Support building images for x86_64.

Added a temporary Haiku64Image file that gets included instead of
HaikuImage when building for x86_64, which I will add to as I port
stuff. Images currently only include the boot loader, kernel and
a bunch of add-ons.

Fixed a copy&paste typo in trace.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@38835 a95241bf-73f2-0310-859d-f6bbb57e9c96

* added forkpty() and login_tty() to bsd compatibility, a test for forkpty().
* added a TODO questioning the closing master and slave in openpty() when applying window size fails.
* added TIOCSCTTY as a TTY ioctl code, the caller become controlling TTY. Review comments are welcome.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@36105 a95241bf-73f2-0310-859d-f6bbb57e9c96

* The usual cleanup behind mmu_man ;-)


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35999 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix tracing code.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35989 a95241bf-73f2-0310-859d-f6bbb57e9c96

Implemented ioctl(FIONREAD) on tty devices. Untested.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35960 a95241bf-73f2-0310-859d-f6bbb57e9c96

Reverted unnecessary part of r35433.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35758 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fixed warning.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35586 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Always reset the requests in WriterLocker::AcquireWriter() and
ReaderLocker::AcquireReader() before starting to wait. This could lead to
busy waiting in loops in certain situations.
* Got rid of the ReaderLocker::AcquireReader(bool) version to avoid confusion.
* Cleaned up and fixed the code introduced in r25408 (VMIN, VTIME support):
- Gave the second ReaderLocker::AcquireReader() parameter the same name as
the corresponding one of WriterLocker::AcquireWriter() and fixed its weird
semantics (one less than the desired number of bytes -- huh?). Since it was
not set on the request, it didn't work correctly anyway.
- tty_input_read(): The O_NONBLOCK return code was broken. It returned B_OK
instead of B_WOULD_BLOCK. The O_NONBLOCK mode overrides VMIN/VTIME now.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35580 a95241bf-73f2-0310-859d-f6bbb57e9c96

RequestOwner::Wait(): No need to publish the condition variable.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35574 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fixed various errors/warnings reported by cppcheck:
* memory leaks
* resource leaks
* added const's to getters
* removed a few reundant conditions


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35433 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Cleanup, no functional change.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34142 a95241bf-73f2-0310-859d-f6bbb57e9c96

Don't perform input processing when writing to the slave end (output written to
terminal was interpreted like input). Fixes #2409.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31417 a95241bf-73f2-0310-859d-f6bbb57e9c96

* tty_select() did not check for ICANON and therefore notified the select
listeners immediately if there was already something in the queue. Factored
out a tty_readable() out of tty_notify_if_available() that tty_select()
now uses.
* This fixes bug #3148.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28687 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Already set tty::lock() in init_driver(). This makes it always safe to
be used.
* Added tty::ref_count. Each cookie keeps a reference. Only when a
cookie is freed the reference is surrendered. A tty is considered used
as long as it is still referenced. This allows to access a tty through
the cookie, even if it already has been closed.
* Fixed tty_deselect(). It was keeping registered select events when
called after the cookie has been closed. The referenced select_sync
structure would become invalid and later attempts to send select
notifications for the tty could crash. Fixes #3126.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28651 a95241bf-73f2-0310-859d-f6bbb57e9c96

shut up complaining for something not even Linux supports.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28267 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix problem with openssh failing to connect to OpenSolaris and Zeta servers:
* we need to initialize c_ospeed and c_ispeed, as a value of 0 means
'hangup' - which is not a good default, I suppose


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26426 a95241bf-73f2-0310-859d-f6bbb57e9c96

* The VERASE char (the one generated by backspace) is 0x7f.
* With output processing enabled, replace the VERASE char by
BS SPACE BS instead of VERASE SPACE VERASE.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26135 a95241bf-73f2-0310-859d-f6bbb57e9c96

axeld + bonefish:
Changed condition variables so that it is allowed to block (e.g. lock
mutexes etc.) between Add() and Wait(). This fixes #2059, since the
block writer used them this way and could thusly fail to wait for a
condition variable, causing a temporary stack object to be used past its
lifetime.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25525 a95241bf-73f2-0310-859d-f6bbb57e9c96

- dump termios struct for ttys
- implement VMIN & VTIME, at least it seems to work but it's 4am and it's overly weird, so please review.
See http://man.cx/termios and http://www.unixwiz.net/techtips/termios-vmin-vtime.html .


