Psi monitor aims to provide a low-latency short-term pressure
detection mechanism configurable by users. It allows users to
monitor psi metrics growth and trigger events whenever a metric
raises above user-defined threshold within user-defined time window.
Time window and threshold are both expressed in usecs. Multiple psi
resources with different thresholds and window sizes can be monitored
concurrently.
Psi monitors activate when system enters stall state for the monitored
psi metric and deactivate upon exit from the stall state. While system
is in the stall state psi signal growth is monitored at a rate of 10 times
per tracking window. Min window size is 500ms, therefore the min monitoring
interval is 50ms. Max window size is 10s with monitoring interval of 1s.
When activated psi monitor stays active for at least the duration of one
tracking window to avoid repeated activations/deactivations when psi
signal is bouncing.
Notifications to the users are rate-limited to one per tracking window.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
(not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052418/)
Bug: 127712811
Bug: 129157727
Test: lmkd in PSI mode
Change-Id: I860049d32420485346ad545c4650f990fe0c08e3
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
kthread.h can't be included in psi_types.h because it creates a circular
inclusion with kthread.h eventually including psi_types.h and complaining
on kthread structures not being defined because they are defined further
in the kthread.h. Resolve this by removing psi_types.h inclusion from the
headers included from kthread.h.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
(not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052417/)
Bug: 127712811
Bug: 129157727
Test: lmkd in PSI mode
Change-Id: I88cd99f41534f0b9df18043cde8d1ee54aaa93de
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Introduce changed_states parameter into collect_percpu_times to track
the states changed since the last update.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
(not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052420/)
Bug: 127712811
Bug: 129157727
Test: lmkd in PSI mode
Change-Id: I944b024cd65e8520a57097bf5a3d7b2c01605bd0
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Split update_stats into collect_percpu_times and update_averages for
collect_percpu_times to be reused later inside psi monitor.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
(not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052419/)
Bug: 127712811
Bug: 129157727
Test: lmkd in PSI mode
Change-Id: Ia9cfed8964fd57e41098fca285a2be0252fd5277
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Renaming psi_group structure member fields used for calculating psi totals
and averages for clear distinction between them and trigger-related fields
that will be added next.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
(not upstream yet, latest version published at: https://lore.kernel.org/patchwork/patch/1052416/)
Bug: 127712811
Bug: 129157727
Test: lmkd in PSI mode
Change-Id: I579a60e0915fa8fedaa508357d3d1aefab9428c4
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Patch series "psi: pressure stall monitors", v3.
Android is adopting psi to detect and remedy memory pressure that results
in stuttering and decreased responsiveness on mobile devices.
Psi gives us the stall information, but because we're dealing with
latencies in the millisecond range, periodically reading the pressure
files to detect stalls in a timely fashion is not feasible. Psi also
doesn't aggregate its averages at a high enough frequency right now.
This patch series extends the psi interface such that users can configure
sensitive latency thresholds and use poll() and friends to be notified
when these are breached.
As high-frequency aggregation is costly, it implements an aggregation
method that is optimized for fast, short-interval averaging, and makes the
aggregation frequency adaptive, such that high-frequency updates only
happen while monitored stall events are actively occurring.
With these patches applied, Android can monitor for, and ward off,
mounting memory shortages before they cause problems for the user. For
example, using memory stall monitors in userspace low memory killer daemon
(lmkd) we can detect mounting pressure and kill less important processes
before device becomes visibly sluggish. In our memory stress testing psi
memory monitors produce roughly 10x less false positives compared to
vmpressure signals. Having ability to specify multiple triggers for the
same psi metric allows other parts of Android framework to monitor memory
state of the device and act accordingly.
The new interface is straightforward. The user opens one of the pressure
files for writing and writes a trigger description into the file
descriptor that defines the stall state - some or full, and the maximum
stall time over a given window of time. E.g.:
/* Signal when stall time exceeds 100ms of a 1s window */
char trigger[] = "full 100000 1000000";
fd = open("/proc/pressure/memory");
write(fd, trigger, sizeof(trigger));
while (poll() >= 0) {
...
}
close(fd);
When the monitored stall state is entered, psi adapts its aggregation
frequency according to what the configured time window requires in order
to emit event signals in a timely fashion. Once the stalling subsides,
aggregation reverts back to normal.
The trigger is associated with the open file descriptor. To stop
monitoring, the user only needs to close the file descriptor and the
trigger is discarded.
Patches 1-4 prepare the psi code for polling support. Patch 5 implements
the adaptive polling logic, the pressure growth detection optimized for
short intervals, and hooks up write() and poll() on the pressure files.
The patches were developed in collaboration with Johannes Weiner.
