diff options
45 files changed, 3082 insertions, 319 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 26eeacab68f..dab57d8420a 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,73 @@ +2014-11-12 Jakub Jelinek <jakub@redhat.com> + + PR c/59708 + * builtin-attrs.def (ATTR_NOTHROW_TYPEGENERIC_LEAF): New attribute. + * builtins.c (fold_builtin_arith_overflow): New function. + (fold_builtin_3): Use it. + * builtins.def (BUILT_IN_ADD_OVERFLOW, BUILT_IN_SUB_OVERFLOW, + BUILT_IN_MUL_OVERFLOW, BUILT_IN_SADD_OVERFLOW, BUILT_IN_SADDL_OVERFLOW, + BUILT_IN_SADDLL_OVERFLOW, BUILT_IN_SSUB_OVERFLOW, + BUILT_IN_SSUBL_OVERFLOW, BUILT_IN_SSUBLL_OVERFLOW, + BUILT_IN_SMUL_OVERFLOW, BUILT_IN_SMULL_OVERFLOW, + BUILT_IN_SMULLL_OVERFLOW, BUILT_IN_UADDL_OVERFLOW, + BUILT_IN_UADDLL_OVERFLOW, BUILT_IN_USUB_OVERFLOW, + BUILT_IN_USUBL_OVERFLOW, BUILT_IN_USUBLL_OVERFLOW, + BUILT_IN_UMUL_OVERFLOW, BUILT_IN_UMULL_OVERFLOW, + BUILT_IN_UMULLL_OVERFLOW): New built-in functions. + * builtin-types.def (BT_PTR_UINT, BT_PTR_ULONG, BT_PTR_LONGLONG, + BT_FN_BOOL_INT_INT_INTPTR, BT_FN_BOOL_LONG_LONG_LONGPTR, + BT_FN_BOOL_LONGLONG_LONGLONG_LONGLONGPTR, BT_FN_BOOL_UINT_UINT_UINTPTR, + BT_FN_BOOL_ULONG_ULONG_ULONGPTR, + BT_FN_BOOL_ULONGLONG_ULONGLONG_ULONGLONGPTR, BT_FN_BOOL_VAR): New. + * expr.c (write_complex_part): Remove prototype, no longer static. + * expr.h (write_complex_part): New prototype. + * function.c (aggregate_value_p): For internal functions return 0. + * gimple-fold.c (arith_overflowed_p): New functions. + (gimple_fold_call): Fold {ADD,SUB,MUL}_OVERFLOW internal calls. + * gimple-fold.h (arith_overflowed_p): New prototype. + * tree-ssa-dce.c: Include tree-ssa-propagate.h and gimple-fold.h. + (find_non_realpart_uses, maybe_optimize_arith_overflow): New + functions. + (eliminate_unnecessary_stmts): Transform {ADD,SUB,MUL}_OVERFLOW + into COMPLEX_CST/COMPLEX_EXPR if IMAGPART_EXPR of the result is + never used. + * gimplify.c (gimplify_call_expr): Handle gimplification of + internal calls with lhs. + * internal-fn.c (get_range_pos_neg, get_min_precision, + expand_arith_overflow_result_store): New functions. + (ubsan_expand_si_overflow_addsub_check): Renamed to ... + (expand_addsub_overflow): ... this. Add LOC, LHS, ARG0, ARG1, + UNSR_P, UNS0_P, UNS1_P, IS_UBSAN arguments, remove STMT argument. + Handle ADD_OVERFLOW and SUB_OVERFLOW expansion. + (ubsan_expand_si_overflow_neg_check): Renamed to ... + (expand_neg_overflow): ... this. Add LOC, LHS, ARG1, IS_UBSAN + arguments, remove STMT argument. Handle SUB_OVERFLOW with + 0 as first argument expansion. + (ubsan_expand_si_overflow_mul_check): Renamed to ... + (expand_mul_overflow): ... this. Add LOC, LHS, ARG0, ARG1, + UNSR_P, UNS0_P, UNS1_P, IS_UBSAN arguments, remove STMT argument. + Handle MUL_OVERFLOW expansion. + (expand_UBSAN_CHECK_ADD): Use expand_addsub_overflow, prepare + arguments for it. + (expand_UBSAN_CHECK_SUB): Use expand_addsub_overflow or + expand_neg_overflow, prepare arguments for it. + (expand_UBSAN_CHECK_MUL): Use expand_mul_overflow, prepare arguments + for it. + (expand_arith_overflow, expand_ADD_OVERFLOW, expand_SUB_OVERFLOW, + expand_MUL_OVERFLOW): New functions. + * internal-fn.def (ADD_OVERFLOW, SUB_OVERFLOW, MUL_OVERFLOW): New + internal functions. + * tree-vrp.c (check_for_binary_op_overflow): New function. + (extract_range_basic): Handle {REAL,IMAG}PART_EXPR if the operand + is SSA_NAME set by {ADD,SUB,MUL}_OVERFLOW internal functions. + (simplify_internal_call_using_ranges): Handle {ADD,SUB,MUL}_OVERFLOW + internal functions. + * optabs.def (umulv4_optab): New optab. + * config/i386/i386.md (umulv<mode>4, <u>mulvqi4): New define_expands. + (*umulv<mode>4, *<u>mulvqi4): New define_insns. + * doc/extend.texi (Integer Overflow Builtins): Document + __builtin_*_overflow. + 2014-11-12 Richard Biener <rguenther@suse.de> * genmatch.c (capture_info::capture_info): Add missing diff --git a/gcc/builtin-attrs.def b/gcc/builtin-attrs.def index 593df2d3922..9c05a949039 100644 --- a/gcc/builtin-attrs.def +++ b/gcc/builtin-attrs.def @@ -178,6 +178,9 @@ DEF_ATTR_TREE_LIST (ATTR_NOTHROW_NONNULL_4, ATTR_NONNULL, ATTR_LIST_4, \ /* Nothrow functions whose fifth parameter is a nonnull pointer. */ DEF_ATTR_TREE_LIST (ATTR_NOTHROW_NONNULL_5, ATTR_NONNULL, ATTR_LIST_5, \ ATTR_NOTHROW_LIST) +/* Nothrow leaf functions which are type-generic. */ +DEF_ATTR_TREE_LIST (ATTR_NOTHROW_TYPEGENERIC_LEAF, ATTR_TYPEGENERIC, ATTR_NULL, \ + ATTR_NOTHROW_LEAF_LIST) /* Nothrow const functions whose pointer parameter(s) are all nonnull. */ DEF_ATTR_TREE_LIST (ATTR_CONST_NOTHROW_NONNULL, ATTR_CONST, ATTR_NULL, \ ATTR_NOTHROW_NONNULL) diff --git a/gcc/builtin-types.def b/gcc/builtin-types.def index 84514404cf2..a8ba0ba12e0 100644 --- a/gcc/builtin-types.def +++ b/gcc/builtin-types.def @@ -126,7 +126,10 @@ DEF_PRIMITIVE_TYPE (BT_I16, builtin_type_for_size (BITS_PER_UNIT*16, 1)) DEF_PRIMITIVE_TYPE (BT_BND, pointer_bounds_type_node) DEF_POINTER_TYPE (BT_PTR_CONST_STRING, BT_CONST_STRING) +DEF_POINTER_TYPE (BT_PTR_UINT, BT_UINT) DEF_POINTER_TYPE (BT_PTR_LONG, BT_LONG) +DEF_POINTER_TYPE (BT_PTR_ULONG, BT_ULONG) +DEF_POINTER_TYPE (BT_PTR_LONGLONG, BT_LONGLONG) DEF_POINTER_TYPE (BT_PTR_ULONGLONG, BT_ULONGLONG) DEF_POINTER_TYPE (BT_PTR_PTR, BT_PTR) @@ -435,6 +438,18 @@ DEF_FUNCTION_TYPE_3 (BT_FN_VOID_VPTR_I16_INT, BT_VOID, BT_VOLATILE_PTR, BT_I16, DEF_FUNCTION_TYPE_3 (BT_FN_INT_PTRPTR_SIZE_SIZE, BT_INT, BT_PTR_PTR, BT_SIZE, BT_SIZE) DEF_FUNCTION_TYPE_3 (BT_FN_PTR_CONST_PTR_CONST_PTR_SIZE, BT_PTR, BT_CONST_PTR, BT_CONST_PTR, BT_SIZE) DEF_FUNCTION_TYPE_3 (BT_FN_VOID_CONST_PTR_BND_CONST_PTR, BT_VOID, BT_CONST_PTR, BT_BND, BT_CONST_PTR) +DEF_FUNCTION_TYPE_3 (BT_FN_BOOL_INT_INT_INTPTR, BT_BOOL, BT_INT, BT_INT, + BT_INT_PTR) +DEF_FUNCTION_TYPE_3 (BT_FN_BOOL_LONG_LONG_LONGPTR, BT_BOOL, BT_LONG, BT_LONG, + BT_PTR_LONG) +DEF_FUNCTION_TYPE_3 (BT_FN_BOOL_LONGLONG_LONGLONG_LONGLONGPTR, BT_BOOL, + BT_LONGLONG, BT_LONGLONG, BT_PTR_LONGLONG) +DEF_FUNCTION_TYPE_3 (BT_FN_BOOL_UINT_UINT_UINTPTR, BT_BOOL, BT_UINT, BT_UINT, + BT_PTR_UINT) +DEF_FUNCTION_TYPE_3 (BT_FN_BOOL_ULONG_ULONG_ULONGPTR, BT_BOOL, BT_ULONG, + BT_ULONG, BT_PTR_ULONG) +DEF_FUNCTION_TYPE_3 (BT_FN_BOOL_ULONGLONG_ULONGLONG_ULONGLONGPTR, BT_BOOL, + BT_ULONGLONG, BT_ULONGLONG, BT_PTR_ULONGLONG) DEF_FUNCTION_TYPE_4 (BT_FN_SIZE_CONST_PTR_SIZE_SIZE_FILEPTR, BT_SIZE, BT_CONST_PTR, BT_SIZE, BT_SIZE, BT_FILEPTR) @@ -532,6 +547,7 @@ DEF_FUNCTION_TYPE_8 (BT_FN_VOID_OMPFN_PTR_OMPCPYFN_LONG_LONG_BOOL_UINT_PTR, DEF_FUNCTION_TYPE_VAR_0 (BT_FN_VOID_VAR, BT_VOID) DEF_FUNCTION_TYPE_VAR_0 (BT_FN_INT_VAR, BT_INT) DEF_FUNCTION_TYPE_VAR_0 (BT_FN_PTR_VAR, BT_PTR) +DEF_FUNCTION_TYPE_VAR_0 (BT_FN_BOOL_VAR, BT_BOOL) DEF_FUNCTION_TYPE_VAR_1 (BT_FN_VOID_VALIST_REF_VAR, BT_VOID, BT_VALIST_REF) diff --git a/gcc/builtins.c b/gcc/builtins.c index 71fbf09caa7..1cd65edb194 100644 --- a/gcc/builtins.c +++ b/gcc/builtins.c @@ -9724,6 +9724,62 @@ fold_builtin_unordered_cmp (location_t loc, tree fndecl, tree arg0, tree arg1, fold_build2_loc (loc, code, type, arg0, arg1)); } +/* Fold __builtin_{,s,u}{add,sub,mul}{,l,ll}_overflow, either into normal + arithmetics if it can never overflow, or into internal functions that + return both result of arithmetics and overflowed boolean flag in + a complex integer result, or some other check for overflow. */ + +static tree +fold_builtin_arith_overflow (location_t loc, enum built_in_function fcode, + tree arg0, tree arg1, tree arg2) +{ + enum internal_fn ifn = IFN_LAST; + tree type = TREE_TYPE (TREE_TYPE (arg2)); + tree mem_arg2 = build_fold_indirect_ref_loc (loc, arg2); + switch (fcode) + { + case BUILT_IN_ADD_OVERFLOW: + case BUILT_IN_SADD_OVERFLOW: + case BUILT_IN_SADDL_OVERFLOW: + case BUILT_IN_SADDLL_OVERFLOW: + case BUILT_IN_UADD_OVERFLOW: + case BUILT_IN_UADDL_OVERFLOW: + case BUILT_IN_UADDLL_OVERFLOW: + ifn = IFN_ADD_OVERFLOW; + break; + case BUILT_IN_SUB_OVERFLOW: + case BUILT_IN_SSUB_OVERFLOW: + case BUILT_IN_SSUBL_OVERFLOW: + case BUILT_IN_SSUBLL_OVERFLOW: + case BUILT_IN_USUB_OVERFLOW: + case BUILT_IN_USUBL_OVERFLOW: + case BUILT_IN_USUBLL_OVERFLOW: + ifn = IFN_SUB_OVERFLOW; + break; + case BUILT_IN_MUL_OVERFLOW: + case BUILT_IN_SMUL_OVERFLOW: + case BUILT_IN_SMULL_OVERFLOW: + case BUILT_IN_SMULLL_OVERFLOW: + case BUILT_IN_UMUL_OVERFLOW: + case BUILT_IN_UMULL_OVERFLOW: + case BUILT_IN_UMULLL_OVERFLOW: + ifn = IFN_MUL_OVERFLOW; + break; + default: + gcc_unreachable (); + } + tree ctype = build_complex_type (type); + tree call = build_call_expr_internal_loc (loc, ifn, ctype, + 2, arg0, arg1); + tree tgt = save_expr (call); + tree intres = build1_loc (loc, REALPART_EXPR, type, tgt); + tree ovfres = build1_loc (loc, IMAGPART_EXPR, type, tgt); + ovfres = fold_convert_loc (loc, boolean_type_node, ovfres); + tree store + = fold_build2_loc (loc, MODIFY_EXPR, void_type_node, mem_arg2, intres); + return build2_loc (loc, COMPOUND_EXPR, boolean_type_node, store, ovfres); +} + /* Fold a call to built-in function FNDECL with 0 arguments. IGNORE is true if the result of the function call is ignored. This function returns NULL_TREE if no simplification was possible. */ @@ -10431,6 +10487,29 @@ fold_builtin_3 (location_t loc, tree fndecl, case BUILT_IN_EXPECT: return fold_builtin_expect (loc, arg0, arg1, arg2); + case BUILT_IN_ADD_OVERFLOW: + case BUILT_IN_SUB_OVERFLOW: + case BUILT_IN_MUL_OVERFLOW: + case BUILT_IN_SADD_OVERFLOW: + case BUILT_IN_SADDL_OVERFLOW: + case BUILT_IN_SADDLL_OVERFLOW: + case BUILT_IN_SSUB_OVERFLOW: + case BUILT_IN_SSUBL_OVERFLOW: + case BUILT_IN_SSUBLL_OVERFLOW: + case BUILT_IN_SMUL_OVERFLOW: + case BUILT_IN_SMULL_OVERFLOW: + case BUILT_IN_SMULLL_OVERFLOW: + case BUILT_IN_UADD_OVERFLOW: + case BUILT_IN_UADDL_OVERFLOW: + case BUILT_IN_UADDLL_OVERFLOW: + case BUILT_IN_USUB_OVERFLOW: + case BUILT_IN_USUBL_OVERFLOW: + case BUILT_IN_USUBLL_OVERFLOW: + case BUILT_IN_UMUL_OVERFLOW: + case BUILT_IN_UMULL_OVERFLOW: + case BUILT_IN_UMULLL_OVERFLOW: + return fold_builtin_arith_overflow (loc, fcode, arg0, arg1, arg2); + default: break; } diff --git a/gcc/builtins.def b/gcc/builtins.def index 552becc3571..040601677c7 100644 --- a/gcc/builtins.def +++ b/gcc/builtins.def @@ -671,6 +671,30 @@ DEF_C94_BUILTIN (BUILT_IN_ISWXDIGIT, "iswxdigit", BT_FN_INT_WINT, ATTR_PU DEF_C94_BUILTIN (BUILT_IN_TOWLOWER, "towlower", BT_FN_WINT_WINT, ATTR_PURE_NOTHROW_LEAF_LIST) DEF_C94_BUILTIN (BUILT_IN_TOWUPPER, "towupper", BT_FN_WINT_WINT, ATTR_PURE_NOTHROW_LEAF_LIST) +/* Category: integer overflow checking builtins. */ +DEF_GCC_BUILTIN (BUILT_IN_ADD_OVERFLOW, "add_overflow", BT_FN_BOOL_VAR, ATTR_NOTHROW_TYPEGENERIC_LEAF) +DEF_GCC_BUILTIN (BUILT_IN_SUB_OVERFLOW, "sub_overflow", BT_FN_BOOL_VAR, ATTR_NOTHROW_TYPEGENERIC_LEAF) +DEF_GCC_BUILTIN (BUILT_IN_MUL_OVERFLOW, "mul_overflow", BT_FN_BOOL_VAR, ATTR_NOTHROW_TYPEGENERIC_LEAF) +/* Clang compatibility. */ +DEF_GCC_BUILTIN (BUILT_IN_SADD_OVERFLOW, "sadd_overflow", BT_FN_BOOL_INT_INT_INTPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SADDL_OVERFLOW, "saddl_overflow", BT_FN_BOOL_LONG_LONG_LONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SADDLL_OVERFLOW, "saddll_overflow", BT_FN_BOOL_LONGLONG_LONGLONG_LONGLONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SSUB_OVERFLOW, "ssub_overflow", BT_FN_BOOL_INT_INT_INTPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SSUBL_OVERFLOW, "ssubl_overflow", BT_FN_BOOL_LONG_LONG_LONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SSUBLL_OVERFLOW, "ssubll_overflow", BT_FN_BOOL_LONGLONG_LONGLONG_LONGLONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SMUL_OVERFLOW, "smul_overflow", BT_FN_BOOL_INT_INT_INTPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SMULL_OVERFLOW, "smull_overflow", BT_FN_BOOL_LONG_LONG_LONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_SMULLL_OVERFLOW, "smulll_overflow", BT_FN_BOOL_LONGLONG_LONGLONG_LONGLONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_UADD_OVERFLOW, "uadd_overflow", BT_FN_BOOL_UINT_UINT_UINTPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_UADDL_OVERFLOW, "uaddl_overflow", BT_FN_BOOL_ULONG_ULONG_ULONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_UADDLL_OVERFLOW, "uaddll_overflow", BT_FN_BOOL_ULONGLONG_ULONGLONG_ULONGLONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_USUB_OVERFLOW, "usub_overflow", BT_FN_BOOL_UINT_UINT_UINTPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_USUBL_OVERFLOW, "usubl_overflow", BT_FN_BOOL_ULONG_ULONG_ULONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_USUBLL_OVERFLOW, "usubll_overflow", BT_FN_BOOL_ULONGLONG_ULONGLONG_ULONGLONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_UMUL_OVERFLOW, "umul_overflow", BT_FN_BOOL_UINT_UINT_UINTPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_UMULL_OVERFLOW, "umull_overflow", BT_FN_BOOL_ULONG_ULONG_ULONGPTR, ATTR_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_UMULLL_OVERFLOW, "umulll_overflow", BT_FN_BOOL_ULONGLONG_ULONGLONG_ULONGLONGPTR, ATTR_NOTHROW_LEAF_LIST) + /* Category: miscellaneous builtins. */ DEF_LIB_BUILTIN (BUILT_IN_ABORT, "abort", BT_FN_VOID, ATTR_NORETURN_NOTHROW_LEAF_LIST) DEF_LIB_BUILTIN (BUILT_IN_ABS, "abs", BT_FN_INT_INT, ATTR_CONST_NOTHROW_LEAF_LIST) diff --git a/gcc/c-family/ChangeLog b/gcc/c-family/ChangeLog index 33c7d29b8a1..7feda0f185d 100644 --- a/gcc/c-family/ChangeLog +++ b/gcc/c-family/ChangeLog @@ -1,3 +1,9 @@ +2014-11-12 Jakub Jelinek <jakub@redhat.com> + + PR c/59708 + * c-common.c (check_builtin_function_arguments): Handle + BUILT_IN_{ADD,SUB,MUL}_OVERFLOW. + 2014-11-10 Andi Kleen <ak@linux.intel.com> PR c/60804 diff --git a/gcc/c-family/c-common.c b/gcc/c-family/c-common.c index ed723146ac6..839111a2122 100644 --- a/gcc/c-family/c-common.c +++ b/gcc/c-family/c-common.c @@ -9649,6 +9649,30 @@ check_builtin_function_arguments (tree fndecl, int nargs, tree *args) } return false; + case BUILT_IN_ADD_OVERFLOW: + case BUILT_IN_SUB_OVERFLOW: + case BUILT_IN_MUL_OVERFLOW: + if (builtin_function_validate_nargs (fndecl, nargs, 3)) + { + unsigned i; + for (i = 0; i < 2; i++) + if (!INTEGRAL_TYPE_P (TREE_TYPE (args[i]))) + { + error ("argument %u in call to function %qE does not have " + "integral type", i + 1, fndecl); + return false; + } + if (TREE_CODE (TREE_TYPE (args[2])) != POINTER_TYPE + || TREE_CODE (TREE_TYPE (TREE_TYPE (args[2]))) != INTEGER_TYPE) + { + error ("argument 3 in call to function %qE does not have " + "pointer to integer type", fndecl); + return false; + } + return true; + } + return false; + default: return true; } diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index 83619b1a2ed..203db11ff06 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -6663,6 +6663,99 @@ (const_string "4")] (const_string "<MODE_SIZE>")))]) +(define_expand "umulv<mode>4" + [(parallel [(set (reg:CCO FLAGS_REG) + (eq:CCO (mult:<DWI> + (zero_extend:<DWI> + (match_operand:SWI48 1 + "nonimmediate_operand")) + (zero_extend:<DWI> + (match_operand:SWI48 2 + "nonimmediate_operand"))) + (zero_extend:<DWI> + (mult:SWI48 (match_dup 1) (match_dup 2))))) + (set (match_operand:SWI48 0 "register_operand") + (mult:SWI48 (match_dup 1) (match_dup 2))) + (clobber (match_scratch:SWI48 4))]) + (set (pc) (if_then_else + (eq (reg:CCO FLAGS_REG) (const_int 0)) + (label_ref (match_operand 3)) + (pc)))] + "" +{ + if (MEM_P (operands[1]) && MEM_P (operands[2])) + operands[1] = force_reg (<MODE>mode, operands[1]); +}) + +(define_insn "*umulv<mode>4" + [(set (reg:CCO FLAGS_REG) + (eq:CCO (mult:<DWI> + (zero_extend:<DWI> + (match_operand:SWI48 1 "nonimmediate_operand" "%0")) + (zero_extend:<DWI> + (match_operand:SWI48 2 "nonimmediate_operand" "rm"))) + (zero_extend:<DWI> + (mult:SWI48 (match_dup 1) (match_dup 2))))) + (set (match_operand:SWI48 0 "register_operand" "=a") + (mult:SWI48 (match_dup 1) (match_dup 2))) + (clobber (match_scratch:SWI48 3 "=d"))] + "!(MEM_P (operands[1]) && MEM_P (operands[2]))" + "mul{<imodesuffix>}\t%2" + [(set_attr "type" "imul") + (set_attr "length_immediate" "0") + (set (attr "athlon_decode") + (if_then_else (eq_attr "cpu" "athlon") + (const_string "vector") + (const_string "double"))) + (set_attr "amdfam10_decode" "double") + (set_attr "bdver1_decode" "direct") + (set_attr "mode" "<MODE>")]) + +(define_expand "<u>mulvqi4" + [(parallel [(set (reg:CCO FLAGS_REG) + (eq:CCO (mult:HI + (any_extend:HI + (match_operand:QI 1 "nonimmediate_operand")) + (any_extend:HI + (match_operand:QI 2 "nonimmediate_operand"))) + (any_extend:HI + (mult:QI (match_dup 1) (match_dup 2))))) + (set (match_operand:QI 0 "register_operand") + (mult:QI (match_dup 1) (match_dup 2)))]) + (set (pc) (if_then_else + (eq (reg:CCO FLAGS_REG) (const_int 0)) + (label_ref (match_operand 3)) + (pc)))] + "TARGET_QIMODE_MATH" +{ + if (MEM_P (operands[1]) && MEM_P (operands[2])) + operands[1] = force_reg (QImode, operands[1]); +}) + +(define_insn "*<u>mulvqi4" + [(set (reg:CCO FLAGS_REG) + (eq:CCO (mult:HI + (any_extend:HI + (match_operand:QI 1 "nonimmediate_operand" "%0")) + (any_extend:HI + (match_operand:QI 2 "nonimmediate_operand" "qm"))) + (any_extend:HI + (mult:QI (match_dup 1) (match_dup 2))))) + (set (match_operand:QI 0 "register_operand" "=a") + (mult:QI (match_dup 1) (match_dup 2)))] + "TARGET_QIMODE_MATH + && !