Ability to load-balance traffic over multiple path is a must-have thing for routers.
It may be used by the servers to balance outgoing traffic over multiple default gateways.
The previous implementation, RADIX_MPATH stayed in the shadow for too long.
It was not well maintained, which lead us to a vicious circle - people were using
non-contiguous mask or firewalls to achieve similar goals. As a result, some routing
daemons implementation still don't have multipath support enabled for FreeBSD.
Turning on ROUTE_MPATH by default would fix it. It will allow to reduce networking
feature gap to other operating systems. Linux and OpenBSD enabled similar support
at least 5 years ago.
ROUTE_MPATH does not consume memory unless actually used. It enables around ~1k LOC.
It does not bring any behaviour changes for userland.
Additionally, feature is (temporarily) turned off by the net.route.multipath sysctl
defaulting to 0.
Differential Revision: https://reviews.freebsd.org/D27428
Follow-up to r353959 and r368070: do the same for other architectures.
arm32 already seems to use its own .fnstart/.fnend directives, which
appear to be ARM-specific variants of the same thing. Likewise, MIPS
uses .frame directives.
Reviewed by: arichardson
Differential Revision: https://reviews.freebsd.org/D27387
In the PCB struct, we need to match the VSX register file layout
correctly, as the VSRs shadow the FPRs.
In LE, we need to have a dword of padding before the fprs so they end up
on the correct side, as the struct may be manipulated by either the FP
routines or the VSX routines.
Additionally, when saving and restoring fprs, we need to explicitly target
the fpr union member so it gets offset correctly on LE.
Fixes weirdness with FP registers in VSX-using programs (A FPR that was
saved by the FP routines but restored by the VSX routines was becoming 0
due to being loaded to the wrong side of the VSR.)
Original patch by jhibbits.
Reviewed by: jhibbits
Differential Revision: https://reviews.freebsd.org/D27431
Replace MAXPHYS by runtime variable maxphys. It is initialized from
MAXPHYS by default, but can be also adjusted with the tunable kern.maxphys.
Make b_pages[] array in struct buf flexible. Size b_pages[] for buffer
cache buffers exactly to atop(maxbcachebuf) (currently it is sized to
atop(MAXPHYS)), and b_pages[] for pbufs is sized to atop(maxphys) + 1.
The +1 for pbufs allow several pbuf consumers, among them vmapbuf(),
to use unaligned buffers still sized to maxphys, esp. when such
buffers come from userspace (*). Overall, we save significant amount
of otherwise wasted memory in b_pages[] for buffer cache buffers,
while bumping MAXPHYS to desired high value.
Eliminate all direct uses of the MAXPHYS constant in kernel and driver
sources, except a place which initialize maxphys. Some random (and
arguably weird) uses of MAXPHYS, e.g. in linuxolator, are converted
straight. Some drivers, which use MAXPHYS to size embeded structures,
get private MAXPHYS-like constant; their convertion is out of scope
for this work.
Changes to cam/, dev/ahci, dev/ata, dev/mpr, dev/mpt, dev/mvs,
dev/siis, where either submitted by, or based on changes by mav.
Suggested by: mav (*)
Reviewed by: imp, mav, imp, mckusick, scottl (intermediate versions)
Tested by: pho
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D27225
It can useful for code outside the VM system to look up the NUMA domain
of a page backing a virtual or physical address, specifically when
creating NUMA-aware data structures. We have _vm_phys_domain() for
this, but the leading underscore implies that it's an internal function,
and vm_phys.h has dependencies on a number of other headers.
Rename vm_phys_domain() to vm_page_domain(), and _vm_phys_domain() to
vm_phys_domain(). Make the latter an inline function.
Add _vm_phys.h and define struct vm_phys_seg there so that it's easier
to use in other headers. Include it from vm_page.h so that
vm_page_domain() can be defined there.
Include machine/vmparam.h from _vm_phys.h since it depends directly on
some constants defined there.
Reviewed by: alc
Reviewed by: dougm, kib (earlier versions)
Differential Revision: https://reviews.freebsd.org/D27207
r367416 should have called save_fpu() before kern_sigprocmask to avoid
race condition
Thanks jhibbits and bdragon for pointing it out
Reviewed by: jhibbits
Sponsored by: Eldorado Research Institute (eldorado.org.br)
Differential Revision: https://reviews.freebsd.org/D27241
After r367417, both mmu_oea64 and mmu_radix were defining the vm.pmap
sysctl node, resulting in the later definition hiding the properties of
the previous one. Avoid this issue by defining vm.pmap in a common
source file and declaring it where needed.
