[xray] Function coverage groups

Add the ability to selectively instrument a subset of functions by dividing the functions into N logical groups and then selecting a group to cover. By selecting different groups over time you could cover the entire application incrementally with lower overhead than instrumenting the entire application at once.

Differential Revision: https://reviews.llvm.org/D87953

clang/include/clang/Basic/CodeGenOptions.def

@@ -120,6 +120,12 @@ CODEGENOPT(XRayOmitFunctionIndex , 1, 0)
 ///< XRay instrumentation.
 VALUE_CODEGENOPT(XRayInstructionThreshold , 32, 200)
 
+///< Only instrument 1 in N functions, by dividing functions into N total groups and
+///< instrumenting only the specified group at a time. Group numbers start at 0
+///< and end at N-1.
+VALUE_CODEGENOPT(XRayTotalFunctionGroups, 32, 1)
+VALUE_CODEGENOPT(XRaySelectedFunctionGroup, 32, 0)
+
 VALUE_CODEGENOPT(PatchableFunctionEntryCount , 32, 0) ///< Number of NOPs at function entry
 VALUE_CODEGENOPT(PatchableFunctionEntryOffset , 32, 0)
 

clang/include/clang/Driver/Options.td

@@ -1339,6 +1339,17 @@ def fxray_instrumentation_bundle :
   Group<f_Group>, Flags<[CC1Option]>,
   HelpText<"Select which XRay instrumentation points to emit. Options: all, none, function-entry, function-exit, function, custom. Default is 'all'.  'function' includes both 'function-entry' and 'function-exit'.">;
 
+def fxray_function_groups :
+  Joined<["-"], "fxray-function-groups=">,
+  Group<f_Group>, Flags<[CC1Option]>,
+  HelpText<"Only instrument 1 of N groups">;
+
+def fxray_selected_function_group :
+  Joined<["-"], "fxray-selected-function-group=">,
+  Group<f_Group>, Flags<[CC1Option]>,
+  HelpText<"When using -fxray-function-groups, select which group of functions to instrument. Valid range is 0 to fxray-function-groups - 1">;
+
+
 def ffine_grained_bitfield_accesses : Flag<["-"],
   "ffine-grained-bitfield-accesses">, Group<f_clang_Group>, Flags<[CC1Option]>,
   HelpText<"Use separate accesses for consecutive bitfield runs with legal widths and alignments.">;

clang/include/clang/Driver/XRayArgs.h

@@ -32,6 +32,8 @@ class XRayArgs {
   bool XRayRT = true;
   bool XRayIgnoreLoops = false;
   bool XRayFunctionIndex;
+  int XRayFunctionGroups = 1;
+  int XRaySelectedFunctionGroup;
 
 public:
   /// Parses the XRay arguments from an argument list.

clang/lib/CodeGen/CodeGenFunction.cpp

@@ -32,6 +32,7 @@
 #include "clang/Basic/TargetInfo.h"
 #include "clang/CodeGen/CGFunctionInfo.h"
 #include "clang/Frontend/FrontendDiagnostic.h"
+#include "llvm/ADT/ArrayRef.h"
 #include "llvm/Frontend/OpenMP/OMPIRBuilder.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Dominators.h"
@@ -40,6 +41,7 @@
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/MDBuilder.h"
 #include "llvm/IR/Operator.h"
+#include "llvm/Support/CRC.h"
 #include "llvm/Transforms/Utils/PromoteMemToReg.h"
 using namespace clang;
 using namespace CodeGen;
@@ -772,13 +774,16 @@ void CodeGenFunction::StartFunction(GlobalDecl GD, QualType RetTy,
         SanOpts.Mask &= ~SanitizerKind::Null;
 
