Sepherosa Ziehau [Mon, 6 Oct 2008 14:51:10 +0000 (14:51 +0000)]
- Rearrange comment
- Reduce RX im timer from 125us to 50us
Sepherosa Ziehau [Mon, 6 Oct 2008 14:22:32 +0000 (14:22 +0000)]
Add RX interrupt moderation suport for PCI-E GigaE chips.
Interrupt moderation register position is obtained from Realtek's
BSD driver v176.
The meaning of the IM register bits is partially reverse engineered:
RX timer position and unit.
This kind of interrupt moderation does not work on PCI GigaE chips.
Sascha Wildner [Sun, 5 Oct 2008 18:26:41 +0000 (18:26 +0000)]
Fix bug: sprintf() was used where snprintf() was meant.
Sascha Wildner [Sun, 5 Oct 2008 10:45:28 +0000 (10:45 +0000)]
Nuke obsolete DEVICE_SYSCTLS option.
Sepherosa Ziehau [Sun, 5 Oct 2008 08:28:32 +0000 (08:28 +0000)]
re_freebufmem() may be re-entered, so set the mbuf tag to NULL after it is
destroyed.
Sepherosa Ziehau [Sun, 5 Oct 2008 07:57:45 +0000 (07:57 +0000)]
- Set hardware timer according to bus clock. Adjust hardware timer to 8000HZ
- For PCI-E device, increase "max read request size" from default value (512)
to 4096. With 512 TX descriptors, this change gives me additional +80-90Mbps
during netperf stream tests on an 8168C.
Sepherosa Ziehau [Sun, 5 Oct 2008 06:15:36 +0000 (06:15 +0000)]
Get bus clock, which will be used to fix broken TCTR setting (hardware timer,
interrupt moderation related)
Sepherosa Ziehau [Sun, 5 Oct 2008 05:00:58 +0000 (05:00 +0000)]
Set ifq maxlen according to number of TX descriptors
Sepherosa Ziehau [Sun, 5 Oct 2008 04:54:51 +0000 (04:54 +0000)]
Add tunable for RX/TX descriptor count
Sepherosa Ziehau [Sun, 5 Oct 2008 02:13:06 +0000 (02:13 +0000)]
Don't assume that RE_RX_DESC_CNT and RE_TX_DESC_CNT are always same
Sepherosa Ziehau [Sun, 5 Oct 2008 01:53:41 +0000 (01:53 +0000)]
Move some macros from if_rereg.h to if_revar.h; regroup them
Sepherosa Ziehau [Sun, 5 Oct 2008 01:43:09 +0000 (01:43 +0000)]
re_chain_data is never used
Sascha Wildner [Sat, 4 Oct 2008 22:38:42 +0000 (22:38 +0000)]
Whitespace adjustment.
Sascha Wildner [Sat, 4 Oct 2008 22:36:25 +0000 (22:36 +0000)]
Remove unnecessary .Pp
Sascha Wildner [Sat, 4 Oct 2008 22:09:17 +0000 (22:09 +0000)]
* Constify return type of gai_strerror() as per bwg2001-009
(see http://www.opengroup.org/platform/resolutions/bwg2001-many.html).
* Return EAI_OVERFLOW instead of EAI_MEMORY when the supplied buffer is
too short. This conforms to RFC 3493, POSIX and XPG6.
* Add a gai_strerror(3) manual page.
Taken-from: FreeBSD
Sascha Wildner [Sat, 4 Oct 2008 14:22:44 +0000 (14:22 +0000)]
Silence warning on UP build with KTR.
Sepherosa Ziehau [Sat, 4 Oct 2008 11:26:09 +0000 (11:26 +0000)]
- Add tunable (net.link.ether.inet.arp_mpsafe) to register ARP as MPSAFE netisr.
- Hold BGL on CARP in arp input path.
Sepherosa Ziehau [Sat, 4 Oct 2008 11:24:37 +0000 (11:24 +0000)]
On ethernet output path:
Hold BGL on IPX, ATALK, CARP and netgraph
Sepherosa Ziehau [Sat, 4 Oct 2008 11:21:10 +0000 (11:21 +0000)]
Recheck ifnet.if_bpf after we hold the BGL
Sepherosa Ziehau [Sat, 4 Oct 2008 10:36:21 +0000 (10:36 +0000)]
- For relative newer parts (8168B), setting MTPS (max transmit packet size)
according to MTU makes jumbo frame + TX csum offloading work. However,
for old ones (8169), setting MTPS does not have much effect.
