text
stringlengths 517
228k
|
|---|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static void cirrus_mem_writeb_mode4and5_16bpp(CirrusVGAState * s,
unsigned mode,
unsigned offset,
uint32_t mem_value)
{
int x;
unsigned val = mem_value;
uint8_t *dst;
dst = s->vram_ptr + offset;
for (x = 0; x < 8; x++) {
if (val & 0x80) {
*dst = s->cirrus_shadow_gr1;
*(dst + 1) = s->gr[0x11];
} else if (mode == 5) {
*dst = s->cirrus_shadow_gr0;
*(dst + 1) = s->gr[0x10];
}
val <<= 1;
dst += 2;
}
cpu_physical_memory_set_dirty(s->vram_offset + offset);
cpu_physical_memory_set_dirty(s->vram_offset + offset + 15);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'CVE-2007-1320 - Cirrus LGD-54XX "bitblt" heap overflow
I have just noticed that patch for CVE-2007-1320 has never been applied
to the QEMU CVS. Please find it below.
| Multiple heap-based buffer overflows in the cirrus_invalidate_region
| function in the Cirrus VGA extension in QEMU 0.8.2, as used in Xen and
| possibly other products, might allow local users to execute arbitrary
| code via unspecified vectors related to "attempting to mark
| non-existent regions as dirty," aka the "bitblt" heap overflow.
git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@4340 c046a42c-6fe2-441c-8c8c-71466251a162'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
unsigned long idx)
{
struct vm_area_struct pvma;
struct page *page;
memset(&pvma, 0, sizeof(struct vm_area_struct));
pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
pvma.vm_pgoff = idx;
pvma.vm_end = PAGE_SIZE;
page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0);
mpol_free(pvma.vm_policy);
return page;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'tmpfs: restore missing clear_highpage
tmpfs was misconverted to __GFP_ZERO in 2.6.11. There's an unusual case in
which shmem_getpage receives the page from its caller instead of allocating.
We must cover this case by clear_highpage before SetPageUptodate, as before.
Signed-off-by: Hugh Dickins <[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: static int setup_frame(int sig, struct k_sigaction *ka,
sigset_t *set, struct pt_regs * regs)
{
void __user *restorer;
struct sigframe __user *frame;
int err = 0;
int usig;
frame = get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
usig = current_thread_info()->exec_domain
&& current_thread_info()->exec_domain->signal_invmap
&& sig < 32
? current_thread_info()->exec_domain->signal_invmap[sig]
: sig;
err = __put_user(usig, &frame->sig);
if (err)
goto give_sigsegv;
err = setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
if (err)
goto give_sigsegv;
if (_NSIG_WORDS > 1) {
err = __copy_to_user(&frame->extramask, &set->sig[1],
sizeof(frame->extramask));
if (err)
goto give_sigsegv;
}
if (current->binfmt->hasvdso)
restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn);
else
restorer = &frame->retcode;
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
/* Set up to return from userspace. */
err |= __put_user(restorer, &frame->pretcode);
/*
* This is popl %eax ; movl $,%eax ; int $0x80
*
* WE DO NOT USE IT ANY MORE! It's only left here for historical
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
err |= __put_user(0xb858, (short __user *)(frame->retcode+0));
err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2));
err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
if (err)
goto give_sigsegv;
/* Set up registers for signal handler */
regs->sp = (unsigned long) frame;
regs->ip = (unsigned long) ka->sa.sa_handler;
regs->ax = (unsigned long) sig;
regs->dx = (unsigned long) 0;
regs->cx = (unsigned long) 0;
regs->ds = __USER_DS;
regs->es = __USER_DS;
regs->ss = __USER_DS;
regs->cs = __USER_CS;
/*
* Clear TF when entering the signal handler, but
* notify any tracer that was single-stepping it.
* The tracer may want to single-step inside the
* handler too.
*/
regs->flags &= ~TF_MASK;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#if DEBUG_SIG
printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
current->comm, current->pid, frame, regs->ip, frame->pretcode);
#endif
return 0;
give_sigsegv:
force_sigsegv(sig, current);
return -EFAULT;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'x86: clear DF before calling signal handler
The Linux kernel currently does not clear the direction flag before
calling a signal handler, whereas the x86/x86-64 ABI requires that.
Linux had this behavior/bug forever, but this becomes a real problem
with gcc version 4.3, which assumes that the direction flag is
correctly cleared at the entry of a function.
This patches changes the setup_frame() functions to clear the
direction before entering the signal handler.
Signed-off-by: Aurelien Jarno <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Acked-by: H. Peter Anvin <[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: _gnutls_server_name_recv_params (gnutls_session_t session,
const opaque * data, size_t _data_size)
{
int i;
const unsigned char *p;
uint16_t len, type;
ssize_t data_size = _data_size;
int server_names = 0;
if (session->security_parameters.entity == GNUTLS_SERVER)
{
DECR_LENGTH_RET (data_size, 2, 0);
len = _gnutls_read_uint16 (data);
if (len != data_size)
{
/* This is unexpected packet length, but
* just ignore it, for now.
*/
gnutls_assert ();
return 0;
}
p = data + 2;
/* Count all server_names in the packet. */
while (data_size > 0)
{
DECR_LENGTH_RET (data_size, 1, 0);
p++;
DECR_LEN (data_size, 2);
len = _gnutls_read_uint16 (p);
p += 2;
DECR_LENGTH_RET (data_size, len, 0);
server_names++;
p += len;
}
session->security_parameters.extensions.server_names_size =
server_names;
if (server_names == 0)
return 0; /* no names found */
/* we cannot accept more server names.
*/
if (server_names > MAX_SERVER_NAME_EXTENSIONS)
server_names = MAX_SERVER_NAME_EXTENSIONS;
p = data + 2;
for (i = 0; i < server_names; i++)
{
type = *p;
p++;
len = _gnutls_read_uint16 (p);
p += 2;
switch (type)
{
case 0: /* NAME_DNS */
if (len <= MAX_SERVER_NAME_SIZE)
{
memcpy (session->security_parameters.extensions.
server_names[i].name, p, len);
session->security_parameters.extensions.
server_names[i].name_length = len;
session->security_parameters.extensions.
server_names[i].type = GNUTLS_NAME_DNS;
break;
}
}
/* move to next record */
p += len;
}
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix GNUTLS-SA-2008-1 security vulnerabilities.
See http://www.gnu.org/software/gnutls/security.html for updates.'</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 do_change_type(struct nameidata *nd, int flag)
{
struct vfsmount *m, *mnt = nd->mnt;
int recurse = flag & MS_REC;
int type = flag & ~MS_REC;
if (nd->dentry != nd->mnt->mnt_root)
return -EINVAL;
down_write(&namespace_sem);
spin_lock(&vfsmount_lock);
for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
change_mnt_propagation(m, type);
spin_unlock(&vfsmount_lock);
up_write(&namespace_sem);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-269'], 'message': 'check privileges before setting mount propagation
There's a missing check for CAP_SYS_ADMIN in do_change_type().
Signed-off-by: Miklos Szeredi <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Signed-off-by: Andrew Morton <[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: static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
{
struct dentry * result;
struct inode *dir = parent->d_inode;
mutex_lock(&dir->i_mutex);
/*
* First re-do the cached lookup just in case it was created
* while we waited for the directory semaphore..
*
* FIXME! This could use version numbering or similar to
* avoid unnecessary cache lookups.
*
* The "dcache_lock" is purely to protect the RCU list walker
* from concurrent renames at this point (we mustn't get false
* negatives from the RCU list walk here, unlike the optimistic
* fast walk).
*
* so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
*/
result = d_lookup(parent, name);
if (!result) {
struct dentry * dentry = d_alloc(parent, name);
result = ERR_PTR(-ENOMEM);
if (dentry) {
result = dir->i_op->lookup(dir, dentry, nd);
if (result)
dput(dentry);
else
result = dentry;
}
mutex_unlock(&dir->i_mutex);
return result;
}
/*
* Uhhuh! Nasty case: the cache was re-populated while
* we waited on the semaphore. Need to revalidate.
*/
mutex_unlock(&dir->i_mutex);
if (result->d_op && result->d_op->d_revalidate) {
result = do_revalidate(result, nd);
if (!result)
result = ERR_PTR(-ENOENT);
}
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-120'], 'message': '[patch] vfs: fix lookup on deleted directory
Lookup can install a child dentry for a deleted directory. This keeps
the directory dentry alive, and the inode pinned in the cache and on
disk, even after all external references have gone away.
This isn't a big problem normally, since memory pressure or umount
will clear out the directory dentry and its children, releasing the
inode. But for UBIFS this causes problems because its orphan area can
overflow.
Fix this by returning ENOENT for all lookups on a S_DEAD directory
before creating a child dentry.
Thanks to Zoltan Sogor for noticing this while testing UBIFS, and
Artem for the excellent analysis of the problem and testing.
Reported-by: Artem Bityutskiy <[email protected]>
Tested-by: Artem Bityutskiy <[email protected]>
Signed-off-by: Miklos Szeredi <[email protected]>
Signed-off-by: Al Viro <[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 file_change(struct diff_options *options,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
const char *base, const char *path)
{
tree_difference = REV_TREE_DIFFERENT;
DIFF_OPT_SET(options, HAS_CHANGES);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix buffer overflow in git diff
If PATH_MAX on your system is smaller than a path stored, it may cause
buffer overflow and stack corruption in diff_addremove() and diff_change()
functions when running git-diff
Signed-off-by: Dmitry Potapov <[email protected]>
Signed-off-by: Junio C Hamano <[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 *syscall_nopage(struct vm_area_struct *vma,
unsigned long adr, int *type)
{
struct page *p = virt_to_page(adr - vma->vm_start + syscall_page);
get_page(p);
return p;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': '[PATCH] i386 vDSO: use install_special_mapping
This patch uses install_special_mapping for the i386 vDSO setup, consolidating
duplicated code.
Signed-off-by: Roland McGrath <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Andi Kleen <[email protected]>
Signed-off-by: Andrew Morton <[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: static int jp2_cmap_getdata(jp2_box_t *box, jas_stream_t *in)
{
jp2_cmap_t *cmap = &box->data.cmap;
jp2_cmapent_t *ent;
unsigned int i;
cmap->numchans = (box->datalen) / 4;
if (!(cmap->ents = jas_malloc(cmap->numchans * sizeof(jp2_cmapent_t)))) {
return -1;
}
for (i = 0; i < cmap->numchans; ++i) {
ent = &cmap->ents[i];
if (jp2_getuint16(in, &ent->cmptno) ||
jp2_getuint8(in, &ent->map) ||
jp2_getuint8(in, &ent->pcol)) {
return -1;
}
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'At many places in the code, jas_malloc or jas_recalloc was being
invoked with the size argument being computed in a manner that would not
allow integer overflow to be detected. Now, these places in the code
have been modified to use special-purpose memory allocation functions
(e.g., jas_alloc2, jas_alloc3, jas_realloc2) that check for overflow.
This should fix many security problems.'</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 jp2_colr_getdata(jp2_box_t *box, jas_stream_t *in)
{
jp2_colr_t *colr = &box->data.colr;
colr->csid = 0;
colr->iccp = 0;
colr->iccplen = 0;
if (jp2_getuint8(in, &colr->method) || jp2_getuint8(in, &colr->pri) ||
jp2_getuint8(in, &colr->approx)) {
return -1;
}
switch (colr->method) {
case JP2_COLR_ENUM:
if (jp2_getuint32(in, &colr->csid)) {
return -1;
}
break;
case JP2_COLR_ICC:
colr->iccplen = box->datalen - 3;
if (!(colr->iccp = jas_malloc(colr->iccplen * sizeof(uint_fast8_t)))) {
return -1;
}
if (jas_stream_read(in, colr->iccp, colr->iccplen) != colr->iccplen) {
return -1;
}
break;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'At many places in the code, jas_malloc or jas_recalloc was being
invoked with the size argument being computed in a manner that would not
allow integer overflow to be detected. Now, these places in the code
have been modified to use special-purpose memory allocation functions
(e.g., jas_alloc2, jas_alloc3, jas_realloc2) that check for overflow.
This should fix many security problems.'</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_qcx_getcompparms(jpc_qcxcp_t *compparms, jpc_cstate_t *cstate,
jas_stream_t *in, uint_fast16_t len)
{
uint_fast8_t tmp;
int n;
int i;
/* Eliminate compiler warning about unused variables. */
cstate = 0;
n = 0;
if (jpc_getuint8(in, &tmp)) {
return -1;
}
++n;
compparms->qntsty = tmp & 0x1f;
compparms->numguard = (tmp >> 5) & 7;
switch (compparms->qntsty) {
case JPC_QCX_SIQNT:
compparms->numstepsizes = 1;
break;
case JPC_QCX_NOQNT:
compparms->numstepsizes = (len - n);
break;
case JPC_QCX_SEQNT:
/* XXX - this is a hack */
compparms->numstepsizes = (len - n) / 2;
break;
}
if (compparms->numstepsizes > 0) {
compparms->stepsizes = jas_malloc(compparms->numstepsizes *
sizeof(uint_fast16_t));
assert(compparms->stepsizes);
for (i = 0; i < compparms->numstepsizes; ++i) {
if (compparms->qntsty == JPC_QCX_NOQNT) {
if (jpc_getuint8(in, &tmp)) {
return -1;
}
compparms->stepsizes[i] = JPC_QCX_EXPN(tmp >> 3);
} else {
if (jpc_getuint16(in, &compparms->stepsizes[i])) {
return -1;
}
}
}
} else {
compparms->stepsizes = 0;
}
if (jas_stream_error(in) || jas_stream_eof(in)) {
jpc_qcx_destroycompparms(compparms);
return -1;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'At many places in the code, jas_malloc or jas_recalloc was being
invoked with the size argument being computed in a manner that would not
allow integer overflow to be detected. Now, these places in the code
have been modified to use special-purpose memory allocation functions
(e.g., jas_alloc2, jas_alloc3, jas_realloc2) that check for overflow.
This should fix many security problems.'</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 *jp2_decode(jas_stream_t *in, char *optstr)
{
jp2_box_t *box;
int found;
jas_image_t *image;
jp2_dec_t *dec;
bool samedtype;
int dtype;
unsigned int i;
jp2_cmap_t *cmapd;
jp2_pclr_t *pclrd;
jp2_cdef_t *cdefd;
unsigned int channo;
int newcmptno;
int_fast32_t *lutents;
#if 0
jp2_cdefchan_t *cdefent;
int cmptno;
#endif
jp2_cmapent_t *cmapent;
jas_icchdr_t icchdr;
jas_iccprof_t *iccprof;
dec = 0;
box = 0;
image = 0;
if (!(dec = jp2_dec_create())) {
goto error;
}
/* Get the first box. This should be a JP box. */
if (!(box = jp2_box_get(in))) {
jas_eprintf("error: cannot get box\n");
goto error;
}
if (box->type != JP2_BOX_JP) {
jas_eprintf("error: expecting signature box\n");
goto error;
}
if (box->data.jp.magic != JP2_JP_MAGIC) {
jas_eprintf("incorrect magic number\n");
goto error;
}
jp2_box_destroy(box);
box = 0;
/* Get the second box. This should be a FTYP box. */
if (!(box = jp2_box_get(in))) {
goto error;
}
if (box->type != JP2_BOX_FTYP) {
jas_eprintf("expecting file type box\n");
goto error;
}
jp2_box_destroy(box);
box = 0;
/* Get more boxes... */
found = 0;
while ((box = jp2_box_get(in))) {
if (jas_getdbglevel() >= 1) {
jas_eprintf("box type %s\n", box->info->name);
}
switch (box->type) {
case JP2_BOX_JP2C:
found = 1;
break;
case JP2_BOX_IHDR:
if (!dec->ihdr) {
dec->ihdr = box;
box = 0;
}
break;
case JP2_BOX_BPCC:
if (!dec->bpcc) {
dec->bpcc = box;
box = 0;
}
break;
case JP2_BOX_CDEF:
if (!dec->cdef) {
dec->cdef = box;
box = 0;
}
break;
case JP2_BOX_PCLR:
if (!dec->pclr) {
dec->pclr = box;
box = 0;
}
break;
case JP2_BOX_CMAP:
if (!dec->cmap) {
dec->cmap = box;
box = 0;
}
break;
case JP2_BOX_COLR:
if (!dec->colr) {
dec->colr = box;
box = 0;
}
break;
}
if (box) {
jp2_box_destroy(box);
box = 0;
}
if (found) {
break;
}
}
if (!found) {
jas_eprintf("error: no code stream found\n");
goto error;
}
if (!(dec->image = jpc_decode(in, optstr))) {
jas_eprintf("error: cannot decode code stream\n");
goto error;
}
/* An IHDR box must be present. */
if (!dec->ihdr) {
jas_eprintf("error: missing IHDR box\n");
goto error;
}
/* Does the number of components indicated in the IHDR box match
the value specified in the code stream? */
if (dec->ihdr->data.ihdr.numcmpts != JAS_CAST(uint, jas_image_numcmpts(dec->image))) {
jas_eprintf("warning: number of components mismatch\n");
}
/* At least one component must be present. */
if (!jas_image_numcmpts(dec->image)) {
jas_eprintf("error: no components\n");
goto error;
}
/* Determine if all components have the same data type. */
samedtype = true;
dtype = jas_image_cmptdtype(dec->image, 0);
for (i = 1; i < JAS_CAST(uint, jas_image_numcmpts(dec->image)); ++i) {
if (jas_image_cmptdtype(dec->image, i) != dtype) {
samedtype = false;
break;
}
}
/* Is the component data type indicated in the IHDR box consistent
with the data in the code stream? */
if ((samedtype && dec->ihdr->data.ihdr.bpc != JP2_DTYPETOBPC(dtype)) ||
(!samedtype && dec->ihdr->data.ihdr.bpc != JP2_IHDR_BPCNULL)) {
jas_eprintf("warning: component data type mismatch\n");
}
/* Is the compression type supported? */
if (dec->ihdr->data.ihdr.comptype != JP2_IHDR_COMPTYPE) {
jas_eprintf("error: unsupported compression type\n");
goto error;
}
if (dec->bpcc) {
/* Is the number of components indicated in the BPCC box
consistent with the code stream data? */
if (dec->bpcc->data.bpcc.numcmpts != JAS_CAST(uint, jas_image_numcmpts(
dec->image))) {
jas_eprintf("warning: number of components mismatch\n");
}
/* Is the component data type information indicated in the BPCC
box consistent with the code stream data? */
if (!samedtype) {
for (i = 0; i < JAS_CAST(uint, jas_image_numcmpts(dec->image)); ++i) {
if (jas_image_cmptdtype(dec->image, i) != JP2_BPCTODTYPE(dec->bpcc->data.bpcc.bpcs[i])) {
jas_eprintf("warning: component data type mismatch\n");
}
}
} else {
jas_eprintf("warning: superfluous BPCC box\n");
}
}
/* A COLR box must be present. */
if (!dec->colr) {
jas_eprintf("error: no COLR box\n");
goto error;
}
switch (dec->colr->data.colr.method) {
case JP2_COLR_ENUM:
jas_image_setclrspc(dec->image, jp2_getcs(&dec->colr->data.colr));
break;
case JP2_COLR_ICC:
iccprof = jas_iccprof_createfrombuf(dec->colr->data.colr.iccp,
dec->colr->data.colr.iccplen);
if (!iccprof) {
jas_eprintf("error: failed to parse ICC profile\n");
goto error;
}
jas_iccprof_gethdr(iccprof, &icchdr);
jas_eprintf("ICC Profile CS %08x\n", icchdr.colorspc);
jas_image_setclrspc(dec->image, fromiccpcs(icchdr.colorspc));
dec->image->cmprof_ = jas_cmprof_createfromiccprof(iccprof);
assert(dec->image->cmprof_);
jas_iccprof_destroy(iccprof);
break;
}
/* If a CMAP box is present, a PCLR box must also be present. */
if (dec->cmap && !dec->pclr) {
jas_eprintf("warning: missing PCLR box or superfluous CMAP box\n");
jp2_box_destroy(dec->cmap);
dec->cmap = 0;
}
/* If a CMAP box is not present, a PCLR box must not be present. */
if (!dec->cmap && dec->pclr) {
jas_eprintf("warning: missing CMAP box or superfluous PCLR box\n");
jp2_box_destroy(dec->pclr);
dec->pclr = 0;
}
/* Determine the number of channels (which is essentially the number
of components after any palette mappings have been applied). */
dec->numchans = dec->cmap ? dec->cmap->data.cmap.numchans : JAS_CAST(uint, jas_image_numcmpts(dec->image));
/* Perform a basic sanity check on the CMAP box if present. */
if (dec->cmap) {
for (i = 0; i < dec->numchans; ++i) {
/* Is the component number reasonable? */
if (dec->cmap->data.cmap.ents[i].cmptno >= JAS_CAST(uint, jas_image_numcmpts(dec->image))) {
jas_eprintf("error: invalid component number in CMAP box\n");
goto error;
}
/* Is the LUT index reasonable? */
if (dec->cmap->data.cmap.ents[i].pcol >= dec->pclr->data.pclr.numchans) {
jas_eprintf("error: invalid CMAP LUT index\n");
goto error;
}
}
}
/* Allocate space for the channel-number to component-number LUT. */
if (!(dec->chantocmptlut = jas_malloc(dec->numchans * sizeof(uint_fast16_t)))) {
jas_eprintf("error: no memory\n");
goto error;
}
if (!dec->cmap) {
for (i = 0; i < dec->numchans; ++i) {
dec->chantocmptlut[i] = i;
}
} else {
cmapd = &dec->cmap->data.cmap;
pclrd = &dec->pclr->data.pclr;
cdefd = &dec->cdef->data.cdef;
for (channo = 0; channo < cmapd->numchans; ++channo) {
cmapent = &cmapd->ents[channo];
if (cmapent->map == JP2_CMAP_DIRECT) {
dec->chantocmptlut[channo] = channo;
} else if (cmapent->map == JP2_CMAP_PALETTE) {
lutents = jas_malloc(pclrd->numlutents * sizeof(int_fast32_t));
for (i = 0; i < pclrd->numlutents; ++i) {
lutents[i] = pclrd->lutdata[cmapent->pcol + i * pclrd->numchans];
}
newcmptno = jas_image_numcmpts(dec->image);
jas_image_depalettize(dec->image, cmapent->cmptno, pclrd->numlutents, lutents, JP2_BPCTODTYPE(pclrd->bpc[cmapent->pcol]), newcmptno);
dec->chantocmptlut[channo] = newcmptno;
jas_free(lutents);
#if 0
if (dec->cdef) {
cdefent = jp2_cdef_lookup(cdefd, channo);
if (!cdefent) {
abort();
}
jas_image_setcmpttype(dec->image, newcmptno, jp2_getct(jas_image_clrspc(dec->image), cdefent->type, cdefent->assoc));
} else {
jas_image_setcmpttype(dec->image, newcmptno, jp2_getct(jas_image_clrspc(dec->image), 0, channo + 1));
}
#endif
}
}
}
/* Mark all components as being of unknown type. */
for (i = 0; i < JAS_CAST(uint, jas_image_numcmpts(dec->image)); ++i) {
jas_image_setcmpttype(dec->image, i, JAS_IMAGE_CT_UNKNOWN);
}
/* Determine the type of each component. */
if (dec->cdef) {
for (i = 0; i < dec->numchans; ++i) {
/* Is the channel number reasonable? */
if (dec->cdef->data.cdef.ents[i].channo >= dec->numchans) {
jas_eprintf("error: invalid channel number in CDEF box\n");
goto error;
}
jas_image_setcmpttype(dec->image,
dec->chantocmptlut[dec->cdef->data.cdef.ents[i].channo],
jp2_getct(jas_image_clrspc(dec->image),
dec->cdef->data.cdef.ents[i].type, dec->cdef->data.cdef.ents[i].assoc));
}
} else {
for (i = 0; i < dec->numchans; ++i) {
jas_image_setcmpttype(dec->image, dec->chantocmptlut[i],
jp2_getct(jas_image_clrspc(dec->image), 0, i + 1));
}
}
/* Delete any components that are not of interest. */
for (i = jas_image_numcmpts(dec->image); i > 0; --i) {
if (jas_image_cmpttype(dec->image, i - 1) == JAS_IMAGE_CT_UNKNOWN) {
jas_image_delcmpt(dec->image, i - 1);
}
}
/* Ensure that some components survived. */
if (!jas_image_numcmpts(dec->image)) {
jas_eprintf("error: no components\n");
goto error;
}
#if 0
jas_eprintf("no of components is %d\n", jas_image_numcmpts(dec->image));
#endif
/* Prevent the image from being destroyed later. */
image = dec->image;
dec->image = 0;
jp2_dec_destroy(dec);
return image;
error:
if (box) {
jp2_box_destroy(box);
}
if (dec) {
jp2_dec_destroy(dec);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'At many places in the code, jas_malloc or jas_recalloc was being
invoked with the size argument being computed in a manner that would not
allow integer overflow to be detected. Now, these places in the code
have been modified to use special-purpose memory allocation functions
(e.g., jas_alloc2, jas_alloc3, jas_realloc2) that check for overflow.
