text
stringlengths 478
483k
|
|---|
<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: ossl_cipher_update(int argc, VALUE *argv, VALUE self)
{
EVP_CIPHER_CTX *ctx;
unsigned char *in;
long in_len, out_len;
VALUE data, str;
rb_scan_args(argc, argv, "11", &data, &str);
StringValue(data);
in = (unsigned char *)RSTRING_PTR(data);
if ((in_len = RSTRING_LEN(data)) == 0)
ossl_raise(rb_eArgError, "data must not be empty");
GetCipher(self, ctx);
out_len = in_len+EVP_CIPHER_CTX_block_size(ctx);
if (out_len <= 0) {
ossl_raise(rb_eRangeError,
"data too big to make output buffer: %ld bytes", in_len);
}
if (NIL_P(str)) {
str = rb_str_new(0, out_len);
} else {
StringValue(str);
rb_str_resize(str, out_len);
}
if (!ossl_cipher_update_long(ctx, (unsigned char *)RSTRING_PTR(str), &out_len, in, in_len))
ossl_raise(eCipherError, NULL);
assert(out_len < RSTRING_LEN(str));
rb_str_set_len(str, out_len);
return str;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-326', 'CWE-310', 'CWE-703'], 'message': 'cipher: don't set dummy encryption key in Cipher#initialize
Remove the encryption key initialization from Cipher#initialize. This
is effectively a revert of r32723 ("Avoid possible SEGV from AES
encryption/decryption", 2011-07-28).
r32723, which added the key initialization, was a workaround for
Ruby Bug #2768. For some certain ciphers, calling EVP_CipherUpdate()
before setting an encryption key caused segfault. It was not a problem
until OpenSSL implemented GCM mode - the encryption key could be
overridden by repeated calls of EVP_CipherInit_ex(). But, it is not the
case for AES-GCM ciphers. Setting a key, an IV, a key, in this order
causes the IV to be reset to an all-zero IV.
The problem of Bug #2768 persists on the current versions of OpenSSL.
So, make Cipher#update raise an exception if a key is not yet set by the
user. Since encrypting or decrypting without key does not make any
sense, this should not break existing applications.
Users can still call Cipher#key= and Cipher#iv= multiple times with
their own responsibility.
Reference: https://bugs.ruby-lang.org/issues/2768
Reference: https://bugs.ruby-lang.org/issues/8221
Reference: https://github.com/ruby/openssl/issues/49'</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: ImagingNew(const char* mode, int xsize, int ysize)
{
int bytes;
Imaging im;
if (strlen(mode) == 1) {
if (mode[0] == 'F' || mode[0] == 'I')
bytes = 4;
else
bytes = 1;
} else
bytes = strlen(mode); /* close enough */
if ((int64_t) xsize * (int64_t) ysize <= THRESHOLD / bytes) {
im = ImagingNewBlock(mode, xsize, ysize);
if (im)
return im;
/* assume memory error; try allocating in array mode instead */
ImagingError_Clear();
}
return ImagingNewArray(mode, xsize, ysize);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-284'], 'message': 'Memory error in Storage.c when accepting negative image size arguments'</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 *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
{
unsigned long val;
void *ptr = NULL;
if (!atomic_pool) {
WARN(1, "coherent pool not initialised!\n");
return NULL;
}
val = gen_pool_alloc(atomic_pool, size);
if (val) {
phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
*ret_page = phys_to_page(phys);
ptr = (void *)val;
if (flags & __GFP_ZERO)
memset(ptr, 0, size);
}
return ptr;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'arm64: dma-mapping: always clear allocated buffers
Buffers allocated by dma_alloc_coherent() are always zeroed on Alpha,
ARM (32bit), MIPS, PowerPC, x86/x86_64 and probably other architectures.
It turned out that some drivers rely on this 'feature'. Allocated buffer
might be also exposed to userspace with dma_mmap() call, so clearing it
is desired from security point of view to avoid exposing random memory
to userspace. This patch unifies dma_alloc_coherent() behavior on ARM64
architecture with other implementations by unconditionally zeroing
allocated buffer.
Cc: <[email protected]> # v3.14+
Signed-off-by: Marek Szyprowski <[email protected]>
Signed-off-by: Will Deacon <[email protected]>'</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: validate_event(struct pmu_hw_events *hw_events,
struct perf_event *event)
{
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
struct hw_perf_event fake_event = event->hw;
struct pmu *leader_pmu = event->group_leader->pmu;
if (is_software_event(event))
return 1;
if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
return 1;
if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
return 1;
return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-284', 'CWE-264'], 'message': 'arm64: perf: reject groups spanning multiple HW PMUs
The perf core implicitly rejects events spanning multiple HW PMUs, as in
these cases the event->ctx will differ. However this validation is
performed after pmu::event_init() is called in perf_init_event(), and
thus pmu::event_init() may be called with a group leader from a
different HW PMU.
The ARM64 PMU driver does not take this fact into account, and when
validating groups assumes that it can call to_arm_pmu(event->pmu) for
any HW event. When the event in question is from another HW PMU this is
wrong, and results in dereferencing garbage.
This patch updates the ARM64 PMU driver to first test for and reject
events from other PMUs, moving the to_arm_pmu and related logic after
this test. Fixes a crash triggered by perf_fuzzer on Linux-4.0-rc2, with
a CCI PMU present:
Bad mode in Synchronous Abort handler detected, code 0x86000006 -- IABT (current EL)
CPU: 0 PID: 1371 Comm: perf_fuzzer Not tainted 3.19.0+ #249
Hardware name: V2F-1XV7 Cortex-A53x2 SMM (DT)
task: ffffffc07c73a280 ti: ffffffc07b0a0000 task.ti: ffffffc07b0a0000
PC is at 0x0
LR is at validate_event+0x90/0xa8
pc : [<0000000000000000>] lr : [<ffffffc000090228>] pstate: 00000145
sp : ffffffc07b0a3ba0
[< (null)>] (null)
[<ffffffc0000907d8>] armpmu_event_init+0x174/0x3cc
[<ffffffc00015d870>] perf_try_init_event+0x34/0x70
[<ffffffc000164094>] perf_init_event+0xe0/0x10c
[<ffffffc000164348>] perf_event_alloc+0x288/0x358
[<ffffffc000164c5c>] SyS_perf_event_open+0x464/0x98c
Code: bad PC value
Also cleans up the code to use the arm_pmu only when we know
that we are dealing with an arm pmu event.
Cc: Will Deacon <[email protected]>
Acked-by: Mark Rutland <[email protected]>
Acked-by: Peter Ziljstra (Intel) <[email protected]>
Signed-off-by: Suzuki K. Poulose <[email protected]>
Signed-off-by: Will Deacon <[email protected]>'</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 struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
struct mm_struct *mm = vma->vm_mm;
struct dev_pagemap *pgmap = NULL;
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
retry:
if (unlikely(pmd_bad(*pmd)))
return no_page_table(vma, flags);
ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
pte = *ptep;
if (!pte_present(pte)) {
swp_entry_t entry;
/*
* KSM's break_ksm() relies upon recognizing a ksm page
* even while it is being migrated, so for that case we
* need migration_entry_wait().
*/
if (likely(!(flags & FOLL_MIGRATION)))
goto no_page;
if (pte_none(pte))
goto no_page;
entry = pte_to_swp_entry(pte);
if (!is_migration_entry(entry))
goto no_page;
pte_unmap_unlock(ptep, ptl);
migration_entry_wait(mm, pmd, address);
goto retry;
}
if ((flags & FOLL_NUMA) && pte_protnone(pte))
goto no_page;
if ((flags & FOLL_WRITE) && !pte_write(pte)) {
pte_unmap_unlock(ptep, ptl);
return NULL;
}
page = vm_normal_page(vma, address, pte);
if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
/*
* Only return device mapping pages in the FOLL_GET case since
* they are only valid while holding the pgmap reference.
*/
pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
if (pgmap)
page = pte_page(pte);
else
goto no_page;
} else if (unlikely(!page)) {
if (flags & FOLL_DUMP) {
/* Avoid special (like zero) pages in core dumps */
page = ERR_PTR(-EFAULT);
goto out;
}
if (is_zero_pfn(pte_pfn(pte))) {
page = pte_page(pte);
} else {
int ret;
ret = follow_pfn_pte(vma, address, ptep, flags);
page = ERR_PTR(ret);
goto out;
}
}
if (flags & FOLL_SPLIT && PageTransCompound(page)) {
int ret;
get_page(page);
pte_unmap_unlock(ptep, ptl);
lock_page(page);
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
if (ret)
return ERR_PTR(ret);
goto retry;
}
if (flags & FOLL_GET) {
get_page(page);
/* drop the pgmap reference now that we hold the page */
if (pgmap) {
put_dev_pagemap(pgmap);
pgmap = NULL;
}
}
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
set_page_dirty(page);
/*
* pte_mkyoung() would be more correct here, but atomic care
* is needed to avoid losing the dirty bit: it is easier to use
* mark_page_accessed().
*/
mark_page_accessed(page);
}
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/* Do not mlock pte-mapped THP */
if (PageTransCompound(page))
goto out;
/*
* The preliminary mapping check is mainly to avoid the
* pointless overhead of lock_page on the ZERO_PAGE
* which might bounce very badly if there is contention.
*
* If the page is already locked, we don't need to
* handle it now - vmscan will handle it later if and
* when it attempts to reclaim the page.
*/
if (page->mapping && trylock_page(page)) {
lru_add_drain(); /* push cached pages to LRU */
/*
* Because we lock page here, and migration is
* blocked by the pte's page reference, and we
* know the page is still mapped, we don't even
* need to check for file-cache page truncation.
*/
mlock_vma_page(page);
unlock_page(page);
}
}
out:
pte_unmap_unlock(ptep, ptl);
return page;
no_page:
pte_unmap_unlock(ptep, ptl);
if (!pte_none(pte))
return NULL;
return no_page_table(vma, flags);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-362'], 'message': 'mm: remove gup_flags FOLL_WRITE games from __get_user_pages()
This is an ancient bug that was actually attempted to be fixed once
(badly) by me eleven years ago in commit 4ceb5db9757a ("Fix
get_user_pages() race for write access") but that was then undone due to
problems on s390 by commit f33ea7f404e5 ("fix get_user_pages bug").
In the meantime, the s390 situation has long been fixed, and we can now
fix it by checking the pte_dirty() bit properly (and do it better). The
s390 dirty bit was implemented in abf09bed3cce ("s390/mm: implement
software dirty bits") which made it into v3.9. Earlier kernels will
have to look at the page state itself.
Also, the VM has become more scalable, and what used a purely
theoretical race back then has become easier to trigger.
To fix it, we introduce a new internal FOLL_COW flag to mark the "yes,
we already did a COW" rather than play racy games with FOLL_WRITE that
is very fundamental, and then use the pte dirty flag to validate that
the FOLL_COW flag is still valid.
Reported-and-tested-by: Phil "not Paul" Oester <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
Reviewed-by: Michal Hocko <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Willy Tarreau <[email protected]>
Cc: Nick Piggin <[email protected]>
Cc: Greg Thelen <[email protected]>
Cc: [email protected]
Signed-off-by: Linus Torvalds <[email protected]>'</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: xmlXPtrNewRangeNodePoint(xmlNodePtr start, xmlXPathObjectPtr end) {
xmlXPathObjectPtr ret;
if (start == NULL)
return(NULL);
if (end == NULL)
return(NULL);
if (start->type != XPATH_POINT)
return(NULL);
if (end->type != XPATH_POINT)
return(NULL);
ret = (xmlXPathObjectPtr) xmlMalloc(sizeof(xmlXPathObject));
if (ret == NULL) {
xmlXPtrErrMemory("allocating range");
return(NULL);
}
memset(ret, 0 , (size_t) sizeof(xmlXPathObject));
ret->type = XPATH_RANGE;
ret->user = start;
ret->index = -1;
ret->user2 = end->user;
ret->index2 = end->index;
xmlXPtrRangeCheckOrder(ret);
return(ret);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Disallow namespace nodes in XPointer ranges
Namespace nodes must be copied to avoid use-after-free errors.
But they don't necessarily have a physical representation in a
document, so simply disallow them in XPointer ranges.
Found with afl-fuzz.
Fixes CVE-2016-4658.'</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: xmlXPtrNewRangeNodeObject(xmlNodePtr start, xmlXPathObjectPtr end) {
xmlXPathObjectPtr ret;
if (start == NULL)
return(NULL);
if (end == NULL)
return(NULL);
switch (end->type) {
case XPATH_POINT:
case XPATH_RANGE:
break;
case XPATH_NODESET:
/*
* Empty set ...
*/
if (end->nodesetval->nodeNr <= 0)
return(NULL);
break;
default:
/* TODO */
return(NULL);
}
ret = (xmlXPathObjectPtr) xmlMalloc(sizeof(xmlXPathObject));
if (ret == NULL) {
xmlXPtrErrMemory("allocating range");
return(NULL);
}
memset(ret, 0 , (size_t) sizeof(xmlXPathObject));
ret->type = XPATH_RANGE;
ret->user = start;
ret->index = -1;
switch (end->type) {
case XPATH_POINT:
ret->user2 = end->user;
ret->index2 = end->index;
break;
case XPATH_RANGE:
ret->user2 = end->user2;
ret->index2 = end->index2;
break;
case XPATH_NODESET: {
ret->user2 = end->nodesetval->nodeTab[end->nodesetval->nodeNr - 1];
ret->index2 = -1;
break;
}
default:
STRANGE
return(NULL);
}
xmlXPtrRangeCheckOrder(ret);
return(ret);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Disallow namespace nodes in XPointer ranges
Namespace nodes must be copied to avoid use-after-free errors.
But they don't necessarily have a physical representation in a
document, so simply disallow them in XPointer ranges.
Found with afl-fuzz.
Fixes CVE-2016-4658.'</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: xmlXPtrNewRangePointNode(xmlXPathObjectPtr start, xmlNodePtr end) {
xmlXPathObjectPtr ret;
if (start == NULL)
return(NULL);
if (end == NULL)
return(NULL);
if (start->type != XPATH_POINT)
return(NULL);
ret = (xmlXPathObjectPtr) xmlMalloc(sizeof(xmlXPathObject));
if (ret == NULL) {
xmlXPtrErrMemory("allocating range");
return(NULL);
}
memset(ret, 0 , (size_t) sizeof(xmlXPathObject));
ret->type = XPATH_RANGE;
ret->user = start->user;
ret->index = start->index;
ret->user2 = end;
ret->index2 = -1;
xmlXPtrRangeCheckOrder(ret);
return(ret);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Disallow namespace nodes in XPointer ranges
Namespace nodes must be copied to avoid use-after-free errors.
But they don't necessarily have a physical representation in a
document, so simply disallow them in XPointer ranges.
Found with afl-fuzz.
Fixes CVE-2016-4658.'</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: xmlXPtrNewRangePoints(xmlXPathObjectPtr start, xmlXPathObjectPtr end) {
xmlXPathObjectPtr ret;
if (start == NULL)
return(NULL);
if (end == NULL)
return(NULL);
if (start->type != XPATH_POINT)
return(NULL);
if (end->type != XPATH_POINT)
return(NULL);
ret = (xmlXPathObjectPtr) xmlMalloc(sizeof(xmlXPathObject));
if (ret == NULL) {
xmlXPtrErrMemory("allocating range");
return(NULL);
}
memset(ret, 0 , (size_t) sizeof(xmlXPathObject));
ret->type = XPATH_RANGE;
ret->user = start->user;
ret->index = start->index;
ret->user2 = end->user;
ret->index2 = end->index;
xmlXPtrRangeCheckOrder(ret);
return(ret);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Disallow namespace nodes in XPointer ranges
Namespace nodes must be copied to avoid use-after-free errors.
But they don't necessarily have a physical representation in a
document, so simply disallow them in XPointer ranges.
Found with afl-fuzz.
Fixes CVE-2016-4658.'</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: xfs_iflush_abort(
xfs_inode_t *ip,
bool stale)
{
xfs_inode_log_item_t *iip = ip->i_itemp;
if (iip) {
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
xfs_trans_ail_remove(&iip->ili_item,
stale ? SHUTDOWN_LOG_IO_ERROR :
SHUTDOWN_CORRUPT_INCORE);
}
iip->ili_logged = 0;
/*
* Clear the ili_last_fields bits now that we know that the
* data corresponding to them is safely on disk.
*/
iip->ili_last_fields = 0;
/*
* Clear the inode logging fields so no more flushes are
* attempted.
*/
iip->ili_fields = 0;
}
/*
* Release the inode's flush lock since we're done with it.
*/
xfs_ifunlock(ip);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-19'], 'message': 'xfs: optimise away log forces on timestamp updates for fdatasync
xfs: timestamp updates cause excessive fdatasync log traffic
Sage Weil reported that a ceph test workload was writing to the
log on every fdatasync during an overwrite workload. Event tracing
showed that the only metadata modification being made was the
timestamp updates during the write(2) syscall, but fdatasync(2)
is supposed to ignore them. The key observation was that the
transactions in the log all looked like this:
INODE: #regs: 4 ino: 0x8b flags: 0x45 dsize: 32
And contained a flags field of 0x45 or 0x85, and had data and
attribute forks following the inode core. This means that the
timestamp updates were triggering dirty relogging of previously
logged parts of the inode that hadn't yet been flushed back to
disk.
There are two parts to this problem. The first is that XFS relogs
dirty regions in subsequent transactions, so it carries around the
fields that have been dirtied since the last time the inode was
written back to disk, not since the last time the inode was forced
into the log.
The second part is that on v5 filesystems, the inode change count
update during inode dirtying also sets the XFS_ILOG_CORE flag, so
on v5 filesystems this makes a timestamp update dirty the entire
inode.
As a result when fdatasync is run, it looks at the dirty fields in
the inode, and sees more than just the timestamp flag, even though
the only metadata change since the last fdatasync was just the
timestamps. Hence we force the log on every subsequent fdatasync
even though it is not needed.
To fix this, add a new field to the inode log item that tracks
changes since the last time fsync/fdatasync forced the log to flush
the changes to the journal. This flag is updated when we dirty the
inode, but we do it before updating the change count so it does not
carry the "core dirty" flag from timestamp updates. The fields are
zeroed when the inode is marked clean (due to writeback/freeing) or
when an fsync/datasync forces the log. Hence if we only dirty the
timestamps on the inode between fsync/fdatasync calls, the fdatasync
will not trigger another log force.
Over 100 runs of the test program:
Ext4 baseline:
runtime: 1.63s +/- 0.24s
avg lat: 1.59ms +/- 0.24ms
iops: ~2000
XFS, vanilla kernel:
runtime: 2.45s +/- 0.18s
avg lat: 2.39ms +/- 0.18ms
log forces: ~400/s
iops: ~1000
XFS, patched kernel:
runtime: 1.49s +/- 0.26s
avg lat: 1.46ms +/- 0.25ms
log forces: ~30/s
iops: ~1500
Reported-by: Sage Weil <[email protected]>
Signed-off-by: Dave Chinner <[email protected]>
Reviewed-by: Brian Foster <[email protected]>
Signed-off-by: Dave Chinner <[email protected]>'</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: xfs_trans_log_inode(
xfs_trans_t *tp,
xfs_inode_t *ip,
uint flags)
{
ASSERT(ip->i_itemp != NULL);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
/*
* First time we log the inode in a transaction, bump the inode change
* counter if it is configured for this to occur. We don't use
* inode_inc_version() because there is no need for extra locking around
* i_version as we already hold the inode locked exclusively for
* metadata modification.
*/
if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
IS_I_VERSION(VFS_I(ip))) {
ip->i_d.di_changecount = ++VFS_I(ip)->i_version;
flags |= XFS_ILOG_CORE;
}
tp->t_flags |= XFS_TRANS_DIRTY;
ip->i_itemp->ili_item.li_desc->lid_flags |= XFS_LID_DIRTY;
/*
* Always OR in the bits from the ili_last_fields field.
* This is to coordinate with the xfs_iflush() and xfs_iflush_done()
* routines in the eventual clearing of the ili_fields bits.
* See the big comment in xfs_iflush() for an explanation of
* this coordination mechanism.
*/
flags |= ip->i_itemp->ili_last_fields;
ip->i_itemp->ili_fields |= flags;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-19'], 'message': 'xfs: optimise away log forces on timestamp updates for fdatasync
xfs: timestamp updates cause excessive fdatasync log traffic
Sage Weil reported that a ceph test workload was writing to the
log on every fdatasync during an overwrite workload. Event tracing
showed that the only metadata modification being made was the
timestamp updates during the write(2) syscall, but fdatasync(2)
is supposed to ignore them. The key observation was that the
transactions in the log all looked like this:
INODE: #regs: 4 ino: 0x8b flags: 0x45 dsize: 32
And contained a flags field of 0x45 or 0x85, and had data and
attribute forks following the inode core. This means that the
timestamp updates were triggering dirty relogging of previously
logged parts of the inode that hadn't yet been flushed back to
disk.
There are two parts to this problem. The first is that XFS relogs
dirty regions in subsequent transactions, so it carries around the
fields that have been dirtied since the last time the inode was
written back to disk, not since the last time the inode was forced
into the log.
The second part is that on v5 filesystems, the inode change count
update during inode dirtying also sets the XFS_ILOG_CORE flag, so
on v5 filesystems this makes a timestamp update dirty the entire
inode.
As a result when fdatasync is run, it looks at the dirty fields in
the inode, and sees more than just the timestamp flag, even though
the only metadata change since the last fdatasync was just the
timestamps. Hence we force the log on every subsequent fdatasync
even though it is not needed.
To fix this, add a new field to the inode log item that tracks
changes since the last time fsync/fdatasync forced the log to flush
the changes to the journal. This flag is updated when we dirty the
inode, but we do it before updating the change count so it does not
carry the "core dirty" flag from timestamp updates. The fields are
zeroed when the inode is marked clean (due to writeback/freeing) or
when an fsync/datasync forces the log. Hence if we only dirty the
timestamps on the inode between fsync/fdatasync calls, the fdatasync
will not trigger another log force.
Over 100 runs of the test program:
Ext4 baseline:
runtime: 1.63s +/- 0.24s
avg lat: 1.59ms +/- 0.24ms
iops: ~2000
XFS, vanilla kernel:
runtime: 2.45s +/- 0.18s
avg lat: 2.39ms +/- 0.18ms
log forces: ~400/s
iops: ~1000
XFS, patched kernel:
runtime: 1.49s +/- 0.26s
avg lat: 1.46ms +/- 0.25ms
log forces: ~30/s
iops: ~1500
Reported-by: Sage Weil <[email protected]>
Signed-off-by: Dave Chinner <[email protected]>
Reviewed-by: Brian Foster <[email protected]>
Signed-off-by: Dave Chinner <[email protected]>'</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: xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
/*
* All metadata updates are logged, which means that we just have
* to flush the log up to the latest LSN that touched the inode.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (lsn)
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return error;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-19'], 'message': 'xfs: optimise away log forces on timestamp updates for fdatasync
xfs: timestamp updates cause excessive fdatasync log traffic
Sage Weil reported that a ceph test workload was writing to the
log on every fdatasync during an overwrite workload. Event tracing
showed that the only metadata modification being made was the
timestamp updates during the write(2) syscall, but fdatasync(2)
is supposed to ignore them. The key observation was that the
transactions in the log all looked like this:
INODE: #regs: 4 ino: 0x8b flags: 0x45 dsize: 32
And contained a flags field of 0x45 or 0x85, and had data and
attribute forks following the inode core. This means that the
timestamp updates were triggering dirty relogging of previously
logged parts of the inode that hadn't yet been flushed back to
disk.
There are two parts to this problem. The first is that XFS relogs
dirty regions in subsequent transactions, so it carries around the
fields that have been dirtied since the last time the inode was
written back to disk, not since the last time the inode was forced
into the log.
The second part is that on v5 filesystems, the inode change count
update during inode dirtying also sets the XFS_ILOG_CORE flag, so
on v5 filesystems this makes a timestamp update dirty the entire
inode.
As a result when fdatasync is run, it looks at the dirty fields in
the inode, and sees more than just the timestamp flag, even though
the only metadata change since the last fdatasync was just the
timestamps. Hence we force the log on every subsequent fdatasync
even though it is not needed.
To fix this, add a new field to the inode log item that tracks
changes since the last time fsync/fdatasync forced the log to flush
the changes to the journal. This flag is updated when we dirty the
inode, but we do it before updating the change count so it does not
carry the "core dirty" flag from timestamp updates. The fields are
zeroed when the inode is marked clean (due to writeback/freeing) or
when an fsync/datasync forces the log. Hence if we only dirty the
timestamps on the inode between fsync/fdatasync calls, the fdatasync
will not trigger another log force.
Over 100 runs of the test program:
Ext4 baseline:
runtime: 1.63s +/- 0.24s
avg lat: 1.59ms +/- 0.24ms
iops: ~2000
XFS, vanilla kernel:
runtime: 2.45s +/- 0.18s
avg lat: 2.39ms +/- 0.18ms
log forces: ~400/s
iops: ~1000
XFS, patched kernel:
runtime: 1.49s +/- 0.26s
avg lat: 1.46ms +/- 0.25ms
log forces: ~30/s
iops: ~1500
Reported-by: Sage Weil <[email protected]>
Signed-off-by: Dave Chinner <[email protected]>
Reviewed-by: Brian Foster <[email protected]>
Signed-off-by: Dave Chinner <[email protected]>'</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 struct sk_buff **gre_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
struct sk_buff *p;
const struct gre_base_hdr *greh;
unsigned int hlen, grehlen;
unsigned int off;
int flush = 1;
struct packet_offload *ptype;
__be16 type;
off = skb_gro_offset(skb);
hlen = off + sizeof(*greh);
greh = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, hlen)) {
greh = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!greh))
goto out;
}
/* Only support version 0 and K (key), C (csum) flags. Note that
* although the support for the S (seq#) flag can be added easily
* for GRO, this is problematic for GSO hence can not be enabled
* here because a GRO pkt may end up in the forwarding path, thus
* requiring GSO support to break it up correctly.
*/
if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
goto out;
type = greh->protocol;
rcu_read_lock();
ptype = gro_find_receive_by_type(type);
if (!ptype)
goto out_unlock;
grehlen = GRE_HEADER_SECTION;
if (greh->flags & GRE_KEY)
grehlen += GRE_HEADER_SECTION;
if (greh->flags & GRE_CSUM)
grehlen += GRE_HEADER_SECTION;
hlen = off + grehlen;
if (skb_gro_header_hard(skb, hlen)) {
greh = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!greh))
goto out_unlock;
}
/* Don't bother verifying checksum if we're going to flush anyway. */
if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) {
if (skb_gro_checksum_simple_validate(skb))
goto out_unlock;
skb_gro_checksum_try_convert(skb, IPPROTO_GRE, 0,
null_compute_pseudo);
}
for (p = *head; p; p = p->next) {
const struct gre_base_hdr *greh2;
if (!NAPI_GRO_CB(p)->same_flow)
continue;
/* The following checks are needed to ensure only pkts
* from the same tunnel are considered for aggregation.
* The criteria for "the same tunnel" includes:
* 1) same version (we only support version 0 here)
* 2) same protocol (we only support ETH_P_IP for now)
* 3) same set of flags
* 4) same key if the key field is present.
*/
greh2 = (struct gre_base_hdr *)(p->data + off);
if (greh2->flags != greh->flags ||
greh2->protocol != greh->protocol) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
if (greh->flags & GRE_KEY) {
/* compare keys */
if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
}
skb_gro_pull(skb, grehlen);
/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
skb_gro_postpull_rcsum(skb, greh, grehlen);
pp = ptype->callbacks.gro_receive(head, skb);
flush = 0;
out_unlock:
rcu_read_unlock();
out:
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-400', 'CWE-703'], 'message': 'tunnels: Don't apply GRO to multiple layers of encapsulation.
When drivers express support for TSO of encapsulated packets, they
only mean that they can do it for one layer of encapsulation.
Supporting additional levels would mean updating, at a minimum,
more IP length fields and they are unaware of this.
No encapsulation device expresses support for handling offloaded
encapsulated packets, so we won't generate these types of frames
in the transmit path. However, GRO doesn't have a check for
multiple levels of encapsulation and will attempt to build them.
UDP tunnel GRO actually does prevent this situation but it only
handles multiple UDP tunnels stacked on top of each other. This
generalizes that solution to prevent any kind of tunnel stacking
that would cause problems.
Fixes: bf5a755f ("net-gre-gro: Add GRE support to the GRO stack")
Signed-off-by: Jesse Gross <[email protected]>
Signed-off-by: David S. Miller <[email protected]>'</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: struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
struct udphdr *uh)
{
struct udp_offload_priv *uo_priv;
struct sk_buff *p, **pp = NULL;
struct udphdr *uh2;
unsigned int off = skb_gro_offset(skb);
int flush = 1;
if (NAPI_GRO_CB(skb)->udp_mark ||
(skb->ip_summed != CHECKSUM_PARTIAL &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
!NAPI_GRO_CB(skb)->csum_valid))
goto out;
/* mark that this skb passed once through the udp gro layer */
NAPI_GRO_CB(skb)->udp_mark = 1;
rcu_read_lock();
uo_priv = rcu_dereference(udp_offload_base);
for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) &&
uo_priv->offload->port == uh->dest &&
uo_priv->offload->callbacks.gro_receive)
goto unflush;
}
goto out_unlock;
unflush:
flush = 0;
for (p = *head; p; p = p->next) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
uh2 = (struct udphdr *)(p->data + off);
/* Match ports and either checksums are either both zero
* or nonzero.
*/
if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
(!uh->check ^ !uh2->check)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
pp = uo_priv->offload->callbacks.gro_receive(head, skb,
uo_priv->offload);
out_unlock:
rcu_read_unlock();
out:
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-400', 'CWE-703'], 'message': 'tunnels: Don't apply GRO to multiple layers of encapsulation.
When drivers express support for TSO of encapsulated packets, they
only mean that they can do it for one layer of encapsulation.
Supporting additional levels would mean updating, at a minimum,
more IP length fields and they are unaware of this.
No encapsulation device expresses support for handling offloaded
encapsulated packets, so we won't generate these types of frames
in the transmit path. However, GRO doesn't have a check for
multiple levels of encapsulation and will attempt to build them.
UDP tunnel GRO actually does prevent this situation but it only
handles multiple UDP tunnels stacked on top of each other. This
generalizes that solution to prevent any kind of tunnel stacking
that would cause problems.
Fixes: bf5a755f ("net-gre-gro: Add GRE support to the GRO stack")
Signed-off-by: Jesse Gross <[email protected]>
Signed-off-by: David S. Miller <[email protected]>'</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: jas_image_t *bmp_decode(jas_stream_t *in, char *optstr)
{
jas_image_t *image;
bmp_hdr_t hdr;
bmp_info_t *info;
uint_fast16_t cmptno;
jas_image_cmptparm_t cmptparms[3];
jas_image_cmptparm_t *cmptparm;
uint_fast16_t numcmpts;
long n;
if (optstr) {
jas_eprintf("warning: ignoring BMP decoder options\n");
}
jas_eprintf(
"THE BMP FORMAT IS NOT FULLY SUPPORTED!\n"
"THAT IS, THE JASPER SOFTWARE CANNOT DECODE ALL TYPES OF BMP DATA.\n"
"IF YOU HAVE ANY PROBLEMS, PLEASE TRY CONVERTING YOUR IMAGE DATA\n"
"TO THE PNM FORMAT, AND USING THIS FORMAT INSTEAD.\n"
);
/* Read the bitmap header. */
if (bmp_gethdr(in, &hdr)) {
jas_eprintf("cannot get header\n");
return 0;
}
/* Read the bitmap information. */
if (!(info = bmp_getinfo(in))) {
jas_eprintf("cannot get info\n");
return 0;
}
/* Ensure that we support this type of BMP file. */
if (!bmp_issupported(&hdr, info)) {
jas_eprintf("error: unsupported BMP encoding\n");
bmp_info_destroy(info);
return 0;
}
/* Skip over any useless data between the end of the palette
and start of the bitmap data. */
if ((n = hdr.off - (BMP_HDRLEN + BMP_INFOLEN + BMP_PALLEN(info))) < 0) {
jas_eprintf("error: possibly bad bitmap offset?\n");
return 0;
}
if (n > 0) {
jas_eprintf("skipping unknown data in BMP file\n");
if (bmp_gobble(in, n)) {
bmp_info_destroy(info);
return 0;
}
}
/* Get the number of components. */
numcmpts = bmp_numcmpts(info);
for (cmptno = 0, cmptparm = cmptparms; cmptno < numcmpts; ++cmptno,
++cmptparm) {
cmptparm->tlx = 0;
cmptparm->tly = 0;
cmptparm->hstep = 1;
cmptparm->vstep = 1;
cmptparm->width = info->width;
cmptparm->height = info->height;
cmptparm->prec = 8;
cmptparm->sgnd = false;
}
/* Create image object. */
if (!(image = jas_image_create(numcmpts, cmptparms,
JAS_CLRSPC_UNKNOWN))) {
bmp_info_destroy(info);
return 0;
}
if (numcmpts == 3) {
jas_image_setclrspc(image, JAS_CLRSPC_SRGB);
jas_image_setcmpttype(image, 0,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_RGB_R));
jas_image_setcmpttype(image, 1,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_RGB_G));
jas_image_setcmpttype(image, 2,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_RGB_B));
} else {
jas_image_setclrspc(image, JAS_CLRSPC_SGRAY);
jas_image_setcmpttype(image, 0,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_GRAY_Y));
}
/* Read the bitmap data. */
if (bmp_getdata(in, info, image)) {
bmp_info_destroy(info);
jas_image_destroy(image);
return 0;
}
bmp_info_destroy(info);
return image;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476', 'CWE-125'], 'message': 'Fixed a sanitizer failure in the BMP codec.
Also, added a --debug-level command line option to the imginfo command
for debugging purposes.'</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: jas_matrix_t *jas_matrix_create(int numrows, int numcols)
{
jas_matrix_t *matrix;
int i;
if (!(matrix = jas_malloc(sizeof(jas_matrix_t)))) {
return 0;
}
matrix->flags_ = 0;
matrix->numrows_ = numrows;
matrix->numcols_ = numcols;
matrix->rows_ = 0;
matrix->maxrows_ = numrows;
matrix->data_ = 0;
matrix->datasize_ = numrows * numcols;
if (matrix->maxrows_ > 0) {
if (!(matrix->rows_ = jas_alloc2(matrix->maxrows_,
sizeof(jas_seqent_t *)))) {
jas_matrix_destroy(matrix);
return 0;
}
}
if (matrix->datasize_ > 0) {
if (!(matrix->data_ = jas_alloc2(matrix->datasize_,
sizeof(jas_seqent_t)))) {
jas_matrix_destroy(matrix);
return 0;
}
}
for (i = 0; i < numrows; ++i) {
matrix->rows_[i] = &matrix->data_[i * matrix->numcols_];
}
for (i = 0; i < matrix->datasize_; ++i) {
matrix->data_[i] = 0;
}
matrix->xstart_ = 0;
matrix->ystart_ = 0;
matrix->xend_ = matrix->numcols_;
matrix->yend_ = matrix->numrows_;
return matrix;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'Fixed a problem with a null pointer dereference in the BMP decoder.'</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 jpc_siz_getparms(jpc_ms_t *ms, jpc_cstate_t *cstate,
jas_stream_t *in)
{
jpc_siz_t *siz = &ms->parms.siz;
unsigned int i;
uint_fast8_t tmp;
/* Eliminate compiler warning about unused variables. */
cstate = 0;
if (jpc_getuint16(in, &siz->caps) ||
jpc_getuint32(in, &siz->width) ||
jpc_getuint32(in, &siz->height) ||
jpc_getuint32(in, &siz->xoff) ||
jpc_getuint32(in, &siz->yoff) ||
jpc_getuint32(in, &siz->tilewidth) ||
jpc_getuint32(in, &siz->tileheight) ||
jpc_getuint32(in, &siz->tilexoff) ||
jpc_getuint32(in, &siz->tileyoff) ||
jpc_getuint16(in, &siz->numcomps)) {
return -1;
}
if (!siz->width || !siz->height || !siz->tilewidth ||
!siz->tileheight || !siz->numcomps) {
return -1;
}
if (!(siz->comps = jas_alloc2(siz->numcomps, sizeof(jpc_sizcomp_t)))) {
return -1;
}
for (i = 0; i < siz->numcomps; ++i) {
if (jpc_getuint8(in, &tmp) ||
jpc_getuint8(in, &siz->comps[i].hsamp) ||
jpc_getuint8(in, &siz->comps[i].vsamp)) {
jas_free(siz->comps);
return -1;
}
siz->comps[i].sgnd = (tmp >> 7) & 1;
siz->comps[i].prec = (tmp & 0x7f) + 1;
}
if (jas_stream_eof(in)) {
jas_free(siz->comps);
return -1;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-369'], 'message': 'Added range check on XRsiz and YRsiz fields of SIZ marker segment.'</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: safe_fprintf(FILE *f, const char *fmt, ...)
{
char fmtbuff_stack[256]; /* Place to format the printf() string. */
char outbuff[256]; /* Buffer for outgoing characters. */
char *fmtbuff_heap; /* If fmtbuff_stack is too small, we use malloc */
char *fmtbuff; /* Pointer to fmtbuff_stack or fmtbuff_heap. */
int fmtbuff_length;
int length, n;
va_list ap;
const char *p;
unsigned i;
wchar_t wc;
char try_wc;
/* Use a stack-allocated buffer if we can, for speed and safety. */
fmtbuff_heap = NULL;
fmtbuff_length = sizeof(fmtbuff_stack);
fmtbuff = fmtbuff_stack;
/* Try formatting into the stack buffer. */
va_start(ap, fmt);
length = vsnprintf(fmtbuff, fmtbuff_length, fmt, ap);
va_end(ap);
/* If the result was too large, allocate a buffer on the heap. */
while (length < 0 || length >= fmtbuff_length) {
if (length >= fmtbuff_length)
fmtbuff_length = length+1;
else if (fmtbuff_length < 8192)
fmtbuff_length *= 2;
else if (fmtbuff_length < 1000000)
fmtbuff_length += fmtbuff_length / 4;
else {
length = fmtbuff_length;
fmtbuff_heap[length-1] = '\0';
break;
}
free(fmtbuff_heap);
fmtbuff_heap = malloc(fmtbuff_length);
/* Reformat the result into the heap buffer if we can. */
if (fmtbuff_heap != NULL) {
fmtbuff = fmtbuff_heap;
va_start(ap, fmt);
length = vsnprintf(fmtbuff, fmtbuff_length, fmt, ap);
va_end(ap);
} else {
/* Leave fmtbuff pointing to the truncated
* string in fmtbuff_stack. */
length = sizeof(fmtbuff_stack) - 1;
break;
}
}
/* Note: mbrtowc() has a cleaner API, but mbtowc() seems a bit
* more portable, so we use that here instead. */
if (mbtowc(NULL, NULL, 1) == -1) { /* Reset the shift state. */
/* mbtowc() should never fail in practice, but
* handle the theoretical error anyway. */
free(fmtbuff_heap);
return;
}
/* Write data, expanding unprintable characters. */
p = fmtbuff;
i = 0;
try_wc = 1;
while (*p != '\0') {
/* Convert to wide char, test if the wide
* char is printable in the current locale. */
if (try_wc && (n = mbtowc(&wc, p, length)) != -1) {
length -= n;
if (iswprint(wc) && wc != L'\\') {
/* Printable, copy the bytes through. */
while (n-- > 0)
outbuff[i++] = *p++;
} else {
/* Not printable, format the bytes. */
while (n-- > 0)
i += (unsigned)bsdtar_expand_char(
outbuff, i, *p++);
}
} else {
/* After any conversion failure, don't bother
* trying to convert the rest. */
i += (unsigned)bsdtar_expand_char(outbuff, i, *p++);
try_wc = 0;
}
/* If our output buffer is full, dump it and keep going. */
if (i > (sizeof(outbuff) - 20)) {
outbuff[i] = '\0';
fprintf(f, "%s", outbuff);
i = 0;
}
}
outbuff[i] = '\0';
fprintf(f, "%s", outbuff);
/* If we allocated a heap-based formatting buffer, free it now. */
free(fmtbuff_heap);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'Issue #767: Buffer overflow printing a filename
The safe_fprintf function attempts to ensure clean output for an
arbitrary sequence of bytes by doing a trial conversion of the
multibyte characters to wide characters -- if the resulting wide
character is printable then we pass through the corresponding bytes
unaltered, otherwise, we convert them to C-style ASCII escapes.
