| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2008-11-26 | only the pool_get() needs to be spl protected; ok claudio dlg | Theo de Raadt | |
| 2008-11-26 | Avoid network livelock. | Theo de Raadt | |
| Use a 1 tick timeout() to determine if the kernel even manages to get below softclock (from an old diff by mpf). If our timeout comes late, reduce the high water marks (to half) for all network interfaces, thus starving them of future packet allocations for their RX rings. For a few ticks longer, also block the high water marks from rising even if RX ring empty conditions would prod us to do so. Cards may start dropping some packets off the end of their smaller RX rings, but we were not able to do the work required in any case. With less interrupt time and mbuf movement, the system finds time to make progress at the network queues. Userland even gets to run. A x40 tuned to 600MHz shows no real reduction in performance. But a soekris has a working console now. ok dlg claudio, and art liked it too | |||
| 2008-11-26 | Use m_defrag instead of collapsing mbufs ourselves. | Mark Kettenis | |
| ok dlg@ | |||
| 2008-11-26 | dont have bpf.h expose the kernel ticks variable wherever it is includeing. | David Gwynne | |
| it is very confusing like this. ok deraadt@ canacar@ | |||
| 2008-11-26 | provide m_clsetlwm, an interface for an interface to raise its low | David Gwynne | |
| watermark for mbuf cluster allocations. this is necessary for things like bge which cannot cope with less than a certain number of pkts on the ring. ok deraadt@ | |||
| 2008-11-26 | Make M_DUP_PKTHDR and M_MOVE_PKTHDR a bit saver by respecting the M_EXT & | Claudio Jeker | |
| M_CLUSTER flags from the target mbuf. Still these function are only allowed on newly allocated buffers. OK dlg@ | |||
| 2008-11-26 | Stop maintaining internal queues of received scsi_xfer structures. | Kenneth R Westerback | |
| We can now just push unwanted ones back up into the SCSI layer with NO_CCB like other drivers. | |||
| 2008-11-26 | Stop maintaining internal queues of received scsi_xfer structures. | Kenneth R Westerback | |
| We can now just push unwanted ones back up into the SCSI layer with NO_CCB like other drivers. | |||
| 2008-11-26 | call pf_pkt_addr_changed() when we do encapsulate | Henning Brauer | |
| fixes v6-over-v4 gifs wrt pf chatter about state linking mismatches ok jsing claudio, tested by Ant La Porte <ant at ukbsd.org> | |||
| 2008-11-26 | Add my copyright here, too. | Marc Balmer | |
| 2008-11-26 | Change the semantics of gpio(4) devices by locking down pin | Marc Balmer | |
| configuration and device attachment/detachment to securelevel 0. GPIO pins can now only be configured at securelevel 0. Once the securelevel is raised, only pins that have been configured and set for securelevel access using the GPIOPINSET ioctl are accessible. This also adds the possibility to give GPIO pins a name. ok uwe@ | |||
| 2008-11-26 | Add some files missed in the original checkin. | Dale Rahn | |
| 2008-11-26 | Start at the port of OpenBSD to the OpenMoko hardware. Work in progress. | Dale Rahn | |
| 2008-11-26 | Add a number of driver files necessary for OpenMoko support, | Dale Rahn | |
| from NetBSD with mods | |||
| 2008-11-26 | Add a missing device. Found by Alex Brodsky <abrodsky@acs.winnipeg.ca>. | Marc Balmer | |
| ok deraadt | |||
| 2008-11-26 | Initial port of OpenBSD to the (xscale based) gumstix, work in progress. | Dale Rahn | |
| Most bits cloned from zaurus. | |||
| 2008-11-26 | Sparc64 still only has 64 virtual address bits and not 65. | Claudio Jeker | |
| OK kettenis@ | |||
| 2008-11-26 | Use bus_dmamap_load_mbuf instead of loading mbuf fragments ourselves, and | Mark Kettenis | |
| use m_defrag to linearize packets that don't fit in 16 segments. ok claudio@ | |||
| 2008-11-26 | Change pci_intr_handle_t to be like i386 where it is a struct that stores the | Mark Kettenis | |
| tag and pin. Reduces the differences between the two architectures and I need it to fix acpiprt(4)-based interrupt routing. ok toby@, jordan@ | |||
| 2008-11-26 | fix boot() function comment | Kevin Lo | |
| ok drahn@ | |||
| 2008-11-26 | rework the filling of the rx ring. this switches us to having the cluster | David Gwynne | |
