ae [Thu, 11 Dec 2014 14:58:55 +0000 (14:58 +0000)]
Remove PACKET_TAG_IPSEC_IN_DONE mbuf tag lookup and usage of its
security policy. The changed block of code in ip*_ipsec_input() is
called when packet has ESP/AH header. Presence of
PACKET_TAG_IPSEC_IN_DONE mbuf tag in the same time means that
packet was already handled by IPSEC and reinjected in the netisr,
and it has another ESP/AH headers (encrypted twice?).
Since it was already processed by IPSEC code, the AH/ESP headers
was already stripped (and probably outer IP header was stripped too)
and security policy from the tdb_ident was applied to those headers.
It is incorrect to apply this security policy to current headers.
Also make ip_ipsec_input() prototype similar to ip6_ipsec_input().
ae [Thu, 11 Dec 2014 14:43:44 +0000 (14:43 +0000)]
Remove check for presence of PACKET_TAG_IPSEC_PENDING_TDB and
PACKET_TAG_IPSEC_OUT_CRYPTO_NEEDED mbuf tags. They aren't used in FreeBSD.
Instead check presence of PACKET_TAG_IPSEC_OUT_DONE mbuf tag. If it
is found, bypass security policy lookup as described in the comment.
PACKET_TAG_IPSEC_OUT_DONE tag added to mbuf when IPSEC code finishes
ESP/AH processing. Since it was already finished, this means the security
policy placed in the tdb_ident was already checked. And there is no reason
to check it again here.
ngie [Wed, 10 Dec 2014 23:18:11 +0000 (23:18 +0000)]
Fix building termcap.db when make obj is run beforehand from a clean tree by
using make variables for the filenames, which helps resolve pathing
appropriately when running cap_mkdb
ngie [Wed, 10 Dec 2014 20:40:03 +0000 (20:40 +0000)]
Remove termcap entry reordering; install the file verbatim instead
termcap entry reordering requires ex (which is available via usr.bin/vi), which
breaks on build hosts where installworld is run with MK_VI == no (or when
make delete-old is run on ^/projects/building-blocks as vi, et al, are
removed on the branch when the knob is tweaked to => "no")
Reordering termcap was believed to improve performance, but the file is now
accessed via /etc/termcap.db, so /etc/termcap (and /usr/share/misc/termcap by
proxy) access is less preferred.
Reordering the file broke the historical comment <-> entry mapping as well,
which could muddle the purpose of entries in the file, so it could be
potentially harmful to readers in its reordered state.
Discussion took place on hackers@ here:
https://lists.freebsd.org/pipermail/freebsd-hackers/2014-December/046657.html
trasz [Wed, 10 Dec 2014 14:36:44 +0000 (14:36 +0000)]
Add "-media" autofs map, to access data on removable media, such as CD
drives or flash keys. It can be enabled by uncommenting a single entry
in default /etc/auto_master. It can also be easily modified to use
fuse-based filesystems instead of in-kernel ones.
There is still one deficiency - the mountpoints are permanent, they
don't disappear when user removes the media. Fixing it needs some
autofs changes.
Differential Revision: https://reviews.freebsd.org/D1210
MFC after: 1 month
Sponsored by: The FreeBSD Foundation
trasz [Wed, 10 Dec 2014 14:14:16 +0000 (14:14 +0000)]
Add fstyp(8). This utility, named after its SVR4 counterpart, detects
filesystems. It differs from file(1) in that it gives machine-parseable
output, it outputs filesystem labels, doesn't get confused by other
formats metadata, and runs in Capsicum sandbox.
Differential Revision: https://reviews.freebsd.org/D1255
Relnotes: yes
Sponsored by: The FreeBSD Foundation
royger [Wed, 10 Dec 2014 13:25:21 +0000 (13:25 +0000)]
xen/intr: balance dynamic interrupts across available vCPUs
By default Xen binds all event channels to vCPU#0, and FreeBSD only shuffles
the interrupt sources once, at the end of the boot process. Since new event
channels might be created after this point (because new devices or backends
are added), try to automatically shuffle them at creation time.
