[XRay] Reduce synthetic references emitted by XRay

Summary:
When we're building with XRay instrumentation, we use a trick that
preserves references from the function to a function sled index. This
index table lives in a separate section, and without this trick the
linker is free to garbage-collect this section and all the segments it
refers to. Until we're able to tell the linkers to preserve these
sections, we use this reference trick to keep around both the index and
the entries in the instrumentation map.

Before this change we emitted both a synthetic reference to the label in
the instrumentation map, and to the entry in the function map index.
This change removes the first synthetic reference and only emits one
synthetic reference to the index -- the index entry has the references
to the labels in the instrumentation map, so the linker will still
preserve those if the function itself is preserved.

This reduces the amount of synthetic references we emit from 16 bytes to
just 8 bytes in x86_64, and similarly to other platforms.

Reviewers: dblaikie

Subscribers: javed.absar, kpw, pelikan, llvm-commits

Differential Revision: https://reviews.llvm.org/D34340

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305880 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/AsmPrinter/AsmPrinter.cpp b/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
index ad348d7..c48fcaa 100644 (file)
--- a/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ b/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -2801,26 +2801,24 @@ void AsmPrinter::emitXRayTable() {
   }
 
   // Before we switch over, we force a reference to a label inside the
-  // xray_instr_map and xray_fn_idx sections. Since this function is always
-  // called just before the function's end, we assume that this is happening
-  // after the last return instruction. We also use the synthetic label in the
-  // xray_inster_map as a delimeter for the range of sleds for this function in
-  // the index.
+  // xray_fn_idx sections. This makes sure that the xray_fn_idx section is kept
+  // live by the linker if the function is not garbage-collected. Since this
+  // function is always called just before the function's end, we assume that
+  // this is happening after the last return instruction.
   auto WordSizeBytes = MAI->getCodePointerSize();
-  MCSymbol *SledsStart = OutContext.createTempSymbol("xray_synthetic_", true);
   MCSymbol *IdxRef = OutContext.createTempSymbol("xray_fn_idx_synth_", true);
   OutStreamer->EmitCodeAlignment(16);
-  OutStreamer->EmitSymbolValue(SledsStart, WordSizeBytes, false);
   OutStreamer->EmitSymbolValue(IdxRef, WordSizeBytes, false);
 
   // Now we switch to the instrumentation map section. Because this is done
   // per-function, we are able to create an index entry that will represent the
   // range of sleds associated with a function.
+  MCSymbol *SledsStart = OutContext.createTempSymbol("xray_sleds_start", true);
   OutStreamer->SwitchSection(InstMap);
   OutStreamer->EmitLabel(SledsStart);
   for (const auto &Sled : Sleds)
     Sled.emit(WordSizeBytes, OutStreamer.get(), CurrentFnSym);
-  MCSymbol *SledsEnd = OutContext.createTempSymbol("xray_synthetic_end", true);
+  MCSymbol *SledsEnd = OutContext.createTempSymbol("xray_sleds_end", true);
   OutStreamer->EmitLabel(SledsEnd);
 
   // We then emit a single entry in the index per function. We use the symbols

diff --git a/test/CodeGen/AArch64/xray-attribute-instrumentation.ll b/test/CodeGen/AArch64/xray-attribute-instrumentation.ll
index 38b62a7..5f01c7c 100644 (file)
--- a/test/CodeGen/AArch64/xray-attribute-instrumentation.ll
+++ b/test/CodeGen/AArch64/xray-attribute-instrumentation.ll
@@ -25,9 +25,9 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
 ; CHECK-NEXT:  ret
 }
 ; CHECK:       .p2align 4
-; CHECK-NEXT:  .xword .Lxray_synthetic_0
 ; CHECK-NEXT:  .xword .Lxray_fn_idx_synth_0
 ; CHECK-NEXT:  .section xray_instr_map,{{.*}}
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0
 ; CHECK:       .xword .Lxray_sled_0
 ; CHECK:       .xword .Lxray_sled_1
+; CHECK-LABEL: Lxray_sleds_end0

