dragonfly.git
15 years agoemx(4): Remove emx_dma_{malloc,free}() and related struct.
Sepherosa Ziehau [Thu, 5 Mar 2009 12:52:02 +0000 (20:52 +0800)]
emx(4): Remove emx_dma_{malloc,free}() and related struct.

15 years agoemx(4): Move TX/RX desc ring alloc/free into ring creation/destroy functions
Sepherosa Ziehau [Thu, 5 Mar 2009 11:49:28 +0000 (19:49 +0800)]
emx(4): Move TX/RX desc ring alloc/free into ring creation/destroy functions

15 years agoemx(4): Regroup RX/TX ring creation code
Sepherosa Ziehau [Thu, 5 Mar 2009 11:25:23 +0000 (19:25 +0800)]
emx(4): Regroup RX/TX ring creation code

15 years agoundo: don't run diff between last tid and tid_max
Simon Schubert [Fri, 6 Mar 2009 14:41:25 +0000 (15:41 +0100)]
undo: don't run diff between last tid and tid_max

Diff works on pairs of tids and not on only the first tid passed in to
the generator.  As a result, there is nothing to do for the last pair of
tids: the last tid and max_tid refer to the same version.  Avoid running
the generator in this case.

15 years agoundo: use MAX_TID for tid_max, or else HAMMER won't find the latest change
Simon Schubert [Fri, 6 Mar 2009 14:29:40 +0000 (15:29 +0100)]
undo: use MAX_TID for tid_max, or else HAMMER won't find the latest change

We should anyways use HAMMER_MAX_TID.  This also works around the bug in
<http://bugs.dragonflybsd.org/issue1307>.

15 years agoundo: for one-shot operations, pass in the last tid and not tid_max
Simon Schubert [Fri, 6 Mar 2009 14:26:46 +0000 (15:26 +0100)]
undo: for one-shot operations, pass in the last tid and not tid_max

This allows diff to print a sensible time of the last modification and
not print the start of the epoch.

15 years agocleanup: typo in comment
Simon Schubert [Wed, 4 Mar 2009 14:00:05 +0000 (15:00 +0100)]
cleanup: typo in comment

15 years agoktrdump: print ktr data using vfprintf()
Simon Schubert [Tue, 3 Mar 2009 17:23:48 +0000 (18:23 +0100)]
ktrdump: print ktr data using vfprintf()

The code previously assumed that there is a maximum of 10 arguments which
are all integer (sized).  Printing of more or differently sized arguments
seemed to work on occasion, or not.

15 years agoemx(4): Compact transmit path a little bit
Sepherosa Ziehau [Wed, 4 Mar 2009 13:31:32 +0000 (21:31 +0800)]
emx(4): Compact transmit path a little bit

- emx_buf.m_head is only set/cleared in the last emx_buf associated with
  the packet, so we don't need to keep clearing it in transmit descriptor
  setup loop.
- Used transmit descriptors do not need to be cleared in txeof and tx_collect

15 years agoem/emx(4): Remove dead code; add comment.
Sepherosa Ziehau [Wed, 4 Mar 2009 12:56:59 +0000 (20:56 +0800)]
em/emx(4): Remove dead code; add comment.

15 years agoem/emx(4): Don't use __predict_false when test m_len against EM_TXCSUM_MINHL
Sepherosa Ziehau [Wed, 4 Mar 2009 12:04:07 +0000 (20:04 +0800)]
em/emx(4): Don't use __predict_false when test m_len against EM_TXCSUM_MINHL

For 100 bytes UDP datagram written by userspace program, m_len is always
less then EM_TXCSUM_MINHL.

15 years agoem/emx(4): Fix comment
Sepherosa Ziehau [Wed, 4 Mar 2009 11:05:16 +0000 (19:05 +0800)]
em/emx(4): Fix comment

15 years agoGet rid of iwicontrol(8)
Sepherosa Ziehau [Tue, 3 Mar 2009 11:35:49 +0000 (19:35 +0800)]
Get rid of iwicontrol(8)

15 years agoUpdate iwi(4) manpage according to recent firmware upgrade.
Sepherosa Ziehau [Tue, 3 Mar 2009 10:58:03 +0000 (18:58 +0800)]
Update iwi(4) manpage according to recent firmware upgrade.

