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-7wj865zidu5ylf87i6i7v6z7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
More stuff that came from git, out of the hodge-podge that is util.h
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-e3lana4gctz3ub4hn4y29hkw@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Should make sense for windows, where git is supported.
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-lzxlhmqrizk72d0zcsreggy8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Both do the same thing, the later is the one we get from
linux/stringify.h, i.e. we now use the same function name/practice as
the kernel sources.
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-w2sxa5o4bfx7fjrd5mu4zmke@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We get them from inttypes.h.
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-qla4e4mwbf1oewafp1ee2etd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Needed to use the PRI[xu](32,64) formatting macros.
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-wkbho8kaw24q67dd11q0j39f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
TYPEOF(), for instance, was only used by MSB() that wasn't used at all,
besides typeof() is used in many places, should be the preferred way.
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-golox8oa2w1oq28snki14z6s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As tools/include/linux/kernel.h has it now, with the goodies present in
the kernel.h counterpart, i.e. checking that the parameter is an array
at build time.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-v0b41ivu6z6dyugbq9ffa9ez@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
And with the goodies present in the kernel.h counterpart, i.e. checking
that the parameter is an array at build time.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-roiwxwgwgld4kygn65if60wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To pave the way for further cleanups where linux/kernel.h may stop being
included in some header.
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-qqxan6tfsl6qx3l0v3nwgjvk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To match the kernel, then look for places redefining it to make it use
this version, which checks that its parameter is an array at build time.
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-txlcf1im83bcbj6kh0wxmyy8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Will be used to adopt the more stringent version of ARRAY_SIZE(), the
one in the kernel sources.
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-d85dpvay1hoqscpezlntyd8x@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
With just what we will need in the upcoming changesets, the
BUILD_BUG_ON_ZERO() definition.
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-lw8zg7x6ttwcvqhp90mwe3vo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We rely on symbol->name[0] since the beginning of tools/perf/, never
having received any complaint about it, also all the containers build
perf just fine, so remove this git codebase remnant.
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-jsjpgojut8e22o2gtz83augk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Since it uses EINVAL unconditionally, it needs to also unconditionally
include errno.h.
Detected when recent changes made errno.h not be included by chance when
tools/perf/arch/arm64/util/unwind-libunwind.c gets included by
tools/perf/util/libunwind/arm64.c.
Putting this changeset just before that change so that we don't lose
bisectability on arm64.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 8ab596afb9 ("perf tools ARM64: Wire up perf_regs and unwind support")
Link: http://lkml.kernel.org/n/tip-60zjev2o1locp5ivod38epa2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The HP ZBook 15u G3 has a Conexant CX20724 with mute led on GPIO1 and
mic mute led on GPIO2.
Adding CXT_FIXUP_MUTE_LED_GPIO inspired on patch_realtek's one.
Signed-off-by: Jerónimo Borque <jeronimo@borque.com.ar>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
This driver adds support for parsing SBSA Generic Watchdog timer
in GTDT, parse all info in SBSA Generic Watchdog Structure in GTDT,
and creating a platform device with that information.
This allows the operating system to obtain device data from the
resource of platform device. The platform device named "sbsa-gwdt"
can be used by the ARM SBSA Generic Watchdog driver.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Tested-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Reviewed-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
The patch add memory-mapped timer register support by using the
information provided by the new GTDT driver of ACPI.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
[Mark: verify CNTFRQ, only register the first frame]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
On platforms booting with ACPI, architected memory-mapped timers'
configuration data is provided by firmware through the ACPI GTDT
static table.
The clocksource architected timer kernel driver requires a firmware
interface to collect timer configuration and configure its driver.
this infrastructure is present for device tree systems, but it is
missing on systems booting with ACPI.
