If anything is still broken (and was not before :)), please shout.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12361 a95241bf-73f2-0310-859d-f6bbb57e9c96
of the kernel. Also fixed unsafe userland communication, and other minor issues.
The packet_buffer encapsulates the ring_buffer and adds some handy functionality
(like locking).
Removed the global open masks - no reason for them to be defined globally.
Lots of cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12358 a95241bf-73f2-0310-859d-f6bbb57e9c96
fix the keyboard/mouse problems of most (because they probably didn't know
about this flag). Still does not work for me, though.
Note, if you want consoled the use the input_server, or if you want to use
the input_server as an R5 replacement, you have to define this flag again.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12356 a95241bf-73f2-0310-859d-f6bbb57e9c96
"consoled" now uses this information to tell the TTY its size.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12355 a95241bf-73f2-0310-859d-f6bbb57e9c96
of months now. This solves (probably) all those strange problems you might have
experienced using it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12354 a95241bf-73f2-0310-859d-f6bbb57e9c96
* we now put data in cbuf at the good offset
The mouse is now working ok in Haiku, tested with input_server.
The current implementation based on our cbuf isn't good, as we're erasing old data, if mouse input addon can't keep up with interrupts.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12352 a95241bf-73f2-0310-859d-f6bbb57e9c96
the advantage that module_image::ref_count does not get messed up, so we could still
determine when to unload such a module (with an extra function).
get_module() now calls put_module_image() if B_MODULE_INIT failed - failing modules
were never unloaded before...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12343 a95241bf-73f2-0310-859d-f6bbb57e9c96
arbitrarily into the current team address space if there are pending bytes
in the chain.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12329 a95241bf-73f2-0310-859d-f6bbb57e9c96
- it's restore_interrupts() not enable_interrupts()
- B_READ_AREA|B_WRITE_AREA gives every *userland* application full access
- fixed coding style
- the PCI module was never put away (but get_module() was called almost everywhere)
- added comments where the code looked buggy on first sight
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12326 a95241bf-73f2-0310-859d-f6bbb57e9c96
- removed libnetapi.so from $NETWORK_LIBS - it's not used by anyone anyway,
and it's definitely not necessary to link against it by default.
Note, this might cause problems in some of the mail add-ons; I haven't
tested this.
- route/ping/... now also link against $SELECT_UNAME_ETC_LIB
makehdimage should now work again under all BeOS platforms.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12325 a95241bf-73f2-0310-859d-f6bbb57e9c96
- pending_chain was set to -1, then MAIL:pending_chain was read into the variable "chain",
but later pending_chain was used again for comparison - and if that was not enough,
"chain" was later used again as well... (Nathan please check this)
- pending_chain was int32, Chain()->ID() uint32
- renamed pending_chain to pendingChain
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12323 a95241bf-73f2-0310-859d-f6bbb57e9c96
Removed GPLd network add-ons from the target image for now as they are only
compilable when the tree was configured to support GPL add-ons.
(I am not even sure if GPLd drivers are a legal problem for us, anyway)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12322 a95241bf-73f2-0310-859d-f6bbb57e9c96