- Reduce max jumbo frame size from 9018 to 7440 (according to DS)
- Fix MTU setting in re_ioctl
Hasso Tepper [Sat, 4 Oct 2008 09:57:14 +0000 (09:57 +0000)]
How buggy this little piece of code could be? Repair strnvis() buffersize
of 4*n+1, with termination gauranteed by the function.
Obtained-from: OpenBSD
Thomas Nikolajsen [Fri, 3 Oct 2008 21:26:28 +0000 (21:26 +0000)]
- adjust boot command description for booting from
root of boot-only file system
- improve markup
- fix exmaple of dummy s0 partition to use enough space for disklabel
Thomas Nikolajsen [Fri, 3 Oct 2008 20:09:12 +0000 (20:09 +0000)]
Start sentence on new line.
Sascha Wildner [Fri, 3 Oct 2008 19:56:11 +0000 (19:56 +0000)]
Silence remaining "'packed' attribute ignored for field of type..." warnings.
Verified-with: md5
Thomas Nikolajsen [Fri, 3 Oct 2008 18:55:57 +0000 (18:55 +0000)]
- fix description of time (cleanup): suffix is mandantory
- describe period use (cleanup)
- use `cyclefile' everywhere, not cycle file
Sepherosa Ziehau [Fri, 3 Oct 2008 14:14:10 +0000 (14:14 +0000)]
Free sysctl tree during detach
Sepherosa Ziehau [Fri, 3 Oct 2008 14:07:02 +0000 (14:07 +0000)]
Transmit csum offload does not work at all on certain hardware revision
once frame length exceeds certain threshold (different parts seems to
have different thresholds). Borrow code from ip_output to do software
csum, if transmit csum offloading is enabled and frame length exceeds
hardware's threshold.
8169, 8169S, 8169SB and 8168B are tested, while 8169S and 8169SB does not
seem to have this bug.
Hasso Tepper [Fri, 3 Oct 2008 12:30:07 +0000 (12:30 +0000)]
Don't allocate space for empty banners. Makes me able to connect various
network equipment again.
Obtained-from: OpenBSD CVS
Sepherosa Ziehau [Fri, 3 Oct 2008 11:35:25 +0000 (11:35 +0000)]
Print hardware revision during attach
Sascha Wildner [Fri, 3 Oct 2008 10:46:41 +0000 (10:46 +0000)]
ether_demux() is now ether_demux_oncpu().
Sascha Wildner [Fri, 3 Oct 2008 10:33:49 +0000 (10:33 +0000)]
Re-add some previously removed docs about devd(8) notifies.
Sascha Wildner [Fri, 3 Oct 2008 10:32:10 +0000 (10:32 +0000)]
Remove extra comma and bump .Dd
Sascha Wildner [Fri, 3 Oct 2008 10:30:43 +0000 (10:30 +0000)]
Bump .Dd
Sascha Wildner [Fri, 3 Oct 2008 10:27:42 +0000 (10:27 +0000)]
Adjust for recent devd(8) import.
Sepherosa Ziehau [Fri, 3 Oct 2008 10:12:35 +0000 (10:12 +0000)]
- Don't substract ETHER_ALIGN from the fragment length, we don't do
m_adj(ETHET_ALIGN) in re_newbuf()
- If one fragment of a multi-fragment packet recolletion fails, we
drop will consecutive fragments of this packet.
- All of the TX descs in TX ring could be used; there is no need to
reserve RE_TXDESC_SPARE TX descs
Sascha Wildner [Fri, 3 Oct 2008 09:25:18 +0000 (09:25 +0000)]
Prefix hex numbers with '0x' in debug messages.
Hasso Tepper [Fri, 3 Oct 2008 08:56:58 +0000 (08:56 +0000)]
Correctly handle Intel g33 chips and add support for g45 chips.
Obtained-from: FreeBSD
Sepherosa Ziehau [Fri, 3 Oct 2008 08:00:06 +0000 (08:00 +0000)]
Factor out re_free_rxchain()
Hasso Tepper [Fri, 3 Oct 2008 07:59:20 +0000 (07:59 +0000)]
If a neighbor solictation or neighbor advertisement isn't from the
unspecified address, make sure that the source address matches one of the
interfaces address prefixes.
