {
/*
* if not uninit if bh is uptodate,
down_write(&grp->alloc_sem);
for (i = 0, blocks_freed = 0; i < count; i++) {
BUFFER_TRACE(bitmap_bh, "clear bit");
- if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+ if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
bit + i, bitmap_bh->b_data)) {
ext4_error(sb, __func__,
"bit already cleared for block %llu",
blocks_freed++;
}
}
- spin_lock(sb_bgl_lock(sbi, block_group));
+ ext4_lock_group(sb, block_group);
blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
ext4_free_blks_set(sb, desc, blk_free_count);
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
- spin_unlock(sb_bgl_lock(sbi, block_group));
+ ext4_unlock_group(sb, block_group);
percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
if (sbi->s_log_groups_per_flex) {
ext4_fsblk_t desc_count;
struct ext4_group_desc *gdp;
ext4_group_t i;
- ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
ext4_fsblk_t bitmap_count;
bitmap_count = 0;
gdp = NULL;
- smp_rmb();
for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
return bitmap_count;
#else
desc_count = 0;
- smp_rmb();
for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
--- /dev/null
+/*
+ * linux/fs/ext4/block_validity.c
+ *
+ * Copyright (C) 2009
+ * Theodore Ts'o (tytso@mit.edu)
+ *
+ * Track which blocks in the filesystem are metadata blocks that
+ * should never be used as data blocks by files or directories.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/version.h>
+#include <linux/blkdev.h>
+#include <linux/mutex.h>
+#include "ext4.h"
+
+struct ext4_system_zone {
+ struct rb_node node;
+ ext4_fsblk_t start_blk;
+ unsigned int count;
+};
+
+static struct kmem_cache *ext4_system_zone_cachep;
+
+int __init init_ext4_system_zone(void)
+{
+ ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone,
+ SLAB_RECLAIM_ACCOUNT);
+ if (ext4_system_zone_cachep == NULL)
+ return -ENOMEM;
+ return 0;
+}
+
+void exit_ext4_system_zone(void)
+{
+ kmem_cache_destroy(ext4_system_zone_cachep);
+}
+
+static inline int can_merge(struct ext4_system_zone *entry1,
+ struct ext4_system_zone *entry2)
+{
+ if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+ return 1;
+ return 0;
+}
+
+/*
+ * Mark a range of blocks as belonging to the "system zone" --- that
+ * is, filesystem metadata blocks which should never be used by
+ * inodes.
+ */
+static int add_system_zone(struct ext4_sb_info *sbi,
+ ext4_fsblk_t start_blk,
+ unsigned int count)
+{
+ struct ext4_system_zone *new_entry = NULL, *entry;
+ struct rb_node **n = &sbi->system_blks.rb_node, *node;
+ struct rb_node *parent = NULL, *new_node = NULL;
+
+ while (*n) {
+ parent = *n;
+ entry = rb_entry(parent, struct ext4_system_zone, node);
+ if (start_blk < entry->start_blk)
+ n = &(*n)->rb_left;
+ else if (start_blk >= (entry->start_blk + entry->count))
+ n = &(*n)->rb_right;
+ else {
+ if (start_blk + count > (entry->start_blk +
+ entry->count))
+ entry->count = (start_blk + count -
+ entry->start_blk);
+ new_node = *n;
+ new_entry = rb_entry(new_node, struct ext4_system_zone,
+ node);
+ break;
+ }
+ }
+
+ if (!new_entry) {
+ new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+ GFP_KERNEL);
+ if (!new_entry)
+ return -ENOMEM;
+ new_entry->start_blk = start_blk;
+ new_entry->count = count;
+ new_node = &new_entry->node;
+
+ rb_link_node(new_node, parent, n);
+ rb_insert_color(new_node, &sbi->system_blks);
+ }
+
+ /* Can we merge to the left? */
+ node = rb_prev(new_node);
+ if (node) {
+ entry = rb_entry(node, struct ext4_system_zone, node);
+ if (can_merge(entry, new_entry)) {
+ new_entry->start_blk = entry->start_blk;
+ new_entry->count += entry->count;
+ rb_erase(node, &sbi->system_blks);
+ kmem_cache_free(ext4_system_zone_cachep, entry);
+ }
+ }
+
+ /* Can we merge to the right? */
+ node = rb_next(new_node);
+ if (node) {
+ entry = rb_entry(node, struct ext4_system_zone, node);
+ if (can_merge(new_entry, entry)) {
+ new_entry->count += entry->count;
+ rb_erase(node, &sbi->system_blks);
+ kmem_cache_free(ext4_system_zone_cachep, entry);
+ }
+ }
+ return 0;
+}
+
+static void debug_print_tree(struct ext4_sb_info *sbi)
+{
+ struct rb_node *node;
+ struct ext4_system_zone *entry;
+ int first = 1;
+
+ printk(KERN_INFO "System zones: ");
+ node = rb_first(&sbi->system_blks);
+ while (node) {
+ entry = rb_entry(node, struct ext4_system_zone, node);
+ printk("%s%llu-%llu", first ? "" : ", ",
+ entry->start_blk, entry->start_blk + entry->count - 1);
+ first = 0;
+ node = rb_next(node);
+ }
+ printk("\n");
+}
+
+int ext4_setup_system_zone(struct super_block *sb)
+{
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_desc *gdp;
+ ext4_group_t i;
+ int flex_size = ext4_flex_bg_size(sbi);
+ int ret;
+
+ if (!test_opt(sb, BLOCK_VALIDITY)) {
+ if (EXT4_SB(sb)->system_blks.rb_node)
+ ext4_release_system_zone(sb);
+ return 0;
+ }
+ if (EXT4_SB(sb)->system_blks.rb_node)
+ return 0;
+
+ for (i=0; i < ngroups; i++) {
+ if (ext4_bg_has_super(sb, i) &&
+ ((i < 5) || ((i % flex_size) == 0)))
+ add_system_zone(sbi, ext4_group_first_block_no(sb, i),
+ sbi->s_gdb_count + 1);
+ gdp = ext4_get_group_desc(sb, i, NULL);
+ ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
+ if (ret)
+ return ret;
+ ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1);
+ if (ret)
+ return ret;
+ ret = add_system_zone(sbi, ext4_inode_table(sb, gdp),
+ sbi->s_itb_per_group);
+ if (ret)
+ return ret;
+ }
+
+ if (test_opt(sb, DEBUG))
+ debug_print_tree(EXT4_SB(sb));
+ return 0;
+}
+
+/* Called when the filesystem is unmounted */
+void ext4_release_system_zone(struct super_block *sb)
+{
+ struct rb_node *n = EXT4_SB(sb)->system_blks.rb_node;
+ struct rb_node *parent;
+ struct ext4_system_zone *entry;
+
+ while (n) {
+ /* Do the node's children first */
+ if (n->rb_left) {
+ n = n->rb_left;
+ continue;
+ }
+ if (n->rb_right) {
+ n = n->rb_right;
+ continue;
+ }
+ /*
+ * The node has no children; free it, and then zero
+ * out parent's link to it. Finally go to the
+ * beginning of the loop and try to free the parent
+ * node.
+ */
+ parent = rb_parent(n);
+ entry = rb_entry(n, struct ext4_system_zone, node);
+ kmem_cache_free(ext4_system_zone_cachep, entry);
+ if (!parent)
+ EXT4_SB(sb)->system_blks.rb_node = NULL;
+ else if (parent->rb_left == n)
+ parent->rb_left = NULL;
+ else if (parent->rb_right == n)
+ parent->rb_right = NULL;
+ n = parent;
+ }
+ EXT4_SB(sb)->system_blks.rb_node = NULL;
+}
+
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with filesystem metadata blocks.
+ */
+int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
+ unsigned int count)
+{
+ struct ext4_system_zone *entry;
+ struct rb_node *n = sbi->system_blks.rb_node;
+
+ if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+ (start_blk + count > ext4_blocks_count(sbi->s_es)))
+ return 0;
+ while (n) {
+ entry = rb_entry(n, struct ext4_system_zone, node);
+ if (start_blk + count - 1 < entry->start_blk)
+ n = n->rb_left;
+ else if (start_blk >= (entry->start_blk + entry->count))
+ n = n->rb_right;
+ else
+ return 0;
+ }
+ return 1;
+}
+
struct buffer_head *bh = NULL;
map_bh.b_state = 0;
- err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh,
- 0, 0, 0);
+ err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0);
if (err > 0) {
pgoff_t index = map_bh.b_blocknr >>
(PAGE_CACHE_SHIFT - inode->i_blkbits);
#include <linux/magic.h>
#include <linux/jbd2.h>
#include <linux/quota.h>
-#include "ext4_i.h"
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
/*
* The fourth extended filesystem constants/structures
#define ext4_debug(f, a...) do {} while (0)
#endif
+/* data type for block offset of block group */
+typedef int ext4_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long long ext4_fsblk_t;
+
+/* data type for file logical block number */
+typedef __u32 ext4_lblk_t;
+
+/* data type for block group number */
+typedef unsigned int ext4_group_t;
+
+
/* prefer goal again. length */
#define EXT4_MB_HINT_MERGE 1
/* blocks already reserved */
#define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */
#define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */
-#ifdef __KERNEL__
-#include "ext4_sb.h"
-#endif
/*
* Macro-instructions used to manage group descriptors
*/
};
/*
- * Following is used by preallocation code to tell get_blocks() that we
- * want uninitialzed extents.
+ * Flags used by ext4_get_blocks()
*/
-#define EXT4_CREATE_UNINITIALIZED_EXT 2
+ /* Allocate any needed blocks and/or convert an unitialized
+ extent to be an initialized ext4 */
+#define EXT4_GET_BLOCKS_CREATE 0x0001
+ /* Request the creation of an unitialized extent */
+#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\
+ EXT4_GET_BLOCKS_CREATE)
+ /* Caller is from the delayed allocation writeout path,
+ so set the magic i_delalloc_reserve_flag after taking the
+ inode allocation semaphore for */
+#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
+ /* Call ext4_da_update_reserve_space() after successfully
+ allocating the blocks */
+#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0008
+
/*
* ioctl commands
#endif /* defined(__KERNEL__) || defined(__linux__) */
+/*
+ * storage for cached extent
+ */
+struct ext4_ext_cache {
+ ext4_fsblk_t ec_start;
+ ext4_lblk_t ec_block;
+ __u32 ec_len; /* must be 32bit to return holes */
+ __u32 ec_type;
+};
+
+/*
+ * fourth extended file system inode data in memory
+ */
+struct ext4_inode_info {
+ __le32 i_data[15]; /* unconverted */
+ __u32 i_flags;
+ ext4_fsblk_t i_file_acl;
+ __u32 i_dtime;
+
+ /*
+ * i_block_group is the number of the block group which contains
+ * this file's inode. Constant across the lifetime of the inode,
+ * it is ued for making block allocation decisions - we try to
+ * place a file's data blocks near its inode block, and new inodes
+ * near to their parent directory's inode.
+ */
+ ext4_group_t i_block_group;
+ __u32 i_state; /* Dynamic state flags for ext4 */
+
+ ext4_lblk_t i_dir_start_lookup;
+#ifdef CONFIG_EXT4_FS_XATTR
+ /*
+ * Extended attributes can be read independently of the main file
+ * data. Taking i_mutex even when reading would cause contention
+ * between readers of EAs and writers of regular file data, so
+ * instead we synchronize on xattr_sem when reading or changing
+ * EAs.
+ */
+ struct rw_semaphore xattr_sem;
+#endif
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+ struct posix_acl *i_acl;
+ struct posix_acl *i_default_acl;
+#endif
+
+ struct list_head i_orphan; /* unlinked but open inodes */
+
+ /*
+ * i_disksize keeps track of what the inode size is ON DISK, not
+ * in memory. During truncate, i_size is set to the new size by
+ * the VFS prior to calling ext4_truncate(), but the filesystem won't
+ * set i_disksize to 0 until the truncate is actually under way.
+ *
+ * The intent is that i_disksize always represents the blocks which
+ * are used by this file. This allows recovery to restart truncate
+ * on orphans if we crash during truncate. We actually write i_disksize
+ * into the on-disk inode when writing inodes out, instead of i_size.
+ *
+ * The only time when i_disksize and i_size may be different is when
+ * a truncate is in progress. The only things which change i_disksize
+ * are ext4_get_block (growth) and ext4_truncate (shrinkth).
+ */
+ loff_t i_disksize;
+
+ /*
+ * i_data_sem is for serialising ext4_truncate() against
+ * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's
+ * data tree are chopped off during truncate. We can't do that in
+ * ext4 because whenever we perform intermediate commits during
+ * truncate, the inode and all the metadata blocks *must* be in a
+ * consistent state which allows truncation of the orphans to restart
+ * during recovery. Hence we must fix the get_block-vs-truncate race
+ * by other means, so we have i_data_sem.
+ */
+ struct rw_semaphore i_data_sem;
+ struct inode vfs_inode;
+ struct jbd2_inode jinode;
+
+ struct ext4_ext_cache i_cached_extent;
+ /*
+ * File creation time. Its function is same as that of
+ * struct timespec i_{a,c,m}time in the generic inode.
+ */
+ struct timespec i_crtime;
+
+ /* mballoc */
+ struct list_head i_prealloc_list;
+ spinlock_t i_prealloc_lock;
+
+ /* ialloc */
+ ext4_group_t i_last_alloc_group;
+
+ /* allocation reservation info for delalloc */
+ unsigned int i_reserved_data_blocks;
+ unsigned int i_reserved_meta_blocks;
+ unsigned int i_allocated_meta_blocks;
+ unsigned short i_delalloc_reserved_flag;
+
+ /* on-disk additional length */
+ __u16 i_extra_isize;
+
+ spinlock_t i_block_reservation_lock;
+};
+
/*
* File system states
*/
#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
+#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
#ifndef _LINUX_EXT2_FS_H
};
#ifdef __KERNEL__
+/*
+ * fourth extended-fs super-block data in memory
+ */
+struct ext4_sb_info {
+ unsigned long s_desc_size; /* Size of a group descriptor in bytes */
+ unsigned long s_inodes_per_block;/* Number of inodes per block */
+ unsigned long s_blocks_per_group;/* Number of blocks in a group */
+ unsigned long s_inodes_per_group;/* Number of inodes in a group */
+ unsigned long s_itb_per_group; /* Number of inode table blocks per group */
+ unsigned long s_gdb_count; /* Number of group descriptor blocks */
+ unsigned long s_desc_per_block; /* Number of group descriptors per block */
+ ext4_group_t s_groups_count; /* Number of groups in the fs */
+ unsigned long s_overhead_last; /* Last calculated overhead */
+ unsigned long s_blocks_last; /* Last seen block count */
+ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
+ struct buffer_head * s_sbh; /* Buffer containing the super block */
+ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
+ struct buffer_head **s_group_desc;
+ unsigned long s_mount_opt;
+ ext4_fsblk_t s_sb_block;
+ uid_t s_resuid;
+ gid_t s_resgid;
+ unsigned short s_mount_state;
+ unsigned short s_pad;
+ int s_addr_per_block_bits;
+ int s_desc_per_block_bits;
+ int s_inode_size;
+ int s_first_ino;
+ unsigned int s_inode_readahead_blks;
+ spinlock_t s_next_gen_lock;
+ u32 s_next_generation;
+ u32 s_hash_seed[4];
+ int s_def_hash_version;
+ int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
+ struct percpu_counter s_freeblocks_counter;
+ struct percpu_counter s_freeinodes_counter;
+ struct percpu_counter s_dirs_counter;
+ struct percpu_counter s_dirtyblocks_counter;
+ struct blockgroup_lock *s_blockgroup_lock;
+ struct proc_dir_entry *s_proc;
+ struct kobject s_kobj;
+ struct completion s_kobj_unregister;
+
+ /* Journaling */
+ struct inode *s_journal_inode;
+ struct journal_s *s_journal;
+ struct list_head s_orphan;
+ struct mutex s_orphan_lock;
+ struct mutex s_resize_lock;
+ unsigned long s_commit_interval;
+ u32 s_max_batch_time;
+ u32 s_min_batch_time;
+ struct block_device *journal_bdev;
+#ifdef CONFIG_JBD2_DEBUG
+ struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
+ wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
+#endif
+#ifdef CONFIG_QUOTA
+ char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
+ int s_jquota_fmt; /* Format of quota to use */
+#endif
+ unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
+ struct rb_root system_blks;
+
+#ifdef EXTENTS_STATS
+ /* ext4 extents stats */
+ unsigned long s_ext_min;
+ unsigned long s_ext_max;
+ unsigned long s_depth_max;
+ spinlock_t s_ext_stats_lock;
+ unsigned long s_ext_blocks;
+ unsigned long s_ext_extents;
+#endif
+
+ /* for buddy allocator */
+ struct ext4_group_info ***s_group_info;
+ struct inode *s_buddy_cache;
+ long s_blocks_reserved;
+ spinlock_t s_reserve_lock;
+ spinlock_t s_md_lock;
+ tid_t s_last_transaction;
+ unsigned short *s_mb_offsets;
+ unsigned int *s_mb_maxs;
+
+ /* tunables */
+ unsigned long s_stripe;
+ unsigned int s_mb_stream_request;
+ unsigned int s_mb_max_to_scan;
+ unsigned int s_mb_min_to_scan;
+ unsigned int s_mb_stats;
+ unsigned int s_mb_order2_reqs;
+ unsigned int s_mb_group_prealloc;
+ /* where last allocation was done - for stream allocation */
+ unsigned long s_mb_last_group;
+ unsigned long s_mb_last_start;
+
+ /* history to debug policy */
+ struct ext4_mb_history *s_mb_history;
+ int s_mb_history_cur;
+ int s_mb_history_max;
+ int s_mb_history_num;
+ spinlock_t s_mb_history_lock;
+ int s_mb_history_filter;
+
+ /* stats for buddy allocator */
+ spinlock_t s_mb_pa_lock;
+ atomic_t s_bal_reqs; /* number of reqs with len > 1 */
+ atomic_t s_bal_success; /* we found long enough chunks */
+ atomic_t s_bal_allocated; /* in blocks */
+ atomic_t s_bal_ex_scanned; /* total extents scanned */
+ atomic_t s_bal_goals; /* goal hits */
+ atomic_t s_bal_breaks; /* too long searches */
+ atomic_t s_bal_2orders; /* 2^order hits */
+ spinlock_t s_bal_lock;
+ unsigned long s_mb_buddies_generated;
+ unsigned long long s_mb_generation_time;
+ atomic_t s_mb_lost_chunks;
+ atomic_t s_mb_preallocated;
+ atomic_t s_mb_discarded;
+
+ /* locality groups */
+ struct ext4_locality_group *s_locality_groups;
+
+ /* for write statistics */
+ unsigned long s_sectors_written_start;
+ u64 s_kbytes_written;
+
+ unsigned int s_log_groups_per_flex;
+ struct flex_groups *s_flex_groups;
+};
+
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
{
return sb->s_fs_info;
current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
}
-
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
{
return ino == EXT4_ROOT_INO ||
ext4_group_t block_group,
struct buffer_head ** bh);
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
+struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
+ ext4_group_t block_group);
+extern unsigned ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t group,
+ struct ext4_group_desc *desc);
+#define ext4_free_blocks_after_init(sb, group, desc) \
+ ext4_init_block_bitmap(sb, NULL, group, desc)
/* dir.c */
extern int ext4_check_dir_entry(const char *, struct inode *,
extern unsigned long ext4_count_free_inodes(struct super_block *);
extern unsigned long ext4_count_dirs(struct super_block *);
extern void ext4_check_inodes_bitmap(struct super_block *);
+extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t group,
+ struct ext4_group_desc *desc);
+extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
/* mballoc.c */
extern long ext4_mb_stats;
__attribute__ ((format (printf, 3, 4)));
extern void ext4_warning(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
+extern void ext4_msg(struct super_block *, const char *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
const char *, const char *, ...)
__attribute__ ((format (printf, 4, 5)));
struct ext4_group_desc *bg, __u32 count);
extern void ext4_itable_unused_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
+extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
+ struct ext4_group_desc *gdp);
+extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
+ struct ext4_group_desc *gdp);
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
return grp_info[indexv][indexh];
}
+/*
+ * Reading s_groups_count requires using smp_rmb() afterwards. See
+ * the locking protocol documented in the comments of ext4_group_add()
+ * in resize.c
+ */
+static inline ext4_group_t ext4_get_groups_count(struct super_block *sb)
+{
+ ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+
+ smp_rmb();
+ return ngroups;
+}
static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
ext4_group_t block_group)
};
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
-#define EXT4_GROUP_INFO_LOCKED_BIT 1
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
-static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
+static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
+ ext4_group_t group)
{
- struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
- bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+ return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
-static inline void ext4_unlock_group(struct super_block *sb,
- ext4_group_t group)
+static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
- struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
- bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+ spin_lock(ext4_group_lock_ptr(sb, group));
}
-static inline int ext4_is_group_locked(struct super_block *sb,
+static inline void ext4_unlock_group(struct super_block *sb,
ext4_group_t group)
{
- struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
- return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
- &(grinfo->bb_state));
+ spin_unlock(ext4_group_lock_ptr(sb, group));
}
/*
/* namei.c */
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
+extern struct dentry *ext4_get_parent(struct dentry *child);
/* symlink.c */
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
+/* block_validity */
+extern void ext4_release_system_zone(struct super_block *sb);
+extern int ext4_setup_system_zone(struct super_block *sb);
+extern int __init init_ext4_system_zone(void);
+extern void exit_ext4_system_zone(void);
+extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
+ ext4_fsblk_t start_blk,
+ unsigned int count);
+
/* extents.c */
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
int chunk);
extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, unsigned int max_blocks,
- struct buffer_head *bh_result,
- int create, int extend_disksize);
+ struct buffer_head *bh_result, int flags);
extern void ext4_ext_truncate(struct inode *);
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
loff_t len);
-extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
- sector_t block, unsigned int max_blocks,
- struct buffer_head *bh, int create,
- int extend_disksize, int flag);
+extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
+ sector_t block, unsigned int max_blocks,
+ struct buffer_head *bh, int flags);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
+++ /dev/null
-/*
- * ext4_i.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- * from
- *
- * linux/include/linux/minix_fs_i.h
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-#ifndef _EXT4_I
-#define _EXT4_I
-
-#include <linux/rwsem.h>
-#include <linux/rbtree.h>
-#include <linux/seqlock.h>
-#include <linux/mutex.h>
-
-/* data type for block offset of block group */
-typedef int ext4_grpblk_t;
-
-/* data type for filesystem-wide blocks number */
-typedef unsigned long long ext4_fsblk_t;
-
-/* data type for file logical block number */
-typedef __u32 ext4_lblk_t;
-
-/* data type for block group number */
-typedef unsigned int ext4_group_t;
-
-/*
- * storage for cached extent
- */
-struct ext4_ext_cache {
- ext4_fsblk_t ec_start;
- ext4_lblk_t ec_block;
- __u32 ec_len; /* must be 32bit to return holes */
- __u32 ec_type;
-};
-
-/*
- * fourth extended file system inode data in memory
- */
-struct ext4_inode_info {
- __le32 i_data[15]; /* unconverted */
- __u32 i_flags;
- ext4_fsblk_t i_file_acl;
- __u32 i_dtime;
-
- /*
- * i_block_group is the number of the block group which contains
- * this file's inode. Constant across the lifetime of the inode,
- * it is ued for making block allocation decisions - we try to
- * place a file's data blocks near its inode block, and new inodes
- * near to their parent directory's inode.
- */
- ext4_group_t i_block_group;
- __u32 i_state; /* Dynamic state flags for ext4 */
-
- ext4_lblk_t i_dir_start_lookup;
-#ifdef CONFIG_EXT4_FS_XATTR
- /*
- * Extended attributes can be read independently of the main file
- * data. Taking i_mutex even when reading would cause contention
- * between readers of EAs and writers of regular file data, so
- * instead we synchronize on xattr_sem when reading or changing
- * EAs.
- */
- struct rw_semaphore xattr_sem;
-#endif
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
- struct posix_acl *i_acl;
- struct posix_acl *i_default_acl;
-#endif
-
- struct list_head i_orphan; /* unlinked but open inodes */
-
- /*
- * i_disksize keeps track of what the inode size is ON DISK, not
- * in memory. During truncate, i_size is set to the new size by
- * the VFS prior to calling ext4_truncate(), but the filesystem won't
- * set i_disksize to 0 until the truncate is actually under way.
- *
- * The intent is that i_disksize always represents the blocks which
- * are used by this file. This allows recovery to restart truncate
- * on orphans if we crash during truncate. We actually write i_disksize
- * into the on-disk inode when writing inodes out, instead of i_size.
- *
- * The only time when i_disksize and i_size may be different is when
- * a truncate is in progress. The only things which change i_disksize
- * are ext4_get_block (growth) and ext4_truncate (shrinkth).
- */
- loff_t i_disksize;
-
- /*
- * i_data_sem is for serialising ext4_truncate() against
- * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's
- * data tree are chopped off during truncate. We can't do that in
- * ext4 because whenever we perform intermediate commits during
- * truncate, the inode and all the metadata blocks *must* be in a
- * consistent state which allows truncation of the orphans to restart
- * during recovery. Hence we must fix the get_block-vs-truncate race
- * by other means, so we have i_data_sem.
- */
- struct rw_semaphore i_data_sem;
- struct inode vfs_inode;
- struct jbd2_inode jinode;
-
- struct ext4_ext_cache i_cached_extent;
- /*
- * File creation time. Its function is same as that of
- * struct timespec i_{a,c,m}time in the generic inode.
- */
- struct timespec i_crtime;
-
- /* mballoc */
- struct list_head i_prealloc_list;
- spinlock_t i_prealloc_lock;
-
- /* ialloc */
- ext4_group_t i_last_alloc_group;
-
- /* allocation reservation info for delalloc */
- unsigned int i_reserved_data_blocks;
- unsigned int i_reserved_meta_blocks;
- unsigned int i_allocated_meta_blocks;
- unsigned short i_delalloc_reserved_flag;
-
- /* on-disk additional length */
- __u16 i_extra_isize;
-
- spinlock_t i_block_reservation_lock;
-};
-
-#endif /* _EXT4_I */
+++ /dev/null
-/*
- * ext4_sb.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- * from
- *
- * linux/include/linux/minix_fs_sb.h
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-#ifndef _EXT4_SB
-#define _EXT4_SB
-
-#ifdef __KERNEL__
-#include <linux/timer.h>
-#include <linux/wait.h>
-#include <linux/blockgroup_lock.h>
-#include <linux/percpu_counter.h>
-#endif
-#include <linux/rbtree.h>
-
-/*
- * fourth extended-fs super-block data in memory
- */
-struct ext4_sb_info {
- unsigned long s_desc_size; /* Size of a group descriptor in bytes */
- unsigned long s_inodes_per_block;/* Number of inodes per block */
- unsigned long s_blocks_per_group;/* Number of blocks in a group */
- unsigned long s_inodes_per_group;/* Number of inodes in a group */
- unsigned long s_itb_per_group; /* Number of inode table blocks per group */
- unsigned long s_gdb_count; /* Number of group descriptor blocks */
- unsigned long s_desc_per_block; /* Number of group descriptors per block */
- ext4_group_t s_groups_count; /* Number of groups in the fs */
- unsigned long s_overhead_last; /* Last calculated overhead */
- unsigned long s_blocks_last; /* Last seen block count */
- loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
- struct buffer_head * s_sbh; /* Buffer containing the super block */
- struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
- struct buffer_head **s_group_desc;
- unsigned long s_mount_opt;
- ext4_fsblk_t s_sb_block;
- uid_t s_resuid;
- gid_t s_resgid;
- unsigned short s_mount_state;
- unsigned short s_pad;
- int s_addr_per_block_bits;
- int s_desc_per_block_bits;
- int s_inode_size;
- int s_first_ino;
- unsigned int s_inode_readahead_blks;
- spinlock_t s_next_gen_lock;
- u32 s_next_generation;
- u32 s_hash_seed[4];
- int s_def_hash_version;
- int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
- struct percpu_counter s_freeblocks_counter;
- struct percpu_counter s_freeinodes_counter;
- struct percpu_counter s_dirs_counter;
- struct percpu_counter s_dirtyblocks_counter;
- struct blockgroup_lock *s_blockgroup_lock;
- struct proc_dir_entry *s_proc;
- struct kobject s_kobj;
- struct completion s_kobj_unregister;
-
- /* Journaling */
- struct inode *s_journal_inode;
- struct journal_s *s_journal;
- struct list_head s_orphan;
- unsigned long s_commit_interval;
- u32 s_max_batch_time;
- u32 s_min_batch_time;
- struct block_device *journal_bdev;
-#ifdef CONFIG_JBD2_DEBUG
- struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
- wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
-#endif
-#ifdef CONFIG_QUOTA
- char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
- int s_jquota_fmt; /* Format of quota to use */
-#endif
- unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
-
-#ifdef EXTENTS_STATS
- /* ext4 extents stats */
- unsigned long s_ext_min;
- unsigned long s_ext_max;
- unsigned long s_depth_max;
- spinlock_t s_ext_stats_lock;
- unsigned long s_ext_blocks;
- unsigned long s_ext_extents;
-#endif
-
- /* for buddy allocator */
- struct ext4_group_info ***s_group_info;
- struct inode *s_buddy_cache;
- long s_blocks_reserved;
- spinlock_t s_reserve_lock;
- spinlock_t s_md_lock;
- tid_t s_last_transaction;
- unsigned short *s_mb_offsets;
- unsigned int *s_mb_maxs;
-
- /* tunables */
- unsigned long s_stripe;
- unsigned int s_mb_stream_request;
- unsigned int s_mb_max_to_scan;
- unsigned int s_mb_min_to_scan;
- unsigned int s_mb_stats;
- unsigned int s_mb_order2_reqs;
- unsigned int s_mb_group_prealloc;
- /* where last allocation was done - for stream allocation */
- unsigned long s_mb_last_group;
- unsigned long s_mb_last_start;
-
- /* history to debug policy */
- struct ext4_mb_history *s_mb_history;
- int s_mb_history_cur;
- int s_mb_history_max;
- int s_mb_history_num;
- spinlock_t s_mb_history_lock;
- int s_mb_history_filter;
-
- /* stats for buddy allocator */
- spinlock_t s_mb_pa_lock;
- atomic_t s_bal_reqs; /* number of reqs with len > 1 */
- atomic_t s_bal_success; /* we found long enough chunks */
- atomic_t s_bal_allocated; /* in blocks */
- atomic_t s_bal_ex_scanned; /* total extents scanned */
- atomic_t s_bal_goals; /* goal hits */
- atomic_t s_bal_breaks; /* too long searches */
- atomic_t s_bal_2orders; /* 2^order hits */
- spinlock_t s_bal_lock;
- unsigned long s_mb_buddies_generated;
- unsigned long long s_mb_generation_time;
- atomic_t s_mb_lost_chunks;
- atomic_t s_mb_preallocated;
- atomic_t s_mb_discarded;
-
- /* locality groups */
- struct ext4_locality_group *s_locality_groups;
-
- /* for write statistics */
- unsigned long s_sectors_written_start;
- u64 s_kbytes_written;
-
- unsigned int s_log_groups_per_flex;
- struct flex_groups *s_flex_groups;
-};
-
-static inline spinlock_t *
-sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group)
-{
- return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
-}
-
-#endif /* _EXT4_SB */
static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
{
- ext4_fsblk_t block = ext_pblock(ext), valid_block;
+ ext4_fsblk_t block = ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
- struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
- valid_block = le32_to_cpu(es->s_first_data_block) +
- EXT4_SB(inode->i_sb)->s_gdb_count;
- if (unlikely(block <= valid_block ||
- ((block + len) > ext4_blocks_count(es))))
- return 0;
- else
- return 1;
+ return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
static int ext4_valid_extent_idx(struct inode *inode,
struct ext4_extent_idx *ext_idx)
{
- ext4_fsblk_t block = idx_pblock(ext_idx), valid_block;
- struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ ext4_fsblk_t block = idx_pblock(ext_idx);
- valid_block = le32_to_cpu(es->s_first_data_block) +
- EXT4_SB(inode->i_sb)->s_gdb_count;
- if (unlikely(block <= valid_block ||
- (block >= ext4_blocks_count(es))))
- return 0;
- else
- return 1;
+ return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
}
static int ext4_valid_extent_entries(struct inode *inode,
ex = EXT_LAST_EXTENT(eh);
ex_ee_block = le32_to_cpu(ex->ee_block);
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
ex_ee_len = ext4_ext_get_actual_len(ex);
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
+
+ if (ext4_ext_is_uninitialized(ex))
+ uninitialized = 1;
+ else
+ uninitialized = 0;
+
ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len);
path[depth].p_ext = ex;
int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock,
unsigned int max_blocks, struct buffer_head *bh_result,
- int create, int extend_disksize)
+ int flags)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent_header *eh;
int err = 0, depth, ret, cache_type;
unsigned int allocated = 0;
struct ext4_allocation_request ar;
- loff_t disksize;
__clear_bit(BH_New, &bh_result->b_state);
ext_debug("blocks %u/%u requested for inode %u\n",
cache_type = ext4_ext_in_cache(inode, iblock, &newex);
if (cache_type) {
if (cache_type == EXT4_EXT_CACHE_GAP) {
- if (!create) {
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
/*
* block isn't allocated yet and
* user doesn't want to allocate it
EXT4_EXT_CACHE_EXTENT);
goto out;
}
- if (create == EXT4_CREATE_UNINITIALIZED_EXT)
+ if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
goto out;
- if (!create) {
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+ if (allocated > max_blocks)
+ allocated = max_blocks;
/*
* We have blocks reserved already. We
* return allocated blocks so that delalloc
* the buffer head will be unmapped so that
* a read from the block returns 0s.
*/
- if (allocated > max_blocks)
- allocated = max_blocks;
set_buffer_unwritten(bh_result);
bh_result->b_bdev = inode->i_sb->s_bdev;
bh_result->b_blocknr = newblock;
* requested block isn't allocated yet;
* we couldn't try to create block if create flag is zero
*/
- if (!create) {
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
/*
* put just found gap into cache to speed up
* subsequent requests
* EXT_UNINIT_MAX_LEN.
*/
if (max_blocks > EXT_INIT_MAX_LEN &&
- create != EXT4_CREATE_UNINITIALIZED_EXT)
+ !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
max_blocks = EXT_INIT_MAX_LEN;
else if (max_blocks > EXT_UNINIT_MAX_LEN &&
- create == EXT4_CREATE_UNINITIALIZED_EXT)
+ (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
max_blocks = EXT_UNINIT_MAX_LEN;
/* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock);
newex.ee_len = cpu_to_le16(ar.len);
- if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */
+ if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) /* Mark uninitialized */
ext4_ext_mark_uninitialized(&newex);
err = ext4_ext_insert_extent(handle, inode, path, &newex);
if (err) {
newblock = ext_pblock(&newex);
allocated = ext4_ext_get_actual_len(&newex);
outnew:
- if (extend_disksize) {
- disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits;
- if (disksize > i_size_read(inode))
- disksize = i_size_read(inode);
- if (disksize > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = disksize;
- }
-
set_buffer_new(bh_result);
/* Cache only when it is _not_ an uninitialized extent */
- if (create != EXT4_CREATE_UNINITIALIZED_EXT)
+ if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
EXT4_EXT_CACHE_EXTENT);
out:
ret = PTR_ERR(handle);
break;
}
- ret = ext4_get_blocks_wrap(handle, inode, block,
- max_blocks, &map_bh,
- EXT4_CREATE_UNINITIALIZED_EXT, 0, 0);
+ map_bh.b_state = 0;
+ ret = ext4_get_blocks(handle, inode, block,
+ max_blocks, &map_bh,
+ EXT4_GET_BLOCKS_CREATE_UNINIT_EXT);
if (ret <= 0) {
#ifdef EXT4FS_DEBUG
WARN_ON(ret <= 0);
void *data)
{
struct fiemap_extent_info *fieinfo = data;
- unsigned long blksize_bits = inode->i_sb->s_blocksize_bits;
+ unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
__u64 logical;
__u64 physical;
__u64 length;
*
* XXX this might miss a single-block extent at EXT_MAX_BLOCK
*/
- if (logical + length - 1 == EXT_MAX_BLOCK ||
- ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK)
+ if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK ||
+ newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) {
+ loff_t size = i_size_read(inode);
+ loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb);
+
flags |= FIEMAP_EXTENT_LAST;
+ if ((flags & FIEMAP_EXTENT_DELALLOC) &&
+ logical+length > size)
+ length = (size - logical + bs - 1) & ~(bs-1);
+ }
error = fiemap_fill_next_extent(fieinfo, logical, physical,
length, flags);
* Walk the extent tree gathering extent information.
* ext4_ext_fiemap_cb will push extents back to user.
*/
- down_write(&EXT4_I(inode)->i_data_sem);
+ down_read(&EXT4_I(inode)->i_data_sem);
error = ext4_ext_walk_space(inode, start_blk, len_blks,
ext4_ext_fiemap_cb, fieinfo);
- up_write(&EXT4_I(inode)->i_data_sem);
+ up_read(&EXT4_I(inode)->i_data_sem);
}
return error;
+++ /dev/null
-/*
- * linux/fs/ext4/group.h
- *
- * Copyright (C) 2007 Cluster File Systems, Inc
- *
- * Author: Andreas Dilger <adilger@clusterfs.com>
- */
-
-#ifndef _LINUX_EXT4_GROUP_H
-#define _LINUX_EXT4_GROUP_H
-
-extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
- struct ext4_group_desc *gdp);
-extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
- struct ext4_group_desc *gdp);
-struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
- ext4_group_t block_group);
-extern unsigned ext4_init_block_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
-#define ext4_free_blocks_after_init(sb, group, desc) \
- ext4_init_block_bitmap(sb, NULL, group, desc)
-extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
-extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
-#endif /* _LINUX_EXT4_GROUP_H */
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
-#include "group.h"
/*
* ialloc.c contains the inodes allocation and deallocation routines
unlock_buffer(bh);
return bh;
}
- spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_lock_group(sb, block_group);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
ext4_init_inode_bitmap(sb, bh, block_group, desc);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
return bh;
}
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ ext4_unlock_group(sb, block_group);
if (buffer_uptodate(bh)) {
/*
* if not uninit if bh is uptodate,
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
- spin_lock(sb_bgl_lock(sbi, block_group));
- cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
- spin_unlock(sb_bgl_lock(sbi, block_group));
+ cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
+ bit, bitmap_bh->b_data);
if (!cleared)
ext4_error(sb, "ext4_free_inode",
"bit already cleared for inode %lu", ino);
if (fatal) goto error_return;
if (gdp) {
- spin_lock(sb_bgl_lock(sbi, block_group));
+ ext4_lock_group(sb, block_group);
count = ext4_free_inodes_count(sb, gdp) + 1;
ext4_free_inodes_set(sb, gdp, count);
if (is_directory) {
}
gdp->bg_checksum = ext4_group_desc_csum(sbi,
block_group, gdp);
- spin_unlock(sb_bgl_lock(sbi, block_group));
+ ext4_unlock_group(sb, block_group);
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
percpu_counter_dec(&sbi->s_dirs_counter);
static int find_group_dir(struct super_block *sb, struct inode *parent,
ext4_group_t *best_group)
{
- ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
unsigned int freei, avefreei;
struct ext4_group_desc *desc, *best_desc = NULL;
ext4_group_t group;
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *desc;
- struct buffer_head *bh;
struct flex_groups *flex_group = sbi->s_flex_groups;
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
- ext4_group_t ngroups = sbi->s_groups_count;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
int flex_size = ext4_flex_bg_size(sbi);
ext4_group_t best_flex = parent_fbg_group;
int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
ext4_group_t n_fbg_groups;
ext4_group_t i;
- n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >>
+ n_fbg_groups = (ngroups + flex_size - 1) >>
sbi->s_log_groups_per_flex;
find_close_to_parent:
found_flexbg:
for (i = best_flex * flex_size; i < ngroups &&
i < (best_flex + 1) * flex_size; i++) {
- desc = ext4_get_group_desc(sb, i, &bh);
+ desc = ext4_get_group_desc(sb, i, NULL);
if (ext4_free_inodes_count(sb, desc)) {
*best_group = i;
goto out;
{
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- ext4_group_t ngroups = sbi->s_groups_count;
+ ext4_group_t real_ngroups = ext4_get_groups_count(sb);
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext4_fsblk_t freeb, avefreeb;
unsigned int ndirs;
int max_dirs, min_inodes;
ext4_grpblk_t min_blocks;
- ext4_group_t i, grp, g;
+ ext4_group_t i, grp, g, ngroups;
struct ext4_group_desc *desc;
struct orlov_stats stats;
int flex_size = ext4_flex_bg_size(sbi);
+ ngroups = real_ngroups;
if (flex_size > 1) {
- ngroups = (ngroups + flex_size - 1) >>
+ ngroups = (real_ngroups + flex_size - 1) >>
sbi->s_log_groups_per_flex;
parent_group >>= sbi->s_log_groups_per_flex;
}
*/
grp *= flex_size;
for (i = 0; i < flex_size; i++) {
- if (grp+i >= sbi->s_groups_count)
+ if (grp+i >= real_ngroups)
break;
desc = ext4_get_group_desc(sb, grp+i, NULL);
if (desc && ext4_free_inodes_count(sb, desc)) {
}
fallback:
- ngroups = sbi->s_groups_count;
+ ngroups = real_ngroups;
avefreei = freei / ngroups;
fallback_retry:
parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t *group, int mode)
{
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
- ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
struct ext4_group_desc *desc;
- ext4_group_t i, last;
int flex_size = ext4_flex_bg_size(EXT4_SB(sb));
/*
/*
* claim the inode from the inode bitmap. If the group
- * is uninit we need to take the groups's sb_bgl_lock
+ * is uninit we need to take the groups's ext4_group_lock
* and clear the uninit flag. The inode bitmap update
* and group desc uninit flag clear should be done
- * after holding sb_bgl_lock so that ext4_read_inode_bitmap
+ * after holding ext4_group_lock so that ext4_read_inode_bitmap
* doesn't race with the ext4_claim_inode
*/
static int ext4_claim_inode(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
- spin_lock(sb_bgl_lock(sbi, group));
+ ext4_lock_group(sb, group);
if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
/* not a free inode */
retval = 1;
ino++;
if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
ino > EXT4_INODES_PER_GROUP(sb)) {
- spin_unlock(sb_bgl_lock(sbi, group));
+ ext4_unlock_group(sb, group);
ext4_error(sb, __func__,
"reserved inode or inode > inodes count - "
"block_group = %u, inode=%lu", group,
}
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
err_ret:
- spin_unlock(sb_bgl_lock(sbi, group));
+ ext4_unlock_group(sb, group);
return retval;
}
struct super_block *sb;
struct buffer_head *inode_bitmap_bh = NULL;
struct buffer_head *group_desc_bh;
- ext4_group_t group = 0;
+ ext4_group_t ngroups, group = 0;
unsigned long ino = 0;
struct inode *inode;
struct ext4_group_desc *gdp = NULL;
- struct ext4_super_block *es;
struct ext4_inode_info *ei;
struct ext4_sb_info *sbi;
int ret2, err = 0;
return ERR_PTR(-EPERM);
sb = dir->i_sb;
+ ngroups = ext4_get_groups_count(sb);
trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id,
dir->i_ino, mode);
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT4_I(inode);
-
sbi = EXT4_SB(sb);
- es = sbi->s_es;
if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
ret2 = find_group_flex(sb, dir, &group);
if (ret2 == -1)
goto out;
- for (i = 0; i < sbi->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
err = -EIO;
gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
* group descriptor metadata has not yet been updated.
* So we just go onto the next blockgroup.
*/
- if (++group == sbi->s_groups_count)
+ if (++group == ngroups)
group = 0;
}
err = -ENOSPC;
}
free = 0;
- spin_lock(sb_bgl_lock(sbi, group));
+ ext4_lock_group(sb, group);
/* recheck and clear flag under lock if we still need to */
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
free = ext4_free_blocks_after_init(sb, group, gdp);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
gdp);
}
- spin_unlock(sb_bgl_lock(sbi, group));
+ ext4_unlock_group(sb, group);
/* Don't need to dirty bitmap block if we didn't change it */
if (free) {
{
unsigned long desc_count;
struct ext4_group_desc *gdp;
- ext4_group_t i;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
unsigned long bitmap_count, x;
desc_count = 0;
bitmap_count = 0;
gdp = NULL;
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
return desc_count;
#else
desc_count = 0;
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
unsigned long ext4_count_dirs(struct super_block * sb)
{
unsigned long count = 0;
- ext4_group_t i;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
}
static int __ext4_check_blockref(const char *function, struct inode *inode,
- __le32 *p, unsigned int max) {
-
- unsigned int maxblocks = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es);
+ __le32 *p, unsigned int max)
+{
__le32 *bref = p;
+ unsigned int blk;
+
while (bref < p+max) {
- if (unlikely(le32_to_cpu(*bref) >= maxblocks)) {
+ blk = le32_to_cpu(*bref++);
+ if (blk &&
+ unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
+ blk, 1))) {
ext4_error(inode->i_sb, function,
- "block reference %u >= max (%u) "
- "in inode #%lu, offset=%d",
- le32_to_cpu(*bref), maxblocks,
- inode->i_ino, (int)(bref-p));
+ "invalid block reference %u "
+ "in inode #%lu", blk, inode->i_ino);
return -EIO;
}
- bref++;
}
return 0;
}
}
/*
+ * The ext4_ind_get_blocks() function handles non-extents inodes
+ * (i.e., using the traditional indirect/double-indirect i_blocks
+ * scheme) for ext4_get_blocks().
+ *
* Allocation strategy is simple: if we have to allocate something, we will
* have to go the whole way to leaf. So let's do it before attaching anything
* to tree, set linkage between the newborn blocks, write them if sync is
* return = 0, if plain lookup failed.
* return < 0, error case.
*
- *
- * Need to be called with
- * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
- * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ * The ext4_ind_get_blocks() function should be called with
+ * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
+ * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
+ * blocks.
*/
-static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, unsigned int maxblocks,
struct buffer_head *bh_result,
- int create, int extend_disksize)
+ int flags)
{
int err = -EIO;
ext4_lblk_t offsets[4];
int indirect_blks;
int blocks_to_boundary = 0;
int depth;
- struct ext4_inode_info *ei = EXT4_I(inode);
int count = 0;
ext4_fsblk_t first_block = 0;
- loff_t disksize;
-
J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
- J_ASSERT(handle != NULL || create == 0);
+ J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
depth = ext4_block_to_path(inode, iblock, offsets,
&blocks_to_boundary);
}
/* Next simple case - plain lookup or failed read of indirect block */
- if (!create || err == -EIO)
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
goto cleanup;
/*
if (!err)
err = ext4_splice_branch(handle, inode, iblock,
partial, indirect_blks, count);
- /*
- * i_disksize growing is protected by i_data_sem. Don't forget to
- * protect it if you're about to implement concurrent
- * ext4_get_block() -bzzz
- */
- if (!err && extend_disksize) {
- disksize = ((loff_t) iblock + count) << inode->i_blkbits;
- if (disksize > i_size_read(inode))
- disksize = i_size_read(inode);
- if (disksize > ei->i_disksize)
- ei->i_disksize = disksize;
- }
- if (err)
+ else
goto cleanup;
set_buffer_new(bh_result);
ext4_discard_preallocations(inode);
}
+static int check_block_validity(struct inode *inode, sector_t logical,
+ sector_t phys, int len)
+{
+ if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
+ ext4_error(inode->i_sb, "check_block_validity",
+ "inode #%lu logical block %llu mapped to %llu "
+ "(size %d)", inode->i_ino,
+ (unsigned long long) logical,
+ (unsigned long long) phys, len);
+ WARN_ON(1);
+ return -EIO;
+ }
+ return 0;
+}
+
/*
- * The ext4_get_blocks_wrap() function try to look up the requested blocks,
+ * The ext4_get_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
* Otherwise it takes the write lock of the i_data_sem and allocate blocks
* mapped.
*
* If file type is extents based, it will call ext4_ext_get_blocks(),
- * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping
+ * Otherwise, call with ext4_ind_get_blocks() to handle indirect mapping
* based files
*
* On success, it returns the number of blocks being mapped or allocate.
*
* It returns the error in case of allocation failure.
*/
-int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
- unsigned int max_blocks, struct buffer_head *bh,
- int create, int extend_disksize, int flag)
+int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
+ unsigned int max_blocks, struct buffer_head *bh,
+ int flags)
{
int retval;
clear_buffer_unwritten(bh);
/*
- * Try to see if we can get the block without requesting
- * for new file system block.
+ * Try to see if we can get the block without requesting a new
+ * file system block.
*/
down_read((&EXT4_I(inode)->i_data_sem));
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
- bh, 0, 0);
+ bh, 0);
} else {
- retval = ext4_get_blocks_handle(handle,
- inode, block, max_blocks, bh, 0, 0);
+ retval = ext4_ind_get_blocks(handle, inode, block, max_blocks,
+ bh, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
+ if (retval > 0 && buffer_mapped(bh)) {
+ int ret = check_block_validity(inode, block,
+ bh->b_blocknr, retval);
+ if (ret != 0)
+ return ret;
+ }
+
/* If it is only a block(s) look up */
- if (!create)
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
return retval;
/*
* let the underlying get_block() function know to
* avoid double accounting
*/
- if (flag)
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
EXT4_I(inode)->i_delalloc_reserved_flag = 1;
/*
* We need to check for EXT4 here because migrate
*/
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
- bh, create, extend_disksize);
+ bh, flags);
} else {
- retval = ext4_get_blocks_handle(handle, inode, block,
- max_blocks, bh, create, extend_disksize);
+ retval = ext4_ind_get_blocks(handle, inode, block,
+ max_blocks, bh, flags);
if (retval > 0 && buffer_new(bh)) {
/*
}
}
- if (flag) {
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
EXT4_I(inode)->i_delalloc_reserved_flag = 0;
- /*
- * Update reserved blocks/metadata blocks
- * after successful block allocation
- * which were deferred till now
- */
- if ((retval > 0) && buffer_delay(bh))
- ext4_da_update_reserve_space(inode, retval);
- }
+
+ /*
+ * Update reserved blocks/metadata blocks after successful
+ * block allocation which had been deferred till now.
+ */
+ if ((retval > 0) && (flags & EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE))
+ ext4_da_update_reserve_space(inode, retval);
up_write((&EXT4_I(inode)->i_data_sem));
+ if (retval > 0 && buffer_mapped(bh)) {
+ int ret = check_block_validity(inode, block,
+ bh->b_blocknr, retval);
+ if (ret != 0)
+ return ret;
+ }
return retval;
}
started = 1;
}
- ret = ext4_get_blocks_wrap(handle, inode, iblock,
- max_blocks, bh_result, create, 0, 0);
+ ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
+ create ? EXT4_GET_BLOCKS_CREATE : 0);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
{
struct buffer_head dummy;
int fatal = 0, err;
+ int flags = 0;
J_ASSERT(handle != NULL || create == 0);
dummy.b_state = 0;
dummy.b_blocknr = -1000;
buffer_trace_init(&dummy.b_history);
- err = ext4_get_blocks_wrap(handle, inode, block, 1,
- &dummy, create, 1, 0);
+ if (create)
+ flags |= EXT4_GET_BLOCKS_CREATE;
+ err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags);
/*
- * ext4_get_blocks_handle() returns number of blocks
- * mapped. 0 in case of a HOLE.
+ * ext4_get_blocks() returns number of blocks mapped. 0 in
+ * case of a HOLE.
*/
if (err > 0) {
if (err > 1)
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
- int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
+ int ret, needed_blocks;
handle_t *handle;
int retries = 0;
struct page *page;
"dev %s ino %lu pos %llu len %u flags %u",
inode->i_sb->s_id, inode->i_ino,
(unsigned long long) pos, len, flags);
+ /*
+ * Reserve one block more for addition to orphan list in case
+ * we allocate blocks but write fails for some reason
+ */
+ needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
index = pos >> PAGE_CACHE_SHIFT;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
if (ret) {
unlock_page(page);
- ext4_journal_stop(handle);
page_cache_release(page);
/*
* block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold i_mutex.
+ *
+ * Add inode to orphan list in case we crash before
+ * truncate finishes
*/
if (pos + len > inode->i_size)
+ ext4_orphan_add(handle, inode);
+
+ ext4_journal_stop(handle);
+ if (pos + len > inode->i_size) {
vmtruncate(inode, inode->i_size);
+ /*
+ * If vmtruncate failed early the inode might
+ * still be on the orphan list; we need to
+ * make sure the inode is removed from the
+ * orphan list in that case.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
return ext4_handle_dirty_metadata(handle, NULL, bh);
}
+static int ext4_generic_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ int i_size_changed = 0;
+ struct inode *inode = mapping->host;
+ handle_t *handle = ext4_journal_current_handle();
+
+ copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+ /*
+ * No need to use i_size_read() here, the i_size
+ * cannot change under us because we hold i_mutex.
+ *
+ * But it's important to update i_size while still holding page lock:
+ * page writeout could otherwise come in and zero beyond i_size.
+ */
+ if (pos + copied > inode->i_size) {
+ i_size_write(inode, pos + copied);
+ i_size_changed = 1;
+ }
+
+ if (pos + copied > EXT4_I(inode)->i_disksize) {
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_update_i_disksize(inode, (pos + copied));
+ i_size_changed = 1;
+ }
+ unlock_page(page);
+ page_cache_release(page);
+
+ /*
+ * Don't mark the inode dirty under page lock. First, it unnecessarily
+ * makes the holding time of page lock longer. Second, it forces lock
+ * ordering of page lock and transaction start for journaling
+ * filesystems.
+ */
+ if (i_size_changed)
+ ext4_mark_inode_dirty(handle, inode);
+
+ return copied;
+}
+
/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
- loff_t new_i_size;
-
- new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize) {
- ext4_update_i_disksize(inode, new_i_size);
- /* We need to mark inode dirty even if
- * new_i_size is less that inode->i_size
- * bu greater than i_disksize.(hint delalloc)
- */
- ext4_mark_inode_dirty(handle, inode);
- }
-
- ret2 = generic_write_end(file, mapping, pos, len, copied,
+ ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
+ if (pos + len > inode->i_size)
+ /* if we have allocated more blocks and copied
+ * less. We will have blocks allocated outside
+ * inode->i_size. So truncate them
+ */
+ ext4_orphan_add(handle, inode);
if (ret2 < 0)
ret = ret2;
}
if (!ret)
ret = ret2;
+ if (pos + len > inode->i_size) {
+ vmtruncate(inode, inode->i_size);
+ /*
+ * If vmtruncate failed early the inode might still be
+ * on the orphan list; we need to make sure the inode
+ * is removed from the orphan list in that case.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
+
+
return ret ? ret : copied;
}
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
int ret = 0, ret2;
- loff_t new_i_size;
trace_mark(ext4_writeback_write_end,
"dev %s ino %lu pos %llu len %u copied %u",
inode->i_sb->s_id, inode->i_ino,
(unsigned long long) pos, len, copied);
- new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize) {
- ext4_update_i_disksize(inode, new_i_size);
- /* We need to mark inode dirty even if
- * new_i_size is less that inode->i_size
- * bu greater than i_disksize.(hint delalloc)
- */
- ext4_mark_inode_dirty(handle, inode);
- }
-
- ret2 = generic_write_end(file, mapping, pos, len, copied,
+ ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
+ if (pos + len > inode->i_size)
+ /* if we have allocated more blocks and copied
+ * less. We will have blocks allocated outside
+ * inode->i_size. So truncate them
+ */
+ ext4_orphan_add(handle, inode);
+
if (ret2 < 0)
ret = ret2;
if (!ret)
ret = ret2;
+ if (pos + len > inode->i_size) {
+ vmtruncate(inode, inode->i_size);
+ /*
+ * If vmtruncate failed early the inode might still be
+ * on the orphan list; we need to make sure the inode
+ * is removed from the orphan list in that case.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
+
return ret ? ret : copied;
}
}
unlock_page(page);
+ page_cache_release(page);
+ if (pos + len > inode->i_size)
+ /* if we have allocated more blocks and copied
+ * less. We will have blocks allocated outside
+ * inode->i_size. So truncate them
+ */
+ ext4_orphan_add(handle, inode);
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
- page_cache_release(page);
+ if (pos + len > inode->i_size) {
+ vmtruncate(inode, inode->i_size);
+ /*
+ * If vmtruncate failed early the inode might still be
+ * on the orphan list; we need to make sure the inode
+ * is removed from the orphan list in that case.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
return ret ? ret : copied;
}
* @logical - first logical block to start assignment with
*
* the function goes through all passed space and put actual disk
- * block numbers into buffer heads, dropping BH_Delay
+ * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten
*/
static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
struct buffer_head *exbh)
do {
if (cur_logical >= logical + blocks)
break;
- if (buffer_delay(bh)) {
- bh->b_blocknr = pblock;
- clear_buffer_delay(bh);
- bh->b_bdev = inode->i_sb->s_bdev;
- } else if (buffer_unwritten(bh)) {
- bh->b_blocknr = pblock;
- clear_buffer_unwritten(bh);
- set_buffer_mapped(bh);
- set_buffer_new(bh);
- bh->b_bdev = inode->i_sb->s_bdev;
+
+ if (buffer_delay(bh) ||
+ buffer_unwritten(bh)) {
+
+ BUG_ON(bh->b_bdev != inode->i_sb->s_bdev);
+
+ if (buffer_delay(bh)) {
+ clear_buffer_delay(bh);
+ bh->b_blocknr = pblock;
+ } else {
+ /*
+ * unwritten already should have
+ * blocknr assigned. Verify that
+ */
+ clear_buffer_unwritten(bh);
+ BUG_ON(bh->b_blocknr != pblock);
+ }
+
} else if (buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
return;
}
-#define EXT4_DELALLOC_RSVED 1
-static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret;
- unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
- loff_t disksize = EXT4_I(inode)->i_disksize;
- handle_t *handle = NULL;
-
- handle = ext4_journal_current_handle();
- BUG_ON(!handle);
- ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
- bh_result, create, 0, EXT4_DELALLOC_RSVED);
- if (ret <= 0)
- return ret;
-
- bh_result->b_size = (ret << inode->i_blkbits);
-
- if (ext4_should_order_data(inode)) {
- int retval;
- retval = ext4_jbd2_file_inode(handle, inode);
- if (retval)
- /*
- * Failed to add inode for ordered mode. Don't
- * update file size
- */
- return retval;
- }
-
- /*
- * Update on-disk size along with block allocation we don't
- * use 'extend_disksize' as size may change within already
- * allocated block -bzzz
- */
- disksize = ((loff_t) iblock + ret) << inode->i_blkbits;
- if (disksize > i_size_read(inode))
- disksize = i_size_read(inode);
- if (disksize > EXT4_I(inode)->i_disksize) {
- ext4_update_i_disksize(inode, disksize);
- ret = ext4_mark_inode_dirty(handle, inode);
- return ret;
- }
- return 0;
-}
-
/*
* mpage_da_map_blocks - go through given space
*
*/
static int mpage_da_map_blocks(struct mpage_da_data *mpd)
{
- int err = 0;
+ int err, blks, get_blocks_flags;
struct buffer_head new;
- sector_t next;
+ sector_t next = mpd->b_blocknr;
+ unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
+ loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
+ handle_t *handle = NULL;
/*
* We consider only non-mapped and non-allocated blocks
*/
if ((mpd->b_state & (1 << BH_Mapped)) &&
- !(mpd->b_state & (1 << BH_Delay)))
+ !(mpd->b_state & (1 << BH_Delay)) &&
+ !(mpd->b_state & (1 << BH_Unwritten)))
return 0;
- new.b_state = mpd->b_state;
- new.b_blocknr = 0;
- new.b_size = mpd->b_size;
- next = mpd->b_blocknr;
+
/*
- * If we didn't accumulate anything
- * to write simply return
+ * If we didn't accumulate anything to write simply return
*/
- if (!new.b_size)
+ if (!mpd->b_size)
return 0;
- err = ext4_da_get_block_write(mpd->inode, next, &new, 1);
- if (err) {
+ handle = ext4_journal_current_handle();
+ BUG_ON(!handle);
+
+ /*
+ * Call ext4_get_blocks() to allocate any delayed allocation
+ * blocks, or to convert an uninitialized extent to be
+ * initialized (in the case where we have written into
+ * one or more preallocated blocks).
+ *
+ * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to
+ * indicate that we are on the delayed allocation path. This
+ * affects functions in many different parts of the allocation
+ * call path. This flag exists primarily because we don't
+ * want to change *many* call functions, so ext4_get_blocks()
+ * will set the magic i_delalloc_reserved_flag once the
+ * inode's allocation semaphore is taken.
+ *
+ * If the blocks in questions were delalloc blocks, set
+ * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
+ * variables are updated after the blocks have been allocated.
+ */
+ new.b_state = 0;
+ get_blocks_flags = (EXT4_GET_BLOCKS_CREATE |
+ EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+ if (mpd->b_state & (1 << BH_Delay))
+ get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE;
+ blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks,
+ &new, get_blocks_flags);
+ if (blks < 0) {
+ err = blks;
/*
* If get block returns with error we simply
* return. Later writepage will redirty the page and
if (err == -ENOSPC) {
ext4_print_free_blocks(mpd->inode);
}
- /* invlaidate all the pages */
+ /* invalidate all the pages */
ext4_da_block_invalidatepages(mpd, next,
mpd->b_size >> mpd->inode->i_blkbits);
return err;
}
- BUG_ON(new.b_size == 0);
+ BUG_ON(blks == 0);
+
+ new.b_size = (blks << mpd->inode->i_blkbits);
if (buffer_new(&new))
__unmap_underlying_blocks(mpd->inode, &new);
(mpd->b_state & (1 << BH_Unwritten)))
mpage_put_bnr_to_bhs(mpd, next, &new);
+ if (ext4_should_order_data(mpd->inode)) {
+ err = ext4_jbd2_file_inode(handle, mpd->inode);
+ if (err)
+ return err;
+ }
+
+ /*
+ * Update on-disk size along with block allocation.
+ */
+ disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits;
+ if (disksize > i_size_read(mpd->inode))
+ disksize = i_size_read(mpd->inode);
+ if (disksize > EXT4_I(mpd->inode)->i_disksize) {
+ ext4_update_i_disksize(mpd->inode, disksize);
+ return ext4_mark_inode_dirty(handle, mpd->inode);
+ }
+
return 0;
}
return;
}
+static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+{
+ /*
+ * unmapped buffer is possible for holes.
+ * delay buffer is possible with delayed allocation.
+ * We also need to consider unwritten buffer as unmapped.
+ */
+ return (!buffer_mapped(bh) || buffer_delay(bh) ||
+ buffer_unwritten(bh)) && buffer_dirty(bh);
+}
+
/*
* __mpage_da_writepage - finds extent of pages and blocks
*
* Otherwise we won't make progress
* with the page in ext4_da_writepage
*/
- if (buffer_dirty(bh) &&
- (!buffer_mapped(bh) || buffer_delay(bh))) {
+ if (ext4_bh_unmapped_or_delay(NULL, bh)) {
mpage_add_bh_to_extent(mpd, logical,
bh->b_size,
bh->b_state);
}
/*
- * this is a special callback for ->write_begin() only
- * it's intention is to return mapped block or reserve space
+ * This is a special get_blocks_t callback which is used by
+ * ext4_da_write_begin(). It will either return mapped block or
+ * reserve space for a single block.
+ *
+ * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
+ * We also have b_blocknr = -1 and b_bdev initialized properly
+ *
+ * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
+ * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
+ * initialized properly.
*/
static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
- ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0);
+ ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0);
if ((ret == 0) && !buffer_delay(bh_result)) {
/* the block isn't (pre)allocated yet, let's reserve space */
/*
set_buffer_delay(bh_result);
} else if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
- /*
- * With sub-block writes into unwritten extents
- * we also need to mark the buffer as new so that
- * the unwritten parts of the buffer gets correctly zeroed.
- */
- if (buffer_unwritten(bh_result))
+ if (buffer_unwritten(bh_result)) {
+ /* A delayed write to unwritten bh should
+ * be marked new and mapped. Mapped ensures
+ * that we don't do get_block multiple times
+ * when we write to the same offset and new
+ * ensures that we do proper zero out for
+ * partial write.
+ */
set_buffer_new(bh_result);
+ set_buffer_mapped(bh_result);
+ }
ret = 0;
}
return ret;
}
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
-{
- /*
- * unmapped buffer is possible for holes.
- * delay buffer is possible with delayed allocation
- */
- return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh));
-}
-
-static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock,
+/*
+ * This function is used as a standard get_block_t calback function
+ * when there is no desire to allocate any blocks. It is used as a
+ * callback function for block_prepare_write(), nobh_writepage(), and
+ * block_write_full_page(). These functions should only try to map a
+ * single block at a time.
+ *
+ * Since this function doesn't do block allocations even if the caller
+ * requests it by passing in create=1, it is critically important that
+ * any caller checks to make sure that any buffer heads are returned
+ * by this function are either all already mapped or marked for
+ * delayed allocation before calling nobh_writepage() or
+ * block_write_full_page(). Otherwise, b_blocknr could be left
+ * unitialized, and the page write functions will be taken by
+ * surprise.
+ */
+static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret = 0;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+ BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+
/*
* we don't want to do block allocation in writepage
* so call get_block_wrap with create = 0
*/
- ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks,
- bh_result, 0, 0, 0);
+ ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0);
+ BUG_ON(create && ret == 0);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
}
/*
- * get called vi ext4_da_writepages after taking page lock (have journal handle)
- * get called via journal_submit_inode_data_buffers (no journal handle)
- * get called via shrink_page_list via pdflush (no journal handle)
- * or grab_page_cache when doing write_begin (have journal handle)
+ * This function can get called via...
+ * - ext4_da_writepages after taking page lock (have journal handle)
+ * - journal_submit_inode_data_buffers (no journal handle)
+ * - shrink_page_list via pdflush (no journal handle)
+ * - grab_page_cache when doing write_begin (have journal handle)
*/
static int ext4_da_writepage(struct page *page,
struct writeback_control *wbc)
* do block allocation here.
*/
ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
- ext4_normal_get_block_write);
+ noalloc_get_block_write);
if (!ret) {
page_bufs = page_buffers(page);
/* check whether all are mapped and non delay */
}
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
- ret = nobh_writepage(page, ext4_normal_get_block_write, wbc);
+ ret = nobh_writepage(page, noalloc_get_block_write, wbc);
else
- ret = block_write_full_page(page,
- ext4_normal_get_block_write,
- wbc);
+ ret = block_write_full_page(page, noalloc_get_block_write,
+ wbc);
return ret;
}
*pagep = page;
ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- ext4_da_get_block_prep);
+ ext4_da_get_block_prep);
if (ret < 0) {
unlock_page(page);
ext4_journal_stop(handle);
for (i = 0; i < idx; i++)
bh = bh->b_this_page;
- if (!buffer_mapped(bh) || (buffer_delay(bh)))
+ if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
return 0;
return 1;
}
struct inode *inode = page->mapping->host;
if (test_opt(inode->i_sb, NOBH))
- return nobh_writepage(page,
- ext4_normal_get_block_write, wbc);
+ return nobh_writepage(page, noalloc_get_block_write, wbc);
else
- return block_write_full_page(page,
- ext4_normal_get_block_write,
- wbc);
+ return block_write_full_page(page, noalloc_get_block_write,
+ wbc);
}
static int ext4_normal_writepage(struct page *page,
int err;
ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
- ext4_normal_get_block_write);
+ noalloc_get_block_write);
if (ret != 0)
goto out_unlock;
* really know unless we go poke around in the buffer_heads.
* But block_write_full_page will do the right thing.
*/
- return block_write_full_page(page,
- ext4_normal_get_block_write,
- wbc);
+ return block_write_full_page(page, noalloc_get_block_write,
+ wbc);
}
no_write:
redirty_page_for_writepage(wbc, page);
if (!ext4_can_truncate(inode))
return;
- if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
+ if (ei->i_disksize && inode->i_size == 0 &&
+ !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
return ext4_force_commit(inode->i_sb);
}
-int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh)
-{
- int err = 0;
-
- mark_buffer_dirty(bh);
- if (inode && inode_needs_sync(inode)) {
- sync_dirty_buffer(bh);
- if (buffer_req(bh) && !buffer_uptodate(bh)) {
- ext4_error(inode->i_sb, __func__,
- "IO error syncing inode, "
- "inode=%lu, block=%llu",
- inode->i_ino,
- (unsigned long long)bh->b_blocknr);
- err = -EIO;
- }
- }
- return err;
-}
-
/*
* ext4_setattr()
*
*/
int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
- int groups, gdpblocks;
+ ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
+ int gdpblocks;
int idxblocks;
int ret = 0;
groups += nrblocks;
gdpblocks = groups;
- if (groups > EXT4_SB(inode->i_sb)->s_groups_count)
- groups = EXT4_SB(inode->i_sb)->s_groups_count;
+ if (groups > ngroups)
+ groups = ngroups;
if (groups > EXT4_SB(inode->i_sb)->s_gdb_count)
gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count;
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
- * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks.
+ * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
ext4_set_bit(bit, addr);
}
-static inline void mb_set_bit_atomic(spinlock_t *lock, int bit, void *addr)
-{
- addr = mb_correct_addr_and_bit(&bit, addr);
- ext4_set_bit_atomic(lock, bit, addr);
-}
-
static inline void mb_clear_bit(int bit, void *addr)
{
addr = mb_correct_addr_and_bit(&bit, addr);
ext4_clear_bit(bit, addr);
}
-static inline void mb_clear_bit_atomic(spinlock_t *lock, int bit, void *addr)
-{
- addr = mb_correct_addr_and_bit(&bit, addr);
- ext4_clear_bit_atomic(lock, bit, addr);
-}
-
static inline int mb_find_next_zero_bit(void *addr, int max, int start)
{
int fix = 0, ret, tmpmax;
if (unlikely(e4b->bd_info->bb_bitmap == NULL))
return;
- BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group));
+ assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
for (i = 0; i < count; i++) {
if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) {
ext4_fsblk_t blocknr;
if (unlikely(e4b->bd_info->bb_bitmap == NULL))
return;
- BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+ assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
for (i = 0; i < count; i++) {
BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap));
mb_set_bit(first + i, e4b->bd_info->bb_bitmap);
static int ext4_mb_init_cache(struct page *page, char *incore)
{
+ ext4_group_t ngroups;
int blocksize;
int blocks_per_page;
int groups_per_page;
inode = page->mapping->host;
sb = inode->i_sb;
+ ngroups = ext4_get_groups_count(sb);
blocksize = 1 << inode->i_blkbits;
blocks_per_page = PAGE_CACHE_SIZE / blocksize;
for (i = 0; i < groups_per_page; i++) {
struct ext4_group_desc *desc;
- if (first_group + i >= EXT4_SB(sb)->s_groups_count)
+ if (first_group + i >= ngroups)
break;
err = -EIO;
unlock_buffer(bh[i]);
continue;
}
- spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+ ext4_lock_group(sb, first_group + i);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
ext4_init_block_bitmap(sb, bh[i],
first_group + i, desc);
set_bitmap_uptodate(bh[i]);
set_buffer_uptodate(bh[i]);
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+ ext4_unlock_group(sb, first_group + i);
unlock_buffer(bh[i]);
continue;
}
- spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+ ext4_unlock_group(sb, first_group + i);
if (buffer_uptodate(bh[i])) {
/*
* if not uninit if bh is uptodate,
struct ext4_group_info *grinfo;
group = (first_block + i) >> 1;
- if (group >= EXT4_SB(sb)->s_groups_count)
+ if (group >= ngroups)
break;
/*
return 0;
}
-static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len)
+static void mb_clear_bits(void *bm, int cur, int len)
{
__u32 *addr;
cur += 32;
continue;
}
- if (lock)
- mb_clear_bit_atomic(lock, cur, bm);
- else
- mb_clear_bit(cur, bm);
+ mb_clear_bit(cur, bm);
cur++;
}
}
-static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len)
+static void mb_set_bits(void *bm, int cur, int len)
{
__u32 *addr;
cur += 32;
continue;
}
- if (lock)
- mb_set_bit_atomic(lock, cur, bm);
- else
- mb_set_bit(cur, bm);
+ mb_set_bit(cur, bm);
cur++;
}
}
struct super_block *sb = e4b->bd_sb;
BUG_ON(first + count > (sb->s_blocksize << 3));
- BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group));
+ assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
mb_check_buddy(e4b);
mb_free_blocks_double(inode, e4b, first, count);
int ord;
void *buddy;
- BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+ assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
BUG_ON(ex == NULL);
buddy = mb_find_buddy(e4b, order, &max);
BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3));
BUG_ON(e4b->bd_group != ex->fe_group);
- BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+ assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
mb_check_buddy(e4b);
mb_mark_used_double(e4b, start, len);
e4b->bd_info->bb_counters[ord]++;
}
- mb_set_bits(sb_bgl_lock(EXT4_SB(e4b->bd_sb), ex->fe_group),
- EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
+ mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
mb_check_buddy(e4b);
return ret;
unsigned free, fragments;
unsigned i, bits;
int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
- struct ext4_group_desc *desc;
struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
BUG_ON(cr < 0 || cr >= 4);
switch (cr) {
case 0:
BUG_ON(ac->ac_2order == 0);
- /* If this group is uninitialized, skip it initially */
- desc = ext4_get_group_desc(ac->ac_sb, group, NULL);
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
- return 0;
/* Avoid using the first bg of a flexgroup for data files */
if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
int block, pnum;
int blocks_per_page;
int groups_per_page;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
ext4_group_t first_group;
struct ext4_group_info *grp;
/* read all groups the page covers into the cache */
for (i = 0; i < groups_per_page; i++) {
- if ((first_group + i) >= EXT4_SB(sb)->s_groups_count)
+ if ((first_group + i) >= ngroups)
break;
grp = ext4_get_group_info(sb, first_group + i);
/* take all groups write allocation
static noinline_for_stack int
ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
{
- ext4_group_t group;
- ext4_group_t i;
+ ext4_group_t ngroups, group, i;
int cr;
int err = 0;
int bsbits;
sb = ac->ac_sb;
sbi = EXT4_SB(sb);
+ ngroups = ext4_get_groups_count(sb);
BUG_ON(ac->ac_status == AC_STATUS_FOUND);
/* first, try the goal */
*/
group = ac->ac_g_ex.fe_group;
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; group++, i++) {
+ for (i = 0; i < ngroups; group++, i++) {
struct ext4_group_info *grp;
struct ext4_group_desc *desc;
- if (group == EXT4_SB(sb)->s_groups_count)
+ if (group == ngroups)
group = 0;
/* quick check to skip empty groups */
ac->ac_groups_scanned++;
desc = ext4_get_group_desc(sb, group, NULL);
- if (cr == 0 || (desc->bg_flags &
- cpu_to_le16(EXT4_BG_BLOCK_UNINIT) &&
- ac->ac_2order != 0))
+ if (cr == 0)
ext4_mb_simple_scan_group(ac, &e4b);
else if (cr == 1 &&
ac->ac_g_ex.fe_len == sbi->s_stripe)
static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
{
struct super_block *sb = seq->private;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t group;
- if (*pos < 0 || *pos >= sbi->s_groups_count)
+ if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
return NULL;
-
group = *pos + 1;
return (void *) ((unsigned long) group);
}
static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct super_block *sb = seq->private;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t group;
++*pos;
- if (*pos < 0 || *pos >= sbi->s_groups_count)
+ if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
return NULL;
group = *pos + 1;
return (void *) ((unsigned long) group);
if (sbi->s_proc != NULL) {
remove_proc_entry("mb_groups", sbi->s_proc);
- remove_proc_entry("mb_history", sbi->s_proc);
+ if (sbi->s_mb_history_max)
+ remove_proc_entry("mb_history", sbi->s_proc);
}
kfree(sbi->s_mb_history);
}
int i;
if (sbi->s_proc != NULL) {
- proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
- &ext4_mb_seq_history_fops, sb);
+ if (sbi->s_mb_history_max)
+ proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
+ &ext4_mb_seq_history_fops, sb);
proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
&ext4_mb_seq_groups_fops, sb);
}
- sbi->s_mb_history_max = 1000;
sbi->s_mb_history_cur = 0;
spin_lock_init(&sbi->s_mb_history_lock);
i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history);
- sbi->s_mb_history = kzalloc(i, GFP_KERNEL);
+ sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL;
/* if we can't allocate history, then we simple won't use it */
}
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_mb_history h;
- if (unlikely(sbi->s_mb_history == NULL))
+ if (sbi->s_mb_history == NULL)
return;
if (!(ac->ac_op & sbi->s_mb_history_filter))
static int ext4_mb_init_backend(struct super_block *sb)
{
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
ext4_group_t i;
int metalen;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *desc;
/* This is the number of blocks used by GDT */
- num_meta_group_infos = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) -
+ num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) -
1) >> EXT4_DESC_PER_BLOCK_BITS(sb);
/*
for (i = 0; i < num_meta_group_infos; i++) {
if ((i + 1) == num_meta_group_infos)
metalen = sizeof(*meta_group_info) *
- (sbi->s_groups_count -
+ (ngroups -
(i << EXT4_DESC_PER_BLOCK_BITS(sb)));
meta_group_info = kmalloc(metalen, GFP_KERNEL);
if (meta_group_info == NULL) {
sbi->s_group_info[i] = meta_group_info;
}
- for (i = 0; i < sbi->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
desc = ext4_get_group_desc(sb, i, NULL);
if (desc == NULL) {
printk(KERN_ERR
return 0;
}
-/* need to called with ext4 group lock (ext4_lock_group) */
+/* need to called with the ext4 group lock held */
static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
{
struct ext4_prealloc_space *pa;
int ext4_mb_release(struct super_block *sb)
{
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
ext4_group_t i;
int num_meta_group_infos;
struct ext4_group_info *grinfo;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (sbi->s_group_info) {
- for (i = 0; i < sbi->s_groups_count; i++) {
+ for (i = 0; i < ngroups; i++) {
grinfo = ext4_get_group_info(sb, i);
#ifdef DOUBLE_CHECK
kfree(grinfo->bb_bitmap);
ext4_unlock_group(sb, i);
kfree(grinfo);
}
- num_meta_group_infos = (sbi->s_groups_count +
+ num_meta_group_infos = (ngroups +
EXT4_DESC_PER_BLOCK(sb) - 1) >>
EXT4_DESC_PER_BLOCK_BITS(sb);
for (i = 0; i < num_meta_group_infos; i++)
+ le32_to_cpu(es->s_first_data_block);
len = ac->ac_b_ex.fe_len;
- if (in_range(ext4_block_bitmap(sb, gdp), block, len) ||
- in_range(ext4_inode_bitmap(sb, gdp), block, len) ||
- in_range(block, ext4_inode_table(sb, gdp),
- EXT4_SB(sb)->s_itb_per_group) ||
- in_range(block + len - 1, ext4_inode_table(sb, gdp),
- EXT4_SB(sb)->s_itb_per_group)) {
+ if (!ext4_data_block_valid(sbi, block, len)) {
ext4_error(sb, __func__,
- "Allocating block %llu in system zone of %d group\n",
- block, ac->ac_b_ex.fe_group);
+ "Allocating blocks %llu-%llu which overlap "
+ "fs metadata\n", block, block+len);
/* File system mounted not to panic on error
* Fix the bitmap and repeat the block allocation
* We leak some of the blocks here.
*/
- mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group),
- bitmap_bh->b_data, ac->ac_b_ex.fe_start,
- ac->ac_b_ex.fe_len);
+ ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+ mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+ ac->ac_b_ex.fe_len);
+ ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!err)
err = -EAGAIN;
goto out_err;
}
+
+ ext4_lock_group(sb, ac->ac_b_ex.fe_group);
#ifdef AGGRESSIVE_CHECK
{
int i;
}
}
#endif
- spin_lock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
- mb_set_bits(NULL, bitmap_bh->b_data,
- ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len);
+ mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
ext4_free_blks_set(sb, gdp,
len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
ext4_free_blks_set(sb, gdp, len);
gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
- spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
+
+ ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
/*
* Now reduce the dirty block count also. Should not go negative
* the function goes through all block freed in the group
* but not yet committed and marks them used in in-core bitmap.
* buddy must be generated from this bitmap
- * Need to be called with ext4 group lock (ext4_lock_group)
+ * Need to be called with the ext4 group lock held
*/
static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
ext4_group_t group)
while (n) {
entry = rb_entry(n, struct ext4_free_data, node);
- mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
- bitmap, entry->start_blk,
- entry->count);
+ mb_set_bits(bitmap, entry->start_blk, entry->count);
n = rb_next(n);
}
return;
/*
* the function goes through all preallocation in this group and marks them
* used in in-core bitmap. buddy must be generated from this bitmap
- * Need to be called with ext4 group lock (ext4_lock_group)
+ * Need to be called with ext4 group lock held
*/
static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group)
if (unlikely(len == 0))
continue;
BUG_ON(groupnr != group);
- mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
- bitmap, start, len);
+ mb_set_bits(bitmap, start, len);
preallocated += len;
count++;
}
static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
{
struct super_block *sb = ac->ac_sb;
- ext4_group_t i;
+ ext4_group_t ngroups, i;
printk(KERN_ERR "EXT4-fs: Can't allocate:"
" Allocation context details:\n");
printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned,
ac->ac_found);
printk(KERN_ERR "EXT4-fs: groups: \n");
- for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ ngroups = ext4_get_groups_count(sb);
+ for (i = 0; i < ngroups; i++) {
struct ext4_group_info *grp = ext4_get_group_info(sb, i);
struct ext4_prealloc_space *pa;
ext4_grpblk_t start;
static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
{
- ext4_group_t i;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
int ret;
int freed = 0;
trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d",
sb->s_id, needed);
- for (i = 0; i < EXT4_SB(sb)->s_groups_count && needed > 0; i++) {
+ for (i = 0; i < ngroups && needed > 0; i++) {
ret = ext4_mb_discard_group_preallocations(sb, i, needed);
freed += ret;
needed -= ret;
new_entry->group = block_group;
new_entry->count = count;
new_entry->t_tid = handle->h_transaction->t_tid;
+
ext4_lock_group(sb, block_group);
- mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
- bit, count);
+ mb_clear_bits(bitmap_bh->b_data, bit, count);
ext4_mb_free_metadata(handle, &e4b, new_entry);
- ext4_unlock_group(sb, block_group);
} else {
- ext4_lock_group(sb, block_group);
/* need to update group_info->bb_free and bitmap
* with group lock held. generate_buddy look at
* them with group lock_held
*/
- mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
- bit, count);
+ ext4_lock_group(sb, block_group);
+ mb_clear_bits(bitmap_bh->b_data, bit, count);
mb_free_blocks(inode, &e4b, bit, count);
ext4_mb_return_to_preallocation(inode, &e4b, block, count);
- ext4_unlock_group(sb, block_group);
}
- spin_lock(sb_bgl_lock(sbi, block_group));
ret = ext4_free_blks_count(sb, gdp) + count;
ext4_free_blks_set(sb, gdp, ret);
gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
- spin_unlock(sb_bgl_lock(sbi, block_group));
+ ext4_unlock_group(sb, block_group);
percpu_counter_add(&sbi->s_freeblocks_counter, count);
if (sbi->s_log_groups_per_flex) {
#include <linux/mutex.h>
#include "ext4_jbd2.h"
#include "ext4.h"
-#include "group.h"
/*
* with AGGRESSIVE_CHECK allocator runs consistency checks over
#include "ext4.h"
#include "ext4_jbd2.h"
-#include "namei.h"
#include "xattr.h"
#include "acl.h"
ext4fs_dirhash(de->name, de->name_len, &h);
map_tail--;
map_tail->hash = h.hash;
- map_tail->offs = (u16) ((char *) de - base);
+ map_tail->offs = ((char *) de - base)>>2;
map_tail->size = le16_to_cpu(de->rec_len);
count++;
cond_resched();
unsigned rec_len = 0;
while (count--) {
- struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + map->offs);
+ struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)
+ (from + (map->offs<<2));
rec_len = EXT4_DIR_REC_LEN(de->name_len);
memcpy (to, de, rec_len);
((struct ext4_dir_entry_2 *) to)->rec_len =
if (!ext4_handle_valid(handle))
return 0;
- lock_super(sb);
+ mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
if (!list_empty(&EXT4_I(inode)->i_orphan))
goto out_unlock;
/* @@@ FIXME: Observation from aviro:
* I think I can trigger J_ASSERT in ext4_orphan_add(). We block
- * here (on lock_super()), so race with ext4_link() which might bump
+ * here (on s_orphan_lock), so race with ext4_link() which might bump
* ->i_nlink. For, say it, character device. Not a regular file,
* not a directory, not a symlink and ->i_nlink > 0.
+ *
+ * tytso, 4/25/2009: I'm not sure how that could happen;
+ * shouldn't the fs core protect us from these sort of
+ * unlink()/link() races?
*/
J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
jbd_debug(4, "orphan inode %lu will point to %d\n",
inode->i_ino, NEXT_ORPHAN(inode));
out_unlock:
- unlock_super(sb);
+ mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
ext4_std_error(inode->i_sb, err);
return err;
}
if (!ext4_handle_valid(handle))
return 0;
- lock_super(inode->i_sb);
- if (list_empty(&ei->i_orphan)) {
- unlock_super(inode->i_sb);
- return 0;
- }
+ mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+ if (list_empty(&ei->i_orphan))
+ goto out;
ino_next = NEXT_ORPHAN(inode);
prev = ei->i_orphan.prev;
out_err:
ext4_std_error(inode->i_sb, err);
out:
- unlock_super(inode->i_sb);
+ mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
return err;
out_brelse:
.removexattr = generic_removexattr,
#endif
.permission = ext4_permission,
+ .fiemap = ext4_fiemap,
};
const struct inode_operations ext4_special_inode_operations = {
+++ /dev/null
-/* linux/fs/ext4/namei.h
- *
- * Copyright (C) 2005 Simtec Electronics
- * Ben Dooks <ben@simtec.co.uk>
- *
-*/
-
-extern struct dentry *ext4_get_parent(struct dentry *child);
#include <linux/slab.h>
#include "ext4_jbd2.h"
-#include "group.h"
#define outside(b, first, last) ((b) < (first) || (b) >= (last))
#define inside(b, first, last) ((b) >= (first) && (b) < (last))
if (IS_ERR(handle))
return PTR_ERR(handle);
- lock_super(sb);
+ mutex_lock(&sbi->s_resize_lock);
if (input->group != sbi->s_groups_count) {
err = -EBUSY;
goto exit_journal;
brelse(bh);
exit_journal:
- unlock_super(sb);
+ mutex_unlock(&sbi->s_resize_lock);
if ((err2 = ext4_journal_stop(handle)) && !err)
err = err2;
* important part is that the new block and inode counts are in the backup
* superblocks, and the location of the new group metadata in the GDT backups.
*
- * We do not need lock_super() for this, because these blocks are not
- * otherwise touched by the filesystem code when it is mounted. We don't
- * need to worry about last changing from sbi->s_groups_count, because the
- * worst that can happen is that we do not copy the full number of backups
- * at this time. The resize which changed s_groups_count will backup again.
+ * We do not need take the s_resize_lock for this, because these
+ * blocks are not otherwise touched by the filesystem code when it is
+ * mounted. We don't need to worry about last changing from
+ * sbi->s_groups_count, because the worst that can happen is that we
+ * do not copy the full number of backups at this time. The resize
+ * which changed s_groups_count will backup again.
*/
static void update_backups(struct super_block *sb,
int blk_off, char *data, int size)
goto exit_put;
}
- lock_super(sb);
+ mutex_lock(&sbi->s_resize_lock);
if (input->group != sbi->s_groups_count) {
ext4_warning(sb, __func__,
"multiple resizers run on filesystem!");
/*
* OK, now we've set up the new group. Time to make it active.
*
- * Current kernels don't lock all allocations via lock_super(),
+ * We do not lock all allocations via s_resize_lock
* so we have to be safe wrt. concurrent accesses the group
* data. So we need to be careful to set all of the relevant
* group descriptor data etc. *before* we enable the group.
*
* The precise rules we use are:
*
- * * Writers of s_groups_count *must* hold lock_super
+ * * Writers of s_groups_count *must* hold s_resize_lock
* AND
* * Writers must perform a smp_wmb() after updating all dependent
* data and before modifying the groups count
*
- * * Readers must hold lock_super() over the access
+ * * Readers must hold s_resize_lock over the access
* OR
* * Readers must perform an smp_rmb() after reading the groups count
* and before reading any dependent data.
sb->s_dirt = 1;
exit_journal:
- unlock_super(sb);
+ mutex_unlock(&sbi->s_resize_lock);
if ((err2 = ext4_journal_stop(handle)) && !err)
err = err2;
if (!err) {
/* We don't need to worry about locking wrt other resizers just
* yet: we're going to revalidate es->s_blocks_count after
- * taking lock_super() below. */
+ * taking the s_resize_lock below. */
o_blocks_count = ext4_blocks_count(es);
o_groups_count = EXT4_SB(sb)->s_groups_count;
goto exit_put;
}
- lock_super(sb);
+ mutex_lock(&EXT4_SB(sb)->s_resize_lock);
if (o_blocks_count != ext4_blocks_count(es)) {
ext4_warning(sb, __func__,
"multiple resizers run on filesystem!");
- unlock_super(sb);
+ mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
ext4_journal_stop(handle);
err = -EBUSY;
goto exit_put;
EXT4_SB(sb)->s_sbh))) {
ext4_warning(sb, __func__,
"error %d on journal write access", err);
- unlock_super(sb);
+ mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
ext4_journal_stop(handle);
goto exit_put;
}
ext4_blocks_count_set(es, o_blocks_count + add);
ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
sb->s_dirt = 1;
- unlock_super(sb);
+ mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
/* We add the blocks to the bitmap and set the group need init bit */
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/time.h>
+#include <linux/vmalloc.h>
#include <linux/jbd2.h>
#include <linux/slab.h>
#include <linux/init.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
-#include "namei.h"
-#include "group.h"
+
+static int default_mb_history_length = 1000;
+
+module_param_named(default_mb_history_length, default_mb_history_length,
+ int, 0644);
+MODULE_PARM_DESC(default_mb_history_length,
+ "Default number of entries saved for mb_history");
struct proc_dir_entry *ext4_proc_root;
static struct kset *ext4_kset;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
-static int ext4_commit_super(struct super_block *sb,
- struct ext4_super_block *es, int sync);
+static int ext4_commit_super(struct super_block *sb, int sync);
static void ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static void ext4_clear_journal_err(struct super_block *sb,
{
return le32_to_cpu(bg->bg_block_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
+ (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
{
return le32_to_cpu(bg->bg_inode_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
+ (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_table(struct super_block *sb,
{
return le32_to_cpu(bg->bg_inode_table_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
+ (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
__u32 ext4_free_blks_count(struct super_block *sb,
{
return le16_to_cpu(bg->bg_free_blocks_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
+ (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
}
__u32 ext4_free_inodes_count(struct super_block *sb,
{
return le16_to_cpu(bg->bg_free_inodes_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+ (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
}
__u32 ext4_used_dirs_count(struct super_block *sb,
{
return le16_to_cpu(bg->bg_used_dirs_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
+ (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
}
__u32 ext4_itable_unused_count(struct super_block *sb,
{
return le16_to_cpu(bg->bg_itable_unused_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
+ (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
}
void ext4_block_bitmap_set(struct super_block *sb,
journal = EXT4_SB(sb)->s_journal;
if (journal) {
if (is_journal_aborted(journal)) {
- ext4_abort(sb, __func__,
- "Detected aborted journal");
+ ext4_abort(sb, __func__, "Detected aborted journal");
return ERR_PTR(-EROFS);
}
return jbd2_journal_start(journal, nblocks);
jbd2_journal_abort(journal, -EIO);
}
if (test_opt(sb, ERRORS_RO)) {
- printk(KERN_CRIT "Remounting filesystem read-only\n");
+ ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
sb->s_flags |= MS_RDONLY;
}
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
{
va_list args;
- printk(KERN_CRIT "ext4_abort called.\n");
-
va_start(args, fmt);
printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
vprintk(fmt, args);
if (sb->s_flags & MS_RDONLY)
return;
- printk(KERN_CRIT "Remounting filesystem read-only\n");
+ ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
sb->s_flags |= MS_RDONLY;
EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
}
+void ext4_msg (struct super_block * sb, const char *prefix,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ printk("%sEXT4-fs (%s): ", prefix, sb->s_id);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+}
+
void ext4_warning(struct super_block *sb, const char *function,
const char *fmt, ...)
{
}
void ext4_grp_locked_error(struct super_block *sb, ext4_group_t grp,
- const char *function, const char *fmt, ...)
+ const char *function, const char *fmt, ...)
