kernel/thread: Refactor thread-local-storage initialization and updating.

* TLS slots are not in any way architecture-specific; we do not even
have a mechanism by which they could be made so at present.
Thus, the initialization of them can be moved to common code, and
out of the per-architecture implementations.

* When dealing with a fork()ed thread, it will already have a TLS array
with values set in it. Therefore, do not overwrite the whole array,
but instead only update the specific values which have changed on fork.
This fixes at least part of #17896.

kernel: Whitespace cleanup only.

Revert team and thread changes for COMPAT_MODE (hrev52010 & hrev52011).

This reverts commit c558f9c8fe54bc14515aa62bac7826271289f0e4.
This reverts commit 44f24718b1505e8d9c75e00e59f2f471a79b5f56.
This reverts commit a69cb330301c4d697daae57e6019a307f285043e.
This reverts commit 951182620e297d10af7fdcfe32f2b04d56086ae9.

There have been multiple reports that these changes break mounting NTFS partitions
(on all systems, see #14204), and shutting down (on certain systems, see #12405.)
Until they can be fixed, they are being backed out.

kernel/x86_64: setup a new thread in compatibility mode.

* define compat_thread_info, compat_rlim_t, compat_rlimit and
compat_thread_creation_attributes to be used when applicable in compatibility
mode.
* handle 32-bit types in _user_spawn_thread(), _user_get_thread_info(),
_user_get_next_thread_info(), _user_getrlimit(), _user_setrlimit(),
other syscalls are compatible as is.
* init TLS for compatibility mode threads.

Change-Id: I483ba95e6198ddac9d240671bcb56fcd2ad831d2

kernel/x86_64: save fpu state at interrupts

The kernel is allowed to use fpu anywhere so we must make sure that
user state is not clobbered by saving fpu state at interrupt entry.
There is no need to do that in case of system calls since all fpu
data registers are caller saved.

We do not need, though, to save the whole fpu state at task swich
(again, thanks to calling convention). Only status and control
registers are preserved. This patch actually adds xmm0-15 register
to clobber list of task swich code, but the only reason of that is
to make sure that nothing bad happens inside the function that
executes that task swich. Inspection of the generated code shows
that no xmm registers are actually saved.

Signed-off-by: Paweł Dziepak <pdziepak@quarnos.org>

runtime_loader: add support for ELF based TLS

This patch introduces support of ELF based TLS handling with lazy allocation
and initalization of TLS block for each DSO and thread. The implementation
generally follows the official ABI except that generation counter in dtv
is in fact a pointer to Generation object that contains both generation
counter and size of the dtv. That simplified the implementation a bit, but
could be changed later. The ABI requirements regariding in memory position
of TLS block is not honoured what results in static TLS model being
unsupported. However, that should not be a problem as long as
"executables" in Haiku are in fact shared objects and optimizations which
require specific TLS block in memory layout are not possible anyway.

kernel: Add CPUSet::{Clear, Set}BitAtomic() functions

kernel: Use CPUSet in ICI code instead of cpu_mask_t

fix a TRACE() formatting string

Cleaner separation of 32-/64-bit specific CPU/interrupt code.

Renamed {32,64}/int.cpp to {32,64}/descriptors.cpp, which now contain
functions for GDT and TSS setup that were previously in arch_cpu.cpp,
as well as the IDT setup code. These get called from the init functions
in arch_cpu.cpp, rather than having a bunch of ifdef'd chunks of code
for 32/64.

Implemented signals for x86_64.

Implemented TLS for x86_64.

Implemented the rest of the kernel debugger functions for x86_64.

Merged with the x86 implementations, mostly the same except for a
few differences. GDB stub is currently broken, will investigate
later.

Implemented threading for x86_64.

* Thread creation and switching is working fine, however threads do not yet
get interrupted because I've not implemented hardware interrupt handling
yet (I'll do that next).
* I've made some changes to struct iframe: I've removed the e/r prefixes
from the member names for both 32/64, so now they're just named ip, ax,
bp, etc. This makes it easier to write code that works with both 32/64
without having to deal with different iframe member names.

Renamed remaining i386_* functions to x86_* for consistency.

Added arch_cpu.cpp to the x86_64 build.

* Some things are currently ifndef'd out completely for x86_64 because
they aren't implemented, there's a few other ifdef's to handle x86_64
differences but most of the code works unchanged.
* Renamed some i386_* functions to x86_*.
* Added a temporary method for setting the current thread on x86_64
(a global variable, not SMP safe). This will be changed to be done
via the GS segment but I've not implemented that yet.

Fix virtual 8086 mode to properly account for TLS.

* The vm86 code or the code running in virtual 8086 mode may clobber the
%fs register that we use for the CPU dependent thread local storage
(TLS). Previously the vm86 code would simply restore %fs on exit, but
this doesn't always work. If the thread got unscheduled while running
in virtual 8086 mode and was then rescheduled on a different CPU, the
vm86 exit code would restore the %fs register with the TLS value of
the old CPU, causing anything using TLS in userland to crash later on.
Instead we skip the %fs register restore on exit (as do the other
interrupt return functions) and explicitly update the potentially
clobbered %fs by calling x86_set_tls_context(). This will repopulate
the %fs register with the TLS value for the right CPU. Fixes #8068.

