summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Fix setfib(1) section number.brueffer2009-09-182-3/+3
| | | | | | PR: 133765 Submitted by: Konstantin Zolotukhin <erebus@gorodok.net> MFC after: 3 days
* Fix mdoc, typos, contractions.brueffer2009-09-181-17/+13
| | | | | | | | This includes: PR: 135520 Submitted by: Nobuyuki Koganemaru Patch by: gavin MFC after: 3 days
* Don't allocate new unnecessary pages when devstat_alloc() looses theattilio2009-09-181-16/+27
| | | | | | | | run for re-acuiring the lock, but recheck if new pages are allocatable from the pool and free the previously allocated ones. Tested by: pho, Giovanni Trematerra <giovanni dot trematerra at gmail dot com>
* Spell Israel correctly.ed2009-09-181-1/+1
| | | | | Submitted by: Alexey Savartsov <asavartsov gmail com> PR: bin/138580
* Call mwl_rxdma_cleanup() if there was an error setting up the RX DMA.rpaulo2009-09-181-1/+3
|
* Style fix - break too long a line in two.zec2009-09-181-1/+2
| | | | | Spotted by: bz MFC after: 3 days
* o DragonflyBSD 2.4.0 added.maxim2009-09-181-0/+2
|
* Various mdoc, spelling etc fixes.brueffer2009-09-1814-39/+38
| | | | MFC after: 3 days
* Fixed markup.ru2009-09-172-7/+9
|
* Change the default transport protocol for use by the Mount protocolrmacklem2009-09-171-1/+1
| | | | | | | | | | | from UDP to TCP, so that it is consistent with TCP for NFS, which became the default at r176198. Without this change, doing an NFS mount against a server that only supports UDP would result in an unusable mount point if a transport protocol option wasn't specified for the mount. Approved by: kib (mentor) MFC after: 3 days
* Add a knob to show 'Starting foo:' messages when faststart is used,dougb2009-09-173-2/+16
| | | | such as at boot time.
* Fix the style of the previous commit.rdivacky2009-09-172-2/+4
| | | | Approved by: ed (mentor, implicit)
* Make these argument/variable unsigned as the defines for them don't fitrdivacky2009-09-172-4/+4
| | | | | | | into signed 32bit integer. Approved by: ed (mentor, implicit) Approved by: sson
* Purge file system namecache when receiving incremental stream and rolling backpjd2009-09-171-0/+3
| | | | | | to it. MFC after: 3 days
* Support for VNET in SCTP (hopefully)rrs2009-09-1710-51/+44
|
* Purge namecache for the file system being rolled back, so it doesn't point atpjd2009-09-171-0/+3
| | | | | | | | invalid vnodes after the rollback resulting in EIO errors when trying to access files which are in the namecache. Reported by: des MFC after: 3 days
* V_irtualize the lltables list, making ARP and ND reasonablyzec2009-09-171-7/+19
| | | | | | | | usable again with options VIMAGE kernels. Submitted by: bz (the original version, probably identical to this one) Reviewed by: many @ DevSummit Cambridge MFC after: 3 days
* Make libc.a provide __stack_chk_fail_local weak alias. This iskan2009-09-171-0/+4
| | | | | | needed to satisfy static libraries that are compiled with -fpic and linked into static binary afterwards. Several libraries in gcc are examples of such static libs.
* Correct a sysctl name.brueffer2009-09-171-2/+2
| | | | | | PR: 137689 Submitted by: Thomas Mueller <tmueller@sysgo.com> MFC after: 3 days
* Fix an xref.brueffer2009-09-171-1/+1
| | | | | | PR: 138833 Submitted by: Alex Keda <admin@lissyara.su> MFC after: 3 days
* Fix the example, -w is the right switch for write failure probability.brueffer2009-09-171-3/+3
| | | | | | | PR: 136219 Submitted by: Kouki Hashimoto <hsmtkk@gmail.com> Patch by: gavin MFC after: 3 days
* Allocate space for the group array in a static credential used inbrooks2009-09-171-0/+2
| | | | | | | | | the quota code. One case was correctly handled in r194498, but this one was missed. PR: kern/138657 Tested by: PR submitter MFC after: 3 days
* Sync driver with Yahoo:scottl2009-09-163-74/+75
| | | | | | | - Implement MSI support (MSIX support was already there) - Use a table to drive MSI/MSIX exceptions - Pre-calculate the command address instead of wasting cycles doing the calculation on every i/o.
