diff mbox series

ipa: Fix C++ member ptr indirect inlining (PR 114254, PR 108802)

Message ID ri6r0gkzvi4.fsf@virgil.suse.cz
State New
Headers show
Series ipa: Fix C++ member ptr indirect inlining (PR 114254, PR 108802) | expand

Commit Message

Martin Jambor March 8, 2024, 1:46 p.m. UTC 
Hi,

Even though we have had code to handle creation of indirect call graph
edges (so that these calls can than be made direct as part of IPA-CP
and inlining and eventually also inlined) for C++ member pointers for
many years, it turns out that it does not work for lambdas and that it
has been severely broken since GCC 10 when the base class has virtual
functions.

Lambdas don't work because the code cannot work with structures
representing member function pointers because they are passed by
reference instead by value and the code was not ready for that.

The presence of virtual methods broke thinks because at some point C++
FE got clever and stopped emitting the check for virtual methods when
the base class does not have any and that in turn made our existing
testcases not test the necessary pattern matching code.  The pattern
matcher had a small bug which did not matter before
r10-917-g3b47da42de621c but did afterwards.

This patch changes the pattern matcher to match both of these cases.

Special thanks to the Linaro automated checker of patches which
reported that the earlier version of my PR 108802 fix was not working
on Aarch64 which in turn made me discover PR 114254.

The patch has passed bootstrap and testing on x86_64-linux,
aarch64-linux and ppc64-linux and I also LTO bootstrap on x86_64-linux.

I understand we have been living with these deficiencies for a while now
but both are technically regressions.  If Honza agrees (and manages to
review the patch quickly), I'm fine with pushing them to master now but
I can also wait until the next stage 1.

Thanks,

Martin


gcc/ChangeLog:

2024-03-06  Martin Jambor  <mjambor@suse.cz>

	PR ipa/108802
	PR ipa/114254
	* ipa-prop.cc (ipa_get_stmt_member_ptr_load_param): Fix case looking
	at COMPONENT_REFs directly from a PARM_DECL, also recognize loads from
	a pointer parameter.
	(ipa_analyze_indirect_call_uses): Also recognize loads from a pointer
	parameter, also recognize the case when pfn pointer is loaded in its
	own BB.

gcc/testsuite/ChangeLog:

2024-03-06  Martin Jambor  <mjambor@suse.cz>

	PR ipa/108802
	PR ipa/114254
	* g++.dg/ipa/iinline-4.C: New test.
	* g++.dg/ipa/pr108802.C: Likewise.
---
 gcc/ipa-prop.cc                      | 110 +++++++++++++++++++--------
 gcc/testsuite/g++.dg/ipa/iinline-4.C |  61 +++++++++++++++
 gcc/testsuite/g++.dg/ipa/pr108802.C  |  14 ++++
 3 files changed, 154 insertions(+), 31 deletions(-)
 create mode 100644 gcc/testsuite/g++.dg/ipa/iinline-4.C
 create mode 100644 gcc/testsuite/g++.dg/ipa/pr108802.C

Comments

Jan Hubicka March 18, 2024, 9:02 a.m. UTC | #1 
> gcc/ChangeLog:
> 
> 2024-03-06  Martin Jambor  <mjambor@suse.cz>
> 
> 	PR ipa/108802
> 	PR ipa/114254
> 	* ipa-prop.cc (ipa_get_stmt_member_ptr_load_param): Fix case looking
> 	at COMPONENT_REFs directly from a PARM_DECL, also recognize loads from
> 	a pointer parameter.
> 	(ipa_analyze_indirect_call_uses): Also recognize loads from a pointer
> 	parameter, also recognize the case when pfn pointer is loaded in its
> 	own BB.
> 
> gcc/testsuite/ChangeLog:
> 
> 2024-03-06  Martin Jambor  <mjambor@suse.cz>
> 
> 	PR ipa/108802
> 	PR ipa/114254
> 	* g++.dg/ipa/iinline-4.C: New test.
> 	* g++.dg/ipa/pr108802.C: Likewise.

OK,
thanks!