* Made the static set_tls_context() into x86_set_tls_context() and made
it available to others to faciliate the above.

* Sync the vm86 specific interrupt code with the changes from hrev23370,
using the iframe pop macro to properly return. Previously what was
pushed in int_bottom wasn't poped on return.

* Account for the time update macro resetting the in_kernel flag and
reset it to 1, as we aren't actually returning to userland. This
didn't cause any harm though as only the time tracking is using that
flag so far.

* Some minor cleanup.

Merged signals-merge branch into trunk with the following changes:
* Reorganized the kernel locking related to threads and teams.
* We now discriminate correctly between process and thread signals. Signal
handlers have been moved to teams. Fixes #5679.
* Implemented real-time signal support, including signal queuing, SA_SIGINFO
support, sigqueue(), sigwaitinfo(), sigtimedwait(), waitid(), and the addition
of the real-time signal range. Closes #1935 and #2695.
* Gave SIGBUS a separate signal number. Fixes #6704.
* Implemented <time.h> clock and timer support, and fixed/completed alarm() and
[set]itimer(). Closes #5682.
* Implemented support for thread cancellation. Closes #5686.
* Moved send_signal() from <signal.h> to <OS.h>. Fixes #7554.
* Lots over smaller more or less related changes.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42116 a95241bf-73f2-0310-859d-f6bbb57e9c96

Merged the signals branch into trunk, with these changes:
* The team and thread kernel structures have been renamed to Team and Thread
respectively and moved into the new BKernel namespace.
* Several (kernel add-on) sources have been converted from C to C++ since
private kernel headers are included that are no longer C compatible.

Changes after merging:
* Fixed gcc 2 build (warnings mainly in the scary firewire bus manager).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40196 a95241bf-73f2-0310-859d-f6bbb57e9c96

Moved paging related files to new subdirectories paging and paging/32bit.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37060 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Removed i386_translation_map_get_pgdir() and adjusted the one place where it
was used.
* Renamed X86VMTranslationMap to X86VMTranslationMap32Bit and pulled the paging
method agnostic part into new base class X86VMTranslationMap.
* Moved X86PagingStructures into its own header/source pair.
* Moved pgdir_virt from X86PagingStructures to X86PagingStructures32Bit where
it is actually used.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37055 a95241bf-73f2-0310-859d-f6bbb57e9c96

x86:
* Renamed i386_context_switch() to x86_context_switch().
* x86_context_switch() no longer sets the page directory.
arch_thread_context_switch() does that explicitly, now. This allows to solve
the TODO by reordering releasing the previous paging structures reference and
setting the new page directory.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37024 a95241bf-73f2-0310-859d-f6bbb57e9c96

x86:
* Renamed vm_translation_map_arch_info to X86PagingStructures, and all
members and local variables of that type accordingly.
* arch_thread_context_switch(): Added TODO: The still active paging structures
can indeed be deleted before we stop using them.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37022 a95241bf-73f2-0310-859d-f6bbb57e9c96

Consequently use uint32 for the physical page directory address.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37011 a95241bf-73f2-0310-859d-f6bbb57e9c96

* First run through the kernel's private parts to use phys_{addr,size}_t
where appropriate.
* Typedef'ed page_num_t to phys_addr_t and used it in more places in
vm_page.{h,cpp}.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@36937 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved the syscall stuff from arch_commpage.cpp to x86_syscalls.{cpp,h}.
* On context switches we do now set the IA32_MSR_SYSENTER_ESP. This saves us
setting esp at the beginning of x86_sysenter(). More importantly when
entering it in single-step mode, this no longer causes a double fault
(cf. #3487). We still don't handle the resulting debug exception correctly,
so that we still get a (continuable) panic().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35609 a95241bf-73f2-0310-859d-f6bbb57e9c96

Refactored vm_translation_map:
* Pulled the physical page mapping functions out of vm_translation_map into
a new interface VMPhysicalPageMapper.
* Renamed vm_translation_map to VMTranslationMap and made it a proper C++
class. The functions in the operations vector have become methods.
* Added class GenericVMPhysicalPageMapper implementing VMPhysicalPageMapper
as far as possible (without actually writing new code).
* Adjusted the x86 and the PPC specifics accordingly (untested for the
latter). For the other architectures the build is, I'm afraid, seriously
broken.

The next steps will modify and extend the VMTranslationMap interface, so that
it will be possible to fix the bugs in vm_unmap_page[s]() and employ
architecture specific optimizations.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35066 a95241bf-73f2-0310-859d-f6bbb57e9c96

Removed unused <arch>_switch_stack_and_call() and
arch_thread_switch_kstack_and_call().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34971 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved the VM headers into subdirectory vm/.
* Renamed vm_cache.h/vm_address_space.h to VMCache.h/VMAddressSpace.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34449 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved VMAddressSpace definition to vm_address_space.h.
* "Classified" VMAddressSpace, i.e. turned the vm_address_space_*() functions
into methods, made all attributes (but "areas") private, and added
accessors.
* Also turned the vm.cpp functions vm_area_lookup() and
remove_area_from_address_space() into VMAddressSpace methods. The rest of
the area management functionality will follow soon.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34447 a95241bf-73f2-0310-859d-f6bbb57e9c96

