| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2009-08-09 | Keep track of number of currently mapped and B_BUSY buffers. beck@ ok | Artur Grabowski | |
| 2009-08-09 | Switch softraid to vnodes to prevent bad things from happening when using | Marco Peereboom | |
| d_open/d_close. tested by many, ok jsing, thib, krw | |||
| 2009-08-09 | Compile OpenBSD/sgi without -traditional-cpp. From jsg@. | Joel Sing | |
| 2009-08-09 | Make dk_mmountroot use vnodes instead of d_open/d_close. This does ugly | Marco Peereboom | |
| things to softraid. ok jsing thib krw beck oga | |||
| 2009-08-09 | no point in clearing/re-initing packet header fields in a non-packet-header | Henning Brauer | |
| mbuf. ok claudio theo | |||
| 2009-08-09 | Use the ANSI/ISO token paste operator. Requested by jsg@ | Joel Sing | |
| ok miod@ jsg@ | |||
| 2009-08-09 | Use an RB tree instead of a SPLAY tree for the page headers tree. | Thordur I. Bjornsson | |
| ok beck@, dlg@ | |||
| 2009-08-09 | if extent_alloc() fails, we don't clear the iomap properly before | Owain Ainsworth | |
| returning an error. so next time we mess around, we may get annoying printfs. Fix this. ok kettenis@ | |||
| 2009-08-09 | set the mrq pointer (request) in the nfsm_reply() macro, as we can return ↵ | Thordur I. Bjornsson | |
| from it. This can cause us to follow garbage in the nfsd loop, causing two kinds of hell. problem noticed by nicm@. OK blambert@. | |||
| 2009-08-09 | Make this compile when SEA_ASSEMBLER is not defined. | Jonathan Gray | |
| 2009-08-09 | 16 bits are enough for tagsset | Henning Brauer | |
| 2009-08-09 | make mbuf tags suck a bit less, performance wise. | Henning Brauer | |
| the most common operation is checking for a particular tag to be there. in the majority of the cases it is not. introduce a "tagsset" in the mbuf packet header which has a bit for each mbuf tag type that is in the chain set, checking for its existance is now as easy and cheap as (tagsset & type) != 0. theo ok | |||
| 2009-08-09 | once again ipsec tries to be clever and plays fast, this time by | Henning Brauer | |
| recycling an mbuf tag and changing its type. just always get a new one. theo ok | |||
| 2009-08-09 | add mpath(4), a driver that steals paths to scsi devices if it | David Gwynne | |
| thinks they could be available via multiple paths. those stolen devices are then made available via mpath(4). this is the minimum amount of code to implement the stealing. it is generally broken and very brittle, so it is currently disabled. it is going in so i can work on it in the tree. | |||
| 2009-08-09 | create a m_free_unlocked which is now used by both m_freem() and m_free(). | Theo de Raadt | |
| this lets m_freem() only do one splnet/splx instead of repeating this all the way down a chain ok henning claudio dlg | |||
| 2009-08-09 | typo; brad | Miod Vallat | |
| 2009-08-09 | do not clear a field before we pool_put it into oblivion; ok henning | Theo de Raadt | |
| 2009-08-09 | protect MCLGET() from inheriting the new semantics of MCLGETI() by casting | Theo de Raadt | |
| it to void idea from damien | |||
| 2009-08-09 | MCLGETI() will now allocate a mbuf header if it is not provided, thus | Theo de Raadt | |
| reducing the amount of splnet/splx dancing required.. especially in the worst case (of m_cldrop) ok dlg kettenis damien | |||
| 2009-08-09 | Rototill system V message queues. | Bret Lambert | |
| No longer allocate a static amount of memory for messages in MD boot path; message queues, message metadata, and message data now all use dynamic memory, which means that runtime sysctls should now be trivial to implement. Since I'm going to be around all week to fix any breakage, this should probably just go in now. | |||
| 2009-08-09 | Tag packets into correct rdomain in tunwrite(). For L2 traffic this will be | Claudio Jeker | |
| done in ether_input() but L3 traffic needs to do it self. | |||
| 2009-08-09 | spelling error | Theo de Raadt | |
| 2009-08-09 | Get node and port WWN's from the Open Firmware tree on sparc64 if they are | Mark Kettenis | |
| provided. ok dlg@, krw@ | |||
| 2009-08-09 | Clear the upper part of 64 bit memory BARs, for they show up as 0xffffffff | Miod Vallat | |
| otherwise. Found the hard way by jasper@, playing with a bge card. | |||
| 2009-08-09 | Rewrite bits of the multicast handling code as it should be. | Kevin Lo | |
| The handling of the IFF_ALLMULTI flag is wrong and the bcmp based range checking shouldn't be there. From Brad | |||
| 2009-08-08 | match 5464 / 5461 IDs found in the Linux broadcom PHY driver and unknown | Christian Weisgerber | |
| Broadcom GigE PHY found in the dmesglog; from Brad | |||
