text
stringlengths 478
483k
|
|---|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static unsigned long long decodeLZ4S(FILE* finput, FILE* foutput)
{
unsigned long long filesize = 0;
char* in_buff;
char* out_buff, *out_start, *out_end;
unsigned char descriptor[LZ4S_MAXHEADERSIZE];
size_t nbReadBytes;
int decodedBytes=0;
unsigned int maxBlockSize;
size_t sizeCheck;
int blockChecksumFlag, streamChecksumFlag, blockIndependenceFlag;
void* streamChecksumState=NULL;
int (*decompressionFunction)(void* ctx, const char* src, char* dst, int cSize, int maxOSize) = LZ4_decompress_safe_continue;
LZ4_streamDecode_t ctx;
// init
memset(&ctx, 0, sizeof(ctx));
(void)blockIndependenceFlag;
// Decode stream descriptor
nbReadBytes = fread(descriptor, 1, 3, finput);
if (nbReadBytes != 3) EXM_THROW(61, "Unreadable header");
{
int version = (descriptor[0] >> 6) & _2BITS;
int streamSize = (descriptor[0] >> 3) & _1BIT;
int reserved1 = (descriptor[0] >> 1) & _1BIT;
int dictionary = (descriptor[0] >> 0) & _1BIT;
int reserved2 = (descriptor[1] >> 7) & _1BIT;
int blockSizeId = (descriptor[1] >> 4) & _3BITS;
int reserved3 = (descriptor[1] >> 0) & _4BITS;
int checkBits = (descriptor[2] >> 0) & _8BITS;
int checkBits_xxh32;
blockIndependenceFlag=(descriptor[0] >> 5) & _1BIT;
blockChecksumFlag = (descriptor[0] >> 4) & _1BIT;
streamChecksumFlag= (descriptor[0] >> 2) & _1BIT;
if (version != 1) EXM_THROW(62, "Wrong version number");
if (streamSize == 1) EXM_THROW(64, "Does not support stream size");
if (reserved1 != 0) EXM_THROW(65, "Wrong value for reserved bits");
if (dictionary == 1) EXM_THROW(66, "Does not support dictionary");
if (reserved2 != 0) EXM_THROW(67, "Wrong value for reserved bits");
if (blockSizeId < 4) EXM_THROW(68, "Unsupported block size");
if (reserved3 != 0) EXM_THROW(67, "Wrong value for reserved bits");
maxBlockSize = LZ4S_GetBlockSize_FromBlockId(blockSizeId);
// Checkbits verification
descriptor[1] &= 0xF0;
checkBits_xxh32 = XXH32(descriptor, 2, LZ4S_CHECKSUM_SEED);
checkBits_xxh32 = LZ4S_GetCheckBits_FromXXH(checkBits_xxh32);
if (checkBits != checkBits_xxh32) EXM_THROW(69, "Stream descriptor error detected");
}
// Allocate Memory
{
size_t outBuffSize = maxBlockSize + 64 KB;
if (outBuffSize < MIN_STREAM_BUFSIZE) outBuffSize = MIN_STREAM_BUFSIZE;
in_buff = (char*)malloc(maxBlockSize);
out_buff = (char*)malloc(outBuffSize);
out_start = out_buff;
out_end = out_start + outBuffSize;
if (!in_buff || !out_buff) EXM_THROW(70, "Allocation error : not enough memory");
if (streamChecksumFlag) streamChecksumState = XXH32_init(LZ4S_CHECKSUM_SEED);
}
// Main Loop
while (1)
{
unsigned int blockSize, uncompressedFlag;
// Block Size
nbReadBytes = fread(&blockSize, 1, 4, finput);
if( nbReadBytes != 4 ) EXM_THROW(71, "Read error : cannot read next block size");
if (blockSize == LZ4S_EOS) break; // End of Stream Mark : stream is completed
blockSize = LITTLE_ENDIAN_32(blockSize); // Convert to little endian
uncompressedFlag = blockSize >> 31;
blockSize &= 0x7FFFFFFF;
if (blockSize > maxBlockSize) EXM_THROW(72, "Error : invalid block size");
// Read Block
nbReadBytes = fread(in_buff, 1, blockSize, finput);
if( nbReadBytes != blockSize ) EXM_THROW(73, "Read error : cannot read data block" );
// Check Block
if (blockChecksumFlag)
{
unsigned int checksum = XXH32(in_buff, blockSize, LZ4S_CHECKSUM_SEED);
unsigned int readChecksum;
sizeCheck = fread(&readChecksum, 1, 4, finput);
if( sizeCheck != 4 ) EXM_THROW(74, "Read error : cannot read next block size");
readChecksum = LITTLE_ENDIAN_32(readChecksum); // Convert to little endian
if (checksum != readChecksum) EXM_THROW(75, "Error : invalid block checksum detected");
}
if (uncompressedFlag)
{
// Write uncompressed Block
sizeCheck = fwrite(in_buff, 1, blockSize, foutput);
if (sizeCheck != (size_t)blockSize) EXM_THROW(76, "Write error : cannot write data block");
filesize += blockSize;
if (streamChecksumFlag) XXH32_update(streamChecksumState, in_buff, blockSize);
if (!independentBlocks)
{
// handle dictionary for streaming
memcpy(in_buff + blockSize - 64 KB, out_buff, 64 KB);
LZ4_setDictDecode(&ctx, out_buff, 64 KB);
out_start = out_buff + 64 KB;
}
}
else
{
// Decode Block
if (out_start + maxBlockSize > out_end) out_start = out_buff;
decodedBytes = decompressionFunction(&ctx, in_buff, out_start, blockSize, maxBlockSize);
if (decodedBytes < 0) EXM_THROW(77, "Decoding Failed ! Corrupted input detected !");
filesize += decodedBytes;
if (streamChecksumFlag) XXH32_update(streamChecksumState, out_start, decodedBytes);
// Write Block
sizeCheck = fwrite(out_start, 1, decodedBytes, foutput);
if (sizeCheck != (size_t)decodedBytes) EXM_THROW(78, "Write error : cannot write decoded block\n");
out_start += decodedBytes;
}
}
// Stream Checksum
if (streamChecksumFlag)
{
unsigned int checksum = XXH32_digest(streamChecksumState);
unsigned int readChecksum;
sizeCheck = fread(&readChecksum, 1, 4, finput);
if (sizeCheck != 4) EXM_THROW(74, "Read error : cannot read stream checksum");
readChecksum = LITTLE_ENDIAN_32(readChecksum); // Convert to little endian
if (checksum != readChecksum) EXM_THROW(79, "Error : invalid stream checksum detected");
}
// Free
free(in_buff);
free(out_buff);
return filesize;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Fixed : issue 52 (reported by Ludwig Strigeus)'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: unsigned int FUZ_rand(unsigned int* src)
{
U32 rand32 = *src;
rand32 *= PRIME1;
rand32 += PRIME2;
rand32 = FUZ_rotl32(rand32, 13);
*src = rand32;
return rand32;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Fixed : issue 52 (reported by Ludwig Strigeus)'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static inline int get_len(LZOContext *c, int x, int mask)
{
int cnt = x & mask;
if (!cnt) {
while (!(x = get_byte(c)))
cnt += 255;
cnt += mask + x;
}
return cnt;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-190'], 'message': 'avutil/lzo: Fix integer overflow
Embargoed-till: 2014-06-27 requested by researcher, but embargo broken by libav today (git and mailing list)
Fixes: LMS-2014-06-16-4
Found-by: "Don A. Bailey" <[email protected]>
See: ccda51b14c0fcae2fad73a24872dce75a7964996
Signed-off-by: Michael Niedermayer <[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 void copy(LZOContext *c, int cnt)
{
register const uint8_t *src = c->in;
register uint8_t *dst = c->out;
if (cnt > c->in_end - src) {
cnt = FFMAX(c->in_end - src, 0);
c->error |= AV_LZO_INPUT_DEPLETED;
}
if (cnt > c->out_end - dst) {
cnt = FFMAX(c->out_end - dst, 0);
c->error |= AV_LZO_OUTPUT_FULL;
}
#if defined(INBUF_PADDED) && defined(OUTBUF_PADDED)
AV_COPY32U(dst, src);
src += 4;
dst += 4;
cnt -= 4;
if (cnt > 0)
#endif
memcpy(dst, src, cnt);
c->in = src + cnt;
c->out = dst + cnt;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-190'], 'message': 'avutil/lzo: add asserts to be double sure against overflows
These asserts cannot fail since d6af26c55c1ea30f85a7d9edbc373f53be1743ee
Based-on: ccda51b14c0fcae2fad73a24872dce75a7964996
Signed-off-by: Michael Niedermayer <[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: init_uncompress( compress_filter_context_t *zfx, z_stream *zs )
{
int rc;
/****************
* PGP uses a windowsize of 13 bits. Using a negative value for
* it forces zlib not to expect a zlib header. This is a
* undocumented feature Peter Gutmann told me about.
*
* We must use 15 bits for the inflator because CryptoEx uses 15
* bits thus the output would get scrambled w/o error indication
* if we would use 13 bits. For the uncompressing this does not
* matter at all.
*/
if( (rc = zfx->algo == 1? inflateInit2( zs, -15)
: inflateInit( zs )) != Z_OK ) {
log_fatal("zlib problem: %s\n", zs->msg? zs->msg :
rc == Z_MEM_ERROR ? "out of core" :
rc == Z_VERSION_ERROR ? "invalid lib version" :
"unknown error" );
}
zfx->inbufsize = 2048;
zfx->inbuf = xmalloc( zfx->inbufsize );
zs->avail_in = 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'gpg: Avoid infinite loop in uncompressing garbled packets.
* g10/compress.c (do_uncompress): Limit the number of extra FF bytes.
--
A packet like (a3 01 5b ff) leads to an infinite loop. Using
--max-output won't help if it is a partial packet. This patch
actually fixes a regression introduced on 1999-05-31 (c34c6769).
Actually it would be sufficient to stuff just one extra 0xff byte.
Given that this problem popped up only after 15 years, I feel safer to
allow for a very few FF bytes.
Thanks to Olivier Levillain and Florian Maury for their detailed
report.'</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 lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
unsigned char *out, size_t *out_len)
{
unsigned char *op;
const unsigned char *ip;
size_t t, next;
size_t state = 0;
const unsigned char *m_pos;
const unsigned char * const ip_end = in + in_len;
unsigned char * const op_end = out + *out_len;
op = out;
ip = in;
if (unlikely(in_len < 3))
goto input_overrun;
if (*ip > 17) {
t = *ip++ - 17;
if (t < 4) {
next = t;
goto match_next;
}
goto copy_literal_run;
}
for (;;) {
t = *ip++;
if (t < 16) {
if (likely(state == 0)) {
if (unlikely(t == 0)) {
while (unlikely(*ip == 0)) {
t += 255;
ip++;
NEED_IP(1);
}
t += 15 + *ip++;
}
t += 3;
copy_literal_run:
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) {
const unsigned char *ie = ip + t;
unsigned char *oe = op + t;
do {
COPY8(op, ip);
op += 8;
ip += 8;
COPY8(op, ip);
op += 8;
ip += 8;
} while (ip < ie);
ip = ie;
op = oe;
} else
#endif
{
NEED_OP(t);
NEED_IP(t + 3);
do {
*op++ = *ip++;
} while (--t > 0);
}
state = 4;
continue;
} else if (state != 4) {
next = t & 3;
m_pos = op - 1;
m_pos -= t >> 2;
m_pos -= *ip++ << 2;
TEST_LB(m_pos);
NEED_OP(2);
op[0] = m_pos[0];
op[1] = m_pos[1];
op += 2;
goto match_next;
} else {
next = t & 3;
m_pos = op - (1 + M2_MAX_OFFSET);
m_pos -= t >> 2;
m_pos -= *ip++ << 2;
t = 3;
}
} else if (t >= 64) {
next = t & 3;
m_pos = op - 1;
m_pos -= (t >> 2) & 7;
m_pos -= *ip++ << 3;
t = (t >> 5) - 1 + (3 - 1);
} else if (t >= 32) {
t = (t & 31) + (3 - 1);
if (unlikely(t == 2)) {
while (unlikely(*ip == 0)) {
t += 255;
ip++;
NEED_IP(1);
}
t += 31 + *ip++;
NEED_IP(2);
}
m_pos = op - 1;
next = get_unaligned_le16(ip);
ip += 2;
m_pos -= next >> 2;
next &= 3;
} else {
m_pos = op;
m_pos -= (t & 8) << 11;
t = (t & 7) + (3 - 1);
if (unlikely(t == 2)) {
while (unlikely(*ip == 0)) {
t += 255;
ip++;
NEED_IP(1);
}
t += 7 + *ip++;
NEED_IP(2);
}
next = get_unaligned_le16(ip);
ip += 2;
m_pos -= next >> 2;
next &= 3;
if (m_pos == op)
goto eof_found;
m_pos -= 0x4000;
}
TEST_LB(m_pos);
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
if (op - m_pos >= 8) {
unsigned char *oe = op + t;
if (likely(HAVE_OP(t + 15))) {
do {
COPY8(op, m_pos);
op += 8;
m_pos += 8;
COPY8(op, m_pos);
op += 8;
m_pos += 8;
} while (op < oe);
op = oe;
if (HAVE_IP(6)) {
state = next;
COPY4(op, ip);
op += next;
ip += next;
continue;
}
} else {
NEED_OP(t);
do {
*op++ = *m_pos++;
} while (op < oe);
}
} else
#endif
{
unsigned char *oe = op + t;
NEED_OP(t);
op[0] = m_pos[0];
op[1] = m_pos[1];
op += 2;
m_pos += 2;
do {
*op++ = *m_pos++;
} while (op < oe);
}
match_next:
state = next;
t = next;
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
if (likely(HAVE_IP(6) && HAVE_OP(4))) {
COPY4(op, ip);
op += t;
ip += t;
} else
#endif
{
NEED_IP(t + 3);
NEED_OP(t);
while (t > 0) {
*op++ = *ip++;
t--;
}
}
}
eof_found:
*out_len = op - out;
return (t != 3 ? LZO_E_ERROR :
ip == ip_end ? LZO_E_OK :
ip < ip_end ? LZO_E_INPUT_NOT_CONSUMED : LZO_E_INPUT_OVERRUN);
input_overrun:
*out_len = op - out;
return LZO_E_INPUT_OVERRUN;
output_overrun:
*out_len = op - out;
return LZO_E_OUTPUT_OVERRUN;
lookbehind_overrun:
*out_len = op - out;
return LZO_E_LOOKBEHIND_OVERRUN;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-190'], 'message': 'lzo: properly check for overruns
The lzo decompressor can, if given some really crazy data, possibly
overrun some variable types. Modify the checking logic to properly
detect overruns before they happen.
Reported-by: "Don A. Bailey" <[email protected]>
Tested-by: "Don A. Bailey" <[email protected]>
Cc: stable <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[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 __poke_user(struct task_struct *child, addr_t addr, addr_t data)
{
struct user *dummy = NULL;
addr_t offset;
if (addr < (addr_t) &dummy->regs.acrs) {
/*
* psw and gprs are stored on the stack
*/
if (addr == (addr_t) &dummy->regs.psw.mask) {
unsigned long mask = PSW_MASK_USER;
mask |= is_ri_task(child) ? PSW_MASK_RI : 0;
if ((data & ~mask) != PSW_USER_BITS)
return -EINVAL;
if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))
return -EINVAL;
}
*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
/*
* access registers are stored in the thread structure
*/
offset = addr - (addr_t) &dummy->regs.acrs;
#ifdef CONFIG_64BIT
/*
* Very special case: old & broken 64 bit gdb writing
* to acrs[15] with a 64 bit value. Ignore the lower
* half of the value and write the upper 32 bit to
* acrs[15]. Sick...
*/
if (addr == (addr_t) &dummy->regs.acrs[15])
child->thread.acrs[15] = (unsigned int) (data >> 32);
else
#endif
*(addr_t *)((addr_t) &child->thread.acrs + offset) = data;
} else if (addr == (addr_t) &dummy->regs.orig_gpr2) {
/*
* orig_gpr2 is stored on the kernel stack
*/
task_pt_regs(child)->orig_gpr2 = data;
} else if (addr < (addr_t) &dummy->regs.fp_regs) {
/*
* prevent writes of padding hole between
* orig_gpr2 and fp_regs on s390.
*/
return 0;
} else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) {
/*
* floating point regs. are stored in the thread structure
*/
if (addr == (addr_t) &dummy->regs.fp_regs.fpc)
if ((unsigned int) data != 0 ||
test_fp_ctl(data >> (BITS_PER_LONG - 32)))
return -EINVAL;
offset = addr - (addr_t) &dummy->regs.fp_regs;
*(addr_t *)((addr_t) &child->thread.fp_regs + offset) = data;
} else if (addr < (addr_t) (&dummy->regs.per_info + 1)) {
/*
* Handle access to the per_info structure.
*/
addr -= (addr_t) &dummy->regs.per_info;
__poke_user_per(child, addr, data);
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264', 'CWE-269'], 'message': 's390/ptrace: fix PSW mask check
The PSW mask check of the PTRACE_POKEUSR_AREA command is incorrect.
The PSW_MASK_USER define contains the PSW_MASK_ASC bits, the ptrace
interface accepts all combinations for the address-space-control
bits. To protect the kernel space the PSW mask check in ptrace needs
to reject the address-space-control bit combination for home space.
Fixes CVE-2014-3534
Cc: [email protected]
Signed-off-by: Martin Schwidefsky <[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: cherokee_validator_ldap_check (cherokee_validator_ldap_t *ldap,
cherokee_connection_t *conn)
{
int re;
ret_t ret;
size_t size;
char *dn;
LDAPMessage *message;
LDAPMessage *first;
char *attrs[] = { LDAP_NO_ATTRS, NULL };
cherokee_validator_ldap_props_t *props = VAL_LDAP_PROP(ldap);
/* Sanity checks
*/
if ((conn->validator == NULL) ||
cherokee_buffer_is_empty (&conn->validator->user))
return ret_error;
size = cherokee_buffer_cnt_cspn (&conn->validator->user, 0, "*()");
if (size != conn->validator->user.len)
return ret_error;
/* Build filter
*/
ret = init_filter (ldap, props, conn);
if (ret != ret_ok)
return ret;
/* Search
*/
re = ldap_search_s (ldap->conn, props->basedn.buf, LDAP_SCOPE_SUBTREE, ldap->filter.buf, attrs, 0, &message);
if (re != LDAP_SUCCESS) {
LOG_ERROR (CHEROKEE_ERROR_VALIDATOR_LDAP_SEARCH,
props->filter.buf ? props->filter.buf : "");
return ret_error;
}
TRACE (ENTRIES, "subtree search (%s): done\n", ldap->filter.buf ? ldap->filter.buf : "");
/* Check that there a single entry
*/
re = ldap_count_entries (ldap->conn, message);
if (re != 1) {
ldap_msgfree (message);
return ret_not_found;
}
/* Pick up the first one
*/
first = ldap_first_entry (ldap->conn, message);
if (first == NULL) {
ldap_msgfree (message);
return ret_not_found;
}
/* Get DN
*/
dn = ldap_get_dn (ldap->conn, first);
if (dn == NULL) {
ldap_msgfree (message);
return ret_error;
}
ldap_msgfree (message);
/* Check that it's right
*/
ret = validate_dn (props, dn, conn->validator->passwd.buf);
if (ret != ret_ok)
return ret;
/* Disconnect from the LDAP server
*/
re = ldap_unbind_s (ldap->conn);
if (re != LDAP_SUCCESS)
return ret_error;
/* Validated!
*/
TRACE (ENTRIES, "Access to use %s has been granted\n", conn->validator->user.buf);
return ret_ok;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-287'], 'message': 'Prevent the LDAP validator from accepting an empty password.'</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: kg_unseal_v1_iov(krb5_context context,
OM_uint32 *minor_status,
krb5_gss_ctx_id_rec *ctx,
gss_iov_buffer_desc *iov,
int iov_count,
size_t token_wrapper_len,
int *conf_state,
gss_qop_t *qop_state,
int toktype)
{
OM_uint32 code;
gss_iov_buffer_t header;
gss_iov_buffer_t trailer;
unsigned char *ptr;
int sealalg;
int signalg;
krb5_checksum cksum;
krb5_checksum md5cksum;
size_t cksum_len = 0;
size_t conflen = 0;
int direction;
krb5_ui_4 seqnum;
OM_uint32 retval;
size_t sumlen;
krb5_keyusage sign_usage = KG_USAGE_SIGN;
md5cksum.length = cksum.length = 0;
md5cksum.contents = cksum.contents = NULL;
header = kg_locate_header_iov(iov, iov_count, toktype);
assert(header != NULL);
trailer = kg_locate_iov(iov, iov_count, GSS_IOV_BUFFER_TYPE_TRAILER);
if (trailer != NULL && trailer->buffer.length != 0) {
*minor_status = (OM_uint32)KRB5_BAD_MSIZE;
return GSS_S_DEFECTIVE_TOKEN;
}
if (header->buffer.length < token_wrapper_len + 14) {
*minor_status = 0;
return GSS_S_DEFECTIVE_TOKEN;
}
ptr = (unsigned char *)header->buffer.value + token_wrapper_len;
signalg = ptr[0];
signalg |= ptr[1] << 8;
sealalg = ptr[2];
sealalg |= ptr[3] << 8;
if (ptr[4] != 0xFF || ptr[5] != 0xFF) {
*minor_status = 0;
return GSS_S_DEFECTIVE_TOKEN;
}
if (toktype != KG_TOK_WRAP_MSG && sealalg != 0xFFFF) {
*minor_status = 0;
return GSS_S_DEFECTIVE_TOKEN;
}
if (toktype == KG_TOK_WRAP_MSG &&
!(sealalg == 0xFFFF || sealalg == ctx->sealalg)) {
*minor_status = 0;
return GSS_S_DEFECTIVE_TOKEN;
}
if ((ctx->sealalg == SEAL_ALG_NONE && signalg > 1) ||
(ctx->sealalg == SEAL_ALG_1 && signalg != SGN_ALG_3) ||
(ctx->sealalg == SEAL_ALG_DES3KD &&
signalg != SGN_ALG_HMAC_SHA1_DES3_KD)||
(ctx->sealalg == SEAL_ALG_MICROSOFT_RC4 &&
signalg != SGN_ALG_HMAC_MD5)) {
*minor_status = 0;
return GSS_S_DEFECTIVE_TOKEN;
}
switch (signalg) {
case SGN_ALG_DES_MAC_MD5:
case SGN_ALG_MD2_5:
case SGN_ALG_HMAC_MD5:
cksum_len = 8;
if (toktype != KG_TOK_WRAP_MSG)
sign_usage = 15;
break;
case SGN_ALG_3:
cksum_len = 16;
break;
case SGN_ALG_HMAC_SHA1_DES3_KD:
cksum_len = 20;
break;
default:
*minor_status = 0;
return GSS_S_DEFECTIVE_TOKEN;
}
/* get the token parameters */
code = kg_get_seq_num(context, ctx->seq, ptr + 14, ptr + 6, &direction,
&seqnum);
if (code != 0) {
*minor_status = code;
return GSS_S_BAD_SIG;
}
/* decode the message, if SEAL */
if (toktype == KG_TOK_WRAP_MSG) {
if (sealalg != 0xFFFF) {
if (ctx->sealalg == SEAL_ALG_MICROSOFT_RC4) {
unsigned char bigend_seqnum[4];
krb5_keyblock *enc_key;
size_t i;
store_32_be(seqnum, bigend_seqnum);
code = krb5_k_key_keyblock(context, ctx->enc, &enc_key);
if (code != 0) {
retval = GSS_S_FAILURE;
goto cleanup;
}
assert(enc_key->length == 16);
for (i = 0; i < enc_key->length; i++)
((char *)enc_key->contents)[i] ^= 0xF0;
code = kg_arcfour_docrypt_iov(context, enc_key, 0,
&bigend_seqnum[0], 4,
iov, iov_count);
krb5_free_keyblock(context, enc_key);
} else {
code = kg_decrypt_iov(context, 0,
((ctx->gss_flags & GSS_C_DCE_STYLE) != 0),
0 /*EC*/, 0 /*RRC*/,
ctx->enc, KG_USAGE_SEAL, NULL,
iov, iov_count);
}
if (code != 0) {
retval = GSS_S_FAILURE;
goto cleanup;
}
}
conflen = kg_confounder_size(context, ctx->enc->keyblock.enctype);
}
if (header->buffer.length != token_wrapper_len + 14 + cksum_len + conflen) {
retval = GSS_S_DEFECTIVE_TOKEN;
goto cleanup;
}
/* compute the checksum of the message */
/* initialize the checksum */
switch (signalg) {
case SGN_ALG_DES_MAC_MD5:
case SGN_ALG_MD2_5:
case SGN_ALG_DES_MAC:
case SGN_ALG_3:
md5cksum.checksum_type = CKSUMTYPE_RSA_MD5;
break;
case SGN_ALG_HMAC_MD5:
md5cksum.checksum_type = CKSUMTYPE_HMAC_MD5_ARCFOUR;
break;
case SGN_ALG_HMAC_SHA1_DES3_KD:
md5cksum.checksum_type = CKSUMTYPE_HMAC_SHA1_DES3;
break;
default:
abort();
}
code = krb5_c_checksum_length(context, md5cksum.checksum_type, &sumlen);
if (code != 0) {
retval = GSS_S_FAILURE;
goto cleanup;
}
md5cksum.length = sumlen;
/* compute the checksum of the message */
code = kg_make_checksum_iov_v1(context, md5cksum.checksum_type,
cksum_len, ctx->seq, ctx->enc,
sign_usage, iov, iov_count, toktype,
&md5cksum);
if (code != 0) {
retval = GSS_S_FAILURE;
goto cleanup;
}
switch (signalg) {
case SGN_ALG_DES_MAC_MD5:
case SGN_ALG_3:
code = kg_encrypt_inplace(context, ctx->seq, KG_USAGE_SEAL,
(g_OID_equal(ctx->mech_used,
gss_mech_krb5_old) ?
ctx->seq->keyblock.contents : NULL),
md5cksum.contents, 16);
if (code != 0) {
retval = GSS_S_FAILURE;
goto cleanup;
}
cksum.length = cksum_len;
cksum.contents = md5cksum.contents + 16 - cksum.length;
code = k5_bcmp(cksum.contents, ptr + 14, cksum.length);
break;
case SGN_ALG_HMAC_SHA1_DES3_KD:
case SGN_ALG_HMAC_MD5:
code = k5_bcmp(md5cksum.contents, ptr + 14, cksum_len);
break;
default:
code = 0;
retval = GSS_S_DEFECTIVE_TOKEN;
goto cleanup;
break;
}
if (code != 0) {
code = 0;
retval = GSS_S_BAD_SIG;
goto cleanup;
}
/*
* For GSS_C_DCE_STYLE, the caller manages the padding, because the
* pad length is in the RPC PDU. The value of the padding may be
* uninitialized. For normal GSS, the last bytes of the decrypted
* data contain the pad length. kg_fixup_padding_iov() will find
* this and fixup the last data IOV appropriately.
*/
if (toktype == KG_TOK_WRAP_MSG &&
(ctx->gss_flags & GSS_C_DCE_STYLE) == 0) {
retval = kg_fixup_padding_iov(&code, iov, iov_count);
if (retval != GSS_S_COMPLETE)
goto cleanup;
}
if (conf_state != NULL)
*conf_state = (sealalg != 0xFFFF);
if (qop_state != NULL)
*qop_state = GSS_C_QOP_DEFAULT;
if ((ctx->initiate && direction != 0xff) ||
(!ctx->initiate && direction != 0)) {
*minor_status = (OM_uint32)G_BAD_DIRECTION;
retval = GSS_S_BAD_SIG;
}
code = 0;
retval = g_seqstate_check(ctx->seqstate, (uint64_t)seqnum);
cleanup:
krb5_free_checksum_contents(context, &md5cksum);
*minor_status = code;
return retval;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-125'], 'message': 'Handle invalid RFC 1964 tokens [CVE-2014-4341...]
Detect the following cases which would otherwise cause invalid memory
accesses and/or integer underflow:
* An RFC 1964 token being processed by an RFC 4121-only context
[CVE-2014-4342]
* A header with fewer than 22 bytes after the token ID or an
incomplete checksum [CVE-2014-4341 CVE-2014-4342]
* A ciphertext shorter than the confounder [CVE-2014-4341]
* A declared padding length longer than the plaintext [CVE-2014-4341]
If we detect a bad pad byte, continue on to compute the checksum to
avoid creating a padding oracle, but treat the checksum as invalid
even if it compares equal.
CVE-2014-4341:
In MIT krb5, an unauthenticated remote attacker with the ability to
inject packets into a legitimately established GSSAPI application
session can cause a program crash due to invalid memory references
when attempting to read beyond the end of a buffer.
CVSSv2 Vector: AV:N/AC:M/Au:N/C:N/I:N/A:P/E:POC/RL:OF/RC:C
CVE-2014-4342:
In MIT krb5 releases krb5-1.7 and later, an unauthenticated remote
attacker with the ability to inject packets into a legitimately
established GSSAPI application session can cause a program crash due
to invalid memory references when reading beyond the end of a buffer
or by causing a null pointer dereference.
CVSSv2 Vector: AV:N/AC:M/Au:N/C:N/I:N/A:P/E:POC/RL:OF/RC:C
[[email protected]: CVE summaries, CVSS]
ticket: 7949 (new)
subject: Handle invalid RFC 1964 tokens [CVE-2014-4341 CVE-2014-4342]
taget_version: 1.12.2
tags: pullup'</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: rs_filter_graph(RSFilter *filter)
{
g_return_if_fail(RS_IS_FILTER(filter));
GString *str = g_string_new("digraph G {\n");
rs_filter_graph_helper(str, filter);
g_string_append_printf(str, "}\n");
g_file_set_contents("/tmp/rs-filter-graph", str->str, str->len, NULL);
if (0 != system("dot -Tpng >/tmp/rs-filter-graph.png </tmp/rs-filter-graph"))
g_warning("Calling dot failed");
if (0 != system("gnome-open /tmp/rs-filter-graph.png"))
g_warning("Calling gnome-open failed.");
g_string_free(str, TRUE);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-59'], 'message': 'Fixes insecure use of temporary file (CVE-2014-4978).'</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: acc_ctx_cont(OM_uint32 *minstat,
gss_buffer_t buf,
gss_ctx_id_t *ctx,
gss_buffer_t *responseToken,
gss_buffer_t *mechListMIC,
OM_uint32 *negState,
send_token_flag *return_token)
{
OM_uint32 ret, tmpmin;
gss_OID supportedMech;
spnego_gss_ctx_id_t sc;
unsigned int len;
unsigned char *ptr, *bufstart;
sc = (spnego_gss_ctx_id_t)*ctx;
ret = GSS_S_DEFECTIVE_TOKEN;
*negState = REJECT;
*minstat = 0;
supportedMech = GSS_C_NO_OID;
*return_token = ERROR_TOKEN_SEND;
*responseToken = *mechListMIC = GSS_C_NO_BUFFER;
ptr = bufstart = buf->value;
#define REMAIN (buf->length - (ptr - bufstart))
if (REMAIN > INT_MAX)
return GSS_S_DEFECTIVE_TOKEN;
/*
* Attempt to work with old Sun SPNEGO.
*/
if (*ptr == HEADER_ID) {
ret = g_verify_token_header(gss_mech_spnego,
&len, &ptr, 0, REMAIN);
if (ret) {
*minstat = ret;
return GSS_S_DEFECTIVE_TOKEN;
}
}
if (*ptr != (CONTEXT | 0x01)) {
return GSS_S_DEFECTIVE_TOKEN;
}
ret = get_negTokenResp(minstat, ptr, REMAIN,
negState, &supportedMech,
responseToken, mechListMIC);
if (ret != GSS_S_COMPLETE)
goto cleanup;
if (*responseToken == GSS_C_NO_BUFFER &&
*mechListMIC == GSS_C_NO_BUFFER) {
ret = GSS_S_DEFECTIVE_TOKEN;
goto cleanup;
}
if (supportedMech != GSS_C_NO_OID) {
ret = GSS_S_DEFECTIVE_TOKEN;
goto cleanup;
}
sc->firstpass = 0;
*negState = ACCEPT_INCOMPLETE;
*return_token = CONT_TOKEN_SEND;
cleanup:
if (supportedMech != GSS_C_NO_OID) {
generic_gss_release_oid(&tmpmin, &supportedMech);
}
return ret;
#undef REMAIN
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'Fix null deref in SPNEGO acceptor [CVE-2014-4344]
When processing a continuation token, acc_ctx_cont was dereferencing
the initial byte of the token without checking the length. This could
result in a null dereference.
CVE-2014-4344:
In MIT krb5 1.5 and newer, an unauthenticated or partially
authenticated remote attacker can cause a NULL dereference and
application crash during a SPNEGO negotiation by sending an empty
token as the second or later context token from initiator to acceptor.
The attacker must provide at least one valid context token in the
security context negotiation before sending the empty token. This can
be done by an unauthenticated attacker by forcing SPNEGO to
renegotiate the underlying mechanism, or by using IAKERB to wrap an
unauthenticated AS-REQ as the first token.
CVSSv2 Vector: AV:N/AC:L/Au:N/C:N/I:N/A:C/E:POC/RL:OF/RC:C
[[email protected]: CVE summary, CVSSv2 vector]
ticket: 7970 (new)
subject: NULL dereference in SPNEGO acceptor for continuation tokens [CVE-2014-4344]
target_version: 1.12.2
tags: pullup'</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: expand_string_integer(uschar *string, BOOL isplus)
{
int_eximarith_t value;
uschar *s = expand_string(string);
uschar *msg = US"invalid integer \"%s\"";
uschar *endptr;
/* If expansion failed, expand_string_message will be set. */
if (s == NULL) return -1;
/* On an overflow, strtol() returns LONG_MAX or LONG_MIN, and sets errno
to ERANGE. When there isn't an overflow, errno is not changed, at least on some
systems, so we set it zero ourselves. */
errno = 0;
expand_string_message = NULL; /* Indicates no error */
/* Before Exim 4.64, strings consisting entirely of whitespace compared
equal to 0. Unfortunately, people actually relied upon that, so preserve
the behaviour explicitly. Stripping leading whitespace is a harmless
noop change since strtol skips it anyway (provided that there is a number
to find at all). */
if (isspace(*s))
{
while (isspace(*s)) ++s;
if (*s == '\0')
{
DEBUG(D_expand)
debug_printf("treating blank string as number 0\n");
return 0;
}
}
value = strtoll(CS s, CSS &endptr, 10);
if (endptr == s)
{
msg = US"integer expected but \"%s\" found";
}
else if (value < 0 && isplus)
{
msg = US"non-negative integer expected but \"%s\" found";
}
else
{
switch (tolower(*endptr))
{
default:
break;
case 'k':
if (value > EXIM_ARITH_MAX/1024 || value < EXIM_ARITH_MIN/1024) errno = ERANGE;
else value *= 1024;
endptr++;
break;
case 'm':
if (value > EXIM_ARITH_MAX/(1024*1024) || value < EXIM_ARITH_MIN/(1024*1024)) errno = ERANGE;
else value *= 1024*1024;
endptr++;
break;
case 'g':
if (value > EXIM_ARITH_MAX/(1024*1024*1024) || value < EXIM_ARITH_MIN/(1024*1024*1024)) errno = ERANGE;
else value *= 1024*1024*1024;
endptr++;
break;
}
if (errno == ERANGE)
msg = US"absolute value of integer \"%s\" is too large (overflow)";
else
{
while (isspace(*endptr)) endptr++;
if (*endptr == 0) return value;
}
}
expand_string_message = string_sprintf(CS msg, s);
return -2;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Only expand integers for integer math once'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void sctp_assoc_update(struct sctp_association *asoc,
struct sctp_association *new)
{
struct sctp_transport *trans;
struct list_head *pos, *temp;
/* Copy in new parameters of peer. */
asoc->c = new->c;
asoc->peer.rwnd = new->peer.rwnd;
asoc->peer.sack_needed = new->peer.sack_needed;
asoc->peer.i = new->peer.i;
sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
asoc->peer.i.initial_tsn, GFP_ATOMIC);
/* Remove any peer addresses not present in the new association. */
list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) {
trans = list_entry(pos, struct sctp_transport, transports);
if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr)) {
sctp_assoc_rm_peer(asoc, trans);
continue;
}
if (asoc->state >= SCTP_STATE_ESTABLISHED)
sctp_transport_reset(trans);
}
/* If the case is A (association restart), use
* initial_tsn as next_tsn. If the case is B, use
* current next_tsn in case data sent to peer
* has been discarded and needs retransmission.
*/
if (asoc->state >= SCTP_STATE_ESTABLISHED) {
asoc->next_tsn = new->next_tsn;
asoc->ctsn_ack_point = new->ctsn_ack_point;
asoc->adv_peer_ack_point = new->adv_peer_ack_point;
/* Reinitialize SSN for both local streams
* and peer's streams.
*/
sctp_ssnmap_clear(asoc->ssnmap);
/* Flush the ULP reassembly and ordered queue.
* Any data there will now be stale and will
* cause problems.
*/
sctp_ulpq_flush(&asoc->ulpq);
/* reset the overall association error count so
* that the restarted association doesn't get torn
* down on the next retransmission timer.
*/
asoc->overall_error_count = 0;
} else {
/* Add any peer addresses from the new association. */
list_for_each_entry(trans, &new->peer.transport_addr_list,
transports) {
if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr))
sctp_assoc_add_peer(asoc, &trans->ipaddr,
GFP_ATOMIC, trans->state);
}
asoc->ctsn_ack_point = asoc->next_tsn - 1;
asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
if (!asoc->ssnmap) {
/* Move the ssnmap. */
asoc->ssnmap = new->ssnmap;
new->ssnmap = NULL;
}
if (!asoc->assoc_id) {
/* get a new association id since we don't have one
* yet.
*/
sctp_assoc_set_id(asoc, GFP_ATOMIC);
}
}
/* SCTP-AUTH: Save the peer parameters from the new associations
* and also move the association shared keys over
*/
kfree(asoc->peer.peer_random);
asoc->peer.peer_random = new->peer.peer_random;
new->peer.peer_random = NULL;
kfree(asoc->peer.peer_chunks);
asoc->peer.peer_chunks = new->peer.peer_chunks;
new->peer.peer_chunks = NULL;
kfree(asoc->peer.peer_hmacs);
asoc->peer.peer_hmacs = new->peer.peer_hmacs;
new->peer.peer_hmacs = NULL;
sctp_auth_key_put(asoc->asoc_shared_key);
sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-476'], 'message': 'net: sctp: inherit auth_capable on INIT collisions
Jason reported an oops caused by SCTP on his ARM machine with
SCTP authentication enabled:
Internal error: Oops: 17 [#1] ARM
CPU: 0 PID: 104 Comm: sctp-test Not tainted 3.13.0-68744-g3632f30c9b20-dirty #1
task: c6eefa40 ti: c6f52000 task.ti: c6f52000
PC is at sctp_auth_calculate_hmac+0xc4/0x10c
LR is at sg_init_table+0x20/0x38
pc : [<c024bb80>] lr : [<c00f32dc>] psr: 40000013
sp : c6f538e8 ip : 00000000 fp : c6f53924
r10: c6f50d80 r9 : 00000000 r8 : 00010000
r7 : 00000000 r6 : c7be4000 r5 : 00000000 r4 : c6f56254
r3 : c00c8170 r2 : 00000001 r1 : 00000008 r0 : c6f1e660
Flags: nZcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user
Control: 0005397f Table: 06f28000 DAC: 00000015
Process sctp-test (pid: 104, stack limit = 0xc6f521c0)
Stack: (0xc6f538e8 to 0xc6f54000)
[...]
Backtrace:
[<c024babc>] (sctp_auth_calculate_hmac+0x0/0x10c) from [<c0249af8>] (sctp_packet_transmit+0x33c/0x5c8)
[<c02497bc>] (sctp_packet_transmit+0x0/0x5c8) from [<c023e96c>] (sctp_outq_flush+0x7fc/0x844)
[<c023e170>] (sctp_outq_flush+0x0/0x844) from [<c023ef78>] (sctp_outq_uncork+0x24/0x28)
[<c023ef54>] (sctp_outq_uncork+0x0/0x28) from [<c0234364>] (sctp_side_effects+0x1134/0x1220)
[<c0233230>] (sctp_side_effects+0x0/0x1220) from [<c02330b0>] (sctp_do_sm+0xac/0xd4)
[<c0233004>] (sctp_do_sm+0x0/0xd4) from [<c023675c>] (sctp_assoc_bh_rcv+0x118/0x160)
[<c0236644>] (sctp_assoc_bh_rcv+0x0/0x160) from [<c023d5bc>] (sctp_inq_push+0x6c/0x74)
[<c023d550>] (sctp_inq_push+0x0/0x74) from [<c024a6b0>] (sctp_rcv+0x7d8/0x888)
While we already had various kind of bugs in that area
ec0223ec48a9 ("net: sctp: fix sctp_sf_do_5_1D_ce to verify if
we/peer is AUTH capable") and b14878ccb7fa ("net: sctp: cache
auth_enable per endpoint"), this one is a bit of a different
kind.
Giving a bit more background on why SCTP authentication is
needed can be found in RFC4895:
SCTP uses 32-bit verification tags to protect itself against
blind attackers. These values are not changed during the
lifetime of an SCTP association.
Looking at new SCTP extensions, there is the need to have a
method of proving that an SCTP chunk(s) was really sent by
the original peer that started the association and not by a
malicious attacker.
To cause this bug, we're triggering an INIT collision between
peers; normal SCTP handshake where both sides intent to
authenticate packets contains RANDOM; CHUNKS; HMAC-ALGO
parameters that are being negotiated among peers:
---------- INIT[RANDOM; CHUNKS; HMAC-ALGO] ---------->
<------- INIT-ACK[RANDOM; CHUNKS; HMAC-ALGO] ---------
-------------------- COOKIE-ECHO -------------------->
<-------------------- COOKIE-ACK ---------------------
RFC4895 says that each endpoint therefore knows its own random
number and the peer's random number *after* the association
has been established. The local and peer's random number along
with the shared key are then part of the secret used for
calculating the HMAC in the AUTH chunk.
Now, in our scenario, we have 2 threads with 1 non-blocking
SEQ_PACKET socket each, setting up common shared SCTP_AUTH_KEY
and SCTP_AUTH_ACTIVE_KEY properly, and each of them calling
sctp_bindx(3), listen(2) and connect(2) against each other,
thus the handshake looks similar to this, e.g.:
---------- INIT[RANDOM; CHUNKS; HMAC-ALGO] ---------->
<------- INIT-ACK[RANDOM; CHUNKS; HMAC-ALGO] ---------
<--------- INIT[RANDOM; CHUNKS; HMAC-ALGO] -----------
-------- INIT-ACK[RANDOM; CHUNKS; HMAC-ALGO] -------->
...
Since such collisions can also happen with verification tags,
the RFC4895 for AUTH rather vaguely says under section 6.1:
In case of INIT collision, the rules governing the handling
of this Random Number follow the same pattern as those for
the Verification Tag, as explained in Section 5.2.4 of
RFC 2960 [5]. Therefore, each endpoint knows its own Random
Number and the peer's Random Number after the association
has been established.
In RFC2960, section 5.2.4, we're eventually hitting Action B:
B) In this case, both sides may be attempting to start an
association at about the same time but the peer endpoint
started its INIT after responding to the local endpoint's
INIT. Thus it may have picked a new Verification Tag not
being aware of the previous Tag it had sent this endpoint.
The endpoint should stay in or enter the ESTABLISHED
state but it MUST update its peer's Verification Tag from
the State Cookie, stop any init or cookie timers that may
running and send a COOKIE ACK.
In other words, the handling of the Random parameter is the
same as behavior for the Verification Tag as described in
Action B of section 5.2.4.
Looking at the code, we exactly hit the sctp_sf_do_dupcook_b()
case which triggers an SCTP_CMD_UPDATE_ASSOC command to the
side effect interpreter, and in fact it properly copies over
peer_{random, hmacs, chunks} parameters from the newly created
association to update the existing one.
Also, the old asoc_shared_key is being released and based on
the new params, sctp_auth_asoc_init_active_key() updated.
However, the issue observed in this case is that the previous
asoc->peer.auth_capable was 0, and has *not* been updated, so
that instead of creating a new secret, we're doing an early
return from the function sctp_auth_asoc_init_active_key()
leaving asoc->asoc_shared_key as NULL. However, we now have to
authenticate chunks from the updated chunk list (e.g. COOKIE-ACK).
That in fact causes the server side when responding with ...
<------------------ AUTH; COOKIE-ACK -----------------
... to trigger a NULL pointer dereference, since in
sctp_packet_transmit(), it discovers that an AUTH chunk is
being queued for xmit, and thus it calls sctp_auth_calculate_hmac().
Since the asoc->active_key_id is still inherited from the
endpoint, and the same as encoded into the chunk, it uses
asoc->asoc_shared_key, which is still NULL, as an asoc_key
and dereferences it in ...
crypto_hash_setkey(desc.tfm, &asoc_key->data[0], asoc_key->len)
... causing an oops. All this happens because sctp_make_cookie_ack()
called with the *new* association has the peer.auth_capable=1
and therefore marks the chunk with auth=1 after checking
sctp_auth_send_cid(), but it is *actually* sent later on over
the then *updated* association's transport that didn't initialize
its shared key due to peer.auth_capable=0. Since control chunks
in that case are not sent by the temporary association which
are scheduled for deletion, they are issued for xmit via
SCTP_CMD_REPLY in the interpreter with the context of the
*updated* association. peer.auth_capable was 0 in the updated
association (which went from COOKIE_WAIT into ESTABLISHED state),
since all previous processing that performed sctp_process_init()
was being done on temporary associations, that we eventually
throw away each time.
