Why removing pmu checking:
Since 3.2-rc1, when arch level event init is called, the event is already
connected to its PMU. Also, validate_event() is _only_ called by
validate_group() in event init, so there is no need of checking or
temporarily assigning event pmu during validate_group().
Why removing event state checking:
Events could be created in PERF_EVENT_STATE_OFF (attr->disabled == 1), when
these events go through this checking, validate_group() does dummy work.
But we do need to do group scheduling emulation for them in event init.
Again, validate_event() is _only_ called by validate_group().
Reference: http://www.spinics.net/lists/mips/msg42190.html
Signed-off-by: Deng-Cheng Zhu <dczhu@mips.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: David Daney <david.daney@cavium.com>
Cc: Eyal Barzilay <eyal@mips.com>
Cc: Zenon Fortuna <zenon@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/3108/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Port the following patch for ARM by Mark Rutland:
- 57ce9bb39b
ARM: 6902/1: perf: Remove erroneous check on active_events
When initialising a PMU, there is a check to protect against races with
other CPUs filling all of the available event slots. Since armpmu_add
checks that an event can be scheduled, we do not need to do this at
initialisation time. Furthermore the current code is broken because it
assumes that atomic_inc_not_zero will unconditionally increment
active_counts and then tries to decrement it again on failure.
This patch removes the broken, redundant code.
Signed-off-by: Deng-Cheng Zhu <dczhu@mips.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: David Daney <david.daney@cavium.com>
Cc: Eyal Barzilay <eyal@mips.com>
Cc: Zenon Fortuna <zenon@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/3106/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
MIPS licensees may want to modify performance counters to count extra
events. Also, now that the user is working on raw events, the manual is
being used for sure. And feeding unsupported events shouldn't cause
hardware failure and the like.
[ralf@linux-mips.org: performance events also being used in internal
performance evaluation and have a tendency to change as the micro-
architecture evolves, even for minor revisions that may not be
distinguishable by PrID. It's not very practicable to maintain a list
of all events and there is no real benefit.]
Signed-off-by: Deng-Cheng Zhu <dczhu@mips.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: David Daney <david.daney@cavium.com>
Cc: Eyal Barzilay <eyal@mips.com>
Cc: Zenon Fortuna <zenon@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/3107/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
People (Linus) objected to using -ENOSPC to signal not having enough
resources on the PMU to satisfy the request. Use -EINVAL.
Requested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-xv8geaz2zpbjhlx0svmpp28n@git.kernel.org
[ merged to newer kernel, fixed up MIPS impact ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The hard coded constants are moved to struct mips_pmu. All counter
register access move to the read_counter and write_counter function
pointers, which are set to either 32-bit or 64-bit access methods at
initialization time.
Many of the function pointers in struct mips_pmu were not needed as
there was only a single implementation, these were removed.
I couldn't figure out what made struct cpu_hw_events.msbs[] at all
useful, so I removed it too.
Some functions and other declarations were reordered to reduce the
need for forward declarations.
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
To: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2792/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The contents of arch/mips/kernel/perf_event.c and
arch/mips/kernel/perf_event_mipsxx.c were divided in a seemingly ad
hoc manner, with the first including the second.
I moved all the hardware counter support code to perf_event_mipsxx.c
and removed the gating #ifdefs to the Kconfig and Makefile.
Now perf_event.c contains only the callchain support, everything else
is in perf_event_mipsxx.c
There are no code changes, only moving of functions from one file to
the other, or removing empty unneeded functions.
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Dezhong Diao <dediao@cisco.com>
Cc: Gabor Juhos <juhosg@openwrt.org>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
To: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2791/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Get rid of a bunch of useless inline declarations, and join a bunch of
improperly split lines.
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
To: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2793/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Add a NODE level to the generic cache events which is used to measure
local vs remote memory accesses. Like all other cache events, an
ACCESS is HIT+MISS, if there is no way to distinguish between reads
and writes do reads only etc..
The below needs filling out for !x86 (which I filled out with
unsupported events).
I'm fairly sure ARM can leave it like that since it doesn't strike me as
an architecture that even has NUMA support. SH might have something since
it does appear to have some NUMA bits.
Sparc64, PowerPC and MIPS certainly want a good look there since they
clearly are NUMA capable.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: David Miller <davem@davemloft.net>
Cc: Anton Blanchard <anton@samba.org>
Cc: David Daney <ddaney@caviumnetworks.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1303508226.4865.8.camel@laptop
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This is the MIPS part of the following commits by Peter Zijlstra:
- a4eaf7f146
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
For MIPSXX, the stopped state is implemented in the way of 1.b as above.
- 33696fc0d1
perf: Per PMU disable
Changes perf_disable() into perf_pmu_disable().
- 24cd7f54a0
perf: Reduce perf_disable() usage
Since the current perf_disable() usage is only an optimization,
remove it for now. This eases the removal of the __weak
hw_perf_enable() interface.