This should fix many security problems.'</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_unk_getparms(jpc_ms_t *ms, jpc_cstate_t *cstate, jas_stream_t *in)
{
jpc_unk_t *unk = &ms->parms.unk;
/* Eliminate compiler warning about unused variables. */
cstate = 0;
if (ms->len > 0) {
if (!(unk->data = jas_malloc(ms->len * sizeof(unsigned char)))) {
return -1;
}
if (jas_stream_read(in, (char *) unk->data, ms->len) != JAS_CAST(int, ms->len)) {
jas_free(unk->data);
return -1;
}
unk->len = ms->len;
} else {
unk->data = 0;
unk->len = 0;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'At many places in the code, jas_malloc or jas_recalloc was being
invoked with the size argument being computed in a manner that would not
allow integer overflow to be detected. Now, these places in the code
have been modified to use special-purpose memory allocation functions
(e.g., jas_alloc2, jas_alloc3, jas_realloc2) that check for overflow.
This should fix many security problems.'</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: char *jas_strdup(const char *s)
{
int n;
char *p;
n = strlen(s) + 1;
if (!(p = jas_malloc(n * sizeof(char)))) {
return 0;
}
strcpy(p, s);
return p;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'At many places in the code, jas_malloc or jas_recalloc was being
invoked with the size argument being computed in a manner that would not
allow integer overflow to be detected. Now, these places in the code
have been modified to use special-purpose memory allocation functions
(e.g., jas_alloc2, jas_alloc3, jas_realloc2) that check for overflow.
This should fix many security problems.'</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_malloc(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;
m = (parity) ? hstartcol : (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-189'], 'message': 'At many places in the code, jas_malloc or jas_recalloc was being
invoked with the size argument being computed in a manner that would not
allow integer overflow to be detected. Now, these places in the code
have been modified to use special-purpose memory allocation functions
(e.g., jas_alloc2, jas_alloc3, jas_realloc2) that check for overflow.
This should fix many security problems.'</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: _dbus_validate_signature_with_reason (const DBusString *type_str,
int type_pos,
int len)
{
const unsigned char *p;
const unsigned char *end;
int last;
int struct_depth;
int array_depth;
int dict_entry_depth;
DBusValidity result;
int element_count;
DBusList *element_count_stack;
result = DBUS_VALID;
element_count_stack = NULL;
if (!_dbus_list_append (&element_count_stack, _DBUS_INT_TO_POINTER (0)))
{
result = DBUS_VALIDITY_UNKNOWN_OOM_ERROR;
goto out;
}
_dbus_assert (type_str != NULL);
_dbus_assert (type_pos < _DBUS_INT32_MAX - len);
_dbus_assert (len >= 0);
_dbus_assert (type_pos >= 0);
if (len > DBUS_MAXIMUM_SIGNATURE_LENGTH)
{
result = DBUS_INVALID_SIGNATURE_TOO_LONG;
goto out;
}
p = _dbus_string_get_const_data_len (type_str, type_pos, 0);
end = _dbus_string_get_const_data_len (type_str, type_pos + len, 0);
struct_depth = 0;
array_depth = 0;
dict_entry_depth = 0;
last = DBUS_TYPE_INVALID;
while (p != end)
{
switch (*p)
{
case DBUS_TYPE_BYTE:
case DBUS_TYPE_BOOLEAN:
case DBUS_TYPE_INT16:
case DBUS_TYPE_UINT16:
case DBUS_TYPE_INT32:
case DBUS_TYPE_UINT32:
case DBUS_TYPE_INT64:
case DBUS_TYPE_UINT64:
case DBUS_TYPE_DOUBLE:
case DBUS_TYPE_STRING:
case DBUS_TYPE_OBJECT_PATH:
case DBUS_TYPE_SIGNATURE:
case DBUS_TYPE_VARIANT:
break;
case DBUS_TYPE_ARRAY:
array_depth += 1;
if (array_depth > DBUS_MAXIMUM_TYPE_RECURSION_DEPTH)
{
result = DBUS_INVALID_EXCEEDED_MAXIMUM_ARRAY_RECURSION;
goto out;
}
break;
case DBUS_STRUCT_BEGIN_CHAR:
struct_depth += 1;
if (struct_depth > DBUS_MAXIMUM_TYPE_RECURSION_DEPTH)
{
result = DBUS_INVALID_EXCEEDED_MAXIMUM_STRUCT_RECURSION;
goto out;
}
if (!_dbus_list_append (&element_count_stack,
_DBUS_INT_TO_POINTER (0)))
{
result = DBUS_VALIDITY_UNKNOWN_OOM_ERROR;
goto out;
}
break;
case DBUS_STRUCT_END_CHAR:
if (struct_depth == 0)
{
result = DBUS_INVALID_STRUCT_ENDED_BUT_NOT_STARTED;
goto out;
}
if (last == DBUS_STRUCT_BEGIN_CHAR)
{
result = DBUS_INVALID_STRUCT_HAS_NO_FIELDS;
goto out;
}
_dbus_list_pop_last (&element_count_stack);
struct_depth -= 1;
break;
case DBUS_DICT_ENTRY_BEGIN_CHAR:
if (last != DBUS_TYPE_ARRAY)
{
result = DBUS_INVALID_DICT_ENTRY_NOT_INSIDE_ARRAY;
goto out;
}
dict_entry_depth += 1;
if (dict_entry_depth > DBUS_MAXIMUM_TYPE_RECURSION_DEPTH)
{
result = DBUS_INVALID_EXCEEDED_MAXIMUM_DICT_ENTRY_RECURSION;
goto out;
}
if (!_dbus_list_append (&element_count_stack,
_DBUS_INT_TO_POINTER (0)))
{
result = DBUS_VALIDITY_UNKNOWN_OOM_ERROR;
goto out;
}
break;
case DBUS_DICT_ENTRY_END_CHAR:
if (dict_entry_depth == 0)
{
result = DBUS_INVALID_DICT_ENTRY_ENDED_BUT_NOT_STARTED;
goto out;
}
dict_entry_depth -= 1;
element_count =
_DBUS_POINTER_TO_INT (_dbus_list_pop_last (&element_count_stack));
if (element_count != 2)
{
if (element_count == 0)
result = DBUS_INVALID_DICT_ENTRY_HAS_NO_FIELDS;
else if (element_count == 1)
result = DBUS_INVALID_DICT_ENTRY_HAS_ONLY_ONE_FIELD;
else
result = DBUS_INVALID_DICT_ENTRY_HAS_TOO_MANY_FIELDS;
goto out;
}
break;
case DBUS_TYPE_STRUCT: /* doesn't appear in signatures */
case DBUS_TYPE_DICT_ENTRY: /* ditto */
default:
result = DBUS_INVALID_UNKNOWN_TYPECODE;
goto out;
}
if (*p != DBUS_TYPE_ARRAY &&
*p != DBUS_DICT_ENTRY_BEGIN_CHAR &&
*p != DBUS_STRUCT_BEGIN_CHAR)
{
element_count =
_DBUS_POINTER_TO_INT (_dbus_list_pop_last (&element_count_stack));
++element_count;
if (!_dbus_list_append (&element_count_stack,
_DBUS_INT_TO_POINTER (element_count)))
{
result = DBUS_VALIDITY_UNKNOWN_OOM_ERROR;
goto out;
}
}
if (array_depth > 0)
{
if (*p == DBUS_TYPE_ARRAY && p != end)
{
const char *p1;
p1 = p + 1;
if (*p1 == DBUS_STRUCT_END_CHAR ||
*p1 == DBUS_DICT_ENTRY_END_CHAR)
{
result = DBUS_INVALID_MISSING_ARRAY_ELEMENT_TYPE;
goto out;
}
}
else
{
array_depth = 0;
}
}
if (last == DBUS_DICT_ENTRY_BEGIN_CHAR &&
!dbus_type_is_basic (*p))
{
result = DBUS_INVALID_DICT_KEY_MUST_BE_BASIC_TYPE;
goto out;
}
last = *p;
++p;
}
if (array_depth > 0)
{
result = DBUS_INVALID_MISSING_ARRAY_ELEMENT_TYPE;
goto out;
}
if (struct_depth > 0)
{
result = DBUS_INVALID_STRUCT_STARTED_BUT_NOT_ENDED;
goto out;
}
if (dict_entry_depth > 0)
{
result = DBUS_INVALID_DICT_ENTRY_STARTED_BUT_NOT_ENDED;
goto out;
}
_dbus_assert (last != DBUS_TYPE_ARRAY);
_dbus_assert (last != DBUS_STRUCT_BEGIN_CHAR);
_dbus_assert (last != DBUS_DICT_ENTRY_BEGIN_CHAR);
result = DBUS_VALID;
out:
_dbus_list_clear (&element_count_stack);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Bug 17803: Panic from dbus_signature_validate
* dbus/dbus-marshal-validate.c: Ensure we validate
a basic type before calling is_basic on it.
* dbus-marshal-validate-util.c: Test.'</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 do_splice_from(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
int ret;
if (unlikely(!out->f_op || !out->f_op->splice_write))
return -EINVAL;
if (unlikely(!(out->f_mode & FMODE_WRITE)))
return -EBADF;
ret = rw_verify_area(WRITE, out, ppos, len);
if (unlikely(ret < 0))
return ret;
return out->f_op->splice_write(pipe, out, ppos, len, flags);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'Don't allow splice() to files opened with O_APPEND
This is debatable, but while we're debating it, let's disallow the
combination of splice and an O_APPEND destination.
It's not entirely clear what the semantics of O_APPEND should be, and
POSIX apparently expects pwrite() to ignore O_APPEND, for example. So
we could make up any semantics we want, including the old ones.
But Miklos convinced me that we should at least give it some thought,
and that accepting writes at arbitrary offsets is wrong at least for
IS_APPEND() files (which always have O_APPEND set, even if the reverse
isn't true: you can obviously have O_APPEND set on a regular file).
So disallow O_APPEND entirely for now. I doubt anybody cares, and this
way we have one less gray area to worry about.
Reported-and-argued-for-by: Miklos Szeredi <[email protected]>
Acked-by: Jens Axboe <[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: static struct audit_chunk *alloc_chunk(int count)
{
struct audit_chunk *chunk;
size_t size;
int i;
size = offsetof(struct audit_chunk, owners) + count * sizeof(struct node);
chunk = kzalloc(size, GFP_KERNEL);
if (!chunk)
return NULL;
INIT_LIST_HEAD(&chunk->hash);
INIT_LIST_HEAD(&chunk->trees);
chunk->count = count;
for (i = 0; i < count; i++) {
INIT_LIST_HEAD(&chunk->owners[i].list);
chunk->owners[i].index = i;
}
inotify_init_watch(&chunk->watch);
return chunk;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-362'], 'message': 'Fix inotify watch removal/umount races
Inotify watch removals suck violently.
To kick the watch out we need (in this order) inode->inotify_mutex and
ih->mutex. That's fine if we have a hold on inode; however, for all
other cases we need to make damn sure we don't race with umount. We can
*NOT* just grab a reference to a watch - inotify_unmount_inodes() will
happily sail past it and we'll end with reference to inode potentially
outliving its superblock.
Ideally we just want to grab an active reference to superblock if we
can; that will make sure we won't go into inotify_umount_inodes() until
we are done. Cleanup is just deactivate_super().
However, that leaves a messy case - what if we *are* racing with
umount() and active references to superblock can't be acquired anymore?
We can bump ->s_count, grab ->s_umount, which will almost certainly wait
until the superblock is shut down and the watch in question is pining
for fjords. That's fine, but there is a problem - we might have hit the
window between ->s_active getting to 0 / ->s_count - below S_BIAS (i.e.
the moment when superblock is past the point of no return and is heading
for shutdown) and the moment when deactivate_super() acquires
->s_umount.
We could just do drop_super() yield() and retry, but that's rather
antisocial and this stuff is luser-triggerable. OTOH, having grabbed
->s_umount and having found that we'd got there first (i.e. that
->s_root is non-NULL) we know that we won't race with
inotify_umount_inodes().
So we could grab a reference to watch and do the rest as above, just
with drop_super() instead of deactivate_super(), right? Wrong. We had
to drop ih->mutex before we could grab ->s_umount. So the watch
could've been gone already.
That still can be dealt with - we need to save watch->wd, do idr_find()
and compare its result with our pointer. If they match, we either have
the damn thing still alive or we'd lost not one but two races at once,
the watch had been killed and a new one got created with the same ->wd
at the same address. That couldn't have happened in inotify_destroy(),
but inotify_rm_wd() could run into that. Still, "new one got created"
is not a problem - we have every right to kill it or leave it alone,
whatever's more convenient.
So we can use idr_find(...) == watch && watch->inode->i_sb == sb as
"grab it and kill it" check. If it's been our original watch, we are
fine, if it's a newcomer - nevermind, just pretend that we'd won the
race and kill the fscker anyway; we are safe since we know that its
superblock won't be going away.
And yes, this is far beyond mere "not very pretty"; so's the entire
concept of inotify to start with.
Signed-off-by: Al Viro <[email protected]>
Acked-by: Greg KH <[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: static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
struct sg_io_v4 *hdr, struct bsg_device *bd,
fmode_t has_write_perm)
{
if (hdr->request_len > BLK_MAX_CDB) {
rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
if (!rq->cmd)
return -ENOMEM;
}
if (copy_from_user(rq->cmd, (void *)(unsigned long)hdr->request,
hdr->request_len))
return -EFAULT;
if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
if (blk_verify_command(&q->cmd_filter, rq->cmd, has_write_perm))
return -EPERM;
} else if (!capable(CAP_SYS_RAWIO))
return -EPERM;
/*
* fill in request structure
*/
rq->cmd_len = hdr->request_len;
rq->cmd_type = REQ_TYPE_BLOCK_PC;
rq->timeout = (hdr->timeout * HZ) / 1000;
if (!rq->timeout)
rq->timeout = q->sg_timeout;
if (!rq->timeout)
rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'Enforce a minimum SG_IO timeout
There's no point in having too short SG_IO timeouts, since if the
command does end up timing out, we'll end up through the reset sequence
that is several seconds long in order to abort the command that timed
out.
As a result, shorter timeouts than a few seconds simply do not make
sense, as the recovery would be longer than the timeout itself.
Add a BLK_MIN_SG_TIMEOUT to match the existign BLK_DEFAULT_SG_TIMEOUT.