The stack trace in Issue #767 suggest that the 20-byte buffer
was getting overflowed trying to format a non-printable multibyte
character. This should only happen if there is a valid multibyte
character of more than 5 bytes that was unprintable. (Each byte
would get expanded to a four-charcter octal-style escape of the form
"\123" resulting in >20 characters for the >5 byte multibyte character.)
I've not been able to reproduce this, but have expanded the conversion
buffer to 128 bytes on the belief that no multibyte character set
has a single character of more than 32 bytes.'</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: read_Header(struct archive_read *a, struct _7z_header_info *h,
int check_header_id)
{
struct _7zip *zip = (struct _7zip *)a->format->data;
const unsigned char *p;
struct _7z_folder *folders;
struct _7z_stream_info *si = &(zip->si);
struct _7zip_entry *entries;
uint32_t folderIndex, indexInFolder;
unsigned i;
int eindex, empty_streams, sindex;
if (check_header_id) {
/*
* Read Header.
*/
if ((p = header_bytes(a, 1)) == NULL)
return (-1);
if (*p != kHeader)
return (-1);
}
/*
* Read ArchiveProperties.
*/
if ((p = header_bytes(a, 1)) == NULL)
return (-1);
if (*p == kArchiveProperties) {
for (;;) {
uint64_t size;
if ((p = header_bytes(a, 1)) == NULL)
return (-1);
if (*p == 0)
break;
if (parse_7zip_uint64(a, &size) < 0)
return (-1);
}
if ((p = header_bytes(a, 1)) == NULL)
return (-1);
}
/*
* Read MainStreamsInfo.
*/
if (*p == kMainStreamsInfo) {
if (read_StreamsInfo(a, &(zip->si)) < 0)
return (-1);
if ((p = header_bytes(a, 1)) == NULL)
return (-1);
}
if (*p == kEnd)
return (0);
/*
* Read FilesInfo.
*/
if (*p != kFilesInfo)
return (-1);
if (parse_7zip_uint64(a, &(zip->numFiles)) < 0)
return (-1);
if (UMAX_ENTRY < zip->numFiles)
return (-1);
zip->entries = calloc((size_t)zip->numFiles, sizeof(*zip->entries));
if (zip->entries == NULL)
return (-1);
entries = zip->entries;
empty_streams = 0;
for (;;) {
int type;
uint64_t size;
size_t ll;
if ((p = header_bytes(a, 1)) == NULL)
return (-1);
type = *p;
if (type == kEnd)
break;
if (parse_7zip_uint64(a, &size) < 0)
return (-1);
if (zip->header_bytes_remaining < size)
return (-1);
ll = (size_t)size;
switch (type) {
case kEmptyStream:
h->emptyStreamBools = calloc((size_t)zip->numFiles,
sizeof(*h->emptyStreamBools));
if (h->emptyStreamBools == NULL)
return (-1);
if (read_Bools(
a, h->emptyStreamBools, (size_t)zip->numFiles) < 0)
return (-1);
empty_streams = 0;
for (i = 0; i < zip->numFiles; i++) {
if (h->emptyStreamBools[i])
empty_streams++;
}
break;
case kEmptyFile:
if (empty_streams <= 0) {
/* Unexcepted sequence. Skip this. */
if (header_bytes(a, ll) == NULL)
return (-1);
break;
}
h->emptyFileBools = calloc(empty_streams,
sizeof(*h->emptyFileBools));
if (h->emptyFileBools == NULL)
return (-1);
if (read_Bools(a, h->emptyFileBools, empty_streams) < 0)
return (-1);
break;
case kAnti:
if (empty_streams <= 0) {
/* Unexcepted sequence. Skip this. */
if (header_bytes(a, ll) == NULL)
return (-1);
break;
}
h->antiBools = calloc(empty_streams,
sizeof(*h->antiBools));
if (h->antiBools == NULL)
return (-1);
if (read_Bools(a, h->antiBools, empty_streams) < 0)
return (-1);
break;
case kCTime:
case kATime:
case kMTime:
if (read_Times(a, h, type) < 0)
return (-1);
break;
case kName:
{
unsigned char *np;
size_t nl, nb;
/* Skip one byte. */
if ((p = header_bytes(a, 1)) == NULL)
return (-1);
ll--;
if ((ll & 1) || ll < zip->numFiles * 4)
return (-1);
zip->entry_names = malloc(ll);
if (zip->entry_names == NULL)
return (-1);
np = zip->entry_names;
nb = ll;
/*
* Copy whole file names.
* NOTE: This loop prevents from expanding
* the uncompressed buffer in order not to
* use extra memory resource.
*/
while (nb) {
size_t b;
if (nb > UBUFF_SIZE)
b = UBUFF_SIZE;
else
b = nb;
if ((p = header_bytes(a, b)) == NULL)
return (-1);
memcpy(np, p, b);
np += b;
nb -= b;
}
np = zip->entry_names;
nl = ll;
for (i = 0; i < zip->numFiles; i++) {
entries[i].utf16name = np;
#if defined(_WIN32) && !defined(__CYGWIN__) && defined(_DEBUG)
entries[i].wname = (wchar_t *)np;
#endif
/* Find a terminator. */
while (nl >= 2 && (np[0] || np[1])) {
np += 2;
nl -= 2;
}
if (nl < 2)
return (-1);/* Terminator not found */
entries[i].name_len = np - entries[i].utf16name;
np += 2;
nl -= 2;
}
break;
}
case kAttributes:
{
int allAreDefined;
if ((p = header_bytes(a, 2)) == NULL)
return (-1);
allAreDefined = *p;
h->attrBools = calloc((size_t)zip->numFiles,
sizeof(*h->attrBools));
if (h->attrBools == NULL)
return (-1);
if (allAreDefined)
memset(h->attrBools, 1, (size_t)zip->numFiles);
else {
if (read_Bools(a, h->attrBools,
(size_t)zip->numFiles) < 0)
return (-1);
}
for (i = 0; i < zip->numFiles; i++) {
if (h->attrBools[i]) {
if ((p = header_bytes(a, 4)) == NULL)
return (-1);
entries[i].attr = archive_le32dec(p);
}
}
break;
}
case kDummy:
if (ll == 0)
break;
default:
if (header_bytes(a, ll) == NULL)
return (-1);
break;
}
}
/*
* Set up entry's attributes.
*/
folders = si->ci.folders;
eindex = sindex = 0;
folderIndex = indexInFolder = 0;
for (i = 0; i < zip->numFiles; i++) {
if (h->emptyStreamBools == NULL || h->emptyStreamBools[i] == 0)
entries[i].flg |= HAS_STREAM;
/* The high 16 bits of attributes is a posix file mode. */
entries[i].mode = entries[i].attr >> 16;
if (entries[i].flg & HAS_STREAM) {
if ((size_t)sindex >= si->ss.unpack_streams)
return (-1);
if (entries[i].mode == 0)
entries[i].mode = AE_IFREG | 0666;
if (si->ss.digestsDefined[sindex])
entries[i].flg |= CRC32_IS_SET;
entries[i].ssIndex = sindex;
sindex++;
} else {
int dir;
if (h->emptyFileBools == NULL)
dir = 1;
else {
if (h->emptyFileBools[eindex])
dir = 0;
else
dir = 1;
eindex++;
}
if (entries[i].mode == 0) {
if (dir)
entries[i].mode = AE_IFDIR | 0777;
else
entries[i].mode = AE_IFREG | 0666;
} else if (dir &&
(entries[i].mode & AE_IFMT) != AE_IFDIR) {
entries[i].mode &= ~AE_IFMT;
entries[i].mode |= AE_IFDIR;
}
if ((entries[i].mode & AE_IFMT) == AE_IFDIR &&
entries[i].name_len >= 2 &&
(entries[i].utf16name[entries[i].name_len-2] != '/' ||
entries[i].utf16name[entries[i].name_len-1] != 0)) {
entries[i].utf16name[entries[i].name_len] = '/';
entries[i].utf16name[entries[i].name_len+1] = 0;
entries[i].name_len += 2;
}
entries[i].ssIndex = -1;
}
if (entries[i].attr & 0x01)
entries[i].mode &= ~0222;/* Read only. */
if ((entries[i].flg & HAS_STREAM) == 0 && indexInFolder == 0) {
/*
* The entry is an empty file or a directory file,
* those both have no contents.
*/
entries[i].folderIndex = -1;
continue;
}
if (indexInFolder == 0) {
for (;;) {
if (folderIndex >= si->ci.numFolders)
return (-1);
if (folders[folderIndex].numUnpackStreams)
break;
folderIndex++;
}
}
entries[i].folderIndex = folderIndex;
if ((entries[i].flg & HAS_STREAM) == 0)
continue;
indexInFolder++;
if (indexInFolder >= folders[folderIndex].numUnpackStreams) {
folderIndex++;
indexInFolder = 0;
}
}
return (0);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-125'], 'message': 'Issue 761: Heap overflow reading corrupted 7Zip files
The sample file that demonstrated this had multiple 'EmptyStream'
attributes. The first one ended up being used to calculate
certain statistics, then was overwritten by the second which
was incompatible with those statistics.
The fix here is to reject any header with multiple EmptyStream
attributes. While here, also reject headers with multiple
EmptyFile, AntiFile, Name, or Attributes markers.'</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: rtadv_read (struct thread *thread)
{
int sock;
int len;
u_char buf[RTADV_MSG_SIZE];
struct sockaddr_in6 from;
ifindex_t ifindex = 0;
int hoplimit = -1;
struct zebra_vrf *zvrf = THREAD_ARG (thread);
sock = THREAD_FD (thread);
zvrf->rtadv.ra_read = NULL;
/* Register myself. */
rtadv_event (zvrf, RTADV_READ, sock);
len = rtadv_recv_packet (sock, buf, BUFSIZ, &from, &ifindex, &hoplimit);
if (len < 0)
{
zlog_warn ("router solicitation recv failed: %s.", safe_strerror (errno));
return len;
}
rtadv_process_packet (buf, (unsigned)len, ifindex, hoplimit, zvrf->vrf_id);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'zebra: stack overrun in IPv6 RA receive code (CVE-2016-1245)
The IPv6 RA code also receives ICMPv6 RS and RA messages.
Unfortunately, by bad coding practice, the buffer size specified on
receiving such messages mixed up 2 constants that in fact have
different values.
The code itself has:
#define RTADV_MSG_SIZE 4096
While BUFSIZ is system-dependent, in my case (x86_64 glibc):
/usr/include/_G_config.h:#define _G_BUFSIZ 8192
/usr/include/libio.h:#define _IO_BUFSIZ _G_BUFSIZ
/usr/include/stdio.h:# define BUFSIZ _IO_BUFSIZ
FreeBSD, OpenBSD, NetBSD and Illumos are not affected, since all of them
have BUFSIZ == 1024.
As the latter is passed to the kernel on recvmsg(), it's possible to
overwrite 4kB of stack -- with ICMPv6 packets that can be globally sent
to any of the system's addresses (using fragmentation to get to 8k).
(The socket has filters installed limiting this to RS and RA packets,
but does not have a filter for source address or TTL.)
Issue discovered by trying to test other stuff, which randomly caused
the stack to be smaller than 8kB in that code location, which then
causes the kernel to report EFAULT (Bad address).
Signed-off-by: David Lamparter <[email protected]>
Reviewed-by: Donald Sharp <[email protected]>'</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: chunk_grow(chunk_t *chunk, size_t sz)
{
off_t offset;
size_t memlen_orig = chunk->memlen;
tor_assert(sz > chunk->memlen);
offset = chunk->data - chunk->mem;
chunk = tor_realloc(chunk, CHUNK_ALLOC_SIZE(sz));
chunk->memlen = sz;
chunk->data = chunk->mem + offset;
#ifdef DEBUG_CHUNK_ALLOC
tor_assert(chunk->DBG_alloc == CHUNK_ALLOC_SIZE(memlen_orig));
chunk->DBG_alloc = CHUNK_ALLOC_SIZE(sz);
#endif
total_bytes_allocated_in_chunks +=
CHUNK_ALLOC_SIZE(sz) - CHUNK_ALLOC_SIZE(memlen_orig);
return chunk;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'Add a one-word sentinel value of 0x0 at the end of each buf_t chunk
This helps protect against bugs where any part of a buf_t's memory
is passed to a function that expects a NUL-terminated input.
It also closes TROVE-2016-10-001 (aka bug 20384).'</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: xsltFormatNumberConversion(xsltDecimalFormatPtr self,
xmlChar *format,
double number,
xmlChar **result)
{
xmlXPathError status = XPATH_EXPRESSION_OK;
xmlBufferPtr buffer;
xmlChar *the_format, *prefix = NULL, *suffix = NULL;
xmlChar *nprefix, *nsuffix = NULL;
xmlChar pchar;
int prefix_length, suffix_length = 0, nprefix_length, nsuffix_length;
double scale;
int j, len;
int self_grouping_len;
xsltFormatNumberInfo format_info;
/*
* delayed_multiplier allows a 'trailing' percent or
* permille to be treated as suffix
*/
int delayed_multiplier = 0;
/* flag to show no -ve format present for -ve number */
char default_sign = 0;
/* flag to show error found, should use default format */
char found_error = 0;
if (xmlStrlen(format) <= 0) {
xsltTransformError(NULL, NULL, NULL,
"xsltFormatNumberConversion : "
"Invalid format (0-length)\n");
}
*result = NULL;
switch (xmlXPathIsInf(number)) {
case -1:
if (self->minusSign == NULL)
*result = xmlStrdup(BAD_CAST "-");
else
*result = xmlStrdup(self->minusSign);
/* no-break on purpose */
case 1:
if ((self == NULL) || (self->infinity == NULL))
*result = xmlStrcat(*result, BAD_CAST "Infinity");
else
*result = xmlStrcat(*result, self->infinity);
return(status);
default:
if (xmlXPathIsNaN(number)) {
if ((self == NULL) || (self->noNumber == NULL))
*result = xmlStrdup(BAD_CAST "NaN");
else
*result = xmlStrdup(self->noNumber);
return(status);
}
}
buffer = xmlBufferCreate();
if (buffer == NULL) {
return XPATH_MEMORY_ERROR;
}
format_info.integer_hash = 0;
format_info.integer_digits = 0;
format_info.frac_digits = 0;
format_info.frac_hash = 0;
format_info.group = -1;
format_info.multiplier = 1;
format_info.add_decimal = FALSE;
format_info.is_multiplier_set = FALSE;
format_info.is_negative_pattern = FALSE;
the_format = format;
/*
* First we process the +ve pattern to get percent / permille,
* as well as main format
*/
prefix = the_format;
prefix_length = xsltFormatNumberPreSuffix(self, &the_format, &format_info);
if (prefix_length < 0) {
found_error = 1;
goto OUTPUT_NUMBER;
}
/*
* Here we process the "number" part of the format. It gets
* a little messy because of the percent/per-mille - if that
* appears at the end, it may be part of the suffix instead
* of part of the number, so the variable delayed_multiplier
* is used to handle it
*/
self_grouping_len = xmlStrlen(self->grouping);
while ((*the_format != 0) &&
(xsltUTF8Charcmp(the_format, self->decimalPoint) != 0) &&
(xsltUTF8Charcmp(the_format, self->patternSeparator) != 0)) {
if (delayed_multiplier != 0) {
format_info.multiplier = delayed_multiplier;
format_info.is_multiplier_set = TRUE;
delayed_multiplier = 0;
}
if (xsltUTF8Charcmp(the_format, self->digit) == 0) {
if (format_info.integer_digits > 0) {
found_error = 1;
goto OUTPUT_NUMBER;
}
format_info.integer_hash++;
if (format_info.group >= 0)
format_info.group++;
} else if (xsltUTF8Charcmp(the_format, self->zeroDigit) == 0) {
format_info.integer_digits++;
if (format_info.group >= 0)
format_info.group++;
} else if ((self_grouping_len > 0) &&
(!xmlStrncmp(the_format, self->grouping, self_grouping_len))) {
/* Reset group count */
format_info.group = 0;
the_format += self_grouping_len;
continue;
} else if (xsltUTF8Charcmp(the_format, self->percent) == 0) {
if (format_info.is_multiplier_set) {
found_error = 1;
goto OUTPUT_NUMBER;
}
delayed_multiplier = 100;
} else if (xsltUTF8Charcmp(the_format, self->permille) == 0) {
if (format_info.is_multiplier_set) {
found_error = 1;
goto OUTPUT_NUMBER;
}
delayed_multiplier = 1000;
} else
break; /* while */
if ((len=xsltUTF8Size(the_format)) < 1) {
found_error = 1;
goto OUTPUT_NUMBER;
}
the_format += len;
}
/* We have finished the integer part, now work on fraction */
if (xsltUTF8Charcmp(the_format, self->decimalPoint) == 0) {
format_info.add_decimal = TRUE;
the_format += xsltUTF8Size(the_format); /* Skip over the decimal */
}
while (*the_format != 0) {
if (xsltUTF8Charcmp(the_format, self->zeroDigit) == 0) {
if (format_info.frac_hash != 0) {
found_error = 1;
goto OUTPUT_NUMBER;
}
format_info.frac_digits++;
} else if (xsltUTF8Charcmp(the_format, self->digit) == 0) {
format_info.frac_hash++;
} else if (xsltUTF8Charcmp(the_format, self->percent) == 0) {
if (format_info.is_multiplier_set) {
found_error = 1;
goto OUTPUT_NUMBER;
}
delayed_multiplier = 100;
if ((len = xsltUTF8Size(the_format)) < 1) {
found_error = 1;
goto OUTPUT_NUMBER;
}
the_format += len;
continue; /* while */
} else if (xsltUTF8Charcmp(the_format, self->permille) == 0) {
if (format_info.is_multiplier_set) {
found_error = 1;
goto OUTPUT_NUMBER;
}
delayed_multiplier = 1000;
if ((len = xsltUTF8Size(the_format)) < 1) {
found_error = 1;
goto OUTPUT_NUMBER;
}
the_format += len;
continue; /* while */
} else if (xsltUTF8Charcmp(the_format, self->grouping) != 0) {
break; /* while */
}
if ((len = xsltUTF8Size(the_format)) < 1) {
found_error = 1;
goto OUTPUT_NUMBER;
}
the_format += len;
if (delayed_multiplier != 0) {
format_info.multiplier = delayed_multiplier;
delayed_multiplier = 0;
format_info.is_multiplier_set = TRUE;
}
}
/*
* If delayed_multiplier is set after processing the
* "number" part, should be in suffix
*/
if (delayed_multiplier != 0) {
the_format -= len;
delayed_multiplier = 0;
}
suffix = the_format;
suffix_length = xsltFormatNumberPreSuffix(self, &the_format, &format_info);
if ( (suffix_length < 0) ||
((*the_format != 0) &&
(xsltUTF8Charcmp(the_format, self->patternSeparator) != 0)) ) {
found_error = 1;
goto OUTPUT_NUMBER;
}
/*
* We have processed the +ve prefix, number part and +ve suffix.
* If the number is -ve, we must substitute the -ve prefix / suffix
*/
if (number < 0) {
/*
* Note that j is the number of UTF8 chars before the separator,
* not the number of bytes! (bug 151975)
*/
j = xmlUTF8Strloc(format, self->patternSeparator);
if (j < 0) {
/* No -ve pattern present, so use default signing */
default_sign = 1;
}
else {
/* Skip over pattern separator (accounting for UTF8) */
the_format = (xmlChar *)xmlUTF8Strpos(format, j + 1);
/*
* Flag changes interpretation of percent/permille
* in -ve pattern
*/
format_info.is_negative_pattern = TRUE;
format_info.is_multiplier_set = FALSE;
/* First do the -ve prefix */
nprefix = the_format;
nprefix_length = xsltFormatNumberPreSuffix(self,
&the_format, &format_info);
if (nprefix_length<0) {
found_error = 1;
goto OUTPUT_NUMBER;
}
while (*the_format != 0) {
if ( (xsltUTF8Charcmp(the_format, (self)->percent) == 0) ||
(xsltUTF8Charcmp(the_format, (self)->permille)== 0) ) {
if (format_info.is_multiplier_set) {
found_error = 1;
goto OUTPUT_NUMBER;
}
format_info.is_multiplier_set = TRUE;
delayed_multiplier = 1;
}
else if (IS_SPECIAL(self, the_format))
delayed_multiplier = 0;
else
break; /* while */
if ((len = xsltUTF8Size(the_format)) < 1) {
found_error = 1;
goto OUTPUT_NUMBER;
}
the_format += len;
}
if (delayed_multiplier != 0) {
format_info.is_multiplier_set = FALSE;
the_format -= len;
}
/* Finally do the -ve suffix */
if (*the_format != 0) {
nsuffix = the_format;
nsuffix_length = xsltFormatNumberPreSuffix(self,
&the_format, &format_info);
if (nsuffix_length < 0) {
found_error = 1;
goto OUTPUT_NUMBER;
}
}
else
nsuffix_length = 0;
if (*the_format != 0) {
found_error = 1;
goto OUTPUT_NUMBER;
}
/*
* Here's another Java peculiarity:
* if -ve prefix/suffix == +ve ones, discard & use default
*/
if ((nprefix_length != prefix_length) ||
(nsuffix_length != suffix_length) ||
((nprefix_length > 0) &&
(xmlStrncmp(nprefix, prefix, prefix_length) !=0 )) ||
((nsuffix_length > 0) &&
(xmlStrncmp(nsuffix, suffix, suffix_length) !=0 ))) {
prefix = nprefix;
prefix_length = nprefix_length;
suffix = nsuffix;
suffix_length = nsuffix_length;
} /* else {
default_sign = 1;
}
*/
}
}
OUTPUT_NUMBER:
if (found_error != 0) {
xsltTransformError(NULL, NULL, NULL,
"xsltFormatNumberConversion : "
"error in format string '%s', using default\n", format);
default_sign = (number < 0.0) ? 1 : 0;
prefix_length = suffix_length = 0;
format_info.integer_hash = 0;
format_info.integer_digits = 1;
format_info.frac_digits = 1;
format_info.frac_hash = 4;
format_info.group = -1;
format_info.multiplier = 1;
format_info.add_decimal = TRUE;
}
/* Ready to output our number. First see if "default sign" is required */
if (default_sign != 0)
xmlBufferAdd(buffer, self->minusSign, xsltUTF8Size(self->minusSign));
/* Put the prefix into the buffer */
for (j = 0; j < prefix_length; j++) {
if ((pchar = *prefix++) == SYMBOL_QUOTE) {
len = xsltUTF8Size(prefix);
xmlBufferAdd(buffer, prefix, len);
prefix += len;
j += len - 1; /* length of symbol less length of quote */
} else
xmlBufferAdd(buffer, &pchar, 1);
}
/* Next do the integer part of the number */
number = fabs(number) * (double)format_info.multiplier;
scale = pow(10.0, (double)(format_info.frac_digits + format_info.frac_hash));
number = floor((scale * number + 0.5)) / scale;
if ((self->grouping != NULL) &&
(self->grouping[0] != 0)) {
len = xmlStrlen(self->grouping);
pchar = xsltGetUTF8Char(self->grouping, &len);
xsltNumberFormatDecimal(buffer, floor(number), self->zeroDigit[0],
format_info.integer_digits,
format_info.group,
pchar, len);
} else
xsltNumberFormatDecimal(buffer, floor(number), self->zeroDigit[0],
format_info.integer_digits,
format_info.group,
',', 1);
/* Special case: java treats '.#' like '.0', '.##' like '.0#', etc. */
if ((format_info.integer_digits + format_info.integer_hash +
format_info.frac_digits == 0) && (format_info.frac_hash > 0)) {
++format_info.frac_digits;
--format_info.frac_hash;
}
/* Add leading zero, if required */
if ((floor(number) == 0) &&
(format_info.integer_digits + format_info.frac_digits == 0)) {
xmlBufferAdd(buffer, self->zeroDigit, xsltUTF8Size(self->zeroDigit));
}
/* Next the fractional part, if required */
if (format_info.frac_digits + format_info.frac_hash == 0) {
if (format_info.add_decimal)
xmlBufferAdd(buffer, self->decimalPoint,
xsltUTF8Size(self->decimalPoint));
}
else {
number -= floor(number);
if ((number != 0) || (format_info.frac_digits != 0)) {
xmlBufferAdd(buffer, self->decimalPoint,
xsltUTF8Size(self->decimalPoint));
number = floor(scale * number + 0.5);
for (j = format_info.frac_hash; j > 0; j--) {
if (fmod(number, 10.0) >= 1.0)
break; /* for */
number /= 10.0;
}
xsltNumberFormatDecimal(buffer, floor(number), self->zeroDigit[0],
format_info.frac_digits + j,
0, 0, 0);
}
}
/* Put the suffix into the buffer */
for (j = 0; j < suffix_length; j++) {
if ((pchar = *suffix++) == SYMBOL_QUOTE) {
len = xsltUTF8Size(suffix);
xmlBufferAdd(buffer, suffix, len);
suffix += len;
j += len - 1; /* length of symbol less length of escape */
} else
xmlBufferAdd(buffer, &pchar, 1);
}
*result = xmlStrdup(xmlBufferContent(buffer));
xmlBufferFree(buffer);
return status;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix heap overread in xsltFormatNumberConversion
An empty decimal-separator could cause a heap overread. This can be
exploited to leak a couple of bytes after the buffer that holds the
pattern string.
Found with afl-fuzz and ASan.'</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 hash_accept(struct socket *sock, struct socket *newsock, int flags)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct hash_ctx *ctx = ask->private;
struct ahash_request *req = &ctx->req;
char state[crypto_ahash_statesize(crypto_ahash_reqtfm(req))];
struct sock *sk2;
struct alg_sock *ask2;
struct hash_ctx *ctx2;
int err;
err = crypto_ahash_export(req, state);
if (err)
return err;
err = af_alg_accept(ask->parent, newsock);
if (err)
return err;
sk2 = newsock->sk;
ask2 = alg_sk(sk2);
ctx2 = ask2->private;
ctx2->more = 1;
err = crypto_ahash_import(&ctx2->req, state);
if (err) {
sock_orphan(sk2);
sock_put(sk2);
}
return err;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'crypto: algif_hash - Only export and import on sockets with data
The hash_accept call fails to work on sockets that have not received
any data. For some algorithm implementations it may cause crashes.
This patch fixes this by ensuring that we only export and import on
sockets that have received data.
Cc: [email protected]
Reported-by: Harsh Jain <[email protected]>
Signed-off-by: Herbert Xu <[email protected]>
Tested-by: Stephan Mueller <[email protected]>'</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: jp2_box_t *jp2_box_get(jas_stream_t *in)
{
jp2_box_t *box;
jp2_boxinfo_t *boxinfo;
jas_stream_t *tmpstream;
uint_fast32_t len;
uint_fast64_t extlen;
bool dataflag;
box = 0;
tmpstream = 0;
if (!(box = jas_malloc(sizeof(jp2_box_t)))) {
goto error;
}
box->ops = &jp2_boxinfo_unk.ops;
if (jp2_getuint32(in, &len) || jp2_getuint32(in, &box->type)) {
goto error;
}
boxinfo = jp2_boxinfolookup(box->type);
box->info = boxinfo;
box->ops = &boxinfo->ops;
box->len = len;
if (box->len == 1) {
if (jp2_getuint64(in, &extlen)) {
goto error;
}
if (extlen > 0xffffffffUL) {
jas_eprintf("warning: cannot handle large 64-bit box length\n");
extlen = 0xffffffffUL;
}
box->len = extlen;
box->datalen = extlen - JP2_BOX_HDRLEN(true);
} else {
box->datalen = box->len - JP2_BOX_HDRLEN(false);
}
if (box->len != 0 && box->len < 8) {
goto error;
}
dataflag = !(box->info->flags & (JP2_BOX_SUPER | JP2_BOX_NODATA));
if (dataflag) {
if (!(tmpstream = jas_stream_memopen(0, 0))) {
goto error;
}
if (jas_stream_copy(tmpstream, in, box->datalen)) {
jas_eprintf("cannot copy box data\n");
goto error;
}
jas_stream_rewind(tmpstream);
if (box->ops->getdata) {
if ((*box->ops->getdata)(box, tmpstream)) {
jas_eprintf("cannot parse box data\n");
goto error;
}
}
jas_stream_close(tmpstream);
}
if (jas_getdbglevel() >= 1) {
jp2_box_dump(box, stderr);
}
return box;
error:
if (box) {
jp2_box_destroy(box);
}
if (tmpstream) {
jas_stream_close(tmpstream);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476', 'CWE-125'], 'message': 'Fixed a bug that resulted in the destruction of JP2 box data that had never
been constructed in the first place.'</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: jp2_box_t *jp2_box_get(jas_stream_t *in)
{
jp2_box_t *box;
jp2_boxinfo_t *boxinfo;
jas_stream_t *tmpstream;
uint_fast32_t len;
uint_fast64_t extlen;
bool dataflag;
box = 0;
tmpstream = 0;
if (!(box = jas_malloc(sizeof(jp2_box_t)))) {
goto error;
}
box->ops = &jp2_boxinfo_unk.ops;
if (jp2_getuint32(in, &len) || jp2_getuint32(in, &box->type)) {
goto error;
}
boxinfo = jp2_boxinfolookup(box->type);
box->info = boxinfo;
box->ops = &boxinfo->ops;
box->len = len;
JAS_DBGLOG(10, (
"preliminary processing of JP2 box: type=%c%s%c (0x%08x); length=%d\n",
'"', boxinfo->name, '"', box->type, box->len
));
if (box->len == 1) {
if (jp2_getuint64(in, &extlen)) {
goto error;
}
if (extlen > 0xffffffffUL) {
jas_eprintf("warning: cannot handle large 64-bit box length\n");
extlen = 0xffffffffUL;
}
box->len = extlen;
box->datalen = extlen - JP2_BOX_HDRLEN(true);
} else {
box->datalen = box->len - JP2_BOX_HDRLEN(false);
}
if (box->len != 0 && box->len < 8) {
goto error;
}
dataflag = !(box->info->flags & (JP2_BOX_SUPER | JP2_BOX_NODATA));
if (dataflag) {
if (!(tmpstream = jas_stream_memopen(0, 0))) {
goto error;
}
if (jas_stream_copy(tmpstream, in, box->datalen)) {
// Mark the box data as never having been constructed
// so that we will not errantly attempt to destroy it later.
box->ops = &jp2_boxinfo_unk.ops;
jas_eprintf("cannot copy box data\n");
goto error;
}
jas_stream_rewind(tmpstream);
if (box->ops->getdata) {
if ((*box->ops->getdata)(box, tmpstream)) {
jas_eprintf("cannot parse box data\n");
goto error;
}
}
jas_stream_close(tmpstream);
}
if (jas_getdbglevel() >= 1) {
jp2_box_dump(box, stderr);
}
return box;
error:
if (box) {
jp2_box_destroy(box);
}
if (tmpstream) {
jas_stream_close(tmpstream);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'Fixed another problem with incorrect cleanup of JP2 box data upon error.'</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 *jas_malloc(size_t size)
{
void *result;
jas_mb_t *mb;
size_t ext_size;
size_t mem;
JAS_DBGLOG(100, ("jas_malloc(%zu)\n", size));
#if defined(JAS_MALLOC_RETURN_NULL_PTR_FOR_ZERO_SIZE)
if (!size) {
return 0;
}
#endif
if (!jas_safe_size_add(size, JAS_MB_SIZE, &ext_size)) {
jas_eprintf("requested memory size is too large\n");
result = 0;
mb = 0;
} else if (!jas_safe_size_add(jas_mem, size, &mem) || mem > jas_max_mem) {
jas_eprintf("maximum memory limit would be exceeded\n");
result = 0;
mb = 0;
} else {
JAS_DBGLOG(100, ("jas_malloc: ext_size=%zu\n", ext_size));
if ((mb = malloc(ext_size))) {
result = jas_mb_get_data(mb);
mb->size = size;
jas_mem = mem;
} else {
result = 0;
}
}
JAS_DBGLOG(99, ("jas_malloc(%zu) -> %p (mb=%p)\n", size, result, mb));
JAS_DBGLOG(102, ("max_mem=%zu; mem=%zu\n", jas_max_mem, jas_mem));
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-190'], 'message': 'Fixed an integer overflow problem.'</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: jas_matrix_t *jas_matrix_create(int numrows, int numcols)
{
jas_matrix_t *matrix;
int i;
if (numrows < 0 || numcols < 0) {
return 0;
}
if (!(matrix = jas_malloc(sizeof(jas_matrix_t)))) {
return 0;
}
matrix->flags_ = 0;
matrix->numrows_ = numrows;
matrix->numcols_ = numcols;
matrix->rows_ = 0;
matrix->maxrows_ = numrows;
matrix->data_ = 0;
matrix->datasize_ = numrows * numcols;
if (matrix->maxrows_ > 0) {
if (!(matrix->rows_ = jas_alloc2(matrix->maxrows_,
sizeof(jas_seqent_t *)))) {
jas_matrix_destroy(matrix);
return 0;
}
}
if (matrix->datasize_ > 0) {
if (!(matrix->data_ = jas_alloc2(matrix->datasize_,
sizeof(jas_seqent_t)))) {
jas_matrix_destroy(matrix);
return 0;
}
}
for (i = 0; i < numrows; ++i) {
matrix->rows_[i] = &matrix->data_[i * matrix->numcols_];
}
for (i = 0; i < matrix->datasize_; ++i) {
matrix->data_[i] = 0;
}
matrix->xstart_ = 0;
matrix->ystart_ = 0;
matrix->xend_ = matrix->numcols_;
matrix->yend_ = matrix->numrows_;
return matrix;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-190'], 'message': 'Fixed an integer overflow problem.'</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 jpc_dec_tilefini(jpc_dec_t *dec, jpc_dec_tile_t *tile)
{
jpc_dec_tcomp_t *tcomp;
int compno;
int bandno;
int rlvlno;
jpc_dec_band_t *band;
jpc_dec_rlvl_t *rlvl;
int prcno;
jpc_dec_prc_t *prc;
jpc_dec_seg_t *seg;
jpc_dec_cblk_t *cblk;
int cblkno;
if (tile->tcomps) {
for (compno = 0, tcomp = tile->tcomps; compno < dec->numcomps;
++compno, ++tcomp) {
for (rlvlno = 0, rlvl = tcomp->rlvls; rlvlno < tcomp->numrlvls;
++rlvlno, ++rlvl) {
if (!rlvl->bands) {
continue;
}
for (bandno = 0, band = rlvl->bands; bandno < rlvl->numbands;
++bandno, ++band) {
if (band->prcs) {
for (prcno = 0, prc = band->prcs; prcno <
rlvl->numprcs; ++prcno, ++prc) {
if (!prc->cblks) {
continue;
}
for (cblkno = 0, cblk = prc->cblks; cblkno <
prc->numcblks; ++cblkno, ++cblk) {
while (cblk->segs.head) {
seg = cblk->segs.head;
jpc_seglist_remove(&cblk->segs, seg);
jpc_seg_destroy(seg);
}
jas_matrix_destroy(cblk->data);
if (cblk->mqdec) {
jpc_mqdec_destroy(cblk->mqdec);
}
if (cblk->nulldec) {
jpc_bitstream_close(cblk->nulldec);
}
if (cblk->flags) {
jas_matrix_destroy(cblk->flags);
}
}
if (prc->incltagtree) {
jpc_tagtree_destroy(prc->incltagtree);
}
if (prc->numimsbstagtree) {
jpc_tagtree_destroy(prc->numimsbstagtree);
}
if (prc->cblks) {
jas_free(prc->cblks);
}
}
}
if (band->data) {
jas_matrix_destroy(band->data);
}
if (band->prcs) {
jas_free(band->prcs);
}
}
if (rlvl->bands) {
jas_free(rlvl->bands);
}
}
if (tcomp->rlvls) {
jas_free(tcomp->rlvls);
}
if (tcomp->data) {
jas_matrix_destroy(tcomp->data);
}
if (tcomp->tsfb) {
jpc_tsfb_destroy(tcomp->tsfb);
}
}
}
if (tile->cp) {
jpc_dec_cp_destroy(tile->cp);
tile->cp = 0;
}
if (tile->tcomps) {
jas_free(tile->tcomps);
tile->tcomps = 0;
}
if (tile->pi) {
jpc_pi_destroy(tile->pi);
tile->pi = 0;
}
if (tile->pkthdrstream) {
jas_stream_close(tile->pkthdrstream);
tile->pkthdrstream = 0;
}
if (tile->pptstab) {
jpc_ppxstab_destroy(tile->pptstab);
tile->pptstab = 0;
}
tile->state = JPC_TILE_DONE;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'The member (pi) in tiles was not properly initialized.
This is now corrected.
Also, each tile is now only cleaned up once.'</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 jpc_dec_process_eoc(jpc_dec_t *dec, jpc_ms_t *ms)
{
int tileno;
jpc_dec_tile_t *tile;
/* Eliminate compiler warnings about unused variables. */
ms = 0;
for (tileno = 0, tile = dec->tiles; tileno < dec->numtiles; ++tileno,
++tile) {
if (tile->state == JPC_TILE_ACTIVE) {
if (jpc_dec_tiledecode(dec, tile)) {
return -1;
}
}
jpc_dec_tilefini(dec, tile);
}
/* We are done processing the code stream. */
dec->state = JPC_MT;
return 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'The member (pi) in tiles was not properly initialized.
This is now corrected.
Also, each tile is now only cleaned up once.'</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 main(int argc, char **argv)
{
int fmtid;
int id;
char *infile;
jas_stream_t *instream;
jas_image_t *image;
int width;
int height;
int depth;
int numcmpts;
int verbose;
char *fmtname;
int debug;
if (jas_init()) {
abort();
}
cmdname = argv[0];
infile = 0;
verbose = 0;
debug = 0;
/* Parse the command line options. */
while ((id = jas_getopt(argc, argv, opts)) >= 0) {
switch (id) {
case OPT_VERBOSE:
verbose = 1;
break;
case OPT_VERSION:
printf("%s\n", JAS_VERSION);
exit(EXIT_SUCCESS);
break;
case OPT_DEBUG:
debug = atoi(jas_optarg);
break;
case OPT_INFILE:
infile = jas_optarg;
break;
case OPT_HELP:
default:
usage();
break;
}
}
jas_setdbglevel(debug);
/* Open the image file. */
if (infile) {
/* The image is to be read from a file. */
if (!(instream = jas_stream_fopen(infile, "rb"))) {
fprintf(stderr, "cannot open input image file %s\n", infile);
exit(EXIT_FAILURE);
}
} else {
/* The image is to be read from standard input. */
if (!(instream = jas_stream_fdopen(0, "rb"))) {
fprintf(stderr, "cannot open standard input\n");
exit(EXIT_FAILURE);
}
}
if ((fmtid = jas_image_getfmt(instream)) < 0) {
fprintf(stderr, "unknown image format\n");
}
/* Decode the image. */
if (!(image = jas_image_decode(instream, fmtid, 0))) {
jas_stream_close(instream);
fprintf(stderr, "cannot load image\n");
return EXIT_FAILURE;
}
/* Close the image file. */
jas_stream_close(instream);
numcmpts = jas_image_numcmpts(image);
width = jas_image_cmptwidth(image, 0);
height = jas_image_cmptheight(image, 0);
depth = jas_image_cmptprec(image, 0);
if (!(fmtname = jas_image_fmttostr(fmtid))) {
abort();
}
printf("%s %d %d %d %d %ld\n", fmtname, numcmpts, width, height, depth, (long) jas_image_rawsize(image));
jas_image_destroy(image);
jas_image_clearfmts();
return EXIT_SUCCESS;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'A new experimental memory allocator has been introduced. The allocator
is experimental in the sense that its API is not considered stable and
the allocator may change or disappear entirely in future versions of
the code. This new allocator tracks how much memory is being used by
jas_malloc and friends. A maximum upper bound on the memory usage can be
set via the experimental API provided and a default value can be set at
build time as well. Such functionality may be useful in run-time
environments where the user wants to be able to limit the amount of
memory used by JasPer. This allocator is not used by default.