15 years agoiwi(4): Upgrade to use 3.0 firmware and use firmware(9) API to load firmware.
Sepherosa Ziehau [Tue, 3 Mar 2009 10:42:18 +0000 (18:42 +0800)]
iwi(4): Upgrade to use 3.0 firmware and use firmware(9) API to load firmware.

Submitted-by: Johannes Hofmann <johannes.hofmann@gmx.de>
15 years agoAllow the IP_MINTTL socket option to be set to zero.
Hasso Tepper [Mon, 2 Mar 2009 13:07:00 +0000 (15:07 +0200)]
Allow the IP_MINTTL socket option to be set to zero.

This disables the feature and is the default actually.

Reported-by: Nick Hilliard <nick at foobar.org>
Dragonfly-bug: <http://bugs.dragonflybsd.org/issue1304>

15 years agoMerge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly
Matthew Dillon [Mon, 2 Mar 2009 02:56:05 +0000 (18:56 -0800)]
Merge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly

15 years agodisklabel64 UFS+HAMMER boot support (was previously just HAMMER boot support)
Matthew Dillon [Mon, 2 Mar 2009 02:49:06 +0000 (18:49 -0800)]
disklabel64 UFS+HAMMER boot support (was previously just HAMMER boot support)

Create a mini-API for boot2 filesystems, split out the filesystem probe &
initialization code, and adjust boot2 to probe multiple filesystems.  While
the coding is fairly generic, only the larger boot2 area in a disklabel64
is big enough to hold a multi-filesystem boot2.  32 bit disklabels can still
only boot from UFS.

As part of this work the BTX loader offset for boot2 had to be adjusted.
boot1 used to load boot2 at 0xA000+0x4000 = 0xE000, but this left only 8KB
available before the segment would overflow in boot1's relocation code.

The BOOT2_VORIGIN was adjusted downward from 0x4000 to 0x2000, reducing
the absolute physical load address for boot2 to 0xC000 and allowing us
to load up to a 16K boot2 without overflowing the segment.

15 years agoFix checkpt's thaw failure error message.
Matthew Dillon [Sun, 1 Mar 2009 18:37:35 +0000 (10:37 -0800)]
Fix checkpt's thaw failure error message.

15 years agoem(4): Give preference to emx(4) based on PCI ids.
Sepherosa Ziehau [Sun, 1 Mar 2009 10:04:43 +0000 (18:04 +0800)]
em(4): Give preference to emx(4) based on PCI ids.

15 years agoCopy em(4) to emx(4), which supports only 8257{1,2,3} parts.
Sepherosa Ziehau [Sun, 1 Mar 2009 09:14:58 +0000 (17:14 +0800)]
Copy em(4) to emx(4), which supports only 8257{1,2,3} parts.

The reasons to create another driver for 8257{1,2,3}:
- Various old hardware bug workaround code are removed, so the
  code is more straightforward, especially on the transmit path.
- Only 8257{1,2,3} support multi RX queues.
- Only 8257{1,2} support multi TX queues (no plan for it yet).
- It could be a sandbox for me to add multi queues support, while
  em(4) always works :).

15 years agoem(4): Put back pkt_txclean KTR
Sepherosa Ziehau [Sun, 1 Mar 2009 09:35:56 +0000 (17:35 +0800)]
em(4): Put back pkt_txclean KTR

15 years agoem(4): We don't need in_detach trick.
Sepherosa Ziehau [Sun, 1 Mar 2009 09:32:24 +0000 (17:32 +0800)]
em(4): We don't need in_detach trick.

15 years agoem(4): Fix comment
Sepherosa Ziehau [Sun, 1 Mar 2009 09:31:37 +0000 (17:31 +0800)]
em(4): Fix comment

15 years agoem(4): We return 0 or errno, but not Intel e1000's error code.
Sepherosa Ziehau [Sun, 1 Mar 2009 09:30:19 +0000 (17:30 +0800)]
em(4): We return 0 or errno, but not Intel e1000's error code.

