Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Sysbench thinks SD_BALANCE_WAKE is too agressive and kbuild doesn't
really mind too much, SD_BALANCE_NEWIDLE picks up most of the
slack.
On a dual socket, quad core, dual thread nehalem system:
sysbench (--num_threads=16):
SD_BALANCE_WAKE-: 13982 tx/s
SD_BALANCE_WAKE+: 15688 tx/s
kbuild (-j16):
SD_BALANCE_WAKE-: 47.648295846 seconds time elapsed ( +- 0.312% )
SD_BALANCE_WAKE+: 47.608607360 seconds time elapsed ( +- 0.026% )
(same within noise)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This is necessary to get ftrace syscall tracing working again.. a fairly
trivial and mechanical change. The one benefit is that this can also be
enabled on sh64, despite not having its own ftrace port.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
If we're looking to place a new task, we might as well find the
idlest position _now_, not 1 tick ago.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Make the idle balancer more agressive, to improve a
x264 encoding workload provided by Jason Garrett-Glaser:
NEXT_BUDDY NO_LB_BIAS
encoded 600 frames, 252.82 fps, 22096.60 kb/s
encoded 600 frames, 250.69 fps, 22096.60 kb/s
encoded 600 frames, 245.76 fps, 22096.60 kb/s
NO_NEXT_BUDDY LB_BIAS
encoded 600 frames, 344.44 fps, 22096.60 kb/s
encoded 600 frames, 346.66 fps, 22096.60 kb/s
encoded 600 frames, 352.59 fps, 22096.60 kb/s
NO_NEXT_BUDDY NO_LB_BIAS
encoded 600 frames, 425.75 fps, 22096.60 kb/s
encoded 600 frames, 425.45 fps, 22096.60 kb/s
encoded 600 frames, 422.49 fps, 22096.60 kb/s
Peter pointed out that this is better done via newidle_idx,
not via LB_BIAS, newidle balancing should look for where
there is load _now_, not where there was load 2 ticks ago.
Worst-case latencies are improved as well as no buddies
means less vruntime spread. (as per prior lkml discussions)
This change improves kbuild-peak parallelism as well.
Reported-by: Jason Garrett-Glaser <darkshikari@gmail.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1253011667.9128.16.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When merging select_task_rq_fair() and sched_balance_self() we lost
the use of wake_idx, restore that and set them to 0 to make wake
balancing more aggressive.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The problem with wake_idle() is that is doesn't respect things like
cpu_power, which means it doesn't deal well with SMT nor the recent
RT interaction.
To cure this, it needs to do what sched_balance_self() does, which
leads to the possibility of merging select_task_rq_fair() and
sched_balance_self().
Modify sched_balance_self() to:
- update_shares() when walking up the domain tree,
(it only called it for the top domain, but it should
have done this anyway), which allows us to remove
this ugly bit from try_to_wake_up().
- do wake_affine() on the smallest domain that contains
both this (the waking) and the prev (the wakee) cpu for
WAKE invocations.
Then use the top-down balance steps it had to replace wake_idle().
This leads to the dissapearance of SD_WAKE_BALANCE and
SD_WAKE_IDLE_FAR, with SD_WAKE_IDLE replaced with SD_BALANCE_WAKE.
SD_WAKE_AFFINE needs SD_BALANCE_WAKE to be effective.
Touch all topology bits to replace the old with new SD flags --
platforms might need re-tuning, enabling SD_BALANCE_WAKE
conditionally on a NUMA distance seems like a good additional
feature, magny-core and small nehalem systems would want this
enabled, systems with slow interconnects would not.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Early clock initialization sets up PLL/FLL values for optimal RF
behaviour. As this relationship is presently undocumented, we document
this in the script so the rationale is apparent.
Signed-off-by: Kuninori Morimoto <morimoto.kuninori@renesas.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
After KYCR2 is set, udelay might become necessary if there are only a
small number of keys attached. This patch introduces an optional delay
through the platform data to address this problem.
Signed-off-by: Kuninori Morimoto <morimoto.kuninori@renesas.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
when you use romImage on EcoVec24, 1st Linux will enable USB device.
But no-one disable it.
So re-started Linux will get interrupt before USB driver is attached.
This patch disable USB device at first
Signed-off-by: Kuninori Morimoto <morimoto.kuninori@renesas.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
romimage macros which are used in kfr2r09 is very useful for other board.
This patch divides kfr2r09's romimage.h into
romimage-macros and partner-jet-setup.
Signed-off-by: Kuninori Morimoto <morimoto.kuninori@renesas.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
This was #define'd as 0 on all platforms, so let's get rid of it.
This change makes pci_scan_slot() slightly easier to read.
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Tony Luck <tony.luck@intel.com>
Cc: David Howells <dhowells@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
Acked-by: Russell King <linux@arm.linux.org.uk>
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This supported all DMA channels, and it was tested in SH7722,
SH7780, SH7785 and SH7763.
