>From cb30112672512c01d5c87e8c6d8ecdf118cf661b Mon Sep 17 00:00:00 2001 From: qing zhao Date: Tue, 22 May 2018 13:07:32 -0400 Subject: [PATCH] 2nd Patch for PR78009 Patch for PR83026 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78809 Inline strcmp with small constant strings https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83026 missing strlen optimization for strcmp of unequal strings The design doc for PR78809 is at: https://www.mail-archive.com/gcc@gcc.gnu.org/msg83822.html this patch is for the second part of change of PR78809 and PR83026: B. for strncmp (s1, s2, n) (!)= 0 or strcmp (s1, s2) (!)= 0 B.1. (PR83026) When the lengths of both arguments are constant and it's a strcmp: * if the lengths are NOT equal, we can safely fold the call to a non-zero value. * otherwise, do nothing now. B.2. (PR78809) When the length of one argument is constant, try to replace the call with a __builtin_str(n)cmp_eq call where possible, i.e: strncmp (s, STR, C) (!)= 0 in which, s is a pointer to a string, STR is a string with constant length, C is a constant. if (C <= strlen(STR) && sizeof_array(s) > C) { replace this call with __builtin_strncmp_eq (s, STR, C) (!)= 0 } if (C > strlen(STR) { it can be safely treated as a call to strcmp (s, STR) (!)= 0 can handled by the following strcmp. } strcmp (s, STR) (!)= 0 in which, s is a pointer to a string, STR is a string with constant length. if (sizeof_array(s) > strlen(STR)) { replace this call with __builtin_strcmp_eq (s, STR, strlen(STR)+1) (!)= 0 } later when expanding the new __builtin_str(n)cmp_eq calls, first expand them as __builtin_memcmp_eq, if the expansion does not succeed, change them back to call to __builtin_str(n)cmp. adding test case strcmpopt_2.c and strcmpopt_4.c into gcc.dg for part B of PR78809 adding test case strcmpopt_3.c into gcc.dg for PR83026 bootstraped and tested on both X86 and Aarch64. no regression. --- gcc/builtins.c | 33 +++++ gcc/builtins.def | 5 + gcc/gimple-fold.c | 5 + gcc/testsuite/gcc.dg/strcmpopt_2.c | 67 ++++++++++ gcc/testsuite/gcc.dg/strcmpopt_3.c | 31 +++++ gcc/testsuite/gcc.dg/strcmpopt_4.c | 16 +++ gcc/tree-ssa-strlen.c | 268 +++++++++++++++++++++++++++++++++++++ gcc/tree-ssa-structalias.c | 2 + gcc/tree.c | 8 ++ 9 files changed, 435 insertions(+) create mode 100644 gcc/testsuite/gcc.dg/strcmpopt_2.c create mode 100644 gcc/testsuite/gcc.dg/strcmpopt_3.c create mode 100644 gcc/testsuite/gcc.dg/strcmpopt_4.c diff --git a/gcc/builtins.c b/gcc/builtins.c index 9a2bf8c..aed7513 100644 --- a/gcc/builtins.c +++ b/gcc/builtins.c @@ -7110,12 +7110,45 @@ expand_builtin (tree exp, rtx target, rtx subtarget, machine_mode mode, return target; break; + /* Expand it as BUILT_IN_MEMCMP_EQ first. If not successful, change it + back to a BUILT_IN_STRCMP. Remember to delete the 3rd paramater + when changing it to a strcmp call. */ + case BUILT_IN_STRCMP_EQ: + target = expand_builtin_memcmp (exp, target, true); + if (target) + return target; + + /* Change this call back to a BUILT_IN_STRCMP. */ + TREE_OPERAND (exp, 1) + = build_fold_addr_expr (builtin_decl_explicit (BUILT_IN_STRCMP)); + + /* Delete the last parameter. */ + unsigned int i; + vec *arg_vec; + vec_alloc (arg_vec, 2); + for (i = 0; i < 2; i++) + arg_vec->quick_push (CALL_EXPR_ARG (exp, i)); + exp = build_call_vec (TREE_TYPE (exp), CALL_EXPR_FN (exp), arg_vec); + /* FALLTHROUGH */ + case BUILT_IN_STRCMP: target = expand_builtin_strcmp (exp, target); if (target) return target; break; + /* Expand