__releases(bitlock)
__acquires(bitlock)
{
if (test_opt(sb, ERRORS_CONT)) {
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, es, 0);
+ ext4_commit_super(sb, 0);
return;
}
ext4_unlock_group(sb, grp);
return;
}
-
void ext4_update_dynamic_rev(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
/*
* Open the external journal device
*/
-static struct block_device *ext4_blkdev_get(dev_t dev)
+static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
{
struct block_device *bdev;
char b[BDEVNAME_SIZE];
return bdev;
fail:
- printk(KERN_ERR "EXT4-fs: failed to open journal device %s: %ld\n",
+ ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
}
{
struct list_head *l;
- printk(KERN_ERR "sb orphan head is %d\n",
- le32_to_cpu(sbi->s_es->s_last_orphan));
+ ext4_msg(sb, KERN_ERR, "sb orphan head is %d",
+ le32_to_cpu(sbi->s_es->s_last_orphan));
printk(KERN_ERR "sb_info orphan list:\n");
list_for_each(l, &sbi->s_orphan) {
struct ext4_super_block *es = sbi->s_es;
int i, err;
+ ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
}
if (sbi->s_proc) {
remove_proc_entry(sb->s_id, ext4_proc_root);
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_group_desc);
- kfree(sbi->s_flex_groups);
+ if (is_vmalloc_addr(sbi->s_flex_groups))
+ vfree(sbi->s_flex_groups);
+ else
+ kfree(sbi->s_flex_groups);
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
lock_kernel();
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
- return;
}
static struct kmem_cache *ext4_inode_cachep;
ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
+
#ifdef CONFIG_EXT4_FS_POSIX_ACL
ei->i_acl = EXT4_ACL_NOT_CACHED;
ei->i_default_acl = EXT4_ACL_NOT_CACHED;
ei->i_allocated_meta_blocks = 0;
ei->i_delalloc_reserved_flag = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
+
return &ei->vfs_inode;
}
static void ext4_destroy_inode(struct inode *inode)
{
if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
- printk("EXT4 Inode %p: orphan list check failed!\n",
- EXT4_I(inode));
+ ext4_msg(inode->i_sb, KERN_ERR,
+ "Inode %lu (%p): orphan list check failed!",
+ inode->i_ino, EXT4_I(inode));
print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
EXT4_I(inode), sizeof(struct ext4_inode_info),
true);
seq_puts(seq, ",noauto_da_alloc");
ext4_show_quota_options(seq, sb);
+
return 0;
}
-
static struct inode *ext4_nfs_get_inode(struct super_block *sb,
- u64 ino, u32 generation)
+ u64 ino, u32 generation)
{
struct inode *inode;
}
static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid,
- int fh_len, int fh_type)
+ int fh_len, int fh_type)
{
return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
ext4_nfs_get_inode);
}
static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
- int fh_len, int fh_type)
+ int fh_len, int fh_type)
{
return generic_fh_to_parent(sb, fid, fh_len, fh_type,
ext4_nfs_get_inode);
* which would prevent try_to_free_buffers() from freeing them, we must use
* jbd2 layer's try_to_free_buffers() function to release them.
*/
-static int bdev_try_to_free_page(struct super_block *sb, struct page *page, gfp_t wait)
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+ gfp_t wait)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
.dirty_inode = ext4_dirty_inode,
.delete_inode = ext4_delete_inode,
.put_super = ext4_put_super,
- .write_super = ext4_write_super,
.sync_fs = ext4_sync_fs,
.freeze_fs = ext4_freeze,
.unfreeze_fs = ext4_unfreeze,
.bdev_try_to_free_page = bdev_try_to_free_page,
};
+static const struct super_operations ext4_nojournal_sops = {
+ .alloc_inode = ext4_alloc_inode,
+ .destroy_inode = ext4_destroy_inode,
+ .write_inode = ext4_write_inode,
+ .dirty_inode = ext4_dirty_inode,
+ .delete_inode = ext4_delete_inode,
+ .write_super = ext4_write_super,
+ .put_super = ext4_put_super,
+ .statfs = ext4_statfs,
+ .remount_fs = ext4_remount,
+ .clear_inode = ext4_clear_inode,
+ .show_options = ext4_show_options,
+#ifdef CONFIG_QUOTA
+ .quota_read = ext4_quota_read,
+ .quota_write = ext4_quota_write,
+#endif
+ .bdev_try_to_free_page = bdev_try_to_free_page,
+};
+
static const struct export_operations ext4_export_ops = {
.fh_to_dentry = ext4_fh_to_dentry,
.fh_to_parent = ext4_fh_to_parent,
Opt_journal_update, Opt_journal_dev,
Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
- Opt_data_err_abort, Opt_data_err_ignore,
+ Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize,
Opt_usrquota, Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
+ Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio
};
{Opt_data_writeback, "data=writeback"},
{Opt_data_err_abort, "data_err=abort"},
{Opt_data_err_ignore, "data_err=ignore"},
+ {Opt_mb_history_length, "mb_history_length=%u"},
{Opt_offusrjquota, "usrjquota="},
{Opt_usrjquota, "usrjquota=%s"},
{Opt_offgrpjquota, "grpjquota="},
{Opt_resize, "resize"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
+ {Opt_block_validity, "block_validity"},
+ {Opt_noblock_validity, "noblock_validity"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
{Opt_journal_ioprio, "journal_ioprio=%u"},
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
if (!options || strncmp(options, "sb=", 3) != 0)
return 1; /* Default location */
+
options += 3;
- /*todo: use simple_strtoll with >32bit ext4 */
+ /* TODO: use simple_strtoll with >32bit ext4 */
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ',') {
printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
if (*options == ',')
options++;
*data = (void *) options;
+
return sb_block;
}
#else
case Opt_user_xattr:
case Opt_nouser_xattr:
- printk(KERN_ERR "EXT4 (no)user_xattr options "
- "not supported\n");
+ ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported");
break;
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
#else
case Opt_acl:
case Opt_noacl:
- printk(KERN_ERR "EXT4 (no)acl options "
- "not supported\n");
+ ext4_msg(sb, KERN_ERR, "(no)acl options not supported");
break;
#endif
case Opt_journal_update:
user to specify an existing inode to be the
journal file. */
if (is_remount) {
- printk(KERN_ERR "EXT4-fs: cannot specify "
- "journal on remount\n");
+ ext4_msg(sb, KERN_ERR,
+ "Cannot specify journal on remount");
return 0;
}
set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
break;
case Opt_journal_dev:
if (is_remount) {
- printk(KERN_ERR "EXT4-fs: cannot specify "
- "journal on remount\n");
+ ext4_msg(sb, KERN_ERR,
+ "Cannot specify journal on remount");
return 0;
}
if (match_int(&args[0], &option))
if (is_remount) {
if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS)
!= data_opt) {
- printk(KERN_ERR
- "EXT4-fs: cannot change data "
- "mode on remount\n");
+ ext4_msg(sb, KERN_ERR,
+ "Cannot change data mode on remount");
return 0;
}
} else {
case Opt_data_err_ignore:
clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
break;
+ case Opt_mb_history_length:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0)
+ return 0;
+ sbi->s_mb_history_max = option;
+ break;
#ifdef CONFIG_QUOTA
case Opt_usrjquota:
qtype = USRQUOTA;
set_qf_name:
if (sb_any_quota_loaded(sb) &&
!sbi->s_qf_names[qtype]) {
- printk(KERN_ERR
- "EXT4-fs: Cannot change journaled "
- "quota options when quota turned on.\n");
+ ext4_msg(sb, KERN_ERR,
+ "Cannot change journaled "
+ "quota options when quota turned on");
return 0;
}
qname = match_strdup(&args[0]);
if (!qname) {
- printk(KERN_ERR
- "EXT4-fs: not enough memory for "
- "storing quotafile name.\n");
+ ext4_msg(sb, KERN_ERR,
+ "Not enough memory for "
+ "storing quotafile name");
return 0;
}
if (sbi->s_qf_names[qtype] &&
strcmp(sbi->s_qf_names[qtype], qname)) {
- printk(KERN_ERR
- "EXT4-fs: %s quota file already "
- "specified.\n", QTYPE2NAME(qtype));
+ ext4_msg(sb, KERN_ERR,
+ "%s quota file already "
+ "specified", QTYPE2NAME(qtype));
kfree(qname);
return 0;
}
sbi->s_qf_names[qtype] = qname;
if (strchr(sbi->s_qf_names[qtype], '/')) {
- printk(KERN_ERR
- "EXT4-fs: quotafile must be on "
- "filesystem root.\n");
+ ext4_msg(sb, KERN_ERR,
+ "quotafile must be on "
+ "filesystem root");
kfree(sbi->s_qf_names[qtype]);
sbi->s_qf_names[qtype] = NULL;
return 0;
clear_qf_name:
if (sb_any_quota_loaded(sb) &&
sbi->s_qf_names[qtype]) {
- printk(KERN_ERR "EXT4-fs: Cannot change "
+ ext4_msg(sb, KERN_ERR, "Cannot change "
"journaled quota options when "
- "quota turned on.\n");
+ "quota turned on");
return 0;
}
/*
set_qf_format:
if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != qfmt) {
- printk(KERN_ERR "EXT4-fs: Cannot change "
+ ext4_msg(sb, KERN_ERR, "Cannot change "
"journaled quota options when "
- "quota turned on.\n");
+ "quota turned on");
return 0;
}
sbi->s_jquota_fmt = qfmt;
break;
case Opt_noquota:
if (sb_any_quota_loaded(sb)) {
- printk(KERN_ERR "EXT4-fs: Cannot change quota "
- "options when quota turned on.\n");
+ ext4_msg(sb, KERN_ERR, "Cannot change quota "
+ "options when quota turned on");
return 0;
}
clear_opt(sbi->s_mount_opt, QUOTA);
case Opt_quota:
case Opt_usrquota:
case Opt_grpquota:
- printk(KERN_ERR
- "EXT4-fs: quota options not supported.\n");
+ ext4_msg(sb, KERN_ERR,
+ "quota options not supported");
break;
case Opt_usrjquota:
case Opt_grpjquota:
case Opt_offgrpjquota:
case Opt_jqfmt_vfsold:
case Opt_jqfmt_vfsv0:
- printk(KERN_ERR
- "EXT4-fs: journaled quota options not "
- "supported.\n");
+ ext4_msg(sb, KERN_ERR,
+ "journaled quota options not supported");
break;
case Opt_noquota:
break;
break;
case Opt_resize:
if (!is_remount) {
- printk("EXT4-fs: resize option only available "
- "for remount\n");
+ ext4_msg(sb, KERN_ERR,
+ "resize option only available "
+ "for remount");
return 0;
}
if (match_int(&args[0], &option) != 0)
case Opt_delalloc:
set_opt(sbi->s_mount_opt, DELALLOC);
break;
+ case Opt_block_validity:
+ set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ break;
+ case Opt_noblock_validity:
+ clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ break;
case Opt_inode_readahead_blks:
if (match_int(&args[0], &option))
return 0;
if (option < 0 || option > (1 << 30))
return 0;
- if (option & (option - 1)) {
- printk(KERN_ERR "EXT4-fs: inode_readahead_blks"
- " must be a power of 2\n");
+ if (!is_power_of_2(option)) {
+ ext4_msg(sb, KERN_ERR,
+ "EXT4-fs: inode_readahead_blks"
+ " must be a power of 2");
return 0;
}
sbi->s_inode_readahead_blks = option;
set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
break;
default:
- printk(KERN_ERR
- "EXT4-fs: Unrecognized mount option \"%s\" "
- "or missing value\n", p);
+ ext4_msg(sb, KERN_ERR,
+ "Unrecognized mount option \"%s\" "
+ "or missing value", p);
return 0;
}
}
(sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) ||
(sbi->s_qf_names[GRPQUOTA] &&
(sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) {
- printk(KERN_ERR "EXT4-fs: old and new quota "
- "format mixing.\n");
+ ext4_msg(sb, KERN_ERR, "old and new quota "
+ "format mixing");
return 0;
}
if (!sbi->s_jquota_fmt) {
- printk(KERN_ERR "EXT4-fs: journaled quota format "
- "not specified.\n");
+ ext4_msg(sb, KERN_ERR, "journaled quota format "
+ "not specified");
return 0;
}
} else {
if (sbi->s_jquota_fmt) {
- printk(KERN_ERR "EXT4-fs: journaled quota format "
+ ext4_msg(sb, KERN_ERR, "journaled quota format "
"specified with no journaling "
- "enabled.\n");
+ "enabled");
return 0;
}
}
int res = 0;
if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
- printk(KERN_ERR "EXT4-fs warning: revision level too high, "
- "forcing read-only mode\n");
+ ext4_msg(sb, KERN_ERR, "revision level too high, "
+ "forcing read-only mode");
res = MS_RDONLY;
}
if (read_only)
return res;
if (!(sbi->s_mount_state & EXT4_VALID_FS))
- printk(KERN_WARNING "EXT4-fs warning: mounting unchecked fs, "
- "running e2fsck is recommended\n");
+ ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
+ "running e2fsck is recommended");
else if ((sbi->s_mount_state & EXT4_ERROR_FS))
- printk(KERN_WARNING
- "EXT4-fs warning: mounting fs with errors, "
- "running e2fsck is recommended\n");
+ ext4_msg(sb, KERN_WARNING,
+ "warning: mounting fs with errors, "
+ "running e2fsck is recommended");
else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
le16_to_cpu(es->s_mnt_count) >=
(unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
- printk(KERN_WARNING
- "EXT4-fs warning: maximal mount count reached, "
- "running e2fsck is recommended\n");
+ ext4_msg(sb, KERN_WARNING,
+ "warning: maximal mount count reached, "
+ "running e2fsck is recommended");
else if (le32_to_cpu(es->s_checkinterval) &&
(le32_to_cpu(es->s_lastcheck) +
le32_to_cpu(es->s_checkinterval) <= get_seconds()))
- printk(KERN_WARNING
- "EXT4-fs warning: checktime reached, "
- "running e2fsck is recommended\n");
- if (!sbi->s_journal)
+ ext4_msg(sb, KERN_WARNING,
+ "warning: checktime reached, "
+ "running e2fsck is recommended");
+ if (!sbi->s_journal)
es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
if (sbi->s_journal)
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04lx]\n",
sbi->s_mount_opt);
if (EXT4_SB(sb)->s_journal) {
- printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
- sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
+ ext4_msg(sb, KERN_INFO, "%s journal on %s",
+ EXT4_SB(sb)->s_journal->j_inode ? "internal" :
"external", EXT4_SB(sb)->s_journal->j_devname);
} else {
- printk(KERN_INFO "EXT4 FS on %s, no journal\n", sb->s_id);
+ ext4_msg(sb, KERN_INFO, "no journal");
}
return res;
}
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = NULL;
- struct buffer_head *bh;
ext4_group_t flex_group_count;
ext4_group_t flex_group;
int groups_per_flex = 0;
+ size_t size;
int i;
if (!sbi->s_es->s_log_groups_per_flex) {
flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
- sbi->s_flex_groups = kzalloc(flex_group_count *
- sizeof(struct flex_groups), GFP_KERNEL);
+ size = flex_group_count * sizeof(struct flex_groups);
+ sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
+ if (sbi->s_flex_groups == NULL) {
+ sbi->s_flex_groups = vmalloc(size);
+ if (sbi->s_flex_groups)
+ memset(sbi->s_flex_groups, 0, size);
+ }
if (sbi->s_flex_groups == NULL) {
- printk(KERN_ERR "EXT4-fs: not enough memory for "
- "%u flex groups\n", flex_group_count);
+ ext4_msg(sb, KERN_ERR, "not enough memory for "
+ "%u flex groups", flex_group_count);
goto failed;
}
for (i = 0; i < sbi->s_groups_count; i++) {
- gdp = ext4_get_group_desc(sb, i, &bh);
+ gdp = ext4_get_group_desc(sb, i, NULL);
flex_group = ext4_flex_group(sbi, i);
atomic_set(&sbi->s_flex_groups[flex_group].free_inodes,
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap < first_block || block_bitmap > last_block) {
- printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
- "(block %llu)!\n", i, block_bitmap);
+ "(block %llu)!", i, block_bitmap);
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
if (inode_bitmap < first_block || inode_bitmap > last_block) {
- printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
- "(block %llu)!\n", i, inode_bitmap);
+ "(block %llu)!", i, inode_bitmap);
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
- printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode table for group %u not in group "
- "(block %llu)!\n", i, inode_table);
+ "(block %llu)!", i, inode_table);
return 0;
}
- spin_lock(sb_bgl_lock(sbi, i));
+ ext4_lock_group(sb, i);
if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
- printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Checksum for group %u failed (%u!=%u)\n",
- i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
- gdp)), le16_to_cpu(gdp->bg_checksum));
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Checksum for group %u failed (%u!=%u)",
+ i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
+ gdp)), le16_to_cpu(gdp->bg_checksum));
if (!(sb->s_flags & MS_RDONLY)) {
- spin_unlock(sb_bgl_lock(sbi, i));
+ ext4_unlock_group(sb, i);
return 0;
}
}
- spin_unlock(sb_bgl_lock(sbi, i));
+ ext4_unlock_group(sb, i);
if (!flexbg_flag)
first_block += EXT4_BLOCKS_PER_GROUP(sb);
}
ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
- sbi->s_es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
+ sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
return 1;
}
}
if (bdev_read_only(sb->s_bdev)) {
- printk(KERN_ERR "EXT4-fs: write access "
- "unavailable, skipping orphan cleanup.\n");
+ ext4_msg(sb, KERN_ERR, "write access "
+ "unavailable, skipping orphan cleanup");
return;
}
}
if (s_flags & MS_RDONLY) {
- printk(KERN_INFO "EXT4-fs: %s: orphan cleanup on readonly fs\n",
- sb->s_id);
+ ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
sb->s_flags &= ~MS_RDONLY;
}
#ifdef CONFIG_QUOTA
if (EXT4_SB(sb)->s_qf_names[i]) {
int ret = ext4_quota_on_mount(sb, i);
if (ret < 0)
- printk(KERN_ERR
- "EXT4-fs: Cannot turn on journaled "
- "quota: error %d\n", ret);
+ ext4_msg(sb, KERN_ERR,
+ "Cannot turn on journaled "
+ "quota: error %d", ret);
}
}
#endif
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
vfs_dq_init(inode);
if (inode->i_nlink) {
- printk(KERN_DEBUG
- "%s: truncating inode %lu to %lld bytes\n",
+ ext4_msg(sb, KERN_DEBUG,
+ "%s: truncating inode %lu to %lld bytes",
__func__, inode->i_ino, inode->i_size);
jbd_debug(2, "truncating inode %lu to %lld bytes\n",
inode->i_ino, inode->i_size);
ext4_truncate(inode);
nr_truncates++;
} else {
- printk(KERN_DEBUG
- "%s: deleting unreferenced inode %lu\n",
+ ext4_msg(sb, KERN_DEBUG,
+ "%s: deleting unreferenced inode %lu",
__func__, inode->i_ino);
jbd_debug(2, "deleting unreferenced inode %lu\n",
inode->i_ino);
#define PLURAL(x) (x), ((x) == 1) ? "" : "s"
if (nr_orphans)
- printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n",
- sb->s_id, PLURAL(nr_orphans));
+ ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted",
+ PLURAL(nr_orphans));
if (nr_truncates)
- printk(KERN_INFO "EXT4-fs: %s: %d truncate%s cleaned up\n",
- sb->s_id, PLURAL(nr_truncates));
+ ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
+ PLURAL(nr_truncates));
#ifdef CONFIG_QUOTA
/* Turn quotas off */
for (i = 0; i < MAXQUOTAS; i++) {
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
}
+
/*
* Maximal extent format file size.
* Resulting logical blkno at s_maxbytes must fit in our on-disk
loff_t res = EXT4_NDIR_BLOCKS;
int meta_blocks;
loff_t upper_limit;
- /* This is calculated to be the largest file size for a
- * dense, bitmapped file such that the total number of
- * sectors in the file, including data and all indirect blocks,
- * does not exceed 2^48 -1
- * __u32 i_blocks_lo and _u16 i_blocks_high representing the
- * total number of 512 bytes blocks of the file
+ /* This is calculated to be the largest file size for a dense, block
+ * mapped file such that the file's total number of 512-byte sectors,
+ * including data and all indirect blocks, does not exceed (2^48 - 1).
+ *
+ * __u32 i_blocks_lo and _u16 i_blocks_high represent the total
+ * number of 512-byte sectors of the file.
*/
if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
/*
- * !has_huge_files or CONFIG_LBD is not enabled
- * implies the inode i_block represent total blocks in
- * 512 bytes 32 == size of vfs inode i_blocks * 8
+ * !has_huge_files or CONFIG_LBD not enabled implies that
+ * the inode i_block field represents total file blocks in
+ * 2^32 512-byte sectors == size of vfs inode i_blocks * 8
*/
upper_limit = (1LL << 32) - 1;
}
static ext4_fsblk_t descriptor_loc(struct super_block *sb,
- ext4_fsblk_t logical_sb_block, int nr)
+ ext4_fsblk_t logical_sb_block, int nr)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t bg, first_meta_bg;
bg = sbi->s_desc_per_block * nr;
if (ext4_bg_has_super(sb, bg))
has_super = 1;
+
return (has_super + ext4_group_first_block_no(sb, bg));
}
if (parse_strtoul(buf, 0x40000000, &t))
return -EINVAL;
- /* inode_readahead_blks must be a power of 2 */
- if (t & (t-1))
+ if (!is_power_of_2(t))
return -EINVAL;
sbi->s_inode_readahead_blks = t;
}
static ssize_t sbi_ui_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
+ struct ext4_sb_info *sbi, char *buf)
{
unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
-
{
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
if (!blocksize) {
- printk(KERN_ERR "EXT4-fs: unable to set blocksize\n");
+ ext4_msg(sb, KERN_ERR, "unable to set blocksize");
goto out_fail;
}
}
if (!(bh = sb_bread(sb, logical_sb_block))) {
- printk(KERN_ERR "EXT4-fs: unable to read superblock\n");
+ ext4_msg(sb, KERN_ERR, "unable to read superblock");
goto out_fail;
}
/*
sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
+ sbi->s_mb_history_max = default_mb_history_length;
set_opt(sbi->s_mount_opt, BARRIER);
*/
set_opt(sbi->s_mount_opt, DELALLOC);
-
if (!parse_options((char *) data, sb, &journal_devnum,
&journal_ioprio, NULL, 0))
goto failed_mount;
(EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U)))
- printk(KERN_WARNING
- "EXT4-fs warning: feature flags set on rev 0 fs, "
- "running e2fsck is recommended\n");
+ ext4_msg(sb, KERN_WARNING,
+ "feature flags set on rev 0 fs, "
+ "running e2fsck is recommended");
/*
* Check feature flags regardless of the revision level, since we
*/
features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
if (features) {
- printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of "
- "unsupported optional features (%x).\n", sb->s_id,
+ ext4_msg(sb, KERN_ERR,
+ "Couldn't mount because of "
+ "unsupported optional features (%x)",
(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
~EXT4_FEATURE_INCOMPAT_SUPP));
goto failed_mount;
}
features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
if (!(sb->s_flags & MS_RDONLY) && features) {
- printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of "
- "unsupported optional features (%x).\n", sb->s_id,
+ ext4_msg(sb, KERN_ERR,
+ "Couldn't mount RDWR because of "
+ "unsupported optional features (%x)",
(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
~EXT4_FEATURE_RO_COMPAT_SUPP));
goto failed_mount;
*/
if (sizeof(root->i_blocks) < sizeof(u64) &&
!(sb->s_flags & MS_RDONLY)) {
- printk(KERN_ERR "EXT4-fs: %s: Filesystem with huge "
+ ext4_msg(sb, KERN_ERR, "Filesystem with huge "
"files cannot be mounted read-write "
- "without CONFIG_LBD.\n", sb->s_id);
+ "without CONFIG_LBD");
goto failed_mount;
}
}
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
- printk(KERN_ERR
- "EXT4-fs: Unsupported filesystem blocksize %d on %s.\n",
- blocksize, sb->s_id);
+ ext4_msg(sb, KERN_ERR,
+ "Unsupported filesystem blocksize %d", blocksize);
goto failed_mount;
}
if (sb->s_blocksize != blocksize) {
-
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
- printk(KERN_ERR "EXT4-fs: bad block size %d.\n",
+ ext4_msg(sb, KERN_ERR, "bad block size %d",
blocksize);
goto failed_mount;
}
offset = do_div(logical_sb_block, blocksize);
bh = sb_bread(sb, logical_sb_block);
if (!bh) {
- printk(KERN_ERR
- "EXT4-fs: Can't read superblock on 2nd try.\n");
+ ext4_msg(sb, KERN_ERR,
+ "Can't read superblock on 2nd try");
goto failed_mount;
}
es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
sbi->s_es = es;
if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
- printk(KERN_ERR
- "EXT4-fs: Magic mismatch, very weird !\n");
+ ext4_msg(sb, KERN_ERR,
+ "Magic mismatch, very weird!");
goto failed_mount;
}
}
if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
(!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
- printk(KERN_ERR
- "EXT4-fs: unsupported inode size: %d\n",
+ ext4_msg(sb, KERN_ERR,
+ "unsupported inode size: %d",
sbi->s_inode_size);
goto failed_mount;
}
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
}
+
sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
!is_power_of_2(sbi->s_desc_size)) {
- printk(KERN_ERR
- "EXT4-fs: unsupported descriptor size %lu\n",
+ ext4_msg(sb, KERN_ERR,
+ "unsupported descriptor size %lu",
sbi->s_desc_size);
goto failed_mount;
}
} else
sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
+
sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
goto cantfind_ext4;
+
sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
if (sbi->s_inodes_per_block == 0)
goto cantfind_ext4;
sbi->s_mount_state = le16_to_cpu(es->s_state);
sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
+
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
}
if (sbi->s_blocks_per_group > blocksize * 8) {
- printk(KERN_ERR
- "EXT4-fs: #blocks per group too big: %lu\n",
+ ext4_msg(sb, KERN_ERR,
+ "#blocks per group too big: %lu",
sbi->s_blocks_per_group);
goto failed_mount;
}
if (sbi->s_inodes_per_group > blocksize * 8) {
- printk(KERN_ERR
- "EXT4-fs: #inodes per group too big: %lu\n",
+ ext4_msg(sb, KERN_ERR,
+ "#inodes per group too big: %lu",
sbi->s_inodes_per_group);
goto failed_mount;
}
if (ext4_blocks_count(es) >
(sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
- printk(KERN_ERR "EXT4-fs: filesystem on %s:"
- " too large to mount safely\n", sb->s_id);
+ ext4_msg(sb, KERN_ERR, "filesystem"
+ " too large to mount safely");
if (sizeof(sector_t) < 8)
- printk(KERN_WARNING "EXT4-fs: CONFIG_LBD not "
- "enabled\n");
+ ext4_msg(sb, KERN_WARNING, "CONFIG_LBD not enabled");
goto failed_mount;
}
/* check blocks count against device size */
blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
if (blocks_count && ext4_blocks_count(es) > blocks_count) {
- printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu "
- "exceeds size of device (%llu blocks)\n",
+ ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu "
+ "exceeds size of device (%llu blocks)",
ext4_blocks_count(es), blocks_count);
goto failed_mount;
}
- /*
- * It makes no sense for the first data block to be beyond the end
- * of the filesystem.
- */
- if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
- printk(KERN_WARNING "EXT4-fs: bad geometry: first data"
- "block %u is beyond end of filesystem (%llu)\n",
- le32_to_cpu(es->s_first_data_block),
- ext4_blocks_count(es));
+ /*
+ * It makes no sense for the first data block to be beyond the end
+ * of the filesystem.
+ */
+ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
+ ext4_msg(sb, KERN_WARNING, "bad geometry: first data"
+ "block %u is beyond end of filesystem (%llu)",
+ le32_to_cpu(es->s_first_data_block),
+ ext4_blocks_count(es));
goto failed_mount;
}
blocks_count = (ext4_blocks_count(es) -
EXT4_BLOCKS_PER_GROUP(sb) - 1);
do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
- printk(KERN_WARNING "EXT4-fs: groups count too large: %u "
+ ext4_msg(sb, KERN_WARNING, "groups count too large: %u "
"(block count %llu, first data block %u, "
- "blocks per group %lu)\n", sbi->s_groups_count,
+ "blocks per group %lu)", sbi->s_groups_count,
ext4_blocks_count(es),
le32_to_cpu(es->s_first_data_block),
EXT4_BLOCKS_PER_GROUP(sb));
sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
- printk(KERN_ERR "EXT4-fs: not enough memory\n");
+ ext4_msg(sb, KERN_ERR, "not enough memory");
goto failed_mount;
}
block = descriptor_loc(sb, logical_sb_block, i);
sbi->s_group_desc[i] = sb_bread(sb, block);
if (!sbi->s_group_desc[i]) {
- printk(KERN_ERR "EXT4-fs: "
- "can't read group descriptor %d\n", i);
+ ext4_msg(sb, KERN_ERR,
+ "can't read group descriptor %d", i);
db_count = i;
goto failed_mount2;
}
}
if (!ext4_check_descriptors(sb)) {
- printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n");
+ ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
goto failed_mount2;
}
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
if (!ext4_fill_flex_info(sb)) {
- printk(KERN_ERR
- "EXT4-fs: unable to initialize "
- "flex_bg meta info!\n");
+ ext4_msg(sb, KERN_ERR,
+ "unable to initialize "
+ "flex_bg meta info!");
goto failed_mount2;
}
err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
}
if (err) {
- printk(KERN_ERR "EXT4-fs: insufficient memory\n");
+ ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount3;
}
/*
* set up enough so that it can read an inode
*/
- sb->s_op = &ext4_sops;
+ if (!test_opt(sb, NOLOAD) &&
+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+ sb->s_op = &ext4_sops;
+ else
+ sb->s_op = &ext4_nojournal_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
sb->dq_op = &ext4_quota_operations;
#endif
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
+ mutex_init(&sbi->s_orphan_lock);
+ mutex_init(&sbi->s_resize_lock);
sb->s_root = NULL;
goto failed_mount3;
if (!(sb->s_flags & MS_RDONLY) &&
EXT4_SB(sb)->s_journal->j_failed_commit) {
- printk(KERN_CRIT "EXT4-fs error (device %s): "
+ ext4_msg(sb, KERN_CRIT, "error: "
"ext4_fill_super: Journal transaction "
- "%u is corrupt\n", sb->s_id,
+ "%u is corrupt",
EXT4_SB(sb)->s_journal->j_failed_commit);
if (test_opt(sb, ERRORS_RO)) {
- printk(KERN_CRIT
- "Mounting filesystem read-only\n");
+ ext4_msg(sb, KERN_CRIT,
+ "Mounting filesystem read-only");
sb->s_flags |= MS_RDONLY;
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
if (test_opt(sb, ERRORS_PANIC)) {
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
goto failed_mount4;
}
}
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
- printk(KERN_ERR "EXT4-fs: required journal recovery "
- "suppressed and not mounted read-only\n");
+ ext4_msg(sb, KERN_ERR, "required journal recovery "
+ "suppressed and not mounted read-only");
goto failed_mount4;
} else {
clear_opt(sbi->s_mount_opt, DATA_FLAGS);
if (ext4_blocks_count(es) > 0xffffffffULL &&
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
- printk(KERN_ERR "EXT4-fs: Failed to set 64-bit journal feature\n");
+ ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
goto failed_mount4;
}
case EXT4_MOUNT_WRITEBACK_DATA:
if (!jbd2_journal_check_available_features
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
- printk(KERN_ERR "EXT4-fs: Journal does not support "
- "requested data journaling mode\n");
+ ext4_msg(sb, KERN_ERR, "Journal does not support "
+ "requested data journaling mode");
goto failed_mount4;
}
default:
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
- printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - "
- "its supported only with writeback mode\n");
+ ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
+ "its supported only with writeback mode");
clear_opt(sbi->s_mount_opt, NOBH);
}
}
root = ext4_iget(sb, EXT4_ROOT_INO);
if (IS_ERR(root)) {
- printk(KERN_ERR "EXT4-fs: get root inode failed\n");
+ ext4_msg(sb, KERN_ERR, "get root inode failed");
ret = PTR_ERR(root);
goto failed_mount4;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
iput(root);
- printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n");
+ ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
goto failed_mount4;
}
sb->s_root = d_alloc_root(root);
if (!sb->s_root) {
- printk(KERN_ERR "EXT4-fs: get root dentry failed\n");
+ ext4_msg(sb, KERN_ERR, "get root dentry failed");
iput(root);
ret = -ENOMEM;
goto failed_mount4;
sbi->s_inode_size) {
sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
- printk(KERN_INFO "EXT4-fs: required extra inode space not"
- "available.\n");
+ ext4_msg(sb, KERN_INFO, "required extra inode space not"
+ "available");
}
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
- printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
- "requested data journaling mode\n");
+ ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
+ "requested data journaling mode");
clear_opt(sbi->s_mount_opt, DELALLOC);
} else if (test_opt(sb, DELALLOC))
- printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
+ ext4_msg(sb, KERN_INFO, "delayed allocation enabled");
+
+ err = ext4_setup_system_zone(sb);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "failed to initialize system "
+ "zone (%d)\n", err);
+ goto failed_mount4;
+ }
ext4_ext_init(sb);
err = ext4_mb_init(sb, needs_recovery);
if (err) {
- printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n",
- err);
+ ext4_msg(sb, KERN_ERR, "failed to initalize mballoc (%d)",
+ err);
goto failed_mount4;
}
goto failed_mount4;
};
- /*
- * akpm: core read_super() calls in here with the superblock locked.
- * That deadlocks, because orphan cleanup needs to lock the superblock
- * in numerous places. Here we just pop the lock - it's relatively
- * harmless, because we are now ready to accept write_super() requests,
- * and aviro says that's the only reason for hanging onto the
- * superblock lock.
- */
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
if (needs_recovery) {
- printk(KERN_INFO "EXT4-fs: recovery complete.\n");
+ ext4_msg(sb, KERN_INFO, "recovery complete");
ext4_mark_recovery_complete(sb, es);
}
if (EXT4_SB(sb)->s_journal) {
} else
descr = "out journal";
- printk(KERN_INFO "EXT4-fs: mounted filesystem %s with%s\n",
- sb->s_id, descr);
+ ext4_msg(sb, KERN_INFO, "mounted filesystem with%s", descr);
lock_kernel();
return 0;
cantfind_ext4:
if (!silent)
- printk(KERN_ERR "VFS: Can't find ext4 filesystem on dev %s.\n",
- sb->s_id);
+ ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
goto failed_mount;
failed_mount4:
- printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id);
+ ext4_msg(sb, KERN_ERR, "mount failed");
+ ext4_release_system_zone(sb);
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
failed_mount3:
+ if (sbi->s_flex_groups) {
+ if (is_vmalloc_addr(sbi->s_flex_groups))
+ vfree(sbi->s_flex_groups);
+ else
+ kfree(sbi->s_flex_groups);
+ }
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
brelse(bh);
out_fail:
sb->s_fs_info = NULL;
+ kfree(sbi->s_blockgroup_lock);
kfree(sbi);
lock_kernel();
return ret;
journal_inode = ext4_iget(sb, journal_inum);
if (IS_ERR(journal_inode)) {
- printk(KERN_ERR "EXT4-fs: no journal found.\n");
+ ext4_msg(sb, KERN_ERR, "no journal found");
return NULL;
}
if (!journal_inode->i_nlink) {
make_bad_inode(journal_inode);
iput(journal_inode);
- printk(KERN_ERR "EXT4-fs: journal inode is deleted.\n");
+ ext4_msg(sb, KERN_ERR, "journal inode is deleted");
return NULL;
}
jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
journal_inode, journal_inode->i_size);
if (!S_ISREG(journal_inode->i_mode)) {
- printk(KERN_ERR "EXT4-fs: invalid journal inode.\n");
+ ext4_msg(sb, KERN_ERR, "invalid journal inode");
iput(journal_inode);
return NULL;
}
journal = jbd2_journal_init_inode(journal_inode);
if (!journal) {
- printk(KERN_ERR "EXT4-fs: Could not load journal inode\n");
+ ext4_msg(sb, KERN_ERR, "Could not load journal inode");
iput(journal_inode);
return NULL;
}
BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
- bdev = ext4_blkdev_get(j_dev);
+ bdev = ext4_blkdev_get(j_dev, sb);
if (bdev == NULL)
return NULL;
if (bd_claim(bdev, sb)) {
- printk(KERN_ERR
- "EXT4-fs: failed to claim external journal device.\n");
+ ext4_msg(sb, KERN_ERR,
+ "failed to claim external journal device");
blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
return NULL;
}
blocksize = sb->s_blocksize;
hblock = bdev_hardsect_size(bdev);
if (blocksize < hblock) {
- printk(KERN_ERR
- "EXT4-fs: blocksize too small for journal device.\n");
+ ext4_msg(sb, KERN_ERR,
+ "blocksize too small for journal device");
goto out_bdev;
}
offset = EXT4_MIN_BLOCK_SIZE % blocksize;
set_blocksize(bdev, blocksize);
if (!(bh = __bread(bdev, sb_block, blocksize))) {
- printk(KERN_ERR "EXT4-fs: couldn't read superblock of "
- "external journal\n");
+ ext4_msg(sb, KERN_ERR, "couldn't read superblock of "
+ "external journal");
goto out_bdev;
}
if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
!(le32_to_cpu(es->s_feature_incompat) &
EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
- printk(KERN_ERR "EXT4-fs: external journal has "
- "bad superblock\n");
+ ext4_msg(sb, KERN_ERR, "external journal has "
+ "bad superblock");
brelse(bh);
goto out_bdev;
}
if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
- printk(KERN_ERR "EXT4-fs: journal UUID does not match\n");
+ ext4_msg(sb, KERN_ERR, "journal UUID does not match");
brelse(bh);
goto out_bdev;
}
journal = jbd2_journal_init_dev(bdev, sb->s_bdev,
start, len, blocksize);
if (!journal) {
- printk(KERN_ERR "EXT4-fs: failed to create device journal\n");
+ ext4_msg(sb, KERN_ERR, "failed to create device journal");
goto out_bdev;
}
journal->j_private = sb;
ll_rw_block(READ, 1, &journal->j_sb_buffer);
wait_on_buffer(journal->j_sb_buffer);
if (!buffer_uptodate(journal->j_sb_buffer)) {
- printk(KERN_ERR "EXT4-fs: I/O error on journal device\n");
+ ext4_msg(sb, KERN_ERR, "I/O error on journal device");
goto out_journal;
}
if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
- printk(KERN_ERR "EXT4-fs: External journal has more than one "
- "user (unsupported) - %d\n",
+ ext4_msg(sb, KERN_ERR, "External journal has more than one "
+ "user (unsupported) - %d",
be32_to_cpu(journal->j_superblock->s_nr_users));
goto out_journal;
}
EXT4_SB(sb)->journal_bdev = bdev;
ext4_init_journal_params(sb, journal);
return journal;
+
out_journal:
jbd2_journal_destroy(journal);
out_bdev:
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
- printk(KERN_INFO "EXT4-fs: external journal device major/minor "
- "numbers have changed\n");
+ ext4_msg(sb, KERN_INFO, "external journal device major/minor "
+ "numbers have changed");
journal_dev = new_decode_dev(journal_devnum);
} else
journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
* crash? For recovery, we need to check in advance whether we
* can get read-write access to the device.
*/
-
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
if (sb->s_flags & MS_RDONLY) {
- printk(KERN_INFO "EXT4-fs: INFO: recovery "
- "required on readonly filesystem.\n");
+ ext4_msg(sb, KERN_INFO, "INFO: recovery "
+ "required on readonly filesystem");
if (really_read_only) {
- printk(KERN_ERR "EXT4-fs: write access "
- "unavailable, cannot proceed.\n");
+ ext4_msg(sb, KERN_ERR, "write access "
+ "unavailable, cannot proceed");
return -EROFS;
}
- printk(KERN_INFO "EXT4-fs: write access will "
- "be enabled during recovery.\n");
+ ext4_msg(sb, KERN_INFO, "write access will "
+ "be enabled during recovery");
}
}
if (journal_inum && journal_dev) {
- printk(KERN_ERR "EXT4-fs: filesystem has both journal "
- "and inode journals!\n");
+ ext4_msg(sb, KERN_ERR, "filesystem has both journal "
+ "and inode journals!");
return -EINVAL;
}
}
if (journal->j_flags & JBD2_BARRIER)
- printk(KERN_INFO "EXT4-fs: barriers enabled\n");
+ ext4_msg(sb, KERN_INFO, "barriers enabled");
else
- printk(KERN_INFO "EXT4-fs: barriers disabled\n");
+ ext4_msg(sb, KERN_INFO, "barriers disabled");
if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
err = jbd2_journal_update_format(journal);
if (err) {
- printk(KERN_ERR "EXT4-fs: error updating journal.\n");
+ ext4_msg(sb, KERN_ERR, "error updating journal");
jbd2_journal_destroy(journal);
return err;
}
err = jbd2_journal_load(journal);
if (err) {
- printk(KERN_ERR "EXT4-fs: error loading journal.\n");
+ ext4_msg(sb, KERN_ERR, "error loading journal");
jbd2_journal_destroy(journal);
return err;
}
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
es->s_journal_dev = cpu_to_le32(journal_devnum);
- sb->s_dirt = 1;
/* Make sure we flush the recovery flag to disk. */
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
}
return 0;
}
-static int ext4_commit_super(struct super_block *sb,
- struct ext4_super_block *es, int sync)
+static int ext4_commit_super(struct super_block *sb, int sync)
{
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
int error = 0;
* be remapped. Nothing we can do but to retry the
* write and hope for the best.
*/
- printk(KERN_ERR "EXT4-fs: previous I/O error to "
- "superblock detected for %s.\n", sb->s_id);
+ ext4_msg(sb, KERN_ERR, "previous I/O error to "
+ "superblock detected");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
&EXT4_SB(sb)->s_freeblocks_counter));
es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
-
+ sb->s_dirt = 0;
BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
if (sync) {
error = buffer_write_io_error(sbh);
if (error) {
- printk(KERN_ERR "EXT4-fs: I/O error while writing "
- "superblock for %s.\n", sb->s_id);
+ ext4_msg(sb, KERN_ERR, "I/O error while writing "
+ "superblock");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
return error;
}
-
/*
* Have we just finished recovery? If so, and if we are mounting (or
* remounting) the filesystem readonly, then we will end up with a
if (jbd2_journal_flush(journal) < 0)
goto out;
- lock_super(sb);
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
sb->s_flags & MS_RDONLY) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
- sb->s_dirt = 0;
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
}
- unlock_super(sb);
out:
jbd2_journal_unlock_updates(journal);
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
jbd2_journal_clear_err(journal);
}
return 0;
journal = EXT4_SB(sb)->s_journal;
- if (journal) {
- sb->s_dirt = 0;
+ if (journal)
ret = ext4_journal_force_commit(journal);
- }
return ret;
}
-/*
- * Ext4 always journals updates to the superblock itself, so we don't
- * have to propagate any other updates to the superblock on disk at this
- * point. (We can probably nuke this function altogether, and remove
- * any mention to sb->s_dirt in all of fs/ext4; eventual cleanup...)
- */
static void ext4_write_super(struct super_block *sb)
{
- if (EXT4_SB(sb)->s_journal) {
- if (mutex_trylock(&sb->s_lock) != 0)
- BUG();
- sb->s_dirt = 0;
- } else {
- ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
- }
+ ext4_commit_super(sb, 1);
}
static int ext4_sync_fs(struct super_block *sb, int wait)
tid_t target;
trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
- sb->s_dirt = 0;
- if (EXT4_SB(sb)->s_journal) {
- if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal,
- &target)) {
- if (wait)
- jbd2_log_wait_commit(EXT4_SB(sb)->s_journal,
- target);
- }
- } else {
- ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait);
+ if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
+ if (wait)
+ jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
}
return ret;
}
{
int error = 0;
journal_t *journal;
- sb->s_dirt = 0;
- if (!(sb->s_flags & MS_RDONLY)) {
- journal = EXT4_SB(sb)->s_journal;
+ if (sb->s_flags & MS_RDONLY)
+ return 0;
- if (journal) {
- /* Now we set up the journal barrier. */
- jbd2_journal_lock_updates(journal);
+ journal = EXT4_SB(sb)->s_journal;
- /*
- * We don't want to clear needs_recovery flag when we
- * failed to flush the journal.
- */
- error = jbd2_journal_flush(journal);
- if (error < 0)
- goto out;
- }
+ /* Now we set up the journal barrier. */
+ jbd2_journal_lock_updates(journal);
- /* Journal blocked and flushed, clear needs_recovery flag. */
- EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
- error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
- if (error)
- goto out;
+ /*
+ * Don't clear the needs_recovery flag if we failed to flush
+ * the journal.
+ */
+ error = jbd2_journal_flush(journal);
+ if (error < 0) {
+ out:
+ jbd2_journal_unlock_updates(journal);
+ return error;
}
+
+ /* Journal blocked and flushed, clear needs_recovery flag. */
+ EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ error = ext4_commit_super(sb, 1);
+ if (error)
+ goto out;
return 0;
-out:
- jbd2_journal_unlock_updates(journal);
- return error;
}
/*
*/
static int ext4_unfreeze(struct super_block *sb)
{
- if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) {
- lock_super(sb);
- /* Reser the needs_recovery flag before the fs is unlocked. */
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
- ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
- unlock_super(sb);
- jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
- }
+ if (sb->s_flags & MS_RDONLY)
+ return 0;
+
+ lock_super(sb);
+ /* Reset the needs_recovery flag before the fs is unlocked. */
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_commit_super(sb, 1);
+ unlock_super(sb);
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return 0;
}
(sbi->s_mount_state & EXT4_VALID_FS))
es->s_state = cpu_to_le16(sbi->s_mount_state);
- /*
- * We have to unlock super so that we can wait for
- * transactions.
- */
- if (sbi->s_journal) {
- unlock_super(sb);
+ if (sbi->s_journal)
ext4_mark_recovery_complete(sb, es);
- lock_super(sb);
- }
} else {
int ret;
if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
~EXT4_FEATURE_RO_COMPAT_SUPP))) {
- printk(KERN_WARNING "EXT4-fs: %s: couldn't "
+ ext4_msg(sb, KERN_WARNING, "couldn't "
"remount RDWR because of unsupported "
- "optional features (%x).\n", sb->s_id,
+ "optional features (%x)",
(le32_to_cpu(sbi->s_es->s_feature_ro_compat) &
~EXT4_FEATURE_RO_COMPAT_SUPP));
err = -EROFS;
/*
* Make sure the group descriptor checksums
- * are sane. If they aren't, refuse to
- * remount r/w.
+ * are sane. If they aren't, refuse to remount r/w.
*/
for (g = 0; g < sbi->s_groups_count; g++) {
struct ext4_group_desc *gdp =
ext4_get_group_desc(sb, g, NULL);
if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
- printk(KERN_ERR
- "EXT4-fs: ext4_remount: "
- "Checksum for group %u failed (%u!=%u)\n",
+ ext4_msg(sb, KERN_ERR,
+ "ext4_remount: Checksum for group %u failed (%u!=%u)",
g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
le16_to_cpu(gdp->bg_checksum));
err = -EINVAL;
* require a full umount/remount for now.
*/
if (es->s_last_orphan) {
- printk(KERN_WARNING "EXT4-fs: %s: couldn't "
+ ext4_msg(sb, KERN_WARNING, "Couldn't "
"remount RDWR because of unprocessed "
"orphan inode list. Please "
- "umount/remount instead.\n",
- sb->s_id);
+ "umount/remount instead");
err = -EINVAL;
goto restore_opts;
}
sb->s_flags &= ~MS_RDONLY;
}
}
+ ext4_setup_system_zone(sb);
if (sbi->s_journal == NULL)
- ext4_commit_super(sb, es, 1);
+ ext4_commit_super(sb, 1);
#ifdef CONFIG_QUOTA
/* Release old quota file names */
kfree(old_opts.s_qf_names[i]);
#endif
return 0;
+
restore_opts:
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.s_mount_opt;
if (test_opt(sb, MINIX_DF)) {
sbi->s_overhead_last = 0;
} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
- ext4_group_t ngroups = sbi->s_groups_count, i;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
ext4_fsblk_t overhead = 0;
- smp_rmb();
/*
* Compute the overhead (FS structures). This is constant
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+
return 0;
}
-/* Helper function for writing quotas on sync - we need to start transaction before quota file
- * is locked for write. Otherwise the are possible deadlocks:
+/* Helper function for writing quotas on sync - we need to start transaction
+ * before quota file is locked for write. Otherwise the are possible deadlocks:
* Process 1 Process 2
* ext4_create() quota_sync()
* jbd2_journal_start() write_dquot()
inode = dquot_to_inode(dquot);
handle = ext4_journal_start(inode,
- EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
+ EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit(dquot);
handle_t *handle;
handle = ext4_journal_start(dquot_to_inode(dquot),
- EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
+ EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_acquire(dquot);
handle_t *handle;
handle = ext4_journal_start(dquot_to_inode(dquot),
- EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+ EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle)) {
/* Release dquot anyway to avoid endless cycle in dqput() */
dquot_release(dquot);
static int ext4_quota_on_mount(struct super_block *sb, int type)
{
return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
- EXT4_SB(sb)->s_jquota_fmt, type);
+ EXT4_SB(sb)->s_jquota_fmt, type);
}
/*
if (EXT4_SB(sb)->s_qf_names[type]) {
/* Quotafile not in fs root? */
if (path.dentry->d_parent != sb->s_root)
- printk(KERN_WARNING
- "EXT4-fs: Quota file not on filesystem root. "
- "Journaled quota will not work.\n");
+ ext4_msg(sb, KERN_WARNING,
+ "Quota file not on filesystem root. "
+ "Journaled quota will not work");
}
/*
handle_t *handle = journal_current_handle();
if (EXT4_SB(sb)->s_journal && !handle) {
- printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)"
- " cancelled because transaction is not started.\n",
+ ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
+ " cancelled because transaction is not started",
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
#endif
-static int ext4_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static int ext4_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data, struct vfsmount *mnt)
{
- return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
+ return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
}
static struct file_system_type ext4_fs_type = {
};
#ifdef CONFIG_EXT4DEV_COMPAT
-static int ext4dev_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static int ext4dev_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data,struct vfsmount *mnt)
{
- printk(KERN_WARNING "EXT4-fs: Update your userspace programs "
- "to mount using ext4\n");
- printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility "
- "will go away by 2.6.31\n");
- return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
+ printk(KERN_WARNING "EXT4-fs (%s): Update your userspace programs "
+ "to mount using ext4\n", dev_name);
+ printk(KERN_WARNING "EXT4-fs (%s): ext4dev backwards compatibility "
+ "will go away by 2.6.31\n", dev_name);
+ return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
}
static struct file_system_type ext4dev_fs_type = {
{
int err;
+ err = init_ext4_system_zone();
+ if (err)
+ return err;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- return -ENOMEM;
+ goto out4;
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
err = init_ext4_mballoc();
if (err)
- return err;
+ goto out3;
err = init_ext4_xattr();
if (err)
exit_ext4_xattr();
out2:
exit_ext4_mballoc();
+out3:
+ remove_proc_entry("fs/ext4", NULL);
+ kset_unregister(ext4_kset);
+out4:
+ exit_ext4_system_zone();
return err;
}
exit_ext4_mballoc();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
+ exit_ext4_system_zone();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>
+#include <linux/ima.h>
#include <asm/uaccess.h>
&hugetlbfs_file_operations);
if (!file)
goto out_dentry; /* inode is already attached */
+ ima_counts_get(file);
return file;
switch (cmd) {
case FIBMAP:
return ioctl_fibmap(filp, p);
- case FS_IOC_FIEMAP:
- return ioctl_fiemap(filp, arg);
- case FIGETBSZ:
- return put_user(inode->i_sb->s_blocksize, p);
case FIONREAD:
return put_user(i_size_read(inode) - filp->f_pos, p);
}
error = ioctl_fsthaw(filp);
break;
+ case FS_IOC_FIEMAP:
+ return ioctl_fiemap(filp, arg);
+
+ case FIGETBSZ:
+ {
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ int __user *p = (int __user *)arg;
+ return put_user(inode->i_sb->s_blocksize, p);
+ }
+
default:
if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
error = file_ioctl(filp, cmd, arg);
* Journal abort has very specific semantics, which we describe
* for journal abort.
*
- * Two internal function, which provide abort to te jbd layer
+ * Two internal functions, which provide abort to the jbd layer
* itself are here.
*/
* int jbd2_journal_errno () - returns the journal's error state.
* @journal: journal to examine.
*
- * This is the errno numbet set with jbd2_journal_abort(), the last
+ * This is the errno number set with jbd2_journal_abort(), the last
* time the journal was mounted - if the journal was stopped
* without calling abort this will be 0.
*
* int jbd2_journal_clear_err () - clears the journal's error state
* @journal: journal to act on.
*
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
* mode.
*/
int jbd2_journal_clear_err(journal_t *journal)
* void jbd2_journal_ack_err() - Ack journal err.
* @journal: journal to act on.
*
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
* mode.
*/
void jbd2_journal_ack_err(journal_t *journal)
struct buffer_head map_bh;
unsigned long first_logical_block = 0;
- clear_buffer_mapped(&map_bh);
+ map_bh.b_state = 0;
+ map_bh.b_size = 0;
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
struct page *page = list_entry(pages->prev, struct page, lru);
struct buffer_head map_bh;
unsigned long first_logical_block = 0;
- clear_buffer_mapped(&map_bh);
+ map_bh.b_state = 0;
+ map_bh.b_size = 0;
bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
&map_bh, &first_logical_block, get_block);
if (bio)
err = inode_permission(nd->path.dentry->d_inode,
MAY_EXEC);
if (!err)
- err = ima_path_check(&nd->path, MAY_EXEC);
+ err = ima_path_check(&nd->path, MAY_EXEC,
+ IMA_COUNT_UPDATE);
if (err)
break;
return error;
error = ima_path_check(path,
- acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
+ acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC),
+ IMA_COUNT_UPDATE);
if (error)
return error;
/*
#include <linux/security.h>
#endif /* CONFIG_NFSD_V4 */
#include <linux/jhash.h>
+#include <linux/ima.h>
#include <asm/uaccess.h>
flags, cred);
if (IS_ERR(*filp))
host_err = PTR_ERR(*filp);
+ else
+ ima_counts_get(*filp);
out_nfserr:
err = nfserrno(host_err);
out:
struct dentry *dentry, int acc)
{
struct inode *inode = dentry->d_inode;
+ struct path path;
int err;
if (acc == NFSD_MAY_NOP)
if (err == -EACCES && S_ISREG(inode->i_mode) &&
acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
err = inode_permission(inode, MAY_EXEC);
+ if (err)
+ goto nfsd_out;
+ /* Do integrity (permission) checking now, but defer incrementing
+ * IMA counts to the actual file open.
+ */
+ path.mnt = exp->ex_path.mnt;
+ path.dentry = dentry;
+ err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC),
+ IMA_COUNT_LEAVE);
+nfsd_out:
return err? nfserrno(err) : 0;
}
if (copy_from_user(page, buf, count))
goto out_free;
+ /* Guard against adverse ptrace interaction */
+ length = mutex_lock_interruptible(&task->cred_guard_mutex);
+ if (length < 0)
+ goto out_free;
+
length = security_setprocattr(task,
(char*)file->f_path.dentry->d_name.name,
(void*)page, count);
+ mutex_unlock(&task->cred_guard_mutex);
out_free:
free_page((unsigned long) page);
out:
static int loadavg_proc_show(struct seq_file *m, void *v)
{
- int a, b, c;
- unsigned long seq;
+ unsigned long avnrun[3];
- do {
- seq = read_seqbegin(&xtime_lock);
- a = avenrun[0] + (FIXED_1/200);
- b = avenrun[1] + (FIXED_1/200);
- c = avenrun[2] + (FIXED_1/200);
- } while (read_seqretry(&xtime_lock, seq));
+ get_avenrun(avnrun, FIXED_1/200, 0);
- seq_printf(m, "%d.%02d %d.%02d %d.%02d %ld/%d %d\n",
- LOAD_INT(a), LOAD_FRAC(a),
- LOAD_INT(b), LOAD_FRAC(b),
- LOAD_INT(c), LOAD_FRAC(c),
+ seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n",
+ LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
+ LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
+ LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
nr_running(), nr_threads,
task_active_pid_ns(current)->last_pid);
return 0;
header-y += rdma/
header-y += video/
header-y += drm/
+header-y += xen/
#endif
/*
- * A facility to provide batching of the reload of page tables with the
- * actual context switch code for paravirtualized guests. By convention,
- * only one of the lazy modes (CPU, MMU) should be active at any given
- * time, entry should never be nested, and entry and exits should always
- * be paired. This is for sanity of maintaining and reasoning about the
- * kernel code.
+ * A facility to provide batching of the reload of page tables and
+ * other process state with the actual context switch code for
+ * paravirtualized guests. By convention, only one of the batched
+ * update (lazy) modes (CPU, MMU) should be active at any given time,
+ * entry should never be nested, and entry and exits should always be
+ * paired. This is for sanity of maintaining and reasoning about the
+ * kernel code. In this case, the exit (end of the context switch) is
+ * in architecture-specific code, and so doesn't need a generic
+ * definition.
*/
-#ifndef __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-#define arch_enter_lazy_cpu_mode() do {} while (0)
-#define arch_leave_lazy_cpu_mode() do {} while (0)
-#define arch_flush_lazy_cpu_mode() do {} while (0)
+#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
+#define arch_start_context_switch(prev) do {} while (0)
#endif
#ifndef __HAVE_PFNMAP_TRACKING
#define BRANCH_PROFILE()
#endif
-#ifdef CONFIG_EVENT_TRACER
+#ifdef CONFIG_EVENT_TRACING
#define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .; \
*(_ftrace_events) \
VMLINUX_SYMBOL(__stop_ftrace_events) = .;
extern int sbf_port;
extern unsigned long acpi_realmode_flags;
-int acpi_register_gsi (u32 gsi, int triggering, int polarity);
+int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
#ifdef CONFIG_X86_IO_APIC
* The remap event
*/
struct blk_io_trace_remap {
- __be32 device;
__be32 device_from;
- __be64 sector;
+ __be32 device_to;
+ __be64 sector_from;
};
enum {
extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
extern void blk_trace_shutdown(struct request_queue *);
-extern int do_blk_trace_setup(struct request_queue *q,
- char *name, dev_t dev, struct blk_user_trace_setup *buts);
+extern int do_blk_trace_setup(struct request_queue *q, char *name,
+ dev_t dev, struct block_device *bdev,
+ struct blk_user_trace_setup *buts);
extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
/**
extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
void *data, size_t len);
extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct block_device *bdev,
char __user *arg);
extern int blk_trace_startstop(struct request_queue *q, int start);
extern int blk_trace_remove(struct request_queue *q);
+extern int blk_trace_init_sysfs(struct device *dev);
extern struct attribute_group blk_trace_attr_group;
#else /* !CONFIG_BLK_DEV_IO_TRACE */
-#define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY)
-#define blk_trace_shutdown(q) do { } while (0)
-#define do_blk_trace_setup(q, name, dev, buts) (-ENOTTY)
-#define blk_add_driver_data(q, rq, data, len) do {} while (0)
-#define blk_trace_setup(q, name, dev, arg) (-ENOTTY)
-#define blk_trace_startstop(q, start) (-ENOTTY)
-#define blk_trace_remove(q) (-ENOTTY)
-#define blk_add_trace_msg(q, fmt, ...) do { } while (0)
+# define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY)
+# define blk_trace_shutdown(q) do { } while (0)
+# define do_blk_trace_setup(q, name, dev, bdev, buts) (-ENOTTY)
+# define blk_add_driver_data(q, rq, data, len) do {} while (0)
+# define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY)
+# define blk_trace_startstop(q, start) (-ENOTTY)
+# define blk_trace_remove(q) (-ENOTTY)
+# define blk_add_trace_msg(q, fmt, ...) do { } while (0)
+static inline int blk_trace_init_sysfs(struct device *dev)
+{
+ return 0;
+}
#endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+
+static inline int blk_cmd_buf_len(struct request *rq)
+{
+ return blk_pc_request(rq) ? rq->cmd_len * 3 : 1;
+}
+
+extern void blk_dump_cmd(char *buf, struct request *rq);
+extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
+extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
+
+#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
+
#endif /* __KERNEL__ */
#endif
int copy_siginfo_to_user32(struct compat_siginfo __user *to, siginfo_t *from);
int get_compat_sigevent(struct sigevent *event,
const struct compat_sigevent __user *u_event);
+long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig,
+ struct compat_siginfo __user *uinfo);
static inline int compat_timeval_compare(struct compat_timeval *lhs,
struct compat_timeval *rhs)
#ifndef DP_WINDOW_SIZE
-/* #include "cyclomz.h" */
-/****************** ****************** *******************/
-/*
- * The data types defined below are used in all ZFIRM interface
- * data structures. They accomodate differences between HW
- * architectures and compilers.
- */
-
-typedef __u64 ucdouble; /* 64 bits, unsigned */
-typedef __u32 uclong; /* 32 bits, unsigned */
-typedef __u16 ucshort; /* 16 bits, unsigned */
-typedef __u8 ucchar; /* 8 bits, unsigned */
-
/*
* Memory Window Sizes
*/
/* Per card data structure */
struct cyclades_card {
- void __iomem *base_addr;
- void __iomem *ctl_addr;
- int irq;
- unsigned int num_chips; /* 0 if card absent, -1 if Z/PCI, else Y */
- unsigned int first_line; /* minor number of first channel on card */
- unsigned int nports; /* Number of ports in the card */
- int bus_index; /* address shift - 0 for ISA, 1 for PCI */
- int intr_enabled; /* FW Interrupt flag - 0 disabled, 1 enabled */
- spinlock_t card_lock;
- struct cyclades_port *ports;
+ void __iomem *base_addr;
+ union {
+ void __iomem *p9050;
+ struct RUNTIME_9060 __iomem *p9060;
+ } ctl_addr;
+ int irq;
+ unsigned int num_chips; /* 0 if card absent, -1 if Z/PCI, else Y */
+ unsigned int first_line; /* minor number of first channel on card */
+ unsigned int nports; /* Number of ports in the card */
+ int bus_index; /* address shift - 0 for ISA, 1 for PCI */
+ int intr_enabled; /* FW Interrupt flag - 0 disabled, 1 enabled */
+ u32 hw_ver;
+ spinlock_t card_lock;
+ struct cyclades_port *ports;
};
/***************************************
extern void dma_debug_init(u32 num_entries);
+extern int dma_debug_resize_entries(u32 num_entries);
+
extern void debug_dma_map_page(struct device *dev, struct page *page,
size_t offset, size_t size,
int direction, dma_addr_t dma_addr,
{
}
+static inline int dma_debug_resize_entries(u32 num_entries)
+{
+ return 0;
+}
+
static inline void debug_dma_map_page(struct device *dev, struct page *page,
size_t offset, size_t size,
int direction, dma_addr_t dma_addr,
};
#ifdef CONFIG_INTR_REMAP
extern int intr_remapping_enabled;
+extern int intr_remapping_supported(void);
extern int enable_intr_remapping(int);
extern void disable_intr_remapping(void);
extern int reenable_intr_remapping(int);
}
#define irq_remapped(irq) (0)
#define enable_intr_remapping(mode) (-1)
+#define disable_intr_remapping() (0)
+#define reenable_intr_remapping(mode) (0)
#define intr_remapping_enabled (0)
#endif
extern int skip_trace(unsigned long ip);
-extern void ftrace_release(void *start, unsigned long size);
-
extern void ftrace_disable_daemon(void);
extern void ftrace_enable_daemon(void);
#else
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
extern void ftrace_init(void);
-extern void ftrace_init_module(struct module *mod,
- unsigned long *start, unsigned long *end);
#else
static inline void ftrace_init(void) { }
-static inline void
-ftrace_init_module(struct module *mod,
- unsigned long *start, unsigned long *end) { }
#endif
/*
unsigned long ret;
unsigned long func;
unsigned long long calltime;
+ unsigned long long subtime;
};
/*
extern int
ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
-extern void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
/*
* Sometimes we don't want to trace a function with the function
extern int ftrace_dump_on_oops;
+#ifdef CONFIG_PREEMPT
+#define INIT_TRACE_RECURSION .trace_recursion = 0,
+#endif
+
#endif /* CONFIG_TRACING */
+#ifndef INIT_TRACE_RECURSION
+#define INIT_TRACE_RECURSION
+#endif
#ifdef CONFIG_HW_BRANCH_TRACER
--- /dev/null
+#ifndef _LINUX_FTRACE_EVENT_H
+#define _LINUX_FTRACE_EVENT_H
+
+#include <linux/trace_seq.h>
+#include <linux/ring_buffer.h>
+#include <linux/percpu.h>
+
+struct trace_array;
+struct tracer;
+struct dentry;
+
+DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq);
+
+struct trace_print_flags {
+ unsigned long mask;
+ const char *name;
+};
+
+const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+ unsigned long flags,
+ const struct trace_print_flags *flag_array);
+
+const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+ const struct trace_print_flags *symbol_array);
+
+/*
+ * The trace entry - the most basic unit of tracing. This is what
+ * is printed in the end as a single line in the trace output, such as:
+ *
+ * bash-15816 [01] 235.197585: idle_cpu <- irq_enter
+ */
+struct trace_entry {
+ unsigned short type;
+ unsigned char flags;
+ unsigned char preempt_count;
+ int pid;
+ int tgid;
+};
+
+#define FTRACE_MAX_EVENT \
+ ((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1)
+
+/*
+ * Trace iterator - used by printout routines who present trace
+ * results to users and which routines might sleep, etc:
+ */
+struct trace_iterator {
+ struct trace_array *tr;
+ struct tracer *trace;
+ void *private;
+ int cpu_file;
+ struct mutex mutex;
+ struct ring_buffer_iter *buffer_iter[NR_CPUS];
+ unsigned long iter_flags;
+
+ /* The below is zeroed out in pipe_read */
+ struct trace_seq seq;
+ struct trace_entry *ent;
+ int cpu;
+ u64 ts;
+
+ loff_t pos;
+ long idx;
+
+ cpumask_var_t started;
+};
+
+
+typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
+ int flags);
+struct trace_event {
+ struct hlist_node node;
+ struct list_head list;
+ int type;
+ trace_print_func trace;
+ trace_print_func raw;
+ trace_print_func hex;
+ trace_print_func binary;
+};
+
+extern int register_ftrace_event(struct trace_event *event);
+extern int unregister_ftrace_event(struct trace_event *event);
+
+/* Return values for print_line callback */
+enum print_line_t {
+ TRACE_TYPE_PARTIAL_LINE = 0, /* Retry after flushing the seq */
+ TRACE_TYPE_HANDLED = 1,
+ TRACE_TYPE_UNHANDLED = 2, /* Relay to other output functions */
+ TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */
+};
+
+
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(int type, unsigned long len,
+ unsigned long flags, int pc);
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+ unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+ unsigned long flags, int pc);
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+
+void tracing_record_cmdline(struct task_struct *tsk);
+
+struct ftrace_event_call {
+ struct list_head list;
+ char *name;
+ char *system;
+ struct dentry *dir;
+ struct trace_event *event;
+ int enabled;
+ int (*regfunc)(void);
+ void (*unregfunc)(void);
+ int id;
+ int (*raw_init)(void);
+ int (*show_format)(struct trace_seq *s);
+ int (*define_fields)(void);
+ struct list_head fields;
+ int filter_active;
+ void *filter;
+ void *mod;
+
+#ifdef CONFIG_EVENT_PROFILE
+ atomic_t profile_count;
+ int (*profile_enable)(struct ftrace_event_call *);
+ void (*profile_disable)(struct ftrace_event_call *);
+#endif
+};
+
+#define MAX_FILTER_PRED 32
+#define MAX_FILTER_STR_VAL 128
+
+extern int init_preds(struct ftrace_event_call *call);
+extern void destroy_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern int filter_current_check_discard(struct ftrace_event_call *call,
+ void *rec,
+ struct ring_buffer_event *event);
+
+extern int trace_define_field(struct ftrace_event_call *call, char *type,
+ char *name, int offset, int size, int is_signed);
+
+#define is_signed_type(type) (((type)(-1)) < 0)
+
+int trace_set_clr_event(const char *system, const char *event, int set);
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement optimizing out.
+ */
+#define event_trace_printk(ip, fmt, args...) \
+do { \
+ __trace_printk_check_format(fmt, ##args); \
+ tracing_record_cmdline(current); \
+ if (__builtin_constant_p(fmt)) { \
+ static const char *trace_printk_fmt \
+ __attribute__((section("__trace_printk_fmt"))) = \
+ __builtin_constant_p(fmt) ? fmt : NULL; \
+ \
+ __trace_bprintk(ip, trace_printk_fmt, ##args); \
+ } else \
+ __trace_printk(ip, fmt, ##args); \
+} while (0)
+
+#define __common_field(type, item, is_signed) \
+ ret = trace_define_field(event_call, #type, "common_" #item, \
+ offsetof(typeof(field.ent), item), \
+ sizeof(field.ent.item), is_signed); \
+ if (ret) \
+ return ret;
+
+#endif /* _LINUX_FTRACE_EVENT_H */
#define FUTEX_TRYLOCK_PI 8
#define FUTEX_WAIT_BITSET 9
#define FUTEX_WAKE_BITSET 10
+#define FUTEX_WAIT_REQUEUE_PI 11
+#define FUTEX_CMP_REQUEUE_PI 12
#define FUTEX_PRIVATE_FLAG 128
#define FUTEX_CLOCK_REALTIME 256
#define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
#define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG)
#define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG)
+#define FUTEX_WAIT_REQUEUE_PI_PRIVATE (FUTEX_WAIT_REQUEUE_PI | \
+ FUTEX_PRIVATE_FLAG)
+#define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \
+ FUTEX_PRIVATE_FLAG)
/*
* Support for robust futexes: the kernel cleans up held futexes at
#include <asm/io.h>
#include <asm/mutex.h>
+/* for request_sense */
+#include <linux/cdrom.h>
+
#if defined(CONFIG_CRIS) || defined(CONFIG_FRV) || defined(CONFIG_MN10300)
# define SUPPORT_VLB_SYNC 0
#else
unsigned int cursg_ofs;
struct request *rq; /* copy of request */
- void *special; /* valid_t generally */
};
/* ATAPI packet command flags */
/* data buffer */
u8 *buf;
- /* current buffer position */
- u8 *cur_pos;
int buf_size;
- /* missing/available data on the current buffer */
- int b_count;
/* the corresponding request */
struct request *rq;
*/
u8 pc_buf[IDE_PC_BUFFER_SIZE];
- /* idetape only */
- struct idetape_bh *bh;
- char *b_data;
-
unsigned long timeout;
};
/* callback for packet commands */
int (*pc_callback)(struct ide_drive_s *, int);
- void (*pc_update_buffers)(struct ide_drive_s *, struct ide_atapi_pc *);
- int (*pc_io_buffers)(struct ide_drive_s *, struct ide_atapi_pc *,
- unsigned int, int);
-
ide_startstop_t (*irq_handler)(struct ide_drive_s *);
unsigned long atapi_flags;
struct ide_atapi_pc request_sense_pc;
- struct request request_sense_rq;
+
+ /* current sense rq and buffer */
+ bool sense_rq_armed;
+ struct request sense_rq;
+ struct request_sense sense_data;
};
typedef struct ide_drive_s ide_drive_t;
int ide_do_start_stop(ide_drive_t *, struct gendisk *, int);
int ide_set_media_lock(ide_drive_t *, struct gendisk *, int);
void ide_create_request_sense_cmd(ide_drive_t *, struct ide_atapi_pc *);
-void ide_retry_pc(ide_drive_t *, struct gendisk *);
+void ide_retry_pc(ide_drive_t *drive);
+
+void ide_prep_sense(ide_drive_t *drive, struct request *rq);
+int ide_queue_sense_rq(ide_drive_t *drive, void *special);
int ide_cd_expiry(ide_drive_t *);
#include <linux/fs.h>
struct linux_binprm;
+#define IMA_COUNT_UPDATE 1
+#define IMA_COUNT_LEAVE 0
+
#ifdef CONFIG_IMA
extern int ima_bprm_check(struct linux_binprm *bprm);
extern int ima_inode_alloc(struct inode *inode);
extern void ima_inode_free(struct inode *inode);
-extern int ima_path_check(struct path *path, int mask);
+extern int ima_path_check(struct path *path, int mask, int update_counts);
extern void ima_file_free(struct file *file);
extern int ima_file_mmap(struct file *file, unsigned long prot);
-extern void ima_shm_check(struct file *file);
+extern void ima_counts_get(struct file *file);
#else
static inline int ima_bprm_check(struct linux_binprm *bprm)
return;
}
-static inline int ima_path_check(struct path *path, int mask)
+static inline int ima_path_check(struct path *path, int mask, int update_counts)
{
return 0;
}
return 0;
}
-static inline void ima_shm_check(struct file *file)
+static inline void ima_counts_get(struct file *file)
{
return;
}
.group_leader = &tsk, \
.real_cred = &init_cred, \
.cred = &init_cred, \
- .cred_exec_mutex = \
- __MUTEX_INITIALIZER(tsk.cred_exec_mutex), \
+ .cred_guard_mutex = \
+ __MUTEX_INITIALIZER(tsk.cred_guard_mutex), \
.comm = "swapper", \
.thread = INIT_THREAD, \
.fs = &init_fs, \
INIT_TRACE_IRQFLAGS \
INIT_LOCKDEP \
INIT_FTRACE_GRAPH \
+ INIT_TRACE_RECURSION \
}
extern int early_irq_init(void);
extern int arch_probe_nr_irqs(void);
extern int arch_early_irq_init(void);
-extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
+extern int arch_init_chip_data(struct irq_desc *desc, int node);
#endif
void (*eoi)(unsigned int irq);
void (*end)(unsigned int irq);
- void (*set_affinity)(unsigned int irq,
+ int (*set_affinity)(unsigned int irq,
const struct cpumask *dest);
int (*retrigger)(unsigned int irq);
int (*set_type)(unsigned int irq, unsigned int flow_type);
spinlock_t lock;
#ifdef CONFIG_SMP
cpumask_var_t affinity;
- unsigned int cpu;
+ unsigned int node;
#ifdef CONFIG_GENERIC_PENDING_IRQ
cpumask_var_t pending_mask;
#endif
} ____cacheline_internodealigned_in_smp;
extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
- struct irq_desc *desc, int cpu);
+ struct irq_desc *desc, int node);
extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
#ifndef CONFIG_SPARSE_IRQ
extern struct irq_desc irq_desc[NR_IRQS];
-#else /* CONFIG_SPARSE_IRQ */
-extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu);
-#endif /* CONFIG_SPARSE_IRQ */
-
-extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu);
+#endif
-static inline struct irq_desc *
-irq_remap_to_desc(unsigned int irq, struct irq_desc *desc)
-{
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
- return irq_to_desc(irq);
+#ifdef CONFIG_NUMA_IRQ_DESC
+extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
#else
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
return desc;
-#endif
}
+#endif
+
+extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
/*
* Migration helpers for obsolete names, they will go away:
extern void set_irq_probe(unsigned int irq);
/* Handle dynamic irq creation and destruction */
-extern unsigned int create_irq_nr(unsigned int irq_want);
+extern unsigned int create_irq_nr(unsigned int irq_want, int node);
extern int create_irq(void);
extern void destroy_irq(unsigned int irq);
#ifdef CONFIG_SMP
/**
- * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * alloc_desc_masks - allocate cpumasks for irq_desc
* @desc: pointer to irq_desc struct
* @cpu: cpu which will be handling the cpumasks
* @boot: true if need bootmem
*
* Allocates affinity and pending_mask cpumask if required.
* Returns true if successful (or not required).
- * Side effect: affinity has all bits set, pending_mask has all bits clear.
*/
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
bool boot)
{
- int node;
-
+#ifdef CONFIG_CPUMASK_OFFSTACK
if (boot) {
alloc_bootmem_cpumask_var(&desc->affinity);
- cpumask_setall(desc->affinity);
#ifdef CONFIG_GENERIC_PENDING_IRQ
alloc_bootmem_cpumask_var(&desc->pending_mask);
- cpumask_clear(desc->pending_mask);
#endif
return true;
}
- node = cpu_to_node(cpu);
-
if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
return false;
- cpumask_setall(desc->affinity);
#ifdef CONFIG_GENERIC_PENDING_IRQ
if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
free_cpumask_var(desc->affinity);
return false;
}
- cpumask_clear(desc->pending_mask);
+#endif
#endif
return true;
}
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+ cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+ cpumask_clear(desc->pending_mask);
+#endif
+}
+
/**
* init_copy_desc_masks - copy cpumasks for irq_desc
* @old_desc: pointer to old irq_desc struct
static inline void init_copy_desc_masks(struct irq_desc *old_desc,
struct irq_desc *new_desc)
{
-#ifdef CONFIG_CPUMASKS_OFFSTACK
+#ifdef CONFIG_CPUMASK_OFFSTACK
cpumask_copy(new_desc->affinity, old_desc->affinity);
#ifdef CONFIG_GENERIC_PENDING_IRQ
#else /* !CONFIG_SMP */
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
bool boot)
{
return true;
}
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+}
+
static inline void init_copy_desc_masks(struct irq_desc *old_desc,
struct irq_desc *new_desc)
{
--- /dev/null
+/*
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ *
+ * This file is released under GPL version 2.
+ */
+
+#ifndef _LINUX_KMEMTRACE_H
+#define _LINUX_KMEMTRACE_H
+
+#ifdef __KERNEL__
+
+#include <trace/events/kmem.h>
+
+#ifdef CONFIG_KMEMTRACE
+extern void kmemtrace_init(void);
+#else
+static inline void kmemtrace_init(void)
+{
+}
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_KMEMTRACE_H */
+
--- /dev/null
+/*
+ * Common LSM logging functions
+ * Heavily borrowed from selinux/avc.h
+ *
+ * Author : Etienne BASSET <etienne.basset@ensta.org>
+ *
+ * All credits to : Stephen Smalley, <sds@epoch.ncsc.mil>
+ * All BUGS to : Etienne BASSET <etienne.basset@ensta.org>
+ */
+#ifndef _LSM_COMMON_LOGGING_
+#define _LSM_COMMON_LOGGING_
+
+#include <linux/stddef.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kdev_t.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/audit.h>
+#include <linux/in6.h>
+#include <linux/path.h>
+#include <linux/key.h>
+#include <linux/skbuff.h>
+#include <asm/system.h>
+
+
+/* Auxiliary data to use in generating the audit record. */
+struct common_audit_data {
+ char type;
+#define LSM_AUDIT_DATA_FS 1
+#define LSM_AUDIT_DATA_NET 2
+#define LSM_AUDIT_DATA_CAP 3
+#define LSM_AUDIT_DATA_IPC 4
+#define LSM_AUDIT_DATA_TASK 5
+#define LSM_AUDIT_DATA_KEY 6
+ struct task_struct *tsk;
+ union {
+ struct {
+ struct path path;
+ struct inode *inode;
+ } fs;
+ struct {
+ int netif;
+ struct sock *sk;
+ u16 family;
+ __be16 dport;
+ __be16 sport;
+ union {
+ struct {
+ __be32 daddr;
+ __be32 saddr;
+ } v4;
+ struct {
+ struct in6_addr daddr;
+ struct in6_addr saddr;
+ } v6;
+ } fam;
+ } net;
+ int cap;
+ int ipc_id;
+ struct task_struct *tsk;
+#ifdef CONFIG_KEYS
+ struct {
+ key_serial_t key;
+ char *key_desc;
+ } key_struct;
+#endif
+ } u;
+ const char *function;
+ /* this union contains LSM specific data */
+ union {
+ /* SMACK data */
+ struct smack_audit_data {
+ char *subject;
+ char *object;
+ char *request;
+ int result;
+ } smack_audit_data;
+ /* SELinux data */
+ struct {
+ u32 ssid;
+ u32 tsid;
+ u16 tclass;
+ u32 requested;
+ u32 audited;
+ struct av_decision *avd;
+ int result;
+ } selinux_audit_data;
+ } lsm_priv;
+ /* these callback will be implemented by a specific LSM */
+ void (*lsm_pre_audit)(struct audit_buffer *, void *);
+ void (*lsm_post_audit)(struct audit_buffer *, void *);
+};
+
+#define v4info fam.v4
+#define v6info fam.v6
+
+int ipv4_skb_to_auditdata(struct sk_buff *skb,
+ struct common_audit_data *ad, u8 *proto);
+
+int ipv6_skb_to_auditdata(struct sk_buff *skb,
+ struct common_audit_data *ad, u8 *proto);
+
+/* Initialize an LSM audit data structure. */
+#define COMMON_AUDIT_DATA_INIT(_d, _t) \
+ { memset((_d), 0, sizeof(struct common_audit_data)); \
+ (_d)->type = LSM_AUDIT_DATA_##_t; (_d)->function = __func__; }
+
+void common_lsm_audit(struct common_audit_data *a);
+
+#endif
#define DEBUGFS_MAGIC 0x64626720
#define SYSFS_MAGIC 0x62656572
#define SECURITYFS_MAGIC 0x73636673
+#define SELINUX_MAGIC 0xf97cff8c
#define TMPFS_MAGIC 0x01021994
#define SQUASHFS_MAGIC 0x73717368
#define EFS_SUPER_MAGIC 0x414A53
struct file_ra_state;
struct user_struct;
struct writeback_control;
+struct rlimit;
#ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
*/
static inline unsigned long round_hint_to_min(unsigned long hint)
{
-#ifdef CONFIG_SECURITY
hint &= PAGE_MASK;
if (((void *)hint != NULL) &&
(hint < mmap_min_addr))
return PAGE_ALIGN(mmap_min_addr);
-#endif
return hint;
}
unsigned long end_pfn);
extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
unsigned long end_pfn);
-extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
- unsigned long end_pfn);
extern void remove_all_active_ranges(void);
extern unsigned long absent_pages_in_range(unsigned long start_pfn,
unsigned long end_pfn);
int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
void vmemmap_populate_print_last(void);
-extern void *alloc_locked_buffer(size_t size);
-extern void free_locked_buffer(void *buffer, size_t size);
-extern void release_locked_buffer(void *buffer, size_t size);
+extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+ size_t size);
+extern void refund_locked_memory(struct mm_struct *mm, size_t size);
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */
extern int register_kmmio_probe(struct kmmio_probe *p);
extern void unregister_kmmio_probe(struct kmmio_probe *p);
+extern int kmmio_init(void);
+extern void kmmio_cleanup(void);
#ifdef CONFIG_MMIOTRACE
/* kmmio is active by some kmmio_probes? */
const char **trace_bprintk_fmt_start;
unsigned int num_trace_bprintk_fmt;
#endif
+#ifdef CONFIG_EVENT_TRACING
+ struct ftrace_event_call *trace_events;
+ unsigned int num_trace_events;
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+ unsigned long *ftrace_callsites;
+ unsigned int num_ftrace_callsites;
+#endif
#ifdef CONFIG_MODULE_UNLOAD
/* What modules depend on me? */
*/
extern int mutex_trylock(struct mutex *lock);
extern void mutex_unlock(struct mutex *lock);
+extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
#endif
#define PCI_DEVICE_ID_OXSEMI_PCIe952_1_U 0xC118
#define PCI_DEVICE_ID_OXSEMI_PCIe952_1_GU 0xC11C
#define PCI_DEVICE_ID_OXSEMI_16PCI954 0x9501
+#define PCI_DEVICE_ID_OXSEMI_C950 0x950B
#define PCI_DEVICE_ID_OXSEMI_16PCI95N 0x9511
#define PCI_DEVICE_ID_OXSEMI_16PCI954PP 0x9513
#define PCI_DEVICE_ID_OXSEMI_16PCI952 0x9521
#define PCI_DEVICE_ID_OXSEMI_16PCI952PP 0x9523
+#define PCI_SUBDEVICE_ID_OXSEMI_C950 0x0001
#define PCI_VENDOR_ID_CHELSIO 0x1425
struct task_struct *new_parent);
extern void __ptrace_unlink(struct task_struct *child);
extern void exit_ptrace(struct task_struct *tracer);
-extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags);
#define PTRACE_MODE_READ 1
#define PTRACE_MODE_ATTACH 2
/* Returns 0 on success, -errno on denial. */
#define arch_ptrace_untrace(task) do { } while (0)
#endif
-#ifndef arch_ptrace_fork
-/*
- * Do machine-specific work to initialize a new task.
- *
- * This is called from copy_process().
- */
-#define arch_ptrace_fork(child, clone_flags) do { } while (0)
-#endif
-
extern int task_current_syscall(struct task_struct *target, long *callno,
unsigned long args[6], unsigned int maxargs,
unsigned long *sp, unsigned long *pc);
--- /dev/null
+/*
+ * rational fractions
+ *
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ *
+ * helper functions when coping with rational numbers,
+ * e.g. when calculating optimum numerator/denominator pairs for
+ * pll configuration taking into account restricted register size
+ */
+
+#ifndef _LINUX_RATIONAL_H
+#define _LINUX_RATIONAL_H
+
+void rational_best_approximation(
+ unsigned long given_numerator, unsigned long given_denominator,
+ unsigned long max_numerator, unsigned long max_denominator,
+ unsigned long *best_numerator, unsigned long *best_denominator);
+
+#endif /* _LINUX_RATIONAL_H */
at->prev = last;
}
+/**
+ * list_entry_rcu - get the struct for this entry
+ * @ptr: the &struct list_head pointer.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_struct within the struct.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_entry_rcu(ptr, type, member) \
+ container_of(rcu_dereference(ptr), type, member)
+
+/**
+ * list_first_entry_rcu - get the first element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_first_entry_rcu(ptr, type, member) \
+ list_entry_rcu((ptr)->next, type, member)
+
#define __list_for_each_rcu(pos, head) \
for (pos = rcu_dereference((head)->next); \
pos != (head); \
* as long as the traversal is guarded by rcu_read_lock().
*/
#define list_for_each_entry_rcu(pos, head, member) \
- for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
+ for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
prefetch(pos->member.next), &pos->member != (head); \
- pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
+ pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
/**
unsigned long offline_fqs; /* Kicked due to being offline. */
unsigned long resched_ipi; /* Sent a resched IPI. */
- /* 5) For future __rcu_pending statistics. */
+ /* 5) __rcu_pending() statistics. */
long n_rcu_pending; /* rcu_pending() calls since boot. */
+ long n_rp_qs_pending;
+ long n_rp_cb_ready;
+ long n_rp_cpu_needs_gp;
+ long n_rp_gp_completed;
+ long n_rp_gp_started;
+ long n_rp_need_fqs;
+ long n_rp_need_nothing;
int cpu;
};
* Don't refer to this struct directly, use functions below.
*/
struct ring_buffer_event {
- u32 type:2, len:3, time_delta:27;
+ u32 type_len:5, time_delta:27;
u32 array[];
};
* size is variable depending on how much
* padding is needed
* If time_delta is non zero:
- * everything else same as RINGBUF_TYPE_DATA
+ * array[0] holds the actual length
+ * size = 4 + length (bytes)
*
* @RINGBUF_TYPE_TIME_EXTEND: Extend the time delta
* array[0] = time delta (28 .. 59)
* array[1..2] = tv_sec
* size = 16 bytes
*
- * @RINGBUF_TYPE_DATA: Data record
- * If len is zero:
+ * <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
+ * Data record
+ * If type_len is zero:
* array[0] holds the actual length
* array[1..(length+3)/4] holds data
- * size = 4 + 4 + length (bytes)
+ * size = 4 + length (bytes)
* else
- * length = len << 2
+ * length = type_len << 2
* array[0..(length+3)/4-1] holds data
* size = 4 + length (bytes)
*/
enum ring_buffer_type {
+ RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
RINGBUF_TYPE_PADDING,
RINGBUF_TYPE_TIME_EXTEND,
/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
RINGBUF_TYPE_TIME_STAMP,
- RINGBUF_TYPE_DATA,
};
unsigned ring_buffer_event_length(struct ring_buffer_event *event);
return event->time_delta;
}
+/*
+ * ring_buffer_event_discard can discard any event in the ring buffer.
+ * it is up to the caller to protect against a reader from
+ * consuming it or a writer from wrapping and replacing it.
+ *
+ * No external protection is needed if this is called before
+ * the event is commited. But in that case it would be better to
+ * use ring_buffer_discard_commit.
+ *
+ * Note, if an event that has not been committed is discarded
+ * with ring_buffer_event_discard, it must still be committed.
+ */
void ring_buffer_event_discard(struct ring_buffer_event *event);
+/*
+ * ring_buffer_discard_commit will remove an event that has not
+ * ben committed yet. If this is used, then ring_buffer_unlock_commit
+ * must not be called on the discarded event. This function
+ * will try to remove the event from the ring buffer completely
+ * if another event has not been written after it.
+ *
+ * Example use:
+ *
+ * if (some_condition)
+ * ring_buffer_discard_commit(buffer, event);
+ * else
+ * ring_buffer_unlock_commit(buffer, event);
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event);
+
/*
* size is in bytes for each per CPU buffer.
*/
struct ring_buffer *
-ring_buffer_alloc(unsigned long size, unsigned flags);
+__ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key);
+
+/*
+ * Because the ring buffer is generic, if other users of the ring buffer get
+ * traced by ftrace, it can produce lockdep warnings. We need to keep each
+ * ring buffer's lock class separate.
+ */
+#define ring_buffer_alloc(size, flags) \
+({ \
+ static struct lock_class_key __key; \
+ __ring_buffer_alloc((size), (flags), &__key); \
+})
+
void ring_buffer_free(struct ring_buffer *buffer);
int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
size_t len, int cpu, int full);
+struct trace_seq;
+
+int ring_buffer_print_entry_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_seq *s);
+
enum ring_buffer_flags {
RB_FL_OVERWRITE = 1 << 0,
};
#include <linux/proportions.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
+#include <linux/rculist.h>
#include <linux/rtmutex.h>
#include <linux/time.h>
struct futex_pi_state;
struct robust_list_head;
struct bio;
-struct bts_tracer;
struct fs_struct;
+struct bts_context;
/*
* List of flags we want to share for kernel threads,
* 11 bit fractions.
*/
extern unsigned long avenrun[]; /* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
#define FSHIFT 11 /* nr of bits of precision */
#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
-extern unsigned long nr_active(void);
extern unsigned long nr_iowait(void);
+extern void calc_global_load(void);
extern unsigned long get_parent_ip(unsigned long addr);
*/
u32 reciprocal_cpu_power;
- unsigned long cpumask[];
+ /*
+ * The CPUs this group covers.
+ *
+ * NOTE: this field is variable length. (Allocated dynamically
+ * by attaching extra space to the end of the structure,
+ * depending on how many CPUs the kernel has booted up with)
+ *
+ * It is also be embedded into static data structures at build
+ * time. (See 'struct static_sched_group' in kernel/sched.c)
+ */
+ unsigned long cpumask[0];
};
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
char *name;
#endif
- /* span of all CPUs in this domain */
- unsigned long span[];
+ /*
+ * Span of all CPUs in this domain.
+ *
+ * NOTE: this field is variable length. (Allocated dynamically
+ * by attaching extra space to the end of the structure,
+ * depending on how many CPUs the kernel has booted up with)
+ *
+ * It is also be embedded into static data structures at build
+ * time. (See 'struct static_sched_domain' in kernel/sched.c)
+ */
+ unsigned long span[0];
};
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
struct list_head ptraced;
struct list_head ptrace_entry;
-#ifdef CONFIG_X86_PTRACE_BTS
/*
* This is the tracer handle for the ptrace BTS extension.
* This field actually belongs to the ptracer task.
*/
- struct bts_tracer *bts;
- /*
- * The buffer to hold the BTS data.
- */
- void *bts_buffer;
- size_t bts_size;
-#endif /* CONFIG_X86_PTRACE_BTS */
+ struct bts_context *bts;
/* PID/PID hash table linkage. */
struct pid_link pids[PIDTYPE_MAX];
* credentials (COW) */
const struct cred *cred; /* effective (overridable) subjective task
* credentials (COW) */
- struct mutex cred_exec_mutex; /* execve vs ptrace cred calculation mutex */
+ struct mutex cred_guard_mutex; /* guard against foreign influences on
+ * credential calculations
+ * (notably. ptrace) */
char comm[TASK_COMM_LEN]; /* executable name excluding path
- access with [gs]et_task_comm (which lock
#ifdef CONFIG_TRACING
/* state flags for use by tracers */
unsigned long trace;
-#endif
+ /* bitmask of trace recursion */
+ unsigned long trace_recursion;
+#endif /* CONFIG_TRACING */
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
+extern void __flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
extern void flush_signal_handlers(struct task_struct *, int force_default);
extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
extern char *get_task_comm(char *to, struct task_struct *tsk);
#ifdef CONFIG_SMP
+extern void wait_task_context_switch(struct task_struct *p);
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
#else
+static inline void wait_task_context_switch(struct task_struct *p) {}
static inline unsigned long wait_task_inactive(struct task_struct *p,
long match_state)
{
}
#endif
-#define next_task(p) list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
+#define next_task(p) \
+ list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
static inline struct task_struct *next_thread(const struct task_struct *p)
{
- return list_entry(rcu_dereference(p->thread_group.next),
- struct task_struct, thread_group);
+ return list_entry_rcu(p->thread_group.next,
+ struct task_struct, thread_group);
}
static inline int thread_group_empty(struct task_struct *p)
unsigned long addr,
unsigned long addr_only)
{
+ if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO))
+ return -EACCES;
return 0;
}
/*
* Definitions for async_struct (and serial_struct) flags field
+ *
+ * Define ASYNCB_* for convenient use with {test,set,clear}_bit.