15 years agoem(4): White space
Sepherosa Ziehau [Sun, 1 Mar 2009 09:29:16 +0000 (17:29 +0800)]
em(4): White space

15 years agoSmall adjustment to committer(7): cherry-pick takes one argument.
Sascha Wildner [Sun, 1 Mar 2009 07:34:34 +0000 (08:34 +0100)]
Small adjustment to committer(7): cherry-pick takes one argument.

15 years agoAdjust checkpoint restore to use same note order as coredumps.
Matthew Dillon [Sun, 1 Mar 2009 07:26:20 +0000 (23:26 -0800)]
Adjust checkpoint restore to use same note order as coredumps.

Recent changes to the coredump code broke the checkpoint restore
code (checkpt -r) due to reordering of the ELF notes.  Adjust the
checkpoint restore code to deal with the new ordering.

Reported-by: Samuel J. Greear <sjg@evilcode.net>
15 years agoMerge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly
Matthew Dillon [Sun, 1 Mar 2009 03:11:55 +0000 (19:11 -0800)]
Merge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly

15 years agoHAMMER VFS - Fix improper cred checks for utimes()
Matthew Dillon [Sat, 28 Feb 2009 23:30:30 +0000 (15:30 -0800)]
HAMMER VFS - Fix improper cred checks for utimes()

Adjust the kern_utimes() code in the kernel to check for write permissions
prior to diving into the VFS.  UFS checks for write perms but HAMMER doesn't.
Generally speaking we want (at least for now) the kernel to do as much of
these checks as possible.

Reported-by: YONETANI Tomokazu <qhwt+dfly@les.ath.cx>
15 years agoMention commit template in committer.7.
Nicolas Thery [Sat, 28 Feb 2009 23:28:08 +0000 (00:28 +0100)]
Mention commit template in committer.7.

15 years agoMerge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly
Matthew Dillon [Sat, 28 Feb 2009 18:00:13 +0000 (10:00 -0800)]
Merge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly

15 years agoVKERNEL - Fix entry into ddb when running a SMP vkernel. Fixes stop/cont
Matthew Dillon [Sat, 28 Feb 2009 17:55:45 +0000 (09:55 -0800)]
VKERNEL - Fix entry into ddb when running a SMP vkernel.  Fixes stop/cont

The vkernel was trying to send individual LWPs a SIGSTOP, but POSIX handles
SIGSTOP differently from other signals and it was not having the desired
effect.

Instead the vkernel now sends SIGXCPU to each individual LWP and installs
a signal handler to pause the thread until the debugger wishes to wake it up
again.

Reported-by: corecode
15 years agomsdosfs: clean up reference counting
Nicolas Thery [Sat, 28 Feb 2009 17:32:49 +0000 (18:32 +0100)]
msdosfs: clean up reference counting

For consistency and robustness, always test de_refcnt with > 0 or <= 0.

Also assert that de_refcnt is > 0 when deleting file.

15 years agomsdosfs: fix deleted-but-open files handling.
Nicolas Thery [Thu, 26 Feb 2009 06:30:33 +0000 (07:30 +0100)]
msdosfs: fix deleted-but-open files handling.

When deleting a file, msdosfs keeps its denode in the denode cache until it is
reclaimed.  This causes a collision in the cache when recycling the directory
entry of a deleted but still open file for a new or renamed file.  This
collision was incorrecly handled resulting in a kernel panic (rename case) or
syscall error and corrupted in-core state (new file case).

Fix by allowing denodes pointing to the same directory entry to coexist in the
cache as long as a single one of them represents an existing file.

Reported-by: corecore@
Dragonfly-bug: <http://bugs.dragonflybsd.org/issue1286>

15 years agomsdosfs: fix bug in msfdosfs_hashins().
Nicolas Thery [Thu, 26 Feb 2009 03:29:14 +0000 (04:29 +0100)]
msdosfs: fix bug in msfdosfs_hashins().

This function returns an error if there is already a denode in the hash table:
EBUSY if the hashed denode represents a live file and EINVAL if it represents a
deleted but still opened file.

There was a typo in the function causing it to check for liveness in the denode
to insert instead of the already inserted one.  As a consequence, if N threads
were in a race in deget() to insert a new denode for the same file in the hash
table, the losers would fail with EINVAL instead of retrying.

