do_blk_trace_setup() will fully initialize 'buts.name', so can remove
the related memcpy(). And also use BLKTRACE_BDEV_SIZE and ARRAY_SIZE
instead of hard code number '32'.
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently each task sends BLK_TN_PROCESS event to the first traced
device it interacts with after a new trace is started. When there are
several traced devices and the task accesses more devices, this logic
can result in BLK_TN_PROCESS being sent several times to some devices
while it is never sent to other devices. Thus blkparse doesn't display
command name when parsing some blktrace files.
Fix the problem by sending BLK_TN_PROCESS event to all traced devices
when a task interacts with any of them.
Signed-off-by: Jan Kara <jack@suse.cz>
Review-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
from a normal user account via the perf syscall "perf_event_open()".
When I was able to reproduce it with trinity, I was able to track down
exactly how it happened.
I discovered that the check for whether the function tracepoint should
be activated or not was using the "perf_paranoid_kernel()" check which
by default, lets the user continue. The user should not by default be
able to enable function tracing. The fix is to use
"perf_paranoid_tracepoint_raw()" which will not let the user enable
function tracing.
This is a security fix as normal users should never be allowed to
enable the function tracer.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)
iQEcBAABAgAGBQJSepxvAAoJEKQekfcNnQGuLeQH/jMe/m3ogrf2NaryszjJ12rc
jyhxXL5tMYNWAY8mp5Dt7WIGgUcNFQFqGq8oNWwc0W/Snil0DHwzwGrbzg6+RMPL
S53qfQvrU0wuFSQu4NdRfhWnq7JaGbji8jbH+d2QdMj2FpktlqxTq8BZETFgJTes
Ex8NmU5paROuYeVNviPeqo5Ss4rPeQYmOE12B3rDhJFYvnzy37D11zO34GiVutoM
mSqSHO5UFig6u2fv347lBM04fBSUDRbK22iXP6kC/xtjgRJh60ElZsRzc5fFzcsQ
usLZ8IcybzpsEReXofFeLDVk98sZKioKYWpzerKwSc8RYDIIrQXaD94T/EDngV8=
=QJRi
-----END PGP SIGNATURE-----
Merge tag 'ftrace-urgent-3.12-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull perf/ftrace fix from Steven Rostedt:
"Dave Jones's trinity program was able to enable the function tracer
from a normal user account via the perf syscall "perf_event_open()".
When I was able to reproduce it with trinity, I was able to track down
exactly how it happened.
I discovered that the check for whether the function tracepoint should
be activated or not was using the "perf_paranoid_kernel()" check which
by default, lets the user continue. The user should not by default be
able to enable function tracing.
The fix is to use "perf_paranoid_tracepoint_raw()" which will not let
the user enable function tracing. This is a security fix as normal
users should never be allowed to enable the function tracer"
* tag 'ftrace-urgent-3.12-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
perf/ftrace: Fix paranoid level for enabling function tracer
Here's the big tty/serial driver update for 3.13-rc1.
There's some more minor n_tty work here, but nothing like previous
kernel releases. Also some new driver ids, driver updates for new
hardware, and other small things.
All of this has been in linux-next for a while with no issues.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)
iEYEABECAAYFAlJ6xnEACgkQMUfUDdst+ylj1QCfaIzUNuFfzTmyB6K6iZrRNhCc
WPgAnRLkkEpI/3rRo7jKwGQsuIuyybUu
=r149
-----END PGP SIGNATURE-----
Merge tag 'tty-3.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty
Pull tty/serial driver updates from Greg KH:
"Here's the big tty/serial driver update for 3.13-rc1.
There's some more minor n_tty work here, but nothing like previous
kernel releases. Also some new driver ids, driver updates for new
hardware, and other small things.
All of this has been in linux-next for a while with no issues"
* tag 'tty-3.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty: (84 commits)
serial: omap: fix missing comma
serial: sh-sci: Enable the driver on all ARM platforms
serial: mfd: Staticize local symbols
serial: omap: fix a few checkpatch warnings
serial: omap: improve RS-485 performance
mrst_max3110: fix unbalanced IRQ issue during resume
serial: omap: Add support for optional wake-up
serial: sirf: remove duplicate defines
tty: xuartps: Fix build error when COMMON_CLK is not set
tty: xuartps: Fix build error due to missing forward declaration
tty: xuartps: Fix "may be used uninitialized" build warning
serial: 8250_pci: add Pericom PCIe Serial board Support (12d8:7952/4/8) - Chip PI7C9X7952/4/8
tty: xuartps: Update copyright information
tty: xuartps: Implement suspend/resume callbacks
tty: xuartps: Dynamically adjust to input frequency changes
tty: xuartps: Updating set_baud_rate()
tty: xuartps: Force enable the UART in xuartps_console_write
tty: xuartps: support 64 byte FIFO size
tty: xuartps: Add polled mode support for xuartps
tty: xuartps: Implement BREAK detection, add SYSRQ support
...
Here's the big driver core / sysfs update for 3.13-rc1.
There's lots of dev_groups updates for different subsystems, as they all
get slowly migrated over to the safe versions of the attribute groups
(removing userspace races with the creation of the sysfs files.) Also
in here are some kobject updates, devres expansions, and the first round
of Tejun's sysfs reworking to enable it to be used by other subsystems
as a backend for an in-kernel filesystem.
All of these have been in linux-next for a while with no reported
issues.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)
iEYEABECAAYFAlJ6xAMACgkQMUfUDdst+yk1kQCfcHXhfnrvFZ5J/mDP509IzhNS
ddEAoLEWoivtBppNsgrWqXpD1vi4UMsE
=JmVW
-----END PGP SIGNATURE-----
Merge tag 'driver-core-3.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull driver core / sysfs patches from Greg KH:
"Here's the big driver core / sysfs update for 3.13-rc1.
There's lots of dev_groups updates for different subsystems, as they
all get slowly migrated over to the safe versions of the attribute
groups (removing userspace races with the creation of the sysfs
files.) Also in here are some kobject updates, devres expansions, and
the first round of Tejun's sysfs reworking to enable it to be used by
other subsystems as a backend for an in-kernel filesystem.
All of these have been in linux-next for a while with no reported
issues"
* tag 'driver-core-3.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (83 commits)
sysfs: rename sysfs_assoc_lock and explain what it's about
sysfs: use generic_file_llseek() for sysfs_file_operations
sysfs: return correct error code on unimplemented mmap()
mdio_bus: convert bus code to use dev_groups
device: Make dev_WARN/dev_WARN_ONCE print device as well as driver name
sysfs: separate out dup filename warning into a separate function
sysfs: move sysfs_hash_and_remove() to fs/sysfs/dir.c
sysfs: remove unused sysfs_get_dentry() prototype
sysfs: honor bin_attr.attr.ignore_lockdep
sysfs: merge sysfs_elem_bin_attr into sysfs_elem_attr
devres: restore zeroing behavior of devres_alloc()
sysfs: fix sysfs_write_file for bin file
input: gameport: convert bus code to use dev_groups
input: serio: remove bus usage of dev_attrs
input: serio: use DEVICE_ATTR_RO()
i2o: convert bus code to use dev_groups
memstick: convert bus code to use dev_groups
tifm: convert bus code to use dev_groups
virtio: convert bus code to use dev_groups
ipack: convert bus code to use dev_groups
...
When system has a lot of highmem (e.g. 16GiB using a 32 bits kernel),
the code to calculate how much memory we need to preallocate in
normal zone may cause overflow. As Leon has analysed:
It looks that during computing 'alloc' variable there is overflow:
alloc = (3943404 - 1970542) - 1978280 = -5418 (signed)
And this function goes to err_out.
Fix this by avoiding that overflow.
References: https://bugzilla.kernel.org/show_bug.cgi?id=60817
Reported-and-tested-by: Leon Drugi <eyak@wp.pl>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The duration field of print_graph_duration() can also be used
to do the space filling by passing an enum in it:
DURATION_FILL_FULL
DURATION_FILL_START
DURATION_FILL_END
The problem is that these are enums and defined as negative,
but the duration field is unsigned long long. Most archs are
fine with this but blackfin fails to compile because of it:
kernel/built-in.o: In function `print_graph_duration':
kernel/trace/trace_functions_graph.c:782: undefined reference to `__ucmpdi2'
Overloading a unsigned long long with an signed enum is just
bad in principle. We can accomplish the same thing by using
part of the flags field instead.
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
In the past, ftrace_off_permanent() was called if something
strange was detected. But the ftrace_bug() now handles all the
anomolies that can happen with ftrace (function tracing), and there
are no uses of ftrace_off_permanent(). Get rid of it.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
In system_tr_open(), the filp->private_data can be assigned the 'dir'
variable even if it was freed. This is on the error path, and is
harmless because the error return code will prevent filp->private_data
from being used. But for correctness, we should not assign it to
a recently freed variable, as that can cause static tools to give
false warnings.
Also have both subsystem_open() and system_tr_open() return -ENODEV
if tracing has been disabled.
Link: http://lkml.kernel.org/r/1383764571-7318-1-git-send-email-geyslan@gmail.com
Signed-off-by: Geyslan G. Bem <geyslan@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The current default perf paranoid level is "1" which has
"perf_paranoid_kernel()" return false, and giving any operations that
use it, access to normal users. Unfortunately, this includes function
tracing and normal users should not be allowed to enable function
tracing by default.
The proper level is defined at "-1" (full perf access), which
"perf_paranoid_tracepoint_raw()" will only give access to. Use that
check instead for enabling function tracing.
Reported-by: Dave Jones <davej@redhat.com>
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Tested-by: Vince Weaver <vincent.weaver@maine.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: stable@vger.kernel.org # 3.4+
CVE: CVE-2013-2930
Fixes: ced39002f5 ("ftrace, perf: Add support to use function tracepoint in perf")
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
set_swbp() and set_orig_insn() are __weak, but this is pointless
because write_opcode() is static.
Export write_opcode() as uprobe_write_opcode() for the upcoming
arm port, this way it can actually override set_swbp() and use
__opcode_to_mem_arm(bpinsn) instead if UPROBE_SWBP_INSN.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Currently xol_get_insn_slot() assumes that we should simply copy
arch_uprobe->insn[] which is (ignoring arch_uprobe_analyze_insn)
just the copy of the original insn.
This is not true for arm which needs to create another insn to
execute it out-of-line.
So this patch simply adds the new member, ->ixol into the union.
This doesn't make any difference for x86 and powerpc, but arm
can divorce insn/ixol and initialize the correct xol insn in
arch_uprobe_analyze_insn().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Turn module_init() into __initcall() and kill module_exit().
This code can't be compiled as a module so these module_*()
calls only add the confusion, especially if arch-dependant
code needs its own initialization hooks.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
sfr pointed out that with CONFIG_UIDGID_STRICT_TYPE_CHECKS set the audit
tree would not build. This is because the oldsessionid in
audit_set_loginuid() was accidentally being declared as a kuid_t. This
patch fixes that declaration mistake.