*/
-#define ASYNC_HUP_NOTIFY 0x0001 /* Notify getty on hangups and closes
- on the callout port */
-#define ASYNC_FOURPORT 0x0002 /* Set OU1, OUT2 per AST Fourport settings */
-#define ASYNC_SAK 0x0004 /* Secure Attention Key (Orange book) */
-#define ASYNC_SPLIT_TERMIOS 0x0008 /* Separate termios for dialin/callout */
-
-#define ASYNC_SPD_MASK 0x1030
-#define ASYNC_SPD_HI 0x0010 /* Use 56000 instead of 38400 bps */
-
-#define ASYNC_SPD_VHI 0x0020 /* Use 115200 instead of 38400 bps */
-#define ASYNC_SPD_CUST 0x0030 /* Use user-specified divisor */
-
-#define ASYNC_SKIP_TEST 0x0040 /* Skip UART test during autoconfiguration */
-#define ASYNC_AUTO_IRQ 0x0080 /* Do automatic IRQ during autoconfiguration */
-#define ASYNC_SESSION_LOCKOUT 0x0100 /* Lock out cua opens based on session */
-#define ASYNC_PGRP_LOCKOUT 0x0200 /* Lock out cua opens based on pgrp */
-#define ASYNC_CALLOUT_NOHUP 0x0400 /* Don't do hangups for cua device */
-
-#define ASYNC_HARDPPS_CD 0x0800 /* Call hardpps when CD goes high */
-
-#define ASYNC_SPD_SHI 0x1000 /* Use 230400 instead of 38400 bps */
-#define ASYNC_SPD_WARP 0x1010 /* Use 460800 instead of 38400 bps */
-
-#define ASYNC_LOW_LATENCY 0x2000 /* Request low latency behaviour */
-
-#define ASYNC_BUGGY_UART 0x4000 /* This is a buggy UART, skip some safety
- * checks. Note: can be dangerous! */
-
-#define ASYNC_AUTOPROBE 0x8000 /* Port was autoprobed by PCI or PNP code */
-
-#define ASYNC_FLAGS 0x7FFF /* Possible legal async flags */
-#define ASYNC_USR_MASK 0x3430 /* Legal flags that non-privileged
- * users can set or reset */
-
-/* Internal flags used only by kernel/chr_drv/serial.c */
-#define ASYNC_INITIALIZED 0x80000000 /* Serial port was initialized */
-#define ASYNC_NORMAL_ACTIVE 0x20000000 /* Normal device is active */
-#define ASYNC_BOOT_AUTOCONF 0x10000000 /* Autoconfigure port on bootup */
-#define ASYNC_CLOSING 0x08000000 /* Serial port is closing */
-#define ASYNC_CTS_FLOW 0x04000000 /* Do CTS flow control */
-#define ASYNC_CHECK_CD 0x02000000 /* i.e., CLOCAL */
-#define ASYNC_SHARE_IRQ 0x01000000 /* for multifunction cards
- --- no longer used */
-#define ASYNC_CONS_FLOW 0x00800000 /* flow control for console */
-
-#define ASYNC_BOOT_ONLYMCA 0x00400000 /* Probe only if MCA bus */
-#define ASYNC_INTERNAL_FLAGS 0xFFC00000 /* Internal flags */
+#define ASYNCB_HUP_NOTIFY 0 /* Notify getty on hangups and closes
+ * on the callout port */
+#define ASYNCB_FOURPORT 1 /* Set OU1, OUT2 per AST Fourport settings */
+#define ASYNCB_SAK 2 /* Secure Attention Key (Orange book) */
+#define ASYNCB_SPLIT_TERMIOS 3 /* Separate termios for dialin/callout */
+#define ASYNCB_SPD_HI 4 /* Use 56000 instead of 38400 bps */
+#define ASYNCB_SPD_VHI 5 /* Use 115200 instead of 38400 bps */
+#define ASYNCB_SKIP_TEST 6 /* Skip UART test during autoconfiguration */
+#define ASYNCB_AUTO_IRQ 7 /* Do automatic IRQ during
+ * autoconfiguration */
+#define ASYNCB_SESSION_LOCKOUT 8 /* Lock out cua opens based on session */
+#define ASYNCB_PGRP_LOCKOUT 9 /* Lock out cua opens based on pgrp */
+#define ASYNCB_CALLOUT_NOHUP 10 /* Don't do hangups for cua device */
+#define ASYNCB_HARDPPS_CD 11 /* Call hardpps when CD goes high */
+#define ASYNCB_SPD_SHI 12 /* Use 230400 instead of 38400 bps */
+#define ASYNCB_LOW_LATENCY 13 /* Request low latency behaviour */
+#define ASYNCB_BUGGY_UART 14 /* This is a buggy UART, skip some safety
+ * checks. Note: can be dangerous! */
+#define ASYNCB_AUTOPROBE 15 /* Port was autoprobed by PCI or PNP code */
+#define ASYNCB_LAST_USER 15
+
+/* Internal flags used only by kernel */
+#define ASYNCB_INITIALIZED 31 /* Serial port was initialized */
+#define ASYNCB_NORMAL_ACTIVE 29 /* Normal device is active */
+#define ASYNCB_BOOT_AUTOCONF 28 /* Autoconfigure port on bootup */
+#define ASYNCB_CLOSING 27 /* Serial port is closing */
+#define ASYNCB_CTS_FLOW 26 /* Do CTS flow control */
+#define ASYNCB_CHECK_CD 25 /* i.e., CLOCAL */
+#define ASYNCB_SHARE_IRQ 24 /* for multifunction cards, no longer used */
+#define ASYNCB_CONS_FLOW 23 /* flow control for console */
+#define ASYNCB_BOOT_ONLYMCA 22 /* Probe only if MCA bus */
+#define ASYNCB_FIRST_KERNEL 22
+
+#define ASYNC_HUP_NOTIFY (1U << ASYNCB_HUP_NOTIFY)
+#define ASYNC_FOURPORT (1U << ASYNCB_FOURPORT)
+#define ASYNC_SAK (1U << ASYNCB_SAK)
+#define ASYNC_SPLIT_TERMIOS (1U << ASYNCB_SPLIT_TERMIOS)
+#define ASYNC_SPD_HI (1U << ASYNCB_SPD_HI)
+#define ASYNC_SPD_VHI (1U << ASYNCB_SPD_VHI)
+#define ASYNC_SKIP_TEST (1U << ASYNCB_SKIP_TEST)
+#define ASYNC_AUTO_IRQ (1U << ASYNCB_AUTO_IRQ)
+#define ASYNC_SESSION_LOCKOUT (1U << ASYNCB_SESSION_LOCKOUT)
+#define ASYNC_PGRP_LOCKOUT (1U << ASYNCB_PGRP_LOCKOUT)
+#define ASYNC_CALLOUT_NOHUP (1U << ASYNCB_CALLOUT_NOHUP)
+#define ASYNC_HARDPPS_CD (1U << ASYNCB_HARDPPS_CD)
+#define ASYNC_SPD_SHI (1U << ASYNCB_SPD_SHI)
+#define ASYNC_LOW_LATENCY (1U << ASYNCB_LOW_LATENCY)
+#define ASYNC_BUGGY_UART (1U << ASYNCB_BUGGY_UART)
+#define ASYNC_AUTOPROBE (1U << ASYNCB_AUTOPROBE)
+
+#define ASYNC_FLAGS ((1U << ASYNCB_LAST_USER) - 1)
+#define ASYNC_USR_MASK (ASYNC_SPD_HI|ASYNC_SPD_VHI| \
+ ASYNC_CALLOUT_NOHUP|ASYNC_SPD_SHI|ASYNC_LOW_LATENCY)
+#define ASYNC_SPD_CUST (ASYNC_SPD_HI|ASYNC_SPD_VHI)
+#define ASYNC_SPD_WARP (ASYNC_SPD_HI|ASYNC_SPD_SHI)
+#define ASYNC_SPD_MASK (ASYNC_SPD_HI|ASYNC_SPD_VHI|ASYNC_SPD_SHI)
+
+#define ASYNC_INITIALIZED (1U << ASYNCB_INITIALIZED)
+#define ASYNC_NORMAL_ACTIVE (1U << ASYNCB_NORMAL_ACTIVE)
+#define ASYNC_BOOT_AUTOCONF (1U << ASYNCB_BOOT_AUTOCONF)
+#define ASYNC_CLOSING (1U << ASYNCB_CLOSING)
+#define ASYNC_CTS_FLOW (1U << ASYNCB_CTS_FLOW)
+#define ASYNC_CHECK_CD (1U << ASYNCB_CHECK_CD)
+#define ASYNC_SHARE_IRQ (1U << ASYNCB_SHARE_IRQ)
+#define ASYNC_CONS_FLOW (1U << ASYNCB_CONS_FLOW)
+#define ASYNC_BOOT_ONLYMCA (1U << ASYNCB_BOOT_ONLYMCA)
+#define ASYNC_INTERNAL_FLAGS (~((1U << ASYNCB_FIRST_KERNEL) - 1))
/*
* Multiport serial configuration structure --- external structure
#define PORT_XSCALE 15
#define PORT_RM9000 16 /* PMC-Sierra RM9xxx internal UART */
#define PORT_OCTEON 17 /* Cavium OCTEON internal UART */
-#define PORT_MAX_8250 17 /* max port ID */
+#define PORT_AR7 18 /* Texas Instruments AR7 internal UART */
+#define PORT_MAX_8250 18 /* max port ID */
/*
* ARM specific type numbers. These are not currently guaranteed
/* MAX3100 */
#define PORT_MAX3100 86
+/* Timberdale UART */
+#define PORT_TIMBUART 87
+
#ifdef __KERNEL__
#include <linux/compiler.h>
extern int next_signal(struct sigpending *pending, sigset_t *mask);
extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p);
extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *);
+extern long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig,
+ siginfo_t *info);
extern long do_sigpending(void __user *, unsigned long);
extern int sigprocmask(int, sigset_t *, sigset_t *);
extern int show_unhandled_signals;
#include <asm/page.h> /* kmalloc_sizes.h needs PAGE_SIZE */
#include <asm/cache.h> /* kmalloc_sizes.h needs L1_CACHE_BYTES */
#include <linux/compiler.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
/* Size description struct for general caches. */
struct cache_sizes {
#include <linux/gfp.h>
#include <linux/workqueue.h>
#include <linux/kobject.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
#define __raw_spin_is_locked(lock) ((void)(lock), 0)
/* for sched.c and kernel_lock.c: */
# define __raw_spin_lock(lock) do { (void)(lock); } while (0)
+# define __raw_spin_lock_flags(lock, flags) do { (void)(lock); } while (0)
# define __raw_spin_unlock(lock) do { (void)(lock); } while (0)
# define __raw_spin_trylock(lock) ({ (void)(lock); 1; })
#endif /* DEBUG_SPINLOCK */
extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev,
phys_addr_t address);
-extern phys_addr_t swiotlb_bus_to_phys(dma_addr_t address);
+extern phys_addr_t swiotlb_bus_to_phys(struct device *hwdev,
+ dma_addr_t address);
extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size);
struct {
unsigned long arg0, arg1, arg2, arg3;
};
- /* For futex_wait */
+ /* For futex_wait and futex_wait_requeue_pi */
struct {
u32 *uaddr;
u32 val;
u32 flags;
u32 bitset;
u64 time;
+ u32 *uaddr2;
} futex;
/* For nanosleep */
struct {
--- /dev/null
+#ifndef _LINUX_TRACE_SEQ_H
+#define _LINUX_TRACE_SEQ_H
+
+#include <linux/fs.h>
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE.
+ */
+
+struct trace_seq {
+ unsigned char buffer[PAGE_SIZE];
+ unsigned int len;
+ unsigned int readpos;
+};
+
+static inline void
+trace_seq_init(struct trace_seq *s)
+{
+ s->len = 0;
+ s->readpos = 0;
+}
+
+/*
+ * Currently only defined when tracing is enabled.
+ */
+#ifdef CONFIG_TRACING
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+ __attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+ __attribute__ ((format (printf, 2, 0)));
+extern int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
+extern void trace_print_seq(struct seq_file *m, struct trace_seq *s);
+extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+ size_t cnt);
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+ size_t len);
+extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+extern int trace_seq_path(struct trace_seq *s, struct path *path);
+
+#else /* CONFIG_TRACING */
+static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+ return 0;
+}
+static inline int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+ return 0;
+}
+
+static inline void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+}
+static inline ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+ size_t cnt)
+{
+ return 0;
+}
+static inline int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+ return 0;
+}
+static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+ return 0;
+}
+static inline int
+trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
+{
+ return 0;
+}
+static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+ size_t len)
+{
+ return 0;
+}
+static inline void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+ return NULL;
+}
+static inline int trace_seq_path(struct trace_seq *s, struct path *path)
+{
+ return 0;
+}
+#endif /* CONFIG_TRACING */
+
+#endif /* _LINUX_TRACE_SEQ_H */
* Keep in sync with vmlinux.lds.h.
*/
+#ifndef DECLARE_TRACE
+
#define TP_PROTO(args...) args
#define TP_ARGS(args...) args
struct tracepoint *end)
{ }
#endif /* CONFIG_TRACEPOINTS */
+#endif /* DECLARE_TRACE */
/*
* Connect a probe to a tracepoint.
}
#define PARAMS(args...) args
-#define TRACE_FORMAT(name, proto, args, fmt) \
- DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-
+#ifndef TRACE_EVENT
/*
* For use with the TRACE_EVENT macro:
*
#define TRACE_EVENT(name, proto, args, struct, assign, print) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#endif
#endif
struct tty_port_operations {
/* Return 1 if the carrier is raised */
int (*carrier_raised)(struct tty_port *port);
- void (*raise_dtr_rts)(struct tty_port *port);
+ void (*dtr_rts)(struct tty_port *port, int raise);
};
struct tty_port {
unsigned char *xmit_buf; /* Optional buffer */
int close_delay; /* Close port delay */
int closing_wait; /* Delay for output */
+ int drain_delay; /* Set to zero if no pure time
+ based drain is needed else
+ set to size of fifo */
};
/*
struct tty_driver *driver;
const struct tty_operations *ops;
int index;
- /* The ldisc objects are protected by tty_ldisc_lock at the moment */
- struct tty_ldisc ldisc;
+
+ /* Protects ldisc changes: Lock tty not pty */
+ struct mutex ldisc_mutex;
+ struct tty_ldisc *ldisc;
+
struct mutex termios_mutex;
spinlock_t ctrl_lock;
/* Termios values are protected by the termios mutex */
#define TTY_CLOSING 7 /* ->close() in progress */
#define TTY_LDISC 9 /* Line discipline attached */
#define TTY_LDISC_CHANGING 10 /* Line discipline changing */
+#define TTY_LDISC_OPEN 11 /* Line discipline is open */
#define TTY_HW_COOK_OUT 14 /* Hardware can do output cooking */
#define TTY_HW_COOK_IN 15 /* Hardware can do input cooking */
#define TTY_PTY_LOCK 16 /* pty private */
extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *);
extern void tty_ldisc_deref(struct tty_ldisc *);
extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *);
+extern void tty_ldisc_hangup(struct tty_struct *tty);
extern const struct file_operations tty_ldiscs_proc_fops;
extern void tty_wakeup(struct tty_struct *tty);
extern void tty_release_dev(struct file *filp);
extern int tty_init_termios(struct tty_struct *tty);
+extern struct tty_struct *tty_pair_get_tty(struct tty_struct *tty);
+extern struct tty_struct *tty_pair_get_pty(struct tty_struct *tty);
+
extern struct mutex tty_mutex;
extern void tty_write_unlock(struct tty_struct *tty);
extern void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty);
extern int tty_port_carrier_raised(struct tty_port *port);
extern void tty_port_raise_dtr_rts(struct tty_port *port);
+extern void tty_port_lower_dtr_rts(struct tty_port *port);
extern void tty_port_hangup(struct tty_port *port);
extern int tty_port_block_til_ready(struct tty_port *port,
struct tty_struct *tty, struct file *filp);
* the line discipline are close to full, and it should somehow
* signal that no more characters should be sent to the tty.
*
- * Optional: Always invoke via tty_throttle();
+ * Optional: Always invoke via tty_throttle(), called under the
+ * termios lock.
*
* void (*unthrottle)(struct tty_struct * tty);
*
* that characters can now be sent to the tty without fear of
* overrunning the input buffers of the line disciplines.
*
- * Optional: Always invoke via tty_unthrottle();
+ * Optional: Always invoke via tty_unthrottle(), called under the
+ * termios lock.
*
* void (*stop)(struct tty_struct *tty);
*
/* Called by console with tty = NULL and by tty */
int (*open)(struct tty_struct *tty,
struct usb_serial_port *port, struct file *filp);
- void (*close)(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+ void (*close)(struct usb_serial_port *port);
int (*write)(struct tty_struct *tty, struct usb_serial_port *port,
const unsigned char *buf, int count);
/* Called only by the tty layer */
int (*tiocmget)(struct tty_struct *tty, struct file *file);
int (*tiocmset)(struct tty_struct *tty, struct file *file,
unsigned int set, unsigned int clear);
+ /* Called by the tty layer for port level work. There may or may not
+ be an attached tty at this point */
+ void (*dtr_rts)(struct usb_serial_port *port, int on);
+ int (*carrier_raised)(struct usb_serial_port *port);
/* USB events */
void (*read_int_callback)(struct urb *urb);
void (*write_int_callback)(struct urb *urb);
struct usb_serial_port *port, struct file *filp);
extern int usb_serial_generic_write(struct tty_struct *tty,
struct usb_serial_port *port, const unsigned char *buf, int count);
-extern void usb_serial_generic_close(struct tty_struct *tty,
- struct usb_serial_port *port, struct file *filp);
+extern void usb_serial_generic_close(struct usb_serial_port *port);
extern int usb_serial_generic_resume(struct usb_serial *serial);
extern int usb_serial_generic_write_room(struct tty_struct *tty);
extern int usb_serial_generic_chars_in_buffer(struct tty_struct *tty);
list_del(&old->task_list);
}
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int sync, void *key);
void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
+++ /dev/null
-#ifndef _TRACE_BLOCK_H
-#define _TRACE_BLOCK_H
-
-#include <linux/blkdev.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(block_rq_abort,
- TP_PROTO(struct request_queue *q, struct request *rq),
- TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_insert,
- TP_PROTO(struct request_queue *q, struct request *rq),
- TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_issue,
- TP_PROTO(struct request_queue *q, struct request *rq),
- TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_requeue,
- TP_PROTO(struct request_queue *q, struct request *rq),
- TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_complete,
- TP_PROTO(struct request_queue *q, struct request *rq),
- TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_bio_bounce,
- TP_PROTO(struct request_queue *q, struct bio *bio),
- TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_complete,
- TP_PROTO(struct request_queue *q, struct bio *bio),
- TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_backmerge,
- TP_PROTO(struct request_queue *q, struct bio *bio),
- TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_frontmerge,
- TP_PROTO(struct request_queue *q, struct bio *bio),
- TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_queue,
- TP_PROTO(struct request_queue *q, struct bio *bio),
- TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_getrq,
- TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
- TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_sleeprq,
- TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
- TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_plug,
- TP_PROTO(struct request_queue *q),
- TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_timer,
- TP_PROTO(struct request_queue *q),
- TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_io,
- TP_PROTO(struct request_queue *q),
- TP_ARGS(q));
-
-DECLARE_TRACE(block_split,
- TP_PROTO(struct request_queue *q, struct bio *bio, unsigned int pdu),
- TP_ARGS(q, bio, pdu));
-
-DECLARE_TRACE(block_remap,
- TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
- sector_t from, sector_t to),
- TP_ARGS(q, bio, dev, from, to));
-
-#endif
--- /dev/null
+/*
+ * Trace files that want to automate creationg of all tracepoints defined
+ * in their file should include this file. The following are macros that the
+ * trace file may define:
+ *
+ * TRACE_SYSTEM defines the system the tracepoint is for
+ *
+ * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h
+ * This macro may be defined to tell define_trace.h what file to include.
+ * Note, leave off the ".h".
+ *
+ * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace
+ * then this macro can define the path to use. Note, the path is relative to
+ * define_trace.h, not the file including it. Full path names for out of tree
+ * modules must be used.
+ */
+
+#ifdef CREATE_TRACE_POINTS
+
+/* Prevent recursion */
+#undef CREATE_TRACE_POINTS
+
+#include <linux/stringify.h>
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
+ DEFINE_TRACE(name)
+
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args) \
+ DEFINE_TRACE(name)
+
+#undef TRACE_INCLUDE
+#undef __TRACE_INCLUDE
+
+#ifndef TRACE_INCLUDE_FILE
+# define TRACE_INCLUDE_FILE TRACE_SYSTEM
+# define UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifndef TRACE_INCLUDE_PATH
+# define __TRACE_INCLUDE(system) <trace/events/system.h>
+# define UNDEF_TRACE_INCLUDE_PATH
+#else
+# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h)
+#endif
+
+# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system)
+
+/* Let the trace headers be reread */
+#define TRACE_HEADER_MULTI_READ
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#ifdef CONFIG_EVENT_TRACING
+#include <trace/ftrace.h>
+#endif
+
+#undef TRACE_HEADER_MULTI_READ
+
+/* Only undef what we defined in this file */
+#ifdef UNDEF_TRACE_INCLUDE_FILE
+# undef TRACE_INCLUDE_FILE
+# undef UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifdef UNDEF_TRACE_INCLUDE_PATH
+# undef TRACE_INCLUDE_PATH
+# undef UNDEF_TRACE_INCLUDE_PATH
+#endif
+
+/* We may be processing more files */
+#define CREATE_TRACE_POINTS
+
+#endif /* CREATE_TRACE_POINTS */
--- /dev/null
+#if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLOCK_H
+
+#include <linux/blktrace_api.h>
+#include <linux/blkdev.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
+TRACE_EVENT(block_rq_abort,
+
+ TP_PROTO(struct request_queue *q, struct request *rq),
+
+ TP_ARGS(q, rq),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( int, errors )
+ __array( char, rwbs, 6 )
+ __dynamic_array( char, cmd, blk_cmd_buf_len(rq) )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->sector = blk_pc_request(rq) ? 0 : rq->hard_sector;
+ __entry->nr_sector = blk_pc_request(rq) ?
+ 0 : rq->hard_nr_sectors;
+ __entry->errors = rq->errors;
+
+ blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_dump_cmd(__get_str(cmd), rq);
+ ),
+
+ TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->rwbs, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_insert,
+
+ TP_PROTO(struct request_queue *q, struct request *rq),
+
+ TP_ARGS(q, rq),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( unsigned int, bytes )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ __dynamic_array( char, cmd, blk_cmd_buf_len(rq) )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->sector = blk_pc_request(rq) ? 0 : rq->hard_sector;
+ __entry->nr_sector = blk_pc_request(rq) ?
+ 0 : rq->hard_nr_sectors;
+ __entry->bytes = blk_pc_request(rq) ? rq->data_len : 0;
+
+ blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_dump_cmd(__get_str(cmd), rq);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->rwbs, __entry->bytes, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_issue,
+
+ TP_PROTO(struct request_queue *q, struct request *rq),
+
+ TP_ARGS(q, rq),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( unsigned int, bytes )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ __dynamic_array( char, cmd, blk_cmd_buf_len(rq) )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->sector = blk_pc_request(rq) ? 0 : rq->hard_sector;
+ __entry->nr_sector = blk_pc_request(rq) ?
+ 0 : rq->hard_nr_sectors;
+ __entry->bytes = blk_pc_request(rq) ? rq->data_len : 0;
+
+ blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_dump_cmd(__get_str(cmd), rq);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->rwbs, __entry->bytes, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_requeue,
+
+ TP_PROTO(struct request_queue *q, struct request *rq),
+
+ TP_ARGS(q, rq),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( int, errors )
+ __array( char, rwbs, 6 )
+ __dynamic_array( char, cmd, blk_cmd_buf_len(rq) )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->sector = blk_pc_request(rq) ? 0 : rq->hard_sector;
+ __entry->nr_sector = blk_pc_request(rq) ?
+ 0 : rq->hard_nr_sectors;
+ __entry->errors = rq->errors;
+
+ blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_dump_cmd(__get_str(cmd), rq);
+ ),
+
+ TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->rwbs, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_complete,
+
+ TP_PROTO(struct request_queue *q, struct request *rq),
+
+ TP_ARGS(q, rq),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( int, errors )
+ __array( char, rwbs, 6 )
+ __dynamic_array( char, cmd, blk_cmd_buf_len(rq) )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->sector = blk_pc_request(rq) ? 0 : rq->hard_sector;
+ __entry->nr_sector = blk_pc_request(rq) ?
+ 0 : rq->hard_nr_sectors;
+ __entry->errors = rq->errors;
+
+ blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_dump_cmd(__get_str(cmd), rq);
+ ),
+
+ TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->rwbs, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->errors)
+);
+TRACE_EVENT(block_bio_bounce,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio),
+
+ TP_ARGS(q, bio),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio->bi_bdev->bd_dev;
+ __entry->sector = bio->bi_sector;
+ __entry->nr_sector = bio->bi_size >> 9;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_complete,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio),
+
+ TP_ARGS(q, bio),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned, nr_sector )
+ __field( int, error )
+ __array( char, rwbs, 6 )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio->bi_bdev->bd_dev;
+ __entry->sector = bio->bi_sector;
+ __entry->nr_sector = bio->bi_size >> 9;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u [%d]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->error)
+);
+
+TRACE_EVENT(block_bio_backmerge,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio),
+
+ TP_ARGS(q, bio),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio->bi_bdev->bd_dev;
+ __entry->sector = bio->bi_sector;
+ __entry->nr_sector = bio->bi_size >> 9;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_frontmerge,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio),
+
+ TP_ARGS(q, bio),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned, nr_sector )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio->bi_bdev->bd_dev;
+ __entry->sector = bio->bi_sector;
+ __entry->nr_sector = bio->bi_size >> 9;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_queue,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio),
+
+ TP_ARGS(q, bio),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio->bi_bdev->bd_dev;
+ __entry->sector = bio->bi_sector;
+ __entry->nr_sector = bio->bi_size >> 9;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_getrq,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+ TP_ARGS(q, bio, rw),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio ? bio->bi_bdev->bd_dev : 0;
+ __entry->sector = bio ? bio->bi_sector : 0;
+ __entry->nr_sector = bio ? bio->bi_size >> 9 : 0;
+ blk_fill_rwbs(__entry->rwbs,
+ bio ? bio->bi_rw : 0, __entry->nr_sector);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_sleeprq,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+ TP_ARGS(q, bio, rw),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio ? bio->bi_bdev->bd_dev : 0;
+ __entry->sector = bio ? bio->bi_sector : 0;
+ __entry->nr_sector = bio ? bio->bi_size >> 9 : 0;
+ blk_fill_rwbs(__entry->rwbs,
+ bio ? bio->bi_rw : 0, __entry->nr_sector);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_plug,
+
+ TP_PROTO(struct request_queue *q),
+
+ TP_ARGS(q),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("[%s]", __entry->comm)
+);
+
+TRACE_EVENT(block_unplug_timer,
+
+ TP_PROTO(struct request_queue *q),
+
+ TP_ARGS(q),
+
+ TP_STRUCT__entry(
+ __field( int, nr_rq )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->nr_rq = q->rq.count[READ] + q->rq.count[WRITE];
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_unplug_io,
+
+ TP_PROTO(struct request_queue *q),
+
+ TP_ARGS(q),
+
+ TP_STRUCT__entry(
+ __field( int, nr_rq )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->nr_rq = q->rq.count[READ] + q->rq.count[WRITE];
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_split,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio,
+ unsigned int new_sector),
+
+ TP_ARGS(q, bio, new_sector),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( sector_t, new_sector )
+ __array( char, rwbs, 6 )
+ __array( char, comm, TASK_COMM_LEN )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio->bi_bdev->bd_dev;
+ __entry->sector = bio->bi_sector;
+ __entry->new_sector = new_sector;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ ),
+
+ TP_printk("%d,%d %s %llu / %llu [%s]",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ (unsigned long long)__entry->new_sector,
+ __entry->comm)
+);
+
+TRACE_EVENT(block_remap,
+
+ TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
+ sector_t from),
+
+ TP_ARGS(q, bio, dev, from),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( dev_t, old_dev )
+ __field( sector_t, old_sector )
+ __array( char, rwbs, 6 )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio->bi_bdev->bd_dev;
+ __entry->sector = bio->bi_sector;
+ __entry->nr_sector = bio->bi_size >> 9;
+ __entry->old_dev = dev;
+ __entry->old_sector = from;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector,
+ MAJOR(__entry->old_dev), MINOR(__entry->old_dev),
+ (unsigned long long)__entry->old_sector)
+);
+
+#endif /* _TRACE_BLOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
--- /dev/null
+#if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_H
+
+#include <linux/tracepoint.h>
+#include <linux/interrupt.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
+#define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
+#define show_softirq_name(val) \
+ __print_symbolic(val, \
+ softirq_name(HI), \
+ softirq_name(TIMER), \
+ softirq_name(NET_TX), \
+ softirq_name(NET_RX), \
+ softirq_name(BLOCK), \
+ softirq_name(TASKLET), \
+ softirq_name(SCHED), \
+ softirq_name(HRTIMER), \
+ softirq_name(RCU))
+
+/**
+ * irq_handler_entry - called immediately before the irq action handler
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ *
+ * The struct irqaction pointed to by @action contains various
+ * information about the handler, including the device name,
+ * @action->name, and the device id, @action->dev_id. When used in
+ * conjunction with the irq_handler_exit tracepoint, we can figure
+ * out irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_entry,
+
+ TP_PROTO(int irq, struct irqaction *action),
+
+ TP_ARGS(irq, action),
+
+ TP_STRUCT__entry(
+ __field( int, irq )
+ __string( name, action->name )
+ ),
+
+ TP_fast_assign(
+ __entry->irq = irq;
+ __assign_str(name, action->name);
+ ),
+
+ TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name))
+);
+
+/**
+ * irq_handler_exit - called immediately after the irq action handler returns
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ * @ret: return value
+ *
+ * If the @ret value is set to IRQ_HANDLED, then we know that the corresponding
+ * @action->handler scuccessully handled this irq. Otherwise, the irq might be
+ * a shared irq line, or the irq was not handled successfully. Can be used in
+ * conjunction with the irq_handler_entry to understand irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_exit,
+
+ TP_PROTO(int irq, struct irqaction *action, int ret),
+
+ TP_ARGS(irq, action, ret),
+
+ TP_STRUCT__entry(
+ __field( int, irq )
+ __field( int, ret )
+ ),
+
+ TP_fast_assign(
+ __entry->irq = irq;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("irq=%d return=%s",
+ __entry->irq, __entry->ret ? "handled" : "unhandled")
+);
+
+/**
+ * softirq_entry - called immediately before the softirq handler
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter, contains a pointer to the struct softirq_action
+ * which has a pointer to the action handler that is called. By subtracting
+ * the @vec pointer from the @h pointer, we can determine the softirq
+ * number. Also, when used in combination with the softirq_exit tracepoint
+ * we can determine the softirq latency.
+ */
+TRACE_EVENT(softirq_entry,
+
+ TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+ TP_ARGS(h, vec),
+
+ TP_STRUCT__entry(
+ __field( int, vec )
+ ),
+
+ TP_fast_assign(
+ __entry->vec = (int)(h - vec);
+ ),
+
+ TP_printk("softirq=%d action=%s", __entry->vec,
+ show_softirq_name(__entry->vec))
+);
+
+/**
+ * softirq_exit - called immediately after the softirq handler returns
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the struct softirq_action
+ * that has handled the softirq. By subtracting the @vec pointer from
+ * the @h pointer, we can determine the softirq number. Also, when used in
+ * combination with the softirq_entry tracepoint we can determine the softirq
+ * latency.
+ */
+TRACE_EVENT(softirq_exit,
+
+ TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+ TP_ARGS(h, vec),
+
+ TP_STRUCT__entry(
+ __field( int, vec )
+ ),
+
+ TP_fast_assign(
+ __entry->vec = (int)(h - vec);
+ ),
+
+ TP_printk("softirq=%d action=%s", __entry->vec,
+ show_softirq_name(__entry->vec))
+);
+
+#endif /* _TRACE_IRQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
--- /dev/null
+#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KMEM_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kmem
+
+/*
+ * The order of these masks is important. Matching masks will be seen
+ * first and the left over flags will end up showing by themselves.
+ *
+ * For example, if we have GFP_KERNEL before GFP_USER we wil get:
+ *
+ * GFP_KERNEL|GFP_HARDWALL
+ *
+ * Thus most bits set go first.
+ */
+#define show_gfp_flags(flags) \
+ (flags) ? __print_flags(flags, "|", \
+ {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"}, \
+ {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \
+ {(unsigned long)GFP_USER, "GFP_USER"}, \
+ {(unsigned long)GFP_TEMPORARY, "GFP_TEMPORARY"}, \
+ {(unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \
+ {(unsigned long)GFP_NOFS, "GFP_NOFS"}, \
+ {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \
+ {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \
+ {(unsigned long)__GFP_HIGH, "GFP_HIGH"}, \
+ {(unsigned long)__GFP_WAIT, "GFP_WAIT"}, \
+ {(unsigned long)__GFP_IO, "GFP_IO"}, \
+ {(unsigned long)__GFP_COLD, "GFP_COLD"}, \
+ {(unsigned long)__GFP_NOWARN, "GFP_NOWARN"}, \
+ {(unsigned long)__GFP_REPEAT, "GFP_REPEAT"}, \
+ {(unsigned long)__GFP_NOFAIL, "GFP_NOFAIL"}, \
+ {(unsigned long)__GFP_NORETRY, "GFP_NORETRY"}, \
+ {(unsigned long)__GFP_COMP, "GFP_COMP"}, \
+ {(unsigned long)__GFP_ZERO, "GFP_ZERO"}, \
+ {(unsigned long)__GFP_NOMEMALLOC, "GFP_NOMEMALLOC"}, \
+ {(unsigned long)__GFP_HARDWALL, "GFP_HARDWALL"}, \
+ {(unsigned long)__GFP_THISNODE, "GFP_THISNODE"}, \
+ {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \
+ {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"} \
+ ) : "GFP_NOWAIT"
+
+TRACE_EVENT(kmalloc,
+
+ TP_PROTO(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags),
+
+ TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ __field( size_t, bytes_req )
+ __field( size_t, bytes_alloc )
+ __field( gfp_t, gfp_flags )
+ ),
+
+ TP_fast_assign(
+ __entry->call_site = call_site;
+ __entry->ptr = ptr;
+ __entry->bytes_req = bytes_req;
+ __entry->bytes_alloc = bytes_alloc;
+ __entry->gfp_flags = gfp_flags;
+ ),
+
+ TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+ __entry->call_site,
+ __entry->ptr,
+ __entry->bytes_req,
+ __entry->bytes_alloc,
+ show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmem_cache_alloc,
+
+ TP_PROTO(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags),
+
+ TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ __field( size_t, bytes_req )
+ __field( size_t, bytes_alloc )
+ __field( gfp_t, gfp_flags )
+ ),
+
+ TP_fast_assign(
+ __entry->call_site = call_site;
+ __entry->ptr = ptr;
+ __entry->bytes_req = bytes_req;
+ __entry->bytes_alloc = bytes_alloc;
+ __entry->gfp_flags = gfp_flags;
+ ),
+
+ TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+ __entry->call_site,
+ __entry->ptr,
+ __entry->bytes_req,
+ __entry->bytes_alloc,
+ show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmalloc_node,
+
+ TP_PROTO(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node),
+
+ TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ __field( size_t, bytes_req )
+ __field( size_t, bytes_alloc )
+ __field( gfp_t, gfp_flags )
+ __field( int, node )
+ ),
+
+ TP_fast_assign(
+ __entry->call_site = call_site;
+ __entry->ptr = ptr;
+ __entry->bytes_req = bytes_req;
+ __entry->bytes_alloc = bytes_alloc;
+ __entry->gfp_flags = gfp_flags;
+ __entry->node = node;
+ ),
+
+ TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+ __entry->call_site,
+ __entry->ptr,
+ __entry->bytes_req,
+ __entry->bytes_alloc,
+ show_gfp_flags(__entry->gfp_flags),
+ __entry->node)
+);
+
+TRACE_EVENT(kmem_cache_alloc_node,
+
+ TP_PROTO(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node),
+
+ TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ __field( size_t, bytes_req )
+ __field( size_t, bytes_alloc )
+ __field( gfp_t, gfp_flags )
+ __field( int, node )
+ ),
+
+ TP_fast_assign(
+ __entry->call_site = call_site;
+ __entry->ptr = ptr;
+ __entry->bytes_req = bytes_req;
+ __entry->bytes_alloc = bytes_alloc;
+ __entry->gfp_flags = gfp_flags;
+ __entry->node = node;
+ ),
+
+ TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+ __entry->call_site,
+ __entry->ptr,
+ __entry->bytes_req,
+ __entry->bytes_alloc,
+ show_gfp_flags(__entry->gfp_flags),
+ __entry->node)
+);
+
+TRACE_EVENT(kfree,
+
+ TP_PROTO(unsigned long call_site, const void *ptr),
+
+ TP_ARGS(call_site, ptr),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ ),
+
+ TP_fast_assign(
+ __entry->call_site = call_site;
+ __entry->ptr = ptr;
+ ),
+
+ TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+
+TRACE_EVENT(kmem_cache_free,
+
+ TP_PROTO(unsigned long call_site, const void *ptr),
+
+ TP_ARGS(call_site, ptr),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ ),
+
+ TP_fast_assign(
+ __entry->call_site = call_site;
+ __entry->ptr = ptr;
+ ),
+
+ TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+#endif /* _TRACE_KMEM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
--- /dev/null
+#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCKDEP_H
+
+#include <linux/lockdep.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lockdep
+
+#ifdef CONFIG_LOCKDEP
+
+TRACE_EVENT(lock_acquire,
+
+ TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
+ int trylock, int read, int check,
+ struct lockdep_map *next_lock, unsigned long ip),
+
+ TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, flags)
+ __string(name, lock->name)
+ ),
+
+ TP_fast_assign(
+ __entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
+ __assign_str(name, lock->name);
+ ),
+
+ TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+ (__entry->flags & 2) ? "read " : "",
+ __get_str(name))
+);
+
+TRACE_EVENT(lock_release,
+
+ TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+
+ TP_ARGS(lock, nested, ip),
+
+ TP_STRUCT__entry(
+ __string(name, lock->name)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, lock->name);
+ ),
+
+ TP_printk("%s", __get_str(name))
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+TRACE_EVENT(lock_contended,
+
+ TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+ TP_ARGS(lock, ip),
+
+ TP_STRUCT__entry(
+ __string(name, lock->name)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, lock->name);
+ ),
+
+ TP_printk("%s", __get_str(name))
+);
+
+TRACE_EVENT(lock_acquired,
+ TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+
+ TP_ARGS(lock, ip, waittime),
+
+ TP_STRUCT__entry(
+ __string(name, lock->name)
+ __field(unsigned long, wait_usec)
+ __field(unsigned long, wait_nsec_rem)
+ ),
+ TP_fast_assign(
+ __assign_str(name, lock->name);
+ __entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
+ __entry->wait_usec = (unsigned long) waittime;
+ ),
+ TP_printk("%s (%lu.%03lu us)", __get_str(name), __entry->wait_usec,
+ __entry->wait_nsec_rem)
+);
+
+#endif
+#endif
+
+#endif /* _TRACE_LOCKDEP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
--- /dev/null
+#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCHED_H
+
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sched
+
+/*
+ * Tracepoint for calling kthread_stop, performed to end a kthread:
+ */
+TRACE_EVENT(sched_kthread_stop,
+
+ TP_PROTO(struct task_struct *t),
+
+ TP_ARGS(t),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, t->comm, TASK_COMM_LEN);
+ __entry->pid = t->pid;
+ ),
+
+ TP_printk("task %s:%d", __entry->comm, __entry->pid)
+);
+
+/*
+ * Tracepoint for the return value of the kthread stopping:
+ */
+TRACE_EVENT(sched_kthread_stop_ret,
+
+ TP_PROTO(int ret),
+
+ TP_ARGS(ret),
+
+ TP_STRUCT__entry(
+ __field( int, ret )
+ ),
+
+ TP_fast_assign(
+ __entry->ret = ret;
+ ),
+
+ TP_printk("ret %d", __entry->ret)
+);
+
+/*
+ * Tracepoint for waiting on task to unschedule:
+ *
+ * (NOTE: the 'rq' argument is not used by generic trace events,
+ * but used by the latency tracer plugin. )
+ */
+TRACE_EVENT(sched_wait_task,
+
+ TP_PROTO(struct rq *rq, struct task_struct *p),
+
+ TP_ARGS(rq, p),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, prio )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->prio = p->prio;
+ ),
+
+ TP_printk("task %s:%d [%d]",
+ __entry->comm, __entry->pid, __entry->prio)
+);
+
+/*
+ * Tracepoint for waking up a task:
+ *
+ * (NOTE: the 'rq' argument is not used by generic trace events,
+ * but used by the latency tracer plugin. )
+ */
+TRACE_EVENT(sched_wakeup,
+
+ TP_PROTO(struct rq *rq, struct task_struct *p, int success),
+
+ TP_ARGS(rq, p, success),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, prio )
+ __field( int, success )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->prio = p->prio;
+ __entry->success = success;
+ ),
+
+ TP_printk("task %s:%d [%d] success=%d",
+ __entry->comm, __entry->pid, __entry->prio,
+ __entry->success)
+);
+
+/*
+ * Tracepoint for waking up a new task:
+ *
+ * (NOTE: the 'rq' argument is not used by generic trace events,
+ * but used by the latency tracer plugin. )
+ */
+TRACE_EVENT(sched_wakeup_new,
+
+ TP_PROTO(struct rq *rq, struct task_struct *p, int success),
+
+ TP_ARGS(rq, p, success),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, prio )
+ __field( int, success )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->prio = p->prio;
+ __entry->success = success;
+ ),
+
+ TP_printk("task %s:%d [%d] success=%d",
+ __entry->comm, __entry->pid, __entry->prio,
+ __entry->success)
+);
+
+/*
+ * Tracepoint for task switches, performed by the scheduler:
+ *
+ * (NOTE: the 'rq' argument is not used by generic trace events,
+ * but used by the latency tracer plugin. )
+ */
+TRACE_EVENT(sched_switch,
+
+ TP_PROTO(struct rq *rq, struct task_struct *prev,
+ struct task_struct *next),
+
+ TP_ARGS(rq, prev, next),
+
+ TP_STRUCT__entry(
+ __array( char, prev_comm, TASK_COMM_LEN )
+ __field( pid_t, prev_pid )
+ __field( int, prev_prio )
+ __field( long, prev_state )
+ __array( char, next_comm, TASK_COMM_LEN )
+ __field( pid_t, next_pid )
+ __field( int, next_prio )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
+ __entry->prev_pid = prev->pid;
+ __entry->prev_prio = prev->prio;
+ __entry->prev_state = prev->state;
+ memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
+ __entry->next_pid = next->pid;
+ __entry->next_prio = next->prio;
+ ),
+
+ TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
+ __entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+ __entry->prev_state ?
+ __print_flags(__entry->prev_state, "|",
+ { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
+ { 16, "Z" }, { 32, "X" }, { 64, "x" },
+ { 128, "W" }) : "R",
+ __entry->next_comm, __entry->next_pid, __entry->next_prio)
+);
+
+/*
+ * Tracepoint for a task being migrated:
+ */
+TRACE_EVENT(sched_migrate_task,
+
+ TP_PROTO(struct task_struct *p, int dest_cpu),
+
+ TP_ARGS(p, dest_cpu),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, prio )
+ __field( int, orig_cpu )
+ __field( int, dest_cpu )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->prio = p->prio;
+ __entry->orig_cpu = task_cpu(p);
+ __entry->dest_cpu = dest_cpu;
+ ),
+
+ TP_printk("task %s:%d [%d] from: %d to: %d",
+ __entry->comm, __entry->pid, __entry->prio,
+ __entry->orig_cpu, __entry->dest_cpu)
+);
+
+/*
+ * Tracepoint for freeing a task:
+ */
+TRACE_EVENT(sched_process_free,
+
+ TP_PROTO(struct task_struct *p),
+
+ TP_ARGS(p),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, prio )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->prio = p->prio;
+ ),
+
+ TP_printk("task %s:%d [%d]",
+ __entry->comm, __entry->pid, __entry->prio)
+);
+
+/*
+ * Tracepoint for a task exiting:
+ */
+TRACE_EVENT(sched_process_exit,
+
+ TP_PROTO(struct task_struct *p),
+
+ TP_ARGS(p),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, prio )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->prio = p->prio;
+ ),
+
+ TP_printk("task %s:%d [%d]",
+ __entry->comm, __entry->pid, __entry->prio)
+);
+
+/*
+ * Tracepoint for a waiting task:
+ */
+TRACE_EVENT(sched_process_wait,
+
+ TP_PROTO(struct pid *pid),
+
+ TP_ARGS(pid),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( int, prio )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+ __entry->pid = pid_nr(pid);
+ __entry->prio = current->prio;
+ ),
+
+ TP_printk("task %s:%d [%d]",
+ __entry->comm, __entry->pid, __entry->prio)
+);
+
+/*
+ * Tracepoint for do_fork:
+ */
+TRACE_EVENT(sched_process_fork,
+
+ TP_PROTO(struct task_struct *parent, struct task_struct *child),
+
+ TP_ARGS(parent, child),
+
+ TP_STRUCT__entry(
+ __array( char, parent_comm, TASK_COMM_LEN )
+ __field( pid_t, parent_pid )
+ __array( char, child_comm, TASK_COMM_LEN )
+ __field( pid_t, child_pid )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN);
+ __entry->parent_pid = parent->pid;
+ memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN);
+ __entry->child_pid = child->pid;
+ ),
+
+ TP_printk("parent %s:%d child %s:%d",
+ __entry->parent_comm, __entry->parent_pid,
+ __entry->child_comm, __entry->child_pid)
+);
+
+/*
+ * Tracepoint for sending a signal:
+ */
+TRACE_EVENT(sched_signal_send,
+
+ TP_PROTO(int sig, struct task_struct *p),
+
+ TP_ARGS(sig, p),
+
+ TP_STRUCT__entry(
+ __field( int, sig )
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+ __entry->pid = p->pid;
+ __entry->sig = sig;
+ ),
+
+ TP_printk("sig: %d task %s:%d",
+ __entry->sig, __entry->comm, __entry->pid)
+);
+
+#endif /* _TRACE_SCHED_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
--- /dev/null
+#if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SKB_H
+
+#include <linux/skbuff.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM skb
+
+/*
+ * Tracepoint for free an sk_buff:
+ */
+TRACE_EVENT(kfree_skb,
+
+ TP_PROTO(struct sk_buff *skb, void *location),
+
+ TP_ARGS(skb, location),
+
+ TP_STRUCT__entry(
+ __field( void *, skbaddr )
+ __field( unsigned short, protocol )
+ __field( void *, location )
+ ),
+
+ TP_fast_assign(
+ __entry->skbaddr = skb;
+ if (skb) {
+ __entry->protocol = ntohs(skb->protocol);
+ }
+ __entry->location = location;
+ ),
+
+ TP_printk("skbaddr=%p protocol=%u location=%p",
+ __entry->skbaddr, __entry->protocol, __entry->location)
+);
+
+#endif /* _TRACE_SKB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
--- /dev/null
+#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WORKQUEUE_H
+
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
+TRACE_EVENT(workqueue_insertion,
+
+ TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+ TP_ARGS(wq_thread, work),
+
+ TP_STRUCT__entry(
+ __array(char, thread_comm, TASK_COMM_LEN)
+ __field(pid_t, thread_pid)
+ __field(work_func_t, func)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+ __entry->thread_pid = wq_thread->pid;
+ __entry->func = work->func;
+ ),
+
+ TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+ __entry->thread_pid, __entry->func)
+);
+
+TRACE_EVENT(workqueue_execution,
+
+ TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+ TP_ARGS(wq_thread, work),
+
+ TP_STRUCT__entry(
+ __array(char, thread_comm, TASK_COMM_LEN)
+ __field(pid_t, thread_pid)
+ __field(work_func_t, func)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+ __entry->thread_pid = wq_thread->pid;
+ __entry->func = work->func;
+ ),
+
+ TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+ __entry->thread_pid, __entry->func)
+);
+
+/* Trace the creation of one workqueue thread on a cpu */
+TRACE_EVENT(workqueue_creation,
+
+ TP_PROTO(struct task_struct *wq_thread, int cpu),
+
+ TP_ARGS(wq_thread, cpu),
+
+ TP_STRUCT__entry(
+ __array(char, thread_comm, TASK_COMM_LEN)
+ __field(pid_t, thread_pid)
+ __field(int, cpu)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+ __entry->thread_pid = wq_thread->pid;
+ __entry->cpu = cpu;
+ ),
+
+ TP_printk("thread=%s:%d cpu=%d", __entry->thread_comm,
+ __entry->thread_pid, __entry->cpu)
+);
+
+TRACE_EVENT(workqueue_destruction,
+
+ TP_PROTO(struct task_struct *wq_thread),
+
+ TP_ARGS(wq_thread),
+
+ TP_STRUCT__entry(
+ __array(char, thread_comm, TASK_COMM_LEN)
+ __field(pid_t, thread_pid)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+ __entry->thread_pid = wq_thread->pid;
+ ),
+
+ TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid)
+);
+
+#endif /* _TRACE_WORKQUEUE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
--- /dev/null
+/*
+ * Stage 1 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * struct ftrace_raw_<call> {
+ * struct trace_entry ent;
+ * <type> <item>;
+ * <type2> <item2>[<len>];
+ * [...]
+ * };
+ *
+ * The <type> <item> is created by the __field(type, item) macro or
+ * the __array(type2, item2, len) macro.
+ * We simply do "type item;", and that will create the fields
+ * in the structure.
+ */
+
+#include <linux/ftrace_event.h>
+
+#undef __field
+#define __field(type, item) type item;
+
+#undef __array
+#define __array(type, item, len) type item[len];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) unsigned short __data_loc_##item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
+ struct ftrace_raw_##name { \
+ struct trace_entry ent; \
+ tstruct \
+ char __data[0]; \
+ }; \
+ static struct ftrace_event_call event_##name
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+
+/*
+ * Stage 2 of the trace events.
+ *
+ * Include the following:
+ *
+ * struct ftrace_data_offsets_<call> {
+ * int <item1>;
+ * int <item2>;
+ * [...]
+ * };
+ *
+ * The __dynamic_array() macro will create each int <item>, this is
+ * to keep the offset of each array from the beginning of the event.
+ */
+
+#undef __field
+#define __field(type, item);
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) int item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
+ struct ftrace_data_offsets_##call { \
+ tstruct; \
+ };
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Setup the showing format of trace point.
+ *
+ * int
+ * ftrace_format_##call(struct trace_seq *s)
+ * {
+ * struct ftrace_raw_##call field;
+ * int ret;
+ *
+ * ret = trace_seq_printf(s, #type " " #item ";"
+ * " offset:%u; size:%u;\n",
+ * offsetof(struct ftrace_raw_##call, item),
+ * sizeof(field.type));
+ *
+ * }
+ */
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef __field
+#define __field(type, item) \
+ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
+ "offset:%u;\tsize:%u;\n", \
+ (unsigned int)offsetof(typeof(field), item), \
+ (unsigned int)sizeof(field.item)); \
+ if (!ret) \
+ return 0;
+
+#undef __array
+#define __array(type, item, len) \
+ ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
+ "offset:%u;\tsize:%u;\n", \
+ (unsigned int)offsetof(typeof(field), item), \
+ (unsigned int)sizeof(field.item)); \
+ if (!ret) \
+ return 0;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) \
+ ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t" \
+ "offset:%u;\tsize:%u;\n", \
+ (unsigned int)offsetof(typeof(field), \
+ __data_loc_##item), \
+ (unsigned int)sizeof(field.__data_loc_##item)); \
+ if (!ret) \
+ return 0;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __entry
+#define __entry REC
+
+#undef __print_symbolic
+#undef __get_dynamic_array
+#undef __get_str
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
+
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
+static int \
+ftrace_format_##call(struct trace_seq *s) \
+{ \
+ struct ftrace_raw_##call field __attribute__((unused)); \
+ int ret = 0; \
+ \
+ tstruct; \
+ \
+ trace_seq_printf(s, "\nprint fmt: " print); \
+ \
+ return ret; \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 3 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * enum print_line_t
+ * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
+ * {
+ * struct trace_seq *s = &iter->seq;
+ * struct ftrace_raw_<call> *field; <-- defined in stage 1
+ * struct trace_entry *entry;
+ * struct trace_seq *p;
+ * int ret;
+ *
+ * entry = iter->ent;
+ *
+ * if (entry->type != event_<call>.id) {
+ * WARN_ON_ONCE(1);
+ * return TRACE_TYPE_UNHANDLED;
+ * }
+ *
+ * field = (typeof(field))entry;
+ *
+ * p = get_cpu_var(ftrace_event_seq);
+ * trace_seq_init(p);
+ * ret = trace_seq_printf(s, <TP_printk> "\n");
+ * put_cpu();
+ * if (!ret)
+ * return TRACE_TYPE_PARTIAL_LINE;
+ *
+ * return TRACE_TYPE_HANDLED;
+ * }
+ *
+ * This is the method used to print the raw event to the trace
+ * output format. Note, this is not needed if the data is read
+ * in binary.
+ */
+
+#undef __entry
+#define __entry field
+
+#undef TP_printk
+#define TP_printk(fmt, args...) fmt "\n", args
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field) \
+ ((void *)__entry + __entry->__data_loc_##field)
+
+#undef __get_str
+#define __get_str(field) (char *)__get_dynamic_array(field)
+
+#undef __print_flags
+#define __print_flags(flag, delim, flag_array...) \
+ ({ \
+ static const struct trace_print_flags flags[] = \
+ { flag_array, { -1, NULL }}; \
+ ftrace_print_flags_seq(p, delim, flag, flags); \
+ })
+
+#undef __print_symbolic
+#define __print_symbolic(value, symbol_array...) \
+ ({ \
+ static const struct trace_print_flags symbols[] = \
+ { symbol_array, { -1, NULL }}; \
+ ftrace_print_symbols_seq(p, value, symbols); \
+ })
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
+enum print_line_t \
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
+{ \
+ struct trace_seq *s = &iter->seq; \
+ struct ftrace_raw_##call *field; \
+ struct trace_entry *entry; \
+ struct trace_seq *p; \
+ int ret; \
+ \
+ entry = iter->ent; \
+ \
+ if (entry->type != event_##call.id) { \
+ WARN_ON_ONCE(1); \
+ return TRACE_TYPE_UNHANDLED; \
+ } \
+ \
+ field = (typeof(field))entry; \
+ \
+ p = &get_cpu_var(ftrace_event_seq); \
+ trace_seq_init(p); \
+ ret = trace_seq_printf(s, #call ": " print); \
+ put_cpu(); \
+ if (!ret) \
+ return TRACE_TYPE_PARTIAL_LINE; \
+ \
+ return TRACE_TYPE_HANDLED; \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef __field
+#define __field(type, item) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed_type(type)); \
+ if (ret) \
+ return ret;
+
+#undef __array
+#define __array(type, item, len) \
+ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
+ ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), 0); \
+ if (ret) \
+ return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) \
+ ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\
+ offsetof(typeof(field), __data_loc_##item), \
+ sizeof(field.__data_loc_##item), 0);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
+int \
+ftrace_define_fields_##call(void) \
+{ \
+ struct ftrace_raw_##call field; \
+ struct ftrace_event_call *event_call = &event_##call; \
+ int ret; \
+ \
+ __common_field(int, type, 1); \
+ __common_field(unsigned char, flags, 0); \
+ __common_field(unsigned char, preempt_count, 0); \
+ __common_field(int, pid, 1); \
+ __common_field(int, tgid, 1); \
+ \
+ tstruct; \
+ \
+ return ret; \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * remember the offset of each array from the beginning of the event.
+ */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) \
+ __data_offsets->item = __data_size + \
+ offsetof(typeof(*entry), __data); \
+ __data_size += (len) * sizeof(type);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1) \
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
+static inline int ftrace_get_offsets_##call( \
+ struct ftrace_data_offsets_##call *__data_offsets, proto) \
+{ \
+ int __data_size = 0; \
+ struct ftrace_raw_##call __maybe_unused *entry; \
+ \
+ tstruct; \
+ \
+ return __data_size; \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 4 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * static void ftrace_event_<call>(proto)
+ * {
+ * event_trace_printk(_RET_IP_, "<call>: " <fmt>);
+ * }
+ *
+ * static int ftrace_reg_event_<call>(void)
+ * {
+ * int ret;
+ *
+ * ret = register_trace_<call>(ftrace_event_<call>);
+ * if (!ret)
+ * pr_info("event trace: Could not activate trace point "
+ * "probe to <call>");
+ * return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ * unregister_trace_<call>(ftrace_event_<call>);
+ * }
+ *
+ *
+ * For those macros defined with TRACE_EVENT:
+ *
+ * static struct ftrace_event_call event_<call>;
+ *
+ * static void ftrace_raw_event_<call>(proto)
+ * {
+ * struct ring_buffer_event *event;
+ * struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ * unsigned long irq_flags;
+ * int pc;
+ *
+ * local_save_flags(irq_flags);
+ * pc = preempt_count();
+ *
+ * event = trace_current_buffer_lock_reserve(event_<call>.id,
+ * sizeof(struct ftrace_raw_<call>),
+ * irq_flags, pc);
+ * if (!event)
+ * return;
+ * entry = ring_buffer_event_data(event);
+ *
+ * <assign>; <-- Here we assign the entries by the __field and
+ * __array macros.
+ *
+ * trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ * }
+ *
+ * static int ftrace_raw_reg_event_<call>(void)
+ * {
+ * int ret;
+ *
+ * ret = register_trace_<call>(ftrace_raw_event_<call>);
+ * if (!ret)
+ * pr_info("event trace: Could not activate trace point "
+ * "probe to <call>");
+ * return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ * unregister_trace_<call>(ftrace_raw_event_<call>);
+ * }
+ *
+ * static struct trace_event ftrace_event_type_<call> = {
+ * .trace = ftrace_raw_output_<call>, <-- stage 2
+ * };
+ *
+ * static int ftrace_raw_init_event_<call>(void)
+ * {
+ * int id;
+ *
+ * id = register_ftrace_event(&ftrace_event_type_<call>);
+ * if (!id)
+ * return -ENODEV;
+ * event_<call>.id = id;
+ * return 0;
+ * }
+ *
+ * static struct ftrace_event_call __used
+ * __attribute__((__aligned__(4)))
+ * __attribute__((section("_ftrace_events"))) event_<call> = {
+ * .name = "<call>",
+ * .system = "<system>",
+ * .raw_init = ftrace_raw_init_event_<call>,
+ * .regfunc = ftrace_reg_event_<call>,
+ * .unregfunc = ftrace_unreg_event_<call>,
+ * .show_format = ftrace_format_<call>,
+ * }
+ *
+ */
+
+#undef TP_FMT
+#define TP_FMT(fmt, args...) fmt "\n", ##args
+
+#ifdef CONFIG_EVENT_PROFILE
+#define _TRACE_PROFILE(call, proto, args) \
+static void ftrace_profile_##call(proto) \
+{ \
+ extern void perf_tpcounter_event(int); \
+ perf_tpcounter_event(event_##call.id); \
+} \
+ \
+static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
+{ \
+ int ret = 0; \
+ \
+ if (!atomic_inc_return(&event_call->profile_count)) \
+ ret = register_trace_##call(ftrace_profile_##call); \
+ \
+ return ret; \
+} \
+ \
+static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
+{ \
+ if (atomic_add_negative(-1, &event_call->profile_count)) \
+ unregister_trace_##call(ftrace_profile_##call); \
+}
+
+#define _TRACE_PROFILE_INIT(call) \
+ .profile_count = ATOMIC_INIT(-1), \
+ .profile_enable = ftrace_profile_enable_##call, \
+ .profile_disable = ftrace_profile_disable_##call,
+
+#else
+#define _TRACE_PROFILE(call, proto, args)
+#define _TRACE_PROFILE_INIT(call)
+#endif
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) \
+ __entry->__data_loc_##item = __data_offsets.item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1) \
+
+#undef __assign_str
+#define __assign_str(dst, src) \
+ strcpy(__get_str(dst), src);
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
+_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \
+ \
+static struct ftrace_event_call event_##call; \
+ \
+static void ftrace_raw_event_##call(proto) \
+{ \
+ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+ struct ftrace_event_call *event_call = &event_##call; \
+ struct ring_buffer_event *event; \
+ struct ftrace_raw_##call *entry; \
+ unsigned long irq_flags; \
+ int __data_size; \
+ int pc; \
+ \
+ local_save_flags(irq_flags); \
+ pc = preempt_count(); \
+ \
+ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+ \
+ event = trace_current_buffer_lock_reserve(event_##call.id, \
+ sizeof(*entry) + __data_size, \
+ irq_flags, pc); \
+ if (!event) \
+ return; \
+ entry = ring_buffer_event_data(event); \
+ \
+ \
+ tstruct \
+ \
+ { assign; } \
+ \
+ if (!filter_current_check_discard(event_call, entry, event)) \
+ trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+} \
+ \
+static int ftrace_raw_reg_event_##call(void) \
+{ \
+ int ret; \
+ \
+ ret = register_trace_##call(ftrace_raw_event_##call); \
+ if (ret) \
+ pr_info("event trace: Could not activate trace point " \
+ "probe to " #call "\n"); \
+ return ret; \
+} \
+ \
+static void ftrace_raw_unreg_event_##call(void) \
+{ \
+ unregister_trace_##call(ftrace_raw_event_##call); \
+} \
+ \
+static struct trace_event ftrace_event_type_##call = { \
+ .trace = ftrace_raw_output_##call, \
+}; \
+ \
+static int ftrace_raw_init_event_##call(void) \
+{ \
+ int id; \
+ \
+ id = register_ftrace_event(&ftrace_event_type_##call); \
+ if (!id) \
+ return -ENODEV; \
+ event_##call.id = id; \
+ INIT_LIST_HEAD(&event_##call.fields); \
+ init_preds(&event_##call); \
+ return 0; \
+} \
+ \
+static struct ftrace_event_call __used \
+__attribute__((__aligned__(4))) \
+__attribute__((section("_ftrace_events"))) event_##call = { \
+ .name = #call, \
+ .system = __stringify(TRACE_SYSTEM), \
+ .event = &ftrace_event_type_##call, \
+ .raw_init = ftrace_raw_init_event_##call, \
+ .regfunc = ftrace_raw_reg_event_##call, \
+ .unregfunc = ftrace_raw_unreg_event_##call, \
+ .show_format = ftrace_format_##call, \
+ .define_fields = ftrace_define_fields_##call, \
+ _TRACE_PROFILE_INIT(call) \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef _TRACE_PROFILE
+#undef _TRACE_PROFILE_INIT
+
+++ /dev/null
-#ifndef _TRACE_IRQ_H
-#define _TRACE_IRQ_H
-
-#include <linux/interrupt.h>
-#include <linux/tracepoint.h>
-
-#include <trace/irq_event_types.h>
-
-#endif
+++ /dev/null
-
-/* use <trace/irq.h> instead */
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM irq
-
-/*
- * Tracepoint for entry of interrupt handler:
- */
-TRACE_FORMAT(irq_handler_entry,
- TP_PROTO(int irq, struct irqaction *action),
- TP_ARGS(irq, action),
- TP_FMT("irq=%d handler=%s", irq, action->name)
- );
-
-/*
- * Tracepoint for return of an interrupt handler:
- */
-TRACE_EVENT(irq_handler_exit,
-
- TP_PROTO(int irq, struct irqaction *action, int ret),
-
- TP_ARGS(irq, action, ret),
-
- TP_STRUCT__entry(
- __field( int, irq )
- __field( int, ret )
- ),
-
- TP_fast_assign(
- __entry->irq = irq;
- __entry->ret = ret;
- ),
-
- TP_printk("irq=%d return=%s",
- __entry->irq, __entry->ret ? "handled" : "unhandled")
-);
-
-TRACE_FORMAT(softirq_entry,
- TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
- TP_ARGS(h, vec),
- TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
- );
-
-TRACE_FORMAT(softirq_exit,
- TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
- TP_ARGS(h, vec),
- TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
- );
-
-#undef TRACE_SYSTEM
+++ /dev/null
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <linux/tracepoint.h>
-#include <linux/types.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-DECLARE_TRACE(kmalloc,
- TP_PROTO(unsigned long call_site,
- const void *ptr,
- size_t bytes_req,
- size_t bytes_alloc,
- gfp_t gfp_flags),
- TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmem_cache_alloc,
- TP_PROTO(unsigned long call_site,
- const void *ptr,
- size_t bytes_req,
- size_t bytes_alloc,
- gfp_t gfp_flags),
- TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmalloc_node,
- TP_PROTO(unsigned long call_site,
- const void *ptr,
- size_t bytes_req,
- size_t bytes_alloc,
- gfp_t gfp_flags,
- int node),
- TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kmem_cache_alloc_node,
- TP_PROTO(unsigned long call_site,
- const void *ptr,
- size_t bytes_req,
- size_t bytes_alloc,
- gfp_t gfp_flags,
- int node),
- TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kfree,
- TP_PROTO(unsigned long call_site, const void *ptr),
- TP_ARGS(call_site, ptr));
-DECLARE_TRACE(kmem_cache_free,
- TP_PROTO(unsigned long call_site, const void *ptr),
- TP_ARGS(call_site, ptr));
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
+++ /dev/null
-#ifndef _TRACE_LOCKDEP_H
-#define _TRACE_LOCKDEP_H
-
-#include <linux/lockdep.h>
-#include <linux/tracepoint.h>
-
-#include <trace/lockdep_event_types.h>
-
-#endif
+++ /dev/null
-
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM lock
-
-#ifdef CONFIG_LOCKDEP
-
-TRACE_FORMAT(lock_acquire,
- TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
- int trylock, int read, int check,
- struct lockdep_map *next_lock, unsigned long ip),
- TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
- TP_FMT("%s%s%s", trylock ? "try " : "",
- read ? "read " : "", lock->name)
- );
-
-TRACE_FORMAT(lock_release,
- TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
- TP_ARGS(lock, nested, ip),
- TP_FMT("%s", lock->name)
- );
-
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_FORMAT(lock_contended,
- TP_PROTO(struct lockdep_map *lock, unsigned long ip),
- TP_ARGS(lock, ip),
- TP_FMT("%s", lock->name)
- );
-
-TRACE_FORMAT(lock_acquired,
- TP_PROTO(struct lockdep_map *lock, unsigned long ip),
- TP_ARGS(lock, ip),
- TP_FMT("%s", lock->name)
- );
-
-#endif
-#endif
-
-#undef TRACE_SYSTEM
+++ /dev/null
-#ifndef _TRACE_SCHED_H
-#define _TRACE_SCHED_H
-
-#include <linux/sched.h>
-#include <linux/tracepoint.h>
-
-#include <trace/sched_event_types.h>
-
-#endif
+++ /dev/null
-
-/* use <trace/sched.h> instead */
-#ifndef TRACE_EVENT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM sched
-
-/*
- * Tracepoint for calling kthread_stop, performed to end a kthread:
- */
-TRACE_EVENT(sched_kthread_stop,
-
- TP_PROTO(struct task_struct *t),
-
- TP_ARGS(t),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, t->comm, TASK_COMM_LEN);
- __entry->pid = t->pid;
- ),
-
- TP_printk("task %s:%d", __entry->comm, __entry->pid)
-);
-
-/*
- * Tracepoint for the return value of the kthread stopping:
- */
-TRACE_EVENT(sched_kthread_stop_ret,
-
- TP_PROTO(int ret),
-
- TP_ARGS(ret),
-
- TP_STRUCT__entry(
- __field( int, ret )
- ),
-
- TP_fast_assign(
- __entry->ret = ret;
- ),
-
- TP_printk("ret %d", __entry->ret)
-);
-
-/*
- * Tracepoint for waiting on task to unschedule:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- * but used by the latency tracer plugin. )
- */
-TRACE_EVENT(sched_wait_task,
-
- TP_PROTO(struct rq *rq, struct task_struct *p),
-
- TP_ARGS(rq, p),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, prio )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->prio = p->prio;
- ),
-
- TP_printk("task %s:%d [%d]",
- __entry->comm, __entry->pid, __entry->prio)
-);
-
-/*
- * Tracepoint for waking up a task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- * but used by the latency tracer plugin. )
- */
-TRACE_EVENT(sched_wakeup,
-
- TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-
- TP_ARGS(rq, p, success),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, prio )
- __field( int, success )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->prio = p->prio;
- __entry->success = success;
- ),
-
- TP_printk("task %s:%d [%d] success=%d",
- __entry->comm, __entry->pid, __entry->prio,
- __entry->success)
-);
-
-/*
- * Tracepoint for waking up a new task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- * but used by the latency tracer plugin. )
- */
-TRACE_EVENT(sched_wakeup_new,
-
- TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-
- TP_ARGS(rq, p, success),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, prio )
- __field( int, success )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->prio = p->prio;
- __entry->success = success;
- ),
-
- TP_printk("task %s:%d [%d] success=%d",
- __entry->comm, __entry->pid, __entry->prio,
- __entry->success)
-);
-
-/*
- * Tracepoint for task switches, performed by the scheduler:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- * but used by the latency tracer plugin. )
- */
-TRACE_EVENT(sched_switch,
-
- TP_PROTO(struct rq *rq, struct task_struct *prev,
- struct task_struct *next),
-
- TP_ARGS(rq, prev, next),
-
- TP_STRUCT__entry(
- __array( char, prev_comm, TASK_COMM_LEN )
- __field( pid_t, prev_pid )
- __field( int, prev_prio )
- __array( char, next_comm, TASK_COMM_LEN )
- __field( pid_t, next_pid )
- __field( int, next_prio )
- ),
-
- TP_fast_assign(
- memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
- __entry->prev_pid = prev->pid;
- __entry->prev_prio = prev->prio;
- memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
- __entry->next_pid = next->pid;
- __entry->next_prio = next->prio;
- ),
-
- TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
- __entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
- __entry->next_comm, __entry->next_pid, __entry->next_prio)
-);
-
-/*
- * Tracepoint for a task being migrated:
- */
-TRACE_EVENT(sched_migrate_task,
-
- TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
-
- TP_ARGS(p, orig_cpu, dest_cpu),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, prio )
- __field( int, orig_cpu )
- __field( int, dest_cpu )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->prio = p->prio;
- __entry->orig_cpu = orig_cpu;
- __entry->dest_cpu = dest_cpu;
- ),
-
- TP_printk("task %s:%d [%d] from: %d to: %d",
- __entry->comm, __entry->pid, __entry->prio,
- __entry->orig_cpu, __entry->dest_cpu)
-);
-
-/*
- * Tracepoint for freeing a task:
- */
-TRACE_EVENT(sched_process_free,
-
- TP_PROTO(struct task_struct *p),
-
- TP_ARGS(p),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, prio )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->prio = p->prio;
- ),
-
- TP_printk("task %s:%d [%d]",
- __entry->comm, __entry->pid, __entry->prio)
-);
-
-/*
- * Tracepoint for a task exiting:
- */
-TRACE_EVENT(sched_process_exit,
-
- TP_PROTO(struct task_struct *p),
-
- TP_ARGS(p),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, prio )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->prio = p->prio;
- ),
-
- TP_printk("task %s:%d [%d]",
- __entry->comm, __entry->pid, __entry->prio)
-);
-
-/*
- * Tracepoint for a waiting task:
- */
-TRACE_EVENT(sched_process_wait,
-
- TP_PROTO(struct pid *pid),
-
- TP_ARGS(pid),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, prio )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
- __entry->pid = pid_nr(pid);
- __entry->prio = current->prio;
- ),
-
- TP_printk("task %s:%d [%d]",
- __entry->comm, __entry->pid, __entry->prio)
-);
-
-/*
- * Tracepoint for do_fork:
- */
-TRACE_EVENT(sched_process_fork,
-
- TP_PROTO(struct task_struct *parent, struct task_struct *child),
-
- TP_ARGS(parent, child),
-
- TP_STRUCT__entry(
- __array( char, parent_comm, TASK_COMM_LEN )
- __field( pid_t, parent_pid )
- __array( char, child_comm, TASK_COMM_LEN )
- __field( pid_t, child_pid )
- ),
-
- TP_fast_assign(
- memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN);
- __entry->parent_pid = parent->pid;
- memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN);
- __entry->child_pid = child->pid;
- ),
-
- TP_printk("parent %s:%d child %s:%d",
- __entry->parent_comm, __entry->parent_pid,
- __entry->child_comm, __entry->child_pid)
-);
-
-/*
- * Tracepoint for sending a signal:
- */
-TRACE_EVENT(sched_signal_send,
-
- TP_PROTO(int sig, struct task_struct *p),
-
- TP_ARGS(sig, p),
-
- TP_STRUCT__entry(
- __field( int, sig )
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->sig = sig;
- ),
-
- TP_printk("sig: %d task %s:%d",
- __entry->sig, __entry->comm, __entry->pid)
-);
-
-#undef TRACE_SYSTEM
+++ /dev/null
-#ifndef _TRACE_SKB_H_
-#define _TRACE_SKB_H_
-
-#include <linux/skbuff.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(kfree_skb,
- TP_PROTO(struct sk_buff *skb, void *location),
- TP_ARGS(skb, location));
-
-#endif
+++ /dev/null
-/* trace/<type>_event_types.h here */
-
-#include <trace/sched_event_types.h>
-#include <trace/irq_event_types.h>
-#include <trace/lockdep_event_types.h>
+++ /dev/null
-/* trace/<type>.h here */
-
-#include <trace/sched.h>
-#include <trace/irq.h>
-#include <trace/lockdep.h>
+++ /dev/null
-#ifndef __TRACE_WORKQUEUE_H
-#define __TRACE_WORKQUEUE_H
-
-#include <linux/tracepoint.h>
-#include <linux/workqueue.h>
-#include <linux/sched.h>
-
-DECLARE_TRACE(workqueue_insertion,
- TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
- TP_ARGS(wq_thread, work));
-
-DECLARE_TRACE(workqueue_execution,
- TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
- TP_ARGS(wq_thread, work));
-
-/* Trace the creation of one workqueue thread on a cpu */
-DECLARE_TRACE(workqueue_creation,
- TP_PROTO(struct task_struct *wq_thread, int cpu),
- TP_ARGS(wq_thread, cpu));
-
-DECLARE_TRACE(workqueue_destruction,
- TP_PROTO(struct task_struct *wq_thread),
- TP_ARGS(wq_thread));
-
-#endif /* __TRACE_WORKQUEUE_H */
--- /dev/null
+header-y += evtchn.h
irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq(int irq);
+/* Determine the IRQ which is bound to an event channel */
+unsigned irq_from_evtchn(unsigned int evtchn);
+
#endif /* _XEN_EVENTS_H */
--- /dev/null
+/******************************************************************************
+ * evtchn.h
+ *
+ * Interface to /dev/xen/evtchn.
+ *
+ * Copyright (c) 2003-2005, K A Fraser
+ *
+ * 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; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __LINUX_PUBLIC_EVTCHN_H__
+#define __LINUX_PUBLIC_EVTCHN_H__
+
+/*
+ * Bind a fresh port to VIRQ @virq.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_VIRQ \
+ _IOC(_IOC_NONE, 'E', 0, sizeof(struct ioctl_evtchn_bind_virq))
+struct ioctl_evtchn_bind_virq {
+ unsigned int virq;
+};
+
+/*
+ * Bind a fresh port to remote <@remote_domain, @remote_port>.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_INTERDOMAIN \
+ _IOC(_IOC_NONE, 'E', 1, sizeof(struct ioctl_evtchn_bind_interdomain))
+struct ioctl_evtchn_bind_interdomain {
+ unsigned int remote_domain, remote_port;
+};
+
+/*
+ * Allocate a fresh port for binding to @remote_domain.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_UNBOUND_PORT \
+ _IOC(_IOC_NONE, 'E', 2, sizeof(struct ioctl_evtchn_bind_unbound_port))
+struct ioctl_evtchn_bind_unbound_port {
+ unsigned int remote_domain;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_UNBIND \
+ _IOC(_IOC_NONE, 'E', 3, sizeof(struct ioctl_evtchn_unbind))
+struct ioctl_evtchn_unbind {
+ unsigned int port;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_NOTIFY \
+ _IOC(_IOC_NONE, 'E', 4, sizeof(struct ioctl_evtchn_notify))
+struct ioctl_evtchn_notify {
+ unsigned int port;
+};
+
+/* Clear and reinitialise the event buffer. Clear error condition. */
+#define IOCTL_EVTCHN_RESET \
+ _IOC(_IOC_NONE, 'E', 5, 0)
+
+#endif /* __LINUX_PUBLIC_EVTCHN_H__ */
/* Declares the features reported by XENVER_get_features. */
#include "features.h"
+/* arg == NULL; returns host memory page size. */
+#define XENVER_pagesize 7
+
#endif /* __XEN_PUBLIC_VERSION_H__ */
void (*otherend_changed)(struct xenbus_device *dev,
enum xenbus_state backend_state);
int (*remove)(struct xenbus_device *dev);
- int (*suspend)(struct xenbus_device *dev);
- int (*suspend_cancel)(struct xenbus_device *dev);
+ int (*suspend)(struct xenbus_device *dev, pm_message_t state);
int (*resume)(struct xenbus_device *dev);
int (*uevent)(struct xenbus_device *, char **, int, char *, int);
struct device_driver driver;
choice
prompt "RCU Implementation"
- default CLASSIC_RCU
+ default TREE_RCU
config CLASSIC_RCU
bool "Classic RCU"
#include <linux/idr.h>
#include <linux/ftrace.h>
#include <linux/async.h>
+#include <linux/kmemtrace.h>
#include <trace/boot.h>
#include <asm/io.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
-#include <trace/kmemtrace.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/smp.h>
int i;
rcu_read_lock();
- un = list_entry(rcu_dereference(ulp->list_proc.next),
- struct sem_undo, list_proc);
+ un = list_entry_rcu(ulp->list_proc.next,
+ struct sem_undo, list_proc);
if (&un->list_proc == &ulp->list_proc)
semid = -1;
else
error = PTR_ERR(file);
if (IS_ERR(file))
goto no_file;
- ima_shm_check(file);
id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
if (id < 0) {
file = alloc_file(path.mnt, path.dentry, f_mode, &shm_file_operations);
if (!file)
goto out_free;
- ima_shm_check(file);
+ ima_counts_get(file);
file->private_data = sfd;
file->f_mapping = shp->shm_file->f_mapping;
obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
+obj-$(CONFIG_X86_DS) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
obj-$(CONFIG_SLOW_WORK) += slow-work.o
}
+asmlinkage long
+compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig,
+ struct compat_siginfo __user *uinfo)
+{
+ siginfo_t info;
+
+ if (copy_siginfo_from_user32(&info, uinfo))
+ return -EFAULT;
+ return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
+}
+
#ifdef __ARCH_WANT_COMPAT_SYS_TIME
/* compat_time_t is a 32 bit "long" and needs to get converted. */
/*
* Prepare credentials for current to perform an execve()
- * - The caller must hold current->cred_exec_mutex
+ * - The caller must hold current->cred_guard_mutex
*/
struct cred *prepare_exec_creds(void)
{
struct cred *new;
int ret;
- mutex_init(&p->cred_exec_mutex);
+ mutex_init(&p->cred_guard_mutex);
if (
#ifdef CONFIG_KEYS
#include <linux/tracehook.h>
#include <linux/fs_struct.h>
#include <linux/init_task.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/mmu_context.h>
#include "cred-internals.h"
-DEFINE_TRACE(sched_process_free);
-DEFINE_TRACE(sched_process_exit);
-DEFINE_TRACE(sched_process_wait);
-
static void exit_mm(struct task_struct * tsk);
static void __unhash_process(struct task_struct *p)
*/
if (*notask_error)
*notask_error = ret;
+ return 0;
}
if (likely(!ptrace) && unlikely(p->ptrace)) {
#include <linux/proc_fs.h>
#include <linux/blkdev.h>
#include <linux/fs_struct.h>
-#include <trace/sched.h>
#include <linux/magic.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
+#include <trace/events/sched.h>
+
/*
* Protected counters by write_lock_irq(&tasklist_lock)
*/
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
-DEFINE_TRACE(sched_process_fork);
-
int nr_processes(void)
{
int cpu;
if (!p)
goto fork_out;
+ ftrace_graph_init_task(p);
+
rt_mutex_init_task(p);
#ifdef CONFIG_PROVE_LOCKING
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
- if (unlikely(current->ptrace))
- ptrace_fork(p, clone_flags);
+
+ p->bts = NULL;
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
}
}
- ftrace_graph_init_task(p);
-
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
if (current->nsproxy != p->nsproxy) {
retval = ns_cgroup_clone(p, pid);
if (retval)
- goto bad_fork_free_graph;
+ goto bad_fork_free_pid;
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
- goto bad_fork_free_graph;
+ goto bad_fork_free_pid;
}
if (clone_flags & CLONE_THREAD) {
cgroup_post_fork(p);
return p;
-bad_fork_free_graph:
- ftrace_graph_exit_task(p);
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
* PRIVATE futexes by Eric Dumazet
* Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
*
+ * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
+ * Copyright (C) IBM Corporation, 2009
+ * Thanks to Thomas Gleixner for conceptual design and careful reviews.
+ *
* Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
* enough at me, Linus for the original (flawed) idea, Matthew
* Kirkwood for proof-of-concept implementation.
*/
struct futex_q {
struct plist_node list;
- /* There can only be a single waiter */
- wait_queue_head_t waiter;
+ /* Waiter reference */
+ struct task_struct *task;
/* Which hash list lock to use: */
spinlock_t *lock_ptr;
/* Optional priority inheritance state: */
struct futex_pi_state *pi_state;
- struct task_struct *task;
+
+ /* rt_waiter storage for requeue_pi: */
+ struct rt_mutex_waiter *rt_waiter;
/* Bitset for the optional bitmasked wakeup */
u32 bitset;
drop_futex_key_refs(key);
}
+/**
+ * futex_top_waiter() - Return the highest priority waiter on a futex
+ * @hb: the hash bucket the futex_q's reside in
+ * @key: the futex key (to distinguish it from other futex futex_q's)
+ *
+ * Must be called with the hb lock held.
+ */
+static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
+ union futex_key *key)
+{
+ struct futex_q *this;
+
+ plist_for_each_entry(this, &hb->chain, list) {
+ if (match_futex(&this->key, key))
+ return this;
+ }
+ return NULL;
+}
+
static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
{
u32 curval;
return 0;
}
+/**
+ * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * @uaddr: the pi futex user address
+ * @hb: the pi futex hash bucket
+ * @key: the futex key associated with uaddr and hb
+ * @ps: the pi_state pointer where we store the result of the
+ * lookup
+ * @task: the task to perform the atomic lock work for. This will
+ * be "current" except in the case of requeue pi.
+ * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Returns:
+ * 0 - ready to wait
+ * 1 - acquired the lock
+ * <0 - error
+ *
+ * The hb->lock and futex_key refs shall be held by the caller.
+ */
+static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
+ union futex_key *key,
+ struct futex_pi_state **ps,
+ struct task_struct *task, int set_waiters)
+{
+ int lock_taken, ret, ownerdied = 0;
+ u32 uval, newval, curval;
+
+retry:
+ ret = lock_taken = 0;
+
+ /*
+ * To avoid races, we attempt to take the lock here again
+ * (by doing a 0 -> TID atomic cmpxchg), while holding all
+ * the locks. It will most likely not succeed.
+ */
+ newval = task_pid_vnr(task);
+ if (set_waiters)
+ newval |= FUTEX_WAITERS;
+
+ curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
+
+ if (unlikely(curval == -EFAULT))
+ return -EFAULT;
+
+ /*
+ * Detect deadlocks.
+ */
+ if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+ return -EDEADLK;
+
+ /*
+ * Surprise - we got the lock. Just return to userspace:
+ */
+ if (unlikely(!curval))
+ return 1;
+
+ uval = curval;
+
+ /*
+ * Set the FUTEX_WAITERS flag, so the owner will know it has someone
+ * to wake at the next unlock.
+ */
+ newval = curval | FUTEX_WAITERS;
+
+ /*
+ * There are two cases, where a futex might have no owner (the
+ * owner TID is 0): OWNER_DIED. We take over the futex in this
+ * case. We also do an unconditional take over, when the owner
+ * of the futex died.
+ *
+ * This is safe as we are protected by the hash bucket lock !
+ */
+ if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
+ /* Keep the OWNER_DIED bit */
+ newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+ ownerdied = 0;
+ lock_taken = 1;
+ }
+
+ curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+
+ if (unlikely(curval == -EFAULT))
+ return -EFAULT;
+ if (unlikely(curval != uval))
+ goto retry;
+
+ /*
+ * We took the lock due to owner died take over.
+ */
+ if (unlikely(lock_taken))
+ return 1;
+
+ /*
+ * We dont have the lock. Look up the PI state (or create it if
+ * we are the first waiter):
+ */
+ ret = lookup_pi_state(uval, hb, key, ps);
+
+ if (unlikely(ret)) {
+ switch (ret) {
+ case -ESRCH:
+ /*
+ * No owner found for this futex. Check if the
+ * OWNER_DIED bit is set to figure out whether
+ * this is a robust futex or not.
+ */
+ if (get_futex_value_locked(&curval, uaddr))
+ return -EFAULT;
+
+ /*
+ * We simply start over in case of a robust
+ * futex. The code above will take the futex
+ * and return happy.
+ */
+ if (curval & FUTEX_OWNER_DIED) {
+ ownerdied = 1;
+ goto retry;
+ }
+ default:
+ break;
+ }
+ }
+
+ return ret;
+}
+
/*
* The hash bucket lock must be held when this is called.
* Afterwards, the futex_q must not be accessed.
*/
static void wake_futex(struct futex_q *q)
{
- plist_del(&q->list, &q->list.plist);
+ struct task_struct *p = q->task;
+
/*
- * The lock in wake_up_all() is a crucial memory barrier after the
- * plist_del() and also before assigning to q->lock_ptr.
+ * We set q->lock_ptr = NULL _before_ we wake up the task. If
+ * a non futex wake up happens on another CPU then the task
+ * might exit and p would dereference a non existing task
+ * struct. Prevent this by holding a reference on p across the
+ * wake up.
*/
- wake_up(&q->waiter);
+ get_task_struct(p);
+
+ plist_del(&q->list, &q->list.plist);
/*
- * The waiting task can free the futex_q as soon as this is written,
- * without taking any locks. This must come last.
- *
- * A memory barrier is required here to prevent the following store to
- * lock_ptr from getting ahead of the wakeup. Clearing the lock at the
- * end of wake_up() does not prevent this store from moving.
+ * The waiting task can free the futex_q as soon as
+ * q->lock_ptr = NULL is written, without taking any locks. A
+ * memory barrier is required here to prevent the following
+ * store to lock_ptr from getting ahead of the plist_del.
*/
smp_wmb();
q->lock_ptr = NULL;
+
+ wake_up_state(p, TASK_NORMAL);
+ put_task_struct(p);
}
static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
plist_for_each_entry_safe(this, next, head, list) {
if (match_futex (&this->key, &key)) {
- if (this->pi_state) {
+ if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
break;
}
return ret;
}
-/*
- * Requeue all waiters hashed on one physical page to another
- * physical page.
+/**
+ * requeue_futex() - Requeue a futex_q from one hb to another
+ * @q: the futex_q to requeue
+ * @hb1: the source hash_bucket
+ * @hb2: the target hash_bucket
+ * @key2: the new key for the requeued futex_q
+ */
+static inline
+void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
+ struct futex_hash_bucket *hb2, union futex_key *key2)
+{
+
+ /*
+ * If key1 and key2 hash to the same bucket, no need to
+ * requeue.
+ */
+ if (likely(&hb1->chain != &hb2->chain)) {
+ plist_del(&q->list, &hb1->chain);
+ plist_add(&q->list, &hb2->chain);
+ q->lock_ptr = &hb2->lock;
+#ifdef CONFIG_DEBUG_PI_LIST
+ q->list.plist.lock = &hb2->lock;
+#endif
+ }
+ get_futex_key_refs(key2);
+ q->key = *key2;
+}
+
+/**
+ * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
+ * q: the futex_q
+ * key: the key of the requeue target futex
+ *
+ * During futex_requeue, with requeue_pi=1, it is possible to acquire the
+ * target futex if it is uncontended or via a lock steal. Set the futex_q key
+ * to the requeue target futex so the waiter can detect the wakeup on the right
+ * futex, but remove it from the hb and NULL the rt_waiter so it can detect
+ * atomic lock acquisition. Must be called with the q->lock_ptr held.
+ */
+static inline
+void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
+{
+ drop_futex_key_refs(&q->key);
+ get_futex_key_refs(key);
+ q->key = *key;
+
+ WARN_ON(plist_node_empty(&q->list));
+ plist_del(&q->list, &q->list.plist);
+
+ WARN_ON(!q->rt_waiter);
+ q->rt_waiter = NULL;
+
+ wake_up_state(q->task, TASK_NORMAL);
+}
+
+/**
+ * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter
+ * @pifutex: the user address of the to futex
+ * @hb1: the from futex hash bucket, must be locked by the caller
+ * @hb2: the to futex hash bucket, must be locked by the caller
+ * @key1: the from futex key
+ * @key2: the to futex key
+ * @ps: address to store the pi_state pointer
+ * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Try and get the lock on behalf of the top waiter if we can do it atomically.
+ * Wake the top waiter if we succeed. If the caller specified set_waiters,
+ * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
+ * hb1 and hb2 must be held by the caller.
+ *
+ * Returns:
+ * 0 - failed to acquire the lock atomicly
+ * 1 - acquired the lock
+ * <0 - error
+ */
+static int futex_proxy_trylock_atomic(u32 __user *pifutex,
+ struct futex_hash_bucket *hb1,
+ struct futex_hash_bucket *hb2,
+ union futex_key *key1, union futex_key *key2,
+ struct futex_pi_state **ps, int set_waiters)
+{
+ struct futex_q *top_waiter = NULL;
+ u32 curval;
+ int ret;
+
+ if (get_futex_value_locked(&curval, pifutex))
+ return -EFAULT;
+
+ /*
+ * Find the top_waiter and determine if there are additional waiters.
+ * If the caller intends to requeue more than 1 waiter to pifutex,
+ * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now,
+ * as we have means to handle the possible fault. If not, don't set
+ * the bit unecessarily as it will force the subsequent unlock to enter
+ * the kernel.
+ */
+ top_waiter = futex_top_waiter(hb1, key1);
+
+ /* There are no waiters, nothing for us to do. */
+ if (!top_waiter)
+ return 0;
+
+ /*
+ * Try to take the lock for top_waiter. Set the FUTEX_WAITERS bit in
+ * the contended case or if set_waiters is 1. The pi_state is returned
+ * in ps in contended cases.
+ */
+ ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
+ set_waiters);
+ if (ret == 1)
+ requeue_pi_wake_futex(top_waiter, key2);
+
+ return ret;
+}
+
+/**
+ * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
+ * uaddr1: source futex user address
+ * uaddr2: target futex user address
+ * nr_wake: number of waiters to wake (must be 1 for requeue_pi)
+ * nr_requeue: number of waiters to requeue (0-INT_MAX)
+ * requeue_pi: if we are attempting to requeue from a non-pi futex to a
+ * pi futex (pi to pi requeue is not supported)
+ *
+ * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
+ * uaddr2 atomically on behalf of the top waiter.
+ *
+ * Returns:
+ * >=0 - on success, the number of tasks requeued or woken
+ * <0 - on error
*/
static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
- int nr_wake, int nr_requeue, u32 *cmpval)
+ int nr_wake, int nr_requeue, u32 *cmpval,
+ int requeue_pi)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
+ int drop_count = 0, task_count = 0, ret;
+ struct futex_pi_state *pi_state = NULL;
struct futex_hash_bucket *hb1, *hb2;
struct plist_head *head1;
struct futex_q *this, *next;
- int ret, drop_count = 0;
+ u32 curval2;
+
+ if (requeue_pi) {
+ /*
+ * requeue_pi requires a pi_state, try to allocate it now
+ * without any locks in case it fails.
+ */
+ if (refill_pi_state_cache())
+ return -ENOMEM;
+ /*
+ * requeue_pi must wake as many tasks as it can, up to nr_wake
+ * + nr_requeue, since it acquires the rt_mutex prior to
+ * returning to userspace, so as to not leave the rt_mutex with
+ * waiters and no owner. However, second and third wake-ups
+ * cannot be predicted as they involve race conditions with the
+ * first wake and a fault while looking up the pi_state. Both
+ * pthread_cond_signal() and pthread_cond_broadcast() should
+ * use nr_wake=1.
+ */
+ if (nr_wake != 1)
+ return -EINVAL;
+ }
retry:
+ if (pi_state != NULL) {
+ /*
+ * We will have to lookup the pi_state again, so free this one
+ * to keep the accounting correct.
+ */
+ free_pi_state(pi_state);
+ pi_state = NULL;
+ }
+
ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
if (unlikely(ret != 0))
goto out;
- ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_READ);
+ ret = get_futex_key(uaddr2, fshared, &key2,
+ requeue_pi ? VERIFY_WRITE : VERIFY_READ);
if (unlikely(ret != 0))
goto out_put_key1;
}
}
+ if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
+ /*
+ * Attempt to acquire uaddr2 and wake the top waiter. If we
+ * intend to requeue waiters, force setting the FUTEX_WAITERS
+ * bit. We force this here where we are able to easily handle
+ * faults rather in the requeue loop below.
+ */
+ ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
+ &key2, &pi_state, nr_requeue);
+
+ /*
+ * At this point the top_waiter has either taken uaddr2 or is
+ * waiting on it. If the former, then the pi_state will not
+ * exist yet, look it up one more time to ensure we have a
+ * reference to it.
