#include "diagnostic.h"
#include "ssaexpand.h"
#include "target-globals.h"
+#include "params.h"
/* Decide whether a function's arguments should be processed
from first to last or from last to first.
HOST_WIDE_INT, enum machine_mode,
tree, tree, int, alias_set_type);
static void store_constructor (tree, rtx, int, HOST_WIDE_INT);
-static rtx store_field (rtx, HOST_WIDE_INT, HOST_WIDE_INT, enum machine_mode,
+static rtx store_field (rtx, HOST_WIDE_INT, HOST_WIDE_INT,
+ unsigned HOST_WIDE_INT, unsigned HOST_WIDE_INT,
+ enum machine_mode,
tree, tree, alias_set_type, bool);
static unsigned HOST_WIDE_INT highest_pow2_factor_for_target (const_tree, const_tree);
TO here. */
if (GET_CODE (from) == SUBREG && SUBREG_PROMOTED_VAR_P (from)
- && (GET_MODE_SIZE (GET_MODE (SUBREG_REG (from)))
- >= GET_MODE_SIZE (to_mode))
+ && (GET_MODE_PRECISION (GET_MODE (SUBREG_REG (from)))
+ >= GET_MODE_PRECISION (to_mode))
&& SUBREG_PROMOTED_UNSIGNED_P (from) == unsignedp)
from = gen_lowpart (to_mode, from), from_mode = to_mode;
/* Now both modes are integers. */
/* Handle expanding beyond a word. */
- if (GET_MODE_BITSIZE (from_mode) < GET_MODE_BITSIZE (to_mode)
- && GET_MODE_BITSIZE (to_mode) > BITS_PER_WORD)
+ if (GET_MODE_PRECISION (from_mode) < GET_MODE_PRECISION (to_mode)
+ && GET_MODE_PRECISION (to_mode) > BITS_PER_WORD)
{
rtx insns;
rtx lowpart;
return;
}
/* Next, try converting via full word. */
- else if (GET_MODE_BITSIZE (from_mode) < BITS_PER_WORD
+ else if (GET_MODE_PRECISION (from_mode) < BITS_PER_WORD
&& ((code = can_extend_p (to_mode, word_mode, unsignedp))
!= CODE_FOR_nothing))
{
from = force_reg (from_mode, from);
/* Get a copy of FROM widened to a word, if necessary. */
- if (GET_MODE_BITSIZE (from_mode) < BITS_PER_WORD)
+ if (GET_MODE_PRECISION (from_mode) < BITS_PER_WORD)
lowpart_mode = word_mode;
else
lowpart_mode = from_mode;
}
/* Truncating multi-word to a word or less. */
- if (GET_MODE_BITSIZE (from_mode) > BITS_PER_WORD
- && GET_MODE_BITSIZE (to_mode) <= BITS_PER_WORD)
+ if (GET_MODE_PRECISION (from_mode) > BITS_PER_WORD
+ && GET_MODE_PRECISION (to_mode) <= BITS_PER_WORD)
{
if (!((MEM_P (from)
&& ! MEM_VOLATILE_P (from)
}
/* Handle extension. */
- if (GET_MODE_BITSIZE (to_mode) > GET_MODE_BITSIZE (from_mode))
+ if (GET_MODE_PRECISION (to_mode) > GET_MODE_PRECISION (from_mode))
{
/* Convert directly if that works. */
if ((code = can_extend_p (to_mode, from_mode, unsignedp))
/* No suitable intermediate mode.
Generate what we need with shifts. */
- shift_amount = (GET_MODE_BITSIZE (to_mode)
- - GET_MODE_BITSIZE (from_mode));
+ shift_amount = (GET_MODE_PRECISION (to_mode)
+ - GET_MODE_PRECISION (from_mode));
from = gen_lowpart (to_mode, force_reg (from_mode, from));
tmp = expand_shift (LSHIFT_EXPR, to_mode, from, shift_amount,
to, unsignedp);
??? Code above formerly short-circuited this, for most integer
mode pairs, with a force_reg in from_mode followed by a recursive
call to this routine. Appears always to have been wrong. */
- if (GET_MODE_BITSIZE (to_mode) < GET_MODE_BITSIZE (from_mode))
+ if (GET_MODE_PRECISION (to_mode) < GET_MODE_PRECISION (from_mode))
{
rtx temp = force_reg (to_mode, gen_lowpart (to_mode, from));
emit_move_insn (to, temp);
wider than HOST_BITS_PER_WIDE_INT, we must be narrowing the operand. */
if ((CONST_INT_P (x)
- && GET_MODE_BITSIZE (mode) <= HOST_BITS_PER_WIDE_INT)
+ && GET_MODE_PRECISION (mode) <= HOST_BITS_PER_WIDE_INT)
|| (GET_MODE_CLASS (mode) == MODE_INT
&& GET_MODE_CLASS (oldmode) == MODE_INT
&& (GET_CODE (x) == CONST_DOUBLE
- || (GET_MODE_SIZE (mode) <= GET_MODE_SIZE (oldmode)
+ || (GET_MODE_PRECISION (mode) <= GET_MODE_PRECISION (oldmode)
&& ((MEM_P (x) && ! MEM_VOLATILE_P (x)
&& direct_load[(int) mode])
|| (REG_P (x)
X does not need sign- or zero-extension. This may not be
the case, but it's the best we can do. */
if (CONST_INT_P (x) && oldmode != VOIDmode
- && GET_MODE_SIZE (mode) > GET_MODE_SIZE (oldmode))
+ && GET_MODE_PRECISION (mode) > GET_MODE_PRECISION (oldmode))
{
HOST_WIDE_INT val = INTVAL (x);
{
x = shallow_copy_rtx (x);
y = shallow_copy_rtx (y);
- set_mem_size (x, size);
- set_mem_size (y, size);
+ set_mem_size (x, INTVAL (size));
+ set_mem_size (y, INTVAL (size));
}
if (CONST_INT_P (size) && MOVE_BY_PIECES_P (INTVAL (size), align))
emit_move_insn (adjust_address (dest, mode, bytepos), tmps[i]);