Note: This feature needs C11 functionality.
Note: The memory allocator is not thread safe in its current form.
A new --memory-limit CLI option has been added to the jasper, imginfo,
imgcmp, and jiv programs. The option is only available when the code is
built with the new memory allocator.
The support for my old debug memory allocator from the 1990s has been
purged from the code. The debug memory allocator is probably not
a very useful thing with the advent of GCC/Clang code sanitizers.
The safe size_t integer functions no longer set their result upon failure.
A safe subtract operation was also added.'</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 jas_image_cmpt_t *jas_image_cmpt_create(uint_fast32_t tlx,
uint_fast32_t tly, uint_fast32_t hstep, uint_fast32_t vstep,
uint_fast32_t width, uint_fast32_t height, uint_fast16_t depth, bool sgnd,
uint_fast32_t inmem)
{
jas_image_cmpt_t *cmpt;
size_t size;
if (!(cmpt = jas_malloc(sizeof(jas_image_cmpt_t)))) {
goto error;
}
cmpt->type_ = JAS_IMAGE_CT_UNKNOWN;
cmpt->tlx_ = tlx;
cmpt->tly_ = tly;
cmpt->hstep_ = hstep;
cmpt->vstep_ = vstep;
cmpt->width_ = width;
cmpt->height_ = height;
cmpt->prec_ = depth;
cmpt->sgnd_ = sgnd;
cmpt->stream_ = 0;
cmpt->cps_ = (depth + 7) / 8;
// size = cmpt->width_ * cmpt->height_ * cmpt->cps_;
if (!jas_safe_size_mul(cmpt->width_, cmpt->height_, &size) ||
!jas_safe_size_mul(size, cmpt->cps_, &size)) {
goto error;
}
cmpt->stream_ = (inmem) ? jas_stream_memopen(0, size) :
jas_stream_tmpfile();
if (!cmpt->stream_) {
goto error;
}
/* Zero the component data. This isn't necessary, but it is
convenient for debugging purposes. */
/* Note: conversion of size - 1 to long can overflow */
if (jas_stream_seek(cmpt->stream_, size - 1, SEEK_SET) < 0 ||
jas_stream_putc(cmpt->stream_, 0) == EOF ||
jas_stream_seek(cmpt->stream_, 0, SEEK_SET) < 0) {
goto error;
}
return cmpt;
error:
if (cmpt) {
jas_image_cmpt_destroy(cmpt);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'A new experimental memory allocator has been introduced. The allocator
is experimental in the sense that its API is not considered stable and
the allocator may change or disappear entirely in future versions of
the code. This new allocator tracks how much memory is being used by
jas_malloc and friends. A maximum upper bound on the memory usage can be
set via the experimental API provided and a default value can be set at
build time as well. Such functionality may be useful in run-time
environments where the user wants to be able to limit the amount of
memory used by JasPer. This allocator is not used by default.
Note: This feature needs C11 functionality.
Note: The memory allocator is not thread safe in its current form.
A new --memory-limit CLI option has been added to the jasper, imginfo,
imgcmp, and jiv programs. The option is only available when the code is
built with the new memory allocator.
The support for my old debug memory allocator from the 1990s has been
purged from the code. The debug memory allocator is probably not
a very useful thing with the advent of GCC/Clang code sanitizers.
The safe size_t integer functions no longer set their result upon failure.
A safe subtract operation was also added.'</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 main(int argc, char **argv)
{
char *origpath;
char *reconpath;
int verbose;
char *metricname;
int metric;
int id;
jas_image_t *origimage;
jas_image_t *reconimage;
jas_matrix_t *origdata;
jas_matrix_t *recondata;
jas_image_t *diffimage;
jas_stream_t *diffstream;
int width;
int height;
int depth;
int numcomps;
double d;
double maxdist;
double mindist;
int compno;
jas_stream_t *origstream;
jas_stream_t *reconstream;
char *diffpath;
int maxonly;
int minonly;
int fmtid;
verbose = 0;
origpath = 0;
reconpath = 0;
metricname = 0;
metric = metricid_none;
diffpath = 0;
maxonly = 0;
minonly = 0;
if (jas_init()) {
abort();
}
cmdname = argv[0];
/* Parse the command line options. */
while ((id = jas_getopt(argc, argv, opts)) >= 0) {
switch (id) {
case OPT_MAXONLY:
maxonly = 1;
break;
case OPT_MINONLY:
minonly = 1;
break;
case OPT_METRIC:
metricname = jas_optarg;
break;
case OPT_ORIG:
origpath = jas_optarg;
break;
case OPT_RECON:
reconpath = jas_optarg;
break;
case OPT_VERBOSE:
verbose = 1;
break;
case OPT_DIFFIMAGE:
diffpath = jas_optarg;
break;
case OPT_VERSION:
printf("%s\n", JAS_VERSION);
exit(EXIT_SUCCESS);
break;
case OPT_HELP:
default:
usage();
break;
}
}
if (verbose) {
cmdinfo();
}
/* Ensure that files are given for both the original and reconstructed
images. */
if (!origpath || !reconpath) {
usage();
}
/* If a metric was specified, process it. */
if (metricname) {
if ((metric = (jas_taginfo_nonull(jas_taginfos_lookup(metrictab,
metricname))->id)) < 0) {
usage();
}
}
/* Open the original image file. */
if (!(origstream = jas_stream_fopen(origpath, "rb"))) {
fprintf(stderr, "cannot open %s\n", origpath);
return EXIT_FAILURE;
}
/* Open the reconstructed image file. */
if (!(reconstream = jas_stream_fopen(reconpath, "rb"))) {
fprintf(stderr, "cannot open %s\n", reconpath);
return EXIT_FAILURE;
}
/* Decode the original image. */
if (!(origimage = jas_image_decode(origstream, -1, 0))) {
fprintf(stderr, "cannot load original image\n");
return EXIT_FAILURE;
}
/* Decoder the reconstructed image. */
if (!(reconimage = jas_image_decode(reconstream, -1, 0))) {
fprintf(stderr, "cannot load reconstructed image\n");
return EXIT_FAILURE;
}
/* Close the original image file. */
jas_stream_close(origstream);
/* Close the reconstructed image file. */
jas_stream_close(reconstream);
/* Ensure that both images have the same number of components. */
numcomps = jas_image_numcmpts(origimage);
if (jas_image_numcmpts(reconimage) != numcomps) {
fprintf(stderr, "number of components differ\n");
return EXIT_FAILURE;
}
/* Compute the difference for each component. */
maxdist = 0;
mindist = FLT_MAX;
for (compno = 0; compno < numcomps; ++compno) {
width = jas_image_cmptwidth(origimage, compno);
height = jas_image_cmptheight(origimage, compno);
depth = jas_image_cmptprec(origimage, compno);
if (jas_image_cmptwidth(reconimage, compno) != width ||
jas_image_cmptheight(reconimage, compno) != height) {
fprintf(stderr, "image dimensions differ\n");
return EXIT_FAILURE;
}
if (jas_image_cmptprec(reconimage, compno) != depth) {
fprintf(stderr, "precisions differ\n");
return EXIT_FAILURE;
}
if (!(origdata = jas_matrix_create(height, width))) {
fprintf(stderr, "internal error\n");
return EXIT_FAILURE;
}
if (!(recondata = jas_matrix_create(height, width))) {
fprintf(stderr, "internal error\n");
return EXIT_FAILURE;
}
if (jas_image_readcmpt(origimage, compno, 0, 0, width, height,
origdata)) {
fprintf(stderr, "cannot read component data\n");
return EXIT_FAILURE;
}
if (jas_image_readcmpt(reconimage, compno, 0, 0, width, height,
recondata)) {
fprintf(stderr, "cannot read component data\n");
return EXIT_FAILURE;
}
if (diffpath) {
if (!(diffstream = jas_stream_fopen(diffpath, "rwb"))) {
fprintf(stderr, "cannot open diff stream\n");
return EXIT_FAILURE;
}
if (!(diffimage = makediffimage(origdata, recondata))) {
fprintf(stderr, "cannot make diff image\n");
return EXIT_FAILURE;
}
fmtid = jas_image_strtofmt("pnm");
if (jas_image_encode(diffimage, diffstream, fmtid, 0)) {
fprintf(stderr, "cannot save\n");
return EXIT_FAILURE;
}
jas_stream_close(diffstream);
jas_image_destroy(diffimage);
}
if (metric != metricid_none) {
d = getdistortion(origdata, recondata, depth, metric);
if (d > maxdist) {
maxdist = d;
}
if (d < mindist) {
mindist = d;
}
if (!maxonly && !minonly) {
if (metric == metricid_pae || metric == metricid_equal) {
printf("%ld\n", (long) ceil(d));
} else {
printf("%f\n", d);
}
}
}
jas_matrix_destroy(origdata);
jas_matrix_destroy(recondata);
}
if (metric != metricid_none && (maxonly || minonly)) {
if (maxonly) {
d = maxdist;
} else if (minonly) {
d = mindist;
} else {
abort();
}
if (metric == metricid_pae || metric == metricid_equal) {
printf("%ld\n", (long) ceil(d));
} else {
printf("%f\n", d);
}
}
jas_image_destroy(origimage);
jas_image_destroy(reconimage);
jas_image_clearfmts();
return EXIT_SUCCESS;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'A new experimental memory allocator has been introduced. The allocator
is experimental in the sense that its API is not considered stable and
the allocator may change or disappear entirely in future versions of
the code. This new allocator tracks how much memory is being used by
jas_malloc and friends. A maximum upper bound on the memory usage can be
set via the experimental API provided and a default value can be set at
build time as well. Such functionality may be useful in run-time
environments where the user wants to be able to limit the amount of
memory used by JasPer. This allocator is not used by default.
Note: This feature needs C11 functionality.
Note: The memory allocator is not thread safe in its current form.
A new --memory-limit CLI option has been added to the jasper, imginfo,
imgcmp, and jiv programs. The option is only available when the code is
built with the new memory allocator.
The support for my old debug memory allocator from the 1990s has been
purged from the code. The debug memory allocator is probably not
a very useful thing with the advent of GCC/Clang code sanitizers.
The safe size_t integer functions no longer set their result upon failure.
A safe subtract operation was also added.'</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: inline static bool jas_safe_size_add(size_t x, size_t y, size_t *result)
{
if (y > SIZE_MAX - x) {
*result = 0;
return false;
}
*result = x + y;
return true;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'A new experimental memory allocator has been introduced. The allocator
is experimental in the sense that its API is not considered stable and
the allocator may change or disappear entirely in future versions of
the code. This new allocator tracks how much memory is being used by
jas_malloc and friends. A maximum upper bound on the memory usage can be
set via the experimental API provided and a default value can be set at
build time as well. Such functionality may be useful in run-time
environments where the user wants to be able to limit the amount of
memory used by JasPer. This allocator is not used by default.
Note: This feature needs C11 functionality.
Note: The memory allocator is not thread safe in its current form.
A new --memory-limit CLI option has been added to the jasper, imginfo,
imgcmp, and jiv programs. The option is only available when the code is
built with the new memory allocator.
The support for my old debug memory allocator from the 1990s has been
purged from the code. The debug memory allocator is probably not
a very useful thing with the advent of GCC/Clang code sanitizers.
The safe size_t integer functions no longer set their result upon failure.
A safe subtract operation was also added.'</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: cmdopts_t *cmdopts_parse(int argc, char **argv)
{
typedef enum {
CMDOPT_HELP = 0,
CMDOPT_VERBOSE,
CMDOPT_INFILE,
CMDOPT_INFMT,
CMDOPT_INOPT,
CMDOPT_OUTFILE,
CMDOPT_OUTFMT,
CMDOPT_OUTOPT,
CMDOPT_VERSION,
CMDOPT_DEBUG,
CMDOPT_CMPTNO,
CMDOPT_SRGB
} cmdoptid_t;
static jas_opt_t cmdoptions[] = {
{CMDOPT_HELP, "help", 0},
{CMDOPT_VERBOSE, "verbose", 0},
{CMDOPT_INFILE, "input", JAS_OPT_HASARG},
{CMDOPT_INFILE, "f", JAS_OPT_HASARG},
{CMDOPT_INFMT, "input-format", JAS_OPT_HASARG},
{CMDOPT_INFMT, "t", JAS_OPT_HASARG},
{CMDOPT_INOPT, "input-option", JAS_OPT_HASARG},
{CMDOPT_INOPT, "o", JAS_OPT_HASARG},
{CMDOPT_OUTFILE, "output", JAS_OPT_HASARG},
{CMDOPT_OUTFILE, "F", JAS_OPT_HASARG},
{CMDOPT_OUTFMT, "output-format", JAS_OPT_HASARG},
{CMDOPT_OUTFMT, "T", JAS_OPT_HASARG},
{CMDOPT_OUTOPT, "output-option", JAS_OPT_HASARG},
{CMDOPT_OUTOPT, "O", JAS_OPT_HASARG},
{CMDOPT_VERSION, "version", 0},
{CMDOPT_DEBUG, "debug-level", JAS_OPT_HASARG},
{CMDOPT_CMPTNO, "cmptno", JAS_OPT_HASARG},
{CMDOPT_SRGB, "force-srgb", 0},
{CMDOPT_SRGB, "S", 0},
{-1, 0, 0}
};
cmdopts_t *cmdopts;
int c;
if (!(cmdopts = malloc(sizeof(cmdopts_t)))) {
fprintf(stderr, "error: insufficient memory\n");
exit(EXIT_FAILURE);
}
cmdopts->infile = 0;
cmdopts->infmt = -1;
cmdopts->inopts = 0;
cmdopts->inoptsbuf[0] = '\0';
cmdopts->outfile = 0;
cmdopts->outfmt = -1;
cmdopts->outopts = 0;
cmdopts->outoptsbuf[0] = '\0';
cmdopts->verbose = 0;
cmdopts->version = 0;
cmdopts->cmptno = -1;
cmdopts->debug = 0;
cmdopts->srgb = 0;
while ((c = jas_getopt(argc, argv, cmdoptions)) != EOF) {
switch (c) {
case CMDOPT_HELP:
cmdusage();
break;
case CMDOPT_VERBOSE:
cmdopts->verbose = 1;
break;
case CMDOPT_VERSION:
cmdopts->version = 1;
break;
case CMDOPT_DEBUG:
cmdopts->debug = atoi(jas_optarg);
break;
case CMDOPT_INFILE:
cmdopts->infile = jas_optarg;
break;
case CMDOPT_INFMT:
if ((cmdopts->infmt = jas_image_strtofmt(jas_optarg)) < 0) {
fprintf(stderr, "warning: ignoring invalid input format %s\n",
jas_optarg);
cmdopts->infmt = -1;
}
break;
case CMDOPT_INOPT:
addopt(cmdopts->inoptsbuf, OPTSMAX, jas_optarg);
cmdopts->inopts = cmdopts->inoptsbuf;
break;
case CMDOPT_OUTFILE:
cmdopts->outfile = jas_optarg;
break;
case CMDOPT_OUTFMT:
if ((cmdopts->outfmt = jas_image_strtofmt(jas_optarg)) < 0) {
fprintf(stderr, "error: invalid output format %s\n", jas_optarg);
badusage();
}
break;
case CMDOPT_OUTOPT:
addopt(cmdopts->outoptsbuf, OPTSMAX, jas_optarg);
cmdopts->outopts = cmdopts->outoptsbuf;
break;
case CMDOPT_CMPTNO:
cmdopts->cmptno = atoi(jas_optarg);
break;
case CMDOPT_SRGB:
cmdopts->srgb = 1;
break;
default:
badusage();
break;
}
}
while (jas_optind < argc) {
fprintf(stderr,
"warning: ignoring bogus command line argument %s\n",
argv[jas_optind]);
++jas_optind;
}
if (cmdopts->version) {
goto done;
}
if (cmdopts->outfmt < 0 && cmdopts->outfile) {
if ((cmdopts->outfmt = jas_image_fmtfromname(cmdopts->outfile)) < 0) {
fprintf(stderr,
"error: cannot guess image format from output file name\n");
}
}
if (cmdopts->outfmt < 0) {
fprintf(stderr, "error: no output format specified\n");
badusage();
}
done:
return cmdopts;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'A new experimental memory allocator has been introduced. The allocator
is experimental in the sense that its API is not considered stable and
the allocator may change or disappear entirely in future versions of
the code. This new allocator tracks how much memory is being used by
jas_malloc and friends. A maximum upper bound on the memory usage can be
set via the experimental API provided and a default value can be set at
build time as well. Such functionality may be useful in run-time
environments where the user wants to be able to limit the amount of
memory used by JasPer. This allocator is not used by default.
Note: This feature needs C11 functionality.
Note: The memory allocator is not thread safe in its current form.
A new --memory-limit CLI option has been added to the jasper, imginfo,
imgcmp, and jiv programs. The option is only available when the code is
built with the new memory allocator.
The support for my old debug memory allocator from the 1990s has been
purged from the code. The debug memory allocator is probably not
a very useful thing with the advent of GCC/Clang code sanitizers.
The safe size_t integer functions no longer set their result upon failure.
A safe subtract operation was also added.'</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 dispatch_bin_command(conn *c) {
int protocol_error = 0;
int extlen = c->binary_header.request.extlen;
int keylen = c->binary_header.request.keylen;
uint32_t bodylen = c->binary_header.request.bodylen;
if (settings.sasl && !authenticated(c)) {
write_bin_error(c, PROTOCOL_BINARY_RESPONSE_AUTH_ERROR, NULL, 0);
c->write_and_go = conn_closing;
return;
}
MEMCACHED_PROCESS_COMMAND_START(c->sfd, c->rcurr, c->rbytes);
c->noreply = true;
/* binprot supports 16bit keys, but internals are still 8bit */
if (keylen > KEY_MAX_LENGTH) {
handle_binary_protocol_error(c);
return;
}
switch (c->cmd) {
case PROTOCOL_BINARY_CMD_SETQ:
c->cmd = PROTOCOL_BINARY_CMD_SET;
break;
case PROTOCOL_BINARY_CMD_ADDQ:
c->cmd = PROTOCOL_BINARY_CMD_ADD;
break;
case PROTOCOL_BINARY_CMD_REPLACEQ:
c->cmd = PROTOCOL_BINARY_CMD_REPLACE;
break;
case PROTOCOL_BINARY_CMD_DELETEQ:
c->cmd = PROTOCOL_BINARY_CMD_DELETE;
break;
case PROTOCOL_BINARY_CMD_INCREMENTQ:
c->cmd = PROTOCOL_BINARY_CMD_INCREMENT;
break;
case PROTOCOL_BINARY_CMD_DECREMENTQ:
c->cmd = PROTOCOL_BINARY_CMD_DECREMENT;
break;
case PROTOCOL_BINARY_CMD_QUITQ:
c->cmd = PROTOCOL_BINARY_CMD_QUIT;
break;
case PROTOCOL_BINARY_CMD_FLUSHQ:
c->cmd = PROTOCOL_BINARY_CMD_FLUSH;
break;
case PROTOCOL_BINARY_CMD_APPENDQ:
c->cmd = PROTOCOL_BINARY_CMD_APPEND;
break;
case PROTOCOL_BINARY_CMD_PREPENDQ:
c->cmd = PROTOCOL_BINARY_CMD_PREPEND;
break;
case PROTOCOL_BINARY_CMD_GETQ:
c->cmd = PROTOCOL_BINARY_CMD_GET;
break;
case PROTOCOL_BINARY_CMD_GETKQ:
c->cmd = PROTOCOL_BINARY_CMD_GETK;
break;
case PROTOCOL_BINARY_CMD_GATQ:
c->cmd = PROTOCOL_BINARY_CMD_GAT;
break;
case PROTOCOL_BINARY_CMD_GATKQ:
c->cmd = PROTOCOL_BINARY_CMD_GATK;
break;
default:
c->noreply = false;
}
switch (c->cmd) {
case PROTOCOL_BINARY_CMD_VERSION:
if (extlen == 0 && keylen == 0 && bodylen == 0) {
write_bin_response(c, VERSION, 0, 0, strlen(VERSION));
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_FLUSH:
if (keylen == 0 && bodylen == extlen && (extlen == 0 || extlen == 4)) {
bin_read_key(c, bin_read_flush_exptime, extlen);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_NOOP:
if (extlen == 0 && keylen == 0 && bodylen == 0) {
write_bin_response(c, NULL, 0, 0, 0);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_SET: /* FALLTHROUGH */
case PROTOCOL_BINARY_CMD_ADD: /* FALLTHROUGH */
case PROTOCOL_BINARY_CMD_REPLACE:
if (extlen == 8 && keylen != 0 && bodylen >= (keylen + 8)) {
bin_read_key(c, bin_reading_set_header, 8);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_GETQ: /* FALLTHROUGH */
case PROTOCOL_BINARY_CMD_GET: /* FALLTHROUGH */
case PROTOCOL_BINARY_CMD_GETKQ: /* FALLTHROUGH */
case PROTOCOL_BINARY_CMD_GETK:
if (extlen == 0 && bodylen == keylen && keylen > 0) {
bin_read_key(c, bin_reading_get_key, 0);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_DELETE:
if (keylen > 0 && extlen == 0 && bodylen == keylen) {
bin_read_key(c, bin_reading_del_header, extlen);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_INCREMENT:
case PROTOCOL_BINARY_CMD_DECREMENT:
if (keylen > 0 && extlen == 20 && bodylen == (keylen + extlen)) {
bin_read_key(c, bin_reading_incr_header, 20);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_APPEND:
case PROTOCOL_BINARY_CMD_PREPEND:
if (keylen > 0 && extlen == 0) {
bin_read_key(c, bin_reading_set_header, 0);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_STAT:
if (extlen == 0) {
bin_read_key(c, bin_reading_stat, 0);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_QUIT:
if (keylen == 0 && extlen == 0 && bodylen == 0) {
write_bin_response(c, NULL, 0, 0, 0);
c->write_and_go = conn_closing;
if (c->noreply) {
conn_set_state(c, conn_closing);
}
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_SASL_LIST_MECHS:
if (extlen == 0 && keylen == 0 && bodylen == 0) {
bin_list_sasl_mechs(c);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_SASL_AUTH:
case PROTOCOL_BINARY_CMD_SASL_STEP:
if (extlen == 0 && keylen != 0) {
bin_read_key(c, bin_reading_sasl_auth, 0);
} else {
protocol_error = 1;
}
break;
case PROTOCOL_BINARY_CMD_TOUCH:
case PROTOCOL_BINARY_CMD_GAT:
case PROTOCOL_BINARY_CMD_GATQ:
case PROTOCOL_BINARY_CMD_GATK:
case PROTOCOL_BINARY_CMD_GATKQ:
if (extlen == 4 && keylen != 0) {
bin_read_key(c, bin_reading_touch_key, 4);
} else {
protocol_error = 1;
}
break;
default:
write_bin_error(c, PROTOCOL_BINARY_RESPONSE_UNKNOWN_COMMAND, NULL,
bodylen);
}
if (protocol_error)
handle_binary_protocol_error(c);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-190'], 'message': 'CVE reported by cisco talos'</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: ZEND_METHOD(CURLFile, __wakeup)
{
zend_update_property_string(curl_CURLFile_class, getThis(), "name", sizeof("name")-1, "" TSRMLS_CC);
zend_throw_exception(NULL, "Unserialization of CURLFile instances is not allowed", 0 TSRMLS_CC);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-416'], 'message': 'Fix bug #73147: Use After Free in PHP7 unserialize()'</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 dynamicGetbuf (gdIOCtxPtr ctx, void *buf, int len)
{
int rlen, remain;
dpIOCtxPtr dctx;
dynamicPtr *dp;
dctx = (dpIOCtxPtr) ctx;
dp = dctx->dp;
remain = dp->logicalSize - dp->pos;
if (remain >= len) {
rlen = len;
} else {
if (remain == 0) {
return EOF;
}
rlen = remain;
}
memcpy(buf, (void *) ((char *) dp->data + dp->pos), rlen);
dp->pos += rlen;
return rlen;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix #73280: Stack Buffer Overflow in GD dynamicGetbuf
We make sure to never pass a negative `rlen` as size to memcpy().
Cf. <https://github.com/libgd/libgd/commit/53110871>.'</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 fwnet_receive_broadcast(struct fw_iso_context *context,
u32 cycle, size_t header_length, void *header, void *data)
{
struct fwnet_device *dev;
struct fw_iso_packet packet;
__be16 *hdr_ptr;
__be32 *buf_ptr;
int retval;
u32 length;
u16 source_node_id;
u32 specifier_id;
u32 ver;
unsigned long offset;
unsigned long flags;
dev = data;
hdr_ptr = header;
length = be16_to_cpup(hdr_ptr);
spin_lock_irqsave(&dev->lock, flags);
offset = dev->rcv_buffer_size * dev->broadcast_rcv_next_ptr;
buf_ptr = dev->broadcast_rcv_buffer_ptrs[dev->broadcast_rcv_next_ptr++];
if (dev->broadcast_rcv_next_ptr == dev->num_broadcast_rcv_ptrs)
dev->broadcast_rcv_next_ptr = 0;
spin_unlock_irqrestore(&dev->lock, flags);
specifier_id = (be32_to_cpu(buf_ptr[0]) & 0xffff) << 8
| (be32_to_cpu(buf_ptr[1]) & 0xff000000) >> 24;
ver = be32_to_cpu(buf_ptr[1]) & 0xffffff;
source_node_id = be32_to_cpu(buf_ptr[0]) >> 16;
if (specifier_id == IANA_SPECIFIER_ID &&
(ver == RFC2734_SW_VERSION
#if IS_ENABLED(CONFIG_IPV6)
|| ver == RFC3146_SW_VERSION
#endif
)) {
buf_ptr += 2;
length -= IEEE1394_GASP_HDR_SIZE;
fwnet_incoming_packet(dev, buf_ptr, length, source_node_id,
context->card->generation, true);
}
packet.payload_length = dev->rcv_buffer_size;
packet.interrupt = 1;
packet.skip = 0;
packet.tag = 3;
packet.sy = 0;
packet.header_length = IEEE1394_GASP_HDR_SIZE;
spin_lock_irqsave(&dev->lock, flags);
retval = fw_iso_context_queue(dev->broadcast_rcv_context, &packet,
&dev->broadcast_rcv_buffer, offset);
spin_unlock_irqrestore(&dev->lock, flags);
if (retval >= 0)
fw_iso_context_queue_flush(dev->broadcast_rcv_context);
else
dev_err(&dev->netdev->dev, "requeue failed\n");
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-284', 'CWE-787'], 'message': 'firewire: net: guard against rx buffer overflows
The IP-over-1394 driver firewire-net lacked input validation when
handling incoming fragmented datagrams. A maliciously formed fragment
with a respectively large datagram_offset would cause a memcpy past the
datagram buffer.
So, drop any packets carrying a fragment with offset + length larger
than datagram_size.
In addition, ensure that
- GASP header, unfragmented encapsulation header, or fragment
encapsulation header actually exists before we access it,
- the encapsulated datagram or fragment is of nonzero size.
Reported-by: Eyal Itkin <[email protected]>
Reviewed-by: Eyal Itkin <[email protected]>
Fixes: CVE 2016-8633
Cc: [email protected]
Signed-off-by: Stefan Richter <[email protected]>'</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: xsltDocumentFunctionLoadDocument(xmlXPathParserContextPtr ctxt, xmlChar* URI)
{
xsltTransformContextPtr tctxt;
xmlURIPtr uri;
xmlChar *fragment;
xsltDocumentPtr idoc; /* document info */
xmlDocPtr doc;
xmlXPathContextPtr xptrctxt = NULL;
xmlXPathObjectPtr resObj = NULL;
tctxt = xsltXPathGetTransformContext(ctxt);
if (tctxt == NULL) {
xsltTransformError(NULL, NULL, NULL,
"document() : internal error tctxt == NULL\n");
valuePush(ctxt, xmlXPathNewNodeSet(NULL));
return;
}
uri = xmlParseURI((const char *) URI);
if (uri == NULL) {
xsltTransformError(tctxt, NULL, NULL,
"document() : failed to parse URI\n");
valuePush(ctxt, xmlXPathNewNodeSet(NULL));
return;
}
/*
* check for and remove fragment identifier
*/
fragment = (xmlChar *)uri->fragment;
if (fragment != NULL) {
xmlChar *newURI;
uri->fragment = NULL;
newURI = xmlSaveUri(uri);
idoc = xsltLoadDocument(tctxt, newURI);
xmlFree(newURI);
} else
idoc = xsltLoadDocument(tctxt, URI);
xmlFreeURI(uri);
if (idoc == NULL) {
if ((URI == NULL) ||
(URI[0] == '#') ||
((tctxt->style->doc != NULL) &&
(xmlStrEqual(tctxt->style->doc->URL, URI))))
{
/*
* This selects the stylesheet's doc itself.
*/
doc = tctxt->style->doc;
} else {
valuePush(ctxt, xmlXPathNewNodeSet(NULL));
if (fragment != NULL)
xmlFree(fragment);
return;
}
} else
doc = idoc->doc;
if (fragment == NULL) {
valuePush(ctxt, xmlXPathNewNodeSet((xmlNodePtr) doc));
return;
}
/* use XPointer of HTML location for fragment ID */
#ifdef LIBXML_XPTR_ENABLED
xptrctxt = xmlXPtrNewContext(doc, NULL, NULL);
if (xptrctxt == NULL) {
xsltTransformError(tctxt, NULL, NULL,
"document() : internal error xptrctxt == NULL\n");
goto out_fragment;
}
resObj = xmlXPtrEval(fragment, xptrctxt);
xmlXPathFreeContext(xptrctxt);
#endif
xmlFree(fragment);
if (resObj == NULL)
goto out_fragment;
switch (resObj->type) {
case XPATH_NODESET:
break;
case XPATH_UNDEFINED:
case XPATH_BOOLEAN:
case XPATH_NUMBER:
case XPATH_STRING:
case XPATH_POINT:
case XPATH_USERS:
case XPATH_XSLT_TREE:
case XPATH_RANGE:
case XPATH_LOCATIONSET:
xsltTransformError(tctxt, NULL, NULL,
"document() : XPointer does not select a node set: #%s\n",
fragment);
goto out_object;
}
valuePush(ctxt, resObj);
return;
out_object:
xmlXPathFreeObject(resObj);
out_fragment:
valuePush(ctxt, xmlXPathNewNodeSet(NULL));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix use-after-free in xsltDocumentFunctionLoadDocument
Also fixes a memory leak in an unlikely error case.
Fixes bug #758291
https://bugzilla.gnome.org/show_bug.cgi?id=758291'</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 tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp;
struct sk_buff *opt_skb = NULL;
/* Imagine: socket is IPv6. IPv4 packet arrives,
goes to IPv4 receive handler and backlogged.
From backlog it always goes here. Kerboom...
Fortunately, tcp_rcv_established and rcv_established
handle them correctly, but it is not case with
tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK
*/
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
if (sk_filter(sk, skb))
goto discard;
/*
* socket locking is here for SMP purposes as backlog rcv
* is currently called with bh processing disabled.
*/
/* Do Stevens' IPV6_PKTOPTIONS.
Yes, guys, it is the only place in our code, where we
may make it not affecting IPv4.
The rest of code is protocol independent,
and I do not like idea to uglify IPv4.
Actually, all the idea behind IPV6_PKTOPTIONS
looks not very well thought. For now we latch
options, received in the last packet, enqueued
by tcp. Feel free to propose better solution.
--ANK (980728)
*/
if (np->rxopt.all)
opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
struct dst_entry *dst = sk->sk_rx_dst;
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
if (dst) {
if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
dst_release(dst);
sk->sk_rx_dst = NULL;
}
}
tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len);
if (opt_skb)
goto ipv6_pktoptions;
return 0;
}
if (tcp_checksum_complete(skb))
goto csum_err;
if (sk->sk_state == TCP_LISTEN) {
struct sock *nsk = tcp_v6_cookie_check(sk, skb);
if (!nsk)
goto discard;
if (nsk != sk) {
sock_rps_save_rxhash(nsk, skb);
sk_mark_napi_id(nsk, skb);
if (tcp_child_process(sk, nsk, skb))
goto reset;
if (opt_skb)
__kfree_skb(opt_skb);
return 0;
}
} else
sock_rps_save_rxhash(sk, skb);
if (tcp_rcv_state_process(sk, skb))
goto reset;
if (opt_skb)
goto ipv6_pktoptions;
return 0;
reset:
tcp_v6_send_reset(sk, skb);
discard:
if (opt_skb)
__kfree_skb(opt_skb);
kfree_skb(skb);
return 0;
csum_err:
TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
goto discard;
ipv6_pktoptions:
/* Do you ask, what is it?
1. skb was enqueued by tcp.
2. skb is added to tail of read queue, rather than out of order.
3. socket is not in passive state.
4. Finally, it really contains options, which user wants to receive.
*/
tp = tcp_sk(sk);
if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
np->mcast_oif = tcp_v6_iif(opt_skb);
if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
if (np->repflow)
np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
skb_set_owner_r(opt_skb, sk);
tcp_v6_restore_cb(opt_skb);
opt_skb = xchg(&np->pktoptions, opt_skb);
} else {
__kfree_skb(opt_skb);
opt_skb = xchg(&np->pktoptions, NULL);
}
}
kfree_skb(opt_skb);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-284'], 'message': 'tcp: take care of truncations done by sk_filter()
With syzkaller help, Marco Grassi found a bug in TCP stack,
crashing in tcp_collapse()
Root cause is that sk_filter() can truncate the incoming skb,
but TCP stack was not really expecting this to happen.
It probably was expecting a simple DROP or ACCEPT behavior.
We first need to make sure no part of TCP header could be removed.
Then we need to adjust TCP_SKB_CB(skb)->end_seq
Many thanks to syzkaller team and Marco for giving us a reproducer.
Signed-off-by: Eric Dumazet <[email protected]>
Reported-by: Marco Grassi <[email protected]>
Reported-by: Vladis Dronov <[email protected]>
Signed-off-by: David S. Miller <[email protected]>'</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 cstm(JF, js_Ast *stm)
{
js_Ast *target;
int loop, cont, then, end;
emitline(J, F, stm);
switch (stm->type) {
case AST_FUNDEC:
break;
case STM_BLOCK:
cstmlist(J, F, stm->a);
break;
case STM_EMPTY:
if (F->script) {
emit(J, F, OP_POP);
emit(J, F, OP_UNDEF);
}
break;
case STM_VAR:
cvarinit(J, F, stm->a);
break;
case STM_IF:
if (stm->c) {
cexp(J, F, stm->a);
then = emitjump(J, F, OP_JTRUE);
cstm(J, F, stm->c);
end = emitjump(J, F, OP_JUMP);
label(J, F, then);
cstm(J, F, stm->b);
label(J, F, end);
} else {
cexp(J, F, stm->a);
end = emitjump(J, F, OP_JFALSE);
cstm(J, F, stm->b);
label(J, F, end);
}
break;
case STM_DO:
loop = here(J, F);
cstm(J, F, stm->a);
cont = here(J, F);
cexp(J, F, stm->b);
emitjumpto(J, F, OP_JTRUE, loop);
labeljumps(J, F, stm->jumps, here(J,F), cont);
break;
case STM_WHILE:
loop = here(J, F);
cexp(J, F, stm->a);
end = emitjump(J, F, OP_JFALSE);
cstm(J, F, stm->b);
emitjumpto(J, F, OP_JUMP, loop);
label(J, F, end);
labeljumps(J, F, stm->jumps, here(J,F), loop);
break;
case STM_FOR:
case STM_FOR_VAR:
if (stm->type == STM_FOR_VAR) {
cvarinit(J, F, stm->a);
} else {
if (stm->a) {
cexp(J, F, stm->a);
emit(J, F, OP_POP);
}
}
loop = here(J, F);
if (stm->b) {
cexp(J, F, stm->b);
end = emitjump(J, F, OP_JFALSE);
} else {
end = 0;
}
cstm(J, F, stm->d);
cont = here(J, F);
if (stm->c) {
cexp(J, F, stm->c);
emit(J, F, OP_POP);
}
emitjumpto(J, F, OP_JUMP, loop);
if (end)
label(J, F, end);
labeljumps(J, F, stm->jumps, here(J,F), cont);
break;
case STM_FOR_IN:
case STM_FOR_IN_VAR:
cexp(J, F, stm->b);
emit(J, F, OP_ITERATOR);
loop = here(J, F);
{
emit(J, F, OP_NEXTITER);
end = emitjump(J, F, OP_JFALSE);
cassignforin(J, F, stm);
if (F->script) {
emit(J, F, OP_ROT2);
cstm(J, F, stm->c);
emit(J, F, OP_ROT2);
} else {
cstm(J, F, stm->c);
}
emitjumpto(J, F, OP_JUMP, loop);
}
label(J, F, end);
labeljumps(J, F, stm->jumps, here(J,F), loop);
break;
case STM_SWITCH:
cswitch(J, F, stm->a, stm->b);
labeljumps(J, F, stm->jumps, here(J,F), 0);
break;
case STM_LABEL:
cstm(J, F, stm->b);
/* skip consecutive labels */
while (stm->type == STM_LABEL)
stm = stm->b;
/* loops and switches have already been labelled */
if (!isloop(stm->type) && stm->type != STM_SWITCH)
labeljumps(J, F, stm->jumps, here(J,F), 0);
break;
case STM_BREAK:
if (stm->a) {
target = breaktarget(J, F, stm, stm->a->string);
if (!target)
jsC_error(J, stm, "break label '%s' not found", stm->a->string);
} else {
target = breaktarget(J, F, stm, NULL);
if (!target)
jsC_error(J, stm, "unlabelled break must be inside loop or switch");
}
cexit(J, F, STM_BREAK, stm, target);
addjump(J, F, STM_BREAK, target, emitjump(J, F, OP_JUMP));
break;
case STM_CONTINUE:
if (stm->a) {
target = continuetarget(J, F, stm, stm->a->string);
if (!target)
jsC_error(J, stm, "continue label '%s' not found", stm->a->string);
} else {
target = continuetarget(J, F, stm, NULL);
if (!target)
jsC_error(J, stm, "continue must be inside loop");
}
cexit(J, F, STM_CONTINUE, stm, target);
addjump(J, F, STM_CONTINUE, target, emitjump(J, F, OP_JUMP));
break;
case STM_RETURN:
if (stm->a)
cexp(J, F, stm->a);
else
emit(J, F, OP_UNDEF);
target = returntarget(J, F, stm);
if (!target)
jsC_error(J, stm, "return not in function");
cexit(J, F, STM_RETURN, stm, target);
emit(J, F, OP_RETURN);
break;
case STM_THROW:
cexp(J, F, stm->a);
emit(J, F, OP_THROW);
break;
case STM_WITH:
cexp(J, F, stm->a);
emit(J, F, OP_WITH);
cstm(J, F, stm->b);
emit(J, F, OP_ENDWITH);
break;
case STM_TRY:
if (stm->b && stm->c) {
if (stm->d)
ctrycatchfinally(J, F, stm->a, stm->b, stm->c, stm->d);
else
ctrycatch(J, F, stm->a, stm->b, stm->c);
} else {
ctryfinally(J, F, stm->a, stm->d);
}
break;
case STM_DEBUGGER:
emit(J, F, OP_DEBUGGER);
break;
default:
if (F->script) {
emit(J, F, OP_POP);
cexp(J, F, stm);
} else {
cexp(J, F, stm);
emit(J, F, OP_POP);
}
break;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'Fix 697172: degenerate labeled break/continue statement.
