Commit graph

678,699 commits

Author SHA1 Message Date
jbrunet
c16fe9a1c7 ARM64: dts: meson-gxl: add i2s output pins
Add EE and AO domains pins for the i2s output clocks and data the gxl
device tree

Acked-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:59:53 -07:00
jbrunet
07a4652f0e ARM64: dts: meson-gxbb: add spdif output pins
Add EE and AO domains pins for the spdif output to the gxbb device tree.

Acked-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:59:43 -07:00
jbrunet
552b1e56d9 ARM64: dts: meson-gxbb: add i2s output pins
Add EE and AO domains pins for the i2s output clocks and data to the gxbb
device tree.

Acked-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:59:27 -07:00
Chris Wilson
090e5fe3f0 drm/i915: Take rpm wakelock around debugfs/i915_gpu_info
Capturing GPU state requires the device to be awake in order to read
registers. Normally, this is taken along the error handler, but for the
direct debugfs access, we cannot make assumptions about the current
device state and so either need to wake it up, or abort.

Fixes: 5a4c6f1b1b ("drm/i915: The return of i915_gpu_info to debugfs")
Testcase: igt/pm_rpm/debugfs-read
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170328131407.14863-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
2017-03-28 15:59:12 +01:00
Neil Armstrong
1db3b92cb2 ARM64: dts: meson-gxbb: Add USB Hub GPIO hog
The ODroid-C2 on-board USB Hub needs to to have it's reset signal set to
high level in order to be enumerated by the USB Host Controller.

But this management must be part of the currently in-development Generic
Power Sequence patch that will allow a USB Controller driver to start and stop
a power sequence associated to the USB Bus.

In the meantime, a simple USB Hog will work to enable the USB Hub.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:56:22 -07:00
Neil Armstrong
8d1b908fe7 ARM: dts: meson8b: Add gpio-ranges properties
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:56:16 -07:00
Neil Armstrong
90f349ade2 ARM: dts: meson8: Add gpio-ranges properties
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:56:06 -07:00
Neil Armstrong
84412e4e85 ARM64: dts: meson-gxl: Add gpio-ranges properties
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:56:00 -07:00
Neil Armstrong
18ae17bc51 ARM64: dts: meson-gxbb: Add gpio-ranges properties
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:55:53 -07:00
Heiko Carstens
b8402b957d s390: make MAX_PHYSMEM_BITS configurable
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2017-03-28 16:55:10 +02:00
Heiko Carstens
fd15a1f333 s390: enable ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
Deferred struct page initialization works on s390. However it makes
only sense for the fake numa case, since the kthreads that initialize
struct pages are started per node. Without fake numa there is just a
single node and therefore no gain.
However there is no reason to not enable this feature. Therefore
select the config option and enable the feature in all config files.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2017-03-28 16:54:32 +02:00
Christian Borntraeger
b8f9828034 s390/MAINTAINERS: add gmap.c to kvm maintainers
gmap.c deals mostly with KVM-related memory management, so a lot
of changes to this file will come via the KVM tree. Reflect this
in MAINTAINERS. Please note that there are intricate ties to
arch/s390/mm/pgtable.c. If changes are needed in both files,
this will continue to be submitted via the s390 tree (or a
topic branch if necessary).

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2017-03-28 16:54:32 +02:00
Michael Holzheu
dcc00b79fc s390/kdump: Add final note
Since linux v3.14 with commit 38dfac843c ("vmcore: prevent PT_NOTE
p_memsz overflow during header update") on s390 we get the following
message in the kdump kernel:

  Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x6b6b6b6b,
  n_descsz=0x6b6b6b6b

The reason for this is that we don't create a final zero note in
the ELF header which the proc/vmcore code uses to find out the end
of the notes section (see also kernel/kexec_core.c:final_note()).

It still worked on s390 by chance because we (most of the time?) have the
byte pattern 0x6b6b6b6b after the notes section which also makes the notes
parsing code stop in update_note_header_size_elf64() because 0x6b6b6b6b is
interpreded as note size:

  if ((real_sz + sz) > max_sz) {
          pr_warn("Warning: Exceeded p_memsz, dropping P ...);
          break;
  }

So fix this and add the missing final note to the ELF header.
We don't have to adjust the memory size for ELF header ("alloc_size")
because the new ELF note still fits into the 0x1000 base memory.

