bapt [Sat, 27 May 2017 12:46:46 +0000 (12:46 +0000)]
Partially revert r314948
While it sounds like a good idea to extract the RFC1048 data from PXE, in the
end it is not and it is causing lots of issues. Our pxeloader might need
options which are incompatible with other pxe servers (for example iPXE, but
not only).
Our pxe loaders are also now settings their own user class, so it is useful to
issue our own pxe request at startup
bapt [Sat, 27 May 2017 12:35:01 +0000 (12:35 +0000)]
Always issue the pxe request
All the code are now only issueing one single dhcp request at startup of the
loader meaning we can always request a the PXE informations from the
dhcp server.
Previous code lost that information, meaning no option 55 anymore (meaning not
working with the kea dhcp server) and no request for rootpath etc, no user class
Remove the flags from the bootp function which is not needed anymore
brooks [Fri, 26 May 2017 21:10:01 +0000 (21:10 +0000)]
Add missing usage and getopt(3) options
- Add the missing option 'n' to the getopt(3) string
- Add the missing options 'libxo' and 'N' to the usage message
- Add the missing options 'M' and 'N' to the man-page
jhb [Fri, 26 May 2017 20:20:40 +0000 (20:20 +0000)]
Fail large requests with EFBIG.
The adapter firmware in general does not accept PDUs larger than 64k - 1
bytes in size. Sending crypto requests larger than this size result in
hangs or incorrect output, so reject them with EFBIG. For requests
chaining an AES cipher with an HMAC, the firmware appears to require
slightly smaller requests (around 512 bytes).
mav [Fri, 26 May 2017 20:15:33 +0000 (20:15 +0000)]
Improve applying unified capabilities to the lagg ports.
Some NICs have some capabilities dependent, so that disabling one require
disabling some other (TXCSUM/RXCSUM on em). This code tries to reach the
consensus more insistently.
avg [Fri, 26 May 2017 17:44:47 +0000 (17:44 +0000)]
Allow PROBE_SPINUP to fail in CAM ATA transport
The motivation for this is two-fold.
1. Some old WD SATA disks may appear as if they need to be spun up
when they are already spinning. Those disks would respond with
an error to the spin-up request.
2. Even if we really fail to spin up the disk, we still can try to
proceed to the subsequent phases. If we fail later on, then no
difference. Otherwise we get a chance to communicate with the
disk which is better than completely ignoring it, because a user
can try to recover the disk.
dab [Fri, 26 May 2017 16:36:30 +0000 (16:36 +0000)]
Add newsyslog capability to write RFC5424 compliant rotation message.
This modification adds the capability to newsyslog to write the
rotation message in a format that is compliant with RFC5424. This
capability is enabled on a per-log file basis through a new value
("T") in the flags field in newsyslog.conf. This is useful on systems
that use the RFC5424 format for log files so that the rotation message
format matches that of the other log messages. There has been recent
mention of adding an RFC5424 compliant mode to syslogd and at least
one alternative system log daemon (rsyslogd) that already has the
capability to use that format.
dim [Fri, 26 May 2017 16:29:55 +0000 (16:29 +0000)]
Define a new __INO64 macro in <sys/_types.h>, to indicate the system
uses 64-bit inode numbers. Programs can use this to avoid including
<sys/param.h>, with its associated namespace pollution.
emaste [Fri, 26 May 2017 16:03:28 +0000 (16:03 +0000)]
rm stale ptrace dependencies after r305012
This is similar to r318912, except that ptrace.[sS] was previously a
file in the source tree, not a generated assembly wrapper.
Check for the existence of ptrace.[sS] in the .depend file to determine
if we have to clean it up. This is a bit hackish and will not be left
in place indefinitely, but provides a useful example case when
investigating a better solution in bmake.
