summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Add workaround to overcome hardware limitation which allows only ayongari2009-12-031-0/+37
| | | | | | | | | | | | | | | | | | | | | | | single outstanding DMA read operation. Most controllers targeted to client with PCIe bus interface(e.g. BCM5761) may have this limitation. All controllers for servers does not have this limitation. Collapsing mbuf chains to reduce number of memory reads before transmitting was most effective way to workaround this. I got about 940Mbps from 850Mbps with mbuf collapsing on BCM5761. However it takes a lot of CPU cycles to collapse mbuf chains so add tunable to control the number of allowed TX buffers before collapsing. The default value is 0 which effectively disables the forced collapsing. For most cases 2 would yield best performance(about 930Mbps) without much sacrificing CPU cycles. Note the collapsing is only activated when the controller is on PCIe bus and the frame does not need TSO operation. TSO does not seem to suffer from the hardware limitation because the payload size is much bigger than normal IP datagram. Thanks to davidch@ who told me the limitation of client controllers and actually gave possible workarounds to mitigate the limitation. Reviewed by: davidch, marius
* Add uhci/ehci controller ids.thompsa2009-12-032-0/+16
| | | | Submitted by: mitya_cabletv.dp.ua
* Change 'load' balancing mode algorithm:mav2009-12-032-30/+26
| | | | | | | | | | | | | - Instead of measuring last request execution time for each drive and choosing one with smallest time, use averaged number of requests, running on each drive. This information is more accurate and timely. It allows to distribute load between drives in more even and predictable way. - For each drive track offset of the last submitted request. If new request offset matches previous one or close for some drive, prefer that drive. It allows to significantly speedup simultaneous sequential reads. PR: kern/113885 Reviewed by: sobomax
* Repair breakage to last-minute API change.ed2009-12-031-4/+2
| | | | | | | I changed ulog_log{in,out} to return a void, but forgot to change ulog-helper as well. Reported by: stefanf
* Properly return an error reply if an NFS remove or link operation fails.jhb2009-12-031-4/+3
| | | | | | | | | | | | Previously the failing operation would allocate an mbuf and construct an error reply, but because the function did not return 0, the NFS server assumed it had failed to generate a reply and would leak the reply mbuf as well as not sending the reply to the NFS client. PR: kern/140853 Submitted by: Ted Faber faber at isi edu (remove) Reviewed by: rmacklem (remove) MFC after: 1 week
* The first argument of dcbz interprets r0 as a literal zero, not the second.nwhitehorn2009-12-031-1/+1
| | | | | | This worked before by accident. MFC after: 1 week
* Remove wrong assertion. Debugee is allowed to lose a signal.kib2009-12-031-3/+2
| | | | | Reported and tested by: jh MFC after: 2 weeks
* Yet another cosmetic fix.trasz2009-12-031-3/+3
|
* Cosmetical fixes.trasz2009-12-031-11/+11
|
* Cosmetical fixes.trasz2009-12-031-23/+21
|
* - Update the Spanish NLS cataloggabor2009-12-031-5/+51
| | | | | | | | | | | Reviewed by: carvay, the.infamous.paul@gmail.com, Joan Picanyol i Puig <lists-freebsd-es@biaix.org>, Ing . Marcos Luis Ortiz Valmaseda <mlortiz@uci.cu>, eskanete@gmail.com, Jose M Rodriguez <josemi@freebsd.jazztel.es>, Guillermo Hernandez <guillermo@QuerySoft.es>, dani.doni@gmail.com
* Description of steps required to setup NFSv4 server is in nfsv4(4);trasz2009-12-031-1/+2
| | | | | add reference to exports(5), since that's the obvious starting point for searching for this.
* Remove unused code.trasz2009-12-031-36/+0
|
* Add manpages for ams(4), akbd(4), adb(4), and cuda(4), which describenwhitehorn2009-12-036-2/+319
| | | | | | various drivers for Apple Desktop Bus controllers and peripherals. MFC after: 3 days
* Remove unneeded ifdefs.trasz2009-12-037-252/+8
| | | | Reviewed by: rmacklem
* Connect unzip to the build.rdivacky2009-12-031-0/+1
| | | | | | Approved by: ed (mentor) Approved by: des (unzip author) Tested by: exp ports build (miwi)
* Use USER_PROCESS instead of LOGIN_PROCESS.ed2009-12-034-7/+7
| | | | | | POSIX isn't clear about how the fields should be used, but according to utmpx(5) on Linux, LOGIN_PROCESS refers to a TTY that's still running a getty.
* Port users(1) to libulog.ed2009-12-032-22/+27
| | | | | | Instead of digging through the utmp database by hand, use proper API calls to do so. Instead of parsing entries with a non-empty ut_user, we now look at LOGIN_PROCESS entries.
* Also implement ut_type.ed2009-12-033-0/+52
| | | | | I thought we couldn't emulate this field, but we can derive this field by looking at special values for ut_host, ut_line and ut_name.
