Commit Graph

3 Commits

Author SHA1 Message Date
Todd Fiala 6c9053ef20 Added a couple more gdb-remote tests to ensure qProcessInfo on darwin is not defining triple.
And likewise for qProcessInfo on Linux, but ensures cputype/cpusubtype is not defined.  The
Apple case is the more important one, since we take a slightly different path to initialize
ProcessGDBRemote-related remote host/process info if triple is present.

Related to http://llvm.org/bugs/show_bug.cgi?id=20755.

llvm-svn: 216473
2014-08-26 18:40:56 +00:00
Todd Fiala c540dd0daf Fix llgs to send triple for non-Apple platforms and lldb to interpret correctly.
This change addresses this bug:
http://llvm.org/bugs/show_bug.cgi?id=20755

This change:
* Modifies llgs to send triple instead of cputype and cpusubtype when not on Apple platforms in qProcessInfo.
* Modifies lldb's GDBRemoteCommunicationClient to handle the triple returned from qProcessInfo if given.
  When given, it will prefer to use triple over cputype and cpusubtype.
* Adds gdb-remote protocol tests to verify that cputype and cpusubtype are specified on darwin, and that triple is specified on Linux.

llvm-svn: 216470
2014-08-26 18:21:02 +00:00
Todd Fiala f76a891299 Refactored existing gdb-remote qProcessInfo tests into separate python file.
I'm about to add some more qProcessInfo tests so I wanted to first pull them out
of the monolithic TestLldbGdbServer test case class.

Related to http://llvm.org/bugs/show_bug.cgi?id=20755

llvm-svn: 216465
2014-08-26 17:19:10 +00:00