Reviewed by: bdrewery
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D10930
vangyzen [Fri, 26 May 2017 15:51:51 +0000 (15:51 +0000)]
libthr: prevent setcontext() from masking SIGTHR
__thr_setcontext() mistakenly tested for the presence of SIGCANCEL
in its local ucontext_t instead of the parameter. Therefore,
if a thread calls setcontext() with a context whose signal mask
contains SIGTHR (a.k.a. SIGCANCEL), that signal will be blocked,
preventing the thread from being cancelled or suspended.
https://www.illumos.org/issues/8166
If we do a scrub while a leaf device is offline (via "zpool offline"),
we will inadvertently clear the DTL (dirty time log) of the offline
device, even though it is still damaged. When the device comes back
online, we will incompletely resilver it, thinking that the scrub
repaired blocks written before the scrub was started. The incomplete
resilver can lead to data loss if there is a subsequent failure of a
different leaf device.
The fix is to never clear the DTL of offline devices. Note that if a
device is onlined while a scrub is in progress, the scrub will be
restarted.
The problem can be worked around by running "zpool scrub" after
"zpool online".
See also https://github.com/zfsonlinux/zfs/issues/5806
Reviewed by: George Wilson george.wilson@delphix.com
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Approved by: Richard Lowe <richlowe@richlowe.net>
Author: Matthew Ahrens <mahrens@delphix.com>
https://www.illumos.org/issues/8063
A standard practice in ZFS is to keep track of "per-txg" state. Any of
the 3 active TXG's (open, quiescing, syncing) can have different values
for this state. We should assert that we do not attempt to modify other
(inactive) TXG's.
Reviewed by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>
https://www.illumos.org/issues/7786
Currently, vdev_online() will only post sysevent if previous state was
"offline". It should also post the event when the state changes from "removed"
or "faulted" to "healthy" or "degraded".
This will fix the following scenario:
- pull disk from slot A
- check that hotspare has taken its place (if available)
- insert disk into slot B
- check that hotspare moved back to "avail" state (if spare was used)
The problem here is that we don't get any ESC_ZFS_VDEV_* notification and fail
to update the vdev FRU.
Reviewed by: Matthew Ahrens mahrens@delphix.com
Reviewed by: George Wilson george.wilson@delphix.com
Approved by: Albert Lee <trisk@forkgnu.org>
Author: Yuri Pankov <yuri.pankov@nexenta.com>
https://www.illumos.org/issues/8025
dbuf_read() creates a zio_root() to track and wait for all the zio's
that may happen as part of this call. However, if the blkptr_t for
this buffer is NULL or a hole, we will not create any more zio's, so
this zio_root() is unnecessary. This is always the case when calling
dbuf_read() on a bonus buffer, because it has no blkptr (it's part of
the containing dnode). For workloads that read a lot of bonus buffers
(e.g. file creation and removal), creating and destroying these
unnecessary zio's can decrease performance by around 3%.
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Prashanth Sreenivasa <pks@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>
FreeBSD note: only a ZFS part of the change is merged, changes to the VM
subsystem are not ported (obviously). Also, now that FreeBSD has
vmem(9) we don't have to ifdef-out the code that uses it.
avg [Fri, 26 May 2017 11:05:56 +0000 (11:05 +0000)]
arc_init: make code closer to upstream by introducing 'allmem' variable
All the differences in calculations are kept.
A comment about arc_max being 1/2 of all memory is fixed to reflect the
actual code that uses 5/8 as a factor.
https://www.illumos.org/issues/7256
error = dmu_sync(zio, lr->lr_common.lrc_txg,
zfs_get_done, zgd);
ASSERT(error || lr->lr_length <= zp->z_blksz);
It's possible, although extremely rare, that the zfs_get_done() callback is
executed before dmu_sync() returns.
In that case the znode's range lock is dropped and the znode is unreferenced.
Thus, the assertion can access some invalid or wrong data via the zp pointer.
size variable caches the correct value of z_blksz and can be safely used here.
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Andriy Gapon <andriy.gapon@clusterhq.com>
https://www.illumos.org/issues/8061
sa_find_idx_tab() is declared as taking and returning "void *" parameters.
These can be declared to be the specific types.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Chris Williamson <chris.williamson@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Matthew Ahrens <mahrens@delphix.com>
pfg [Fri, 26 May 2017 01:14:58 +0000 (01:14 +0000)]
fts_open: move bogus initialization further below, before it is used.
