> On Aug 16, 2021, at 2:40 AM, Richard Biener <rguent...@suse.de> wrote:
>
> On Thu, 12 Aug 2021, Qing Zhao wrote:
>
>> Hi, Richard,
>>
>> For RTL expansion of call to .DEFERRED_INIT, I changed my code per your
>> suggestions like following:
>>
>> ======================
>> #define INIT_PATTERN_VALUE 0xFE
>> static void
>> expand_DEFERRED_INIT (internal_fn, gcall *stmt)
>> {
>> tree lhs = gimple_call_lhs (stmt);
>> tree var_size = gimple_call_arg (stmt, 0);
>> enum auto_init_type init_type
>> = (enum auto_init_type) TREE_INT_CST_LOW (gimple_call_arg (stmt, 1));
>> bool is_vla = (bool) TREE_INT_CST_LOW (gimple_call_arg (stmt, 2));
>>
>> tree var_type = TREE_TYPE (lhs);
>> gcc_assert (init_type > AUTO_INIT_UNINITIALIZED);
>>
>> if (is_vla || (!can_native_interpret_type_p (var_type)))
>> {
>> /* If this is a VLA or the type of the variable cannot be natively
>> interpreted, expand to a memset to initialize it. */
>> if (TREE_CODE (lhs) == SSA_NAME)
>> lhs = SSA_NAME_VAR (lhs);
>> tree var_addr = NULL_TREE;
>> if (is_vla)
>> var_addr = TREE_OPERAND (lhs, 0);
>> else
>> {
>> TREE_ADDRESSABLE (lhs) = 1;
>> var_addr = build_fold_addr_expr (lhs);
>> }
>> tree value = (init_type == AUTO_INIT_PATTERN) ?
>> build_int_cst (unsigned_char_type_node,
>> INIT_PATTERN_VALUE) :
>> build_zero_cst (unsigned_char_type_node);
>> tree m_call = build_call_expr (builtin_decl_implicit (BUILT_IN_MEMSET),
>> 3, var_addr, value, var_size);
>> /* Expand this memset call. */
>> expand_builtin_memset (m_call, NULL_RTX, TYPE_MODE (var_type));
>> }
>> else
>> {
>> /* If this is not a VLA and the type of the variable can be natively
>> interpreted, expand to assignment to generate better code. */
>> tree pattern = NULL_TREE;
>> unsigned HOST_WIDE_INT total_bytes
>> = tree_to_uhwi (TYPE_SIZE_UNIT (var_type));
>>
>> if (init_type == AUTO_INIT_PATTERN)
>> {
>> unsigned char *buf = (unsigned char *) xmalloc (total_bytes);
>> memset (buf, INIT_PATTERN_VALUE, total_bytes);
>> pattern = native_interpret_expr (var_type, buf, total_bytes);
>> gcc_assert (pattern);
>> }
>>
>> tree init = (init_type == AUTO_INIT_PATTERN) ?
>> pattern :
>> build_zero_cst (var_type);
>> expand_assignment (lhs, init, false);
>> }
>> }
>> ===========================
>>
>> Now, I used “can_native_interpret_type_p (var_type)” instead of
>> “use_register_for_decl (lhs)” to decide
>> whether to use “memset” or use “assign” to expand this function.
>>
>> However, this exposed an bug that is very hard to be addressed:
>>
>> *******For the testing case: test suite/gcc.dg/uninit-I.c:
>>
>> /* { dg-do compile } */
>> /* { dg-options "-O2 -Wuninitialized" } */
>>
>> int sys_msgctl (void)
>> {
>> struct { int mode; } setbuf;
>> return setbuf.mode; /* { dg-warning "'setbuf\.mode' is used" } */
>> ==
>>
>> ******the above auto var “setbuf” has “struct” type, which
>> “can_native_interpret_type_p(var_type)” is false, therefore,
>> Expanding this .DEFERRED_INIT call went down the “memset” expansion route.
>>
>> However, this structure type can be fitted into a register, therefore cannot
>> be taken address anymore at this stage, even though I tried:
>>
>> TREE_ADDRESSABLE (lhs) = 1;
>> var_addr = build_fold_addr_expr (lhs);
>>
>> To create an address variable for it, the expansion still failed at expr.c:
>> line 8412:
>> during RTL pass: expand
>> /home/opc/Work/GCC/latest-gcc/gcc/testsuite/gcc.dg/auto-init-uninit-I.c:6:24:
>> internal compiler error: in expand_expr_addr_expr_1, at expr.c:8412
>> 0xd04104 expand_expr_addr_expr_1
>> ../../latest-gcc/gcc/expr.c:8412
>> 0xd04a95 expand_expr_addr_expr
>> ../../latest-gcc/gcc/expr.c:8525
>> 0xd13592 expand_expr_real_1(tree_node*, rtx_def*, machine_mode,
>> expand_modifier, rtx_def**, bool)
>> ../../latest-gcc/gcc/expr.c:11741
>> 0xd05142 expand_expr_real(tree_node*, rtx_def*, machine_mode,
>> expand_modifier, rtx_def**, bool)
>> ../../latest-gcc/gcc/expr.c:8713
>> 0xaed1d3 expand_expr
>> ../../latest-gcc/gcc/expr.h:301
>> 0xaf0d89 get_memory_rtx
>> ../../latest-gcc/gcc/builtins.c:1370
>> 0xafb4fb expand_builtin_memset_args
>> ../../latest-gcc/gcc/builtins.c:4102
>> 0xafacde expand_builtin_memset(tree_node*, rtx_def*, machine_mode)
>> ../../latest-gcc/gcc/builtins.c:3886
>> 0xe97fb3 expand_DEFERRED_INIT
>>
>> ******That’s the major reason why I chose “use_register_for_decl(lhs)” to
>> decide “memset” expansion or “assign” expansion, “memset” expansion
>> needs to take address of the variable, if the variable has been decided to
>> fit into a register, then its address cannot taken anymore at this stage.
