Index: bolt/lib/Rewrite/RewriteInstance.cpp
===================================================================
--- bolt/lib/Rewrite/RewriteInstance.cpp
+++ bolt/lib/Rewrite/RewriteInstance.cpp
@@ -1839,8 +1839,9 @@
     exit(1);
   }
 
-  if (opts::ReorderFunctions != ReorderFunctions::RT_NONE &&
-      !opts::HotText.getNumOccurrences()) {
+  if (opts::Instrument ||
+      (opts::ReorderFunctions != ReorderFunctions::RT_NONE &&
+       !opts::HotText.getNumOccurrences())) {
     opts::HotText = true;
   } else if (opts::HotText && !BC->HasRelocations) {
     errs() << "BOLT-WARNING: hot text is disabled in non-relocation mode\n";
Index: bolt/runtime/common.h
===================================================================
--- bolt/runtime/common.h
+++ bolt/runtime/common.h
@@ -165,6 +165,20 @@
 // Anonymous namespace covering everything but our library entry point
 namespace {
 
+// Get the difference between runtime addrress of .text section and
+// static address in section header table. Can be extracted from arbitrary
+// pc value recorded at runtime to get the corresponding static address, which
+// in turn can be used to search for indirect call description. Needed because
+// indirect call descriptions are read-only non-relocatable data.
+uint64_t getTextBaseAddress() {
+  uint64_t DynAddr;
+  uint64_t StaticAddr;
+  __asm__ volatile("leaq __hot_end(%%rip), %0\n\t"
+                   "movabsq $__hot_end, %1\n\t"
+                   : "=r"(DynAddr), "=r"(StaticAddr));
+  return DynAddr - StaticAddr;
+}
+
 constexpr uint32_t BufSize = 10240;
 
 #define _STRINGIFY(x) #x
Index: bolt/runtime/instr.cpp
===================================================================
--- bolt/runtime/instr.cpp
+++ bolt/runtime/instr.cpp
@@ -215,6 +215,12 @@
 /// __bolt_instr_setup, our initialization routine.
 BumpPtrAllocator *GlobalAlloc;
 
+// Base address which we substract from recorded PC values when searching for
+// indirect call description entries. Needed because indCall descriptions are
+// mapped read-only and contain static addresses. Initialized in
+// __bolt_instr_setup.
+uint64_t TextBaseAddress = 0;
+
 // Storage for GlobalAlloc which can be shared if not using
 // instrumentation-file-append-pid.
 void *GlobalMetadataStorage;
@@ -1389,7 +1395,7 @@
   const IndCallDescription *CallsiteDesc =
       &Ctx->IndCallDescriptions[CallsiteID];
   const IndCallTargetDescription *TargetDesc =
-      Ctx->lookupIndCallTarget(Entry.Key);
+      Ctx->lookupIndCallTarget(Entry.Key - TextBaseAddress);
   if (!TargetDesc) {
     DEBUG(report("Failed to lookup indirect call target\n"));
     char LineBuf[BufSize];
@@ -1607,6 +1613,7 @@
 extern "C" void __attribute((force_align_arg_pointer)) __bolt_instr_setup() {
   __bolt_ind_call_counter_func_pointer = __bolt_instr_indirect_call;
   __bolt_ind_tailcall_counter_func_pointer = __bolt_instr_indirect_tailcall;
+  TextBaseAddress = getTextBaseAddress();
 
