i386: Insert ENDBR before the profiling counter callhjl/pr82699

ENDBR must be the first instruction of a function.  This patch queues
ENDBR if we need to put the profiling counter call before the prologue
and generate ENDBR before the profiling counter call.

gcc/

	PR target/82699
	* config/i386/i386.c (rest_of_insert_endbranch): Set
	endbr_queued_at_entrance to true and don't insert ENDBR if
	x86_function_profiler will be called.
	(x86_function_profiler): Insert ENDBR if endbr_queued_at_entrance
	is true.
	* config/i386/i386.h (machine_function): Add
	endbr_queued_at_entrance.

gcc/testsuite/

	PR target/82699
	* gcc.target/i386/pr82699-1.c: New file.
	* gcc.target/i386/pr82699-2.c: Likewise.
	* gcc.target/i386/pr82699-3.c: Likewise.
	* gcc.target/i386/pr82699-4.c: Likewise.
	* gcc.target/i386/pr82699-5.c: Likewise.
	* gcc.target/i386/pr82699-6.c: Likewise.

8 files changed, 83 insertions, 4 deletions

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index d2188ad6086..7974a915b38 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -2590,11 +2590,17 @@ rest_of_insert_endbranch (void)
 			 TYPE_ATTRIBUTES (TREE_TYPE (cfun->decl)))
       && !cgraph_node::get (cfun->decl)->only_called_directly_p ())
     {
-      cet_eb = gen_nop_endbr ();
+      /* Queue ENDBR insertion to x86_function_profiler.  */
+      if (crtl->profile && flag_fentry)
+	cfun->machine->endbr_queued_at_entrance = true;
+      else
+	{
+	  cet_eb = gen_nop_endbr ();
 
-      bb = ENTRY_BLOCK_PTR_FOR_FN (cfun)->next_bb;
-      insn = BB_HEAD (bb);
-      emit_insn_before (cet_eb, insn);
+	  bb = ENTRY_BLOCK_PTR_FOR_FN (cfun)->next_bb;
+	  insn = BB_HEAD (bb);
+	  emit_insn_before (cet_eb, insn);
+	}
     }
 
   bb = 0;
@@ -40427,6 +40433,10 @@ x86_function_profiler (FILE *file, int labelno ATTRIBUTE_UNUSED)
 {
   const char *mcount_name = (flag_fentry ? MCOUNT_NAME_BEFORE_PROLOGUE
 					 : MCOUNT_NAME);
+
+  if (cfun->machine->endbr_queued_at_entrance)
+    fprintf (file, "\t%s\n", TARGET_64BIT ? "endbr64" : "endbr32");
+
   if (TARGET_64BIT)
     {
 #ifndef NO_PROFILE_COUNTERS
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 27fc9f08cc7..925557d32cb 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2581,6 +2581,9 @@ struct GTY(()) machine_function {
   /* Nonzero if the function places outgoing arguments on stack.  */
   BOOL_BITFIELD outgoing_args_on_stack : 1;
 
+  /* If true, ENDBR is queued at function entrance.  */
+  BOOL_BITFIELD endbr_queued_at_entrance : 1;
+
   /* During prologue/epilogue generation, the current frame state.
      Otherwise, the frame state at the end of the prologue.  */
   struct machine_frame_state fs;
diff --git a/gcc/testsuite/gcc.target/i386/pr82699-1.c b/gcc/testsuite/gcc.target/i386/pr82699-1.c
new file mode 100644
index 00000000000..4fc404753e8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr82699-1.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fcf-protection -mcet -pg -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr82699-2.c b/gcc/testsuite/gcc.target/i386/pr82699-2.c
new file mode 100644
index 00000000000..4fb9cb9e68b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr82699-2.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fcf-protection -mcet -pg -mfentry -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr82699-3.c b/gcc/testsuite/gcc.target/i386/pr82699-3.c
new file mode 100644
index 00000000000..92d84ee4ab5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr82699-3.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fpic -fcf-protection -mcet -pg -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr82699-4.c b/gcc/testsuite/gcc.target/i386/pr82699-4.c
new file mode 100644
index 00000000000..415ce3b913a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr82699-4.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target { *-*-linux* && { ! ia32 } } } } */
+/* { dg-options "-O2 -fpic -fcf-protection -mcet -pg -mfentry -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr82699-5.c b/gcc/testsuite/gcc.target/i386/pr82699-5.c
new file mode 100644
index 00000000000..c0820352ac2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr82699-5.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fcf-protection -mcet -mfentry -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr82699-6.c b/gcc/testsuite/gcc.target/i386/pr82699-6.c
new file mode 100644
index 00000000000..c142ccb12f6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr82699-6.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fcf-protection -mcet -pg -mfentry -mrecord-mcount -mnop-mcount -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}