Commit Graph

126418 Commits

Author SHA1 Message Date
Alan Somers
1cedd6dfac fusefs: replace the fufh table with a linked list
The FUSE protocol allows each open file descriptor to have a unique file
handle.  On FreeBSD, these file handles must all be stored in the vnode.
The old method (also used by OSX and OpenBSD) is to store them all in a
small array.  But that limits the total number that can be stored.  This
commit replaces the array with a linked list (a technique also used by
Illumos).  There is not yet any change in functionality, but this is the
first step to fixing several bugs.

PR:		236329, 236340, 236381, 236560, 236844
Discussed with:	cem
Sponsored by:	The FreeBSD Foundation
2019-03-31 03:19:10 +00:00
Alan Somers
5fccbf313a fusefs: don't force direct io for files opened O_WRONLY
Previously fusefs would treat any file opened O_WRONLY as though the
FOPEN_DIRECT_IO flag were set, in an attempt to avoid issuing reads as part
of a RMW write operation on a cached part of the file.  However, the FUSE
protocol explicitly allows reads of write-only files for precisely that
reason.

Sponsored by:	The FreeBSD Foundation
2019-03-30 00:57:07 +00:00
Alan Somers
415e34c4d5 MFHead@r345677 2019-03-29 03:25:20 +00:00
Justin Hibbits
0499e9c619 powerpc64: Use medium code model in asm files for TOC references
Summary:
With a sufficiently large TOC, it's possible to index out of range, as
the immediate load instructions only permit 16-bit indices, allowing up
to 64kB range (signed) from the base pointer.  Allow +/- 2GB range, with
the medium code model TOC accesses in asm.

Patch originally by Brandon Bergren.  The issue appears to impact ELFv2
more than ELFv1.

Reviewed by:	luporl
Differential Revision: https://reviews.freebsd.org/D19708
2019-03-29 02:38:30 +00:00
Alan Somers
080518d810 fusefs: convert debug printfs into dtrace probes
fuse(4) was heavily instrumented with debug printf statements that could
only be enabled with compile-time flags. They fell into three basic groups:

1. Totally redundant with dtrace FBT probes. These I deleted.
2. Print textual information, usually error messages. These I converted to
   SDT probes of the form fuse:fuse:FILE:trace. They work just like the old
   printf statements except they can be enabled at runtime with dtrace. They
   can be filtered by FILE and/or by priority.
3. More complicated probes that print detailed information. These I
   converted into ad-hoc SDT probes.

Also, de-inline fuse_internal_cache_attrs.  It's big enough to be a regular
function, and this way it gets a dtrace FBT probe.

This commit is a merge of r345304, r344914, r344703, and r344664 from
projects/fuse2.

Reviewed by:	cem
MFC after:	2 weeks
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D19667
2019-03-29 02:13:06 +00:00
Justin Hibbits
4b4b6f0191 powerpc: Remove now-obsolete P9H MMU name 2019-03-29 02:11:48 +00:00
Alan Somers
98852a32af fusefs: fix error handling in fuse_vnop_strategy
Reported by:	cem
Sponsored by:	The FreeBSD Foundation
2019-03-28 21:57:42 +00:00
Edward Tomasz Napierala
09c78d53bf Factor out retrieving the interpreter path from the main ELF
loader routine.

Reviewed by:	kib
MFC after:	2 weeks
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D19715
2019-03-28 21:43:01 +00:00
Navdeep Parhar
dd3b96ecec cxgbe(4): Count and clear interrupts generated at the software's request.
An interrupt can be requested by setting the F_SWINT bit in PL_PF_CTL.

MFC after:	1 week
Sponsored by:	Chelsio Communications
2019-03-28 21:22:28 +00:00
John Baldwin
841613dcdc Use a dedicated malloc type for lagg(4)'s structures.
Reviewed by:	gallatin
MFC after:	1 month
Sponsored by:	Netflix
Differential Revision:	https://reviews.freebsd.org/D19719
2019-03-28 21:00:54 +00:00
Eric Joyner
225eae1bb7 iflib: return ENETDOWN when the network device is down
From Jake:
iflib_if_transmit returns ENOBUFS when the device is down, or when the
link isn't active.