Renamed vm_address_space to VMAddressSpace.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34422 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Reverted r32216 (by mmlr): it's not a good idea to access a variable on the
stack after that has just been changed, and does not contain the data one
would assume.
* This fixes the leaking the vm_translation_map_arch_info objects, and thus
bug #4957.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34090 a95241bf-73f2-0310-859d-f6bbb57e9c96

After creating a userland thread we didn't set up the breakpoints for it.
Fixes #4665.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33369 a95241bf-73f2-0310-859d-f6bbb57e9c96

The reference of the currently active translation map shouldn't be released
until the data it protects isn't in active use anymore. Previously it would
release the translation map and therefore the page directory reference while
the page dir was still set on the CPU, as only the actual call to
i386_context_switch() will replace the page directory in the control register.
This didn't cause any harm though, as during the context switch interrupts are
disabled and therefore the page directory would only be deferred_delete()ed and
not directly freed/overwritten. Still this is logically more correct.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32216 a95241bf-73f2-0310-859d-f6bbb57e9c96

User debugger support:
* Generalized address checks. The debugger can now also read the commpage.
* Added new syscall _kern_get_thread_cpu_state() to get the CPU state of a
not running thread. Introduced arch_get_thread_debug_cpu_state() for that
purpose, which is only implemented for x86 ATM (uses the new
i386_get_thread_user_iframe()).
* Don't allow a debugger to change a thread's "esp" anymore. That's the esp
register in the kernel. "user_esp" can still be changed.
* Generally set RF (resume flag) in eflags in interrupt handlers, not only
after a instruction breakpoint debug exception. This should prevent
breakpoints from being triggered more than once (e.g. when the breakpoint is
on an instruction that can cause a page fault). I still saw those with bdb
in VMware, but that might be a VMware bug.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31045 a95241bf-73f2-0310-859d-f6bbb57e9c96

When switching to a kernel thread we no longer set the page directory.
This is not necessary, since userland teams' page directories also
contain the kernel mappings, and avoids unnecessary TLB flushes. To make
that possible the vm_translation_map_arch_info objects are reference
counted now.

This optimization reduces the kernel time of the Haiku build on my
machine with SMP disabled a few percent, but interestingly the total
time decreases only marginally. Haven't tested with SMP yet, but for
full impact CPU affinity would be needed.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28287 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Prefixed memset_physical() and memcpy_to_physical() with "vm_",
added vm_memcpy_from_physical() and vm_memcpy_physical_page(), and
added respective functions to the vm_translation_map operations. The
architecture specific implementation can now decide how to implement
them most efficiently. Added generic implementations that can be used,
though.
* Changed vm_{get,put}_physical_page(). The former no longer accepts
flags (the only flag PHYSICAL_PAGE_DONT_WAIT wasn't needed anymore).
Instead it returns an implementation-specific handle that has to be
passed to the latter. Added vm_{get,put}_physical_page_current_cpu()
and *_debug() variants, that work only for the current CPU,
respectively when in the kernel debugger. Also adjusted the
vm_translation_map operations accordingly.
* Made consequent use of the physical memory operations in the source
tree.
* Also adjusted the m68k and ppc implementations with respect to the
vm_translation_map operation changes, but they are probably broken,
nevertheless.
* For x86 the generic physical page mapper isn't used anymore. It is
suboptimal in any case. For systems with small memory it is too much
overhead, since one can just map the complete physical memory (that's
not done yet, though). For systems with large memory it counteracts
the VM strategy to reuse the least recently used pages. Since those
pages will most likely not be mapped by the page mapper anymore, it
will keep remapping chunks. This was also the reason why building
Haiku in Haiku was significantly faster with only 256 MB RAM (since
that much could be kept mapped all the time).
Now we're using a different strategy: We have small pools of virtual
page slots per CPU that are used for the physical page operations
(memset_physical(), memcpy_*_physical()) with CPU-pinned thread.
Furthermore we have four slots per translation map, which are used to
map page tables.

These changes speed up the Haiku image build in Haiku significantly. On
my Core2 Duo 2.2 GHz 2 GB machine about 40% to 20 min 40 s (KDEBUG
disabled, block cache debug disabled). Still more than factor 3 slower
than FreeBSD and Linux, though.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28244 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Added "from" address space parameter to vm_swap_address_space()/
arch_vm_aspace_swap().
* The x86 implementation does now maintain a bit mask per
vm_translation_map_arch_info indicating on which CPUs the address
space is active. This allows flush_tmap() to avoid ICI for user
address spaces when the team isn't currently running on any other CPU.
In this context ICI is relatively expensive, particularly since we map
most pages via vm_map_page() and therefore invoke flush_tmap() pretty
much for every single page.
This optimization speeds up a "hello world" compilation about 20% on
my machine (KDEBUG turned off, freshly booted), but interestingly it
has virtually no effect on the "-j2" haiku build time.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27912 a95241bf-73f2-0310-859d-f6bbb57e9c96