+ */
+ if (ret == 1) {
+ WARN_ON(pi_state);
+ task_count++;
+ ret = get_futex_value_locked(&curval2, uaddr2);
+ if (!ret)
+ ret = lookup_pi_state(curval2, hb2, &key2,
+ &pi_state);
+ }
+
+ switch (ret) {
+ case 0:
+ break;
+ case -EFAULT:
+ double_unlock_hb(hb1, hb2);
+ put_futex_key(fshared, &key2);
+ put_futex_key(fshared, &key1);
+ ret = get_user(curval2, uaddr2);
+ if (!ret)
+ goto retry;
+ goto out;
+ case -EAGAIN:
+ /* The owner was exiting, try again. */
+ double_unlock_hb(hb1, hb2);
+ put_futex_key(fshared, &key2);
+ put_futex_key(fshared, &key1);
+ cond_resched();
+ goto retry;
+ default:
+ goto out_unlock;
+ }
+ }
+
head1 = &hb1->chain;
plist_for_each_entry_safe(this, next, head1, list) {
- if (!match_futex (&this->key, &key1))
+ if (task_count - nr_wake >= nr_requeue)
+ break;
+
+ if (!match_futex(&this->key, &key1))
continue;
- if (++ret <= nr_wake) {
+
+ WARN_ON(!requeue_pi && this->rt_waiter);
+ WARN_ON(requeue_pi && !this->rt_waiter);
+
+ /*
+ * Wake nr_wake waiters. For requeue_pi, if we acquired the
+ * lock, we already woke the top_waiter. If not, it will be
+ * woken by futex_unlock_pi().
+ */
+ if (++task_count <= nr_wake && !requeue_pi) {
wake_futex(this);
- } else {
- /*
- * If key1 and key2 hash to the same bucket, no need to
- * requeue.
- */
- if (likely(head1 != &hb2->chain)) {
- plist_del(&this->list, &hb1->chain);
- plist_add(&this->list, &hb2->chain);
- this->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
- this->list.plist.lock = &hb2->lock;
-#endif
- }
- this->key = key2;
- get_futex_key_refs(&key2);
- drop_count++;
+ continue;
+ }
- if (ret - nr_wake >= nr_requeue)
- break;
+ /*
+ * Requeue nr_requeue waiters and possibly one more in the case
+ * of requeue_pi if we couldn't acquire the lock atomically.
+ */
+ if (requeue_pi) {
+ /* Prepare the waiter to take the rt_mutex. */
+ atomic_inc(&pi_state->refcount);
+ this->pi_state = pi_state;
+ ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
+ this->rt_waiter,
+ this->task, 1);
+ if (ret == 1) {
+ /* We got the lock. */
+ requeue_pi_wake_futex(this, &key2);
+ continue;
+ } else if (ret) {
+ /* -EDEADLK */
+ this->pi_state = NULL;
+ free_pi_state(pi_state);
+ goto out_unlock;
+ }
}
+ requeue_futex(this, hb1, hb2, &key2);
+ drop_count++;
}
out_unlock:
out_put_key1:
put_futex_key(fshared, &key1);
out:
- return ret;
+ if (pi_state != NULL)
+ free_pi_state(pi_state);
+ return ret ? ret : task_count;
}
/* The key must be already stored in q->key. */
{
struct futex_hash_bucket *hb;
- init_waitqueue_head(&q->waiter);
-
get_futex_key_refs(&q->key);
hb = hash_futex(&q->key);
q->lock_ptr = &hb->lock;
*/
#define FLAGS_SHARED 0x01
#define FLAGS_CLOCKRT 0x02
+#define FLAGS_HAS_TIMEOUT 0x04
static long futex_wait_restart(struct restart_block *restart);
-static int futex_wait(u32 __user *uaddr, int fshared,
- u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+/**
+ * fixup_owner() - Post lock pi_state and corner case management
+ * @uaddr: user address of the futex
+ * @fshared: whether the futex is shared (1) or not (0)
+ * @q: futex_q (contains pi_state and access to the rt_mutex)
+ * @locked: if the attempt to take the rt_mutex succeeded (1) or not (0)
+ *
+ * After attempting to lock an rt_mutex, this function is called to cleanup
+ * the pi_state owner as well as handle race conditions that may allow us to
+ * acquire the lock. Must be called with the hb lock held.
+ *
+ * Returns:
+ * 1 - success, lock taken
+ * 0 - success, lock not taken
+ * <0 - on error (-EFAULT)
+ */
+static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
+ int locked)
{
- struct task_struct *curr = current;
- struct restart_block *restart;
- DECLARE_WAITQUEUE(wait, curr);
- struct futex_hash_bucket *hb;
- struct futex_q q;
- u32 uval;
- int ret;
- struct hrtimer_sleeper t;
- int rem = 0;
-
- if (!bitset)
- return -EINVAL;
+ struct task_struct *owner;
+ int ret = 0;
- q.pi_state = NULL;
- q.bitset = bitset;
-retry:
- q.key = FUTEX_KEY_INIT;
- ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_READ);
- if (unlikely(ret != 0))
+ if (locked) {
+ /*
+ * Got the lock. We might not be the anticipated owner if we
+ * did a lock-steal - fix up the PI-state in that case:
+ */
+ if (q->pi_state->owner != current)
+ ret = fixup_pi_state_owner(uaddr, q, current, fshared);
goto out;
+ }
-retry_private:
- hb = queue_lock(&q);
+ /*
+ * Catch the rare case, where the lock was released when we were on the
+ * way back before we locked the hash bucket.
+ */
+ if (q->pi_state->owner == current) {
+ /*
+ * Try to get the rt_mutex now. This might fail as some other
+ * task acquired the rt_mutex after we removed ourself from the
+ * rt_mutex waiters list.
+ */
+ if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
+ locked = 1;
+ goto out;
+ }
+
+ /*
+ * pi_state is incorrect, some other task did a lock steal and
+ * we returned due to timeout or signal without taking the
+ * rt_mutex. Too late. We can access the rt_mutex_owner without
+ * locking, as the other task is now blocked on the hash bucket
+ * lock. Fix the state up.
+ */
+ owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+ ret = fixup_pi_state_owner(uaddr, q, owner, fshared);
+ goto out;
+ }
/*
- * Access the page AFTER the hash-bucket is locked.
- * Order is important:
+ * Paranoia check. If we did not take the lock, then we should not be
+ * the owner, nor the pending owner, of the rt_mutex.
+ */
+ if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+ printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
+ "pi-state %p\n", ret,
+ q->pi_state->pi_mutex.owner,
+ q->pi_state->owner);
+
+out:
+ return ret ? ret : locked;
+}
+
+/**
+ * futex_wait_queue_me() - queue_me() and wait for wakeup, timeout, or signal
+ * @hb: the futex hash bucket, must be locked by the caller
+ * @q: the futex_q to queue up on
+ * @timeout: the prepared hrtimer_sleeper, or null for no timeout
+ */
+static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
+ struct hrtimer_sleeper *timeout)
+{
+ queue_me(q, hb);
+
+ /*
+ * There might have been scheduling since the queue_me(), as we
+ * cannot hold a spinlock across the get_user() in case it
+ * faults, and we cannot just set TASK_INTERRUPTIBLE state when
+ * queueing ourselves into the futex hash. This code thus has to
+ * rely on the futex_wake() code removing us from hash when it
+ * wakes us up.
+ */
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /* Arm the timer */
+ if (timeout) {
+ hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+ if (!hrtimer_active(&timeout->timer))
+ timeout->task = NULL;
+ }
+
+ /*
+ * !plist_node_empty() is safe here without any lock.
+ * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
+ */
+ if (likely(!plist_node_empty(&q->list))) {
+ /*
+ * If the timer has already expired, current will already be
+ * flagged for rescheduling. Only call schedule if there
+ * is no timeout, or if it has yet to expire.
+ */
+ if (!timeout || timeout->task)
+ schedule();
+ }
+ __set_current_state(TASK_RUNNING);
+}
+
+/**
+ * futex_wait_setup() - Prepare to wait on a futex
+ * @uaddr: the futex userspace address
+ * @val: the expected value
+ * @fshared: whether the futex is shared (1) or not (0)
+ * @q: the associated futex_q
+ * @hb: storage for hash_bucket pointer to be returned to caller
+ *
+ * Setup the futex_q and locate the hash_bucket. Get the futex value and
+ * compare it with the expected value. Handle atomic faults internally.
+ * Return with the hb lock held and a q.key reference on success, and unlocked
+ * with no q.key reference on failure.
+ *
+ * Returns:
+ * 0 - uaddr contains val and hb has been locked
+ * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked
+ */
+static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
+ struct futex_q *q, struct futex_hash_bucket **hb)
+{
+ u32 uval;
+ int ret;
+
+ /*
+ * Access the page AFTER the hash-bucket is locked.
+ * Order is important:
*
* Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val);
* Userspace waker: if (cond(var)) { var = new; futex_wake(&var); }
* A consequence is that futex_wait() can return zero and absorb
* a wakeup when *uaddr != val on entry to the syscall. This is
* rare, but normal.
- *
- * For shared futexes, we hold the mmap semaphore, so the mapping
- * cannot have changed since we looked it up in get_futex_key.
*/
+retry:
+ q->key = FUTEX_KEY_INIT;
+ ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ);
+ if (unlikely(ret != 0))
+ return ret;
+
+retry_private:
+ *hb = queue_lock(q);
+
ret = get_futex_value_locked(&uval, uaddr);
- if (unlikely(ret)) {
- queue_unlock(&q, hb);
+ if (ret) {
+ queue_unlock(q, *hb);
ret = get_user(uval, uaddr);
if (ret)
- goto out_put_key;
+ goto out;
if (!fshared)
goto retry_private;
- put_futex_key(fshared, &q.key);
+ put_futex_key(fshared, &q->key);
goto retry;
}
- ret = -EWOULDBLOCK;
- if (unlikely(uval != val)) {
- queue_unlock(&q, hb);
- goto out_put_key;
- }
- /* Only actually queue if *uaddr contained val. */
- queue_me(&q, hb);
+ if (uval != val) {
+ queue_unlock(q, *hb);
+ ret = -EWOULDBLOCK;
+ }
- /*
- * There might have been scheduling since the queue_me(), as we
- * cannot hold a spinlock across the get_user() in case it
- * faults, and we cannot just set TASK_INTERRUPTIBLE state when
- * queueing ourselves into the futex hash. This code thus has to
- * rely on the futex_wake() code removing us from hash when it
- * wakes us up.
- */
+out:
+ if (ret)
+ put_futex_key(fshared, &q->key);
+ return ret;
+}
- /* add_wait_queue is the barrier after __set_current_state. */
- __set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&q.waiter, &wait);
- /*
- * !plist_node_empty() is safe here without any lock.
- * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
- */
- if (likely(!plist_node_empty(&q.list))) {
- if (!abs_time)
- schedule();
- else {
- hrtimer_init_on_stack(&t.timer,
- clockrt ? CLOCK_REALTIME :
- CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS);
- hrtimer_init_sleeper(&t, current);
- hrtimer_set_expires_range_ns(&t.timer, *abs_time,
- current->timer_slack_ns);
-
- hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
- if (!hrtimer_active(&t.timer))
- t.task = NULL;
+static int futex_wait(u32 __user *uaddr, int fshared,
+ u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+{
+ struct hrtimer_sleeper timeout, *to = NULL;
+ struct restart_block *restart;
+ struct futex_hash_bucket *hb;
+ struct futex_q q;
+ int ret;
- /*
- * the timer could have already expired, in which
- * case current would be flagged for rescheduling.
- * Don't bother calling schedule.
- */
- if (likely(t.task))
- schedule();
+ if (!bitset)
+ return -EINVAL;
- hrtimer_cancel(&t.timer);
+ q.pi_state = NULL;
+ q.bitset = bitset;
+ q.rt_waiter = NULL;
- /* Flag if a timeout occured */
- rem = (t.task == NULL);
+ if (abs_time) {
+ to = &timeout;
- destroy_hrtimer_on_stack(&t.timer);
- }
+ hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
+ CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init_sleeper(to, current);
+ hrtimer_set_expires_range_ns(&to->timer, *abs_time,
+ current->timer_slack_ns);
}
- __set_current_state(TASK_RUNNING);
- /*
- * NOTE: we don't remove ourselves from the waitqueue because
- * we are the only user of it.
- */
+ /* Prepare to wait on uaddr. */
+ ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+ if (ret)
+ goto out;
+
+ /* queue_me and wait for wakeup, timeout, or a signal. */
+ futex_wait_queue_me(hb, &q, to);
/* If we were woken (and unqueued), we succeeded, whatever. */
ret = 0;
if (!unqueue_me(&q))
goto out_put_key;
ret = -ETIMEDOUT;
- if (rem)
+ if (to && !to->task)
goto out_put_key;
/*
restart->futex.val = val;
restart->futex.time = abs_time->tv64;
restart->futex.bitset = bitset;
- restart->futex.flags = 0;
+ restart->futex.flags = FLAGS_HAS_TIMEOUT;
if (fshared)
restart->futex.flags |= FLAGS_SHARED;
out_put_key:
put_futex_key(fshared, &q.key);
out:
+ if (to) {
+ hrtimer_cancel(&to->timer);
+ destroy_hrtimer_on_stack(&to->timer);
+ }
return ret;
}
{
u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
int fshared = 0;
- ktime_t t;
+ ktime_t t, *tp = NULL;
- t.tv64 = restart->futex.time;
+ if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
+ t.tv64 = restart->futex.time;
+ tp = &t;
+ }
restart->fn = do_no_restart_syscall;
if (restart->futex.flags & FLAGS_SHARED)
fshared = 1;
- return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
+ return (long)futex_wait(uaddr, fshared, restart->futex.val, tp,
restart->futex.bitset,
restart->futex.flags & FLAGS_CLOCKRT);
}
int detect, ktime_t *time, int trylock)
{
struct hrtimer_sleeper timeout, *to = NULL;
- struct task_struct *curr = current;
struct futex_hash_bucket *hb;
- u32 uval, newval, curval;
+ u32 uval;
struct futex_q q;
- int ret, lock_taken, ownerdied = 0;
+ int res, ret;
if (refill_pi_state_cache())
return -ENOMEM;
}
q.pi_state = NULL;
+ q.rt_waiter = NULL;
retry:
q.key = FUTEX_KEY_INIT;
ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE);
retry_private:
hb = queue_lock(&q);
-retry_locked:
- ret = lock_taken = 0;
-
- /*
- * To avoid races, we attempt to take the lock here again
- * (by doing a 0 -> TID atomic cmpxchg), while holding all
- * the locks. It will most likely not succeed.
- */
- newval = task_pid_vnr(current);
-
- curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
- if (unlikely(curval == -EFAULT))
- goto uaddr_faulted;
-
- /*
- * Detect deadlocks. In case of REQUEUE_PI this is a valid
- * situation and we return success to user space.
- */
- if (unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(current))) {
- ret = -EDEADLK;
- goto out_unlock_put_key;
- }
-
- /*
- * Surprise - we got the lock. Just return to userspace:
- */
- if (unlikely(!curval))
- goto out_unlock_put_key;
-
- uval = curval;
-
- /*
- * Set the WAITERS flag, so the owner will know it has someone
- * to wake at next unlock
- */
- newval = curval | FUTEX_WAITERS;
-
- /*
- * There are two cases, where a futex might have no owner (the
- * owner TID is 0): OWNER_DIED. We take over the futex in this
- * case. We also do an unconditional take over, when the owner
- * of the futex died.
- *
- * This is safe as we are protected by the hash bucket lock !
- */
- if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
- /* Keep the OWNER_DIED bit */
- newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(current);
- ownerdied = 0;
- lock_taken = 1;
- }
-
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (unlikely(curval == -EFAULT))
- goto uaddr_faulted;
- if (unlikely(curval != uval))
- goto retry_locked;
-
- /*
- * We took the lock due to owner died take over.
- */
- if (unlikely(lock_taken))
- goto out_unlock_put_key;
-
- /*
- * We dont have the lock. Look up the PI state (or create it if
- * we are the first waiter):
- */
- ret = lookup_pi_state(uval, hb, &q.key, &q.pi_state);
-
+ ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0);
if (unlikely(ret)) {
switch (ret) {
-
+ case 1:
+ /* We got the lock. */
+ ret = 0;
+ goto out_unlock_put_key;
+ case -EFAULT:
+ goto uaddr_faulted;
case -EAGAIN:
/*
* Task is exiting and we just wait for the
put_futex_key(fshared, &q.key);
cond_resched();
goto retry;
-
- case -ESRCH:
- /*
- * No owner found for this futex. Check if the
- * OWNER_DIED bit is set to figure out whether
- * this is a robust futex or not.
- */
- if (get_futex_value_locked(&curval, uaddr))
- goto uaddr_faulted;
-
- /*
- * We simply start over in case of a robust
- * futex. The code above will take the futex
- * and return happy.
- */
- if (curval & FUTEX_OWNER_DIED) {
- ownerdied = 1;
- goto retry_locked;
- }
default:
goto out_unlock_put_key;
}
}
spin_lock(q.lock_ptr);
-
- if (!ret) {
- /*
- * Got the lock. We might not be the anticipated owner
- * if we did a lock-steal - fix up the PI-state in
- * that case:
- */
- if (q.pi_state->owner != curr)
- ret = fixup_pi_state_owner(uaddr, &q, curr, fshared);
- } else {
- /*
- * Catch the rare case, where the lock was released
- * when we were on the way back before we locked the
- * hash bucket.
- */
- if (q.pi_state->owner == curr) {
- /*
- * Try to get the rt_mutex now. This might
- * fail as some other task acquired the
- * rt_mutex after we removed ourself from the
- * rt_mutex waiters list.
- */
- if (rt_mutex_trylock(&q.pi_state->pi_mutex))
- ret = 0;
- else {
- /*
- * pi_state is incorrect, some other
- * task did a lock steal and we
- * returned due to timeout or signal
- * without taking the rt_mutex. Too
- * late. We can access the
- * rt_mutex_owner without locking, as
- * the other task is now blocked on
- * the hash bucket lock. Fix the state
- * up.
- */
- struct task_struct *owner;
- int res;
-
- owner = rt_mutex_owner(&q.pi_state->pi_mutex);
- res = fixup_pi_state_owner(uaddr, &q, owner,
- fshared);
-
- /* propagate -EFAULT, if the fixup failed */
- if (res)
- ret = res;
- }
- } else {
- /*
- * Paranoia check. If we did not take the lock
- * in the trylock above, then we should not be
- * the owner of the rtmutex, neither the real
- * nor the pending one:
- */
- if (rt_mutex_owner(&q.pi_state->pi_mutex) == curr)
- printk(KERN_ERR "futex_lock_pi: ret = %d "
- "pi-mutex: %p pi-state %p\n", ret,
- q.pi_state->pi_mutex.owner,
- q.pi_state->owner);
- }
- }
+ /*
+ * Fixup the pi_state owner and possibly acquire the lock if we
+ * haven't already.
+ */
+ res = fixup_owner(uaddr, fshared, &q, !ret);
+ /*
+ * If fixup_owner() returned an error, proprogate that. If it acquired
+ * the lock, clear our -ETIMEDOUT or -EINTR.
+ */
+ if (res)
+ ret = (res < 0) ? res : 0;
/*
- * If fixup_pi_state_owner() faulted and was unable to handle the
- * fault, unlock it and return the fault to userspace.
+ * If fixup_owner() faulted and was unable to handle the fault, unlock
+ * it and return the fault to userspace.
*/
if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
rt_mutex_unlock(&q.pi_state->pi_mutex);
/* Unqueue and drop the lock */
unqueue_me_pi(&q);
- if (to)
- destroy_hrtimer_on_stack(&to->timer);
- return ret != -EINTR ? ret : -ERESTARTNOINTR;
+ goto out;
out_unlock_put_key:
queue_unlock(&q, hb);
out:
if (to)
destroy_hrtimer_on_stack(&to->timer);
- return ret;
+ return ret != -EINTR ? ret : -ERESTARTNOINTR;
uaddr_faulted:
/*
goto retry;
}
-
/*
* Userspace attempted a TID -> 0 atomic transition, and failed.
* This is the in-kernel slowpath: we look up the PI state (if any),
return ret;
}
+/**
+ * handle_early_requeue_pi_wakeup() - Detect early wakeup on the initial futex
+ * @hb: the hash_bucket futex_q was original enqueued on
+ * @q: the futex_q woken while waiting to be requeued
+ * @key2: the futex_key of the requeue target futex
+ * @timeout: the timeout associated with the wait (NULL if none)
+ *
+ * Detect if the task was woken on the initial futex as opposed to the requeue
+ * target futex. If so, determine if it was a timeout or a signal that caused
+ * the wakeup and return the appropriate error code to the caller. Must be
+ * called with the hb lock held.
+ *
+ * Returns
+ * 0 - no early wakeup detected
+ * <0 - -ETIMEDOUT or -ERESTARTNOINTR
+ */
+static inline
+int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
+ struct futex_q *q, union futex_key *key2,
+ struct hrtimer_sleeper *timeout)
+{
+ int ret = 0;
+
+ /*
+ * With the hb lock held, we avoid races while we process the wakeup.
+ * We only need to hold hb (and not hb2) to ensure atomicity as the
+ * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb.
+ * It can't be requeued from uaddr2 to something else since we don't
+ * support a PI aware source futex for requeue.
+ */
+ if (!match_futex(&q->key, key2)) {
+ WARN_ON(q->lock_ptr && (&hb->lock != q->lock_ptr));
+ /*
+ * We were woken prior to requeue by a timeout or a signal.
+ * Unqueue the futex_q and determine which it was.
+ */
+ plist_del(&q->list, &q->list.plist);
+ drop_futex_key_refs(&q->key);
+
+ if (timeout && !timeout->task)
+ ret = -ETIMEDOUT;
+ else
+ ret = -ERESTARTNOINTR;
+ }
+ return ret;
+}
+
+/**
+ * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
+ * @uaddr: the futex we initialyl wait on (non-pi)
+ * @fshared: whether the futexes are shared (1) or not (0). They must be
+ * the same type, no requeueing from private to shared, etc.
+ * @val: the expected value of uaddr
+ * @abs_time: absolute timeout
+ * @bitset: 32 bit wakeup bitset set by userspace, defaults to all.
+ * @clockrt: whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
+ * @uaddr2: the pi futex we will take prior to returning to user-space
+ *
+ * The caller will wait on uaddr and will be requeued by futex_requeue() to
+ * uaddr2 which must be PI aware. Normal wakeup will wake on uaddr2 and
+ * complete the acquisition of the rt_mutex prior to returning to userspace.
+ * This ensures the rt_mutex maintains an owner when it has waiters; without
+ * one, the pi logic wouldn't know which task to boost/deboost, if there was a
+ * need to.
+ *
+ * We call schedule in futex_wait_queue_me() when we enqueue and return there
+ * via the following:
+ * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
+ * 2) wakeup on uaddr2 after a requeue and subsequent unlock
+ * 3) signal (before or after requeue)
+ * 4) timeout (before or after requeue)
+ *
+ * If 3, we setup a restart_block with futex_wait_requeue_pi() as the function.
+ *
+ * If 2, we may then block on trying to take the rt_mutex and return via:
+ * 5) successful lock
+ * 6) signal
+ * 7) timeout
+ * 8) other lock acquisition failure
+ *
+ * If 6, we setup a restart_block with futex_lock_pi() as the function.
+ *
+ * If 4 or 7, we cleanup and return with -ETIMEDOUT.
+ *
+ * Returns:
+ * 0 - On success
+ * <0 - On error
+ */
+static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
+ u32 val, ktime_t *abs_time, u32 bitset,
+ int clockrt, u32 __user *uaddr2)
+{
+ struct hrtimer_sleeper timeout, *to = NULL;
+ struct rt_mutex_waiter rt_waiter;
+ struct rt_mutex *pi_mutex = NULL;
+ struct futex_hash_bucket *hb;
+ union futex_key key2;
+ struct futex_q q;
+ int res, ret;
+
+ if (!bitset)
+ return -EINVAL;
+
+ if (abs_time) {
+ to = &timeout;
+ hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
+ CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init_sleeper(to, current);
+ hrtimer_set_expires_range_ns(&to->timer, *abs_time,
+ current->timer_slack_ns);
+ }
+
+ /*
+ * The waiter is allocated on our stack, manipulated by the requeue
+ * code while we sleep on uaddr.
+ */
+ debug_rt_mutex_init_waiter(&rt_waiter);
+ rt_waiter.task = NULL;
+
+ q.pi_state = NULL;
+ q.bitset = bitset;
+ q.rt_waiter = &rt_waiter;
+
+ key2 = FUTEX_KEY_INIT;
+ ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
+ if (unlikely(ret != 0))
+ goto out;
+
+ /* Prepare to wait on uaddr. */
+ ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+ if (ret)
+ goto out_key2;
+
+ /* Queue the futex_q, drop the hb lock, wait for wakeup. */
+ futex_wait_queue_me(hb, &q, to);
+
+ spin_lock(&hb->lock);
+ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+ spin_unlock(&hb->lock);
+ if (ret)
+ goto out_put_keys;
+
+ /*
+ * In order for us to be here, we know our q.key == key2, and since
+ * we took the hb->lock above, we also know that futex_requeue() has
+ * completed and we no longer have to concern ourselves with a wakeup
+ * race with the atomic proxy lock acquition by the requeue code.
+ */
+
+ /* Check if the requeue code acquired the second futex for us. */
+ if (!q.rt_waiter) {
+ /*
+ * Got the lock. We might not be the anticipated owner if we
+ * did a lock-steal - fix up the PI-state in that case.
+ */
+ if (q.pi_state && (q.pi_state->owner != current)) {
+ spin_lock(q.lock_ptr);
+ ret = fixup_pi_state_owner(uaddr2, &q, current,
+ fshared);
+ spin_unlock(q.lock_ptr);
+ }
+ } else {
+ /*
+ * We have been woken up by futex_unlock_pi(), a timeout, or a
+ * signal. futex_unlock_pi() will not destroy the lock_ptr nor
+ * the pi_state.
+ */
+ WARN_ON(!&q.pi_state);
+ pi_mutex = &q.pi_state->pi_mutex;
+ ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+ debug_rt_mutex_free_waiter(&rt_waiter);
+
+ spin_lock(q.lock_ptr);
+ /*
+ * Fixup the pi_state owner and possibly acquire the lock if we
+ * haven't already.
+ */
+ res = fixup_owner(uaddr2, fshared, &q, !ret);
+ /*
+ * If fixup_owner() returned an error, proprogate that. If it
+ * acquired the lock, clear our -ETIMEDOUT or -EINTR.
+ */
+ if (res)
+ ret = (res < 0) ? res : 0;
+
+ /* Unqueue and drop the lock. */
+ unqueue_me_pi(&q);
+ }
+
+ /*
+ * If fixup_pi_state_owner() faulted and was unable to handle the
+ * fault, unlock the rt_mutex and return the fault to userspace.
+ */
+ if (ret == -EFAULT) {
+ if (rt_mutex_owner(pi_mutex) == current)
+ rt_mutex_unlock(pi_mutex);
+ } else if (ret == -EINTR) {
+ /*
+ * We've already been requeued, but we have no way to
+ * restart by calling futex_lock_pi() directly. We
+ * could restart the syscall, but that will look at
+ * the user space value and return right away. So we
+ * drop back with EWOULDBLOCK to tell user space that
+ * "val" has been changed. That's the same what the
+ * restart of the syscall would do in
+ * futex_wait_setup().
+ */
+ ret = -EWOULDBLOCK;
+ }
+
+out_put_keys:
+ put_futex_key(fshared, &q.key);
+out_key2:
+ put_futex_key(fshared, &key2);
+
+out:
+ if (to) {
+ hrtimer_cancel(&to->timer);
+ destroy_hrtimer_on_stack(&to->timer);
+ }
+ return ret;
+}
+
/*
* Support for robust futexes: the kernel cleans up held futexes at
* thread exit time.
fshared = 1;
clockrt = op & FUTEX_CLOCK_REALTIME;
- if (clockrt && cmd != FUTEX_WAIT_BITSET)
+ if (clockrt && cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
return -ENOSYS;
switch (cmd) {
ret = futex_wake(uaddr, fshared, val, val3);
break;
case FUTEX_REQUEUE:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL);
+ ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL, 0);
break;
case FUTEX_CMP_REQUEUE:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3);
+ ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
+ 0);
break;
case FUTEX_WAKE_OP:
ret = futex_wake_op(uaddr, fshared, uaddr2, val, val2, val3);
if (futex_cmpxchg_enabled)
ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1);
break;
+ case FUTEX_WAIT_REQUEUE_PI:
+ val3 = FUTEX_BITSET_MATCH_ANY;
+ ret = futex_wait_requeue_pi(uaddr, fshared, val, timeout, val3,
+ clockrt, uaddr2);
+ break;
+ case FUTEX_CMP_REQUEUE_PI:
+ ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
+ 1);
+ break;
default:
ret = -ENOSYS;
}
int cmd = op & FUTEX_CMD_MASK;
if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
- cmd == FUTEX_WAIT_BITSET)) {
+ cmd == FUTEX_WAIT_BITSET ||
+ cmd == FUTEX_WAIT_REQUEUE_PI)) {
if (copy_from_user(&ts, utime, sizeof(ts)) != 0)
return -EFAULT;
if (!timespec_valid(&ts))
tp = &t;
}
/*
- * requeue parameter in 'utime' if cmd == FUTEX_REQUEUE.
+ * requeue parameter in 'utime' if cmd == FUTEX_*_REQUEUE_*.
* number of waiters to wake in 'utime' if cmd == FUTEX_WAKE_OP.
*/
if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
- cmd == FUTEX_WAKE_OP)
+ cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
val2 = (u32) (unsigned long) utime;
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
-obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o
+obj-$(CONFIG_NUMA_IRQ_DESC) += numa_migrate.o
obj-$(CONFIG_PM_SLEEP) += pm.o
spin_lock(&desc->lock);
mask_ack_irq(desc, irq);
- desc = irq_remap_to_desc(irq, desc);
if (unlikely(desc->status & IRQ_INPROGRESS))
goto out_unlock;
desc->status &= ~IRQ_INPROGRESS;
out:
desc->chip->eoi(irq);
- desc = irq_remap_to_desc(irq, desc);
spin_unlock(&desc->lock);
}
!desc->action)) {
desc->status |= (IRQ_PENDING | IRQ_MASKED);
mask_ack_irq(desc, irq);
- desc = irq_remap_to_desc(irq, desc);
goto out_unlock;
}
kstat_incr_irqs_this_cpu(irq, desc);
/* Start handling the irq */
if (desc->chip->ack)
desc->chip->ack(irq);
- desc = irq_remap_to_desc(irq, desc);
/* Mark the IRQ currently in progress.*/
desc->status |= IRQ_INPROGRESS;
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
- if (desc->chip->eoi) {
+ if (desc->chip->eoi)
desc->chip->eoi(irq);
- desc = irq_remap_to_desc(irq, desc);
- }
}
void
/* Uninstall? */
if (handle == handle_bad_irq) {
- if (desc->chip != &no_irq_chip) {
+ if (desc->chip != &no_irq_chip)
mask_ack_irq(desc, irq);
- desc = irq_remap_to_desc(irq, desc);
- }
desc->status |= IRQ_DISABLED;
desc->depth = 1;
}
*/
#include <linux/irq.h>
+#include <linux/slab.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/rculist.h>
#include <linux/hash.h>
-#include <trace/irq.h>
#include <linux/bootmem.h>
+#include <trace/events/irq.h>
#include "internals.h"
.lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
};
-void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
+void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
{
- int node;
void *ptr;
- node = cpu_to_node(cpu);
- ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), GFP_ATOMIC, node);
+ if (slab_is_available())
+ ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
+ GFP_ATOMIC, node);
+ else
+ ptr = alloc_bootmem_node(NODE_DATA(node),
+ nr * sizeof(*desc->kstat_irqs));
/*
* don't overwite if can not get new one
* init_copy_kstat_irqs() could still use old one
*/
if (ptr) {
- printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n",
- cpu, node);
+ printk(KERN_DEBUG " alloc kstat_irqs on node %d\n", node);
desc->kstat_irqs = ptr;
}
}
-static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
+static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
{
memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
spin_lock_init(&desc->lock);
desc->irq = irq;
#ifdef CONFIG_SMP
- desc->cpu = cpu;
+ desc->node = node;
#endif
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
- init_kstat_irqs(desc, cpu, nr_cpu_ids);
+ init_kstat_irqs(desc, node, nr_cpu_ids);
if (!desc->kstat_irqs) {
printk(KERN_ERR "can not alloc kstat_irqs\n");
BUG_ON(1);
}
- if (!init_alloc_desc_masks(desc, cpu, false)) {
+ if (!alloc_desc_masks(desc, node, false)) {
printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
BUG_ON(1);
}
- arch_init_chip_data(desc, cpu);
+ init_desc_masks(desc);
+ arch_init_chip_data(desc, node);
}
/*
desc[i].irq = i;
desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
- init_alloc_desc_masks(&desc[i], 0, true);
+ alloc_desc_masks(&desc[i], 0, true);
+ init_desc_masks(&desc[i]);
irq_desc_ptrs[i] = desc + i;
}
return NULL;
}
-struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
{
struct irq_desc *desc;
unsigned long flags;
- int node;
if (irq >= nr_irqs) {
WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
if (desc)
goto out_unlock;
- node = cpu_to_node(cpu);
- desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
- printk(KERN_DEBUG " alloc irq_desc for %d on cpu %d node %d\n",
- irq, cpu, node);
+ if (slab_is_available())
+ desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
+ else
+ desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc));
+
+ printk(KERN_DEBUG " alloc irq_desc for %d on node %d\n", irq, node);
if (!desc) {
printk(KERN_ERR "can not alloc irq_desc\n");
BUG_ON(1);
}
- init_one_irq_desc(irq, desc, cpu);
+ init_one_irq_desc(irq, desc, node);
irq_desc_ptrs[irq] = desc;
for (i = 0; i < count; i++) {
desc[i].irq = i;
- init_alloc_desc_masks(&desc[i], 0, true);
+ alloc_desc_masks(&desc[i], 0, true);
+ init_desc_masks(&desc[i]);
desc[i].kstat_irqs = kstat_irqs_all[i];
}
return arch_early_irq_init();
return (irq < NR_IRQS) ? irq_desc + irq : NULL;
}
-struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
{
return irq_to_desc(irq);
}
"but no thread function available.", irq, action->name);
}
-DEFINE_TRACE(irq_handler_entry);
-DEFINE_TRACE(irq_handler_exit);
-
/**
* handle_IRQ_event - irq action chain handler
* @irq: the interrupt number
/*
* No locking required for CPU-local interrupts:
*/
- if (desc->chip->ack) {
+ if (desc->chip->ack)
desc->chip->ack(irq);
- /* get new one */
- desc = irq_remap_to_desc(irq, desc);
- }
if (likely(!(desc->status & IRQ_DISABLED))) {
action_ret = handle_IRQ_event(irq, desc->action);
if (!noirqdebug)
}
spin_lock(&desc->lock);
- if (desc->chip->ack) {
+ if (desc->chip->ack)
desc->chip->ack(irq);
- desc = irq_remap_to_desc(irq, desc);
- }
/*
* REPLAY is when Linux resends an IRQ that was dropped earlier
* WAITING is used by probe to mark irqs that are being tested
extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
extern struct lock_class_key irq_desc_lock_class;
-extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
+extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
extern void clear_kstat_irqs(struct irq_desc *desc);
extern spinlock_t sparse_irq_lock;
extern int irq_select_affinity_usr(unsigned int irq);
+extern void
+irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask);
+
/*
* Debugging printout:
*/
return 1;
}
-static void
+void
irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
{
struct irqaction *action = desc->action;
spin_lock_irqsave(&desc->lock, flags);
#ifdef CONFIG_GENERIC_PENDING_IRQ
- if (desc->status & IRQ_MOVE_PCNTXT)
- desc->chip->set_affinity(irq, cpumask);
+ if (desc->status & IRQ_MOVE_PCNTXT) {
+ if (!desc->chip->set_affinity(irq, cpumask)) {
+ cpumask_copy(desc->affinity, cpumask);
+ irq_set_thread_affinity(desc, cpumask);
+ }
+ }
else {
desc->status |= IRQ_MOVE_PENDING;
cpumask_copy(desc->pending_mask, cpumask);
}
#else
- cpumask_copy(desc->affinity, cpumask);
- desc->chip->set_affinity(irq, cpumask);
+ if (!desc->chip->set_affinity(irq, cpumask)) {
+ cpumask_copy(desc->affinity, cpumask);
+ irq_set_thread_affinity(desc, cpumask);
+ }
#endif
- irq_set_thread_affinity(desc, cpumask);
desc->status |= IRQ_AFFINITY_SET;
spin_unlock_irqrestore(&desc->lock, flags);
return 0;
#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include "internals.h"
void move_masked_irq(int irq)
{
* masking the irqs.
*/
if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
- < nr_cpu_ids)) {
- cpumask_and(desc->affinity,
- desc->pending_mask, cpu_online_mask);
- desc->chip->set_affinity(irq, desc->affinity);
- }
+ < nr_cpu_ids))
+ if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
+ cpumask_copy(desc->affinity, desc->pending_mask);
+ irq_set_thread_affinity(desc, desc->pending_mask);
+ }
+
cpumask_clear(desc->pending_mask);
}
static void init_copy_kstat_irqs(struct irq_desc *old_desc,
struct irq_desc *desc,
- int cpu, int nr)
+ int node, int nr)
{
- init_kstat_irqs(desc, cpu, nr);
+ init_kstat_irqs(desc, node, nr);
if (desc->kstat_irqs != old_desc->kstat_irqs)
memcpy(desc->kstat_irqs, old_desc->kstat_irqs,
}
static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
- struct irq_desc *desc, int cpu)
+ struct irq_desc *desc, int node)
{
memcpy(desc, old_desc, sizeof(struct irq_desc));
- if (!init_alloc_desc_masks(desc, cpu, false)) {
+ if (!alloc_desc_masks(desc, node, false)) {
printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
"for migration.\n", irq);
return false;
}
spin_lock_init(&desc->lock);
- desc->cpu = cpu;
+ desc->node = node;
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
- init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+ init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
init_copy_desc_masks(old_desc, desc);
- arch_init_copy_chip_data(old_desc, desc, cpu);
+ arch_init_copy_chip_data(old_desc, desc, node);
return true;
}
}
static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
- int cpu)
+ int node)
{
struct irq_desc *desc;
unsigned int irq;
unsigned long flags;
- int node;
irq = old_desc->irq;
if (desc && old_desc != desc)
goto out_unlock;
- node = cpu_to_node(cpu);
desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
if (!desc) {
printk(KERN_ERR "irq %d: can not get new irq_desc "
desc = old_desc;
goto out_unlock;
}
- if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
+ if (!init_copy_one_irq_desc(irq, old_desc, desc, node)) {
/* still use old one */
kfree(desc);
desc = old_desc;
/* free the old one */
free_one_irq_desc(old_desc, desc);
- spin_unlock(&old_desc->lock);
kfree(old_desc);
- spin_lock(&desc->lock);
return desc;
return desc;
}
-struct irq_desc *move_irq_desc(struct irq_desc *desc, int cpu)
+struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
{
- int old_cpu;
- int node, old_node;
-
/* those all static, do move them */
if (desc->irq < NR_IRQS_LEGACY)
return desc;
- old_cpu = desc->cpu;
- if (old_cpu != cpu) {
- node = cpu_to_node(cpu);
- old_node = cpu_to_node(old_cpu);
- if (old_node != node)
- desc = __real_move_irq_desc(desc, cpu);
- else
- desc->cpu = cpu;
- }
+ if (desc->node != node)
+ desc = __real_move_irq_desc(desc, node);
return desc;
}
#include <linux/file.h>
#include <linux/module.h>
#include <linux/mutex.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#define KTHREAD_NICE_LEVEL (-5)
static LIST_HEAD(kthread_create_list);
struct task_struct *kthreadd_task;
-DEFINE_TRACE(sched_kthread_stop);
-DEFINE_TRACE(sched_kthread_stop_ret);
-
struct kthread_create_info
{
/* Information passed to kthread() from kthreadd. */
#include <linux/hash.h>
#include <linux/ftrace.h>
#include <linux/stringify.h>
-#include <trace/lockdep.h>
#include <asm/sections.h>
#include "lockdep_internals.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/lockdep.h>
+
#ifdef CONFIG_PROVE_LOCKING
int prove_locking = 1;
module_param(prove_locking, int, 0644);
}
EXPORT_SYMBOL_GPL(lock_set_class);
-DEFINE_TRACE(lock_acquire);
-
/*
* We are not always called with irqs disabled - do that here,
* and also avoid lockdep recursion:
}
EXPORT_SYMBOL_GPL(lock_acquire);
-DEFINE_TRACE(lock_release);
-
void lock_release(struct lockdep_map *lock, int nested,
unsigned long ip)
{
hlock->holdtime_stamp = now;
}
+ trace_lock_acquired(lock, ip, waittime);
+
stats = get_lock_stats(hlock_class(hlock));
if (waittime) {
if (hlock->read)
lock->ip = ip;
}
-DEFINE_TRACE(lock_contended);
-
void lock_contended(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
}
EXPORT_SYMBOL_GPL(lock_contended);
-DEFINE_TRACE(lock_acquired);
-
void lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
- trace_lock_acquired(lock, ip);
-
if (unlikely(!lock_stat))
return;
*/
#include <linux/module.h>
#include <linux/moduleloader.h>
+#include <linux/ftrace_event.h>
#include <linux/init.h>
#include <linux/kallsyms.h>
#include <linux/fs.h>
EXPORT_SYMBOL_GPL(module_mutex);
static LIST_HEAD(modules);
+/* Block module loading/unloading? */
+int modules_disabled = 0;
+
/* Waiting for a module to finish initializing? */
static DECLARE_WAIT_QUEUE_HEAD(module_wq);
char name[MODULE_NAME_LEN];
int ret, forced = 0;
- if (!capable(CAP_SYS_MODULE))
+ if (!capable(CAP_SYS_MODULE) || modules_disabled)
return -EPERM;
if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0)
/* Free any allocated parameters. */
destroy_params(mod->kp, mod->num_kp);
- /* release any pointers to mcount in this module */
- ftrace_release(mod->module_core, mod->core_size);
-
/* This may be NULL, but that's OK */
module_free(mod, mod->module_init);
kfree(mod->args);
unsigned int symindex = 0;
unsigned int strindex = 0;
unsigned int modindex, versindex, infoindex, pcpuindex;
- unsigned int num_mcount;
struct module *mod;
long err = 0;
void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
- unsigned long *mseg;
mm_segment_t old_fs;
DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
sizeof(*mod->tracepoints),
&mod->num_tracepoints);
#endif
-
+#ifdef CONFIG_EVENT_TRACING
+ mod->trace_events = section_objs(hdr, sechdrs, secstrings,
+ "_ftrace_events",
+ sizeof(*mod->trace_events),
+ &mod->num_trace_events);
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+ /* sechdrs[0].sh_size is always zero */
+ mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings,
+ "__mcount_loc",
+ sizeof(*mod->ftrace_callsites),
+ &mod->num_ftrace_callsites);
+#endif
#ifdef CONFIG_MODVERSIONS
if ((mod->num_syms && !mod->crcs)
|| (mod->num_gpl_syms && !mod->gpl_crcs)
dynamic_debug_setup(debug, num_debug);
}
- /* sechdrs[0].sh_size is always zero */
- mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
- sizeof(*mseg), &num_mcount);
- ftrace_init_module(mod, mseg, mseg + num_mcount);
-
err = module_finalize(hdr, sechdrs, mod);
if (err < 0)
goto cleanup;
cleanup:
kobject_del(&mod->mkobj.kobj);
kobject_put(&mod->mkobj.kobj);
- ftrace_release(mod->module_core, mod->core_size);
free_unload:
module_unload_free(mod);
#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
int ret = 0;
/* Must have permission */
- if (!capable(CAP_SYS_MODULE))
+ if (!capable(CAP_SYS_MODULE) || modules_disabled)
return -EPERM;
/* Only one module load at a time, please */
/* didnt get the lock, go to sleep: */
spin_unlock_mutex(&lock->wait_lock, flags);
- __schedule();
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
spin_lock_mutex(&lock->wait_lock, flags);
}
return ret;
}
-
EXPORT_SYMBOL(mutex_trylock);
+
+/**
+ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
+ * @cnt: the atomic which we are to dec
+ * @lock: the mutex to return holding if we dec to 0
+ *
+ * return true and hold lock if we dec to 0, return false otherwise
+ */
+int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
+{
+ /* dec if we can't possibly hit 0 */
+ if (atomic_add_unless(cnt, -1, 1))
+ return 0;
+ /* we might hit 0, so take the lock */
+ mutex_lock(lock);
+ if (!atomic_dec_and_test(cnt)) {
+ /* when we actually did the dec, we didn't hit 0 */
+ mutex_unlock(lock);
+ return 0;
+ }
+ /* we hit 0, and we hold the lock */
+ return 1;
+}
+EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
#include <linux/uaccess.h>
-/*
- * Initialize a new task whose father had been ptraced.
- *
- * Called from copy_process().
- */
-void ptrace_fork(struct task_struct *child, unsigned long clone_flags)
-{
- arch_ptrace_fork(child, clone_flags);
-}
-
/*
* ptrace a task: make the debugger its new parent and
* move it to the ptrace list.
if (same_thread_group(task, current))
goto out;
- /* Protect exec's credential calculations against our interference;
- * SUID, SGID and LSM creds get determined differently under ptrace.
+ /* Protect the target's credential calculations against our
+ * interference; SUID, SGID and LSM creds get determined differently
+ * under ptrace.
*/
- retval = mutex_lock_interruptible(&task->cred_exec_mutex);
+ retval = mutex_lock_interruptible(&task->cred_guard_mutex);
if (retval < 0)
goto out;
bad:
write_unlock_irqrestore(&tasklist_lock, flags);
task_unlock(task);
- mutex_unlock(&task->cred_exec_mutex);
+ mutex_unlock(&task->cred_guard_mutex);
out:
return retval;
}
rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
- ret = 0;
+ ret = 0; /* unused */
__wait_event_interruptible(rcu_ctrlblk.sched_wq,
rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
ret);
- /*
- * Signals would prevent us from sleeping, and we cannot
- * do much with them in any case. So flush them.
- */
- if (ret)
- flush_signals(current);
couldsleepnext = 0;
} while (!kthread_should_stop());
check_cpu_stall(rsp, rdp);
/* Is the RCU core waiting for a quiescent state from this CPU? */
- if (rdp->qs_pending)
+ if (rdp->qs_pending) {
+ rdp->n_rp_qs_pending++;
return 1;
+ }
/* Does this CPU have callbacks ready to invoke? */
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (cpu_has_callbacks_ready_to_invoke(rdp)) {
+ rdp->n_rp_cb_ready++;
return 1;
+ }
/* Has RCU gone idle with this CPU needing another grace period? */
- if (cpu_needs_another_gp(rsp, rdp))
+ if (cpu_needs_another_gp(rsp, rdp)) {
+ rdp->n_rp_cpu_needs_gp++;
return 1;
+ }
/* Has another RCU grace period completed? */
- if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */
+ if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */
+ rdp->n_rp_gp_completed++;
return 1;
+ }
/* Has a new RCU grace period started? */
- if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */
+ if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */
+ rdp->n_rp_gp_started++;
return 1;
+ }
/* Has an RCU GP gone long enough to send resched IPIs &c? */
if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
- ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0))
+ ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) {
+ rdp->n_rp_need_fqs++;
return 1;
+ }
/* nothing to do */
+ rdp->n_rp_need_nothing++;
return 0;
}
.release = single_release,
};
-static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir;
+static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
+{
+ seq_printf(m, "%3d%cnp=%ld "
+ "qsp=%ld cbr=%ld cng=%ld gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+ rdp->cpu,
+ cpu_is_offline(rdp->cpu) ? '!' : ' ',
+ rdp->n_rcu_pending,
+ rdp->n_rp_qs_pending,
+ rdp->n_rp_cb_ready,
+ rdp->n_rp_cpu_needs_gp,
+ rdp->n_rp_gp_completed,
+ rdp->n_rp_gp_started,
+ rdp->n_rp_need_fqs,
+ rdp->n_rp_need_nothing);
+}
+
+static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp)
+{
+ int cpu;
+ struct rcu_data *rdp;
+
+ for_each_possible_cpu(cpu) {
+ rdp = rsp->rda[cpu];
+ if (rdp->beenonline)
+ print_one_rcu_pending(m, rdp);
+ }
+}
+
+static int show_rcu_pending(struct seq_file *m, void *unused)
+{
+ seq_puts(m, "rcu:\n");
+ print_rcu_pendings(m, &rcu_state);
+ seq_puts(m, "rcu_bh:\n");
+ print_rcu_pendings(m, &rcu_bh_state);
+ return 0;
+}
+
+static int rcu_pending_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, show_rcu_pending, NULL);
+}
+
+static struct file_operations rcu_pending_fops = {
+ .owner = THIS_MODULE,
+ .open = rcu_pending_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *rcudir;
+static struct dentry *datadir;
+static struct dentry *datadir_csv;
+static struct dentry *gpdir;
+static struct dentry *hierdir;
+static struct dentry *rcu_pendingdir;
+
static int __init rcuclassic_trace_init(void)
{
rcudir = debugfs_create_dir("rcu", NULL);
NULL, &rcuhier_fops);
if (!hierdir)
goto free_out;
+
+ rcu_pendingdir = debugfs_create_file("rcu_pending", 0444, rcudir,
+ NULL, &rcu_pending_fops);
+ if (!rcu_pendingdir)
+ goto free_out;
return 0;
free_out:
if (datadir)
debugfs_remove(datadir_csv);
debugfs_remove(gpdir);
debugfs_remove(hierdir);
+ debugfs_remove(rcu_pendingdir);
debugfs_remove(rcudir);
}
* assigned pending owner [which might not have taken the
* lock yet]:
*/
-static inline int try_to_steal_lock(struct rt_mutex *lock)
+static inline int try_to_steal_lock(struct rt_mutex *lock,
+ struct task_struct *task)
{
struct task_struct *pendowner = rt_mutex_owner(lock);
struct rt_mutex_waiter *next;
if (!rt_mutex_owner_pending(lock))
return 0;
- if (pendowner == current)
+ if (pendowner == task)
return 1;
spin_lock_irqsave(&pendowner->pi_lock, flags);
- if (current->prio >= pendowner->prio) {
+ if (task->prio >= pendowner->prio) {
spin_unlock_irqrestore(&pendowner->pi_lock, flags);
return 0;
}
* We are going to steal the lock and a waiter was
* enqueued on the pending owners pi_waiters queue. So
* we have to enqueue this waiter into
- * current->pi_waiters list. This covers the case,
- * where current is boosted because it holds another
+ * task->pi_waiters list. This covers the case,
+ * where task is boosted because it holds another
* lock and gets unboosted because the booster is
* interrupted, so we would delay a waiter with higher
- * priority as current->normal_prio.
+ * priority as task->normal_prio.
*
* Note: in the rare case of a SCHED_OTHER task changing
* its priority and thus stealing the lock, next->task
- * might be current:
+ * might be task:
*/
- if (likely(next->task != current)) {
- spin_lock_irqsave(¤t->pi_lock, flags);
- plist_add(&next->pi_list_entry, ¤t->pi_waiters);
- __rt_mutex_adjust_prio(current);
- spin_unlock_irqrestore(¤t->pi_lock, flags);
+ if (likely(next->task != task)) {
+ spin_lock_irqsave(&task->pi_lock, flags);
+ plist_add(&next->pi_list_entry, &task->pi_waiters);
+ __rt_mutex_adjust_prio(task);
+ spin_unlock_irqrestore(&task->pi_lock, flags);
}
return 1;
}
*/
mark_rt_mutex_waiters(lock);
- if (rt_mutex_owner(lock) && !try_to_steal_lock(lock))
+ if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
return 0;
/* We got the lock. */
*/
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
+ struct task_struct *task,
int detect_deadlock)
{
struct task_struct *owner = rt_mutex_owner(lock);
unsigned long flags;
int chain_walk = 0, res;
- spin_lock_irqsave(¤t->pi_lock, flags);
- __rt_mutex_adjust_prio(current);
- waiter->task = current;
+ spin_lock_irqsave(&task->pi_lock, flags);
+ __rt_mutex_adjust_prio(task);
+ waiter->task = task;
waiter->lock = lock;
- plist_node_init(&waiter->list_entry, current->prio);
- plist_node_init(&waiter->pi_list_entry, current->prio);
+ plist_node_init(&waiter->list_entry, task->prio);
+ plist_node_init(&waiter->pi_list_entry, task->prio);
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
top_waiter = rt_mutex_top_waiter(lock);
plist_add(&waiter->list_entry, &lock->wait_list);
- current->pi_blocked_on = waiter;
+ task->pi_blocked_on = waiter;
- spin_unlock_irqrestore(¤t->pi_lock, flags);
+ spin_unlock_irqrestore(&task->pi_lock, flags);
if (waiter == rt_mutex_top_waiter(lock)) {
spin_lock_irqsave(&owner->pi_lock, flags);
spin_unlock(&lock->wait_lock);
res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
- current);
+ task);
spin_lock(&lock->wait_lock);
rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
}
-/*
- * Slow path lock function:
+/**
+ * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
+ * @lock: the rt_mutex to take
+ * @state: the state the task should block in (TASK_INTERRUPTIBLE
+ * or TASK_UNINTERRUPTIBLE)
+ * @timeout: the pre-initialized and started timer, or NULL for none
+ * @waiter: the pre-initialized rt_mutex_waiter
+ * @detect_deadlock: passed to task_blocks_on_rt_mutex
+ *
+ * lock->wait_lock must be held by the caller.
*/
static int __sched
-rt_mutex_slowlock(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout,
- int detect_deadlock)
+__rt_mutex_slowlock(struct rt_mutex *lock, int state,
+ struct hrtimer_sleeper *timeout,
+ struct rt_mutex_waiter *waiter,
+ int detect_deadlock)
{
- struct rt_mutex_waiter waiter;
int ret = 0;
- debug_rt_mutex_init_waiter(&waiter);
- waiter.task = NULL;
-
- spin_lock(&lock->wait_lock);
-
- /* Try to acquire the lock again: */
- if (try_to_take_rt_mutex(lock)) {
- spin_unlock(&lock->wait_lock);
- return 0;
- }
-
- set_current_state(state);
-
- /* Setup the timer, when timeout != NULL */
- if (unlikely(timeout)) {
- hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
- if (!hrtimer_active(&timeout->timer))
- timeout->task = NULL;
- }
-
for (;;) {
/* Try to acquire the lock: */
if (try_to_take_rt_mutex(lock))
}
/*
- * waiter.task is NULL the first time we come here and
+ * waiter->task is NULL the first time we come here and
* when we have been woken up by the previous owner
* but the lock got stolen by a higher prio task.
*/
- if (!waiter.task) {
- ret = task_blocks_on_rt_mutex(lock, &waiter,
+ if (!waiter->task) {
+ ret = task_blocks_on_rt_mutex(lock, waiter, current,
detect_deadlock);
/*
* If we got woken up by the owner then start loop
* all over without going into schedule to try
* to get the lock now:
*/
- if (unlikely(!waiter.task)) {
+ if (unlikely(!waiter->task)) {
/*
* Reset the return value. We might
* have returned with -EDEADLK and the
spin_unlock(&lock->wait_lock);
- debug_rt_mutex_print_deadlock(&waiter);
+ debug_rt_mutex_print_deadlock(waiter);
- if (waiter.task)
+ if (waiter->task)
schedule_rt_mutex(lock);
spin_lock(&lock->wait_lock);
set_current_state(state);
}
+ return ret;
+}
+
+/*
+ * Slow path lock function:
+ */
+static int __sched
+rt_mutex_slowlock(struct rt_mutex *lock, int state,
+ struct hrtimer_sleeper *timeout,
+ int detect_deadlock)
+{
+ struct rt_mutex_waiter waiter;
+ int ret = 0;
+
+ debug_rt_mutex_init_waiter(&waiter);
+ waiter.task = NULL;
+
+ spin_lock(&lock->wait_lock);
+
+ /* Try to acquire the lock again: */
+ if (try_to_take_rt_mutex(lock)) {
+ spin_unlock(&lock->wait_lock);
+ return 0;
+ }
+
+ set_current_state(state);
+
+ /* Setup the timer, when timeout != NULL */
+ if (unlikely(timeout)) {
+ hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+ if (!hrtimer_active(&timeout->timer))
+ timeout->task = NULL;
+ }
+
+ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
+ detect_deadlock);
+
set_current_state(TASK_RUNNING);
if (unlikely(waiter.task))
EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
/**
- * rt_mutex_lock_interruptible_ktime - lock a rt_mutex interruptible
- * the timeout structure is provided
- * by the caller
+ * rt_mutex_timed_lock - lock a rt_mutex interruptible
+ * the timeout structure is provided
+ * by the caller
*
* @lock: the rt_mutex to be locked
* @timeout: timeout structure or NULL (no timeout)
}
EXPORT_SYMBOL_GPL(rt_mutex_unlock);
-/***
+/**
* rt_mutex_destroy - mark a mutex unusable
* @lock: the mutex to be destroyed
*
rt_mutex_deadlock_account_unlock(proxy_owner);
}
+/**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock: the rt_mutex to take
+ * @waiter: the pre-initialized rt_mutex_waiter
+ * @task: the task to prepare
+ * @detect_deadlock: perform deadlock detection (1) or not (0)
+ *
+ * Returns:
+ * 0 - task blocked on lock
+ * 1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter,
+ struct task_struct *task, int detect_deadlock)
+{
+ int ret;
+
+ spin_lock(&lock->wait_lock);
+
+ mark_rt_mutex_waiters(lock);
+
+ if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
+ /* We got the lock for task. */
+ debug_rt_mutex_lock(lock);
+
+ rt_mutex_set_owner(lock, task, 0);
+
+ rt_mutex_deadlock_account_lock(lock, task);
+ return 1;
+ }
+
+ ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+
+
+ if (ret && !waiter->task) {
+ /*
+ * Reset the return value. We might have
+ * returned with -EDEADLK and the owner
+ * released the lock while we were walking the
+ * pi chain. Let the waiter sort it out.
+ */
+ ret = 0;
+ }
+ spin_unlock(&lock->wait_lock);
+
+ debug_rt_mutex_print_deadlock(waiter);
+
+ return ret;
+}
+
/**
* rt_mutex_next_owner - return the next owner of the lock
*
return rt_mutex_top_waiter(lock)->task;
}
+
+/**
+ * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * @lock: the rt_mutex we were woken on
+ * @to: the timeout, null if none. hrtimer should already have
+ * been started.
+ * @waiter: the pre-initialized rt_mutex_waiter
+ * @detect_deadlock: perform deadlock detection (1) or not (0)
+ *
+ * Complete the lock acquisition started our behalf by another thread.
+ *
+ * Returns:
+ * 0 - success
+ * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ *
+ * Special API call for PI-futex requeue support
+ */
+int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+ struct hrtimer_sleeper *to,
+ struct rt_mutex_waiter *waiter,
+ int detect_deadlock)
+{
+ int ret;
+
+ spin_lock(&lock->wait_lock);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
+ detect_deadlock);
+
+ set_current_state(TASK_RUNNING);
+
+ if (unlikely(waiter->task))
+ remove_waiter(lock, waiter);
+
+ /*
+ * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+ * have to fix that up.
+ */
+ fixup_rt_mutex_waiters(lock);
+
+ spin_unlock(&lock->wait_lock);
+
+ /*
+ * Readjust priority, when we did not get the lock. We might have been
+ * the pending owner and boosted. Since we did not take the lock, the
+ * PI boost has to go.
+ */
+ if (unlikely(ret))
+ rt_mutex_adjust_prio(current);
+
+ return ret;
+}
struct task_struct *proxy_owner);
extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
struct task_struct *proxy_owner);
+extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter,
+ struct task_struct *task,
+ int detect_deadlock);
+extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+ struct hrtimer_sleeper *to,
+ struct rt_mutex_waiter *waiter,
+ int detect_deadlock);
#ifdef CONFIG_DEBUG_RT_MUTEXES
# include "rtmutex-debug.h"
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>
-#include <trace/sched.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
#include "sched_cpupri.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
* to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
*/
#define RUNTIME_INF ((u64)~0ULL)
-DEFINE_TRACE(sched_wait_task);
-DEFINE_TRACE(sched_wakeup);
-DEFINE_TRACE(sched_wakeup_new);
-DEFINE_TRACE(sched_switch);
-DEFINE_TRACE(sched_migrate_task);
-
#ifdef CONFIG_SMP
static void double_rq_lock(struct rq *rq1, struct rq *rq2);
struct list_head migration_queue;
#endif
+ /* calc_load related fields */
+ unsigned long calc_load_update;
+ long calc_load_active;
+
#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
int hrtick_csd_pending;
}
#endif
+static void calc_load_account_active(struct rq *this_rq);
+
#include "sched_stats.h"
#include "sched_idletask.c"
#include "sched_fair.c"
clock_offset = old_rq->clock - new_rq->clock;
- trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+ trace_sched_migrate_task(p, new_cpu);
#ifdef CONFIG_SCHEDSTATS
if (p->se.wait_start)
return 1;
}
+/*
+ * wait_task_context_switch - wait for a thread to complete at least one
+ * context switch.
+ *
+ * @p must not be current.
+ */
+void wait_task_context_switch(struct task_struct *p)
+{
+ unsigned long nvcsw, nivcsw, flags;
+ int running;
+ struct rq *rq;
+
+ nvcsw = p->nvcsw;
+ nivcsw = p->nivcsw;
+ for (;;) {
+ /*
+ * The runqueue is assigned before the actual context
+ * switch. We need to take the runqueue lock.
+ *
+ * We could check initially without the lock but it is
+ * very likely that we need to take the lock in every
+ * iteration.
+ */
+ rq = task_rq_lock(p, &flags);
+ running = task_running(rq, p);
+ task_rq_unlock(rq, &flags);
+
+ if (likely(!running))
+ break;
+ /*
+ * The switch count is incremented before the actual
+ * context switch. We thus wait for two switches to be
+ * sure at least one completed.
+ */
+ if ((p->nvcsw - nvcsw) > 1)
+ break;
+ if ((p->nivcsw - nivcsw) > 1)
+ break;
+
+ cpu_relax();
+ }
+}
+
/*
* wait_task_inactive - wait for a thread to unschedule.
*
return success;
}
+/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+ * Attempt to wake up the nominated process and move it to the set of runnable
+ * processes. Returns 1 if the process was woken up, 0 if it was already
+ * running.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
int wake_up_process(struct task_struct *p)
{
return try_to_wake_up(p, TASK_ALL, 0);
* combine the page table reload and the switch backend into
* one hypercall.
*/
- arch_enter_lazy_cpu_mode();
+ arch_start_context_switch(prev);
if (unlikely(!mm)) {
next->active_mm = oldmm;
return sum;
}
-unsigned long nr_active(void)
+/* Variables and functions for calc_load */
+static atomic_long_t calc_load_tasks;
+static unsigned long calc_load_update;
+unsigned long avenrun[3];
+EXPORT_SYMBOL(avenrun);
+
+/**
+ * get_avenrun - get the load average array
+ * @loads: pointer to dest load array
+ * @offset: offset to add
+ * @shift: shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+ loads[0] = (avenrun[0] + offset) << shift;
+ loads[1] = (avenrun[1] + offset) << shift;
+ loads[2] = (avenrun[2] + offset) << shift;
+}
+
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
{
- unsigned long i, running = 0, uninterruptible = 0;
+ load *= exp;
+ load += active * (FIXED_1 - exp);
+ return load >> FSHIFT;
+}
- for_each_online_cpu(i) {
- running += cpu_rq(i)->nr_running;
- uninterruptible += cpu_rq(i)->nr_uninterruptible;
- }
+/*
+ * calc_load - update the avenrun load estimates 10 ticks after the
+ * CPUs have updated calc_load_tasks.
+ */
+void calc_global_load(void)
+{
+ unsigned long upd = calc_load_update + 10;
+ long active;
- if (unlikely((long)uninterruptible < 0))
- uninterruptible = 0;
+ if (time_before(jiffies, upd))
+ return;
- return running + uninterruptible;
+ active = atomic_long_read(&calc_load_tasks);
+ active = active > 0 ? active * FIXED_1 : 0;
+
+ avenrun[0] = calc_load(avenrun[0], EXP_1, active);
+ avenrun[1] = calc_load(avenrun[1], EXP_5, active);
+ avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+ calc_load_update += LOAD_FREQ;
+}
+
+/*
+ * Either called from update_cpu_load() or from a cpu going idle
+ */
+static void calc_load_account_active(struct rq *this_rq)
+{
+ long nr_active, delta;
+
+ nr_active = this_rq->nr_running;
+ nr_active += (long) this_rq->nr_uninterruptible;
+
+ if (nr_active != this_rq->calc_load_active) {
+ delta = nr_active - this_rq->calc_load_active;
+ this_rq->calc_load_active = nr_active;
+ atomic_long_add(delta, &calc_load_tasks);
+ }
}
/*
new_load += scale-1;
this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
}
+
+ if (time_after_eq(jiffies, this_rq->calc_load_update)) {
+ this_rq->calc_load_update += LOAD_FREQ;
+ calc_load_account_active(this_rq);
+ }
}
#ifdef CONFIG_SMP
static struct {
atomic_t load_balancer;
cpumask_var_t cpu_mask;
+ cpumask_var_t ilb_grp_nohz_mask;
} nohz ____cacheline_aligned = {
.load_balancer = ATOMIC_INIT(-1),
};
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * lowest_flag_domain - Return lowest sched_domain containing flag.
+ * @cpu: The cpu whose lowest level of sched domain is to
+ * be returned.
+ * @flag: The flag to check for the lowest sched_domain
+ * for the given cpu.
+ *
+ * Returns the lowest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+ struct sched_domain *sd;
+
+ for_each_domain(cpu, sd)
+ if (sd && (sd->flags & flag))
+ break;
+
+ return sd;
+}
+
+/**
+ * for_each_flag_domain - Iterates over sched_domains containing the flag.
+ * @cpu: The cpu whose domains we're iterating over.
+ * @sd: variable holding the value of the power_savings_sd
+ * for cpu.
+ * @flag: The flag to filter the sched_domains to be iterated.
+ *
+ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
+ * set, starting from the lowest sched_domain to the highest.
+ */
+#define for_each_flag_domain(cpu, sd, flag) \
+ for (sd = lowest_flag_domain(cpu, flag); \
+ (sd && (sd->flags & flag)); sd = sd->parent)
+
+/**
+ * is_semi_idle_group - Checks if the given sched_group is semi-idle.
+ * @ilb_group: group to be checked for semi-idleness
+ *
+ * Returns: 1 if the group is semi-idle. 0 otherwise.
+ *
+ * We define a sched_group to be semi idle if it has atleast one idle-CPU
+ * and atleast one non-idle CPU. This helper function checks if the given
+ * sched_group is semi-idle or not.
+ */
+static inline int is_semi_idle_group(struct sched_group *ilb_group)
+{
+ cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
+ sched_group_cpus(ilb_group));
+
+ /*
+ * A sched_group is semi-idle when it has atleast one busy cpu
+ * and atleast one idle cpu.
+ */
+ if (cpumask_empty(nohz.ilb_grp_nohz_mask))
+ return 0;
+
+ if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
+ return 0;
+
+ return 1;
+}
+/**
+ * find_new_ilb - Finds the optimum idle load balancer for nomination.
+ * @cpu: The cpu which is nominating a new idle_load_balancer.
+ *
+ * Returns: Returns the id of the idle load balancer if it exists,
+ * Else, returns >= nr_cpu_ids.
+ *
+ * This algorithm picks the idle load balancer such that it belongs to a
+ * semi-idle powersavings sched_domain. The idea is to try and avoid
+ * completely idle packages/cores just for the purpose of idle load balancing
+ * when there are other idle cpu's which are better suited for that job.
+ */
+static int find_new_ilb(int cpu)
+{
+ struct sched_domain *sd;
+ struct sched_group *ilb_group;
+
+ /*
+ * Have idle load balancer selection from semi-idle packages only
+ * when power-aware load balancing is enabled
+ */
+ if (!(sched_smt_power_savings || sched_mc_power_savings))
+ goto out_done;
+
+ /*
+ * Optimize for the case when we have no idle CPUs or only one
+ * idle CPU. Don't walk the sched_domain hierarchy in such cases
+ */
+ if (cpumask_weight(nohz.cpu_mask) < 2)
+ goto out_done;
+
+ for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
+ ilb_group = sd->groups;
+
+ do {
+ if (is_semi_idle_group(ilb_group))
+ return cpumask_first(nohz.ilb_grp_nohz_mask);
+
+ ilb_group = ilb_group->next;
+
+ } while (ilb_group != sd->groups);
+ }
+
+out_done:
+ return cpumask_first(nohz.cpu_mask);
+}
+#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
+static inline int find_new_ilb(int call_cpu)
+{
+ return cpumask_first(nohz.cpu_mask);
+}
+#endif
+
/*
* This routine will try to nominate the ilb (idle load balancing)
* owner among the cpus whose ticks are stopped. ilb owner will do the idle
/* make me the ilb owner */
if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
return 1;
- } else if (atomic_read(&nohz.load_balancer) == cpu)
+ } else if (atomic_read(&nohz.load_balancer) == cpu) {
+ int new_ilb;
+
+ if (!(sched_smt_power_savings ||
+ sched_mc_power_savings))
+ return 1;
+ /*
+ * Check to see if there is a more power-efficient
+ * ilb.
+ */
+ new_ilb = find_new_ilb(cpu);
+ if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
+ atomic_set(&nohz.load_balancer, -1);
+ resched_cpu(new_ilb);
+ return 0;
+ }
return 1;
+ }
} else {
if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
return 0;
}
if (atomic_read(&nohz.load_balancer) == -1) {
- /*
- * simple selection for now: Nominate the
- * first cpu in the nohz list to be the next
- * ilb owner.
- *
- * TBD: Traverse the sched domains and nominate
- * the nearest cpu in the nohz.cpu_mask.
- */
- int ilb = cpumask_first(nohz.cpu_mask);
+ int ilb = find_new_ilb(cpu);
if (ilb < nr_cpu_ids)
resched_cpu(ilb);
/*
* schedule() is the main scheduler function.
*/
-asmlinkage void __sched __schedule(void)
+asmlinkage void __sched schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
+need_resched:
+ preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
rcu_qsctr_inc(cpu);
if (unlikely(reacquire_kernel_lock(current) < 0))
goto need_resched_nonpreemptible;
-}
-asmlinkage void __sched schedule(void)
-{
-need_resched:
- preempt_disable();
- __schedule();
preempt_enable_no_resched();
- if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+ if (need_resched())
goto need_resched;
}
EXPORT_SYMBOL(schedule);
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, int sync, void *key)
{
wait_queue_t *curr, *next;
* @mode: which threads
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
*/
void __wake_up(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, void *key)
* with each other. This can prevent needless bouncing between CPUs.
*
* On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
*/
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, void *key)
* awakened in the same order in which they were queued.
*
* See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
*/
void complete(struct completion *x)
{
* @x: holds the state of this particular completion
*
* This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
*/
void complete_all(struct completion *x)
{
#ifdef CONFIG_DEBUG_STACK_USAGE
free = stack_not_used(p);
#endif
- printk(KERN_CONT "%5lu %5d %6d\n", free,
- task_pid_nr(p), task_pid_nr(p->real_parent));
+ printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
+ task_pid_nr(p), task_pid_nr(p->real_parent),
+ (unsigned long)task_thread_info(p)->flags);
show_stack(p, NULL);
}
}
}
+
+/*
+ * remove the tasks which were accounted by rq from calc_load_tasks.
+ */
+static void calc_global_load_remove(struct rq *rq)
+{
+ atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+}
#endif /* CONFIG_HOTPLUG_CPU */
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
/* Update our root-domain */
rq = cpu_rq(cpu);
spin_lock_irqsave(&rq->lock, flags);
+ rq->calc_load_update = calc_load_update;
+ rq->calc_load_active = 0;
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
cpuset_unlock();
migrate_nr_uninterruptible(rq);
BUG_ON(rq->nr_running != 0);
-
+ calc_global_load_remove(rq);
/*
* No need to migrate the tasks: it was best-effort if
* they didn't take sched_hotcpu_mutex. Just wake up
/*
* The cpus mask in sched_group and sched_domain hangs off the end.
- * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space
- * for nr_cpu_ids < CONFIG_NR_CPUS.
+ *
+ * ( See the the comments in include/linux/sched.h:struct sched_group
+ * and struct sched_domain. )
*/
struct static_sched_group {
struct sched_group sg;
struct sched_domain *sd;
sd = &per_cpu(phys_domains, j).sd;
- if (j != cpumask_first(sched_group_cpus(sd->groups))) {
+ if (j != group_first_cpu(sd->groups)) {
/*
* Only add "power" once for each
* physical package.
WARN_ON(!sd || !sd->groups);
- if (cpu != cpumask_first(sched_group_cpus(sd->groups)))
+ if (cpu != group_first_cpu(sd->groups))
return;
child = sd->child;
rq = cpu_rq(i);
spin_lock_init(&rq->lock);
rq->nr_running = 0;
+ rq->calc_load_active = 0;
+ rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs, rq);
init_rt_rq(&rq->rt, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
* when this runqueue becomes "idle".
*/
init_idle(current, smp_processor_id());
+
+ calc_load_update = jiffies + LOAD_FREQ;
+
/*
* During early bootup we pretend to be a normal task:
*/
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
alloc_bootmem_cpumask_var(&nohz.cpu_mask);
+ alloc_bootmem_cpumask_var(&nohz.ilb_grp_nohz_mask);
#endif
alloc_bootmem_cpumask_var(&cpu_isolated_map);
#endif /* SMP */
if (sysctl_sched_rt_period <= 0)
return -EINVAL;
+ /*
+ * There's always some RT tasks in the root group
+ * -- migration, kstopmachine etc..
+ */
+ if (sysctl_sched_rt_runtime == 0)
+ return -EBUSY;
+
spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
for_each_possible_cpu(i) {
struct rt_rq *rt_rq = &cpu_rq(i)->rt;
find_matching_se(&se, &pse);
- while (se) {
- BUG_ON(!pse);
+ BUG_ON(!pse);
- if (wakeup_preempt_entity(se, pse) == 1) {
- resched_task(curr);
- break;
- }
-
- se = parent_entity(se);
- pse = parent_entity(pse);
- }
+ if (wakeup_preempt_entity(se, pse) == 1)
+ resched_task(curr);
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
static struct task_struct *pick_next_task_idle(struct rq *rq)
{
schedstat_inc(rq, sched_goidle);
-
+ /* adjust the active tasks as we might go into a long sleep */
+ calc_load_account_active(rq);
return rq->idle;
}
#include <linux/freezer.h>
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include <asm/param.h>
#include <asm/uaccess.h>
static struct kmem_cache *sigqueue_cachep;
-DEFINE_TRACE(sched_signal_send);
-
static void __user *sig_handler(struct task_struct *t, int sig)
{
return t->sighand->action[sig - 1].sa.sa_handler;
/*
* Flush all pending signals for a task.
*/
+void __flush_signals(struct task_struct *t)
+{
+ clear_tsk_thread_flag(t, TIF_SIGPENDING);
+ flush_sigqueue(&t->pending);
+ flush_sigqueue(&t->signal->shared_pending);
+}
+
void flush_signals(struct task_struct *t)
{
unsigned long flags;
spin_lock_irqsave(&t->sighand->siglock, flags);
- clear_tsk_thread_flag(t, TIF_SIGPENDING);
- flush_sigqueue(&t->pending);
- flush_sigqueue(&t->signal->shared_pending);
+ __flush_signals(t);
spin_unlock_irqrestore(&t->sighand->siglock, flags);
}
return kill_something_info(sig, &info, pid);
}
-static int do_tkill(pid_t tgid, pid_t pid, int sig)
+static int
+do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
{
- int error;
- struct siginfo info;
struct task_struct *p;
unsigned long flags;
-
- error = -ESRCH;
- info.si_signo = sig;
- info.si_errno = 0;
- info.si_code = SI_TKILL;
- info.si_pid = task_tgid_vnr(current);
- info.si_uid = current_uid();
+ int error = -ESRCH;
rcu_read_lock();
p = find_task_by_vpid(pid);
if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) {
- error = check_kill_permission(sig, &info, p);
+ error = check_kill_permission(sig, info, p);
/*
* The null signal is a permissions and process existence
* probe. No signal is actually delivered.
* signal is private anyway.
*/
if (!error && sig && lock_task_sighand(p, &flags)) {
- error = specific_send_sig_info(sig, &info, p);
+ error = specific_send_sig_info(sig, info, p);
unlock_task_sighand(p, &flags);
}
}
return error;
}
+static int do_tkill(pid_t tgid, pid_t pid, int sig)
+{
+ struct siginfo info;
+
+ info.si_signo = sig;
+ info.si_errno = 0;
+ info.si_code = SI_TKILL;
+ info.si_pid = task_tgid_vnr(current);
+ info.si_uid = current_uid();
+
+ return do_send_specific(tgid, pid, sig, &info);
+}
+
/**
* sys_tgkill - send signal to one specific thread
* @tgid: the thread group ID of the thread
return kill_proc_info(sig, &info, pid);
}
+long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info)
+{
+ /* This is only valid for single tasks */
+ if (pid <= 0 || tgid <= 0)
+ return -EINVAL;
+
+ /* Not even root can pretend to send signals from the kernel.
+ Nor can they impersonate a kill(), which adds source info. */
+ if (info->si_code >= 0)
+ return -EPERM;
+ info->si_signo = sig;
+
+ return do_send_specific(tgid, pid, sig, info);
+}
+
+SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig,
+ siginfo_t __user *, uinfo)
+{
+ siginfo_t info;
+
+ if (copy_from_user(&info, uinfo, sizeof(siginfo_t)))
+ return -EFAULT;
+
+ return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
+}
+
int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
{
struct task_struct *t = current;
#include <linux/ftrace.h>
#include <linux/smp.h>
#include <linux/tick.h>
-#include <trace/irq.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/irq.h>
#include <asm/irq.h>
/*
*/
#define MAX_SOFTIRQ_RESTART 10
-DEFINE_TRACE(softirq_entry);
-DEFINE_TRACE(softirq_exit);
-
asmlinkage void __do_softirq(void)
{
struct softirq_action *h;
return 0;
}
-int __weak arch_init_chip_data(struct irq_desc *desc, int cpu)
+int __weak arch_init_chip_data(struct irq_desc *desc, int node)
{
return 0;
}
#ifdef CONFIG_MODULES
extern char modprobe_path[];
+extern int modules_disabled;
#endif
#ifdef CONFIG_CHR_DEV_SG
extern int sg_big_buff;
.proc_handler = &proc_dostring,
.strategy = &sysctl_string,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "modules_disabled",
+ .data = &modules_disabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ /* only handle a transition from default "0" to "1" */
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &one,
+ },
#endif
#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
{
.mode = 0444,
.proc_handler = &proc_dointvec,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "bootloader_version",
+ .data = &bootloader_version,
+ .maxlen = sizeof (int),
+ .mode = 0444,
+ .proc_handler = &proc_dointvec,
+ },
{
.ctl_name = CTL_UNNUMBERED,
.procname = "kstack_depth_to_print",
.strategy = &sysctl_jiffies,
},
#endif
-#ifdef CONFIG_SECURITY
{
.ctl_name = CTL_UNNUMBERED,
.procname = "mmap_min_addr",
.mode = 0644,
.proc_handler = &proc_doulongvec_minmax,
},
-#endif
#ifdef CONFIG_NUMA
{
.ctl_name = CTL_UNNUMBERED,
/*
* This read-write spinlock protects us from races in SMP while
- * playing with xtime and avenrun.
+ * playing with xtime.
*/
__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
run_posix_cpu_timers(p);
}
-/*
- * Nr of active tasks - counted in fixed-point numbers
- */
-static unsigned long count_active_tasks(void)
-{
- return nr_active() * FIXED_1;
-}
-
-/*
- * Hmm.. Changed this, as the GNU make sources (load.c) seems to
- * imply that avenrun[] is the standard name for this kind of thing.
- * Nothing else seems to be standardized: the fractional size etc
- * all seem to differ on different machines.
- *
- * Requires xtime_lock to access.
- */
-unsigned long avenrun[3];
-
-EXPORT_SYMBOL(avenrun);
-
-/*
- * calc_load - given tick count, update the avenrun load estimates.
- * This is called while holding a write_lock on xtime_lock.
- */
-static inline void calc_load(unsigned long ticks)
-{
- unsigned long active_tasks; /* fixed-point */
- static int count = LOAD_FREQ;
-
- count -= ticks;
- if (unlikely(count < 0)) {
- active_tasks = count_active_tasks();
- do {
- CALC_LOAD(avenrun[0], EXP_1, active_tasks);
- CALC_LOAD(avenrun[1], EXP_5, active_tasks);
- CALC_LOAD(avenrun[2], EXP_15, active_tasks);
- count += LOAD_FREQ;
- } while (count < 0);
- }
-}
-
/*
* This function runs timers and the timer-tq in bottom half context.
*/
softlockup_tick();
}
-/*
- * Called by the timer interrupt. xtime_lock must already be taken
- * by the timer IRQ!
- */
-static inline void update_times(unsigned long ticks)
-{
- update_wall_time();
- calc_load(ticks);
-}
-
/*
* The 64-bit jiffies value is not atomic - you MUST NOT read it
* without sampling the sequence number in xtime_lock.
void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
- update_times(ticks);
+ update_wall_time();
+ calc_global_load();
}
#ifdef __ARCH_WANT_SYS_ALARM
{
unsigned long mem_total, sav_total;
unsigned int mem_unit, bitcount;
- unsigned long seq;
+ struct timespec tp;
memset(info, 0, sizeof(struct sysinfo));
- do {
- struct timespec tp;
- seq = read_seqbegin(&xtime_lock);
-
- /*
- * This is annoying. The below is the same thing
- * posix_get_clock_monotonic() does, but it wants to
- * take the lock which we want to cover the loads stuff
- * too.
- */
-
- getnstimeofday(&tp);
- tp.tv_sec += wall_to_monotonic.tv_sec;
- tp.tv_nsec += wall_to_monotonic.tv_nsec;
- monotonic_to_bootbased(&tp);
- if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
- tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
- tp.tv_sec++;
- }
- info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
+ ktime_get_ts(&tp);
+ monotonic_to_bootbased(&tp);
+ info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
- info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
- info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
- info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);
+ get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
- info->procs = nr_threads;
- } while (read_seqretry(&xtime_lock, seq));
+ info->procs = nr_threads;
si_meminfo(info);
si_swapinfo(info);
depends on HAVE_FTRACE_NMI_ENTER
default y
+config EVENT_TRACING
+ select CONTEXT_SWITCH_TRACER
+ bool
+
+config CONTEXT_SWITCH_TRACER
+ select MARKERS
+ bool
+
+# All tracer options should select GENERIC_TRACER. For those options that are
+# enabled by all tracers (context switch and event tracer) they select TRACING.
+# This allows those options to appear when no other tracer is selected. But the
+# options do not appear when something else selects it. We need the two options
+# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
+# hidding of the automatic options options.
+
config TRACING
bool
select DEBUG_FS
select TRACEPOINTS
select NOP_TRACER
select BINARY_PRINTF
+ select EVENT_TRACING
+
+config GENERIC_TRACER
+ bool
+ select TRACING
#
# Minimum requirements an architecture has to meet for us to
if TRACING_SUPPORT
-menu "Tracers"
+menuconfig FTRACE
+ bool "Tracers"
+ default y if DEBUG_KERNEL
+ help
+ Enable the kernel tracing infrastructure.
+
+if FTRACE
config FUNCTION_TRACER
bool "Kernel Function Tracer"
depends on HAVE_FUNCTION_TRACER
select FRAME_POINTER
select KALLSYMS
- select TRACING
+ select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
help
Enable the kernel to trace every kernel function. This is done
the return value. This is done by setting the current return
address on the current task structure into a stack of calls.
+
config IRQSOFF_TRACER
bool "Interrupts-off Latency Tracer"
default n
depends on TRACE_IRQFLAGS_SUPPORT
depends on GENERIC_TIME
select TRACE_IRQFLAGS
- select TRACING
+ select GENERIC_TRACER
select TRACER_MAX_TRACE
help
This option measures the time spent in irqs-off critical
default n
depends on GENERIC_TIME
depends on PREEMPT
- select TRACING
+ select GENERIC_TRACER
select TRACER_MAX_TRACE
help
This option measures the time spent in preemption off critical
config SYSPROF_TRACER
bool "Sysprof Tracer"
depends on X86
- select TRACING
+ select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
help
This tracer provides the trace needed by the 'Sysprof' userspace
config SCHED_TRACER
bool "Scheduling Latency Tracer"
- select TRACING
+ select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
select TRACER_MAX_TRACE
help
This tracer tracks the latency of the highest priority task
to be scheduled in, starting from the point it has woken up.
-config CONTEXT_SWITCH_TRACER
- bool "Trace process context switches"
- select TRACING
- select MARKERS
- help
- This tracer gets called from the context switch and records
- all switching of tasks.
-
-config EVENT_TRACER
- bool "Trace various events in the kernel"
+config ENABLE_DEFAULT_TRACERS
+ bool "Trace process context switches and events"
+ depends on !GENERIC_TRACER
select TRACING
help
This tracer hooks to various trace points in the kernel
allowing the user to pick and choose which trace point they
- want to trace.
+ want to trace. It also includes the sched_switch tracer plugin.
config FTRACE_SYSCALLS
bool "Trace syscalls"
depends on HAVE_FTRACE_SYSCALLS
- select TRACING
+ select GENERIC_TRACER
select KALLSYMS
help
Basic tracer to catch the syscall entry and exit events.
config BOOT_TRACER
bool "Trace boot initcalls"
- select TRACING
+ select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
help
This tracer helps developers to optimize boot times: it records
to enable this on bootup.
config TRACE_BRANCH_PROFILING
+ bool
+ select GENERIC_TRACER
+
+choice
+ prompt "Branch Profiling"
+ default BRANCH_PROFILE_NONE
+ help
+ The branch profiling is a software profiler. It will add hooks
+ into the C conditionals to test which path a branch takes.
+
+ The likely/unlikely profiler only looks at the conditions that
+ are annotated with a likely or unlikely macro.
+
+ The "all branch" profiler will profile every if statement in the
+ kernel. This profiler will also enable the likely/unlikely
+ profiler as well.
+
+ Either of the above profilers add a bit of overhead to the system.
+ If unsure choose "No branch profiling".
+
+config BRANCH_PROFILE_NONE
+ bool "No branch profiling"
+ help
+ No branch profiling. Branch profiling adds a bit of overhead.
+ Only enable it if you want to analyse the branching behavior.
+ Otherwise keep it disabled.
+
+config PROFILE_ANNOTATED_BRANCHES
bool "Trace likely/unlikely profiler"
- select TRACING
+ select TRACE_BRANCH_PROFILING
help
This tracer profiles all the the likely and unlikely macros
in the kernel. It will display the results in:
Note: this will add a significant overhead, only turn this
on if you need to profile the system's use of these macros.
- Say N if unsure.
-
config PROFILE_ALL_BRANCHES
bool "Profile all if conditionals"
- depends on TRACE_BRANCH_PROFILING
+ select TRACE_BRANCH_PROFILING
help
This tracer profiles all branch conditions. Every if ()
taken in the kernel is recorded whether it hit or miss.
/debugfs/tracing/profile_branch
+ This option also enables the likely/unlikely profiler.
+
This configuration, when enabled, will impose a great overhead
on the system. This should only be enabled when the system
is to be analyzed
-
- Say N if unsure.
+endchoice
config TRACING_BRANCHES
bool
config POWER_TRACER
bool "Trace power consumption behavior"
depends on X86
- select TRACING
+ select GENERIC_TRACER
help
This tracer helps developers to analyze and optimize the kernels
power management decisions, specifically the C-state and P-state
config HW_BRANCH_TRACER
depends on HAVE_HW_BRANCH_TRACER
bool "Trace hw branches"
- select TRACING
+ select GENERIC_TRACER
help
This tracer records all branches on the system in a circular
buffer giving access to the last N branches for each cpu.
config KMEMTRACE
bool "Trace SLAB allocations"
- select TRACING
+ select GENERIC_TRACER
help
kmemtrace provides tracing for slab allocator functions, such as
kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
config WORKQUEUE_TRACER
bool "Trace workqueues"
- select TRACING
+ select GENERIC_TRACER
help
The workqueue tracer provides some statistical informations
about each cpu workqueue thread such as the number of the
select RELAY
select DEBUG_FS
select TRACEPOINTS
- select TRACING
+ select GENERIC_TRACER
select STACKTRACE
help
Say Y here if you want to be able to trace the block layer actions
were made. If so, it runs stop_machine (stops all CPUS)
and modifies the code to jump over the call to ftrace.
+config FUNCTION_PROFILER
+ bool "Kernel function profiler"
+ depends on FUNCTION_TRACER
+ default n
+ help
+ This option enables the kernel function profiler. A file is created
+ in debugfs called function_profile_enabled which defaults to zero.
+ When a 1 is echoed into this file profiling begins, and when a
+ zero is entered, profiling stops. A file in the trace_stats
+ directory called functions, that show the list of functions that
+ have been hit and their counters.
+
+ If in doubt, say N
+
config FTRACE_MCOUNT_RECORD
def_bool y
depends on DYNAMIC_FTRACE
config FTRACE_STARTUP_TEST
bool "Perform a startup test on ftrace"
- depends on TRACING
+ depends on GENERIC_TRACER
select FTRACE_SELFTEST
help
This option performs a series of startup tests on ftrace. On bootup
config MMIOTRACE
bool "Memory mapped IO tracing"
depends on HAVE_MMIOTRACE_SUPPORT && PCI
- select TRACING
+ select GENERIC_TRACER
help
Mmiotrace traces Memory Mapped I/O access and is meant for
debugging and reverse engineering. It is called from the ioremap
Say N, unless you absolutely know what you are doing.
-endmenu
+config RING_BUFFER_BENCHMARK
+ tristate "Ring buffer benchmark stress tester"
+ depends on RING_BUFFER
+ help
+ This option creates a test to stress the ring buffer and bench mark it.
+ It creates its own ring buffer such that it will not interfer with
+ any other users of the ring buffer (such as ftrace). It then creates
+ a producer and consumer that will run for 10 seconds and sleep for
+ 10 seconds. Each interval it will print out the number of events
+ it recorded and give a rough estimate of how long each iteration took.
+
+ It does not disable interrupts or raise its priority, so it may be
+ affected by processes that are running.