This patch (of 5):
Kernfs has a standardized poll/notification mechanism for waking all
pollers on all fds when a filesystem node changes. To allow polling for
custom events, add a .poll callback that can override the default.
This is in preparation for pollable cgroup pressure files which have
per-fd trigger configurations.
Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
(cherry picked from commit: 147e1a97c4)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: I67d81f9c2ac340830aa4fb8954554b5ff8628244
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
We've been seeing hard-to-trigger psi crashes when running inside VM
instances:
divide error: 0000 [#1] SMP PTI
Modules linked in: [...]
CPU: 0 PID: 212 Comm: kworker/0:2 Not tainted 4.16.18-119_fbk9_3817_gfe944c98d695 #119
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015
Workqueue: events psi_clock
RIP: 0010:psi_update_stats+0x270/0x490
RSP: 0018:ffffc90001117e10 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8800a35a13f8
RDX: 0000000000000000 RSI: ffff8800a35a1340 RDI: 0000000000000000
RBP: 0000000000000658 R08: ffff8800a35a1470 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 00000000000f8502
FS: 0000000000000000(0000) GS:ffff88023fc00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fbe370fa000 CR3: 00000000b1e3a000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
psi_clock+0x12/0x50
process_one_work+0x1e0/0x390
worker_thread+0x2b/0x3c0
? rescuer_thread+0x330/0x330
kthread+0x113/0x130
? kthread_create_worker_on_cpu+0x40/0x40
? SyS_exit_group+0x10/0x10
ret_from_fork+0x35/0x40
Code: 48 0f 47 c7 48 01 c2 45 85 e4 48 89 16 0f 85 e6 00 00 00 4c 8b 49 10 4c 8b 51 08 49 69 d9 f2 07 00 00 48 6b c0 64 4c 8b 29 31 d2 <48> f7 f7 49 69 d5 8d 06 00 00 48 89 c5 4c 69 f0 00 98 0b 00 48
The Code-line points to `period` being 0 inside update_stats(), and we
divide by that when calculating that period's pressure percentage.
The elapsed period should never be 0. The reason this can happen is due
to an off-by-one in the idle time / missing period calculation combined
with a coarse sched_clock() in the virtual machine.
The target time for aggregation is advanced into the future on a fixed
grid to prevent clock drift. So when an aggregation runs after some idle
period, we can not just set it to "now + psi_period", but have to
calculate the downtime and advance the target time relative to itself.
However, if the aggregator was disabled exactly one psi_period (ns), we
drop one idle period in the calculation due to a > when we should do >=.
In that case, next_update will be advanced from 'now - psi_period' to
'now' when it should be moved to 'now + psi_period'. The run finishes
with last_update == next_update == sched_clock().
With hardware clocks, this exact nanosecond match isn't likely in the
first place; but if it does happen, the clock will still have moved on and
the period non-zero by the time the worker runs. A pointlessly short
period, but besides the extra work, no harm no foul. However, a slow
sched_clock() like we have on VMs might not have advanced either by the
time the worker runs again. And when we calculate the elapsed period, the
result, our pressure divisor, will be 0. Ouch.
Fix this by correctly handling the situation when the elapsed time between
aggregation runs is precisely two periods, and advance the expiration
timestamp correctly to period into the future.
Link: http://lkml.kernel.org/r/20190214193157.15788-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Łukasz Siudut <lsiudut@fb.com
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit 4e37504d1c)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: I40917c84354f9f32259c6703f00b6b1d21f45f02
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
The current help text caused some confusion in online forums about
whether or not to default-enable or default-disable psi in vendor
kernels. This is because it doesn't communicate the reason for why we
made this setting configurable in the first place: that the overhead is
non-zero in an artificial scheduler stress test.
Since this isn't representative of real workloads, and the effect was
not measurable in scheduler-heavy real world applications such as the
webservers and memcache installations at Facebook, it's fair to point
out that this is a pretty cautious option to select.
Link: http://lkml.kernel.org/r/20190129233617.16767-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit 7b2489d37e)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: I5d0cb901562fd74c82d9d211544745b802776d8a
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
psi has provisions to shut off the periodic aggregation worker when
there is a period of no task activity - and thus no data that needs
aggregating. However, while developing psi monitoring, Suren noticed
that the aggregation clock currently won't stay shut off for good.
Debugging this revealed a flaw in the idle design: an aggregation run
will see no task activity and decide to go to sleep; shortly thereafter,
the kworker thread that executed the aggregation will go idle and cause
a scheduling change, during which the psi callback will kick the
!pending worker again. This will ping-pong forever, and is equivalent
to having no shut-off logic at all (but with more code!)
