asomers [Wed, 7 May 2014 18:49:25 +0000 (18:49 +0000)]
MFC r263445 and r265385. Note that the change to ObsoleteFiles.inc in
r265385 does not need to be MFCed, because the obsolete files in question
were never MFCed to any stable branch.
r265385
Remove the ifconfig test added in rev 263445. After discussion with
melifaro, we agreed that ifconfig's behavior was not a bug. The main
motivation for bin/187551 was to partially resolve kern/187549, but we
resolved kern/187549 in a different way instead.
r263445
Add several ATF tests that deal with multiple fibs. They're described in
several different PRs, but the tests share some common code, so I'm
committing them together.
sbin/ifconfig/tests
sbin/ifconfig/tests/fibs_test.sh
sbin/ifconfig/tests/Makefile
sbin/ifconfig/Makefile
Add fibs_test.sh, which regresses bin/187551
tests/sys/netinet
tests/sys/netinet/fibs_test.sh
tests/sys/netinet/udp_dontroute.c
tests/sys/netinet/Makefile
tests/sys/Makefile
Add fibs_test.sh, which regresses kern/167947, kern/187552
kern/187549, kern/187550, and kern/187553
etc/mtree/BSD.tests.dist
Add newly created directories
jimharris [Wed, 7 May 2014 17:00:39 +0000 (17:00 +0000)]
MFC r263277:
nvme: Remove the software progress marker SET_FEATURE command during
controller initialization.
The spec says OS drivers should send this command after controller
initialization completes successfully, but other NVMe OS drivers are
not sending this command. This change will therefore reduce differences
between the FreeBSD and other OS drivers.
jimharris [Wed, 7 May 2014 16:55:08 +0000 (16:55 +0000)]
MFC r260382:
For IDENTIFY passthrough commands to Chatham prototype controllers, copy
the spoofed identify data into the user buffer rather than issuing the
command to the controller, since Chatham IDENTIFY data is always spoofed.
While here, fix a bug in the spoofed data for Chatham submission and
completion queue entry sizes.
jimharris [Wed, 7 May 2014 16:53:42 +0000 (16:53 +0000)]
MFC r260381:
For "nvmecontrol devlist", show namespace sizes in terms of MB instead of
GB to improve granularity of the reporting - especially for namespaces
that are on the order of 1 or 2 GB.
jimharris [Wed, 7 May 2014 16:52:29 +0000 (16:52 +0000)]
MFC r258071:
Check for special status code from FIRMWARE_ACTIVATE command
signifying that a reboot is required to complete activation
of the requested firmware image.
trasz [Wed, 7 May 2014 07:56:36 +0000 (07:56 +0000)]
MFC r264549:
Make it possible for the initiator side to operate in both proxy
and normal mode; this makes it possible to compile with the former
by default, but use it only when neccessary. That's especially
important for the userland part.
trasz [Wed, 7 May 2014 07:35:21 +0000 (07:35 +0000)]
MFC r264528:
Rework the way we enable CTL iSCSI port. Previously conf_apply()
needed it to be already enabled, because listening in proxy mode
requires it; however, it's conf_apply() that opens pidfiles,
so it resulted in port being enabled before pidfile was opened.
This was not so bad, but it was also disabled when pidfile couldn't
be opened due to ctld already running; this means that starting
second ctld instance screwed up the first.
trasz [Wed, 7 May 2014 07:29:39 +0000 (07:29 +0000)]
MFC r264524:
Make it possible for the iSCSI target side to operate in both normal
and ICL_KERNEL_PROXY mode, and fix some bit rot so the latter actually
works again.
trasz [Wed, 7 May 2014 06:38:19 +0000 (06:38 +0000)]
MFC r264025:
Get rid of the "autoscaling", instead just set socket buffer sizes
in the usual way. The only thing the old code did was making things
less predictable.
trasz [Wed, 7 May 2014 06:29:01 +0000 (06:29 +0000)]
MFC r264022:
Get rid of ICL lock; use upper-layer (initiator or target) lock instead.
This avoids extra locking in icl_pdu_queue(); the upper layer needs to call
it while holding its own lock anyway, to avoid sending PDUs out of order.
trasz [Wed, 7 May 2014 06:24:46 +0000 (06:24 +0000)]
MFC r263979:
Hide CTL messages about SCSI error responses. Too many users take
them for actual target errors. They can be enabled back by setting
kern.cam.ctl.verbose=1, or booting with bootverbose.
alc [Wed, 7 May 2014 00:32:49 +0000 (00:32 +0000)]
MFC r262338
When the kernel is running in a virtual machine, it cannot rely upon the
processor family to determine if the workaround for AMD Family 10h Erratum
383 should be enabled. To enable virtual machine migration among a
heterogeneous collection of physical machines, the hypervisor may have
been configured to report an older processor family with a reduced feature
set. Effectively, the reported processor family and its features are like
a "least common denominator" for the collection of machines.
