text
stringlengths 478
227k
|
|---|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static bool fix_and_check_vcol_expr(THD *thd, TABLE *table,
Virtual_column_info *vcol)
{
Item* func_expr= vcol->expr;
DBUG_ENTER("fix_and_check_vcol_expr");
DBUG_PRINT("info", ("vcol: %p", vcol));
DBUG_ASSERT(func_expr);
if (func_expr->fixed)
DBUG_RETURN(0); // nothing to do
if (fix_vcol_expr(thd, vcol))
DBUG_RETURN(1);
if (vcol->flags)
DBUG_RETURN(0); // already checked, no need to do it again
/* fix_fields could've changed the expression */
func_expr= vcol->expr;
/* this was checked in check_expression(), but the frm could be mangled... */
if (unlikely(func_expr->result_type() == ROW_RESULT))
{
my_error(ER_OPERAND_COLUMNS, MYF(0), 1);
DBUG_RETURN(1);
}
/*
Walk through the Item tree checking if all items are valid
to be part of the virtual column
*/
Item::vcol_func_processor_result res;
res.errors= 0;
int error= func_expr->walk(&Item::check_vcol_func_processor, 0, &res);
if (unlikely(error || (res.errors & VCOL_IMPOSSIBLE)))
{
// this can only happen if the frm was corrupted
my_error(ER_VIRTUAL_COLUMN_FUNCTION_IS_NOT_ALLOWED, MYF(0), res.name,
vcol->get_vcol_type_name(), vcol->name.str);
DBUG_RETURN(1);
}
else if (unlikely(res.errors & VCOL_AUTO_INC))
{
/*
An auto_increment field may not be used in an expression for
a check constraint, a default value or a generated column
Note that this error condition is not detected during parsing
of the statement because the field item does not have a field
pointer at that time
*/
myf warn= table->s->frm_version < FRM_VER_EXPRESSSIONS ? ME_JUST_WARNING : 0;
my_error(ER_VIRTUAL_COLUMN_FUNCTION_IS_NOT_ALLOWED, MYF(warn),
"AUTO_INCREMENT", vcol->get_vcol_type_name(), res.name);
if (!warn)
DBUG_RETURN(1);
}
vcol->flags= res.errors;
if (vcol->flags & VCOL_SESSION_FUNC)
table->s->vcols_need_refixing= true;
DBUG_RETURN(0);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-416'], 'message': 'MDEV-24176 Preparations
1. moved fix_vcol_exprs() call to open_table()
mysql_alter_table() doesn't do lock_tables() so it cannot win from
fix_vcol_exprs() from there. Tests affected: main.default_session
2. Vanilla cleanups and comments.'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: uint prep_alter_part_table(THD *thd, TABLE *table, Alter_info *alter_info,
HA_CREATE_INFO *create_info,
Alter_table_ctx *alter_ctx,
bool *partition_changed,
bool *fast_alter_table)
{
DBUG_ENTER("prep_alter_part_table");
/* Foreign keys on partitioned tables are not supported, waits for WL#148 */
if (table->part_info && (alter_info->flags & (ALTER_ADD_FOREIGN_KEY |
ALTER_DROP_FOREIGN_KEY)))
{
my_error(ER_FOREIGN_KEY_ON_PARTITIONED, MYF(0));
DBUG_RETURN(TRUE);
}
/* Remove partitioning on a not partitioned table is not possible */
if (!table->part_info && (alter_info->partition_flags &
ALTER_PARTITION_REMOVE))
{
my_error(ER_PARTITION_MGMT_ON_NONPARTITIONED, MYF(0));
DBUG_RETURN(TRUE);
}
partition_info *alt_part_info= thd->lex->part_info;
/*
This variable is TRUE in very special case when we add only DEFAULT
partition to the existing table
*/
bool only_default_value_added=
(alt_part_info &&
alt_part_info->current_partition &&
alt_part_info->current_partition->list_val_list.elements == 1 &&
alt_part_info->current_partition->list_val_list.head()->
added_items >= 1 &&
alt_part_info->current_partition->list_val_list.head()->
col_val_array[0].max_value) &&
alt_part_info->part_type == LIST_PARTITION &&
(alter_info->partition_flags & ALTER_PARTITION_ADD);
if (only_default_value_added &&
!thd->lex->part_info->num_columns)
thd->lex->part_info->num_columns= 1; // to make correct clone
/*
One of these is done in handle_if_exists_option():
thd->work_part_info= thd->lex->part_info;
or
thd->work_part_info= NULL;
*/
if (thd->work_part_info &&
!(thd->work_part_info= thd->work_part_info->get_clone(thd)))
DBUG_RETURN(TRUE);
/* ALTER_PARTITION_ADMIN is handled in mysql_admin_table */
DBUG_ASSERT(!(alter_info->partition_flags & ALTER_PARTITION_ADMIN));
partition_info *saved_part_info= NULL;
if (alter_info->partition_flags &
(ALTER_PARTITION_ADD |
ALTER_PARTITION_DROP |
ALTER_PARTITION_COALESCE |
ALTER_PARTITION_REORGANIZE |
ALTER_PARTITION_TABLE_REORG |
ALTER_PARTITION_REBUILD))
{
/*
You can't add column when we are doing alter related to partition
*/
DBUG_EXECUTE_IF("test_pseudo_invisible", {
my_error(ER_INTERNAL_ERROR, MYF(0), "Don't to it with test_pseudo_invisible");
DBUG_RETURN(1);
});
DBUG_EXECUTE_IF("test_completely_invisible", {
my_error(ER_INTERNAL_ERROR, MYF(0), "Don't to it with test_completely_invisible");
DBUG_RETURN(1);
});
partition_info *tab_part_info;
ulonglong flags= 0;
bool is_last_partition_reorged= FALSE;
part_elem_value *tab_max_elem_val= NULL;
part_elem_value *alt_max_elem_val= NULL;
longlong tab_max_range= 0, alt_max_range= 0;
alt_part_info= thd->work_part_info;
if (!table->part_info)
{
my_error(ER_PARTITION_MGMT_ON_NONPARTITIONED, MYF(0));
DBUG_RETURN(TRUE);
}
/*
Open our intermediate table, we will operate on a temporary instance
of the original table, to be able to skip copying all partitions.
Open it as a copy of the original table, and modify its partition_info
object to allow fast_alter_partition_table to perform the changes.
*/
DBUG_ASSERT(thd->mdl_context.is_lock_owner(MDL_key::TABLE,
alter_ctx->db.str,
alter_ctx->table_name.str,
MDL_INTENTION_EXCLUSIVE));
tab_part_info= table->part_info;
if (alter_info->partition_flags & ALTER_PARTITION_TABLE_REORG)
{
uint new_part_no, curr_part_no;
/*
'ALTER TABLE t REORG PARTITION' only allowed with auto partition
if default partitioning is used.
*/
if (tab_part_info->part_type != HASH_PARTITION ||
((table->s->db_type()->partition_flags() & HA_USE_AUTO_PARTITION) &&
!tab_part_info->use_default_num_partitions) ||
((!(table->s->db_type()->partition_flags() & HA_USE_AUTO_PARTITION)) &&
tab_part_info->use_default_num_partitions))
{
my_error(ER_REORG_NO_PARAM_ERROR, MYF(0));
goto err;
}
new_part_no= table->file->get_default_no_partitions(create_info);
curr_part_no= tab_part_info->num_parts;
if (new_part_no == curr_part_no)
{
/*
No change is needed, we will have the same number of partitions
after the change as before. Thus we can reply ok immediately
without any changes at all.
*/
flags= table->file->alter_table_flags(alter_info->flags);
if (flags & (HA_FAST_CHANGE_PARTITION | HA_PARTITION_ONE_PHASE))
{
*fast_alter_table= true;
/* Force table re-open for consistency with the main case. */
table->mark_table_for_reopen();
}
else
{
/*
Create copy of partition_info to avoid modifying original
TABLE::part_info, to keep it safe for later use.
*/
if (!(tab_part_info= tab_part_info->get_clone(thd)))
DBUG_RETURN(TRUE);
}
thd->work_part_info= tab_part_info;
DBUG_RETURN(FALSE);
}
else if (new_part_no > curr_part_no)
{
/*
We will add more partitions, we use the ADD PARTITION without
setting the flag for no default number of partitions
*/
alter_info->partition_flags|= ALTER_PARTITION_ADD;
thd->work_part_info->num_parts= new_part_no - curr_part_no;
}
else
{
/*
We will remove hash partitions, we use the COALESCE PARTITION
without setting the flag for no default number of partitions
*/
alter_info->partition_flags|= ALTER_PARTITION_COALESCE;
alter_info->num_parts= curr_part_no - new_part_no;
}
}
if (!(flags= table->file->alter_table_flags(alter_info->flags)))
{
my_error(ER_PARTITION_FUNCTION_FAILURE, MYF(0));
goto err;
}
if ((flags & (HA_FAST_CHANGE_PARTITION | HA_PARTITION_ONE_PHASE)) != 0)
{
/*
"Fast" change of partitioning is supported in this case.
We will change TABLE::part_info (as this is how we pass
information to storage engine in this case), so the table
must be reopened.
*/
*fast_alter_table= true;
table->mark_table_for_reopen();
}
else
{
/*
"Fast" changing of partitioning is not supported. Create
a copy of TABLE::part_info object, so we can modify it safely.
Modifying original TABLE::part_info will cause problems when
we read data from old version of table using this TABLE object
while copying them to new version of table.
*/
if (!(tab_part_info= tab_part_info->get_clone(thd)))
DBUG_RETURN(TRUE);
}
DBUG_PRINT("info", ("*fast_alter_table flags: 0x%llx", flags));
if ((alter_info->partition_flags & ALTER_PARTITION_ADD) ||
(alter_info->partition_flags & ALTER_PARTITION_REORGANIZE))
{
if (thd->work_part_info->part_type != tab_part_info->part_type)
{
if (thd->work_part_info->part_type == NOT_A_PARTITION)
{
if (tab_part_info->part_type == RANGE_PARTITION)
{
my_error(ER_PARTITIONS_MUST_BE_DEFINED_ERROR, MYF(0), "RANGE");
goto err;
}
else if (tab_part_info->part_type == LIST_PARTITION)
{
my_error(ER_PARTITIONS_MUST_BE_DEFINED_ERROR, MYF(0), "LIST");
goto err;
}
/*
Hash partitions can be altered without parser finds out about
that it is HASH partitioned. So no error here.
*/
}
else
{
if (thd->work_part_info->part_type == RANGE_PARTITION)
{
my_error(ER_PARTITION_WRONG_VALUES_ERROR, MYF(0),
"RANGE", "LESS THAN");
}
else if (thd->work_part_info->part_type == LIST_PARTITION)
{
DBUG_ASSERT(thd->work_part_info->part_type == LIST_PARTITION);
my_error(ER_PARTITION_WRONG_VALUES_ERROR, MYF(0),
"LIST", "IN");
}
else if (thd->work_part_info->part_type == VERSIONING_PARTITION ||
tab_part_info->part_type == VERSIONING_PARTITION)
{
my_error(ER_PARTITION_WRONG_TYPE, MYF(0), "SYSTEM_TIME");
}
else
{
DBUG_ASSERT(tab_part_info->part_type == RANGE_PARTITION ||
tab_part_info->part_type == LIST_PARTITION);
(void) tab_part_info->error_if_requires_values();
}
goto err;
}
}
if ((tab_part_info->column_list &&
alt_part_info->num_columns != tab_part_info->num_columns &&
!only_default_value_added) ||
(!tab_part_info->column_list &&
(tab_part_info->part_type == RANGE_PARTITION ||
tab_part_info->part_type == LIST_PARTITION) &&
alt_part_info->num_columns != 1U &&
!only_default_value_added) ||
(!tab_part_info->column_list &&
tab_part_info->part_type == HASH_PARTITION &&
(alt_part_info->num_columns != 0)))
{
my_error(ER_PARTITION_COLUMN_LIST_ERROR, MYF(0));
goto err;
}
alt_part_info->column_list= tab_part_info->column_list;
if (alt_part_info->fix_parser_data(thd))
{
goto err;
}
}
if (alter_info->partition_flags & ALTER_PARTITION_ADD)
{
if (*fast_alter_table && thd->locked_tables_mode)
{
MEM_ROOT *old_root= thd->mem_root;
thd->mem_root= &thd->locked_tables_list.m_locked_tables_root;
saved_part_info= tab_part_info->get_clone(thd);
thd->mem_root= old_root;
saved_part_info->read_partitions= tab_part_info->read_partitions;
saved_part_info->lock_partitions= tab_part_info->lock_partitions;
saved_part_info->bitmaps_are_initialized= tab_part_info->bitmaps_are_initialized;
}
/*
We start by moving the new partitions to the list of temporary
partitions. We will then check that the new partitions fit in the
partitioning scheme as currently set-up.
Partitions are always added at the end in ADD PARTITION.
*/
uint num_new_partitions= alt_part_info->num_parts;
uint num_orig_partitions= tab_part_info->num_parts;
uint check_total_partitions= num_new_partitions + num_orig_partitions;
uint new_total_partitions= check_total_partitions;
/*
We allow quite a lot of values to be supplied by defaults, however we
must know the number of new partitions in this case.
*/
if (thd->lex->no_write_to_binlog &&
tab_part_info->part_type != HASH_PARTITION &&
tab_part_info->part_type != VERSIONING_PARTITION)
{
my_error(ER_NO_BINLOG_ERROR, MYF(0));
goto err;
}
if (tab_part_info->defined_max_value &&
(tab_part_info->part_type == RANGE_PARTITION ||
alt_part_info->defined_max_value))
{
my_error((tab_part_info->part_type == RANGE_PARTITION ?
ER_PARTITION_MAXVALUE_ERROR :
ER_PARTITION_DEFAULT_ERROR), MYF(0));
goto err;
}
if (num_new_partitions == 0)
{
my_error(ER_ADD_PARTITION_NO_NEW_PARTITION, MYF(0));
goto err;
}
if (tab_part_info->is_sub_partitioned())
{
if (alt_part_info->num_subparts == 0)
alt_part_info->num_subparts= tab_part_info->num_subparts;
else if (alt_part_info->num_subparts != tab_part_info->num_subparts)
{
my_error(ER_ADD_PARTITION_SUBPART_ERROR, MYF(0));
goto err;
}
check_total_partitions= new_total_partitions*
alt_part_info->num_subparts;
}
if (check_total_partitions > MAX_PARTITIONS)
{
my_error(ER_TOO_MANY_PARTITIONS_ERROR, MYF(0));
goto err;
}
alt_part_info->part_type= tab_part_info->part_type;
alt_part_info->subpart_type= tab_part_info->subpart_type;
if (alt_part_info->set_up_defaults_for_partitioning(thd, table->file, 0,
tab_part_info->num_parts))
{
goto err;
}
/*
Handling of on-line cases:
ADD PARTITION for RANGE/LIST PARTITIONING:
------------------------------------------
For range and list partitions add partition is simply adding a
new empty partition to the table. If the handler support this we
will use the simple method of doing this. The figure below shows
an example of this and the states involved in making this change.
Existing partitions New added partitions
------ ------ ------ ------ | ------ ------
| | | | | | | | | | | | |
| p0 | | p1 | | p2 | | p3 | | | p4 | | p5 |
------ ------ ------ ------ | ------ ------
PART_NORMAL PART_NORMAL PART_NORMAL PART_NORMAL PART_TO_BE_ADDED*2
PART_NORMAL PART_NORMAL PART_NORMAL PART_NORMAL PART_IS_ADDED*2
The first line is the states before adding the new partitions and the
second line is after the new partitions are added. All the partitions are
in the partitions list, no partitions are placed in the temp_partitions
list.
ADD PARTITION for HASH PARTITIONING
-----------------------------------
This little figure tries to show the various partitions involved when
adding two new partitions to a linear hash based partitioned table with
four partitions to start with, which lists are used and the states they
pass through. Adding partitions to a normal hash based is similar except
that it is always all the existing partitions that are reorganised not
only a subset of them.
Existing partitions New added partitions
------ ------ ------ ------ | ------ ------
| | | | | | | | | | | | |
| p0 | | p1 | | p2 | | p3 | | | p4 | | p5 |
------ ------ ------ ------ | ------ ------
PART_CHANGED PART_CHANGED PART_NORMAL PART_NORMAL PART_TO_BE_ADDED
PART_IS_CHANGED*2 PART_NORMAL PART_NORMAL PART_IS_ADDED
PART_NORMAL PART_NORMAL PART_NORMAL PART_NORMAL PART_IS_ADDED
Reorganised existing partitions
------ ------
| | | |
| p0'| | p1'|
------ ------
p0 - p5 will be in the partitions list of partitions.
p0' and p1' will actually not exist as separate objects, there presence can
be deduced from the state of the partition and also the names of those
partitions can be deduced this way.
After adding the partitions and copying the partition data to p0', p1',
p4 and p5 from p0 and p1 the states change to adapt for the new situation
where p0 and p1 is dropped and replaced by p0' and p1' and the new p4 and
p5 are in the table again.
The first line above shows the states of the partitions before we start
adding and copying partitions, the second after completing the adding
and copying and finally the third line after also dropping the partitions
that are reorganised.
*/
if (*fast_alter_table && tab_part_info->part_type == HASH_PARTITION)
{
uint part_no= 0, start_part= 1, start_sec_part= 1;
uint end_part= 0, end_sec_part= 0;
uint upper_2n= tab_part_info->linear_hash_mask + 1;
uint lower_2n= upper_2n >> 1;
bool all_parts= TRUE;
if (tab_part_info->linear_hash_ind && num_new_partitions < upper_2n)
{
/*
An analysis of which parts needs reorganisation shows that it is
divided into two intervals. The first interval is those parts
that are reorganised up until upper_2n - 1. From upper_2n and
onwards it starts again from partition 0 and goes on until
it reaches p(upper_2n - 1). If the last new partition reaches
beyond upper_2n - 1 then the first interval will end with
p(lower_2n - 1) and start with p(num_orig_partitions - lower_2n).
If lower_2n partitions are added then p0 to p(lower_2n - 1) will
be reorganised which means that the two interval becomes one
interval at this point. Thus only when adding less than
lower_2n partitions and going beyond a total of upper_2n we
actually get two intervals.
To exemplify this assume we have 6 partitions to start with and
add 1, 2, 3, 5, 6, 7, 8, 9 partitions.
The first to add after p5 is p6 = 110 in bit numbers. Thus we
can see that 10 = p2 will be partition to reorganise if only one
partition.
If 2 partitions are added we reorganise [p2, p3]. Those two
cases are covered by the second if part below.
If 3 partitions are added we reorganise [p2, p3] U [p0,p0]. This
part is covered by the else part below.
If 5 partitions are added we get [p2,p3] U [p0, p2] = [p0, p3].
This is covered by the first if part where we need the max check
to here use lower_2n - 1.
If 7 partitions are added we get [p2,p3] U [p0, p4] = [p0, p4].
This is covered by the first if part but here we use the first
calculated end_part.
Finally with 9 new partitions we would also reorganise p6 if we
used the method below but we cannot reorganise more partitions
than what we had from the start and thus we simply set all_parts
to TRUE. In this case we don't get into this if-part at all.
*/
all_parts= FALSE;
if (num_new_partitions >= lower_2n)
{
/*
In this case there is only one interval since the two intervals
overlap and this starts from zero to last_part_no - upper_2n
*/
start_part= 0;
end_part= new_total_partitions - (upper_2n + 1);
end_part= max(lower_2n - 1, end_part);
}
else if (new_total_partitions <= upper_2n)
{
/*
Also in this case there is only one interval since we are not
going over a 2**n boundary
*/
start_part= num_orig_partitions - lower_2n;
end_part= start_part + (num_new_partitions - 1);
}
else
{
/* We have two non-overlapping intervals since we are not
passing a 2**n border and we have not at least lower_2n
new parts that would ensure that the intervals become
overlapping.
