[v3,1/7] debuginfod: fix skipping <built-in> source file

Message ID 46cae5909ccc3ed390e37bd68eb54d032a4ad8a2.1721377314.git.osandov@fb.com
State Superseded
Headers
Series debuginfod: speed up extraction from kernel debuginfo packages by 200x |

Commit Message

Omar Sandoval July 19, 2024, 8:31 a.m. UTC
  From: Omar Sandoval <osandov@fb.com>

dwarf_extract_source_paths explicitly skips source files that equal
"<built-in>", but dwarf_filesrc may return a path like "dir/<built-in>".
Check for and skip that case, too.

In particular, the test debuginfod RPMs have paths like this.  However,
the test cases didn't catch this because they have a bug, too: they
follow symlinks, which results in double-counting every file.  Fix that,
too.

Signed-off-by: Omar Sandoval <osandov@fb.com>
---
 debuginfod/debuginfod.cxx             | 3 ++-
 tests/run-debuginfod-archive-groom.sh | 2 +-
 tests/run-debuginfod-extraction.sh    | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)
  

Patch

diff --git a/debuginfod/debuginfod.cxx b/debuginfod/debuginfod.cxx
index 305edde8..92022f3d 100644
--- a/debuginfod/debuginfod.cxx
+++ b/debuginfod/debuginfod.cxx
@@ -3446,7 +3446,8 @@  dwarf_extract_source_paths (Elf *elf, set<string>& debug_sourcefiles)
           if (hat == NULL)
             continue;
 
-          if (string(hat) == "<built-in>") // gcc intrinsics, don't bother record
+          if (string(hat) == "<built-in>"
+              || string_endswith(hat, "<built-in>")) // gcc intrinsics, don't bother record
             continue;
 
           string waldo;
diff --git a/tests/run-debuginfod-archive-groom.sh b/tests/run-debuginfod-archive-groom.sh
index e2c394ef..0131158f 100755
--- a/tests/run-debuginfod-archive-groom.sh
+++ b/tests/run-debuginfod-archive-groom.sh
@@ -109,7 +109,7 @@  for i in $newrpms; do
     rpm2cpio ../$i | cpio -ivd;
     cd ..;
 done
-sourcefiles=$(find -name \*\\.debug \
+sourcefiles=$(find -name \*\\.debug -type f \
               | env LD_LIBRARY_PATH=$ldpath xargs \
                 ${abs_top_builddir}/src/readelf --debug-dump=decodedline \
               | grep mtime: | wc --lines)
diff --git a/tests/run-debuginfod-extraction.sh b/tests/run-debuginfod-extraction.sh
index da6b25cf..f49dc6f6 100755
--- a/tests/run-debuginfod-extraction.sh
+++ b/tests/run-debuginfod-extraction.sh
@@ -94,7 +94,7 @@  for i in $newrpms; do
     rpm2cpio ../$i | cpio -ivd;
     cd ..;
 done
-sourcefiles=$(find -name \*\\.debug \
+sourcefiles=$(find -name \*\\.debug -type f \
               | env LD_LIBRARY_PATH=$ldpath xargs \
                 ${abs_top_builddir}/src/readelf --debug-dump=decodedline \
               | grep mtime: | wc --lines)