/* A pass for lowering trees to RTL.
- Copyright (C) 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
+ Copyright (C) 2004, 2005, 2006, 2007, 2008, 2009
+ Free Software Foundation, Inc.
This file is part of GCC.
#include "tree-inline.h"
#include "value-prof.h"
#include "target.h"
+#include "ssaexpand.h"
+/* This variable holds information helping the rewriting of SSA trees
+ into RTL. */
+struct ssaexpand SA;
+
/* Return an expression tree corresponding to the RHS of GIMPLE
statement STMT. */
gimple_assign_rhs_to_tree (gimple stmt)
{
tree t;
- enum gimple_rhs_class class;
+ enum gimple_rhs_class grhs_class;
- class = get_gimple_rhs_class (gimple_expr_code (stmt));
+ grhs_class = get_gimple_rhs_class (gimple_expr_code (stmt));
- if (class == GIMPLE_BINARY_RHS)
+ if (grhs_class == GIMPLE_BINARY_RHS)
t = build2 (gimple_assign_rhs_code (stmt),
TREE_TYPE (gimple_assign_lhs (stmt)),
gimple_assign_rhs1 (stmt),
gimple_assign_rhs2 (stmt));
- else if (class == GIMPLE_UNARY_RHS)
+ else if (grhs_class == GIMPLE_UNARY_RHS)
t = build1 (gimple_assign_rhs_code (stmt),
TREE_TYPE (gimple_assign_lhs (stmt)),
gimple_assign_rhs1 (stmt));
- else if (class == GIMPLE_SINGLE_RHS)
+ else if (grhs_class == GIMPLE_SINGLE_RHS)
t = gimple_assign_rhs1 (stmt);
else
gcc_unreachable ();
static tree
gimple_cond_pred_to_tree (gimple stmt)
{
+ /* We're sometimes presented with such code:
+ D.123_1 = x < y;
+ if (D.123_1 != 0)
+ ...
+ This would expand to two comparisons which then later might
+ be cleaned up by combine. But some pattern matchers like if-conversion
+ work better when there's only one compare, so make up for this
+ here as special exception if TER would have made the same change. */
+ tree lhs = gimple_cond_lhs (stmt);
+ if (SA.values
+ && TREE_CODE (lhs) == SSA_NAME
+ && bitmap_bit_p (SA.values, SSA_NAME_VERSION (lhs)))
+ lhs = gimple_assign_rhs_to_tree (SSA_NAME_DEF_STMT (lhs));
+
return build2 (gimple_cond_code (stmt), boolean_type_node,
- gimple_cond_lhs (stmt), gimple_cond_rhs (stmt));
+ lhs, gimple_cond_rhs (stmt));
}
/* Helper for gimple_to_tree. Set EXPR_LOCATION for every expression
t = build_vl_exp (CALL_EXPR, gimple_call_num_args (stmt) + 3);
- fn = gimple_call_fn (stmt);
- if (TREE_CODE (fn) == FUNCTION_DECL)
- CALL_EXPR_FN (t) = build1 (ADDR_EXPR,
- build_pointer_type (TREE_TYPE (fn)),
- fn);
- else
- CALL_EXPR_FN (t) = fn;
-
+ CALL_EXPR_FN (t) = gimple_call_fn (stmt);
TREE_TYPE (t) = gimple_call_return_type (stmt);
-
CALL_EXPR_STATIC_CHAIN (t) = gimple_call_chain (stmt);
for (i = 0; i < gimple_call_num_args (stmt); i++)
/* Record the original call statement, as it may be used
to retrieve profile information during expansion. */
- if (TREE_CODE (fn) == FUNCTION_DECL && DECL_BUILT_IN (fn))
+
+ if ((fn = gimple_call_fndecl (stmt)) != NULL_TREE
+ && DECL_BUILT_IN (fn))
{
ann = get_tree_common_ann (t);
ann->stmt = stmt;
case GIMPLE_CALL:
if (gimple_call_lhs (stmt))
{
- if (TREE_CODE (gimple_call_fn (stmt)) == FUNCTION_DECL)
- ggc_free (CALL_EXPR_FN (TREE_OPERAND (stmt_tree, 1)));
ann = tree_common_ann (TREE_OPERAND (stmt_tree, 1));
if (ann)
ggc_free (ann);
ggc_free (TREE_OPERAND (stmt_tree, 1));
}
- else if (TREE_CODE (gimple_call_fn (stmt)) == FUNCTION_DECL)
- ggc_free (CALL_EXPR_FN (stmt_tree));
break;
default:
break;
#define STACK_ALIGNMENT_NEEDED 1
#endif
+#define SSAVAR(x) (TREE_CODE (x) == SSA_NAME ? SSA_NAME_VAR (x) : x)
+
+/* Associate declaration T with storage space X. If T is no
+ SSA name this is exactly SET_DECL_RTL, otherwise make the
+ partition of T associated with X. */
+static inline void
+set_rtl (tree t, rtx x)
+{
+ if (TREE_CODE (t) == SSA_NAME)
+ {
+ SA.partition_to_pseudo[var_to_partition (SA.map, t)] = x;
+ if (x && !MEM_P (x))
+ set_reg_attrs_for_decl_rtl (SSA_NAME_VAR (t), x);
+ /* For the benefit of debug information at -O0 (where vartracking
+ doesn't run) record the place also in the base DECL if it's
+ a normal variable (not a parameter). */
+ if (x && x != pc_rtx && TREE_CODE (SSA_NAME_VAR (t)) == VAR_DECL)
+ {
+ tree var = SSA_NAME_VAR (t);
+ /* If we don't yet have something recorded, just record it now. */
+ if (!DECL_RTL_SET_P (var))
+ SET_DECL_RTL (var, x);
+ /* If we have it set alrady to "multiple places" don't
+ change this. */
+ else if (DECL_RTL (var) == pc_rtx)
+ ;
+ /* If we have something recorded and it's not the same place
+ as we want to record now, we have multiple partitions for the
+ same base variable, with different places. We can't just
+ randomly chose one, hence we have to say that we don't know.