* Fix locking around copyout() operations.scottl2009-09-161-3/+9
|
* Make MSI and PERFORMANT interrupts work correctly. Only require the minimumscottl2009-09-162-4/+13
| | | | | | | number of MSIX interrupts that are needed, and don't strictly check for 4. Enable enough interrupt mask bits so that the controller will generate interrupts in PERFORMANT mode. This fixes the hang-on-boot issues that people were seeing with newer controllers.
* Increase CISS_MAX_PHYSTGT to 256 so that it matches what the controller mightscottl2009-09-161-1/+1
| | | | | give us. Without this, certain data structures get sized incorrectly, leading to a panic on certain cards that want to use high-value target numbers.
* The buffer returned by fgenln is not a "C" string and might not be NULsepotvin2009-09-162-1/+3
| | | | | | | terminated. Make sure that it is before using it. Reviewed by: marck@ MFC after: 3 days
* Fix a bug reported by Daniel Mentz:tuexen2009-09-161-2/+7
| | | | | | | | | When authenticating DATA chunks some DATA chunks might get stuck when the MTU gets decreased via an ICMP message. Approved by: rrs (mentor) MFC after: immediately
* When checking traffic endpoint's adresses families in key_spdadd(),vanhu2009-09-161-12/+2
| | | | | | | | | | compare them together instead of comparing each one with respective tunnel endpoint. PR: kern/138439 Submitted by: aurelien.ansel@netasq.com Obtained from: NETASQ MFC after: 1 m
* Remove trailing spaces.edwin2009-09-161-41/+41
|
* Extend the keyboard character size to 24 bits.ed2009-09-161-11/+17
| | | | | | | | | | | Because we use an int to store keyboard chacacters and their flags, we can easily store the flags in the top byte instead of the second byte. This means it's a lot easier to make Unicode work. The only change that still needs to be made, is that keyent_t's map is extended to u_int. Obtained from: //depot/projects/newcons/sys/sys/kbio.h
* Fix an off-by-one error in the marking of the O_CH operatordds2009-09-161-1/+1
| | | | | | | following an OOR2 operator. PR: 130504 MFC after: 2 weeks
* Add a couple of debugging statements.dds2009-09-161-0/+3
|
* Add the ability to see TCP timers via netstat -x. This can be a usefulsilby2009-09-166-8/+58
| | | | | | | | | feature when you have a seemingly stuck socket and want to figure out why it has not been closed yet. No plans to MFC this, as it changes the netstat sysctl ABI. Reviewed by: andre, rwatson, Eric Van Gyzen
* Add EV_RECEIPT to kevents.sson2009-09-163-2/+11
| | | | | | | | EV_RECEIPT is useful to disambiguating error conditions when multiple events structures are passed to kevent(2). The error code is returned in the data field and EV_ERROR is set. Approved by: rwatson (co-mentor)
* Add the EV_DISPATCH flag to kevents.sson2009-09-163-2/+11
| | | | | | | | When the EV_DISPATCH flag is used the event source will be disabled immediately after the delivery of an event. This is similar to the EV_ONESHOT flag but it doesn't delete the event. Approved by: rwatson (co-mentor)
* Add EVFILT_USER to kevents.sson2009-09-163-2/+159
| | | | | | | | | Add user events support to kernel events which are not associated with any kernel mechanism but are triggered by user level code. This is useful for adding user level events to an event handler that may also be monitoring kernel events. Approved by: rwatson (co-mentor)
* Add optional touch event filter hooks to kevents.sson2009-09-162-37/+68
| | | | | | | | The touch event filter is called when a kernel event data is possibly updated. There are two hook points. First, during a kevent() system call. Second, when an event has been triggered. Approved by: rwatson (co-mentor)
* -Put the optimized soreceive_stream() under a compile time option calledandre2009-09-154-6/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | TCP_SORECEIVE_STREAM for the time being. Requested by: brooks Once compiled in make it easily switchable for testers by using a tuneable net.inet.tcp.soreceive_stream and a corresponding read-only sysctl to report the current state. Suggested by: rwatson MFC after: 2 days -This line, and those below, will be ignored-- > Description of fields to fill in above: 76 columns --| > PR: If a GNATS PR is affected by the change. > Submitted by: If someone else sent in the change. > Reviewed by: If someone else reviewed your modification. > Approved by: If you needed approval for this commit. > Obtained from: If the change is from a third party. > MFC after: N [day[s]|week[s]|month[s]]. Request a reminder email. > Security: Vulnerability reference (one per line) or description. > Empty fields above will be automatically removed. M sys/conf/options M sys/kern/uipc_socket.c M sys/netinet/tcp_subr.c M sys/netinet/tcp_usrreq.c