This does not affect VIRQ or IPI event channels, that are already bound to a
specific vCPU as requested by the caller.
royger [Wed, 10 Dec 2014 11:42:02 +0000 (11:42 +0000)]
xen: mask event channels while binding them to a vCPU
Mask the event channel source before trying to bind it to a CPU, this
prevents stray interrupts from firing while assigning them and hitting the
KASSERT in xen_intr_handle_upcall.
royger [Wed, 10 Dec 2014 11:21:52 +0000 (11:21 +0000)]
xen: move grant table code
Mave the grant table code into the dev/xen folder in preparation for turning
it into a device using the newbus interface. This is just code motion, no
functional changes.
delphij [Wed, 10 Dec 2014 08:18:22 +0000 (08:18 +0000)]
In r268924 __fflush was modified so that when write(2) was not successful,
_p and _w are adjusted to account for the partial write (if any).
However, _p and _w should not be unconditionally adjusted and should only
be changed when we actually wrote some bytes, or the accumulated accounting
error will eventually result in a heap buffer overflow.
Reported by: adrian and alfred (Norse Corporation)
Security: FreeBSD-SA-14:27.stdio
Security: CVE-2014-8611
ian [Wed, 10 Dec 2014 04:54:43 +0000 (04:54 +0000)]
Fix the watchdog timeout calculation to prevent wrap. The RPi hardware
can't do a timeout bigger than 15 seconds. The code wasn't checking for
this and because bitmasking was involved the requested timeout was
basically adjusted modulo-16. That led to things like a 128 second
timeout actually being a 9 second timeout, which accidentally worked fine
until watchdogd was changed to only pet the dog once every 10 seconds.
royger [Tue, 9 Dec 2014 18:03:25 +0000 (18:03 +0000)]
xen: create a new PCI bus override
When running as a Xen PVH Dom0 we need to add custom buses that override
some of the functionality present in the ACPI PCI Bus and the PCI Bus. We
currently override the ACPI PCI Bus, but not the PCI Bus, so add a new
override for the PCI Bus and share the generic functions between them.
Reported by: David P. Discher <dpd@dpdtech.com>
Sponsored by: Citrix Systems R&D
conf/files.amd64:
- Add the new files.
x86/xen/xen_pci_bus.c:
- Generic file that contains the PCI overrides so they can be used by the
several PCI specific buses.
xen/xen_pci.h:
- Prototypes for the generic overried functions.
dev/xen/pci/xen_pci.c:
- Xen specific override for the PCI bus.
dev/xen/pci/xen_acpi_pci.c:
- Xen specific override for the ACPI PCI bus.
o Add BERI Virtio Networking Frontend (if_vtbe)
o Move similar block/networking methods to common file
o Follow r275640 and correct MMIO registers width
o Pass value to MMIO platform_note method.
pfg [Tue, 9 Dec 2014 14:56:00 +0000 (14:56 +0000)]
ext2fs: Fix old out-of-bounds access.
Overrunning buffer pointed to by (caddr_t)&oip->i_db[0] of 48 bytes by
passing it to a function which accesses it at byte offset 59 using
argument 60UL.
The issue was inherited from an older FFS implementation and
fixed there with by merging UFS2 in r98542. We follow the
FFS fix.
Discussed with: bde
CID: 1007665
MFC after: 3 days
andrew [Tue, 9 Dec 2014 10:31:35 +0000 (10:31 +0000)]
Update the virtio driver to work on the ARM AArch64 Foundation Model.
There are two main parts to get it to work, 1) most of the register
accesses need to be word sized, other than the config register which
needs to be byte aligned, and 2) we don't need the platform driver
for this to work on the Foundation Model, allow it to be NULL.
Differential Revision: https://reviews.freebsd.org/D1240
Reviewed by: bryanv
Sponsored by: The FreeBSD Foundation
kib [Tue, 9 Dec 2014 10:00:47 +0000 (10:00 +0000)]
Do not call VFS_SYNC() before VFS_UNMOUNT() for forced unmount.
Since VFS does not/cannot stop writes, sync might run indefinitely, or
be a wrong thing to do at all. E. g. NFS ignores VFS_SYNC() for
forced unmounts, since non-responding server does not allow sync to
finish. On the other hand, filesystems can and do stop writes using
fs-specific facilities, and should already fully flush caches in
VFS_UNMOUNT() due to the race.
Adjust msdosfs tp sync in unmount for forced call, to accomodate the
new behaviour. Note that it is still racy, since writes are not
stopped.