Implement the kernel infrastructure required to parse the static
ACPI GTDT table so that the architected timer clocksource driver can
make use of it on systems booting with ACPI, therefore enabling
the corresponding timers configuration.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
[Mark: restructure error handling]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
The window scale may be enlarged from 14 to 15 according to the itef
draft https://tools.ietf.org/html/draft-nishida-tcpm-maxwin-03.
Use the macro TCP_MAX_WSCALE to support it easily with TCP stack in
the future.
Signed-off-by: Gao Feng <fgao@ikuai8.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The commit ab8bc7ed86
("netfilter: remove nf_ct_is_untracked")
changed the line
if (ct && !nf_ct_is_untracked(ct) && nfct_nat(ct)) {
to
if (ct && nfct_nat(ct)) {
meanwhile, the commit 41390895e5
("netfilter: ipvs: don't check for presence of nat extension")
from ipvs-next had changed the same line to
if (ct && !nf_ct_is_untracked(ct) && (ct->status & IPS_NAT_MASK)) {
When ipvs-next got merged into nf-next, the merge resolution took
the first version, dropping the conversion of nfct_nat().
While this doesn't cause a problem at the moment, it will once we stop
adding the nat extension by default.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Only "cache" needs to use ulong (its used with set_bit()), missed can use
u16. Also add build-time assertion to ensure event bits fit.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
If insertion of a new conntrack fails because the table is full, the kernel
searches the next buckets of the hash slot where the new connection
was supposed to be inserted at for an entry that hasn't seen traffic
in reply direction (non-assured), if it finds one, that entry is
is dropped and the new connection entry is allocated.
Allow the conntrack gc worker to also remove *assured* conntracks if
resources are low.
Do this by querying the l4 tracker, e.g. tcp connections are now dropped
if they are no longer established (e.g. in finwait).
This could be refined further, e.g. by adding 'soft' established timeout
(i.e., a timeout that is only used once we get close to resource
exhaustion).
Cc: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
commit 223b02d923
("netfilter: nf_conntrack: reserve two bytes for nf_ct_ext->len")
had to increase size of the extension offsets because total size of the
extensions had increased to a point where u8 did overflow.
3 years later we've managed to diet extensions a bit and we no longer
need u16. Furthermore we can now add a compile-time assertion for this
problem.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
get rid of the (now unused) nf_ct_ext_add_length define and also
rename the function to plain nf_ct_ext_add().
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
No need to track this for inkernel helpers anymore as
NF_CT_HELPER_BUILD_BUG_ON checks do this now.
All inkernel helpers know what kind of structure they
stored in helper->data.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Userspace should not abuse the kernel to store large amounts of data,
reject requests larger than the private area can accommodate.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
add a 32 byte scratch area in the helper struct instead of relying
on variable sized helpers plus compile-time asserts to let us know
if 32 bytes aren't enough anymore.
Not having variable sized helpers will later allow to add BUILD_BUG_ON
for the total size of conntrack extensions -- the helper extension is
the only one that doesn't have a fixed size.
The (useless!) NF_CT_HELPER_BUILD_BUG_ON(0); are added so that in case
someone adds a new helper and copy-pastes from one that doesn't store
private data at least some indication that this macro should be used
somehow is there...
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
By default the kernel emits all ctnetlink events for a connection.
This allows to select the types of events to generate.
This can be used to e.g. only send DESTROY events but no NEW/UPDATE ones
and will work even if sysctl net.netfilter.nf_conntrack_events is set to 0.
This was already possible via iptables' CT target, but the nft version has
the advantage that it can also be used with already-established conntracks.
The added nf_ct_is_template() check isn't a bug fix as we only support
mark and labels (and unlike ecache the conntrack core doesn't copy those).
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
When iterating over the used LRs, be careful not to try to access
an unused LR, or even an unimplemented one if you're unlucky...
