| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
| |
Check for packet_length is greater than 60 bytes as well as packet_length is
greater than len_on_bd, before invoking the routine to handle jumbo over SGL
(bxe_service_rxsgl()).
Add counters for number of jumbo_over_SGL packets (rx_bxe_service_rxsgl) and
erroneous jumbo_over_SGL packets (rx_erroneous_jumbo_sge_pkts)
Fix formatting in bxe_sysctl_state()
|
|
|
|
| |
Add support for reading device temperature
|
|
|
|
|
|
| |
Drop the clang patch which adds recognition of 'CC' suffixes as aliases
for --driver-mode=g++, since this was never upstreamed. For backwards
compatibility, add a wrapper shell script.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- Generate opt_inet.h appropriately according to MK_INET_SUPPORT
- Only add in_gif.c to SRCS if MK_INET_SUPPORT != no
This is a surgical fix since the build infrastructure has diverged sufficiently
between stable/10 and head.
This change will likely be reverted if and when imp's changes to config.mk have
been backported to ^/stable/10 .
Reviewed by: ae (no serious objections)
Differential Revision: https://reviews.freebsd.org/D4864
MFC after: 1 week
Sponsored by: EMCC / Isilon Storage Division
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add the ability to detect ZFS and GELI encrypted file systems to fstyp(8)
MFC: r284644
Fix GCC Warnings
MFC: r284728
Only build ZFS support in absense of WITHOUT_ZFS
MFC: r285426
Remove excess copyrights
MFC: r286569
Use GELI sentinel constant
MFC: r287937
Eliminate unneeded copying of vdev data, goto, etc. and add a note
that checksum of vdev label should be checked (which is not done
currently).
No functional change.
While I'm there, raise WARNS to 2.
MFC: r292757
Fix order of includes in usr.sbin/fstyp/zfs.c
MFC: r292829
Eliminate unneeded includes.
|
|
|
|
|
|
|
|
|
|
|
| |
introduced with r293742, just like it was hidden before that commit.
This is a direct commit to 10-STABLE; this special case is not needed
in 11-CURRENT, because devfs supports forced unmounts there. The forced
unmount could be MFC-ed, but there are some LORs at shutdown, and I have
a weird feelings about it.
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
| |
Fix resource leaks in error cases.
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
|
|
|
|
|
|
| |
Userspace part of reroot support. This makes it possible to change
the root filesystem without full reboot, using "reboot -r". This can
be used to to eg. boot from a temporary md_image preloaded by loader(8),
setup an iSCSI session, and continue booting from rootfs mounted over
iSCSI.
Relnotes: yes
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D3693
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Kernel part of reroot support - a way to change rootfs without reboot.
Note that the mountlist manipulations are somewhat fragile, and not very
pretty. The reason for this is to avoid changing vfs_mountroot(), which
is (obviously) rather mission-critical, but not very well documented,
and thus hard to test properly. It might be possible to rework it to use
its own simple root mount mechanism instead of vfs_mountroot().
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D2698
|
|
|
|
|
|
|
|
|
| |
Make vfs_unmountall() unmount /dev after /, not before. The only
reason this didn't result in an unclean shutdown is that devfs ignores
MNT_FORCE flag.
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D3467
|
|
|
|
|
|
|
| |
Remove reboot.S (part of libc). It's not needed and was actually
broken - returning 0 from reboot(2) resulted in SIGBUS.
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
|
|
|
|
| |
Make geom_nop(4) collect statistics on all types of BIOs, not just
reads and writes.
PR: kern/198405
Submitted by: Matthew D. Fuller <fullermd at over-yonder dot net>
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D3679
|
|
|
|
|
| |
Handle when filedescriptors are closed before initialized. An early
fdclose() call can cause fget_unlocked() to fail.
|
|
|
|
| |
Fix for directly connected FULL or LOW speed USB devices.
|
|
|
|
|
|
| |
Make ifconfig always exit with an error code if an important ioctl fails
PR: 203062
|
|
|
|
|
|
|
| |
service(8) -e does not respect /etc/rc.conf.d/* entries
PR: 173454
Submitted by: giantlock@gmail.com (original patch)
|
|
|
|
|
|
|
| |
Document the sctp blackhole sysctl MIB
PR: 184110
Submitted by: Marie Helene Kvello-Aune <marieheleneka@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Use strtonum(3) instead of atoi(3)
MFC: r286289
Introduce -P0, creating as many concurrent processes as possible
Relnotes: yes
MFC: r286461
Fix regression in xargs -Px, add more regression tests
MFC: r287004
MFC: r287005
Fix the racy xargs -P0 -n2 test added in r286289
PR: 199976
Submitted by: Nikolai Lifanov <lifanov@mail.lifanov.com>
|
|
|
|
|
|
|
|
|
|
| |
Prevent memstick installation medium from attempting to mount
the root filesystem read-write. This causes problems booting
the memstick installation medium from write-protected USB flash
drives.
PR: 187161, 205886
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
|
| |
MFC: r292012
Add an option to use rfc6675 based pipe/inflight bytes calculation in cubic and
newreno.
|
|
|
|
| |
Improve tcp duplicate ack processing when SACK is present.
|
|
|
|
|
|
|
|
|
| |
Calculate the correct amount of bytes that are in-flight for a connection as
suggested by RFC 6675.
MFC: r292046
r290122 added 4 bytes and removed 8 in struct sackhint. Add a pad entry of 4
bytes to restore the size.
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
------------------------------------------------------------------------
r292743 | dchagin | 2015-12-26 01:04:47 -0800 (сб, 26 дек. 2015) | 5 lines
Do not allow access to emuldata for non Linux processes.
