cpufreq is currently keeping it a secret which cpus are sharing
clock source. The scheduler needs to know about clock domains as well
to become more energy aware. The SD_SHARE_CAP_STATES domain flag
indicates whether cpus belonging to the sched_domain share capacity
states (P-states).
There is no connection with cpufreq (yet). The flag must be set by
the arch specific topology code.
cc: Russell King <linux@arm.linux.org.uk>
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
The sched_group_energy (sge) pointer of the first sched_group (sg) in
the sched_domain (sd) is initialized to point to the appropriate (in
terms of sd level and cpu) sge data defined in the arch and so to the
correct part of the Energy Model (EM).
Energy-aware scheduling allows that a system has only EM data up to a
certain sd level (so called highest energy aware balancing sd level).
A check in init_sched_energy() enforces that all sd's below this sd
level contain EM data.
The 'int cpu' parameter of sched_domain_energy_f requires that
check_sched_energy_data() makes sure that all cpus spanned by a sg
are provisioned with the same EM data.
This patch has also been tested with feature FORCE_SD_OVERLAP enabled.
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
This patch introduces the ENERGY_AWARE sched feature, which is
implemented using jump labels when SCHED_DEBUG is defined. It is
statically set false when SCHED_DEBUG is not defined. Hence this doesn't
allow energy awareness to be enabled without SCHED_DEBUG. This
sched_feature knob will be replaced later with a more appropriate
control knob when things have matured a bit.
ENERGY_AWARE is based on per-entity load-tracking hence FAIR_GROUP_SCHED
must be enable. This dependency isn't checked at compile time yet.
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
This documentation patch provides an overview of the experimental
scheduler energy costing model, associated data structures, and a
reference recipe on how platforms can be characterized to derive energy
models.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
Scenarios with the busiest group having just one task and the local
being idle on topologies with sched groups with different numbers of
cpus manage to dodge all load-balance bailout conditions resulting the
nr_balance_failed counter to be incremented. This eventually causes a
pointless active migration of the task. This patch prevents this by not
incrementing the counter when the busiest group only has one task.
ASYM_PACKING migrations and migrations due to reduced capacity should
still take place as these are explicitly captured by
need_active_balance().
A better solution would be to not attempt the load-balance in the first
place, but that requires significant changes to the order of bailout
conditions and statistics gathering.
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
We do not want to miss out on the ability to pull a single remaining
task from a potential source cpu towards an idle destination cpu. Add an
extra criteria to need_active_balance() to kick off active load balance
if the source cpu is over-utilized and has lower capacity than the
destination cpu.
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
find_idlest_group() selects the wake-up target group purely
based on group load which leads to suboptimal choices in low load
scenarios. An idle group with reduced capacity (due to RT tasks or
different cpu type) isn't necessarily a better target than a lightly
loaded group with higher capacity.
The patch adds spare capacity as an additional group selection
parameter. The target group is now selected based on the following
criteria:
1. Return the group with the cpu with most spare capacity and this
capacity is significant if such group exists. Significant spare capacity
is currently at least 20% to spare.
2. Return the group with the lowest load, unless it is the local group
in which case NULL is returned and the search is continued at the next
(lower) level.
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
Wakeup balancing is completely unaware of cpu capacity, cpu utilization
and task utilization. The task is preferably placed on a cpu which is
idle in the instant the wakeup happens. New tasks
(SD_BALANCE_{FORK,EXEC} are placed on an idle cpu in the idlest group if
such can be found, otherwise it goes on the least loaded one. Existing
tasks (SD_BALANCE_WAKE) are placed on the previous cpu or an idle cpu
sharing the same last level cache unless the wakee_flips heuristic in
wake_wide() decides to fallback to considering cpus outside SD_LLC.
Hence existing tasks are not guaranteed to get a chance to migrate to a
different group at wakeup in case the current one has reduced cpu
capacity (due RT/IRQ pressure or different uarch e.g. ARM big.LITTLE).
They may eventually get pulled by other cpus doing
periodic/idle/nohz_idle balance, but it may take quite a while before it
happens.
This patch adds capacity awareness to find_idlest_{group,queue} (used by
SD_BALANCE_{FORK,EXEC} and SD_BALANCE_WAKE under certain circumstances)
such that groups/cpus that can accommodate the waking task based on task
utilization are preferred. In addition, wakeup of existing tasks
(SD_BALANCE_WAKE) is sent through find_idlest_{group,queue} also if the
task doesn't fit the capacity of the previous cpu to allow it to escape
(override wake_affine) when necessary instead of relying on
periodic/idle/nohz_idle balance to eventually sort it out.
cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
Defines arch_scale_freq_capacity() to use cpufreq implementation.