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
When emulating a GICv2-on-GICv3, special care must be taken to only
save/restore VMCR_EL2 when ICC_SRE_EL1.SRE is cleared. Otherwise,
all Group-0 interrupts end-up being delivered as FIQ, which is
probably not what the guest expects, as demonstrated here with
an unhappy EFI:
FIQ Exception at 0x000000013BD21CC4
This means that we cannot perform the load/put trick when dealing
with VMCR_EL2 (because the host has SRE set), and we have to deal
with it in the world-switch.
Fortunately, this is not the most common case (modern guests should
be able to deal with GICv3 directly), and the performance is not worse
than what it was before the VMCR optimization.
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Fix potential races in kvm_psci_vcpu_on() by taking the kvm->lock
mutex. In general, it's a bad idea to allow more than one PSCI_CPU_ON
to process the same target VCPU at the same time. One such problem
that may arise is that one PSCI_CPU_ON could be resetting the target
vcpu, which fills the entire sys_regs array with a temporary value
including the MPIDR register, while another looks up the VCPU based
on the MPIDR value, resulting in no target VCPU found. Resolves both
races found with the kvm-unit-tests/arm/psci unit test.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reported-by: Levente Kurusa <lkurusa@redhat.com>
Suggested-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Andrew Jones <drjones@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Christoffer Dall <cdall@linaro.org>
The patch update arm_arch_timer driver to use the function
provided by the new GTDT driver of ACPI.
By this way, arm_arch_timer.c can be simplified, and separate
all the ACPI GTDT knowledge from this timer driver.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Tested-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
This patch adds support for parsing arch timer info in GTDT,
provides some kernel APIs to parse all the PPIs and
always-on info in GTDT and export them.
By this driver, we can simplify arm_arch_timer drivers, and
separate the ACPI GTDT knowledge from it.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Currently the code to probe MMIO architected timers mixes DT parsing with
actual poking of hardware. This makes the code harder than necessary to
understand, and makes it difficult to add support for probing via ACPI.
This patch splits the DT parsing from HW probing. The DT parsing now
lives in arch_timer_mem_of_init(), which fills in an arch_timer_mem
structure that it hands to probing functions that can be reused for ACPI
support.
Since the rate detection logic will be slight different when using ACPI,
the probing is performed as a number of steps. This results in more code
for the moment, and some arguably redundant work, but simplifies matters
considerably when ACPI support is added.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
[Mark: refactor the probing split]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
In preparation for ACPI GTDT support, this patch adds structs to
describe the MMIO timers indepedent of the firmware interface.
Subsequent patches will use these to split the FW/HW probing logic, so
that the HW probing logic can be shared by ACPI and DT.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
To cleanly split code paths specific to ACPI or DT at a higher level,
this patch removes arch_timer_init(), folding the relevant
parts of its logic into existing callers.
This pathes the way for further rework, and saves a few lines.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
[Mark: reword commit message]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
When booting with DT, it's possible for timer nodes to be probed in any
order. Some common initialisation needs to occur after all nodes have
been probed, and arch_timer_common_init() has code to detect when this
has happened.
This logic is DT-specific, and it would be best to factor it out of the
common code that will be shared with ACPI.
This patch folds this into the existing arch_timer_needs_probing(),
which is renamed to arch_timer_needs_of_probing(), and no longer takes
any arguments. This is only called when using DT, and not when using
ACPI, which will have a deterministic probe order.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
[Mark: reword commit message]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
For historical reasons, rate detection when probing via DT is somewhat
convoluted. We tried to package this up in arch_timer_detect_rate(), but
with the addition of ACPI worse, and gets in the way of stringent rate
checking when ACPI is used.
This patch makes arch_timer_detect_rate() specific to DT, ripping out
ACPI logic. In preparation for rework of the MMIO timer probing, the
reading of the relevant CNTFRQ register is factored out to callers. The
function is then renamed to arch_timer_of_configure_rate(), which better
represents its new place in the world.
Comments are added in the DT and ACPI probe paths to explain this.