Simplified x86_next_page_directory().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27904 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added i386_get_current_iframe(), returning the innermost iframe, if any.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27165 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Changed the meaning of the {KERNEL,USER}_STACK_SIZE macros to not
include the guard pages. Adjusted the kernel and boot loader code
accordingly -- the guard pages size is added/not removed respectively.
The stack size passed to _kern_spawn_thread() is now the actually usable
size, and it is no longer possible to specify a size smaller than or
equal to the guard pages size.
* vm_create_anonymous_area(): Precommit two pages maximum -- a stack with
only one page usable size obviously doesn't need two pages.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26819 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Patch by Andreas: we did not store ebp in vregs::ebp, and we did not store
ebx at all.
* This fixes bug #2569.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26818 a95241bf-73f2-0310-859d-f6bbb57e9c96

arch_setup_signal_frame(): panic() if we don't have a user iframe.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26808 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Removed -Wno-unused from all KernelMergeObjects in kernel Jamfiles.
* Fixed most of the warnings resulting from that by removing actually not used
variables or moving declaration into the #IF. Left unused functions there
though, as I wouldn't know if they are supposed to be used again.
* Fixed two statements with no effect (clamping to MAX_ANCILLARY_DATA_LEN in
socket.cpp and unsetting fCounterSem in MessagingService.cpp).
* Some style cleanups.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26253 a95241bf-73f2-0310-859d-f6bbb57e9c96

stippi + bonefish:
* Missing backslash in UPDATE_THREAD_KERNEL_TIME() macro. Caused the
thread's kernel time never to be updated when the thread left the
kernel. The time would be added to the user time instead.
* Changed semantics of thread_at_kernel_exit(). It leaves interrupts
disabled when returning, now. All code using it would disable
interrupts afterwards anyway, and inbetween the thread could be
interrupted causing two more time updates (or actually not causing
them erroneously).
* The code in x86's interrupt handler entry (int_bottom) also checks
thread::in_kernel now, to determine whether the thread was already
considered to be in userland. This is necessary since the sysexit
instruction doesn't reenable interrupts, so that we have to do that
with the preceeding instruction. Hence an interrupt can occur
inbetween, which would incorrectly add the interrupt's kernel time
to the thread's user time.
* For userland threads team_create_thread_start() didn't invoke
thread_at_kernel_exit() or any equivalent. We do that in
arch_thread_enter_userspace() now.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26240 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Jan Klötzke:
* For vm86 mode the kernel stack top is adjusted -> do not rely on the
kernel_stack_base + KERNEL_STACK_SIZE calculation.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25608 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Jan Klötzke:
* In vm86 mode CS will have arbitrary values so we check for both USER_CODE_SEG
and the VM flag in EFLAGS. This is also done when entering interrupt gates.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25607 a95241bf-73f2-0310-859d-f6bbb57e9c96

* For each userland team the kernel creates an area in the userland
address space that is fully locked and marked B_KERNEL_AREA. It can
thus be accessed by the kernel without additional checks.
* For each userland thread we do create a user_thread structure in that
area. The structure is accessible from userland via TLS, using the
private get_user_thread() function.
* Introduced private userland functions [un]defer_signals(). They can be
used to cheaply disable/re-enable signal delivery. They use the
user_thread::defer_signals/pending_signals fields which are
checked/updated by the kernel.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25451 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Fixed warnings, mostly due to NULL changes.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24487 a95241bf-73f2-0310-859d-f6bbb57e9c96

We have to update the pending signals thread flag when restoring the
signal block mask when returning from a signal handler.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24064 a95241bf-73f2-0310-859d-f6bbb57e9c96

gcc4 build fix


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23992 a95241bf-73f2-0310-859d-f6bbb57e9c96

gcc4 build fix


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23991 a95241bf-73f2-0310-859d-f6bbb57e9c96

axeld + bonefish:
* Implemented automatic syscall restarts:
- A syscall can indicate that it has been interrupted and can be
restarted by setting a respective bit in thread::flags. It can
store parameters it wants to be preserved for the restart in
thread::syscall_restart::parameters. Another thread::flags bit
indicates whether it has been restarted.
- handle_signals() clears the restart flag, if the handled signal
has a handler function installed and SA_RESTART is not set. Another
thread flag (THREAD_FLAGS_DONT_RESTART_SYSCALL) can prevent syscalls
from being restarted, even if they could be (not used yet, but we
might want to use it in resume_thread(), so that we stay
behaviorally compatible with BeOS).
- The architecture specific syscall handler restarts the syscall, if
the restart flag is set. Implemented for x86 only.
- Added some support functions in the private <syscall_restart.h> to
simplify the syscall restart code in the syscalls.
- Adjusted all syscalls that can potentially be restarted accordingly.
- _user_ioctl() sets new thread flag THREAD_FLAGS_IOCTL_SYSCALL while
calling the underlying FS's/driver's hook, so that syscall restarts
can also be supported there.
* thread_at_kernel_exit() invokes handle_signals() in a loop now, as
long as the latter indicates that the thread shall be suspended, so
that after waking up signals received in the meantime will be handled
before the thread returns to userland. Adjusted handle_signals()
accordingly -- when encountering a suspending signal we don't check
for further signals.
* Fixed sigsuspend(): Suspending the thread and rescheduling doesn't
result in the correct behavior. Instead we employ a temporary
condition variable and interruptably wait on it. The POSIX test
suite test passes, now.
* Made the switch_sem[_etc]() behavior on interruption consistent.
Depending on when the signal arrived (before the call or when already
waiting) the first semaphore would or wouldn't be released. Now we
consistently release it.
* Refactored _user_{read,write}[v]() syscalls. Use a common function for
either pair. The iovec version doesn't fail anymore, if anything could
be read/written at all. It also checks whether a complete vector
could be read/written, so that we won't skip data, if the underlying
FS/driver couldn't read/write more ATM.
* Some refactoring in the x86 syscall handler: The int 99 and sysenter
handlers use a common subroutine to avoid code duplication.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23983 a95241bf-73f2-0310-859d-f6bbb57e9c96