+
+ If unsure, say N
+
+endif # FTRACE
endif # TRACING_SUPPORT
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
endif
+#
+# Make the trace clocks available generally: it's infrastructure
+# relied on by ptrace for example:
+#
+obj-y += trace_clock.o
+
obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
+obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
obj-$(CONFIG_TRACING) += trace.o
-obj-$(CONFIG_TRACING) += trace_clock.o
obj-$(CONFIG_TRACING) += trace_output.o
obj-$(CONFIG_TRACING) += trace_stat.o
obj-$(CONFIG_TRACING) += trace_printk.o
obj-$(CONFIG_POWER_TRACER) += trace_power.o
obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
-obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events.o
-obj-$(CONFIG_EVENT_TRACER) += events.o
-obj-$(CONFIG_EVENT_TRACER) += trace_export.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
+ifeq ($(CONFIG_BLOCK),y)
+obj-$(CONFIG_EVENT_TRACING) += blktrace.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events.o
+obj-$(CONFIG_EVENT_TRACING) += trace_export.o
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
libftrace-y := ftrace.o
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/time.h>
-#include <trace/block.h>
#include <linux/uaccess.h>
+
+#include <trace/events/block.h>
+
#include "trace_output.h"
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+
static unsigned int blktrace_seq __read_mostly = 1;
static struct trace_array *blk_tr;
{
if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
return 1;
- if (sector < bt->start_lba || sector > bt->end_lba)
+ if (sector && (sector < bt->start_lba || sector > bt->end_lba))
return 1;
if (bt->pid && pid != bt->pid)
return 1;
what |= MASK_TC_BIT(rw, DISCARD);
pid = tsk->pid;
- if (unlikely(act_log_check(bt, what, sector, pid)))
+ if (act_log_check(bt, what, sector, pid))
return;
cpu = raw_smp_processor_id();
{
debugfs_remove(bt->msg_file);
debugfs_remove(bt->dropped_file);
+ debugfs_remove(bt->dir);
relay_close(bt->rchan);
free_percpu(bt->sequence);
free_percpu(bt->msg_data);
.remove_buf_file = blk_remove_buf_file_callback,
};
+static void blk_trace_setup_lba(struct blk_trace *bt,
+ struct block_device *bdev)
+{
+ struct hd_struct *part = NULL;
+
+ if (bdev)
+ part = bdev->bd_part;
+
+ if (part) {
+ bt->start_lba = part->start_sect;
+ bt->end_lba = part->start_sect + part->nr_sects;
+ } else {
+ bt->start_lba = 0;
+ bt->end_lba = -1ULL;
+ }
+}
+
/*
* Setup everything required to start tracing
*/
int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
- struct blk_user_trace_setup *buts)
+ struct block_device *bdev,
+ struct blk_user_trace_setup *buts)
{
struct blk_trace *old_bt, *bt = NULL;
struct dentry *dir = NULL;
if (!bt->act_mask)
bt->act_mask = (u16) -1;
- bt->start_lba = buts->start_lba;
- bt->end_lba = buts->end_lba;
- if (!bt->end_lba)
- bt->end_lba = -1ULL;
+ blk_trace_setup_lba(bt, bdev);
+
+ /* overwrite with user settings */
+ if (buts->start_lba)
+ bt->start_lba = buts->start_lba;
+ if (buts->end_lba)
+ bt->end_lba = buts->end_lba;
bt->pid = buts->pid;
bt->trace_state = Blktrace_setup;
}
int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct block_device *bdev,
char __user *arg)
{
struct blk_user_trace_setup buts;
if (ret)
return -EFAULT;
- ret = do_blk_trace_setup(q, name, dev, &buts);
+ ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
if (ret)
return ret;
switch (cmd) {
case BLKTRACESETUP:
bdevname(bdev, b);
- ret = blk_trace_setup(q, b, bdev->bd_dev, arg);
+ ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
break;
case BLKTRACESTART:
start = 1;
* @bio: the source bio
* @dev: target device
* @from: source sector
- * @to: target sector
*
* Description:
* Device mapper or raid target sometimes need to split a bio because
*
**/
static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
- dev_t dev, sector_t from, sector_t to)
+ dev_t dev, sector_t from)
{
struct blk_trace *bt = q->blk_trace;
struct blk_io_trace_remap r;
if (likely(!bt))
return;
- r.device = cpu_to_be32(dev);
- r.device_from = cpu_to_be32(bio->bi_bdev->bd_dev);
- r.sector = cpu_to_be64(to);
+ r.device_from = cpu_to_be32(dev);
+ r.device_to = cpu_to_be32(bio->bi_bdev->bd_dev);
+ r.sector_from = cpu_to_be64(from);
- __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP,
- !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
+ BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE),
+ sizeof(r), &r);
}
/**
return te_blk_io_trace(ent) + 1;
}
+static inline u32 t_action(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->action;
+}
+
+static inline u32 t_bytes(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->bytes;
+}
+
static inline u32 t_sec(const struct trace_entry *ent)
{
return te_blk_io_trace(ent)->bytes >> 9;
struct blk_io_trace_remap *r)
{
const struct blk_io_trace_remap *__r = pdu_start(ent);
- __u64 sector = __r->sector;
+ __u64 sector_from = __r->sector_from;
- r->device = be32_to_cpu(__r->device);
r->device_from = be32_to_cpu(__r->device_from);
- r->sector = be64_to_cpu(sector);
+ r->device_to = be32_to_cpu(__r->device_to);
+ r->sector_from = be64_to_cpu(sector_from);
}
typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
MAJOR(t->device), MINOR(t->device), act, rwbs);
}
+static int blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
+{
+ const unsigned char *pdu_buf;
+ int pdu_len;
+ int i, end, ret;
+
+ pdu_buf = pdu_start(ent);
+ pdu_len = te_blk_io_trace(ent)->pdu_len;
+
+ if (!pdu_len)
+ return 1;
+
+ /* find the last zero that needs to be printed */
+ for (end = pdu_len - 1; end >= 0; end--)
+ if (pdu_buf[end])
+ break;
+ end++;
+
+ if (!trace_seq_putc(s, '('))
+ return 0;
+
+ for (i = 0; i < pdu_len; i++) {
+
+ ret = trace_seq_printf(s, "%s%02x",
+ i == 0 ? "" : " ", pdu_buf[i]);
+ if (!ret)
+ return ret;
+
+ /*
+ * stop when the rest is just zeroes and indicate so
+ * with a ".." appended
+ */
+ if (i == end && end != pdu_len - 1)
+ return trace_seq_puts(s, " ..) ");
+ }
+
+ return trace_seq_puts(s, ") ");
+}
+
static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
{
char cmd[TASK_COMM_LEN];
trace_find_cmdline(ent->pid, cmd);
- if (t_sec(ent))
- return trace_seq_printf(s, "%llu + %u [%s]\n",
- t_sector(ent), t_sec(ent), cmd);
- return trace_seq_printf(s, "[%s]\n", cmd);
+ if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+ int ret;
+
+ ret = trace_seq_printf(s, "%u ", t_bytes(ent));
+ if (!ret)
+ return 0;
+ ret = blk_log_dump_pdu(s, ent);
+ if (!ret)
+ return 0;
+ return trace_seq_printf(s, "[%s]\n", cmd);
+ } else {
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%s]\n",
+ t_sector(ent), t_sec(ent), cmd);
+ return trace_seq_printf(s, "[%s]\n", cmd);
+ }
}
static int blk_log_with_error(struct trace_seq *s,
const struct trace_entry *ent)
{
- if (t_sec(ent))
- return trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent),
- t_sec(ent), t_error(ent));
- return trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent));
+ if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+ int ret;
+
+ ret = blk_log_dump_pdu(s, ent);
+ if (ret)
+ return trace_seq_printf(s, "[%d]\n", t_error(ent));
+ return 0;
+ } else {
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%d]\n",
+ t_sector(ent),
+ t_sec(ent), t_error(ent));
+ return trace_seq_printf(s, "%llu [%d]\n",
+ t_sector(ent), t_error(ent));
+ }
}
static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
{
- struct blk_io_trace_remap r = { .device = 0, };
+ struct blk_io_trace_remap r = { .device_from = 0, };
get_pdu_remap(ent, &r);
return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
- t_sector(ent),
- t_sec(ent), MAJOR(r.device), MINOR(r.device),
- (unsigned long long)r.sector);
+ t_sector(ent), t_sec(ent),
+ MAJOR(r.device_from), MINOR(r.device_from),
+ (unsigned long long)r.sector_from);
}
static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
static void blk_tracer_start(struct trace_array *tr)
{
blk_tracer_enabled = true;
- trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
}
static int blk_tracer_init(struct trace_array *tr)
static void blk_tracer_stop(struct trace_array *tr)
{
blk_tracer_enabled = false;
- trace_flags |= TRACE_ITER_CONTEXT_INFO;
}
static void blk_tracer_reset(struct trace_array *tr)
}
if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
- ret = trace_seq_printf(s, "Bad pc action %x\n", what);
+ ret = trace_seq_printf(s, "Unknown action %x\n", what);
else {
ret = log_action(iter, what2act[what].act[long_act]);
if (ret)
static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
int flags)
{
- if (!trace_print_context(iter))
- return TRACE_TYPE_PARTIAL_LINE;
-
return print_one_line(iter, false);
}
return print_one_line(iter, true);
}
+static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+{
+ /* don't output context-info for blk_classic output */
+ if (bit == TRACE_BLK_OPT_CLASSIC) {
+ if (set)
+ trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
+ else
+ trace_flags |= TRACE_ITER_CONTEXT_INFO;
+ }
+ return 0;
+}
+
static struct tracer blk_tracer __read_mostly = {
.name = "blk",
.init = blk_tracer_init,
.print_header = blk_tracer_print_header,
.print_line = blk_tracer_print_line,
.flags = &blk_tracer_flags,
+ .set_flag = blk_tracer_set_flag,
};
static struct trace_event trace_blk_event = {
/*
* Setup everything required to start tracing
*/
-static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
+static int blk_trace_setup_queue(struct request_queue *q,
+ struct block_device *bdev)
{
struct blk_trace *old_bt, *bt = NULL;
int ret = -ENOMEM;
if (!bt->msg_data)
goto free_bt;
- bt->dev = dev;
+ bt->dev = bdev->bd_dev;
bt->act_mask = (u16)-1;
- bt->end_lba = -1ULL;
+
+ blk_trace_setup_lba(bt, bdev);
old_bt = xchg(&q->blk_trace, bt);
if (old_bt != NULL) {
if (attr == &dev_attr_enable) {
if (value)
- ret = blk_trace_setup_queue(q, bdev->bd_dev);
+ ret = blk_trace_setup_queue(q, bdev);
else
ret = blk_trace_remove_queue(q);
goto out_unlock_bdev;
ret = 0;
if (q->blk_trace == NULL)
- ret = blk_trace_setup_queue(q, bdev->bd_dev);
+ ret = blk_trace_setup_queue(q, bdev);
if (ret == 0) {
if (attr == &dev_attr_act_mask)
return ret ? ret : count;
}
+int blk_trace_init_sysfs(struct device *dev)
+{
+ return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
+}
+
+#endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#ifdef CONFIG_EVENT_TRACING
+
+void blk_dump_cmd(char *buf, struct request *rq)
+{
+ int i, end;
+ int len = rq->cmd_len;
+ unsigned char *cmd = rq->cmd;
+
+ if (!blk_pc_request(rq)) {
+ buf[0] = '\0';
+ return;
+ }
+
+ for (end = len - 1; end >= 0; end--)
+ if (cmd[end])
+ break;
+ end++;
+
+ for (i = 0; i < len; i++) {
+ buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]);
+ if (i == end && end != len - 1) {
+ sprintf(buf, " ..");
+ break;
+ }
+ }
+}
+
+void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
+{
+ int i = 0;
+
+ if (rw & WRITE)
+ rwbs[i++] = 'W';
+ else if (rw & 1 << BIO_RW_DISCARD)
+ rwbs[i++] = 'D';
+ else if (bytes)
+ rwbs[i++] = 'R';
+ else
+ rwbs[i++] = 'N';
+
+ if (rw & 1 << BIO_RW_AHEAD)
+ rwbs[i++] = 'A';
+ if (rw & 1 << BIO_RW_BARRIER)
+ rwbs[i++] = 'B';
+ if (rw & 1 << BIO_RW_SYNCIO)
+ rwbs[i++] = 'S';
+ if (rw & 1 << BIO_RW_META)
+ rwbs[i++] = 'M';
+
+ rwbs[i] = '\0';
+}
+
+void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
+{
+ int rw = rq->cmd_flags & 0x03;
+ int bytes;
+
+ if (blk_discard_rq(rq))
+ rw |= (1 << BIO_RW_DISCARD);
+
+ if (blk_pc_request(rq))
+ bytes = rq->data_len;
+ else
+ bytes = rq->hard_nr_sectors << 9;
+
+ blk_fill_rwbs(rwbs, rw, bytes);
+}
+
+#endif /* CONFIG_EVENT_TRACING */
+
+++ /dev/null
-/*
- * This is the place to register all trace points as events.
- */
-
-#include <linux/stringify.h>
-
-#include <trace/trace_events.h>
-
-#include "trace_output.h"
-
-#include "trace_events_stage_1.h"
-#include "trace_events_stage_2.h"
-#include "trace_events_stage_3.h"
-
#include <linux/list.h>
#include <linux/hash.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include <asm/ftrace.h>
+#include <asm/setup.h>
-#include "trace.h"
+#include "trace_output.h"
+#include "trace_stat.h"
#define FTRACE_WARN_ON(cond) \
do { \
static struct ftrace_ops ftrace_list_end __read_mostly =
{
- .func = ftrace_stub,
+ .func = ftrace_stub,
};
static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
#endif
}
+#ifdef CONFIG_FUNCTION_PROFILER
+struct ftrace_profile {
+ struct hlist_node node;
+ unsigned long ip;
+ unsigned long counter;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ unsigned long long time;
+#endif
+};
+
+struct ftrace_profile_page {
+ struct ftrace_profile_page *next;
+ unsigned long index;
+ struct ftrace_profile records[];
+};
+
+struct ftrace_profile_stat {
+ atomic_t disabled;
+ struct hlist_head *hash;
+ struct ftrace_profile_page *pages;
+ struct ftrace_profile_page *start;
+ struct tracer_stat stat;
+};
+
+#define PROFILE_RECORDS_SIZE \
+ (PAGE_SIZE - offsetof(struct ftrace_profile_page, records))
+
+#define PROFILES_PER_PAGE \
+ (PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
+
+static int ftrace_profile_bits __read_mostly;
+static int ftrace_profile_enabled __read_mostly;
+
+/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
+static DEFINE_MUTEX(ftrace_profile_lock);
+
+static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
+
+#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+
+static void *
+function_stat_next(void *v, int idx)
+{
+ struct ftrace_profile *rec = v;
+ struct ftrace_profile_page *pg;
+
+ pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
+
+ again:
+ rec++;
+ if ((void *)rec >= (void *)&pg->records[pg->index]) {
+ pg = pg->next;
+ if (!pg)
+ return NULL;
+ rec = &pg->records[0];
+ if (!rec->counter)
+ goto again;
+ }
+
+ return rec;
+}
+
+static void *function_stat_start(struct tracer_stat *trace)
+{
+ struct ftrace_profile_stat *stat =
+ container_of(trace, struct ftrace_profile_stat, stat);
+
+ if (!stat || !stat->start)
+ return NULL;
+
+ return function_stat_next(&stat->start->records[0], 0);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* function graph compares on total time */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->time < b->time)
+ return -1;
+ if (a->time > b->time)
+ return 1;
+ else
+ return 0;
+}
+#else
+/* not function graph compares against hits */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->counter < b->counter)
+ return -1;
+ if (a->counter > b->counter)
+ return 1;
+ else
+ return 0;
+}
+#endif
+
+static int function_stat_headers(struct seq_file *m)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " Function "
+ "Hit Time Avg\n"
+ " -------- "
+ "--- ---- ---\n");
+#else
+ seq_printf(m, " Function Hit\n"
+ " -------- ---\n");
+#endif
+ return 0;
+}
+
+static int function_stat_show(struct seq_file *m, void *v)
+{
+ struct ftrace_profile *rec = v;
+ char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ static DEFINE_MUTEX(mutex);
+ static struct trace_seq s;
+ unsigned long long avg;
+#endif
+
+ kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+ seq_printf(m, " %-30.30s %10lu", str, rec->counter);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " ");
+ avg = rec->time;
+ do_div(avg, rec->counter);
+
+ mutex_lock(&mutex);
+ trace_seq_init(&s);
+ trace_print_graph_duration(rec->time, &s);
+ trace_seq_puts(&s, " ");
+ trace_print_graph_duration(avg, &s);
+ trace_print_seq(m, &s);
+ mutex_unlock(&mutex);
+#endif
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+
+ pg = stat->pages = stat->start;
+
+ while (pg) {
+ memset(pg->records, 0, PROFILE_RECORDS_SIZE);
+ pg->index = 0;
+ pg = pg->next;
+ }
+
+ memset(stat->hash, 0,
+ FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
+}
+
+int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+ int functions;
+ int pages;
+ int i;
+
+ /* If we already allocated, do nothing */
+ if (stat->pages)
+ return 0;
+
+ stat->pages = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!stat->pages)
+ return -ENOMEM;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ functions = ftrace_update_tot_cnt;
+#else
+ /*
+ * We do not know the number of functions that exist because
+ * dynamic tracing is what counts them. With past experience
+ * we have around 20K functions. That should be more than enough.
+ * It is highly unlikely we will execute every function in
+ * the kernel.
+ */
+ functions = 20000;
+#endif
+
+ pg = stat->start = stat->pages;
+
+ pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
+
+ for (i = 0; i < pages; i++) {
+ pg->next = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!pg->next)
+ goto out_free;
+ pg = pg->next;
+ }
+
+ return 0;
+
+ out_free:
+ pg = stat->start;
+ while (pg) {
+ unsigned long tmp = (unsigned long)pg;
+
+ pg = pg->next;
+ free_page(tmp);
+ }
+
+ free_page((unsigned long)stat->pages);
+ stat->pages = NULL;
+ stat->start = NULL;
+
+ return -ENOMEM;
+}
+
+static int ftrace_profile_init_cpu(int cpu)
+{
+ struct ftrace_profile_stat *stat;
+ int size;
+
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ if (stat->hash) {
+ /* If the profile is already created, simply reset it */
+ ftrace_profile_reset(stat);
+ return 0;
+ }
+
+ /*
+ * We are profiling all functions, but usually only a few thousand
+ * functions are hit. We'll make a hash of 1024 items.
+ */
+ size = FTRACE_PROFILE_HASH_SIZE;
+
+ stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL);
+
+ if (!stat->hash)
+ return -ENOMEM;
+
+ if (!ftrace_profile_bits) {
+ size--;
+
+ for (; size; size >>= 1)
+ ftrace_profile_bits++;
+ }
+
+ /* Preallocate the function profiling pages */
+ if (ftrace_profile_pages_init(stat) < 0) {
+ kfree(stat->hash);
+ stat->hash = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int ftrace_profile_init(void)
+{
+ int cpu;
+ int ret = 0;
+
+ for_each_online_cpu(cpu) {
+ ret = ftrace_profile_init_cpu(cpu);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/* interrupts must be disabled */
+static struct ftrace_profile *
+ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec;
+ struct hlist_head *hhd;
+ struct hlist_node *n;
+ unsigned long key;
+
+ key = hash_long(ip, ftrace_profile_bits);
+ hhd = &stat->hash[key];
+
+ if (hlist_empty(hhd))
+ return NULL;
+
+ hlist_for_each_entry_rcu(rec, n, hhd, node) {
+ if (rec->ip == ip)
+ return rec;
+ }
+
+ return NULL;
+}
+
+static void ftrace_add_profile(struct ftrace_profile_stat *stat,
+ struct ftrace_profile *rec)
+{
+ unsigned long key;
+
+ key = hash_long(rec->ip, ftrace_profile_bits);
+ hlist_add_head_rcu(&rec->node, &stat->hash[key]);
+}
+
+/*
+ * The memory is already allocated, this simply finds a new record to use.
+ */
+static struct ftrace_profile *
+ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec = NULL;
+
+ /* prevent recursion (from NMIs) */
+ if (atomic_inc_return(&stat->disabled) != 1)
+ goto out;
+
+ /*
+ * Try to find the function again since an NMI
+ * could have added it
+ */
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (rec)
+ goto out;
+
+ if (stat->pages->index == PROFILES_PER_PAGE) {
+ if (!stat->pages->next)
+ goto out;
+ stat->pages = stat->pages->next;
+ }
+
+ rec = &stat->pages->records[stat->pages->index++];
+ rec->ip = ip;
+ ftrace_add_profile(stat, rec);
+
+ out:
+ atomic_dec(&stat->disabled);
+
+ return rec;
+}
+
+static void
+function_profile_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_profile_stat *stat;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ if (!ftrace_profile_enabled)
+ return;
+
+ local_irq_save(flags);
+
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash || !ftrace_profile_enabled)
+ goto out;
+
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (!rec) {
+ rec = ftrace_profile_alloc(stat, ip);
+ if (!rec)
+ goto out;
+ }
+
+ rec->counter++;
+ out:
+ local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int profile_graph_entry(struct ftrace_graph_ent *trace)
+{
+ function_profile_call(trace->func, 0);
+ return 1;
+}
+
+static void profile_graph_return(struct ftrace_graph_ret *trace)
+{
+ struct ftrace_profile_stat *stat;
+ unsigned long long calltime;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash || !ftrace_profile_enabled)
+ goto out;
+
+ calltime = trace->rettime - trace->calltime;
+
+ if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+ int index;
+
+ index = trace->depth;
+
+ /* Append this call time to the parent time to subtract */
+ if (index)
+ current->ret_stack[index - 1].subtime += calltime;
+
+ if (current->ret_stack[index].subtime < calltime)
+ calltime -= current->ret_stack[index].subtime;
+ else
+ calltime = 0;
+ }
+
+ rec = ftrace_find_profiled_func(stat, trace->func);
+ if (rec)
+ rec->time += calltime;
+
+ out:
+ local_irq_restore(flags);
+}
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_graph(&profile_graph_return,
+ &profile_graph_entry);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_graph();
+}
+#else
+static struct ftrace_ops ftrace_profile_ops __read_mostly =
+{
+ .func = function_profile_call,
+};
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_function(&ftrace_profile_ops);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_function(&ftrace_profile_ops);
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static ssize_t
+ftrace_profile_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long val;
+ char buf[64]; /* big enough to hold a number */
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ val = !!val;
+
+ mutex_lock(&ftrace_profile_lock);
+ if (ftrace_profile_enabled ^ val) {
+ if (val) {
+ ret = ftrace_profile_init();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+
+ ret = register_ftrace_profiler();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+ ftrace_profile_enabled = 1;
+ } else {
+ ftrace_profile_enabled = 0;
+ /*
+ * unregister_ftrace_profiler calls stop_machine
+ * so this acts like an synchronize_sched.
+ */
+ unregister_ftrace_profiler();
+ }
+ }
+ out:
+ mutex_unlock(&ftrace_profile_lock);
+
+ filp->f_pos += cnt;
+
+ return cnt;
+}
+
+static ssize_t
+ftrace_profile_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64]; /* big enough to hold a number */
+ int r;
+
+ r = sprintf(buf, "%u\n", ftrace_profile_enabled);
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static const struct file_operations ftrace_profile_fops = {
+ .open = tracing_open_generic,
+ .read = ftrace_profile_read,
+ .write = ftrace_profile_write,
+};
+
+/* used to initialize the real stat files */
+static struct tracer_stat function_stats __initdata = {
+ .name = "functions",
+ .stat_start = function_stat_start,
+ .stat_next = function_stat_next,
+ .stat_cmp = function_stat_cmp,
+ .stat_headers = function_stat_headers,
+ .stat_show = function_stat_show
+};
+
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+ struct ftrace_profile_stat *stat;
+ struct dentry *entry;
+ char *name;
+ int ret;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ /* allocate enough for function name + cpu number */
+ name = kmalloc(32, GFP_KERNEL);
+ if (!name) {
+ /*
+ * The files created are permanent, if something happens
+ * we still do not free memory.
+ */
+ kfree(stat);
+ WARN(1,
+ "Could not allocate stat file for cpu %d\n",
+ cpu);
+ return;
+ }
+ stat->stat = function_stats;
+ snprintf(name, 32, "function%d", cpu);
+ stat->stat.name = name;
+ ret = register_stat_tracer(&stat->stat);
+ if (ret) {
+ WARN(1,
+ "Could not register function stat for cpu %d\n",
+ cpu);
+ kfree(name);
+ return;
+ }
+ }
+
+ entry = debugfs_create_file("function_profile_enabled", 0644,
+ d_tracer, NULL, &ftrace_profile_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'function_profile_enabled' entry\n");
+}
+
+#else /* CONFIG_FUNCTION_PROFILER */
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+}
+#endif /* CONFIG_FUNCTION_PROFILER */
+
/* set when tracing only a pid */
struct pid *ftrace_pid_trace;
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
struct rcu_head rcu;
};
-
enum {
FTRACE_ENABLE_CALLS = (1 << 0),
FTRACE_DISABLE_CALLS = (1 << 1),
rec->flags |= FTRACE_FL_FREE;
}
-void ftrace_release(void *start, unsigned long size)
-{
- struct dyn_ftrace *rec;
- struct ftrace_page *pg;
- unsigned long s = (unsigned long)start;
- unsigned long e = s + size;
-
- if (ftrace_disabled || !start)
- return;
-
- mutex_lock(&ftrace_lock);
- do_for_each_ftrace_rec(pg, rec) {
- if ((rec->ip >= s) && (rec->ip < e)) {
- /*
- * rec->ip is changed in ftrace_free_rec()
- * It should not between s and e if record was freed.
- */
- FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
- ftrace_free_rec(rec);
- }
- } while_for_each_ftrace_rec();
- mutex_unlock(&ftrace_lock);
-}
-
static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
{
struct dyn_ftrace *rec;
static struct ftrace_ops trace_probe_ops __read_mostly =
{
- .func = function_trace_probe_call,
+ .func = function_trace_probe_call,
};
static int ftrace_probe_registered;
ftrace_set_regex(buf, len, reset, 0);
}
+/*
+ * command line interface to allow users to set filters on boot up.
+ */
+#define FTRACE_FILTER_SIZE COMMAND_LINE_SIZE
+static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
+static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
+
+static int __init set_ftrace_notrace(char *str)
+{
+ strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+ return 1;
+}
+__setup("ftrace_notrace=", set_ftrace_notrace);
+
+static int __init set_ftrace_filter(char *str)
+{
+ strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+ return 1;
+}
+__setup("ftrace_filter=", set_ftrace_filter);
+
+static void __init set_ftrace_early_filter(char *buf, int enable)
+{
+ char *func;
+
+ while (buf) {
+ func = strsep(&buf, ",");
+ ftrace_set_regex(func, strlen(func), 0, enable);
+ }
+}
+
+static void __init set_ftrace_early_filters(void)
+{
+ if (ftrace_filter_buf[0])
+ set_ftrace_early_filter(ftrace_filter_buf, 1);
+ if (ftrace_notrace_buf[0])
+ set_ftrace_early_filter(ftrace_notrace_buf, 0);
+}
+
static int
ftrace_regex_release(struct inode *inode, struct file *file, int enable)
{
static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
{
- struct dentry *entry;
- entry = debugfs_create_file("available_filter_functions", 0444,
- d_tracer, NULL, &ftrace_avail_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'available_filter_functions' entry\n");
+ trace_create_file("available_filter_functions", 0444,
+ d_tracer, NULL, &ftrace_avail_fops);
- entry = debugfs_create_file("failures", 0444,
- d_tracer, NULL, &ftrace_failures_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'failures' entry\n");
+ trace_create_file("failures", 0444,
+ d_tracer, NULL, &ftrace_failures_fops);
- entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer,
- NULL, &ftrace_filter_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_ftrace_filter' entry\n");
+ trace_create_file("set_ftrace_filter", 0644, d_tracer,
+ NULL, &ftrace_filter_fops);
- entry = debugfs_create_file("set_ftrace_notrace", 0644, d_tracer,
+ trace_create_file("set_ftrace_notrace", 0644, d_tracer,
NULL, &ftrace_notrace_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_ftrace_notrace' entry\n");
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- entry = debugfs_create_file("set_graph_function", 0444, d_tracer,
+ trace_create_file("set_graph_function", 0444, d_tracer,
NULL,
&ftrace_graph_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_graph_function' entry\n");
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
return 0;
return 0;
}
-void ftrace_init_module(struct module *mod,
- unsigned long *start, unsigned long *end)
+#ifdef CONFIG_MODULES
+void ftrace_release(void *start, void *end)
+{
+ struct dyn_ftrace *rec;
+ struct ftrace_page *pg;
+ unsigned long s = (unsigned long)start;
+ unsigned long e = (unsigned long)end;
+
+ if (ftrace_disabled || !start || start == end)
+ return;
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+ if ((rec->ip >= s) && (rec->ip < e)) {
+ /*
+ * rec->ip is changed in ftrace_free_rec()
+ * It should not between s and e if record was freed.
+ */
+ FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
+ ftrace_free_rec(rec);
+ }
+ } while_for_each_ftrace_rec();
+ mutex_unlock(&ftrace_lock);
+}
+
+static void ftrace_init_module(struct module *mod,
+ unsigned long *start, unsigned long *end)
{
if (ftrace_disabled || start == end)
return;
ftrace_convert_nops(mod, start, end);
}
+static int ftrace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ ftrace_init_module(mod, mod->ftrace_callsites,
+ mod->ftrace_callsites +
+ mod->num_ftrace_callsites);
+ break;
+ case MODULE_STATE_GOING:
+ ftrace_release(mod->ftrace_callsites,
+ mod->ftrace_callsites +
+ mod->num_ftrace_callsites);
+ break;
+ }
+
+ return 0;
+}
+#else
+static int ftrace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block ftrace_module_nb = {
+ .notifier_call = ftrace_module_notify,
+ .priority = 0,
+};
+
extern unsigned long __start_mcount_loc[];
extern unsigned long __stop_mcount_loc[];
__start_mcount_loc,
__stop_mcount_loc);
+ ret = register_module_notifier(&ftrace_module_nb);
+ if (ret)
+ pr_warning("Failed to register trace ftrace module notifier\n");
+
+ set_ftrace_early_filters();
+
return;
failed:
ftrace_disabled = 1;
static __init int ftrace_init_debugfs(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
if (!d_tracer)
ftrace_init_dyn_debugfs(d_tracer);
- entry = debugfs_create_file("set_ftrace_pid", 0644, d_tracer,
- NULL, &ftrace_pid_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'set_ftrace_pid' entry\n");
+ trace_create_file("set_ftrace_pid", 0644, d_tracer,
+ NULL, &ftrace_pid_fops);
+
+ ftrace_profile_debugfs(d_tracer);
+
return 0;
}
fs_initcall(ftrace_init_debugfs);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static atomic_t ftrace_graph_active;
+static int ftrace_graph_active;
static struct notifier_block ftrace_suspend_notifier;
int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
}
if (t->ret_stack == NULL) {
- t->curr_ret_stack = -1;
- /* Make sure IRQs see the -1 first: */
- barrier();
- t->ret_stack = ret_stack_list[start++];
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
+ t->curr_ret_stack = -1;
+ /* Make sure the tasks see the -1 first: */
+ smp_wmb();
+ t->ret_stack = ret_stack_list[start++];
}
} while_each_thread(g, t);
return -ENOMEM;
/* The cpu_boot init_task->ret_stack will never be freed */
- for_each_online_cpu(cpu)
- ftrace_graph_init_task(idle_task(cpu));
+ for_each_online_cpu(cpu) {
+ if (!idle_task(cpu)->ret_stack)
+ ftrace_graph_init_task(idle_task(cpu));
+ }
do {
ret = alloc_retstack_tasklist(ret_stack_list);
mutex_lock(&ftrace_lock);
/* we currently allow only one tracer registered at a time */
- if (atomic_read(&ftrace_graph_active)) {
+ if (ftrace_graph_active) {
ret = -EBUSY;
goto out;
}
ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
register_pm_notifier(&ftrace_suspend_notifier);
- atomic_inc(&ftrace_graph_active);
+ ftrace_graph_active++;
ret = start_graph_tracing();
if (ret) {
- atomic_dec(&ftrace_graph_active);
+ ftrace_graph_active--;
goto out;
}
{
mutex_lock(&ftrace_lock);
- if (!unlikely(atomic_read(&ftrace_graph_active)))
+ if (unlikely(!ftrace_graph_active))
goto out;
- atomic_dec(&ftrace_graph_active);
+ ftrace_graph_active--;
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
ftrace_graph_entry = ftrace_graph_entry_stub;
/* Allocate a return stack for newly created task */
void ftrace_graph_init_task(struct task_struct *t)
{
- if (atomic_read(&ftrace_graph_active)) {
- t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+ /* Make sure we do not use the parent ret_stack */
+ t->ret_stack = NULL;
+
+ if (ftrace_graph_active) {
+ struct ftrace_ret_stack *ret_stack;
+
+ ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
* sizeof(struct ftrace_ret_stack),
GFP_KERNEL);
- if (!t->ret_stack)
+ if (!ret_stack)
return;
t->curr_ret_stack = -1;
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
t->ftrace_timestamp = 0;
- } else
- t->ret_stack = NULL;
+ /* make curr_ret_stack visable before we add the ret_stack */
+ smp_wmb();
+ t->ret_stack = ret_stack;
+ }
}
void ftrace_graph_exit_task(struct task_struct *t)
#include <linux/dcache.h>
#include <linux/fs.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
#include "trace_output.h"
#include "trace.h"
gfp_t gfp_flags,
int node)
{
+ struct ftrace_event_call *call = &event_kmem_alloc;
struct trace_array *tr = kmemtrace_array;
struct kmemtrace_alloc_entry *entry;
struct ring_buffer_event *event;
entry->gfp_flags = gfp_flags;
entry->node = node;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
trace_wake_up();
}
unsigned long call_site,
const void *ptr)
{
+ struct ftrace_event_call *call = &event_kmem_free;
struct trace_array *tr = kmemtrace_array;
struct kmemtrace_free_entry *entry;
struct ring_buffer_event *event;
entry->call_site = call_site;
entry->ptr = ptr;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
trace_wake_up();
}
#include "trace.h"
+/*
+ * The ring buffer header is special. We must manually up keep it.
+ */
+int ring_buffer_print_entry_header(struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_seq_printf(s, "# compressed entry header\n");
+ ret = trace_seq_printf(s, "\ttype_len : 5 bits\n");
+ ret = trace_seq_printf(s, "\ttime_delta : 27 bits\n");
+ ret = trace_seq_printf(s, "\tarray : 32 bits\n");
+ ret = trace_seq_printf(s, "\n");
+ ret = trace_seq_printf(s, "\tpadding : type == %d\n",
+ RINGBUF_TYPE_PADDING);
+ ret = trace_seq_printf(s, "\ttime_extend : type == %d\n",
+ RINGBUF_TYPE_TIME_EXTEND);
+ ret = trace_seq_printf(s, "\tdata max type_len == %d\n",
+ RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+
+ return ret;
+}
+
/*
* The ring buffer is made up of a list of pages. A separate list of pages is
* allocated for each CPU. A writer may only write to a buffer that is
#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
#define RB_ALIGNMENT 4U
-#define RB_MAX_SMALL_DATA 28
+#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+
+/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
+#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
enum {
RB_LEN_TIME_EXTEND = 8,
static inline int rb_null_event(struct ring_buffer_event *event)
{
- return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+ return event->type_len == RINGBUF_TYPE_PADDING
+ && event->time_delta == 0;
}
static inline int rb_discarded_event(struct ring_buffer_event *event)
{
- return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+ return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
}
static void rb_event_set_padding(struct ring_buffer_event *event)
{
- event->type = RINGBUF_TYPE_PADDING;
+ event->type_len = RINGBUF_TYPE_PADDING;
event->time_delta = 0;
}
-/**
- * ring_buffer_event_discard - discard an event in the ring buffer
- * @buffer: the ring buffer
- * @event: the event to discard
- *
- * Sometimes a event that is in the ring buffer needs to be ignored.
- * This function lets the user discard an event in the ring buffer
- * and then that event will not be read later.
- *
- * Note, it is up to the user to be careful with this, and protect
- * against races. If the user discards an event that has been consumed
- * it is possible that it could corrupt the ring buffer.
- */
-void ring_buffer_event_discard(struct ring_buffer_event *event)
-{
- event->type = RINGBUF_TYPE_PADDING;
- /* time delta must be non zero */
- if (!event->time_delta)
- event->time_delta = 1;
-}
-
static unsigned
rb_event_data_length(struct ring_buffer_event *event)
{
unsigned length;
- if (event->len)
- length = event->len * RB_ALIGNMENT;
+ if (event->type_len)
+ length = event->type_len * RB_ALIGNMENT;
else
length = event->array[0];
return length + RB_EVNT_HDR_SIZE;
static unsigned
rb_event_length(struct ring_buffer_event *event)
{
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
if (rb_null_event(event))
/* undefined */
return -1;
- return rb_event_data_length(event);
+ return event->array[0] + RB_EVNT_HDR_SIZE;
case RINGBUF_TYPE_TIME_EXTEND:
return RB_LEN_TIME_EXTEND;
unsigned ring_buffer_event_length(struct ring_buffer_event *event)
{
unsigned length = rb_event_length(event);
- if (event->type != RINGBUF_TYPE_DATA)
+ if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
return length;
length -= RB_EVNT_HDR_SIZE;
if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
static void *
rb_event_data(struct ring_buffer_event *event)
{
- BUG_ON(event->type != RINGBUF_TYPE_DATA);
+ BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
/* If length is in len field, then array[0] has the data */
- if (event->len)
+ if (event->type_len)
return (void *)&event->array[0];
/* Otherwise length is in array[0] and array[1] has the data */
return (void *)&event->array[1];
};
struct buffer_page {
+ struct list_head list; /* list of buffer pages */
local_t write; /* index for next write */
unsigned read; /* index for next read */
- struct list_head list; /* list of free pages */
+ local_t entries; /* entries on this page */
struct buffer_data_page *page; /* Actual data page */
};
#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
+/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
+#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
+
+/* Max number of timestamps that can fit on a page */
+#define RB_TIMESTAMPS_PER_PAGE (BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
+
+int ring_buffer_print_page_header(struct trace_seq *s)
+{
+ struct buffer_data_page field;
+ int ret;
+
+ ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+ "offset:0;\tsize:%u;\n",
+ (unsigned int)sizeof(field.time_stamp));
+
+ ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
+ "offset:%u;\tsize:%u;\n",
+ (unsigned int)offsetof(typeof(field), commit),
+ (unsigned int)sizeof(field.commit));
+
+ ret = trace_seq_printf(s, "\tfield: char data;\t"
+ "offset:%u;\tsize:%u;\n",
+ (unsigned int)offsetof(typeof(field), data),
+ (unsigned int)BUF_PAGE_SIZE);
+
+ return ret;
+}
+
/*
* head_page == tail_page && head == tail then buffer is empty.
*/
struct buffer_page *tail_page; /* write to tail */
struct buffer_page *commit_page; /* committed pages */
struct buffer_page *reader_page;
+ unsigned long nmi_dropped;
+ unsigned long commit_overrun;
unsigned long overrun;
- unsigned long entries;
+ unsigned long read;
+ local_t entries;
u64 write_stamp;
u64 read_stamp;
atomic_t record_disabled;
atomic_t record_disabled;
cpumask_var_t cpumask;
+ struct lock_class_key *reader_lock_key;
+
struct mutex mutex;
struct ring_buffer_per_cpu **buffers;
/* Up this if you want to test the TIME_EXTENTS and normalization */
#define DEBUG_SHIFT 0
+static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu)
+{
+ /* shift to debug/test normalization and TIME_EXTENTS */
+ return buffer->clock() << DEBUG_SHIFT;
+}
+
u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
{
u64 time;
preempt_disable_notrace();
- /* shift to debug/test normalization and TIME_EXTENTS */
- time = buffer->clock() << DEBUG_SHIFT;
+ time = rb_time_stamp(buffer, cpu);
preempt_enable_no_resched_notrace();
return time;
cpu_buffer->cpu = cpu;
cpu_buffer->buffer = buffer;
spin_lock_init(&cpu_buffer->reader_lock);
+ lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
INIT_LIST_HEAD(&cpu_buffer->pages);
* when the buffer wraps. If this flag is not set, the buffer will
* drop data when the tail hits the head.
*/
-struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
+struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
+ struct lock_class_key *key)
{
struct ring_buffer *buffer;
int bsize;
buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
buffer->flags = flags;
buffer->clock = trace_clock_local;
+ buffer->reader_lock_key = key;
/* need at least two pages */
if (buffer->pages == 1)
kfree(buffer);
return NULL;
}
-EXPORT_SYMBOL_GPL(ring_buffer_alloc);
+EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
/**
* ring_buffer_free - free a ring buffer.
return rb_page_commit(cpu_buffer->head_page);
}
-/*
- * When the tail hits the head and the buffer is in overwrite mode,
- * the head jumps to the next page and all content on the previous
- * page is discarded. But before doing so, we update the overrun
- * variable of the buffer.
- */
-static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
-{
- struct ring_buffer_event *event;
- unsigned long head;
-
- for (head = 0; head < rb_head_size(cpu_buffer);
- head += rb_event_length(event)) {
-
- event = __rb_page_index(cpu_buffer->head_page, head);
- if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
- return;
- /* Only count data entries */
- if (event->type != RINGBUF_TYPE_DATA)
- continue;
- cpu_buffer->overrun++;
- cpu_buffer->entries--;
- }
-}
-
static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
struct buffer_page **bpage)
{
return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
}
-static int
+static inline int
rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
rb_update_event(struct ring_buffer_event *event,
unsigned type, unsigned length)
{
- event->type = type;
+ event->type_len = type;
switch (type) {
case RINGBUF_TYPE_PADDING:
- break;
-
case RINGBUF_TYPE_TIME_EXTEND:
- event->len = DIV_ROUND_UP(RB_LEN_TIME_EXTEND, RB_ALIGNMENT);
- break;
-
case RINGBUF_TYPE_TIME_STAMP:
- event->len = DIV_ROUND_UP(RB_LEN_TIME_STAMP, RB_ALIGNMENT);
break;
- case RINGBUF_TYPE_DATA:
+ case 0:
length -= RB_EVNT_HDR_SIZE;
- if (length > RB_MAX_SMALL_DATA) {
- event->len = 0;
+ if (length > RB_MAX_SMALL_DATA)
event->array[0] = length;
- } else
- event->len = DIV_ROUND_UP(length, RB_ALIGNMENT);
+ else
+ event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
break;
default:
BUG();
return length;
}
+
static struct ring_buffer_event *
-__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned type, unsigned long length, u64 *ts)
+rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned long length, unsigned long tail,
+ struct buffer_page *commit_page,
+ struct buffer_page *tail_page, u64 *ts)
{
- struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
- unsigned long tail, write;
+ struct buffer_page *next_page, *head_page, *reader_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct ring_buffer_event *event;
- unsigned long flags;
bool lock_taken = false;
+ unsigned long flags;
- commit_page = cpu_buffer->commit_page;
- /* we just need to protect against interrupts */
- barrier();
- tail_page = cpu_buffer->tail_page;
- write = local_add_return(length, &tail_page->write);
- tail = write - length;
+ next_page = tail_page;
- /* See if we shot pass the end of this buffer page */
- if (write > BUF_PAGE_SIZE) {
- struct buffer_page *next_page = tail_page;
+ local_irq_save(flags);
+ /*
+ * Since the write to the buffer is still not
+ * fully lockless, we must be careful with NMIs.
+ * The locks in the writers are taken when a write
+ * crosses to a new page. The locks protect against
+ * races with the readers (this will soon be fixed
+ * with a lockless solution).
+ *
+ * Because we can not protect against NMIs, and we
+ * want to keep traces reentrant, we need to manage
+ * what happens when we are in an NMI.
+ *
+ * NMIs can happen after we take the lock.
+ * If we are in an NMI, only take the lock
+ * if it is not already taken. Otherwise
+ * simply fail.
+ */
+ if (unlikely(in_nmi())) {
+ if (!__raw_spin_trylock(&cpu_buffer->lock)) {
+ cpu_buffer->nmi_dropped++;
+ goto out_reset;
+ }
+ } else
+ __raw_spin_lock(&cpu_buffer->lock);
- local_irq_save(flags);
- /*
- * Since the write to the buffer is still not
- * fully lockless, we must be careful with NMIs.
- * The locks in the writers are taken when a write
- * crosses to a new page. The locks protect against
- * races with the readers (this will soon be fixed
- * with a lockless solution).
- *
- * Because we can not protect against NMIs, and we
- * want to keep traces reentrant, we need to manage
- * what happens when we are in an NMI.
- *
- * NMIs can happen after we take the lock.
- * If we are in an NMI, only take the lock
- * if it is not already taken. Otherwise
- * simply fail.
- */
- if (unlikely(in_nmi())) {
- if (!__raw_spin_trylock(&cpu_buffer->lock))
- goto out_reset;
- } else
- __raw_spin_lock(&cpu_buffer->lock);
+ lock_taken = true;
- lock_taken = true;
+ rb_inc_page(cpu_buffer, &next_page);
- rb_inc_page(cpu_buffer, &next_page);
+ head_page = cpu_buffer->head_page;
+ reader_page = cpu_buffer->reader_page;
- head_page = cpu_buffer->head_page;
- reader_page = cpu_buffer->reader_page;
+ /* we grabbed the lock before incrementing */
+ if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+ goto out_reset;
- /* we grabbed the lock before incrementing */
- if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
- goto out_reset;
+ /*
+ * If for some reason, we had an interrupt storm that made
+ * it all the way around the buffer, bail, and warn
+ * about it.
+ */
+ if (unlikely(next_page == commit_page)) {
+ cpu_buffer->commit_overrun++;
+ goto out_reset;
+ }
- /*
- * If for some reason, we had an interrupt storm that made
- * it all the way around the buffer, bail, and warn
- * about it.
- */
- if (unlikely(next_page == commit_page)) {
- WARN_ON_ONCE(1);
+ if (next_page == head_page) {
+ if (!(buffer->flags & RB_FL_OVERWRITE))
goto out_reset;
- }
- if (next_page == head_page) {
- if (!(buffer->flags & RB_FL_OVERWRITE))
- goto out_reset;
-
- /* tail_page has not moved yet? */
- if (tail_page == cpu_buffer->tail_page) {
- /* count overflows */
- rb_update_overflow(cpu_buffer);
+ /* tail_page has not moved yet? */
+ if (tail_page == cpu_buffer->tail_page) {
+ /* count overflows */
+ cpu_buffer->overrun +=
+ local_read(&head_page->entries);
- rb_inc_page(cpu_buffer, &head_page);
- cpu_buffer->head_page = head_page;
- cpu_buffer->head_page->read = 0;
- }
+ rb_inc_page(cpu_buffer, &head_page);
+ cpu_buffer->head_page = head_page;
+ cpu_buffer->head_page->read = 0;
}
+ }
- /*
- * If the tail page is still the same as what we think
- * it is, then it is up to us to update the tail
- * pointer.
- */
- if (tail_page == cpu_buffer->tail_page) {
- local_set(&next_page->write, 0);
- local_set(&next_page->page->commit, 0);
- cpu_buffer->tail_page = next_page;
+ /*
+ * If the tail page is still the same as what we think
+ * it is, then it is up to us to update the tail
+ * pointer.
+ */
+ if (tail_page == cpu_buffer->tail_page) {
+ local_set(&next_page->write, 0);
+ local_set(&next_page->entries, 0);
+ local_set(&next_page->page->commit, 0);
+ cpu_buffer->tail_page = next_page;
+
+ /* reread the time stamp */
+ *ts = rb_time_stamp(buffer, cpu_buffer->cpu);
+ cpu_buffer->tail_page->page->time_stamp = *ts;
+ }
- /* reread the time stamp */
- *ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
- cpu_buffer->tail_page->page->time_stamp = *ts;
- }
+ /*
+ * The actual tail page has moved forward.
+ */
+ if (tail < BUF_PAGE_SIZE) {
+ /* Mark the rest of the page with padding */
+ event = __rb_page_index(tail_page, tail);
+ rb_event_set_padding(event);
+ }
- /*
- * The actual tail page has moved forward.
- */
- if (tail < BUF_PAGE_SIZE) {
- /* Mark the rest of the page with padding */
- event = __rb_page_index(tail_page, tail);
- rb_event_set_padding(event);
- }
+ /* Set the write back to the previous setting */
+ local_sub(length, &tail_page->write);
- if (tail <= BUF_PAGE_SIZE)
- /* Set the write back to the previous setting */
- local_set(&tail_page->write, tail);
+ /*
+ * If this was a commit entry that failed,
+ * increment that too
+ */
+ if (tail_page == cpu_buffer->commit_page &&
+ tail == rb_commit_index(cpu_buffer)) {
+ rb_set_commit_to_write(cpu_buffer);
+ }
- /*
- * If this was a commit entry that failed,
- * increment that too
- */
- if (tail_page == cpu_buffer->commit_page &&
- tail == rb_commit_index(cpu_buffer)) {
- rb_set_commit_to_write(cpu_buffer);
- }
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ /* fail and let the caller try again */
+ return ERR_PTR(-EAGAIN);
+
+ out_reset:
+ /* reset write */
+ local_sub(length, &tail_page->write);
+ if (likely(lock_taken))
__raw_spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
+ local_irq_restore(flags);
+ return NULL;
+}
- /* fail and let the caller try again */
- return ERR_PTR(-EAGAIN);
- }
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned type, unsigned long length, u64 *ts)
+{
+ struct buffer_page *tail_page, *commit_page;
+ struct ring_buffer_event *event;
+ unsigned long tail, write;
+
+ commit_page = cpu_buffer->commit_page;
+ /* we just need to protect against interrupts */
+ barrier();
+ tail_page = cpu_buffer->tail_page;
+ write = local_add_return(length, &tail_page->write);
+ tail = write - length;
+
+ /* See if we shot pass the end of this buffer page */
+ if (write > BUF_PAGE_SIZE)
+ return rb_move_tail(cpu_buffer, length, tail,
+ commit_page, tail_page, ts);
/* We reserved something on the buffer */
event = __rb_page_index(tail_page, tail);
rb_update_event(event, type, length);
+ /* The passed in type is zero for DATA */
+ if (likely(!type))
+ local_inc(&tail_page->entries);
+
/*
* If this is a commit and the tail is zero, then update
* this page's time stamp.
cpu_buffer->commit_page->page->time_stamp = *ts;
return event;
+}
- out_reset:
- /* reset write */
- if (tail <= BUF_PAGE_SIZE)
- local_set(&tail_page->write, tail);
+static inline int
+rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ unsigned long new_index, old_index;
+ struct buffer_page *bpage;
+ unsigned long index;
+ unsigned long addr;
- if (likely(lock_taken))
- __raw_spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
- return NULL;
+ new_index = rb_event_index(event);
+ old_index = new_index + rb_event_length(event);
+ addr = (unsigned long)event;
+ addr &= PAGE_MASK;
+
+ bpage = cpu_buffer->tail_page;
+
+ if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+ /*
+ * This is on the tail page. It is possible that
+ * a write could come in and move the tail page
+ * and write to the next page. That is fine
+ * because we just shorten what is on this page.
+ */
+ index = local_cmpxchg(&bpage->write, old_index, new_index);
+ if (index == old_index)
+ return 1;
+ }
+
+ /* could not discard */
+ return 0;
}
static int
event->array[0] = *delta >> TS_SHIFT;
} else {
cpu_buffer->commit_page->page->time_stamp = *ts;
- event->time_delta = 0;
- event->array[0] = 0;
+ /* try to discard, since we do not need this */
+ if (!rb_try_to_discard(cpu_buffer, event)) {
+ /* nope, just zero it */
+ event->time_delta = 0;
+ event->array[0] = 0;
+ }
}
cpu_buffer->write_stamp = *ts;
/* let the caller know this was the commit */
ret = 1;
} else {
- /* Darn, this is just wasted space */
- event->time_delta = 0;
- event->array[0] = 0;
+ /* Try to discard the event */
+ if (!rb_try_to_discard(cpu_buffer, event)) {
+ /* Darn, this is just wasted space */
+ event->time_delta = 0;
+ event->array[0] = 0;
+ }
ret = 0;
}
static struct ring_buffer_event *
rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned type, unsigned long length)
+ unsigned long length)
{
struct ring_buffer_event *event;
- u64 ts, delta;
+ u64 ts, delta = 0;
int commit = 0;
int nr_loops = 0;
+ length = rb_calculate_event_length(length);
again:
/*
* We allow for interrupts to reenter here and do a trace.
if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
return NULL;
- ts = ring_buffer_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
+ ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
/*
* Only the first commit can update the timestamp.
* also be made. But only the entry that did the actual
* commit will be something other than zero.
*/
- if (cpu_buffer->tail_page == cpu_buffer->commit_page &&
- rb_page_write(cpu_buffer->tail_page) ==
- rb_commit_index(cpu_buffer)) {
+ if (likely(cpu_buffer->tail_page == cpu_buffer->commit_page &&
+ rb_page_write(cpu_buffer->tail_page) ==
+ rb_commit_index(cpu_buffer))) {
+ u64 diff;
- delta = ts - cpu_buffer->write_stamp;
+ diff = ts - cpu_buffer->write_stamp;
- /* make sure this delta is calculated here */
+ /* make sure this diff is calculated here */
barrier();
/* Did the write stamp get updated already? */
if (unlikely(ts < cpu_buffer->write_stamp))
- delta = 0;
+ goto get_event;
- if (test_time_stamp(delta)) {
+ delta = diff;
+ if (unlikely(test_time_stamp(delta))) {
commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
-
if (commit == -EBUSY)
return NULL;
RB_WARN_ON(cpu_buffer, commit < 0);
}
- } else
- /* Non commits have zero deltas */
- delta = 0;
+ }
- event = __rb_reserve_next(cpu_buffer, type, length, &ts);
- if (PTR_ERR(event) == -EAGAIN)
+ get_event:
+ event = __rb_reserve_next(cpu_buffer, 0, length, &ts);
+ if (unlikely(PTR_ERR(event) == -EAGAIN))
goto again;
if (!event) {
* If the timestamp was commited, make the commit our entry
* now so that we will update it when needed.
*/
- if (commit)
+ if (unlikely(commit))
rb_set_commit_event(cpu_buffer, event);
else if (!rb_is_commit(cpu_buffer, event))
delta = 0;
return event;
}
+#define TRACE_RECURSIVE_DEPTH 16
+
+static int trace_recursive_lock(void)
+{
+ current->trace_recursion++;
+
+ if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+ return 0;
+
+ /* Disable all tracing before we do anything else */
+ tracing_off_permanent();
+
+ printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
+ "HC[%lu]:SC[%lu]:NMI[%lu]\n",
+ current->trace_recursion,
+ hardirq_count() >> HARDIRQ_SHIFT,
+ softirq_count() >> SOFTIRQ_SHIFT,
+ in_nmi());
+
+ WARN_ON_ONCE(1);
+ return -1;
+}
+
+static void trace_recursive_unlock(void)
+{
+ WARN_ON_ONCE(!current->trace_recursion);
+
+ current->trace_recursion--;
+}
+
static DEFINE_PER_CPU(int, rb_need_resched);
/**
/* If we are tracing schedule, we don't want to recurse */
resched = ftrace_preempt_disable();
+ if (trace_recursive_lock())
+ goto out_nocheck;
+
cpu = raw_smp_processor_id();
if (!cpumask_test_cpu(cpu, buffer->cpumask))
if (atomic_read(&cpu_buffer->record_disabled))
goto out;
- length = rb_calculate_event_length(length);
- if (length > BUF_PAGE_SIZE)
+ if (length > BUF_MAX_DATA_SIZE)
goto out;
- event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
+ event = rb_reserve_next_event(cpu_buffer, length);
if (!event)
goto out;
return event;
out:
+ trace_recursive_unlock();
+
+ out_nocheck:
ftrace_preempt_enable(resched);
return NULL;
}
static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
- cpu_buffer->entries++;
+ local_inc(&cpu_buffer->entries);
/* Only process further if we own the commit */
if (!rb_is_commit(cpu_buffer, event))
rb_commit(cpu_buffer, event);
+ trace_recursive_unlock();
+
/*
* Only the last preempt count needs to restore preemption.
*/
}
EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
+static inline void rb_event_discard(struct ring_buffer_event *event)
+{
+ /* array[0] holds the actual length for the discarded event */
+ event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
+ event->type_len = RINGBUF_TYPE_PADDING;
+ /* time delta must be non zero */
+ if (!event->time_delta)
+ event->time_delta = 1;
+}
+
+/**
+ * ring_buffer_event_discard - discard any event in the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+ rb_event_discard(event);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
+
+/**
+ * ring_buffer_commit_discard - discard an event that has not been committed
+ * @buffer: the ring buffer
+ * @event: non committed event to discard
+ *
+ * This is similar to ring_buffer_event_discard but must only be
+ * performed on an event that has not been committed yet. The difference
+ * is that this will also try to free the event from the ring buffer
+ * if another event has not been added behind it.
+ *
+ * If another event has been added behind it, it will set the event
+ * up as discarded, and perform the commit.
+ *
+ * If this function is called, do not call ring_buffer_unlock_commit on
+ * the event.
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ int cpu;
+
+ /* The event is discarded regardless */
+ rb_event_discard(event);
+
+ /*
+ * This must only be called if the event has not been
+ * committed yet. Thus we can assume that preemption
+ * is still disabled.
+ */
+ RB_WARN_ON(buffer, preemptible());
+
+ cpu = smp_processor_id();
+ cpu_buffer = buffer->buffers[cpu];
+
+ if (!rb_try_to_discard(cpu_buffer, event))
+ goto out;
+
+ /*
+ * The commit is still visible by the reader, so we
+ * must increment entries.
+ */
+ local_inc(&cpu_buffer->entries);
+ out:
+ /*
+ * If a write came in and pushed the tail page
+ * we still need to update the commit pointer
+ * if we were the commit.
+ */
+ if (rb_is_commit(cpu_buffer, event))
+ rb_set_commit_to_write(cpu_buffer);
+
+ trace_recursive_unlock();
+
+ /*
+ * Only the last preempt count needs to restore preemption.
+ */
+ if (preempt_count() == 1)
+ ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+ else
+ preempt_enable_no_resched_notrace();
+
+}
+EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
+
/**
* ring_buffer_write - write data to the buffer without reserving
* @buffer: The ring buffer to write to.
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
- unsigned long event_length;
void *body;
int ret = -EBUSY;
int cpu, resched;
if (atomic_read(&cpu_buffer->record_disabled))
goto out;
- event_length = rb_calculate_event_length(length);
- event = rb_reserve_next_event(cpu_buffer,
- RINGBUF_TYPE_DATA, event_length);
+ if (length > BUF_MAX_DATA_SIZE)
+ goto out;
+
+ event = rb_reserve_next_event(cpu_buffer, length);
if (!event)
goto out;
return 0;
cpu_buffer = buffer->buffers[cpu];
- ret = cpu_buffer->entries;
+ ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+ - cpu_buffer->read;
return ret;
}
}
EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
+/**
+ * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = cpu_buffer->nmi_dropped;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
+
+/**
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = cpu_buffer->commit_overrun;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
+
/**
* ring_buffer_entries - get the number of entries in a buffer
* @buffer: The ring buffer
/* if you care about this being correct, lock the buffer */
for_each_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
- entries += cpu_buffer->entries;
+ entries += (local_read(&cpu_buffer->entries) -
+ cpu_buffer->overrun) - cpu_buffer->read;
}
return entries;
{
u64 delta;
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
return;
{
u64 delta;
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
return;
cpu_buffer->reader_page->list.prev = reader->list.prev;
local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->entries, 0);
local_set(&cpu_buffer->reader_page->page->commit, 0);
/* Make the reader page now replace the head */
event = rb_reader_event(cpu_buffer);
- if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
- cpu_buffer->entries--;
+ if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
+ || rb_discarded_event(event))
+ cpu_buffer->read++;
rb_update_read_stamp(cpu_buffer, event);
* Check if we are at the end of the buffer.
*/
if (iter->head >= rb_page_size(iter->head_page)) {
- if (RB_WARN_ON(buffer,
- iter->head_page == cpu_buffer->commit_page))
+ /* discarded commits can make the page empty */
+ if (iter->head_page == cpu_buffer->commit_page)
return;
rb_inc_iter(iter);
return;
/*
* We repeat when a timestamp is encountered. It is possible
* to get multiple timestamps from an interrupt entering just
- * as one timestamp is about to be written. The max times
- * that this can happen is the number of nested interrupts we
- * can have. Nesting 10 deep of interrupts is clearly
- * an anomaly.
+ * as one timestamp is about to be written, or from discarded
+ * commits. The most that we can have is the number on a single page.
*/
- if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
return NULL;
reader = rb_get_reader_page(cpu_buffer);
event = rb_reader_event(cpu_buffer);
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
if (rb_null_event(event))
RB_WARN_ON(cpu_buffer, 1);
again:
/*
- * We repeat when a timestamp is encountered. It is possible
- * to get multiple timestamps from an interrupt entering just
- * as one timestamp is about to be written. The max times
- * that this can happen is the number of nested interrupts we
- * can have. Nesting 10 deep of interrupts is clearly
- * an anomaly.
+ * We repeat when a timestamp is encountered.
+ * We can get multiple timestamps by nested interrupts or also
+ * if filtering is on (discarding commits). Since discarding
+ * commits can be frequent we can get a lot of timestamps.
+ * But we limit them by not adding timestamps if they begin
+ * at the start of a page.
*/
- if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
return NULL;
if (rb_per_cpu_empty(cpu_buffer))
event = rb_iter_head_event(iter);
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
if (rb_null_event(event)) {
rb_inc_iter(iter);
event = rb_buffer_peek(buffer, cpu, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
event = rb_iter_peek(iter, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
out:
preempt_enable();
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
out:
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
- if (event && event->type == RINGBUF_TYPE_PADDING) {
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
cpu_relax();
goto again;
}
cpu_buffer->head_page
= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
local_set(&cpu_buffer->head_page->write, 0);
+ local_set(&cpu_buffer->head_page->entries, 0);
local_set(&cpu_buffer->head_page->page->commit, 0);
cpu_buffer->head_page->read = 0;
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->entries, 0);
local_set(&cpu_buffer->reader_page->page->commit, 0);
cpu_buffer->reader_page->read = 0;
+ cpu_buffer->nmi_dropped = 0;
+ cpu_buffer->commit_overrun = 0;
cpu_buffer->overrun = 0;
- cpu_buffer->entries = 0;
+ cpu_buffer->read = 0;
+ local_set(&cpu_buffer->entries, 0);
cpu_buffer->write_stamp = 0;
cpu_buffer->read_stamp = 0;
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return;
+ atomic_inc(&cpu_buffer->record_disabled);
+
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
__raw_spin_lock(&cpu_buffer->lock);
__raw_spin_unlock(&cpu_buffer->lock);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ atomic_dec(&cpu_buffer->record_disabled);
}
EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
}
EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
-static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
- struct buffer_data_page *bpage,
- unsigned int offset)
-{
- struct ring_buffer_event *event;
- unsigned long head;
-
- __raw_spin_lock(&cpu_buffer->lock);
- for (head = offset; head < local_read(&bpage->commit);
- head += rb_event_length(event)) {
-
- event = __rb_data_page_index(bpage, head);
- if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
- return;
- /* Only count data entries */
- if (event->type != RINGBUF_TYPE_DATA)
- continue;
- cpu_buffer->entries--;
- }
- __raw_spin_unlock(&cpu_buffer->lock);
-}
-
/**
* ring_buffer_alloc_read_page - allocate a page to read from buffer
* @buffer: the buffer to allocate for.
return bpage;
}
+EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
/**
* ring_buffer_free_read_page - free an allocated read page
{
free_page((unsigned long)data);
}
+EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
/**
* ring_buffer_read_page - extract a page from the ring buffer
/* we copied everything to the beginning */
read = 0;
} else {
+ /* update the entry counter */
+ cpu_buffer->read += local_read(&reader->entries);
+
/* swap the pages */
rb_init_page(bpage);
bpage = reader->page;
reader->page = *data_page;
local_set(&reader->write, 0);
+ local_set(&reader->entries, 0);
reader->read = 0;
*data_page = bpage;
-
- /* update the entry counter */
- rb_remove_entries(cpu_buffer, bpage, read);
}
ret = read;
out:
return ret;
}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page);
static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
static __init int rb_init_debugfs(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
- entry = debugfs_create_file("tracing_on", 0644, d_tracer,
- &ring_buffer_flags, &rb_simple_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'tracing_on' entry\n");
+ trace_create_file("tracing_on", 0644, d_tracer,
+ &ring_buffer_flags, &rb_simple_fops);
return 0;
}
--- /dev/null
+/*
+ * ring buffer tester and benchmark
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/time.h>
+
+struct rb_page {
+ u64 ts;
+ local_t commit;
+ char data[4080];
+};
+
+/* run time and sleep time in seconds */
+#define RUN_TIME 10
+#define SLEEP_TIME 10
+
+/* number of events for writer to wake up the reader */
+static int wakeup_interval = 100;
+
+static int reader_finish;
+static struct completion read_start;
+static struct completion read_done;
+
+static struct ring_buffer *buffer;
+static struct task_struct *producer;
+static struct task_struct *consumer;
+static unsigned long read;
+
+static int disable_reader;
+module_param(disable_reader, uint, 0644);
+MODULE_PARM_DESC(disable_reader, "only run producer");
+
+static int read_events;
+
+static int kill_test;
+
+#define KILL_TEST() \
+ do { \
+ if (!kill_test) { \
+ kill_test = 1; \
+ WARN_ON(1); \
+ } \
+ } while (0)
+
+enum event_status {
+ EVENT_FOUND,
+ EVENT_DROPPED,
+};
+
+static enum event_status read_event(int cpu)
+{
+ struct ring_buffer_event *event;
+ int *entry;
+ u64 ts;
+
+ event = ring_buffer_consume(buffer, cpu, &ts);
+ if (!event)
+ return EVENT_DROPPED;
+
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ return EVENT_DROPPED;
+ }
+
+ read++;
+ return EVENT_FOUND;
+}
+
+static enum event_status read_page(int cpu)
+{
+ struct ring_buffer_event *event;
+ struct rb_page *rpage;
+ unsigned long commit;
+ void *bpage;
+ int *entry;
+ int ret;
+ int inc;
+ int i;
+
+ bpage = ring_buffer_alloc_read_page(buffer);
+ if (!bpage)
+ return EVENT_DROPPED;
+
+ ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+ if (ret >= 0) {
+ rpage = bpage;
+ commit = local_read(&rpage->commit);
+ for (i = 0; i < commit && !kill_test; i += inc) {
+
+ if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+ KILL_TEST();
+ break;
+ }
+
+ inc = -1;
+ event = (void *)&rpage->data[i];
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ /* We don't expect any padding */
+ KILL_TEST();
+ break;
+ case RINGBUF_TYPE_TIME_EXTEND:
+ inc = 8;
+ break;
+ case 0:
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ break;
+ }
+ read++;
+ if (!event->array[0]) {
+ KILL_TEST();
+ break;
+ }
+ inc = event->array[0];
+ break;
+ default:
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ break;
+ }
+ read++;
+ inc = ((event->type_len + 1) * 4);
+ }
+ if (kill_test)
+ break;
+
+ if (inc <= 0) {
+ KILL_TEST();
+ break;
+ }
+ }
+ }
+ ring_buffer_free_read_page(buffer, bpage);
+
+ if (ret < 0)
+ return EVENT_DROPPED;
+ return EVENT_FOUND;
+}
+
+static void ring_buffer_consumer(void)
+{
+ /* toggle between reading pages and events */
+ read_events ^= 1;
+
+ read = 0;
+ while (!reader_finish && !kill_test) {
+ int found;
+
+ do {
+ int cpu;
+
+ found = 0;
+ for_each_online_cpu(cpu) {
+ enum event_status stat;
+
+ if (read_events)
+ stat = read_event(cpu);
+ else
+ stat = read_page(cpu);
+
+ if (kill_test)
+ break;
+ if (stat == EVENT_FOUND)
+ found = 1;
+ }
+ } while (found && !kill_test);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (reader_finish)
+ break;
+
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+ reader_finish = 0;
+ complete(&read_done);
+}
+
+static void ring_buffer_producer(void)
+{
+ struct timeval start_tv;
+ struct timeval end_tv;
+ unsigned long long time;
+ unsigned long long entries;
+ unsigned long long overruns;
+ unsigned long missed = 0;
+ unsigned long hit = 0;
+ unsigned long avg;
+ int cnt = 0;
+
+ /*
+ * Hammer the buffer for 10 secs (this may
+ * make the system stall)
+ */
+ pr_info("Starting ring buffer hammer\n");
+ do_gettimeofday(&start_tv);
+ do {
+ struct ring_buffer_event *event;
+ int *entry;
+
+ event = ring_buffer_lock_reserve(buffer, 10);
+ if (!event) {
+ missed++;
+ } else {
+ hit++;
+ entry = ring_buffer_event_data(event);
+ *entry = smp_processor_id();
+ ring_buffer_unlock_commit(buffer, event);
+ }
+ do_gettimeofday(&end_tv);
+
+ cnt++;
+ if (consumer && !(cnt % wakeup_interval))
+ wake_up_process(consumer);
+
+#ifndef CONFIG_PREEMPT
+ /*
+ * If we are a non preempt kernel, the 10 second run will
+ * stop everything while it runs. Instead, we will call
+ * cond_resched and also add any time that was lost by a
+ * rescedule.
+ *
+ * Do a cond resched at the same frequency we would wake up
+ * the reader.
+ */
+ if (cnt % wakeup_interval)
+ cond_resched();
+#endif
+
+ } while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
+ pr_info("End ring buffer hammer\n");
+
+ if (consumer) {
+ /* Init both completions here to avoid races */
+ init_completion(&read_start);
+ init_completion(&read_done);
+ /* the completions must be visible before the finish var */
+ smp_wmb();
+ reader_finish = 1;
+ /* finish var visible before waking up the consumer */
+ smp_wmb();
+ wake_up_process(consumer);
+ wait_for_completion(&read_done);
+ }
+
+ time = end_tv.tv_sec - start_tv.tv_sec;
+ time *= USEC_PER_SEC;
+ time += (long long)((long)end_tv.tv_usec - (long)start_tv.tv_usec);
+
+ entries = ring_buffer_entries(buffer);
+ overruns = ring_buffer_overruns(buffer);
+
+ if (kill_test)
+ pr_info("ERROR!\n");
+ pr_info("Time: %lld (usecs)\n", time);
+ pr_info("Overruns: %lld\n", overruns);
+ if (disable_reader)
+ pr_info("Read: (reader disabled)\n");
+ else
+ pr_info("Read: %ld (by %s)\n", read,
+ read_events ? "events" : "pages");
+ pr_info("Entries: %lld\n", entries);
+ pr_info("Total: %lld\n", entries + overruns + read);
+ pr_info("Missed: %ld\n", missed);
+ pr_info("Hit: %ld\n", hit);
+
+ /* Convert time from usecs to millisecs */
+ do_div(time, USEC_PER_MSEC);
+ if (time)
+ hit /= (long)time;
+ else
+ pr_info("TIME IS ZERO??\n");
+
+ pr_info("Entries per millisec: %ld\n", hit);
+
+ if (hit) {
+ /* Calculate the average time in nanosecs */
+ avg = NSEC_PER_MSEC / hit;
+ pr_info("%ld ns per entry\n", avg);
+ }
+
+ if (missed) {
+ if (time)
+ missed /= (long)time;
+
+ pr_info("Total iterations per millisec: %ld\n", hit + missed);
+
+ /* it is possible that hit + missed will overflow and be zero */
+ if (!(hit + missed)) {
+ pr_info("hit + missed overflowed and totalled zero!\n");
+ hit--; /* make it non zero */
+ }
+
+ /* Caculate the average time in nanosecs */
+ avg = NSEC_PER_MSEC / (hit + missed);
+ pr_info("%ld ns per entry\n", avg);
+ }
+}
+
+static void wait_to_die(void)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ __set_current_state(TASK_RUNNING);
+}
+
+static int ring_buffer_consumer_thread(void *arg)
+{
+ while (!kthread_should_stop() && !kill_test) {
+ complete(&read_start);
+
+ ring_buffer_consumer();
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (kthread_should_stop() || kill_test)
+ break;
+
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+ __set_current_state(TASK_RUNNING);
+
+ if (kill_test)
+ wait_to_die();
+
+ return 0;
+}
+
+static int ring_buffer_producer_thread(void *arg)
+{
+ init_completion(&read_start);
+
+ while (!kthread_should_stop() && !kill_test) {
+ ring_buffer_reset(buffer);
+
+ if (consumer) {
+ smp_wmb();
+ wake_up_process(consumer);
+ wait_for_completion(&read_start);
+ }
+
+ ring_buffer_producer();
+
+ pr_info("Sleeping for 10 secs\n");
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(HZ * SLEEP_TIME);
+ __set_current_state(TASK_RUNNING);
+ }
+
+ if (kill_test)
+ wait_to_die();
+
+ return 0;
+}
+
+static int __init ring_buffer_benchmark_init(void)
+{
+ int ret;
+
+ /* make a one meg buffer in overwite mode */
+ buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
+ if (!buffer)
+ return -ENOMEM;
+
+ if (!disable_reader) {
+ consumer = kthread_create(ring_buffer_consumer_thread,
+ NULL, "rb_consumer");
+ ret = PTR_ERR(consumer);
+ if (IS_ERR(consumer))
+ goto out_fail;
+ }
+
+ producer = kthread_run(ring_buffer_producer_thread,
+ NULL, "rb_producer");
+ ret = PTR_ERR(producer);
+
+ if (IS_ERR(producer))
+ goto out_kill;
+
+ return 0;
+
+ out_kill:
+ if (consumer)
+ kthread_stop(consumer);
+
+ out_fail:
+ ring_buffer_free(buffer);
+ return ret;
+}
+
+static void __exit ring_buffer_benchmark_exit(void)
+{
+ kthread_stop(producer);
+ if (consumer)
+ kthread_stop(consumer);
+ ring_buffer_free(buffer);
+}
+
+module_init(ring_buffer_benchmark_init);
+module_exit(ring_buffer_benchmark_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("ring_buffer_benchmark");
+MODULE_LICENSE("GPL");
static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
+int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+ struct ring_buffer_event *event)
+{
+ return filter_check_discard(call, rec, global_trace.buffer, event);
+}
+EXPORT_SYMBOL_GPL(filter_current_check_discard);
+
cycle_t ftrace_now(int cpu)
{
u64 ts;
/* trace_flags holds trace_options default values */
unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
- TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;
+ TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
+ TRACE_ITER_GRAPH_TIME;
/**
* trace_wake_up - wake up tasks waiting for trace input
"latency-format",
"global-clock",
"sleep-time",
+ "graph-time",
NULL
};
return cnt;
}
-static void
-trace_print_seq(struct seq_file *m, struct trace_seq *s)
-{
- int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
-
- s->buffer[len] = 0;
- seq_puts(m, s->buffer);
-
- trace_seq_init(s);
-}
-
/**
* update_max_tr - snapshot all trace buffers from global_trace to max_tr
* @tr: tracer
tracing_reset(tr, cpu);
}
+void tracing_reset_current(int cpu)
+{
+ tracing_reset(&global_trace, cpu);
+}
+
+void tracing_reset_current_online_cpus(void)
+{
+ tracing_reset_online_cpus(&global_trace);
+}
+
#define SAVED_CMDLINES 128
#define NO_CMDLINE_MAP UINT_MAX
static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
return;
}
+ preempt_disable();
__raw_spin_lock(&trace_cmdline_lock);
map = map_pid_to_cmdline[pid];
if (map != NO_CMDLINE_MAP)
strcpy(comm, "<...>");
__raw_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
}
void tracing_record_cmdline(struct task_struct *tsk)
}
struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
- unsigned char type,
+ int type,
unsigned long len,
unsigned long flags, int pc)
{
}
struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
+trace_current_buffer_lock_reserve(int type, unsigned long len,
unsigned long flags, int pc)
{
return trace_buffer_lock_reserve(&global_trace,
type, len, flags, pc);
}
+EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
unsigned long flags, int pc)
{
- return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+ __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
}
+EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
unsigned long flags, int pc)
{
- return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+ __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
+
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+{
+ ring_buffer_discard_commit(global_trace.buffer, event);
}
+EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
void
trace_function(struct trace_array *tr,
unsigned long ip, unsigned long parent_ip, unsigned long flags,
int pc)
{
+ struct ftrace_event_call *call = &event_function;
struct ring_buffer_event *event;
struct ftrace_entry *entry;
entry = ring_buffer_event_data(event);
entry->ip = ip;
entry->parent_ip = parent_ip;
- ring_buffer_unlock_commit(tr->buffer, event);
+
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned long flags,
int pc)
{
+ struct ftrace_event_call *call = &event_funcgraph_entry;
struct ring_buffer_event *event;
struct ftrace_graph_ent_entry *entry;
return 0;
entry = ring_buffer_event_data(event);
entry->graph_ent = *trace;
- ring_buffer_unlock_commit(global_trace.buffer, event);
+ if (!filter_current_check_discard(call, entry, event))
+ ring_buffer_unlock_commit(global_trace.buffer, event);
return 1;
}
unsigned long flags,
int pc)
{
+ struct ftrace_event_call *call = &event_funcgraph_exit;
struct ring_buffer_event *event;
struct ftrace_graph_ret_entry *entry;
return;
entry = ring_buffer_event_data(event);
entry->ret = *trace;
- ring_buffer_unlock_commit(global_trace.buffer, event);
+ if (!filter_current_check_discard(call, entry, event))
+ ring_buffer_unlock_commit(global_trace.buffer, event);
}
#endif
int skip, int pc)
{
#ifdef CONFIG_STACKTRACE
+ struct ftrace_event_call *call = &event_kernel_stack;
struct ring_buffer_event *event;
struct stack_entry *entry;
struct stack_trace trace;
trace.entries = entry->caller;
save_stack_trace(&trace);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
#endif
}
unsigned long flags, int pc)
{
#ifdef CONFIG_STACKTRACE
+ struct ftrace_event_call *call = &event_user_stack;
struct ring_buffer_event *event;
struct userstack_entry *entry;
struct stack_trace trace;
trace.entries = entry->caller;
save_stack_trace_user(&trace);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
#endif
}
struct task_struct *next,
unsigned long flags, int pc)
{
+ struct ftrace_event_call *call = &event_context_switch;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
entry->next_prio = next->prio;
entry->next_state = next->state;
entry->next_cpu = task_cpu(next);
- trace_buffer_unlock_commit(tr, event, flags, pc);
+
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, flags, pc);
}
void
struct task_struct *curr,
unsigned long flags, int pc)
{
+ struct ftrace_event_call *call = &event_wakeup;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
entry->next_state = wakee->state;
entry->next_cpu = task_cpu(wakee);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
ftrace_trace_stack(tr, flags, 6, pc);
ftrace_trace_userstack(tr, flags, pc);
}
(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
static u32 trace_buf[TRACE_BUF_SIZE];
+ struct ftrace_event_call *call = &event_bprint;
struct ring_buffer_event *event;
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
struct bprint_entry *entry;
unsigned long flags;
+ int disable;
int resched;
int cpu, len = 0, size, pc;
cpu = raw_smp_processor_id();
data = tr->data[cpu];
- if (unlikely(atomic_read(&data->disabled)))
+ disable = atomic_inc_return(&data->disabled);
+ if (unlikely(disable != 1))
goto out;
/* Lockdep uses trace_printk for lock tracing */
entry->fmt = fmt;
memcpy(entry->buf, trace_buf, sizeof(u32) * len);
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
out_unlock:
__raw_spin_unlock(&trace_buf_lock);
local_irq_restore(flags);
out:
+ atomic_dec_return(&data->disabled);
ftrace_preempt_enable(resched);
unpause_graph_tracing();
static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
static char trace_buf[TRACE_BUF_SIZE];
+ struct ftrace_event_call *call = &event_print;
struct ring_buffer_event *event;
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
int cpu, len = 0, size, pc;
struct print_entry *entry;
unsigned long irq_flags;
+ int disable;
if (tracing_disabled || tracing_selftest_running)
return 0;
cpu = raw_smp_processor_id();
data = tr->data[cpu];
- if (unlikely(atomic_read(&data->disabled)))
+ disable = atomic_inc_return(&data->disabled);
+ if (unlikely(disable != 1))
goto out;
pause_graph_tracing();
memcpy(&entry->buf, trace_buf, len);
entry->buf[len] = 0;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
out_unlock:
__raw_spin_unlock(&trace_buf_lock);
raw_local_irq_restore(irq_flags);
unpause_graph_tracing();
out:
+ atomic_dec_return(&data->disabled);
preempt_enable_notrace();
return len;
p = s_next(m, p, &l);
}
+ trace_event_read_lock();
return p;
}
static void s_stop(struct seq_file *m, void *p)
{
atomic_dec(&trace_record_cmdline_disabled);
+ trace_event_read_unlock();
}
static void print_lat_help_header(struct seq_file *m)
return 1;
}
+/* Called with trace_event_read_lock() held. */
static enum print_line_t print_trace_line(struct trace_iterator *iter)
{
enum print_line_t ret;
.read = tracing_readme_read,
};
+static ssize_t
+tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char *buf_comm;
+ char *file_buf;
+ char *buf;
+ int len = 0;
+ int pid;
+ int i;
+
+ file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
+ if (!file_buf)
+ return -ENOMEM;
+
+ buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
+ if (!buf_comm) {
+ kfree(file_buf);
+ return -ENOMEM;
+ }
+
+ buf = file_buf;
+
+ for (i = 0; i < SAVED_CMDLINES; i++) {
+ int r;
+
+ pid = map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ trace_find_cmdline(pid, buf_comm);
+ r = sprintf(buf, "%d %s\n", pid, buf_comm);
+ buf += r;
+ len += r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, len);
+
+ kfree(file_buf);
+ kfree(buf_comm);
+
+ return len;
+}
+
+static const struct file_operations tracing_saved_cmdlines_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_saved_cmdlines_read,
+};
+
static ssize_t
tracing_ctrl_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
/* trace pipe does not show start of buffer */
cpumask_setall(iter->started);
+ if (trace_flags & TRACE_ITER_LATENCY_FMT)
+ iter->iter_flags |= TRACE_FILE_LAT_FMT;
+
iter->cpu_file = cpu_file;
iter->tr = &global_trace;
mutex_init(&iter->mutex);
offsetof(struct trace_iterator, seq));
iter->pos = -1;
+ trace_event_read_lock();
while (find_next_entry_inc(iter) != NULL) {
enum print_line_t ret;
int len = iter->seq.len;
if (iter->seq.len >= cnt)
break;
}
+ trace_event_read_unlock();
/* Now copy what we have to the user */
sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
goto out_err;
}
+ trace_event_read_lock();
+
/* Fill as many pages as possible. */
for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
pages[i] = alloc_page(GFP_KERNEL);
trace_seq_init(&iter->seq);
}
+ trace_event_read_unlock();
mutex_unlock(&iter->mutex);
spd.nr_pages = i;
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int size, i;
+ int entries, size, i;
size_t ret;
if (*ppos & (PAGE_SIZE - 1)) {
len &= PAGE_MASK;
}
- for (i = 0; i < PIPE_BUFFERS && len; i++, len -= PAGE_SIZE) {
+ entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+
+ for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
struct page *page;
int r;
}
r = ring_buffer_read_page(ref->buffer, &ref->page,
- len, info->cpu, 0);
+ len, info->cpu, 1);
if (r < 0) {
ring_buffer_free_read_page(ref->buffer,
ref->page);
spd.partial[i].private = (unsigned long)ref;
spd.nr_pages++;
*ppos += PAGE_SIZE;
+
+ entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
}
spd.nr_pages = i;
.llseek = no_llseek,
};
+static ssize_t
+tracing_stats_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long cpu = (unsigned long)filp->private_data;
+ struct trace_array *tr = &global_trace;
+ struct trace_seq *s;
+ unsigned long cnt;
+
+ s = kmalloc(sizeof(*s), GFP_ATOMIC);
+ if (!s)
+ return ENOMEM;
+
+ trace_seq_init(s);
+
+ cnt = ring_buffer_entries_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "entries: %ld\n", cnt);
+
+ cnt = ring_buffer_overrun_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "overrun: %ld\n", cnt);
+
+ cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "commit overrun: %ld\n", cnt);
+
+ cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
+
+ count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return count;
+}
+
+static const struct file_operations tracing_stats_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_stats_read,
+};
+
#ifdef CONFIG_DYNAMIC_FTRACE
int __weak ftrace_arch_read_dyn_info(char *buf, int size)
static void tracing_init_debugfs_percpu(long cpu)
{
struct dentry *d_percpu = tracing_dentry_percpu();
- struct dentry *entry, *d_cpu;
+ struct dentry *d_cpu;
/* strlen(cpu) + MAX(log10(cpu)) + '\0' */
char cpu_dir[7];
}
/* per cpu trace_pipe */
- entry = debugfs_create_file("trace_pipe", 0444, d_cpu,
- (void *) cpu, &tracing_pipe_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace_pipe' entry\n");
+ trace_create_file("trace_pipe", 0444, d_cpu,
+ (void *) cpu, &tracing_pipe_fops);
/* per cpu trace */
- entry = debugfs_create_file("trace", 0644, d_cpu,
- (void *) cpu, &tracing_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace' entry\n");
+ trace_create_file("trace", 0644, d_cpu,
+ (void *) cpu, &tracing_fops);
+
+ trace_create_file("trace_pipe_raw", 0444, d_cpu,
+ (void *) cpu, &tracing_buffers_fops);
- entry = debugfs_create_file("trace_pipe_raw", 0444, d_cpu,
- (void *) cpu, &tracing_buffers_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace_pipe_raw' entry\n");
+ trace_create_file("stats", 0444, d_cpu,
+ (void *) cpu, &tracing_stats_fops);
}
#ifdef CONFIG_FTRACE_SELFTEST
.write = trace_options_core_write,
};
+struct dentry *trace_create_file(const char *name,
+ mode_t mode,
+ struct dentry *parent,
+ void *data,
+ const struct file_operations *fops)
+{
+ struct dentry *ret;
+
+ ret = debugfs_create_file(name, mode, parent, data, fops);
+ if (!ret)
+ pr_warning("Could not create debugfs '%s' entry\n", name);
+
+ return ret;
+}
+
+
static struct dentry *trace_options_init_dentry(void)
{
struct dentry *d_tracer;
struct tracer_opt *opt)
{
struct dentry *t_options;
- struct dentry *entry;
t_options = trace_options_init_dentry();
if (!t_options)
topt->flags = flags;
topt->opt = opt;
- entry = debugfs_create_file(opt->name, 0644, t_options, topt,
+ topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
&trace_options_fops);
- topt->entry = entry;
-
}
static struct trace_option_dentry *
create_trace_option_core_file(const char *option, long index)
{
struct dentry *t_options;
- struct dentry *entry;
t_options = trace_options_init_dentry();
if (!t_options)
return NULL;
- entry = debugfs_create_file(option, 0644, t_options, (void *)index,
+ return trace_create_file(option, 0644, t_options, (void *)index,
&trace_options_core_fops);
-
- return entry;
}
static __init void create_trace_options_dir(void)
{
struct dentry *t_options;
- struct dentry *entry;
int i;
t_options = trace_options_init_dentry();
if (!t_options)
return;
- for (i = 0; trace_options[i]; i++) {
- entry = create_trace_option_core_file(trace_options[i], i);
- if (!entry)
- pr_warning("Could not create debugfs %s entry\n",
- trace_options[i]);
- }
+ for (i = 0; trace_options[i]; i++)
+ create_trace_option_core_file(trace_options[i], i);
}
static __init int tracer_init_debugfs(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
int cpu;
d_tracer = tracing_init_dentry();
- entry = debugfs_create_file("tracing_enabled", 0644, d_tracer,
- &global_trace, &tracing_ctrl_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'tracing_enabled' entry\n");
+ trace_create_file("tracing_enabled", 0644, d_tracer,
+ &global_trace, &tracing_ctrl_fops);
- entry = debugfs_create_file("trace_options", 0644, d_tracer,
- NULL, &tracing_iter_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace_options' entry\n");
+ trace_create_file("trace_options", 0644, d_tracer,
+ NULL, &tracing_iter_fops);
- create_trace_options_dir();
+ trace_create_file("tracing_cpumask", 0644, d_tracer,
+ NULL, &tracing_cpumask_fops);
+
+ trace_create_file("trace", 0644, d_tracer,
+ (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
- entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer,
- NULL, &tracing_cpumask_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
-
- entry = debugfs_create_file("trace", 0644, d_tracer,
- (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'trace' entry\n");
-
- entry = debugfs_create_file("available_tracers", 0444, d_tracer,
- &global_trace, &show_traces_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'available_tracers' entry\n");
-
- entry = debugfs_create_file("current_tracer", 0444, d_tracer,
- &global_trace, &set_tracer_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'current_tracer' entry\n");
-
- entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer,
- &tracing_max_latency,
- &tracing_max_lat_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'tracing_max_latency' entry\n");
-
- entry = debugfs_create_file("tracing_thresh", 0644, d_tracer,
- &tracing_thresh, &tracing_max_lat_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'tracing_thresh' entry\n");
- entry = debugfs_create_file("README", 0644, d_tracer,
- NULL, &tracing_readme_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'README' entry\n");
-
- entry = debugfs_create_file("trace_pipe", 0444, d_tracer,
+ trace_create_file("available_tracers", 0444, d_tracer,
+ &global_trace, &show_traces_fops);
+
+ trace_create_file("current_tracer", 0644, d_tracer,
+ &global_trace, &set_tracer_fops);
+
+ trace_create_file("tracing_max_latency", 0644, d_tracer,
+ &tracing_max_latency, &tracing_max_lat_fops);
+
+ trace_create_file("tracing_thresh", 0644, d_tracer,
+ &tracing_thresh, &tracing_max_lat_fops);
+
+ trace_create_file("README", 0444, d_tracer,
+ NULL, &tracing_readme_fops);
+
+ trace_create_file("trace_pipe", 0444, d_tracer,
(void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'trace_pipe' entry\n");
-
- entry = debugfs_create_file("buffer_size_kb", 0644, d_tracer,
- &global_trace, &tracing_entries_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'buffer_size_kb' entry\n");
-
- entry = debugfs_create_file("trace_marker", 0220, d_tracer,
- NULL, &tracing_mark_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'trace_marker' entry\n");
+
+ trace_create_file("buffer_size_kb", 0644, d_tracer,
+ &global_trace, &tracing_entries_fops);
+
+ trace_create_file("trace_marker", 0220, d_tracer,
+ NULL, &tracing_mark_fops);
+
+ trace_create_file("saved_cmdlines", 0444, d_tracer,
+ NULL, &tracing_saved_cmdlines_fops);
#ifdef CONFIG_DYNAMIC_FTRACE
- entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
- &ftrace_update_tot_cnt,
- &tracing_dyn_info_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'dyn_ftrace_total_info' entry\n");
+ trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
+ &ftrace_update_tot_cnt, &tracing_dyn_info_fops);
#endif
#ifdef CONFIG_SYSPROF_TRACER
init_tracer_sysprof_debugfs(d_tracer);
#endif
+ create_trace_options_dir();
+
for_each_tracing_cpu(cpu)
tracing_init_debugfs_percpu(cpu);
static void __ftrace_dump(bool disable_tracing)
{
- static DEFINE_SPINLOCK(ftrace_dump_lock);
+ static raw_spinlock_t ftrace_dump_lock =
+ (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
/* use static because iter can be a bit big for the stack */
static struct trace_iterator iter;
unsigned int old_userobj;
int cnt = 0, cpu;
/* only one dump */
- spin_lock_irqsave(&ftrace_dump_lock, flags);
+ local_irq_save(flags);
+ __raw_spin_lock(&ftrace_dump_lock);
if (dump_ran)
goto out;
}
out:
- spin_unlock_irqrestore(&ftrace_dump_lock, flags);
+ __raw_spin_unlock(&ftrace_dump_lock);
+ local_irq_restore(flags);
}
/* By default: disable tracing after the dump */
#include <linux/mmiotrace.h>
#include <linux/ftrace.h>
#include <trace/boot.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
#include <trace/power.h>
+#include <linux/trace_seq.h>
+#include <linux/ftrace_event.h>
+
enum trace_type {
__TRACE_FIRST_TYPE = 0,
__TRACE_LAST_TYPE,
};
-/*
- * The trace entry - the most basic unit of tracing. This is what
- * is printed in the end as a single line in the trace output, such as:
- *
- * bash-15816 [01] 235.197585: idle_cpu <- irq_enter
- */
-struct trace_entry {
- unsigned char type;
- unsigned char flags;
- unsigned char preempt_count;
- int pid;
- int tgid;
-};
-
/*
* Function trace entry - function address and parent function addres:
*/
char comm[TASK_COMM_LEN];
};
-struct trace_iterator;
-
/*
* The trace array - an array of per-CPU trace arrays. This is the
* highest level data structure that individual tracers deal with.
__ftrace_bad_type(); \
} while (0)
-/* Return values for print_line callback */
-enum print_line_t {
- TRACE_TYPE_PARTIAL_LINE = 0, /* Retry after flushing the seq */
- TRACE_TYPE_HANDLED = 1,
- TRACE_TYPE_UNHANDLED = 2, /* Relay to other output functions */
- TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */
-};
-
-
/*
* An option specific to a tracer. This is a boolean value.
