Sascha Wildner [Wed, 11 Oct 2017 20:05:26 +0000 (22:05 +0200)]
kernel/atkbdc: Fix a prototype.
Sascha Wildner [Wed, 11 Oct 2017 20:04:43 +0000 (22:04 +0200)]
kernel/cam: Add some missing parameter names.
Just like the rest of the file.
Sascha Wildner [Wed, 11 Oct 2017 17:31:25 +0000 (19:31 +0200)]
<vfs/hammer2/hammer2.h>: Fix parameter names in two prototypes.
Discussed-with: dillon
Sascha Wildner [Wed, 11 Oct 2017 14:55:23 +0000 (16:55 +0200)]
kernel: Simplify various redundant conditions.
Found-by: cppcheck
One was reported by dcb in <https://bugs.dragonflybsd.org/issues/3078>.
Matthew Dillon [Tue, 10 Oct 2017 22:38:08 +0000 (15:38 -0700)]
libc - Bring in s_ceill.c v1.2 from OpenBSD (2)
* Note, correction, v1.3 from OpenBSD, not v1.2
* Restore a cast that we need to compile with our higher WARNS level.
Reported-by: marino, xenu
Lubos Boucek [Mon, 2 Oct 2017 02:16:10 +0000 (02:16 +0000)]
kernel/mrsas: Simplify redundant conditions and remove never used variable
Reported-by: dcb
Matthew Dillon [Tue, 10 Oct 2017 02:17:32 +0000 (19:17 -0700)]
libc - Bring in s_ceill.c v1.2 from OpenBSD
fix a case where ceill() returns 1.0L: in the x86 extended precision format
the fraction part has no implicit bit.
Reported-by: xenu
Taken-from: OpenBSD
Sascha Wildner [Sun, 8 Oct 2017 07:47:58 +0000 (09:47 +0200)]
hammer2.8/pthread_attr_setaffinity_np.3: Fix mdoc issues.
Thomas Nikolajsen [Sat, 7 Oct 2017 14:14:52 +0000 (16:14 +0200)]
disklabel64.8: Add HAMMER2 fstype info.
Thomas Nikolajsen [Sat, 7 Oct 2017 14:09:36 +0000 (16:09 +0200)]
periodic.conf.5: Add hammer2 variables.
Add description for periodic HAMMER2 script variables: 161.clean_hammer2.
While here add HAMMER man pages to SEE ALSO section.
Thomas Nikolajsen [Sat, 7 Oct 2017 13:53:37 +0000 (15:53 +0200)]
etc/periodic/daily/161.clean-hammer2: Fix typo
pfslist variable for HAMMER, not HAMMER2 was used.
This will typically have no effect, as pfslist is typically empty.
Thomas Nikolajsen [Sat, 7 Oct 2017 13:19:41 +0000 (15:19 +0200)]
periodic.conf: Fix typo in comment
Thomas Nikolajsen [Sat, 7 Oct 2017 13:13:11 +0000 (15:13 +0200)]
mount_hammer2(8): Add man page.
Matthew Dillon [Fri, 6 Oct 2017 05:59:40 +0000 (22:59 -0700)]
kernel - Refuse to swapoff under certain conditions
* Both tmpfs and vn can't handle swapoff's method of bringing pages
back in from the swap partition being decomissioned.
* Fixing this properly is fairly involved. The normal swapoff procedure
is to page swap into the related VM object, but tmpfs and vn use their
VM objects ONLY to track swap blocks and not for vm_page manipulation,
so that just won't work. In addition, the swap code may associate
a swap block with a VM object before issuing the write I/O to page
out the data, and the swapoff code's asynchronous pagein might cause
problems.
For now, just make sure that swapoff refuses to remove the partition
under these conditions, so it doesn't blow up tmpfs or vn.
Matthew Dillon [Fri, 6 Oct 2017 01:57:33 +0000 (18:57 -0700)]
tmpfs - Fix bug in call to vinitvmio()
* TMPFS_BLKMASK was being passed to vinitvmio() instead of
TMPFS_BLKSIZE. It is unclear if this caused any particular
issue other than an occasional console warning. Fixed.
