chore(profiling): add non-running tests for stack v2 (#8576)

This PR creates a harness for independently building and running the
stack v2 code. I did it this way for a few reasons

* Don't want to add unnecessary overhead to our normal test process
* Want to run the build for these native components under multiple
static analysis tools
* Want to run some of the tests for these components under sanitizers?
* But also want to do exhaustive testing of the interfaces, since we've
had a few regressions here

This PR includes both the tests and the fixups they demand. A separate
PR will add a CI job to execute these (or will add it to a pre-existing
job, TBD).

There IS some dead code in here, since we do provide the recipe for
getting and running Infer. During testing, I found that I couldn't
reliably get infer to find stdlib headers, which completely broke the
quality of its output, so it won't actually be used. At the same time, I
think we might want to use it someday, and the setup is a little fiddly,
so I'm including it here.

I'm recommending a backport to 2.7 for this because the latest 2.7
releases make this feature available, but the implementation is subtly
(and sometimes not-so-subtly) broken without the fixups here. Since this
feature is so isolated (I'm the only one backporting anything related!),
this feels safe...ish.

## Checklist

- [x] Change(s) are motivated and described in the PR description
- [x] Testing strategy is described if automated tests are not included
in the PR
- [x] Risks are described (performance impact, potential for breakage,
maintainability)
- [x] Change is maintainable (easy to change, telemetry, documentation)
- [x] [Library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
are followed or label `changelog/no-changelog` is set
- [x] Documentation is included (in-code, generated user docs, [public
corp docs](https://github.com/DataDog/documentation/))
- [x] Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))
- [x] If this PR changes the public interface, I've notified
`@DataDog/apm-tees`.
- [x] If change touches code that signs or publishes builds or packages,
or handles credentials of any kind, I've requested a review from
`@DataDog/security-design-and-guidance`.

## Reviewer Checklist

- [x] Title is accurate
- [x] All changes are related to the pull request's stated goal
- [x] Description motivates each change
- [x] Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- [x] Testing strategy adequately addresses listed risks
- [x] Change is maintainable (easy to change, telemetry, documentation)
- [x] Release note makes sense to a user of the library
- [x] Author has acknowledged and discussed the performance implications
of this PR as reported in the benchmarks PR comment
- [x] Backport labels are set in a manner that is consistent with the
[release branch maintenance
policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

---------

Co-authored-by: sanchda <[email protected]>
Co-authored-by: Gabriele N. Tornetta <[email protected]>

Author: sanchda

ddtrace/internal/datadog/profiling/cmake/AnalysisFunc.cmake

@@ -10,7 +10,8 @@ function(add_ddup_config target)
       "$<$<CONFIG:Release>:-s>"
       -Wl,--as-needed -Wl,-Bsymbolic-functions -Wl,--gc-sections
     )
-    set_property(TARGET ${target} PROPERTY INTERPROCEDURAL_OPTIMIZATION TRUE)
+
+    # If we can IPO, then do so
     check_ipo_supported(RESULT result)
     if (result)
       set_property(TARGET ${target} PROPERTY INTERPROCEDURAL_OPTIMIZATION TRUE)
@@ -22,6 +23,18 @@ function(add_ddup_config target)
         # pointers, so we include it here.
         target_compile_options(${target} PRIVATE -fsanitize=${SANITIZE_OPTIONS} -fno-omit-frame-pointer)
         target_link_options(${target} PRIVATE -fsanitize=${SANITIZE_OPTIONS})
+
+        # We need to do a little bit of work in order to ensure the dynamic *san libraries can be linked
+        # Procedure adapted from datadog/ddprof :)
+        execute_process(
+            COMMAND ${CMAKE_CXX_COMPILER} -print-file-name=
+            OUTPUT_VARIABLE LIBSAN_LIB_PATH
+            OUTPUT_STRIP_TRAILING_WHITESPACE COMMAND_ERROR_IS_FATAL ANY
+        )
+        set_target_properties(${target} PROPERTIES
+            INSTALL_RPATH ${LIBSAN_LIB_PATH}
+            BUILD_RPATH ${LIBSAN_LIB_PATH}
+        )
     endif()
 
