That follows Linux and fixes related drm-kmod-5.3 panic.
Reviewed by: imp, hselasky
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D25657
Previously it would check 4, 3, 2, 1 lists. In practice by the time
it is getting called all lists have some elements and consequently
this does not result in new evictions.
Nonetheless, the code is clearer.
Tested by: pho
.. and stuff if into the unused target vnode field
This gets rid of concurrent nc_flag modifications racing with the
shrinker and consequently fixes a bug where such a change could have
been missed when cache_ncp_invalidate was being issued..
Reported by: zeising
Tested by: pho, zeising
Fixes: r362828 ("cache: lockless forward lookup with smr")
Stop using smp_ipi_mtx to protect global shootdown state, and
move/multiply the global state into pcpu. Now each CPU can initiate
shootdown IPI independently from other CPUs. Initiator enters
critical section, then fills its local PCPU shootdown info
(pc_smp_tlb_XXX), then clears scoreboard generation at location (cpu,
my_cpuid) for each target cpu. After that IPI is sent to all targets
which scan for zeroed scoreboard generation words. Upon finding such
word the shootdown data is read from corresponding cpu' pcpu, and
generation is set. Meantime initiator loops waiting for all zeroed
generations in scoreboard to update.
Initiator does not disable interrupts, which should allow
non-invalidation IPIs from deadlocking, it only needs to disable
preemption to pin itself to the instance of the pcpu smp_tlb data.
The generation is set before the actual invalidation is performed in
handler. It is safe because target CPU cannot return to userspace
before handler finishes. In principle only NMI can preempt the
handler, but NMI would see the kernel handler frame and not touch
not-invalidated user page table.
Handlers loop until they do not see zeroed scoreboard generations.
This, together with hardware keeping one pending IPI in LAPIC IRR
should prevent lost shootdowns.
Notes.
1. The code does protect writes to LAPIC ICR with exclusion. I believe
this is fine because we in fact do not send IPIs from interrupt
handlers. More for !x2APIC mode where ICR access for write requires
two registers write, we disable interrupts around it. If considered
incorrect, I can add per-cpu spinlock around ipi_send().
2. Scoreboard lines owned by given target CPU can be padded to the
cache line, to reduce ping-pong.
Reviewed by: markj (previous version)
Discussed with: alc
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 3 weeks
Differential revision: https://reviews.freebsd.org/D25510
In case of errors, the cleanup was not consistent.
Thanks to Felix Weinrank for fuzzing the userland stack and making
me aware of the issue.
MFC after: 1 week
realtime priorities
The current `ps -axO rtprio' show threads running at interrupt
priority such as the [intr] thread as '1:48' and threads running
at kernel priority such as [pagedaemon] as normal:4294967260.
This change shows [intr] as intr:48 and [pagedaemon] as kernel:4.
Reviewed by: kib
MFC after: 1 week (together with -r362369)
Differential Revision: https://reviews.freebsd.org/D25660
It can be useful to get a dump of all registers when investigating why we
received an exception that we are unable to handle. In these cases we
already call panic, however we don't always print the registers.
Add calls to print_registers and print esr and far when applicable.
Sponsored by: Innovate UK
It follows the equivalent Linux change to be able to differentiate
skylakex and cascadelakex, sharing the same model but not stepping.
This fixes skylakex handling broken by r363144.
MFC after: 6 days
The EIP-97 is a packet processing module found on the ESPRESSObin. This
commit adds a crypto(9) driver for the crypto and hash engine in this
device. An initial skeleton driver that could attach and submit
requests was written by loos and others at Netgate, and the driver was
finished by me.
Support for separate AAD and output buffers will be added in a separate
commit, to simplify merging to stable/12 (where those features don't
exist).
Reviewed by: gnn, jhb
Feedback from: andrew, cem, manu
MFC after: 1 week
Sponsored by: Rubicon Communications, LLC (Netgate)
Differential Revision: https://reviews.freebsd.org/D25417
so it can be used on other IOMMU systems.
Provide MI iommu_unit, iommu_domain and iommu_ctx structs in sys/iommu.h;
use them as a first member of MD dmar_unit, dmar_domain and dmar_ctx.
Change the namespace in DMAR backend: use iommu_ prefix instead of dmar_.
Move some macroses and function prototypes to sys/iommu.h.
Reviewed by: kib
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D25574
to coalesce tx work requests.
Note that Coverity will still treat this as an out-of-bounds access. We
do want to compare 16B starting from ethmacdst but cmp_l2hdr was was
going beyond that by 2B.
cmp_l2hdr was introduced in r362905.
