Setting the doze registers wasn't actually working, and was being masked by a
bad #ifdef. Since the #ifdef was fixed, now e500mc-based SoCs hang at idle.
Fix this by using the intended wait.
MFC after: 1 week
The tag fastroute came from ipf and was removed in OpenBSD in 2011. The code
allows to skip the in pfil hooks and completely removes the out pfil invoke,
albeit looking up a route that the IP stack will likely find on its own.
The code between IPv4 and IPv6 is also inconsistent and marked as "XXX"
for years.
Submitted by: Franco Fichtner <franco@opnsense.org>
Differential Revision: https://reviews.freebsd.org/D8058
Reduce the cost of TLB invalidation on x86 by using per-CPU completion flags
Reduce contention during TLB invalidation operations by using a per-CPU
completion flag, rather than a single atomically-updated variable.
On a Westmere system (2 sockets x 4 cores x 1 threads), dtrace measurements
show that smp_tlb_shootdown is about 50% faster with this patch; observations
with VTune show that the percentage of time spent in invlrng_single_page on an
interrupt (actually doing invalidation, rather than synchronization) increases
from 31% with the old mechanism to 71% with the new one. (Running a basic file
server workload.)
Submitted by: Anton Rang <rang at acm.org>
Reviewed by: cem (earlier version)
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D8041
Usually there is some slack after the last partition due to 4k alignment
In the 10.3 EC2 images, there was not. EC2 seems to hang if you try to
read past the end of the disk in the loader, resulting in an unbootable
instance after upgrading to 11.0
PR: 213196
Reported by: Peter Ankerstal <peter@pean.org>
Tested by: cperciva
Reviewed by: tsoome
MFC after: 3 days
Sponsored by: ScaleEngine Inc.
Differential Revision: https://reviews.freebsd.org/D8144
These are older MIPS4kc parts from Atheros. They typically ran at
sub-200MHz and have 11bg, 11a, or 11abg wifi MAC/PHYs integrated.
This port is the initial non-wifi pieces required to bring up the
chip. I'll commit the redboot and other pieces later, and then
hopefully(!) wifi support will follow.
Submitted by: Mori Hiroki <yamori813@yahoo.co.jp>
Differential Revision: https://reviews.freebsd.org/D7237
for later Cortex-A CPUs that support the Multiprocessor Extensions. This
will be needed to support both in a single GENERIC kernel while still
being able to only build for a single SoC.
Reviewed by: mmel
Relnotes: yes
Sponsored by: ABT Systems Ltd
Differential Revision: https://reviews.freebsd.org/D8138
For the extended attributes the order between z_teardown_lock and the
vnode lock is different.
The bug was triggered only with DIAGNOSTIC turned on.
This fix is developed in cooperation with avos.
PR: 213112
Reported by: avos
Tested by: avos
MFC after: 1 week
This list is incomplete, however we don't have the ID values for the
missing Cortex-A32 or A35.
Submitted by: loos (Cortex-A53)
Sponsored by: ABT Systems Ltd
descriptors are reclaimed as soon as possible.
Without this the free buffers are reclaimed only on watchdog runs or after
trying to enqueue more packets.
Sponsored by: Rubicon Communications, LLC (Netgte)
On machines with just the wrong amount of physical memory (enough to
have a lot of bufs, but not enough to use VM_FREELIST_DMA32) it is
possible for 32-bit address limited devices to have little to no
memory left when attaching, due to potentially large vfs bio configs
consuming all memory below 4GB not protected by VM_FREELIST_ISADMA.
This causes the 32-bit devices to allocate from VM_FREELIST_ISADMA,
leaving that freelist emtpy when ISA devices need DMAable memory.
Rather than decrease VM_DMA32_NPAGES_THRESHOLD, use the time honored
technique of putting initially allocated kernel data structs
at the end (or at least not the beginning) of memory.
Since this allocation is done at boot and is wired, is not freed,
so the system is low on 32-bit (and ISA) dma'ble memory forever.
So it is a good candidate to move above 4GB.
While here, remove an unneeded round_page() from kmem_malloc's size
argument as suggested by alc. The first thing kmem_malloc() does
is a round_page(size), so there is no need to do it before the call.
Reviewed by: alc
Sponsored by: Netflix
- Initialize lock before starting worker process
- Do not hold lock when destroying evdev. By that time ther should be no
other active code pathes that can access softc
purgevfs is purely optional and induces lock contention in workloads
which frequently mount and unmount filesystems.
In particular, poudriere will do this for filesystems with 4 vnodes or
less. Full cache scan is clearly wasteful.
Since there is no explicit counter for namecache entries, the number of
vnodes used by the target fs is checked.
The default limit is the number of bucket locks.
