i386: Prefer PLT indirection for __fentry__ calls under -fPIC [PR119386]

Commit bde21de1205 ("i386: Honour -mdirect-extern-access when calling
__fentry__") updated the logic that emits mcount() / __fentry__() calls
into function prologues when profiling is enabled, to avoid GOT-based
indirect calls when a direct call would suffice.

There are two problems with that change:
- it relies on -mdirect-extern-access rather than -fno-plt to decide
  whether or not a direct [PLT based] call is appropriate;
- for the PLT case, it falls through to x86_print_call_or_nop(), which
  does not emit the @PLT suffix, resulting in the wrong relocation to be
  used (R_X86_64_PC32 instead of R_X86_64_PLT32)

Fix this by testing flag_plt instead of ix86_direct_extern_access, and
updating x86_print_call_or_nop() to take flag_pic and flag_plt into
account. This also ensures that -mnop-mcount works as expected when
emitting the PLT based profiling calls.

While at it, fix the 32-bit logic as well, and issue a PLT call unless
PLTs are explicitly disabled.

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119386

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>

gcc/ChangeLog:

	PR target/119386
	* config/i386/i386.cc (x86_print_call_or_nop): Add @PLT suffix
	where appropriate.
	(x86_function_profiler): Fall through to x86_print_call_or_nop()
	for PIC codegen when flag_plt is set.

gcc/testsuite/ChangeLog:

	PR target/119386
	* gcc.target/i386/pr119386-1.c: New test.
	* gcc.target/i386/pr119386-2.c: New test.

3 files changed, 32 insertions, 2 deletions

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index b172f71..38df84f 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -23164,6 +23164,12 @@ x86_print_call_or_nop (FILE *file, const char *target)
   if (flag_nop_mcount || !strcmp (target, "nop"))
     /* 5 byte nop: nopl 0(%[re]ax,%[re]ax,1) */
     fprintf (file, "1:" ASM_BYTE "0x0f, 0x1f, 0x44, 0x00, 0x00\n");
+  else if (!TARGET_PECOFF && flag_pic)
+    {
+      gcc_assert (flag_plt);
+
+      fprintf (file, "1:\tcall\t%s@PLT\n", target);
+    }
   else
     fprintf (file, "1:\tcall\t%s\n", target);
 }
@@ -23327,7 +23333,7 @@ x86_function_profiler (FILE *file, int labelno ATTRIBUTE_UNUSED)
 	      break;
 	    case CM_SMALL_PIC:
 	    case CM_MEDIUM_PIC:
-	      if (!ix86_direct_extern_access)
+	      if (!flag_plt)
 		{
 		  if (ASSEMBLER_DIALECT == ASM_INTEL)
 		    fprintf (file, "1:\tcall\t[QWORD PTR %s@GOTPCREL[rip]]\n",
@@ -23358,7 +23364,9 @@ x86_function_profiler (FILE *file, int labelno ATTRIBUTE_UNUSED)
 		 "\tleal\t%sP%d@GOTOFF(%%ebx), %%" PROFILE_COUNT_REGISTER "\n",
 		 LPREFIX, labelno);
 #endif
-      if (ASSEMBLER_DIALECT == ASM_INTEL)
+      if (flag_plt)
+	x86_print_call_or_nop (file, mcount_name);
+      else if (ASSEMBLER_DIALECT == ASM_INTEL)
 	fprintf (file, "1:\tcall\t[DWORD PTR %s@GOT[ebx]]\n", mcount_name);
       else
 	fprintf (file, "1:\tcall\t*%s@GOT(%%ebx)\n", mcount_name);
diff --git a/gcc/testsuite/gcc.target/i386/pr119386-1.c b/gcc/testsuite/gcc.target/i386/pr119386-1.c
new file mode 100644
index 0000000..9a0dc64
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr119386-1.c
@@ -0,0 +1,10 @@
+/* PR target/119386 */
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fpic -pg" } */
+/* { dg-final { scan-assembler "call\[ \t\]+mcount@PLT" } } */
+
+int
+main ()
+{
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr119386-2.c b/gcc/testsuite/gcc.target/i386/pr119386-2.c
new file mode 100644
index 0000000..3ea978e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr119386-2.c
@@ -0,0 +1,12 @@
+/* PR target/119386 */
+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fpic -fno-plt -pg" } */
+/* { dg-final { scan-assembler "call\[ \t\]+\\*mcount@GOTPCREL\\(" { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler "call\[ \t\]+\\*mcount@GOT\\(" { target ia32 } } } */
+
+
+int
+main ()
+{
+  return 0;
+}