Suggested-by: Alan Cox <[email protected]>
Acked-by: Tejun Heo <[email protected]>
Acked-by: Jens Axboe <[email protected]>
Cc: Jeff Garzik <[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: static void ms_adpcm_reset2 (_AFmoduleinst *i)
{
ms_adpcm_data *d = (ms_adpcm_data *) i->modspec;
int framesPerBlock;
framesPerBlock = d->samplesPerBlock / d->track->f.channelCount;
d->track->fpos_next_frame = d->track->fpos_first_frame +
d->blockAlign * (d->track->nextfframe / framesPerBlock);
d->track->frames2ignore += d->framesToIgnore;
assert(d->track->nextfframe % framesPerBlock == 0);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix decoding of multi-channel ADPCM audio files.'</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 status ParseFormat (AFfilehandle filehandle, AFvirtualfile *fp,
uint32_t id, size_t size)
{
_Track *track;
uint16_t formatTag, channelCount;
uint32_t sampleRate, averageBytesPerSecond;
uint16_t blockAlign;
_WAVEInfo *wave;
assert(filehandle != NULL);
assert(fp != NULL);
assert(!memcmp(&id, "fmt ", 4));
track = _af_filehandle_get_track(filehandle, AF_DEFAULT_TRACK);
assert(filehandle->formatSpecific != NULL);
wave = (_WAVEInfo *) filehandle->formatSpecific;
af_read_uint16_le(&formatTag, fp);
af_read_uint16_le(&channelCount, fp);
af_read_uint32_le(&sampleRate, fp);
af_read_uint32_le(&averageBytesPerSecond, fp);
af_read_uint16_le(&blockAlign, fp);
track->f.channelCount = channelCount;
track->f.sampleRate = sampleRate;
track->f.byteOrder = AF_BYTEORDER_LITTLEENDIAN;
/* Default to uncompressed audio data. */
track->f.compressionType = AF_COMPRESSION_NONE;
switch (formatTag)
{
case WAVE_FORMAT_PCM:
{
uint16_t bitsPerSample;
af_read_uint16_le(&bitsPerSample, fp);
track->f.sampleWidth = bitsPerSample;
if (bitsPerSample == 0 || bitsPerSample > 32)
{
_af_error(AF_BAD_WIDTH,
"bad sample width of %d bits",
bitsPerSample);
return AF_FAIL;
}
if (bitsPerSample <= 8)
track->f.sampleFormat = AF_SAMPFMT_UNSIGNED;
else
track->f.sampleFormat = AF_SAMPFMT_TWOSCOMP;
}
break;
case WAVE_FORMAT_MULAW:
case IBM_FORMAT_MULAW:
track->f.sampleWidth = 16;
track->f.sampleFormat = AF_SAMPFMT_TWOSCOMP;
track->f.compressionType = AF_COMPRESSION_G711_ULAW;
break;
case WAVE_FORMAT_ALAW:
case IBM_FORMAT_ALAW:
track->f.sampleWidth = 16;
track->f.sampleFormat = AF_SAMPFMT_TWOSCOMP;
track->f.compressionType = AF_COMPRESSION_G711_ALAW;
break;
case WAVE_FORMAT_IEEE_FLOAT:
{
uint16_t bitsPerSample;
af_read_uint16_le(&bitsPerSample, fp);
if (bitsPerSample == 64)
{
track->f.sampleWidth = 64;
track->f.sampleFormat = AF_SAMPFMT_DOUBLE;
}
else
{
track->f.sampleWidth = 32;
track->f.sampleFormat = AF_SAMPFMT_FLOAT;
}
}
break;
case WAVE_FORMAT_ADPCM:
{
uint16_t bitsPerSample, extraByteCount,
samplesPerBlock, numCoefficients;
int i;
AUpvlist pv;
long l;
void *v;
if (track->f.channelCount != 1 &&
track->f.channelCount != 2)
{
_af_error(AF_BAD_CHANNELS,
"WAVE file with MS ADPCM compression "
"must have 1 or 2 channels");
}
af_read_uint16_le(&bitsPerSample, fp);
af_read_uint16_le(&extraByteCount, fp);
af_read_uint16_le(&samplesPerBlock, fp);
af_read_uint16_le(&numCoefficients, fp);
/* numCoefficients should be at least 7. */
assert(numCoefficients >= 7 && numCoefficients <= 255);
for (i=0; i<numCoefficients; i++)
{
int16_t a0, a1;
af_fread(&a0, 1, 2, fp);
af_fread(&a1, 1, 2, fp);
a0 = LENDIAN_TO_HOST_INT16(a0);
a1 = LENDIAN_TO_HOST_INT16(a1);
wave->msadpcmCoefficients[i][0] = a0;
wave->msadpcmCoefficients[i][1] = a1;
}
track->f.sampleWidth = 16;
track->f.sampleFormat = AF_SAMPFMT_TWOSCOMP;
track->f.compressionType = AF_COMPRESSION_MS_ADPCM;
track->f.byteOrder = _AF_BYTEORDER_NATIVE;
/* Create the parameter list. */
pv = AUpvnew(4);
AUpvsetparam(pv, 0, _AF_MS_ADPCM_NUM_COEFFICIENTS);
AUpvsetvaltype(pv, 0, AU_PVTYPE_LONG);
l = numCoefficients;
AUpvsetval(pv, 0, &l);
AUpvsetparam(pv, 1, _AF_MS_ADPCM_COEFFICIENTS);
AUpvsetvaltype(pv, 1, AU_PVTYPE_PTR);
v = wave->msadpcmCoefficients;
AUpvsetval(pv, 1, &v);
AUpvsetparam(pv, 2, _AF_SAMPLES_PER_BLOCK);
AUpvsetvaltype(pv, 2, AU_PVTYPE_LONG);
l = samplesPerBlock;
AUpvsetval(pv, 2, &l);
AUpvsetparam(pv, 3, _AF_BLOCK_SIZE);
AUpvsetvaltype(pv, 3, AU_PVTYPE_LONG);
l = blockAlign;
AUpvsetval(pv, 3, &l);
track->f.compressionParams = pv;
}
break;
case WAVE_FORMAT_DVI_ADPCM:
{
AUpvlist pv;
long l;
uint16_t bitsPerSample, extraByteCount,
samplesPerBlock;
af_read_uint16_le(&bitsPerSample, fp);
af_read_uint16_le(&extraByteCount, fp);
af_read_uint16_le(&samplesPerBlock, fp);
track->f.sampleWidth = 16;
track->f.sampleFormat = AF_SAMPFMT_TWOSCOMP;
track->f.compressionType = AF_COMPRESSION_IMA;
track->f.byteOrder = _AF_BYTEORDER_NATIVE;
/* Create the parameter list. */
pv = AUpvnew(2);
AUpvsetparam(pv, 0, _AF_SAMPLES_PER_BLOCK);
AUpvsetvaltype(pv, 0, AU_PVTYPE_LONG);
l = samplesPerBlock;
AUpvsetval(pv, 0, &l);
AUpvsetparam(pv, 1, _AF_BLOCK_SIZE);
AUpvsetvaltype(pv, 1, AU_PVTYPE_LONG);
l = blockAlign;
AUpvsetval(pv, 1, &l);
track->f.compressionParams = pv;
}
break;
case WAVE_FORMAT_YAMAHA_ADPCM:
case WAVE_FORMAT_OKI_ADPCM:
case WAVE_FORMAT_CREATIVE_ADPCM:
case IBM_FORMAT_ADPCM:
_af_error(AF_BAD_NOT_IMPLEMENTED, "WAVE ADPCM data format 0x%x is not currently supported", formatTag);
return AF_FAIL;
break;
case WAVE_FORMAT_MPEG:
_af_error(AF_BAD_NOT_IMPLEMENTED, "WAVE MPEG data format is not supported");
return AF_FAIL;
break;
case WAVE_FORMAT_MPEGLAYER3:
_af_error(AF_BAD_NOT_IMPLEMENTED, "WAVE MPEG layer 3 data format is not supported");
return AF_FAIL;
break;
default:
_af_error(AF_BAD_NOT_IMPLEMENTED, "WAVE file data format 0x%x not currently supported", formatTag);
return AF_FAIL;
break;
}
_af_set_sample_format(&track->f, track->f.sampleFormat, track->f.sampleWidth);
return AF_SUCCEED;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix decoding of multi-channel ADPCM audio files.'</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 nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
struct nfs_fh *mntfh)
{
struct nfs_client *parent_client;
struct nfs_server *server, *parent_server;
struct nfs_fattr fattr;
int error;
dprintk("--> nfs4_create_referral_server()\n");
server = nfs_alloc_server();
if (!server)
return ERR_PTR(-ENOMEM);
parent_server = NFS_SB(data->sb);
parent_client = parent_server->nfs_client;
/* Get a client representation.
* Note: NFSv4 always uses TCP, */
error = nfs4_set_client(server, data->hostname, data->addr,
parent_client->cl_ipaddr,
data->authflavor,
parent_server->client->cl_xprt->prot,
parent_client->retrans_timeo,
parent_client->retrans_count);
if (error < 0)
goto error;
/* Initialise the client representation from the parent server */
nfs_server_copy_userdata(server, parent_server);
server->caps |= NFS_CAP_ATOMIC_OPEN;
error = nfs_init_server_rpcclient(server, data->authflavor);
if (error < 0)
goto error;
BUG_ON(!server->nfs_client);
BUG_ON(!server->nfs_client->rpc_ops);
BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
/* Probe the root fh to retrieve its FSID and filehandle */
error = nfs4_path_walk(server, mntfh, data->mnt_path);
if (error < 0)
goto error;
/* probe the filesystem info for this server filesystem */
error = nfs_probe_fsinfo(server, mntfh, &fattr);
if (error < 0)
goto error;
dprintk("Referral FSID: %llx:%llx\n",
(unsigned long long) server->fsid.major,
(unsigned long long) server->fsid.minor);
spin_lock(&nfs_client_lock);
list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
list_add_tail(&server->master_link, &nfs_volume_list);
spin_unlock(&nfs_client_lock);
server->mount_time = jiffies;
dprintk("<-- nfs_create_referral_server() = %p\n", server);
return server;
error:
nfs_free_server(server);
dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
return ERR_PTR(error);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'NFS: Fix an Oops in encode_lookup()
It doesn't look as if the NFS file name limit is being initialised correctly
in the struct nfs_server. Make sure that we limit whatever is being set in
nfs_probe_fsinfo() and nfs_init_server().
Also ensure that readdirplus and nfs4_path_walk respect our file name
limits.
Signed-off-by: Trond Myklebust <[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: int huft_build(b, n, s, d, e, t, m)
unsigned *b; /* code lengths in bits (all assumed <= BMAX) */
unsigned n; /* number of codes (assumed <= N_MAX) */
unsigned s; /* number of simple-valued codes (0..s-1) */
ush *d; /* list of base values for non-simple codes */
ush *e; /* list of extra bits for non-simple codes */
struct huft **t; /* result: starting table */
int *m; /* maximum lookup bits, returns actual */
/* Given a list of code lengths and a maximum table size, make a set of
tables to decode that set of codes. Return zero on success, one if
the given code set is incomplete (the tables are still built in this
case), two if the input is invalid (all zero length codes or an
oversubscribed set of lengths), and three if not enough memory. */
{
unsigned a; /* counter for codes of length k */
unsigned c[BMAX+1]; /* bit length count table */
unsigned f; /* i repeats in table every f entries */
int g; /* maximum code length */
int h; /* table level */
register unsigned i; /* counter, current code */
register unsigned j; /* counter */
register int k; /* number of bits in current code */
int l; /* bits per table (returned in m) */
register unsigned *p; /* pointer into c[], b[], or v[] */
register struct huft *q; /* points to current table */
struct huft r; /* table entry for structure assignment */
struct huft *u[BMAX]; /* table stack */
unsigned v[N_MAX]; /* values in order of bit length */
register int w; /* bits before this table == (l * h) */
unsigned x[BMAX+1]; /* bit offsets, then code stack */
unsigned *xp; /* pointer into x */
int y; /* number of dummy codes added */
unsigned z; /* number of entries in current table */
/* Generate counts for each bit length */
memzero(c, sizeof(c));
p = b; i = n;
do {
Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"),
n-i, *p));
c[*p]++; /* assume all entries <= BMAX */
p++; /* Can't combine with above line (Solaris bug) */
} while (--i);
if (c[0] == n) /* null input--all zero length codes */
{
q = (struct huft *) malloc (2 * sizeof *q);
if (!q)
return 3;
hufts += 2;
q[0].v.t = (struct huft *) NULL;
q[1].e = 99; /* invalid code marker */
q[1].b = 1;
*t = q + 1;
*m = 1;
return 0;
}
/* Find minimum and maximum length, bound *m by those */
l = *m;
for (j = 1; j <= BMAX; j++)
if (c[j])
break;
k = j; /* minimum code length */
if ((unsigned)l < j)
l = j;
for (i = BMAX; i; i--)
if (c[i])
break;
g = i; /* maximum code length */
if ((unsigned)l > i)
l = i;
*m = l;
/* Adjust last length count to fill out codes, if needed */
for (y = 1 << j; j < i; j++, y <<= 1)
if ((y -= c[j]) < 0)
return 2; /* bad input: more codes than bits */
if ((y -= c[i]) < 0)
return 2;
c[i] += y;
/* Generate starting offsets into the value table for each length */
x[1] = j = 0;
p = c + 1; xp = x + 2;
while (--i) { /* note that i == g from above */
*xp++ = (j += *p++);
}
/* Make a table of values in order of bit lengths */
p = b; i = 0;
do {
if ((j = *p++) != 0)
v[x[j]++] = i;
} while (++i < n);
n = x[g]; /* set n to length of v */
/* Generate the Huffman codes and for each, make the table entries */
x[0] = i = 0; /* first Huffman code is zero */
p = v; /* grab values in bit order */
h = -1; /* no tables yet--level -1 */
w = -l; /* bits decoded == (l * h) */
u[0] = (struct huft *)NULL; /* just to keep compilers happy */
q = (struct huft *)NULL; /* ditto */
z = 0; /* ditto */
/* go through the bit lengths (k already is bits in shortest code) */
for (; k <= g; k++)
{
a = c[k];
while (a--)
{
/* here i is the Huffman code of length k bits for value *p */
/* make tables up to required level */
while (k > w + l)
{
h++;
w += l; /* previous table always l bits */
/* compute minimum size table less than or equal to l bits */
z = (z = g - w) > (unsigned)l ? l : z; /* upper limit on table size */
if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */
{ /* too few codes for k-w bit table */
f -= a + 1; /* deduct codes from patterns left */
xp = c + k;
if (j < z)
while (++j < z) /* try smaller tables up to z bits */
{
if ((f <<= 1) <= *++xp)
break; /* enough codes to use up j bits */
f -= *xp; /* else deduct codes from patterns */
}
}
z = 1 << j; /* table entries for j-bit table */
/* allocate and link in new table */
if ((q = (struct huft *)malloc((z + 1)*sizeof(struct huft))) ==
(struct huft *)NULL)
{
if (h)
huft_free(u[0]);
return 3; /* not enough memory */
}
hufts += z + 1; /* track memory usage */
*t = q + 1; /* link to list for huft_free() */
*(t = &(q->v.t)) = (struct huft *)NULL;
u[h] = ++q; /* table starts after link */
/* connect to last table, if there is one */
if (h)
{
x[h] = i; /* save pattern for backing up */
r.b = (uch)l; /* bits to dump before this table */
r.e = (uch)(16 + j); /* bits in this table */
r.v.t = q; /* pointer to this table */
j = i >> (w - l); /* (get around Turbo C bug) */
u[h-1][j] = r; /* connect to last table */
}
}
/* set up table entry in r */
r.b = (uch)(k - w);
if (p >= v + n)
r.e = 99; /* out of values--invalid code */
else if (*p < s)
{
r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */
r.v.n = (ush)(*p); /* simple code is just the value */
p++; /* one compiler does not like *p++ */
}
else
{
r.e = (uch)e[*p - s]; /* non-simple--look up in lists */
r.v.n = d[*p++ - s];
}
/* fill code-like entries with r */
f = 1 << (k - w);
for (j = i >> w; j < z; j += f)
q[j] = r;
/* backwards increment the k-bit code i */
for (j = 1 << (k - 1); i & j; j >>= 1)
i ^= j;
i ^= j;
/* backup over finished tables */
while ((i & ((1 << w) - 1)) != x[h])
{
h--; /* don't need to update q */
w -= l;
}
}
}
/* Return true (1) if we were given an incomplete table */
return y != 0 && g != 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'avoid creating an undersized buffer for the hufts table
A malformed input file can cause gzip to crash with a segmentation
violation or hang in an endless loop.
Reported in <http://bugs.debian.org/507263>.
* NEWS (Bug fixes): Mention it.'</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 nr_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct full_sockaddr_ax25 *sax = (struct full_sockaddr_ax25 *)uaddr;
struct sock *sk = sock->sk;
struct nr_sock *nr = nr_sk(sk);
lock_sock(sk);
if (peer != 0) {
if (sk->sk_state != TCP_ESTABLISHED) {
release_sock(sk);
return -ENOTCONN;
}
sax->fsa_ax25.sax25_family = AF_NETROM;
sax->fsa_ax25.sax25_ndigis = 1;
sax->fsa_ax25.sax25_call = nr->user_addr;
sax->fsa_digipeater[0] = nr->dest_addr;
*uaddr_len = sizeof(struct full_sockaddr_ax25);
} else {
sax->fsa_ax25.sax25_family = AF_NETROM;
sax->fsa_ax25.sax25_ndigis = 0;
sax->fsa_ax25.sax25_call = nr->source_addr;
*uaddr_len = sizeof(struct sockaddr_ax25);
}
release_sock(sk);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'netrom: Fix nr_getname() leak
nr_getname() can leak kernel memory to user.
Signed-off-by: Eric Dumazet <[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 __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl)
{
unsigned char *b = skb->tail;
struct tc_cbq_police opt;
if (cl->police) {
opt.police = cl->police;
RTA_PUT(skb, TCA_CBQ_POLICE, sizeof(opt), &opt);
}
return skb->len;
rtattr_failure:
skb_trim(skb, b - skb->data);
return -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': '[NETLINK]: Missing initializations in dumped data
Mostly missing initialization of padding fields of 1 or 2 bytes length,
two instances of uninitialized nlmsgerr->msg of 16 bytes length.