Matthew Dillon [Thu, 5 Oct 2017 20:46:54 +0000 (13:46 -0700)]
kernel - Change index fields from unsigned to signed
* We use a signed trick for (j), fix the code so it actually works.
* The chipset field used to index (i) cannot exceed 1024 anyway.
Reported-by: lubos Bug #3020
Lubos Boucek [Sat, 23 Sep 2017 07:12:28 +0000 (07:12 +0000)]
Fix seg-faults on crypt(3) failure
Lubos Boucek [Fri, 22 Sep 2017 22:27:18 +0000 (22:27 +0000)]
Improve kdump.1 and ktrace.1
Aaron LI [Wed, 27 Sep 2017 10:24:05 +0000 (18:24 +0800)]
nologin(8): Sync with FreeBSD; Symlink as /usr/sbin/nologin
* Sync "nologin.c" with FreeBSD. Login attempts are logged into syslog.
* Create symlink "/usr/sbin/nologin" to "/sbin/nologin". FreeBSD
(and Linux) installs "nologin" at "/usr/sbin/nologin", and the users
created by DPorts/packages also use "/usr/sbin/nologin" (see
"/usr/dports/UIDs").
* Statically link "nologin" as done by FreeBSD.
Sascha Wildner [Thu, 5 Oct 2017 18:16:24 +0000 (20:16 +0200)]
camcontrol(8): Check scsiserial()'s error, too.
After some testing with devices that have no serial number, it looks
like this is safe to add nowadays.
Reported-by: dcb
Submitted-by: Lubos Boucek <bouceklubos@gmail.com>
Dragonfly-bug: <https://bugs.dragonflybsd.org/issues/3059>
Sepherosa Ziehau [Thu, 5 Oct 2017 06:06:11 +0000 (14:06 +0800)]
socket: Limit the number of accepted sockets that kevent reports.
By default it is limited to 32. It can be changed through:
sysctl kern.ipc.soavailconn=X
This change does _not_ affect userland using accept(2) in the following
way:
for (;;) {
s = accept();
if (s < 0 && errno == EAGAIN)
break;
/* Processing accepted socket. */
}
This change only affects optimized userland using kevent.data to avoid
extra accept(2) syscall:
for (i = 0; i < kevent.data; ++i) {
s = accept();
/* Processing accepted socket. */
}
The above logic is applied by nginx. However, due to the cost of the
"Processing accepted socket" parts, this kinda of loop can increase
latency and destablize latency.
The comparison w/ 30K concurrent connections, 1 request/connection.
1K web object
| performance | lat-avg | lat-stdev | lat-99%
---------+--------------+----------+-----------+----------
no limit | 210279.88tps | 59.19ms | 4.60ms | 69.02ms
---------+--------------+----------+-----------+----------
32 limit | 217599.01tps | 32.00ms | 2.35ms | 35.59ms
========
8K web object
| performance | lat-avg | lat-stdev | lat-99%
---------+--------------+----------+-----------+----------
no limit | 180627.61tps | 70.53ms | 4.95ms | 80.61ms
---------+--------------+----------+-----------+----------
32 limit | 186324.41tps | 37.41ms | 4.81ms | 48.69ms
========
16K web object
| performance | lat-avg | lat-stdev | lat-99%
---------+--------------+----------+-----------+----------
no limit | 138667.84tps | 95.93ms | 14.90ms | 135.47ms
---------+--------------+----------+-----------+----------
32 limit | 138778.11tps | 60.90ms | 11.80ms | 92.07ms
This change significantly reduces average latency and .99 latency,
and performance is improved slightly.
Sascha Wildner [Wed, 4 Oct 2017 17:01:17 +0000 (19:01 +0200)]
Bring in vmx(4) (VMware virtual network driver, aka vmxnet3).
Some features are still disabled, namely LRO, TSO, VLAN_HWFILTER,
and MSI-X support. That being said, it works and seems stable.