This was changed in r308792 from return (0), so that the function
correctly reports an error that it was unable to transmit.

However, using ENOBUFS can cause some network applications to produce
the following or similar errors:

"ping: sendto: No buffer space available"

This is a bit confusing as the real cause of the issue is that the
network device is down.

Replace the ENOBUFS return with ENETDOWN to indicate more clearly that
the reason for the failure to send is due to the network device is
offline.

This will cause the error message to be reported as

"ping: sendto: Network is down"

Submitted by:	Jacob Keller <jacob.e.keller@intel.com>
Reviewed by:	shurd@, sbruno@, bz@
MFC after:	1 week
Sponsored by:	Intel Corporation
Differential Revision:	https://reviews.freebsd.org/D19652
2019-03-28 20:46:45 +00:00
Eric Joyner
aac9c817af iflib: hold the CTX lock in iflib_pseudo_register
From Jake:
The iflib_device_register function takes the CTX lock before calling
IFDI_ATTACH_PRE, and releases it upon finishing the registration.

Mirror this process in iflib_pseudo_register, so that we always hold the
CTX lock during the attach process when registering a pseudo interface
or a regular interface.

This was caught by code inspection while attempting to analyze where the
CTX lock was held.

Submitted by:	Jacob Keller <jacob.e.keller@intel.com>
Reviewed by:	shurd@, erj@
MFC after:	1 week
Sponsored by:	Intel Corporation
Differential Revision:	https://reviews.freebsd.org/D19604
2019-03-28 20:43:47 +00:00
Alexander Motin
b059686a71 Do not map small IOCTL buffers to KVA, but copy.
CAM IOCTL interfaces traditionally mapped user-space data buffers to KVA.
It was nice originally, but now it takes too much to handle respective
TLB shootdowns, while small kernel memory allocations up to 64KB backed
by UMA and accompanied by copyin()/copyout() can be much cheaper.

For large buffers mapping still may have sense, and unmapped I/O would
be even better, but the last unfortunately is more tricky, since unmapped
I/O API is too specific to struct bio now.

MFC after:	2 weeks
Sponsored by:	iXsystems, Inc.
2019-03-28 20:41:02 +00:00
John Baldwin
2f59b04af1 Remove nested epochs from lagg(4).
lagg_bcast_start appeared to have a bug in that was using the last
lagg port structure after exiting the epoch that was keeping that
structure alive.  However, upon further inspection, the epoch was
already entered by the caller (lagg_transmit), so the epoch enter/exit
in lagg_bcast_start was actually unnecessary.

This commit generally removes uses of the net epoch via LAGG_RLOCK to
protect the list of ports when the list of ports was already protected
by an existing LAGG_RLOCK in a caller, or the LAGG_XLOCK.

It also adds a missing epoch enter/exit in lagg_snd_tag_alloc while
accessing the lagg port structures.  An ifp is still accessed via an
unsafe reference after the epoch is exited, but that is true in the
current code and will be fixed in a future change.

Reviewed by:	gallatin
MFC after:	1 month
Sponsored by:	Netflix
Differential Revision:	https://reviews.freebsd.org/D19718
2019-03-28 20:25:36 +00:00
Ed Maste
5bf271b2f8 Revert change accidentally committed along with r345625
Reported by:	Oliver Pinter <oliver.pinter@hardenedbsd.org>
2019-03-28 10:56:27 +00:00
Hans Petter Selasky
b55bfda75c Add new USB PCI ID.
Submitted by:		Dmitry Luhtionov <dmitryluhtionov@gmail.com>
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2019-03-28 09:00:56 +00:00
Li-Wen Hsu
dac21b8d14 Fix make in sys/modules
Sponsored by:	The FreeBSD Foundation
2019-03-28 08:59:11 +00:00
Li-Wen Hsu
3cf75dbc4e Add dependent header files
Reported by:	https://ci.freebsd.org/job/FreeBSD-head-mips-build/6702/console
2019-03-28 08:30:45 +00:00
Kyle Evans
93c9d31918 if_bridge(4): ensure all traffic passing over the bridge is accounted for
Consider a bridge0 with em0 and em1 members. Traffic rx'd by em0 and
transmitted by bridge0 through em1 gets accounted for in IPACKETS/IBYTES
and bridge0 bpf -- assuming it's not unicast traffic destined for em1.
Unicast traffic destined for em1 traffic is not accounted for by any
mechanism, and isn't pushed through bridge0's bpf machinery as any other
packets that pass over the bridge do.