Signed-off-by: Patrick McHardy <[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: __rta_reserve(struct sk_buff *skb, int attrtype, int attrlen)
{
struct rtattr *rta;
int size = RTA_LENGTH(attrlen);
rta = (struct rtattr*)skb_put(skb, RTA_ALIGN(size));
rta->rta_type = attrtype;
rta->rta_len = size;
return rta;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': '[NETLINK]: Clear padding in netlink messages
Signed-off-by: Patrick McHardy <[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: int main(int argc, char ** argv)
{
int c;
unsigned long flags = MS_MANDLOCK;
char * orgoptions = NULL;
char * share_name = NULL;
const char * ipaddr = NULL;
char * uuid = NULL;
char * mountpoint = NULL;
char * options = NULL;
char * optionstail;
char * resolved_path = NULL;
char * temp;
char * dev_name;
int rc = 0;
int rsize = 0;
int wsize = 0;
int nomtab = 0;
int uid = 0;
int gid = 0;
int optlen = 0;
int orgoptlen = 0;
size_t options_size = 0;
size_t current_len;
int retry = 0; /* set when we have to retry mount with uppercase */
struct addrinfo *addrhead = NULL, *addr;
struct utsname sysinfo;
struct mntent mountent;
struct sockaddr_in *addr4;
struct sockaddr_in6 *addr6;
FILE * pmntfile;
/* setlocale(LC_ALL, "");
bindtextdomain(PACKAGE, LOCALEDIR);
textdomain(PACKAGE); */
if(argc && argv)
thisprogram = argv[0];
else
mount_cifs_usage(stderr);
if(thisprogram == NULL)
thisprogram = "mount.cifs";
uname(&sysinfo);
/* BB add workstation name and domain and pass down */
/* #ifdef _GNU_SOURCE
fprintf(stderr, " node: %s machine: %s sysname %s domain %s\n", sysinfo.nodename,sysinfo.machine,sysinfo.sysname,sysinfo.domainname);
#endif */
if(argc > 2) {
dev_name = argv[1];
share_name = strndup(argv[1], MAX_UNC_LEN);
if (share_name == NULL) {
fprintf(stderr, "%s: %s", argv[0], strerror(ENOMEM));
exit(EX_SYSERR);
}
mountpoint = argv[2];
} else if (argc == 2) {
if ((strcmp(argv[1], "-V") == 0) ||
(strcmp(argv[1], "--version") == 0))
{
print_cifs_mount_version();
exit(0);
}
if ((strcmp(argv[1], "-h") == 0) ||
(strcmp(argv[1], "-?") == 0) ||
(strcmp(argv[1], "--help") == 0))
mount_cifs_usage(stdout);
mount_cifs_usage(stderr);
} else {
mount_cifs_usage(stderr);
}
/* add sharename in opts string as unc= parm */
while ((c = getopt_long (argc, argv, "afFhilL:no:O:rsSU:vVwt:",
longopts, NULL)) != -1) {
switch (c) {
/* No code to do the following options yet */
/* case 'l':
list_with_volumelabel = 1;
break;
case 'L':
volumelabel = optarg;
break; */
/* case 'a':
++mount_all;
break; */
case '?':
case 'h': /* help */
mount_cifs_usage(stdout);
case 'n':
++nomtab;
break;
case 'b':
#ifdef MS_BIND
flags |= MS_BIND;
#else
fprintf(stderr,
"option 'b' (MS_BIND) not supported\n");
#endif
break;
case 'm':
#ifdef MS_MOVE
flags |= MS_MOVE;
#else
fprintf(stderr,
"option 'm' (MS_MOVE) not supported\n");
#endif
break;
case 'o':
orgoptions = strdup(optarg);
break;
case 'r': /* mount readonly */
flags |= MS_RDONLY;
break;
case 'U':
uuid = optarg;
break;
case 'v':
++verboseflag;
break;
case 'V':
print_cifs_mount_version();
exit (0);
case 'w':
flags &= ~MS_RDONLY;
break;
case 'R':
rsize = atoi(optarg) ;
break;
case 'W':
wsize = atoi(optarg);
break;
case '1':
if (isdigit(*optarg)) {
char *ep;
uid = strtoul(optarg, &ep, 10);
if (*ep) {
fprintf(stderr, "bad uid value \"%s\"\n", optarg);
exit(EX_USAGE);
}
} else {
struct passwd *pw;
if (!(pw = getpwnam(optarg))) {
fprintf(stderr, "bad user name \"%s\"\n", optarg);
exit(EX_USAGE);
}
uid = pw->pw_uid;
endpwent();
}
break;
case '2':
if (isdigit(*optarg)) {
char *ep;
gid = strtoul(optarg, &ep, 10);
if (*ep) {
fprintf(stderr, "bad gid value \"%s\"\n", optarg);
exit(EX_USAGE);
}
} else {
struct group *gr;
if (!(gr = getgrnam(optarg))) {
fprintf(stderr, "bad user name \"%s\"\n", optarg);
exit(EX_USAGE);
}
gid = gr->gr_gid;
endpwent();
}
break;
case 'u':
got_user = 1;
user_name = optarg;
break;
case 'd':
domain_name = optarg; /* BB fix this - currently ignored */
got_domain = 1;
break;
case 'p':
if(mountpassword == NULL)
mountpassword = (char *)calloc(MOUNT_PASSWD_SIZE+1,1);
if(mountpassword) {
got_password = 1;
strlcpy(mountpassword,optarg,MOUNT_PASSWD_SIZE+1);
}
break;
case 'S':
get_password_from_file(0 /* stdin */,NULL);
break;
case 't':
break;
case 'f':
++fakemnt;
break;
default:
fprintf(stderr, "unknown mount option %c\n",c);
mount_cifs_usage(stderr);
}
}
if((argc < 3) || (dev_name == NULL) || (mountpoint == NULL)) {
mount_cifs_usage(stderr);
}
/* make sure mountpoint is legit */
rc = chdir(mountpoint);
if (rc) {
fprintf(stderr, "Couldn't chdir to %s: %s\n", mountpoint,
strerror(errno));
rc = EX_USAGE;
goto mount_exit;
}
rc = check_mountpoint(thisprogram, mountpoint);
if (rc)
goto mount_exit;
/* sanity check for unprivileged mounts */
if (getuid()) {
rc = check_fstab(thisprogram, mountpoint, dev_name,
&orgoptions);
if (rc)
goto mount_exit;
/* enable any default user mount flags */
flags |= CIFS_SETUID_FLAGS;
}
if (getenv("PASSWD")) {
if(mountpassword == NULL)
mountpassword = (char *)calloc(MOUNT_PASSWD_SIZE+1,1);
if(mountpassword) {
strlcpy(mountpassword,getenv("PASSWD"),MOUNT_PASSWD_SIZE+1);
got_password = 1;
}
} else if (getenv("PASSWD_FD")) {
get_password_from_file(atoi(getenv("PASSWD_FD")),NULL);
} else if (getenv("PASSWD_FILE")) {
get_password_from_file(0, getenv("PASSWD_FILE"));
}
if (orgoptions && parse_options(&orgoptions, &flags)) {
rc = EX_USAGE;
goto mount_exit;
}
if (getuid()) {
#if !CIFS_LEGACY_SETUID_CHECK
if (!(flags & (MS_USERS|MS_USER))) {
fprintf(stderr, "%s: permission denied\n", thisprogram);
rc = EX_USAGE;
goto mount_exit;
}
#endif /* !CIFS_LEGACY_SETUID_CHECK */
if (geteuid()) {
fprintf(stderr, "%s: not installed setuid - \"user\" "
"CIFS mounts not supported.",
thisprogram);
rc = EX_FAIL;
goto mount_exit;
}
}
flags &= ~(MS_USERS|MS_USER);
addrhead = addr = parse_server(&share_name);
if((addrhead == NULL) && (got_ip == 0)) {
fprintf(stderr, "No ip address specified and hostname not found\n");
rc = EX_USAGE;
goto mount_exit;
}
/* BB save off path and pop after mount returns? */
resolved_path = (char *)malloc(PATH_MAX+1);
if (!resolved_path) {
fprintf(stderr, "Unable to allocate memory.\n");
rc = EX_SYSERR;
goto mount_exit;
}
/* Note that if we can not canonicalize the name, we get
another chance to see if it is valid when we chdir to it */
if(!realpath(".", resolved_path)) {
fprintf(stderr, "Unable to resolve %s to canonical path: %s\n",
mountpoint, strerror(errno));
rc = EX_SYSERR;
goto mount_exit;
}
mountpoint = resolved_path;
if(got_user == 0) {
/* Note that the password will not be retrieved from the
USER env variable (ie user%password form) as there is
already a PASSWD environment varaible */
if (getenv("USER"))
user_name = strdup(getenv("USER"));
if (user_name == NULL)
user_name = getusername();
got_user = 1;
}
if(got_password == 0) {
char *tmp_pass = getpass("Password: "); /* BB obsolete sys call but
no good replacement yet. */
mountpassword = (char *)calloc(MOUNT_PASSWD_SIZE+1,1);
if (!tmp_pass || !mountpassword) {
fprintf(stderr, "Password not entered, exiting\n");
exit(EX_USAGE);
}
strlcpy(mountpassword, tmp_pass, MOUNT_PASSWD_SIZE+1);
got_password = 1;
}
/* FIXME launch daemon (handles dfs name resolution and credential change)
remember to clear parms and overwrite password field before launching */
if(orgoptions) {
optlen = strlen(orgoptions);
orgoptlen = optlen;
} else
optlen = 0;
if(share_name)
optlen += strlen(share_name) + 4;
else {
fprintf(stderr, "No server share name specified\n");
fprintf(stderr, "\nMounting the DFS root for server not implemented yet\n");
exit(EX_USAGE);
}
if(user_name)
optlen += strlen(user_name) + 6;
optlen += MAX_ADDRESS_LEN + 4;
if(mountpassword)
optlen += strlen(mountpassword) + 6;
mount_retry:
SAFE_FREE(options);
options_size = optlen + 10 + DOMAIN_SIZE;
options = (char *)malloc(options_size /* space for commas in password */ + 8 /* space for domain= , domain name itself was counted as part of the length username string above */);
if(options == NULL) {
fprintf(stderr, "Could not allocate memory for mount options\n");
exit(EX_SYSERR);
}
strlcpy(options, "unc=", options_size);
strlcat(options,share_name,options_size);
/* scan backwards and reverse direction of slash */
temp = strrchr(options, '/');
if(temp > options + 6)
*temp = '\\';
if(user_name) {
/* check for syntax like user=domain\user */
if(got_domain == 0)
domain_name = check_for_domain(&user_name);
strlcat(options,",user=",options_size);
strlcat(options,user_name,options_size);
}
if(retry == 0) {
if(domain_name) {
/* extra length accounted for in option string above */
strlcat(options,",domain=",options_size);
strlcat(options,domain_name,options_size);
}
}
strlcat(options,",ver=",options_size);
strlcat(options,MOUNT_CIFS_VERSION_MAJOR,options_size);
if(orgoptions) {
strlcat(options,",",options_size);
strlcat(options,orgoptions,options_size);
}
if(prefixpath) {
strlcat(options,",prefixpath=",options_size);
strlcat(options,prefixpath,options_size); /* no need to cat the / */
}
/* convert all '\\' to '/' in share portion so that /proc/mounts looks pretty */
replace_char(dev_name, '\\', '/', strlen(share_name));
if (!got_ip && addr) {
strlcat(options, ",ip=", options_size);
current_len = strnlen(options, options_size);
optionstail = options + current_len;
switch (addr->ai_addr->sa_family) {
case AF_INET6:
addr6 = (struct sockaddr_in6 *) addr->ai_addr;
ipaddr = inet_ntop(AF_INET6, &addr6->sin6_addr, optionstail,
options_size - current_len);
break;
case AF_INET:
addr4 = (struct sockaddr_in *) addr->ai_addr;
ipaddr = inet_ntop(AF_INET, &addr4->sin_addr, optionstail,
options_size - current_len);
break;
default:
ipaddr = NULL;
}
/* if the address looks bogus, try the next one */
if (!ipaddr) {
addr = addr->ai_next;
if (addr)
goto mount_retry;
rc = EX_SYSERR;
goto mount_exit;
}
}
if (addr->ai_addr->sa_family == AF_INET6 && addr6->sin6_scope_id) {
strlcat(options, "%", options_size);
current_len = strnlen(options, options_size);
optionstail = options + current_len;
snprintf(optionstail, options_size - current_len, "%u",
addr6->sin6_scope_id);
}
if(verboseflag)
fprintf(stderr, "\nmount.cifs kernel mount options: %s", options);
if (mountpassword) {
/*
* Commas have to be doubled, or else they will
* look like the parameter separator
*/
if(retry == 0)
check_for_comma(&mountpassword);
strlcat(options,",pass=",options_size);
strlcat(options,mountpassword,options_size);
if (verboseflag)
fprintf(stderr, ",pass=********");
}
if (verboseflag)
fprintf(stderr, "\n");
if (!fakemnt && mount(dev_name, ".", cifs_fstype, flags, options)) {
switch (errno) {
case ECONNREFUSED:
case EHOSTUNREACH:
if (addr) {
addr = addr->ai_next;
if (addr)
goto mount_retry;
}
break;
case ENODEV:
fprintf(stderr, "mount error: cifs filesystem not supported by the system\n");
break;
case ENXIO:
if(retry == 0) {
retry = 1;
if (uppercase_string(dev_name) &&
uppercase_string(share_name) &&
uppercase_string(prefixpath)) {
fprintf(stderr, "retrying with upper case share name\n");
goto mount_retry;
}
}
}
fprintf(stderr, "mount error(%d): %s\n", errno, strerror(errno));
fprintf(stderr, "Refer to the mount.cifs(8) manual page (e.g. man "
"mount.cifs)\n");
rc = EX_FAIL;
goto mount_exit;
}
if (nomtab)
goto mount_exit;
atexit(unlock_mtab);
rc = lock_mtab();
if (rc) {
fprintf(stderr, "cannot lock mtab");
goto mount_exit;
}
pmntfile = setmntent(MOUNTED, "a+");
if (!pmntfile) {
fprintf(stderr, "could not update mount table\n");
unlock_mtab();
rc = EX_FILEIO;
goto mount_exit;
}
mountent.mnt_fsname = dev_name;
mountent.mnt_dir = mountpoint;
mountent.mnt_type = (char *)(void *)cifs_fstype;
mountent.mnt_opts = (char *)malloc(220);
if(mountent.mnt_opts) {
char * mount_user = getusername();
memset(mountent.mnt_opts,0,200);
if(flags & MS_RDONLY)
strlcat(mountent.mnt_opts,"ro",220);
else
strlcat(mountent.mnt_opts,"rw",220);
if(flags & MS_MANDLOCK)
strlcat(mountent.mnt_opts,",mand",220);
if(flags & MS_NOEXEC)
strlcat(mountent.mnt_opts,",noexec",220);
if(flags & MS_NOSUID)
strlcat(mountent.mnt_opts,",nosuid",220);
if(flags & MS_NODEV)
strlcat(mountent.mnt_opts,",nodev",220);
if(flags & MS_SYNCHRONOUS)
strlcat(mountent.mnt_opts,",sync",220);
if(mount_user) {
if(getuid() != 0) {
strlcat(mountent.mnt_opts,
",user=", 220);
strlcat(mountent.mnt_opts,
mount_user, 220);
}
}
}
mountent.mnt_freq = 0;
mountent.mnt_passno = 0;
rc = addmntent(pmntfile,&mountent);
endmntent(pmntfile);
unlock_mtab();
SAFE_FREE(mountent.mnt_opts);
if (rc)
rc = EX_FILEIO;
mount_exit:
if(mountpassword) {
int len = strlen(mountpassword);
memset(mountpassword,0,len);
SAFE_FREE(mountpassword);
}
if (addrhead)
freeaddrinfo(addrhead);
SAFE_FREE(options);
SAFE_FREE(orgoptions);
SAFE_FREE(resolved_path);
SAFE_FREE(share_name);
exit(rc);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-59'], 'message': 'mount.cifs: check for invalid characters in device name and mountpoint
It's apparently possible to corrupt the mtab if you pass embedded
newlines to addmntent. Apparently tabs are also a problem with certain
earlier glibc versions. Backslashes are also a minor issue apparently,
but we can't reasonably filter those.
Make sure that neither the devname or mountpoint contain any problematic
characters before allowing the mount to proceed.
Signed-off-by: Jeff Layton <[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: x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
{
struct decode_cache *c = &ctxt->decode;
int rc = 0;
int mode = ctxt->mode;
int def_op_bytes, def_ad_bytes, group;
/* Shadow copy of register state. Committed on successful emulation. */
memset(c, 0, sizeof(struct decode_cache));
c->eip = kvm_rip_read(ctxt->vcpu);
ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
switch (mode) {
case X86EMUL_MODE_REAL:
case X86EMUL_MODE_PROT16:
def_op_bytes = def_ad_bytes = 2;
break;
case X86EMUL_MODE_PROT32:
def_op_bytes = def_ad_bytes = 4;
break;
#ifdef CONFIG_X86_64
case X86EMUL_MODE_PROT64:
def_op_bytes = 4;
def_ad_bytes = 8;
break;
#endif
default:
return -1;
}
c->op_bytes = def_op_bytes;
c->ad_bytes = def_ad_bytes;
/* Legacy prefixes. */
for (;;) {
switch (c->b = insn_fetch(u8, 1, c->eip)) {
case 0x66: /* operand-size override */
/* switch between 2/4 bytes */
c->op_bytes = def_op_bytes ^ 6;
break;
case 0x67: /* address-size override */
if (mode == X86EMUL_MODE_PROT64)
/* switch between 4/8 bytes */
c->ad_bytes = def_ad_bytes ^ 12;
else
/* switch between 2/4 bytes */
c->ad_bytes = def_ad_bytes ^ 6;
break;
case 0x26: /* ES override */
case 0x2e: /* CS override */
case 0x36: /* SS override */
case 0x3e: /* DS override */
set_seg_override(c, (c->b >> 3) & 3);
break;
case 0x64: /* FS override */
case 0x65: /* GS override */
set_seg_override(c, c->b & 7);
break;
case 0x40 ... 0x4f: /* REX */
if (mode != X86EMUL_MODE_PROT64)
goto done_prefixes;
c->rex_prefix = c->b;
continue;
case 0xf0: /* LOCK */
c->lock_prefix = 1;
break;
case 0xf2: /* REPNE/REPNZ */
c->rep_prefix = REPNE_PREFIX;
break;
case 0xf3: /* REP/REPE/REPZ */
c->rep_prefix = REPE_PREFIX;
break;
default:
goto done_prefixes;
}
/* Any legacy prefix after a REX prefix nullifies its effect. */
c->rex_prefix = 0;
}
done_prefixes:
/* REX prefix. */
if (c->rex_prefix)
if (c->rex_prefix & 8)
c->op_bytes = 8; /* REX.W */
/* Opcode byte(s). */
c->d = opcode_table[c->b];
if (c->d == 0) {
/* Two-byte opcode? */
if (c->b == 0x0f) {
c->twobyte = 1;
c->b = insn_fetch(u8, 1, c->eip);
c->d = twobyte_table[c->b];
}
}
if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) {
kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction");;
return -1;
}
if (c->d & Group) {
group = c->d & GroupMask;
c->modrm = insn_fetch(u8, 1, c->eip);
--c->eip;
group = (group << 3) + ((c->modrm >> 3) & 7);
if ((c->d & GroupDual) && (c->modrm >> 6) == 3)
c->d = group2_table[group];
else
c->d = group_table[group];
}
/* Unrecognised? */
if (c->d == 0) {
DPRINTF("Cannot emulate %02x\n", c->b);
return -1;
}
if (mode == X86EMUL_MODE_PROT64 && (c->d & Stack))
c->op_bytes = 8;
/* ModRM and SIB bytes. */
if (c->d & ModRM)
rc = decode_modrm(ctxt, ops);
else if (c->d & MemAbs)
rc = decode_abs(ctxt, ops);
if (rc)
goto done;
if (!c->has_seg_override)
set_seg_override(c, VCPU_SREG_DS);
if (!(!c->twobyte && c->b == 0x8d))
c->modrm_ea += seg_override_base(ctxt, c);
if (c->ad_bytes != 8)
c->modrm_ea = (u32)c->modrm_ea;
/*
* Decode and fetch the source operand: register, memory
* or immediate.
*/
switch (c->d & SrcMask) {
case SrcNone:
break;
case SrcReg:
decode_register_operand(&c->src, c, 0);
break;
case SrcMem16:
c->src.bytes = 2;
goto srcmem_common;
case SrcMem32:
c->src.bytes = 4;
goto srcmem_common;
case SrcMem:
c->src.bytes = (c->d & ByteOp) ? 1 :
c->op_bytes;
/* Don't fetch the address for invlpg: it could be unmapped. */
if (c->twobyte && c->b == 0x01 && c->modrm_reg == 7)
break;
srcmem_common:
/*
* For instructions with a ModR/M byte, switch to register
* access if Mod = 3.
*/
if ((c->d & ModRM) && c->modrm_mod == 3) {
c->src.type = OP_REG;
c->src.val = c->modrm_val;
c->src.ptr = c->modrm_ptr;
break;
}
c->src.type = OP_MEM;
break;
case SrcImm:
case SrcImmU:
c->src.type = OP_IMM;
c->src.ptr = (unsigned long *)c->eip;
c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
if (c->src.bytes == 8)
c->src.bytes = 4;
/* NB. Immediates are sign-extended as necessary. */
switch (c->src.bytes) {
case 1:
c->src.val = insn_fetch(s8, 1, c->eip);
break;
case 2:
c->src.val = insn_fetch(s16, 2, c->eip);
break;
case 4:
c->src.val = insn_fetch(s32, 4, c->eip);
break;
}
if ((c->d & SrcMask) == SrcImmU) {
switch (c->src.bytes) {
case 1:
c->src.val &= 0xff;
break;
case 2:
c->src.val &= 0xffff;
break;
case 4:
c->src.val &= 0xffffffff;
break;
}
}
break;
case SrcImmByte:
case SrcImmUByte:
c->src.type = OP_IMM;
c->src.ptr = (unsigned long *)c->eip;
c->src.bytes = 1;
if ((c->d & SrcMask) == SrcImmByte)
c->src.val = insn_fetch(s8, 1, c->eip);
else
c->src.val = insn_fetch(u8, 1, c->eip);
break;
case SrcOne:
c->src.bytes = 1;
c->src.val = 1;
break;
}
/*
* Decode and fetch the second source operand: register, memory
* or immediate.