This change also standardizes the tunable name used to enable superpages
and change its default to disabled on radix MMU, because it still has some
issues with superpages.
Reviewed by: bdragon, jhibbits
Sponsored by: Eldorado Research Institute (eldorado.org.br)
Differential Revision: https://reviews.freebsd.org/D27156
There were many, many endianness fixes needed for Radix MMU. The Radix
pagetable is stored in BE (as it is read and written to by the MMU hw),
so we need to convert back and forth every time we interact with it when
running in LE.
With these changes, I can successfully boot with radix enabled on POWER9 hw.
Reviewed by: luporl, jhibbits
Sponsored by: Tag1 Consulting, Inc.
Differential Revision: https://reviews.freebsd.org/D27181
The HPT is always stored in big-endian, as it is accessed directly by the
hardware as well as the kernel. As such, it is necessary to convert values
to and from native endian when running on LE.
Some unconverted accesses snuck in accidentally with r367417.
Apply the appropriate conversions to fix boot hanging on powerpc64le.
Sponsored by: Tag1 Consulting, Inc.
This brings its 'struct syscall_args' in sync with other architectures.
Reviewed by: bdragon, jhibbits
MFC after: 2 weeks
Sponsored by: EPSRC
Differential Revision: https://reviews.freebsd.org/D26605
Fix build errors introduced by r367417 and r367390:
- Guard label reached only by powerpc64
- Guard vm_reserv_level_iffullpop call, that is not defined on powerpc
variants that don't support superpages
- Add missing hwpmc file, for when hwpmc is built into kernel
This change adds support for transparent superpages for PowerPC64
systems using Hashed Page Tables (HPT). All pmap operations are
supported.
The changes were inspired by RISC-V implementation of superpages,
by @markj (r344106), but heavily adapted to fit PPC64 HPT architecture
and existing MMU OEA64 code.
While these changes are not better tested, superpages support is disabled by
default. To enable it, use vm.pmap.superpages_enabled=1.
In this initial implementation, when superpages are disabled, system
performance stays at the same level as without these changes. When
superpages are enabled, buildworld time increases a bit (~2%). However,
for workloads that put a heavy pressure on the TLB the performance boost
is much bigger (see HPC Challenge and pgbench on D25237).
Reviewed by: jhibbits
Sponsored by: Eldorado Research Institute (eldorado.org.br)
Differential Revision: https://reviews.freebsd.org/D25237
Add support for Floating-Point Exception traps on 32 and 64 bit platforms.
Also make sure to clean FPSCR on EXEC and thread exit
Author of initial version: Renato Riolino <renato.riolino@eldorad.org.br>
Reviewed by: jhibbits
Sponsored by: Eldorado Research Institute (eldorado.org.br)
Differential Revision: https://reviews.freebsd.org/D23623
This change adds support for POWER8 and POWER9 PMCs (bare metal and
pseries).
All PowerISA 2.07B non-random events are supported.
Implementation was based on that of PPC970.
Reviewed by: jhibbits
Sponsored by: Eldorado Research Institute (eldorado.org.br)
Differential Revision: https://reviews.freebsd.org/D26110
And add a _74XX suffix to 74XX SPRs.
This is a preparation for adding support to POWER8/9 PMCs, which have most
SPRs equal to 970 ones.
Reviewed by: jhibbits
Sponsored by: Eldorado Research Institute (eldorado.org.br)
Differential Revision: https://reviews.freebsd.org/D26532
VM_ALLOC_WAITOK and vm_page_unwire_noq(), have eliminated the need for
many of the #includes.
Reviewed by: kib, markj
Differential Revision: https://reviews.freebsd.org/D27052
Move dump_avail[] extern declaration and inlines into a new header
vm/vm_dumpset.h. This fixes default gcc build for mips.
Reviewed by: alc, scottph
Tested by: kevans (previous version)
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D26741
Push the root seed version to userspace through the VDSO page, if
the RANDOM_FENESTRASX algorithm is enabled. Otherwise, there is no
functional change. The mechanism can be disabled with
debug.fxrng_vdso_enable=0.
arc4random(3) obtains a pointer to the root seed version published by
the kernel in the shared page at allocation time. Like arc4random(9),
it maintains its own per-process copy of the seed version corresponding
to the root seed version at the time it last rekeyed. On read requests,
the process seed version is compared with the version published in the
shared page; if they do not match, arc4random(3) reseeds from the
kernel before providing generated output.