+ This only happens with optimization, and there var-tracking
+ will figure out the right thing. */
+ else if (DECL_RTL (var) != x)
+ SET_DECL_RTL (var, pc_rtx);
+ }
+ }
+ else
+ SET_DECL_RTL (t, x);
+}
/* This structure holds data relevant to one variable that will be
placed in a stack slot. */
{
unsigned int align;
- align = DECL_ALIGN (decl);
- align = LOCAL_ALIGNMENT (TREE_TYPE (decl), align);
- if (align > PREFERRED_STACK_BOUNDARY)
- align = PREFERRED_STACK_BOUNDARY;
+ align = LOCAL_DECL_ALIGNMENT (decl);
+
+ if (align > MAX_SUPPORTED_STACK_ALIGNMENT)
+ align = MAX_SUPPORTED_STACK_ALIGNMENT;
+
+ if (SUPPORTS_STACK_ALIGNMENT)
+ {
+ if (crtl->stack_alignment_estimated < align)
+ {
+ gcc_assert(!crtl->stack_realign_processed);
+ crtl->stack_alignment_estimated = align;
+ }
+ }
+
+ /* stack_alignment_needed > PREFERRED_STACK_BOUNDARY is permitted.
+ So here we only make sure stack_alignment_needed >= align. */
if (crtl->stack_alignment_needed < align)
crtl->stack_alignment_needed = align;
+ if (crtl->max_used_stack_slot_alignment < align)
+ crtl->max_used_stack_slot_alignment = align;
return align / BITS_PER_UNIT;
}
}
stack_vars[stack_vars_num].decl = decl;
stack_vars[stack_vars_num].offset = 0;
- stack_vars[stack_vars_num].size = tree_low_cst (DECL_SIZE_UNIT (decl), 1);
- stack_vars[stack_vars_num].alignb = get_decl_align_unit (decl);
+ stack_vars[stack_vars_num].size = tree_low_cst (DECL_SIZE_UNIT (SSAVAR (decl)), 1);
+ stack_vars[stack_vars_num].alignb = get_decl_align_unit (SSAVAR (decl));
/* All variables are initially in their own partition. */
stack_vars[stack_vars_num].representative = stack_vars_num;
stack_vars[stack_vars_num].next = EOC;
/* Ensure that this decl doesn't get put onto the list twice. */
- SET_DECL_RTL (decl, pc_rtx);
+ set_rtl (decl, pc_rtx);
stack_vars_num++;
}
}
/* A subroutine of partition_stack_vars. A comparison function for qsort,
- sorting an array of indices by the size of the object. */
+ sorting an array of indices by the size and type of the object. */
static int
stack_var_size_cmp (const void *a, const void *b)
{
HOST_WIDE_INT sa = stack_vars[*(const size_t *)a].size;
HOST_WIDE_INT sb = stack_vars[*(const size_t *)b].size;
- unsigned int uida = DECL_UID (stack_vars[*(const size_t *)a].decl);
- unsigned int uidb = DECL_UID (stack_vars[*(const size_t *)b].decl);
+ tree decla, declb;
+ unsigned int uida, uidb;
if (sa < sb)
return -1;
if (sa > sb)
return 1;
- /* For stack variables of the same size use the uid of the decl
- to make the sort stable. */
+ decla = stack_vars[*(const size_t *)a].decl;
+ declb = stack_vars[*(const size_t *)b].decl;
+ /* For stack variables of the same size use and id of the decls
+ to make the sort stable. Two SSA names are compared by their
+ version, SSA names come before non-SSA names, and two normal
+ decls are compared by their DECL_UID. */
+ if (TREE_CODE (decla) == SSA_NAME)
+ {
+ if (TREE_CODE (declb) == SSA_NAME)
+ uida = SSA_NAME_VERSION (decla), uidb = SSA_NAME_VERSION (declb);
+ else
+ return -1;
+ }
+ else if (TREE_CODE (declb) == SSA_NAME)
+ return 1;
+ else
+ uida = DECL_UID (decla), uidb = DECL_UID (declb);
if (uida < uidb)
return -1;
if (uida > uidb)
return 0;
}
+
+/* If the points-to solution *PI points to variables that are in a partition
+ together with other variables add all partition members to the pointed-to
+ variables bitmap. */
+
+static void
+add_partitioned_vars_to_ptset (struct pt_solution *pt,
+ struct pointer_map_t *decls_to_partitions,
+ struct pointer_set_t *visited, bitmap temp)
+{
+ bitmap_iterator bi;
+ unsigned i;
+ bitmap *part;
+
+ if (pt->anything
+ || pt->vars == NULL
+ /* The pointed-to vars bitmap is shared, it is enough to
+ visit it once. */
+ || pointer_set_insert(visited, pt->vars))
+ return;
+
+ bitmap_clear (temp);
+
+ /* By using a temporary bitmap to store all members of the partitions
+ we have to add we make sure to visit each of the partitions only
+ once. */
+ EXECUTE_IF_SET_IN_BITMAP (pt->vars, 0, i, bi)
+ if ((!temp
+ || !bitmap_bit_p (temp, i))
+ && (part = (bitmap *) pointer_map_contains (decls_to_partitions,
+ (void *)(size_t) i)))
+ bitmap_ior_into (temp, *part);
+ if (!bitmap_empty_p (temp))
+ bitmap_ior_into (pt->vars, temp);
+}
+
+/* Update points-to sets based on partition info, so we can use them on RTL.