The correct fix is to update to the new peer.auth_capable
value as well in the collision case via sctp_assoc_update(),
so that in case the collision migrated from 0 -> 1,
sctp_auth_asoc_init_active_key() can properly recalculate
the secret. This therefore fixes the observed server panic.
Fixes: 730fc3d05cd4 ("[SCTP]: Implete SCTP-AUTH parameter processing")
Reported-by: Jason Gunthorpe <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Tested-by: Jason Gunthorpe <[email protected]>
Cc: Vlad Yasevich <[email protected]>
Acked-by: Vlad Yasevich <[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: gcry_mpi_powm (gcry_mpi_t res,
gcry_mpi_t base, gcry_mpi_t expo, gcry_mpi_t mod)
{
/* Pointer to the limbs of the arguments, their size and signs. */
mpi_ptr_t rp, ep, mp, bp;
mpi_size_t esize, msize, bsize, rsize;
int msign, bsign, rsign;
/* Flags telling the secure allocation status of the arguments. */
int esec, msec, bsec;
/* Size of the result including space for temporary values. */
mpi_size_t size;
/* Helper. */
int mod_shift_cnt;
int negative_result;
mpi_ptr_t mp_marker = NULL;
mpi_ptr_t bp_marker = NULL;
mpi_ptr_t ep_marker = NULL;
mpi_ptr_t xp_marker = NULL;
unsigned int mp_nlimbs = 0;
unsigned int bp_nlimbs = 0;
unsigned int ep_nlimbs = 0;
unsigned int xp_nlimbs = 0;
mpi_ptr_t tspace = NULL;
mpi_size_t tsize = 0;
esize = expo->nlimbs;
msize = mod->nlimbs;
size = 2 * msize;
msign = mod->sign;
esec = mpi_is_secure(expo);
msec = mpi_is_secure(mod);
bsec = mpi_is_secure(base);
rp = res->d;
ep = expo->d;
if (!msize)
_gcry_divide_by_zero();
if (!esize)
{
/* Exponent is zero, result is 1 mod MOD, i.e., 1 or 0 depending
on if MOD equals 1. */
res->nlimbs = (msize == 1 && mod->d[0] == 1) ? 0 : 1;
if (res->nlimbs)
{
RESIZE_IF_NEEDED (res, 1);
rp = res->d;
rp[0] = 1;
}
res->sign = 0;
goto leave;
}
/* Normalize MOD (i.e. make its most significant bit set) as
required by mpn_divrem. This will make the intermediate values
in the calculation slightly larger, but the correct result is
obtained after a final reduction using the original MOD value. */
mp_nlimbs = msec? msize:0;
mp = mp_marker = mpi_alloc_limb_space(msize, msec);
count_leading_zeros (mod_shift_cnt, mod->d[msize-1]);
if (mod_shift_cnt)
_gcry_mpih_lshift (mp, mod->d, msize, mod_shift_cnt);
else
MPN_COPY( mp, mod->d, msize );
bsize = base->nlimbs;
bsign = base->sign;
if (bsize > msize)
{
/* The base is larger than the module. Reduce it.
Allocate (BSIZE + 1) with space for remainder and quotient.
(The quotient is (bsize - msize + 1) limbs.) */
bp_nlimbs = bsec ? (bsize + 1):0;
bp = bp_marker = mpi_alloc_limb_space( bsize + 1, bsec );
MPN_COPY ( bp, base->d, bsize );
/* We don't care about the quotient, store it above the
* remainder, at BP + MSIZE. */
_gcry_mpih_divrem( bp + msize, 0, bp, bsize, mp, msize );
bsize = msize;
/* Canonicalize the base, since we are going to multiply with it
quite a few times. */
MPN_NORMALIZE( bp, bsize );
}
else
bp = base->d;
if (!bsize)
{
res->nlimbs = 0;
res->sign = 0;
goto leave;
}
/* Make BASE, EXPO and MOD not overlap with RES. */
if ( rp == bp )
{
/* RES and BASE are identical. Allocate temp. space for BASE. */
gcry_assert (!bp_marker);
bp_nlimbs = bsec? bsize:0;
bp = bp_marker = mpi_alloc_limb_space( bsize, bsec );
MPN_COPY(bp, rp, bsize);
}
if ( rp == ep )
{
/* RES and EXPO are identical. Allocate temp. space for EXPO. */
ep_nlimbs = esec? esize:0;
ep = ep_marker = mpi_alloc_limb_space( esize, esec );
MPN_COPY(ep, rp, esize);
}
if ( rp == mp )
{
/* RES and MOD are identical. Allocate temporary space for MOD.*/
gcry_assert (!mp_marker);
mp_nlimbs = msec?msize:0;
mp = mp_marker = mpi_alloc_limb_space( msize, msec );
MPN_COPY(mp, rp, msize);
}
/* Copy base to the result. */
if (res->alloced < size)
{
mpi_resize (res, size);
rp = res->d;
}
MPN_COPY ( rp, bp, bsize );
rsize = bsize;
rsign = bsign;
/* Main processing. */
{
mpi_size_t i;
mpi_ptr_t xp;
int c;
mpi_limb_t e;
mpi_limb_t carry_limb;
struct karatsuba_ctx karactx;
xp_nlimbs = msec? (2 * (msize + 1)):0;
xp = xp_marker = mpi_alloc_limb_space( 2 * (msize + 1), msec );
memset( &karactx, 0, sizeof karactx );
negative_result = (ep[0] & 1) && base->sign;
i = esize - 1;
e = ep[i];
count_leading_zeros (c, e);
e = (e << c) << 1; /* Shift the expo bits to the left, lose msb. */
c = BITS_PER_MPI_LIMB - 1 - c;
/* Main loop.
Make the result be pointed to alternately by XP and RP. This
helps us avoid block copying, which would otherwise be
necessary with the overlap restrictions of
_gcry_mpih_divmod. With 50% probability the result after this
loop will be in the area originally pointed by RP (==RES->d),
and with 50% probability in the area originally pointed to by XP. */
for (;;)
{
while (c)
{
mpi_ptr_t tp;
mpi_size_t xsize;
/*mpih_mul_n(xp, rp, rp, rsize);*/
if ( rsize < KARATSUBA_THRESHOLD )
_gcry_mpih_sqr_n_basecase( xp, rp, rsize );
else
{
if ( !tspace )
{
tsize = 2 * rsize;
tspace = mpi_alloc_limb_space( tsize, 0 );
}
else if ( tsize < (2*rsize) )
{
_gcry_mpi_free_limb_space (tspace, 0);
tsize = 2 * rsize;
tspace = mpi_alloc_limb_space (tsize, 0 );
}
_gcry_mpih_sqr_n (xp, rp, rsize, tspace);
}
xsize = 2 * rsize;
if ( xsize > msize )
{
_gcry_mpih_divrem(xp + msize, 0, xp, xsize, mp, msize);
xsize = msize;
}
tp = rp; rp = xp; xp = tp;
rsize = xsize;
/* To mitigate the Yarom/Falkner flush+reload cache
* side-channel attack on the RSA secret exponent, we do
* the multiplication regardless of the value of the
* high-bit of E. But to avoid this performance penalty
* we do it only if the exponent has been stored in secure
* memory and we can thus assume it is a secret exponent. */
if (esec || (mpi_limb_signed_t)e < 0)
{
/*mpih_mul( xp, rp, rsize, bp, bsize );*/
if( bsize < KARATSUBA_THRESHOLD )
_gcry_mpih_mul ( xp, rp, rsize, bp, bsize );
else
_gcry_mpih_mul_karatsuba_case (xp, rp, rsize, bp, bsize,
&karactx);
xsize = rsize + bsize;
if ( xsize > msize )
{
_gcry_mpih_divrem(xp + msize, 0, xp, xsize, mp, msize);
xsize = msize;
}
}
if ( (mpi_limb_signed_t)e < 0 )
{
tp = rp; rp = xp; xp = tp;
rsize = xsize;
}
e <<= 1;
c--;
}
i--;
if ( i < 0 )
break;
e = ep[i];
c = BITS_PER_MPI_LIMB;
}
/* We shifted MOD, the modulo reduction argument, left
MOD_SHIFT_CNT steps. Adjust the result by reducing it with the
original MOD.
Also make sure the result is put in RES->d (where it already
might be, see above). */
if ( mod_shift_cnt )
{
carry_limb = _gcry_mpih_lshift( res->d, rp, rsize, mod_shift_cnt);
rp = res->d;
if ( carry_limb )
{
rp[rsize] = carry_limb;
rsize++;
}
}
else if (res->d != rp)
{
MPN_COPY (res->d, rp, rsize);
rp = res->d;
}
if ( rsize >= msize )
{
_gcry_mpih_divrem(rp + msize, 0, rp, rsize, mp, msize);
rsize = msize;
}
/* Remove any leading zero words from the result. */
if ( mod_shift_cnt )
_gcry_mpih_rshift( rp, rp, rsize, mod_shift_cnt);
MPN_NORMALIZE (rp, rsize);
_gcry_mpih_release_karatsuba_ctx (&karactx );
}
/* Fixup for negative results. */
if ( negative_result && rsize )
{
if ( mod_shift_cnt )
_gcry_mpih_rshift( mp, mp, msize, mod_shift_cnt);
_gcry_mpih_sub( rp, mp, msize, rp, rsize);
rsize = msize;
rsign = msign;
MPN_NORMALIZE(rp, rsize);
}
gcry_assert (res->d == rp);
res->nlimbs = rsize;
res->sign = rsign;
leave:
if (mp_marker)
_gcry_mpi_free_limb_space( mp_marker, mp_nlimbs );
if (bp_marker)
_gcry_mpi_free_limb_space( bp_marker, bp_nlimbs );
if (ep_marker)
_gcry_mpi_free_limb_space( ep_marker, ep_nlimbs );
if (xp_marker)
_gcry_mpi_free_limb_space( xp_marker, xp_nlimbs );
if (tspace)
_gcry_mpi_free_limb_space( tspace, 0 );
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'mpi: mpi-pow improvement.
* mpi/mpi-pow.c (gcry_mpi_powm): New implementation of left-to-right
k-ary exponentiation.
--
Signed-off-by: NIIBE Yutaka <[email protected]>
For the Yarom/Falkner flush+reload cache side-channel attack, we
changed the code so that it always calls the multiplication routine
(even if we can skip it to get result). This results some performance
regression.
This change is for recovering performance with efficient algorithm.
(cherry picked from commit 45aa6131e93fac89d46733b3436d960f35fb99b2)'</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: getword(f, word, newlinep, filename)
FILE *f;
char *word;
int *newlinep;
char *filename;
{
int c, len, escape;
int quoted, comment;
int value, digit, got, n;
#define isoctal(c) ((c) >= '0' && (c) < '8')
*newlinep = 0;
len = 0;
escape = 0;
comment = 0;
quoted = 0;
/*
* First skip white-space and comments.
*/
for (;;) {
c = getc(f);
if (c == EOF)
break;
/*
* A newline means the end of a comment; backslash-newline
* is ignored. Note that we cannot have escape && comment.
*/
if (c == '\n') {
if (!escape) {
*newlinep = 1;
comment = 0;
} else
escape = 0;
continue;
}
/*
* Ignore characters other than newline in a comment.
*/
if (comment)
continue;
/*
* If this character is escaped, we have a word start.
*/
if (escape)
break;
/*
* If this is the escape character, look at the next character.
*/
if (c == '\\') {
escape = 1;
continue;
}
/*
* If this is the start of a comment, ignore the rest of the line.
*/
if (c == '#') {
comment = 1;
continue;
}
/*
* A non-whitespace character is the start of a word.
*/
if (!isspace(c))
break;
}
/*
* Process characters until the end of the word.
*/
while (c != EOF) {
if (escape) {
/*
* This character is escaped: backslash-newline is ignored,
* various other characters indicate particular values
* as for C backslash-escapes.
*/
escape = 0;
if (c == '\n') {
c = getc(f);
continue;
}
got = 0;
switch (c) {
case 'a':
value = '\a';
break;
case 'b':
value = '\b';
break;
case 'f':
value = '\f';
break;
case 'n':
value = '\n';
break;
case 'r':
value = '\r';
break;
case 's':
value = ' ';
break;
case 't':
value = '\t';
break;
default:
if (isoctal(c)) {
/*
* \ddd octal sequence
*/
value = 0;
for (n = 0; n < 3 && isoctal(c); ++n) {
value = (value << 3) + (c & 07);
c = getc(f);
}
got = 1;
break;
}
if (c == 'x') {
/*
* \x<hex_string> sequence
*/
value = 0;
c = getc(f);
for (n = 0; n < 2 && isxdigit(c); ++n) {
digit = toupper(c) - '0';
if (digit > 10)
digit += '0' + 10 - 'A';
value = (value << 4) + digit;
c = getc (f);
}
got = 1;
break;
}
/*
* Otherwise the character stands for itself.
*/
value = c;
break;
}
/*
* Store the resulting character for the escape sequence.
*/
if (len < MAXWORDLEN-1)
word[len] = value;
++len;
if (!got)
c = getc(f);
continue;
}
/*
* Backslash starts a new escape sequence.
*/
if (c == '\\') {
escape = 1;
c = getc(f);
continue;
}
/*
* Not escaped: check for the start or end of a quoted
* section and see if we've reached the end of the word.
*/
if (quoted) {
if (c == quoted) {
quoted = 0;
c = getc(f);
continue;
}
} else if (c == '"' || c == '\'') {
quoted = c;
c = getc(f);
continue;
} else if (isspace(c) || c == '#') {
ungetc (c, f);
break;
}
/*
* An ordinary character: store it in the word and get another.
*/
if (len < MAXWORDLEN-1)
word[len] = c;
++len;
c = getc(f);
}
/*
* End of the word: check for errors.
*/
if (c == EOF) {
if (ferror(f)) {
if (errno == 0)
errno = EIO;
option_error("Error reading %s: %m", filename);
die(1);
}
/*
* If len is zero, then we didn't find a word before the
* end of the file.
*/
if (len == 0)
return 0;
if (quoted)
option_error("warning: quoted word runs to end of file (%.20s...)",
filename, word);
}
/*
* Warn if the word was too long, and append a terminating null.
*/
if (len >= MAXWORDLEN) {
option_error("warning: word in file %s too long (%.20s...)",
filename, word);
len = MAXWORDLEN - 1;
}
word[len] = 0;
return 1;
#undef isoctal
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-415', 'CWE-119'], 'message': 'pppd: Eliminate potential integer overflow in option parsing
When we are reading in a word from an options file, we maintain a count
of the length we have seen so far in 'len', which is an int. When len
exceeds MAXWORDLEN - 1 (i.e. 1023) we cease storing characters in the
buffer but we continue to increment len. Since len is an int, it will
wrap around to -2147483648 after it reaches 2147483647. At that point
our test of (len < MAXWORDLEN-1) will succeed and we will start writing
characters to memory again.
This may enable an attacker to overwrite the heap and thereby corrupt
security-relevant variables. For this reason it has been assigned a
CVE identifier, CVE-2014-3158.
This fixes the bug by ceasing to increment len once it reaches MAXWORDLEN.
Reported-by: Lee Campbell <[email protected]>
Signed-off-by: Paul Mackerras <[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 change_mount_flags(struct vfsmount *mnt, int ms_flags)
{
int error = 0;
int readonly_request = 0;
if (ms_flags & MS_RDONLY)
readonly_request = 1;
if (readonly_request == __mnt_is_readonly(mnt))
return 0;
if (mnt->mnt_flags & MNT_LOCK_READONLY)
return -EPERM;
if (readonly_request)
error = mnt_make_readonly(real_mount(mnt));
else
__mnt_unmake_readonly(real_mount(mnt));
return error;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-269'], 'message': 'mnt: Move the test for MNT_LOCK_READONLY from change_mount_flags into do_remount
There are no races as locked mount flags are guaranteed to never change.
Moving the test into do_remount makes it more visible, and ensures all
filesystem remounts pass the MNT_LOCK_READONLY permission check. This
second case is not an issue today as filesystem remounts are guarded
by capable(CAP_DAC_ADMIN) and thus will always fail in less privileged
mount namespaces, but it could become an issue in the future.
Cc: [email protected]
Acked-by: Serge E. Hallyn <[email protected]>
Signed-off-by: "Eric W. Biederman" <[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 mount *clone_mnt(struct mount *old, struct dentry *root,
int flag)
{
struct super_block *sb = old->mnt.mnt_sb;
struct mount *mnt;
int err;
mnt = alloc_vfsmnt(old->mnt_devname);
if (!mnt)
return ERR_PTR(-ENOMEM);
if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE))
mnt->mnt_group_id = 0; /* not a peer of original */
else
mnt->mnt_group_id = old->mnt_group_id;
if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
err = mnt_alloc_group_id(mnt);
if (err)
goto out_free;
}
mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
/* Don't allow unprivileged users to change mount flags */
if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
/* Don't allow unprivileged users to reveal what is under a mount */
if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire))
mnt->mnt.mnt_flags |= MNT_LOCKED;
atomic_inc(&sb->s_active);
mnt->mnt.mnt_sb = sb;
mnt->mnt.mnt_root = dget(root);
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
unlock_mount_hash();
if ((flag & CL_SLAVE) ||
((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) {
list_add(&mnt->mnt_slave, &old->mnt_slave_list);
mnt->mnt_master = old;
CLEAR_MNT_SHARED(mnt);
} else if (!(flag & CL_PRIVATE)) {
if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
list_add(&mnt->mnt_share, &old->mnt_share);
if (IS_MNT_SLAVE(old))
list_add(&mnt->mnt_slave, &old->mnt_slave);
mnt->mnt_master = old->mnt_master;
}
if (flag & CL_MAKE_SHARED)
set_mnt_shared(mnt);
/* stick the duplicate mount on the same expiry list
* as the original if that was on one */
if (flag & CL_EXPIRE) {
if (!list_empty(&old->mnt_expire))
list_add(&mnt->mnt_expire, &old->mnt_expire);
}
return mnt;
out_free:
mnt_free_id(mnt);
free_vfsmnt(mnt);
return ERR_PTR(err);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-269'], 'message': 'mnt: Correct permission checks in do_remount
While invesgiating the issue where in "mount --bind -oremount,ro ..."
would result in later "mount --bind -oremount,rw" succeeding even if
the mount started off locked I realized that there are several
additional mount flags that should be locked and are not.
In particular MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, and the atime
flags in addition to MNT_READONLY should all be locked. These
flags are all per superblock, can all be changed with MS_BIND,
and should not be changable if set by a more privileged user.
The following additions to the current logic are added in this patch.
- nosuid may not be clearable by a less privileged user.
- nodev may not be clearable by a less privielged user.
- noexec may not be clearable by a less privileged user.
- atime flags may not be changeable by a less privileged user.
The logic with atime is that always setting atime on access is a
global policy and backup software and auditing software could break if
atime bits are not updated (when they are configured to be updated),
and serious performance degradation could result (DOS attack) if atime
updates happen when they have been explicitly disabled. Therefore an
unprivileged user should not be able to mess with the atime bits set
by a more privileged user.
The additional restrictions are implemented with the addition of
MNT_LOCK_NOSUID, MNT_LOCK_NODEV, MNT_LOCK_NOEXEC, and MNT_LOCK_ATIME
mnt flags.
Taken together these changes and the fixes for MNT_LOCK_READONLY
should make it safe for an unprivileged user to create a user
namespace and to call "mount --bind -o remount,... ..." without
the danger of mount flags being changed maliciously.
Cc: [email protected]
Acked-by: Serge E. Hallyn <[email protected]>
Signed-off-by: "Eric W. Biederman" <[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 do_new_mount(struct path *path, const char *fstype, int flags,
int mnt_flags, const char *name, void *data)
{
struct file_system_type *type;
struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
struct vfsmount *mnt;
int err;
if (!fstype)
return -EINVAL;
type = get_fs_type(fstype);
if (!type)
return -ENODEV;
if (user_ns != &init_user_ns) {
if (!(type->fs_flags & FS_USERNS_MOUNT)) {
put_filesystem(type);
return -EPERM;
}
/* Only in special cases allow devices from mounts
* created outside the initial user namespace.
*/
if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
flags |= MS_NODEV;
mnt_flags |= MNT_NODEV;
}
}
mnt = vfs_kern_mount(type, flags, name, data);
if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
!mnt->mnt_sb->s_subtype)
mnt = fs_set_subtype(mnt, fstype);
put_filesystem(type);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
err = do_add_mount(real_mount(mnt), path, mnt_flags);
if (err)
mntput(mnt);
return err;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-269'], 'message': 'mnt: Correct permission checks in do_remount
While invesgiating the issue where in "mount --bind -oremount,ro ..."
would result in later "mount --bind -oremount,rw" succeeding even if
the mount started off locked I realized that there are several
additional mount flags that should be locked and are not.
In particular MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, and the atime
flags in addition to MNT_READONLY should all be locked. These
flags are all per superblock, can all be changed with MS_BIND,
and should not be changable if set by a more privileged user.
The following additions to the current logic are added in this patch.
- nosuid may not be clearable by a less privileged user.
- nodev may not be clearable by a less privielged user.
- noexec may not be clearable by a less privileged user.
- atime flags may not be changeable by a less privileged user.
The logic with atime is that always setting atime on access is a
global policy and backup software and auditing software could break if
atime bits are not updated (when they are configured to be updated),
and serious performance degradation could result (DOS attack) if atime
updates happen when they have been explicitly disabled. Therefore an
unprivileged user should not be able to mess with the atime bits set
by a more privileged user.
The additional restrictions are implemented with the addition of
MNT_LOCK_NOSUID, MNT_LOCK_NODEV, MNT_LOCK_NOEXEC, and MNT_LOCK_ATIME
mnt flags.
Taken together these changes and the fixes for MNT_LOCK_READONLY
should make it safe for an unprivileged user to create a user
namespace and to call "mount --bind -o remount,... ..." without
the danger of mount flags being changed maliciously.
Cc: [email protected]
Acked-by: Serge E. Hallyn <[email protected]>
Signed-off-by: "Eric W. Biederman" <[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 u_char *php_parserr(u_char *cp, querybuf *answer, int type_to_fetch, int store, int raw, zval **subarray)
{
u_short type, class, dlen;
u_long ttl;
long n, i;
u_short s;
u_char *tp, *p;
char name[MAXHOSTNAMELEN];
int have_v6_break = 0, in_v6_break = 0;
*subarray = NULL;
n = dn_expand(answer->qb2, answer->qb2+65536, cp, name, sizeof(name) - 2);
if (n < 0) {
return NULL;
}
cp += n;
GETSHORT(type, cp);
GETSHORT(class, cp);
GETLONG(ttl, cp);
GETSHORT(dlen, cp);
if (type_to_fetch != T_ANY && type != type_to_fetch) {
cp += dlen;
return cp;
}
if (!store) {
cp += dlen;
return cp;
}
ALLOC_INIT_ZVAL(*subarray);
array_init(*subarray);
add_assoc_string(*subarray, "host", name, 1);
add_assoc_string(*subarray, "class", "IN", 1);
add_assoc_long(*subarray, "ttl", ttl);
if (raw) {
add_assoc_long(*subarray, "type", type);
add_assoc_stringl(*subarray, "data", (char*) cp, (uint) dlen, 1);
cp += dlen;
return cp;
}
switch (type) {
case DNS_T_A:
add_assoc_string(*subarray, "type", "A", 1);
snprintf(name, sizeof(name), "%d.%d.%d.%d", cp[0], cp[1], cp[2], cp[3]);
add_assoc_string(*subarray, "ip", name, 1);
cp += dlen;
break;
case DNS_T_MX:
add_assoc_string(*subarray, "type", "MX", 1);
GETSHORT(n, cp);
add_assoc_long(*subarray, "pri", n);
/* no break; */
case DNS_T_CNAME:
if (type == DNS_T_CNAME) {
add_assoc_string(*subarray, "type", "CNAME", 1);
}
/* no break; */
case DNS_T_NS:
if (type == DNS_T_NS) {
add_assoc_string(*subarray, "type", "NS", 1);
}
/* no break; */
case DNS_T_PTR:
if (type == DNS_T_PTR) {
add_assoc_string(*subarray, "type", "PTR", 1);
}
n = dn_expand(answer->qb2, answer->qb2+65536, cp, name, (sizeof name) - 2);
if (n < 0) {
return NULL;
}
cp += n;
add_assoc_string(*subarray, "target", name, 1);
break;
case DNS_T_HINFO:
/* See RFC 1010 for values */
add_assoc_string(*subarray, "type", "HINFO", 1);
n = *cp & 0xFF;
cp++;
add_assoc_stringl(*subarray, "cpu", (char*)cp, n, 1);
cp += n;
n = *cp & 0xFF;
cp++;
add_assoc_stringl(*subarray, "os", (char*)cp, n, 1);
cp += n;
break;
case DNS_T_TXT:
{
int ll = 0;
zval *entries = NULL;
add_assoc_string(*subarray, "type", "TXT", 1);
tp = emalloc(dlen + 1);
MAKE_STD_ZVAL(entries);
array_init(entries);
while (ll < dlen) {
n = cp[ll];
if ((ll + n) >= dlen) {
// Invalid chunk length, truncate
n = dlen - (ll + 1);
}
memcpy(tp + ll , cp + ll + 1, n);
add_next_index_stringl(entries, cp + ll + 1, n, 1);
ll = ll + n + 1;
}
tp[dlen] = '\0';
cp += dlen;
add_assoc_stringl(*subarray, "txt", tp, (dlen>0)?dlen - 1:0, 0);
add_assoc_zval(*subarray, "entries", entries);
}
break;
case DNS_T_SOA:
add_assoc_string(*subarray, "type", "SOA", 1);
n = dn_expand(answer->qb2, answer->qb2+65536, cp, name, (sizeof name) -2);
if (n < 0) {
return NULL;
}
cp += n;
add_assoc_string(*subarray, "mname", name, 1);
n = dn_expand(answer->qb2, answer->qb2+65536, cp, name, (sizeof name) -2);
if (n < 0) {
return NULL;
}
cp += n;
add_assoc_string(*subarray, "rname", name, 1);
GETLONG(n, cp);
add_assoc_long(*subarray, "serial", n);
GETLONG(n, cp);
add_assoc_long(*subarray, "refresh", n);
GETLONG(n, cp);
add_assoc_long(*subarray, "retry", n);
GETLONG(n, cp);
add_assoc_long(*subarray, "expire", n);
GETLONG(n, cp);
add_assoc_long(*subarray, "minimum-ttl", n);
break;
case DNS_T_AAAA:
tp = (u_char*)name;
for(i=0; i < 8; i++) {
GETSHORT(s, cp);
if (s != 0) {
if (tp > (u_char *)name) {
in_v6_break = 0;
tp[0] = ':';
tp++;
}
tp += sprintf((char*)tp,"%x",s);
} else {
if (!have_v6_break) {
have_v6_break = 1;
in_v6_break = 1;
tp[0] = ':';
tp++;
} else if (!in_v6_break) {
tp[0] = ':';
tp++;
tp[0] = '0';
tp++;
}
}
}
if (have_v6_break && in_v6_break) {
tp[0] = ':';
tp++;
}
tp[0] = '\0';
add_assoc_string(*subarray, "type", "AAAA", 1);
add_assoc_string(*subarray, "ipv6", name, 1);
break;
case DNS_T_A6:
p = cp;
add_assoc_string(*subarray, "type", "A6", 1);
n = ((int)cp[0]) & 0xFF;
cp++;
add_assoc_long(*subarray, "masklen", n);
tp = (u_char*)name;
if (n > 15) {
have_v6_break = 1;
in_v6_break = 1;
tp[0] = ':';
tp++;
}
if (n % 16 > 8) {
/* Partial short */
if (cp[0] != 0) {
if (tp > (u_char *)name) {
in_v6_break = 0;
tp[0] = ':';
tp++;
}
sprintf((char*)tp, "%x", cp[0] & 0xFF);
} else {
if (!have_v6_break) {
have_v6_break = 1;
in_v6_break = 1;
tp[0] = ':';
tp++;
} else if (!in_v6_break) {
tp[0] = ':';
tp++;
tp[0] = '0';
tp++;
}
}
cp++;
}
for (i = (n + 8) / 16; i < 8; i++) {
GETSHORT(s, cp);
if (s != 0) {
if (tp > (u_char *)name) {
in_v6_break = 0;
tp[0] = ':';
tp++;
}
tp += sprintf((char*)tp,"%x",s);
} else {
if (!have_v6_break) {
have_v6_break = 1;
in_v6_break = 1;
tp[0] = ':';
tp++;
} else if (!in_v6_break) {
tp[0] = ':';
tp++;
tp[0] = '0';
tp++;
}
}
}
if (have_v6_break && in_v6_break) {
tp[0] = ':';
tp++;
}
tp[0] = '\0';
add_assoc_string(*subarray, "ipv6", name, 1);
if (cp < p + dlen) {
n = dn_expand(answer->qb2, answer->qb2+65536, cp, name, (sizeof name) - 2);
if (n < 0) {
return NULL;
}
cp += n;
add_assoc_string(*subarray, "chain", name, 1);
}
break;
case DNS_T_SRV:
add_assoc_string(*subarray, "type", "SRV", 1);
GETSHORT(n, cp);
add_assoc_long(*subarray, "pri", n);
GETSHORT(n, cp);
add_assoc_long(*subarray, "weight", n);
GETSHORT(n, cp);
add_assoc_long(*subarray, "port", n);
n = dn_expand(answer->qb2, answer->qb2+65536, cp, name, (sizeof name) - 2);
if (n < 0) {
return NULL;
}
cp += n;
add_assoc_string(*subarray, "target", name, 1);
break;
case DNS_T_NAPTR:
add_assoc_string(*subarray, "type", "NAPTR", 1);
GETSHORT(n, cp);
add_assoc_long(*subarray, "order", n);
GETSHORT(n, cp);
add_assoc_long(*subarray, "pref", n);
n = (cp[0] & 0xFF);
add_assoc_stringl(*subarray, "flags", (char*)++cp, n, 1);
cp += n;
n = (cp[0] & 0xFF);
add_assoc_stringl(*subarray, "services", (char*)++cp, n, 1);
cp += n;
n = (cp[0] & 0xFF);
add_assoc_stringl(*subarray, "regex", (char*)++cp, n, 1);
cp += n;
n = dn_expand(answer->qb2, answer->qb2+65536, cp, name, (sizeof name) - 2);
if (n < 0) {
return NULL;
}
cp += n;
add_assoc_string(*subarray, "replacement", name, 1);
break;
default:
zval_ptr_dtor(subarray);
*subarray = NULL;
cp += dlen;
break;
}
return cp;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'Fixed Sec Bug #67717 segfault in dns_get_record CVE-2014-3597
Incomplete fix for CVE-2014-4049
Check possible buffer overflow
- pass real buffer end to dn_expand calls
- check buffer len before each read'</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 _php_image_output_ctx(INTERNAL_FUNCTION_PARAMETERS, int image_type, char *tn, void (*func_p)())
{
zval *imgind;
char *file = NULL;
int file_len = 0;
long quality, basefilter;
gdImagePtr im;
int argc = ZEND_NUM_ARGS();
int q = -1, i;
int f = -1;
gdIOCtx *ctx = NULL;
zval *to_zval = NULL;
php_stream *stream;
/* The third (quality) parameter for Wbmp stands for the threshold when called from image2wbmp().
* The third (quality) parameter for Wbmp and Xbm stands for the foreground color index when called
* from imagey<type>().
*/
if (image_type == PHP_GDIMG_TYPE_XBM) {
if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "rp!|ll", &imgind, &file, &file_len, &quality, &basefilter) == FAILURE) {
return;
}
} else {
/* PHP_GDIMG_TYPE_GIF
* PHP_GDIMG_TYPE_PNG
* PHP_GDIMG_TYPE_JPG
* PHP_GDIMG_TYPE_WBM
* PHP_GDIMG_TYPE_WEBP
* */
if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "r|z/!ll", &imgind, &to_zval, &quality, &basefilter) == FAILURE) {
return;
}
}
ZEND_FETCH_RESOURCE(im, gdImagePtr, &imgind, -1, "Image", phpi_get_le_gd());
if (argc >= 3) {
q = quality; /* or colorindex for foreground of BW images (defaults to black) */
if (argc == 4) {
f = basefilter;
}
}
if (argc > 1 && to_zval != NULL) {
if (Z_TYPE_P(to_zval) == IS_RESOURCE) {
php_stream_from_zval_no_verify(stream, &to_zval);
if (stream == NULL) {
RETURN_FALSE;
}
} else if (Z_TYPE_P(to_zval) == IS_STRING) {
stream = php_stream_open_wrapper(Z_STRVAL_P(to_zval), "wb", REPORT_ERRORS|IGNORE_PATH|IGNORE_URL_WIN, NULL);
if (stream == NULL) {
RETURN_FALSE;
}
} else {
php_error_docref(NULL TSRMLS_CC, E_WARNING, "Invalid 2nd parameter, it must a filename or a stream");
RETURN_FALSE;
}
} else {
ctx = emalloc(sizeof(gdIOCtx));
ctx->putC = _php_image_output_putc;
ctx->putBuf = _php_image_output_putbuf;
ctx->gd_free = _php_image_output_ctxfree;
#if APACHE && defined(CHARSET_EBCDIC)
/* XXX this is unlikely to work any more [email protected] */
/* This is a binary file already: avoid EBCDIC->ASCII conversion */
ap_bsetflag(php3_rqst->connection->client, B_EBCDIC2ASCII, 0);
#endif
}
if (!ctx) {
ctx = emalloc(sizeof(gdIOCtx));
ctx->putC = _php_image_stream_putc;
ctx->putBuf = _php_image_stream_putbuf;
ctx->gd_free = _php_image_stream_ctxfree;
ctx->data = (void *)stream;
}
switch(image_type) {
case PHP_GDIMG_CONVERT_WBM:
if(q<0||q>255) {
php_error_docref(NULL TSRMLS_CC, E_WARNING, "Invalid threshold value '%d'. It must be between 0 and 255", q);
}
case PHP_GDIMG_TYPE_JPG:
(*func_p)(im, ctx, q);
break;
case PHP_GDIMG_TYPE_WEBP:
if (q == -1) {
q = 80;
}
(*func_p)(im, ctx, q);
break;
case PHP_GDIMG_TYPE_PNG:
(*func_p)(im, ctx, q, f);
break;
case PHP_GDIMG_TYPE_XBM:
case PHP_GDIMG_TYPE_WBM:
if (argc < 3) {
for(i=0; i < gdImageColorsTotal(im); i++) {
if(!gdImageRed(im, i) && !gdImageGreen(im, i) && !gdImageBlue(im, i)) break;
}
q = i;
}
if (image_type == PHP_GDIMG_TYPE_XBM) {
(*func_p)(im, file, q, ctx);
} else {
(*func_p)(im, q, ctx);
}
break;
default:
(*func_p)(im, ctx);
break;
}
ctx->gd_free(ctx);
RETURN_TRUE;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Fix bug #67730 - Null byte injection possible with imagexxx functions'</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 vbe_ioport_write_data(void *opaque, uint32_t addr, uint32_t val)
{
VGACommonState *s = opaque;
if (s->vbe_index <= VBE_DISPI_INDEX_NB) {
#ifdef DEBUG_BOCHS_VBE
printf("VBE: write index=0x%x val=0x%x\n", s->vbe_index, val);
#endif
switch(s->vbe_index) {
case VBE_DISPI_INDEX_ID:
if (val == VBE_DISPI_ID0 ||
val == VBE_DISPI_ID1 ||
val == VBE_DISPI_ID2 ||
val == VBE_DISPI_ID3 ||
val == VBE_DISPI_ID4) {
s->vbe_regs[s->vbe_index] = val;
}
break;
case VBE_DISPI_INDEX_XRES:
if ((val <= VBE_DISPI_MAX_XRES) && ((val & 7) == 0)) {
s->vbe_regs[s->vbe_index] = val;
}
break;
case VBE_DISPI_INDEX_YRES:
if (val <= VBE_DISPI_MAX_YRES) {
s->vbe_regs[s->vbe_index] = val;
}
break;
case VBE_DISPI_INDEX_BPP:
if (val == 0)
val = 8;
if (val == 4 || val == 8 || val == 15 ||
val == 16 || val == 24 || val == 32) {
s->vbe_regs[s->vbe_index] = val;
}
break;
case VBE_DISPI_INDEX_BANK:
if (s->vbe_regs[VBE_DISPI_INDEX_BPP] == 4) {
val &= (s->vbe_bank_mask >> 2);
} else {
val &= s->vbe_bank_mask;
}
s->vbe_regs[s->vbe_index] = val;
s->bank_offset = (val << 16);
vga_update_memory_access(s);
break;
case VBE_DISPI_INDEX_ENABLE:
if ((val & VBE_DISPI_ENABLED) &&
!(s->vbe_regs[VBE_DISPI_INDEX_ENABLE] & VBE_DISPI_ENABLED)) {
int h, shift_control;
s->vbe_regs[VBE_DISPI_INDEX_VIRT_WIDTH] =
s->vbe_regs[VBE_DISPI_INDEX_XRES];
s->vbe_regs[VBE_DISPI_INDEX_VIRT_HEIGHT] =
s->vbe_regs[VBE_DISPI_INDEX_YRES];
s->vbe_regs[VBE_DISPI_INDEX_X_OFFSET] = 0;
s->vbe_regs[VBE_DISPI_INDEX_Y_OFFSET] = 0;
if (s->vbe_regs[VBE_DISPI_INDEX_BPP] == 4)
s->vbe_line_offset = s->vbe_regs[VBE_DISPI_INDEX_XRES] >> 1;
else
s->vbe_line_offset = s->vbe_regs[VBE_DISPI_INDEX_XRES] *
((s->vbe_regs[VBE_DISPI_INDEX_BPP] + 7) >> 3);
s->vbe_start_addr = 0;
/* clear the screen (should be done in BIOS) */
if (!(val & VBE_DISPI_NOCLEARMEM)) {
memset(s->vram_ptr, 0,
s->vbe_regs[VBE_DISPI_INDEX_YRES] * s->vbe_line_offset);
}
/* we initialize the VGA graphic mode (should be done
in BIOS) */
/* graphic mode + memory map 1 */
s->gr[VGA_GFX_MISC] = (s->gr[VGA_GFX_MISC] & ~0x0c) | 0x04 |
VGA_GR06_GRAPHICS_MODE;
s->cr[VGA_CRTC_MODE] |= 3; /* no CGA modes */
s->cr[VGA_CRTC_OFFSET] = s->vbe_line_offset >> 3;
/* width */
s->cr[VGA_CRTC_H_DISP] =
(s->vbe_regs[VBE_DISPI_INDEX_XRES] >> 3) - 1;
/* height (only meaningful if < 1024) */
h = s->vbe_regs[VBE_DISPI_INDEX_YRES] - 1;
s->cr[VGA_CRTC_V_DISP_END] = h;
s->cr[VGA_CRTC_OVERFLOW] = (s->cr[VGA_CRTC_OVERFLOW] & ~0x42) |
((h >> 7) & 0x02) | ((h >> 3) & 0x40);
/* line compare to 1023 */
s->cr[VGA_CRTC_LINE_COMPARE] = 0xff;
s->cr[VGA_CRTC_OVERFLOW] |= 0x10;
s->cr[VGA_CRTC_MAX_SCAN] |= 0x40;
if (s->vbe_regs[VBE_DISPI_INDEX_BPP] == 4) {
shift_control = 0;
s->sr[VGA_SEQ_CLOCK_MODE] &= ~8; /* no double line */
} else {
shift_control = 2;
/* set chain 4 mode */
s->sr[VGA_SEQ_MEMORY_MODE] |= VGA_SR04_CHN_4M;
/* activate all planes */
s->sr[VGA_SEQ_PLANE_WRITE] |= VGA_SR02_ALL_PLANES;
}
s->gr[VGA_GFX_MODE] = (s->gr[VGA_GFX_MODE] & ~0x60) |
(shift_control << 5);
s->cr[VGA_CRTC_MAX_SCAN] &= ~0x9f; /* no double scan */
} else {
/* XXX: the bios should do that */
s->bank_offset = 0;
}
s->dac_8bit = (val & VBE_DISPI_8BIT_DAC) > 0;
s->vbe_regs[s->vbe_index] = val;
vga_update_memory_access(s);
break;
case VBE_DISPI_INDEX_VIRT_WIDTH:
{
int w, h, line_offset;
if (val < s->vbe_regs[VBE_DISPI_INDEX_XRES])
return;
w = val;
if (s->vbe_regs[VBE_DISPI_INDEX_BPP] == 4)
line_offset = w >> 1;
else
line_offset = w * ((s->vbe_regs[VBE_DISPI_INDEX_BPP] + 7) >> 3);
h = s->vbe_size / line_offset;
/* XXX: support weird bochs semantics ? */
if (h < s->vbe_regs[VBE_DISPI_INDEX_YRES])
return;
s->vbe_regs[VBE_DISPI_INDEX_VIRT_WIDTH] = w;
s->vbe_regs[VBE_DISPI_INDEX_VIRT_HEIGHT] = h;
s->vbe_line_offset = line_offset;
}
break;
case VBE_DISPI_INDEX_X_OFFSET:
case VBE_DISPI_INDEX_Y_OFFSET:
{
int x;
s->vbe_regs[s->vbe_index] = val;
s->vbe_start_addr = s->vbe_line_offset * s->vbe_regs[VBE_DISPI_INDEX_Y_OFFSET];
x = s->vbe_regs[VBE_DISPI_INDEX_X_OFFSET];
if (s->vbe_regs[VBE_DISPI_INDEX_BPP] == 4)
s->vbe_start_addr += x >> 1;
else
s->vbe_start_addr += x * ((s->vbe_regs[VBE_DISPI_INDEX_BPP] + 7) >> 3);
s->vbe_start_addr >>= 2;
}
break;
default:
break;
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'vbe: rework sanity checks
Plug a bunch of holes in the bochs dispi interface parameter checking.
Add a function doing verification on all registers. Call that
unconditionally on every register write. That way we should catch
everything, even changing one register affecting the valid range of
another register.
Some of the holes have been added by commit
e9c6149f6ae6873f14a12eea554925b6aa4c4dec. Before that commit the
maximum possible framebuffer (VBE_DISPI_MAX_XRES * VBE_DISPI_MAX_YRES *
32 bpp) has been smaller than the qemu vga memory (8MB) and the checking
for VBE_DISPI_MAX_XRES + VBE_DISPI_MAX_YRES + VBE_DISPI_MAX_BPP was ok.
Some of the holes have been there forever, such as
VBE_DISPI_INDEX_X_OFFSET and VBE_DISPI_INDEX_Y_OFFSET register writes
lacking any verification.
Security impact:
(1) Guest can make the ui (gtk/vnc/...) use memory rages outside the vga
frame buffer as source -> host memory leak. Memory isn't leaked to
the guest but to the vnc client though.
(2) Qemu will segfault in case the memory range happens to include
unmapped areas -> Guest can DoS itself.
The guest can not modify host memory, so I don't think this can be used
by the guest to escape.
CVE-2014-3615
Cc: [email protected]
Cc: [email protected]
Signed-off-by: Gerd Hoffmann <[email protected]>
Reviewed-by: Laszlo Ersek <[email protected]>'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void qemu_spice_display_init_common(SimpleSpiceDisplay *ssd)
{
qemu_mutex_init(&ssd->lock);
QTAILQ_INIT(&ssd->updates);
ssd->mouse_x = -1;
ssd->mouse_y = -1;
if (ssd->num_surfaces == 0) {
ssd->num_surfaces = 1024;
}
ssd->bufsize = (16 * 1024 * 1024);
ssd->buf = g_malloc(ssd->bufsize);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'spice: make sure we don't overflow ssd->buf
Related spice-only bug. We have a fixed 16 MB buffer here, being
presented to the spice-server as qxl video memory in case spice is
used with a non-qxl card. It's also used with qxl in vga mode.
When using display resolutions requiring more than 16 MB of memory we
are going to overflow that buffer. In theory the guest can write,
indirectly via spice-server. The spice-server clears the memory after
setting a new video mode though, triggering a segfault in the overflow
case, so qemu crashes before the guest has a chance to do something
evil.
Fix that by switching to dynamic allocation for the buffer.
CVE-2014-3615
Cc: [email protected]
Cc: [email protected]
Signed-off-by: Gerd Hoffmann <[email protected]>
Reviewed-by: Laszlo Ersek <[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: defaults (void)
{
char *tmp;
/* Most of the default values are 0 (and 0.0, NULL, and false).