Tested-by: swildner (VMware Player 7.1.4 build-3848939)
tuxillo (VMware ESXi 6.5.0 (Build 4887370))
Taken-from: FreeBSD (in turn based on OpenBSD's driver)
Matthew Dillon [Tue, 3 Oct 2017 01:42:34 +0000 (18:42 -0700)]
kernel - Fix GCC reordering problem with td_critcount
* Wrap all ++td->td_critcount and --td->td_critcount use cases
with an inline which executes cpu_ccfence() before and after,
to guarantee that GCC does not try to reorder the operation around
critical memory changes.
* This fixes a race in lockmgr() and possibly a few other places
too.
Matthew Dillon [Sun, 1 Oct 2017 18:18:49 +0000 (11:18 -0700)]
kernel - Fix rare lockmgr() state transition (2)
* Fix two lock timeout cases for LK_EXCLUPGRADE and LK_UPGRADE, and
fix a bug in undo_upreq().
* A tsleep failure (such as the LK_TIMELOCK case via
vm_map_lock_read_to()) was not properly backing-out a LKC_UPREQ,
resulting in a situation where the lock becomes exclusively owned
by nobody and deadlocks against all-comers. Fix by properly
calling undo_upreq().
* Fix a bug in undo_upreq() itself. When undoing a granted UPREQ,
the lockholder must be set prior to releasing the now-granted
exclusive lock in order to avoid an assertion panic.
* While we are at it, replace a weird cmpset count,count with a
fetchadd(count, 0).
Tomohiro Kusumi [Sun, 1 Oct 2017 12:37:54 +0000 (15:37 +0300)]
sbin/hammer: Fix compile-time warning by some Linux distros
--
test_dupkey.c: In function 'main':
test_dupkey.c:54:1: warning: control reaches end of non-void function [-Wreturn-type]
}
Sascha Wildner [Sun, 1 Oct 2017 10:09:02 +0000 (12:09 +0200)]
Fix some minor issues in several manual pages.
Sascha Wildner [Sun, 1 Oct 2017 09:35:59 +0000 (11:35 +0200)]
X86_64_GENERIC: Fix indent.
Matthew Dillon [Sun, 1 Oct 2017 01:17:55 +0000 (18:17 -0700)]
kernel - Improve tsleep/wakeup queue collisions (3)
* Doh, fix variable declaration.
Matthew Dillon [Sun, 1 Oct 2017 01:11:08 +0000 (18:11 -0700)]
kernel - Improve tsleep/wakeup queue collisions (2)
* Fix SMP race. When testing ident0 against -1 or the ident value
as stored in a remote cpu's structure, ident0 must be loaded from memory
once to avoid a cross-over race.
Matthew Dillon [Sat, 30 Sep 2017 22:12:30 +0000 (15:12 -0700)]
kernel - Fix rare lockmgr() state transition
* When lockmgr() is releasing the last count on an exclusive lock
with an upgrade request pending, and the atomic op fails, the
code fails to properly retry. Fixed by properly retrying.
* This situation should not be possible to even get into, hence 'rare'.
It requires UPREQ to be set while the lock is being held exclusively,
which should never be possible because there is no shared lock holder
in that case who might attempt to upgrade.
I checked race conditions when multiple shared holders attempt
to upgrade but all that happens is that one will release and
acquire a normal exclusive lock instead.
Sascha Wildner [Sat, 30 Sep 2017 21:31:36 +0000 (23:31 +0200)]
mandoc(1): Changed OSNAME to match 5.1.
Sascha Wildner [Sat, 30 Sep 2017 21:18:41 +0000 (23:18 +0200)]
Fix some Xr punctuation issues in several manual pages.
Sascha Wildner [Sat, 30 Sep 2017 21:12:11 +0000 (23:12 +0200)]
Use standard section name 'AUTHORS' in several manual pages.
Imre Vadász [Sat, 30 Sep 2017 19:08:51 +0000 (21:08 +0200)]
Revert "Update drm/radeon to Linux 4.7.10 as much as possible..."
This caused severe issues on some modern radeon models (e.g. Kaveri APUs).
Not reverting the
62dc643ef61b347c4c2e60ad9ea68dd766741c90 commit, it's just
a 2 character diff that was conflicting with this change.
This reverts commit
a7a95252afec8bfcc34ee5b8725136b17b77043f.
