Commit Graph

3826 Commits

Author SHA1 Message Date
Axel Dörfler
97c5bef4a1 Added missing assembly functions for __swap_float() and __swap_double().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12767 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-22 23:16:55 +00:00
Axel Dörfler
fe9bc5ae27 Added sqrt() and sqrtf() assembly versions.
Still they are not yet really used.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12731 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-19 14:13:22 +00:00
Axel Dörfler
62f9753de5 Added public domain versions of sin() and cos() (taken from glibc).
Not yet used, though - we probably need to rearrange the source files a bit.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12727 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-18 22:19:35 +00:00
Andrew Bachmann
dfdc5e411e use "national" math (fixes copysign/drem)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12720 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-18 20:43:52 +00:00
Axel Dörfler
62d6961672 Renamed vm.c to vm.cpp and made all the changes to let it compile without
errors. Also made the VM headers C++ safe.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12694 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-16 23:17:45 +00:00
Axel Dörfler
8f8d46a3ff vm_put_area() now gives feedback wether it deleted the area or not (it
will return true in the former case).
vm_delete_areas() is now using this information to print out a warning
in this case (so that a missing vm_put_area() can now be found easier).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12693 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-16 22:37:34 +00:00
Axel Dörfler
4393552b4d The heap is now located at 384 MB, and creates a reserved range that spans over the
following 1152 MB - that area only guarantees that the heap can grow this much before
the application need the memory for something else. And even then, the heap range
is reused from top-to-bottom, allowing for maximum heap usage. Of course, if the
memory after the heap range is not claimed yet, it can still be claimed by the heap,
too. Added new syscall to create the reserved range.
Fixed a bug in vm_delete_areas(): when it removed reserved areas, the area list
could get messed up.
Fixed a bug in resize_area(): resized areas could never be deleted (missing vm_put_area())!
resize_area() now supports reserved regions (but not perfectly yet, see ToDo items).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12692 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-16 22:15:13 +00:00
Axel Dörfler
a3e9996e9d Added support for special reserved address ranges: they will be used
only if memory becomes tight, and then the range is used from end to
start.
This is useful to reserve heap address ranges.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12675 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-15 15:56:55 +00:00
Axel Dörfler
20a6e5473b Renamed RESERVED_REGION_ID to RESERVED_AREA_ID.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12674 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-15 15:06:57 +00:00
Axel Dörfler
ccc8865ba2 Added an additional flag B_OVERCOMMITTING_AREA (currently to be specified
along the protection flags).
Changed the handling of B_STACK_AREA types and anonymous vm_areas: now
every area can overcommit if B_OVERCOMMITTING_AREA was specified.
B_STACK_AREA areas are still automatically overcommitting, but
B_KERNEL_STACK_AREA areas no longer.
vm_store_anonymous_noswap.c now only tests for guard pages if there were
any specified which is only done for B_STACK_AREA areas.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12673 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-15 15:03:44 +00:00
Axel Dörfler
d5b04e50f8 First step into a new block allocation strategy for the block_cache
(right now, it's still malloc/free, just encapsulated in an allocator class).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12662 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-13 18:18:28 +00:00
Axel Dörfler
0faec19e8a Cleanup, turned off debug output.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12653 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-12 23:43:39 +00:00
Axel Dörfler
6bdc405f75 Whenever KPath is used, it will now be tested if it could be initialized
(thanks to Ingo for the reminder...).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12652 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-12 23:31:04 +00:00
Axel Dörfler
90a0e0b9d9 Cleanup, turned off debug output.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12651 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-12 23:29:28 +00:00
Axel Dörfler
6094d89f2f Merged branches/developer/axeld/driver_recognition changed r12307:12637 into trunk.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12638 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-12 03:27:44 +00:00
Axel Dörfler
cbd1d9977f Changed all _kern_*() calls to use KPath instead of a path buffer on the stack.
This reduces the stack usage quite a lot, and since file system calls could be
nested (for example, a mounted image on a volume), definitely a must, too.
Might be a good idea for user calls, too, though, although it's not urgent.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12636 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-12 01:14:01 +00:00
Axel Dörfler
895e2a0375 Reenabled the Qemu workaround: the frame buffer is now cleared after a mode change.
After all, there might be real graphics card which behave the same??


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12551 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-03 02:06:08 +00:00
Axel Dörfler
0953c83ebd Fixed another bug: after a partition had been mounted, it was only marked
mounted, but no one told it about its volume ID - that caused "mountvolume"
not to be able to return a valid mount point.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12548 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-03 01:59:17 +00:00
Axel Dörfler
47729f044c Fixed a possible bug in path_to_vnode(): if called before a root
file system has been mounted, it would have crashed (that for example
happened if you deleted the kernel settings file...).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12547 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-05-03 01:05:20 +00:00
Axel Dörfler
b20667b35b {install|remove}_io_interrupt_handler() now correctly handle the B_NO_ENABLE_COUNTER flag.
Lots of cleanup:
- moved B_NO_ENABLE_COUNTER flag definition out of int.h to KernelExport.h, as it's
  described in the BeBook (although it's probably not really used that often :))
- int.c no longer has any platform dependent code (+ 0x20 on interrupt numbers is gone);
  it's now entirely handled in the arch/x86/ section.
- the io_vectors[] is now statically initialized, instead of allocated from the heap
- removed {install|remove}_interrupt_handler(); they weren't that useful, arch_smp_init()
  is now calling install_io_interrupt_handler() correctly instead
- introduced a new arch_int.h header file that currently contains NUM_IO_VECTORS only
  (though on x86, it also has ARCH_INTERRUPT_BASE == 0x20).
- changed the return type from {install|remove}_io_interrupt_handler() from "long" to
  "status_t"
- rearranged and cleaned the PIC initialization code, made the PIC code more prominent
- changed comments that talk about a non existing 8239 (the PIC chip is actually 8259)
- moved arch/x86/interrupts.h to the source directory, as it's not used outside
- added BeOS compatible interrupts_enabled() function, that should replace our
  equivalent (and private) are_interrupts_enabled()


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12477 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-04-27 01:08:35 +00:00
Axel Dörfler
0f757dc5df This fixes the build with GCC 3.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12397 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-04-14 22:15:38 +00:00
Axel Dörfler
b51d2e941a Now uses the ring_buffer implementation instead of cbuf.
Decreased the pipe buffer to 32768 bytes (it's 4096 on BeOS).
pipefs_select/deselect() did no locking.
Switched to using the BenaphoreLocker where possible.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12381 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-04-13 22:43:35 +00:00
Axel Dörfler
900849fa0d Since objects/.../system/kernel is now a directory, the kernel target is now
called kernel_${arch} like on disk. A "jam kernel" will still work, though.
Also updated all those Jamfiles I forgot to update before.
Since makehdimage now runs through (and even builds a working image), I guess
most of the consequences of the "kernel/core" -> "system/kernel" rename task
are solved.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12364 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-04-13 14:49:55 +00:00
Axel Dörfler
718b5114e0 This should fix the build after all the kernel/system renaming.
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
2005-04-13 13:59:17 +00:00
Axel Dörfler
2d690920ac Renamed system/core to system/kernel.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12360 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-04-13 13:22:10 +00:00
Axel Dörfler
5af32e7526 Renamed src/kernel to src/system.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12359 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-04-13 13:06:35 +00:00