A labeled break statement will look for a matching label through
its chain of parent statements. We start looking at the break statement
though, so if the label is attached to the break, we'll return the break
statement itself as a break target.
Start looking for targets one level up instead.'</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: MagickExport Image *WaveletDenoiseImage(const Image *image,
const double threshold,const double softness,ExceptionInfo *exception)
{
CacheView
*image_view,
*noise_view;
float
*kernel,
*pixels;
Image
*noise_image;
MagickBooleanType
status;
MagickSizeType
number_pixels;
MemoryInfo
*pixels_info;
ssize_t
channel;
static const float
noise_levels[] = { 0.8002f, 0.2735f, 0.1202f, 0.0585f, 0.0291f, 0.0152f,
0.0080f, 0.0044f };
/*
Initialize noise image attributes.
*/
assert(image != (const Image *) NULL);
assert(image->signature == MagickCoreSignature);
if (image->debug != MagickFalse)
(void) LogMagickEvent(TraceEvent,GetMagickModule(),"%s",image->filename);
assert(exception != (ExceptionInfo *) NULL);
assert(exception->signature == MagickCoreSignature);
#if defined(MAGICKCORE_OPENCL_SUPPORT)
noise_image=AccelerateWaveletDenoiseImage(image,threshold,exception);
if (noise_image != (Image *) NULL)
return(noise_image);
#endif
noise_image=CloneImage(image,0,0,MagickTrue,exception);
if (noise_image == (Image *) NULL)
return((Image *) NULL);
if (SetImageStorageClass(noise_image,DirectClass,exception) == MagickFalse)
{
noise_image=DestroyImage(noise_image);
return((Image *) NULL);
}
if (AcquireMagickResource(WidthResource,4*image->columns) == MagickFalse)
ThrowImageException(ResourceLimitError,"MemoryAllocationFailed");
pixels_info=AcquireVirtualMemory(3*image->columns,image->rows*
sizeof(*pixels));
kernel=(float *) AcquireQuantumMemory(MagickMax(image->rows,image->columns),
GetOpenMPMaximumThreads()*sizeof(*kernel));
if ((pixels_info == (MemoryInfo *) NULL) || (kernel == (float *) NULL))
{
if (kernel != (float *) NULL)
kernel=(float *) RelinquishMagickMemory(kernel);
if (pixels_info != (MemoryInfo *) NULL)
pixels_info=RelinquishVirtualMemory(pixels_info);
ThrowImageException(ResourceLimitError,"MemoryAllocationFailed");
}
pixels=(float *) GetVirtualMemoryBlob(pixels_info);
status=MagickTrue;
number_pixels=(MagickSizeType) image->columns*image->rows;
image_view=AcquireAuthenticCacheView(image,exception);
noise_view=AcquireAuthenticCacheView(noise_image,exception);
for (channel=0; channel < (ssize_t) GetPixelChannels(image); channel++)
{
register ssize_t
i;
size_t
high_pass,
low_pass;
ssize_t
level,
y;
PixelChannel
pixel_channel;
PixelTrait
traits;
if (status == MagickFalse)
continue;
traits=GetPixelChannelTraits(image,(PixelChannel) channel);
if (traits == UndefinedPixelTrait)
continue;
pixel_channel=GetPixelChannelChannel(image,channel);
if ((pixel_channel != RedPixelChannel) &&
(pixel_channel != GreenPixelChannel) &&
(pixel_channel != BluePixelChannel))
continue;
/*
Copy channel from image to wavelet pixel array.
*/
i=0;
for (y=0; y < (ssize_t) image->rows; y++)
{
register const Quantum
*magick_restrict p;
ssize_t
x;
p=GetCacheViewAuthenticPixels(image_view,0,y,image->columns,1,exception);
if (p == (const Quantum *) NULL)
{
status=MagickFalse;
break;
}
for (x=0; x < (ssize_t) image->columns; x++)
{
pixels[i++]=(float) p[channel];
p+=GetPixelChannels(image);
}
}
/*
Low pass filter outputs are called approximation kernel & high pass
filters are referred to as detail kernel. The detail kernel
have high values in the noisy parts of the signal.
*/
high_pass=0;
for (level=0; level < 5; level++)
{
double
magnitude;
ssize_t
x,
y;
low_pass=(size_t) (number_pixels*((level & 0x01)+1));
#if defined(MAGICKCORE_OPENMP_SUPPORT)
#pragma omp parallel for schedule(static,1) \
magick_threads(image,image,image->rows,1)
#endif
for (y=0; y < (ssize_t) image->rows; y++)
{
const int
id = GetOpenMPThreadId();
register float
*magick_restrict p,
*magick_restrict q;
register ssize_t
x;
p=kernel+id*image->columns;
q=pixels+y*image->columns;
HatTransform(q+high_pass,1,image->columns,(size_t) (1 << level),p);
q+=low_pass;
for (x=0; x < (ssize_t) image->columns; x++)
*q++=(*p++);
}
#if defined(MAGICKCORE_OPENMP_SUPPORT)
#pragma omp parallel for schedule(static,1) \
magick_threads(image,image,image->columns,1)
#endif
for (x=0; x < (ssize_t) image->columns; x++)
{
const int
id = GetOpenMPThreadId();
register float
*magick_restrict p,
*magick_restrict q;
register ssize_t
y;
p=kernel+id*image->rows;
q=pixels+x+low_pass;
HatTransform(q,image->columns,image->rows,(size_t) (1 << level),p);
for (y=0; y < (ssize_t) image->rows; y++)
{
*q=(*p++);
q+=image->columns;
}
}
/*
To threshold, each coefficient is compared to a threshold value and
attenuated / shrunk by some factor.
*/
magnitude=threshold*noise_levels[level];
for (i=0; i < (ssize_t) number_pixels; ++i)
{
pixels[high_pass+i]-=pixels[low_pass+i];
if (pixels[high_pass+i] < -magnitude)
pixels[high_pass+i]+=magnitude-softness*magnitude;
else
if (pixels[high_pass+i] > magnitude)
pixels[high_pass+i]-=magnitude-softness*magnitude;
else
pixels[high_pass+i]*=softness;
if (high_pass != 0)
pixels[i]+=pixels[high_pass+i];
}
high_pass=low_pass;
}
/*
Reconstruct image from the thresholded wavelet kernel.
*/
i=0;
for (y=0; y < (ssize_t) image->rows; y++)
{
MagickBooleanType
sync;
register Quantum
*magick_restrict q;
register ssize_t
x;
ssize_t
offset;
q=GetCacheViewAuthenticPixels(noise_view,0,y,noise_image->columns,1,
exception);
if (q == (Quantum *) NULL)
{
status=MagickFalse;
break;
}
offset=GetPixelChannelOffset(noise_image,pixel_channel);
for (x=0; x < (ssize_t) image->columns; x++)
{
MagickRealType
pixel;
pixel=(MagickRealType) pixels[i]+pixels[low_pass+i];
q[offset]=ClampToQuantum(pixel);
i++;
q+=GetPixelChannels(noise_image);
}
sync=SyncCacheViewAuthenticPixels(noise_view,exception);
if (sync == MagickFalse)
status=MagickFalse;
}
if (image->progress_monitor != (MagickProgressMonitor) NULL)
{
MagickBooleanType
proceed;
proceed=SetImageProgress(image,AddNoiseImageTag,(MagickOffsetType)
channel,GetPixelChannels(image));
if (proceed == MagickFalse)
status=MagickFalse;
}
}
noise_view=DestroyCacheView(noise_view);
image_view=DestroyCacheView(image_view);
kernel=(float *) RelinquishMagickMemory(kernel);
pixels_info=RelinquishVirtualMemory(pixels_info);
if (status == MagickFalse)
noise_image=DestroyImage(noise_image);
return(noise_image);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-703'], 'message': 'https://github.com/ImageMagick/ImageMagick/issues/296'</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 CClient::ProcessServerPacket(CNetChunk *pPacket)
{
CUnpacker Unpacker;
Unpacker.Reset(pPacket->m_pData, pPacket->m_DataSize);
// unpack msgid and system flag
int Msg = Unpacker.GetInt();
int Sys = Msg&1;
Msg >>= 1;
if(Unpacker.Error())
return;
if(Sys)
{
// system message
if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0 && Msg == NETMSG_MAP_CHANGE)
{
const char *pMap = Unpacker.GetString(CUnpacker::SANITIZE_CC|CUnpacker::SKIP_START_WHITESPACES);
int MapCrc = Unpacker.GetInt();
int MapSize = Unpacker.GetInt();
const char *pError = 0;
if(Unpacker.Error())
return;
// check for valid standard map
if(!m_MapChecker.IsMapValid(pMap, MapCrc, MapSize))
pError = "invalid standard map";
for(int i = 0; pMap[i]; i++) // protect the player from nasty map names
{
if(pMap[i] == '/' || pMap[i] == '\\')
pError = "strange character in map name";
}
if(MapSize < 0)
pError = "invalid map size";
if(pError)
DisconnectWithReason(pError);
else
{
pError = LoadMapSearch(pMap, MapCrc);
if(!pError)
{
m_pConsole->Print(IConsole::OUTPUT_LEVEL_ADDINFO, "client/network", "loading done");
SendReady();
}
else
{
str_format(m_aMapdownloadFilename, sizeof(m_aMapdownloadFilename), "downloadedmaps/%s_%08x.map", pMap, MapCrc);
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "starting to download map to '%s'", m_aMapdownloadFilename);
m_pConsole->Print(IConsole::OUTPUT_LEVEL_ADDINFO, "client/network", aBuf);
m_MapdownloadChunk = 0;
str_copy(m_aMapdownloadName, pMap, sizeof(m_aMapdownloadName));
if(m_MapdownloadFile)
io_close(m_MapdownloadFile);
m_MapdownloadFile = Storage()->OpenFile(m_aMapdownloadFilename, IOFLAG_WRITE, IStorage::TYPE_SAVE);
m_MapdownloadCrc = MapCrc;
m_MapdownloadTotalsize = MapSize;
m_MapdownloadAmount = 0;
CMsgPacker Msg(NETMSG_REQUEST_MAP_DATA);
Msg.AddInt(m_MapdownloadChunk);
SendMsgEx(&Msg, MSGFLAG_VITAL|MSGFLAG_FLUSH);
if(g_Config.m_Debug)
{
str_format(aBuf, sizeof(aBuf), "requested chunk %d", m_MapdownloadChunk);
m_pConsole->Print(IConsole::OUTPUT_LEVEL_DEBUG, "client/network", aBuf);
}
}
}
}
else if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0 && Msg == NETMSG_MAP_DATA)
{
int Last = Unpacker.GetInt();
int MapCRC = Unpacker.GetInt();
int Chunk = Unpacker.GetInt();
int Size = Unpacker.GetInt();
const unsigned char *pData = Unpacker.GetRaw(Size);
// check fior errors
if(Unpacker.Error() || Size <= 0 || MapCRC != m_MapdownloadCrc || Chunk != m_MapdownloadChunk || !m_MapdownloadFile)
return;
io_write(m_MapdownloadFile, pData, Size);
m_MapdownloadAmount += Size;
if(Last)
{
const char *pError;
m_pConsole->Print(IConsole::OUTPUT_LEVEL_ADDINFO, "client/network", "download complete, loading map");
if(m_MapdownloadFile)
io_close(m_MapdownloadFile);
m_MapdownloadFile = 0;
m_MapdownloadAmount = 0;
m_MapdownloadTotalsize = -1;
// load map
pError = LoadMap(m_aMapdownloadName, m_aMapdownloadFilename, m_MapdownloadCrc);
if(!pError)
{
m_pConsole->Print(IConsole::OUTPUT_LEVEL_ADDINFO, "client/network", "loading done");
SendReady();
}
else
DisconnectWithReason(pError);
}
else
{
// request new chunk
m_MapdownloadChunk++;
CMsgPacker Msg(NETMSG_REQUEST_MAP_DATA);
Msg.AddInt(m_MapdownloadChunk);
SendMsgEx(&Msg, MSGFLAG_VITAL|MSGFLAG_FLUSH);
if(g_Config.m_Debug)
{
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "requested chunk %d", m_MapdownloadChunk);
m_pConsole->Print(IConsole::OUTPUT_LEVEL_DEBUG, "client/network", aBuf);
}
}
}
else if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0 && Msg == NETMSG_CON_READY)
{
GameClient()->OnConnected();
}
else if(Msg == NETMSG_PING)
{
CMsgPacker Msg(NETMSG_PING_REPLY);
SendMsgEx(&Msg, 0);
}
else if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0 && Msg == NETMSG_RCON_CMD_ADD)
{
const char *pName = Unpacker.GetString(CUnpacker::SANITIZE_CC);
const char *pHelp = Unpacker.GetString(CUnpacker::SANITIZE_CC);
const char *pParams = Unpacker.GetString(CUnpacker::SANITIZE_CC);
if(Unpacker.Error() == 0)
m_pConsole->RegisterTemp(pName, pParams, CFGFLAG_SERVER, pHelp);
}
else if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0 && Msg == NETMSG_RCON_CMD_REM)
{
const char *pName = Unpacker.GetString(CUnpacker::SANITIZE_CC);
if(Unpacker.Error() == 0)
m_pConsole->DeregisterTemp(pName);
}
else if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0 && Msg == NETMSG_RCON_AUTH_STATUS)
{
int Result = Unpacker.GetInt();
if(Unpacker.Error() == 0)
m_RconAuthed = Result;
int Old = m_UseTempRconCommands;
m_UseTempRconCommands = Unpacker.GetInt();
if(Unpacker.Error() != 0)
m_UseTempRconCommands = 0;
if(Old != 0 && m_UseTempRconCommands == 0)
m_pConsole->DeregisterTempAll();
}
else if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0 && Msg == NETMSG_RCON_LINE)
{
const char *pLine = Unpacker.GetString();
if(Unpacker.Error() == 0)
GameClient()->OnRconLine(pLine);
}
else if(Msg == NETMSG_PING_REPLY)
{
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "latency %.2f", (time_get() - m_PingStartTime)*1000 / (float)time_freq());
m_pConsole->Print(IConsole::OUTPUT_LEVEL_STANDARD, "client/network", aBuf);
}
else if(Msg == NETMSG_INPUTTIMING)
{
int InputPredTick = Unpacker.GetInt();
int TimeLeft = Unpacker.GetInt();
// adjust our prediction time
int64 Target = 0;
for(int k = 0; k < 200; k++)
{
if(m_aInputs[k].m_Tick == InputPredTick)
{
Target = m_aInputs[k].m_PredictedTime + (time_get() - m_aInputs[k].m_Time);
Target = Target - (int64)(((TimeLeft-PREDICTION_MARGIN)/1000.0f)*time_freq());
break;
}
}
if(Target)
m_PredictedTime.Update(&m_InputtimeMarginGraph, Target, TimeLeft, 1);
}
else if(Msg == NETMSG_SNAP || Msg == NETMSG_SNAPSINGLE || Msg == NETMSG_SNAPEMPTY)
{
int NumParts = 1;
int Part = 0;
int GameTick = Unpacker.GetInt();
int DeltaTick = GameTick-Unpacker.GetInt();
int PartSize = 0;
int Crc = 0;
int CompleteSize = 0;
const char *pData = 0;
// we are not allowed to process snapshot yet
if(State() < IClient::STATE_LOADING)
return;
if(Msg == NETMSG_SNAP)
{
NumParts = Unpacker.GetInt();
Part = Unpacker.GetInt();
}
if(Msg != NETMSG_SNAPEMPTY)
{
Crc = Unpacker.GetInt();
PartSize = Unpacker.GetInt();
}
pData = (const char *)Unpacker.GetRaw(PartSize);
if(Unpacker.Error())
return;
if(GameTick >= m_CurrentRecvTick)
{
if(GameTick != m_CurrentRecvTick)
{
m_SnapshotParts = 0;
m_CurrentRecvTick = GameTick;
}
// TODO: clean this up abit
mem_copy((char*)m_aSnapshotIncommingData + Part*MAX_SNAPSHOT_PACKSIZE, pData, PartSize);
m_SnapshotParts |= 1<<Part;
if(m_SnapshotParts == (unsigned)((1<<NumParts)-1))
{
static CSnapshot Emptysnap;
CSnapshot *pDeltaShot = &Emptysnap;
int PurgeTick;
void *pDeltaData;
int DeltaSize;
unsigned char aTmpBuffer2[CSnapshot::MAX_SIZE];
unsigned char aTmpBuffer3[CSnapshot::MAX_SIZE];
CSnapshot *pTmpBuffer3 = (CSnapshot*)aTmpBuffer3; // Fix compiler warning for strict-aliasing
int SnapSize;
CompleteSize = (NumParts-1) * MAX_SNAPSHOT_PACKSIZE + PartSize;
// reset snapshoting
m_SnapshotParts = 0;
// find snapshot that we should use as delta
Emptysnap.Clear();
// find delta
if(DeltaTick >= 0)
{
int DeltashotSize = m_SnapshotStorage.Get(DeltaTick, 0, &pDeltaShot, 0);
if(DeltashotSize < 0)
{
// couldn't find the delta snapshots that the server used
// to compress this snapshot. force the server to resync
if(g_Config.m_Debug)
{
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "error, couldn't find the delta snapshot");
m_pConsole->Print(IConsole::OUTPUT_LEVEL_DEBUG, "client", aBuf);
}
// ack snapshot
// TODO: combine this with the input message
m_AckGameTick = -1;
return;
}
}
// decompress snapshot
pDeltaData = m_SnapshotDelta.EmptyDelta();
DeltaSize = sizeof(int)*3;
if(CompleteSize)
{
int IntSize = CVariableInt::Decompress(m_aSnapshotIncommingData, CompleteSize, aTmpBuffer2);
if(IntSize < 0) // failure during decompression, bail
return;
pDeltaData = aTmpBuffer2;
DeltaSize = IntSize;
}
// unpack delta
SnapSize = m_SnapshotDelta.UnpackDelta(pDeltaShot, pTmpBuffer3, pDeltaData, DeltaSize);
if(SnapSize < 0)
{
m_pConsole->Print(IConsole::OUTPUT_LEVEL_DEBUG, "client", "delta unpack failed!");
return;
}
if(Msg != NETMSG_SNAPEMPTY && pTmpBuffer3->Crc() != Crc)
{
if(g_Config.m_Debug)
{
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "snapshot crc error #%d - tick=%d wantedcrc=%d gotcrc=%d compressed_size=%d delta_tick=%d",
m_SnapCrcErrors, GameTick, Crc, pTmpBuffer3->Crc(), CompleteSize, DeltaTick);
m_pConsole->Print(IConsole::OUTPUT_LEVEL_DEBUG, "client", aBuf);
}
m_SnapCrcErrors++;
if(m_SnapCrcErrors > 10)
{
// to many errors, send reset
m_AckGameTick = -1;
SendInput();
m_SnapCrcErrors = 0;
}
return;
}
else
{
if(m_SnapCrcErrors)
m_SnapCrcErrors--;
}
// purge old snapshots
PurgeTick = DeltaTick;
if(m_aSnapshots[SNAP_PREV] && m_aSnapshots[SNAP_PREV]->m_Tick < PurgeTick)
PurgeTick = m_aSnapshots[SNAP_PREV]->m_Tick;
if(m_aSnapshots[SNAP_CURRENT] && m_aSnapshots[SNAP_CURRENT]->m_Tick < PurgeTick)
PurgeTick = m_aSnapshots[SNAP_CURRENT]->m_Tick;
m_SnapshotStorage.PurgeUntil(PurgeTick);
// add new
m_SnapshotStorage.Add(GameTick, time_get(), SnapSize, pTmpBuffer3, 1);
// add snapshot to demo
if(m_DemoRecorder.IsRecording())
{
// write snapshot
m_DemoRecorder.RecordSnapshot(GameTick, pTmpBuffer3, SnapSize);
}
// apply snapshot, cycle pointers
m_RecivedSnapshots++;
m_CurrentRecvTick = GameTick;
// we got two snapshots until we see us self as connected
if(m_RecivedSnapshots == 2)
{
// start at 200ms and work from there
m_PredictedTime.Init(GameTick*time_freq()/50);
m_PredictedTime.SetAdjustSpeed(1, 1000.0f);
m_GameTime.Init((GameTick-1)*time_freq()/50);
m_aSnapshots[SNAP_PREV] = m_SnapshotStorage.m_pFirst;
m_aSnapshots[SNAP_CURRENT] = m_SnapshotStorage.m_pLast;
m_LocalStartTime = time_get();
SetState(IClient::STATE_ONLINE);
DemoRecorder_HandleAutoStart();
}
// adjust game time
if(m_RecivedSnapshots > 2)
{
int64 Now = m_GameTime.Get(time_get());
int64 TickStart = GameTick*time_freq()/50;
int64 TimeLeft = (TickStart-Now)*1000 / time_freq();
m_GameTime.Update(&m_GametimeMarginGraph, (GameTick-1)*time_freq()/50, TimeLeft, 0);
}
// ack snapshot
m_AckGameTick = GameTick;
}
}
}
}
else
{
if((pPacket->m_Flags&NET_CHUNKFLAG_VITAL) != 0)
{
// game message
if(m_DemoRecorder.IsRecording())
m_DemoRecorder.RecordMessage(pPacket->m_pData, pPacket->m_DataSize);
GameClient()->OnMessage(Msg, &Unpacker);
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'added some checks to snap handling'</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 jpc_dec_process_siz(jpc_dec_t *dec, jpc_ms_t *ms)
{
jpc_siz_t *siz = &ms->parms.siz;
int compno;
int tileno;
jpc_dec_tile_t *tile;
jpc_dec_tcomp_t *tcomp;
int htileno;
int vtileno;
jpc_dec_cmpt_t *cmpt;
dec->xstart = siz->xoff;
dec->ystart = siz->yoff;
dec->xend = siz->width;
dec->yend = siz->height;
dec->tilewidth = siz->tilewidth;
dec->tileheight = siz->tileheight;
dec->tilexoff = siz->tilexoff;
dec->tileyoff = siz->tileyoff;
dec->numcomps = siz->numcomps;
if (!(dec->cp = jpc_dec_cp_create(dec->numcomps))) {
return -1;
}
if (!(dec->cmpts = jas_alloc2(dec->numcomps, sizeof(jpc_dec_cmpt_t)))) {
return -1;
}
for (compno = 0, cmpt = dec->cmpts; compno < dec->numcomps; ++compno,
++cmpt) {
cmpt->prec = siz->comps[compno].prec;
cmpt->sgnd = siz->comps[compno].sgnd;
cmpt->hstep = siz->comps[compno].hsamp;
cmpt->vstep = siz->comps[compno].vsamp;
cmpt->width = JPC_CEILDIV(dec->xend, cmpt->hstep) -
JPC_CEILDIV(dec->xstart, cmpt->hstep);
cmpt->height = JPC_CEILDIV(dec->yend, cmpt->vstep) -
JPC_CEILDIV(dec->ystart, cmpt->vstep);
cmpt->hsubstep = 0;
cmpt->vsubstep = 0;
}
dec->image = 0;
dec->numhtiles = JPC_CEILDIV(dec->xend - dec->tilexoff, dec->tilewidth);
dec->numvtiles = JPC_CEILDIV(dec->yend - dec->tileyoff, dec->tileheight);
dec->numtiles = dec->numhtiles * dec->numvtiles;
JAS_DBGLOG(10, ("numtiles = %d; numhtiles = %d; numvtiles = %d;\n",
dec->numtiles, dec->numhtiles, dec->numvtiles));
if (!(dec->tiles = jas_alloc2(dec->numtiles, sizeof(jpc_dec_tile_t)))) {
return -1;
}
for (tileno = 0, tile = dec->tiles; tileno < dec->numtiles; ++tileno,
++tile) {
htileno = tileno % dec->numhtiles;
vtileno = tileno / dec->numhtiles;
tile->realmode = 0;
tile->state = JPC_TILE_INIT;
tile->xstart = JAS_MAX(dec->tilexoff + htileno * dec->tilewidth,
dec->xstart);
tile->ystart = JAS_MAX(dec->tileyoff + vtileno * dec->tileheight,
dec->ystart);
tile->xend = JAS_MIN(dec->tilexoff + (htileno + 1) *
dec->tilewidth, dec->xend);
tile->yend = JAS_MIN(dec->tileyoff + (vtileno + 1) *
dec->tileheight, dec->yend);
tile->numparts = 0;
tile->partno = 0;
tile->pkthdrstream = 0;
tile->pkthdrstreampos = 0;
tile->pptstab = 0;
tile->cp = 0;
tile->pi = 0;
if (!(tile->tcomps = jas_alloc2(dec->numcomps,
sizeof(jpc_dec_tcomp_t)))) {
return -1;
}
for (compno = 0, cmpt = dec->cmpts, tcomp = tile->tcomps;
compno < dec->numcomps; ++compno, ++cmpt, ++tcomp) {
tcomp->rlvls = 0;
tcomp->numrlvls = 0;
tcomp->data = 0;
tcomp->xstart = JPC_CEILDIV(tile->xstart, cmpt->hstep);
tcomp->ystart = JPC_CEILDIV(tile->ystart, cmpt->vstep);
tcomp->xend = JPC_CEILDIV(tile->xend, cmpt->hstep);
tcomp->yend = JPC_CEILDIV(tile->yend, cmpt->vstep);
tcomp->tsfb = 0;
}
}
dec->pkthdrstreams = 0;
/* We should expect to encounter other main header marker segments
or an SOT marker segment next. */
dec->state = JPC_MH;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-190'], 'message': 'Fixed another integer overflow problem.'</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 jpc_dec_process_siz(jpc_dec_t *dec, jpc_ms_t *ms)
{
jpc_siz_t *siz = &ms->parms.siz;
int compno;
int tileno;
jpc_dec_tile_t *tile;
jpc_dec_tcomp_t *tcomp;
int htileno;
int vtileno;
jpc_dec_cmpt_t *cmpt;
size_t size;
dec->xstart = siz->xoff;
dec->ystart = siz->yoff;
dec->xend = siz->width;
dec->yend = siz->height;
dec->tilewidth = siz->tilewidth;
dec->tileheight = siz->tileheight;
dec->tilexoff = siz->tilexoff;
dec->tileyoff = siz->tileyoff;
dec->numcomps = siz->numcomps;
if (!(dec->cp = jpc_dec_cp_create(dec->numcomps))) {
return -1;
}
if (!(dec->cmpts = jas_alloc2(dec->numcomps, sizeof(jpc_dec_cmpt_t)))) {
return -1;
}
for (compno = 0, cmpt = dec->cmpts; compno < dec->numcomps; ++compno,
++cmpt) {
cmpt->prec = siz->comps[compno].prec;
cmpt->sgnd = siz->comps[compno].sgnd;
cmpt->hstep = siz->comps[compno].hsamp;
cmpt->vstep = siz->comps[compno].vsamp;
cmpt->width = JPC_CEILDIV(dec->xend, cmpt->hstep) -
JPC_CEILDIV(dec->xstart, cmpt->hstep);
cmpt->height = JPC_CEILDIV(dec->yend, cmpt->vstep) -
JPC_CEILDIV(dec->ystart, cmpt->vstep);
cmpt->hsubstep = 0;
cmpt->vsubstep = 0;
}
dec->image = 0;
dec->numhtiles = JPC_CEILDIV(dec->xend - dec->tilexoff, dec->tilewidth);
dec->numvtiles = JPC_CEILDIV(dec->yend - dec->tileyoff, dec->tileheight);
if (!jas_safe_size_mul(dec->numhtiles, dec->numvtiles, &size)) {
return -1;
}
dec->numtiles = size;
JAS_DBGLOG(10, ("numtiles = %d; numhtiles = %d; numvtiles = %d;\n",
dec->numtiles, dec->numhtiles, dec->numvtiles));
if (!(dec->tiles = jas_alloc2(dec->numtiles, sizeof(jpc_dec_tile_t)))) {
return -1;
}
for (tileno = 0, tile = dec->tiles; tileno < dec->numtiles; ++tileno,
++tile) {
htileno = tileno % dec->numhtiles;
vtileno = tileno / dec->numhtiles;
tile->realmode = 0;
tile->state = JPC_TILE_INIT;
tile->xstart = JAS_MAX(dec->tilexoff + htileno * dec->tilewidth,
dec->xstart);
tile->ystart = JAS_MAX(dec->tileyoff + vtileno * dec->tileheight,
dec->ystart);
tile->xend = JAS_MIN(dec->tilexoff + (htileno + 1) *
dec->tilewidth, dec->xend);
tile->yend = JAS_MIN(dec->tileyoff + (vtileno + 1) *
dec->tileheight, dec->yend);
tile->numparts = 0;
tile->partno = 0;
tile->pkthdrstream = 0;
tile->pkthdrstreampos = 0;
tile->pptstab = 0;
tile->cp = 0;
tile->pi = 0;
if (!(tile->tcomps = jas_alloc2(dec->numcomps,
sizeof(jpc_dec_tcomp_t)))) {
return -1;
}
for (compno = 0, cmpt = dec->cmpts, tcomp = tile->tcomps;
compno < dec->numcomps; ++compno, ++cmpt, ++tcomp) {
tcomp->rlvls = 0;
tcomp->numrlvls = 0;
tcomp->data = 0;
tcomp->xstart = JPC_CEILDIV(tile->xstart, cmpt->hstep);
tcomp->ystart = JPC_CEILDIV(tile->ystart, cmpt->vstep);
tcomp->xend = JPC_CEILDIV(tile->xend, cmpt->hstep);
tcomp->yend = JPC_CEILDIV(tile->yend, cmpt->vstep);
tcomp->tsfb = 0;
}
}
dec->pkthdrstreams = 0;
/* We should expect to encounter other main header marker segments
or an SOT marker segment next. */
dec->state = JPC_MH;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-399'], 'message': 'Ensure that not all tiles lie outside the image 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: long jpc_bitstream_getbits(jpc_bitstream_t *bitstream, int n)
{
long v;
int u;
/* We can reliably get at most 31 bits since ISO/IEC 9899 only
guarantees that a long can represent values up to 2^31-1. */
assert(n >= 0 && n < 32);
/* Get the number of bits requested from the specified bit stream. */
v = 0;
while (--n >= 0) {
if ((u = jpc_bitstream_getbit(bitstream)) < 0) {
return -1;
}
v = (v << 1) | u;
}
return v;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-703'], 'message': 'Changed the JPC bitstream code to more gracefully handle a request
for a larger sized integer than what can be handled (i.e., return
with an error instead of failing an assert).'</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 calcstepsizes(uint_fast16_t refstepsize, int numrlvls,
uint_fast16_t *stepsizes)
{
int bandno;
int numbands;
uint_fast16_t expn;
uint_fast16_t mant;
expn = JPC_QCX_GETEXPN(refstepsize);
mant = JPC_QCX_GETMANT(refstepsize);
numbands = 3 * numrlvls - 2;
for (bandno = 0; bandno < numbands; ++bandno) {
stepsizes[bandno] = JPC_QCX_MANT(mant) | JPC_QCX_EXPN(expn +
(numrlvls - 1) - (numrlvls - 1 - ((bandno > 0) ? ((bandno + 2) / 3) : (0))));
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-703'], 'message': 'Changed the JPC bitstream code to more gracefully handle a request
for a larger sized integer than what can be handled (i.e., return
with an error instead of failing an assert).'</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 jpc_siz_getparms(jpc_ms_t *ms, jpc_cstate_t *cstate,
jas_stream_t *in)
{
jpc_siz_t *siz = &ms->parms.siz;
unsigned int i;
uint_fast8_t tmp;
/* Eliminate compiler warning about unused variables. */
cstate = 0;
if (jpc_getuint16(in, &siz->caps) ||
jpc_getuint32(in, &siz->width) ||
jpc_getuint32(in, &siz->height) ||
jpc_getuint32(in, &siz->xoff) ||
jpc_getuint32(in, &siz->yoff) ||
jpc_getuint32(in, &siz->tilewidth) ||
jpc_getuint32(in, &siz->tileheight) ||
jpc_getuint32(in, &siz->tilexoff) ||
jpc_getuint32(in, &siz->tileyoff) ||
jpc_getuint16(in, &siz->numcomps)) {
return -1;
}
if (!siz->width || !siz->height || !siz->tilewidth ||
!siz->tileheight || !siz->numcomps || siz->numcomps > 16384) {
return -1;
}
if (siz->tilexoff >= siz->width || siz->tileyoff >= siz->height) {
jas_eprintf("all tiles are outside the image area\n");
return -1;
}
if (!(siz->comps = jas_alloc2(siz->numcomps, sizeof(jpc_sizcomp_t)))) {
return -1;
}
for (i = 0; i < siz->numcomps; ++i) {
if (jpc_getuint8(in, &tmp) ||
jpc_getuint8(in, &siz->comps[i].hsamp) ||
jpc_getuint8(in, &siz->comps[i].vsamp)) {
jas_free(siz->comps);
return -1;
}
if (siz->comps[i].hsamp == 0 || siz->comps[i].hsamp > 255) {
jas_eprintf("invalid XRsiz value %d\n", siz->comps[i].hsamp);
jas_free(siz->comps);
return -1;
}
if (siz->comps[i].vsamp == 0 || siz->comps[i].vsamp > 255) {
jas_eprintf("invalid YRsiz value %d\n", siz->comps[i].vsamp);
jas_free(siz->comps);
return -1;
}
siz->comps[i].sgnd = (tmp >> 7) & 1;
siz->comps[i].prec = (tmp & 0x7f) + 1;
}
if (jas_stream_eof(in)) {
jas_free(siz->comps);
return -1;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-703'], 'message': 'Added some missing sanity checks on the data in a SIZ marker segment.'</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: jas_seq2d_t *jas_seq2d_copy(jas_seq2d_t *x)
{
jas_matrix_t *y;
int i;
int j;
y = jas_seq2d_create(jas_seq2d_xstart(x), jas_seq2d_ystart(x),
jas_seq2d_xend(x), jas_seq2d_yend(x));
assert(y);
for (i = 0; i < x->numrows_; ++i) {
for (j = 0; j < x->numcols_; ++j) {
*jas_matrix_getref(y, i, j) = jas_matrix_get(x, i, j);
}
}
return y;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 main(int argc, char **argv)
{
int fmtid;
int id;
char *infile;
jas_stream_t *instream;
jas_image_t *image;
int width;
int height;
int depth;
int numcmpts;
int verbose;
char *fmtname;
int debug;
size_t max_mem;
if (jas_init()) {
abort();
}
cmdname = argv[0];
infile = 0;
verbose = 0;
debug = 0;
#if defined(JAS_DEFAULT_MAX_MEM_USAGE)
max_mem = JAS_DEFAULT_MAX_MEM_USAGE;
#endif
/* Parse the command line options. */
while ((id = jas_getopt(argc, argv, opts)) >= 0) {
switch (id) {
case OPT_VERBOSE:
verbose = 1;
break;
case OPT_VERSION:
printf("%s\n", JAS_VERSION);
exit(EXIT_SUCCESS);
break;
case OPT_DEBUG:
debug = atoi(jas_optarg);
break;
case OPT_INFILE:
infile = jas_optarg;
break;
case OPT_MAXMEM:
max_mem = strtoull(jas_optarg, 0, 10);
break;
case OPT_HELP:
default:
usage();
break;
}
}
jas_setdbglevel(debug);
#if defined(JAS_DEFAULT_MAX_MEM_USAGE)
jas_set_max_mem_usage(max_mem);
#endif
/* Open the image file. */
if (infile) {
/* The image is to be read from a file. */
if (!(instream = jas_stream_fopen(infile, "rb"))) {
fprintf(stderr, "cannot open input image file %s\n", infile);
exit(EXIT_FAILURE);
}
} else {
/* The image is to be read from standard input. */
if (!(instream = jas_stream_fdopen(0, "rb"))) {
fprintf(stderr, "cannot open standard input\n");
exit(EXIT_FAILURE);
}
}
if ((fmtid = jas_image_getfmt(instream)) < 0) {
fprintf(stderr, "unknown image format\n");
}
/* Decode the image. */
if (!(image = jas_image_decode(instream, fmtid, 0))) {
jas_stream_close(instream);
fprintf(stderr, "cannot load image\n");
return EXIT_FAILURE;
}
/* Close the image file. */
jas_stream_close(instream);
if (!(numcmpts = jas_image_numcmpts(image))) {
fprintf(stderr, "warning: image has no components\n");
}
if (numcmpts) {
width = jas_image_cmptwidth(image, 0);
height = jas_image_cmptheight(image, 0);
depth = jas_image_cmptprec(image, 0);
} else {
width = 0;
height = 0;
depth = 0;
}
if (!(fmtname = jas_image_fmttostr(fmtid))) {
abort();
}
printf("%s %d %d %d %d %ld\n", fmtname, numcmpts, width, height, depth, (long) jas_image_rawsize(image));
jas_image_destroy(image);
jas_image_clearfmts();
return EXIT_SUCCESS;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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: jas_image_t *bmp_decode(jas_stream_t *in, char *optstr)
{
jas_image_t *image;
bmp_hdr_t hdr;
bmp_info_t *info;
uint_fast16_t cmptno;
jas_image_cmptparm_t cmptparms[3];
jas_image_cmptparm_t *cmptparm;
uint_fast16_t numcmpts;
long n;
image = 0;
info = 0;
if (optstr) {
jas_eprintf("warning: ignoring BMP decoder options\n");
}
jas_eprintf(
"THE BMP FORMAT IS NOT FULLY SUPPORTED!\n"
"THAT IS, THE JASPER SOFTWARE CANNOT DECODE ALL TYPES OF BMP DATA.\n"
"IF YOU HAVE ANY PROBLEMS, PLEASE TRY CONVERTING YOUR IMAGE DATA\n"
"TO THE PNM FORMAT, AND USING THIS FORMAT INSTEAD.\n"
);
/* Read the bitmap header. */
if (bmp_gethdr(in, &hdr)) {
jas_eprintf("cannot get header\n");
goto error;
//return 0;
}
JAS_DBGLOG(1, (
"BMP header: magic 0x%x; siz %d; res1 %d; res2 %d; off %d\n",
hdr.magic, hdr.siz, hdr.reserved1, hdr.reserved2, hdr.off
));
/* Read the bitmap information. */
if (!(info = bmp_getinfo(in))) {
jas_eprintf("cannot get info\n");
//return 0;
goto error;
}
JAS_DBGLOG(1,
("BMP information: len %ld; width %ld; height %ld; numplanes %d; "
"depth %d; enctype %ld; siz %ld; hres %ld; vres %ld; numcolors %ld; "
"mincolors %ld\n", JAS_CAST(long, info->len),
JAS_CAST(long, info->width), JAS_CAST(long, info->height),
JAS_CAST(long, info->numplanes), JAS_CAST(long, info->depth),
JAS_CAST(long, info->enctype), JAS_CAST(long, info->siz),
JAS_CAST(long, info->hres), JAS_CAST(long, info->vres),
JAS_CAST(long, info->numcolors), JAS_CAST(long, info->mincolors)));
if (info->width < 0 || info->height < 0 || info->numplanes < 0 ||
info->depth < 0 || info->siz < 0 || info->hres < 0 || info->vres < 0) {
jas_eprintf("corrupt bit stream\n");
goto error;
}
/* Ensure that we support this type of BMP file. */
if (!bmp_issupported(&hdr, info)) {
jas_eprintf("error: unsupported BMP encoding\n");
//bmp_info_destroy(info);
//return 0;
goto error;
}
/* Skip over any useless data between the end of the palette
and start of the bitmap data. */
if ((n = hdr.off - (BMP_HDRLEN + BMP_INFOLEN + BMP_PALLEN(info))) < 0) {
jas_eprintf("error: possibly bad bitmap offset?\n");
goto error;
//return 0;
}
if (n > 0) {
jas_eprintf("skipping unknown data in BMP file\n");
if (bmp_gobble(in, n)) {
//bmp_info_destroy(info);
//return 0;
goto error;
}
}
/* Get the number of components. */
numcmpts = bmp_numcmpts(info);
for (cmptno = 0, cmptparm = cmptparms; cmptno < numcmpts; ++cmptno,
++cmptparm) {
cmptparm->tlx = 0;
cmptparm->tly = 0;
cmptparm->hstep = 1;
cmptparm->vstep = 1;
cmptparm->width = info->width;
cmptparm->height = info->height;
cmptparm->prec = 8;
cmptparm->sgnd = false;
}
/* Create image object. */
if (!(image = jas_image_create(numcmpts, cmptparms,
JAS_CLRSPC_UNKNOWN))) {
//bmp_info_destroy(info);
//return 0;
goto error;
}
if (numcmpts == 3) {
jas_image_setclrspc(image, JAS_CLRSPC_SRGB);
jas_image_setcmpttype(image, 0,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_RGB_R));
jas_image_setcmpttype(image, 1,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_RGB_G));
jas_image_setcmpttype(image, 2,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_RGB_B));
} else {
jas_image_setclrspc(image, JAS_CLRSPC_SGRAY);
jas_image_setcmpttype(image, 0,
JAS_IMAGE_CT_COLOR(JAS_CLRSPC_CHANIND_GRAY_Y));
}
/* Read the bitmap data. */
if (bmp_getdata(in, info, image)) {
//bmp_info_destroy(info);
//jas_image_destroy(image);
//return 0;
goto error;
}
bmp_info_destroy(info);
return image;
error:
if (info) {
bmp_info_destroy(info);
}
if (image) {
jas_image_destroy(image);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 pgx_gethdr(jas_stream_t *in, pgx_hdr_t *hdr)
{
int c;
uchar buf[2];
if ((c = jas_stream_getc(in)) == EOF) {
goto error;
}
buf[0] = c;
if ((c = jas_stream_getc(in)) == EOF) {
goto error;
}
buf[1] = c;
hdr->magic = buf[0] << 8 | buf[1];
if (hdr->magic != PGX_MAGIC) {
jas_eprintf("invalid PGX signature\n");
goto error;
}
if ((c = pgx_getc(in)) == EOF || !isspace(c)) {
goto error;
}
if (pgx_getbyteorder(in, &hdr->bigendian)) {
jas_eprintf("cannot get byte order\n");
goto error;
}
if (pgx_getsgnd(in, &hdr->sgnd)) {
jas_eprintf("cannot get signedness\n");
goto error;
}
if (pgx_getuint32(in, &hdr->prec)) {
jas_eprintf("cannot get precision\n");
goto error;
}
if (pgx_getuint32(in, &hdr->width)) {
jas_eprintf("cannot get width\n");
goto error;
}
if (pgx_getuint32(in, &hdr->height)) {
jas_eprintf("cannot get height\n");
goto error;
}
return 0;
error:
return -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_matrix_divpow2(jas_matrix_t *matrix, int n)
{
int i;
int j;
jas_seqent_t *rowstart;
int rowstep;
jas_seqent_t *data;
if (jas_matrix_numrows(matrix) > 0 && jas_matrix_numcols(matrix) > 0) {
assert(matrix->rows_);
rowstep = jas_matrix_rowstep(matrix);
for (i = matrix->numrows_, rowstart = matrix->rows_[0]; i > 0; --i,
rowstart += rowstep) {
for (j = matrix->numcols_, data = rowstart; j > 0; --j,
++data) {
*data = (*data >= 0) ? ((*data) >> n) :
(-((-(*data)) >> n));
}
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jpc_enc_encodemainhdr(jpc_enc_t *enc)
{
jpc_siz_t *siz;
jpc_cod_t *cod;
jpc_qcd_t *qcd;
int i;
long startoff;
long mainhdrlen;
jpc_enc_cp_t *cp;
jpc_qcc_t *qcc;
jpc_enc_tccp_t *tccp;
uint_fast16_t cmptno;
jpc_tsfb_band_t bandinfos[JPC_MAXBANDS];
jpc_fix_t mctsynweight;
jpc_enc_tcp_t *tcp;
jpc_tsfb_t *tsfb;
jpc_tsfb_band_t *bandinfo;
uint_fast16_t numbands;
uint_fast16_t bandno;
uint_fast16_t rlvlno;
uint_fast16_t analgain;
jpc_fix_t absstepsize;
char buf[1024];
jpc_com_t *com;
cp = enc->cp;
startoff = jas_stream_getrwcount(enc->out);
/* Write SOC marker segment. */
if (!(enc->mrk = jpc_ms_create(JPC_MS_SOC))) {
return -1;
}
if (jpc_putms(enc->out, enc->cstate, enc->mrk)) {
jas_eprintf("cannot write SOC marker\n");
return -1;
}
jpc_ms_destroy(enc->mrk);
enc->mrk = 0;
/* Write SIZ marker segment. */
if (!(enc->mrk = jpc_ms_create(JPC_MS_SIZ))) {
return -1;
}
siz = &enc->mrk->parms.siz;
siz->caps = 0;
siz->xoff = cp->imgareatlx;
siz->yoff = cp->imgareatly;
siz->width = cp->refgrdwidth;
siz->height = cp->refgrdheight;
siz->tilexoff = cp->tilegrdoffx;
siz->tileyoff = cp->tilegrdoffy;
siz->tilewidth = cp->tilewidth;
siz->tileheight = cp->tileheight;
siz->numcomps = cp->numcmpts;
siz->comps = jas_alloc2(siz->numcomps, sizeof(jpc_sizcomp_t));
assert(siz->comps);
for (i = 0; i < JAS_CAST(int, cp->numcmpts); ++i) {
siz->comps[i].prec = cp->ccps[i].prec;
siz->comps[i].sgnd = cp->ccps[i].sgnd;
siz->comps[i].hsamp = cp->ccps[i].sampgrdstepx;
siz->comps[i].vsamp = cp->ccps[i].sampgrdstepy;
}
if (jpc_putms(enc->out, enc->cstate, enc->mrk)) {
jas_eprintf("cannot write SIZ marker\n");
return -1;
}
jpc_ms_destroy(enc->mrk);
enc->mrk = 0;
if (!(enc->mrk = jpc_ms_create(JPC_MS_COM))) {
return -1;
}
sprintf(buf, "Creator: JasPer Version %s", jas_getversion());
com = &enc->mrk->parms.com;
com->len = JAS_CAST(uint_fast16_t, strlen(buf));
com->regid = JPC_COM_LATIN;
if (!(com->data = JAS_CAST(uchar *, jas_strdup(buf)))) {
abort();
}
if (jpc_putms(enc->out, enc->cstate, enc->mrk)) {
jas_eprintf("cannot write COM marker\n");
return -1;
}
jpc_ms_destroy(enc->mrk);
enc->mrk = 0;
#if 0
if (!(enc->mrk = jpc_ms_create(JPC_MS_CRG))) {
return -1;
}
crg = &enc->mrk->parms.crg;
crg->comps = jas_alloc2(crg->numcomps, sizeof(jpc_crgcomp_t));
if (jpc_putms(enc->out, enc->cstate, enc->mrk)) {
jas_eprintf("cannot write CRG marker\n");
return -1;
}
jpc_ms_destroy(enc->mrk);
enc->mrk = 0;
#endif
tcp = &cp->tcp;
tccp = &cp->tccp;
for (cmptno = 0; cmptno < cp->numcmpts; ++cmptno) {
tsfb = jpc_cod_gettsfb(tccp->qmfbid, tccp->maxrlvls - 1);
jpc_tsfb_getbands(tsfb, 0, 0, 1 << tccp->maxrlvls, 1 << tccp->maxrlvls,
bandinfos);
jpc_tsfb_destroy(tsfb);
mctsynweight = jpc_mct_getsynweight(tcp->mctid, cmptno);
numbands = 3 * tccp->maxrlvls - 2;
for (bandno = 0, bandinfo = bandinfos; bandno < numbands;
++bandno, ++bandinfo) {
rlvlno = (bandno) ? ((bandno - 1) / 3 + 1) : 0;
analgain = JPC_NOMINALGAIN(tccp->qmfbid, tccp->maxrlvls,
rlvlno, bandinfo->orient);
if (!tcp->intmode) {
absstepsize = jpc_fix_div(jpc_inttofix(1 <<
(analgain + 1)), bandinfo->synenergywt);
} else {
absstepsize = jpc_inttofix(1);
}
cp->ccps[cmptno].stepsizes[bandno] =
jpc_abstorelstepsize(absstepsize,
cp->ccps[cmptno].prec + analgain);
}
cp->ccps[cmptno].numstepsizes = numbands;
}
if (!(enc->mrk = jpc_ms_create(JPC_MS_COD))) {
return -1;
}
cod = &enc->mrk->parms.cod;
cod->csty = cp->tccp.csty | cp->tcp.csty;
cod->compparms.csty = cp->tccp.csty | cp->tcp.csty;
cod->compparms.numdlvls = cp->tccp.maxrlvls - 1;
cod->compparms.numrlvls = cp->tccp.maxrlvls;
cod->prg = cp->tcp.prg;
cod->numlyrs = cp->tcp.numlyrs;
cod->compparms.cblkwidthval = JPC_COX_CBLKSIZEEXPN(cp->tccp.cblkwidthexpn);
cod->compparms.cblkheightval = JPC_COX_CBLKSIZEEXPN(cp->tccp.cblkheightexpn);
cod->compparms.cblksty = cp->tccp.cblksty;
cod->compparms.qmfbid = cp->tccp.qmfbid;
cod->mctrans = (cp->tcp.mctid != JPC_MCT_NONE);
if (tccp->csty & JPC_COX_PRT) {
for (rlvlno = 0; rlvlno < tccp->maxrlvls; ++rlvlno) {
cod->compparms.rlvls[rlvlno].parwidthval = tccp->prcwidthexpns[rlvlno];
cod->compparms.rlvls[rlvlno].parheightval = tccp->prcheightexpns[rlvlno];
}
}
if (jpc_putms(enc->out, enc->cstate, enc->mrk)) {
jas_eprintf("cannot write COD marker\n");
return -1;
}
jpc_ms_destroy(enc->mrk);
enc->mrk = 0;
if (!(enc->mrk = jpc_ms_create(JPC_MS_QCD))) {
return -1;
}
qcd = &enc->mrk->parms.qcd;
qcd->compparms.qntsty = (tccp->qmfbid == JPC_COX_INS) ?