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25408 a95241bf-73f2-0310-859d-f6bbb57e9c96

- dump winsize info too.
- prepare for VTIME and VMIN handling: allow waiting with timeout.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25405 a95241bf-73f2-0310-859d-f6bbb57e9c96

- mark BeOS-specific ioctls we support for legacy apps,
- add 'wsiz' which is a private alias for TIOCSWINSZ,
- add some we might want to implement (or not) as reminder,
- add hw signal ioctls with a note for later (call driver service func),
- implement 'ichr' undocumented ioctl that waits on N chars on input, this fixes behaviour of rhapsody IRC client and many other curses apps. Oddly it seems even our own curses still uses it, that should likely be fixed as we support select(). But we must keep this one in to support apps that have their own curses lib.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25400 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix a warning, print the pointer to the mutex instead of implying a cast of the address of the pointer to an int.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25339 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Removed old mutex implementation and renamed cutex to mutex.
* Trivial adjustments of code using mutexes. Mostly removing the
mutex_init() return value check.
* Added mutex_lock_threads_locked(), which is called with the threads
spinlock being held. The spinlock is released while waiting, of
course. This function is useful in cases where the existence of the
mutex object is ensured by holding the threads spinlock.
* Changed the two instances in the VFS code where an IO context of
another team needs to be locked to use mutex_lock_threads_locked().
Before it required a semaphore-based mutex implementation.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25283 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Set reasonable terminal flag defaults. This makes telnetd fully usable
again.
* Publish /dev/ptmx. Opening it will open a fresh pty master. In
principle /dev/pt/ is obsolete now, but I guess we keep it around for
compatibility with BeOS. Though there shouldn't be many applications
opening a pty, that we might be interested in...
* New ioctls B_IOCTL_GET_TTY_INDEX (returns the tty index) and
B_IOCTL_GRANT_TTY (grants tty slave access rights).



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25133 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Detemplatized ConditionVariable{Entry}. Merged them with their
respective Private* base class.
* Changed sigwait() and sigsuspend() to use thread_block() instead of a
condition variable.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25100 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Introduced a set of functions (thread_prepare_to_block(),
thread_block(), thread_unblock(),...) that allow a thread to wait for
something without needing a semaphore or condition variable. It can
simply block and another thread can unblock it. Supports timeouts and
interrupting. Both semaphores and condition variables use this
common mechanism, now.
* Semaphores:
- Some simplifications due to the thread blocking mechanism.
- Changed locking order to sem -> thread. It was the other way around
before and when introducing the wait_for_objects() support I had
also introduced a situation where the locking was reverse, which
could potentially cause a dead lock on SMP systems.
- Instead of queueing thread structures, a semaphore queues
queued_thread entries now, which are created on the stack. The
thread::sem structure could thus be removed.
- Added sem_entry::net_count, which is sem_entry::count plus the
acquisition count of all waiting threads. This number is needed in
remove_thread_from_sem() and instead of computing it there we
maintain it.
- Fixed remove_thread_from_sem(). It would not unblock threads, if
the sem count was <= 0.
- Made sem::last_acquirer unconditional. It is actually needed for
sem_info::latest_holder. Fixed fill_sem_info() accordingly.
- Added some optional tracing output, though only via ktrace_printf().
* Condition variables:
- Could be simplified significantly through the use of the thread
blocking mechanism. Removed a good deal of unnecessary code.
- Moved the ConditionVariableEntry "flags" parameter from Wait() to
Add(), and adjusted all places where condition variables are used
accordingly.
* snooze() uses thread_block_with_timeout() instead of a semaphore.
* Simplified thread interrupting in the signal and user debugger code.
Instead of separate functions for threads waiting on a semaphore or
condititon variable, we only have a single thread_interrupt(), now.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25099 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Don't check the open count of the other tty anymore when acquiring a
reference. The places where that is of relevance do that anyway, and
tty_ioctl(), where it isn't, failed before, although that was not
necessary. This prevented for instance ioctls() on the master tty
before any slave had been opened.
* If the tty has no process group set, don't check for background reads.
This was a problem with telnetd, respectively the executed login,
which couldn't access the tty, since telnetd makes sure neither itself
nor login has a controlling tty.
telnet still doesn't work, exactly because it has no controlling tty
and cannot set the tty process group. Not sure how that is supposed to
work. Furthermore the tty doesn't have the usual flags set, which is
apparrently the reason for the workaround (read_string()) in login.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25038 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Added debugger command "tty", which dumps some info about a tty.
* RequestOwner was removing the wrong request from the second queue,
which could cause the list structure to become invalid and result in
bug #1526.
* In the writer loops we do now call tty_notify_if_available() when
we're potentially going to wait and had written something before, so
that a waiting reader will be woken up also when we write more bytes
than fit into the ring buffer.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22421 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Renamed fs/vfs_select.cpp to wait_for_objects.cpp and got rid of
vfs_select.h, respectively moved most of it into the new kernel
private header wait_for_objects.h.
* Added new experimental API functions wait_for_objects[_etc](). They
work pretty much like poll(), but also for semaphores, ports, and
threads.
* Removed the "ref" parameter from notify_select_events() and the
select_sync_pool functions as well as from fd_ops::fd_[de]select(). It
is no longer needed. The FS interface select() hook still has it,
though -- the VFS will always pass 0.
* de]select_fd() take a select_info* instead of a select_sync* + ref
pair, now. Added respective functions for semaphores, ports, and
threads.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22416 a95241bf-73f2-0310-859d-f6bbb57e9c96