else
store_bit_field (dest, bytelen * BITS_PER_UNIT, bytepos * BITS_PER_UNIT,
- mode, tmps[i]);
+ 0, 0, mode, tmps[i]);
}
/* Copy from the pseudo into the (probable) hard reg. */
/* Use xbitpos for the source extraction (right justified) and
bitpos for the destination store (left justified). */
- store_bit_field (dst, bitsize, bitpos % BITS_PER_WORD, copy_mode,
+ store_bit_field (dst, bitsize, bitpos % BITS_PER_WORD, 0, 0, copy_mode,
extract_bit_field (src, bitsize,
xbitpos % BITS_PER_WORD, 1, false,
NULL_RTX, copy_mode, copy_mode));
gcc_assert (MEM_P (cplx) && ibitsize < BITS_PER_WORD);
}
- store_bit_field (cplx, ibitsize, imag_p ? ibitsize : 0, imode, val);
+ store_bit_field (cplx, ibitsize, imag_p ? ibitsize : 0, 0, 0, imode, val);
}
/* Extract one of the components of the complex value CPLX. Extract the
return memory_address (GET_CLASS_NARROWEST_MODE (MODE_INT), temp);
}
-#ifdef PUSH_ROUNDING
+/* A utility routine that returns the base of an auto-inc memory, or NULL. */
+
+static rtx
+mem_autoinc_base (rtx mem)
+{
+ if (MEM_P (mem))
+ {
+ rtx addr = XEXP (mem, 0);
+ if (GET_RTX_CLASS (GET_CODE (addr)) == RTX_AUTOINC)
+ return XEXP (addr, 0);
+ }
+ return NULL;
+}
+
+/* A utility routine used here, in reload, and in try_split. The insns
+ after PREV up to and including LAST are known to adjust the stack,
+ with a final value of END_ARGS_SIZE. Iterate backward from LAST
+ placing notes as appropriate. PREV may be NULL, indicating the
+ entire insn sequence prior to LAST should be scanned.
+
+ The set of allowed stack pointer modifications is small:
+ (1) One or more auto-inc style memory references (aka pushes),
+ (2) One or more addition/subtraction with the SP as destination,
+ (3) A single move insn with the SP as destination,
+ (4) A call_pop insn.
+
+ Insns in the sequence that do not modify the SP are ignored.
+
+ The return value is the amount of adjustment that can be trivially
+ verified, via immediate operand or auto-inc. If the adjustment
+ cannot be trivially extracted, the return value is INT_MIN. */
+
+int
+fixup_args_size_notes (rtx prev, rtx last, int end_args_size)
+{
+ int args_size = end_args_size;
+ bool saw_unknown = false;
+ rtx insn;
+
+ for (insn = last; insn != prev; insn = PREV_INSN (insn))
+ {
+ rtx dest, set, pat;
+ HOST_WIDE_INT this_delta = 0;
+ int i;
+ if (!NONDEBUG_INSN_P (insn))
+ continue;
+ pat = PATTERN (insn);
+ set = NULL;
+
+ /* Look for a call_pop pattern. */
+ if (CALL_P (insn))
+ {
+ /* We're not supposed to see non-pop call patterns here. */
+ gcc_assert (GET_CODE (pat) == PARALLEL);
+
+ /* All call_pop have a stack pointer adjust in the parallel.
+ The call itself is always first, and the stack adjust is
+ usually last, so search from the end. */
+ for (i = XVECLEN (pat, 0) - 1; i > 0; --i)
+ {
+ set = XVECEXP (pat, 0, i);
+ if (GET_CODE (set) != SET)
+ continue;
+ dest = SET_DEST (set);
+ if (dest == stack_pointer_rtx)
+ break;
+ }
+ /* We'd better have found the stack pointer adjust. */
+ gcc_assert (i > 0);
+ /* Fall through to process the extracted SET and DEST
+ as if it was a standalone insn. */
+ }
+ else if (GET_CODE (pat) == SET)
+ set = pat;
+ else if ((set = single_set (insn)) != NULL)
+ ;
+ else if (GET_CODE (pat) == PARALLEL)
+ {
+ /* ??? Some older ports use a parallel with a stack adjust
+ and a store for a PUSH_ROUNDING pattern, rather than a
+ PRE/POST_MODIFY rtx. Don't force them to update yet... */
+ /* ??? See h8300 and m68k, pushqi1. */
+ for (i = XVECLEN (pat, 0) - 1; i >= 0; --i)
+ {
+ set = XVECEXP (pat, 0, i);
+ if (GET_CODE (set) != SET)
+ continue;
+ dest = SET_DEST (set);
+ if (dest == stack_pointer_rtx)
+ break;
+
+ /* We do not expect an auto-inc of the sp in the parallel. */
+ gcc_checking_assert (mem_autoinc_base (dest)
+ != stack_pointer_rtx);
+ gcc_checking_assert (mem_autoinc_base (SET_SRC (set))
+ != stack_pointer_rtx);
+ }
+ if (i < 0)
+ continue;
+ }
+ else
+ continue;
+ dest = SET_DEST (set);
+
+ /* Look for direct modifications of the stack pointer. */
+ if (dest == stack_pointer_rtx)
+ {
+ gcc_assert (!saw_unknown);
+ /* Look for a trivial adjustment, otherwise assume nothing. */
+ if (GET_CODE (SET_SRC (set)) == PLUS
+ && XEXP (SET_SRC (set), 0) == stack_pointer_rtx
+ && CONST_INT_P (XEXP (SET_SRC (set), 1)))