* The bit is the bit index that sets its value on the
struct tracer_stat *stats;
};
-struct trace_seq {
- unsigned char buffer[PAGE_SIZE];
- unsigned int len;
- unsigned int readpos;
-};
-
-static inline void
-trace_seq_init(struct trace_seq *s)
-{
- s->len = 0;
- s->readpos = 0;
-}
-
#define TRACE_PIPE_ALL_CPU -1
-/*
- * Trace iterator - used by printout routines who present trace
- * results to users and which routines might sleep, etc:
- */
-struct trace_iterator {
- struct trace_array *tr;
- struct tracer *trace;
- void *private;
- int cpu_file;
- struct mutex mutex;
- struct ring_buffer_iter *buffer_iter[NR_CPUS];
-
- /* The below is zeroed out in pipe_read */
- struct trace_seq seq;
- struct trace_entry *ent;
- int cpu;
- u64 ts;
-
- unsigned long iter_flags;
- loff_t pos;
- long idx;
-
- cpumask_var_t started;
-};
-
int tracer_init(struct tracer *t, struct trace_array *tr);
int tracing_is_enabled(void);
void trace_wake_up(void);
void tracing_reset(struct trace_array *tr, int cpu);
void tracing_reset_online_cpus(struct trace_array *tr);
+void tracing_reset_current(int cpu);
+void tracing_reset_current_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
+struct dentry *trace_create_file(const char *name,
+ mode_t mode,
+ struct dentry *parent,
+ void *data,
+ const struct file_operations *fops);
+
struct dentry *tracing_init_dentry(void);
void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
struct ring_buffer_event;
struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
- unsigned char type,
+ int type,
unsigned long len,
unsigned long flags,
int pc);
struct ring_buffer_event *event,
unsigned long flags, int pc);
-struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
- unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
- unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
- unsigned long flags, int pc);
-
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
struct trace_array_cpu *data);
struct task_struct *prev,
struct task_struct *next,
unsigned long flags, int pc);
-void tracing_record_cmdline(struct task_struct *tsk);
void tracing_sched_wakeup_trace(struct trace_array *tr,
struct task_struct *wakee,
struct trace_array *tr);
extern int trace_selftest_startup_branch(struct tracer *trace,
struct trace_array *tr);
+extern int trace_selftest_startup_hw_branches(struct tracer *trace,
+ struct trace_array *tr);
#endif /* CONFIG_FTRACE_STARTUP_TEST */
extern void *head_page(struct trace_array_cpu *data);
/* Standard output formatting function used for function return traces */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
return 1;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
-
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
static inline enum print_line_t
print_graph_function(struct trace_iterator *iter)
TRACE_ITER_LATENCY_FMT = 0x40000,
TRACE_ITER_GLOBAL_CLK = 0x80000,
TRACE_ITER_SLEEP_TIME = 0x100000,
+ TRACE_ITER_GRAPH_TIME = 0x200000,
};
/*
char *type;
int offset;
int size;
+ int is_signed;
};
-struct ftrace_event_call {
- char *name;
- char *system;
- struct dentry *dir;
- int enabled;
- int (*regfunc)(void);
- void (*unregfunc)(void);
- int id;
- int (*raw_init)(void);
- int (*show_format)(struct trace_seq *s);
- int (*define_fields)(void);
- struct list_head fields;
+struct event_filter {
+ int n_preds;
struct filter_pred **preds;
-
-#ifdef CONFIG_EVENT_PROFILE
- atomic_t profile_count;
- int (*profile_enable)(struct ftrace_event_call *);
- void (*profile_disable)(struct ftrace_event_call *);
-#endif
+ char *filter_string;
};
struct event_subsystem {
struct list_head list;
const char *name;
struct dentry *entry;
- struct filter_pred **preds;
+ void *filter;
};
-#define events_for_each(event) \
- for (event = __start_ftrace_events; \
- (unsigned long)event < (unsigned long)__stop_ftrace_events; \
- event++)
-
-#define MAX_FILTER_PRED 8
-
struct filter_pred;
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
+ int val1, int val2);
struct filter_pred {
filter_pred_fn_t fn;
u64 val;
- char *str_val;
+ char str_val[MAX_FILTER_STR_VAL];
int str_len;
char *field_name;
int offset;
int not;
- int or;
- int compound;
- int clear;
+ int op;
+ int pop_n;
};
-int trace_define_field(struct ftrace_event_call *call, char *type,
- char *name, int offset, int size);
-extern void filter_free_pred(struct filter_pred *pred);
-extern void filter_print_preds(struct filter_pred **preds,
+extern void print_event_filter(struct ftrace_event_call *call,
struct trace_seq *s);
-extern int filter_parse(char **pbuf, struct filter_pred *pred);
-extern int filter_add_pred(struct ftrace_event_call *call,
- struct filter_pred *pred);
-extern void filter_free_preds(struct ftrace_event_call *call);
-extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern void filter_free_subsystem_preds(struct event_subsystem *system);
-extern int filter_add_subsystem_pred(struct event_subsystem *system,
- struct filter_pred *pred);
-
-void event_trace_printk(unsigned long ip, const char *fmt, ...);
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
-
-#define for_each_event(event) \
- for (event = __start_ftrace_events; \
- (unsigned long)event < (unsigned long)__stop_ftrace_events; \
- event++)
+extern int apply_event_filter(struct ftrace_event_call *call,
+ char *filter_string);
+extern int apply_subsystem_event_filter(struct event_subsystem *system,
+ char *filter_string);
+extern void print_subsystem_event_filter(struct event_subsystem *system,
+ struct trace_seq *s);
+
+static inline int
+filter_check_discard(struct ftrace_event_call *call, void *rec,
+ struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+ ring_buffer_discard_commit(buffer, event);
+ return 1;
+ }
+
+ return 0;
+}
+
+#define DEFINE_COMPARISON_PRED(type) \
+static int filter_pred_##type(struct filter_pred *pred, void *event, \
+ int val1, int val2) \
+{ \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ int match = 0; \
+ \
+ switch (pred->op) { \
+ case OP_LT: \
+ match = (*addr < val); \
+ break; \
+ case OP_LE: \
+ match = (*addr <= val); \
+ break; \
+ case OP_GT: \
+ match = (*addr > val); \
+ break; \
+ case OP_GE: \
+ match = (*addr >= val); \
+ break; \
+ default: \
+ break; \
+ } \
+ \
+ return match; \
+}
+
+#define DEFINE_EQUALITY_PRED(size) \
+static int filter_pred_##size(struct filter_pred *pred, void *event, \
+ int val1, int val2) \
+{ \
+ u##size *addr = (u##size *)(event + pred->offset); \
+ u##size val = (u##size)pred->val; \
+ int match; \
+ \
+ match = (val == *addr) ^ pred->not; \
+ \
+ return match; \
+}
+
+extern struct mutex event_mutex;
+extern struct list_head ftrace_events;
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
-/*
- * The double __builtin_constant_p is because gcc will give us an error
- * if we try to allocate the static variable to fmt if it is not a
- * constant. Even with the outer if statement optimizing out.
- */
-#define event_trace_printk(ip, fmt, args...) \
-do { \
- __trace_printk_check_format(fmt, ##args); \
- tracing_record_cmdline(current); \
- if (__builtin_constant_p(fmt)) { \
- static const char *trace_printk_fmt \
- __attribute__((section("__trace_printk_fmt"))) = \
- __builtin_constant_p(fmt) ? fmt : NULL; \
- \
- __trace_bprintk(ip, trace_printk_fmt, ##args); \
- } else \
- __trace_printk(ip, fmt, ##args); \
-} while (0)
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
+ extern struct ftrace_event_call event_##call;
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, tpfmt)
+#include "trace_event_types.h"
#endif /* _LINUX_KERNEL_TRACE_H */
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <linux/kallsyms.h>
+#include <linux/time.h>
#include "trace.h"
#include "trace_output.h"
trace_assign_type(field, entry);
call = &field->boot_call;
ts = iter->ts;
- nsec_rem = do_div(ts, 1000000000);
+ nsec_rem = do_div(ts, NSEC_PER_SEC);
ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n",
(unsigned long)ts, nsec_rem, call->func, call->caller);
trace_assign_type(field, entry);
init_ret = &field->boot_ret;
ts = iter->ts;
- nsec_rem = do_div(ts, 1000000000);
+ nsec_rem = do_div(ts, NSEC_PER_SEC);
ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
"returned %d after %llu msecs\n",
static void
probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
{
+ struct ftrace_event_call *call = &event_branch;
struct trace_array *tr = branch_tracer;
struct ring_buffer_event *event;
struct trace_branch *entry;
entry->line = f->line;
entry->correct = val == expect;
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
out:
atomic_dec(&tr->data[cpu]->disabled);
return 0;
}
-static void *annotated_branch_stat_start(void)
+static void *annotated_branch_stat_start(struct tracer_stat *trace)
{
return __start_annotated_branch_profile;
}
return 0;
}
-static void *all_branch_stat_start(void)
+static void *all_branch_stat_start(struct tracer_stat *trace)
{
return __start_branch_profile;
}
int ftrace_profile_enable(int event_id)
{
struct ftrace_event_call *event;
+ int ret = -EINVAL;
- for_each_event(event) {
- if (event->id == event_id)
- return event->profile_enable(event);
+ mutex_lock(&event_mutex);
+ list_for_each_entry(event, &ftrace_events, list) {
+ if (event->id == event_id) {
+ ret = event->profile_enable(event);
+ break;
+ }
}
+ mutex_unlock(&event_mutex);
- return -EINVAL;
+ return ret;
}
void ftrace_profile_disable(int event_id)
{
struct ftrace_event_call *event;
- for_each_event(event) {
- if (event->id == event_id)
- return event->profile_disable(event);
+ mutex_lock(&event_mutex);
+ list_for_each_entry(event, &ftrace_events, list) {
+ if (event->id == event_id) {
+ event->profile_disable(event);
+ break;
+ }
}
+ mutex_unlock(&event_mutex);
}
-
TP_RAW_FMT("%u:%u:%u ==+ %u:%u:%u [%03u]")
);
-TRACE_EVENT_FORMAT(special, TRACE_SPECIAL, special_entry, ignore,
+TRACE_EVENT_FORMAT_NOFILTER(special, TRACE_SPECIAL, special_entry, ignore,
TRACE_STRUCT(
TRACE_FIELD(unsigned long, arg1, arg1)
TRACE_FIELD(unsigned long, arg2, arg2)
TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore,
TRACE_STRUCT(
TRACE_FIELD(unsigned int, line, line)
- TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func, func)
- TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file, file)
+ TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func,
+ TRACE_FUNC_SIZE+1, func)
+ TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file,
+ TRACE_FUNC_SIZE+1, file)
TRACE_FIELD(char, correct, correct)
),
TP_RAW_FMT("%u:%s:%s (%u)")
TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore,
TRACE_STRUCT(
- TRACE_FIELD(ktime_t, state_data.stamp, stamp)
- TRACE_FIELD(ktime_t, state_data.end, end)
+ TRACE_FIELD_SIGN(ktime_t, state_data.stamp, stamp, 1)
+ TRACE_FIELD_SIGN(ktime_t, state_data.end, end, 1)
TRACE_FIELD(int, state_data.type, type)
TRACE_FIELD(int, state_data.state, state)
),
*
*/
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
+#include <linux/delay.h>
#include "trace_output.h"
#define TRACE_SYSTEM "TRACE_SYSTEM"
-static DEFINE_MUTEX(event_mutex);
+DEFINE_MUTEX(event_mutex);
+
+LIST_HEAD(ftrace_events);
int trace_define_field(struct ftrace_event_call *call, char *type,
- char *name, int offset, int size)
+ char *name, int offset, int size, int is_signed)
{
struct ftrace_event_field *field;
field->offset = offset;
field->size = size;
+ field->is_signed = is_signed;
list_add(&field->link, &call->fields);
return 0;
return -ENOMEM;
}
+EXPORT_SYMBOL_GPL(trace_define_field);
-static void ftrace_clear_events(void)
-{
- struct ftrace_event_call *call = (void *)__start_ftrace_events;
-
+#ifdef CONFIG_MODULES
- while ((unsigned long)call < (unsigned long)__stop_ftrace_events) {
+static void trace_destroy_fields(struct ftrace_event_call *call)
+{
+ struct ftrace_event_field *field, *next;
- if (call->enabled) {
- call->enabled = 0;
- call->unregfunc();
- }
- call++;
+ list_for_each_entry_safe(field, next, &call->fields, link) {
+ list_del(&field->link);
+ kfree(field->type);
+ kfree(field->name);
+ kfree(field);
}
}
+#endif /* CONFIG_MODULES */
+
static void ftrace_event_enable_disable(struct ftrace_event_call *call,
int enable)
{
-
switch (enable) {
case 0:
if (call->enabled) {
call->enabled = 0;
+ tracing_stop_cmdline_record();
call->unregfunc();
}
break;
case 1:
if (!call->enabled) {
call->enabled = 1;
+ tracing_start_cmdline_record();
call->regfunc();
}
break;
}
}
+static void ftrace_clear_events(void)
+{
+ struct ftrace_event_call *call;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+ ftrace_event_enable_disable(call, 0);
+ }
+ mutex_unlock(&event_mutex);
+}
+
+/*
+ * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
+ */
+static int __ftrace_set_clr_event(const char *match, const char *sub,
+ const char *event, int set)
+{
+ struct ftrace_event_call *call;
+ int ret = -EINVAL;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+
+ if (!call->name || !call->regfunc)
+ continue;
+
+ if (match &&
+ strcmp(match, call->name) != 0 &&
+ strcmp(match, call->system) != 0)
+ continue;
+
+ if (sub && strcmp(sub, call->system) != 0)
+ continue;
+
+ if (event && strcmp(event, call->name) != 0)
+ continue;
+
+ ftrace_event_enable_disable(call, set);
+
+ ret = 0;
+ }
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
static int ftrace_set_clr_event(char *buf, int set)
{
- struct ftrace_event_call *call = __start_ftrace_events;
char *event = NULL, *sub = NULL, *match;
- int ret = -EINVAL;
/*
* The buf format can be <subsystem>:<event-name>
event = NULL;
}
- mutex_lock(&event_mutex);
- for_each_event(call) {
-
- if (!call->name || !call->regfunc)
- continue;
-
- if (match &&
- strcmp(match, call->name) != 0 &&
- strcmp(match, call->system) != 0)
- continue;
-
- if (sub && strcmp(sub, call->system) != 0)
- continue;
-
- if (event && strcmp(event, call->name) != 0)
- continue;
-
- ftrace_event_enable_disable(call, set);
-
- ret = 0;
- }
- mutex_unlock(&event_mutex);
+ return __ftrace_set_clr_event(match, sub, event, set);
+}
- return ret;
+/**
+ * trace_set_clr_event - enable or disable an event
+ * @system: system name to match (NULL for any system)
+ * @event: event name to match (NULL for all events, within system)
+ * @set: 1 to enable, 0 to disable
+ *
+ * This is a way for other parts of the kernel to enable or disable
+ * event recording.
+ *
+ * Returns 0 on success, -EINVAL if the parameters do not match any
+ * registered events.
+ */
+int trace_set_clr_event(const char *system, const char *event, int set)
+{
+ return __ftrace_set_clr_event(NULL, system, event, set);
}
/* 128 should be much more than enough */
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct ftrace_event_call *call = m->private;
- struct ftrace_event_call *next = call;
+ struct list_head *list = m->private;
+ struct ftrace_event_call *call;
(*pos)++;
for (;;) {
- if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+ if (list == &ftrace_events)
return NULL;
+ call = list_entry(list, struct ftrace_event_call, list);
+
/*
* The ftrace subsystem is for showing formats only.
* They can not be enabled or disabled via the event files.
if (call->regfunc)
break;
- call++;
- next = call;
+ list = list->next;
}
- m->private = ++next;
+ m->private = list->next;
return call;
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
+ mutex_lock(&event_mutex);
+ if (*pos == 0)
+ m->private = ftrace_events.next;
return t_next(m, NULL, pos);
}
static void *
s_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct ftrace_event_call *call = m->private;
- struct ftrace_event_call *next;
+ struct list_head *list = m->private;
+ struct ftrace_event_call *call;
(*pos)++;
retry:
- if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+ if (list == &ftrace_events)
return NULL;
+ call = list_entry(list, struct ftrace_event_call, list);
+
if (!call->enabled) {
- call++;
+ list = list->next;
goto retry;
}
- next = call;
- m->private = ++next;
+ m->private = list->next;
return call;
}
static void *s_start(struct seq_file *m, loff_t *pos)
{
+ mutex_lock(&event_mutex);
+ if (*pos == 0)
+ m->private = ftrace_events.next;
return s_next(m, NULL, pos);
}
static void t_stop(struct seq_file *m, void *p)
{
+ mutex_unlock(&event_mutex);
}
static int
ftrace_event_seq_open(struct inode *inode, struct file *file)
{
- int ret;
const struct seq_operations *seq_ops;
if ((file->f_mode & FMODE_WRITE) &&
ftrace_clear_events();
seq_ops = inode->i_private;
- ret = seq_open(file, seq_ops);
- if (!ret) {
- struct seq_file *m = file->private_data;
-
- m->private = __start_ftrace_events;
- }
- return ret;
+ return seq_open(file, seq_ops);
}
static ssize_t
return cnt;
}
+static ssize_t
+system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ const char set_to_char[4] = { '?', '0', '1', 'X' };
+ const char *system = filp->private_data;
+ struct ftrace_event_call *call;
+ char buf[2];
+ int set = 0;
+ int ret;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (!call->name || !call->regfunc)
+ continue;
+
+ if (system && strcmp(call->system, system) != 0)
+ continue;
+
+ /*
+ * We need to find out if all the events are set
+ * or if all events or cleared, or if we have
+ * a mixture.
+ */
+ set |= (1 << !!call->enabled);
+
+ /*
+ * If we have a mixture, no need to look further.
+ */
+ if (set == 3)
+ break;
+ }
+ mutex_unlock(&event_mutex);
+
+ buf[0] = set_to_char[set];
+ buf[1] = '\n';
+
+ ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+
+ return ret;
+}
+
+static ssize_t
+system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ const char *system = filp->private_data;
+ unsigned long val;
+ char buf[64];
+ ssize_t ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ ret = tracing_update_buffers();
+ if (ret < 0)
+ return ret;
+
+ if (val != 0 && val != 1)
+ return -EINVAL;
+
+ ret = __ftrace_set_clr_event(NULL, system, NULL, val);
+ if (ret)
+ goto out;
+
+ ret = cnt;
+
+out:
+ *ppos += cnt;
+
+ return ret;
+}
+
+extern char *__bad_type_size(void);
+
#undef FIELD
#define FIELD(type, name) \
+ sizeof(type) != sizeof(field.name) ? __bad_type_size() : \
#type, "common_" #name, offsetof(typeof(field), name), \
sizeof(field.name)
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\n",
- FIELD(unsigned char, type),
+ FIELD(unsigned short, type),
FIELD(unsigned char, flags),
FIELD(unsigned char, preempt_count),
FIELD(int, pid),
trace_seq_init(s);
- filter_print_preds(call->preds, s);
+ print_event_filter(call, s);
r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
- char buf[64], *pbuf = buf;
- struct filter_pred *pred;
+ char *buf;
int err;
- if (cnt >= sizeof(buf))
+ if (cnt >= PAGE_SIZE)
return -EINVAL;
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
- buf[cnt] = '\0';
-
- pred = kzalloc(sizeof(*pred), GFP_KERNEL);
- if (!pred)
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
return -ENOMEM;
- err = filter_parse(&pbuf, pred);
- if (err < 0) {
- filter_free_pred(pred);
- return err;
- }
-
- if (pred->clear) {
- filter_free_preds(call);
- filter_free_pred(pred);
- return cnt;
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long) buf);
+ return -EFAULT;
}
+ buf[cnt] = '\0';
- err = filter_add_pred(call, pred);
- if (err < 0) {
- filter_free_pred(pred);
+ err = apply_event_filter(call, buf);
+ free_page((unsigned long) buf);
+ if (err < 0)
return err;
- }
*ppos += cnt;
trace_seq_init(s);
- filter_print_preds(system->preds, s);
+ print_subsystem_event_filter(system, s);
r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
loff_t *ppos)
{
struct event_subsystem *system = filp->private_data;
- char buf[64], *pbuf = buf;
- struct filter_pred *pred;
+ char *buf;
int err;
- if (cnt >= sizeof(buf))
+ if (cnt >= PAGE_SIZE)
return -EINVAL;
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
- buf[cnt] = '\0';
-
- pred = kzalloc(sizeof(*pred), GFP_KERNEL);
- if (!pred)
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
return -ENOMEM;
- err = filter_parse(&pbuf, pred);
- if (err < 0) {
- filter_free_pred(pred);
- return err;
- }
-
- if (pred->clear) {
- filter_free_subsystem_preds(system);
- filter_free_pred(pred);
- return cnt;
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long) buf);
+ return -EFAULT;
}
+ buf[cnt] = '\0';
- err = filter_add_subsystem_pred(system, pred);
- if (err < 0) {
- filter_free_subsystem_preds(system);
- filter_free_pred(pred);
+ err = apply_subsystem_event_filter(system, buf);
+ free_page((unsigned long) buf);
+ if (err < 0)
return err;
- }
*ppos += cnt;
return cnt;
}
+static ssize_t
+show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ int (*func)(struct trace_seq *s) = filp->private_data;
+ struct trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ func(s);
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return r;
+}
+
static const struct seq_operations show_event_seq_ops = {
.start = t_start,
.next = t_next,
.write = subsystem_filter_write,
};
+static const struct file_operations ftrace_system_enable_fops = {
+ .open = tracing_open_generic,
+ .read = system_enable_read,
+ .write = system_enable_write,
+};
+
+static const struct file_operations ftrace_show_header_fops = {
+ .open = tracing_open_generic,
+ .read = show_header,
+};
+
static struct dentry *event_trace_events_dir(void)
{
static struct dentry *d_tracer;
event_subsystem_dir(const char *name, struct dentry *d_events)
{
struct event_subsystem *system;
+ struct dentry *entry;
/* First see if we did not already create this dir */
list_for_each_entry(system, &event_subsystems, list) {
return d_events;
}
- system->name = name;
+ system->name = kstrdup(name, GFP_KERNEL);
+ if (!system->name) {
+ debugfs_remove(system->entry);
+ kfree(system);
+ return d_events;
+ }
+
list_add(&system->list, &event_subsystems);
- system->preds = NULL;
+ system->filter = NULL;
+
+ system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+ if (!system->filter) {
+ pr_warning("Could not allocate filter for subsystem "
+ "'%s'\n", name);
+ return system->entry;
+ }
+
+ entry = debugfs_create_file("filter", 0644, system->entry, system,
+ &ftrace_subsystem_filter_fops);
+ if (!entry) {
+ kfree(system->filter);
+ system->filter = NULL;
+ pr_warning("Could not create debugfs "
+ "'%s/filter' entry\n", name);
+ }
+
+ entry = trace_create_file("enable", 0644, system->entry,
+ (void *)system->name,
+ &ftrace_system_enable_fops);
return system->entry;
}
static int
-event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
+event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
+ const struct file_operations *id,
+ const struct file_operations *enable,
+ const struct file_operations *filter,
+ const struct file_operations *format)
{
struct dentry *entry;
int ret;
* If the trace point header did not define TRACE_SYSTEM
* then the system would be called "TRACE_SYSTEM".
*/
- if (strcmp(call->system, "TRACE_SYSTEM") != 0)
+ if (strcmp(call->system, TRACE_SYSTEM) != 0)
d_events = event_subsystem_dir(call->system, d_events);
if (call->raw_init) {
return -1;
}
- if (call->regfunc) {
- entry = debugfs_create_file("enable", 0644, call->dir, call,
- &ftrace_enable_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'%s/enable' entry\n", call->name);
- }
+ if (call->regfunc)
+ entry = trace_create_file("enable", 0644, call->dir, call,
+ enable);
- if (call->id) {
- entry = debugfs_create_file("id", 0444, call->dir, call,
- &ftrace_event_id_fops);
- if (!entry)
- pr_warning("Could not create debugfs '%s/id' entry\n",
- call->name);
- }
+ if (call->id)
+ entry = trace_create_file("id", 0444, call->dir, call,
+ id);
if (call->define_fields) {
ret = call->define_fields();
" events/%s\n", call->name);
return ret;
}
- entry = debugfs_create_file("filter", 0644, call->dir, call,
- &ftrace_event_filter_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'%s/filter' entry\n", call->name);
+ entry = trace_create_file("filter", 0644, call->dir, call,
+ filter);
}
/* A trace may not want to export its format */
if (!call->show_format)
return 0;
- entry = debugfs_create_file("format", 0444, call->dir, call,
- &ftrace_event_format_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'%s/format' entry\n", call->name);
+ entry = trace_create_file("format", 0444, call->dir, call,
+ format);
+
+ return 0;
+}
+
+#define for_each_event(event, start, end) \
+ for (event = start; \
+ (unsigned long)event < (unsigned long)end; \
+ event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+ struct list_head list;
+ struct module *mod;
+ struct file_operations id;
+ struct file_operations enable;
+ struct file_operations format;
+ struct file_operations filter;
+};
+
+static struct ftrace_module_file_ops *
+trace_create_file_ops(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops;
+
+ /*
+ * This is a bit of a PITA. To allow for correct reference
+ * counting, modules must "own" their file_operations.
+ * To do this, we allocate the file operations that will be
+ * used in the event directory.
+ */
+
+ file_ops = kmalloc(sizeof(*file_ops), GFP_KERNEL);
+ if (!file_ops)
+ return NULL;
+
+ file_ops->mod = mod;
+
+ file_ops->id = ftrace_event_id_fops;
+ file_ops->id.owner = mod;
+
+ file_ops->enable = ftrace_enable_fops;
+ file_ops->enable.owner = mod;
+
+ file_ops->filter = ftrace_event_filter_fops;
+ file_ops->filter.owner = mod;
+
+ file_ops->format = ftrace_event_format_fops;
+ file_ops->format.owner = mod;
+
+ list_add(&file_ops->list, &ftrace_module_file_list);
+
+ return file_ops;
+}
+
+static void trace_module_add_events(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops = NULL;
+ struct ftrace_event_call *call, *start, *end;
+ struct dentry *d_events;
+
+ start = mod->trace_events;
+ end = mod->trace_events + mod->num_trace_events;
+
+ if (start == end)
+ return;
+
+ d_events = event_trace_events_dir();
+ if (!d_events)
+ return;
+
+ for_each_event(call, start, end) {
+ /* The linker may leave blanks */
+ if (!call->name)
+ continue;
+
+ /*
+ * This module has events, create file ops for this module
+ * if not already done.
+ */
+ if (!file_ops) {
+ file_ops = trace_create_file_ops(mod);
+ if (!file_ops)
+ return;
+ }
+ call->mod = mod;
+ list_add(&call->list, &ftrace_events);
+ event_create_dir(call, d_events,
+ &file_ops->id, &file_ops->enable,
+ &file_ops->filter, &file_ops->format);
+ }
+}
+
+static void trace_module_remove_events(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops;
+ struct ftrace_event_call *call, *p;
+ bool found = false;
+
+ down_write(&trace_event_mutex);
+ list_for_each_entry_safe(call, p, &ftrace_events, list) {
+ if (call->mod == mod) {
+ found = true;
+ ftrace_event_enable_disable(call, 0);
+ if (call->event)
+ __unregister_ftrace_event(call->event);
+ debugfs_remove_recursive(call->dir);
+ list_del(&call->list);
+ trace_destroy_fields(call);
+ destroy_preds(call);
+ }
+ }
+
+ /* Now free the file_operations */
+ list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
+ if (file_ops->mod == mod)
+ break;
+ }
+ if (&file_ops->list != &ftrace_module_file_list) {
+ list_del(&file_ops->list);
+ kfree(file_ops);
+ }
+
+ /*
+ * It is safest to reset the ring buffer if the module being unloaded
+ * registered any events.
+ */
+ if (found)
+ tracing_reset_current_online_cpus();
+ up_write(&trace_event_mutex);
+}
+
+static int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ mutex_lock(&event_mutex);
+ switch (val) {
+ case MODULE_STATE_COMING:
+ trace_module_add_events(mod);
+ break;
+ case MODULE_STATE_GOING:
+ trace_module_remove_events(mod);
+ break;
+ }
+ mutex_unlock(&event_mutex);
return 0;
}
+#else
+static int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block trace_module_nb = {
+ .notifier_call = trace_module_notify,
+ .priority = 0,
+};
+
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
static __init int event_trace_init(void)
{
- struct ftrace_event_call *call = __start_ftrace_events;
+ struct ftrace_event_call *call;
struct dentry *d_tracer;
struct dentry *entry;
struct dentry *d_events;
+ int ret;
d_tracer = tracing_init_dentry();
if (!d_tracer)
if (!d_events)
return 0;
- for_each_event(call) {
+ /* ring buffer internal formats */
+ trace_create_file("header_page", 0444, d_events,
+ ring_buffer_print_page_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("header_event", 0444, d_events,
+ ring_buffer_print_entry_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("enable", 0644, d_events,
+ NULL, &ftrace_system_enable_fops);
+
+ for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
/* The linker may leave blanks */
if (!call->name)
continue;
- event_create_dir(call, d_events);
+ list_add(&call->list, &ftrace_events);
+ event_create_dir(call, d_events, &ftrace_event_id_fops,
+ &ftrace_enable_fops, &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
}
+ ret = register_module_notifier(&trace_module_nb);
+ if (ret)
+ pr_warning("Failed to register trace events module notifier\n");
+
return 0;
}
fs_initcall(event_trace_init);
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static DEFINE_SPINLOCK(test_spinlock);
+static DEFINE_SPINLOCK(test_spinlock_irq);
+static DEFINE_MUTEX(test_mutex);
+
+static __init void test_work(struct work_struct *dummy)
+{
+ spin_lock(&test_spinlock);
+ spin_lock_irq(&test_spinlock_irq);
+ udelay(1);
+ spin_unlock_irq(&test_spinlock_irq);
+ spin_unlock(&test_spinlock);
+
+ mutex_lock(&test_mutex);
+ msleep(1);
+ mutex_unlock(&test_mutex);
+}
+
+static __init int event_test_thread(void *unused)
+{
+ void *test_malloc;
+
+ test_malloc = kmalloc(1234, GFP_KERNEL);
+ if (!test_malloc)
+ pr_info("failed to kmalloc\n");
+
+ schedule_on_each_cpu(test_work);
+
+ kfree(test_malloc);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop())
+ schedule();
+
+ return 0;
+}
+
+/*
+ * Do various things that may trigger events.
+ */
+static __init void event_test_stuff(void)
+{
+ struct task_struct *test_thread;
+
+ test_thread = kthread_run(event_test_thread, NULL, "test-events");
+ msleep(1);
+ kthread_stop(test_thread);
+}
+
+/*
+ * For every trace event defined, we will test each trace point separately,
+ * and then by groups, and finally all trace points.
+ */
+static __init void event_trace_self_tests(void)
+{
+ struct ftrace_event_call *call;
+ struct event_subsystem *system;
+ int ret;
+
+ pr_info("Running tests on trace events:\n");
+
+ list_for_each_entry(call, &ftrace_events, list) {
+
+ /* Only test those that have a regfunc */
+ if (!call->regfunc)
+ continue;
+
+ pr_info("Testing event %s: ", call->name);
+
+ /*
+ * If an event is already enabled, someone is using
+ * it and the self test should not be on.
+ */
+ if (call->enabled) {
+ pr_warning("Enabled event during self test!\n");
+ WARN_ON_ONCE(1);
+ continue;
+ }
+
+ ftrace_event_enable_disable(call, 1);
+ event_test_stuff();
+ ftrace_event_enable_disable(call, 0);
+
+ pr_cont("OK\n");
+ }
+
+ /* Now test at the sub system level */
+
+ pr_info("Running tests on trace event systems:\n");
+
+ list_for_each_entry(system, &event_subsystems, list) {
+
+ /* the ftrace system is special, skip it */
+ if (strcmp(system->name, "ftrace") == 0)
+ continue;
+
+ pr_info("Testing event system %s: ", system->name);
+
+ ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1);
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error enabling system %s\n",
+ system->name);
+ continue;
+ }
+
+ event_test_stuff();
+
+ ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
+ if (WARN_ON_ONCE(ret))
+ pr_warning("error disabling system %s\n",
+ system->name);
+
+ pr_cont("OK\n");
+ }
+
+ /* Test with all events enabled */
+
+ pr_info("Running tests on all trace events:\n");
+ pr_info("Testing all events: ");
+
+ ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1);
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error enabling all events\n");
+ return;
+ }
+
+ event_test_stuff();
+
+ /* reset sysname */
+ ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0);
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error disabling all events\n");
+ return;
+ }
+
+ pr_cont("OK\n");
+}
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+static DEFINE_PER_CPU(atomic_t, test_event_disable);
+
+static void
+function_test_events_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ring_buffer_event *event;
+ struct ftrace_entry *entry;
+ unsigned long flags;
+ long disabled;
+ int resched;
+ int cpu;
+ int pc;
+
+ pc = preempt_count();
+ resched = ftrace_preempt_disable();
+ cpu = raw_smp_processor_id();
+ disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+
+ if (disabled != 1)
+ goto out;
+
+ local_save_flags(flags);
+
+ event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+ flags, pc);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+ entry->parent_ip = parent_ip;
+
+ trace_nowake_buffer_unlock_commit(event, flags, pc);
+
+ out:
+ atomic_dec(&per_cpu(test_event_disable, cpu));
+ ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_ops __initdata =
+{
+ .func = function_test_events_call,
+};
+
+static __init void event_trace_self_test_with_function(void)
+{
+ register_ftrace_function(&trace_ops);
+ pr_info("Running tests again, along with the function tracer\n");
+ event_trace_self_tests();
+ unregister_ftrace_function(&trace_ops);
+}
+#else
+static __init void event_trace_self_test_with_function(void)
+{
+}
+#endif
+
+static __init int event_trace_self_tests_init(void)
+{
+
+ event_trace_self_tests();
+
+ event_trace_self_test_with_function();
+
+ return 0;
+}
+
+late_initcall(event_trace_self_tests_init);
+
+#endif
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
+#include <linux/mutex.h>
#include "trace.h"
#include "trace_output.h"
-static int filter_pred_64(struct filter_pred *pred, void *event)
+static DEFINE_MUTEX(filter_mutex);
+
+enum filter_op_ids
+{
+ OP_OR,
+ OP_AND,
+ OP_NE,
+ OP_EQ,
+ OP_LT,
+ OP_LE,
+ OP_GT,
+ OP_GE,
+ OP_NONE,
+ OP_OPEN_PAREN,
+};
+
+struct filter_op {
+ int id;
+ char *string;
+ int precedence;
+};
+
+static struct filter_op filter_ops[] = {
+ { OP_OR, "||", 1 },
+ { OP_AND, "&&", 2 },
+ { OP_NE, "!=", 4 },
+ { OP_EQ, "==", 4 },
+ { OP_LT, "<", 5 },
+ { OP_LE, "<=", 5 },
+ { OP_GT, ">", 5 },
+ { OP_GE, ">=", 5 },
+ { OP_NONE, "OP_NONE", 0 },
+ { OP_OPEN_PAREN, "(", 0 },
+};
+
+enum {
+ FILT_ERR_NONE,
+ FILT_ERR_INVALID_OP,
+ FILT_ERR_UNBALANCED_PAREN,
+ FILT_ERR_TOO_MANY_OPERANDS,
+ FILT_ERR_OPERAND_TOO_LONG,
+ FILT_ERR_FIELD_NOT_FOUND,
+ FILT_ERR_ILLEGAL_FIELD_OP,
+ FILT_ERR_ILLEGAL_INTVAL,
+ FILT_ERR_BAD_SUBSYS_FILTER,
+ FILT_ERR_TOO_MANY_PREDS,
+ FILT_ERR_MISSING_FIELD,
+ FILT_ERR_INVALID_FILTER,
+};
+
+static char *err_text[] = {
+ "No error",
+ "Invalid operator",
+ "Unbalanced parens",
+ "Too many operands",
+ "Operand too long",
+ "Field not found",
+ "Illegal operation for field type",
+ "Illegal integer value",
+ "Couldn't find or set field in one of a subsystem's events",
+ "Too many terms in predicate expression",
+ "Missing field name and/or value",
+ "Meaningless filter expression",
+};
+
+struct opstack_op {
+ int op;
+ struct list_head list;
+};
+
+struct postfix_elt {
+ int op;
+ char *operand;
+ struct list_head list;
+};
+
+struct filter_parse_state {
+ struct filter_op *ops;
+ struct list_head opstack;
+ struct list_head postfix;
+ int lasterr;
+ int lasterr_pos;
+
+ struct {
+ char *string;
+ unsigned int cnt;
+ unsigned int tail;
+ } infix;
+
+ struct {
+ char string[MAX_FILTER_STR_VAL];
+ int pos;
+ unsigned int tail;
+ } operand;
+};
+
+DEFINE_COMPARISON_PRED(s64);
+DEFINE_COMPARISON_PRED(u64);
+DEFINE_COMPARISON_PRED(s32);
+DEFINE_COMPARISON_PRED(u32);
+DEFINE_COMPARISON_PRED(s16);
+DEFINE_COMPARISON_PRED(u16);
+DEFINE_COMPARISON_PRED(s8);
+DEFINE_COMPARISON_PRED(u8);
+
+DEFINE_EQUALITY_PRED(64);
+DEFINE_EQUALITY_PRED(32);
+DEFINE_EQUALITY_PRED(16);
+DEFINE_EQUALITY_PRED(8);
+
+static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
+ void *event __attribute((unused)),
+ int val1, int val2)
+{
+ return val1 && val2;
+}
+
+static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
+ void *event __attribute((unused)),
+ int val1, int val2)
+{
+ return val1 || val2;
+}
+
+/* Filter predicate for fixed sized arrays of characters */
+static int filter_pred_string(struct filter_pred *pred, void *event,
+ int val1, int val2)
{
- u64 *addr = (u64 *)(event + pred->offset);
- u64 val = (u64)pred->val;
- int match;
+ char *addr = (char *)(event + pred->offset);
+ int cmp, match;
+
+ cmp = strncmp(addr, pred->str_val, pred->str_len);
- match = (val == *addr) ^ pred->not;
+ match = (!cmp) ^ pred->not;
return match;
}
-static int filter_pred_32(struct filter_pred *pred, void *event)
+/*
+ * Filter predicate for dynamic sized arrays of characters.
+ * These are implemented through a list of strings at the end
+ * of the entry.
+ * Also each of these strings have a field in the entry which
+ * contains its offset from the beginning of the entry.
+ * We have then first to get this field, dereference it
+ * and add it to the address of the entry, and at last we have
+ * the address of the string.
+ */
+static int filter_pred_strloc(struct filter_pred *pred, void *event,
+ int val1, int val2)
{
- u32 *addr = (u32 *)(event + pred->offset);
- u32 val = (u32)pred->val;
- int match;
+ int str_loc = *(int *)(event + pred->offset);
+ char *addr = (char *)(event + str_loc);
+ int cmp, match;
+
+ cmp = strncmp(addr, pred->str_val, pred->str_len);
- match = (val == *addr) ^ pred->not;
+ match = (!cmp) ^ pred->not;
return match;
}
-static int filter_pred_16(struct filter_pred *pred, void *event)
+static int filter_pred_none(struct filter_pred *pred, void *event,
+ int val1, int val2)
+{
+ return 0;
+}
+
+/* return 1 if event matches, 0 otherwise (discard) */
+int filter_match_preds(struct ftrace_event_call *call, void *rec)
{
- u16 *addr = (u16 *)(event + pred->offset);
- u16 val = (u16)pred->val;
- int match;
+ struct event_filter *filter = call->filter;
+ int match, top = 0, val1 = 0, val2 = 0;
+ int stack[MAX_FILTER_PRED];
+ struct filter_pred *pred;
+ int i;
+
+ for (i = 0; i < filter->n_preds; i++) {
+ pred = filter->preds[i];
+ if (!pred->pop_n) {
+ match = pred->fn(pred, rec, val1, val2);
+ stack[top++] = match;
+ continue;
+ }
+ if (pred->pop_n > top) {
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+ val1 = stack[--top];
+ val2 = stack[--top];
+ match = pred->fn(pred, rec, val1, val2);
+ stack[top++] = match;
+ }
- match = (val == *addr) ^ pred->not;
+ return stack[--top];
+}
+EXPORT_SYMBOL_GPL(filter_match_preds);
- return match;
+static void parse_error(struct filter_parse_state *ps, int err, int pos)
+{
+ ps->lasterr = err;
+ ps->lasterr_pos = pos;
}
-static int filter_pred_8(struct filter_pred *pred, void *event)
+static void remove_filter_string(struct event_filter *filter)
{
- u8 *addr = (u8 *)(event + pred->offset);
- u8 val = (u8)pred->val;
- int match;
+ kfree(filter->filter_string);
+ filter->filter_string = NULL;
+}
- match = (val == *addr) ^ pred->not;
+static int replace_filter_string(struct event_filter *filter,
+ char *filter_string)
+{
+ kfree(filter->filter_string);
+ filter->filter_string = kstrdup(filter_string, GFP_KERNEL);
+ if (!filter->filter_string)
+ return -ENOMEM;
- return match;
+ return 0;
}
-static int filter_pred_string(struct filter_pred *pred, void *event)
+static int append_filter_string(struct event_filter *filter,
+ char *string)
{
- char *addr = (char *)(event + pred->offset);
- int cmp, match;
+ int newlen;
+ char *new_filter_string;
- cmp = strncmp(addr, pred->str_val, pred->str_len);
+ BUG_ON(!filter->filter_string);
+ newlen = strlen(filter->filter_string) + strlen(string) + 1;
+ new_filter_string = kmalloc(newlen, GFP_KERNEL);
+ if (!new_filter_string)
+ return -ENOMEM;
- match = (!cmp) ^ pred->not;
+ strcpy(new_filter_string, filter->filter_string);
+ strcat(new_filter_string, string);
+ kfree(filter->filter_string);
+ filter->filter_string = new_filter_string;
- return match;
+ return 0;
}
-/* return 1 if event matches, 0 otherwise (discard) */
-int filter_match_preds(struct ftrace_event_call *call, void *rec)
+static void append_filter_err(struct filter_parse_state *ps,
+ struct event_filter *filter)
{
- int i, matched, and_failed = 0;
- struct filter_pred *pred;
+ int pos = ps->lasterr_pos;
+ char *buf, *pbuf;
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (call->preds[i]) {
- pred = call->preds[i];
- if (and_failed && !pred->or)
- continue;
- matched = pred->fn(pred, rec);
- if (!matched && !pred->or) {
- and_failed = 1;
- continue;
- } else if (matched && pred->or)
- return 1;
- } else
- break;
- }
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return;
- if (and_failed)
- return 0;
+ append_filter_string(filter, "\n");
+ memset(buf, ' ', PAGE_SIZE);
+ if (pos > PAGE_SIZE - 128)
+ pos = 0;
+ buf[pos] = '^';
+ pbuf = &buf[pos] + 1;
- return 1;
+ sprintf(pbuf, "\nparse_error: %s\n", err_text[ps->lasterr]);
+ append_filter_string(filter, buf);
+ free_page((unsigned long) buf);
}
-void filter_print_preds(struct filter_pred **preds, struct trace_seq *s)
+void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
{
- char *field_name;
- struct filter_pred *pred;
- int i;
+ struct event_filter *filter = call->filter;
- if (!preds) {
+ mutex_lock(&filter_mutex);
+ if (filter->filter_string)
+ trace_seq_printf(s, "%s\n", filter->filter_string);
+ else
trace_seq_printf(s, "none\n");
- return;
- }
+ mutex_unlock(&filter_mutex);
+}
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (preds[i]) {
- pred = preds[i];
- field_name = pred->field_name;
- if (i)
- trace_seq_printf(s, pred->or ? "|| " : "&& ");
- trace_seq_printf(s, "%s ", field_name);
- trace_seq_printf(s, pred->not ? "!= " : "== ");
- if (pred->str_val)
- trace_seq_printf(s, "%s\n", pred->str_val);
- else
- trace_seq_printf(s, "%llu\n", pred->val);
- } else
- break;
- }
+void print_subsystem_event_filter(struct event_subsystem *system,
+ struct trace_seq *s)
+{
+ struct event_filter *filter = system->filter;
+
+ mutex_lock(&filter_mutex);
+ if (filter->filter_string)
+ trace_seq_printf(s, "%s\n", filter->filter_string);
+ else
+ trace_seq_printf(s, "none\n");
+ mutex_unlock(&filter_mutex);
}
static struct ftrace_event_field *
return NULL;
}
-void filter_free_pred(struct filter_pred *pred)
+static void filter_free_pred(struct filter_pred *pred)
{
if (!pred)
return;
kfree(pred->field_name);
- kfree(pred->str_val);
kfree(pred);
}
-void filter_free_preds(struct ftrace_event_call *call)
+static void filter_clear_pred(struct filter_pred *pred)
{
- int i;
+ kfree(pred->field_name);
+ pred->field_name = NULL;
+ pred->str_len = 0;
+}
- if (call->preds) {
- for (i = 0; i < MAX_FILTER_PRED; i++)
- filter_free_pred(call->preds[i]);
- kfree(call->preds);
- call->preds = NULL;
+static int filter_set_pred(struct filter_pred *dest,
+ struct filter_pred *src,
+ filter_pred_fn_t fn)
+{
+ *dest = *src;
+ if (src->field_name) {
+ dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
+ if (!dest->field_name)
+ return -ENOMEM;
}
+ dest->fn = fn;
+
+ return 0;
}
-void filter_free_subsystem_preds(struct event_subsystem *system)
+static void filter_disable_preds(struct ftrace_event_call *call)
{
- struct ftrace_event_call *call = __start_ftrace_events;
+ struct event_filter *filter = call->filter;
int i;
- if (system->preds) {
- for (i = 0; i < MAX_FILTER_PRED; i++)
- filter_free_pred(system->preds[i]);
- kfree(system->preds);
- system->preds = NULL;
- }
+ call->filter_active = 0;
+ filter->n_preds = 0;
- events_for_each(call) {
- if (!call->name || !call->regfunc)
- continue;
+ for (i = 0; i < MAX_FILTER_PRED; i++)
+ filter->preds[i]->fn = filter_pred_none;
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+ struct event_filter *filter = call->filter;
+ int i;
- if (!strcmp(call->system, system->name))
- filter_free_preds(call);
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ if (filter->preds[i])
+ filter_free_pred(filter->preds[i]);
}
+ kfree(filter->preds);
+ kfree(filter);
+ call->filter = NULL;
}
-static int __filter_add_pred(struct ftrace_event_call *call,
- struct filter_pred *pred)
+int init_preds(struct ftrace_event_call *call)
{
+ struct event_filter *filter;
+ struct filter_pred *pred;
int i;
- if (call->preds && !pred->compound)
- filter_free_preds(call);
+ filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!call->filter)
+ return -ENOMEM;
- if (!call->preds) {
- call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
- GFP_KERNEL);
- if (!call->preds)
- return -ENOMEM;
- }
+ call->filter_active = 0;
+ filter->n_preds = 0;
+
+ filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
+ if (!filter->preds)
+ goto oom;
for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (!call->preds[i]) {
- call->preds[i] = pred;
- return 0;
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ goto oom;
+ pred->fn = filter_pred_none;
+ filter->preds[i] = pred;
+ }
+
+ return 0;
+
+oom:
+ destroy_preds(call);
+
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(init_preds);
+
+static void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+ struct event_filter *filter = system->filter;
+ struct ftrace_event_call *call;
+ int i;
+
+ if (filter->n_preds) {
+ for (i = 0; i < filter->n_preds; i++)
+ filter_free_pred(filter->preds[i]);
+ kfree(filter->preds);
+ filter->preds = NULL;
+ filter->n_preds = 0;
+ }
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (!call->define_fields)
+ continue;
+
+ if (!strcmp(call->system, system->name)) {
+ filter_disable_preds(call);
+ remove_filter_string(call->filter);
}
}
+ mutex_unlock(&event_mutex);
+}
+
+static int filter_add_pred_fn(struct filter_parse_state *ps,
+ struct ftrace_event_call *call,
+ struct filter_pred *pred,
+ filter_pred_fn_t fn)
+{
+ struct event_filter *filter = call->filter;
+ int idx, err;
+
+ if (filter->n_preds == MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
+ }
+
+ idx = filter->n_preds;
+ filter_clear_pred(filter->preds[idx]);
+ err = filter_set_pred(filter->preds[idx], pred, fn);
+ if (err)
+ return err;
- return -ENOSPC;
+ filter->n_preds++;
+ call->filter_active = 1;
+
+ return 0;
}
+enum {
+ FILTER_STATIC_STRING = 1,
+ FILTER_DYN_STRING
+};
+
static int is_string_field(const char *type)
{
+ if (strstr(type, "__data_loc") && strstr(type, "char"))
+ return FILTER_DYN_STRING;
+
if (strchr(type, '[') && strstr(type, "char"))
- return 1;
+ return FILTER_STATIC_STRING;
return 0;
}
-int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred)
+static int is_legal_op(struct ftrace_event_field *field, int op)
{
- struct ftrace_event_field *field;
-
- field = find_event_field(call, pred->field_name);
- if (!field)
- return -EINVAL;
+ if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE))
+ return 0;
- pred->offset = field->offset;
+ return 1;
+}
- if (is_string_field(field->type)) {
- if (!pred->str_val)
- return -EINVAL;
- pred->fn = filter_pred_string;
- pred->str_len = field->size;
- return __filter_add_pred(call, pred);
- } else {
- if (pred->str_val)
- return -EINVAL;
- }
+static filter_pred_fn_t select_comparison_fn(int op, int field_size,
+ int field_is_signed)
+{
+ filter_pred_fn_t fn = NULL;
- switch (field->size) {
+ switch (field_size) {
case 8:
- pred->fn = filter_pred_64;
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_64;
+ else if (field_is_signed)
+ fn = filter_pred_s64;
+ else
+ fn = filter_pred_u64;
break;
case 4:
- pred->fn = filter_pred_32;
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_32;
+ else if (field_is_signed)
+ fn = filter_pred_s32;
+ else
+ fn = filter_pred_u32;
break;
case 2:
- pred->fn = filter_pred_16;
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_16;
+ else if (field_is_signed)
+ fn = filter_pred_s16;
+ else
+ fn = filter_pred_u16;
break;
case 1:
- pred->fn = filter_pred_8;
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_8;
+ else if (field_is_signed)
+ fn = filter_pred_s8;
+ else
+ fn = filter_pred_u8;
break;
- default:
- return -EINVAL;
}
- return __filter_add_pred(call, pred);
+ return fn;
}
-static struct filter_pred *copy_pred(struct filter_pred *pred)
+static int filter_add_pred(struct filter_parse_state *ps,
+ struct ftrace_event_call *call,
+ struct filter_pred *pred)
{
- struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL);
- if (!new_pred)
- return NULL;
+ struct ftrace_event_field *field;
+ filter_pred_fn_t fn;
+ unsigned long long val;
+ int string_type;
+
+ pred->fn = filter_pred_none;
+
+ if (pred->op == OP_AND) {
+ pred->pop_n = 2;
+ return filter_add_pred_fn(ps, call, pred, filter_pred_and);
+ } else if (pred->op == OP_OR) {
+ pred->pop_n = 2;
+ return filter_add_pred_fn(ps, call, pred, filter_pred_or);
+ }
+
+ field = find_event_field(call, pred->field_name);
+ if (!field) {
+ parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
+ return -EINVAL;
+ }
- memcpy(new_pred, pred, sizeof(*pred));
+ pred->offset = field->offset;
- if (pred->field_name) {
- new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
- if (!new_pred->field_name) {
- kfree(new_pred);
- return NULL;
- }
+ if (!is_legal_op(field, pred->op)) {
+ parse_error(ps, FILT_ERR_ILLEGAL_FIELD_OP, 0);
+ return -EINVAL;
}
- if (pred->str_val) {
- new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL);
- if (!new_pred->str_val) {
- filter_free_pred(new_pred);
- return NULL;
+ string_type = is_string_field(field->type);
+ if (string_type) {
+ if (string_type == FILTER_STATIC_STRING)
+ fn = filter_pred_string;
+ else
+ fn = filter_pred_strloc;
+ pred->str_len = field->size;
+ if (pred->op == OP_NE)
+ pred->not = 1;
+ return filter_add_pred_fn(ps, call, pred, fn);
+ } else {
+ if (strict_strtoull(pred->str_val, 0, &val)) {
+ parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
+ return -EINVAL;
}
+ pred->val = val;
+ }
+
+ fn = select_comparison_fn(pred->op, field->size, field->is_signed);
+ if (!fn) {
+ parse_error(ps, FILT_ERR_INVALID_OP, 0);
+ return -EINVAL;
}
- return new_pred;
+ if (pred->op == OP_NE)
+ pred->not = 1;
+
+ return filter_add_pred_fn(ps, call, pred, fn);
}
-int filter_add_subsystem_pred(struct event_subsystem *system,
- struct filter_pred *pred)
+static int filter_add_subsystem_pred(struct filter_parse_state *ps,
+ struct event_subsystem *system,
+ struct filter_pred *pred,
+ char *filter_string)
{
- struct ftrace_event_call *call = __start_ftrace_events;
- struct filter_pred *event_pred;
- int i;
-
- if (system->preds && !pred->compound)
- filter_free_subsystem_preds(system);
+ struct event_filter *filter = system->filter;
+ struct ftrace_event_call *call;
+ int err = 0;
- if (!system->preds) {
- system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+ if (!filter->preds) {
+ filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
GFP_KERNEL);
- if (!system->preds)
+
+ if (!filter->preds)
return -ENOMEM;
}
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (!system->preds[i]) {
- system->preds[i] = pred;
- break;
- }
+ if (filter->n_preds == MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
}
- if (i == MAX_FILTER_PRED)
- return -ENOSPC;
+ filter->preds[filter->n_preds] = pred;
+ filter->n_preds++;
- events_for_each(call) {
- int err;
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
- if (!call->name || !call->regfunc)
+ if (!call->define_fields)
continue;
if (strcmp(call->system, system->name))
continue;
- if (!find_event_field(call, pred->field_name))
- continue;
+ err = filter_add_pred(ps, call, pred);
+ if (err) {
+ mutex_unlock(&event_mutex);
+ filter_free_subsystem_preds(system);
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ goto out;
+ }
+ replace_filter_string(call->filter, filter_string);
+ }
+ mutex_unlock(&event_mutex);
+out:
+ return err;
+}
- event_pred = copy_pred(pred);
- if (!event_pred)
- goto oom;
+static void parse_init(struct filter_parse_state *ps,
+ struct filter_op *ops,
+ char *infix_string)
+{
+ memset(ps, '\0', sizeof(*ps));
- err = filter_add_pred(call, event_pred);
- if (err)
- filter_free_pred(event_pred);
- if (err == -ENOMEM)
- goto oom;
+ ps->infix.string = infix_string;
+ ps->infix.cnt = strlen(infix_string);
+ ps->ops = ops;
+
+ INIT_LIST_HEAD(&ps->opstack);
+ INIT_LIST_HEAD(&ps->postfix);
+}
+
+static char infix_next(struct filter_parse_state *ps)
+{
+ ps->infix.cnt--;
+
+ return ps->infix.string[ps->infix.tail++];
+}
+
+static char infix_peek(struct filter_parse_state *ps)
+{
+ if (ps->infix.tail == strlen(ps->infix.string))
+ return 0;
+
+ return ps->infix.string[ps->infix.tail];
+}
+
+static void infix_advance(struct filter_parse_state *ps)
+{
+ ps->infix.cnt--;
+ ps->infix.tail++;
+}
+
+static inline int is_precedence_lower(struct filter_parse_state *ps,
+ int a, int b)
+{
+ return ps->ops[a].precedence < ps->ops[b].precedence;
+}
+
+static inline int is_op_char(struct filter_parse_state *ps, char c)
+{
+ int i;
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (ps->ops[i].string[0] == c)
+ return 1;
}
return 0;
+}
-oom:
- system->preds[i] = NULL;
- return -ENOMEM;
+static int infix_get_op(struct filter_parse_state *ps, char firstc)
+{
+ char nextc = infix_peek(ps);
+ char opstr[3];
+ int i;
+
+ opstr[0] = firstc;
+ opstr[1] = nextc;
+ opstr[2] = '\0';
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (!strcmp(opstr, ps->ops[i].string)) {
+ infix_advance(ps);
+ return ps->ops[i].id;
+ }
+ }
+
+ opstr[1] = '\0';
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (!strcmp(opstr, ps->ops[i].string))
+ return ps->ops[i].id;
+ }
+
+ return OP_NONE;
}
-int filter_parse(char **pbuf, struct filter_pred *pred)
+static inline void clear_operand_string(struct filter_parse_state *ps)
{
- char *tmp, *tok, *val_str = NULL;
- int tok_n = 0;
+ memset(ps->operand.string, '\0', MAX_FILTER_STR_VAL);
+ ps->operand.tail = 0;
+}
- /* field ==/!= number, or/and field ==/!= number, number */
- while ((tok = strsep(pbuf, " \n"))) {
- if (tok_n == 0) {
- if (!strcmp(tok, "0")) {
- pred->clear = 1;
- return 0;
- } else if (!strcmp(tok, "&&")) {
- pred->or = 0;
- pred->compound = 1;
- } else if (!strcmp(tok, "||")) {
- pred->or = 1;
- pred->compound = 1;
- } else
- pred->field_name = tok;
- tok_n = 1;
+static inline int append_operand_char(struct filter_parse_state *ps, char c)
+{
+ if (ps->operand.tail == MAX_FILTER_STR_VAL - 1)
+ return -EINVAL;
+
+ ps->operand.string[ps->operand.tail++] = c;
+
+ return 0;
+}
+
+static int filter_opstack_push(struct filter_parse_state *ps, int op)
+{
+ struct opstack_op *opstack_op;
+
+ opstack_op = kmalloc(sizeof(*opstack_op), GFP_KERNEL);
+ if (!opstack_op)
+ return -ENOMEM;
+
+ opstack_op->op = op;
+ list_add(&opstack_op->list, &ps->opstack);
+
+ return 0;
+}
+
+static int filter_opstack_empty(struct filter_parse_state *ps)
+{
+ return list_empty(&ps->opstack);
+}
+
+static int filter_opstack_top(struct filter_parse_state *ps)
+{
+ struct opstack_op *opstack_op;
+
+ if (filter_opstack_empty(ps))
+ return OP_NONE;
+
+ opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+
+ return opstack_op->op;
+}
+
+static int filter_opstack_pop(struct filter_parse_state *ps)
+{
+ struct opstack_op *opstack_op;
+ int op;
+
+ if (filter_opstack_empty(ps))
+ return OP_NONE;
+
+ opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+ op = opstack_op->op;
+ list_del(&opstack_op->list);
+
+ kfree(opstack_op);
+
+ return op;
+}
+
+static void filter_opstack_clear(struct filter_parse_state *ps)
+{
+ while (!filter_opstack_empty(ps))
+ filter_opstack_pop(ps);
+}
+
+static char *curr_operand(struct filter_parse_state *ps)
+{
+ return ps->operand.string;
+}
+
+static int postfix_append_operand(struct filter_parse_state *ps, char *operand)
+{
+ struct postfix_elt *elt;
+
+ elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+ if (!elt)
+ return -ENOMEM;
+
+ elt->op = OP_NONE;
+ elt->operand = kstrdup(operand, GFP_KERNEL);
+ if (!elt->operand) {
+ kfree(elt);
+ return -ENOMEM;
+ }
+
+ list_add_tail(&elt->list, &ps->postfix);
+
+ return 0;
+}
+
+static int postfix_append_op(struct filter_parse_state *ps, int op)
+{
+ struct postfix_elt *elt;
+
+ elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+ if (!elt)
+ return -ENOMEM;
+
+ elt->op = op;
+ elt->operand = NULL;
+
+ list_add_tail(&elt->list, &ps->postfix);
+
+ return 0;
+}
+
+static void postfix_clear(struct filter_parse_state *ps)
+{
+ struct postfix_elt *elt;
+
+ while (!list_empty(&ps->postfix)) {
+ elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
+ kfree(elt->operand);
+ list_del(&elt->list);
+ }
+}
+
+static int filter_parse(struct filter_parse_state *ps)
+{
+ int in_string = 0;
+ int op, top_op;
+ char ch;
+
+ while ((ch = infix_next(ps))) {
+ if (ch == '"') {
+ in_string ^= 1;
continue;
}
- if (tok_n == 1) {
- if (!pred->field_name)
- pred->field_name = tok;
- else if (!strcmp(tok, "!="))
- pred->not = 1;
- else if (!strcmp(tok, "=="))
- pred->not = 0;
- else {
- pred->field_name = NULL;
+
+ if (in_string)
+ goto parse_operand;
+
+ if (isspace(ch))
+ continue;
+
+ if (is_op_char(ps, ch)) {
+ op = infix_get_op(ps, ch);
+ if (op == OP_NONE) {
+ parse_error(ps, FILT_ERR_INVALID_OP, 0);
return -EINVAL;
}
- tok_n = 2;
+
+ if (strlen(curr_operand(ps))) {
+ postfix_append_operand(ps, curr_operand(ps));
+ clear_operand_string(ps);
+ }
+
+ while (!filter_opstack_empty(ps)) {
+ top_op = filter_opstack_top(ps);
+ if (!is_precedence_lower(ps, top_op, op)) {
+ top_op = filter_opstack_pop(ps);
+ postfix_append_op(ps, top_op);
+ continue;
+ }
+ break;
+ }
+
+ filter_opstack_push(ps, op);
continue;
}
- if (tok_n == 2) {
- if (pred->compound) {
- if (!strcmp(tok, "!="))
- pred->not = 1;
- else if (!strcmp(tok, "=="))
- pred->not = 0;
- else {
- pred->field_name = NULL;
- return -EINVAL;
- }
- } else {
- val_str = tok;
- break; /* done */
+
+ if (ch == '(') {
+ filter_opstack_push(ps, OP_OPEN_PAREN);
+ continue;
+ }
+
+ if (ch == ')') {
+ if (strlen(curr_operand(ps))) {
+ postfix_append_operand(ps, curr_operand(ps));
+ clear_operand_string(ps);
+ }
+
+ top_op = filter_opstack_pop(ps);
+ while (top_op != OP_NONE) {
+ if (top_op == OP_OPEN_PAREN)
+ break;
+ postfix_append_op(ps, top_op);
+ top_op = filter_opstack_pop(ps);
+ }
+ if (top_op == OP_NONE) {
+ parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+ return -EINVAL;
}
- tok_n = 3;
continue;
}
- if (tok_n == 3) {
- val_str = tok;
- break; /* done */
+parse_operand:
+ if (append_operand_char(ps, ch)) {
+ parse_error(ps, FILT_ERR_OPERAND_TOO_LONG, 0);
+ return -EINVAL;
}
}
- if (!val_str) {
- pred->field_name = NULL;
- return -EINVAL;
+ if (strlen(curr_operand(ps)))
+ postfix_append_operand(ps, curr_operand(ps));
+
+ while (!filter_opstack_empty(ps)) {
+ top_op = filter_opstack_pop(ps);
+ if (top_op == OP_NONE)
+ break;
+ if (top_op == OP_OPEN_PAREN) {
+ parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+ return -EINVAL;
+ }
+ postfix_append_op(ps, top_op);
}
- pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
- if (!pred->field_name)
- return -ENOMEM;
+ return 0;
+}
- pred->val = simple_strtoull(val_str, &tmp, 0);
- if (tmp == val_str) {
- pred->str_val = kstrdup(val_str, GFP_KERNEL);
- if (!pred->str_val)
- return -ENOMEM;
- } else if (*tmp != '\0')
+static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
+{
+ struct filter_pred *pred;
+
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return NULL;
+
+ pred->field_name = kstrdup(operand1, GFP_KERNEL);
+ if (!pred->field_name) {
+ kfree(pred);
+ return NULL;
+ }
+
+ strcpy(pred->str_val, operand2);
+ pred->str_len = strlen(operand2);
+
+ pred->op = op;
+
+ return pred;
+}
+
+static struct filter_pred *create_logical_pred(int op)
+{
+ struct filter_pred *pred;
+
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return NULL;
+
+ pred->op = op;
+
+ return pred;
+}
+
+static int check_preds(struct filter_parse_state *ps)
+{
+ int n_normal_preds = 0, n_logical_preds = 0;
+ struct postfix_elt *elt;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE)
+ continue;
+
+ if (elt->op == OP_AND || elt->op == OP_OR) {
+ n_logical_preds++;
+ continue;
+ }
+ n_normal_preds++;
+ }
+
+ if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+ parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
return -EINVAL;
+ }
return 0;
}
+static int replace_preds(struct event_subsystem *system,
+ struct ftrace_event_call *call,
+ struct filter_parse_state *ps,
+ char *filter_string)
+{
+ char *operand1 = NULL, *operand2 = NULL;
+ struct filter_pred *pred;
+ struct postfix_elt *elt;
+ int err;
+
+ err = check_preds(ps);
+ if (err)
+ return err;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE) {
+ if (!operand1)
+ operand1 = elt->operand;
+ else if (!operand2)
+ operand2 = elt->operand;
+ else {
+ parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
+ return -EINVAL;
+ }
+ continue;
+ }
+
+ if (elt->op == OP_AND || elt->op == OP_OR) {
+ pred = create_logical_pred(elt->op);
+ if (call) {
+ err = filter_add_pred(ps, call, pred);
+ filter_free_pred(pred);
+ } else
+ err = filter_add_subsystem_pred(ps, system,
+ pred, filter_string);
+ if (err)
+ return err;
+
+ operand1 = operand2 = NULL;
+ continue;
+ }
+
+ if (!operand1 || !operand2) {
+ parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
+ return -EINVAL;
+ }
+
+ pred = create_pred(elt->op, operand1, operand2);
+ if (call) {
+ err = filter_add_pred(ps, call, pred);
+ filter_free_pred(pred);
+ } else
+ err = filter_add_subsystem_pred(ps, system, pred,
+ filter_string);
+ if (err)
+ return err;
+
+ operand1 = operand2 = NULL;
+ }
+
+ return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+ int err;
+
+ struct filter_parse_state *ps;
+
+ mutex_lock(&filter_mutex);
+
+ if (!strcmp(strstrip(filter_string), "0")) {
+ filter_disable_preds(call);
+ remove_filter_string(call->filter);
+ mutex_unlock(&filter_mutex);
+ return 0;
+ }
+
+ err = -ENOMEM;
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ goto out_unlock;
+
+ filter_disable_preds(call);
+ replace_filter_string(call->filter, filter_string);
+
+ parse_init(ps, filter_ops, filter_string);
+ err = filter_parse(ps);
+ if (err) {
+ append_filter_err(ps, call->filter);
+ goto out;
+ }
+
+ err = replace_preds(NULL, call, ps, filter_string);
+ if (err)
+ append_filter_err(ps, call->filter);
+
+out:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+out_unlock:
+ mutex_unlock(&filter_mutex);
+
+ return err;
+}
+
+int apply_subsystem_event_filter(struct event_subsystem *system,
+ char *filter_string)
+{
+ int err;
+
+ struct filter_parse_state *ps;
+
+ mutex_lock(&filter_mutex);
+
+ if (!strcmp(strstrip(filter_string), "0")) {
+ filter_free_subsystem_preds(system);
+ remove_filter_string(system->filter);
+ mutex_unlock(&filter_mutex);
+ return 0;
+ }
+
+ err = -ENOMEM;
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ goto out_unlock;
+
+ filter_free_subsystem_preds(system);
+ replace_filter_string(system->filter, filter_string);
+
+ parse_init(ps, filter_ops, filter_string);
+ err = filter_parse(ps);
+ if (err) {
+ append_filter_err(ps, system->filter);
+ goto out;
+ }
+
+ err = replace_preds(system, NULL, ps, filter_string);
+ if (err)
+ append_filter_err(ps, system->filter);
+
+out:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+out_unlock:
+ mutex_unlock(&filter_mutex);
+
+ return err;
+}
+++ /dev/null
-/*
- * Stage 1 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * struct ftrace_raw_<call> {
- * struct trace_entry ent;
- * <type> <item>;
- * <type2> <item2>[<len>];
- * [...]
- * };
- *
- * The <type> <item> is created by the __field(type, item) macro or
- * the __array(type2, item2, len) macro.
- * We simply do "type item;", and that will create the fields
- * in the structure.
- */
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt)
-
-#undef __array
-#define __array(type, item, len) type item[len];
-
-#undef __field
-#define __field(type, item) type item;
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
- struct ftrace_raw_##name { \
- struct trace_entry ent; \
- tstruct \
- }; \
- static struct ftrace_event_call event_##name
-
-#include <trace/trace_event_types.h>
+++ /dev/null
-/*
- * Stage 2 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * enum print_line_t
- * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
- * {
- * struct trace_seq *s = &iter->seq;
- * struct ftrace_raw_<call> *field; <-- defined in stage 1
- * struct trace_entry *entry;
- * int ret;
- *
- * entry = iter->ent;
- *
- * if (entry->type != event_<call>.id) {
- * WARN_ON_ONCE(1);
- * return TRACE_TYPE_UNHANDLED;
- * }
- *
- * field = (typeof(field))entry;
- *
- * ret = trace_seq_printf(s, <TP_printk> "\n");
- * if (!ret)
- * return TRACE_TYPE_PARTIAL_LINE;
- *
- * return TRACE_TYPE_HANDLED;
- * }
- *
- * This is the method used to print the raw event to the trace
- * output format. Note, this is not needed if the data is read
- * in binary.
- */
-
-#undef __entry
-#define __entry field
-
-#undef TP_printk
-#define TP_printk(fmt, args...) fmt "\n", args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
-enum print_line_t \
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
-{ \
- struct trace_seq *s = &iter->seq; \
- struct ftrace_raw_##call *field; \
- struct trace_entry *entry; \
- int ret; \
- \
- entry = iter->ent; \
- \
- if (entry->type != event_##call.id) { \
- WARN_ON_ONCE(1); \
- return TRACE_TYPE_UNHANDLED; \
- } \
- \
- field = (typeof(field))entry; \
- \
- ret = trace_seq_printf(s, #call ": " print); \
- if (!ret) \
- return TRACE_TYPE_PARTIAL_LINE; \
- \
- return TRACE_TYPE_HANDLED; \
-}
-
-#include <trace/trace_event_types.h>
-
-/*
- * Setup the showing format of trace point.
- *
- * int
- * ftrace_format_##call(struct trace_seq *s)
- * {
- * struct ftrace_raw_##call field;
- * int ret;
- *
- * ret = trace_seq_printf(s, #type " " #item ";"
- * " offset:%u; size:%u;\n",
- * offsetof(struct ftrace_raw_##call, item),
- * sizeof(field.type));
- *
- * }
- */
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef __field
-#define __field(type, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%u;\tsize:%u;\n", \
- (unsigned int)offsetof(typeof(field), item), \
- (unsigned int)sizeof(field.item)); \
- if (!ret) \
- return 0;
-
-#undef __array
-#define __array(type, item, len) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%u;\tsize:%u;\n", \
- (unsigned int)offsetof(typeof(field), item), \
- (unsigned int)sizeof(field.item)); \
- if (!ret) \
- return 0;
-
-#undef __entry
-#define __entry REC
-
-#undef TP_printk
-#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
-static int \
-ftrace_format_##call(struct trace_seq *s) \
-{ \
- struct ftrace_raw_##call field; \
- int ret; \
- \
- tstruct; \
- \
- trace_seq_printf(s, "\nprint fmt: " print); \
- \
- return ret; \
-}
-
-#include <trace/trace_event_types.h>
-
-#undef __field
-#define __field(type, item) \
- ret = trace_define_field(event_call, #type, #item, \
- offsetof(typeof(field), item), \
- sizeof(field.item)); \
- if (ret) \
- return ret;
-
-#undef __array
-#define __array(type, item, len) \
- ret = trace_define_field(event_call, #type "[" #len "]", #item, \
- offsetof(typeof(field), item), \
- sizeof(field.item)); \
- if (ret) \
- return ret;
-
-#define __common_field(type, item) \
- ret = trace_define_field(event_call, #type, "common_" #item, \
- offsetof(typeof(field.ent), item), \
- sizeof(field.ent.item)); \
- if (ret) \
- return ret;
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
-int \
-ftrace_define_fields_##call(void) \
-{ \
- struct ftrace_raw_##call field; \
- struct ftrace_event_call *event_call = &event_##call; \
- int ret; \
- \
- __common_field(unsigned char, type); \
- __common_field(unsigned char, flags); \
- __common_field(unsigned char, preempt_count); \
- __common_field(int, pid); \
- __common_field(int, tgid); \
- \
- tstruct; \
- \
- return ret; \
-}
-
-#include <trace/trace_event_types.h>
+++ /dev/null
-/*
- * Stage 3 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * static void ftrace_event_<call>(proto)
- * {
- * event_trace_printk(_RET_IP_, "<call>: " <fmt>);
- * }
- *
- * static int ftrace_reg_event_<call>(void)
- * {
- * int ret;
- *
- * ret = register_trace_<call>(ftrace_event_<call>);
- * if (!ret)
- * pr_info("event trace: Could not activate trace point "
- * "probe to <call>");
- * return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- * unregister_trace_<call>(ftrace_event_<call>);
- * }
- *
- * For those macros defined with TRACE_FORMAT:
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- * .name = "<call>",
- * .regfunc = ftrace_reg_event_<call>,
- * .unregfunc = ftrace_unreg_event_<call>,
- * }
- *
- *
- * For those macros defined with TRACE_EVENT:
- *
- * static struct ftrace_event_call event_<call>;
- *
- * static void ftrace_raw_event_<call>(proto)
- * {
- * struct ring_buffer_event *event;
- * struct ftrace_raw_<call> *entry; <-- defined in stage 1
- * unsigned long irq_flags;
- * int pc;
- *
- * local_save_flags(irq_flags);
- * pc = preempt_count();
- *
- * event = trace_current_buffer_lock_reserve(event_<call>.id,
- * sizeof(struct ftrace_raw_<call>),
- * irq_flags, pc);
- * if (!event)
- * return;
- * entry = ring_buffer_event_data(event);
- *
- * <assign>; <-- Here we assign the entries by the __field and
- * __array macros.
- *
- * trace_current_buffer_unlock_commit(event, irq_flags, pc);
- * }
- *
- * static int ftrace_raw_reg_event_<call>(void)
- * {
- * int ret;
- *
- * ret = register_trace_<call>(ftrace_raw_event_<call>);
- * if (!ret)
- * pr_info("event trace: Could not activate trace point "
- * "probe to <call>");
- * return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- * unregister_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
- * static struct trace_event ftrace_event_type_<call> = {
- * .trace = ftrace_raw_output_<call>, <-- stage 2
- * };
- *
- * static int ftrace_raw_init_event_<call>(void)
- * {
- * int id;
- *
- * id = register_ftrace_event(&ftrace_event_type_<call>);
- * if (!id)
- * return -ENODEV;
- * event_<call>.id = id;
- * return 0;
- * }
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- * .name = "<call>",
- * .system = "<system>",
- * .raw_init = ftrace_raw_init_event_<call>,
- * .regfunc = ftrace_reg_event_<call>,
- * .unregfunc = ftrace_unreg_event_<call>,
- * .show_format = ftrace_format_<call>,
- * }
- *
- */
-
-#undef TP_FMT
-#define TP_FMT(fmt, args...) fmt "\n", ##args
-
-#ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args) \
-static void ftrace_profile_##call(proto) \
-{ \
- extern void perf_tpcounter_event(int); \
- perf_tpcounter_event(event_##call.id); \
-} \
- \
-static int ftrace_profile_enable_##call(struct ftrace_event_call *call) \
-{ \
- int ret = 0; \
- \
- if (!atomic_inc_return(&call->profile_count)) \
- ret = register_trace_##call(ftrace_profile_##call); \
- \
- return ret; \
-} \
- \
-static void ftrace_profile_disable_##call(struct ftrace_event_call *call) \
-{ \
- if (atomic_add_negative(-1, &call->profile_count)) \
- unregister_trace_##call(ftrace_profile_##call); \
-}
-
-#define _TRACE_PROFILE_INIT(call) \
- .profile_count = ATOMIC_INIT(-1), \
- .profile_enable = ftrace_profile_enable_##call, \
- .profile_disable = ftrace_profile_disable_##call,
-
-#else
-#define _TRACE_PROFILE(call, proto, args)
-#define _TRACE_PROFILE_INIT(call)
-#endif
-
-#define _TRACE_FORMAT(call, proto, args, fmt) \
-static void ftrace_event_##call(proto) \
-{ \
- event_trace_printk(_RET_IP_, #call ": " fmt); \
-} \
- \
-static int ftrace_reg_event_##call(void) \
-{ \
- int ret; \
- \
- ret = register_trace_##call(ftrace_event_##call); \
- if (ret) \
- pr_info("event trace: Could not activate trace point " \
- "probe to " #call "\n"); \
- return ret; \
-} \
- \
-static void ftrace_unreg_event_##call(void) \
-{ \
- unregister_trace_##call(ftrace_event_##call); \
-} \
- \
-static struct ftrace_event_call event_##call; \
- \
-static int ftrace_init_event_##call(void) \
-{ \
- int id; \
- \
- id = register_ftrace_event(NULL); \
- if (!id) \
- return -ENODEV; \
- event_##call.id = id; \
- return 0; \
-}
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt) \
-_TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt)) \
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \
-static struct ftrace_event_call __used \
-__attribute__((__aligned__(4))) \
-__attribute__((section("_ftrace_events"))) event_##call = { \
- .name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
- .raw_init = ftrace_init_event_##call, \
- .regfunc = ftrace_reg_event_##call, \
- .unregfunc = ftrace_unreg_event_##call, \
- _TRACE_PROFILE_INIT(call) \
-}
-
-#undef __entry
-#define __entry entry
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \
- \
-static struct ftrace_event_call event_##call; \
- \
-static void ftrace_raw_event_##call(proto) \
-{ \
- struct ftrace_event_call *call = &event_##call; \
- struct ring_buffer_event *event; \
- struct ftrace_raw_##call *entry; \
- unsigned long irq_flags; \
- int pc; \
- \
- local_save_flags(irq_flags); \
- pc = preempt_count(); \
- \
- event = trace_current_buffer_lock_reserve(event_##call.id, \
- sizeof(struct ftrace_raw_##call), \
- irq_flags, pc); \
- if (!event) \
- return; \
- entry = ring_buffer_event_data(event); \
- \
- assign; \
- \
- if (call->preds && !filter_match_preds(call, entry)) \
- ring_buffer_event_discard(event); \
- \
- trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
- \
-} \
- \
-static int ftrace_raw_reg_event_##call(void) \
-{ \
- int ret; \
- \
- ret = register_trace_##call(ftrace_raw_event_##call); \
- if (ret) \
- pr_info("event trace: Could not activate trace point " \
- "probe to " #call "\n"); \
- return ret; \
-} \
- \
-static void ftrace_raw_unreg_event_##call(void) \
-{ \
- unregister_trace_##call(ftrace_raw_event_##call); \
-} \
- \
-static struct trace_event ftrace_event_type_##call = { \
- .trace = ftrace_raw_output_##call, \
-}; \
- \
-static int ftrace_raw_init_event_##call(void) \
-{ \
- int id; \
- \
- id = register_ftrace_event(&ftrace_event_type_##call); \
- if (!id) \
- return -ENODEV; \
- event_##call.id = id; \
- INIT_LIST_HEAD(&event_##call.fields); \
- return 0; \
-} \
- \
-static struct ftrace_event_call __used \
-__attribute__((__aligned__(4))) \
-__attribute__((section("_ftrace_events"))) event_##call = { \
- .name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
- .raw_init = ftrace_raw_init_event_##call, \
- .regfunc = ftrace_raw_reg_event_##call, \
- .unregfunc = ftrace_raw_unreg_event_##call, \
- .show_format = ftrace_format_##call, \
- .define_fields = ftrace_define_fields_##call, \
- _TRACE_PROFILE_INIT(call) \
-}
-
-#include <trace/trace_event_types.h>
-
-#undef _TRACE_PROFILE
-#undef _TRACE_PROFILE_INIT
-
#undef TRACE_STRUCT
#define TRACE_STRUCT(args...) args
+extern void __bad_type_size(void);
+
#undef TRACE_FIELD
#define TRACE_FIELD(type, item, assign) \
+ if (sizeof(type) != sizeof(field.item)) \
+ __bad_type_size(); \
ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
"offset:%u;\tsize:%u;\n", \
(unsigned int)offsetof(typeof(field), item), \
#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \
ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t" \
"offset:%u;\tsize:%u;\n", \
(unsigned int)offsetof(typeof(field), item), \
if (!ret) \
return 0;
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
+ TRACE_FIELD(type, item, assign)
#undef TP_RAW_FMT
#define TP_RAW_FMT(args...) args
return ret; \
}
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
+ tpfmt) \
+static int \
+ftrace_format_##call(struct trace_seq *s) \
+{ \
+ struct args field; \
+ int ret; \
+ \
+ tstruct; \
+ \
+ trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt); \
+ \
+ return ret; \
+}
+
#include "trace_event_types.h"
#undef TRACE_ZERO_CHAR
#define TRACE_FIELD(type, item, assign)\
entry->item = assign;
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
+ TRACE_FIELD(type, item, assign)
+
#undef TP_CMD
#define TP_CMD(cmd...) cmd
#define TRACE_ENTRY entry
#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \
cmd;
#undef TRACE_EVENT_FORMAT
#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
+int ftrace_define_fields_##call(void); \
+static int ftrace_raw_init_event_##call(void); \
+ \
+struct ftrace_event_call __used \
+__attribute__((__aligned__(4))) \
+__attribute__((section("_ftrace_events"))) event_##call = { \
+ .name = #call, \
+ .id = proto, \
+ .system = __stringify(TRACE_SYSTEM), \
+ .raw_init = ftrace_raw_init_event_##call, \
+ .show_format = ftrace_format_##call, \
+ .define_fields = ftrace_define_fields_##call, \
+}; \
+static int ftrace_raw_init_event_##call(void) \
+{ \
+ INIT_LIST_HEAD(&event_##call.fields); \
+ init_preds(&event_##call); \
+ return 0; \
+} \
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
+ tpfmt) \
\
-static struct ftrace_event_call __used \
+struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.id = proto, \
.system = __stringify(TRACE_SYSTEM), \
.show_format = ftrace_format_##call, \
+};
+
+#include "trace_event_types.h"
+
+#undef TRACE_FIELD
+#define TRACE_FIELD(type, item, assign) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed_type(type)); \
+ if (ret) \
+ return ret;
+
+#undef TRACE_FIELD_SPECIAL
+#define TRACE_FIELD_SPECIAL(type, item, len, cmd) \
+ ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), 0); \
+ if (ret) \
+ return ret;
+
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed); \
+ if (ret) \
+ return ret;
+
+#undef TRACE_FIELD_ZERO_CHAR
+#define TRACE_FIELD_ZERO_CHAR(item)
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
+int \
+ftrace_define_fields_##call(void) \
+{ \
+ struct ftrace_event_call *event_call = &event_##call; \
+ struct args field; \
+ int ret; \
+ \
+ __common_field(unsigned char, type, 0); \
+ __common_field(unsigned char, flags, 0); \
+ __common_field(unsigned char, preempt_count, 0); \
+ __common_field(int, pid, 1); \
+ __common_field(int, tgid, 1); \
+ \
+ tstruct; \
+ \
+ return ret; \
}
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
+ tpfmt)
+
#include "trace_event_types.h"
if (!current->ret_stack)
return -EBUSY;
+ /*
+ * We must make sure the ret_stack is tested before we read
+ * anything else.
+ */
+ smp_rmb();
+
/* The return trace stack is full */
if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
atomic_inc(¤t->trace_overrun);
current->ret_stack[index].ret = ret;
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = calltime;
+ current->ret_stack[index].subtime = 0;
*depth = index;
return 0;
}
/* Retrieve a function return address to the trace stack on thread info.*/
-void
+static void
ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
{
int index;
trace->calltime = current->ret_stack[index].calltime;
trace->overrun = atomic_read(¤t->trace_overrun);
trace->depth = index;
- barrier();
- current->curr_ret_stack--;
-
}
/*
ftrace_pop_return_trace(&trace, &ret);
trace.rettime = trace_clock_local();
ftrace_graph_return(&trace);
+ barrier();
+ current->curr_ret_stack--;
if (unlikely(!ret)) {
ftrace_graph_stop();
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t
-print_graph_duration(unsigned long long duration, struct trace_seq *s)
+enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
{
unsigned long nsecs_rem = do_div(duration, 1000);
/* log10(ULONG_MAX) + '\0' */
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_print_graph_duration(duration, s);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
ret = trace_seq_printf(s, "| ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
- return TRACE_TYPE_HANDLED;
+ return TRACE_TYPE_HANDLED;
}
/* Case of a leaf function on its call entry */
/*
- * h/w branch tracer for x86 based on bts
+ * h/w branch tracer for x86 based on BTS
*
* Copyright (C) 2008-2009 Intel Corporation.
* Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
*/
-#include <linux/spinlock.h>
#include <linux/kallsyms.h>
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <asm/ds.h>
-#include "trace.h"
#include "trace_output.h"
+#include "trace.h"
-#define SIZEOF_BTS (1 << 13)
+#define BTS_BUFFER_SIZE (1 << 13)
-/*
- * The tracer lock protects the below per-cpu tracer array.
- * It needs to be held to:
- * - start tracing on all cpus
- * - stop tracing on all cpus
- * - start tracing on a single hotplug cpu
- * - stop tracing on a single hotplug cpu
- * - read the trace from all cpus
- * - read the trace from a single cpu
- */
-static DEFINE_SPINLOCK(bts_tracer_lock);
static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
#define this_tracer per_cpu(tracer, smp_processor_id())
-#define this_buffer per_cpu(buffer, smp_processor_id())
-static int __read_mostly trace_hw_branches_enabled;
+static int trace_hw_branches_enabled __read_mostly;
+static int trace_hw_branches_suspended __read_mostly;
static struct trace_array *hw_branch_trace __read_mostly;
-/*
- * Start tracing on the current cpu.
- * The argument is ignored.
- *
- * pre: bts_tracer_lock must be locked.
- */
-static void bts_trace_start_cpu(void *arg)
+static void bts_trace_init_cpu(int cpu)
{
- if (this_tracer)
- ds_release_bts(this_tracer);
-
- this_tracer =
- ds_request_bts(/* task = */ NULL, this_buffer, SIZEOF_BTS,
- /* ovfl = */ NULL, /* th = */ (size_t)-1,
- BTS_KERNEL);
- if (IS_ERR(this_tracer)) {
- this_tracer = NULL;
- return;
- }
+ per_cpu(tracer, cpu) =
+ ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
+ NULL, (size_t)-1, BTS_KERNEL);
+
+ if (IS_ERR(per_cpu(tracer, cpu)))
+ per_cpu(tracer, cpu) = NULL;
}
-static void bts_trace_start(struct trace_array *tr)
+static int bts_trace_init(struct trace_array *tr)
{
- spin_lock(&bts_tracer_lock);
+ int cpu;
+
+ hw_branch_trace = tr;
+ trace_hw_branches_enabled = 0;
- on_each_cpu(bts_trace_start_cpu, NULL, 1);
- trace_hw_branches_enabled = 1;
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ bts_trace_init_cpu(cpu);
- spin_unlock(&bts_tracer_lock);
+ if (likely(per_cpu(tracer, cpu)))
+ trace_hw_branches_enabled = 1;
+ }
+ trace_hw_branches_suspended = 0;
+ put_online_cpus();
+
+ /* If we could not enable tracing on a single cpu, we fail. */
+ return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
}
-/*
- * Stop tracing on the current cpu.
- * The argument is ignored.
- *
- * pre: bts_tracer_lock must be locked.
- */
-static void bts_trace_stop_cpu(void *arg)
+static void bts_trace_reset(struct trace_array *tr)
{
- if (this_tracer) {
- ds_release_bts(this_tracer);
- this_tracer = NULL;
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ if (likely(per_cpu(tracer, cpu))) {
+ ds_release_bts(per_cpu(tracer, cpu));
+ per_cpu(tracer, cpu) = NULL;
+ }
}
+ trace_hw_branches_enabled = 0;
+ trace_hw_branches_suspended = 0;
+ put_online_cpus();
}
-static void bts_trace_stop(struct trace_array *tr)
+static void bts_trace_start(struct trace_array *tr)
{
- spin_lock(&bts_tracer_lock);
+ int cpu;
- trace_hw_branches_enabled = 0;
- on_each_cpu(bts_trace_stop_cpu, NULL, 1);
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(tracer, cpu)))
+ ds_resume_bts(per_cpu(tracer, cpu));
+ trace_hw_branches_suspended = 0;
+ put_online_cpus();
+}
- spin_unlock(&bts_tracer_lock);
+static void bts_trace_stop(struct trace_array *tr)
+{
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(tracer, cpu)))
+ ds_suspend_bts(per_cpu(tracer, cpu));
+ trace_hw_branches_suspended = 1;
+ put_online_cpus();
}
static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
- unsigned int cpu = (unsigned long)hcpu;
-
- spin_lock(&bts_tracer_lock);
-
- if (!trace_hw_branches_enabled)
- goto out;
+ int cpu = (long)hcpu;
switch (action) {
case CPU_ONLINE:
case CPU_DOWN_FAILED:
- smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1);
+ /* The notification is sent with interrupts enabled. */
+ if (trace_hw_branches_enabled) {
+ bts_trace_init_cpu(cpu);
+
+ if (trace_hw_branches_suspended &&
+ likely(per_cpu(tracer, cpu)))
+ ds_suspend_bts(per_cpu(tracer, cpu));
+ }
break;
+
case CPU_DOWN_PREPARE:
- smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1);
- break;
+ /* The notification is sent with interrupts enabled. */
+ if (likely(per_cpu(tracer, cpu))) {
+ ds_release_bts(per_cpu(tracer, cpu));
+ per_cpu(tracer, cpu) = NULL;
+ }
}
- out:
- spin_unlock(&bts_tracer_lock);
return NOTIFY_DONE;
}
.notifier_call = bts_hotcpu_handler
};
-static int bts_trace_init(struct trace_array *tr)
-{
- hw_branch_trace = tr;
-
- bts_trace_start(tr);
-
- return 0;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
- bts_trace_stop(tr);
-}
-
static void bts_trace_print_header(struct seq_file *m)
{
seq_puts(m, "# CPU# TO <- FROM\n");
static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
{
+ unsigned long symflags = TRACE_ITER_SYM_OFFSET;
struct trace_entry *entry = iter->ent;
struct trace_seq *seq = &iter->seq;
struct hw_branch_entry *it;
- unsigned long symflags = TRACE_ITER_SYM_OFFSET;
trace_assign_type(it, entry);
void trace_hw_branch(u64 from, u64 to)
{
+ struct ftrace_event_call *call = &event_hw_branch;
struct trace_array *tr = hw_branch_trace;
struct ring_buffer_event *event;
struct hw_branch_entry *entry;
entry->ent.type = TRACE_HW_BRANCHES;
entry->from = from;
entry->to = to;
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, 0, 0);
out:
atomic_dec(&tr->data[cpu]->disabled);
/*
* Collect the trace on the current cpu and write it into the ftrace buffer.
*
- * pre: bts_tracer_lock must be locked
+ * pre: tracing must be suspended on the current cpu
*/
static void trace_bts_cpu(void *arg)
{
- struct trace_array *tr = (struct trace_array *) arg;
+ struct trace_array *tr = (struct trace_array *)arg;
const struct bts_trace *trace;
unsigned char *at;
if (unlikely(!this_tracer))
return;
- ds_suspend_bts(this_tracer);
trace = ds_read_bts(this_tracer);
if (!trace)
- goto out;
+ return;
for (at = trace->ds.top; (void *)at < trace->ds.end;
at += trace->ds.size)
for (at = trace->ds.begin; (void *)at < trace->ds.top;
at += trace->ds.size)
trace_bts_at(trace, at);
-
-out:
- ds_resume_bts(this_tracer);
}
static void trace_bts_prepare(struct trace_iterator *iter)
{
- spin_lock(&bts_tracer_lock);
+ int cpu;
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(tracer, cpu)))
+ ds_suspend_bts(per_cpu(tracer, cpu));
+ /*
+ * We need to collect the trace on the respective cpu since ftrace
+ * implicitly adds the record for the current cpu.
+ * Once that is more flexible, we could collect the data from any cpu.
+ */
on_each_cpu(trace_bts_cpu, iter->tr, 1);
- spin_unlock(&bts_tracer_lock);
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(tracer, cpu)))
+ ds_resume_bts(per_cpu(tracer, cpu));
+ put_online_cpus();
}
static void trace_bts_close(struct trace_iterator *iter)
void trace_hw_branch_oops(void)
{
- spin_lock(&bts_tracer_lock);
-
- trace_bts_cpu(hw_branch_trace);
-
- spin_unlock(&bts_tracer_lock);
+ if (this_tracer) {
+ ds_suspend_bts_noirq(this_tracer);
+ trace_bts_cpu(hw_branch_trace);
+ ds_resume_bts_noirq(this_tracer);
+ }
}
struct tracer bts_tracer __read_mostly =
.start = bts_trace_start,
.stop = bts_trace_stop,
.open = trace_bts_prepare,
- .close = trace_bts_close
+ .close = trace_bts_close,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_hw_branches,
+#endif /* CONFIG_FTRACE_SELFTEST */
};
__init static int init_bts_trace(void)
#include <linux/kernel.h>
#include <linux/mmiotrace.h>
#include <linux/pci.h>
+#include <linux/time.h>
+
#include <asm/atomic.h>
#include "trace.h"
struct mmiotrace_rw *rw;
struct trace_seq *s = &iter->seq;
unsigned long long t = ns2usecs(iter->ts);
- unsigned long usec_rem = do_div(t, 1000000ULL);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned secs = (unsigned long)t;
int ret = 1;
struct mmiotrace_map *m;
struct trace_seq *s = &iter->seq;
unsigned long long t = ns2usecs(iter->ts);
- unsigned long usec_rem = do_div(t, 1000000ULL);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned secs = (unsigned long)t;
int ret;
/* must be a power of 2 */
#define EVENT_HASHSIZE 128
-static DEFINE_MUTEX(trace_event_mutex);
+DECLARE_RWSEM(trace_event_mutex);
+
+DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq);
+EXPORT_PER_CPU_SYMBOL(ftrace_event_seq);
+
static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
static int next_event_type = __TRACE_LAST_TYPE + 1;
+void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+ int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+
+ s->buffer[len] = 0;
+ seq_puts(m, s->buffer);
+
+ trace_seq_init(s);
+}
+
enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
return len;
}
+EXPORT_SYMBOL_GPL(trace_seq_printf);
+
+/**
+ * trace_seq_vprintf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
+trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+{
+ int len = (PAGE_SIZE - 1) - s->len;
+ int ret;
+
+ if (!len)
+ return 0;
+
+ ret = vsnprintf(s->buffer + s->len, len, fmt, args);
+
+ /* If we can't write it all, don't bother writing anything */
+ if (ret >= len)
+ return 0;
+
+ s->len += ret;
+
+ return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_vprintf);
int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
{
return 0;
}
+const char *
+ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+ unsigned long flags,
+ const struct trace_print_flags *flag_array)
+{
+ unsigned long mask;
+ const char *str;
+ const char *ret = p->buffer + p->len;
+ int i;
+
+ for (i = 0; flag_array[i].name && flags; i++) {
+
+ mask = flag_array[i].mask;
+ if ((flags & mask) != mask)
+ continue;
+
+ str = flag_array[i].name;
+ flags &= ~mask;
+ if (p->len && delim)
+ trace_seq_puts(p, delim);
+ trace_seq_puts(p, str);
+ }
+
+ /* check for left over flags */
+ if (flags) {
+ if (p->len && delim)
+ trace_seq_puts(p, delim);
+ trace_seq_printf(p, "0x%lx", flags);
+ }
+
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+EXPORT_SYMBOL(ftrace_print_flags_seq);
+
+const char *
+ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+ const struct trace_print_flags *symbol_array)
+{
+ int i;
+ const char *ret = p->buffer + p->len;
+
+ for (i = 0; symbol_array[i].name; i++) {
+
+ if (val != symbol_array[i].mask)
+ continue;
+
+ trace_seq_puts(p, symbol_array[i].name);
+ break;
+ }
+
+ if (!p->len)
+ trace_seq_printf(p, "0x%lx", val);
+
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq);
+
#ifdef CONFIG_KRETPROBES
static inline const char *kretprobed(const char *name)
{
if (ip == ULONG_MAX || !ret)
break;
- if (i && ret)
- ret = trace_seq_puts(s, " <- ");
+ if (ret)
+ ret = trace_seq_puts(s, " => ");
if (!ip) {
if (ret)
ret = trace_seq_puts(s, "??");
+ if (ret)
+ ret = trace_seq_puts(s, "\n");
continue;
}
if (!ret)
break;
if (ret)
ret = seq_print_user_ip(s, mm, ip, sym_flags);
+ ret = trace_seq_puts(s, "\n");
}
if (mm)
* @type: the type of event to look for
*
* Returns an event of type @type otherwise NULL
+ * Called with trace_event_read_lock() held.