Moved the select_sync_pool from tty_cookie to tty. No need to have one
per cookie.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22392 a95241bf-73f2-0310-859d-f6bbb57e9c96

Notifying readers and select() takes canonical input processing into
account when checking for the number of readable bytes. For readers
it doesn't make a difference, since they were looping anyway, but
select() would report read-availability incorrectly.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22379 a95241bf-73f2-0310-859d-f6bbb57e9c96

* When canonical input processing is enabled reads should only return
anything, if a line is available. Fixes bug #1483.
* Replaced the request owner waiting semaphore by a condition variable
and removed the now no longer needed SemaphorePool.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22357 a95241bf-73f2-0310-859d-f6bbb57e9c96

* We store the ID of the controlling terminal and the foreground process
group ID with the session and let the terminal update them.
* Added an "orphaned" flag to the process_group structure and code to
maintain it.
* Handle the death of a controlling process correctly: The
foreground process group gets a SIGHUP and all newly-orphaned process
groups containing at least one stopped processes are sent
SIGHUP+SIGCONT.
* The tty handles the O_NOCTTY flag correctly, now.
* The tty handles reads/writes from processes from other sessions
correctly, now.
* Handle tcsetpgrp() from background processes correctly.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22187 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Send SIGTTIN/SIGTTOU when a background process tries to read
from/write to a tty.
* Send SIGTSTP when the suspend character is typed.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22064 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved members pgrp_id, termios, window_size from the tty structure to
the new structure tty_settings of which there's only one instance per
master/slave tty pair. Previously the existence of two instances of those
members caused several kinds of problems, e.g. the Terminal setting
the window size on the master and CLI programs readings the unchanged
values from the slave. E.g. less correctly adjusts the display when the
Terminal size changes, now.
* Reorganized writing to a TTY. We do no longer handle writes to master
and slave the same way. Writes to the master are "input" and need to
be processed differently from writes to the slave ("output"). Before,
both were processed first as output then as input, which caused incorrect
behavior. E.g. CRs were not echoed correctly.
* Added canonical ERASE (backspace) and KILL (clear line) processing.
Couldn't really see it work. glibc's fgets() seems to read single
chars, so that we never have anything in the line buffer.
* Added handling for EOF. Works well with Be's Terminal, ours seems to
write an ESC sequence instead of the EOF char (Ctrl-D), though.
* Extended output processing support (ECHOE, ECHOK, ECHONL, OCRNL,
ONLRET, OLCUC).
* Writes use user_memcpy() now.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@21735 a95241bf-73f2-0310-859d-f6bbb57e9c96

adding default value for suspend key : CTRL(Z)


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@18940 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Changed type of "bytesNeeded" to size_t whereever it's used.
* Minor cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@17491 a95241bf-73f2-0310-859d-f6bbb57e9c96

AcquireWriter() could succeed without fulfilling the bytesNeeded acquirement.
This fixes bug #477.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@17490 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fixed an endless loop in tty_write_to_tty() that happened if there was not enough
space left to write a '\r\n'. This fixes bug #80 and probably bug #477, too.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@17479 a95241bf-73f2-0310-859d-f6bbb57e9c96