Discussed with: avg, bjk, mckusick
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 3 weeks
This fixes a bug in the llvm vectorizer, which could sometimes cause
vectorized loops to perform an additional iteration, leading to possible
buffer overruns. Symptoms of this, which are usually segfaults, were
first noticed when building gcc ports, here:
ngie [Mon, 8 Dec 2014 18:29:20 +0000 (18:29 +0000)]
Add makewhatis to ITOOLS if MK_MAN != no
This will fix installation with differing host targets in installworld, so
one can build i386/i386 on an amd64 host, then install to an i386/i386 target
Reported by: alfred
Phabric: D1280
MFC after: 1 week
kib [Mon, 8 Dec 2014 16:48:57 +0000 (16:48 +0000)]
Add functions syncer_suspend() and syncer_resume(), which are supposed
to be called before suspension and after resume, correspondingly. The
syncer_suspend() ensures that all filesystems dirty data and metadata
are saved to the permanent storage, and stops kernel threads which
might modify filesystems. The syncer_resume() restores stopped
threads.
For now, only syncer is stopped. This is needed, because each sync
loop causes superblock updates for UFS.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
kib [Mon, 8 Dec 2014 16:42:34 +0000 (16:42 +0000)]
When getnewbuf_reuse_bp() is called to reclaim some (clean) buffer,
the vnode owning the buffer is not locked. More, it cannot be locked
safely, since getnewbuf_reuse_bp() is called from newbuf(), and some
other vnode is already locked, for which reused buffer will be
reassigned.
As the consequence, reclamation of the owning vnode could go in
parallel, in particular, the call to vnode_destroy_vobject(), which
deallocates the vm object and zeroes the v_bufobj->bo_object. Note
that the pages wired by the buffer are left wired and can be safely
freed by the vfs_vmio_release() without the need for the vm object
lock. Also, seeing stale pointer to the v_object is safe due to vm
object type stability.
Check for bo_bufobj != NULL and cache the value in local variable to
avoid trying to lock NULL vm object.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
kib [Mon, 8 Dec 2014 16:33:18 +0000 (16:33 +0000)]
Current reaction of the nfsd worker threads to any signal is exit.
This is not correct at least for the stop requests. Check for stop
conditions and suspend threads if requested.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
kib [Mon, 8 Dec 2014 16:27:43 +0000 (16:27 +0000)]
Do some refactoring and minor cleanups of the thread_single() code in
preparation for the global stop commit.
Move the code to weed suspended or sleeping threads into the
appropriate state, into the helper weed_inhib(). Current code already
has deep nesting and hard to follow [1].
Add currently useless helper remain_for_mode(), which returns the
count of threads which are allowed to run, according to the
single-threading mode.
In thread_single_end(), do not save curthread into local variable, it
is unused after, except to find curproc.
Remove stray empty line.
Requested by: avg [1]
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
kib [Mon, 8 Dec 2014 16:18:05 +0000 (16:18 +0000)]
Thread waiting for the vfork(2)-ed child to exec or exit, must allow
for the suspension.
Currently, the loop performs uninterruptible cv_wait(9) call, which
prevents suspension until child allows further execution of parent.
If child is stopped, suspension or single-threading is delayed
indefinitely.
Create a helper thread_suspend_check_needed() to identify the need for
a call to thread_suspend_check(). It is required since call to the
thread_suspend_check() cannot be safely done while owning the child
(p2) process lock. Only when suspension is needed, drop p2 lock and
call thread_suspend_check(). Perform wait for cv with timeout, in
case suspend is requested after wait started; I do not see a better
way to interrupt the wait.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
kib [Mon, 8 Dec 2014 16:02:02 +0000 (16:02 +0000)]
When process is exiting, check for suspension regardless of
multithreaded status of the process.
The stopped state must be cleared before P_WEXIT is set. A stop
signal delivered just before first PROC_LOCK() block in exit1(9) would
put the process into pending stop with P_WEXIT set or assertion
triggered. Also recheck for the suspension after failed
thread_single(9) call, since process lock could be dropped.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
pfg [Mon, 8 Dec 2014 15:10:48 +0000 (15:10 +0000)]
patch(1): avoid line number overflows
Introduce strtolinenum to properly check line numbers while parsing:
no signs, no spaces, just digits, 0 <= x <= LONG_MAX
Properly validate line ranges supplied in diff file to prevent overflows.
Also fixes an out of boundary memory access because the resulting values
are used as array indices.
rodrigc [Mon, 8 Dec 2014 07:25:59 +0000 (07:25 +0000)]
Use CURVNET macros inside inet_get_local_port_range() function.
