Commit Graph

32 Commits

Author SHA1 Message Date
Mohit K. Bhakkad 13763c3046 [LLDB][Watchpoint] Change ignore_count condition location to fix watchpoint ignore feature for architectures with watchpoint_exceptions_received=before
Reviewers: jingham.
Subscribers: clayborg, jaydeep, bhushan, sagar, nitesh.jain, lldb-commits.
Differential Revision: http://reviews.llvm.org/D13296

llvm-svn: 251905
2015-11-03 09:04:33 +00:00
Jim Ingham 19a63fc6fa Add the ability to pass an EvaluateExpressionOptions when you make a UserExpression. This
isn't used in this commit but will be in a future commit.

llvm-svn: 251887
2015-11-03 02:11:24 +00:00
Eugene Zelenko 16fd7511b2 Fix Clang-tidy modernize-use-nullptr warnings in source/Breakpoint; other minor fixes.
llvm-svn: 251716
2015-10-30 18:50:12 +00:00
Mohit K. Bhakkad 18af8a20c5 [LLDB] Fix display of value of a vector variables in watchpoint operations
Reviewers: clayborg, zturner.
Subscribers: jaydeep, bhushan, sagar, nitesh.jain, brucem,lldb-commits.
Differential Revision: http://reviews.llvm.org/D13202

llvm-svn: 249838
2015-10-09 15:13:20 +00:00
Jim Ingham 151c032c86 This patch makes Clang-independent base classes for all the expression types that lldb currently vends.
Before we had:

ClangFunction
ClangUtilityFunction
ClangUserExpression

and code all over in lldb that explicitly made Clang-based expressions. This patch adds an Expression 
base class, and three pure virtual implementations for the Expression kinds:

FunctionCaller
UtilityFunction
UserExpression

You can request one of these expression types from the Target using the Get<ExpressionType>ForLanguage. 
The Target will then consult all the registered TypeSystem plugins, and if the type system that matches 
the language can make an expression of that kind, it will do so and return it.

Because all of the real expression types need to communicate with their ExpressionParser in a uniform way, 
I also added a ExpressionTypeSystemHelper class that expressions generically can vend, and a ClangExpressionHelper 
that encapsulates the operations that the ClangExpressionParser needs to perform on the ClangExpression types. 
Then each of the Clang* expression kinds constructs the appropriate helper to do what it needs.

The patch also fixes a wart in the UtilityFunction that to use it you had to create a parallel FunctionCaller 
to actually call the function made by the UtilityFunction. Now the UtilityFunction can be asked to vend a 
FunctionCaller that will run its function. This cleaned up a lot of boiler plate code using UtilityFunctions.

Note, in this patch all the expression types explicitly depend on the LLVM JIT and IR, and all the common 
JIT running code is in the FunctionCaller etc base classes. At some point we could also abstract that dependency 
but I don't see us adding another back end in the near term, so I'll leave that exercise till it is actually necessary.

llvm-svn: 247720
2015-09-15 21:13:50 +00:00
Greg Clayton a1e5dc86a6 ClangASTType is now CompilerType.
This is more preparation for multiple different kinds of types from different compilers (clang, Pascal, Go, RenderScript, Swift, etc).

llvm-svn: 244689
2015-08-11 22:53:00 +00:00
Greg Clayton 57ee306789 Huge change to clean up types.
A long time ago we start with clang types that were created by the symbol files and there were many functions in lldb_private::ClangASTContext that helped. Later we create ClangASTType which contains a clang::ASTContext and an opauque QualType, but we didn't switch over to fully using it. There were a lot of places where we would pass around a raw clang_type_t and also pass along a clang::ASTContext separately. This left room for error.

This checkin change all type code over to use ClangASTType everywhere and I cleaned up the interfaces quite a bit. Any code that was in ClangASTContext that was type related, was moved over into ClangASTType. All code that used these types was switched over to use all of the new goodness.

llvm-svn: 186130
2013-07-11 22:46:58 +00:00
Greg Clayton c7bece56fa <rdar://problem/13069948>
Major fixed to allow reading files that are over 4GB. The main problems were that the DataExtractor was using 32 bit offsets as a data cursor, and since we mmap all of our object files we could run into cases where if we had a very large core file that was over 4GB, we were running into the 4GB boundary.