This can not use with SH DMA API.
Signed-off-by: Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
Reviewed-by: Matt Fleming <matt@console-pimps.org>
Acked-by: Maciej Sosnowski <maciej.sosnowski@intel.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This fixes up the kmap_coherent/kunmap_coherent() interface for recent
changes both in the page fault path and the shared cache flushers, as
well as adding in some optimizations.
One of the key things to note here is that the TLB flush itself is
deferred until the unmap, and the call in to update_mmu_cache() itself
goes away, relying on the regular page fault path to handle the lazy
dcache writeback if necessary.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
The kgdb stub has traditionally tied in to the NMI slot, and manually
handled debounce. Now that we have a generic way to do this instead, all
of the stub-specific debounce silliness can be killed off.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
This implements support for NMI debugging that was shamelessly copied
from the avr32 port. A bit of special magic is needed in the interrupt
exception path given that the NMI exception handler is stubbed in to the
regular exception handling table despite being reported in INTEVT. So we
mangle the lookup and kick off an EXPEVT-style exception dispatch from
the INTEVT path for exceptions that do_IRQ() has no chance of handling.
As a result, we also drop the evt2irq() conversion from the do_IRQ() path
and just do it in assembly.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Some unaligned accesses are completely expected. For example, the
trapped_io code uses the unaligned access fixup code path so there's no
need to warn about having to fixup the unaligned access.
Signed-off-by: Matt Fleming <matt@console-pimps.org>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
The method of ETHER_LINK pin is board dependence.
This patch adding paramters are:
- no_ether_link : If set to 1, do not use ETHER_LINK
- ether_link_active_low : If set to 1, ETHER_LINK is active low.
Signed-off-by: Yoshihiro Shimoda <shimoda.yoshihiro@renesas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is supposed to be the equivalent of __NR_syscalls, not
__NR_syscalls -1. The x86 code this was based on had simply fallen
out of sync at the time this was implemented. Fix it up now.
As a result, tracing of __NR_perf_counter_open works as advertised.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
sys_cacheflush should return with EINVAL if the cache parameter is not
one of ICACHE, DCACHE or BCACHE.
So, we need to include 0 in the first check.
It also adds the three definitions above as wrapper of the existent macros.
PS: ltp cacheflush01 test now passes.
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Adds a system call to allow user code to flush code from the cache.
You can use instructions for the data side, but the iside can
only be done by a flush ROM which really only works with a direct
mapped cache. The later SH4's have 2 way Iside, so this call allows
a portable way to flush the cache.
Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Reading from the ROM is not a good idea as it could disturb some
flash operation that it is in progress.
Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
The SH instruction set has several instructions which accept an 8 bit
immediate operand. For logical instructions this operand is zero extended,
for arithmetic instructions the operand is sign extended. After adding an
option to the assembler to check this, it was found that several pieces
of assembly code were assuming this behaviour, and in one case
getting it wrong.
So this patch explicitly sign extends any immediate operands, which makes
it obvious what is happening, and fixes the one case which got it wrong.
Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
The synopsys PCI cell used in the later STMicro chips requires code to
be run in order to do IO cycles, rather than just memory mapping the IO
space. Rather than extending the existing SH infrastructure to allow
this, use the GENERIC_IOMAP implmentation to save re-inventing the
wheel.
This set of changes allows the SH to be built with GENERIC_IOMAP
enabled, it just ifdef's out the functions provided by the GENERIC_IOMAP
implementation, and provides a few required missing functions.
Signed-off-by: David McKay <david.mckay@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
This patch is V3 of the SuperH Mobile Runtime PM platform bus
implentation matching Rafael's Runtime PM v16.
The code gets invoked from the SuperH specific Runtime PM
platform bus functions that override the weak symbols for:
- platform_pm_runtime_suspend()
- platform_pm_runtime_resume()
- platform_pm_runtime_idle()
This Runtime PM implementation performs two levels of power
management. At the time of platform bus runtime suspend the
clock to the device is stopped instantly. Later on if all
devices within the power domain has their clocks stopped
then the device driver ->runtime_suspend() callbacks are
used to save hardware register state for each device.
Device driver ->runtime_suspend() calls are scheduled from
cpuidle context using platform_pm_runtime_suspend_idle().
When all devices have been fully suspended the processor
is allowed to enter deep sleep from cpuidle.
The runtime resume operation turns on clocks and also
restores registers if needed. It is worth noting that the
devices start in a suspended state and the device driver
is responsible for calling runtime resume before accessing
the actual hardware.
In this particular platform bus implementation runtime
resume is not allowed from interrupt context. Runtime
suspend is however allowed from interrupt context as
long as the synchronous functions are avoided.
[ updated for v17 -- PFM. ]
Signed-off-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
sh64 does not yet support GENERIC_BUG, but still wants unwinder support.
