[V3,2/3] Use the counted_by atribute info in builtin object size [PR108896]
Checks
Commit Message
Use the counted_by atribute info in builtin object size to compute the
subobject size for flexible array members.
gcc/ChangeLog:
PR C/108896
* tree-object-size.cc (addr_object_size): Use the counted_by
attribute info.
* tree.cc (component_ref_has_counted_by_p): New function.
(component_ref_get_counted_by): New function.
* tree.h (component_ref_has_counted_by_p): New prototype.
(component_ref_get_counted_by): New prototype.
gcc/testsuite/ChangeLog:
PR C/108896
* gcc.dg/flex-array-counted-by-2.c: New test.
* gcc.dg/flex-array-counted-by-3.c: New test.
---
.../gcc.dg/flex-array-counted-by-2.c | 74 ++++++
.../gcc.dg/flex-array-counted-by-3.c | 210 ++++++++++++++++++
gcc/tree-object-size.cc | 37 ++-
gcc/tree.cc | 95 +++++++-
gcc/tree.h | 10 +
5 files changed, 418 insertions(+), 8 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
Comments
Ping.
thanks.
Qing
> On Aug 25, 2023, at 11:24 AM, Qing Zhao <qing.zhao@oracle.com> wrote:
>
> Use the counted_by atribute info in builtin object size to compute the
> subobject size for flexible array members.
>
> gcc/ChangeLog:
>
> PR C/108896
> * tree-object-size.cc (addr_object_size): Use the counted_by
> attribute info.
> * tree.cc (component_ref_has_counted_by_p): New function.
> (component_ref_get_counted_by): New function.
> * tree.h (component_ref_has_counted_by_p): New prototype.
> (component_ref_get_counted_by): New prototype.
>
> gcc/testsuite/ChangeLog:
>
> PR C/108896
> * gcc.dg/flex-array-counted-by-2.c: New test.
> * gcc.dg/flex-array-counted-by-3.c: New test.
> ---
> .../gcc.dg/flex-array-counted-by-2.c | 74 ++++++
> .../gcc.dg/flex-array-counted-by-3.c | 210 ++++++++++++++++++
> gcc/tree-object-size.cc | 37 ++-
> gcc/tree.cc | 95 +++++++-
> gcc/tree.h | 10 +
> 5 files changed, 418 insertions(+), 8 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
>
> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> new file mode 100644
> index 000000000000..ec580c1f1f01
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> @@ -0,0 +1,74 @@
> +/* test the attribute counted_by and its usage in
> + * __builtin_dynamic_object_size. */
> +/* { dg-do run } */
> +/* { dg-options "-O2" } */
> +
> +#include "builtin-object-size-common.h"
> +
> +#define expect(p, _v) do { \
> + size_t v = _v; \
> + if (p == v) \
> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
> + else \
> + { \
> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
> + FAIL (); \
> + } \
> +} while (0);
> +
> +struct flex {
> + int b;
> + int c[];
> +} *array_flex;
> +
> +struct annotated {
> + int b;
> + int c[] __attribute__ ((counted_by (b)));
> +} *array_annotated;
> +
> +struct nested_annotated {
> + struct {
> + union {
> + int b;
> + float f;
> + };
> + int n;
> + };
> + int c[] __attribute__ ((counted_by (b)));
> +} *array_nested_annotated;
> +
> +void __attribute__((__noinline__)) setup (int normal_count, int attr_count)
> +{
> + array_flex
> + = (struct flex *)malloc (sizeof (struct flex)
> + + normal_count * sizeof (int));
> + array_flex->b = normal_count;
> +
> + array_annotated
> + = (struct annotated *)malloc (sizeof (struct annotated)
> + + attr_count * sizeof (int));
> + array_annotated->b = attr_count;
> +
> + array_nested_annotated
> + = (struct nested_annotated *)malloc (sizeof (struct nested_annotated)
> + + attr_count * sizeof (int));
> + array_nested_annotated->b = attr_count;
> +
> + return;
> +}
> +
> +void __attribute__((__noinline__)) test ()
> +{
> + expect(__builtin_dynamic_object_size(array_flex->c, 1), -1);
> + expect(__builtin_dynamic_object_size(array_annotated->c, 1),
> + array_annotated->b * sizeof (int));
> + expect(__builtin_dynamic_object_size(array_nested_annotated->c, 1),
> + array_nested_annotated->b * sizeof (int));
> +}
> +
> +int main(int argc, char *argv[])
> +{
> + setup (10,10);
> + test ();
> + DONE ();
> +}
> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
> new file mode 100644
> index 000000000000..a0c3cb88ec71
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
> @@ -0,0 +1,210 @@
> +/* test the attribute counted_by and its usage in
> +__builtin_dynamic_object_size: what's the correct behavior when the
> +allocation size mismatched with the value of counted_by attribute? */
> +/* { dg-do run } */
> +/* { dg-options "-O -fstrict-flex-arrays=3" } */
> +
> +#include "builtin-object-size-common.h"
> +
> +struct annotated {
> + size_t foo;
> + char others;
> + char array[] __attribute__((counted_by (foo)));
> +};
> +
> +#define expect(p, _v) do { \
> + size_t v = _v; \
> + if (p == v) \
> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
> + else \
> + { \
> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
> + FAIL (); \
> + } \
> +} while (0);
> +
> +#define noinline __attribute__((__noinline__))
> +#define SIZE_BUMP 10
> +#define MAX(a, b) ((a) > (b) ? (a) : (b))
> +#define MIN(a, b) ((a) < (b) ? (a) : (b))
> +
> +/* In general, Due to type casting, the type for the pointee of a pointer
> + does not say anything about the object it points to,
> + So, __builtin_object_size can not directly use the type of the pointee
> + to decide the size of the object the pointer points to.
> +
> + there are only two reliable ways:
> + A. observed allocations (call to the allocation functions in the routine)
> + B. observed accesses (read or write access to the location of the
> + pointer points to)
> +
> + that provide information about the type/existence of an object at
> + the corresponding address.
> +
> + for A, we use the "alloc_size" attribute for the corresponding allocation
> + functions to determine the object size;
> +
> + For B, we use the SIZE info of the TYPE attached to the corresponding access.
> + (We treat counted_by attribute as a complement to the SIZE info of the TYPE
> + for FMA)
> +
> + The only other way in C which ensures that a pointer actually points
> + to an object of the correct type is 'static':
> +
> + void foo(struct P *p[static 1]);
> +
> + See https://gcc.gnu.org/pipermail/gcc-patches/2023-July/624814.html
> + for more details. */
> +
> +/* in the following function, malloc allocated more space than the value
> + of counted_by attribute. Then what's the correct behavior we expect
> + the __builtin_dynamic_object_size should have for each of the cases? */
> +
> +static struct annotated * noinline alloc_buf_more (size_t index)
> +{
> + struct annotated *p;
> + size_t allocated_size
> + = MAX (sizeof (struct annotated),
> + (__builtin_offsetof (struct annotated, array[0])
> + + (index + SIZE_BUMP) * sizeof (char)));
> + p = (struct annotated *) malloc (allocated_size);
> +
> + p->foo = index;
> +
> + /*when checking the observed access p->array, we have info on both
> + observered allocation and observed access,
> + A. from observed allocation:
> + allocated_size - offsetof (struct annotated, array[0])
> + B. from observed access: p->foo * sizeof (char)
> + */
> +
> + /* for size in the whole object: always uses A. */
> + /* for size in the sub-object: chose the smaller of A and B.
> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
> + * for details on why. */
> +
> + /* for MAXIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 1),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /* for MINIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 2),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 3),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /*when checking the pointer p, we only have info on the observed allocation.
> + So, the object size info can only been obtained from the call to malloc.
> + for both MAXIMUM and MINIMUM: A = (index + SIZE_BUMP) * sizeof (char) */
> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
> + return p;
> +}
> +
> +/* in the following function, malloc allocated less space than the value
> + of counted_by attribute. Then what's the correct behavior we expect
> + the __builtin_dynamic_object_size should have for each of the cases?
> + NOTE: this is an user error, GCC should issue warnings for such case.
> + this is a seperate issue we should address later. */
> +
> +static struct annotated * noinline alloc_buf_less (size_t index)
> +{
> + struct annotated *p;
> + size_t allocated_size
> + = MAX (sizeof (struct annotated),
> + (__builtin_offsetof (struct annotated, array[0])
> + + (index) * sizeof (char)));
> + p = (struct annotated *) malloc (allocated_size);
> +
> + p->foo = index + SIZE_BUMP;
> +
> + /*when checking the observed access p->array, we have info on both
> + observered allocation and observed access,
> + A. from observed allocation:
> + allocated_size - offsetof (struct annotated, array[0])
> + B. from observed access: p->foo * sizeof (char)
> + */
> +
> + /* for size in the whole object: always uses A. */
> + /* for size in the sub-object: chose the smaller of A and B.
> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
> + * for details on why. */
> +
> + /* for MAXIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 1),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /* for MINIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 2),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 3),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /*when checking the pointer p, we only have info on the observed
> + allocation. So, the object size info can only been obtained from
> + the call to malloc. */
> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
> + return p;
> +}
> +
> +int main ()
> +{
> + struct annotated *p, *q;
> + p = alloc_buf_more (10);
> + q = alloc_buf_less (10);
> +
> + /*when checking the observed access p->array, we only have info on the
> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
> + info on the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0), -1);
> + expect(__builtin_dynamic_object_size(p->array, 1), p->foo * sizeof(char));
> + expect(__builtin_dynamic_object_size(p->array, 2), 0);
> + expect(__builtin_dynamic_object_size(p->array, 3), p->foo * sizeof(char));
> + /*when checking the pointer p, we have no observed allocation nor observed
> + access, therefore, we cannot determine the size info here. */
> + expect(__builtin_dynamic_object_size(p, 0), -1);
> + expect(__builtin_dynamic_object_size(p, 1), -1);
> + expect(__builtin_dynamic_object_size(p, 2), 0);
> + expect(__builtin_dynamic_object_size(p, 3), 0);
> +
> + /*when checking the observed access p->array, we only have info on the
> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
> + info on the whole object. */
> + expect(__builtin_dynamic_object_size(q->array, 0), -1);
> + expect(__builtin_dynamic_object_size(q->array, 1), q->foo * sizeof(char));
> + expect(__builtin_dynamic_object_size(q->array, 2), 0);
> + expect(__builtin_dynamic_object_size(q->array, 3), q->foo * sizeof(char));
> + /*when checking the pointer p, we have no observed allocation nor observed
> + access, therefore, we cannot determine the size info here. */
> + expect(__builtin_dynamic_object_size(q, 0), -1);
> + expect(__builtin_dynamic_object_size(q, 1), -1);
> + expect(__builtin_dynamic_object_size(q, 2), 0);
> + expect(__builtin_dynamic_object_size(q, 3), 0);
> +
> + DONE ();
> +}
> diff --git a/gcc/tree-object-size.cc b/gcc/tree-object-size.cc
> index a62af0500563..cf7843c5684b 100644
> --- a/gcc/tree-object-size.cc
> +++ b/gcc/tree-object-size.cc
> @@ -585,6 +585,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> if (pt_var != TREE_OPERAND (ptr, 0))
> {
> tree var;
> + tree counted_by_ref = NULL_TREE;
>
> if (object_size_type & OST_SUBOBJECT)
> {
> @@ -600,11 +601,12 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> var = TREE_OPERAND (var, 0);
> if (var != pt_var && TREE_CODE (var) == ARRAY_REF)
> var = TREE_OPERAND (var, 0);
> - if (! TYPE_SIZE_UNIT (TREE_TYPE (var))
> + if (! component_ref_has_counted_by_p (var)
> + && ((! TYPE_SIZE_UNIT (TREE_TYPE (var))
> || ! tree_fits_uhwi_p (TYPE_SIZE_UNIT (TREE_TYPE (var)))
> || (pt_var_size && TREE_CODE (pt_var_size) == INTEGER_CST
> && tree_int_cst_lt (pt_var_size,
> - TYPE_SIZE_UNIT (TREE_TYPE (var)))))
> + TYPE_SIZE_UNIT (TREE_TYPE (var)))))))
> var = pt_var;
> else if (var != pt_var && TREE_CODE (pt_var) == MEM_REF)
> {
> @@ -612,6 +614,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> /* For &X->fld, compute object size if fld isn't a flexible array
> member. */
> bool is_flexible_array_mem_ref = false;
> +
> while (v && v != pt_var)
> switch (TREE_CODE (v))
> {
> @@ -660,6 +663,8 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> /* Now the ref is to an array type. */
> gcc_assert (TREE_CODE (TREE_TYPE (v)) == ARRAY_TYPE);
> is_flexible_array_mem_ref = array_ref_flexible_size_p (v);
> + counted_by_ref = component_ref_get_counted_by (v);
> +
> while (v != pt_var && TREE_CODE (v) == COMPONENT_REF)
> if (TREE_CODE (TREE_TYPE (TREE_OPERAND (v, 0)))
> != UNION_TYPE
> @@ -673,8 +678,11 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> == RECORD_TYPE)
> {
> /* compute object size only if v is not a
> - flexible array member. */
> - if (!is_flexible_array_mem_ref)
> + flexible array member or the flexible array member
> + has a known element count indicated by the user
> + through attribute counted_by. */
> + if (!is_flexible_array_mem_ref
> + || counted_by_ref)
> {
> v = NULL_TREE;
> break;
> @@ -707,9 +715,24 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>
> if (var != pt_var)
> {
> - var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
> - if (!TREE_CONSTANT (var_size))
> - var_size = get_or_create_ssa_default_def (cfun, var_size);
> + if (!counted_by_ref)
> + {
> + var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
> + if (!TREE_CONSTANT (var_size))
> + var_size = get_or_create_ssa_default_def (cfun, var_size);
> + }
> + else
> + {
> + gcc_assert (TREE_CODE (var) == COMPONENT_REF
> + && TREE_CODE (TREE_TYPE (var)) == ARRAY_TYPE);
> + tree element_size = TYPE_SIZE_UNIT (TREE_TYPE (TREE_TYPE (var)));
> + var_size
> + = size_binop (MULT_EXPR,
> + fold_convert (sizetype, counted_by_ref),
> + fold_convert (sizetype, element_size));
> + if (!todo)
> + todo = TODO_update_ssa_only_virtuals;
> + }
> if (!var_size)
> return false;
> }
> diff --git a/gcc/tree.cc b/gcc/tree.cc
> index fcd36ae0cd74..3b6ddcbdcbf8 100644
> --- a/gcc/tree.cc
> +++ b/gcc/tree.cc
> @@ -12745,6 +12745,32 @@ array_ref_element_size (tree exp)
> return SUBSTITUTE_PLACEHOLDER_IN_EXPR (TYPE_SIZE_UNIT (elmt_type), exp);
> }
>
> +/* For a component_ref that has an array type ARRAY_REF, return TRUE when
> + an counted_by attribute attached to the corresponding FIELD_DECL.