Fix this by exempting aggregation workers from psi's clock waking logic
when the state change is them going to sleep. To do this, tag workers
with the last work function they executed, and if in psi we see a worker
going to sleep after aggregating psi data, we will not reschedule the
aggregation work item.
What if the worker is also executing other items before or after?
Any psi state times that were incurred by work items preceding the
aggregation work will have been collected from the per-cpu buckets
during the aggregation itself. If there are work items following the
aggregation work, the worker's last_func tag will be overwritten and the
aggregator will be kept alive to process this genuine new activity.
If the aggregation work is the last thing the worker does, and we decide
to go idle, the brief period of non-idle time incurred between the
aggregation run and the kworker's dequeue will be stranded in the
per-cpu buckets until the clock is woken by later activity. But that
should not be a problem. The buckets can hold 4s worth of time, and
future activity will wake the clock with a 2s delay, giving us 2s worth
of data we can leave behind when disabling aggregation. If it takes a
worker more than two seconds to go idle after it finishes its last work
item, we likely have bigger problems in the system, and won't notice one
sample that was averaged with a bogus per-CPU weight.
Link: http://lkml.kernel.org/r/20190116193501.1910-1-hannes@cmpxchg.org
Fixes: eb414681d5 ("psi: pressure stall information for CPU, memory, and IO")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit 1b69ac6b40)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: I2877fec3d381b1006b8bd1261895fdfd68bd21db
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Mel Gorman reports a hackbench regression with psi that would prohibit
shipping the suse kernel with it default-enabled, but he'd still like
users to be able to opt in at little to no cost to others.
With the current combination of CONFIG_PSI and the psi_disabled bool set
from the commandline, this is a challenge. Do the following things to
make it easier:
1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros
to enable CONFIG_PSI in their kernel but leave the feature disabled
unless a user requests it at boot-time.
To avoid double negatives, rename psi_disabled= to psi=.
2. Make psi_disabled a static branch to eliminate any branch costs
when the feature is disabled.
In terms of numbers before and after this patch, Mel says:
: The following is a comparision using CONFIG_PSI=n as a baseline against
: your patch and a vanilla kernel
:
: 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4
: kconfigdisable-v1r1 vanilla psidisable-v1r1
: Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%)
: Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%)
: Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%)
: Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%)
: Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%)
: Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%)
: Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%)
: Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%)
: Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%)
:
: It's showing that the vanilla kernel takes a hit (as the bisection
: indicated it would) and that disabling PSI by default is reasonably
: close in terms of performance for this particular workload on this
: particular machine so;
Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Mel Gorman <mgorman@techsingularity.net>
Reported-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit e0c274472d)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: I6cb666fa351e8901df82e4d6931bfec0c5ce230d
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
The existing code triggered an invalid warning about 'rq' possibly being
used uninitialized. Instead of doing the silly warning suppression by
initializa it to NULL, refactor the code to bail out early instead.
Warning was:
kernel/sched/psi.c: In function `cgroup_move_task':
kernel/sched/psi.c:639:13: warning: `rq' may be used uninitialized in this function [-Wmaybe-uninitialized]
Link: http://lkml.kernel.org/r/20181103183339.8669-1-olof@lixom.net
Fixes: 2ce7135adc ("psi: cgroup support")
Signed-off-by: Olof Johansson <olof@lixom.net>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit 8fcb2312d1)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: Id989da224a726082e0cfa5d5d9460bf63d448a93
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
When systems are overcommitted and resources become contended, it's hard
to tell exactly the impact this has on workload productivity, or how close
the system is to lockups and OOM kills. In particular, when machines work
multiple jobs concurrently, the impact of overcommit in terms of latency
and throughput on the individual job can be enormous.
In order to maximize hardware utilization without sacrificing individual
job health or risk complete machine lockups, this patch implements a way
to quantify resource pressure in the system.
A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that
expose the percentage of time the system is stalled on CPU, memory, or IO,
respectively. Stall states are aggregate versions of the per-task delay
accounting delays:
cpu: some tasks are runnable but not executing on a CPU
memory: tasks are reclaiming, or waiting for swapin or thrashing cache
io: tasks are waiting for io completions
These percentages of walltime can be thought of as pressure percentages,
and they give a general sense of system health and productivity loss
incurred by resource overcommit. They can also indicate when the system
is approaching lockup scenarios and OOMs.
To do this, psi keeps track of the task states associated with each CPU
and samples the time they spend in stall states. Every 2 seconds, the
samples are averaged across CPUs - weighted by the CPUs' non-idle time to
eliminate artifacts from unused CPUs - and translated into percentages of
walltime. A running average of those percentages is maintained over 10s,
1m, and 5m periods (similar to the loadaverage).
