#
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
|