Fix this and simplify GRAB_OUR_PACKETS by bailing out early if it was rx'd
by the interface that it was addressed for. Everything else there is
relevant for any traffic that came in from one member that's being directed
at another member of the bridge.

Reviewed by:	kp
MFC after:	1 week
Differential Revision:	https://reviews.freebsd.org/D19614
2019-03-28 03:31:51 +00:00
Ed Maste
09b47fc1c2 revert r341429 "disable BIND_NOW in libc, libthr, and rtld"
r345620 by kib@ fixed the rtld issue that caused a crash at startup
during resolution of libc's ifuncs with BIND_NOW.

PR:		233333
Sponsored by:	The FreeBSD Foundation
2019-03-28 02:12:32 +00:00
Ravi Pokala
ca219866e3 Teach jedec_dimm(4) to be more forgiving of non-fatal errors.
It looks like some DIMMs claim to have a TSOD, but actually don't. Some
claim they weren't able to change the SPD page, but they did. Neither of
those should be fatal errors.

PR:		235944
Submitted by:	Greg V <greg@unrelenting.technology>
Reported by:	Greg V <greg@unrelenting.technology>
Reviewed by:	cem
MFC after:	1 weeks
Sponsored by:	Panasas
Differential Revision:	https://reviews.freebsd.org/D19681
2019-03-27 21:50:01 +00:00
Tycho Nightingale
cec2287b6a Use the BUS_DMA_NOWRITE flag to expose and create the read-only VT-d
IOMMU mappings.

Reviewed by:	kib
Sponsored by:	Dell EMC Isilon
Differential Revision:	https://reviews.freebsd.org/D19729
2019-03-27 20:15:51 +00:00
Mark Johnston
963ae7a63e Stop using -fdebug-prefix-map to map the object directory.
We were doing so as a workaround for the problem addressed by r345593, so
it's no longer necessary.

Reviewed by:	jhb
Discussed with:	emaste
MFC after:	2 weeks
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D19705
2019-03-27 19:34:19 +00:00
Alan Somers
f203d1734d fusefs: don't ignore errors in fuse_vnode_refreshsize
Reported by:	Coverity
Coverity CID:	1368622
Sponsored by:	The FreeBSD Foundation
2019-03-27 16:45:30 +00:00
Ruslan Bukin
61fef9e860 Grab timer frequency from FDT.
RISC-V timer has no dedicated DTS node and we have to get timer
frequency from cpus node.

Tested on Government Furnished Equipment (GFE) cores synthesized
on Xilinx VCU118.

Reviewed by:	markj
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D19727
2019-03-27 16:26:03 +00:00
Alan Somers
019dca0199 fusefs: delete dead code in fuse_vnop_setattr
The dead code in question was a broken and incomplete attempt to support the
default_permissions mount option during VOP_SETATTR.  There wasn't anything
there worth saving; I'll have to rewrite it later.

Reported by:	Coverity
Coverity CID:	1008668
Sponsored by:	The FreeBSD Foundation
2019-03-27 16:19:02 +00:00
Alan Somers
3885d4091d fusefs: fix a derefence-after-null-check
Reported by:	Coverity
Coverity CID:	1017940
Sponsored by:	The FreeBSD Foundation
2019-03-27 14:15:35 +00:00
Scott Long
aa24a04abf Add missing break statements. Coverity CID 1400446.
Reported by:	mav
2019-03-27 12:25:46 +00:00
Alan Somers
e0bec057db fusefs: correctly set fuse_release_in.flags in an error path
fuse_vnop_create must close the newly created file if it can't allocate a
vnode.  When it does so, it must use the same file flags for FUSE_RELEASE as
it used for FUSE_OPEN or FUSE_CREATE.

Reported by:	Coverity
Coverity CID:	1066204
Sponsored by:	The FreeBSD Foundation
2019-03-27 02:57:59 +00:00
Alan Somers
4a4282cb06 FUSEFS: during FUSE_READDIR, set the read size correctly.
The old formula was unnecessarily restrictive.