[hannes@cmpxchg.org: doc fixlet, per Randy]
Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org
[hannes@cmpxchg.org: code optimization]
Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org
[hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter]
Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org
[hannes@cmpxchg.org: fix build]
Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org
Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit eb414681d5)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: Id00d23c977169b0c4636d92016fc1fee0274be05
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Delay accounting already measures the time a task spends in direct reclaim
and waiting for swapin, but in low memory situations tasks spend can spend
a significant amount of their time waiting on thrashing page cache. This
isn't tracked right now.
To know the full impact of memory contention on an individual task,
measure the delay when waiting for a recently evicted active cache page to
read back into memory.
Also update tools/accounting/getdelays.c:
[hannes@computer accounting]$ sudo ./getdelays -d -p 1
print delayacct stats ON
PID 1
CPU count real total virtual total delay total delay average
50318 745000000 847346785 400533713 0.008ms
IO count delay total delay average
435 122601218 0ms
SWAP count delay total delay average
0 0 0ms
RECLAIM count delay total delay average
0 0 0ms
THRASHING count delay total delay average
19 12621439 0ms
Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit b1d29ba82c)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: I259f693987cf04e6a52ee7e8accf55a17e0de005
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Refaults happen during transitions between workingsets as well as in-place
thrashing. Knowing the difference between the two has a range of
applications, including measuring the impact of memory shortage on the
system performance, as well as the ability to smarter balance pressure
between the filesystem cache and the swap-backed workingset.
During workingset transitions, inactive cache refaults and pushes out
established active cache. When that active cache isn't stale, however,
and also ends up refaulting, that's bonafide thrashing.
Introduce a new page flag that tells on eviction whether the page has been
active or not in its lifetime. This bit is then stored in the shadow
entry, to classify refaults as transitioning or thrashing.
How many page->flags does this leave us with on 32-bit?
20 bits are always page flags
21 if you have an MMU
23 with the zone bits for DMA, Normal, HighMem, Movable
29 with the sparsemem section bits
30 if PAE is enabled
31 with this patch.
So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If
that's not enough, the system can switch to discontigmem and re-gain the 6
or 7 sparsemem section bits.
Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit 8508cf3ffa)
Bug: 127712811
Test: lmkd in PSI mode
Change-Id: I71df060dce5590a3c654f9a0e8e54deeb74b64c2
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Changes in 4.19.30
connector: fix unsafe usage of ->real_parent
gro_cells: make sure device is up in gro_cells_receive()
ipv4/route: fail early when inet dev is missing
l2tp: fix infoleak in l2tp_ip6_recvmsg()
lan743x: Fix RX Kernel Panic
lan743x: Fix TX Stall Issue
net: hsr: fix memory leak in hsr_dev_finalize()
net/hsr: fix possible crash in add_timer()
net: sit: fix UBSAN Undefined behaviour in check_6rd
net/x25: fix use-after-free in x25_device_event()
net/x25: reset state in x25_connect()
pptp: dst_release sk_dst_cache in pptp_sock_destruct
ravb: Decrease TxFIFO depth of Q3 and Q2 to one
route: set the deleted fnhe fnhe_daddr to 0 in ip_del_fnhe to fix a race
rxrpc: Fix client call queueing, waiting for channel
sctp: remove sched init from sctp_stream_init
tcp: do not report TCP_CM_INQ of 0 for closed connections
tcp: Don't access TCP_SKB_CB before initializing it
tcp: handle inet_csk_reqsk_queue_add() failures
vxlan: Fix GRO cells race condition between receive and link delete
vxlan: test dev->flags & IFF_UP before calling gro_cells_receive()
net/mlx4_core: Fix reset flow when in command polling mode
net/mlx4_core: Fix locking in SRIOV mode when switching between events and polling
net/mlx4_core: Fix qp mtt size calculation
net/x25: fix a race in x25_bind()
mdio_bus: Fix use-after-free on device_register fails
net: Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255
ipv6: route: purge exception on removal
team: use operstate consistently for linkup
ipvlan: disallow userns cap_net_admin to change global mode/flags
ipv6: route: enforce RCU protection in rt6_update_exception_stamp_rt()
ipv6: route: enforce RCU protection in ip6_route_check_nh_onlink()
bonding: fix PACKET_ORIGDEV regression
net/smc: fix smc_poll in SMC_INIT state
missing barriers in some of unix_sock ->addr and ->path accesses
net: sched: flower: insert new filter to idr after setting its mask
f2fs: wait on atomic writes to count F2FS_CP_WB_DATA
perf/x86: Fixup typo in stub functions
ALSA: bebob: use more identical mod_alias for Saffire Pro 10 I/O against Liquid Saffire 56
ALSA: firewire-motu: fix construction of PCM frame for capture direction
ALSA: hda: Extend i915 component bind timeout
ALSA: hda - add more quirks for HP Z2 G4 and HP Z240
ALSA: hda/realtek: Enable audio jacks of ASUS UX362FA with ALC294
ALSA: hda/realtek - Reduce click noise on Dell Precision 5820 headphone
ALSA: hda/realtek: Enable headset MIC of Acer TravelMate X514-51T with ALC255
perf/x86/intel: Fix memory corruption
perf/x86/intel: Make dev_attr_allow_tsx_force_abort static
It's wrong to add len to sector_nr in raid10 reshape twice
drm: Block fb changes for async plane updates
staging: erofs: fix race when the managed cache is enabled
i40e: report correct statistics when XDP is enabled
vhost/vsock: fix vhost vsock cid hashing inconsistent
Linux 4.19.30
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
commit 7fbe078c37 upstream.
