It's often useful to have a callback when an I/O takes more than a
threshold amount of time. This adds the infrastructure for periph
devices to register one.
One use-case is as a debugging aide when you need a semi-realtime
indication of an I/O outlier so you can trigger bus capture gear for
vendor analysis.
Sponsored by: Netflix, Inc
rather than the floor(). Returning the floor means that
sbttoX(Xtosbt(y)) != y for almost all values of y. In practice, this
results in a difference of at most 1 in the lsb of the sbintime_t.
This difference is meaningless for all current users of these
functions, but is important for the newly introduced sysctl conversion
routines which implicitly rely on the transformation being idempotent.
Sponsored by: Netflix, Inc
iflib_stop() was not resetting the rxq completion queue state variables.
This meant that for any driver that has receive completion queues, after a
reinit, iflib would start asking what's available on the rx side starting at
whatever the completion queue index was prior to the stop, instead of at 0.
Submitted by: pkelsey
Reported by: pkelsey
MFC after: 3 days
Sponsored by: Limelight Networks
option, we pass -1 down to listen, which causes it to use the
kern.ipc.soacceptqueue sysctl.
Approved by: mav
MFC after: 2 weeks
Sponsored by: iXsystems Inc
The off-by-one errors in 332735 weren't actual errors and were
preventing the last MSI interrupt source from being used. Instead,
the issue is that when all MSI interrupt sources were allocated, the
loop in msix_alloc() would terminate with 'msi' still set to non-null.
The only check for 'i' overflowing was in the 'msi' == NULL case, so
msix_alloc() would try to reuse the last MSI interrupt source instead
of failing.
Fix by moving the check for all sources being in use to just after the
loop.
Reviewed by: kib, markj
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D17976
netmap(4) support for vtnet(4) was incomplete and had multiple bugs.
This commit fixes those bugs to bring netmap on vtnet in a functional state.
Changelist:
- handle errors returned by virtqueue_enqueue() properly (they were
previously ignored)
- make sure netmap XOR rest of the kernel access each virtqueue.
- compute the number of netmap slots for TX and RX separately, according to
whether indirect descriptors are used or not for a given virtqueue.
- make sure sglist are freed according to their type (mbufs or netmap
buffers)
- add support for mulitiqueue and netmap host (aka sw) rings.
- intercept VQ interrupts directly instead of intercepting them in txq_eof
and rxq_eof. This simplifies the code and makes it easier to make sure
taskqueues are not running for a VQ while it is in netmap mode.
- implement vntet_netmap_config() to cope with changes in the number of queues.
Reviewed by: bryanv
Approved by: gnn (mentor)
MFC after: 3 days
Sponsored by: Sunny Valley Networks
Differential Revision: https://reviews.freebsd.org/D17916
Ensure that any time CSUM_IP_TSO or CSUM_IP6_TSO is set that the corresponding
CSUM_IP6?_TCP / CSUM_IP flags are also set.
Rather than requireing drivers to bake-in an understanding that TSO implies
checksum offloads, make it explicit.
This change requires us to move the IFLIB_NEED_ZERO_CSUM implementation to
ensure it's zeroed for TSO.
Reported by: Jacob Keller <jacob.e.keller@intel.com>
MFC after: 1 week
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D17801
r333502 removed initialization of ifc_nhwtxqs, and it's not clear
there's a need to copy it into the struct iflib_ctx at all. Use
ctx->ifc_sctx->isc_ntxqs instead.
Further, iflib_stop() did not clear the last ring in the case where
isc_nfl != isc_nrxqs (such as when IFLIB_HAS_RXCQ is set). Use
ctx->ifc_sctx->isc_nrxqs here instead of isc_nfl.
Reported by: pkelsey
Reviewed by: pkelsey
MFC after: 3 days
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D17979
Also, make the path to the example configuration file absolute.
Reviewed by: bcr
Approved by: krion (mentor, implicit), mat (mentor, implicit)
Differential Revision: https://reviews.freebsd.org/D17985
The d_off field has been added to the dirent structure recently.
Currently filesystems don't support this feature. Support has been
added and tested for zfs, ufs, ext2fs, fdescfs, msdosfs and unionfs.
A stub implementation is available for cd9660, nandfs, udf and
pseudofs but hasn't been tested.