*/
start_part= num_orig_partitions - lower_2n;
end_part= upper_2n - 1;
start_sec_part= 0;
end_sec_part= new_total_partitions - (upper_2n + 1);
}
}
List_iterator<partition_element> tab_it(tab_part_info->partitions);
part_no= 0;
do
{
partition_element *p_elem= tab_it++;
if (all_parts ||
(part_no >= start_part && part_no <= end_part) ||
(part_no >= start_sec_part && part_no <= end_sec_part))
{
p_elem->part_state= PART_CHANGED;
}
} while (++part_no < num_orig_partitions);
}
/*
Need to concatenate the lists here to make it possible to check the
partition info for correctness using check_partition_info.
For on-line add partition we set the state of this partition to
PART_TO_BE_ADDED to ensure that it is known that it is not yet
usable (becomes usable when partition is created and the switch of
partition configuration is made.
*/
{
partition_element *now_part= NULL;
if (tab_part_info->part_type == VERSIONING_PARTITION)
{
List_iterator<partition_element> it(tab_part_info->partitions);
partition_element *el;
while ((el= it++))
{
if (el->type == partition_element::CURRENT)
{
it.remove();
now_part= el;
}
}
if (*fast_alter_table && tab_part_info->vers_info->interval.is_set())
{
partition_element *hist_part= tab_part_info->vers_info->hist_part;
if (hist_part->range_value <= thd->query_start())
hist_part->part_state= PART_CHANGED;
}
}
List_iterator<partition_element> alt_it(alt_part_info->partitions);
uint part_count= 0;
do
{
partition_element *part_elem= alt_it++;
if (*fast_alter_table)
part_elem->part_state= PART_TO_BE_ADDED;
if (unlikely(tab_part_info->partitions.push_back(part_elem,
thd->mem_root)))
goto err;
} while (++part_count < num_new_partitions);
tab_part_info->num_parts+= num_new_partitions;
if (tab_part_info->part_type == VERSIONING_PARTITION)
{
DBUG_ASSERT(now_part);
if (unlikely(tab_part_info->partitions.push_back(now_part,
thd->mem_root)))
goto err;
}
}
/*
If we specify partitions explicitly we don't use defaults anymore.
Using ADD PARTITION also means that we don't have the default number
of partitions anymore. We use this code also for Table reorganisations
and here we don't set any default flags to FALSE.
*/
if (!(alter_info->partition_flags & ALTER_PARTITION_TABLE_REORG))
{
if (!alt_part_info->use_default_partitions)
{
DBUG_PRINT("info", ("part_info: %p", tab_part_info));
tab_part_info->use_default_partitions= FALSE;
}
tab_part_info->use_default_num_partitions= FALSE;
tab_part_info->is_auto_partitioned= FALSE;
}
}
else if (alter_info->partition_flags & ALTER_PARTITION_DROP)
{
/*
Drop a partition from a range partition and list partitioning is
always safe and can be made more or less immediate. It is necessary
however to ensure that the partition to be removed is safely removed
and that REPAIR TABLE can remove the partition if for some reason the
command to drop the partition failed in the middle.
*/
uint part_count= 0;
uint num_parts_dropped= alter_info->partition_names.elements;
uint num_parts_found= 0;
List_iterator<partition_element> part_it(tab_part_info->partitions);
tab_part_info->is_auto_partitioned= FALSE;
if (tab_part_info->part_type == VERSIONING_PARTITION)
{
if (num_parts_dropped >= tab_part_info->num_parts - 1)
{
DBUG_ASSERT(table && table->s && table->s->table_name.str);
my_error(ER_VERS_WRONG_PARTS, MYF(0), table->s->table_name.str);
goto err;
}
}
else
{
if (!(tab_part_info->part_type == RANGE_PARTITION ||
tab_part_info->part_type == LIST_PARTITION))
{
my_error(ER_ONLY_ON_RANGE_LIST_PARTITION, MYF(0), "DROP");
goto err;
}
if (num_parts_dropped >= tab_part_info->num_parts)
{
my_error(ER_DROP_LAST_PARTITION, MYF(0));
goto err;
}
}
do
{
partition_element *part_elem= part_it++;
if (is_name_in_list(part_elem->partition_name,
alter_info->partition_names))
{
if (tab_part_info->part_type == VERSIONING_PARTITION)
{
if (part_elem->type == partition_element::CURRENT)
{
my_error(ER_VERS_WRONG_PARTS, MYF(0), table->s->table_name.str);
goto err;
}
if (tab_part_info->vers_info->interval.is_set())
{
if (num_parts_found < part_count)
{
my_error(ER_VERS_DROP_PARTITION_INTERVAL, MYF(0));
goto err;
}
tab_part_info->vers_info->interval.start=
(my_time_t)part_elem->range_value;
}
}
/*
Set state to indicate that the partition is to be dropped.
*/
num_parts_found++;
part_elem->part_state= PART_TO_BE_DROPPED;
}
} while (++part_count < tab_part_info->num_parts);
if (num_parts_found != num_parts_dropped)
{
my_error(ER_DROP_PARTITION_NON_EXISTENT, MYF(0), "DROP");
goto err;
}
if (table->file->is_fk_defined_on_table_or_index(MAX_KEY))
{
my_error(ER_ROW_IS_REFERENCED, MYF(0));
goto err;
}
tab_part_info->num_parts-= num_parts_dropped;
}
else if (alter_info->partition_flags & ALTER_PARTITION_REBUILD)
{
set_engine_all_partitions(tab_part_info,
tab_part_info->default_engine_type);
if (set_part_state(alter_info, tab_part_info, PART_CHANGED))
{
my_error(ER_DROP_PARTITION_NON_EXISTENT, MYF(0), "REBUILD");
goto err;
}
if (!(*fast_alter_table))
{
table->file->print_error(HA_ERR_WRONG_COMMAND, MYF(0));
goto err;
}
}
else if (alter_info->partition_flags & ALTER_PARTITION_COALESCE)
{
uint num_parts_coalesced= alter_info->num_parts;
uint num_parts_remain= tab_part_info->num_parts - num_parts_coalesced;
List_iterator<partition_element> part_it(tab_part_info->partitions);
if (tab_part_info->part_type != HASH_PARTITION)
{
my_error(ER_COALESCE_ONLY_ON_HASH_PARTITION, MYF(0));
goto err;
}
if (num_parts_coalesced == 0)
{
my_error(ER_COALESCE_PARTITION_NO_PARTITION, MYF(0));
goto err;
}
if (num_parts_coalesced >= tab_part_info->num_parts)
{
my_error(ER_DROP_LAST_PARTITION, MYF(0));
goto err;
}
/*
Online handling:
COALESCE PARTITION:
-------------------
The figure below shows the manner in which partitions are handled when
performing an on-line coalesce partition and which states they go through
at start, after adding and copying partitions and finally after dropping
the partitions to drop. The figure shows an example using four partitions
to start with, using linear hash and coalescing one partition (always the
last partition).
Using linear hash then all remaining partitions will have a new reorganised
part.
Existing partitions Coalesced partition
------ ------ ------ | ------
| | | | | | | | |
| p0 | | p1 | | p2 | | | p3 |
------ ------ ------ | ------
PART_NORMAL PART_CHANGED PART_NORMAL PART_REORGED_DROPPED
PART_NORMAL PART_IS_CHANGED PART_NORMAL PART_TO_BE_DROPPED
PART_NORMAL PART_NORMAL PART_NORMAL PART_IS_DROPPED
Reorganised existing partitions
------
| |
| p1'|
------
p0 - p3 is in the partitions list.
The p1' partition will actually not be in any list it is deduced from the
state of p1.
*/
{
uint part_count= 0, start_part= 1, start_sec_part= 1;
uint end_part= 0, end_sec_part= 0;
bool all_parts= TRUE;
if (*fast_alter_table &&
tab_part_info->linear_hash_ind)
{
uint upper_2n= tab_part_info->linear_hash_mask + 1;
uint lower_2n= upper_2n >> 1;
all_parts= FALSE;
if (num_parts_coalesced >= lower_2n)
{
all_parts= TRUE;
}
else if (num_parts_remain >= lower_2n)
{
end_part= tab_part_info->num_parts - (lower_2n + 1);
start_part= num_parts_remain - lower_2n;
}
else
{
start_part= 0;
end_part= tab_part_info->num_parts - (lower_2n + 1);
end_sec_part= (lower_2n >> 1) - 1;
start_sec_part= end_sec_part - (lower_2n - (num_parts_remain + 1));
}
}
do
{
partition_element *p_elem= part_it++;
if (*fast_alter_table &&
(all_parts ||
(part_count >= start_part && part_count <= end_part) ||
(part_count >= start_sec_part && part_count <= end_sec_part)))
p_elem->part_state= PART_CHANGED;
if (++part_count > num_parts_remain)
{
if (*fast_alter_table)
p_elem->part_state= PART_REORGED_DROPPED;
else
part_it.remove();
}
} while (part_count < tab_part_info->num_parts);
tab_part_info->num_parts= num_parts_remain;
}
if (!(alter_info->partition_flags & ALTER_PARTITION_TABLE_REORG))
{
tab_part_info->use_default_num_partitions= FALSE;
tab_part_info->is_auto_partitioned= FALSE;
}
}
else if (alter_info->partition_flags & ALTER_PARTITION_REORGANIZE)
{
/*
Reorganise partitions takes a number of partitions that are next
to each other (at least for RANGE PARTITIONS) and then uses those
to create a set of new partitions. So data is copied from those
partitions into the new set of partitions. Those new partitions
can have more values in the LIST value specifications or less both
are allowed. The ranges can be different but since they are
changing a set of consecutive partitions they must cover the same
range as those changed from.
This command can be used on RANGE and LIST partitions.
*/
uint num_parts_reorged= alter_info->partition_names.elements;
uint num_parts_new= thd->work_part_info->partitions.elements;
uint check_total_partitions;
tab_part_info->is_auto_partitioned= FALSE;
if (num_parts_reorged > tab_part_info->num_parts)
{
my_error(ER_REORG_PARTITION_NOT_EXIST, MYF(0));
goto err;
}
if (!(tab_part_info->part_type == RANGE_PARTITION ||
tab_part_info->part_type == LIST_PARTITION) &&
(num_parts_new != num_parts_reorged))
{
my_error(ER_REORG_HASH_ONLY_ON_SAME_NO, MYF(0));
goto err;
}
if (tab_part_info->is_sub_partitioned() &&
alt_part_info->num_subparts &&
alt_part_info->num_subparts != tab_part_info->num_subparts)
{
my_error(ER_PARTITION_WRONG_NO_SUBPART_ERROR, MYF(0));
goto err;
}
check_total_partitions= tab_part_info->num_parts + num_parts_new;
check_total_partitions-= num_parts_reorged;
if (check_total_partitions > MAX_PARTITIONS)
{
my_error(ER_TOO_MANY_PARTITIONS_ERROR, MYF(0));
goto err;
}
alt_part_info->part_type= tab_part_info->part_type;
alt_part_info->subpart_type= tab_part_info->subpart_type;
alt_part_info->num_subparts= tab_part_info->num_subparts;
DBUG_ASSERT(!alt_part_info->use_default_partitions);
/* We specified partitions explicitly so don't use defaults anymore. */
tab_part_info->use_default_partitions= FALSE;
if (alt_part_info->set_up_defaults_for_partitioning(thd, table->file, 0,
0))
{
goto err;
}
check_datadir_altered_for_innodb(thd, tab_part_info, alt_part_info);
/*
Online handling:
REORGANIZE PARTITION:
---------------------
The figure exemplifies the handling of partitions, their state changes and
how they are organised. It exemplifies four partitions where two of the
partitions are reorganised (p1 and p2) into two new partitions (p4 and p5).
The reason of this change could be to change range limits, change list
values or for hash partitions simply reorganise the partition which could
also involve moving them to new disks or new node groups (MySQL Cluster).
Existing partitions
------ ------ ------ ------
| | | | | | | |
| p0 | | p1 | | p2 | | p3 |
------ ------ ------ ------
PART_NORMAL PART_TO_BE_REORGED PART_NORMAL
PART_NORMAL PART_TO_BE_DROPPED PART_NORMAL
PART_NORMAL PART_IS_DROPPED PART_NORMAL
Reorganised new partitions (replacing p1 and p2)
------ ------
| | | |
| p4 | | p5 |
------ ------
PART_TO_BE_ADDED
PART_IS_ADDED
PART_IS_ADDED
All unchanged partitions and the new partitions are in the partitions list
in the order they will have when the change is completed. The reorganised
partitions are placed in the temp_partitions list. PART_IS_ADDED is only a
temporary state not written in the frm file. It is used to ensure we write
the generated partition syntax in a correct manner.
*/
{
List_iterator<partition_element> tab_it(tab_part_info->partitions);
uint part_count= 0;
bool found_first= FALSE;
bool found_last= FALSE;
uint drop_count= 0;
do
{
partition_element *part_elem= tab_it++;
is_last_partition_reorged= FALSE;
if (is_name_in_list(part_elem->partition_name,
alter_info->partition_names))
{
is_last_partition_reorged= TRUE;
drop_count++;
if (tab_part_info->column_list)
{
List_iterator<part_elem_value> p(part_elem->list_val_list);
tab_max_elem_val= p++;
}
else
tab_max_range= part_elem->range_value;
if (*fast_alter_table &&
unlikely(tab_part_info->temp_partitions.
push_back(part_elem, thd->mem_root)))
goto err;
if (*fast_alter_table)
part_elem->part_state= PART_TO_BE_REORGED;
if (!found_first)
{
uint alt_part_count= 0;
partition_element *alt_part_elem;
List_iterator<partition_element>
alt_it(alt_part_info->partitions);
found_first= TRUE;
do
{
alt_part_elem= alt_it++;
if (tab_part_info->column_list)
{
List_iterator<part_elem_value> p(alt_part_elem->list_val_list);
alt_max_elem_val= p++;
}
else
alt_max_range= alt_part_elem->range_value;
if (*fast_alter_table)
alt_part_elem->part_state= PART_TO_BE_ADDED;
if (alt_part_count == 0)
tab_it.replace(alt_part_elem);
else
tab_it.after(alt_part_elem);
} while (++alt_part_count < num_parts_new);
}
else if (found_last)
{
my_error(ER_CONSECUTIVE_REORG_PARTITIONS, MYF(0));
goto err;
}
else
tab_it.remove();
}
else
{
if (found_first)
found_last= TRUE;
}
} while (++part_count < tab_part_info->num_parts);
if (drop_count != num_parts_reorged)
{
my_error(ER_DROP_PARTITION_NON_EXISTENT, MYF(0), "REORGANIZE");
goto err;
}
tab_part_info->num_parts= check_total_partitions;
}
}
else
{
DBUG_ASSERT(FALSE);
}
*partition_changed= TRUE;
thd->work_part_info= tab_part_info;
if (alter_info->partition_flags & (ALTER_PARTITION_ADD |
ALTER_PARTITION_REORGANIZE))
{
if (tab_part_info->use_default_subpartitions &&
!alt_part_info->use_default_subpartitions)
{
tab_part_info->use_default_subpartitions= FALSE;
tab_part_info->use_default_num_subpartitions= FALSE;
}
if (tab_part_info->check_partition_info(thd, (handlerton**)NULL,
table->file, 0, alt_part_info))
{
goto err;
}
/*
The check below needs to be performed after check_partition_info
since this function "fixes" the item trees of the new partitions
to reorganize into
*/
if (alter_info->partition_flags == ALTER_PARTITION_REORGANIZE &&
tab_part_info->part_type == RANGE_PARTITION &&
((is_last_partition_reorged &&
(tab_part_info->column_list ?
(partition_info_compare_column_values(
alt_max_elem_val->col_val_array,
tab_max_elem_val->col_val_array) < 0) :
alt_max_range < tab_max_range)) ||
(!is_last_partition_reorged &&
(tab_part_info->column_list ?
(partition_info_compare_column_values(
alt_max_elem_val->col_val_array,
tab_max_elem_val->col_val_array) != 0) :
alt_max_range != tab_max_range))))
{
/*
For range partitioning the total resulting range before and
after the change must be the same except in one case. This is
when the last partition is reorganised, in this case it is
acceptable to increase the total range.
The reason is that it is not allowed to have "holes" in the
middle of the ranges and thus we should not allow to reorganise
to create "holes".
*/
my_error(ER_REORG_OUTSIDE_RANGE, MYF(0));
goto err;
}
}
} // ADD, DROP, COALESCE, REORGANIZE, TABLE_REORG, REBUILD
else
{
/*
When thd->lex->part_info has a reference to a partition_info the
ALTER TABLE contained a definition of a partitioning.
Case I:
If there was a partition before and there is a new one defined.
We use the new partitioning. The new partitioning is already
defined in the correct variable so no work is needed to
accomplish this.
We do however need to update partition_changed to ensure that not
only the frm file is changed in the ALTER TABLE command.
Case IIa:
There was a partitioning before and there is no new one defined.
Also the user has not specified to remove partitioning explicitly.
We use the old partitioning also for the new table. We do this
by assigning the partition_info from the table loaded in
open_table to the partition_info struct used by mysql_create_table
later in this method.
Case IIb:
There was a partitioning before and there is no new one defined.
The user has specified explicitly to remove partitioning
Since the user has specified explicitly to remove partitioning
we override the old partitioning info and create a new table using
the specified engine.
In this case the partition also is changed.
Case III:
There was no partitioning before altering the table, there is
partitioning defined in the altered table. Use the new partitioning.
No work needed since the partitioning info is already in the
correct variable.
In this case we discover one case where the new partitioning is using
the same partition function as the default (PARTITION BY KEY or
PARTITION BY LINEAR KEY with the list of fields equal to the primary
key fields OR PARTITION BY [LINEAR] KEY() for tables without primary
key)
Also here partition has changed and thus a new table must be
created.
Case IV:
There was no partitioning before and no partitioning defined.
Obviously no work needed.
*/
partition_info *tab_part_info= table->part_info;
if (tab_part_info)
{
if (alter_info->partition_flags & ALTER_PARTITION_REMOVE)
{
DBUG_PRINT("info", ("Remove partitioning"));
if (!(create_info->used_fields & HA_CREATE_USED_ENGINE))
{
DBUG_PRINT("info", ("No explicit engine used"));
create_info->db_type= tab_part_info->default_engine_type;
}
DBUG_PRINT("info", ("New engine type: %s",
ha_resolve_storage_engine_name(create_info->db_type)));
thd->work_part_info= NULL;
*partition_changed= TRUE;
}
else if (!thd->work_part_info)
{
/*
Retain partitioning but possibly with a new storage engine
beneath.
Create a copy of TABLE::part_info to be able to modify it freely.
*/
if (!(tab_part_info= tab_part_info->get_clone(thd)))
DBUG_RETURN(TRUE);
thd->work_part_info= tab_part_info;
if (create_info->used_fields & HA_CREATE_USED_ENGINE &&
create_info->db_type != tab_part_info->default_engine_type)
{
/*
Make sure change of engine happens to all partitions.
*/
DBUG_PRINT("info", ("partition changed"));
if (tab_part_info->is_auto_partitioned)
{
/*
If the user originally didn't specify partitioning to be
used we can remove it now.
*/
thd->work_part_info= NULL;
}
else
{
/*
Ensure that all partitions have the proper engine set-up
*/
set_engine_all_partitions(thd->work_part_info,
create_info->db_type);
}
*partition_changed= TRUE;
}
}
/*
Prohibit inplace when partitioned by primary key and the primary key is changed.
*/
if (!*partition_changed &&
tab_part_info->part_field_array &&
!tab_part_info->part_field_list.elements &&
table->s->primary_key != MAX_KEY)
{
if (alter_info->flags & (ALTER_DROP_SYSTEM_VERSIONING |
ALTER_ADD_SYSTEM_VERSIONING))
{
*partition_changed= true;
}
else
{
KEY *primary_key= table->key_info + table->s->primary_key;
List_iterator_fast<Alter_drop> drop_it(alter_info->drop_list);
const char *primary_name= primary_key->name.str;
const Alter_drop *drop;
drop_it.rewind();
while ((drop= drop_it++))
{
if (drop->type == Alter_drop::KEY &&
0 == my_strcasecmp(system_charset_info, primary_name, drop->name))
break;
}
if (drop)
*partition_changed= TRUE;
}
}
}
if (thd->work_part_info)
{
partition_info *part_info= thd->work_part_info;
bool is_native_partitioned= FALSE;
/*
Need to cater for engine types that can handle partition without
using the partition handler.