Tested-By: ivadasz
Reported-By: several people on #dragonflybsd
Tomohiro Kusumi [Sat, 30 Sep 2017 11:21:25 +0000 (14:21 +0300)]
sbin/mount_hammer: Remove redundant test_volumes() on mount(2) failure
This code was originally added by
1a607e3e which added signature check
when mount(2) failed, and later modified by several commits including
1e297b34 which copied code from sbin/hammer/ondisk.c. But as mentioned
in
1e297b34, this entire checking wasn't needed (as it's in dmesg),
or it may even show the wrong reason of failure.
The correct way is to just type dmesg, and see what the kernel said,
instead of resorting to wild guess in userspace by reading volume header
*after* mount(2) failure (If you really want this it should be done
*before* mount(2)).
This originally didn't exist till 2009 and that was better.
Tomohiro Kusumi [Sat, 30 Sep 2017 11:17:32 +0000 (14:17 +0300)]
sys/vfs/hammer: Check root voume# is 0 on mount(2)
We could check this in addition to the existing conditional to
know the volume is the root volume. /sbin/hammer and /sbin/mount_hammer
do this, so why not.
If failed here, the volume which has just been inserted to the rbtree
(and other volumes already inserted) are going to be removed by
hammer_free_hmp().
Tomohiro Kusumi [Sat, 30 Sep 2017 10:12:51 +0000 (13:12 +0300)]
sbin/hammer: Add UUID string on error and blockmap,show
to make clear whether ondisk vol_fstype UUID is simply wrong or
due to byte order of the first 8 bytes (4-2-2 part).
Tomohiro Kusumi [Sat, 30 Sep 2017 09:29:07 +0000 (12:29 +0300)]
sbin/hammer: Minor cleanup
The prototype was originally brought (copied) from uuid(3).
Matthew Dillon [Sat, 30 Sep 2017 18:06:49 +0000 (11:06 -0700)]
tmpfs - Conditionalize atomic adds on mount structure
* Conditionalize tracking of the total pages allocated to avoid
the atomic op when the delta change is 0.
Suggested-by: mjg_
Sascha Wildner [Sat, 30 Sep 2017 17:45:42 +0000 (19:45 +0200)]
<sys/param.h>: Fix __DragonFly_version.
Reported-by: zrj
Sascha Wildner [Sat, 30 Sep 2017 17:29:42 +0000 (19:29 +0200)]
Update UPDATING a bit for the disabling of FFS_ROOT.
Sascha Wildner [Sat, 30 Sep 2017 14:47:04 +0000 (16:47 +0200)]
rc.conf.5: Improve moused_type description a bit more.
Justin C. Sherrill [Sat, 30 Sep 2017 00:11:33 +0000 (20:11 -0400)]
5.1 commit.
Sascha Wildner [Fri, 29 Sep 2017 19:03:36 +0000 (21:03 +0200)]
rc.conf.5: Improve wording of the moused_type variable description.
Especially, point out that the default is 'auto' and if that is
what the user wants, they need not set it explicitly in their
/etc/rc.conf.
Reported-by: htse (Harald Brinkhof)
Sepherosa Ziehau [Fri, 29 Sep 2017 06:38:35 +0000 (14:38 +0800)]
arp: Allocate context memory on owner cpu.
Sepherosa Ziehau [Fri, 29 Sep 2017 01:30:46 +0000 (09:30 +0800)]
syncache: Timer queue iteration is MPsafe; no need to use marker.
Sepherosa Ziehau [Fri, 29 Sep 2017 01:03:46 +0000 (09:03 +0800)]
syncache: Move local variables close their usage.
Sepherosa Ziehau [Fri, 29 Sep 2017 01:02:03 +0000 (09:02 +0800)]
syncache: inpcb will never be NULL.
Sepherosa Ziehau [Fri, 29 Sep 2017 00:11:18 +0000 (08:11 +0800)]
syncache: Resurrect net.inet.tcp.syncache.count
Sepherosa Ziehau [Thu, 28 Sep 2017 23:38:19 +0000 (07:38 +0800)]
syncache: Allocate syncache context on the owner cpu.