Example of problem:
kernel/auditsc.c: In function 'audit_set_loginuid':
kernel/auditsc.c:2003:15: error: incompatible types when assigning to
type 'kuid_t' from type 'int'
oldsessionid = audit_get_sessionid(current);
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Eric Paris <eparis@redhat.com>
With ftrace_dump_on_oops, we previously did not open the tracer in
question, sometimes causing the trace output to be useless.
For example, the function_graph tracer with tracing_thresh set dumped via
ftrace_dump_on_oops would show a series of '}' indented at different levels,
but no function names.
call trace->open() (and do a few other fixups copied from the normal dump
path) to make the output more intelligible.
Link: http://lkml.kernel.org/r/1382554197-16961-1-git-send-email-cody@linux.vnet.ibm.com
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
nr_busy_cpus parameter is used by nohz_kick_needed() to find out the
number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES
flag set. Therefore instead of updating nr_busy_cpus at every level
of sched domain, since it is irrelevant, we can update this parameter
only at the parent domain of the sd which has this flag set. Introduce
a per-cpu parameter sd_busy which represents this parent domain.
In nohz_kick_needed() we directly query the nr_busy_cpus parameter
associated with the groups of sd_busy.
By associating sd_busy with the highest domain which has
SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains
which could have this flag set and trigger nohz_idle_balancing if any
of the levels have more than one busy cpu.
sd_busy is irrelevant for asymmetric load balancing. However sd_asym
has been introduced to represent the highest sched domain which has
SD_ASYM_PACKING flag set so that it can be queried directly when
required.
While we are at it, we might as well change the nohz_idle parameter to
be updated at the sd_busy domain level alone and not the base domain
level of a CPU. This will unify the concept of busy cpus at just one
level of sched domain where it is currently used.
Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: svaidy@linux.vnet.ibm.com
Cc: vincent.guittot@linaro.org
Cc: bitbucket@online.de
Cc: benh@kernel.crashing.org
Cc: anton@samba.org
Cc: Morten.Rasmussen@arm.com
Cc: pjt@google.com
Cc: peterz@infradead.org
Cc: mikey@neuling.org
Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Asymmetric scheduling within a core is a scheduler loadbalancing
feature that is triggered when SD_ASYM_PACKING flag is set. The goal
for the load balancer is to move tasks to lower order idle SMT threads
within a core on a POWER7 system.
In nohz_kick_needed(), we intend to check if our sched domain (core)
is completely busy or we have idle cpu.
The following check for SD_ASYM_PACKING:
(cpumask_first_and(nohz.idle_cpus_mask, sched_domain_span(sd)) < cpu)
already covers the case of checking if the domain has an idle cpu,
because cpumask_first_and() will not yield any set bits if this domain
has no idle cpu.
Hence, nr_busy check against group weight can be removed.
Reported-by: Michael Neuling <michael.neuling@au1.ibm.com>
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Tested-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: vincent.guittot@linaro.org
Cc: bitbucket@online.de
Cc: benh@kernel.crashing.org
Cc: anton@samba.org
Cc: Morten.Rasmussen@arm.com
Cc: pjt@google.com
Link: http://lkml.kernel.org/r/20131030031242.23426.13019.stgit@preeti.in.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While this is really minor, but strncpy() does the unnecessary
zero-padding till the end of tmp[16] and it is called every time
we are going to use the string literal.
Turn these strncpy()'s into the single strlcpy() under the new
label, saves 72 bytes.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131017182417.GA17753@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The arch_perf_output_copy_user() default of
__copy_from_user_inatomic() returns bytes not copied, while all other
argument functions given DEFINE_OUTPUT_COPY() return bytes copied.
Since copy_from_user_nmi() is the odd duck out by returning bytes
copied where all other *copy_{to,from}* functions return bytes not
copied, change it over and ammend DEFINE_OUTPUT_COPY() to expect bytes
not copied.
Oddly enough DEFINE_OUTPUT_COPY() already returned bytes not copied
while expecting its worker functions to return bytes copied.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: will.deacon@arm.com
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20131030201622.GR16117@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Avoid touching the lost_event and sample_data cachelines twince. Its
not like we end up doing less work, but it might help to keep all
accesses to these cachelines in one place.
Due to code shuffle, this looses 4 bytes on x86_64-defconfig.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: james.hogan@imgtec.com
Cc: Vince Weaver <vince@deater.net>
Cc: Victor Kaplansky <VICTORK@il.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Anton Blanchard <anton@samba.org>
Link: http://lkml.kernel.org/n/tip-zfxnc58qxj0eawdoj31hhupv@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There's no point in re-doing the memory-barrier when we fail the
cmpxchg(). Also placing it after the space reservation loop makes it
clearer it only separates the userpage->tail read from the data
stores.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: james.hogan@imgtec.com
Cc: Vince Weaver <vince@deater.net>
Cc: Victor Kaplansky <VICTORK@il.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Anton Blanchard <anton@samba.org>
Link: http://lkml.kernel.org/n/tip-c19u6egfldyx86tpyc3zgkw9@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Add unlikely() annotations to 'slow' paths:
When having a sampling event but no output buffer; you have bigger
issues -- also the bail is still faster than actually doing the work.
When having a sampling event but a control page only buffer, you have
bigger issues -- again the bail is still faster than actually doing
work.
Optimize for the case where you're not loosing events -- again, not
doing the work is still faster but make sure that when you have to
actually do work its as fast as possible.
The typical watermark is 1/2 the buffer size, so most events will not
take this path.
Shrinks perf_output_begin() by 16 bytes on x86_64-defconfig.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: james.hogan@imgtec.com
Cc: Vince Weaver <vince@deater.net>
Cc: Victor Kaplansky <VICTORK@il.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Anton Blanchard <anton@samba.org>
Link: http://lkml.kernel.org/n/tip-wlg3jew3qnutm8opd0hyeuwn@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
By using CIRC_SPACE() we can obviate the need for perf_output_space().
Shrinks the size of perf_output_begin() by 17 bytes on
x86_64-defconfig.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: james.hogan@imgtec.com
Cc: Vince Weaver <vince@deater.net>
Cc: Victor Kaplansky <VICTORK@il.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Anton Blanchard <anton@samba.org>
Link: http://lkml.kernel.org/n/tip-vtb0xb0llebmsdlfn1v5vtfj@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Notably: changed lib/rwsem* targets from lib- to obj-, no idea about
the ramifications of that.
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-g0kynfh5feriwc6p3h6kpbw6@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In certain occasions it is possible for a hung task detector
positive to be false: continuation from a paused VM, for example.
Add a method to reset detection, similar as is done
with other kernel watchdogs.
Acked-by: Don Zickus <dzickus@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Conflicts:
kernel/Makefile
There are conflicts in kernel/Makefile due to file moving in the
scheduler tree - resolve them.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Completions already have their own header file: linux/completion.h
Move the implementation out of kernel/sched/core.c and into its own
file: kernel/sched/completion.c.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-x2y49rmxu5dljt66ai2lcfuw@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For some reason only the wait part of the wait api lives in
kernel/sched/wait.c and the wake part still lives in kernel/sched/core.c;
ammend this.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-ftycee88naznulqk7ei5mbci@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There are conflicts in lockdep.c due to RCU changes, and also the RCU
tree changes kernel/Makefile - so pre-merge it to ease the moving of
locking related .c files to kernel/locking/.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The original SOFT_DISABLE patches didn't add support for soft disable
of syscall events; this adds it.
Add an array of ftrace_event_file pointers indexed by syscall number
to the trace array and remove the existing enabled bitmaps, which as a
result are now redundant. The ftrace_event_file structs in turn
contain the soft disable flags we need for per-syscall soft disable
accounting.
Adding ftrace_event_files also means we can remove the USE_CALL_FILTER
bit, thus enabling multibuffer filter support for syscall events.
Link: http://lkml.kernel.org/r/6e72b566e85d8df8042f133efbc6c30e21fb017e.1382620672.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The trace event filters are still tied to event calls rather than
event files, which means you don't get what you'd expect when using
filters in the multibuffer case:
Before:
# echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
bytes_alloc > 8192
# mkdir /sys/kernel/debug/tracing/instances/test1
# echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
bytes_alloc > 2048
# cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
bytes_alloc > 2048
Setting the filter in tracing/instances/test1/events shouldn't affect
the same event in tracing/events as it does above.
After:
# echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
bytes_alloc > 8192
# mkdir /sys/kernel/debug/tracing/instances/test1
# echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
# cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
bytes_alloc > 8192
# cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
bytes_alloc > 2048
We'd like to just move the filter directly from ftrace_event_call to
ftrace_event_file, but there are a couple cases that don't yet have
multibuffer support and therefore have to continue using the current
event_call-based filters. For those cases, a new USE_CALL_FILTER bit
is added to the event_call flags, whose main purpose is to keep the
old behavior for those cases until they can be updated with
multibuffer support; at that point, the USE_CALL_FILTER flag (and the
new associated call_filter_check_discard() function) can go away.
The multibuffer support also made filter_current_check_discard()
redundant, so this change removes that function as well and replaces
it with filter_check_discard() (or call_filter_check_discard() as
appropriate).
Link: http://lkml.kernel.org/r/f16e9ce4270c62f46b2e966119225e1c3cca7e60.1382620672.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Dave Jones reported that trinity would be able to trigger the following
back trace:
===============================
[ INFO: suspicious RCU usage. ]
3.10.0-rc2+ #38 Not tainted
-------------------------------
include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle!
other info that might help us debug this:
RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0
RCU used illegally from extended quiescent state!