*/
if (part_info != tab_part_info)
{
if (part_info->fix_parser_data(thd))
{
goto err;
}
/*
Compare the old and new part_info. If only key_algorithm
change is done, don't consider it as changed partitioning (to avoid
rebuild). This is to handle KEY (numeric_cols) partitioned tables
created in 5.1. For more info, see bug#14521864.
*/
if (alter_info->partition_flags != ALTER_PARTITION_INFO ||
!table->part_info ||
alter_info->algorithm(thd) !=
Alter_info::ALTER_TABLE_ALGORITHM_INPLACE ||
!table->part_info->has_same_partitioning(part_info))
{
DBUG_PRINT("info", ("partition changed"));
*partition_changed= true;
}
}
/*
Set up partition default_engine_type either from the create_info
or from the previus table
*/
if (create_info->used_fields & HA_CREATE_USED_ENGINE)
part_info->default_engine_type= create_info->db_type;
else
{
if (tab_part_info)
part_info->default_engine_type= tab_part_info->default_engine_type;
else
part_info->default_engine_type= create_info->db_type;
}
DBUG_ASSERT(part_info->default_engine_type &&
part_info->default_engine_type != partition_hton);
if (check_native_partitioned(create_info, &is_native_partitioned,
part_info, thd))
{
goto err;
}
if (!is_native_partitioned)
{
DBUG_ASSERT(create_info->db_type);
create_info->db_type= partition_hton;
}
}
}
DBUG_RETURN(FALSE);
err:
*fast_alter_table= false;
if (saved_part_info)
table->part_info= saved_part_info;
DBUG_RETURN(TRUE);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-416'], 'message': 'MDEV-24176 Preparations
1. moved fix_vcol_exprs() call to open_table()
mysql_alter_table() doesn't do lock_tables() so it cannot win from
fix_vcol_exprs() from there. Tests affected: main.default_session
2. Vanilla cleanups and comments.'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void close_thread_tables(THD *thd)
{
TABLE *table;
DBUG_ENTER("close_thread_tables");
THD_STAGE_INFO(thd, stage_closing_tables);
#ifdef EXTRA_DEBUG
DBUG_PRINT("tcache", ("open tables:"));
for (table= thd->open_tables; table; table= table->next)
DBUG_PRINT("tcache", ("table: '%s'.'%s' %p", table->s->db.str,
table->s->table_name.str, table));
#endif
#if defined(ENABLED_DEBUG_SYNC)
/* debug_sync may not be initialized for some slave threads */
if (thd->debug_sync_control)
DEBUG_SYNC(thd, "before_close_thread_tables");
#endif
DBUG_ASSERT(thd->transaction.stmt.is_empty() || thd->in_sub_stmt ||
(thd->state_flags & Open_tables_state::BACKUPS_AVAIL));
/* Detach MERGE children after every statement. Even under LOCK TABLES. */
for (table= thd->open_tables; table; table= table->next)
{
/* Table might be in use by some outer statement. */
DBUG_PRINT("tcache", ("table: '%s' query_id: %lu",
table->s->table_name.str, (ulong) table->query_id));
if (thd->locked_tables_mode <= LTM_LOCK_TABLES ||
table->query_id == thd->query_id)
{
DBUG_ASSERT(table->file);
table->file->extra(HA_EXTRA_DETACH_CHILDREN);
}
}
/*
We are assuming here that thd->derived_tables contains ONLY derived
tables for this substatement. i.e. instead of approach which uses
query_id matching for determining which of the derived tables belong
to this substatement we rely on the ability of substatements to
save/restore thd->derived_tables during their execution.
TODO: Probably even better approach is to simply associate list of
derived tables with (sub-)statement instead of thread and destroy
them at the end of its execution.
*/
if (thd->derived_tables)
{
TABLE *next;
/*
Close all derived tables generated in queries like
SELECT * FROM (SELECT * FROM t1)
*/
for (table= thd->derived_tables ; table ; table= next)
{
next= table->next;
free_tmp_table(thd, table);
}
thd->derived_tables= 0;
}
if (thd->rec_tables)
{
TABLE *next;
/*
Close all temporary tables created for recursive table references.
This action was postponed because the table could be used in the
statements like ANALYZE WITH r AS (...) SELECT * from r
where r is defined through recursion.
*/
for (table= thd->rec_tables ; table ; table= next)
{
next= table->next;
free_tmp_table(thd, table);
}
thd->rec_tables= 0;
}
/*
Mark all temporary tables used by this statement as free for reuse.
*/
thd->mark_tmp_tables_as_free_for_reuse();
if (thd->locked_tables_mode)
{
/* Ensure we are calling ha_reset() for all used tables */
mark_used_tables_as_free_for_reuse(thd, thd->open_tables);
/*
We are under simple LOCK TABLES or we're inside a sub-statement
of a prelocked statement, so should not do anything else.
Note that even if we are in LTM_LOCK_TABLES mode and statement
requires prelocking (e.g. when we are closing tables after
failing ot "open" all tables required for statement execution)
we will exit this function a few lines below.
*/
if (! thd->lex->requires_prelocking())
DBUG_VOID_RETURN;
/*
We are in the top-level statement of a prelocked statement,
so we have to leave the prelocked mode now with doing implicit
UNLOCK TABLES if needed.
*/
if (thd->locked_tables_mode == LTM_PRELOCKED_UNDER_LOCK_TABLES)
thd->locked_tables_mode= LTM_LOCK_TABLES;
if (thd->locked_tables_mode == LTM_LOCK_TABLES)
DBUG_VOID_RETURN;
thd->leave_locked_tables_mode();
/* Fallthrough */
}
if (thd->lock)
{
/*
For RBR we flush the pending event just before we unlock all the
tables. This means that we are at the end of a topmost
statement, so we ensure that the STMT_END_F flag is set on the
pending event. For statements that are *inside* stored
functions, the pending event will not be flushed: that will be
handled either before writing a query log event (inside
binlog_query()) or when preparing a pending event.
*/
(void)thd->binlog_flush_pending_rows_event(TRUE);
mysql_unlock_tables(thd, thd->lock);
thd->lock=0;
}
/*
Closing a MERGE child before the parent would be fatal if the
other thread tries to abort the MERGE lock in between.
*/
while (thd->open_tables)
(void) close_thread_table(thd, &thd->open_tables);
DBUG_VOID_RETURN;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-416', 'CWE-703'], 'message': 'MDEV-24176 Server crashes after insert in the table with virtual
column generated using date_format() and if()
vcol_info->expr is allocated on expr_arena at parsing stage. Since
expr item is allocated on expr_arena all its containee items must be
allocated on expr_arena too. Otherwise fix_session_expr() will
encounter prematurely freed item.
When table is reopened from cache vcol_info contains stale
expression. We refresh expression via TABLE::vcol_fix_exprs() but
first we must prepare a proper context (Vcol_expr_context) which meets
some requirements:
1. As noted above expr update must be done on expr_arena as there may
be new items created. It was a bug in fix_session_expr_for_read() and
was just not reproduced because of no second refix. Now refix is done
for more cases so it does reproduce. Tests affected: vcol.binlog
2. Also name resolution context must be narrowed to the single table.
Tested by: vcol.update main.default vcol.vcol_syntax gcol.gcol_bugfixes
3. sql_mode must be clean and not fail expr update.
sql_mode such as MODE_NO_BACKSLASH_ESCAPES, MODE_NO_ZERO_IN_DATE, etc
must not affect vcol expression update. If the table was created
successfully any further evaluation must not fail. Tests affected:
main.func_like
Reviewed by: Sergei Golubchik <serg@mariadb.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: bool parse_vcol_defs(THD *thd, MEM_ROOT *mem_root, TABLE *table,
bool *error_reported, vcol_init_mode mode)
{
CHARSET_INFO *save_character_set_client= thd->variables.character_set_client;
CHARSET_INFO *save_collation= thd->variables.collation_connection;
Query_arena *backup_stmt_arena_ptr= thd->stmt_arena;
const uchar *pos= table->s->vcol_defs.str;
const uchar *end= pos + table->s->vcol_defs.length;
Field **field_ptr= table->field - 1;
Field **vfield_ptr= table->vfield;
Field **dfield_ptr= table->default_field;
Virtual_column_info **check_constraint_ptr= table->check_constraints;
sql_mode_t saved_mode= thd->variables.sql_mode;
Query_arena backup_arena;
Virtual_column_info *vcol= 0;
StringBuffer<MAX_FIELD_WIDTH> expr_str;
bool res= 1;
DBUG_ENTER("parse_vcol_defs");
if (check_constraint_ptr)
memcpy(table->check_constraints + table->s->field_check_constraints,
table->s->check_constraints,
table->s->table_check_constraints * sizeof(Virtual_column_info*));
DBUG_ASSERT(table->expr_arena == NULL);
/*
We need to use CONVENTIONAL_EXECUTION here to ensure that
any new items created by fix_fields() are not reverted.
*/
table->expr_arena= new (alloc_root(mem_root, sizeof(Table_arena)))
Table_arena(mem_root,
Query_arena::STMT_CONVENTIONAL_EXECUTION);
if (!table->expr_arena)
DBUG_RETURN(1);
thd->set_n_backup_active_arena(table->expr_arena, &backup_arena);
thd->stmt_arena= table->expr_arena;
thd->update_charset(&my_charset_utf8mb4_general_ci, table->s->table_charset);
expr_str.append(&parse_vcol_keyword);
thd->variables.sql_mode &= ~MODE_NO_BACKSLASH_ESCAPES;
while (pos < end)
{
uint type, expr_length;
if (table->s->frm_version >= FRM_VER_EXPRESSSIONS)
{
uint field_nr, name_length;
/* see pack_expression() for how data is stored */
type= pos[0];
field_nr= uint2korr(pos+1);
expr_length= uint2korr(pos+3);
name_length= pos[5];
pos+= FRM_VCOL_NEW_HEADER_SIZE + name_length;
field_ptr= table->field + field_nr;
}
else
{
/*
see below in ::init_from_binary_frm_image for how data is stored
in versions below 10.2 (that includes 5.7 too)
*/
while (*++field_ptr && !(*field_ptr)->vcol_info) /* no-op */;
if (!*field_ptr)
{
open_table_error(table->s, OPEN_FRM_CORRUPTED, 1);
goto end;
}
type= (*field_ptr)->vcol_info->stored_in_db
? VCOL_GENERATED_STORED : VCOL_GENERATED_VIRTUAL;
expr_length= uint2korr(pos+1);
if (table->s->mysql_version > 50700 && table->s->mysql_version < 100000)
pos+= 4; // MySQL from 5.7
else
pos+= pos[0] == 2 ? 4 : 3; // MariaDB from 5.2 to 10.1
}
expr_str.length(parse_vcol_keyword.length);
expr_str.append((char*)pos, expr_length);
thd->where= vcol_type_name(static_cast<enum_vcol_info_type>(type));
switch (type) {
case VCOL_GENERATED_VIRTUAL:
case VCOL_GENERATED_STORED:
vcol= unpack_vcol_info_from_frm(thd, mem_root, table, &expr_str,
&((*field_ptr)->vcol_info), error_reported);
*(vfield_ptr++)= *field_ptr;
if (vcol && field_ptr[0]->check_vcol_sql_mode_dependency(thd, mode))
{
DBUG_ASSERT(thd->is_error());
*error_reported= true;
goto end;
}
break;
case VCOL_DEFAULT:
vcol= unpack_vcol_info_from_frm(thd, mem_root, table, &expr_str,
&((*field_ptr)->default_value),
error_reported);
*(dfield_ptr++)= *field_ptr;
if (vcol && (vcol->flags & (VCOL_NON_DETERMINISTIC | VCOL_SESSION_FUNC)))
table->s->non_determinstic_insert= true;
break;
case VCOL_CHECK_FIELD:
vcol= unpack_vcol_info_from_frm(thd, mem_root, table, &expr_str,
&((*field_ptr)->check_constraint),
error_reported);
*check_constraint_ptr++= (*field_ptr)->check_constraint;
break;
case VCOL_CHECK_TABLE:
vcol= unpack_vcol_info_from_frm(thd, mem_root, table, &expr_str,
check_constraint_ptr, error_reported);
check_constraint_ptr++;
break;
}
if (!vcol)
goto end;
pos+= expr_length;
}
/* Now, initialize CURRENT_TIMESTAMP fields */
for (field_ptr= table->field; *field_ptr; field_ptr++)
{
Field *field= *field_ptr;
if (field->has_default_now_unireg_check())
{
expr_str.length(parse_vcol_keyword.length);
expr_str.append(STRING_WITH_LEN("current_timestamp("));
expr_str.append_ulonglong(field->decimals());
expr_str.append(')');
vcol= unpack_vcol_info_from_frm(thd, mem_root, table, &expr_str,
&((*field_ptr)->default_value),
error_reported);
*(dfield_ptr++)= *field_ptr;
if (!field->default_value->expr)
goto end;
}
else if (field->has_update_default_function() && !field->default_value)
*(dfield_ptr++)= *field_ptr;
}
if (vfield_ptr)
*vfield_ptr= 0;
if (dfield_ptr)
*dfield_ptr= 0;
if (check_constraint_ptr)
*check_constraint_ptr= 0;
/* Check that expressions aren't referring to not yet initialized fields */
for (field_ptr= table->field; *field_ptr; field_ptr++)
{
Field *field= *field_ptr;
if (check_vcol_forward_refs(field, field->vcol_info) ||
check_vcol_forward_refs(field, field->check_constraint) ||
check_vcol_forward_refs(field, field->default_value))
{
*error_reported= true;
goto end;
}
}
res=0;
end:
thd->restore_active_arena(table->expr_arena, &backup_arena);
thd->stmt_arena= backup_stmt_arena_ptr;
if (save_character_set_client)
thd->update_charset(save_character_set_client, save_collation);
thd->variables.sql_mode= saved_mode;
DBUG_RETURN(res);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-416'], 'message': 'MDEV-26281 ASAN use-after-poison when complex conversion is involved in blob
the bug was that in_vector array in Item_func_in was allocated in the
statement arena, not in the table->expr_arena.
revert part of the 5acd391e8b2d. Instead, change the arena correctly
in fix_all_session_vcol_exprs().
Remove TABLE_ARENA, that was introduced in 5acd391e8b2d to force
item tree changes to be rolled back (because they were allocated in the
wrong arena and didn't persist. now they do)'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: Field *create_tmp_field_from_field(THD *thd, Field *org_field,
const char *name, TABLE *table,
Item_field *item)
{
Field *new_field;
new_field= org_field->make_new_field(thd->mem_root, table,
table == org_field->table);
if (new_field)
{
new_field->init(table);
new_field->orig_table= org_field->orig_table;
if (item)
item->result_field= new_field;
else
new_field->field_name= name;
new_field->flags|= (org_field->flags & NO_DEFAULT_VALUE_FLAG);
if (org_field->maybe_null() || (item && item->maybe_null))
new_field->flags&= ~NOT_NULL_FLAG; // Because of outer join
if (org_field->type() == MYSQL_TYPE_VAR_STRING ||
org_field->type() == MYSQL_TYPE_VARCHAR)
table->s->db_create_options|= HA_OPTION_PACK_RECORD;
else if (org_field->type() == FIELD_TYPE_DOUBLE)
((Field_double *) new_field)->not_fixed= TRUE;
new_field->vcol_info= new_field->default_value=
new_field->check_constraint= 0;
new_field->cond_selectivity= 1.0;
new_field->next_equal_field= NULL;
new_field->option_list= NULL;
new_field->option_struct= NULL;
}
return new_field;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-89'], 'message': 'MDEV-28403 ASAN heap-use-after-free in String::copy / get_field_default_value
This reverts commit 5ba77222e9fe7af8ff403816b5338b18b342053c
but keeps the test. A different fix for
MDEV-21028 Server crashes in Query_arena::set_query_arena upon SELECT from view
internal temporary tables should use THD as expr_area'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void OPENSSL_LH_flush(OPENSSL_LHASH *lh)
{
unsigned int i;
OPENSSL_LH_NODE *n, *nn;
if (lh == NULL)
return;
for (i = 0; i < lh->num_nodes; i++) {
n = lh->b[i];
while (n != NULL) {
nn = n->next;
OPENSSL_free(n);
n = nn;
}
lh->b[i] = NULL;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-404'], 'message': 'Fix bug in OPENSSL_LH_flush
Fixes #18139.
Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/18141)
(cherry picked from commit e5da68183410c06f7b350a0721bc2bd6057e438e)'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: int llhttp__after_headers_complete(llhttp_t* parser, const char* p,
const char* endp) {
int hasBody;
hasBody = parser->flags & F_CHUNKED || parser->content_length > 0;
if (parser->upgrade && (parser->method == HTTP_CONNECT ||
(parser->flags & F_SKIPBODY) || !hasBody)) {
/* Exit, the rest of the message is in a different protocol. */
return 1;
}
if (parser->flags & F_SKIPBODY) {
return 0;
} else if (parser->flags & F_CHUNKED) {
/* chunked encoding - ignore Content-Length header, prepare for a chunk */
return 2;
} else if (parser->flags & F_TRANSFER_ENCODING) {
if (parser->type == HTTP_REQUEST &&
(parser->lenient_flags & LENIENT_CHUNKED_LENGTH) == 0) {
/* RFC 7230 3.3.3 */
/* If a Transfer-Encoding header field
* is present in a request and the chunked transfer coding is not
* the final encoding, the message body length cannot be determined
* reliably; the server MUST respond with the 400 (Bad Request)
* status code and then close the connection.
*/
return 5;
} else {
/* RFC 7230 3.3.3 */
/* If a Transfer-Encoding header field is present in a response and
* the chunked transfer coding is not the final encoding, the
* message body length is determined by reading the connection until
* it is closed by the server.
*/
return 4;
}
} else {
if (!(parser->flags & F_CONTENT_LENGTH)) {
if (!llhttp_message_needs_eof(parser)) {
/* Assume content-length 0 - read the next */
return 0;
} else {
/* Read body until EOF */
return 4;
}
} else if (parser->content_length == 0) {
/* Content-Length header given but zero: Content-Length: 0\r\n */
return 0;
} else {
/* Content-Length header given and non-zero */
return 3;
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-444'], 'message': 'http: stricter Transfer-Encoding and header separator parsing
Reviewed-By: Matteo Collina <matteo.collina@gmail.com>
Reviewed-By: James M Snell <jasnell@gmail.com>
Reviewed-By: Rich Trott <rtrott@gmail.com>
Reviewed-By: Vladimir de Turckheim <vlad2t@hotmail.com>
PR-URL: https://github.com/nodejs-private/node-private/pull/315
CVE-ID: CVE-2022-32215,CVE-2022-32214,CVE-2022-32212
Backport-PR-URL: https://github.com/nodejs-private/node-private/pull/326'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: zfs_fuid_create_cred(zfsvfs_t *zfsvfs, zfs_fuid_type_t type,
cred_t *cr, zfs_fuid_info_t **fuidp)
{
uid_t id;
VERIFY(type == ZFS_OWNER || type == ZFS_GROUP);
id = (type == ZFS_OWNER) ? crgetuid(cr) : crgetgid(cr);
if (IS_EPHEMERAL(id))
return ((type == ZFS_OWNER) ? UID_NOBODY : GID_NOBODY);
return ((uint64_t)id);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200', 'CWE-732'], 'message': 'FreeBSD: Fix UNIX permissions checking
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10727'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: process(register int code, unsigned char** fill)
{
int incode;
static unsigned char firstchar;
if (code == clear) {
codesize = datasize + 1;
codemask = (1 << codesize) - 1;
avail = clear + 2;
oldcode = -1;
return 1;
}
if (oldcode == -1) {
*(*fill)++ = suffix[code];
firstchar = oldcode = code;
return 1;
}
if (code > avail) {
fprintf(stderr, "code %d too large for %d\n", code, avail);
return 0;
}
incode = code;
if (code == avail) { /* the first code is always < avail */
*stackp++ = firstchar;
code = oldcode;
}
while (code > clear) {
*stackp++ = suffix[code];
code = prefix[code];
}
*stackp++ = firstchar = suffix[code];
prefix[avail] = oldcode;
suffix[avail] = firstchar;
avail++;
if (((avail & codemask) == 0) && (avail < 4096)) {
codesize++;
codemask += avail;
}
oldcode = incode;
do {
*(*fill)++ = *--stackp;
} while (stackp > stack);
return 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'fix possible OOB write in gif2tiff.c'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: unsigned char *ssl_add_serverhello_tlsext(SSL *s, unsigned char *buf,
unsigned char *limit, int *al)
{
int extdatalen = 0;
unsigned char *orig = buf;
unsigned char *ret = buf;
#ifndef OPENSSL_NO_NEXTPROTONEG
int next_proto_neg_seen;
#endif
#ifndef OPENSSL_NO_EC
unsigned long alg_k = s->s3->tmp.new_cipher->algorithm_mkey;
unsigned long alg_a = s->s3->tmp.new_cipher->algorithm_auth;
int using_ecc = (alg_k & SSL_kECDHE) || (alg_a & SSL_aECDSA);
using_ecc = using_ecc && (s->session->tlsext_ecpointformatlist != NULL);
#endif
ret += 2;
if (ret >= limit)
return NULL; /* this really never occurs, but ... */
if (s->s3->send_connection_binding) {
int el;
if (!ssl_add_serverhello_renegotiate_ext(s, 0, &el, 0)) {
SSLerr(SSL_F_SSL_ADD_SERVERHELLO_TLSEXT, ERR_R_INTERNAL_ERROR);
return NULL;
}
/*-
* check for enough space.