Just reset everything, and fill in the non-zero values. Note
that initializing pointers to NULL this way is technically
illegal, but porting Wget to a machine where NULL is not all-zero
bit pattern will be the least of the implementors' worries. */
xzero (opt);
opt.cookies = true;
opt.verbose = -1;
opt.ntry = 20;
opt.reclevel = 5;
opt.add_hostdir = true;
opt.netrc = true;
opt.ftp_glob = true;
opt.htmlify = true;
opt.http_keep_alive = true;
opt.use_proxy = true;
tmp = getenv ("no_proxy");
if (tmp)
opt.no_proxy = sepstring (tmp);
opt.prefer_family = prefer_none;
opt.allow_cache = true;
opt.read_timeout = 900;
opt.use_robots = true;
opt.remove_listing = true;
opt.dot_bytes = 1024;
opt.dot_spacing = 10;
opt.dots_in_line = 50;
opt.dns_cache = true;
opt.ftp_pasv = true;
#ifdef HAVE_SSL
opt.check_cert = true;
#endif
/* The default for file name restriction defaults to the OS type. */
#if defined(WINDOWS) || defined(MSDOS) || defined(__CYGWIN__)
opt.restrict_files_os = restrict_windows;
#else
opt.restrict_files_os = restrict_unix;
#endif
opt.restrict_files_ctrl = true;
opt.restrict_files_nonascii = false;
opt.restrict_files_case = restrict_no_case_restriction;
opt.regex_type = regex_type_posix;
opt.max_redirect = 20;
opt.waitretry = 10;
#ifdef ENABLE_IRI
opt.enable_iri = true;
#else
opt.enable_iri = false;
#endif
opt.locale = NULL;
opt.encoding_remote = NULL;
opt.useservertimestamps = true;
opt.show_all_dns_entries = false;
opt.warc_maxsize = 0; /* 1024 * 1024 * 1024; */
#ifdef HAVE_LIBZ
opt.warc_compression_enabled = true;
#else
opt.warc_compression_enabled = false;
#endif
opt.warc_digests_enabled = true;
opt.warc_cdx_enabled = false;
opt.warc_cdx_dedup_filename = NULL;
opt.warc_tempdir = NULL;
opt.warc_keep_log = true;
/* Use a negative value to mark the absence of --start-pos option */
opt.start_pos = -1;
opt.show_progress = false;
opt.noscroll = false;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-22'], 'message': 'CVE-2014-4877: Arbitrary Symlink Access
Wget was susceptible to a symlink attack which could create arbitrary
files, directories or symbolic links and set their permissions when
retrieving a directory recursively through FTP. This commit changes the
default settings in Wget such that Wget no longer creates local symbolic
links, but rather traverses them and retrieves the pointed-to file in
such a retrieval.
The old behaviour can be attained by passing the --retr-symlinks=no
option to the Wget invokation command.'</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 assoc_array_gc(struct assoc_array *array,
const struct assoc_array_ops *ops,
bool (*iterator)(void *object, void *iterator_data),
void *iterator_data)
{
struct assoc_array_shortcut *shortcut, *new_s;
struct assoc_array_node *node, *new_n;
struct assoc_array_edit *edit;
struct assoc_array_ptr *cursor, *ptr;
struct assoc_array_ptr *new_root, *new_parent, **new_ptr_pp;
unsigned long nr_leaves_on_tree;
int keylen, slot, nr_free, next_slot, i;
pr_devel("-->%s()\n", __func__);
if (!array->root)
return 0;
edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
if (!edit)
return -ENOMEM;
edit->array = array;
edit->ops = ops;
edit->ops_for_excised_subtree = ops;
edit->set[0].ptr = &array->root;
edit->excised_subtree = array->root;
new_root = new_parent = NULL;
new_ptr_pp = &new_root;
cursor = array->root;
descend:
/* If this point is a shortcut, then we need to duplicate it and
* advance the target cursor.
*/
if (assoc_array_ptr_is_shortcut(cursor)) {
shortcut = assoc_array_ptr_to_shortcut(cursor);
keylen = round_up(shortcut->skip_to_level, ASSOC_ARRAY_KEY_CHUNK_SIZE);
keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
new_s = kmalloc(sizeof(struct assoc_array_shortcut) +
keylen * sizeof(unsigned long), GFP_KERNEL);
if (!new_s)
goto enomem;
pr_devel("dup shortcut %p -> %p\n", shortcut, new_s);
memcpy(new_s, shortcut, (sizeof(struct assoc_array_shortcut) +
keylen * sizeof(unsigned long)));
new_s->back_pointer = new_parent;
new_s->parent_slot = shortcut->parent_slot;
*new_ptr_pp = new_parent = assoc_array_shortcut_to_ptr(new_s);
new_ptr_pp = &new_s->next_node;
cursor = shortcut->next_node;
}
/* Duplicate the node at this position */
node = assoc_array_ptr_to_node(cursor);
new_n = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
if (!new_n)
goto enomem;
pr_devel("dup node %p -> %p\n", node, new_n);
new_n->back_pointer = new_parent;
new_n->parent_slot = node->parent_slot;
*new_ptr_pp = new_parent = assoc_array_node_to_ptr(new_n);
new_ptr_pp = NULL;
slot = 0;
continue_node:
/* Filter across any leaves and gc any subtrees */
for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
ptr = node->slots[slot];
if (!ptr)
continue;
if (assoc_array_ptr_is_leaf(ptr)) {
if (iterator(assoc_array_ptr_to_leaf(ptr),
iterator_data))
/* The iterator will have done any reference
* counting on the object for us.
*/
new_n->slots[slot] = ptr;
continue;
}
new_ptr_pp = &new_n->slots[slot];
cursor = ptr;
goto descend;
}
pr_devel("-- compress node %p --\n", new_n);
/* Count up the number of empty slots in this node and work out the
* subtree leaf count.
*/
new_n->nr_leaves_on_branch = 0;
nr_free = 0;
for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
ptr = new_n->slots[slot];
if (!ptr)
nr_free++;
else if (assoc_array_ptr_is_leaf(ptr))
new_n->nr_leaves_on_branch++;
}
pr_devel("free=%d, leaves=%lu\n", nr_free, new_n->nr_leaves_on_branch);
/* See what we can fold in */
next_slot = 0;
for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
struct assoc_array_shortcut *s;
struct assoc_array_node *child;
ptr = new_n->slots[slot];
if (!ptr || assoc_array_ptr_is_leaf(ptr))
continue;
s = NULL;
if (assoc_array_ptr_is_shortcut(ptr)) {
s = assoc_array_ptr_to_shortcut(ptr);
ptr = s->next_node;
}
child = assoc_array_ptr_to_node(ptr);
new_n->nr_leaves_on_branch += child->nr_leaves_on_branch;
if (child->nr_leaves_on_branch <= nr_free + 1) {
/* Fold the child node into this one */
pr_devel("[%d] fold node %lu/%d [nx %d]\n",
slot, child->nr_leaves_on_branch, nr_free + 1,
next_slot);
/* We would already have reaped an intervening shortcut
* on the way back up the tree.
*/
BUG_ON(s);
new_n->slots[slot] = NULL;
nr_free++;
if (slot < next_slot)
next_slot = slot;
for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
struct assoc_array_ptr *p = child->slots[i];
if (!p)
continue;
BUG_ON(assoc_array_ptr_is_meta(p));
while (new_n->slots[next_slot])
next_slot++;
BUG_ON(next_slot >= ASSOC_ARRAY_FAN_OUT);
new_n->slots[next_slot++] = p;
nr_free--;
}
kfree(child);
} else {
pr_devel("[%d] retain node %lu/%d [nx %d]\n",
slot, child->nr_leaves_on_branch, nr_free + 1,
next_slot);
}
}
pr_devel("after: %lu\n", new_n->nr_leaves_on_branch);
nr_leaves_on_tree = new_n->nr_leaves_on_branch;
/* Excise this node if it is singly occupied by a shortcut */
if (nr_free == ASSOC_ARRAY_FAN_OUT - 1) {
for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++)
if ((ptr = new_n->slots[slot]))
break;
if (assoc_array_ptr_is_meta(ptr) &&
assoc_array_ptr_is_shortcut(ptr)) {
pr_devel("excise node %p with 1 shortcut\n", new_n);
new_s = assoc_array_ptr_to_shortcut(ptr);
new_parent = new_n->back_pointer;
slot = new_n->parent_slot;
kfree(new_n);
if (!new_parent) {
new_s->back_pointer = NULL;
new_s->parent_slot = 0;
new_root = ptr;
goto gc_complete;
}
if (assoc_array_ptr_is_shortcut(new_parent)) {
/* We can discard any preceding shortcut also */
struct assoc_array_shortcut *s =
assoc_array_ptr_to_shortcut(new_parent);
pr_devel("excise preceding shortcut\n");
new_parent = new_s->back_pointer = s->back_pointer;
slot = new_s->parent_slot = s->parent_slot;
kfree(s);
if (!new_parent) {
new_s->back_pointer = NULL;
new_s->parent_slot = 0;
new_root = ptr;
goto gc_complete;
}
}
new_s->back_pointer = new_parent;
new_s->parent_slot = slot;
new_n = assoc_array_ptr_to_node(new_parent);
new_n->slots[slot] = ptr;
goto ascend_old_tree;
}
}
/* Excise any shortcuts we might encounter that point to nodes that
* only contain leaves.
*/
ptr = new_n->back_pointer;
if (!ptr)
goto gc_complete;
if (assoc_array_ptr_is_shortcut(ptr)) {
new_s = assoc_array_ptr_to_shortcut(ptr);
new_parent = new_s->back_pointer;
slot = new_s->parent_slot;
if (new_n->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT) {
struct assoc_array_node *n;
pr_devel("excise shortcut\n");
new_n->back_pointer = new_parent;
new_n->parent_slot = slot;
kfree(new_s);
if (!new_parent) {
new_root = assoc_array_node_to_ptr(new_n);
goto gc_complete;
}
n = assoc_array_ptr_to_node(new_parent);
n->slots[slot] = assoc_array_node_to_ptr(new_n);
}
} else {
new_parent = ptr;
}
new_n = assoc_array_ptr_to_node(new_parent);
ascend_old_tree:
ptr = node->back_pointer;
if (assoc_array_ptr_is_shortcut(ptr)) {
shortcut = assoc_array_ptr_to_shortcut(ptr);
slot = shortcut->parent_slot;
cursor = shortcut->back_pointer;
} else {
slot = node->parent_slot;
cursor = ptr;
}
BUG_ON(!ptr);
node = assoc_array_ptr_to_node(cursor);
slot++;
goto continue_node;
gc_complete:
edit->set[0].to = new_root;
assoc_array_apply_edit(edit);
array->nr_leaves_on_tree = nr_leaves_on_tree;
return 0;
enomem:
pr_devel("enomem\n");
assoc_array_destroy_subtree(new_root, edit->ops);
kfree(edit);
return -ENOMEM;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'KEYS: Fix termination condition in assoc array garbage collection
This fixes CVE-2014-3631.
It is possible for an associative array to end up with a shortcut node at the
root of the tree if there are more than fan-out leaves in the tree, but they
all crowd into the same slot in the lowest level (ie. they all have the same
first nibble of their index keys).
When assoc_array_gc() returns back up the tree after scanning some leaves, it
can fall off of the root and crash because it assumes that the back pointer
from a shortcut (after label ascend_old_tree) must point to a normal node -
which isn't true of a shortcut node at the root.
Should we find we're ascending rootwards over a shortcut, we should check to
see if the backpointer is zero - and if it is, we have completed the scan.
This particular bug cannot occur if the root node is not a shortcut - ie. if
you have fewer than 17 keys in a keyring or if you have at least two keys that
sit into separate slots (eg. a keyring and a non keyring).
This can be reproduced by:
ring=`keyctl newring bar @s`
for ((i=1; i<=18; i++)); do last_key=`keyctl newring foo$i $ring`; done
keyctl timeout $last_key 2
Doing this:
echo 3 >/proc/sys/kernel/keys/gc_delay
first will speed things up.
If we do fall off of the top of the tree, we get the following oops:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
IP: [<ffffffff8136cea7>] assoc_array_gc+0x2f7/0x540
PGD dae15067 PUD cfc24067 PMD 0
Oops: 0000 [#1] SMP
Modules linked in: xt_nat xt_mark nf_conntrack_netbios_ns nf_conntrack_broadcast ip6t_rpfilter ip6t_REJECT xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_ni
CPU: 0 PID: 26011 Comm: kworker/0:1 Not tainted 3.14.9-200.fc20.x86_64 #1
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
Workqueue: events key_garbage_collector
task: ffff8800918bd580 ti: ffff8800aac14000 task.ti: ffff8800aac14000
RIP: 0010:[<ffffffff8136cea7>] [<ffffffff8136cea7>] assoc_array_gc+0x2f7/0x540
RSP: 0018:ffff8800aac15d40 EFLAGS: 00010206
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8800aaecacc0
RDX: ffff8800daecf440 RSI: 0000000000000001 RDI: ffff8800aadc2bc0
RBP: ffff8800aac15da8 R08: 0000000000000001 R09: 0000000000000003
R10: ffffffff8136ccc7 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000070 R15: 0000000000000001
FS: 0000000000000000(0000) GS:ffff88011fc00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000018 CR3: 00000000db10d000 CR4: 00000000000006f0
Stack:
ffff8800aac15d50 0000000000000011 ffff8800aac15db8 ffffffff812e2a70
ffff880091a00600 0000000000000000 ffff8800aadc2bc3 00000000cd42c987
ffff88003702df20 ffff88003702dfa0 0000000053b65c09 ffff8800aac15fd8
Call Trace:
[<ffffffff812e2a70>] ? keyring_detect_cycle_iterator+0x30/0x30
[<ffffffff812e3e75>] keyring_gc+0x75/0x80
[<ffffffff812e1424>] key_garbage_collector+0x154/0x3c0
[<ffffffff810a67b6>] process_one_work+0x176/0x430
[<ffffffff810a744b>] worker_thread+0x11b/0x3a0
[<ffffffff810a7330>] ? rescuer_thread+0x3b0/0x3b0
[<ffffffff810ae1a8>] kthread+0xd8/0xf0
[<ffffffff810ae0d0>] ? insert_kthread_work+0x40/0x40
[<ffffffff816ffb7c>] ret_from_fork+0x7c/0xb0
[<ffffffff810ae0d0>] ? insert_kthread_work+0x40/0x40
Code: 08 4c 8b 22 0f 84 bf 00 00 00 41 83 c7 01 49 83 e4 fc 41 83 ff 0f 4c 89 65 c0 0f 8f 5a fe ff ff 48 8b 45 c0 4d 63 cf 49 83 c1 02 <4e> 8b 34 c8 4d 85 f6 0f 84 be 00 00 00 41 f6 c6 01 0f 84 92
RIP [<ffffffff8136cea7>] assoc_array_gc+0x2f7/0x540
RSP <ffff8800aac15d40>
CR2: 0000000000000018
---[ end trace 1129028a088c0cbd ]---
Signed-off-by: David Howells <[email protected]>
Acked-by: Don Zickus <[email protected]>
Signed-off-by: James Morris <[email protected]>'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
struct ceph_crypto_key *secret,
void *buf, void *end)
{
void *p = buf;
char *dbuf;
char *ticket_buf;
u8 reply_struct_v;
u32 num;
int ret;
dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
if (!dbuf)
return -ENOMEM;
ret = -ENOMEM;
ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
if (!ticket_buf)
goto out_dbuf;
ceph_decode_8_safe(&p, end, reply_struct_v, bad);
if (reply_struct_v != 1)
return -EINVAL;
ceph_decode_32_safe(&p, end, num, bad);
dout("%d tickets\n", num);
while (num--) {
ret = process_one_ticket(ac, secret, &p, end,
dbuf, ticket_buf);
if (ret)
goto out;
}
ret = 0;
out:
kfree(ticket_buf);
out_dbuf:
kfree(dbuf);
return ret;
bad:
ret = -EINVAL;
goto out;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399', 'CWE-119'], 'message': 'libceph: do not hard code max auth ticket len
We hard code cephx auth ticket buffer size to 256 bytes. This isn't
enough for any moderate setups and, in case tickets themselves are not
encrypted, leads to buffer overflows (ceph_x_decrypt() errors out, but
ceph_decode_copy() doesn't - it's just a memcpy() wrapper). Since the
buffer is allocated dynamically anyway, allocated it a bit later, at
the point where we know how much is going to be needed.
Fixes: http://tracker.ceph.com/issues/8979
Cc: [email protected]
Signed-off-by: Ilya Dryomov <[email protected]>
Reviewed-by: Sage Weil <[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 ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
struct ceph_authorizer *a, size_t len)
{
struct ceph_x_authorizer *au = (void *)a;
struct ceph_x_ticket_handler *th;
int ret = 0;
struct ceph_x_authorize_reply reply;
void *p = au->reply_buf;
void *end = p + sizeof(au->reply_buf);
th = get_ticket_handler(ac, au->service);
if (IS_ERR(th))
return PTR_ERR(th);
ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply));
if (ret < 0)
return ret;
if (ret != sizeof(reply))
return -EPERM;
if (au->nonce + 1 != le64_to_cpu(reply.nonce_plus_one))
ret = -EPERM;
else
ret = 0;
dout("verify_authorizer_reply nonce %llx got %llx ret %d\n",
au->nonce, le64_to_cpu(reply.nonce_plus_one), ret);
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399', 'CWE-119'], 'message': 'libceph: do not hard code max auth ticket len
We hard code cephx auth ticket buffer size to 256 bytes. This isn't
enough for any moderate setups and, in case tickets themselves are not
encrypted, leads to buffer overflows (ceph_x_decrypt() errors out, but
ceph_decode_copy() doesn't - it's just a memcpy() wrapper). Since the
buffer is allocated dynamically anyway, allocated it a bit later, at
the point where we know how much is going to be needed.
Fixes: http://tracker.ceph.com/issues/8979
Cc: [email protected]
Signed-off-by: Ilya Dryomov <[email protected]>
Reviewed-by: Sage Weil <[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 rfbBool MallocFrameBuffer(rfbClient* client) {
if(client->frameBuffer)
free(client->frameBuffer);
client->frameBuffer=malloc(client->width*client->height*client->format.bitsPerPixel/8);
return client->frameBuffer?TRUE:FALSE;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix integer overflow in MallocFrameBuffer()
Promote integers to uint64_t to avoid integer overflow issue during
frame buffer allocation for very large screen sizes'</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: HandleRFBServerMessage(rfbClient* client)
{
rfbServerToClientMsg msg;
if (client->serverPort==-1)
client->vncRec->readTimestamp = TRUE;
if (!ReadFromRFBServer(client, (char *)&msg, 1))
return FALSE;
switch (msg.type) {
case rfbSetColourMapEntries:
{
/* TODO:
int i;
uint16_t rgb[3];
XColor xc;
if (!ReadFromRFBServer(client, ((char *)&msg) + 1,
sz_rfbSetColourMapEntriesMsg - 1))
return FALSE;
msg.scme.firstColour = rfbClientSwap16IfLE(msg.scme.firstColour);
msg.scme.nColours = rfbClientSwap16IfLE(msg.scme.nColours);
for (i = 0; i < msg.scme.nColours; i++) {
if (!ReadFromRFBServer(client, (char *)rgb, 6))
return FALSE;
xc.pixel = msg.scme.firstColour + i;
xc.red = rfbClientSwap16IfLE(rgb[0]);
xc.green = rfbClientSwap16IfLE(rgb[1]);
xc.blue = rfbClientSwap16IfLE(rgb[2]);
xc.flags = DoRed|DoGreen|DoBlue;
XStoreColor(dpy, cmap, &xc);
}
*/
break;
}
case rfbFramebufferUpdate:
{
rfbFramebufferUpdateRectHeader rect;
int linesToRead;
int bytesPerLine;
int i;
if (!ReadFromRFBServer(client, ((char *)&msg.fu) + 1,
sz_rfbFramebufferUpdateMsg - 1))
return FALSE;
msg.fu.nRects = rfbClientSwap16IfLE(msg.fu.nRects);
for (i = 0; i < msg.fu.nRects; i++) {
if (!ReadFromRFBServer(client, (char *)&rect, sz_rfbFramebufferUpdateRectHeader))
return FALSE;
rect.encoding = rfbClientSwap32IfLE(rect.encoding);
if (rect.encoding == rfbEncodingLastRect)
break;
rect.r.x = rfbClientSwap16IfLE(rect.r.x);
rect.r.y = rfbClientSwap16IfLE(rect.r.y);
rect.r.w = rfbClientSwap16IfLE(rect.r.w);
rect.r.h = rfbClientSwap16IfLE(rect.r.h);
if (rect.encoding == rfbEncodingXCursor ||
rect.encoding == rfbEncodingRichCursor) {
if (!HandleCursorShape(client,
rect.r.x, rect.r.y, rect.r.w, rect.r.h,
rect.encoding)) {
return FALSE;
}
continue;
}
if (rect.encoding == rfbEncodingPointerPos) {
if (!client->HandleCursorPos(client,rect.r.x, rect.r.y)) {
return FALSE;
}
continue;
}
if (rect.encoding == rfbEncodingKeyboardLedState) {
/* OK! We have received a keyboard state message!!! */
client->KeyboardLedStateEnabled = 1;
if (client->HandleKeyboardLedState!=NULL)
client->HandleKeyboardLedState(client, rect.r.x, 0);
/* stash it for the future */
client->CurrentKeyboardLedState = rect.r.x;
continue;
}
if (rect.encoding == rfbEncodingNewFBSize) {
client->width = rect.r.w;
client->height = rect.r.h;
client->updateRect.x = client->updateRect.y = 0;
client->updateRect.w = client->width;
client->updateRect.h = client->height;
client->MallocFrameBuffer(client);
SendFramebufferUpdateRequest(client, 0, 0, rect.r.w, rect.r.h, FALSE);
rfbClientLog("Got new framebuffer size: %dx%d\n", rect.r.w, rect.r.h);
continue;
}
/* rect.r.w=byte count */
if (rect.encoding == rfbEncodingSupportedMessages) {
int loop;
if (!ReadFromRFBServer(client, (char *)&client->supportedMessages, sz_rfbSupportedMessages))
return FALSE;
/* msgs is two sets of bit flags of supported messages client2server[] and server2client[] */
/* currently ignored by this library */
rfbClientLog("client2server supported messages (bit flags)\n");
for (loop=0;loop<32;loop+=8)
rfbClientLog("%02X: %04x %04x %04x %04x - %04x %04x %04x %04x\n", loop,
client->supportedMessages.client2server[loop], client->supportedMessages.client2server[loop+1],
client->supportedMessages.client2server[loop+2], client->supportedMessages.client2server[loop+3],
client->supportedMessages.client2server[loop+4], client->supportedMessages.client2server[loop+5],
client->supportedMessages.client2server[loop+6], client->supportedMessages.client2server[loop+7]);
rfbClientLog("server2client supported messages (bit flags)\n");
for (loop=0;loop<32;loop+=8)
rfbClientLog("%02X: %04x %04x %04x %04x - %04x %04x %04x %04x\n", loop,
client->supportedMessages.server2client[loop], client->supportedMessages.server2client[loop+1],
client->supportedMessages.server2client[loop+2], client->supportedMessages.server2client[loop+3],
client->supportedMessages.server2client[loop+4], client->supportedMessages.server2client[loop+5],
client->supportedMessages.server2client[loop+6], client->supportedMessages.server2client[loop+7]);
continue;
}
/* rect.r.w=byte count, rect.r.h=# of encodings */
if (rect.encoding == rfbEncodingSupportedEncodings) {
char *buffer;
buffer = malloc(rect.r.w);
if (!ReadFromRFBServer(client, buffer, rect.r.w))
{
free(buffer);
return FALSE;
}
/* buffer now contains rect.r.h # of uint32_t encodings that the server supports */
/* currently ignored by this library */
free(buffer);
continue;
}
/* rect.r.w=byte count */
if (rect.encoding == rfbEncodingServerIdentity) {
char *buffer;
buffer = malloc(rect.r.w+1);
if (!ReadFromRFBServer(client, buffer, rect.r.w))
{
free(buffer);
return FALSE;
}
buffer[rect.r.w]=0; /* null terminate, just in case */
rfbClientLog("Connected to Server \"%s\"\n", buffer);
free(buffer);
continue;
}
/* rfbEncodingUltraZip is a collection of subrects. x = # of subrects, and h is always 0 */
if (rect.encoding != rfbEncodingUltraZip)
{
if ((rect.r.x + rect.r.w > client->width) ||
(rect.r.y + rect.r.h > client->height))
{
rfbClientLog("Rect too large: %dx%d at (%d, %d)\n",
rect.r.w, rect.r.h, rect.r.x, rect.r.y);
return FALSE;
}
/* UltraVNC with scaling, will send rectangles with a zero W or H
*
if ((rect.encoding != rfbEncodingTight) &&
(rect.r.h * rect.r.w == 0))
{
rfbClientLog("Zero size rect - ignoring (encoding=%d (0x%08x) %dx, %dy, %dw, %dh)\n", rect.encoding, rect.encoding, rect.r.x, rect.r.y, rect.r.w, rect.r.h);
continue;
}
*/
/* If RichCursor encoding is used, we should prevent collisions
between framebuffer updates and cursor drawing operations. */
client->SoftCursorLockArea(client, rect.r.x, rect.r.y, rect.r.w, rect.r.h);
}
switch (rect.encoding) {
case rfbEncodingRaw: {
int y=rect.r.y, h=rect.r.h;
bytesPerLine = rect.r.w * client->format.bitsPerPixel / 8;
linesToRead = RFB_BUFFER_SIZE / bytesPerLine;
while (h > 0) {
if (linesToRead > h)
linesToRead = h;
if (!ReadFromRFBServer(client, client->buffer,bytesPerLine * linesToRead))
return FALSE;
CopyRectangle(client, (uint8_t *)client->buffer,
rect.r.x, y, rect.r.w,linesToRead);
h -= linesToRead;
y += linesToRead;
}
} break;
case rfbEncodingCopyRect:
{
rfbCopyRect cr;
if (!ReadFromRFBServer(client, (char *)&cr, sz_rfbCopyRect))
return FALSE;
cr.srcX = rfbClientSwap16IfLE(cr.srcX);
cr.srcY = rfbClientSwap16IfLE(cr.srcY);
/* If RichCursor encoding is used, we should extend our
"cursor lock area" (previously set to destination
rectangle) to the source rectangle as well. */
client->SoftCursorLockArea(client,
cr.srcX, cr.srcY, rect.r.w, rect.r.h);
if (client->GotCopyRect != NULL) {
client->GotCopyRect(client, cr.srcX, cr.srcY, rect.r.w, rect.r.h,
rect.r.x, rect.r.y);
} else
CopyRectangleFromRectangle(client,
cr.srcX, cr.srcY, rect.r.w, rect.r.h,
rect.r.x, rect.r.y);
break;
}
case rfbEncodingRRE:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleRRE8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (!HandleRRE16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 32:
if (!HandleRRE32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
break;
}
case rfbEncodingCoRRE:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleCoRRE8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (!HandleCoRRE16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 32:
if (!HandleCoRRE32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
break;
}
case rfbEncodingHextile:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleHextile8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (!HandleHextile16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 32:
if (!HandleHextile32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
break;
}
case rfbEncodingUltra:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleUltra8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (!HandleUltra16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 32:
if (!HandleUltra32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
break;
}
case rfbEncodingUltraZip:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleUltraZip8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (!HandleUltraZip16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 32:
if (!HandleUltraZip32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
break;
}
#ifdef LIBVNCSERVER_HAVE_LIBZ
case rfbEncodingZlib:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleZlib8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (!HandleZlib16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 32:
if (!HandleZlib32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
break;
}
#ifdef LIBVNCSERVER_HAVE_LIBJPEG
case rfbEncodingTight:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleTight8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (!HandleTight16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 32:
if (!HandleTight32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
break;
}
#endif
case rfbEncodingZRLE:
/* Fail safe for ZYWRLE unsupport VNC server. */
client->appData.qualityLevel = 9;
/* fall through */
case rfbEncodingZYWRLE:
{
switch (client->format.bitsPerPixel) {
case 8:
if (!HandleZRLE8(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
case 16:
if (client->si.format.greenMax > 0x1F) {
if (!HandleZRLE16(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
} else {
if (!HandleZRLE15(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
}
break;
case 32:
{
uint32_t maxColor=(client->format.redMax<<client->format.redShift)|
(client->format.greenMax<<client->format.greenShift)|
(client->format.blueMax<<client->format.blueShift);
if ((client->format.bigEndian && (maxColor&0xff)==0) ||
(!client->format.bigEndian && (maxColor&0xff000000)==0)) {
if (!HandleZRLE24(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
} else if (!client->format.bigEndian && (maxColor&0xff)==0) {
if (!HandleZRLE24Up(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
} else if (client->format.bigEndian && (maxColor&0xff000000)==0) {
if (!HandleZRLE24Down(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
} else if (!HandleZRLE32(client, rect.r.x,rect.r.y,rect.r.w,rect.r.h))
return FALSE;
break;
}
}
break;
}
#endif
#ifdef LIBVNCSERVER_CONFIG_LIBVA
case rfbEncodingH264:
{
if (!HandleH264(client, rect.r.x, rect.r.y, rect.r.w, rect.r.h))
return FALSE;
break;
}
#endif
default:
{
rfbBool handled = FALSE;
rfbClientProtocolExtension* e;
for(e = rfbClientExtensions; !handled && e; e = e->next)
if(e->handleEncoding && e->handleEncoding(client, &rect))
handled = TRUE;
if(!handled) {
rfbClientLog("Unknown rect encoding %d\n",
(int)rect.encoding);
return FALSE;
}
}
}
/* Now we may discard "soft cursor locks". */
client->SoftCursorUnlockScreen(client);
client->GotFrameBufferUpdate(client, rect.r.x, rect.r.y, rect.r.w, rect.r.h);
}
if (!SendIncrementalFramebufferUpdateRequest(client))
return FALSE;
if (client->FinishedFrameBufferUpdate)
client->FinishedFrameBufferUpdate(client);
break;
}
case rfbBell:
{
client->Bell(client);
break;
}
case rfbServerCutText:
{
char *buffer;
if (!ReadFromRFBServer(client, ((char *)&msg) + 1,
sz_rfbServerCutTextMsg - 1))
return FALSE;
msg.sct.length = rfbClientSwap32IfLE(msg.sct.length);
buffer = malloc(msg.sct.length+1);
if (!ReadFromRFBServer(client, buffer, msg.sct.length))
return FALSE;
buffer[msg.sct.length] = 0;
if (client->GotXCutText)
client->GotXCutText(client, buffer, msg.sct.length);
free(buffer);
break;
}
case rfbTextChat:
{
char *buffer=NULL;
if (!ReadFromRFBServer(client, ((char *)&msg) + 1,
sz_rfbTextChatMsg- 1))
return FALSE;
msg.tc.length = rfbClientSwap32IfLE(msg.sct.length);
switch(msg.tc.length) {
case rfbTextChatOpen:
rfbClientLog("Received TextChat Open\n");
if (client->HandleTextChat!=NULL)
client->HandleTextChat(client, (int)rfbTextChatOpen, NULL);
break;
case rfbTextChatClose:
rfbClientLog("Received TextChat Close\n");
if (client->HandleTextChat!=NULL)
client->HandleTextChat(client, (int)rfbTextChatClose, NULL);
break;
case rfbTextChatFinished:
rfbClientLog("Received TextChat Finished\n");
if (client->HandleTextChat!=NULL)
client->HandleTextChat(client, (int)rfbTextChatFinished, NULL);
break;
default:
buffer=malloc(msg.tc.length+1);
if (!ReadFromRFBServer(client, buffer, msg.tc.length))
{
free(buffer);
return FALSE;
}
/* Null Terminate <just in case> */
buffer[msg.tc.length]=0;
rfbClientLog("Received TextChat \"%s\"\n", buffer);
if (client->HandleTextChat!=NULL)
client->HandleTextChat(client, (int)msg.tc.length, buffer);
free(buffer);
break;
}
break;
}
case rfbXvp:
{
if (!ReadFromRFBServer(client, ((char *)&msg) + 1,
sz_rfbXvpMsg -1))
return FALSE;
SetClient2Server(client, rfbXvp);
/* technically, we only care what we can *send* to the server
* but, we set Server2Client Just in case it ever becomes useful
*/
SetServer2Client(client, rfbXvp);
if(client->HandleXvpMsg)
client->HandleXvpMsg(client, msg.xvp.version, msg.xvp.code);
break;
}
case rfbResizeFrameBuffer:
{
if (!ReadFromRFBServer(client, ((char *)&msg) + 1,
sz_rfbResizeFrameBufferMsg -1))
return FALSE;
client->width = rfbClientSwap16IfLE(msg.rsfb.framebufferWidth);
client->height = rfbClientSwap16IfLE(msg.rsfb.framebufferHeigth);
client->updateRect.x = client->updateRect.y = 0;
client->updateRect.w = client->width;
client->updateRect.h = client->height;
client->MallocFrameBuffer(client);
SendFramebufferUpdateRequest(client, 0, 0, client->width, client->height, FALSE);
rfbClientLog("Got new framebuffer size: %dx%d\n", client->width, client->height);
break;
}
case rfbPalmVNCReSizeFrameBuffer:
{
if (!ReadFromRFBServer(client, ((char *)&msg) + 1,
sz_rfbPalmVNCReSizeFrameBufferMsg -1))
return FALSE;
client->width = rfbClientSwap16IfLE(msg.prsfb.buffer_w);
client->height = rfbClientSwap16IfLE(msg.prsfb.buffer_h);
client->updateRect.x = client->updateRect.y = 0;
client->updateRect.w = client->width;
client->updateRect.h = client->height;
client->MallocFrameBuffer(client);
SendFramebufferUpdateRequest(client, 0, 0, client->width, client->height, FALSE);
rfbClientLog("Got new framebuffer size: %dx%d\n", client->width, client->height);
break;
}
default:
{
rfbBool handled = FALSE;
rfbClientProtocolExtension* e;
for(e = rfbClientExtensions; !handled && e; e = e->next)
if(e->handleMessage && e->handleMessage(client, &msg))
handled = TRUE;
if(!handled) {
char buffer[256];
rfbClientLog("Unknown message type %d from VNC server\n",msg.type);
ReadFromRFBServer(client, buffer, 256);
return FALSE;
}
}
}
return TRUE;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Check for MallocFrameBuffer() return value
If MallocFrameBuffer() returns FALSE, frame buffer pointer is left to
NULL. Subsequent writes into that buffer could lead to memory
corruption, or even arbitrary code execution.'</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: rfbProcessClientNormalMessage(rfbClientPtr cl)
{
int n=0;
rfbClientToServerMsg msg;
char *str;
int i;
uint32_t enc=0;
uint32_t lastPreferredEncoding = -1;
char encBuf[64];
char encBuf2[64];
#ifdef LIBVNCSERVER_WITH_WEBSOCKETS
if (cl->wsctx && webSocketCheckDisconnect(cl))
return;
#endif
if ((n = rfbReadExact(cl, (char *)&msg, 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
switch (msg.type) {
case rfbSetPixelFormat:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbSetPixelFormatMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
cl->format.bitsPerPixel = msg.spf.format.bitsPerPixel;
cl->format.depth = msg.spf.format.depth;
cl->format.bigEndian = (msg.spf.format.bigEndian ? TRUE : FALSE);
cl->format.trueColour = (msg.spf.format.trueColour ? TRUE : FALSE);
cl->format.redMax = Swap16IfLE(msg.spf.format.redMax);
cl->format.greenMax = Swap16IfLE(msg.spf.format.greenMax);
cl->format.blueMax = Swap16IfLE(msg.spf.format.blueMax);
cl->format.redShift = msg.spf.format.redShift;
cl->format.greenShift = msg.spf.format.greenShift;
cl->format.blueShift = msg.spf.format.blueShift;
cl->readyForSetColourMapEntries = TRUE;
cl->screen->setTranslateFunction(cl);
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbSetPixelFormatMsg, sz_rfbSetPixelFormatMsg);
return;
case rfbFixColourMapEntries:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbFixColourMapEntriesMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbSetPixelFormatMsg, sz_rfbSetPixelFormatMsg);
rfbLog("rfbProcessClientNormalMessage: %s",
"FixColourMapEntries unsupported\n");
rfbCloseClient(cl);
return;
/* NOTE: Some clients send us a set of encodings (ie: PointerPos) designed to enable/disable features...
* We may want to look into this...
* Example:
* case rfbEncodingXCursor:
* cl->enableCursorShapeUpdates = TRUE;
*
* Currently: cl->enableCursorShapeUpdates can *never* be turned off...
*/
case rfbSetEncodings:
{
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbSetEncodingsMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
msg.se.nEncodings = Swap16IfLE(msg.se.nEncodings);
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbSetEncodingsMsg+(msg.se.nEncodings*4),sz_rfbSetEncodingsMsg+(msg.se.nEncodings*4));
/*
* UltraVNC Client has the ability to adapt to changing network environments
* So, let's give it a change to tell us what it wants now!