Sepherosa Ziehau [Thu, 28 Sep 2017 23:10:19 +0000 (07:10 +0800)]
syncache: Group timeout queue related fields together.
Sepherosa Ziehau [Thu, 28 Sep 2017 22:44:50 +0000 (06:44 +0800)]
syncache: Simplify timer message
Sepherosa Ziehau [Thu, 28 Sep 2017 22:15:32 +0000 (06:15 +0800)]
syncache: Remove unnecessary struct field
Sepherosa Ziehau [Thu, 28 Sep 2017 21:59:58 +0000 (05:59 +0800)]
syncache: Staticize syncache_lookup
Sepherosa Ziehau [Thu, 28 Sep 2017 21:51:34 +0000 (05:51 +0800)]
syncache: Stringent assertion.
Sepherosa Ziehau [Thu, 28 Sep 2017 19:37:56 +0000 (03:37 +0800)]
kern: Allocate sleep hash on owner cpu.
Matthew Dillon [Fri, 29 Sep 2017 00:43:20 +0000 (17:43 -0700)]
vkernel - Print mmap() failures in megabytes
* Print mmap() failures for vkd* drives in megabytes instead
of bytes.
Matthew Dillon [Fri, 29 Sep 2017 00:41:32 +0000 (17:41 -0700)]
kernel - Add poor-man's AMD TOPOEXT support
* Add a poor-man's TOPOEXT support which should properly detect
the Ryzen topology. I don't know about EPYC, though. And it
might muff the topology for older AMD cpus (also don't know).
Matthew Dillon [Fri, 29 Sep 2017 00:34:47 +0000 (17:34 -0700)]
kernel - Improve tsleep/wakeup queue collisions
* Expand the per-cpu array of TAILQs into an array of structures for
tsleep/wakeup operation.
The new structure stores up to four idents using a 4-way set-associative
algorithm (-1 in ident0 handles overflows), allowing the originating cpu
for a wakeup() to implement a second-level filter after the global array's
cpumask.
* This filter prevents nearly all possible spurious IPIs that used to occur
due to ident hash collisions, even when the hash table size is forced to
be relatively small. The code isn't the best in the world, but the IPIs
it saves probably blow away the added overhead.
Testing-by: sephe, dillon
Imre Vadász [Thu, 28 Sep 2017 22:15:08 +0000 (00:15 +0200)]
sound - Don't need to use swi_taskq to call KNOTE from the interrupt.
* Also the dsp_read_filterops and dsp_write_filterops kqueue filters can
be flagged FILTEROP_MPSAFE.
Matthew Dillon [Thu, 28 Sep 2017 19:55:19 +0000 (12:55 -0700)]
kernel - Restrict kill(-1, ...) to the reaper group as well
* When kill(-1, ...) is issued to 'all processes', restrict the list
of processes signaled to the sender's reaper group or any sub-group
of that group.
* This works around issues found when testing low maxproc limits.
At least one (and probably several) third party programs do not
properly handle errors when [v]fork() returns -1 and may try to
signal the returned 'pid', which being -1 crowbars the entire system.
* Fixes issue when a cmake running under synth hits a fork failure
and tries to signal the whole system. With this change, the cmake
winds up only crowbaring its own chroot due to synthexec's use of
the reaper feature.
* Adjust the kill.2 manual page to reflect the change.
Sascha Wildner [Thu, 28 Sep 2017 18:15:03 +0000 (20:15 +0200)]
mandoc(1): Move the config.h to the build directory.
Next mandoc upgrade will remove it on the vendor branch as well.
Sepherosa Ziehau [Thu, 28 Sep 2017 07:14:49 +0000 (15:14 +0800)]
ipfw: Add interface network filter.
This eases src/dst matching if the IP address is assigned to the interface
dynamically, e.g. by DHCP.
Sepherosa Ziehau [Thu, 28 Sep 2017 01:42:04 +0000 (09:42 +0800)]
uipc: Use sendmsg_oncpu, if possible.
This further reduces unnecessary IPIs (5500/s -> 5000/s).