*/
switch (c->d & Src2Mask) {
case Src2None:
break;
case Src2CL:
c->src2.bytes = 1;
c->src2.val = c->regs[VCPU_REGS_RCX] & 0x8;
break;
case Src2ImmByte:
c->src2.type = OP_IMM;
c->src2.ptr = (unsigned long *)c->eip;
c->src2.bytes = 1;
c->src2.val = insn_fetch(u8, 1, c->eip);
break;
case Src2Imm16:
c->src2.type = OP_IMM;
c->src2.ptr = (unsigned long *)c->eip;
c->src2.bytes = 2;
c->src2.val = insn_fetch(u16, 2, c->eip);
break;
case Src2One:
c->src2.bytes = 1;
c->src2.val = 1;
break;
}
/* Decode and fetch the destination operand: register or memory. */
switch (c->d & DstMask) {
case ImplicitOps:
/* Special instructions do their own operand decoding. */
return 0;
case DstReg:
decode_register_operand(&c->dst, c,
c->twobyte && (c->b == 0xb6 || c->b == 0xb7));
break;
case DstMem:
if ((c->d & ModRM) && c->modrm_mod == 3) {
c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
c->dst.type = OP_REG;
c->dst.val = c->dst.orig_val = c->modrm_val;
c->dst.ptr = c->modrm_ptr;
break;
}
c->dst.type = OP_MEM;
break;
case DstAcc:
c->dst.type = OP_REG;
c->dst.bytes = c->op_bytes;
c->dst.ptr = &c->regs[VCPU_REGS_RAX];
switch (c->op_bytes) {
case 1:
c->dst.val = *(u8 *)c->dst.ptr;
break;
case 2:
c->dst.val = *(u16 *)c->dst.ptr;
break;
case 4:
c->dst.val = *(u32 *)c->dst.ptr;
break;
}
c->dst.orig_val = c->dst.val;
break;
}
if (c->rip_relative)
c->modrm_ea += c->eip;
done:
return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'KVM: x86 emulator: limit instructions to 15 bytes
While we are never normally passed an instruction that exceeds 15 bytes,
smp games can cause us to attempt to interpret one, which will cause
large latencies in non-preempt hosts.
Cc: [email protected]
Signed-off-by: Avi Kivity <[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: add_connection_real (NMAGConfSettings *self, NMAGConfConnection *connection)
{
NMAGConfSettingsPrivate *priv = NMA_GCONF_SETTINGS_GET_PRIVATE (self);
g_return_if_fail (connection != NULL);
priv->connections = g_slist_prepend (priv->connections, connection);
g_signal_connect (connection, "new-secrets-requested",
G_CALLBACK (connection_new_secrets_requested_cb),
self);
g_signal_connect (connection, "removed", G_CALLBACK (connection_removed), self);
/* Export the connection over dbus if requested */
if (priv->bus) {
nm_exported_connection_register_object (NM_EXPORTED_CONNECTION (connection),
NM_CONNECTION_SCOPE_USER,
priv->bus);
dbus_g_connection_unref (priv->bus);
}
nm_settings_signal_new_connection (NM_SETTINGS (self), NM_EXPORTED_CONNECTION (connection));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'applet: fix dbus connection refcounting after 8627880e07c8345f69ed639325280c7f62a8f894'</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: get_settings (NMExportedConnection *exported)
{
NMConnection *connection;
GHashTable *settings;
connection = nm_exported_connection_get_connection (exported);
utils_fill_connection_certs (connection);
settings = nm_connection_to_hash (connection);
utils_clear_filled_connection_certs (connection);
return settings;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-310'], 'message': 'core: fix CA cert mishandling after cert file deletion (deb #560067) (rh #546793)
If a connection was created with a CA certificate, but the user later
moved or deleted that CA certificate, the applet would simply provide the
connection to NetworkManager without any CA certificate. This could cause
NM to connect to the original network (or a network spoofing the original
network) without verifying the identity of the network as the user
expects.
In the future we can/should do better here by (1) alerting the user that
some connection is now no longer complete by flagging it in the connection
editor or notifying the user somehow, and (2) by using a freaking' cert
store already (not that Linux has one yet).'</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: hb_ot_layout_build_glyph_classes (hb_face_t *face,
uint16_t num_total_glyphs,
hb_codepoint_t *glyphs,
unsigned char *klasses,
uint16_t count)
{
if (HB_OBJECT_IS_INERT (face))
return;
hb_ot_layout_t *layout = &face->ot_layout;
if (HB_UNLIKELY (!count || !glyphs || !klasses))
return;
if (layout->new_gdef.len == 0) {
layout->new_gdef.klasses = (unsigned char *) calloc (num_total_glyphs, sizeof (unsigned char));
layout->new_gdef.len = count;
}
for (unsigned int i = 0; i < count; i++)
_hb_ot_layout_set_glyph_class (face, glyphs[i], (hb_ot_layout_glyph_class_t) klasses[i]);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': '[HB/GDEF] Fix bug in building synthetic GDEF table'</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: _gnutls_x509_oid2mac_algorithm (const char *oid)
{
gnutls_mac_algorithm_t ret = 0;
GNUTLS_HASH_LOOP (if (strcmp (oid, p->oid) == 0)
{
ret = p->id; break;}
);
if (ret == 0)
return GNUTLS_MAC_UNKNOWN;
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-310'], 'message': '(_gnutls_x509_oid2mac_algorithm): Don't crash trying to strcmp the
NULL OID value in the hash_algorithms array, which happens when the
input OID doesn't match our OIDs for SHA1, MD5, MD2 or RIPEMD160.
Reported by satyakumar <[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 Server::getUserID(const QString &name) {
if (qhUserIDCache.contains(name))
return qhUserIDCache.value(name);
int id = -2;
emit nameToIdSig(id, name);
if (id != -2) {
qhUserIDCache.insert(name, id);
qhUserNameCache.insert(id, name);
return id;
}
TransactionHolder th;
QSqlQuery &query = *th.qsqQuery;
SQLPREP("SELECT `user_id` FROM `%1users` WHERE `server_id` = ? AND `name` like ?");
query.addBindValue(iServerNum);
query.addBindValue(name);
SQLEXEC();
if (query.next()) {
id = query.value(0).toInt();
qhUserIDCache.insert(name, id);
qhUserNameCache.insert(id, name);
}
return id;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Don't crash on long usernames'</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 keyctl_session_to_parent(void)
{
#ifdef TIF_NOTIFY_RESUME
struct task_struct *me, *parent;
const struct cred *mycred, *pcred;
struct cred *cred, *oldcred;
key_ref_t keyring_r;
int ret;
keyring_r = lookup_user_key(KEY_SPEC_SESSION_KEYRING, 0, KEY_LINK);
if (IS_ERR(keyring_r))
return PTR_ERR(keyring_r);
/* our parent is going to need a new cred struct, a new tgcred struct
* and new security data, so we allocate them here to prevent ENOMEM in
* our parent */
ret = -ENOMEM;
cred = cred_alloc_blank();
if (!cred)
goto error_keyring;
cred->tgcred->session_keyring = key_ref_to_ptr(keyring_r);
keyring_r = NULL;
me = current;
rcu_read_lock();
write_lock_irq(&tasklist_lock);
parent = me->real_parent;
ret = -EPERM;
/* the parent mustn't be init and mustn't be a kernel thread */
if (parent->pid <= 1 || !parent->mm)
goto not_permitted;
/* the parent must be single threaded */
if (!thread_group_empty(parent))
goto not_permitted;
/* the parent and the child must have different session keyrings or
* there's no point */
mycred = current_cred();
pcred = __task_cred(parent);
if (mycred == pcred ||
mycred->tgcred->session_keyring == pcred->tgcred->session_keyring)
goto already_same;
/* the parent must have the same effective ownership and mustn't be
* SUID/SGID */
if (pcred->uid != mycred->euid ||
pcred->euid != mycred->euid ||
pcred->suid != mycred->euid ||
pcred->gid != mycred->egid ||
pcred->egid != mycred->egid ||
pcred->sgid != mycred->egid)
goto not_permitted;
/* the keyrings must have the same UID */
if (pcred->tgcred->session_keyring->uid != mycred->euid ||
mycred->tgcred->session_keyring->uid != mycred->euid)
goto not_permitted;
/* if there's an already pending keyring replacement, then we replace
* that */
oldcred = parent->replacement_session_keyring;
/* the replacement session keyring is applied just prior to userspace
* restarting */
parent->replacement_session_keyring = cred;
cred = NULL;
set_ti_thread_flag(task_thread_info(parent), TIF_NOTIFY_RESUME);
write_unlock_irq(&tasklist_lock);
rcu_read_unlock();
if (oldcred)
put_cred(oldcred);
return 0;
already_same:
ret = 0;
not_permitted:
write_unlock_irq(&tasklist_lock);
rcu_read_unlock();
put_cred(cred);
return ret;
error_keyring:
key_ref_put(keyring_r);
return ret;
#else /* !TIF_NOTIFY_RESUME */
/*
* To be removed when TIF_NOTIFY_RESUME has been implemented on
* m68k/xtensa
*/
#warning TIF_NOTIFY_RESUME not implemented
return -EOPNOTSUPP;
#endif /* !TIF_NOTIFY_RESUME */
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'KEYS: Fix bug in keyctl_session_to_parent() if parent has no session keyring
Fix a bug in keyctl_session_to_parent() whereby it tries to check the ownership
of the parent process's session keyring whether or not the parent has a session
keyring [CVE-2010-2960].
This results in the following oops:
BUG: unable to handle kernel NULL pointer dereference at 00000000000000a0
IP: [<ffffffff811ae4dd>] keyctl_session_to_parent+0x251/0x443
...
Call Trace:
[<ffffffff811ae2f3>] ? keyctl_session_to_parent+0x67/0x443
[<ffffffff8109d286>] ? __do_fault+0x24b/0x3d0
[<ffffffff811af98c>] sys_keyctl+0xb4/0xb8
[<ffffffff81001eab>] system_call_fastpath+0x16/0x1b
if the parent process has no session keyring.
If the system is using pam_keyinit then it mostly protected against this as all
processes derived from a login will have inherited the session keyring created
by pam_keyinit during the log in procedure.
To test this, pam_keyinit calls need to be commented out in /etc/pam.d/.
Reported-by: Tavis Ormandy <[email protected]>
Signed-off-by: David Howells <[email protected]>
Acked-by: Tavis Ormandy <[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: static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
{
u32 host_sysenter_cs, msr_low, msr_high;
u32 junk;
u64 host_pat, tsc_this, tsc_base;
unsigned long a;
struct desc_ptr dt;
int i;
unsigned long kvm_vmx_return;
u32 exec_control;
/* I/O */
vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a));
vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b));
if (cpu_has_vmx_msr_bitmap())
vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
/* Control */
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL,
vmcs_config.pin_based_exec_ctrl);
exec_control = vmcs_config.cpu_based_exec_ctrl;
if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) {
exec_control &= ~CPU_BASED_TPR_SHADOW;
#ifdef CONFIG_X86_64
exec_control |= CPU_BASED_CR8_STORE_EXITING |
CPU_BASED_CR8_LOAD_EXITING;
#endif
}
if (!enable_ept)
exec_control |= CPU_BASED_CR3_STORE_EXITING |
CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_INVLPG_EXITING;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
if (cpu_has_secondary_exec_ctrls()) {
exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
exec_control &=
~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
if (vmx->vpid == 0)
exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
if (!enable_ept) {
exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
enable_unrestricted_guest = 0;
}
if (!enable_unrestricted_guest)
exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
if (!ple_gap)
exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
if (ple_gap) {
vmcs_write32(PLE_GAP, ple_gap);
vmcs_write32(PLE_WINDOW, ple_window);
}
vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf);
vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */
vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 22.2.3 */
vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */
vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */
vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */
vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */
vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */
vmcs_write16(HOST_FS_SELECTOR, kvm_read_fs()); /* 22.2.4 */
vmcs_write16(HOST_GS_SELECTOR, kvm_read_gs()); /* 22.2.4 */
vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */
#ifdef CONFIG_X86_64
rdmsrl(MSR_FS_BASE, a);
vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */
rdmsrl(MSR_GS_BASE, a);
vmcs_writel(HOST_GS_BASE, a); /* 22.2.4 */
#else
vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */
vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */
#endif
vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */
native_store_idt(&dt);
vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk);
vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs);
rdmsrl(MSR_IA32_SYSENTER_ESP, a);
vmcs_writel(HOST_IA32_SYSENTER_ESP, a); /* 22.2.3 */
rdmsrl(MSR_IA32_SYSENTER_EIP, a);
vmcs_writel(HOST_IA32_SYSENTER_EIP, a); /* 22.2.3 */
if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
host_pat = msr_low | ((u64) msr_high << 32);
vmcs_write64(HOST_IA32_PAT, host_pat);
}
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
host_pat = msr_low | ((u64) msr_high << 32);
/* Write the default value follow host pat */
vmcs_write64(GUEST_IA32_PAT, host_pat);
/* Keep arch.pat sync with GUEST_IA32_PAT */
vmx->vcpu.arch.pat = host_pat;
}
for (i = 0; i < NR_VMX_MSR; ++i) {
u32 index = vmx_msr_index[i];
u32 data_low, data_high;
int j = vmx->nmsrs;
if (rdmsr_safe(index, &data_low, &data_high) < 0)
continue;
if (wrmsr_safe(index, data_low, data_high) < 0)
continue;
vmx->guest_msrs[j].index = i;
vmx->guest_msrs[j].data = 0;
vmx->guest_msrs[j].mask = -1ull;
++vmx->nmsrs;
}
vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
/* 22.2.1, 20.8.1 */
vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl);
vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
if (enable_ept)
vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc;
rdtscll(tsc_this);
if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc)
tsc_base = tsc_this;
guest_write_tsc(0, tsc_base);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-400'], 'message': 'KVM: Fix fs/gs reload oops with invalid ldt
kvm reloads the host's fs and gs blindly, however the underlying segment
descriptors may be invalid due to the user modifying the ldt after loading
them.
Fix by using the safe accessors (loadsegment() and load_gs_index()) instead
of home grown unsafe versions.
This is CVE-2010-3698.
KVM-Stable-Tag.
Signed-off-by: Avi Kivity <[email protected]>
Signed-off-by: Marcelo Tosatti <[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: */
xmlNodePtr
xmlXPathNextFollowing(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) {
if ((ctxt == NULL) || (ctxt->context == NULL)) return(NULL);
if ((ctxt->context->node->type == XML_ATTRIBUTE_NODE) ||
(ctxt->context->node->type == XML_NAMESPACE_DECL))
return(NULL);
if (cur != NULL) {
if ((cur->type == XML_ATTRIBUTE_NODE) ||
(cur->type == XML_NAMESPACE_DECL))
return(NULL);
if (cur->children != NULL)
return cur->children ;
}
if (cur == NULL) cur = ctxt->context->node;
if (cur == NULL) return(NULL) ; /* ERROR */
if (cur->next != NULL) return(cur->next) ;
do {
cur = cur->parent;
if (cur == NULL) break;
if (cur == (xmlNodePtr) ctxt->context->doc) return(NULL);
if (cur->next != NULL) return(cur->next);
} while (cur != NULL); ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix a change of semantic on XPath preceding and following axis
This was introduced in the prevous fix, while preceding-sibling and
following sibling axis are empty for attributes and namespaces,
preceding and following axis should still work based on the parent
element. However the parent element is not available for a namespace
node, so we keep the axis empty in that 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: int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
{
int rc = NET_RX_SUCCESS;
if (sk_filter(sk, skb))
goto discard_and_relse;
skb->dev = NULL;
if (nested)
bh_lock_sock_nested(sk);
else
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
/*
* trylock + unlock semantics:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);
rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
} else if (sk_add_backlog(sk, skb)) {
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
bh_unlock_sock(sk);
out:
sock_put(sk);
return rc;
discard_and_relse:
kfree_skb(skb);
goto out;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-400'], 'message': 'net: sk_add_backlog() take rmem_alloc into account
Current socket backlog limit is not enough to really stop DDOS attacks,
because user thread spend many time to process a full backlog each
round, and user might crazy spin on socket lock.
We should add backlog size and receive_queue size (aka rmem_alloc) to
pace writers, and let user run without being slow down too much.
Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in
stress situations.
Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp
receiver can now process ~200.000 pps (instead of ~100 pps before the
patch) on a 8 core machine.