*/
if (cl->preferredEncoding!=-1)
lastPreferredEncoding = cl->preferredEncoding;
/* Reset all flags to defaults (allows us to switch between PointerPos and Server Drawn Cursors) */
cl->preferredEncoding=-1;
cl->useCopyRect = FALSE;
cl->useNewFBSize = FALSE;
cl->cursorWasChanged = FALSE;
cl->useRichCursorEncoding = FALSE;
cl->enableCursorPosUpdates = FALSE;
cl->enableCursorShapeUpdates = FALSE;
cl->enableCursorShapeUpdates = FALSE;
cl->enableLastRectEncoding = FALSE;
cl->enableKeyboardLedState = FALSE;
cl->enableSupportedMessages = FALSE;
cl->enableSupportedEncodings = FALSE;
cl->enableServerIdentity = FALSE;
#if defined(LIBVNCSERVER_HAVE_LIBZ) || defined(LIBVNCSERVER_HAVE_LIBPNG)
cl->tightQualityLevel = -1;
#ifdef LIBVNCSERVER_HAVE_LIBJPEG
cl->tightCompressLevel = TIGHT_DEFAULT_COMPRESSION;
cl->turboSubsampLevel = TURBO_DEFAULT_SUBSAMP;
cl->turboQualityLevel = -1;
#endif
#endif
for (i = 0; i < msg.se.nEncodings; i++) {
if ((n = rfbReadExact(cl, (char *)&enc, 4)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
enc = Swap32IfLE(enc);
switch (enc) {
case rfbEncodingCopyRect:
cl->useCopyRect = TRUE;
break;
case rfbEncodingRaw:
case rfbEncodingRRE:
case rfbEncodingCoRRE:
case rfbEncodingHextile:
case rfbEncodingUltra:
#ifdef LIBVNCSERVER_HAVE_LIBZ
case rfbEncodingZlib:
case rfbEncodingZRLE:
case rfbEncodingZYWRLE:
#ifdef LIBVNCSERVER_HAVE_LIBJPEG
case rfbEncodingTight:
#endif
#endif
#ifdef LIBVNCSERVER_HAVE_LIBPNG
case rfbEncodingTightPng:
#endif
/* The first supported encoding is the 'preferred' encoding */
if (cl->preferredEncoding == -1)
cl->preferredEncoding = enc;
break;
case rfbEncodingXCursor:
if(!cl->screen->dontConvertRichCursorToXCursor) {
rfbLog("Enabling X-style cursor updates for client %s\n",
cl->host);
/* if cursor was drawn, hide the cursor */
if(!cl->enableCursorShapeUpdates)
rfbRedrawAfterHideCursor(cl,NULL);
cl->enableCursorShapeUpdates = TRUE;
cl->cursorWasChanged = TRUE;
}
break;
case rfbEncodingRichCursor:
rfbLog("Enabling full-color cursor updates for client %s\n",
cl->host);
/* if cursor was drawn, hide the cursor */
if(!cl->enableCursorShapeUpdates)
rfbRedrawAfterHideCursor(cl,NULL);
cl->enableCursorShapeUpdates = TRUE;
cl->useRichCursorEncoding = TRUE;
cl->cursorWasChanged = TRUE;
break;
case rfbEncodingPointerPos:
if (!cl->enableCursorPosUpdates) {
rfbLog("Enabling cursor position updates for client %s\n",
cl->host);
cl->enableCursorPosUpdates = TRUE;
cl->cursorWasMoved = TRUE;
}
break;
case rfbEncodingLastRect:
if (!cl->enableLastRectEncoding) {
rfbLog("Enabling LastRect protocol extension for client "
"%s\n", cl->host);
cl->enableLastRectEncoding = TRUE;
}
break;
case rfbEncodingNewFBSize:
if (!cl->useNewFBSize) {
rfbLog("Enabling NewFBSize protocol extension for client "
"%s\n", cl->host);
cl->useNewFBSize = TRUE;
}
break;
case rfbEncodingKeyboardLedState:
if (!cl->enableKeyboardLedState) {
rfbLog("Enabling KeyboardLedState protocol extension for client "
"%s\n", cl->host);
cl->enableKeyboardLedState = TRUE;
}
break;
case rfbEncodingSupportedMessages:
if (!cl->enableSupportedMessages) {
rfbLog("Enabling SupportedMessages protocol extension for client "
"%s\n", cl->host);
cl->enableSupportedMessages = TRUE;
}
break;
case rfbEncodingSupportedEncodings:
if (!cl->enableSupportedEncodings) {
rfbLog("Enabling SupportedEncodings protocol extension for client "
"%s\n", cl->host);
cl->enableSupportedEncodings = TRUE;
}
break;
case rfbEncodingServerIdentity:
if (!cl->enableServerIdentity) {
rfbLog("Enabling ServerIdentity protocol extension for client "
"%s\n", cl->host);
cl->enableServerIdentity = TRUE;
}
break;
case rfbEncodingXvp:
rfbLog("Enabling Xvp protocol extension for client "
"%s\n", cl->host);
if (!rfbSendXvp(cl, 1, rfbXvp_Init)) {
rfbCloseClient(cl);
return;
}
break;
default:
#if defined(LIBVNCSERVER_HAVE_LIBZ) || defined(LIBVNCSERVER_HAVE_LIBPNG)
if ( enc >= (uint32_t)rfbEncodingCompressLevel0 &&
enc <= (uint32_t)rfbEncodingCompressLevel9 ) {
cl->zlibCompressLevel = enc & 0x0F;
#ifdef LIBVNCSERVER_HAVE_LIBJPEG
cl->tightCompressLevel = enc & 0x0F;
rfbLog("Using compression level %d for client %s\n",
cl->tightCompressLevel, cl->host);
#endif
} else if ( enc >= (uint32_t)rfbEncodingQualityLevel0 &&
enc <= (uint32_t)rfbEncodingQualityLevel9 ) {
cl->tightQualityLevel = enc & 0x0F;
rfbLog("Using image quality level %d for client %s\n",
cl->tightQualityLevel, cl->host);
#ifdef LIBVNCSERVER_HAVE_LIBJPEG
cl->turboQualityLevel = tight2turbo_qual[enc & 0x0F];
cl->turboSubsampLevel = tight2turbo_subsamp[enc & 0x0F];
rfbLog("Using JPEG subsampling %d, Q%d for client %s\n",
cl->turboSubsampLevel, cl->turboQualityLevel, cl->host);
} else if ( enc >= (uint32_t)rfbEncodingFineQualityLevel0 + 1 &&
enc <= (uint32_t)rfbEncodingFineQualityLevel100 ) {
cl->turboQualityLevel = enc & 0xFF;
rfbLog("Using fine quality level %d for client %s\n",
cl->turboQualityLevel, cl->host);
} else if ( enc >= (uint32_t)rfbEncodingSubsamp1X &&
enc <= (uint32_t)rfbEncodingSubsampGray ) {
cl->turboSubsampLevel = enc & 0xFF;
rfbLog("Using subsampling level %d for client %s\n",
cl->turboSubsampLevel, cl->host);
#endif
} else
#endif
{
rfbExtensionData* e;
for(e = cl->extensions; e;) {
rfbExtensionData* next = e->next;
if(e->extension->enablePseudoEncoding &&
e->extension->enablePseudoEncoding(cl,
&e->data, (int)enc))
/* ext handles this encoding */
break;
e = next;
}
if(e == NULL) {
rfbBool handled = FALSE;
/* if the pseudo encoding is not handled by the
enabled extensions, search through all
extensions. */
rfbProtocolExtension* e;
for(e = rfbGetExtensionIterator(); e;) {
int* encs = e->pseudoEncodings;
while(encs && *encs!=0) {
if(*encs==(int)enc) {
void* data = NULL;
if(!e->enablePseudoEncoding(cl, &data, (int)enc)) {
rfbLog("Installed extension pretends to handle pseudo encoding 0x%x, but does not!\n",(int)enc);
} else {
rfbEnableExtension(cl, e, data);
handled = TRUE;
e = NULL;
break;
}
}
encs++;
}
if(e)
e = e->next;
}
rfbReleaseExtensionIterator();
if(!handled)
rfbLog("rfbProcessClientNormalMessage: "
"ignoring unsupported encoding type %s\n",
encodingName(enc,encBuf,sizeof(encBuf)));
}
}
}
}
if (cl->preferredEncoding == -1) {
if (lastPreferredEncoding==-1) {
cl->preferredEncoding = rfbEncodingRaw;
rfbLog("Defaulting to %s encoding for client %s\n", encodingName(cl->preferredEncoding,encBuf,sizeof(encBuf)),cl->host);
}
else {
cl->preferredEncoding = lastPreferredEncoding;
rfbLog("Sticking with %s encoding for client %s\n", encodingName(cl->preferredEncoding,encBuf,sizeof(encBuf)),cl->host);
}
}
else
{
if (lastPreferredEncoding==-1) {
rfbLog("Using %s encoding for client %s\n", encodingName(cl->preferredEncoding,encBuf,sizeof(encBuf)),cl->host);
} else {
rfbLog("Switching from %s to %s Encoding for client %s\n",
encodingName(lastPreferredEncoding,encBuf2,sizeof(encBuf2)),
encodingName(cl->preferredEncoding,encBuf,sizeof(encBuf)), cl->host);
}
}
if (cl->enableCursorPosUpdates && !cl->enableCursorShapeUpdates) {
rfbLog("Disabling cursor position updates for client %s\n",
cl->host);
cl->enableCursorPosUpdates = FALSE;
}
return;
}
case rfbFramebufferUpdateRequest:
{
sraRegionPtr tmpRegion;
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbFramebufferUpdateRequestMsg-1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbFramebufferUpdateRequestMsg,sz_rfbFramebufferUpdateRequestMsg);
/* The values come in based on the scaled screen, we need to convert them to
* values based on the main screen's coordinate system
*/
if(!rectSwapIfLEAndClip(&msg.fur.x,&msg.fur.y,&msg.fur.w,&msg.fur.h,cl))
{
rfbLog("Warning, ignoring rfbFramebufferUpdateRequest: %dXx%dY-%dWx%dH\n",msg.fur.x, msg.fur.y, msg.fur.w, msg.fur.h);
return;
}
tmpRegion =
sraRgnCreateRect(msg.fur.x,
msg.fur.y,
msg.fur.x+msg.fur.w,
msg.fur.y+msg.fur.h);
LOCK(cl->updateMutex);
sraRgnOr(cl->requestedRegion,tmpRegion);
if (!cl->readyForSetColourMapEntries) {
/* client hasn't sent a SetPixelFormat so is using server's */
cl->readyForSetColourMapEntries = TRUE;
if (!cl->format.trueColour) {
if (!rfbSetClientColourMap(cl, 0, 0)) {
sraRgnDestroy(tmpRegion);
TSIGNAL(cl->updateCond);
UNLOCK(cl->updateMutex);
return;
}
}
}
if (!msg.fur.incremental) {
sraRgnOr(cl->modifiedRegion,tmpRegion);
sraRgnSubtract(cl->copyRegion,tmpRegion);
}
TSIGNAL(cl->updateCond);
UNLOCK(cl->updateMutex);
sraRgnDestroy(tmpRegion);
return;
}
case rfbKeyEvent:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbKeyEventMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbKeyEventMsg, sz_rfbKeyEventMsg);
if(!cl->viewOnly) {
cl->screen->kbdAddEvent(msg.ke.down, (rfbKeySym)Swap32IfLE(msg.ke.key), cl);
}
return;
case rfbPointerEvent:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbPointerEventMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbPointerEventMsg, sz_rfbPointerEventMsg);
if (cl->screen->pointerClient && cl->screen->pointerClient != cl)
return;
if (msg.pe.buttonMask == 0)
cl->screen->pointerClient = NULL;
else
cl->screen->pointerClient = cl;
if(!cl->viewOnly) {
if (msg.pe.buttonMask != cl->lastPtrButtons ||
cl->screen->deferPtrUpdateTime == 0) {
cl->screen->ptrAddEvent(msg.pe.buttonMask,
ScaleX(cl->scaledScreen, cl->screen, Swap16IfLE(msg.pe.x)),
ScaleY(cl->scaledScreen, cl->screen, Swap16IfLE(msg.pe.y)),
cl);
cl->lastPtrButtons = msg.pe.buttonMask;
} else {
cl->lastPtrX = ScaleX(cl->scaledScreen, cl->screen, Swap16IfLE(msg.pe.x));
cl->lastPtrY = ScaleY(cl->scaledScreen, cl->screen, Swap16IfLE(msg.pe.y));
cl->lastPtrButtons = msg.pe.buttonMask;
}
}
return;
case rfbFileTransfer:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbFileTransferMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
msg.ft.size = Swap32IfLE(msg.ft.size);
msg.ft.length = Swap32IfLE(msg.ft.length);
/* record statistics in rfbProcessFileTransfer as length is filled with garbage when it is not valid */
rfbProcessFileTransfer(cl, msg.ft.contentType, msg.ft.contentParam, msg.ft.size, msg.ft.length);
return;
case rfbSetSW:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbSetSWMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
msg.sw.x = Swap16IfLE(msg.sw.x);
msg.sw.y = Swap16IfLE(msg.sw.y);
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbSetSWMsg, sz_rfbSetSWMsg);
/* msg.sw.status is not initialized in the ultraVNC viewer and contains random numbers (why???) */
rfbLog("Received a rfbSetSingleWindow(%d x, %d y)\n", msg.sw.x, msg.sw.y);
if (cl->screen->setSingleWindow!=NULL)
cl->screen->setSingleWindow(cl, msg.sw.x, msg.sw.y);
return;
case rfbSetServerInput:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbSetServerInputMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbSetServerInputMsg, sz_rfbSetServerInputMsg);
/* msg.sim.pad is not initialized in the ultraVNC viewer and contains random numbers (why???) */
/* msg.sim.pad = Swap16IfLE(msg.sim.pad); */
rfbLog("Received a rfbSetServerInput(%d status)\n", msg.sim.status);
if (cl->screen->setServerInput!=NULL)
cl->screen->setServerInput(cl, msg.sim.status);
return;
case rfbTextChat:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbTextChatMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
msg.tc.pad2 = Swap16IfLE(msg.tc.pad2);
msg.tc.length = Swap32IfLE(msg.tc.length);
switch (msg.tc.length) {
case rfbTextChatOpen:
case rfbTextChatClose:
case rfbTextChatFinished:
/* commands do not have text following */
/* Why couldn't they have used the pad byte??? */
str=NULL;
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbTextChatMsg, sz_rfbTextChatMsg);
break;
default:
if ((msg.tc.length>0) && (msg.tc.length<rfbTextMaxSize))
{
str = (char *)malloc(msg.tc.length);
if (str==NULL)
{
rfbLog("Unable to malloc %d bytes for a TextChat Message\n", msg.tc.length);
rfbCloseClient(cl);
return;
}
if ((n = rfbReadExact(cl, str, msg.tc.length)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
free(str);
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbTextChatMsg+msg.tc.length, sz_rfbTextChatMsg+msg.tc.length);
}
else
{
/* This should never happen */
rfbLog("client sent us a Text Message that is too big %d>%d\n", msg.tc.length, rfbTextMaxSize);
rfbCloseClient(cl);
return;
}
}
/* Note: length can be commands: rfbTextChatOpen, rfbTextChatClose, and rfbTextChatFinished
* at which point, the str is NULL (as it is not sent)
*/
if (cl->screen->setTextChat!=NULL)
cl->screen->setTextChat(cl, msg.tc.length, str);
free(str);
return;
case rfbClientCutText:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbClientCutTextMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
msg.cct.length = Swap32IfLE(msg.cct.length);
str = (char *)malloc(msg.cct.length);
if (str == NULL) {
rfbLogPerror("rfbProcessClientNormalMessage: not enough memory");
rfbCloseClient(cl);
return;
}
if ((n = rfbReadExact(cl, str, msg.cct.length)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
free(str);
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbClientCutTextMsg+msg.cct.length, sz_rfbClientCutTextMsg+msg.cct.length);
if(!cl->viewOnly) {
cl->screen->setXCutText(str, msg.cct.length, cl);
}
free(str);
return;
case rfbPalmVNCSetScaleFactor:
cl->PalmVNC = TRUE;
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbSetScaleMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbSetScaleMsg, sz_rfbSetScaleMsg);
rfbLog("rfbSetScale(%d)\n", msg.ssc.scale);
rfbScalingSetup(cl,cl->screen->width/msg.ssc.scale, cl->screen->height/msg.ssc.scale);
rfbSendNewScaleSize(cl);
return;
case rfbSetScale:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbSetScaleMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbSetScaleMsg, sz_rfbSetScaleMsg);
rfbLog("rfbSetScale(%d)\n", msg.ssc.scale);
rfbScalingSetup(cl,cl->screen->width/msg.ssc.scale, cl->screen->height/msg.ssc.scale);
rfbSendNewScaleSize(cl);
return;
case rfbXvp:
if ((n = rfbReadExact(cl, ((char *)&msg) + 1,
sz_rfbXvpMsg - 1)) <= 0) {
if (n != 0)
rfbLogPerror("rfbProcessClientNormalMessage: read");
rfbCloseClient(cl);
return;
}
rfbStatRecordMessageRcvd(cl, msg.type, sz_rfbXvpMsg, sz_rfbXvpMsg);
/* only version when is defined, so echo back a fail */
if(msg.xvp.version != 1) {
rfbSendXvp(cl, msg.xvp.version, rfbXvp_Fail);
}
else {
/* if the hook exists and fails, send a fail msg */
if(cl->screen->xvpHook && !cl->screen->xvpHook(cl, msg.xvp.version, msg.xvp.code))
rfbSendXvp(cl, 1, rfbXvp_Fail);
}
return;
default:
{
rfbExtensionData *e,*next;
for(e=cl->extensions; e;) {
next = e->next;
if(e->extension->handleMessage &&
e->extension->handleMessage(cl, e->data, &msg))
{
rfbStatRecordMessageRcvd(cl, msg.type, 0, 0); /* Extension should handle this */
return;
}
e = next;
}
rfbLog("rfbProcessClientNormalMessage: unknown message type %d\n",
msg.type);
rfbLog(" ... closing connection\n");
rfbCloseClient(cl);
return;
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Do not accept a scaling factor of zero on PalmVNCSetScaleFactor and SetScale client->server messages. This would cause a division by zero and crash the server.'</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: evbuffer_add(struct evbuffer *buf, const void *data, size_t datlen)
{
size_t need = buf->misalign + buf->off + datlen;
size_t oldoff = buf->off;
if (buf->totallen < need) {
if (evbuffer_expand(buf, datlen) == -1)
return (-1);
}
memcpy(buf->buffer + buf->off, data, datlen);
buf->off += datlen;
if (datlen && buf->cb != NULL)
(*buf->cb)(buf, oldoff, buf->off, buf->cbarg);
return (0);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 1.4
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.'</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: evbuffer_ptr_memcmp(const struct evbuffer *buf, const struct evbuffer_ptr *pos,
const char *mem, size_t len)
{
struct evbuffer_chain *chain;
size_t position;
int r;
ASSERT_EVBUFFER_LOCKED(buf);
if (pos->pos + len > buf->total_len)
return -1;
chain = pos->_internal.chain;
position = pos->_internal.pos_in_chain;
while (len && chain) {
size_t n_comparable;
if (len + position > chain->off)
n_comparable = chain->off - position;
else
n_comparable = len;
r = memcmp(chain->buffer + chain->misalign + position, mem,
n_comparable);
if (r)
return r;
mem += n_comparable;
len -= n_comparable;
position = 0;
chain = chain->next;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.0
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_add_vprintf(struct evbuffer *buf, const char *fmt, va_list ap)
{
char *buffer;
size_t space;
int sz, result = -1;
va_list aq;
struct evbuffer_chain *chain;
EVBUFFER_LOCK(buf);
if (buf->freeze_end) {
goto done;
}
/* make sure that at least some space is available */
if ((chain = evbuffer_expand_singlechain(buf, 64)) == NULL)
goto done;
for (;;) {
#if 0
size_t used = chain->misalign + chain->off;
buffer = (char *)chain->buffer + chain->misalign + chain->off;
EVUTIL_ASSERT(chain->buffer_len >= used);
space = chain->buffer_len - used;
#endif
buffer = (char*) CHAIN_SPACE_PTR(chain);
space = (size_t) CHAIN_SPACE_LEN(chain);
#ifndef va_copy
#define va_copy(dst, src) memcpy(&(dst), &(src), sizeof(va_list))
#endif
va_copy(aq, ap);
sz = evutil_vsnprintf(buffer, space, fmt, aq);
va_end(aq);
if (sz < 0)
goto done;
if ((size_t)sz < space) {
chain->off += sz;
buf->total_len += sz;
buf->n_add_for_cb += sz;
advance_last_with_data(buf);
evbuffer_invoke_callbacks(buf);
result = sz;
goto done;
}
if ((chain = evbuffer_expand_singlechain(buf, sz + 1)) == NULL)
goto done;
}
/* NOTREACHED */
done:
EVBUFFER_UNLOCK(buf);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.0
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_ptr_set(struct evbuffer *buf, struct evbuffer_ptr *pos,
size_t position, enum evbuffer_ptr_how how)
{
size_t left = position;
struct evbuffer_chain *chain = NULL;
EVBUFFER_LOCK(buf);
switch (how) {
case EVBUFFER_PTR_SET:
chain = buf->first;
pos->pos = position;
position = 0;
break;
case EVBUFFER_PTR_ADD:
/* this avoids iterating over all previous chains if
we just want to advance the position */
chain = pos->_internal.chain;
pos->pos += position;
position = pos->_internal.pos_in_chain;
break;
}
while (chain && position + left >= chain->off) {
left -= chain->off - position;
chain = chain->next;
position = 0;
}
if (chain) {
pos->_internal.chain = chain;
pos->_internal.pos_in_chain = position + left;
} else {
pos->_internal.chain = NULL;
pos->pos = -1;
}
EVBUFFER_UNLOCK(buf);
return chain != NULL ? 0 : -1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.0
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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_n_bytes_readable_on_socket(evutil_socket_t fd)
{
#if defined(FIONREAD) && defined(WIN32)
unsigned long lng = EVBUFFER_MAX_READ;
if (ioctlsocket(fd, FIONREAD, &lng) < 0)
return -1;
return (int)lng;
#elif defined(FIONREAD)
int n = EVBUFFER_MAX_READ;
if (ioctl(fd, FIONREAD, &n) < 0)
return -1;
return n;
#else
return EVBUFFER_MAX_READ;
#endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.0
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_chain_new(size_t size)
{
struct evbuffer_chain *chain;
size_t to_alloc;
size += EVBUFFER_CHAIN_SIZE;
/* get the next largest memory that can hold the buffer */
to_alloc = MIN_BUFFER_SIZE;
while (to_alloc < size)
to_alloc <<= 1;
/* we get everything in one chunk */
if ((chain = mm_malloc(to_alloc)) == NULL)
return (NULL);
memset(chain, 0, EVBUFFER_CHAIN_SIZE);
chain->buffer_len = to_alloc - EVBUFFER_CHAIN_SIZE;
/* this way we can manipulate the buffer to different addresses,
* which is required for mmap for example.
*/
chain->buffer = EVBUFFER_CHAIN_EXTRA(u_char, chain);
return (chain);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.0
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_prepend(struct evbuffer *buf, const void *data, size_t datlen)
{
struct evbuffer_chain *chain, *tmp;
int result = -1;
EVBUFFER_LOCK(buf);
if (buf->freeze_start) {
goto done;
}
chain = buf->first;
if (chain == NULL) {
chain = evbuffer_chain_new(datlen);
if (!chain)
goto done;
evbuffer_chain_insert(buf, chain);
}
/* we cannot touch immutable buffers */
if ((chain->flags & EVBUFFER_IMMUTABLE) == 0) {
/* If this chain is empty, we can treat it as
* 'empty at the beginning' rather than 'empty at the end' */
if (chain->off == 0)
chain->misalign = chain->buffer_len;
if ((size_t)chain->misalign >= datlen) {
/* we have enough space to fit everything */
memcpy(chain->buffer + chain->misalign - datlen,
data, datlen);
chain->off += datlen;
chain->misalign -= datlen;
buf->total_len += datlen;
buf->n_add_for_cb += datlen;
goto out;
} else if (chain->misalign) {
/* we can only fit some of the data. */
memcpy(chain->buffer,
(char*)data + datlen - chain->misalign,
(size_t)chain->misalign);
chain->off += (size_t)chain->misalign;
buf->total_len += (size_t)chain->misalign;
buf->n_add_for_cb += (size_t)chain->misalign;
datlen -= (size_t)chain->misalign;
chain->misalign = 0;
}
}
/* we need to add another chain */
if ((tmp = evbuffer_chain_new(datlen)) == NULL)
goto done;
buf->first = tmp;
if (buf->last_with_datap == &buf->first)
buf->last_with_datap = &tmp->next;
tmp->next = chain;
tmp->off = datlen;
tmp->misalign = tmp->buffer_len - datlen;
memcpy(tmp->buffer + tmp->misalign, data, datlen);
buf->total_len += datlen;
buf->n_add_for_cb += (size_t)chain->misalign;
out:
evbuffer_invoke_callbacks(buf);
result = 0;
done:
EVBUFFER_UNLOCK(buf);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.0
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_expand_singlechain(struct evbuffer *buf, size_t datlen)
{
struct evbuffer_chain *chain, **chainp;
struct evbuffer_chain *result = NULL;
ASSERT_EVBUFFER_LOCKED(buf);
chainp = buf->last_with_datap;
/* XXX If *chainp is no longer writeable, but has enough space in its
* misalign, this might be a bad idea: we could still use *chainp, not
* (*chainp)->next. */
if (*chainp && CHAIN_SPACE_LEN(*chainp) == 0)
chainp = &(*chainp)->next;
/* 'chain' now points to the first chain with writable space (if any)
* We will either use it, realign it, replace it, or resize it. */
chain = *chainp;
if (chain == NULL ||
(chain->flags & (EVBUFFER_IMMUTABLE|EVBUFFER_MEM_PINNED_ANY))) {
/* We can't use the last_with_data chain at all. Just add a
* new one that's big enough. */
goto insert_new;
}
/* If we can fit all the data, then we don't have to do anything */
if (CHAIN_SPACE_LEN(chain) >= datlen) {
result = chain;
goto ok;
}
/* If the chain is completely empty, just replace it by adding a new
* empty chain. */
if (chain->off == 0) {
goto insert_new;
}
/* If the misalignment plus the remaining space fulfills our data
* needs, we could just force an alignment to happen. Afterwards, we
* have enough space. But only do this if we're saving a lot of space
* and not moving too much data. Otherwise the space savings are
* probably offset by the time lost in copying.
*/
if (evbuffer_chain_should_realign(chain, datlen)) {
evbuffer_chain_align(chain);
result = chain;
goto ok;
}
/* At this point, we can either resize the last chunk with space in
* it, use the next chunk after it, or If we add a new chunk, we waste
* CHAIN_SPACE_LEN(chain) bytes in the former last chunk. If we
* resize, we have to copy chain->off bytes.
*/
/* Would expanding this chunk be affordable and worthwhile? */
if (CHAIN_SPACE_LEN(chain) < chain->buffer_len / 8 ||
chain->off > MAX_TO_COPY_IN_EXPAND) {
/* It's not worth resizing this chain. Can the next one be
* used? */
if (chain->next && CHAIN_SPACE_LEN(chain->next) >= datlen) {
/* Yes, we can just use the next chain (which should
* be empty. */
result = chain->next;
goto ok;
} else {
/* No; append a new chain (which will free all
* terminal empty chains.) */
goto insert_new;
}
} else {
/* Okay, we're going to try to resize this chain: Not doing so
* would waste at least 1/8 of its current allocation, and we
* can do so without having to copy more than
* MAX_TO_COPY_IN_EXPAND bytes. */
/* figure out how much space we need */
size_t length = chain->off + datlen;
struct evbuffer_chain *tmp = evbuffer_chain_new(length);
if (tmp == NULL)
goto err;
/* copy the data over that we had so far */
tmp->off = chain->off;
memcpy(tmp->buffer, chain->buffer + chain->misalign,
chain->off);
/* fix up the list */
EVUTIL_ASSERT(*chainp == chain);
result = *chainp = tmp;
if (buf->last == chain)
buf->last = tmp;
tmp->next = chain->next;
evbuffer_chain_free(chain);
goto ok;
}
insert_new:
result = evbuffer_chain_insert_new(buf, datlen);
if (!result)
goto err;
ok:
EVUTIL_ASSERT(result);
EVUTIL_ASSERT(CHAIN_SPACE_LEN(result) >= datlen);
err:
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.0
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_ptr_subtract(struct evbuffer *buf, struct evbuffer_ptr *pos,
size_t howfar)
{
if (howfar > (size_t)pos->pos)
return -1;
if (pos->internal_.chain && howfar <= pos->internal_.pos_in_chain) {
pos->internal_.pos_in_chain -= howfar;
pos->pos -= howfar;
return 0;
} else {
const size_t newpos = pos->pos - howfar;
/* Here's the inefficient part: it walks over the
* chains until we hit newpos. */
return evbuffer_ptr_set(buf, pos, newpos, EVBUFFER_PTR_SET);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.1
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_copyout_from(struct evbuffer *buf, const struct evbuffer_ptr *pos,
void *data_out, size_t datlen)
{
/*XXX fails badly on sendfile case. */
struct evbuffer_chain *chain;
char *data = data_out;
size_t nread;
ev_ssize_t result = 0;
size_t pos_in_chain;
EVBUFFER_LOCK(buf);
if (pos) {
chain = pos->internal_.chain;
pos_in_chain = pos->internal_.pos_in_chain;
if (datlen + pos->pos > buf->total_len)
datlen = buf->total_len - pos->pos;
} else {
chain = buf->first;
pos_in_chain = 0;
if (datlen > buf->total_len)
datlen = buf->total_len;
}
if (datlen == 0)
goto done;
if (buf->freeze_start) {
result = -1;
goto done;
}
nread = datlen;
while (datlen && datlen >= chain->off - pos_in_chain) {
size_t copylen = chain->off - pos_in_chain;
memcpy(data,
chain->buffer + chain->misalign + pos_in_chain,
copylen);
data += copylen;
datlen -= copylen;
chain = chain->next;
pos_in_chain = 0;
EVUTIL_ASSERT(chain || datlen==0);
}
if (datlen) {
EVUTIL_ASSERT(chain);
memcpy(data, chain->buffer + chain->misalign + pos_in_chain,
datlen);
}
result = nread;
done:
EVBUFFER_UNLOCK(buf);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.1
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_chain_new(size_t size)
{
struct evbuffer_chain *chain;
size_t to_alloc;
size += EVBUFFER_CHAIN_SIZE;
/* get the next largest memory that can hold the buffer */
to_alloc = MIN_BUFFER_SIZE;
while (to_alloc < size)
to_alloc <<= 1;
/* we get everything in one chunk */
if ((chain = mm_malloc(to_alloc)) == NULL)
return (NULL);
memset(chain, 0, EVBUFFER_CHAIN_SIZE);
chain->buffer_len = to_alloc - EVBUFFER_CHAIN_SIZE;
/* this way we can manipulate the buffer to different addresses,
* which is required for mmap for example.
*/
chain->buffer = EVBUFFER_CHAIN_EXTRA(u_char, chain);
chain->refcnt = 1;
return (chain);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.1
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_ptr_set(struct evbuffer *buf, struct evbuffer_ptr *pos,
size_t position, enum evbuffer_ptr_how how)
{
size_t left = position;
struct evbuffer_chain *chain = NULL;
int result = 0;
EVBUFFER_LOCK(buf);
switch (how) {
case EVBUFFER_PTR_SET:
chain = buf->first;
pos->pos = position;
position = 0;
break;
case EVBUFFER_PTR_ADD:
/* this avoids iterating over all previous chains if
we just want to advance the position */
chain = pos->internal_.chain;
pos->pos += position;
position = pos->internal_.pos_in_chain;
break;
}
while (chain && position + left >= chain->off) {
left -= chain->off - position;
chain = chain->next;
position = 0;
}
if (chain) {
pos->internal_.chain = chain;
pos->internal_.pos_in_chain = position + left;
} else if (left == 0) {
/* The first byte in the (nonexistent) chain after the last chain */
pos->internal_.chain = NULL;
pos->internal_.pos_in_chain = 0;
} else {
PTR_NOT_FOUND(pos);
result = -1;
}
EVBUFFER_UNLOCK(buf);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.1
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_prepend(struct evbuffer *buf, const void *data, size_t datlen)
{
struct evbuffer_chain *chain, *tmp;
int result = -1;
EVBUFFER_LOCK(buf);
if (buf->freeze_start) {
goto done;
}
chain = buf->first;
if (chain == NULL) {
chain = evbuffer_chain_new(datlen);
if (!chain)
goto done;
evbuffer_chain_insert(buf, chain);
}
/* we cannot touch immutable buffers */
if ((chain->flags & EVBUFFER_IMMUTABLE) == 0) {
/* If this chain is empty, we can treat it as
* 'empty at the beginning' rather than 'empty at the end' */
if (chain->off == 0)
chain->misalign = chain->buffer_len;
if ((size_t)chain->misalign >= datlen) {
/* we have enough space to fit everything */
memcpy(chain->buffer + chain->misalign - datlen,
data, datlen);
chain->off += datlen;
chain->misalign -= datlen;
buf->total_len += datlen;
buf->n_add_for_cb += datlen;
goto out;
} else if (chain->misalign) {
/* we can only fit some of the data. */
memcpy(chain->buffer,
(char*)data + datlen - chain->misalign,
(size_t)chain->misalign);
chain->off += (size_t)chain->misalign;
buf->total_len += (size_t)chain->misalign;
buf->n_add_for_cb += (size_t)chain->misalign;
datlen -= (size_t)chain->misalign;
chain->misalign = 0;
}
}
/* we need to add another chain */
if ((tmp = evbuffer_chain_new(datlen)) == NULL)
goto done;
buf->first = tmp;
if (buf->last_with_datap == &buf->first)
buf->last_with_datap = &tmp->next;
tmp->next = chain;
tmp->off = datlen;
tmp->misalign = tmp->buffer_len - datlen;
memcpy(tmp->buffer + tmp->misalign, data, datlen);
buf->total_len += datlen;
buf->n_add_for_cb += (size_t)chain->misalign;
out:
evbuffer_invoke_callbacks_(buf);
result = 0;
done:
EVBUFFER_UNLOCK(buf);
return result;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.1
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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: evbuffer_expand_fast_(struct evbuffer *buf, size_t datlen, int n)
{
struct evbuffer_chain *chain = buf->last, *tmp, *next;
size_t avail;
int used;
ASSERT_EVBUFFER_LOCKED(buf);
EVUTIL_ASSERT(n >= 2);
if (chain == NULL || (chain->flags & EVBUFFER_IMMUTABLE)) {
/* There is no last chunk, or we can't touch the last chunk.
* Just add a new chunk. */
chain = evbuffer_chain_new(datlen);
if (chain == NULL)
return (-1);
evbuffer_chain_insert(buf, chain);
return (0);
}
used = 0; /* number of chains we're using space in. */
avail = 0; /* how much space they have. */
/* How many bytes can we stick at the end of buffer as it is? Iterate
* over the chains at the end of the buffer, tring to see how much
* space we have in the first n. */
for (chain = *buf->last_with_datap; chain; chain = chain->next) {
if (chain->off) {
size_t space = (size_t) CHAIN_SPACE_LEN(chain);
EVUTIL_ASSERT(chain == *buf->last_with_datap);
if (space) {
avail += space;
++used;
}
} else {
/* No data in chain; realign it. */
chain->misalign = 0;
avail += chain->buffer_len;
++used;
}
if (avail >= datlen) {
/* There is already enough space. Just return */
return (0);
}
if (used == n)
break;
}
/* There wasn't enough space in the first n chains with space in
* them. Either add a new chain with enough space, or replace all
* empty chains with one that has enough space, depending on n. */
if (used < n) {
/* The loop ran off the end of the chains before it hit n
* chains; we can add another. */
EVUTIL_ASSERT(chain == NULL);
tmp = evbuffer_chain_new(datlen - avail);
if (tmp == NULL)
return (-1);
buf->last->next = tmp;
buf->last = tmp;
/* (we would only set last_with_data if we added the first
* chain. But if the buffer had no chains, we would have
* just allocated a new chain earlier) */
return (0);
} else {
/* Nuke _all_ the empty chains. */
int rmv_all = 0; /* True iff we removed last_with_data. */
chain = *buf->last_with_datap;
if (!chain->off) {
EVUTIL_ASSERT(chain == buf->first);
rmv_all = 1;
avail = 0;
} else {
avail = (size_t) CHAIN_SPACE_LEN(chain);
chain = chain->next;
}
for (; chain; chain = next) {
next = chain->next;
EVUTIL_ASSERT(chain->off == 0);
evbuffer_chain_free(chain);
}
tmp = evbuffer_chain_new(datlen - avail);
if (tmp == NULL) {
if (rmv_all) {
ZERO_CHAIN(buf);
} else {
buf->last = *buf->last_with_datap;
(*buf->last_with_datap)->next = NULL;
}
return (-1);
}
if (rmv_all) {
buf->first = buf->last = tmp;
buf->last_with_datap = &buf->first;
} else {
(*buf->last_with_datap)->next = tmp;
buf->last = tmp;
}
return (0);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fix CVE-2014-6272 in Libevent 2.1
For this fix, we need to make sure that passing too-large inputs to
the evbuffer functions can't make us do bad things with the heap.
Also, lower the maximum chunk size to the lower of off_t, size_t maximum.
This is necessary since otherwise we could get into an infinite loop
if we make a chunk that 'misalign' cannot index into.'</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 __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
{
struct kvm_pit *pit = vcpu->kvm->arch.vpit;
struct hrtimer *timer;
if (!kvm_vcpu_is_bsp(vcpu) || !pit)
return;
timer = &pit->pit_state.timer;
if (hrtimer_cancel(timer))
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-362'], 'message': 'KVM: x86: Improve thread safety in pit
There's a race condition in the PIT emulation code in KVM. In
__kvm_migrate_pit_timer the pit_timer object is accessed without
synchronization. If the race condition occurs at the wrong time this
can crash the host kernel.
This fixes CVE-2014-3611.
Cc: [email protected]
Signed-off-by: Andrew Honig <[email protected]>
Signed-off-by: Paolo Bonzini <[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 sctp_verify_asconf(const struct sctp_association *asoc,
struct sctp_paramhdr *param_hdr, void *chunk_end,
struct sctp_paramhdr **errp) {
sctp_addip_param_t *asconf_param;
union sctp_params param;
int length, plen;
param.v = (sctp_paramhdr_t *) param_hdr;
while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) {
length = ntohs(param.p->length);
*errp = param.p;
if (param.v > chunk_end - length ||
length < sizeof(sctp_paramhdr_t))
return 0;
switch (param.p->type) {
case SCTP_PARAM_ADD_IP:
case SCTP_PARAM_DEL_IP:
case SCTP_PARAM_SET_PRIMARY:
asconf_param = (sctp_addip_param_t *)param.v;
plen = ntohs(asconf_param->param_hdr.length);
if (plen < sizeof(sctp_addip_param_t) +
sizeof(sctp_paramhdr_t))
return 0;
break;
case SCTP_PARAM_SUCCESS_REPORT:
case SCTP_PARAM_ADAPTATION_LAYER_IND:
if (length != sizeof(sctp_addip_param_t))
return 0;
break;
default:
break;
}
param.v += WORD_ROUND(length);
}
if (param.v != chunk_end)
return 0;
return 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-399'], 'message': 'net: sctp: fix skb_over_panic when receiving malformed ASCONF chunks
Commit 6f4c618ddb0 ("SCTP : Add paramters validity check for
ASCONF chunk") added basic verification of ASCONF chunks, however,
it is still possible to remotely crash a server by sending a
special crafted ASCONF chunk, even up to pre 2.6.12 kernels:
skb_over_panic: text:ffffffffa01ea1c3 len:31056 put:30768
head:ffff88011bd81800 data:ffff88011bd81800 tail:0x7950
end:0x440 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:129!
[...]
Call Trace:
<IRQ>
[<ffffffff8144fb1c>] skb_put+0x5c/0x70
[<ffffffffa01ea1c3>] sctp_addto_chunk+0x63/0xd0 [sctp]
[<ffffffffa01eadaf>] sctp_process_asconf+0x1af/0x540 [sctp]
[<ffffffff8152d025>] ? _read_unlock_bh+0x15/0x20
[<ffffffffa01e0038>] sctp_sf_do_asconf+0x168/0x240 [sctp]
[<ffffffffa01e3751>] sctp_do_sm+0x71/0x1210 [sctp]
[<ffffffff8147645d>] ? fib_rules_lookup+0xad/0xf0
[<ffffffffa01e6b22>] ? sctp_cmp_addr_exact+0x32/0x40 [sctp]
[<ffffffffa01e8393>] sctp_assoc_bh_rcv+0xd3/0x180 [sctp]
[<ffffffffa01ee986>] sctp_inq_push+0x56/0x80 [sctp]
[<ffffffffa01fcc42>] sctp_rcv+0x982/0xa10 [sctp]
[<ffffffffa01d5123>] ? ipt_local_in_hook+0x23/0x28 [iptable_filter]
[<ffffffff8148bdc9>] ? nf_iterate+0x69/0xb0
[<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
[<ffffffff8148bf86>] ? nf_hook_slow+0x76/0x120
[<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
[<ffffffff81496ded>] ip_local_deliver_finish+0xdd/0x2d0
[<ffffffff81497078>] ip_local_deliver+0x98/0xa0
[<ffffffff8149653d>] ip_rcv_finish+0x12d/0x440
[<ffffffff81496ac5>] ip_rcv+0x275/0x350
[<ffffffff8145c88b>] __netif_receive_skb+0x4ab/0x750
[<ffffffff81460588>] netif_receive_skb+0x58/0x60
This can be triggered e.g., through a simple scripted nmap
connection scan injecting the chunk after the handshake, for
example, ...
-------------- INIT[ASCONF; ASCONF_ACK] ------------->
<----------- INIT-ACK[ASCONF; ASCONF_ACK] ------------
-------------------- COOKIE-ECHO -------------------->
<-------------------- COOKIE-ACK ---------------------
------------------ ASCONF; UNKNOWN ------------------>
... where ASCONF chunk of length 280 contains 2 parameters ...
1) Add IP address parameter (param length: 16)
2) Add/del IP address parameter (param length: 255)
... followed by an UNKNOWN chunk of e.g. 4 bytes. Here, the
Address Parameter in the ASCONF chunk is even missing, too.
This is just an example and similarly-crafted ASCONF chunks
could be used just as well.
The ASCONF chunk passes through sctp_verify_asconf() as all
parameters passed sanity checks, and after walking, we ended
up successfully at the chunk end boundary, and thus may invoke
sctp_process_asconf(). Parameter walking is done with
WORD_ROUND() to take padding into account.
In sctp_process_asconf()'s TLV processing, we may fail in
sctp_process_asconf_param() e.g., due to removal of the IP
address that is also the source address of the packet containing
the ASCONF chunk, and thus we need to add all TLVs after the
failure to our ASCONF response to remote via helper function
sctp_add_asconf_response(), which basically invokes a
sctp_addto_chunk() adding the error parameters to the given
skb.
When walking to the next parameter this time, we proceed
with ...
length = ntohs(asconf_param->param_hdr.length);
asconf_param = (void *)asconf_param + length;
... instead of the WORD_ROUND()'ed length, thus resulting here
in an off-by-one that leads to reading the follow-up garbage
parameter length of 12336, and thus throwing an skb_over_panic
for the reply when trying to sctp_addto_chunk() next time,
which implicitly calls the skb_put() with that length.
Fix it by using sctp_walk_params() [ which is also used in
INIT parameter processing ] macro in the verification *and*
in ASCONF processing: it will make sure we don't spill over,
that we walk parameters WORD_ROUND()'ed. Moreover, we're being
more defensive and guard against unknown parameter types and
missized addresses.
Joint work with Vlad Yasevich.
Fixes: b896b82be4ae ("[SCTP] ADDIP: Support for processing incoming ASCONF_ACK chunks.")
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Vlad Yasevich <[email protected]>
Acked-by: Neil Horman <[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: sctp_disposition_t sctp_sf_do_asconf(struct net *net,
const struct sctp_endpoint *ep,
const struct sctp_association *asoc,
const sctp_subtype_t type, void *arg,
sctp_cmd_seq_t *commands)
{
struct sctp_chunk *chunk = arg;
struct sctp_chunk *asconf_ack = NULL;
struct sctp_paramhdr *err_param = NULL;
sctp_addiphdr_t *hdr;
union sctp_addr_param *addr_param;
__u32 serial;
int length;
if (!sctp_vtag_verify(chunk, asoc)) {
sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG,
SCTP_NULL());
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
/* ADD-IP: Section 4.1.1
* This chunk MUST be sent in an authenticated way by using
* the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk
* is received unauthenticated it MUST be silently discarded as
* described in [I-D.ietf-tsvwg-sctp-auth].
*/
if (!net->sctp.addip_noauth && !chunk->auth)
return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
/* Make sure that the ASCONF ADDIP chunk has a valid length. */
if (!sctp_chunk_length_valid(chunk, sizeof(sctp_addip_chunk_t)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
commands);
hdr = (sctp_addiphdr_t *)chunk->skb->data;
serial = ntohl(hdr->serial);
addr_param = (union sctp_addr_param *)hdr->params;
length = ntohs(addr_param->p.length);
if (length < sizeof(sctp_paramhdr_t))
return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
(void *)addr_param, commands);
/* Verify the ASCONF chunk before processing it. */
if (!sctp_verify_asconf(asoc,
(sctp_paramhdr_t *)((void *)addr_param + length),
(void *)chunk->chunk_end,
&err_param))
return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
(void *)err_param, commands);
/* ADDIP 5.2 E1) Compare the value of the serial number to the value
* the endpoint stored in a new association variable
* 'Peer-Serial-Number'.
*/
if (serial == asoc->peer.addip_serial + 1) {
/* If this is the first instance of ASCONF in the packet,
* we can clean our old ASCONF-ACKs.
*/
if (!chunk->has_asconf)
sctp_assoc_clean_asconf_ack_cache(asoc);
/* ADDIP 5.2 E4) When the Sequence Number matches the next one
* expected, process the ASCONF as described below and after
* processing the ASCONF Chunk, append an ASCONF-ACK Chunk to
* the response packet and cache a copy of it (in the event it
* later needs to be retransmitted).
*
* Essentially, do V1-V5.
*/
asconf_ack = sctp_process_asconf((struct sctp_association *)
asoc, chunk);
if (!asconf_ack)
return SCTP_DISPOSITION_NOMEM;
} else if (serial < asoc->peer.addip_serial + 1) {
/* ADDIP 5.2 E2)
* If the value found in the Sequence Number is less than the
* ('Peer- Sequence-Number' + 1), simply skip to the next
* ASCONF, and include in the outbound response packet
* any previously cached ASCONF-ACK response that was
* sent and saved that matches the Sequence Number of the
* ASCONF. Note: It is possible that no cached ASCONF-ACK
* Chunk exists. This will occur when an older ASCONF
* arrives out of order. In such a case, the receiver
* should skip the ASCONF Chunk and not include ASCONF-ACK
* Chunk for that chunk.
*/
asconf_ack = sctp_assoc_lookup_asconf_ack(asoc, hdr->serial);
if (!asconf_ack)
return SCTP_DISPOSITION_DISCARD;
/* Reset the transport so that we select the correct one
* this time around. This is to make sure that we don't
* accidentally use a stale transport that's been removed.
*/
asconf_ack->transport = NULL;
} else {
/* ADDIP 5.2 E5) Otherwise, the ASCONF Chunk is discarded since
* it must be either a stale packet or from an attacker.
*/
return SCTP_DISPOSITION_DISCARD;
}
/* ADDIP 5.2 E6) The destination address of the SCTP packet
* containing the ASCONF-ACK Chunks MUST be the source address of
* the SCTP packet that held the ASCONF Chunks.
*
* To do this properly, we'll set the destination address of the chunk
* and at the transmit time, will try look up the transport to use.
* Since ASCONFs may be bundled, the correct transport may not be
* created until we process the entire packet, thus this workaround.
*/
asconf_ack->dest = chunk->source;
sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asconf_ack));
if (asoc->new_transport) {
sctp_sf_heartbeat(ep, asoc, type, asoc->new_transport, commands);
((struct sctp_association *)asoc)->new_transport = NULL;
}
return SCTP_DISPOSITION_CONSUME;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-399'], 'message': 'net: sctp: fix skb_over_panic when receiving malformed ASCONF chunks
Commit 6f4c618ddb0 ("SCTP : Add paramters validity check for
ASCONF chunk") added basic verification of ASCONF chunks, however,
it is still possible to remotely crash a server by sending a
special crafted ASCONF chunk, even up to pre 2.6.12 kernels:
skb_over_panic: text:ffffffffa01ea1c3 len:31056 put:30768
head:ffff88011bd81800 data:ffff88011bd81800 tail:0x7950
end:0x440 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:129!
[...]
Call Trace:
<IRQ>
[<ffffffff8144fb1c>] skb_put+0x5c/0x70
[<ffffffffa01ea1c3>] sctp_addto_chunk+0x63/0xd0 [sctp]
[<ffffffffa01eadaf>] sctp_process_asconf+0x1af/0x540 [sctp]
[<ffffffff8152d025>] ? _read_unlock_bh+0x15/0x20
[<ffffffffa01e0038>] sctp_sf_do_asconf+0x168/0x240 [sctp]
[<ffffffffa01e3751>] sctp_do_sm+0x71/0x1210 [sctp]
[<ffffffff8147645d>] ? fib_rules_lookup+0xad/0xf0
[<ffffffffa01e6b22>] ? sctp_cmp_addr_exact+0x32/0x40 [sctp]
[<ffffffffa01e8393>] sctp_assoc_bh_rcv+0xd3/0x180 [sctp]
[<ffffffffa01ee986>] sctp_inq_push+0x56/0x80 [sctp]
[<ffffffffa01fcc42>] sctp_rcv+0x982/0xa10 [sctp]
[<ffffffffa01d5123>] ? ipt_local_in_hook+0x23/0x28 [iptable_filter]
[<ffffffff8148bdc9>] ? nf_iterate+0x69/0xb0
[<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
[<ffffffff8148bf86>] ? nf_hook_slow+0x76/0x120
[<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
[<ffffffff81496ded>] ip_local_deliver_finish+0xdd/0x2d0
[<ffffffff81497078>] ip_local_deliver+0x98/0xa0
[<ffffffff8149653d>] ip_rcv_finish+0x12d/0x440
[<ffffffff81496ac5>] ip_rcv+0x275/0x350
[<ffffffff8145c88b>] __netif_receive_skb+0x4ab/0x750
[<ffffffff81460588>] netif_receive_skb+0x58/0x60
This can be triggered e.g., through a simple scripted nmap
connection scan injecting the chunk after the handshake, for
example, ...
-------------- INIT[ASCONF; ASCONF_ACK] ------------->
<----------- INIT-ACK[ASCONF; ASCONF_ACK] ------------
-------------------- COOKIE-ECHO -------------------->
<-------------------- COOKIE-ACK ---------------------
------------------ ASCONF; UNKNOWN ------------------>
... where ASCONF chunk of length 280 contains 2 parameters ...
1) Add IP address parameter (param length: 16)
2) Add/del IP address parameter (param length: 255)
... followed by an UNKNOWN chunk of e.g. 4 bytes. Here, the
Address Parameter in the ASCONF chunk is even missing, too.
This is just an example and similarly-crafted ASCONF chunks
could be used just as well.
The ASCONF chunk passes through sctp_verify_asconf() as all
parameters passed sanity checks, and after walking, we ended
up successfully at the chunk end boundary, and thus may invoke
sctp_process_asconf(). Parameter walking is done with
WORD_ROUND() to take padding into account.
In sctp_process_asconf()'s TLV processing, we may fail in
sctp_process_asconf_param() e.g., due to removal of the IP
address that is also the source address of the packet containing
the ASCONF chunk, and thus we need to add all TLVs after the
failure to our ASCONF response to remote via helper function
sctp_add_asconf_response(), which basically invokes a
sctp_addto_chunk() adding the error parameters to the given
skb.
When walking to the next parameter this time, we proceed
with ...
length = ntohs(asconf_param->param_hdr.length);
asconf_param = (void *)asconf_param + length;
... instead of the WORD_ROUND()'ed length, thus resulting here
in an off-by-one that leads to reading the follow-up garbage
parameter length of 12336, and thus throwing an skb_over_panic
for the reply when trying to sctp_addto_chunk() next time,
which implicitly calls the skb_put() with that length.
Fix it by using sctp_walk_params() [ which is also used in
INIT parameter processing ] macro in the verification *and*
in ASCONF processing: it will make sure we don't spill over,
that we walk parameters WORD_ROUND()'ed. Moreover, we're being
more defensive and guard against unknown parameter types and
missized addresses.
Joint work with Vlad Yasevich.
Fixes: b896b82be4ae ("[SCTP] ADDIP: Support for processing incoming ASCONF_ACK chunks.")
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Vlad Yasevich <[email protected]>
Acked-by: Neil Horman <[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: xfs_da3_fixhashpath(
struct xfs_da_state *state,
struct xfs_da_state_path *path)
{
struct xfs_da_state_blk *blk;
struct xfs_da_intnode *node;
struct xfs_da_node_entry *btree;
xfs_dahash_t lasthash=0;
int level;
int count;
struct xfs_inode *dp = state->args->dp;
trace_xfs_da_fixhashpath(state->args);
level = path->active-1;
blk = &path->blk[ level ];
switch (blk->magic) {
case XFS_ATTR_LEAF_MAGIC:
lasthash = xfs_attr_leaf_lasthash(blk->bp, &count);
if (count == 0)
return;
break;
case XFS_DIR2_LEAFN_MAGIC:
lasthash = xfs_dir2_leafn_lasthash(dp, blk->bp, &count);
if (count == 0)
return;
break;
case XFS_DA_NODE_MAGIC:
lasthash = xfs_da3_node_lasthash(dp, blk->bp, &count);
if (count == 0)
return;
break;
}
for (blk--, level--; level >= 0; blk--, level--) {
struct xfs_da3_icnode_hdr nodehdr;
node = blk->bp->b_addr;
dp->d_ops->node_hdr_from_disk(&nodehdr, node);
btree = dp->d_ops->node_tree_p(node);
if (be32_to_cpu(btree->hashval) == lasthash)
break;
blk->hashval = lasthash;
btree[blk->index].hashval = cpu_to_be32(lasthash);
xfs_trans_log_buf(state->args->trans, blk->bp,
XFS_DA_LOGRANGE(node, &btree[blk->index],
sizeof(*btree)));
lasthash = be32_to_cpu(btree[nodehdr.count - 1].hashval);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'xfs: fix directory hash ordering bug
Commit f5ea1100 ("xfs: add CRCs to dir2/da node blocks") introduced
in 3.10 incorrectly converted the btree hash index array pointer in
xfs_da3_fixhashpath(). It resulted in the the current hash always
being compared against the first entry in the btree rather than the
current block index into the btree block's hash entry array. As a
result, it was comparing the wrong hashes, and so could misorder the
entries in the btree.