Reported by: Coverity (CID 1430284)
Sponsored by: Chelsio Communications
When dummynet initializes it prints a debug message with the current VNET
pointer unnecessarily revealing kernel memory layout. This appears to be left
over from when the first pieces of vimage support were added.
PR: 238658
Submitted by: huangfq.daxian@gmail.com
Reviewed by: markj, bz, gnn, kp, melifaro
Approved by: jtl (co-mentor), bz (co-mentor)
Event: July 2020 Bugathon
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D25619
The statement "nd->nd_bpos = mcp;" was in both the if and else. Correct,
but potentially confusing. This patch fixes this.
There should be no semantics change caused by this commit.
This file is only compiled if INET or INET6 is defined. So there
is no need for checking that.
Reviewed by: markj
Differential Revision: https://reviews.freebsd.org/D25635
r363079 introduced the possibility of loading the SCTP stack as a module in
addition to compiling it into the kernel. As part of this, the registration
of the system calls was removed and put into the loading of the module.
Therefore, the system calls are not registered anymore when compiling the
SCTP into the kernel. This patch addresses that.
Reviewed by: markj
Differential Revision: https://reviews.freebsd.org/D25632
Old subscription model allowed only single customer.
Switch inet6 to the new subscription api and eliminate the old model.
Differential Revision: https://reviews.freebsd.org/D25615
Subscriptions are planned to be used by modules such as route lookup engines.
In that case that's the module task to properly unsibscribe before detach.
However, the in-kernel customer - inet6 wants to track default route changes.
To avoid having inet6 store per-fib subscriptions, handle automatic
destruction internally.
Differential Revision: https://reviews.freebsd.org/D25614
It is documented as a raw hardware-based clock not subject to NTP or
incremental adjustments. With this "not as precise as CLOCK_MONOTONIC"
description in mind, map it to our CLOCK_MONOTNIC_FAST (the same
mapping as for the linux CLOCK_MONOTONIC_COARSE).
This is needed for the webcomponent of steam (chromium) and some
other steam component or game.
The linux-steam-utils port contains a LD_PRELOAD based fix for this.
There this is mapped to CLOCK_MONOTONIC.
As an untrained ear/eye (= the majority of people) is normaly not
noticing a difference of jitter in the 10-20 ms range, specially
if you don't pay attention like for example in a browser session
while watching a video stream, the mapping to CLOCK_MONOTONIC_FAST
seems more appropriate than to CLOCK_MONOTONIC.
Linux processes these clocks in reverse order and some DT relies
on this fact. For example, the frequency setting for a given PLL
is the last in the list, preceded by the frequency setting of its
following divider or so...
MFC after: 1 week
Module name (unlike of the of driver name) must be system wide unique.
Reported by: Mark Millard(bcm_pci), andrew(mvebu_gpio)
MFC with: r362954, r362385
We don't expect to fail acquiring the reference unless running into a corner
case. Just in case ensure forward progress by taking the lock.
Reviewed by: kib, markj
Differential Revision: https://reviews.freebsd.org/D25616
Fixes sudo (sudo-1.8.21p2-3ubuntu1.2); previously would fail
with "sudo: no tty present and no askpass program specified".
Reviewed by: kib, emaste
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25588
The reason for this is to work around an idiosyncrasy of glibc
getttynam(3) implementation: it checks whether st_dev returned for
fd 0 is the same as st_dev returned for the target of /proc/self/fd/0
symlink, and with linux chroots having their own devfs instance,
the check will fail if you chrooted into it.
PR: kern/240767
Reviewed by: kib
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25559
With this change, a kernel compiled with "options SCTP_SUPPORT" and
without "options SCTP" supports dynamic loading of the SCTP stack.
Currently sctp.ko cannot be unloaded since some prerequisite teardown
logic is not yet implemented. Attempts to unload the module will return
EOPNOTSUPP.
Discussed with: tuexen
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D21997
checks if the bitmap pointed to by the first argument is a subset of
the bitmap pointed to by the second argument. The function returns one
on success and zero on failure.
MFC after: 1 week
Sponsored by: Mellanox Technologies
basically multiplies its two arguments and returns SIZE_MAX if the
result overflows the size_t type. Else the product of the two
arguments is returned.
Bump the FreeBSD_version to mitigate issues with existing
implementation of array_size() in drm-devel-kmod.
Discussed with: manu@
MFC after: 1 week
Sponsored by: Mellanox Technologies
The kernel would unlock already unlocked mutex if the buffer got filled up
before the mount list ended.