Cc: stable@vger.kernel.org # v4.4+
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2017-03-28 16:54:31 +02:00
Heiko Carstens
59cea29a34 s390: remove HAVE_ARCH_EARLY_PFN_TO_NID select statement
HAVE_ARCH_EARLY_PFN_TO_NID selects a not present Kconfig
option. Therefore remove it.
Given that the first call of early_pfn_to_nid() happens after
numa_setup() finished to establish the memory to node mapping, there
is no need to implement an architecture private version of
__early_pfn_to_nid() like (only) ia64 does.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2017-03-28 16:54:30 +02:00
Stefan Haberland
ab24fbd35a s390/dasd: suppress command reject error for query host access command
On some z/VM systems the query host access command is not supported for
temp disks, though the corresponding feature code is set.
This does not have any impact beside that the information is not available.
Suppress the full blown command reject error messages to not confuse the
user. The error is still logged in the s390dbf.

Signed-off-by: Stefan Haberland <sth@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2017-03-28 16:54:28 +02:00
Stefan Haberland
ccd53fa226 s390/dasd: check if query host access feature is supported
Some storage servers might not support the query host access feature.
Check if the corresponding feature code is set.

Signed-off-by: Stefan Haberland <sth@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2017-03-28 16:54:27 +02:00
Neil Armstrong
57ef579878 ARM64: dts: meson-gx: Add Mali nodes for GXBB and GXL
The same Mali-450 MP3 GPU is present in the GXBB and GXL SoCs.

The node is simply added in the meson-gxbb.dtsi file.

For GXL, since a lot is shared with the GXM that has a Mali-T820 IP, this
patch adds a new meson-gxl-mali.dtsi and is included in the SoC specific
dtsi files.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
[khilman: s/MALI/Mali in changelog]
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
2017-03-28 07:48:27 -07:00
Geert Uytterhoeven
5d3fa803b1 MAINTAINERS: Add file patterns for perf device tree bindings
Submitters of device tree binding documentation may forget to CC
the subsystem maintainer if this is missing.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-03-28 15:36:31 +01:00
James Hogan
0ae3abcda2 MIPS: Allow KVM to be enabled on Octeon CPUs
Octeon III has VZ ASE support, so allow KVM to be enabled on Octeon
CPUs as it should now be functional.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:20 +01:00
James Hogan
1f48f9be4d KVM: MIPS/VZ: Handle Octeon III guest.PRid register
Octeon III implements a read-only guest CP0_PRid register, so add cases
to the KVM register access API for Octeon to ensure the correct value is
read and writes are ignored.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:20 +01:00
James Hogan
3ba731daf0 KVM: MIPS/VZ: Emulate hit CACHE ops for Octeon III
Octeon III doesn't implement the optional GuestCtl0.CG bit to allow
guest mode to execute virtual address based CACHE instructions, so
implement emulation of a few important ones specifically for Octeon III
in response to a GPSI exception.

Currently the main reason to perform these operations is for icache
synchronisation, so they are implemented as a simple icache flush with
local_flush_icache_range().

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:19 +01:00
James Hogan
824533ad16 KVM: MIPS/VZ: VZ hardware setup for Octeon III
Set up hardware virtualisation on Octeon III cores, configuring guest
interrupt routing and carving out half of the root TLB for guest use,
restoring it back again afterwards.

We need to be careful to inhibit TLB shutdown machine check exceptions
while invalidating guest TLB entries, since TLB invalidation is not
available so guest entries must be invalidated by setting them to unique
unmapped addresses, which could conflict with mappings set by the guest
or root if recently repartitioned.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:18 +01:00
James Hogan
867f4da752 KVM: MIPS/T&E: Report correct dcache line size
Octeon CPUs don't report the correct dcache line size in CP0_Config1.DL,
so encode the correct value for the guest CP0_Config1.DL based on
cpu_dcache_line_size().

