Pavel Labath 62930e57eb Add Utility/Environment class for handling... environments
Summary:
There was some confusion in the code about how to represent process
environment. Most of the code (ab)used the Args class for this purpose,
but some of it used a more basic StringList class instead. In either
case, the fact that the underlying abstraction did not provide primitive
operations for the typical environment operations meant that even a
simple operation like checking for an environment variable value was
several lines of code.

This patch adds a separate Environment class, which is essentialy a
llvm::StringMap<std::string> in disguise. To standard StringMap
functionality, it adds a couple of new functions, which are specific to
the environment use case:
- (most important) envp conversion for passing into execve() and likes.
  Instead of trying to maintain a constantly up-to-date envp view, it
  provides a function which creates a envp view on demand, with the
  expectation that this will be called as the very last thing before
  handing the value to the system function.
- insert(StringRef KeyEqValue) - splits KeyEqValue into (key, value)
  pair and inserts it into the environment map.
- compose(value_type KeyValue) - takes a map entry and converts in back
  into "KEY=VALUE" representation.

With this interface most of the environment-manipulating code becomes
one-liners. The only tricky part was maintaining compatibility in
SBLaunchInfo, which expects that the environment entries are accessible
by index and that the returned const char* is backed by the launch info
object (random access into maps is hard and the map stores the entry in
a deconstructed form, so we cannot just return a .c_str() value). To
solve this, I have the SBLaunchInfo convert the environment into the
"envp" form, and use it to answer the environment queries. Extra code is
added to make sure the envp version is always in sync.

(This also improves the layering situation as Args was in the Interpreter module
whereas Environment is in Utility.)