Including <linux/cpufreq.h> in topology.h like for the arm arch doesn't
work because of CONFIG_COMPAT=y (Kernel support for 32-bit EL0).
That's why cpufreq_scale_freq_capacity() has to be declared extern in
topology.h.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
Implements cpufreq_scale_freq_capacity() to provide the scheduler with a
frequency scaling correction factor for more accurate load-tracking.
The factor is:
current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_freq(cpu)
In fact, freq_scale should be a struct cpufreq_policy data member. But
this would require that the scheduler hot path (__update_load_avg()) would
have to grab the cpufreq lock. This can be avoided by using per-cpu data
initialized to SCHED_CAPACITY_SCALE for freq_scale.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
We don't need to export the governors for use as the default governor,
because the default governor will be built-in anyway and we can access
the symbol directly.
This also fixes the following sparse warnings:
drivers/cpufreq/cpufreq_conservative.c:578:25: warning: symbol 'cpufreq_gov_conservative' was not declared. Should it be static?
drivers/cpufreq/cpufreq_ondemand.c:582:25: warning: symbol 'cpufreq_gov_ondemand' was not declared. Should it be static?
drivers/cpufreq/cpufreq_performance.c:39:25: warning: symbol 'cpufreq_gov_performance' was not declared. Should it be static?
drivers/cpufreq/cpufreq_powersave.c:38:25: warning: symbol 'cpufreq_gov_powersave' was not declared. Should it be static?
drivers/cpufreq/cpufreq_userspace.c:190:25: warning: symbol 'cpufreq_gov_userspace' was not declared. Should it be static?
Signed-off-by: Sven Wegener <sven.wegener@stealer.net>
Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: Andres Oportus <andresoportus@google.com>
Enable qcom's memory state tracking driver config
CONFIG_MEMORY_STATE_TIME in android-recommended.config
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
The aio interface adds substantial attack surface for a feature that's not
being exposed by Android at all. It's unlikely that anyone is using the
kernel feature directly either. This feature is rarely used even on
servers. The glibc POSIX aio calls really use thread pools. The lack of
widespread usage also means this is relatively poorly audited/tested.
The kernel's aio rarely provides performance benefits over using a thread
pool and is quite incomplete in terms of system call coverage along with
having edge cases where blocking can occur. Part of the performance issue
is the fact that it only supports direct io, not buffered io. The
existing API is considered fundamentally flawed and it's unlikely it will
be expanded, but rather replaced:
https://marc.info/?l=linux-aio&m=145255815216051&w=2
Since ext4 encryption means no direct io support, kernel aio isn't even
going to work properly on Android devices using file-based encryption.
Reviewed-at: https://android-review.googlesource.com/#/c/292158/
Link: http://lkml.kernel.org/r/1481113148-29204-1-git-send-email-amit.pundir@linaro.org
Signed-off-by: Daniel Micay <danielmicay@gmail.com>
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Cc: Rob Herring <rob.herring@linaro.org>
Cc: John Stultz <john.stultz@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
If compiler has stack protector support, set
CONFIG_CC_STACKPROTECTOR_STRONG.
Bug: 28967314
Change-Id: I588c2d544250e9e4b5082b43c237b8f85b7313ca
Signed-off-by: Jeff Vander Stoep <jeffv@google.com>
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Enabled UID_CPUTIME and dependent PROFILING config option.
UID_CPUTIME (/proc/uid_cputime) interfaces provide amount of time a
UID's processes spent executing in user-space and kernel-space. It is
used by batterystats service.
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Add:
CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y
to android-base.cfg
The kernel.perf_event_paranoid sysctl is set to 3 by default.
No unprivileged use of the perf_event_open syscall will be
permitted unless it is changed.
Bug: 29054680
Change-Id: Ie7512259150e146d8e382dc64d40e8faaa438917
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Now that Android is moving towards ConfigFS based USB gadgets,
lets enable USB_CONFIGFS and relevant Android gadget functions
instead of obsolete USB_G_ANDROID composite driver which doesn't
exist now.