   // Apply xray attributes to the function (as a string, for now)
+  bool AlwaysXRayAttr = false;
   if (const auto *XRayAttr = D ? D->getAttr<XRayInstrumentAttr>() : nullptr) {
     if (CGM.getCodeGenOpts().XRayInstrumentationBundle.has(
             XRayInstrKind::FunctionEntry) ||
         CGM.getCodeGenOpts().XRayInstrumentationBundle.has(
             XRayInstrKind::FunctionExit)) {
-      if (XRayAttr->alwaysXRayInstrument() && ShouldXRayInstrumentFunction())
+      if (XRayAttr->alwaysXRayInstrument() && ShouldXRayInstrumentFunction()) {
         Fn->addFnAttr("function-instrument", "xray-always");
+        AlwaysXRayAttr = true;
+      }
       if (XRayAttr->neverXRayInstrument())
         Fn->addFnAttr("function-instrument", "xray-never");
       if (const auto *LogArgs = D->getAttr<XRayLogArgsAttr>())
@@ -804,6 +809,16 @@ void CodeGenFunction::StartFunction(GlobalDecl GD, QualType RetTy,
     if (!CGM.getCodeGenOpts().XRayInstrumentationBundle.has(
             XRayInstrKind::FunctionEntry))
       Fn->addFnAttr("xray-skip-entry");
+
+    auto FuncGroups = CGM.getCodeGenOpts().XRayTotalFunctionGroups;
+    if (FuncGroups > 1) {
+      auto FuncName = llvm::makeArrayRef<uint8_t>(
+          CurFn->getName().bytes_begin(), CurFn->getName().bytes_end());
+      auto Group = crc32(FuncName) % FuncGroups;
+      if (Group != CGM.getCodeGenOpts().XRaySelectedFunctionGroup &&
+          !AlwaysXRayAttr)
+        Fn->addFnAttr("function-instrument", "xray-never");
+    }
   }
 
   unsigned Count, Offset;

clang/lib/Driver/XRayArgs.cpp

@@ -186,6 +186,21 @@ XRayArgs::XRayArgs(const ToolChain &TC, const ArgList &Args) {
           Modes.push_back(std::string(M));
     }
 
+  if (const Arg *A = Args.getLastArg(options::OPT_fxray_function_groups)) {
+    StringRef S = A->getValue();
+    if (S.getAsInteger(0, XRayFunctionGroups) || XRayFunctionGroups < 1)
+      D.Diag(clang::diag::err_drv_invalid_value) << A->getAsString(Args) << S;
+  }
+
+  if (const Arg *A =
+          Args.getLastArg(options::OPT_fxray_selected_function_group)) {
+    StringRef S = A->getValue();
+    if (S.getAsInteger(0, XRaySelectedFunctionGroup) ||
+        XRaySelectedFunctionGroup < 0 ||
+        XRaySelectedFunctionGroup >= XRayFunctionGroups)
+      D.Diag(clang::diag::err_drv_invalid_value) << A->getAsString(Args) << S;
+  }
+
   // Then we want to sort and unique the modes we've collected.
   llvm::sort(Modes);
   Modes.erase(std::unique(Modes.begin(), Modes.end()), Modes.end());
@@ -210,6 +225,17 @@ void XRayArgs::addArgs(const ToolChain &TC, const ArgList &Args,
   if (!XRayFunctionIndex)
     CmdArgs.push_back("-fno-xray-function-index");
 
+  if (XRayFunctionGroups > 1) {
+    CmdArgs.push_back(Args.MakeArgString(Twine("-fxray-function-groups=") +
+                                         Twine(XRayFunctionGroups)));
+  }
+
+  if (XRaySelectedFunctionGroup != 0) {
+    CmdArgs.push_back(
+        Args.MakeArgString(Twine("-fxray-selected-function-group=") +
+                           Twine(XRaySelectedFunctionGroup)));
+  }
+
   CmdArgs.push_back(Args.MakeArgString(Twine(XRayInstructionThresholdOption) +
                                        Twine(InstructionThreshold)));
 