CVE-2008-2476
Obtained-from: NetBSD with modifications
Sepherosa Ziehau [Fri, 3 Oct 2008 07:52:26 +0000 (07:52 +0000)]
Rework DMA stuffs' allocation/free
Sepherosa Ziehau [Fri, 3 Oct 2008 05:47:07 +0000 (05:47 +0000)]
If RX/TX ring initialization failed, then stop re(4) and return
Sepherosa Ziehau [Fri, 3 Oct 2008 05:09:18 +0000 (05:09 +0000)]
Rework re_newbuf() and re_encap()
Hasso Tepper [Fri, 3 Oct 2008 00:47:36 +0000 (00:47 +0000)]
devctl(4)/devd(8) support in acpi_thinkpad(4).
Hasso Tepper [Fri, 3 Oct 2008 00:26:21 +0000 (00:26 +0000)]
Welcome devctl(4) and devd(8).
Obtained-from: FreeBSD
Sascha Wildner [Thu, 2 Oct 2008 07:51:51 +0000 (07:51 +0000)]
Regenerate the pciconf(8) database from the following files:
Hart: Jan 22, 2008 (version 671)
Boemler: Oct 1, 2008
Mares: Sep 16, 2008
Sepherosa Ziehau [Thu, 2 Oct 2008 04:14:13 +0000 (04:14 +0000)]
- Instead of using magic number 4 define it as RE_TXDESC_SPARE
- Clear if_timer only if all TX descs are free
- Clear IFF_OACTIVE only if more than RE_TXDESC_SPARE TX descs ar free
Sascha Wildner [Wed, 1 Oct 2008 11:01:02 +0000 (11:01 +0000)]
Don't use .Fn for getcap. Reference it with .Xr instead.
Sascha Wildner [Wed, 1 Oct 2008 10:53:48 +0000 (10:53 +0000)]
Add KTR_ETHERNET.
Sepherosa Ziehau [Wed, 1 Oct 2008 09:16:18 +0000 (09:16 +0000)]
Split arprequest() into two parts, arpreq_alloc() and arpreq_send().
arprequest() simply calls these two functions sequencially.
Add arprequest_async(), which allocates the arp request using arpreq_alloc()
and then dispatch the real sending (arpreq_send()) to current CPU's netisr.
Callers of arprequest_async() do not need to worry about the ifp's serializer
state. This function also makes sure that the network output happens in
TDF_NETWORK kernel thread.
Let arp_ifinit(), arp_ifinit2() and arp_rtrequest() call arprequest_async().
Sepherosa Ziehau [Wed, 1 Oct 2008 07:29:16 +0000 (07:29 +0000)]
- Constify 'enaddr'
- Minor style change
Matthew Dillon [Tue, 30 Sep 2008 23:13:08 +0000 (23:13 +0000)]
HAMMER Utilities: Adjust 'show' defaults.
* 'hammer show' now defaults to full verboseness.
* -q may now be used to reduce verboseness.
Sascha Wildner [Tue, 30 Sep 2008 21:08:10 +0000 (21:08 +0000)]
Fix HISTORY.
Sascha Wildner [Tue, 30 Sep 2008 17:47:21 +0000 (17:47 +0000)]
Silence warnings.
Sascha Wildner [Tue, 30 Sep 2008 17:11:16 +0000 (17:11 +0000)]
Raise WARNS to 6.
Sascha Wildner [Tue, 30 Sep 2008 16:57:06 +0000 (16:57 +0000)]
Ansify (i.e., silence -Wold-style-definition) the rest of lib/
(minus contrib/). Also remove a couple of "register" keywords.
Sascha Wildner [Tue, 30 Sep 2008 13:26:17 +0000 (13:26 +0000)]
Use spaces instead of tabs like everywhere else.
Sascha Wildner [Tue, 30 Sep 2008 13:13:11 +0000 (13:13 +0000)]
Add MLINKS.
Hasso Tepper [Tue, 30 Sep 2008 12:20:29 +0000 (12:20 +0000)]
The devinfo(3) library provides userspace access to the internal device
hierarchy. The devinfo(8) utility can be used to view that information.
Ported by Sascha Wildner.
Obtained-from: FreeBSD
Sascha Wildner [Tue, 30 Sep 2008 08:28:59 +0000 (08:28 +0000)]
Remove trailing whitespace.
Sascha Wildner [Tue, 30 Sep 2008 08:28:36 +0000 (08:28 +0000)]
Use .In for include files.
Matthew Dillon [Mon, 29 Sep 2008 20:52:23 +0000 (20:52 +0000)]
Do not return an EINVAL error for certain abort and disconnect cases.
Otherwise an async close() by the other end can cause our close() to
return EINVAL.
Matthew Dillon [Mon, 29 Sep 2008 20:27:38 +0000 (20:27 +0000)]
Add support for "RealTek 8102EL PCIe 10/100baseTX". Checksum support
doesn't work yet for this card so disable hardware checksumming.