Sepherosa Ziehau [Wed, 27 Sep 2017 23:20:26 +0000 (07:20 +0800)]
callout: Embed thread in per-cpu callout context.
Sepherosa Ziehau [Wed, 27 Sep 2017 23:18:37 +0000 (07:18 +0800)]
kern: Enhance wakeup hash construction to reduce hash collision.
With-input-from: dillon
Tested-by: dillon
Sascha Wildner [Thu, 28 Sep 2017 06:22:34 +0000 (08:22 +0200)]
Remove libmandoc.
Maintaining it separately, along with its manual pages and headers,
is more maintenance burden than it has real value.
Nothing but mandoc(1) needs it, so just include the source files in
the mandoc(1) build for now.
In-discussion-with: Lubos Boucek <bouceklubos@gmail.com>
Sepherosa Ziehau [Wed, 27 Sep 2017 19:29:44 +0000 (03:29 +0800)]
kern: Add read-only sysctl for sleep queue table size
Matthew Dillon [Thu, 28 Sep 2017 02:40:13 +0000 (19:40 -0700)]
kernel - Fix cpu_rotator in lwkt_alloc_thread()
* The cpu and rotator are signed. Use an unsigned modulo to ensure
that the resulting cpu is properly ranged.
Matthew Dillon [Wed, 27 Sep 2017 21:51:48 +0000 (14:51 -0700)]
ppp - Fix seg-fault on crypt failure
* Fix an issue where the program seg-faults if crypt() returns
NULL. Return 0 (failure for this routine) in case of NULL
Submitted-by: lubos
Sepherosa Ziehau [Wed, 27 Sep 2017 07:01:25 +0000 (15:01 +0800)]
callout: Allocate per-cpu callout context on the owner cpu.
Thread is not embedded in the per-cpu callout context.
Sepherosa Ziehau [Wed, 27 Sep 2017 06:47:23 +0000 (14:47 +0800)]
callout: Allocate wheel on owner cpu.
Sepherosa Ziehau [Wed, 27 Sep 2017 06:43:22 +0000 (14:43 +0800)]
Revert "callout: Allocate callout wheel/thread on the owner cpu."
This reverts commit
8def3b58c71a8b3527e2cc9aed97c1467dc0a74c.
It causes large amount of unnecessary IPIs to the last CPU during
some TCP related tests. Needs more investigation.
Sepherosa Ziehau [Wed, 27 Sep 2017 07:50:24 +0000 (15:50 +0800)]
ipfw: Add interface IP filter.
This eases src/dst matching if the IP address is assigned to the interface
dynamically, e.g. by DHCP.
Sepherosa Ziehau [Wed, 27 Sep 2017 06:20:52 +0000 (14:20 +0800)]
ipfw(8): Fix comment
Matthew Dillon [Wed, 27 Sep 2017 04:31:04 +0000 (21:31 -0700)]
kernel - Fix rare allproc scan vs p_ucred race
* This race can occur because p->p_ucred can change out from under
an allproc scan when the allproc scan is filtering based on
credentials.
* Access p->p_ucred via the per-process spinlock (p->p_spin). Also
maintain a cache of the last ucred during the loop in order to
avoid having to spin-lock every process.
* Add missing spinlock around p->p_ucred = NULL in exit1(). This
is also only applicable to races against allproc scans since
p_token is held during exit1().
Reported-by: mjg_
Matthew Dillon [Wed, 27 Sep 2017 04:28:12 +0000 (21:28 -0700)]
kernel - Fix unnecessary ucred duplication
* Fix unnecessary ucred replication. This is not a memory leak, but it
is annoying.
* Replicated ucreds can build-up in the system (up to maxvnodes) due to
to unlinked files.
* Fix by flagging unlinked files in np->n_flag and immediately recycling
the related vnode in the inactive code if it has been flagged for
removal.
Sepherosa Ziehau [Tue, 26 Sep 2017 04:46:39 +0000 (12:46 +0800)]
callout: Allocate callout wheel/thread on the owner cpu.