+ this_delta = INTVAL (XEXP (SET_SRC (set), 1));
+ else
+ saw_unknown = true;
+ }
+ /* Otherwise only think about autoinc patterns. */
+ else if (mem_autoinc_base (dest) == stack_pointer_rtx)
+ {
+ rtx addr = XEXP (dest, 0);
+ gcc_assert (!saw_unknown);
+ switch (GET_CODE (addr))
+ {
+ case PRE_INC:
+ case POST_INC:
+ this_delta = GET_MODE_SIZE (GET_MODE (dest));
+ break;
+ case PRE_DEC:
+ case POST_DEC:
+ this_delta = -GET_MODE_SIZE (GET_MODE (dest));
+ break;
+ case PRE_MODIFY:
+ case POST_MODIFY:
+ addr = XEXP (addr, 1);
+ gcc_assert (GET_CODE (addr) == PLUS);
+ gcc_assert (XEXP (addr, 0) == stack_pointer_rtx);
+ gcc_assert (CONST_INT_P (XEXP (addr, 1)));
+ this_delta = INTVAL (XEXP (addr, 1));
+ break;
+ default:
+ gcc_unreachable ();
+ }
+ }
+ else
+ continue;
+
+ add_reg_note (insn, REG_ARGS_SIZE, GEN_INT (args_size));
+#ifdef STACK_GROWS_DOWNWARD
+ this_delta = -this_delta;
+#endif
+ args_size -= this_delta;
+ }
+
+ return saw_unknown ? INT_MIN : args_size;
+}
+
+#ifdef PUSH_ROUNDING
/* Emit single push insn. */
static void
-emit_single_push_insn (enum machine_mode mode, rtx x, tree type)
+emit_single_push_insn_1 (enum machine_mode mode, rtx x, tree type)
{
rtx dest_addr;
unsigned rounded_size = PUSH_ROUNDING (GET_MODE_SIZE (mode));
}
emit_move_insn (dest, x);
}
+
+/* Emit and annotate a single push insn. */
+
+static void
+emit_single_push_insn (enum machine_mode mode, rtx x, tree type)
+{
+ int delta, old_delta = stack_pointer_delta;
+ rtx prev = get_last_insn ();
+ rtx last;
+
+ emit_single_push_insn_1 (mode, x, type);
+
+ last = get_last_insn ();
+
+ /* Notice the common case where we emitted exactly one insn. */
+ if (PREV_INSN (last) == prev)
+ {
+ add_reg_note (last, REG_ARGS_SIZE, GEN_INT (stack_pointer_delta));
+ return;
+ }
+
+ delta = fixup_args_size_notes (prev, last, stack_pointer_delta);
+ gcc_assert (delta == INT_MIN || delta == old_delta);
+}
#endif
/* Generate code to push X onto the stack, assuming it has mode MODE and
static bool
optimize_bitfield_assignment_op (unsigned HOST_WIDE_INT bitsize,
unsigned HOST_WIDE_INT bitpos,
+ unsigned HOST_WIDE_INT bitregion_start,
+ unsigned HOST_WIDE_INT bitregion_end,
enum machine_mode mode1, rtx str_rtx,
tree to, tree src)
{
if (str_bitsize == 0 || str_bitsize > BITS_PER_WORD)
str_mode = word_mode;
str_mode = get_best_mode (bitsize, bitpos,
+ bitregion_start, bitregion_end,
MEM_ALIGN (str_rtx), str_mode, 0);
if (str_mode == VOIDmode)
return false;
return false;
}
+/* In the C++ memory model, consecutive bit fields in a structure are
+ considered one memory location.
+
+ Given a COMPONENT_REF, this function returns the bit range of
+ consecutive bits in which this COMPONENT_REF belongs in. The
+ values are returned in *BITSTART and *BITEND. If either the C++
+ memory model is not activated, or this memory access is not thread
+ visible, 0 is returned in *BITSTART and *BITEND.
+
+ EXP is the COMPONENT_REF.
+ INNERDECL is the actual object being referenced.
+ BITPOS is the position in bits where the bit starts within the structure.
+ BITSIZE is size in bits of the field being referenced in EXP.
+
+ For example, while storing into FOO.A here...
+
+ struct {
+ BIT 0:
+ unsigned int a : 4;
+ unsigned int b : 1;
+ BIT 8:
+ unsigned char c;
+ unsigned int d : 6;
+ } foo;
+
+ ...we are not allowed to store past <b>, so for the layout above, a
+ range of 0..7 (because no one cares if we store into the
+ padding). */
+
+static void
+get_bit_range (unsigned HOST_WIDE_INT *bitstart,
+ unsigned HOST_WIDE_INT *bitend,
+ tree exp, tree innerdecl,
+ HOST_WIDE_INT bitpos, HOST_WIDE_INT bitsize)
+{
+ tree field, record_type, fld;
+ bool found_field = false;
+ bool prev_field_is_bitfield;
+
+ gcc_assert (TREE_CODE (exp) == COMPONENT_REF);
+
+ /* If other threads can't see this value, no need to restrict stores. */
+ if (ALLOW_STORE_DATA_RACES
+ || ((TREE_CODE (innerdecl) == MEM_REF
+ || TREE_CODE (innerdecl) == TARGET_MEM_REF)
+ && !ptr_deref_may_alias_global_p (TREE_OPERAND (innerdecl, 0)))
+ || (DECL_P (innerdecl)
+ && (DECL_THREAD_LOCAL_P (innerdecl)
+ || !TREE_STATIC (innerdecl))))
+ {
+ *bitstart = *bitend = 0;
+ return;
+ }
+
+ /* Bit field we're storing into. */
+ field = TREE_OPERAND (exp, 1);
+ record_type = DECL_FIELD_CONTEXT (field);
+
+ /* Count the contiguous bitfields for the memory location that