* mca: small enhancements related to cpu quirksavg2009-12-032-16/+44
| | | | | | | | | | | | - use utility macros for CPU family/model checking - limit Intel P6 quirk to pre-Nehalem models (taken from OpenSolaris) - add AMD GartTblWkEn quirk for families 0Fh and 10h; I haven't experienced any problems without the quirk but both Linux and OpenSolaris do this - slightly re-arrange quirk code to provide for the future generalization and separation of vendor-specific quirk functions Reviewed by: jhb MFC after: 1 week
* Fix a problem with high CPU consumption (up to 30%) by bsnmpd on a loaded ↵syrinx2009-12-035-3/+77
| | | | | | | | | | | | | system. Instead of constantly calling the mibII_idle function when the server is not busy call the function only once every 10 seconds to avoid bsnmpd constantly doing gettimeofday syscalls. Make the idle polling interval confugurable via begemotIfDataPoll. Reported and tested by: misho (at) aitbg (dot) com Oked by: harti MFC after: 1 week
* Add a new library: libulog.ed2009-12-0315-2/+790
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | One of the things I really want to do, is to get rid of the limitations of our current utmp(5) mechanism: - It only allows 8 byte TTY device names. - The hostname only allows 16 bytes of storage. I'm not a big fan of <utmpx.h>, but I think we should at least try to add parts of it. Unfortunately we cannot implement <utmpx.h>, because we miss various fields, such as ut_id, ut_pid, etc. The API provided by libulog shares some similarities with <utmpx.h>, so it shouldn't be too hard to port these applications eventually. In most simple cases, it should just be a matter of removing the ulog_ prefix everywhere. As a bonus, it also implements a function called ulog_login_pseudo(), which allows unprivileged applications to write log entries, provided they have a valid file descriptor to a pseudo-terminal master device. libulog will allow a smoother transition to a new file format by adding a library interface to deal with utmp/wtmp/lastlog files. I initially thought about adding the functionality to libutil, but because I'm not planning on keeping this library around forever, we'd better keep it separated. Next items on the todo list: 1. Port applications in the base system (and ports) to libulog, instead of letting them use <utmp.h>. 2. Remove <utmp.h>, implement <utmpx.h> and reimplement this library on top. 3. Port as many applications as possible back to <utmpx.h>.
* The fd_mask type is an unsigned long, not an int, so treat the mask as ajhb2009-12-031-2/+2
| | | | | | | | | | long instead of an int when examining the results of select() to look for RPC requests. Previously this routine would ignore RPC requests to sockets whose file descriptor mod 64 was greater than 31 on a 64-bit platform. PR: amd64/141130 Submitted by: liujb of array networks MFC after: 3 days
* Use a better check for a valid kernel stack address when capturingjkoshy2009-12-031-2/+3
| | | | | | | kernel call chains. Submitted by: Mark Unangst <mju at panasas.com> Tested by: fabient
* preparation work to replace the monster switch in ipfw_chk() withluigi2009-12-031-137/+203
| | | | | | | | | | | table of functions. This commit (which is heavily based on work done by Marta Carbone in this year's GSOC project), removes the goto's and explicit return from the inner switch(), so we will have a easier time when putting the blocks into individual functions. MFC after: 3 weeks
* Add change that was somehow missed in r192586. It could manifest bytrasz2009-12-031-2/+3
| | | | | incorrectly returning EINVAL from acl_valid(3) for applications linked against pre-8.0 libc.
* use qsort_r instead of heapsort;luigi2009-12-031-4/+4
| | | | | | staticize two functions. MFC after: 3 days
* Teach an IPv6 to the debug prints.ume2009-12-031-14/+62
|
* Disable SSL renegotiation in order to protect against a seriouscperciva2009-12-035-6/+14
| | | | | | | | | | | | | | | protocol flaw. [09:15] Correctly handle failures from unsetenv resulting from a corrupt environment in rtld-elf. [09:16] Fix permissions in freebsd-update in order to prevent leakage of sensitive files. [09:17] Approved by: so (cperciva) Security: FreeBSD-SA-09:15.ssl Security: FreeBSD-SA-09:16.rtld Security: FreeBSD-SA-09:17.freebsd-udpate
* ichsmb: try attaching only to intel hardware in the default caseavg2009-12-031-2/+4
| | | | | | | | | | Ideally we should attempt attaching only to known supported devices. But I am not sure that we have all supported PCI IDs already listed, and I am too young to die, err, I don't want to take the heat from causing a trouble to someone. MFC after: 1 week X-ToDo: drop the default case
* ichsmb: add pci ids for some newer supported hardwareavg2009-12-031-0/+12
| | | | | Submitted by: Dmitry S. Luhtionov <mitya@cabletv.dp.ua> MFC after: 5 days
* Make sure bus space accesses use unorder memory loads and stores.marcel2009-12-034-80/+148
| | | | | | | | | | | | Memory accesses are posted in program order by virtue of the uncacheable memory attribute. Since GCC, by default, adds acquire and release semantics to volatile memory loads and stores, we need to use inline assembly to guarantee it. With inline assembly, we don't need volatile pointers anymore. Itanium does not support semaphore instructions to uncacheable memory.