kernel/x86_64: save fpu state at interrupts

The kernel is allowed to use fpu anywhere so we must make sure that
user state is not clobbered by saving fpu state at interrupt entry.
There is no need to do that in case of system calls since all fpu
data registers are caller saved.

We do not need, though, to save the whole fpu state at task swich
(again, thanks to calling convention). Only status and control
registers are preserved. This patch actually adds xmm0-15 register
to clobber list of task swich code, but the only reason of that is
to make sure that nothing bad happens inside the function that
executes that task swich. Inspection of the generated code shows
that no xmm registers are actually saved.

Signed-off-by: Paweł Dziepak <pdziepak@quarnos.org>

runtime_loader: add support for ELF based TLS

This patch introduces support of ELF based TLS handling with lazy allocation
and initalization of TLS block for each DSO and thread. The implementation
generally follows the official ABI except that generation counter in dtv
is in fact a pointer to Generation object that contains both generation
counter and size of the dtv. That simplified the implementation a bit, but
could be changed later. The ABI requirements regariding in memory position
of TLS block is not honoured what results in static TLS model being
unsupported. However, that should not be a problem as long as
"executables" in Haiku are in fact shared objects and optimizations which
require specific TLS block in memory layout are not possible anyway.

kernel: Add CPUSet::{Clear, Set}BitAtomic() functions

kernel: Use CPUSet in ICI code instead of cpu_mask_t

fix a TRACE() formatting string

Cleaner separation of 32-/64-bit specific CPU/interrupt code.

Renamed {32,64}/int.cpp to {32,64}/descriptors.cpp, which now contain
functions for GDT and TSS setup that were previously in arch_cpu.cpp,
as well as the IDT setup code. These get called from the init functions
in arch_cpu.cpp, rather than having a bunch of ifdef'd chunks of code
for 32/64.

Implemented signals for x86_64.

Implemented TLS for x86_64.

Implemented the rest of the kernel debugger functions for x86_64.

Merged with the x86 implementations, mostly the same except for a
few differences. GDB stub is currently broken, will investigate
later.

Implemented threading for x86_64.

* Thread creation and switching is working fine, however threads do not yet
get interrupted because I've not implemented hardware interrupt handling
yet (I'll do that next).
* I've made some changes to struct iframe: I've removed the e/r prefixes
from the member names for both 32/64, so now they're just named ip, ax,
bp, etc. This makes it easier to write code that works with both 32/64
without having to deal with different iframe member names.

Renamed remaining i386_* functions to x86_* for consistency.

Added arch_cpu.cpp to the x86_64 build.

* Some things are currently ifndef'd out completely for x86_64 because
they aren't implemented, there's a few other ifdef's to handle x86_64
differences but most of the code works unchanged.
* Renamed some i386_* functions to x86_*.
* Added a temporary method for setting the current thread on x86_64
(a global variable, not SMP safe). This will be changed to be done
via the GS segment but I've not implemented that yet.

Fix virtual 8086 mode to properly account for TLS.

* The vm86 code or the code running in virtual 8086 mode may clobber the
%fs register that we use for the CPU dependent thread local storage
(TLS). Previously the vm86 code would simply restore %fs on exit, but
this doesn't always work. If the thread got unscheduled while running
in virtual 8086 mode and was then rescheduled on a different CPU, the
vm86 exit code would restore the %fs register with the TLS value of
the old CPU, causing anything using TLS in userland to crash later on.
Instead we skip the %fs register restore on exit (as do the other
interrupt return functions) and explicitly update the potentially
clobbered %fs by calling x86_set_tls_context(). This will repopulate
the %fs register with the TLS value for the right CPU. Fixes #8068.

* Made the static set_tls_context() into x86_set_tls_context() and made
it available to others to faciliate the above.

* Sync the vm86 specific interrupt code with the changes from hrev23370,
using the iframe pop macro to properly return. Previously what was
pushed in int_bottom wasn't poped on return.

* Account for the time update macro resetting the in_kernel flag and
reset it to 1, as we aren't actually returning to userland. This
didn't cause any harm though as only the time tracking is using that
flag so far.

* Some minor cleanup.