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:18 +01:00
James Hogan
1c506c9c10 KVM: MIPS/TLB: Handle virtually tagged icaches
When TLB entries are invalidated in the presence of a virtually tagged
icache, such as that found on Octeon CPUs, flush the icache so that we
don't get a reserved instruction exception even though the TLB mapping
is removed.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:17 +01:00
James Hogan
4fa9de5a64 KVM: MIPS/Emulate: Adapt T&E CACHE emulation for Octeon
Cache management is implemented separately for Cavium Octeon CPUs, so
r4k_blast_[id]cache aren't available. Instead for Octeon perform a local
icache flush using local_flush_icache_range(), and for other platforms
which don't use c-r4k.c use __flush_cache_all() / flush_icache_all().

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:17 +01:00
James Hogan
7d8a528d19 MIPS: Add Octeon III register accessors & definitions
Add accessors for some VZ related Cavium Octeon III specific COP0
registers, along with field definitions. These will mostly be used by
KVM to set up interrupt routing and partition the TLB between root and
guest.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Cc: David Daney <david.daney@cavium.com>
Cc: Andreas Herrmann <andreas.herrmann@caviumnetworks.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 15:36:04 +01:00
Wei Yongjun
f147140c7f ARM: hisi: fix error return code in hip04_smp_init()
Fix to return error code -ENODEV from the of_find_compatible_node()
error handling case instead of 0, as done elsewhere in this function.

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Wei Xu <xuwei5@hisilicon.com>
2017-03-28 15:30:54 +01:00
Arnaldo Carvalho de Melo
c68677014b perf tools: Remove support for command aliases
This came from 'git', but isn't documented anywhere in
tools/perf/Documentation/, looks like baggage we can do without, ditch
it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-e7uwkn60t4hmlnwj99ba4t2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-28 11:19:59 -03:00
SeongJae Park
4f6cce3910 Fix dead URLs to ftp.kernel.org
URLs to ftp.kernel.org are still exist though the service is closed [0].
This commit fixes the URLs to use www.kernel.org instead.

[0] https://www.kernel.org/shutting-down-ftp-services.html

Signed-off-by: SeongJae Park <sj38.park@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-03-28 16:16:52 +02:00
Shaohua Li
53696b8d21 blk-throttle: add latency target support
One hard problem adding .low limit is to detect idle cgroup. If one
cgroup doesn't dispatch enough IO against its low limit, we must have a
mechanism to determine if other cgroups dispatch more IO. We added the
think time detection mechanism before, but it doesn't work for all
workloads. Here we add a latency based approach.

We already have mechanism to calculate latency threshold for each IO
size. For every IO dispatched from a cgorup, we compare its latency
against its threshold and record the info. If most IO latency is below
threshold (in the code I use 75%), the cgroup could be treated idle and
other cgroups can dispatch more IO.

Currently this latency target check is only for SSD as we can't
calcualte the latency target for hard disk. And this is only for cgroup
leaf node so far.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
b9147dd1ba blk-throttle: add a mechanism to estimate IO latency
User configures latency target, but the latency threshold for each
request size isn't fixed. For a SSD, the IO latency highly depends on
request size. To calculate latency threshold, we sample some data, eg,
average latency for request size 4k, 8k, 16k, 32k .. 1M. The latency
threshold of each request size will be the sample latency (I'll call it
base latency) plus latency target. For example, the base latency for
request size 4k is 80us and user configures latency target 60us. The 4k
latency threshold will be 80 + 60 = 140us.

To sample data, we calculate the order base 2 of rounded up IO sectors.
If the IO size is bigger than 1M, it will be accounted as 1M. Since the
calculation does round up, the base latency will be slightly smaller
than actual value. Also if there isn't any IO dispatched for a specific
IO size, we will use the base latency of smaller IO size for this IO
size.

But we shouldn't sample data at any time. The base latency is supposed
to be latency where disk isn't congested, because we use latency
threshold to schedule IOs between cgroups. If disk is congested, the
latency is higher, using it for scheduling is meaningless. Hence we only
do the sampling when block throttling is in the LOW limit, with
assumption disk isn't congested in such state. If the assumption isn't
true, eg, low limit is too high, calculated latency threshold will be
higher.