Reported by: pho
Fixes: r363069 ("vfs: depessimize getfsstat when only the count is requested")
memfd_create fds will no longer require an ftruncate(2) to set the size;
they'll grow (to the extent that it's possible) upon write(2)-like syscalls.
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D25502
Lack of SHM_GROW_ON_WRITE is actively breaking Python's memfd_create tests,
so go ahead and implement it. A future change will make memfd_create always
set SHM_GROW_ON_WRITE, to match Linux behavior and unbreak Python's tests
on -CURRENT.
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D25502
On 32-bit platforms, this expands the shm_size to a 64-bit quantity and
resolves a mismatch between the shmfd size and underlying vm_object size.
The implementation did not account for this kind of mismatch.
Reviewed by: kib
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D25602
While this behaviour is harmless, it is really just an artifact of the
fact that the msgctl(2) implementation uses a user-visible structure as
part of the internal implementation, so it is not deliberate and these
pointers are not useful to userspace. Thus, NULL them out before
copying out, and remove references to them from the manual page.
Reported by: Jeffball <jeffball@grimm-co.com>
Reviewed by: emaste, kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25600
Communicating with the Raspberry Pi firmware is currently handled by each
driver calling into the mbox driver, however the device tree is structured
such that they should be calling into a firmware driver.
Add a driver for this node with an interface to communicate to the firmware
via the mbox interface.
There is a sysctl to get the firmware revision. This is a unix date so can
be parsed with:
root@generic:~ # date -j -f '%s' sysctl -n dev.bcm2835_firmware.0.revision
Tue Nov 19 16:40:28 UTC 2019
Reviewed by: manu
Sponsored by: Innovate UK
Differential Revision: https://reviews.freebsd.org/D25572
Every revision of twsi after the A20 have a bug where we need to
write again the control register after each interrupts. We also need
to add some delay before writing to this register, a simple read of the
same register does the job so do that.
Also fix the case when we have finish sending all the bytes, it only worked
for 1 byte transfer (the same kind that we do for talking to the PMIC on A20
boards).
While here add more debug messages and rework some of them.
This was tested by talking to a AT23C32 eeprom and a DS3231 RTC from an
H3 and A20 board.
PR: 247576
Reported by: Manuel Stühn (freebsd@justmail.de)
MFC after: 1 week
On some boards there is a lot of of syscon node that are unused as
more specific drivers is probed before, no need to flood the console
for the mostly-unused generic ones.
MFC after: 1 week
geli does all of its crypto operations in a separate thread pool, so
g_eli_start, g_eli_read_done, and g_eli_write_done don't actually do very
much work. Enabling direct dispatch eliminates the g_up/g_down bottlenecks,
doubling IOPs on my system. This change does not affect the thread pool.
Reviewed by: markj
MFC after: 2 weeks
Sponsored by: Axcient
Differential Revision: https://reviews.freebsd.org/D25587
This patch uses a slightly different algorithm for the non-ext_pgs case,
where a variable called "mcp" is maintained, pointing to the current
location that mbuf data can be filled into. This avoids use of
mtod(mp, char *) + mp->m_len to calculate the location, since this does
not work for ext_pgs mbufs and I think it makes the algorithm more readable.
This change should not result in semantic changes for the non-ext_pgs case.
This is another in the series of commits that add support to the NFS client
and server for building RPC messages in ext_pgs mbufs with anonymous pages.
This is useful so that the entire mbuf list does not need to be
copied before calling sosend() when NFS over TLS is enabled.
Since ND_EXTPG is never set yet, there is no semantic change at this time.
While testing with system default cc set to cubic, and
running a memory exhaustion validation, FreeBSD panics for a
missing inpcb reference / lock.
Reviewed by: rgrimes (mentor), tuexen (mentor)
Approved by: rgrimes (mentor), tuexen (mentor)
MFC after: 3 weeks
Sponsored by: NetApp, Inc.
Differential Revision: https://reviews.freebsd.org/D25583
This is another in the series of commits that add support to the NFS client
and server for building RPC messages in ext_pgs mbufs with anonymous pages.
This is useful so that the entire mbuf list does not need to be
copied before calling sosend() when NFS over TLS is enabled.
Since ND_EXTPG is never set yet, there is no semantic change at this time.
We cannot complete the interrupt (i.e. write to the claims/complete register
until the interrupt handler has actually run. We don't run the interrupt
handler immediately from intr_isrc_dispatch(), we only schedule it for later
execution.
If we immediately complete it (i.e. before the interrupt handler proper has
run) the interrupt may be triggered again if the interrupt source remains set.