Merged signals-merge branch into trunk with the following changes:
* Reorganized the kernel locking related to threads and teams.
* We now discriminate correctly between process and thread signals. Signal
handlers have been moved to teams. Fixes #5679.
* Implemented real-time signal support, including signal queuing, SA_SIGINFO
support, sigqueue(), sigwaitinfo(), sigtimedwait(), waitid(), and the addition
of the real-time signal range. Closes #1935 and #2695.
* Gave SIGBUS a separate signal number. Fixes #6704.
* Implemented <time.h> clock and timer support, and fixed/completed alarm() and
[set]itimer(). Closes #5682.
* Implemented support for thread cancellation. Closes #5686.
* Moved send_signal() from <signal.h> to <OS.h>. Fixes #7554.
* Lots over smaller more or less related changes.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42116 a95241bf-73f2-0310-859d-f6bbb57e9c96

Merged the signals branch into trunk, with these changes:
* The team and thread kernel structures have been renamed to Team and Thread
respectively and moved into the new BKernel namespace.
* Several (kernel add-on) sources have been converted from C to C++ since
private kernel headers are included that are no longer C compatible.

Changes after merging:
* Fixed gcc 2 build (warnings mainly in the scary firewire bus manager).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40196 a95241bf-73f2-0310-859d-f6bbb57e9c96

Moved paging related files to new subdirectories paging and paging/32bit.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37060 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Removed i386_translation_map_get_pgdir() and adjusted the one place where it
was used.
* Renamed X86VMTranslationMap to X86VMTranslationMap32Bit and pulled the paging
method agnostic part into new base class X86VMTranslationMap.
* Moved X86PagingStructures into its own header/source pair.
* Moved pgdir_virt from X86PagingStructures to X86PagingStructures32Bit where
it is actually used.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37055 a95241bf-73f2-0310-859d-f6bbb57e9c96

x86:
* Renamed i386_context_switch() to x86_context_switch().
* x86_context_switch() no longer sets the page directory.
arch_thread_context_switch() does that explicitly, now. This allows to solve
the TODO by reordering releasing the previous paging structures reference and
setting the new page directory.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37024 a95241bf-73f2-0310-859d-f6bbb57e9c96

x86:
* Renamed vm_translation_map_arch_info to X86PagingStructures, and all
members and local variables of that type accordingly.
* arch_thread_context_switch(): Added TODO: The still active paging structures
can indeed be deleted before we stop using them.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37022 a95241bf-73f2-0310-859d-f6bbb57e9c96

Consequently use uint32 for the physical page directory address.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37011 a95241bf-73f2-0310-859d-f6bbb57e9c96

* First run through the kernel's private parts to use phys_{addr,size}_t
where appropriate.
* Typedef'ed page_num_t to phys_addr_t and used it in more places in
vm_page.{h,cpp}.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@36937 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved the syscall stuff from arch_commpage.cpp to x86_syscalls.{cpp,h}.
* On context switches we do now set the IA32_MSR_SYSENTER_ESP. This saves us
setting esp at the beginning of x86_sysenter(). More importantly when
entering it in single-step mode, this no longer causes a double fault
(cf. #3487). We still don't handle the resulting debug exception correctly,
so that we still get a (continuable) panic().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35609 a95241bf-73f2-0310-859d-f6bbb57e9c96

Refactored vm_translation_map:
* Pulled the physical page mapping functions out of vm_translation_map into
a new interface VMPhysicalPageMapper.
* Renamed vm_translation_map to VMTranslationMap and made it a proper C++
class. The functions in the operations vector have become methods.
* Added class GenericVMPhysicalPageMapper implementing VMPhysicalPageMapper
as far as possible (without actually writing new code).
* Adjusted the x86 and the PPC specifics accordingly (untested for the
latter). For the other architectures the build is, I'm afraid, seriously
broken.

The next steps will modify and extend the VMTranslationMap interface, so that
it will be possible to fix the bugs in vm_unmap_page[s]() and employ
architecture specific optimizations.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35066 a95241bf-73f2-0310-859d-f6bbb57e9c96

Removed unused <arch>_switch_stack_and_call() and
arch_thread_switch_kstack_and_call().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34971 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved the VM headers into subdirectory vm/.
* Renamed vm_cache.h/vm_address_space.h to VMCache.h/VMAddressSpace.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34449 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved VMAddressSpace definition to vm_address_space.h.
* "Classified" VMAddressSpace, i.e. turned the vm_address_space_*() functions
into methods, made all attributes (but "areas") private, and added
accessors.
* Also turned the vm.cpp functions vm_area_lookup() and
remove_area_from_address_space() into VMAddressSpace methods. The rest of
the area management functionality will follow soon.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34447 a95241bf-73f2-0310-859d-f6bbb57e9c96

Renamed vm_address_space to VMAddressSpace.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34422 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Reverted r32216 (by mmlr): it's not a good idea to access a variable on the
stack after that has just been changed, and does not contain the data one
would assume.
* This fixes the leaking the vm_translation_map_arch_info objects, and thus
bug #4957.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34090 a95241bf-73f2-0310-859d-f6bbb57e9c96

After creating a userland thread we didn't set up the breakpoints for it.
Fixes #4665.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33369 a95241bf-73f2-0310-859d-f6bbb57e9c96