+ contains FIELD. */
+ *bitstart = 0;
+ prev_field_is_bitfield = true;
+ for (fld = TYPE_FIELDS (record_type); fld; fld = DECL_CHAIN (fld))
+ {
+ tree t, offset;
+ enum machine_mode mode;
+ int unsignedp, volatilep;
+
+ if (TREE_CODE (fld) != FIELD_DECL)
+ continue;
+
+ t = build3 (COMPONENT_REF, TREE_TYPE (exp),
+ unshare_expr (TREE_OPERAND (exp, 0)),
+ fld, NULL_TREE);
+ get_inner_reference (t, &bitsize, &bitpos, &offset,
+ &mode, &unsignedp, &volatilep, true);
+
+ if (field == fld)
+ found_field = true;
+
+ if (DECL_BIT_FIELD_TYPE (fld) && bitsize > 0)
+ {
+ if (prev_field_is_bitfield == false)
+ {
+ *bitstart = bitpos;
+ prev_field_is_bitfield = true;
+ }
+ }
+ else
+ {
+ prev_field_is_bitfield = false;
+ if (found_field)
+ break;
+ }
+ }
+ gcc_assert (found_field);
+
+ if (fld)
+ {
+ /* We found the end of the bit field sequence. Include the
+ padding up to the next field and be done. */
+ *bitend = bitpos - 1;
+ }
+ else
+ {
+ /* If this is the last element in the structure, include the padding
+ at the end of structure. */
+ *bitend = TREE_INT_CST_LOW (TYPE_SIZE (record_type)) - 1;
+ }
+}
/* Expand an assignment that stores the value of FROM into TO. If NONTEMPORAL
is true, try generating a nontemporal store. */
{
enum machine_mode mode1;
HOST_WIDE_INT bitsize, bitpos;
+ unsigned HOST_WIDE_INT bitregion_start = 0;
+ unsigned HOST_WIDE_INT bitregion_end = 0;
tree offset;
int unsignedp;
int volatilep = 0;
tem = get_inner_reference (to, &bitsize, &bitpos, &offset, &mode1,
&unsignedp, &volatilep, true);
+ if (TREE_CODE (to) == COMPONENT_REF
+ && DECL_BIT_FIELD_TYPE (TREE_OPERAND (to, 1)))
+ get_bit_range (&bitregion_start, &bitregion_end,
+ to, tem, bitpos, bitsize);
+
/* If we are going to use store_bit_field and extract_bit_field,
make sure to_rtx will be safe for multiple use. */
if (!MEM_P (to_rtx)
&& GET_MODE (to_rtx) != BLKmode
&& (unsigned HOST_WIDE_INT) bitpos
- >= GET_MODE_BITSIZE (GET_MODE (to_rtx)))
+ >= GET_MODE_PRECISION (GET_MODE (to_rtx)))
{
expand_normal (from);
result = NULL;
nontemporal);
else if (bitpos + bitsize <= mode_bitsize / 2)
result = store_field (XEXP (to_rtx, 0), bitsize, bitpos,
+ bitregion_start, bitregion_end,
mode1, from, TREE_TYPE (tem),
get_alias_set (to), nontemporal);
else if (bitpos >= mode_bitsize / 2)
result = store_field (XEXP (to_rtx, 1), bitsize,
- bitpos - mode_bitsize / 2, mode1, from,
+ bitpos - mode_bitsize / 2,
+ bitregion_start, bitregion_end,
+ mode1, from,
TREE_TYPE (tem), get_alias_set (to),
nontemporal);
else if (bitpos == 0 && bitsize == mode_bitsize)
0);
write_complex_part (temp, XEXP (to_rtx, 0), false);
write_complex_part (temp, XEXP (to_rtx, 1), true);
- result = store_field (temp, bitsize, bitpos, mode1, from,
+ result = store_field (temp, bitsize, bitpos,
+ bitregion_start, bitregion_end,
+ mode1, from,
TREE_TYPE (tem), get_alias_set (to),
nontemporal);
emit_move_insn (XEXP (to_rtx, 0), read_complex_part (temp, false));
MEM_KEEP_ALIAS_SET_P (to_rtx) = 1;
}
- if (optimize_bitfield_assignment_op (bitsize, bitpos, mode1,
+ if (optimize_bitfield_assignment_op (bitsize, bitpos,
+ bitregion_start, bitregion_end,
+ mode1,
to_rtx, to, from))
result = NULL;
else
- result = store_field (to_rtx, bitsize, bitpos, mode1, from,
+ result = store_field (to_rtx, bitsize, bitpos,
+ bitregion_start, bitregion_end,
+ mode1, from,
TREE_TYPE (tem), get_alias_set (to),
nontemporal);
}
: BLOCK_OP_NORMAL));
else if (GET_MODE (target) == BLKmode)
store_bit_field (target, INTVAL (expr_size (exp)) * BITS_PER_UNIT,
- 0, GET_MODE (temp), temp);
+ 0, 0, 0, GET_MODE (temp), temp);
else
convert_move (target, temp, unsignedp);
}
return NULL_RTX;
}
\f
+/* Return true if field F of structure TYPE is a flexible array. */
+
+static bool
+flexible_array_member_p (const_tree f, const_tree type)
+{
+ const_tree tf;
+
+ tf = TREE_TYPE (f);
+ return (DECL_CHAIN (f) == NULL
+ && TREE_CODE (tf) == ARRAY_TYPE
+ && TYPE_DOMAIN (tf)
+ && TYPE_MIN_VALUE (TYPE_DOMAIN (tf))
+ && integer_zerop (TYPE_MIN_VALUE (TYPE_DOMAIN (tf)))
+ && !TYPE_MAX_VALUE (TYPE_DOMAIN (tf))
+ && int_size_in_bytes (type) >= 0);
+}
+
+/* If FOR_CTOR_P, return the number of top-level elements that a constructor
+ must have in order for it to completely initialize a value of type TYPE.
+ Return -1 if the number isn't known.