> + return FALSE otherwise. */
> +bool
> +component_ref_has_counted_by_p (tree array_ref)
> +{
> + if (TREE_CODE (array_ref) != COMPONENT_REF)
> + return false;
> +
> + if (TREE_CODE (TREE_TYPE (array_ref)) != ARRAY_TYPE)
> + return false;
> +
> + tree struct_object = TREE_OPERAND (array_ref, 0);
> + tree struct_type = TREE_TYPE (struct_object);
> +
> + if (!RECORD_OR_UNION_TYPE_P (struct_type))
> + return false;
> + tree field_decl = TREE_OPERAND (array_ref, 1);
> + tree attr_counted_by = lookup_attribute ("counted_by",
> + DECL_ATTRIBUTES (field_decl));
> +
> + if (!attr_counted_by)
> + return false;
> + return true;
> +}
> +
> /* Given a field list, FIELDLIST, of a structure/union, return a TREE_LIST,
> with each TREE_VALUE a FIELD_DECL stepping down the chain to the FIELD
> whose name is FIELDNAME, which is the last TREE_VALUE of the list.
> @@ -12771,7 +12797,7 @@ get_named_field (tree fieldlist, const char *fieldname)
> fields inside it recursively. */
> else if (RECORD_OR_UNION_TYPE_P (TREE_TYPE (field)))
> if ((named_field = get_named_field (TYPE_FIELDS (TREE_TYPE (field)),
> - fieldname)) != NULL_TREE)
> + fieldname)) != NULL_TREE)
> {
> named_field = tree_cons (NULL_TREE, field, named_field);
> break;
> @@ -12784,6 +12810,73 @@ get_named_field (tree fieldlist, const char *fieldname)
> return named_field;
> }
>
> +/* For a component_ref that has an array type ARRAY_REF, get the object that
> + represents its counted_by per the attribute counted_by attached to
> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
> + object.
> + For example, if:
> +
> + struct P {
> + int k;
> + int x[] __attribute__ ((counted_by (k)));
> + } *p;
> +
> + for the following reference:
> +
> + p->x[b]
> +
> + the object that represents its element count will be:
> +
> + p->k
> +
> + So, when component_ref_get_counted_by (p->x[b]) is called, p->k should be
> + returned.
> +*/
> +
> +tree
> +component_ref_get_counted_by (tree array_ref)
> +{
> + if (! component_ref_has_counted_by_p (array_ref))
> + return NULL_TREE;
> +
> + tree struct_object = TREE_OPERAND (array_ref, 0);
> + tree struct_type = TREE_TYPE (struct_object);
> + tree field_decl = TREE_OPERAND (array_ref, 1);
> + tree attr_counted_by = lookup_attribute ("counted_by",
> + DECL_ATTRIBUTES (field_decl));
> + gcc_assert (attr_counted_by);
> +
> + /* If there is an counted_by attribute attached to the field,
> + get the field that maps to the counted_by. */
> +
> + const char *fieldname
> + = IDENTIFIER_POINTER (TREE_VALUE (TREE_VALUE (attr_counted_by)));
> +
> + tree counted_by_field = get_named_field (TYPE_FIELDS (struct_type),
> + fieldname);
> +
> + gcc_assert (counted_by_field);
> +
> + /* generate the tree node that represent the counted_by of this array
> + ref. This is a (possible nested) COMPONENT_REF to the counted_by_field
> + of the containing structure. */
> +
> + tree counted_by_ref = NULL_TREE;
> + tree object = struct_object;
> + do
> + {
> + tree field = TREE_VALUE (counted_by_field);
> +
> + counted_by_ref = build3 (COMPONENT_REF,
> + TREE_TYPE (field),
> + unshare_expr (object), field,
> + NULL_TREE);
> + object = counted_by_ref;
> + counted_by_field = TREE_CHAIN (counted_by_field);
> + }
> + while (counted_by_field);
> + return counted_by_ref;
> +}
>
> /* Return a tree representing the lower bound of the array mentioned in
> EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
> diff --git a/gcc/tree.h b/gcc/tree.h
> index 4859becaa1e7..07eed7219835 100644
> --- a/gcc/tree.h
> +++ b/gcc/tree.h
> @@ -5619,11 +5619,21 @@ extern tree get_base_address (tree t);
> of EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
> extern tree array_ref_element_size (tree);
>
> +/* Give a component_ref that has an array type, return true when an
> + attribute counted_by attached to the corresponding FIELD_DECL. */
> +extern bool component_ref_has_counted_by_p (tree);
> +
> /* Given a field list, FIELDLIST, of a structure/union, return the FIELD whose
> name is FIELDNAME, return NULL_TREE if such field is not found.
> searching nested anonymous structure/union recursively. */
> extern tree get_named_field (tree, const char *);
>
> +/* Give a component_ref that has an array type, return the object that
> + represents its counted_by per the attribute counted_by attached to
> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
> + object. */
> +extern tree component_ref_get_counted_by (tree);
> +
> /* Return a typenode for the "standard" C type with a given name. */
> extern tree get_typenode_from_name (const char *);
>
> --
> 2.31.1
>
Hi,
I’d like to ping this patch set one more time.
Thanks
Qing
> On Aug 25, 2023, at 11:24 AM, Qing Zhao <qing.zhao@oracle.com> wrote:
>
> Use the counted_by atribute info in builtin object size to compute the
> subobject size for flexible array members.
>
> gcc/ChangeLog:
>
> PR C/108896
> * tree-object-size.cc (addr_object_size): Use the counted_by
> attribute info.
> * tree.cc (component_ref_has_counted_by_p): New function.
> (component_ref_get_counted_by): New function.
> * tree.h (component_ref_has_counted_by_p): New prototype.
> (component_ref_get_counted_by): New prototype.
>
> gcc/testsuite/ChangeLog:
>
> PR C/108896
> * gcc.dg/flex-array-counted-by-2.c: New test.
> * gcc.dg/flex-array-counted-by-3.c: New test.
> ---
> .../gcc.dg/flex-array-counted-by-2.c | 74 ++++++
> .../gcc.dg/flex-array-counted-by-3.c | 210 ++++++++++++++++++
> gcc/tree-object-size.cc | 37 ++-
> gcc/tree.cc | 95 +++++++-
> gcc/tree.h | 10 +
> 5 files changed, 418 insertions(+), 8 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
>
> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> new file mode 100644
> index 000000000000..ec580c1f1f01
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> @@ -0,0 +1,74 @@
> +/* test the attribute counted_by and its usage in
> + * __builtin_dynamic_object_size. */
> +/* { dg-do run } */
> +/* { dg-options "-O2" } */
> +
> +#include "builtin-object-size-common.h"
> +
> +#define expect(p, _v) do { \
> + size_t v = _v; \
> + if (p == v) \
> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
> + else \
> + { \
> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
> + FAIL (); \
> + } \
> +} while (0);
> +
> +struct flex {
> + int b;
> + int c[];
> +} *array_flex;
> +
> +struct annotated {
> + int b;
> + int c[] __attribute__ ((counted_by (b)));
> +} *array_annotated;
> +
> +struct nested_annotated {
> + struct {
> + union {
> + int b;
> + float f;
> + };
> + int n;
> + };
> + int c[] __attribute__ ((counted_by (b)));
> +} *array_nested_annotated;
> +
> +void __attribute__((__noinline__)) setup (int normal_count, int attr_count)
> +{
> + array_flex
> + = (struct flex *)malloc (sizeof (struct flex)
> + + normal_count * sizeof (int));
> + array_flex->b = normal_count;
> +
> + array_annotated
> + = (struct annotated *)malloc (sizeof (struct annotated)
> + + attr_count * sizeof (int));
> + array_annotated->b = attr_count;
> +
> + array_nested_annotated
> + = (struct nested_annotated *)malloc (sizeof (struct nested_annotated)
> + + attr_count * sizeof (int));
> + array_nested_annotated->b = attr_count;
> +
> + return;
> +}
> +
> +void __attribute__((__noinline__)) test ()
> +{
> + expect(__builtin_dynamic_object_size(array_flex->c, 1), -1);
> + expect(__builtin_dynamic_object_size(array_annotated->c, 1),
> + array_annotated->b * sizeof (int));
> + expect(__builtin_dynamic_object_size(array_nested_annotated->c, 1),
> + array_nested_annotated->b * sizeof (int));
> +}
> +
> +int main(int argc, char *argv[])
> +{
> + setup (10,10);
> + test ();
> + DONE ();
> +}
> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
> new file mode 100644
> index 000000000000..a0c3cb88ec71
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
> @@ -0,0 +1,210 @@
> +/* test the attribute counted_by and its usage in
> +__builtin_dynamic_object_size: what's the correct behavior when the
> +allocation size mismatched with the value of counted_by attribute? */
> +/* { dg-do run } */
> +/* { dg-options "-O -fstrict-flex-arrays=3" } */
> +
> +#include "builtin-object-size-common.h"
> +
> +struct annotated {
> + size_t foo;
> + char others;
> + char array[] __attribute__((counted_by (foo)));
> +};
> +
> +#define expect(p, _v) do { \
> + size_t v = _v; \
> + if (p == v) \
> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
> + else \
> + { \
> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
> + FAIL (); \
> + } \
> +} while (0);
> +
> +#define noinline __attribute__((__noinline__))
> +#define SIZE_BUMP 10
> +#define MAX(a, b) ((a) > (b) ? (a) : (b))
> +#define MIN(a, b) ((a) < (b) ? (a) : (b))
> +
> +/* In general, Due to type casting, the type for the pointee of a pointer
> + does not say anything about the object it points to,
> + So, __builtin_object_size can not directly use the type of the pointee
> + to decide the size of the object the pointer points to.
> +
> + there are only two reliable ways:
> + A. observed allocations (call to the allocation functions in the routine)
> + B. observed accesses (read or write access to the location of the
> + pointer points to)
> +
> + that provide information about the type/existence of an object at
> + the corresponding address.
> +
> + for A, we use the "alloc_size" attribute for the corresponding allocation
> + functions to determine the object size;
> +
> + For B, we use the SIZE info of the TYPE attached to the corresponding access.
> + (We treat counted_by attribute as a complement to the SIZE info of the TYPE
> + for FMA)
> +
> + The only other way in C which ensures that a pointer actually points
> + to an object of the correct type is 'static':
> +
> + void foo(struct P *p[static 1]);
> +
> + See https://gcc.gnu.org/pipermail/gcc-patches/2023-July/624814.html
> + for more details. */
> +
> +/* in the following function, malloc allocated more space than the value
> + of counted_by attribute. Then what's the correct behavior we expect
> + the __builtin_dynamic_object_size should have for each of the cases? */
> +
> +static struct annotated * noinline alloc_buf_more (size_t index)
> +{
> + struct annotated *p;
> + size_t allocated_size
> + = MAX (sizeof (struct annotated),
> + (__builtin_offsetof (struct annotated, array[0])
> + + (index + SIZE_BUMP) * sizeof (char)));
> + p = (struct annotated *) malloc (allocated_size);
> +
> + p->foo = index;
> +
> + /*when checking the observed access p->array, we have info on both
> + observered allocation and observed access,
> + A. from observed allocation:
> + allocated_size - offsetof (struct annotated, array[0])
> + B. from observed access: p->foo * sizeof (char)
> + */
> +
> + /* for size in the whole object: always uses A. */
> + /* for size in the sub-object: chose the smaller of A and B.
> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
> + * for details on why. */
> +
> + /* for MAXIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 1),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /* for MINIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 2),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 3),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /*when checking the pointer p, we only have info on the observed allocation.
> + So, the object size info can only been obtained from the call to malloc.
> + for both MAXIMUM and MINIMUM: A = (index + SIZE_BUMP) * sizeof (char) */
> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
> + return p;
> +}
> +
> +/* in the following function, malloc allocated less space than the value
> + of counted_by attribute. Then what's the correct behavior we expect
> + the __builtin_dynamic_object_size should have for each of the cases?
> + NOTE: this is an user error, GCC should issue warnings for such case.
> + this is a seperate issue we should address later. */
> +
> +static struct annotated * noinline alloc_buf_less (size_t index)
> +{
> + struct annotated *p;
> + size_t allocated_size
> + = MAX (sizeof (struct annotated),
> + (__builtin_offsetof (struct annotated, array[0])
> + + (index) * sizeof (char)));
> + p = (struct annotated *) malloc (allocated_size);
> +
> + p->foo = index + SIZE_BUMP;
> +
> + /*when checking the observed access p->array, we have info on both
> + observered allocation and observed access,
> + A. from observed allocation:
> + allocated_size - offsetof (struct annotated, array[0])
> + B. from observed access: p->foo * sizeof (char)
> + */
> +
> + /* for size in the whole object: always uses A. */
> + /* for size in the sub-object: chose the smaller of A and B.
> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
> + * for details on why. */
> +
> + /* for MAXIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 1),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /* for MINIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 2),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 3),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /*when checking the pointer p, we only have info on the observed
> + allocation. So, the object size info can only been obtained from
> + the call to malloc. */
> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
> + return p;
> +}
> +
> +int main ()
> +{
> + struct annotated *p, *q;
> + p = alloc_buf_more (10);
> + q = alloc_buf_less (10);
> +
> + /*when checking the observed access p->array, we only have info on the
> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
> + info on the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0), -1);
> + expect(__builtin_dynamic_object_size(p->array, 1), p->foo * sizeof(char));
> + expect(__builtin_dynamic_object_size(p->array, 2), 0);
> + expect(__builtin_dynamic_object_size(p->array, 3), p->foo * sizeof(char));
> + /*when checking the pointer p, we have no observed allocation nor observed
> + access, therefore, we cannot determine the size info here. */
> + expect(__builtin_dynamic_object_size(p, 0), -1);
> + expect(__builtin_dynamic_object_size(p, 1), -1);
> + expect(__builtin_dynamic_object_size(p, 2), 0);
> + expect(__builtin_dynamic_object_size(p, 3), 0);
> +
> + /*when checking the observed access p->array, we only have info on the
> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
> + info on the whole object. */
> + expect(__builtin_dynamic_object_size(q->array, 0), -1);
> + expect(__builtin_dynamic_object_size(q->array, 1), q->foo * sizeof(char));
> + expect(__builtin_dynamic_object_size(q->array, 2), 0);
> + expect(__builtin_dynamic_object_size(q->array, 3), q->foo * sizeof(char));
> + /*when checking the pointer p, we have no observed allocation nor observed
> + access, therefore, we cannot determine the size info here. */
> + expect(__builtin_dynamic_object_size(q, 0), -1);
> + expect(__builtin_dynamic_object_size(q, 1), -1);
> + expect(__builtin_dynamic_object_size(q, 2), 0);
> + expect(__builtin_dynamic_object_size(q, 3), 0);
> +
> + DONE ();
> +}
> diff --git a/gcc/tree-object-size.cc b/gcc/tree-object-size.cc
> index a62af0500563..cf7843c5684b 100644
> --- a/gcc/tree-object-size.cc
> +++ b/gcc/tree-object-size.cc
> @@ -585,6 +585,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> if (pt_var != TREE_OPERAND (ptr, 0))
> {
> tree var;
> + tree counted_by_ref = NULL_TREE;
>
> if (object_size_type & OST_SUBOBJECT)
> {
> @@ -600,11 +601,12 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> var = TREE_OPERAND (var, 0);
> if (var != pt_var && TREE_CODE (var) == ARRAY_REF)
> var = TREE_OPERAND (var, 0);
> - if (! TYPE_SIZE_UNIT (TREE_TYPE (var))
> + if (! component_ref_has_counted_by_p (var)
> + && ((! TYPE_SIZE_UNIT (TREE_TYPE (var))
> || ! tree_fits_uhwi_p (TYPE_SIZE_UNIT (TREE_TYPE (var)))
> || (pt_var_size && TREE_CODE (pt_var_size) == INTEGER_CST
> && tree_int_cst_lt (pt_var_size,
> - TYPE_SIZE_UNIT (TREE_TYPE (var)))))
> + TYPE_SIZE_UNIT (TREE_TYPE (var)))))))
> var = pt_var;
> else if (var != pt_var && TREE_CODE (pt_var) == MEM_REF)
> {
> @@ -612,6 +614,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> /* For &X->fld, compute object size if fld isn't a flexible array
> member. */
> bool is_flexible_array_mem_ref = false;
> +
> while (v && v != pt_var)
> switch (TREE_CODE (v))
> {
> @@ -660,6 +663,8 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> /* Now the ref is to an array type. */
> gcc_assert (TREE_CODE (TREE_TYPE (v)) == ARRAY_TYPE);
> is_flexible_array_mem_ref = array_ref_flexible_size_p (v);
> + counted_by_ref = component_ref_get_counted_by (v);
> +
> while (v != pt_var && TREE_CODE (v) == COMPONENT_REF)
> if (TREE_CODE (TREE_TYPE (TREE_OPERAND (v, 0)))
> != UNION_TYPE
> @@ -673,8 +678,11 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> == RECORD_TYPE)
> {
> /* compute object size only if v is not a
> - flexible array member. */
> - if (!is_flexible_array_mem_ref)
> + flexible array member or the flexible array member
> + has a known element count indicated by the user
> + through attribute counted_by. */
> + if (!is_flexible_array_mem_ref
> + || counted_by_ref)
> {
> v = NULL_TREE;
> break;
> @@ -707,9 +715,24 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>
> if (var != pt_var)
> {
> - var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
> - if (!TREE_CONSTANT (var_size))
> - var_size = get_or_create_ssa_default_def (cfun, var_size);
> + if (!counted_by_ref)
> + {
> + var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
> + if (!TREE_CONSTANT (var_size))
> + var_size = get_or_create_ssa_default_def (cfun, var_size);
> + }
> + else
> + {
> + gcc_assert (TREE_CODE (var) == COMPONENT_REF
> + && TREE_CODE (TREE_TYPE (var)) == ARRAY_TYPE);
> + tree element_size = TYPE_SIZE_UNIT (TREE_TYPE (TREE_TYPE (var)));
> + var_size
> + = size_binop (MULT_EXPR,
> + fold_convert (sizetype, counted_by_ref),
> + fold_convert (sizetype, element_size));
> + if (!todo)
> + todo = TODO_update_ssa_only_virtuals;
> + }
> if (!var_size)
> return false;
> }
> diff --git a/gcc/tree.cc b/gcc/tree.cc
> index fcd36ae0cd74..3b6ddcbdcbf8 100644
> --- a/gcc/tree.cc
> +++ b/gcc/tree.cc
> @@ -12745,6 +12745,32 @@ array_ref_element_size (tree exp)
> return SUBSTITUTE_PLACEHOLDER_IN_EXPR (TYPE_SIZE_UNIT (elmt_type), exp);
> }
>
> +/* For a component_ref that has an array type ARRAY_REF, return TRUE when
> + an counted_by attribute attached to the corresponding FIELD_DECL.
> + return FALSE otherwise. */
> +bool
> +component_ref_has_counted_by_p (tree array_ref)
> +{
> + if (TREE_CODE (array_ref) != COMPONENT_REF)
> + return false;
> +
> + if (TREE_CODE (TREE_TYPE (array_ref)) != ARRAY_TYPE)
> + return false;
> +
> + tree struct_object = TREE_OPERAND (array_ref, 0);
> + tree struct_type = TREE_TYPE (struct_object);
> +
> + if (!RECORD_OR_UNION_TYPE_P (struct_type))
> + return false;
> + tree field_decl = TREE_OPERAND (array_ref, 1);
> + tree attr_counted_by = lookup_attribute ("counted_by",
> + DECL_ATTRIBUTES (field_decl));
> +
> + if (!attr_counted_by)
> + return false;
> + return true;
> +}
> +
> /* Given a field list, FIELDLIST, of a structure/union, return a TREE_LIST,
> with each TREE_VALUE a FIELD_DECL stepping down the chain to the FIELD
> whose name is FIELDNAME, which is the last TREE_VALUE of the list.
> @@ -12771,7 +12797,7 @@ get_named_field (tree fieldlist, const char *fieldname)
> fields inside it recursively. */
> else if (RECORD_OR_UNION_TYPE_P (TREE_TYPE (field)))
> if ((named_field = get_named_field (TYPE_FIELDS (TREE_TYPE (field)),
> - fieldname)) != NULL_TREE)
> + fieldname)) != NULL_TREE)
> {
> named_field = tree_cons (NULL_TREE, field, named_field);
> break;
> @@ -12784,6 +12810,73 @@ get_named_field (tree fieldlist, const char *fieldname)
> return named_field;
> }
>
> +/* For a component_ref that has an array type ARRAY_REF, get the object that
> + represents its counted_by per the attribute counted_by attached to
> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
> + object.
> + For example, if:
> +
> + struct P {
> + int k;
> + int x[] __attribute__ ((counted_by (k)));
> + } *p;
> +
> + for the following reference:
> +
> + p->x[b]
> +
> + the object that represents its element count will be:
> +
> + p->k
> +
> + So, when component_ref_get_counted_by (p->x[b]) is called, p->k should be
> + returned.
> +*/
> +
> +tree
> +component_ref_get_counted_by (tree array_ref)
> +{
> + if (! component_ref_has_counted_by_p (array_ref))
> + return NULL_TREE;
> +
> + tree struct_object = TREE_OPERAND (array_ref, 0);
> + tree struct_type = TREE_TYPE (struct_object);
> + tree field_decl = TREE_OPERAND (array_ref, 1);
> + tree attr_counted_by = lookup_attribute ("counted_by",
> + DECL_ATTRIBUTES (field_decl));
> + gcc_assert (attr_counted_by);
> +
> + /* If there is an counted_by attribute attached to the field,
> + get the field that maps to the counted_by. */
> +
> + const char *fieldname
> + = IDENTIFIER_POINTER (TREE_VALUE (TREE_VALUE (attr_counted_by)));
> +
> + tree counted_by_field = get_named_field (TYPE_FIELDS (struct_type),
> + fieldname);
> +
> + gcc_assert (counted_by_field);
> +
> + /* generate the tree node that represent the counted_by of this array
> + ref. This is a (possible nested) COMPONENT_REF to the counted_by_field
> + of the containing structure. */
> +
> + tree counted_by_ref = NULL_TREE;
> + tree object = struct_object;
> + do
> + {
> + tree field = TREE_VALUE (counted_by_field);
> +
> + counted_by_ref = build3 (COMPONENT_REF,
> + TREE_TYPE (field),
> + unshare_expr (object), field,
> + NULL_TREE);
> + object = counted_by_ref;
> + counted_by_field = TREE_CHAIN (counted_by_field);
> + }
> + while (counted_by_field);
> + return counted_by_ref;
> +}
>
> /* Return a tree representing the lower bound of the array mentioned in
> EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
> diff --git a/gcc/tree.h b/gcc/tree.h
> index 4859becaa1e7..07eed7219835 100644
> --- a/gcc/tree.h
> +++ b/gcc/tree.h
> @@ -5619,11 +5619,21 @@ extern tree get_base_address (tree t);
> of EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
> extern tree array_ref_element_size (tree);
>
> +/* Give a component_ref that has an array type, return true when an
> + attribute counted_by attached to the corresponding FIELD_DECL. */
> +extern bool component_ref_has_counted_by_p (tree);
> +
> /* Given a field list, FIELDLIST, of a structure/union, return the FIELD whose
> name is FIELDNAME, return NULL_TREE if such field is not found.
