[Lldb-commits] [lldb] [lldb] Include checksum in source cache dump (PR #106773)

[Jonas Devlieghere via lldb-commits]

https://github.com/JDevlieghere created https://github.com/llvm/llvm-project/pull/106773

This patch updates the source cache dump command to print both the actual (on-disk) checksum and the expected (line table) checksum. To achieve that we now read and store the on-disk checksum in the cached object. The same information will be used in a future path to print a warning when the checksums differ.

>From a73b63a4b3e74b92b9ef5f913c75b4710859bca6 Mon Sep 17 00:00:00 2001
From: Jonas Devlieghere <jonas at devlieghere.com>
Date: Fri, 30 Aug 2024 11:07:50 -0700
Subject: [PATCH] [lldb] Include checksum in source cache dump

This patch updates the source cache dump command to print both the
actual (on-disk) checksum and the expected (line table) checksum. To
achieve that we now read and store the on-disk checksum in the cached
object. The same information will be used in a future path to print a
warning when the checksums differ.
---
 lldb/include/lldb/Core/SourceManager.h | 12 ++++++++++++
 lldb/source/Core/SourceManager.cpp     | 27 +++++++++++++++++++-------
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/lldb/include/lldb/Core/SourceManager.h b/lldb/include/lldb/Core/SourceManager.h
index ae7bd3d2311f96..70325f134f2a68 100644
--- a/lldb/include/lldb/Core/SourceManager.h
+++ b/lldb/include/lldb/Core/SourceManager.h
@@ -9,6 +9,7 @@
 #ifndef LLDB_CORE_SOURCEMANAGER_H
 #define LLDB_CORE_SOURCEMANAGER_H
 
+#include "lldb/Utility/Checksum.h"
 #include "lldb/Utility/FileSpec.h"
 #include "lldb/lldb-defines.h"
 #include "lldb/lldb-forward.h"
@@ -42,6 +43,7 @@ class SourceManager {
 
     bool ModificationTimeIsStale() const;
     bool PathRemappingIsStale() const;
+    bool ChecksumIsStale() const;
 
     size_t DisplaySourceLines(uint32_t line, std::optional<size_t> column,
                               uint32_t context_before, uint32_t context_after,
@@ -71,6 +73,10 @@ class SourceManager {
 
     llvm::sys::TimePoint<> GetTimestamp() const { return m_mod_time; }
 
+    const Checksum &GetChecksum() const { return m_checksum; }
+
+    llvm::once_flag &GetChecksumOnceFlag() { return m_checksum_once_flag; }
+
   protected:
     /// Set file and update modification time.
     void SetSupportFile(lldb::SupportFileSP support_file_sp);
@@ -81,6 +87,12 @@ class SourceManager {
     /// different from the original support file passed to the constructor.
     lldb::SupportFileSP m_support_file_sp;
 
+    /// Keep track of the on-disk checksum.
+    Checksum m_checksum;
+
+    /// Only warn once of checksum mismatch.
+    llvm::once_flag m_checksum_once_flag;
+
     // Keep the modification time that this file data is valid for
     llvm::sys::TimePoint<> m_mod_time;
 
diff --git a/lldb/source/Core/SourceManager.cpp b/lldb/source/Core/SourceManager.cpp
index c427bb91f4643a..f6e59ce731a573 100644
--- a/lldb/source/Core/SourceManager.cpp
+++ b/lldb/source/Core/SourceManager.cpp
@@ -447,13 +447,14 @@ void SourceManager::FindLinesMatchingRegex(SupportFileSP support_file_sp,
 
 SourceManager::File::File(SupportFileSP support_file_sp,
                           lldb::DebuggerSP debugger_sp)
-    : m_support_file_sp(std::make_shared<SupportFile>()), m_mod_time(),
-      m_debugger_wp(debugger_sp), m_target_wp(TargetSP()) {
+    : m_support_file_sp(std::make_shared<SupportFile>()), m_checksum(),
+      m_mod_time(), m_debugger_wp(debugger_sp), m_target_wp(TargetSP()) {
   CommonInitializer(support_file_sp, {});
 }
 
 SourceManager::File::File(SupportFileSP support_file_sp, TargetSP target_sp)
-    : m_support_file_sp(std::make_shared<SupportFile>()), m_mod_time(),
+    : m_support_file_sp(std::make_shared<SupportFile>()), m_checksum(),
+      m_mod_time(),
       m_debugger_wp(target_sp ? target_sp->GetDebugger().shared_from_this()
                               : DebuggerSP()),
       m_target_wp(target_sp) {
@@ -532,9 +533,11 @@ void SourceManager::File::CommonInitializer(SupportFileSP support_file_sp,
   }
 
   // If the file exists, read in the data.
-  if (m_mod_time != llvm::sys::TimePoint<>())
+  if (m_mod_time != llvm::sys::TimePoint<>()) {
     m_data_sp = FileSystem::Instance().CreateDataBuffer(
         m_support_file_sp->GetSpecOnly());
+    m_checksum = llvm::MD5::hash(m_data_sp->GetData());
+  }
 }
 
 void SourceManager::File::SetSupportFile(lldb::SupportFileSP support_file_sp) {
@@ -835,14 +838,24 @@ SourceManager::FileSP SourceManager::SourceFileCache::FindSourceFile(
   return {};
 }
 
+static std::string toString(const Checksum &checksum) {
+  if (!checksum)
+    return "";
+  return std::string(llvm::formatv("{0}", checksum.digest()));
+}
+
 void SourceManager::SourceFileCache::Dump(Stream &stream) const {
-  stream << "Modification time   Lines    Path\n";
-  stream << "------------------- -------- --------------------------------\n";
+  // clang-format off
+  stream << "Modification time   MD5 Checksum (on-disk)           MD5 Checksum (line table)        Lines    Path\n";
+  stream << "------------------- -------------------------------- -------------------------------- -------- --------------------------------\n";
+  // clang-format on
   for (auto &entry : m_file_cache) {
     if (!entry.second)
       continue;
     FileSP file = entry.second;
-    stream.Format("{0:%Y-%m-%d %H:%M:%S} {1,8:d} {2}\n", file->GetTimestamp(),
+    stream.Format("{0:%Y-%m-%d %H:%M:%S} {1,32} {2,32} {3,8:d} {4}\n",
+                  file->GetTimestamp(), toString(file->GetChecksum()),
+                  toString(file->GetSupportFile()->GetChecksum()),
                   file->GetNumLines(), entry.first.GetPath());
   }
 }