+
+ If !FOR_CTOR_P, return an estimate of the number of scalars in TYPE. */
+
+static HOST_WIDE_INT
+count_type_elements (const_tree type, bool for_ctor_p)
+{
+ switch (TREE_CODE (type))
+ {
+ case ARRAY_TYPE:
+ {
+ tree nelts;
+
+ nelts = array_type_nelts (type);
+ if (nelts && host_integerp (nelts, 1))
+ {
+ unsigned HOST_WIDE_INT n;
+
+ n = tree_low_cst (nelts, 1) + 1;
+ if (n == 0 || for_ctor_p)
+ return n;
+ else
+ return n * count_type_elements (TREE_TYPE (type), false);
+ }
+ return for_ctor_p ? -1 : 1;
+ }
+
+ case RECORD_TYPE:
+ {
+ unsigned HOST_WIDE_INT n;
+ tree f;
+
+ n = 0;
+ for (f = TYPE_FIELDS (type); f ; f = DECL_CHAIN (f))
+ if (TREE_CODE (f) == FIELD_DECL)
+ {
+ if (!for_ctor_p)
+ n += count_type_elements (TREE_TYPE (f), false);
+ else if (!flexible_array_member_p (f, type))
+ /* Don't count flexible arrays, which are not supposed
+ to be initialized. */
+ n += 1;
+ }
+
+ return n;
+ }
+
+ case UNION_TYPE:
+ case QUAL_UNION_TYPE:
+ {
+ tree f;
+ HOST_WIDE_INT n, m;
+
+ gcc_assert (!for_ctor_p);
+ /* Estimate the number of scalars in each field and pick the
+ maximum. Other estimates would do instead; the idea is simply
+ to make sure that the estimate is not sensitive to the ordering
+ of the fields. */
+ n = 1;
+ for (f = TYPE_FIELDS (type); f ; f = DECL_CHAIN (f))
+ if (TREE_CODE (f) == FIELD_DECL)
+ {
+ m = count_type_elements (TREE_TYPE (f), false);
+ /* If the field doesn't span the whole union, add an extra
+ scalar for the rest. */
+ if (simple_cst_equal (TYPE_SIZE (TREE_TYPE (f)),
+ TYPE_SIZE (type)) != 1)
+ m++;
+ if (n < m)
+ n = m;
+ }
+ return n;
+ }
+
+ case COMPLEX_TYPE:
+ return 2;
+
+ case VECTOR_TYPE:
+ return TYPE_VECTOR_SUBPARTS (type);
+
+ case INTEGER_TYPE:
+ case REAL_TYPE:
+ case FIXED_POINT_TYPE:
+ case ENUMERAL_TYPE:
+ case BOOLEAN_TYPE:
+ case POINTER_TYPE:
+ case OFFSET_TYPE:
+ case REFERENCE_TYPE:
+ return 1;
+
+ case ERROR_MARK:
+ return 0;
+
+ case VOID_TYPE:
+ case METHOD_TYPE:
+ case FUNCTION_TYPE:
+ case LANG_TYPE:
+ default:
+ gcc_unreachable ();
+ }
+}
+
/* Helper for categorize_ctor_elements. Identical interface. */
static bool
categorize_ctor_elements_1 (const_tree ctor, HOST_WIDE_INT *p_nz_elts,
- HOST_WIDE_INT *p_elt_count,
- bool *p_must_clear)
+ HOST_WIDE_INT *p_init_elts, bool *p_complete)
{
unsigned HOST_WIDE_INT idx;
- HOST_WIDE_INT nz_elts, elt_count;
- tree value, purpose;
+ HOST_WIDE_INT nz_elts, init_elts, num_fields;
+ tree value, purpose, elt_type;
/* Whether CTOR is a valid constant initializer, in accordance with what
initializer_constant_valid_p does. If inferred from the constructor
bool const_p = const_from_elts_p ? true : TREE_STATIC (ctor);
nz_elts = 0;
- elt_count = 0;
+ init_elts = 0;
+ num_fields = 0;
+ elt_type = NULL_TREE;
FOR_EACH_CONSTRUCTOR_ELT (CONSTRUCTOR_ELTS (ctor), idx, purpose, value)
{
mult = (tree_low_cst (hi_index, 1)
- tree_low_cst (lo_index, 1) + 1);
}
+ num_fields += mult;
+ elt_type = TREE_TYPE (value);
switch (TREE_CODE (value))
{
{
HOST_WIDE_INT nz = 0, ic = 0;
- bool const_elt_p
- = categorize_ctor_elements_1 (value, &nz, &ic, p_must_clear);
+ bool const_elt_p = categorize_ctor_elements_1 (value, &nz, &ic,
+ p_complete);
nz_elts += mult * nz;
- elt_count += mult * ic;
+ init_elts += mult * ic;
if (const_from_elts_p && const_p)
const_p = const_elt_p;
case FIXED_CST:
if (!initializer_zerop (value))
nz_elts += mult;
- elt_count += mult;
+ init_elts += mult;
break;
case STRING_CST:
nz_elts += mult * TREE_STRING_LENGTH (value);
- elt_count += mult * TREE_STRING_LENGTH (value);
+ init_elts += mult * TREE_STRING_LENGTH (value);
break;
case COMPLEX_CST:
nz_elts += mult;
if (!initializer_zerop (TREE_IMAGPART (value)))
nz_elts += mult;
- elt_count += mult;
+ init_elts += mult;
break;
case VECTOR_CST:
{
if (!initializer_zerop (TREE_VALUE (v)))
nz_elts += mult;
- elt_count += mult;
+ init_elts += mult;
}
}
break;
default:
{
- HOST_WIDE_INT tc = count_type_elements (TREE_TYPE (value), true);
- if (tc < 1)
- tc = 1;
+ HOST_WIDE_INT tc = count_type_elements (elt_type, false);
nz_elts += mult * tc;
- elt_count += mult * tc;
+ init_elts += mult * tc;
if (const_from_elts_p && const_p)
- const_p = initializer_constant_valid_p (value, TREE_TYPE (value))
+ const_p = initializer_constant_valid_p (value, elt_type)
!= NULL_TREE;
}
break;
}
}
- if (!*p_must_clear
- && (TREE_CODE (TREE_TYPE (ctor)) == UNION_TYPE
- || TREE_CODE (TREE_TYPE (ctor)) == QUAL_UNION_TYPE))
- {
- tree init_sub_type;
- bool clear_this = true;
-
- if (!VEC_empty (constructor_elt, CONSTRUCTOR_ELTS (ctor)))
- {
- /* We don't expect more than one element of the union to be
- initialized. Not sure what we should do otherwise... */
- gcc_assert (VEC_length (constructor_elt, CONSTRUCTOR_ELTS (ctor))
- == 1);
-
- init_sub_type = TREE_TYPE (VEC_index (constructor_elt,
- CONSTRUCTOR_ELTS (ctor),
- 0)->value);
-
- /* ??? We could look at each element of the union, and find the
- largest element. Which would avoid comparing the size of the
- initialized element against any tail padding in the union.