> searching nested anonymous structure/union recursively. */
> extern tree get_named_field (tree, const char *);
>
> +/* Give a component_ref that has an array type, return the object that
> + represents its counted_by per the attribute counted_by attached to
> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
> + object. */
> +extern tree component_ref_get_counted_by (tree);
> +
> /* Return a typenode for the "standard" C type with a given name. */
> extern tree get_typenode_from_name (const char *);
>
> --
> 2.31.1
>
On 2023-08-25 11:24, Qing Zhao wrote:
> Use the counted_by atribute info in builtin object size to compute the
> subobject size for flexible array members.
>
> gcc/ChangeLog:
>
> PR C/108896
> * tree-object-size.cc (addr_object_size): Use the counted_by
> attribute info.
> * tree.cc (component_ref_has_counted_by_p): New function.
> (component_ref_get_counted_by): New function.
> * tree.h (component_ref_has_counted_by_p): New prototype.
> (component_ref_get_counted_by): New prototype.
>
> gcc/testsuite/ChangeLog:
>
> PR C/108896
> * gcc.dg/flex-array-counted-by-2.c: New test.
> * gcc.dg/flex-array-counted-by-3.c: New test.
> ---
> .../gcc.dg/flex-array-counted-by-2.c | 74 ++++++
> .../gcc.dg/flex-array-counted-by-3.c | 210 ++++++++++++++++++
> gcc/tree-object-size.cc | 37 ++-
> gcc/tree.cc | 95 +++++++-
> gcc/tree.h | 10 +
> 5 files changed, 418 insertions(+), 8 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
>
> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> new file mode 100644
> index 000000000000..ec580c1f1f01
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
> @@ -0,0 +1,74 @@
> +/* test the attribute counted_by and its usage in
> + * __builtin_dynamic_object_size. */
> +/* { dg-do run } */
> +/* { dg-options "-O2" } */
> +
> +#include "builtin-object-size-common.h"
> +
> +#define expect(p, _v) do { \
> + size_t v = _v; \
> + if (p == v) \
> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
> + else \
> + { \
> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
> + FAIL (); \
> + } \
> +} while (0);
You're using this in a bunch of tests already; does it make sense to
consolidate it into builtin-object-size-common.h?
> +
> +struct flex {
> + int b;
> + int c[];
> +} *array_flex;
> +
> +struct annotated {
> + int b;
> + int c[] __attribute__ ((counted_by (b)));
> +} *array_annotated;
> +
> +struct nested_annotated {
> + struct {
> + union {
> + int b;
> + float f;
> + };
> + int n;
> + };
> + int c[] __attribute__ ((counted_by (b)));
> +} *array_nested_annotated;
> +
> +void __attribute__((__noinline__)) setup (int normal_count, int attr_count)
> +{
> + array_flex
> + = (struct flex *)malloc (sizeof (struct flex)
> + + normal_count * sizeof (int));
> + array_flex->b = normal_count;
> +
> + array_annotated
> + = (struct annotated *)malloc (sizeof (struct annotated)
> + + attr_count * sizeof (int));
> + array_annotated->b = attr_count;
> +
> + array_nested_annotated
> + = (struct nested_annotated *)malloc (sizeof (struct nested_annotated)
> + + attr_count * sizeof (int));
> + array_nested_annotated->b = attr_count;
> +
> + return;
> +}
> +
> +void __attribute__((__noinline__)) test ()
> +{
> + expect(__builtin_dynamic_object_size(array_flex->c, 1), -1);
> + expect(__builtin_dynamic_object_size(array_annotated->c, 1),
> + array_annotated->b * sizeof (int));
> + expect(__builtin_dynamic_object_size(array_nested_annotated->c, 1),
> + array_nested_annotated->b * sizeof (int));
> +}
Maybe another test where the allocation, size assignment and __bdos call
happen in the same function, where the allocator is not recognized by gcc:
void *
__attribute__ ((noinline))
alloc (size_t sz)
{
return __builtin_malloc (sz);
}
void test (size_t sz)
{
array_annotated = alloc (sz);
array_annotated->b = sz;
return __builtin_dynamic_object_size (array_annotated->c, 1);
}
The interesting thing to test (and ensure in the codegen) is that the
assignment to array_annotated->b does not get reordered to below the
__builtin_dynamic_object_size call since technically there is no data
dependency between the two.
> +
> +int main(int argc, char *argv[])
> +{
> + setup (10,10);
> + test ();
> + DONE ();
> +}
> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
> new file mode 100644
> index 000000000000..a0c3cb88ec71
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
> @@ -0,0 +1,210 @@
> +/* test the attribute counted_by and its usage in
> +__builtin_dynamic_object_size: what's the correct behavior when the
> +allocation size mismatched with the value of counted_by attribute? */
If the behaviour is undefined, does it make sense to add tests for this?
Maybe once you have a -Wmismatched-counted-by or similar, we could
have tests for that. I guess the counter-argument is that we keep track
of this behaviour but not necessarily guarantee it.
> +/* { dg-do run } */
> +/* { dg-options "-O -fstrict-flex-arrays=3" } */
> +
> +#include "builtin-object-size-common.h"
> +
> +struct annotated {
> + size_t foo;
> + char others;
> + char array[] __attribute__((counted_by (foo)));
> +};
> +
> +#define expect(p, _v) do { \
> + size_t v = _v; \
> + if (p == v) \
> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
> + else \
> + { \
> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
> + FAIL (); \
> + } \
> +} while (0);
Same, maybe consolidate this into builtin-object-size-common.h.
> +
> +#define noinline __attribute__((__noinline__))
> +#define SIZE_BUMP 10
> +#define MAX(a, b) ((a) > (b) ? (a) : (b))
> +#define MIN(a, b) ((a) < (b) ? (a) : (b))
> +
> +/* In general, Due to type casting, the type for the pointee of a pointer
> + does not say anything about the object it points to,
> + So, __builtin_object_size can not directly use the type of the pointee
> + to decide the size of the object the pointer points to.
> +
> + there are only two reliable ways:
> + A. observed allocations (call to the allocation functions in the routine)
> + B. observed accesses (read or write access to the location of the
> + pointer points to)
> +
> + that provide information about the type/existence of an object at
> + the corresponding address.
> +
> + for A, we use the "alloc_size" attribute for the corresponding allocation
> + functions to determine the object size;
> +
> + For B, we use the SIZE info of the TYPE attached to the corresponding access.
> + (We treat counted_by attribute as a complement to the SIZE info of the TYPE
> + for FMA)
> +
> + The only other way in C which ensures that a pointer actually points
> + to an object of the correct type is 'static':
> +
> + void foo(struct P *p[static 1]);
> +
> + See https://gcc.gnu.org/pipermail/gcc-patches/2023-July/624814.html
> + for more details. */
> +
> +/* in the following function, malloc allocated more space than the value
> + of counted_by attribute. Then what's the correct behavior we expect
> + the __builtin_dynamic_object_size should have for each of the cases? */
> +
> +static struct annotated * noinline alloc_buf_more (size_t index)
> +{
> + struct annotated *p;
> + size_t allocated_size
> + = MAX (sizeof (struct annotated),
> + (__builtin_offsetof (struct annotated, array[0])
> + + (index + SIZE_BUMP) * sizeof (char)));
> + p = (struct annotated *) malloc (allocated_size);
> +
> + p->foo = index;
> +
> + /*when checking the observed access p->array, we have info on both
> + observered allocation and observed access,
> + A. from observed allocation:
> + allocated_size - offsetof (struct annotated, array[0])
> + B. from observed access: p->foo * sizeof (char)
> + */
> +
> + /* for size in the whole object: always uses A. */
> + /* for size in the sub-object: chose the smaller of A and B.
> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
> + * for details on why. */
> +
> + /* for MAXIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 1),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /* for MINIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 2),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 3),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /*when checking the pointer p, we only have info on the observed allocation.
> + So, the object size info can only been obtained from the call to malloc.
> + for both MAXIMUM and MINIMUM: A = (index + SIZE_BUMP) * sizeof (char) */
> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
> + return p;
> +}
> +
> +/* in the following function, malloc allocated less space than the value
> + of counted_by attribute. Then what's the correct behavior we expect
> + the __builtin_dynamic_object_size should have for each of the cases?
> + NOTE: this is an user error, GCC should issue warnings for such case.
> + this is a seperate issue we should address later. */
> +
> +static struct annotated * noinline alloc_buf_less (size_t index)
> +{
> + struct annotated *p;
> + size_t allocated_size
> + = MAX (sizeof (struct annotated),
> + (__builtin_offsetof (struct annotated, array[0])
> + + (index) * sizeof (char)));
> + p = (struct annotated *) malloc (allocated_size);
> +
> + p->foo = index + SIZE_BUMP;
> +
> + /*when checking the observed access p->array, we have info on both
> + observered allocation and observed access,
> + A. from observed allocation:
> + allocated_size - offsetof (struct annotated, array[0])
> + B. from observed access: p->foo * sizeof (char)
> + */
> +
> + /* for size in the whole object: always uses A. */
> + /* for size in the sub-object: chose the smaller of A and B.
> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
> + * for details on why. */
> +
> + /* for MAXIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 1),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /* for MINIMUM size in the whole object: use the allocation size
> + for the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 2),
> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
> +
> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
> + expect(__builtin_dynamic_object_size(p->array, 3),
> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
> + (p->foo) * sizeof(char)));
> +
> + /*when checking the pointer p, we only have info on the observed
> + allocation. So, the object size info can only been obtained from
> + the call to malloc. */
> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
> + return p;
> +}
> +
> +int main ()
> +{
> + struct annotated *p, *q;
> + p = alloc_buf_more (10);
> + q = alloc_buf_less (10);
> +
> + /*when checking the observed access p->array, we only have info on the
> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
> + info on the whole object. */
> + expect(__builtin_dynamic_object_size(p->array, 0), -1);
> + expect(__builtin_dynamic_object_size(p->array, 1), p->foo * sizeof(char));
> + expect(__builtin_dynamic_object_size(p->array, 2), 0);
> + expect(__builtin_dynamic_object_size(p->array, 3), p->foo * sizeof(char));
> + /*when checking the pointer p, we have no observed allocation nor observed
> + access, therefore, we cannot determine the size info here. */
> + expect(__builtin_dynamic_object_size(p, 0), -1);
> + expect(__builtin_dynamic_object_size(p, 1), -1);
> + expect(__builtin_dynamic_object_size(p, 2), 0);
> + expect(__builtin_dynamic_object_size(p, 3), 0);
> +
> + /*when checking the observed access p->array, we only have info on the
> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
> + info on the whole object. */
> + expect(__builtin_dynamic_object_size(q->array, 0), -1);
> + expect(__builtin_dynamic_object_size(q->array, 1), q->foo * sizeof(char));
> + expect(__builtin_dynamic_object_size(q->array, 2), 0);
> + expect(__builtin_dynamic_object_size(q->array, 3), q->foo * sizeof(char));
> + /*when checking the pointer p, we have no observed allocation nor observed
> + access, therefore, we cannot determine the size info here. */
> + expect(__builtin_dynamic_object_size(q, 0), -1);
> + expect(__builtin_dynamic_object_size(q, 1), -1);
> + expect(__builtin_dynamic_object_size(q, 2), 0);
> + expect(__builtin_dynamic_object_size(q, 3), 0);
> +
> + DONE ();
> +}
> diff --git a/gcc/tree-object-size.cc b/gcc/tree-object-size.cc
> index a62af0500563..cf7843c5684b 100644
> --- a/gcc/tree-object-size.cc
> +++ b/gcc/tree-object-size.cc
> @@ -585,6 +585,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> if (pt_var != TREE_OPERAND (ptr, 0))
> {
> tree var;
> + tree counted_by_ref = NULL_TREE;
>
> if (object_size_type & OST_SUBOBJECT)
> {
> @@ -600,11 +601,12 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> var = TREE_OPERAND (var, 0);
> if (var != pt_var && TREE_CODE (var) == ARRAY_REF)
> var = TREE_OPERAND (var, 0);
> - if (! TYPE_SIZE_UNIT (TREE_TYPE (var))
> + if (! component_ref_has_counted_by_p (var)
> + && ((! TYPE_SIZE_UNIT (TREE_TYPE (var))
> || ! tree_fits_uhwi_p (TYPE_SIZE_UNIT (TREE_TYPE (var)))
> || (pt_var_size && TREE_CODE (pt_var_size) == INTEGER_CST
> && tree_int_cst_lt (pt_var_size,
> - TYPE_SIZE_UNIT (TREE_TYPE (var)))))
> + TYPE_SIZE_UNIT (TREE_TYPE (var)))))))
> var = pt_var;
> else if (var != pt_var && TREE_CODE (pt_var) == MEM_REF)
> {
Hmm, only for subobject size? I thought we had consensus on using
sizeof (struct) + counted_by_size as the conservative maximum size for
whole object size too, didn't we?
> @@ -612,6 +614,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> /* For &X->fld, compute object size if fld isn't a flexible array
> member. */
> bool is_flexible_array_mem_ref = false;
> +
> while (v && v != pt_var)
> switch (TREE_CODE (v))
> {
Unnecessary newline.