   const uint64_t CountersStart =
       reinterpret_cast<uint64_t>(&__bolt_instr_locations[0]);
Index: bolt/test/runtime/instrumentation-indirect-2.c
===================================================================
--- /dev/null
+++ bolt/test/runtime/instrumentation-indirect-2.c
@@ -0,0 +1,168 @@
+// Check that indirect call hash tables properly register multiple calls,
+// and that calls from different processes don't get mixed up when using
+// --instrumentation-file-append-pid.
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+__attribute__((noinline)) void funcA(int pid) { printf("funcA %d\n", pid); }
+__attribute__((noinline)) void funcB(int pid) { printf("funcB %d\n", pid); }
+__attribute__((noinline)) void funcC(int pid) { printf("funcC %d\n", pid); }
+__attribute__((noinline)) void funcD(int pid) { printf("funcD %d\n", pid); }
+__attribute__((noinline)) void funcE(int pid) { printf("funcE %d\n", pid); }
+__attribute__((noinline)) void funcF(int pid) { printf("funcF %d\n", pid); }
+__attribute__((noinline)) void funcG(int pid) { printf("funcG %d\n", pid); }
+__attribute__((noinline)) void funcH(int pid) { printf("funcH %d\n", pid); }
+__attribute__((noinline)) void funcI(int pid) { printf("funcI %d\n", pid); }
+__attribute__((noinline)) void funcJ(int pid) { printf("funcJ %d\n", pid); }
+__attribute__((noinline)) void funcK(int pid) { printf("funcK %d\n", pid); }
+__attribute__((noinline)) void funcL(int pid) { printf("funcL %d\n", pid); }
+__attribute__((noinline)) void funcM(int pid) { printf("funcM %d\n", pid); }
+__attribute__((noinline)) void funcN(int pid) { printf("funcN %d\n", pid); }
+__attribute__((noinline)) void funcO(int pid) { printf("funcO %d\n", pid); }
+__attribute__((noinline)) void funcP(int pid) { printf("funcP %d\n", pid); }
+
+int main() {
+
+  void (*funcs[])(int) = {funcA, funcB, funcC, funcD, funcE, funcF,
+                          funcG, funcH, funcI, funcJ, funcK, funcL,
+                          funcM, funcN, funcO, funcP};
+  int i;
+
+  switch (fork()) {
+  case -1:
+    printf("Failed to fork!\n");
+    exit(-1);
+    break;
+  case 0:
+    i = 0;
+    break;
+  default:
+    i = 1;
+    break;
+  }
+  int pid = getpid();
+  for (; i < sizeof(funcs) / sizeof(void *); i += 2) {
+    funcs[i](pid);
+  }
+
+  return 0;
+}
+/*
+REQUIRES: system-linux, shell
+
+RUN: %clang %cflags %s -o %t.exe -Wl,-q -no-pie -fno-pie
+
+RUN: llvm-bolt %t.exe --instrument --instrumentation-file=%t.fdata \
+RUN:   --conservative-instrumentation -o %t.instrumented_conservative \
+RUN: --instrumentation-sleep-time=1 --instrumentation-no-counters-clear \
+RUN: --instrumentation-wait-forks
+
+# Instrumented program needs to finish returning zero
+# Both output and profile must contain all 16 functions
+RUN: %t.instrumented_conservative > %t.output
+# Wait for profile and output to be fully written
+RUN: bash %S/wait_file.sh %t.output
+RUN: bash %S/wait_file.sh %t.fdata
+RUN: cat %t.output | FileCheck %s --check-prefix=CHECK-OUTPUT
+RUN: cat %t.fdata | FileCheck %s --check-prefix=CHECK-COMMON-PROF
+
+CHECK-OUTPUT-DAG: funcA
+CHECK-OUTPUT-DAG: funcB
+CHECK-OUTPUT-DAG: funcC
+CHECK-OUTPUT-DAG: funcD
+CHECK-OUTPUT-DAG: funcE
+CHECK-OUTPUT-DAG: funcF
+CHECK-OUTPUT-DAG: funcG
+CHECK-OUTPUT-DAG: funcH
+CHECK-OUTPUT-DAG: funcI
+CHECK-OUTPUT-DAG: funcJ
+CHECK-OUTPUT-DAG: funcK
+CHECK-OUTPUT-DAG: funcL
+CHECK-OUTPUT-DAG: funcM
+CHECK-OUTPUT-DAG: funcN
+CHECK-OUTPUT-DAG: funcO
+CHECK-OUTPUT-DAG: funcP
+
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcA 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcB 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcC 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcD 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcE 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcF 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcG 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcH 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcI 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcJ 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcK 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcL 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcM 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcN 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcO 0 0 1
