gh-138122: Implement frame caching in RemoteUnwinder to reduce memory reads (#142137)

This PR implements frame caching in the RemoteUnwinder class to significantly reduce memory reads when profiling remote processes with deep call stacks.

When cache_frames=True, the unwinder stores the frame chain from each sample and reuses unchanged portions in subsequent samples. Since most profiling samples capture similar call stacks (especially the parent frames), this optimization avoids repeatedly reading the same frame data from the target process.

The implementation adds a last_profiled_frame field to the thread state that tracks where the previous sample stopped. On the next sample, if the current frame chain reaches this marker, the cached frames from that point onward are reused instead of being re-read from remote memory.

The sampling profiler now enables frame caching by default.

Python/remote_debug.h

@@ -1102,6 +1102,115 @@ _Py_RemoteDebug_ReadRemoteMemory(proc_handle_t *handle, uintptr_t remote_address
 #endif
 }
 
+#if defined(__linux__) && HAVE_PROCESS_VM_READV
+// Fallback write using /proc/pid/mem
+static int
+_Py_RemoteDebug_WriteRemoteMemoryFallback(proc_handle_t *handle, uintptr_t remote_address, size_t len, const void* src)
+{
+    if (handle->memfd == -1) {
+        if (open_proc_mem_fd(handle) < 0) {
+            return -1;
+        }
+    }
+
+    struct iovec local[1];
+    Py_ssize_t result = 0;
+    Py_ssize_t written = 0;
+
+    do {
+        local[0].iov_base = (char*)src + result;
+        local[0].iov_len = len - result;
+        off_t offset = remote_address + result;
+
+        written = pwritev(handle->memfd, local, 1, offset);
+        if (written < 0) {
+            PyErr_SetFromErrno(PyExc_OSError);
+            return -1;
+        }
+
+        result += written;
+    } while ((size_t)written != local[0].iov_len);
+    return 0;
+}
+#endif // __linux__
+
+// Platform-independent memory write function
+UNUSED static int
+_Py_RemoteDebug_WriteRemoteMemory(proc_handle_t *handle, uintptr_t remote_address, size_t len, const void* src)
+{
+#ifdef MS_WINDOWS
+    SIZE_T written = 0;
+    SIZE_T result = 0;
+    do {
+        if (!WriteProcessMemory(handle->hProcess, (LPVOID)(remote_address + result), (const char*)src + result, len - result, &written)) {
+            PyErr_SetFromWindowsErr(0);
+            DWORD error = GetLastError();
+            _set_debug_exception_cause(PyExc_OSError,
+                "WriteProcessMemory failed for PID %d at address 0x%lx "
+                "(size %zu, partial write %zu bytes): Windows error %lu",
+                handle->pid, remote_address + result, len - result, result, error);
+            return -1;
+        }
+        result += written;
+    } while (result < len);
+    return 0;
+#elif defined(__linux__) && HAVE_PROCESS_VM_READV
+    if (handle->memfd != -1) {
+        return _Py_RemoteDebug_WriteRemoteMemoryFallback(handle, remote_address, len, src);
+    }
+    struct iovec local[1];
+    struct iovec remote[1];
+    Py_ssize_t result = 0;
+    Py_ssize_t written = 0;
+
+    do {
+        local[0].iov_base = (void*)((char*)src + result);
+        local[0].iov_len = len - result;
+        remote[0].iov_base = (void*)((char*)remote_address + result);
+        remote[0].iov_len = len - result;
+
+        written = process_vm_writev(handle->pid, local, 1, remote, 1, 0);
+        if (written < 0) {
+            if (errno == ENOSYS) {
+                return _Py_RemoteDebug_WriteRemoteMemoryFallback(handle, remote_address, len, src);
+            }
+            PyErr_SetFromErrno(PyExc_OSError);
+            _set_debug_exception_cause(PyExc_OSError,
+                "process_vm_writev failed for PID %d at address 0x%lx "
+                "(size %zu, partial write %zd bytes): %s",
+                handle->pid, remote_address + result, len - result, result, strerror(errno));
+            return -1;
+        }
+
+        result += written;
+    } while ((size_t)written != local[0].iov_len);
+    return 0;
+#elif defined(__APPLE__) && defined(TARGET_OS_OSX) && TARGET_OS_OSX
+    kern_return_t kr = mach_vm_write(
+        handle->task,
+        (mach_vm_address_t)remote_address,
+        (vm_offset_t)src,
+        (mach_msg_type_number_t)len);
+
+    if (kr != KERN_SUCCESS) {
+        switch (kr) {
+        case KERN_PROTECTION_FAILURE:
+            PyErr_SetString(PyExc_PermissionError, "Not enough permissions to write memory");
+            break;
+        case KERN_INVALID_ARGUMENT:
+            PyErr_SetString(PyExc_PermissionError, "Invalid argument to mach_vm_write");
+            break;
+        default:
+            PyErr_Format(PyExc_RuntimeError, "Unknown error writing memory: %d", (int)kr);
+        }
+        return -1;
+    }
+    return 0;
+#else
+    Py_UNREACHABLE();
+#endif
+}
+
 UNUSED static int
 _Py_RemoteDebug_PagedReadRemoteMemory(proc_handle_t *handle,
                                       uintptr_t addr,