+ The bitmaps representing stack partitions will be saved until expand,
+ where partitioned decls used as bases in memory expressions will be
+ rewritten. */
+
+static void
+update_alias_info_with_stack_vars (void)
+{
+ struct pointer_map_t *decls_to_partitions = NULL;
+ size_t i, j;
+ tree var = NULL_TREE;
+
+ for (i = 0; i < stack_vars_num; i++)
+ {
+ bitmap part = NULL;
+ tree name;
+ struct ptr_info_def *pi;
+
+ /* Not interested in partitions with single variable. */
+ if (stack_vars[i].representative != i
+ || stack_vars[i].next == EOC)
+ continue;
+
+ if (!decls_to_partitions)
+ {
+ decls_to_partitions = pointer_map_create ();
+ cfun->gimple_df->decls_to_pointers = pointer_map_create ();
+ }
+
+ /* Create an SSA_NAME that points to the partition for use
+ as base during alias-oracle queries on RTL for bases that
+ have been partitioned. */
+ if (var == NULL_TREE)
+ var = create_tmp_var (ptr_type_node, NULL);
+ name = make_ssa_name (var, NULL);
+
+ /* Create bitmaps representing partitions. They will be used for
+ points-to sets later, so use GGC alloc. */
+ part = BITMAP_GGC_ALLOC ();
+ for (j = i; j != EOC; j = stack_vars[j].next)
+ {
+ tree decl = stack_vars[j].decl;
+ unsigned int uid = DECL_UID (decl);
+ /* We should never end up partitioning SSA names (though they
+ may end up on the stack). Neither should we allocate stack
+ space to something that is unused and thus unreferenced. */
+ gcc_assert (DECL_P (decl)
+ && referenced_var_lookup (uid));
+ bitmap_set_bit (part, uid);
+ *((bitmap *) pointer_map_insert (decls_to_partitions,
+ (void *)(size_t) uid)) = part;
+ *((tree *) pointer_map_insert (cfun->gimple_df->decls_to_pointers,
+ decl)) = name;
+ }
+
+ /* Make the SSA name point to all partition members. */
+ pi = get_ptr_info (name);
+ pt_solution_set (&pi->pt, part);
+ }
+
+ /* Make all points-to sets that contain one member of a partition
+ contain all members of the partition. */
+ if (decls_to_partitions)
+ {
+ unsigned i;
+ struct pointer_set_t *visited = pointer_set_create ();
+ bitmap temp = BITMAP_ALLOC (NULL);
+
+ for (i = 1; i < num_ssa_names; i++)
+ {
+ tree name = ssa_name (i);
+ struct ptr_info_def *pi;
+
+ if (name
+ && POINTER_TYPE_P (TREE_TYPE (name))
+ && ((pi = SSA_NAME_PTR_INFO (name)) != NULL))
+ add_partitioned_vars_to_ptset (&pi->pt, decls_to_partitions,
+ visited, temp);
+ }
+
+ add_partitioned_vars_to_ptset (&cfun->gimple_df->escaped,
+ decls_to_partitions, visited, temp);
+ add_partitioned_vars_to_ptset (&cfun->gimple_df->callused,
+ decls_to_partitions, visited, temp);
+
+ pointer_set_destroy (visited);
+ pointer_map_destroy (decls_to_partitions);
+ BITMAP_FREE (temp);
+ }
+}
+
/* A subroutine of partition_stack_vars. The UNION portion of a UNION/FIND
partitioning algorithm. Partitions A and B are known to be non-conflicting.
Merge them into a single partition A.
break;
}
}
+
+ if (optimize)
+ update_alias_info_with_stack_vars ();
}
/* A debugging aid for expand_used_vars. Dump the generated partitions. */
static void
expand_one_stack_var_at (tree decl, HOST_WIDE_INT offset)
{
- HOST_WIDE_INT align;
+ /* Alignment is unsigned. */
+ unsigned HOST_WIDE_INT align;
rtx x;
/* If this fails, we've overflowed the stack frame. Error nicely? */
gcc_assert (offset == trunc_int_for_mode (offset, Pmode));
x = plus_constant (virtual_stack_vars_rtx, offset);
- x = gen_rtx_MEM (DECL_MODE (decl), x);
-
- /* Set alignment we actually gave this decl. */
- offset -= frame_phase;
- align = offset & -offset;
- align *= BITS_PER_UNIT;
- if (align > STACK_BOUNDARY || align == 0)
- align = STACK_BOUNDARY;
- DECL_ALIGN (decl) = align;
- DECL_USER_ALIGN (decl) = 0;
-
- set_mem_attributes (x, decl, true);
- SET_DECL_RTL (decl, x);
+ x = gen_rtx_MEM (DECL_MODE (SSAVAR (decl)), x);
+
+ if (TREE_CODE (decl) != SSA_NAME)
+ {
+ /* Set alignment we actually gave this decl if it isn't an SSA name.