Honza
diff mbox series

Patch

diff --git a/gcc/ipa-prop.cc b/gcc/ipa-prop.cc
index e22c4f78405..e8e4918d5a8 100644
--- a/gcc/ipa-prop.cc
+++ b/gcc/ipa-prop.cc
@@ -2500,7 +2500,9 @@  static tree
 ipa_get_stmt_member_ptr_load_param (gimple *stmt, bool use_delta,
 				    HOST_WIDE_INT *offset_p)
 {
-  tree rhs, rec, ref_field, ref_offset, fld, ptr_field, delta_field;
+  tree rhs, fld, ptr_field, delta_field;
+  tree ref_field = NULL_TREE;
+  tree ref_offset = NULL_TREE;
 
   if (!gimple_assign_single_p (stmt))
     return NULL_TREE;
@@ -2511,35 +2513,53 @@  ipa_get_stmt_member_ptr_load_param (gimple *stmt, bool use_delta,
       ref_field = TREE_OPERAND (rhs, 1);
       rhs = TREE_OPERAND (rhs, 0);
     }
+
+  if (TREE_CODE (rhs) == MEM_REF)
+    {
+      ref_offset = TREE_OPERAND (rhs, 1);
+      if (ref_field && integer_nonzerop (ref_offset))
+	return NULL_TREE;
+    }
+  else if (!ref_field)
+    return NULL_TREE;
+
+  if (TREE_CODE (rhs) == MEM_REF
+      && TREE_CODE (TREE_OPERAND (rhs, 0)) == SSA_NAME
+      && SSA_NAME_IS_DEFAULT_DEF (TREE_OPERAND (rhs, 0)))
+    {
+      rhs = TREE_OPERAND (rhs, 0);
+      if (TREE_CODE (SSA_NAME_VAR (rhs)) != PARM_DECL
+	  || !type_like_member_ptr_p (TREE_TYPE (TREE_TYPE (rhs)), &ptr_field,
+				      &delta_field))
+	return NULL_TREE;
+    }
   else
-    ref_field = NULL_TREE;
-  if (TREE_CODE (rhs) != MEM_REF)
-    return NULL_TREE;
-  rec = TREE_OPERAND (rhs, 0);
-  if (TREE_CODE (rec) != ADDR_EXPR)
-    return NULL_TREE;
-  rec = TREE_OPERAND (rec, 0);
-  if (TREE_CODE (rec) != PARM_DECL
-      || !type_like_member_ptr_p (TREE_TYPE (rec), &ptr_field, &delta_field))
-    return NULL_TREE;
-  ref_offset = TREE_OPERAND (rhs, 1);
+    {
+      if (TREE_CODE (rhs) == MEM_REF
+	  && TREE_CODE (TREE_OPERAND (rhs, 0)) == ADDR_EXPR)
+	rhs = TREE_OPERAND (TREE_OPERAND (rhs, 0), 0);
+      if (TREE_CODE (rhs) != PARM_DECL
+	  || !type_like_member_ptr_p (TREE_TYPE (rhs), &ptr_field,
+				      &delta_field))
+	return NULL_TREE;
+    }
 
   if (use_delta)
     fld = delta_field;
   else
     fld = ptr_field;
-  if (offset_p)
-    *offset_p = int_bit_position (fld);
 
   if (ref_field)
     {
-      if (integer_nonzerop (ref_offset))
+      if (ref_field != fld)
 	return NULL_TREE;
-      return ref_field == fld ? rec : NULL_TREE;
     }
-  else
-    return tree_int_cst_equal (byte_position (fld), ref_offset) ? rec
-      : NULL_TREE;
+  else if (!tree_int_cst_equal (byte_position (fld), ref_offset))
+    return NULL_TREE;
+
+  if (offset_p)
+    *offset_p = int_bit_position (fld);
+  return rhs;
 }
 
 /* Returns true iff T is an SSA_NAME defined by a statement.  */
@@ -2585,8 +2605,9 @@  ipa_note_param_call (struct cgraph_node *node, int param_index,
    describing the call is created.  This is very simple for ordinary pointers
    represented in SSA but not-so-nice when it comes to member pointers.  The
    ugly part of this function does nothing more than trying to match the
-   pattern of such a call.  An example of such a pattern is the gimple dump
-   below, the call is on the last line:
+   pattern of such a call.  Look up the documentation of macro
+   TARGET_PTRMEMFUNC_VBIT_LOCATION for details.  An example of such a pattern
+   is the gimple dump below, the call is on the last line:
 
      <bb 2>:
        f$__delta_5 = f.__delta;
@@ -2710,10 +2731,23 @@  ipa_analyze_indirect_call_uses (struct ipa_func_body_info *fbi, gcall *call,
      corresponding to the pattern. */
 
   if (!single_pred_p (virt_bb) || !single_succ_p (virt_bb)
-      || single_pred (virt_bb) != bb
       || single_succ (virt_bb) != join)
     return;
 