*/
struct trace_event *ftrace_find_event(int type)
{
key = type & (EVENT_HASHSIZE - 1);
- hlist_for_each_entry_rcu(event, n, &event_hash[key], node) {
+ hlist_for_each_entry(event, n, &event_hash[key], node) {
if (event->type == type)
return event;
}
return NULL;
}
+static LIST_HEAD(ftrace_event_list);
+
+static int trace_search_list(struct list_head **list)
+{
+ struct trace_event *e;
+ int last = __TRACE_LAST_TYPE;
+
+ if (list_empty(&ftrace_event_list)) {
+ *list = &ftrace_event_list;
+ return last + 1;
+ }
+
+ /*
+ * We used up all possible max events,
+ * lets see if somebody freed one.
+ */
+ list_for_each_entry(e, &ftrace_event_list, list) {
+ if (e->type != last + 1)
+ break;
+ last++;
+ }
+
+ /* Did we used up all 65 thousand events??? */
+ if ((last + 1) > FTRACE_MAX_EVENT)
+ return 0;
+
+ *list = &e->list;
+ return last + 1;
+}
+
+void trace_event_read_lock(void)
+{
+ down_read(&trace_event_mutex);
+}
+
+void trace_event_read_unlock(void)
+{
+ up_read(&trace_event_mutex);
+}
+
/**
* register_ftrace_event - register output for an event type
* @event: the event type to register
unsigned key;
int ret = 0;
- mutex_lock(&trace_event_mutex);
+ down_write(&trace_event_mutex);
- if (!event) {
- ret = next_event_type++;
+ if (WARN_ON(!event))
goto out;
- }
- if (!event->type)
- event->type = next_event_type++;
- else if (event->type > __TRACE_LAST_TYPE) {
+ INIT_LIST_HEAD(&event->list);
+
+ if (!event->type) {
+ struct list_head *list = NULL;
+
+ if (next_event_type > FTRACE_MAX_EVENT) {
+
+ event->type = trace_search_list(&list);
+ if (!event->type)
+ goto out;
+
+ } else {
+
+ event->type = next_event_type++;
+ list = &ftrace_event_list;
+ }
+
+ if (WARN_ON(ftrace_find_event(event->type)))
+ goto out;
+
+ list_add_tail(&event->list, list);
+
+ } else if (event->type > __TRACE_LAST_TYPE) {
printk(KERN_WARNING "Need to add type to trace.h\n");
WARN_ON(1);
- }
-
- if (ftrace_find_event(event->type))
goto out;
+ } else {
+ /* Is this event already used */
+ if (ftrace_find_event(event->type))
+ goto out;
+ }
if (event->trace == NULL)
event->trace = trace_nop_print;
key = event->type & (EVENT_HASHSIZE - 1);
- hlist_add_head_rcu(&event->node, &event_hash[key]);
+ hlist_add_head(&event->node, &event_hash[key]);
ret = event->type;
out:
- mutex_unlock(&trace_event_mutex);
+ up_write(&trace_event_mutex);
return ret;
}
+EXPORT_SYMBOL_GPL(register_ftrace_event);
+
+/*
+ * Used by module code with the trace_event_mutex held for write.
+ */
+int __unregister_ftrace_event(struct trace_event *event)
+{
+ hlist_del(&event->node);
+ list_del(&event->list);
+ return 0;
+}
/**
* unregister_ftrace_event - remove a no longer used event
*/
int unregister_ftrace_event(struct trace_event *event)
{
- mutex_lock(&trace_event_mutex);
- hlist_del(&event->node);
- mutex_unlock(&trace_event_mutex);
+ down_write(&trace_event_mutex);
+ __unregister_ftrace_event(event);
+ up_write(&trace_event_mutex);
return 0;
}
+EXPORT_SYMBOL_GPL(unregister_ftrace_event);
/*
* Standard events
trace_assign_type(field, iter->ent);
+ if (!trace_seq_puts(s, "<stack trace>\n"))
+ goto partial;
for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
- if (i) {
- if (!trace_seq_puts(s, " <= "))
- goto partial;
+ if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
+ break;
+ if (!trace_seq_puts(s, " => "))
+ goto partial;
- if (!seq_print_ip_sym(s, field->caller[i], flags))
- goto partial;
- }
+ if (!seq_print_ip_sym(s, field->caller[i], flags))
+ goto partial;
if (!trace_seq_puts(s, "\n"))
goto partial;
}
trace_assign_type(field, iter->ent);
- if (!seq_print_userip_objs(field, s, flags))
+ if (!trace_seq_puts(s, "<user stack trace>\n"))
goto partial;
- if (!trace_seq_putc(s, '\n'))
+ if (!seq_print_userip_objs(field, s, flags))
goto partial;
return TRACE_TYPE_HANDLED;
#ifndef __TRACE_EVENTS_H
#define __TRACE_EVENTS_H
+#include <linux/trace_seq.h>
#include "trace.h"
-typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
- int flags);
-
-struct trace_event {
- struct hlist_node node;
- int type;
- trace_print_func trace;
- trace_print_func raw;
- trace_print_func hex;
- trace_print_func binary;
-};
-
extern enum print_line_t
trace_print_bprintk_msg_only(struct trace_iterator *iter);
extern enum print_line_t
trace_print_printk_msg_only(struct trace_iterator *iter);
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
- __attribute__ ((format (printf, 2, 3)));
-extern int
-trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
extern int
seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
unsigned long sym_flags);
-extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
- size_t cnt);
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
-extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
- size_t len);
-extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
-extern int trace_seq_path(struct trace_seq *s, struct path *path);
extern int seq_print_userip_objs(const struct userstack_entry *entry,
struct trace_seq *s, unsigned long sym_flags);
extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
extern int trace_print_context(struct trace_iterator *iter);
extern int trace_print_lat_context(struct trace_iterator *iter);
+extern void trace_event_read_lock(void);
+extern void trace_event_read_unlock(void);
extern struct trace_event *ftrace_find_event(int type);
-extern int register_ftrace_event(struct trace_event *event);
-extern int unregister_ftrace_event(struct trace_event *event);
extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
int flags);
+/* used by module unregistering */
+extern int __unregister_ftrace_event(struct trace_event *event);
+extern struct rw_semaphore trace_event_mutex;
+
#define MAX_MEMHEX_BYTES 8
#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1)
static void probe_power_end(struct power_trace *it)
{
+ struct ftrace_event_call *call = &event_power;
struct ring_buffer_event *event;
struct trace_power *entry;
struct trace_array_cpu *data;
goto out;
entry = ring_buffer_event_data(event);
entry->state_data = *it;
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, 0, 0);
out:
preempt_enable();
}
static void probe_power_mark(struct power_trace *it, unsigned int type,
unsigned int level)
{
+ struct ftrace_event_call *call = &event_power;
struct ring_buffer_event *event;
struct trace_power *entry;
struct trace_array_cpu *data;
goto out;
entry = ring_buffer_event_data(event);
entry->state_data = *it;
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ trace_buffer_unlock_commit(tr, event, 0, 0);
out:
preempt_enable();
}
static __init int init_trace_printk_function_export(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
if (!d_tracer)
return 0;
- entry = debugfs_create_file("printk_formats", 0444, d_tracer,
+ trace_create_file("printk_formats", 0444, d_tracer,
NULL, &ftrace_formats_fops);
- if (!entry)
- pr_warning("Could not create debugfs "
- "'printk_formats' entry\n");
return 0;
}
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include "trace.h"
int cpu;
int pc;
- if (!sched_ref || sched_stopped)
+ if (unlikely(!sched_ref))
return;
tracing_record_cmdline(prev);
tracing_record_cmdline(next);
- if (!tracer_enabled)
+ if (!tracer_enabled || sched_stopped)
return;
pc = preempt_count();
unsigned long flags;
int cpu, pc;
- if (!likely(tracer_enabled))
+ if (unlikely(!sched_ref))
return;
- pc = preempt_count();
tracing_record_cmdline(current);
- if (sched_stopped)
+ if (!tracer_enabled || sched_stopped)
return;
+ pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = ctx_trace->data[cpu];
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
#include "trace.h"
pc = preempt_count();
- /* The task we are waiting for is waking up */
- data = wakeup_trace->data[wakeup_cpu];
-
/* disable local data, not wakeup_cpu data */
cpu = raw_smp_processor_id();
disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
if (unlikely(!tracer_enabled || next != wakeup_task))
goto out_unlock;
+ /* The task we are waiting for is waking up */
+ data = wakeup_trace->data[wakeup_cpu];
+
trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
case TRACE_BRANCH:
case TRACE_GRAPH_ENT:
case TRACE_GRAPH_RET:
+ case TRACE_HW_BRANCHES:
return 1;
}
return 0;
#else
# define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; })
#endif /* CONFIG_DYNAMIC_FTRACE */
+
/*
* Simple verification test of ftrace function tracer.
* Enable ftrace, sleep 1/10 second, and then read the trace
return ret;
}
#endif /* CONFIG_BRANCH_TRACER */
+
+#ifdef CONFIG_HW_BRANCH_TRACER
+int
+trace_selftest_startup_hw_branches(struct tracer *trace,
+ struct trace_array *tr)
+{
+ struct trace_iterator *iter;
+ struct tracer tracer;
+ unsigned long count;
+ int ret;
+
+ if (!trace->open) {
+ printk(KERN_CONT "missing open function...");
+ return -1;
+ }
+
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /*
+ * The hw-branch tracer needs to collect the trace from the various
+ * cpu trace buffers - before tracing is stopped.
+ */
+ iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ memcpy(&tracer, trace, sizeof(tracer));
+
+ iter->trace = &tracer;
+ iter->tr = tr;
+ iter->pos = -1;
+ mutex_init(&iter->mutex);
+
+ trace->open(iter);
+
+ mutex_destroy(&iter->mutex);
+ kfree(iter);
+
+ tracing_stop();
+
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT "no entries found..");
+ ret = -1;
+ }
+
+ return ret;
+}
+#endif /* CONFIG_HW_BRANCH_TRACER */
seq_printf(m, " Depth Size Location"
" (%d entries)\n"
" ----- ---- --------\n",
- max_stack_trace.nr_entries);
+ max_stack_trace.nr_entries - 1);
if (!stack_tracer_enabled && !max_stack_size)
print_disabled(m);
static __init int stack_trace_init(void)
{
struct dentry *d_tracer;
- struct dentry *entry;
d_tracer = tracing_init_dentry();
- entry = debugfs_create_file("stack_max_size", 0644, d_tracer,
- &max_stack_size, &stack_max_size_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'stack_max_size' entry\n");
+ trace_create_file("stack_max_size", 0644, d_tracer,
+ &max_stack_size, &stack_max_size_fops);
- entry = debugfs_create_file("stack_trace", 0444, d_tracer,
- NULL, &stack_trace_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'stack_trace' entry\n");
+ trace_create_file("stack_trace", 0444, d_tracer,
+ NULL, &stack_trace_fops);
if (stack_tracer_enabled)
register_ftrace_function(&trace_ops);
/*
* Infrastructure for statistic tracing (histogram output).
*
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
*
* Based on the code from trace_branch.c which is
* Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
#include <linux/list.h>
+#include <linux/rbtree.h>
#include <linux/debugfs.h>
#include "trace_stat.h"
#include "trace.h"
-/* List of stat entries from a tracer */
-struct trace_stat_list {
- struct list_head list;
+/*
+ * List of stat red-black nodes from a tracer
+ * We use a such tree to sort quickly the stat
+ * entries from the tracer.
+ */
+struct stat_node {
+ struct rb_node node;
void *stat;
};
/* A stat session is the stats output in one file */
-struct tracer_stat_session {
+struct stat_session {
struct list_head session_list;
struct tracer_stat *ts;
- struct list_head stat_list;
+ struct rb_root stat_root;
struct mutex stat_mutex;
struct dentry *file;
};
/* The root directory for all stat files */
static struct dentry *stat_dir;
+/*
+ * Iterate through the rbtree using a post order traversal path
+ * to release the next node.
+ * It won't necessary release one at each iteration
+ * but it will at least advance closer to the next one
+ * to be released.
+ */
+static struct rb_node *release_next(struct rb_node *node)
+{
+ struct stat_node *snode;
+ struct rb_node *parent = rb_parent(node);
+
+ if (node->rb_left)
+ return node->rb_left;
+ else if (node->rb_right)
+ return node->rb_right;
+ else {
+ if (!parent)
+ ;
+ else if (parent->rb_left == node)
+ parent->rb_left = NULL;
+ else
+ parent->rb_right = NULL;
+
+ snode = container_of(node, struct stat_node, node);
+ kfree(snode);
+
+ return parent;
+ }
+}
-static void reset_stat_session(struct tracer_stat_session *session)
+static void reset_stat_session(struct stat_session *session)
{
- struct trace_stat_list *node, *next;
+ struct rb_node *node = session->stat_root.rb_node;
- list_for_each_entry_safe(node, next, &session->stat_list, list)
- kfree(node);
+ while (node)
+ node = release_next(node);
- INIT_LIST_HEAD(&session->stat_list);
+ session->stat_root = RB_ROOT;
}
-static void destroy_session(struct tracer_stat_session *session)
+static void destroy_session(struct stat_session *session)
{
debugfs_remove(session->file);
reset_stat_session(session);
kfree(session);
}
+typedef int (*cmp_stat_t)(void *, void *);
+
+static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+ struct stat_node *data;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+ data->stat = stat;
+
+ /*
+ * Figure out where to put new node
+ * This is a descendent sorting
+ */
+ while (*new) {
+ struct stat_node *this;
+ int result;
+
+ this = container_of(*new, struct stat_node, node);
+ result = cmp(data->stat, this->stat);
+
+ parent = *new;
+ if (result >= 0)
+ new = &((*new)->rb_left);
+ else
+ new = &((*new)->rb_right);
+ }
+
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+ return 0;
+}
+
/*
* For tracers that don't provide a stat_cmp callback.
- * This one will force an immediate insertion on tail of
- * the list.
+ * This one will force an insertion as right-most node
+ * in the rbtree.
*/
static int dummy_cmp(void *p1, void *p2)
{
- return 1;
+ return -1;
}
/*
- * Initialize the stat list at each trace_stat file opening.
+ * Initialize the stat rbtree at each trace_stat file opening.
* All of these copies and sorting are required on all opening
* since the stats could have changed between two file sessions.
*/
-static int stat_seq_init(struct tracer_stat_session *session)
+static int stat_seq_init(struct stat_session *session)
{
- struct trace_stat_list *iter_entry, *new_entry;
struct tracer_stat *ts = session->ts;
+ struct rb_root *root = &session->stat_root;
void *stat;
int ret = 0;
int i;
if (!ts->stat_cmp)
ts->stat_cmp = dummy_cmp;
- stat = ts->stat_start();
+ stat = ts->stat_start(ts);
if (!stat)
goto exit;
- /*
- * The first entry. Actually this is the second, but the first
- * one (the stat_list head) is pointless.
- */
- new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
- if (!new_entry) {
- ret = -ENOMEM;
+ ret = insert_stat(root, stat, ts->stat_cmp);
+ if (ret)
goto exit;
- }
-
- INIT_LIST_HEAD(&new_entry->list);
-
- list_add(&new_entry->list, &session->stat_list);
-
- new_entry->stat = stat;
/*
- * Iterate over the tracer stat entries and store them in a sorted
- * list.
+ * Iterate over the tracer stat entries and store them in an rbtree.
*/
for (i = 1; ; i++) {
stat = ts->stat_next(stat, i);
if (!stat)
break;
- new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
- if (!new_entry) {
- ret = -ENOMEM;
- goto exit_free_list;
- }
-
- INIT_LIST_HEAD(&new_entry->list);
- new_entry->stat = stat;
-
- list_for_each_entry_reverse(iter_entry, &session->stat_list,
- list) {
-
- /* Insertion with a descendent sorting */
- if (ts->stat_cmp(iter_entry->stat,
- new_entry->stat) >= 0) {
-
- list_add(&new_entry->list, &iter_entry->list);
- break;
- }
- }
-
- /* The current larger value */
- if (list_empty(&new_entry->list))
- list_add(&new_entry->list, &session->stat_list);
+ ret = insert_stat(root, stat, ts->stat_cmp);
+ if (ret)
+ goto exit_free_rbtree;
}
+
exit:
mutex_unlock(&session->stat_mutex);
return ret;
-exit_free_list:
+exit_free_rbtree:
reset_stat_session(session);
mutex_unlock(&session->stat_mutex);
return ret;
static void *stat_seq_start(struct seq_file *s, loff_t *pos)
{
- struct tracer_stat_session *session = s->private;
+ struct stat_session *session = s->private;
+ struct rb_node *node;
+ int i;
- /* Prevent from tracer switch or stat_list modification */
+ /* Prevent from tracer switch or rbtree modification */
mutex_lock(&session->stat_mutex);
/* If we are in the beginning of the file, print the headers */
- if (!*pos && session->ts->stat_headers)
+ if (!*pos && session->ts->stat_headers) {
+ (*pos)++;
return SEQ_START_TOKEN;
+ }
- return seq_list_start(&session->stat_list, *pos);
+ node = rb_first(&session->stat_root);
+ for (i = 0; node && i < *pos; i++)
+ node = rb_next(node);
+
+ (*pos)++;
+
+ return node;
}
static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos)
{
- struct tracer_stat_session *session = s->private;
+ struct stat_session *session = s->private;
+ struct rb_node *node = p;
+
+ (*pos)++;
if (p == SEQ_START_TOKEN)
- return seq_list_start(&session->stat_list, *pos);
+ return rb_first(&session->stat_root);
- return seq_list_next(p, &session->stat_list, pos);
+ return rb_next(node);
}
static void stat_seq_stop(struct seq_file *s, void *p)
{
- struct tracer_stat_session *session = s->private;
+ struct stat_session *session = s->private;
mutex_unlock(&session->stat_mutex);
}
static int stat_seq_show(struct seq_file *s, void *v)
{
- struct tracer_stat_session *session = s->private;
- struct trace_stat_list *l = list_entry(v, struct trace_stat_list, list);
+ struct stat_session *session = s->private;
+ struct stat_node *l = container_of(v, struct stat_node, node);
if (v == SEQ_START_TOKEN)
return session->ts->stat_headers(s);
{
int ret;
- struct tracer_stat_session *session = inode->i_private;
+ struct stat_session *session = inode->i_private;
ret = seq_open(file, &trace_stat_seq_ops);
if (!ret) {
}
/*
- * Avoid consuming memory with our now useless list.
+ * Avoid consuming memory with our now useless rbtree.
*/
static int tracing_stat_release(struct inode *i, struct file *f)
{
- struct tracer_stat_session *session = i->i_private;
+ struct stat_session *session = i->i_private;
mutex_lock(&session->stat_mutex);
reset_stat_session(session);
return 0;
}
-static int init_stat_file(struct tracer_stat_session *session)
+static int init_stat_file(struct stat_session *session)
{
if (!stat_dir && tracing_stat_init())
return -ENODEV;
int register_stat_tracer(struct tracer_stat *trace)
{
- struct tracer_stat_session *session, *node, *tmp;
+ struct stat_session *session, *node;
int ret;
if (!trace)
/* Already registered? */
mutex_lock(&all_stat_sessions_mutex);
- list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
+ list_for_each_entry(node, &all_stat_sessions, session_list) {
if (node->ts == trace) {
mutex_unlock(&all_stat_sessions_mutex);
return -EINVAL;
mutex_unlock(&all_stat_sessions_mutex);
/* Init the session */
- session = kmalloc(sizeof(struct tracer_stat_session), GFP_KERNEL);
+ session = kzalloc(sizeof(*session), GFP_KERNEL);
if (!session)
return -ENOMEM;
session->ts = trace;
INIT_LIST_HEAD(&session->session_list);
- INIT_LIST_HEAD(&session->stat_list);
mutex_init(&session->stat_mutex);
- session->file = NULL;
ret = init_stat_file(session);
if (ret) {
void unregister_stat_tracer(struct tracer_stat *trace)
{
- struct tracer_stat_session *node, *tmp;
+ struct stat_session *node, *tmp;
mutex_lock(&all_stat_sessions_mutex);
list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
/* The name of your stat file */
const char *name;
/* Iteration over statistic entries */
- void *(*stat_start)(void);
+ void *(*stat_start)(struct tracer_stat *trace);
void *(*stat_next)(void *prev, int idx);
/* Compare two entries for stats sorting */
int (*stat_cmp)(void *p1, void *p2);
void init_tracer_sysprof_debugfs(struct dentry *d_tracer)
{
- struct dentry *entry;
- entry = debugfs_create_file("sysprof_sample_period", 0644,
+ trace_create_file("sysprof_sample_period", 0644,
d_tracer, NULL, &sysprof_sample_fops);
- if (entry)
- return;
- pr_warning("Could not create debugfs 'sysprof_sample_period' entry\n");
}
*/
-#include <trace/workqueue.h>
+#include <trace/events/workqueue.h>
#include <linux/list.h>
#include <linux/percpu.h>
#include "trace_stat.h"
/* A cpu workqueue thread */
struct cpu_workqueue_stats {
struct list_head list;
-/* Useful to know if we print the cpu headers */
- bool first_entry;
int cpu;
pid_t pid;
/* Can be inserted from interrupt or user context, need to be atomic */
struct work_struct *work)
{
int cpu = cpumask_first(&wq_thread->cpus_allowed);
- struct cpu_workqueue_stats *node, *next;
+ struct cpu_workqueue_stats *node;
unsigned long flags;
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
- list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
- list) {
+ list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
if (node->pid == wq_thread->pid) {
atomic_inc(&node->inserted);
goto found;
struct work_struct *work)
{
int cpu = cpumask_first(&wq_thread->cpus_allowed);
- struct cpu_workqueue_stats *node, *next;
+ struct cpu_workqueue_stats *node;
unsigned long flags;
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
- list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
- list) {
+ list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
if (node->pid == wq_thread->pid) {
node->executed++;
goto found;
cws->pid = wq_thread->pid;
spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
- if (list_empty(&workqueue_cpu_stat(cpu)->list))
- cws->first_entry = true;
list_add_tail(&cws->list, &workqueue_cpu_stat(cpu)->list);
spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
}
return ret;
}
-static void *workqueue_stat_start(void)
+static void *workqueue_stat_start(struct tracer_stat *trace)
{
int cpu;
void *ret = NULL;
static int workqueue_stat_show(struct seq_file *s, void *p)
{
struct cpu_workqueue_stats *cws = p;
- unsigned long flags;
- int cpu = cws->cpu;
struct pid *pid;
struct task_struct *tsk;
- spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
- if (&cws->list == workqueue_cpu_stat(cpu)->list.next)
- seq_printf(s, "\n");
- spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
-
pid = find_get_pid(cws->pid);
if (pid) {
tsk = get_pid_task(pid, PIDTYPE_PID);
if (!list_empty(&wait->task_list))
list_del_init(&wait->task_list);
else if (waitqueue_active(q))
- __wake_up_common(q, mode, 1, 0, key);
+ __wake_up_locked_key(q, mode, key);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(abort_exclusive_wait);
#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
-#include <trace/workqueue.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
/*
* The per-CPU workqueue (if single thread, we always use the first
return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
}
-DEFINE_TRACE(workqueue_insertion);
-
static void insert_work(struct cpu_workqueue_struct *cwq,
struct work_struct *work, struct list_head *head)
{
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);
-DEFINE_TRACE(workqueue_execution);
-
static void run_workqueue(struct cpu_workqueue_struct *cwq)
{
spin_lock_irq(&cwq->lock);
return cwq;
}
-DEFINE_TRACE(workqueue_creation);
-
static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
}
EXPORT_SYMBOL_GPL(__create_workqueue_key);
-DEFINE_TRACE(workqueue_destruction);
-
static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
{
/*
config BITREVERSE
tristate
+config RATIONAL
+ boolean
+
config GENERIC_FIND_FIRST_BIT
bool
endif
obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_RATIONAL) += rational.o
obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
obj-$(CONFIG_CRC16) += crc16.o
obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
#include <linux/dma-debug.h>
#include <linux/spinlock.h>
#include <linux/debugfs.h>
+#include <linux/uaccess.h>
#include <linux/device.h>
#include <linux/types.h>
#include <linux/sched.h>
+#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/slab.h>
static u32 num_free_entries;
static u32 min_free_entries;
+static u32 nr_total_entries;
/* number of preallocated entries requested by kernel cmdline */
static u32 req_entries;
static struct dentry *show_num_errors_dent __read_mostly;
static struct dentry *num_free_entries_dent __read_mostly;
static struct dentry *min_free_entries_dent __read_mostly;
+static struct dentry *filter_dent __read_mostly;
+
+/* per-driver filter related state */
+
+#define NAME_MAX_LEN 64
+
+static char current_driver_name[NAME_MAX_LEN] __read_mostly;
+static struct device_driver *current_driver __read_mostly;
+
+static DEFINE_RWLOCK(driver_name_lock);
static const char *type2name[4] = { "single", "page",
"scather-gather", "coherent" };
static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
"DMA_FROM_DEVICE", "DMA_NONE" };
+/* little merge helper - remove it after the merge window */
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
+
/*
* The access to some variables in this macro is racy. We can't use atomic_t
* here because all these variables are exported to debugfs. Some of them even
{
#ifdef CONFIG_STACKTRACE
if (entry) {
- printk(KERN_WARNING "Mapped at:\n");
+ pr_warning("Mapped at:\n");
print_stack_trace(&entry->stacktrace, 0);
}
#endif
}
+static bool driver_filter(struct device *dev)
+{
+ struct device_driver *drv;
+ unsigned long flags;
+ bool ret;
+
+ /* driver filter off */
+ if (likely(!current_driver_name[0]))
+ return true;
+
+ /* driver filter on and initialized */
+ if (current_driver && dev->driver == current_driver)
+ return true;
+
+ if (current_driver || !current_driver_name[0])
+ return false;
+
+ /* driver filter on but not yet initialized */
+ drv = get_driver(dev->driver);
+ if (!drv)
+ return false;
+
+ /* lock to protect against change of current_driver_name */
+ read_lock_irqsave(&driver_name_lock, flags);
+
+ ret = false;
+ if (drv->name &&
+ strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
+ current_driver = drv;
+ ret = true;
+ }
+
+ read_unlock_irqrestore(&driver_name_lock, flags);
+ put_driver(drv);
+
+ return ret;
+}
+
#define err_printk(dev, entry, format, arg...) do { \
error_count += 1; \
- if (show_all_errors || show_num_errors > 0) { \
+ if (driver_filter(dev) && \
+ (show_all_errors || show_num_errors > 0)) { \
WARN(1, "%s %s: " format, \
dev_driver_string(dev), \
dev_name(dev) , ## arg); \
static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
struct dma_debug_entry *ref)
{
- struct dma_debug_entry *entry;
+ struct dma_debug_entry *entry, *ret = NULL;
+ int matches = 0, match_lvl, last_lvl = 0;
list_for_each_entry(entry, &bucket->list, list) {
- if ((entry->dev_addr == ref->dev_addr) &&
- (entry->dev == ref->dev))
+ if ((entry->dev_addr != ref->dev_addr) ||
+ (entry->dev != ref->dev))
+ continue;
+
+ /*
+ * Some drivers map the same physical address multiple
+ * times. Without a hardware IOMMU this results in the
+ * same device addresses being put into the dma-debug
+ * hash multiple times too. This can result in false
+ * positives being reported. Therfore we implement a
+ * best-fit algorithm here which returns the entry from
+ * the hash which fits best to the reference value
+ * instead of the first-fit.
+ */
+ matches += 1;
+ match_lvl = 0;
+ entry->size == ref->size ? ++match_lvl : match_lvl;
+ entry->type == ref->type ? ++match_lvl : match_lvl;
+ entry->direction == ref->direction ? ++match_lvl : match_lvl;
+
+ if (match_lvl == 3) {
+ /* perfect-fit - return the result */
return entry;
+ } else if (match_lvl > last_lvl) {
+ /*
+ * We found an entry that fits better then the
+ * previous one
+ */
+ last_lvl = match_lvl;
+ ret = entry;
+ }
}
- return NULL;
+ /*
+ * If we have multiple matches but no perfect-fit, just return
+ * NULL.
+ */
+ ret = (matches == 1) ? ret : NULL;
+
+ return ret;
}
/*
put_hash_bucket(bucket, &flags);
}
+static struct dma_debug_entry *__dma_entry_alloc(void)
+{
+ struct dma_debug_entry *entry;
+
+ entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+ list_del(&entry->list);
+ memset(entry, 0, sizeof(*entry));
+
+ num_free_entries -= 1;
+ if (num_free_entries < min_free_entries)
+ min_free_entries = num_free_entries;
+
+ return entry;
+}
+
/* struct dma_entry allocator
*
* The next two functions implement the allocator for
spin_lock_irqsave(&free_entries_lock, flags);
if (list_empty(&free_entries)) {
- printk(KERN_ERR "DMA-API: debugging out of memory "
- "- disabling\n");
+ pr_err("DMA-API: debugging out of memory - disabling\n");
global_disable = true;
goto out;
}
- entry = list_entry(free_entries.next, struct dma_debug_entry, list);
- list_del(&entry->list);
- memset(entry, 0, sizeof(*entry));
+ entry = __dma_entry_alloc();
#ifdef CONFIG_STACKTRACE
entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
entry->stacktrace.skip = 2;
save_stack_trace(&entry->stacktrace);
#endif
- num_free_entries -= 1;
- if (num_free_entries < min_free_entries)
- min_free_entries = num_free_entries;
out:
spin_unlock_irqrestore(&free_entries_lock, flags);
spin_unlock_irqrestore(&free_entries_lock, flags);
}
+int dma_debug_resize_entries(u32 num_entries)
+{
+ int i, delta, ret = 0;
+ unsigned long flags;
+ struct dma_debug_entry *entry;
+ LIST_HEAD(tmp);
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ if (nr_total_entries < num_entries) {
+ delta = num_entries - nr_total_entries;
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+ for (i = 0; i < delta; i++) {
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ break;
+
+ list_add_tail(&entry->list, &tmp);
+ }
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ list_splice(&tmp, &free_entries);
+ nr_total_entries += i;
+ num_free_entries += i;
+ } else {
+ delta = nr_total_entries - num_entries;
+
+ for (i = 0; i < delta && !list_empty(&free_entries); i++) {
+ entry = __dma_entry_alloc();
+ kfree(entry);
+ }
+
+ nr_total_entries -= i;
+ }
+
+ if (nr_total_entries != num_entries)
+ ret = 1;
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL(dma_debug_resize_entries);
+
/*
* DMA-API debugging init code
*
num_free_entries = num_entries;
min_free_entries = num_entries;
- printk(KERN_INFO "DMA-API: preallocated %d debug entries\n",
- num_entries);
+ pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
return 0;
return -ENOMEM;
}
+static ssize_t filter_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ char buf[NAME_MAX_LEN + 1];
+ unsigned long flags;
+ int len;
+
+ if (!current_driver_name[0])
+ return 0;
+
+ /*
+ * We can't copy to userspace directly because current_driver_name can
+ * only be read under the driver_name_lock with irqs disabled. So
+ * create a temporary copy first.
+ */
+ read_lock_irqsave(&driver_name_lock, flags);
+ len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
+ read_unlock_irqrestore(&driver_name_lock, flags);
+
+ return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t filter_write(struct file *file, const char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ char buf[NAME_MAX_LEN];
+ unsigned long flags;
+ size_t len;
+ int i;
+
+ /*
+ * We can't copy from userspace directly. Access to
+ * current_driver_name is protected with a write_lock with irqs
+ * disabled. Since copy_from_user can fault and may sleep we
+ * need to copy to temporary buffer first
+ */
+ len = min(count, (size_t)(NAME_MAX_LEN - 1));
+ if (copy_from_user(buf, userbuf, len))
+ return -EFAULT;
+
+ buf[len] = 0;
+
+ write_lock_irqsave(&driver_name_lock, flags);
+
+ /*
+ * Now handle the string we got from userspace very carefully.
+ * The rules are:
+ * - only use the first token we got
+ * - token delimiter is everything looking like a space
+ * character (' ', '\n', '\t' ...)
+ *
+ */
+ if (!isalnum(buf[0])) {
+ /*
+ * If the first character userspace gave us is not
+ * alphanumerical then assume the filter should be
+ * switched off.
+ */
+ if (current_driver_name[0])
+ pr_info("DMA-API: switching off dma-debug driver filter\n");
+ current_driver_name[0] = 0;
+ current_driver = NULL;
+ goto out_unlock;
+ }
+
+ /*
+ * Now parse out the first token and use it as the name for the
+ * driver to filter for.
+ */
+ for (i = 0; i < NAME_MAX_LEN; ++i) {
+ current_driver_name[i] = buf[i];
+ if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
+ break;
+ }
+ current_driver_name[i] = 0;
+ current_driver = NULL;
+
+ pr_info("DMA-API: enable driver filter for driver [%s]\n",
+ current_driver_name);
+
+out_unlock:
+ write_unlock_irqrestore(&driver_name_lock, flags);
+
+ return count;
+}
+
+const struct file_operations filter_fops = {
+ .read = filter_read,
+ .write = filter_write,
+};
+
static int dma_debug_fs_init(void)
{
dma_debug_dent = debugfs_create_dir("dma-api", NULL);
if (!dma_debug_dent) {
- printk(KERN_ERR "DMA-API: can not create debugfs directory\n");
+ pr_err("DMA-API: can not create debugfs directory\n");
return -ENOMEM;
}
if (!min_free_entries_dent)
goto out_err;
+ filter_dent = debugfs_create_file("driver_filter", 0644,
+ dma_debug_dent, NULL, &filter_fops);
+ if (!filter_dent)
+ goto out_err;
+
return 0;
out_err:
return -ENOMEM;
}
+static int device_dma_allocations(struct device *dev)
+{
+ struct dma_debug_entry *entry;
+ unsigned long flags;
+ int count = 0, i;
+
+ local_irq_save(flags);
+
+ for (i = 0; i < HASH_SIZE; ++i) {
+ spin_lock(&dma_entry_hash[i].lock);
+ list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
+ if (entry->dev == dev)
+ count += 1;
+ }
+ spin_unlock(&dma_entry_hash[i].lock);
+ }
+
+ local_irq_restore(flags);
+
+ return count;
+}
+
+static int dma_debug_device_change(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct device *dev = data;
+ int count;
+
+
+ switch (action) {
+ case BUS_NOTIFY_UNBOUND_DRIVER:
+ count = device_dma_allocations(dev);
+ if (count == 0)
+ break;
+ err_printk(dev, NULL, "DMA-API: device driver has pending "
+ "DMA allocations while released from device "
+ "[count=%d]\n", count);
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
void dma_debug_add_bus(struct bus_type *bus)
{
- /* FIXME: register notifier */
+ struct notifier_block *nb;
+
+ nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+ if (nb == NULL) {
+ pr_err("dma_debug_add_bus: out of memory\n");
+ return;
+ }
+
+ nb->notifier_call = dma_debug_device_change;
+
+ bus_register_notifier(bus, nb);
}
/*
}
if (dma_debug_fs_init() != 0) {
- printk(KERN_ERR "DMA-API: error creating debugfs entries "
- "- disabling\n");
+ pr_err("DMA-API: error creating debugfs entries - disabling\n");
global_disable = true;
return;
num_entries = req_entries;
if (prealloc_memory(num_entries) != 0) {
- printk(KERN_ERR "DMA-API: debugging out of memory error "
- "- disabled\n");
+ pr_err("DMA-API: debugging out of memory error - disabled\n");
global_disable = true;
return;
}
- printk(KERN_INFO "DMA-API: debugging enabled by kernel config\n");
+ nr_total_entries = num_free_entries;
+
+ pr_info("DMA-API: debugging enabled by kernel config\n");
}
static __init int dma_debug_cmdline(char *str)
return -EINVAL;
if (strncmp(str, "off", 3) == 0) {
- printk(KERN_INFO "DMA-API: debugging disabled on kernel "
- "command line\n");
+ pr_info("DMA-API: debugging disabled on kernel command line\n");
global_disable = true;
}
entry->type = dma_debug_sg;
entry->dev = dev;
entry->paddr = sg_phys(s);
- entry->size = s->length;
- entry->dev_addr = s->dma_address;
+ entry->size = sg_dma_len(s);
+ entry->dev_addr = sg_dma_address(s);
entry->direction = direction;
entry->sg_call_ents = nents;
entry->sg_mapped_ents = mapped_ents;
if (!PageHighMem(sg_page(s))) {
check_for_stack(dev, sg_virt(s));
- check_for_illegal_area(dev, sg_virt(s), s->length);
+ check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
}
add_dma_entry(entry);
}
EXPORT_SYMBOL(debug_dma_map_sg);
+static int get_nr_mapped_entries(struct device *dev, struct scatterlist *s)
+{
+ struct dma_debug_entry *entry, ref;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+ int mapped_ents;
+
+ ref.dev = dev;
+ ref.dev_addr = sg_dma_address(s);
+ ref.size = sg_dma_len(s),
+
+ bucket = get_hash_bucket(&ref, &flags);
+ entry = hash_bucket_find(bucket, &ref);
+ mapped_ents = 0;
+
+ if (entry)
+ mapped_ents = entry->sg_mapped_ents;
+ put_hash_bucket(bucket, &flags);
+
+ return mapped_ents;
+}
+
void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
int nelems, int dir)
{
- struct dma_debug_entry *entry;
struct scatterlist *s;
int mapped_ents = 0, i;
- unsigned long flags;
if (unlikely(global_disable))
return;
.type = dma_debug_sg,
.dev = dev,
.paddr = sg_phys(s),
- .dev_addr = s->dma_address,
- .size = s->length,
+ .dev_addr = sg_dma_address(s),
+ .size = sg_dma_len(s),
.direction = dir,
.sg_call_ents = 0,
};
if (mapped_ents && i >= mapped_ents)
break;
- if (mapped_ents == 0) {
- struct hash_bucket *bucket;
+ if (!i) {
ref.sg_call_ents = nelems;
- bucket = get_hash_bucket(&ref, &flags);
- entry = hash_bucket_find(bucket, &ref);
- if (entry)
- mapped_ents = entry->sg_mapped_ents;
- put_hash_bucket(bucket, &flags);
+ mapped_ents = get_nr_mapped_entries(dev, s);
}
check_unmap(&ref);
int nelems, int direction)
{
struct scatterlist *s;
- int i;
+ int mapped_ents = 0, i;
if (unlikely(global_disable))
return;
for_each_sg(sg, s, nelems, i) {
- check_sync(dev, s->dma_address, s->dma_length, 0,
- direction, true);
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, s);
+
+ if (i >= mapped_ents)
+ break;
+
+ check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
+ direction, true);
}
}
EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
int nelems, int direction)
{
struct scatterlist *s;
- int i;
+ int mapped_ents = 0, i;
if (unlikely(global_disable))
return;
for_each_sg(sg, s, nelems, i) {
- check_sync(dev, s->dma_address, s->dma_length, 0,
- direction, false);
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, s);
+
+ if (i >= mapped_ents)
+ break;
+
+ check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
+ direction, false);
}
}
EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
+static int __init dma_debug_driver_setup(char *str)
+{
+ int i;
+
+ for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
+ current_driver_name[i] = *str;
+ if (*str == 0)
+ break;
+ }
+
+ if (current_driver_name[0])
+ pr_info("DMA-API: enable driver filter for driver [%s]\n",
+ current_driver_name);
+
+
+ return 1;
+}
+__setup("dma_debug_driver=", dma_debug_driver_setup);
--- /dev/null
+/*
+ * rational fractions
+ *
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ *
+ * helper functions when coping with rational numbers
+ */
+
+#include <linux/rational.h>
+
+/*
+ * calculate best rational approximation for a given fraction
+ * taking into account restricted register size, e.g. to find
+ * appropriate values for a pll with 5 bit denominator and
+ * 8 bit numerator register fields, trying to set up with a
+ * frequency ratio of 3.1415, one would say:
+ *
+ * rational_best_approximation(31415, 10000,
+ * (1 << 8) - 1, (1 << 5) - 1, &n, &d);
+ *
+ * you may look at given_numerator as a fixed point number,
+ * with the fractional part size described in given_denominator.
+ *
+ * for theoretical background, see:
+ * http://en.wikipedia.org/wiki/Continued_fraction
+ */
+
+void rational_best_approximation(
+ unsigned long given_numerator, unsigned long given_denominator,
+ unsigned long max_numerator, unsigned long max_denominator,
+ unsigned long *best_numerator, unsigned long *best_denominator)
+{
+ unsigned long n, d, n0, d0, n1, d1;
+ n = given_numerator;
+ d = given_denominator;
+ n0 = d1 = 0;
+ n1 = d0 = 1;
+ for (;;) {
+ unsigned long t, a;
+ if ((n1 > max_numerator) || (d1 > max_denominator)) {
+ n1 = n0;
+ d1 = d0;
+ break;
+ }
+ if (d == 0)
+ break;
+ t = d;
+ a = n / d;
+ d = n % d;
+ n = t;
+ t = n0 + a * n1;
+ n0 = n1;
+ n1 = t;
+ t = d0 + a * d1;
+ d0 = d1;
+ d1 = t;
+ }
+ *best_numerator = n1;
+ *best_denominator = d1;
+}
+
+EXPORT_SYMBOL(rational_best_approximation);
int swiotlb_force;
/*
- * Used to do a quick range check in swiotlb_unmap_single and
- * swiotlb_sync_single_*, to see if the memory was in fact allocated by this
+ * Used to do a quick range check in unmap_single and
+ * sync_single_*, to see if the memory was in fact allocated by this
* API.
*/
static char *io_tlb_start, *io_tlb_end;
return paddr;
}
-phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr)
+phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
{
return baddr;
}
return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
}
-static void *swiotlb_bus_to_virt(dma_addr_t address)
+void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
{
- return phys_to_virt(swiotlb_bus_to_phys(address));
+ return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
+}
+
+int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
+ dma_addr_t addr, size_t size)
+{
+ return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
}
int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
return -ENOMEM;
}
-static int
+static inline int
address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
{
- return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+ return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
}
static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
unsigned long flags;
while (size) {
- sz = min(PAGE_SIZE - offset, size);
+ sz = min_t(size_t, PAGE_SIZE - offset, size);
local_irq_save(flags);
buffer = kmap_atomic(pfn_to_page(pfn),
* dma_addr is the kernel virtual address of the bounce buffer to unmap.
*/
static void
-unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
+do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
{
unsigned long flags;
int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
size)) {
/*
* The allocated memory isn't reachable by the device.
- * Fall back on swiotlb_map_single().
*/
free_pages((unsigned long) ret, order);
ret = NULL;
if (!ret) {
/*
* We are either out of memory or the device can't DMA
- * to GFP_DMA memory; fall back on
- * swiotlb_map_single(), which will grab memory from
- * the lowest available address range.
+ * to GFP_DMA memory; fall back on map_single(), which
+ * will grab memory from the lowest available address range.
*/
ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
if (!ret)
(unsigned long long)dev_addr);
/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
- unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
+ do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
return NULL;
}
*dma_handle = dev_addr;
free_pages((unsigned long) vaddr, get_order(size));
else
/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
- unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
+ do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
}
EXPORT_SYMBOL(swiotlb_free_coherent);
* physical address to use is returned.
*
* Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
+ * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
*/
dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size,
struct dma_attrs *attrs)
{
phys_addr_t phys = page_to_phys(page) + offset;
- void *ptr = page_address(page) + offset;
dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
void *map;
BUG_ON(dir == DMA_NONE);
/*
- * If the pointer passed in happens to be in the device's DMA window,
+ * If the address happens to be in the device's DMA window,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
if (!address_needs_mapping(dev, dev_addr, size) &&
- !range_needs_mapping(virt_to_phys(ptr), size))
+ !range_needs_mapping(phys, size))
return dev_addr;
/*
/*
* Unmap a single streaming mode DMA translation. The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_single call. All
+ * match what was provided for in a previous swiotlb_map_page call. All
* other usages are undefined.
*
* After this call, reads by the cpu to the buffer are guaranteed to see
* whatever the device wrote there.
*/
+static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, int dir)
+{
+ char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+
+ BUG_ON(dir == DMA_NONE);
+
+ if (is_swiotlb_buffer(dma_addr)) {
+ do_unmap_single(hwdev, dma_addr, size, dir);
+ return;
+ }
+
+ if (dir != DMA_FROM_DEVICE)
+ return;
+
+ dma_mark_clean(dma_addr, size);
+}
+
void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- char *dma_addr = swiotlb_bus_to_virt(dev_addr);
-
- BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(dma_addr))
- unmap_single(hwdev, dma_addr, size, dir);
- else if (dir == DMA_FROM_DEVICE)
- dma_mark_clean(dma_addr, size);
+ unmap_single(hwdev, dev_addr, size, dir);
}
EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
* Make physical memory consistent for a single streaming mode DMA translation
* after a transfer.
*
- * If you perform a swiotlb_map_single() but wish to interrogate the buffer
+ * If you perform a swiotlb_map_page() but wish to interrogate the buffer
* using the cpu, yet do not wish to teardown the dma mapping, you must
* call this function before doing so. At the next point you give the dma
* address back to the card, you must first perform a
swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, int dir, int target)
{
- char *dma_addr = swiotlb_bus_to_virt(dev_addr);
+ char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(dma_addr))
+
+ if (is_swiotlb_buffer(dma_addr)) {
sync_single(hwdev, dma_addr, size, dir, target);
- else if (dir == DMA_FROM_DEVICE)
- dma_mark_clean(dma_addr, size);
+ return;
+ }
+
+ if (dir != DMA_FROM_DEVICE)
+ return;
+
+ dma_mark_clean(dma_addr, size);
}
void
unsigned long offset, size_t size,
int dir, int target)
{
- char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset;
-
- BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(dma_addr))
- sync_single(hwdev, dma_addr, size, dir, target);
- else if (dir == DMA_FROM_DEVICE)
- dma_mark_clean(dma_addr, size);
+ swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target);
}
void
/*
* Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_single
+ * This is the scatter-gather version of the above swiotlb_map_page
* interface. Here the scatter gather list elements are each tagged with the
* appropriate dma address and length. They are obtained via
* sg_dma_{address,length}(SG).
* The routine returns the number of addr/length pairs actually
* used, at most nents.
*
- * Device ownership issues as mentioned above for swiotlb_map_single are the
+ * Device ownership issues as mentioned above for swiotlb_map_page are the
* same here.
*/
int
/*
* Unmap a set of streaming mode DMA translations. Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_single() above.
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
*/
void
swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
BUG_ON(dir == DMA_NONE);
- for_each_sg(sgl, sg, nelems, i) {
- if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
- unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
- sg->dma_length, dir);
- else if (dir == DMA_FROM_DEVICE)
- dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
- }
+ for_each_sg(sgl, sg, nelems, i)
+ unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
}
EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
struct scatterlist *sg;
int i;
- BUG_ON(dir == DMA_NONE);
-
- for_each_sg(sgl, sg, nelems, i) {
- if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
- sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
+ for_each_sg(sgl, sg, nelems, i)
+ swiotlb_sync_single(hwdev, sg->dma_address,
sg->dma_length, dir, target);
- else if (dir == DMA_FROM_DEVICE)
- dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
- }
}
void
FORMAT_TYPE_LONG_LONG,
FORMAT_TYPE_ULONG,
FORMAT_TYPE_LONG,
+ FORMAT_TYPE_UBYTE,
+ FORMAT_TYPE_BYTE,
FORMAT_TYPE_USHORT,
FORMAT_TYPE_SHORT,
FORMAT_TYPE_UINT,
}
static char *symbol_string(char *buf, char *end, void *ptr,
- struct printf_spec spec)
+ struct printf_spec spec, char ext)
{
unsigned long value = (unsigned long) ptr;
#ifdef CONFIG_KALLSYMS
char sym[KSYM_SYMBOL_LEN];
- sprint_symbol(sym, value);
+ if (ext != 'f')
+ sprint_symbol(sym, value);
+ else
+ kallsyms_lookup(value, NULL, NULL, NULL, sym);
return string(buf, end, sym, spec);
#else
spec.field_width = 2*sizeof(void *);
*
* Right now we handle:
*
- * - 'F' For symbolic function descriptor pointers
+ * - 'F' For symbolic function descriptor pointers with offset
+ * - 'f' For simple symbolic function names without offset
* - 'S' For symbolic direct pointers
* - 'R' For a struct resource pointer, it prints the range of
* addresses (not the name nor the flags)
switch (*fmt) {
case 'F':
+ case 'f':
ptr = dereference_function_descriptor(ptr);
/* Fallthrough */
case 'S':
- return symbol_string(buf, end, ptr, spec);
+ return symbol_string(buf, end, ptr, spec, *fmt);
case 'R':
return resource_string(buf, end, ptr, spec);
case 'm':
spec->qualifier = -1;
if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
*fmt == 'Z' || *fmt == 'z' || *fmt == 't') {
- spec->qualifier = *fmt;
- ++fmt;
- if (spec->qualifier == 'l' && *fmt == 'l') {
- spec->qualifier = 'L';
- ++fmt;
+ spec->qualifier = *fmt++;
+ if (unlikely(spec->qualifier == *fmt)) {
+ if (spec->qualifier == 'l') {
+ spec->qualifier = 'L';
+ ++fmt;
+ } else if (spec->qualifier == 'h') {
+ spec->qualifier = 'H';
+ ++fmt;
+ }
}
}
spec->type = FORMAT_TYPE_SIZE_T;
} else if (spec->qualifier == 't') {
spec->type = FORMAT_TYPE_PTRDIFF;
+ } else if (spec->qualifier == 'H') {
+ if (spec->flags & SIGN)
+ spec->type = FORMAT_TYPE_BYTE;
+ else
+ spec->type = FORMAT_TYPE_UBYTE;
} else if (spec->qualifier == 'h') {
if (spec->flags & SIGN)
spec->type = FORMAT_TYPE_SHORT;
*
* This function follows C99 vsnprintf, but has some extensions:
* %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
* %pR output the address range in a struct resource
*
* The return value is the number of characters which would
case FORMAT_TYPE_PTRDIFF:
num = va_arg(args, ptrdiff_t);
break;
+ case FORMAT_TYPE_UBYTE:
+ num = (unsigned char) va_arg(args, int);
+ break;
+ case FORMAT_TYPE_BYTE:
+ num = (signed char) va_arg(args, int);
+ break;
case FORMAT_TYPE_USHORT:
num = (unsigned short) va_arg(args, int);
break;
case FORMAT_TYPE_PTRDIFF:
save_arg(ptrdiff_t);
break;
+ case FORMAT_TYPE_UBYTE:
+ case FORMAT_TYPE_BYTE:
+ save_arg(char);
+ break;
case FORMAT_TYPE_USHORT:
case FORMAT_TYPE_SHORT:
save_arg(short);
*
* The format follows C99 vsnprintf, but has some extensions:
* %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
* %pR output the address range in a struct resource
* %n is ignored
*
case FORMAT_TYPE_PTRDIFF:
num = get_arg(ptrdiff_t);
break;
+ case FORMAT_TYPE_UBYTE:
+ num = get_arg(unsigned char);
+ break;
+ case FORMAT_TYPE_BYTE:
+ num = get_arg(signed char);
+ break;
case FORMAT_TYPE_USHORT:
num = get_arg(unsigned short);
break;
config MMU_NOTIFIER
bool
+config DEFAULT_MMAP_MIN_ADDR
+ int "Low address space to protect from user allocation"
+ default 4096
+ help
+ This is the portion of low virtual memory which should be protected
+ from userspace allocation. Keeping a user from writing to low pages
+ can help reduce the impact of kernel NULL pointer bugs.
+
+ For most ia64, ppc64 and x86 users with lots of address space
+ a value of 65536 is reasonable and should cause no problems.
+ On arm and other archs it should not be higher than 32768.
+ Programs which use vm86 functionality would either need additional
+ permissions from either the LSM or the capabilities module or have
+ this protection disabled.
+
+ This value can be changed after boot using the
+ /proc/sys/vm/mmap_min_addr tunable.
+
+
config NOMMU_INITIAL_TRIM_EXCESS
int "Turn on mmap() excess space trimming before booting"
depends on !MMU
#include <linux/hash.h>
#include <linux/highmem.h>
#include <linux/blktrace_api.h>
-#include <trace/block.h>
#include <asm/tlbflush.h>
+#include <trace/events/block.h>
+
#define POOL_SIZE 64
#define ISA_POOL_SIZE 16
static mempool_t *page_pool, *isa_page_pool;
-DEFINE_TRACE(block_bio_bounce);
-
#ifdef CONFIG_HIGHMEM
static __init int init_emergency_pool(void)
{
free_uid(user);
}
-void *alloc_locked_buffer(size_t size)
+int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+ size_t size)
{
- unsigned long rlim, vm, pgsz;
- void *buffer = NULL;
+ unsigned long lim, vm, pgsz;
+ int error = -ENOMEM;
pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
- down_write(¤t->mm->mmap_sem);
-
- rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
- vm = current->mm->total_vm + pgsz;
- if (rlim < vm)
- goto out;
+ down_write(&mm->mmap_sem);
- rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
- vm = current->mm->locked_vm + pgsz;
- if (rlim < vm)
+ lim = rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+ vm = mm->total_vm + pgsz;
+ if (lim < vm)
goto out;
- buffer = kzalloc(size, GFP_KERNEL);
- if (!buffer)
+ lim = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+ vm = mm->locked_vm + pgsz;
+ if (lim < vm)
goto out;
- current->mm->total_vm += pgsz;
- current->mm->locked_vm += pgsz;
+ mm->total_vm += pgsz;
+ mm->locked_vm += pgsz;
+ error = 0;
out:
- up_write(¤t->mm->mmap_sem);
- return buffer;
+ up_write(&mm->mmap_sem);
+ return error;
}
-void release_locked_buffer(void *buffer, size_t size)
+void refund_locked_memory(struct mm_struct *mm, size_t size)
{
unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
- down_write(¤t->mm->mmap_sem);
-
- current->mm->total_vm -= pgsz;
- current->mm->locked_vm -= pgsz;
-
- up_write(¤t->mm->mmap_sem);
-}
+ down_write(&mm->mmap_sem);
-void free_locked_buffer(void *buffer, size_t size)
-{
- release_locked_buffer(buffer, size);
+ mm->total_vm -= pgsz;
+ mm->locked_vm -= pgsz;
- kfree(buffer);
+ up_write(&mm->mmap_sem);
}
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
struct percpu_counter vm_committed_as;
+/* amount of vm to protect from userspace access */
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+
/*
* Check that a process has enough memory to allocate a new virtual
* mapping. 0 means there is enough memory for the allocation to
int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
int heap_stack_gap = 0;
+/* amount of vm to protect from userspace access */
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+
atomic_long_t mmap_pages_allocated;
EXPORT_SYMBOL(mem_map);
static int __meminitdata nr_nodemap_entries;
static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
- static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
- static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
static unsigned long __initdata required_kernelcore;
static unsigned long __initdata required_movablecore;
static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
early_node_map[i].end_pfn);
}
-/**
- * push_node_boundaries - Push node boundaries to at least the requested boundary
- * @nid: The nid of the node to push the boundary for
- * @start_pfn: The start pfn of the node
- * @end_pfn: The end pfn of the node
- *
- * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
- * time. Specifically, on x86_64, SRAT will report ranges that can potentially
- * be hotplugged even though no physical memory exists. This function allows
- * an arch to push out the node boundaries so mem_map is allocated that can
- * be used later.
- */
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-void __init push_node_boundaries(unsigned int nid,
- unsigned long start_pfn, unsigned long end_pfn)
-{
- mminit_dprintk(MMINIT_TRACE, "zoneboundary",
- "Entering push_node_boundaries(%u, %lu, %lu)\n",
- nid, start_pfn, end_pfn);
-
- /* Initialise the boundary for this node if necessary */
- if (node_boundary_end_pfn[nid] == 0)
- node_boundary_start_pfn[nid] = -1UL;
-
- /* Update the boundaries */
- if (node_boundary_start_pfn[nid] > start_pfn)
- node_boundary_start_pfn[nid] = start_pfn;
- if (node_boundary_end_pfn[nid] < end_pfn)
- node_boundary_end_pfn[nid] = end_pfn;
-}
-
-/* If necessary, push the node boundary out for reserve hotadd */
-static void __meminit account_node_boundary(unsigned int nid,
- unsigned long *start_pfn, unsigned long *end_pfn)
-{
- mminit_dprintk(MMINIT_TRACE, "zoneboundary",
- "Entering account_node_boundary(%u, %lu, %lu)\n",
- nid, *start_pfn, *end_pfn);
-
- /* Return if boundary information has not been provided */
- if (node_boundary_end_pfn[nid] == 0)
- return;
-
- /* Check the boundaries and update if necessary */
- if (node_boundary_start_pfn[nid] < *start_pfn)
- *start_pfn = node_boundary_start_pfn[nid];
- if (node_boundary_end_pfn[nid] > *end_pfn)
- *end_pfn = node_boundary_end_pfn[nid];
-}
-#else
-void __init push_node_boundaries(unsigned int nid,
- unsigned long start_pfn, unsigned long end_pfn) {}
-
-static void __meminit account_node_boundary(unsigned int nid,
- unsigned long *start_pfn, unsigned long *end_pfn) {}
-#endif
-
-
/**
* get_pfn_range_for_nid - Return the start and end page frames for a node
* @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
if (*start_pfn == -1UL)
*start_pfn = 0;
-
- /* Push the node boundaries out if requested */
- account_node_boundary(nid, start_pfn, end_pfn);
}
/*
{
memset(early_node_map, 0, sizeof(early_node_map));
nr_nodemap_entries = 0;
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
- memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn));
- memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn));
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
}
/* Compare two active node_active_regions */
* Allocation is done in offset-size areas of single unit space. Ie,
* an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0,
* c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring
- * percpu base registers UNIT_SIZE apart.
+ * percpu base registers pcpu_unit_size apart.
*
* There are usually many small percpu allocations many of them as
* small as 4 bytes. The allocator organizes chunks into lists
* region and negative allocated. Allocation inside a chunk is done
* by scanning this map sequentially and serving the first matching
* entry. This is mostly copied from the percpu_modalloc() allocator.
- * Chunks are also linked into a rb tree to ease address to chunk
- * mapping during free.
+ * Chunks can be determined from the address using the index field
+ * in the page struct. The index field contains a pointer to the chunk.
*
* To use this allocator, arch code should do the followings.
*
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/pfn.h>
-#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
struct pcpu_chunk {
struct list_head list; /* linked to pcpu_slot lists */
- struct rb_node rb_node; /* key is chunk->vm->addr */
int free_size; /* free bytes in the chunk */
int contig_hint; /* max contiguous size hint */
struct vm_struct *vm; /* mapped vmalloc region */
void *pcpu_base_addr __read_mostly;
EXPORT_SYMBOL_GPL(pcpu_base_addr);
-/* optional reserved chunk, only accessible for reserved allocations */
+/*
+ * The first chunk which always exists. Note that unlike other
+ * chunks, this one can be allocated and mapped in several different
+ * ways and thus often doesn't live in the vmalloc area.
+ */
+static struct pcpu_chunk *pcpu_first_chunk;
+
+/*
+ * Optional reserved chunk. This chunk reserves part of the first
+ * chunk and serves it for reserved allocations. The amount of
+ * reserved offset is in pcpu_reserved_chunk_limit. When reserved
+ * area doesn't exist, the following variables contain NULL and 0
+ * respectively.
+ */
static struct pcpu_chunk *pcpu_reserved_chunk;
-/* offset limit of the reserved chunk */
static int pcpu_reserved_chunk_limit;
/*
* There are two locks - pcpu_alloc_mutex and pcpu_lock. The former
* protects allocation/reclaim paths, chunks and chunk->page arrays.
* The latter is a spinlock and protects the index data structures -
- * chunk slots, rbtree, chunks and area maps in chunks.
+ * chunk slots, chunks and area maps in chunks.
*
* During allocation, pcpu_alloc_mutex is kept locked all the time and
* pcpu_lock is grabbed and released as necessary. All actual memory
static DEFINE_SPINLOCK(pcpu_lock); /* protects index data structures */
static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
-static struct rb_root pcpu_addr_root = RB_ROOT; /* chunks by address */
/* reclaim work to release fully free chunks, scheduled from free path */
static void pcpu_reclaim(struct work_struct *work);
return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
}
+/* set the pointer to a chunk in a page struct */
+static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
+{
+ page->index = (unsigned long)pcpu;
+}
+
+/* obtain pointer to a chunk from a page struct */
+static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
+{
+ return (struct pcpu_chunk *)page->index;
+}
+
/**
* pcpu_mem_alloc - allocate memory
* @size: bytes to allocate
}
}
-static struct rb_node **pcpu_chunk_rb_search(void *addr,
- struct rb_node **parentp)
-{
- struct rb_node **p = &pcpu_addr_root.rb_node;
- struct rb_node *parent = NULL;
- struct pcpu_chunk *chunk;
-
- while (*p) {
- parent = *p;
- chunk = rb_entry(parent, struct pcpu_chunk, rb_node);
-
- if (addr < chunk->vm->addr)
- p = &(*p)->rb_left;
- else if (addr > chunk->vm->addr)
- p = &(*p)->rb_right;
- else
- break;
- }
-
- if (parentp)
- *parentp = parent;
- return p;
-}
-
/**
- * pcpu_chunk_addr_search - search for chunk containing specified address
- * @addr: address to search for
- *
- * Look for chunk which might contain @addr. More specifically, it
- * searchs for the chunk with the highest start address which isn't
- * beyond @addr.
- *
- * CONTEXT:
- * pcpu_lock.
+ * pcpu_chunk_addr_search - determine chunk containing specified address
+ * @addr: address for which the chunk needs to be determined.
*
* RETURNS:
* The address of the found chunk.
*/
static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
- struct rb_node *n, *parent;
- struct pcpu_chunk *chunk;
+ void *first_start = pcpu_first_chunk->vm->addr;
- /* is it in the reserved chunk? */
- if (pcpu_reserved_chunk) {
- void *start = pcpu_reserved_chunk->vm->addr;
-
- if (addr >= start && addr < start + pcpu_reserved_chunk_limit)
+ /* is it in the first chunk? */
+ if (addr >= first_start && addr < first_start + pcpu_chunk_size) {
+ /* is it in the reserved area? */
+ if (addr < first_start + pcpu_reserved_chunk_limit)
return pcpu_reserved_chunk;
+ return pcpu_first_chunk;
}
- /* nah... search the regular ones */
- n = *pcpu_chunk_rb_search(addr, &parent);
- if (!n) {
- /* no exactly matching chunk, the parent is the closest */
- n = parent;
- BUG_ON(!n);
- }
- chunk = rb_entry(n, struct pcpu_chunk, rb_node);
-
- if (addr < chunk->vm->addr) {
- /* the parent was the next one, look for the previous one */
- n = rb_prev(n);
- BUG_ON(!n);
- chunk = rb_entry(n, struct pcpu_chunk, rb_node);
- }
-
- return chunk;
-}
-
-/**
- * pcpu_chunk_addr_insert - insert chunk into address rb tree
- * @new: chunk to insert
- *
- * Insert @new into address rb tree.
- *
- * CONTEXT:
- * pcpu_lock.
- */
-static void pcpu_chunk_addr_insert(struct pcpu_chunk *new)
-{
- struct rb_node **p, *parent;
-
- p = pcpu_chunk_rb_search(new->vm->addr, &parent);
- BUG_ON(*p);
- rb_link_node(&new->rb_node, parent, p);
- rb_insert_color(&new->rb_node, &pcpu_addr_root);
+ return pcpu_get_page_chunk(vmalloc_to_page(addr));
}
/**
alloc_mask, 0);
if (!*pagep)
goto err;
+ pcpu_set_page_chunk(*pagep, chunk);
}
}
spin_lock_irq(&pcpu_lock);
pcpu_chunk_relocate(chunk, -1);
- pcpu_chunk_addr_insert(chunk);
goto restart;
area_found:
if (chunk == list_first_entry(head, struct pcpu_chunk, list))
continue;
- rb_erase(&chunk->rb_node, &pcpu_addr_root);
list_move(&chunk->list, &todo);
}
if (reserved_size) {
schunk->free_size = reserved_size;
- pcpu_reserved_chunk = schunk; /* not for dynamic alloc */
+ pcpu_reserved_chunk = schunk;
+ pcpu_reserved_chunk_limit = static_size + reserved_size;
} else {
schunk->free_size = dyn_size;
dyn_size = 0; /* dynamic area covered */
if (schunk->free_size)
schunk->map[schunk->map_used++] = schunk->free_size;
- pcpu_reserved_chunk_limit = static_size + schunk->free_size;
-
/* init dynamic chunk if necessary */
if (dyn_size) {
dchunk = alloc_bootmem(sizeof(struct pcpu_chunk));
}
/* link the first chunk in */
- if (!dchunk) {
- pcpu_chunk_relocate(schunk, -1);
- pcpu_chunk_addr_insert(schunk);
- } else {
- pcpu_chunk_relocate(dchunk, -1);
- pcpu_chunk_addr_insert(dchunk);
- }
+ pcpu_first_chunk = dchunk ?: schunk;
+ pcpu_chunk_relocate(pcpu_first_chunk, -1);
/* we're done */
pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
if (error)
goto close_file;
#endif
+ ima_counts_get(file);
return file;
close_file:
if (IS_ERR(file))
return PTR_ERR(file);
- ima_shm_check(file);
if (vma->vm_file)
fput(vma->vm_file);
vma->vm_file = file;
#include <linux/cpu.h>
#include <linux/sysctl.h>
#include <linux/module.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
#include <linux/rcupdate.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
#include <asm/atomic.h>
/*
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/sched.h>
-#include <linux/tracepoint.h>
#include <asm/uaccess.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/kmem.h>
+
/**
* kstrdup - allocate space for and copy an existing string
* @s: the string to duplicate
EXPORT_SYMBOL_GPL(get_user_pages_fast);
/* Tracepoints definitions. */
-DEFINE_TRACE(kmalloc);
-DEFINE_TRACE(kmem_cache_alloc);
-DEFINE_TRACE(kmalloc_node);
-DEFINE_TRACE(kmem_cache_alloc_node);
-DEFINE_TRACE(kfree);
-DEFINE_TRACE(kmem_cache_free);
-
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
#include <linux/bitops.h>
#include <net/genetlink.h>
-#include <trace/skb.h>
+#include <trace/events/skb.h>
#include <asm/unaligned.h>
#include <linux/workqueue.h>
#include <linux/netlink.h>
#include <linux/net_dropmon.h>
-#include <trace/skb.h>
#include <asm/unaligned.h>
#include <asm/bitops.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/skb.h>
-DEFINE_TRACE(kfree_skb);
EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
#include <asm/uaccess.h>
#include <asm/system.h>
-#include <trace/skb.h>
+#include <trace/events/skb.h>
#include "kmap_skb.h"
help
This build tracepoints example modules.
+config SAMPLE_TRACE_EVENTS
+ tristate "Build trace_events examples -- loadable modules only"
+ depends on EVENT_TRACING && m
+ help
+ This build trace event example modules.
+
config SAMPLE_KOBJECT
tristate "Build kobject examples"
help
# Makefile for Linux samples code
-obj-$(CONFIG_SAMPLES) += markers/ kobject/ kprobes/ tracepoints/
+obj-$(CONFIG_SAMPLES) += markers/ kobject/ kprobes/ tracepoints/ trace_events/
--- /dev/null
+# builds the trace events example kernel modules;
+# then to use one (as root): insmod <module_name.ko>
+
+CFLAGS_trace-events-sample.o := -I$(src)
+
+obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace-events-sample.o
--- /dev/null
+#include <linux/module.h>
+#include <linux/kthread.h>
+
+/*
+ * Any file that uses trace points, must include the header.
+ * But only one file, must include the header by defining
+ * CREATE_TRACE_POINTS first. This will make the C code that
+ * creates the handles for the trace points.
+ */
+#define CREATE_TRACE_POINTS
+#include "trace-events-sample.h"
+
+
+static void simple_thread_func(int cnt)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(HZ);
+ trace_foo_bar("hello", cnt);
+}
+
+static int simple_thread(void *arg)
+{
+ int cnt = 0;
+
+ while (!kthread_should_stop())
+ simple_thread_func(cnt++);
+
+ return 0;
+}
+
+static struct task_struct *simple_tsk;
+
+static int __init trace_event_init(void)
+{
+ simple_tsk = kthread_run(simple_thread, NULL, "event-sample");
+ if (IS_ERR(simple_tsk))
+ return -1;
+
+ return 0;
+}
+
+static void __exit trace_event_exit(void)
+{
+ kthread_stop(simple_tsk);
+}
+
+module_init(trace_event_init);
+module_exit(trace_event_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("trace-events-sample");
+MODULE_LICENSE("GPL");
--- /dev/null
+/*
+ * Notice that this file is not protected like a normal header.
+ * We also must allow for rereading of this file. The
+ *
+ * || defined(TRACE_HEADER_MULTI_READ)
+ *
+ * serves this purpose.
+ */
+#if !defined(_TRACE_EVENT_SAMPLE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EVENT_SAMPLE_H
+
+/*
+ * All trace headers should include tracepoint.h, until we finally
+ * make it into a standard header.
+ */
+#include <linux/tracepoint.h>
+
+/*
+ * If TRACE_SYSTEM is defined, that will be the directory created
+ * in the ftrace directory under /debugfs/tracing/events/<system>
+ *
+ * The define_trace.h belowe will also look for a file name of
+ * TRACE_SYSTEM.h where TRACE_SYSTEM is what is defined here.
+ *
+ * If you want a different system than file name, you can override
+ * the header name by defining TRACE_INCLUDE_FILE
+ *
+ * If this file was called, goofy.h, then we would define:
+ *
+ * #define TRACE_INCLUDE_FILE goofy
+ *
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sample
+
+/*
+ * The TRACE_EVENT macro is broken up into 5 parts.
+ *
+ * name: name of the trace point. This is also how to enable the tracepoint.
+ * A function called trace_foo_bar() will be created.
+ *
+ * proto: the prototype of the function trace_foo_bar()
+ * Here it is trace_foo_bar(char *foo, int bar).
+ *
+ * args: must match the arguments in the prototype.
+ * Here it is simply "foo, bar".
+ *
+ * struct: This defines the way the data will be stored in the ring buffer.
+ * There are currently two types of elements. __field and __array.
+ * a __field is broken up into (type, name). Where type can be any
+ * type but an array.
+ * For an array. there are three fields. (type, name, size). The
+ * type of elements in the array, the name of the field and the size
+ * of the array.
+ *
+ * __array( char, foo, 10) is the same as saying char foo[10].
+ *
+ * fast_assign: This is a C like function that is used to store the items
+ * into the ring buffer.
+ *
+ * printk: This is a way to print out the data in pretty print. This is
+ * useful if the system crashes and you are logging via a serial line,
+ * the data can be printed to the console using this "printk" method.
+ *
+ * Note, that for both the assign and the printk, __entry is the handler
+ * to the data structure in the ring buffer, and is defined by the
+ * TP_STRUCT__entry.
+ */
+TRACE_EVENT(foo_bar,
+
+ TP_PROTO(char *foo, int bar),
+
+ TP_ARGS(foo, bar),
+
+ TP_STRUCT__entry(
+ __array( char, foo, 10 )
+ __field( int, bar )
+ ),
+
+ TP_fast_assign(
+ strncpy(__entry->foo, foo, 10);
+ __entry->bar = bar;
+ ),
+
+ TP_printk("foo %s %d", __entry->foo, __entry->bar)
+);
+#endif
+
+/***** NOTICE! The #if protection ends here. *****/
+
+
+/*
+ * There are several ways I could have done this. If I left out the
+ * TRACE_INCLUDE_PATH, then it would default to the kernel source
+ * include/trace/events directory.
+ *
+ * I could specify a path from the define_trace.h file back to this
+ * file.
+ *
+ * #define TRACE_INCLUDE_PATH ../../samples/trace_events
+ *
+ * But I chose to simply make it use the current directory and then in
+ * the Makefile I added:
+ *
+ * CFLAGS_trace-events-sample.o := -I$(PWD)/samples/trace_events/
+ *
+ * This will make sure the current path is part of the include
+ * structure for our file so that we can find it.
+ *
+ * I could have made only the top level directory the include:
+ *
+ * CFLAGS_trace-events-sample.o := -I$(PWD)
+ *
+ * And then let the path to this directory be the TRACE_INCLUDE_PATH:
+ *
+ * #define TRACE_INCLUDE_PATH samples/trace_events
+ *
+ * But then if something defines "samples" or "trace_events" then we
+ * could risk that being converted too, and give us an unexpected
+ * result.
+ */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+/*
+ * TRACE_INCLUDE_FILE is not needed if the filename and TRACE_SYSTEM are equal
+ */
+#define TRACE_INCLUDE_FILE trace-events-sample
+#include <trace/define_trace.h>
# ---------------------------------------------------------------------------
quiet_cmd_gzip = GZIP $@
-cmd_gzip = gzip -f -9 < $< > $@
+cmd_gzip = (cat $(filter-out FORCE,$^) | gzip -f -9 > $@) || \
+ (rm -f $@ ; false)
# Bzip2
# ---------------------------------------------------------------------------
-# Bzip2 does not include size in file... so we have to fake that
-size_append=$(CONFIG_SHELL) $(srctree)/scripts/bin_size
-
-quiet_cmd_bzip2 = BZIP2 $@
-cmd_bzip2 = (bzip2 -9 < $< && $(size_append) $<) > $@ || (rm -f $@ ; false)
+# Bzip2 and LZMA do not include size in file... so we have to fake that;
+# append the size as a 32-bit littleendian number as gzip does.
+size_append = echo -ne $(shell \
+dec_size=0; \
+for F in $1; do \
+ fsize=$$(stat -c "%s" $$F); \
+ dec_size=$$(expr $$dec_size + $$fsize); \
+done; \
+printf "%08x" $$dec_size | \
+ sed 's/\(..\)\(..\)\(..\)\(..\)/\\\\x\4\\\\x\3\\\\x\2\\\\x\1/g' \
+)
+
+quiet_cmd_bzip2 = BZIP2 $@
+cmd_bzip2 = (cat $(filter-out FORCE,$^) | \
+ bzip2 -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
+ (rm -f $@ ; false)
# Lzma
# ---------------------------------------------------------------------------
quiet_cmd_lzma = LZMA $@
-cmd_lzma = (lzma -9 -c $< && $(size_append) $<) >$@ || (rm -f $@ ; false)
+cmd_lzma = (cat $(filter-out FORCE,$^) | \
+ lzma -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
+ (rm -f $@ ; false)
+++ /dev/null
-#!/bin/sh
-
-if [ $# = 0 ] ; then
- echo Usage: $0 file
-fi
-
-size_dec=`stat -c "%s" $1`
-size_hex_echo_string=`printf "%08x" $size_dec |
- sed 's/\(..\)\(..\)\(..\)\(..\)/\\\\x\4\\\\x\3\\\\x\2\\\\x\1/g'`
-/bin/echo -ne $size_hex_echo_string
$state = 0;
}
+sub tracepoint_munge($) {
+ my $file = shift;
+ my $tracepointname = 0;
+ my $tracepointargs = 0;
+
+ if($prototype =~ m/TRACE_EVENT\((.*?),/) {
+ $tracepointname = $1;
+ }
+ if($prototype =~ m/TP_PROTO\((.*?)\)/) {
+ $tracepointargs = $1;
+ }
+ if (($tracepointname eq 0) || ($tracepointargs eq 0)) {
+ print STDERR "Warning(${file}:$.): Unrecognized tracepoint format: \n".
+ "$prototype\n";
+ } else {
+ $prototype = "static inline void trace_$tracepointname($tracepointargs)";
+ }
+}
+
sub syscall_munge() {
my $void = 0;
if ($prototype =~ /SYSCALL_DEFINE/) {
syscall_munge();
}
+ if ($prototype =~ /TRACE_EVENT/) {
+ tracepoint_munge($file);
+ }
dump_function($prototype, $file);
reset_state();
}
# which will also be the location of that section after final link.
# e.g.
#
-# .section ".text.sched"
+# .section ".sched.text", "ax"
# .globl my_func
# my_func:
# [...]
# [...]
#
# Both relocation offsets for the mcounts in the above example will be
-# offset from .text.sched. If we make another file called tmp.s with:
+# offset from .sched.text. If we make another file called tmp.s with:
#
# .section __mcount_loc
# .quad my_func + 0x5
# But this gets hard if my_func is not globl (a static function).
# In such a case we have:
#
-# .section ".text.sched"
+# .section ".sched.text", "ax"
# my_func:
# [...]
# call mcount (offset: 0x5)
See <http://www.linuxjournal.com/article.php?sid=6279> for
more information about this module.
-
- If you are unsure how to answer this question, answer N.
-
-config SECURITY_DEFAULT_MMAP_MIN_ADDR
- int "Low address space to protect from user allocation"
- depends on SECURITY
- default 0
- help
- This is the portion of low virtual memory which should be protected
- from userspace allocation. Keeping a user from writing to low pages
- can help reduce the impact of kernel NULL pointer bugs.
-
- For most ia64, ppc64 and x86 users with lots of address space
- a value of 65536 is reasonable and should cause no problems.
- On arm and other archs it should not be higher than 32768.
- Programs which use vm86 functionality would either need additional
- permissions from either the LSM or the capabilities module or have
- this protection disabled.
-
- This value can be changed after boot using the
- /proc/sys/vm/mmap_min_addr tunable.
+ If you are unsure how to answer this question, answer N.
source security/selinux/Kconfig
source security/smack/Kconfig
# Must precede capability.o in order to stack properly.
obj-$(CONFIG_SECURITY_SELINUX) += selinux/built-in.o
obj-$(CONFIG_SECURITY_SMACK) += smack/built-in.o
+ifeq ($(CONFIG_AUDIT),y)
+obj-$(CONFIG_SECURITY_SMACK) += lsm_audit.o
+endif
obj-$(CONFIG_SECURITY_TOMOYO) += tomoyo/built-in.o
obj-$(CONFIG_SECURITY_ROOTPLUG) += root_plug.o
obj-$(CONFIG_CGROUP_DEVICE) += device_cgroup.o
#include <linux/prctl.h>
#include <linux/securebits.h>
+/*
+ * If a non-root user executes a setuid-root binary in
+ * !secure(SECURE_NOROOT) mode, then we raise capabilities.
+ * However if fE is also set, then the intent is for only
+ * the file capabilities to be applied, and the setuid-root
+ * bit is left on either to change the uid (plausible) or
+ * to get full privilege on a kernel without file capabilities
+ * support. So in that case we do not raise capabilities.
+ *
+ * Warn if that happens, once per boot.
+ */
+static void warn_setuid_and_fcaps_mixed(char *fname)
+{
+ static int warned;
+ if (!warned) {
+ printk(KERN_INFO "warning: `%s' has both setuid-root and"
+ " effective capabilities. Therefore not raising all"
+ " capabilities.\n", fname);
+ warned = 1;
+ }
+}
+
int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
{
NETLINK_CB(skb).eff_cap = current_cap();
return ret;
if (!issecure(SECURE_NOROOT)) {
+ /*
+ * If the legacy file capability is set, then don't set privs
+ * for a setuid root binary run by a non-root user. Do set it
+ * for a root user just to cause least surprise to an admin.
+ */
+ if (effective && new->uid != 0 && new->euid == 0) {
+ warn_setuid_and_fcaps_mixed(bprm->filename);
+ goto skip;
+ }
/*
* To support inheritance of root-permissions and suid-root
* executables under compatibility mode, we override the
if (new->euid == 0)
effective = true;
}
+skip:
/* Don't let someone trace a set[ug]id/setpcap binary with the revised
* credentials unless they have the appropriate permit
{
struct dentry *parent;
- if (!dentry)
+ if (!dentry || IS_ERR(dentry))
return;
parent = dentry->d_parent;
static int __init ima_audit_setup(char *str)
{
unsigned long audit;
- int rc, result = 0;
- char *op = "ima_audit";
- char *cause;
- rc = strict_strtoul(str, 0, &audit);
- if (rc || audit > 1)
- result = 1;
- else
- ima_audit = audit;
- cause = ima_audit ? "enabled" : "not_enabled";
- integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL,
- op, cause, result, 0);
+ if (!strict_strtoul(str, 0, &audit))
+ ima_audit = audit ? 1 : 0;
return 1;
}
__setup("ima_audit=", ima_audit_setup);
ab = audit_log_start(current->audit_context, GFP_KERNEL, audit_msgno);
audit_log_format(ab, "integrity: pid=%d uid=%u auid=%u ses=%u",
- current->pid, current->cred->uid,
+ current->pid, current_cred()->uid,
audit_get_loginuid(current),
audit_get_sessionid(current));
audit_log_task_context(ab);
- switch (audit_msgno) {
- case AUDIT_INTEGRITY_DATA:
- case AUDIT_INTEGRITY_METADATA:
- case AUDIT_INTEGRITY_PCR:
- case AUDIT_INTEGRITY_STATUS:
- audit_log_format(ab, " op=%s cause=%s", op, cause);
- break;
- case AUDIT_INTEGRITY_HASH:
- audit_log_format(ab, " op=%s hash=%s", op, cause);
- break;
- default:
- audit_log_format(ab, " op=%s", op);
- }
+ audit_log_format(ab, " op=");
+ audit_log_string(ab, op);
+ audit_log_format(ab, " cause=");
+ audit_log_string(ab, cause);
audit_log_format(ab, " comm=");
audit_log_untrustedstring(ab, current->comm);
if (fname) {
return rc;
}
-static void ima_pcrread(int idx, u8 *pcr)
+static void __init ima_pcrread(int idx, u8 *pcr)
{
if (!ima_used_chip)
return;
/*
* Calculate the boot aggregate hash
*/
-int ima_calc_boot_aggregate(char *digest)
+int __init ima_calc_boot_aggregate(char *digest)
{
struct hash_desc desc;
struct scatterlist sg;
* implemenents security file system for reporting
* current measurement list and IMA statistics
*/
+#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/rculist.h>
* against concurrent list-extension
*/
rcu_read_lock();
- qe = list_entry(rcu_dereference(qe->later.next),
- struct ima_queue_entry, later);
+ qe = list_entry_rcu(qe->later.next,
+ struct ima_queue_entry, later);
rcu_read_unlock();
(*pos)++;
*/
int ima_open_policy(struct inode * inode, struct file * filp)
{
+ /* No point in being allowed to open it if you aren't going to write */
+ if (!(filp->f_flags & O_WRONLY))
+ return -EACCES;
if (atomic_dec_and_test(&policy_opencount))
return 0;
return -EBUSY;
.release = ima_release_policy
};
-int ima_fs_init(void)
+int __init ima_fs_init(void)
{
ima_dir = securityfs_create_dir("ima", NULL);
if (IS_ERR(ima_dir))
goto out;
ima_policy = securityfs_create_file("policy",
- S_IRUSR | S_IRGRP | S_IWUSR,
+ S_IWUSR,
ima_dir, NULL,
&ima_measure_policy_ops);
if (IS_ERR(ima_policy))
kref_set(&iint->refcount, 1);
}
-void ima_iintcache_init(void)
+void __init ima_iintcache_init(void)
{
iint_cache =
kmem_cache_create("iint_cache", sizeof(struct ima_iint_cache), 0,
* a different value.) Violations add a zero entry to the measurement
* list and extend the aggregate PCR value with ff...ff's.
*/
-static void ima_add_boot_aggregate(void)
+static void __init ima_add_boot_aggregate(void)
{
struct ima_template_entry *entry;
const char *op = "add_boot_aggregate";
audit_cause, result, 0);
}
-int ima_init(void)
+int __init ima_init(void)
{
u8 pcr_i[IMA_DIGEST_SIZE];
int rc;
char *ima_hash = "sha1";
static int __init hash_setup(char *str)
{
- const char *op = "hash_setup";
- const char *hash = "sha1";
- int result = 0;
- int audit_info = 0;
-
- if (strncmp(str, "md5", 3) == 0) {
- hash = "md5";
- ima_hash = str;
- } else if (strncmp(str, "sha1", 4) != 0) {
- hash = "invalid_hash_type";
- result = 1;
- }
- integrity_audit_msg(AUDIT_INTEGRITY_HASH, NULL, NULL, op, hash,
- result, audit_info);
+ if (strncmp(str, "md5", 3) == 0)
+ ima_hash = "md5";
return 1;
}
__setup("ima_hash=", hash_setup);
{
int rc = 0;
- if (IS_ERR(file)) {
- pr_info("%s dentry_open failed\n", filename);
- return rc;
- }
iint->opencount++;
iint->readcount++;
return rc;
}
+static void ima_update_counts(struct ima_iint_cache *iint, int mask)
+{
+ iint->opencount++;
+ if ((mask & MAY_WRITE) || (mask == 0))
+ iint->writecount++;
+ else if (mask & (MAY_READ | MAY_EXEC))
+ iint->readcount++;
+}
+
/**
* ima_path_check - based on policy, collect/store measurement.
* @path: contains a pointer to the path to be measured
* - Opening a file for read when already open for write,
* could result in a file measurement error.
*
- * Return 0 on success, an error code on failure.
- * (Based on the results of appraise_measurement().)
+ * Always return 0 and audit dentry_open failures.
+ * (Return code will be based upon measurement appraisal.)
*/
-int ima_path_check(struct path *path, int mask)
+int ima_path_check(struct path *path, int mask, int update_counts)
{
struct inode *inode = path->dentry->d_inode;
struct ima_iint_cache *iint;
return 0;
mutex_lock(&iint->mutex);
- iint->opencount++;
- if ((mask & MAY_WRITE) || (mask == 0))
- iint->writecount++;
- else if (mask & (MAY_READ | MAY_EXEC))
- iint->readcount++;
+ if (update_counts)
+ ima_update_counts(iint, mask);
rc = ima_must_measure(iint, inode, MAY_READ, PATH_CHECK);
if (rc < 0)
struct dentry *dentry = dget(path->dentry);
struct vfsmount *mnt = mntget(path->mnt);
- file = dentry_open(dentry, mnt, O_RDONLY, current->cred);
+ file = dentry_open(dentry, mnt, O_RDONLY | O_LARGEFILE,
+ current_cred());
+ if (IS_ERR(file)) {
+ int audit_info = 0;
+
+ integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
+ dentry->d_name.name,
+ "add_measurement",
+ "dentry_open failed",
+ 1, audit_info);
+ file = NULL;
+ goto out;
+ }
rc = get_path_measurement(iint, file, dentry->d_name.name);
}
out:
kref_put(&iint->refcount, iint_free);
return 0;
}
+EXPORT_SYMBOL_GPL(ima_path_check);
static int process_measurement(struct file *file, const unsigned char *filename,
int mask, int function)
return rc;
}
-static void opencount_get(struct file *file)
+/*
+ * ima_opens_get - increment file counts
+ *
+ * - for IPC shm and shmat file.
+ * - for nfsd exported files.
+ *
+ * Increment the counts for these files to prevent unnecessary
+ * imbalance messages.
+ */
+void ima_counts_get(struct file *file)
{
struct inode *inode = file->f_dentry->d_inode;
struct ima_iint_cache *iint;
return;
mutex_lock(&iint->mutex);
iint->opencount++;
+ if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+ iint->readcount++;
+
+ if (file->f_mode & FMODE_WRITE)
+ iint->writecount++;
mutex_unlock(&iint->mutex);
}
+EXPORT_SYMBOL_GPL(ima_counts_get);
/**
* ima_file_mmap - based on policy, collect/store measurement.
return 0;
}
-/*
- * ima_shm_check - IPC shm and shmat create/fput a file
- *
- * Maintain the opencount for these files to prevent unnecessary
- * imbalance messages.
- */
-void ima_shm_check(struct file *file)
-{
- opencount_get(file);
- return;
-}
-
/**
* ima_bprm_check - based on policy, collect/store measurement.
* @bprm: contains the linux_binprm structure
} lsm[MAX_LSM_RULES];
};
-/* Without LSM specific knowledge, the default policy can only be
+/*
+ * Without LSM specific knowledge, the default policy can only be
* written in terms of .action, .func, .mask, .fsmagic, and .uid
*/
+
+/*
+ * The minimum rule set to allow for full TCB coverage. Measures all files
+ * opened or mmap for exec and everything read by root. Dangerous because
+ * normal users can easily run the machine out of memory simply building
+ * and running executables.
+ */
static struct ima_measure_rule_entry default_rules[] = {
- {.action = DONT_MEASURE,.fsmagic = PROC_SUPER_MAGIC,
- .flags = IMA_FSMAGIC},
+ {.action = DONT_MEASURE,.fsmagic = PROC_SUPER_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = SYSFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = DEBUGFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = TMPFS_MAGIC,.flags = IMA_FSMAGIC},
- {.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,
- .flags = IMA_FSMAGIC},
- {.action = DONT_MEASURE,.fsmagic = 0xF97CFF8C,.flags = IMA_FSMAGIC},
+ {.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,.flags = IMA_FSMAGIC},
+ {.action = DONT_MEASURE,.fsmagic = SELINUX_MAGIC,.flags = IMA_FSMAGIC},
{.action = MEASURE,.func = FILE_MMAP,.mask = MAY_EXEC,
.flags = IMA_FUNC | IMA_MASK},
{.action = MEASURE,.func = BPRM_CHECK,.mask = MAY_EXEC,
.flags = IMA_FUNC | IMA_MASK},
{.action = MEASURE,.func = PATH_CHECK,.mask = MAY_READ,.uid = 0,
- .flags = IMA_FUNC | IMA_MASK | IMA_UID}
+ .flags = IMA_FUNC | IMA_MASK | IMA_UID},
};
static LIST_HEAD(measure_default_rules);
static DEFINE_MUTEX(ima_measure_mutex);
+static bool ima_use_tcb __initdata;
+static int __init default_policy_setup(char *str)
+{
+ ima_use_tcb = 1;
+ return 1;
+}
+__setup("ima_tcb", default_policy_setup);
+
/**
* ima_match_rules - determine whether an inode matches the measure rule.
* @rule: a pointer to a rule
if ((rule->flags & IMA_UID) && rule->uid != tsk->cred->uid)
return false;
for (i = 0; i < MAX_LSM_RULES; i++) {
- int rc;
+ int rc = 0;
u32 osid, sid;
if (!rule->lsm[i].rule)
security_inode_getsecid(inode, &osid);
rc = security_filter_rule_match(osid,
rule->lsm[i].type,
- AUDIT_EQUAL,
+ Audit_equal,
rule->lsm[i].rule,
NULL);
break;
security_task_getsecid(tsk, &sid);
rc = security_filter_rule_match(sid,
rule->lsm[i].type,
- AUDIT_EQUAL,
+ Audit_equal,
rule->lsm[i].rule,
NULL);
default:
* ima_measure points to either the measure_default_rules or the
* the new measure_policy_rules.
*/
-void ima_init_policy(void)
+void __init ima_init_policy(void)
{
- int i;
+ int i, entries;
+
+ /* if !ima_use_tcb set entries = 0 so we load NO default rules */
+ if (ima_use_tcb)
+ entries = ARRAY_SIZE(default_rules);
+ else
+ entries = 0;
- for (i = 0; i < ARRAY_SIZE(default_rules); i++)
+ for (i = 0; i < entries; i++)
list_add_tail(&default_rules[i].list, &measure_default_rules);
ima_measure = &measure_default_rules;
}
entry->lsm[lsm_rule].type = audit_type;
result = security_filter_rule_init(entry->lsm[lsm_rule].type,
- AUDIT_EQUAL, args,
+ Audit_equal, args,
&entry->lsm[lsm_rule].rule);
return result;
}
--- /dev/null
+/*
+ * common LSM auditing functions
+ *
+ * Based on code written for SELinux by :
+ * Stephen Smalley, <sds@epoch.ncsc.mil>
+ * James Morris <jmorris@redhat.com>
+ * Author : Etienne Basset, <etienne.basset@ensta.org>
+ *
+ * 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.