* Fix cut'n paste on the AR9280 entry.thompsa2009-12-022-2/+2
| | | | Submitted by: pluknet
* Include <sys/sysctl.h>, to get the declarations of ostype andmarcel2009-12-021-2/+1
| | | | osrelease. Remove the duplicate declarations from this file.
* Add missing parameter description.trasz2009-12-021-1/+3
|
* Don't use ap->a_td->td_ucred when we were passed ap->a_cred.trasz2009-12-021-1/+1
|
* - initialize src_ip in the main loop to prevent a compiler warningluigi2009-12-021-5/+8
| | | | | | | | | (gcc 4.x under linux, not sure how real is the complaint). - rename a macro argument to prevent name clashes. - add the macro name on a couple of #endif - add a blank line for readability. MFC after: 3 days
* Bump __FreeBSD_version for sigpause(3) addition [1] andkib2009-12-021-1/+1
| | | | | | PIE support in csu. Requested by: fluffy [1]
* Properly support -fPIE by linking PIE binaries with specially-builtkib2009-12-0210-39/+97
| | | | | | | | | | | | | | Scrt1.o instead of crt1.o, since the later is built as non-PIC. Separate i386-elf crt1.c into the pure assembler part and C code, supplying all data extracted by assembler stub as explicit parameters [1]. Hide and localize _start1 symbol used as an interface between asm and C code. In collaboration with: kan Inspired by: PR i386/127387 [1] Prodded and tested by: rdivacky [1] MFC after: 3 weeks
* ndis_scan_results() can sleep if the scan results are not ready whenjhb2009-12-021-9/+5
| | | | | | | | | ndis_scan() is called. However, ndis_scan() is invoked from softclock() and cannot sleep. Move ndis_scan_results() to the ndis' driver's scan_end hook instead. Submitted by: Paul B Mahol onemda of gmail MFC after: 1 week
* Fix several cases where the periph lock was held over malloc.scottl2009-12-021-54/+24
| | | | Submitted by: Jaakko Heinonen
* Make <libutil.h> work when included by itself.ed2009-12-021-0/+28
| | | | | | | There are several reasons why it didn't work: - It was missing <sys/cdefs.h> for __BEGIN_DECLS. - It uses various primitive types that were not declared.
* Dispatch sockopt calls to ipfw and dummynetluigi2009-12-021-0/+4
| | | | | | | | using the new option numbers, IP_FW3 and IP_DUMMYNET3. Right now the modules return an error if called with those arguments so there is no danger of unwanted behaviour. MFC after: 3 days
* mca: improve status checking, recording and reportingavg2009-12-024-98/+126
| | | | | | | | | | - directly print mca information in case we fail to allocate memory for a record - include bank number into mca record - print raw mca status value for extended information Reviewed by: jhb MFC after: 10 days
* small changes for portability and diff reduction wrt/ FreeBSD 7.luigi2009-12-021-15/+38
| | | | | | | | | | | | | | | | | | | No functional differences. - use the div64() macro to wrap 64 bit divisions (which almost always are 64 / 32 bits) so they are easier to handle with compilers or OS that do not have native support for 64bit divisions; - use a local variable for p_numbytes even if not strictly necessary on HEAD, as it reduces diffs with FreeBSD7 - in dummynet_send() check that a tag is present before dereferencing the pointer. - add a couple of blank lines for readability near the end of a function MFC after: 3 days
* Unify rc.firewall and rc.firewall6, and obsolete rc.firewall6ume2009-12-028-365/+178
| | | | | | | and rc.d/ip6fw. Reviewed by: dougb, jhb MFC after: 1 month
* Teach an IPv6 to send_pkt() and ipfw_tick().ume2009-12-021-112/+166
| | | | | | | | It fixes the issue which keep-alive doesn't work for an IPv6. PR: kern/117234 Submitted by: mlaier, Joost Bekkers <joost__at__jodocus.org> MFC after: 1 month
* Until this moment carp(4) used a strange logging priority. It used debugglebius2009-12-021-16/+16
| | | | | | | | | priority for such important information as MASTER/BACKUP state change, and used a normal logging priority for such innocent messages as receiving short packet (which is a normal VRRP packet between some other routers) or receving a CARP packet on non-carp interface (someone else running CARP). This commit shifts message logging priorities to a more sane default.
* Add new sockopt names for ipfw and dummynet.luigi2009-12-021-0/+8
| | | | | | | | This commit is just grabbing entries for the new names that will be used in the future, so you don't need to rebuild anything now. MFC after: 3 days
* change the type of the opcode from enum *:8 to u_int8_tluigi2009-12-021-1/+1
| | | | | | | | | | so the size and alignment of the ipfw_insn is not compiler dependent. No changes in the code generated by gcc. There was only one instance of this kind in our entire source tree, so i suspect the old definition was a poor choice (which i made). MFC after: 3 days
OpenPOWER on IntegriCloud