> @@ -660,6 +663,8 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> /* Now the ref is to an array type. */
> gcc_assert (TREE_CODE (TREE_TYPE (v)) == ARRAY_TYPE);
> is_flexible_array_mem_ref = array_ref_flexible_size_p (v);
> + counted_by_ref = component_ref_get_counted_by (v);
> +
> while (v != pt_var && TREE_CODE (v) == COMPONENT_REF)
> if (TREE_CODE (TREE_TYPE (TREE_OPERAND (v, 0)))
> != UNION_TYPE
> @@ -673,8 +678,11 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
> == RECORD_TYPE)
> {
> /* compute object size only if v is not a
> - flexible array member. */
> - if (!is_flexible_array_mem_ref)
> + flexible array member or the flexible array member
> + has a known element count indicated by the user
> + through attribute counted_by. */
> + if (!is_flexible_array_mem_ref
> + || counted_by_ref)
> {
> v = NULL_TREE;
> break;
> @@ -707,9 +715,24 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>
> if (var != pt_var)
> {
> - var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
> - if (!TREE_CONSTANT (var_size))
> - var_size = get_or_create_ssa_default_def (cfun, var_size);
> + if (!counted_by_ref)
> + {
> + var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
> + if (!TREE_CONSTANT (var_size))
> + var_size = get_or_create_ssa_default_def (cfun, var_size);
> + }
> + else
> + {
> + gcc_assert (TREE_CODE (var) == COMPONENT_REF
> + && TREE_CODE (TREE_TYPE (var)) == ARRAY_TYPE);
> + tree element_size = TYPE_SIZE_UNIT (TREE_TYPE (TREE_TYPE (var)));
> + var_size
> + = size_binop (MULT_EXPR,
> + fold_convert (sizetype, counted_by_ref),
> + fold_convert (sizetype, element_size));
> + if (!todo)
> + todo = TODO_update_ssa_only_virtuals;
> + }
I feel like this could make a good separate function (get_subobject_size
or something like that) to make it easier to read.
> if (!var_size)
> return false;
> }
> diff --git a/gcc/tree.cc b/gcc/tree.cc
> index fcd36ae0cd74..3b6ddcbdcbf8 100644
> --- a/gcc/tree.cc
> +++ b/gcc/tree.cc
> @@ -12745,6 +12745,32 @@ array_ref_element_size (tree exp)
> return SUBSTITUTE_PLACEHOLDER_IN_EXPR (TYPE_SIZE_UNIT (elmt_type), exp);
> }
>
> +/* For a component_ref that has an array type ARRAY_REF, return TRUE when
> + an counted_by attribute attached to the corresponding FIELD_DECL.
> + return FALSE otherwise. */
> +bool
> +component_ref_has_counted_by_p (tree array_ref)
> +{
> + if (TREE_CODE (array_ref) != COMPONENT_REF)
> + return false;
> +
> + if (TREE_CODE (TREE_TYPE (array_ref)) != ARRAY_TYPE)
> + return false;
> +
> + tree struct_object = TREE_OPERAND (array_ref, 0);
> + tree struct_type = TREE_TYPE (struct_object);
> +
> + if (!RECORD_OR_UNION_TYPE_P (struct_type))
> + return false;
> + tree field_decl = TREE_OPERAND (array_ref, 1);
> + tree attr_counted_by = lookup_attribute ("counted_by",
> + DECL_ATTRIBUTES (field_decl));
> +
> + if (!attr_counted_by)
> + return false;
> + return true;
> +}
> +
> /* Given a field list, FIELDLIST, of a structure/union, return a TREE_LIST,
> with each TREE_VALUE a FIELD_DECL stepping down the chain to the FIELD
> whose name is FIELDNAME, which is the last TREE_VALUE of the list.
> @@ -12771,7 +12797,7 @@ get_named_field (tree fieldlist, const char *fieldname)
> fields inside it recursively. */
> else if (RECORD_OR_UNION_TYPE_P (TREE_TYPE (field)))
> if ((named_field = get_named_field (TYPE_FIELDS (TREE_TYPE (field)),
> - fieldname)) != NULL_TREE)
> + fieldname)) != NULL_TREE)
Unrelated whitespace change?
> {
> named_field = tree_cons (NULL_TREE, field, named_field);
> break;
> @@ -12784,6 +12810,73 @@ get_named_field (tree fieldlist, const char *fieldname)
> return named_field;
> }
>
> +/* For a component_ref that has an array type ARRAY_REF, get the object that
> + represents its counted_by per the attribute counted_by attached to
> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
> + object.
> + For example, if:
> +
> + struct P {
> + int k;
> + int x[] __attribute__ ((counted_by (k)));
> + } *p;
> +
> + for the following reference:
> +
> + p->x[b]
> +
> + the object that represents its element count will be:
> +
> + p->k
> +
> + So, when component_ref_get_counted_by (p->x[b]) is called, p->k should be
> + returned.
> +*/
> +
> +tree
> +component_ref_get_counted_by (tree array_ref)
> +{
> + if (! component_ref_has_counted_by_p (array_ref))
> + return NULL_TREE;
> +
> + tree struct_object = TREE_OPERAND (array_ref, 0);
> + tree struct_type = TREE_TYPE (struct_object);
> + tree field_decl = TREE_OPERAND (array_ref, 1);
> + tree attr_counted_by = lookup_attribute ("counted_by",
> + DECL_ATTRIBUTES (field_decl));
> + gcc_assert (attr_counted_by);
> +
> + /* If there is an counted_by attribute attached to the field,
> + get the field that maps to the counted_by. */
> +
> + const char *fieldname
> + = IDENTIFIER_POINTER (TREE_VALUE (TREE_VALUE (attr_counted_by)));
> +
> + tree counted_by_field = get_named_field (TYPE_FIELDS (struct_type),
> + fieldname);
> +
> + gcc_assert (counted_by_field);
> +
> + /* generate the tree node that represent the counted_by of this array
Capitalize first word. Also s/represent/represents/
> + ref. This is a (possible nested) COMPONENT_REF to the counted_by_field
possibly nested
> + of the containing structure. */
> +
> + tree counted_by_ref = NULL_TREE;
> + tree object = struct_object;
> + do
> + {
> + tree field = TREE_VALUE (counted_by_field);
> +
> + counted_by_ref = build3 (COMPONENT_REF,
> + TREE_TYPE (field),
> + unshare_expr (object), field,
> + NULL_TREE);
> + object = counted_by_ref;
> + counted_by_field = TREE_CHAIN (counted_by_field);
> + }
> + while (counted_by_field);
> + return counted_by_ref;
> +}
>
> /* Return a tree representing the lower bound of the array mentioned in
> EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
> diff --git a/gcc/tree.h b/gcc/tree.h
> index 4859becaa1e7..07eed7219835 100644
> --- a/gcc/tree.h
> +++ b/gcc/tree.h
> @@ -5619,11 +5619,21 @@ extern tree get_base_address (tree t);
> of EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
> extern tree array_ref_element_size (tree);
>
> +/* Give a component_ref that has an array type, return true when an
> + attribute counted_by attached to the corresponding FIELD_DECL. */
> +extern bool component_ref_has_counted_by_p (tree);
> +
> /* Given a field list, FIELDLIST, of a structure/union, return the FIELD whose
> name is FIELDNAME, return NULL_TREE if such field is not found.
> searching nested anonymous structure/union recursively. */
> extern tree get_named_field (tree, const char *);
>
> +/* Give a component_ref that has an array type, return the object that
> + represents its counted_by per the attribute counted_by attached to
> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
> + object. */
> +extern tree component_ref_get_counted_by (tree);
> +
> /* Return a typenode for the "standard" C type with a given name. */
> extern tree get_typenode_from_name (const char *);
>
Hi, Sid,
Thanks a lot for the detailed comments.
See my responds embedded below.
Qing
> On Oct 5, 2023, at 4:01 PM, Siddhesh Poyarekar <siddhesh@gotplt.org> wrote:
>
>
>
> On 2023-08-25 11:24, Qing Zhao wrote:
>> Use the counted_by atribute info in builtin object size to compute the
>> subobject size for flexible array members.
>> gcc/ChangeLog:
>> PR C/108896
>> * tree-object-size.cc (addr_object_size): Use the counted_by
>> attribute info.
>> * tree.cc (component_ref_has_counted_by_p): New function.
>> (component_ref_get_counted_by): New function.
>> * tree.h (component_ref_has_counted_by_p): New prototype.
>> (component_ref_get_counted_by): New prototype.
>> gcc/testsuite/ChangeLog:
>> PR C/108896
>> * gcc.dg/flex-array-counted-by-2.c: New test.
>> * gcc.dg/flex-array-counted-by-3.c: New test.
>> ---
>> .../gcc.dg/flex-array-counted-by-2.c | 74 ++++++
>> .../gcc.dg/flex-array-counted-by-3.c | 210 ++++++++++++++++++
>> gcc/tree-object-size.cc | 37 ++-
>> gcc/tree.cc | 95 +++++++-
>> gcc/tree.h | 10 +
>> 5 files changed, 418 insertions(+), 8 deletions(-)
>> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
>> create mode 100644 gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
>> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
>> new file mode 100644
>> index 000000000000..ec580c1f1f01
>> --- /dev/null
>> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-2.c
>> @@ -0,0 +1,74 @@
>> +/* test the attribute counted_by and its usage in
>> + * __builtin_dynamic_object_size. */
>> +/* { dg-do run } */
>> +/* { dg-options "-O2" } */
>> +
>> +#include "builtin-object-size-common.h"
>> +
>> +#define expect(p, _v) do { \
>> + size_t v = _v; \
>> + if (p == v) \
>> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
>> + else \
>> + { \
>> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
>> + FAIL (); \
>> + } \
>> +} while (0);
>
> You're using this in a bunch of tests already; does it make sense to consolidate it into builtin-object-size-common.h?
Will do this.
>
>> +
>> +struct flex {
>> + int b;
>> + int c[];
>> +} *array_flex;
>> +
>> +struct annotated {
>> + int b;
>> + int c[] __attribute__ ((counted_by (b)));
>> +} *array_annotated;
>> +
>> +struct nested_annotated {
>> + struct {
>> + union {
>> + int b;
>> + float f;
>> + };
>> + int n;
>> + };
>> + int c[] __attribute__ ((counted_by (b)));
>> +} *array_nested_annotated;
>> +
>> +void __attribute__((__noinline__)) setup (int normal_count, int attr_count)
>> +{
>> + array_flex
>> + = (struct flex *)malloc (sizeof (struct flex)
>> + + normal_count * sizeof (int));
>> + array_flex->b = normal_count;
>> +
>> + array_annotated
>> + = (struct annotated *)malloc (sizeof (struct annotated)
>> + + attr_count * sizeof (int));
>> + array_annotated->b = attr_count;
>> +
>> + array_nested_annotated
>> + = (struct nested_annotated *)malloc (sizeof (struct nested_annotated)
>> + + attr_count * sizeof (int));
>> + array_nested_annotated->b = attr_count;
>> +
>> + return;
>> +}
>> +
>> +void __attribute__((__noinline__)) test ()
>> +{
>> + expect(__builtin_dynamic_object_size(array_flex->c, 1), -1);
>> + expect(__builtin_dynamic_object_size(array_annotated->c, 1),
>> + array_annotated->b * sizeof (int));
>> + expect(__builtin_dynamic_object_size(array_nested_annotated->c, 1),
>> + array_nested_annotated->b * sizeof (int));
>> +}
>
> Maybe another test where the allocation, size assignment and __bdos call happen in the same function, where the allocator is not recognized by gcc:
>
> void *
> __attribute__ ((noinline))
> alloc (size_t sz)
> {
> return __builtin_malloc (sz);
> }
>
> void test (size_t sz)
> {
> array_annotated = alloc (sz);
> array_annotated->b = sz;
> return __builtin_dynamic_object_size (array_annotated->c, 1);
> }
>
> The interesting thing to test (and ensure in the codegen) is that the assignment to array_annotated->b does not get reordered to below the __builtin_dynamic_object_size call since technically there is no data dependency between the two.
Good point.
Will add such testing case.
>
>> +
>> +int main(int argc, char *argv[])
>> +{
>> + setup (10,10);
>> + test ();
>> + DONE ();
>> +}
>> diff --git a/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
>> new file mode 100644
>> index 000000000000..a0c3cb88ec71
>> --- /dev/null
>> +++ b/gcc/testsuite/gcc.dg/flex-array-counted-by-3.c
>> @@ -0,0 +1,210 @@
>> +/* test the attribute counted_by and its usage in
>> +__builtin_dynamic_object_size: what's the correct behavior when the
>> +allocation size mismatched with the value of counted_by attribute? */
>
> If the behaviour is undefined, does it make sense to add tests for this? Maybe once you have a -Wmismatched-counted-by or similar, we could have tests for that. I guess the counter-argument is that we keep track of this behaviour but not necessarily guarantee it.