diff --git a/test/CodeGen/AArch64/xray-tail-call-sled.ll b/test/CodeGen/AArch64/xray-tail-call-sled.ll
index fb89950..a7e993b 100644 (file)
--- a/test/CodeGen/AArch64/xray-tail-call-sled.ll
+++ b/test/CodeGen/AArch64/xray-tail-call-sled.ll
@@ -28,21 +28,20 @@ define i32 @callee() nounwind noinline uwtable "function-instrument"="xray-alway
 ; CHECK-NEXT:  ret\r
 }\r
 ; CHECK:       .p2align 4\r
-; CHECK-NEXT:  .xword .Lxray_synthetic_0\r
 ; CHECK-NEXT:  .xword .Lxray_fn_idx_synth_0\r
 ; CHECK-NEXT:  .section xray_instr_map,{{.*}}\r
-; CHECK-LABEL: Lxray_synthetic_0:\r
+; CHECK-LABEL: Lxray_sleds_start0:\r
 ; CHECK:       .xword .Lxray_sled_0\r
 ; CHECK:       .xword .Lxray_sled_1\r
-; CHECK-LABEL: Lxray_synthetic_end0:\r
+; CHECK-LABEL: Lxray_sleds_end0:\r
 ; CHECK:       .section xray_fn_idx,{{.*}}\r
 ; CHECK-LABEL: Lxray_fn_idx_synth_0:\r
-; CHECK:       .xword .Lxray_synthetic_0\r
-; CHECK-NEXT:  .xword .Lxray_synthetic_end0\r
+; CHECK:       .xword .Lxray_sleds_start0\r
+; CHECK-NEXT:  .xword .Lxray_sleds_end0\r
 \r
 define i32 @caller() nounwind noinline uwtable "function-instrument"="xray-always" {\r
 ; CHECK:       .p2align        2\r
-; CHECK-LABEL: .Lxray_sled_2:\r
+; CHECK-LABEL: Lxray_sled_2:\r
 ; CHECK-NEXT:  b       #32\r
 ; CHECK-NEXT:  nop\r
 ; CHECK-NEXT:  nop\r
@@ -53,7 +52,7 @@ define i32 @caller() nounwind noinline uwtable "function-instrument"="xray-alway
 ; CHECK-NEXT:  nop\r
 ; CHECK-LABEL: .Ltmp2:\r
 ; CHECK:       .p2align        2\r
-; CHECK-LABEL: .Lxray_sled_3:\r
+; CHECK-LABEL: Lxray_sled_3:\r
 ; CHECK-NEXT:  b       #32\r
 ; CHECK-NEXT:  nop\r
 ; CHECK-NEXT:  nop\r
@@ -68,14 +67,13 @@ define i32 @caller() nounwind noinline uwtable "function-instrument"="xray-alway
   ret i32 %retval\r
 }\r
 ; CHECK:       .p2align 4\r
-; CHECK-NEXT:  .xword .Lxray_synthetic_1\r
 ; CHECK-NEXT:  .xword .Lxray_fn_idx_synth_1\r
 ; CHECK-NEXT:  .section xray_instr_map,{{.*}}\r
-; CHECK-LABEL: Lxray_synthetic_1:\r
+; CHECK-LABEL: Lxray_sleds_start1:\r
 ; CHECK:       .xword .Lxray_sled_2\r
 ; CHECK:       .xword .Lxray_sled_3\r
-; CHECK-LABEL: Lxray_synthetic_end1:\r
+; CHECK-LABEL: Lxray_sleds_end1:\r
 ; CHECK:       .section xray_fn_idx,{{.*}}\r
 ; CHECK-LABEL: Lxray_fn_idx_synth_1:\r
-; CHECK:       .xword .Lxray_synthetic_1\r
-; CHECK-NEXT:  .xword .Lxray_synthetic_end1\r
+; CHECK:       .xword .Lxray_sleds_start1\r
+; CHECK-NEXT:  .xword .Lxray_sleds_end1\r

diff --git a/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll b/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll
index 5e3c45c..5017de8 100644 (file)
--- a/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll
+++ b/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll
@@ -24,14 +24,13 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
 ; CHECK-NEXT:  bx      lr
 }
 ; CHECK:       .p2align 4
-; CHECK-NEXT:  .long {{.*}}Lxray_synthetic_0
 ; CHECK-NEXT:  .long {{.*}}Lxray_fn_idx_synth_0
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map{{.*}}
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
 ; CHECK:       .long {{.*}}Lxray_sled_0
 ; CHECK:       .long {{.*}}Lxray_sled_1
-; CHECK-LABEL: Lxray_synthetic_end0:
+; CHECK-LABEL: Lxray_sleds_end0:
 ; CHECK:       .section {{.*}}xray_fn_idx{{.*}}
 ; CHECK-LABEL: Lxray_fn_idx_synth_0:
-; CHECK:       .long {{.*}}Lxray_synthetic_0
-; CHECK-NEXT:  .long {{.*}}Lxray_synthetic_end0
+; CHECK:       .long {{.*}}Lxray_sleds_start0
+; CHECK-NEXT:  .long {{.*}}Lxray_sleds_end0