Move an unneeded initialization, introduced in r54770 to quiet down GCC,
to a place nearer to its first use. This has no practical effect, it just
keeps the garbage better sorted.
Hinted by: OpenBSD (CVS rev. 1.56, without obfuscations)
emaste [Fri, 26 May 2017 00:51:05 +0000 (00:51 +0000)]
libc: rm stale generated files which are no longer syscalls
This is an attempt to help -DNO_CLEAN builds after r302092 (which
removed the pipe libc syscall wrapper) and r318736 (which removed
getdents, lstat, mknod, and stat).
Dependencies cannot cope with certain source tree changes,
particularly with respect to removing source files and replacing
generated files. Handle these cases from _worldtmp in an ad-hoc
fashion.
Reviewed by: bdrewery, cem
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D10876
dim [Thu, 25 May 2017 23:14:51 +0000 (23:14 +0000)]
Pull in r303257 from upstream llvm trunk (by Krzysztof Parzyszek)
[PPC] Properly update register save area offsets
The variables MinGPR/MinG8R were not updated properly when resetting the
offsets, which in the included testcase lead to saving the CR register
in the same location as R30.
bapt [Thu, 25 May 2017 21:16:39 +0000 (21:16 +0000)]
Remove the old man.template
In FreeBSD we only use mdoc(7) format. A template is available as mdoc.template
The usage of man(7) format is discouraged and this file was driving people into
the front direction as a template to use.
dteske [Thu, 25 May 2017 18:16:17 +0000 (18:16 +0000)]
Fix long standing issue in bsdconfig's keymap selection
Since the translation to vt as terminal emulator, the keymaps files
path has changed and this change does not get followed in bsdconfig.
This implicates boot time warnings about a wrong keymap file, what
is very confusing for the new users and for me too, so initialize
the default keymaps search path depending on terminal type.
Differential Revision: https://reviews.freebsd.org/D8734
Submitted by: Oliver Pinter <oliver.pinter@hardenedbsd.org>
Reviewed by: ed, jilles, dteske
MFC after: 3 days
X-MFC-to: stable/11
Sponsored by: HardenedBSD
Signed-off-by: Oliver Pinter <oliver.pinter@hardenedbsd.org>
bapt [Thu, 25 May 2017 17:45:50 +0000 (17:45 +0000)]
Import working progress BSD diff3
import bsd diff3 from OpenBSD.
Differences with OpenBSD:
- lots of warning fixed
- no shell wrapper with diff3 actually living in libexec
- capsicumized
Keep it disconnected as it is not yet good enough to replace GNU diff
The motivation to import it now it to allow other people to jump in and also to
have an open development on it
emaste [Thu, 25 May 2017 16:41:07 +0000 (16:41 +0000)]
lldb: map TRAP_CAP to a trace trap
In the absense of a more specific handler for TRAP_CAP (generated by
ENOTCAPABLE or ECAPMODE while in capability mode) treat it as a trace
trap.
Example usage (testing the bug in PR219173):
% proccontrol -m trapcap lldb usr.bin/hexdump/obj/hexdump -- -Cv -s 1 /bin/ls
...
(lldb) run
Process 12980 launching
Process 12980 launched: '.../usr.bin/hexdump/obj/hexdump' (x86_64)
Process 12980 stopped
* thread #1, stop reason = trace
frame #0: 0x0000004b80c65f1a libc.so.7`__sys_lseek + 10
...
In the future we should have LLDB control the trapcap procctl itself
(as it does with ASLR), as well as report a specific stop reason.
This change eliminates an assertion failure from LLDB for now.
bapt [Thu, 25 May 2017 14:54:22 +0000 (14:54 +0000)]
In preparation for the removal of the roff toolchain, disconnect the
roff documentation from the build.