Alias UNWINDER_BUG and UNWINDER_BUG_ON to their BUG counterparts until
the conversion to GENERIC_BUG is completed.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
This simplifies the unwinder trap handling, dropping the use of the
special trapa vector and simply piggybacking on top of the BUG support. A
new BUGFLAG_UNWINDER is added for flagging the unwinder fault, before
continuing on with regular BUG dispatch.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Allow a DWARF register to have an undefined value. When applied to the
DWARF return address register this lets lets us label a function as
having no direct caller, e.g. kernel_thread_helper().
Signed-off-by: Matt Fleming <matt@console-pimps.org>
We can't assume that if we execute the unwinder code and the unwinder
was already running that it has faulted. Clearly two kernel threads can
invoke the unwinder at the same time and may be running simultaneously.
The previous approach used BUG() and BUG_ON() in the unwinder code to
detect whether the unwinder was incapable of unwinding the stack, and
that the next available unwinder should be used instead. A better
approach is to explicitly invoke a trap handler to switch unwinders when
the current unwinder cannot continue.
Signed-off-by: Matt Fleming <matt@console-pimps.org>
The handling of DW_CFA_val_offset ops was incorrectly using the
DWARF_REG_OFFSET flag but the register's value cannot be calculated
using the DWARF_REG_OFFSET method. Create a new flag to indicate that a
different method must be used to calculate the register's value even
though there is no implementation for DWARF_VAL_OFFSET yet; it's mainly
just a place holder.
Signed-off-by: Matt Fleming <matt@console-pimps.org>
Plug a memory leak in dwarf_unwinder_dump() where we didn't free the
memory that we had previously allocated for the DWARF frames and DWARF
registers.
Now is also a opportune time to implement our own mempool and kmem
cache. It's a good idea to have a certain number of frame and register
objects in reserve at all times, so that we are guaranteed to have our
allocation satisfied even when memory is scarce. Since we have pools to
allocate from we can implement the registers for each frame as a linked
list as opposed to a sparsely populated array. Whilst it's true that the
lookup time for a linked list is larger than for arrays, there's only
usually a maximum of 8 registers per frame. So the overhead isn't that
much of a concern.
Signed-off-by: Matt Fleming <matt@console-pimps.org>
This does a bit of rework for making the cache flushers SMP-aware. The
function pointer-based flushers are renamed to local variants with the
exported interface being commonly implemented and wrapping as necessary.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
All CPU-specific overloads are done at runtime now, so this common header
can go away and simply be folded back in to asm/ version.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Add a P1 jump to the the kfr2r09 romimage code. With this
patch applied the initial zImage assembly code will run
with instruction cache enabled.
Signed-off-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Add instruction cache and TLB invalidation code for the
the kfr2r09 romimage target.
Signed-off-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
When get_mmu_context() runs out of new ASIDs it flushes the TLB and
wraps around. Despite the fact the ASIDs are tracked per-CPU, a global
TLB flush was being used. Switch this over to a local one, as matches
the intent.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
As an excellent indicator of how much testing the DSP code gets, a couple
of rather glaring bugs in the DSP save/restore paths were found:
- In the DSP restore case a0 needs to be popped off before a0g,
or the value of a0g is clobbered by the MSB of a0 in the case
of sign extension.
- Beyond that, the save and restore orders were out of sync,
so this fixes that up as well. At the same time, we switch over
to using movs.l for both the save and restore of the general DSP
registers as opposed to using sts.l (which was initially put in
place to work around a bug in ancient binutils versions which
the kernel no longer supports).
Reported-by: Chee Soon Yip <yip.cheesoon@renesas.com>
Cc: Chu Lih Kwek <kwek.chulih@renesas.com>,
Cc: General Lai <general.lai@renesas.com>,
Cc: Robert Cozens <Robert.Cozens@renesas.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
While most platforms implement LED banks in sets of 8/16/32, some use
different configurations. This adds a LED mask to the heartbeat platform
data to allow platforms to constrain the bitmap, which is otherwise
derived from the register size.
Signed-off-by: Kuninori Morimoto <morimoto.kuninori@renesas.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
FLLFRQ setting is needed to use correct PLL clock for kfr2409.
Signed-off-by: Kuninori Morimoto <morimoto.kuninori@renesas.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
This moves the initialization over to an early_initcall(). This fixes up
some lockdep interaction issues. At the same time, kill off some
superfluous locking in the init path.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Also, remove the "fix" to DW_CFA_def_cfa_register where we reset the
frame's cfa_offset to 0. This action is incorrect when handling
DW_CFA_def_cfa_register as the DWARF spec specifically states that the
previous contents of cfa_offset should be used with the new
register. The reason that I thought cfa_offset should be reset to 0 was
because it was being assigned a bogus value prior to executing the
DW_CFA_def_cfa_register op. It turns out that the bogus cfa_offset value
came from interpreting .cfi_escape pseudo-ops (those used by the GNU
extensions) as CFA_DW_def_cfa ops.
Signed-off-by: Matt Fleming <matt@console-pimps.org>
Rusty Russell