[libc-commits] [libc] [libc] implement sys/getauxval (PR #78493)

[Schrodinger ZHU Yifan via libc-commits]

================
@@ -0,0 +1,218 @@
+//===-- Implementation file for getauxval function --------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "src/sys/auxv/getauxval.h"
+#include "config/linux/app.h"
+#include "src/__support/common.h"
+#include "src/errno/libc_errno.h"
+#include <linux/auxvec.h>
+
+// for guarded initialization
+#include "src/__support/threads/callonce.h"
+#include "src/__support/threads/linux/futex_word.h"
+
+// for mallocing the global auxv
+#include "src/sys/mman/mmap.h"
+#include "src/sys/mman/munmap.h"
+
+// for reading /proc/self/auxv
+#include "src/fcntl/open.h"
+#include "src/sys/prctl/prctl.h"
+#include "src/unistd/close.h"
+#include "src/unistd/read.h"
+
+// getauxval will work either with or without __cxa_atexit support.
+// In order to detect if __cxa_atexit is supported, we define a weak symbol.
+// We prefer __cxa_atexit as it is always defined as a C symbol whileas atexit
+// may not be created via objcopy yet. Also, for glibc, atexit is provided via
+// libc_nonshared.a rather than libc.so. So, it is may not be made ready for
+// overlay builds.
+extern "C" [[gnu::weak]] int __cxa_atexit(void (*callback)(void *),
+                                          void *payload, void *);
+
+namespace LIBC_NAMESPACE {
+
+constexpr static size_t MAX_AUXV_ENTRIES = 64;
+
+// Helper to recover or set errno
+class AuxvErrnoGuard {
+public:
+  AuxvErrnoGuard() : saved(libc_errno), failure(false) {}
+  ~AuxvErrnoGuard() { libc_errno = failure ? ENOENT : saved; }
+  void mark_failure() { failure = true; }
+
+private:
+  int saved;
+  bool failure;
+};
+
+// Helper to manage the memory
+static AuxEntry *auxv = nullptr;
+
+class AuxvMMapGuard {
+public:
+  constexpr static size_t AUXV_MMAP_SIZE = sizeof(AuxEntry) * MAX_AUXV_ENTRIES;
+
+  AuxvMMapGuard()
+      : ptr(mmap(nullptr, AUXV_MMAP_SIZE, PROT_READ | PROT_WRITE,
+                 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0)) {}
+  ~AuxvMMapGuard() {
+    if (ptr != MAP_FAILED) {
+      munmap(ptr, AUXV_MMAP_SIZE);
+    }
+  }
+  void submit_to_global() {
+    // atexit may fail, we do not set it to global in that case.
+    int ret = __cxa_atexit(
+        [](void *) {
+          munmap(auxv, AUXV_MMAP_SIZE);
+          auxv = nullptr;
+        },
+        nullptr, nullptr);
+
+    if (ret != 0)
+      return;
+
+    auxv = reinterpret_cast<AuxEntry *>(ptr);
+    ptr = MAP_FAILED;
+  }
+  bool allocated() const { return ptr != MAP_FAILED; }
+  void *get() const { return ptr; }
+
+private:
+  void *ptr;
+};
+
+class AuxvFdGuard {
+public:
+  AuxvFdGuard() : fd(open("/proc/self/auxv", O_RDONLY | O_CLOEXEC)) {}
+  ~AuxvFdGuard() {
+    if (fd != -1) {
+      close(fd);
+    }
+  }
+  bool valid() const { return fd != -1; }
+  int get() const { return fd; }
+
+private:
+  int fd;
+};
+
+static void initialize_auxv_once(void) {
+  // If we cannot get atexit, we cannot register the cleanup function.
+  if (&__cxa_atexit == nullptr)
+    return;
+
+  AuxvMMapGuard mmap_guard;
+  if (!mmap_guard.allocated())
+    return;
+  auto *ptr = reinterpret_cast<AuxEntry *>(mmap_guard.get());
+
+  // We get one less than the max size to make sure the search always
+  // terminates. MMAP private pages are zeroed out already.
+  size_t available_size = AuxvMMapGuard::AUXV_MMAP_SIZE - sizeof(AuxEntryType);
+  // PR_GET_AUXV is only available on Linux kernel 6.1 and above. If this is not
+  // defined, we direcly fall back to reading /proc/self/auxv. In case the libc
+  // is compiled and run on separate kernels, we also check the return value of
+  // prctl.
+#ifdef PR_GET_AUXV
+  int ret = prctl(PR_GET_AUXV, reinterpret_cast<unsigned long>(ptr),
+                  available_size, 0, 0);
+  if (ret >= 0) {
+    mmap_guard.submit_to_global();
+    return;
+  }
+#endif
+  AuxvFdGuard fd_guard;
+  if (!fd_guard.valid())
+    return;
+  auto *buf = reinterpret_cast<char *>(ptr);
+  libc_errno = 0;
+  bool error_detected = false;
+  // Read until we use up all the available space or we finish reading the file.
+  while (available_size != 0) {
+    ssize_t bytes_read = read(fd_guard.get(), buf, available_size);
+    if (bytes_read <= 0) {
+      if (libc_errno == EINTR)
+        continue;
+      if (bytes_read == -1)
+        error_detected = true;
----------------
SchrodingerZhu wrote:

Here it is returning early since `break` to be executed directly. `error_detected` is used because `bytes_read` can be zero, indicating that all entries are read into the buffer.

https://github.com/llvm/llvm-project/pull/78493