+ If it is we generate stack slots only accidentally so it isn't as
+ important, we'll simply use the alignment that is already set. */
+ offset -= frame_phase;
+ align = offset & -offset;
+ align *= BITS_PER_UNIT;
+ if (align == 0)
+ align = STACK_BOUNDARY;
+ else if (align > MAX_SUPPORTED_STACK_ALIGNMENT)
+ align = MAX_SUPPORTED_STACK_ALIGNMENT;
+
+ DECL_ALIGN (decl) = align;
+ DECL_USER_ALIGN (decl) = 0;
+ }
+
+ set_mem_attributes (x, SSAVAR (decl), true);
+ set_rtl (decl, x);
}
/* A subroutine of expand_used_vars. Give each partition representative
/* Skip variables that have already had rtl assigned. See also
add_stack_var where we perpetrate this pc_rtx hack. */
- if (DECL_RTL (stack_vars[i].decl) != pc_rtx)
+ if ((TREE_CODE (stack_vars[i].decl) == SSA_NAME
+ ? SA.partition_to_pseudo[var_to_partition (SA.map, stack_vars[i].decl)]
+ : DECL_RTL (stack_vars[i].decl)) != pc_rtx)
continue;
/* Check the predicate to see whether this variable should be
size += stack_vars[i].size;
for (j = i; j != EOC; j = stack_vars[j].next)
- SET_DECL_RTL (stack_vars[j].decl, NULL);
+ set_rtl (stack_vars[j].decl, NULL);
}
return size;
}
{
HOST_WIDE_INT size, offset, align;
- size = tree_low_cst (DECL_SIZE_UNIT (var), 1);
- align = get_decl_align_unit (var);
+ size = tree_low_cst (DECL_SIZE_UNIT (SSAVAR (var)), 1);
+ align = get_decl_align_unit (SSAVAR (var));
offset = alloc_stack_frame_space (size, align);
expand_one_stack_var_at (var, offset);
static void
expand_one_register_var (tree var)
{
- tree type = TREE_TYPE (var);
+ tree decl = SSAVAR (var);
+ tree type = TREE_TYPE (decl);
int unsignedp = TYPE_UNSIGNED (type);
enum machine_mode reg_mode
- = promote_mode (type, DECL_MODE (var), &unsignedp, 0);
+ = promote_mode (type, DECL_MODE (decl), &unsignedp, 0);
rtx x = gen_reg_rtx (reg_mode);
- SET_DECL_RTL (var, x);
+ set_rtl (var, x);
/* Note if the object is a user variable. */
- if (!DECL_ARTIFICIAL (var))
- mark_user_reg (x);
+ if (!DECL_ARTIFICIAL (decl))
+ mark_user_reg (x);
if (POINTER_TYPE_P (type))
- mark_reg_pointer (x, TYPE_ALIGN (TREE_TYPE (TREE_TYPE (var))));
+ mark_reg_pointer (x, TYPE_ALIGN (TREE_TYPE (type)));
}
/* A subroutine of expand_one_var. Called to assign rtl to a VAR_DECL that
static HOST_WIDE_INT
expand_one_var (tree var, bool toplevel, bool really_expand)
{
- if (TREE_CODE (var) != VAR_DECL)
+ tree origvar = var;
+ var = SSAVAR (var);
+
+ if (SUPPORTS_STACK_ALIGNMENT
+ && TREE_TYPE (var) != error_mark_node
+ && TREE_CODE (var) == VAR_DECL)
+ {
+ unsigned int align;
+
+ /* Because we don't know if VAR will be in register or on stack,
+ we conservatively assume it will be on stack even if VAR is
+ eventually put into register after RA pass. For non-automatic
+ variables, which won't be on stack, we collect alignment of
+ type and ignore user specified alignment. */
+ if (TREE_STATIC (var) || DECL_EXTERNAL (var))
+ align = MINIMUM_ALIGNMENT (TREE_TYPE (var),
+ TYPE_MODE (TREE_TYPE (var)),
+ TYPE_ALIGN (TREE_TYPE (var)));
+ else
+ align = MINIMUM_ALIGNMENT (var, DECL_MODE (var), DECL_ALIGN (var));
+
+ if (crtl->stack_alignment_estimated < align)
+ {
+ /* stack_alignment_estimated shouldn't change after stack
+ realign decision made */
+ gcc_assert(!crtl->stack_realign_processed);
+ crtl->stack_alignment_estimated = align;
+ }
+ }
+
+ if (TREE_CODE (origvar) == SSA_NAME)
+ {
+ gcc_assert (TREE_CODE (var) != VAR_DECL
+ || (!DECL_EXTERNAL (var)
+ && !DECL_HAS_VALUE_EXPR_P (var)
+ && !TREE_STATIC (var)
+ && TREE_TYPE (var) != error_mark_node
+ && !DECL_HARD_REGISTER (var)
+ && really_expand));
+ }
+ if (TREE_CODE (var) != VAR_DECL && TREE_CODE (origvar) != SSA_NAME)
;
else if (DECL_EXTERNAL (var))
;
;
else if (TREE_STATIC (var))
;
- else if (DECL_RTL_SET_P (var))
+ else if (TREE_CODE (origvar) != SSA_NAME && DECL_RTL_SET_P (var))
;
else if (TREE_TYPE (var) == error_mark_node)
{
if (really_expand)
expand_one_error_var (var);
}
- else if (DECL_HARD_REGISTER (var))
+ else if (TREE_CODE (var) == VAR_DECL && DECL_HARD_REGISTER (var))
{
if (really_expand)
expand_one_hard_reg_var (var);
else if (use_register_for_decl (var))
{
if (really_expand)
- expand_one_register_var (var);
+ expand_one_register_var (origvar);
}
else if (defer_stack_allocation (var, toplevel))
- add_stack_var (var);
+ add_stack_var (origvar);
else
{
if (really_expand)
- expand_one_stack_var (var);
+ expand_one_stack_var (origvar);
return tree_low_cst (DECL_SIZE_UNIT (var), 1);
}
return 0;
static void
create_stack_guard (void)
{
- tree guard = build_decl (VAR_DECL, NULL, ptr_type_node);
+ tree guard = build_decl (DECL_SOURCE_LOCATION (current_function_decl),
+ VAR_DECL, NULL, ptr_type_node);
TREE_THIS_VOLATILE (guard) = 1;
TREE_USED (guard) = 1;
expand_one_stack_var (guard);
stack_vars_conflict_alloc = 0;
}
+/* Make a fair guess for the size of the stack frame of the current
+ function. This doesn't have to be exact, the result is only used
+ in the inline heuristics. So we don't want to run the full stack
+ var packing algorithm (which is quadratic in the number of stack
+ vars). Instead, we calculate the total size of all stack vars.