15 years agomsdosfs: Fix error path in deget().
Nicolas Thery [Thu, 26 Feb 2009 01:48:28 +0000 (02:48 +0100)]
msdosfs: Fix error path in deget().

There was one error path where the depp output parameter was not set to NULL.

15 years agoUpdate busdma(9) manpage according to recent changes.
Sepherosa Ziehau [Sat, 28 Feb 2009 06:41:36 +0000 (14:41 +0800)]
Update busdma(9) manpage according to recent changes.

15 years agoem(4) manpage: Update according to the recent changes.
Sepherosa Ziehau [Sat, 28 Feb 2009 03:22:38 +0000 (11:22 +0800)]
em(4) manpage: Update according to the recent changes.

- Hardware vlan tagging is always on
- Add hw.em.int_tx_nsegs
- Nuke hw.em.rx_{abs_int_delay,int_delay}
- Nuke hw.em.tx_{abs_int_delay,int_delay}

15 years agoioctl(9): Add more ioctl chars plus a missing struct keyword in example.
Sascha Wildner [Fri, 27 Feb 2009 21:29:26 +0000 (22:29 +0100)]
ioctl(9): Add more ioctl chars plus a missing struct keyword in example.

Submitted-by: Stathis Kamperis <ekamperi@gmail.com>
15 years agoem(4): Reduce EM_TXDD_SAFE from 50 to 48.
Sepherosa Ziehau [Fri, 27 Feb 2009 13:36:39 +0000 (21:36 +0800)]
em(4): Reduce EM_TXDD_SAFE from 50 to 48.

With this change, the device will have at most 48 TX descriptors pending
to be write back.  48 is chosen according to the table listed on:
Intel 82571EB/82572EI Ethernet Controller Revision 6.0, Page 43,
Item 70. 82571/82572 Overwrites Transmit Descriptors in Internal Buffer.

15 years agoem(4): Don't write ITR, if the NIC is not running yet.
Sepherosa Ziehau [Fri, 27 Feb 2009 13:30:25 +0000 (21:30 +0800)]
em(4): Don't write ITR, if the NIC is not running yet.

15 years agoem(4): We don't dynamicly config txd_cmd; there is no reason to keep it anymore.
Sepherosa Ziehau [Fri, 27 Feb 2009 13:26:42 +0000 (21:26 +0800)]
em(4): We don't dynamicly config txd_cmd; there is no reason to keep it anymore.

15 years agoem(4): We don't embrace TIDV/TADV; nuke the related bits.
Sepherosa Ziehau [Fri, 27 Feb 2009 13:14:43 +0000 (21:14 +0800)]
em(4): We don't embrace TIDV/TADV; nuke the related bits.

15 years agoem(4): Don't turn on/off TX descs' IDE bit in sysctl.
Sepherosa Ziehau [Fri, 27 Feb 2009 11:26:37 +0000 (19:26 +0800)]
em(4): Don't turn on/off TX descs' IDE bit in sysctl.

We don't use TIDV/TADV to implement TX interrupt moderation, i.e.
TX desc's IDE bit should always be off.  When we set TX desc's RS
bit, we do want TX interrupt to come immediately after the TX
desc's DD bit is set by hardware.

15 years agoem(4): Adjust RDTR/RADV comment that they should not be used
Sepherosa Ziehau [Thu, 26 Feb 2009 11:58:23 +0000 (19:58 +0800)]
em(4): Adjust RDTR/RADV comment that they should not be used

15 years agoem(4): Don't configure RADV (default is 0), which is deprecated.
Sepherosa Ziehau [Thu, 26 Feb 2009 11:42:05 +0000 (19:42 +0800)]
em(4): Don't configure RADV (default is 0), which is deprecated.

- In 82573 workaround, we still need to configure RADV, since RDTR is used.
- Revoke tunable/sysctl node for RADV.

15 years agoem(4): Add tunable for the 82573 workaround, enabled by default.
Sepherosa Ziehau [Wed, 25 Feb 2009 13:35:33 +0000 (21:35 +0800)]
em(4): Add tunable for the 82573 workaround, enabled by default.