The vsock core only supports 32bit CID, but the Virtio-vsock spec define
CID (dst_cid and src_cid) as u64 and the upper 32bits is reserved as
zero. This inconsistency causes one bug in vhost vsock driver. The
scenarios is:
0. A hash table (vhost_vsock_hash) is used to map an CID to a vsock
object. And hash_min() is used to compute the hash key. hash_min() is
defined as:
(sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)).
That means the hash algorithm has dependency on the size of macro
argument 'val'.
0. In function vhost_vsock_set_cid(), a 64bit CID is passed to
hash_min() to compute the hash key when inserting a vsock object into
the hash table.
0. In function vhost_vsock_get(), a 32bit CID is passed to hash_min()
to compute the hash key when looking up a vsock for an CID.
Because the different size of the CID, hash_min() returns different hash
key, thus fails to look up the vsock object for an CID.
To fix this bug, we keep CID as u64 in the IOCTLs and virtio message
headers, but explicitly convert u64 to u32 when deal with the hash table
and vsock core.
Fixes: 834e772c8d ("vhost/vsock: fix use-after-free in network stack callers")
Link: https://github.com/stefanha/virtio/blob/vsock/trunk/content.tex
Signed-off-by: Zha Bin <zhabin@linux.alibaba.com>
Reviewed-by: Liu Jiang <gerry@linux.alibaba.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Shengjing Zhu <i@zhsj.me>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit cdec2141c2 upstream.
When XDP is enabled, the driver will report incorrect
statistics. Received frames will reported as transmitted frames.
This commits fixes the i40e implementation of ndo_get_stats64 (struct
net_device_ops), so that iproute2 will report correct statistics
(e.g. when running "ip -stats link show dev eth0") even when XDP is
enabled.
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Fixes: 74608d17fe ("i40e: add support for XDP_TX action")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Emeric Brun <ebrun@haproxy.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 51232df5e4 upstream.
When the managed cache is enabled, the last reference count
of a workgroup must be used for its workstation.
Otherwise, it could lead to incorrect (un)freezes in
the reclaim path, and it would be harmful.
A typical race as follows:
Thread 1 (In the reclaim path) Thread 2
workgroup_freeze(grp, 1) refcnt = 1
...
workgroup_unfreeze(grp, 1) refcnt = 1
workgroup_get(grp) refcnt = 2 (x)
workgroup_put(grp) refcnt = 1 (x)
...unexpected behaviors
* grp is detached but still used, which violates cache-managed
freeze constraint.
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 25dc194b34 upstream.
The prepare_fb call always happens on new_plane_state.
The drm_atomic_helper_cleanup_planes checks to see if
plane state pointer has changed when deciding to call cleanup_fb on
either the new_plane_state or the old_plane_state.
For a non-async atomic commit the state pointer is swapped, so this
helper calls prepare_fb on the new_plane_state and cleanup_fb on the
old_plane_state. This makes sense, since we want to prepare the
framebuffer we are going to use and cleanup the the framebuffer we are
no longer using.
For the async atomic update helpers this differs. The async atomic
update helpers perform in-place updates on the existing state. They call
drm_atomic_helper_cleanup_planes but the state pointer is not swapped.
This means that prepare_fb is called on the new_plane_state and
cleanup_fb is called on the new_plane_state (not the old).
In the case where old_plane_state->fb == new_plane_state->fb then
there should be no behavioral difference between an async update
and a non-async commit. But there are issues that arise when
old_plane_state->fb != new_plane_state->fb.
The first is that the new_plane_state->fb is immediately cleaned up
after it has been prepared, so we're using a fb that we shouldn't
be.