JPC_QCX_SEQNT : JPC_QCX_NOQNT;
qcd->compparms.numstepsizes = cp->ccps[0].numstepsizes;
qcd->compparms.numguard = cp->tccp.numgbits;
qcd->compparms.stepsizes = cp->ccps[0].stepsizes;
if (jpc_putms(enc->out, enc->cstate, enc->mrk)) {
return -1;
}
/* We do not want the step size array to be freed! */
qcd->compparms.stepsizes = 0;
jpc_ms_destroy(enc->mrk);
enc->mrk = 0;
tccp = &cp->tccp;
for (cmptno = 1; cmptno < cp->numcmpts; ++cmptno) {
if (!(enc->mrk = jpc_ms_create(JPC_MS_QCC))) {
return -1;
}
qcc = &enc->mrk->parms.qcc;
qcc->compno = cmptno;
qcc->compparms.qntsty = (tccp->qmfbid == JPC_COX_INS) ?
JPC_QCX_SEQNT : JPC_QCX_NOQNT;
qcc->compparms.numstepsizes = cp->ccps[cmptno].numstepsizes;
qcc->compparms.numguard = cp->tccp.numgbits;
qcc->compparms.stepsizes = cp->ccps[cmptno].stepsizes;
if (jpc_putms(enc->out, enc->cstate, enc->mrk)) {
return -1;
}
/* We do not want the step size array to be freed! */
qcc->compparms.stepsizes = 0;
jpc_ms_destroy(enc->mrk);
enc->mrk = 0;
}
#define MAINTLRLEN 2
mainhdrlen = jas_stream_getrwcount(enc->out) - startoff;
enc->len += mainhdrlen;
if (enc->cp->totalsize != UINT_FAST32_MAX) {
uint_fast32_t overhead;
overhead = mainhdrlen + MAINTLRLEN;
enc->mainbodysize = (enc->cp->totalsize >= overhead) ?
(enc->cp->totalsize - overhead) : 0;
} else {
enc->mainbodysize = UINT_FAST32_MAX;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jpc_ppm_getparms(jpc_ms_t *ms, jpc_cstate_t *cstate, jas_stream_t *in)
{
jpc_ppm_t *ppm = &ms->parms.ppm;
/* Eliminate compiler warning about unused variables. */
cstate = 0;
ppm->data = 0;
if (ms->len < 1) {
goto error;
}
if (jpc_getuint8(in, &ppm->ind)) {
goto error;
}
ppm->len = ms->len - 1;
if (ppm->len > 0) {
if (!(ppm->data = jas_malloc(ppm->len))) {
goto error;
}
if (JAS_CAST(uint, jas_stream_read(in, ppm->data, ppm->len)) != ppm->len) {
goto error;
}
} else {
ppm->data = 0;
}
return 0;
error:
jpc_ppm_destroyparms(ms);
return -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_iccgetuint64(jas_stream_t *in, jas_iccuint64_t *val)
{
ulonglong tmp;
if (jas_iccgetuint(in, 8, &tmp))
return -1;
*val = tmp;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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: jas_image_t *jas_image_create0()
{
jas_image_t *image;
if (!(image = jas_malloc(sizeof(jas_image_t)))) {
return 0;
}
image->tlx_ = 0;
image->tly_ = 0;
image->brx_ = 0;
image->bry_ = 0;
image->clrspc_ = JAS_CLRSPC_UNKNOWN;
image->numcmpts_ = 0;
image->maxcmpts_ = 0;
image->cmpts_ = 0;
image->inmem_ = true;
image->cmprof_ = 0;
return image;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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: jpc_streamlist_t *jpc_ppmstabtostreams(jpc_ppxstab_t *tab)
{
jpc_streamlist_t *streams;
uchar *dataptr;
uint_fast32_t datacnt;
uint_fast32_t tpcnt;
jpc_ppxstabent_t *ent;
int entno;
jas_stream_t *stream;
int n;
if (!(streams = jpc_streamlist_create())) {
goto error;
}
if (!tab->numents) {
return streams;
}
entno = 0;
ent = tab->ents[entno];
dataptr = ent->data;
datacnt = ent->len;
for (;;) {
/* Get the length of the packet header data for the current
tile-part. */
if (datacnt < 4) {
goto error;
}
if (!(stream = jas_stream_memopen(0, 0))) {
goto error;
}
if (jpc_streamlist_insert(streams, jpc_streamlist_numstreams(streams),
stream)) {
goto error;
}
tpcnt = (dataptr[0] << 24) | (dataptr[1] << 16) | (dataptr[2] << 8)
| dataptr[3];
datacnt -= 4;
dataptr += 4;
/* Get the packet header data for the current tile-part. */
while (tpcnt) {
if (!datacnt) {
if (++entno >= tab->numents) {
goto error;
}
ent = tab->ents[entno];
dataptr = ent->data;
datacnt = ent->len;
}
n = JAS_MIN(tpcnt, datacnt);
if (jas_stream_write(stream, dataptr, n) != n) {
goto error;
}
tpcnt -= n;
dataptr += n;
datacnt -= n;
}
jas_stream_rewind(stream);
if (!datacnt) {
if (++entno >= tab->numents) {
break;
}
ent = tab->ents[entno];
dataptr = ent->data;
datacnt = ent->len;
}
}
return streams;
error:
if (streams) {
jpc_streamlist_destroy(streams);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 ras_validate(jas_stream_t *in)
{
uchar buf[RAS_MAGICLEN];
int i;
int n;
uint_fast32_t magic;
assert(JAS_STREAM_MAXPUTBACK >= RAS_MAGICLEN);
/* Read the validation data (i.e., the data used for detecting
the format). */
if ((n = jas_stream_read(in, buf, RAS_MAGICLEN)) < 0) {
return -1;
}
/* Put the validation data back onto the stream, so that the
stream position will not be changed. */
for (i = n - 1; i >= 0; --i) {
if (jas_stream_ungetc(in, buf[i]) == EOF) {
return -1;
}
}
/* Did we read enough data? */
if (n < RAS_MAGICLEN) {
return -1;
}
magic = (JAS_CAST(uint_fast32_t, buf[0]) << 24) |
(JAS_CAST(uint_fast32_t, buf[1]) << 16) |
(JAS_CAST(uint_fast32_t, buf[2]) << 8) |
buf[3];
/* Is the signature correct for the Sun Rasterfile format? */
if (magic != RAS_MAGIC) {
return -1;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_iccgetuint(jas_stream_t *in, int n, ulonglong *val)
{
int i;
int c;
ulonglong v;
v = 0;
for (i = n; i > 0; --i) {
if ((c = jas_stream_getc(in)) == EOF)
return -1;
v = (v << 8) | c;
}
*val = v;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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: jas_image_t *jas_image_create(int numcmpts, jas_image_cmptparm_t *cmptparms,
int clrspc)
{
jas_image_t *image;
uint_fast32_t rawsize;
uint_fast32_t inmem;
int cmptno;
jas_image_cmptparm_t *cmptparm;
if (!(image = jas_image_create0())) {
return 0;
}
image->clrspc_ = clrspc;
image->maxcmpts_ = numcmpts;
image->inmem_ = true;
/* Allocate memory for the per-component information. */
if (!(image->cmpts_ = jas_alloc2(image->maxcmpts_,
sizeof(jas_image_cmpt_t *)))) {
jas_image_destroy(image);
return 0;
}
/* Initialize in case of failure. */
for (cmptno = 0; cmptno < image->maxcmpts_; ++cmptno) {
image->cmpts_[cmptno] = 0;
}
/* Compute the approximate raw size of the image. */
rawsize = 0;
for (cmptno = 0, cmptparm = cmptparms; cmptno < numcmpts; ++cmptno,
++cmptparm) {
rawsize += cmptparm->width * cmptparm->height *
(cmptparm->prec + 7) / 8;
}
/* Decide whether to buffer the image data in memory, based on the
raw size of the image. */
inmem = (rawsize < JAS_IMAGE_INMEMTHRESH);
/* Create the individual image components. */
for (cmptno = 0, cmptparm = cmptparms; cmptno < numcmpts; ++cmptno,
++cmptparm) {
if (!(image->cmpts_[cmptno] = jas_image_cmpt_create(cmptparm->tlx,
cmptparm->tly, cmptparm->hstep, cmptparm->vstep,
cmptparm->width, cmptparm->height, cmptparm->prec,
cmptparm->sgnd, inmem))) {
jas_image_destroy(image);
return 0;
}
++image->numcmpts_;
}
/* Determine the bounding box for all of the components on the
reference grid (i.e., the image area) */
jas_image_setbbox(image);
return image;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_memdump(FILE *out, void *data, size_t len)
{
size_t i;
size_t j;
uchar *dp;
dp = data;
for (i = 0; i < len; i += 16) {
fprintf(out, "%04zx:", i);
for (j = 0; j < 16; ++j) {
if (i + j < len) {
fprintf(out, " %02x", dp[i + j]);
}
}
fprintf(out, "\n");
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_matrix_setall(jas_matrix_t *matrix, jas_seqent_t val)
{
int i;
int j;
jas_seqent_t *rowstart;
int rowstep;
jas_seqent_t *data;
if (jas_matrix_numrows(matrix) > 0 && jas_matrix_numcols(matrix) > 0) {
assert(matrix->rows_);
rowstep = jas_matrix_rowstep(matrix);
for (i = matrix->numrows_, rowstart = matrix->rows_[0]; i > 0; --i,
rowstart += rowstep) {
for (j = matrix->numcols_, data = rowstart; j > 0; --j,
++data) {
*data = val;
}
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 mif_hdr_t *mif_hdr_get(jas_stream_t *in)
{
uchar magicbuf[MIF_MAGICLEN];
char buf[4096];
mif_hdr_t *hdr;
bool done;
jas_tvparser_t *tvp;
int id;
hdr = 0;
tvp = 0;
if (jas_stream_read(in, magicbuf, MIF_MAGICLEN) != MIF_MAGICLEN) {
goto error;
}
if (magicbuf[0] != (MIF_MAGIC >> 24) || magicbuf[1] != ((MIF_MAGIC >> 16) &
0xff) || magicbuf[2] != ((MIF_MAGIC >> 8) & 0xff) || magicbuf[3] !=
(MIF_MAGIC & 0xff)) {
jas_eprintf("error: bad signature\n");
goto error;
}
if (!(hdr = mif_hdr_create(0))) {
goto error;
}
done = false;
do {
if (!mif_getline(in, buf, sizeof(buf))) {
jas_eprintf("mif_getline failed\n");
goto error;
}
if (buf[0] == '\0') {
continue;
}
JAS_DBGLOG(10, ("header line: len=%d; %s\n", strlen(buf), buf));
if (!(tvp = jas_tvparser_create(buf))) {
jas_eprintf("jas_tvparser_create failed\n");
goto error;
}
if (jas_tvparser_next(tvp)) {
jas_eprintf("cannot get record type\n");
goto error;
}
id = jas_taginfo_nonull(jas_taginfos_lookup(mif_tags2,
jas_tvparser_gettag(tvp)))->id;
jas_tvparser_destroy(tvp);
tvp = 0;
switch (id) {
case MIF_CMPT:
if (mif_process_cmpt(hdr, buf)) {
jas_eprintf("cannot get component information\n");
goto error;
}
break;
case MIF_END:
done = 1;
break;
default:
jas_eprintf("invalid header information: %s\n", buf);
goto error;
break;
}
} while (!done);
return hdr;
error:
if (hdr) {
mif_hdr_destroy(hdr);
}
if (tvp) {
jas_tvparser_destroy(tvp);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_matrix_asr(jas_matrix_t *matrix, int n)
{
int i;
int j;
jas_seqent_t *rowstart;
int rowstep;
jas_seqent_t *data;
assert(n >= 0);
if (jas_matrix_numrows(matrix) > 0 && jas_matrix_numcols(matrix) > 0) {
assert(matrix->rows_);
rowstep = jas_matrix_rowstep(matrix);
for (i = matrix->numrows_, rowstart = matrix->rows_[0]; i > 0; --i,
rowstart += rowstep) {
for (j = matrix->numcols_, data = rowstart; j > 0; --j,
++data) {
//*data >>= n;
*data = jas_seqent_asr(*data, n);
}
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_matrix_clip(jas_matrix_t *matrix, jas_seqent_t minval,
jas_seqent_t maxval)
{
int i;
int j;
jas_seqent_t v;
jas_seqent_t *rowstart;
jas_seqent_t *data;
int rowstep;
if (jas_matrix_numrows(matrix) > 0 && jas_matrix_numcols(matrix) > 0) {
assert(matrix->rows_);
rowstep = jas_matrix_rowstep(matrix);
for (i = matrix->numrows_, rowstart = matrix->rows_[0]; i > 0; --i,
rowstart += rowstep) {
data = rowstart;
for (j = matrix->numcols_, data = rowstart; j > 0; --j,
++data) {
v = *data;
if (v < minval) {
*data = minval;
} else if (v > maxval) {
*data = maxval;
}
}
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 bmp_validate(jas_stream_t *in)
{
int n;
int i;
uchar buf[2];
assert(JAS_STREAM_MAXPUTBACK >= 2);
/* Read the first two characters that constitute the signature. */
if ((n = jas_stream_read(in, (char *) buf, 2)) < 0) {
return -1;
}
/* Put the characters read back onto the stream. */
for (i = n - 1; i >= 0; --i) {
if (jas_stream_ungetc(in, buf[i]) == EOF) {
return -1;
}
}
/* Did we read enough characters? */
if (n < 2) {
return -1;
}
/* Is the signature correct for the BMP format? */
if (buf[0] == (BMP_MAGIC & 0xff) && buf[1] == (BMP_MAGIC >> 8)) {
return 0;
}
return -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_image_cmpt_t *jas_image_cmpt_create(int_fast32_t tlx,
int_fast32_t tly, int_fast32_t hstep, int_fast32_t vstep,
int_fast32_t width, int_fast32_t height, uint_fast16_t depth, bool sgnd,
uint_fast32_t inmem)
{
jas_image_cmpt_t *cmpt;
size_t size;
cmpt = 0;
if (width < 0 || height < 0 || hstep <= 0 || vstep <= 0) {
goto error;
}
if (!jas_safe_intfast32_add(tlx, width, 0) ||
!jas_safe_intfast32_add(tly, height, 0)) {
goto error;
}
if (!(cmpt = jas_malloc(sizeof(jas_image_cmpt_t)))) {
goto error;
}
cmpt->type_ = JAS_IMAGE_CT_UNKNOWN;
cmpt->tlx_ = tlx;
cmpt->tly_ = tly;
cmpt->hstep_ = hstep;
cmpt->vstep_ = vstep;
cmpt->width_ = width;
cmpt->height_ = height;
cmpt->prec_ = depth;
cmpt->sgnd_ = sgnd;
cmpt->stream_ = 0;
cmpt->cps_ = (depth + 7) / 8;
// Compute the number of samples in the image component, while protecting
// against overflow.
// size = cmpt->width_ * cmpt->height_ * cmpt->cps_;
if (!jas_safe_size_mul(cmpt->width_, cmpt->height_, &size) ||
!jas_safe_size_mul(size, cmpt->cps_, &size)) {
goto error;
}
cmpt->stream_ = (inmem) ? jas_stream_memopen2(0, size) :
jas_stream_tmpfile();
if (!cmpt->stream_) {
goto error;
}
/* Zero the component data. This isn't necessary, but it is
convenient for debugging purposes. */
/* Note: conversion of size - 1 to long can overflow */
if (size > 0) {
if (size - 1 > LONG_MAX) {
goto error;
}
if (jas_stream_seek(cmpt->stream_, size - 1, SEEK_SET) < 0 ||
jas_stream_putc(cmpt->stream_, 0) == EOF ||
jas_stream_seek(cmpt->stream_, 0, SEEK_SET) < 0) {
goto error;
}
}
return cmpt;
error:
if (cmpt) {
jas_image_cmpt_destroy(cmpt);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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: jpc_ms_t *jpc_getms(jas_stream_t *in, jpc_cstate_t *cstate)
{
jpc_ms_t *ms;
jpc_mstabent_t *mstabent;
jas_stream_t *tmpstream;
if (!(ms = jpc_ms_create(0))) {
return 0;
}
/* Get the marker type. */
if (jpc_getuint16(in, &ms->id) || ms->id < JPC_MS_MIN ||
ms->id > JPC_MS_MAX) {
jpc_ms_destroy(ms);
return 0;
}
mstabent = jpc_mstab_lookup(ms->id);
ms->ops = &mstabent->ops;
/* Get the marker segment length and parameters if present. */
/* Note: It is tacitly assumed that a marker segment cannot have
parameters unless it has a length field. That is, there cannot
be a parameters field without a length field and vice versa. */
if (JPC_MS_HASPARMS(ms->id)) {
/* Get the length of the marker segment. */
if (jpc_getuint16(in, &ms->len) || ms->len < 3) {
jpc_ms_destroy(ms);
return 0;
}
/* Calculate the length of the marker segment parameters. */
ms->len -= 2;
/* Create and prepare a temporary memory stream from which to
read the marker segment parameters. */
/* Note: This approach provides a simple way of ensuring that
we never read beyond the end of the marker segment (even if
the marker segment length is errantly set too small). */
if (!(tmpstream = jas_stream_memopen(0, 0))) {
jpc_ms_destroy(ms);
return 0;
}
if (jas_stream_copy(tmpstream, in, ms->len) ||
jas_stream_seek(tmpstream, 0, SEEK_SET) < 0) {
jas_stream_close(tmpstream);
jpc_ms_destroy(ms);
return 0;
}
/* Get the marker segment parameters. */
if ((*ms->ops->getparms)(ms, cstate, tmpstream)) {
ms->ops = 0;
jpc_ms_destroy(ms);
jas_stream_close(tmpstream);
return 0;
}
if (jas_getdbglevel() > 0) {
jpc_ms_dump(ms, stderr);
}
if (JAS_CAST(ulong, jas_stream_tell(tmpstream)) != ms->len) {
jas_eprintf(
"warning: trailing garbage in marker segment (%ld bytes)\n",
ms->len - jas_stream_tell(tmpstream));
}
/* Close the temporary stream. */
jas_stream_close(tmpstream);
} else {
/* There are no marker segment parameters. */
ms->len = 0;
if (jas_getdbglevel() > 0) {
jpc_ms_dump(ms, stderr);
}
}
/* Update the code stream state information based on the type of
marker segment read. */
/* Note: This is a bit of a hack, but I'm not going to define another
type of virtual function for this one special case. */
if (ms->id == JPC_MS_SIZ) {
cstate->numcomps = ms->parms.siz.numcomps;
}
return ms;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 long decode_twos_comp(ulong c, int prec)
{
long result;
assert(prec >= 2);
jas_eprintf("warning: support for signed data is untested\n");
// NOTE: Is this correct?
result = (c & ((1 << (prec - 1)) - 1)) - (c & (1 << (prec - 1)));
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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: jas_matrix_t *jas_matrix_copy(jas_matrix_t *x)
{
jas_matrix_t *y;
int i;
int j;
y = jas_matrix_create(x->numrows_, x->numcols_);
for (i = 0; i < x->numrows_; ++i) {
for (j = 0; j < x->numcols_; ++j) {
*jas_matrix_getref(y, i, j) = jas_matrix_get(x, i, j);
}
}
return y;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 jas_iccgetuint32(jas_stream_t *in, jas_iccuint32_t *val)
{
ulonglong tmp;
if (jas_iccgetuint(in, 4, &tmp))
return -1;
*val = tmp;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-190'], 'message': 'The generation of the configuration file jas_config.h has been completely
reworked in order to avoid pollution of the global namespace.
Some problematic types like uchar, ulong, and friends have been replaced
with names with a jas_ prefix.
An option max_samples has been added to the BMP and JPEG decoders to
restrict the maximum size of image that they can decode. This change
was made as a (possibly temporary) fix to address security concerns.
A max_samples command-line option has also been added to imginfo.
Whether an image component (for jas_image_t) is stored in memory or on
disk is now based on the component size (rather than the image size).
Some debug log message were added.
Some new integer overflow checks were added.
Some new safe integer add/multiply functions were added.
More pre-C99 cruft was removed. JasPer has numerous "hacks" to
handle pre-C99 compilers. JasPer now assumes C99 support. So, this
pre-C99 cruft is unnecessary and can be removed.
The regression jasper-doublefree-mem_close.jpg has been re-enabled.
Theoretically, it should work more predictably now.'</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 calcstepsizes(uint_fast16_t refstepsize, int numrlvls,
uint_fast16_t *stepsizes)
{
int bandno;
int numbands;
uint_fast16_t expn;
uint_fast16_t mant;
expn = JPC_QCX_GETEXPN(refstepsize);
mant = JPC_QCX_GETMANT(refstepsize);
numbands = 3 * numrlvls - 2;
for (bandno = 0; bandno < numbands; ++bandno) {
//jas_eprintf("DEBUG %d %d %d %d %d\n", bandno, expn, numrlvls, bandno, ((numrlvls - 1) - (numrlvls - 1 - ((bandno > 0) ? ((bandno + 2) / 3) : (0)))));
stepsizes[bandno] = JPC_QCX_MANT(mant) | JPC_QCX_EXPN(expn + (bandno + 2) / 3);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-617'], 'message': 'jpc_dec: check for JPC_QCX_EXPN() parameter overflow
Avoid the assertion failure in the JPC_QCX_EXPN() function. While the
"expn" variable cannot be bigger than 0x1f, adding something to it may
exceed that limit.
This condition could be exploited with a malicious JP2 file, allowing
a denial of service attack on processes which parse JP2 files.
Fixes CVE-2016-9399 and CVE-2017-13751
Closes https://github.com/jasper-maint/jasper/issues/1'</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: MagickExport MagickBooleanType SetImageProperty(Image *image,
const char *property,const char *value,ExceptionInfo *exception)
{
MagickBooleanType
status;
MagickStatusType
flags;
assert(image != (Image *) NULL);
assert(image->signature == MagickCoreSignature);
if (image->debug != MagickFalse)
(void) LogMagickEvent(TraceEvent,GetMagickModule(),"%s",image->filename);
if (image->properties == (void *) NULL)
image->properties=NewSplayTree(CompareSplayTreeString,
RelinquishMagickMemory,RelinquishMagickMemory); /* create splay-tree */
if (value == (const char *) NULL)
return(DeleteImageProperty(image,property)); /* delete if NULL */
status=MagickTrue;
if (strlen(property) <= 1)
{
/*
Do not 'set' single letter properties - read only shorthand.
*/
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
/* FUTURE: binary chars or quotes in key should produce a error */
/* Set attributes with known names or special prefixes
return result is found, or break to set a free form properity
*/
switch (*property)
{
#if 0 /* Percent escape's sets values with this prefix: for later use
Throwing an exception causes this setting to fail */
case '8':
{
if (LocaleNCompare("8bim:",property,5) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break;
}
#endif
case 'B':
case 'b':
{
if (LocaleCompare("background",property) == 0)
{
(void) QueryColorCompliance(value,AllCompliance,
&image->background_color,exception);
/* check for FUTURE: value exception?? */
/* also add user input to splay tree */
}
break; /* not an attribute, add as a property */
}
case 'C':
case 'c':
{
if (LocaleCompare("channels",property) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
if (LocaleCompare("colorspace",property) == 0)
{
ssize_t
colorspace;
colorspace=ParseCommandOption(MagickColorspaceOptions,MagickFalse,
value);
if (colorspace < 0)
return(MagickFalse); /* FUTURE: value exception?? */
return(SetImageColorspace(image,(ColorspaceType) colorspace,exception));
}
if (LocaleCompare("compose",property) == 0)
{
ssize_t
compose;
compose=ParseCommandOption(MagickComposeOptions,MagickFalse,value);
if (compose < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->compose=(CompositeOperator) compose;
return(MagickTrue);
}
if (LocaleCompare("compress",property) == 0)
{
ssize_t
compression;
compression=ParseCommandOption(MagickCompressOptions,MagickFalse,
value);
if (compression < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->compression=(CompressionType) compression;
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
case 'D':
case 'd':
{
if (LocaleCompare("delay",property) == 0)
{
GeometryInfo
geometry_info;
flags=ParseGeometry(value,&geometry_info);
if ((flags & GreaterValue) != 0)
{
if (image->delay > (size_t) floor(geometry_info.rho+0.5))
image->delay=(size_t) floor(geometry_info.rho+0.5);
}
else
if ((flags & LessValue) != 0)
{
if (image->delay < (size_t) floor(geometry_info.rho+0.5))
image->delay=(ssize_t)
floor(geometry_info.sigma+0.5);
}
else
image->delay=(size_t) floor(geometry_info.rho+0.5);
if ((flags & SigmaValue) != 0)
image->ticks_per_second=(ssize_t) floor(geometry_info.sigma+0.5);
return(MagickTrue);
}
if (LocaleCompare("delay_units",property) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
if (LocaleCompare("density",property) == 0)
{
GeometryInfo
geometry_info;
flags=ParseGeometry(value,&geometry_info);
image->resolution.x=geometry_info.rho;
image->resolution.y=geometry_info.sigma;
if ((flags & SigmaValue) == 0)
image->resolution.y=image->resolution.x;
return(MagickTrue);
}
if (LocaleCompare("depth",property) == 0)
{
image->depth=StringToUnsignedLong(value);
return(MagickTrue);
}
if (LocaleCompare("dispose",property) == 0)
{
ssize_t
dispose;
dispose=ParseCommandOption(MagickDisposeOptions,MagickFalse,value);
if (dispose < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->dispose=(DisposeType) dispose;
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
#if 0 /* Percent escape's sets values with this prefix: for later use
Throwing an exception causes this setting to fail */
case 'E':
case 'e':
{
if (LocaleNCompare("exif:",property,5) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
}
case 'F':
case 'f':
{
if (LocaleNCompare("fx:",property,3) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
}
#endif
case 'G':
case 'g':
{
if (LocaleCompare("gamma",property) == 0)
{
image->gamma=StringToDouble(value,(char **) NULL);
return(MagickTrue);
}
if (LocaleCompare("gravity",property) == 0)
{
ssize_t
gravity;
gravity=ParseCommandOption(MagickGravityOptions,MagickFalse,value);
if (gravity < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->gravity=(GravityType) gravity;
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
case 'H':
case 'h':
{
if (LocaleCompare("height",property) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
}
case 'I':
case 'i':
{
if (LocaleCompare("intensity",property) == 0)
{
ssize_t
intensity;
intensity=ParseCommandOption(MagickIntentOptions,MagickFalse,value);
if (intensity < 0)
return(MagickFalse);
image->intensity=(PixelIntensityMethod) intensity;
return(MagickTrue);
}
if (LocaleCompare("intent",property) == 0)
{
ssize_t
rendering_intent;
rendering_intent=ParseCommandOption(MagickIntentOptions,MagickFalse,
value);
if (rendering_intent < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->rendering_intent=(RenderingIntent) rendering_intent;
return(MagickTrue);
}
if (LocaleCompare("interpolate",property) == 0)
{
ssize_t
interpolate;
interpolate=ParseCommandOption(MagickInterpolateOptions,MagickFalse,
value);
if (interpolate < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->interpolate=(PixelInterpolateMethod) interpolate;
return(MagickTrue);
}
#if 0 /* Percent escape's sets values with this prefix: for later use
Throwing an exception causes this setting to fail */
if (LocaleNCompare("iptc:",property,5) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
#endif
break; /* not an attribute, add as a property */
}
case 'K':
case 'k':
if (LocaleCompare("kurtosis",property) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
case 'L':
case 'l':
{
if (LocaleCompare("loop",property) == 0)
{
image->iterations=StringToUnsignedLong(value);
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
case 'M':
case 'm':
if ((LocaleCompare("magick",property) == 0) ||
(LocaleCompare("max",property) == 0) ||
(LocaleCompare("mean",property) == 0) ||
(LocaleCompare("min",property) == 0) ||
(LocaleCompare("min",property) == 0))
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
case 'O':
case 'o':
if (LocaleCompare("opaque",property) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
case 'P':
case 'p':
{
if (LocaleCompare("page",property) == 0)
{
char
*geometry;
geometry=GetPageGeometry(value);
flags=ParseAbsoluteGeometry(geometry,&image->page);
geometry=DestroyString(geometry);
return(MagickTrue);
}
#if 0 /* Percent escape's sets values with this prefix: for later use
Throwing an exception causes this setting to fail */
if (LocaleNCompare("pixel:",property,6) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
#endif
if (LocaleCompare("profile",property) == 0)
{
ImageInfo
*image_info;
StringInfo
*profile;
image_info=AcquireImageInfo();
(void) CopyMagickString(image_info->filename,value,MagickPathExtent);
(void) SetImageInfo(image_info,1,exception);
profile=FileToStringInfo(image_info->filename,~0UL,exception);
if (profile != (StringInfo *) NULL)
status=SetImageProfile(image,image_info->magick,profile,exception);
image_info=DestroyImageInfo(image_info);
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
case 'R':
case 'r':
{
if (LocaleCompare("rendering-intent",property) == 0)
{
ssize_t
rendering_intent;
rendering_intent=ParseCommandOption(MagickIntentOptions,MagickFalse,
value);
if (rendering_intent < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->rendering_intent=(RenderingIntent) rendering_intent;
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
case 'S':
case 's':
if ((LocaleCompare("size",property) == 0) ||
(LocaleCompare("skewness",property) == 0) ||
(LocaleCompare("scenes",property) == 0) ||
(LocaleCompare("standard-deviation",property) == 0))
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
case 'T':
case 't':
{
if (LocaleCompare("tile-offset",property) == 0)
{
char
*geometry;
geometry=GetPageGeometry(value);
flags=ParseAbsoluteGeometry(geometry,&image->tile_offset);
geometry=DestroyString(geometry);
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
case 'U':
case 'u':
{
if (LocaleCompare("units",property) == 0)
{
ssize_t
units;
units=ParseCommandOption(MagickResolutionOptions,MagickFalse,value);
if (units < 0)
return(MagickFalse); /* FUTURE: value exception?? */
image->units=(ResolutionType) units;
return(MagickTrue);
}
break; /* not an attribute, add as a property */
}
case 'V':
case 'v':
{
if (LocaleCompare("version",property) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
}
case 'W':
case 'w':
{
if (LocaleCompare("width",property) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
}
#if 0 /* Percent escape's sets values with this prefix: for later use
Throwing an exception causes this setting to fail */
case 'X':
case 'x':
{
if (LocaleNCompare("xmp:",property,4) == 0)
{
(void) ThrowMagickException(exception,GetMagickModule(),OptionError,
"SetReadOnlyProperty","`%s'",property);
return(MagickFalse);
}
break; /* not an attribute, add as a property */
}
#endif
}
/* Default: not an attribute, add as a property */
status=AddValueToSplayTree((SplayTreeInfo *) image->properties,
ConstantString(property),ConstantString(value));
/* FUTURE: error if status is bad? */
return(status);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'https://github.com/ImageMagick/ImageMagick/issues/298'</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 MagickBooleanType WriteTXTImage(const ImageInfo *image_info,Image *image,
ExceptionInfo *exception)
{
char
buffer[MagickPathExtent],
colorspace[MagickPathExtent],
tuple[MagickPathExtent];
MagickBooleanType
status;
MagickOffsetType
scene;
PixelInfo
pixel;
register const Quantum
*p;
register ssize_t
x;
ssize_t
y;
/*
Open output image file.