     # If DO_FANALYZER is specified and we're using gcc, then we can use -fanalyzer

ddtrace/internal/datadog/profiling/cmake/FindClangtidy.cmake

@@ -0,0 +1,19 @@
+# Enable clang-tidy by default
+option(DO_CLANGTIDY "Enable clang-tidy" OFF)
+
+# Default executable for clang-tidy
+if (NOT DEFINED CLANGTIDY_CMD)
+    find_program(CLANGTIDY_CMD NAMES clang-tidy)
+endif()
+
+function(add_clangtidy_target TARGET)
+    if (NOT DO_CLANGTIDY)
+        return()
+    endif()
+
+    if (CLANGTIDY_CMD)
+      set_target_properties(${TARGET} PROPERTIES CXX_CLANG_TIDY "${CLANGTIDY_CMD};--checks=bugprone-*,clang-analyzer-*,cppcoreguidelines-*,modernize-*,performance-*,readability-*,-modernize-use-trailing-return-type,-performance-avoid-endl")
+    else()
+        message(FATAL_ERROR "clang-tidy requested but executable not found")
+    endif()
+endfunction()

ddtrace/internal/datadog/profiling/cmake/FindCppcheck.cmake

@@ -3,16 +3,21 @@ if (TARGET cppcheck_project)
     return()
 endif()
 
+# Set the default value for the cppcheck option
+option(DO_CPPCHECK "Enable cppcheck" OFF)
+
 include(ExternalProject)
 
 # Build cppcheck from sources
 if (DO_CPPCHECK)
-  ExternalProject_Add(cppcheck_project
-    GIT_REPOSITORY https://github.com/danmar/cppcheck.git
-    GIT_TAG "2.13.3"
-    CMAKE_ARGS -DCMAKE_INSTALL_PREFIX=${CMAKE_BINARY_DIR}/cppcheck
-  )
-  set(CPPCHECK_EXECUTABLE ${CMAKE_BINARY_DIR}/cppcheck/bin/cppcheck)
+  if (NOT CPPCHECK_EXECUTABLE OR NOT EXISTS "${CPPCHECK_EXECUTABLE}")
+    ExternalProject_Add(cppcheck_project
+      GIT_REPOSITORY https://github.com/danmar/cppcheck.git
+      GIT_TAG "2.13.3"
+      CMAKE_ARGS -DCMAKE_INSTALL_PREFIX=${CMAKE_BINARY_DIR}/cppcheck
+    )
+    set(CPPCHECK_EXECUTABLE ${CMAKE_BINARY_DIR}/cppcheck/bin/cppcheck)
+  endif()
 
   # The function we use to register targets for cppcheck would require us to run separate
   # commands for each target, which is annoying.  Instead we'll consolidate all the targets
@@ -30,7 +35,7 @@ function(add_cppcheck_target)
   cmake_parse_arguments(PARSE_ARGV 0 ARG "${options}" "${oneValueArgs}" "${multiValueArgs}")
 
   # Automatically generate the cppcheck target name
-  set(NAME "cppcheck_dd_${ARGV0}")
+  set(NAME "cppcheck_${ARGV0}")
 
   if (DO_CPPCHECK)
     # Initialize command variable
@@ -50,6 +55,7 @@ function(add_cppcheck_target)
 
     # Append include directories to the command
     foreach(INCLUDE_DIR ${ARG_INCLUDE})
+      message(STATUS "Adding include directory to cppcheck: ${INCLUDE_DIR}")
       list(APPEND cppcheck_cmd -I ${INCLUDE_DIR})
     endforeach()
 
@@ -73,4 +79,13 @@ function(add_cppcheck_target)
       COMMENT "cppcheck is disabled for ${ARGV0}"
     )
   endif()
+
+  # Create a standard target to run everything
+  if (NOT TARGET cppcheck)
+    add_custom_target(cppcheck COMMENT "Runs cppcheck on all projects")
+  endif()
+
+  if (DO_CPPCHECK)
+    add_dependencies(cppcheck ${NAME})
+  endif()
 endfunction()