>>
>> ******using “can_native_interpret_type_p” did make the “pattern” generation
>> part much cleaner and simpler, however, looks like it didn’t work correctly.
>>
>> Based on this, I’d like to keep my previous implementation by using
>> “use_register_for_decl” to decide whether to take “memset” expansion or
>> “assign” expansion.
>> Therefore, I might still need to keep the “UGLY” implementation of
>> generatting “pattern” constant for different types?
>>
>> Let me know your opinion on this.
>
> Hmm, I think you can use use_register_for_decl(lhs) to decide to use an
> alternate type to generate the pattern (and feed to
> can_native_interpret_type_p) by using
> lang_hooks.type_for_mode (TYPE_MODE (TREE_TYPE (lhs))). You can then
> build the assignment from the pattern as
>
> VIEW_CONVERT <reg-type> (lhs) = pattern_cst;
>
> note that more RTL-expand-ish would be to simply expand 'lhs' and
> see whether it's a REG_P or a MEM_P and decide based on that. Of course
> that no longer allows you to use the high-level expand_assignment
> or memset but you'd need to work on a lower level then.
>
> Richard.
My current code for expand_DEFERRED_INIT is like the following, could you check
and see whether there is any issue for it:
#define INIT_PATTERN_VALUE 0xFE
static void
expand_DEFERRED_INIT (internal_fn, gcall *stmt)
{
tree lhs = gimple_call_lhs (stmt);
tree var_size = gimple_call_arg (stmt, 0);
enum auto_init_type init_type
= (enum auto_init_type) TREE_INT_CST_LOW (gimple_call_arg (stmt, 1));
bool is_vla = (bool) TREE_INT_CST_LOW (gimple_call_arg (stmt, 2));
tree var_type = TREE_TYPE (lhs);
gcc_assert (init_type > AUTO_INIT_UNINITIALIZED);
if (is_vla || (!use_register_for_decl (lhs)))
{
if (TREE_CODE (lhs) == SSA_NAME)
lhs = SSA_NAME_VAR (lhs);
/* If this is a VLA or the variable is not in register,
expand to a memset to initialize it. */
tree var_addr = NULL_TREE;
if (is_vla)
var_addr = TREE_OPERAND (lhs, 0);
else
{
TREE_ADDRESSABLE (lhs) = 1;
var_addr = build_fold_addr_expr (lhs);
}
tree value = (init_type == AUTO_INIT_PATTERN) ?
build_int_cst (unsigned_char_type_node,
INIT_PATTERN_VALUE) :
build_zero_cst (unsigned_char_type_node);
tree m_call = build_call_expr (builtin_decl_implicit (BUILT_IN_MEMSET),
3, var_addr, value, var_size);
/* Expand this memset call. */
expand_builtin_memset (m_call, NULL_RTX, TYPE_MODE (var_type));
}
else
{
/* If this variable is in a register, use expand_assignment might
generate better code. */
tree pattern = NULL_TREE;
unsigned HOST_WIDE_INT total_bytes
= tree_to_uhwi (TYPE_SIZE_UNIT (var_type));
if (init_type == AUTO_INIT_PATTERN)
{
if (can_native_interpret_type_p (var_type))
{
unsigned char *buf = (unsigned char *) xmalloc (total_bytes);
memset (buf, INIT_PATTERN_VALUE, total_bytes);
pattern = native_interpret_expr (var_type, buf, total_bytes);
gcc_assert (pattern);
}
else
{
tree index_type = build_index_type (size_int (total_bytes - 1));
tree array_type = build_array_type (unsigned_char_type_node,
index_type);
tree element = build_int_cst (unsigned_char_type_node,
INIT_PATTERN_VALUE);
vec<constructor_elt, va_gc> *elts = NULL;
for (unsigned int i = 0; i < total_bytes; i++)
CONSTRUCTOR_APPEND_ELT (elts, NULL_TREE, element);
pattern = build_constructor (array_type, elts);
pattern = build1 (VIEW_CONVERT_EXPR, var_type, pattern);
}
}
tree init = (init_type == AUTO_INIT_PATTERN) ?
pattern :
build_zero_cst (var_type);
expand_assignment (lhs, init, false);
}
}
Thanks.
Qing