| 2009-08-08 | regen | Christian Weisgerber | |
| 2009-08-08 | 5464 / 5461 IDs found in the Linux broadcom PHY driver and unknown | Christian Weisgerber | |
| Broadcom GigE PHY found in the dmesglog; from Brad | |||
| 2009-08-08 | Add support for the IC Plus IP1001 GigE PHY. From FreeBSD, via Brad. | Christian Weisgerber | |
| Tested by jasper@ with a IP1000A PHY to make sure it doesn't break existing model. | |||
| 2009-08-08 | bring comments in line with reality; from Brad | Christian Weisgerber | |
| 2009-08-08 | two things: | Bob Beck | |
| 1) fix buffer cache low water mark to allow for extremely low memory machines without dying 2) Add "show bcstats" to ddb to allow for looking at the buffer cache statistics in ddb ok art@ oga@ | |||
| 2009-08-08 | fix the page daemon to back off the buffer cache correctly even in the case | Bob Beck | |
| where we are below the inactive page target. This fixes a problem with a large buffer cache on low memory machines where the the page daemon would woken up, however the buffer cache would never be backed off because we were below the inactive page target, which could result in constant paging and basically a livelock condition. ok oga@ art@ | |||
| 2009-08-08 | add alc(4) to the i386 and amd64 RAMDISK_CD configs | Kevin Lo | |
| 2009-08-08 | if the port is fc, populate the adapters scsi_link structure with the wwpn | David Gwynne | |
| and wwnn so scsibus can use it. requested by and ok deraadt@ | |||
| 2009-08-08 | if the port is fc, populate the adapters scsi_link structure with the wwpn | David Gwynne | |
| and wwnn so scsibus can use it. requested by and ok deraadt@ | |||
| 2009-08-08 | if the adapters wwn fields are set, print them out when attaching scsibus. | David Gwynne | |
| we need this to get some clue as to which ports are which on an fc fabric. requested by and ok deraadt@ | |||
| 2009-08-08 | alc(4) is a driver for the Atheros AR8131/AR8132 ethernet chip. | Kevin Lo | |
| this driver was written by Pyun YongHyeon from FreeBSD. "go ahead" deraadt@ | |||
| 2009-08-08 | In ixgbe_acquire_swfw_sync don't return -IXGBE_ERR_SWFW_SYNC as this | Jonathan Gray | |
| works out to --16, which is nonsense. No functional change as all callers only check if the return value is or isn't equal to IXGBE_SUCCESS. | |||
| 2009-08-07 | pull some more missing; for err&errx, printf, write, bzopy&bzero | Martynas Venckus | |
| ok jsg@ | |||
| 2009-08-06 | Handle failed disk I/O for RAID6 | Jordan Hargrave | |
| RAID6 still disabled in softraid.c | |||
| 2009-08-06 | Make sure <machine/cpu.h> includes <machine/intr.h> when included with _LOCORE | Miod Vallat | |
| defined; cp0access.S relies on this. | |||
| 2009-08-06 | Work in progress support for Loongson2E/2F processors; need option CPU_LOONGSON2 | Miod Vallat | |
| in the kernel to be brought in, due to invasive differences in tlb operation. Comes with a separate cache operations file due to the cache being R5k-style with R10k-style way number encoding. | |||
| 2009-08-06 | R4k-style coprocessor 0 config register uses 3 bits wide fields to tell | Miod Vallat | |
| L1 caches sizes; fix the masking accordingly. | |||
| 2009-08-06 | Remove _InvalidateICachePage cache op, it isn't used by anything. | Miod Vallat | |
| 2009-08-06 | Only compile RM7000 performance counter support if defined(RM7K_PERFCNTR). | Miod Vallat | |
| This code needs to be cleaned up, and made more generic to work with other processors counters as well. | |||
| 2009-08-06 | By popular demand and peer pressure, check-in work in progress work to support | Miod Vallat | |
| the Yeelong Lemote mips-based netbook. Kernel bits only for now, needs polishing; most of this work done during h2k9 last month, although the porting effort started earlier this year. | |||
| 2009-08-06 | Add device id for BCM5716S, tidy whitespace. From Brad. | Stuart Henderson | |
| 2009-08-06 | reintroduce the uvm_tree commit. | Owain Ainsworth | |
| Now instead of the global object hashtable, we have a per object tree. Testing shows no performance difference and a slight code shrink. OTOH when locking is more fine grained this should be faster due to lock contention on uvm.hashlock. ok thib@, art@. | |||
| 2009-08-06 | Backout r1.274, william@ has tracked down watchdog timeouts with | Stuart Henderson | |
| his BCM5703 A2 to this commit. Original commit message was: "Set the DMA read watermark to 4 on the BCM5703 chipset in PCI-X mode. This is needed to prevent some TX timeouts. From Brad. Tested by myself on BCM5703 B0 on PCI-X 64/66". | |||
| 2009-08-05 | timeout_add -> timeout_add_msec | Bret Lambert | |
| ok krw@ | |||
 |
index : src | |
| OpenBSD base system |
| summaryrefslogtreecommitdiff |