1 lock held by trinity-child1/18786:
#0: (rcu_read_lock){.+.+..}, at: [<ffffffff8113dd48>] __perf_event_overflow+0x108/0x310
stack backtrace:
CPU: 3 PID: 18786 Comm: trinity-child1 Not tainted 3.10.0-rc2+ #38
0000000000000000 ffff88020767bac8 ffffffff816e2f6b ffff88020767baf8
ffffffff810b5897 ffff88021de92520 0000000000000000 ffff88020767bbf8
0000000000000000 ffff88020767bb78 ffffffff8113ded4 ffffffff8113dd48
Call Trace:
[<ffffffff816e2f6b>] dump_stack+0x19/0x1b
[<ffffffff810b5897>] lockdep_rcu_suspicious+0xe7/0x120
[<ffffffff8113ded4>] __perf_event_overflow+0x294/0x310
[<ffffffff8113dd48>] ? __perf_event_overflow+0x108/0x310
[<ffffffff81309289>] ? __const_udelay+0x29/0x30
[<ffffffff81076054>] ? __rcu_read_unlock+0x54/0xa0
[<ffffffff816f4000>] ? ftrace_call+0x5/0x2f
[<ffffffff8113dfa1>] perf_swevent_overflow+0x51/0xe0
[<ffffffff8113e08f>] perf_swevent_event+0x5f/0x90
[<ffffffff8113e1c9>] perf_tp_event+0x109/0x4f0
[<ffffffff8113e36f>] ? perf_tp_event+0x2af/0x4f0
[<ffffffff81074630>] ? __rcu_read_lock+0x20/0x20
[<ffffffff8112d79f>] perf_ftrace_function_call+0xbf/0xd0
[<ffffffff8110e1e1>] ? ftrace_ops_control_func+0x181/0x210
[<ffffffff81074630>] ? __rcu_read_lock+0x20/0x20
[<ffffffff81100cae>] ? rcu_eqs_enter_common+0x5e/0x470
[<ffffffff8110e1e1>] ftrace_ops_control_func+0x181/0x210
[<ffffffff816f4000>] ftrace_call+0x5/0x2f
[<ffffffff8110e229>] ? ftrace_ops_control_func+0x1c9/0x210
[<ffffffff816f4000>] ? ftrace_call+0x5/0x2f
[<ffffffff81074635>] ? debug_lockdep_rcu_enabled+0x5/0x40
[<ffffffff81074635>] ? debug_lockdep_rcu_enabled+0x5/0x40
[<ffffffff81100cae>] ? rcu_eqs_enter_common+0x5e/0x470
[<ffffffff8110112a>] rcu_eqs_enter+0x6a/0xb0
[<ffffffff81103673>] rcu_user_enter+0x13/0x20
[<ffffffff8114541a>] user_enter+0x6a/0xd0
[<ffffffff8100f6d8>] syscall_trace_leave+0x78/0x140
[<ffffffff816f46af>] int_check_syscall_exit_work+0x34/0x3d
------------[ cut here ]------------
Perf uses rcu_read_lock() but as the function tracer can trace functions
even when RCU is not currently active, this makes the rcu_read_lock()
used by perf ineffective.
As perf is currently the only user of the ftrace_ops_control_func() and
perf is also the only function callback that actively uses rcu_read_lock(),
the quick fix is to prevent the ftrace_ops_control_func() from calling
its callbacks if RCU is not active.
With Paul's new "rcu_is_watching()" we can tell if RCU is active or not.
Reported-by: Dave Jones <davej@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
As perf uses the rcu_read_lock() primitives for recording into its
ring buffer, perf tracing can not be called when RCU in inactive.
With the perf function tracing, there are functions that can be
traced when RCU is not active, and perf must not have its function
callback called when this is the case.
Luckily, Paul McKenney has created a way to detect when RCU is
active or not with the rcu_is_watching() function. Unfortunately,
this function can also be traced, and if that happens it can cause
a bit of overhead for the perf function calls that do the check.
Recursion protection prevents anything bad from happening, but
there is a bit of added overhead for every function being traced that
must detect that the rcu_is_watching() is also being traced.
As rcu_is_watching() is a helper routine and not part of the
critical logic in RCU, it does not need to be traced in order to
debug RCU itself. Add the "notrace" annotation to all the rcu_is_watching()
calls such that we never trace it.
Link: http://lkml.kernel.org/r/20131104202736.72dd8e45@gandalf.local.home
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Use rbtree_postorder_for_each_entry_safe() to destroy the rbtree instead
of opencoding an alternate postorder iteration that modifies the tree
Link: http://lkml.kernel.org/r/1383345566-25087-2-git-send-email-cody@linux.vnet.ibm.com
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Move the audit_bprm() call from search_binary_handler() to exec_binprm(). This
allows us to get rid of the mm member of struct audit_aux_data_execve since
bprm->mm will equal current->mm.
This also mitigates the issue that ->argc could be modified by the
load_binary() call in search_binary_handler().
audit_bprm() was being called to add an AUDIT_EXECVE record to the audit
context every time search_binary_handler() was recursively called. Only one
reference is necessary.
Reported-by: Oleg Nesterov <onestero@redhat.com>
Cc: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
This patch is against 3.11, but was developed on Oleg's post-3.11 patches that
introduce exec_binprm().
audit_bprm() was being called to add an AUDIT_EXECVE record to the audit
context every time search_binary_handler() was recursively called. Only one
reference is necessary, so just update it. Move the the contents of
audit_aux_data_execve into the union in audit_context, removing dependence on a
kmalloc along the way.
Reported-by: Oleg Nesterov <onestero@redhat.com>
Cc: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Get rid of write-only audit_aux_data_exeve structure member envc.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
(cherry picked from ebiederman commit 6904431d6b41190e42d6b94430b67cb4e7e6a4b7)
Signed-off-by: Eric Paris <eparis@redhat.com>
commit ab61d38ed8 tried to merge the
invalid filter checking into a single function. However AUDIT_INODE
filters were not verified in the new generic checker. Thus such rules
were being denied even though they were perfectly valid.
Ex:
$ auditctl -a exit,always -F arch=b64 -S open -F key=/foo -F inode=6955 -F devmajor=9 -F devminor=1
Error sending add rule data request (Invalid argument)
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
...to make it clear what the intent behind each record's operation was.
In many cases you can infer this, based on the context of the syscall
and the result. In other cases it's not so obvious. For instance, in
the case where you have a file being renamed over another, you'll have
two different records with the same filename but different inode info.
By logging this information we can clearly tell which one was created
and which was deleted.
This fixes what was broken in commit bfcec708.
Commit 79f6530c should also be backported to stable v3.7+.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
In send/GET, we don't want the kernel to lie about what value is set.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Using the nlmsg_len member of the netlink header to test if the message
is valid is wrong as it includes the size of the netlink header itself.
Thereby allowing to send short netlink messages that pass those checks.
Use nlmsg_len() instead to test for the right message length. The result
of nlmsg_len() is guaranteed to be non-negative as the netlink message
already passed the checks of nlmsg_ok().
Also switch to min_t() to please checkpatch.pl.
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Paris <eparis@redhat.com>
Cc: stable@vger.kernel.org # v2.6.6+ for the 1st hunk, v2.6.23+ for the 2nd
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
We currently are setting fields to 0 to initialize the structure
declared on the stack. This is a bad idea as if the structure has holes
or unpacked space these will not be initialized. Just use memset. This
is not a performance critical section of code.
Signed-off-by: Eric Paris <eparis@redhat.com>
We leak 4 bytes of kernel stack in response to an AUDIT_GET request as
we miss to initialize the mask member of status_set. Fix that.
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Paris <eparis@redhat.com>
Cc: stable@vger.kernel.org # v2.6.6+
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
It appears this one comparison function got missed in f368c07d (and 9c937dcc).
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
This adds a new 'audit_feature' bit which allows userspace to set it
such that the loginuid is absolutely immutable, even if you have
CAP_AUDIT_CONTROL.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
This is a new audit feature which only grants processes with
CAP_AUDIT_CONTROL the ability to unset their loginuid. They cannot
directly set it from a valid uid to another valid uid. The ability to
unset the loginuid is nice because a priviledged task, like that of
container creation, can unset the loginuid and then priv is not needed
inside the container when a login daemon needs to set the loginuid.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
If a task has CAP_AUDIT_CONTROL allow that task to unset their loginuid.
This would allow a child of that task to set their loginuid without
CAP_AUDIT_CONTROL. Thus when launching a new login daemon, a
priviledged helper would be able to unset the loginuid and then the
daemon, which may be malicious user facing, do not need priv to function
correctly.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
After trying to use this feature in Fedora we found the hard coding
policy like this into the kernel was a bad idea. Surprise surprise.
We ran into these problems because it was impossible to launch a
container as a logged in user and run a login daemon inside that container.
This reverts back to the old behavior before this option was added. The
option will be re-added in a userspace selectable manor such that
userspace can choose when it is and when it is not appropriate.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
This is just a code rework. It makes things more readable. It does not
make any functional changes.
It does change the log messages to include both the old session id as
well the new and it includes a new res field, which means we get
messages even when the user did not have permission to change the
loginuid.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
The audit_status structure was not designed with extensibility in mind.
Define a new AUDIT_SET_FEATURE message type which takes a new structure
of bits where things can be enabled/disabled/locked one at a time. This
structure should be able to grow in the future while maintaining forward
and backward compatibility (based loosly on the ideas from capabilities
and prctl)
This does not actually add any features, but is just infrastructure to
allow new on/off types of audit system features.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
SFR reported this 2013-05-15:
> After merging the final tree, today's linux-next build (i386 defconfig)
> produced this warning:
>
> kernel/auditfilter.c: In function 'audit_data_to_entry':
> kernel/auditfilter.c:426:3: warning: this decimal constant is unsigned only
> in ISO C90 [enabled by default]
>
> Introduced by commit 780a7654ce ("audit: Make testing for a valid
> loginuid explicit") from Linus' tree.
Replace this decimal constant in the code with a macro to make it more readable
(add to the unsigned cast to quiet the warning).
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
When the audit=1 kernel parameter is absent and auditd is not running,
AUDIT_USER_AVC messages are being silently discarded.
AUDIT_USER_AVC messages should be sent to userspace using printk(), as
mentioned in the commit message of 4a4cd633 ("AUDIT: Optimise the
audit-disabled case for discarding user messages").
When audit_enabled is 0, audit_receive_msg() discards all user messages
except for AUDIT_USER_AVC messages. However, audit_log_common_recv_msg()
refuses to allocate an audit_buffer if audit_enabled is 0. The fix is to
special case AUDIT_USER_AVC messages in both functions.
It looks like commit 50397bd1 ("[AUDIT] clean up audit_receive_msg()")
introduced this bug.
Cc: <stable@kernel.org> # v2.6.25+
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Paris <eparis@redhat.com>
Cc: linux-audit@redhat.com
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
If audit_filter_task() nacks the new thread it makes sense
to clear TIF_SYSCALL_AUDIT which can be copied from parent
by dup_task_struct().
A wrong TIF_SYSCALL_AUDIT is not really bad but it triggers
the "slow" audit paths in entry.S to ensure the task can not
miss audit_syscall_*() calls, this is pointless if the task
has no ->audit_context.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Steve Grubb <sgrubb@redhat.com>
Acked-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Remove it.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
A newline was accidentally added during session ID helper refactorization in
commit 4d3fb709. This needlessly uses up buffer space, messes up syslog
formatting and makes userspace processing less efficient. Remove it.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Acked-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Ilya V. Matveychikov <matvejchikov@gmail.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Messages of type AUDIT_USER_TTY were being formatted to 1024 octets,
truncating messages approaching MAX_AUDIT_MESSAGE_LENGTH (8970 octets).
Set the formatting to 8560 characters, given maximum estimates for prefix and
suffix budgets.