Without this fix, a kernel with VIMAGE + Infiniband will panic on bootup.
Certain necessary #include statements require LIST_HEAD.
Add these includes to ofed/include/linux/list.h, because
LIST_HEAD is specifically overridden in this file.
delphij [Mon, 8 Dec 2014 06:10:47 +0000 (06:10 +0000)]
Use calloc() instead of malloc() + bzero(). This also gets rid of a warning
because bzero is defined by strings.h which is not included in thread_pool.c.
delphij [Mon, 8 Dec 2014 06:04:42 +0000 (06:04 +0000)]
MFV r275540:
When importing a pool, don't assume that the passed pool configuration
at vdev_load is always vaild. It's possible that a stale configuration
that comes with extra vdevs, where metaslab_init() would fail because
of lower layer returns error.
Change the code to make metaslab_init() handle and return errors from
lower layer and pass it back to upper layer and handle it there.
Illumos issue:
5213 panic in metaslab_init due to space_map_open returning ENXIO
markj [Mon, 8 Dec 2014 04:44:40 +0000 (04:44 +0000)]
Add refcounting to IPv6 DAD objects and simplify the DAD code to fix a
number of races which could cause double frees or use-after-frees when
performing DAD on an address. In particular, an IPv6 address can now only be
marked as a duplicate from the DAD callout.
avg [Sun, 7 Dec 2014 11:21:41 +0000 (11:21 +0000)]
remove opensolaris cyclic code, replace with high-precision callouts
In the old days callout(9) had 1 tick precision and that was inadequate
for some uses, e.g. DTrace profile module, so we had to emulate cyclic
API and behavior. Now we can directly use callout(9) in the very few
places where cyclic was used.
mav [Sat, 6 Dec 2014 20:39:25 +0000 (20:39 +0000)]
Count consecutive read requests as blocking in CTL for files and ZVOLs.
Technically read requests can be executed in any order or simultaneously
since they are not changing any data. But ZFS prefetcher goes crasy when
it receives consecutive requests from different threads. Since prefetcher
works on level of separate blocks, instead of two consecutive 128K requests
it may receive 32 8K requests in mixed order.
This patch is more workaround then a real fix, and it does not fix all of
prefetcher problems, but it improves sequential read speed by 3-4x times
in some configurations. On the other side it may hurt performance if
some backing store has no prefetch, that is why it is disabled by default
for raw devices.
delphij [Sat, 6 Dec 2014 00:38:55 +0000 (00:38 +0000)]
4181 zfs(1m): 'zfs allow' examples in the man page are outdated
Reviewed by: Richard Lowe <richlowe@richlowe.net>
Reviewed by: Gordon Ross <gordon.ross@nexenta.com>
Reviewed by: Yuri Pankov <yuri.pankov@nexenta.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Marcel Telka <marcel.telka@nexenta.com>
delphij [Sat, 6 Dec 2014 00:17:25 +0000 (00:17 +0000)]
5312 libzfs should be decoupled from kernel's zfs_context.h
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Will Andrews <willa@spectralogic.com>
Reviewed by: Andriy Gapon <avg@FreeBSD.org>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Justin T. Gibbs <justing@spectralogic.com>
cxgbe(4): Allow for different pad and pack boundaries for different
adapters. Set the pack boundary for T5 cards to be the same as the
PCIe max payload size. The chip likes it this way.
In this revision the driver allocate rx buffers that align on both
boundaries. This is not a strict requirement and a followup commit
will switch the driver to a more relaxed allocation strategy.
delphij [Sat, 6 Dec 2014 00:10:47 +0000 (00:10 +0000)]
5316 allow smbadm join to use RPC
Reviewed by: Bayard Bell <bayard.bell@nexenta.com>
Reviewed by: Dan McDonald <danmcd@nexenta.com>
Reviewed by: Thomas Keiser <thomas.keiser@nexenta.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Gordon Ross <gwr@nexenta.com>
delphij [Sat, 6 Dec 2014 00:01:19 +0000 (00:01 +0000)]
3363 Mark non-returning functions in ctftools
Reviewed by: Richard Lowe <richlowe@richlowe.net>
Reviewed by: Josef 'Jeff' Sipek <josef.sipek@nexenta.com>
Approved by: Albert Lee <trisk@omniti.com>
Author: Erik Cederstrand <erik@cederstrand.dk>