So I defined a new "lldb::offset_t" which should be used for all file offsets.

After making this change, I enabled warnings for data loss and for enexpected implicit conversions temporarily and found a ton of things that I fixed.

Any functions that take an index internally, should use "size_t" for any indexes and also should return "size_t" for any sizes of collections.

llvm-svn: 173463
2013-01-25 18:06:21 +00:00
Jim Ingham 1b5792e5ad Adding events when watchpoints are set or changed.
<rdar://problem/11597849>

llvm-svn: 170400
2012-12-18 02:03:49 +00:00
Daniel Malea d01b2953fa Resolve printf formatting warnings on Linux:
- use macros from inttypes.h for format strings instead of OS-specific types

Patch from Matt Kopec!

llvm-svn: 168945
2012-11-29 21:49:15 +00:00
Jim Ingham ce0740d8cf Turns out there are 8 bits in a byte.
llvm-svn: 166502
2012-10-23 21:09:09 +00:00
Jim Ingham a7dfb665e3 Watchpoints remember the type of the expression or variable they were set with, and use
it to print the old and new values.
Temporarily disable the "out of scope" checking since it didn't work correctly, and was
not what people generally expected watchpoints to be doing.  

llvm-svn: 166472
2012-10-23 07:20:06 +00:00
Johnny Chen 892943f9dd Cope with the case where the user-supplied callbacks want the watchpoint itself to be disabled!
Previously we put a WatchpointSentry object within StopInfo.cpp to disable-and-then-enable the watchpoint itself
while we are performing the actions associated with the triggered watchpoint, which can cause the user-initiated
watchpoint disabling action to be negated.

Add a test case to verify that a watchpoint can be disabled during the callbacks.

llvm-svn: 162483
2012-08-23 22:28:26 +00:00
Johnny Chen 4fe2302ae2 Fix test failures in TestWatchpointIter.py due to http://llvm.org/viewvc/llvm-project?rev=162322&view=rev.
llvm-svn: 162328
2012-08-21 23:17:04 +00:00
Johnny Chen 0f7ad8d98f rdar://problem/12144930
Watchpoint conditions were hitting watchpoint, smashing LLDB's stack.
Make sure watchpoint is properly disabled and subsequently enabled while performing watchpoint actions.

llvm-svn: 162322
2012-08-21 22:06:34 +00:00
Johnny Chen 6cf6f89005 A little bit of refactoring.
llvm-svn: 161903
2012-08-14 23:09:48 +00:00
Johnny Chen 25c0eb4a38 When trying to take snapshots of a watched variable, if the frame is unable to evaluate the variable expression,
do not take the sanpshot and forget about the stop info.  It is possible that the variable expression has gone
out of scope, we'll revise the hit count due to the false alarms.

llvm-svn: 161892
2012-08-14 20:56:37 +00:00
Johnny Chen 88fc73b8f7 Simplify the "Watchpoint ... hit" printout, make it more terse.
Change the test case, too. 

llvm-svn: 161806
2012-08-13 23:27:50 +00:00
Johnny Chen 209bd65ea4 rdar://problem/12007576
Record the snapshot of our watched value when the watchpoint is set or hit.
And report the old/new values when watchpoint is triggered.  Add some test scenarios.

llvm-svn: 161785
2012-08-13 21:09:54 +00:00
Johnny Chen e9a5627e7a rdar://problem/11457143 [ER] need "watchpoint command ..."
Add 'watchpoint command add/delete/list' to lldb, plus two .py test files.

llvm-svn: 161638
2012-08-09 23:09:42 +00:00
Jim Ingham c7dccb797e Jeeze... Remove two unneeded #include's of ThreadPlanTestCondition.h, and replace them with
includes of ClangUserExpression that were being errantly dragged in through same.