See the problem discussion:
https://www.redhat.com/archives/linux-audit/2009-January/msg00030.html
And the new size rationale:
https://www.redhat.com/archives/linux-audit/2013-September/msg00016.html
Test ~8k messages with:
auditctl -m "$(for i in $(seq -w 001 820);do echo -n "${i}0______";done)"
Reported-by: LC Bruzenak <lenny@magitekltd.com>
Reported-by: Justin Stephenson <jstephen@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Conflicts:
drivers/net/ethernet/emulex/benet/be.h
drivers/net/netconsole.c
net/bridge/br_private.h
Three mostly trivial conflicts.
The net/bridge/br_private.h conflict was a function signature (argument
addition) change overlapping with the extern removals from Joe Perches.
In drivers/net/netconsole.c we had one change adjusting a printk message
whilst another changed "printk(KERN_INFO" into "pr_info(".
Lastly, the emulex change was a new inline function addition overlapping
with Joe Perches's extern removals.
Signed-off-by: David S. Miller <davem@davemloft.net>
Resolve cherry-picking conflicts:
Conflicts:
mm/huge_memory.c
mm/memory.c
mm/mprotect.c
See this upstream merge commit for more details:
52469b4fcd Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently check_hung_task() prints a warning if it detects the
problem, but it is not convenient to watch the system logs if
user-space wants to be notified about the hang.
Add the new trace_sched_process_hang() into check_hung_task(),
this way a user-space monitor can easily wait for the hang and
potentially resolve a problem.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Dave Sullivan <dsulliva@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20131019161828.GA7439@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If a macro is only used within 2 times, and also its contents are
within 2 lines, recommend to expand it to shrink code line.
For our case, the macro is not portable either: some architectures'
assembler may use another character to mark newline in a macro (e.g.
'`' for arc), which will cause issue.
If still want to use macro and let it portable enough, it will also
need include additional header file (e.g "#include <linux/linkage.h>",
although it also need be fixed).
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Using a spinlock to atomically increase a counter sounds wrong -- we've
atomic_t for this!
Also move 'seq_nr' to a different cache line than 'lock' to reduce cache
line trashing. This has the nice side effect of decreasing the size of
struct parallel_data from 192 to 128 bytes for a x86-64 build, e.g.
occupying only two instead of three cache lines.
Those changes results in a 5% performance increase on an IPsec test run
using pcrypt.
Btw. the seq_lock spinlock was never explicitly initialized -- one more
reason to get rid of it.
Signed-off-by: Mathias Krause <mathias.krause@secunet.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
uprobe_copy_process() does nothing if the child shares ->mm with
the forking process, but there is a special case: CLONE_VFORK.
In this case it would be more correct to do dup_utask() but avoid
dup_xol(). This is not that important, the child should not unwind
its stack too much, this can corrupt the parent's stack, but at
least we need this to allow to ret-probe __vfork() itself.
Note: in theory, it would be better to check task_pt_regs(p)->sp
instead of CLONE_VFORK, we need to dup_utask() if and only if the
child can return from the function called by the parent. But this
needs the arch-dependant helper, and I think that nobody actually
does clone(same_stack, CLONE_VM).
Reported-by: Martin Cermak <mcermak@redhat.com>
Reported-by: David Smith <dsmith@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
This finally fixes the serious bug in uretprobes: a forked child
crashes if the parent called fork() with the pending ret probe.
Trivial test-case:
# perf probe -x /lib/libc.so.6 __fork%return
# perf record -e probe_libc:__fork perl -le 'fork || print "OK"'
(the child doesn't print "OK", it is killed by SIGSEGV)
If the child returns from the probed function it actually returns
to trampoline_vaddr, because it got the copy of parent's stack
mangled by prepare_uretprobe() when the parent entered this func.
It crashes because a) this address is not mapped and b) until the
previous change it doesn't have the proper->return_instances info.
This means that uprobe_copy_process() has to create xol_area which
has the trampoline slot, and its vaddr should be equal to parent's
xol_area->vaddr.
Unfortunately, uprobe_copy_process() can not simply do
__create_xol_area(child, xol_area->vaddr). This could actually work
but perf_event_mmap() doesn't expect the usage of foreign ->mm. So
we offload this to task_work_run(), and pass the argument via not
yet used utask->vaddr.
We know that this vaddr is fine for install_special_mapping(), the
necessary hole was recently "created" by dup_mmap() which skips the
parent's VM_DONTCOPY area, and nobody else could use the new mm.
Unfortunately, this also means that we can not handle the errors
properly, we obviously can not abort the already completed fork().
So we simply print the warning if GFP_KERNEL allocation (the only
possible reason) fails.
Reported-by: Martin Cermak <mcermak@redhat.com>
Reported-by: David Smith <dsmith@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
uprobe_copy_process() assumes that the new child doesn't need
->utask, it should be allocated by demand.
But this is not true if the forking task has the pending ret-
probes, the child should report them as well and thus it needs
the copy of parent's ->return_instances chain. Otherwise the
child crashes when it returns from the probed function.
Alternatively we could cleanup the child's stack, but this needs
per-arch changes and this is not what we want. At least systemtap
expects a .return in the child too.
Note: this change alone doesn't fix the problem, see the next
change.
Reported-by: Martin Cermak <mcermak@redhat.com>
Reported-by: David Smith <dsmith@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Currently xol_add_vma() uses get_unmapped_area() for area->vaddr,
but the next patches need to use the fixed address. So this patch
adds the new "vaddr" argument to __create_xol_area() which should
be used as area->vaddr if it is nonzero.
xol_add_vma() doesn't bother to verify that the predefined addr is
not used, insert_vm_struct() should fail if find_vma_links() detects
the overlap with the existing vma.
Also, __create_xol_area() doesn't need __GFP_ZERO to allocate area.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
No functional changes, preparation.
Extract the code which actually allocates/installs the new area
into the new helper, __create_xol_area().
While at it remove the unnecessary "ret = ENOMEM" and "ret = 0"
in xol_add_vma(), they both have no effect.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Preparation for the next patches.
Move the callsite of uprobe_copy_process() in copy_process() down
to the succesfull return. We do not care if copy_process() fails,
uprobe_free_utask() won't be called in this case so the wrong
->utask != NULL doesn't matter.
OTOH, with this change we know that copy_process() can't fail when
uprobe_copy_process() is called, the new task should either return
to user-mode or call do_exit(). This way uprobe_copy_process() can:
1. setup p->utask != NULL if necessary
2. setup uprobes_state.xol_area
3. use task_work_add(p)
Also, move the definition of uprobe_copy_process() down so that it
can see get_utask().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Currently we only optimize the context switch between two
contexts that have the same parent; this forgoes the
optimization between parent and child context, even though these
contexts could be equivalent too.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Shishkin, Alexander <alexander.shishkin@intel.com>
Link: http://lkml.kernel.org/r/20131007164257.GH3081@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg complained about the excessive 0-ing in perf_event_mmap_event(),
so try and be smarter about it while keeping it fairly fool proof and
avoid leaking random bits out to userspace.
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-8jirlm99m6if2z13wd6rbyu6@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
perf_event_mmap_event() does kzalloc(PATH_MAX + sizeof(u64)) to
ensure we can align the size later. However this means that we
actually allocate PAGE_SIZE * 2 buffer, seems too much.
Change this code to allocate PATH_MAX==PAGE_SIZE bytes, but tell
d_path() to not use the last sizeof(u64) bytes.
Note: it is not clear why do we need __GFP_ZERO, see the next patch.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131016201004.GC23214@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
1. perf_event_mmap(vma) is never called with a gate_vma-like arg,
remove the "if (!vma->vm_mm)" code.
2. arch_vma_name() can use the chached value of mmap_event->vma.
3. Change the code to not call arch_vma_name() twice.
4. Purely cosmetic, but since we use "goto got_name" all the time
remove "else" from "[stack]" branch just for symmetry.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131016200945.GB23214@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
throttle_cfs_rq() doesn't check to make sure that period_timer is running,
and while update_curr/assign_cfs_runtime does, a concurrently running
period_timer on another cpu could cancel itself between this cpu's
update_curr and throttle_cfs_rq(). If there are no other cfs_rqs running
in the tg to restart the timer, this causes the cfs_rq to be stranded
forever.
Fix this by calling __start_cfs_bandwidth() in throttle if the timer is
inactive.
(Also add some sched_debug lines for cfs_bandwidth.)
Tested: make a run/sleep task in a cgroup, loop switching the cgroup
between 1ms/100ms quota and unlimited, checking for timer_active=0 and
throttled=1 as a failure. With the throttle_cfs_rq() change commented out
this fails, with the full patch it passes.
Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: pjt@google.com
Link: http://lkml.kernel.org/r/20131016181632.22647.84174.stgit@sword-of-the-dawn.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently, group entity load-weights are initialized to zero. This
admits some races with respect to the first time they are re-weighted in
earlty use. ( Let g[x] denote the se for "g" on cpu "x". )
Suppose that we have root->a and that a enters a throttled state,
immediately followed by a[0]->t1 (the only task running on cpu[0])
blocking:
put_prev_task(group_cfs_rq(a[0]), t1)
put_prev_entity(..., t1)
check_cfs_rq_runtime(group_cfs_rq(a[0]))
throttle_cfs_rq(group_cfs_rq(a[0]))
Then, before unthrottling occurs, let a[0]->b[0]->t2 wake for the first
time:
enqueue_task_fair(rq[0], t2)
enqueue_entity(group_cfs_rq(b[0]), t2)
enqueue_entity_load_avg(group_cfs_rq(b[0]), t2)
account_entity_enqueue(group_cfs_ra(b[0]), t2)
update_cfs_shares(group_cfs_rq(b[0]))
< skipped because b is part of a throttled hierarchy >
enqueue_entity(group_cfs_rq(a[0]), b[0])
...
We now have b[0] enqueued, yet group_cfs_rq(a[0])->load.weight == 0
which violates invariants in several code-paths. Eliminate the
possibility of this by initializing group entity weight.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131016181627.22647.47543.stgit@sword-of-the-dawn.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
__start_cfs_bandwidth calls hrtimer_cancel while holding rq->lock,
waiting for the hrtimer to finish. However, if sched_cfs_period_timer
runs for another loop iteration, the hrtimer can attempt to take
rq->lock, resulting in deadlock.
Fix this by ensuring that cfs_b->timer_active is cleared only if the
_latest_ call to do_sched_cfs_period_timer is returning as idle. Then
__start_cfs_bandwidth can just call hrtimer_try_to_cancel and wait for
that to succeed or timer_active == 1.
Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: pjt@google.com
Link: http://lkml.kernel.org/r/20131016181622.22647.16643.stgit@sword-of-the-dawn.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
hrtimer_expires_remaining does not take internal hrtimer locks and thus
must be guarded against concurrent __hrtimer_start_range_ns (but
returning HRTIMER_RESTART is safe). Use cfs_b->lock to make it safe.
Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: pjt@google.com
Link: http://lkml.kernel.org/r/20131016181617.22647.73829.stgit@sword-of-the-dawn.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When we transition cfs_bandwidth_used to false, any currently
throttled groups will incorrectly return false from cfs_rq_throttled.
While tg_set_cfs_bandwidth will unthrottle them eventually, currently
running code (including at least dequeue_task_fair and
distribute_cfs_runtime) will cause errors.
Fix this by turning off cfs_bandwidth_used only after unthrottling all
cfs_rqs.
Tested: toggle bandwidth back and forth on a loaded cgroup. Caused
crashes in minutes without the patch, hasn't crashed with it.
Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: pjt@google.com
Link: http://lkml.kernel.org/r/20131016181611.22647.80365.stgit@sword-of-the-dawn.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The PPC64 people noticed a missing memory barrier and crufty old
comments in the perf ring buffer code. So update all the comments and
add the missing barrier.
When the architecture implements local_t using atomic_long_t there
will be double barriers issued; but short of introducing more
conditional barrier primitives this is the best we can do.
Reported-by: Victor Kaplansky <victork@il.ibm.com>
Tested-by: Victor Kaplansky <victork@il.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: michael@ellerman.id.au
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: anton@samba.org
Cc: benh@kernel.crashing.org
Link: http://lkml.kernel.org/r/20131025173749.GG19466@laptop.lan
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In commit ee23871389 ("genirq: Set irq thread to RT priority on
creation") we moved the assigment of the thread's priority from the
thread's function into __setup_irq(). That function may run in user
context for instance if the user opens an UART node and then driver
calls requests in the ->open() callback. That user may not have
CAP_SYS_NICE and so the irq thread won't run with the SCHED_OTHER
policy.
This patch uses sched_setscheduler_nocheck() so we omit the CAP_SYS_NICE
check which is otherwise required for the SCHED_OTHER policy.
[bigeasy: Rewrite the changelog]
Signed-off-by: Thomas Pfaff <tpfaff@pcs.com>
Cc: Ivo Sieben <meltedpianoman@gmail.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1381489240-29626-1-git-send-email-bigeasy@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Pull timer fix from Ingo Molnar:
"This tree contains a clockevents regression fix for certain ARM
subarchitectures"
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
clockevents: Sanitize ticks to nsec conversion
Pull perf fixes from Ingo Molnar:
"The tree contains three fixes:
- Two tooling fixes
- Reversal of the new 'MMAP2' extended mmap record ABI, introduced in
this merge window. (Patches were proposed to fix it but it was all
a bit late and we felt it's safer to just delay the ABI one more
kernel release and do it right)"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf: Disable PERF_RECORD_MMAP2 support
perf scripting perl: Fix build error on Fedora 12
perf probe: Fix to initialize fname always before use it
Pull locking fix from Ingo Molnar:
"This tree fixes a boot crash in CONFIG_DEBUG_MUTEXES=y kernels, on
kernels built with GCC 3.x (there are still such distros)"
Side note: it's not just a fix for old gcc versions, it's also removing
an incredibly broken/subtle check that LLVM had issues with, and that
made no sense.
* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
mutex: Avoid gcc version dependent __builtin_constant_p() usage
This issue was introduced by 454c79999f ("sched/rt: Fix SCHED_RR
across cgroups") that missed the word 'not'. Fix it.
Signed-off-by: Li Bin <huawei.libin@huawei.com>
Cc: <guohanjun@huawei.com>
Cc: <xiexiuqi@huawei.com>
Cc: <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1382357743-54136-1-git-send-email-huawei.libin@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
- Fix for rounding errors in intel_pstate causing CPU utilization to
be underestimated from Brennan Shacklett.
- intel_pstate fix to always use the correct max pstate value when
computing the min pstate from Dirk Brandewie.
- Hibernation fix for deadlocking resume in cases when the probing
of the device containing the image is deferred from Russ Dill.
- acpi-cpufreq fix to prevent the module from staying in memory
when the driver cannot be registered and then attempting to
unregister things that have never been registered on exit.
/
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)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=PsHF
-----END PGP SIGNATURE-----
Merge tag 'pm+acpi-3.12-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull ACPI and power management fixes from
"These fix two bugs in the intel_pstate driver, a hibernate bug leading
to nasty resume failures sometimes and acpi-cpufreq initialization bug
that causes problems to happen during module unload when intel_pstate
is in use.
Specifics:
- Fix for rounding errors in intel_pstate causing CPU utilization to
be underestimated from Brennan Shacklett.
- intel_pstate fix to always use the correct max pstate value when
computing the min pstate from Dirk Brandewie.
- Hibernation fix for deadlocking resume in cases when the probing of
the device containing the image is deferred from Russ Dill.
- acpi-cpufreq fix to prevent the module from staying in memory when
the driver cannot be registered and then attempting to unregister
things that have never been registered on exit"
* tag 'pm+acpi-3.12-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
acpi-cpufreq: Fail initialization if driver cannot be registered
PM / hibernate: Move software_resume to late_initcall_sync
intel_pstate: Correct calculation of min pstate value
intel_pstate: Improve accuracy by not truncating until final result
This patch makes use of the newly defined common hash algorithm info,
replacing, for example, PKEY_HASH with HASH_ALGO.
Changelog:
- Lindent fixes - Mimi
CC: David Howells <dhowells@redhat.com>
Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
blk-mq reuses the request potentially immediately, since the most
cache hot is always given out first. This means that rq->csd could
be reused between csd->func() being called and csd_unlock() being
called. This isn't a problem, since we never use wait == 1 for
the smp call function. Add CSD_FLAG_WAIT to be able to tell the
difference, retaining the warning for other cases.
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The blk-mq core and the blk-mq null driver uses it.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
software_resume is being called after deferred_probe_initcall in
drivers base. If the probing of the device that contains the resume
image is deferred, and the system has been instructed to wait for
it to show up, this wait will occur in software_resume. This causes
a deadlock.
Move software_resume into late_initcall_sync so that it happens
after all the other late_initcalls.
Signed-off-by: Russ Dill <Russ.Dill@ti.com>
Acked-by: Pavel Machek <Pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
All the callers of irq_create_of_mapping() pass the contents of a struct
of_phandle_args structure to the function. Since all the callers already
have an of_phandle_args pointer, why not pass it directly to
irq_create_of_mapping()?
Signed-off-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Michal Simek <monstr@monstr.eu>
Acked-by: Tony Lindgren <tony@atomide.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Conflicts:
drivers/net/usb/qmi_wwan.c
include/net/dst.h
Trivial merge conflicts, both were overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Marc Kleine-Budde pointed out, that commit 77cc982 "clocksource: use
clockevents_config_and_register() where possible" caused a regression
for some of the converted subarchs.
The reason is, that the clockevents core code converts the minimal
hardware tick delta to a nanosecond value for core internal
usage. This conversion is affected by integer math rounding loss, so
the backwards conversion to hardware ticks will likely result in a
value which is less than the configured hardware limitation. The
affected subarchs used their own workaround (SIGH!) which got lost in
the conversion.
The solution for the issue at hand is simple: adding evt->mult - 1 to
the shifted value before the integer divison in the core conversion
function takes care of it. But this only works for the case where for
the scaled math mult/shift pair "mult <= 1 << shift" is true. For the
case where "mult > 1 << shift" we can apply the rounding add only for
the minimum delta value to make sure that the backward conversion is
not less than the given hardware limit. For the upper bound we need to
omit the rounding add, because the backwards conversion is always
larger than the original latch value. That would violate the upper
bound of the hardware device.
Though looking closer at the details of that function reveals another
bogosity: The upper bounds check is broken as well. Checking for a
resulting "clc" value greater than KTIME_MAX after the conversion is
pointless. The conversion does:
u64 clc = (latch << evt->shift) / evt->mult;
So there is no sanity check for (latch << evt->shift) exceeding the
64bit boundary. The latch argument is "unsigned long", so on a 64bit
arch the handed in argument could easily lead to an unnoticed shift
overflow. With the above rounding fix applied the calculation before
the divison is:
u64 clc = (latch << evt->shift) + evt->mult - 1;
So we need to make sure, that neither the shift nor the rounding add
is overflowing the u64 boundary.
[ukl: move assignment to rnd after eventually changing mult, fix build
issue and correct comment with the right math]
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Russell King - ARM Linux <linux@arm.linux.org.uk>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: nicolas.ferre@atmel.com
Cc: Marc Pignat <marc.pignat@hevs.ch>
Cc: john.stultz@linaro.org
Cc: kernel@pengutronix.de
Cc: Ronald Wahl <ronald.wahl@raritan.com>
Cc: LAK <linux-arm-kernel@lists.infradead.org>
Cc: Ludovic Desroches <ludovic.desroches@atmel.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1380052223-24139-1-git-send-email-u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Pull cgroup fixes from Tejun Heo:
"Two late fixes for cgroup.
One fixes descendant walk introduced during this rc1 cycle. The other
fixes a post 3.9 bug during task attach which can lead to hang. Both
fixes are critical and the fixes are relatively straight-forward"
* 'for-3.12-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: fix to break the while loop in cgroup_attach_task() correctly
cgroup: fix cgroup post-order descendant walk of empty subtree
Usage of the static key primitives to toggle a branch must not be used
before jump_label_init() is called from init/main.c. jump_label_init
reorganizes and wires up the jump_entries so usage before that could
have unforeseen consequences.
Following primitives are now checked for correct use:
* static_key_slow_inc
* static_key_slow_dec
* static_key_slow_dec_deferred
* jump_label_rate_limit
The x86 architecture already checks this by testing if the default_nop
was already replaced with an optimal nop or with a branch instruction. It
will panic then. Other architectures don't check for this.
Because we need to relax this check for the x86 arch to allow code to
transition from default_nop to the enabled state and other architectures
did not check for this at all this patch introduces checking on the
static_key primitives in a non-arch dependent manner.
All checked functions are considered slow-path so the additional check
does no harm to performance.
The warnings are best observed with earlyprintk.
Based on a patch from Andi Kleen.
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The parser set up is just a generic utility that uses local variables
allocated by the function. There's no need to hold the graph_lock for
this set up.
This also makes the code simpler.
Link: http://lkml.kernel.org/r/1381739066-7531-4-git-send-email-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The struct ftrace_graph_data is for generalizing the access to
set_graph_function file. This is a preparation for adding support to
set_graph_notrace.
Link: http://lkml.kernel.org/r/1381739066-7531-3-git-send-email-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The ftrace_graph_filter_enabled means that user sets function filter
and it always has same meaning of ftrace_graph_count > 0.