- b0a873ebbf
perf: Register PMU implementations
Simple registration interface for struct pmu, this provides the
infrastructure for removing all the weak functions.
- 51b0fe3954
perf: Deconstify struct pmu
sed -ie 's/const struct pmu\>/struct pmu/g' `git grep -l "const struct pmu\>"`
Reported-by: Wu Zhangjin <wuzhangjin@gmail.com>
Acked-by: David Daney <ddaney@caviumnetworks.com>
Signed-off-by: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
To: a.p.zijlstra@chello.nl
To: fweisbec@gmail.com
To: will.deacon@arm.com
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: wuzhangjin@gmail.com
Cc: paulus@samba.org
Cc: mingo@elte.hu
Cc: acme@redhat.com
Cc: dengcheng.zhu@gmail.com
Cc: matt@console-pimps.org
Cc: sshtylyov@mvista.com
Cc: ddaney@caviumnetworks.com
Patchwork: http://patchwork.linux-mips.org/patch/2012/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This is the MIPS part of the following commit by Peter Zijlstra:
- e360adbe29
irq_work: Add generic hardirq context callbacks
Provide a mechanism that allows running code in IRQ context. It is
most useful for NMI code that needs to interact with the rest of the
system -- like wakeup a task to drain buffers.
Perf currently has such a mechanism, so extract that and provide it as
a generic feature, independent of perf so that others may also
benefit.
The IRQ context callback is generated through self-IPIs where
possible, or on architectures like powerpc the decrementer (the
built-in timer facility) is set to generate an interrupt immediately.
Architectures that don't have anything like this get to do with a
callback from the timer tick. These architectures can call
irq_work_run() at the tail of any IRQ handlers that might enqueue such
work (like the perf IRQ handler) to avoid undue latencies in
processing the work.
For MIPSXX, we need to call irq_work_run() at the tail of the perf IRQ
handler as described above.
Reported-by: Wu Zhangjin <wuzhangjin@gmail.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: David Daney <ddaney@caviumnetworks.com>
Signed-off-by: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
To: fweisbec@gmail.com
To: will.deacon@arm.com
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: paulus@samba.org
Cc: mingo@elte.hu
Cc: acme@redhat.com
Cc: matt@console-pimps.org
Cc: sshtylyov@mvista.com,
Patchwork: http://patchwork.linux-mips.org/patch/2011/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The perf hardware pmu got initialized at various points in the boot,
some before early_initcall() some after (notably arch_initcall).
The problem is that the NMI lockup detector is ran from early_initcall()
and expects the hardware pmu to be present.
Sanitize this by moving all architecture hardware pmu implementations to
initialize at early_initcall() and move the lockup detector to an explicit
initcall right after that.
Cc: paulus <paulus@samba.org>
Cc: davem <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1290707759.2145.119.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds the mipsxx Perf-events support based on the skeleton.
Generic hardware events and cache events are now fully implemented for
the 24K/34K/74K/1004K cores. To support other cores in mipsxx (such as
R10000/SB1), the generic hardware event tables and cache event tables
need to be filled out. To support other CPUs which have different PMU
than mipsxx, such as RM9000 and LOONGSON2, the additional files
perf_event_$cpu.c need to be created.
Raw event is an important part of Perf-events. It helps the user collect
performance data for events that are not listed as the generic hardware
events and cache events but ARE supported by the CPU's PMU.
This patch also adds this feature for mipsxx 24K/34K/74K/1004K. For how to
use it, please refer to processor core software user's manual and the
comments for mipsxx_pmu_map_raw_event() for more details.
Please note that this is a "precise" implementation, which means the
kernel will check whether the requested raw events are supported by this
CPU and which hardware counters can be assigned for them.
To test the functionality of Perf-event, you may want to compile the tool
"perf" for your MIPS platform. You can refer to the following URL:
http://www.linux-mips.org/archives/linux-mips/2010-10/msg00126.html
You also need to customize the CFLAGS and LDFLAGS in tools/perf/Makefile
for your libs, includes, etc.
In case you encounter the boot failure in SMVP kernel on multi-threading
CPUs, you may take a look at:
http://www.linux-mips.org/git?p=linux-mti.git;a=commitdiff;h=5460815027d802697b879644c74f0e8365254020
Signed-off-by: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
To: linux-mips@linux-mips.org
Cc: a.p.zijlstra@chello.nl
Cc: paulus@samba.org
Cc: mingo@elte.hu
Cc: acme@redhat.com
Cc: jamie.iles@picochip.com
Cc: ddaney@caviumnetworks.com
Cc: matt@console-pimps.org
Patchwork: https://patchwork.linux-mips.org/patch/1689/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
create mode 100644 arch/mips/kernel/perf_event_mipsxx.c
Linus Torvalds