A TTY now refuses read/write requests while the other end is dead; it also
notified the other end when it has been closed. This fixes bug #388.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16965 a95241bf-73f2-0310-859d-f6bbb57e9c96

get_tty_index() did not work correctly, this fixes bug #265 (included the fixed
version, thanks barber).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16624 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Dealt with (hopefully) all open/close race conditions.
* Implemented unblocking of pending operations when closing a cookie.
Needed to change the simple one reader semaphore, one writer
semaphore strategy for blocking to a request queue based approach
(otherwise unblocking would have been really hairy).
* Implemented select() support.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11931 a95241bf-73f2-0310-859d-f6bbb57e9c96

Turned off debugging.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10675 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added a temporary work-around for the doubled shell prompt.
Added some missing return values.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10309 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added some more debug output.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9715 a95241bf-73f2-0310-859d-f6bbb57e9c96

tty_write_to_tty() used the wrong TTY to look at the ECHO flag; also added
a comment that explains why the other TTY has to be chosen there.
Improved debug output.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9698 a95241bf-73f2-0310-859d-f6bbb57e9c96

WriterLocker mixed up source and target and always locked the wrong one.
tty_write_to_tty() now takes the extra character into account that may be
inserted with OPOST and ONLCR and don't write more characters as there is
space.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9151 a95241bf-73f2-0310-859d-f6bbb57e9c96

tty_input_read() was blocking until the whole buffer could be filled - that's
not really standard behaviour...
tty_input_putc() now also releases the reader semaphore if that hasn't been
done before.
tty_input_putc_locked() now does character processing and sends some signals -
not yet complete, though, especially VERASE and VKILL do nothing right now.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9109 a95241bf-73f2-0310-859d-f6bbb57e9c96

Work in progress. Basic data exchange seems to work.
Only slightly tested (moved data to and from pty <-> tty).


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9087 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added the beginnings of our TTY layer.
After having had a look at our own Terminal code (former MuTerm), I even
copied the original mess in /dev/tt/ and /dev/pt/.
The /dev/tt/ entries could be created and removed on demand, though, but
that can't be done yet.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9041 a95241bf-73f2-0310-859d-f6bbb57e9c96

Support building images for x86_64.

Added a temporary Haiku64Image file that gets included instead of
HaikuImage when building for x86_64, which I will add to as I port
stuff. Images currently only include the boot loader, kernel and
a bunch of add-ons.

Fixed a copy&paste typo in trace.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@38835 a95241bf-73f2-0310-859d-f6bbb57e9c96

* added forkpty() and login_tty() to bsd compatibility, a test for forkpty().
* added a TODO questioning the closing master and slave in openpty() when applying window size fails.
* added TIOCSCTTY as a TTY ioctl code, the caller become controlling TTY. Review comments are welcome.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@36105 a95241bf-73f2-0310-859d-f6bbb57e9c96

* The usual cleanup behind mmu_man ;-)


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35999 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix tracing code.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35989 a95241bf-73f2-0310-859d-f6bbb57e9c96

Implemented ioctl(FIONREAD) on tty devices. Untested.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35960 a95241bf-73f2-0310-859d-f6bbb57e9c96

Reverted unnecessary part of r35433.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35758 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fixed warning.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35586 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Always reset the requests in WriterLocker::AcquireWriter() and
ReaderLocker::AcquireReader() before starting to wait. This could lead to
busy waiting in loops in certain situations.
* Got rid of the ReaderLocker::AcquireReader(bool) version to avoid confusion.
* Cleaned up and fixed the code introduced in r25408 (VMIN, VTIME support):
- Gave the second ReaderLocker::AcquireReader() parameter the same name as
the corresponding one of WriterLocker::AcquireWriter() and fixed its weird
semantics (one less than the desired number of bytes -- huh?). Since it was
not set on the request, it didn't work correctly anyway.
- tty_input_read(): The O_NONBLOCK return code was broken. It returned B_OK
instead of B_WOULD_BLOCK. The O_NONBLOCK mode overrides VMIN/VTIME now.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35580 a95241bf-73f2-0310-859d-f6bbb57e9c96

RequestOwner::Wait(): No need to publish the condition variable.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35574 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fixed various errors/warnings reported by cppcheck:
* memory leaks
* resource leaks
* added const's to getters
* removed a few reundant conditions