Link: http://lkml.kernel.org/r/1381739066-7531-2-git-send-email-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Andrey reported the following report:
ERROR: AddressSanitizer: heap-buffer-overflow on address ffff8800359c99f3
ffff8800359c99f3 is located 0 bytes to the right of 243-byte region [ffff8800359c9900, ffff8800359c99f3)
Accessed by thread T13003:
#0 ffffffff810dd2da (asan_report_error+0x32a/0x440)
#1 ffffffff810dc6b0 (asan_check_region+0x30/0x40)
#2 ffffffff810dd4d3 (__tsan_write1+0x13/0x20)
#3 ffffffff811cd19e (ftrace_regex_release+0x1be/0x260)
#4 ffffffff812a1065 (__fput+0x155/0x360)
#5 ffffffff812a12de (____fput+0x1e/0x30)
#6 ffffffff8111708d (task_work_run+0x10d/0x140)
#7 ffffffff810ea043 (do_exit+0x433/0x11f0)
#8 ffffffff810eaee4 (do_group_exit+0x84/0x130)
#9 ffffffff810eafb1 (SyS_exit_group+0x21/0x30)
#10 ffffffff81928782 (system_call_fastpath+0x16/0x1b)
Allocated by thread T5167:
#0 ffffffff810dc778 (asan_slab_alloc+0x48/0xc0)
#1 ffffffff8128337c (__kmalloc+0xbc/0x500)
#2 ffffffff811d9d54 (trace_parser_get_init+0x34/0x90)
#3 ffffffff811cd7b3 (ftrace_regex_open+0x83/0x2e0)
#4 ffffffff811cda7d (ftrace_filter_open+0x2d/0x40)
#5 ffffffff8129b4ff (do_dentry_open+0x32f/0x430)
#6 ffffffff8129b668 (finish_open+0x68/0xa0)
#7 ffffffff812b66ac (do_last+0xb8c/0x1710)
#8 ffffffff812b7350 (path_openat+0x120/0xb50)
#9 ffffffff812b8884 (do_filp_open+0x54/0xb0)
#10 ffffffff8129d36c (do_sys_open+0x1ac/0x2c0)
#11 ffffffff8129d4b7 (SyS_open+0x37/0x50)
#12 ffffffff81928782 (system_call_fastpath+0x16/0x1b)
Shadow bytes around the buggy address:
ffff8800359c9700: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd
ffff8800359c9780: fd fd fd fd fd fd fd fd fa fa fa fa fa fa fa fa
ffff8800359c9800: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
ffff8800359c9880: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
ffff8800359c9900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
=>ffff8800359c9980: 00 00 00 00 00 00 00 00 00 00 00 00 00 00[03]fb
ffff8800359c9a00: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
ffff8800359c9a80: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
ffff8800359c9b00: fa fa fa fa fa fa fa fa 00 00 00 00 00 00 00 00
ffff8800359c9b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffff8800359c9c00: 00 00 00 00 00 00 00 00 fa fa fa fa fa fa fa fa
Shadow byte legend (one shadow byte represents 8 application bytes):
Addressable: 00
Partially addressable: 01 02 03 04 05 06 07
Heap redzone: fa
Heap kmalloc redzone: fb
Freed heap region: fd
Shadow gap: fe
The out-of-bounds access happens on 'parser->buffer[parser->idx] = 0;'
Although the crash happened in ftrace_regex_open() the real bug
occurred in trace_get_user() where there's an incrementation to
parser->idx without a check against the size. The way it is triggered
is if userspace sends in 128 characters (EVENT_BUF_SIZE + 1), the loop
that reads the last character stores it and then breaks out because
there is no more characters. Then the last character is read to determine
what to do next, and the index is incremented without checking size.
Then the caller of trace_get_user() usually nulls out the last character
with a zero, but since the index is equal to the size, it writes a nul
character after the allocated space, which can corrupt memory.
Luckily, only root user has write access to this file.
Link: http://lkml.kernel.org/r/20131009222323.04fd1a0d@gandalf.local.home
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
sysfs_get_uname() is erroneously declared as returning size_t even
though it may return a negative value, specifically -EINVAL. Its
callers then check whether its return value is less than zero and indeed
that is never the case for size_t.
This patch changes sysfs_get_uname() to return ssize_t and makes sure
its callers use ssize_t accordingly.
Signed-off-by: Patrick Palka <patrick@parcs.ath.cx>
[jstultz: Didn't apply cleanly, as a similar partial fix was also applied
so had to resolve the collisions]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Fedora Ruby maintainer reported latest Ruby doesn't work on Fedora Rawhide
on ARM. (http://bugs.ruby-lang.org/issues/9008)
Because of, commit 1c6b39ad3f (alarmtimers: Return -ENOTSUPP if no
RTC device is present) intruduced to return ENOTSUPP when
clock_get{time,res} can't find a RTC device. However this is incorrect.
First, ENOTSUPP isn't exported to userland (ENOTSUP or EOPNOTSUP are the
closest userland equivlents).
Second, Posix and Linux man pages agree that clock_gettime and
clock_getres should return EINVAL if clk_id argument is invalid.
While the arugment that the clockid is valid, but just not supported
on this hardware could be made, this is just a technicality that
doesn't help userspace applicaitons, and only complicates error
handling.
Thus, this patch changes the code to use EINVAL.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: stable <stable@vger.kernel.org> #3.0 and up
Reported-by: Vit Ondruch <v.ondruch@tiscali.cz>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
[jstultz: Tweaks to commit message to include full rational]
Signed-off-by: John Stultz <john.stultz@linaro.org>
The snapshot_data structure used internally by the hibernate user
space interface code in user.c has three char fields that are used
to store boolean values. Change their data type to bool and use
true and false instead of 1 and 0, respectively, in assignments
involving those fields.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Commit 040a0a37 ("mutex: Add support for wound/wait style locks")
used "!__builtin_constant_p(p == NULL)" but gcc 3.x cannot
handle such expression correctly, leading to boot failure when
built with CONFIG_DEBUG_MUTEXES=y.
Fix it by explicitly passing a bool which tells whether p != NULL
or not.
[ PeterZ: This is a sad patch, but provided it actually generates
similar code I suppose its the best we can do bar whole
sale deprecating gcc-3. ]
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Cc: peterz@infradead.org
Cc: imirkin@alum.mit.edu
Cc: daniel.vetter@ffwll.ch
Cc: robdclark@gmail.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/201310171945.AGB17114.FSQVtHOJFOOFML@I-love.SAKURA.ne.jp
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Rather than hard-lock the kernel, dump the suspend/resume thread stack
and panic() to capture a message in pstore when a driver takes too long
to suspend/resume. Default suspend/resume watchdog timeout is set to 12
seconds to be longer than the usbhid 10 second timeout, but could be
changed at compile time.
Exclude from the watchdog the time spent waiting for children that
are resumed asynchronously and time every device, whether or not they
resumed synchronously.
This patch is targeted for mobile devices where a suspend/resume lockup
could cause a system reboot. Information about failing device can be
retrieved in subsequent boot session by mounting pstore and inspecting
the log. Laptops with EFI-enabled pstore could also benefit from
this feature.
The hardware watchdog timer is likely suspended during this time and
couldn't be relied upon. The soft-lockup detector would eventually tell
that tasks are not scheduled, but would provide little context as to why.
The patch hence uses system timer and assumes it is still active while the
devices are suspended/resumed.
This feature can be enabled/disabled during kernel configuration.
This change is based on earlier work by San Mehat.
Signed-off-by: Benoit Goby <benoit@android.com>
Signed-off-by: Zoran Markovic <zoran.markovic@linaro.org>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Let kstrtos32_from_user() do the necessary calls and checks.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
For now, we disable the extended MMAP record support (MMAP2).
We have identified cases where it would not report the correct mapping
information, clone(VM_CLONE) but with separate pids. We will revisit
the support once we find a solution for this case.
The patch changes the kernel to return EINVAL if attr->mmap2 is set. The
patch also modifies the perf tool to use regular PERF_RECORD_MMAP for
synthetic events and it also prevents the tool from requesting
attr->mmap2 mode because the kernel would reject it.
The support will be revisited once the kenrel interface is updated.
In V2, we reduce the patch to the strict minimum.
In V3, we avoid calling perf_event_open() with mmap2 set because we know
it will fail and require fallback retry.
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131017173215.GA8820@quad
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This adds the .init_array section as yet another section with constructors. This
is needed because gcc could add __gcov_init calls to .init_array or .ctors
section, depending on gcc (and binutils) version .
v2: - reuse mod->ctors for .init_array section for modules, because gcc uses
.ctors or .init_array, but not both at the same time
v3: - fail to load if that does happen somehow.
Signed-off-by: Frantisek Hrbata <fhrbata@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Turn the initial value of sysctl kernel.sysrq (SYSRQ_DEFAULT_ENABLE)
into a Kconfig variable.
Original version by Bastian Blank <waldi@debian.org>.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add the new helper, prepare_to_wait_event() which should only be used
by ___wait_event().
prepare_to_wait_event() returns -ERESTARTSYS if signal_pending_state()
is true, otherwise it does prepare_to_wait/exclusive. This allows to
uninline the signal-pending checks in wait_event*() macros.
Also, it can initialize wait->private/func. We do not care if they were
already initialized, the values are the same. This also shaves a couple
of insns from the inlined code.
This obviously makes prepare_*() path a little bit slower, but we are
likely going to sleep anyway, so I think it makes sense to shrink .text:
text data bss dec hex filename
===================================================
before: 5126092 2959248 10117120 18202460 115bf5c vmlinux
after: 5124618 2955152 10117120 18196890 115a99a vmlinux
on my build.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131007161824.GA29757@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Remove get_online_cpus() usage from the scheduler; there's 4 sites that
use it:
- sched_init_smp(); where its completely superfluous since we're in
'early' boot and there simply cannot be any hotplugging.
- sched_getaffinity(); we already take a raw spinlock to protect the
task cpus_allowed mask, this disables preemption and therefore
also stabilizes cpu_online_mask as that's modified using
stop_machine. However switch to active mask for symmetry with
sched_setaffinity()/set_cpus_allowed_ptr(). We guarantee active
mask stability by inserting sync_rcu/sched() into _cpu_down.
- sched_setaffinity(); we don't appear to need get_online_cpus()
either, there's two sites where hotplug appears relevant:
* cpuset_cpus_allowed(); for the !cpuset case we use possible_mask,
for the cpuset case we hold task_lock, which is a spinlock and
thus for mainline disables preemption (might cause pain on RT).
* set_cpus_allowed_ptr(); Holds all scheduler locks and thus has
preemption properly disabled; also it already deals with hotplug
races explicitly where it releases them.
- migrate_swap(); we can make stop_two_cpus() do the heavy lifting for
us with a little trickery. By adding a sync_sched/rcu() after the
CPU_DOWN_PREPARE notifier we can provide preempt/rcu guarantees for
cpu_active_mask. Use these to validate that both our cpus are active
when queueing the stop work before we queue the stop_machine works
for take_cpu_down().