+ This turns out to be a pretty fair estimate -- packing of stack
+ vars doesn't happen very often. */
+
HOST_WIDE_INT
estimated_stack_frame_size (void)
{
HOST_WIDE_INT size = 0;
+ size_t i;
tree t, outer_block = DECL_INITIAL (current_function_decl);
init_vars_expansion ();
- /* At this point all variables on the local_decls with TREE_USED
- set are not associated with any block scope. Lay them out. */
for (t = cfun->local_decls; t; t = TREE_CHAIN (t))
{
tree var = TREE_VALUE (t);
TREE_USED (var) = 1;
}
size += account_used_vars_for_block (outer_block, true);
+
if (stack_vars_num > 0)
{
- /* Due to the way alias sets work, no variables with non-conflicting
- alias sets may be assigned the same address. Add conflicts to
- reflect this. */
- add_alias_set_conflicts ();
-
- /* If stack protection is enabled, we don't share space between
- vulnerable data and non-vulnerable data. */
- if (flag_stack_protect)
- add_stack_protection_conflicts ();
-
- /* Now that we have collected all stack variables, and have computed a
- minimal interference graph, attempt to save some stack space. */
- partition_stack_vars ();
- if (dump_file)
- dump_stack_var_partition ();
-
+ /* Fake sorting the stack vars for account_stack_vars (). */
+ stack_vars_sorted = XNEWVEC (size_t, stack_vars_num);
+ for (i = 0; i < stack_vars_num; ++i)
+ stack_vars_sorted[i] = i;
size += account_stack_vars ();
fini_vars_expansion ();
}
+
return size;
}
static void
expand_used_vars (void)
{
- tree t, outer_block = DECL_INITIAL (current_function_decl);
+ tree t, next, outer_block = DECL_INITIAL (current_function_decl);
+ unsigned i;
/* Compute the phase of the stack frame for this function. */
{
init_vars_expansion ();
+ for (i = 0; i < SA.map->num_partitions; i++)
+ {
+ tree var = partition_to_var (SA.map, i);
+
+ gcc_assert (is_gimple_reg (var));
+ if (TREE_CODE (SSA_NAME_VAR (var)) == VAR_DECL)
+ expand_one_var (var, true, true);
+ else
+ {
+ /* This is a PARM_DECL or RESULT_DECL. For those partitions that
+ contain the default def (representing the parm or result itself)
+ we don't do anything here. But those which don't contain the
+ default def (representing a temporary based on the parm/result)
+ we need to allocate space just like for normal VAR_DECLs. */
+ if (!bitmap_bit_p (SA.partition_has_default_def, i))
+ {
+ expand_one_var (var, true, true);
+ gcc_assert (SA.partition_to_pseudo[i]);
+ }
+ }
+ }
+
/* At this point all variables on the local_decls with TREE_USED
set are not associated with any block scope. Lay them out. */
- for (t = cfun->local_decls; t; t = TREE_CHAIN (t))
+ t = cfun->local_decls;
+ cfun->local_decls = NULL_TREE;
+ for (; t; t = next)
{
tree var = TREE_VALUE (t);
bool expand_now = false;
+ next = TREE_CHAIN (t);
+
+ /* Expanded above already. */
+ if (is_gimple_reg (var))
+ {
+ TREE_USED (var) = 0;
+ ggc_free (t);
+ continue;
+ }
/* We didn't set a block for static or extern because it's hard
to tell the difference between a global variable (re)declared
in a local scope, and one that's really declared there to
begin with. And it doesn't really matter much, since we're
not giving them stack space. Expand them now. */
- if (TREE_STATIC (var) || DECL_EXTERNAL (var))
- expand_now = true;
-
- /* Any variable that could have been hoisted into an SSA_NAME
- will have been propagated anywhere the optimizers chose,
- i.e. not confined to their original block. Allocate them
- as if they were defined in the outermost scope. */
- else if (is_gimple_reg (var))
+ else if (TREE_STATIC (var) || DECL_EXTERNAL (var))
expand_now = true;
/* If the variable is not associated with any block, then it
TREE_USED (var) = 1;
if (expand_now)
- expand_one_var (var, true, true);
+ {
+ expand_one_var (var, true, true);
+ if (DECL_ARTIFICIAL (var) && !DECL_IGNORED_P (var))
+ {
+ rtx rtl = DECL_RTL_IF_SET (var);
+
+ /* Keep artificial non-ignored vars in cfun->local_decls
+ chain until instantiate_decls. */
+ if (rtl && (MEM_P (rtl) || GET_CODE (rtl) == CONCAT))
+ {
+ TREE_CHAIN (t) = cfun->local_decls;
+ cfun->local_decls = t;
+ continue;
+ }
+ }
+ }
+
+ ggc_free (t);
}
- cfun->local_decls = NULL_TREE;
/* At this point, all variables within the block tree with TREE_USED
set are actually used by the optimized function. Lay them out. */
}
+/* A subroutine of expand_gimple_cond. Given E, a fallthrough edge
+ of a basic block where we just expanded the conditional at the end,
+ possibly clean up the CFG and instruction sequence. */
+
+static void
+maybe_cleanup_end_of_block (edge e)
+{
+ /* Special case: when jumpif decides that the condition is
+ trivial it emits an unconditional jump (and the necessary
+ barrier). But we still have two edges, the fallthru one is
+ wrong. purge_dead_edges would clean this up later. Unfortunately
+ we have to insert insns (and split edges) before
+ find_many_sub_basic_blocks and hence before purge_dead_edges.