Given not all 82573 based NICs have this problem and RDTR is
deprecated, adding a tunable to disable the workaround for a bad
hardware design seems like a quite reasonable compromise ...

15 years agoem(4): Revoke tunable/sysctl node for RDTR, which is dangerous and deprecated.
Sepherosa Ziehau [Wed, 25 Feb 2009 12:05:00 +0000 (20:05 +0800)]
em(4): Revoke tunable/sysctl node for RDTR, which is dangerous and deprecated.

15 years agoem(4): Make sure that the upper 16bits of ITR is 0.
Sepherosa Ziehau [Wed, 25 Feb 2009 11:33:05 +0000 (19:33 +0800)]
em(4): Make sure that the upper 16bits of ITR is 0.

15 years agoem(4): Reduce TX interrupt rate and device's TX desc write requests
Sepherosa Ziehau [Sun, 22 Feb 2009 09:57:22 +0000 (17:57 +0800)]
em(4): Reduce TX interrupt rate and device's TX desc write requests

The RS (report status) bit in the TX desc controls whether DD bit
should be set by device (via write request) and whether TX interrupt
should be generated.  By setting RS bit in the last TX desc of
int_tx_nsegs TX descs, we greatly reduce the TX interrupt rate
(from 20000/s to 1200/s for full speed 1472bytes UDP datagrams) and
the number of device's TX desc write requests.  This also gives me
additional +10Kpps on 82573E_IAMT.  Add sysctl node for int_tx_nsegs,
its default value is 1/16 number of TX descs.  The implementation
details are commented near struct adapter's related fields.

15 years agoSync em(4) manual page with FreeBSD.
Sascha Wildner [Fri, 27 Feb 2009 13:27:08 +0000 (14:27 +0100)]
Sync em(4) manual page with FreeBSD.

15 years agoSome small fixes.
Sascha Wildner [Fri, 27 Feb 2009 07:36:44 +0000 (08:36 +0100)]
Some small fixes.

15 years agoexpr(1): Add support for -- as required by POSIX
Joe Talbott [Fri, 27 Feb 2009 00:53:15 +0000 (19:53 -0500)]
expr(1): Add support for -- as required by POSIX

Reported-By: vstemen on #dragonflybsd
15 years agoMerge branch 'master' of git://venus/dragonfly
Joe Talbott [Fri, 27 Feb 2009 00:48:16 +0000 (19:48 -0500)]
Merge branch 'master' of git://venus/dragonfly

15 years agoatacontrol(8): Fix amd64 warnings.
Sascha Wildner [Thu, 26 Feb 2009 22:45:32 +0000 (23:45 +0100)]
atacontrol(8): Fix amd64 warnings.

15 years agopppoed(8): Fix amd64 warnings.
Sascha Wildner [Thu, 26 Feb 2009 22:15:06 +0000 (23:15 +0100)]
pppoed(8): Fix amd64 warnings.

15 years agoAdd OFF_MIN and OFF_MAX to limits.h.
Sascha Wildner [Thu, 26 Feb 2009 21:08:49 +0000 (22:08 +0100)]
Add OFF_MIN and OFF_MAX to limits.h.

While here, clean up the comments in amd64's limits.h a bit.

15 years agosail(6): Fix amd64 warnings.
Sascha Wildner [Thu, 26 Feb 2009 20:51:57 +0000 (21:51 +0100)]
sail(6): Fix amd64 warnings.

The Write() function was being used for printing both numbers and strings
in an unportable way. Split it into Write() for numbers and Writestr()
for strings.

Taken-from: NetBSD

15 years agolibopie: on update, 0-pad the sequence integers to keep seed length
Simon Schubert [Thu, 26 Feb 2009 13:04:00 +0000 (14:04 +0100)]
libopie:  on update, 0-pad the sequence integers to keep seed length

OPIE requires a certain seed length and generates a default seed, using
a 0-padded random number.  Subsequently changing the password will
increment this seed.  The code missed 0-padding this increased integer,
so opiepasswd would advance the seed from e.g. "la0092" to "la93".  This
would prevent opiekey(1) from working, complaining about a too short
seed.

