[PATCH 1/2] strlen: fold strstr() even if the length isn't previously known [PR96601]

[PATCH 1/2] strlen: fold strstr() even if the length isn't previously known [PR96601]

[Hamza Mahfooz]

Currently, we give up in fold_strstr_to_strncmp() if the length of the
the second argument to strstr() isn't known to us by the time we hit
that function. However, we can instead insert a strlen() in ourselves
and continue trying to fold strstr() into strlen()+strncmp().

	PR tree-optimization/96601

gcc/ChangeLog:

	* tree-ssa-strlen.cc (fold_strstr_to_strncmp): If arg1_len == NULL,
	insert a strlen() for strstr()'s arg1 and use it as arg1_len.

gcc/testsuite/ChangeLog:

	* gcc.dg/strlenopt-30.c: Modify test.

Signed-off-by: Hamza Mahfooz <someguy@effective-light.com>
---
Please push this for me if you think it looks good. Since, I don't have
write access to the repository.
---
 gcc/testsuite/gcc.dg/strlenopt-30.c |  5 +-
 gcc/tree-ssa-strlen.cc              | 81 ++++++++++++++++-------------
 2 files changed, 45 insertions(+), 41 deletions(-)

diff --git a/gcc/testsuite/gcc.dg/strlenopt-30.c b/gcc/testsuite/gcc.dg/strlenopt-30.c
index 2a3098ba96f..1ee814048c1 100644
--- a/gcc/testsuite/gcc.dg/strlenopt-30.c
+++ b/gcc/testsuite/gcc.dg/strlenopt-30.c
@@ -38,9 +38,6 @@ void f5(char *s)
     foo_f5();
 }
 
-/* Do not perform transform, since strlen (t)
-   is unknown.  */
-
 __attribute__((no_icf))
 _Bool f6(char *s, char *t)
 {
@@ -60,4 +57,4 @@ _Bool f7(char *s)
   return (t1 == s);
 }
 
-/* { dg-final { scan-tree-dump-times "__builtin_strncmp" 5 "strlen1" } } */
+/* { dg-final { scan-tree-dump-times "__builtin_strncmp" 6 "strlen1" } } */
diff --git a/gcc/tree-ssa-strlen.cc b/gcc/tree-ssa-strlen.cc
index 8b7ef919826..b0ebbb0db62 100644
--- a/gcc/tree-ssa-strlen.cc
+++ b/gcc/tree-ssa-strlen.cc
@@ -5273,6 +5273,7 @@ fold_strstr_to_strncmp (tree rhs1, tree rhs2, gimple *stmt)
 	  tree arg1 = gimple_call_arg (call_stmt, 1);
 	  tree arg1_len = NULL_TREE;
 	  int idx = get_stridx (arg1, call_stmt);
+	  gimple_stmt_iterator gsi = gsi_for_stmt (call_stmt);
 
 	  if (idx)
 	    {
@@ -5286,51 +5287,57 @@ fold_strstr_to_strncmp (tree rhs1, tree rhs2, gimple *stmt)
 		}
 	    }
 
-	  if (arg1_len != NULL_TREE)
+	  if (arg1_len == NULL_TREE)
 	    {
-	      gimple_stmt_iterator gsi = gsi_for_stmt (call_stmt);
-	      tree strncmp_decl = builtin_decl_explicit (BUILT_IN_STRNCMP);
+	      tree strlen_decl = builtin_decl_explicit (BUILT_IN_STRLEN);
+	      gcall *strlen_call = gimple_build_call (strlen_decl, 1, arg1);
+	      tree strlen_lhs = make_ssa_name (size_type_node, strlen_call);
+
+	      gimple_call_set_lhs (strlen_call, strlen_lhs);
+	      gimple_set_vuse (strlen_call, gimple_vuse (call_stmt));
+	      gsi_insert_before (&gsi, strlen_call, GSI_SAME_STMT);
+	      arg1_len = strlen_lhs;
+	    }
+	  else if (!is_gimple_val (arg1_len))
+	    {
+	      tree arg1_len_tmp = make_ssa_name (TREE_TYPE (arg1_len));
+	      gassign *arg1_stmt = gimple_build_assign (arg1_len_tmp,
+							arg1_len);
+	      gsi_insert_before (&gsi, arg1_stmt, GSI_SAME_STMT);
+	      arg1_len = arg1_len_tmp;
+	    }
 