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: http://lkml.kernel.org/r/20131011123820.GV3081@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is a subtle race in migrate_swap, when task P, on CPU A, decides to swap
places with task T, on CPU B.
Task P:
- call migrate_swap
Task T:
- go to sleep, removing itself from the runqueue
Task P:
- double lock the runqueues on CPU A & B
Task T:
- get woken up, place itself on the runqueue of CPU C
Task P:
- see that task T is on a runqueue, and pretend to remove it
from the runqueue on CPU B
Now CPUs B & C both have corrupted scheduler data structures.
This patch fixes it, by holding the pi_lock for both of the tasks
involved in the migrate swap. This prevents task T from waking up,
and placing itself onto another runqueue, until after migrate_swap
has released all locks.
This means that, when migrate_swap checks, task T will be either
on the runqueue where it was originally seen, or not on any
runqueue at all. Migrate_swap deals correctly with of those cases.
Tested-by: Joe Mario <jmario@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: hannes@cmpxchg.org
Cc: aarcange@redhat.com
Cc: srikar@linux.vnet.ibm.com
Cc: tglx@linutronix.de
Cc: hpa@zytor.com
Link: http://lkml.kernel.org/r/20131010181722.GO13848@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Both Anjana and Eunki reported a stall in the while_each_thread loop
in cgroup_attach_task().
It's because, when we attach a single thread to a cgroup, if the cgroup
is exiting or is already in that cgroup, we won't break the loop.
If the task is already in the cgroup, the bug can lead to another thread
being attached to the cgroup unexpectedly:
# echo 5207 > tasks
# cat tasks
5207
# echo 5207 > tasks
# cat tasks
5207
5215
What's worse, if the task to be attached isn't the leader of the thread
group, we might never exit the loop, hence cpu stall. Thanks for Oleg's
analysis.
This bug was introduced by commit 081aa458c3
("cgroup: consolidate cgroup_attach_task() and cgroup_attach_proc()")
[ lizf: - fixed the first continue, pointed out by Oleg,
- rewrote changelog. ]
Cc: <stable@vger.kernel.org> # 3.9+
Reported-by: Eunki Kim <eunki_kim@samsung.com>
Reported-by: Anjana V Kumar <anjanavk12@gmail.com>
Signed-off-by: Anjana V Kumar <anjanavk12@gmail.com>
Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The balance parameter was removed by 23f0d20 ("sched: Factor out
code to should_we_balance()", 2013-08-06).
Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381400433-2030-1-git-send-email-artagnon@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We can enable/disable timer statistics collection via:
echo [1|0] > /proc/timers_stats
and it would be nice if apps had the ability to check
what the current collection status is.
This patch adds a 'Collection: active/inactive' line to display the
current timer collection status.
Also bump up the timer stats version to v0.3.
Signed-off-by: Dong Zhu <bluezhudong@gmail.com>
Cc: John Stultz <john.stultz@linaro.org>
Link: http://lkml.kernel.org/r/20131010075618.GH2139@zhudong.nay.redhat.com
[ Improved the changelog and the code. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull more timekeeping items for v3.13 from John Stultz:
* Small cleanup in the clocksource code.
* Fix for rtc-pl031 to let it work with alarmtimers.
* Move arm64 to using the generic sched_clock framework & resulting
cleanup in the generic sched_clock code.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The current "help" that comes out of the snapshot file when it is
not allocated looks like this:
# * Snapshot is freed *
#
# Snapshot commands:
# echo 0 > snapshot : Clears and frees snapshot buffer
# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.
# Takes a snapshot of the main buffer.
# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)
# (Doesn't have to be '2' works with any number that
# is not a '0' or '1')
Echo 2 says that it does not allocate the buffer, which is correct,
but to be more consistent with "echo 0" it should also state
that it does not free.
Link: http://lkml.kernel.org/r/20130914045916.GA4243@udknight
Signed-off-by: Wang YanQing <udknight@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Nobody is using sched_clock_func() anymore now that sched_clock
supports up to 64 bits. Remove the hook so that new code only
uses sched_clock_register().
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Reflow the function a bit because GCC gets confused:
kernel/sched/fair.c: In function ‘task_numa_fault’:
kernel/sched/fair.c:1448:3: warning: ‘my_grp’ may be used uninitialized in this function [-Wmaybe-uninitialized]
kernel/sched/fair.c:1463:27: note: ‘my_grp’ was declared here
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-6ebt6x7u64pbbonq1khqu2z9@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Short spikes of CPU load can lead to a task being migrated
away from its preferred node for temporary reasons.
It is important that the task is migrated back to where it
belongs, in order to avoid migrating too much memory to its
new location, and generally disturbing a task's NUMA location.
This patch fixes NUMA placement for 4 specjbb instances on
a 4 node system. Without this patch, things take longer to
converge, and processes are not always completely on their
own node.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-64-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
As Peter says "If you're going to hold locks you can also do away with all
that atomic_long_*() nonsense". Lock aquisition moved slightly to protect
the updates.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-63-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Shared faults can lead to lots of unnecessary page migrations,
slowing down the system, and causing private faults to hit the
per-pgdat migration ratelimit.
This patch adds sysctl numa_balancing_migrate_deferred, which specifies
how many shared page migrations to skip unconditionally, after each page
migration that is skipped because it is a shared fault.
This reduces the number of page migrations back and forth in
shared fault situations. It also gives a strong preference to
the tasks that are already running where most of the memory is,
and to moving the other tasks to near the memory.
Testing this with a much higher scan rate than the default
still seems to result in fewer page migrations than before.
Memory seems to be somewhat better consolidated than previously,
with multi-instance specjbb runs on a 4 node system.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-62-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
With the scan rate code working (at least for multi-instance specjbb),
the large hammer that is "sched: Do not migrate memory immediately after
switching node" can be replaced with something smarter. Revert temporarily
migration disabling and all traces of numa_migrate_seq.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-61-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
With scan rate adaptions based on whether the workload has properly
converged or not there should be no need for the scan period reset
hammer. Get rid of it.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-60-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Adjust numa_scan_period in task_numa_placement, depending on how much
useful work the numa code can do. The more local faults there are in a
given scan window the longer the period (and hence the slower the scan rate)
during the next window. If there are excessive shared faults then the scan
period will decrease with the amount of scaling depending on whether the
ratio of shared/private faults. If the preferred node changes then the
scan rate is reset to recheck if the task is properly placed.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-59-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Scan rate is altered based on whether shared/private faults dominated.
task_numa_group() may detect false sharing but that information is not
taken into account when adapting the scan rate. Take it into account.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-58-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Due to the way the pid is truncated, and tasks are moved between
CPUs by the scheduler, it is possible for the current task_numa_fault
to group together tasks that do not actually share memory together.
This patch adds a few easy sanity checks to task_numa_fault, joining
tasks together if they share the same tsk->mm, or if the fault was on
a page with an elevated mapcount, in a shared VMA.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-57-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch classifies scheduler domains and runqueues into types depending
the number of tasks that are about their NUMA placement and the number
that are currently running on their preferred node. The types are
regular: There are tasks running that do not care about their NUMA
placement.
remote: There are tasks running that care about their placement but are
currently running on a node remote to their ideal placement
all: No distinction
To implement this the patch tracks the number of tasks that are optimally
NUMA placed (rq->nr_preferred_running) and the number of tasks running
that care about their placement (nr_numa_running). The load balancer
uses this information to avoid migrating idea placed NUMA tasks as long
as better options for load balancing exists. For example, it will not
consider balancing between a group whose tasks are all perfectly placed
and a group with remote tasks.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1381141781-10992-56-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch separately considers task and group affinities when
searching for swap candidates during NUMA placement. If tasks
are part of the same group, or no group at all, the task weights
are considered.
Some hysteresis is added to prevent tasks within one group from
getting bounced between NUMA nodes due to tiny differences.
If tasks are part of different groups, the code compares group
weights, in order to favor grouping task groups together.
The patch also changes the group weight multiplier to be the
same as the task weight multiplier, since the two are no longer
added up like before.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-55-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch separately considers task and group affinities when searching
for swap candidates during task NUMA placement. If tasks are not part of
a group or the same group then the task weights are considered.
Otherwise the group weights are compared.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-54-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Having multiple tasks in a group go through task_numa_placement
simultaneously can lead to a task picking a wrong node to run on, because
the group stats may be in the middle of an update. This patch avoids
parallel updates by holding the numa_group lock during placement
decisions.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-52-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
It is possible for a task in a numa group to call exec, and
have the new (unrelated) executable inherit the numa group
association from its former self.
This has the potential to break numa grouping, and is trivial
to fix.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-51-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch uses the fraction of faults on a particular node for both task
and group, to figure out the best node to place a task. If the task and
group statistics disagree on what the preferred node should be then a full
rescan will select the node with the best combined weight.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-50-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
A newly spawned thread inside a process should stay on the same
NUMA node as its parent. This prevents processes from being "torn"
across multiple NUMA nodes every time they spawn a new thread.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-49-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
And here's a little something to make sure not the whole world ends up
in a single group.
As while we don't migrate shared executable pages, we do scan/fault on
them. And since everybody links to libc, everybody ends up in the same
group.
Suggested-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1381141781-10992-47-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
It is desirable to model from userspace how the scheduler groups tasks
over time. This patch adds an ID to the numa_group and reports it via
/proc/PID/status.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-45-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While parallel applications tend to align their data on the cache
boundary, they tend not to align on the page or THP boundary.
Consequently tasks that partition their data can still "false-share"
pages presenting a problem for optimal NUMA placement.
This patch uses NUMA hinting faults to chain tasks together into
numa_groups. As well as storing the NID a task was running on when
accessing a page a truncated representation of the faulting PID is
stored. If subsequent faults are from different PIDs it is reasonable
to assume that those two tasks share a page and are candidates for
being grouped together. Note that this patch makes no scheduling
decisions based on the grouping information.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1381141781-10992-44-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Change the per page last fault tracking to use cpu,pid instead of
nid,pid. This will allow us to try and lookup the alternate task more
easily. Note that even though it is the cpu that is store in the page
flags that the mpol_misplaced decision is still based on the node.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1381141781-10992-43-git-send-email-mgorman@suse.de
[ Fixed build failure on 32-bit systems. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The load balancer will spread workloads across multiple NUMA nodes,
in order to balance the load on the system. This means that sometimes
a task's preferred node has available capacity, but moving the task
there will not succeed, because that would create too large an imbalance.
In that case, other NUMA nodes need to be considered.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-42-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
A tasks preferred node is selected based on the number of faults
recorded for a node but the actual task_numa_migate() conducts a global
search regardless of the preferred nid. This patch checks if the
preferred nid has capacity and if so, searches for a CPU within that
node. This avoids a global search when the preferred node is not
overloaded.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-41-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch implements a system-wide search for swap/migration candidates
based on total NUMA hinting faults. It has a balance limit, however it
doesn't properly consider total node balance.