Signed-off-by: Eric Dumazet <[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: readconf_main(void)
{
int sep = 0;
struct stat statbuf;
uschar *s, *filename;
uschar *list = config_main_filelist;
/* Loop through the possible file names */
while((filename = string_nextinlist(&list, &sep, big_buffer, big_buffer_size))
!= NULL)
{
/* Cut out all the fancy processing unless specifically wanted */
#if defined(CONFIGURE_FILE_USE_NODE) || defined(CONFIGURE_FILE_USE_EUID)
uschar *suffix = filename + Ustrlen(filename);
/* Try for the node-specific file if a node name exists */
#ifdef CONFIGURE_FILE_USE_NODE
struct utsname uts;
if (uname(&uts) >= 0)
{
#ifdef CONFIGURE_FILE_USE_EUID
sprintf(CS suffix, ".%ld.%.256s", (long int)original_euid, uts.nodename);
config_file = Ufopen(filename, "rb");
if (config_file == NULL)
#endif /* CONFIGURE_FILE_USE_EUID */
{
sprintf(CS suffix, ".%.256s", uts.nodename);
config_file = Ufopen(filename, "rb");
}
}
#endif /* CONFIGURE_FILE_USE_NODE */
/* Otherwise, try the generic name, possibly with the euid added */
#ifdef CONFIGURE_FILE_USE_EUID
if (config_file == NULL)
{
sprintf(CS suffix, ".%ld", (long int)original_euid);
config_file = Ufopen(filename, "rb");
}
#endif /* CONFIGURE_FILE_USE_EUID */
/* Finally, try the unadorned name */
if (config_file == NULL)
{
*suffix = 0;
config_file = Ufopen(filename, "rb");
}
#else /* if neither defined */
/* This is the common case when the fancy processing is not included. */
config_file = Ufopen(filename, "rb");
#endif
/* If the file does not exist, continue to try any others. For any other
error, break out (and die). */
if (config_file != NULL || errno != ENOENT) break;
}
/* On success, save the name for verification; config_filename is used when
logging configuration errors (it changes for .included files) whereas
config_main_filename is the name shown by -bP. Failure to open a configuration
file is a serious disaster. */
if (config_file != NULL)
{
config_filename = config_main_filename = string_copy(filename);
}
else
{
if (filename == NULL)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "non-existent configuration file(s): "
"%s", config_main_filelist);
else
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "%s", string_open_failed(errno,
"configuration file %s", filename));
}
/* Check the status of the file we have opened, unless it was specified on
the command line, in which case privilege was given away at the start. */
if (!config_changed)
{
if (fstat(fileno(config_file), &statbuf) != 0)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "failed to stat configuration file %s",
big_buffer);
if ((statbuf.st_uid != root_uid && /* owner not root */
statbuf.st_uid != exim_uid /* owner not exim */
#ifdef CONFIGURE_OWNER
&& statbuf.st_uid != config_uid /* owner not the special one */
#endif
) || /* or */
(statbuf.st_gid != exim_gid /* group not exim & */
#ifdef CONFIGURE_GROUP
&& statbuf.st_gid != config_gid /* group not the special one */
#endif
&& (statbuf.st_mode & 020) != 0) || /* group writeable */
/* or */
((statbuf.st_mode & 2) != 0)) /* world writeable */
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "Exim configuration file %s has the "
"wrong owner, group, or mode", big_buffer);
}
/* Process the main configuration settings. They all begin with a lower case
letter. If we see something starting with an upper case letter, it is taken as
a macro definition. */
while ((s = get_config_line()) != NULL)
{
if (isupper(s[0])) read_macro_assignment(s);
else if (Ustrncmp(s, "domainlist", 10) == 0)
read_named_list(&domainlist_anchor, &domainlist_count,
MAX_NAMED_LIST, s+10, US"domain list");
else if (Ustrncmp(s, "hostlist", 8) == 0)
read_named_list(&hostlist_anchor, &hostlist_count,
MAX_NAMED_LIST, s+8, US"host list");
else if (Ustrncmp(s, US"addresslist", 11) == 0)
read_named_list(&addresslist_anchor, &addresslist_count,
MAX_NAMED_LIST, s+11, US"address list");
else if (Ustrncmp(s, US"localpartlist", 13) == 0)
read_named_list(&localpartlist_anchor, &localpartlist_count,
MAX_NAMED_LIST, s+13, US"local part list");
else
(void) readconf_handle_option(s, optionlist_config, optionlist_config_size,
NULL, US"main option \"%s\" unknown");
}
/* If local_sender_retain is set, local_from_check must be unset. */
if (local_sender_retain && local_from_check)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "both local_from_check and "
"local_sender_retain are set; this combination is not allowed");
/* If the timezone string is empty, set it to NULL, implying no TZ variable
wanted. */
if (timezone_string != NULL && *timezone_string == 0) timezone_string = NULL;
/* The max retry interval must not be greater than 24 hours. */
if (retry_interval_max > 24*60*60) retry_interval_max = 24*60*60;
/* remote_max_parallel must be > 0 */
if (remote_max_parallel <= 0) remote_max_parallel = 1;
/* Save the configured setting of freeze_tell, so we can re-instate it at the
start of a new SMTP message. */
freeze_tell_config = freeze_tell;
/* The primary host name may be required for expansion of spool_directory
and log_file_path, so make sure it is set asap. It is obtained from uname(),
but if that yields an unqualified value, make a FQDN by using gethostbyname to
canonize it. Some people like upper case letters in their host names, so we
don't force the case. */
if (primary_hostname == NULL)
{
uschar *hostname;
struct utsname uts;
if (uname(&uts) < 0)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "uname() failed to yield host name");
hostname = US uts.nodename;
if (Ustrchr(hostname, '.') == NULL)
{
int af = AF_INET;
struct hostent *hostdata;
#if HAVE_IPV6
if (!disable_ipv6 && (dns_ipv4_lookup == NULL ||
match_isinlist(hostname, &dns_ipv4_lookup, 0, NULL, NULL, MCL_DOMAIN,
TRUE, NULL) != OK))
af = AF_INET6;
#else
af = AF_INET;
#endif
for (;;)
{
#if HAVE_IPV6
#if HAVE_GETIPNODEBYNAME
int error_num;
hostdata = getipnodebyname(CS hostname, af, 0, &error_num);
#else
hostdata = gethostbyname2(CS hostname, af);
#endif
#else
hostdata = gethostbyname(CS hostname);
#endif
if (hostdata != NULL)
{
hostname = US hostdata->h_name;
break;
}
if (af == AF_INET) break;
af = AF_INET;
}
}
primary_hostname = string_copy(hostname);
}
/* Set up default value for smtp_active_hostname */
smtp_active_hostname = primary_hostname;
/* If spool_directory wasn't set in the build-time configuration, it must have
got set above. Of course, writing to the log may not work if log_file_path is
not set, but it will at least get to syslog or somewhere, with any luck. */
if (*spool_directory == 0)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "spool_directory undefined: cannot "
"proceed");
/* Expand the spool directory name; it may, for example, contain the primary
host name. Same comment about failure. */
s = expand_string(spool_directory);
if (s == NULL)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "failed to expand spool_directory "
"\"%s\": %s", spool_directory, expand_string_message);
spool_directory = s;
/* Expand log_file_path, which must contain "%s" in any component that isn't
the null string or "syslog". It is also allowed to contain one instance of %D.
However, it must NOT contain % followed by anything else. */
if (*log_file_path != 0)
{
uschar *ss, *sss;
int sep = ':'; /* Fixed for log file path */
s = expand_string(log_file_path);
if (s == NULL)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "failed to expand log_file_path "
"\"%s\": %s", log_file_path, expand_string_message);
ss = s;
while ((sss = string_nextinlist(&ss,&sep,big_buffer,big_buffer_size)) != NULL)
{
uschar *t;
if (sss[0] == 0 || Ustrcmp(sss, "syslog") == 0) continue;
t = Ustrstr(sss, "%s");
if (t == NULL)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "log_file_path \"%s\" does not "
"contain \"%%s\"", sss);
*t = 'X';
t = Ustrchr(sss, '%');
if (t != NULL)
{
if (t[1] != 'D' || Ustrchr(t+2, '%') != NULL)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "log_file_path \"%s\" contains "
"unexpected \"%%\" character", s);
}
}
log_file_path = s;
}
/* Interpret syslog_facility into an integer argument for 'ident' param to
openlog(). Default is LOG_MAIL set in globals.c. Allow the user to omit the
leading "log_". */
if (syslog_facility_str != NULL)
{
int i;
uschar *s = syslog_facility_str;
if ((Ustrlen(syslog_facility_str) >= 4) &&
(strncmpic(syslog_facility_str, US"log_", 4) == 0))
s += 4;
for (i = 0; i < syslog_list_size; i++)
{
if (strcmpic(s, syslog_list[i].name) == 0)
{
syslog_facility = syslog_list[i].value;
break;
}
}
if (i >= syslog_list_size)
{
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"failed to interpret syslog_facility \"%s\"", syslog_facility_str);
}
}
/* Expand pid_file_path */
if (*pid_file_path != 0)
{
s = expand_string(pid_file_path);
if (s == NULL)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "failed to expand pid_file_path "
"\"%s\": %s", pid_file_path, expand_string_message);
pid_file_path = s;
}
/* Compile the regex for matching a UUCP-style "From_" line in an incoming
message. */
regex_From = regex_must_compile(uucp_from_pattern, FALSE, TRUE);
/* Unpick the SMTP rate limiting options, if set */
if (smtp_ratelimit_mail != NULL)
{
unpick_ratelimit(smtp_ratelimit_mail, &smtp_rlm_threshold,
&smtp_rlm_base, &smtp_rlm_factor, &smtp_rlm_limit);
}
if (smtp_ratelimit_rcpt != NULL)
{
unpick_ratelimit(smtp_ratelimit_rcpt, &smtp_rlr_threshold,
&smtp_rlr_base, &smtp_rlr_factor, &smtp_rlr_limit);
}
/* The qualify domains default to the primary host name */
if (qualify_domain_sender == NULL)
qualify_domain_sender = primary_hostname;
if (qualify_domain_recipient == NULL)
qualify_domain_recipient = qualify_domain_sender;
/* Setting system_filter_user in the configuration sets the gid as well if a
name is given, but a numerical value does not. */
if (system_filter_uid_set && !system_filter_gid_set)
{
struct passwd *pw = getpwuid(system_filter_uid);
if (pw == NULL)
log_write(0, LOG_MAIN|LOG_PANIC_DIE, "Failed to look up uid %ld",
(long int)system_filter_uid);
system_filter_gid = pw->pw_gid;
system_filter_gid_set = TRUE;
}
/* If the errors_reply_to field is set, check that it is syntactically valid
and ensure it contains a domain. */
if (errors_reply_to != NULL)
{
uschar *errmess;
int start, end, domain;
uschar *recipient = parse_extract_address(errors_reply_to, &errmess,
&start, &end, &domain, FALSE);
if (recipient == NULL)
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"error in errors_reply_to (%s): %s", errors_reply_to, errmess);
if (domain == 0)
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"errors_reply_to (%s) does not contain a domain", errors_reply_to);
}
/* If smtp_accept_queue or smtp_accept_max_per_host is set, then
smtp_accept_max must also be set. */
if (smtp_accept_max == 0 &&
(smtp_accept_queue > 0 || smtp_accept_max_per_host != NULL))
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"smtp_accept_max must be set if smtp_accept_queue or "
"smtp_accept_max_per_host is set");
/* Set up the host number if anything is specified. It is an expanded string
so that it can be computed from the host name, for example. We do this last
so as to ensure that everything else is set up before the expansion. */
if (host_number_string != NULL)
{
uschar *end;
uschar *s = expand_string(host_number_string);
long int n = Ustrtol(s, &end, 0);
while (isspace(*end)) end++;
if (*end != 0)
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"localhost_number value is not a number: %s", s);
if (n > LOCALHOST_MAX)
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"localhost_number is greater than the maximum allowed value (%d)",
LOCALHOST_MAX);
host_number = n;
}
#ifdef SUPPORT_TLS
/* If tls_verify_hosts is set, tls_verify_certificates must also be set */
if ((tls_verify_hosts != NULL || tls_try_verify_hosts != NULL) &&
tls_verify_certificates == NULL)
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"tls_%sverify_hosts is set, but tls_verify_certificates is not set",
(tls_verify_hosts != NULL)? "" : "try_");
/* If openssl_options is set, validate it */
if (openssl_options != NULL)
{
# ifdef USE_GNUTLS
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"openssl_options is set but we're using GnuTLS");
# else
long dummy;
if (!(tls_openssl_options_parse(openssl_options, &dummy)))
log_write(0, LOG_PANIC_DIE|LOG_CONFIG,
"openssl_options parse error: %s", openssl_options);
# endif
}
#endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'Don't allow a configure file which is writeable by the Exim user or group
(Bug 1044, CVE-2010-4345)'</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 mainloop(CLIENT *client) {
struct nbd_request request;
struct nbd_reply reply;
gboolean go_on=TRUE;
#ifdef DODBG
int i = 0;
#endif
negotiate(client);
DEBUG("Entering request loop!\n");
reply.magic = htonl(NBD_REPLY_MAGIC);
reply.error = 0;
while (go_on) {
char buf[BUFSIZE];
size_t len;
#ifdef DODBG
i++;
printf("%d: ", i);
#endif
if (client->server->timeout)
alarm(client->server->timeout);
readit(client->net, &request, sizeof(request));
request.from = ntohll(request.from);
request.type = ntohl(request.type);
if (request.type==NBD_CMD_DISC) {
msg2(LOG_INFO, "Disconnect request received.");
if (client->difmap) g_free(client->difmap) ;
if (client->difffile>=0) {
close(client->difffile);
unlink(client->difffilename);
free(client->difffilename);
}
go_on=FALSE;
continue;
}
len = ntohl(request.len);
if (request.magic != htonl(NBD_REQUEST_MAGIC))
err("Not enough magic.");
if (len > BUFSIZE)
err("Request too big!");
#ifdef DODBG
printf("%s from %Lu (%Lu) len %d, ", request.type ? "WRITE" :
"READ", (unsigned long long)request.from,
(unsigned long long)request.from / 512, len);
#endif
memcpy(reply.handle, request.handle, sizeof(reply.handle));
if ((request.from + len) > (OFFT_MAX)) {
DEBUG("[Number too large!]");
ERROR(client, reply);
continue;
}
if (((ssize_t)((off_t)request.from + len) > client->exportsize) ||
((client->server->flags & F_READONLY) && request.type)) {
DEBUG("[RANGE!]");
ERROR(client, reply);
continue;
}
if (request.type==NBD_CMD_WRITE) {
DEBUG("wr: net->buf, ");
readit(client->net, buf, len);
DEBUG("buf->exp, ");
if ((client->server->flags & F_AUTOREADONLY) ||
expwrite(request.from, buf, len,
client)) {
DEBUG("Write failed: %m" );
ERROR(client, reply);
continue;
}
SEND(client->net, reply);
DEBUG("OK!\n");
continue;
}
/* READ */
DEBUG("exp->buf, ");
if (expread(request.from, buf + sizeof(struct nbd_reply), len, client)) {
DEBUG("Read failed: %m");
ERROR(client, reply);
continue;
}
DEBUG("buf->net, ");
memcpy(buf, &reply, sizeof(struct nbd_reply));
writeit(client->net, buf, len + sizeof(struct nbd_reply));
DEBUG("OK!\n");
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'r134: CVE-2005-3534'</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: xsltGenerateIdFunction(xmlXPathParserContextPtr ctxt, int nargs){
xmlNodePtr cur = NULL;
unsigned long val;
xmlChar str[20];
if (nargs == 0) {
cur = ctxt->context->node;
} else if (nargs == 1) {
xmlXPathObjectPtr obj;
xmlNodeSetPtr nodelist;
int i, ret;
if ((ctxt->value == NULL) || (ctxt->value->type != XPATH_NODESET)) {
ctxt->error = XPATH_INVALID_TYPE;
xsltTransformError(xsltXPathGetTransformContext(ctxt), NULL, NULL,
"generate-id() : invalid arg expecting a node-set\n");
return;
}
obj = valuePop(ctxt);
nodelist = obj->nodesetval;
if ((nodelist == NULL) || (nodelist->nodeNr <= 0)) {
xmlXPathFreeObject(obj);
valuePush(ctxt, xmlXPathNewCString(""));
return;
}
cur = nodelist->nodeTab[0];
for (i = 1;i < nodelist->nodeNr;i++) {
ret = xmlXPathCmpNodes(cur, nodelist->nodeTab[i]);
if (ret == -1)
cur = nodelist->nodeTab[i];
}
xmlXPathFreeObject(obj);
} else {
xsltTransformError(xsltXPathGetTransformContext(ctxt), NULL, NULL,
"generate-id() : invalid number of args %d\n", nargs);
ctxt->error = XPATH_INVALID_ARITY;
return;
}
/*
* Okay this is ugly but should work, use the NodePtr address
* to forge the ID
*/
val = (unsigned long)((char *)cur - (char *)0);
val /= sizeof(xmlNode);
sprintf((char *)str, "id%ld", val);
valuePush(ctxt, xmlXPathNewString(str));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'Fix generate-id() to not expose object addresses
As pointed out by Chris Evans <[email protected]> it's better
security wise to not expose object addresses directly, use a diff
w.r.t. the document root own address to avoid this
* libxslt/functions.c: fix IDs generation code'</s> |
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static ssize_t clusterip_proc_write(struct file *file, const char __user *input,
size_t size, loff_t *ofs)
{
struct clusterip_config *c = PDE(file->f_path.dentry->d_inode)->data;
#define PROC_WRITELEN 10
char buffer[PROC_WRITELEN+1];
unsigned long nodenum;
if (copy_from_user(buffer, input, PROC_WRITELEN))
return -EFAULT;
if (*buffer == '+') {
nodenum = simple_strtoul(buffer+1, NULL, 10);
if (clusterip_add_node(c, nodenum))
return -ENOMEM;
} else if (*buffer == '-') {
nodenum = simple_strtoul(buffer+1, NULL,10);
if (clusterip_del_node(c, nodenum))
return -ENOENT;
} else
return -EIO;
return size;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-120'], 'message': 'netfilter: ipt_CLUSTERIP: fix buffer overflow
'buffer' string is copied from userspace. It is not checked whether it is
zero terminated. This may lead to overflow inside of simple_strtoul().
Changli Gao suggested to copy not more than user supplied 'size' bytes.
It was introduced before the git epoch. Files "ipt_CLUSTERIP/*" are
root writable only by default, however, on some setups permissions might be
relaxed to e.g. network admin user.
Signed-off-by: Vasiliy Kulikov <[email protected]>
Acked-by: Changli Gao <[email protected]>
Signed-off-by: Patrick McHardy <[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: msg_t* MsgDup(msg_t* pOld)
{
msg_t* pNew;
rsRetVal localRet;
assert(pOld != NULL);
BEGINfunc
if(msgConstructWithTime(&pNew, &pOld->tTIMESTAMP, pOld->ttGenTime) != RS_RET_OK) {
return NULL;
}
/* now copy the message properties */
pNew->iRefCount = 1;
pNew->iSeverity = pOld->iSeverity;
pNew->iFacility = pOld->iFacility;
pNew->msgFlags = pOld->msgFlags;
pNew->iProtocolVersion = pOld->iProtocolVersion;
pNew->ttGenTime = pOld->ttGenTime;
pNew->offMSG = pOld->offMSG;
pNew->iLenRawMsg = pOld->iLenRawMsg;
pNew->iLenMSG = pOld->iLenMSG;
pNew->iLenTAG = pOld->iLenTAG;
pNew->iLenHOSTNAME = pOld->iLenHOSTNAME;
if((pOld->msgFlags & NEEDS_DNSRESOL) == 1) {
localRet = msgSetFromSockinfo(pNew, pOld->rcvFrom.pfrominet);
if(localRet != RS_RET_OK) {
/* if something fails, we accept loss of this property, it is
* better than losing the whole message.
*/
pNew->msgFlags &= ~NEEDS_DNSRESOL;
}
} else {
if(pOld->rcvFrom.pRcvFrom != NULL) {
pNew->rcvFrom.pRcvFrom = pOld->rcvFrom.pRcvFrom;
prop.AddRef(pNew->rcvFrom.pRcvFrom);
}
}
if(pOld->pRcvFromIP != NULL) {
pNew->pRcvFromIP = pOld->pRcvFromIP;
prop.AddRef(pNew->pRcvFromIP);
}
if(pOld->pInputName != NULL) {
pNew->pInputName = pOld->pInputName;
prop.AddRef(pNew->pInputName);
}
/* enable this, if someone actually uses UxTradMsg, delete after some time has
* passed and nobody complained -- rgerhards, 2009-06-16
pNew->offAfterPRI = pOld->offAfterPRI;
*/
if(pOld->iLenTAG > 0) {
if(pOld->iLenTAG < CONF_TAG_BUFSIZE) {
memcpy(pNew->TAG.szBuf, pOld->TAG.szBuf, pOld->iLenTAG);
} else {
if((pNew->TAG.pszTAG = srUtilStrDup(pOld->TAG.pszTAG, pOld->iLenTAG)) == NULL) {
msgDestruct(&pNew);
return NULL;
}
pNew->iLenTAG = pOld->iLenTAG;
}
}
if(pOld->iLenRawMsg < CONF_RAWMSG_BUFSIZE) {
memcpy(pNew->szRawMsg, pOld->szRawMsg, pOld->iLenRawMsg + 1);
pNew->pszRawMsg = pNew->szRawMsg;
} else {
tmpCOPYSZ(RawMsg);
}
if(pOld->iLenHOSTNAME < CONF_HOSTNAME_BUFSIZE) {
memcpy(pNew->szHOSTNAME, pOld->szHOSTNAME, pOld->iLenHOSTNAME + 1);
pNew->pszHOSTNAME = pNew->szHOSTNAME;
} else {
tmpCOPYSZ(HOSTNAME);
}
tmpCOPYCSTR(ProgName);
tmpCOPYCSTR(StrucData);
tmpCOPYCSTR(APPNAME);
tmpCOPYCSTR(PROCID);
tmpCOPYCSTR(MSGID);
/* we do not copy all other cache properties, as we do not even know
* if they are needed once again. So we let them re-create if needed.
*/
ENDfunc
return pNew;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-772'], 'message': 'backporting abort condition fix from 5.7.7'</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
mono_reflection_create_dynamic_method (MonoReflectionDynamicMethod *mb)
{ ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399', 'CWE-264'], 'message': 'Don't use finalization to cleanup dynamic methods.
* reflection.c: Use a reference queue to cleanup
dynamic methods instead of finalization.
* runtime.c: Shutdown the dynamic method queue
before runtime cleanup begins.
* DynamicMethod.cs: No longer finalizable.
* icall-def.h: Remove unused dynamic method icall.
Fixes #660422
Implement a reference queue API.
