[v2] rs6000: Rework ELFv2 support for -fpatchable-function-entry* [PR99888]

diff --git a/gcc/config/rs6000/rs6000-internal.h b/gcc/config/rs6000/rs6000-internal.h
index b9e82c0468d..da809d1ac8b 100644
--- a/gcc/config/rs6000/rs6000-internal.h
+++ b/gcc/config/rs6000/rs6000-internal.h
@@ -182,10 +182,15 @@  extern tree rs6000_fold_builtin (tree fndecl ATTRIBUTE_UNUSED,
 			         tree *args ATTRIBUTE_UNUSED,
 			         bool ignore ATTRIBUTE_UNUSED);

+extern void rs6000_print_patchable_function_entry (FILE *,
+						   unsigned HOST_WIDE_INT,
+						   bool);
+
 extern bool rs6000_passes_float;
 extern bool rs6000_passes_long_double;
 extern bool rs6000_passes_vector;
 extern bool rs6000_returns_struct;
 extern bool cpu_builtin_p;

+
 #endif
diff --git a/gcc/config/rs6000/rs6000-logue.cc b/gcc/config/rs6000/rs6000-logue.cc
index 59fe1c8cb8b..3e2b1773154 100644
--- a/gcc/config/rs6000/rs6000-logue.cc
+++ b/gcc/config/rs6000/rs6000-logue.cc
@@ -4013,11 +4013,43 @@  rs6000_output_function_prologue (FILE *file)
 	  fprintf (file, "\tadd 2,2,12\n");
 	}

+      unsigned short patch_area_size = crtl->patch_area_size;
+      unsigned short patch_area_entry = crtl->patch_area_entry;
+      /* Need to emit the patching area.  */
+      if (patch_area_size > 0)
+	{
+	  cfun->machine->global_entry_emitted = true;
+	  /* As ELFv2 ABI shows, the allowable bytes between the global
+	     and local entry points are 0, 4, 8, 16, 32 and 64 when
+	     there is a local entry point.  Considering there are two
+	     non-prefixed instructions for global entry point prologue
+	     (8 bytes), the count for patchable NOPs before local entry
+	     point would be 2, 6 and 14.  It's possible to support those
+	     other counts of NOPs by not making a local entry point, but
+	     we don't have clear user cases for them, so leave them
+	     unsupported for now.  */
+	  if (patch_area_entry > 0)
+	    {
+	      if (patch_area_entry != 2
+		  && patch_area_entry != 6
+		  && patch_area_entry != 14)
+		error ("unsupported number of nops before function entry (%u)",
+		       patch_area_entry);
+	      rs6000_print_patchable_function_entry (file, patch_area_entry,
+						     true);
+	      patch_area_size -= patch_area_entry;
+	    }
+	}
+
       fputs ("\t.localentry\t", file);
       assemble_name (file, name);
       fputs (",.-", file);
       assemble_name (file, name);
       fputs ("\n", file);
+      /* Emit the NOPs after local entry.  */
+      if (patch_area_size > 0)
+	rs6000_print_patchable_function_entry (file, patch_area_size,
+					       patch_area_entry == 0);
     }

   else if (rs6000_pcrel_p ())
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 777a06599c3..c79a0ee7a49 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -14898,8 +14898,14 @@  rs6000_print_patchable_function_entry (FILE *file,
   if (!(TARGET_64BIT && DEFAULT_ABI != ABI_ELFv2)
       && HAVE_GAS_SECTION_LINK_ORDER)
     flags |= SECTION_LINK_ORDER;
-  default_print_patchable_function_entry_1 (file, patch_area_size, record_p,
-					    flags);
+  bool global_entry_needed_p = rs6000_global_entry_point_prologue_needed_p ();
+  /* For a function which needs global entry point, we will emit the
+     patchable area before and after local entry point under the control of
+     cfun->machine->global_entry_emitted, see the handling in function
+     rs6000_output_function_prologue.  */
+  if (!global_entry_needed_p || cfun->machine->global_entry_emitted)
+    default_print_patchable_function_entry_1 (file, patch_area_size, record_p,
+					      flags);
 }


 enum rtx_code
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index ad9bf0f7358..c352421e87c 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -2439,6 +2439,10 @@  typedef struct GTY(()) machine_function
   bool lr_is_wrapped_separately;
   bool toc_is_wrapped_separately;
   bool mma_return_type_error;
+  /* Indicate global entry is emitted, only useful when the function requires
+     global entry.  It helps to control the patchable area before and after
+     local entry.  */
+  bool global_entry_emitted;
 } machine_function;
 #endif