Reviewed by: kib
Replace various void * / int argument combinations with common structures:
- ieee80211_ratectl_tx_status for *_tx_complete();
- ieee80211_ratectl_tx_stats for *_tx_update();
While here, improve amrr_tx_update() for a bit:
1. In case, if receiver is not known (typical for Ralink USB drivers),
refresh Tx rate for all nodes on the interface.
2. There was a misuse:
- otus(4) sends non-decreasing counters (as originally intended);
- but ural(4), rum(4) and run(4) are using 'read & clear' registers
to obtain statistics for some period of time (and those 'last period'
values are used as arguments for tx_update()). If arguments are not big
enough, they are just discarded after the next call.
Fix: move counting into *_tx_update()
(now otus(4) will zero out all node counters after every tx_update() call)
Tested with:
- Intel 3945BG (wpi(4)), STA mode.
- WUSB54GC (rum(4)), STA / HOSTAP mode.
- RTL8188EU (urtwn(4)), STA mode.
Reviewed by: adrian
Differential Revision: https://reviews.freebsd.org/D8037
- Add a counter into 'struct ieee80211_node_table' to save current number
of allocated nodes.
(allows to remove array overflow checking in ieee80211_iterate_nodes()).
- Add ieee80211_iterate_nodes_vap() function; unlike non-vap version,
it iterates on nodes for specified vap only.
In addition to the above:
- Remove ieee80211_iterate_nt(); it is not used by drivers / net80211
outside ieee80211_iterate_nodes() function + cannot be separated due
to structural changes in code.
Since size of 'struct ieee80211_node_table' (part of ieee80211com,
which is a part of driver's softc) is changed all wireless drivers /
kernel need to be recompiled.
Tested with wpi(4), STA mode.
Reviewed by: adrian
Differential Revision: https://reviews.freebsd.org/D7996
- Convert "options EVDEV" to "device evdev" and "device uinput", add
modules for both new devices. They are isolated subsystems and do not
require any compile-time changes to general kernel subsytems
- For hybrid drivers that have evdev as an optional way to deliver input
events add option EVDEV_SUPPORT. Update all existing hybrid drivers
to use it instead of EVDEV
- Remove no-op DECLARE_MODULE in evdev, it's not required, MODULE_VERSION
is enough
- Add evdev module dependency to uinput
Submitted by: Vladimir Kondratiev <wulf@cicgroup.ru>
A single gratuitous ARP (GARP) is always transmitted when an IPv4
address is added to an interface, and that is usually sufficient.
However, in some circumstances, such as when a shared address is
passed between cluster nodes, this single GARP may occasionally be
dropped or lost. This can lead to neighbors on the network link
working with a stale ARP cache and sending packets destined for
that address to the node that previously owned the address, which
may not respond.
To avoid this situation, GARP retransmissions can be enabled by setting
the net.link.ether.inet.garp_rexmit_count sysctl to a value greater
than zero. The setting represents the maximum number of retransmissions.
The interval between retransmissions is calculated using an exponential
backoff algorithm, doubling each time, so the retransmission intervals
are: {1, 2, 4, 8, 16, ...} (seconds).
Due to the exponential backoff algorithm used for the interval
between GARP retransmissions, the maximum number of retransmissions
is limited to 16 for sanity. This limit corresponds to a maximum
interval between retransmissions of 2^16 seconds ~= 18 hours.
Increasing this limit is possible, but sending out GARPs spaced
days apart would be of little use.
Submitted by: David A. Bright <david.a.bright@dell.com>
MFC after: 1 month
Relnotes: yes
Sponsored by: Dell EMC
Differential Revision: https://reviews.freebsd.org/D7695
This restriction was inherited from upstream but is not relevant on FreeBSD.
Furthermore, it hindered the tracing of locking primitive subroutines.
MFC after: 1 week
The kernel uses a few negative errno values for internal conditions
such as requesting a system call restart. Normally these errno values
are not exposed to userland. However, kdump needs access to these
values as some of then can be present in a ktrace system call return
record. Previously kdump was defining _KERNEL to gain access to ehse
values, but was then having to manually declare 'errno' (and doing it
incorrectly). Now, kdump uses _WANT_KERNEL_ERRNO instead of _KERNEL
and uses the system-provided declaration of errno.
is NULL and the function jumps to the "release:" label.
For this case, the "inp" was write locked, but the code attempted to
read unlock it. This patch fixes the problem.
This case could occur for NFS over UDP mounts, where the server was
down for a few minutes under certain circumstances.
Reported by: bde
Tested by: bde
Reviewed by: gnn
MFC after: 2 weeks
VM_MEMATTR_WRITE_COMBINING sets write-through cache flag for framebuffer
memory that prevents pixel data from being stuck in cache until evicition
happens