it as BUILT_IN_MEMCMP_EQ first. If not successful, change it + back to a BUILT_IN_STRNCMP. */ + case BUILT_IN_STRNCMP_EQ: + target = expand_builtin_memcmp (exp, target, true); + if (target) + return target; + + /* Change it back to a BUILT_IN_STRNCMP. */ + TREE_OPERAND (exp, 1) + = build_fold_addr_expr (builtin_decl_explicit (BUILT_IN_STRNCMP)); + /* FALLTHROUGH */ + case BUILT_IN_STRNCMP: target = expand_builtin_strncmp (exp, target, mode); if (target) diff --git a/gcc/builtins.def b/gcc/builtins.def index 449d08d..58b4698 100644 --- a/gcc/builtins.def +++ b/gcc/builtins.def @@ -971,6 +971,11 @@ DEF_BUILTIN_STUB (BUILT_IN_ALLOCA_WITH_ALIGN_AND_MAX, "__builtin_alloca_with_ali equality with zero. */ DEF_BUILTIN_STUB (BUILT_IN_MEMCMP_EQ, "__builtin_memcmp_eq") +/* An internal version of strcmp/strncmp, used when the result is only + tested for equality with zero. */ +DEF_BUILTIN_STUB (BUILT_IN_STRCMP_EQ, "__builtin_strcmp_eq") +DEF_BUILTIN_STUB (BUILT_IN_STRNCMP_EQ, "__builtin_strncmp_eq") + /* Object size checking builtins. */ DEF_GCC_BUILTIN (BUILT_IN_OBJECT_SIZE, "object_size", BT_FN_SIZE_CONST_PTR_INT, ATTR_PURE_NOTHROW_LEAF_LIST) DEF_EXT_LIB_BUILTIN_CHKP (BUILT_IN_MEMCPY_CHK, "__memcpy_chk", BT_FN_PTR_PTR_CONST_PTR_SIZE_SIZE, ATTR_RET1_NOTHROW_NONNULL_LEAF) diff --git a/gcc/gimple-fold.c b/gcc/gimple-fold.c index b45798c..53bfcbb 100644 --- a/gcc/gimple-fold.c +++ b/gcc/gimple-fold.c @@ -2215,12 +2215,14 @@ gimple_fold_builtin_string_compare (gimple_stmt_iterator *gsi) switch (fcode) { case BUILT_IN_STRCMP: + case BUILT_IN_STRCMP_EQ: { r = strcmp (p1, p2); known_result = true; break; } case BUILT_IN_STRNCMP: + case BUILT_IN_STRNCMP_EQ: { if (length == -1) break; @@ -2254,6 +2256,7 @@ gimple_fold_builtin_string_compare (gimple_stmt_iterator *gsi) bool nonzero_length = length >= 1 || fcode == BUILT_IN_STRCMP + || fcode == BUILT_IN_STRCMP_EQ || fcode == BUILT_IN_STRCASECMP; location_t loc = gimple_location (stmt); @@ -3687,8 +3690,10 @@ gimple_fold_builtin (gimple_stmt_iterator *gsi) case BUILT_IN_STRSTR: return gimple_fold_builtin_strstr (gsi); case BUILT_IN_STRCMP: + case BUILT_IN_STRCMP_EQ: case BUILT_IN_STRCASECMP: case BUILT_IN_STRNCMP: + case BUILT_IN_STRNCMP_EQ: case BUILT_IN_STRNCASECMP: return gimple_fold_builtin_string_compare (gsi); case BUILT_IN_MEMCHR: diff --git a/gcc/testsuite/gcc.dg/strcmpopt_2.c b/gcc/testsuite/gcc.dg/strcmpopt_2.c new file mode 100644 index 0000000..0131b8f --- /dev/null +++ b/gcc/testsuite/gcc.dg/strcmpopt_2.c @@ -0,0 +1,67 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -fdump-tree-strlen" } */ + +char s[100] = {'a','b','c','d'}; +typedef struct { char s[8]; int x; } S; + +__attribute__ ((noinline)) int +f1 (S *s) +{ + return __builtin_strcmp (s->s, "abc") != 0; +} + +__attribute__ ((noinline)) int +f2 (void) +{ + return __builtin_strcmp (s, "abc") != 0; +} + +__attribute__ ((noinline)) int +f3 (S *s) +{ + return __builtin_strcmp ("abc", s->s) != 0; +} + +__attribute__ ((noinline)) int +f4 (void) +{ + return __builtin_strcmp ("abc", s) != 0; +} + +__attribute__ ((noinline)) int +f5 (S *s) +{ + return __builtin_strncmp (s->s, "abc", 3) != 0; +} + +__attribute__ ((noinline)) int +f6 (void) +{ + return __builtin_strncmp (s, "abc", 2) != 0; +} + +__attribute__ ((noinline)) int +f7 (S *s) +{ + return __builtin_strncmp ("abc", s->s, 3) != 0; +} + +__attribute__ ((noinline)) int +f8 (void) +{ + return __builtin_strncmp ("abc", s, 2) != 0; +} + +int main (void) +{ + S ss = {{'a','b','c'}, 2}; + + if (f1 (&ss) != 0 || f2 () != 1 || f3 (&ss) != 0 || + f4 () != 1 || f5 (&ss) != 0 || f6 () != 0 || + f7 (&ss) != 0 || f8 () != 0) + __builtin_abort (); + + return 0; +} + +/* { dg-final { scan-tree-dump-times "cmp_eq \\(" 8 "strlen" } } */ diff --git a/gcc/testsuite/gcc.dg/strcmpopt_3.c b/gcc/testsuite/gcc.dg/strcmpopt_3.c new file mode 100644 index 0000000..86a0d7a --- /dev/null +++ b/gcc/testsuite/gcc.dg/strcmpopt_3.c @@ -0,0 +1,31 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -fdump-tree-strlen" } */ + +__attribute__ ((noinline)) int +f1 (void) +{ + char *s0= "abcd"; + char s[8]; + __builtin_strcpy (s, s0); + return __builtin_strcmp(s, "abc") != 0; +} + +__attribute__ ((noinline)) int +f2 (void) +{ + char *s0 = "ab"; + char s[8]; + __builtin_strcpy (s, s0); + return __builtin_strcmp("abc", s) != 0; +} + +int main (void) +{ + if (f1 () != 1 + || f2 () != 1) + __builtin_abort (); + + return 0; +} + +/* { dg-final { scan-tree-dump-times "strcmp" 0 "strlen" } } */ diff --git a/gcc/testsuite/gcc.dg/strcmpopt_4.c b/gcc/testsuite/gcc.dg/strcmpopt_4.c new file mode 100644 index 0000000..d727bc3 --- /dev/null +++ b/gcc/testsuite/gcc.dg/strcmpopt_4.c @@ -0,0 +1,16 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-strlen" } */ + +typedef struct { char s[8]; int x; } S; +extern int max_i; + +int +f1 (S * s) +{ + int result, i; + for (i = 0; i < max_i; i++) + result += __builtin_strcmp (s->s, "abc") != 0 ? 2 : 1; + return result; +} + +/* { dg-final { scan-tree-dump-times "cmp_eq \\(" 1 "strlen" } } */ diff --git a/gcc/tree-ssa-strlen.c b/gcc/tree-ssa-strlen.c index 33004b6..f733bf4 100644 --- a/gcc/tree-ssa-strlen.c +++ b/gcc/tree-ssa-strlen.c @@ -48,6 +48,7 @@ along with GCC; see the file COPYING3. If not see #include "params.h" #include "ipa-chkp.h" #include "tree-hash-traits.h" +#include "tree-object-size.h" #include "builtins.h" #include "target.h" #include "diagnostic-core.h" @@ -2764,6 +2765,268 @@ handle_builtin_memcmp (gimple_stmt_iterator *gsi) return false; } +/* Given an index to the strinfo vector, compute the string length for the + corresponding string. Return -1 when unknown. */ + +static HOST_WIDE_INT +compute_string_length (int idx) +{ + HOST_WIDE_INT string_leni = -1; + gcc_assert (idx != 0); + + if (idx < 0) + return ~idx; + + strinfo *si = get_strinfo (idx); + if (si) + { + tree const_string_len = get_string_length (si); + if (const_string_len && tree_fits_shwi_p (const_string_len)) + string_leni = tree_to_shwi (const_string_len); + } + + if (string_leni < 0) + return -1; + + return string_leni; +} + +/* Determine the minimum size of the object referenced by DEST expression which + must have a pointer type. + Return the minimum size of the object if successful or NULL when the size + cannot be determined. */ +static tree +determine_min_objsize (tree dest) +{ + unsigned HOST_WIDE_INT size = 0; + + if (compute_builtin_object_size (dest, 2, &size)) + return build_int_cst (sizetype, size); + + /* Try to determine the size of the object through the RHS of the + assign statement. */ + if (TREE_CODE (dest) == SSA_NAME) + { + gimple *stmt = SSA_NAME_DEF_STMT (dest); + if (!is_gimple_assign (stmt)) + return NULL_TREE; + + if (!gimple_assign_single_p (stmt) + && !gimple_assign_unary_nop_p (stmt)) + return NULL_TREE; + + dest = gimple_assign_rhs1 (stmt); + return determine_min_objsize (dest); + } + + /* Try to determine the size of the object from its type. */ + if (TREE_CODE (dest) != ADDR_EXPR) + return