by other sources as well. Maybe we can remove that parameter from
mmu_map_physical_memory() altogether, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12283 a95241bf-73f2-0310-859d-f6bbb57e9c96
it doesn't really do anything, it just passes the initial frame buffer
on to the app_server).
While it seems to work on real hardware (if you set the video mode to
640x480x32, app_server restriction), under Bochs, the app_server crashes.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12273 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also changed readlink() to be POSIX compliant with those changes.
"ls -l" does now resolve links properly again (the new coreutils version outlined the problems).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12263 a95241bf-73f2-0310-859d-f6bbb57e9c96
to ours - pretty hefty bugs, I wonder how it could work before at all.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12261 a95241bf-73f2-0310-859d-f6bbb57e9c96
already before mapping it. That's necessary because the vm_soft_fault()
function cannot guaranty to call the fault handler only once.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12260 a95241bf-73f2-0310-859d-f6bbb57e9c96
RUN_WITHOUT_APP_SERVER is no longer needed.
This reduces the hassle when switching between the real app_server and
consoled.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12256 a95241bf-73f2-0310-859d-f6bbb57e9c96
know it yet - this fixes an endless loop in the VM fault handler.
set_area_protection() no longer disallows settings B_EXECUTE_AREA and B_WRITE_AREA
at the same time.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12252 a95241bf-73f2-0310-859d-f6bbb57e9c96
might be a better choice, this error suggests a kernel error - it shouldn't be
possible to achieve this with the public API).
Added fix_protection() function to make the area protection valid (ie. add
missing kernel protections), and also to make it consistent throughout the
API.
set_area_protection() no longer disallows setting B_EXECUTE_AREA and B_WRITE_AREA
at the same time: a) you can create areas with these flags, and b) it was thought
as a security feature, but it would be very weak (you could simply clone the
area read/write aynway).
The internal APIs now ask the arch VM if it can support the protection the
caller asked for.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12251 a95241bf-73f2-0310-859d-f6bbb57e9c96
create_area() and friends should fail if it's not supported.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12248 a95241bf-73f2-0310-859d-f6bbb57e9c96
with the IDs for the calling team, ie. setpgid(getpid(), getpid())
because it's essentially the same thing.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12247 a95241bf-73f2-0310-859d-f6bbb57e9c96
This fixes the "setpgrp() failed in child" message in gdb (that happened because
it lied and called setpgid() instead).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12246 a95241bf-73f2-0310-859d-f6bbb57e9c96
for these changes. I was mostly just staring in amazement at the screen
while Axel and Thomas were discussing IA32 internals. A particularly
fascinating moment was when Thomas produced the cause of a bug we had
been trying to track down for hours off the top of his head (of course
iret behaves specially when the NT bit is set :-). His slowness must be
excused though, since he hadn't slept for more then 30 hours. ;-)
The code doesn't wholeheartedly deal with multi-processor machines yet.
Axel will certainly do some cleanup...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12239 a95241bf-73f2-0310-859d-f6bbb57e9c96
* #undef DEBUG in plib/physmem.c to avoid debug code
* comment out #define mktime rpl_mktime, don't know why it wasn't detected
* now links mv, chown, chgrp, rm, chmod, du, mkdir, pwd against libroot.so for fchdir
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12238 a95241bf-73f2-0310-859d-f6bbb57e9c96
In case of an unknown error, it will now also take the error base definitions
into account (ie. it could return "Unknown Application Kit Error (x)").
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12237 a95241bf-73f2-0310-859d-f6bbb57e9c96
you choose it in the menu.
The boot loader now always switches into a graphics mode unless it's in
debug mode (currently triggered by pressing the escape key on startup).
That means, "Standard VGA" now actually means mode 0x12 (640x480x4)
instead of text mode.
Since the current limited boot logo code would do stupid things with VGA
planes, there will now only be some colored blocks visible during boot.
Implemented support for monochrome modes in the frame buffer console.
Additionally, the frame buffer console now has support for the VGA mode; it
will treat all 4 bit modes as monochrome for now (the VGA 0x12 mode is a
planar mode so this works nicely).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12235 a95241bf-73f2-0310-859d-f6bbb57e9c96
