Maxim Sobolev [Tue, 18 Dec 2007 01:50:49 +0000 (01:50 +0000)]
Fix logical bug in the bzip2 reading code, which results in bogus EIO
returned on a perfectly valid bzip2 stream whose decompressed size
is multiple of read-ahead buffer size. Reproduce the problem is easy:
create some power-of-two sized file (truncate -s 1m file will do),
bzip2 it and try to load it as md_image from loader. See how it fails.
The bug doesn't affect gzip code (which most of bzip2-reading code was
copied from) probably due to the fact that libgzip doesn't report
Z_STREAM_END with the last block, but requires extra call to inflate()
to retrieve it and has some extra data in the input stream at that time.
However, apply similar fix to gzipfs.c just in the case the API will
change in the future to do what bzip2 code does.
Add some ifdef'ed code to enable testing bzipfs.c from witin normal
FreeBSD environment as opposed to the restricted loader one, so that
one can use gdb and whatnot.
Sponsored by: Sippy Software, Inc., http://www.sippysoft.com/
MFC in: 7 days
David Schultz [Tue, 18 Dec 2007 01:15:20 +0000 (01:15 +0000)]
Remove z_abs(). The z_*() functions were in libf77, and for some reason
someone thought it would be a good idea to copy z_abs() to libm in 1994.
However, it's never been declared or documented anywhere, and I'm
reasonably confident that nobody uses it.
Ken Smith [Mon, 17 Dec 2007 23:22:58 +0000 (23:22 +0000)]
A few more adjustments needed because of changes in xorg. Just installing
xorg-server doesn't include any video drivers so install xorg-drivers as
well. And if font-alias isn't installed the X server won't start,
complaining it can't find the font "fixed".
Insta-MFC coming, this was tested with a RELENG_6_3 release build and
the necessary packages as part of the first round of testing for 6.3-RC2.
Bruce Evans [Mon, 17 Dec 2007 18:12:06 +0000 (18:12 +0000)]
Translate from the i386 so that this compiles and runs.
I hope that this and the i386 version of it will not be needed, but
this is currently about 16 cycles or 36% faster than the C version,
and the i386 version is about 8 cycles or 19% faster than the C
version, due to poor optimization of the C version.
Robert Watson [Mon, 17 Dec 2007 17:26:32 +0000 (17:26 +0000)]
Fix a MAC label leak for POSIX semaphores, in which per-policy labels
would be properly disposed of, but the global label structure for the
semaphore wouldn't be freed.
MFC after: 3 days
Reported by: tanyong <tanyong at ercist dot iscas dot ac dot cn>,
zhouzhouyi
Robert Watson [Mon, 17 Dec 2007 17:20:57 +0000 (17:20 +0000)]
Fix leaking MAC labels for IPv6 inpcbs by adding missing MAC label
destroy call; this transpired because the inpcb alloc path for IPv4/IPv6
is the same code, but IPv6 has a separate free path. The results was
that as new IPv6 TCP connections were created, kernel memory would
gradually leak.
MFC after: 3 days
Reported by: tanyong <tanyong at ercist dot iscas dot ac dot cn>,
zhouzhouyi
Kip Macy [Mon, 17 Dec 2007 08:17:51 +0000 (08:17 +0000)]
Make TCP offload work on HEAD (modulo negative interaction between sbcompress
and t3_push_frames).
- Import latest changes to cxgb_main.c and cxgb_sge.c from toestack p4 branch
- make driver local copy of tcp_subr.c and tcp_usrreq.c and override tcp_usrreqs so
TOE can also functions on versions with unmodified TCP
Kip Macy [Mon, 17 Dec 2007 07:56:27 +0000 (07:56 +0000)]
incorporate feedback since initial commit
- rename tcp_ofld.[ch] to tcp_offload.[ch]
- document usage and locking conventions of the functions in the
toe_usrreqs function vector
- document tcpcb, inpcb, and socket fields used by toe
- widen the listen interface into 2 functions
- rename DISABLE_TCP_OFFLOAD to TCP_OFFLOAD_DISABLE
- shrink conditional compilation to reduce the likelihood of bitrot
- replace sc->sc_toepcb checks in tcp_syncache.c with TOEPCB_ISSET
David Xu [Mon, 17 Dec 2007 05:55:07 +0000 (05:55 +0000)]
Add missing changes for fixing LOR of umtx lock and thread lock, follow
the committing of files:
kern_resource.c revision 1.181
sched_4bsd.c revision 1.111
sched_ule.c revision 1.218
Kip Macy [Mon, 17 Dec 2007 04:19:25 +0000 (04:19 +0000)]
Don't panic in arpresolve if we're given a null mbuf. We could
insist that the caller just pass in an initialized mbuf even
if didn't have any data - but that seems rather contrived.
Jason Evans [Mon, 17 Dec 2007 01:20:04 +0000 (01:20 +0000)]
Refactor features a bit in order to make it possible to disable lazy
deallocation and dynamic load balancing via the MALLOC_LAZY_FREE and
MALLOC_BALANCE knobs. This is a non-functional change, since these
features are still enabled when possible.
