the APM driver to see it at work).
The frame buffer console now creates such a boot item to give a potential
VESA driver access to the boot frame buffer configuration.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12221 a95241bf-73f2-0310-859d-f6bbb57e9c96
Probably only works under Haiku due to the new area flags.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12219 a95241bf-73f2-0310-859d-f6bbb57e9c96
be used from posix/math.h but some glibc headers. This is not nice, but
it works.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12218 a95241bf-73f2-0310-859d-f6bbb57e9c96
describe partitions that are out of bounds. We simply ignore those now,
instead of letting the complete scanning fail.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12206 a95241bf-73f2-0310-859d-f6bbb57e9c96
selected "/safemode/" options are now passed to the kernel.
Added help texts to some safe mode options.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12204 a95241bf-73f2-0310-859d-f6bbb57e9c96
with the number of the actual string length, but it was still used for a
subsequent user_strlcpy() to the user buffer - therefore, it cut off one
byte from the result string.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12202 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added a ToDo comment about the forgotten find_directory().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12201 a95241bf-73f2-0310-859d-f6bbb57e9c96
- we must not use static C++ locks: the heap is initialized before the
global constructors are called which means that our sLockList was
initialized twice, and lost all locks added inbetween
- *but* the lock implementation was completely wrong anyway: Hoard used
to allocate superblocks, but it never freed them - instead, their memory
was recycled when their time came. That caused semaphores to be in fact
thrown away, but also corrupted the lock list
- I've now implemented the locks like they are implemented in the other
architectures supported by Hoard: via a spinning (busy waiting) lock.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12200 a95241bf-73f2-0310-859d-f6bbb57e9c96
- vfs_exec_io_context() did not close descriptors
- no variant of dup() did increment the open_count
This allows "VARIABLE=`command`" bash lines to work again.
Removed redundant PRINT() macro from fd.c.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12199 a95241bf-73f2-0310-859d-f6bbb57e9c96
Removed m4, po directories
UTF8 filenames don't seem to be displayed well with ls in Terminal
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12192 a95241bf-73f2-0310-859d-f6bbb57e9c96
MenuItem::SetData() now asks for a const parameter.
The safemode menu options now set their MenuItem::Data() to the safemode option string.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12191 a95241bf-73f2-0310-859d-f6bbb57e9c96
to compile our libbe.so with RUN_WIHTOUT_APP_SERVER for the image.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12190 a95241bf-73f2-0310-859d-f6bbb57e9c96
partitioning system module relies on it, otherwise extended
partitions won't be recognized.
* Be a little less lazy and do the priority partition recognition,
i.e. all partitioning systems are asked to identify a partition and
the one that believes it can handle the partition best, wins the pot.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12187 a95241bf-73f2-0310-859d-f6bbb57e9c96
* We apparently cannot use constants like kPartitionTypeIntelExtended
in static array initializers in the kernel.
* Fixed misunderstanding between Axel (boot loader) and me (Intel
partitioning system module) how to deal with the cookie the
identify() hook returns. We switch to a someone cleaner method by
always invoking free_identify_cookie() for it, even if it were passed
to scan(). Since we want to keep the cookie, we add a reference
counter to it.
This should fix a couple of issues with recognizing the boot partition.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12185 a95241bf-73f2-0310-859d-f6bbb57e9c96