This testing case was added mainly for documentation purpose. It includes a detailed explanation on how the current _bdo estimates the size of the object.
Even though there is mismatch between the actual allocation size and the value of counted_by attribute, the behavior of the compiler is still defined based on the algorithm.
When -Wmismatched-counted-by is added later, we can update this testing case with new warning messages, but the behavior of _bdo still keep the same.
>
>> +/* { dg-do run } */
>> +/* { dg-options "-O -fstrict-flex-arrays=3" } */
>> +
>> +#include "builtin-object-size-common.h"
>> +
>> +struct annotated {
>> + size_t foo;
>> + char others;
>> + char array[] __attribute__((counted_by (foo)));
>> +};
>> +
>> +#define expect(p, _v) do { \
>> + size_t v = _v; \
>> + if (p == v) \
>> + __builtin_printf ("ok: %s == %zd\n", #p, p); \
>> + else \
>> + { \
>> + __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
>> + FAIL (); \
>> + } \
>> +} while (0);
>
> Same, maybe consolidate this into builtin-object-size-common.h.
Okay.
>
>> +
>> +#define noinline __attribute__((__noinline__))
>> +#define SIZE_BUMP 10
>> +#define MAX(a, b) ((a) > (b) ? (a) : (b))
>> +#define MIN(a, b) ((a) < (b) ? (a) : (b))
>> +
>> +/* In general, Due to type casting, the type for the pointee of a pointer
>> + does not say anything about the object it points to,
>> + So, __builtin_object_size can not directly use the type of the pointee
>> + to decide the size of the object the pointer points to.
>> +
>> + there are only two reliable ways:
>> + A. observed allocations (call to the allocation functions in the routine)
>> + B. observed accesses (read or write access to the location of the
>> + pointer points to)
>> +
>> + that provide information about the type/existence of an object at
>> + the corresponding address.
>> +
>> + for A, we use the "alloc_size" attribute for the corresponding allocation
>> + functions to determine the object size;
>> +
>> + For B, we use the SIZE info of the TYPE attached to the corresponding access.
>> + (We treat counted_by attribute as a complement to the SIZE info of the TYPE
>> + for FMA)
>> +
>> + The only other way in C which ensures that a pointer actually points
>> + to an object of the correct type is 'static':
>> +
>> + void foo(struct P *p[static 1]);
>> +
>> + See https://gcc.gnu.org/pipermail/gcc-patches/2023-July/624814.html
>> + for more details. */
>> +
>> +/* in the following function, malloc allocated more space than the value
>> + of counted_by attribute. Then what's the correct behavior we expect
>> + the __builtin_dynamic_object_size should have for each of the cases? */
>> +
>> +static struct annotated * noinline alloc_buf_more (size_t index)
>> +{
>> + struct annotated *p;
>> + size_t allocated_size
>> + = MAX (sizeof (struct annotated),
>> + (__builtin_offsetof (struct annotated, array[0])
>> + + (index + SIZE_BUMP) * sizeof (char)));
>> + p = (struct annotated *) malloc (allocated_size);
>> +
>> + p->foo = index;
>> +
>> + /*when checking the observed access p->array, we have info on both
>> + observered allocation and observed access,
>> + A. from observed allocation:
>> + allocated_size - offsetof (struct annotated, array[0])
>> + B. from observed access: p->foo * sizeof (char)
>> + */
>> +
>> + /* for size in the whole object: always uses A. */
>> + /* for size in the sub-object: chose the smaller of A and B.
>> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
>> + * for details on why. */
>> +
>> + /* for MAXIMUM size in the whole object: use the allocation size
>> + for the whole object. */
>> + expect(__builtin_dynamic_object_size(p->array, 0),
>> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
>> +
>> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
>> + expect(__builtin_dynamic_object_size(p->array, 1),
>> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
>> + (p->foo) * sizeof(char)));
>> +
>> + /* for MINIMUM size in the whole object: use the allocation size
>> + for the whole object. */
>> + expect(__builtin_dynamic_object_size(p->array, 2),
>> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
>> +
>> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
>> + expect(__builtin_dynamic_object_size(p->array, 3),
>> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
>> + (p->foo) * sizeof(char)));
>> +
>> + /*when checking the pointer p, we only have info on the observed allocation.
>> + So, the object size info can only been obtained from the call to malloc.
>> + for both MAXIMUM and MINIMUM: A = (index + SIZE_BUMP) * sizeof (char) */
>> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
>> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
>> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
>> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
>> + return p;
>> +}
>> +
>> +/* in the following function, malloc allocated less space than the value
>> + of counted_by attribute. Then what's the correct behavior we expect
>> + the __builtin_dynamic_object_size should have for each of the cases?
>> + NOTE: this is an user error, GCC should issue warnings for such case.
>> + this is a seperate issue we should address later. */
>> +
>> +static struct annotated * noinline alloc_buf_less (size_t index)
>> +{
>> + struct annotated *p;
>> + size_t allocated_size
>> + = MAX (sizeof (struct annotated),
>> + (__builtin_offsetof (struct annotated, array[0])
>> + + (index) * sizeof (char)));
>> + p = (struct annotated *) malloc (allocated_size);
>> +
>> + p->foo = index + SIZE_BUMP;
>> +
>> + /*when checking the observed access p->array, we have info on both
>> + observered allocation and observed access,
>> + A. from observed allocation:
>> + allocated_size - offsetof (struct annotated, array[0])
>> + B. from observed access: p->foo * sizeof (char)
>> + */
>> +
>> + /* for size in the whole object: always uses A. */
>> + /* for size in the sub-object: chose the smaller of A and B.
>> + * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
>> + * for details on why. */
>> +
>> + /* for MAXIMUM size in the whole object: use the allocation size
>> + for the whole object. */
>> + expect(__builtin_dynamic_object_size(p->array, 0),
>> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
>> +
>> + /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
>> + expect(__builtin_dynamic_object_size(p->array, 1),
>> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
>> + (p->foo) * sizeof(char)));
>> +
>> + /* for MINIMUM size in the whole object: use the allocation size
>> + for the whole object. */
>> + expect(__builtin_dynamic_object_size(p->array, 2),
>> + allocated_size - __builtin_offsetof (struct annotated, array[0]));
>> +
>> + /* for MINIMUM size in the sub-object: use the smaller of A and B. */
>> + expect(__builtin_dynamic_object_size(p->array, 3),
>> + MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
>> + (p->foo) * sizeof(char)));
>> +
>> + /*when checking the pointer p, we only have info on the observed
>> + allocation. So, the object size info can only been obtained from
>> + the call to malloc. */
>> + expect(__builtin_dynamic_object_size(p, 0), allocated_size);
>> + expect(__builtin_dynamic_object_size(p, 1), allocated_size);
>> + expect(__builtin_dynamic_object_size(p, 2), allocated_size);
>> + expect(__builtin_dynamic_object_size(p, 3), allocated_size);
>> + return p;
>> +}
>> +
>> +int main ()
>> +{
>> + struct annotated *p, *q;
>> + p = alloc_buf_more (10);
>> + q = alloc_buf_less (10);
>> +
>> + /*when checking the observed access p->array, we only have info on the
>> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
>> + info on the whole object. */
>> + expect(__builtin_dynamic_object_size(p->array, 0), -1);
>> + expect(__builtin_dynamic_object_size(p->array, 1), p->foo * sizeof(char));
>> + expect(__builtin_dynamic_object_size(p->array, 2), 0);
>> + expect(__builtin_dynamic_object_size(p->array, 3), p->foo * sizeof(char));
>> + /*when checking the pointer p, we have no observed allocation nor observed
>> + access, therefore, we cannot determine the size info here. */
>> + expect(__builtin_dynamic_object_size(p, 0), -1);
>> + expect(__builtin_dynamic_object_size(p, 1), -1);
>> + expect(__builtin_dynamic_object_size(p, 2), 0);
>> + expect(__builtin_dynamic_object_size(p, 3), 0);
>> +
>> + /*when checking the observed access p->array, we only have info on the
>> + observed access, i.e, the TYPE_SIZE info from the access. We don't have
>> + info on the whole object. */
>> + expect(__builtin_dynamic_object_size(q->array, 0), -1);
>> + expect(__builtin_dynamic_object_size(q->array, 1), q->foo * sizeof(char));
>> + expect(__builtin_dynamic_object_size(q->array, 2), 0);
>> + expect(__builtin_dynamic_object_size(q->array, 3), q->foo * sizeof(char));
>> + /*when checking the pointer p, we have no observed allocation nor observed
>> + access, therefore, we cannot determine the size info here. */
>> + expect(__builtin_dynamic_object_size(q, 0), -1);
>> + expect(__builtin_dynamic_object_size(q, 1), -1);
>> + expect(__builtin_dynamic_object_size(q, 2), 0);
>> + expect(__builtin_dynamic_object_size(q, 3), 0);
>> +
>> + DONE ();
>> +}
>> diff --git a/gcc/tree-object-size.cc b/gcc/tree-object-size.cc
>> index a62af0500563..cf7843c5684b 100644
>> --- a/gcc/tree-object-size.cc
>> +++ b/gcc/tree-object-size.cc
>> @@ -585,6 +585,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>> if (pt_var != TREE_OPERAND (ptr, 0))
>> {
>> tree var;
>> + tree counted_by_ref = NULL_TREE;
>> if (object_size_type & OST_SUBOBJECT)
>> {
>> @@ -600,11 +601,12 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>> var = TREE_OPERAND (var, 0);
>> if (var != pt_var && TREE_CODE (var) == ARRAY_REF)
>> var = TREE_OPERAND (var, 0);
>> - if (! TYPE_SIZE_UNIT (TREE_TYPE (var))
>> + if (! component_ref_has_counted_by_p (var)
>> + && ((! TYPE_SIZE_UNIT (TREE_TYPE (var))
>> || ! tree_fits_uhwi_p (TYPE_SIZE_UNIT (TREE_TYPE (var)))
>> || (pt_var_size && TREE_CODE (pt_var_size) == INTEGER_CST
>> && tree_int_cst_lt (pt_var_size,
>> - TYPE_SIZE_UNIT (TREE_TYPE (var)))))
>> + TYPE_SIZE_UNIT (TREE_TYPE (var)))))))
>> var = pt_var;
>> else if (var != pt_var && TREE_CODE (pt_var) == MEM_REF)
>> {
>
> Hmm, only for subobject size? I thought we had consensus on using sizeof (struct) + counted_by_size as the conservative maximum size for whole object size too, didn't we?
Yes, in this initial patch set, only minimum change to tree-object-size.cc. therefore only handle subobject size. (And subobject size is more important for linux kernel security purpose)
And I will add a follow up patch to add new code into tree-object-size.cc to support whole object size by using sizeof(struct) + counted_by_size.
Is this Okay?
>
>> @@ -612,6 +614,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>> /* For &X->fld, compute object size if fld isn't a flexible array
>> member. */
>> bool is_flexible_array_mem_ref = false;
>> +
>> while (v && v != pt_var)
>> switch (TREE_CODE (v))
>> {
>
> Unnecessary newline.
Okay.
>
>> @@ -660,6 +663,8 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>> /* Now the ref is to an array type. */
>> gcc_assert (TREE_CODE (TREE_TYPE (v)) == ARRAY_TYPE);
>> is_flexible_array_mem_ref = array_ref_flexible_size_p (v);
>> + counted_by_ref = component_ref_get_counted_by (v);
>> +
>> while (v != pt_var && TREE_CODE (v) == COMPONENT_REF)
>> if (TREE_CODE (TREE_TYPE (TREE_OPERAND (v, 0)))
>> != UNION_TYPE
>> @@ -673,8 +678,11 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>> == RECORD_TYPE)
>> {
>> /* compute object size only if v is not a
>> - flexible array member. */
>> - if (!is_flexible_array_mem_ref)
>> + flexible array member or the flexible array member
>> + has a known element count indicated by the user
>> + through attribute counted_by. */
>> + if (!is_flexible_array_mem_ref
>> + || counted_by_ref)
>> {
>> v = NULL_TREE;
>> break;
>> @@ -707,9 +715,24 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
>> if (var != pt_var)
>> {
>> - var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
>> - if (!TREE_CONSTANT (var_size))
>> - var_size = get_or_create_ssa_default_def (cfun, var_size);
>> + if (!counted_by_ref)
>> + {
>> + var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
>> + if (!TREE_CONSTANT (var_size))
>> + var_size = get_or_create_ssa_default_def (cfun, var_size);
>> + }
>> + else
>> + {
>> + gcc_assert (TREE_CODE (var) == COMPONENT_REF
>> + && TREE_CODE (TREE_TYPE (var)) == ARRAY_TYPE);
>> + tree element_size = TYPE_SIZE_UNIT (TREE_TYPE (TREE_TYPE (var)));
>> + var_size
>> + = size_binop (MULT_EXPR,
>> + fold_convert (sizetype, counted_by_ref),
>> + fold_convert (sizetype, element_size));
>> + if (!todo)
>> + todo = TODO_update_ssa_only_virtuals;
>> + }
>
> I feel like this could make a good separate function (get_subobject_size or something like that) to make it easier to read.