Those documents will be added to the doc tree and distributed as PDF from
the documentation website. As they are valuable has history, but do not match
current FreeBSD
Further more, the ascii format we were using to distribute them is not really
accurate for such documents.
more details:
https://lists.freebsd.org/pipermail/freebsd-arch/2017-May/018211.html
zbb [Thu, 25 May 2017 14:25:05 +0000 (14:25 +0000)]
Add workaround for CESA MBUS windows with 4GB DRAM
Armada 38x SoC's equipped with 4GB DRAM suffer freeze
during CESA operation, if MBUS window opened at given
DRAM CS reaches end of the address space. Apply a workaround
by setting the window size to the closest possible
value, i.e. divide it by 2 (it has to be power-of-2).
zbb [Thu, 25 May 2017 14:22:00 +0000 (14:22 +0000)]
Introduce separate watchdog driver for Armada to fix phony DELAY
DELAY is a problematic routine called all over the kernel.
Armada38x using CA-9 CPUs are using mpcore timer to count events
and measure time but DELAY in the mpcore timer code is a weak
function reference and therefore will be replaced by the platform
implementation if the one is introduced. Since Armada38x uses
on-chip watchdog to which the driver is merged with the on-chip timer
driver there will be a platform DELAY implementation.
The latter however will not use any HW timers as it will not attempt
to configure any. Phony busy loop will be used instead.
To fix that we introduce a separate watchdog driver for Armada platforms,
(currently only A38X) and stop using Marvell timer driver. That
switches DELAY to the desired implementation.
zbb [Thu, 25 May 2017 14:16:43 +0000 (14:16 +0000)]
Fix memory corruption while configuring CPU windows on Marvell SoCs
Resolving CPU windows from localbus entry caused buffer overflow
and memory corruption. Fix wrong indexing and ensure the index
does not exceed table size.
avg [Thu, 25 May 2017 10:49:56 +0000 (10:49 +0000)]
fix vmxnet3 crash when LRO is enabled
The crash can occur when all of the following conditions are true:
- a packet consists of multiple segements (requires LRO enabled)
- there has been a failure to allocate an mbuf for the packet and
the packet has to be dropped
- a host (vmware) still owned at least one segment of the packet,
so the driver had to wait for another interrupt to proceed to
discarding the remaning segment(s)
adrian [Thu, 25 May 2017 04:18:46 +0000 (04:18 +0000)]
[ath] [ath_hal] (etc, etc) - begin the task of re-modularising the HAL.
In the deep past, when this code compiled as a binary module, ath_hal
built as a module. This allowed custom, smaller HAL modules to be built.
This was especially beneficial for small embedded platforms where you
didn't require /everything/ just to run.
However, sometime around the HAL opening fanfare, the HAL landed here
as one big driver+HAL thing, and a lot of the (dirty) infrastructure
(ie, #ifdef AH_SUPPORT_XXX) to build specific subsets of the HAL went away.
This was retained in sys/conf/files as "ath_hal_XXX" but it wasn't
really floated up to the modules themselves.
I'm now in a position where for the reaaaaaly embedded boards (both the
really old and the last couple generation of QCA MIPS boards) having a
cut down HAL module and driver loaded at runtime is /actually/ beneficial.