Clean up a few things that more pedantic compiler settings would cause
complaints over.
David Schultz [Sun, 16 Dec 2007 21:19:28 +0000 (21:19 +0000)]
Implement and document nan(), nanf(), and nanl(). This commit
adds two new directories in msun: ld80 and ld128. These are for
long double functions specific to the 80-bit long double format
used on x86-derived architectures, and the 128-bit format used on
sparc64, respectively.
David Schultz [Sun, 16 Dec 2007 21:14:33 +0000 (21:14 +0000)]
Fix strto{f,d,ld}() so they don't return signaling NaNs. C99
says they are never supposed to, and the fact that they did could
cause apps that run with unmasked FP exceptions to SIGFPE after a
scanf() or strtod(). The vendor stated that he will not be fixing
this, citing portability concerns.
David Schultz [Sun, 16 Dec 2007 21:13:54 +0000 (21:13 +0000)]
Some changes the vendor didn't want:
- Accept the '0x' prefix so strtod("nan(0x...)", NULL) returns the same
thing as gcc's builtin nan("0x...") for such strings.
- Don't return uninitialized memory.
- Finish processing the string up to the closing ')' (provided it's
lexically valid) for compatibility with C99 and *scanf().
Implement -E option which will erase the filesystem sectors before
making the new filesystem. Reserved space in front of the superblock
(bootcode) is not erased.
NB: Erasing can take as long time as writing every sector sequentially.
This is relevant for all flash based disks which use wearlevelling.
When moving a directory across devices to a place where a directory
with the same name exists, delete that directory first, before performing
the copy. This ensures that mv(1) across devices follows the semantics
of rename(2), as required by POSIX.
This change could introduce the potential of data loss, even if the
copy fails, violating the atomicity properties of rename(2). This is
(mostly) mitigated by first renaming the destination and obliterating
it only after a succesfull copy.
The above logic also led to the introduction of code that will cleanup
the results of a partial copy, if a cross-device copy fails.
Stanislav Sedov [Sun, 16 Dec 2007 12:39:50 +0000 (12:39 +0000)]
- Add quirk for the TrendNet TU-S9 adapter, which uses new version of PL2303
chip (revision 0x400). This allows it to be correctly identified as PL2303X.
Jeff Roberson [Sun, 16 Dec 2007 06:21:20 +0000 (06:21 +0000)]
Refactor select to reduce contention and hide internal implementation
details from consumers.
- Track individual selecters on a per-descriptor basis such that there
are no longer collisions and after sleeping for events only those
descriptors which triggered events must be rescaned.
- Protect the selinfo (per descriptor) structure with a mtx pool mutex.
mtx pool mutexes were chosen to preserve api compatibility with
existing code which does nothing but bzero() to setup selinfo
structures.
- Use a per-thread wait channel rather than a global wait channel.
- Hide select implementation details in a seltd structure which is
opaque to the rest of the kernel.
- Provide a 'selsocket' interface for those kernel consumers who wish to
select on a socket when they have no fd so they no longer have to
be aware of select implementation details.
Marcel Moolenaar [Sun, 16 Dec 2007 01:02:47 +0000 (01:02 +0000)]
Make files under src/sys/powerpc/aim, as well as Open Firmware related
files dependent upon option/cpu AIM. This is in preparation of adding
support for Book-E (e500) support.
Marcel Moolenaar [Sun, 16 Dec 2007 00:45:56 +0000 (00:45 +0000)]
Rename OEA to AIM. The former means nothing as it applies to all
processors (it's the PowerPC Operating Environment Architecture).
AIM designates the processors made by the Apple-IBM-Motorola
alliance and those we typically support.
While here, remove the NetBSD option IPKDB. It's not an option
used by us. Also, PPC_HAVE_FPU is not used by us either. Remove
that too.
Jeff Roberson [Sat, 15 Dec 2007 23:13:31 +0000 (23:13 +0000)]
- Re-implement lock profiling in such a way that it no longer breaks
the ABI when enabled. There is no longer an embedded lock_profile_object
in each lock. Instead a list of lock_profile_objects is kept per-thread
for each lock it may own. The cnt_hold statistic is now always 0 to
facilitate this.
- Support shared locking by tracking individual lock instances and
statistics in the per-thread per-instance lock_profile_object.
- Make the lock profiling hash table a per-cpu singly linked list with a
per-cpu static lock_prof allocator. This removes the need for an array
of spinlocks and reduces cache contention between cores.
- Use a seperate hash for spinlocks and other locks so that only a
critical_enter() is required and not a spinlock_enter() to modify the
per-cpu tables.
- Count time spent spinning in the lock statistics.
- Remove the LOCK_PROFILE_SHARED option as it is always supported now.
- Specifically drop and release the scheduler locks in both schedulers
since we track owners now.
In collaboration with: Kip Macy
Sponsored by: Nokia