(MEM_P (operands[1]) && MEM_P (operands[2]))" + "<sgnprefix>mul{b}\t%2" + [(set_attr "type" "imul") + (set_attr "length_immediate" "0") + (set (attr "athlon_decode") + (if_then_else (eq_attr "cpu" "athlon") + (const_string "vector") + (const_string "direct"))) + (set_attr "amdfam10_decode" "direct") + (set_attr "bdver1_decode" "direct") + (set_attr "mode" "QI")]) + (define_expand "<u>mul<mode><dwi>3" [(parallel [(set (match_operand:<DWI> 0 "register_operand") (mult:<DWI> diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi index 36127b56ace..d10a815a977 100644 --- a/gcc/doc/extend.texi +++ b/gcc/doc/extend.texi @@ -76,6 +76,8 @@ extensions, accepted by GCC in C90 mode and in C++. * Offsetof:: Special syntax for implementing @code{offsetof}. * __sync Builtins:: Legacy built-in functions for atomic memory access. * __atomic Builtins:: Atomic built-in functions with memory model. +* Integer Overflow Builtins:: Built-in functions to perform arithmetics and + arithmetic overflow checking. * x86 specific memory model extensions for transactional memory:: x86 memory models. * Object Size Checking:: Built-in functions for limited buffer overflow checking. @@ -8487,6 +8489,65 @@ alignment. A value of 0 indicates typical alignment should be used. The compiler may also ignore this parameter. @end deftypefn +@node Integer Overflow Builtins +@section Built-in functions to perform arithmetics and arithmetic overflow checking. + +The following built-in functions allow performing simple arithmetic operations +together with checking whether the operations overflowed. + +@deftypefn {Built-in Function} bool __builtin_add_overflow (@var{type1} a, @var{type2} b, @var{type3} *res) +@deftypefnx {Built-in Function} bool __builtin_sadd_overflow (int a, int b, int *res) +@deftypefnx {Built-in Function} bool __builtin_saddl_overflow (long int a, long int b, long int *res) +@deftypefnx {Built-in Function} bool __builtin_saddll_overflow (long long int a, long long int b, long int *res) +@deftypefnx {Built-in Function} bool __builtin_uadd_overflow (unsigned int a, unsigned int b, unsigned int *res) +@deftypefnx {Built-in Function} bool __builtin_uaddl_overflow (unsigned long int a, unsigned long int b, unsigned long int *res) +@deftypefnx {Built-in Function} bool __builtin_uaddll_overflow (unsigned long long int a, unsigned long long int b, unsigned long int *res) + +These built-in functions promote the first two operands into infinite precision signed +type and perform addition on those promoted operands. The result is then +cast to the type the third pointer argument points to and stored there. +If the stored result is equal to the infinite precision result, the built-in +functions return false, otherwise they return true. As the addition is +performed in infinite signed precision, these built-in functions have fully defined +behavior for all argument values. + +The first built-in function allows arbitrary integral types for operands and +the result type must be pointer to some integer type, the rest of the built-in +functions have explicit integer types. + +The compiler will attempt to use hardware instructions to implement +these built-in functions where possible, like conditional jump on overflow +after addition, conditional jump on carry etc. + +@end deftypefn + +@deftypefn {Built-in Function} bool __builtin_sub_overflow (@var{type1} a, @var{type2} b, @var{type3} *res) +@deftypefnx {Built-in Function} bool __builtin_ssub_overflow (int a, int b, int *res) +@deftypefnx {Built-in Function} bool __builtin_ssubl_overflow (long int a, long int b, long int *res) +@deftypefnx {Built-in Function} bool __builtin_ssubll_overflow (long long int a, long long int b, long int *res) +@deftypefnx {Built-in Function} bool __builtin_usub_overflow (unsigned int a, unsigned int b, unsigned int *res) +@deftypefnx {Built-in Function} bool __builtin_usubl_overflow (unsigned long int a, unsigned long int b, unsigned long int *res) +@deftypefnx {Built-in Function} bool __builtin_usubll_overflow (unsigned long long int a, unsigned long long int b, unsigned long int *res) + +These built-in functions are similar to the add overflow checking built-in +functions above, except they perform subtraction, subtract the second argument +from the first one, instead of addition. + +@end deftypefn + +@deftypefn {Built-in Function} bool __builtin_mul_overflow (@var{type1} a, @var{type2} b, @var{type3} *res) +@deftypefnx {Built-in Function} bool __builtin_smul_overflow (int a, int b, int *res) +@deftypefnx {Built-in Function} bool __builtin_smull_overflow (long int a, long int b, long int *res) +@deftypefnx {Built-in Function} bool __builtin_smulll_overflow (long long int a, long long int b, long int *res) +@deftypefnx {Built-in Function} bool __builtin_umul_overflow (unsigned int a, unsigned int b, unsigned int *res) +@deftypefnx {Built-in Function} bool __builtin_umull_overflow (unsigned long int a, unsigned long int b, unsigned long int *res) +@deftypefnx {Built-in Function} bool __builtin_umulll_overflow (unsigned long long int a, unsigned long long int b, unsigned long int *res) + +These built-in functions are similar to the add overflow checking built-in +functions above, except they perform multiplication, instead of addition. + +@end deftypefn + @node x86 specific memory model extensions for transactional memory @section x86 specific memory model extensions for transactional memory diff --git a/gcc/expr.c b/gcc/expr.c index 0ef06ea98ae..2e7f839f316 100644 --- a/gcc/expr.c +++ b/gcc/expr.c @@ -168,7 +168,6 @@ static void emit_single_push_insn (machine_mode, rtx, tree); #endif static void do_tablejump (rtx, machine_mode, rtx, rtx, rtx, int); static rtx const_vector_from_tree (tree); -static void write_complex_part (rtx, rtx, bool); /* This is run to set up which modes can be used @@ -2995,7 +2994,7 @@ set_storage_via_setmem (rtx object, rtx size, rtx val, unsigned int align, /* Write to one of the components of the complex value CPLX. Write VAL to the real part if IMAG_P is false, and the imaginary part if its true. */ -static void +void write_complex_part (rtx cplx, rtx val, bool imag_p) { machine_mode cmode; diff --git a/gcc/expr.h b/gcc/expr.h index a188b6d6863..02cce0f0807 100644 --- a/gcc/expr.h +++ b/gcc/expr.h @@ -255,6 +255,7 @@ extern rtx_insn *emit_move_insn_1 (rtx, rtx); extern rtx_insn *emit_move_complex_push (machine_mode, rtx, rtx); extern rtx_insn *emit_move_complex_parts (rtx, rtx); +extern void write_complex_part (rtx, rtx, bool); extern rtx emit_move_resolve_push (machine_mode, rtx); /* Push a block of length SIZE (perhaps variable) diff --git a/gcc/function.c b/gcc/function.c index 6bdb500baeb..ef980915909 100644 --- a/gcc/function.c +++ b/gcc/function.c @@ -2020,9 +2020,14 @@ aggregate_value_p (const_tree exp, const_tree fntype) case CALL_EXPR: { tree fndecl = get_callee_fndecl (fntype); - fntype = (fndecl - ? TREE_TYPE (fndecl) - : TREE_TYPE (TREE_TYPE (CALL_EXPR_FN (fntype)))); + if (fndecl) + fntype = TREE_TYPE (fndecl); + else if (CALL_EXPR_FN (fntype)) + fntype = TREE_TYPE (TREE_TYPE (CALL_EXPR_FN (fntype))); + else + /* For internal functions, assume nothing needs to be + returned in memory. */ + return 0; } break; case FUNCTION_DECL: diff --git a/gcc/gimple-fold.c b/gcc/gimple-fold.c index 71e46388d61..aeb180370d8 100644 --- a/gcc/gimple-fold.c +++ b/gcc/gimple-fold.c @@ -2586,6 +2586,33 @@ gimple_fold_builtin (gimple_stmt_iterator *gsi) return false; } +/* Return true if ARG0 CODE ARG1 in infinite signed precision operation + doesn't fit into TYPE. The test for overflow should be regardless of + -fwrapv, and even for unsigned types. */ + +bool +arith_overflowed_p (enum tree_code code, const_tree type, + const_tree arg0, const_tree arg1) +{ + typedef FIXED_WIDE_INT (WIDE_INT_MAX_PRECISION * 2) widest2_int; + typedef generic_wide_int <wi::extended_tree <WIDE_INT_MAX_PRECISION * 2> > + widest2_int_cst; + widest2_int warg0 = widest2_int_cst (arg0); + widest2_int warg1 = widest2_int_cst (arg1); + widest2_int wres; + switch (code) + { + case PLUS_EXPR: wres = wi::add (warg0, warg1); break; + case MINUS_EXPR: wres = wi::sub (warg0, warg1); break; + case MULT_EXPR: wres = wi::mul (warg0, warg1); break; + default: gcc_unreachable (); + } + signop sign = TYPE_SIGN (type); + if (sign == UNSIGNED && wi::neg_p (wres)) + return true; + return wi::min_precision (wres, sign) > TYPE_PRECISION (type); +} + /* Attempt to fold a call statement referenced by the statement iterator GSI. The statement may be replaced by another statement, e.g., if the call simplifies to a constant value. Return true if any changes were made. @@ -2714,6 +2741,8 @@ gimple_fold_call (gimple_stmt_iterator *gsi, bool inplace) { enum tree_code subcode = ERROR_MARK; tree result = NULL_TREE; + bool cplx_result = false; + tree overflow = NULL_TREE; switch (gimple_call_internal_fn (stmt)) { case IFN_BUILTIN_EXPECT: @@ -2744,6 +2773,18 @@ gimple_fold_call (gimple_stmt_iterator *gsi, bool inplace) case IFN_UBSAN_CHECK_MUL: subcode = MULT_EXPR; break; + case IFN_ADD_OVERFLOW: + subcode = PLUS_EXPR; + cplx_result = true; + break; + case IFN_SUB_OVERFLOW: + subcode = MINUS_EXPR; + cplx_result = true; + break; + case IFN_MUL_OVERFLOW: + subcode = MULT_EXPR; + cplx_result = true; + break; default: break; } @@ -2751,30 +2792,88 @@ gimple_fold_call (gimple_stmt_iterator *gsi, bool inplace) { tree arg0 = gimple_call_arg (stmt, 0); tree arg1 = gimple_call_arg (stmt, 1); + tree type = TREE_TYPE (arg0); + if (cplx_result) + { + tree lhs = gimple_call_lhs (stmt); + if (lhs == NULL_TREE) + type = NULL_TREE; + else + type = TREE_TYPE (TREE_TYPE (lhs)); + } + if (type == NULL_TREE) + ; /* x = y + 0; x = y - 0; x = y * 0; */ - if (integer_zerop (arg1)) - result = subcode == MULT_EXPR - ? build_zero_cst (TREE_TYPE (arg0)) - : arg0; + else if (integer_zerop (arg1)) + result = subcode == MULT_EXPR ? integer_zero_node : arg0; /* x = 0 + y; x = 0 * y; */ else if (subcode != MINUS_EXPR && integer_zerop (arg0)) - result = subcode == MULT_EXPR - ? build_zero_cst (TREE_TYPE (arg0)) - : arg1; + result = subcode == MULT_EXPR ? integer_zero_node : arg1; /* x = y - y; */ else if (subcode == MINUS_EXPR && operand_equal_p (arg0, arg1, 0)) - result = build_zero_cst (TREE_TYPE (arg0)); + result = integer_zero_node; /* x = y * 1; x = 1 * y; */ - else if (subcode == MULT_EXPR) + else if (subcode == MULT_EXPR && integer_onep (arg1)) + result = arg0; + else if (subcode == MULT_EXPR && integer_onep (arg0)) + result = arg1; + else if (TREE_CODE (arg0) == INTEGER_CST + && TREE_CODE (arg1) == INTEGER_CST) + { + if (cplx_result) + result = int_const_binop (subcode, fold_convert (type, arg0), + fold_convert (type, arg1)); + else + result = int_const_binop (subcode, arg0, arg1); + if (result && arith_overflowed_p (subcode, type, arg0, arg1)) + { + if (cplx_result) + overflow = build_one_cst (type); + else + result = NULL_TREE; + } + } + if (result) { - if (integer_onep (arg1)) - result = arg0; - else if (integer_onep (arg0)) - result = arg1; + if (result == integer_zero_node) + result = build_zero_cst (type); + else if (cplx_result && TREE_TYPE (result) != type) + { + if (TREE_CODE (result) == INTEGER_CST) + { + if (arith_overflowed_p (PLUS_EXPR, type, result, + integer_zero_node)) + overflow = build_one_cst (type); + } + else if ((!TYPE_UNSIGNED (TREE_TYPE (result)) + && TYPE_UNSIGNED (type)) + || (TYPE_PRECISION (type) + < (TYPE_PRECISION (TREE_TYPE (result)) + + (TYPE_UNSIGNED (TREE_TYPE (result)) + && !TYPE_UNSIGNED (type))))) + result = NULL_TREE; + if (result) + result = fold_convert (type, result); + } } } + if (result) { + if (TREE_CODE (result) == INTEGER_CST && TREE_OVERFLOW (result)) + result = drop_tree_overflow (result); + if (cplx_result) + { + if (overflow == NULL_TREE) + overflow = build_zero_cst (TREE_TYPE (result)); + tree ctype = build_complex_type (TREE_TYPE (result)); + if (TREE_CODE (result) == INTEGER_CST + && TREE_CODE (overflow) == INTEGER_CST) + result = build_complex (ctype, result, overflow); + else + result = build2_loc (gimple_location (stmt), COMPLEX_EXPR, + ctype, result, overflow); + } if (!update_call_from_tree (gsi, result)) gimplify_and_update_call_from_tree (gsi, result); changed = true; diff --git a/gcc/gimple-fold.h b/gcc/gimple-fold.h index 0cd2899494e..f42ff0264e3 100644 --- a/gcc/gimple-fold.h +++ b/gcc/gimple-fold.h @@ -32,6 +32,8 @@ extern tree maybe_fold_and_comparisons (enum tree_code, tree, tree, enum tree_code, tree, tree); extern tree maybe_fold_or_comparisons (enum tree_code, tree, tree, enum tree_code, tree, tree); +extern bool arith_overflowed_p (enum tree_code, const_tree, const_tree, + const_tree); extern tree no_follow_ssa_edges (tree); extern tree follow_single_use_edges (tree); extern tree gimple_fold_stmt_to_constant_1 (gimple, tree (*) (tree)); diff --git a/gcc/gimplify.c b/gcc/gimplify.c index f5afc0da292..93c06debda5 100644 --- a/gcc/gimplify.c +++ b/gcc/gimplify.c @@ -2281,6 +2281,9 @@ gimplify_call_expr (tree *expr_p, gimple_seq *pre_p, bool want_value) /* Gimplify internal functions created in the FEs. */ if (CALL_EXPR_FN (*expr_p) == NULL_TREE) { + if (want_value) + return GS_ALL_DONE; + nargs = call_expr_nargs (*expr_p); enum internal_fn ifn = CALL_EXPR_IFN (*expr_p); auto_vec<tree> vargs (nargs); @@ -4644,22 +4647,41 @@ gimplify_modify_expr (tree *expr_p, gimple_seq *pre_p, gimple_seq *post_p, { /* Since the RHS is a CALL_EXPR, we need to create a GIMPLE_CALL instead of a GIMPLE_ASSIGN. */ - tree fnptrtype = TREE_TYPE (CALL_EXPR_FN (*from_p)); - CALL_EXPR_FN (*from_p) = TREE_OPERAND (CALL_EXPR_FN (*from_p), 0); - STRIP_USELESS_TYPE_CONVERSION (CALL_EXPR_FN (*from_p)); - tree fndecl = get_callee_fndecl (*from_p); - if (fndecl - && DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_NORMAL - && DECL_FUNCTION_CODE (fndecl) == BUILT_IN_EXPECT - && call_expr_nargs (*from_p) == 3) - assign = gimple_build_call_internal (IFN_BUILTIN_EXPECT, 3, - CALL_EXPR_ARG (*from_p, 0), - CALL_EXPR_ARG (*from_p, 1), - CALL_EXPR_ARG (*from_p, 2)); + if (CALL_EXPR_FN (*from_p) == NULL_TREE) + { + /* Gimplify internal functions created in the FEs. */ + int nargs = call_expr_nargs (*from_p), i; + enum internal_fn ifn = CALL_EXPR_IFN (*from_p); + auto_vec<tree> vargs (nargs); + + for (i = 0; i < nargs; i++) + { + gimplify_arg (&CALL_EXPR_ARG (*from_p, i), pre_p, + EXPR_LOCATION (*from_p)); + vargs.quick_push (CALL_EXPR_ARG (*from_p, i)); + } + assign = gimple_build_call_internal_vec (ifn, vargs); + gimple_set_location (assign, EXPR_LOCATION (*expr_p)); + } else { - assign = gimple_build_call_from_tree (*from_p); - gimple_call_set_fntype (assign, TREE_TYPE (fnptrtype)); + tree fnptrtype = TREE_TYPE (CALL_EXPR_FN (*from_p)); + CALL_EXPR_FN (*from_p) = TREE_OPERAND (CALL_EXPR_FN (*from_p), 0); + STRIP_USELESS_TYPE_CONVERSION (CALL_EXPR_FN (*from_p)); + tree fndecl = get_callee_fndecl (*from_p); + if (fndecl + && DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_NORMAL + && DECL_FUNCTION_CODE (fndecl) == BUILT_IN_EXPECT + && call_expr_nargs (*from_p) == 3) + assign = gimple_build_call_internal (IFN_BUILTIN_EXPECT, 3, + CALL_EXPR_ARG (*from_p, 0), + CALL_EXPR_ARG (*from_p, 1), + CALL_EXPR_ARG (*from_p, 2)); + else + { + assign = gimple_build_call_from_tree (*from_p); + gimple_call_set_fntype (assign, TREE_TYPE (fnptrtype)); + } } notice_special_calls (assign); if (!gimple_call_noreturn_p (assign)) diff --git a/gcc/internal-fn.c b/gcc/internal-fn.c index 04f8b6415fb..073d941d8ce 100644 --- a/gcc/internal-fn.c +++ b/gcc/internal-fn.c @@ -208,32 +208,494 @@ expand_ASAN_CHECK (gimple stmt ATTRIBUTE_UNUSED) gcc_unreachable (); } +/* Helper function for expand_addsub_overflow. Return 1 + if ARG interpreted as signed in its precision is known to be always + positive or 2 if ARG is known to be always negative, or 3 if ARG may + be positive or negative. */ + +static int +get_range_pos_neg (tree arg) +{ + if (arg == error_mark_node) + return 3; + + int prec = TYPE_PRECISION (TREE_TYPE (arg)); + int cnt = 0; + if (TREE_CODE (arg) == INTEGER_CST) + { + wide_int w = wi::sext (arg, prec); + if (wi::neg_p (w)) + return 2; + else + return 1; + } + while (CONVERT_EXPR_P (arg) + && INTEGRAL_TYPE_P (TREE_TYPE (TREE_OPERAND (arg, 0))) + && TYPE_PRECISION (TREE_TYPE (TREE_OPERAND (arg, 0))) <= prec) + { + arg = TREE_OPERAND (arg, 0); + /* Narrower value zero extended into wider type + will always result in positive values. */ + if (TYPE_UNSIGNED (TREE_TYPE (arg)) + && TYPE_PRECISION (TREE_TYPE (arg)) < prec) + return 1; + prec = TYPE_PRECISION (TREE_TYPE (arg)); + if (++cnt > 30) + return 3; + } + + if (TREE_CODE (arg) != SSA_NAME) + return 3; + wide_int arg_min, arg_max; + while (get_range_info (arg, &arg_min, &arg_max) != VR_RANGE) + { + gimple g = SSA_NAME_DEF_STMT (arg); + if (is_gimple_assign (g) + && CONVERT_EXPR_CODE_P (gimple_assign_rhs_code (g))) + { + tree t = gimple_assign_rhs1 (g); + if (INTEGRAL_TYPE_P (TREE_TYPE (t)) + && TYPE_PRECISION (TREE_TYPE (t)) <= prec) + { + if (TYPE_UNSIGNED (TREE_TYPE (t)) + && TYPE_PRECISION (TREE_TYPE (t)) < prec) + return 1; + prec = TYPE_PRECISION (TREE_TYPE (t)); + arg = t; + if (++cnt > 30) + return 3; + continue; + } + } + return 3; + } + if (TYPE_UNSIGNED (TREE_TYPE (arg))) + { + /* For unsigned values, the "positive" range comes + below the "negative" range. */ + if (!wi::neg_p (wi::sext (arg_max, prec), SIGNED)) + return 1; + if (wi::neg_p (wi::sext (arg_min, prec), SIGNED)) + return 2; + } + else + { + if (!wi::neg_p (wi::sext (arg_min, prec), SIGNED)) + return 1; + if (wi::neg_p (wi::sext (arg_max, prec), SIGNED)) + return 2; + } + return 3; +} + +/* Return minimum precision needed to represent all values + of ARG in SIGNed integral type. */ + +static int +get_min_precision (tree arg, signop sign) +{ + int prec = TYPE_PRECISION (TREE_TYPE (arg)); + int cnt = 0; + signop orig_sign = sign; + if (TREE_CODE (arg) == INTEGER_CST) + { + int p; + if (TYPE_SIGN (TREE_TYPE (arg)) != sign) + { + widest_int w = wi::to_widest (arg); + w = wi::ext (w, prec, sign); + p = wi::min_precision (w, sign); + } + else + p = wi::min_precision (arg, sign); + return MIN (p, prec); + } + while (CONVERT_EXPR_P (arg) + && INTEGRAL_TYPE_P (TREE_TYPE (TREE_OPERAND (arg, 0))) + && TYPE_PRECISION (TREE_TYPE (TREE_OPERAND (arg, 0))) <= prec) + { + arg = TREE_OPERAND (arg, 0); + if (TYPE_PRECISION (TREE_TYPE (arg)) < prec) + { + if (TYPE_UNSIGNED (TREE_TYPE (arg))) + sign = UNSIGNED; + else if (sign == UNSIGNED && get_range_pos_neg (arg) != 1) + return prec + (orig_sign != sign); + prec = TYPE_PRECISION (TREE_TYPE (arg)); + } + if (++cnt > 30) + return prec + (orig_sign != sign); + } + if (TREE_CODE (arg) != SSA_NAME) + return prec + (orig_sign != sign); + wide_int arg_min, arg_max; + while (get_range_info (arg, &arg_min, &arg_max) != VR_RANGE) + { + gimple g = SSA_NAME_DEF_STMT (arg); + if (is_gimple_assign (g) + && CONVERT_EXPR_CODE_P (gimple_assign_rhs_code (g))) + { + tree t = gimple_assign_rhs1 (g); + if (INTEGRAL_TYPE_P (TREE_TYPE (t)) + && TYPE_PRECISION (TREE_TYPE (t)) <= prec) + { + arg = t; + if (TYPE_PRECISION (TREE_TYPE (arg)) < prec) + { + if (TYPE_UNSIGNED (TREE_TYPE (arg))) + sign = UNSIGNED; + else if (sign == UNSIGNED && get_range_pos_neg (arg) != 1) + return prec + (orig_sign != sign); + prec = TYPE_PRECISION (TREE_TYPE (arg)); + } + if (++cnt > 30) + return prec + (orig_sign != sign); + continue; + } + } + return prec + (orig_sign != sign); + } + if (sign == TYPE_SIGN (TREE_TYPE (arg))) + { + int p1 = wi::min_precision (arg_min, sign); + int p2 = wi::min_precision (arg_max, sign); + p1 = MAX (p1, p2); + prec = MIN (prec, p1); + } + else if (sign == UNSIGNED && !wi::neg_p (arg_min, SIGNED)) + { + int p = wi::min_precision (arg_max, SIGNED); + prec = MIN (prec, p); + } + return prec + (orig_sign != sign); +} + +/* Helper for expand_*_overflow. Store RES into the __real__ part + of TARGET. If RES has larger MODE than __real__ part of TARGET, + set the __imag__ part to 1 if RES doesn't fit into it. */ + +static void +expand_arith_overflow_result_store (tree lhs, rtx target, + machine_mode mode, rtx res) +{ + machine_mode tgtmode = GET_MODE_INNER (GET_MODE (target)); + rtx lres = res; + if (tgtmode != mode) + { + rtx_code_label *done_label = gen_label_rtx (); + int uns = TYPE_UNSIGNED (TREE_TYPE (TREE_TYPE (lhs))); + lres = convert_modes (tgtmode, mode, res, uns); + gcc_assert (GET_MODE_PRECISION (tgtmode) < GET_MODE_PRECISION (mode)); + emit_cmp_and_jump_insns (res, convert_modes (mode, tgtmode, lres, uns), + EQ, NULL_RTX, mode, false, done_label, + PROB_VERY_LIKELY); + write_complex_part (target, const1_rtx, true); + emit_label (done_label); + } + write_complex_part (target, lres, false); +} + /* Add sub/add overflow checking to the statement STMT. CODE says whether the operation is +, or -. */ -void -ubsan_expand_si_overflow_addsub_check (tree_code code, gimple stmt) +static void +expand_addsub_overflow (location_t loc, tree_code code, tree lhs, + tree arg0, tree arg1, bool unsr_p, bool uns0_p, + bool uns1_p, bool is_ubsan) { - rtx res, op0, op1; - tree lhs, fn, arg0, arg1; - rtx_code_label *done_label, *do_error; - rtx target = NULL_RTX; - - lhs = gimple_call_lhs (stmt); - arg0 = gimple_call_arg (stmt, 0); - arg1 = gimple_call_arg (stmt, 1); - done_label = gen_label_rtx (); - do_error = gen_label_rtx (); + rtx res, target = NULL_RTX; + tree fn; + rtx_code_label *done_label = gen_label_rtx (); + rtx_code_label *do_error = gen_label_rtx (); do_pending_stack_adjust (); - op0 = expand_normal (arg0); - op1 = expand_normal (arg1); - + rtx op0 = expand_normal (arg0); + rtx op1 = expand_normal (arg1); machine_mode mode = TYPE_MODE (TREE_TYPE (arg0)); + int prec = GET_MODE_PRECISION (mode); + rtx sgn = immed_wide_int_const (wi::min_value (prec, SIGNED), mode); + bool do_xor = false; + + if (is_ubsan) + gcc_assert (!unsr_p && !uns0_p && !uns1_p); + if (lhs) - target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + { + target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + if (!is_ubsan) + write_complex_part (target, const0_rtx, true); + } + + /* We assume both operands and result have the same precision + here (GET_MODE_BITSIZE (mode)), S stands for signed type + with that precision, U for unsigned type with that precision, + sgn for unsigned most significant bit in that precision. + s1 is signed first operand, u1 is unsigned first operand, + s2 is signed second operand, u2 is unsigned second operand, + sr is signed result, ur is unsigned result and the following + rules say how to compute result (which is always result of + the operands as if both were unsigned, cast to the right + signedness) and how to compute whether operation overflowed. + + s1 + s2 -> sr + res = (S) ((U) s1 + (U) s2) + ovf = s2 < 0 ? res > s1 : res < s1 (or jump on overflow) + s1 - s2 -> sr + res = (S) ((U) s1 - (U) s2) + ovf = s2 < 0 ? res < s1 : res > s2 (or jump on overflow) + u1 + u2 -> ur + res = u1 + u2 + ovf = res < u1 (or jump on carry, but RTL opts will handle it) + u1 - u2 -> ur + res = u1 - u2 + ovf = res > u1 (or jump on carry, but RTL opts will handle it) + s1 + u2 -> sr + res = (S) ((U) s1 + u2) + ovf = ((U) res ^ sgn) < u2 + s1 + u2 -> ur + t1 = (S) (u2 ^ sgn) + t2 = s1 + t1 + res = (U) t2 ^ sgn + ovf = t1 < 0 ? t2 > s1 : t2 < s1 (or jump on overflow) + s1 - u2 -> sr + res = (S) ((U) s1 - u2) + ovf = u2 > ((U) s1 ^ sgn) + s1 - u2 -> ur + res = (U) s1 - u2 + ovf = s1 < 0 || u2 > (U) s1 + u1 - s2 -> sr + res = u1 - (U) s2 + ovf = u1 >= ((U) s2 ^ sgn) + u1 - s2 -> ur + t1 = u1 ^ sgn + t2 = t1 - (U) s2 + res = t2 ^ sgn + ovf = s2 < 0 ? (S) t2 < (S) t1 : (S) t2 > (S) t1 (or jump on overflow) + s1 + s2 -> ur + res = (U) s1 + (U) s2 + ovf = s2 < 0 ? (s1 | (S) res) < 0) : (s1 & (S) res) < 0) + u1 + u2 -> sr + res = (S) (u1 + u2) + ovf = (U) res < u2 || res < 0 + u1 - u2 -> sr + res = (S) (u1 - u2) + ovf = u1 >= u2 ? res < 0 : res >= 0 + s1 - s2 -> ur + res = (U) s1 - (U) s2 + ovf = s2 >= 0 ? ((s1 | (S) res) < 0) : ((s1 & (S) res) < 0) */ + + if (code == PLUS_EXPR && uns0_p && !uns1_p) + { + /* PLUS_EXPR is commutative, if operand signedness differs, + canonicalize to the first operand being signed and second + unsigned to simplify following code. */ + rtx tem = op1; + op1 = op0; + op0 = tem; + tree t = arg1; + arg1 = arg0; + arg0 = t; + uns0_p = 0; + uns1_p = 1; + } + + /* u1 +- u2 -> ur */ + if (uns0_p && uns1_p && unsr_p) + { + /* Compute the operation. On RTL level, the addition is always + unsigned. */ + res = expand_binop (mode, code == PLUS_EXPR ? add_optab : sub_optab, + op0, op1, NULL_RTX, false, OPTAB_LIB_WIDEN); + rtx tem = op0; + /* For PLUS_EXPR, the operation is commutative, so we can pick + operand to compare against. For prec <= BITS_PER_WORD, I think + preferring REG operand is better over CONST_INT, because + the CONST_INT might enlarge the instruction or CSE would need + to figure out we'd already loaded it into a register before. + For prec > BITS_PER_WORD, I think CONST_INT might be more beneficial, + as then the multi-word comparison can be perhaps simplified. */ + if (code == PLUS_EXPR + && (prec <= BITS_PER_WORD + ? (CONST_SCALAR_INT_P (op0) && REG_P (op1)) + : CONST_SCALAR_INT_P (op1))) + tem = op1; + emit_cmp_and_jump_insns (res, tem, code == PLUS_EXPR ? GEU : LEU, + NULL_RTX, mode, false, done_label, + PROB_VERY_LIKELY); + goto do_error_label; + } + + /* s1 +- u2 -> sr */ + if (!uns0_p && uns1_p && !unsr_p) + { + /* Compute the operation. On RTL level, the addition is always + unsigned. */ + res = expand_binop (mode, code == PLUS_EXPR ? add_optab : sub_optab, + op0, op1, NULL_RTX, false, OPTAB_LIB_WIDEN); + rtx tem = expand_binop (mode, add_optab, + code == PLUS_EXPR ? res : op0, sgn, + NULL_RTX, false, OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (tem, op1, GEU, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + goto do_error_label; + } + + /* s1 + u2 -> ur */ + if (code == PLUS_EXPR && !uns0_p && uns1_p && unsr_p) + { + op1 = expand_binop (mode, add_optab, op1, sgn, NULL_RTX, false, + OPTAB_LIB_WIDEN); + /* As we've changed op1, we have to avoid using the value range + for the original argument. */ + arg1 = error_mark_node; + do_xor = true; + goto do_signed; + } + + /* u1 - s2 -> ur */ + if (code == MINUS_EXPR && uns0_p && !uns1_p && unsr_p) + { + op0 = expand_binop (mode, add_optab, op0, sgn, NULL_RTX, false, + OPTAB_LIB_WIDEN); + /* As we've changed op0, we have to avoid using the value range + for the original argument. */ + arg0 = error_mark_node; + do_xor = true; + goto do_signed; + } + + /* s1 - u2 -> ur */ + if (code == MINUS_EXPR && !uns0_p && uns1_p && unsr_p) + { + /* Compute the operation. On RTL level, the addition is always + unsigned. */ + res = expand_binop (mode, sub_optab, op0, op1, NULL_RTX, false, + OPTAB_LIB_WIDEN); + int pos_neg = get_range_pos_neg (arg0); + if (pos_neg == 2) + /* If ARG0 is known to be always negative, this is always overflow. */ + emit_jump (do_error); + else if (pos_neg == 3) + /* If ARG0 is not known to be always positive, check at runtime. */ + emit_cmp_and_jump_insns (op0, const0_rtx, LT, NULL_RTX, mode, false, + do_error, PROB_VERY_UNLIKELY); + emit_cmp_and_jump_insns (op1, op0, LEU, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + goto do_error_label; + } + + /* u1 - s2 -> sr */ + if (code == MINUS_EXPR && uns0_p && !uns1_p && !unsr_p) + { + /* Compute the operation. On RTL level, the addition is always + unsigned. */ + res = expand_binop (mode, sub_optab, op0, op1, NULL_RTX, false, + OPTAB_LIB_WIDEN); + rtx tem = expand_binop (mode, add_optab, op1, sgn, NULL_RTX, false, + OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (op0, tem, LTU, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + goto do_error_label; + } + + /* u1 + u2 -> sr */ + if (code == PLUS_EXPR && uns0_p && uns1_p && !unsr_p) + { + /* Compute the operation. On RTL level, the addition is always + unsigned. */ + res = expand_binop (mode, add_optab, op0, op1, NULL_RTX, false, + OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (res, const0_rtx, LT, NULL_RTX, mode, false, + do_error, PROB_VERY_UNLIKELY); + rtx tem = op1; + /* The operation is commutative, so we can pick operand to compare + against. For prec <= BITS_PER_WORD, I think preferring REG operand + is better over CONST_INT, because the CONST_INT might enlarge the + instruction or CSE would need to figure out we'd already loaded it + into a register before. For prec > BITS_PER_WORD, I think CONST_INT + might be more beneficial, as then the multi-word comparison can be + perhaps simplified. */ + if (prec <= BITS_PER_WORD + ? (CONST_SCALAR_INT_P (op1) && REG_P (op0)) + : CONST_SCALAR_INT_P (op0)) + tem = op0; + emit_cmp_and_jump_insns (res, tem, GEU, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + goto do_error_label; + } + + /* s1 +- s2 -> ur */ + if (!uns0_p && !uns1_p && unsr_p) + { + /* Compute the operation. On RTL level, the addition is always + unsigned. */ + res = expand_binop (mode, code == PLUS_EXPR ? add_optab : sub_optab, + op0, op1, NULL_RTX, false, OPTAB_LIB_WIDEN); + int pos_neg = get_range_pos_neg (arg1); + if (code == PLUS_EXPR) + { + int pos_neg0 = get_range_pos_neg (arg0); + if (pos_neg0 != 3 && pos_neg == 3) + { + rtx tem = op1; + op1 = op0; + op0 = tem; + pos_neg = pos_neg0; + } + } + rtx tem; + if (pos_neg != 3) + { + tem = expand_binop (mode, ((pos_neg == 1) ^ (code == MINUS_EXPR)) + ? and_optab : ior_optab, + op0, res, NULL_RTX, false, OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (tem, const0_rtx, GE, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + } + else + { + rtx_code_label *do_ior_label = gen_label_rtx (); + emit_cmp_and_jump_insns (op1, const0_rtx, + code == MINUS_EXPR ? GE : LT, NULL_RTX, + mode, false, do_ior_label, PROB_EVEN); + tem = expand_binop (mode, and_optab, op0, res, NULL_RTX, false, + OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (tem, const0_rtx, GE, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + emit_jump (do_error); + emit_label (do_ior_label); + tem = expand_binop (mode, ior_optab, op0, res, NULL_RTX, false, + OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (tem, const0_rtx, GE, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + } + goto do_error_label; + } + + /* u1 - u2 -> sr */ + if (code == MINUS_EXPR && uns0_p && uns1_p && !unsr_p) + { + /* Compute the operation. On RTL level, the addition is always + unsigned. */ + res = expand_binop (mode, sub_optab, op0, op1, NULL_RTX, false, + OPTAB_LIB_WIDEN); + rtx_code_label *op0_geu_op1 = gen_label_rtx (); + emit_cmp_and_jump_insns (op0, op1, GEU, NULL_RTX, mode, false, + op0_geu_op1, PROB_EVEN); + emit_cmp_and_jump_insns (res, const0_rtx, LT, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + emit_jump (do_error); + emit_label (op0_geu_op1); + emit_cmp_and_jump_insns (res, const0_rtx, GE, NULL_RTX, mode, false, + done_label, PROB_VERY_LIKELY); + goto do_error_label; + } - enum insn_code icode - = optab_handler (code == PLUS_EXPR ? addv4_optab : subv4_optab, mode); + gcc_assert (!uns0_p && !uns1_p && !unsr_p); + + /* s1 +- s2 -> sr */ + do_signed: ; + enum insn_code icode; + icode = optab_handler (code == PLUS_EXPR ? addv4_optab : subv4_optab, mode); if (icode != CODE_FOR_nothing) { struct expand_operand ops[4]; @@ -289,14 +751,7 @@ ubsan_expand_si_overflow_addsub_check (tree_code code, gimple stmt) ; else if (code == PLUS_EXPR && TREE_CODE (arg0) == SSA_NAME) { - wide_int arg0_min, arg0_max; - if (get_range_info (arg0, &arg0_min, &arg0_max) == VR_RANGE) - { - if (!wi::neg_p (arg0_min, TYPE_SIGN (TREE_TYPE (arg0)))) - pos_neg = 1; - else if (wi::neg_p (arg0_max, TYPE_SIGN (TREE_TYPE (arg0)))) - pos_neg = 2; - } + pos_neg = get_range_pos_neg (arg0); if (pos_neg != 3) { rtx tem = op0; @@ -305,16 +760,7 @@ ubsan_expand_si_overflow_addsub_check (tree_code code, gimple stmt) } } if (pos_neg == 3 && !CONST_INT_P (op1) && TREE_CODE (arg1) == SSA_NAME) - { - wide_int arg1_min, arg1_max; - if (get_range_info (arg1, &arg1_min, &arg1_max) == VR_RANGE) - { - if (!wi::neg_p (arg1_min, TYPE_SIGN (TREE_TYPE (arg1)))) - pos_neg = 1; - else if (wi::neg_p (arg1_max, TYPE_SIGN (TREE_TYPE (arg1)))) - pos_neg = 2; - } - } + pos_neg = get_range_pos_neg (arg1); /* If the op1 is negative, we have to use a different check. */ if (pos_neg == 3) @@ -342,34 +788,49 @@ ubsan_expand_si_overflow_addsub_check (tree_code code, gimple stmt) PROB_VERY_LIKELY); } + do_error_label: emit_label (do_error); - /* Expand the ubsan builtin call. */ - push_temp_slots (); - fn = ubsan_build_overflow_builtin (code, gimple_location (stmt), - TREE_TYPE (arg0), arg0, arg1); - expand_normal (fn); - pop_temp_slots (); - do_pending_stack_adjust (); + if (is_ubsan) + { + /* Expand the ubsan builtin call. */ + push_temp_slots (); + fn = ubsan_build_overflow_builtin (code, loc, TREE_TYPE (arg0), + arg0, arg1); + expand_normal (fn); + pop_temp_slots (); + do_pending_stack_adjust (); + } + else if (lhs) + write_complex_part (target, const1_rtx, true); /* We're done. */ emit_label (done_label); if (lhs) - emit_move_insn (target, res); + { + if (is_ubsan) + emit_move_insn (target, res); + else + { + if (do_xor) + res = expand_binop (mode, add_optab, res, sgn, NULL_RTX, false, + OPTAB_LIB_WIDEN); + + expand_arith_overflow_result_store (lhs, target, mode, res); + } + } } /* Add negate overflow checking to the statement STMT. */ -void -ubsan_expand_si_overflow_neg_check (gimple stmt) +static void +expand_neg_overflow (location_t loc, tree lhs, tree arg1, bool is_ubsan) { rtx res, op1; - tree lhs, fn, arg1; + tree fn; rtx_code_label *done_label, *do_error; rtx target = NULL_RTX; - lhs = gimple_call_lhs (stmt); - arg1 = gimple_call_arg (stmt, 1); done_label = gen_label_rtx (); do_error = gen_label_rtx (); @@ -378,7 +839,11 @@ ubsan_expand_si_overflow_neg_check (gimple stmt) machine_mode mode = TYPE_MODE (TREE_TYPE (arg1)); if (lhs) - target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + { + target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + if (!is_ubsan) + write_complex_part (target, const0_rtx, true); + } enum insn_code icode = optab_handler (negv3_optab, mode); if (icode != CODE_FOR_nothing) @@ -420,34 +885,44 @@ ubsan_expand_si_overflow_neg_check (gimple stmt) } emit_label (do_error); - /* Expand the ubsan builtin call. */ - push_temp_slots (); - fn = ubsan_build_overflow_builtin (NEGATE_EXPR, gimple_location (stmt), - TREE_TYPE (arg1), arg1, NULL_TREE); - expand_normal (fn); - pop_temp_slots (); - do_pending_stack_adjust (); + if (is_ubsan) + { + /* Expand the ubsan builtin call. */ + push_temp_slots (); + fn = ubsan_build_overflow_builtin (NEGATE_EXPR, loc, TREE_TYPE (arg1), + arg1, NULL_TREE); + expand_normal (fn); + pop_temp_slots (); + do_pending_stack_adjust (); + } + else if (lhs) + write_complex_part (target, const1_rtx, true); /* We're done. */ emit_label (done_label); if (lhs) - emit_move_insn (target, res); + { + if (is_ubsan) + emit_move_insn (target, res); + else + expand_arith_overflow_result_store (lhs, target, mode, res); + } } /* Add mul overflow checking to the statement STMT. */ -void -ubsan_expand_si_overflow_mul_check (gimple stmt) +static void +expand_mul_overflow (location_t loc, tree lhs, tree arg0, tree arg1, + bool unsr_p, bool uns0_p, bool uns1_p, bool is_ubsan) { rtx res, op0, op1; - tree lhs, fn, arg0, arg1; + tree fn, type; rtx_code_label *done_label, *do_error; rtx target = NULL_RTX; + signop sign; + enum insn_code icode; - lhs = gimple_call_lhs (stmt); - arg0 = gimple_call_arg (stmt, 0); - arg1 = gimple_call_arg (stmt, 1); done_label = gen_label_rtx (); do_error = gen_label_rtx (); @@ -456,10 +931,243 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) op1 = expand_normal (arg1); machine_mode mode = TYPE_MODE (TREE_TYPE (arg0)); + bool uns = unsr_p; if (lhs) - target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + { + target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + if (!is_ubsan) + write_complex_part (target, const0_rtx, true); + } + + if (is_ubsan) + gcc_assert (!unsr_p && !uns0_p && !uns1_p); + + /* We assume both operands and result have the same precision + here (GET_MODE_BITSIZE (mode)), S stands for signed type + with that precision, U for unsigned type with that precision, + sgn for unsigned most significant bit in that precision. + s1 is signed first operand, u1 is unsigned first operand, + s2 is signed second operand, u2 is unsigned second operand, + sr is signed result, ur is unsigned result and the following + rules say how to compute result (which is always result of + the operands as if both were unsigned, cast to the right + signedness) and how to compute whether operation overflowed. + main_ovf (false) stands for jump on signed multiplication + overflow or the main algorithm with uns == false. + main_ovf (true) stands for jump on unsigned multiplication + overflow or the main algorithm with uns == true. + + s1 * s2 -> sr + res = (S) ((U) s1 * (U) s2) + ovf = main_ovf (false) + u1 * u2 -> ur + res = u1 * u2 + ovf = main_ovf (true) + s1 * u2 -> ur + res = (U) s1 * u2 + ovf = (s1 < 0 && u2) || main_ovf (true) + u1 * u2 -> sr + res = (S) (u1 * u2) + ovf = res < 0 || main_ovf (true) + s1 * u2 -> sr + res = (S) ((U) s1 * u2) + ovf = (S) u2 >= 0 ? main_ovf (false) + : (s1 != 0 && (s1 != -1 || u2 != (U) res)) + s1 * s2 -> ur + t1 = (s1 & s2) < 0 ? (-(U) s1) : ((U) s1) + t2 = (s1 & s2) < 0 ? (-(U) s2) : ((U) s2) + res = t1 * t2 + ovf = (s1 ^ s2) < 0 ? (s1 && s2) : main_ovf (true) */ + + if (uns0_p && !uns1_p) + { + /* Multiplication is commutative, if operand signedness differs, + canonicalize to the first operand being signed and second + unsigned to simplify following code. */ + rtx tem = op1; + op1 = op0; + op0 = tem; + tree t = arg1; + arg1 = arg0; + arg0 = t; + uns0_p = 0; + uns1_p = 1; + } + + int pos_neg0 = get_range_pos_neg (arg0); + int pos_neg1 = get_range_pos_neg (arg1); + + /* s1 * u2 -> ur */ + if (!uns0_p && uns1_p && unsr_p) + { + switch (pos_neg0) + { + case 1: + /* If s1 is non-negative, just perform normal u1 * u2 -> ur. */ + goto do_main; + case 2: + /* If s1 is negative, avoid the main code, just multiply and + signal overflow if op1 is not 0. */ + struct separate_ops ops; + ops.code = MULT_EXPR; + ops.type = TREE_TYPE (arg1); + ops.op0 = make_tree (ops.type, op0); + ops.op1 = make_tree (ops.type, op1); + ops.op2 = NULL_TREE; + ops.location = loc; + res = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); + emit_cmp_and_jump_insns (op1, const0_rtx, EQ, NULL_RTX, mode, + false, done_label, PROB_VERY_LIKELY); + goto do_error_label; + case 3: + rtx_code_label *do_main_label; + do_main_label = gen_label_rtx (); + emit_cmp_and_jump_insns (op0, const0_rtx, GE, NULL_RTX, mode, + false, do_main_label, PROB_VERY_LIKELY); + emit_cmp_and_jump_insns (op1, const0_rtx, EQ, NULL_RTX, mode, + false, do_main_label, PROB_VERY_LIKELY); + write_complex_part (target, const1_rtx, true); + emit_label (do_main_label); + goto do_main; + default: + gcc_unreachable (); + } + } + + /* u1 * u2 -> sr */ + if (uns0_p && uns1_p && !unsr_p) + { + uns = true; + /* Rest of handling of this case after res is computed. */ + goto do_main; + } + + /* s1 * u2 -> sr */ + if (!uns0_p && uns1_p && !unsr_p) + { + switch (pos_neg1) + { + case 1: + goto do_main; + case 2: + /* If (S) u2 is negative (i.e. u2 is larger than maximum of S, + avoid the main code, just multiply and signal overflow + unless 0 * u2 or -1 * ((U) Smin). */ + struct separate_ops ops; + ops.code = MULT_EXPR; + ops.type = TREE_TYPE (arg1); + ops.op0 = make_tree (ops.type, op0); + ops.op1 = make_tree (ops.type, op1); + ops.op2 = NULL_TREE; + ops.location = loc; + res = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); + emit_cmp_and_jump_insns (op0, const0_rtx, EQ, NULL_RTX, mode, + false, done_label, PROB_VERY_LIKELY); + emit_cmp_and_jump_insns (op0, constm1_rtx, NE, NULL_RTX, mode, + false, do_error, PROB_VERY_UNLIKELY); + int prec; + prec = GET_MODE_PRECISION (mode); + rtx sgn; + sgn = immed_wide_int_const (wi::min_value (prec, SIGNED), mode); + emit_cmp_and_jump_insns (op1, sgn, EQ, NULL_RTX, mode, + false, done_label, PROB_VERY_LIKELY); + goto do_error_label; + case 3: + /* Rest of handling of this case after res is computed. */ + goto do_main; + default: + gcc_unreachable (); + } + } + + /* s1 * s2 -> ur */ + if (!uns0_p && !uns1_p && unsr_p) + { + rtx tem, tem2; + switch (pos_neg0 | pos_neg1) + { + case 1: /* Both operands known to be non-negative. */ + goto do_main; + case 2: /* Both operands known to be negative. */ + op0 = expand_unop (mode, neg_optab, op0, NULL_RTX, false); + op1 = expand_unop (mode, neg_optab, op1, NULL_RTX, false); + /* Avoid looking at arg0/arg1 ranges, as we've changed + the arguments. */ + arg0 = error_mark_node; + arg1 = error_mark_node; + goto do_main; + case 3: + if ((pos_neg0 ^ pos_neg1) == 3) + { + /* If one operand is known to be negative and the other + non-negative, this overflows always, unless the non-negative + one is 0. Just do normal multiply and set overflow + unless one of the operands is 0. */ + struct separate_ops ops; + ops.code = MULT_EXPR; + ops.type + = build_nonstandard_integer_type (GET_MODE_PRECISION (mode), + 1); + ops.op0 = make_tree (ops.type, op0); + ops.op1 = make_tree (ops.type, op1); + ops.op2 = NULL_TREE; + ops.location = loc; + res = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); + tem = expand_binop (mode, and_optab, op0, op1, NULL_RTX, false, + OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (tem, const0_rtx, EQ, NULL_RTX, mode, + false, done_label, PROB_VERY_LIKELY); + goto do_error_label; + } + /* The general case, do all the needed comparisons at runtime. */ + rtx_code_label *do_main_label, *after_negate_label; + rtx rop0, rop1; + rop0 = gen_reg_rtx (mode); + rop1 = gen_reg_rtx (mode); + emit_move_insn (rop0, op0); + emit_move_insn (rop1, op1); + op0 = rop0; + op1 = rop1; + do_main_label = gen_label_rtx (); + after_negate_label = gen_label_rtx (); + tem = expand_binop (mode, and_optab, op0, op1, NULL_RTX, false, + OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (tem, const0_rtx, GE, NULL_RTX, mode, false, + after_negate_label, PROB_VERY_LIKELY); + /* Both arguments negative here, negate them and continue with + normal unsigned overflow checking multiplication. */ + emit_move_insn (op0, expand_unop (mode, neg_optab, op0, + NULL_RTX, false)); + emit_move_insn (op1, expand_unop (mode, neg_optab, op1, + NULL_RTX, false)); + /* Avoid looking at arg0/arg1 ranges, as we might have changed + the arguments. */ + arg0 = error_mark_node; + arg1 = error_mark_node; + emit_jump (do_main_label); + emit_label (after_negate_label); + tem2 = expand_binop (mode, xor_optab, op0, op1, NULL_RTX, false, + OPTAB_LIB_WIDEN); + emit_cmp_and_jump_insns (tem2, const0_rtx, GE, NULL_RTX, mode, false, + do_main_label, PROB_VERY_LIKELY); + /* One argument is negative here, the other positive. This + overflows always, unless one of the arguments is 0. But + if e.g. s2 is 0, (U) s1 * 0 doesn't overflow, whatever s1 + is, thus we can keep do_main code oring in overflow as is. */ + emit_cmp_and_jump_insns (tem, const0_rtx, EQ, NULL_RTX, mode, false, + do_main_label, PROB_VERY_LIKELY); + write_complex_part (target, const1_rtx, true); + emit_label (do_main_label); + goto do_main; + default: + gcc_unreachable (); + } + } - enum insn_code icode = optab_handler (mulv4_optab, mode); + do_main: + type = build_nonstandard_integer_type (GET_MODE_PRECISION (mode), uns); + sign = uns ? UNSIGNED : SIGNED; + icode = optab_handler (uns ? umulv4_optab : mulv4_optab, mode); if (icode != CODE_FOR_nothing) { struct expand_operand ops[4]; @@ -490,59 +1198,69 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) if (icode == CODE_FOR_nothing) { struct separate_ops ops; - machine_mode hmode - = mode_for_size (GET_MODE_PRECISION (mode) / 2, MODE_INT, 1); - ops.op0 = arg0; - ops.op1 = arg1; + int prec = GET_MODE_PRECISION (mode); + machine_mode hmode = mode_for_size (prec / 2, MODE_INT, 1); + ops.op0 = make_tree (type, op0); + ops.op1 = make_tree (type, op1); ops.op2 = NULL_TREE; - ops.location = gimple_location (stmt); + ops.location = loc; if (GET_MODE_2XWIDER_MODE (mode) != VOIDmode && targetm.scalar_mode_supported_p (GET_MODE_2XWIDER_MODE (mode))) { machine_mode wmode = GET_MODE_2XWIDER_MODE (mode); ops.code = WIDEN_MULT_EXPR; ops.type - = build_nonstandard_integer_type (GET_MODE_PRECISION (wmode), 0); + = build_nonstandard_integer_type (GET_MODE_PRECISION (wmode), uns); res = expand_expr_real_2 (&ops, NULL_RTX, wmode, EXPAND_NORMAL); - rtx hipart = expand_shift (RSHIFT_EXPR, wmode, res, - GET_MODE_PRECISION (mode), NULL_RTX, 0); + rtx hipart = expand_shift (RSHIFT_EXPR, wmode, res, prec, + NULL_RTX, uns); hipart = gen_lowpart (mode, hipart); res = gen_lowpart (mode, res); - rtx signbit = expand_shift (RSHIFT_EXPR, mode, res, - GET_MODE_PRECISION (mode) - 1, - NULL_RTX, 0); - /* RES is low half of the double width result, HIPART - the high half. There was overflow if - HIPART is different from RES < 0 ? -1 : 0. */ - emit_cmp_and_jump_insns (signbit, hipart, EQ, NULL_RTX, mode, - false, done_label, PROB_VERY_LIKELY); + if (uns) + /* For the unsigned multiplication, there was overflow if + HIPART is non-zero. */ + emit_cmp_and_jump_insns (hipart, const0_rtx, EQ, NULL_RTX, mode, + false, done_label, PROB_VERY_LIKELY); + else + { + rtx signbit = expand_shift (RSHIFT_EXPR, mode, res, prec - 1, + NULL_RTX, 0); + /* RES is low half of the double width result, HIPART + the high half. There was overflow if + HIPART is different from RES < 0 ? -1 : 0. */ + emit_cmp_and_jump_insns (signbit, hipart, EQ, NULL_RTX, mode, + false, done_label, PROB_VERY_LIKELY); + } } - else if (hmode != BLKmode - && 2 * GET_MODE_PRECISION (hmode) == GET_MODE_PRECISION (mode)) + else if (hmode != BLKmode && 2 * GET_MODE_PRECISION (hmode) == prec) { rtx_code_label *large_op0 = gen_label_rtx (); rtx_code_label *small_op0_large_op1 = gen_label_rtx (); rtx_code_label *one_small_one_large = gen_label_rtx (); rtx_code_label *both_ops_large = gen_label_rtx (); - rtx_code_label *after_hipart_neg = gen_label_rtx (); - rtx_code_label *after_lopart_neg = gen_label_rtx (); + rtx_code_label *after_hipart_neg = uns ? NULL : gen_label_rtx (); + rtx_code_label *after_lopart_neg = uns ? NULL : gen_label_rtx (); rtx_code_label *do_overflow = gen_label_rtx (); - rtx_code_label *hipart_different = gen_label_rtx (); + rtx_code_label *hipart_different = uns ? NULL : gen_label_rtx (); unsigned int hprec = GET_MODE_PRECISION (hmode); rtx hipart0 = expand_shift (RSHIFT_EXPR, mode, op0, hprec, - NULL_RTX, 0); + NULL_RTX, uns); hipart0 = gen_lowpart (hmode, hipart0); rtx lopart0 = gen_lowpart (hmode, op0); - rtx signbit0 = expand_shift (RSHIFT_EXPR, hmode, lopart0, hprec - 1, - NULL_RTX, 0); + rtx signbit0 = const0_rtx; + if (!uns) + signbit0 = expand_shift (RSHIFT_EXPR, hmode, lopart0, hprec - 1, + NULL_RTX, 0); rtx hipart1 = expand_shift (RSHIFT_EXPR, mode, op1, hprec, - NULL_RTX, 0); + NULL_RTX, uns); hipart1 = gen_lowpart (hmode, hipart1); rtx lopart1 = gen_lowpart (hmode, op1); - rtx signbit1 = expand_shift (RSHIFT_EXPR, hmode, lopart1, hprec - 1, - NULL_RTX, 0); + rtx signbit1 = const0_rtx; + if (!uns) + signbit1 = expand_shift (RSHIFT_EXPR, hmode, lopart1, hprec - 1, + NULL_RTX, 0); res = gen_reg_rtx (mode); @@ -560,40 +1278,29 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) int op0_sign = 1; int op1_sign = 1; - if (TREE_CODE (arg0) == SSA_NAME) - { - wide_int arg0_min, arg0_max; - if (get_range_info (arg0, &arg0_min, &arg0_max) == VR_RANGE) - { - unsigned int mprec0 = wi::min_precision (arg0_min, SIGNED); - unsigned int mprec1 = wi::min_precision (arg0_max, SIGNED); - if (mprec0 <= hprec && mprec1 <= hprec) - op0_small_p = true; - else if (mprec0 <= hprec + 1 && mprec1 <= hprec + 1) - op0_medium_p = true; - if (!wi::neg_p (arg0_min, TYPE_SIGN (TREE_TYPE (arg0)))) - op0_sign = 0; - else if (wi::neg_p (arg0_max, TYPE_SIGN (TREE_TYPE (arg0)))) - op0_sign = -1; - } - } - if (TREE_CODE (arg1) == SSA_NAME) - { - wide_int arg1_min, arg1_max; - if (get_range_info (arg1, &arg1_min, &arg1_max) == VR_RANGE) - { - unsigned int mprec0 = wi::min_precision (arg1_min, SIGNED); - unsigned int mprec1 = wi::min_precision (arg1_max, SIGNED); - if (mprec0 <= hprec && mprec1 <= hprec) - op1_small_p = true; - else if (mprec0 <= hprec + 1 && mprec1 <= hprec + 1) - op1_medium_p = true; - if (!wi::neg_p (arg1_min, TYPE_SIGN (TREE_TYPE (arg1)))) - op1_sign = 0; - else if (wi::neg_p (arg1_max, TYPE_SIGN (TREE_TYPE (arg1)))) - op1_sign = -1; - } - } + if (pos_neg0 == 1) + op0_sign = 0; + else if (pos_neg0 == 2) + op0_sign = -1; + if (pos_neg1 == 1) + op1_sign = 0; + else if (pos_neg1 == 2) + op1_sign = -1; + + unsigned int mprec0 = prec; + if (arg0 != error_mark_node) + mprec0 = get_min_precision (arg0, sign); + if (mprec0 <= hprec) + op0_small_p = true; + else if (!uns && mprec0 <= hprec + 1) + op0_medium_p = true; + unsigned int mprec1 = prec; + if (arg1 != error_mark_node) + mprec1 = get_min_precision (arg1, sign); + if (mprec1 <= hprec) + op1_small_p = true; + else if (!uns && mprec1 <= hprec + 1) + op1_medium_p = true; int smaller_sign = 1; int larger_sign = 1; @@ -622,24 +1329,27 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) false, small_op0_large_op1, PROB_UNLIKELY); - /* If both op0 and op1 are sign extended from hmode to mode, - the multiplication will never overflow. We can do just one - hmode x hmode => mode widening multiplication. */ + /* If both op0 and op1 are sign (!uns) or zero (uns) extended from + hmode to mode, the multiplication will never overflow. We can + do just one hmode x hmode => mode widening multiplication. */ + rtx lopart0s = lopart0, lopart1s = lopart1; if (GET_CODE (lopart0) == SUBREG) { - SUBREG_PROMOTED_VAR_P (lopart0) = 1; - SUBREG_PROMOTED_SET (lopart0, 0); + lopart0s = shallow_copy_rtx (lopart0); + SUBREG_PROMOTED_VAR_P (lopart0s) = 1; + SUBREG_PROMOTED_SET (lopart0s, uns ? SRP_UNSIGNED : SRP_SIGNED); } if (GET_CODE (lopart1) == SUBREG) { - SUBREG_PROMOTED_VAR_P (lopart1) = 1; - SUBREG_PROMOTED_SET (lopart1, 0); + lopart1s = shallow_copy_rtx (lopart1); + SUBREG_PROMOTED_VAR_P (lopart1s) = 1; + SUBREG_PROMOTED_SET (lopart1s, uns ? SRP_UNSIGNED : SRP_SIGNED); } - tree halfstype = build_nonstandard_integer_type (hprec, 0); - ops.op0 = make_tree (halfstype, lopart0); - ops.op1 = make_tree (halfstype, lopart1); + tree halfstype = build_nonstandard_integer_type (hprec, uns); + ops.op0 = make_tree (halfstype, lopart0s); + ops.op1 = make_tree (halfstype, lopart1s); ops.code = WIDEN_MULT_EXPR; - ops.type = TREE_TYPE (arg0); + ops.type = type; rtx thisres = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); emit_move_insn (res, thisres); @@ -647,9 +1357,9 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) emit_label (small_op0_large_op1); - /* If op0 is sign extended from hmode to mode, but op1 is not, - just swap the arguments and handle it as op1 sign extended, - op0 not. */ + /* If op0 is sign (!uns) or zero (uns) extended from hmode to mode, + but op1 is not, just swap