* 4 bytes for the reneg type and extension length
* + reneg data length
*/
if (CHECKLEN(ret, 4 + el, limit))
return NULL;
s2n(TLSEXT_TYPE_renegotiate, ret);
s2n(el, ret);
if (!ssl_add_serverhello_renegotiate_ext(s, ret, &el, el)) {
SSLerr(SSL_F_SSL_ADD_SERVERHELLO_TLSEXT, ERR_R_INTERNAL_ERROR);
return NULL;
}
ret += el;
}
/* Only add RI for SSLv3 */
if (s->version == SSL3_VERSION)
goto done;
if (!s->hit && s->servername_done == 1
&& s->session->tlsext_hostname != NULL) {
/*-
* check for enough space.
* 4 bytes for the server name type and extension length
*/
if (CHECKLEN(ret, 4, limit))
return NULL;
s2n(TLSEXT_TYPE_server_name, ret);
s2n(0, ret);
}
#ifndef OPENSSL_NO_EC
if (using_ecc) {
const unsigned char *plist;
size_t plistlen;
/*
* Add TLS extension ECPointFormats to the ServerHello message
*/
tls1_get_formatlist(s, &plist, &plistlen);
if (plistlen > 255) {
SSLerr(SSL_F_SSL_ADD_SERVERHELLO_TLSEXT, ERR_R_INTERNAL_ERROR);
return NULL;
}
/*-
* check for enough space.
* 4 bytes for the ec points format type and extension length
* 1 byte for the points format list length
* + length of points format list
*/
if (CHECKLEN(ret, 5 + plistlen, limit))
return NULL;
s2n(TLSEXT_TYPE_ec_point_formats, ret);
s2n(plistlen + 1, ret);
*(ret++) = (unsigned char)plistlen;
memcpy(ret, plist, plistlen);
ret += plistlen;
}
/*
* Currently the server should not respond with a SupportedCurves
* extension
*/
#endif /* OPENSSL_NO_EC */
if (s->tlsext_ticket_expected && tls_use_ticket(s)) {
/*-
* check for enough space.
* 4 bytes for the Ticket type and extension length
*/
if (CHECKLEN(ret, 4, limit))
return NULL;
s2n(TLSEXT_TYPE_session_ticket, ret);
s2n(0, ret);
} else {
/*
* if we don't add the above TLSEXT, we can't add a session ticket
* later
*/
s->tlsext_ticket_expected = 0;
}
if (s->tlsext_status_expected) {
/*-
* check for enough space.
* 4 bytes for the Status request type and extension length
*/
if (CHECKLEN(ret, 4, limit))
return NULL;
s2n(TLSEXT_TYPE_status_request, ret);
s2n(0, ret);
}
#ifndef OPENSSL_NO_SRTP
if (SSL_IS_DTLS(s) && s->srtp_profile) {
int el;
/* Returns 0 on success!! */
if (ssl_add_serverhello_use_srtp_ext(s, 0, &el, 0)) {
SSLerr(SSL_F_SSL_ADD_SERVERHELLO_TLSEXT, ERR_R_INTERNAL_ERROR);
return NULL;
}
/*-
* check for enough space.
* 4 bytes for the SRTP profiles type and extension length
* + length of the SRTP profiles list
*/
if (CHECKLEN(ret, 4 + el, limit))
return NULL;
s2n(TLSEXT_TYPE_use_srtp, ret);
s2n(el, ret);
if (ssl_add_serverhello_use_srtp_ext(s, ret, &el, el)) {
SSLerr(SSL_F_SSL_ADD_SERVERHELLO_TLSEXT, ERR_R_INTERNAL_ERROR);
return NULL;
}
ret += el;
}
#endif
if (((s->s3->tmp.new_cipher->id & 0xFFFF) == 0x80
|| (s->s3->tmp.new_cipher->id & 0xFFFF) == 0x81)
&& (SSL_get_options(s) & SSL_OP_CRYPTOPRO_TLSEXT_BUG)) {
const unsigned char cryptopro_ext[36] = {
0xfd, 0xe8, /* 65000 */
0x00, 0x20, /* 32 bytes length */
0x30, 0x1e, 0x30, 0x08, 0x06, 0x06, 0x2a, 0x85,
0x03, 0x02, 0x02, 0x09, 0x30, 0x08, 0x06, 0x06,
0x2a, 0x85, 0x03, 0x02, 0x02, 0x16, 0x30, 0x08,
0x06, 0x06, 0x2a, 0x85, 0x03, 0x02, 0x02, 0x17
};
/* check for enough space. */
if (CHECKLEN(ret, sizeof(cryptopro_ext), limit))
return NULL;
memcpy(ret, cryptopro_ext, sizeof(cryptopro_ext));
ret += sizeof(cryptopro_ext);
}
#ifndef OPENSSL_NO_HEARTBEATS
/* Add Heartbeat extension if we've received one */
if (SSL_IS_DTLS(s) && (s->tlsext_heartbeat & SSL_DTLSEXT_HB_ENABLED)) {
/*-
* check for enough space.
* 4 bytes for the Heartbeat type and extension length
* 1 byte for the mode
*/
if (CHECKLEN(ret, 5, limit))
return NULL;
s2n(TLSEXT_TYPE_heartbeat, ret);
s2n(1, ret);
/*-
* Set mode:
* 1: peer may send requests
* 2: peer not allowed to send requests
*/
if (s->tlsext_heartbeat & SSL_DTLSEXT_HB_DONT_RECV_REQUESTS)
*(ret++) = SSL_DTLSEXT_HB_DONT_SEND_REQUESTS;
else
*(ret++) = SSL_DTLSEXT_HB_ENABLED;
}
#endif
#ifndef OPENSSL_NO_NEXTPROTONEG
next_proto_neg_seen = s->s3->next_proto_neg_seen;
s->s3->next_proto_neg_seen = 0;
if (next_proto_neg_seen && s->ctx->next_protos_advertised_cb) {
const unsigned char *npa;
unsigned int npalen;
int r;
r = s->ctx->next_protos_advertised_cb(s, &npa, &npalen,
s->
ctx->next_protos_advertised_cb_arg);
if (r == SSL_TLSEXT_ERR_OK) {
/*-
* check for enough space.
* 4 bytes for the NPN type and extension length
* + length of protocols list
*/
if (CHECKLEN(ret, 4 + npalen, limit))
return NULL;
s2n(TLSEXT_TYPE_next_proto_neg, ret);
s2n(npalen, ret);
memcpy(ret, npa, npalen);
ret += npalen;
s->s3->next_proto_neg_seen = 1;
}
}
#endif
if (!custom_ext_add(s, 1, &ret, limit, al))
return NULL;
if (s->s3->flags & TLS1_FLAGS_ENCRYPT_THEN_MAC) {
/*
* Don't use encrypt_then_mac if AEAD or RC4 might want to disable
* for other cases too.
*/
if (SSL_IS_DTLS(s) || s->s3->tmp.new_cipher->algorithm_mac == SSL_AEAD
|| s->s3->tmp.new_cipher->algorithm_enc == SSL_RC4
|| s->s3->tmp.new_cipher->algorithm_enc == SSL_eGOST2814789CNT
|| s->s3->tmp.new_cipher->algorithm_enc == SSL_eGOST2814789CNT12)
s->s3->flags &= ~TLS1_FLAGS_ENCRYPT_THEN_MAC;
else {
/*-
* check for enough space.
* 4 bytes for the ETM type and extension length
*/
if (CHECKLEN(ret, 4, limit))
return NULL;
s2n(TLSEXT_TYPE_encrypt_then_mac, ret);
s2n(0, ret);
}
}
if (s->s3->flags & TLS1_FLAGS_RECEIVED_EXTMS) {
/*-
* check for enough space.
* 4 bytes for the EMS type and extension length
*/
if (CHECKLEN(ret, 4, limit))
return NULL;
s2n(TLSEXT_TYPE_extended_master_secret, ret);
s2n(0, ret);
}
if (s->s3->alpn_selected != NULL) {
const unsigned char *selected = s->s3->alpn_selected;
size_t len = s->s3->alpn_selected_len;
/*-
* check for enough space.
* 4 bytes for the ALPN type and extension length
* 2 bytes for ALPN data length
* 1 byte for selected protocol length
* + length of the selected protocol
*/
if (CHECKLEN(ret, 7 + len, limit))
return NULL;
s2n(TLSEXT_TYPE_application_layer_protocol_negotiation, ret);
s2n(3 + len, ret);
s2n(1 + len, ret);
*ret++ = len;
memcpy(ret, selected, len);
ret += len;
}
done:
if ((extdatalen = ret - orig - 2) == 0)
return orig;
s2n(extdatalen, orig);
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Don't change the state of the ETM flags until CCS processing
Changing the ciphersuite during a renegotiation can result in a crash
leading to a DoS attack. ETM has not been implemented in 1.1.0 for DTLS
so this is TLS only.
The problem is caused by changing the flag indicating whether to use ETM
or not immediately on negotiation of ETM, rather than at CCS. Therefore,
during a renegotiation, if the ETM state is changing (usually due to a
change of ciphersuite), then an error/crash will occur.
Due to the fact that there are separate CCS messages for read and write
we actually now need two flags to determine whether to use ETM or not.
CVE-2017-3733
Reviewed-by: Richard Levitte <levitte@openssl.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: BIO *PKCS7_dataDecode(PKCS7 *p7, EVP_PKEY *pkey, BIO *in_bio, X509 *pcert)
{
int i, j;
BIO *out = NULL, *btmp = NULL, *etmp = NULL, *bio = NULL;
X509_ALGOR *xa;
ASN1_OCTET_STRING *data_body = NULL;
const EVP_MD *evp_md;
const EVP_CIPHER *evp_cipher = NULL;
EVP_CIPHER_CTX *evp_ctx = NULL;
X509_ALGOR *enc_alg = NULL;
STACK_OF(X509_ALGOR) *md_sk = NULL;
STACK_OF(PKCS7_RECIP_INFO) *rsk = NULL;
PKCS7_RECIP_INFO *ri = NULL;
unsigned char *ek = NULL, *tkey = NULL;
int eklen = 0, tkeylen = 0;
if (p7 == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE, PKCS7_R_INVALID_NULL_POINTER);
return NULL;
}
if (p7->d.ptr == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE, PKCS7_R_NO_CONTENT);
return NULL;
}
i = OBJ_obj2nid(p7->type);
p7->state = PKCS7_S_HEADER;
switch (i) {
case NID_pkcs7_signed:
data_body = PKCS7_get_octet_string(p7->d.sign->contents);
if (!PKCS7_is_detached(p7) && data_body == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE,
PKCS7_R_INVALID_SIGNED_DATA_TYPE);
goto err;
}
md_sk = p7->d.sign->md_algs;
break;
case NID_pkcs7_signedAndEnveloped:
rsk = p7->d.signed_and_enveloped->recipientinfo;
md_sk = p7->d.signed_and_enveloped->md_algs;
data_body = p7->d.signed_and_enveloped->enc_data->enc_data;
enc_alg = p7->d.signed_and_enveloped->enc_data->algorithm;
evp_cipher = EVP_get_cipherbyobj(enc_alg->algorithm);
if (evp_cipher == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE,
PKCS7_R_UNSUPPORTED_CIPHER_TYPE);
goto err;
}
break;
case NID_pkcs7_enveloped:
rsk = p7->d.enveloped->recipientinfo;
enc_alg = p7->d.enveloped->enc_data->algorithm;
data_body = p7->d.enveloped->enc_data->enc_data;
evp_cipher = EVP_get_cipherbyobj(enc_alg->algorithm);
if (evp_cipher == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE,
PKCS7_R_UNSUPPORTED_CIPHER_TYPE);
goto err;
}
break;
default:
PKCS7err(PKCS7_F_PKCS7_DATADECODE, PKCS7_R_UNSUPPORTED_CONTENT_TYPE);
goto err;
}
/* We will be checking the signature */
if (md_sk != NULL) {
for (i = 0; i < sk_X509_ALGOR_num(md_sk); i++) {
xa = sk_X509_ALGOR_value(md_sk, i);
if ((btmp = BIO_new(BIO_f_md())) == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE, ERR_R_BIO_LIB);
goto err;
}
j = OBJ_obj2nid(xa->algorithm);
evp_md = EVP_get_digestbynid(j);
if (evp_md == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE,
PKCS7_R_UNKNOWN_DIGEST_TYPE);
goto err;
}
BIO_set_md(btmp, evp_md);
if (out == NULL)
out = btmp;
else
BIO_push(out, btmp);
btmp = NULL;
}
}
if (evp_cipher != NULL) {
if ((etmp = BIO_new(BIO_f_cipher())) == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE, ERR_R_BIO_LIB);
goto err;
}
/*
* It was encrypted, we need to decrypt the secret key with the
* private key
*/
/*
* Find the recipientInfo which matches the passed certificate (if
* any)
*/
if (pcert) {
for (i = 0; i < sk_PKCS7_RECIP_INFO_num(rsk); i++) {
ri = sk_PKCS7_RECIP_INFO_value(rsk, i);
if (!pkcs7_cmp_ri(ri, pcert))
break;
ri = NULL;
}
if (ri == NULL) {
PKCS7err(PKCS7_F_PKCS7_DATADECODE,
PKCS7_R_NO_RECIPIENT_MATCHES_CERTIFICATE);
goto err;
}
}
/* If we haven't got a certificate try each ri in turn */
if (pcert == NULL) {
/*
* Always attempt to decrypt all rinfo even after success as a
* defence against MMA timing attacks.
*/
for (i = 0; i < sk_PKCS7_RECIP_INFO_num(rsk); i++) {
ri = sk_PKCS7_RECIP_INFO_value(rsk, i);
if (pkcs7_decrypt_rinfo(&ek, &eklen, ri, pkey) < 0)
goto err;
ERR_clear_error();
}
} else {
/* Only exit on fatal errors, not decrypt failure */
if (pkcs7_decrypt_rinfo(&ek, &eklen, ri, pkey) < 0)
goto err;
ERR_clear_error();
}
evp_ctx = NULL;
BIO_get_cipher_ctx(etmp, &evp_ctx);
if (EVP_CipherInit_ex(evp_ctx, evp_cipher, NULL, NULL, NULL, 0) <= 0)
goto err;
if (EVP_CIPHER_asn1_to_param(evp_ctx, enc_alg->parameter) < 0)
goto err;
/* Generate random key as MMA defence */
tkeylen = EVP_CIPHER_CTX_key_length(evp_ctx);
tkey = OPENSSL_malloc(tkeylen);
if (!tkey)
goto err;
if (EVP_CIPHER_CTX_rand_key(evp_ctx, tkey) <= 0)
goto err;
if (ek == NULL) {
ek = tkey;
eklen = tkeylen;
tkey = NULL;
}
if (eklen != EVP_CIPHER_CTX_key_length(evp_ctx)) {
/*
* Some S/MIME clients don't use the same key and effective key
* length. The key length is determined by the size of the
* decrypted RSA key.
*/
if (!EVP_CIPHER_CTX_set_key_length(evp_ctx, eklen)) {
/* Use random key as MMA defence */
OPENSSL_clear_free(ek, eklen);
ek = tkey;
eklen = tkeylen;
tkey = NULL;
}
}
/* Clear errors so we don't leak information useful in MMA */
ERR_clear_error();
if (EVP_CipherInit_ex(evp_ctx, NULL, NULL, ek, NULL, 0) <= 0)
goto err;
OPENSSL_clear_free(ek, eklen);
ek = NULL;
OPENSSL_clear_free(tkey, tkeylen);
tkey = NULL;
if (out == NULL)
out = etmp;
else
BIO_push(out, etmp);
etmp = NULL;
}
if (PKCS7_is_detached(p7) || (in_bio != NULL)) {
bio = in_bio;
} else {
if (data_body->length > 0)
bio = BIO_new_mem_buf(data_body->data, data_body->length);
else {
bio = BIO_new(BIO_s_mem());
BIO_set_mem_eof_return(bio, 0);
}
if (bio == NULL)
goto err;
}
BIO_push(out, bio);
bio = NULL;
return out;
err:
OPENSSL_clear_free(ek, eklen);
OPENSSL_clear_free(tkey, tkeylen);
BIO_free_all(out);
BIO_free_all(btmp);
BIO_free_all(etmp);
BIO_free_all(bio);
return NULL;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-703'], 'message': 'PKCS#7: Fix NULL dereference with missing EncryptedContent.