ddtrace/internal/datadog/profiling/cmake/FindInfer.cmake

@@ -0,0 +1,66 @@
+# Only add this project if Infer is not defined
+if(TARGET Infer)
+    return()
+endif()
+
+include(ExternalProject)
+# Only grab infer dependencies if we need to
+if (DO_INFER)
+    if (NOT Infer_EXECUTABLE OR NOT EXISTS "${Infer_EXECUTABLE}")
+        set(TAG_INFER
+            "v1.1.0"
+            CACHE STRING "infer github tag")
+
+        set(Infer_BUILD_DIR ${CMAKE_BINARY_DIR}/infer)
+        set(Infer_ROOT ${Infer_BUILD_DIR}/infer-${TAG_LIBDATADOG})
+
+        message(STATUS "${CMAKE_CURRENT_LIST_DIR}/tools/fetch_infer.sh ${TAG_INFER} ${Infer_ROOT}")
+        execute_process(
+          COMMAND "${CMAKE_CURRENT_LIST_DIR}/tools/fetch_infer.sh" ${TAG_INFER} ${Infer_ROOT}
+          WORKING_DIRECTORY ${CMAKE_CURRENT_LIST_DIR}
+          COMMAND_ERROR_IS_FATAL ANY
+        )
+
+        set(Infer_DIR "${Infer_ROOT}")
+        set(Infer_EXECUTABLE "${Infer_DIR}/bin/infer")
+    endif()
+endif()
+
+# Add a target for using infer.  It does nothing if DO_INFER is not set
+function(add_infer_target TARGET)
+  # Automatically generate the infer target name
+  set(NAME "infer_dd_${TARGET}")
+
+  if (NOT TARGET ${TARGET})
+    message(FATAL_ERROR "Target ${TARGET} does not exist")
+    return()
+  endif()
+
+  if (DO_INFER)
+    # Initialize command variable
+    set(infer_cmd
+      ${Infer_EXECUTABLE}
+      --compilation-database ${CMAKE_CURRENT_BINARY_DIR}/compile_commands.json
+    )
+
+    # Define the custom target with the constructed command
+    add_custom_target(${NAME}
+      COMMAND ${infer_cmd}
+      COMMENT "Running infer on ${TARGET}"
+    )
+
+    # infer can't seem to find stdlib headers, so we have to add them to the target so they are included in the compile_commands.json
+    foreach(inc ${CMAKE_CXX_IMPLICIT_INCLUDE_DIRECTORIES})
+      target_include_directories(${TARGET} PRIVATE ${inc})
+    endforeach()
+
+    # Make the infer target a dependent of the specified target
+    add_dependencies(${TARGET} ${NAME})
+  else()
+    # Define a do-nothing target if infer is disabled
+    add_custom_target(${NAME}
+      COMMAND echo "infer target ${NAME} is disabled."
+      COMMENT "infer is disabled for ${TARGET}"
+    )
+  endif()
+endfunction()

ddtrace/internal/datadog/profiling/cmake/tools/fetch_infer.sh

@@ -0,0 +1,76 @@
+#!/bin/bash
+# http://redsymbol.net/articles/unofficial-bash-strict-mode/
+set -euox pipefail
+IFS=$'\n\t'
+
+usage() {
+    echo "Usage :"
+    echo "$0 <version> <path>"
+    echo ""
+    echo "Example"
+    echo "  $0 v0.7.0-rc.1 ./vendor"
+}
+
+if [ $# != 2 ] || [ "$1" == "-h" ]; then
+    usage
+    exit 1
+fi
+
+SCRIPTPATH=$(readlink -f "$0")
+SCRIPTDIR=$(dirname "$SCRIPTPATH")
+
+MARCH=$(uname -m)
+
+TAG_INFER=$1
+TARGET_EXTRACT=$2
+
+CHECKSUM_FILE=${SCRIPTDIR}/infer_checksums.txt
+
+# https://github.com/facebook/infer/releases/download/v1.1.0/infer-linux64-v1.1.0.tar.xz
+TAR_INFER=infer-linux64-${TAG_INFER}.tar.xz
+GITHUB_URL_INFER=https://github.com/facebook/infer/releases/download/${TAG_INFER}/${TAR_INFER}
+
+SHA256_INFER="blank"
+while IFS='  ' read -r checksum filename; do
+    if [ "$filename" == "$TAR_INFER" ]; then
+        SHA256_INFER="$checksum  $filename"
+        break
+    fi
+done < "$CHECKSUM_FILE"
+
+if [ "$SHA256_INFER" == "blank" ]; then
+    echo "Could not find checksum for ${TAR_INFER} in ${CHECKSUM_FILE}"
+    exit 1
+else
+  echo "Using infer sha256: ${SHA256_INFER}"
+fi
+
+mkdir -p "$TARGET_EXTRACT" || true
+cd "$TARGET_EXTRACT"
+
+if [[ -e "${TAR_INFER}" ]]; then
+    already_present=1
+else
+    already_present=0
+    echo "Downloading infer ${GITHUB_URL_INFER}..."
+    if command -v curl > /dev/null 2>&1; then
+        curl -fsSLO "${GITHUB_URL_INFER}"
+    elif command -v wget > /dev/null 2>&1; then
+        wget -q -O "${GITHUB_URL_INFER##*/}" "${GITHUB_URL_INFER}"
+    else
+        echo "Error: neither curl nor wget is available." >&2
+        exit 1
+    fi
+fi
+
+echo "Checking infer sha256"
+if ! echo "${SHA256_INFER}" | sha256sum -c -; then
+    echo "Error validating infer SHA256"
+    echo "Please clear $TARGET_EXTRACT before restarting"
+    exit 1
+fi
+
+if [[ $already_present -eq 0 ]]; then
+    echo "Extracting ${TAR_INFER}"
+    tar xf "${TAR_INFER}" --strip-components=1 --no-same-owner
+fi