diff --git a/gcc/testsuite/c-c++-common/patchable_function_entry-default.c b/gcc/testsuite/c-c++-common/patchable_function_entry-default.c
index 7036f7bfbea..fc9ab9ac8cd 100644
--- a/gcc/testsuite/c-c++-common/patchable_function_entry-default.c
+++ b/gcc/testsuite/c-c++-common/patchable_function_entry-default.c
@@ -1,6 +1,7 @@ 
 /* { dg-do compile { target { ! { nvptx*-*-* visium-*-* } } } } */
 /* { dg-options "-O2 -fpatchable-function-entry=3,1" } */
 /* { dg-additional-options "-fno-pie" { target sparc*-*-* } } */
+/* { dg-additional-options "-fpatchable-function-entry=3,2" { target powerpc_elfv2 } } */
 /* { dg-final { scan-assembler-times "nop|NOP|SWYM" 3 { target { ! { alpha*-*-* } } } } } */
 /* { dg-final { scan-assembler-times "bis" 3 { target alpha*-*-* } } } */

diff --git a/gcc/testsuite/gcc.target/powerpc/pr99888-1.c b/gcc/testsuite/gcc.target/powerpc/pr99888-1.c
new file mode 100644
index 00000000000..d35b9845629
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr99888-1.c
@@ -0,0 +1,45 @@ 
+/* { dg-require-effective-target powerpc_elfv2 } */
+
+/* Verify no errors for different NOPs after local entry.  */
+
+extern int a;
+
+__attribute__ ((noipa, patchable_function_entry (1, 0)))
+int test1 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (2, 0)))
+int test2 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (3, 0)))
+int test3 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (4, 0)))
+int test4 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (5, 0)))
+int test5 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (6, 0)))
+int test6 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (7, 0)))
+int test7 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (8, 0)))
+int test8 (int b) {
+  return a + b;
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/pr99888-2.c b/gcc/testsuite/gcc.target/powerpc/pr99888-2.c
new file mode 100644
index 00000000000..5a96ccd03d3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr99888-2.c
@@ -0,0 +1,45 @@ 
+/* { dg-require-effective-target powerpc_elfv2 } */
+
+/* Verify no errors for 2, 6 and 14 NOPs before local entry.  */
+
+extern int a;
+
+__attribute__ ((noipa, patchable_function_entry (2, 2)))
+int test1 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (4, 2)))
+int test2 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (6, 6)))
+int test3 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (8, 6)))
+int test4 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (16, 6)))
+int test5 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (14, 14)))
+int test6 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (28, 14)))
+int test7 (int b) {
+  return a + b;
+}
+
+__attribute__ ((noipa, patchable_function_entry (64, 14)))
+int test8 (int b) {
+  return a + b;
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/pr99888-3.c b/gcc/testsuite/gcc.target/powerpc/pr99888-3.c
new file mode 100644
index 00000000000..6e5395ae3de
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr99888-3.c
@@ -0,0 +1,12 @@ 
+/* { dg-require-effective-target powerpc_elfv2 } */
+/* { dg-options "-fpatchable-function-entry=1" } */
+
+/* Verify no errors, using command line option instead of function
+   attribute.  */
+
+extern int a;
+
+int test (int b) {
+  return a + b;
+}
+
diff --git a/gcc/testsuite/gcc.target/powerpc/pr99888-4.c b/gcc/testsuite/gcc.target/powerpc/pr99888-4.c
new file mode 100644
index 00000000000..6d2293d192a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr99888-4.c
@@ -0,0 +1,13 @@ 
+/* { dg-require-effective-target powerpc_elfv2 } */
+/* There is no global entry point prologue with pcrel.  */
+/* { dg-options "-mno-pcrel -fpatchable-function-entry=1,1" } */
+
+/* Verify one error emitted for unexpected 1 NOP before local
+   entry.  */
+
+extern int a;
+
+int test (int b) {
+  return a + b;
+}
+/* { dg-error "unsupported number of nops before function entry \\(1\\)" "" { target *-*-* } .-1 } */
diff --git a/gcc/testsuite/gcc.target/powerpc/pr99888-5.c b/gcc/testsuite/gcc.target/powerpc/pr99888-5.c
new file mode 100644
index 00000000000..3cb3d591fc7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr99888-5.c
@@ -0,0 +1,13 @@ 
+/* { dg-require-effective-target powerpc_elfv2 } */
+/* There is no global entry point prologue with pcrel.  */
+/* { dg-options "-mno-pcrel -fpatchable-function-entry=7,3" } */
+
+/* Verify one error emitted for unexpected 3 NOP before local
+   entry.  */
+
+extern int a;
+
+int test (int b) {
+  return a + b;
+}
+/* { dg-error "unsupported number of nops before function entry \\(3\\)" "" { target *-*-* } .-1 } */
diff --git a/gcc/testsuite/gcc.target/powerpc/pr99888-6.c b/gcc/testsuite/gcc.target/powerpc/pr99888-6.c
new file mode 100644
index 00000000000..02953cbaf8b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr99888-6.c
@@ -0,0 +1,14 @@ 
+/* { dg-require-effective-target powerpc_elfv2 } */
+/* There is no global entry point prologue with pcrel.  */
+/* { dg-options "-mno-pcrel" } */
+
+/* Verify one error emitted for unexpected 4 NOP before local
+   entry.  */
+
+extern int a;
+
+__attribute__ ((patchable_function_entry (20, 4)))
+int test (int b) {
+  return a + b;
+}
+/* { dg-error "unsupported number of nops before function entry \\(4\\)" "" { target *-*-* } .-1 } */