+ */
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <net/sock.h>
+#include <linux/un.h>
+#include <net/af_unix.h>
+#include <linux/audit.h>
+#include <linux/ipv6.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/dccp.h>
+#include <linux/sctp.h>
+#include <linux/lsm_audit.h>
+
+/**
+ * ipv4_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return 0 on success
+ */
+int ipv4_skb_to_auditdata(struct sk_buff *skb,
+ struct common_audit_data *ad, u8 *proto)
+{
+ int ret = 0;
+ struct iphdr *ih;
+
+ ih = ip_hdr(skb);
+ if (ih == NULL)
+ return -EINVAL;
+
+ ad->u.net.v4info.saddr = ih->saddr;
+ ad->u.net.v4info.daddr = ih->daddr;
+
+ if (proto)
+ *proto = ih->protocol;
+ /* non initial fragment */
+ if (ntohs(ih->frag_off) & IP_OFFSET)
+ return 0;
+
+ switch (ih->protocol) {
+ case IPPROTO_TCP: {
+ struct tcphdr *th = tcp_hdr(skb);
+ if (th == NULL)
+ break;
+
+ ad->u.net.sport = th->source;
+ ad->u.net.dport = th->dest;
+ break;
+ }
+ case IPPROTO_UDP: {
+ struct udphdr *uh = udp_hdr(skb);
+ if (uh == NULL)
+ break;
+
+ ad->u.net.sport = uh->source;
+ ad->u.net.dport = uh->dest;
+ break;
+ }
+ case IPPROTO_DCCP: {
+ struct dccp_hdr *dh = dccp_hdr(skb);
+ if (dh == NULL)
+ break;
+
+ ad->u.net.sport = dh->dccph_sport;
+ ad->u.net.dport = dh->dccph_dport;
+ break;
+ }
+ case IPPROTO_SCTP: {
+ struct sctphdr *sh = sctp_hdr(skb);
+ if (sh == NULL)
+ break;
+ ad->u.net.sport = sh->source;
+ ad->u.net.dport = sh->dest;
+ break;
+ }
+ default:
+ ret = -EINVAL;
+ }
+ return ret;
+}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+/**
+ * ipv6_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return 0 on success
+ */
+int ipv6_skb_to_auditdata(struct sk_buff *skb,
+ struct common_audit_data *ad, u8 *proto)
+{
+ int offset, ret = 0;
+ struct ipv6hdr *ip6;
+ u8 nexthdr;
+
+ ip6 = ipv6_hdr(skb);
+ if (ip6 == NULL)
+ return -EINVAL;
+ ipv6_addr_copy(&ad->u.net.v6info.saddr, &ip6->saddr);
+ ipv6_addr_copy(&ad->u.net.v6info.daddr, &ip6->daddr);
+ ret = 0;
+ /* IPv6 can have several extension header before the Transport header
+ * skip them */
+ offset = skb_network_offset(skb);
+ offset += sizeof(*ip6);
+ nexthdr = ip6->nexthdr;
+ offset = ipv6_skip_exthdr(skb, offset, &nexthdr);
+ if (offset < 0)
+ return 0;
+ if (proto)
+ *proto = nexthdr;
+ switch (nexthdr) {
+ case IPPROTO_TCP: {
+ struct tcphdr _tcph, *th;
+
+ th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+ if (th == NULL)
+ break;
+
+ ad->u.net.sport = th->source;
+ ad->u.net.dport = th->dest;
+ break;
+ }
+ case IPPROTO_UDP: {
+ struct udphdr _udph, *uh;
+
+ uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+ if (uh == NULL)
+ break;
+
+ ad->u.net.sport = uh->source;
+ ad->u.net.dport = uh->dest;
+ break;
+ }
+ case IPPROTO_DCCP: {
+ struct dccp_hdr _dccph, *dh;
+
+ dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
+ if (dh == NULL)
+ break;
+
+ ad->u.net.sport = dh->dccph_sport;
+ ad->u.net.dport = dh->dccph_dport;
+ break;
+ }
+ case IPPROTO_SCTP: {
+ struct sctphdr _sctph, *sh;
+
+ sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
+ if (sh == NULL)
+ break;
+ ad->u.net.sport = sh->source;
+ ad->u.net.dport = sh->dest;
+ break;
+ }
+ default:
+ ret = -EINVAL;
+ }
+ return ret;
+}
+#endif
+
+
+static inline void print_ipv6_addr(struct audit_buffer *ab,
+ struct in6_addr *addr, __be16 port,
+ char *name1, char *name2)
+{
+ if (!ipv6_addr_any(addr))
+ audit_log_format(ab, " %s=%pI6", name1, addr);
+ if (port)
+ audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr,
+ __be16 port, char *name1, char *name2)
+{
+ if (addr)
+ audit_log_format(ab, " %s=%pI4", name1, &addr);
+ if (port)
+ audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+/**
+ * dump_common_audit_data - helper to dump common audit data
+ * @a : common audit data
+ *
+ */
+static void dump_common_audit_data(struct audit_buffer *ab,
+ struct common_audit_data *a)
+{
+ struct inode *inode = NULL;
+ struct task_struct *tsk = current;
+
+ if (a->tsk)
+ tsk = a->tsk;
+ if (tsk && tsk->pid) {
+ audit_log_format(ab, " pid=%d comm=", tsk->pid);
+ audit_log_untrustedstring(ab, tsk->comm);
+ }
+
+ switch (a->type) {
+ case LSM_AUDIT_DATA_IPC:
+ audit_log_format(ab, " key=%d ", a->u.ipc_id);
+ break;
+ case LSM_AUDIT_DATA_CAP:
+ audit_log_format(ab, " capability=%d ", a->u.cap);
+ break;
+ case LSM_AUDIT_DATA_FS:
+ if (a->u.fs.path.dentry) {
+ struct dentry *dentry = a->u.fs.path.dentry;
+ if (a->u.fs.path.mnt) {
+ audit_log_d_path(ab, "path=", &a->u.fs.path);
+ } else {
+ audit_log_format(ab, " name=");
+ audit_log_untrustedstring(ab,
+ dentry->d_name.name);
+ }
+ inode = dentry->d_inode;
+ } else if (a->u.fs.inode) {
+ struct dentry *dentry;
+ inode = a->u.fs.inode;
+ dentry = d_find_alias(inode);
+ if (dentry) {
+ audit_log_format(ab, " name=");
+ audit_log_untrustedstring(ab,
+ dentry->d_name.name);
+ dput(dentry);
+ }
+ }
+ if (inode)
+ audit_log_format(ab, " dev=%s ino=%lu",
+ inode->i_sb->s_id,
+ inode->i_ino);
+ break;
+ case LSM_AUDIT_DATA_TASK:
+ tsk = a->u.tsk;
+ if (tsk && tsk->pid) {
+ audit_log_format(ab, " pid=%d comm=", tsk->pid);
+ audit_log_untrustedstring(ab, tsk->comm);
+ }
+ break;
+ case LSM_AUDIT_DATA_NET:
+ if (a->u.net.sk) {
+ struct sock *sk = a->u.net.sk;
+ struct unix_sock *u;
+ int len = 0;
+ char *p = NULL;
+
+ switch (sk->sk_family) {
+ case AF_INET: {
+ struct inet_sock *inet = inet_sk(sk);
+
+ print_ipv4_addr(ab, inet->rcv_saddr,
+ inet->sport,
+ "laddr", "lport");
+ print_ipv4_addr(ab, inet->daddr,
+ inet->dport,
+ "faddr", "fport");
+ break;
+ }
+ case AF_INET6: {
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipv6_pinfo *inet6 = inet6_sk(sk);
+
+ print_ipv6_addr(ab, &inet6->rcv_saddr,
+ inet->sport,
+ "laddr", "lport");
+ print_ipv6_addr(ab, &inet6->daddr,
+ inet->dport,
+ "faddr", "fport");
+ break;
+ }
+ case AF_UNIX:
+ u = unix_sk(sk);
+ if (u->dentry) {
+ struct path path = {
+ .dentry = u->dentry,
+ .mnt = u->mnt
+ };
+ audit_log_d_path(ab, "path=", &path);
+ break;
+ }
+ if (!u->addr)
+ break;
+ len = u->addr->len-sizeof(short);
+ p = &u->addr->name->sun_path[0];
+ audit_log_format(ab, " path=");
+ if (*p)
+ audit_log_untrustedstring(ab, p);
+ else
+ audit_log_n_hex(ab, p, len);
+ break;
+ }
+ }
+
+ switch (a->u.net.family) {
+ case AF_INET:
+ print_ipv4_addr(ab, a->u.net.v4info.saddr,
+ a->u.net.sport,
+ "saddr", "src");
+ print_ipv4_addr(ab, a->u.net.v4info.daddr,
+ a->u.net.dport,
+ "daddr", "dest");
+ break;
+ case AF_INET6:
+ print_ipv6_addr(ab, &a->u.net.v6info.saddr,
+ a->u.net.sport,
+ "saddr", "src");
+ print_ipv6_addr(ab, &a->u.net.v6info.daddr,
+ a->u.net.dport,
+ "daddr", "dest");
+ break;
+ }
+ if (a->u.net.netif > 0) {
+ struct net_device *dev;
+
+ /* NOTE: we always use init's namespace */
+ dev = dev_get_by_index(&init_net, a->u.net.netif);
+ if (dev) {
+ audit_log_format(ab, " netif=%s", dev->name);
+ dev_put(dev);
+ }
+ }
+ break;
+#ifdef CONFIG_KEYS
+ case LSM_AUDIT_DATA_KEY:
+ audit_log_format(ab, " key_serial=%u", a->u.key_struct.key);
+ if (a->u.key_struct.key_desc) {
+ audit_log_format(ab, " key_desc=");
+ audit_log_untrustedstring(ab, a->u.key_struct.key_desc);
+ }
+ break;
+#endif
+ } /* switch (a->type) */
+}
+
+/**
+ * common_lsm_audit - generic LSM auditing function
+ * @a: auxiliary audit data
+ *
+ * setup the audit buffer for common security information
+ * uses callback to print LSM specific information
+ */
+void common_lsm_audit(struct common_audit_data *a)
+{
+ struct audit_buffer *ab;
+
+ if (a == NULL)
+ return;
+ /* we use GFP_ATOMIC so we won't sleep */
+ ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_AVC);
+
+ if (ab == NULL)
+ return;
+
+ if (a->lsm_pre_audit)
+ a->lsm_pre_audit(ab, a);
+
+ dump_common_audit_data(ab, a);
+
+ if (a->lsm_post_audit)
+ a->lsm_post_audit(ab, a);
+
+ audit_log_end(ab);
+}
}
static struct security_operations rootplug_security_ops = {
- /* Use the capability functions for some of the hooks */
- .ptrace_may_access = cap_ptrace_may_access,
- .ptrace_traceme = cap_ptrace_traceme,
- .capget = cap_capget,
- .capset = cap_capset,
- .capable = cap_capable,
-
- .bprm_set_creds = cap_bprm_set_creds,
-
- .task_fix_setuid = cap_task_fix_setuid,
- .task_prctl = cap_task_prctl,
-
.bprm_check_security = rootplug_bprm_check_security,
};
struct security_operations *security_ops; /* Initialized to NULL */
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR;
-
static inline int verify(struct security_operations *ops)
{
/* verify the security_operations structure exists */
if (denied) {
if (flags & AVC_STRICT)
rc = -EACCES;
- else if (!selinux_enforcing || security_permissive_sid(ssid))
+ else if (!selinux_enforcing || (avd->flags & AVD_FLAGS_PERMISSIVE))
avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
tsid, tclass, avd->seqno);
else
u32 tsid, sid;
int rc;
- rc = secondary_ops->sysctl(table, op);
- if (rc)
- return rc;
-
sid = current_sid();
rc = selinux_sysctl_get_sid(table, (op == 0001) ?
{
const struct task_security_struct *tsec = current_security();
struct itimerval itimer;
- struct sighand_struct *psig;
u32 osid, sid;
int rc, i;
- unsigned long flags;
osid = tsec->osid;
sid = tsec->sid;
memset(&itimer, 0, sizeof itimer);
for (i = 0; i < 3; i++)
do_setitimer(i, &itimer, NULL);
- flush_signals(current);
spin_lock_irq(¤t->sighand->siglock);
- flush_signal_handlers(current, 1);
- sigemptyset(¤t->blocked);
- recalc_sigpending();
+ if (!(current->signal->flags & SIGNAL_GROUP_EXIT)) {
+ __flush_signals(current);
+ flush_signal_handlers(current, 1);
+ sigemptyset(¤t->blocked);
+ }
spin_unlock_irq(¤t->sighand->siglock);
}
/* Wake up the parent if it is waiting so that it can recheck
* wait permission to the new task SID. */
- read_lock_irq(&tasklist_lock);
- psig = current->parent->sighand;
- spin_lock_irqsave(&psig->siglock, flags);
- wake_up_interruptible(¤t->parent->signal->wait_chldexit);
- spin_unlock_irqrestore(&psig->siglock, flags);
- read_unlock_irq(&tasklist_lock);
+ read_lock(&tasklist_lock);
+ wake_up_interruptible(¤t->real_parent->signal->wait_chldexit);
+ read_unlock(&tasklist_lock);
}
/* superblock security operations */
#ifndef _SELINUX_SECURITY_H_
#define _SELINUX_SECURITY_H_
+#include <linux/magic.h>
#include "flask.h"
#define SECSID_NULL 0x00000000 /* unspecified SID */
#define SECSID_WILD 0xffffffff /* wildcard SID */
#define SECCLASS_NULL 0x0000 /* no class */
-#define SELINUX_MAGIC 0xf97cff8c
-
/* Identify specific policy version changes */
#define POLICYDB_VERSION_BASE 15
#define POLICYDB_VERSION_BOOL 16
u32 auditallow;
u32 auditdeny;
u32 seqno;
+ u32 flags;
};
-int security_permissive_sid(u32 sid);
+/* definitions of av_decision.flags */
+#define AVD_FLAGS_PERMISSIVE 0x0001
int security_compute_av(u32 ssid, u32 tsid,
u16 tclass, u32 requested,
{ AUDIT_DEL_RULE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
{ AUDIT_USER, NETLINK_AUDIT_SOCKET__NLMSG_RELAY },
{ AUDIT_SIGNAL_INFO, NETLINK_AUDIT_SOCKET__NLMSG_READ },
+ { AUDIT_TRIM, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+ { AUDIT_MAKE_EQUIV, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
{ AUDIT_TTY_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ },
{ AUDIT_TTY_SET, NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT },
};
goto out2;
length = scnprintf(buf, SIMPLE_TRANSACTION_LIMIT,
- "%x %x %x %x %u",
+ "%x %x %x %x %u %x",
avd.allowed, 0xffffffff,
avd.auditallow, avd.auditdeny,
- avd.seqno);
+ avd.seqno, avd.flags);
out2:
kfree(tcon);
out:
goto out;
}
- if (count > PAGE_SIZE) {
- ret = -EINVAL;
- goto out;
- }
page = (char *)get_zeroed_page(GFP_KERNEL);
if (!page) {
ret = -ENOMEM;
avd->auditallow = 0;
avd->auditdeny = 0xffffffff;
avd->seqno = latest_granting;
+ avd->flags = 0;
/*
* Check for all the invalid cases.
return 0;
}
-/*
- * Given a sid find if the type has the permissive flag set
- */
-int security_permissive_sid(u32 sid)
-{
- struct context *context;
- u32 type;
- int rc;
-
- read_lock(&policy_rwlock);
-
- context = sidtab_search(&sidtab, sid);
- BUG_ON(!context);
-
- type = context->type;
- /*
- * we are intentionally using type here, not type-1, the 0th bit may
- * someday indicate that we are globally setting permissive in policy.
- */
- rc = ebitmap_get_bit(&policydb.permissive_map, type);
-
- read_unlock(&policy_rwlock);
- return rc;
-}
-
static int security_validtrans_handle_fail(struct context *ocontext,
struct context *ncontext,
struct context *tcontext,
rc = context_struct_compute_av(scontext, tcontext, tclass,
requested, avd);
+
+ /* permissive domain? */
+ if (ebitmap_get_bit(&policydb.permissive_map, scontext->type))
+ avd->flags |= AVD_FLAGS_PERMISSIVE;
out:
read_unlock(&policy_rwlock);
return rc;
#include <net/netlabel.h>
#include <linux/list.h>
#include <linux/rculist.h>
+#include <linux/lsm_audit.h>
/*
* Why 23? CIPSO is constrained to 30, so a 32 byte buffer is
#define MAY_READWRITE (MAY_READ | MAY_WRITE)
#define MAY_NOT 0
+/*
+ * Number of access types used by Smack (rwxa)
+ */
+#define SMK_NUM_ACCESS_TYPE 4
+
+/*
+ * Smack audit data; is empty if CONFIG_AUDIT not set
+ * to save some stack
+ */
+struct smk_audit_info {
+#ifdef CONFIG_AUDIT
+ struct common_audit_data a;
+#endif
+};
/*
* These functions are in smack_lsm.c
*/
/*
* These functions are in smack_access.c
*/
-int smk_access(char *, char *, int);
-int smk_curacc(char *, u32);
+int smk_access(char *, char *, int, struct smk_audit_info *);
+int smk_curacc(char *, u32, struct smk_audit_info *);
int smack_to_cipso(const char *, struct smack_cipso *);
void smack_from_cipso(u32, char *, char *);
char *smack_from_secid(const u32);
return sip->smk_inode;
}
+/*
+ * logging functions
+ */
+#define SMACK_AUDIT_DENIED 0x1
+#define SMACK_AUDIT_ACCEPT 0x2
+extern int log_policy;
+
+void smack_log(char *subject_label, char *object_label,
+ int request,
+ int result, struct smk_audit_info *auditdata);
+
+#ifdef CONFIG_AUDIT
+
+/*
+ * some inline functions to set up audit data
+ * they do nothing if CONFIG_AUDIT is not set
+ *
+ */
+static inline void smk_ad_init(struct smk_audit_info *a, const char *func,
+ char type)
+{
+ memset(a, 0, sizeof(*a));
+ a->a.type = type;
+ a->a.function = func;
+}
+
+static inline void smk_ad_setfield_u_tsk(struct smk_audit_info *a,
+ struct task_struct *t)
+{
+ a->a.u.tsk = t;
+}
+static inline void smk_ad_setfield_u_fs_path_dentry(struct smk_audit_info *a,
+ struct dentry *d)
+{
+ a->a.u.fs.path.dentry = d;
+}
+static inline void smk_ad_setfield_u_fs_path_mnt(struct smk_audit_info *a,
+ struct vfsmount *m)
+{
+ a->a.u.fs.path.mnt = m;
+}
+static inline void smk_ad_setfield_u_fs_inode(struct smk_audit_info *a,
+ struct inode *i)
+{
+ a->a.u.fs.inode = i;
+}
+static inline void smk_ad_setfield_u_fs_path(struct smk_audit_info *a,
+ struct path p)
+{
+ a->a.u.fs.path = p;
+}
+static inline void smk_ad_setfield_u_net_sk(struct smk_audit_info *a,
+ struct sock *sk)
+{
+ a->a.u.net.sk = sk;
+}
+
+#else /* no AUDIT */
+
+static inline void smk_ad_init(struct smk_audit_info *a, const char *func,
+ char type)
+{
+}
+static inline void smk_ad_setfield_u_tsk(struct smk_audit_info *a,
+ struct task_struct *t)
+{
+}
+static inline void smk_ad_setfield_u_fs_path_dentry(struct smk_audit_info *a,
+ struct dentry *d)
+{
+}
+static inline void smk_ad_setfield_u_fs_path_mnt(struct smk_audit_info *a,
+ struct vfsmount *m)
+{
+}
+static inline void smk_ad_setfield_u_fs_inode(struct smk_audit_info *a,
+ struct inode *i)
+{
+}
+static inline void smk_ad_setfield_u_fs_path(struct smk_audit_info *a,
+ struct path p)
+{
+}
+static inline void smk_ad_setfield_u_net_sk(struct smk_audit_info *a,
+ struct sock *sk)
+{
+}
+#endif
+
#endif /* _SECURITY_SMACK_H */
*/
static u32 smack_next_secid = 10;
+/*
+ * what events do we log
+ * can be overwritten at run-time by /smack/logging
+ */
+int log_policy = SMACK_AUDIT_DENIED;
+
/**
* smk_access - determine if a subject has a specific access to an object
* @subject_label: a pointer to the subject's Smack label
* @object_label: a pointer to the object's Smack label
* @request: the access requested, in "MAY" format
+ * @a : a pointer to the audit data
*
* This function looks up the subject/object pair in the
* access rule list and returns 0 if the access is permitted,
* will be on the list, so checking the pointers may be a worthwhile
* optimization.
*/
-int smk_access(char *subject_label, char *object_label, int request)
+int smk_access(char *subject_label, char *object_label, int request,
+ struct smk_audit_info *a)
{
u32 may = MAY_NOT;
struct smack_rule *srp;
+ int rc = 0;
/*
* Hardcoded comparisons.
* A star subject can't access any object.
*/
if (subject_label == smack_known_star.smk_known ||
- strcmp(subject_label, smack_known_star.smk_known) == 0)
- return -EACCES;
+ strcmp(subject_label, smack_known_star.smk_known) == 0) {
+ rc = -EACCES;
+ goto out_audit;
+ }
/*
* An internet object can be accessed by any subject.
* Tasks cannot be assigned the internet label.
subject_label == smack_known_web.smk_known ||
strcmp(object_label, smack_known_web.smk_known) == 0 ||
strcmp(subject_label, smack_known_web.smk_known) == 0)
- return 0;
+ goto out_audit;
/*
* A star object can be accessed by any subject.
*/
if (object_label == smack_known_star.smk_known ||
strcmp(object_label, smack_known_star.smk_known) == 0)
- return 0;
+ goto out_audit;
/*
* An object can be accessed in any way by a subject
* with the same label.
*/
if (subject_label == object_label ||
strcmp(subject_label, object_label) == 0)
- return 0;
+ goto out_audit;
/*
* A hat subject can read any object.
* A floor object can be read by any subject.
if ((request & MAY_ANYREAD) == request) {
if (object_label == smack_known_floor.smk_known ||
strcmp(object_label, smack_known_floor.smk_known) == 0)
- return 0;
+ goto out_audit;
if (subject_label == smack_known_hat.smk_known ||
strcmp(subject_label, smack_known_hat.smk_known) == 0)
- return 0;
+ goto out_audit;
}
/*
* Beyond here an explicit relationship is required.
* This is a bit map operation.
*/
if ((request & may) == request)
- return 0;
-
- return -EACCES;
+ goto out_audit;
+
+ rc = -EACCES;
+out_audit:
+#ifdef CONFIG_AUDIT
+ if (a)
+ smack_log(subject_label, object_label, request, rc, a);
+#endif
+ return rc;
}
/**
* smk_curacc - determine if current has a specific access to an object
* @obj_label: a pointer to the object's Smack label
* @mode: the access requested, in "MAY" format
+ * @a : common audit data
*
* This function checks the current subject label/object label pair
* in the access rule list and returns 0 if the access is permitted,
* non zero otherwise. It allows that current may have the capability
* to override the rules.
*/
-int smk_curacc(char *obj_label, u32 mode)
+int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
{
int rc;
+ char *sp = current_security();
- rc = smk_access(current_security(), obj_label, mode);
+ rc = smk_access(sp, obj_label, mode, NULL);
if (rc == 0)
- return 0;
+ goto out_audit;
/*
* Return if a specific label has been designated as the
* have that label.
*/
if (smack_onlycap != NULL && smack_onlycap != current->cred->security)
- return rc;
+ goto out_audit;
if (capable(CAP_MAC_OVERRIDE))
return 0;
+out_audit:
+#ifdef CONFIG_AUDIT
+ if (a)
+ smack_log(sp, obj_label, mode, rc, a);
+#endif
return rc;
}
+#ifdef CONFIG_AUDIT
+/**
+ * smack_str_from_perm : helper to transalate an int to a
+ * readable string
+ * @string : the string to fill
+ * @access : the int
+ *
+ */
+static inline void smack_str_from_perm(char *string, int access)
+{
+ int i = 0;
+ if (access & MAY_READ)
+ string[i++] = 'r';
+ if (access & MAY_WRITE)
+ string[i++] = 'w';
+ if (access & MAY_EXEC)
+ string[i++] = 'x';
+ if (access & MAY_APPEND)
+ string[i++] = 'a';
+ string[i] = '\0';
+}
+/**
+ * smack_log_callback - SMACK specific information
+ * will be called by generic audit code
+ * @ab : the audit_buffer
+ * @a : audit_data
+ *
+ */
+static void smack_log_callback(struct audit_buffer *ab, void *a)
+{
+ struct common_audit_data *ad = a;
+ struct smack_audit_data *sad = &ad->lsm_priv.smack_audit_data;
+ audit_log_format(ab, "lsm=SMACK fn=%s action=%s", ad->function,
+ sad->result ? "denied" : "granted");
+ audit_log_format(ab, " subject=");
+ audit_log_untrustedstring(ab, sad->subject);
+ audit_log_format(ab, " object=");
+ audit_log_untrustedstring(ab, sad->object);
+ audit_log_format(ab, " requested=%s", sad->request);
+}
+
+/**
+ * smack_log - Audit the granting or denial of permissions.
+ * @subject_label : smack label of the requester
+ * @object_label : smack label of the object being accessed
+ * @request: requested permissions
+ * @result: result from smk_access
+ * @a: auxiliary audit data
+ *
+ * Audit the granting or denial of permissions in accordance
+ * with the policy.
+ */
+void smack_log(char *subject_label, char *object_label, int request,
+ int result, struct smk_audit_info *ad)
+{
+ char request_buffer[SMK_NUM_ACCESS_TYPE + 1];
+ struct smack_audit_data *sad;
+ struct common_audit_data *a = &ad->a;
+
+ /* check if we have to log the current event */
+ if (result != 0 && (log_policy & SMACK_AUDIT_DENIED) == 0)
+ return;
+ if (result == 0 && (log_policy & SMACK_AUDIT_ACCEPT) == 0)
+ return;
+
+ if (a->function == NULL)
+ a->function = "unknown";
+
+ /* end preparing the audit data */
+ sad = &a->lsm_priv.smack_audit_data;
+ smack_str_from_perm(request_buffer, request);
+ sad->subject = subject_label;
+ sad->object = object_label;
+ sad->request = request_buffer;
+ sad->result = result;
+ a->lsm_pre_audit = smack_log_callback;
+
+ common_lsm_audit(a);
+}
+#else /* #ifdef CONFIG_AUDIT */
+void smack_log(char *subject_label, char *object_label, int request,
+ int result, struct smk_audit_info *ad)
+{
+}
+#endif
+
static DEFINE_MUTEX(smack_known_lock);
/**
if (found)
smack[i] = '\0';
else if (i >= len || string[i] > '~' || string[i] <= ' ' ||
- string[i] == '/') {
+ string[i] == '/' || string[i] == '"' ||
+ string[i] == '\\' || string[i] == '\'') {
smack[i] = '\0';
found = 1;
} else
#include <net/netlabel.h>
#include <net/cipso_ipv4.h>
#include <linux/audit.h>
-
#include "smack.h"
#define task_security(task) (task_cred_xxx((task), security))
static int smack_ptrace_may_access(struct task_struct *ctp, unsigned int mode)
{
int rc;
+ struct smk_audit_info ad;
+ char *sp, *tsp;
rc = cap_ptrace_may_access(ctp, mode);
if (rc != 0)
return rc;
- rc = smk_access(current_security(), task_security(ctp), MAY_READWRITE);
+ sp = current_security();
+ tsp = task_security(ctp);
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+ smk_ad_setfield_u_tsk(&ad, ctp);
+
+ /* we won't log here, because rc can be overriden */
+ rc = smk_access(sp, tsp, MAY_READWRITE, NULL);
if (rc != 0 && capable(CAP_MAC_OVERRIDE))
- return 0;
+ rc = 0;
+
+ smack_log(sp, tsp, MAY_READWRITE, rc, &ad);
return rc;
}
static int smack_ptrace_traceme(struct task_struct *ptp)
{
int rc;
+ struct smk_audit_info ad;
+ char *sp, *tsp;
rc = cap_ptrace_traceme(ptp);
if (rc != 0)
return rc;
- rc = smk_access(task_security(ptp), current_security(), MAY_READWRITE);
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+ smk_ad_setfield_u_tsk(&ad, ptp);
+
+ sp = current_security();
+ tsp = task_security(ptp);
+ /* we won't log here, because rc can be overriden */
+ rc = smk_access(tsp, sp, MAY_READWRITE, NULL);
if (rc != 0 && has_capability(ptp, CAP_MAC_OVERRIDE))
- return 0;
+ rc = 0;
+
+ smack_log(tsp, sp, MAY_READWRITE, rc, &ad);
return rc;
}
static int smack_sb_statfs(struct dentry *dentry)
{
struct superblock_smack *sbp = dentry->d_sb->s_security;
+ int rc;
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
- return smk_curacc(sbp->smk_floor, MAY_READ);
+ rc = smk_curacc(sbp->smk_floor, MAY_READ, &ad);
+ return rc;
}
/**
char *type, unsigned long flags, void *data)
{
struct superblock_smack *sbp = path->mnt->mnt_sb->s_security;
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path(&ad, *path);
- return smk_curacc(sbp->smk_floor, MAY_WRITE);
+ return smk_curacc(sbp->smk_floor, MAY_WRITE, &ad);
}
/**
static int smack_sb_umount(struct vfsmount *mnt, int flags)
{
struct superblock_smack *sbp;
+ struct smk_audit_info ad;
- sbp = mnt->mnt_sb->s_security;
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, mnt->mnt_mountpoint);
+ smk_ad_setfield_u_fs_path_mnt(&ad, mnt);
- return smk_curacc(sbp->smk_floor, MAY_WRITE);
+ sbp = mnt->mnt_sb->s_security;
+ return smk_curacc(sbp->smk_floor, MAY_WRITE, &ad);
}
/*
static int smack_inode_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *new_dentry)
{
- int rc;
char *isp;
+ struct smk_audit_info ad;
+ int rc;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, old_dentry);
isp = smk_of_inode(old_dentry->d_inode);
- rc = smk_curacc(isp, MAY_WRITE);
+ rc = smk_curacc(isp, MAY_WRITE, &ad);
if (rc == 0 && new_dentry->d_inode != NULL) {
isp = smk_of_inode(new_dentry->d_inode);
- rc = smk_curacc(isp, MAY_WRITE);
+ smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
+ rc = smk_curacc(isp, MAY_WRITE, &ad);
}
return rc;
static int smack_inode_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *ip = dentry->d_inode;
+ struct smk_audit_info ad;
int rc;
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
/*
* You need write access to the thing you're unlinking
*/
- rc = smk_curacc(smk_of_inode(ip), MAY_WRITE);
- if (rc == 0)
+ rc = smk_curacc(smk_of_inode(ip), MAY_WRITE, &ad);
+ if (rc == 0) {
/*
* You also need write access to the containing directory
*/
- rc = smk_curacc(smk_of_inode(dir), MAY_WRITE);
-
+ smk_ad_setfield_u_fs_path_dentry(&ad, NULL);
+ smk_ad_setfield_u_fs_inode(&ad, dir);
+ rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+ }
return rc;
}
*/
static int smack_inode_rmdir(struct inode *dir, struct dentry *dentry)
{
+ struct smk_audit_info ad;
int rc;
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
/*
* You need write access to the thing you're removing
*/
- rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
- if (rc == 0)
+ rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+ if (rc == 0) {
/*
* You also need write access to the containing directory
*/
- rc = smk_curacc(smk_of_inode(dir), MAY_WRITE);
+ smk_ad_setfield_u_fs_path_dentry(&ad, NULL);
+ smk_ad_setfield_u_fs_inode(&ad, dir);
+ rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+ }
return rc;
}
{
int rc;
char *isp;
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, old_dentry);
isp = smk_of_inode(old_dentry->d_inode);
- rc = smk_curacc(isp, MAY_READWRITE);
+ rc = smk_curacc(isp, MAY_READWRITE, &ad);
if (rc == 0 && new_dentry->d_inode != NULL) {
isp = smk_of_inode(new_dentry->d_inode);
- rc = smk_curacc(isp, MAY_READWRITE);
+ smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
+ rc = smk_curacc(isp, MAY_READWRITE, &ad);
}
-
return rc;
}
*/
static int smack_inode_permission(struct inode *inode, int mask)
{
+ struct smk_audit_info ad;
/*
* No permission to check. Existence test. Yup, it's there.
*/
if (mask == 0)
return 0;
-
- return smk_curacc(smk_of_inode(inode), mask);
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_inode(&ad, inode);
+ return smk_curacc(smk_of_inode(inode), mask, &ad);
}
/**
*/
static int smack_inode_setattr(struct dentry *dentry, struct iattr *iattr)
{
+ struct smk_audit_info ad;
/*
* Need to allow for clearing the setuid bit.
*/
if (iattr->ia_valid & ATTR_FORCE)
return 0;
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
- return smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
+ return smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
}
/**
*/
static int smack_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
{
- return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ);
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+ smk_ad_setfield_u_fs_path_mnt(&ad, mnt);
+ return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
}
/**
static int smack_inode_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
+ struct smk_audit_info ad;
int rc = 0;
if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
} else
rc = cap_inode_setxattr(dentry, name, value, size, flags);
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
if (rc == 0)
- rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
+ rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
return rc;
}
*/
static int smack_inode_getxattr(struct dentry *dentry, const char *name)
{
- return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ);
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+ return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
}
/*
*/
static int smack_inode_removexattr(struct dentry *dentry, const char *name)
{
+ struct smk_audit_info ad;
int rc = 0;
if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
} else
rc = cap_inode_removexattr(dentry, name);
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
if (rc == 0)
- rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
+ rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
return rc;
}
unsigned long arg)
{
int rc = 0;
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path(&ad, file->f_path);
if (_IOC_DIR(cmd) & _IOC_WRITE)
- rc = smk_curacc(file->f_security, MAY_WRITE);
+ rc = smk_curacc(file->f_security, MAY_WRITE, &ad);
if (rc == 0 && (_IOC_DIR(cmd) & _IOC_READ))
- rc = smk_curacc(file->f_security, MAY_READ);
+ rc = smk_curacc(file->f_security, MAY_READ, &ad);
return rc;
}
*/
static int smack_file_lock(struct file *file, unsigned int cmd)
{
- return smk_curacc(file->f_security, MAY_WRITE);
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path_dentry(&ad, file->f_path.dentry);
+ return smk_curacc(file->f_security, MAY_WRITE, &ad);
}
/**
static int smack_file_fcntl(struct file *file, unsigned int cmd,
unsigned long arg)
{
+ struct smk_audit_info ad;
int rc;
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+ smk_ad_setfield_u_fs_path(&ad, file->f_path);
+
switch (cmd) {
case F_DUPFD:
case F_GETFD:
case F_GETLK:
case F_GETOWN:
case F_GETSIG:
- rc = smk_curacc(file->f_security, MAY_READ);
+ rc = smk_curacc(file->f_security, MAY_READ, &ad);
break;
case F_SETFD:
case F_SETFL:
case F_SETLKW:
case F_SETOWN:
case F_SETSIG:
- rc = smk_curacc(file->f_security, MAY_WRITE);
+ rc = smk_curacc(file->f_security, MAY_WRITE, &ad);
break;
default:
- rc = smk_curacc(file->f_security, MAY_READWRITE);
+ rc = smk_curacc(file->f_security, MAY_READWRITE, &ad);
}
return rc;
{
struct file *file;
int rc;
+ char *tsp = tsk->cred->security;
+ struct smk_audit_info ad;
/*
* struct fown_struct is never outside the context of a struct file
*/
file = container_of(fown, struct file, f_owner);
- rc = smk_access(file->f_security, tsk->cred->security, MAY_WRITE);
+ /* we don't log here as rc can be overriden */
+ rc = smk_access(file->f_security, tsp, MAY_WRITE, NULL);
if (rc != 0 && has_capability(tsk, CAP_MAC_OVERRIDE))
- return 0;
+ rc = 0;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+ smk_ad_setfield_u_tsk(&ad, tsk);
+ smack_log(file->f_security, tsp, MAY_WRITE, rc, &ad);
return rc;
}
static int smack_file_receive(struct file *file)
{
int may = 0;
+ struct smk_audit_info ad;
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+ smk_ad_setfield_u_fs_path(&ad, file->f_path);
/*
* This code relies on bitmasks.
*/
if (file->f_mode & FMODE_WRITE)
may |= MAY_WRITE;
- return smk_curacc(file->f_security, may);
+ return smk_curacc(file->f_security, may, &ad);
}
/*
return 0;
}
+/**
+ * smk_curacc_on_task - helper to log task related access
+ * @p: the task object
+ * @access : the access requested
+ *
+ * Return 0 if access is permitted
+ */
+static int smk_curacc_on_task(struct task_struct *p, int access)
+{
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+ smk_ad_setfield_u_tsk(&ad, p);
+ return smk_curacc(task_security(p), access, &ad);
+}
+
/**
* smack_task_setpgid - Smack check on setting pgid
* @p: the task object
*/
static int smack_task_setpgid(struct task_struct *p, pid_t pgid)
{
- return smk_curacc(task_security(p), MAY_WRITE);
+ return smk_curacc_on_task(p, MAY_WRITE);
}
/**
*/
static int smack_task_getpgid(struct task_struct *p)
{
- return smk_curacc(task_security(p), MAY_READ);
+ return smk_curacc_on_task(p, MAY_READ);
}
/**
*/
static int smack_task_getsid(struct task_struct *p)
{
- return smk_curacc(task_security(p), MAY_READ);
+ return smk_curacc_on_task(p, MAY_READ);
}
/**
rc = cap_task_setnice(p, nice);
if (rc == 0)
- rc = smk_curacc(task_security(p), MAY_WRITE);
+ rc = smk_curacc_on_task(p, MAY_WRITE);
return rc;
}
rc = cap_task_setioprio(p, ioprio);
if (rc == 0)
- rc = smk_curacc(task_security(p), MAY_WRITE);
+ rc = smk_curacc_on_task(p, MAY_WRITE);
return rc;
}
*/
static int smack_task_getioprio(struct task_struct *p)
{
- return smk_curacc(task_security(p), MAY_READ);
+ return smk_curacc_on_task(p, MAY_READ);
}
/**
rc = cap_task_setscheduler(p, policy, lp);
if (rc == 0)
- rc = smk_curacc(task_security(p), MAY_WRITE);
+ rc = smk_curacc_on_task(p, MAY_WRITE);
return rc;
}
*/
static int smack_task_getscheduler(struct task_struct *p)
{
- return smk_curacc(task_security(p), MAY_READ);
+ return smk_curacc_on_task(p, MAY_READ);
}
/**
*/
static int smack_task_movememory(struct task_struct *p)
{
- return smk_curacc(task_security(p), MAY_WRITE);
+ return smk_curacc_on_task(p, MAY_WRITE);
}
/**
static int smack_task_kill(struct task_struct *p, struct siginfo *info,
int sig, u32 secid)
{
+ struct smk_audit_info ad;
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+ smk_ad_setfield_u_tsk(&ad, p);
/*
* Sending a signal requires that the sender
* can write the receiver.
*/
if (secid == 0)
- return smk_curacc(task_security(p), MAY_WRITE);
+ return smk_curacc(task_security(p), MAY_WRITE, &ad);
/*
* If the secid isn't 0 we're dealing with some USB IO
* specific behavior. This is not clean. For one thing
* we can't take privilege into account.
*/
- return smk_access(smack_from_secid(secid), task_security(p), MAY_WRITE);
+ return smk_access(smack_from_secid(secid), task_security(p),
+ MAY_WRITE, &ad);
}
/**
*/
static int smack_task_wait(struct task_struct *p)
{
+ struct smk_audit_info ad;
+ char *sp = current_security();
+ char *tsp = task_security(p);
int rc;
- rc = smk_access(current_security(), task_security(p), MAY_WRITE);
+ /* we don't log here, we can be overriden */
+ rc = smk_access(sp, tsp, MAY_WRITE, NULL);
if (rc == 0)
- return 0;
+ goto out_log;
/*
* Allow the operation to succeed if either task
* the smack value.
*/
if (capable(CAP_MAC_OVERRIDE) || has_capability(p, CAP_MAC_OVERRIDE))
- return 0;
-
+ rc = 0;
+ /* we log only if we didn't get overriden */
+ out_log:
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+ smk_ad_setfield_u_tsk(&ad, p);
+ smack_log(sp, tsp, MAY_WRITE, rc, &ad);
return rc;
}
int sk_lbl;
char *hostsp;
struct socket_smack *ssp = sk->sk_security;
+ struct smk_audit_info ad;
rcu_read_lock();
hostsp = smack_host_label(sap);
if (hostsp != NULL) {
sk_lbl = SMACK_UNLABELED_SOCKET;
- rc = smk_access(ssp->smk_out, hostsp, MAY_WRITE);
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+ ad.a.u.net.family = sap->sin_family;
+ ad.a.u.net.dport = sap->sin_port;
+ ad.a.u.net.v4info.daddr = sap->sin_addr.s_addr;
+#endif
+ rc = smk_access(ssp->smk_out, hostsp, MAY_WRITE, &ad);
} else {
sk_lbl = SMACK_CIPSO_SOCKET;
rc = 0;
isp->security = NULL;
}
+/**
+ * smk_curacc_shm : check if current has access on shm
+ * @shp : the object
+ * @access : access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smk_curacc_shm(struct shmid_kernel *shp, int access)
+{
+ char *ssp = smack_of_shm(shp);
+ struct smk_audit_info ad;
+
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+ ad.a.u.ipc_id = shp->shm_perm.id;
+#endif
+ return smk_curacc(ssp, access, &ad);
+}
+
/**
* smack_shm_associate - Smack access check for shm
* @shp: the object
*/
static int smack_shm_associate(struct shmid_kernel *shp, int shmflg)
{
- char *ssp = smack_of_shm(shp);
int may;
may = smack_flags_to_may(shmflg);
- return smk_curacc(ssp, may);
+ return smk_curacc_shm(shp, may);
}
/**
*/
static int smack_shm_shmctl(struct shmid_kernel *shp, int cmd)
{
- char *ssp;
int may;
switch (cmd) {
default:
return -EINVAL;
}
-
- ssp = smack_of_shm(shp);
- return smk_curacc(ssp, may);
+ return smk_curacc_shm(shp, may);
}
/**
static int smack_shm_shmat(struct shmid_kernel *shp, char __user *shmaddr,
int shmflg)
{
- char *ssp = smack_of_shm(shp);
int may;
may = smack_flags_to_may(shmflg);
- return smk_curacc(ssp, may);
+ return smk_curacc_shm(shp, may);
}
/**
isp->security = NULL;
}
+/**
+ * smk_curacc_sem : check if current has access on sem
+ * @sma : the object
+ * @access : access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smk_curacc_sem(struct sem_array *sma, int access)
+{
+ char *ssp = smack_of_sem(sma);
+ struct smk_audit_info ad;
+
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+ ad.a.u.ipc_id = sma->sem_perm.id;
+#endif
+ return smk_curacc(ssp, access, &ad);
+}
+
/**
* smack_sem_associate - Smack access check for sem
* @sma: the object
*/
static int smack_sem_associate(struct sem_array *sma, int semflg)
{
- char *ssp = smack_of_sem(sma);
int may;
may = smack_flags_to_may(semflg);
- return smk_curacc(ssp, may);
+ return smk_curacc_sem(sma, may);
}
/**
*/
static int smack_sem_semctl(struct sem_array *sma, int cmd)
{
- char *ssp;
int may;
switch (cmd) {
return -EINVAL;
}
- ssp = smack_of_sem(sma);
- return smk_curacc(ssp, may);
+ return smk_curacc_sem(sma, may);
}
/**
static int smack_sem_semop(struct sem_array *sma, struct sembuf *sops,
unsigned nsops, int alter)
{
- char *ssp = smack_of_sem(sma);
-
- return smk_curacc(ssp, MAY_READWRITE);
+ return smk_curacc_sem(sma, MAY_READWRITE);
}
/**
return (char *)msq->q_perm.security;
}
+/**
+ * smk_curacc_msq : helper to check if current has access on msq
+ * @msq : the msq
+ * @access : access requested
+ *
+ * return 0 if current has access, error otherwise
+ */
+static int smk_curacc_msq(struct msg_queue *msq, int access)
+{
+ char *msp = smack_of_msq(msq);
+ struct smk_audit_info ad;
+
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+ ad.a.u.ipc_id = msq->q_perm.id;
+#endif
+ return smk_curacc(msp, access, &ad);
+}
+
/**
* smack_msg_queue_associate - Smack access check for msg_queue
* @msq: the object
*/
static int smack_msg_queue_associate(struct msg_queue *msq, int msqflg)
{
- char *msp = smack_of_msq(msq);
int may;
may = smack_flags_to_may(msqflg);
- return smk_curacc(msp, may);
+ return smk_curacc_msq(msq, may);
}
/**
*/
static int smack_msg_queue_msgctl(struct msg_queue *msq, int cmd)
{
- char *msp;
int may;
switch (cmd) {
return -EINVAL;
}
- msp = smack_of_msq(msq);
- return smk_curacc(msp, may);
+ return smk_curacc_msq(msq, may);
}
/**
static int smack_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg,
int msqflg)
{
- char *msp = smack_of_msq(msq);
- int rc;
+ int may;
- rc = smack_flags_to_may(msqflg);
- return smk_curacc(msp, rc);
+ may = smack_flags_to_may(msqflg);
+ return smk_curacc_msq(msq, may);
}
/**
static int smack_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg,
struct task_struct *target, long type, int mode)
{
- char *msp = smack_of_msq(msq);
-
- return smk_curacc(msp, MAY_READWRITE);
+ return smk_curacc_msq(msq, MAY_READWRITE);
}
/**
static int smack_ipc_permission(struct kern_ipc_perm *ipp, short flag)
{
char *isp = ipp->security;
- int may;
+ int may = smack_flags_to_may(flag);
+ struct smk_audit_info ad;
- may = smack_flags_to_may(flag);
- return smk_curacc(isp, may);
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+ ad.a.u.ipc_id = ipp->id;
+#endif
+ return smk_curacc(isp, may, &ad);
}
/**
{
struct inode *sp = SOCK_INODE(sock);
struct inode *op = SOCK_INODE(other);
+ struct smk_audit_info ad;
- return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_READWRITE);
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+ smk_ad_setfield_u_net_sk(&ad, other->sk);
+ return smk_access(smk_of_inode(sp), smk_of_inode(op),
+ MAY_READWRITE, &ad);
}
/**
{
struct inode *sp = SOCK_INODE(sock);
struct inode *op = SOCK_INODE(other);
+ struct smk_audit_info ad;
- return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_WRITE);
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+ smk_ad_setfield_u_net_sk(&ad, other->sk);
+ return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_WRITE, &ad);
}
/**
char smack[SMK_LABELLEN];
char *csp;
int rc;
-
+ struct smk_audit_info ad;
if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
return 0;
netlbl_secattr_destroy(&secattr);
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+ ad.a.u.net.family = sk->sk_family;
+ ad.a.u.net.netif = skb->iif;
+ ipv4_skb_to_auditdata(skb, &ad.a, NULL);
+#endif
/*
* Receiving a packet requires that the other end
* be able to write here. Read access is not required.
* This is the simplist possible security model
* for networking.
*/
- rc = smk_access(csp, ssp->smk_in, MAY_WRITE);
+ rc = smk_access(csp, ssp->smk_in, MAY_WRITE, &ad);
if (rc != 0)
netlbl_skbuff_err(skb, rc, 0);
return rc;
struct iphdr *hdr;
char smack[SMK_LABELLEN];
int rc;
+ struct smk_audit_info ad;
/* handle mapped IPv4 packets arriving via IPv6 sockets */
if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
strncpy(smack, smack_known_huh.smk_known, SMK_MAXLEN);
netlbl_secattr_destroy(&secattr);
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+ ad.a.u.net.family = family;
+ ad.a.u.net.netif = skb->iif;
+ ipv4_skb_to_auditdata(skb, &ad.a, NULL);
+#endif
/*
* Receiving a packet requires that the other end be able to write
* here. Read access is not required.
*/
- rc = smk_access(smack, ssp->smk_in, MAY_WRITE);
+ rc = smk_access(smack, ssp->smk_in, MAY_WRITE, &ad);
if (rc != 0)
return rc;
const struct cred *cred, key_perm_t perm)
{
struct key *keyp;
+ struct smk_audit_info ad;
keyp = key_ref_to_ptr(key_ref);
if (keyp == NULL)
*/
if (cred->security == NULL)
return -EACCES;
-
- return smk_access(cred->security, keyp->security, MAY_READWRITE);
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_KEY);
+ ad.a.u.key_struct.key = keyp->serial;
+ ad.a.u.key_struct.key_desc = keyp->description;
+#endif
+ return smk_access(cred->security, keyp->security,
+ MAY_READWRITE, &ad);
}
#endif /* CONFIG_KEYS */
.ptrace_may_access = smack_ptrace_may_access,
.ptrace_traceme = smack_ptrace_traceme,
- .capget = cap_capget,
- .capset = cap_capset,
- .capable = cap_capable,
.syslog = smack_syslog,
- .settime = cap_settime,
- .vm_enough_memory = cap_vm_enough_memory,
-
- .bprm_set_creds = cap_bprm_set_creds,
- .bprm_secureexec = cap_bprm_secureexec,
.sb_alloc_security = smack_sb_alloc_security,
.sb_free_security = smack_sb_free_security,
.inode_post_setxattr = smack_inode_post_setxattr,
.inode_getxattr = smack_inode_getxattr,
.inode_removexattr = smack_inode_removexattr,
- .inode_need_killpriv = cap_inode_need_killpriv,
- .inode_killpriv = cap_inode_killpriv,
.inode_getsecurity = smack_inode_getsecurity,
.inode_setsecurity = smack_inode_setsecurity,
.inode_listsecurity = smack_inode_listsecurity,
.cred_commit = smack_cred_commit,
.kernel_act_as = smack_kernel_act_as,
.kernel_create_files_as = smack_kernel_create_files_as,
- .task_fix_setuid = cap_task_fix_setuid,
.task_setpgid = smack_task_setpgid,
.task_getpgid = smack_task_getpgid,
.task_getsid = smack_task_getsid,
.task_kill = smack_task_kill,
.task_wait = smack_task_wait,
.task_to_inode = smack_task_to_inode,
- .task_prctl = cap_task_prctl,
.ipc_permission = smack_ipc_permission,
.ipc_getsecid = smack_ipc_getsecid,
.sem_semctl = smack_sem_semctl,
.sem_semop = smack_sem_semop,
- .netlink_send = cap_netlink_send,
- .netlink_recv = cap_netlink_recv,
-
.d_instantiate = smack_d_instantiate,
.getprocattr = smack_getprocattr,
SMK_AMBIENT = 7, /* internet ambient label */
SMK_NETLBLADDR = 8, /* single label hosts */
SMK_ONLYCAP = 9, /* the only "capable" label */
+ SMK_LOGGING = 10, /* logging */
};
/*
return;
}
- m = list_entry(rcu_dereference(smk_netlbladdr_list.next),
- struct smk_netlbladdr, list);
+ m = list_entry_rcu(smk_netlbladdr_list.next,
+ struct smk_netlbladdr, list);
/* the comparison '>' is a bit hacky, but works */
if (new->smk_mask.s_addr > m->smk_mask.s_addr) {
list_add_rcu(&new->list, &m->list);
return;
}
- m_next = list_entry(rcu_dereference(m->list.next),
- struct smk_netlbladdr, list);
+ m_next = list_entry_rcu(m->list.next,
+ struct smk_netlbladdr, list);
if (new->smk_mask.s_addr > m_next->smk_mask.s_addr) {
list_add_rcu(&new->list, &m->list);
return;
struct sockaddr_in newname;
char smack[SMK_LABELLEN];
char *sp;
- char data[SMK_NETLBLADDRMAX];
+ char data[SMK_NETLBLADDRMAX + 1];
char *host = (char *)&newname.sin_addr.s_addr;
int rc;
struct netlbl_audit audit_info;
.write = smk_write_onlycap,
};
+/**
+ * smk_read_logging - read() for /smack/logging
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @cn: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_logging(struct file *filp, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ char temp[32];
+ ssize_t rc;
+
+ if (*ppos != 0)
+ return 0;
+
+ sprintf(temp, "%d\n", log_policy);
+ rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+ return rc;
+}
+
+/**
+ * smk_write_logging - write() for /smack/logging
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_logging(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ char temp[32];
+ int i;
+
+ if (!capable(CAP_MAC_ADMIN))
+ return -EPERM;
+
+ if (count >= sizeof(temp) || count == 0)
+ return -EINVAL;
+
+ if (copy_from_user(temp, buf, count) != 0)
+ return -EFAULT;
+
+ temp[count] = '\0';
+
+ if (sscanf(temp, "%d", &i) != 1)
+ return -EINVAL;
+ if (i < 0 || i > 3)
+ return -EINVAL;
+ log_policy = i;
+ return count;
+}
+
+
+
+static const struct file_operations smk_logging_ops = {
+ .read = smk_read_logging,
+ .write = smk_write_logging,
+};
/**
* smk_fill_super - fill the /smackfs superblock
* @sb: the empty superblock
{"netlabel", &smk_netlbladdr_ops, S_IRUGO|S_IWUSR},
[SMK_ONLYCAP] =
{"onlycap", &smk_onlycap_ops, S_IRUGO|S_IWUSR},
+ [SMK_LOGGING] =
+ {"logging", &smk_logging_ops, S_IRUGO|S_IWUSR},
/* last one */ {""}
};
"disabled", "enabled", "enabled", "enabled"
};
-/* Table for profile. */
+/*
+ * tomoyo_control_array is a static data which contains
+ *
+ * (1) functionality name used by /sys/kernel/security/tomoyo/profile .
+ * (2) initial values for "struct tomoyo_profile".
+ * (3) max values for "struct tomoyo_profile".
+ */
static struct {
const char *keyword;
unsigned int current_value;
[TOMOYO_VERBOSE] = { "TOMOYO_VERBOSE", 1, 1 },
};
-/* Profile table. Memory is allocated as needed. */
+/*
+ * tomoyo_profile is a structure which is used for holding the mode of access
+ * controls. TOMOYO has 4 modes: disabled, learning, permissive, enforcing.
+ * An administrator can define up to 256 profiles.
+ * The ->profile of "struct tomoyo_domain_info" is used for remembering
+ * the profile's number (0 - 255) assigned to that domain.
+ */
static struct tomoyo_profile {
unsigned int value[TOMOYO_MAX_CONTROL_INDEX];
const struct tomoyo_path_info *comment;
const char *name = ptr->name;
const int len = strlen(name);
- ptr->total_len = len;
ptr->const_len = tomoyo_const_part_length(name);
ptr->is_dir = len && (name[len - 1] == '/');
ptr->is_patterned = (ptr->const_len < len);
if (profile >= TOMOYO_MAX_PROFILES)
return NULL;
- /***** EXCLUSIVE SECTION START *****/
mutex_lock(&lock);
ptr = tomoyo_profile_ptr[profile];
if (ptr)
tomoyo_profile_ptr[profile] = ptr;
ok:
mutex_unlock(&lock);
- /***** EXCLUSIVE SECTION END *****/
return ptr;
}
return 0;
}
-/* Structure for policy manager. */
+/*
+ * tomoyo_policy_manager_entry is a structure which is used for holding list of
+ * domainnames or programs which are permitted to modify configuration via
+ * /sys/kernel/security/tomoyo/ interface.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_policy_manager_list .
+ * (2) "manager" is a domainname or a program's pathname.
+ * (3) "is_domain" is a bool which is true if "manager" is a domainname, false
+ * otherwise.
+ * (4) "is_deleted" is a bool which is true if marked as deleted, false
+ * otherwise.
+ */
struct tomoyo_policy_manager_entry {
struct list_head list;
/* A path to program or a domainname. */
bool is_deleted; /* True if this entry is deleted. */
};
-/* The list for "struct tomoyo_policy_manager_entry". */
+/*
+ * tomoyo_policy_manager_list is used for holding list of domainnames or
+ * programs which are permitted to modify configuration via
+ * /sys/kernel/security/tomoyo/ interface.
+ *
+ * An entry is added by
+ *
+ * # echo '<kernel> /sbin/mingetty /bin/login /bin/bash' > \
+ * /sys/kernel/security/tomoyo/manager
+ * (if you want to specify by a domainname)
+ *
+ * or
+ *
+ * # echo '/usr/lib/ccs/editpolicy' > /sys/kernel/security/tomoyo/manager
+ * (if you want to specify by a program's location)
+ *
+ * and is deleted by
+ *
+ * # echo 'delete <kernel> /sbin/mingetty /bin/login /bin/bash' > \
+ * /sys/kernel/security/tomoyo/manager
+ *
+ * or
+ *
+ * # echo 'delete /usr/lib/ccs/editpolicy' > \
+ * /sys/kernel/security/tomoyo/manager
+ *
+ * and all entries are retrieved by
+ *
+ * # cat /sys/kernel/security/tomoyo/manager
+ */
static LIST_HEAD(tomoyo_policy_manager_list);
static DECLARE_RWSEM(tomoyo_policy_manager_list_lock);
saved_manager = tomoyo_save_name(manager);
if (!saved_manager)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_policy_manager_list_lock);
list_for_each_entry(ptr, &tomoyo_policy_manager_list, list) {
if (ptr->manager != saved_manager)
error = 0;
out:
up_write(&tomoyo_policy_manager_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
list);
if (ptr->is_deleted)
continue;
- if (!tomoyo_io_printf(head, "%s\n", ptr->manager->name)) {
- done = false;
+ done = tomoyo_io_printf(head, "%s\n", ptr->manager->name);
+ if (!done)
break;
- }
}
up_read(&tomoyo_policy_manager_list_lock);
head->read_eof = done;
if (sscanf(data, "pid=%u", &pid) == 1) {
struct task_struct *p;
- /***** CRITICAL SECTION START *****/
read_lock(&tasklist_lock);
p = find_task_by_vpid(pid);
if (p)
domain = tomoyo_real_domain(p);
read_unlock(&tasklist_lock);
- /***** CRITICAL SECTION END *****/
} else if (!strncmp(data, "domain=", 7)) {
if (tomoyo_is_domain_def(data + 7)) {
down_read(&tomoyo_domain_list_lock);
TOMOYO_DOMAIN_FLAGS_IGNORE_GLOBAL_ALLOW_READ)
ignore_global_allow_read
= TOMOYO_KEYWORD_IGNORE_GLOBAL_ALLOW_READ "\n";
- if (!tomoyo_io_printf(head,
- "%s\n" TOMOYO_KEYWORD_USE_PROFILE "%u\n"
- "%s%s%s\n", domain->domainname->name,
- domain->profile, quota_exceeded,
- transition_failed,
- ignore_global_allow_read)) {
- done = false;
+ done = tomoyo_io_printf(head, "%s\n" TOMOYO_KEYWORD_USE_PROFILE
+ "%u\n%s%s%s\n",
+ domain->domainname->name,
+ domain->profile, quota_exceeded,
+ transition_failed,
+ ignore_global_allow_read);
+ if (!done)
break;
- }
head->read_step = 2;
acl_loop:
if (head->read_step == 3)
/* Print ACL entries in the domain. */
down_read(&tomoyo_domain_acl_info_list_lock);
list_for_each_cookie(apos, head->read_var2,
- &domain->acl_info_list) {
+ &domain->acl_info_list) {
struct tomoyo_acl_info *ptr
= list_entry(apos, struct tomoyo_acl_info,
- list);
- if (!tomoyo_print_entry(head, ptr)) {
- done = false;
+ list);
+ done = tomoyo_print_entry(head, ptr);
+ if (!done)
break;
- }
}
up_read(&tomoyo_domain_acl_info_list_lock);
if (!done)
break;
head->read_step = 3;
tail_mark:
- if (!tomoyo_io_printf(head, "\n")) {
- done = false;
+ done = tomoyo_io_printf(head, "\n");
+ if (!done)
break;
- }
head->read_step = 1;
if (head->read_single_domain)
break;
domain = list_entry(pos, struct tomoyo_domain_info, list);
if (domain->is_deleted)
continue;
- if (!tomoyo_io_printf(head, "%u %s\n", domain->profile,
- domain->domainname->name)) {
- done = false;
+ done = tomoyo_io_printf(head, "%u %s\n", domain->profile,
+ domain->domainname->name);
+ if (!done)
break;
- }
}
up_read(&tomoyo_domain_list_lock);
head->read_eof = done;
const int pid = head->read_step;
struct task_struct *p;
struct tomoyo_domain_info *domain = NULL;
- /***** CRITICAL SECTION START *****/
read_lock(&tasklist_lock);
p = find_task_by_vpid(pid);
if (p)
domain = tomoyo_real_domain(p);
read_unlock(&tasklist_lock);
- /***** CRITICAL SECTION END *****/
if (domain)
tomoyo_io_printf(head, "%d %u %s", pid, domain->profile,
domain->domainname->name);
return tomoyo_write_control(file, buf, count);
}
-/* Operations for /sys/kernel/security/tomoyo/ interface. */
+/*
+ * tomoyo_operations is a "struct file_operations" which is used for handling
+ * /sys/kernel/security/tomoyo/ interface.
+ *
+ * Some files under /sys/kernel/security/tomoyo/ directory accept open(O_RDWR).
+ * See tomoyo_io_buffer for internals.
+ */
static const struct file_operations tomoyo_operations = {
.open = tomoyo_open,
.release = tomoyo_release,
struct dentry;
struct vfsmount;
-/* Temporary buffer for holding pathnames. */
+/*
+ * tomoyo_page_buffer is a structure which is used for holding a pathname
+ * obtained from "struct dentry" and "struct vfsmount" pair.
+ * As of now, it is 4096 bytes. If users complain that 4096 bytes is too small
+ * (because TOMOYO escapes non ASCII printable characters using \ooo format),
+ * we will make the buffer larger.
+ */
struct tomoyo_page_buffer {
char buffer[4096];
};
-/* Structure for holding a token. */
+/*
+ * tomoyo_path_info is a structure which is used for holding a string data
+ * used by TOMOYO.
+ * This structure has several fields for supporting pattern matching.
+ *
+ * (1) "name" is the '\0' terminated string data.
+ * (2) "hash" is full_name_hash(name, strlen(name)).
+ * This allows tomoyo_pathcmp() to compare by hash before actually compare
+ * using strcmp().
+ * (3) "const_len" is the length of the initial segment of "name" which
+ * consists entirely of non wildcard characters. In other words, the length
+ * which we can compare two strings using strncmp().
+ * (4) "is_dir" is a bool which is true if "name" ends with "/",
+ * false otherwise.
+ * TOMOYO distinguishes directory and non-directory. A directory ends with
+ * "/" and non-directory does not end with "/".
+ * (5) "is_patterned" is a bool which is true if "name" contains wildcard
+ * characters, false otherwise. This allows TOMOYO to use "hash" and
+ * strcmp() for string comparison if "is_patterned" is false.
+ * (6) "depth" is calculated using the number of "/" characters in "name".
+ * This allows TOMOYO to avoid comparing two pathnames which never match
+ * (e.g. whether "/var/www/html/index.html" matches "/tmp/sh-thd-\$").
+ */
struct tomoyo_path_info {
const char *name;
u32 hash; /* = full_name_hash(name, strlen(name)) */
- u16 total_len; /* = strlen(name) */
u16 const_len; /* = tomoyo_const_part_length(name) */
bool is_dir; /* = tomoyo_strendswith(name, "/") */
bool is_patterned; /* = tomoyo_path_contains_pattern(name) */
*/
#define TOMOYO_MAX_PATHNAME_LEN 4000
-/* Structure for holding requested pathname. */
+/*
+ * tomoyo_path_info_with_data is a structure which is used for holding a
+ * pathname obtained from "struct dentry" and "struct vfsmount" pair.
+ *
+ * "struct tomoyo_path_info_with_data" consists of "struct tomoyo_path_info"
+ * and buffer for the pathname, while "struct tomoyo_page_buffer" consists of
+ * buffer for the pathname only.
+ *
+ * "struct tomoyo_path_info_with_data" is intended to allow TOMOYO to release
+ * both "struct tomoyo_path_info" and buffer for the pathname by single kfree()
+ * so that we don't need to return two pointers to the caller. If the caller
+ * puts "struct tomoyo_path_info" on stack memory, we will be able to remove
+ * "struct tomoyo_path_info_with_data".
+ */
struct tomoyo_path_info_with_data {
/* Keep "head" first, for this pointer is passed to tomoyo_free(). */
struct tomoyo_path_info head;
};
/*
- * Common header for holding ACL entries.
+ * tomoyo_acl_info is a structure which is used for holding
+ *
+ * (1) "list" which is linked to the ->acl_info_list of
+ * "struct tomoyo_domain_info"
+ * (2) "type" which tells
+ * (a) type & 0x7F : type of the entry (either
+ * "struct tomoyo_single_path_acl_record" or
+ * "struct tomoyo_double_path_acl_record")
+ * (b) type & 0x80 : whether the entry is marked as "deleted".
*
* Packing "struct tomoyo_acl_info" allows
* "struct tomoyo_single_path_acl_record" to embed "u16" and
/* This ACL entry is deleted. */
#define TOMOYO_ACL_DELETED 0x80
-/* Structure for domain information. */
+/*
+ * tomoyo_domain_info is a structure which is used for holding permissions
+ * (e.g. "allow_read /lib/libc-2.5.so") given to each domain.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_domain_list .
+ * (2) "acl_info_list" which is linked to "struct tomoyo_acl_info".
+ * (3) "domainname" which holds the name of the domain.
+ * (4) "profile" which remembers profile number assigned to this domain.
+ * (5) "is_deleted" is a bool which is true if this domain is marked as
+ * "deleted", false otherwise.
+ * (6) "quota_warned" is a bool which is used for suppressing warning message
+ * when learning mode learned too much entries.
+ * (7) "flags" which remembers this domain's attributes.
+ *
+ * A domain's lifecycle is an analogy of files on / directory.
+ * Multiple domains with the same domainname cannot be created (as with
+ * creating files with the same filename fails with -EEXIST).
+ * If a process reached a domain, that process can reside in that domain after
+ * that domain is marked as "deleted" (as with a process can access an already
+ * open()ed file after that file was unlink()ed).
+ */
struct tomoyo_domain_info {
struct list_head list;
struct list_head acl_info_list;
#define TOMOYO_DOMAIN_FLAGS_TRANSITION_FAILED 2
/*
- * Structure for "allow_read/write", "allow_execute", "allow_read",
- * "allow_write", "allow_create", "allow_unlink", "allow_mkdir", "allow_rmdir",
- * "allow_mkfifo", "allow_mksock", "allow_mkblock", "allow_mkchar",
- * "allow_truncate", "allow_symlink" and "allow_rewrite" directive.
+ * tomoyo_single_path_acl_record is a structure which is used for holding an
+ * entry with one pathname operation (e.g. open(), mkdir()).
+ * It has following fields.
+ *
+ * (1) "head" which is a "struct tomoyo_acl_info".
+ * (2) "perm" which is a bitmask of permitted operations.
+ * (3) "filename" is the pathname.
+ *
+ * Directives held by this structure are "allow_read/write", "allow_execute",
+ * "allow_read", "allow_write", "allow_create", "allow_unlink", "allow_mkdir",
+ * "allow_rmdir", "allow_mkfifo", "allow_mksock", "allow_mkblock",
+ * "allow_mkchar", "allow_truncate", "allow_symlink" and "allow_rewrite".
*/
struct tomoyo_single_path_acl_record {
struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_SINGLE_PATH_ACL */
const struct tomoyo_path_info *filename;
};
-/* Structure for "allow_rename" and "allow_link" directive. */
+/*
+ * tomoyo_double_path_acl_record is a structure which is used for holding an
+ * entry with two pathnames operation (i.e. link() and rename()).
+ * It has following fields.
+ *
+ * (1) "head" which is a "struct tomoyo_acl_info".
+ * (2) "perm" which is a bitmask of permitted operations.
+ * (3) "filename1" is the source/old pathname.
+ * (4) "filename2" is the destination/new pathname.
+ *
+ * Directives held by this structure are "allow_rename" and "allow_link".
+ */
struct tomoyo_double_path_acl_record {
struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_DOUBLE_PATH_ACL */
u8 perm;
#define TOMOYO_VERBOSE 2
#define TOMOYO_MAX_CONTROL_INDEX 3
-/* Structure for reading/writing policy via securityfs interfaces. */
+/*
+ * tomoyo_io_buffer is a structure which is used for reading and modifying
+ * configuration via /sys/kernel/security/tomoyo/ interface.
+ * It has many fields. ->read_var1 , ->read_var2 , ->write_var1 are used as
+ * cursors.
+ *
+ * Since the content of /sys/kernel/security/tomoyo/domain_policy is a list of
+ * "struct tomoyo_domain_info" entries and each "struct tomoyo_domain_info"
+ * entry has a list of "struct tomoyo_acl_info", we need two cursors when
+ * reading (one is for traversing tomoyo_domain_list and the other is for
+ * traversing "struct tomoyo_acl_info"->acl_info_list ).
+ *
+ * If a line written to /sys/kernel/security/tomoyo/domain_policy starts with
+ * "select ", TOMOYO seeks the cursor ->read_var1 and ->write_var1 to the
+ * domain with the domainname specified by the rest of that line (NULL is set
+ * if seek failed).
+ * If a line written to /sys/kernel/security/tomoyo/domain_policy starts with
+ * "delete ", TOMOYO deletes an entry or a domain specified by the rest of that
+ * line (->write_var1 is set to NULL if a domain was deleted).
+ * If a line written to /sys/kernel/security/tomoyo/domain_policy starts with
+ * neither "select " nor "delete ", an entry or a domain specified by that line
+ * is appended.
+ */
struct tomoyo_io_buffer {
int (*read) (struct tomoyo_io_buffer *);
int (*write) (struct tomoyo_io_buffer *);
/* The initial domain. */
struct tomoyo_domain_info tomoyo_kernel_domain;
-/* The list for "struct tomoyo_domain_info". */
+/*
+ * tomoyo_domain_list is used for holding list of domains.
+ * The ->acl_info_list of "struct tomoyo_domain_info" is used for holding
+ * permissions (e.g. "allow_read /lib/libc-2.5.so") given to each domain.
+ *
+ * An entry is added by
+ *
+ * # ( echo "<kernel>"; echo "allow_execute /sbin/init" ) > \
+ * /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and is deleted by
+ *
+ * # ( echo "<kernel>"; echo "delete allow_execute /sbin/init" ) > \
+ * /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # cat /sys/kernel/security/tomoyo/domain_policy
+ *
+ * A domain is added by
+ *
+ * # echo "<kernel>" > /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and is deleted by
+ *
+ * # echo "delete <kernel>" > /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and all domains are retrieved by
+ *
+ * # grep '^<kernel>' /sys/kernel/security/tomoyo/domain_policy
+ *
+ * Normally, a domainname is monotonically getting longer because a domainname
+ * which the process will belong to if an execve() operation succeeds is
+ * defined as a concatenation of "current domainname" + "pathname passed to
+ * execve()".
+ * See tomoyo_domain_initializer_list and tomoyo_domain_keeper_list for
+ * exceptions.
+ */
LIST_HEAD(tomoyo_domain_list);
DECLARE_RWSEM(tomoyo_domain_list_lock);
-/* Structure for "initialize_domain" and "no_initialize_domain" keyword. */
+/*
+ * tomoyo_domain_initializer_entry is a structure which is used for holding
+ * "initialize_domain" and "no_initialize_domain" entries.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_domain_initializer_list .
+ * (2) "domainname" which is "a domainname" or "the last component of a
+ * domainname". This field is NULL if "from" clause is not specified.
+ * (3) "program" which is a program's pathname.
+ * (4) "is_deleted" is a bool which is true if marked as deleted, false
+ * otherwise.
+ * (5) "is_not" is a bool which is true if "no_initialize_domain", false
+ * otherwise.
+ * (6) "is_last_name" is a bool which is true if "domainname" is "the last
+ * component of a domainname", false otherwise.
+ */
struct tomoyo_domain_initializer_entry {
struct list_head list;
const struct tomoyo_path_info *domainname; /* This may be NULL */
bool is_last_name;
};
-/* Structure for "keep_domain" and "no_keep_domain" keyword. */
+/*
+ * tomoyo_domain_keeper_entry is a structure which is used for holding
+ * "keep_domain" and "no_keep_domain" entries.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_domain_keeper_list .
+ * (2) "domainname" which is "a domainname" or "the last component of a
+ * domainname".
+ * (3) "program" which is a program's pathname.
+ * This field is NULL if "from" clause is not specified.
+ * (4) "is_deleted" is a bool which is true if marked as deleted, false
+ * otherwise.
+ * (5) "is_not" is a bool which is true if "no_initialize_domain", false
+ * otherwise.
+ * (6) "is_last_name" is a bool which is true if "domainname" is "the last
+ * component of a domainname", false otherwise.
+ */
struct tomoyo_domain_keeper_entry {
struct list_head list;
const struct tomoyo_path_info *domainname;
bool is_last_name;
};
-/* Structure for "alias" keyword. */
+/*
+ * tomoyo_alias_entry is a structure which is used for holding "alias" entries.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_alias_list .
+ * (2) "original_name" which is a dereferenced pathname.
+ * (3) "aliased_name" which is a symlink's pathname.
+ * (4) "is_deleted" is a bool which is true if marked as deleted, false
+ * otherwise.
+ */
struct tomoyo_alias_entry {
struct list_head list;
const struct tomoyo_path_info *original_name;
{
/* We need to serialize because this is bitfield operation. */
static DEFINE_SPINLOCK(lock);
- /***** CRITICAL SECTION START *****/
spin_lock(&lock);
if (!is_delete)
domain->flags |= flags;
else
domain->flags &= ~flags;
spin_unlock(&lock);
- /***** CRITICAL SECTION END *****/
}
/**
return cp0;
}
-/* The list for "struct tomoyo_domain_initializer_entry". */
+/*
+ * tomoyo_domain_initializer_list is used for holding list of programs which
+ * triggers reinitialization of domainname. Normally, a domainname is
+ * monotonically getting longer. But sometimes, we restart daemon programs.
+ * It would be convenient for us that "a daemon started upon system boot" and
+ * "the daemon restarted from console" belong to the same domain. Thus, TOMOYO
+ * provides a way to shorten domainnames.
+ *
+ * An entry is added by
+ *
+ * # echo 'initialize_domain /usr/sbin/httpd' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete initialize_domain /usr/sbin/httpd' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^initialize_domain /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, /usr/sbin/httpd will belong to
+ * "<kernel> /usr/sbin/httpd" domain.
+ *
+ * You may specify a domainname using "from" keyword.
+ * "initialize_domain /usr/sbin/httpd from <kernel> /etc/rc.d/init.d/httpd"
+ * will cause "/usr/sbin/httpd" executed from "<kernel> /etc/rc.d/init.d/httpd"
+ * domain to belong to "<kernel> /usr/sbin/httpd" domain.
+ *
+ * You may add "no_" prefix to "initialize_domain".
+ * "initialize_domain /usr/sbin/httpd" and
+ * "no_initialize_domain /usr/sbin/httpd from <kernel> /etc/rc.d/init.d/httpd"
+ * will cause "/usr/sbin/httpd" to belong to "<kernel> /usr/sbin/httpd" domain
+ * unless executed from "<kernel> /etc/rc.d/init.d/httpd" domain.
+ */
static LIST_HEAD(tomoyo_domain_initializer_list);
static DECLARE_RWSEM(tomoyo_domain_initializer_list_lock);
saved_program = tomoyo_save_name(program);
if (!saved_program)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_domain_initializer_list_lock);
list_for_each_entry(ptr, &tomoyo_domain_initializer_list, list) {
if (ptr->is_not != is_not ||
error = 0;
out:
up_write(&tomoyo_domain_initializer_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
from = " from ";
domain = ptr->domainname->name;
}
- if (!tomoyo_io_printf(head,
- "%s" TOMOYO_KEYWORD_INITIALIZE_DOMAIN
- "%s%s%s\n", no, ptr->program->name, from,
- domain)) {
- done = false;
+ done = tomoyo_io_printf(head,
+ "%s" TOMOYO_KEYWORD_INITIALIZE_DOMAIN
+ "%s%s%s\n", no, ptr->program->name,
+ from, domain);
+ if (!done)
break;
- }
}
up_read(&tomoyo_domain_initializer_list_lock);
return done;
return flag;
}
-/* The list for "struct tomoyo_domain_keeper_entry". */
+/*
+ * tomoyo_domain_keeper_list is used for holding list of domainnames which
+ * suppresses domain transition. Normally, a domainname is monotonically
+ * getting longer. But sometimes, we want to suppress domain transition.
+ * It would be convenient for us that programs executed from a login session
+ * belong to the same domain. Thus, TOMOYO provides a way to suppress domain
+ * transition.
+ *
+ * An entry is added by
+ *
+ * # echo 'keep_domain <kernel> /usr/sbin/sshd /bin/bash' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete keep_domain <kernel> /usr/sbin/sshd /bin/bash' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^keep_domain /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, any process which belongs to
+ * "<kernel> /usr/sbin/sshd /bin/bash" domain will remain in that domain,
+ * unless explicitly specified by "initialize_domain" or "no_keep_domain".
+ *
+ * You may specify a program using "from" keyword.
+ * "keep_domain /bin/pwd from <kernel> /usr/sbin/sshd /bin/bash"
+ * will cause "/bin/pwd" executed from "<kernel> /usr/sbin/sshd /bin/bash"
+ * domain to remain in "<kernel> /usr/sbin/sshd /bin/bash" domain.
+ *
+ * You may add "no_" prefix to "keep_domain".
+ * "keep_domain <kernel> /usr/sbin/sshd /bin/bash" and
+ * "no_keep_domain /usr/bin/passwd from <kernel> /usr/sbin/sshd /bin/bash" will
+ * cause "/usr/bin/passwd" to belong to
+ * "<kernel> /usr/sbin/sshd /bin/bash /usr/bin/passwd" domain, unless
+ * explicitly specified by "initialize_domain".
+ */
static LIST_HEAD(tomoyo_domain_keeper_list);
static DECLARE_RWSEM(tomoyo_domain_keeper_list_lock);
struct tomoyo_domain_keeper_entry *ptr;
const struct tomoyo_path_info *saved_domainname;
const struct tomoyo_path_info *saved_program = NULL;
- static DEFINE_MUTEX(lock);
int error = -ENOMEM;
bool is_last_name = false;
saved_domainname = tomoyo_save_name(domainname);
if (!saved_domainname)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_domain_keeper_list_lock);
list_for_each_entry(ptr, &tomoyo_domain_keeper_list, list) {
if (ptr->is_not != is_not ||
error = 0;
out:
up_write(&tomoyo_domain_keeper_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
from = " from ";
program = ptr->program->name;
}
- if (!tomoyo_io_printf(head,
- "%s" TOMOYO_KEYWORD_KEEP_DOMAIN
- "%s%s%s\n", no, program, from,
- ptr->domainname->name)) {
- done = false;
+ done = tomoyo_io_printf(head,
+ "%s" TOMOYO_KEYWORD_KEEP_DOMAIN
+ "%s%s%s\n", no, program, from,
+ ptr->domainname->name);
+ if (!done)
break;
- }
}
up_read(&tomoyo_domain_keeper_list_lock);
return done;
return flag;
}
-/* The list for "struct tomoyo_alias_entry". */
+/*
+ * tomoyo_alias_list is used for holding list of symlink's pathnames which are
+ * allowed to be passed to an execve() request. Normally, the domainname which
+ * the current process will belong to after execve() succeeds is calculated
+ * using dereferenced pathnames. But some programs behave differently depending
+ * on the name passed to argv[0]. For busybox, calculating domainname using
+ * dereferenced pathnames will cause all programs in the busybox to belong to
+ * the same domain. Thus, TOMOYO provides a way to allow use of symlink's
+ * pathname for checking execve()'s permission and calculating domainname which
+ * the current process will belong to after execve() succeeds.
+ *
+ * An entry is added by
+ *
+ * # echo 'alias /bin/busybox /bin/cat' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete alias /bin/busybox /bin/cat' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^alias /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, if /bin/cat is a symlink to /bin/busybox and execution
+ * of /bin/cat is requested, permission is checked for /bin/cat rather than
+ * /bin/busybox and domainname which the current process will belong to after
+ * execve() succeeds is calculated using /bin/cat rather than /bin/busybox .
+ */
static LIST_HEAD(tomoyo_alias_list);
static DECLARE_RWSEM(tomoyo_alias_list_lock);
saved_aliased_name = tomoyo_save_name(aliased_name);
if (!saved_original_name || !saved_aliased_name)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_alias_list_lock);
list_for_each_entry(ptr, &tomoyo_alias_list, list) {
if (ptr->original_name != saved_original_name ||
error = 0;
out:
up_write(&tomoyo_alias_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
ptr = list_entry(pos, struct tomoyo_alias_entry, list);
if (ptr->is_deleted)
continue;
- if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_ALIAS "%s %s\n",
- ptr->original_name->name,
- ptr->aliased_name->name)) {
- done = false;
+ done = tomoyo_io_printf(head, TOMOYO_KEYWORD_ALIAS "%s %s\n",
+ ptr->original_name->name,
+ ptr->aliased_name->name);
+ if (!done)
break;
- }
}
up_read(&tomoyo_alias_list_lock);
return done;
name.name = domainname;
tomoyo_fill_path_info(&name);
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_domain_list_lock);
/* Is there an active domain? */
list_for_each_entry(domain, &tomoyo_domain_list, list) {
break;
}
up_write(&tomoyo_domain_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return 0;
}
struct tomoyo_domain_info *domain = NULL;
const struct tomoyo_path_info *saved_domainname;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_domain_list_lock);
domain = tomoyo_find_domain(domainname);
if (domain)
domain->domainname != saved_domainname)
continue;
flag = false;
- /***** CRITICAL SECTION START *****/
read_lock(&tasklist_lock);
for_each_process(p) {
if (tomoyo_real_domain(p) != domain)
break;
}
read_unlock(&tasklist_lock);
- /***** CRITICAL SECTION END *****/
if (flag)
continue;
list_for_each_entry(ptr, &domain->acl_info_list, list) {
}
out:
up_write(&tomoyo_domain_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return domain;
}
}
/* Check execute permission. */
- retval = tomoyo_check_exec_perm(old_domain, &r, tmp);
+ retval = tomoyo_check_exec_perm(old_domain, &r);
if (retval < 0)
goto out;
#include "realpath.h"
#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
-/* Structure for "allow_read" keyword. */
+/*
+ * tomoyo_globally_readable_file_entry is a structure which is used for holding
+ * "allow_read" entries.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_globally_readable_list .
+ * (2) "filename" is a pathname which is allowed to open(O_RDONLY).
+ * (3) "is_deleted" is a bool which is true if marked as deleted, false
+ * otherwise.
+ */
struct tomoyo_globally_readable_file_entry {
struct list_head list;
const struct tomoyo_path_info *filename;
bool is_deleted;
};
-/* Structure for "file_pattern" keyword. */
+/*
+ * tomoyo_pattern_entry is a structure which is used for holding
+ * "tomoyo_pattern_list" entries.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_pattern_list .
+ * (2) "pattern" is a pathname pattern which is used for converting pathnames
+ * to pathname patterns during learning mode.
+ * (3) "is_deleted" is a bool which is true if marked as deleted, false
+ * otherwise.
+ */
struct tomoyo_pattern_entry {
struct list_head list;
const struct tomoyo_path_info *pattern;
bool is_deleted;
};
-/* Structure for "deny_rewrite" keyword. */
+/*
+ * tomoyo_no_rewrite_entry is a structure which is used for holding
+ * "deny_rewrite" entries.
+ * It has following fields.
+ *
+ * (1) "list" which is linked to tomoyo_no_rewrite_list .
+ * (2) "pattern" is a pathname which is by default not permitted to modify
+ * already existing content.
+ * (3) "is_deleted" is a bool which is true if marked as deleted, false
+ * otherwise.
+ */
struct tomoyo_no_rewrite_entry {
struct list_head list;
const struct tomoyo_path_info *pattern;
struct tomoyo_domain_info *
const domain, const bool is_delete);
-/* The list for "struct tomoyo_globally_readable_file_entry". */
+/*
+ * tomoyo_globally_readable_list is used for holding list of pathnames which
+ * are by default allowed to be open()ed for reading by any process.
+ *
+ * An entry is added by
+ *
+ * # echo 'allow_read /lib/libc-2.5.so' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete allow_read /lib/libc-2.5.so' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^allow_read /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, any process is allowed to
+ * open("/lib/libc-2.5.so", O_RDONLY).
+ * One exception is, if the domain which current process belongs to is marked
+ * as "ignore_global_allow_read", current process can't do so unless explicitly
+ * given "allow_read /lib/libc-2.5.so" to the domain which current process
+ * belongs to.
+ */
static LIST_HEAD(tomoyo_globally_readable_list);
static DECLARE_RWSEM(tomoyo_globally_readable_list_lock);
saved_filename = tomoyo_save_name(filename);
if (!saved_filename)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_globally_readable_list_lock);
list_for_each_entry(ptr, &tomoyo_globally_readable_list, list) {
if (ptr->filename != saved_filename)
error = 0;
out:
up_write(&tomoyo_globally_readable_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
list);
if (ptr->is_deleted)
continue;
- if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_ALLOW_READ "%s\n",
- ptr->filename->name)) {
- done = false;
+ done = tomoyo_io_printf(head, TOMOYO_KEYWORD_ALLOW_READ "%s\n",
+ ptr->filename->name);
+ if (!done)
break;
- }
}
up_read(&tomoyo_globally_readable_list_lock);
return done;
}
-/* The list for "struct tomoyo_pattern_entry". */
+/* tomoyo_pattern_list is used for holding list of pathnames which are used for
+ * converting pathnames to pathname patterns during learning mode.
+ *
+ * An entry is added by
+ *
+ * # echo 'file_pattern /proc/\$/mounts' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete file_pattern /proc/\$/mounts' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^file_pattern /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, if a process which belongs to a domain which is in
+ * learning mode requested open("/proc/1/mounts", O_RDONLY),
+ * "allow_read /proc/\$/mounts" is automatically added to the domain which that
+ * process belongs to.
+ *
+ * It is not a desirable behavior that we have to use /proc/\$/ instead of
+ * /proc/self/ when current process needs to access only current process's
+ * information. As of now, LSM version of TOMOYO is using __d_path() for
+ * calculating pathname. Non LSM version of TOMOYO is using its own function
+ * which pretends as if /proc/self/ is not a symlink; so that we can forbid
+ * current process from accessing other process's information.
+ */
static LIST_HEAD(tomoyo_pattern_list);
static DECLARE_RWSEM(tomoyo_pattern_list_lock);
saved_pattern = tomoyo_save_name(pattern);
if (!saved_pattern)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_pattern_list_lock);
list_for_each_entry(ptr, &tomoyo_pattern_list, list) {
if (saved_pattern != ptr->pattern)
error = 0;
out:
up_write(&tomoyo_pattern_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
ptr = list_entry(pos, struct tomoyo_pattern_entry, list);
if (ptr->is_deleted)
continue;
- if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_FILE_PATTERN "%s\n",
- ptr->pattern->name)) {
- done = false;
+ done = tomoyo_io_printf(head, TOMOYO_KEYWORD_FILE_PATTERN
+ "%s\n", ptr->pattern->name);
+ if (!done)
break;
- }
}
up_read(&tomoyo_pattern_list_lock);
return done;
}
-/* The list for "struct tomoyo_no_rewrite_entry". */
+/*
+ * tomoyo_no_rewrite_list is used for holding list of pathnames which are by
+ * default forbidden to modify already written content of a file.
+ *
+ * An entry is added by
+ *
+ * # echo 'deny_rewrite /var/log/messages' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete deny_rewrite /var/log/messages' > \
+ * /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^deny_rewrite /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, if a process requested to rewrite /var/log/messages ,
+ * the process can't rewrite unless the domain which that process belongs to
+ * has "allow_rewrite /var/log/messages" entry.
+ *
+ * It is not a desirable behavior that we have to add "\040(deleted)" suffix
+ * when we want to allow rewriting already unlink()ed file. As of now,
+ * LSM version of TOMOYO is using __d_path() for calculating pathname.
+ * Non LSM version of TOMOYO is using its own function which doesn't append
+ * " (deleted)" suffix if the file is already unlink()ed; so that we don't
+ * need to worry whether the file is already unlink()ed or not.
+ */
static LIST_HEAD(tomoyo_no_rewrite_list);
static DECLARE_RWSEM(tomoyo_no_rewrite_list_lock);
saved_pattern = tomoyo_save_name(pattern);
if (!saved_pattern)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_no_rewrite_list_lock);
list_for_each_entry(ptr, &tomoyo_no_rewrite_list, list) {
if (ptr->pattern != saved_pattern)
error = 0;
out:
up_write(&tomoyo_no_rewrite_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
ptr = list_entry(pos, struct tomoyo_no_rewrite_entry, list);
if (ptr->is_deleted)
continue;
- if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_DENY_REWRITE "%s\n",
- ptr->pattern->name)) {
- done = false;
+ done = tomoyo_io_printf(head, TOMOYO_KEYWORD_DENY_REWRITE
+ "%s\n", ptr->pattern->name);
+ if (!done)
break;
- }
}
up_read(&tomoyo_no_rewrite_list_lock);
return done;
saved_filename = tomoyo_save_name(filename);
if (!saved_filename)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_domain_acl_info_list_lock);
if (is_delete)
goto delete;
}
out:
up_write(&tomoyo_domain_acl_info_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
saved_filename2 = tomoyo_save_name(filename2);
if (!saved_filename1 || !saved_filename2)
return -ENOMEM;
- /***** EXCLUSIVE SECTION START *****/
down_write(&tomoyo_domain_acl_info_list_lock);
if (is_delete)
goto delete;
}
out:
up_write(&tomoyo_domain_acl_info_list_lock);
- /***** EXCLUSIVE SECTION END *****/
return error;
}
*
* @domain: Pointer to "struct tomoyo_domain_info".
* @filename: Check permission for "execute".
- * @tmp: Buffer for temporary use.
*
* Returns 0 on success, negativevalue otherwise.
*/
int tomoyo_check_exec_perm(struct tomoyo_domain_info *domain,
- const struct tomoyo_path_info *filename,
- struct tomoyo_page_buffer *tmp)
+ const struct tomoyo_path_info *filename)
{
const u8 mode = tomoyo_check_flags(domain, TOMOYO_MAC_FOR_FILE);
= roundup(size, max(sizeof(void *), sizeof(long)));
if (word_aligned_size > PATH_MAX)
return NULL;
- /***** EXCLUSIVE SECTION START *****/
mutex_lock(&lock);
if (buf_used_len + word_aligned_size > PATH_MAX) {
if (!tomoyo_quota_for_elements ||
}
}
mutex_unlock(&lock);
- /***** EXCLUSIVE SECTION END *****/
return ptr;
}
*/
#define TOMOYO_MAX_HASH 256
-/* Structure for string data. */
+/*
+ * tomoyo_name_entry is a structure which is used for linking
+ * "struct tomoyo_path_info" into tomoyo_name_list .
+ *
+ * Since tomoyo_name_list manages a list of strings which are shared by
+ * multiple processes (whereas "struct tomoyo_path_info" inside
+ * "struct tomoyo_path_info_with_data" is not shared), a reference counter will
+ * be added to "struct tomoyo_name_entry" rather than "struct tomoyo_path_info"
+ * when TOMOYO starts supporting garbage collector.
+ */
struct tomoyo_name_entry {
struct list_head list;
struct tomoyo_path_info entry;
};
/*
- * The list for "struct tomoyo_name_entry".
- *
- * This list is updated only inside tomoyo_save_name(), thus
- * no global mutex exists.
+ * tomoyo_name_list is used for holding string data used by TOMOYO.
+ * Since same string data is likely used for multiple times (e.g.
+ * "/lib/libc-2.5.so"), TOMOYO shares string data in the form of
+ * "const struct tomoyo_path_info *".
*/
static struct list_head tomoyo_name_list[TOMOYO_MAX_HASH];
return NULL;
}
hash = full_name_hash((const unsigned char *) name, len - 1);
- /***** EXCLUSIVE SECTION START *****/
mutex_lock(&lock);
list_for_each_entry(ptr, &tomoyo_name_list[hash % TOMOYO_MAX_HASH],
list) {
}
out:
mutex_unlock(&lock);
- /***** EXCLUSIVE SECTION END *****/
return ptr ? &ptr->entry : NULL;
}
return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path, flags);
}
+/*
+ * tomoyo_security_ops is a "struct security_operations" which is used for
+ * registering TOMOYO.
+ */
static struct security_operations tomoyo_security_ops = {
.name = "tomoyo",
.cred_prepare = tomoyo_cred_prepare,
struct inode;
struct linux_binprm;
struct pt_regs;
-struct tomoyo_page_buffer;
int tomoyo_check_file_perm(struct tomoyo_domain_info *domain,
const char *filename, const u8 perm);
int tomoyo_check_exec_perm(struct tomoyo_domain_info *domain,
- const struct tomoyo_path_info *filename,
- struct tomoyo_page_buffer *buf);
+ const struct tomoyo_path_info *filename);
int tomoyo_check_open_permission(struct tomoyo_domain_info *domain,
struct path *path, const int flag);
int tomoyo_check_1path_perm(struct tomoyo_domain_info *domain,
return current_cred()->security;
}
-/* Caller holds tasklist_lock spinlock. */
static inline struct tomoyo_domain_info *tomoyo_real_domain(struct task_struct
*task)
{
- /***** CRITICAL SECTION START *****/
- const struct cred *cred = get_task_cred(task);
- struct tomoyo_domain_info *domain = cred->security;
-
- put_cred(cred);
- return domain;
- /***** CRITICAL SECTION END *****/
+ return task_cred_xxx(task, security);
}
#endif /* !defined(_SECURITY_TOMOYO_TOMOYO_H) */
projects / GitHub / moto-9609 / android_kernel_motorola_exynos9610.git / commitdiff