15 years agosyntax cleanup to unbreak code highlighting
Simon Schubert [Tue, 10 Feb 2009 18:58:23 +0000 (19:58 +0100)]
syntax cleanup to unbreak code highlighting

15 years agomtree: create usr/include/dev/misc/ppi to properly install headers
Simon Schubert [Tue, 10 Feb 2009 14:04:21 +0000 (15:04 +0100)]
mtree: create usr/include/dev/misc/ppi to properly install headers

15 years agoReturn EBUSY if we're detaching a vn with vnode refs to it.
Stathis Kamperis [Thu, 5 Feb 2009 18:51:08 +0000 (18:51 +0000)]
Return EBUSY if we're detaching a vn with vnode refs to it.

Dragonfly-bug: <http://bugs.dragonflybsd.org/issue998>

15 years agopax(1): Fix amd64 warnings.
Sascha Wildner [Thu, 26 Feb 2009 05:47:49 +0000 (06:47 +0100)]
pax(1): Fix amd64 warnings.

15 years agorcp(1): Fix amd64 warnings.
Sascha Wildner [Thu, 26 Feb 2009 05:34:09 +0000 (06:34 +0100)]
rcp(1): Fix amd64 warnings.

15 years agols(1): Fix amd64 warnings.
Sascha Wildner [Thu, 26 Feb 2009 05:22:48 +0000 (06:22 +0100)]
ls(1): Fix amd64 warnings.

15 years agodf(1): Fix amd64 warnings (type widths).
Sascha Wildner [Thu, 26 Feb 2009 04:54:04 +0000 (05:54 +0100)]
df(1): Fix amd64 warnings (type widths).

Taken-from: FreeBSD

15 years agoHAMMER Utiliites: undo can now detect all prior replacements of a file.
Matthew Dillon [Wed, 25 Feb 2009 23:59:56 +0000 (15:59 -0800)]
HAMMER Utiliites: undo can now detect all prior replacements of a file.

The undo code will now iterate the history of the parent directory and
attempt to locate all versions of the requested file even if the inode
number changes due to the file being deleted and recreated, or
renamed-over.

undo -i attempts to show inode number changes and deletions in the list.

undo -a (-d/-D) is now able to span inode number changes.

Suggested-by: corecode
15 years agoHAMMER VFS: Allow the form ".@@<snapshot>"
Matthew Dillon [Wed, 25 Feb 2009 22:27:44 +0000 (14:27 -0800)]
HAMMER VFS:  Allow the form ".@@<snapshot>"

Normally "." is processed by the kernel, but since extended snapshot
filenames are handled by the VFS trying to access a snapshot of "."
is passed through.  Handle it properly.

Note that the "..@@<snapshot>" form is not handled.

15 years agoHAMMER Utilities: Use a Red-Black tree to track HAMMER TIDs, use diff -N
Matthew Dillon [Wed, 25 Feb 2009 22:24:23 +0000 (14:24 -0800)]
HAMMER Utilities: Use a Red-Black tree to track HAMMER TIDs, use diff -N

Begin using a red-black tree to track the TIDs used to generate diff sets.

Use diff -N to deal with pre-creation/post-creation undo diffs.

Use diff -r.  However, running undo -a -d on a directory is not yet
meaningful because only the directory TIDs are used right now.

15 years agoRemove the horribly designed RB_AUGMENT.
Matthew Dillon [Wed, 25 Feb 2009 22:16:15 +0000 (14:16 -0800)]
Remove the horribly designed RB_AUGMENT.

15 years agoMerge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly
Matthew Dillon [Wed, 25 Feb 2009 18:41:16 +0000 (10:41 -0800)]
Merge branch 'master' of ssh://crater.dragonflybsd.org/repository/git/dragonfly

15 years agoHAMMER VFS: Add missing hammer_rel_volume() call in deadlock/retry case.
Matthew Dillon [Wed, 25 Feb 2009 18:39:42 +0000 (10:39 -0800)]
HAMMER VFS: Add missing hammer_rel_volume() call in deadlock/retry case.

A late collision in hammer_get_buffer() could result in a ref count leak
on a hammer_volume structure.  Fix the leak.