diff --git a/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll b/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll
index 739151f..118c02a 100644 (file)
--- a/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll
+++ b/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll
@@ -24,15 +24,14 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
 ; CHECK-NEXT:  bx lr
 }
 ; CHECK:       .p2align 4
-; CHECK-NEXT:  .long {{.*}}Lxray_synthetic_0
 ; CHECK-NEXT:  .long {{.*}}Lxray_fn_idx_synth_0
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map{{.*}}
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
 ; CHECK:       .long {{.*}}Lxray_sled_0
 ; CHECK:       .long {{.*}}Lxray_sled_1
-; CHECK-LABEL: Lxray_synthetic_end0:
+; CHECK-LABEL: Lxray_sleds_end0:
 ; CHECK:       .section {{.*}}xray_fn_idx{{.*}}
 ; CHECK-LABEL: Lxray_fn_idx_synth_0:
-; CHECK:       .long {{.*}}xray_synthetic_0
-; CHECK-NEXT:  .long {{.*}}xray_synthetic_end0
+; CHECK:       .long {{.*}}xray_sleds_start0
+; CHECK-NEXT:  .long {{.*}}xray_sleds_end0
 

diff --git a/test/CodeGen/X86/xray-attribute-instrumentation.ll b/test/CodeGen/X86/xray-attribute-instrumentation.ll
index 7c60327..00b45f8 100644 (file)
--- a/test/CodeGen/X86/xray-attribute-instrumentation.ll
+++ b/test/CodeGen/X86/xray-attribute-instrumentation.ll
@@ -14,17 +14,16 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 }
 ; CHECK:       .p2align 4, 0x90
-; CHECK-NEXT:  .quad {{.*}}xray_synthetic_0
 ; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_0
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
 ; CHECK:       .quad {{.*}}xray_sled_0
 ; CHECK:       .quad {{.*}}xray_sled_1
-; CHECK-LABEL: Lxray_synthetic_end0:
+; CHECK-LABEL: Lxray_sleds_end0:
 ; CHECK:       .section {{.*}}xray_fn_idx
 ; CHECK-LABEL: Lxray_fn_idx_synth_0:
-; CHECK:       .quad {{.*}}xray_synthetic_0
-; CHECK-NEXT:  .quad {{.*}}xray_synthetic_end0
+; CHECK:       .quad {{.*}}xray_sleds_start0
+; CHECK-NEXT:  .quad {{.*}}xray_sleds_end0
 
 
 ; We test multiple returns in a single function to make sure we're getting all
@@ -52,15 +51,14 @@ NotEqual:
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 }
 ; CHECK:       .p2align 4, 0x90
-; CHECK-NEXT:  .quad {{.*}}xray_synthetic_1
 ; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_1
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map
-; CHECK-LABEL: Lxray_synthetic_1:
+; CHECK-LABEL: Lxray_sleds_start1:
 ; CHECK:       .quad {{.*}}xray_sled_2
 ; CHECK:       .quad {{.*}}xray_sled_3
 ; CHECK:       .quad {{.*}}xray_sled_4
-; CHECK-LABEL: Lxray_synthetic_end1:
+; CHECK-LABEL: Lxray_sleds_end1:
 ; CHECK:       .section {{.*}}xray_fn_idx
 ; CHECK-LABEL: Lxray_fn_idx_synth_1:
-; CHECK:       .quad {{.*}}xray_synthetic_1
-; CHECK-NEXT:  .quad {{.*}}xray_synthetic_end1
+; CHECK:       .quad {{.*}}xray_sleds_start1
+; CHECK-NEXT:  .quad {{.*}}xray_sleds_end1