-	      if (!is_gimple_val (arg1_len))
+	  tree strncmp_decl = builtin_decl_explicit (BUILT_IN_STRNCMP);
+	  gcall *strncmp_call = gimple_build_call (strncmp_decl, 3,
+						   arg0, arg1, arg1_len);
+	  tree strncmp_lhs = make_ssa_name (integer_type_node);
+	  gimple_set_vuse (strncmp_call, gimple_vuse (call_stmt));
+	  gimple_call_set_lhs (strncmp_call, strncmp_lhs);
+	  gsi_remove (&gsi, true);
+	  gsi_insert_before (&gsi, strncmp_call, GSI_SAME_STMT);
+	  tree zero = build_zero_cst (TREE_TYPE (strncmp_lhs));
+
+	  if (is_gimple_assign (stmt))
+	    {
+	      if (gimple_assign_rhs_code (stmt) == COND_EXPR)
 		{
-		  tree arg1_len_tmp = make_ssa_name (TREE_TYPE (arg1_len));
-		  gassign *arg1_stmt = gimple_build_assign (arg1_len_tmp,
-							    arg1_len);
-		  gsi_insert_before (&gsi, arg1_stmt, GSI_SAME_STMT);
-		  arg1_len = arg1_len_tmp;
-		}
-
-	      gcall *strncmp_call = gimple_build_call (strncmp_decl, 3,
-						      arg0, arg1, arg1_len);
-	      tree strncmp_lhs = make_ssa_name (integer_type_node);
-	      gimple_set_vuse (strncmp_call, gimple_vuse (call_stmt));
-	      gimple_call_set_lhs (strncmp_call, strncmp_lhs);
-	      gsi_remove (&gsi, true);
-	      gsi_insert_before (&gsi, strncmp_call, GSI_SAME_STMT);
-	      tree zero = build_zero_cst (TREE_TYPE (strncmp_lhs));
-
-	      if (is_gimple_assign (stmt))
-		{
-		  if (gimple_assign_rhs_code (stmt) == COND_EXPR)
-		    {
-		      tree cond = gimple_assign_rhs1 (stmt);
-		      TREE_OPERAND (cond, 0) = strncmp_lhs;
-		      TREE_OPERAND (cond, 1) = zero;
-		    }
-		  else
-		    {
-		      gimple_assign_set_rhs1 (stmt, strncmp_lhs);
-		      gimple_assign_set_rhs2 (stmt, zero);
-		    }
+		  tree cond = gimple_assign_rhs1 (stmt);
+		  TREE_OPERAND (cond, 0) = strncmp_lhs;
+		  TREE_OPERAND (cond, 1) = zero;
 		}
 	      else
 		{
-		  gcond *cond = as_a<gcond *> (stmt);
-		  gimple_cond_set_lhs (cond, strncmp_lhs);
-		  gimple_cond_set_rhs (cond, zero);
+		  gimple_assign_set_rhs1 (stmt, strncmp_lhs);
+		  gimple_assign_set_rhs2 (stmt, zero);
 		}
-	      update_stmt (stmt);
 	    }
+	  else
+	    {
+	      gcond *cond = as_a<gcond *> (stmt);
+	      gimple_cond_set_lhs (cond, strncmp_lhs);
+	      gimple_cond_set_rhs (cond, zero);
+	    }
+	  update_stmt (stmt);
 	}
     }
 }
-- 
2.42.0

[PATCH 2/2] strlen: call handle_builtin_strlen() from fold_strstr_to_strncmp()

[Hamza Mahfooz]

Currently, we are not saving the strlen() call we inserted for possible
future common subexpression elimination. Also, it's possible that we can
further fold that strlen() call. So, refactor handle_builtin_strlen()
so that it can be called from fold_strstr_to_strncmp().

gcc/ChangeLog:

	* tree-ssa-strlen.cc (strlen_pass::handle_builtin_strlen):
	Remove from class and mark as static.
	(handle_builtin_strlen): Add parameter
	"gimple_stmt_iterator gsi" and replace references of m_gsi
	with gsi.
	(fold_strstr_to_strncmp): Call handle_builtin_strlen().
	(strlen_pass::check_and_optimize_call): Add m_gsi to the
	handle_builtin_strlen() call.

gcc/testsuite/ChangeLog:

	* gcc.dg/strlenopt-30.c: Add a test.

Signed-off-by: Hamza Mahfooz <someguy@effective-light.com>
---
Please push this for me if you think it looks good. Since, I don't have
write access to the repository.
---
 gcc/testsuite/gcc.dg/strlenopt-30.c |  7 +++++++
 gcc/tree-ssa-strlen.cc              | 23 ++++++++++++-----------
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/gcc/testsuite/gcc.dg/strlenopt-30.c b/gcc/testsuite/gcc.dg/strlenopt-30.c
index 1ee814048c1..de51a66383b 100644
--- a/gcc/testsuite/gcc.dg/strlenopt-30.c
+++ b/gcc/testsuite/gcc.dg/strlenopt-30.c
@@ -44,6 +44,12 @@ _Bool f6(char *s, char *t)
   return __builtin_strstr (s, t) == s;
 }
 