Enabled following ConfigFS gadget functions:
F_FS for ADB
F_MTP/PTP for MTP/PTP
F_ACC for Android USB Accessory
F_AUDIO_SRC for USB Audio Source
F_MIDI for MIDI, and
CONFIGFS_UEVENT for communicating USB state change notifications to userspace.
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Upstream now supports AOSP kernel config fragments:
commit 27eb6622ab ("config: add android config fragments").
This patch merge non-upstream AOSP config fragments from
android/configs/android-* of common kernel experimental/android-4.9
to kernel/configs/android-*.
Added initial set of AOSP config fragments and a README.android,
from AOSP Change-ID: I3a4883f3b04d2820e90ceb3c4d02390d6458d6ce
("android: configs: Initial commit of Android config fragments"),
to explain the purpose of Android config fragments and how to use
them to generate a device config compatible with Android.
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
New driver memory_state_time tracks time spent in different DDR
frequency and bandwidth states.
Memory drivers such as qcom,cpubw can post updated state to the driver
after registering a callback. Processed by a workqueue
Bandwidth buckets are read in from device tree in the relevant qualcomm
section, can be defined in any quantity and spacing.
The data is exposed at /sys/kernel/memory_state_time, able to be read by
the Android framework.
Functionality is behind a config option CONFIG_MEMORY_STATE_TIME
Change-Id: I4fee165571cb975fb9eacbc9aada5e6d7dd748f0
Signed-off-by: James Carr <carrja@google.com>
->setattr() was recently implemented for socket files to sync the socket
inode's uid to the new 'sk_uid' member of struct sock. It does this by
copying over the ia_uid member of struct iattr. However, ia_uid is
actually only valid when ATTR_UID is set in ia_valid, indicating that
the uid is being changed, e.g. by chown. Other metadata operations such
as chmod or utimes leave ia_uid uninitialized. Therefore, sk_uid could
be set to a "garbage" value from the stack.
Fix this by only copying the uid over when ATTR_UID is set.
Change-Id: I1efd83bd955325b33be3d4addccf5bac8ec803db
Fixes: 86741ec254 ("net: core: Add a UID field to struct sock.")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Tested-by: Lorenzo Colitti <lorenzo@google.com>
Acked-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We want to use network trace events in production
builds, to help diagnose Wifi problems. However, we
don't want to expose raw kernel pointers in such
builds.
Change the format specifier for the skbaddr field,
so that, if kptr_restrict is enabled, the pointers
will be reported as 0.
Bug: 30090733
Change-Id: Ic4bd583d37af6637343601feca875ee24479ddff
Signed-off-by: mukesh agrawal <quiche@google.com>
Commit e2d118a1cb ("net: inet: Support UID-based routing in IP
protocols.") made __build_flow_key call sock_net(sk) to determine
the network namespace of the passed-in socket. This crashes if sk
is NULL.
Fix this by getting the network namespace from the skb instead.
Change-Id: Ife860a7af8471bf40cc987f7803059d7bb9cc7e3
Fixes: e2d118a1cb ("net: inet: Support UID-based routing in IP protocols.")
Reported-by: Erez Shitrit <erezsh@dev.mellanox.co.il>
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Use the UID in routing lookups made by protocol connect() and
sendmsg() functions.
- Make sure that routing lookups triggered by incoming packets
(e.g., Path MTU discovery) take the UID of the socket into
account.
- For packets not associated with a userspace socket, (e.g., ping
replies) use UID 0 inside the user namespace corresponding to
the network namespace the socket belongs to. This allows
all namespaces to apply routing and iptables rules to
kernel-originated traffic in that namespaces by matching UID 0.
This is better than using the UID of the kernel socket that is
sending the traffic, because the UID of kernel sockets created
at namespace creation time (e.g., the per-processor ICMP and
TCP sockets) is the UID of the user that created the socket,
which might not be mapped in the namespace.
Change-Id: Ie35761630d9a77746399d6808ff0efb143efabb8
Tested: compiles allnoconfig, allyesconfig, allmodconfig
Tested: https://android-review.googlesource.com/253302
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Define a new FIB rule attributes, FRA_UID_RANGE, to describe a
range of UIDs.
- Define a RTA_UID attribute for per-UID route lookups and dumps.
- Support passing these attributes to and from userspace via
rtnetlink. The value INVALID_UID indicates no UID was
specified.
- Add a UID field to the flow structures.
Change-Id: I4d9d03e357ed5f35a65751b6d8ad919f0336dbfb
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Protocol sockets (struct sock) don't have UIDs, but most of the
time, they map 1:1 to userspace sockets (struct socket) which do.
