[libunwind] Unwind through Linux riscv sigreturn trampoline

Similar to D90898 (Linux AArch64) and D124765 (SystemZ).

On an Arch Linux RISC-V (riscv64gc), the following code

```
#define _GNU_SOURCE
#include <dlfcn.h>
#include <libunwind.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>

static void handler(int signo) {
  unw_context_t context;
  unw_cursor_t cursor;
  unw_getcontext(&context);
  unw_init_local(&cursor, &context);
  unw_word_t pc, sp;
  do {
    unw_get_reg(&cursor, UNW_REG_IP, &pc);
    unw_get_reg(&cursor, UNW_REG_SP, &sp);
    printf("pc=0x%016zx sp=0x%016zx", (size_t)pc, (size_t)sp);
    Dl_info info = {};
    if (dladdr((void *)pc, &info))
      printf(" %s:%s", info.dli_fname, info.dli_sname ? info.dli_sname : "");
    puts("");
  } while (unw_step(&cursor) > 0);
  exit(0);
}

int main() {
  signal(SIGUSR1, handler);
  raise(SIGUSR1);
  return 1;
}
```

linked with `-Wl,--export-dynamic` gives an output like
```
pc=0x0000000000010a82 sp=0x00007fffd8a0b910 ./b:
pc=0x00007fffa7e77800 sp=0x00007fffd8a0c520 linux-vdso.so.1:__vdso_rt_sigreturn
pc=0x00007fffa7d73bee sp=0x00007fffd8a0c960 /usr/lib/libc.so.6:
pc=0x00007fffa7d3ed66 sp=0x00007fffd8a0c9b0 /usr/lib/libc.so.6:gsignal
pc=0x0000000000010a3c sp=0x00007fffd8a0c9c0 ./b:main
pc=0x00007fffa7d2f1d4 sp=0x00007fffd8a0c9e0 /usr/lib/libc.so.6:
pc=0x00007fffa7d2f27c sp=0x00007fffd8a0cb10 /usr/lib/libc.so.6:__libc_start_main
pc=0x00000000000109a0 sp=0x00007fffd8a0cb60 ./b:_start
```

Co-Authored-By: Fangrui Song <i@maskray.me>

Reviewed By: #libunwind, MaskRay

Differential Revision: https://reviews.llvm.org/D148499

3 files changed, 62 insertions, 3 deletions

diff --git a/libunwind/src/UnwindCursor.hpp b/libunwind/src/UnwindCursor.hpp
index db6d0ec853f3..dde94773bc34 100644
--- a/libunwind/src/UnwindCursor.hpp
+++ b/libunwind/src/UnwindCursor.hpp
@@ -31,7 +31,8 @@
 #endif
 
 #if defined(_LIBUNWIND_TARGET_LINUX) &&                                        \
-    (defined(_LIBUNWIND_TARGET_AARCH64) || defined(_LIBUNWIND_TARGET_S390X))
+    (defined(_LIBUNWIND_TARGET_AARCH64) || defined(_LIBUNWIND_TARGET_RISCV) || \
+     defined(_LIBUNWIND_TARGET_S390X))
 #include <sys/syscall.h>
 #include <sys/uio.h>
 #include <unistd.h>
@@ -993,6 +994,10 @@ private:
   bool setInfoForSigReturn(Registers_arm64 &);
   int stepThroughSigReturn(Registers_arm64 &);
 #endif
+#if defined(_LIBUNWIND_TARGET_RISCV)
+  bool setInfoForSigReturn(Registers_riscv &);
+  int stepThroughSigReturn(Registers_riscv &);
+#endif
 #if defined(_LIBUNWIND_TARGET_S390X)
   bool setInfoForSigReturn(Registers_s390x &);
   int stepThroughSigReturn(Registers_s390x &);
@@ -2721,6 +2726,60 @@ int UnwindCursor<A, R>::stepThroughSigReturn(Registers_arm64 &) {
        // defined(_LIBUNWIND_TARGET_AARCH64)
 
