Commit Graph

236737 Commits

Author SHA1 Message Date
ngie
56d12910dc Only run mdconfig -d -u 3 if /dev/md3 exists on the system
This will prevent "cleanup failures" (exit code != 0 returned) when
tmpfs is not loaded

MFC after:	1 week
2016-12-09 22:50:43 +00:00
sobomax
fb62448269 Check that SCM_XXX timestamp returned by the kernel is less 1 second
away in the past from the current time. This should be plenty for the
scheduler to do its job. It provides assurance that the timestamp
returned is actually a valid one, not just some random garbage.
2016-12-09 22:13:00 +00:00
glebius
6042079e9d Allow bogus_page to be passed to pager(s). 2016-12-09 21:21:24 +00:00
glebius
678917bbda Fix build for 32-bit machines.
Submitted by:	tuexen
2016-12-09 20:50:35 +00:00
emaste
382ab60337 src.conf.5: regen after r309142 (WITH_LLD_AS_LD knob)
Reported by:	Nikolai Lifanov
Sponsored by:	The FreeBSD Foundation
2016-12-09 19:09:58 +00:00
glebius
40efd8a66e Use acquire write to cr_lock to complement with release write at end
of locked region.

Submitted by:	kib
2016-12-09 19:07:31 +00:00
markj
b0a8bb2436 Conditionalize PG_CACHE sysctls on COMPAT_FREEBSD11.
Reviewed by:	glebius, imp, jhb
Differential Revision:	https://reviews.freebsd.org/D8736
2016-12-09 18:55:27 +00:00
markj
8bb19c4929 Add a COMPAT_FREEBSD11 kernel option.
Use it wherever COMPAT_FREEBSD10 is currently specified.

Reviewed by:	glebius, imp, jhb
Differential Revision:	https://reviews.freebsd.org/D8736
2016-12-09 18:54:12 +00:00
glebius
f8eae77f98 Treat R_X86_64_PLT32 relocs as R_X86_64_PC32.
If we load a binary that is designed to be a library, it produces
relocatable code via assembler directives in the assembly itself
(rather than compiler options).  This emits R_X86_64_PLT32 relocations,
which are not handled by the kernel linker.

Submitted by:	gallatin
Reviewed by:	kib
2016-12-09 18:07:28 +00:00
glebius
6c5967127b Backout accidentially leaked in r309746 not yet reviewed patch :( 2016-12-09 18:00:45 +00:00
glebius
4f37ca1641 Use counter_ratecheck() in the ICMP rate limiting.
Together with:	rrs, jtl
2016-12-09 17:59:15 +00:00
glebius
592e0af9a0 Provide counter_ratecheck(), a MP-friendly substitution to ppsratecheck().
When rated event happens at a very quick rate, the ppsratecheck() is not
only racy, but also becomes a performance bottleneck.

Together with:	rrs, jtl
2016-12-09 17:58:34 +00:00
tuexen
07971cc856 Don't bundle a SACK chunk with a SHUTDOWN chunk if it is not required.
MFC after:	1 week
2016-12-09 17:58:07 +00:00
tuexen
de802bfc55 Don't send multiple SHUTDOWN chunks in a single packet.
Thanks to Felix Weinrank for making me aware of this issue.

MFC after:	1 week
2016-12-09 17:57:17 +00:00
br
a7d10e0e2c Add registers for jz4780 audio and PDMA controllers.
Sponsored by:	DARPA, AFRL
2016-12-09 17:16:09 +00:00
des
a6f2fe6497 More debugging code I missed in r309051.
Reported by:	jbeich, jkim
2016-12-09 16:14:55 +00:00
hselasky
d9c0bb6f7d Add more LinuxKPI PCI definitions.
Obtained from:	kmacy @
Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-12-09 15:05:09 +00:00
hselasky
8edea1bc1a Prefer function macros over regular macros in the LinuxKPI.
MFC after:	1 week
Sponsored by:	Mellanox Technologies
2016-12-09 15:01:37 +00:00
robak
31aeb5905c Capsicum support for dd(1)
Adds Capsicum sandboxing to dd utility.

Submitted by:	Pawel Biernacki <pawel.biernacki@gmail.com>
Reviewed by:	allanjude, emaste, oshogbo
Approved by:	oshogbo
Sponsored by:	Mysterious Code Ltd.
Differential Revision:	https://reviews.freebsd.org/D8543
2016-12-09 14:51:05 +00:00
hselasky
e2142136d1 Avoid malloc() warnings when using the LinuxKPI by zero-checking
the allocation flags.

Obtained from:		kmacy @
Sponsored by:           Mellanox Technologies
MFC after:		1 week
2016-12-09 14:06:22 +00:00
hselasky
bfcaed294a MSIX can support more than 256 IRQs. Make sure the invalid IRQ number
set in the LinuxKPI is big enough.

Sponsored by:           Mellanox Technologies
MFC after:		1 week
2016-12-09 13:53:31 +00:00
hselasky
7dcfee78f0 Prefix some _pci_xxx() functions in the Linux KPI with linux_ and make
sure the IRQ number used by these functions is unsigned.