15 years agoHAMMER Utility: Allow -b to specify bytes per second if no suffix is supplied
Matthew Dillon [Wed, 25 Feb 2009 17:32:36 +0000 (09:32 -0800)]
HAMMER Utility: Allow -b to specify bytes per second if no suffix is supplied

15 years agoAllow fractional delay specs for iostats and bstats, set lower limit to 0.001.
Matthew Dillon [Wed, 25 Feb 2009 17:20:00 +0000 (09:20 -0800)]
Allow fractional delay specs for iostats and bstats, set lower limit to 0.001.

Suggested-by: cmpgt <cmpgt00@gmail.com>
15 years agodntpd(8): Fix amd64 warnings.
Sascha Wildner [Wed, 25 Feb 2009 14:21:48 +0000 (15:21 +0100)]
dntpd(8): Fix amd64 warnings.

15 years agopctrack(8): Fix amd64 warnings.
Sascha Wildner [Wed, 25 Feb 2009 14:21:01 +0000 (15:21 +0100)]
pctrack(8): Fix amd64 warnings.

15 years agosockstat(1): Fix amd64 warnings.
Sascha Wildner [Wed, 25 Feb 2009 14:21:25 +0000 (15:21 +0100)]
sockstat(1): Fix amd64 warnings.

15 years agorconfig(8): Fix amd64 warnings.
Sascha Wildner [Wed, 25 Feb 2009 14:20:33 +0000 (15:20 +0100)]
rconfig(8): Fix amd64 warnings.

15 years agoinit(8): Fix amd64 warnings.
Sascha Wildner [Wed, 25 Feb 2009 14:20:09 +0000 (15:20 +0100)]
init(8): Fix amd64 warnings.

15 years agodisklabel(8): Fix amd64 warnings.
Sascha Wildner [Wed, 25 Feb 2009 14:19:46 +0000 (15:19 +0100)]
disklabel(8): Fix amd64 warnings.

15 years agopax(1): Raise WARNS to 2.
Sascha Wildner [Tue, 24 Feb 2009 21:58:10 +0000 (22:58 +0100)]
pax(1): Raise WARNS to 2.

15 years agodma(8): Raise WARNS to 6.
Sascha Wildner [Tue, 24 Feb 2009 22:00:55 +0000 (23:00 +0100)]
dma(8): Raise WARNS to 6.

15 years agosystat(1): Fix 'systat -ip' support
Sepherosa Ziehau [Tue, 24 Feb 2009 11:26:54 +0000 (19:26 +0800)]
systat(1): Fix 'systat -ip' support

Based-on: related implementation in netstat(1)
Reported-by: ruse39 on EFNET #dragonflybsd
15 years agoem(4): Correct the conditions to be asserted
Sepherosa Ziehau [Sat, 21 Feb 2009 05:36:30 +0000 (13:36 +0800)]
em(4): Correct the conditions to be asserted

15 years agoem(4): Turn on/off SPEED_MODE according to the current link speed.
Sepherosa Ziehau [Fri, 20 Feb 2009 14:00:32 +0000 (22:00 +0800)]
em(4): Turn on/off SPEED_MODE according to the current link speed.

15 years agoem(4): Avoid allocating a csum offloading TX desc whenever possible.
Sepherosa Ziehau [Fri, 20 Feb 2009 11:21:53 +0000 (19:21 +0800)]
em(4): Avoid allocating a csum offloading TX desc whenever possible.

According to Intel's PCIe GbE Controllers Open Source Software
Developer's Manual Revision 1.8: a csum offloading TX desc will
prevent TX data read requests from being pipelined, thus reduce TX
performance.  The pipelining effect is not obvious when transmitting
bulk data (e.g. 1472 bytes UDP datagram), but it could be dominant
when transmitting tiny packets.  So we should avoid allocating a
csum offloading TX desc whenever possible to take advantage of the
pipelining effect.

On 82573E_IAMT,
Before this commit: ~700Kpps
After this commit:  ~990Kpps

The funny thing about this commit is:
Old driver code from Intel's FreeBSD driver 6.2.9 roughly did what
we are doing in this commit, while Intel's FreeBSD driver 6.9.6
simply follows Linux's way to flush the performance to the toilet ...