For most cases, this doesn't cause any problems as it requires hash
collisions to expose the ordering problem. However, when there are
hash collisions within a directory there is a very good probability
that the entries will be ordered incorrectly and that actually
matters when duplicate hashes are placed into or removed from the
btree block hash entry array.
This bug results in an on-disk directory corruption and that results
in directory verifier functions throwing corruption warnings into
the logs. While no data or directory entries are lost, access to
them may be compromised, and attempts to remove entries from a
directory that has suffered from this corruption may result in a
filesystem shutdown. xfs_repair will fix the directory hash
ordering without data loss occuring.
[dchinner: wrote useful a commit message]
cc: <[email protected]>
Reported-by: Hannes Frederic Sowa <[email protected]>
Signed-off-by: Mark Tinguely <[email protected]>
Reviewed-by: Ben Myers <[email protected]>
Signed-off-by: Dave Chinner <[email protected]>'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: bool __net_get_random_once(void *buf, int nbytes, bool *done,
struct static_key *done_key)
{
static DEFINE_SPINLOCK(lock);
unsigned long flags;
spin_lock_irqsave(&lock, flags);
if (*done) {
spin_unlock_irqrestore(&lock, flags);
return false;
}
get_random_bytes(buf, nbytes);
*done = true;
spin_unlock_irqrestore(&lock, flags);
__net_random_once_disable_jump(done_key);
return true;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'net: avoid dependency of net_get_random_once on nop patching
net_get_random_once depends on the static keys infrastructure to patch up
the branch to the slow path during boot. This was realized by abusing the
static keys api and defining a new initializer to not enable the call
site while still indicating that the branch point should get patched
up. This was needed to have the fast path considered likely by gcc.
The static key initialization during boot up normally walks through all
the registered keys and either patches in ideal nops or enables the jump
site but omitted that step on x86 if ideal nops where already placed at
static_key branch points. Thus net_get_random_once branches not always
became active.
This patch switches net_get_random_once to the ordinary static_key
api and thus places the kernel fast path in the - by gcc considered -
unlikely path. Microbenchmarks on Intel and AMD x86-64 showed that
the unlikely path actually beats the likely path in terms of cycle cost
and that different nop patterns did not make much difference, thus this
switch should not be noticeable.
Fixes: a48e42920ff38b ("net: introduce new macro net_get_random_once")
Reported-by: Tuomas Räsänen <[email protected]>
Cc: Linus Torvalds <[email protected]>
Signed-off-by: Hannes Frederic Sowa <[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: Suite *tm_suite(void)
{
Suite *s = suite_create("tm_suite methods");
TCase * tc = tcase_create("tm");
tcase_add_test(tc, test_tm_poll_bad_init);
tcase_add_test(tc, test_tm_poll_bad_result);
suite_add_tcase(s, tc);
return s;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'TRQ-2885 - limit tm_adopt() to only adopt a session id that
is owned by the calling user.'</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: START_TEST(test_tm_adopt_ispidowner)
{
/* we are the owner of this pid so should return true */
fail_unless(TRUE == ispidowner(getpid()));
/* assuming the unit test is not run as root, owner */
/* owner of this pid is not the owner of pid 1 (init) */
fail_unless(FALSE == ispidowner(1));
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-264'], 'message': 'TRQ-2885 - clean up unit test so it passes when run as root'</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: SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
const char __user *, put_old)
{
struct path new, old, parent_path, root_parent, root;
struct mount *new_mnt, *root_mnt, *old_mnt;
struct mountpoint *old_mp, *root_mp;
int error;
if (!may_mount())
return -EPERM;
error = user_path_dir(new_root, &new);
if (error)
goto out0;
error = user_path_dir(put_old, &old);
if (error)
goto out1;
error = security_sb_pivotroot(&old, &new);
if (error)
goto out2;
get_fs_root(current->fs, &root);
old_mp = lock_mount(&old);
error = PTR_ERR(old_mp);
if (IS_ERR(old_mp))
goto out3;
error = -EINVAL;
new_mnt = real_mount(new.mnt);
root_mnt = real_mount(root.mnt);
old_mnt = real_mount(old.mnt);
if (IS_MNT_SHARED(old_mnt) ||
IS_MNT_SHARED(new_mnt->mnt_parent) ||
IS_MNT_SHARED(root_mnt->mnt_parent))
goto out4;
if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
goto out4;
if (new_mnt->mnt.mnt_flags & MNT_LOCKED)
goto out4;
error = -ENOENT;
if (d_unlinked(new.dentry))
goto out4;
error = -EBUSY;
if (new_mnt == root_mnt || old_mnt == root_mnt)
goto out4; /* loop, on the same file system */
error = -EINVAL;
if (root.mnt->mnt_root != root.dentry)
goto out4; /* not a mountpoint */
if (!mnt_has_parent(root_mnt))
goto out4; /* not attached */
root_mp = root_mnt->mnt_mp;
if (new.mnt->mnt_root != new.dentry)
goto out4; /* not a mountpoint */
if (!mnt_has_parent(new_mnt))
goto out4; /* not attached */
/* make sure we can reach put_old from new_root */
if (!is_path_reachable(old_mnt, old.dentry, &new))
goto out4;
root_mp->m_count++; /* pin it so it won't go away */
lock_mount_hash();
detach_mnt(new_mnt, &parent_path);
detach_mnt(root_mnt, &root_parent);
if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
new_mnt->mnt.mnt_flags |= MNT_LOCKED;
root_mnt->mnt.mnt_flags &= ~MNT_LOCKED;
}
/* mount old root on put_old */
attach_mnt(root_mnt, old_mnt, old_mp);
/* mount new_root on / */
attach_mnt(new_mnt, real_mount(root_parent.mnt), root_mp);
touch_mnt_namespace(current->nsproxy->mnt_ns);
unlock_mount_hash();
chroot_fs_refs(&root, &new);
put_mountpoint(root_mp);
error = 0;
out4:
unlock_mount(old_mp);
if (!error) {
path_put(&root_parent);
path_put(&parent_path);
}
out3:
path_put(&root);
out2:
path_put(&old);
out1:
path_put(&new);
out0:
return error;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-400'], 'message': 'mnt: Prevent pivot_root from creating a loop in the mount tree
Andy Lutomirski recently demonstrated that when chroot is used to set
the root path below the path for the new ``root'' passed to pivot_root
the pivot_root system call succeeds and leaks mounts.
In examining the code I see that starting with a new root that is
below the current root in the mount tree will result in a loop in the
mount tree after the mounts are detached and then reattached to one
another. Resulting in all kinds of ugliness including a leak of that
mounts involved in the leak of the mount loop.
Prevent this problem by ensuring that the new mount is reachable from
the current root of the mount tree.
[Added stable cc. Fixes CVE-2014-7970. --Andy]
Cc: [email protected]
Reported-by: Andy Lutomirski <[email protected]>
Reviewed-by: Andy Lutomirski <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: "Eric W. Biederman" <[email protected]>
Signed-off-by: Andy Lutomirski <[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 gnutls_error_to_alert(int err, int *level)
{
int ret, _level = -1;
switch (err) { /* send appropriate alert */
case GNUTLS_E_DECRYPTION_FAILED:
/* GNUTLS_A_DECRYPTION_FAILED is not sent, because
* it is not defined in SSL3. Note that we must
* not distinguish Decryption failures from mac
* check failures, due to the possibility of some
* attacks.
*/
ret = GNUTLS_A_BAD_RECORD_MAC;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_DECOMPRESSION_FAILED:
ret = GNUTLS_A_DECOMPRESSION_FAILURE;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_RECEIVED_ILLEGAL_PARAMETER:
case GNUTLS_E_ILLEGAL_SRP_USERNAME:
ret = GNUTLS_A_ILLEGAL_PARAMETER;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_UNKNOWN_SRP_USERNAME:
ret = GNUTLS_A_UNKNOWN_PSK_IDENTITY;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_ASN1_ELEMENT_NOT_FOUND:
case GNUTLS_E_ASN1_IDENTIFIER_NOT_FOUND:
case GNUTLS_E_ASN1_DER_ERROR:
case GNUTLS_E_ASN1_VALUE_NOT_FOUND:
case GNUTLS_E_ASN1_GENERIC_ERROR:
case GNUTLS_E_ASN1_VALUE_NOT_VALID:
case GNUTLS_E_ASN1_TAG_ERROR:
case GNUTLS_E_ASN1_TAG_IMPLICIT:
case GNUTLS_E_ASN1_TYPE_ANY_ERROR:
case GNUTLS_E_ASN1_SYNTAX_ERROR:
case GNUTLS_E_ASN1_DER_OVERFLOW:
case GNUTLS_E_CERTIFICATE_ERROR:
ret = GNUTLS_A_BAD_CERTIFICATE;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_UNKNOWN_CIPHER_SUITE:
case GNUTLS_E_UNKNOWN_COMPRESSION_ALGORITHM:
case GNUTLS_E_INSUFFICIENT_CREDENTIALS:
case GNUTLS_E_NO_CIPHER_SUITES:
case GNUTLS_E_NO_COMPRESSION_ALGORITHMS:
case GNUTLS_E_UNSUPPORTED_SIGNATURE_ALGORITHM:
case GNUTLS_E_SAFE_RENEGOTIATION_FAILED:
case GNUTLS_E_INCOMPAT_DSA_KEY_WITH_TLS_PROTOCOL:
ret = GNUTLS_A_HANDSHAKE_FAILURE;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_RECEIVED_ILLEGAL_EXTENSION:
ret = GNUTLS_A_UNSUPPORTED_EXTENSION;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_USER_ERROR:
ret = GNUTLS_A_USER_CANCELED;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_UNEXPECTED_PACKET:
case GNUTLS_E_UNEXPECTED_HANDSHAKE_PACKET:
case GNUTLS_E_PREMATURE_TERMINATION:
ret = GNUTLS_A_UNEXPECTED_MESSAGE;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_REHANDSHAKE:
case GNUTLS_E_UNSAFE_RENEGOTIATION_DENIED:
ret = GNUTLS_A_NO_RENEGOTIATION;
_level = GNUTLS_AL_WARNING;
break;
case GNUTLS_E_UNSUPPORTED_VERSION_PACKET:
ret = GNUTLS_A_PROTOCOL_VERSION;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_UNSUPPORTED_CERTIFICATE_TYPE:
ret = GNUTLS_A_UNSUPPORTED_CERTIFICATE;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_UNEXPECTED_PACKET_LENGTH:
ret = GNUTLS_A_RECORD_OVERFLOW;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_INTERNAL_ERROR:
case GNUTLS_E_NO_TEMPORARY_DH_PARAMS:
case GNUTLS_E_NO_TEMPORARY_RSA_PARAMS:
ret = GNUTLS_A_INTERNAL_ERROR;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_OPENPGP_GETKEY_FAILED:
ret = GNUTLS_A_CERTIFICATE_UNOBTAINABLE;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_DH_PRIME_UNACCEPTABLE:
case GNUTLS_E_NO_CERTIFICATE_FOUND:
ret = GNUTLS_A_INSUFFICIENT_SECURITY;
_level = GNUTLS_AL_FATAL;
break;
case GNUTLS_E_NO_APPLICATION_PROTOCOL:
ret = GNUTLS_A_NO_APPLICATION_PROTOCOL;
_level = GNUTLS_AL_FATAL;
break;
default:
ret = GNUTLS_A_INTERNAL_ERROR;
_level = GNUTLS_AL_FATAL;
break;
}
if (level != NULL)
*level = _level;
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-310'], 'message': 'handshake: check for TLS_FALLBACK_SCSV
If TLS_FALLBACK_SCSV was sent by the client during the handshake, and
the advertised protocol version is lower than GNUTLS_TLS_VERSION_MAX,
send the "Inappropriate fallback" fatal alert and abort the handshake.
This mechanism was defined in RFC7507.'</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: copy_ciphersuites(gnutls_session_t session,
gnutls_buffer_st * cdata, int add_scsv)
{
int ret;
uint8_t cipher_suites[MAX_CIPHERSUITE_SIZE + 2]; /* allow space for SCSV */
int cipher_suites_size;
size_t init_length = cdata->length;
ret =
_gnutls_supported_ciphersuites(session, cipher_suites,
sizeof(cipher_suites) - 2);
if (ret < 0)
return gnutls_assert_val(ret);
/* Here we remove any ciphersuite that does not conform
* the certificate requested, or to the
* authentication requested (eg SRP).
*/
ret =
_gnutls_remove_unwanted_ciphersuites(session, cipher_suites,
ret, NULL, 0);
if (ret < 0)
return gnutls_assert_val(ret);
/* If no cipher suites were enabled.
*/
if (ret == 0)
return
gnutls_assert_val(GNUTLS_E_INSUFFICIENT_CREDENTIALS);
cipher_suites_size = ret;
if (add_scsv) {
cipher_suites[cipher_suites_size] = 0x00;
cipher_suites[cipher_suites_size + 1] = 0xff;
cipher_suites_size += 2;
ret = _gnutls_ext_sr_send_cs(session);
if (ret < 0)
return gnutls_assert_val(ret);
}
ret =
_gnutls_buffer_append_data_prefix(cdata, 16, cipher_suites,
cipher_suites_size);
if (ret < 0)
return gnutls_assert_val(ret);
ret = cdata->length - init_length;
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-310'], 'message': 'handshake: add FALLBACK_SCSV priority option
This allows clients to enable the TLS_FALLBACK_SCSV mechanism during
the handshake, as defined in RFC7507.'</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 __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long debugctlmsr;
/* Record the guest's net vcpu time for enforced NMI injections. */
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
vmx->entry_time = ktime_get();
/* Don't enter VMX if guest state is invalid, let the exit handler
start emulation until we arrive back to a valid state */
if (vmx->emulation_required)
return;
if (vmx->ple_window_dirty) {
vmx->ple_window_dirty = false;
vmcs_write32(PLE_WINDOW, vmx->ple_window);
}
if (vmx->nested.sync_shadow_vmcs) {
copy_vmcs12_to_shadow(vmx);
vmx->nested.sync_shadow_vmcs = false;
}
if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
/* When single-stepping over STI and MOV SS, we must clear the
* corresponding interruptibility bits in the guest state. Otherwise
* vmentry fails as it then expects bit 14 (BS) in pending debug
* exceptions being set, but that's not correct for the guest debugging
* case. */
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
atomic_switch_perf_msrs(vmx);
debugctlmsr = get_debugctlmsr();
vmx->__launched = vmx->loaded_vmcs->launched;
asm(
/* Store host registers */
"push %%" _ASM_DX "; push %%" _ASM_BP ";"
"push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */
"push %%" _ASM_CX " \n\t"
"cmp %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
"je 1f \n\t"
"mov %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
"1: \n\t"
/* Reload cr2 if changed */
"mov %c[cr2](%0), %%" _ASM_AX " \n\t"
"mov %%cr2, %%" _ASM_DX " \n\t"
"cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t"
"je 2f \n\t"
"mov %%" _ASM_AX", %%cr2 \n\t"
"2: \n\t"
/* Check if vmlaunch of vmresume is needed */
"cmpl $0, %c[launched](%0) \n\t"
/* Load guest registers. Don't clobber flags. */
"mov %c[rax](%0), %%" _ASM_AX " \n\t"
"mov %c[rbx](%0), %%" _ASM_BX " \n\t"
"mov %c[rdx](%0), %%" _ASM_DX " \n\t"
"mov %c[rsi](%0), %%" _ASM_SI " \n\t"
"mov %c[rdi](%0), %%" _ASM_DI " \n\t"
"mov %c[rbp](%0), %%" _ASM_BP " \n\t"
#ifdef CONFIG_X86_64
"mov %c[r8](%0), %%r8 \n\t"
"mov %c[r9](%0), %%r9 \n\t"
"mov %c[r10](%0), %%r10 \n\t"
"mov %c[r11](%0), %%r11 \n\t"
"mov %c[r12](%0), %%r12 \n\t"
"mov %c[r13](%0), %%r13 \n\t"
"mov %c[r14](%0), %%r14 \n\t"
"mov %c[r15](%0), %%r15 \n\t"
#endif
"mov %c[rcx](%0), %%" _ASM_CX " \n\t" /* kills %0 (ecx) */
/* Enter guest mode */
"jne 1f \n\t"
__ex(ASM_VMX_VMLAUNCH) "\n\t"
"jmp 2f \n\t"
"1: " __ex(ASM_VMX_VMRESUME) "\n\t"
"2: "
/* Save guest registers, load host registers, keep flags */
"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
"pop %0 \n\t"
"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
"mov %%" _ASM_DX ", %c[rdx](%0) \n\t"
"mov %%" _ASM_SI ", %c[rsi](%0) \n\t"
"mov %%" _ASM_DI ", %c[rdi](%0) \n\t"
"mov %%" _ASM_BP ", %c[rbp](%0) \n\t"
#ifdef CONFIG_X86_64
"mov %%r8, %c[r8](%0) \n\t"
"mov %%r9, %c[r9](%0) \n\t"
"mov %%r10, %c[r10](%0) \n\t"
"mov %%r11, %c[r11](%0) \n\t"
"mov %%r12, %c[r12](%0) \n\t"
"mov %%r13, %c[r13](%0) \n\t"
"mov %%r14, %c[r14](%0) \n\t"
"mov %%r15, %c[r15](%0) \n\t"
#endif
"mov %%cr2, %%" _ASM_AX " \n\t"
"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
"pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t"
"setbe %c[fail](%0) \n\t"
".pushsection .rodata \n\t"
".global vmx_return \n\t"
"vmx_return: " _ASM_PTR " 2b \n\t"
".popsection"
: : "c"(vmx), "d"((unsigned long)HOST_RSP),
[launched]"i"(offsetof(struct vcpu_vmx, __launched)),
[fail]"i"(offsetof(struct vcpu_vmx, fail)),
[host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)),
[rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])),
[rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])),
[rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])),
[rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])),
[rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])),
[rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])),
[rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])),
#ifdef CONFIG_X86_64
[r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])),
[r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])),
[r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])),
[r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])),
[r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])),
[r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])),
[r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])),
[r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])),
#endif
[cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)),
[wordsize]"i"(sizeof(ulong))
: "cc", "memory"
#ifdef CONFIG_X86_64
, "rax", "rbx", "rdi", "rsi"
, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
#else
, "eax", "ebx", "edi", "esi"
#endif
);
/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
if (debugctlmsr)
update_debugctlmsr(debugctlmsr);
#ifndef CONFIG_X86_64
/*
* The sysexit path does not restore ds/es, so we must set them to
* a reasonable value ourselves.
*
* We can't defer this to vmx_load_host_state() since that function
* may be executed in interrupt context, which saves and restore segments
* around it, nullifying its effect.
*/
loadsegment(ds, __USER_DS);
loadsegment(es, __USER_DS);
#endif
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
| (1 << VCPU_EXREG_RFLAGS)
| (1 << VCPU_EXREG_PDPTR)
| (1 << VCPU_EXREG_SEGMENTS)
| (1 << VCPU_EXREG_CR3));
vcpu->arch.regs_dirty = 0;
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
vmx->loaded_vmcs->launched = 1;
vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX);
/*
* the KVM_REQ_EVENT optimization bit is only on for one entry, and if
* we did not inject a still-pending event to L1 now because of
* nested_run_pending, we need to re-enable this bit.
*/
if (vmx->nested.nested_run_pending)
kvm_make_request(KVM_REQ_EVENT, vcpu);
vmx->nested.nested_run_pending = 0;
vmx_complete_atomic_exit(vmx);
vmx_recover_nmi_blocking(vmx);
vmx_complete_interrupts(vmx);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-400', 'CWE-399', 'CWE-703'], 'message': 'x86,kvm,vmx: Preserve CR4 across VM entry
CR4 isn't constant; at least the TSD and PCE bits can vary.
TBH, treating CR0 and CR3 as constant scares me a bit, too, but it looks
like it's correct.
This adds a branch and a read from cr4 to each vm entry. Because it is
extremely likely that consecutive entries into the same vcpu will have
the same host cr4 value, this fixes up the vmcs instead of restoring cr4
after the fact. A subsequent patch will add a kernel-wide cr4 shadow,
reducing the overhead in the common case to just two memory reads and a
branch.
Signed-off-by: Andy Lutomirski <[email protected]>
Acked-by: Paolo Bonzini <[email protected]>
Cc: [email protected]
Cc: Petr Matousek <[email protected]>
Cc: Gleb Natapov <[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 inline int object_custom(UNSERIALIZE_PARAMETER, zend_class_entry *ce)
{
long datalen;
datalen = parse_iv2((*p) + 2, p);
(*p) += 2;
if (datalen < 0 || (*p) + datalen >= max) {
zend_error(E_WARNING, "Insufficient data for unserializing - %ld required, %ld present", datalen, (long)(max - (*p)));
return 0;
}
if (ce->unserialize == NULL) {
zend_error(E_WARNING, "Class %s has no unserializer", ce->name);
object_init_ex(*rval, ce);
} else if (ce->unserialize(rval, ce, (const unsigned char*)*p, datalen, (zend_unserialize_data *)var_hash TSRMLS_CC) != SUCCESS) {
return 0;
}
(*p) += datalen;
return finish_nested_data(UNSERIALIZE_PASSTHRU);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'Fixed bug #68044: Integer overflow in unserialize() (32-bits only)'</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 date_from_ISO8601 (const char *text, time_t * value) {
struct tm tm;
int n;
int i;
char buf[30];
if (strchr (text, '-')) {
char *p = (char *) text, *p2 = buf;
while (p && *p) {
if (*p != '-') {
*p2 = *p;
p2++;
if (p2-buf >= sizeof(buf)) {
return -1;
}
}
p++;
}
text = buf;
}
tm.tm_isdst = -1;
#define XMLRPC_IS_NUMBER(x) if (x < '0' || x > '9') return -1;
n = 1000;
tm.tm_year = 0;
for(i = 0; i < 4; i++) {
XMLRPC_IS_NUMBER(text[i])
tm.tm_year += (text[i]-'0')*n;
n /= 10;
}
n = 10;
tm.tm_mon = 0;
for(i = 0; i < 2; i++) {
XMLRPC_IS_NUMBER(text[i])
tm.tm_mon += (text[i+4]-'0')*n;
n /= 10;
}
tm.tm_mon --;
n = 10;
tm.tm_mday = 0;
for(i = 0; i < 2; i++) {
XMLRPC_IS_NUMBER(text[i])
tm.tm_mday += (text[i+6]-'0')*n;
n /= 10;
}
n = 10;
tm.tm_hour = 0;
for(i = 0; i < 2; i++) {
XMLRPC_IS_NUMBER(text[i])
tm.tm_hour += (text[i+9]-'0')*n;
n /= 10;
}
n = 10;
tm.tm_min = 0;
for(i = 0; i < 2; i++) {
XMLRPC_IS_NUMBER(text[i])
tm.tm_min += (text[i+12]-'0')*n;
n /= 10;
}
n = 10;
tm.tm_sec = 0;
for(i = 0; i < 2; i++) {
XMLRPC_IS_NUMBER(text[i])
tm.tm_sec += (text[i+15]-'0')*n;
n /= 10;
}
tm.tm_year -= 1900;
*value = mkgmtime(&tm);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix bug #68027 - fix date parsing in XMLRPC lib'</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 Curl_freeset(struct SessionHandle *data)
{
/* Free all dynamic strings stored in the data->set substructure. */
enum dupstring i;
for(i=(enum dupstring)0; i < STRING_LAST; i++)
Curl_safefree(data->set.str[i]);
if(data->change.referer_alloc) {
Curl_safefree(data->change.referer);
data->change.referer_alloc = FALSE;
}
data->change.referer = NULL;
if(data->change.url_alloc) {
Curl_safefree(data->change.url);
data->change.url_alloc = FALSE;
}
data->change.url = NULL;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'curl_easy_duphandle: CURLOPT_COPYPOSTFIELDS read out of bounds
When duplicating a handle, the data to post was duplicated using
strdup() when it could be binary and contain zeroes and it was not even
zero terminated! This caused read out of bounds crashes/segfaults.
Since the lib/strdup.c file no longer is easily shared with the curl
tool with this change, it now uses its own version instead.
Bug: http://curl.haxx.se/docs/adv_20141105.html
CVE: CVE-2014-3707
Reported-By: Symeon Paraschoudis'</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 char *memdup(const char *src, size_t buffer_length)
{
size_t length;
bool add = FALSE;
char *buffer;
if(buffer_length)
length = buffer_length;
else if(src) {
length = strlen(src);
add = TRUE;
}
else
/* no length and a NULL src pointer! */
return strdup("");
buffer = malloc(length+add);
if(!buffer)
return NULL; /* fail */
memcpy(buffer, src, length);
/* if length unknown do null termination */
if(add)
buffer[length] = '\0';
return buffer;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-200'], 'message': 'curl_easy_duphandle: CURLOPT_COPYPOSTFIELDS read out of bounds
When duplicating a handle, the data to post was duplicated using
strdup() when it could be binary and contain zeroes and it was not even
zero terminated! This caused read out of bounds crashes/segfaults.
Since the lib/strdup.c file no longer is easily shared with the curl
tool with this change, it now uses its own version instead.
Bug: http://curl.haxx.se/docs/adv_20141105.html
CVE: CVE-2014-3707
Reported-By: Symeon Paraschoudis'</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 sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
{
struct sctp_chunk *chunk;
sctp_chunkhdr_t *ch = NULL;
/* The assumption is that we are safe to process the chunks
* at this time.
*/
if ((chunk = queue->in_progress)) {
/* There is a packet that we have been working on.
* Any post processing work to do before we move on?
*/
if (chunk->singleton ||
chunk->end_of_packet ||
chunk->pdiscard) {
sctp_chunk_free(chunk);
chunk = queue->in_progress = NULL;
} else {
/* Nothing to do. Next chunk in the packet, please. */
ch = (sctp_chunkhdr_t *) chunk->chunk_end;
/* Force chunk->skb->data to chunk->chunk_end. */
skb_pull(chunk->skb,
chunk->chunk_end - chunk->skb->data);
/* Verify that we have at least chunk headers
* worth of buffer left.
*/
if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) {
sctp_chunk_free(chunk);
chunk = queue->in_progress = NULL;
}
}
}
/* Do we need to take the next packet out of the queue to process? */
if (!chunk) {
struct list_head *entry;
/* Is the queue empty? */
if (list_empty(&queue->in_chunk_list))
return NULL;
entry = queue->in_chunk_list.next;
chunk = queue->in_progress =
list_entry(entry, struct sctp_chunk, list);
list_del_init(entry);
/* This is the first chunk in the packet. */
chunk->singleton = 1;
ch = (sctp_chunkhdr_t *) chunk->skb->data;
chunk->data_accepted = 0;
}
chunk->chunk_hdr = ch;
chunk->chunk_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
/* In the unlikely case of an IP reassembly, the skb could be
* non-linear. If so, update chunk_end so that it doesn't go past
* the skb->tail.
*/
if (unlikely(skb_is_nonlinear(chunk->skb))) {
if (chunk->chunk_end > skb_tail_pointer(chunk->skb))
chunk->chunk_end = skb_tail_pointer(chunk->skb);
}
skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
chunk->subh.v = NULL; /* Subheader is no longer valid. */
if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) {
/* This is not a singleton */
chunk->singleton = 0;
} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
/* RFC 2960, Section 6.10 Bundling
*
* Partial chunks MUST NOT be placed in an SCTP packet.
* If the receiver detects a partial chunk, it MUST drop
* the chunk.
*
* Since the end of the chunk is past the end of our buffer
* (which contains the whole packet, we can freely discard
* the whole packet.
*/
sctp_chunk_free(chunk);
chunk = queue->in_progress = NULL;
return NULL;
} else {
/* We are at the end of the packet, so mark the chunk
* in case we need to send a SACK.
*/
chunk->end_of_packet = 1;
}
pr_debug("+++sctp_inq_pop+++ chunk:%p[%s], length:%d, skb->len:%d\n",
chunk, sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)),
ntohs(chunk->chunk_hdr->length), chunk->skb->len);
return chunk;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'net: sctp: fix remote memory pressure from excessive queueing
This scenario is not limited to ASCONF, just taken as one
example triggering the issue. When receiving ASCONF probes
in the form of ...
-------------- INIT[ASCONF; ASCONF_ACK] ------------->
<----------- INIT-ACK[ASCONF; ASCONF_ACK] ------------
-------------------- COOKIE-ECHO -------------------->
<-------------------- COOKIE-ACK ---------------------
---- ASCONF_a; [ASCONF_b; ...; ASCONF_n;] JUNK ------>
[...]
---- ASCONF_m; [ASCONF_o; ...; ASCONF_z;] JUNK ------>
... where ASCONF_a, ASCONF_b, ..., ASCONF_z are good-formed
ASCONFs and have increasing serial numbers, we process such
ASCONF chunk(s) marked with !end_of_packet and !singleton,
since we have not yet reached the SCTP packet end. SCTP does
only do verification on a chunk by chunk basis, as an SCTP
packet is nothing more than just a container of a stream of
chunks which it eats up one by one.
We could run into the case that we receive a packet with a
malformed tail, above marked as trailing JUNK. All previous
chunks are here goodformed, so the stack will eat up all
previous chunks up to this point. In case JUNK does not fit
into a chunk header and there are no more other chunks in
the input queue, or in case JUNK contains a garbage chunk
header, but the encoded chunk length would exceed the skb
tail, or we came here from an entirely different scenario
and the chunk has pdiscard=1 mark (without having had a flush
point), it will happen, that we will excessively queue up
the association's output queue (a correct final chunk may
then turn it into a response flood when flushing the
queue ;)): I ran a simple script with incremental ASCONF
serial numbers and could see the server side consuming
excessive amount of RAM [before/after: up to 2GB and more].
The issue at heart is that the chunk train basically ends
with !end_of_packet and !singleton markers and since commit
2e3216cd54b1 ("sctp: Follow security requirement of responding
with 1 packet") therefore preventing an output queue flush
point in sctp_do_sm() -> sctp_cmd_interpreter() on the input
chunk (chunk = event_arg) even though local_cork is set,
but its precedence has changed since then. In the normal
case, the last chunk with end_of_packet=1 would trigger the
queue flush to accommodate possible outgoing bundling.
In the input queue, sctp_inq_pop() seems to do the right thing
in terms of discarding invalid chunks. So, above JUNK will
not enter the state machine and instead be released and exit
the sctp_assoc_bh_rcv() chunk processing loop. It's simply
the flush point being missing at loop exit. Adding a try-flush
approach on the output queue might not work as the underlying
infrastructure might be long gone at this point due to the
side-effect interpreter run.
One possibility, albeit a bit of a kludge, would be to defer
invalid chunk freeing into the state machine in order to
possibly trigger packet discards and thus indirectly a queue
flush on error. It would surely be better to discard chunks
as in the current, perhaps better controlled environment, but
going back and forth, it's simply architecturally not possible.
I tried various trailing JUNK attack cases and it seems to
look good now.
Joint work with Vlad Yasevich.
Fixes: 2e3216cd54b1 ("sctp: Follow security requirement of responding with 1 packet")
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Vlad Yasevich <[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: QByteArray Cipher::blowfishECB(QByteArray cipherText, bool direction)
{
QCA::Initializer init;
QByteArray temp = cipherText;
//do padding ourselves
if (direction)
{
while ((temp.length() % 8) != 0) temp.append('\0');
}
else
{
temp = b64ToByte(temp);
while ((temp.length() % 8) != 0) temp.append('\0');
}
QCA::Direction dir = (direction) ? QCA::Encode : QCA::Decode;
QCA::Cipher cipher(m_type, QCA::Cipher::ECB, QCA::Cipher::NoPadding, dir, m_key);
QByteArray temp2 = cipher.update(QCA::MemoryRegion(temp)).toByteArray();
temp2 += cipher.final().toByteArray();
if (!cipher.ok())
return cipherText;
if (direction)
temp2 = byteToB64(temp2);
return temp2;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-125'], 'message': 'Check for invalid input in encrypted buffers
The ECB Blowfish decryption function assumed that encrypted input would
always come in blocks of 12 characters, as specified. However, buggy
clients or annoying people may not adhere to that assumption, causing
the core to crash while trying to process the invalid base64 input.
With this commit we make sure that we're not overstepping the bounds of
the input string while decoding it; instead we bail out early and display
the original input. Fixes #1314.
Thanks to Tucos for finding that one!'</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 pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
unsigned long size)
{
gfn_t end_gfn;
pfn_t pfn;
pfn = gfn_to_pfn_memslot(slot, gfn);
end_gfn = gfn + (size >> PAGE_SHIFT);
gfn += 1;
if (is_error_noslot_pfn(pfn))
return pfn;
while (gfn < end_gfn)
gfn_to_pfn_memslot(slot, gfn++);
return pfn;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'kvm: fix excessive pages un-pinning in kvm_iommu_map error path.
The third parameter of kvm_unpin_pages() when called from
kvm_iommu_map_pages() is wrong, it should be the number of pages to un-pin
and not the page size.
This error was facilitated with an inconsistent API: kvm_pin_pages() takes
a size, but kvn_unpin_pages() takes a number of pages, so fix the problem
by matching the two.
This was introduced by commit 350b8bd ("kvm: iommu: fix the third parameter
of kvm_iommu_put_pages (CVE-2014-3601)"), which fixes the lack of
un-pinning for pages intended to be un-pinned (i.e. memory leak) but
unfortunately potentially aggravated the number of pages we un-pin that
should have stayed pinned. As far as I understand though, the same
practical mitigations apply.
This issue was found during review of Red Hat 6.6 patches to prepare
Ksplice rebootless updates.
Thanks to Vegard for his time on a late Friday evening to help me in
understanding this code.
Fixes: 350b8bd ("kvm: iommu: fix the third parameter of... (CVE-2014-3601)")
Cc: [email protected]
Signed-off-by: Quentin Casasnovas <[email protected]>
Signed-off-by: Vegard Nossum <[email protected]>
Signed-off-by: Jamie Iles <[email protected]>
Reviewed-by: Sasha Levin <[email protected]>
Signed-off-by: Paolo Bonzini <[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 x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
{
int rc = X86EMUL_CONTINUE;
int mode = ctxt->mode;
int def_op_bytes, def_ad_bytes, goffset, simd_prefix;
bool op_prefix = false;
bool has_seg_override = false;
struct opcode opcode;
ctxt->memop.type = OP_NONE;
ctxt->memopp = NULL;
ctxt->_eip = ctxt->eip;
ctxt->fetch.ptr = ctxt->fetch.data;
ctxt->fetch.end = ctxt->fetch.data + insn_len;
ctxt->opcode_len = 1;
if (insn_len > 0)
memcpy(ctxt->fetch.data, insn, insn_len);
else {
rc = __do_insn_fetch_bytes(ctxt, 1);
if (rc != X86EMUL_CONTINUE)
return rc;
}
switch (mode) {
case X86EMUL_MODE_REAL:
case X86EMUL_MODE_VM86:
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 EMULATION_FAILED;
}
ctxt->op_bytes = def_op_bytes;
ctxt->ad_bytes = def_ad_bytes;
/* Legacy prefixes. */
for (;;) {
switch (ctxt->b = insn_fetch(u8, ctxt)) {
case 0x66: /* operand-size override */
op_prefix = true;
/* switch between 2/4 bytes */
ctxt->op_bytes = def_op_bytes ^ 6;
break;
case 0x67: /* address-size override */
if (mode == X86EMUL_MODE_PROT64)
/* switch between 4/8 bytes */
ctxt->ad_bytes = def_ad_bytes ^ 12;
else
/* switch between 2/4 bytes */
ctxt->ad_bytes = def_ad_bytes ^ 6;
break;
case 0x26: /* ES override */
case 0x2e: /* CS override */
case 0x36: /* SS override */
case 0x3e: /* DS override */
has_seg_override = true;
ctxt->seg_override = (ctxt->b >> 3) & 3;
break;
case 0x64: /* FS override */
case 0x65: /* GS override */
has_seg_override = true;
ctxt->seg_override = ctxt->b & 7;
break;
case 0x40 ... 0x4f: /* REX */
if (mode != X86EMUL_MODE_PROT64)
goto done_prefixes;
ctxt->rex_prefix = ctxt->b;
continue;
case 0xf0: /* LOCK */
ctxt->lock_prefix = 1;
break;
case 0xf2: /* REPNE/REPNZ */
case 0xf3: /* REP/REPE/REPZ */
ctxt->rep_prefix = ctxt->b;
break;
default:
goto done_prefixes;
}
/* Any legacy prefix after a REX prefix nullifies its effect. */
ctxt->rex_prefix = 0;
}
done_prefixes:
/* REX prefix. */
if (ctxt->rex_prefix & 8)
ctxt->op_bytes = 8; /* REX.W */
/* Opcode byte(s). */
opcode = opcode_table[ctxt->b];
/* Two-byte opcode? */
if (ctxt->b == 0x0f) {
ctxt->opcode_len = 2;
ctxt->b = insn_fetch(u8, ctxt);
opcode = twobyte_table[ctxt->b];
/* 0F_38 opcode map */
if (ctxt->b == 0x38) {
ctxt->opcode_len = 3;
ctxt->b = insn_fetch(u8, ctxt);
opcode = opcode_map_0f_38[ctxt->b];
}
}
ctxt->d = opcode.flags;
if (ctxt->d & ModRM)
ctxt->modrm = insn_fetch(u8, ctxt);
/* vex-prefix instructions are not implemented */
if (ctxt->opcode_len == 1 && (ctxt->b == 0xc5 || ctxt->b == 0xc4) &&
(mode == X86EMUL_MODE_PROT64 ||
(mode >= X86EMUL_MODE_PROT16 && (ctxt->modrm & 0x80)))) {
ctxt->d = NotImpl;
}
while (ctxt->d & GroupMask) {
switch (ctxt->d & GroupMask) {
case Group:
goffset = (ctxt->modrm >> 3) & 7;
opcode = opcode.u.group[goffset];
break;
case GroupDual:
goffset = (ctxt->modrm >> 3) & 7;
if ((ctxt->modrm >> 6) == 3)
opcode = opcode.u.gdual->mod3[goffset];
else
opcode = opcode.u.gdual->mod012[goffset];
break;
case RMExt:
goffset = ctxt->modrm & 7;
opcode = opcode.u.group[goffset];
break;
case Prefix:
if (ctxt->rep_prefix && op_prefix)
return EMULATION_FAILED;
simd_prefix = op_prefix ? 0x66 : ctxt->rep_prefix;
switch (simd_prefix) {
case 0x00: opcode = opcode.u.gprefix->pfx_no; break;
case 0x66: opcode = opcode.u.gprefix->pfx_66; break;
case 0xf2: opcode = opcode.u.gprefix->pfx_f2; break;
case 0xf3: opcode = opcode.u.gprefix->pfx_f3; break;
}
break;
case Escape:
if (ctxt->modrm > 0xbf)
opcode = opcode.u.esc->high[ctxt->modrm - 0xc0];
else
opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
break;
default:
return EMULATION_FAILED;
}
ctxt->d &= ~(u64)GroupMask;
ctxt->d |= opcode.flags;
}
/* Unrecognised? */
if (ctxt->d == 0)
return EMULATION_FAILED;
ctxt->execute = opcode.u.execute;
if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD)))
return EMULATION_FAILED;
if (unlikely(ctxt->d &
(NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
/*
* These are copied unconditionally here, and checked unconditionally
* in x86_emulate_insn.
*/
ctxt->check_perm = opcode.check_perm;
ctxt->intercept = opcode.intercept;
if (ctxt->d & NotImpl)
return EMULATION_FAILED;
if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
ctxt->op_bytes = 8;
if (ctxt->d & Op3264) {
if (mode == X86EMUL_MODE_PROT64)
ctxt->op_bytes = 8;
else
ctxt->op_bytes = 4;
}
if (ctxt->d & Sse)
ctxt->op_bytes = 16;
else if (ctxt->d & Mmx)
ctxt->op_bytes = 8;
}
/* ModRM and SIB bytes. */
if (ctxt->d & ModRM) {
rc = decode_modrm(ctxt, &ctxt->memop);
if (!has_seg_override) {
has_seg_override = true;
ctxt->seg_override = ctxt->modrm_seg;
}
} else if (ctxt->d & MemAbs)
rc = decode_abs(ctxt, &ctxt->memop);
if (rc != X86EMUL_CONTINUE)
goto done;
if (!has_seg_override)
ctxt->seg_override = VCPU_SREG_DS;
ctxt->memop.addr.mem.seg = ctxt->seg_override;
/*
* Decode and fetch the source operand: register, memory
* or immediate.
*/
rc = decode_operand(ctxt, &ctxt->src, (ctxt->d >> SrcShift) & OpMask);
if (rc != X86EMUL_CONTINUE)
goto done;
/*
* Decode and fetch the second source operand: register, memory
* or immediate.
*/
rc = decode_operand(ctxt, &ctxt->src2, (ctxt->d >> Src2Shift) & OpMask);
if (rc != X86EMUL_CONTINUE)
goto done;
/* Decode and fetch the destination operand: register or memory. */
rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
done:
if (ctxt->rip_relative)
ctxt->memopp->addr.mem.ea += ctxt->_eip;
return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'KVM: emulate: avoid accessing NULL ctxt->memopp
A failure to decode the instruction can cause a NULL pointer access.
This is fixed simply by moving the "done" label as close as possible
to the return.
This fixes CVE-2014-8481.