* Reverting the previous change for now. Some users reports the patchqingli2009-09-151-0/+4
| | | | | | | | fixes their issues but one reports a failure in NFS ROOT. Revert the change for now pending further investigation. Reviewed by: bz MFC after: immediately
* Add two test cases from PR 130504.dds2009-09-151-0/+3
| | | | | | | | | | An additional one coming from http://www.research.att.com/~gsf/testregex/ was not added; at some point the entire AT&T regression test harness should be imported here. But that would also mean commitment to fix the uncovered errors. PR: 130504 Submitted by: Chris Kuklewicz
* Self pointing routes are installed for configured interface addressesqingli2009-09-155-76/+67
| | | | | | | | | | and address aliases. After an interface is brought down and brought back up again, those self pointing routes disappeared. This patch ensures after an interface is brought back up, the loopback routes are reinstalled properly. Reviewed by: bz MFC after: immediately
* This patch enables the node to respond to ARP requests forqingli2009-09-151-46/+54
| | | | | | | configured proxy ARP entries. Reviewed by: bz MFC after: immediately
* Use explicit int values for the device states in order to allow,attilio2009-09-152-8/+8
| | | | | | | | if necessary, in the future, adds of new states without breaking ABI between revisions. Proposed by: kib Approved by: imp
* Fix sched_switch_migrate():attilio2009-09-151-11/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - In 8.x and above the run-queue locks are nomore shared even in the HTT case, so remove the special case. - The deadlock explained in the removed comment here is still possible even with different locks, with the contribution of tdq_lock_pair(). An explanation is here: (hypotesis: a thread needs to migrate on another CPU, thread1 is doing sched_switch_migrate() and thread2 is the one handling the sched_switch() request or in other words, thread1 is the thread that needs to migrate and thread2 is a thread that is going to be preempted, most likely an idle thread. Also, 'old' is referred to the context (in terms of run-queue and CPU) thread1 is leaving and 'new' is referred to the context thread1 is going into. Finally, thread3 is doing tdq_idletd() or sched_balance() and definitively doing tdq_lock_pair()) * thread1 blocks its td_lock. Now td_lock is 'blocked' * thread1 drops its old runqueue lock * thread1 acquires the new runqueue lock * thread1 adds itself to the new runqueue and sends an IPI_PREEMPT through tdq_notify() to the new CPU * thread1 drops the new lock * thread3, scanning the runqueues, locks the old lock * thread2 received the IPI_PREEMPT and does thread_lock() with td_lock pointing to the new runqueue * thread3 wants to acquire the new runqueue lock, but it can't because it is held by thread2 so it spins * thread1 wants to acquire old lock, but as long as it is held by thread3 it can't * thread2 going further, at some point wants to switchin in thread1, but it will wait forever because thread1->td_lock is in blocked state This deadlock has been manifested mostly on 7.x and reported several time on mailing lists under the voice 'spinlock held too long'. Many thanks to des@ for having worked hard on producing suitable textdumps and Jeff for help on the comment wording. Reviewed by: jeff Reported by: des, others Tested by: des, Giovanni Trematerra <giovanni dot trematerra at gmail dot com> (STABLE_7 based version)
* Forced unmounts work just fine in my tests under heavy load. There mightpjd2009-09-151-5/+0
| | | | still be a problem, but it isn't worth a warning.
* We believe ZFS is ready for production use. Remove a warning about it beingpjd2009-09-151-2/+0
| | | | experimental. :)
* Accomodate old style XPT_IMMED_NOTIFY and XPT_NOTIFY_ACK so thatmjacob2009-09-152-27/+43
| | | | | | | | | we at least don't panic. We don't really support dual role mode (INITIATOR/TARGET) any more. We should but it's broken and will take a fair amount of effort to fix and correctly manage both initiator and target roles sharing the port database. So, for now, disallow it.
* Simply remove the code instead of using "#if 0".qingli2009-09-151-6/+0
| | | | Pointed out by sam
* The bootp code installs an interface address and the nfs clientqingli2009-09-152-0/+15
| | | | | | | | | | module tries to install the same address again. This extra code is removed, which was discovered by the removal of a call to in_ifscrub() in r196714. This call to in_ifscrub is put back here because the SIOCAIFADDR command can be used to change the prefix length of an existing alias. Reviewed by: kmacy
OpenPOWER on IntegriCloud