------------------------------------------------------------------------
r293627 | dchagin | 2016-01-09 23:36:43 -0800 (сб, 09 янв. 2016) | 6 lines
Unlock process lock when return error from getrobustlist call and add
an forgotten dtrace probe when return the same error.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Don't retry SAS commands in response to protocol errors
sys/dev/mpr/mpr_sas_lsi.c
sys/dev/mps/mps_sas_lsi.c
When mp[rs]sas_get_sata_identify returns
MPI2_IOCSTATUS_SCSI_PROTOCOL_ERROR, don't bother retrying. Protocol
errors aren't likely to be fixed by sleeping.
Without this change, a system that generated may protocol errors due
to signal integrity issues was taking more than an hour to boot, due
to all the retries.
|
|
|
|
| |
Fix upgrading from OSVERSION 1000002-1000032 after r288829.
|
|
|
|
|
|
|
| |
When iostat(8) receives SIGINT while running with "-w" or "-c", it will now
print statistics one more time before exiting. Also, it now implements the
wait using setitimer instead of sleep, so the waits will be more consistent
when the system is heavily loaded.
|
|
|
|
|
|
|
| |
Increase devd's client socket buffer size to 256KB. This is not as large as
it looks, because we'll hit the sockbuf's mbuf limit long before hitting its
data limit. A 256KB data limit allows creating a ZFS pool on about 450
drives without overflowing the client socket buffers.
|
|
|
|
|
|
| |
Document iSCSI and autofs(5) variables in rc.conf(5).
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
|
| |
The dumpfs(8) utility doesn't actually use disktab(5); remove it
from "SEE ALSO".
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
|
|
|
|
|
| |
It's 2015, and some people are still trying to use fdisk and then
go asking what debug flags to set for GEOM to make it work. Advice
them to use gpart(8) instead.
Something similar should probably done with disklabel,
but I need to rewrite the disklabel examples first.
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
| |
Point potential geom_fox(4) users to gmultipath(8).
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
| |
Add 'p' postfix to mdconfig(8).
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
| |
Provide better debug message on kernel module name clash.
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
| |
Make rctl(8) use more reasonable buffer size for retrieving the rules.
Sponsored by: The FreeBSD Foundation
|
|
|
|
|
|
|
|
|
| |
Fix unlikely memory leak.
It is unlikely since the first check in the function is that dir[0] is '/',
but later code changes may make it real.
Coverity CID: 1332104
|
|
|
|
| |
Regression: fix usershow -7
|
|
|
|
|
|
| |
Fix markup in rctl(8) - the 'rule' or 'filter' arguments are not optional.
Sponsored by: The FreeBSD Foundation
|
|
|
|
| |
ismt: fix ISMT_DESC_ADDR_RW macro
|
|
|
|
|
|
|
|
|
| |
Add ismt(4) driver.
ismt(4) supports the SMBus Message Transport controller found on Intel
C2000 series (Avoton) and S1200 series (Briarwood) Atom SoCs.
Relnotes: Yes
|
|
|
|
| |
nvme: replace NVME_CEILING macro with howmany()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
nvme: add hw.nvme.min_cpus_per_ioq tunable
Due to FreeBSD system-wide limits on number of MSI-X vectors
(https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=199321),
it may be desirable to allocate fewer than the maximum number
of vectors for an NVMe device, in order to save vectors for
other devices (usually Ethernet) that can take better
advantage of them and may be probed after NVMe.
This tunable is expressed in terms of minimum number of CPUs
per I/O queue instead of max number of queues per controller,
to allow for a more even distribution of CPUs per queue. This
avoids cases where some number of CPUs have a dedicated queue,
but other CPUs need to share queues. Ideally the PR referenced
above will eventually be fixed and the mechanism implemented
here becomes obsolete anyways.
While here, fix a bug in the CPUs per I/O queue calculation to
properly account for the admin queue's MSI-X vector.
|
|
|
|
|
|
|
|
|
|
| |
nvme: do not revert to single I/O queue when per-CPU queues not available
Previously nvme(4) would revert to a single I/O queue if it could not
allocate enought interrupt vectors or NVMe submission/completion queues
to have one I/O queue per core. This patch determines how to utilize a
smaller number of available interrupt vectors, and assigns (as closely
as possible) an equal number of cores to each associated I/O queue.
|
|
|
|
| |
nvme: break out interrupt setup code into a separate function
|
|
|
|
|
|
|
| |
nvme: do not pre-allocate MSI-X IRQ resources
The issue referenced here was resolved by other changes
in recent commits, so this code is no longer needed.
|
|
|
|
|
|
|
|
|
|
| |
nvme: remove per_cpu_io_queues from struct nvme_controller
Instead just use num_io_queues to make this determination.
This prepares for some future changes enabling use of multiple
queues when we do not have enough queues or MSI-X vectors
for one queue per CPU.
|
|
|
|
|
|
|
| |
nvme: simplify some of the nested ifs in interrupt setup code
This prepares for some follow-up commits which do more work in
this area.
|
|
|
|
|
|
|
|
|
| |
nvd: submit bios directly when BIO_ORDERED not set or in flight
This significantly improves parallelism in the most common case.
The taskqueue is still used whenever BIO_ORDERED bios are in flight.
This patch is based heavily on a patch from gallatin@.
|
|
|
|
|
|
|
| |
nvd: break out submission logic into separate function
This enables a future patch using this same logic to submit
I/O directly bypassing the taskqueue.
|
|
|
|
|
|
|
|
| |
nvd: skip BIO_ORDERED logic when bio fails submission
This ensures the bio flags are not read after biodone().
The ordering will still be enforced, after the bio is
submitted successfully.
|
|
|
|
|
|
|
| |
nvd: do not wait for previous bios before submitting ordered bio
Still wait until all in-flight bios (including the ordered bio)
complete before processing more bios from the queue.
|