Hard disk is completely different. Latency depends on spindle seek
instead of request size. Currently this feature is SSD only, we probably
can use a fixed threshold like 4ms for hard disk though.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
88eeca495b block: track request size in blk_issue_stat
Currently there is no way to know the request size when the request is
finished. Next patch will need this info. We could add extra field to
record the size, but blk_issue_stat has enough space to record it, so
this patch just overloads blk_issue_stat. With this, we will have 49bits
to track time, which still is very long time.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
ec80991d6f blk-throttle: add interface for per-cgroup target latency
Here we introduce per-cgroup latency target. The target determines how a
cgroup can afford latency increasement. We will use the target latency
to calculate a threshold and use it to schedule IO for cgroups. If a
cgroup's bandwidth is below its low limit but its average latency is
below the threshold, other cgroups can safely dispatch more IO even
their bandwidth is higher than their low limits. On the other hand, if
the first cgroup's latency is higher than the threshold, other cgroups
are throttled to their low limits. So the target latency determines how
we efficiently utilize free disk resource without sacifice of worload's
IO latency.

For example, assume 4k IO average latency is 50us when disk isn't
congested. A cgroup sets the target latency to 30us. Then the cgroup can
accept 50+30=80us IO latency. If the cgroupt's average IO latency is
90us and its bandwidth is below low limit, other cgroups are throttled
to their low limit. If the cgroup's average IO latency is 60us, other
cgroups are allowed to dispatch more IO. When other cgroups dispatch
more IO, the first cgroup's IO latency will increase. If it increases to
81us, we then throttle other cgroups.

User will configure the interface in this way:
echo "8:16 rbps=2097152 wbps=max latency=100 idle=200" > io.low

latency is in microsecond unit

By default, latency target is 0, which means to guarantee IO latency.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
fa6fb5aab8 blk-throttle: ignore idle cgroup limit
Last patch introduces a way to detect idle cgroup. We use it to make
upgrade/downgrade decision. And the new algorithm can detect completely
idle cgroup too, so we can delete the corresponding code.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
ada75b6e5b blk-throttle: add interface to configure idle time threshold
Add interface to configure the threshold. The io.low interface will
like:
echo "8:16 rbps=2097152 wbps=max idle=2000" > io.low

idle is in microsecond unit.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
9e234eeafb blk-throttle: add a simple idle detection
A cgroup gets assigned a low limit, but the cgroup could never dispatch
enough IO to cross the low limit. In such case, the queue state machine
will remain in LIMIT_LOW state and all other cgroups will be throttled
according to low limit. This is unfair for other cgroups. We should
treat the cgroup idle and upgrade the state machine to lower state.

We also have a downgrade logic. If the state machine upgrades because of
cgroup idle (real idle), the state machine will downgrade soon as the
cgroup is below its low limit. This isn't what we want. A more
complicated case is cgroup isn't idle when queue is in LIMIT_LOW. But
when queue gets upgraded to lower state, other cgroups could dispatch
more IO and this cgroup can't dispatch enough IO, so the cgroup is below
its low limit and looks like idle (fake idle). In this case, the queue
should downgrade soon. The key to determine if we should do downgrade is
to detect if cgroup is truely idle.

Unfortunately it's very hard to determine if a cgroup is real idle. This
patch uses the 'think time check' idea from CFQ for the purpose. Please
note, the idea doesn't work for all workloads. For example, a workload
with io depth 8 has disk utilization 100%, hence think time is 0, eg,
not idle. But the workload can run higher bandwidth with io depth 16.
Compared to io depth 16, the io depth 8 workload is idle. We use the
idea to roughly determine if a cgroup is idle.

We treat a cgroup idle if its think time is above a threshold (by
default 1ms for SSD and 100ms for HD). The idea is think time above the
threshold will start to harm performance. HD is much slower so a longer
think time is ok.

The patch (and the latter patches) uses 'unsigned long' to track time.
We convert 'ns' to 'us' with 'ns >> 10'. This is fast but loses
precision, should not a big deal.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
7394e31fa4 blk-throttle: make bandwidth change smooth
When cgroups all reach low limit, cgroups can dispatch more IO. This
could make some cgroups dispatch more IO but others not, and even some
cgroups could dispatch less IO than their low limit. For example, cg1
low limit 10MB/s, cg2 limit 80MB/s, assume disk maximum bandwidth is
120M/s for the workload. Their bps could something like this:

cg1/cg2 bps: T1: 10/80 -> T2: 60/60 -> T3: 10/80

At T1, all cgroups reach low limit, so they can dispatch more IO later.
Then cg1 dispatch more IO and cg2 has no room to dispatch enough IO. At
T2, cg2 only dispatches 60M/s. Since We detect cg2 dispatches less IO
than its low limit 80M/s, we downgrade the queue from LIMIT_MAX to
LIMIT_LOW, then all cgroups are throttled to their low limit (T3). cg2
will have bandwidth below its low limit at most time.