The reference of the currently active translation map shouldn't be released
until the data it protects isn't in active use anymore. Previously it would
release the translation map and therefore the page directory reference while
the page dir was still set on the CPU, as only the actual call to
i386_context_switch() will replace the page directory in the control register.
This didn't cause any harm though, as during the context switch interrupts are
disabled and therefore the page directory would only be deferred_delete()ed and
not directly freed/overwritten. Still this is logically more correct.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32216 a95241bf-73f2-0310-859d-f6bbb57e9c96

User debugger support:
* Generalized address checks. The debugger can now also read the commpage.
* Added new syscall _kern_get_thread_cpu_state() to get the CPU state of a
not running thread. Introduced arch_get_thread_debug_cpu_state() for that
purpose, which is only implemented for x86 ATM (uses the new
i386_get_thread_user_iframe()).
* Don't allow a debugger to change a thread's "esp" anymore. That's the esp
register in the kernel. "user_esp" can still be changed.
* Generally set RF (resume flag) in eflags in interrupt handlers, not only
after a instruction breakpoint debug exception. This should prevent
breakpoints from being triggered more than once (e.g. when the breakpoint is
on an instruction that can cause a page fault). I still saw those with bdb
in VMware, but that might be a VMware bug.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31045 a95241bf-73f2-0310-859d-f6bbb57e9c96

When switching to a kernel thread we no longer set the page directory.
This is not necessary, since userland teams' page directories also
contain the kernel mappings, and avoids unnecessary TLB flushes. To make
that possible the vm_translation_map_arch_info objects are reference
counted now.

This optimization reduces the kernel time of the Haiku build on my
machine with SMP disabled a few percent, but interestingly the total
time decreases only marginally. Haven't tested with SMP yet, but for
full impact CPU affinity would be needed.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28287 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Prefixed memset_physical() and memcpy_to_physical() with "vm_",
added vm_memcpy_from_physical() and vm_memcpy_physical_page(), and
added respective functions to the vm_translation_map operations. The
architecture specific implementation can now decide how to implement
them most efficiently. Added generic implementations that can be used,
though.
* Changed vm_{get,put}_physical_page(). The former no longer accepts
flags (the only flag PHYSICAL_PAGE_DONT_WAIT wasn't needed anymore).
Instead it returns an implementation-specific handle that has to be
passed to the latter. Added vm_{get,put}_physical_page_current_cpu()
and *_debug() variants, that work only for the current CPU,
respectively when in the kernel debugger. Also adjusted the
vm_translation_map operations accordingly.
* Made consequent use of the physical memory operations in the source
tree.
* Also adjusted the m68k and ppc implementations with respect to the
vm_translation_map operation changes, but they are probably broken,
nevertheless.
* For x86 the generic physical page mapper isn't used anymore. It is
suboptimal in any case. For systems with small memory it is too much
overhead, since one can just map the complete physical memory (that's
not done yet, though). For systems with large memory it counteracts
the VM strategy to reuse the least recently used pages. Since those
pages will most likely not be mapped by the page mapper anymore, it
will keep remapping chunks. This was also the reason why building
Haiku in Haiku was significantly faster with only 256 MB RAM (since
that much could be kept mapped all the time).
Now we're using a different strategy: We have small pools of virtual
page slots per CPU that are used for the physical page operations
(memset_physical(), memcpy_*_physical()) with CPU-pinned thread.
Furthermore we have four slots per translation map, which are used to
map page tables.

These changes speed up the Haiku image build in Haiku significantly. On
my Core2 Duo 2.2 GHz 2 GB machine about 40% to 20 min 40 s (KDEBUG
disabled, block cache debug disabled). Still more than factor 3 slower
than FreeBSD and Linux, though.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28244 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Added "from" address space parameter to vm_swap_address_space()/
arch_vm_aspace_swap().
* The x86 implementation does now maintain a bit mask per
vm_translation_map_arch_info indicating on which CPUs the address
space is active. This allows flush_tmap() to avoid ICI for user
address spaces when the team isn't currently running on any other CPU.
In this context ICI is relatively expensive, particularly since we map
most pages via vm_map_page() and therefore invoke flush_tmap() pretty
much for every single page.
This optimization speeds up a "hello world" compilation about 20% on
my machine (KDEBUG turned off, freshly booted), but interestingly it
has virtually no effect on the "-j2" haiku build time.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27912 a95241bf-73f2-0310-859d-f6bbb57e9c96

Simplified x86_next_page_directory().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27904 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added i386_get_current_iframe(), returning the innermost iframe, if any.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27165 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Changed the meaning of the {KERNEL,USER}_STACK_SIZE macros to not
include the guard pages. Adjusted the kernel and boot loader code
accordingly -- the guard pages size is added/not removed respectively.
The stack size passed to _kern_spawn_thread() is now the actually usable
size, and it is no longer possible to specify a size smaller than or
equal to the guard pages size.
* vm_create_anonymous_area(): Precommit two pages maximum -- a stack with
only one page usable size obviously doesn't need two pages.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26819 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Patch by Andreas: we did not store ebp in vregs::ebp, and we did not store
ebx at all.
* This fixes bug #2569.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26818 a95241bf-73f2-0310-859d-f6bbb57e9c96