Submitted-by: "Mitja Horvat" <pinkfluid@gmail.com>
Hasso Tepper [Mon, 29 Sep 2008 06:59:45 +0000 (06:59 +0000)]
Update acpi_battery(4) related code to the latest one from FreeBSD HEAD.
Obtained-from: FreeBSD
Thomas Nikolajsen [Sun, 28 Sep 2008 21:27:56 +0000 (21:27 +0000)]
* Fix `cleanup' usage to match program
* Expand `cleanup' description
* Add note that `snapshot' is a per PFS operation
* Sync recommended path for slave PFS snapshots to program
* Add `-offset indent' to .Bd where missing
* Break too long line
Thomas Nikolajsen [Sun, 28 Sep 2008 21:19:58 +0000 (21:19 +0000)]
* Add note on HAMMER use for NFS exporting PFSs
* Add note that UFS for lower layer is assumed in example
* Improve markup
Thomas Nikolajsen [Sun, 28 Sep 2008 21:15:46 +0000 (21:15 +0000)]
Add:
* description of NFS exports, including handling of PFSs;
also remove BUGS section, which said PFSs couldn't be NFS exported.
* note that null mounts of PFSs are recommended
* note on `hammer cleanup'
* note that reblocking is needed for nohistory mounts
* description of data integrity checking from HAMMER article
* `-offset indent' to .Bd missing it
Victor Balada Diaz [Sun, 28 Sep 2008 20:58:11 +0000 (20:58 +0000)]
This file is an amd64 config file, not i386
Sascha Wildner [Sun, 28 Sep 2008 18:05:26 +0000 (18:05 +0000)]
Revert part of my previous commit which was removing too much.
Sascha Wildner [Sun, 28 Sep 2008 17:43:32 +0000 (17:43 +0000)]
Remove checks for other BSDs.
Sascha Wildner [Sun, 28 Sep 2008 17:33:35 +0000 (17:33 +0000)]
Remove Lua backend and add README.DELETED.
Peter Avalos [Sun, 28 Sep 2008 17:18:02 +0000 (17:18 +0000)]
Install a moduli(5) manual page.
Sascha Wildner [Sun, 28 Sep 2008 16:40:05 +0000 (16:40 +0000)]
Add .Lb
Sascha Wildner [Sun, 28 Sep 2008 16:33:35 +0000 (16:33 +0000)]
Add documentation for the statvfs, fstatvfs and fhstatvfs system calls.
Adapted-from: OpenBSD and NetBSD
Sascha Wildner [Sun, 28 Sep 2008 15:11:34 +0000 (15:11 +0000)]
We no longer specify block and fragment sizes using disklabel(8).
Make the installer pass them to newfs(8) instead.
Matthew Dillon [Sun, 28 Sep 2008 05:08:16 +0000 (05:08 +0000)]
Linux emulation adjustments.
* Change the special case value for the compat option to getdents,
newer versions of linux were using the value to probe availability
of the 64 bit getdents.
* Change the cookie sequencing a bit for getdents. It still isn't quite
right.
* Generate a hashed 32 bit inode number from our 64 bit inode number.
Matthew Dillon [Sun, 28 Sep 2008 05:04:22 +0000 (05:04 +0000)]
Use the new vop_stdpathconf() instead of rolling our own.
Matthew Dillon [Sun, 28 Sep 2008 04:31:50 +0000 (04:31 +0000)]
Add vop_stdpathconf and default it so filesystems do not need to declare
it.
Peter Avalos [Sun, 28 Sep 2008 03:19:46 +0000 (03:19 +0000)]
Upgrade build for OpenSSH 5.1p1.
Peter Avalos [Sat, 27 Sep 2008 22:32:45 +0000 (22:32 +0000)]
Merge from vendor branch OPENSSH:
Import OpenSSH-5.1p1.
Peter Avalos [Sat, 27 Sep 2008 22:32:45 +0000 (22:32 +0000)]
Import OpenSSH-5.1p1.
Peter Avalos [Sat, 27 Sep 2008 21:04:49 +0000 (21:04 +0000)]
Upgrade to OpenSSL 0.9.8i.
Peter Avalos [Sat, 27 Sep 2008 20:51:29 +0000 (20:51 +0000)]
Merge from vendor branch OPENSSL:
Import OpenSSL-0.9.8i.
Peter Avalos [Sat, 27 Sep 2008 20:51:29 +0000 (20:51 +0000)]
Import OpenSSL-0.9.8i.