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35433 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Cleanup, no functional change.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34142 a95241bf-73f2-0310-859d-f6bbb57e9c96

Don't perform input processing when writing to the slave end (output written to
terminal was interpreted like input). Fixes #2409.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31417 a95241bf-73f2-0310-859d-f6bbb57e9c96

* tty_select() did not check for ICANON and therefore notified the select
listeners immediately if there was already something in the queue. Factored
out a tty_readable() out of tty_notify_if_available() that tty_select()
now uses.
* This fixes bug #3148.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28687 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Already set tty::lock() in init_driver(). This makes it always safe to
be used.
* Added tty::ref_count. Each cookie keeps a reference. Only when a
cookie is freed the reference is surrendered. A tty is considered used
as long as it is still referenced. This allows to access a tty through
the cookie, even if it already has been closed.
* Fixed tty_deselect(). It was keeping registered select events when
called after the cookie has been closed. The referenced select_sync
structure would become invalid and later attempts to send select
notifications for the tty could crash. Fixes #3126.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28651 a95241bf-73f2-0310-859d-f6bbb57e9c96

shut up complaining for something not even Linux supports.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28267 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix problem with openssh failing to connect to OpenSolaris and Zeta servers:
* we need to initialize c_ospeed and c_ispeed, as a value of 0 means
'hangup' - which is not a good default, I suppose


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26426 a95241bf-73f2-0310-859d-f6bbb57e9c96

* The VERASE char (the one generated by backspace) is 0x7f.
* With output processing enabled, replace the VERASE char by
BS SPACE BS instead of VERASE SPACE VERASE.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26135 a95241bf-73f2-0310-859d-f6bbb57e9c96

axeld + bonefish:
Changed condition variables so that it is allowed to block (e.g. lock
mutexes etc.) between Add() and Wait(). This fixes #2059, since the
block writer used them this way and could thusly fail to wait for a
condition variable, causing a temporary stack object to be used past its
lifetime.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25525 a95241bf-73f2-0310-859d-f6bbb57e9c96

- dump termios struct for ttys
- implement VMIN & VTIME, at least it seems to work but it's 4am and it's overly weird, so please review.
See http://man.cx/termios and http://www.unixwiz.net/techtips/termios-vmin-vtime.html .


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25408 a95241bf-73f2-0310-859d-f6bbb57e9c96

- dump winsize info too.
- prepare for VTIME and VMIN handling: allow waiting with timeout.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25405 a95241bf-73f2-0310-859d-f6bbb57e9c96

- mark BeOS-specific ioctls we support for legacy apps,
- add 'wsiz' which is a private alias for TIOCSWINSZ,
- add some we might want to implement (or not) as reminder,
- add hw signal ioctls with a note for later (call driver service func),
- implement 'ichr' undocumented ioctl that waits on N chars on input, this fixes behaviour of rhapsody IRC client and many other curses apps. Oddly it seems even our own curses still uses it, that should likely be fixed as we support select(). But we must keep this one in to support apps that have their own curses lib.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25400 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix a warning, print the pointer to the mutex instead of implying a cast of the address of the pointer to an int.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25339 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Removed old mutex implementation and renamed cutex to mutex.
* Trivial adjustments of code using mutexes. Mostly removing the
mutex_init() return value check.
* Added mutex_lock_threads_locked(), which is called with the threads
spinlock being held. The spinlock is released while waiting, of
course. This function is useful in cases where the existence of the
mutex object is ensured by holding the threads spinlock.
* Changed the two instances in the VFS code where an IO context of
another team needs to be locked to use mutex_lock_threads_locked().
Before it required a semaphore-based mutex implementation.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25283 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Set reasonable terminal flag defaults. This makes telnetd fully usable
again.
* Publish /dev/ptmx. Opening it will open a fresh pty master. In
principle /dev/pt/ is obsolete now, but I guess we keep it around for
compatibility with BeOS. Though there shouldn't be many applications
opening a pty, that we might be interested in...
* New ioctls B_IOCTL_GET_TTY_INDEX (returns the tty index) and
B_IOCTL_GRANT_TTY (grants tty slave access rights).