NULL_TREE; + + tree type = TREE_TYPE (dest); + if (TREE_CODE (type) == POINTER_TYPE) + type = TREE_TYPE (type); + + type = TYPE_MAIN_VARIANT (type); + + /* We cannot determine the size of the array if it's a flexible array, + which is declared at the end of a structure. */ + if (TREE_CODE (type) == ARRAY_TYPE + && !array_at_struct_end_p (dest)) + { + tree size_t = TYPE_SIZE_UNIT (type); + if (size_t && TREE_CODE (size_t) == INTEGER_CST + && !integer_zerop (size_t)) + return size_t; + } + + return NULL_TREE; +} + +/* Handle a call to strcmp or strncmp. When the result is ONLY used to do + equality test against zero: + + A. When the lengths of both arguments are constant and it's a strcmp: + * if the lengths are NOT equal, we can safely fold the call + to a non-zero value. + * otherwise, do nothing now. + + B. When the length of one argument is constant, try to replace the call with + a __builtin_str(n)cmp_eq call where possible, i.e: + + strncmp (s, STR, C) (!)= 0 in which, s is a pointer to a string, STR is a + string with constant length , C is a constant. + if (C <= strlen(STR) && sizeof_array(s) > C) + { + replace this call with + strncmp_eq (s, STR, C) (!)= 0 + } + if (C > strlen(STR) + { + it can be safely treated as a call to strcmp (s, STR) (!)= 0 + can handled by the following strcmp. + } + + strcmp (s, STR) (!)= 0 in which, s is a pointer to a string, STR is a + string with constant length. + if (sizeof_array(s) > strlen(STR)) + { + replace this call with + strcmp_eq (s, STR, strlen(STR)+1) (!)= 0 + } + + Return false when the call is transformed, return true otherwise. + */ + +static bool +handle_builtin_string_cmp (gimple_stmt_iterator *gsi) +{ + gcall *stmt = as_a (gsi_stmt (*gsi)); + tree res = gimple_call_lhs (stmt); + use_operand_p use_p; + imm_use_iterator iter; + tree arg1 = gimple_call_arg (stmt, 0); + tree arg2 = gimple_call_arg (stmt, 1); + int idx1 = get_stridx (arg1); + int idx2 = get_stridx (arg2); + HOST_WIDE_INT length = -1; + bool is_ncmp = false; + + if (!res) + return true; + + /* When both arguments are unknown, do nothing. */ + if (idx1 == 0 && idx2 == 0) + return true; + + /* Handle strncmp function. */ + if (gimple_call_num_args (stmt) == 3) + { + tree len = gimple_call_arg (stmt, 2); + if (tree_fits_shwi_p (len)) + length = tree_to_shwi (len); + + is_ncmp = true; + } + + /* For strncmp, if the length argument is NOT known, do nothing. */ + if (is_ncmp && length < 0) + return true; + + /* When the result is ONLY used to do equality test against zero. */ + FOR_EACH_IMM_USE_FAST (use_p, iter, res) + { + gimple *use_stmt = USE_STMT (use_p); + + if (is_gimple_debug (use_stmt)) + continue; + if (gimple_code (use_stmt) == GIMPLE_ASSIGN) + { + tree_code code = gimple_assign_rhs_code (use_stmt); + if (code == COND_EXPR) + { + tree cond_expr = gimple_assign_rhs1 (use_stmt); + if ((TREE_CODE (cond_expr) != EQ_EXPR + && (TREE_CODE (cond_expr) != NE_EXPR)) + || !integer_zerop (TREE_OPERAND (cond_expr, 1))) + return true; + } + else if (code == EQ_EXPR || code == NE_EXPR) + { + if (!integer_zerop (gimple_assign_rhs2 (use_stmt))) + return true; + } + else + return true; + } + else if (gimple_code (use_stmt) == GIMPLE_COND) + { + tree_code code = gimple_cond_code (use_stmt); + if ((code != EQ_EXPR && code != NE_EXPR) + || !integer_zerop (gimple_cond_rhs (use_stmt))) + return true; + } + else + return true; + } + + /* When the lengths of both arguments are known, and they are unequal, we can + safely fold the call to a non-zero value for strcmp; + othewise, do nothing now. */ + if (idx1 != 0 && idx2 != 0) + { + HOST_WIDE_INT const_string_leni1 = compute_string_length (idx1); + HOST_WIDE_INT const_string_leni2 = compute_string_length (idx2); + + if (!is_ncmp + && const_string_leni1 != -1 + && const_string_leni2 != -1 + && const_string_leni1 != const_string_leni2) + { + replace_call_with_value (gsi, integer_one_node); + return false; + } + return true; + } + + /* When the length of one argument is constant. */ + tree var_string = NULL_TREE; + HOST_WIDE_INT const_string_leni = -1; + + if (idx1) + { + const_string_leni = compute_string_length (idx1); + var_string = arg2; + } + else + { + gcc_checking_assert (idx2); + const_string_leni = compute_string_length (idx2); + var_string = arg1; + } + + if (const_string_leni < 0) + return true; + + unsigned HOST_WIDE_INT var_sizei = 0; + /* try to determine the minimum size of the object pointed by var_string. */ + tree size = determine_min_objsize (var_string); + + if (!size) + return true; + + if (tree_fits_uhwi_p (size)) + var_sizei = tree_to_uhwi (size); + + if (var_sizei == 0) + return true; + + /* For strncmp, if length > const_string_leni , this call can be safely + transformed to a strcmp. */ + if (is_ncmp && length > const_string_leni) + is_ncmp = false; + + unsigned HOST_WIDE_INT final_length + = is_ncmp ? length : const_string_leni + 1; + + /* Replace strcmp or strncmp with the corresponding str(n)cmp_eq. */ + if (var_sizei > final_length) + { + tree fn + = (is_ncmp + ? builtin_decl_implicit (BUILT_IN_STRNCMP_EQ) + : builtin_decl_implicit (BUILT_IN_STRCMP_EQ)); + if (!fn) + return true; + tree const_string_len = build_int_cst (size_type_node, final_length); + update_gimple_call (gsi, fn, 3, arg1, arg2, const_string_len); + } + else + return true; + + return false; +} + /* Handle a POINTER_PLUS_EXPR statement. For p = "abcd" + 2; compute associated length, or if p = q + off is pointing to a '\0' character of a string, call @@ -3216,6 +3479,11 @@ strlen_check_and_optimize_stmt (gimple_stmt_iterator *gsi, bool *cleanup_eh) if (!handle_builtin_memcmp (gsi)) return false; break; + case BUILT_IN_STRCMP: + case BUILT_IN_STRNCMP: + if (!handle_builtin_string_cmp (gsi)) + return false; + break; default: break; } diff --git a/gcc/tree-ssa-structalias.c b/gcc/tree-ssa-structalias.c index 8fb13a0..14ab83a 100644 --- a/gcc/tree-ssa-structalias.c +++ b/gcc/tree-ssa-structalias.c @@ -4498,7 +4498,9 @@ find_func_aliases_for_builtin_call (struct function *fn, gcall *t) that use the memory pointed to by their arguments (but not transitively). */ case BUILT_IN_STRCMP: + case BUILT_IN_STRCMP_EQ: case BUILT_IN_STRNCMP: + case BUILT_IN_STRNCMP_EQ: case BUILT_IN_STRCASECMP: case BUILT_IN_STRNCASECMP: case BUILT_IN_MEMCMP: diff --git a/gcc/tree.c b/gcc/tree.c index ff982fe..5f65001 100644 --- a/gcc/tree.c +++ b/gcc/tree.c @@ -10279,6 +10279,14 @@ build_common_builtin_nodes (void) "__builtin_memcmp_eq", ECF_PURE | ECF_NOTHROW | ECF_LEAF); + local_define_builtin ("__builtin_strncmp_eq", ftype, BUILT_IN_STRNCMP_EQ, + "__builtin_strncmp_eq", + ECF_PURE | ECF_NOTHROW | ECF_LEAF); + + local_define_builtin ("__builtin_strcmp_eq", ftype, BUILT_IN_STRCMP_EQ, + "__builtin_strcmp_eq", + ECF_PURE | ECF_NOTHROW | ECF_LEAF); + /* If there's a possibility that we might use the ARM EABI, build the alternate __cxa_end_cleanup node used to resume from C++. */ if (targetm.arm_eabi_unwinder) -- 1.8.3.1