ddtrace/internal/datadog/profiling/cmake/tools/infer_checksums.txt

@@ -0,0 +1 @@
+5f5d453814422e93e2a70998d8946b09a2721628ff427f67ff0123dea87461d4  infer-linux64-v1.1.0.tar.xz

ddtrace/internal/datadog/profiling/dd_wrapper/CMakeLists.txt

@@ -15,7 +15,9 @@ include(FetchContent)
 include(ExternalProject)
 include(FindLibdatadog)
 include(AnalysisFunc)
+include(FindClangtidy)
 include(FindCppcheck)
+include(FindInfer)
 
 # Library sources
 add_library(dd_wrapper SHARED
@@ -59,6 +61,9 @@ add_cppcheck_target(dd_wrapper
     SRC ${CMAKE_CURRENT_SOURCE_DIR}/src
 )
 
+add_infer_target(dd_wrapper)
+add_clangtidy_target(dd_wrapper)
+
 # Add the tests
 if (BUILD_TESTING)
     enable_testing()

ddtrace/internal/datadog/profiling/dd_wrapper/include/interface.hpp

@@ -27,7 +27,7 @@ extern "C"
 
     bool ddup_is_initialized();
     void ddup_init();
-    void ddup_set_runtime_id(std::string_view id);
+    void ddup_set_runtime_id(std::string_view runtime_id);
     bool ddup_upload();
 
     // Proxy functions to the underlying sample
@@ -36,8 +36,8 @@ extern "C"
     void ddup_push_cputime(Datadog::Sample* sample, int64_t cputime, int64_t count);
     void ddup_push_acquire(Datadog::Sample* sample, int64_t acquire_time, int64_t count);
     void ddup_push_release(Datadog::Sample* sample, int64_t release_time, int64_t count);
-    void ddup_push_alloc(Datadog::Sample* sample, uint64_t size, uint64_t count);
-    void ddup_push_heap(Datadog::Sample* sample, uint64_t size);
+    void ddup_push_alloc(Datadog::Sample* sample, int64_t size, int64_t count);
+    void ddup_push_heap(Datadog::Sample* sample, int64_t size);
     void ddup_push_lock_name(Datadog::Sample* sample, std::string_view lock_name);
     void ddup_push_threadinfo(Datadog::Sample* sample,
                               int64_t thread_id,

ddtrace/internal/datadog/profiling/dd_wrapper/include/libdatadog_helpers.hpp

@@ -4,6 +4,7 @@
 #include <iostream>
 #include <string>
 #include <string_view>
+#include <variant>
 
 extern "C"
 {
@@ -126,6 +127,16 @@ add_tag(ddog_Vec_Tag& tags, const ExportTagKey key, std::string_view val, std::s
     return add_tag(tags, key_sv, val, errmsg);
 }
 
+inline std::variant<ddog_prof_Exporter*, ddog_Error>
+get_newexporter_result(const ddog_prof_Exporter_NewResult& res)
+{
+    if (res.tag == DDOG_PROF_EXPORTER_NEW_RESULT_OK) {
+        return res.ok; // NOLINT (cppcoreguidelines-pro-type-union-access)
+    } else {
+        return res.err; // NOLINT (cppcoreguidelines-pro-type-union-access)
+    }
+}
+
 // Keep macros from propagating
 #undef X_STR
 #undef X_ENUM

ddtrace/internal/datadog/profiling/dd_wrapper/include/profile.hpp

@@ -70,7 +70,7 @@ class Profile
     void profile_release();
 
     // String table manipulation
-    std::string_view insert_or_get(std::string_view sv);
+    std::string_view insert_or_get(std::string_view str);
 
     // constref getters
     const ValueIndex& val();