Therefore, when the kernel is running in a virtual machine, instead of
relying upon the processor family, we now test for features that prove
that the underlying processor is not affected by the erratum. (The
features that we test for are unlikely to ever be emulated in software
on an affected physical processor.)
rmacklem [Tue, 6 May 2014 22:04:50 +0000 (22:04 +0000)]
MFC: r264739
Add {} braces so that the code conforms to the indentation.
Fortunately, I don't think doing the assignment of cap->tsomax
unconditionally causes any problem.
rmacklem [Tue, 6 May 2014 21:59:48 +0000 (21:59 +0000)]
MFC: r264738
For an NFSv4 mount with the "nocto" option, don't get the
up to date file attributes upon close. This reduces the
Getattr RPC count by about 65% for software builds.
rmacklem [Tue, 6 May 2014 21:54:52 +0000 (21:54 +0000)]
MFC: r264705, r264749
Modify the NFSv4 client create/mkdir RPC so that it acquires
post-create/mkdir directory attributes. This allows the RPC to
name cache the newly created directory and reduces the lookup RPC
count for applications creating a lot of directories.
rmacklem [Tue, 6 May 2014 21:47:43 +0000 (21:47 +0000)]
MFC: r264681
Modify the NFSv4 client open/create RPC so that it acquires
post-open/create directory attributes. This allows the RPC to
name cache the newly created file and reduces the lookup RPC
count by about 10% for software builds.
Exit with an error when make is called without a target at the top level
rather than poluting the source tree and causing use confusion in future
builds.
rmacklem [Tue, 6 May 2014 12:15:05 +0000 (12:15 +0000)]
MFC: r264672
Modify the Lookup RPC for NFSv4 so that it acquires directory
attributes. This allows the client to cache directory names
when they are looked up, reducing the Lookup RPC count by
about 40% for software builds.
Read card capabilities after firmware initialization, instead of setting
them up as part of firmware initialization (which the driver gets to do
only if it's the master driver).
Read the range of tids available for the ETHOFLD functionality if it's
enabled.
New is_ftid() and is_etid() functions to test whether a tid falls within
the range of filter tids or ETHOFLD tids respectively.
- More flexible cluster size selection, including the ability to fall
back to a safe cluster size (PAGE_SIZE from zone_jumbop by default) in
case an allocation of a larger size fails.
- A single get_fl_payload() function that assembles the payload into an
mbuf chain for any kind of freelist. This replaces two variants: one
for freelists with buffer packing enabled and another for those without.
- Buffer packing with any sized cluster. It was limited to 4K clusters
only before this change.
- Enable buffer packing for TOE rx queues as well.
- Statistics and tunables to go with all these changes. The driver's
man page will be updated separately.
r263412:
cxgbe(4): if_iqdrops statistic should include tunnel congestion drops.
rmacklem [Tue, 6 May 2014 02:54:59 +0000 (02:54 +0000)]
MFC: r264630
For NFS mounts using rsize,wsize=65536 over TSO enabled
network interfaces limited to 32 transmit segments, there
are two known issues.
The more serious one is that for an I/O of slightly less than 64K,
the net device driver prepends an ethernet header, resulting in a
TSO segment slightly larger than 64K. Since m_defrag() copies this
into 33 mbuf clusters, the transmit fails with EFBIG.
A tester indicated observing a similar failure using iSCSI.
The second less critical problem is that the network
device driver must copy the mbuf chain via m_defrag()
(m_collapse() is not sufficient), resulting in measurable overhead.
This patch reduces the default size of if_hw_tsomax
slightly, so that the first issue is avoided.
