History log of /haiku-fatelf/src/bin/gdb/gdb/haiku-nat.c
Revision Date Author Comments
# a15a38c1 11-Dec-2011 Michael Lotz <mmlr@mlotz.ch>

Fix use after free. CID 10567.


# 1e525344 23-Feb-2009 Ingo Weinhold <ingo_weinhold@gmx.de>

* Automatic white-space cleanup.
* Handle the new B_DEBUGGER_MESSAGE_HANDED_OVER and pick the "causing thread"
as our first victim. Fixes #2956.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29303 a95241bf-73f2-0310-859d-f6bbb57e9c96


# b74ede5b 10-Aug-2008 Philippe Houdoin <philippe.houdoin@gmail.com>

Fixed a typo. Structs debug_image_created and debug_image_deleted are today identical,
but better not assume they're.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26916 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 7baddcf9 28-Jan-2006 Ingo Weinhold <ingo_weinhold@gmx.de>

Added TODOs regarding gdb blocking in some situations (e.g. on
"info threads" when one of the team's threads is waiting
uninterruptably on a semaphore).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16133 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 66d1795a 04-Nov-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

Explicitly load symbols from libraries after loading a program. gdb
doesn't work quite well when symbols are not loaded -- e.g. stack crawls
are usually broken. Also stack crawls ending in a syscall work. gdb can
deal well enough with frameless function, which I realized, of course,
only after writing code for explicitly supporting syscall functions.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14680 a95241bf-73f2-0310-859d-f6bbb57e9c96


# e2bc2d6a 03-Nov-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

* We do now filter the debug nub thread out of the list of threads.
* When being asked for a thread's CPU state, we stop the thread now. Not
sure, if that is as it is supposed to work, but I don't see any other
way. A side effect is that "info threads" will stop all threads.
Another side effect is, that switching between threads should now work
properly. Unless there is another problem, I'm not aware of, that is.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14663 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 6ff2656c 19-Jul-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

* We now use libdebug.so, which saves us a couple lines of code.
* Print the debugger message in case the debugged team called debugger(),
and the description of an occurred exception respectively.
* Properly keep gdb's internal thread list up to date. This fixes the
problem that an attached debugger always resumed all threads of the
debugged team.
* A bit of cleanup of the attaching code.

Discovered an ugly bug: When invoking gdb with an executable -- regardless
of whether attaching gdb to a running process or just starting a debugger
session with the executable -- the executable is modified. I tested with
"crashing_app" and in the second debug session gdb fails to read the debug
info from the file and encounters a weird error when closing the file:
"No space left on device." I have the suspicion that this is another bug
in Axel's VM/file cache pet. :-P



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13775 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 2ee6ee5b 19-Jul-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

Added TODO.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13761 a95241bf-73f2-0310-859d-f6bbb57e9c96


# ffe68e41 25-Mar-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

Generic and i386 specific Haiku native and target debugger support.
The target debugger won't work though, since quite a bit of code
would need to be moved from the native support files to those for
the target support. But that's not that important at the moment, since
we're mainly want a native debugger.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12027 a95241bf-73f2-0310-859d-f6bbb57e9c96


# a15a38c104f805851a69b7a932ea597bee86202e 11-Dec-2011 Michael Lotz <mmlr@mlotz.ch>

Fix use after free. CID 10567.


# 1e525344d6a8cbb374a2a0185879a0b8cca6e467 23-Feb-2009 Ingo Weinhold <ingo_weinhold@gmx.de>

* Automatic white-space cleanup.
* Handle the new B_DEBUGGER_MESSAGE_HANDED_OVER and pick the "causing thread"
as our first victim. Fixes #2956.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29303 a95241bf-73f2-0310-859d-f6bbb57e9c96


# b74ede5b2ce28a0430bcf0d64b4840503d17c5fe 10-Aug-2008 Philippe Houdoin <philippe.houdoin@gmail.com>

Fixed a typo. Structs debug_image_created and debug_image_deleted are today identical,
but better not assume they're.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26916 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 7baddcf950506d77792b595023716ba95c7d8afb 28-Jan-2006 Ingo Weinhold <ingo_weinhold@gmx.de>

Added TODOs regarding gdb blocking in some situations (e.g. on
"info threads" when one of the team's threads is waiting
uninterruptably on a semaphore).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16133 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 66d1795a8631ea14e5ca9fa183a81b92c8b66685 04-Nov-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

Explicitly load symbols from libraries after loading a program. gdb
doesn't work quite well when symbols are not loaded -- e.g. stack crawls
are usually broken. Also stack crawls ending in a syscall work. gdb can
deal well enough with frameless function, which I realized, of course,
only after writing code for explicitly supporting syscall functions.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14680 a95241bf-73f2-0310-859d-f6bbb57e9c96


# e2bc2d6a6736c64da95ba412f7e65008396a44e6 03-Nov-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

* We do now filter the debug nub thread out of the list of threads.
* When being asked for a thread's CPU state, we stop the thread now. Not
sure, if that is as it is supposed to work, but I don't see any other
way. A side effect is that "info threads" will stop all threads.
Another side effect is, that switching between threads should now work
properly. Unless there is another problem, I'm not aware of, that is.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14663 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 6ff2656c03cd3ec6d773ff7d2684074b5cb63a0c 19-Jul-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

* We now use libdebug.so, which saves us a couple lines of code.
* Print the debugger message in case the debugged team called debugger(),
and the description of an occurred exception respectively.
* Properly keep gdb's internal thread list up to date. This fixes the
problem that an attached debugger always resumed all threads of the
debugged team.
* A bit of cleanup of the attaching code.

Discovered an ugly bug: When invoking gdb with an executable -- regardless
of whether attaching gdb to a running process or just starting a debugger
session with the executable -- the executable is modified. I tested with
"crashing_app" and in the second debug session gdb fails to read the debug
info from the file and encounters a weird error when closing the file:
"No space left on device." I have the suspicion that this is another bug
in Axel's VM/file cache pet. :-P



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13775 a95241bf-73f2-0310-859d-f6bbb57e9c96


# 2ee6ee5b8c1b225f5cea4afd60aa89c519db70cd 19-Jul-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

Added TODO.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13761 a95241bf-73f2-0310-859d-f6bbb57e9c96


# ffe68e41fba151c799ac2c43de1472f1c4e07c2f 25-Mar-2005 Ingo Weinhold <ingo_weinhold@gmx.de>

Generic and i386 specific Haiku native and target debugger support.
The target debugger won't work though, since quite a bit of code
would need to be moved from the native support files to those for
the target support. But that's not that important at the moment, since
we're mainly want a native debugger.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12027 a95241bf-73f2-0310-859d-f6bbb57e9c96