clang/lib/Frontend/CompilerInvocation.cpp

@@ -1130,6 +1130,10 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
       getLastArgIntValue(Args, OPT_fxray_instruction_threshold_EQ, 200, Diags);
   Opts.XRayIgnoreLoops = Args.hasArg(OPT_fxray_ignore_loops);
   Opts.XRayOmitFunctionIndex = Args.hasArg(OPT_fno_xray_function_index);
+  Opts.XRayTotalFunctionGroups =
+      getLastArgIntValue(Args, OPT_fxray_function_groups, 1, Diags);
+  Opts.XRaySelectedFunctionGroup =
+      getLastArgIntValue(Args, OPT_fxray_selected_function_group, 0, Diags);
 
   auto XRayInstrBundles =
       Args.getAllArgValues(OPT_fxray_instrumentation_bundle);

clang/test/CodeGen/xray-function-groups.cpp

@@ -0,0 +1,56 @@
+// RUN: %clang_cc1 -fxray-instrument -fxray-instruction-threshold=1 -fxray-function-groups=3 -fxray-selected-function-group=0 \
+// RUN:            -emit-llvm -o - %s -triple x86_64-unknown-linux-gnu | FileCheck --check-prefix=GROUP0 %s
+
+// RUN: %clang_cc1 -fxray-instrument -fxray-instruction-threshold=1 -fxray-function-groups=3 -fxray-selected-function-group=1 \
+// RUN:            -emit-llvm -o - %s -triple x86_64-unknown-linux-gnu | FileCheck --check-prefix=GROUP1 %s
+
+// RUN: %clang_cc1 -fxray-instrument -fxray-instruction-threshold=1 -fxray-function-groups=3 -fxray-selected-function-group=2 \
+// RUN:            -emit-llvm -o - %s -triple x86_64-unknown-linux-gnu | FileCheck --check-prefix=GROUP2 %s
+
+static int foo() { // part of group 0
+  return 1;
+}
+
+int bar() { // part of group 2
+  return 1;
+}
+
+int yarr() { // part of group 1
+  foo();
+  return 1;
+}
+
+[[clang::xray_always_instrument]] int always() { // part of group 0
+  return 1;
+}
+
+[[clang::xray_never_instrument]] int never() { // part of group 1
+  return 1;
+}
+
+// GROUP0: define{{.*}} i32 @_Z3barv() #[[ATTRS_BAR:[0-9]+]] {
+// GROUP0: define{{.*}} i32 @_Z4yarrv() #[[ATTRS_BAR]] {
+// GROUP0: define{{.*}} i32 @_ZL3foov() #[[ATTRS_FOO:[0-9]+]] {
+// GROUP0: define{{.*}} i32 @_Z6alwaysv() #[[ATTRS_ALWAYS:[0-9]+]] {
+// GROUP0: define{{.*}} i32 @_Z5neverv() #[[ATTRS_NEVER:[0-9]+]] {
+// GROUP0-DAG: attributes #[[ATTRS_BAR]] = {{.*}} "function-instrument"="xray-never" {{.*}}
+// GROUP0-DAG: attributes #[[ATTRS_ALWAYS]] = {{.*}} "function-instrument"="xray-always" {{.*}}
+// GROUP0-DAG: attributes #[[ATTRS_NEVER]] = {{.*}} "function-instrument"="xray-never" {{.*}}
+
+// GROUP1: define{{.*}} i32 @_Z3barv() #[[ATTRS_BAR:[0-9]+]] {
+// GROUP1: define{{.*}} i32 @_Z4yarrv() #[[ATTRS_YARR:[0-9]+]] {
+// GROUP1: define{{.*}} i32 @_ZL3foov() #[[ATTRS_BAR]] {
+// GROUP1: define{{.*}} i32 @_Z6alwaysv() #[[ATTRS_ALWAYS:[0-9]+]] {
+// GROUP1: define{{.*}} i32 @_Z5neverv() #[[ATTRS_NEVER:[0-9]+]] {
+// GROUP1-DAG: attributes #[[ATTRS_BAR]] = {{.*}} "function-instrument"="xray-never" {{.*}}
+// GROUP1-DAG: attributes #[[ATTRS_ALWAYS]] = {{.*}} "function-instrument"="xray-always" {{.*}}
+// GROUP1-DAG: attributes #[[ATTRS_NEVER]] = {{.*}} "function-instrument"="xray-never" {{.*}}
+
+// GROUP2: define{{.*}} i32 @_Z3barv() #[[ATTRS_BAR:[0-9]+]] {
+// GROUP2: define{{.*}} i32 @_Z4yarrv() #[[ATTRS_YARR:[0-9]+]] {
+// GROUP2: define{{.*}} i32 @_ZL3foov() #[[ATTRS_YARR]] {
+// GROUP2: define{{.*}} i32 @_Z6alwaysv() #[[ATTRS_ALWAYS:[0-9]+]] {
+// GROUP2: define{{.*}} i32 @_Z5neverv() #[[ATTRS_NEVER:[0-9]+]] {
+// GROUP2-DAG: attributes #[[ATTRS_YARR]] = {{.*}} "function-instrument"="xray-never" {{.*}}
+// GROUP2-DAG: attributes #[[ATTRS_ALWAYS]] = {{.*}} "function-instrument"="xray-always" {{.*}}
+// GROUP2-DAG: attributes #[[ATTRS_NEVER]] = {{.*}} "function-instrument"="xray-never" {{.*}}