This reduces the kernel size down by quite a bit. The MIPS modules look
like this:
adrian@gertrude:~/work/freebsd/head-embedded/src % ls -l ../root/mips_ap/boot/kernel.CARAMBOLA2/ath*ko
-r-xr-xr-x 1 adrian adrian 5076 May 23 23:45 ../root/mips_ap/boot/kernel.CARAMBOLA2/ath_dfs.ko
-r-xr-xr-x 1 adrian adrian 100588 May 23 23:45 ../root/mips_ap/boot/kernel.CARAMBOLA2/ath_hal.ko
-r-xr-xr-x 1 adrian adrian 627324 May 23 23:45 ../root/mips_ap/boot/kernel.CARAMBOLA2/ath_hal_ar9300.ko
-r-xr-xr-x 1 adrian adrian 314588 May 23 23:45 ../root/mips_ap/boot/kernel.CARAMBOLA2/ath_main.ko
-r-xr-xr-x 1 adrian adrian 23472 May 23 23:45 ../root/mips_ap/boot/kernel.CARAMBOLA2/ath_rate.ko
And the x86 versions, like this:
root@gertrude:/home/adrian # ls -l /boot/kernel/ath*ko
-r-xr-xr-x 1 root wheel 36632 May 24 18:32 /boot/kernel/ath_dfs.ko
-r-xr-xr-x 1 root wheel 134440 May 24 18:32 /boot/kernel/ath_hal.ko
-r-xr-xr-x 1 root wheel 82320 May 24 18:32 /boot/kernel/ath_hal_ar5210.ko
-r-xr-xr-x 1 root wheel 104976 May 24 18:32 /boot/kernel/ath_hal_ar5211.ko
-r-xr-xr-x 1 root wheel 236144 May 24 18:32 /boot/kernel/ath_hal_ar5212.ko
-r-xr-xr-x 1 root wheel 336104 May 24 18:32 /boot/kernel/ath_hal_ar5416.ko
-r-xr-xr-x 1 root wheel 598336 May 24 18:32 /boot/kernel/ath_hal_ar9300.ko
-r-xr-xr-x 1 root wheel 406144 May 24 18:32 /boot/kernel/ath_main.ko
-r-xr-xr-x 1 root wheel 55352 May 24 18:32 /boot/kernel/ath_rate.ko
.. so you can see, not building the whole HAL can save quite a bit.
For example, if you don't need AR9300 support, you can actually avoid
wasting half a megabyte of RAM. On embedded routers this is quite a
big deal.
The AR9300 HAL can be later further shrunk because, hilariously,
it indeed supports AH_SUPPORT_<xxx> for optionally adding chipset support.
(I'll chase that down later as it's quite a big savings if you're only
building for a single embedded target.)
So:
* Create a very hackish way to load/unload HAL modules
* Create module metadata for each HAL subtype - ah_osdep_arXXXX.c
* Create module metadata for ath_rate and ath_dfs (bluetooth is
currently just built as part of it)
* .. yes, this means we could actually build multiple rate control
modules and pick one at load time, but I'd rather just glue this
into net80211's rate control code. Oh well, baby steps.
* Main driver is now "ath_main"
* Create an "if_ath" module that does what the ye olde one did -
load PCI glue, main driver, HAL and all child modules.
In this way, if you have "if_ath_load=YES" in /boot/modules.conf
it will load everything the old way and stuff should still work.
* For module autoloading purposes, I actually /did/ fix up
the name of the modules in if_ath_pci and if_ath_ahb.
If you want to selectively load things (eg on ye cheape ARM/MIPS platforms
where RAM is at a premium) you should:
* load ath_hal
* load the chip modules in question
* load ath_rate, ath_dfs
* load ath_main
* load if_ath_pci and/or if_ath_ahb depending upon your particular
bus bind type - this is where probe/attach is done.
TODO:
* AR5312 module and associated pieces - yes, we have the SoC side support
now so the wifi support would be good to "round things out";
* Just nuke AH_SUPPORT_AR5416 for now and always bloat the packet
structures; this'll simplify other things.
* Should add a simple refcnt thing to the HAL RF/chip modules so you
can't unload them whilst you're using them.
* Manpage updates, UPDATING if appropriate, etc.
https://www.illumos.org/issues/6101
lzc_create(), or more correctly, zfs_ioc_create() does not reject an attempt to
create a filesystem as a child of a volume, instead it proceeds to a crash.
A crash stack obtained on FreeBSD:
page fault while in kernel mode
zap_leaf_lookup()
fzap_lookup()
zap_lookup_norm()
zap_lookup()
zfs_get_zplprop()
zfs_fill_zplprops_impl()
zfs_ioc_create()
zfsdev_ioctl()
devfs_ioctl_f()
kern_ioctl()
sys_ioctl()
This crash happened with a kernel without debugging assertions.
The immediate cause of crash appears to an attempt to interpret a zvol object
as a zap object.