15 years agopktgen: Put -DSMP under '.ifdef SMP'
Sepherosa Ziehau [Thu, 19 Feb 2009 14:45:21 +0000 (22:45 +0800)]
pktgen: Put -DSMP under '.ifdef SMP'

15 years agoem(4): Free incomplete received packet in em_stop().
Sepherosa Ziehau [Wed, 18 Feb 2009 10:38:24 +0000 (18:38 +0800)]
em(4): Free incomplete received packet in em_stop().

15 years agoem(4): Put back the workaround and related comment for 82542 rev2
Sepherosa Ziehau [Tue, 17 Feb 2009 12:58:57 +0000 (20:58 +0800)]
em(4): Put back the workaround and related comment for 82542 rev2

15 years agoem(4): On TX path, make sure that ether header and ip.ip_hl are contiguous.
Sepherosa Ziehau [Mon, 16 Feb 2009 15:12:31 +0000 (23:12 +0800)]
em(4): On TX path, make sure that ether header and ip.ip_hl are contiguous.

This must be done mainly because if hardware TX csum offloading is enabled,
setting up context TX descriptor will need to access ip.ip_hl.

15 years agoem(4): Sync with Intel's em-6.9.6(FreeBSD)
Sepherosa Ziehau [Sun, 15 Feb 2009 11:46:46 +0000 (19:46 +0800)]
em(4): Sync with Intel's em-6.9.6(FreeBSD)

In addition to adding support for some chips (e.g. 82574L), this also gives
me the chance to rearrange and clean up if_em.[ch] :)

Noticable changes to the FreeBSD driver:
- The hardware abstraction layer is put into a seperate module (ig_hal)
- IP csum offloading is supported when hardware TX csum offloading is enabled
- mbufs on RX/TX ring are freed in em_stop(), i.e. during "ifconfig emX down"
- TX pattern is adjusted that we test number of avaiable TX descs before
  dequeuing mbuf from ifq.  We also reserve double spare TX descs for 82544
  cards on PCI-X bus, so we will not need to unload the loaded mbuf in the
  mid way due to short of TX descs; this at least makes the logic a little
  bit simpler.

15 years agoAdd git commit template
Matthias Schmidt [Mon, 23 Feb 2009 22:16:30 +0000 (23:16 +0100)]
Add git commit template

Rename the old CVS template and add it to the repo.  As git is a DSCM
you have to install the template yourself.  Just use the following
command:

git config --add commit.template /usr/src/tools/gittemplate

15 years agomount_udf(8): Raise WARNS to 6 and fix warning.
Sascha Wildner [Tue, 24 Feb 2009 03:29:25 +0000 (04:29 +0100)]
mount_udf(8): Raise WARNS to 6 and fix warning.

15 years agodhclient(8): Raise WARNS to 2 and fix a warning.
Sascha Wildner [Tue, 24 Feb 2009 02:24:28 +0000 (03:24 +0100)]
dhclient(8): Raise WARNS to 2 and fix a warning.

15 years agolibstand: Raise WARNS to 2 and fix warnings.
Sascha Wildner [Tue, 24 Feb 2009 01:58:49 +0000 (02:58 +0100)]
libstand: Raise WARNS to 2 and fix warnings.

15 years agolibpthread: Raise WARNS to 6 :)
Sascha Wildner [Tue, 24 Feb 2009 01:22:48 +0000 (02:22 +0100)]
libpthread: Raise WARNS to 6 :)

15 years agolibdevstat: Raise WARNS to 6 and fix warnings.
Sascha Wildner [Tue, 24 Feb 2009 01:14:32 +0000 (02:14 +0100)]
libdevstat: Raise WARNS to 6 and fix warnings.

15 years agolibbluetooth: Raise WARNS to 6.
Sascha Wildner [Tue, 24 Feb 2009 01:02:03 +0000 (02:02 +0100)]
libbluetooth: Raise WARNS to 6.

15 years agolibusbhid: Raise WARNS to 6.
Sascha Wildner [Tue, 24 Feb 2009 00:52:16 +0000 (01:52 +0100)]
libusbhid: Raise WARNS to 6.