Signed-off-by: Fu Wei <fu.wei@linaro.org>
[Mark: reword commit message]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
This was just a proof of concept user for the SCSI OSD library, and
never had any real users.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Boaz Harrosh <ooo@electrozaur.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When CFQ is used as an elevator, it disables writeback throttling
because they don't play well together. Later when a different elevator
is chosen for the device, writeback throttling doesn't get enabled
again as it should. Make sure CFQ enables writeback throttling (if it
should be enabled by default) when we switch from it to another IO
scheduler.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
The BFQ I/O scheduler features an optimal fair-queuing
(proportional-share) scheduling algorithm, enriched with several
mechanisms to boost throughput and reduce latency for interactive and
real-time applications. This makes BFQ a large and complex piece of
code. This commit addresses this issue by splitting BFQ into three
main, independent components, and by moving each component into a
separate source file:
1. Main algorithm: handles the interaction with the kernel, and
decides which requests to dispatch; it uses the following two further
components to achieve its goals.
2. Scheduling engine (Hierarchical B-WF2Q+ scheduling algorithm):
computes the schedule, using weights and budgets provided by the above
component.
3. cgroups support: handles group operations (creation, destruction,
move, ...).
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
When a bfq queue is set in service and when it is merged, a reference
to the I/O context associated with the queue is taken. This reference
is then released when the queue is deselected from service or
split. More precisely, the release of the reference is postponed to
when the scheduler lock is released, to avoid nesting between the
scheduler and the I/O-context lock. In fact, such nesting would lead
to deadlocks, because of other code paths that take the same locks in
the opposite order. This postponing of I/O-context releases does
complicate code.
This commit addresses these issue by modifying involved operations in
such a way to not need to get the above I/O-context references any
more. Then it also removes any get and release of these references.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
Many popular I/O-intensive services or applications spawn or
reactivate many parallel threads/processes during short time
intervals. Examples are systemd during boot or git grep. These
services or applications benefit mostly from a high throughput: the
quicker the I/O generated by their processes is cumulatively served,
the sooner the target job of these services or applications gets
completed. As a consequence, it is almost always counterproductive to
weight-raise any of the queues associated to the processes of these
services or applications: in most cases it would just lower the
throughput, mainly because weight-raising also implies device idling.
To address this issue, an I/O scheduler needs, first, to detect which
queues are associated with these services or applications. In this
respect, we have that, from the I/O-scheduler standpoint, these
services or applications cause bursts of activations, i.e.,
activations of different queues occurring shortly after each
other. However, a shorter burst of activations may be caused also by
the start of an application that does not consist in a lot of parallel
I/O-bound threads (see the comments on the function bfq_handle_burst
for details).
In view of these facts, this commit introduces:
1) an heuristic to detect (only) bursts of queue activations caused by
services or applications consisting in many parallel I/O-bound
threads;
2) the prevention of device idling and weight-raising for the queues
belonging to these bursts.
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch is basically the counterpart, for NCQ-capable rotational
devices, of the previous patch. Exactly as the previous patch does on
flash-based devices and for any workload, this patch disables device
idling on rotational devices, but only for random I/O. In fact, only
with these queues disabling idling boosts the throughput on
NCQ-capable rotational devices. To not break service guarantees,
idling is disabled for NCQ-enabled rotational devices only when the
same symmetry conditions considered in the previous patches hold.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch boosts the throughput on NCQ-capable flash-based devices,
while still preserving latency guarantees for interactive and soft
real-time applications. The throughput is boosted by just not idling
the device when the in-service queue remains empty, even if the queue
is sync and has a non-null idle window. This helps to keep the drive's
internal queue full, which is necessary to achieve maximum
performance. This solution to boost the throughput is a port of
commits a68bbdd and f7d7b7a for CFQ.
As already highlighted in a previous patch, allowing the device to
prefetch and internally reorder requests trivially causes loss of
control on the request service order, and hence on service guarantees.