Matthew Dillon [Sat, 27 Sep 2008 20:29:52 +0000 (20:29 +0000)]
Do not loop forever if narg becomes negative. This can happen when asked
to kdump trace output created by emulated system calls.
Sepherosa Ziehau [Sat, 27 Sep 2008 11:45:30 +0000 (11:45 +0000)]
Revoke the INTR_MPSAFE flag; nata is not MPSAFE yet.
Sepherosa Ziehau [Sat, 27 Sep 2008 11:29:47 +0000 (11:29 +0000)]
For SMP kernel
- Don't call arp_update_oncpu() again in in_arpinput()
- Pass dologging to arp_update_oncpu(), only if the current cpu is CPU0,
remove the redundant cpu==0 checks
Reviewed-by: dillon@
Sepherosa Ziehau [Fri, 26 Sep 2008 12:12:36 +0000 (12:12 +0000)]
Schedule ipfw_tick() to IPFW_CFGPORT to run, this function is too time
consuming and complex to run in callout thread.
Use MPSAFE callout after above change.
Hasso Tepper [Fri, 26 Sep 2008 08:21:22 +0000 (08:21 +0000)]
Attempt to fix the crash if accessing usb device(s) after unloading usb.ko.
Sepherosa Ziehau [Thu, 25 Sep 2008 14:08:06 +0000 (14:08 +0000)]
- Minor style and white space changes
- Break long line
Sepherosa Ziehau [Thu, 25 Sep 2008 13:30:15 +0000 (13:30 +0000)]
If not in debugger, output kernel debug information to both the console and
kernel message buffer via printf.
Obtained-from: FreeBSD
Sepherosa Ziehau [Thu, 25 Sep 2008 12:08:51 +0000 (12:08 +0000)]
Add NETISR_TO_MSGF() to convert netisr.ni_flags to lwkt_msg.ms_flags to
avoid potential tranlation bugs
Pointed-out-by: hsu@
Matthias Schmidt [Thu, 25 Sep 2008 09:09:06 +0000 (09:09 +0000)]
Remove the untrue example section of the man page. We have the -S option to
sort entries by size.
Sascha Wildner [Wed, 24 Sep 2008 19:48:40 +0000 (19:48 +0000)]
Fix function name.
Sepherosa Ziehau [Wed, 24 Sep 2008 15:06:45 +0000 (15:06 +0000)]
If the current thread is not a network thread then rejecting the packet back
into netisrX when it becomes eligible. Add comment about possible situation
that the current thread is not a network thread.
Sepherosa Ziehau [Wed, 24 Sep 2008 14:26:39 +0000 (14:26 +0000)]
Add NETISR_FLAG_NOTMPSAFE, which could be used as the last parameter to
netisr_register(), more expressive and less error-prone than 0.
Suggested-by: hsu@
Sepherosa Ziehau [Wed, 24 Sep 2008 12:07:19 +0000 (12:07 +0000)]
Mark all msgs used by polling(4) as MPSAFE ones
Sepherosa Ziehau [Wed, 24 Sep 2008 11:14:43 +0000 (11:14 +0000)]
Include necessary head file for {get,rel}_mplock() to unbreak UP kernel build
Pointed-out-by: y0netan1@
Matthew Dillon [Wed, 24 Sep 2008 01:42:50 +0000 (01:42 +0000)]
Additions to 'hammer pfs-*':
* Add 'snapshots=dir' and 'snapshots-clear' options
This allows you to specify the snapshots directory for any PFS, master
or slave. The option will override the default "snapshots"
sub-directory used by the 'hammer cleanup' directive for PFS masters.
This option is required for PFS slaves since the hammer cleanup
directive cannot use a directory in the slave PFS as a working
directory (because its a slave).
Additions to 'hammer cleanup':
* Implement the snapshot limit found the config file. e.g. if the
<fs>/snapshots/config file contains: 'snapshots 1d 60d' then
the filesystem is snapshotted once a day and snapshot softlinks over
60 days old will be deleted.
* This directive now checks the snapshots path configured in the PFS
and uses it if it is not empty. The snapshots path must be configured
for slaves.
Matthew Dillon [Wed, 24 Sep 2008 00:53:51 +0000 (00:53 +0000)]
sleep for a shorter period of time when an excessive number of inodes are
being recycled.
Matthew Dillon [Wed, 24 Sep 2008 00:53:16 +0000 (00:53 +0000)]
Rename the PFSD structure's prune_path[64] to snapshots[64].