the arguments and handle it as op1 + sign/zero extended, op0 not. */ rtx larger = gen_reg_rtx (mode); rtx hipart = gen_reg_rtx (hmode); rtx lopart = gen_reg_rtx (hmode); @@ -664,9 +1374,9 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) emit_cmp_and_jump_insns (signbit1, hipart1, NE, NULL_RTX, hmode, false, both_ops_large, PROB_UNLIKELY); - /* If op1 is sign extended from hmode to mode, but op0 is not, - prepare larger, hipart and lopart pseudos and handle it together - with small_op0_large_op1. */ + /* If op1 is sign (!uns) or zero (uns) extended from hmode to mode, + but op0 is not, prepare larger, hipart and lopart pseudos and + handle it together with small_op0_large_op1. */ emit_move_insn (larger, op0); emit_move_insn (hipart, hipart0); emit_move_insn (lopart, lopart1); @@ -691,33 +1401,38 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) rtx tem = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); emit_move_insn (loxhi, tem); - /* if (hipart < 0) loxhi -= lopart << (bitsize / 2); */ - if (larger_sign == 0) - emit_jump (after_hipart_neg); - else if (larger_sign != -1) - emit_cmp_and_jump_insns (hipart, const0_rtx, GE, NULL_RTX, hmode, - false, after_hipart_neg, PROB_EVEN); - - tem = convert_modes (mode, hmode, lopart, 1); - tem = expand_shift (LSHIFT_EXPR, mode, tem, hprec, NULL_RTX, 1); - tem = expand_simple_binop (mode, MINUS, loxhi, tem, NULL_RTX, - 1, OPTAB_DIRECT); - emit_move_insn (loxhi, tem); - - emit_label (after_hipart_neg); - - /* if (lopart < 0) loxhi -= larger; */ - if (smaller_sign == 0) - emit_jump (after_lopart_neg); - else if (smaller_sign != -1) - emit_cmp_and_jump_insns (lopart, const0_rtx, GE, NULL_RTX, hmode, - false, after_lopart_neg, PROB_EVEN); - - tem = expand_simple_binop (mode, MINUS, loxhi, larger, NULL_RTX, - 1, OPTAB_DIRECT); - emit_move_insn (loxhi, tem); - - emit_label (after_lopart_neg); + if (!uns) + { + /* if (hipart < 0) loxhi -= lopart << (bitsize / 2); */ + if (larger_sign == 0) + emit_jump (after_hipart_neg); + else if (larger_sign != -1) + emit_cmp_and_jump_insns (hipart, const0_rtx, GE, NULL_RTX, + hmode, false, after_hipart_neg, + PROB_EVEN); + + tem = convert_modes (mode, hmode, lopart, 1); + tem = expand_shift (LSHIFT_EXPR, mode, tem, hprec, NULL_RTX, 1); + tem = expand_simple_binop (mode, MINUS, loxhi, tem, NULL_RTX, + 1, OPTAB_DIRECT); + emit_move_insn (loxhi, tem); + + emit_label (after_hipart_neg); + + /* if (lopart < 0) loxhi -= larger; */ + if (smaller_sign == 0) + emit_jump (after_lopart_neg); + else if (smaller_sign != -1) + emit_cmp_and_jump_insns (lopart, const0_rtx, GE, NULL_RTX, + hmode, false, after_lopart_neg, + PROB_EVEN); + + tem = expand_simple_binop (mode, MINUS, loxhi, larger, NULL_RTX, + 1, OPTAB_DIRECT); + emit_move_insn (loxhi, tem); + + emit_label (after_lopart_neg); + } /* loxhi += (uns) lo0xlo1 >> (bitsize / 2); */ tem = expand_shift (RSHIFT_EXPR, mode, lo0xlo1, hprec, NULL_RTX, 1); @@ -726,13 +1441,16 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) emit_move_insn (loxhi, tem); /* if (loxhi >> (bitsize / 2) - == (hmode) loxhi >> (bitsize / 2 - 1)) */ + == (hmode) loxhi >> (bitsize / 2 - 1)) (if !uns) + if (loxhi >> (bitsize / 2) == 0 (if uns). */ rtx hipartloxhi = expand_shift (RSHIFT_EXPR, mode, loxhi, hprec, NULL_RTX, 0); hipartloxhi = gen_lowpart (hmode, hipartloxhi); - rtx lopartloxhi = gen_lowpart (hmode, loxhi); - rtx signbitloxhi = expand_shift (RSHIFT_EXPR, hmode, lopartloxhi, - hprec - 1, NULL_RTX, 0); + rtx signbitloxhi = const0_rtx; + if (!uns) + signbitloxhi = expand_shift (RSHIFT_EXPR, hmode, + gen_lowpart (hmode, loxhi), + hprec - 1, NULL_RTX, 0); emit_cmp_and_jump_insns (signbitloxhi, hipartloxhi, NE, NULL_RTX, hmode, false, do_overflow, @@ -751,82 +1469,131 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) emit_label (both_ops_large); - /* If both operands are large (not sign extended from hmode), - then perform the full multiplication which will be the result - of the operation. The only cases which don't overflow are - some cases where both hipart0 and highpart1 are 0 or -1. */ + /* If both operands are large (not sign (!uns) or zero (uns) + extended from hmode), then perform the full multiplication + which will be the result of the operation. + The only cases which don't overflow are for signed multiplication + some cases where both hipart0 and highpart1 are 0 or -1. + For unsigned multiplication when high parts are both non-zero + this overflows always. */ ops.code = MULT_EXPR; - ops.op0 = make_tree (TREE_TYPE (arg0), op0); - ops.op1 = make_tree (TREE_TYPE (arg0), op1); + ops.op0 = make_tree (type, op0); + ops.op1 = make_tree (type, op1); tem = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); emit_move_insn (res, tem); - if (!op0_medium_p) + if (!uns) { - tem = expand_simple_binop (hmode, PLUS, hipart0, const1_rtx, - NULL_RTX, 1, OPTAB_DIRECT); - emit_cmp_and_jump_insns (tem, const1_rtx, GTU, NULL_RTX, hmode, - true, do_error, PROB_VERY_UNLIKELY); - } + if (!op0_medium_p) + { + tem = expand_simple_binop (hmode, PLUS, hipart0, const1_rtx, + NULL_RTX, 1, OPTAB_DIRECT); + emit_cmp_and_jump_insns (tem, const1_rtx, GTU, NULL_RTX, + hmode, true, do_error, + PROB_VERY_UNLIKELY); + } - if (!op1_medium_p) - { - tem = expand_simple_binop (hmode, PLUS, hipart1, const1_rtx, - NULL_RTX, 1, OPTAB_DIRECT); - emit_cmp_and_jump_insns (tem, const1_rtx, GTU, NULL_RTX, hmode, - true, do_error, PROB_VERY_UNLIKELY); - } + if (!op1_medium_p) + { + tem = expand_simple_binop (hmode, PLUS, hipart1, const1_rtx, + NULL_RTX, 1, OPTAB_DIRECT); + emit_cmp_and_jump_insns (tem, const1_rtx, GTU, NULL_RTX, + hmode, true, do_error, + PROB_VERY_UNLIKELY); + } - /* At this point hipart{0,1} are both in [-1, 0]. If they are the - same, overflow happened if res is negative, if they are different, - overflow happened if res is positive. */ - if (op0_sign != 1 && op1_sign != 1 && op0_sign != op1_sign) - emit_jump (hipart_different); - else if (op0_sign == 1 || op1_sign == 1) - emit_cmp_and_jump_insns (hipart0, hipart1, NE, NULL_RTX, hmode, - true, hipart_different, PROB_EVEN); - - emit_cmp_and_jump_insns (res, const0_rtx, LT, NULL_RTX, mode, false, - do_error, PROB_VERY_UNLIKELY); - emit_jump (done_label); + /* At this point hipart{0,1} are both in [-1, 0]. If they are + the same, overflow happened if res is negative, if they are + different, overflow happened if res is positive. */ + if (op0_sign != 1 && op1_sign != 1 && op0_sign != op1_sign) + emit_jump (hipart_different); + else if (op0_sign == 1 || op1_sign == 1) + emit_cmp_and_jump_insns (hipart0, hipart1, NE, NULL_RTX, hmode, + true, hipart_different, PROB_EVEN); - emit_label (hipart_different); + emit_cmp_and_jump_insns (res, const0_rtx, LT, NULL_RTX, mode, + false, do_error, PROB_VERY_UNLIKELY); + emit_jump (done_label); - emit_cmp_and_jump_insns (res, const0_rtx, GE, NULL_RTX, mode, false, - do_error, PROB_VERY_UNLIKELY); - emit_jump (done_label); + emit_label (hipart_different); + + emit_cmp_and_jump_insns (res, const0_rtx, GE, NULL_RTX, mode, + false, do_error, PROB_VERY_UNLIKELY); + emit_jump (done_label); + } emit_label (do_overflow); /* Overflow, do full multiplication and fallthru into do_error. */ - ops.op0 = make_tree (TREE_TYPE (arg0), op0); - ops.op1 = make_tree (TREE_TYPE (arg0), op1); + ops.op0 = make_tree (type, op0); + ops.op1 = make_tree (type, op1); tem = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); emit_move_insn (res, tem); } else { + gcc_assert (!is_ubsan); ops.code = MULT_EXPR; - ops.type = TREE_TYPE (arg0); + ops.type = type; res = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); emit_jump (done_label); } } + do_error_label: emit_label (do_error); - /* Expand the ubsan builtin call. */ - push_temp_slots (); - fn = ubsan_build_overflow_builtin (MULT_EXPR, gimple_location (stmt), - TREE_TYPE (arg0), arg0, arg1); - expand_normal (fn); - pop_temp_slots (); - do_pending_stack_adjust (); + if (is_ubsan) + { + /* Expand the ubsan builtin call. */ + push_temp_slots (); + fn = ubsan_build_overflow_builtin (MULT_EXPR, loc, TREE_TYPE (arg0), + arg0, arg1); + expand_normal (fn); + pop_temp_slots (); + do_pending_stack_adjust (); + } + else if (lhs) + write_complex_part (target, const1_rtx, true); /* We're done. */ emit_label (done_label); + /* u1 * u2 -> sr */ + if (uns0_p && uns1_p && !unsr_p) + { + rtx_code_label *all_done_label = gen_label_rtx (); + emit_cmp_and_jump_insns (res, const0_rtx, GE, NULL_RTX, mode, + false, all_done_label, PROB_VERY_LIKELY); + write_complex_part (target, const1_rtx, true); + emit_label (all_done_label); + } + + /* s1 * u2 -> sr */ + if (!uns0_p && uns1_p && !unsr_p && pos_neg1 == 3) + { + rtx_code_label *all_done_label = gen_label_rtx (); + rtx_code_label *set_noovf = gen_label_rtx (); + emit_cmp_and_jump_insns (op1, const0_rtx, GE, NULL_RTX, mode, + false, all_done_label, PROB_VERY_LIKELY); + write_complex_part (target, const1_rtx, true); + emit_cmp_and_jump_insns (op0, const0_rtx, EQ, NULL_RTX, mode, + false, set_noovf, PROB_VERY_LIKELY); + emit_cmp_and_jump_insns (op0, constm1_rtx, NE, NULL_RTX, mode, + false, all_done_label, PROB_VERY_UNLIKELY); + emit_cmp_and_jump_insns (op1, res, NE, NULL_RTX, mode, + false, all_done_label, PROB_VERY_UNLIKELY); + emit_label (set_noovf); + write_complex_part (target, const0_rtx, true); + emit_label (all_done_label); + } + if (lhs) - emit_move_insn (target, res); + { + if (is_ubsan) + emit_move_insn (target, res); + else + expand_arith_overflow_result_store (lhs, target, mode, res); + } } /* Expand UBSAN_CHECK_ADD call STMT. */ @@ -834,7 +1601,12 @@ ubsan_expand_si_overflow_mul_check (gimple stmt) static void expand_UBSAN_CHECK_ADD (gimple stmt) { - ubsan_expand_si_overflow_addsub_check (PLUS_EXPR, stmt); + location_t loc = gimple_location (stmt); + tree lhs = gimple_call_lhs (stmt); + tree arg0 = gimple_call_arg (stmt, 0); + tree arg1 = gimple_call_arg (stmt, 1); + expand_addsub_overflow (loc, PLUS_EXPR, lhs, arg0, arg1, + false, false, false, true); } /* Expand UBSAN_CHECK_SUB call STMT. */ @@ -842,10 +1614,15 @@ expand_UBSAN_CHECK_ADD (gimple stmt) static void expand_UBSAN_CHECK_SUB (gimple stmt) { - if (integer_zerop (gimple_call_arg (stmt, 0))) - ubsan_expand_si_overflow_neg_check (stmt); + location_t loc = gimple_location (stmt); + tree lhs = gimple_call_lhs (stmt); + tree arg0 = gimple_call_arg (stmt, 0); + tree arg1 = gimple_call_arg (stmt, 1); + if (integer_zerop (arg0)) + expand_neg_overflow (loc, lhs, arg1, true); else - ubsan_expand_si_overflow_addsub_check (MINUS_EXPR, stmt); + expand_addsub_overflow (loc, MINUS_EXPR, lhs, arg0, arg1, + false, false, false, true); } /* Expand UBSAN_CHECK_MUL call STMT. */ @@ -853,7 +1630,208 @@ expand_UBSAN_CHECK_SUB (gimple stmt) static void expand_UBSAN_CHECK_MUL (gimple stmt) { - ubsan_expand_si_overflow_mul_check (stmt); + location_t loc = gimple_location (stmt); + tree lhs = gimple_call_lhs (stmt); + tree arg0 = gimple_call_arg (stmt, 0); + tree arg1 = gimple_call_arg (stmt, 1); + expand_mul_overflow (loc, lhs, arg0, arg1, false, false, false, true); +} + +/* Helper function for {ADD,SUB,MUL}_OVERFLOW call stmt expansion. */ + +static void +expand_arith_overflow (enum tree_code code, gimple stmt) +{ + tree lhs = gimple_call_lhs (stmt); + if (lhs == NULL_TREE) + return; + tree arg0 = gimple_call_arg (stmt, 0); + tree arg1 = gimple_call_arg (stmt, 1); + tree type = TREE_TYPE (TREE_TYPE (lhs)); + int uns0_p = TYPE_UNSIGNED (TREE_TYPE (arg0)); + int uns1_p = TYPE_UNSIGNED (TREE_TYPE (arg1)); + int unsr_p = TYPE_UNSIGNED (type); + int prec0 = TYPE_PRECISION (TREE_TYPE (arg0)); + int prec1 = TYPE_PRECISION (TREE_TYPE (arg1)); + int precres = TYPE_PRECISION (type); + location_t loc = gimple_location (stmt); + if (!uns0_p && get_range_pos_neg (arg0) == 1) + uns0_p = true; + if (!uns1_p && get_range_pos_neg (arg1) == 1) + uns1_p = true; + int pr = get_min_precision (arg0, uns0_p ? UNSIGNED : SIGNED); + prec0 = MIN (prec0, pr); + pr = get_min_precision (arg1, uns1_p ? UNSIGNED : SIGNED); + prec1 = MIN (prec1, pr); + + /* If uns0_p && uns1_p, precop is minimum needed precision + of unsigned type to hold the exact result, otherwise + precop is minimum needed precision of signed type to + hold the exact result. */ + int precop; + if (code == MULT_EXPR) + precop = prec0 + prec1 + (uns0_p != uns1_p); + else + { + if (uns0_p == uns1_p) + precop = MAX (prec0, prec1) + 1; + else if (uns0_p) + precop = MAX (prec0 + 1, prec1) + 1; + else + precop = MAX (prec0, prec1 + 1) + 1; + } + int orig_precres = precres; + + do + { + if ((uns0_p && uns1_p) + ? ((precop + !unsr_p) <= precres + /* u1 - u2 -> ur can overflow, no matter what precision + the result has. */ + && (code != MINUS_EXPR || !unsr_p)) + : (!unsr_p && precop <= precres)) + { + /* The infinity precision result will always fit into result. */ + rtx target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + write_complex_part (target, const0_rtx, true); + enum machine_mode mode = TYPE_MODE (type); + struct separate_ops ops; + ops.code = code; + ops.type = type; + ops.op0 = fold_convert_loc (loc, type, arg0); + ops.op1 = fold_convert_loc (loc, type, arg1); + ops.op2 = NULL_TREE; + ops.location = loc; + rtx tem = expand_expr_real_2 (&ops, NULL_RTX, mode, EXPAND_NORMAL); + expand_arith_overflow_result_store (lhs, target, mode, tem); + return; + } + +#ifdef WORD_REGISTER_OPERATIONS + /* For sub-word operations, if target doesn't have them, start + with precres widening right away, otherwise do it only + if the most simple cases can't be used. */ + if (orig_precres == precres && precres < BITS_PER_WORD) + ; + else +#endif + if ((uns0_p && uns1_p && unsr_p && prec0 <= precres && prec1 <= precres) + || ((!uns0_p || !uns1_p) && !unsr_p + && prec0 + uns0_p <= precres + && prec1 + uns1_p <= precres)) + { + arg0 = fold_convert_loc (loc, type, arg0); + arg1 = fold_convert_loc (loc, type, arg1); + switch (code) + { + case MINUS_EXPR: + if (integer_zerop (arg0) && !unsr_p) + expand_neg_overflow (loc, lhs, arg1, false); + /* FALLTHRU */ + case PLUS_EXPR: + expand_addsub_overflow (loc, code, lhs, arg0, arg1, + unsr_p, unsr_p, unsr_p, false); + return; + case MULT_EXPR: + expand_mul_overflow (loc, lhs, arg0, arg1, + unsr_p, unsr_p, unsr_p, false); + return; + default: + gcc_unreachable (); + } + } + + /* For sub-word operations, retry with a wider type first. */ + if (orig_precres == precres && precop <= BITS_PER_WORD) + { +#ifdef WORD_REGISTER_OPERATIONS + int p = BITS_PER_WORD; +#else + int p = precop; +#endif + enum machine_mode m = smallest_mode_for_size (p, MODE_INT); + tree optype = build_nonstandard_integer_type (GET_MODE_PRECISION (m), + uns0_p && uns1_p + && unsr_p); + p = TYPE_PRECISION (optype); + if (p > precres) + { + precres = p; + unsr_p = TYPE_UNSIGNED (optype); + type = optype; + continue; + } + } + + if (prec0 <= precres && prec1 <= precres) + { + tree types[2]; + if (unsr_p) + { + types[0] = build_nonstandard_integer_type (precres, 0); + types[1] = type; + } + else + { + types[0] = type; + types[1] = build_nonstandard_integer_type (precres, 1); + } + arg0 = fold_convert_loc (loc, types[uns0_p], arg0); + arg1 = fold_convert_loc (loc, types[uns1_p], arg1); + if (code != MULT_EXPR) + expand_addsub_overflow (loc, code, lhs, arg0, arg1, unsr_p, + uns0_p, uns1_p, false); + else + expand_mul_overflow (loc, lhs, arg0, arg1, unsr_p, + uns0_p, uns1_p, false); + return; + } + + /* Retry with a wider type. */ + if (orig_precres == precres) + { + int p = MAX (prec0, prec1); + enum machine_mode m = smallest_mode_for_size (p, MODE_INT); + tree optype = build_nonstandard_integer_type (GET_MODE_PRECISION (m), + uns0_p && uns1_p + && unsr_p); + p = TYPE_PRECISION (optype); + if (p > precres) + { + precres = p; + unsr_p = TYPE_UNSIGNED (optype); + type = optype; + continue; + } + } + + gcc_unreachable (); + } + while (1); +} + +/* Expand ADD_OVERFLOW STMT. */ + +static void +expand_ADD_OVERFLOW (gimple stmt) +{ + expand_arith_overflow (PLUS_EXPR, stmt); +} + +/* Expand SUB_OVERFLOW STMT. */ + +static void +expand_SUB_OVERFLOW (gimple stmt) +{ + expand_arith_overflow (MINUS_EXPR, stmt); +} + +/* Expand MUL_OVERFLOW STMT. */ + +static void +expand_MUL_OVERFLOW (gimple stmt) +{ + expand_arith_overflow (MULT_EXPR, stmt); } /* This should get folded in tree-vectorizer.c. */ diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def index b8e457c5090..b966c721d74 100644 --- a/gcc/internal-fn.def +++ b/gcc/internal-fn.def @@ -57,3 +57,6 @@ DEF_INTERNAL_FN (UBSAN_OBJECT_SIZE, ECF_LEAF | ECF_NOTHROW, NULL) DEF_INTERNAL_FN (ABNORMAL_DISPATCHER, ECF_NORETURN, NULL) DEF_INTERNAL_FN (BUILTIN_EXPECT, ECF_CONST | ECF_LEAF | ECF_NOTHROW, NULL) DEF_INTERNAL_FN (ASAN_CHECK, ECF_TM_PURE | ECF_LEAF | ECF_NOTHROW, ".W...") +DEF_INTERNAL_FN (ADD_OVERFLOW, ECF_CONST | ECF_LEAF | ECF_NOTHROW, NULL) +DEF_INTERNAL_FN (SUB_OVERFLOW, ECF_CONST | ECF_LEAF | ECF_NOTHROW, NULL) +DEF_INTERNAL_FN (MUL_OVERFLOW, ECF_CONST | ECF_LEAF | ECF_NOTHROW, NULL) diff --git a/gcc/optabs.def b/gcc/optabs.def index a07e1639ed6..ed054e2b96d 100644 --- a/gcc/optabs.def +++ b/gcc/optabs.def @@ -190,6 +190,7 @@ OPTAB_D (ctrap_optab, "ctrap$a4") OPTAB_D (addv4_optab, "addv$I$a4") OPTAB_D (subv4_optab, "subv$I$a4") OPTAB_D (mulv4_optab, "mulv$I$a4") +OPTAB_D (umulv4_optab, "umulv$I$a4") OPTAB_D (negv3_optab, "negv$I$a3") OPTAB_D (addptr3_optab, "addptr$a3") diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 7b284c10537..9ec99af67cb 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,31 @@ +2014-11-12 Jakub Jelinek <jakub@redhat.com> + + PR c/59708 + * c-c++-common/builtin-arith-overflow-1.c: New test. + * c-c++-common/torture/builtin-arith-overflow-10.c: New test. + * c-c++-common/torture/builtin-arith-overflow-11.c: New test. + * c-c++-common/torture/builtin-arith-overflow-12.c: New test. + * c-c++-common/torture/builtin-arith-overflow-12.h: New file. + * c-c++-common/torture/builtin-arith-overflow-13.c: New test. + * c-c++-common/torture/builtin-arith-overflow-14.c: New test. + * c-c++-common/torture/builtin-arith-overflow-15.c: New test. + * c-c++-common/torture/builtin-arith-overflow-16.c: New test. + * c-c++-common/torture/builtin-arith-overflow-17.c: New test. + * c-c++-common/torture/builtin-arith-overflow-18.c: New test. + * c-c++-common/torture/builtin-arith-overflow-1.c: New test. + * c-c++-common/torture/builtin-arith-overflow-1.h: New file. + * c-c++-common/torture/builtin-arith-overflow-2.c: New test. + * c-c++-common/torture/builtin-arith-overflow-3.c: New test. + * c-c++-common/torture/builtin-arith-overflow-4.c: New test. + * c-c++-common/torture/builtin-arith-overflow-5.c: New test. + * c-c++-common/torture/builtin-arith-overflow-6.c: New test. + * c-c++-common/torture/builtin-arith-overflow-7.c: New test. + * c-c++-common/torture/builtin-arith-overflow-8.c: New test. + * c-c++-common/torture/builtin-arith-overflow-9.c: New test. + * c-c++-common/torture/builtin-arith-overflow.h: New file. + * gcc.dg/builtin-arith-overflow-1.c: New test. + * gcc.dg/builtin-arith-overflow-2.c: New test. + 2014-11-12 Richard Biener <rguenther@suse.de> PR middle-end/63821 diff --git a/gcc/testsuite/c-c++-common/builtin-arith-overflow-1.c b/gcc/testsuite/c-c++-common/builtin-arith-overflow-1.c new file mode 100644 index 00000000000..69b508386d5 --- /dev/null +++ b/gcc/testsuite/c-c++-common/builtin-arith-overflow-1.c @@ -0,0 +1,49 @@ +/* { dg-do compile } */ + +int +f1 (void) +{ + int x = __builtin_add_overflow (); /* { dg-error "not enough arguments to function" } */ + x += __builtin_sub_overflow (); /* { dg-error "not enough arguments to function" } */ + x += __builtin_mul_overflow (); /* { dg-error "not enough arguments to function" } */ + return x; +} + +int +f2 (int a, int b, int *c, int d) +{ + int x = __builtin_add_overflow (a, b, c, d); /* { dg-error "too many arguments to function" } */ + x += __builtin_sub_overflow (a, b, c, d, d, d); /* { dg-error "too many arguments to function" } */ + x += __builtin_mul_overflow (a, b, c, d); /* { dg-error "too many arguments to function" } */ + return x; +} + +enum E { e0 = 0, e1 = 1 }; + +#ifndef __cplusplus +#define bool _Bool +#endif + +int +f3 (float fa, int a, _Complex long int ca, double fb, void *pb, int b, enum E eb, bool bb, int *c) +{ + int x = __builtin_add_overflow (fa, b, c); /* { dg-error "argument 1 in call to function\[^\n\r]*does not have integral type" } */ + x += __builtin_sub_overflow (ca, b, c); /* { dg-error "argument 1 in call to function\[^\n\r]*does not have integral type" } */ + x += __builtin_mul_overflow (a, fb, c); /* { dg-error "argument 2 in call to function\[^\n\r]*does not have integral type" } */ + x += __builtin_add_overflow (a, pb, c); /* { dg-error "argument 2 in call to function\[^\n\r]*does not have integral type" } */ + x += __builtin_sub_overflow (a, eb, c); + x += __builtin_mul_overflow (a, bb, c); + return x; +} + +int +f4 (float *fp, double *dp, _Complex int *cp, enum E *ep, bool *bp, long long int *llp) +{ + int x = __builtin_add_overflow (1, 2, fp); /* { dg-error "argument 3 in call to function\[^\n\r]*does not have pointer to integer type" } */ + x += __builtin_sub_overflow (1, 2, dp); /* { dg-error "argument 3 in call to function\[^\n\r]*does not have pointer to integer type" } */ + x += __builtin_mul_overflow (1, 2, cp); /* { dg-error "argument 3 in call to function\[^\n\r]*does not have pointer to integer type" } */ + x += __builtin_add_overflow (1, 2, ep); /* { dg-error "argument 3 in call to function\[^\n\r]*does not have pointer to integer type" } */ + x += __builtin_sub_overflow (1, 2, bp); /* { dg-error "argument 3 in call to function\[^\n\r]*does not have pointer to integer type" } */ + x += __builtin_mul_overflow (1, 2, llp); + return x; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-1.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-1.c new file mode 100644 index 00000000000..4d90ba5e1db --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-1.c @@ -0,0 +1,24 @@ +/* Test __builtin_{add,sub,mul,{s,u}add,{s,u}sub,{s,u}mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-1.h" + +#define U(s, op) s##op +TESTS (int, INT_MIN, INT_MAX) +#undef U +#define U(s, op) op +TESTS (int, INT_MIN, INT_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (int, INT_MIN, INT_MAX) +#undef U +#define U(s, op) s##op + TESTS (int, INT_MIN, INT_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-1.h b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-1.h new file mode 100644 index 00000000000..b7ae82ea85b --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-1.h @@ -0,0 +1,37 @@ +#include "builtin-arith-overflow.h" + +#define TESTS(type, min, max) \ +ST (100, signed type, 2, 3, 5, U(s, add), 0) \ +ST (101, signed type, max, -1, max - 1, U(s, add), 0) \ +ST (102, signed type, max, 0, max, U(s, add), 0) \ +ST (103, signed type, 1, max, min, U(s, add), 1) \ +ST (104, signed type, 0, min, min, U(s, sub), 1) \ +ST (110, signed type, 2, 3, -1, U(s, sub), 0) \ +ST (111, signed type, max, -1, min, U(s, sub), 1) \ +ST (112, signed type, max, 0, max, U(s, sub), 0) \ +ST (113, signed type, 1, max, min + 2, U(s, sub), 0) \ +ST (114, signed type, max, -1, min, U(s, sub), 1) \ +ST (120, signed type, 2, 3, 6, U(s, mul), 0) \ +ST (122, signed type, min, -1, min, U(s, mul), 1) \ +ST (123, signed type, max, 0, 0, U(s, mul), 0) \ +ST (124, signed type, 1, max, max, U(s, mul), 0) \ +ST (125, signed type, max, 2, -2, U(s, mul), 1) \ +ST (126, signed type, max / 25, 25, max / 25 * 25, U(s, mul), 0) \ +ST (127, signed type, max / 25 + 1, 25, max / 25 * 25 + (unsigned type) 25, U(s, mul), 1) \ +ST (150, unsigned type, 2, 3, 5, U(u, add), 0) \ +ST (151, unsigned type, -1, -1, -2, U(u, add), 1) \ +ST (152, unsigned type, -1, 0, -1, U(u, add), 0) \ +ST (153, unsigned type, 1, -1, 0, U(u, add), 1) \ +ST (154, unsigned type, 0, min, min, U(u, sub), 1) \ +ST (160, unsigned type, 2, 3, -1, U(u, sub), 1) \ +ST (161, unsigned type, -1, -1, 0, U(u, sub), 0) \ +ST (162, unsigned type, -1, 0, -1, U(u, sub), 0) \ +ST (163, unsigned type, 1, -1, 2, U(u, sub), 1) \ +ST (164, unsigned type, 15, 14, 1, U(u, sub), 0) \ +ST (170, unsigned type, 2, 3, 6, U(u, mul), 0) \ +ST (171, unsigned type, max, 3, 3 * (unsigned type) max, U(u, mul), 1) \ +ST (172, unsigned type, -1, 0, 0, U(u, mul), 0) \ +ST (173, unsigned type, 1, -1, -1, U(u, mul), 0) \ +ST (174, unsigned type, -1, 2, -2, U(u, mul), 1) \ +ST (175, unsigned type, ((unsigned type) -1) / 25, 25, ((unsigned type) -1) / 25 * 25, U(u, mul), 0) \ +ST (176, unsigned type, ((unsigned type) -1) / 25 + 1, 25, ((unsigned type) -1) / 25 * 25 + (unsigned type) 25, U(u, mul), 1) diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-10.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-10.c new file mode 100644 index 00000000000..6b1c427c91c --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-10.c @@ -0,0 +1,19 @@ +/* Test __builtin_{add,sub}_overflow on {,un}signed long int. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +typedef signed long int S; +typedef unsigned long int U; +#define COND 1 +#define SHIFT ((__SIZEOF_LONG__ - 1) * __CHAR_BIT__) +#define S_MAX __LONG_MAX__ +#define S_MIN (-__LONG_MAX__ - 1) +#if __SIZEOF_LONG_LONG__ > __SIZEOF_LONG__ +typedef long long int W; +#elif __SIZEOF_INT128__ > __SIZEOF_LONG__ +typedef __int128 W; +#else +#undef COND +#define COND 0 +#endif +#include "builtin-arith-overflow-7.c" diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-11.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-11.c new file mode 100644 index 00000000000..1e7d4ae3424 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-11.c @@ -0,0 +1,17 @@ +/* Test __builtin_{add,sub}_overflow on {,un}signed long long int. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +typedef signed long long int S; +typedef unsigned long long int U; +#define COND 1 +#define SHIFT ((__SIZEOF_LONG_LONG__ - 1) * __CHAR_BIT__) +#define S_MAX __LONG_LONG_MAX__ +#define S_MIN (-__LONG_LONG_MAX__ - 1) +#if __SIZEOF_INT128__ > __SIZEOF_LONG_LONG__ +typedef __int128 W; +#else +#undef COND +#define COND 0 +#endif +#include "builtin-arith-overflow-7.c" diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-12.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-12.c new file mode 100644 index 00000000000..a37d817205b --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-12.c @@ -0,0 +1,17 @@ +/* Test __builtin_{add,sub,mul_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-12.h" + +TESTS (int, INT_MIN, INT_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (int, INT_MIN, INT_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-12.h b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-12.h new file mode 100644 index 00000000000..1e48456dd64 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-12.h @@ -0,0 +1,80 @@ +#include "builtin-arith-overflow.h" + +#define TESTS(type, min, max) \ +T (100, signed type, unsigned type, unsigned type, -1, 0, 0, mul, 0) \ +T (101, signed type, unsigned type, unsigned type, -1, 1, (unsigned type) -1, mul, 1) \ +T (102, unsigned type, signed type, unsigned type, 12, -3, (unsigned type) -36, mul, 1) \ +T (103, signed type, unsigned type, unsigned type, 3, 4, 12, mul, 0) \ +T (104, unsigned type, signed type, unsigned type, (unsigned type) -1 / 12, 12, (unsigned type) -1 / 12 * 12, mul, 0) \ +T (105, unsigned type, signed type, unsigned type, (unsigned type) -1 / 12, 13, (unsigned type) -1 / 12 * 13, mul, 1) \ +T (106, unsigned type, unsigned type, signed type, 0, 0, 0, mul, 0) \ +T (107, unsigned type, unsigned type, signed type, max / 31, 31, (signed type) ((unsigned type) max / 31 * 31), mul, 0) \ +T (108, unsigned type, unsigned type, signed type, max / 31, 32, (signed type) ((unsigned type) max / 31 * 32), mul, 1) \ +T (109, unsigned type, unsigned type, signed type, max / 31, 65, (signed type) ((unsigned type) max / 31 * 65), mul, 1) \ +T (110, signed type, unsigned type, signed type, -1, 7, -7, mul, 0) \ +T (111, unsigned type, signed type, signed type, 2, min / 2, min, mul, 0) \ +T (112, signed type, unsigned type, signed type, max / 12, 13, (signed type) ((unsigned type) max / 12 * 13), mul, 1) \ +T (113, unsigned type, signed type, signed type, (unsigned type) max + 19, 0, 0, mul, 0) \ +T (114, signed type, unsigned type, signed type, 0, (unsigned type) max + 1, 0, mul, 0) \ +T (115, unsigned type, signed type, signed type, (unsigned type) max + 1, -1, min, mul, 0) \ +T (116, signed type, unsigned type, signed type, -1, (unsigned type) max + 2, max, mul, 1) \ +T (117, signed type, signed type, unsigned type, min / 64, -64, (unsigned type) min, mul, 0) \ +T (118, signed type, signed type, unsigned type, min / 32, -33, ((unsigned type) max + 1) / 32 * 33, mul, 0) \ +T (119, signed type, signed type, unsigned type, min / 32, -65, ((unsigned type) max + 1) / 32 * 65, mul, 1) \ +T (120, signed type, signed type, unsigned type, -1, -1, 1, mul, 0) \ +T (121, signed type, signed type, unsigned type, 0, 0, 0, mul, 0) \ +T (122, signed type, signed type, unsigned type, 0, -6, 0, mul, 0) \ +T (123, signed type, signed type, unsigned type, -15, 0, 0, mul, 0) \ +T (124, signed type, signed type, unsigned type, -1, 1, ~(unsigned type) 0, mul, 1) \ +T (125, signed type, signed type, unsigned type, -17, 5, (unsigned type) -17 * 5, mul, 1) \ +T (126, signed type, signed type, unsigned type, 7, max / 7, max / 7 * 7, mul, 0) \ +T (127, signed type, signed type, unsigned type, max / 7, 8, (unsigned type) max / 7 * 8, mul, 0) \ +T (128, signed type, signed type, unsigned type, 15, max / 7, (unsigned type) max / 7 * 15, mul, 1) \ +T (129, signed type, unsigned type, signed type, min, 5, min + 5, add, 0) \ +T (130, unsigned type, signed type, signed type, ~(unsigned type) 0, min, max, add, 0) \ +T (131, signed type, unsigned type, signed type, max, 1, min, add, 1) \ +T (132, unsigned type, signed type, signed type, max / 2, max / 2 + 1, max, add, 0) \ +T (133, signed type, unsigned type, signed type, max / 2 + 1, max / 2 + 1, min, add, 1) \ +T (134, signed type, unsigned type, unsigned type, min, ~(unsigned type) 0, max, add, 0) \ +T (135, unsigned type, signed type, unsigned type, ~(unsigned type) 0, min + 1, (unsigned type) max + 1, add, 0) \ +T (136, signed type, unsigned type, unsigned type, 1, ~(unsigned type) 0, 0, add, 1) \ +T (137, unsigned type, signed type, unsigned type, 2, -3, ~(unsigned type) 0, add, 1) \ +T (138, signed type, unsigned type, signed type, min, 1, max, sub, 1) \ +T (139, signed type, unsigned type, signed type, min + 1, 1, min, sub, 0) \ +T (140, signed type, unsigned type, signed type, max, (unsigned type) max + 1, -1, sub, 0) \ +T (141, signed type, unsigned type, signed type, max, ~(unsigned type) 0, min, sub, 0) \ +T (142, signed type, unsigned type, signed type, max - 1, ~(unsigned type) 0, max, sub, 1) \ +T (143, signed type, unsigned type, unsigned type, -1, 0, ~(unsigned type) 0, sub, 1) \ +T (144, signed type, unsigned type, unsigned type, -1, ~(unsigned type) 0, 0, sub, 1) \ +T (145, signed type, unsigned type, unsigned type, min, 0, min, sub, 1) \ +T (146, signed type, unsigned type, unsigned type, max, max, 0, sub, 0) \ +T (147, signed type, unsigned type, unsigned type, max, (unsigned type) max + 1, -1, sub, 1) \ +T (148, signed type, unsigned type, unsigned type, max - 1, max, -1, sub, 1) \ +T (149, unsigned type, signed type, signed type, 0, max, -max, sub, 0) \ +T (150, unsigned type, signed type, signed type, (unsigned type) max + 1, 0, min, sub, 1) \ +T (151, unsigned type, signed type, signed type, (unsigned type) max + 1, 1, max, sub, 0) \ +T (152, unsigned type, unsigned type, signed type, 0, (unsigned type) max + 1, min, add, 1) \ +T (153, signed type, signed type, unsigned type, -1, 0, -1, add, 1) \ +T (154, unsigned type, signed type, unsigned type, 5, 6, -1, sub, 1) \ +T (155, unsigned type, signed type, unsigned type, ~(unsigned type) 0, max, (unsigned type) max + 1, sub, 0) \ +T (156, unsigned type, signed type, unsigned type, (unsigned type) max + 1, min, 0, sub, 1) \ +T (157, signed type, signed type, unsigned type, 3, -2, 1, add, 0) \ +T (158, signed type, signed type, unsigned type, 3, -4, -1, add, 1) \ +T (159, signed type, signed type, unsigned type, -3, -4, -7, add, 1) \ +T (160, signed type, signed type, unsigned type, -5, 4, -1, add, 1) \ +T (161, signed type, signed type, unsigned type, -5, 5, 0, add, 0) \ +T (162, signed type, signed type, unsigned type, min, 1, min + 1, add, 1) \ +T (163, unsigned type, unsigned type, signed type, max, 1, min, add, 1) \ +T (164, unsigned type, unsigned type, signed type, max - 1, 1, max, add, 0) \ +T (165, unsigned type, unsigned type, signed type, ~(unsigned type) 0, ~(unsigned type) 0, ~(unsigned type) 0 - 1, add, 1) \ +T (166, unsigned type, unsigned type, signed type, (unsigned type) max + 3, 2, min, sub, 1) \ +T (167, unsigned type, unsigned type, signed type, (unsigned type) max + 2, 2, max, sub, 0) \ +T (168, unsigned type, unsigned type, signed type, (unsigned type) max + 2, (unsigned type) max + 3, -1, sub, 0) \ +T (169, unsigned type, unsigned type, signed type, 0, (unsigned type) max + 1, min, sub, 0) \ +T (170, unsigned type, unsigned type, signed type, 0, (unsigned type) max + 2, max, sub, 1) \ +T (171, signed type, signed type, unsigned type, 3, 2, 1, sub, 0) \ +T (172, signed type, signed type, unsigned type, 3, 4, -1, sub, 1) \ +T (173, signed type, signed type, unsigned type, -3, 4, -7, sub, 1) \ +T (174, signed type, signed type, unsigned type, -5, -4, -1, sub, 1) \ +T (175, signed type, signed type, unsigned type, -5, -5, 0, sub, 0) \ +T (176, signed type, signed type, unsigned type, min, -1, min + 1, sub, 1) diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-13.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-13.c new file mode 100644 index 00000000000..730b6d964af --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-13.c @@ -0,0 +1,17 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-12.h" + +TESTS (long, LONG_MIN, LONG_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (long, LONG_MIN, LONG_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-14.