llvm/docs/XRay.rst

@@ -62,17 +62,18 @@ For example:
 
   clang -fxray-instrument ...
 
-By default, functions that have at least 200 instructions will get XRay
-instrumentation points. You can tweak that number through the
+By default, functions that have at least 200 instructions (or contain a loop) will
+get XRay instrumentation points. You can tweak that number through the
 ``-fxray-instruction-threshold=`` flag:
 
 ::
 
   clang -fxray-instrument -fxray-instruction-threshold=1 ...
 
-You can also specifically instrument functions in your binary to either always
-or never be instrumented using source-level attributes. You can do it using the
-GCC-style attributes or C++11-style attributes.
+The loop detection can be disabled with ``-fxray-ignore-loops`` to use only the
+instruction threshold. You can also specifically instrument functions in your
+binary to either always or never be instrumented using source-level attributes.
+You can do it using the GCC-style attributes or C++11-style attributes.
 
 .. code-block:: c++
 
@@ -309,6 +310,35 @@ libraries, distributed with the LLVM distribution. These are:
   instrumentation map in XRay-instrumented object files and binaries. The
   ``extract`` and ``stack`` subcommands uses this particular library.
 
+
+Minimizing Binary Size
+----------------------
+
+XRay supports several different instrumentation points including ``function-entry``,
+``function-exit``, ``custom``, and ``typed`` points. These can be enabled individually
+using the ``-fxray-instrumentaton-bundle=`` flag. For example if you only wanted to
+instrument function entry and custom points you could specify:
+
+::
+
+  clang -fxray-instrument -fxray-instrumentation-bundle=function-entry,custom ...
+
+This will omit the other sled types entirely, reducing the binary size. You can also
+instrument just a sampled subset of functions using instrumentation groups.
+For example, to instrument only a quarter of available functions invoke:
+
+::
+
+  clang -fxray-instrument -fxray-function-groups=4
+
+A subset will be chosen arbitrarily based on a hash of the function name. To sample a
+different subset you can specify ``-fxray-selected-function-group=`` with a group number
+in the range of 0 to ``xray-function-groups`` - 1.  Together these options could be used
+to produce multiple binaries with different instrumented subsets. If all you need is
+runtime control over which functions are being traced at any given time it is better
+to selectively patch and unpatch the individual functions you need using the XRay
+Runtime Library's ``__xray_patch_function()`` method.
+
 Future Work
 ===========