The big problem here is we don't know the maximum bandwidth of the
workload, so we can't make smart decision to avoid the situation. This
patch makes cgroup bandwidth change smooth. After disk upgrades from
LIMIT_LOW to LIMIT_MAX, we don't allow cgroups use all bandwidth upto
their max limit immediately. Their bandwidth limit will be increased
gradually to avoid above situation. So above example will became
something like:

cg1/cg2 bps: 10/80 -> 15/105 -> 20/100 -> 25/95 -> 30/90 -> 35/85 -> 40/80
-> 45/75 -> 22/98

In this way cgroups bandwidth will be above their limit in majority
time, this still doesn't fully utilize disk bandwidth, but that's
something we pay for sharing.

Scale up is linear. The limit scales up 1/2 .low limit every
throtl_slice after upgrade. The scale up will stop if the adjusted limit
hits .max limit. Scale down is exponential. We cut the scale value half
if a cgroup doesn't hit its .low limit. If the scale becomes 0, we then
fully downgrade the queue to LIMIT_LOW state.

Note this doesn't completely avoid cgroup running under its low limit.
The best way to guarantee cgroup doesn't run under its limit is to set
max limit. For example, if we set cg1 max limit to 40, cg2 will never
run under its low limit.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
aec242468c blk-throttle: detect completed idle cgroup
cgroup could be assigned a limit, but doesn't dispatch enough IO, eg the
cgroup is idle. When this happens, the cgroup doesn't hit its limit, so
we can't move the state machine to higher level and all cgroups will be
throttled to their lower limit, so we waste bandwidth. Detecting idle
cgroup is hard. This patch handles a simple case, a cgroup doesn't
dispatch any IO. We ignore such cgroup's limit, so other cgroups can use
the bandwidth.

Please note this will be replaced with a more sophisticated algorithm
later, but this demonstrates the idea how we handle idle cgroups, so I
leave it here.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
d61fcfa4bb blk-throttle: choose a small throtl_slice for SSD
The throtl_slice is 100ms by default. This is a long time for SSD, a lot
of IO can run. To make cgroups have smoother throughput, we choose a
small value (20ms) for SSD.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
297e3d8547 blk-throttle: make throtl_slice tunable
throtl_slice is important for blk-throttling. It's called slice
internally but it really is a time window blk-throttling samples data.
blk-throttling will make decision based on the samplings. An example is
bandwidth measurement. A cgroup's bandwidth is measured in the time
interval of throtl_slice.

A small throtl_slice meanse cgroups have smoother throughput but burn
more CPUs. It has 100ms default value, which is not appropriate for all
disks. A fast SSD can dispatch a lot of IOs in 100ms. This patch makes
it tunable.

Since throtl_slice isn't a time slice, the sysfs name
'throttle_sample_time' reflects its character better.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
06cceedcca blk-throttle: make sure expire time isn't too big
cgroup could be throttled to a limit but when all cgroups cross high
limit, queue enters a higher state and so the group should be throttled
to a higher limit. It's possible the cgroup is sleeping because of
throttle and other cgroups don't dispatch IO any more. In this case,
nobody can trigger current downgrade/upgrade logic. To fix this issue,
we could either set up a timer to wakeup the cgroup if other cgroups are
idle or make sure this cgroup doesn't sleep too long. Setting up a timer
means we must change the timer very frequently. This patch chooses the
latter. Making cgroup sleep time not too big wouldn't change cgroup
bps/iops, but could make it wakeup more frequently, which isn't a big
issue because throtl_slice * 8 is already quite big.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
3f0abd8066 blk-throttle: add downgrade logic
When queue state machine is in LIMIT_MAX state, but a cgroup is below
its low limit for some time, the queue should be downgraded to lower
state as one cgroup's low limit isn't met.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
c79892c557 blk-throttle: add upgrade logic for LIMIT_LOW state
When queue is in LIMIT_LOW state and all cgroups with low limit cross
the bps/iops limitation, we will upgrade queue's state to
LIMIT_MAX. To determine if a cgroup exceeds its limitation, we check if
the cgroup has pending request. Since cgroup is throttled according to
the limit, pending request means the cgroup reaches the limit.

