[Lldb-commits] [PATCH] D131630: [trace][intel pt] Fix per-psb packet decoding

[walter erquinigo via Phabricator via lldb-commits]

wallace created this revision.
wallace added reviewers: jj10306, persona0220.
Herald added a project: All.
wallace requested review of this revision.
Herald added a project: LLDB.
Herald added a subscriber: lldb-commits.

The per-PSB packet decoding logic was wrong because it was assuming that pt_insn_get_sync_offset was being udpated after every PSB. Silly me, that is not true. It returns the offset of the PSB packet after invoking pt_insn_sync_forward regardless of how many PSBs are visited later. Instead, I'm now following the approach described in https://github.com/intel/libipt/blob/master/doc/howto_libipt.md#parallel-decode for parallel decoding, which is basically what we need.

A nasty error that happened because of this is that when we had two PSBs (A and B), the following was happening

1. PSB A was processed all the way up to the end of the trace, which includes PSB B.
2. PSB B was then processed until the end of the trace.

The instructions emitted by step 2. were also emitted as part of step 1. so our trace had duplicated chunks. This problem becomes worse when you many PSBs.

As part of making sure this diff is correct, I added some other features that are very useful.

- Added a "synchronization point" event to the TraceCursor, so we can inspect when PSBs are emitted.
- Removed the single-thread decoder. Now the per-cpu decoder and single-thread decoder use the same code paths.
- Use the query decoder to fetch PSBs and timestamps. It turns out that the pt_insn_sync_forward of the instruction decoder can move past several PSBs (this means that we could skip some TSCs). On the other hand, the pt_query_sync_forward method doesn't skip PSBs, so we can get more accurate sync events and timing information.
- Turned LibiptDecoder into PSBBlockDecoder, which decodes single PSB blocks. It is the fundamental processing unit for decoding.
- Added many comments, asserts and improved error handling for clarity.
- Improved DecodeSystemWideTraceForThread so that a TSC is emitted always before a cpu change event. This was a bug that was annoying me before.
- SplitTraceInContinuousExecutions and FindLowestTSCInTrace are now using the query decoder, which can identify precisely each PSB along with their TSCs.

I did extensive testing and I think we should have an in-house testing CI. The LLVM buildbots are not capable of supporting testing post-mortem traces of hundreds of megabytes. I'll leave that for later, but at least for now the current tests were able to catch most of the issues I encountered when doing this task.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D131630

Files:
  lldb/include/lldb/Target/TraceCursor.h
  lldb/include/lldb/Target/TraceDumper.h
  lldb/include/lldb/lldb-enumerations.h
  lldb/source/Commands/CommandObjectThread.cpp
  lldb/source/Commands/Options.td
  lldb/source/Plugins/Trace/intel-pt/DecodedThread.cpp
  lldb/source/Plugins/Trace/intel-pt/DecodedThread.h
  lldb/source/Plugins/Trace/intel-pt/LibiptDecoder.cpp
  lldb/source/Plugins/Trace/intel-pt/LibiptDecoder.h
  lldb/source/Plugins/Trace/intel-pt/TraceCursorIntelPT.cpp
  lldb/source/Plugins/Trace/intel-pt/TraceCursorIntelPT.h
  lldb/source/Plugins/Trace/intel-pt/TraceIntelPT.cpp
  lldb/source/Plugins/Trace/intel-pt/TraceIntelPTMultiCpuDecoder.cpp
  lldb/source/Target/TraceCursor.cpp
  lldb/source/Target/TraceDumper.cpp
  lldb/test/API/commands/trace/TestTraceDumpInfo.py
  lldb/test/API/commands/trace/TestTraceDumpInstructions.py
  lldb/test/API/commands/trace/TestTraceEvents.py
  lldb/test/API/commands/trace/TestTraceLoad.py
  lldb/test/API/commands/trace/TestTraceStartStop.py

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D131630.451668.patch
Type: text/x-patch
Size: 92627 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/lldb-commits/attachments/20220810/733b6bd5/attachment-0001.bin>