Reported-by: Andy Lutomirski <[email protected]>
Cc: [email protected]
Fixes: 41061cdb98a0bec464278b4db8e894a3121671f5
Signed-off-by: Paolo Bonzini <[email protected]>'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void gps_tracker( void )
{
ssize_t unused;
int gpsd_sock;
char line[256], *temp;
struct sockaddr_in gpsd_addr;
int ret, is_json, pos;
fd_set read_fd;
struct timeval timeout;
/* attempt to connect to localhost, port 2947 */
pos = 0;
gpsd_sock = socket( AF_INET, SOCK_STREAM, 0 );
if( gpsd_sock < 0 ) {
return;
}
gpsd_addr.sin_family = AF_INET;
gpsd_addr.sin_port = htons( 2947 );
gpsd_addr.sin_addr.s_addr = inet_addr( "127.0.0.1" );
if( connect( gpsd_sock, (struct sockaddr *) &gpsd_addr,
sizeof( gpsd_addr ) ) < 0 ) {
return;
}
// Check if it's GPSd < 2.92 or the new one
// 2.92+ immediately send stuff
// < 2.92 requires to send PVTAD command
FD_ZERO(&read_fd);
FD_SET(gpsd_sock, &read_fd);
timeout.tv_sec = 1;
timeout.tv_usec = 0;
is_json = select(gpsd_sock + 1, &read_fd, NULL, NULL, &timeout);
if (is_json) {
/*
{"class":"VERSION","release":"2.95","rev":"2010-11-16T21:12:35","proto_major":3,"proto_minor":3}
?WATCH={"json":true};
{"class":"DEVICES","devices":[]}
*/
// Get the crap and ignore it: {"class":"VERSION","release":"2.95","rev":"2010-11-16T21:12:35","proto_major":3,"proto_minor":3}
if( recv( gpsd_sock, line, sizeof( line ) - 1, 0 ) <= 0 )
return;
is_json = (line[0] == '{');
if (is_json) {
// Send ?WATCH={"json":true};
memset( line, 0, sizeof( line ) );
strcpy(line, "?WATCH={\"json\":true};\n");
if( send( gpsd_sock, line, 22, 0 ) != 22 )
return;
// Check that we have devices
memset(line, 0, sizeof(line));
if( recv( gpsd_sock, line, sizeof( line ) - 1, 0 ) <= 0 )
return;
// Stop processing if there is no device
if (strncmp(line, "{\"class\":\"DEVICES\",\"devices\":[]}", 32) == 0) {
close(gpsd_sock);
return;
} else {
pos = strlen(line);
}
}
}
/* loop reading the GPS coordinates */
while( G.do_exit == 0 )
{
usleep( 500000 );
memset( G.gps_loc, 0, sizeof( float ) * 5 );
/* read position, speed, heading, altitude */
if (is_json) {
// Format definition: http://catb.org/gpsd/gpsd_json.html
if (pos == sizeof( line )) {
memset(line, 0, sizeof(line));
pos = 0;
}
// New version, JSON
if( recv( gpsd_sock, line + pos, sizeof( line ) - 1, 0 ) <= 0 )
return;
// search for TPV class: {"class":"TPV"
temp = strstr(line, "{\"class\":\"TPV\"");
if (temp == NULL) {
continue;
}
// Make sure the data we have is complete
if (strchr(temp, '}') == NULL) {
// Move the data at the beginning of the buffer;
pos = strlen(temp);
if (temp != line) {
memmove(line, temp, pos);
memset(line + pos, 0, sizeof(line) - pos);
}
}
// Example line: {"class":"TPV","tag":"MID2","device":"/dev/ttyUSB0","time":1350957517.000,"ept":0.005,"lat":46.878936576,"lon":-115.832602964,"alt":1968.382,"track":0.0000,"speed":0.000,"climb":0.000,"mode":3}
// Latitude
temp = strstr(temp, "\"lat\":");
if (temp == NULL) {
continue;
}
ret = sscanf(temp + 6, "%f", &G.gps_loc[0]);
// Longitude
temp = strstr(temp, "\"lon\":");
if (temp == NULL) {
continue;
}
ret = sscanf(temp + 6, "%f", &G.gps_loc[1]);
// Altitude
temp = strstr(temp, "\"alt\":");
if (temp == NULL) {
continue;
}
ret = sscanf(temp + 6, "%f", &G.gps_loc[4]);
// Speed
temp = strstr(temp, "\"speed\":");
if (temp == NULL) {
continue;
}
ret = sscanf(temp + 6, "%f", &G.gps_loc[2]);
// No more heading
// Get the next TPV class
temp = strstr(temp, "{\"class\":\"TPV\"");
if (temp == NULL) {
memset( line, 0, sizeof( line ) );
pos = 0;
} else {
pos = strlen(temp);
memmove(line, temp, pos);
memset(line + pos, 0, sizeof(line) - pos);
}
} else {
memset( line, 0, sizeof( line ) );
snprintf( line, sizeof( line ) - 1, "PVTAD\r\n" );
if( send( gpsd_sock, line, 7, 0 ) != 7 )
return;
memset( line, 0, sizeof( line ) );
if( recv( gpsd_sock, line, sizeof( line ) - 1, 0 ) <= 0 )
return;
if( memcmp( line, "GPSD,P=", 7 ) != 0 )
continue;
/* make sure the coordinates are present */
if( line[7] == '?' )
continue;
ret = sscanf( line + 7, "%f %f", &G.gps_loc[0], &G.gps_loc[1] );
if( ( temp = strstr( line, "V=" ) ) == NULL ) continue;
ret = sscanf( temp + 2, "%f", &G.gps_loc[2] ); /* speed */
if( ( temp = strstr( line, "T=" ) ) == NULL ) continue;
ret = sscanf( temp + 2, "%f", &G.gps_loc[3] ); /* heading */
if( ( temp = strstr( line, "A=" ) ) == NULL ) continue;
ret = sscanf( temp + 2, "%f", &G.gps_loc[4] ); /* altitude */
}
if (G.record_data)
fputs( line, G.f_gps );
G.save_gps = 1;
if (G.do_exit == 0)
{
unused = write( G.gc_pipe[1], G.gps_loc, sizeof( float ) * 5 );
kill( getppid(), SIGUSR2 );
}
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-787'], 'message': 'Airodump-ng: Fixed GPS stack overflow (Closes #13 on GitHub).
git-svn-id: http://svn.aircrack-ng.org/trunk@2416 28c6078b-6c39-48e3-add9-af49d547ecab'</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 handle(int s, unsigned char* data, int len, struct sockaddr_in *s_in)
{
char buf[2048];
unsigned short *cmd = (unsigned short *)buf;
int plen;
struct in_addr *addr = &s_in->sin_addr;
unsigned short *pid = (unsigned short*) data;
/* inet check */
if (len == S_HELLO_LEN && memcmp(data, "sorbo", 5) == 0) {
unsigned short *id = (unsigned short*) (data+5);
int x = 2+4+2;
*cmd = htons(S_CMD_INET_CHECK);
memcpy(cmd+1, addr, 4);
memcpy(cmd+1+2, id, 2);
printf("Inet check by %s %d\n",
inet_ntoa(*addr), ntohs(*id));
if (send(s, buf, x, 0) != x)
return 1;
return 0;
}
*cmd++ = htons(S_CMD_PACKET);
*cmd++ = *pid;
plen = len - 2;
last_id = ntohs(*pid);
if (last_id > 20000)
wrap = 1;
if (wrap && last_id < 100) {
wrap = 0;
memset(ids, 0, sizeof(ids));
}
printf("Got packet %d %d", last_id, plen);
if (is_dup(last_id)) {
printf(" (DUP)\n");
return 0;
}
printf("\n");
*cmd++ = htons(plen);
memcpy(cmd, data+2, plen);
plen += 2 + 2 + 2;
assert(plen <= (int) sizeof(buf));
if (send(s, buf, plen, 0) != plen)
return 1;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20', 'CWE-787'], 'message': 'Buddy-ng: Fixed segmentation fault (Closes #15 on GitHub).
git-svn-id: http://svn.aircrack-ng.org/trunk@2418 28c6078b-6c39-48e3-add9-af49d547ecab'</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 ssl_parse_supported_elliptic_curves( ssl_context *ssl,
const unsigned char *buf,
size_t len )
{
size_t list_size, our_size;
const unsigned char *p;
const ecp_curve_info *curve_info, **curves;
list_size = ( ( buf[0] << 8 ) | ( buf[1] ) );
if( list_size + 2 != len ||
list_size % 2 != 0 )
{
SSL_DEBUG_MSG( 1, ( "bad client hello message" ) );
return( POLARSSL_ERR_SSL_BAD_HS_CLIENT_HELLO );
}
/* Don't allow our peer to make us allocate too much memory,
* and leave room for a final 0 */
our_size = list_size / 2 + 1;
if( our_size > POLARSSL_ECP_DP_MAX )
our_size = POLARSSL_ECP_DP_MAX;
if( ( curves = polarssl_malloc( our_size * sizeof( *curves ) ) ) == NULL )
return( POLARSSL_ERR_SSL_MALLOC_FAILED );
/* explicit void pointer cast for buggy MS compiler */
memset( (void *) curves, 0, our_size * sizeof( *curves ) );
ssl->handshake->curves = curves;
p = buf + 2;
while( list_size > 0 && our_size > 1 )
{
curve_info = ecp_curve_info_from_tls_id( ( p[0] << 8 ) | p[1] );
if( curve_info != NULL )
{
*curves++ = curve_info;
our_size--;
}
list_size -= 2;
p += 2;
}
return( 0 );
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-310'], 'message': 'Fix memory leak with crafted ClientHello'</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_ecc_ansi_x963_export (gnutls_ecc_curve_t curve, bigint_t x, bigint_t y,
gnutls_datum_t * out)
{
int numlen = gnutls_ecc_curve_get_size (curve);
int byte_size, ret;
size_t size;
if (numlen == 0)
return gnutls_assert_val (GNUTLS_E_INVALID_REQUEST);
out->size = 1 + 2 * numlen;
out->data = gnutls_malloc (out->size);
if (out->data == NULL)
return gnutls_assert_val (GNUTLS_E_MEMORY_ERROR);
memset (out->data, 0, out->size);
/* store byte 0x04 */
out->data[0] = 0x04;
/* pad and store x */
byte_size = (_gnutls_mpi_get_nbits (x) + 7) / 8;
size = out->size - (1 + (numlen - byte_size));
ret = _gnutls_mpi_print (x, &out->data[1 + (numlen - byte_size)], &size);
if (ret < 0)
return gnutls_assert_val (ret);
byte_size = (_gnutls_mpi_get_nbits (y) + 7) / 8;
size = out->size - (1 + (numlen + numlen - byte_size));
ret =
_gnutls_mpi_print (y, &out->data[1 + numlen + numlen - byte_size], &size);
if (ret < 0)
return gnutls_assert_val (ret);
/* pad and store y */
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-310'], 'message': 'when exporting curve coordinates to X9.63 format, perform additional sanity checks on input
Reported by Sean Burford.'</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 ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
{
struct trace_array *tr = data;
struct ftrace_event_file *ftrace_file;
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
unsigned long irq_flags;
int pc;
int syscall_nr;
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
if (!ftrace_file)
return;
if (ftrace_trigger_soft_disabled(ftrace_file))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
local_save_flags(irq_flags);
pc = preempt_count();
buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer,
sys_data->enter_event->event.type, size, irq_flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
irq_flags, pc);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-125', 'CWE-476', 'CWE-119', 'CWE-264'], 'message': 'tracing/syscalls: Ignore numbers outside NR_syscalls' range
ARM has some private syscalls (for example, set_tls(2)) which lie
outside the range of NR_syscalls. If any of these are called while
syscall tracing is being performed, out-of-bounds array access will
occur in the ftrace and perf sys_{enter,exit} handlers.
# trace-cmd record -e raw_syscalls:* true && trace-cmd report
...
true-653 [000] 384.675777: sys_enter: NR 192 (0, 1000, 3, 4000022, ffffffff, 0)
true-653 [000] 384.675812: sys_exit: NR 192 = 1995915264
true-653 [000] 384.675971: sys_enter: NR 983045 (76f74480, 76f74000, 76f74b28, 76f74480, 76f76f74, 1)
true-653 [000] 384.675988: sys_exit: NR 983045 = 0
...
# trace-cmd record -e syscalls:* true
[ 17.289329] Unable to handle kernel paging request at virtual address aaaaaace
[ 17.289590] pgd = 9e71c000
[ 17.289696] [aaaaaace] *pgd=00000000
[ 17.289985] Internal error: Oops: 5 [#1] PREEMPT SMP ARM
[ 17.290169] Modules linked in:
[ 17.290391] CPU: 0 PID: 704 Comm: true Not tainted 3.18.0-rc2+ #21
[ 17.290585] task: 9f4dab00 ti: 9e710000 task.ti: 9e710000
[ 17.290747] PC is at ftrace_syscall_enter+0x48/0x1f8
[ 17.290866] LR is at syscall_trace_enter+0x124/0x184
Fix this by ignoring out-of-NR_syscalls-bounds syscall numbers.
Commit cd0980fc8add "tracing: Check invalid syscall nr while tracing syscalls"
added the check for less than zero, but it should have also checked
for greater than NR_syscalls.
Link: http://lkml.kernel.org/p/[email protected]
Fixes: cd0980fc8add "tracing: Check invalid syscall nr while tracing syscalls"
Cc: [email protected] # 2.6.33+
Signed-off-by: Rabin Vincent <[email protected]>
Signed-off-by: Steven Rostedt <[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 perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
struct hlist_head *head;
int syscall_nr;
int rctx;
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
head = this_cpu_ptr(sys_data->exit_event->perf_events);
if (hlist_empty(head))
return;
/* We can probably do that at build time */
size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
sys_data->exit_event->event.type, regs, &rctx);
if (!rec)
return;
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-125', 'CWE-476', 'CWE-119', 'CWE-264'], 'message': 'tracing/syscalls: Ignore numbers outside NR_syscalls' range
ARM has some private syscalls (for example, set_tls(2)) which lie
outside the range of NR_syscalls. If any of these are called while
syscall tracing is being performed, out-of-bounds array access will
occur in the ftrace and perf sys_{enter,exit} handlers.
# trace-cmd record -e raw_syscalls:* true && trace-cmd report
...
true-653 [000] 384.675777: sys_enter: NR 192 (0, 1000, 3, 4000022, ffffffff, 0)
true-653 [000] 384.675812: sys_exit: NR 192 = 1995915264
true-653 [000] 384.675971: sys_enter: NR 983045 (76f74480, 76f74000, 76f74b28, 76f74480, 76f76f74, 1)
true-653 [000] 384.675988: sys_exit: NR 983045 = 0
...
# trace-cmd record -e syscalls:* true
[ 17.289329] Unable to handle kernel paging request at virtual address aaaaaace
[ 17.289590] pgd = 9e71c000
[ 17.289696] [aaaaaace] *pgd=00000000
[ 17.289985] Internal error: Oops: 5 [#1] PREEMPT SMP ARM
[ 17.290169] Modules linked in:
[ 17.290391] CPU: 0 PID: 704 Comm: true Not tainted 3.18.0-rc2+ #21
[ 17.290585] task: 9f4dab00 ti: 9e710000 task.ti: 9e710000
[ 17.290747] PC is at ftrace_syscall_enter+0x48/0x1f8
[ 17.290866] LR is at syscall_trace_enter+0x124/0x184
Fix this by ignoring out-of-NR_syscalls-bounds syscall numbers.
Commit cd0980fc8add "tracing: Check invalid syscall nr while tracing syscalls"
added the check for less than zero, but it should have also checked
for greater than NR_syscalls.
Link: http://lkml.kernel.org/p/[email protected]
Fixes: cd0980fc8add "tracing: Check invalid syscall nr while tracing syscalls"
Cc: [email protected] # 2.6.33+
Signed-off-by: Rabin Vincent <[email protected]>
Signed-off-by: Steven Rostedt <[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 sctp_process_param(struct sctp_association *asoc,
union sctp_params param,
const union sctp_addr *peer_addr,
gfp_t gfp)
{
struct net *net = sock_net(asoc->base.sk);
union sctp_addr addr;
int i;
__u16 sat;
int retval = 1;
sctp_scope_t scope;
time_t stale;
struct sctp_af *af;
union sctp_addr_param *addr_param;
struct sctp_transport *t;
struct sctp_endpoint *ep = asoc->ep;
/* We maintain all INIT parameters in network byte order all the
* time. This allows us to not worry about whether the parameters
* came from a fresh INIT, and INIT ACK, or were stored in a cookie.
*/
switch (param.p->type) {
case SCTP_PARAM_IPV6_ADDRESS:
if (PF_INET6 != asoc->base.sk->sk_family)
break;
goto do_addr_param;
case SCTP_PARAM_IPV4_ADDRESS:
/* v4 addresses are not allowed on v6-only socket */
if (ipv6_only_sock(asoc->base.sk))
break;
do_addr_param:
af = sctp_get_af_specific(param_type2af(param.p->type));
af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0);
scope = sctp_scope(peer_addr);
if (sctp_in_scope(net, &addr, scope))
if (!sctp_assoc_add_peer(asoc, &addr, gfp, SCTP_UNCONFIRMED))
return 0;
break;
case SCTP_PARAM_COOKIE_PRESERVATIVE:
if (!net->sctp.cookie_preserve_enable)
break;
stale = ntohl(param.life->lifespan_increment);
/* Suggested Cookie Life span increment's unit is msec,
* (1/1000sec).
*/
asoc->cookie_life = ktime_add_ms(asoc->cookie_life, stale);
break;
case SCTP_PARAM_HOST_NAME_ADDRESS:
pr_debug("%s: unimplemented SCTP_HOST_NAME_ADDRESS\n", __func__);
break;
case SCTP_PARAM_SUPPORTED_ADDRESS_TYPES:
/* Turn off the default values first so we'll know which
* ones are really set by the peer.
*/
asoc->peer.ipv4_address = 0;
asoc->peer.ipv6_address = 0;
/* Assume that peer supports the address family
* by which it sends a packet.
*/
if (peer_addr->sa.sa_family == AF_INET6)
asoc->peer.ipv6_address = 1;
else if (peer_addr->sa.sa_family == AF_INET)
asoc->peer.ipv4_address = 1;
/* Cycle through address types; avoid divide by 0. */
sat = ntohs(param.p->length) - sizeof(sctp_paramhdr_t);
if (sat)
sat /= sizeof(__u16);
for (i = 0; i < sat; ++i) {
switch (param.sat->types[i]) {
case SCTP_PARAM_IPV4_ADDRESS:
asoc->peer.ipv4_address = 1;
break;
case SCTP_PARAM_IPV6_ADDRESS:
if (PF_INET6 == asoc->base.sk->sk_family)
asoc->peer.ipv6_address = 1;
break;
case SCTP_PARAM_HOST_NAME_ADDRESS:
asoc->peer.hostname_address = 1;
break;
default: /* Just ignore anything else. */
break;
}
}
break;
case SCTP_PARAM_STATE_COOKIE:
asoc->peer.cookie_len =
ntohs(param.p->length) - sizeof(sctp_paramhdr_t);
asoc->peer.cookie = param.cookie->body;
break;
case SCTP_PARAM_HEARTBEAT_INFO:
/* Would be odd to receive, but it causes no problems. */
break;
case SCTP_PARAM_UNRECOGNIZED_PARAMETERS:
/* Rejected during verify stage. */
break;
case SCTP_PARAM_ECN_CAPABLE:
asoc->peer.ecn_capable = 1;
break;
case SCTP_PARAM_ADAPTATION_LAYER_IND:
asoc->peer.adaptation_ind = ntohl(param.aind->adaptation_ind);
break;
case SCTP_PARAM_SET_PRIMARY:
if (!net->sctp.addip_enable)
goto fall_through;
addr_param = param.v + sizeof(sctp_addip_param_t);
af = sctp_get_af_specific(param_type2af(param.p->type));
af->from_addr_param(&addr, addr_param,
htons(asoc->peer.port), 0);
/* if the address is invalid, we can't process it.
* XXX: see spec for what to do.
*/
if (!af->addr_valid(&addr, NULL, NULL))
break;
t = sctp_assoc_lookup_paddr(asoc, &addr);
if (!t)
break;
sctp_assoc_set_primary(asoc, t);
break;
case SCTP_PARAM_SUPPORTED_EXT:
sctp_process_ext_param(asoc, param);
break;
case SCTP_PARAM_FWD_TSN_SUPPORT:
if (net->sctp.prsctp_enable) {
asoc->peer.prsctp_capable = 1;
break;
}
/* Fall Through */
goto fall_through;
case SCTP_PARAM_RANDOM:
if (!ep->auth_enable)
goto fall_through;
/* Save peer's random parameter */
asoc->peer.peer_random = kmemdup(param.p,
ntohs(param.p->length), gfp);
if (!asoc->peer.peer_random) {
retval = 0;
break;
}
break;
case SCTP_PARAM_HMAC_ALGO:
if (!ep->auth_enable)
goto fall_through;
/* Save peer's HMAC list */
asoc->peer.peer_hmacs = kmemdup(param.p,
ntohs(param.p->length), gfp);
if (!asoc->peer.peer_hmacs) {
retval = 0;
break;
}
/* Set the default HMAC the peer requested*/
sctp_auth_asoc_set_default_hmac(asoc, param.hmac_algo);
break;
case SCTP_PARAM_CHUNKS:
if (!ep->auth_enable)
goto fall_through;
asoc->peer.peer_chunks = kmemdup(param.p,
ntohs(param.p->length), gfp);
if (!asoc->peer.peer_chunks)
retval = 0;
break;
fall_through:
default:
/* Any unrecognized parameters should have been caught
* and handled by sctp_verify_param() which should be
* called prior to this routine. Simply log the error
* here.
*/
pr_debug("%s: ignoring param:%d for association:%p.\n",
__func__, ntohs(param.p->type), asoc);
break;
}
return retval;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'net: sctp: fix NULL pointer dereference in af->from_addr_param on malformed packet
An SCTP server doing ASCONF will panic on malformed INIT ping-of-death
in the form of:
------------ INIT[PARAM: SET_PRIMARY_IP] ------------>
While the INIT chunk parameter verification dissects through many things
in order to detect malformed input, it misses to actually check parameters
inside of parameters. E.g. RFC5061, section 4.2.4 proposes a 'set primary
IP address' parameter in ASCONF, which has as a subparameter an address
parameter.
So an attacker may send a parameter type other than SCTP_PARAM_IPV4_ADDRESS
or SCTP_PARAM_IPV6_ADDRESS, param_type2af() will subsequently return 0
and thus sctp_get_af_specific() returns NULL, too, which we then happily
dereference unconditionally through af->from_addr_param().
The trace for the log:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000078
IP: [<ffffffffa01e9c62>] sctp_process_init+0x492/0x990 [sctp]
PGD 0
Oops: 0000 [#1] SMP
[...]
Pid: 0, comm: swapper Not tainted 2.6.32-504.el6.x86_64 #1 Bochs Bochs
RIP: 0010:[<ffffffffa01e9c62>] [<ffffffffa01e9c62>] sctp_process_init+0x492/0x990 [sctp]
[...]
Call Trace:
<IRQ>
[<ffffffffa01f2add>] ? sctp_bind_addr_copy+0x5d/0xe0 [sctp]
[<ffffffffa01e1fcb>] sctp_sf_do_5_1B_init+0x21b/0x340 [sctp]
[<ffffffffa01e3751>] sctp_do_sm+0x71/0x1210 [sctp]
[<ffffffffa01e5c09>] ? sctp_endpoint_lookup_assoc+0xc9/0xf0 [sctp]
[<ffffffffa01e61f6>] sctp_endpoint_bh_rcv+0x116/0x230 [sctp]
[<ffffffffa01ee986>] sctp_inq_push+0x56/0x80 [sctp]
[<ffffffffa01fcc42>] sctp_rcv+0x982/0xa10 [sctp]
[<ffffffffa01d5123>] ? ipt_local_in_hook+0x23/0x28 [iptable_filter]
[<ffffffff8148bdc9>] ? nf_iterate+0x69/0xb0
[<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
[<ffffffff8148bf86>] ? nf_hook_slow+0x76/0x120
[<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
[...]
A minimal way to address this is to check for NULL as we do on all
other such occasions where we know sctp_get_af_specific() could
possibly return with NULL.
Fixes: d6de3097592b ("[SCTP]: Add the handling of "Set Primary IP Address" parameter to INIT")
Signed-off-by: Daniel Borkmann <[email protected]>
Cc: Vlad Yasevich <[email protected]>
Acked-by: Neil Horman <[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 int handle_emulation_failure(struct kvm_vcpu *vcpu)
{
int r = EMULATE_DONE;
++vcpu->stat.insn_emulation_fail;
trace_kvm_emulate_insn_failed(vcpu);
if (!is_guest_mode(vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
r = EMULATE_FAIL;
}
kvm_queue_exception(vcpu, UD_VECTOR);
return r;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-362'], 'message': 'KVM: x86: Don't report guest userspace emulation error to userspace
Commit fc3a9157d314 ("KVM: X86: Don't report L2 emulation failures to
user-space") disabled the reporting of L2 (nested guest) emulation failures to
userspace due to race-condition between a vmexit and the instruction emulator.
The same rational applies also to userspace applications that are permitted by
the guest OS to access MMIO area or perform PIO.
This patch extends the current behavior - of injecting a #UD instead of
reporting it to userspace - also for guest userspace code.
Signed-off-by: Nadav Amit <[email protected]>
Signed-off-by: Paolo Bonzini <[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 ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struct dvb_diseqc_master_cmd *cmd)
{
struct ttusbdecfe_state* state = (struct ttusbdecfe_state*) fe->demodulator_priv;
u8 b[] = { 0x00, 0xff, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00,
0x00, 0x00 };
memcpy(&b[4], cmd->msg, cmd->msg_len);
state->config->send_command(fe, 0x72,
sizeof(b) - (6 - cmd->msg_len), b,
NULL, NULL);
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': '[media] ttusb-dec: buffer overflow in ioctl
We need to add a limit check here so we don't overflow the buffer.
Signed-off-by: Dan Carpenter <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void CServer::ProcessClientPacket(CNetChunk *pPacket)
{
int ClientID = pPacket->m_ClientID;
CUnpacker Unpacker;
Unpacker.Reset(pPacket->m_pData, pPacket->m_DataSize);
// unpack msgid and system flag
int Msg = Unpacker.GetInt();
int Sys = Msg&1;
Msg >>= 1;
if(Unpacker.Error())
return;
if(Sys)
{
// system message
if(Msg == NETMSG_INFO)
{
if(m_aClients[ClientID].m_State == CClient::STATE_AUTH)
{
const char *pVersion = Unpacker.GetString(CUnpacker::SANITIZE_CC);
if(str_comp(pVersion, GameServer()->NetVersion()) != 0)
{
// wrong version
char aReason[256];
str_format(aReason, sizeof(aReason), "Wrong version. Server is running '%s' and client '%s'", GameServer()->NetVersion(), pVersion);
m_NetServer.Drop(ClientID, aReason);
return;
}
const char *pPassword = Unpacker.GetString(CUnpacker::SANITIZE_CC);
if(g_Config.m_Password[0] != 0 && str_comp(g_Config.m_Password, pPassword) != 0)
{
// wrong password
m_NetServer.Drop(ClientID, "Wrong password");
return;
}
m_aClients[ClientID].m_State = CClient::STATE_CONNECTING;
SendMap(ClientID);
}
}
else if(Msg == NETMSG_REQUEST_MAP_DATA)
{
if(m_aClients[ClientID].m_State < CClient::STATE_CONNECTING)
return;
int Chunk = Unpacker.GetInt();
int ChunkSize = 1024-128;
int Offset = Chunk * ChunkSize;
int Last = 0;
// drop faulty map data requests
if(Chunk < 0 || Offset > m_CurrentMapSize)
return;
if(Offset+ChunkSize >= m_CurrentMapSize)
{
ChunkSize = m_CurrentMapSize-Offset;
if(ChunkSize < 0)
ChunkSize = 0;
Last = 1;
}
CMsgPacker Msg(NETMSG_MAP_DATA);
Msg.AddInt(Last);
Msg.AddInt(m_CurrentMapCrc);
Msg.AddInt(Chunk);
Msg.AddInt(ChunkSize);
Msg.AddRaw(&m_pCurrentMapData[Offset], ChunkSize);
SendMsgEx(&Msg, MSGFLAG_VITAL|MSGFLAG_FLUSH, ClientID, true);
if(g_Config.m_Debug)
{
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "sending chunk %d with size %d", Chunk, ChunkSize);
Console()->Print(IConsole::OUTPUT_LEVEL_DEBUG, "server", aBuf);
}
}
else if(Msg == NETMSG_READY)
{
if(m_aClients[ClientID].m_State == CClient::STATE_CONNECTING)
{
char aAddrStr[NETADDR_MAXSTRSIZE];
net_addr_str(m_NetServer.ClientAddr(ClientID), aAddrStr, sizeof(aAddrStr), true);
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "player is ready. ClientID=%x addr=%s", ClientID, aAddrStr);
Console()->Print(IConsole::OUTPUT_LEVEL_ADDINFO, "server", aBuf);
m_aClients[ClientID].m_State = CClient::STATE_READY;
GameServer()->OnClientConnected(ClientID);
SendConnectionReady(ClientID);
}
}
else if(Msg == NETMSG_ENTERGAME)
{
if(m_aClients[ClientID].m_State == CClient::STATE_READY && GameServer()->IsClientReady(ClientID))
{
char aAddrStr[NETADDR_MAXSTRSIZE];
net_addr_str(m_NetServer.ClientAddr(ClientID), aAddrStr, sizeof(aAddrStr), true);
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "player has entered the game. ClientID=%x addr=%s", ClientID, aAddrStr);
Console()->Print(IConsole::OUTPUT_LEVEL_STANDARD, "server", aBuf);
m_aClients[ClientID].m_State = CClient::STATE_INGAME;
GameServer()->OnClientEnter(ClientID);
}
}
else if(Msg == NETMSG_INPUT)
{
CClient::CInput *pInput;
int64 TagTime;
m_aClients[ClientID].m_LastAckedSnapshot = Unpacker.GetInt();
int IntendedTick = Unpacker.GetInt();
int Size = Unpacker.GetInt();
// check for errors
if(Unpacker.Error() || Size/4 > MAX_INPUT_SIZE)
return;
if(m_aClients[ClientID].m_LastAckedSnapshot > 0)
m_aClients[ClientID].m_SnapRate = CClient::SNAPRATE_FULL;
if(m_aClients[ClientID].m_Snapshots.Get(m_aClients[ClientID].m_LastAckedSnapshot, &TagTime, 0, 0) >= 0)
m_aClients[ClientID].m_Latency = (int)(((time_get()-TagTime)*1000)/time_freq());
// add message to report the input timing
// skip packets that are old
if(IntendedTick > m_aClients[ClientID].m_LastInputTick)
{
int TimeLeft = ((TickStartTime(IntendedTick)-time_get())*1000) / time_freq();
CMsgPacker Msg(NETMSG_INPUTTIMING);
Msg.AddInt(IntendedTick);
Msg.AddInt(TimeLeft);
SendMsgEx(&Msg, 0, ClientID, true);
}
m_aClients[ClientID].m_LastInputTick = IntendedTick;
pInput = &m_aClients[ClientID].m_aInputs[m_aClients[ClientID].m_CurrentInput];
if(IntendedTick <= Tick())
IntendedTick = Tick()+1;
pInput->m_GameTick = IntendedTick;
for(int i = 0; i < Size/4; i++)
pInput->m_aData[i] = Unpacker.GetInt();
mem_copy(m_aClients[ClientID].m_LatestInput.m_aData, pInput->m_aData, MAX_INPUT_SIZE*sizeof(int));
m_aClients[ClientID].m_CurrentInput++;
m_aClients[ClientID].m_CurrentInput %= 200;
// call the mod with the fresh input data
if(m_aClients[ClientID].m_State == CClient::STATE_INGAME)
GameServer()->OnClientDirectInput(ClientID, m_aClients[ClientID].m_LatestInput.m_aData);
}
else if(Msg == NETMSG_RCON_CMD)
{
const char *pCmd = Unpacker.GetString();
if(Unpacker.Error() == 0 && m_aClients[ClientID].m_Authed)
{
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "ClientID=%d rcon='%s'", ClientID, pCmd);
Console()->Print(IConsole::OUTPUT_LEVEL_ADDINFO, "server", aBuf);
m_RconClientID = ClientID;
m_RconAuthLevel = m_aClients[ClientID].m_Authed;
Console()->SetAccessLevel(m_aClients[ClientID].m_Authed == AUTHED_ADMIN ? IConsole::ACCESS_LEVEL_ADMIN : IConsole::ACCESS_LEVEL_MOD);
Console()->ExecuteLineFlag(pCmd, CFGFLAG_SERVER);
Console()->SetAccessLevel(IConsole::ACCESS_LEVEL_ADMIN);
m_RconClientID = IServer::RCON_CID_SERV;
m_RconAuthLevel = AUTHED_ADMIN;
}
}
else if(Msg == NETMSG_RCON_AUTH)
{
const char *pPw;
Unpacker.GetString(); // login name, not used
pPw = Unpacker.GetString(CUnpacker::SANITIZE_CC);
if(Unpacker.Error() == 0)
{
if(g_Config.m_SvRconPassword[0] == 0 && g_Config.m_SvRconModPassword[0] == 0)
{
SendRconLine(ClientID, "No rcon password set on server. Set sv_rcon_password and/or sv_rcon_mod_password to enable the remote console.");
}
else if(g_Config.m_SvRconPassword[0] && str_comp(pPw, g_Config.m_SvRconPassword) == 0)
{
CMsgPacker Msg(NETMSG_RCON_AUTH_STATUS);
Msg.AddInt(1); //authed
Msg.AddInt(1); //cmdlist
SendMsgEx(&Msg, MSGFLAG_VITAL, ClientID, true);
m_aClients[ClientID].m_Authed = AUTHED_ADMIN;
int SendRconCmds = Unpacker.GetInt();
if(Unpacker.Error() == 0 && SendRconCmds)
m_aClients[ClientID].m_pRconCmdToSend = Console()->FirstCommandInfo(IConsole::ACCESS_LEVEL_ADMIN, CFGFLAG_SERVER);
SendRconLine(ClientID, "Admin authentication successful. Full remote console access granted.");
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "ClientID=%d authed (admin)", ClientID);
Console()->Print(IConsole::OUTPUT_LEVEL_STANDARD, "server", aBuf);
}
else if(g_Config.m_SvRconModPassword[0] && str_comp(pPw, g_Config.m_SvRconModPassword) == 0)
{
CMsgPacker Msg(NETMSG_RCON_AUTH_STATUS);
Msg.AddInt(1); //authed
Msg.AddInt(1); //cmdlist
SendMsgEx(&Msg, MSGFLAG_VITAL, ClientID, true);
m_aClients[ClientID].m_Authed = AUTHED_MOD;
int SendRconCmds = Unpacker.GetInt();
if(Unpacker.Error() == 0 && SendRconCmds)
m_aClients[ClientID].m_pRconCmdToSend = Console()->FirstCommandInfo(IConsole::ACCESS_LEVEL_MOD, CFGFLAG_SERVER);
SendRconLine(ClientID, "Moderator authentication successful. Limited remote console access granted.");
char aBuf[256];
str_format(aBuf, sizeof(aBuf), "ClientID=%d authed (moderator)", ClientID);
Console()->Print(IConsole::OUTPUT_LEVEL_STANDARD, "server", aBuf);
}
else if(g_Config.m_SvRconMaxTries)
{
m_aClients[ClientID].m_AuthTries++;
char aBuf[128];
str_format(aBuf, sizeof(aBuf), "Wrong password %d/%d.", m_aClients[ClientID].m_AuthTries, g_Config.m_SvRconMaxTries);
SendRconLine(ClientID, aBuf);
if(m_aClients[ClientID].m_AuthTries >= g_Config.m_SvRconMaxTries)
{
if(!g_Config.m_SvRconBantime)
m_NetServer.Drop(ClientID, "Too many remote console authentication tries");
else
m_ServerBan.BanAddr(m_NetServer.ClientAddr(ClientID), g_Config.m_SvRconBantime*60, "Too many remote console authentication tries");
}
}
else
{
SendRconLine(ClientID, "Wrong password.");
}
}
}
else if(Msg == NETMSG_PING)
{
CMsgPacker Msg(NETMSG_PING_REPLY);
SendMsgEx(&Msg, 0, ClientID, true);
}
else
{
if(g_Config.m_Debug)
{
char aHex[] = "0123456789ABCDEF";
char aBuf[512];
for(int b = 0; b < pPacket->m_DataSize && b < 32; b++)
{
aBuf[b*3] = aHex[((const unsigned char *)pPacket->m_pData)[b]>>4];
aBuf[b*3+1] = aHex[((const unsigned char *)pPacket->m_pData)[b]&0xf];
aBuf[b*3+2] = ' ';
aBuf[b*3+3] = 0;
}
char aBufMsg[256];
str_format(aBufMsg, sizeof(aBufMsg), "strange message ClientID=%d msg=%d data_size=%d", ClientID, Msg, pPacket->m_DataSize);
Console()->Print(IConsole::OUTPUT_LEVEL_DEBUG, "server", aBufMsg);
Console()->Print(IConsole::OUTPUT_LEVEL_DEBUG, "server", aBuf);
}
}
}
else
{
// game message
if(m_aClients[ClientID].m_State >= CClient::STATE_READY)
GameServer()->OnMessage(Msg, &Unpacker, ClientID);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'fixed a server crash'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int jpc_dec_process_coc(jpc_dec_t *dec, jpc_ms_t *ms)
{
jpc_coc_t *coc = &ms->parms.coc;
jpc_dec_tile_t *tile;
if (JAS_CAST(int, coc->compno) > dec->numcomps) {
jas_eprintf("invalid component number in COC marker segment\n");
return -1;
}
switch (dec->state) {
case JPC_MH:
jpc_dec_cp_setfromcoc(dec->cp, coc);
break;
case JPC_TPH:
if (!(tile = dec->curtile)) {
return -1;
}
if (tile->partno > 0) {
return -1;
}
jpc_dec_cp_setfromcoc(tile->cp, coc);
break;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'CVE-2014-9029'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: static int jpc_dec_process_qcc(jpc_dec_t *dec, jpc_ms_t *ms)
{
jpc_qcc_t *qcc = &ms->parms.qcc;
jpc_dec_tile_t *tile;
if (JAS_CAST(int, qcc->compno) > dec->numcomps) {
jas_eprintf("invalid component number in QCC marker segment\n");
return -1;
}
switch (dec->state) {
case JPC_MH:
jpc_dec_cp_setfromqcc(dec->cp, qcc);
break;
case JPC_TPH:
if (!(tile = dec->curtile)) {
return -1;
}
if (tile->partno > 0) {
return -1;
}
jpc_dec_cp_setfromqcc(tile->cp, qcc);
break;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-189'], 'message': 'CVE-2014-9029'</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: FLAC__bool read_residual_partitioned_rice_(FLAC__StreamDecoder *decoder, unsigned predictor_order, unsigned partition_order, FLAC__EntropyCodingMethod_PartitionedRiceContents *partitioned_rice_contents, FLAC__int32 *residual, FLAC__bool is_extended)
{
FLAC__uint32 rice_parameter;
int i;
unsigned partition, sample, u;
const unsigned partitions = 1u << partition_order;
const unsigned partition_samples = partition_order > 0? decoder->private_->frame.header.blocksize >> partition_order : decoder->private_->frame.header.blocksize - predictor_order;
const unsigned plen = is_extended? FLAC__ENTROPY_CODING_METHOD_PARTITIONED_RICE2_PARAMETER_LEN : FLAC__ENTROPY_CODING_METHOD_PARTITIONED_RICE_PARAMETER_LEN;
const unsigned pesc = is_extended? FLAC__ENTROPY_CODING_METHOD_PARTITIONED_RICE2_ESCAPE_PARAMETER : FLAC__ENTROPY_CODING_METHOD_PARTITIONED_RICE_ESCAPE_PARAMETER;
/* sanity checks */
if(partition_order == 0) {
if(decoder->private_->frame.header.blocksize < predictor_order) {
send_error_to_client_(decoder, FLAC__STREAM_DECODER_ERROR_STATUS_LOST_SYNC);
decoder->protected_->state = FLAC__STREAM_DECODER_SEARCH_FOR_FRAME_SYNC;
/* We have received a potentially malicious bit stream. All we can do is error out to avoid a heap overflow. */
return false;
}
}
else {
if(partition_samples < predictor_order) {
send_error_to_client_(decoder, FLAC__STREAM_DECODER_ERROR_STATUS_LOST_SYNC);
decoder->protected_->state = FLAC__STREAM_DECODER_SEARCH_FOR_FRAME_SYNC;
return true;
}
}
if(!FLAC__format_entropy_coding_method_partitioned_rice_contents_ensure_size(partitioned_rice_contents, flac_max(6u, partition_order))) {
decoder->protected_->state = FLAC__STREAM_DECODER_MEMORY_ALLOCATION_ERROR;
return false;
}
sample = 0;
for(partition = 0; partition < partitions; partition++) {
if(!FLAC__bitreader_read_raw_uint32(decoder->private_->input, &rice_parameter, plen))
return false; /* read_callback_ sets the state for us */
partitioned_rice_contents->parameters[partition] = rice_parameter;
if(rice_parameter < pesc) {
partitioned_rice_contents->raw_bits[partition] = 0;
u = (partition_order == 0 || partition > 0)? partition_samples : partition_samples - predictor_order;
if(!FLAC__bitreader_read_rice_signed_block(decoder->private_->input, residual + sample, u, rice_parameter))
return false; /* read_callback_ sets the state for us */
sample += u;
}
else {
if(!FLAC__bitreader_read_raw_uint32(decoder->private_->input, &rice_parameter, FLAC__ENTROPY_CODING_METHOD_PARTITIONED_RICE_RAW_LEN))
return false; /* read_callback_ sets the state for us */
partitioned_rice_contents->raw_bits[partition] = rice_parameter;
for(u = (partition_order == 0 || partition > 0)? 0 : predictor_order; u < partition_samples; u++, sample++) {
if(!FLAC__bitreader_read_raw_int32(decoder->private_->input, &i, rice_parameter))
return false; /* read_callback_ sets the state for us */
residual[sample] = i;
}
}
}
return true;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'src/libFLAC/stream_decoder.c : Fail safely to avoid a heap overflow.
This fix is closely related to the fix for CVE-2014-9028. When that
fix went public Miroslav Lichvar noticed a similar potential problem
spot in the same function and was able to craft a file to trigger a
heap write overflow.
Reported-by : Miroslav Lichvar <[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: hivex_open (const char *filename, int flags)
{
hive_h *h = NULL;
assert (sizeof (struct ntreg_header) == 0x1000);
assert (offsetof (struct ntreg_header, csum) == 0x1fc);
h = calloc (1, sizeof *h);
if (h == NULL)
goto error;
h->msglvl = flags & HIVEX_OPEN_MSGLVL_MASK;
const char *debug = getenv ("HIVEX_DEBUG");
if (debug && STREQ (debug, "1"))
h->msglvl = 2;
DEBUG (2, "created handle %p", h);
h->writable = !!(flags & HIVEX_OPEN_WRITE);
h->filename = strdup (filename);
if (h->filename == NULL)
goto error;
#ifdef O_CLOEXEC
h->fd = open (filename, O_RDONLY | O_CLOEXEC | O_BINARY);
#else
h->fd = open (filename, O_RDONLY | O_BINARY);
#endif
if (h->fd == -1)
goto error;
#ifndef O_CLOEXEC
fcntl (h->fd, F_SETFD, FD_CLOEXEC);
#endif
struct stat statbuf;
if (fstat (h->fd, &statbuf) == -1)
goto error;
h->size = statbuf.st_size;
if (h->size < 0x2000) {
SET_ERRNO (EINVAL,
"%s: file is too small to be a Windows NT Registry hive file",
filename);
goto error;
}
if (!h->writable) {
h->addr = mmap (NULL, h->size, PROT_READ, MAP_SHARED, h->fd, 0);
if (h->addr == MAP_FAILED)
goto error;
DEBUG (2, "mapped file at %p", h->addr);
} else {
h->addr = malloc (h->size);
if (h->addr == NULL)
goto error;
if (full_read (h->fd, h->addr, h->size) < h->size)
goto error;
/* We don't need the file descriptor along this path, since we
* have read all the data.
*/
if (close (h->fd) == -1)
goto error;
h->fd = -1;
}
/* Check header. */
if (h->hdr->magic[0] != 'r' ||
h->hdr->magic[1] != 'e' ||
h->hdr->magic[2] != 'g' ||
h->hdr->magic[3] != 'f') {
SET_ERRNO (ENOTSUP,
"%s: not a Windows NT Registry hive file", filename);
goto error;
}
/* Check major version. */
uint32_t major_ver = le32toh (h->hdr->major_ver);
if (major_ver != 1) {
SET_ERRNO (ENOTSUP,
"%s: hive file major version %" PRIu32 " (expected 1)",
filename, major_ver);
goto error;
}
h->bitmap = calloc (1 + h->size / 32, 1);
if (h->bitmap == NULL)
goto error;
/* Header checksum. */
uint32_t sum = header_checksum (h);
if (sum != le32toh (h->hdr->csum)) {
SET_ERRNO (EINVAL, "%s: bad checksum in hive header", filename);
goto error;
}
/* Last modified time. */
h->last_modified = le64toh ((int64_t) h->hdr->last_modified);
if (h->msglvl >= 2) {
char *name = _hivex_windows_utf16_to_utf8 (h->hdr->name, 64);
fprintf (stderr,
"hivex_open: header fields:\n"
" file version %" PRIu32 ".%" PRIu32 "\n"
" sequence nos %" PRIu32 " %" PRIu32 "\n"
" (sequences nos should match if hive was synched at shutdown)\n"
" last modified %" PRIu64 "\n"
" (Windows filetime, x 100 ns since 1601-01-01)\n"
" original file name %s\n"
" (only 32 chars are stored, name is probably truncated)\n"
" root offset 0x%x + 0x1000\n"
" end of last page 0x%x + 0x1000 (total file size 0x%zx)\n"
" checksum 0x%x (calculated 0x%x)\n",
major_ver, le32toh (h->hdr->minor_ver),
le32toh (h->hdr->sequence1), le32toh (h->hdr->sequence2),
h->last_modified,
name ? name : "(conversion failed)",
le32toh (h->hdr->offset),
le32toh (h->hdr->blocks), h->size,
le32toh (h->hdr->csum), sum);
free (name);
}
h->rootoffs = le32toh (h->hdr->offset) + 0x1000;
h->endpages = le32toh (h->hdr->blocks) + 0x1000;
DEBUG (2, "root offset = 0x%zx", h->rootoffs);
/* We'll set this flag when we see a block with the root offset (ie.
* the root block).
*/
int seen_root_block = 0, bad_root_block = 0;
/* Collect some stats. */
size_t pages = 0; /* Number of hbin pages read. */
size_t smallest_page = SIZE_MAX, largest_page = 0;
size_t blocks = 0; /* Total number of blocks found. */
size_t smallest_block = SIZE_MAX, largest_block = 0, blocks_bytes = 0;
size_t used_blocks = 0; /* Total number of used blocks found. */
size_t used_size = 0; /* Total size (bytes) of used blocks. */
/* Read the pages and blocks. The aim here is to be robust against
* corrupt or malicious registries. So we make sure the loops
* always make forward progress. We add the address of each block
* we read to a hash table so pointers will only reference the start
* of valid blocks.