+ But splitting edges might create new blocks which depend on the
+ fact that if there are two edges there's no barrier. So the
+ barrier would get lost and verify_flow_info would ICE. Instead
+ of auditing all edge splitters to care for the barrier (which
+ normally isn't there in a cleaned CFG), fix it here. */
+ if (BARRIER_P (get_last_insn ()))
+ {
+ basic_block bb = e->src;
+ rtx insn;
+ remove_edge (e);
+ /* Now, we have a single successor block, if we have insns to
+ insert on the remaining edge we potentially will insert
+ it at the end of this block (if the dest block isn't feasible)
+ in order to avoid splitting the edge. This insertion will take
+ place in front of the last jump. But we might have emitted
+ multiple jumps (conditional and one unconditional) to the
+ same destination. Inserting in front of the last one then
+ is a problem. See PR 40021. We fix this by deleting all
+ jumps except the last unconditional one. */
+ insn = PREV_INSN (get_last_insn ());
+ /* Make sure we have an unconditional jump. Otherwise we're
+ confused. */
+ gcc_assert (JUMP_P (insn) && !any_condjump_p (insn));
+ for (insn = PREV_INSN (insn); insn != BB_HEAD (bb);)
+ {
+ insn = PREV_INSN (insn);
+ if (JUMP_P (NEXT_INSN (insn)))
+ delete_insn (NEXT_INSN (insn));
+ }
+ }
+}
+
+
/* A subroutine of expand_gimple_basic_block. Expand one GIMPLE_COND.
Returns a new basic block if we've terminated the current basic
block and created a new one. */
add_reg_br_prob_note (last, true_edge->probability);
maybe_dump_rtl_for_gimple_stmt (stmt, last);
if (true_edge->goto_locus)
- set_curr_insn_source_location (true_edge->goto_locus);
+ {
+ set_curr_insn_source_location (true_edge->goto_locus);
+ set_curr_insn_block (true_edge->goto_block);
+ true_edge->goto_locus = curr_insn_locator ();
+ }
+ true_edge->goto_block = NULL;
false_edge->flags |= EDGE_FALLTHRU;
ggc_free (pred);
+ maybe_cleanup_end_of_block (false_edge);
return NULL;
}
if (true_edge->dest == bb->next_bb)
add_reg_br_prob_note (last, false_edge->probability);
maybe_dump_rtl_for_gimple_stmt (stmt, last);
if (false_edge->goto_locus)
- set_curr_insn_source_location (false_edge->goto_locus);
+ {
+ set_curr_insn_source_location (false_edge->goto_locus);
+ set_curr_insn_block (false_edge->goto_block);
+ false_edge->goto_locus = curr_insn_locator ();
+ }
+ false_edge->goto_block = NULL;
true_edge->flags |= EDGE_FALLTHRU;
ggc_free (pred);
+ maybe_cleanup_end_of_block (true_edge);
return NULL;
}
jumpif (pred, label_rtx_for_bb (true_edge->dest));
add_reg_br_prob_note (last, true_edge->probability);
last = get_last_insn ();
+ if (false_edge->goto_locus)
+ {
+ set_curr_insn_source_location (false_edge->goto_locus);
+ set_curr_insn_block (false_edge->goto_block);
+ false_edge->goto_locus = curr_insn_locator ();
+ }
+ false_edge->goto_block = NULL;
emit_jump (label_rtx_for_bb (false_edge->dest));
BB_END (bb) = last;
maybe_dump_rtl_for_gimple_stmt (stmt, last2);
- if (false_edge->goto_locus)
- set_curr_insn_source_location (false_edge->goto_locus);
+ if (true_edge->goto_locus)
+ {
+ set_curr_insn_source_location (true_edge->goto_locus);
+ set_curr_insn_block (true_edge->goto_block);
+ true_edge->goto_locus = curr_insn_locator ();
+ }
+ true_edge->goto_block = NULL;
ggc_free (pred);
return new_bb;
NOTE_BASIC_BLOCK (note) = bb;
- for (ei = ei_start (bb->succs); (e = ei_safe_edge (ei)); )
- {
- /* Clear EDGE_EXECUTABLE. This flag is never used in the backend. */
- e->flags &= ~EDGE_EXECUTABLE;
-
- /* At the moment not all abnormal edges match the RTL representation.