Sponsored by:	The FreeBSD Foundation
2019-03-27 02:01:34 +00:00
Alan Somers
3ba6a4d473 fusefs: set fuse_init_in->max_readahead correctly
The old value was correct only by coincidence.

Sponsored by:	The FreeBSD Foundation
2019-03-27 01:49:35 +00:00
Conrad Meyer
8207def158 x86: Use XSAVEOPT for fpusave(), when available
Remove redundant npxsave_core definition while here.

Suggested by:	Anton Rang
Reviewed by:	kib, Anton Rang <rang AT acm.org>
Sponsored by:	Dell EMC Isilon
Differential Revision:	https://reviews.freebsd.org/D19665
2019-03-26 22:45:41 +00:00
Mark Johnston
7762bbc30e Add CTLFLAG_VNET to the net.inet.icmp.tstamprepl definition.
Reported by:	Hans Fiedler <hans@hfconsulting.com>
MFC after:	3 days
2019-03-26 22:14:50 +00:00
Ed Maste
a342f5772f pf: use UID_ROOT and GID_WHEEL named constants in make_dev
No functional change but improves consistency and greppability of
make_dev calls.

Discussed with: kp
2019-03-26 21:20:42 +00:00
Edward Tomasz Napierala
0b208315f4 Improve error reporting when the swap pager runs out of memory.
Reviewed by:	kib
MFC after:	2 weeks
Sponsored by:	Klara Inc.
Differential Revision:	https://reviews.freebsd.org/D19699
2019-03-26 19:11:15 +00:00
Oleksandr Tymoshenko
b25ce41e33 Change default value of kern.bootfile to reflect reality
In most cases kernel.bootfile is populated from the information
provided by loader(8). There are certain scenarios when loader
is not available, for instance when kernel is loaded by u-boot
or some other BootROM directly. In this case the default value
"/kernel" points to invalid location and breaks some functinality,
like using installkernel on self-hosted system or dtrace's CTF
lookup. This can be fixed by setting the value manually but the
default that reflects correct location is better than default that
points to invalid one.

Current default was set around FreeBSD 1, when "/kernel" was the
actual path. Transition to /boot/kernel/kernel happened circa FreeBSD 3.

PR:		221550
Reviewed by:	ian, imp
MFC after:	1 week
Differential Revision:	https://reviews.freebsd.org/D18902
2019-03-26 18:03:18 +00:00
Edward Tomasz Napierala
7000d321e8 Make smartpqi(4) behave better when running out of memory, by returning
CAM_RESRC_UNAVAIL instead of CAM_REQUEUE_REQ.  This makes CAM delay a bit
before retrying, so that the retries actually get a chance to succeed.

Reviewed by:	sbruno
MFC after:	2 weeks
Sponsored by:	Klara Inc.
Differential Revision:	https://reviews.freebsd.org/D19696
2019-03-26 15:47:13 +00:00
Edward Tomasz Napierala
20e1174a00 Factor out resource limit enforcement code in the ELF loader.
It makes the code slightly easier to follow, and might make
it easier to fix the resouce accounting to also account for
the interpreter.

The PROC_UNLOCK() is moved earlier - I don't see anything
it should protect; the lim_max() is a wrapper around lim_rlimit(),
and that, differently from lim_rlimit_proc(), doesn't require
the proc lock to be held.

Reviewed by:	kib
MFC after:	2 weeks
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D19689
2019-03-26 15:35:49 +00:00
Randall Stewart
7854c63d6f Fix a small bug in the tcp_log_id where the bucket
was unlocked and yet the bucket-unlock flag was not
changed to false. This can cause a panic if INVARIANTS
is on and we go through the right path (though rare).

Reported by:	syzbot+179a1ad49f3c4c215fa2@syzkaller.appspotmail.com
Reviewed by:	tuexen@
MFC after:	1 week
2019-03-26 10:41:27 +00:00
Michael Tuexen
eb3b9ea3fe Fix a double free of an SCTP association in an error path.
This is joint work with rrs@. The issue was found by running
syzkaller.