*/
assert(image_info != (const ImageInfo *) NULL);
assert(image_info->signature == MagickCoreSignature);
assert(image != (Image *) NULL);
assert(image->signature == MagickCoreSignature);
if (image->debug != MagickFalse)
(void) LogMagickEvent(TraceEvent,GetMagickModule(),"%s",image->filename);
status=OpenBlob(image_info,image,WriteBlobMode,exception);
if (status == MagickFalse)
return(status);
scene=0;
do
{
ComplianceType
compliance;
const char
*value;
(void) CopyMagickString(colorspace,CommandOptionToMnemonic(
MagickColorspaceOptions,(ssize_t) image->colorspace),MagickPathExtent);
LocaleLower(colorspace);
image->depth=GetImageQuantumDepth(image,MagickTrue);
if (image->alpha_trait != UndefinedPixelTrait)
(void) ConcatenateMagickString(colorspace,"a",MagickPathExtent);
compliance=NoCompliance;
value=GetImageOption(image_info,"txt:compliance");
if (value != (char *) NULL)
compliance=(ComplianceType) ParseCommandOption(MagickComplianceOptions,
MagickFalse,value);
if (LocaleCompare(image_info->magick,"SPARSE-COLOR") != 0)
{
size_t
depth;
depth=compliance == SVGCompliance ? image->depth :
MAGICKCORE_QUANTUM_DEPTH;
(void) FormatLocaleString(buffer,MagickPathExtent,
"# ImageMagick pixel enumeration: %.20g,%.20g,%.20g,%s\n",(double)
image->columns,(double) image->rows,(double) ((MagickOffsetType)
GetQuantumRange(depth)),colorspace);
(void) WriteBlobString(image,buffer);
}
GetPixelInfo(image,&pixel);
for (y=0; y < (ssize_t) image->rows; y++)
{
p=GetVirtualPixels(image,0,y,image->columns,1,exception);
if (p == (const Quantum *) NULL)
break;
for (x=0; x < (ssize_t) image->columns; x++)
{
GetPixelInfoPixel(image,p,&pixel);
if (pixel.colorspace == LabColorspace)
{
pixel.green-=(QuantumRange+1)/2.0;
pixel.blue-=(QuantumRange+1)/2.0;
}
if (LocaleCompare(image_info->magick,"SPARSE-COLOR") == 0)
{
/*
Sparse-color format.
*/
if (GetPixelAlpha(image,p) == (Quantum) OpaqueAlpha)
{
GetColorTuple(&pixel,MagickFalse,tuple);
(void) FormatLocaleString(buffer,MagickPathExtent,
"%.20g,%.20g,",(double) x,(double) y);
(void) WriteBlobString(image,buffer);
(void) WriteBlobString(image,tuple);
(void) WriteBlobString(image," ");
}
p+=GetPixelChannels(image);
continue;
}
(void) FormatLocaleString(buffer,MagickPathExtent,"%.20g,%.20g: ",
(double) x,(double) y);
(void) WriteBlobString(image,buffer);
(void) CopyMagickString(tuple,"(",MagickPathExtent);
if (pixel.colorspace == GRAYColorspace)
ConcatenateColorComponent(&pixel,GrayPixelChannel,compliance,
tuple);
else
{
ConcatenateColorComponent(&pixel,RedPixelChannel,compliance,tuple);
(void) ConcatenateMagickString(tuple,",",MagickPathExtent);
ConcatenateColorComponent(&pixel,GreenPixelChannel,compliance,
tuple);
(void) ConcatenateMagickString(tuple,",",MagickPathExtent);
ConcatenateColorComponent(&pixel,BluePixelChannel,compliance,tuple);
}
if (pixel.colorspace == CMYKColorspace)
{
(void) ConcatenateMagickString(tuple,",",MagickPathExtent);
ConcatenateColorComponent(&pixel,BlackPixelChannel,compliance,
tuple);
}
if (pixel.alpha_trait != UndefinedPixelTrait)
{
(void) ConcatenateMagickString(tuple,",",MagickPathExtent);
ConcatenateColorComponent(&pixel,AlphaPixelChannel,compliance,
tuple);
}
(void) ConcatenateMagickString(tuple,")",MagickPathExtent);
(void) WriteBlobString(image,tuple);
(void) WriteBlobString(image," ");
GetColorTuple(&pixel,MagickTrue,tuple);
(void) FormatLocaleString(buffer,MagickPathExtent,"%s",tuple);
(void) WriteBlobString(image,buffer);
(void) WriteBlobString(image," ");
(void) QueryColorname(image,&pixel,SVGCompliance,tuple,exception);
(void) WriteBlobString(image,tuple);
(void) WriteBlobString(image,"\n");
p+=GetPixelChannels(image);
}
status=SetImageProgress(image,SaveImageTag,(MagickOffsetType) y,
image->rows);
if (status == MagickFalse)
break;
}
if (GetNextImageInList(image) == (Image *) NULL)
break;
image=SyncNextImageInList(image);
status=SetImageProgress(image,SaveImagesTag,scene++,
GetImageListLength(image));
if (status == MagickFalse)
break;
} while (image_info->adjoin != MagickFalse);
(void) CloseBlob(image);
return(MagickTrue);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'https://github.com/ImageMagick/ImageMagick/issues/298'</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: did_set_string_option(
int opt_idx, /* index in options[] table */
char_u **varp, /* pointer to the option variable */
int new_value_alloced, /* new value was allocated */
char_u *oldval, /* previous value of the option */
char_u *errbuf, /* buffer for errors, or NULL */
int opt_flags) /* OPT_LOCAL and/or OPT_GLOBAL */
{
char_u *errmsg = NULL;
char_u *s, *p;
int did_chartab = FALSE;
char_u **gvarp;
long_u free_oldval = (options[opt_idx].flags & P_ALLOCED);
#ifdef FEAT_GUI
/* set when changing an option that only requires a redraw in the GUI */
int redraw_gui_only = FALSE;
#endif
/* Get the global option to compare with, otherwise we would have to check
* two values for all local options. */
gvarp = (char_u **)get_varp_scope(&(options[opt_idx]), OPT_GLOBAL);
/* Disallow changing some options from secure mode */
if ((secure
#ifdef HAVE_SANDBOX
|| sandbox != 0
#endif
) && (options[opt_idx].flags & P_SECURE))
{
errmsg = e_secure;
}
/* Check for a "normal" file name in some options. Disallow a path
* separator (slash and/or backslash), wildcards and characters that are
* often illegal in a file name. */
else if ((options[opt_idx].flags & P_NFNAME)
&& vim_strpbrk(*varp, (char_u *)"/\\*?[|<>") != NULL)
{
errmsg = e_invarg;
}
/* 'term' */
else if (varp == &T_NAME)
{
if (T_NAME[0] == NUL)
errmsg = (char_u *)N_("E529: Cannot set 'term' to empty string");
#ifdef FEAT_GUI
if (gui.in_use)
errmsg = (char_u *)N_("E530: Cannot change term in GUI");
else if (term_is_gui(T_NAME))
errmsg = (char_u *)N_("E531: Use \":gui\" to start the GUI");
#endif
else if (set_termname(T_NAME) == FAIL)
errmsg = (char_u *)N_("E522: Not found in termcap");
else
/* Screen colors may have changed. */
redraw_later_clear();
}
/* 'backupcopy' */
else if (gvarp == &p_bkc)
{
char_u *bkc = p_bkc;
unsigned int *flags = &bkc_flags;
if (opt_flags & OPT_LOCAL)
{
bkc = curbuf->b_p_bkc;
flags = &curbuf->b_bkc_flags;
}
if ((opt_flags & OPT_LOCAL) && *bkc == NUL)
/* make the local value empty: use the global value */
*flags = 0;
else
{
if (opt_strings_flags(bkc, p_bkc_values, flags, TRUE) != OK)
errmsg = e_invarg;
if ((((int)*flags & BKC_AUTO) != 0)
+ (((int)*flags & BKC_YES) != 0)
+ (((int)*flags & BKC_NO) != 0) != 1)
{
/* Must have exactly one of "auto", "yes" and "no". */
(void)opt_strings_flags(oldval, p_bkc_values, flags, TRUE);
errmsg = e_invarg;
}
}
}
/* 'backupext' and 'patchmode' */
else if (varp == &p_bex || varp == &p_pm)
{
if (STRCMP(*p_bex == '.' ? p_bex + 1 : p_bex,
*p_pm == '.' ? p_pm + 1 : p_pm) == 0)
errmsg = (char_u *)N_("E589: 'backupext' and 'patchmode' are equal");
}
#ifdef FEAT_LINEBREAK
/* 'breakindentopt' */
else if (varp == &curwin->w_p_briopt)
{
if (briopt_check(curwin) == FAIL)
errmsg = e_invarg;
}
#endif
/*
* 'isident', 'iskeyword', 'isprint or 'isfname' option: refill g_chartab[]
* If the new option is invalid, use old value. 'lisp' option: refill
* g_chartab[] for '-' char
*/
else if ( varp == &p_isi
|| varp == &(curbuf->b_p_isk)
|| varp == &p_isp
|| varp == &p_isf)
{
if (init_chartab() == FAIL)
{
did_chartab = TRUE; /* need to restore it below */
errmsg = e_invarg; /* error in value */
}
}
/* 'helpfile' */
else if (varp == &p_hf)
{
/* May compute new values for $VIM and $VIMRUNTIME */
if (didset_vim)
{
vim_setenv((char_u *)"VIM", (char_u *)"");
didset_vim = FALSE;
}
if (didset_vimruntime)
{
vim_setenv((char_u *)"VIMRUNTIME", (char_u *)"");
didset_vimruntime = FALSE;
}
}
#ifdef FEAT_SYN_HL
/* 'colorcolumn' */
else if (varp == &curwin->w_p_cc)
errmsg = check_colorcolumn(curwin);
#endif
#ifdef FEAT_MULTI_LANG
/* 'helplang' */
else if (varp == &p_hlg)
{
/* Check for "", "ab", "ab,cd", etc. */
for (s = p_hlg; *s != NUL; s += 3)
{
if (s[1] == NUL || ((s[2] != ',' || s[3] == NUL) && s[2] != NUL))
{
errmsg = e_invarg;
break;
}
if (s[2] == NUL)
break;
}
}
#endif
/* 'highlight' */
else if (varp == &p_hl)
{
if (highlight_changed() == FAIL)
errmsg = e_invarg; /* invalid flags */
}
/* 'nrformats' */
else if (gvarp == &p_nf)
{
if (check_opt_strings(*varp, p_nf_values, TRUE) != OK)
errmsg = e_invarg;
}
#ifdef FEAT_SESSION
/* 'sessionoptions' */
else if (varp == &p_ssop)
{
if (opt_strings_flags(p_ssop, p_ssop_values, &ssop_flags, TRUE) != OK)
errmsg = e_invarg;
if ((ssop_flags & SSOP_CURDIR) && (ssop_flags & SSOP_SESDIR))
{
/* Don't allow both "sesdir" and "curdir". */
(void)opt_strings_flags(oldval, p_ssop_values, &ssop_flags, TRUE);
errmsg = e_invarg;
}
}
/* 'viewoptions' */
else if (varp == &p_vop)
{
if (opt_strings_flags(p_vop, p_ssop_values, &vop_flags, TRUE) != OK)
errmsg = e_invarg;
}
#endif
/* 'scrollopt' */
#ifdef FEAT_SCROLLBIND
else if (varp == &p_sbo)
{
if (check_opt_strings(p_sbo, p_scbopt_values, TRUE) != OK)
errmsg = e_invarg;
}
#endif
/* 'ambiwidth' */
#ifdef FEAT_MBYTE
else if (varp == &p_ambw || varp == &p_emoji)
{
if (check_opt_strings(p_ambw, p_ambw_values, FALSE) != OK)
errmsg = e_invarg;
else if (set_chars_option(&p_lcs) != NULL)
errmsg = (char_u *)_("E834: Conflicts with value of 'listchars'");
# if defined(FEAT_WINDOWS) || defined(FEAT_FOLDING)
else if (set_chars_option(&p_fcs) != NULL)
errmsg = (char_u *)_("E835: Conflicts with value of 'fillchars'");
# endif
}
#endif
/* 'background' */
else if (varp == &p_bg)
{
if (check_opt_strings(p_bg, p_bg_values, FALSE) == OK)
{
#ifdef FEAT_EVAL
int dark = (*p_bg == 'd');
#endif
init_highlight(FALSE, FALSE);
#ifdef FEAT_EVAL
if (dark != (*p_bg == 'd')
&& get_var_value((char_u *)"g:colors_name") != NULL)
{
/* The color scheme must have set 'background' back to another
* value, that's not what we want here. Disable the color
* scheme and set the colors again. */
do_unlet((char_u *)"g:colors_name", TRUE);
free_string_option(p_bg);
p_bg = vim_strsave((char_u *)(dark ? "dark" : "light"));
check_string_option(&p_bg);
init_highlight(FALSE, FALSE);
}
#endif
}
else
errmsg = e_invarg;
}
/* 'wildmode' */
else if (varp == &p_wim)
{
if (check_opt_wim() == FAIL)
errmsg = e_invarg;
}
#ifdef FEAT_CMDL_COMPL
/* 'wildoptions' */
else if (varp == &p_wop)
{
if (check_opt_strings(p_wop, p_wop_values, TRUE) != OK)
errmsg = e_invarg;
}
#endif
#ifdef FEAT_WAK
/* 'winaltkeys' */
else if (varp == &p_wak)
{
if (*p_wak == NUL
|| check_opt_strings(p_wak, p_wak_values, FALSE) != OK)
errmsg = e_invarg;
# ifdef FEAT_MENU
# ifdef FEAT_GUI_MOTIF
else if (gui.in_use)
gui_motif_set_mnemonics(p_wak[0] == 'y' || p_wak[0] == 'm');
# else
# ifdef FEAT_GUI_GTK
else if (gui.in_use)
gui_gtk_set_mnemonics(p_wak[0] == 'y' || p_wak[0] == 'm');
# endif
# endif
# endif
}
#endif
#ifdef FEAT_AUTOCMD
/* 'eventignore' */
else if (varp == &p_ei)
{
if (check_ei() == FAIL)
errmsg = e_invarg;
}
#endif
#ifdef FEAT_MBYTE
/* 'encoding' and 'fileencoding' */
else if (varp == &p_enc || gvarp == &p_fenc || varp == &p_tenc)
{
if (gvarp == &p_fenc)
{
if (!curbuf->b_p_ma && opt_flags != OPT_GLOBAL)
errmsg = e_modifiable;
else if (vim_strchr(*varp, ',') != NULL)
/* No comma allowed in 'fileencoding'; catches confusing it
* with 'fileencodings'. */
errmsg = e_invarg;
else
{
# ifdef FEAT_TITLE
/* May show a "+" in the title now. */
redraw_titles();
# endif
/* Add 'fileencoding' to the swap file. */
ml_setflags(curbuf);
}
}
if (errmsg == NULL)
{
/* canonize the value, so that STRCMP() can be used on it */
p = enc_canonize(*varp);
if (p != NULL)
{
vim_free(*varp);
*varp = p;
}
if (varp == &p_enc)
{
errmsg = mb_init();
# ifdef FEAT_TITLE
redraw_titles();
# endif
}
}
# if defined(FEAT_GUI_GTK)
if (errmsg == NULL && varp == &p_tenc && gui.in_use)
{
/* GTK+ 2 uses only a single encoding, and that is UTF-8. */
if (STRCMP(p_tenc, "utf-8") != 0)
errmsg = (char_u *)N_("E617: Cannot be changed in the GTK+ 2 GUI");
}
# endif
if (errmsg == NULL)
{
# ifdef FEAT_KEYMAP
/* When 'keymap' is used and 'encoding' changes, reload the keymap
* (with another encoding). */
if (varp == &p_enc && *curbuf->b_p_keymap != NUL)
(void)keymap_init();
# endif
/* When 'termencoding' is not empty and 'encoding' changes or when
* 'termencoding' changes, need to setup for keyboard input and
* display output conversion. */
if (((varp == &p_enc && *p_tenc != NUL) || varp == &p_tenc))
{
convert_setup(&input_conv, p_tenc, p_enc);
convert_setup(&output_conv, p_enc, p_tenc);
}
# if defined(WIN3264) && defined(FEAT_MBYTE)
/* $HOME may have characters in active code page. */
if (varp == &p_enc)
init_homedir();
# endif
}
}
#endif
#if defined(FEAT_POSTSCRIPT)
else if (varp == &p_penc)
{
/* Canonize printencoding if VIM standard one */
p = enc_canonize(p_penc);
if (p != NULL)
{
vim_free(p_penc);
p_penc = p;
}
else
{
/* Ensure lower case and '-' for '_' */
for (s = p_penc; *s != NUL; s++)
{
if (*s == '_')
*s = '-';
else
*s = TOLOWER_ASC(*s);
}
}
}
#endif
#if defined(FEAT_XIM) && defined(FEAT_GUI_GTK)
else if (varp == &p_imak)
{
if (gui.in_use && !im_xim_isvalid_imactivate())
errmsg = e_invarg;
}
#endif
#ifdef FEAT_KEYMAP
else if (varp == &curbuf->b_p_keymap)
{
/* load or unload key mapping tables */
errmsg = keymap_init();
if (errmsg == NULL)
{
if (*curbuf->b_p_keymap != NUL)
{
/* Installed a new keymap, switch on using it. */
curbuf->b_p_iminsert = B_IMODE_LMAP;
if (curbuf->b_p_imsearch != B_IMODE_USE_INSERT)
curbuf->b_p_imsearch = B_IMODE_LMAP;
}
else
{
/* Cleared the keymap, may reset 'iminsert' and 'imsearch'. */
if (curbuf->b_p_iminsert == B_IMODE_LMAP)
curbuf->b_p_iminsert = B_IMODE_NONE;
if (curbuf->b_p_imsearch == B_IMODE_LMAP)
curbuf->b_p_imsearch = B_IMODE_USE_INSERT;
}
if ((opt_flags & OPT_LOCAL) == 0)
{
set_iminsert_global();
set_imsearch_global();
}
# ifdef FEAT_WINDOWS
status_redraw_curbuf();
# endif
}
}
#endif
/* 'fileformat' */
else if (gvarp == &p_ff)
{
if (!curbuf->b_p_ma && !(opt_flags & OPT_GLOBAL))
errmsg = e_modifiable;
else if (check_opt_strings(*varp, p_ff_values, FALSE) != OK)
errmsg = e_invarg;
else
{
/* may also change 'textmode' */
if (get_fileformat(curbuf) == EOL_DOS)
curbuf->b_p_tx = TRUE;
else
curbuf->b_p_tx = FALSE;
#ifdef FEAT_TITLE
redraw_titles();
#endif
/* update flag in swap file */
ml_setflags(curbuf);
/* Redraw needed when switching to/from "mac": a CR in the text
* will be displayed differently. */
if (get_fileformat(curbuf) == EOL_MAC || *oldval == 'm')
redraw_curbuf_later(NOT_VALID);
}
}
/* 'fileformats' */
else if (varp == &p_ffs)
{
if (check_opt_strings(p_ffs, p_ff_values, TRUE) != OK)
errmsg = e_invarg;
else
{
/* also change 'textauto' */
if (*p_ffs == NUL)
p_ta = FALSE;
else
p_ta = TRUE;
}
}
#if defined(FEAT_CRYPT)
/* 'cryptkey' */
else if (gvarp == &p_key)
{
# if defined(FEAT_CMDHIST)
/* Make sure the ":set" command doesn't show the new value in the
* history. */
remove_key_from_history();
# endif
if (STRCMP(curbuf->b_p_key, oldval) != 0)
/* Need to update the swapfile. */
ml_set_crypt_key(curbuf, oldval,
*curbuf->b_p_cm == NUL ? p_cm : curbuf->b_p_cm);
}
else if (gvarp == &p_cm)
{
if (opt_flags & OPT_LOCAL)
p = curbuf->b_p_cm;
else
p = p_cm;
if (check_opt_strings(p, p_cm_values, TRUE) != OK)
errmsg = e_invarg;
else if (crypt_self_test() == FAIL)
errmsg = e_invarg;
else
{
/* When setting the global value to empty, make it "zip". */
if (*p_cm == NUL)
{
if (new_value_alloced)
free_string_option(p_cm);
p_cm = vim_strsave((char_u *)"zip");
new_value_alloced = TRUE;
}
/* When using ":set cm=name" the local value is going to be empty.
* Do that here, otherwise the crypt functions will still use the
* local value. */
if ((opt_flags & (OPT_LOCAL | OPT_GLOBAL)) == 0)
{
free_string_option(curbuf->b_p_cm);
curbuf->b_p_cm = empty_option;
}
/* Need to update the swapfile when the effective method changed.
* Set "s" to the effective old value, "p" to the effective new
* method and compare. */
if ((opt_flags & OPT_LOCAL) && *oldval == NUL)
s = p_cm; /* was previously using the global value */
else
s = oldval;
if (*curbuf->b_p_cm == NUL)
p = p_cm; /* is now using the global value */
else
p = curbuf->b_p_cm;
if (STRCMP(s, p) != 0)
ml_set_crypt_key(curbuf, curbuf->b_p_key, s);
/* If the global value changes need to update the swapfile for all
* buffers using that value. */
if ((opt_flags & OPT_GLOBAL) && STRCMP(p_cm, oldval) != 0)
{
buf_T *buf;
FOR_ALL_BUFFERS(buf)
if (buf != curbuf && *buf->b_p_cm == NUL)
ml_set_crypt_key(buf, buf->b_p_key, oldval);
}
}
}
#endif
/* 'matchpairs' */
else if (gvarp == &p_mps)
{
#ifdef FEAT_MBYTE
if (has_mbyte)
{
for (p = *varp; *p != NUL; ++p)
{
int x2 = -1;
int x3 = -1;
if (*p != NUL)
p += mb_ptr2len(p);
if (*p != NUL)
x2 = *p++;
if (*p != NUL)
{
x3 = mb_ptr2char(p);
p += mb_ptr2len(p);
}
if (x2 != ':' || x3 == -1 || (*p != NUL && *p != ','))
{
errmsg = e_invarg;
break;
}
if (*p == NUL)
break;
}
}
else
#endif
{
/* Check for "x:y,x:y" */
for (p = *varp; *p != NUL; p += 4)
{
if (p[1] != ':' || p[2] == NUL || (p[3] != NUL && p[3] != ','))
{
errmsg = e_invarg;
break;
}
if (p[3] == NUL)
break;
}
}
}
#ifdef FEAT_COMMENTS
/* 'comments' */
else if (gvarp == &p_com)
{
for (s = *varp; *s; )
{
while (*s && *s != ':')
{
if (vim_strchr((char_u *)COM_ALL, *s) == NULL
&& !VIM_ISDIGIT(*s) && *s != '-')
{
errmsg = illegal_char(errbuf, *s);
break;
}
++s;
}
if (*s++ == NUL)
errmsg = (char_u *)N_("E524: Missing colon");
else if (*s == ',' || *s == NUL)
errmsg = (char_u *)N_("E525: Zero length string");
if (errmsg != NULL)
break;
while (*s && *s != ',')
{
if (*s == '\\' && s[1] != NUL)
++s;
++s;
}
s = skip_to_option_part(s);
}
}
#endif
/* 'listchars' */
else if (varp == &p_lcs)
{
errmsg = set_chars_option(varp);
}
#if defined(FEAT_WINDOWS) || defined(FEAT_FOLDING)
/* 'fillchars' */
else if (varp == &p_fcs)
{
errmsg = set_chars_option(varp);
}
#endif
#ifdef FEAT_CMDWIN
/* 'cedit' */
else if (varp == &p_cedit)
{
errmsg = check_cedit();
}
#endif
/* 'verbosefile' */
else if (varp == &p_vfile)
{
verbose_stop();
if (*p_vfile != NUL && verbose_open() == FAIL)
errmsg = e_invarg;
}
#ifdef FEAT_VIMINFO
/* 'viminfo' */
else if (varp == &p_viminfo)
{
for (s = p_viminfo; *s;)
{
/* Check it's a valid character */
if (vim_strchr((char_u *)"!\"%'/:<@cfhnrs", *s) == NULL)
{
errmsg = illegal_char(errbuf, *s);
break;
}
if (*s == 'n') /* name is always last one */
{
break;
}
else if (*s == 'r') /* skip until next ',' */
{
while (*++s && *s != ',')
;
}
else if (*s == '%')
{
/* optional number */
while (vim_isdigit(*++s))
;
}
else if (*s == '!' || *s == 'h' || *s == 'c')
++s; /* no extra chars */
else /* must have a number */
{
while (vim_isdigit(*++s))
;
if (!VIM_ISDIGIT(*(s - 1)))
{
if (errbuf != NULL)
{
sprintf((char *)errbuf,
_("E526: Missing number after <%s>"),
transchar_byte(*(s - 1)));
errmsg = errbuf;
}
else
errmsg = (char_u *)"";
break;
}
}
if (*s == ',')
++s;
else if (*s)
{
if (errbuf != NULL)
errmsg = (char_u *)N_("E527: Missing comma");
else
errmsg = (char_u *)"";
break;
}
}
if (*p_viminfo && errmsg == NULL && get_viminfo_parameter('\'') < 0)
errmsg = (char_u *)N_("E528: Must specify a ' value");
}
#endif /* FEAT_VIMINFO */
/* terminal options */
else if (istermoption(&options[opt_idx]) && full_screen)
{
/* ":set t_Co=0" and ":set t_Co=1" do ":set t_Co=" */
if (varp == &T_CCO)
{
int colors = atoi((char *)T_CCO);
/* Only reinitialize colors if t_Co value has really changed to
* avoid expensive reload of colorscheme if t_Co is set to the
* same value multiple times. */
if (colors != t_colors)
{
t_colors = colors;
if (t_colors <= 1)
{
if (new_value_alloced)
vim_free(T_CCO);
T_CCO = empty_option;
}
/* We now have a different color setup, initialize it again. */
init_highlight(TRUE, FALSE);
}
}
ttest(FALSE);
if (varp == &T_ME)
{
out_str(T_ME);
redraw_later(CLEAR);
#if defined(WIN3264) && !defined(FEAT_GUI_W32)
/* Since t_me has been set, this probably means that the user
* wants to use this as default colors. Need to reset default
* background/foreground colors. */
mch_set_normal_colors();
#endif
}
}
#ifdef FEAT_LINEBREAK
/* 'showbreak' */
else if (varp == &p_sbr)
{
for (s = p_sbr; *s; )
{
if (ptr2cells(s) != 1)
errmsg = (char_u *)N_("E595: contains unprintable or wide character");
mb_ptr_adv(s);
}
}
#endif
#ifdef FEAT_GUI
/* 'guifont' */
else if (varp == &p_guifont)
{
if (gui.in_use)
{
p = p_guifont;
# if defined(FEAT_GUI_GTK)
/*
* Put up a font dialog and let the user select a new value.
* If this is cancelled go back to the old value but don't
* give an error message.
*/
if (STRCMP(p, "*") == 0)
{
p = gui_mch_font_dialog(oldval);
if (new_value_alloced)
free_string_option(p_guifont);
p_guifont = (p != NULL) ? p : vim_strsave(oldval);
new_value_alloced = TRUE;
}
# endif
if (p != NULL && gui_init_font(p_guifont, FALSE) != OK)
{
# if defined(FEAT_GUI_MSWIN) || defined(FEAT_GUI_PHOTON)
if (STRCMP(p_guifont, "*") == 0)
{
/* Dialog was cancelled: Keep the old value without giving
* an error message. */
if (new_value_alloced)
free_string_option(p_guifont);
p_guifont = vim_strsave(oldval);
new_value_alloced = TRUE;
}
else
# endif
errmsg = (char_u *)N_("E596: Invalid font(s)");
}
}
redraw_gui_only = TRUE;
}
# ifdef FEAT_XFONTSET
else if (varp == &p_guifontset)
{
if (STRCMP(p_guifontset, "*") == 0)
errmsg = (char_u *)N_("E597: can't select fontset");
else if (gui.in_use && gui_init_font(p_guifontset, TRUE) != OK)
errmsg = (char_u *)N_("E598: Invalid fontset");
redraw_gui_only = TRUE;
}
# endif
# ifdef FEAT_MBYTE
else if (varp == &p_guifontwide)
{
if (STRCMP(p_guifontwide, "*") == 0)
errmsg = (char_u *)N_("E533: can't select wide font");
else if (gui_get_wide_font() == FAIL)
errmsg = (char_u *)N_("E534: Invalid wide font");
redraw_gui_only = TRUE;
}
# endif
#endif
#ifdef CURSOR_SHAPE
/* 'guicursor' */
else if (varp == &p_guicursor)
errmsg = parse_shape_opt(SHAPE_CURSOR);
#endif
#ifdef FEAT_MOUSESHAPE
/* 'mouseshape' */
else if (varp == &p_mouseshape)
{
errmsg = parse_shape_opt(SHAPE_MOUSE);
update_mouseshape(-1);
}
#endif
#ifdef FEAT_PRINTER
else if (varp == &p_popt)
errmsg = parse_printoptions();
# if defined(FEAT_MBYTE) && defined(FEAT_POSTSCRIPT)
else if (varp == &p_pmfn)
errmsg = parse_printmbfont();
# endif
#endif
#ifdef FEAT_LANGMAP
/* 'langmap' */
else if (varp == &p_langmap)
langmap_set();
#endif
#ifdef FEAT_LINEBREAK
/* 'breakat' */
else if (varp == &p_breakat)
fill_breakat_flags();
#endif
#ifdef FEAT_TITLE
/* 'titlestring' and 'iconstring' */
else if (varp == &p_titlestring || varp == &p_iconstring)
{
# ifdef FEAT_STL_OPT
int flagval = (varp == &p_titlestring) ? STL_IN_TITLE : STL_IN_ICON;
/* NULL => statusline syntax */
if (vim_strchr(*varp, '%') && check_stl_option(*varp) == NULL)
stl_syntax |= flagval;
else
stl_syntax &= ~flagval;
# endif
did_set_title(varp == &p_iconstring);
}
#endif
#ifdef FEAT_GUI
/* 'guioptions' */
else if (varp == &p_go)
{
gui_init_which_components(oldval);
redraw_gui_only = TRUE;
}
#endif
#if defined(FEAT_GUI_TABLINE)
/* 'guitablabel' */
else if (varp == &p_gtl)
{
redraw_tabline = TRUE;
redraw_gui_only = TRUE;
}
/* 'guitabtooltip' */
else if (varp == &p_gtt)
{
redraw_gui_only = TRUE;
}
#endif
#if defined(FEAT_MOUSE_TTY) && (defined(UNIX) || defined(VMS))
/* 'ttymouse' */
else if (varp == &p_ttym)
{
/* Switch the mouse off before changing the escape sequences used for
* that. */
mch_setmouse(FALSE);
if (opt_strings_flags(p_ttym, p_ttym_values, &ttym_flags, FALSE) != OK)
errmsg = e_invarg;
else
check_mouse_termcode();
if (termcap_active)
setmouse(); /* may switch it on again */
}
#endif
/* 'selection' */
else if (varp == &p_sel)
{
if (*p_sel == NUL
|| check_opt_strings(p_sel, p_sel_values, FALSE) != OK)
errmsg = e_invarg;
}
/* 'selectmode' */
else if (varp == &p_slm)
{
if (check_opt_strings(p_slm, p_slm_values, TRUE) != OK)
errmsg = e_invarg;
}
#ifdef FEAT_BROWSE
/* 'browsedir' */
else if (varp == &p_bsdir)
{
if (check_opt_strings(p_bsdir, p_bsdir_values, FALSE) != OK
&& !mch_isdir(p_bsdir))
errmsg = e_invarg;
}
#endif
/* 'keymodel' */
else if (varp == &p_km)
{
if (check_opt_strings(p_km, p_km_values, TRUE) != OK)
errmsg = e_invarg;
else
{
km_stopsel = (vim_strchr(p_km, 'o') != NULL);
km_startsel = (vim_strchr(p_km, 'a') != NULL);
}
}
/* 'mousemodel' */
else if (varp == &p_mousem)
{
if (check_opt_strings(p_mousem, p_mousem_values, FALSE) != OK)
errmsg = e_invarg;
#if defined(FEAT_GUI_MOTIF) && defined(FEAT_MENU) && (XmVersion <= 1002)
else if (*p_mousem != *oldval)
/* Changed from "extend" to "popup" or "popup_setpos" or vv: need
* to create or delete the popup menus. */
gui_motif_update_mousemodel(root_menu);
#endif
}
/* 'switchbuf' */
else if (varp == &p_swb)
{
if (opt_strings_flags(p_swb, p_swb_values, &swb_flags, TRUE) != OK)
errmsg = e_invarg;
}
/* 'debug' */
else if (varp == &p_debug)
{
if (check_opt_strings(p_debug, p_debug_values, TRUE) != OK)
errmsg = e_invarg;
}
/* 'display' */
else if (varp == &p_dy)
{
if (opt_strings_flags(p_dy, p_dy_values, &dy_flags, TRUE) != OK)
errmsg = e_invarg;
else
(void)init_chartab();
}
#ifdef FEAT_WINDOWS
/* 'eadirection' */
else if (varp == &p_ead)
{
if (check_opt_strings(p_ead, p_ead_values, FALSE) != OK)
errmsg = e_invarg;
}
#endif
#ifdef FEAT_CLIPBOARD
/* 'clipboard' */
else if (varp == &p_cb)
errmsg = check_clipboard_option();
#endif
#ifdef FEAT_SPELL
/* When 'spelllang' or 'spellfile' is set and there is a window for this
* buffer in which 'spell' is set load the wordlists. */
else if (varp == &(curwin->w_s->b_p_spl)
|| varp == &(curwin->w_s->b_p_spf))
{
errmsg = did_set_spell_option(varp == &(curwin->w_s->b_p_spf));
}
/* When 'spellcapcheck' is set compile the regexp program. */
else if (varp == &(curwin->w_s->b_p_spc))
{
errmsg = compile_cap_prog(curwin->w_s);
}
/* 'spellsuggest' */
else if (varp == &p_sps)
{
if (spell_check_sps() != OK)
errmsg = e_invarg;
}
/* 'mkspellmem' */
else if (varp == &p_msm)
{
if (spell_check_msm() != OK)
errmsg = e_invarg;
}
#endif
#ifdef FEAT_QUICKFIX
/* When 'bufhidden' is set, check for valid value. */
else if (gvarp == &p_bh)
{
if (check_opt_strings(curbuf->b_p_bh, p_bufhidden_values, FALSE) != OK)
errmsg = e_invarg;
}
/* When 'buftype' is set, check for valid value. */
else if (gvarp == &p_bt)
{
if (check_opt_strings(curbuf->b_p_bt, p_buftype_values, FALSE) != OK)
errmsg = e_invarg;
else
{
# ifdef FEAT_WINDOWS
if (curwin->w_status_height)
{
curwin->w_redr_status = TRUE;
redraw_later(VALID);
}
# endif
curbuf->b_help = (curbuf->b_p_bt[0] == 'h');
# ifdef FEAT_TITLE
redraw_titles();
# endif
}
}
#endif
#ifdef FEAT_STL_OPT
/* 'statusline' or 'rulerformat' */
else if (gvarp == &p_stl || varp == &p_ruf)
{
int wid;
if (varp == &p_ruf) /* reset ru_wid first */
ru_wid = 0;
s = *varp;
if (varp == &p_ruf && *s == '%')
{
/* set ru_wid if 'ruf' starts with "%99(" */
if (*++s == '-') /* ignore a '-' */
s++;
wid = getdigits(&s);
if (wid && *s == '(' && (errmsg = check_stl_option(p_ruf)) == NULL)
ru_wid = wid;
else
errmsg = check_stl_option(p_ruf);
}
/* check 'statusline' only if it doesn't start with "%!" */
else if (varp == &p_ruf || s[0] != '%' || s[1] != '!')
errmsg = check_stl_option(s);
if (varp == &p_ruf && errmsg == NULL)
comp_col();
}
#endif
#ifdef FEAT_INS_EXPAND
/* check if it is a valid value for 'complete' -- Acevedo */
else if (gvarp == &p_cpt)
{
for (s = *varp; *s;)
{
while (*s == ',' || *s == ' ')
s++;
if (!*s)
break;
if (vim_strchr((char_u *)".wbuksid]tU", *s) == NULL)
{
errmsg = illegal_char(errbuf, *s);
break;
}
if (*++s != NUL && *s != ',' && *s != ' ')
{
if (s[-1] == 'k' || s[-1] == 's')
{
/* skip optional filename after 'k' and 's' */
while (*s && *s != ',' && *s != ' ')
{
if (*s == '\\')
++s;
++s;
}
}
else
{
if (errbuf != NULL)
{
sprintf((char *)errbuf,
_("E535: Illegal character after <%c>"),
*--s);
errmsg = errbuf;
}
else
errmsg = (char_u *)"";
break;
}
}
}
}
/* 'completeopt' */
else if (varp == &p_cot)
{
if (check_opt_strings(p_cot, p_cot_values, TRUE) != OK)
errmsg = e_invarg;
else
completeopt_was_set();
}
#endif /* FEAT_INS_EXPAND */
#ifdef FEAT_SIGNS
/* 'signcolumn' */
else if (varp == &curwin->w_p_scl)
{
if (check_opt_strings(*varp, p_scl_values, FALSE) != OK)
errmsg = e_invarg;
}
#endif
#if defined(FEAT_TOOLBAR) && !defined(FEAT_GUI_W32)
else if (varp == &p_toolbar)
{
if (opt_strings_flags(p_toolbar, p_toolbar_values,
&toolbar_flags, TRUE) != OK)
errmsg = e_invarg;
else
{
out_flush();
gui_mch_show_toolbar((toolbar_flags &
(TOOLBAR_TEXT | TOOLBAR_ICONS)) != 0);
}
}
#endif
#if defined(FEAT_TOOLBAR) && defined(FEAT_GUI_GTK)
/* 'toolbariconsize': GTK+ 2 only */
else if (varp == &p_tbis)
{
if (opt_strings_flags(p_tbis, p_tbis_values, &tbis_flags, FALSE) != OK)
errmsg = e_invarg;
else
{
out_flush();
gui_mch_show_toolbar((toolbar_flags &
(TOOLBAR_TEXT | TOOLBAR_ICONS)) != 0);
}
}
#endif
/* 'pastetoggle': translate key codes like in a mapping */
else if (varp == &p_pt)
{
if (*p_pt)
{
(void)replace_termcodes(p_pt, &p, TRUE, TRUE, FALSE);
if (p != NULL)
{
if (new_value_alloced)
free_string_option(p_pt);
p_pt = p;
new_value_alloced = TRUE;
}
}
}
/* 'backspace' */
else if (varp == &p_bs)
{
if (VIM_ISDIGIT(*p_bs))
{
if (*p_bs > '2' || p_bs[1] != NUL)
errmsg = e_invarg;
}
else if (check_opt_strings(p_bs, p_bs_values, TRUE) != OK)
errmsg = e_invarg;
}
else if (varp == &p_bo)
{
if (opt_strings_flags(p_bo, p_bo_values, &bo_flags, TRUE) != OK)
errmsg = e_invarg;
}
/* 'tagcase' */
else if (gvarp == &p_tc)
{
unsigned int *flags;
if (opt_flags & OPT_LOCAL)
{
p = curbuf->b_p_tc;
flags = &curbuf->b_tc_flags;
}
else
{
p = p_tc;
flags = &tc_flags;
}
if ((opt_flags & OPT_LOCAL) && *p == NUL)
/* make the local value empty: use the global value */
*flags = 0;
else if (*p == NUL
|| opt_strings_flags(p, p_tc_values, flags, FALSE) != OK)
errmsg = e_invarg;
}
#ifdef FEAT_MBYTE
/* 'casemap' */
else if (varp == &p_cmp)
{
if (opt_strings_flags(p_cmp, p_cmp_values, &cmp_flags, TRUE) != OK)
errmsg = e_invarg;
}
#endif
#ifdef FEAT_DIFF
/* 'diffopt' */
else if (varp == &p_dip)
{
if (diffopt_changed() == FAIL)
errmsg = e_invarg;
}
#endif
#ifdef FEAT_FOLDING
/* 'foldmethod' */
else if (gvarp == &curwin->w_allbuf_opt.wo_fdm)
{
if (check_opt_strings(*varp, p_fdm_values, FALSE) != OK
|| *curwin->w_p_fdm == NUL)
errmsg = e_invarg;
else
{
foldUpdateAll(curwin);
if (foldmethodIsDiff(curwin))
newFoldLevel();
}
}
# ifdef FEAT_EVAL
/* 'foldexpr' */
else if (varp == &curwin->w_p_fde)
{
if (foldmethodIsExpr(curwin))
foldUpdateAll(curwin);
}
# endif
/* 'foldmarker' */
else if (gvarp == &curwin->w_allbuf_opt.wo_fmr)
{
p = vim_strchr(*varp, ',');
if (p == NULL)
errmsg = (char_u *)N_("E536: comma required");
else if (p == *varp || p[1] == NUL)
errmsg = e_invarg;
else if (foldmethodIsMarker(curwin))
foldUpdateAll(curwin);
}
/* 'commentstring' */
else if (gvarp == &p_cms)
{
if (**varp != NUL && strstr((char *)*varp, "%s") == NULL)
errmsg = (char_u *)N_("E537: 'commentstring' must be empty or contain %s");
}
/* 'foldopen' */
else if (varp == &p_fdo)
{
if (opt_strings_flags(p_fdo, p_fdo_values, &fdo_flags, TRUE) != OK)
errmsg = e_invarg;
}
/* 'foldclose' */
else if (varp == &p_fcl)
{
if (check_opt_strings(p_fcl, p_fcl_values, TRUE) != OK)
errmsg = e_invarg;
}
/* 'foldignore' */
else if (gvarp == &curwin->w_allbuf_opt.wo_fdi)
{
if (foldmethodIsIndent(curwin))
foldUpdateAll(curwin);
}
#endif
#ifdef FEAT_VIRTUALEDIT
/* 'virtualedit' */
else if (varp == &p_ve)
{
if (opt_strings_flags(p_ve, p_ve_values, &ve_flags, TRUE) != OK)
errmsg = e_invarg;
else if (STRCMP(p_ve, oldval) != 0)
{
/* Recompute cursor position in case the new 've' setting
* changes something. */
validate_virtcol();
coladvance(curwin->w_virtcol);
}
}
#endif
#if defined(FEAT_CSCOPE) && defined(FEAT_QUICKFIX)
else if (varp == &p_csqf)
{
if (p_csqf != NULL)
{
p = p_csqf;
while (*p != NUL)
{
if (vim_strchr((char_u *)CSQF_CMDS, *p) == NULL
|| p[1] == NUL
|| vim_strchr((char_u *)CSQF_FLAGS, p[1]) == NULL
|| (p[2] != NUL && p[2] != ','))
{
errmsg = e_invarg;
break;
}
else if (p[2] == NUL)
break;
else
p += 3;
}
}
}
#endif
#ifdef FEAT_CINDENT
/* 'cinoptions' */
else if (gvarp == &p_cino)
{
/* TODO: recognize errors */
parse_cino(curbuf);
}
#endif
#if defined(FEAT_RENDER_OPTIONS)
else if (varp == &p_rop && gui.in_use)
{
if (!gui_mch_set_rendering_options(p_rop))
errmsg = e_invarg;
}
#endif
/* Options that are a list of flags. */
else
{
p = NULL;
if (varp == &p_ww)
p = (char_u *)WW_ALL;
if (varp == &p_shm)
p = (char_u *)SHM_ALL;
else if (varp == &(p_cpo))
p = (char_u *)CPO_ALL;
else if (varp == &(curbuf->b_p_fo))
p = (char_u *)FO_ALL;
#ifdef FEAT_CONCEAL
else if (varp == &curwin->w_p_cocu)
p = (char_u *)COCU_ALL;
#endif
else if (varp == &p_mouse)
{
#ifdef FEAT_MOUSE
p = (char_u *)MOUSE_ALL;
#else
if (*p_mouse != NUL)
errmsg = (char_u *)N_("E538: No mouse support");
#endif
}
#if defined(FEAT_GUI)
else if (varp == &p_go)
p = (char_u *)GO_ALL;
#endif
if (p != NULL)
{
for (s = *varp; *s; ++s)
if (vim_strchr(p, *s) == NULL)
{
errmsg = illegal_char(errbuf, *s);
break;
}
}
}
/*
* If error detected, restore the previous value.