- It is safe to remove them here as find_many_sub_basic_blocks will
- rediscover them. In the future we should get this fixed properly. */
- if (e->flags & EDGE_ABNORMAL)
- remove_edge (e);
- else
- ei_next (&ei);
- }
-
for (; !gsi_end_p (gsi); gsi_next (&gsi))
{
gimple stmt = gsi_stmt (gsi);
}
else
{
- tree stmt_tree = gimple_to_tree (stmt);
+ def_operand_p def_p;
+ tree stmt_tree;
+ def_p = SINGLE_SSA_DEF_OPERAND (stmt, SSA_OP_DEF);
+
+ if (def_p != NULL)
+ {
+ /* Ignore this stmt if it is in the list of
+ replaceable expressions. */
+ if (SA.values
+ && bitmap_bit_p (SA.values,
+ SSA_NAME_VERSION (DEF_FROM_PTR (def_p))))
+ continue;
+ }
+ stmt_tree = gimple_to_tree (stmt);
last = get_last_insn ();
expand_expr_stmt (stmt_tree);
maybe_dump_rtl_for_gimple_stmt (stmt, last);
}
}
- /* Expand implicit goto. */
+ /* Expand implicit goto and convert goto_locus. */
FOR_EACH_EDGE (e, ei, bb->succs)
{
- if (e->flags & EDGE_FALLTHRU)
- break;
- }
-
- if (e && e->dest != bb->next_bb)
- {
- emit_jump (label_rtx_for_bb (e->dest));
- if (e->goto_locus)
- set_curr_insn_source_location (e->goto_locus);
- e->flags &= ~EDGE_FALLTHRU;
+ if (e->goto_locus && e->goto_block)
+ {
+ set_curr_insn_source_location (e->goto_locus);
+ set_curr_insn_block (e->goto_block);
+ e->goto_locus = curr_insn_locator ();
+ }
+ e->goto_block = NULL;
+ if ((e->flags & EDGE_FALLTHRU) && e->dest != bb->next_bb)
+ {
+ emit_jump (label_rtx_for_bb (e->dest));
+ e->flags &= ~EDGE_FALLTHRU;
+ }
}
do_pending_stack_adjust ();
if (TREE_CODE (t) == ARRAY_REF || TREE_CODE (t) == ARRAY_RANGE_REF)
{
t = get_base_address (t);
- if (t && DECL_P (t))
+ if (t && DECL_P (t)
+ && DECL_MODE (t) != BLKmode)
TREE_ADDRESSABLE (t) = 1;
}
}
}
+/* This function sets crtl->args.internal_arg_pointer to a virtual
+ register if DRAP is needed. Local register allocator will replace
+ virtual_incoming_args_rtx with the virtual register. */
+
+static void
+expand_stack_alignment (void)
+{
+ rtx drap_rtx;
+ unsigned int preferred_stack_boundary;
+
+ if (! SUPPORTS_STACK_ALIGNMENT)
+ return;
+
+ if (cfun->calls_alloca
+ || cfun->has_nonlocal_label
+ || crtl->has_nonlocal_goto)
+ crtl->need_drap = true;
+
+ gcc_assert (crtl->stack_alignment_needed
+ <= crtl->stack_alignment_estimated);
+
+ /* Update crtl->stack_alignment_estimated and use it later to align
+ stack. We check PREFERRED_STACK_BOUNDARY if there may be non-call
+ exceptions since callgraph doesn't collect incoming stack alignment
+ in this case. */
+ if (flag_non_call_exceptions
+ && PREFERRED_STACK_BOUNDARY > crtl->preferred_stack_boundary)
+ preferred_stack_boundary = PREFERRED_STACK_BOUNDARY;
+ else
+ preferred_stack_boundary = crtl->preferred_stack_boundary;
+ if (preferred_stack_boundary > crtl->stack_alignment_estimated)
+ crtl->stack_alignment_estimated = preferred_stack_boundary;
+ if (preferred_stack_boundary > crtl->stack_alignment_needed)
+ crtl->stack_alignment_needed = preferred_stack_boundary;
+
+ crtl->stack_realign_needed
+ = INCOMING_STACK_BOUNDARY < crtl->stack_alignment_estimated;
+ crtl->stack_realign_tried = crtl->stack_realign_needed;
+
+ crtl->stack_realign_processed = true;
+
+ /* Target has to redefine TARGET_GET_DRAP_RTX to support stack
+ alignment. */
+ gcc_assert (targetm.calls.get_drap_rtx != NULL);
+ drap_rtx = targetm.calls.get_drap_rtx ();
+
+ /* stack_realign_drap and drap_rtx must match. */
+ gcc_assert ((stack_realign_drap != 0) == (drap_rtx != NULL));
+
+ /* Do nothing if NULL is returned, which means DRAP is not needed. */
+ if (NULL != drap_rtx)
+ {
+ crtl->args.internal_arg_pointer = drap_rtx;
+
+ /* Call fixup_tail_calls to clean up REG_EQUIV note if DRAP is
+ needed. */
+ fixup_tail_calls ();
+ }
+}
+
/* Translate the intermediate representation contained in the CFG
from GIMPLE trees to RTL.
sbitmap blocks;
edge_iterator ei;
edge e;
+ unsigned i;
+
+ rewrite_out_of_ssa (&SA);
+ SA.partition_to_pseudo = (rtx *)xcalloc (SA.map->num_partitions,
+ sizeof (rtx));
/* Some backends want to know that we are expanding to RTL. */
currently_expanding_to_rtl = 1;
rtl_profile_for_bb (ENTRY_BLOCK_PTR);
insn_locators_alloc ();
- if (!DECL_BUILT_IN (current_function_decl))
- set_curr_insn_source_location (DECL_SOURCE_LOCATION (current_function_decl));
+ if (!DECL_IS_BUILTIN (current_function_decl))
+ {
+ /* Eventually, all FEs should explicitly set function_start_locus. */
+ if (cfun->function_start_locus == UNKNOWN_LOCATION)
+ set_curr_insn_source_location
+ (DECL_SOURCE_LOCATION (current_function_decl));
+ else
+ set_curr_insn_source_location (cfun->function_start_locus);
+ }
set_curr_insn_block (DECL_INITIAL (current_function_decl));
prologue_locator = curr_insn_locator ();
targetm.expand_to_rtl_hook ();
crtl->stack_alignment_needed = STACK_BOUNDARY;
+ crtl->max_used_stack_slot_alignment = STACK_BOUNDARY;
+ crtl->stack_alignment_estimated = STACK_BOUNDARY;
crtl->preferred_stack_boundary = STACK_BOUNDARY;
cfun->cfg->max_jumptable_ents = 0;
/* Set up parameters and prepare for return, for the function. */
expand_function_start (current_function_decl);
+ /* Now that we also have the parameter RTXs, copy them over to our
+ partitions. */
+ for (i = 0; i < SA.map->num_partitions; i++)
+ {
+ tree var = SSA_NAME_VAR (partition_to_var (SA.map, i));
+
+ if (TREE_CODE (var) != VAR_DECL
+ && !SA.partition_to_pseudo[i])
+ SA.partition_to_pseudo[i] = DECL_RTL_IF_SET (var);
+ gcc_assert (SA.partition_to_pseudo[i]);
+
+ /* If this decl was marked as living in multiple places, reset
+ this now to NULL. */
+ if (DECL_RTL_IF_SET (var) == pc_rtx)
+ SET_DECL_RTL (var, NULL);
+
+ /* Some RTL parts really want to look at DECL_RTL(x) when x
+ was a decl marked in REG_ATTR or MEM_ATTR. We could use
+ SET_DECL_RTL here making this available, but that would mean
+ to select one of the potentially many RTLs for one DECL. Instead
+ of doing that we simply reset the MEM_EXPR of the RTL in question,
+ then nobody can get at it and hence nobody can call DECL_RTL on it. */
+ if (!DECL_RTL_SET_P (var))
+ {
+ if (MEM_P (SA.partition_to_pseudo[i]))
+ set_mem_expr (SA.partition_to_pseudo[i], NULL);
+ }
+ }
+
/* If this function is `main', emit a call to `__main'
to run global initializers, etc. */
if (DECL_NAME (current_function_decl)
if (crtl->stack_protect_guard)
stack_protect_prologue ();
+ /* Update stack boundary if needed. */
+ if (SUPPORTS_STACK_ALIGNMENT)
+ {
+ /* Call update_stack_boundary here to update incoming stack
+ boundary before TARGET_FUNCTION_OK_FOR_SIBCALL is called.