For filesystems:
#define MASTER_NODE_OBJ 1
For zvols:
#define ZVOL_OBJ 1ULL
#define ZVOL_ZAP_OBJ 2ULL
So, I see two problems here:
1. an attempt to create a filesystem under a zvol should be rejected as
early as possible, maybe in zfs_fill_zplprops()
2. maybe zap_lookup / zap_lockdir should reject objects that are not of one
of the zap object types
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Andriy Gapon <avg@FreeBSD.org>
MFC after: 2 weeks
https://www.illumos.org/issues/8026
zfs_throttle_delay and zfs_throttle_resolution became disused since the new
write throttling mechanism was introduced.
https://www.illumos.org/issues/5380
A stream created with zfs send -p -I contains properties of all snapshots of a
given dataset as opposed to only properties of snapshots in a given range.
Not only this is suboptimal but the receive code also does not filter
properties by the range. So, properties of earlier snapshots would be updated
even though the snapshots themselves are not in the stream (just their
properties).
Given that modifying the snapshot properties requires a TXG sync and that the
snapshots are updated one by one the described behavior may lead to a sever
performance penalty.
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Andriy Gapon <avg@FreeBSD.org>
MFC after: 3 weeks
https://www.illumos.org/issues/8027
dsl_pool_dirty_delta() should not wake up waiters when dp->dp_dirty_total ==
zfs_dirty_data_max, because they wait for dp_dirty_total to fall strictly below
the threshold.
It's probably very rare for that condition to occur, but it's better to have
more accurate code.
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Andriy Gapon <avg@FreeBSD.org>
MFC after: 1 week
https://www.illumos.org/issues/7968
spa_sync() iterates over all the dirty dnodes and processes each of them by
calling dnode_sync(). If there are many dirty dnodes (e.g. because we created
or removed a lot of files), the single thread of spa_sync() calling
dnode_sync() can become a bottleneck. Additionally, if many dnodes are dirtied
concurrently in open context (e.g. due to concurrent file creation), the
os_lock will experience lock contention via dnode_setdirty().
The solution is to track dirty dnodes on a multilist_t, and for spa_sync() to
use separate threads to process each of the sublists in the multilist.
On the concurrent file creation microbenchmark, the performance improvement
from dnode_setdirty() is up to 7%. Additionally, the wall clock time spent in
spa_sync() is reduced to 15%-40% of the single-threaded case. In terms of cost/
reward, once the other bottlenecks are addressed, fixing this bug will provide
a medium-large performance gain and require a medium amount of effort to
implement.
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: Saso Kiselkov <saso.kiselkov@nexenta.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Matthew Ahrens <mahrens@delphix.com>
MFC after: 3 weeks
https://www.illumos.org/issues/7970
The global tunable zfs_arc_num_sublists_per_state is used by the ARC and
the dbuf cache, and other users are planned. We should change this
tunable to be common to all multilists.
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: Saso Kiselkov <saso.kiselkov@nexenta.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Matthew Ahrens <mahrens@delphix.com>
MFC after: 3 weeks
https://www.illumos.org/issues/7801
Add *_by_dnode() routines for accessing objects given their
dnode_t *, this is more efficient than accessing the object by
(objset_t *, uint64_t object). This change converts some but
not all of the existing consumers. As performance-sensitive
code paths are discovered they should be converted to use
these routines.
Ported from: https://github.com/zfsonlinux/zfs/commit/0eef1bde31d67091d3deed23fe2394f5a8bf2276
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: bzzz77 <bzzz.tomas@gmail.com>
MFC after: 24 days
https://www.illumos.org/issues/7869
The issue fixed by this patch is a race condition in the deadlist code.
A thread executing an administrative command that uses
`dsl_deadlist_space_range()` holds the lock of the whole `deadlist_t` to
protect the access of all its entries that the deadlist contains in an
avl tree.
Sync threads trying to insert a new entry in the deadlist
(through `dsl_deadlist_insert()` -> `dle_enqueue()`) do not hold the
deadlist lock at that moment. If the `dle_bpobj` is the empty bpobj (our
sentinel value), we close and reopen it. Between these two operations,
it is possible for the `dsl_deadlist_space_range()` thread to dereference
that bpobj which is `NULL` during that window.
Threads should hold the a deadlist's `dl_lock` when they manipulate its
internal data so scenarios like the one above are avoided. In addition,
threads should also hold the bpobj lock whenever they are allocating the
subobj list of a bpobj, and not just when they actually insert the subobj
to the list. This way we can avoid potential memory leaks.