Various operations such as the iptables xt_owner match need
access to the "UID of a socket", and do so by following the
backpointer to the struct socket. This involves taking
sk_callback_lock and doesn't work when there is no socket
because userspace has already called close().
Simplify this by adding a sk_uid field to struct sock whose value
matches the UID of the corresponding struct socket. The semantics
are as follows:
1. Whenever sk_socket is non-null: sk_uid is the same as the UID
in sk_socket, i.e., matches the return value of sock_i_uid.
Specifically, the UID is set when userspace calls socket(),
fchown(), or accept().
2. When sk_socket is NULL, sk_uid is defined as follows:
- For a socket that no longer has a sk_socket because
userspace has called close(): the previous UID.
- For a cloned socket (e.g., an incoming connection that is
established but on which userspace has not yet called
accept): the UID of the socket it was cloned from.
- For a socket that has never had an sk_socket: UID 0 inside
the user namespace corresponding to the network namespace
the socket belongs to.
Kernel sockets created by sock_create_kern are a special case
of #1 and sk_uid is the user that created them. For kernel
sockets created at network namespace creation time, such as the
per-processor ICMP and TCP sockets, this is the user that created
the network namespace.
Change-Id: Id890c6ea724b6929cc543a474ab37ec2d9e3f815
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adds tracepoints in ext4/f2fs/mpage to track readpages/buffered
write()s. This allows us to track files that are being read/written
to PIDs. (Merged from android4.4-common).
Signed-off-by: Mohan Srinivasan <srmohan@google.com>
This patch adds a new sysfs node (latency_hist) and reports
IO (svc time) latency histograms. Disabled by default, can be
enabled by echoing 0 into latency_hist, stats can be cleared
by writing 2 into latency_hist. This commit fixes the 32 bit
build breakage in the previous commit. Tested on both 32 bit
and 64 bit arm devices. (Merged from android4.4-common).
Bug: 30677035
Change-Id: I9403ea093f4cd54ebae08f12a11d01ef153118d0
Signed-off-by: Mohan Srinivasan <srmohan@google.com>
Userspace can close the sync device while there are still active fence
points, in which case kernel produces the following warning:
[ 43.853176] ------------[ cut here ]------------
[ 43.857834] WARNING: CPU: 0 PID: 892 at /mnt/host/source/src/third_party/kernel/v3.18/drivers/staging/android/sync.c:439 android_fence_release+0x88/0x104()
[ 43.871741] CPU: 0 PID: 892 Comm: Binder_5 Tainted: G U 3.18.0-07661-g0550ce9 #1
[ 43.880176] Hardware name: Google Tegra210 Smaug Rev 1+ (DT)
[ 43.885834] Call trace:
[ 43.888294] [<ffffffc000207464>] dump_backtrace+0x0/0x10c
[ 43.893697] [<ffffffc000207580>] show_stack+0x10/0x1c
[ 43.898756] [<ffffffc000ab1258>] dump_stack+0x74/0xb8
[ 43.903814] [<ffffffc00021d414>] warn_slowpath_common+0x84/0xb0
[ 43.909736] [<ffffffc00021d530>] warn_slowpath_null+0x14/0x20
[ 43.915482] [<ffffffc00088aefc>] android_fence_release+0x84/0x104
[ 43.921582] [<ffffffc000671cc4>] fence_release+0x104/0x134
[ 43.927066] [<ffffffc00088b0cc>] sync_fence_free+0x74/0x9c
[ 43.932552] [<ffffffc00088b128>] sync_fence_release+0x34/0x48
[ 43.938304] [<ffffffc000317bbc>] __fput+0x100/0x1b8
[ 43.943185] [<ffffffc000317cc8>] ____fput+0x8/0x14
[ 43.947982] [<ffffffc000237f38>] task_work_run+0xb0/0xe4
[ 43.953297] [<ffffffc000207074>] do_notify_resume+0x44/0x5c
[ 43.958867] ---[ end trace 5a2aa4027cc5d171 ]---
Let's fix it by introducing a new optional callback (disable_signaling)
to fence operations so that drivers can do proper clean ups when we
remove last callback for given fence.
BUG=chrome-os-partner:40303
TEST=Boot Smaug and observe that warning is gone.