Will try this in the next version.
>
>> if (!var_size)
>> return false;
>> }
>> diff --git a/gcc/tree.cc b/gcc/tree.cc
>> index fcd36ae0cd74..3b6ddcbdcbf8 100644
>> --- a/gcc/tree.cc
>> +++ b/gcc/tree.cc
>> @@ -12745,6 +12745,32 @@ array_ref_element_size (tree exp)
>> return SUBSTITUTE_PLACEHOLDER_IN_EXPR (TYPE_SIZE_UNIT (elmt_type), exp);
>> }
>> +/* For a component_ref that has an array type ARRAY_REF, return TRUE when
>> + an counted_by attribute attached to the corresponding FIELD_DECL.
>> + return FALSE otherwise. */
>> +bool
>> +component_ref_has_counted_by_p (tree array_ref)
>> +{
>> + if (TREE_CODE (array_ref) != COMPONENT_REF)
>> + return false;
>> +
>> + if (TREE_CODE (TREE_TYPE (array_ref)) != ARRAY_TYPE)
>> + return false;
>> +
>> + tree struct_object = TREE_OPERAND (array_ref, 0);
>> + tree struct_type = TREE_TYPE (struct_object);
>> +
>> + if (!RECORD_OR_UNION_TYPE_P (struct_type))
>> + return false;
>> + tree field_decl = TREE_OPERAND (array_ref, 1);
>> + tree attr_counted_by = lookup_attribute ("counted_by",
>> + DECL_ATTRIBUTES (field_decl));
>> +
>> + if (!attr_counted_by)
>> + return false;
>> + return true;
>> +}
>> +
>> /* Given a field list, FIELDLIST, of a structure/union, return a TREE_LIST,
>> with each TREE_VALUE a FIELD_DECL stepping down the chain to the FIELD
>> whose name is FIELDNAME, which is the last TREE_VALUE of the list.
>> @@ -12771,7 +12797,7 @@ get_named_field (tree fieldlist, const char *fieldname)
>> fields inside it recursively. */
>> else if (RECORD_OR_UNION_TYPE_P (TREE_TYPE (field)))
>> if ((named_field = get_named_field (TYPE_FIELDS (TREE_TYPE (field)),
>> - fieldname)) != NULL_TREE)
>> + fieldname)) != NULL_TREE)
>
> Unrelated whitespace change?
Will check on this and fix it in the next version.
>
>> {
>> named_field = tree_cons (NULL_TREE, field, named_field);
>> break;
>> @@ -12784,6 +12810,73 @@ get_named_field (tree fieldlist, const char *fieldname)
>> return named_field;
>> }
>> +/* For a component_ref that has an array type ARRAY_REF, get the object that
>> + represents its counted_by per the attribute counted_by attached to
>> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
>> + object.
>> + For example, if:
>> +
>> + struct P {
>> + int k;
>> + int x[] __attribute__ ((counted_by (k)));
>> + } *p;
>> +
>> + for the following reference:
>> +
>> + p->x[b]
>> +
>> + the object that represents its element count will be:
>> +
>> + p->k
>> +
>> + So, when component_ref_get_counted_by (p->x[b]) is called, p->k should be
>> + returned.
>> +*/
>> +
>> +tree
>> +component_ref_get_counted_by (tree array_ref)
>> +{
>> + if (! component_ref_has_counted_by_p (array_ref))
>> + return NULL_TREE;
>> +
>> + tree struct_object = TREE_OPERAND (array_ref, 0);
>> + tree struct_type = TREE_TYPE (struct_object);
>> + tree field_decl = TREE_OPERAND (array_ref, 1);
>> + tree attr_counted_by = lookup_attribute ("counted_by",
>> + DECL_ATTRIBUTES (field_decl));
>> + gcc_assert (attr_counted_by);
>> +
>> + /* If there is an counted_by attribute attached to the field,
>> + get the field that maps to the counted_by. */
>> +
>> + const char *fieldname
>> + = IDENTIFIER_POINTER (TREE_VALUE (TREE_VALUE (attr_counted_by)));
>> +
>> + tree counted_by_field = get_named_field (TYPE_FIELDS (struct_type),
>> + fieldname);
>> +
>> + gcc_assert (counted_by_field);
>> +
>> + /* generate the tree node that represent the counted_by of this array
>
> Capitalize first word. Also s/represent/represents/
Okay.
>
>> + ref. This is a (possible nested) COMPONENT_REF to the counted_by_field
>
> possibly nested
Okay.
>
>> + of the containing structure. */
>> +
>> + tree counted_by_ref = NULL_TREE;
>> + tree object = struct_object;
>> + do
>> + {
>> + tree field = TREE_VALUE (counted_by_field);
>> +
>> + counted_by_ref = build3 (COMPONENT_REF,
>> + TREE_TYPE (field),
>> + unshare_expr (object), field,
>> + NULL_TREE);
>> + object = counted_by_ref;
>> + counted_by_field = TREE_CHAIN (counted_by_field);
>> + }
>> + while (counted_by_field);
>> + return counted_by_ref;
>> +}
>> /* Return a tree representing the lower bound of the array mentioned in
>> EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
>> diff --git a/gcc/tree.h b/gcc/tree.h
>> index 4859becaa1e7..07eed7219835 100644
>> --- a/gcc/tree.h
>> +++ b/gcc/tree.h
>> @@ -5619,11 +5619,21 @@ extern tree get_base_address (tree t);
>> of EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
>> extern tree array_ref_element_size (tree);
>> +/* Give a component_ref that has an array type, return true when an
>> + attribute counted_by attached to the corresponding FIELD_DECL. */
>> +extern bool component_ref_has_counted_by_p (tree);
>> +
>> /* Given a field list, FIELDLIST, of a structure/union, return the FIELD whose
>> name is FIELDNAME, return NULL_TREE if such field is not found.
>> searching nested anonymous structure/union recursively. */
>> extern tree get_named_field (tree, const char *);
>> +/* Give a component_ref that has an array type, return the object that
>> + represents its counted_by per the attribute counted_by attached to
>> + the corresponding FIELD_DECL. return NULL_TREE when cannot find such
>> + object. */
>> +extern tree component_ref_get_counted_by (tree);
>> +
>> /* Return a typenode for the "standard" C type with a given name. */
>> extern tree get_typenode_from_name (const char *);
new file mode 100644
@@ -0,0 +1,74 @@
+/* test the attribute counted_by and its usage in
+ * __builtin_dynamic_object_size. */
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+
+#include "builtin-object-size-common.h"
+
+#define expect(p, _v) do { \
+ size_t v = _v; \
+ if (p == v) \
+ __builtin_printf ("ok: %s == %zd\n", #p, p); \
+ else \
+ { \
+ __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
+ FAIL (); \
+ } \
+} while (0);
+
+struct flex {
+ int b;
+ int c[];
+} *array_flex;
+
+struct annotated {
+ int b;
+ int c[] __attribute__ ((counted_by (b)));
+} *array_annotated;
+
+struct nested_annotated {
+ struct {
+ union {
+ int b;
+ float f;
+ };
+ int n;
+ };
+ int c[] __attribute__ ((counted_by (b)));
+} *array_nested_annotated;
+
+void __attribute__((__noinline__)) setup (int normal_count, int attr_count)
+{
+ array_flex
+ = (struct flex *)malloc (sizeof (struct flex)
+ + normal_count * sizeof (int));
+ array_flex->b = normal_count;
+
+ array_annotated
+ = (struct annotated *)malloc (sizeof (struct annotated)
+ + attr_count * sizeof (int));
+ array_annotated->b = attr_count;
+
+ array_nested_annotated
+ = (struct nested_annotated *)malloc (sizeof (struct nested_annotated)
+ + attr_count * sizeof (int));
+ array_nested_annotated->b = attr_count;
+
+ return;
+}
+
+void __attribute__((__noinline__)) test ()
+{
+ expect(__builtin_dynamic_object_size(array_flex->c, 1), -1);
+ expect(__builtin_dynamic_object_size(array_annotated->c, 1),
+ array_annotated->b * sizeof (int));
+ expect(__builtin_dynamic_object_size(array_nested_annotated->c, 1),
+ array_nested_annotated->b * sizeof (int));
+}
+
+int main(int argc, char *argv[])
+{
+ setup (10,10);
+ test ();
+ DONE ();
+}
new file mode 100644
@@ -0,0 +1,210 @@
+/* test the attribute counted_by and its usage in
+__builtin_dynamic_object_size: what's the correct behavior when the
+allocation size mismatched with the value of counted_by attribute? */
+/* { dg-do run } */
+/* { dg-options "-O -fstrict-flex-arrays=3" } */
+
+#include "builtin-object-size-common.h"
+
+struct annotated {
+ size_t foo;
+ char others;
+ char array[] __attribute__((counted_by (foo)));
+};
+
+#define expect(p, _v) do { \
+ size_t v = _v; \
+ if (p == v) \
+ __builtin_printf ("ok: %s == %zd\n", #p, p); \
+ else \
+ { \
+ __builtin_printf ("WAT: %s == %zd (expected %zd)\n", #p, p, v); \
+ FAIL (); \
+ } \
+} while (0);
+
+#define noinline __attribute__((__noinline__))
+#define SIZE_BUMP 10
+#define MAX(a, b) ((a) > (b) ? (a) : (b))
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+
+/* In general, Due to type casting, the type for the pointee of a pointer
+ does not say anything about the object it points to,
+ So, __builtin_object_size can not directly use the type of the pointee
+ to decide the size of the object the pointer points to.
+
+ there are only two reliable ways:
+ A. observed allocations (call to the allocation functions in the routine)
+ B. observed accesses (read or write access to the location of the
+ pointer points to)
+
+ that provide information about the type/existence of an object at
+ the corresponding address.
+
+ for A, we use the "alloc_size" attribute for the corresponding allocation
+ functions to determine the object size;
+
+ For B, we use the SIZE info of the TYPE attached to the corresponding access.
+ (We treat counted_by attribute as a complement to the SIZE info of the TYPE
+ for FMA)
+
+ The only other way in C which ensures that a pointer actually points
+ to an object of the correct type is 'static':
+
+ void foo(struct P *p[static 1]);
+
+ See https://gcc.gnu.org/pipermail/gcc-patches/2023-July/624814.html
+ for more details. */
+
+/* in the following function, malloc allocated more space than the value
+ of counted_by attribute. Then what's the correct behavior we expect
+ the __builtin_dynamic_object_size should have for each of the cases? */
+
+static struct annotated * noinline alloc_buf_more (size_t index)
+{
+ struct annotated *p;
+ size_t allocated_size
+ = MAX (sizeof (struct annotated),
+ (__builtin_offsetof (struct annotated, array[0])
+ + (index + SIZE_BUMP) * sizeof (char)));
+ p = (struct annotated *) malloc (allocated_size);
+
+ p->foo = index;
+
+ /*when checking the observed access p->array, we have info on both
+ observered allocation and observed access,
+ A. from observed allocation:
+ allocated_size - offsetof (struct annotated, array[0])
+ B. from observed access: p->foo * sizeof (char)
+ */
+
+ /* for size in the whole object: always uses A. */
+ /* for size in the sub-object: chose the smaller of A and B.
+ * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
+ * for details on why. */
+
+ /* for MAXIMUM size in the whole object: use the allocation size
+ for the whole object. */
+ expect(__builtin_dynamic_object_size(p->array, 0),
+ allocated_size - __builtin_offsetof (struct annotated, array[0]));
+
+ /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
+ expect(__builtin_dynamic_object_size(p->array, 1),
+ MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
+ (p->foo) * sizeof(char)));
+
+ /* for MINIMUM size in the whole object: use the allocation size
+ for the whole object. */
+ expect(__builtin_dynamic_object_size(p->array, 2),
+ allocated_size - __builtin_offsetof (struct annotated, array[0]));
+
+ /* for MINIMUM size in the sub-object: use the smaller of A and B. */
+ expect(__builtin_dynamic_object_size(p->array, 3),
+ MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
+ (p->foo) * sizeof(char)));
+
+ /*when checking the pointer p, we only have info on the observed allocation.
+ So, the object size info can only been obtained from the call to malloc.
+ for both MAXIMUM and MINIMUM: A = (index + SIZE_BUMP) * sizeof (char) */
+ expect(__builtin_dynamic_object_size(p, 0), allocated_size);
+ expect(__builtin_dynamic_object_size(p, 1), allocated_size);
+ expect(__builtin_dynamic_object_size(p, 2), allocated_size);
+ expect(__builtin_dynamic_object_size(p, 3), allocated_size);
+ return p;
+}
+
+/* in the following function, malloc allocated less space than the value
+ of counted_by attribute. Then what's the correct behavior we expect
+ the __builtin_dynamic_object_size should have for each of the cases?