Motivation for this feature: our usecase is for a userspace nfs server
(nfs-ganesha) with zfs. At the moment we cache direntry offsets by
calling lseek once per entry, with this patch we can get the offset
directly from getdirentries(2) calls which provides a significant
speedup.
Submitted by: Jack Halford <jack@gandi.net>
Reviewed by: mckusick, pfg, rmacklem (previous versions)
Sponsored by: Gandi.net
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D17917
Avoid touching all pages in extent_recycle for debug build.
We may have a large number of pages with *zero set (since they are populated on
demand). Only check the first page to avoid paging in all of them.
This makes it easy to compare performance with and without 'retain:true'.
Discussed with: jasone
Obtained from: Qi Wang <interwq at gwu dot edu>
MFC after: 2 weeks
Sponsored by: DARPA, AFRL
- Adding a note to UPDATING
- Adding a note to the history section of the manpage ctm.1
- Adding a message printed to STDERR to the ctm program
This version is meant for release in FreeBSD-12.0 and should remain in
FreeBSD-12 over its life-time.
A follow-up commit will remove ctm from -CURRENT after the MFC to 12
has happened.
Approved by: imp, rgrimes, bcr (man-page)
MFC after: 3 days
Relnotes: yes
Differential Revision: https://reviews.freebsd.org/D17969
Update the AMD family 17h temperature reporting based on AMD Tech Doc 56255
OSRR, section 4.2.1.
For CPUS w/CUR_TEMP_RANGE_SEL set, scale the reported temperature into the
range -49..206; i.e., subtract 49°C.
Submitted by: gallatin@
Reported by: bcran@
Reviewed by: me (long ago)
MFC after: 22.57 seconds
Relnotes: yea
Differential Revision: https://reviews.freebsd.org/D16855
As reported, tested, and patch supplied by Johannes.
There may be future work to do to support multiple sensors, but for now, any
sensor at all is a strict improvement for Ryzen 2 systems.
PR: 228480
Submitted by: Johannes Lundberg <johalun0 AT gmail.com> (earlier version)
Reported by: deischen@, Johannes, and numerous others
MFC after: 3.72 days
Allow the location of capabilities.conf to be configured.
Also allow a per-abi syscall prefix to be configured with the
abi_func_prefix syscalls.conf variable and check syscalls against
entries in capabilities.conf with and without the prefix amended.
Take advantage of these two features to allow use shared capabilities.conf
between the default syscall vector and the freebsd32 compatability
layer. We've been inconsistent about keeping the two in sync as
evidenced by the bugs fixed in r340294. This eliminates that problem
going forward.
Reviewed by: kib
Obtained from: CheriBSD
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D17932
Every µcode-updater must open the cpucontrol devfs node RDWR, open a
firmware file, validate the FW file has a positive length, mmap it, etc.
De-duplicate that identical logic between every individual platform.
Also, constify references to the readonly-mapped firmware files while here.
Sponsored by: Dell EMC Isilon
This was for pre-7.0 CAM support. Neither the CAM nor the busdma
changes over the years have not been ifdef'd. The code cannot build
on 6.x anymore. Support for 6.4 ended in 2010, so remove them.
mutexes but now are converted to epoch(9) use thread-private epoch_tracker.
Embedding tracker into ifnet(9) or ifnet derived structures creates a non
reentrable function, that will fail miserably if called simultaneously from
two different contexts.
A thread private tracker will provide a single tracker that would allow to
call these functions safely. It doesn't allow nested call, but this is not
expected from compatibility KPIs.
Reviewed by: markj
document the libufs interface for fetching and storing inodes.
The undocumented getino / putino interface has been replaced
with a new getinode / putinode interface.
Convert the utilities that had been using the undocumented
interface to use the new documented interface.
No functional change (as for now the libufs library does not
do inode check-hashes).
Reviewed by: kib
Tested by: Peter Holm
Sponsored by: Netflix
They only showed up after I redefined LOCKSTAT_ENABLED to 0.
doing_lockprof in mutex.c is a real (but harmless) bug. Should the
value be non-zero it will do checks for lock profiling which would
otherwise be skipped.
state in rwlock.c is a wart from the compiler, the value can't be
used if lock profiling is not enabled.