CVE-2015-1790
Reviewed-by: Rich Salz <rsalz@openssl.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int pdo_sqlite_handle_factory(pdo_dbh_t *dbh, zval *driver_options TSRMLS_DC) /* {{{ */
{
pdo_sqlite_db_handle *H;
int i, ret = 0;
long timeout = 60;
char *filename;
H = pecalloc(1, sizeof(pdo_sqlite_db_handle), dbh->is_persistent);
H->einfo.errcode = 0;
H->einfo.errmsg = NULL;
dbh->driver_data = H;
filename = make_filename_safe(dbh->data_source TSRMLS_CC);
if (!filename) {
zend_throw_exception_ex(php_pdo_get_exception(), 0 TSRMLS_CC,
"safe_mode/open_basedir prohibits opening %s",
dbh->data_source);
goto cleanup;
}
i = sqlite3_open(filename, &H->db);
efree(filename);
if (i != SQLITE_OK) {
pdo_sqlite_error(dbh);
goto cleanup;
}
if (PG(safe_mode) || (PG(open_basedir) && *PG(open_basedir))) {
sqlite3_set_authorizer(H->db, authorizer, NULL);
}
if (driver_options) {
timeout = pdo_attr_lval(driver_options, PDO_ATTR_TIMEOUT, timeout TSRMLS_CC);
}
sqlite3_busy_timeout(H->db, timeout * 1000);
dbh->alloc_own_columns = 1;
dbh->max_escaped_char_length = 2;
ret = 1;
cleanup:
dbh->methods = &sqlite_methods;
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'Improve check for :memory: pseudo-filename in SQlite'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int sqlite_handle_quoter(pdo_dbh_t *dbh, const char *unquoted, int unquotedlen, char **quoted, int *quotedlen, enum pdo_param_type paramtype TSRMLS_DC)
{
*quoted = safe_emalloc(2, unquotedlen, 3);
sqlite3_snprintf(2*unquotedlen + 3, *quoted, "'%q'", unquoted);
*quotedlen = strlen(*quoted);
return 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'Improve check for :memory: pseudo-filename in SQlite'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void pdo_sqlite_cleanup_callbacks(pdo_sqlite_db_handle *H TSRMLS_DC)
{
struct pdo_sqlite_func *func;
while (H->funcs) {
func = H->funcs;
H->funcs = func->next;
if (H->db) {
/* delete the function from the handle */
sqlite3_create_function(H->db,
func->funcname,
func->argc,
SQLITE_UTF8,
func,
NULL, NULL, NULL);
}
efree((char*)func->funcname);
if (func->func) {
zval_ptr_dtor(&func->func);
}
if (func->step) {
zval_ptr_dtor(&func->step);
}
if (func->fini) {
zval_ptr_dtor(&func->fini);
}
efree(func);
}
while (H->collations) {
struct pdo_sqlite_collation *collation;
collation = H->collations;
H->collations = collation->next;
if (H->db) {
/* delete the collation from the handle */
sqlite3_create_collation(H->db,
collation->name,
SQLITE_UTF8,
collation,
NULL);
}
efree((char*)collation->name);
if (collation->callback) {
zval_ptr_dtor(&collation->callback);
}
efree(collation);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'Improve check for :memory: pseudo-filename in SQlite'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void cirrus_bitblt_reset(CirrusVGAState * s)
{
s->gr[0x31] &=
~(CIRRUS_BLT_START | CIRRUS_BLT_BUSY | CIRRUS_BLT_FIFOUSED);
s->cirrus_srcptr = &s->cirrus_bltbuf[0];
s->cirrus_srcptr_end = &s->cirrus_bltbuf[0];
s->cirrus_srccounter = 0;
cirrus_update_memory_access(s);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void cirrus_mmio_blt_write(CirrusVGAState * s, unsigned address,
uint8_t value)
{
switch (address) {
case (CIRRUS_MMIO_BLTBGCOLOR + 0):
cirrus_hook_write_gr(s, 0x00, value);
break;
case (CIRRUS_MMIO_BLTBGCOLOR + 1):
cirrus_hook_write_gr(s, 0x10, value);
break;
case (CIRRUS_MMIO_BLTBGCOLOR + 2):
cirrus_hook_write_gr(s, 0x12, value);
break;
case (CIRRUS_MMIO_BLTBGCOLOR + 3):
cirrus_hook_write_gr(s, 0x14, value);
break;
case (CIRRUS_MMIO_BLTFGCOLOR + 0):
cirrus_hook_write_gr(s, 0x01, value);
break;
case (CIRRUS_MMIO_BLTFGCOLOR + 1):
cirrus_hook_write_gr(s, 0x11, value);
break;
case (CIRRUS_MMIO_BLTFGCOLOR + 2):
cirrus_hook_write_gr(s, 0x13, value);
break;
case (CIRRUS_MMIO_BLTFGCOLOR + 3):
cirrus_hook_write_gr(s, 0x15, value);
break;
case (CIRRUS_MMIO_BLTWIDTH + 0):
cirrus_hook_write_gr(s, 0x20, value);
break;
case (CIRRUS_MMIO_BLTWIDTH + 1):
cirrus_hook_write_gr(s, 0x21, value);
break;
case (CIRRUS_MMIO_BLTHEIGHT + 0):
cirrus_hook_write_gr(s, 0x22, value);
break;
case (CIRRUS_MMIO_BLTHEIGHT + 1):
cirrus_hook_write_gr(s, 0x23, value);
break;
case (CIRRUS_MMIO_BLTDESTPITCH + 0):
cirrus_hook_write_gr(s, 0x24, value);
break;
case (CIRRUS_MMIO_BLTDESTPITCH + 1):
cirrus_hook_write_gr(s, 0x25, value);
break;
case (CIRRUS_MMIO_BLTSRCPITCH + 0):
cirrus_hook_write_gr(s, 0x26, value);
break;
case (CIRRUS_MMIO_BLTSRCPITCH + 1):
cirrus_hook_write_gr(s, 0x27, value);
break;
case (CIRRUS_MMIO_BLTDESTADDR + 0):
cirrus_hook_write_gr(s, 0x28, value);
break;
case (CIRRUS_MMIO_BLTDESTADDR + 1):
cirrus_hook_write_gr(s, 0x29, value);
break;
case (CIRRUS_MMIO_BLTDESTADDR + 2):
cirrus_hook_write_gr(s, 0x2a, value);
break;
case (CIRRUS_MMIO_BLTDESTADDR + 3):
/* ignored */
break;
case (CIRRUS_MMIO_BLTSRCADDR + 0):
cirrus_hook_write_gr(s, 0x2c, value);
break;
case (CIRRUS_MMIO_BLTSRCADDR + 1):
cirrus_hook_write_gr(s, 0x2d, value);
break;
case (CIRRUS_MMIO_BLTSRCADDR + 2):
cirrus_hook_write_gr(s, 0x2e, value);
break;
case CIRRUS_MMIO_BLTWRITEMASK:
cirrus_hook_write_gr(s, 0x2f, value);
break;
case CIRRUS_MMIO_BLTMODE:
cirrus_hook_write_gr(s, 0x30, value);
break;
case CIRRUS_MMIO_BLTROP:
cirrus_hook_write_gr(s, 0x32, value);
break;
case CIRRUS_MMIO_BLTMODEEXT:
cirrus_hook_write_gr(s, 0x33, value);
break;
case (CIRRUS_MMIO_BLTTRANSPARENTCOLOR + 0):
cirrus_hook_write_gr(s, 0x34, value);
break;
case (CIRRUS_MMIO_BLTTRANSPARENTCOLOR + 1):
cirrus_hook_write_gr(s, 0x35, value);
break;
case (CIRRUS_MMIO_BLTTRANSPARENTCOLORMASK + 0):
cirrus_hook_write_gr(s, 0x38, value);
break;
case (CIRRUS_MMIO_BLTTRANSPARENTCOLORMASK + 1):
cirrus_hook_write_gr(s, 0x39, value);
break;
case CIRRUS_MMIO_BLTSTATUS:
cirrus_hook_write_gr(s, 0x31, value);
break;
default:
#ifdef DEBUG_CIRRUS
printf("cirrus: mmio write - addr 0x%04x val 0x%02x (ignored)\n",
address, value);
#endif
break;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static uint32_t cirrus_linear_readb(void *opaque, target_phys_addr_t addr)
{
CirrusVGAState *s = (CirrusVGAState *) opaque;
uint32_t ret;
addr &= s->cirrus_addr_mask;
if (((s->sr[0x17] & 0x44) == 0x44) &&
((addr & s->linear_mmio_mask) == s->linear_mmio_mask)) {
/* memory-mapped I/O */
ret = cirrus_mmio_blt_read(s, addr & 0xff);
} else if (0) {
/* XXX handle bitblt */
ret = 0xff;
} else {
/* video memory */
if ((s->gr[0x0B] & 0x14) == 0x14) {
addr <<= 4;
} else if (s->gr[0x0B] & 0x02) {
addr <<= 3;
}
addr &= s->cirrus_addr_mask;
ret = *(s->vram_ptr + addr);
}
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: glue(glue(cirrus_bitblt_rop_fwd_transp_, ROP_NAME),_16)(CirrusVGAState *s,
uint8_t *dst,const uint8_t *src,
int dstpitch,int srcpitch,
int bltwidth,int bltheight)
{
int x,y;
uint8_t p1, p2;
dstpitch -= bltwidth;
srcpitch -= bltwidth;
for (y = 0; y < bltheight; y++) {
for (x = 0; x < bltwidth; x+=2) {
p1 = *dst;
p2 = *(dst+1);
ROP_OP(p1, *src);
ROP_OP(p2, *(src+1));
if ((p1 != s->gr[0x34]) || (p2 != s->gr[0x35])) {
*dst = p1;
*(dst+1) = p2;
}
dst+=2;
src+=2;
}
dst += dstpitch;
src += srcpitch;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int cirrus_bitblt_videotovideo(CirrusVGAState * s)
{
int ret;
if (s->cirrus_blt_mode & CIRRUS_BLTMODE_PATTERNCOPY) {
ret = cirrus_bitblt_videotovideo_patterncopy(s);
} else {
ret = cirrus_bitblt_videotovideo_copy(s);
}
if (ret)
cirrus_bitblt_reset(s);
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void cirrus_cursor_invalidate(VGAState *s1)
{
CirrusVGAState *s = (CirrusVGAState *)s1;
int size;
if (!s->sr[0x12] & CIRRUS_CURSOR_SHOW) {
size = 0;
} else {
if (s->sr[0x12] & CIRRUS_CURSOR_LARGE)
size = 64;
else
size = 32;
}
/* invalidate last cursor and new cursor if any change */
if (s->last_hw_cursor_size != size ||
s->last_hw_cursor_x != s->hw_cursor_x ||
s->last_hw_cursor_y != s->hw_cursor_y) {
invalidate_cursor1(s);
s->last_hw_cursor_size = size;
s->last_hw_cursor_x = s->hw_cursor_x;
s->last_hw_cursor_y = s->hw_cursor_y;
/* compute the real cursor min and max y */
cirrus_cursor_compute_yrange(s);
invalidate_cursor1(s);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int cirrus_hook_write_palette(CirrusVGAState * s, int reg_value)
{
if (!(s->sr[0x12] & CIRRUS_CURSOR_HIDDENPEL))
return CIRRUS_HOOK_NOT_HANDLED;
s->dac_cache[s->dac_sub_index] = reg_value;
if (++s->dac_sub_index == 3) {
memcpy(&s->cirrus_hidden_palette[(s->dac_write_index & 0x0f) * 3],
s->dac_cache, 3);
/* XXX update cursor */
s->dac_sub_index = 0;
s->dac_write_index++;
}
return CIRRUS_HOOK_HANDLED;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void vga_ioport_write(void *opaque, uint32_t addr, uint32_t val)
{
CirrusVGAState *s = opaque;
int index;
/* check port range access depending on color/monochrome mode */
if ((addr >= 0x3b0 && addr <= 0x3bf && (s->msr & MSR_COLOR_EMULATION))
|| (addr >= 0x3d0 && addr <= 0x3df
&& !(s->msr & MSR_COLOR_EMULATION)))
return;
#ifdef DEBUG_VGA
printf("VGA: write addr=0x%04x data=0x%02x\n", addr, val);
#endif
switch (addr) {
case 0x3c0:
if (s->ar_flip_flop == 0) {
val &= 0x3f;
s->ar_index = val;
} else {
index = s->ar_index & 0x1f;
switch (index) {
case 0x00 ... 0x0f:
s->ar[index] = val & 0x3f;
break;
case 0x10:
s->ar[index] = val & ~0x10;
break;
case 0x11:
s->ar[index] = val;
break;
case 0x12:
s->ar[index] = val & ~0xc0;
break;
case 0x13:
s->ar[index] = val & ~0xf0;
break;
case 0x14:
s->ar[index] = val & ~0xf0;
break;
default:
break;
}
}
s->ar_flip_flop ^= 1;
break;
case 0x3c2:
s->msr = val & ~0x10;
break;
case 0x3c4:
s->sr_index = val;
break;
case 0x3c5:
if (cirrus_hook_write_sr(s, s->sr_index, val))
break;
#ifdef DEBUG_VGA_REG
printf("vga: write SR%x = 0x%02x\n", s->sr_index, val);
#endif
s->sr[s->sr_index] = val & sr_mask[s->sr_index];
break;
case 0x3c6:
cirrus_write_hidden_dac(s, val);
break;
case 0x3c7:
s->dac_read_index = val;
s->dac_sub_index = 0;
s->dac_state = 3;
break;
case 0x3c8:
s->dac_write_index = val;
s->dac_sub_index = 0;
s->dac_state = 0;
break;
case 0x3c9:
if (cirrus_hook_write_palette(s, val))
break;
s->dac_cache[s->dac_sub_index] = val;
if (++s->dac_sub_index == 3) {
memcpy(&s->palette[s->dac_write_index * 3], s->dac_cache, 3);
s->dac_sub_index = 0;
s->dac_write_index++;
}
break;
case 0x3ce:
s->gr_index = val;
break;
case 0x3cf:
if (cirrus_hook_write_gr(s, s->gr_index, val))
break;
#ifdef DEBUG_VGA_REG
printf("vga: write GR%x = 0x%02x\n", s->gr_index, val);
#endif
s->gr[s->gr_index] = val & gr_mask[s->gr_index];
break;
case 0x3b4:
case 0x3d4:
s->cr_index = val;
break;
case 0x3b5:
case 0x3d5:
if (cirrus_hook_write_cr(s, s->cr_index, val))
break;
#ifdef DEBUG_VGA_REG
printf("vga: write CR%x = 0x%02x\n", s->cr_index, val);
#endif
/* handle CR0-7 protection */
if ((s->cr[0x11] & 0x80) && s->cr_index <= 7) {
/* can always write bit 4 of CR7 */
if (s->cr_index == 7)
s->cr[7] = (s->cr[7] & ~0x10) | (val & 0x10);
return;
}
switch (s->cr_index) {
case 0x01: /* horizontal display end */
case 0x07:
case 0x09:
case 0x0c:
case 0x0d:
case 0x12: /* vertical display end */
s->cr[s->cr_index] = val;
break;
default:
s->cr[s->cr_index] = val;
break;
}
break;
case 0x3ba:
case 0x3da:
s->fcr = val & 0x10;
break;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void vga_ioport_write(void *opaque, uint32_t addr, uint32_t val)
{
CirrusVGAState *s = opaque;
int index;
/* check port range access depending on color/monochrome mode */
if ((addr >= 0x3b0 && addr <= 0x3bf && (s->msr & MSR_COLOR_EMULATION))
|| (addr >= 0x3d0 && addr <= 0x3df
&& !(s->msr & MSR_COLOR_EMULATION)))
return;
#ifdef DEBUG_VGA
printf("VGA: write addr=0x%04x data=0x%02x\n", addr, val);
#endif
switch (addr) {
case 0x3c0:
if (s->ar_flip_flop == 0) {
val &= 0x3f;
s->ar_index = val;
} else {
index = s->ar_index & 0x1f;
switch (index) {
case 0x00 ... 0x0f:
s->ar[index] = val & 0x3f;
break;
case 0x10:
s->ar[index] = val & ~0x10;
break;
case 0x11:
s->ar[index] = val;
break;
case 0x12:
s->ar[index] = val & ~0xc0;
break;
case 0x13:
s->ar[index] = val & ~0xf0;
break;
case 0x14:
s->ar[index] = val & ~0xf0;
break;
default:
break;
}
}
s->ar_flip_flop ^= 1;
break;
case 0x3c2:
s->msr = val & ~0x10;
s->update_retrace_info((VGAState *) s);
break;
case 0x3c4:
s->sr_index = val;
break;
case 0x3c5:
if (cirrus_hook_write_sr(s, s->sr_index, val))
break;
#ifdef DEBUG_VGA_REG
printf("vga: write SR%x = 0x%02x\n", s->sr_index, val);
#endif
s->sr[s->sr_index] = val & sr_mask[s->sr_index];
if (s->sr_index == 1) s->update_retrace_info((VGAState *) s);
break;
case 0x3c6:
cirrus_write_hidden_dac(s, val);
break;
case 0x3c7:
s->dac_read_index = val;
s->dac_sub_index = 0;
s->dac_state = 3;
break;
case 0x3c8:
s->dac_write_index = val;
s->dac_sub_index = 0;
s->dac_state = 0;
break;
case 0x3c9:
if (cirrus_hook_write_palette(s, val))
break;
s->dac_cache[s->dac_sub_index] = val;
if (++s->dac_sub_index == 3) {
memcpy(&s->palette[s->dac_write_index * 3], s->dac_cache, 3);
s->dac_sub_index = 0;
s->dac_write_index++;
}
break;
case 0x3ce:
s->gr_index = val;
break;
case 0x3cf:
if (cirrus_hook_write_gr(s, s->gr_index, val))
break;
#ifdef DEBUG_VGA_REG
printf("vga: write GR%x = 0x%02x\n", s->gr_index, val);
#endif
s->gr[s->gr_index] = val & gr_mask[s->gr_index];
break;
case 0x3b4:
case 0x3d4:
s->cr_index = val;
break;
case 0x3b5:
case 0x3d5:
if (cirrus_hook_write_cr(s, s->cr_index, val))
break;
#ifdef DEBUG_VGA_REG
printf("vga: write CR%x = 0x%02x\n", s->cr_index, val);
#endif
/* handle CR0-7 protection */
if ((s->cr[0x11] & 0x80) && s->cr_index <= 7) {
/* can always write bit 4 of CR7 */
if (s->cr_index == 7)
s->cr[7] = (s->cr[7] & ~0x10) | (val & 0x10);
return;
}
switch (s->cr_index) {
case 0x01: /* horizontal display end */
case 0x07:
case 0x09:
case 0x0c:
case 0x0d:
case 0x12: /* vertical display end */
s->cr[s->cr_index] = val;
break;
default:
s->cr[s->cr_index] = val;
break;
}
switch(s->cr_index) {
case 0x00:
case 0x04:
case 0x05:
case 0x06:
case 0x07:
case 0x11:
case 0x17:
s->update_retrace_info((VGAState *) s);
break;
}
break;
case 0x3ba:
case 0x3da:
s->fcr = val & 0x10;
break;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2008-4539: fix a heap overflow in Cirrus emulation
The code in hw/cirrus_vga.c has changed a lot between CVE-2007-1320 has
been announced and the patch has been applied. As a consequence it has
wrongly applied and QEMU is still vulnerable to this bug if using VNC.
(noticed by Jan Niehusmann)
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5587 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
struct user * dummy = NULL;
int i, ret;
unsigned long __user *datap = (unsigned long __user *)data;
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA:
ret = generic_ptrace_peekdata(child, addr, data);
break;
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long tmp;
ret = -EIO;
if ((addr & 3) || addr < 0 ||
addr > sizeof(struct user) - 3)
break;
tmp = 0; /* Default return condition */
if(addr < FRAME_SIZE*sizeof(long))
tmp = getreg(child, addr);
if(addr >= (long) &dummy->u_debugreg[0] &&
addr <= (long) &dummy->u_debugreg[7]){
addr -= (long) &dummy->u_debugreg[0];
addr = addr >> 2;
tmp = child->thread.debugreg[addr];
}
ret = put_user(tmp, datap);
break;
}
/* when I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = generic_ptrace_pokedata(child, addr, data);
break;
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
ret = -EIO;
if ((addr & 3) || addr < 0 ||
addr > sizeof(struct user) - 3)
break;
if (addr < FRAME_SIZE*sizeof(long)) {
ret = putreg(child, addr, data);
break;
}
/* We need to be very careful here. We implicitly
want to modify a portion of the task_struct, and we
have to be selective about what portions we allow someone
to modify. */
ret = -EIO;
if(addr >= (long) &dummy->u_debugreg[0] &&
addr <= (long) &dummy->u_debugreg[7]){
if(addr == (long) &dummy->u_debugreg[4]) break;
if(addr == (long) &dummy->u_debugreg[5]) break;
if(addr < (long) &dummy->u_debugreg[4] &&
((unsigned long) data) >= TASK_SIZE-3) break;
/* Sanity-check data. Take one half-byte at once with
* check = (val >> (16 + 4*i)) & 0xf. It contains the
* R/Wi and LENi bits; bits 0 and 1 are R/Wi, and bits
* 2 and 3 are LENi. Given a list of invalid values,
* we do mask |= 1 << invalid_value, so that
* (mask >> check) & 1 is a correct test for invalid
* values.
*
* R/Wi contains the type of the breakpoint /
* watchpoint, LENi contains the length of the watched
* data in the watchpoint case.
*
* The invalid values are:
* - LENi == 0x10 (undefined), so mask |= 0x0f00.
* - R/Wi == 0x10 (break on I/O reads or writes), so
* mask |= 0x4444.
* - R/Wi == 0x00 && LENi != 0x00, so we have mask |=
* 0x1110.
*
* Finally, mask = 0x0f00 | 0x4444 | 0x1110 == 0x5f54.
*
* See the Intel Manual "System Programming Guide",
* 15.2.4
*
* Note that LENi == 0x10 is defined on x86_64 in long
* mode (i.e. even for 32-bit userspace software, but
* 64-bit kernel), so the x86_64 mask value is 0x5454.