+ NOTE: this is an user error, GCC should issue warnings for such case.
+ this is a seperate issue we should address later. */
+
+static struct annotated * noinline alloc_buf_less (size_t index)
+{
+ struct annotated *p;
+ size_t allocated_size
+ = MAX (sizeof (struct annotated),
+ (__builtin_offsetof (struct annotated, array[0])
+ + (index) * sizeof (char)));
+ p = (struct annotated *) malloc (allocated_size);
+
+ p->foo = index + SIZE_BUMP;
+
+ /*when checking the observed access p->array, we have info on both
+ observered allocation and observed access,
+ A. from observed allocation:
+ allocated_size - offsetof (struct annotated, array[0])
+ B. from observed access: p->foo * sizeof (char)
+ */
+
+ /* for size in the whole object: always uses A. */
+ /* for size in the sub-object: chose the smaller of A and B.
+ * Please see https://gcc.gnu.org/pipermail/gcc-patches/2023-July/625891.html
+ * for details on why. */
+
+ /* for MAXIMUM size in the whole object: use the allocation size
+ for the whole object. */
+ expect(__builtin_dynamic_object_size(p->array, 0),
+ allocated_size - __builtin_offsetof (struct annotated, array[0]));
+
+ /* for MAXIMUM size in the sub-object. use the smaller of A and B. */
+ expect(__builtin_dynamic_object_size(p->array, 1),
+ MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
+ (p->foo) * sizeof(char)));
+
+ /* for MINIMUM size in the whole object: use the allocation size
+ for the whole object. */
+ expect(__builtin_dynamic_object_size(p->array, 2),
+ allocated_size - __builtin_offsetof (struct annotated, array[0]));
+
+ /* for MINIMUM size in the sub-object: use the smaller of A and B. */
+ expect(__builtin_dynamic_object_size(p->array, 3),
+ MIN (allocated_size - __builtin_offsetof (struct annotated, array[0]),
+ (p->foo) * sizeof(char)));
+
+ /*when checking the pointer p, we only have info on the observed
+ allocation. So, the object size info can only been obtained from
+ the call to malloc. */
+ expect(__builtin_dynamic_object_size(p, 0), allocated_size);
+ expect(__builtin_dynamic_object_size(p, 1), allocated_size);
+ expect(__builtin_dynamic_object_size(p, 2), allocated_size);
+ expect(__builtin_dynamic_object_size(p, 3), allocated_size);
+ return p;
+}
+
+int main ()
+{
+ struct annotated *p, *q;
+ p = alloc_buf_more (10);
+ q = alloc_buf_less (10);
+
+ /*when checking the observed access p->array, we only have info on the
+ observed access, i.e, the TYPE_SIZE info from the access. We don't have
+ info on the whole object. */
+ expect(__builtin_dynamic_object_size(p->array, 0), -1);
+ expect(__builtin_dynamic_object_size(p->array, 1), p->foo * sizeof(char));
+ expect(__builtin_dynamic_object_size(p->array, 2), 0);
+ expect(__builtin_dynamic_object_size(p->array, 3), p->foo * sizeof(char));
+ /*when checking the pointer p, we have no observed allocation nor observed
+ access, therefore, we cannot determine the size info here. */
+ expect(__builtin_dynamic_object_size(p, 0), -1);
+ expect(__builtin_dynamic_object_size(p, 1), -1);
+ expect(__builtin_dynamic_object_size(p, 2), 0);
+ expect(__builtin_dynamic_object_size(p, 3), 0);
+
+ /*when checking the observed access p->array, we only have info on the
+ observed access, i.e, the TYPE_SIZE info from the access. We don't have
+ info on the whole object. */
+ expect(__builtin_dynamic_object_size(q->array, 0), -1);
+ expect(__builtin_dynamic_object_size(q->array, 1), q->foo * sizeof(char));
+ expect(__builtin_dynamic_object_size(q->array, 2), 0);
+ expect(__builtin_dynamic_object_size(q->array, 3), q->foo * sizeof(char));
+ /*when checking the pointer p, we have no observed allocation nor observed
+ access, therefore, we cannot determine the size info here. */
+ expect(__builtin_dynamic_object_size(q, 0), -1);
+ expect(__builtin_dynamic_object_size(q, 1), -1);
+ expect(__builtin_dynamic_object_size(q, 2), 0);
+ expect(__builtin_dynamic_object_size(q, 3), 0);
+
+ DONE ();
+}
@@ -585,6 +585,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
if (pt_var != TREE_OPERAND (ptr, 0))
{
tree var;
+ tree counted_by_ref = NULL_TREE;
if (object_size_type & OST_SUBOBJECT)
{
@@ -600,11 +601,12 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
var = TREE_OPERAND (var, 0);
if (var != pt_var && TREE_CODE (var) == ARRAY_REF)
var = TREE_OPERAND (var, 0);
- if (! TYPE_SIZE_UNIT (TREE_TYPE (var))
+ if (! component_ref_has_counted_by_p (var)
+ && ((! TYPE_SIZE_UNIT (TREE_TYPE (var))
|| ! tree_fits_uhwi_p (TYPE_SIZE_UNIT (TREE_TYPE (var)))
|| (pt_var_size && TREE_CODE (pt_var_size) == INTEGER_CST
&& tree_int_cst_lt (pt_var_size,
- TYPE_SIZE_UNIT (TREE_TYPE (var)))))
+ TYPE_SIZE_UNIT (TREE_TYPE (var)))))))
var = pt_var;
else if (var != pt_var && TREE_CODE (pt_var) == MEM_REF)
{
@@ -612,6 +614,7 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
/* For &X->fld, compute object size if fld isn't a flexible array
member. */
bool is_flexible_array_mem_ref = false;
+
while (v && v != pt_var)
switch (TREE_CODE (v))
{
@@ -660,6 +663,8 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
/* Now the ref is to an array type. */
gcc_assert (TREE_CODE (TREE_TYPE (v)) == ARRAY_TYPE);
is_flexible_array_mem_ref = array_ref_flexible_size_p (v);
+ counted_by_ref = component_ref_get_counted_by (v);
+
while (v != pt_var && TREE_CODE (v) == COMPONENT_REF)
if (TREE_CODE (TREE_TYPE (TREE_OPERAND (v, 0)))
!= UNION_TYPE
@@ -673,8 +678,11 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
== RECORD_TYPE)
{
/* compute object size only if v is not a
- flexible array member. */
- if (!is_flexible_array_mem_ref)
+ flexible array member or the flexible array member
+ has a known element count indicated by the user
+ through attribute counted_by. */
+ if (!is_flexible_array_mem_ref
+ || counted_by_ref)
{
v = NULL_TREE;
break;
@@ -707,9 +715,24 @@ addr_object_size (struct object_size_info *osi, const_tree ptr,
if (var != pt_var)
{
- var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
- if (!TREE_CONSTANT (var_size))
- var_size = get_or_create_ssa_default_def (cfun, var_size);
+ if (!counted_by_ref)
+ {
+ var_size = TYPE_SIZE_UNIT (TREE_TYPE (var));
+ if (!TREE_CONSTANT (var_size))
+ var_size = get_or_create_ssa_default_def (cfun, var_size);
+ }
+ else
+ {
+ gcc_assert (TREE_CODE (var) == COMPONENT_REF
+ && TREE_CODE (TREE_TYPE (var)) == ARRAY_TYPE);
+ tree element_size = TYPE_SIZE_UNIT (TREE_TYPE (TREE_TYPE (var)));
+ var_size
+ = size_binop (MULT_EXPR,
+ fold_convert (sizetype, counted_by_ref),
+ fold_convert (sizetype, element_size));
+ if (!todo)
+ todo = TODO_update_ssa_only_virtuals;
+ }
if (!var_size)
return false;
}
@@ -12745,6 +12745,32 @@ array_ref_element_size (tree exp)
return SUBSTITUTE_PLACEHOLDER_IN_EXPR (TYPE_SIZE_UNIT (elmt_type), exp);
}
+/* For a component_ref that has an array type ARRAY_REF, return TRUE when
+ an counted_by attribute attached to the corresponding FIELD_DECL.
+ return FALSE otherwise. */
+bool
+component_ref_has_counted_by_p (tree array_ref)
+{
+ if (TREE_CODE (array_ref) != COMPONENT_REF)
+ return false;
+
+ if (TREE_CODE (TREE_TYPE (array_ref)) != ARRAY_TYPE)
+ return false;
+
+ tree struct_object = TREE_OPERAND (array_ref, 0);
+ tree struct_type = TREE_TYPE (struct_object);
+
+ if (!RECORD_OR_UNION_TYPE_P (struct_type))
+ return false;
+ tree field_decl = TREE_OPERAND (array_ref, 1);
+ tree attr_counted_by = lookup_attribute ("counted_by",
+ DECL_ATTRIBUTES (field_decl));
+
+ if (!attr_counted_by)
+ return false;
+ return true;
+}
+
/* Given a field list, FIELDLIST, of a structure/union, return a TREE_LIST,
with each TREE_VALUE a FIELD_DECL stepping down the chain to the FIELD
whose name is FIELDNAME, which is the last TREE_VALUE of the list.
@@ -12771,7 +12797,7 @@ get_named_field (tree fieldlist, const char *fieldname)
fields inside it recursively. */
else if (RECORD_OR_UNION_TYPE_P (TREE_TYPE (field)))
if ((named_field = get_named_field (TYPE_FIELDS (TREE_TYPE (field)),
- fieldname)) != NULL_TREE)
+ fieldname)) != NULL_TREE)
{
named_field = tree_cons (NULL_TREE, field, named_field);
break;
@@ -12784,6 +12810,73 @@ get_named_field (tree fieldlist, const char *fieldname)
return named_field;
}
+/* For a component_ref that has an array type ARRAY_REF, get the object that
+ represents its counted_by per the attribute counted_by attached to
+ the corresponding FIELD_DECL. return NULL_TREE when cannot find such
+ object.
+ For example, if:
+
+ struct P {
+ int k;
+ int x[] __attribute__ ((counted_by (k)));
+ } *p;
+
+ for the following reference:
+
+ p->x[b]
+
+ the object that represents its element count will be:
+
+ p->k
+
+ So, when component_ref_get_counted_by (p->x[b]) is called, p->k should be
+ returned.
+*/
+
+tree
+component_ref_get_counted_by (tree array_ref)
+{
+ if (! component_ref_has_counted_by_p (array_ref))
+ return NULL_TREE;
+
+ tree struct_object = TREE_OPERAND (array_ref, 0);
+ tree struct_type = TREE_TYPE (struct_object);
+ tree field_decl = TREE_OPERAND (array_ref, 1);
+ tree attr_counted_by = lookup_attribute ("counted_by",
+ DECL_ATTRIBUTES (field_decl));
+ gcc_assert (attr_counted_by);
+
+ /* If there is an counted_by attribute attached to the field,
+ get the field that maps to the counted_by. */
+
+ const char *fieldname
+ = IDENTIFIER_POINTER (TREE_VALUE (TREE_VALUE (attr_counted_by)));
+
+ tree counted_by_field = get_named_field (TYPE_FIELDS (struct_type),
+ fieldname);
+
+ gcc_assert (counted_by_field);
+
+ /* generate the tree node that represent the counted_by of this array
+ ref. This is a (possible nested) COMPONENT_REF to the counted_by_field
+ of the containing structure. */
+
+ tree counted_by_ref = NULL_TREE;
+ tree object = struct_object;
+ do
+ {
+ tree field = TREE_VALUE (counted_by_field);
+
+ counted_by_ref = build3 (COMPONENT_REF,
+ TREE_TYPE (field),
+ unshare_expr (object), field,
+ NULL_TREE);
+ object = counted_by_ref;
+ counted_by_field = TREE_CHAIN (counted_by_field);
+ }
+ while (counted_by_field);
+ return counted_by_ref;
+}
/* Return a tree representing the lower bound of the array mentioned in
EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
@@ -5619,11 +5619,21 @@ extern tree get_base_address (tree t);
of EXP, an ARRAY_REF or an ARRAY_RANGE_REF. */
extern tree array_ref_element_size (tree);
+/* Give a component_ref that has an array type, return true when an
+ attribute counted_by attached to the corresponding FIELD_DECL. */
+extern bool component_ref_has_counted_by_p (tree);
+
/* Given a field list, FIELDLIST, of a structure/union, return the FIELD whose
name is FIELDNAME, return NULL_TREE if such field is not found.
searching nested anonymous structure/union recursively. */
extern tree get_named_field (tree, const char *);
+/* Give a component_ref that has an array type, return the object that
+ represents its counted_by per the attribute counted_by attached to
+ the corresponding FIELD_DECL. return NULL_TREE when cannot find such
+ object. */
+extern tree component_ref_get_counted_by (tree);
+
/* Return a typenode for the "standard" C type with a given name. */
extern tree get_typenode_from_name (const char *);