diff --git a/test/CodeGen/X86/xray-custom-log.ll b/test/CodeGen/X86/xray-custom-log.ll
index 63625d4..69fd0f3 100644 (file)
--- a/test/CodeGen/X86/xray-custom-log.ll
+++ b/test/CodeGen/X86/xray-custom-log.ll
@@ -17,7 +17,7 @@ define i32 @fn() nounwind noinline uwtable "function-instrument"="xray-always" {
     ret i32 0
 }
 ; CHECK:       .section {{.*}}xray_instr_map
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
 ; CHECK:       .quad {{.*}}xray_event_sled_0
 
 declare void @llvm.xray.customevent(i8*, i32)

diff --git a/test/CodeGen/X86/xray-log-args.ll b/test/CodeGen/X86/xray-log-args.ll
index a551868..6fe450a 100644 (file)
--- a/test/CodeGen/X86/xray-log-args.ll
+++ b/test/CodeGen/X86/xray-log-args.ll
@@ -6,7 +6,7 @@
 define i32 @callee(i32 %arg) nounwind noinline uwtable "function-instrument"="xray-always" "xray-log-args"="1" {
   ret i32 %arg
 }
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
 ; CHECK:       .quad   {{\.?}}Lxray_sled_0
 ; CHECK:       .quad   {{_?}}callee
 ; CHECK:       .byte   3
@@ -22,7 +22,7 @@ define i32 @caller(i32 %arg) nounwind noinline uwtable "function-instrument"="xr
   %retval = tail call i32 @callee(i32 %arg)
   ret i32 %retval
 }
-; CHECK-LABEL: Lxray_synthetic_1:
+; CHECK-LABEL: Lxray_sleds_start1:
 ; CHECK:       .quad   {{\.?}}Lxray_sled_2
 ; CHECK:       .quad   {{_?}}caller
 ; CHECK:       .byte   3

diff --git a/test/CodeGen/X86/xray-tail-call-sled.ll b/test/CodeGen/X86/xray-tail-call-sled.ll
index b12c78a..c4a973e 100644 (file)
--- a/test/CodeGen/X86/xray-tail-call-sled.ll
+++ b/test/CodeGen/X86/xray-tail-call-sled.ll
@@ -14,17 +14,16 @@ define i32 @callee() nounwind noinline uwtable "function-instrument"="xray-alway
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 }
 ; CHECK:       .p2align 4, 0x90
-; CHECK-NEXT:  .quad {{.*}}xray_synthetic_0{{.*}}
 ; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_0{{.*}}
 ; CHECK-NEXT:  .section {{.*}}xray_instr_map
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
 ; CHECK:       .quad {{.*}}xray_sled_0
 ; CHECK:       .quad {{.*}}xray_sled_1
-; CHECK-LABEL: Lxray_synthetic_end0:
+; CHECK-LABEL: Lxray_sleds_end0:
 ; CHECK-NEXT:  .section {{.*}}xray_fn_idx
 ; CHECK-LABEL: Lxray_fn_idx_synth_0:
-; CHECK:       .quad {{.*}}xray_synthetic_0
-; CHECK-NEXT:  .quad {{.*}}xray_synthetic_end0
+; CHECK:       .quad {{.*}}xray_sleds_start0
+; CHECK-NEXT:  .quad {{.*}}xray_sleds_end0
 
 define i32 @caller() nounwind noinline uwtable "function-instrument"="xray-always" {
 ; CHECK:       .p2align 1, 0x90
@@ -42,13 +41,12 @@ define i32 @caller() nounwind noinline uwtable "function-instrument"="xray-alway
   ret i32 %retval
 }
 ; CHECK:       .p2align 4, 0x90
-; CHECK-NEXT:  .quad {{.*}}xray_synthetic_1{{.*}}
 ; CHECK-NEXT:  .quad {{.*}}xray_fn_idx_synth_1{{.*}}
-; CHECK-LABEL: Lxray_synthetic_1:
+; CHECK-LABEL: Lxray_sleds_start1:
 ; CHECK:       .quad {{.*}}xray_sled_2
 ; CHECK:       .quad {{.*}}xray_sled_3
-; CHECK-LABEL: Lxray_synthetic_end1:
+; CHECK-LABEL: Lxray_sleds_end1:
 ; CHECK:       .section {{.*}}xray_fn_idx
 ; CHECK-LABEL: Lxray_fn_idx_synth_1:
-; CHECK:       .quad {{.*}}xray_synthetic_1
-; CHECK:       .quad {{.*}}xray_synthetic_end1
+; CHECK:       .quad {{.*}}xray_sleds_start1
+; CHECK:       .quad {{.*}}xray_sleds_end1