Add perf trampoline support for macOS

Author: canova

Python/asm_trampoline.S

@@ -1,13 +1,21 @@
     .text
+#if defined(__APPLE__)
+    .globl	__Py_trampoline_func_start
+#else
     .globl	_Py_trampoline_func_start
+#endif
 # The following assembly is equivalent to:
 # PyObject *
 # trampoline(PyThreadState *ts, _PyInterpreterFrame *f,
 #            int throwflag, py_evaluator evaluator)
 # {
 #     return evaluator(ts, f, throwflag);
 # }
+#if defined(__APPLE__)
+__Py_trampoline_func_start:
+#else
 _Py_trampoline_func_start:
+#endif
 #ifdef __x86_64__
 #if defined(__CET__) && (__CET__ & 1)
     endbr64
@@ -34,9 +42,14 @@ _Py_trampoline_func_start:
     addi    sp,sp,16
     jr      ra
 #endif
+#if defined(__APPLE__)
+    .globl	__Py_trampoline_func_end
+__Py_trampoline_func_end:
+#else
     .globl	_Py_trampoline_func_end
 _Py_trampoline_func_end:
     .section        .note.GNU-stack,"",@progbits
+#endif
 # Note for indicating the assembly code supports CET
 #if defined(__x86_64__) && defined(__CET__) && (__CET__ & 1)
     .section    .note.gnu.property,"a"

Python/perf_jit_trampoline.c

@@ -66,15 +66,19 @@
 #ifdef PY_HAVE_PERF_TRAMPOLINE
 
 /* Standard library includes for perf jitdump implementation */
-#include <elf.h>                  // ELF architecture constants
+#if defined(__linux__)
+#  include <elf.h>                // ELF architecture constants
+#endif
 #include <fcntl.h>                // File control operations
 #include <stdio.h>                // Standard I/O operations
 #include <stdlib.h>               // Standard library functions
 #include <sys/mman.h>             // Memory mapping functions (mmap)
 #include <sys/types.h>            // System data types
 #include <unistd.h>               // System calls (sysconf, getpid)
 #include <sys/time.h>             // Time functions (gettimeofday)
-#include <sys/syscall.h>          // System call interface
+#if defined(__linux__)
+#  include <sys/syscall.h>        // System call interface
+#endif
 
 // =============================================================================
 //                           CONSTANTS AND CONFIGURATION
@@ -102,6 +106,16 @@
  */
 #define PERF_JIT_CODE_PADDING 0x100
 
+
+/* These constants are defined inside <elf.h>, which we can't use outside of linux. */
+#if !defined(__linux__)
+#  define EM_386      3
+#  define EM_X86_64   62
+#  define EM_ARM      40
+#  define EM_AARCH64  183
+#  define EM_RISCV    243
+#endif
+
 /* Convenient access to the global trampoline API state */
 #define trampoline_api _PyRuntime.ceval.perf.trampoline_api
 
@@ -195,7 +209,7 @@ struct BaseEvent {
 typedef struct {
     struct BaseEvent base;   // Common event header
     uint32_t process_id;     // Process ID where code was generated
-    uint32_t thread_id;      // Thread ID where code was generated
+    uint64_t thread_id;      // Thread ID where code was generated
     uint64_t vma;            // Virtual memory address where code is loaded
     uint64_t code_address;   // Address of the actual machine code
     uint64_t code_size;      // Size of the machine code in bytes
@@ -1166,7 +1180,11 @@ static void perf_map_jit_write_entry(void *state, const void *code_addr,
     ev.base.size = sizeof(ev) + (name_length+1) + size;
     ev.base.time_stamp = get_current_monotonic_ticks();
     ev.process_id = getpid();
+#if defined(__APPLE__)
+    pthread_threadid_np(NULL, &ev.thread_id);
+#else
     ev.thread_id = syscall(SYS_gettid);  // Get thread ID via system call
+#endif
     ev.vma = base;                       // Virtual memory address
     ev.code_address = base;              // Same as VMA for our use case
     ev.code_size = size;
@@ -1262,4 +1280,4 @@ _PyPerf_Callbacks _Py_perfmap_jit_callbacks = {
     &perf_map_jit_fini,        // Cleanup function
 };
 
-#endif /* PY_HAVE_PERF_TRAMPOLINE */
+#endif /* PY_HAVE_PERF_TRAMPOLINE */

configure

@@ -3690,12 +3690,13 @@ case "$ac_sys_system" in
 esac
 AC_MSG_RESULT([$SHLIBS])
 
-dnl perf trampoline is Linux specific and requires an arch-specific
+dnl perf trampoline is Linux and macOS specific and requires an arch-specific
 dnl trampoline in assembly.
 AC_MSG_CHECKING([perf trampoline])
 AS_CASE([$PLATFORM_TRIPLET],
   [x86_64-linux-gnu], [perf_trampoline=yes],
   [aarch64-linux-gnu], [perf_trampoline=yes],
+  [darwin], [perf_trampoline=yes],
   [perf_trampoline=no]
 )
 AC_MSG_RESULT([$perf_trampoline])