Files
clang-p2996/lldb/source/Utility/StringExtractor.cpp
Greg Clayton 32e0a7509c Many improvements to the Platform base class and subclasses. The base Platform
class now implements the Host functionality for a lot of things that make 
sense by default so that subclasses can check:

int
PlatformSubclass::Foo ()
{
    if (IsHost())
        return Platform::Foo (); // Let the platform base class do the host specific stuff
    
    // Platform subclass specific code...
    int result = ...
    return result;
}

Added new functions to the platform:

    virtual const char *Platform::GetUserName (uint32_t uid);
    virtual const char *Platform::GetGroupName (uint32_t gid);

The user and group names are cached locally so that remote platforms can avoid
sending packets multiple times to resolve this information.

Added the parent process ID to the ProcessInfo class. 

Added a new ProcessInfoMatch class which helps us to match processes up
and changed the Host layer over to using this new class. The new class allows
us to search for processs:
1 - by name (equal to, starts with, ends with, contains, and regex)
2 - by pid
3 - And further check for parent pid == value, uid == value, gid == value, 
    euid == value, egid == value, arch == value, parent == value.
    
This is all hookup up to the "platform process list" command which required
adding dumping routines to dump process information. If the Host class 
implements the process lookup routines, you can now lists processes on 
your local machine:

machine1.foo.com % lldb
(lldb) platform process list 
PID    PARENT USER       GROUP      EFF USER   EFF GROUP  TRIPLE                   NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99538  1      username   usergroup  username   usergroup  x86_64-apple-darwin      FileMerge
94943  1      username   usergroup  username   usergroup  x86_64-apple-darwin      mdworker
94852  244    username   usergroup  username   usergroup  x86_64-apple-darwin      Safari
94727  244    username   usergroup  username   usergroup  x86_64-apple-darwin      Xcode
92742  92710  username   usergroup  username   usergroup  i386-apple-darwin        debugserver


This of course also works remotely with the lldb-platform:

machine1.foo.com % lldb-platform --listen 1234

machine2.foo.com % lldb
(lldb) platform create remote-macosx
  Platform: remote-macosx
 Connected: no
(lldb) platform connect connect://localhost:1444
  Platform: remote-macosx
    Triple: x86_64-apple-darwin
OS Version: 10.6.7 (10J869)
    Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386
  Hostname: machine1.foo.com
 Connected: yes
(lldb) platform process list 
PID    PARENT USER       GROUP      EFF USER   EFF GROUP  TRIPLE                   NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99556  244    username   usergroup  username   usergroup  x86_64-apple-darwin      trustevaluation
99548  65539  username   usergroup  username   usergroup  x86_64-apple-darwin      lldb
99538  1      username   usergroup  username   usergroup  x86_64-apple-darwin      FileMerge
94943  1      username   usergroup  username   usergroup  x86_64-apple-darwin      mdworker
94852  244    username   usergroup  username   usergroup  x86_64-apple-darwin      Safari

The lldb-platform implements everything with the Host:: layer, so this should
"just work" for linux. I will probably be adding more stuff to the Host layer
for launching processes and attaching to processes so that this support should
eventually just work as well.

Modified the target to be able to be created with an architecture that differs
from the main executable. This is needed for iOS debugging since we can have
an "armv6" binary which can run on an "armv7" machine, so we want to be able
to do:

% lldb
(lldb) platform create remote-ios
(lldb) file --arch armv7 a.out

Where "a.out" is an armv6 executable. The platform then can correctly decide
to open all "armv7" images for all dependent shared libraries.