*/
size_t off;
struct ntreg_hbin_page *page;
for (off = 0x1000; off < h->size; off += le32toh (page->page_size)) {
if (off >= h->endpages)
break;
page = (struct ntreg_hbin_page *) ((char *) h->addr + off);
if (page->magic[0] != 'h' ||
page->magic[1] != 'b' ||
page->magic[2] != 'i' ||
page->magic[3] != 'n') {
SET_ERRNO (ENOTSUP,
"%s: trailing garbage at end of file "
"(at 0x%zx, after %zu pages)",
filename, off, pages);
goto error;
}
size_t page_size = le32toh (page->page_size);
DEBUG (2, "page at 0x%zx, size %zu", off, page_size);
pages++;
if (page_size < smallest_page) smallest_page = page_size;
if (page_size > largest_page) largest_page = page_size;
if (page_size <= sizeof (struct ntreg_hbin_page) ||
(page_size & 0x0fff) != 0) {
SET_ERRNO (ENOTSUP,
"%s: page size %zu at 0x%zx, bad registry",
filename, page_size, off);
goto error;
}
/* Read the blocks in this page. */
size_t blkoff;
struct ntreg_hbin_block *block;
size_t seg_len;
for (blkoff = off + 0x20;
blkoff < off + page_size;
blkoff += seg_len) {
blocks++;
int is_root = blkoff == h->rootoffs;
if (is_root)
seen_root_block = 1;
block = (struct ntreg_hbin_block *) ((char *) h->addr + blkoff);
int used;
seg_len = block_len (h, blkoff, &used);
if (seg_len <= 4 || (seg_len & 3) != 0) {
SET_ERRNO (ENOTSUP,
"%s: block size %" PRIu32 " at 0x%zx, bad registry",
filename, le32toh (block->seg_len), blkoff);
goto error;
}
if (h->msglvl >= 2) {
unsigned char *id = (unsigned char *) block->id;
int id0 = id[0], id1 = id[1];
fprintf (stderr, "%s: %s: "
"%s block id %d,%d (%c%c) at 0x%zx size %zu%s\n",
"hivex", __func__,
used ? "used" : "free",
id0, id1,
c_isprint (id0) ? id0 : '.',
c_isprint (id1) ? id1 : '.',
blkoff,
seg_len, is_root ? " (root)" : "");
}
blocks_bytes += seg_len;
if (seg_len < smallest_block) smallest_block = seg_len;
if (seg_len > largest_block) largest_block = seg_len;
if (is_root && !used)
bad_root_block = 1;
if (used) {
used_blocks++;
used_size += seg_len;
/* Root block must be an nk-block. */
if (is_root && (block->id[0] != 'n' || block->id[1] != 'k'))
bad_root_block = 1;
/* Note this blkoff is a valid address. */
BITMAP_SET (h->bitmap, blkoff);
}
}
}
if (!seen_root_block) {
SET_ERRNO (ENOTSUP, "%s: no root block found", filename);
goto error;
}
if (bad_root_block) {
SET_ERRNO (ENOTSUP, "%s: bad root block (free or not nk)", filename);
goto error;
}
DEBUG (1, "successfully read Windows Registry hive file:\n"
" pages: %zu [sml: %zu, lge: %zu]\n"
" blocks: %zu [sml: %zu, avg: %zu, lge: %zu]\n"
" blocks used: %zu\n"
" bytes used: %zu",
pages, smallest_page, largest_page,
blocks, smallest_block, blocks_bytes / blocks, largest_block,
used_blocks, used_size);
return h;
error:;
int err = errno;
if (h) {
free (h->bitmap);
if (h->addr && h->size && h->addr != MAP_FAILED) {
if (!h->writable)
munmap (h->addr, h->size);
else
free (h->addr);
}
if (h->fd >= 0)
close (h->fd);
free (h->filename);
free (h);
}
errno = err;
return NULL;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'handle: Check that pages do not extend beyond the end of the file.
Thanks: Mahmoud Al-Qudsi'</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 print_value(int output, int num, const char *devname,
const char *value, const char *name, size_t valsz)
{
if (output & OUTPUT_VALUE_ONLY) {
fputs(value, stdout);
fputc('\n', stdout);
} else if (output & OUTPUT_UDEV_LIST) {
print_udev_format(name, value);
} else if (output & OUTPUT_EXPORT_LIST) {
if (num == 1 && devname)
printf("DEVNAME=%s\n", devname);
fputs(name, stdout);
fputs("=", stdout);
safe_print(value, valsz, NULL);
fputs("\n", stdout);
} else {
if (num == 1 && devname)
printf("%s:", devname);
fputs(" ", stdout);
fputs(name, stdout);
fputs("=\"", stdout);
safe_print(value, valsz, "\"");
fputs("\"", stdout);
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-77'], 'message': 'libblkid: care about unsafe chars in cache
The high-level libblkid API uses /run/blkid/blkid.tab cache to
store probing results. The cache format is
<device NAME="value" ...>devname</device>
and unfortunately the cache code does not escape quotation marks:
# mkfs.ext4 -L 'AAA"BBB'
# cat /run/blkid/blkid.tab
...
<device ... LABEL="AAA"BBB" ...>/dev/sdb1</device>
such string is later incorrectly parsed and blkid(8) returns
nonsenses. And for use-cases like
# eval $(blkid -o export /dev/sdb1)
it's also insecure.
Note that mount, udevd and blkid -p are based on low-level libblkid
API, it bypass the cache and directly read data from the devices.
The current udevd upstream does not depend on blkid(8) output at all,
it's directly linked with the library and all unsafe chars are encoded by
\x<hex> notation.
# mkfs.ext4 -L 'X"`/tmp/foo` "' /dev/sdb1
# udevadm info --export-db | grep LABEL
...
E: ID_FS_LABEL=X__/tmp/foo___
E: ID_FS_LABEL_ENC=X\x22\x60\x2ftmp\x2ffoo\x60\x20\x22
Signed-off-by: Karel Zak <[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: yaml_parser_save_simple_key(yaml_parser_t *parser)
{
/*
* A simple key is required at the current position if the scanner is in
* the block context and the current column coincides with the indentation
* level.
*/
int required = (!parser->flow_level
&& parser->indent == (ptrdiff_t)parser->mark.column);
/*
* A simple key is required only when it is the first token in the current
* line. Therefore it is always allowed. But we add a check anyway.
*/
assert(parser->simple_key_allowed || !required); /* Impossible. */
/*
* If the current position may start a simple key, save it.
*/
if (parser->simple_key_allowed)
{
yaml_simple_key_t simple_key;
simple_key.possible = 1;
simple_key.required = required;
simple_key.token_number =
parser->tokens_parsed + (parser->tokens.tail - parser->tokens.head);
simple_key.mark = parser->mark;
if (!yaml_parser_remove_simple_key(parser)) return 0;
*(parser->simple_keys.top-1) = simple_key;
}
return 1;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-20'], 'message': 'Fix for https://bitbucket.org/xi/libyaml/issue/10/
https://bitbucket.org/xi/libyaml/issue/10/wrapped-strings-cause-assert-failure
Commenting out the assert makes the scanner do the right thing and
results in just a simple parse failure.'</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 __init trap_init(void)
{
int i;
#ifdef CONFIG_EISA
void __iomem *p = early_ioremap(0x0FFFD9, 4);
if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24))
EISA_bus = 1;
early_iounmap(p, 4);
#endif
set_intr_gate(X86_TRAP_DE, divide_error);
set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK);
/* int4 can be called from all */
set_system_intr_gate(X86_TRAP_OF, &overflow);
set_intr_gate(X86_TRAP_BR, bounds);
set_intr_gate(X86_TRAP_UD, invalid_op);
set_intr_gate(X86_TRAP_NM, device_not_available);
#ifdef CONFIG_X86_32
set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS);
#else
set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK);
#endif
set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun);
set_intr_gate(X86_TRAP_TS, invalid_TSS);
set_intr_gate(X86_TRAP_NP, segment_not_present);
set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
set_intr_gate(X86_TRAP_GP, general_protection);
set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug);
set_intr_gate(X86_TRAP_MF, coprocessor_error);
set_intr_gate(X86_TRAP_AC, alignment_check);
#ifdef CONFIG_X86_MCE
set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK);
#endif
set_intr_gate(X86_TRAP_XF, simd_coprocessor_error);
/* Reserve all the builtin and the syscall vector: */
for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
set_bit(i, used_vectors);
#ifdef CONFIG_IA32_EMULATION
set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
#ifdef CONFIG_X86_32
set_system_trap_gate(SYSCALL_VECTOR, &system_call);
set_bit(SYSCALL_VECTOR, used_vectors);
#endif
/*
* Set the IDT descriptor to a fixed read-only location, so that the
* "sidt" instruction will not leak the location of the kernel, and
* to defend the IDT against arbitrary memory write vulnerabilities.
* It will be reloaded in cpu_init() */
__set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
idt_descr.address = fix_to_virt(FIX_RO_IDT);
/*
* Should be a barrier for any external CPU state:
*/
cpu_init();
x86_init.irqs.trap_init();
#ifdef CONFIG_X86_64
memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16);
set_nmi_gate(X86_TRAP_DB, &debug);
set_nmi_gate(X86_TRAP_BP, &int3);
#endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-17'], 'message': 'x86_64, traps: Stop using IST for #SS
On a 32-bit kernel, this has no effect, since there are no IST stacks.
On a 64-bit kernel, #SS can only happen in user code, on a failed iret
to user space, a canonical violation on access via RSP or RBP, or a
genuine stack segment violation in 32-bit kernel code. The first two
cases don't need IST, and the latter two cases are unlikely fatal bugs,
and promoting them to double faults would be fine.
This fixes a bug in which the espfix64 code mishandles a stack segment
violation.
This saves 4k of memory per CPU and a tiny bit of code.
Signed-off-by: Andy Lutomirski <[email protected]>
Reviewed-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Signed-off-by: Linus Torvalds <[email protected]>'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: donote(struct magic_set *ms, void *vbuf, size_t offset, size_t size,
int clazz, int swap, size_t align, int *flags)
{
Elf32_Nhdr nh32;
Elf64_Nhdr nh64;
size_t noff, doff;
#ifdef ELFCORE
int os_style = -1;
#endif
uint32_t namesz, descsz;
unsigned char *nbuf = CAST(unsigned char *, vbuf);
if (xnh_sizeof + offset > size) {
/*
* We're out of note headers.
*/
return xnh_sizeof + offset;
}
(void)memcpy(xnh_addr, &nbuf[offset], xnh_sizeof);
offset += xnh_sizeof;
namesz = xnh_namesz;
descsz = xnh_descsz;
if ((namesz == 0) && (descsz == 0)) {
/*
* We're out of note headers.
*/
return (offset >= size) ? offset : size;
}
if (namesz & 0x80000000) {
(void)file_printf(ms, ", bad note name size 0x%lx",
(unsigned long)namesz);
return offset;
}
if (descsz & 0x80000000) {
(void)file_printf(ms, ", bad note description size 0x%lx",
(unsigned long)descsz);
return offset;
}
noff = offset;
doff = ELF_ALIGN(offset + namesz);
if (offset + namesz > size) {
/*
* We're past the end of the buffer.
*/
return doff;
}
offset = ELF_ALIGN(doff + descsz);
if (doff + descsz > size) {
/*
* We're past the end of the buffer.
*/
return (offset >= size) ? offset : size;
}
if ((*flags & (FLAGS_DID_NOTE|FLAGS_DID_BUILD_ID)) ==
(FLAGS_DID_NOTE|FLAGS_DID_BUILD_ID))
goto core;
if (namesz == 5 && strcmp((char *)&nbuf[noff], "SuSE") == 0 &&
xnh_type == NT_GNU_VERSION && descsz == 2) {
file_printf(ms, ", for SuSE %d.%d", nbuf[doff], nbuf[doff + 1]);
}
if (namesz == 4 && strcmp((char *)&nbuf[noff], "GNU") == 0 &&
xnh_type == NT_GNU_VERSION && descsz == 16) {
uint32_t desc[4];
(void)memcpy(desc, &nbuf[doff], sizeof(desc));
if (file_printf(ms, ", for GNU/") == -1)
return size;
switch (elf_getu32(swap, desc[0])) {
case GNU_OS_LINUX:
if (file_printf(ms, "Linux") == -1)
return size;
break;
case GNU_OS_HURD:
if (file_printf(ms, "Hurd") == -1)
return size;
break;
case GNU_OS_SOLARIS:
if (file_printf(ms, "Solaris") == -1)
return size;
break;
case GNU_OS_KFREEBSD:
if (file_printf(ms, "kFreeBSD") == -1)
return size;
break;
case GNU_OS_KNETBSD:
if (file_printf(ms, "kNetBSD") == -1)
return size;
break;
default:
if (file_printf(ms, "<unknown>") == -1)
return size;
}
if (file_printf(ms, " %d.%d.%d", elf_getu32(swap, desc[1]),
elf_getu32(swap, desc[2]), elf_getu32(swap, desc[3])) == -1)
return size;
*flags |= FLAGS_DID_NOTE;
return size;
}
if (namesz == 4 && strcmp((char *)&nbuf[noff], "GNU") == 0 &&
xnh_type == NT_GNU_BUILD_ID && (descsz == 16 || descsz == 20)) {
uint8_t desc[20];
uint32_t i;
if (file_printf(ms, ", BuildID[%s]=", descsz == 16 ? "md5/uuid" :
"sha1") == -1)
return size;
(void)memcpy(desc, &nbuf[doff], descsz);
for (i = 0; i < descsz; i++)
if (file_printf(ms, "%02x", desc[i]) == -1)
return size;
*flags |= FLAGS_DID_BUILD_ID;
}
if (namesz == 4 && strcmp((char *)&nbuf[noff], "PaX") == 0 &&
xnh_type == NT_NETBSD_PAX && descsz == 4) {
static const char *pax[] = {
"+mprotect",
"-mprotect",
"+segvguard",
"-segvguard",
"+ASLR",
"-ASLR",
};
uint32_t desc;
size_t i;
int did = 0;
(void)memcpy(&desc, &nbuf[doff], sizeof(desc));
desc = elf_getu32(swap, desc);
if (desc && file_printf(ms, ", PaX: ") == -1)
return size;
for (i = 0; i < __arraycount(pax); i++) {
if (((1 << i) & desc) == 0)
continue;
if (file_printf(ms, "%s%s", did++ ? "," : "",
pax[i]) == -1)
return size;
}
}
if (namesz == 7 && strcmp((char *)&nbuf[noff], "NetBSD") == 0) {
switch (xnh_type) {
case NT_NETBSD_VERSION:
if (descsz == 4) {
do_note_netbsd_version(ms, swap, &nbuf[doff]);
*flags |= FLAGS_DID_NOTE;
return size;
}
break;
case NT_NETBSD_MARCH:
if (file_printf(ms, ", compiled for: %.*s", (int)descsz,
(const char *)&nbuf[doff]) == -1)
return size;
break;
case NT_NETBSD_CMODEL:
if (file_printf(ms, ", compiler model: %.*s",
(int)descsz, (const char *)&nbuf[doff]) == -1)
return size;
break;
default:
if (file_printf(ms, ", note=%u", xnh_type) == -1)
return size;
break;
}
return size;
}
if (namesz == 8 && strcmp((char *)&nbuf[noff], "FreeBSD") == 0) {
if (xnh_type == NT_FREEBSD_VERSION && descsz == 4) {
do_note_freebsd_version(ms, swap, &nbuf[doff]);
*flags |= FLAGS_DID_NOTE;
return size;
}
}
if (namesz == 8 && strcmp((char *)&nbuf[noff], "OpenBSD") == 0 &&
xnh_type == NT_OPENBSD_VERSION && descsz == 4) {
if (file_printf(ms, ", for OpenBSD") == -1)
return size;
/* Content of note is always 0 */
*flags |= FLAGS_DID_NOTE;
return size;
}
if (namesz == 10 && strcmp((char *)&nbuf[noff], "DragonFly") == 0 &&
xnh_type == NT_DRAGONFLY_VERSION && descsz == 4) {
uint32_t desc;
if (file_printf(ms, ", for DragonFly") == -1)
return size;
(void)memcpy(&desc, &nbuf[doff], sizeof(desc));
desc = elf_getu32(swap, desc);
if (file_printf(ms, " %d.%d.%d", desc / 100000,
desc / 10000 % 10, desc % 10000) == -1)
return size;
*flags |= FLAGS_DID_NOTE;
return size;
}
core:
/*
* Sigh. The 2.0.36 kernel in Debian 2.1, at
* least, doesn't correctly implement name
* sections, in core dumps, as specified by
* the "Program Linking" section of "UNIX(R) System
* V Release 4 Programmer's Guide: ANSI C and
* Programming Support Tools", because my copy
* clearly says "The first 'namesz' bytes in 'name'
* contain a *null-terminated* [emphasis mine]
* character representation of the entry's owner
* or originator", but the 2.0.36 kernel code
* doesn't include the terminating null in the
* name....
*/
if ((namesz == 4 && strncmp((char *)&nbuf[noff], "CORE", 4) == 0) ||
(namesz == 5 && strcmp((char *)&nbuf[noff], "CORE") == 0)) {
os_style = OS_STYLE_SVR4;
}
if ((namesz == 8 && strcmp((char *)&nbuf[noff], "FreeBSD") == 0)) {
os_style = OS_STYLE_FREEBSD;
}
if ((namesz >= 11 && strncmp((char *)&nbuf[noff], "NetBSD-CORE", 11)
== 0)) {
os_style = OS_STYLE_NETBSD;
}
#ifdef ELFCORE
if ((*flags & FLAGS_DID_CORE) != 0)
return size;
if (os_style != -1 && (*flags & FLAGS_DID_CORE_STYLE) == 0) {
if (file_printf(ms, ", %s-style", os_style_names[os_style])
== -1)
return size;
*flags |= FLAGS_DID_CORE_STYLE;
}
switch (os_style) {
case OS_STYLE_NETBSD:
if (xnh_type == NT_NETBSD_CORE_PROCINFO) {
uint32_t signo;
/*
* Extract the program name. It is at
* offset 0x7c, and is up to 32-bytes,
* including the terminating NUL.
*/
if (file_printf(ms, ", from '%.31s'",
&nbuf[doff + 0x7c]) == -1)
return size;
/*
* Extract the signal number. It is at
* offset 0x08.
*/
(void)memcpy(&signo, &nbuf[doff + 0x08],
sizeof(signo));
if (file_printf(ms, " (signal %u)",
elf_getu32(swap, signo)) == -1)
return size;
*flags |= FLAGS_DID_CORE;
return size;
}
break;
default:
if (xnh_type == NT_PRPSINFO && *flags & FLAGS_IS_CORE) {
size_t i, j;
unsigned char c;
/*
* Extract the program name. We assume
* it to be 16 characters (that's what it
* is in SunOS 5.x and Linux).
*
* Unfortunately, it's at a different offset
* in various OSes, so try multiple offsets.
* If the characters aren't all printable,
* reject it.
*/
for (i = 0; i < NOFFSETS; i++) {
unsigned char *cname, *cp;
size_t reloffset = prpsoffsets(i);
size_t noffset = doff + reloffset;
size_t k;
for (j = 0; j < 16; j++, noffset++,
reloffset++) {
/*
* Make sure we're not past
* the end of the buffer; if
* we are, just give up.
*/
if (noffset >= size)
goto tryanother;
/*
* Make sure we're not past
* the end of the contents;
* if we are, this obviously
* isn't the right offset.
*/
if (reloffset >= descsz)
goto tryanother;
c = nbuf[noffset];
if (c == '\0') {
/*
* A '\0' at the
* beginning is
* obviously wrong.
* Any other '\0'
* means we're done.
*/
if (j == 0)
goto tryanother;
else
break;
} else {
/*
* A nonprintable
* character is also
* wrong.
*/
if (!isprint(c) || isquote(c))
goto tryanother;
}
}
/*
* Well, that worked.
*/
/*
* Try next offsets, in case this match is
* in the middle of a string.
*/
for (k = i + 1 ; k < NOFFSETS ; k++) {
size_t no;
int adjust = 1;
if (prpsoffsets(k) >= prpsoffsets(i))
continue;
for (no = doff + prpsoffsets(k);
no < doff + prpsoffsets(i); no++)
adjust = adjust
&& isprint(nbuf[no]);
if (adjust)
i = k;
}
cname = (unsigned char *)
&nbuf[doff + prpsoffsets(i)];
for (cp = cname; *cp && isprint(*cp); cp++)
continue;
/*
* Linux apparently appends a space at the end
* of the command line: remove it.
*/
while (cp > cname && isspace(cp[-1]))
cp--;
if (file_printf(ms, ", from '%.*s'",
(int)(cp - cname), cname) == -1)
return size;
*flags |= FLAGS_DID_CORE;
return size;
tryanother:
;
}
}
break;
}
#endif
return offset;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399', 'CWE-284'], 'message': '- limit the number of program and section header number of sections to be
processed to avoid excessive processing time.
- if a bad note is found, return 0 to stop processing immediately.'</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: file_tryelf(struct magic_set *ms, int fd, const unsigned char *buf,
size_t nbytes)
{
union {
int32_t l;
char c[sizeof (int32_t)];
} u;
int clazz;
int swap;
struct stat st;
off_t fsize;
int flags = 0;
Elf32_Ehdr elf32hdr;
Elf64_Ehdr elf64hdr;
uint16_t type;
if (ms->flags & (MAGIC_MIME|MAGIC_APPLE))
return 0;
/*
* ELF executables have multiple section headers in arbitrary
* file locations and thus file(1) cannot determine it from easily.
* Instead we traverse thru all section headers until a symbol table
* one is found or else the binary is stripped.
* Return immediately if it's not ELF (so we avoid pipe2file unless needed).
*/
if (buf[EI_MAG0] != ELFMAG0
|| (buf[EI_MAG1] != ELFMAG1 && buf[EI_MAG1] != OLFMAG1)
|| buf[EI_MAG2] != ELFMAG2 || buf[EI_MAG3] != ELFMAG3)
return 0;
/*
* If we cannot seek, it must be a pipe, socket or fifo.
*/
if((lseek(fd, (off_t)0, SEEK_SET) == (off_t)-1) && (errno == ESPIPE))
fd = file_pipe2file(ms, fd, buf, nbytes);
if (fstat(fd, &st) == -1) {
file_badread(ms);
return -1;
}
fsize = st.st_size;
clazz = buf[EI_CLASS];
switch (clazz) {
case ELFCLASS32:
#undef elf_getu
#define elf_getu(a, b) elf_getu32(a, b)
#undef elfhdr
#define elfhdr elf32hdr
#include "elfclass.h"
case ELFCLASS64:
#undef elf_getu
#define elf_getu(a, b) elf_getu64(a, b)
#undef elfhdr
#define elfhdr elf64hdr
#include "elfclass.h"
default:
if (file_printf(ms, ", unknown class %d", clazz) == -1)
return -1;
break;
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399', 'CWE-284'], 'message': '- limit the number of program and section header number of sections to be
processed to avoid excessive processing time.
- if a bad note is found, return 0 to stop processing immediately.'</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:
private int
mget(struct magic_set *ms, const unsigned char *s, struct magic *m,
size_t nbytes, size_t o, unsigned int cont_level, int mode, int text,
int flip, int recursion_level, int *printed_something,
int *need_separator, int *returnval)
{
uint32_t offset = ms->offset;
uint32_t lhs;
file_pushbuf_t *pb;
int rv, oneed_separator, in_type;
char *rbuf;
union VALUETYPE *p = &ms->ms_value;
struct mlist ml;
if (recursion_level >= MAX_RECURSION_LEVEL) {
file_error(ms, 0, "recursion nesting exceeded");
return -1;
}
if (mcopy(ms, p, m->type, m->flag & INDIR, s, (uint32_t)(offset + o),
(uint32_t)nbytes, m) == -1)
return -1;
if ((ms->flags & MAGIC_DEBUG) != 0) {
fprintf(stderr, "mget(type=%d, flag=%x, offset=%u, o=%"
SIZE_T_FORMAT "u, " "nbytes=%" SIZE_T_FORMAT "u)\n",
m->type, m->flag, offset, o, nbytes);
mdebug(offset, (char *)(void *)p, sizeof(union VALUETYPE));
#ifndef COMPILE_ONLY
file_mdump(m);
#endif
}
if (m->flag & INDIR) {
int off = m->in_offset;
if (m->in_op & FILE_OPINDIRECT) {
const union VALUETYPE *q = CAST(const union VALUETYPE *,
((const void *)(s + offset + off)));
switch (cvt_flip(m->in_type, flip)) {
case FILE_BYTE:
off = q->b;
break;
case FILE_SHORT:
off = q->h;
break;
case FILE_BESHORT:
off = (short)((q->hs[0]<<8)|(q->hs[1]));
break;
case FILE_LESHORT:
off = (short)((q->hs[1]<<8)|(q->hs[0]));
break;
case FILE_LONG:
off = q->l;
break;
case FILE_BELONG:
case FILE_BEID3:
off = (int32_t)((q->hl[0]<<24)|(q->hl[1]<<16)|
(q->hl[2]<<8)|(q->hl[3]));
break;
case FILE_LEID3:
case FILE_LELONG:
off = (int32_t)((q->hl[3]<<24)|(q->hl[2]<<16)|
(q->hl[1]<<8)|(q->hl[0]));
break;
case FILE_MELONG:
off = (int32_t)((q->hl[1]<<24)|(q->hl[0]<<16)|
(q->hl[3]<<8)|(q->hl[2]));
break;
}
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect offs=%u\n", off);
}
switch (in_type = cvt_flip(m->in_type, flip)) {
case FILE_BYTE:
if (OFFSET_OOB(nbytes, offset, 1))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->b & off;
break;
case FILE_OPOR:
offset = p->b | off;
break;
case FILE_OPXOR:
offset = p->b ^ off;
break;
case FILE_OPADD:
offset = p->b + off;
break;
case FILE_OPMINUS:
offset = p->b - off;
break;
case FILE_OPMULTIPLY:
offset = p->b * off;
break;
case FILE_OPDIVIDE:
offset = p->b / off;
break;
case FILE_OPMODULO:
offset = p->b % off;
break;
}
} else
offset = p->b;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_BESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
lhs = (p->hs[0] << 8) | p->hs[1];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
lhs = (p->hs[1] << 8) | p->hs[0];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_SHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->h & off;
break;
case FILE_OPOR:
offset = p->h | off;
break;
case FILE_OPXOR:
offset = p->h ^ off;
break;
case FILE_OPADD:
offset = p->h + off;
break;
case FILE_OPMINUS:
offset = p->h - off;
break;
case FILE_OPMULTIPLY:
offset = p->h * off;
break;
case FILE_OPDIVIDE:
offset = p->h / off;
break;
case FILE_OPMODULO:
offset = p->h % off;
break;
}
}
else
offset = p->h;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_BELONG:
case FILE_BEID3:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[0] << 24) | (p->hl[1] << 16) |
(p->hl[2] << 8) | p->hl[3];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LELONG:
case FILE_LEID3:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[3] << 24) | (p->hl[2] << 16) |
(p->hl[1] << 8) | p->hl[0];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_MELONG:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[1] << 24) | (p->hl[0] << 16) |
(p->hl[3] << 8) | p->hl[2];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LONG:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->l & off;
break;
case FILE_OPOR:
offset = p->l | off;
break;
case FILE_OPXOR:
offset = p->l ^ off;
break;
case FILE_OPADD:
offset = p->l + off;
break;
case FILE_OPMINUS:
offset = p->l - off;
break;
case FILE_OPMULTIPLY:
offset = p->l * off;
break;
case FILE_OPDIVIDE:
offset = p->l / off;
break;
case FILE_OPMODULO:
offset = p->l % off;
break;
}
} else
offset = p->l;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
default:
break;
}
switch (in_type) {
case FILE_LEID3:
case FILE_BEID3:
offset = ((((offset >> 0) & 0x7f) << 0) |
(((offset >> 8) & 0x7f) << 7) |
(((offset >> 16) & 0x7f) << 14) |
(((offset >> 24) & 0x7f) << 21)) + 10;
break;
default:
break;
}
if (m->flag & INDIROFFADD) {
offset += ms->c.li[cont_level-1].off;
if (offset == 0) {
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr,
"indirect *zero* offset\n");
return 0;
}
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect +offs=%u\n", offset);
}
if (mcopy(ms, p, m->type, 0, s, offset, nbytes, m) == -1)
return -1;
ms->offset = offset;
if ((ms->flags & MAGIC_DEBUG) != 0) {
mdebug(offset, (char *)(void *)p,
sizeof(union VALUETYPE));
#ifndef COMPILE_ONLY
file_mdump(m);
#endif
}
}
/* Verify we have enough data to match magic type */
switch (m->type) {
case FILE_BYTE:
if (OFFSET_OOB(nbytes, offset, 1))
return 0;
break;
case FILE_SHORT:
case FILE_BESHORT:
case FILE_LESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
break;
case FILE_LONG:
case FILE_BELONG:
case FILE_LELONG:
case FILE_MELONG:
case FILE_DATE:
case FILE_BEDATE:
case FILE_LEDATE:
case FILE_MEDATE:
case FILE_LDATE:
case FILE_BELDATE:
case FILE_LELDATE:
case FILE_MELDATE:
case FILE_FLOAT:
case FILE_BEFLOAT:
case FILE_LEFLOAT:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
break;
case FILE_DOUBLE:
case FILE_BEDOUBLE:
case FILE_LEDOUBLE:
if (OFFSET_OOB(nbytes, offset, 8))
return 0;
break;
case FILE_STRING:
case FILE_PSTRING:
case FILE_SEARCH:
if (OFFSET_OOB(nbytes, offset, m->vallen))
return 0;
break;
case FILE_REGEX:
if (nbytes < offset)
return 0;
break;
case FILE_INDIRECT:
if (offset == 0)
return 0;
if (nbytes < offset)
return 0;
if ((pb = file_push_buffer(ms)) == NULL)
return -1;
rv = file_softmagic(ms, s + offset, nbytes - offset,
recursion_level, BINTEST, text);
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect @offs=%u[%d]\n", offset, rv);
rbuf = file_pop_buffer(ms, pb);
if (rbuf == NULL)
return -1;
if (rv == 1) {
if ((ms->flags & (MAGIC_MIME|MAGIC_APPLE)) == 0 &&
file_printf(ms, F(ms, m, "%u"), offset) == -1) {
free(rbuf);
return -1;
}
if (file_printf(ms, "%s", rbuf) == -1) {
free(rbuf);
return -1;
}
}
free(rbuf);
return rv;
case FILE_USE:
if (nbytes < offset)
return 0;
rbuf = m->value.s;
if (*rbuf == '^') {
rbuf++;
flip = !flip;
}
if (file_magicfind(ms, rbuf, &ml) == -1) {
file_error(ms, 0, "cannot find entry `%s'", rbuf);
return -1;
}
oneed_separator = *need_separator;
if (m->flag & NOSPACE)
*need_separator = 0;
rv = match(ms, ml.magic, ml.nmagic, s, nbytes, offset + o,
mode, text, flip, recursion_level, printed_something,
need_separator, returnval);
if (rv != 1)
*need_separator = oneed_separator;
return rv;
case FILE_NAME:
if (file_printf(ms, "%s", m->desc) == -1)
return -1;
return 1;
case FILE_DEFAULT: /* nothing to check */
case FILE_CLEAR:
default:
break;
}
if (!mconvert(ms, m, flip))
return 0; ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'bump recursion to 15, and allow it to be set from the command line.'</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: match(struct magic_set *ms, struct magic *magic, uint32_t nmagic,
const unsigned char *s, size_t nbytes, size_t offset, int mode, int text,
int flip, int recursion_level, int *printed_something, int *need_separator,
int *returnval)
{
uint32_t magindex = 0;
unsigned int cont_level = 0;
int returnvalv = 0, e; /* if a match is found it is set to 1*/
int firstline = 1; /* a flag to print X\n X\n- X */
int print = (ms->flags & (MAGIC_MIME|MAGIC_APPLE)) == 0;
if (returnval == NULL)
returnval = &returnvalv;
if (file_check_mem(ms, cont_level) == -1)
return -1;
for (magindex = 0; magindex < nmagic; magindex++) {
int flush = 0;
struct magic *m = &magic[magindex];
if (m->type != FILE_NAME)
if ((IS_STRING(m->type) &&
#define FLT (STRING_BINTEST | STRING_TEXTTEST)
((text && (m->str_flags & FLT) == STRING_BINTEST) ||
(!text && (m->str_flags & FLT) == STRING_TEXTTEST))) ||
(m->flag & mode) != mode) {
/* Skip sub-tests */
while (magindex + 1 < nmagic &&
magic[magindex + 1].cont_level != 0 &&
++magindex)
continue;
continue; /* Skip to next top-level test*/
}
ms->offset = m->offset;
ms->line = m->lineno;
/* if main entry matches, print it... */
switch (mget(ms, s, m, nbytes, offset, cont_level, mode, text,
flip, recursion_level + 1, printed_something,
need_separator, returnval)) {
case -1:
return -1;
case 0:
flush = m->reln != '!';
break;
default:
if (m->type == FILE_INDIRECT)
*returnval = 1;
switch (magiccheck(ms, m)) {
case -1:
return -1;
case 0:
flush++;
break;
default:
flush = 0;
break;
}
break;
}
if (flush) {
/*
* main entry didn't match,
* flush its continuations
*/
while (magindex < nmagic - 1 &&
magic[magindex + 1].cont_level != 0)
magindex++;
continue;
}
if ((e = handle_annotation(ms, m)) != 0) {
*need_separator = 1;
*printed_something = 1;
*returnval = 1;
return e;
}
/*
* If we are going to print something, we'll need to print
* a blank before we print something else.
*/
if (*m->desc) {
*need_separator = 1;
*printed_something = 1;
if (print_sep(ms, firstline) == -1)
return -1;
}
if (print && mprint(ms, m) == -1)
return -1;
ms->c.li[cont_level].off = moffset(ms, m);
/* and any continuations that match */
if (file_check_mem(ms, ++cont_level) == -1)
return -1;
while (magindex + 1 < nmagic &&
magic[magindex + 1].cont_level != 0) {
m = &magic[++magindex];
ms->line = m->lineno; /* for messages */
if (cont_level < m->cont_level)
continue;
if (cont_level > m->cont_level) {
/*
* We're at the end of the level
* "cont_level" continuations.
*/
cont_level = m->cont_level;
}
ms->offset = m->offset;
if (m->flag & OFFADD) {
ms->offset +=
ms->c.li[cont_level - 1].off;
}
#ifdef ENABLE_CONDITIONALS
if (m->cond == COND_ELSE ||
m->cond == COND_ELIF) {
if (ms->c.li[cont_level].last_match == 1)
continue;
}
#endif
switch (mget(ms, s, m, nbytes, offset, cont_level, mode,
text, flip, recursion_level + 1, printed_something,
need_separator, returnval)) {
case -1:
return -1;
case 0:
if (m->reln != '!')
continue;
flush = 1;
break;
default:
if (m->type == FILE_INDIRECT)
*returnval = 1;
flush = 0;
break;
}
switch (flush ? 1 : magiccheck(ms, m)) {
case -1:
return -1;
case 0:
#ifdef ENABLE_CONDITIONALS
ms->c.li[cont_level].last_match = 0;
#endif
break;
default:
#ifdef ENABLE_CONDITIONALS
ms->c.li[cont_level].last_match = 1;
#endif
if (m->type == FILE_CLEAR)
ms->c.li[cont_level].got_match = 0;
else if (ms->c.li[cont_level].got_match) {
if (m->type == FILE_DEFAULT)
break;
} else
ms->c.li[cont_level].got_match = 1;
if ((e = handle_annotation(ms, m)) != 0) {
*need_separator = 1;
*printed_something = 1;
*returnval = 1;
return e;
}
/*
* If we are going to print something,
* make sure that we have a separator first.
*/
if (*m->desc) {
if (!*printed_something) {
*printed_something = 1;
if (print_sep(ms, firstline)
== -1)
return -1;
}
}
/*
* This continuation matched. Print
* its message, with a blank before it
* if the previous item printed and
* this item isn't empty.
*/
/* space if previous printed */
if (*need_separator
&& ((m->flag & NOSPACE) == 0)
&& *m->desc) {
if (print &&
file_printf(ms, " ") == -1)
return -1;
*need_separator = 0;
}
if (print && mprint(ms, m) == -1)
return -1;
ms->c.li[cont_level].off = moffset(ms, m);
if (*m->desc)
*need_separator = 1;
/*
* If we see any continuations
* at a higher level,
* process them.
*/
if (file_check_mem(ms, ++cont_level) == -1)
return -1;
break;
}
}
if (*printed_something) {
firstline = 0;
if (print)
*returnval = 1;
}
if ((ms->flags & MAGIC_CONTINUE) == 0 && *printed_something) {
return *returnval; /* don't keep searching */
}
}
return *returnval; /* This is hit if -k is set or there is no match */
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'bump recursion to 15, and allow it to be set from the command line.'</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:
private int
mget(struct magic_set *ms, const unsigned char *s, struct magic *m,
size_t nbytes, size_t o, unsigned int cont_level, int mode, int text,
int flip, uint16_t indir_level, uint16_t *name_count,
int *printed_something, int *need_separator, int *returnval)
{
uint32_t offset = ms->offset;
uint32_t lhs;
file_pushbuf_t *pb;
int rv, oneed_separator, in_type;
char *rbuf;
union VALUETYPE *p = &ms->ms_value;
struct mlist ml;
if (indir_level >= ms->indir_max) {
file_error(ms, 0, "indirect recursion nesting (%hu) exceeded",
indir_level);
return -1;
}
if (*name_count >= ms->name_max) {
file_error(ms, 0, "name use count (%hu) exceeded",
*name_count);
return -1;
}
if (mcopy(ms, p, m->type, m->flag & INDIR, s, (uint32_t)(offset + o),
(uint32_t)nbytes, m) == -1)
return -1;
if ((ms->flags & MAGIC_DEBUG) != 0) {
fprintf(stderr, "mget(type=%d, flag=%x, offset=%u, o=%"
SIZE_T_FORMAT "u, " "nbytes=%" SIZE_T_FORMAT
"u, il=%hu, nc=%hu)\n",
m->type, m->flag, offset, o, nbytes,
indir_level, *name_count);
mdebug(offset, (char *)(void *)p, sizeof(union VALUETYPE));
#ifndef COMPILE_ONLY
file_mdump(m);
#endif
}
if (m->flag & INDIR) {
int off = m->in_offset;
if (m->in_op & FILE_OPINDIRECT) {
const union VALUETYPE *q = CAST(const union VALUETYPE *,
((const void *)(s + offset + off)));
switch (cvt_flip(m->in_type, flip)) {
case FILE_BYTE:
off = q->b;
break;
case FILE_SHORT:
off = q->h;
break;
case FILE_BESHORT:
off = (short)((q->hs[0]<<8)|(q->hs[1]));
break;
case FILE_LESHORT:
off = (short)((q->hs[1]<<8)|(q->hs[0]));
break;
case FILE_LONG:
off = q->l;
break;
case FILE_BELONG:
case FILE_BEID3:
off = (int32_t)((q->hl[0]<<24)|(q->hl[1]<<16)|
(q->hl[2]<<8)|(q->hl[3]));
break;
case FILE_LEID3:
case FILE_LELONG:
off = (int32_t)((q->hl[3]<<24)|(q->hl[2]<<16)|
(q->hl[1]<<8)|(q->hl[0]));
break;
case FILE_MELONG:
off = (int32_t)((q->hl[1]<<24)|(q->hl[0]<<16)|
(q->hl[3]<<8)|(q->hl[2]));
break;
}
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect offs=%u\n", off);
}
switch (in_type = cvt_flip(m->in_type, flip)) {
case FILE_BYTE:
if (OFFSET_OOB(nbytes, offset, 1))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->b & off;
break;
case FILE_OPOR:
offset = p->b | off;
break;
case FILE_OPXOR:
offset = p->b ^ off;
break;
case FILE_OPADD:
offset = p->b + off;
break;
case FILE_OPMINUS:
offset = p->b - off;
break;
case FILE_OPMULTIPLY:
offset = p->b * off;
break;
case FILE_OPDIVIDE:
offset = p->b / off;
break;
case FILE_OPMODULO:
offset = p->b % off;
break;
}
} else
offset = p->b;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_BESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
lhs = (p->hs[0] << 8) | p->hs[1];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
lhs = (p->hs[1] << 8) | p->hs[0];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_SHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->h & off;
break;
case FILE_OPOR:
offset = p->h | off;
break;
case FILE_OPXOR:
offset = p->h ^ off;
break;
case FILE_OPADD:
offset = p->h + off;
break;
case FILE_OPMINUS:
offset = p->h - off;
break;
case FILE_OPMULTIPLY:
offset = p->h * off;
break;
case FILE_OPDIVIDE:
offset = p->h / off;
break;
case FILE_OPMODULO:
offset = p->h % off;
break;
}
}
else
offset = p->h;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_BELONG:
case FILE_BEID3:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[0] << 24) | (p->hl[1] << 16) |
(p->hl[2] << 8) | p->hl[3];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LELONG:
case FILE_LEID3:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[3] << 24) | (p->hl[2] << 16) |
(p->hl[1] << 8) | p->hl[0];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_MELONG:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[1] << 24) | (p->hl[0] << 16) |
(p->hl[3] << 8) | p->hl[2];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LONG:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->l & off;
break;
case FILE_OPOR:
offset = p->l | off;
break;
case FILE_OPXOR:
offset = p->l ^ off;
break;
case FILE_OPADD:
offset = p->l + off;
break;
case FILE_OPMINUS:
offset = p->l - off;
break;
case FILE_OPMULTIPLY:
offset = p->l * off;
break;
case FILE_OPDIVIDE:
offset = p->l / off;
break;
case FILE_OPMODULO:
offset = p->l % off;
break;
}
} else
offset = p->l;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
default:
break;
}
switch (in_type) {
case FILE_LEID3:
case FILE_BEID3:
offset = ((((offset >> 0) & 0x7f) << 0) |
(((offset >> 8) & 0x7f) << 7) |
(((offset >> 16) & 0x7f) << 14) |
(((offset >> 24) & 0x7f) << 21)) + 10;
break;
default:
break;
}
if (m->flag & INDIROFFADD) {
offset += ms->c.li[cont_level-1].off;
if (offset == 0) {
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr,
"indirect *zero* offset\n");
return 0;
}
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect +offs=%u\n", offset);
}
if (mcopy(ms, p, m->type, 0, s, offset, nbytes, m) == -1)
return -1;
ms->offset = offset;
if ((ms->flags & MAGIC_DEBUG) != 0) {
mdebug(offset, (char *)(void *)p,
sizeof(union VALUETYPE));
#ifndef COMPILE_ONLY
file_mdump(m);
#endif
}
}
/* Verify we have enough data to match magic type */
switch (m->type) {
case FILE_BYTE:
if (OFFSET_OOB(nbytes, offset, 1))
return 0;
break;
case FILE_SHORT:
case FILE_BESHORT:
case FILE_LESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
break;
case FILE_LONG:
case FILE_BELONG:
case FILE_LELONG:
case FILE_MELONG:
case FILE_DATE:
case FILE_BEDATE:
case FILE_LEDATE:
case FILE_MEDATE:
case FILE_LDATE:
case FILE_BELDATE:
case FILE_LELDATE:
case FILE_MELDATE:
case FILE_FLOAT:
case FILE_BEFLOAT:
case FILE_LEFLOAT:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
break;
case FILE_DOUBLE:
case FILE_BEDOUBLE:
case FILE_LEDOUBLE:
if (OFFSET_OOB(nbytes, offset, 8))
return 0;
break;
case FILE_STRING:
case FILE_PSTRING:
case FILE_SEARCH:
if (OFFSET_OOB(nbytes, offset, m->vallen))
return 0;
break;
case FILE_REGEX:
if (nbytes < offset)
return 0;
break;
case FILE_INDIRECT:
if (offset == 0)
return 0;
if (nbytes < offset)
return 0;
if ((pb = file_push_buffer(ms)) == NULL)
return -1;
rv = file_softmagic(ms, s + offset, nbytes - offset,
indir_level + 1, name_count, BINTEST, text);
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect @offs=%u[%d]\n", offset, rv);
rbuf = file_pop_buffer(ms, pb);
if (rbuf == NULL)
return -1;
if (rv == 1) {
if ((ms->flags & (MAGIC_MIME|MAGIC_APPLE)) == 0 &&
file_printf(ms, F(ms, m, "%u"), offset) == -1) {
free(rbuf);
return -1;
}
if (file_printf(ms, "%s", rbuf) == -1) {
free(rbuf);
return -1;
}
}
free(rbuf);
return rv;
case FILE_USE:
if (nbytes < offset)
return 0;
rbuf = m->value.s;
if (*rbuf == '^') {
rbuf++;
flip = !flip;
}
if (file_magicfind(ms, rbuf, &ml) == -1) {
file_error(ms, 0, "cannot find entry `%s'", rbuf);
return -1;
}
(*name_count)++;
oneed_separator = *need_separator;
if (m->flag & NOSPACE)
*need_separator = 0;
rv = match(ms, ml.magic, ml.nmagic, s, nbytes, offset + o,
mode, text, flip, indir_level, name_count,
printed_something, need_separator, returnval);
if (rv != 1)
*need_separator = oneed_separator;
return rv;
case FILE_NAME:
if (file_printf(ms, "%s", m->desc) == -1)
return -1;
return 1;
case FILE_DEFAULT: /* nothing to check */
case FILE_CLEAR:
default:
break;
}
if (!mconvert(ms, m, flip))
return 0; ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': 'Don't bail if there was no error, buf could have been NULL on entry.'</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 regset_tls_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
const struct user_desc *info;
if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
(pos % sizeof(struct user_desc)) != 0 ||
(count % sizeof(struct user_desc)) != 0)
return -EINVAL;
if (kbuf)
info = kbuf;
else if (__copy_from_user(infobuf, ubuf, count))
return -EFAULT;
else
info = infobuf;
set_tls_desc(target,
GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
info, count / sizeof(struct user_desc));
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-284', 'CWE-264'], 'message': 'x86/tls: Validate TLS entries to protect espfix
Installing a 16-bit RW data segment into the GDT defeats espfix.
AFAICT this will not affect glibc, Wine, or dosemu at all.