If a cgroup has limit set for both read and write, we consider the
combination of them for upgrade. The reason is read IO and write IO can
interfere with each other. If we do the upgrade based in one direction
IO, the other direction IO could be severly harmed.

For a cgroup hierarchy, there are two cases. Children has lower low
limit than parent. Parent's low limit is meaningless. If children's
bps/iops cross low limit, we can upgrade queue state. The other case is
children has higher low limit than parent. Children's low limit is
meaningless. As long as parent's bps/iops (which is a sum of childrens
bps/iops) cross low limit, we can upgrade queue state.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
b22c417c88 blk-throttle: configure bps/iops limit for cgroup in low limit
each queue will have a state machine. Initially queue is in LIMIT_LOW
state, which means all cgroups will be throttled according to their low
limit. After all cgroups with low limit cross the limit, the queue state
gets upgraded to LIMIT_MAX state.
For max limit, cgroup will use the limit configured by user.
For low limit, cgroup will use the minimal value between low limit and
max limit configured by user. If the minimal value is 0, which means the
cgroup doesn't configure low limit, we will use max limit to throttle
the cgroup and the cgroup is ready to upgrade to LIMIT_MAX

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
cd5ab1b0fc blk-throttle: add .low interface
Add low limit for cgroup and corresponding cgroup interface. To be
consistent with memcg, we allow users configure .low limit higher than
.max limit. But the internal logic always assumes .low limit is lower
than .max limit. So we add extra bps/iops_conf fields in throtl_grp for
userspace configuration. Old bps/iops fields in throtl_grp will be the
actual limit we use for throttling.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
327ffb9b37 blk-throttle: add configure option for new .low interface
As discussed in LSF, add configure option for the interface and mark it
as experimental, so people can try/test.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
9f626e372a blk-throttle: prepare support multiple limits
We are going to support low/max limit, each cgroup will have 2 limits
after that. This patch prepares for the multiple limits change.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
Shaohua Li
2ab5492de5 blk-throttle: use U64_MAX/UINT_MAX to replace -1
clean up the code to avoid using -1

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-28 08:02:20 -06:00
James Hogan
edec9d7bdc KVM: MIPS/VZ: Trace guest mode changes
Create a trace event for guest mode changes, and enable VZ's
GuestCtl0.MC bit after the trace event is enabled to trap all guest mode
changes.

The MC bit causes Guest Hardware Field Change (GHFC) exceptions whenever
a guest mode change occurs (such as an exception entry or return from
exception), so we need to handle this exception now. The MC bit is only
enabled when restoring register state, so enabling the trace event won't
take immediate effect.

Tracing guest mode changes can be particularly handy when trying to work
out what a guest OS gets up to before something goes wrong, especially
if the problem occurs as a result of some previous guest userland
exception which would otherwise be invisible in the trace.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 14:54:00 +01:00
James Hogan
f4474d50c7 KVM: MIPS/VZ: Support hardware guest timer
Transfer timer state to the VZ guest context (CP0_GTOffset & guest
CP0_Count) when entering guest mode, enabling direct guest access to it,
and transfer back to soft timer when saving guest register state.

This usually allows guest code to directly read CP0_Count (via MFC0 and
RDHWR) and read/write CP0_Compare, without trapping to the hypervisor
for it to emulate the guest timer. Writing to CP0_Count or CP0_Cause.DC
is much less common and still triggers a hypervisor GPSI exception, in
which case the timer state is transferred back to an hrtimer before
emulating the write.

We are careful to prevent small amounts of drift from building up due to
undeterministic time intervals between reading of the ktime and reading
of CP0_Count. Some drift is expected however, since the system
clocksource may use a different timer to the local CP0_Count timer used
by VZ. This is permitted to prevent guest CP0_Count from appearing to go
backwards.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: kvm@vger.kernel.org
2017-03-28 14:53:59 +01:00