+__attribute__((no_icf))
+_Bool f6plus(char *s, char *t)
+{
+  return __builtin_strstr (s, t) == s && __builtin_strlen(t) > 10;
+}
+
 /* Do not perform transform in this case, since
    t1 doesn't have single use.  */
 
@@ -57,4 +63,5 @@ _Bool f7(char *s)
   return (t1 == s);
 }
 
+/* { dg-final { scan-tree-dump-times "__builtin_strlen" 2 "strlen1" } } */
 /* { dg-final { scan-tree-dump-times "__builtin_strncmp" 6 "strlen1" } } */
diff --git a/gcc/tree-ssa-strlen.cc b/gcc/tree-ssa-strlen.cc
index b0ebbb0db62..8ec6ddbc7c0 100644
--- a/gcc/tree-ssa-strlen.cc
+++ b/gcc/tree-ssa-strlen.cc
@@ -252,7 +252,6 @@ public:
   bool handle_assign (tree lhs, bool *zero_write);
   bool handle_store (bool *zero_write);
   void handle_pointer_plus ();
-  void handle_builtin_strlen ();
   void handle_builtin_strchr ();
   void handle_builtin_strcpy (built_in_function);
   void handle_integral_assign (bool *cleanup_eh);
@@ -2211,10 +2210,10 @@ strlen_pass::maybe_warn_overflow (gimple *stmt, bool call_lhs,
    the strlen call with the known value, otherwise remember that strlen
    of the argument is stored in the lhs SSA_NAME.  */
 
-void
-strlen_pass::handle_builtin_strlen ()
+static void
+handle_builtin_strlen (gimple_stmt_iterator gsi)
 {
-  gimple *stmt = gsi_stmt (m_gsi);
+  gimple *stmt = gsi_stmt (gsi);
   tree lhs = gimple_call_lhs (stmt);
 
   if (lhs == NULL_TREE)
@@ -2268,8 +2267,8 @@ strlen_pass::handle_builtin_strlen ()
 	  if (bound)
 	    rhs = fold_build2_loc (loc, MIN_EXPR, TREE_TYPE (rhs), rhs, bound);
 
-	  gimplify_and_update_call_from_tree (&m_gsi, rhs);
-	  stmt = gsi_stmt (m_gsi);
+	  gimplify_and_update_call_from_tree (&gsi, rhs);
+	  stmt = gsi_stmt (gsi);
 	  update_stmt (stmt);
 	  if (dump_file && (dump_flags & TDF_DETAILS) != 0)
 	    {
@@ -2367,8 +2366,8 @@ strlen_pass::handle_builtin_strlen ()
 	      }
 	    if (!useless_type_conversion_p (TREE_TYPE (lhs), TREE_TYPE (ret)))
 	      ret = fold_convert_loc (loc, TREE_TYPE (lhs), ret);
-	    gimplify_and_update_call_from_tree (&m_gsi, ret);
-	    stmt = gsi_stmt (m_gsi);
+	    gimplify_and_update_call_from_tree (&gsi, ret);
+	    stmt = gsi_stmt (gsi);
 	    update_stmt (stmt);
 	    if (dump_file && (dump_flags & TDF_DETAILS) != 0)
 	      {
@@ -5272,8 +5271,9 @@ fold_strstr_to_strncmp (tree rhs1, tree rhs2, gimple *stmt)
 	{
 	  tree arg1 = gimple_call_arg (call_stmt, 1);
 	  tree arg1_len = NULL_TREE;
-	  int idx = get_stridx (arg1, call_stmt);
 	  gimple_stmt_iterator gsi = gsi_for_stmt (call_stmt);
+again:
+	  int idx = get_stridx (arg1, call_stmt);
 
 	  if (idx)
 	    {
@@ -5296,7 +5296,8 @@ fold_strstr_to_strncmp (tree rhs1, tree rhs2, gimple *stmt)
 	      gimple_call_set_lhs (strlen_call, strlen_lhs);
 	      gimple_set_vuse (strlen_call, gimple_vuse (call_stmt));
 	      gsi_insert_before (&gsi, strlen_call, GSI_SAME_STMT);
-	      arg1_len = strlen_lhs;
+	      handle_builtin_strlen (gsi_for_stmt (strlen_call));
+	      goto again;
 	    }
 	  else if (!is_gimple_val (arg1_len))
 	    {
@@ -5393,7 +5394,7 @@ strlen_pass::check_and_optimize_call (bool *zero_write)
     {
     case BUILT_IN_STRLEN:
     case BUILT_IN_STRNLEN:
-      handle_builtin_strlen ();
+      handle_builtin_strlen (m_gsi);
       break;
     case BUILT_IN_STRCHR:
       handle_builtin_strchr ();
-- 
2.42.0