arch_setup_signal_frame(): panic() if we don't have a user iframe.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26808 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Removed -Wno-unused from all KernelMergeObjects in kernel Jamfiles.
* Fixed most of the warnings resulting from that by removing actually not used
variables or moving declaration into the #IF. Left unused functions there
though, as I wouldn't know if they are supposed to be used again.
* Fixed two statements with no effect (clamping to MAX_ANCILLARY_DATA_LEN in
socket.cpp and unsetting fCounterSem in MessagingService.cpp).
* Some style cleanups.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26253 a95241bf-73f2-0310-859d-f6bbb57e9c96

stippi + bonefish:
* Missing backslash in UPDATE_THREAD_KERNEL_TIME() macro. Caused the
thread's kernel time never to be updated when the thread left the
kernel. The time would be added to the user time instead.
* Changed semantics of thread_at_kernel_exit(). It leaves interrupts
disabled when returning, now. All code using it would disable
interrupts afterwards anyway, and inbetween the thread could be
interrupted causing two more time updates (or actually not causing
them erroneously).
* The code in x86's interrupt handler entry (int_bottom) also checks
thread::in_kernel now, to determine whether the thread was already
considered to be in userland. This is necessary since the sysexit
instruction doesn't reenable interrupts, so that we have to do that
with the preceeding instruction. Hence an interrupt can occur
inbetween, which would incorrectly add the interrupt's kernel time
to the thread's user time.
* For userland threads team_create_thread_start() didn't invoke
thread_at_kernel_exit() or any equivalent. We do that in
arch_thread_enter_userspace() now.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26240 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Jan Klötzke:
* For vm86 mode the kernel stack top is adjusted -> do not rely on the
kernel_stack_base + KERNEL_STACK_SIZE calculation.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25608 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Jan Klötzke:
* In vm86 mode CS will have arbitrary values so we check for both USER_CODE_SEG
and the VM flag in EFLAGS. This is also done when entering interrupt gates.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25607 a95241bf-73f2-0310-859d-f6bbb57e9c96

* For each userland team the kernel creates an area in the userland
address space that is fully locked and marked B_KERNEL_AREA. It can
thus be accessed by the kernel without additional checks.
* For each userland thread we do create a user_thread structure in that
area. The structure is accessible from userland via TLS, using the
private get_user_thread() function.
* Introduced private userland functions [un]defer_signals(). They can be
used to cheaply disable/re-enable signal delivery. They use the
user_thread::defer_signals/pending_signals fields which are
checked/updated by the kernel.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25451 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Fixed warnings, mostly due to NULL changes.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24487 a95241bf-73f2-0310-859d-f6bbb57e9c96

We have to update the pending signals thread flag when restoring the
signal block mask when returning from a signal handler.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24064 a95241bf-73f2-0310-859d-f6bbb57e9c96

gcc4 build fix


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23992 a95241bf-73f2-0310-859d-f6bbb57e9c96

gcc4 build fix


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23991 a95241bf-73f2-0310-859d-f6bbb57e9c96

axeld + bonefish:
* Implemented automatic syscall restarts:
- A syscall can indicate that it has been interrupted and can be
restarted by setting a respective bit in thread::flags. It can
store parameters it wants to be preserved for the restart in
thread::syscall_restart::parameters. Another thread::flags bit
indicates whether it has been restarted.
- handle_signals() clears the restart flag, if the handled signal
has a handler function installed and SA_RESTART is not set. Another
thread flag (THREAD_FLAGS_DONT_RESTART_SYSCALL) can prevent syscalls
from being restarted, even if they could be (not used yet, but we
might want to use it in resume_thread(), so that we stay
behaviorally compatible with BeOS).
- The architecture specific syscall handler restarts the syscall, if
the restart flag is set. Implemented for x86 only.
- Added some support functions in the private <syscall_restart.h> to
simplify the syscall restart code in the syscalls.
- Adjusted all syscalls that can potentially be restarted accordingly.
- _user_ioctl() sets new thread flag THREAD_FLAGS_IOCTL_SYSCALL while
calling the underlying FS's/driver's hook, so that syscall restarts
can also be supported there.
* thread_at_kernel_exit() invokes handle_signals() in a loop now, as
long as the latter indicates that the thread shall be suspended, so
that after waking up signals received in the meantime will be handled
before the thread returns to userland. Adjusted handle_signals()
accordingly -- when encountering a suspending signal we don't check
for further signals.
* Fixed sigsuspend(): Suspending the thread and rescheduling doesn't
result in the correct behavior. Instead we employ a temporary
condition variable and interruptably wait on it. The POSIX test
suite test passes, now.
* Made the switch_sem[_etc]() behavior on interruption consistent.
Depending on when the signal arrived (before the call or when already
waiting) the first semaphore would or wouldn't be released. Now we
consistently release it.
* Refactored _user_{read,write}[v]() syscalls. Use a common function for
either pair. The iovec version doesn't fail anymore, if anything could
be read/written at all. It also checks whether a complete vector
could be read/written, so that we won't skip data, if the underlying
FS/driver couldn't read/write more ATM.
* Some refactoring in the x86 syscall handler: The int 99 and sysenter
handlers use a common subroutine to avoid code duplication.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23983 a95241bf-73f2-0310-859d-f6bbb57e9c96