+CHECK-COMMON-PROF-DAG: 1 main {{[0-9a-f]+}} 1 funcP 0 0 1
+
+RUN: llvm-bolt %t.exe --instrument --instrumentation-file=%t \
+RUN:   --instrumentation-file-append-pid \
+RUN:   -o %t.instrumented
+
+RUN: %t.instrumented > %t.output
+# Wait till output is fully written in case child outlives parent
+RUN: bash %S/wait_file.sh %t.output
+# Make sure all functions were called
+RUN: cat %t.output | FileCheck %s --check-prefix=CHECK-OUTPUT
+
+RUN: child_pid=$(cat %t.output | grep funcA | awk '{print $2;}')
+RUN: par_pid=$(cat %t.output | grep funcB | awk '{print $2;}')
+
+RUN: bash %S/wait_file.sh %t.output %t.$child_pid.fdata
+RUN: bash %S/wait_file.sh %t.output %t.$par_pid.fdata
+
+RUN: mv %t.$child_pid.fdata %t.child.fdata
+RUN: mv %t.$par_pid.fdata %t.parent.fdata
+
+# Instrumented binary must produce two profiles with only local calls
+# recorded. Functions called only in child should not appear in parent's
+# process and vice versa.
+RUN: cat %t.child.fdata | FileCheck %s --check-prefix=CHECK-CHILD
+RUN: cat %t.child.fdata | FileCheck %s --check-prefix=CHECK-NOCHILD
+RUN: cat %t.parent.fdata | FileCheck %s --check-prefix=CHECK-PARENT
+RUN: cat %t.parent.fdata | FileCheck %s --check-prefix=CHECK-NOPARENT
+
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcA 0 0 1
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcC 0 0 1
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcE 0 0 1
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcG 0 0 1
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcI 0 0 1
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcK 0 0 1
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcM 0 0 1
+CHECK-CHILD-DAG: 1 main {{[0-9a-f]+}} 1 funcO 0 0 1
+
+CHECK-NOCHILD-NOT: funcB
+CHECK-NOCHILD-NOT: funcD
+CHECK-NOCHILD-NOT: funcF
+CHECK-NOCHILD-NOT: funcH
+CHECK-NOCHILD-NOT: funcJ
+CHECK-NOCHILD-NOT: funcL
+CHECK-NOCHILD-NOT: funcN
+CHECK-NOCHILD-NOT: funcP
+
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcB 0 0 1
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcD 0 0 1
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcF 0 0 1
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcH 0 0 1
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcJ 0 0 1
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcL 0 0 1
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcN 0 0 1
+CHECK-PARENT-DAG: 1 main {{[0-9a-f]+}} 1 funcP 0 0 1
+
+CHECK-NOPARENT-NOT: funcA
+CHECK-NOPARENT-NOT: funcC
+CHECK-NOPARENT-NOT: funcE
+CHECK-NOPARENT-NOT: funcG
+CHECK-NOPARENT-NOT: funcI
+CHECK-NOPARENT-NOT: funcK
+CHECK-NOPARENT-NOT: funcM
+CHECK-NOPARENT-NOT: funcO
+
+ */
Index: bolt/test/runtime/wait_file.sh
===================================================================
--- /dev/null
+++ bolt/test/runtime/wait_file.sh
@@ -0,0 +1,38 @@
+#!/bin/bash
+
+check_file() {
+    local file="$1"
+    if [ -z "$file" ]; then
+        echo "No file passed!"
+        exit 1
+    fi
+    if [ ! -f "$file" ]; then
+        return 1
+    fi
+
+    fuser "$file" &> /dev/null
+    if [ $? -eq 0 ]; then
+        return 1
+    fi
+    return 0
+}
+
+wait_file() {
+    local file="$1"
+    local max_sleep=10
+    check_file "$file"
+    local ret=$?
+    while [ $ret -ne 0 ] && [ $max_sleep -ne 0 ]; do
+        sleep 1
+        max_sleep=$((max_sleep - 1))
+        check_file $file
+        ret=$?
+    done
+    if [ $max_sleep -eq 0 ]; then
+        echo "The file does not exist or the test hung!"
+        exit 1
+    fi
+
+}
+file="$1"
+wait_file "$file"