* See the AMD manual no. 24593 (AMD64 System
* Programming)*/
if(addr == (long) &dummy->u_debugreg[7]) {
data &= ~DR_CONTROL_RESERVED;
for(i=0; i<4; i++)
if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
goto out_tsk;
if (data)
set_tsk_thread_flag(child, TIF_DEBUG);
else
clear_tsk_thread_flag(child, TIF_DEBUG);
}
addr -= (long) &dummy->u_debugreg;
addr = addr >> 2;
child->thread.debugreg[addr] = data;
ret = 0;
}
break;
case PTRACE_SYSEMU: /* continue and stop at next syscall, which will not be executed */
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: /* restart after signal. */
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSEMU) {
set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
} else if (request == PTRACE_SYSCALL) {
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
} else {
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
child->exit_code = data;
/* make sure the single step bit is not set. */
clear_singlestep(child);
wake_up_process(child);
ret = 0;
break;
/*
* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL:
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
/* make sure the single step bit is not set. */
clear_singlestep(child);
wake_up_process(child);
break;
case PTRACE_SYSEMU_SINGLESTEP: /* Same as SYSEMU, but singlestep if not syscall */
case PTRACE_SINGLESTEP: /* set the trap flag. */
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSEMU_SINGLESTEP)
set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
set_singlestep(child);
child->exit_code = data;
/* give it a chance to run. */
wake_up_process(child);
ret = 0;
break;
case PTRACE_DETACH:
/* detach a process that was attached. */
ret = ptrace_detach(child, data);
break;
case PTRACE_GETREGS: { /* Get all gp regs from the child. */
if (!access_ok(VERIFY_WRITE, datap, FRAME_SIZE*sizeof(long))) {
ret = -EIO;
break;
}
for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
__put_user(getreg(child, i), datap);
datap++;
}
ret = 0;
break;
}
case PTRACE_SETREGS: { /* Set all gp regs in the child. */
unsigned long tmp;
if (!access_ok(VERIFY_READ, datap, FRAME_SIZE*sizeof(long))) {
ret = -EIO;
break;
}
for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
__get_user(tmp, datap);
putreg(child, i, tmp);
datap++;
}
ret = 0;
break;
}
case PTRACE_GETFPREGS: { /* Get the child FPU state. */
if (!access_ok(VERIFY_WRITE, datap,
sizeof(struct user_i387_struct))) {
ret = -EIO;
break;
}
ret = 0;
if (!tsk_used_math(child))
init_fpu(child);
get_fpregs((struct user_i387_struct __user *)data, child);
break;
}
case PTRACE_SETFPREGS: { /* Set the child FPU state. */
if (!access_ok(VERIFY_READ, datap,
sizeof(struct user_i387_struct))) {
ret = -EIO;
break;
}
set_stopped_child_used_math(child);
set_fpregs(child, (struct user_i387_struct __user *)data);
ret = 0;
break;
}
case PTRACE_GETFPXREGS: { /* Get the child extended FPU state. */
if (!access_ok(VERIFY_WRITE, datap,
sizeof(struct user_fxsr_struct))) {
ret = -EIO;
break;
}
if (!tsk_used_math(child))
init_fpu(child);
ret = get_fpxregs((struct user_fxsr_struct __user *)data, child);
break;
}
case PTRACE_SETFPXREGS: { /* Set the child extended FPU state. */
if (!access_ok(VERIFY_READ, datap,
sizeof(struct user_fxsr_struct))) {
ret = -EIO;
break;
}
set_stopped_child_used_math(child);
ret = set_fpxregs(child, (struct user_fxsr_struct __user *)data);
break;
}
case PTRACE_GET_THREAD_AREA:
ret = ptrace_get_thread_area(child, addr,
(struct user_desc __user *) data);
break;
case PTRACE_SET_THREAD_AREA:
ret = ptrace_set_thread_area(child, addr,
(struct user_desc __user *) data);
break;
default:
ret = ptrace_request(child, request, addr, data);
break;
}
out_tsk:
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Handle bogus %cs selector in single-step instruction decoding
The code for LDT segment selectors was not robust in the face of a bogus
selector set in %cs via ptrace before the single-step was done.
Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void ptrace_disable(struct task_struct *child)
{
clear_singlestep(child);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Handle bogus %cs selector in single-step instruction decoding
The code for LDT segment selectors was not robust in the face of a bogus
selector set in %cs via ptrace before the single-step was done.
Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static inline int get_stack_long(struct task_struct *task, int offset)
{
unsigned char *stack;
stack = (unsigned char *)task->thread.esp0 - sizeof(struct pt_regs);
stack += offset;
return (*((int *)stack));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Handle bogus %cs selector in single-step instruction decoding
The code for LDT segment selectors was not robust in the face of a bogus
selector set in %cs via ptrace before the single-step was done.
Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void pwc_rvfree(void * mem, unsigned long size)
{
unsigned long adr;
if (!mem)
return;
adr=(unsigned long) mem;
while ((long) size > 0)
{
ClearPageReserved(vmalloc_to_page((void *)adr));
adr += PAGE_SIZE;
size -= PAGE_SIZE;
}
vfree(mem);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'USB: fix DoS in pwc USB video driver
the pwc driver has a disconnect method that waits for user space to
close the device. This opens up an opportunity for a DoS attack,
blocking the USB subsystem and making khubd's task busy wait in
kernel space. This patch shifts freeing resources to close if an opened
device is disconnected.
Signed-off-by: Oliver Neukum <oneukum@suse.de>
CC: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int pwc_video_close(struct inode *inode, struct file *file)
{
struct video_device *vdev = file->private_data;
struct pwc_device *pdev;
int i, hint;
PWC_DEBUG_OPEN(">> video_close called(vdev = 0x%p).\n", vdev);
pdev = (struct pwc_device *)vdev->priv;
if (pdev->vopen == 0)
PWC_DEBUG_MODULE("video_close() called on closed device?\n");
/* Dump statistics, but only if a reasonable amount of frames were
processed (to prevent endless log-entries in case of snap-shot
programs)
*/
if (pdev->vframe_count > 20)
PWC_DEBUG_MODULE("Closing video device: %d frames received, dumped %d frames, %d frames with errors.\n", pdev->vframe_count, pdev->vframes_dumped, pdev->vframes_error);
if (DEVICE_USE_CODEC1(pdev->type))
pwc_dec1_exit();
else
pwc_dec23_exit();
pwc_isoc_cleanup(pdev);
pwc_free_buffers(pdev);
lock_kernel();
/* Turn off LEDS and power down camera, but only when not unplugged */
if (!pdev->unplugged) {
/* Turn LEDs off */
if (pwc_set_leds(pdev, 0, 0) < 0)
PWC_DEBUG_MODULE("Failed to set LED on/off time.\n");
if (power_save) {
i = pwc_camera_power(pdev, 0);
if (i < 0)
PWC_ERROR("Failed to power down camera (%d)\n", i);
}
pdev->vopen--;
PWC_DEBUG_OPEN("<< video_close() vopen=%d\n", i);
} else {
pwc_cleanup(pdev);
/* Free memory (don't set pdev to 0 just yet) */
kfree(pdev);
/* search device_hint[] table if we occupy a slot, by any chance */
for (hint = 0; hint < MAX_DEV_HINTS; hint++)
if (device_hint[hint].pdev == pdev)
device_hint[hint].pdev = NULL;
}
unlock_kernel();
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'USB: fix DoS in pwc USB video driver
the pwc driver has a disconnect method that waits for user space to
close the device. This opens up an opportunity for a DoS attack,
blocking the USB subsystem and making khubd's task busy wait in
kernel space. This patch shifts freeing resources to close if an opened
device is disconnected.
Signed-off-by: Oliver Neukum <oneukum@suse.de>
CC: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static ssize_t show_pan_tilt(struct class_device *class_dev, char *buf)
{
struct pwc_device *pdev = cd_to_pwc(class_dev);
return sprintf(buf, "%d %d\n", pdev->pan_angle, pdev->tilt_angle);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'USB: fix DoS in pwc USB video driver
the pwc driver has a disconnect method that waits for user space to
close the device. This opens up an opportunity for a DoS attack,
blocking the USB subsystem and making khubd's task busy wait in
kernel space. This patch shifts freeing resources to close if an opened
device is disconnected.
Signed-off-by: Oliver Neukum <oneukum@suse.de>
CC: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void hash_preload(struct mm_struct *mm, unsigned long ea,
unsigned long access, unsigned long trap)
{
unsigned long vsid;
void *pgdir;
pte_t *ptep;
cpumask_t mask;
unsigned long flags;
int local = 0;
/* We don't want huge pages prefaulted for now
*/
if (unlikely(in_hugepage_area(mm->context, ea)))
return;
DBG_LOW("hash_preload(mm=%p, mm->pgdir=%p, ea=%016lx, access=%lx,"
" trap=%lx\n", mm, mm->pgd, ea, access, trap);
/* Get PTE, VSID, access mask */
pgdir = mm->pgd;
if (pgdir == NULL)
return;
ptep = find_linux_pte(pgdir, ea);
if (!ptep)
return;
vsid = get_vsid(mm->context.id, ea);
/* Hash it in */
local_irq_save(flags);
mask = cpumask_of_cpu(smp_processor_id());
if (cpus_equal(mm->cpu_vm_mask, mask))
local = 1;
#ifndef CONFIG_PPC_64K_PAGES
__hash_page_4K(ea, access, vsid, ptep, trap, local);
#else
if (mmu_ci_restrictions) {
/* If this PTE is non-cacheable, switch to 4k */
if (mm->context.user_psize == MMU_PAGE_64K &&
(pte_val(*ptep) & _PAGE_NO_CACHE))
demote_segment_4k(mm, ea);
}
if (mm->context.user_psize == MMU_PAGE_64K)
__hash_page_64K(ea, access, vsid, ptep, trap, local);
else
__hash_page_4K(ea, access, vsid, ptep, trap, local);
#endif /* CONFIG_PPC_64K_PAGES */
local_irq_restore(flags);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': '[POWERPC] Allow drivers to map individual 4k pages to userspace
Some drivers have resources that they want to be able to map into
userspace that are 4k in size. On a kernel configured with 64k pages
we currently end up mapping the 4k we want plus another 60k of
physical address space, which could contain anything. This can
introduce security problems, for example in the case of an infiniband
adaptor where the other 60k could contain registers that some other
program is using for its communications.
This patch adds a new function, remap_4k_pfn, which drivers can use to
map a single 4k page to userspace regardless of whether the kernel is
using a 4k or a 64k page size. Like remap_pfn_range, it would
typically be called in a driver's mmap function. It only maps a
single 4k page, which on a 64k page kernel appears replicated 16 times
throughout a 64k page. On a 4k page kernel it reduces to a call to
remap_pfn_range.
The way this works on a 64k kernel is that a new bit, _PAGE_4K_PFN,
gets set on the linux PTE. This alters the way that __hash_page_4K
computes the real address to put in the HPTE. The RPN field of the
linux PTE becomes the 4k RPN directly rather than being interpreted as
a 64k RPN. Since the RPN field is 32 bits, this means that physical
addresses being mapped with remap_4k_pfn have to be below 2^44,
i.e. 0x100000000000.
The patch also factors out the code in arch/powerpc/mm/hash_utils_64.c
that deals with demoting a process to use 4k pages into one function
that gets called in the various different places where we need to do
that. There were some discrepancies between exactly what was done in
the various places, such as a call to spu_flush_all_slbs in one case
but not in others.
Signed-off-by: Paul Mackerras <paulus@samba.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static unsigned long __init htab_get_table_size(void)
{
unsigned long mem_size, rnd_mem_size, pteg_count;
/* If hash size isn't already provided by the platform, we try to
* retrieve it from the device-tree. If it's not there neither, we
* calculate it now based on the total RAM size
*/
if (ppc64_pft_size == 0)
of_scan_flat_dt(htab_dt_scan_pftsize, NULL);
if (ppc64_pft_size)
return 1UL << ppc64_pft_size;
/* round mem_size up to next power of 2 */
mem_size = lmb_phys_mem_size();
rnd_mem_size = 1UL << __ilog2(mem_size);
if (rnd_mem_size < mem_size)
rnd_mem_size <<= 1;
/* # pages / 2 */
pteg_count = max(rnd_mem_size >> (12 + 1), 1UL << 11);
return pteg_count << 7;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': '[POWERPC] Allow drivers to map individual 4k pages to userspace
Some drivers have resources that they want to be able to map into
userspace that are 4k in size. On a kernel configured with 64k pages
we currently end up mapping the 4k we want plus another 60k of
physical address space, which could contain anything. This can
introduce security problems, for example in the case of an infiniband
adaptor where the other 60k could contain registers that some other
program is using for its communications.
This patch adds a new function, remap_4k_pfn, which drivers can use to
map a single 4k page to userspace regardless of whether the kernel is
using a 4k or a 64k page size. Like remap_pfn_range, it would
typically be called in a driver's mmap function. It only maps a
single 4k page, which on a 64k page kernel appears replicated 16 times
throughout a 64k page. On a 4k page kernel it reduces to a call to
remap_pfn_range.
The way this works on a 64k kernel is that a new bit, _PAGE_4K_PFN,
gets set on the linux PTE. This alters the way that __hash_page_4K
computes the real address to put in the HPTE. The RPN field of the
linux PTE becomes the 4k RPN directly rather than being interpreted as
a 64k RPN. Since the RPN field is 32 bits, this means that physical
addresses being mapped with remap_4k_pfn have to be below 2^44,
i.e. 0x100000000000.
The patch also factors out the code in arch/powerpc/mm/hash_utils_64.c
that deals with demoting a process to use 4k pages into one function
that gets called in the various different places where we need to do
that. There were some discrepancies between exactly what was done in
the various places, such as a call to spu_flush_all_slbs in one case
but not in others.
Signed-off-by: Paul Mackerras <paulus@samba.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int ieee80211_qos_convert_ac_to_parameters(struct
ieee80211_qos_parameter_info
*param_elm, struct
ieee80211_qos_parameters
*qos_param)
{
int rc = 0;
int i;
struct ieee80211_qos_ac_parameter *ac_params;
u32 txop;
u8 cw_min;
u8 cw_max;
for (i = 0; i < QOS_QUEUE_NUM; i++) {
ac_params = &(param_elm->ac_params_record[i]);
qos_param->aifs[i] = (ac_params->aci_aifsn) & 0x0F;
qos_param->aifs[i] -= (qos_param->aifs[i] < 2) ? 0 : 2;
cw_min = ac_params->ecw_min_max & 0x0F;
qos_param->cw_min[i] = (u16) ((1 << cw_min) - 1);
cw_max = (ac_params->ecw_min_max & 0xF0) >> 4;
qos_param->cw_max[i] = (u16) ((1 << cw_max) - 1);
qos_param->flag[i] =
(ac_params->aci_aifsn & 0x10) ? 0x01 : 0x00;
txop = le16_to_cpu(ac_params->tx_op_limit) * 32;
qos_param->tx_op_limit[i] = (u16) txop;
}
return rc;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': '[IEEE80211]: avoid integer underflow for runt rx frames
Reported by Chris Evans <scarybeasts@gmail.com>:
> The summary is that an evil 80211 frame can crash out a victim's
> machine. It only applies to drivers using the 80211 wireless code, and
> only then to certain drivers (and even then depends on a card's
> firmware not dropping a dubious packet). I must confess I'm not
> keeping track of Linux wireless support, and the different protocol
> stacks etc.
>
> Details are as follows:
>
> ieee80211_rx() does not explicitly check that "skb->len >= hdrlen".
> There are other skb->len checks, but not enough to prevent a subtle
> off-by-two error if the frame has the IEEE80211_STYPE_QOS_DATA flag
> set.
>
> This leads to integer underflow and crash here:
>
> if (frag != 0)
> flen -= hdrlen;
>
> (flen is subsequently used as a memcpy length parameter).
How about this?
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: ieee80211_rx_frame_decrypt(struct ieee80211_device *ieee, struct sk_buff *skb,
struct ieee80211_crypt_data *crypt)
{
struct ieee80211_hdr_3addr *hdr;
int res, hdrlen;
if (crypt == NULL || crypt->ops->decrypt_mpdu == NULL)
return 0;
hdr = (struct ieee80211_hdr_3addr *)skb->data;
hdrlen = ieee80211_get_hdrlen(le16_to_cpu(hdr->frame_ctl));
atomic_inc(&crypt->refcnt);
res = crypt->ops->decrypt_mpdu(skb, hdrlen, crypt->priv);
atomic_dec(&crypt->refcnt);
if (res < 0) {
IEEE80211_DEBUG_DROP("decryption failed (SA=" MAC_FMT
") res=%d\n", MAC_ARG(hdr->addr2), res);
if (res == -2)
IEEE80211_DEBUG_DROP("Decryption failed ICV "
"mismatch (key %d)\n",
skb->data[hdrlen + 3] >> 6);
ieee->ieee_stats.rx_discards_undecryptable++;
return -1;
}
return res;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': '[IEEE80211]: avoid integer underflow for runt rx frames
Reported by Chris Evans <scarybeasts@gmail.com>:
> The summary is that an evil 80211 frame can crash out a victim's
> machine. It only applies to drivers using the 80211 wireless code, and
> only then to certain drivers (and even then depends on a card's
> firmware not dropping a dubious packet). I must confess I'm not
> keeping track of Linux wireless support, and the different protocol
> stacks etc.
>
> Details are as follows:
>
> ieee80211_rx() does not explicitly check that "skb->len >= hdrlen".
> There are other skb->len checks, but not enough to prevent a subtle
> off-by-two error if the frame has the IEEE80211_STYPE_QOS_DATA flag
> set.
>
> This leads to integer underflow and crash here:
>
> if (frag != 0)
> flen -= hdrlen;
>
> (flen is subsequently used as a memcpy length parameter).
How about this?