Fortunately, as discussed in detail in the comments on the function
bfq_bfqq_may_idle(), if every process has to receive the same
fraction of the throughput, then the service order enforced by the
internal scheduler of a flash-based device is relatively close to that
enforced by BFQ. In particular, it is close enough to let service
guarantees be substantially preserved.
Things change in an asymmetric scenario, i.e., if not every process
has to receive the same fraction of the throughput. In this case, to
guarantee the desired throughput distribution, the device must be
prevented from prefetching requests. This is exactly what this patch
does in asymmetric scenarios.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
A seeky queue (i..e, a queue containing random requests) is assigned a
very small device-idling slice, for throughput issues. Unfortunately,
given the process associated with a seeky queue, this behavior causes
the following problem: if the process, say P, performs sync I/O and
has a higher weight than some other processes doing I/O and associated
with non-seeky queues, then BFQ may fail to guarantee to P its
reserved share of the throughput. The reason is that idling is key
for providing service guarantees to processes doing sync I/O [1].
This commit addresses this issue by allowing the device-idling slice
to be reduced for a seeky queue only if the scenario happens to be
symmetric, i.e., if all the queues are to receive the same share of
the throughput.
[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
Scheduler", Proceedings of the First Workshop on Mobile System
Technologies (MST-2015), May 2015.
http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Riccardo Pizzetti <riccardo.pizzetti@gmail.com>
Signed-off-by: Samuele Zecchini <samuele.zecchini92@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
A set of processes may happen to perform interleaved reads, i.e.,
read requests whose union would give rise to a sequential read pattern.
There are two typical cases: first, processes reading fixed-size chunks
of data at a fixed distance from each other; second, processes reading
variable-size chunks at variable distances. The latter case occurs for
example with QEMU, which splits the I/O generated by a guest into
multiple chunks, and lets these chunks be served by a pool of I/O
threads, iteratively assigning the next chunk of I/O to the first
available thread. CFQ denotes as 'cooperating' a set of processes that
are doing interleaved I/O, and when it detects cooperating processes,
it merges their queues to obtain a sequential I/O pattern from the union
of their I/O requests, and hence boost the throughput.
Unfortunately, in the following frequent case, the mechanism
implemented in CFQ for detecting cooperating processes and merging
their queues is not responsive enough to handle also the fluctuating
I/O pattern of the second type of processes. Suppose that one process
of the second type issues a request close to the next request to serve
of another process of the same type. At that time the two processes
would be considered as cooperating. But, if the request issued by the
first process is to be merged with some other already-queued request,
then, from the moment at which this request arrives, to the moment
when CFQ controls whether the two processes are cooperating, the two
processes are likely to be already doing I/O in distant zones of the
disk surface or device memory.
CFQ uses however preemption to get a sequential read pattern out of
the read requests performed by the second type of processes too. As a
consequence, CFQ uses two different mechanisms to achieve the same
goal: boosting the throughput with interleaved I/O.
This patch introduces Early Queue Merge (EQM), a unified mechanism to
get a sequential read pattern with both types of processes. The main
idea is to immediately check whether a newly-arrived request lets some
pair of processes become cooperating, both in the case of actual
request insertion and, to be responsive with the second type of
processes, in the case of request merge. Both types of processes are
then handled by just merging their queues.
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Mauro Andreolini <mauro.andreolini@unimore.it>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch introduces an heuristic that reduces latency when the
I/O-request pool is saturated. This goal is achieved by disabling
device idling, for non-weight-raised queues, when there are weight-
raised queues with pending or in-flight requests. In fact, as
explained in more detail in the comment on the function
bfq_bfqq_may_idle(), this reduces the rate at which processes
associated with non-weight-raised queues grab requests from the pool,
thereby increasing the probability that processes associated with
weight-raised queues get a request immediately (or at least soon) when
they need one. Along the same line, if there are weight-raised queues,
then this patch halves the service rate of async (write) requests for
non-weight-raised queues.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