Sponsored by:           Mellanox Technologies
MFC after:		1 week
2016-12-09 13:47:50 +00:00
hselasky
c247abf015 Prefix the Linux KPI's kmem_xxx() functions with linux_ to avoid
conflict with the opensolaris kernel module.

This patch solves a problem where the kernel linker will incorrectly
resolve opensolaris kmem_xxx() functions as linuxkpi ones, which leads
to a panic when these functions are used.

Submitted by:		gallatin @
Sponsored by:           Mellanox Technologies
MFC after:		1 week
2016-12-09 13:41:26 +00:00
sephe
80c55f08a0 hyperv/storvsc: Minor style changes; no functional changes.
Reported by:	rpokala
MFC after:	1 week
Sponsored by:	Microsoft
2016-12-09 06:18:12 +00:00
sephe
c7444a12c9 hyperv/storvsc: Fix the SCSI disk attachment issue.
On pre-WS2016 Hyper-V, if the only LUNs > 7 are used, then all disks
fails to attach.  Mainly because those versions of Hyper-V do not set
SRB_STATUS properly and deliver junky INQUERY responses.

Submitted by:	Hongjiang Zhang <honzhan microsoft com>
Reported by:	Hongxiong Xian <v-hoxian microsoft com>
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8724
2016-12-09 03:16:36 +00:00
np
4f95df0e92 cxgbe(4): netmap does not set IFCAP_NETMAP in an ifnet's if_capabilities
any more (since r307394).  Do it in the driver instead.

MFC after:	1 week
2016-12-09 02:21:27 +00:00
rmacklem
fea344561b Patch the nfsd so that it doesn't register with rpcbind for an NFSv4 only
server.

This patch uses the sysctl vfs.nfsd.server_min_nfsvers to determine
if/what versions of NFS service should be registered with rpcbind.
For NFSv4 only, it does not register at all, since NFSv4 always uses 2049
and does not require rpcbind.
For NFSv3 minimum, it registers NFSv3 but not NFSv2.

Tested by:	jmader2@gmu.edu
Submitted by:	jmader2@gmu.edu (earlier version)
MFC after:	2 weeks
Differential Revision:	https://reviews.freebsd.org/D8696
2016-12-08 23:29:56 +00:00
dim
bb29338288 Pull in r281586 from upstream llvm trunk (by Wei Mi):
Add some shortcuts in LazyValueInfo to reduce compile time of
  Correlated Value Propagation.

  The patch is to partially fix PR10584. Correlated Value Propagation
  queries LVI to check non-null for pointer params of each callsite. If
  we know the def of param is an alloca instruction, we know it is
  non-null and can return early from LVI. Similarly, CVP queries LVI to
  check whether pointer for each mem access is constant. If the def of
  the pointer is an alloca instruction, we know it is not a constant
  pointer. These shortcuts can reduce the cost of CVP significantly.

  Differential Revision: https://reviews.llvm.org/D18066

This significantly reduces memory usage and compilation time when
compiling a particular C++ source file of the graphics/colmap port.

PR:		215136
MFC after:	3 days
2016-12-08 21:02:34 +00:00
avos
bbc879af50 rsu: fix incorrect register addresses. 2016-12-08 20:54:54 +00:00
dteske
8a7a41fe62 Functions in their own section 2016-12-08 19:28:12 +00:00
dteske
4efe9f28d0 Remove unnecessary trailing backslashes 2016-12-08 19:26:22 +00:00
markj
44f636d610 err.D_PROC_CREATEFAIL.many.d passes, so remove the EFAIL annotation.
MFC after:	1 week
Sponsored by:	Dell EMC Isilon
2016-12-08 18:56:35 +00:00
loos
94e387806b Fix the typos and style(9) in comment.
MFC after:	2 weeks
Sponsored by:	Rubicon Communications, LLC (Netgate)
2016-12-08 18:18:48 +00:00
dteske
66cde2d5d3 Add support for "hidden" Wi-Fi networks
PR:		bin/214933
Submitted by:	Maxim Filimonov <che@bein.link>
Reviewed by:	dteske, allanjude, adrian
MFC after:	6 days
X-MFC-with:	Follow-up commit for style
2016-12-08 16:41:18 +00:00
br
68a3ee5bac Add jz4780 internal codec initialization driver.
Sponsored by:	DARPA, AFRL
2016-12-08 16:28:34 +00:00
mav
59a1ac276a Fix spa_alloc_tree sorting by offset in r305331.
Original commit "7090 zfs should improve allocation order" declares alloc
queue sorted by time and offset.  But in practice io_offset is always zero,
so sorting happened only by time, while order of writes with equal time was
completely random.  On Illumos this did not affected much thanks to using
high resolution timestamps.  On FreeBSD due to using much faster but low
resolution timestamps it caused bad data placement on disks, affecting
further read performance.

This change switches zio_timestamp_compare() from comparing uninitialized
io_offset to really populated io_bookmark values.  I haven't decided yet
what to do with timestampts, but on simple tests this change gives the
same peformance results by just making code to work as declared.