llvm-svn: 155970
2012-05-02 00:30:53 +00:00
Johnny Chen a4d6bc9ff8 Make the Watchpoint IDs unique per target, not across targets as before.
Now Each newly created target has its Watchpoint IDs as 1, 2, 3 ...

llvm-svn: 151435
2012-02-25 06:44:30 +00:00
Jason Molenda 7e1f45f9c5 Make a nested if .. if .. else block nesting more explicit with some curly braces.
llvm-svn: 151292
2012-02-23 22:32:13 +00:00
Johnny Chen dedb67ab9b Add "watch set" command as a more general interface in conjunction with "frame var -w".
Also add test cases for watching a variable as well as a location expressed as an expression.

o TestMyFirstWatchpoint.py:

  Modified to test "watchpoint set -w write global".

o TestWatchLocationWithWatchSet.py:

  Added to test "watchpoint set -w write -x 1 g_char_ptr + 7" where a contrived example program
  with several threads is supposed to only access the array index within the range [0..6], but
  there's some misbehaving thread writing past the range.

rdar://problem/10701761

llvm-svn: 149280
2012-01-30 21:46:17 +00:00
Johnny Chen a5cde26b3e Minor comment change. Plus use member function instead of directly accessing member field.
llvm-svn: 148756
2012-01-24 00:11:02 +00:00
Johnny Chen fab7a91d92 Tiny refactoring to use member functions instead of directly accessing member fields.
llvm-svn: 148743
2012-01-23 23:03:59 +00:00
Sean Callanan 20bb3aa53a The "desired result type" code in the expression
parser has hitherto been an implementation waiting
for a use.  I have now tied the '-o' option for
the expression command -- which indicates that the
result is an Objective-C object and needs to be
printed -- to the ExpressionParser, which
communicates the desired type to Clang.

Now, if the result of an expression is determined
by an Objective-C method call for which there is
no type information, that result is implicitly
cast to id if and only if the -o option is passed
to the expression command.  (Otherwise if there
is no explicit cast Clang will issue an error.
This behavior is identical to what happened before
r146756.)

Also added a testcase for -o enabled and disabled.

llvm-svn: 147099
2011-12-21 22:22:58 +00:00
Greg Clayton c91d804af9 Fixed some extra warnings that show up with the new clang.
llvm-svn: 145735
2011-12-03 00:46:21 +00:00
Sean Callanan c7b650670e Added a language parameter to the expression parser,
which will in the future allow expressions to be
compiled as C, C++, and Objective-C instead of the
current default Objective-C++.  This feature requires
some additional support from Clang -- specifically, it
requires reference types in the parser regardless of
language -- so it is not yet exposed to the user.

llvm-svn: 144042
2011-11-07 23:35:40 +00:00
Johnny Chen 16dcf718d3 Add a commnad to set a condition for a watchpoint. Example:
watchpoint modify -c 'global==5'

modifies the last created watchpoint so that the condition expression
is evaluated at the stop point to decide whether we should proceed with
the stopping.

Also add SBWatchpont::SetCondition(const char *condition) to set condition
programmatically.

Test cases to come later.

llvm-svn: 142227
2011-10-17 18:58:00 +00:00
Johnny Chen ed456eb0a9 Add SBWatchpoint::GetError() API, which is not currently populated as yet.
llvm-svn: 141979
2011-10-14 19:15:48 +00:00
Johnny Chen 01a678603a SBValue::Watch() and SBValue::WatchPointee() are now the official API for creating
a watchpoint for either the variable encapsulated by SBValue (Watch) or the pointee
encapsulated by SBValue (WatchPointee).

Removed SBFrame::WatchValue() and SBFrame::WatchLocation() API as a result of that.

Modified the watchpoint related test suite to reflect the change.

Plus replacing WatchpointLocation with Watchpoint throughout the code base.

There are still cleanups to be dome.  This patch passes the whole test suite.
Check it in so that we aggressively catch regressions.

llvm-svn: 141925
2011-10-14 00:42:25 +00:00