The second occurs during a sequence of async atomic updates and
non-async regular atomic commits. Suppose there are two framebuffers
being interleaved in a double-buffering scenario, fb1 and fb2:
- Async update, oldfb = NULL, newfb = fb1, prepare fb1, cleanup fb1
- Async update, oldfb = fb1, newfb = fb2, prepare fb2, cleanup fb2
- Non-async commit, oldfb = fb2, newfb = fb1, prepare fb1, cleanup fb2
We call cleanup_fb on fb2 twice in this example scenario, and any
further use will result in use-after-free.
The simple fix to this problem is to block framebuffer changes
in the drm_atomic_helper_async_check function for now.
v2: Move check by itself, add a FIXME (Daniel)
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: <stable@vger.kernel.org> # v4.14+
Fixes: fef9df8b59 ("drm/atomic: initial support for asynchronous plane update")
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Link: https://patchwork.freedesktop.org/patch/275364/
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit b761dcf121 upstream.
In reshape_request it already adds len to sector_nr already. It's wrong to add len to
sector_nr again after adding pages to bio. If there is bad block it can't copy one chunk
at a time, it needs to goto read_more. Now the sector_nr is wrong. It can cause data
corruption.
Cc: stable@vger.kernel.org # v3.16+
Signed-off-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit cbc05fd670 upstream.
The Acer TravelMate X514-51T with ALC255 cannot detect the headset MIC
until ALC255_FIXUP_ACER_HEADSET_MIC quirk applied. Although, the
internal DMIC uses another module - snd_soc_skl as the driver. We still
need the NID 0x1a in the quirk to enable the headset MIC.
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Signed-off-by: Kailang Yang <kailang@realtek.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit c0ca5eced2 upstream.
Dell Precision 5820 with ALC3234 codec (which is equivalent with
ALC255) shows click noises at (runtime) PM resume on the headphone.
The biggest source of the noise comes from the cleared headphone pin
control at resume, which is done via the standard shutup procedure.
Although we have an override of the standard shutup callback to
replace with NOP, this would skip other needed stuff (e.g. the pull
down of headset power). So, instead, this "fixes" the behavior of
alc_fixup_no_shutup() by introducing spec->no_shutup_pins flag.
When this flag is set, Realtek codec won't call the standard
snd_hda_shutup_pins() & co. Now alc_fixup_no_shutup() just sets this
flag instead of overriding spec->shutup callback itself. This allows
us to apply the similar fix for other entries easily if needed in
future.
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 8bb37a2a4d upstream.
The ASUS UX362FA with ALC294 cannot detect the headset MIC and outputs
through the internal speaker and the headphone. This issue can be fixed
by the quirk in the commit 4e0511067 ALSA: hda/realtek: Enable audio
jacks of ASUS UX533FD with ALC294.
Besides, ASUS UX362FA and UX533FD have the same audio initial pin config
values. So, this patch replaces SND_PCI_QUIRK of UX533FD with a new
SND_HDA_PIN_QUIRK which benefits both UX362FA and UX533FD.
Fixes: 4e05110673 ("ALSA: hda/realtek: Enable audio jacks of ASUS UX533FD with ALC294")
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Signed-off-by: Ming Shuo Chiu <chiu@endlessm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit cfc35f9c12 upstream.
I set 10 seconds for the timeout of the i915 audio component binding
with a hope that recent machines are fast enough to handle all probe
tasks in that period, but I was too optimistic. The binding may take
longer than that, and this caused a problem on the machine with both
audio and graphics driver modules loaded in parallel, as Paul Menzel
experienced. This problem haven't hit so often just because the KMS
driver is loaded in initrd on most machines.
As a simple workaround, extend the timeout to 60 seconds.
Fixes: f9b54e1961 ("ALSA: hda/i915: Allow delayed i915 audio component binding")
Reported-by: Paul Menzel <pmenzel+alsa-devel@molgen.mpg.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit f97a0944a7 upstream.
In data blocks of common isochronous packet for MOTU devices, PCM
frames are multiplexed in a shape of '24 bit * 4 Audio Pack', described
in IEC 61883-6. The frames are not aligned to quadlet.
For capture PCM substream, ALSA firewire-motu driver constructs PCM
frames by reading data blocks byte-by-byte. However this operation
includes bug for lower byte of the PCM sample. This brings invalid
content of the PCM samples.
This commit fixes the bug.
Reported-by: Peter Sjöberg <autopeter@gmail.com>
Cc: <stable@vger.kernel.org> # v4.12+
Fixes: 4641c93940 ("ALSA: firewire-motu: add MOTU specific protocol layer")
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 31867b23d7 upstream.
Otherwise, we can get wrong counts incurring checkpoint hang.