From RISC-V Instruction Set Manual: Volume II: Priviliged Architecture, 7.4
Interrupt Gateways:
"If a level-sensitive interrupt source deasserts the interrupt after the PLIC
core accepts the request and before the interrupt is serviced, the interrupt
request remains present in the IP bit of the PLIC core and will be serviced by
a handler, which will then have to determine that the interrupt device no
longer requires service."
In other words, we may receive interrupts twice.
Avoid that by postponing the completion until after the interrupt handler has
run.
If the interrupt is handled by a filter rather than by scheduling an interrupt
thread we must also complete the interrupt, so set up a post_filter handler
(which is the same as the post_ithread handler).
Reviewed by: mhorne
Sponsored by: Axiado
Differential Revision: https://reviews.freebsd.org/D25531
Now nhop_ref_object() unconditionally acquires a reference, and the new
nhop_try_ref_object() uses refcount_acquire_if_not_zero() to
conditionally acquire a reference. Since the former is cheaper, use it
when we know that the initial counter value is non-zero. No functional
change intended.
Reviewed by: melifaro
Differential Revision: https://reviews.freebsd.org/D25535
This implementation doesn't have any major deviations from the other EFI
ports. I've copied the boilerplate from arm and arm64.
I've tested this with the following boot flows:
OpenSBI (M-mode) -> u-boot (S-mode) -> loader.efi -> FreeBSD
OpenSBI (M-mode) -> u-boot (S-mode) -> boot1.efi -> loader.efi -> FreeBSD
Due to the way that u-boot handles secondary CPUs, OpenSBI >= v0.7 is required,
as the HSM extension is needed to bring them up explicitly. Because of this,
using BBL as the SBI implementation will not be possible. Additionally, there
are a few recent u-boot changes that are required as well, all of which will be
present in the upcoming v2020.07 release.
Looks good: emaste
Differential Revision: https://reviews.freebsd.org/D25135
These system calls already perform validation of their parameters when
called in capability mode, identical to cpuset_(get|set)affinity().
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
cpuset_(get|set)(affinity|domain)(2) permit a get or set of the calling
thread or process' CPU and domain set in capability mode, but only when
the thread or process ID is specified as -1. Extend this to cover the
case where the ID actually matches the caller's TID or PID, since some
code, such as our pthread_attr_get_np() implementation, always provides
an explicit ID.
It was not and still is not permitted to access CPU and domain sets for
other threads in the same process when the process is in capability
mode. This might change in the future.
Submitted by: Greg V <greg@unrelenting.technology> (original version)
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D25552
Add a more compact display format for kern.tty_info_kstacks inspired by
procstat -kk. Set it as a default one.
# sysctl kern.tty_info_kstacks=1
kern.tty_info_kstacks: 0 -> 1
# sleep 2
^T
load: 0.17 cmd: sleep 623 [nanslp] 0.72r 0.00u 0.00s 0% 2124k
#0 0xffffffff80c4443e at mi_switch+0xbe
#1 0xffffffff80c98044 at sleepq_catch_signals+0x494
#2 0xffffffff80c982c2 at sleepq_timedwait_sig+0x12
#3 0xffffffff80c43af3 at _sleep+0x193
#4 0xffffffff80c50e31 at kern_clock_nanosleep+0x1a1
#5 0xffffffff80c5119b at sys_nanosleep+0x3b
#6 0xffffffff810ffc69 at amd64_syscall+0x119
#7 0xffffffff810d5520 at fast_syscall_common+0x101
sleep: about 1 second(s) left out of the original 2
^C
# sysctl kern.tty_info_kstacks=2
kern.tty_info_kstacks: 1 -> 2
# sleep 2
^T
load: 0.24 cmd: sleep 625 [nanslp] 0.81r 0.00u 0.00s 0% 2124k
mi_switch+0xbe sleepq_catch_signals+0x494 sleepq_timedwait_sig+0x12
sleep+0x193 kern_clock_nanosleep+0x1a1 sys_nanosleep+0x3b
amd64_syscall+0x119 fast_syscall_common+0x101
sleep: about 1 second(s) left out of the original 2
^C
Suggested by: avg
Reviewed by: mjg
Relnotes: yes
Sponsored by: Mysterious Code Ltd.
Differential Revision: https://reviews.freebsd.org/D25487
Otherwise the same checks are duplicated across four different system
call implementations, cpuset_(get|set)(affinity|domain)(). No
functional change intended.
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
* Only read the DPCPU pointer once per xive_dispatch call.
* Optimize HE decoding for the common cases.