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25133 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Detemplatized ConditionVariable{Entry}. Merged them with their
respective Private* base class.
* Changed sigwait() and sigsuspend() to use thread_block() instead of a
condition variable.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25100 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Introduced a set of functions (thread_prepare_to_block(),
thread_block(), thread_unblock(),...) that allow a thread to wait for
something without needing a semaphore or condition variable. It can
simply block and another thread can unblock it. Supports timeouts and
interrupting. Both semaphores and condition variables use this
common mechanism, now.
* Semaphores:
- Some simplifications due to the thread blocking mechanism.
- Changed locking order to sem -> thread. It was the other way around
before and when introducing the wait_for_objects() support I had
also introduced a situation where the locking was reverse, which
could potentially cause a dead lock on SMP systems.
- Instead of queueing thread structures, a semaphore queues
queued_thread entries now, which are created on the stack. The
thread::sem structure could thus be removed.
- Added sem_entry::net_count, which is sem_entry::count plus the
acquisition count of all waiting threads. This number is needed in
remove_thread_from_sem() and instead of computing it there we
maintain it.
- Fixed remove_thread_from_sem(). It would not unblock threads, if
the sem count was <= 0.
- Made sem::last_acquirer unconditional. It is actually needed for
sem_info::latest_holder. Fixed fill_sem_info() accordingly.
- Added some optional tracing output, though only via ktrace_printf().
* Condition variables:
- Could be simplified significantly through the use of the thread
blocking mechanism. Removed a good deal of unnecessary code.
- Moved the ConditionVariableEntry "flags" parameter from Wait() to
Add(), and adjusted all places where condition variables are used
accordingly.
* snooze() uses thread_block_with_timeout() instead of a semaphore.
* Simplified thread interrupting in the signal and user debugger code.
Instead of separate functions for threads waiting on a semaphore or
condititon variable, we only have a single thread_interrupt(), now.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25099 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Don't check the open count of the other tty anymore when acquiring a
reference. The places where that is of relevance do that anyway, and
tty_ioctl(), where it isn't, failed before, although that was not
necessary. This prevented for instance ioctls() on the master tty
before any slave had been opened.
* If the tty has no process group set, don't check for background reads.
This was a problem with telnetd, respectively the executed login,
which couldn't access the tty, since telnetd makes sure neither itself
nor login has a controlling tty.
telnet still doesn't work, exactly because it has no controlling tty
and cannot set the tty process group. Not sure how that is supposed to
work. Furthermore the tty doesn't have the usual flags set, which is
apparrently the reason for the workaround (read_string()) in login.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25038 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Added debugger command "tty", which dumps some info about a tty.
* RequestOwner was removing the wrong request from the second queue,
which could cause the list structure to become invalid and result in
bug #1526.
* In the writer loops we do now call tty_notify_if_available() when
we're potentially going to wait and had written something before, so
that a waiting reader will be woken up also when we write more bytes
than fit into the ring buffer.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22421 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Renamed fs/vfs_select.cpp to wait_for_objects.cpp and got rid of
vfs_select.h, respectively moved most of it into the new kernel
private header wait_for_objects.h.
* Added new experimental API functions wait_for_objects[_etc](). They
work pretty much like poll(), but also for semaphores, ports, and
threads.
* Removed the "ref" parameter from notify_select_events() and the
select_sync_pool functions as well as from fd_ops::fd_[de]select(). It
is no longer needed. The FS interface select() hook still has it,
though -- the VFS will always pass 0.
* de]select_fd() take a select_info* instead of a select_sync* + ref
pair, now. Added respective functions for semaphores, ports, and
threads.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22416 a95241bf-73f2-0310-859d-f6bbb57e9c96

Moved the select_sync_pool from tty_cookie to tty. No need to have one
per cookie.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22392 a95241bf-73f2-0310-859d-f6bbb57e9c96

Notifying readers and select() takes canonical input processing into
account when checking for the number of readable bytes. For readers
it doesn't make a difference, since they were looping anyway, but
select() would report read-availability incorrectly.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22379 a95241bf-73f2-0310-859d-f6bbb57e9c96

* When canonical input processing is enabled reads should only return
anything, if a line is available. Fixes bug #1483.
* Replaced the request owner waiting semaphore by a condition variable
and removed the now no longer needed SemaphorePool.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22357 a95241bf-73f2-0310-859d-f6bbb57e9c96