Modified the disassembly to show the current PC value. Example output:

(lldb) disassemble --frame
a.out`main:
   0x1eb7:  pushl  %ebp
   0x1eb8:  movl   %esp, %ebp
   0x1eba:  pushl  %ebx
   0x1ebb:  subl   $20, %esp
   0x1ebe:  calll  0x1ec3                   ; main + 12 at test.c:18
   0x1ec3:  popl   %ebx
-> 0x1ec4:  calll  0x1f12                   ; getpid
   0x1ec9:  movl   %eax, 4(%esp)
   0x1ecd:  leal   199(%ebx), %eax
   0x1ed3:  movl   %eax, (%esp)
   0x1ed6:  calll  0x1f18                   ; printf
   0x1edb:  leal   213(%ebx), %eax
   0x1ee1:  movl   %eax, (%esp)
   0x1ee4:  calll  0x1f1e                   ; puts
   0x1ee9:  calll  0x1f0c                   ; getchar
   0x1eee:  movl   $20, (%esp)
   0x1ef5:  calll  0x1e6a                   ; sleep_loop at test.c:6
   0x1efa:  movl   $12, %eax
   0x1eff:  addl   $20, %esp
   0x1f02:  popl   %ebx
   0x1f03:  leave
   0x1f04:  ret
   
This can be handy when dealing with the new --line options that was recently
added:

(lldb) disassemble --line
a.out`main + 13 at test.c:19
   18  	{
-> 19  		printf("Process: %i\n\n", getpid());
   20  	    puts("Press any key to continue..."); getchar();
-> 0x1ec4:  calll  0x1f12                   ; getpid
   0x1ec9:  movl   %eax, 4(%esp)
   0x1ecd:  leal   199(%ebx), %eax
   0x1ed3:  movl   %eax, (%esp)
   0x1ed6:  calll  0x1f18                   ; printf

Modified the ModuleList to have a lookup based solely on a UUID. Since the
UUID is typically the MD5 checksum of a binary image, there is no need
to give the path and architecture when searching for a pre-existing
image in an image list.

Now that we support remote debugging a bit better, our lldb_private::Module
needs to be able to track what the original path for file was as the platform
knows it, as well as where the file is locally. The module has the two 
following functions to retrieve both paths:

const FileSpec &Module::GetFileSpec () const;
const FileSpec &Module::GetPlatformFileSpec () const;