+
+  if (single_pred (virt_bb) != bb)
+    {
+      /* In cases when the distinction between a normal and a virtual
+	 function is encoded in the delta field, the load of the
+	 actual non-virtual function pointer can be in its own BB.  */
+
+      if (!single_pred_p (bb) || !single_succ_p (bb))
+	return;
+      bb = single_pred (bb);
+      if (bb != single_pred (virt_bb))
+	return;
+    }
+
   /* Third, let's see that the branching is done depending on the least
      significant bit of the pfn. */
 
@@ -2759,17 +2793,31 @@  ipa_analyze_indirect_call_uses (struct ipa_func_body_info *fbi, gcall *call,
   if (rec != rec2)
     return;
 
-  index = ipa_get_param_decl_index (info, rec);
-  if (index >= 0
-      && parm_preserved_before_stmt_p (fbi, index, call, rec))
+  if (TREE_CODE (rec) == SSA_NAME)
     {
-      struct cgraph_edge *cs = ipa_note_param_call (fbi->node, index,
-	 					    call, false);
-      cs->indirect_info->offset = offset;
-      cs->indirect_info->agg_contents = 1;
-      cs->indirect_info->member_ptr = 1;
-      cs->indirect_info->guaranteed_unmodified = 1;
+      index = ipa_get_param_decl_index (info, SSA_NAME_VAR (rec));
+      if (index < 0
+	  || !parm_ref_data_preserved_p (fbi, index, call,
+					 gimple_assign_rhs1 (def)))
+	return;
+      by_ref = true;
     }
+  else
+    {
+      index = ipa_get_param_decl_index (info, rec);
+      if (index < 0
+	  || !parm_preserved_before_stmt_p (fbi, index, call, rec))
+	return;
+      by_ref = false;
+    }
+
+  struct cgraph_edge *cs = ipa_note_param_call (fbi->node, index,
+						call, false);
+  cs->indirect_info->offset = offset;
+  cs->indirect_info->agg_contents = 1;
+  cs->indirect_info->member_ptr = 1;
+  cs->indirect_info->by_ref = by_ref;
+  cs->indirect_info->guaranteed_unmodified = 1;
 
   return;
 }
diff --git a/gcc/testsuite/g++.dg/ipa/iinline-4.C b/gcc/testsuite/g++.dg/ipa/iinline-4.C
new file mode 100644
index 00000000000..b7ab89bb4d5
--- /dev/null
+++ b/gcc/testsuite/g++.dg/ipa/iinline-4.C
@@ -0,0 +1,61 @@ 
+/* Verify that simple indirect calls are inlined even without early
+   inlining..  */
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-ipa-inline -fno-early-inlining"  } */
+/* { dg-add-options bind_pic_locally } */
+
+extern void non_existent (const char *, int);
+
+class String
+{
+private:
+  const char *data;
+
+public:
+  String (const char *d) : data(d)
+  {}
+
+  int funcOne (int delim) const;
+  int printStuffTwice (int delim) const;
+  virtual int whee (int delim) const;
+};
+
+
+int String::funcOne (int delim) const
+{
+  int i;
+  for (i = 0; i < delim; i++)
+    non_existent(data, i);
+
+  return 1;
+}
+
+extern int global;
+
+int docalling (int c, int (String::* f)(int delim) const)
+{
+  String S ("muhehehe");
+
+  if (c > 2)
+    global = 3;
+  else
+    global = 5;
+
+  return (S.*f)(4);
+}
+
+int __attribute__ ((noinline,noclone)) get_input (void)
+{
+  return 1;
+}
+
+int main (int argc, char *argv[])
+{
+  int i = 0;
+  while (i < 1000)
+    i += docalling (get_input (), &String::funcOne);
+  non_existent ("done", i);
+  return 0;
+}
+
+/* { dg-final { scan-ipa-dump "String::funcOne\[^\\n\]*inline copy in int main"  "inline"  } } */
diff --git a/gcc/testsuite/g++.dg/ipa/pr108802.C b/gcc/testsuite/g++.dg/ipa/pr108802.C
new file mode 100644
index 00000000000..2e2b6c66b64
--- /dev/null
+++ b/gcc/testsuite/g++.dg/ipa/pr108802.C
@@ -0,0 +1,14 @@ 
+/* { dg-do compile  } */
+/* { dg-options "-O2 -std=c++14 -fdump-ipa-inline -fno-early-inlining"  } */
+/* { dg-add-options bind_pic_locally } */
+
+struct A {
+    int interesting(int x) { return 2 * x; }
+};
+
+int f1() {
+    A a;
+    return [&](auto&& f) { return (a.*f)(42); } (&A::interesting);
+}
+
+/* { dg-final { scan-ipa-dump "A::interesting\[^\\n\]*inline copy in int f1"  "inline"  } } */