* gc.c: A reference queue allows one to queue
callbcks for when objects are collected.
It allows for safe cleanup of objects that can
only be done when it is effectively collected.
The major difference with regular finalization
is that the collector makes sure the object
was collected - and can't be resurrected.
* gc-internal.h: Export entrypoints for the
new API.'</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 virtio_blk_handle_read(VirtIOBlockReq *req)
{
BlockDriverAIOCB *acb;
uint64_t sector;
sector = ldq_p(&req->out->sector);
if (sector & req->dev->sector_mask) {
virtio_blk_rw_complete(req, -EIO);
return;
}
acb = bdrv_aio_readv(req->dev->bs, sector, &req->qiov,
req->qiov.size / BDRV_SECTOR_SIZE,
virtio_blk_rw_complete, req);
if (!acb) {
virtio_blk_rw_complete(req, -EIO);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'virtio-blk: fail unaligned requests
Like all block drivers virtio-blk should not allow small than block size
granularity access. But given that the protocol specifies a
byte unit length field we currently accept such requests, which cause
qemu to abort() in lower layers. Add checks to the main read and
write handlers to catch them early.
Reported-by: Conor Murphy <[email protected]>
Tested-by: Conor Murphy <[email protected]>
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Stefan Hajnoczi <[email protected]>
Signed-off-by: Kevin Wolf <[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: const char *string_of_NPPVariable(int variable)
{
const char *str;
switch (variable) {
#define _(VAL) case VAL: str = #VAL; break;
_(NPPVpluginNameString);
_(NPPVpluginDescriptionString);
_(NPPVpluginWindowBool);
_(NPPVpluginTransparentBool);
_(NPPVjavaClass);
_(NPPVpluginWindowSize);
_(NPPVpluginTimerInterval);
_(NPPVpluginScriptableInstance);
_(NPPVpluginScriptableIID);
_(NPPVjavascriptPushCallerBool);
_(NPPVpluginKeepLibraryInMemory);
_(NPPVpluginNeedsXEmbed);
_(NPPVpluginScriptableNPObject);
_(NPPVformValue);
#undef _
default:
switch (variable & 0xff) {
#define _(VAL, VAR) case VAL: str = #VAR; break
_(10, NPPVpluginScriptableInstance);
#undef _
default:
str = "<unknown variable>";
break;
}
break;
}
return str;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'Support all the new variables 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 NOINLINE void attach_option(
struct option_set **opt_list,
const struct dhcp_optflag *optflag,
char *buffer,
int length)
{
struct option_set *existing, *new, **curr;
char *allocated = NULL;
existing = udhcp_find_option(*opt_list, optflag->code);
if (!existing) {
log2("Attaching option %02x to list", optflag->code);
allocated = allocate_tempopt_if_needed(optflag, buffer, &length);
#if ENABLE_FEATURE_UDHCP_RFC3397
if ((optflag->flags & OPTION_TYPE_MASK) == OPTION_DNS_STRING) {
/* reuse buffer and length for RFC1035-formatted string */
allocated = buffer = (char *)dname_enc(NULL, 0, buffer, &length);
}
#endif
/* make a new option */
new = xmalloc(sizeof(*new));
new->data = xmalloc(length + OPT_DATA);
new->data[OPT_CODE] = optflag->code;
new->data[OPT_LEN] = length;
memcpy(new->data + OPT_DATA, (allocated ? allocated : buffer), length);
curr = opt_list;
while (*curr && (*curr)->data[OPT_CODE] < optflag->code)
curr = &(*curr)->next;
new->next = *curr;
*curr = new;
goto ret;
}
if (optflag->flags & OPTION_LIST) {
unsigned old_len;
/* add it to an existing option */
log2("Attaching option %02x to existing member of list", optflag->code);
allocated = allocate_tempopt_if_needed(optflag, buffer, &length);
old_len = existing->data[OPT_LEN];
#if ENABLE_FEATURE_UDHCP_RFC3397
if ((optflag->flags & OPTION_TYPE_MASK) == OPTION_DNS_STRING) {
/* reuse buffer and length for RFC1035-formatted string */
allocated = buffer = (char *)dname_enc(existing->data + OPT_DATA, old_len, buffer, &length);
}
#endif
if (old_len + length < 255) {
/* actually 255 is ok too, but adding a space can overlow it */
existing->data = xrealloc(existing->data, OPT_DATA + 1 + old_len + length);
if ((optflag->flags & OPTION_TYPE_MASK) == OPTION_STRING) {
/* add space separator between STRING options in a list */
existing->data[OPT_DATA + old_len] = ' ';
old_len++;
}
memcpy(existing->data + OPT_DATA + old_len, buffer, length);
existing->data[OPT_LEN] = old_len + length;
} /* else, ignore the data, we could put this in a second option in the future */
} /* else, ignore the new data */
ret:
free(allocated);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'udhcpc: sanitize hostnames in incoming packets. Closes 3979.
The following options are replaced with string "bad" if they
contain malformed hostname:
HOST_NAME, DOMAIN_NAME, NIS_DOMAIN, TFTP_SERVER_NAME
function old new delta
xmalloc_optname_optval 850 888 +38
attach_option 440 443 +3
len_of_option_as_string 13 14 +1
dhcp_option_lengths 13 14 +1
------------------------------------------------------------------------------
(add/remove: 0/0 grow/shrink: 4/0 up/down: 43/0) Total: 43 bytes
Signed-off-by: Denys Vlasenko <[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: gif_read (GifContext *context, guchar *buffer, size_t len)
{
gint retval;
#ifdef IO_GIFDEBUG
gint i;
#endif
if (context->file) {
#ifdef IO_GIFDEBUG
count += len;
g_print ("Fsize :%d\tcount :%d\t", len, count);
#endif
retval = (fread(buffer, len, 1, context->file) != 0);
if (!retval && ferror (context->file))
g_set_error (context->error,
G_FILE_ERROR,
g_file_error_from_errno (errno),
_("Failure reading GIF: %s"), strerror (errno));
#ifdef IO_GIFDEBUG
if (len < 100) {
for (i = 0; i < len; i++)
g_print ("%d ", buffer[i]);
}
g_print ("\n");
#endif
return retval;
} else {
#ifdef IO_GIFDEBUG
/* g_print ("\tlooking for %d bytes. size == %d, ptr == %d\n", len, context->size, context->ptr); */
#endif
if ((context->size - context->ptr) >= len) {
#ifdef IO_GIFDEBUG
count += len;
#endif
memcpy (buffer, context->buf + context->ptr, len);
context->ptr += len;
context->amount_needed = 0;
#ifdef IO_GIFDEBUG
g_print ("Psize :%d\tcount :%d\t", len, count);
if (len < 100) {
for (i = 0; i < len; i++)
g_print ("%d ", buffer[i]);
}
g_print ("\n");
#endif
return TRUE;
}
context->amount_needed = len - (context->size - context->ptr);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Initial stab at getting the focus code to work.
Fri Jun 1 18:54:47 2001 Jonathan Blandford <[email protected]>
* gtk/gtktreeview.c: (gtk_tree_view_focus): Initial stab at
getting the focus code to work.
(gtk_tree_view_class_init): Add a bunch of keybindings.
* gtk/gtktreeviewcolumn.c
(gtk_tree_view_column_set_cell_data_func):
s/GtkCellDataFunc/GtkTreeCellDataFunc.
(_gtk_tree_view_column_set_tree_view): Use "notify::model" instead
of "properties_changed" to help justify the death of the latter
signal. (-:
* tests/testtreefocus.c (main): Let some columns be focussable to
test focus better.'</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: gdk_pixbuf__gif_image_load_increment (gpointer data,
const guchar *buf, guint size,
GError **error)
{
gint retval;
GifContext *context = (GifContext *) data;
context->error = error;
if (context->amount_needed == 0) {
/* we aren't looking for some bytes. */
/* we can use buf now, but we don't want to keep it around at all.
* it will be gone by the end of the call. */
context->buf = (guchar*) buf; /* very dubious const cast */
context->ptr = 0;
context->size = size;
} else {
/* we need some bytes */
if (size < context->amount_needed) {
context->amount_needed -= size;
/* copy it over and return */
memcpy (context->buf + context->size, buf, size);
context->size += size;
return TRUE;
} else if (size == context->amount_needed) {
memcpy (context->buf + context->size, buf, size);
context->size += size;
} else {
context->buf = g_realloc (context->buf, context->size + size);
memcpy (context->buf + context->size, buf, size);
context->size += size;
}
}
retval = gif_main_loop (context);
if (retval == -2)
return FALSE;
if (retval == -1) {
/* we didn't have enough memory */
/* prepare for the next image_load_increment */
if (context->buf == buf) {
g_assert (context->size == size);
context->buf = (guchar *)g_new (guchar, context->amount_needed + (context->size - context->ptr));
memcpy (context->buf, buf + context->ptr, context->size - context->ptr);
} else {
/* copy the left overs to the begining of the buffer */
/* and realloc the memory */
memmove (context->buf, context->buf + context->ptr, context->size - context->ptr);
context->buf = g_realloc (context->buf, context->amount_needed + (context->size - context->ptr));
}
context->size = context->size - context->ptr;
context->ptr = 0;
} else {
/* we are prolly all done */
if (context->buf == buf)
context->buf = NULL;
}
return TRUE;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Initial stab at getting the focus code to work.
Fri Jun 1 18:54:47 2001 Jonathan Blandford <[email protected]>
* gtk/gtktreeview.c: (gtk_tree_view_focus): Initial stab at
getting the focus code to work.
(gtk_tree_view_class_init): Add a bunch of keybindings.
* gtk/gtktreeviewcolumn.c
(gtk_tree_view_column_set_cell_data_func):
s/GtkCellDataFunc/GtkTreeCellDataFunc.
(_gtk_tree_view_column_set_tree_view): Use "notify::model" instead
of "properties_changed" to help justify the death of the latter
signal. (-:
* tests/testtreefocus.c (main): Let some columns be focussable to
test focus better.'</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: jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
{
/*
* Convert jiffies to nanoseconds and separate with
* one divide.
*/
u64 nsec = (u64)jiffies * TICK_NSEC;
value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_nsec);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'remove div_long_long_rem
x86 is the only arch right now, which provides an optimized for
div_long_long_rem and it has the downside that one has to be very careful that
the divide doesn't overflow.
The API is a little akward, as the arguments for the unsigned divide are
signed. The signed version also doesn't handle a negative divisor and
produces worse code on 64bit archs.
There is little incentive to keep this API alive, so this converts the few
users to the new API.
Signed-off-by: Roman Zippel <[email protected]>
Cc: Ralf Baechle <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: john stultz <[email protected]>
Cc: Christoph Lameter <[email protected]>
Signed-off-by: Andrew Morton <[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: static int sgi_timer_set(struct k_itimer *timr, int flags,
struct itimerspec * new_setting,
struct itimerspec * old_setting)
{
unsigned long when, period, irqflags;
int err = 0;
cnodeid_t nodeid;
struct mmtimer *base;
struct rb_node *n;
if (old_setting)
sgi_timer_get(timr, old_setting);
sgi_timer_del(timr);
when = timespec_to_ns(new_setting->it_value);
period = timespec_to_ns(new_setting->it_interval);
if (when == 0)
/* Clear timer */
return 0;
base = kmalloc(sizeof(struct mmtimer), GFP_KERNEL);
if (base == NULL)
return -ENOMEM;
if (flags & TIMER_ABSTIME) {
struct timespec n;
unsigned long now;
getnstimeofday(&n);
now = timespec_to_ns(n);
if (when > now)
when -= now;
else
/* Fire the timer immediately */
when = 0;
}
/*
* Convert to sgi clock period. Need to keep rtc_time() as near as possible
* to getnstimeofday() in order to be as faithful as possible to the time
* specified.
*/
when = (when + sgi_clock_period - 1) / sgi_clock_period + rtc_time();
period = (period + sgi_clock_period - 1) / sgi_clock_period;
/*
* We are allocating a local SHub comparator. If we would be moved to another
* cpu then another SHub may be local to us. Prohibit that by switching off
* preemption.
*/
preempt_disable();
nodeid = cpu_to_node(smp_processor_id());
/* Lock the node timer structure */
spin_lock_irqsave(&timers[nodeid].lock, irqflags);
base->timer = timr;
base->cpu = smp_processor_id();
timr->it.mmtimer.clock = TIMER_SET;
timr->it.mmtimer.node = nodeid;
timr->it.mmtimer.incr = period;
timr->it.mmtimer.expires = when;
n = timers[nodeid].next;
/* Add the new struct mmtimer to node's timer list */
mmtimer_add_list(base);
if (timers[nodeid].next == n) {
/* No need to reprogram comparator for now */
spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
preempt_enable();
return err;
}
/* We need to reprogram the comparator */
if (n)
mmtimer_disable_int(cnodeid_to_nasid(nodeid), COMPARATOR);
mmtimer_set_next_timer(nodeid);
/* Unlock the node timer structure */
spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
preempt_enable();
return err;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'remove div_long_long_rem
x86 is the only arch right now, which provides an optimized for
div_long_long_rem and it has the downside that one has to be very careful that
the divide doesn't overflow.
The API is a little akward, as the arguments for the unsigned divide are
signed. The signed version also doesn't handle a negative divisor and
produces worse code on 64bit archs.
There is little incentive to keep this API alive, so this converts the few
users to the new API.
Signed-off-by: Roman Zippel <[email protected]>
Cc: Ralf Baechle <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: john stultz <[email protected]>
Cc: Christoph Lameter <[email protected]>
Signed-off-by: Andrew Morton <[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: */
static int
xmlXPathCompOpEval(xmlXPathParserContextPtr ctxt, xmlXPathStepOpPtr op)
{
int total = 0;
int equal, ret;
xmlXPathCompExprPtr comp;
xmlXPathObjectPtr arg1, arg2;
xmlNodePtr bak;
xmlDocPtr bakd;
int pp;
int cs;
CHECK_ERROR0;
comp = ctxt->comp;
switch (op->op) {
case XPATH_OP_END:
return (0);
case XPATH_OP_AND:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
xmlXPathBooleanFunction(ctxt, 1);
if ((ctxt->value == NULL) || (ctxt->value->boolval == 0))
return (total);
arg2 = valuePop(ctxt);
ctxt->context->doc = bakd;
ctxt->context->node = bak;
ctxt->context->proximityPosition = pp;
ctxt->context->contextSize = cs;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
if (ctxt->error) {
xmlXPathFreeObject(arg2);
return(0);
}
xmlXPathBooleanFunction(ctxt, 1);
arg1 = valuePop(ctxt);
arg1->boolval &= arg2->boolval;
valuePush(ctxt, arg1);
xmlXPathReleaseObject(ctxt->context, arg2);
return (total);
case XPATH_OP_OR:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
xmlXPathBooleanFunction(ctxt, 1);
if ((ctxt->value == NULL) || (ctxt->value->boolval == 1))
return (total);
arg2 = valuePop(ctxt);
ctxt->context->doc = bakd;
ctxt->context->node = bak;
ctxt->context->proximityPosition = pp;
ctxt->context->contextSize = cs;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
if (ctxt->error) {
xmlXPathFreeObject(arg2);
return(0);
}
xmlXPathBooleanFunction(ctxt, 1);
arg1 = valuePop(ctxt);
arg1->boolval |= arg2->boolval;
valuePush(ctxt, arg1);
xmlXPathReleaseObject(ctxt->context, arg2);
return (total);
case XPATH_OP_EQUAL:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
ctxt->context->doc = bakd;
ctxt->context->node = bak;
ctxt->context->proximityPosition = pp;
ctxt->context->contextSize = cs;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
CHECK_ERROR0;
if (op->value)
equal = xmlXPathEqualValues(ctxt);
else
equal = xmlXPathNotEqualValues(ctxt);
valuePush(ctxt, xmlXPathCacheNewBoolean(ctxt->context, equal));
return (total);
case XPATH_OP_CMP:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
ctxt->context->doc = bakd;
ctxt->context->node = bak;
ctxt->context->proximityPosition = pp;
ctxt->context->contextSize = cs;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
CHECK_ERROR0;
ret = xmlXPathCompareValues(ctxt, op->value, op->value2);
valuePush(ctxt, xmlXPathCacheNewBoolean(ctxt->context, ret));
return (total);
case XPATH_OP_PLUS:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
if (op->ch2 != -1) {
ctxt->context->doc = bakd;
ctxt->context->node = bak;
ctxt->context->proximityPosition = pp;
ctxt->context->contextSize = cs;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
}
CHECK_ERROR0;
if (op->value == 0)
xmlXPathSubValues(ctxt);
else if (op->value == 1)
xmlXPathAddValues(ctxt);
else if (op->value == 2)
xmlXPathValueFlipSign(ctxt);
else if (op->value == 3) {
CAST_TO_NUMBER;
CHECK_TYPE0(XPATH_NUMBER);
}
return (total);
case XPATH_OP_MULT:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
ctxt->context->doc = bakd;
ctxt->context->node = bak;
ctxt->context->proximityPosition = pp;
ctxt->context->contextSize = cs;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
CHECK_ERROR0;
if (op->value == 0)
xmlXPathMultValues(ctxt);
else if (op->value == 1)
xmlXPathDivValues(ctxt);
else if (op->value == 2)
xmlXPathModValues(ctxt);
return (total);
case XPATH_OP_UNION:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
ctxt->context->doc = bakd;
ctxt->context->node = bak;
ctxt->context->proximityPosition = pp;
ctxt->context->contextSize = cs;
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
CHECK_ERROR0;
CHECK_TYPE0(XPATH_NODESET);
arg2 = valuePop(ctxt);
CHECK_TYPE0(XPATH_NODESET);
arg1 = valuePop(ctxt);
if ((arg1->nodesetval == NULL) ||
((arg2->nodesetval != NULL) &&
(arg2->nodesetval->nodeNr != 0)))
{
arg1->nodesetval = xmlXPathNodeSetMerge(arg1->nodesetval,
arg2->nodesetval);
}
valuePush(ctxt, arg1);
xmlXPathReleaseObject(ctxt->context, arg2);
return (total);
case XPATH_OP_ROOT:
xmlXPathRoot(ctxt);
return (total);
case XPATH_OP_NODE:
if (op->ch1 != -1)
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
if (op->ch2 != -1)
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
CHECK_ERROR0;
valuePush(ctxt, xmlXPathCacheNewNodeSet(ctxt->context,
ctxt->context->node));
return (total);
case XPATH_OP_RESET:
if (op->ch1 != -1)
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
if (op->ch2 != -1)
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
CHECK_ERROR0;
ctxt->context->node = NULL;
return (total);
case XPATH_OP_COLLECT:{
if (op->ch1 == -1)
return (total);
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
total += xmlXPathNodeCollectAndTest(ctxt, op, NULL, NULL, 0);
return (total);
}
case XPATH_OP_VALUE:
valuePush(ctxt,
xmlXPathCacheObjectCopy(ctxt->context,
(xmlXPathObjectPtr) op->value4));
return (total);
case XPATH_OP_VARIABLE:{
xmlXPathObjectPtr val;
if (op->ch1 != -1)
total +=
xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
if (op->value5 == NULL) {
val = xmlXPathVariableLookup(ctxt->context, op->value4);
if (val == NULL) {
ctxt->error = XPATH_UNDEF_VARIABLE_ERROR;
return(0);
}
valuePush(ctxt, val);
} else {
const xmlChar *URI;
URI = xmlXPathNsLookup(ctxt->context, op->value5);
if (URI == NULL) {
xmlGenericError(xmlGenericErrorContext,
"xmlXPathCompOpEval: variable %s bound to undefined prefix %s\n",
(char *) op->value4, (char *)op->value5);
return (total);
}
val = xmlXPathVariableLookupNS(ctxt->context,
op->value4, URI);
if (val == NULL) {
ctxt->error = XPATH_UNDEF_VARIABLE_ERROR;
return(0);
}
valuePush(ctxt, val);
}
return (total);
}
case XPATH_OP_FUNCTION:{
xmlXPathFunction func;
const xmlChar *oldFunc, *oldFuncURI;
int i;
if (op->ch1 != -1)
total +=
xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
if (ctxt->valueNr < op->value) {
xmlGenericError(xmlGenericErrorContext,
"xmlXPathCompOpEval: parameter error\n");
ctxt->error = XPATH_INVALID_OPERAND;
return (total);
}
for (i = 0; i < op->value; i++)
if (ctxt->valueTab[(ctxt->valueNr - 1) - i] == NULL) {
xmlGenericError(xmlGenericErrorContext,
"xmlXPathCompOpEval: parameter error\n");
ctxt->error = XPATH_INVALID_OPERAND;
return (total);
}
if (op->cache != NULL)
XML_CAST_FPTR(func) = op->cache;
else {
const xmlChar *URI = NULL;
if (op->value5 == NULL)
func =
xmlXPathFunctionLookup(ctxt->context,
op->value4);
else {
URI = xmlXPathNsLookup(ctxt->context, op->value5);
if (URI == NULL) {
xmlGenericError(xmlGenericErrorContext,
"xmlXPathCompOpEval: function %s bound to undefined prefix %s\n",
(char *)op->value4, (char *)op->value5);
return (total);
}
func = xmlXPathFunctionLookupNS(ctxt->context,
op->value4, URI);
}
if (func == NULL) {
xmlGenericError(xmlGenericErrorContext,
"xmlXPathCompOpEval: function %s not found\n",
(char *)op->value4);
XP_ERROR0(XPATH_UNKNOWN_FUNC_ERROR);
}
op->cache = XML_CAST_FPTR(func);
op->cacheURI = (void *) URI;
}
oldFunc = ctxt->context->function;
oldFuncURI = ctxt->context->functionURI;
ctxt->context->function = op->value4;
ctxt->context->functionURI = op->cacheURI;
func(ctxt, op->value);
ctxt->context->function = oldFunc;
ctxt->context->functionURI = oldFuncURI;
return (total);
}
case XPATH_OP_ARG:
bakd = ctxt->context->doc;
bak = ctxt->context->node;
pp = ctxt->context->proximityPosition;
cs = ctxt->context->contextSize;
if (op->ch1 != -1)
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
ctxt->context->contextSize = cs;
ctxt->context->proximityPosition = pp;
ctxt->context->node = bak;
ctxt->context->doc = bakd;
CHECK_ERROR0;
if (op->ch2 != -1) {
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch2]);
ctxt->context->doc = bakd;
ctxt->context->node = bak;
CHECK_ERROR0;
}
return (total);
case XPATH_OP_PREDICATE:
case XPATH_OP_FILTER:{
xmlXPathObjectPtr res;
xmlXPathObjectPtr obj, tmp;
xmlNodeSetPtr newset = NULL;
xmlNodeSetPtr oldset;
xmlNodePtr oldnode;
xmlDocPtr oldDoc;
int i;
/*
* Optimization for ()[1] selection i.e. the first elem
*/
if ((op->ch1 != -1) && (op->ch2 != -1) &&
#ifdef XP_OPTIMIZED_FILTER_FIRST
/*
* FILTER TODO: Can we assume that the inner processing
* will result in an ordered list if we have an
* XPATH_OP_FILTER?