Reported by: jhibbits (in irc)
Reviewed by: jhibbits
Sponsored by: Tag1 Consulting, Inc.
Differential Revision: https://reviews.freebsd.org/D25545
- Get rid of the ifl_vm_addrs array. It is not used by any existing
consumer, so we are just dirtying a couple of cache lines for no
reason.
- Use uma_zalloc(fl->ifl_zone) instead of m_cljget(). Otherwise
m_cljget() is doing unnecessary work to look up the correct zone, when
iflib already knows what that zone is.
- ifl_gen is only used when INVARIANTS is on, so make that more clear.
- Fix some style nits and inconsistencies.
Reviewed by: gallatin
Tested by: pho
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25490
When refilling an rx freelist, make sure we only update the hardware
producer index if at least one cluster was allocated. Otherwise the
NIC is programmed to write a previously used cluster, typically
resulting in a use-after-free when packet data is written by the
hardware.
Also make sure that we don't update the fragment index cursor if the
last allocation attempt didn't succeed. For at least Intel drivers,
iflib assumes that the consumer index and fragment index cursor stay in
lockstep, but this assumption was violated in the face of cluster
allocation failures.
Reported and tested by: pho
Reviewed by: gallatin, hselasky
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25489
This adds support for the Broadcom bcm2711 PCI express controller, found
on the Raspberry Pi 4 (aka the bcm2838 SoC). The driver has only been
developed against the soldered-on VIA XHCI controller and not tested
with other end points.
Submitted by: Robert Crowston <crowston_protonmail.com>
Differential Revision: https://reviews.freebsd.org/D25068
Currently the linking order of the infiniband, IB, modules decide in which
order the clients are attached and detached. For example one IB client may
use resources from another IB client. This can lead to a potential deadlock
at shutdown. For example if the ipoib is unregistered after the ib_multicast
client is detached, then if ipoib is using multicast addresses a deadlock may
happen, because ib_multicast will wait for all its resources to be freed before
returning from the remove method.
Fix this by using module_xxx_order() instead of module_xxx().
Differential Revision: https://reviews.freebsd.org/D23973
MFC after: 1 week
Sponsored by: Mellanox Technologies
Also, add a new function nfsm_add_ext_pgs() which will either add a page
or add a new ext_pgs mbuf with a page to the mbuf list. Used by nfsm_strtom().
This is another in the series of commits that add support to the NFS client
and server for building RPC messages in ext_pgs mbufs with anonymous pages.
This is useful so that the entire mbuf list does not need to be
copied before calling sosend() when NFS over TLS is enabled.
Since ND_EXTPG is never set yet, there is no semantic change at this time.
On architectures that use RELA relocations it is safe to rerun the ifunc
resolvers on after all CPUs have started, but while they are sill parked.
On arm64 with big.LITTLE this is needed as some SoCs have shipped with
different ID register values the big and little clusters meaning we were
unable to rely on the register values from the boot CPU.
Add support for rerunning the resolvers on arm64 and amd64 as these are
both RELA using architectures.
Reviewed by: kib
Sponsored by: Innovate UK
Differential Revision: https://reviews.freebsd.org/D25455
it would fail with EINVAL, breaking some of the Python regression
tests.
While here, cap the user-controlled message length.
Note that the code doesn't seem to be copying out the new length
in either (success or failure) case. This will be addressed separately.
Reviewed by: kib
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25392
create /sys/class/power_supply/. This silences some warnings
from biology/linux-foldingathome.
Reported by: 0mp
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D25557
TCGETS et al are frequently issued by Linux binaries while the previous code
avoidably ping-pongs a global sx lock and serializes on Giant.
Note that even with the fix the common case will serialize on a per-tty lock.
This is another in the series of commits that add support to the NFS client
and server for building RPC messages in ext_pgs mbufs with anonymous pages.
This is useful so that the entire mbuf list does not need to be
copied before calling sosend() when NFS over TLS is enabled.
Since ND_EXTPG is never set yet, there is no semantic change at this time.
Like other types of allocation, fpu_kern_ctx are frequently allocated per-cpu.
Provide the API and sketch some example consumers.
fpu_kern_alloc_ctx_domain() preferentially allocates memory from the
provided domain, and falls back to other domains if that one is empty
(DOMAINSET_PREF(domain) policy).
Maybe it makes more sense to just shove one of these in the DPCPU area
sooner or later -- left for future work.
Reviewed by: markj
Differential Revision: https://reviews.freebsd.org/D22053
They trigger for some people, the bug is not obvious, there are no takers
for fixing it, the issue already had to be there for years beforehand and
is low priority.