| allocation limited by per ifp statistics, ie, we're not guaranteed to have mbufs in every slot on the rx ring. instead of filling the ring with 256 mbufs all the time (about 512KB of kva) when em is brought up, we give it 4. as demand grows we increase the number of mbufs allowed on the ring. i will bet most users wont go above 50ish mbufs, so we're saving them 400KB of kva. tested by many, including one on sparc64 ok claudio@ deraadt@ henning@ krw@ | |||
| 2008-11-26 | Zero the surface when we free them. stops some state problems which cause | Owain Ainsworth | |
| corruption on second X start on some machines. This driver is really quite dumb. | |||
| 2008-11-25 | Add generic sr_scsi_done function that does the spl dance | Marco Peereboom | |
| 2008-11-25 | Halt scanning by returning proper sense for illegal LUN. | Marco Peereboom | |
| 2008-11-25 | more sizeof->nitems | Damien Bergamini | |
| 2008-11-25 | use shiny new m_defrag() and nitems() instead of rolling our own. | Damien Bergamini | |
| 2008-11-25 | m_defrag() a mbuf chain defragmenter. It will collaps a mbuf chain into a | Claudio Jeker | |
| single buffer without changing the head mbuf. This is done with a lot of magic so there will be dragons. Tested and OK dlg@, kettenis@ | |||
| 2008-11-25 | we are heading quickly to a world where isp(4) will not fit, so let us | Theo de Raadt | |
| just accept the situation with a little sigh | |||
| 2008-11-25 | move some generic PCIe register flags used in wpi(4) and iwn(4) | Damien Bergamini | |
| into common pcireg.h ok deraadt@, kettenis@, dlg@ | |||
| 2008-11-25 | fixes to build; thanks ratchov@ | Todd T. Fries | |
| 2008-11-25 | dontqueue is set but never used. garbage collect it. | Kenneth R Westerback | |
| 2008-11-25 | Punctuate comment for clarity, and keep tense consistent throughout | Bret Lambert | |
| ok and improvements jmc@ | |||
| 2008-11-25 | Back out the large page pools for now. The compare function is | Artur Grabowski | |
| borked and instead of stressing to figure out how to fix it, I'll let peoples kernels to work. | |||
| 2008-11-25 | Another bunch of TRY_AGAIN_LATER -> NO_CCB when no I/O could be started. | Kenneth R Westerback | |
| "looks sane to me" marco@ | |||
| 2008-11-25 | Unbreak the tree | Owain Ainsworth | |
| *sigh* | |||
| 2008-11-25 | fix: add output mixer class | Alexandre Ratchov | |
| 2008-11-25 | set parameters to native ones; don't setup emulation for now | Alexandre Ratchov | |
| to ease debugging ok uwe | |||
| 2008-11-25 | add a shitload of bus_dmamap_sync() calls, even though they are no-ops | Damien Bergamini | |
| on i386 and amd64 (we do not implement bounce buffers) where this hardware is likely to be found. this is good programming practice. | |||
| 2008-11-25 | Don't try and enable the vblank handler if irqs are disabled. | Owain Ainsworth | |
| This is the source of the radeon issues with seizing at X startup. I didn't see this since my test box in coimbra is a pcie amd64 machine running MP. i.e. it has a slightly less shitty interrupt controller. | |||
| 2008-11-25 | backout large cluster allocators. | David Gwynne | |
| 2008-11-25 | expect if_flags to have IFF_RUNNING rather than IFF_UP before modifying | David Gwynne | |
| the per ifp cluster allocator. should prevent the hwm being raised innapropriately when a driver fills its rx ring for the first time. | |||
| 2008-11-25 | Fix dmesg ugliness caused by not printing iotdb stuff. | Mark Kettenis | |
| 2008-11-25 | put 9k frames on the jumbo ring | David Gwynne | |
| 2008-11-25 | art says he doesnt suck anymore, so enable the really big cluster | David Gwynne | |
| allocators again. | |||
| 2008-11-25 | rename zaurus_reg.h to machine_reg and rename some of the internal fields | Dale Rahn | |
| so that arm/xscale/... is not referring to zaurus specific defines. ok miod kevlo, with some suggested changes from deraadt@ | |||
| 2008-11-25 | unbreak build on sgi (thanks jasper) | Uwe Stuehler | |
| 2008-11-25 | Make sure that equal elements always compare equal. Logic error spotted | Artur Grabowski | |
| by otto@ ok otto@ | |||
| 2008-11-25 | Factor increases are not needed, +1 appears to work as well. | Theo de Raadt | |
| ok dlg | |||
| 2008-11-25 | spacing | Theo de Raadt | |
| 2008-11-25 | delay /etc/netstart until IPv6-DAD (dup-address-detection) is completed. | Markus Friedl | |
| ok fries, hshoexer, claudio | |||
 |
index : src | |
| OpenBSD base system |
| summaryrefslogtreecommitdiff |