Fixing the second issue will require a way for the
network device driver to inform tcp_output() that it
is limited to 32 transmit segments.
rmacklem [Tue, 6 May 2014 02:49:31 +0000 (02:49 +0000)]
MFC: r264517
Vlan did not set the value of if_hw_tsomax, so when vlan
was stacked on top of a network interface that set if_hw_tsomax,
tcp_output() would see the default value instead of the value
set by the network interface. This patch modifies vlan so that
it sets if_hw_tsomax to the value of the parent interface.
rmacklem [Tue, 6 May 2014 02:44:01 +0000 (02:44 +0000)]
MFC: r264469, r264498
Lagg did not set the value of if_hw_tsomax, so when lagg
was stacked on top of network interfaces that set if_hw_tsomax,
tcp_output() would see the default value instead of the value
set by the network interface(s). This patch modifies lagg so that
it sets if_hw_tsomax to the minimum of the value(s) for the
underlying network interfaces.
r261533:
cxgbe(4): Use the port's tx channel to identify it to t4_clr_port_stats.
r261536:
cxgbe(4): The T5 allows for a different freelist starvation threshold
for queues with buffer packing. Use the correct value to calculate a
freelist's low water mark.
r261537:
cxgbe(4): Use the rx channel map (instead of the tx channel map) as the
congestion channel map.
r263457:
cxgbe(4): Recognize the "spider" configuration where a T5 card's 40G
QSFP port is presented as 4 distinct 10G SFP+ ports to the driver.
ken [Mon, 5 May 2014 20:35:35 +0000 (20:35 +0000)]
MFC the mpr(4) driver for LSI's 12Gb SAS cards.
This includes r265236, r265237, r265241 and r265261:
------------------------------------------------------------------------
r265236 | ken | 2014-05-02 14:25:09 -0600 (Fri, 02 May 2014) | 51 lines
Bring in the mpr(4) driver for LSI's MPT3 12Gb SAS controllers.
This is derived from the mps(4) driver, but it supports only the 12Gb
IT and IR hardware including the SAS 3004, SAS 3008 and SAS 3108.
Some notes about this driver:
o The 12Gb hardware can do "FastPath" I/O, and that capability is included in
this driver.
o WarpDrive functionality has been removed, since it isn't supported in
the 12Gb driver interface.
o The Scatter/Gather list handling code is significantly different between
the 6Gb and 12Gb hardware. The 12Gb boards support IEEE Scatter/Gather
lists.
Thanks to LSI for developing and testing this driver for FreeBSD.
share/man/man4/mpr.4:
mpr(4) man page.
sys/dev/mpr/*:
mpr(4) driver files.
sys/modules/Makefile,
sys/modules/mpr/Makefile:
Add a module Makefile for the mpr(4) driver.
sys/conf/files:
Add the mpr(4) driver.
sys/amd64/conf/GENERIC,
sys/i386/conf/GENERIC,
sys/mips/conf/OCTEON1,
sys/sparc64/conf/GENERIC:
Add the mpr(4) driver to all config files that currently
have the mps(4) driver.
sys/ia64/conf/GENERIC:
Add the mps(4) and mpr(4) drivers to the ia64 GENERIC
config file.
sys/i386/conf/XEN:
Exclude the mpr module from building here.
Submitted by: Steve McConnell <Stephen.McConnell@lsi.com>
Tested by: Chris Reeves <chrisr@spectralogic.com>
Sponsored by: LSI, Spectra Logic
Relnotes: LSI 12Gb SAS driver mpr(4) added
------------------------------------------------------------------------
------------------------------------------------------------------------
r265237 | ken | 2014-05-02 14:36:20 -0600 (Fri, 02 May 2014) | 8 lines
Add the mpr(4) man page to the man4 Makefile.
This should have been included in r265236.
Submitted by: Steve McConnell <Stephen.McConnell@lsi.com>
MFC after: 3 days
Sponsored by: LSI, Spectra Logic
ghelmer [Mon, 5 May 2014 16:52:38 +0000 (16:52 +0000)]
MFC r264617:
Fix releasing the lock in the parent atrun process after the queue
directory has been processed. Otherwise, a long-running child process
caused other atrun invocations to stall unnecessarily.
- Read and write the MAC address in the config space byte by byte
- Also include the mbuf's csum_flags in an assert message
- Remove stray space
- Move duplicated transmit start code into a single function
- Avoid queue unlock followed by relock when the enable interrupt race
is lost
- Check for a full virtqueue in the multiqueue transmit path
- Do not place the sglist used for Rx/Tx on the stack
- Use m_defrag() instead of m_collapse() to compact a long mbuf chain
MFC r264494:
Use SMB_QUERY_FS_SIZE_INFO request to populate statfs structure.
When server doesn't support this request, try to use SMB_INFO_ALLOCATION.
And use SMB_COM_QUERY_INFORMATION_DISK request as fallback.
MFC r264600:
Remove redundant unlock.
This code was removed from the opensolaris and darwin's
netsmb implementations, in DfBSD it also has been disabled.
projects / FreeBSD / stable / 10.git / log