MFC after:		1 week
2019-03-26 08:27:00 +00:00
Alan Somers
fd2749f25d fusefs: delete dead code
This change also inlines several previously #define'd symbols that didn't
really have the meanings indicated by the comments.

Sponsored by:	The FreeBSD Foundation
2019-03-26 03:02:45 +00:00
Justin Hibbits
9f1a007da7 powerpc64: Micro-optimize moea64 native pmap tlbie
* Cache moea64_need_lock in a local variable; gcc generates slightly better
  code this way, it doesn't need to reload the value from memory each read.
* VPN cropping is only needed on PowerPC ISA 2.02 and older cores, a subset
  of those that need serialization, so move this under the need_lock check,
  so those that don't need the lock don't even need to check this.
2019-03-26 02:53:35 +00:00
Kyle Evans
dc4636133f Allow kernel config to specify DTS/DTSO to build, and out-of-tree support
This allows for directives such as

makeoptions DTS+=/out/of/tree/myboard.dts
# in tree! Same rules applied as if this were in a dtb/ module
makeoptions DTS+=otherboard.dts

to be specified in config(5) and have these built/installed alongside th
kernel. The assumption that overlays live in an overlays/ directory is only
made for in-tree DTSO, but we still make the assumption that out-of-tree
arm64 DTS will be in vendored directories (for now).

This lowers the cost to hacking on an overlay or dts by being able to
quickly throw it in a custom config, especially if it doesn't fit one of the
current dtb/modules quite appropriately or it's not intended for commit
there.

The build/install targets were split out of dtb.mk to centralize the build
logic and leave out the all/realinstall/CLEANFILES additions... it was
believed that we didn't want to pollute the kernel build with these.

The build rules were converted to suffix rules at the suggestion of Ian to
clean things up a little bit in a world where we can have mixed
in-tree/out-of-tree DTS/DTSO specified.

Reviewed by:	ian
MFC after:	1 week
Differential Revision:	https://reviews.freebsd.org/D19351
2019-03-26 02:45:23 +00:00
Maxim Sobolev
4f20706113 Refine r345425: get rid of superfluous helper macro that I have added.
MFC after:	2 weeks
2019-03-26 01:28:10 +00:00
Mark Johnston
fd76e780a7 Reject F_SETLK_REMOTE commands when sysid == 0.
A sysid of 0 denotes the local system, and some handlers for remote
locking commands do not attempt to deal with local locks.  Note that
F_SETLK_REMOTE is only available to privileged users as it is intended
to be used as a testing interface.

Reviewed by:	kib
Reported by:	syzbot+9c457a6ae014a3281eb8@syzkaller.appspotmail.com
MFC after:	2 weeks
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D19702
2019-03-25 21:38:58 +00:00
Andrew Turner
40fcc4760e Sort printing of the ID registers on arm64 to be identical to the
documentation. This will simplify checking new fields when they are added.

MFC after:	2 weeks
Sponsored by:	DARPA, AFRL
2019-03-25 18:02:04 +00:00
Michael Tuexen
7c96d54f20 Initialize scheduler specific data for the FCFS scheduler.
This is joint work with rrs@. The issue was reported by using
syzkaller.

MFC after:		1 week
2019-03-25 16:40:54 +00:00
Michael Tuexen
689ed08920 Improve locking when tearing down an SCTP association.
This is joint work with rrs@ and the issue was found by
syzkaller.

MFC after:		1 week
2019-03-25 15:23:20 +00:00
Hans Petter Selasky
d7c5dccd66 Change all kernel C-type macros into static inline functions.
The current kernel C-type macros might obscurely hide the fact that
the input argument might be used multiple times.

This breaks code like:
isalpha(*ptr++)

Use static inline functions instead of macros to fix this.

Reviewed by:		kib @
Differential Revision:	https://reviews.freebsd.org/D19694
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2019-03-25 13:50:38 +00:00
Michael Tuexen
2de5b90420 Fix the handling of fragmented unordered messages when using DATA chunks
and FORWARD-TSN.

This bug was reported in https://github.com/sctplab/usrsctp/issues/286
for the userland stack.

This is joint work with rrs@.

MFC after:		1 week
2019-03-25 09:47:22 +00:00