* We store the ID of the controlling terminal and the foreground process
group ID with the session and let the terminal update them.
* Added an "orphaned" flag to the process_group structure and code to
maintain it.
* Handle the death of a controlling process correctly: The
foreground process group gets a SIGHUP and all newly-orphaned process
groups containing at least one stopped processes are sent
SIGHUP+SIGCONT.
* The tty handles the O_NOCTTY flag correctly, now.
* The tty handles reads/writes from processes from other sessions
correctly, now.
* Handle tcsetpgrp() from background processes correctly.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22187 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Send SIGTTIN/SIGTTOU when a background process tries to read
from/write to a tty.
* Send SIGTSTP when the suspend character is typed.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22064 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Moved members pgrp_id, termios, window_size from the tty structure to
the new structure tty_settings of which there's only one instance per
master/slave tty pair. Previously the existence of two instances of those
members caused several kinds of problems, e.g. the Terminal setting
the window size on the master and CLI programs readings the unchanged
values from the slave. E.g. less correctly adjusts the display when the
Terminal size changes, now.
* Reorganized writing to a TTY. We do no longer handle writes to master
and slave the same way. Writes to the master are "input" and need to
be processed differently from writes to the slave ("output"). Before,
both were processed first as output then as input, which caused incorrect
behavior. E.g. CRs were not echoed correctly.
* Added canonical ERASE (backspace) and KILL (clear line) processing.
Couldn't really see it work. glibc's fgets() seems to read single
chars, so that we never have anything in the line buffer.
* Added handling for EOF. Works well with Be's Terminal, ours seems to
write an ESC sequence instead of the EOF char (Ctrl-D), though.
* Extended output processing support (ECHOE, ECHOK, ECHONL, OCRNL,
ONLRET, OLCUC).
* Writes use user_memcpy() now.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@21735 a95241bf-73f2-0310-859d-f6bbb57e9c96

adding default value for suspend key : CTRL(Z)


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@18940 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Changed type of "bytesNeeded" to size_t whereever it's used.
* Minor cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@17491 a95241bf-73f2-0310-859d-f6bbb57e9c96

AcquireWriter() could succeed without fulfilling the bytesNeeded acquirement.
This fixes bug #477.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@17490 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fixed an endless loop in tty_write_to_tty() that happened if there was not enough
space left to write a '\r\n'. This fixes bug #80 and probably bug #477, too.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@17479 a95241bf-73f2-0310-859d-f6bbb57e9c96

A TTY now refuses read/write requests while the other end is dead; it also
notified the other end when it has been closed. This fixes bug #388.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16965 a95241bf-73f2-0310-859d-f6bbb57e9c96

get_tty_index() did not work correctly, this fixes bug #265 (included the fixed
version, thanks barber).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16624 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Dealt with (hopefully) all open/close race conditions.
* Implemented unblocking of pending operations when closing a cookie.
Needed to change the simple one reader semaphore, one writer
semaphore strategy for blocking to a request queue based approach
(otherwise unblocking would have been really hairy).
* Implemented select() support.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11931 a95241bf-73f2-0310-859d-f6bbb57e9c96

Turned off debugging.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10675 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added a temporary work-around for the doubled shell prompt.
Added some missing return values.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10309 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added some more debug output.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9715 a95241bf-73f2-0310-859d-f6bbb57e9c96

tty_write_to_tty() used the wrong TTY to look at the ECHO flag; also added
a comment that explains why the other TTY has to be chosen there.
Improved debug output.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9698 a95241bf-73f2-0310-859d-f6bbb57e9c96

WriterLocker mixed up source and target and always locked the wrong one.
tty_write_to_tty() now takes the extra character into account that may be
inserted with OPOST and ONLCR and don't write more characters as there is
space.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9151 a95241bf-73f2-0310-859d-f6bbb57e9c96

tty_input_read() was blocking until the whole buffer could be filled - that's
not really standard behaviour...
tty_input_putc() now also releases the reader semaphore if that hasn't been
done before.
tty_input_putc_locked() now does character processing and sends some signals -
not yet complete, though, especially VERASE and VKILL do nothing right now.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9109 a95241bf-73f2-0310-859d-f6bbb57e9c96

Work in progress. Basic data exchange seems to work.
Only slightly tested (moved data to and from pty <-> tty).


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9087 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added the beginnings of our TTY layer.
After having had a look at our own Terminal code (former MuTerm), I even
copied the original mess in /dev/tt/ and /dev/pt/.
The /dev/tt/ entries could be created and removed on demand, though, but
that can't be done yet.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@9041 a95241bf-73f2-0310-859d-f6bbb57e9c96