Fix and build again net_server_driver.
Rollback to NET_STACK_GET_COOKIE trick for accept() implementation.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3926 a95241bf-73f2-0310-859d-f6bbb57e9c96
usage clearer. Also added a comment that explains why it's okay that
blocksNeeded and blocksRequested can be different.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3579 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added file system global locking around creating, deleting, and renaming
inodes - that's not nice, but since we have only sequential journal access,
it won't hurt concurrency much. The locks are needed to prevent certain
things from happening like two threads could theoretically create the same
file twice (one of them would have failed, but relatively late in the process).
Anyway, a better locking scheme will be implemented at a later date, but maybe
not for R1.
Small cleanup.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3562 a95241bf-73f2-0310-859d-f6bbb57e9c96
think that it shouldn't drop any packets anymore (only delay them)
- I implemented a packet wrap, so after 64k the driver will start over again
- I fixed a bug where packets with the largest ethernet frame size (1514)
weren't accepted.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3561 a95241bf-73f2-0310-859d-f6bbb57e9c96
Sorry for the enthousiasm. For the first time in my life a made a driver
somewhat work. There's still a major list of things to do, but at least I
feel safer now that this is working. I can already do pings. Moreover, I'm
doing this commit with my own driver. I'm just ashamed for the major mistake
I made that took me so much time to find. I'm off sending this beast to
testers.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3555 a95241bf-73f2-0310-859d-f6bbb57e9c96
the interrupt handler, now it is done in the read_hook itself. This means that
less memory is used because the packet reception isn't double-buffered anymore.
It also wasn't the performance it I'd expect it to be (probably thanks to BeOS
scheduling!). The problem with the strange loss of around 50% of the packets
remains.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3526 a95241bf-73f2-0310-859d-f6bbb57e9c96
(disk device manager) and moved it to a nicer place.
First tests look good, though my hard disk structure doesn't even
have extended partitions. Going to install Linux now...
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3504 a95241bf-73f2-0310-859d-f6bbb57e9c96
Add a Jamfile to build it (thanks to Axel's sis900 jamfile).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3487 a95241bf-73f2-0310-859d-f6bbb57e9c96
the old attribute value wasn't evaluated at all.
Also, Index::Update() got a type code of zero, instead of the real value
in situations where this didn't make any sense.
Minor cleanup in kernel_interface.cpp.
New method Volume::CheckForLiveQuery() that checks if there is a live query
depending on the specified attribute - not yet implemented, but already used;
always returns "true" right now, which doesn't cause any harm but reducing
the speed lightly.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3394 a95241bf-73f2-0310-859d-f6bbb57e9c96
a name - that's mostly done to:
1) force better fitting lock names
2) make the API consistent (the empty ReadWriteLock constructor doesn't
initialize the lock anymore).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@3366 a95241bf-73f2-0310-859d-f6bbb57e9c96