- Doesn't seem worth the effort... */
- if (simple_cst_equal (TYPE_SIZE (TREE_TYPE (ctor)),
- TYPE_SIZE (init_sub_type)) == 1)
- {
- /* And now we have to find out if the element itself is fully
- constructed. E.g. for union { struct { int a, b; } s; } u
- = { .s = { .a = 1 } }. */
- if (elt_count == count_type_elements (init_sub_type, false))
- clear_this = false;
- }
- }
-
- *p_must_clear = clear_this;
- }
+ if (*p_complete && !complete_ctor_at_level_p (TREE_TYPE (ctor),
+ num_fields, elt_type))
+ *p_complete = false;
*p_nz_elts += nz_elts;
- *p_elt_count += elt_count;
+ *p_init_elts += init_elts;
return const_p;
}
and place it in *P_NZ_ELTS;
* how many scalar fields in total are in CTOR,
and place it in *P_ELT_COUNT.
- * if a type is a union, and the initializer from the constructor
- is not the largest element in the union, then set *p_must_clear.
+ * whether the constructor is complete -- in the sense that every
+ meaningful byte is explicitly given a value --
+ and place it in *P_COMPLETE.
Return whether or not CTOR is a valid static constant initializer, the same
as "initializer_constant_valid_p (CTOR, TREE_TYPE (CTOR)) != 0". */
bool
categorize_ctor_elements (const_tree ctor, HOST_WIDE_INT *p_nz_elts,
- HOST_WIDE_INT *p_elt_count,
- bool *p_must_clear)
+ HOST_WIDE_INT *p_init_elts, bool *p_complete)
{
*p_nz_elts = 0;
- *p_elt_count = 0;
- *p_must_clear = false;
+ *p_init_elts = 0;
+ *p_complete = true;
- return
- categorize_ctor_elements_1 (ctor, p_nz_elts, p_elt_count, p_must_clear);
+ return categorize_ctor_elements_1 (ctor, p_nz_elts, p_init_elts, p_complete);
}
-/* Count the number of scalars in TYPE. Return -1 on overflow or
- variable-sized. If ALLOW_FLEXARR is true, don't count flexible
- array member at the end of the structure. */
+/* TYPE is initialized by a constructor with NUM_ELTS elements, the last
+ of which had type LAST_TYPE. Each element was itself a complete
+ initializer, in the sense that every meaningful byte was explicitly
+ given a value. Return true if the same is true for the constructor
+ as a whole. */
-HOST_WIDE_INT
-count_type_elements (const_tree type, bool allow_flexarr)
+bool
+complete_ctor_at_level_p (const_tree type, HOST_WIDE_INT num_elts,
+ const_tree last_type)
{
- const HOST_WIDE_INT max = ~((HOST_WIDE_INT)1 << (HOST_BITS_PER_WIDE_INT-1));
- switch (TREE_CODE (type))
+ if (TREE_CODE (type) == UNION_TYPE
+ || TREE_CODE (type) == QUAL_UNION_TYPE)
{
- case ARRAY_TYPE:
- {
- tree telts = array_type_nelts (type);
- if (telts && host_integerp (telts, 1))
- {
- HOST_WIDE_INT n = tree_low_cst (telts, 1) + 1;
- HOST_WIDE_INT m = count_type_elements (TREE_TYPE (type), false);
- if (n == 0)
- return 0;
- else if (max / n > m)
- return n * m;
- }
- return -1;
- }
-
- case RECORD_TYPE:
- {
- HOST_WIDE_INT n = 0, t;
- tree f;
-
- for (f = TYPE_FIELDS (type); f ; f = DECL_CHAIN (f))
- if (TREE_CODE (f) == FIELD_DECL)
- {
- t = count_type_elements (TREE_TYPE (f), false);
- if (t < 0)
- {
- /* Check for structures with flexible array member. */
- tree tf = TREE_TYPE (f);
- if (allow_flexarr
- && DECL_CHAIN (f) == NULL
- && TREE_CODE (tf) == ARRAY_TYPE
- && TYPE_DOMAIN (tf)
- && TYPE_MIN_VALUE (TYPE_DOMAIN (tf))
- && integer_zerop (TYPE_MIN_VALUE (TYPE_DOMAIN (tf)))
- && !TYPE_MAX_VALUE (TYPE_DOMAIN (tf))
- && int_size_in_bytes (type) >= 0)
- break;
-
- return -1;
- }
- n += t;
- }
-
- return n;
- }
-
- case UNION_TYPE:
- case QUAL_UNION_TYPE:
- return -1;
-
- case COMPLEX_TYPE:
- return 2;
-
- case VECTOR_TYPE:
- return TYPE_VECTOR_SUBPARTS (type);
-
- case INTEGER_TYPE:
- case REAL_TYPE:
- case FIXED_POINT_TYPE:
- case ENUMERAL_TYPE:
- case BOOLEAN_TYPE:
- case POINTER_TYPE:
- case OFFSET_TYPE:
- case REFERENCE_TYPE:
- return 1;
+ if (num_elts == 0)
+ return false;
- case ERROR_MARK:
- return 0;
+ gcc_assert (num_elts == 1 && last_type);
- case VOID_TYPE:
- case METHOD_TYPE:
- case FUNCTION_TYPE:
- case LANG_TYPE:
- default:
- gcc_unreachable ();
+ /* ??? We could look at each element of the union, and find the
+ largest element. Which would avoid comparing the size of the
+ initialized element against any tail padding in the union.
