[llvm] edc8388 - [LLVM] Add file magic detection for SPIR-V files. (#75363)

[via llvm-commits]

Author: Joseph Huber
Date: 2023-12-13T20:39:50-06:00
New Revision: edc83886d479e110c87d104e7241ce67ee1b6316

URL: https://github.com/llvm/llvm-project/commit/edc83886d479e110c87d104e7241ce67ee1b6316
DIFF: https://github.com/llvm/llvm-project/commit/edc83886d479e110c87d104e7241ce67ee1b6316.diff

LOG: [LLVM] Add file magic detection for SPIR-V files. (#75363)

Summary:
More SPIR-V related patches are being upstreamed. We should add support
to detect when a binary file is SPIR-V. This will be used in the future
when support for SPIR-V is added to the offloading runtime or more
support for bundling.

The magic number is described in the official documentation:
https://registry.khronos.org/SPIR-V/specs/1.0/SPIRV.html#Magic. Notably,
SPIR-V files are streams of 32-bit words. This means that the magic
numbers differ depending on the endianness. Here we simply check the
strandard and byte-reversed versions.

Added: 
    

Modified: 
    llvm/include/llvm/BinaryFormat/Magic.h
    llvm/lib/BinaryFormat/Magic.cpp
    llvm/lib/Object/Binary.cpp
    llvm/lib/Object/ObjectFile.cpp
    llvm/unittests/BinaryFormat/TestFileMagic.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/BinaryFormat/Magic.h b/llvm/include/llvm/BinaryFormat/Magic.h
index a28710dcdfaf2c..c635a269576587 100644
--- a/llvm/include/llvm/BinaryFormat/Magic.h
+++ b/llvm/include/llvm/BinaryFormat/Magic.h
@@ -57,6 +57,7 @@ struct file_magic {
     dxcontainer_object,        ///< DirectX container file
     offload_bundle,            ///< Clang offload bundle file
     offload_bundle_compressed, ///< Compressed clang offload bundle file
+    spirv_object,              ///< A binary SPIR-V file
   };
 
   bool is_object() const { return V != unknown; }

diff  --git a/llvm/lib/BinaryFormat/Magic.cpp b/llvm/lib/BinaryFormat/Magic.cpp
index 255937a5bdd04a..45a0b7e11452b4 100644
--- a/llvm/lib/BinaryFormat/Magic.cpp
+++ b/llvm/lib/BinaryFormat/Magic.cpp
@@ -72,6 +72,14 @@ file_magic llvm::identify_magic(StringRef Magic) {
   case 0x03:
     if (startswith(Magic, "\x03\xF0\x00"))
       return file_magic::goff_object;
+    // SPIR-V format in little-endian mode.
+    if (startswith(Magic, "\x03\x02\x23\x07"))
+      return file_magic::spirv_object;
+    break;
+
+  case 0x07: // SPIR-V format in big-endian mode.
+    if (startswith(Magic, "\x07\x23\x02\x03"))
+      return file_magic::spirv_object;
     break;
 
   case 0x10:

diff  --git a/llvm/lib/Object/Binary.cpp b/llvm/lib/Object/Binary.cpp
index 0ee9f7fac448a2..0b9d95485287dc 100644
--- a/llvm/lib/Object/Binary.cpp
+++ b/llvm/lib/Object/Binary.cpp
@@ -89,6 +89,7 @@ Expected<std::unique_ptr<Binary>> object::createBinary(MemoryBufferRef Buffer,
   case file_magic::dxcontainer_object:
   case file_magic::offload_bundle:
   case file_magic::offload_bundle_compressed:
+  case file_magic::spirv_object:
     // Unrecognized object file format.
     return errorCodeToError(object_error::invalid_file_type);
   case file_magic::offload_binary:

diff  --git a/llvm/lib/Object/ObjectFile.cpp b/llvm/lib/Object/ObjectFile.cpp
index 428166f58070d0..ca921836b7f65a 100644
--- a/llvm/lib/Object/ObjectFile.cpp
+++ b/llvm/lib/Object/ObjectFile.cpp
@@ -160,6 +160,7 @@ ObjectFile::createObjectFile(MemoryBufferRef Object, file_magic Type,
   case file_magic::dxcontainer_object:
   case file_magic::offload_bundle:
   case file_magic::offload_bundle_compressed:
+  case file_magic::spirv_object:
     return errorCodeToError(object_error::invalid_file_type);
   case file_magic::tapi_file:
     return errorCodeToError(object_error::invalid_file_type);

diff  --git a/llvm/unittests/BinaryFormat/TestFileMagic.cpp b/llvm/unittests/BinaryFormat/TestFileMagic.cpp
index b09a2c07309f82..766f8bfae72b00 100644
--- a/llvm/unittests/BinaryFormat/TestFileMagic.cpp
+++ b/llvm/unittests/BinaryFormat/TestFileMagic.cpp
@@ -87,6 +87,8 @@ const char pdb[] = "Microsoft C/C++ MSF 7.00\r\n\x1a"
                    "DS\x00\x00\x00";
 const char tapi_file[] = "--- !tapi-tbd-v1\n";
 const char tapi_file_tbd_v1[] = "---\narchs: [";
+const char spirv_object_le[] = "\x03\x02\x23\x07";
+const char spirv_object_be[] = "\x07\x23\x02\x03";
 
 TEST_F(MagicTest, Magic) {
   struct type {
@@ -117,6 +119,10 @@ TEST_F(MagicTest, Magic) {
       DEFINE(macho_dynamically_linked_shared_lib_stub),
       DEFINE(macho_dsym_companion),
       DEFINE(macho_kext_bundle),
+      {"spirv_object_le", spirv_object_le, sizeof(spirv_object_le),
+       file_magic ::spirv_object},
+      {"spirv_object_be", spirv_object_be, sizeof(spirv_object_be),
+       file_magic ::spirv_object},
       DEFINE(windows_resource),
       DEFINE(pdb),
       {"ms_dos_stub_broken", ms_dos_stub_broken, sizeof(ms_dos_stub_broken),