* What about an additional field or flag on
* xmlXPathObject like @sorted ? This way we wouln'd need
* to assume anything, so it would be more robust and
* easier to optimize.
*/
((comp->steps[op->ch1].op == XPATH_OP_SORT) || /* 18 */
(comp->steps[op->ch1].op == XPATH_OP_FILTER)) && /* 17 */
#else
(comp->steps[op->ch1].op == XPATH_OP_SORT) &&
#endif
(comp->steps[op->ch2].op == XPATH_OP_VALUE)) { /* 12 */
xmlXPathObjectPtr val;
val = comp->steps[op->ch2].value4;
if ((val != NULL) && (val->type == XPATH_NUMBER) &&
(val->floatval == 1.0)) {
xmlNodePtr first = NULL;
total +=
xmlXPathCompOpEvalFirst(ctxt,
&comp->steps[op->ch1],
&first);
CHECK_ERROR0;
/*
* The nodeset should be in document order,
* Keep only the first value
*/
if ((ctxt->value != NULL) &&
(ctxt->value->type == XPATH_NODESET) &&
(ctxt->value->nodesetval != NULL) &&
(ctxt->value->nodesetval->nodeNr > 1))
ctxt->value->nodesetval->nodeNr = 1;
return (total);
}
}
/*
* Optimization for ()[last()] selection i.e. the last elem
*/
if ((op->ch1 != -1) && (op->ch2 != -1) &&
(comp->steps[op->ch1].op == XPATH_OP_SORT) &&
(comp->steps[op->ch2].op == XPATH_OP_SORT)) {
int f = comp->steps[op->ch2].ch1;
if ((f != -1) &&
(comp->steps[f].op == XPATH_OP_FUNCTION) &&
(comp->steps[f].value5 == NULL) &&
(comp->steps[f].value == 0) &&
(comp->steps[f].value4 != NULL) &&
(xmlStrEqual
(comp->steps[f].value4, BAD_CAST "last"))) {
xmlNodePtr last = NULL;
total +=
xmlXPathCompOpEvalLast(ctxt,
&comp->steps[op->ch1],
&last);
CHECK_ERROR0;
/*
* The nodeset should be in document order,
* Keep only the last value
*/
if ((ctxt->value != NULL) &&
(ctxt->value->type == XPATH_NODESET) &&
(ctxt->value->nodesetval != NULL) &&
(ctxt->value->nodesetval->nodeTab != NULL) &&
(ctxt->value->nodesetval->nodeNr > 1)) {
ctxt->value->nodesetval->nodeTab[0] =
ctxt->value->nodesetval->nodeTab[ctxt->
value->
nodesetval->
nodeNr -
1];
ctxt->value->nodesetval->nodeNr = 1;
}
return (total);
}
}
/*
* Process inner predicates first.
* Example "index[parent::book][1]":
* ...
* PREDICATE <-- we are here "[1]"
* PREDICATE <-- process "[parent::book]" first
* SORT
* COLLECT 'parent' 'name' 'node' book
* NODE
* ELEM Object is a number : 1
*/
if (op->ch1 != -1)
total +=
xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
if (op->ch2 == -1)
return (total);
if (ctxt->value == NULL)
return (total);
oldnode = ctxt->context->node;
#ifdef LIBXML_XPTR_ENABLED
/*
* Hum are we filtering the result of an XPointer expression
*/
if (ctxt->value->type == XPATH_LOCATIONSET) {
xmlLocationSetPtr newlocset = NULL;
xmlLocationSetPtr oldlocset;
/*
* Extract the old locset, and then evaluate the result of the
* expression for all the element in the locset. use it to grow
* up a new locset.
*/
CHECK_TYPE0(XPATH_LOCATIONSET);
obj = valuePop(ctxt);
oldlocset = obj->user;
ctxt->context->node = NULL;
if ((oldlocset == NULL) || (oldlocset->locNr == 0)) {
ctxt->context->contextSize = 0;
ctxt->context->proximityPosition = 0;
if (op->ch2 != -1)
total +=
xmlXPathCompOpEval(ctxt,
&comp->steps[op->ch2]);
res = valuePop(ctxt);
if (res != NULL) {
xmlXPathReleaseObject(ctxt->context, res);
}
valuePush(ctxt, obj);
CHECK_ERROR0;
return (total);
}
newlocset = xmlXPtrLocationSetCreate(NULL);
for (i = 0; i < oldlocset->locNr; i++) {
/*
* Run the evaluation with a node list made of a
* single item in the nodelocset.
*/
ctxt->context->node = oldlocset->locTab[i]->user;
ctxt->context->contextSize = oldlocset->locNr;
ctxt->context->proximityPosition = i + 1;
tmp = xmlXPathCacheNewNodeSet(ctxt->context,
ctxt->context->node);
valuePush(ctxt, tmp);
if (op->ch2 != -1)
total +=
xmlXPathCompOpEval(ctxt,
&comp->steps[op->ch2]);
if (ctxt->error != XPATH_EXPRESSION_OK) {
xmlXPathFreeObject(obj);
return(0);
}
/*
* The result of the evaluation need to be tested to
* decided whether the filter succeeded or not
*/
res = valuePop(ctxt);
if (xmlXPathEvaluatePredicateResult(ctxt, res)) {
xmlXPtrLocationSetAdd(newlocset,
xmlXPathObjectCopy
(oldlocset->locTab[i]));
}
/*
* Cleanup
*/
if (res != NULL) {
xmlXPathReleaseObject(ctxt->context, res);
}
if (ctxt->value == tmp) {
res = valuePop(ctxt);
xmlXPathReleaseObject(ctxt->context, res);
}
ctxt->context->node = NULL;
}
/*
* The result is used as the new evaluation locset.
*/
xmlXPathReleaseObject(ctxt->context, obj);
ctxt->context->node = NULL;
ctxt->context->contextSize = -1;
ctxt->context->proximityPosition = -1;
valuePush(ctxt, xmlXPtrWrapLocationSet(newlocset));
ctxt->context->node = oldnode;
return (total);
}
#endif /* LIBXML_XPTR_ENABLED */
/*
* Extract the old set, and then evaluate the result of the
* expression for all the element in the set. use it to grow
* up a new set.
*/
CHECK_TYPE0(XPATH_NODESET);
obj = valuePop(ctxt);
oldset = obj->nodesetval;
oldnode = ctxt->context->node;
oldDoc = ctxt->context->doc;
ctxt->context->node = NULL;
if ((oldset == NULL) || (oldset->nodeNr == 0)) {
ctxt->context->contextSize = 0;
ctxt->context->proximityPosition = 0;
/*
if (op->ch2 != -1)
total +=
xmlXPathCompOpEval(ctxt,
&comp->steps[op->ch2]);
CHECK_ERROR0;
res = valuePop(ctxt);
if (res != NULL)
xmlXPathFreeObject(res);
*/
valuePush(ctxt, obj);
ctxt->context->node = oldnode;
CHECK_ERROR0;
} else {
tmp = NULL;
/*
* Initialize the new set.
* Also set the xpath document in case things like
* key() evaluation are attempted on the predicate
*/
newset = xmlXPathNodeSetCreate(NULL);
/*
* SPEC XPath 1.0:
* "For each node in the node-set to be filtered, the
* PredicateExpr is evaluated with that node as the
* context node, with the number of nodes in the
* node-set as the context size, and with the proximity
* position of the node in the node-set with respect to
* the axis as the context position;"
* @oldset is the node-set" to be filtered.
*
* SPEC XPath 1.0:
* "only predicates change the context position and
* context size (see [2.4 Predicates])."
* Example:
* node-set context pos
* nA 1
* nB 2
* nC 3
* After applying predicate [position() > 1] :
* node-set context pos
* nB 1
* nC 2
*
* removed the first node in the node-set, then
* the context position of the
*/
for (i = 0; i < oldset->nodeNr; i++) {
/*
* Run the evaluation with a node list made of
* a single item in the nodeset.
*/
ctxt->context->node = oldset->nodeTab[i];
if ((oldset->nodeTab[i]->type != XML_NAMESPACE_DECL) &&
(oldset->nodeTab[i]->doc != NULL))
ctxt->context->doc = oldset->nodeTab[i]->doc;
if (tmp == NULL) {
tmp = xmlXPathCacheNewNodeSet(ctxt->context,
ctxt->context->node);
} else {
xmlXPathNodeSetAddUnique(tmp->nodesetval,
ctxt->context->node);
}
valuePush(ctxt, tmp);
ctxt->context->contextSize = oldset->nodeNr;
ctxt->context->proximityPosition = i + 1;
/*
* Evaluate the predicate against the context node.
* Can/should we optimize position() predicates
* here (e.g. "[1]")?
*/
if (op->ch2 != -1)
total +=
xmlXPathCompOpEval(ctxt,
&comp->steps[op->ch2]);
if (ctxt->error != XPATH_EXPRESSION_OK) {
xmlXPathFreeNodeSet(newset);
xmlXPathFreeObject(obj);
return(0);
}
/*
* The result of the evaluation needs to be tested to
* decide whether the filter succeeded or not
*/
/*
* OPTIMIZE TODO: Can we use
* xmlXPathNodeSetAdd*Unique()* instead?
*/
res = valuePop(ctxt);
if (xmlXPathEvaluatePredicateResult(ctxt, res)) {
xmlXPathNodeSetAdd(newset, oldset->nodeTab[i]);
}
/*
* Cleanup
*/
if (res != NULL) {
xmlXPathReleaseObject(ctxt->context, res);
}
if (ctxt->value == tmp) {
valuePop(ctxt);
xmlXPathNodeSetClear(tmp->nodesetval, 1);
/*
* Don't free the temporary nodeset
* in order to avoid massive recreation inside this
* loop.
*/
} else
tmp = NULL;
ctxt->context->node = NULL;
}
if (tmp != NULL)
xmlXPathReleaseObject(ctxt->context, tmp);
/*
* The result is used as the new evaluation set.
*/
xmlXPathReleaseObject(ctxt->context, obj);
ctxt->context->node = NULL;
ctxt->context->contextSize = -1;
ctxt->context->proximityPosition = -1;
/* may want to move this past the '}' later */
ctxt->context->doc = oldDoc;
valuePush(ctxt,
xmlXPathCacheWrapNodeSet(ctxt->context, newset));
}
ctxt->context->node = oldnode;
return (total);
}
case XPATH_OP_SORT:
if (op->ch1 != -1)
total += xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
CHECK_ERROR0;
if ((ctxt->value != NULL) &&
(ctxt->value->type == XPATH_NODESET) &&
(ctxt->value->nodesetval != NULL) &&
(ctxt->value->nodesetval->nodeNr > 1))
{
xmlXPathNodeSetSort(ctxt->value->nodesetval);
}
return (total);
#ifdef LIBXML_XPTR_ENABLED
case XPATH_OP_RANGETO:{
xmlXPathObjectPtr range;
xmlXPathObjectPtr res, obj;
xmlXPathObjectPtr tmp;
xmlLocationSetPtr newlocset = NULL;
xmlLocationSetPtr oldlocset;
xmlNodeSetPtr oldset;
int i, j;
if (op->ch1 != -1)
total +=
xmlXPathCompOpEval(ctxt, &comp->steps[op->ch1]);
if (op->ch2 == -1)
return (total);
if (ctxt->value->type == XPATH_LOCATIONSET) {
/*
* Extract the old locset, and then evaluate the result of the
* expression for all the element in the locset. use it to grow
* up a new locset.
*/
CHECK_TYPE0(XPATH_LOCATIONSET);
obj = valuePop(ctxt);
oldlocset = obj->user;
if ((oldlocset == NULL) || (oldlocset->locNr == 0)) {
ctxt->context->node = NULL;
ctxt->context->contextSize = 0;
ctxt->context->proximityPosition = 0;
total += xmlXPathCompOpEval(ctxt,&comp->steps[op->ch2]);
res = valuePop(ctxt);
if (res != NULL) {
xmlXPathReleaseObject(ctxt->context, res);
}
valuePush(ctxt, obj);
CHECK_ERROR0;
return (total);
}
newlocset = xmlXPtrLocationSetCreate(NULL);
for (i = 0; i < oldlocset->locNr; i++) {
/*
* Run the evaluation with a node list made of a
* single item in the nodelocset.
*/
ctxt->context->node = oldlocset->locTab[i]->user;
ctxt->context->contextSize = oldlocset->locNr;
ctxt->context->proximityPosition = i + 1;
tmp = xmlXPathCacheNewNodeSet(ctxt->context,
ctxt->context->node);
valuePush(ctxt, tmp);
if (op->ch2 != -1)
total +=
xmlXPathCompOpEval(ctxt,
&comp->steps[op->ch2]);
if (ctxt->error != XPATH_EXPRESSION_OK) {
xmlXPathFreeObject(obj);
return(0);
}
res = valuePop(ctxt);
if (res->type == XPATH_LOCATIONSET) {
xmlLocationSetPtr rloc =
(xmlLocationSetPtr)res->user;
for (j=0; j<rloc->locNr; j++) {
range = xmlXPtrNewRange(
oldlocset->locTab[i]->user,
oldlocset->locTab[i]->index,
rloc->locTab[j]->user2,
rloc->locTab[j]->index2);
if (range != NULL) {
xmlXPtrLocationSetAdd(newlocset, range);
}
}
} else {
range = xmlXPtrNewRangeNodeObject(
(xmlNodePtr)oldlocset->locTab[i]->user, res);
if (range != NULL) {
xmlXPtrLocationSetAdd(newlocset,range);
}
}
/*
* Cleanup
*/
if (res != NULL) {
xmlXPathReleaseObject(ctxt->context, res);
}
if (ctxt->value == tmp) {
res = valuePop(ctxt);
xmlXPathReleaseObject(ctxt->context, res);
}
ctxt->context->node = NULL;
}
} else { /* Not a location set */
CHECK_TYPE0(XPATH_NODESET);
obj = valuePop(ctxt);
oldset = obj->nodesetval;
ctxt->context->node = NULL;
newlocset = xmlXPtrLocationSetCreate(NULL);
if (oldset != NULL) {
for (i = 0; i < oldset->nodeNr; i++) {
/*
* Run the evaluation with a node list made of a single item
* in the nodeset.
*/
ctxt->context->node = oldset->nodeTab[i];
/*
* OPTIMIZE TODO: Avoid recreation for every iteration.
*/
tmp = xmlXPathCacheNewNodeSet(ctxt->context,
ctxt->context->node);
valuePush(ctxt, tmp);
if (op->ch2 != -1)
total +=
xmlXPathCompOpEval(ctxt,
&comp->steps[op->ch2]);
if (ctxt->error != XPATH_EXPRESSION_OK) {
xmlXPathFreeObject(obj);
return(0);
}
res = valuePop(ctxt);
range =
xmlXPtrNewRangeNodeObject(oldset->nodeTab[i],
res);
if (range != NULL) {
xmlXPtrLocationSetAdd(newlocset, range);
}
/*
* Cleanup
*/
if (res != NULL) {
xmlXPathReleaseObject(ctxt->context, res);
}
if (ctxt->value == tmp) {
res = valuePop(ctxt);
xmlXPathReleaseObject(ctxt->context, res);
}
ctxt->context->node = NULL;
}
}
}
/*
* The result is used as the new evaluation set.
*/
xmlXPathReleaseObject(ctxt->context, obj);
ctxt->context->node = NULL;
ctxt->context->contextSize = -1;
ctxt->context->proximityPosition = -1;
valuePush(ctxt, xmlXPtrWrapLocationSet(newlocset));
return (total);
}
#endif /* LIBXML_XPTR_ENABLED */
}
xmlGenericError(xmlGenericErrorContext,
"XPath: unknown precompiled operation %d\n", op->op); ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-415'], 'message': 'Hardening of XPath evaluation
Add a mechanism of frame for XPath evaluation when entering a function
or a scoped evaluation, also fix a potential problem in predicate
evaluation.'</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 SCSIRequest *scsi_new_request(SCSIDevice *d, uint32_t tag,
uint32_t lun, void *hba_private)
{
SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, d);
SCSIRequest *req;
SCSIDiskReq *r;
req = scsi_req_alloc(&scsi_disk_reqops, &s->qdev, tag, lun, hba_private);
r = DO_UPCAST(SCSIDiskReq, req, req);
r->iov.iov_base = qemu_blockalign(s->bs, SCSI_DMA_BUF_SIZE);
return req;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'scsi-disk: lazily allocate bounce buffer
It will not be needed for reads and writes if the HBA provides a sglist.
In addition, this lets scsi-disk refuse commands with an excessive
allocation length, as well as limit memory on usual well-behaved guests.
Signed-off-by: Paolo Bonzini <[email protected]>
Signed-off-by: Kevin Wolf <[email protected]>'</s> |
End of preview. Expand
in Dataset Viewer.
No dataset card yet
New: Create and edit this dataset card directly on the website!
Contribute a Dataset Card- Downloads last month
- 4