Sepherosa Ziehau [Tue, 26 Sep 2017 04:30:02 +0000 (12:30 +0800)]
callout: Minor style changes
Sepherosa Ziehau [Tue, 26 Sep 2017 00:49:01 +0000 (08:49 +0800)]
pktgen: Allow building w/o INVARIANTS
Sepherosa Ziehau [Mon, 25 Sep 2017 23:40:33 +0000 (07:40 +0800)]
ethernet: Restructure vlan check.
Sepherosa Ziehau [Mon, 25 Sep 2017 23:14:06 +0000 (07:14 +0800)]
ipflow: Use netisr APIs
Sepherosa Ziehau [Mon, 25 Sep 2017 22:17:38 +0000 (06:17 +0800)]
ipflow: Remove compat macro
Tomohiro Kusumi [Mon, 25 Sep 2017 20:19:48 +0000 (23:19 +0300)]
sbin/hammer: Use uuid_compare(3) instead of bcmp(3)
(missed ones from
118205ce)
Matthew Dillon [Mon, 25 Sep 2017 21:12:59 +0000 (14:12 -0700)]
kcollect - Final dbm support code
* Fix time conversion issues and memory leaks
* Code cleanup
* Documentation cleanup (from swildner)
Submitted-by: htse (Harald Brinkhof)
Sepherosa Ziehau [Mon, 25 Sep 2017 07:25:20 +0000 (15:25 +0800)]
ipflow: Utilize netisr_domsg_global
Sepherosa Ziehau [Mon, 25 Sep 2017 06:51:41 +0000 (14:51 +0800)]
ipflow: Allocate ipflow context on its owner cpu.
Sepherosa Ziehau [Mon, 25 Sep 2017 06:02:33 +0000 (14:02 +0800)]
ipflow: Use INTWAIT | NULLOK for kmalloc
Sepherosa Ziehau [Mon, 25 Sep 2017 06:01:21 +0000 (14:01 +0800)]
ipflow: No need to mark it cachealign.
ipflow is allocated on the owner cpu.
Sepherosa Ziehau [Mon, 25 Sep 2017 05:58:25 +0000 (13:58 +0800)]
ipflow: Remove reference counting, which no longer applies.
Sepherosa Ziehau [Mon, 25 Sep 2017 05:07:02 +0000 (13:07 +0800)]
ipflow: Stringent assertion.
Sepherosa Ziehau [Mon, 25 Sep 2017 05:05:31 +0000 (13:05 +0800)]
route: Minor style change.
Sepherosa Ziehau [Mon, 25 Sep 2017 04:47:22 +0000 (12:47 +0800)]
polling: Utilize netisr_domsg_global
Sepherosa Ziehau [Mon, 25 Sep 2017 04:41:37 +0000 (12:41 +0800)]
polling: No need to explicitly align io context and systimer context
Sepherosa Ziehau [Mon, 25 Sep 2017 04:34:07 +0000 (12:34 +0800)]
polling: Adjust comment
Sepherosa Ziehau [Mon, 25 Sep 2017 00:42:56 +0000 (08:42 +0800)]
polling: Don't do direct input in critical section.
Matthew Dillon [Sun, 24 Sep 2017 18:17:03 +0000 (11:17 -0700)]
kcollect - Add initial dbm support
* Fully implement the -b and -d options to allow a dbm file to
be recorded / appended, and played back.
* Still needs a little fleshing out for scaling info and
headers.
Submitted-by: htse (Harald Brinkhof)
Tomohiro Kusumi [Sun, 24 Sep 2017 15:22:28 +0000 (18:22 +0300)]
sbin/hammer: Fix strncpy(3) length
The last one is ok, but HAMMER userspace doesn't use strl variants
except for this, then just use strncpy(3) for better portability.
Sascha Wildner [Sun, 24 Sep 2017 12:39:15 +0000 (14:39 +0200)]
kernel: Remove no longer used FFS_ROOT option.
Last used in code removed in
8840cec90a57df5e7c0f84c3c3c1e9abea7f2632.
While here, remove some no longer necessary opt_ffs.h #includes.
Sascha Wildner [Sun, 24 Sep 2017 11:30:30 +0000 (13:30 +0200)]
<machine/stdint.h>: Add __suseconds_t for suseconds_t definitions.