This change does not implement the FenestrasX concept of PCPU userspace
generators seeded from a per-process base generator. That change is
left for future discussion/work.
Reviewed by: kib (previous version)
Approved by: csprng (me -- only touching FXRNG here)
Differential Revision: https://reviews.freebsd.org/D22839
Now that config(8) has supported include for 19 years, transition to
including the NOTES files. include support didn't exist at the time,
nor did the envvar stuff recently added. Now that it does, eliminate
the building of LINT files by just including everything you need.
Note: This may cause conflicts with updating in some cases.
find sys -name LINT\* -rm
is suggested across this commit to remove the generated LINT
files.
Reviewed by: kevans
Differential Revision: https://reviews.freebsd.org/D26540
Add support for sysctl 'machdep.uprintf_signal' that prints debugging
information on trap signal.
Reviewed by: jhibbits, luporl, bdragon
Sponsored by: Eldorado Research Institute (eldorado.org.br)
Differential Revision: https://reviews.freebsd.org/D26004
It is unlikely, but possible, that an unrecognized or unsupported
relocation type is encountered while trying to load a kernel module. If
this occurs we should offer the symbol index as a hint to the user.
While here, fix some small style issues.
Reviewed by: markj, kib (amd64 part, in D26701)
Sponsored by: NetApp, Inc.
Sponsored by: Klara, Inc.
Similar to OPAL calls, switch to big endian to do calls to RTAS.
(Missed this one when I was doing the bulk commit of PowerPC64LE support.)
Sponsored by: Tag1 Consulting, Inc.
Due to enter_idle_powerx fabricating a MSR from scratch, it is necessary
for it to care about the endianness, so we don't accidentally switch
endian the first time we idle a thread.
Took about five seconds to spot after seeing an unmangled backtrace.
The hard bit was needing to temporarily set up a mutex to sort out the
logjam that happens when every thread simultaneously wakes up in the wrong
endian due to the panic IPI and panics, leaving what I can best describe as
"alphabet soup" on the console.
Luckily, I already had a patch sitting around to do that.
This brings POWER8 up to equivilence with POWER9 on PPC64LE.
Sponsored by: Tag1 Consulting, Inc.
OPAL unconditionally enters secondary CPUs with only HV and SF set.
I tried writing a secondary entry point instead, but OPAL rejected it
and I am unsure why, so I resorted to making the system reset interrupt
endian-flexible.
This means we take a slight performance hit on wakeup on LE, but it is
a good stopgap until we can figure out a reliable way to make OPAL enter
where we want it to.
It probably makes sense to have it around anyway, because I can imagine
scenarios where the cpu resets itself to BE and does a software reset.
Sponsored by: Tag1 Consulting, Inc.
More endian conversion.
* Install TCEs correctly (i.e. in big endian)
* Convert to big endian and back when setting up queue pages and IRQs.
Sponsored by: Tag1 Consulting, Inc.
Since OPAL runs in big endian, any data being passed back and forth
via memory instead of registers needs to be byteswapped.
From my notes during development:
"A good way to find candidates is to look for vtophys() in opal_call()
parameters. The memory being passed will be written into in BE."
Sponsored by: Tag1 Consulting, Inc.
It's much easier to implement this in an endian-independent way when we
don't also have to worry about masking half of the dword off.
Given that this code ran on a machine that ran a poudriere bulk with no
kernel oddities, I am relatively certain it is correctly implemented. ;)
This should be a minor performance boost on BE as well.
Sponsored by: Tag1 Consulting, Inc.
For a body of code that had its endian conversion bits written blind without
the ability to test, moea64 was VERY close to being correct.
There were only four instances where the existing code was getting it wrong.
Sponsored by: Tag1 Consulting, Inc.
This is slightly stripped down from GENERIC64, as PowerMac G5 machines
are incapable of running in LE mode (so we can skip the Mac drivers.)
While technically POWER6 and POWER7 have the hardware capability of running
in LE mode, they have a tendency to trap excessively when a load/store is
misaligned. (an extremely common occurrence in LE code, and one of the main
reasons I consider BE to be superior, as it turns potential security issues
into immediately obvious mangled numbers.)
Additionally, there was no mechanism to control what endian interrupts
are delivered in, so supporting LE operation on POWER6 and POWER7 involves
some really dirty tricks in the interrupt vectors that I would rather
avoid.