*/
if (errmsg != NULL)
{
if (new_value_alloced)
free_string_option(*varp);
*varp = oldval;
/*
* When resetting some values, need to act on it.
*/
if (did_chartab)
(void)init_chartab();
if (varp == &p_hl)
(void)highlight_changed();
}
else
{
#ifdef FEAT_EVAL
/* Remember where the option was set. */
set_option_scriptID_idx(opt_idx, opt_flags, current_SID);
#endif
/*
* Free string options that are in allocated memory.
* Use "free_oldval", because recursiveness may change the flags under
* our fingers (esp. init_highlight()).
*/
if (free_oldval)
free_string_option(oldval);
if (new_value_alloced)
options[opt_idx].flags |= P_ALLOCED;
else
options[opt_idx].flags &= ~P_ALLOCED;
if ((opt_flags & (OPT_LOCAL | OPT_GLOBAL)) == 0
&& ((int)options[opt_idx].indir & PV_BOTH))
{
/* global option with local value set to use global value; free
* the local value and make it empty */
p = get_varp_scope(&(options[opt_idx]), OPT_LOCAL);
free_string_option(*(char_u **)p);
*(char_u **)p = empty_option;
}
/* May set global value for local option. */
else if (!(opt_flags & OPT_LOCAL) && opt_flags != OPT_GLOBAL)
set_string_option_global(opt_idx, varp);
#ifdef FEAT_AUTOCMD
/*
* Trigger the autocommand only after setting the flags.
*/
# ifdef FEAT_SYN_HL
/* When 'syntax' is set, load the syntax of that name */
if (varp == &(curbuf->b_p_syn))
{
apply_autocmds(EVENT_SYNTAX, curbuf->b_p_syn,
curbuf->b_fname, TRUE, curbuf);
}
# endif
else if (varp == &(curbuf->b_p_ft))
{
/* 'filetype' is set, trigger the FileType autocommand */
did_filetype = TRUE;
apply_autocmds(EVENT_FILETYPE, curbuf->b_p_ft,
curbuf->b_fname, TRUE, curbuf);
}
#endif
#ifdef FEAT_SPELL
if (varp == &(curwin->w_s->b_p_spl))
{
char_u fname[200];
char_u *q = curwin->w_s->b_p_spl;
/* Skip the first name if it is "cjk". */
if (STRNCMP(q, "cjk,", 4) == 0)
q += 4;
/*
* Source the spell/LANG.vim in 'runtimepath'.
* They could set 'spellcapcheck' depending on the language.
* Use the first name in 'spelllang' up to '_region' or
* '.encoding'.
*/
for (p = q; *p != NUL; ++p)
if (vim_strchr((char_u *)"_.,", *p) != NULL)
break;
vim_snprintf((char *)fname, 200, "spell/%.*s.vim", (int)(p - q), q);
source_runtime(fname, DIP_ALL);
}
#endif
}
#ifdef FEAT_MOUSE
if (varp == &p_mouse)
{
# ifdef FEAT_MOUSE_TTY
if (*p_mouse == NUL)
mch_setmouse(FALSE); /* switch mouse off */
else
# endif
setmouse(); /* in case 'mouse' changed */
}
#endif
if (curwin->w_curswant != MAXCOL
&& (options[opt_idx].flags & (P_CURSWANT | P_RALL)) != 0)
curwin->w_set_curswant = TRUE;
#ifdef FEAT_GUI
/* check redraw when it's not a GUI option or the GUI is active. */
if (!redraw_gui_only || gui.in_use)
#endif
check_redraw(options[opt_idx].flags);
return errmsg;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'patch 8.0.0056
Problem: When setting 'filetype' there is no check for a valid name.
Solution: Only allow valid characters in 'filetype', 'syntax' and 'keymap'.'</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 attach_child_main(void* data)
{
struct attach_clone_payload* payload = (struct attach_clone_payload*)data;
int ipc_socket = payload->ipc_socket;
int procfd = payload->procfd;
lxc_attach_options_t* options = payload->options;
struct lxc_proc_context_info* init_ctx = payload->init_ctx;
#if HAVE_SYS_PERSONALITY_H
long new_personality;
#endif
int ret;
int status;
int expected;
long flags;
int fd;
uid_t new_uid;
gid_t new_gid;
/* wait for the initial thread to signal us that it's ready
* for us to start initializing
*/
expected = 0;
status = -1;
ret = lxc_read_nointr_expect(ipc_socket, &status, sizeof(status), &expected);
if (ret <= 0) {
ERROR("error using IPC to receive notification from initial process (0)");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
/* A description of the purpose of this functionality is
* provided in the lxc-attach(1) manual page. We have to
* remount here and not in the parent process, otherwise
* /proc may not properly reflect the new pid namespace.
*/
if (!(options->namespaces & CLONE_NEWNS) && (options->attach_flags & LXC_ATTACH_REMOUNT_PROC_SYS)) {
ret = lxc_attach_remount_sys_proc();
if (ret < 0) {
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
}
/* now perform additional attachments*/
#if HAVE_SYS_PERSONALITY_H
if (options->personality < 0)
new_personality = init_ctx->personality;
else
new_personality = options->personality;
if (options->attach_flags & LXC_ATTACH_SET_PERSONALITY) {
ret = personality(new_personality);
if (ret < 0) {
SYSERROR("could not ensure correct architecture");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
}
#endif
if (options->attach_flags & LXC_ATTACH_DROP_CAPABILITIES) {
ret = lxc_attach_drop_privs(init_ctx);
if (ret < 0) {
ERROR("could not drop privileges");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
}
/* always set the environment (specify (LXC_ATTACH_KEEP_ENV, NULL, NULL) if you want this to be a no-op) */
ret = lxc_attach_set_environment(options->env_policy, options->extra_env_vars, options->extra_keep_env);
if (ret < 0) {
ERROR("could not set initial environment for attached process");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
/* set user / group id */
new_uid = 0;
new_gid = 0;
/* ignore errors, we will fall back to root in that case
* (/proc was not mounted etc.)
*/
if (options->namespaces & CLONE_NEWUSER)
lxc_attach_get_init_uidgid(&new_uid, &new_gid);
if (options->uid != (uid_t)-1)
new_uid = options->uid;
if (options->gid != (gid_t)-1)
new_gid = options->gid;
/* setup the control tty */
if (options->stdin_fd && isatty(options->stdin_fd)) {
if (setsid() < 0) {
SYSERROR("unable to setsid");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
if (ioctl(options->stdin_fd, TIOCSCTTY, (char *)NULL) < 0) {
SYSERROR("unable to TIOCSTTY");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
}
/* try to set the uid/gid combination */
if ((new_gid != 0 || options->namespaces & CLONE_NEWUSER)) {
if (setgid(new_gid) || setgroups(0, NULL)) {
SYSERROR("switching to container gid");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
}
if ((new_uid != 0 || options->namespaces & CLONE_NEWUSER) && setuid(new_uid)) {
SYSERROR("switching to container uid");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
/* tell initial process it may now put us into the cgroups */
status = 1;
ret = lxc_write_nointr(ipc_socket, &status, sizeof(status));
if (ret != sizeof(status)) {
ERROR("error using IPC to notify initial process for initialization (1)");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
/* wait for the initial thread to signal us that it has done
* everything for us when it comes to cgroups etc.
*/
expected = 2;
status = -1;
ret = lxc_read_nointr_expect(ipc_socket, &status, sizeof(status), &expected);
if (ret <= 0) {
ERROR("error using IPC to receive final notification from initial process (2)");
shutdown(ipc_socket, SHUT_RDWR);
rexit(-1);
}
shutdown(ipc_socket, SHUT_RDWR);
close(ipc_socket);
if ((init_ctx->container && init_ctx->container->lxc_conf &&
init_ctx->container->lxc_conf->no_new_privs) ||
(options->attach_flags & LXC_ATTACH_NO_NEW_PRIVS)) {
if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) < 0) {
SYSERROR("PR_SET_NO_NEW_PRIVS could not be set. "
"Process can use execve() gainable "
"privileges.");
rexit(-1);
}
INFO("PR_SET_NO_NEW_PRIVS is set. Process cannot use execve() "
"gainable privileges.");
}
/* set new apparmor profile/selinux context */
if ((options->namespaces & CLONE_NEWNS) && (options->attach_flags & LXC_ATTACH_LSM) && init_ctx->lsm_label) {
int on_exec;
on_exec = options->attach_flags & LXC_ATTACH_LSM_EXEC ? 1 : 0;
if (lsm_set_label_at(procfd, on_exec, init_ctx->lsm_label) < 0) {
rexit(-1);
}
}
if (init_ctx->container && init_ctx->container->lxc_conf &&
init_ctx->container->lxc_conf->seccomp &&
(lxc_seccomp_load(init_ctx->container->lxc_conf) != 0)) {
ERROR("Loading seccomp policy");
rexit(-1);
}
lxc_proc_put_context_info(init_ctx);
/* The following is done after the communication socket is
* shut down. That way, all errors that might (though
* unlikely) occur up until this point will have their messages
* printed to the original stderr (if logging is so configured)
* and not the fd the user supplied, if any.
*/
/* fd handling for stdin, stdout and stderr;
* ignore errors here, user may want to make sure
* the fds are closed, for example */
if (options->stdin_fd >= 0 && options->stdin_fd != 0)
dup2(options->stdin_fd, 0);
if (options->stdout_fd >= 0 && options->stdout_fd != 1)
dup2(options->stdout_fd, 1);
if (options->stderr_fd >= 0 && options->stderr_fd != 2)
dup2(options->stderr_fd, 2);
/* close the old fds */
if (options->stdin_fd > 2)
close(options->stdin_fd);
if (options->stdout_fd > 2)
close(options->stdout_fd);
if (options->stderr_fd > 2)
close(options->stderr_fd);
/* try to remove CLOEXEC flag from stdin/stdout/stderr,
* but also here, ignore errors */
for (fd = 0; fd <= 2; fd++) {
flags = fcntl(fd, F_GETFL);
if (flags < 0)
continue;
if (flags & FD_CLOEXEC)
if (fcntl(fd, F_SETFL, flags & ~FD_CLOEXEC) < 0)
SYSERROR("Unable to clear CLOEXEC from fd");
}
/* we don't need proc anymore */
close(procfd);
/* we're done, so we can now do whatever the user intended us to do */
rexit(payload->exec_function(payload->exec_payload));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-284', 'CWE-264'], 'message': 'attach: do not send procfd to attached process
So far, we opened a file descriptor refering to proc on the host inside the
host namespace and handed that fd to the attached process in
attach_child_main(). This was done to ensure that LSM labels were correctly
setup. However, by exploiting a potential kernel bug, ptrace could be used to
prevent the file descriptor from being closed which in turn could be used by an
unprivileged container to gain access to the host namespace. Aside from this
needing an upstream kernel fix, we should make sure that we don't pass the fd
for proc itself to the attached process. However, we cannot completely prevent
this, as the attached process needs to be able to change its apparmor profile
by writing to /proc/self/attr/exec or /proc/self/attr/current. To minimize the
attack surface, we only send the fd for /proc/self/attr/exec or
/proc/self/attr/current to the attached process. To do this we introduce a
little more IPC between the child and parent:
* IPC mechanism: (X is receiver)
* initial process intermediate attached
* X <--- send pid of
* attached proc,
* then exit
* send 0 ------------------------------------> X
* [do initialization]
* X <------------------------------------ send 1
* [add to cgroup, ...]
* send 2 ------------------------------------> X
* [set LXC_ATTACH_NO_NEW_PRIVS]
* X <------------------------------------ send 3
* [open LSM label fd]
* send 4 ------------------------------------> X
* [set LSM label]
* close socket close socket
* run program
The attached child tells the parent when it is ready to have its LSM labels set
up. The parent then opens an approriate fd for the child PID to
/proc/<pid>/attr/exec or /proc/<pid>/attr/current and sends it via SCM_RIGHTS
to the child. The child can then set its LSM laben. Both sides then close the
socket fds and the child execs the requested process.
Signed-off-by: Christian Brauner <[email protected]>'</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 jpc_dec_tileinit(jpc_dec_t *dec, jpc_dec_tile_t *tile)
{
jpc_dec_tcomp_t *tcomp;
int compno;
int rlvlno;
jpc_dec_rlvl_t *rlvl;
jpc_dec_band_t *band;
jpc_dec_prc_t *prc;
int bndno;
jpc_tsfb_band_t *bnd;
int bandno;
jpc_dec_ccp_t *ccp;
int prccnt;
jpc_dec_cblk_t *cblk;
int cblkcnt;
uint_fast32_t tlprcxstart;
uint_fast32_t tlprcystart;
uint_fast32_t brprcxend;
uint_fast32_t brprcyend;
uint_fast32_t tlcbgxstart;
uint_fast32_t tlcbgystart;
uint_fast32_t brcbgxend;
uint_fast32_t brcbgyend;
uint_fast32_t cbgxstart;
uint_fast32_t cbgystart;
uint_fast32_t cbgxend;
uint_fast32_t cbgyend;
uint_fast32_t tlcblkxstart;
uint_fast32_t tlcblkystart;
uint_fast32_t brcblkxend;
uint_fast32_t brcblkyend;
uint_fast32_t cblkxstart;
uint_fast32_t cblkystart;
uint_fast32_t cblkxend;
uint_fast32_t cblkyend;
uint_fast32_t tmpxstart;
uint_fast32_t tmpystart;
uint_fast32_t tmpxend;
uint_fast32_t tmpyend;
jpc_dec_cp_t *cp;
jpc_tsfb_band_t bnds[64];
jpc_pchg_t *pchg;
int pchgno;
jpc_dec_cmpt_t *cmpt;
cp = tile->cp;
tile->realmode = 0;
if (cp->mctid == JPC_MCT_ICT) {
tile->realmode = 1;
}
for (compno = 0, tcomp = tile->tcomps, cmpt = dec->cmpts; compno <
dec->numcomps; ++compno, ++tcomp, ++cmpt) {
ccp = &tile->cp->ccps[compno];
if (ccp->qmfbid == JPC_COX_INS) {
tile->realmode = 1;
}
tcomp->numrlvls = ccp->numrlvls;
if (!(tcomp->rlvls = jas_alloc2(tcomp->numrlvls,
sizeof(jpc_dec_rlvl_t)))) {
return -1;
}
if (!(tcomp->data = jas_seq2d_create(JPC_CEILDIV(tile->xstart,
cmpt->hstep), JPC_CEILDIV(tile->ystart, cmpt->vstep),
JPC_CEILDIV(tile->xend, cmpt->hstep), JPC_CEILDIV(tile->yend,
cmpt->vstep)))) {
return -1;
}
if (!(tcomp->tsfb = jpc_cod_gettsfb(ccp->qmfbid,
tcomp->numrlvls - 1))) {
return -1;
}
{
jpc_tsfb_getbands(tcomp->tsfb, jas_seq2d_xstart(tcomp->data),
jas_seq2d_ystart(tcomp->data), jas_seq2d_xend(tcomp->data),
jas_seq2d_yend(tcomp->data), bnds);
}
for (rlvlno = 0, rlvl = tcomp->rlvls; rlvlno < tcomp->numrlvls;
++rlvlno, ++rlvl) {
rlvl->bands = 0;
rlvl->xstart = JPC_CEILDIVPOW2(tcomp->xstart,
tcomp->numrlvls - 1 - rlvlno);
rlvl->ystart = JPC_CEILDIVPOW2(tcomp->ystart,
tcomp->numrlvls - 1 - rlvlno);
rlvl->xend = JPC_CEILDIVPOW2(tcomp->xend,
tcomp->numrlvls - 1 - rlvlno);
rlvl->yend = JPC_CEILDIVPOW2(tcomp->yend,
tcomp->numrlvls - 1 - rlvlno);
rlvl->prcwidthexpn = ccp->prcwidthexpns[rlvlno];
rlvl->prcheightexpn = ccp->prcheightexpns[rlvlno];
tlprcxstart = JPC_FLOORDIVPOW2(rlvl->xstart,
rlvl->prcwidthexpn) << rlvl->prcwidthexpn;
tlprcystart = JPC_FLOORDIVPOW2(rlvl->ystart,
rlvl->prcheightexpn) << rlvl->prcheightexpn;
brprcxend = JPC_CEILDIVPOW2(rlvl->xend,
rlvl->prcwidthexpn) << rlvl->prcwidthexpn;
brprcyend = JPC_CEILDIVPOW2(rlvl->yend,
rlvl->prcheightexpn) << rlvl->prcheightexpn;
rlvl->numhprcs = (brprcxend - tlprcxstart) >>
rlvl->prcwidthexpn;
rlvl->numvprcs = (brprcyend - tlprcystart) >>
rlvl->prcheightexpn;
rlvl->numprcs = rlvl->numhprcs * rlvl->numvprcs;
if (rlvl->xstart >= rlvl->xend || rlvl->ystart >= rlvl->yend) {
rlvl->bands = 0;
rlvl->numprcs = 0;
rlvl->numhprcs = 0;
rlvl->numvprcs = 0;
continue;
}
if (!rlvlno) {
tlcbgxstart = tlprcxstart;
tlcbgystart = tlprcystart;
brcbgxend = brprcxend;
brcbgyend = brprcyend;
rlvl->cbgwidthexpn = rlvl->prcwidthexpn;
rlvl->cbgheightexpn = rlvl->prcheightexpn;
} else {
tlcbgxstart = JPC_CEILDIVPOW2(tlprcxstart, 1);
tlcbgystart = JPC_CEILDIVPOW2(tlprcystart, 1);
brcbgxend = JPC_CEILDIVPOW2(brprcxend, 1);
brcbgyend = JPC_CEILDIVPOW2(brprcyend, 1);
rlvl->cbgwidthexpn = rlvl->prcwidthexpn - 1;
rlvl->cbgheightexpn = rlvl->prcheightexpn - 1;
}
rlvl->cblkwidthexpn = JAS_MIN(ccp->cblkwidthexpn,
rlvl->cbgwidthexpn);
rlvl->cblkheightexpn = JAS_MIN(ccp->cblkheightexpn,
rlvl->cbgheightexpn);
rlvl->numbands = (!rlvlno) ? 1 : 3;
if (!(rlvl->bands = jas_alloc2(rlvl->numbands,
sizeof(jpc_dec_band_t)))) {
return -1;
}
for (bandno = 0, band = rlvl->bands;
bandno < rlvl->numbands; ++bandno, ++band) {
bndno = (!rlvlno) ? 0 : (3 * (rlvlno - 1) +
bandno + 1);
bnd = &bnds[bndno];
band->orient = bnd->orient;
band->stepsize = ccp->stepsizes[bndno];
band->analgain = JPC_NOMINALGAIN(ccp->qmfbid,
tcomp->numrlvls - 1, rlvlno, band->orient);
band->absstepsize = jpc_calcabsstepsize(band->stepsize,
cmpt->prec + band->analgain);
band->numbps = ccp->numguardbits +
JPC_QCX_GETEXPN(band->stepsize) - 1;
band->roishift = (ccp->roishift + band->numbps >= JPC_PREC) ?
(JPC_PREC - 1 - band->numbps) : ccp->roishift;
band->data = 0;
band->prcs = 0;
if (bnd->xstart == bnd->xend || bnd->ystart == bnd->yend) {
continue;
}
if (!(band->data = jas_seq2d_create(0, 0, 0, 0))) {
return -1;
}
jas_seq2d_bindsub(band->data, tcomp->data, bnd->locxstart,
bnd->locystart, bnd->locxend, bnd->locyend);
jas_seq2d_setshift(band->data, bnd->xstart, bnd->ystart);
assert(rlvl->numprcs);
if (!(band->prcs = jas_alloc2(rlvl->numprcs,
sizeof(jpc_dec_prc_t)))) {
return -1;
}
/************************************************/
cbgxstart = tlcbgxstart;
cbgystart = tlcbgystart;
for (prccnt = rlvl->numprcs, prc = band->prcs;
prccnt > 0; --prccnt, ++prc) {
cbgxend = cbgxstart + (1 << rlvl->cbgwidthexpn);
cbgyend = cbgystart + (1 << rlvl->cbgheightexpn);
prc->xstart = JAS_MAX(cbgxstart, JAS_CAST(uint_fast32_t,
jas_seq2d_xstart(band->data)));
prc->ystart = JAS_MAX(cbgystart, JAS_CAST(uint_fast32_t,
jas_seq2d_ystart(band->data)));
prc->xend = JAS_MIN(cbgxend, JAS_CAST(uint_fast32_t,
jas_seq2d_xend(band->data)));
prc->yend = JAS_MIN(cbgyend, JAS_CAST(uint_fast32_t,
jas_seq2d_yend(band->data)));
if (prc->xend > prc->xstart && prc->yend > prc->ystart) {
tlcblkxstart = JPC_FLOORDIVPOW2(prc->xstart,
rlvl->cblkwidthexpn) << rlvl->cblkwidthexpn;
tlcblkystart = JPC_FLOORDIVPOW2(prc->ystart,
rlvl->cblkheightexpn) << rlvl->cblkheightexpn;
brcblkxend = JPC_CEILDIVPOW2(prc->xend,
rlvl->cblkwidthexpn) << rlvl->cblkwidthexpn;
brcblkyend = JPC_CEILDIVPOW2(prc->yend,
rlvl->cblkheightexpn) << rlvl->cblkheightexpn;
prc->numhcblks = (brcblkxend - tlcblkxstart) >>
rlvl->cblkwidthexpn;
prc->numvcblks = (brcblkyend - tlcblkystart) >>
rlvl->cblkheightexpn;
prc->numcblks = prc->numhcblks * prc->numvcblks;
assert(prc->numcblks > 0);
if (!(prc->incltagtree = jpc_tagtree_create(
prc->numhcblks, prc->numvcblks))) {
return -1;
}
if (!(prc->numimsbstagtree = jpc_tagtree_create(
prc->numhcblks, prc->numvcblks))) {
return -1;
}
if (!(prc->cblks = jas_alloc2(prc->numcblks,
sizeof(jpc_dec_cblk_t)))) {
return -1;
}
cblkxstart = cbgxstart;
cblkystart = cbgystart;
for (cblkcnt = prc->numcblks, cblk = prc->cblks;
cblkcnt > 0;) {
cblkxend = cblkxstart + (1 << rlvl->cblkwidthexpn);
cblkyend = cblkystart + (1 << rlvl->cblkheightexpn);
tmpxstart = JAS_MAX(cblkxstart, prc->xstart);
tmpystart = JAS_MAX(cblkystart, prc->ystart);
tmpxend = JAS_MIN(cblkxend, prc->xend);
tmpyend = JAS_MIN(cblkyend, prc->yend);
if (tmpxend > tmpxstart && tmpyend > tmpystart) {
cblk->firstpassno = -1;
cblk->mqdec = 0;
cblk->nulldec = 0;
cblk->flags = 0;
cblk->numpasses = 0;
cblk->segs.head = 0;
cblk->segs.tail = 0;
cblk->curseg = 0;
cblk->numimsbs = 0;
cblk->numlenbits = 3;
cblk->flags = 0;
if (!(cblk->data = jas_seq2d_create(0, 0, 0,
0))) {
return -1;
}
jas_seq2d_bindsub(cblk->data, band->data,
tmpxstart, tmpystart, tmpxend, tmpyend);
++cblk;
--cblkcnt;
}
cblkxstart += 1 << rlvl->cblkwidthexpn;
if (cblkxstart >= cbgxend) {
cblkxstart = cbgxstart;
cblkystart += 1 << rlvl->cblkheightexpn;
}
}
} else {
prc->cblks = 0;
prc->incltagtree = 0;
prc->numimsbstagtree = 0;
}
cbgxstart += 1 << rlvl->cbgwidthexpn;
if (cbgxstart >= brcbgxend) {
cbgxstart = tlcbgxstart;
cbgystart += 1 << rlvl->cbgheightexpn;
}
}
/********************************************/
}
}
}
if (!(tile->pi = jpc_dec_pi_create(dec, tile))) {
return -1;
}
for (pchgno = 0; pchgno < jpc_pchglist_numpchgs(tile->cp->pchglist);
++pchgno) {
pchg = jpc_pchg_copy(jpc_pchglist_get(tile->cp->pchglist, pchgno));
assert(pchg);
jpc_pi_addpchg(tile->pi, pchg);
}
jpc_pi_init(tile->pi);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'Fixed an array overflow problem in the JPC decoder.'</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 jpc_qmfb_join_colgrp(jpc_fix_t *a, int numrows, int stride,
int parity)
{
int bufsize = JPC_CEILDIVPOW2(numrows, 1);
jpc_fix_t joinbuf[QMFB_JOINBUFSIZE * JPC_QMFB_COLGRPSIZE];
jpc_fix_t *buf = joinbuf;
jpc_fix_t *srcptr;
jpc_fix_t *dstptr;
register jpc_fix_t *srcptr2;
register jpc_fix_t *dstptr2;
register int n;
register int i;
int hstartcol;
/* Allocate memory for the join buffer from the heap. */
if (bufsize > QMFB_JOINBUFSIZE) {
if (!(buf = jas_alloc3(bufsize, JPC_QMFB_COLGRPSIZE, sizeof(jpc_fix_t)))) {
/* We have no choice but to commit suicide. */
abort();
}
}
hstartcol = (numrows + 1 - parity) >> 1;
/* Save the samples from the lowpass channel. */
n = hstartcol;
srcptr = &a[0];
dstptr = buf;
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < JPC_QMFB_COLGRPSIZE; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
srcptr += stride;
dstptr += JPC_QMFB_COLGRPSIZE;
}
/* Copy the samples from the highpass channel into place. */
srcptr = &a[hstartcol * stride];
dstptr = &a[(1 - parity) * stride];
n = numrows - hstartcol;
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < JPC_QMFB_COLGRPSIZE; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
dstptr += 2 * stride;
srcptr += stride;
}
/* Copy the samples from the lowpass channel into place. */
srcptr = buf;
dstptr = &a[parity * stride];
n = hstartcol;
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < JPC_QMFB_COLGRPSIZE; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
dstptr += 2 * stride;
srcptr += JPC_QMFB_COLGRPSIZE;
}
/* If the join buffer was allocated on the heap, free this memory. */
if (buf != joinbuf) {
jas_free(buf);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'Fixed a buffer overrun problem in the QMFB code in the JPC codec
that was caused by a buffer being allocated with a size that was too small
in some cases.
Added a new regression test case.'</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 jpc_qmfb_split_colres(jpc_fix_t *a, int numrows, int numcols,
int stride, int parity)
{
int bufsize = JPC_CEILDIVPOW2(numrows, 1);
jpc_fix_t splitbuf[QMFB_SPLITBUFSIZE * JPC_QMFB_COLGRPSIZE];
jpc_fix_t *buf = splitbuf;
jpc_fix_t *srcptr;
jpc_fix_t *dstptr;
register jpc_fix_t *srcptr2;
register jpc_fix_t *dstptr2;
register int n;
register int i;
int m;
int hstartcol;
/* Get a buffer. */
if (bufsize > QMFB_SPLITBUFSIZE) {
if (!(buf = jas_alloc2(bufsize, sizeof(jpc_fix_t)))) {
/* We have no choice but to commit suicide in this case. */
abort();
}
}
if (numrows >= 2) {
hstartcol = (numrows + 1 - parity) >> 1;
// ORIGINAL (WRONG): m = (parity) ? hstartcol : (numrows - hstartcol);
m = numrows - hstartcol;
/* Save the samples destined for the highpass channel. */
n = m;
dstptr = buf;
srcptr = &a[(1 - parity) * stride];
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < numcols; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
dstptr += numcols;
srcptr += stride << 1;
}
/* Copy the appropriate samples into the lowpass channel. */
dstptr = &a[(1 - parity) * stride];
srcptr = &a[(2 - parity) * stride];
n = numrows - m - (!parity);
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < numcols; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
dstptr += stride;
srcptr += stride << 1;
}
/* Copy the saved samples into the highpass channel. */
dstptr = &a[hstartcol * stride];
srcptr = buf;
n = m;
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < numcols; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
dstptr += stride;
srcptr += numcols;
}
}
/* If the split buffer was allocated on the heap, free this memory. */
if (buf != splitbuf) {
jas_free(buf);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'Fixed a buffer overrun problem in the QMFB code in the JPC codec
that was caused by a buffer being allocated with a size that was too small
in some cases.
Added a new regression test case.'</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 __init big_key_init(void)
{
return register_key_type(&key_type_big_key);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'KEYS: Sort out big_key initialisation
big_key has two separate initialisation functions, one that registers the
key type and one that registers the crypto. If the key type fails to
register, there's no problem if the crypto registers successfully because
there's no way to reach the crypto except through the key type.
However, if the key type registers successfully but the crypto does not,
big_key_rng and big_key_blkcipher may end up set to NULL - but the code
neither checks for this nor unregisters the big key key type.
Furthermore, since the key type is registered before the crypto, it is
theoretically possible for the kernel to try adding a big_key before the
crypto is set up, leading to the same effect.
Fix this by merging big_key_crypto_init() and big_key_init() and calling
the resulting function late. If they're going to be encrypted, we
shouldn't be creating big_keys before we have the facilities to do the
encryption available. The key type registration is also moved after the
crypto initialisation.
The fix also includes message printing on failure.
If the big_key type isn't correctly set up, simply doing:
dd if=/dev/zero bs=4096 count=1 | keyctl padd big_key a @s
ought to cause an oops.
Fixes: 13100a72f40f5748a04017e0ab3df4cf27c809ef ('Security: Keys: Big keys stored encrypted')
Signed-off-by: David Howells <[email protected]>
cc: Peter Hlavaty <[email protected]>
cc: Kirill Marinushkin <[email protected]>
cc: Artem Savkov <[email protected]>
cc: [email protected]
Signed-off-by: James Morris <[email protected]>'</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: do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
struct pt_regs *regs, long error_code)
{
if (v8086_mode(regs)) {
/*
* Traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
* On nmi (interrupt 2), do_trap should not be called.
*/
if (trapnr < X86_TRAP_UD) {
if (!handle_vm86_trap((struct kernel_vm86_regs *) regs,
error_code, trapnr))
return 0;
}
return -1;
}
if (!user_mode(regs)) {
if (!fixup_exception(regs)) {
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = trapnr;
die(str, regs, error_code);
}
return 0;
}
return -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'x86/mm: Expand the exception table logic to allow new handling options
Huge amounts of help from Andy Lutomirski and Borislav Petkov to
produce this. Andy provided the inspiration to add classes to the
exception table with a clever bit-squeezing trick, Boris pointed
out how much cleaner it would all be if we just had a new field.
Linus Torvalds blessed the expansion with:
' I'd rather not be clever in order to save just a tiny amount of space
in the exception table, which isn't really criticial for anybody. '
The third field is another relative function pointer, this one to a
handler that executes the actions.
We start out with three handlers:
1: Legacy - just jumps the to fixup IP
2: Fault - provide the trap number in %ax to the fixup code
3: Cleaned up legacy for the uaccess error hack
Signed-off-by: Tony Luck <[email protected]>
Reviewed-by: Borislav Petkov <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/f6af78fcbd348cf4939875cfda9c19689b5e50b8.1455732970.git.tony.luck@intel.com
Signed-off-by: Ingo Molnar <[email protected]>'</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 fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *fixup;
unsigned long new_ip;
#ifdef CONFIG_PNPBIOS
if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp;
extern u32 pnp_bios_is_utter_crap;
pnp_bios_is_utter_crap = 1;
printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n");
__asm__ volatile(
"movl %0, %%esp\n\t"
"jmp *%1\n\t"
: : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip));
panic("do_trap: can't hit this");
}
#endif
fixup = search_exception_tables(regs->ip);
if (fixup) {
new_ip = ex_fixup_addr(fixup);
if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
/* Special hack for uaccess_err */
current_thread_info()->uaccess_err = 1;
new_ip -= 0x7ffffff0;
}
regs->ip = new_ip;
return 1;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'x86/mm: Expand the exception table logic to allow new handling options
Huge amounts of help from Andy Lutomirski and Borislav Petkov to
produce this. Andy provided the inspiration to add classes to the
exception table with a clever bit-squeezing trick, Boris pointed
out how much cleaner it would all be if we just had a new field.
Linus Torvalds blessed the expansion with:
' I'd rather not be clever in order to save just a tiny amount of space
in the exception table, which isn't really criticial for anybody. '
The third field is another relative function pointer, this one to a
handler that executes the actions.
We start out with three handlers:
1: Legacy - just jumps the to fixup IP
2: Fault - provide the trap number in %ax to the fixup code
3: Cleaned up legacy for the uaccess error hack
Signed-off-by: Tony Luck <[email protected]>
Reviewed-by: Borislav Petkov <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/f6af78fcbd348cf4939875cfda9c19689b5e50b8.1455732970.git.tony.luck@intel.com
Signed-off-by: Ingo Molnar <[email protected]>'</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 sort_extable(struct exception_table_entry *start,
struct exception_table_entry *finish)
{
struct exception_table_entry *p;
int i;
/* Convert all entries to being relative to the start of the section */
i = 0;
for (p = start; p < finish; p++) {
p->insn += i;
i += 4;
p->fixup += i;
i += 4;
}
sort(start, finish - start, sizeof(struct exception_table_entry),
cmp_ex, NULL);
/* Denormalize all entries */
i = 0;
for (p = start; p < finish; p++) {
p->insn -= i;
i += 4;
p->fixup -= i;
i += 4;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'x86/mm: Expand the exception table logic to allow new handling options
Huge amounts of help from Andy Lutomirski and Borislav Petkov to
produce this. Andy provided the inspiration to add classes to the
exception table with a clever bit-squeezing trick, Boris pointed
out how much cleaner it would all be if we just had a new field.
Linus Torvalds blessed the expansion with:
' I'd rather not be clever in order to save just a tiny amount of space
in the exception table, which isn't really criticial for anybody. '
The third field is another relative function pointer, this one to a
handler that executes the actions.
We start out with three handlers:
1: Legacy - just jumps the to fixup IP
2: Fault - provide the trap number in %ax to the fixup code
3: Cleaned up legacy for the uaccess error hack
Signed-off-by: Tony Luck <[email protected]>
Reviewed-by: Borislav Petkov <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/f6af78fcbd348cf4939875cfda9c19689b5e50b8.1455732970.git.tony.luck@intel.com
Signed-off-by: Ingo Molnar <[email protected]>'</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: no_context(struct pt_regs *regs, unsigned long error_code,
unsigned long address, int signal, int si_code)
{
struct task_struct *tsk = current;
unsigned long flags;
int sig;
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs)) {
/*
* Any interrupt that takes a fault gets the fixup. This makes
* the below recursive fault logic only apply to a faults from
* task context.
