Skip to content
Snippets Groups Projects
Select Git revision
1 result Searching

libjvmti.c

Blame
    • Ben Gainey's avatar
      ca58d7e6
      perf jvmti: Generate correct debug information for inlined code · ca58d7e6
      Ben Gainey authored
      
      tools/perf/jvmti is broken in so far as it generates incorrect debug
      information. Specifically it attributes all debug lines to the original
      method being output even in the case that some code is being inlined
      from elsewhere.  This patch fixes the issue.
      
      To test (from within linux/tools/perf):
      
      export JDIR=/usr/lib/jvm/java-8-openjdk-amd64/
      make
      cat << __EOF > Test.java
      public class Test
      {
          private StringBuilder b = new StringBuilder();
      
          private void loop(int i, String... args)
          {
              for (String a : args)
                  b.append(a);
      
              long hc = b.hashCode() * System.nanoTime();
      
              b = new StringBuilder();
              b.append(hc);
      
              System.out.printf("Iteration %d = %d\n", i, hc);
          }
      
          public void run(String... args)
          {
              for (int i = 0; i < 10000; ++i)
              {
                  loop(i, args);
              }
          }
      
          public static void main(String... args)
          {
              Test t = new Test();
              t.run(args);
          }
      }
      __EOF
      $JDIR/bin/javac Test.java
      ./perf record -F 10000 -g -k mono $JDIR/bin/java -agentpath:`pwd`/libperf-jvmti.so Test
      ./perf inject --jit -i perf.data -o perf.data.jitted
      ./perf annotate -i perf.data.jitted --stdio | grep Test\.java: | sort -u
      
      Before this patch, Test.java line numbers get reported that are greater
      than the number of lines in the Test.java file.  They come from the
      source file of the inlined function, e.g. java/lang/String.java:1085.
      For further validation one can examine those lines in the JDK source
      distribution and confirm that they map to inlined functions called by
      Test.java.
      
      After this patch, the filename of the inlined function is output
      rather than the incorrect original source filename.
      
      Signed-off-by: default avatarBen Gainey <ben.gainey@arm.com>
      Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      Tested-by: default avatarStephane Eranian <eranian@google.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Ben Gainey <ben.gainey@arm.com>
      Cc: Colin King <colin.king@canonical.com>
      Cc: Darren Hart <dvhart@infradead.org>
      Cc: Jiri Olsa <jolsa@redhat.com>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Fixes: 598b7c69 ("perf jit: add source line info support")
      Link: http://lkml.kernel.org/r/20171122182541.d25599a3eb1ada3480d142fa@arm.com
      
      
      Signed-off-by: default avatarKim Phillips <kim.phillips@arm.com>
      Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      ca58d7e6
      History
      perf jvmti: Generate correct debug information for inlined code
      Ben Gainey authored
      
      tools/perf/jvmti is broken in so far as it generates incorrect debug
      information. Specifically it attributes all debug lines to the original
      method being output even in the case that some code is being inlined
      from elsewhere.  This patch fixes the issue.
      
      To test (from within linux/tools/perf):
      
      export JDIR=/usr/lib/jvm/java-8-openjdk-amd64/
      make
      cat << __EOF > Test.java
      public class Test
      {
          private StringBuilder b = new StringBuilder();
      
          private void loop(int i, String... args)
          {
              for (String a : args)
                  b.append(a);
      
              long hc = b.hashCode() * System.nanoTime();
      
              b = new StringBuilder();
              b.append(hc);
      
              System.out.printf("Iteration %d = %d\n", i, hc);
          }
      
          public void run(String... args)
          {
              for (int i = 0; i < 10000; ++i)
              {
                  loop(i, args);
              }
          }
      
          public static void main(String... args)
          {
              Test t = new Test();
              t.run(args);
          }
      }
      __EOF
      $JDIR/bin/javac Test.java
      ./perf record -F 10000 -g -k mono $JDIR/bin/java -agentpath:`pwd`/libperf-jvmti.so Test
      ./perf inject --jit -i perf.data -o perf.data.jitted
      ./perf annotate -i perf.data.jitted --stdio | grep Test\.java: | sort -u
      
      Before this patch, Test.java line numbers get reported that are greater
      than the number of lines in the Test.java file.  They come from the
      source file of the inlined function, e.g. java/lang/String.java:1085.
      For further validation one can examine those lines in the JDK source
      distribution and confirm that they map to inlined functions called by
      Test.java.
      
      After this patch, the filename of the inlined function is output
      rather than the incorrect original source filename.
      
      Signed-off-by: default avatarBen Gainey <ben.gainey@arm.com>
      Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      Tested-by: default avatarStephane Eranian <eranian@google.com>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Ben Gainey <ben.gainey@arm.com>
      Cc: Colin King <colin.king@canonical.com>
      Cc: Darren Hart <dvhart@infradead.org>
      Cc: Jiri Olsa <jolsa@redhat.com>
      Cc: Namhyung Kim <namhyung@kernel.org>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Fixes: 598b7c69 ("perf jit: add source line info support")
      Link: http://lkml.kernel.org/r/20171122182541.d25599a3eb1ada3480d142fa@arm.com
      
      
      Signed-off-by: default avatarKim Phillips <kim.phillips@arm.com>
      Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
    root.c 8.69 KiB