Change-Id: I05c34dcf74438c28405438c7ead0706b1f810fff
Signed-off-by: Dmitry Torokhov <dtor@chromium.org>
Reviewed-on: https://chromium-review.googlesource.com/303409
Reviewed-by: Andrew Bresticker <abrestic@chromium.org>
[AmitP: Refactored original changes by renaming
android_fence_disable_signaling to
timeline_fence_disable_signaling so as to
align with the upstream naming convention].
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
If the get_user_pages_fast() call in goldfish_pipe_read_write() failed,
it would return while still holding pipe->lock.
goldfish_pipe_read_write() later releases and tries to re-acquire
pipe->lock. If the re-acquire call failed, goldfish_pipe_read_write()
would try unlock pipe->lock on exit anyway.
This fixes the smatch messages:
drivers/platform/goldfish/goldfish_pipe.c:392 goldfish_pipe_read_write() error: double unlock 'mutex:&pipe->lock'
drivers/platform/goldfish/goldfish_pipe.c:397 goldfish_pipe_read_write() warn: inconsistent returns 'mutex:&pipe->lock'.
Change-Id: Ifd06a76b32027ca451a001704ade0c5440ed69c4
Signed-off-by: Greg Hackmann <ghackmann@google.com>
Function get_free_pipe_id_locked called on line 671 inside lock on line
669 but uses GFP_KERNEL. Replace with GFP_ATOMIC.
Generated by: scripts/coccinelle/locks/call_kern.cocci
Change-Id: I49bd59abdf4533dbaa826f48c266883031179c7e
CC: Yurii Zubrytskyi <zyy@google.com>
Signed-off-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Guenter Roeck <groeck@chromium.org>
This is a driver code for a redesigned android pipe.
Currently it works for x86 and x64 emulators with the following
performance results:
ADB push to /dev/null,
Ubuntu,
400 MB file,
times are for 1/10/100 parallel adb commands
x86 adb push: (4.4s / 11.5s / 2m10s) -> (2.8s / 6s / 51s)
x64 adb push: (7s / 15s / (too long, 6m+) -> (2.7s / 6.2s / 52s)
ADB pull and push to /data/ have the same %% of speedup
More importantly, I don't see any signs of slowdowns when
run in parallel with Antutu benchmark, so it is definitely
making much better job at multithreading.
The code features dynamic host detection: old emulator gets
the previous version of the pipe driver code.
Combine follow patch from android-goldfish-3.10
b543285 [pipe] Increase the default pipe buffers size, make it configurable
Signed-off-by: "Yurii Zubrytskyi" <zyy@google.com>
Change-Id: I140d506204cab6e78dd503e5a43abc8886e4ffff
Combine following patches from android-goldfish-3.18 branch:
c0f015a [pipe] Fix the pipe driver for x64 platform + correct pages count
48e6bf5 [pipe] Use get_use_pages_fast() which is possibly faster
fb20f13 [goldfish] More pages in goldfish pipe
f180e6d goldfish_pipe: Return from read_write on signal and EIO
3dec3b7 [pipe] Fix a minor leak in setup_access_params_addr()
Change-Id: I1041fd65d7faaec123e6cedd3dbbc5a2fbb86c4d
- For device like eMMC, it gives better performance to read more hash
blocks at a time.
- For android, set it to default 128.
For other devices, set it to 1 which is the same as now.
- saved boot-up time by 300ms in tested device
bug: 32246564
Change-Id: Ibc0401a0cddba64b862a80445844b4e595213621
Cc: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Keun-young Park <keunyoung@google.com>
This boot clock can be used as a tracing clock and will account for
suspend time.
To keep it NMI safe since we're accessing from tracing, we're not using a
separate timekeeper with updates to monotonic clock and boot offset
protected with seqlocks. This has the following minor side effects:
(1) Its possible that a timestamp be taken after the boot offset is updated
but before the timekeeper is updated. If this happens, the new boot offset
is added to the old timekeeping making the clock appear to update slightly
earlier:
CPU 0 CPU 1
timekeeping_inject_sleeptime64()
__timekeeping_inject_sleeptime(tk, delta);
timestamp();
timekeeping_update(tk, TK_CLEAR_NTP...);
(2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
partially updated. Since the tk->offs_boot update is a rare event, this
should be a rare occurrence which postprocessing should be able to handle.
Bug: b/33184060
Change-Id: If79be2ed9d7a25ac39805b1fd81743026fc96575
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Joel Fernandes <joelaf@google.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