In the old scheme a task selected a preferred node based on the highest
number of private faults recorded on the node. In this scheme, the preferred
node is based on the total number of faults. If the preferred node for a
task changes then task_numa_migrate will search the whole system looking
for tasks to swap with that would improve both the overall compute
balance and minimise the expected number of remote NUMA hinting faults.
Not there is no guarantee that the node the source task is placed
on by task_numa_migrate() has any relationship to the newly selected
task->numa_preferred_nid due to compute overloading.
Signed-off-by: Mel Gorman <mgorman@suse.de>
[ Do not swap with tasks that cannot run on source cpu]
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
[ Fixed compiler warning on UP. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-40-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Use the new stop_two_cpus() to implement migrate_swap(), a function that
flips two tasks between their respective cpus.
I'm fairly sure there's a less crude way than employing the stop_two_cpus()
method, but everything I tried either got horribly fragile and/or complex. So
keep it simple for now.
The notable detail is how we 'migrate' tasks that aren't runnable
anymore. We'll make it appear like we migrated them before they went to
sleep. The sole difference is the previous cpu in the wakeup path, so we
override this.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/1381141781-10992-39-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Introduce stop_two_cpus() in order to allow controlled swapping of two
tasks. It repurposes the stop_machine() state machine but only stops
the two cpus which we can do with on-stack structures and avoid
machine wide synchronization issues.
The ordering of CPUs is important to avoid deadlocks. If unordered then
two cpus calling stop_two_cpus on each other simultaneously would attempt
to queue in the opposite order on each CPU causing an AB-BA style deadlock.
By always having the lowest number CPU doing the queueing of works, we can
guarantee that works are always queued in the same order, and deadlocks
are avoided.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
[ Implemented deadlock avoidance. ]
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/1381141781-10992-38-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
NUMA hinting faults will not migrate a shared executable page mapped by
multiple processes on the grounds that the data is probably in the CPU
cache already and the page may just bounce between tasks running on multipl
nodes. Even if the migration is avoided, there is still the overhead of
trapping the fault, updating the statistics, making scheduler placement
decisions based on the information etc. If we are never going to migrate
the page, it is overhead for no gain and worse a process may be placed on
a sub-optimal node for shared executable pages. This patch avoids trapping
faults for shared libraries entirely.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-36-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a task is already running on its preferred node, increment
numa_migrate_seq to indicate that the task is settled if migration is
temporarily disabled, and memory should migrate towards it.
Signed-off-by: Rik van Riel <riel@redhat.com>
[ Only increment migrate_seq if migration temporarily disabled. ]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-35-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a preferred node is selected for a tasks there is an attempt to migrate
the task to a CPU there. This may fail in which case the task will only
migrate if the active load balancer takes action. This may never happen if
the conditions are not right. This patch will check at NUMA hinting fault
time if another attempt should be made to migrate the task. It will only
make an attempt once every five seconds.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-34-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch replaces find_idlest_cpu_node with task_numa_find_cpu.
find_idlest_cpu_node has two critical limitations. It does not take the
scheduling class into account when calculating the load and it is unsuitable
for using when comparing loads between NUMA nodes.
task_numa_find_cpu uses similar load calculations to wake_affine() when
selecting the least loaded CPU within a scheduling domain common to the
source and destimation nodes. It avoids causing CPU load imbalances in
the machine by refusing to migrate if the relative load on the target
CPU is higher than the source CPU.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-33-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is a 90% regression observed with a large Oracle performance test
on a 4 node system. Profiles indicated that the overhead was due to
contention on sp_lock when looking up shared memory policies. These
policies do not have the appropriate flags to allow them to be
automatically balanced so trapping faults on them is pointless. This
patch skips VMAs that do not have MPOL_F_MOF set.
[riel@redhat.com: Initial patch]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-and-tested-by: Joe Mario <jmario@redhat.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-32-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The load balancer can move tasks between nodes and does not take NUMA
locality into account. With automatic NUMA balancing this may result in the
tasks working set being migrated to the new node. However, as the fault
buffer will still store faults from the old node the schduler may decide to
reset the preferred node and migrate the task back resulting in more
migrations.
The ideal would be that the scheduler did not migrate tasks with a heavy
memory footprint but this may result nodes being overloaded. We could
also discard the fault information on task migration but this would still
cause all the tasks working set to be migrated. This patch simply avoids
migrating the memory for a short time after a task is migrated.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-31-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Ideally it would be possible to distinguish between NUMA hinting faults that
are private to a task and those that are shared. If treated identically
there is a risk that shared pages bounce between nodes depending on
the order they are referenced by tasks. Ultimately what is desirable is
that task private pages remain local to the task while shared pages are
interleaved between sharing tasks running on different nodes to give good
average performance. This is further complicated by THP as even
applications that partition their data may not be partitioning on a huge
page boundary.
To start with, this patch assumes that multi-threaded or multi-process
applications partition their data and that in general the private accesses
are more important for cpu->memory locality in the general case. Also,
no new infrastructure is required to treat private pages properly but
interleaving for shared pages requires additional infrastructure.
To detect private accesses the pid of the last accessing task is required
but the storage requirements are a high. This patch borrows heavily from
Ingo Molnar's patch "numa, mm, sched: Implement last-CPU+PID hash tracking"
to encode some bits from the last accessing task in the page flags as
well as the node information. Collisions will occur but it is better than
just depending on the node information. Node information is then used to
determine if a page needs to migrate. The PID information is used to detect
private/shared accesses. The preferred NUMA node is selected based on where
the maximum number of approximately private faults were measured. Shared
faults are not taken into consideration for a few reasons.
First, if there are many tasks sharing the page then they'll all move
towards the same node. The node will be compute overloaded and then
scheduled away later only to bounce back again. Alternatively the shared
tasks would just bounce around nodes because the fault information is
effectively noise. Either way accounting for shared faults the same as
private faults can result in lower performance overall.
The second reason is based on a hypothetical workload that has a small
number of very important, heavily accessed private pages but a large shared
array. The shared array would dominate the number of faults and be selected
as a preferred node even though it's the wrong decision.
The third reason is that multiple threads in a process will race each
other to fault the shared page making the fault information unreliable.
Signed-off-by: Mel Gorman <mgorman@suse.de>
[ Fix complication error when !NUMA_BALANCING. ]
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-30-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
task_numa_work skips small VMAs. At the time the logic was to reduce the
scanning overhead which was considerable. It is a dubious hack at best.
It would make much more sense to cache where faults have been observed
and only rescan those regions during subsequent PTE scans. Remove this
hack as motivation to do it properly in the future.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-29-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
task_numa_placement checks current->mm but after buffers for faults
have already been uselessly allocated. Move the check earlier.
[peterz@infradead.org: Identified the problem]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-27-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Ideally it would be possible to distinguish between NUMA hinting faults
that are private to a task and those that are shared. This patch prepares
infrastructure for separately accounting shared and private faults by
allocating the necessary buffers and passing in relevant information. For
now, all faults are treated as private and detection will be introduced
later.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-26-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
A preferred node is selected based on the node the most NUMA hinting
faults was incurred on. There is no guarantee that the task is running
on that node at the time so this patch rescheules the task to run on
the most idle CPU of the selected node when selected. This avoids
waiting for the balancer to make a decision.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-25-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Just as "sched: Favour moving tasks towards the preferred node" favours
moving tasks towards nodes with a higher number of recorded NUMA hinting
faults, this patch resists moving tasks towards nodes with lower faults.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-24-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch favours moving tasks towards NUMA node that recorded a higher
number of NUMA faults during active load balancing. Ideally this is
self-reinforcing as the longer the task runs on that node, the more faults
it should incur causing task_numa_placement to keep the task running on that
node. In reality a big weakness is that the nodes CPUs can be overloaded
and it would be more efficient to queue tasks on an idle node and migrate
to the new node. This would require additional smarts in the balancer so
for now the balancer will simply prefer to place the task on the preferred
node for a PTE scans which is controlled by the numa_balancing_settle_count
sysctl. Once the settle_count number of scans has complete the schedule
is free to place the task on an alternative node if the load is imbalanced.
[srikar@linux.vnet.ibm.com: Fixed statistics]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
[ Tunable and use higher faults instead of preferred. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-23-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
NUMA hinting fault counts and placement decisions are both recorded in the
same array which distorts the samples in an unpredictable fashion. The values
linearly accumulate during the scan and then decay creating a sawtooth-like
pattern in the per-node counts. It also means that placement decisions are
time sensitive. At best it means that it is very difficult to state that
the buffer holds a decaying average of past faulting behaviour. At worst,
it can confuse the load balancer if it sees one node with an artifically high
count due to very recent faulting activity and may create a bouncing effect.
This patch adds a second array. numa_faults stores the historical data
which is used for placement decisions. numa_faults_buffer holds the
fault activity during the current scan window. When the scan completes,
numa_faults decays and the values from numa_faults_buffer are copied
across.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-22-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch selects a preferred node for a task to run on based on the
NUMA hinting faults. This information is later used to migrate tasks
towards the node during balancing.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-21-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch tracks what nodes numa hinting faults were incurred on.
This information is later used to schedule a task on the node storing
the pages most frequently faulted by the task.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-20-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
NUMA PTE scanning slows if a NUMA hinting fault was trapped and no page
was migrated. For long-lived but idle processes there may be no faults
but the scan rate will be high and just waste CPU. This patch will slow
the scan rate for processes that are not trapping faults.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-19-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The NUMA PTE scan rate is controlled with a combination of the
numa_balancing_scan_period_min, numa_balancing_scan_period_max and
numa_balancing_scan_size. This scan rate is independent of the size
of the task and as an aside it is further complicated by the fact that
numa_balancing_scan_size controls how many pages are marked pte_numa and
not how much virtual memory is scanned.
In combination, it is almost impossible to meaningfully tune the min and
max scan periods and reasoning about performance is complex when the time
to complete a full scan is is partially a function of the tasks memory
size. This patch alters the semantic of the min and max tunables to be
about tuning the length time it takes to complete a scan of a tasks occupied
virtual address space. Conceptually this is a lot easier to understand. There
is a "sanity" check to ensure the scan rate is never extremely fast based on
the amount of virtual memory that should be scanned in a second. The default
of 2.5G seems arbitrary but it is to have the maximum scan rate after the
patch roughly match the maximum scan rate before the patch was applied.
On a similar note, numa_scan_period is in milliseconds and not
jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies
to numa_scan_period means that the rate scanning slows depends on HZ which
is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Scan delay logic and resets are currently initialised to start scanning
immediately instead of delaying properly. Initialise them properly at
fork time and catch when a new mm has been allocated.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-17-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Al Viro