Signed-off-by: Andy Lutomirski <[email protected]>
Acked-by: H. Peter Anvin <[email protected]>
Cc: [email protected]
Cc: Konrad Rzeszutek Wilk <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: [email protected] <[email protected]>
Cc: Willy Tarreau <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: 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);
assert(iccprof);
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) {
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-119'], 'message': 'CVE-2014-8138'</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: krb5_encode_krbsecretkey(krb5_key_data *key_data_in, int n_key_data,
krb5_kvno mkvno) {
struct berval **ret = NULL;
int currkvno;
int num_versions = 1;
int i, j, last;
krb5_error_code err = 0;
krb5_key_data *key_data;
if (n_key_data <= 0)
return NULL;
/* Make a shallow copy of the key data so we can alter it. */
key_data = k5calloc(n_key_data, sizeof(*key_data), &err);
if (key_data_in == NULL)
goto cleanup;
memcpy(key_data, key_data_in, n_key_data * sizeof(*key_data));
/* Unpatched krb5 1.11 and 1.12 cannot decode KrbKey sequences with no salt
* field. For compatibility, always encode a salt field. */
for (i = 0; i < n_key_data; i++) {
if (key_data[i].key_data_ver == 1) {
key_data[i].key_data_ver = 2;
key_data[i].key_data_type[1] = KRB5_KDB_SALTTYPE_NORMAL;
key_data[i].key_data_length[1] = 0;
key_data[i].key_data_contents[1] = NULL;
}
}
/* Find the number of key versions */
for (i = 0; i < n_key_data - 1; i++)
if (key_data[i].key_data_kvno != key_data[i + 1].key_data_kvno)
num_versions++;
ret = (struct berval **) calloc (num_versions + 1, sizeof (struct berval *));
if (ret == NULL) {
err = ENOMEM;
goto cleanup;
}
for (i = 0, last = 0, j = 0, currkvno = key_data[0].key_data_kvno; i < n_key_data; i++) {
krb5_data *code;
if (i == n_key_data - 1 || key_data[i + 1].key_data_kvno != currkvno) {
ret[j] = k5alloc(sizeof(struct berval), &err);
if (ret[j] == NULL)
goto cleanup;
err = asn1_encode_sequence_of_keys(key_data + last,
(krb5_int16)i - last + 1,
mkvno, &code);
if (err)
goto cleanup;
/*CHECK_NULL(ret[j]); */
ret[j]->bv_len = code->length;
ret[j]->bv_val = code->data;
free(code);
j++;
last = i + 1;
if (i < n_key_data - 1)
currkvno = key_data[i + 1].key_data_kvno;
}
}
ret[num_versions] = NULL;
cleanup:
free(key_data);
if (err != 0) {
if (ret != NULL) {
for (i = 0; i <= num_versions; i++)
if (ret[i] != NULL)
free (ret[i]);
free (ret);
ret = NULL;
}
}
return ret;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-703'], 'message': 'Support keyless principals in LDAP [CVE-2014-5354]
Operations like "kadmin -q 'addprinc -nokey foo'" or
"kadmin -q 'purgekeys -all foo'" result in principal entries with
no keys present, so krb5_encode_krbsecretkey() would just return
NULL, which then got unconditionally dereferenced in
krb5_add_ber_mem_ldap_mod().
Apply some fixes to krb5_encode_krbsecretkey() to handle zero-key
principals better, correct the test for an allocation failure, and
slightly restructure the cleanup handler to be shorter and more
appropriate for the usage. Once it no longer short-circuits when
n_key_data is zero, it will produce an array of length two with both
entries NULL, which is treated as an empty list by the LDAP library,
the correct behavior for a keyless principal.
However, attributes with empty values are only handled by the LDAP
library for Modify operations, not Add operations (which only get
a sequence of Attribute, with no operation field). Therefore, only
add an empty krbprincipalkey to the modlist when we will be performing a
Modify, and not when we will be performing an Add, which is conditional
on the (misspelled) create_standalone_prinicipal boolean.
CVE-2014-5354:
In MIT krb5, when kadmind is configured to use LDAP for the KDC
database, an authenticated remote attacker can cause a NULL
dereference by inserting into the database a principal entry which
contains no long-term keys.
In order for the LDAP KDC backend to translate a principal entry
from the database abstraction layer into the form expected by the
LDAP schema, the principal's keys are encoded into a
NULL-terminated array of length-value entries to be stored in the
LDAP database. However, the subroutine which produced this array
did not correctly handle the case where no keys were present,
returning NULL instead of an empty array, and the array was
unconditionally dereferenced while adding to the list of LDAP
operations to perform.
Versions of MIT krb5 prior to 1.12 did not expose a way for
principal entries to have no long-term key material, and
therefore are not vulnerable.
CVSSv2 Vector: AV:N/AC:M/Au:S/C:N/I:N/A:P/E:H/RL:OF/RC:C
ticket: 8041 (new)
tags: pullup
target_version: 1.13.1
subject: kadmind with ldap backend crashes when putting keyless entries'</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:
private int
mget(struct magic_set *ms, const unsigned char *s, struct magic *m,
size_t nbytes, size_t o, unsigned int cont_level, int mode, int text,
int flip, int recursion_level, int *printed_something,
int *need_separator, int *returnval)
{
uint32_t soffset, offset = ms->offset;
uint32_t lhs;
int rv, oneed_separator, in_type;
char *sbuf, *rbuf;
union VALUETYPE *p = &ms->ms_value;
struct mlist ml;
if (recursion_level >= 20) {
file_error(ms, 0, "recursion nesting exceeded");
return -1;
}
if (mcopy(ms, p, m->type, m->flag & INDIR, s, (uint32_t)(offset + o),
(uint32_t)nbytes, m) == -1)
return -1;
if ((ms->flags & MAGIC_DEBUG) != 0) {
fprintf(stderr, "mget(type=%d, flag=%x, offset=%u, o=%"
SIZE_T_FORMAT "u, " "nbytes=%" SIZE_T_FORMAT "u)\n",
m->type, m->flag, offset, o, nbytes);
mdebug(offset, (char *)(void *)p, sizeof(union VALUETYPE));
#ifndef COMPILE_ONLY
file_mdump(m);
#endif
}
if (m->flag & INDIR) {
int off = m->in_offset;
if (m->in_op & FILE_OPINDIRECT) {
const union VALUETYPE *q = CAST(const union VALUETYPE *,
((const void *)(s + offset + off)));
switch (cvt_flip(m->in_type, flip)) {
case FILE_BYTE:
off = q->b;
break;
case FILE_SHORT:
off = q->h;
break;
case FILE_BESHORT:
off = (short)((q->hs[0]<<8)|(q->hs[1]));
break;
case FILE_LESHORT:
off = (short)((q->hs[1]<<8)|(q->hs[0]));
break;
case FILE_LONG:
off = q->l;
break;
case FILE_BELONG:
case FILE_BEID3:
off = (int32_t)((q->hl[0]<<24)|(q->hl[1]<<16)|
(q->hl[2]<<8)|(q->hl[3]));
break;
case FILE_LEID3:
case FILE_LELONG:
off = (int32_t)((q->hl[3]<<24)|(q->hl[2]<<16)|
(q->hl[1]<<8)|(q->hl[0]));
break;
case FILE_MELONG:
off = (int32_t)((q->hl[1]<<24)|(q->hl[0]<<16)|
(q->hl[3]<<8)|(q->hl[2]));
break;
}
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect offs=%u\n", off);
}
switch (in_type = cvt_flip(m->in_type, flip)) {
case FILE_BYTE:
if (OFFSET_OOB(nbytes, offset, 1))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->b & off;
break;
case FILE_OPOR:
offset = p->b | off;
break;
case FILE_OPXOR:
offset = p->b ^ off;
break;
case FILE_OPADD:
offset = p->b + off;
break;
case FILE_OPMINUS:
offset = p->b - off;
break;
case FILE_OPMULTIPLY:
offset = p->b * off;
break;
case FILE_OPDIVIDE:
offset = p->b / off;
break;
case FILE_OPMODULO:
offset = p->b % off;
break;
}
} else
offset = p->b;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_BESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
lhs = (p->hs[0] << 8) | p->hs[1];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
lhs = (p->hs[1] << 8) | p->hs[0];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_SHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->h & off;
break;
case FILE_OPOR:
offset = p->h | off;
break;
case FILE_OPXOR:
offset = p->h ^ off;
break;
case FILE_OPADD:
offset = p->h + off;
break;
case FILE_OPMINUS:
offset = p->h - off;
break;
case FILE_OPMULTIPLY:
offset = p->h * off;
break;
case FILE_OPDIVIDE:
offset = p->h / off;
break;
case FILE_OPMODULO:
offset = p->h % off;
break;
}
}
else
offset = p->h;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_BELONG:
case FILE_BEID3:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[0] << 24) | (p->hl[1] << 16) |
(p->hl[2] << 8) | p->hl[3];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LELONG:
case FILE_LEID3:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[3] << 24) | (p->hl[2] << 16) |
(p->hl[1] << 8) | p->hl[0];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_MELONG:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
lhs = (p->hl[1] << 24) | (p->hl[0] << 16) |
(p->hl[3] << 8) | p->hl[2];
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = lhs & off;
break;
case FILE_OPOR:
offset = lhs | off;
break;
case FILE_OPXOR:
offset = lhs ^ off;
break;
case FILE_OPADD:
offset = lhs + off;
break;
case FILE_OPMINUS:
offset = lhs - off;
break;
case FILE_OPMULTIPLY:
offset = lhs * off;
break;
case FILE_OPDIVIDE:
offset = lhs / off;
break;
case FILE_OPMODULO:
offset = lhs % off;
break;
}
} else
offset = lhs;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
case FILE_LONG:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
if (off) {
switch (m->in_op & FILE_OPS_MASK) {
case FILE_OPAND:
offset = p->l & off;
break;
case FILE_OPOR:
offset = p->l | off;
break;
case FILE_OPXOR:
offset = p->l ^ off;
break;
case FILE_OPADD:
offset = p->l + off;
break;
case FILE_OPMINUS:
offset = p->l - off;
break;
case FILE_OPMULTIPLY:
offset = p->l * off;
break;
case FILE_OPDIVIDE:
offset = p->l / off;
break;
case FILE_OPMODULO:
offset = p->l % off;
break;
}
} else
offset = p->l;
if (m->in_op & FILE_OPINVERSE)
offset = ~offset;
break;
default:
break;
}
switch (in_type) {
case FILE_LEID3:
case FILE_BEID3:
offset = ((((offset >> 0) & 0x7f) << 0) |
(((offset >> 8) & 0x7f) << 7) |
(((offset >> 16) & 0x7f) << 14) |
(((offset >> 24) & 0x7f) << 21)) + 10;
break;
default:
break;
}
if (m->flag & INDIROFFADD) {
offset += ms->c.li[cont_level-1].off;
if (offset == 0) {
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr,
"indirect *zero* offset\n");
return 0;
}
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect +offs=%u\n", offset);
}
if (mcopy(ms, p, m->type, 0, s, offset, nbytes, m) == -1)
return -1;
ms->offset = offset;
if ((ms->flags & MAGIC_DEBUG) != 0) {
mdebug(offset, (char *)(void *)p,
sizeof(union VALUETYPE));
#ifndef COMPILE_ONLY
file_mdump(m);
#endif
}
}
/* Verify we have enough data to match magic type */
switch (m->type) {
case FILE_BYTE:
if (OFFSET_OOB(nbytes, offset, 1))
return 0;
break;
case FILE_SHORT:
case FILE_BESHORT:
case FILE_LESHORT:
if (OFFSET_OOB(nbytes, offset, 2))
return 0;
break;
case FILE_LONG:
case FILE_BELONG:
case FILE_LELONG:
case FILE_MELONG:
case FILE_DATE:
case FILE_BEDATE:
case FILE_LEDATE:
case FILE_MEDATE:
case FILE_LDATE:
case FILE_BELDATE:
case FILE_LELDATE:
case FILE_MELDATE:
case FILE_FLOAT:
case FILE_BEFLOAT:
case FILE_LEFLOAT:
if (OFFSET_OOB(nbytes, offset, 4))
return 0;
break;
case FILE_DOUBLE:
case FILE_BEDOUBLE:
case FILE_LEDOUBLE:
if (OFFSET_OOB(nbytes, offset, 8))
return 0;
break;
case FILE_STRING:
case FILE_PSTRING:
case FILE_SEARCH:
if (OFFSET_OOB(nbytes, offset, m->vallen))
return 0;
break;
case FILE_REGEX:
if (nbytes < offset)
return 0;
break;
case FILE_INDIRECT:
if (offset == 0)
return 0;
if (nbytes < offset)
return 0;
sbuf = ms->o.buf;
soffset = ms->offset;
ms->o.buf = NULL;
ms->offset = 0;
rv = file_softmagic(ms, s + offset, nbytes - offset,
recursion_level, BINTEST, text);
if ((ms->flags & MAGIC_DEBUG) != 0)
fprintf(stderr, "indirect @offs=%u[%d]\n", offset, rv);
rbuf = ms->o.buf;
ms->o.buf = sbuf;
ms->offset = soffset;
if (rv == 1) {
if ((ms->flags & (MAGIC_MIME|MAGIC_APPLE)) == 0 &&
file_printf(ms, F(ms, m, "%u"), offset) == -1) {
free(rbuf);
return -1;
}
if (file_printf(ms, "%s", rbuf) == -1) {
free(rbuf);
return -1;
}
}
free(rbuf);
return rv;
case FILE_USE:
if (nbytes < offset)
return 0;
sbuf = m->value.s;
if (*sbuf == '^') {
sbuf++;
flip = !flip;
}
if (file_magicfind(ms, sbuf, &ml) == -1) {
file_error(ms, 0, "cannot find entry `%s'", sbuf);
return -1;
}
oneed_separator = *need_separator;
if (m->flag & NOSPACE)
*need_separator = 0;
rv = match(ms, ml.magic, ml.nmagic, s, nbytes, offset + o,
mode, text, flip, recursion_level, printed_something,
need_separator, returnval);
if (rv != 1)
*need_separator = oneed_separator;
return rv;
case FILE_NAME:
if (file_printf(ms, "%s", m->desc) == -1)
return -1;
return 1;
case FILE_DEFAULT: /* nothing to check */
case FILE_CLEAR:
default:
break;
}
if (!mconvert(ms, m, flip))
return 0; ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': '- reduce recursion level from 20 to 10 and make a symbolic constant for it.
- pull out the guts of saving and restoring the output buffer into functions
and take care not to overwrite the error message if an error happened.'</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: toomany(struct magic_set *ms, const char *name, uint16_t num)
{
if (file_printf(ms, ", too many %s header sections (%u)", name, num
) == -1)
return -1;
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': '- Add a limit to the number of ELF notes processed (Suggested by Alexander
Cherepanov)
- Restructure ELF note printing so that we don't print the same message
multiple times on repeated notes of the same kind.'</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: file_ms_alloc(int flags)
{
struct magic_set *ms;
size_t i, len;
if ((ms = CAST(struct magic_set *, calloc((size_t)1,
sizeof(struct magic_set)))) == NULL)
return NULL;
if (magic_setflags(ms, flags) == -1) {
errno = EINVAL;
goto free;
}
ms->o.buf = ms->o.pbuf = NULL;
len = (ms->c.len = 10) * sizeof(*ms->c.li);
if ((ms->c.li = CAST(struct level_info *, malloc(len))) == NULL)
goto free;
ms->event_flags = 0;
ms->error = -1;
for (i = 0; i < MAGIC_SETS; i++)
ms->mlist[i] = NULL;
ms->file = "unknown";
ms->line = 0;
ms->indir_max = FILE_INDIR_MAX;
ms->name_max = FILE_NAME_MAX;
ms->elf_shnum_max = FILE_ELF_SHNUM_MAX;
ms->elf_phnum_max = FILE_ELF_PHNUM_MAX;
return ms;
free:
free(ms);
return NULL;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': '- Add a limit to the number of ELF notes processed (Suggested by Alexander
Cherepanov)
- Restructure ELF note printing so that we don't print the same message
multiple times on repeated notes of the same kind.'</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: magic_setparam(struct magic_set *ms, int param, const void *val)
{
switch (param) {
case MAGIC_PARAM_INDIR_MAX:
ms->indir_max = *(const size_t *)val;
return 0;
case MAGIC_PARAM_NAME_MAX:
ms->name_max = *(const size_t *)val;
return 0;
case MAGIC_PARAM_ELF_PHNUM_MAX:
ms->elf_phnum_max = *(const size_t *)val;
return 0;
case MAGIC_PARAM_ELF_SHNUM_MAX:
ms->elf_shnum_max = *(const size_t *)val;
return 0;
default:
errno = EINVAL;
return -1;
}
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': '- Add a limit to the number of ELF notes processed (Suggested by Alexander
Cherepanov)
- Restructure ELF note printing so that we don't print the same message
multiple times on repeated notes of the same kind.'</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: dophn_core(struct magic_set *ms, int clazz, int swap, int fd, off_t off,
int num, size_t size, off_t fsize, int *flags)
{
Elf32_Phdr ph32;
Elf64_Phdr ph64;
size_t offset, len;
unsigned char nbuf[BUFSIZ];
ssize_t bufsize;
if (size != xph_sizeof) {
if (file_printf(ms, ", corrupted program header size") == -1)
return -1;
return 0;
}
/*
* Loop through all the program headers.
*/
for ( ; num; num--) {
if (pread(fd, xph_addr, xph_sizeof, off) < (ssize_t)xph_sizeof) {
file_badread(ms);
return -1;
}
off += size;
if (fsize != SIZE_UNKNOWN && xph_offset > fsize) {
/* Perhaps warn here */
continue;
}
if (xph_type != PT_NOTE)
continue;
/*
* This is a PT_NOTE section; loop through all the notes
* in the section.
*/
len = xph_filesz < sizeof(nbuf) ? xph_filesz : sizeof(nbuf);
if ((bufsize = pread(fd, nbuf, len, xph_offset)) == -1) {
file_badread(ms);
return -1;
}
offset = 0;
for (;;) {
if (offset >= (size_t)bufsize)
break;
offset = donote(ms, nbuf, offset, (size_t)bufsize,
clazz, swap, 4, flags);
if (offset == 0)
break;
}
}
return 0;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': '- Add a limit to the number of ELF notes processed (Suggested by Alexander
Cherepanov)
- Restructure ELF note printing so that we don't print the same message
multiple times on repeated notes of the same kind.'</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: switch (type) {
#ifdef ELFCORE
case ET_CORE:
phnum = elf_getu16(swap, elfhdr.e_phnum);
if (phnum > ms->elf_phnum_max)
return toomany(ms, "program", phnum);
flags |= FLAGS_IS_CORE;
if (dophn_core(ms, clazz, swap, fd,
(off_t)elf_getu(swap, elfhdr.e_phoff), phnum,
(size_t)elf_getu16(swap, elfhdr.e_phentsize),
fsize, &flags) == -1)
return -1;
break;
#endif
case ET_EXEC:
case ET_DYN:
phnum = elf_getu16(swap, elfhdr.e_phnum);
if (phnum > ms->elf_phnum_max)
return toomany(ms, "program", phnum);
shnum = elf_getu16(swap, elfhdr.e_shnum);
if (shnum > ms->elf_shnum_max)
return toomany(ms, "section", shnum);
if (dophn_exec(ms, clazz, swap, fd,
(off_t)elf_getu(swap, elfhdr.e_phoff), phnum,
(size_t)elf_getu16(swap, elfhdr.e_phentsize),
fsize, &flags, shnum) == -1)
return -1;
/*FALLTHROUGH*/
case ET_REL:
shnum = elf_getu16(swap, elfhdr.e_shnum);
if (shnum > ms->elf_shnum_max)
return toomany(ms, "section", shnum);
if (doshn(ms, clazz, swap, fd,
(off_t)elf_getu(swap, elfhdr.e_shoff), shnum,
(size_t)elf_getu16(swap, elfhdr.e_shentsize),
fsize, &flags, elf_getu16(swap, elfhdr.e_machine),
(int)elf_getu16(swap, elfhdr.e_shstrndx)) == -1)
return -1;
break;
default:
break;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-399'], 'message': '- Add a limit to the number of ELF notes processed (Suggested by Alexander
Cherepanov)
- Restructure ELF note printing so that we don't print the same message
multiple times on repeated notes of the same kind.'</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: psf_fwrite (const void *ptr, sf_count_t bytes, sf_count_t items, SF_PRIVATE *psf)
{ sf_count_t total = 0 ;
ssize_t count ;
if (psf->virtual_io)
return psf->vio.write (ptr, bytes*items, psf->vio_user_data) / bytes ;
items *= bytes ;
/* Do this check after the multiplication above. */
if (items <= 0)
return 0 ;
while (items > 0)
{ /* Break the writes down to a sensible size. */
count = (items > SENSIBLE_SIZE) ? SENSIBLE_SIZE : items ;
count = write (psf->file.filedes, ((const char*) ptr) + total, count) ;
if (count == -1)
{ if (errno == EINTR)
continue ;
psf_log_syserr (psf, errno) ;
break ;
} ;
if (count == 0)
break ;
total += count ;
items -= count ;
} ;
if (psf->is_pipe)
psf->pipeoffset += total ;
return total / bytes ;
} /* psf_fwrite */ ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-369', 'CWE-189'], 'message': 'src/file_io.c : Prevent potential divide-by-zero.
Closes: https://github.com/erikd/libsndfile/issues/92'</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: psf_fwrite (const void *ptr, sf_count_t bytes, sf_count_t items, SF_PRIVATE *psf)
{ sf_count_t total = 0 ;
ssize_t count ;
DWORD dwNumberOfBytesWritten ;
if (psf->virtual_io)
return psf->vio.write (ptr, bytes * items, psf->vio_user_data) / bytes ;
items *= bytes ;
/* Do this check after the multiplication above. */
if (items <= 0)
return 0 ;
while (items > 0)
{ /* Break the writes down to a sensible size. */
count = (items > SENSIBLE_SIZE) ? SENSIBLE_SIZE : (ssize_t) items ;
if (WriteFile (psf->file.handle, ((const char*) ptr) + total, count, &dwNumberOfBytesWritten, 0) == 0)
{ psf_log_syserr (psf, GetLastError ()) ;
break ;
}
else
count = dwNumberOfBytesWritten ;
if (count == 0)
break ;
total += count ;
items -= count ;
} ;
if (psf->is_pipe)
psf->pipeoffset += total ;
return total / bytes ;
} /* psf_fwrite */ ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-369', 'CWE-189'], 'message': 'src/file_io.c : Prevent potential divide-by-zero.
Closes: https://github.com/erikd/libsndfile/issues/92'</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: apprentice_load(struct magic_set *ms, const char *fn, int action)
{
int errs = 0;
uint32_t i, j;
size_t files = 0, maxfiles = 0;
char **filearr = NULL;
struct stat st;
struct magic_map *map;
struct magic_entry_set mset[MAGIC_SETS];
php_stream *dir;
php_stream_dirent d;
TSRMLS_FETCH();
memset(mset, 0, sizeof(mset));
ms->flags |= MAGIC_CHECK; /* Enable checks for parsed files */
if ((map = CAST(struct magic_map *, ecalloc(1, sizeof(*map)))) == NULL)
{
file_oomem(ms, sizeof(*map));
return NULL;
}
/* print silly verbose header for USG compat. */
if (action == FILE_CHECK)
(void)fprintf(stderr, "%s\n", usg_hdr);
/* load directory or file */
/* FIXME: Read file names and sort them to prevent
non-determinism. See Debian bug #488562. */
if (php_sys_stat(fn, &st) == 0 && S_ISDIR(st.st_mode)) {
int mflen;
char mfn[MAXPATHLEN];
dir = php_stream_opendir((char *)fn, REPORT_ERRORS, NULL);
if (!dir) {
errs++;
goto out;
}
while (php_stream_readdir(dir, &d)) {
if ((mflen = snprintf(mfn, sizeof(mfn), "%s/%s", fn, d.d_name)) < 0) {
file_oomem(ms,
strlen(fn) + strlen(d.d_name) + 2);
errs++;
php_stream_closedir(dir);
goto out;
}
if (stat(mfn, &st) == -1 || !S_ISREG(st.st_mode)) {
continue;
}
if (files >= maxfiles) {
size_t mlen;
maxfiles = (maxfiles + 1) * 2;
mlen = maxfiles * sizeof(*filearr);
if ((filearr = CAST(char **,
erealloc(filearr, mlen))) == NULL) {
file_oomem(ms, mlen);
efree(mfn);
php_stream_closedir(dir);
errs++;
goto out;
}
}
filearr[files++] = estrndup(mfn, (mflen > sizeof(mfn) - 1)? sizeof(mfn) - 1: mflen);
}
php_stream_closedir(dir);
qsort(filearr, files, sizeof(*filearr), cmpstrp);
for (i = 0; i < files; i++) {
load_1(ms, action, filearr[i], &errs, mset);
efree(filearr[i]);
}
efree(filearr);
} else
load_1(ms, action, fn, &errs, mset);
if (errs)
goto out;
for (j = 0; j < MAGIC_SETS; j++) {
/* Set types of tests */
for (i = 0; i < mset[j].count; ) {
if (mset[j].me[i].mp->cont_level != 0) {
i++;
continue;
}
i = set_text_binary(ms, mset[j].me, mset[j].count, i);
}
qsort(mset[j].me, mset[j].count, sizeof(*mset[j].me),
apprentice_sort);
/*
* Make sure that any level 0 "default" line is last
* (if one exists).
*/
set_last_default(ms, mset[j].me, mset[j].count);
/* coalesce per file arrays into a single one */
if (coalesce_entries(ms, mset[j].me, mset[j].count,
&map->magic[j], &map->nmagic[j]) == -1) {
errs++;
goto out;
}
}
out:
for (j = 0; j < MAGIC_SETS; j++)
magic_entry_free(mset[j].me, mset[j].count);
if (errs) {
for (j = 0; j < MAGIC_SETS; j++) {
if (map->magic[j])
efree(map->magic[j]);
}
efree(map);
return NULL;
}
return map;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-17'], 'message': 'Fixed bug #68665 (Invalid free)'</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: sd2_parse_rsrc_fork (SF_PRIVATE *psf)
{ SD2_RSRC rsrc ;
int k, marker, error = 0 ;
psf_use_rsrc (psf, SF_TRUE) ;
memset (&rsrc, 0, sizeof (rsrc)) ;
rsrc.rsrc_len = psf_get_filelen (psf) ;
psf_log_printf (psf, "Resource length : %d (0x%04X)\n", rsrc.rsrc_len, rsrc.rsrc_len) ;
if (rsrc.rsrc_len > SIGNED_SIZEOF (psf->header))
{ rsrc.rsrc_data = calloc (1, rsrc.rsrc_len) ;
rsrc.need_to_free_rsrc_data = SF_TRUE ;
}
else
{
rsrc.rsrc_data = psf->header ;
rsrc.need_to_free_rsrc_data = SF_FALSE ;
} ;
/* Read in the whole lot. */
psf_fread (rsrc.rsrc_data, rsrc.rsrc_len, 1, psf) ;
/* Reset the header storage because we have changed to the rsrcdes. */
psf->headindex = psf->headend = rsrc.rsrc_len ;
rsrc.data_offset = read_rsrc_int (&rsrc, 0) ;
rsrc.map_offset = read_rsrc_int (&rsrc, 4) ;
rsrc.data_length = read_rsrc_int (&rsrc, 8) ;
rsrc.map_length = read_rsrc_int (&rsrc, 12) ;
if (rsrc.data_offset == 0x51607 && rsrc.map_offset == 0x20000)
{ psf_log_printf (psf, "Trying offset of 0x52 bytes.\n") ;
rsrc.data_offset = read_rsrc_int (&rsrc, 0x52 + 0) + 0x52 ;
rsrc.map_offset = read_rsrc_int (&rsrc, 0x52 + 4) + 0x52 ;
rsrc.data_length = read_rsrc_int (&rsrc, 0x52 + 8) ;
rsrc.map_length = read_rsrc_int (&rsrc, 0x52 + 12) ;
} ;
psf_log_printf (psf, " data offset : 0x%04X\n map offset : 0x%04X\n"
" data length : 0x%04X\n map length : 0x%04X\n",
rsrc.data_offset, rsrc.map_offset, rsrc.data_length, rsrc.map_length) ;
if (rsrc.data_offset > rsrc.rsrc_len)
{ psf_log_printf (psf, "Error : rsrc.data_offset (%d, 0x%x) > len\n", rsrc.data_offset, rsrc.data_offset) ;
error = SFE_SD2_BAD_DATA_OFFSET ;
goto parse_rsrc_fork_cleanup ;
} ;
if (rsrc.map_offset > rsrc.rsrc_len)
{ psf_log_printf (psf, "Error : rsrc.map_offset > len\n") ;
error = SFE_SD2_BAD_MAP_OFFSET ;
goto parse_rsrc_fork_cleanup ;
} ;
if (rsrc.data_length > rsrc.rsrc_len)
{ psf_log_printf (psf, "Error : rsrc.data_length > len\n") ;
error = SFE_SD2_BAD_DATA_LENGTH ;
goto parse_rsrc_fork_cleanup ;
} ;
if (rsrc.map_length > rsrc.rsrc_len)
{ psf_log_printf (psf, "Error : rsrc.map_length > len\n") ;
error = SFE_SD2_BAD_MAP_LENGTH ;
goto parse_rsrc_fork_cleanup ;
} ;
if (rsrc.data_offset + rsrc.data_length != rsrc.map_offset || rsrc.map_offset + rsrc.map_length != rsrc.rsrc_len)
{ psf_log_printf (psf, "Error : This does not look like a MacOSX resource fork.\n") ;
error = SFE_SD2_BAD_RSRC ;
goto parse_rsrc_fork_cleanup ;
} ;
if (rsrc.map_offset + 28 >= rsrc.rsrc_len)
{ psf_log_printf (psf, "Bad map offset (%d + 28 > %d).\n", rsrc.map_offset, rsrc.rsrc_len) ;
error = SFE_SD2_BAD_RSRC ;
goto parse_rsrc_fork_cleanup ;
} ;
rsrc.string_offset = rsrc.map_offset + read_rsrc_short (&rsrc, rsrc.map_offset + 26) ;
if (rsrc.string_offset > rsrc.rsrc_len)
{ psf_log_printf (psf, "Bad string offset (%d).\n", rsrc.string_offset) ;
error = SFE_SD2_BAD_RSRC ;
goto parse_rsrc_fork_cleanup ;
} ;
rsrc.type_offset = rsrc.map_offset + 30 ;
rsrc.type_count = read_rsrc_short (&rsrc, rsrc.map_offset + 28) + 1 ;
if (rsrc.type_count < 1)
{ psf_log_printf (psf, "Bad type count.\n") ;
error = SFE_SD2_BAD_RSRC ;
goto parse_rsrc_fork_cleanup ;
} ;
rsrc.item_offset = rsrc.type_offset + rsrc.type_count * 8 ;
if (rsrc.item_offset < 0 || rsrc.item_offset > rsrc.rsrc_len)
{ psf_log_printf (psf, "Bad item offset (%d).\n", rsrc.item_offset) ;
error = SFE_SD2_BAD_RSRC ;
goto parse_rsrc_fork_cleanup ;
} ;
rsrc.str_index = -1 ;
for (k = 0 ; k < rsrc.type_count ; k ++)
{ marker = read_rsrc_marker (&rsrc, rsrc.type_offset + k * 8) ;
if (marker == STR_MARKER)
{ rsrc.str_index = k ;
rsrc.str_count = read_rsrc_short (&rsrc, rsrc.type_offset + k * 8 + 4) + 1 ;
error = parse_str_rsrc (psf, &rsrc) ;
goto parse_rsrc_fork_cleanup ;
} ;
} ;
psf_log_printf (psf, "No 'STR ' resource.\n") ;
error = SFE_SD2_BAD_RSRC ;
parse_rsrc_fork_cleanup :
psf_use_rsrc (psf, SF_FALSE) ;
if (rsrc.need_to_free_rsrc_data)
free (rsrc.rsrc_data) ;
return error ;
} /* sd2_parse_rsrc_fork */ ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119', 'CWE-787'], 'message': 'src/sd2.c : Fix two potential buffer read overflows.
Closes: https://github.com/erikd/libsndfile/issues/93'</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: HttpTransact::build_redirect_response(State* s)
{
DebugTxn("http_redirect", "[HttpTransact::build_redirect_response]");
URL *u;
const char *old_host;
int old_host_len;
const char *new_url = NULL;
int new_url_len;
char *to_free = NULL;
char body_language[256], body_type[256];
HTTPStatus status_code = HTTP_STATUS_MOVED_TEMPORARILY;
char *reason_phrase = (char *) (http_hdr_reason_lookup(status_code));
build_response(s, &s->hdr_info.client_response, s->client_info.http_version, status_code, reason_phrase);
//////////////////////////////////////////////////////////
// figure out what new url should be. this little hack //
// inserts expanded hostname into old url in order to //
// get scheme information, then puts the old url back. //
//////////////////////////////////////////////////////////
u = s->hdr_info.client_request.url_get();
old_host = u->host_get(&old_host_len);
u->host_set(s->dns_info.lookup_name, strlen(s->dns_info.lookup_name));
new_url = to_free = u->string_get(&s->arena, &new_url_len);
if (new_url == NULL) {
new_url = "";
}
u->host_set(old_host, old_host_len);
//////////////////////////
// set redirect headers //
//////////////////////////
HTTPHdr *h = &s->hdr_info.client_response;
if (s->txn_conf->insert_response_via_string) {
const char pa[] = "Proxy-agent";
h->value_append(pa, sizeof(pa) - 1, s->http_config_param->proxy_response_via_string,
s->http_config_param->proxy_response_via_string_len);
}
h->value_set(MIME_FIELD_LOCATION, MIME_LEN_LOCATION, new_url, new_url_len);
//////////////////////////
// set descriptive text //
//////////////////////////
s->internal_msg_buffer_index = 0;
s->free_internal_msg_buffer();
s->internal_msg_buffer_fast_allocator_size = -1;
s->internal_msg_buffer = body_factory->fabricate_with_old_api_build_va("redirect#moved_temporarily", s, 8192,
&s->internal_msg_buffer_size,
body_language, sizeof(body_language),
body_type, sizeof(body_type),
"%s <a href=\"%s\">%s</a>. %s.",
"The document you requested is now",
new_url, new_url,
"Please update your documents and bookmarks accordingly", NULL);
h->set_content_length(s->internal_msg_buffer_size);
h->value_set(MIME_FIELD_CONTENT_TYPE, MIME_LEN_CONTENT_TYPE, "text/html", 9);
s->arena.str_free(to_free);
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix the internal buffer sizing. Thanks to Sudheer for helping isolating this bug'</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: HttpTransact::build_error_response(State *s, HTTPStatus status_code, const char *reason_phrase_or_null,
const char *error_body_type, const char *format, ...)
{
va_list ap;
const char *reason_phrase;
char *url_string;
char body_language[256], body_type[256];
if (NULL == error_body_type) {
error_body_type = "default";
}
////////////////////////////////////////////////////////////
// get the url --- remember this is dynamically allocated //
////////////////////////////////////////////////////////////
if (s->hdr_info.client_request.valid()) {
url_string = s->hdr_info.client_request.url_string_get(&s->arena);
} else {
url_string = NULL;
}
// Make sure that if this error occured before we initailzied the state variables that we do now.
initialize_state_variables_from_request(s, &s->hdr_info.client_request);
//////////////////////////////////////////////////////
// If there is a request body, we must disable //
// keep-alive to prevent the body being read as //
// the next header (unless we've already drained //
// which we do for NTLM auth) //
//////////////////////////////////////////////////////
if (status_code == HTTP_STATUS_REQUEST_TIMEOUT ||
s->hdr_info.client_request.get_content_length() != 0 ||
s->client_info.transfer_encoding == HttpTransact::CHUNKED_ENCODING) {
s->client_info.keep_alive = HTTP_NO_KEEPALIVE;
} else {
// We don't have a request body. Since we are
// generating the error, we know we can trust
// the content-length
s->hdr_info.trust_response_cl = true;
}
switch (status_code) {
case HTTP_STATUS_BAD_REQUEST:
SET_VIA_STRING(VIA_CLIENT_REQUEST, VIA_CLIENT_ERROR);
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_HEADER_SYNTAX);
break;
case HTTP_STATUS_BAD_GATEWAY:
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_CONNECTION);
break;
case HTTP_STATUS_GATEWAY_TIMEOUT:
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_TIMEOUT);
break;
case HTTP_STATUS_NOT_FOUND:
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_SERVER);
break;
case HTTP_STATUS_FORBIDDEN:
SET_VIA_STRING(VIA_CLIENT_REQUEST, VIA_CLIENT_ERROR);
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_FORBIDDEN);
break;
case HTTP_STATUS_HTTPVER_NOT_SUPPORTED:
SET_VIA_STRING(VIA_CLIENT_REQUEST, VIA_CLIENT_ERROR);
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_SERVER);
break;
case HTTP_STATUS_INTERNAL_SERVER_ERROR:
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_DNS_FAILURE);
break;
case HTTP_STATUS_MOVED_TEMPORARILY:
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_SERVER);
break;
case HTTP_STATUS_PROXY_AUTHENTICATION_REQUIRED:
SET_VIA_STRING(VIA_CLIENT_REQUEST, VIA_CLIENT_ERROR);
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_AUTHORIZATION);
break;
case HTTP_STATUS_UNAUTHORIZED:
SET_VIA_STRING(VIA_CLIENT_REQUEST, VIA_CLIENT_ERROR);
SET_VIA_STRING(VIA_ERROR_TYPE, VIA_ERROR_AUTHORIZATION);
break;
default:
break;
}
reason_phrase = (reason_phrase_or_null ? reason_phrase_or_null : (char *) (http_hdr_reason_lookup(status_code)));
if (unlikely(!reason_phrase))
reason_phrase = "Unknown HTTP Status";
// set the source to internal so that chunking is handled correctly
s->source = SOURCE_INTERNAL;
build_response(s, &s->hdr_info.client_response, s->client_info.http_version, status_code, reason_phrase);
if (status_code == HTTP_STATUS_SERVICE_UNAVAILABLE) {
if (s->pCongestionEntry != NULL) {
int ret_tmp;
int retry_after = s->pCongestionEntry->client_retry_after();
s->congestion_control_crat = retry_after;
if (s->hdr_info.client_response.value_get(MIME_FIELD_RETRY_AFTER, MIME_LEN_RETRY_AFTER, &ret_tmp) == NULL)
s->hdr_info.client_response.value_set_int(MIME_FIELD_RETRY_AFTER, MIME_LEN_RETRY_AFTER, retry_after);
}
}
if (status_code == HTTP_STATUS_PROXY_AUTHENTICATION_REQUIRED &&
s->method == HTTP_WKSIDX_CONNECT && s->hdr_info.client_response.presence(MIME_PRESENCE_PROXY_CONNECTION)) {
int has_ua_msie = 0;
int user_agent_value_len, slen;
const char *user_agent_value, *c, *e;
user_agent_value = s->hdr_info.client_request.value_get(MIME_FIELD_USER_AGENT, MIME_LEN_USER_AGENT, &user_agent_value_len);
if (user_agent_value && user_agent_value_len >= 4) {
c = user_agent_value;
e = c + user_agent_value_len - 4;
while (1) {
slen = (int) (e - c);
c = (const char *) memchr(c, 'M', slen);
if (c == NULL || (e - c) < 3)
break;
if ((c[1] == 'S') && (c[2] == 'I') && (c[3] == 'E')) {
has_ua_msie = 1;
break;
}
c++;
}
}
if (has_ua_msie)
s->hdr_info.client_response.value_set(MIME_FIELD_PROXY_CONNECTION, MIME_LEN_PROXY_CONNECTION, "close", 5);
}
// Add a bunch of headers to make sure that caches between
// the Traffic Server and the client do not cache the error
// page.
s->hdr_info.client_response.value_set(MIME_FIELD_CACHE_CONTROL, MIME_LEN_CACHE_CONTROL, "no-store", 8);
// Make sure there are no Expires and Last-Modified headers.
s->hdr_info.client_response.field_delete(MIME_FIELD_EXPIRES, MIME_LEN_EXPIRES);
s->hdr_info.client_response.field_delete(MIME_FIELD_LAST_MODIFIED, MIME_LEN_LAST_MODIFIED);
if ((status_code == HTTP_STATUS_TEMPORARY_REDIRECT ||
status_code == HTTP_STATUS_MOVED_TEMPORARILY ||
status_code == HTTP_STATUS_MOVED_PERMANENTLY) &&
s->remap_redirect) {
s->hdr_info.client_response.value_set(MIME_FIELD_LOCATION, MIME_LEN_LOCATION, s->remap_redirect, strlen(s->remap_redirect));
}
////////////////////////////////////////////////////////////////////
// create the error message using the "body factory", which will //
// build a customized error message if available, or generate the //
// old style internal defaults otherwise --- the body factory //
// supports language targeting using the Accept-Language header //
////////////////////////////////////////////////////////////////////
int64_t len;
char * new_msg;
va_start(ap, format);
new_msg = body_factory->fabricate_with_old_api(error_body_type, s, 8192,
&len,
body_language, sizeof(body_language),
body_type, sizeof(body_type),
format, ap);
va_end(ap);
// After the body factory is called, a new "body" is allocated, and we must replace it. It is
// unfortunate that there's no way to avoid this fabrication even when there is no substitutions...
s->free_internal_msg_buffer();
s->internal_msg_buffer = new_msg;
s->internal_msg_buffer_size = len;
s->internal_msg_buffer_index = 0;
s->internal_msg_buffer_fast_allocator_size = -1;
s->hdr_info.client_response.value_set(MIME_FIELD_CONTENT_TYPE, MIME_LEN_CONTENT_TYPE, body_type, strlen(body_type));
s->hdr_info.client_response.value_set(MIME_FIELD_CONTENT_LANGUAGE, MIME_LEN_CONTENT_LANGUAGE, body_language,
strlen(body_language));
////////////////////////////////////////
// log a description in the error log //
////////////////////////////////////////
if (s->current.state == CONNECTION_ERROR) {
char *reason_buffer;
int buf_len = sizeof(char) * (strlen(get_error_string(s->cause_of_death_errno)) + 50);
reason_buffer = (char *) alloca(buf_len);
snprintf(reason_buffer, buf_len, "Connect Error <%s/%d>", get_error_string(s->cause_of_death_errno), s->cause_of_death_errno);
reason_phrase = reason_buffer;
}
if (s->http_config_param->errors_log_error_pages && status_code >= HTTP_STATUS_BAD_REQUEST) {
char ip_string[INET6_ADDRSTRLEN];
Log::error("RESPONSE: sent %s status %d (%s) for '%s'",
ats_ip_ntop(&s->client_info.addr.sa, ip_string, sizeof(ip_string)),
status_code,
reason_phrase,
(url_string ? url_string : "<none>"));
}
if (url_string) {
s->arena.str_free(url_string);
}
s->next_action = SM_ACTION_SEND_ERROR_CACHE_NOOP;
return;
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'Fix the internal buffer sizing. Thanks to Sudheer for helping isolating this bug'</s>
|
<s>[INST] Given the following code containing errors, provide Common Weakness Enumeration (CWE) identifiers and corresponding messages in JSON format. Each identified weakness should have a unique entry in the JSON array.
Code: void jpc_qmfb_join_colgrp(jpc_fix_t *a, int numrows, int stride,
int parity)
{
int bufsize = JPC_CEILDIVPOW2(numrows, 1);
#if !defined(HAVE_VLA)
jpc_fix_t joinbuf[QMFB_JOINBUFSIZE * JPC_QMFB_COLGRPSIZE];
#else
jpc_fix_t joinbuf[bufsize * JPC_QMFB_COLGRPSIZE];
#endif
jpc_fix_t *buf = joinbuf;
jpc_fix_t *srcptr;
jpc_fix_t *dstptr;
register jpc_fix_t *srcptr2;
register jpc_fix_t *dstptr2;
register int n;
register int i;
int hstartcol;
#if !defined(HAVE_VLA)
/* Allocate memory for the join buffer from the heap. */
if (bufsize > QMFB_JOINBUFSIZE) {
if (!(buf = jas_malloc(bufsize * JPC_QMFB_COLGRPSIZE * sizeof(jpc_fix_t)))) {
/* We have no choice but to commit suicide. */
abort();
}
}
#endif
hstartcol = (numrows + 1 - parity) >> 1;
/* Save the samples from the lowpass channel. */
n = hstartcol;
srcptr = &a[0];
dstptr = buf;
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < JPC_QMFB_COLGRPSIZE; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
srcptr += stride;
dstptr += JPC_QMFB_COLGRPSIZE;
}
/* Copy the samples from the highpass channel into place. */
srcptr = &a[hstartcol * stride];
dstptr = &a[(1 - parity) * stride];
n = numrows - hstartcol;
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < JPC_QMFB_COLGRPSIZE; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
dstptr += 2 * stride;
srcptr += stride;
}
/* Copy the samples from the lowpass channel into place. */
srcptr = buf;
dstptr = &a[parity * stride];
n = hstartcol;
while (n-- > 0) {
dstptr2 = dstptr;
srcptr2 = srcptr;
for (i = 0; i < JPC_QMFB_COLGRPSIZE; ++i) {
*dstptr2 = *srcptr2;
++dstptr2;
++srcptr2;
}
dstptr += 2 * stride;
srcptr += JPC_QMFB_COLGRPSIZE;
}
#if !defined(HAVE_VLA)
/* If the join buffer was allocated on the heap, free this memory. */
if (buf != joinbuf) {
jas_free(buf);
}
#endif
} ; Sample JSON Format Confermily Expected output: "examples" => "cwe": "xxx"; "message": "xxx"
[/INST] 'cwe': ['CWE-119'], 'message': 'CVE-2014-8158'</s>
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.