Reviewers: zturner, davide, jingham, clayborg

Subscribers: emaste, lldb-commits, mgorny

Differential Revision: https://reviews.llvm.org/D41359

llvm-svn: 322174
2018-01-10 11:57:31 +00:00

305 lines
8.7 KiB
C++

//===-- source/Host/linux/Host.cpp ------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
// C Includes
#include <dirent.h>
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/utsname.h>
#include <unistd.h>
// C++ Includes
// Other libraries and framework includes
#include "llvm/Support/ScopedPrinter.h"
// Project includes
#include "lldb/Target/Process.h"
#include "lldb/Utility/Log.h"
#include "lldb/Utility/Status.h"
#include "lldb/Host/Host.h"
#include "lldb/Host/HostInfo.h"
#include "lldb/Host/linux/Support.h"
#include "lldb/Utility/DataBufferHeap.h"
#include "lldb/Utility/DataExtractor.h"
#include "lldb/Core/ModuleSpec.h"
#include "lldb/Symbol/ObjectFile.h"
using namespace lldb;
using namespace lldb_private;
namespace {
enum class ProcessState {
Unknown,
DiskSleep,
Paging,
Running,
Sleeping,
TracedOrStopped,
Zombie,
};
}
static bool GetStatusInfo(::pid_t Pid, ProcessInstanceInfo &ProcessInfo,
ProcessState &State, ::pid_t &TracerPid) {
auto BufferOrError = getProcFile(Pid, "status");
if (!BufferOrError)
return false;
llvm::StringRef Rest = BufferOrError.get()->getBuffer();
while(!Rest.empty()) {
llvm::StringRef Line;
std::tie(Line, Rest) = Rest.split('\n');
if (Line.consume_front("Gid:")) {
// Real, effective, saved set, and file system GIDs. Read the first two.
Line = Line.ltrim();
uint32_t RGid, EGid;
Line.consumeInteger(10, RGid);
Line = Line.ltrim();
Line.consumeInteger(10, EGid);
ProcessInfo.SetGroupID(RGid);
ProcessInfo.SetEffectiveGroupID(EGid);
} else if (Line.consume_front("Uid:")) {
// Real, effective, saved set, and file system UIDs. Read the first two.
Line = Line.ltrim();
uint32_t RUid, EUid;
Line.consumeInteger(10, RUid);
Line = Line.ltrim();
Line.consumeInteger(10, EUid);
ProcessInfo.SetUserID(RUid);
ProcessInfo.SetEffectiveUserID(EUid);
} else if (Line.consume_front("PPid:")) {
::pid_t PPid;
Line.ltrim().consumeInteger(10, PPid);
ProcessInfo.SetParentProcessID(PPid);
} else if (Line.consume_front("State:")) {
char S = Line.ltrim().front();
switch (S) {
case 'R':
State = ProcessState::Running;
break;
case 'S':
State = ProcessState::Sleeping;
break;
case 'D':
State = ProcessState::DiskSleep;
break;
case 'Z':
State = ProcessState::Zombie;
break;
case 'T':
State = ProcessState::TracedOrStopped;
break;
case 'W':
State = ProcessState::Paging;
break;
}
} else if (Line.consume_front("TracerPid:")) {
Line = Line.ltrim();
Line.consumeInteger(10, TracerPid);
}
}
return true;
}
static bool IsDirNumeric(const char *dname) {
for (; *dname; dname++) {
if (!isdigit(*dname))
return false;
}
return true;
}
static bool GetELFProcessCPUType(llvm::StringRef exe_path,
ProcessInstanceInfo &process_info) {
// Clear the architecture.
process_info.GetArchitecture().Clear();
ModuleSpecList specs;
FileSpec filespec(exe_path, false);
const size_t num_specs =
ObjectFile::GetModuleSpecifications(filespec, 0, 0, specs);
// GetModuleSpecifications() could fail if the executable has been deleted or
// is locked.
// But it shouldn't return more than 1 architecture.
assert(num_specs <= 1 && "Linux plugin supports only a single architecture");
if (num_specs == 1) {
ModuleSpec module_spec;
if (specs.GetModuleSpecAtIndex(0, module_spec) &&
module_spec.GetArchitecture().IsValid()) {
process_info.GetArchitecture() = module_spec.GetArchitecture();
return true;
}
}
return false;
}
static bool GetProcessAndStatInfo(::pid_t pid,
ProcessInstanceInfo &process_info,
ProcessState &State, ::pid_t &tracerpid) {
tracerpid = 0;
process_info.Clear();
Log *log(GetLogIfAllCategoriesSet(LIBLLDB_LOG_PROCESS));
// We can't use getProcFile here because proc/[pid]/exe is a symbolic link.
llvm::SmallString<64> ProcExe;
(llvm::Twine("/proc/") + llvm::Twine(pid) + "/exe").toVector(ProcExe);
std::string ExePath(PATH_MAX, '\0');
ssize_t len = readlink(ProcExe.c_str(), &ExePath[0], PATH_MAX);
if (len <= 0) {
LLDB_LOG(log, "failed to read link exe link for {0}: {1}", pid,
Status(errno, eErrorTypePOSIX));
return false;
}
ExePath.resize(len);
// If the binary has been deleted, the link name has " (deleted)" appended.
// Remove if there.
llvm::StringRef PathRef = ExePath;
PathRef.consume_back(" (deleted)");
GetELFProcessCPUType(PathRef, process_info);
// Get the process environment.
auto BufferOrError = getProcFile(pid, "environ");
if (!BufferOrError)
return false;
std::unique_ptr<llvm::MemoryBuffer> Environ = std::move(*BufferOrError);
// Get the command line used to start the process.
BufferOrError = getProcFile(pid, "cmdline");
if (!BufferOrError)
return false;
std::unique_ptr<llvm::MemoryBuffer> Cmdline = std::move(*BufferOrError);
// Get User and Group IDs and get tracer pid.
if (!GetStatusInfo(pid, process_info, State, tracerpid))
return false;
process_info.SetProcessID(pid);
process_info.GetExecutableFile().SetFile(PathRef, false);
process_info.GetArchitecture().MergeFrom(HostInfo::GetArchitecture());
llvm::StringRef Rest = Environ->getBuffer();
while (!Rest.empty()) {
llvm::StringRef Var;
std::tie(Var, Rest) = Rest.split('\0');
process_info.GetEnvironment().insert(Var);
}
llvm::StringRef Arg0;
std::tie(Arg0, Rest) = Cmdline->getBuffer().split('\0');
process_info.SetArg0(Arg0);
while (!Rest.empty()) {
llvm::StringRef Arg;
std::tie(Arg, Rest) = Rest.split('\0');
process_info.GetArguments().AppendArgument(Arg);
}
return true;
}
uint32_t Host::FindProcesses(const ProcessInstanceInfoMatch &match_info,
ProcessInstanceInfoList &process_infos) {
static const char procdir[] = "/proc/";
DIR *dirproc = opendir(procdir);
if (dirproc) {
struct dirent *direntry = NULL;
const uid_t our_uid = getuid();
const lldb::pid_t our_pid = getpid();
bool all_users = match_info.GetMatchAllUsers();
while ((direntry = readdir(dirproc)) != NULL) {
if (direntry->d_type != DT_DIR || !IsDirNumeric(direntry->d_name))
continue;
lldb::pid_t pid = atoi(direntry->d_name);
// Skip this process.
if (pid == our_pid)
continue;
::pid_t tracerpid;
ProcessState State;
ProcessInstanceInfo process_info;
if (!GetProcessAndStatInfo(pid, process_info, State, tracerpid))
continue;
// Skip if process is being debugged.
if (tracerpid != 0)
continue;
if (State == ProcessState::Zombie)
continue;
// Check for user match if we're not matching all users and not running as
// root.
if (!all_users && (our_uid != 0) && (process_info.GetUserID() != our_uid))
continue;
if (match_info.Matches(process_info)) {
process_infos.Append(process_info);
}
}
closedir(dirproc);
}
return process_infos.GetSize();
}
bool Host::FindProcessThreads(const lldb::pid_t pid, TidMap &tids_to_attach) {
bool tids_changed = false;
static const char procdir[] = "/proc/";
static const char taskdir[] = "/task/";
std::string process_task_dir = procdir + llvm::to_string(pid) + taskdir;
DIR *dirproc = opendir(process_task_dir.c_str());
if (dirproc) {
struct dirent *direntry = NULL;
while ((direntry = readdir(dirproc)) != NULL) {
if (direntry->d_type != DT_DIR || !IsDirNumeric(direntry->d_name))
continue;
lldb::tid_t tid = atoi(direntry->d_name);
TidMap::iterator it = tids_to_attach.find(tid);
if (it == tids_to_attach.end()) {
tids_to_attach.insert(TidPair(tid, false));
tids_changed = true;
}
}
closedir(dirproc);
}
return tids_changed;
}
bool Host::GetProcessInfo(lldb::pid_t pid, ProcessInstanceInfo &process_info) {
::pid_t tracerpid;
ProcessState State;
return GetProcessAndStatInfo(pid, process_info, State, tracerpid);
}
Environment Host::GetEnvironment() { return Environment(environ); }
Status Host::ShellExpandArguments(ProcessLaunchInfo &launch_info) {
return Status("unimplemented");
}