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb,
struct ieee80211_rx_stats *rx_stats)
{
struct net_device *dev = ieee->dev;
struct ieee80211_hdr_4addr *hdr;
size_t hdrlen;
u16 fc, type, stype, sc;
struct net_device_stats *stats;
unsigned int frag;
u8 *payload;
u16 ethertype;
#ifdef NOT_YET
struct net_device *wds = NULL;
struct sk_buff *skb2 = NULL;
struct net_device *wds = NULL;
int frame_authorized = 0;
int from_assoc_ap = 0;
void *sta = NULL;
#endif
u8 dst[ETH_ALEN];
u8 src[ETH_ALEN];
struct ieee80211_crypt_data *crypt = NULL;
int keyidx = 0;
int can_be_decrypted = 0;
hdr = (struct ieee80211_hdr_4addr *)skb->data;
stats = &ieee->stats;
if (skb->len < 10) {
printk(KERN_INFO "%s: SKB length < 10\n", dev->name);
goto rx_dropped;
}
fc = le16_to_cpu(hdr->frame_ctl);
type = WLAN_FC_GET_TYPE(fc);
stype = WLAN_FC_GET_STYPE(fc);
sc = le16_to_cpu(hdr->seq_ctl);
frag = WLAN_GET_SEQ_FRAG(sc);
hdrlen = ieee80211_get_hdrlen(fc);
if (skb->len < hdrlen) {
printk(KERN_INFO "%s: invalid SKB length %d\n",
dev->name, skb->len);
goto rx_dropped;
}
/* Put this code here so that we avoid duplicating it in all
* Rx paths. - Jean II */
#ifdef CONFIG_WIRELESS_EXT
#ifdef IW_WIRELESS_SPY /* defined in iw_handler.h */
/* If spy monitoring on */
if (ieee->spy_data.spy_number > 0) {
struct iw_quality wstats;
wstats.updated = 0;
if (rx_stats->mask & IEEE80211_STATMASK_RSSI) {
wstats.level = rx_stats->rssi;
wstats.updated |= IW_QUAL_LEVEL_UPDATED;
} else
wstats.updated |= IW_QUAL_LEVEL_INVALID;
if (rx_stats->mask & IEEE80211_STATMASK_NOISE) {
wstats.noise = rx_stats->noise;
wstats.updated |= IW_QUAL_NOISE_UPDATED;
} else
wstats.updated |= IW_QUAL_NOISE_INVALID;
if (rx_stats->mask & IEEE80211_STATMASK_SIGNAL) {
wstats.qual = rx_stats->signal;
wstats.updated |= IW_QUAL_QUAL_UPDATED;
} else
wstats.updated |= IW_QUAL_QUAL_INVALID;
/* Update spy records */
wireless_spy_update(ieee->dev, hdr->addr2, &wstats);
}
#endif /* IW_WIRELESS_SPY */
#endif /* CONFIG_WIRELESS_EXT */
#ifdef NOT_YET
hostap_update_rx_stats(local->ap, hdr, rx_stats);
#endif
if (ieee->iw_mode == IW_MODE_MONITOR) {
stats->rx_packets++;
stats->rx_bytes += skb->len;
ieee80211_monitor_rx(ieee, skb, rx_stats);
return 1;
}
can_be_decrypted = (is_multicast_ether_addr(hdr->addr1) ||
is_broadcast_ether_addr(hdr->addr2)) ?
ieee->host_mc_decrypt : ieee->host_decrypt;
if (can_be_decrypted) {
if (skb->len >= hdrlen + 3) {
/* Top two-bits of byte 3 are the key index */
keyidx = skb->data[hdrlen + 3] >> 6;
}
/* ieee->crypt[] is WEP_KEY (4) in length. Given that keyidx
* is only allowed 2-bits of storage, no value of keyidx can
* be provided via above code that would result in keyidx
* being out of range */
crypt = ieee->crypt[keyidx];
#ifdef NOT_YET
sta = NULL;
/* Use station specific key to override default keys if the
* receiver address is a unicast address ("individual RA"). If
* bcrx_sta_key parameter is set, station specific key is used
* even with broad/multicast targets (this is against IEEE
* 802.11, but makes it easier to use different keys with
* stations that do not support WEP key mapping). */
if (!(hdr->addr1[0] & 0x01) || local->bcrx_sta_key)
(void)hostap_handle_sta_crypto(local, hdr, &crypt,
&sta);
#endif
/* allow NULL decrypt to indicate an station specific override
* for default encryption */
if (crypt && (crypt->ops == NULL ||
crypt->ops->decrypt_mpdu == NULL))
crypt = NULL;
if (!crypt && (fc & IEEE80211_FCTL_PROTECTED)) {
/* This seems to be triggered by some (multicast?)
* frames from other than current BSS, so just drop the
* frames silently instead of filling system log with
* these reports. */
IEEE80211_DEBUG_DROP("Decryption failed (not set)"
" (SA=" MAC_FMT ")\n",
MAC_ARG(hdr->addr2));
ieee->ieee_stats.rx_discards_undecryptable++;
goto rx_dropped;
}
}
#ifdef NOT_YET
if (type != WLAN_FC_TYPE_DATA) {
if (type == WLAN_FC_TYPE_MGMT && stype == WLAN_FC_STYPE_AUTH &&
fc & IEEE80211_FCTL_PROTECTED && ieee->host_decrypt &&
(keyidx = hostap_rx_frame_decrypt(ieee, skb, crypt)) < 0) {
printk(KERN_DEBUG "%s: failed to decrypt mgmt::auth "
"from " MAC_FMT "\n", dev->name,
MAC_ARG(hdr->addr2));
/* TODO: could inform hostapd about this so that it
* could send auth failure report */
goto rx_dropped;
}
if (ieee80211_rx_frame_mgmt(ieee, skb, rx_stats, type, stype))
goto rx_dropped;
else
goto rx_exit;
}
#endif
/* drop duplicate 802.11 retransmissions (IEEE 802.11 Chap. 9.29) */
if (sc == ieee->prev_seq_ctl)
goto rx_dropped;
else
ieee->prev_seq_ctl = sc;
/* Data frame - extract src/dst addresses */
if (skb->len < IEEE80211_3ADDR_LEN)
goto rx_dropped;
switch (fc & (IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS)) {
case IEEE80211_FCTL_FROMDS:
memcpy(dst, hdr->addr1, ETH_ALEN);
memcpy(src, hdr->addr3, ETH_ALEN);
break;
case IEEE80211_FCTL_TODS:
memcpy(dst, hdr->addr3, ETH_ALEN);
memcpy(src, hdr->addr2, ETH_ALEN);
break;
case IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS:
if (skb->len < IEEE80211_4ADDR_LEN)
goto rx_dropped;
memcpy(dst, hdr->addr3, ETH_ALEN);
memcpy(src, hdr->addr4, ETH_ALEN);
break;
case 0:
memcpy(dst, hdr->addr1, ETH_ALEN);
memcpy(src, hdr->addr2, ETH_ALEN);
break;
}
#ifdef NOT_YET
if (hostap_rx_frame_wds(ieee, hdr, fc, &wds))
goto rx_dropped;
if (wds) {
skb->dev = dev = wds;
stats = hostap_get_stats(dev);
}
if (ieee->iw_mode == IW_MODE_MASTER && !wds &&
(fc & (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) ==
IEEE80211_FCTL_FROMDS && ieee->stadev
&& !compare_ether_addr(hdr->addr2, ieee->assoc_ap_addr)) {
/* Frame from BSSID of the AP for which we are a client */
skb->dev = dev = ieee->stadev;
stats = hostap_get_stats(dev);
from_assoc_ap = 1;
}
#endif
dev->last_rx = jiffies;
#ifdef NOT_YET
if ((ieee->iw_mode == IW_MODE_MASTER ||
ieee->iw_mode == IW_MODE_REPEAT) && !from_assoc_ap) {
switch (hostap_handle_sta_rx(ieee, dev, skb, rx_stats,
wds != NULL)) {
case AP_RX_CONTINUE_NOT_AUTHORIZED:
frame_authorized = 0;
break;
case AP_RX_CONTINUE:
frame_authorized = 1;
break;
case AP_RX_DROP:
goto rx_dropped;
case AP_RX_EXIT:
goto rx_exit;
}
}
#endif
/* Nullfunc frames may have PS-bit set, so they must be passed to
* hostap_handle_sta_rx() before being dropped here. */
stype &= ~IEEE80211_STYPE_QOS_DATA;
if (stype != IEEE80211_STYPE_DATA &&
stype != IEEE80211_STYPE_DATA_CFACK &&
stype != IEEE80211_STYPE_DATA_CFPOLL &&
stype != IEEE80211_STYPE_DATA_CFACKPOLL) {
if (stype != IEEE80211_STYPE_NULLFUNC)
IEEE80211_DEBUG_DROP("RX: dropped data frame "
"with no data (type=0x%02x, "
"subtype=0x%02x, len=%d)\n",
type, stype, skb->len);
goto rx_dropped;
}
/* skb: hdr + (possibly fragmented, possibly encrypted) payload */
if ((fc & IEEE80211_FCTL_PROTECTED) && can_be_decrypted &&
(keyidx = ieee80211_rx_frame_decrypt(ieee, skb, crypt)) < 0)
goto rx_dropped;
hdr = (struct ieee80211_hdr_4addr *)skb->data;
/* skb: hdr + (possibly fragmented) plaintext payload */
// PR: FIXME: hostap has additional conditions in the "if" below:
// ieee->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) &&
if ((frag != 0) || (fc & IEEE80211_FCTL_MOREFRAGS)) {
int flen;
struct sk_buff *frag_skb = ieee80211_frag_cache_get(ieee, hdr);
IEEE80211_DEBUG_FRAG("Rx Fragment received (%u)\n", frag);
if (!frag_skb) {
IEEE80211_DEBUG(IEEE80211_DL_RX | IEEE80211_DL_FRAG,
"Rx cannot get skb from fragment "
"cache (morefrag=%d seq=%u frag=%u)\n",
(fc & IEEE80211_FCTL_MOREFRAGS) != 0,
WLAN_GET_SEQ_SEQ(sc), frag);
goto rx_dropped;
}
flen = skb->len;
if (frag != 0)
flen -= hdrlen;
if (frag_skb->tail + flen > frag_skb->end) {
printk(KERN_WARNING "%s: host decrypted and "
"reassembled frame did not fit skb\n",
dev->name);
ieee80211_frag_cache_invalidate(ieee, hdr);
goto rx_dropped;
}
if (frag == 0) {
/* copy first fragment (including full headers) into
* beginning of the fragment cache skb */
skb_copy_from_linear_data(skb, skb_put(frag_skb, flen), flen);
} else {
/* append frame payload to the end of the fragment
* cache skb */
skb_copy_from_linear_data_offset(skb, hdrlen,
skb_put(frag_skb, flen), flen);
}
dev_kfree_skb_any(skb);
skb = NULL;
if (fc & IEEE80211_FCTL_MOREFRAGS) {
/* more fragments expected - leave the skb in fragment
* cache for now; it will be delivered to upper layers
* after all fragments have been received */
goto rx_exit;
}
/* this was the last fragment and the frame will be
* delivered, so remove skb from fragment cache */
skb = frag_skb;
hdr = (struct ieee80211_hdr_4addr *)skb->data;
ieee80211_frag_cache_invalidate(ieee, hdr);
}
/* skb: hdr + (possible reassembled) full MSDU payload; possibly still
* encrypted/authenticated */
if ((fc & IEEE80211_FCTL_PROTECTED) && can_be_decrypted &&
ieee80211_rx_frame_decrypt_msdu(ieee, skb, keyidx, crypt))
goto rx_dropped;
hdr = (struct ieee80211_hdr_4addr *)skb->data;
if (crypt && !(fc & IEEE80211_FCTL_PROTECTED) && !ieee->open_wep) {
if ( /*ieee->ieee802_1x && */
ieee80211_is_eapol_frame(ieee, skb)) {
/* pass unencrypted EAPOL frames even if encryption is
* configured */
} else {
IEEE80211_DEBUG_DROP("encryption configured, but RX "
"frame not encrypted (SA=" MAC_FMT
")\n", MAC_ARG(hdr->addr2));
goto rx_dropped;
}
}
if (crypt && !(fc & IEEE80211_FCTL_PROTECTED) && !ieee->open_wep &&
!ieee80211_is_eapol_frame(ieee, skb)) {
IEEE80211_DEBUG_DROP("dropped unencrypted RX data "
"frame from " MAC_FMT
" (drop_unencrypted=1)\n",
MAC_ARG(hdr->addr2));
goto rx_dropped;
}
/* If the frame was decrypted in hardware, we may need to strip off
* any security data (IV, ICV, etc) that was left behind */
if (!can_be_decrypted && (fc & IEEE80211_FCTL_PROTECTED) &&
ieee->host_strip_iv_icv) {
int trimlen = 0;
/* Top two-bits of byte 3 are the key index */
if (skb->len >= hdrlen + 3)
keyidx = skb->data[hdrlen + 3] >> 6;
/* To strip off any security data which appears before the
* payload, we simply increase hdrlen (as the header gets
* chopped off immediately below). For the security data which
* appears after the payload, we use skb_trim. */
switch (ieee->sec.encode_alg[keyidx]) {
case SEC_ALG_WEP:
/* 4 byte IV */
hdrlen += 4;
/* 4 byte ICV */
trimlen = 4;
break;
case SEC_ALG_TKIP:
/* 4 byte IV, 4 byte ExtIV */
hdrlen += 8;
/* 8 byte MIC, 4 byte ICV */
trimlen = 12;
break;
case SEC_ALG_CCMP:
/* 8 byte CCMP header */
hdrlen += 8;
/* 8 byte MIC */
trimlen = 8;
break;
}
if (skb->len < trimlen)
goto rx_dropped;
__skb_trim(skb, skb->len - trimlen);
if (skb->len < hdrlen)
goto rx_dropped;
}
/* skb: hdr + (possible reassembled) full plaintext payload */
payload = skb->data + hdrlen;
ethertype = (payload[6] << 8) | payload[7];
#ifdef NOT_YET
/* If IEEE 802.1X is used, check whether the port is authorized to send
* the received frame. */
if (ieee->ieee802_1x && ieee->iw_mode == IW_MODE_MASTER) {
if (ethertype == ETH_P_PAE) {
printk(KERN_DEBUG "%s: RX: IEEE 802.1X frame\n",
dev->name);
if (ieee->hostapd && ieee->apdev) {
/* Send IEEE 802.1X frames to the user
* space daemon for processing */
prism2_rx_80211(ieee->apdev, skb, rx_stats,
PRISM2_RX_MGMT);
ieee->apdevstats.rx_packets++;
ieee->apdevstats.rx_bytes += skb->len;
goto rx_exit;
}
} else if (!frame_authorized) {
printk(KERN_DEBUG "%s: dropped frame from "
"unauthorized port (IEEE 802.1X): "
"ethertype=0x%04x\n", dev->name, ethertype);
goto rx_dropped;
}
}
#endif
/* convert hdr + possible LLC headers into Ethernet header */
if (skb->len - hdrlen >= 8 &&
((memcmp(payload, rfc1042_header, SNAP_SIZE) == 0 &&
ethertype != ETH_P_AARP && ethertype != ETH_P_IPX) ||
memcmp(payload, bridge_tunnel_header, SNAP_SIZE) == 0)) {
/* remove RFC1042 or Bridge-Tunnel encapsulation and
* replace EtherType */
skb_pull(skb, hdrlen + SNAP_SIZE);
memcpy(skb_push(skb, ETH_ALEN), src, ETH_ALEN);
memcpy(skb_push(skb, ETH_ALEN), dst, ETH_ALEN);
} else {
u16 len;
/* Leave Ethernet header part of hdr and full payload */
skb_pull(skb, hdrlen);
len = htons(skb->len);
memcpy(skb_push(skb, 2), &len, 2);
memcpy(skb_push(skb, ETH_ALEN), src, ETH_ALEN);
memcpy(skb_push(skb, ETH_ALEN), dst, ETH_ALEN);
}
#ifdef NOT_YET
if (wds && ((fc & (IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) ==
IEEE80211_FCTL_TODS) && skb->len >= ETH_HLEN + ETH_ALEN) {
/* Non-standard frame: get addr4 from its bogus location after
* the payload */
skb_copy_to_linear_data_offset(skb, ETH_ALEN,
skb->data + skb->len - ETH_ALEN,
ETH_ALEN);
skb_trim(skb, skb->len - ETH_ALEN);
}
#endif
stats->rx_packets++;
stats->rx_bytes += skb->len;
#ifdef NOT_YET
if (ieee->iw_mode == IW_MODE_MASTER && !wds && ieee->ap->bridge_packets) {
if (dst[0] & 0x01) {
/* copy multicast frame both to the higher layers and
* to the wireless media */
ieee->ap->bridged_multicast++;
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 == NULL)
printk(KERN_DEBUG "%s: skb_clone failed for "
"multicast frame\n", dev->name);
} else if (hostap_is_sta_assoc(ieee->ap, dst)) {
/* send frame directly to the associated STA using
* wireless media and not passing to higher layers */
ieee->ap->bridged_unicast++;
skb2 = skb;
skb = NULL;
}
}
if (skb2 != NULL) {
/* send to wireless media */
skb2->dev = dev;
skb2->protocol = __constant_htons(ETH_P_802_3);
skb_reset_mac_header(skb2);
skb_reset_network_header(skb2);
/* skb2->network_header += ETH_HLEN; */
dev_queue_xmit(skb2);
}
#endif
if (skb) {
skb->protocol = eth_type_trans(skb, dev);
memset(skb->cb, 0, sizeof(skb->cb));
skb->ip_summed = CHECKSUM_NONE; /* 802.11 crc not sufficient */
if (netif_rx(skb) == NET_RX_DROP) {
/* netif_rx always succeeds, but it might drop
* the packet. If it drops the packet, we log that
* in our stats. */
IEEE80211_DEBUG_DROP
("RX: netif_rx dropped the packet\n");
stats->rx_dropped++;
}
}
rx_exit:
#ifdef NOT_YET
if (sta)
hostap_handle_sta_release(sta);
#endif
return 1;
rx_dropped:
stats->rx_dropped++;
/* Returning 0 indicates to caller that we have not handled the SKB--
* so it is still allocated and can be used again by underlying
* hardware as a DMA target */
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': '[IEEE80211]: avoid integer underflow for runt rx frames
Reported by Chris Evans <scarybeasts@gmail.com>:
> The summary is that an evil 80211 frame can crash out a victim's
> machine. It only applies to drivers using the 80211 wireless code, and
> only then to certain drivers (and even then depends on a card's
> firmware not dropping a dubious packet). I must confess I'm not
> keeping track of Linux wireless support, and the different protocol
> stacks etc.
>
> Details are as follows:
>
> ieee80211_rx() does not explicitly check that "skb->len >= hdrlen".
> There are other skb->len checks, but not enough to prevent a subtle
> off-by-two error if the frame has the IEEE80211_STYPE_QOS_DATA flag
> set.
>
> This leads to integer underflow and crash here:
>
> if (frag != 0)
> flen -= hdrlen;
>
> (flen is subsequently used as a memcpy length parameter).
How about this?
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static __inline__ void isdn_net_device_stop_queue(isdn_net_local *lp)
{
if (lp->master)
netif_stop_queue(lp->master);
else
netif_stop_queue(lp->netdev->dev);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'isdn: avoid copying overly-long strings
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9416
Signed-off-by: Karsten Keil <kkeil@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_net_addphone(isdn_net_ioctl_phone * phone)
{
isdn_net_dev *p = isdn_net_findif(phone->name);
isdn_net_phone *n;
if (p) {
if (!(n = kmalloc(sizeof(isdn_net_phone), GFP_KERNEL)))
return -ENOMEM;
strlcpy(n->num, phone->phone, sizeof(n->num));
n->next = p->local->phone[phone->outgoing & 1];
p->local->phone[phone->outgoing & 1] = n;
return 0;
}
return -ENODEV;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'isdn: avoid copying overly-long strings
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9416
Signed-off-by: Karsten Keil <kkeil@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_net_force_dial(char *name)
{
isdn_net_dev *p = isdn_net_findif(name);
if (!p)
return -ENODEV;
return (isdn_net_force_dial_lp(p->local));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'isdn: avoid copying overly-long strings
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9416
Signed-off-by: Karsten Keil <kkeil@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_net_getphones(isdn_net_ioctl_phone * phone, char __user *phones)
{
isdn_net_dev *p = isdn_net_findif(phone->name);
int inout = phone->outgoing & 1;
int more = 0;
int count = 0;
isdn_net_phone *n;
if (!p)
return -ENODEV;
inout &= 1;
for (n = p->local->phone[inout]; n; n = n->next) {
if (more) {
put_user(' ', phones++);
count++;
}
if (copy_to_user(phones, n->num, strlen(n->num) + 1)) {
return -EFAULT;
}
phones += strlen(n->num);
count += strlen(n->num);
more = 1;
}
put_user(0, phones);
count++;
return count;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'isdn: avoid copying overly-long strings
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9416
Signed-off-by: Karsten Keil <kkeil@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_net_swapbind(int drvidx)
{
isdn_net_dev *p;
#ifdef ISDN_DEBUG_NET_ICALL
printk(KERN_DEBUG "n_fi: swapping ch of %d\n", drvidx);
#endif
p = dev->netdev;
while (p) {
if (p->local->pre_device == drvidx)
switch (p->local->pre_channel) {
case 0:
p->local->pre_channel = 1;
break;
case 1:
p->local->pre_channel = 0;
break;
}
p = (isdn_net_dev *) p->next;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'isdn: avoid copying overly-long strings
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9416
Signed-off-by: Karsten Keil <kkeil@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_net_ciscohdlck_alloc_skb(isdn_net_local *lp, int len)
{
unsigned short hl = dev->drv[lp->isdn_device]->interface->hl_hdrlen;
struct sk_buff *skb;
skb = alloc_skb(hl + len, GFP_ATOMIC);
if (skb)
skb_reserve(skb, hl);
else
printk("isdn out of mem at %s:%d!\n", __FILE__, __LINE__);
return skb;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'isdn: avoid copying overly-long strings
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9416
Signed-off-by: Karsten Keil <kkeil@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int esp_init_aead(struct xfrm_state *x)
{
struct esp_data *esp = x->data;
struct crypto_aead *aead;
int err;
aead = crypto_alloc_aead(x->aead->alg_name, 0, 0);
err = PTR_ERR(aead);
if (IS_ERR(aead))
goto error;
esp->aead = aead;
err = crypto_aead_setkey(aead, x->aead->alg_key,
(x->aead->alg_key_len + 7) / 8);
if (err)
goto error;
err = crypto_aead_setauthsize(aead, x->aead->alg_icv_len / 8);
if (err)
goto error;
error:
return err;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-16'], 'message': '[ESP]: Ensure IV is in linear part of the skb to avoid BUG() due to OOB access
ESP does not account for the IV size when calling pskb_may_pull() to
ensure everything it accesses directly is within the linear part of a
potential fragment. This results in a BUG() being triggered when the
both the IPv4 and IPv6 ESP stack is fed with an skb where the first
fragment ends between the end of the esp header and the end of the IV.