IO_W (CP: -24, Data: 24, Flush: ( 0 0 1), Discard: ( 0 0))
Thread A Thread B
- f2fs_write_data_pages
- __write_data_page
- f2fs_submit_page_write
- inc_page_count(F2FS_WB_DATA)
type is F2FS_WB_DATA due to file is non-atomic one
- f2fs_ioc_start_atomic_write
- set_inode_flag(FI_ATOMIC_FILE)
- f2fs_write_end_io
- dec_page_count(F2FS_WB_CP_DATA)
type is F2FS_WB_DATA due to file becomes
atomic one
Cc: <stable@vger.kernel.org>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit ecb3dea400 ]
When adding new filter to flower classifier, fl_change() inserts it to
handle_idr before initializing filter extensions and assigning it a mask.
Normally this ordering doesn't matter because all flower classifier ops
callbacks assume rtnl lock protection. However, when filter has an action
that doesn't have its kernel module loaded, rtnl lock is released before
call to request_module(). During this time the filter can be accessed bu
concurrent task before its initialization is completed, which can lead to a
crash.
Example case of NULL pointer dereference in concurrent dump:
Task 1 Task 2
tc_new_tfilter()
fl_change()
idr_alloc_u32(fnew)
fl_set_parms()
tcf_exts_validate()
tcf_action_init()
tcf_action_init_1()
rtnl_unlock()
request_module()
... rtnl_lock()
tc_dump_tfilter()
tcf_chain_dump()
fl_walk()
idr_get_next_ul()
tcf_node_dump()
tcf_fill_node()
fl_dump()
mask = &f->mask->key; <- NULL ptr
rtnl_lock()
Extension initialization and mask assignment don't depend on fnew->handle
that is allocated by idr_alloc_u32(). Move idr allocation code after action
creation and mask assignment in fl_change() to prevent concurrent access
to not fully initialized filter when rtnl lock is released to load action
module.
Fixes: 01683a1469 ("net: sched: refactor flower walk to iterate over idr")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit ae3b564179 ]
Several u->addr and u->path users are not holding any locks in
common with unix_bind(). unix_state_lock() is useless for those
purposes.
u->addr is assign-once and *(u->addr) is fully set up by the time
we set u->addr (all under unix_table_lock). u->path is also
set in the same critical area, also before setting u->addr, and
any unix_sock with ->path filled will have non-NULL ->addr.
So setting ->addr with smp_store_release() is all we need for those
"lockless" users - just have them fetch ->addr with smp_load_acquire()
and don't even bother looking at ->path if they see NULL ->addr.
Users of ->addr and ->path fall into several classes now:
1) ones that do smp_load_acquire(u->addr) and access *(u->addr)
and u->path only if smp_load_acquire() has returned non-NULL.
2) places holding unix_table_lock. These are guaranteed that
*(u->addr) is seen fully initialized. If unix_sock is in one of the
"bound" chains, so's ->path.
3) unix_sock_destructor() using ->addr is safe. All places
that set u->addr are guaranteed to have seen all stores *(u->addr)
while holding a reference to u and unix_sock_destructor() is called
when (atomic) refcount hits zero.
4) unix_release_sock() using ->path is safe. unix_bind()
is serialized wrt unix_release() (normally - by struct file
refcount), and for the instances that had ->path set by unix_bind()
unix_release_sock() comes from unix_release(), so they are fine.
Instances that had it set in unix_stream_connect() either end up
attached to a socket (in unix_accept()), in which case the call
chain to unix_release_sock() and serialization are the same as in
the previous case, or they never get accept'ed and unix_release_sock()
is called when the listener is shut down and its queue gets purged.
In that case the listener's queue lock provides the barriers needed -
unix_stream_connect() shoves our unix_sock into listener's queue
under that lock right after having set ->path and eventual
unix_release_sock() caller picks them from that queue under the
same lock right before calling unix_release_sock().
5) unix_find_other() use of ->path is pointless, but safe -
it happens with successful lookup by (abstract) name, so ->path.dentry
is guaranteed to be NULL there.
earlier-variant-reviewed-by: "Paul E. McKenney" <paulmck@linux.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit d7cf4a3bf3 ]
smc_poll() returns with mask bit EPOLLPRI if the connection urg_state
is SMC_URG_VALID. Since SMC_URG_VALID is zero, smc_poll signals
EPOLLPRI errorneously if called in state SMC_INIT before the connection
is created, for instance in a non-blocking connect scenario.
This patch switches to non-zero values for the urg states.
Reviewed-by: Karsten Graul <kgraul@linux.ibm.com>
Fixes: de8474eb9d ("net/smc: urgent data support")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 3c963a3306 ]
This patch fixes a subtle PACKET_ORIGDEV regression which was a side
effect of fixes introduced by:
6a9e461f6f bonding: pass link-local packets to bonding master also.