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-14.c new file mode 100644 index 00000000000..6f03cf71949 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-14.c @@ -0,0 +1,17 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-12.h" + +TESTS (long long, LLONG_MIN, LLONG_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (long long, LLONG_MIN, LLONG_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-15.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-15.c new file mode 100644 index 00000000000..3d78994d7dd --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-15.c @@ -0,0 +1,17 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-12.h" + +TESTS (char, SCHAR_MIN, SCHAR_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (char, SCHAR_MIN, SCHAR_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-16.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-16.c new file mode 100644 index 00000000000..d148be6507e --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-16.c @@ -0,0 +1,17 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-12.h" + +TESTS (short, SHRT_MIN, SHRT_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (short, SHRT_MIN, SHRT_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-17.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-17.c new file mode 100644 index 00000000000..3b33e49220c --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-17.c @@ -0,0 +1,20 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run { target int128 } } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-12.h" + +#define INT128_MAX ((signed __int128) (((unsigned __int128) 1 << (__SIZEOF_INT128__ * __CHAR_BIT__ - 1)) - 1)) +#define INT128_MIN (-INT128_MAX - 1) + +TESTS (__int128, INT128_MIN, INT128_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (__int128, INT128_MIN, INT128_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-18.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-18.c new file mode 100644 index 00000000000..cce5b11b7cf --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-18.c @@ -0,0 +1,36 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow.h" + +#ifdef __SIZEOF_INT128__ +#define WTYPE __int128 +#else +#define WTYPE long long int +#endif + +#define TESTS \ +T (100, signed char, signed char, unsigned WTYPE, -1, 0, -1, add, 1) \ +T (101, unsigned char, unsigned char, unsigned WTYPE, 5, 5, 10, add, 0) \ +T (102, signed char, unsigned short, unsigned WTYPE, 5, 5, 0, sub, 0) \ +T (103, signed char, unsigned short, unsigned WTYPE, 5, 6, -1, sub, 1) \ +T (104, signed char, signed char, unsigned WTYPE, -1, -1, 1, mul, 0) \ +T (105, unsigned char, signed char, unsigned WTYPE, 17, -2, -34, mul, 1) \ +T (106, unsigned WTYPE, signed WTYPE, signed char, 5, -2, -10, mul, 0) \ +T (107, long long int, long long int, unsigned char, -3, 5, 2, add, 0) \ +T (108, long long int, int, unsigned char, -5, 3, -2, add, 1) \ +T (109, int, WTYPE, unsigned char, -3, 5, 2, add, 0) \ +T (110, unsigned char, unsigned char, unsigned WTYPE, SCHAR_MAX - 1, (unsigned char) SCHAR_MAX + 4, -5, sub, 1) + +TESTS + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-2.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-2.c new file mode 100644 index 00000000000..4b51d9eaa04 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-2.c @@ -0,0 +1,24 @@ +/* Test __builtin_{add,sub,mul,{s,u}addl,{s,u}subl,{s,u}mull}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-1.h" + +#define U(s, op) s##op##l +TESTS (long, LONG_MIN, LONG_MAX) +#undef U +#define U(s, op) op +TESTS (long, LONG_MIN, LONG_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (long, LONG_MIN, LONG_MAX) +#undef U +#define U(s, op) s##op##l + TESTS (long, LONG_MIN, LONG_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-3.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-3.c new file mode 100644 index 00000000000..cc1a44117ad --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-3.c @@ -0,0 +1,24 @@ +/* Test __builtin_{add,sub,mul,{s,u}addll,{s,u}subll,{s,u}mulll}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-1.h" + +#define U(s, op) s##op##ll +TESTS (long long, LLONG_MIN, LLONG_MAX) +#undef U +#define U(s, op) op +TESTS (long long, LLONG_MIN, LLONG_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (long long, LLONG_MIN, LLONG_MAX) +#undef U +#define U(s, op) s##op##ll + TESTS (long long, LLONG_MIN, LLONG_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-4.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-4.c new file mode 100644 index 00000000000..6d35aa1ae15 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-4.c @@ -0,0 +1,18 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-1.h" + +#define U(s, op) op +TESTS (char, SCHAR_MIN, SCHAR_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (char, SCHAR_MIN, SCHAR_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-5.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-5.c new file mode 100644 index 00000000000..fd5c7c981c4 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-5.c @@ -0,0 +1,18 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-1.h" + +#define U(s, op) op +TESTS (short, SHRT_MIN, SHRT_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (short, SHRT_MIN, SHRT_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-6.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-6.c new file mode 100644 index 00000000000..e2661e77149 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-6.c @@ -0,0 +1,21 @@ +/* Test __builtin_{add,sub,mul}_overflow. */ +/* { dg-do run { target int128 } } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#include "builtin-arith-overflow-1.h" + +#define INT128_MAX ((signed __int128) (((unsigned __int128) 1 << (__SIZEOF_INT128__ * __CHAR_BIT__ - 1)) - 1)) +#define INT128_MIN (-INT128_MAX - 1) + +#define U(s, op) op +TESTS (__int128, INT128_MIN, INT128_MAX) + +#undef T +#define T(n, t1, t2, tr, v1, v2, vr, b, o) t##n##b (); + +int +main () +{ + TESTS (__int128, INT128_MIN, INT128_MAX) + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-7.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-7.c new file mode 100644 index 00000000000..6f61d7c553c --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-7.c @@ -0,0 +1,80 @@ +/* Test __builtin_{add,sub}_overflow on {,un}signed char. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +#define UCHAR_MAX ((unsigned char) ~0) +#ifndef SHIFT +typedef signed char S; +typedef unsigned char U; +typedef int W; +#define SHIFT 0 +#define S_MAX __SCHAR_MAX__ +#define S_MIN (-__SCHAR_MAX__ - 1) +#define COND (__SIZEOF_INT__ > 1) +#endif + +#define F(n, t1, t2, tr, b) \ +__attribute__((noinline, noclone)) tr \ +n (t1 x, t2 y, int *ovf) \ +{ \ + tr res; \ + *ovf = __builtin_##b##_overflow (x, y, &res); \ + return res; \ +} + +F (spses, S, S, S, add) +F (upueu, U, U, U, add) +F (spseu, S, S, U, add) +F (upues, U, U, S, add) +F (spues, S, U, S, add) +F (upses, U, S, S, add) +F (spueu, S, U, U, add) +F (upseu, U, S, U, add) +F (ssses, S, S, S, sub) +F (usueu, U, U, U, sub) +F (ssseu, S, S, U, sub) +F (usues, U, U, S, sub) +F (ssues, S, U, S, sub) +F (usses, U, S, S, sub) +F (ssueu, S, U, U, sub) +F (usseu, U, S, U, sub) + +int +main () +{ +#if COND + int i, j; + for (i = 0; i < UCHAR_MAX; i++) + for (j = 0; j < UCHAR_MAX; j++) + { + S s1 = ((W) i << SHIFT) + S_MIN; + U u1 = ((W) i << SHIFT); + S s2 = ((W) j << SHIFT) + S_MIN; + U u2 = ((W) j << SHIFT); + W w; + int ovf; +#define T(n, t1, t2, tr, op) \ + w = ((W) t1##1) op ((W) t2##2); \ + if (n (t1##1, t2##2, &ovf) != (tr) w \ + || ovf != (w != (tr) w)) \ + __builtin_abort (); + T (spses, s, s, S, +) + T (upueu, u, u, U, +) + T (spseu, s, s, U, +) + T (upues, u, u, S, +) + T (spues, s, u, S, +) + T (upses, u, s, S, +) + T (spueu, s, u, U, +) + T (upseu, u, s, U, +) + T (ssses, s, s, S, -) + T (usueu, u, u, U, -) + T (ssseu, s, s, U, -) + T (usues, u, u, S, -) + T (ssues, s, u, S, -) + T (usses, u, s, S, -) + T (ssueu, s, u, U, -) + T (usseu, u, s, U, -) + } +#endif + return 0; +} diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-8.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-8.c new file mode 100644 index 00000000000..9e1754fed30 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-8.c @@ -0,0 +1,23 @@ +/* Test __builtin_{add,sub}_overflow on {,un}signed short. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +typedef signed short int S; +typedef unsigned short int U; +#define COND 1 +#define SHIFT ((__SIZEOF_SHORT__ - 1) * __CHAR_BIT__) +#define S_MAX __SHRT_MAX__ +#define S_MIN (-__SHRT_MAX__ - 1) +#if __SIZEOF_INT__ > __SIZEOF_SHORT__ +typedef int W; +#elif __SIZEOF_LONG__ > __SIZEOF_SHORT__ +typedef long int W; +#elif __SIZEOF_LONG_LONG__ > __SIZEOF_SHORT__ +typedef long long int W; +#elif __SIZEOF_INT128__ > __SIZEOF_SHORT__ +typedef __int128 W; +#else +#undef COND +#define COND 0 +#endif +#include "builtin-arith-overflow-7.c" diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-9.c b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-9.c new file mode 100644 index 00000000000..80549069718 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow-9.c @@ -0,0 +1,21 @@ +/* Test __builtin_{add,sub}_overflow on {,un}signed int. */ +/* { dg-do run } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ + +typedef signed int S; +typedef unsigned int U; +#define COND 1 +#define SHIFT ((__SIZEOF_INT__ - 1) * __CHAR_BIT__) +#define S_MAX __INT_MAX__ +#define S_MIN (-__INT_MAX__ - 1) +#if __SIZEOF_LONG__ > __SIZEOF_INT__ +typedef long int W; +#elif __SIZEOF_LONG_LONG__ > __SIZEOF_INT__ +typedef long long int W; +#elif __SIZEOF_INT128__ > __SIZEOF_INT__ +typedef __int128 W; +#else +#undef COND +#define COND 0 +#endif +#include "builtin-arith-overflow-7.c" diff --git a/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow.h b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow.h new file mode 100644 index 00000000000..9bf3ecf1f21 --- /dev/null +++ b/gcc/testsuite/c-c++-common/torture/builtin-arith-overflow.h @@ -0,0 +1,94 @@ +#define SCHAR_MAX __SCHAR_MAX__ +#define SCHAR_MIN (-__SCHAR_MAX__ - 1) +#define SHRT_MAX __SHRT_MAX__ +#define SHRT_MIN (-__SHRT_MAX__ - 1) +#define INT_MAX __INT_MAX__ +#define INT_MIN (-__INT_MAX__ - 1) +#define LONG_MAX __LONG_MAX__ +#define LONG_MIN (-__LONG_MAX__ - 1) +#define LLONG_MAX __LONG_LONG_MAX__ +#define LLONG_MIN (-__LONG_LONG_MAX__ - 1) + +int v; + +__attribute__((noinline, noclone)) void +bar (void) +{ + v++; +} + +#define T(n, t1, t2, tr, v1, v2, vr, b, o) \ +__attribute__((noinline, noclone)) tr \ +t##n##_1##b (t1 x, t2 y) \ +{ \ + tr r; \ + if (__builtin_##b##_overflow (x, y, &r)) \ + bar (); \ + return r; \ +} \ + \ +__attribute__((noinline, noclone)) tr \ +t##n##_2##b (t2 y) \ +{ \ + t1 x = (v1); \ + tr r; \ + if (__builtin_##b##_overflow (x, y, &r)) \ + bar (); \ + return r; \ +} \ + \ +__attribute__((noinline, noclone)) tr \ +t##n##_3##b (t2 y) \ +{ \ + tr r; \ + if (__builtin_##b##_overflow ((t1) (v1), y, \ + &r)) \ + bar (); \ + return r; \ +} \ + \ +__attribute__((noinline, noclone)) tr \ +t##n##_4##b (t1 x) \ +{ \ + t2 y = (v2); \ + tr r; \ + if (__builtin_##b##_overflow (x, y, &r)) \ + bar (); \ + return r; \ +} \ + \ +__attribute__((noinline, noclone)) tr \ +t##n##_5##b (t1 x) \ +{ \ + tr r; \ + if (__builtin_##b##_overflow (x, (t2) (v2), \ + &r)) \ + bar (); \ + return r; \ +} \ + \ +__attribute__((noinline, noclone)) void \ +t##n##b (void) \ +{ \ + t1 x = (v1); \ + t2 y = (v2); \ + tr r1, r2; \ + v = 0; \ + if (t##n##_1##b (x, y) != (tr) (vr) \ + || t##n##_2##b (y) != (tr) (vr) \ + || t##n##_3##b (y) != (tr) (vr) \ + || t##n##_4##b (x) != (tr) (vr) \ + || t##n##_5##b (x) != (tr) (vr)) \ + __builtin_abort (); \ + if (__builtin_##b##_overflow (x, y, &r1)) \ + bar (); \ + if (r1 != (tr) (vr)) \ + __builtin_abort (); \ + if (__builtin_##b##_overflow ((t1) (v1), \ + (t2) (v2), &r2))\ + bar (); \ + if (r2 != (tr) (vr) || v != 7 * o) \ + __builtin_abort (); \ +} +#define ST(n, t, v1, v2, vr, b, o) \ +T (n, t, t, t, v1, v2, vr, b, o) diff --git a/gcc/testsuite/gcc.dg/builtin-arith-overflow-1.c b/gcc/testsuite/gcc.dg/builtin-arith-overflow-1.c new file mode 100644 index 00000000000..b9c1517310e --- /dev/null +++ b/gcc/testsuite/gcc.dg/builtin-arith-overflow-1.c @@ -0,0 +1,132 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -fdump-tree-optimized -g" } */ + +/* SUB_OVERFLOW should be folded into unsigned subtraction, + because ovf is never used. */ +__attribute__((noinline, noclone)) int +fn1 (int x, unsigned int y) +{ + int res; + int ovf = __builtin_sub_overflow (x, y, &res); + int res2 = res; + int res3 = res2 - 2; + (void) ovf; + return res; +} + +/* MUL_OVERFLOW should be folded into unsigned multiplication, + because ovf is never used. */ +__attribute__((noinline, noclone)) int +fn2 (char x, long int y) +{ + short int res; + int ovf = __builtin_mul_overflow (x, y, &res); + int res2 = res; + int res3 = res2 - 2; + (void) ovf; + return res; +} + +#if __SIZEOF_INT__ > __SIZEOF_SHORT__ && __SIZEOF_INT__ > 1 +/* ADD_OVERFLOW should be folded into unsigned addition, + because it never overflows. */ +__attribute__((noinline, noclone)) int +fn3 (char x, unsigned short y, int *ovf) +{ + int res; + *ovf = __builtin_add_overflow (x, y, &res); + return res; +} +#endif + +/* MUL_OVERFLOW should be folded into unsigned multiplication, + because it never overflows. */ +__attribute__((noinline, noclone)) long int +fn4 (long int x, long int y, int *ovf) +{ + long int res; + x &= 65535; + y = (y & 65535) - 32768; + *ovf = __builtin_mul_overflow (x, y, &res); + return res; +} + +#if __SIZEOF_INT__ > 1 +/* MUL_OVERFLOW should be folded into unsigned multiplication, + because it always overflows. */ +__attribute__((noinline, noclone)) signed char +fn5 (long int x, long int y, int *ovf) +{ + signed char res; + x = (x & 63) + (__SCHAR_MAX__ / 4); + y = (y & 3) + 5; + *ovf = __builtin_mul_overflow (x, y, &res); + return res; +} +#endif + +/* ADD_OVERFLOW should be folded into unsigned additrion, + because it never overflows. */ +__attribute__((noinline, noclone)) unsigned char +fn6 (unsigned char x, unsigned char y, int *ovf) +{ + unsigned char res; + x = (x & 63) + ((unsigned char) ~0 - 66); + y = (y & 3); + *ovf = __builtin_add_overflow (x, y, &res); + return res; +} + +/* ADD_OVERFLOW should be folded into unsigned additrion, + because it always overflows. */ +__attribute__((noinline, noclone)) unsigned char +fn7 (unsigned char x, unsigned char y, int *ovf) +{ + unsigned char res; + x = (x & 15) + ((unsigned char) ~0 - 15); + y = (y & 3) + 16; + *ovf = __builtin_add_overflow (x, y, &res); + return res; +} + +int +main () +{ + int ovf; + if (fn1 (-10, __INT_MAX__) != (int) (-10U - __INT_MAX__) + || fn2 (0, 0) != 0 + || fn2 (32, 16383) != (short int) 524256ULL) + __builtin_abort (); +#if __SIZEOF_INT__ > __SIZEOF_SHORT__ && __SIZEOF_INT__ > 1 + if (fn3 (__SCHAR_MAX__, (unsigned short) ~0, &ovf) != (int) (__SCHAR_MAX__ + (unsigned short) ~0) + || ovf + || fn3 (-__SCHAR_MAX__ - 1, 0, &ovf) != (int) (-__SCHAR_MAX__ - 1) + || ovf) + __builtin_abort (); +#endif + if (fn4 (65535, 0, &ovf) != 65535L * -32768 || ovf) + __builtin_abort (); +#if __SIZEOF_INT__ > 1 + if (fn5 (0, 0, &ovf) != (signed char) (__SCHAR_MAX__ / 4 * 5) + || !ovf + || fn5 (63, 3, &ovf) != (signed char) ((__SCHAR_MAX__ / 4 + 63) * 8) + || !ovf) + __builtin_abort (); +#endif + if (fn6 (0, 0, &ovf) != (unsigned char) ~0 - 66 + || ovf + || fn6 (63, 3, &ovf) != (unsigned char) ~0 + || ovf) + __builtin_abort (); + if (fn7 (0, 0, &ovf) != 0 + || !ovf + || fn7 (63, 3, &ovf) != 18 + || !ovf) + __builtin_abort (); + return 0; +} + +/* { dg-final { scan-tree-dump-not "ADD_OVERFLOW" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "SUB_OVERFLOW" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "MUL_OVERFLOW" "optimized" } } */ +/* { dg-final { cleanup-tree-dump "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/builtin-arith-overflow-2.c b/gcc/testsuite/gcc.dg/builtin-arith-overflow-2.c new file mode 100644 index 00000000000..e64a400d389 --- /dev/null +++ b/gcc/testsuite/gcc.dg/builtin-arith-overflow-2.c @@ -0,0 +1,110 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -fdump-tree-optimized" } */ + +/* MUL_OVERFLOW should not be folded into unsigned multiplication, + because it sometimes overflows and sometimes does not. */ +__attribute__((noinline, noclone)) long int +fn1 (long int x, long int y, int *ovf) +{ + long int res; + x &= 65535; + y = (y & 65535) - (__LONG_MAX__ / 65535 + 32768); + *ovf = __builtin_mul_overflow (x, y, &res); + return res; +} + +/* MUL_OVERFLOW should not be folded into unsigned multiplication, + because it sometimes overflows and sometimes does not. */ +__attribute__((noinline, noclone)) signed char +fn2 (long int x, long int y, int *ovf) +{ + signed char res; + x = (x & 63) + (__SCHAR_MAX__ / 4); + y = (y & 3) + 4; + *ovf = __builtin_mul_overflow (x, y, &res); + return res; +} + +/* ADD_OVERFLOW should be folded into unsigned additrion, + because it sometimes overflows and sometimes does not. */ +__attribute__((noinline, noclone)) unsigned char +fn3 (unsigned char x, unsigned char y, int *ovf) +{ + unsigned char res; + x = (x & 63) + ((unsigned char) ~0 - 65); + y = (y & 3); + *ovf = __builtin_add_overflow (x, y, &res); + return res; +} + +/* ADD_OVERFLOW should be folded into unsigned additrion, + because it sometimes overflows and sometimes does not. */ +__attribute__((noinline, noclone)) unsigned char +fn4 (unsigned char x, unsigned char y, int *ovf) +{ + unsigned char res; + x = (x & 15) + ((unsigned char) ~0 - 16); + y = (y & 3) + 16; + *ovf = __builtin_add_overflow (x, y, &res); + return res; +} + +/* MUL_OVERFLOW should not be folded into unsigned multiplication, + because it sometimes overflows and sometimes does not. */ +__attribute__((noinline, noclone)) long int +fn5 (long int x, unsigned long int y, int *ovf) +{ + long int res; + y = -65536UL + (y & 65535); + *ovf = __builtin_mul_overflow (x, y, &res); + return res; +} + +int +main () +{ + int ovf; + if (fn1 (0, 0, &ovf) != 0 + || ovf + || fn1 (65535, 0, &ovf) != (long int) ((__LONG_MAX__ / 65535 + 32768UL) * -65535UL) + || !ovf) + __builtin_abort (); + if (fn2 (0, 0, &ovf) != (signed char) (__SCHAR_MAX__ / 4 * 4U) + || ovf + || fn2 (0, 1, &ovf) != (signed char) (__SCHAR_MAX__ / 4 * 5U) + || !ovf) + __builtin_abort (); + if (fn3 (0, 0, &ovf) != (unsigned char) ~0 - 65 + || ovf + || fn3 (63, 2, &ovf) != (unsigned char) ~0 + || ovf + || fn3 (62, 3, &ovf) != (unsigned char) ~0 + || ovf + || fn3 (63, 3, &ovf) != 0 + || !ovf) + __builtin_abort (); + if (fn4 (0, 0, &ovf) != (unsigned char) ~0 + || ovf + || fn4 (1, 0, &ovf) != 0 + || !ovf + || fn4 (0, 1, &ovf) != 0 + || !ovf + || fn4 (63, 3, &ovf) != 17 + || !ovf) + __builtin_abort (); + if (fn5 (0, 0, &ovf) != 0 + || ovf + || fn5 (1, 0, &ovf) != -65536L + || !ovf + || fn5 (2, 32768, &ovf) != -65536L + || !ovf + || fn5 (4, 32768 + 16384 + 8192, &ovf) != -32768L + || !ovf) + __builtin_abort (); + return 0; +} + +/* { dg-final { scan-tree-dump-times "ADD_OVERFLOW" 2 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "SUB_OVERFLOW" 0 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "MUL_OVERFLOW" 3 "optimized" } } */ +/* { dg-final { cleanup-tree-dump "optimized" } } */ diff --git a/gcc/tree-ssa-dce.c b/gcc/tree-ssa-dce.c index 923a0341fad..6543dc7d26a 100644 --- a/gcc/tree-ssa-dce.c +++ b/gcc/tree-ssa-dce.c @@ -85,6 +85,8 @@ along with GCC; see the file COPYING3. If not see #include "cfgloop.h" #include "tree-scalar-evolution.h" #include "tree-chkp.h" +#include "tree-ssa-propagate.h" +#include "gimple-fold.h" static struct stmt_stats { @@ -1162,6 +1164,109 @@ remove_dead_stmt (gimple_stmt_iterator *i, basic_block bb) release_defs (stmt); } +/* Helper for maybe_optimize_arith_overflow. Find in *TP if there are any + uses of data (SSA_NAME) other than REALPART_EXPR referencing it. */ + +static tree +find_non_realpart_uses (tree *tp, int *walk_subtrees, void *data) +{ + if (TYPE_P (*tp) || TREE_CODE (*tp) == REALPART_EXPR) + *walk_subtrees = 0; + if (*tp == (tree) data) + return *tp; + return NULL_TREE; +} + +/* If the IMAGPART_EXPR of the {ADD,SUB,MUL}_OVERFLOW result is never used, + but REALPART_EXPR is, optimize the {ADD,SUB,MUL}_OVERFLOW internal calls + into plain unsigned {PLUS,MINUS,MULT}_EXPR, and if needed reset debug + uses. */ + +static void +maybe_optimize_arith_overflow (gimple_stmt_iterator *gsi, + enum tree_code subcode) +{ + gimple stmt = gsi_stmt (*gsi); + tree lhs = gimple_call_lhs (stmt); + + if (lhs == NULL || TREE_CODE (lhs) != SSA_NAME) + return; + + imm_use_iterator imm_iter; + use_operand_p use_p; + bool has_debug_uses = false; + bool has_realpart_uses = false; + bool has_other_uses = false; + FOR_EACH_IMM_USE_FAST (use_p, imm_iter, lhs) + { + gimple use_stmt = USE_STMT (use_p); + if (is_gimple_debug (use_stmt)) + has_debug_uses = true; + else if (is_gimple_assign (use_stmt) + && gimple_assign_rhs_code (use_stmt) == REALPART_EXPR + && TREE_OPERAND (gimple_assign_rhs1 (use_stmt), 0) == lhs) + has_realpart_uses = true; + else + { + has_other_uses = true; + break; + } + } + + if (!has_realpart_uses || has_other_uses) + return; + + tree arg0 = gimple_call_arg (stmt, 0); + tree arg1 = gimple_call_arg (stmt, 1); + location_t loc = gimple_location (stmt); + tree type = TREE_TYPE (TREE_TYPE (lhs)); + tree utype = type; + if (!TYPE_UNSIGNED (type)) + utype = build_nonstandard_integer_type (TYPE_PRECISION (type), 1); + tree result = fold_build2_loc (loc, subcode, utype, + fold_convert_loc (loc, utype, arg0), + fold_convert_loc (loc, utype, arg1)); + result = fold_convert_loc (loc, type, result); + + if (has_debug_uses) + { + gimple use_stmt; + FOR_EACH_IMM_USE_STMT (use_stmt, imm_iter, lhs) + { + if (!gimple_debug_bind_p (use_stmt)) + continue; + tree v = gimple_debug_bind_get_value (use_stmt); + if (walk_tree (&v, find_non_realpart_uses, lhs, NULL)) + { + gimple_debug_bind_reset_value (use_stmt); + update_stmt (use_stmt); + } + } + } + + if (TREE_CODE (result) == INTEGER_CST && TREE_OVERFLOW (result)) + result = drop_tree_overflow (result); + tree overflow = build_zero_cst (type); + tree ctype = build_complex_type (type); + if (TREE_CODE (result) == INTEGER_CST) + result = build_complex (ctype, result, overflow); + else + result = build2_loc (gimple_location (stmt), COMPLEX_EXPR, + ctype, result, overflow); + + if (dump_file && (dump_flags & TDF_DETAILS)) + { + fprintf (dump_file, "Transforming call: "); + print_gimple_stmt (dump_file, stmt, 0, TDF_SLIM); + fprintf (dump_file, "because the overflow result is never used into: "); + print_generic_stmt (dump_file, result, TDF_SLIM); + fprintf (dump_file, "\n"); + } + + if (!update_call_from_tree (gsi, result)) + gimplify_and_update_call_from_tree (gsi, result); +} + /* Eliminate unnecessary statements. Any instruction not marked as necessary contributes nothing to the program, and can be deleted. */ @@ -1298,6 +1403,21 @@ eliminate_unnecessary_stmts (void) update_stmt (stmt); release_ssa_name (name); } + else if (gimple_call_internal_p (stmt)) + switch (gimple_call_internal_fn (stmt)) + { + case IFN_ADD_OVERFLOW: + maybe_optimize_arith_overflow (&gsi, PLUS_EXPR); + break; + case IFN_SUB_OVERFLOW: + maybe_optimize_arith_overflow (&gsi, MINUS_EXPR); + break; + case IFN_MUL_OVERFLOW: + maybe_optimize_arith_overflow (&gsi, MULT_EXPR); + break; + default: + break; + } } } } diff --git a/gcc/tree-vrp.c b/gcc/tree-vrp.c index f0a4382f5d8..b2872828334 100644 --- a/gcc/tree-vrp.c +++ b/gcc/tree-vrp.c @@ -3754,6 +3754,113 @@ extract_range_from_comparison (value_range_t *vr, enum tree_code code, set_value_range_to_truthvalue (vr, type); } +/* Helper function for simplify_internal_call_using_ranges and + extract_range_basic. Return true if OP0 SUBCODE OP1 for + SUBCODE {PLUS,MINUS,MULT}_EXPR is known to never overflow or + always overflow. Set *OVF to true if it is known to always + overflow. */ + +static bool +check_for_binary_op_overflow (enum tree_code subcode, tree type, + tree op0, tree op1, bool *ovf) +{ + value_range_t vr0 = VR_INITIALIZER; + value_range_t vr1 = VR_INITIALIZER; + if (TREE_CODE (op0) == SSA_NAME) + vr0 = *get_value_range (op0); + else if (TREE_CODE (op0) == INTEGER_CST) + set_value_range_to_value (&vr0, op0, NULL); + else + set_value_range_to_varying (&vr0); + + if (TREE_CODE (op1) == SSA_NAME) + vr1 = *get_value_range (op1); + else if (TREE_CODE (op1) == INTEGER_CST) + set_value_range_to_value (&vr1, op1, NULL); + else + set_value_range_to_varying (&vr1); + + if (!range_int_cst_p (&vr0) + || TREE_OVERFLOW (vr0.min) + || TREE_OVERFLOW (vr0.max)) + { + vr0.min = vrp_val_min (TREE_TYPE (op0)); + vr0.max = vrp_val_max (TREE_TYPE (op0)); + } + if (!range_int_cst_p (&vr1) + || TREE_OVERFLOW (vr1.min) + || TREE_OVERFLOW (vr1.max)) + { + vr1.min = vrp_val_min (TREE_TYPE (op1)); + vr1.max = vrp_val_max (TREE_TYPE (op1)); + } + *ovf = arith_overflowed_p (subcode, type, vr0.min, + subcode == MINUS_EXPR ? vr1.max : vr1.min); + if (arith_overflowed_p (subcode, type, vr0.max, + subcode == MINUS_EXPR ? vr1.min : vr1.max) != *ovf) + return false; + if (subcode == MULT_EXPR) + { + if (arith_overflowed_p (subcode, type, vr0.min, vr1.max) != *ovf + || arith_overflowed_p (subcode, type, vr0.max, vr1.min) != *ovf) + return false; + } + if (*ovf) + { + /* So far we found that there is an overflow on the boundaries. + That doesn't prove that there is an overflow even for all values + in between the boundaries. For that compute widest_int range + of the result and see if it doesn't overlap the range of + type. */ + widest_int wmin, wmax; + widest_int w[4]; + int i; + w[0] = wi::to_widest (vr0.min); + w[1] = wi::to_widest (vr0.max); + w[2] = wi::to_widest (vr1.min); + w[3] = wi::to_widest (vr1.max); + for (i = 0; i < 4; i++) + { + widest_int wt; + switch (subcode) + { + case PLUS_EXPR: + wt = wi::add (w[i & 1], w[2 + (i & 2) / 2]); + break; + case MINUS_EXPR: + wt = wi::sub (w[i & 1], w[2 + (i & 2) / 2]); + break; + case MULT_EXPR: + wt = wi::mul (w[i & 1], w[2 + (i & 2) / 2]); + break; + default: + gcc_unreachable (); + } + if (i == 0) + { + wmin = wt; + wmax = wt; + } + else + { + wmin = wi::smin (wmin, wt); + wmax = wi::smax (wmax, wt); + } + } + /* The result of op0 CODE op1 is known to be in range + [wmin, wmax]. */ + widest_int wtmin = wi::to_widest (vrp_val_min (type)); + widest_int wtmax = wi::to_widest (vrp_val_max (type)); + /* If all values in [wmin, wmax] are smaller than + [wtmin, wtmax] or all are larger than [wtmin, wtmax], + the arithmetic operation will always overflow. */ + if (wi::lts_p (wmax, wtmin) || wi::gts_p (wmin, wtmax)) + return true; + return false; + } + return true; +} + /* Try to derive a nonnegative or nonzero range out of STMT relying primarily on generic routines in fold in conjunction with range data. Store the result in *VR */ @@ -3943,8 +4050,7 @@ extract_range_basic (value_range_t *vr, gimple stmt) break; } } - else if (is_gimple_call (stmt) - && gimple_call_internal_p (stmt)) + else if (is_gimple_call (stmt) && gimple_call_internal_p (stmt)) { enum tree_code subcode = ERROR_MARK; switch (gimple_call_internal_fn (stmt)) @@ -3984,6 +4090,84 @@ extract_range_basic (value_range_t *vr, gimple stmt) return; } } + /* Handle extraction of the two results (result of arithmetics and + a flag whether arithmetics overflowed) from {ADD,SUB,MUL}_OVERFLOW + internal function. */ + else if (is_gimple_assign (stmt) + && (gimple_assign_rhs_code (stmt) == REALPART_EXPR + || gimple_assign_rhs_code (stmt) == IMAGPART_EXPR) + && INTEGRAL_TYPE_P (type)) + { + enum tree_code code = gimple_assign_rhs_code (stmt); + tree op = gimple_assign_rhs1 (stmt); + if (TREE_CODE (op) == code && TREE_CODE (TREE_OPERAND (op, 0)) == SSA_NAME) + { + gimple g = SSA_NAME_DEF_STMT (TREE_OPERAND (op, 0)); + if (is_gimple_call (g) && gimple_call_internal_p (g)) + { + enum tree_code subcode = ERROR_MARK; + switch (gimple_call_internal_fn (g)) + { + case IFN_ADD_OVERFLOW: + subcode = PLUS_EXPR; + break; + case IFN_SUB_OVERFLOW: + subcode = MINUS_EXPR; + break; + case IFN_MUL_OVERFLOW: + subcode = MULT_EXPR; + break; + default: + break; + } + if (subcode != ERROR_MARK) + { + tree op0 = gimple_call_arg (g, 0); + tree op1 = gimple_call_arg (g, 1); + if (code == IMAGPART_EXPR) + { + bool ovf = false; + if (check_for_binary_op_overflow (subcode, type, + op0, op1, &ovf)) + set_value_range_to_value (vr, + build_int_cst (type, ovf), + NULL); + else + set_value_range (vr, VR_RANGE, build_int_cst (type, 0), + build_int_cst (type, 1), NULL); + } + else if (types_compatible_p (type, TREE_TYPE (op0)) + && types_compatible_p (type, TREE_TYPE (op1))) + { + bool saved_flag_wrapv = flag_wrapv; + /* Pretend the arithmetics is wrapping. If there is + any overflow, IMAGPART_EXPR will be set. */ + flag_wrapv = 1; + extract_range_from_binary_expr (vr, subcode, type, + op0, op1); + flag_wrapv = saved_flag_wrapv; + } + else + { + value_range_t vr0 = VR_INITIALIZER; + value_range_t vr1 = VR_INITIALIZER; + bool saved_flag_wrapv = flag_wrapv; + /* Pretend the arithmetics is wrapping. If there is + any overflow, IMAGPART_EXPR will be set. */ + flag_wrapv = 1; + extract_range_from_unary_expr (&vr0, NOP_EXPR, + type, op0); + extract_range_from_unary_expr (&vr1, NOP_EXPR, + type, op1); + extract_range_from_binary_expr_1 (vr, subcode, type, + &vr0, &vr1); + flag_wrapv = saved_flag_wrapv; + } + return; + } + } + } + } if (INTEGRAL_TYPE_P (type) && gimple_stmt_nonnegative_warnv_p (stmt, &sop)) set_value_range_to_nonnegative (vr, type, @@ -9419,87 +9603,100 @@ static bool simplify_internal_call_using_ranges (gimple_stmt_iterator *gsi, gimple stmt) { enum tree_code subcode; + bool is_ubsan = false; + bool ovf = false; switch (gimple_call_internal_fn (stmt)) { case IFN_UBSAN_CHECK_ADD: subcode = PLUS_EXPR; + is_ubsan = true; break; case IFN_UBSAN_CHECK_SUB: subcode = MINUS_EXPR; + is_ubsan = true; break; case IFN_UBSAN_CHECK_MUL: subcode = MULT_EXPR; + is_ubsan = true; + break; + case IFN_ADD_OVERFLOW: + subcode = PLUS_EXPR; + break; + case IFN_SUB_OVERFLOW: + subcode = MINUS_EXPR; + break; + case IFN_MUL_OVERFLOW: + subcode = MULT_EXPR; break; default: return false; } - value_range_t vr0 = VR_INITIALIZER; - value_range_t vr1 = VR_INITIALIZER; tree op0 = gimple_call_arg (stmt, 0); tree op1 = gimple_call_arg (stmt, 1); - - if (TREE_CODE (op0) == SSA_NAME) - vr0 = *get_value_range (op0); - else if (TREE_CODE (op0) == INTEGER_CST) - set_value_range_to_value (&vr0, op0, NULL); - else - set_value_range_to_varying (&vr0); - - if (TREE_CODE (op1) == SSA_NAME) - vr1 = *get_value_range (op1); - else if (TREE_CODE (op1) == INTEGER_CST) - set_value_range_to_value (&vr1, op1, NULL); + tree type; + if (is_ubsan) + type = TREE_TYPE (op0); + else if (gimple_call_lhs (stmt) == NULL_TREE) + return false; else - set_value_range_to_varying (&vr1); + type = TREE_TYPE (TREE_TYPE (gimple_call_lhs (stmt))); + if (!check_for_binary_op_overflow (subcode, type, op0, op1, &ovf) + || (is_ubsan && ovf)) + return false; - if (!range_int_cst_p (&vr0)) - { - /* If one range is VR_ANTI_RANGE, VR_VARYING etc., - optimize at least x = y + 0; x = y - 0; x = y * 0; - and x = y * 1; which never overflow. */ - if (!range_int_cst_p (&vr1)) - return false; - if (tree_int_cst_sgn (vr1.min) == -1) - return false; - if (compare_tree_int (vr1.max, subcode == MULT_EXPR) == 1) - return false; - } - else if (!range_int_cst_p (&vr1)) - { - /* If one range is VR_ANTI_RANGE, VR_VARYING etc., - optimize at least x = 0 + y; x = 0 * y; and x = 1 * y; - which never overflow. */ - if (subcode == MINUS_EXPR) - return false; - if (!range_int_cst_p (&vr0)) - return false; - if (tree_int_cst_sgn (vr0.min) == -1) - return false; - if (compare_tree_int (vr0.max, subcode == MULT_EXPR) == 1) - return false; - } + gimple g; + location_t loc = gimple_location (stmt); + if (is_ubsan) + g = gimple_build_assign_with_ops (subcode, gimple_call_lhs (stmt), + op0, op1); else { - tree r1 = int_const_binop (subcode, vr0.min, - subcode == MINUS_EXPR ? vr1.max : vr1.min); - tree r2 = int_const_binop (subcode, vr0.max, - subcode == MINUS_EXPR ? vr1.min : vr1.max); - if (r1 == NULL_TREE || TREE_OVERFLOW (r1) - || r2 == NULL_TREE || TREE_OVERFLOW (r2)) - return false; - if (subcode == MULT_EXPR) - { - tree r3 = int_const_binop (subcode, vr0.min, vr1.max); - tree r4 = int_const_binop (subcode, vr0.max, vr1.min); - if (r3 == NULL_TREE || TREE_OVERFLOW (r3) - || r4 == NULL_TREE || TREE_OVERFLOW (r4)) - return false; + int prec = TYPE_PRECISION (type); + tree utype = type; + if (ovf + || !useless_type_conversion_p (type, TREE_TYPE (op0)) + || !useless_type_conversion_p (type, TREE_TYPE (op1))) + utype = build_nonstandard_integer_type (prec, 1); + if (TREE_CODE (op0) == INTEGER_CST) + op0 = fold_convert (utype, op0); + else if (!useless_type_conversion_p (utype, TREE_TYPE (op0))) + { + g = gimple_build_assign_with_ops (NOP_EXPR, + make_ssa_name (utype, NULL), + op0, NULL_TREE); + gimple_set_location (g, loc); + gsi_insert_before (gsi, g, GSI_SAME_STMT); + op0 = gimple_assign_lhs (g); } - } - - gimple g = gimple_build_assign_with_ops (subcode, gimple_call_lhs (stmt), - op0, op1); + if (TREE_CODE (op1) == INTEGER_CST) + op1 = fold_convert (utype, op1); + else if (!useless_type_conversion_p (utype, TREE_TYPE (op1))) + { + g = gimple_build_assign_with_ops (NOP_EXPR, + make_ssa_name (utype, NULL), + op1, NULL_TREE); + gimple_set_location (g, loc); + gsi_insert_before (gsi, g, GSI_SAME_STMT); + op1 = gimple_assign_lhs (g); + } + g = gimple_build_assign_with_ops (subcode, make_ssa_name (utype, NULL), + op0, op1); + gimple_set_location (g, loc); + gsi_insert_before (gsi, g, GSI_SAME_STMT); + if (utype != type) + { + g = gimple_build_assign_with_ops (NOP_EXPR, + make_ssa_name (type, NULL), + gimple_assign_lhs (g), NULL_TREE); + gimple_set_location (g, loc); + gsi_insert_before (gsi, g, GSI_SAME_STMT); + } + g = gimple_build_assign_with_ops (COMPLEX_EXPR, gimple_call_lhs (stmt), + gimple_assign_lhs (g), + build_int_cst (type, ovf)); + } + gimple_set_location (g, loc); gsi_replace (gsi, g, false); return true; } |