*/
if (in_interrupt())
return;
/*
* Per the above we're !in_interrupt(), aka. task context.
*
* In this case we need to make sure we're not recursively
* faulting through the emulate_vsyscall() logic.
*/
if (current_thread_info()->sig_on_uaccess_error && signal) {
tsk->thread.trap_nr = X86_TRAP_PF;
tsk->thread.error_code = error_code | PF_USER;
tsk->thread.cr2 = address;
/* XXX: hwpoison faults will set the wrong code. */
force_sig_info_fault(signal, si_code, address, tsk, 0);
}
/*
* Barring that, we can do the fixup and be happy.
*/
return;
}
/*
* 32-bit:
*
* Valid to do another page fault here, because if this fault
* had been triggered by is_prefetch fixup_exception would have
* handled it.
*
* 64-bit:
*
* Hall of shame of CPU/BIOS bugs.
*/
if (is_prefetch(regs, error_code, address))
return;
if (is_errata93(regs, address))
return;
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice:
*/
flags = oops_begin();
show_fault_oops(regs, error_code, address);
if (task_stack_end_corrupted(tsk))
printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
tsk->thread.cr2 = address;
tsk->thread.trap_nr = X86_TRAP_PF;
tsk->thread.error_code = error_code;
sig = SIGKILL;
if (__die("Oops", regs, error_code))
sig = 0;
/* Executive summary in case the body of the oops scrolled away */
printk(KERN_DEFAULT "CR2: %016lx\n", address);
oops_end(flags, regs, sig);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'x86/mm: Expand the exception table logic to allow new handling options
Huge amounts of help from Andy Lutomirski and Borislav Petkov to
produce this. Andy provided the inspiration to add classes to the
exception table with a clever bit-squeezing trick, Boris pointed
out how much cleaner it would all be if we just had a new field.
Linus Torvalds blessed the expansion with:
' I'd rather not be clever in order to save just a tiny amount of space
in the exception table, which isn't really criticial for anybody. '
The third field is another relative function pointer, this one to a
handler that executes the actions.
We start out with three handlers:
1: Legacy - just jumps the to fixup IP
2: Fault - provide the trap number in %ax to the fixup code
3: Cleaned up legacy for the uaccess error hack
Signed-off-by: Tony Luck <[email protected]>
Reviewed-by: Borislav Petkov <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/f6af78fcbd348cf4939875cfda9c19689b5e50b8.1455732970.git.tony.luck@intel.com
Signed-off-by: Ingo Molnar <[email protected]>'</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: dbd_st_fetch(SV *sth, imp_sth_t* imp_sth)
{
dTHX;
int num_fields, ChopBlanks, i, rc;
unsigned long *lengths;
AV *av;
int av_length, av_readonly;
MYSQL_ROW cols;
D_imp_dbh_from_sth;
MYSQL* svsock= imp_dbh->pmysql;
imp_sth_fbh_t *fbh;
D_imp_xxh(sth);
#if MYSQL_VERSION_ID >=SERVER_PREPARE_VERSION
MYSQL_BIND *buffer;
#endif
MYSQL_FIELD *fields;
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t-> dbd_st_fetch\n");
#if MYSQL_ASYNC
if(imp_dbh->async_query_in_flight) {
if(mysql_db_async_result(sth, &imp_sth->result) <= 0) {
return Nullav;
}
}
#endif
#if MYSQL_VERSION_ID >=SERVER_PREPARE_VERSION
if (imp_sth->use_server_side_prepare)
{
if (!DBIc_ACTIVE(imp_sth) )
{
do_error(sth, JW_ERR_SEQUENCE, "no statement executing\n",NULL);
return Nullav;
}
if (imp_sth->fetch_done)
{
do_error(sth, JW_ERR_SEQUENCE, "fetch() but fetch already done",NULL);
return Nullav;
}
if (!imp_sth->done_desc)
{
if (!dbd_describe(sth, imp_sth))
{
do_error(sth, JW_ERR_SEQUENCE, "Error while describe result set.",
NULL);
return Nullav;
}
}
}
#endif
ChopBlanks = DBIc_is(imp_sth, DBIcf_ChopBlanks);
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh),
"\t\tdbd_st_fetch for %p, chopblanks %d\n",
sth, ChopBlanks);
if (!imp_sth->result)
{
do_error(sth, JW_ERR_SEQUENCE, "fetch() without execute()" ,NULL);
return Nullav;
}
/* fix from 2.9008 */
imp_dbh->pmysql->net.last_errno = 0;
#if MYSQL_VERSION_ID >=SERVER_PREPARE_VERSION
if (imp_sth->use_server_side_prepare)
{
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t\tdbd_st_fetch calling mysql_fetch\n");
if ((rc= mysql_stmt_fetch(imp_sth->stmt)))
{
if (rc == 1)
do_error(sth, mysql_stmt_errno(imp_sth->stmt),
mysql_stmt_error(imp_sth->stmt),
mysql_stmt_sqlstate(imp_sth->stmt));
#if MYSQL_VERSION_ID >= MYSQL_VERSION_5_0
if (rc == MYSQL_DATA_TRUNCATED) {
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t\tdbd_st_fetch data truncated\n");
goto process;
}
#endif
if (rc == MYSQL_NO_DATA)
{
/* Update row_num to affected_rows value */
imp_sth->row_num= mysql_stmt_affected_rows(imp_sth->stmt);
imp_sth->fetch_done=1;
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t\tdbd_st_fetch no data\n");
}
dbd_st_finish(sth, imp_sth);
return Nullav;
}
process:
imp_sth->currow++;
av= DBIc_DBISTATE(imp_sth)->get_fbav(imp_sth);
num_fields=mysql_stmt_field_count(imp_sth->stmt);
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh),
"\t\tdbd_st_fetch called mysql_fetch, rc %d num_fields %d\n",
rc, num_fields);
for (
buffer= imp_sth->buffer,
fbh= imp_sth->fbh,
i= 0;
i < num_fields;
i++,
fbh++,
buffer++
)
{
SV *sv= AvARRAY(av)[i]; /* Note: we (re)use the SV in the AV */
STRLEN len;
/* This is wrong, null is not being set correctly
* This is not the way to determine length (this would break blobs!)
*/
if (fbh->is_null)
(void) SvOK_off(sv); /* Field is NULL, return undef */
else
{
/* In case of BLOB/TEXT fields we allocate only 8192 bytes
in dbd_describe() for data. Here we know real size of field
so we should increase buffer size and refetch column value
*/
if (fbh->length > buffer->buffer_length || fbh->error)
{
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh),
"\t\tRefetch BLOB/TEXT column: %d, length: %lu, error: %d\n",
i, fbh->length, fbh->error);
Renew(fbh->data, fbh->length, char);
buffer->buffer_length= fbh->length;
buffer->buffer= (char *) fbh->data;
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2) {
int j;
int m = MIN(*buffer->length, buffer->buffer_length);
char *ptr = (char*)buffer->buffer;
PerlIO_printf(DBIc_LOGPIO(imp_xxh),"\t\tbefore buffer->buffer: ");
for (j = 0; j < m; j++) {
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "%c", *ptr++);
}
PerlIO_printf(DBIc_LOGPIO(imp_xxh),"\n");
}
/*TODO: Use offset instead of 0 to fetch only remain part of data*/
if (mysql_stmt_fetch_column(imp_sth->stmt, buffer , i, 0))
do_error(sth, mysql_stmt_errno(imp_sth->stmt),
mysql_stmt_error(imp_sth->stmt),
mysql_stmt_sqlstate(imp_sth->stmt));
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2) {
int j;
int m = MIN(*buffer->length, buffer->buffer_length);
char *ptr = (char*)buffer->buffer;
PerlIO_printf(DBIc_LOGPIO(imp_xxh),"\t\tafter buffer->buffer: ");
for (j = 0; j < m; j++) {
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "%c", *ptr++);
}
PerlIO_printf(DBIc_LOGPIO(imp_xxh),"\n");
}
}
/* This does look a lot like Georg's PHP driver doesn't it? --Brian */
/* Credit due to Georg - mysqli_api.c ;) --PMG */
switch (buffer->buffer_type) {
case MYSQL_TYPE_DOUBLE:
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t\tst_fetch double data %f\n", fbh->ddata);
sv_setnv(sv, fbh->ddata);
break;
case MYSQL_TYPE_LONG:
case MYSQL_TYPE_LONGLONG:
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t\tst_fetch int data %"IVdf", unsigned? %d\n",
fbh->ldata, buffer->is_unsigned);
if (buffer->is_unsigned)
sv_setuv(sv, fbh->ldata);
else
sv_setiv(sv, fbh->ldata);
break;
case MYSQL_TYPE_BIT:
sv_setpvn(sv, fbh->data, fbh->length);
break;
default:
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t\tERROR IN st_fetch_string");
len= fbh->length;
/* ChopBlanks server-side prepared statement */
if (ChopBlanks)
{
/*
see bottom of:
http://www.mysql.org/doc/refman/5.0/en/c-api-datatypes.html
*/
if (fbh->charsetnr != 63)
while (len && fbh->data[len-1] == ' ') { --len; }
}
/* END OF ChopBlanks */
sv_setpvn(sv, fbh->data, len);
/* UTF8 */
/*HELMUT*/
#if defined(sv_utf8_decode) && MYSQL_VERSION_ID >=SERVER_PREPARE_VERSION
#if MYSQL_VERSION_ID >= FIELD_CHARSETNR_VERSION
/* SHOW COLLATION WHERE Id = 63; -- 63 == charset binary, collation binary */
if ((imp_dbh->enable_utf8 || imp_dbh->enable_utf8mb4) && fbh->charsetnr != 63)
#else
if ((imp_dbh->enable_utf8 || imp_dbh->enable_utf8mb4) && !(fbh->flags & BINARY_FLAG))
#endif
sv_utf8_decode(sv);
#endif
/* END OF UTF8 */
break;
}
}
}
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t<- dbd_st_fetch, %d cols\n", num_fields);
return av;
}
else
{
#endif
imp_sth->currow++;
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
{
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\tdbd_st_fetch result set details\n");
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\timp_sth->result=%p\n", imp_sth->result);
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\tmysql_num_fields=%u\n",
mysql_num_fields(imp_sth->result));
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\tmysql_num_rows=%llu\n",
mysql_num_rows(imp_sth->result));
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\tmysql_affected_rows=%llu\n",
mysql_affected_rows(imp_dbh->pmysql));
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\tdbd_st_fetch for %p, currow= %d\n",
sth,imp_sth->currow);
}
if (!(cols= mysql_fetch_row(imp_sth->result)))
{
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
{
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\tdbd_st_fetch, no more rows to fetch");
}
if (mysql_errno(imp_dbh->pmysql))
do_error(sth, mysql_errno(imp_dbh->pmysql),
mysql_error(imp_dbh->pmysql),
mysql_sqlstate(imp_dbh->pmysql));
#if MYSQL_VERSION_ID >= MULTIPLE_RESULT_SET_VERSION
if (!mysql_more_results(svsock))
#endif
dbd_st_finish(sth, imp_sth);
return Nullav;
}
num_fields= mysql_num_fields(imp_sth->result);
fields= mysql_fetch_fields(imp_sth->result);
lengths= mysql_fetch_lengths(imp_sth->result);
if ((av= DBIc_FIELDS_AV(imp_sth)) != Nullav)
{
av_length= av_len(av)+1;
if (av_length != num_fields) /* Resize array if necessary */
{
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t<- dbd_st_fetch, size of results array(%d) != num_fields(%d)\n",
av_length, num_fields);
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t<- dbd_st_fetch, result fields(%d)\n",
DBIc_NUM_FIELDS(imp_sth));
av_readonly = SvREADONLY(av);
if (av_readonly)
SvREADONLY_off( av ); /* DBI sets this readonly */
while (av_length < num_fields)
{
av_store(av, av_length++, newSV(0));
}
while (av_length > num_fields)
{
SvREFCNT_dec(av_pop(av));
av_length--;
}
if (av_readonly)
SvREADONLY_on(av);
}
}
av= DBIc_DBISTATE(imp_sth)->get_fbav(imp_sth);
for (i= 0; i < num_fields; ++i)
{
char *col= cols[i];
SV *sv= AvARRAY(av)[i]; /* Note: we (re)use the SV in the AV */
if (col)
{
STRLEN len= lengths[i];
if (ChopBlanks)
{
while (len && col[len-1] == ' ')
{ --len; }
}
/* Set string value returned from mysql server */
sv_setpvn(sv, col, len);
switch (mysql_to_perl_type(fields[i].type)) {
case MYSQL_TYPE_DOUBLE:
/* Coerce to dobule and set scalar as NV */
(void) SvNV(sv);
SvNOK_only(sv);
break;
case MYSQL_TYPE_LONG:
case MYSQL_TYPE_LONGLONG:
/* Coerce to integer and set scalar as UV resp. IV */
if (fields[i].flags & UNSIGNED_FLAG)
{
(void) SvUV(sv);
SvIOK_only_UV(sv);
}
else
{
(void) SvIV(sv);
SvIOK_only(sv);
}
break;
#if MYSQL_VERSION_ID > NEW_DATATYPE_VERSION
case MYSQL_TYPE_BIT:
/* Let it as binary string */
break;
#endif
default:
/* UTF8 */
/*HELMUT*/
#if defined(sv_utf8_decode) && MYSQL_VERSION_ID >=SERVER_PREPARE_VERSION
/* see bottom of: http://www.mysql.org/doc/refman/5.0/en/c-api-datatypes.html */
if ((imp_dbh->enable_utf8 || imp_dbh->enable_utf8mb4) && fields[i].charsetnr != 63)
sv_utf8_decode(sv);
#endif
/* END OF UTF8 */
break;
}
}
else
(void) SvOK_off(sv); /* Field is NULL, return undef */
}
if (DBIc_TRACE_LEVEL(imp_xxh) >= 2)
PerlIO_printf(DBIc_LOGPIO(imp_xxh), "\t<- dbd_st_fetch, %d cols\n", num_fields);
return av;
#if MYSQL_VERSION_ID >= SERVER_PREPARE_VERSION
}
#endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-416'], 'message': 'Fix use-after-free for repeated fetchrow_arrayref calls when mysql_server_prepare=1
Function dbd_st_fetch() via Renew() can reallocate output buffer for
mysql_stmt_fetch() call. But it does not update pointer to that buffer in
imp_sth->stmt structure initialized by mysql_stmt_bind_result() function.
That leads to use-after-free in any mysql function which access
imp_sth->stmt structure (e.g. mysql_stmt_fetch()).
This patch fix this problem and properly updates pointer in imp_sth->stmt
structure after Renew() call.
Test 40server_prepare_crash.t is extended to check for that use-after-free
crash.'</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: formUpdateBuffer(Anchor *a, Buffer *buf, FormItemList *form)
{
Buffer save;
char *p;
int spos, epos, rows, c_rows, pos, col = 0;
Line *l;
copyBuffer(&save, buf);
gotoLine(buf, a->start.line);
switch (form->type) {
case FORM_TEXTAREA:
case FORM_INPUT_TEXT:
case FORM_INPUT_FILE:
case FORM_INPUT_PASSWORD:
case FORM_INPUT_CHECKBOX:
case FORM_INPUT_RADIO:
#ifdef MENU_SELECT
case FORM_SELECT:
#endif /* MENU_SELECT */
spos = a->start.pos;
epos = a->end.pos;
break;
default:
spos = a->start.pos + 1;
epos = a->end.pos - 1;
}
switch (form->type) {
case FORM_INPUT_CHECKBOX:
case FORM_INPUT_RADIO:
if (form->checked)
buf->currentLine->lineBuf[spos] = '*';
else
buf->currentLine->lineBuf[spos] = ' ';
break;
case FORM_INPUT_TEXT:
case FORM_INPUT_FILE:
case FORM_INPUT_PASSWORD:
case FORM_TEXTAREA:
#ifdef MENU_SELECT
case FORM_SELECT:
if (form->type == FORM_SELECT) {
p = form->label->ptr;
updateSelectOption(form, form->select_option);
}
else
#endif /* MENU_SELECT */
p = form->value->ptr;
l = buf->currentLine;
if (form->type == FORM_TEXTAREA) {
int n = a->y - buf->currentLine->linenumber;
if (n > 0)
for (; l && n; l = l->prev, n--) ;
else if (n < 0)
for (; l && n; l = l->prev, n++) ;
if (!l)
break;
}
rows = form->rows ? form->rows : 1;
col = COLPOS(l, a->start.pos);
for (c_rows = 0; c_rows < rows; c_rows++, l = l->next) {
if (rows > 1) {
pos = columnPos(l, col);
a = retrieveAnchor(buf->formitem, l->linenumber, pos);
if (a == NULL)
break;
spos = a->start.pos;
epos = a->end.pos;
}
pos = form_update_line(l, &p, spos, epos, COLPOS(l, epos) - col,
rows > 1,
form->type == FORM_INPUT_PASSWORD);
if (pos != epos) {
shiftAnchorPosition(buf->href, buf->hmarklist,
a->start.line, spos, pos - epos);
shiftAnchorPosition(buf->name, buf->hmarklist,
a->start.line, spos, pos - epos);
shiftAnchorPosition(buf->img, buf->hmarklist,
a->start.line, spos, pos - epos);
shiftAnchorPosition(buf->formitem, buf->hmarklist,
a->start.line, spos, pos - epos);
}
}
break;
}
copyBuffer(buf, &save);
arrangeLine(buf);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Prevent segfault for formUpdateBuffer
Bug-Debian: https://github.com/tats/w3m/issues/9
Bug-Debian: https://github.com/tats/w3m/issues/10'</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: addMultirowsForm(Buffer *buf, AnchorList *al)
{
int i, j, k, col, ecol, pos;
Anchor a_form, *a;
Line *l, *ls;
if (al == NULL || al->nanchor == 0)
return;
for (i = 0; i < al->nanchor; i++) {
a_form = al->anchors[i];
al->anchors[i].rows = 1;
if (a_form.hseq < 0 || a_form.rows <= 1)
continue;
for (l = buf->firstLine; l != NULL; l = l->next) {
if (l->linenumber == a_form.y)
break;
}
if (!l)
continue;
if (a_form.y == a_form.start.line)
ls = l;
else {
for (ls = l; ls != NULL;
ls = (a_form.y < a_form.start.line) ? ls->next : ls->prev) {
if (ls->linenumber == a_form.start.line)
break;
}
if (!ls)
continue;
}
col = COLPOS(ls, a_form.start.pos);
ecol = COLPOS(ls, a_form.end.pos);
for (j = 0; l && j < a_form.rows; l = l->next, j++) {
pos = columnPos(l, col);
if (j == 0) {
buf->hmarklist->marks[a_form.hseq].line = l->linenumber;
buf->hmarklist->marks[a_form.hseq].pos = pos;
}
if (a_form.start.line == l->linenumber)
continue;
buf->formitem = putAnchor(buf->formitem, a_form.url,
a_form.target, &a, NULL, NULL, '\0',
l->linenumber, pos);
a->hseq = a_form.hseq;
a->y = a_form.y;
a->end.pos = pos + ecol - col;
l->lineBuf[pos - 1] = '[';
l->lineBuf[a->end.pos] = ']';
for (k = pos; k < a->end.pos; k++)
l->propBuf[k] |= PE_FORM;
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Prevent segfault due to buffer overflows in addMultirowsForm
Bug-Debian: https://github.com/tats/w3m/issues/21
Bug-Debian: https://github.com/tats/w3m/issues/26'</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: GC_API GC_ATTR_MALLOC void * GC_CALL GC_calloc_explicitly_typed(size_t n,
size_t lb, GC_descr d)
{
word *op;
size_t lg;
GC_descr simple_descr;
complex_descriptor *complex_descr;
int descr_type;
struct LeafDescriptor leaf;
GC_ASSERT(GC_explicit_typing_initialized);
descr_type = GC_make_array_descriptor((word)n, (word)lb, d, &simple_descr,
&complex_descr, &leaf);
switch(descr_type) {
case NO_MEM: return(0);
case SIMPLE: return(GC_malloc_explicitly_typed(n*lb, simple_descr));
case LEAF:
lb *= n;
lb += sizeof(struct LeafDescriptor) + TYPD_EXTRA_BYTES;
break;
case COMPLEX:
lb *= n;
lb += TYPD_EXTRA_BYTES;
break;
}
op = GC_malloc_kind(lb, GC_array_kind);
if (EXPECT(NULL == op, FALSE))
return NULL;
lg = SMALL_OBJ(lb) ? GC_size_map[lb] : BYTES_TO_GRANULES(GC_size(op));
if (descr_type == LEAF) {
/* Set up the descriptor inside the object itself. */
volatile struct LeafDescriptor * lp =
(struct LeafDescriptor *)
(op + GRANULES_TO_WORDS(lg)
- (BYTES_TO_WORDS(sizeof(struct LeafDescriptor)) + 1));
lp -> ld_tag = LEAF_TAG;
lp -> ld_size = leaf.ld_size;
lp -> ld_nelements = leaf.ld_nelements;
lp -> ld_descriptor = leaf.ld_descriptor;
((volatile word *)op)[GRANULES_TO_WORDS(lg) - 1] = (word)lp;
} else {
# ifndef GC_NO_FINALIZATION
size_t lw = GRANULES_TO_WORDS(lg);
op[lw - 1] = (word)complex_descr;
/* Make sure the descriptor is cleared once there is any danger */
/* it may have been collected. */
if (EXPECT(GC_general_register_disappearing_link(
(void **)(op + lw - 1), op)
== GC_NO_MEMORY, FALSE))
# endif
{
/* Couldn't register it due to lack of memory. Punt. */
/* This will probably fail too, but gives the recovery code */
/* a chance. */
return GC_malloc(lb);
}
}
return op;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix calloc_explicitly_typed in case of lb*n overflow
* typd_mlc.c: Include limits.h (for SIZE_MAX).
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): New macro (same as in
malloc.c).
* typd_mlc.c (GC_calloc_explicitly_typed): Return NULL if lb * n
overflows (same algorithm as in calloc defined in malloc.c); eliminate
lb *= n code duplication.'</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 ptr_t GC_unmap_start(ptr_t start, size_t bytes)
{
ptr_t result = (ptr_t)ROUNDUP_PAGESIZE((word)start);
if ((word)(result + GC_page_size) > (word)(start + bytes)) return 0;
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_API GC_ATTR_MALLOC void * GC_CALL GC_malloc_many(size_t lb)
{
void *result;
GC_generic_malloc_many(ROUNDUP_GRANULE_SIZE(lb + EXTRA_BYTES),
NORMAL, &result);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_debug_malloc_atomic_uncollectable(size_t lb, GC_EXTRA_PARAMS)
{
void * result =
GC_malloc_atomic_uncollectable(lb + UNCOLLECTABLE_DEBUG_BYTES);
if (result == 0) {
GC_err_printf("GC_debug_malloc_atomic_uncollectable(%lu)"
" returning NULL (%s:%d)\n", (unsigned long)lb, s, i);
return(0);
}
if (!GC_debugging_started) {
GC_start_debugging();
}
ADD_CALL_CHAIN(result, ra);
return (GC_store_debug_info(result, (word)lb, s, i));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: ptr_t GC_unix_get_mem(word bytes)
{
# if defined(MMAP_SUPPORTED)
/* By default, we try both sbrk and mmap, in that order. */
static GC_bool sbrk_failed = FALSE;
ptr_t result = 0;
if (!sbrk_failed) result = GC_unix_sbrk_get_mem(bytes);
if (0 == result) {
sbrk_failed = TRUE;
result = GC_unix_mmap_get_mem(bytes);
}
if (0 == result) {
/* Try sbrk again, in case sbrk memory became available. */
result = GC_unix_sbrk_get_mem(bytes);
}
return result;
# else /* !MMAP_SUPPORTED */
return GC_unix_sbrk_get_mem(bytes);
# endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_INNER void * GC_debug_generic_malloc_inner(size_t lb, int k)
{
void * result = GC_generic_malloc_inner(lb + DEBUG_BYTES, k);
if (result == 0) {
GC_err_printf("GC internal allocation (%lu bytes) returning NULL\n",
(unsigned long) lb);
return(0);
}
if (!GC_debugging_started) {
GC_start_debugging_inner();
}
ADD_CALL_CHAIN(result, GC_RETURN_ADDR);
return (GC_store_debug_info_inner(result, (word)lb, "INTERNAL", 0));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_generic_malloc_ignore_off_page(size_t lb, int k)
{
void *result;
size_t lg;
size_t lb_rounded;
word n_blocks;
GC_bool init;
DCL_LOCK_STATE;
if (SMALL_OBJ(lb))
return GC_generic_malloc(lb, k);
GC_ASSERT(k < MAXOBJKINDS);
lg = ROUNDED_UP_GRANULES(lb);
lb_rounded = GRANULES_TO_BYTES(lg);
if (lb_rounded < lb)
return((*GC_get_oom_fn())(lb));
n_blocks = OBJ_SZ_TO_BLOCKS(lb_rounded);
init = GC_obj_kinds[k].ok_init;
if (EXPECT(GC_have_errors, FALSE))
GC_print_all_errors();
GC_INVOKE_FINALIZERS();
GC_DBG_COLLECT_AT_MALLOC(lb);
LOCK();
result = (ptr_t)GC_alloc_large(ADD_SLOP(lb), k, IGNORE_OFF_PAGE);
if (0 != result) {
if (GC_debugging_started) {
BZERO(result, n_blocks * HBLKSIZE);
} else {
# ifdef THREADS
/* Clear any memory that might be used for GC descriptors */
/* before we release the lock. */
((word *)result)[0] = 0;
((word *)result)[1] = 0;
((word *)result)[GRANULES_TO_WORDS(lg)-1] = 0;
((word *)result)[GRANULES_TO_WORDS(lg)-2] = 0;
# endif
}
}
GC_bytes_allocd += lb_rounded;
if (0 == result) {
GC_oom_func oom_fn = GC_oom_fn;
UNLOCK();
return((*oom_fn)(lb));
} else {
UNLOCK();
if (init && !GC_debugging_started) {
BZERO(result, n_blocks * HBLKSIZE);
}
return(result);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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 LONG WINAPI GC_write_fault_handler(
struct _EXCEPTION_POINTERS *exc_info)
# endif /* MSWIN32 || MSWINCE */
{
# if !defined(MSWIN32) && !defined(MSWINCE)
char *addr = si -> si_addr;
# else
char * addr = (char *) (exc_info -> ExceptionRecord
-> ExceptionInformation[1]);
# endif
unsigned i;
if (SIG_OK && CODE_OK) {
register struct hblk * h =
(struct hblk *)((word)addr & ~(GC_page_size-1));
GC_bool in_allocd_block;
# ifdef CHECKSUMS
GC_record_fault(h);
# endif
# ifdef SUNOS5SIGS
/* Address is only within the correct physical page. */
in_allocd_block = FALSE;
for (i = 0; i < divHBLKSZ(GC_page_size); i++) {
if (HDR(h+i) != 0) {
in_allocd_block = TRUE;
break;
}
}
# else
in_allocd_block = (HDR(addr) != 0);
# endif
if (!in_allocd_block) {
/* FIXME - We should make sure that we invoke the */
/* old handler with the appropriate calling */
/* sequence, which often depends on SA_SIGINFO. */
/* Heap blocks now begin and end on page boundaries */
SIG_HNDLR_PTR old_handler;
# if defined(MSWIN32) || defined(MSWINCE)
old_handler = GC_old_segv_handler;
# else
GC_bool used_si;
# if defined(FREEBSD) || defined(HURD) || defined(HPUX)
if (sig == SIGBUS) {
old_handler = GC_old_bus_handler;
used_si = GC_old_bus_handler_used_si;
} else
# endif
/* else */ {
old_handler = GC_old_segv_handler;
used_si = GC_old_segv_handler_used_si;
}
# endif
if (old_handler == (SIG_HNDLR_PTR)SIG_DFL) {
# if !defined(MSWIN32) && !defined(MSWINCE)
ABORT_ARG1("Unexpected bus error or segmentation fault",
" at %p", addr);
# else
return(EXCEPTION_CONTINUE_SEARCH);
# endif
} else {
/*
* FIXME: This code should probably check if the
* old signal handler used the traditional style and
* if so call it using that style.
*/
# if defined(MSWIN32) || defined(MSWINCE)
return((*old_handler)(exc_info));
# else
if (used_si)
((SIG_HNDLR_PTR)old_handler) (sig, si, raw_sc);
else
/* FIXME: should pass nonstandard args as well. */
((PLAIN_HNDLR_PTR)old_handler) (sig);
return;
# endif
}
}
UNPROTECT(h, GC_page_size);
/* We need to make sure that no collection occurs between */
/* the UNPROTECT and the setting of the dirty bit. Otherwise */
/* a write by a third thread might go unnoticed. Reversing */
/* the order is just as bad, since we would end up unprotecting */
/* a page in a GC cycle during which it's not marked. */
/* Currently we do this by disabling the thread stopping */
/* signals while this handler is running. An alternative might */
/* be to record the fact that we're about to unprotect, or */
/* have just unprotected a page in the GC's thread structure, */
/* and then to have the thread stopping code set the dirty */
/* flag, if necessary. */
for (i = 0; i < divHBLKSZ(GC_page_size); i++) {
size_t index = PHT_HASH(h+i);
async_set_pht_entry_from_index(GC_dirty_pages, index);
}
/* The write may not take place before dirty bits are read. */
/* But then we'll fault again ... */
# if defined(MSWIN32) || defined(MSWINCE)
return(EXCEPTION_CONTINUE_EXECUTION);
# else
return;
# endif
}
# if defined(MSWIN32) || defined(MSWINCE)
return EXCEPTION_CONTINUE_SEARCH;
# else
ABORT_ARG1("Unexpected bus error or segmentation fault",
" at %p", addr);
# endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_INNER ptr_t GC_scratch_alloc(size_t bytes)
{
ptr_t result = scratch_free_ptr;
word bytes_to_get;
bytes = ROUNDUP_GRANULE_SIZE(bytes);
for (;;) {
scratch_free_ptr += bytes;
if ((word)scratch_free_ptr <= (word)GC_scratch_end_ptr) {
/* Unallocated space of scratch buffer has enough size. */
return result;
}
if (bytes >= MINHINCR * HBLKSIZE) {
bytes_to_get = ROUNDUP_PAGESIZE_IF_MMAP(bytes);
result = (ptr_t)GET_MEM(bytes_to_get);
GC_add_to_our_memory(result, bytes_to_get);
/* Undo scratch free area pointer update; get memory directly. */
scratch_free_ptr -= bytes;
if (result != NULL) {
/* Update end point of last obtained area (needed only */
/* by GC_register_dynamic_libraries for some targets). */
GC_scratch_last_end_ptr = result + bytes;
}
return result;
}
bytes_to_get = ROUNDUP_PAGESIZE_IF_MMAP(MINHINCR * HBLKSIZE);
/* round up for safety */
result = (ptr_t)GET_MEM(bytes_to_get);
GC_add_to_our_memory(result, bytes_to_get);
if (NULL == result) {
WARN("Out of memory - trying to allocate requested amount"
" (%" WARN_PRIdPTR " bytes)...\n", (word)bytes);
scratch_free_ptr -= bytes; /* Undo free area pointer update */
bytes_to_get = ROUNDUP_PAGESIZE_IF_MMAP(bytes);
result = (ptr_t)GET_MEM(bytes_to_get);
GC_add_to_our_memory(result, bytes_to_get);
return result;
}
/* Update scratch area pointers and retry. */
scratch_free_ptr = result;
GC_scratch_end_ptr = scratch_free_ptr + bytes_to_get;
GC_scratch_last_end_ptr = GC_scratch_end_ptr;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_API GC_ATTR_MALLOC void * GC_CALL GC_generic_malloc(size_t lb, int k)
{
void * result;
DCL_LOCK_STATE;
GC_ASSERT(k < MAXOBJKINDS);
if (EXPECT(GC_have_errors, FALSE))
GC_print_all_errors();
GC_INVOKE_FINALIZERS();
GC_DBG_COLLECT_AT_MALLOC(lb);
if (SMALL_OBJ(lb)) {
LOCK();
result = GC_generic_malloc_inner(lb, k);
UNLOCK();
} else {
size_t lg;
size_t lb_rounded;
word n_blocks;
GC_bool init;
lg = ROUNDED_UP_GRANULES(lb);
lb_rounded = GRANULES_TO_BYTES(lg);
if (lb_rounded < lb)
return((*GC_get_oom_fn())(lb));
n_blocks = OBJ_SZ_TO_BLOCKS(lb_rounded);
init = GC_obj_kinds[k].ok_init;
LOCK();
result = (ptr_t)GC_alloc_large(lb_rounded, k, 0);
if (0 != result) {
if (GC_debugging_started) {
BZERO(result, n_blocks * HBLKSIZE);
} else {
# ifdef THREADS
/* Clear any memory that might be used for GC descriptors */
/* before we release the lock. */
((word *)result)[0] = 0;
((word *)result)[1] = 0;
((word *)result)[GRANULES_TO_WORDS(lg)-1] = 0;
((word *)result)[GRANULES_TO_WORDS(lg)-2] = 0;
# endif
}
}
GC_bytes_allocd += lb_rounded;
UNLOCK();
if (init && !GC_debugging_started && 0 != result) {
BZERO(result, n_blocks * HBLKSIZE);
}
}
if (0 == result) {
return((*GC_get_oom_fn())(lb));
} else {
return(result);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_API GC_ATTR_MALLOC void * GC_CALL GC_memalign(size_t align, size_t lb)
{
size_t new_lb;
size_t offset;
ptr_t result;
if (align <= GRANULE_BYTES) return GC_malloc(lb);
if (align >= HBLKSIZE/2 || lb >= HBLKSIZE/2) {
if (align > HBLKSIZE) {
return (*GC_get_oom_fn())(LONG_MAX-1024); /* Fail */
}
return GC_malloc(lb <= HBLKSIZE? HBLKSIZE : lb);
/* Will be HBLKSIZE aligned. */
}
/* We could also try to make sure that the real rounded-up object size */
/* is a multiple of align. That would be correct up to HBLKSIZE. */
new_lb = lb + align - 1;
result = GC_malloc(new_lb);
/* It is OK not to check result for NULL as in that case */
/* GC_memalign returns NULL too since (0 + 0 % align) is 0. */
offset = (word)result % align;
if (offset != 0) {
offset = align - offset;
if (!GC_all_interior_pointers) {
GC_STATIC_ASSERT(VALID_OFFSET_SZ <= HBLKSIZE);
GC_ASSERT(offset < VALID_OFFSET_SZ);
GC_register_displacement(offset);
}
}
result = (void *) ((ptr_t)result + offset);
GC_ASSERT((word)result % align == 0);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</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: GC_API GC_ATTR_MALLOC void * GC_CALL GC_finalized_malloc(size_t lb,
const struct GC_finalizer_closure *fclos)
{
word *op;
GC_ASSERT(done_init);
op = GC_malloc_kind(lb + sizeof(word), GC_finalized_kind);
if (EXPECT(NULL == op, FALSE))
return NULL;
*op = (word)fclos | FINALIZER_CLOSURE_FLAG;
return op + 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix malloc routines to prevent size value wrap-around
See issue #135 on Github.
* allchblk.c (GC_allochblk, GC_allochblk_nth): Use
OBJ_SZ_TO_BLOCKS_CHECKED instead of OBJ_SZ_TO_BLOCKS.
* malloc.c (GC_alloc_large): Likewise.
* alloc.c (GC_expand_hp_inner): Type of "bytes" local variable changed
from word to size_t; cast ROUNDUP_PAGESIZE argument to size_t; prevent
overflow when computing GC_heapsize+bytes > GC_max_heapsize.
* dbg_mlc.c (GC_debug_malloc, GC_debug_malloc_ignore_off_page,
GC_debug_malloc_atomic_ignore_off_page, GC_debug_generic_malloc,
GC_debug_generic_malloc_inner,
GC_debug_generic_malloc_inner_ignore_off_page,
GC_debug_malloc_stubborn, GC_debug_malloc_atomic,
GC_debug_malloc_uncollectable, GC_debug_malloc_atomic_uncollectable):
Use SIZET_SAT_ADD (instead of "+" operator) to add extra bytes to lb
value.
* fnlz_mlc.c (GC_finalized_malloc): Likewise.
* gcj_mlc.c (GC_debug_gcj_malloc): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Likewise.
* include/private/gcconfig.h (GET_MEM): Likewise.
* mallocx.c (GC_malloc_many, GC_memalign): Likewise.
* os_dep.c (GC_wince_get_mem, GC_win32_get_mem): Likewise.
* typd_mlc.c (GC_malloc_explicitly_typed,
GC_malloc_explicitly_typed_ignore_off_page,
GC_calloc_explicitly_typed): Likewise.
* headers.c (GC_scratch_alloc): Change type of bytes_to_get from word
to size_t (because ROUNDUP_PAGESIZE_IF_MMAP result type changed).
* include/private/gc_priv.h: Include limits.h (unless SIZE_MAX already
defined).
* include/private/gc_priv.h (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Move from
malloc.c file.
* include/private/gc_priv.h (SIZET_SAT_ADD): New macro (defined before
include gcconfig.h).
* include/private/gc_priv.h (EXTRA_BYTES, GC_page_size): Change type
to size_t.
* os_dep.c (GC_page_size): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, ROUNDUP_PAGESIZE): Add comment about the argument.
* include/private/gcconfig.h (GET_MEM): Likewise.
* include/private/gc_priv.h (ROUNDUP_GRANULE_SIZE, ROUNDED_UP_GRANULES,
ADD_SLOP, OBJ_SZ_TO_BLOCKS, ROUNDUP_PAGESIZE,
ROUNDUP_PAGESIZE_IF_MMAP): Rename argument to "lb".
* include/private/gc_priv.h (OBJ_SZ_TO_BLOCKS_CHECKED): New macro.
* include/private/gcconfig.h (GC_win32_get_mem, GC_wince_get_mem,
GC_unix_get_mem): Change argument type from word to int.
* os_dep.c (GC_unix_mmap_get_mem, GC_unix_get_mem,
GC_unix_sbrk_get_mem, GC_wince_get_mem, GC_win32_get_mem): Likewise.
* malloc.c (GC_alloc_large_and_clear): Call OBJ_SZ_TO_BLOCKS only
if no value wrap around is guaranteed.
* malloc.c (GC_generic_malloc): Do not check for lb_rounded < lb case
(because ROUNDED_UP_GRANULES and GRANULES_TO_BYTES guarantees no value
wrap around).
* mallocx.c (GC_generic_malloc_ignore_off_page): Likewise.
* misc.c (GC_init_size_map): Change "i" local variable type from int
to size_t.
* os_dep.c (GC_write_fault_handler, catch_exception_raise): Likewise.
* misc.c (GC_envfile_init): Cast len to size_t when passed to
ROUNDUP_PAGESIZE_IF_MMAP.
* os_dep.c (GC_setpagesize): Cast GC_sysinfo.dwPageSize and
GETPAGESIZE() to size_t (when setting GC_page_size).
* os_dep.c (GC_unix_mmap_get_mem, GC_unmap_start, GC_remove_protection):
Expand ROUNDUP_PAGESIZE macro but without value wrap-around checking
(the argument is of word type).
* os_dep.c (GC_unix_mmap_get_mem): Replace -GC_page_size with
~GC_page_size+1 (because GC_page_size is unsigned); remove redundant
cast to size_t.
* os_dep.c (GC_unix_sbrk_get_mem): Add explicit cast of GC_page_size
to SBRK_ARG_T.
* os_dep.c (GC_wince_get_mem): Change type of res_bytes local variable
to size_t.
* typd_mlc.c: Do not include limits.h.
* typd_mlc.c (GC_SIZE_MAX, GC_SQRT_SIZE_MAX): Remove (as defined in
gc_priv.h now).'</s> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.