+ Doesn't seem worth the effort... */
+ return simple_cst_equal (TYPE_SIZE (type), TYPE_SIZE (last_type)) == 1;
}
+
+ return count_type_elements (type, true) == num_elts;
}
/* Return 1 if EXP contains mostly (3/4) zeros. */
mostly_zeros_p (const_tree exp)
{
if (TREE_CODE (exp) == CONSTRUCTOR)
-
{
- HOST_WIDE_INT nz_elts, count, elts;
- bool must_clear;
-
- categorize_ctor_elements (exp, &nz_elts, &count, &must_clear);
- if (must_clear)
- return 1;
-
- elts = count_type_elements (TREE_TYPE (exp), false);
+ HOST_WIDE_INT nz_elts, init_elts;
+ bool complete_p;
- return nz_elts < elts / 4;
+ categorize_ctor_elements (exp, &nz_elts, &init_elts, &complete_p);
+ return !complete_p || nz_elts < init_elts / 4;
}
return initializer_zerop (exp);
all_zeros_p (const_tree exp)
{
if (TREE_CODE (exp) == CONSTRUCTOR)
-
{
- HOST_WIDE_INT nz_elts, count;
- bool must_clear;
+ HOST_WIDE_INT nz_elts, init_elts;
+ bool complete_p;
- categorize_ctor_elements (exp, &nz_elts, &count, &must_clear);
+ categorize_ctor_elements (exp, &nz_elts, &init_elts, &complete_p);
return nz_elts == 0;
}
store_constructor (exp, target, cleared, bitsize / BITS_PER_UNIT);
}
else
- store_field (target, bitsize, bitpos, mode, exp, type, alias_set, false);
+ store_field (target, bitsize, bitpos, 0, 0, mode, exp, type, alias_set,
+ false);
}
/* Store the value of constructor EXP into the rtx TARGET.
BITSIZE bits, starting BITPOS bits from the start of TARGET.
If MODE is VOIDmode, it means that we are storing into a bit-field.
+ BITREGION_START is bitpos of the first bitfield in this region.
+ BITREGION_END is the bitpos of the ending bitfield in this region.
+ These two fields are 0, if the C++ memory model does not apply,
+ or we are not interested in keeping track of bitfield regions.
+
Always return const0_rtx unless we have something particular to
return.
static rtx
store_field (rtx target, HOST_WIDE_INT bitsize, HOST_WIDE_INT bitpos,
+ unsigned HOST_WIDE_INT bitregion_start,
+ unsigned HOST_WIDE_INT bitregion_end,
enum machine_mode mode, tree exp, tree type,
alias_set_type alias_set, bool nontemporal)
{
if (bitsize != (HOST_WIDE_INT) GET_MODE_BITSIZE (GET_MODE (target)))
emit_move_insn (object, target);
- store_field (blk_object, bitsize, bitpos, mode, exp, type, alias_set,
- nontemporal);
+ store_field (blk_object, bitsize, bitpos,
+ bitregion_start, bitregion_end,
+ mode, exp, type, alias_set, nontemporal);
emit_move_insn (target, object);
}
/* Store the value in the bitfield. */
- store_bit_field (target, bitsize, bitpos, mode, temp);
+ store_bit_field (target, bitsize, bitpos,
+ bitregion_start, bitregion_end,
+ mode, temp);
return const0_rtx;
}
/* If the DECL isn't in memory, then the DECL wasn't properly
marked TREE_ADDRESSABLE, which will be either a front-end
or a tree optimizer bug. */
- gcc_assert (MEM_P (result));
+
+ if (TREE_ADDRESSABLE (exp)
+ && ! MEM_P (result)
+ && ! targetm.calls.allocate_stack_slots_for_args())
+ {
+ error ("local frame unavailable (naked function?)");
+ return result;
+ }
+ else
+ gcc_assert (MEM_P (result));
result = XEXP (result, 0);
/* ??? Is this needed anymore? */
(treeop0))
* BITS_PER_UNIT),
(HOST_WIDE_INT) GET_MODE_BITSIZE (mode)),
- 0, TYPE_MODE (valtype), treeop0,
+ 0, 0, 0, TYPE_MODE (valtype), treeop0,
type, 0, false);
}
if (modifier == EXPAND_STACK_PARM)
target = 0;
if (TREE_CODE (treeop0) == INTEGER_CST
- && GET_MODE_BITSIZE (mode) <= HOST_BITS_PER_WIDE_INT
+ && GET_MODE_PRECISION (mode) <= HOST_BITS_PER_WIDE_INT
&& TREE_CONSTANT (treeop1))
{
rtx constant_part;
}
else if (TREE_CODE (treeop1) == INTEGER_CST
- && GET_MODE_BITSIZE (mode) <= HOST_BITS_PER_WIDE_INT
+ && GET_MODE_PRECISION (mode) <= HOST_BITS_PER_WIDE_INT
&& TREE_CONSTANT (treeop0))
{
rtx constant_part;
VOIDmode, EXPAND_NORMAL);
if (modifier == EXPAND_STACK_PARM)
target = 0;
- temp = expand_unop (mode, one_cmpl_optab, op0, target, 1);
+ /* In case we have to reduce the result to bitfield precision
+ expand this as XOR with a proper constant instead. */
+ if (reduce_bit_field)
+ temp = expand_binop (mode, xor_optab, op0,
+ immed_double_int_const
+ (double_int_mask (TYPE_PRECISION (type)), mode),
+ target, 1, OPTAB_LIB_WIDEN);
+ else
+ temp = expand_unop (mode, one_cmpl_optab, op0, target, 1);
gcc_assert (temp);
return temp;
and (a bitwise1 b) bitwise2 b (etc)
but that is probably not worth while. */
- /* BIT_AND_EXPR is for bitwise anding. TRUTH_AND_EXPR is for anding two
- boolean values when we want in all cases to compute both of them. In
- general it is fastest to do TRUTH_AND_EXPR by computing both operands
- as actual zero-or-1 values and then bitwise anding. In cases where
- there cannot be any side effects, better code would be made by
- treating TRUTH_AND_EXPR like TRUTH_ANDIF_EXPR; but the question is
- how to recognize those cases. */
-
- case TRUTH_AND_EXPR:
- code = BIT_AND_EXPR;
case BIT_AND_EXPR:
- goto binop;
-
- case TRUTH_OR_EXPR:
- code = BIT_IOR_EXPR;
case BIT_IOR_EXPR:
- goto binop;
-
- case TRUTH_XOR_EXPR:
- code = BIT_XOR_EXPR;
case BIT_XOR_EXPR:
goto binop;