IBM drew the line in the sand at POWER8 some time around 2013, embracing
full support for LE in the platform, and making a push across the board
for LE code to target POWER8 as a minimum requirement. As such, usage of
LE kernels on POWER6 and POWER7 is practically nil, despite it being
technically possible to do.
The so-called "TRUELE" feature bit which is the baseline requirement for
needed for PowerPC64LE was introduced in POWER8.
Sponsored by: Tag1 Consulting, Inc.
When running without a hypervisor, we need to set the ILE bit in the LPCR
ourselves.
For the boot processor, handle it in powernv_attach() like we do for other
LPCR bits.
No change for the APs, as they will use the lpcr global to set up their own
LPCR when they do their own cpudep_ap_early_bootstrap() and pick up this
automatically.
Sponsored by: Tag1 Consulting, Inc.
OPAL runs in big endian, so we need to rfid into it to switch endian
atomically when branching to it, and we need to do the
RETURN_TO_NATIVE_ENDIAN dance when it returns to us.
Sponsored by: Tag1 Consulting, Inc.
Unlike virtio, which in legacy mode is guest endian, the hypervisor vscsi
interface operates in big endian, so we must convert back and forth in several
places.
These changes are enough to attach a rootdisk.
Sponsored by: Tag1 Consulting, Inc.
The TCG implementation of mtmsrd in qemu blindly copies the entire register
to the MSR, instead of the specific bit positions listed in the ISA.
This means that qemu will prematurely switch endian out from under the
running code instead of waiting for the rfid, causing an immediate trap
as it attempts to interpret the next instruction in the wrong endianness.
To work around this, ensure PSL_LE is still set before doing the mtmsrd.
In the future, we may wish to just turn off translation and unconditionally
use rfid to switch to the ofmsr instead of quasi-switching to the ofmsr.
Add a new platform option so this can be disabled. (And so that we can
conditonalize additional QEMU-specific hacks in the platform code.)
Sponsored by: Tag1 Consulting, Inc.
Since we will need to be able to take traps relatively early in the process,
ensure that the hypervisor changes our ILE for us as soon as we are ready.
Sponsored by: Tag1 Consulting, Inc.
Since OFW always runs in big endian in practice, we need to convert several
bits back and forth.
This is necessary to communicate with SLOF on LE pseries.
Sponsored by: Tag1 Consulting, Inc.
This is the initial set up for PowerPC64LE.
The current plan is for this arch to remain experimental for FreeBSD 13.
This started as a weekend learning project for me and kinda snowballed from
there.
(More to follow momentarily.)
Reviewed by: imp (earlier version), emaste
Sponsored by: Tag1 Consulting, Inc.
Differential Revision: https://reviews.freebsd.org/D26399
On Ampere Altra systems, the sparse population of RAM within the
physical address space causes the vm_page_dump bitmap to be much
larger than necessary, increasing the size from ~8 Mib to > 2 Gib
(and overflowing `int` for the size).
Changing the page dump bitmap also changes the minidump file
format, so changes are also necessary in libkvm.
Reviewed by: jhb
Approved by: scottl (implicit)
MFC after: 1 week
Sponsored by: Ampere Computing, Inc.
Differential Revision: https://reviews.freebsd.org/D26131
These definitions were repeated by all architectures, with small
variations. Consolidate the common definitons in machine
independent code and use bitset(9) macros for manipulation. Many
opportunities for deduplication remain in the machine dependent
minidump logic. The only intended functional change is increasing
the bit index type to vm_pindex_t, allowing the indexing of pages
with address of 8 TiB and greater.
Reviewed by: kib, markj
Approved by: scottl (implicit)
MFC after: 1 week
Sponsored by: Ampere Computing, Inc.
Differential Revision: https://reviews.freebsd.org/D26129
One problem with the bus_space_read_N() and bus_space_write_N() family of
functions is that they provide no protection against exceptions which can
occur when no physical hardware or device responds to the read or write
cycles. In such a situation, the system typically would panic due to a
kernel-mode bus error. The bus_space_peek_N() and bus_space_poke_N() family
of functions provide a mechanism to handle these exceptions gracefully
without the risk of crashing the system.
Typical example is access to PCI(e) configuration space in bus enumeration
function on badly implemented PCI(e) root complexes (RK3399 or Neoverse
N1 N1SDP and/or access to PCI(e) register when device is in deep sleep state.
This commit adds a real implementation for arm64 only. The remaining
architectures have bus_space_peek()/bus_space_poke() emulated by using
bus_space_read()/bus_space_write() (without exception handling).
MFC after: 1 month
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D25371
