From 540a5904eb5644056f4fcc9a264826e0e40ee385 Mon Sep 17 00:00:00 2001 From: Lancelot SIX Date: Wed, 26 Jul 2023 11:30:56 +0100 Subject: [PATCH] gdb/solib-rocm: Detect SO for unsupported AMDGPU device It is possible to debug a process which uses unsupported AMDGPU devices. In such scenario, we can still use librocm-dbgapi.so to attach to the process and complete the runtime activation sequence. However, when listing shared objects loaded on the AMDGPU devices, we might list SOs loaded on the unsupported devices. If such SO is seen, one of two things can happen. First, if the arch of this device is unknown to BFD, 'gdbarch_find_by_info (gdbarch_info info)' will return the gdbarch matching default_bfd_arch. As a result, rocm_solib_relocate_section_addresses will delegate the relocation operation to svr4_so_ops.relocate_section_addresses, but this makes no sense: this code object was not loaded by the system loader. The second case is if BFD knows the micro-architecture of the device, but dbgapi does not support it. In such case, gdbarch_info_fill will successfully identify an amdgcn architecture (bfd_arch_amdgcn). From there, gdbarch_find_by_info calls amdgpu_gdbarch_init which will fail to query arch specific details from dbgapi and subsequently fail to initialize the gdbarch object. As a result, gdbarch_find_by_info returns nullptr, which will down the line cause some "gdb_assert (gdbarch != nullptr)" assertion failures. This patch proposes to add a check in rocm_solib_bfd_open to ensure that the architecture associated with the code object to open is fully supported by both BFD and amd-dbgapi, and error-out otherwise. Change-Id: Ica97ab7cba45e4944b77d3080c54c1038aaeda54 Approved-By: Pedro Alves --- gdb/solib-rocm.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) diff --git a/gdb/solib-rocm.c b/gdb/solib-rocm.c index 882920a3711..56c210e9fa5 100644 --- a/gdb/solib-rocm.c +++ b/gdb/solib-rocm.c @@ -663,6 +663,56 @@ rocm_solib_bfd_open (const char *pathname) error (_("`%s': ELF file HSA OS ABI version is not supported (%d)."), bfd_get_filename (abfd.get ()), osabiversion); + /* For GDB to be able to use this solib, the exact AMDGPU processor type + must be supported by both BFD and the amd-dbgapi library. */ + const unsigned char gfx_arch + = elf_elfheader (abfd)->e_flags & EF_AMDGPU_MACH ; + const bfd_arch_info_type *bfd_arch_info + = bfd_lookup_arch (bfd_arch_amdgcn, gfx_arch); + + amd_dbgapi_architecture_id_t architecture_id; + amd_dbgapi_status_t dbgapi_query_arch + = amd_dbgapi_get_architecture (gfx_arch, &architecture_id); + + if (dbgapi_query_arch != AMD_DBGAPI_STATUS_SUCCESS + || bfd_arch_info == nullptr) + { + if (dbgapi_query_arch != AMD_DBGAPI_STATUS_SUCCESS + && bfd_arch_info == nullptr) + { + /* Neither of the libraries knows about this arch, so we cannot + provide a human readable name for it. */ + error (_("'%s': AMDGCN architecture %#02x is not supported."), + bfd_get_filename (abfd.get ()), gfx_arch); + } + else if (dbgapi_query_arch != AMD_DBGAPI_STATUS_SUCCESS) + { + gdb_assert (bfd_arch_info != nullptr); + error (_("'%s': AMDGCN architecture %s not supported by " + "amd-dbgapi."), + bfd_get_filename (abfd.get ()), + bfd_arch_info->printable_name); + } + else + { + gdb_assert (dbgapi_query_arch == AMD_DBGAPI_STATUS_SUCCESS); + char *arch_name; + if (amd_dbgapi_architecture_get_info + (architecture_id, AMD_DBGAPI_ARCHITECTURE_INFO_NAME, + sizeof (arch_name), &arch_name) != AMD_DBGAPI_STATUS_SUCCESS) + error ("amd_dbgapi_architecture_get_info call failed for arch " + "%#02x.", gfx_arch); + gdb::unique_xmalloc_ptr arch_name_cleaner (arch_name); + + error (_("'%s': AMDGCN architecture %s not supported."), + bfd_get_filename (abfd.get ()), + arch_name); + } + } + + gdb_assert (gdbarch_from_bfd (abfd.get ()) != nullptr); + gdb_assert (is_amdgpu_arch (gdbarch_from_bfd (abfd.get ()))); + return abfd; } -- 2.30.2