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: John Kennedy <john.kennedy@delphix.com>
Reviewed by: George Melikov <mail@gmelikov.ru>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Serapheim Dimitropoulos <serapheim@delphix.com>
MFC after: 2 weeks
https://www.illumos.org/issues/7793
Background information: This assertion about tx_space_* verifies that we
are not dirtying more stuff than we thought we would. We “need” to know
how much we will dirty so that we can check if we should fail this
transaction with ENOSPC/EDQUOT, in dmu_tx_assign(). While the
transaction is open (i.e. between dmu_tx_assign() and dmu_tx_commit() —
typically less than a millisecond), we call dbuf_dirty() on the exact
blocks that will be modified. Once this happens, the temporary
accounting in tx_space_* is unnecessary, because we know exactly what
blocks are newly dirtied; we call dnode_willuse_space() to track this
more exact accounting.
The fundamental problem causing this bug is that dmu_tx_hold_*() relies
on the current state in the DMU (e.g. dn_nlevels) to predict how much
will be dirtied by this transaction, but this state can change before we
actually perform the transaction (i.e. call dbuf_dirty()).
This bug will be fixed by removing the assertion that the tx_space_*
accounting is perfectly accurate (i.e. we never dirty more than was
predicted by dmu_tx_hold_*()). By removing the requirement that this
accounting be perfectly accurate, we can also vastly simplify it, e.g.
removing most of the logic in dmu_tx_count_*().
The new tx space accounting will be very approximate, and may be more or
less than what is actually dirtied. It will still be used to determine
if this transaction will put us over quota. Transactions that are marked
by dmu_tx_mark_netfree() will be excepted from this check. We won’t make
an attempt to determine how much space will be freed by the transaction
— this was rarely accurate enough to determine if a transaction should
be permitted when we are over quota, which is why dmu_tx_mark_netfree()
was introduced in 2014.
We also won’t attempt to give “credit” when overwriting existing blocks,
if those blocks may be freed. This allows us to remove the
do_free_accounting logic in dbuf_dirty(), and associated routines. This
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>
MFC after: 3 weeks
hselasky [Wed, 24 May 2017 21:42:48 +0000 (21:42 +0000)]
Increase the allowed maximum number of audio channels from 31 to 127
in the PCM feeder mixer. Without this change a value of 32 channels is
treated like zero, due to using a mask of 0x1f, causing a kernel
assert when trying to playback bitperfect 32-channel audio. Also
update the AWK script which is generating the division tables to
handle more than 18 channels. This commit complements r282650.
https://www.illumos.org/issues/7541
When calling zpool import, zpool does a few ioctls to ZFS.
zpool allocates a buffer in userland and passes it to the kernel so that ZFS
can copy info into it. ZFS will use it to put the nvlist that describes the
pool configuration.
If the allocated buffer is too small, ZFS will return ENOMEM and the call will
have to be redone. This wastes CPU time and slows down the import process. This
happens very often for the ZFS_IOC_POOL_TRYIMPORT call.
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Pavel Zakharov <pavel.zakharov@delphix.com>
MFC after: 2 weeks
FreeBSD note: recent FreeBSD was not affected by the issue fixed as the
name cache is completely bypassed when normalization is enabled.
The change is imported for the sake of ZAP infrastructure modifications.
Reviewed by: Yuri Pankov <yuri.pankov@nexenta.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Kevin Crowe <kevin.crowe@nexenta.com>
https://www.illumos.org/issues/7545
When evicting from the ARC, we manipulate some refcount_t's, e.g. arcs_size.
When using zdb to examine a large amount of data (e.g. zdb -bb on a large pool
with small blocks), the ARC may have a large number of entries. If reference
tracking is enabled, there will be ~1 reference for each block in the ARC. When
evicting, we decrement the refcount and have to search all the references to
find the one that we are removing, which is very slow.
Since zdb is typically used to find problems with the on-disk format, and not
with the code it is running, we should disable reference tracking in zdb.
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>