 #if defined(_LIBUNWIND_CHECK_LINUX_SIGRETURN) &&                               \
+    defined(_LIBUNWIND_TARGET_RISCV)
+template <typename A, typename R>
+bool UnwindCursor<A, R>::setInfoForSigReturn(Registers_riscv &) {
+  const pint_t pc = static_cast<pint_t>(getReg(UNW_REG_IP));
+  uint32_t instructions[2];
+  struct iovec local_iov = {&instructions, sizeof instructions};
+  struct iovec remote_iov = {reinterpret_cast<void *>(pc), sizeof instructions};
+  long bytesRead =
+      syscall(SYS_process_vm_readv, getpid(), &local_iov, 1, &remote_iov, 1, 0);
+  // Look for the two instructions used in the sigreturn trampoline
+  // __vdso_rt_sigreturn:
+  //
+  // 0x08b00893 li a7,0x8b
+  // 0x00000073 ecall
+  if (bytesRead != sizeof instructions || instructions[0] != 0x08b00893 ||
+      instructions[1] != 0x00000073)
+    return false;
+
+  _info = {};
+  _info.start_ip = pc;
+  _info.end_ip = pc + 4;
+  _isSigReturn = true;
+  return true;
+}
+
+template <typename A, typename R>
+int UnwindCursor<A, R>::stepThroughSigReturn(Registers_riscv &) {
+  // In the signal trampoline frame, sp points to an rt_sigframe[1], which is:
+  //  - 128-byte siginfo struct
+  //  - ucontext_t struct:
+  //     - 8-byte long (__uc_flags)
+  //     - 8-byte pointer (*uc_link)
+  //     - 24-byte uc_stack
+  //     - 8-byte uc_sigmask
+  //     - 120-byte of padding to allow sigset_t to be expanded in the future
+  //     - 8 bytes of padding because sigcontext has 16-byte alignment
+  //     - struct sigcontext uc_mcontext
+  // [1]
+  // https://github.com/torvalds/linux/blob/master/arch/riscv/kernel/signal.c
+  const pint_t kOffsetSpToSigcontext = 128 + 8 + 8 + 24 + 8 + 128;
+
+  const pint_t sigctx = _registers.getSP() + kOffsetSpToSigcontext;
+  _registers.setIP(_addressSpace.get64(sigctx));
+  for (int i = UNW_RISCV_X1; i <= UNW_RISCV_X31; ++i) {
+    uint64_t value = _addressSpace.get64(sigctx + static_cast<pint_t>(i * 8));
+    _registers.setRegister(i, value);
+  }
+  _isSignalFrame = true;
+  return UNW_STEP_SUCCESS;
+}
+#endif // defined(_LIBUNWIND_CHECK_LINUX_SIGRETURN) &&
+       // defined(_LIBUNWIND_TARGET_RISCV)
+
+#if defined(_LIBUNWIND_CHECK_LINUX_SIGRETURN) &&                               \
     defined(_LIBUNWIND_TARGET_S390X)
 template <typename A, typename R>
 bool UnwindCursor<A, R>::setInfoForSigReturn(Registers_s390x &) {
diff --git a/libunwind/test/signal_unwind.pass.cpp b/libunwind/test/signal_unwind.pass.cpp
index 2a731414aa85..954a5d4ba3db 100644
--- a/libunwind/test/signal_unwind.pass.cpp
+++ b/libunwind/test/signal_unwind.pass.cpp
@@ -8,7 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 // Ensure that the unwinder can cope with the signal handler.
-// REQUIRES: target={{(aarch64|s390x|x86_64)-.+linux.*}}
+// REQUIRES: target={{(aarch64|riscv64|s390x|x86_64)-.+linux.*}}
 
 // TODO: Figure out why this fails with Memory Sanitizer.
 // XFAIL: msan
diff --git a/libunwind/test/unwind_leaffunction.pass.cpp b/libunwind/test/unwind_leaffunction.pass.cpp
index c1b223bb6966..8c9912e3c386 100644
--- a/libunwind/test/unwind_leaffunction.pass.cpp
+++ b/libunwind/test/unwind_leaffunction.pass.cpp
@@ -8,7 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 // Ensure that leaf function can be unwund.
-// REQUIRES: target={{(aarch64|s390x|x86_64)-.+linux.*}}
+// REQUIRES: target={{(aarch64|riscv64|s390x|x86_64)-.+linux.*}}
 
 // TODO: Figure out why this fails with Memory Sanitizer.
 // XFAIL: msan