This bug was found by Dirk Nehring <dnehring@gmx.net> .
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
{
struct esp_data *esp = x->data;
u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
u32 align = max_t(u32, blksize, esp->padlen);
u32 rem;
mtu -= x->props.header_len + crypto_aead_authsize(esp->aead);
rem = mtu & (align - 1);
mtu &= ~(align - 1);
if (x->props.mode != XFRM_MODE_TUNNEL) {
u32 padsize = ((blksize - 1) & 7) + 1;
mtu -= blksize - padsize;
mtu += min_t(u32, blksize - padsize, rem);
}
return mtu - 2;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-16'], 'message': '[ESP]: Ensure IV is in linear part of the skb to avoid BUG() due to OOB access
ESP does not account for the IV size when calling pskb_may_pull() to
ensure everything it accesses directly is within the linear part of a
potential fragment. This results in a BUG() being triggered when the
both the IPv4 and IPv6 ESP stack is fed with an skb where the first
fragment ends between the end of the esp header and the end of the IV.
This bug was found by Dirk Nehring <dnehring@gmx.net> .
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void __exit esp4_fini(void)
{
if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0)
printk(KERN_INFO "ip esp close: can't remove protocol\n");
if (xfrm_unregister_type(&esp_type, AF_INET) < 0)
printk(KERN_INFO "ip esp close: can't remove xfrm type\n");
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-16'], 'message': '[ESP]: Ensure IV is in linear part of the skb to avoid BUG() due to OOB access
ESP does not account for the IV size when calling pskb_may_pull() to
ensure everything it accesses directly is within the linear part of a
potential fragment. This results in a BUG() being triggered when the
both the IPv4 and IPv6 ESP stack is fed with an skb where the first
fragment ends between the end of the esp header and the end of the IV.
This bug was found by Dirk Nehring <dnehring@gmx.net> .
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_readbchan(int di, int channel, u_char * buf, u_char * fp, int len, wait_queue_head_t *sleep)
{
int count;
int count_pull;
int count_put;
int dflag;
struct sk_buff *skb;
u_char *cp;
if (!dev->drv[di])
return 0;
if (skb_queue_empty(&dev->drv[di]->rpqueue[channel])) {
if (sleep)
interruptible_sleep_on(sleep);
else
return 0;
}
if (len > dev->drv[di]->rcvcount[channel])
len = dev->drv[di]->rcvcount[channel];
cp = buf;
count = 0;
while (len) {
if (!(skb = skb_peek(&dev->drv[di]->rpqueue[channel])))
break;
#ifdef CONFIG_ISDN_AUDIO
if (ISDN_AUDIO_SKB_LOCK(skb))
break;
ISDN_AUDIO_SKB_LOCK(skb) = 1;
if ((ISDN_AUDIO_SKB_DLECOUNT(skb)) || (dev->drv[di]->DLEflag & (1 << channel))) {
char *p = skb->data;
unsigned long DLEmask = (1 << channel);
dflag = 0;
count_pull = count_put = 0;
while ((count_pull < skb->len) && (len > 0)) {
len--;
if (dev->drv[di]->DLEflag & DLEmask) {
*cp++ = DLE;
dev->drv[di]->DLEflag &= ~DLEmask;
} else {
*cp++ = *p;
if (*p == DLE) {
dev->drv[di]->DLEflag |= DLEmask;
(ISDN_AUDIO_SKB_DLECOUNT(skb))--;
}
p++;
count_pull++;
}
count_put++;
}
if (count_pull >= skb->len)
dflag = 1;
} else {
#endif
/* No DLE's in buff, so simply copy it */
dflag = 1;
if ((count_pull = skb->len) > len) {
count_pull = len;
dflag = 0;
}
count_put = count_pull;
skb_copy_from_linear_data(skb, cp, count_put);
cp += count_put;
len -= count_put;
#ifdef CONFIG_ISDN_AUDIO
}
#endif
count += count_put;
if (fp) {
memset(fp, 0, count_put);
fp += count_put;
}
if (dflag) {
/* We got all the data in this buff.
* Now we can dequeue it.
*/
if (fp)
*(fp - 1) = 0xff;
#ifdef CONFIG_ISDN_AUDIO
ISDN_AUDIO_SKB_LOCK(skb) = 0;
#endif
skb = skb_dequeue(&dev->drv[di]->rpqueue[channel]);
dev_kfree_skb(skb);
} else {
/* Not yet emptied this buff, so it
* must stay in the queue, for further calls
* but we pull off the data we got until now.
*/
skb_pull(skb, count_pull);
#ifdef CONFIG_ISDN_AUDIO
ISDN_AUDIO_SKB_LOCK(skb) = 0;
#endif
}
dev->drv[di]->rcvcount[channel] -= count_put;
}
return count;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'I4L: fix isdn_ioctl memory overrun vulnerability
Fix possible memory overrun issue in the isdn ioctl code.
Found by ADLAB <adlab@venustech.com.cn>
Signed-off-by: Karsten Keil <kkeil@suse.de>
Cc: ADLAB <adlab@venustech.com.cn>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_dc2minor(int di, int ch)
{
int i;
for (i = 0; i < ISDN_MAX_CHANNELS; i++)
if (dev->chanmap[i] == ch && dev->drvmap[i] == di)
return i;
return -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'I4L: fix isdn_ioctl memory overrun vulnerability
Fix possible memory overrun issue in the isdn ioctl code.
Found by ADLAB <adlab@venustech.com.cn>
Signed-off-by: Karsten Keil <kkeil@suse.de>
Cc: ADLAB <adlab@venustech.com.cn>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_timer_ctrl(int tf, int onoff)
{
unsigned long flags;
int old_tflags;
spin_lock_irqsave(&dev->timerlock, flags);
if ((tf & ISDN_TIMER_SLOW) && (!(dev->tflags & ISDN_TIMER_SLOW))) {
/* If the slow-timer wasn't activated until now */
isdn_timer_cnt1 = 0;
isdn_timer_cnt2 = 0;
}
old_tflags = dev->tflags;
if (onoff)
dev->tflags |= tf;
else
dev->tflags &= ~tf;
if (dev->tflags && !old_tflags)
mod_timer(&dev->timer, jiffies+ISDN_TIMER_RES);
spin_unlock_irqrestore(&dev->timerlock, flags);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'I4L: fix isdn_ioctl memory overrun vulnerability
Fix possible memory overrun issue in the isdn ioctl code.
Found by ADLAB <adlab@venustech.com.cn>
Signed-off-by: Karsten Keil <kkeil@suse.de>
Cc: ADLAB <adlab@venustech.com.cn>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: set_global_features(void)
{
int drvidx;
dev->global_features = 0;
for (drvidx = 0; drvidx < ISDN_MAX_DRIVERS; drvidx++) {
if (!dev->drv[drvidx])
continue;
if (dev->drv[drvidx]->interface)
dev->global_features |= dev->drv[drvidx]->interface->features;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'I4L: fix isdn_ioctl memory overrun vulnerability
Fix possible memory overrun issue in the isdn ioctl code.
Found by ADLAB <adlab@venustech.com.cn>
Signed-off-by: Karsten Keil <kkeil@suse.de>
Cc: ADLAB <adlab@venustech.com.cn>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: isdn_free_channel(int di, int ch, int usage)
{
int i;
if ((di < 0) || (ch < 0)) {
printk(KERN_WARNING "%s: called with invalid drv(%d) or channel(%d)\n",
__FUNCTION__, di, ch);
return;
}
for (i = 0; i < ISDN_MAX_CHANNELS; i++)
if (((!usage) || ((dev->usage[i] & ISDN_USAGE_MASK) == usage)) &&
(dev->drvmap[i] == di) &&
(dev->chanmap[i] == ch)) {
dev->usage[i] &= (ISDN_USAGE_NONE | ISDN_USAGE_EXCLUSIVE);
strcpy(dev->num[i], "???");
dev->ibytes[i] = 0;
dev->obytes[i] = 0;
// 20.10.99 JIM, try to reinitialize v110 !
dev->v110emu[i] = 0;
atomic_set(&(dev->v110use[i]), 0);
isdn_v110_close(dev->v110[i]);
dev->v110[i] = NULL;
// 20.10.99 JIM, try to reinitialize v110 !
isdn_info_update();
if (dev->drv[di])
skb_queue_purge(&dev->drv[di]->rpqueue[ch]);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'I4L: fix isdn_ioctl memory overrun vulnerability
Fix possible memory overrun issue in the isdn ioctl code.
Found by ADLAB <adlab@venustech.com.cn>
Signed-off-by: Karsten Keil <kkeil@suse.de>
Cc: ADLAB <adlab@venustech.com.cn>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static inline int shmem_acct_block(unsigned long flags)
{
return (flags & VM_ACCOUNT)?
0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: int shmem_unuse(swp_entry_t entry, struct page *page)
{
struct list_head *p, *next;
struct shmem_inode_info *info;
int found = 0;
spin_lock(&shmem_swaplist_lock);
list_for_each_safe(p, next, &shmem_swaplist) {
info = list_entry(p, struct shmem_inode_info, swaplist);
if (!info->swapped)
list_del_init(&info->swaplist);
else if (shmem_unuse_inode(info, entry, page)) {
/* move head to start search for next from here */
list_move_tail(&shmem_swaplist, &info->swaplist);
found = 1;
break;
}
}
spin_unlock(&shmem_swaplist_lock);
return found;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
{
if (!IS_ERR(nd_get_link(nd))) {
struct page *page = cookie;
kunmap(page);
mark_page_accessed(page);
page_cache_release(page);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int shmem_map_and_free_swp(struct page *subdir, int offset,
int limit, struct page ***dir, spinlock_t *punch_lock)
{
swp_entry_t *ptr;
int freed = 0;
ptr = shmem_swp_map(subdir);
for (; offset < limit; offset += LATENCY_LIMIT) {
int size = limit - offset;
if (size > LATENCY_LIMIT)
size = LATENCY_LIMIT;
freed += shmem_free_swp(ptr+offset, ptr+offset+size,
punch_lock);
if (need_resched()) {
shmem_swp_unmap(ptr);
if (*dir) {
shmem_dir_unmap(*dir);
*dir = NULL;
}
cond_resched();
ptr = shmem_swp_map(subdir);
}
}
shmem_swp_unmap(ptr);
return freed;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int shmem_match(struct inode *ino, void *vfh)
{
__u32 *fh = vfh;
__u64 inum = fh[2];
inum = (inum << 32) | fh[1];
return ino->i_ino == inum && fh[0] == ino->i_generation;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static inline void shmem_swp_unmap(swp_entry_t *entry)
{
kunmap_atomic(entry, KM_USER1);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void init_once(struct kmem_cache *cachep, void *foo)
{
struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
inode_init_once(&p->vfs_inode);
#ifdef CONFIG_TMPFS_POSIX_ACL
p->i_acl = NULL;
p->i_default_acl = NULL;
#endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static inline int shmem_parse_mpol(char *value, int *policy,
nodemask_t *policy_nodes)
{
return 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: shm_access(ClientPtr client, SHMPERM_TYPE *perm, int readonly)
{
int uid, gid;
mode_t mask;
int uidset = 0, gidset = 0;
LocalClientCredRec *lcc;
if (GetLocalClientCreds(client, &lcc) != -1) {
if (lcc->fieldsSet & LCC_UID_SET) {
uid = lcc->euid;
uidset = 1;
}
if (lcc->fieldsSet & LCC_GID_SET) {
gid = lcc->egid;
gidset = 1;
}
#if defined(HAVE_GETZONEID) && defined(SHMPERM_ZONEID)
if ( ((lcc->fieldsSet & LCC_ZID_SET) == 0) || (lcc->zoneid == -1)
|| (lcc->zoneid != SHMPERM_ZONEID(perm))) {
uidset = 0;
gidset = 0;
}
#endif
FreeLocalClientCreds(lcc);
if (uidset) {
/* User id 0 always gets access */
if (uid == 0) {
return 0;
}
/* Check the owner */
if (SHMPERM_UID(perm) == uid || SHMPERM_CUID(perm) == uid) {
mask = S_IRUSR;
if (!readonly) {
mask |= S_IWUSR;
}
return (SHMPERM_MODE(perm) & mask) == mask ? 0 : -1;
}
}
if (gidset) {
/* Check the group */
if (SHMPERM_GID(perm) == gid || SHMPERM_CGID(perm) == gid) {
mask = S_IRGRP;
if (!readonly) {
mask |= S_IWGRP;
}
return (SHMPERM_MODE(perm) & mask) == mask ? 0 : -1;
}
}
}
/* Otherwise, check everyone else */
mask = S_IROTH;
if (!readonly) {
mask |= S_IWOTH;
}
return (SHMPERM_MODE(perm) & mask) == mask ? 0 : -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'CVE-2007-6429: Always test for size+offset wrapping.'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: SShmCompletionEvent(from, to)
xShmCompletionEvent *from, *to;
{
to->type = from->type;
cpswaps(from->sequenceNumber, to->sequenceNumber);
cpswapl(from->drawable, to->drawable);
cpswaps(from->minorEvent, to->minorEvent);
to->majorEvent = from->majorEvent;
cpswapl(from->shmseg, to->shmseg);
cpswapl(from->offset, to->offset);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'CVE-2007-6429: Always test for size+offset wrapping.'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: ShmDetachSegment(value, shmseg)
pointer value; /* must conform to DeleteType */
XID shmseg;
{
ShmDescPtr shmdesc = (ShmDescPtr)value;
ShmDescPtr *prev;
if (--shmdesc->refcnt)
return TRUE;
shmdt(shmdesc->addr);
for (prev = &Shmsegs; *prev != shmdesc; prev = &(*prev)->next)
;
*prev = shmdesc->next;
xfree(shmdesc);
return Success;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'CVE-2007-6429: Always test for size+offset wrapping.'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
if (!(buf->flags & PIPE_BUF_FLAG_GIFT))
return 1;
buf->flags |= PIPE_BUF_FLAG_LRU;
return generic_pipe_buf_steal(pipe, buf);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-94'], 'message': 'splice: missing user pointer access verification
vmsplice_to_user() must always check the user pointer and length
with access_ok() before copying. Likewise, for the slow path of
copy_from_user_mmap_sem() we need to check that we may read from
the user region.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Cc: Wojciech Purczynski <cliph@research.coseinc.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int pipe_to_sendpage(struct pipe_inode_info *pipe,
struct pipe_buffer *buf, struct splice_desc *sd)
{
struct file *file = sd->u.file;
loff_t pos = sd->pos;
int ret, more;
ret = buf->ops->confirm(pipe, buf);
if (!ret) {
more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
ret = file->f_op->sendpage(file, buf->page, buf->offset,
sd->len, &pos, more);
}
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-94'], 'message': 'splice: missing user pointer access verification
vmsplice_to_user() must always check the user pointer and length
with access_ok() before copying. Likewise, for the slow path of
copy_from_user_mmap_sem() we need to check that we may read from
the user region.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Cc: Wojciech Purczynski <cliph@research.coseinc.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static inline struct pipe_inode_info *pipe_info(struct inode *inode)
{
if (S_ISFIFO(inode->i_mode))
return inode->i_pipe;
return NULL;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-94'], 'message': 'splice: missing user pointer access verification
vmsplice_to_user() must always check the user pointer and length
with access_ok() before copying. Likewise, for the slow path of
copy_from_user_mmap_sem() we need to check that we may read from
the user region.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Cc: Wojciech Purczynski <cliph@research.coseinc.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: int raw_notifier_chain_register(struct raw_notifier_head *nh,
struct notifier_block *n)
{
return notifier_chain_register(&nh->head, n);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'CPU time limit patch / setrlimit(RLIMIT_CPU, 0) cheat fix
As discovered here today, the change in Kernel 2.6.17 intended to inhibit
users from setting RLIMIT_CPU to 0 (as that is equivalent to unlimited) by
"cheating" and setting it to 1 in such a case, does not make a difference,
as the check is done in the wrong place (too late), and only applies to the
profiling code.
On all systems I checked running kernels above 2.6.17, no matter what the
hard and soft CPU time limits were before, a user could escape them by
issuing in the shell (sh/bash/zsh) "ulimit -t 0", and then the user's
process was not ever killed.
Attached is a trivial patch to fix that. Simply moving the check to a
slightly earlier location (specifically, before the line that actually
assigns the limit - *old_rlim = new_rlim), does the trick.
Do note that at least the zsh (but not ash, dash, or bash) shell has the
problem of "caching" the limits set by the ulimit command, so when running
zsh the fix will not immediately be evident - after entering "ulimit -t 0",
"ulimit -a" will show "-t: cpu time (seconds) 0", even though the actual
limit as returned by getrlimit(...) will be 1. It can be verified by
opening a subshell (which will not have the values of the parent shell in
cache) and checking in it, or just by running a CPU intensive command like
"echo '65536^1048576' | bc" and verifying that it dumps core after one
second.
Regardless of whether that is a misfeature in the shell, perhaps it would
be better to return -EINVAL from setrlimit in such a case instead of
cheating and setting to 1, as that does not really reflect the actual state
of the process anymore. I do not however know what the ground for that
decision was in the original 2.6.17 change, and whether there would be any
"backward" compatibility issues, so I preferred not to touch that right
now.
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int groups_from_user(struct group_info *group_info,
gid_t __user *grouplist)
{
int i;
int count = group_info->ngroups;
for (i = 0; i < group_info->nblocks; i++) {
int cp_count = min(NGROUPS_PER_BLOCK, count);
int off = i * NGROUPS_PER_BLOCK;
int len = cp_count * sizeof(*grouplist);
if (copy_from_user(group_info->blocks[i], grouplist+off, len))
return -EFAULT;
count -= cp_count;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'CPU time limit patch / setrlimit(RLIMIT_CPU, 0) cheat fix
As discovered here today, the change in Kernel 2.6.17 intended to inhibit
users from setting RLIMIT_CPU to 0 (as that is equivalent to unlimited) by
"cheating" and setting it to 1 in such a case, does not make a difference,
as the check is done in the wrong place (too late), and only applies to the
profiling code.
On all systems I checked running kernels above 2.6.17, no matter what the
hard and soft CPU time limits were before, a user could escape them by
issuing in the shell (sh/bash/zsh) "ulimit -t 0", and then the user's
process was not ever killed.
Attached is a trivial patch to fix that. Simply moving the check to a
slightly earlier location (specifically, before the line that actually
assigns the limit - *old_rlim = new_rlim), does the trick.
Do note that at least the zsh (but not ash, dash, or bash) shell has the
problem of "caching" the limits set by the ulimit command, so when running
zsh the fix will not immediately be evident - after entering "ulimit -t 0",
"ulimit -a" will show "-t: cpu time (seconds) 0", even though the actual
limit as returned by getrlimit(...) will be 1. It can be verified by
opening a subshell (which will not have the values of the parent shell in
cache) and checking in it, or just by running a CPU intensive command like
"echo '65536^1048576' | bc" and verifying that it dumps core after one
second.
Regardless of whether that is a misfeature in the shell, perhaps it would
be better to return -EINVAL from setrlimit in such a case instead of
cheating and setting to 1, as that does not really reflect the actual state
of the process anymore. I do not however know what the ground for that
decision was in the original 2.6.17 change, and whether there would be any
"backward" compatibility issues, so I preferred not to touch that right
now.
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>'</s> |