... to:
b89f04c61e bonding: deliver link-local packets with skb->dev set to link that packets arrived on
While 6a9e461f6f restored pre-b89f04c61efe presence of link-local
packets on bonding masters (which is required e.g. by linux bridges
participating in spanning tree or needed for lab-like setups created
with group_fwd_mask) it also caused the originating device
information to be lost due to cloning.
Maciej Żenczykowski proposed another solution that doesn't require
packet cloning and retains original device information - instead of
returning RX_HANDLER_PASS for all link-local packets it's now limited
only to packets from inactive slaves.
At the same time, packets passed to bonding masters retain correct
information about the originating device and PACKET_ORIGDEV can be used
to determine it.
This elegantly solves all issues so far:
- link-local packets that were removed from bonding masters
- LLDP daemons being forced to explicitly bind to slave interfaces
- PACKET_ORIGDEV having no effect on bond interfaces
Fixes: 6a9e461f6f (bonding: pass link-local packets to bonding master also.)
Reported-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: Michal Soltys <soltys@ziu.info>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit bf1dc8bad1 ]
We need a RCU critical section around rt6_info->from deference, and
proper annotation.
Fixes: 4ed591c8ab ("net/ipv6: Allow onlink routes to have a device mismatch if it is the default route")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 193f3685d0 ]
We must access rt6_info->from under RCU read lock: move the
dereference under such lock, with proper annotation.
v1 -> v2:
- avoid using multiple, racy, fetch operations for rt->from
Fixes: a68886a691 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 7cc9f7003a ]
When running Docker with userns isolation e.g. --userns-remap="default"
and spawning up some containers with CAP_NET_ADMIN under this realm, I
noticed that link changes on ipvlan slave device inside that container
can affect all devices from this ipvlan group which are in other net
namespaces where the container should have no permission to make changes
to, such as the init netns, for example.
This effectively allows to undo ipvlan private mode and switch globally to
bridge mode where slaves can communicate directly without going through
hostns, or it allows to switch between global operation mode (l2/l3/l3s)
for everyone bound to the given ipvlan master device. libnetwork plugin
here is creating an ipvlan master and ipvlan slave in hostns and a slave
each that is moved into the container's netns upon creation event.
* In hostns:
# ip -d a
[...]
8: cilium_host@bond0: <BROADCAST,MULTICAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
ipvlan mode l3 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
inet 10.41.0.1/32 scope link cilium_host
valid_lft forever preferred_lft forever
[...]
* Spawn container & change ipvlan mode setting inside of it:
# docker run -dt --cap-add=NET_ADMIN --network cilium-net --name client -l app=test cilium/netperf
9fff485d69dcb5ce37c9e33ca20a11ccafc236d690105aadbfb77e4f4170879c
# docker exec -ti client ip -d a
[...]
10: cilium0@if4: <BROADCAST,MULTICAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
ipvlan mode l3 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0
valid_lft forever preferred_lft forever
# docker exec -ti client ip link change link cilium0 name cilium0 type ipvlan mode l2
# docker exec -ti client ip -d a
[...]
10: cilium0@if4: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0
valid_lft forever preferred_lft forever
* In hostns (mode switched to l2):
# ip -d a
[...]
8: cilium_host@bond0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
inet 10.41.0.1/32 scope link cilium_host
valid_lft forever preferred_lft forever
[...]
Same l3 -> l2 switch would also happen by creating another slave inside
the container's network namespace when specifying the existing cilium0
link to derive the actual (bond0) master:
# docker exec -ti client ip link add link cilium0 name cilium1 type ipvlan mode l2
# docker exec -ti client ip -d a
[...]
2: cilium1@if4: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
10: cilium0@if4: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0
valid_lft forever preferred_lft forever
* In hostns:
# ip -d a
[...]
8: cilium_host@bond0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
ipvlan mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
inet 10.41.0.1/32 scope link cilium_host
valid_lft forever preferred_lft forever
[...]
One way to mitigate it is to check CAP_NET_ADMIN permissions of
the ipvlan master device's ns, and only then allow to change
mode or flags for all devices bound to it. Above two cases are
then disallowed after the patch.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 8c7a77267e ]
When a port is added to a team, its initial state is derived
from netif_carrier_ok rather than netif_oper_up.
If it is carrier up but operationally down at the time of being
added, the port state.linkup will be set prematurely.
port state.linkup should be set consistently using
netif_oper_up rather than netif_carrier_ok.
Fixes: f1d22a1e05 ("team: account for oper state")
Signed-off-by: George Wilkie <gwilkie@vyatta.att-mail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
