the thread count need to be accessed atomically.
* Made debugging through exec*() work.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11993 a95241bf-73f2-0310-859d-f6bbb57e9c96
* A new select sync pool entry wasn't really added to the pool.
* More debug output.
* The semaphore created in common_{select,poll}() needs to be created
with count 0, otherwise we won't block.
* A serious race condition remains in common_{select,poll)(). When a
selected FD is closed we can't deselect select events anymore, so
that subsequent notify_select_events() issued by the FS/driver might
write into already free()d memory. A solution would be to get_fd()
the involved FDs and operate directly on them instead of using the
indices. I'm just too lazy to do that now.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11929 a95241bf-73f2-0310-859d-f6bbb57e9c96
now uses this one instead of using map() for every single page - this should
be faster in most cases, and also, more importantly, does not mess up the
map_count counter anymore.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11916 a95241bf-73f2-0310-859d-f6bbb57e9c96
removed unused headers. Adapted sources to still compile with the new
header locations.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11913 a95241bf-73f2-0310-859d-f6bbb57e9c96
be private, as it serves no useful purpose outside of the kernel.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11893 a95241bf-73f2-0310-859d-f6bbb57e9c96
team boundaries; if you didn't actually call close() from within the
application, the close-hook of the file system was never called.
Also, you could close files of other teams (ie. invoke close on a
shared file descriptor).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11892 a95241bf-73f2-0310-859d-f6bbb57e9c96
they are public now, they might become private later on.
It's almost the same as acquire_sem() but allows you to release another semaphore
atomically. This makes condvar implementations and the like very simple to do.
Added B_CHECK_PERMISSION flags to the user calls, although it's not honored yet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11887 a95241bf-73f2-0310-859d-f6bbb57e9c96
and drivers that need to provide special select() support with
managing select notification information.
* Renamed vfs_select.c to *.cpp and fixed the resulting C++ compiler
errors. Added tracing macros.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11886 a95241bf-73f2-0310-859d-f6bbb57e9c96
and free_*_cookie() hooks of the underlying FS were always called
together when the reference count of the FD dropped to zero. When
blocking operations (reading/writing) on the FD were still in progress
this would never happen, though. Now we additionally maintain an open
count and call the close_*() hook when it drops to zero.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11882 a95241bf-73f2-0310-859d-f6bbb57e9c96
is perfectly okay on x86 anyway, but should be moved into the arch stuff).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11869 a95241bf-73f2-0310-859d-f6bbb57e9c96
Should work correctly, although there is a big race condition left when you're
using F_SETLKW. Will be fixed next.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11868 a95241bf-73f2-0310-859d-f6bbb57e9c96
simple cases - it might not work properly though, since we don't know yet if
a cache has children; therefore it will print out a warning as a constant
reminder if used in that way. It will still not work if we would need to
insert a new cache inbetween (in case the cache has children or only read-only
areas (even if there is no way yet to specify how exactly the VM should behave
in this case yet).
Added a comment to vm_map_file() about what we still need to do there.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11751 a95241bf-73f2-0310-859d-f6bbb57e9c96
function publish_vnode(). When calling new_vnode(), the node is only
reserved, but not yet accessible for others. Only when you call
publish_vnode(), it will become available. That simplifies new node
handling/locking considerably.
Note, you don't have to call new_vnode() before publish_vnode(); ie.
publish_vnode() acts exactly like new_vnode() did before if used that
way.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11719 a95241bf-73f2-0310-859d-f6bbb57e9c96
* user_debug_break_or_watchpoint_hit() into separate functions for
break- and watchpoints. The one for breakpoints gets another parameter
which indicates whether the breakpoint was a soft- or hardware
breakpoint. This info is also sent to the debugger.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11714 a95241bf-73f2-0310-859d-f6bbb57e9c96
* No longer kill the time when a page fault occurs, but rather send a
SIGSEGV.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11705 a95241bf-73f2-0310-859d-f6bbb57e9c96
of a signal.
* Added sigaction_etc(). It's just a sigaction() for which the thread
in question can be specified.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11704 a95241bf-73f2-0310-859d-f6bbb57e9c96
not to be notified.
* Added debugger commands for setting/getting of thread signal ignore
masks and signal handlers.
* Renamed user_debug_fault_occurred() to a more correct
user_debug_exception_occurred(). It no longer sends a `stopped' message,
but the new one dedicated to exceptions. Additionally the number of the
signal is supplied that will be sent, when the thread continues (without
indicating to ignore the event).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11703 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added support for debugger handover. The current debugger need to send
a B_DEBUG_MESSAGE_HANDED_OVER message. The rest is completely
transparent to the new debugger. It simply calls install_team_debugger().
* Implemented _user_wait_for_debugger().
* Reworked a few bits to ensure that after a remove_team_debugger() or
after requesting a debugger handover the debugger doesn't get any more
messages.
* When the debugger is removed or dies, the debugged threads should now
cleanup their debug info and continue, instead of waiting at their
debug port forever.
All the new features are not tested. Will happen, when gdb will be
debugged.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11697 a95241bf-73f2-0310-859d-f6bbb57e9c96
(new `flags' parameter, flag B_WAIT_TILL_LOADED). This is the default
behaviour for load_image(), so it behaves like R5's implementation now,
i.e. errors while loading are reported to the caller.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11696 a95241bf-73f2-0310-859d-f6bbb57e9c96
* We no longer notify the debugger about a new image when it is registered,
but when it has been relocated.
* When the application image has been relocated, we notify the one who
initiated its loading.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11694 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also removed team::user_env_base: environment variables are now changed on the app's heap.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11672 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added some musings about what is missing, when a debugger is removed and
how _user_wait_for_debugger() shall be supported.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11636 a95241bf-73f2-0310-859d-f6bbb57e9c96
threadID parameter to spawn_kernel_thread_etc(). It's now possible to
set the ID of a new thread. Used in team.c to make team ID and the ID of
the main thread equal.
Fascinatingly the two added functions prompt my compiler to issue
`missing prototype' warnings, although those are obviously there. It would
be nice if someone could solve that riddle.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11621 a95241bf-73f2-0310-859d-f6bbb57e9c96
a previous and unfinished transaction. It should now work correctly.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11553 a95241bf-73f2-0310-859d-f6bbb57e9c96