Sponsored by: The FreeBSD Foundation
Change the assert paths in rm, rw, and sx locks to match the lock
and unlock paths. I did this for mutexes in r306346.
Reported by: Travis Lane <tlane@isilon.com>
MFC after: 2 weeks
Sponsored by: Dell EMC Isilon
libnv used fcntl(fd, F_GETFL) to test whether fd is a valid file
descriptor. Aside from being racy, this check requires CAP_FCNTL
rights on fd. Instead, use fcntl(fd, F_GETFD), which does not require
any capability rights.
Also remove some redundant fd_is_valid() checks to avoid extra system
calls; in many cases we were performing this check immediately before
dup()ing the descriptor.
Reviewed by: cem, oshogbo (previous version)
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D17963
list and remaining references from the script used to create the
MANIFEST file used by bsdinstall(8).
No MFC is planned at this time.
Sponsored by: The FreeBSD Foundation
was removed in r318881 when roff was removed from the base
system.
This results in the doc.txz distribution set containing a
single directory (./) which is empty.
Remove the "Additional documentation" option from the menu
selection of bsdinstall(8), as the plain-text documentation
installed in /usr/share/doc is installed as part of the
packageworld target.
The doc entry has not been removed from EXTRA_DISTRIBUTIONS
in Makefile.inc1, in case its removal triggers an issue with
freebsd-update(8), which is currently aware of the world/doc
component, so the empty doc.txz continues to be created as
a precaution.
Noticed by: rgrimes
MFC after: 2 days
MFC before: 12.0-RC1
Sponsored by: The FreeBSD Foundation
In particular, track the current size of the cache and maintain an
estimate of its working set size. This will be used to decide how
much to shrink various caches when the kernel attempts to reclaim
pages. As a secondary effect, it makes statistics aggregation (done
by, e.g., vmstat -z) cheaper since sysctl_vm_zone_stats() no longer
needs to iterate over lists of cached buckets.
Discussed with: alc, glebius, jeff
Tested by: pho (previous version)
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D16666
processors would benefit from avoiding a function call, but bloating
code. In fact, clang created an uninlined real function for many
object files in the network stack.
- Move epoch_private.h into subr_epoch.c. Code copied exactly, avoiding
any changes, including style(9).
- Remove private copies of critical_enter/exit.
Reviewed by: kib, jtl
Differential Revision: https://reviews.freebsd.org/D17879
Remove restrictions that prevent allocation requests to cross the
boundary between two meta nodes.
Replace the bmu_avail field in meta nodes with a bitmap that identifies
which subtrees have some free memory, and iterate over the nonempty
subtrees only in blst_meta_alloc. If free memory is scarce, this should
make searching for it faster.
Put the code for handling the next-leaf allocation in a separate
function. When taking blocks from the next leaf empties the leaf, be
sure to clear the appropriate bit in its parent, and so on, up to the
least-common ancestor of this leaf and the next.
Eliminate special terminator nodes, and rely instead on the fact that
there is a 0-bit at the end of the bitmask at the root of the tree that
will stop a meta_alloc search, or a next-leaf search, before the search
falls off the end of the tree. Make sure that the tree is big enough to
have space for that 0-bit.
Eliminate special all-free indicators. Lazy initialization of subtrees
stands in the way of having an allocation span a meta-node boundary, so
a subtree of all free blocks is not treated specially. Subtrees of
all-allocated blocks are still recognized by looking at the bitmask at
the root and finding 0.
Don't print all-allocated subtrees. Do print the bitmasks for meta
nodes, when tree-printing.
Submitted by: Doug Moore <dougm@rice.edu>
Reviewed by: alc
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D12635
The RISC-V spec defines several performance counter CSRs such as: cycle,
time, instret, hpmcounter(3...31). They are defined to be 64-bits wide
on all RISC-V architectures. On RV64 and RV128 they can be read from a
single CSR. On RV32, additional CSRs (given the suffix "h") are present
which contain the upper 32 bits of these counters, and must be read as
well. (See section 2.8 in the User ISA Spec for full details.)
This change adds macros for reading these values safely on any RISC-V
ISA length. Obviously we aren't supporting anything other than RV64
at the moment, but this ensures we won't need to change how we read
these values if we ever do.
Submitted by: Mitchell Horne <mhorne063@gmail.com>
Reviewed by: jhb
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D17952