llvm-svn: 128563
2011-03-30 18:16:51 +00:00

393 lines
10 KiB
C++

//===-- StringExtractor.cpp -------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "Utility/StringExtractor.h"
// C Includes
// C++ Includes
// Other libraries and framework includes
// Project includes
static inline int
xdigit_to_sint (char ch)
{
if (ch >= 'a' && ch <= 'f')
return 10 + ch - 'a';
if (ch >= 'A' && ch <= 'F')
return 10 + ch - 'A';
return ch - '0';
}
static inline unsigned int
xdigit_to_uint (uint8_t ch)
{
if (ch >= 'a' && ch <= 'f')
return 10u + ch - 'a';
if (ch >= 'A' && ch <= 'F')
return 10u + ch - 'A';
return ch - '0';
}
//----------------------------------------------------------------------
// StringExtractor constructor
//----------------------------------------------------------------------
StringExtractor::StringExtractor() :
m_packet(),
m_index (0)
{
}
StringExtractor::StringExtractor(const char *packet_cstr) :
m_packet(),
m_index (0)
{
if (packet_cstr)
m_packet.assign (packet_cstr);
}
//----------------------------------------------------------------------
// StringExtractor copy constructor
//----------------------------------------------------------------------
StringExtractor::StringExtractor(const StringExtractor& rhs) :
m_packet (rhs.m_packet),
m_index (rhs.m_index)
{
}
//----------------------------------------------------------------------
// StringExtractor assignment operator
//----------------------------------------------------------------------
const StringExtractor&
StringExtractor::operator=(const StringExtractor& rhs)
{
if (this != &rhs)
{
m_packet = rhs.m_packet;
m_index = rhs.m_index;
}
return *this;
}
//----------------------------------------------------------------------
// Destructor
//----------------------------------------------------------------------
StringExtractor::~StringExtractor()
{
}
char
StringExtractor::GetChar (char fail_value)
{
if (m_index < m_packet.size())
{
char ch = m_packet[m_index];
++m_index;
return ch;
}
m_index = UINT32_MAX;
return fail_value;
}
uint32_t
StringExtractor::GetNumHexASCIICharsAtFilePos (uint32_t max) const
{
uint32_t idx = m_index;
const size_t size = m_packet.size();
while (idx < size && idx - m_index < max && isxdigit(m_packet[idx]))
++idx;
return idx - m_index;
}
//----------------------------------------------------------------------
// Extract a signed character from two hex ASCII chars in the packet
// string
//----------------------------------------------------------------------
int8_t
StringExtractor::GetHexS8 (int8_t fail_value)
{
if (GetNumHexASCIICharsAtFilePos(2))
{
char hi_nibble_char = m_packet[m_index];
char lo_nibble_char = m_packet[m_index+1];
if (isxdigit(hi_nibble_char) && isxdigit(lo_nibble_char))
{
char hi_nibble = xdigit_to_sint (hi_nibble_char);
char lo_nibble = xdigit_to_sint (lo_nibble_char);
m_index += 2;
return (hi_nibble << 4) + lo_nibble;
}
}
m_index = UINT32_MAX;
return fail_value;
}
//----------------------------------------------------------------------
// Extract an unsigned character from two hex ASCII chars in the packet
// string
//----------------------------------------------------------------------
uint8_t
StringExtractor::GetHexU8 (uint8_t fail_value)
{
if (GetNumHexASCIICharsAtFilePos(2))
{
uint8_t hi_nibble_char = m_packet[m_index];
uint8_t lo_nibble_char = m_packet[m_index+1];
if (isxdigit(hi_nibble_char) && isxdigit(lo_nibble_char))
{
uint8_t hi_nibble = xdigit_to_uint (hi_nibble_char);
uint8_t lo_nibble = xdigit_to_uint (lo_nibble_char);
m_index += 2;
return (hi_nibble << 4) + lo_nibble;
}
}
m_index = UINT32_MAX;
return fail_value;
}
uint32_t
StringExtractor::GetU32 (uint32_t fail_value, int base)
{
if (m_index < m_packet.size())
{
char *end = NULL;
const char *start = m_packet.c_str();
const char *uint_cstr = start + m_index;
uint32_t result = ::strtoul (uint_cstr, &end, base);
if (end && end != uint_cstr)
{
m_index = end - start;
return result;
}
}
return fail_value;
}
uint32_t
StringExtractor::GetHexMaxU32 (bool little_endian, uint32_t fail_value)
{
uint32_t result = 0;
uint32_t nibble_count = 0;
if (little_endian)
{
uint32_t shift_amount = 0;
while (m_index < m_packet.size() && ::isxdigit (m_packet[m_index]))