emit_label (op1);
return target;
- case TRUTH_NOT_EXPR:
- if (modifier == EXPAND_STACK_PARM)
- target = 0;
- op0 = expand_expr (treeop0, target,
- VOIDmode, EXPAND_NORMAL);
- /* The parser is careful to generate TRUTH_NOT_EXPR
- only with operands that are always zero or one. */
- temp = expand_binop (mode, xor_optab, op0, const1_rtx,
- target, 1, OPTAB_LIB_WIDEN);
- gcc_assert (temp);
- return temp;
-
case COMPLEX_EXPR:
/* Get the rtx code of the operands. */
op0 = expand_normal (treeop0);
temp = expand_binop (mode, this_optab, op0, op1, target,
unsignedp, OPTAB_LIB_WIDEN);
gcc_assert (temp);
+ /* Bitwise operations do not need bitfield reduction as we expect their
+ operands being properly truncated. */
+ if (code == BIT_XOR_EXPR
+ || code == BIT_AND_EXPR
+ || code == BIT_IOR_EXPR)
+ return temp;
return REDUCE_BIT_FIELD (temp);
}
#undef REDUCE_BIT_FIELD
{
addr_space_t as = TYPE_ADDR_SPACE (TREE_TYPE (exp));
struct mem_address addr;
- int icode, align;
+ enum insn_code icode;
+ int align;
get_address_description (exp, &addr);
op0 = addr_for_mem_ref (&addr, as, true);
&& ((icode = optab_handler (movmisalign_optab, mode))
!= CODE_FOR_nothing))
{
- rtx reg, insn;
+ struct expand_operand ops[2];
/* We've already validated the memory, and we're creating a
- new pseudo destination. The predicates really can't fail. */
- reg = gen_reg_rtx (mode);
-
- /* Nor can the insn generator. */
- insn = GEN_FCN (icode) (reg, temp);
- gcc_assert (insn != NULL_RTX);
- emit_insn (insn);
-
- return reg;
+ new pseudo destination. The predicates really can't fail,
+ nor can the generator. */
+ create_output_operand (&ops[0], NULL_RTX, mode);
+ create_fixed_operand (&ops[1], temp);
+ expand_insn (icode, 2, ops);
+ return ops[0].value;
}
return temp;
}
enum machine_mode address_mode;
tree base = TREE_OPERAND (exp, 0);
gimple def_stmt;
- int icode, align;
+ enum insn_code icode;
+ int align;
/* Handle expansion of non-aliased memory with non-BLKmode. That
might end up in a register. */
if (TREE_CODE (base) == ADDR_EXPR)
&& ((icode = optab_handler (movmisalign_optab, mode))
!= CODE_FOR_nothing))
{
- rtx reg, insn;
+ struct expand_operand ops[2];
/* We've already validated the memory, and we're creating a
- new pseudo destination. The predicates really can't fail. */
- reg = gen_reg_rtx (mode);
-
- /* Nor can the insn generator. */
- insn = GEN_FCN (icode) (reg, temp);
- emit_insn (insn);
-
- return reg;
+ new pseudo destination. The predicates really can't fail,
+ nor can the generator. */
+ create_output_operand (&ops[0], NULL_RTX, mode);
+ create_fixed_operand (&ops[1], temp);
+ expand_insn (icode, 2, ops);
+ return ops[0].value;
}
return temp;
}
we can't do this optimization. */
&& (! DECL_BIT_FIELD (field)
|| ((GET_MODE_CLASS (DECL_MODE (field)) == MODE_INT)
- && (GET_MODE_BITSIZE (DECL_MODE (field))
+ && (GET_MODE_PRECISION (DECL_MODE (field))
<= HOST_BITS_PER_WIDE_INT))))
{
if (DECL_BIT_FIELD (field)
}
else
{
- int count = GET_MODE_BITSIZE (imode) - bitsize;
+ int count = GET_MODE_PRECISION (imode) - bitsize;
op0 = expand_shift (LSHIFT_EXPR, imode, op0, count,
target, 0);
/* If neither mode is BLKmode, and both modes are the same size
then we can use gen_lowpart. */
else if (mode != BLKmode && GET_MODE (op0) != BLKmode
- && GET_MODE_SIZE (mode) == GET_MODE_SIZE (GET_MODE (op0))
+ && (GET_MODE_PRECISION (mode)
+ == GET_MODE_PRECISION (GET_MODE (op0)))
&& !COMPLEX_MODE_P (GET_MODE (op0)))
{
if (GET_CODE (op0) == SUBREG)
return op0;
- /* Use a compare and a jump for BLKmode comparisons, or for function
- type comparisons is HAVE_canonicalize_funcptr_for_compare. */
-
- /* Although TRUTH_{AND,OR}IF_EXPR aren't present in GIMPLE, they
- are occassionally created by folding during expansion. */
- case TRUTH_ANDIF_EXPR:
- case TRUTH_ORIF_EXPR:
- if (! ignore
- && (target == 0
- || modifier == EXPAND_STACK_PARM
- || ! safe_from_p (target, treeop0, 1)
- || ! safe_from_p (target, treeop1, 1)
- /* Make sure we don't have a hard reg (such as function's return
- value) live across basic blocks, if not optimizing. */
- || (!optimize && REG_P (target)
- && REGNO (target) < FIRST_PSEUDO_REGISTER)))
- target = gen_reg_rtx (tmode != VOIDmode ? tmode : mode);
-
- if (target)
- emit_move_insn (target, const0_rtx);
-
- op1 = gen_label_rtx ();
- jumpifnot_1 (code, treeop0, treeop1, op1, -1);
-
- if (target)
- emit_move_insn (target, const1_rtx);
-
- emit_label (op1);
- return ignore ? const0_rtx : target;
-
- case STATEMENT_LIST:
- {
- tree_stmt_iterator iter;
-
- gcc_assert (ignore);
-
- for (iter = tsi_start (exp); !tsi_end_p (iter); tsi_next (&iter))
- expand_expr (tsi_stmt (iter), const0_rtx, VOIDmode, modifier);
- }
- return const0_rtx;
-
case COND_EXPR:
/* A COND_EXPR with its type being VOID_TYPE represents a
conditional jump and is handled in
}
else
{
- int count = GET_MODE_BITSIZE (GET_MODE (exp)) - prec;
+ int count = GET_MODE_PRECISION (GET_MODE (exp)) - prec;
exp = expand_shift (LSHIFT_EXPR, GET_MODE (exp),
exp, count, target, 0);
return expand_shift (RSHIFT_EXPR, GET_MODE (exp),