+ TARGET_FUNCTION_OK_FOR_SIBCALL needs to know the accurate
+ incoming stack alignment to check if it is OK to perform
+ sibcall optimization since sibcall optimization will only
+ align the outgoing stack to incoming stack boundary. */
+ if (targetm.calls.update_stack_boundary)
+ targetm.calls.update_stack_boundary ();
+
+ /* The incoming stack frame has to be aligned at least at
+ parm_stack_boundary. */
+ gcc_assert (crtl->parm_stack_boundary <= INCOMING_STACK_BOUNDARY);
+ }
+
+ expand_phi_nodes (&SA);
+
/* Register rtl specific functions for cfg. */
rtl_register_cfg_hooks ();
init_block = construct_init_block ();
/* Clear EDGE_EXECUTABLE on the entry edge(s). It is cleaned from the
- remaining edges in expand_gimple_basic_block. */
+ remaining edges later. */
FOR_EACH_EDGE (e, ei, ENTRY_BLOCK_PTR->succs)
e->flags &= ~EDGE_EXECUTABLE;
FOR_BB_BETWEEN (bb, init_block->next_bb, EXIT_BLOCK_PTR, next_bb)
bb = expand_gimple_basic_block (bb);
+ execute_free_datastructures ();
+ finish_out_of_ssa (&SA);
+
/* Expansion is used by optimization passes too, set maybe_hot_insn_p
conservatively to true until they are all profile aware. */
pointer_map_destroy (lab_rtx_for_bb);
set_curr_insn_block (DECL_INITIAL (current_function_decl));
insn_locators_finalize ();
- /* We're done expanding trees to RTL. */
- currently_expanding_to_rtl = 0;
-
/* Convert tree EH labels to RTL EH labels and zap the tree EH table. */
convert_from_eh_region_ranges ();
set_eh_throw_stmt_table (cfun, NULL);
rebuild_jump_labels (get_insns ());
find_exception_handler_labels ();
+ FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR, EXIT_BLOCK_PTR, next_bb)
+ {
+ edge e;
+ edge_iterator ei;
+ for (ei = ei_start (bb->succs); (e = ei_safe_edge (ei)); )
+ {
+ if (e->insns.r)
+ commit_one_edge_insertion (e);
+ else
+ ei_next (&ei);
+ }
+ }
+
+ /* We're done expanding trees to RTL. */
+ currently_expanding_to_rtl = 0;
+
+ FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR->next_bb, EXIT_BLOCK_PTR, next_bb)
+ {
+ edge e;
+ edge_iterator ei;
+ for (ei = ei_start (bb->succs); (e = ei_safe_edge (ei)); )
+ {
+ /* Clear EDGE_EXECUTABLE. This flag is never used in the backend. */
+ e->flags &= ~EDGE_EXECUTABLE;
+
+ /* At the moment not all abnormal edges match the RTL
+ representation. It is safe to remove them here as
+ find_many_sub_basic_blocks will rediscover them.
+ In the future we should get this fixed properly. */
+ if ((e->flags & EDGE_ABNORMAL)
+ && !(e->flags & EDGE_SIBCALL))
+ remove_edge (e);
+ else
+ ei_next (&ei);
+ }
+ }
+
blocks = sbitmap_alloc (last_basic_block);
sbitmap_ones (blocks);
find_many_sub_basic_blocks (blocks);
- purge_all_dead_edges ();
sbitmap_free (blocks);
+ purge_all_dead_edges ();
compact_blocks ();
+
+ expand_stack_alignment ();
+
#ifdef ENABLE_CHECKING
verify_flow_info ();
#endif
NULL, /* next */
0, /* static_pass_number */
TV_EXPAND, /* tv_id */
- /* ??? If TER is enabled, we actually receive GENERIC. */
- PROP_gimple_leh | PROP_cfg, /* properties_required */
+ PROP_ssa | PROP_gimple_leh | PROP_cfg,/* properties_required */
PROP_rtl, /* properties_provided */
- PROP_trees, /* properties_destroyed */
- 0, /* todo_flags_start */
- TODO_dump_func, /* todo_flags_finish */
+ PROP_ssa | PROP_trees, /* properties_destroyed */
+ TODO_verify_ssa | TODO_verify_flow
+ | TODO_verify_stmts, /* todo_flags_start */
+ TODO_dump_func
+ | TODO_ggc_collect /* todo_flags_finish */
}
};
OSDN Git Service