{
// Make sure we don't exceed the size of a uint32_t...
if (nibble_count >= (sizeof(uint32_t) * 2))
{
m_index = UINT32_MAX;
return fail_value;
}
uint8_t nibble_lo;
uint8_t nibble_hi = xdigit_to_sint (m_packet[m_index]);
++m_index;
if (m_index < m_packet.size() && ::isxdigit (m_packet[m_index]))
{
nibble_lo = xdigit_to_sint (m_packet[m_index]);
++m_index;
result |= ((uint32_t)nibble_hi << (shift_amount + 4));
result |= ((uint32_t)nibble_lo << shift_amount);
nibble_count += 2;
shift_amount += 8;
}
else
{
result |= ((uint32_t)nibble_hi << shift_amount);
nibble_count += 1;
shift_amount += 4;
}
}
}
else
{
while (m_index < m_packet.size() && ::isxdigit (m_packet[m_index]))
{
// Make sure we don't exceed the size of a uint32_t...
if (nibble_count >= (sizeof(uint32_t) * 2))
{
m_index = UINT32_MAX;
return fail_value;
}
uint8_t nibble = xdigit_to_sint (m_packet[m_index]);
// Big Endian
result <<= 4;
result |= nibble;
++m_index;
++nibble_count;
}
}
return result;
}
uint64_t
StringExtractor::GetHexMaxU64 (bool little_endian, uint64_t fail_value)
{
uint64_t result = 0;
uint32_t nibble_count = 0;
if (little_endian)
{
uint32_t shift_amount = 0;
while (m_index < m_packet.size() && ::isxdigit (m_packet[m_index]))
{
// Make sure we don't exceed the size of a uint64_t...
if (nibble_count >= (sizeof(uint64_t) * 2))
{
m_index = UINT32_MAX;
return fail_value;
}
uint8_t nibble_lo;
uint8_t nibble_hi = xdigit_to_sint (m_packet[m_index]);
++m_index;
if (m_index < m_packet.size() && ::isxdigit (m_packet[m_index]))
{
nibble_lo = xdigit_to_sint (m_packet[m_index]);
++m_index;
result |= ((uint64_t)nibble_hi << (shift_amount + 4));
result |= ((uint64_t)nibble_lo << shift_amount);
nibble_count += 2;
shift_amount += 8;
}
else
{
result |= ((uint64_t)nibble_hi << shift_amount);
nibble_count += 1;
shift_amount += 4;
}
}
}
else
{
while (m_index < m_packet.size() && ::isxdigit (m_packet[m_index]))
{
// Make sure we don't exceed the size of a uint64_t...
if (nibble_count >= (sizeof(uint64_t) * 2))
{
m_index = UINT32_MAX;
return fail_value;
}
uint8_t nibble = xdigit_to_sint (m_packet[m_index]);
// Big Endian
result <<= 4;
result |= nibble;
++m_index;
++nibble_count;
}
}
return result;
}
size_t
StringExtractor::GetHexBytes (void *dst_void, size_t dst_len, uint8_t fail_fill_value)
{
uint8_t *dst = (uint8_t*)dst_void;
size_t bytes_extracted = 0;
while (bytes_extracted < dst_len && GetBytesLeft ())
{
dst[bytes_extracted] = GetHexU8 (fail_fill_value);
if (IsGood())
++bytes_extracted;
else
break;
}
for (size_t i = bytes_extracted; i < dst_len; ++i)
dst[i] = fail_fill_value;
return bytes_extracted;
}
// Consume ASCII hex nibble character pairs until we have decoded byte_size
// bytes of data.
uint64_t
StringExtractor::GetHexWithFixedSize (uint32_t byte_size, bool little_endian, uint64_t fail_value)
{
if (byte_size <= 8 && GetBytesLeft() >= byte_size * 2)
{
uint64_t result = 0;
uint32_t i;
if (little_endian)
{
// Little Endian
uint32_t shift_amount;
for (i = 0, shift_amount = 0;
i < byte_size && m_index != UINT32_MAX;
++i, shift_amount += 8)
{
result |= ((uint64_t)GetHexU8() << shift_amount);
}
}
else
{
// Big Endian
for (i = 0; i < byte_size && m_index != UINT32_MAX; ++i)
{
result <<= 8;
result |= GetHexU8();
}
}
}
m_index = UINT32_MAX;
return fail_value;
}
size_t
StringExtractor::GetHexByteString (std::string &str)
{
str.clear();
char ch;
while ((ch = GetHexU8()) != '\0')
str.append(1, ch);
return str.size();
}
bool
StringExtractor::GetNameColonValue (std::string &name, std::string &value)
{
// Read something in the form of NNNN:VVVV; where NNNN is any character
// that is not a colon, followed by a ':' character, then a value (one or
// more ';' chars), followed by a ';'
if (m_index < m_packet.size())
{
const size_t colon_idx = m_packet.find (':', m_index);
if (colon_idx != std::string::npos)
{
const size_t semicolon_idx = m_packet.find (';', colon_idx);
if (semicolon_idx != std::string::npos)
{
name.assign (m_packet, m_index, colon_idx - m_index);
value.assign (m_packet, colon_idx + 1, semicolon_idx - (colon_idx + 1));
m_index = semicolon_idx + 1;
return true;
}
}
}
m_index = UINT32_MAX;
return false;
}