MFC after:	1 week
2016-12-08 15:58:03 +00:00
kib
b7561e3695 Use the populate() driver paging method for i915 driver.
In particular, the fault access type is accounted for when the
aperture page is moved to GTT domain.  On the other hand, the current
pager structure is left intact, most important, only one page is
instantiated per populate call.

Reviewed by:	alc
Sponsored by:	The FreeBSD Foundation
MFC after:	3 weeks
2016-12-08 11:39:08 +00:00
kib
fd9c8a16f1 Implement the populate() pager method for phys pager.
It allows to provide configurable agressive prefaulting and useful
hints to page daemon about memory allocations, on faults for pages
managed by phys pager.  In fact, this implementation is superior to
the MAP_SHARED_PHYS hack from my Postgresql paper, while giving
similar benefits of reducing the page faults numbers on SysV shared
memory mappings.

Reviewed by:	alc
Tested by:	pho
Sponsored by:	The FreeBSD Foundation
MFC after:	3 weeks
2016-12-08 11:35:53 +00:00
kib
2819db13ca Add a new populate() pager method and extend device pager ops vector
with cdev_pg_populate() to provide device drivers access to it.  It
gives drivers fine control of the pages ownership and allows drivers
to implement arbitrary prefault policies.

The populate method is called on a page fault and is supposed to
populate the vm object with the page at the fault location and some
amount of pages around it, at pager's discretion.  VM provides the
pager with the hints about current range of the object mapping, to
avoid instantiation of immediately unused pages, if pager decides so.
Also, VM passes the fault type and map entry protection to the pager,
allowing it to force the optimal required ownership of the mapped
pages.

Installed pages must contiguously fill the returned region, be fully
valid and exclusively busied.  Of course, the pages must be compatible
with the object' type.

After populate() successfully returned, VM fault handler installs as
many instantiated pages into the process page tables as it sees
reasonable, while still obeying the correct semantic for COW and vm
map locking.

The method is opt-in, pager sets OBJ_POPULATE flag to indicate that
the method can be called.  If pager' vm objects can be shadowed, pager
must implement the traditional getpages() method in addition to the
populate().  Populate() might fall back to the getpages() on per-call
basis as well, by returning VM_PAGER_BAD error code.

For now for device pagers, the populate() method is only allowed to be
used by the managed device pagers, but the limitation is only made
because there is no unmanaged fault handlers which could use it right
now.

KPI designed together with, and reviewed by:	alc
Tested by:	pho
Sponsored by:	The FreeBSD Foundation
MFC after:	3 weeks
2016-12-08 11:26:11 +00:00
kib
a497cae7b6 Move map_generation snapshot value into struct faultstate.
Reviewed by:	alc
Tested by:	pho
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
2016-12-08 10:29:41 +00:00
kib
5671ac5680 Style.
Reviewed by:	alc
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
2016-12-08 10:28:51 +00:00
adrian
1eeb35ff17 [net80211] add a field for storing a 64 bit TSC. 2016-12-08 07:57:16 +00:00
adrian
a88b5e72ee [net80211] begin fleshing out support for channel survey information to be
pushed back up into net80211.
2016-12-08 07:56:25 +00:00
sephe
6091327a9b hyperv/timesync: Support "sent TC" to improve accuracy.
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8723
2016-12-08 05:37:39 +00:00
sephe
092f1602f5 hyperv/vmbus: Utilize vmbus_chan_run_task()
MFC after:	1 week
Sponsored by:	Microsoft
Differential Revision:	https://reviews.freebsd.org/D8686
2016-12-08 05:15:00 +00:00
alc
7571ef95c1 Previously, vm_radix_remove() would panic if the radix trie didn't
contain a vm_page_t at the specified index.  However, with this
change, vm_radix_remove() no longer panics.  Instead, it returns NULL
if there is no vm_page_t at the specified index.  Otherwise, it
returns the vm_page_t.  The motivation for this change is that it
simplifies the use of radix tries in the amd64, arm64, and i386 pmap
implementations.  Instead of performing a lookup before every remove,
the pmap can simply perform the remove.

Reviewed by:	kib, markj
Differential Revision:	https://reviews.freebsd.org/D8708
2016-12-08 04:29:29 +00:00
markj
0ec6d3190b Use the correct path to date(1).
MFC after:	1 week
Sponsored by:	Dell EMC Isilon
2016-12-07 23:38:18 +00:00
markj
03e5175f9d Use the native data model instead of forcing ILP32 in tst.provregex3.ksh.
MFC after:	1 week
Sponsored by:	Dell EMC Isilon
2016-12-07 23:37:51 +00:00
markj
c9f66bbdde Run DTrace test scripts with "tst" set to the test script file name.
MFC after:	1 week
Sponsored by:	Dell EMC Isilon
2016-12-07 23:36:15 +00:00
avos
5419d24d35 net80211: remove obsolete comment.
The described LOR should be fixed in r302283.
2016-12-07 23:33:59 +00:00