Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.


Messages - Martin Iturbide

Pages: [1] 2 3 ... 343
1
Programming / Re: Brainstorm: OS/2 on a Different Kernel
« on: June 30, 2025, 11:27:41 pm »
Thanks Igor for the link. I didn't know that Valery wrote those articles.

I know that Yuri Prokushev and Valery worked a lot on the OSFree project, but I was never able to translate their progress to try to send news to the community. I was hoping that OSFree can do some little progress and generate software things that the OS/2 community can use, so they can gain recognition and move forward to the final goal, but it didn't happen.

The idea of using the L4 Microkernel was great, but maybe we need more popular kernel like the Linux one. My idea of using Zircon is just a wild shot brainstorming since I want a Microkernel too.

Regards

2
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 30, 2025, 04:27:05 pm »
Hello Dave.

Thanks, it worked here putting the /share folder in "/usr/local/". It is working fine, windowed and full screen, sounds work and I think that controls and speed are fine.

Just wonder if it can be more easy to the user like having the .exe and the directories on the same folder to ship it in a simple way in the package. I'm attaching the picture of the older build for an idea.

Regards

3
Programming / Re: Brainstorm: OS/2 on a Different Kernel
« on: June 30, 2025, 04:02:14 pm »
What is now left to do is to persuade ChatGPT to write the code for you.
I'm waiting for that AI tool  ;D ;D ;D

4
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 30, 2025, 05:42:22 am »
Hello Dave

Thanks for giving it a try.
In my case I have a problem that can not found the menu.ogg file. (error attached) I tried located the files in different paths and I can not make the .exe find the files. Is there something I'm missing?

Regards

5
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 28, 2025, 07:42:52 pm »
Thanks Dave

Seems to be working fine here.

Do you see that "Amoebax" is also compilable? It uses also zlib , libpng, Ogg, Vorbis

https://github.com/OSSGames/GAME-SDL-PUZZLE-Amoebax

Do you use automake for the ones that have "Makefile.am" ?

Regards

6
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 28, 2025, 05:25:35 pm »
Hello

I contacted the Alizarin Tetris author, because the page says that latest version is 1.0.7 and the source code there is for version 1.0.6.

She replied:

Quote
Martin,

Thanks for letting me know.  It seems this page wasn't updated correctly, and enough time has passed that I'm having trouble finding the files locally.  I recommend working with version 1.0.6.  The main  change for 1.0.7 (which you can duplicate) was to avoid buffer overruns by changing calls to sprintf() to instead use this macro, added to atris.h:

atris.h:#define SPRINTF(buf, fmt, args...) snprintf(buf, sizeof(buf), fmt, ## args)

I hope this is helpful!

        Kiri

It is not a big change, I guess.
Regards

7
Programming / Re: Brainstorm: OS/2 on a Different Kernel
« on: June 28, 2025, 03:32:16 am »
Is the FuchsiaOS Starnix component the same as developing a Developing a Compatibility Layer (Personality)?

That's an excellent and insightful question. You've hit on a core architectural component of Fuchsia that is directly related to your project goal.

**Yes, the FuchsiaOS Starnix component is a specific, real-world example of a "compatibility layer" or "personality."**

Let's break down the relationship:

* **Compatibility Layer / Personality:** This is the general, architectural term for a layer of software that translates the API and ABI of one operating system to another. It's a broad concept. The OS/2-on-Zircon layer you're imagining is a personality layer.
* **Starnix:** This is the **concrete implementation** of a compatibility layer for the Linux ABI on top of the Zircon kernel.

So, Starnix is not just *like* a compatibility layer; it *is* one. It's a perfect case study for your project.

### How Starnix Works (and how it's relevant to your OS/2 goal)

Based on the information available and the design goals of Starnix, here's how it functions:

1.  **User-Space Implementation:** Starnix is not part of the Zircon kernel itself. It's a user-space component, which is a key principle of the microkernel design. This is different from a monolithic kernel where a compatibility layer might be integrated into the kernel.
2.  **ABI Translation:** Starnix acts as a **syscall translator**. When a Linux binary (an unmodified one) running on Fuchsia makes a Linux system call (e.g., `open()`, `read()`, `fork()`), that call is intercepted. Starnix then translates that request into one or more Zircon syscalls and/or IPC messages to other Fuchsia services.
    * **Example:** A Linux program calls `read()` on a file descriptor. Starnix intercepts this, figures out which underlying Fuchsia VFS (Virtual File System) component corresponds to that file descriptor, and then sends a message to that component via a Zircon channel to perform the read operation.
3.  **No Kernel Modifications:** The goal is to run Linux binaries without modifying the Zircon kernel. All the complex logic for Linux compatibility lives in user space within the Starnix component. This makes the kernel more secure and stable, as the compatibility layer's potential bugs are contained.
4.  **Emulation of User-Space Concepts:** Beyond just syscalls, Starnix has to emulate a lot of Linux-specific concepts that don't exist in Zircon's native world, such as:
    * **File Descriptors:** Managing a table of file descriptors for each process.
    * **Filesystem Layout:** Providing a `/dev`, `/proc`, and other Linux-style virtual filesystems.
    * **Process and Thread Semantics:** Replicating the behavior of `fork()`, `exec()`, signals, and process groups.
    * **Networking:** Translating Linux network socket calls to Zircon's network stack.

### Analogy to Your Project

Your proposed **OS/2 Personality Layer on Zircon** would be the Starnix equivalent for OS/2.

| **Concept** | **Fuchsia/Linux World** | **Your Proposed OS/2 World** |
| --------------------------------- | ---------------------------- | ---------------------------- |
| **Microkernel** | Zircon                       | Zircon                       |
| **Compatibility Layer / Runner** | Starnix                      | Your OS/2 Personality Layer  |
| **"Untouched" Binaries** | Linux binaries               | OS/2 binaries (LX format)    |
| **System Call to Translate** | Linux ABI (syscalls)         | OS/2 ABI (`Dos*`, `Win*`)      |
| **Source Code for Reference** | Starnix Source Code          | OSFree, 2ine, OS2Linux source |

**In short, studying the Starnix source code would be a brilliant way to learn how to approach your OS/2 project.** It's a living, working example of exactly the kind of architecture you need to build. You can see how they intercept system calls, manage state, and translate requests from one ABI to another.

The challenges you would face would be similar, but for the OS/2 ABI instead of the Linux ABI:

* **Understanding the ABI:** You need to map every OS/2 system call to Zircon primitives.
* **Emulating Behavior:** Replicating OS/2's memory model, IPC, and resource management.
* **Building User-Space Services:** Creating an HPFS filesystem driver and other services that integrate with Zircon.

The Starnix component is proof that this architectural approach is feasible for running unmodified binaries on a microkernel like Zircon. Your task would be to do the same for the OS/2 ABI instead of the Linux ABI.

8
Programming / Re: Brainstorm: OS/2 on a Different Kernel
« on: June 27, 2025, 04:01:02 pm »
There are three open source projects that tried to replicate the OS/2 functionality, osfree, 2ine and OS2Linux. Do you know those? How this source code can help?

Yes, I am aware of **OSFree**, **2ine (or TwoIne)**, and **OS2Linux**. These projects are highly relevant to your stated goal of running OS/2 user-space components, especially the "untouched" aspect, as they directly grapple with the challenges of OS/2's Application Binary Interface (ABI) and API compatibility.

Here's an overview of each and how their source code could potentially help:

### 1. OSFree

* **What it is:** OSFree is an ambitious project aiming to create a free, open-source, and compatible replacement for the OS/2 operating system. Its goal is to provide a modern, stable, and secure platform that can run existing OS/2 applications. It seeks to re-implement the OS/2 kernel and its user-space components from scratch, following the original OS/2 architecture as closely as possible.
* **Key Relevance:** OSFree is perhaps the most direct reference for your goal. Its core effort lies in understanding and replicating the OS/2 kernel's internal workings and, crucially, the **OS/2 API and ABI**. If they've successfully managed to get any OS/2 applications running, their code base will contain the fundamental mappings between OS/2 system calls/data structures and their own re-implementation.
* **How its source code can help:**
    * **OS/2 API and ABI Documentation (De Facto):** The OSFree source code acts as a de facto specification for how OS/2 system calls (`Dos*` functions, `Win*` functions) are implemented and what parameters they expect. You can trace how they handle things like memory allocation, file I/O, process creation, and IPC.
    * **Kernel Internals:** For a project aiming to put OS/2 userland on a new kernel, understanding how OS/2's kernel handled interrupts, task switching, memory management, and process loading is critical. OSFree's kernel implementation (or parts of it) would demonstrate their approach to these challenges.
    * **Resource Management:** How do they manage handles, semaphores, mutexes, and other OS/2-specific resources? Their implementation would provide insights into the internal state required for OS/2 compatibility.
    * **File System Drivers:** OSFree would need to implement HPFS support. Their source code for this would be invaluable for understanding how to read and write HPFS volumes, which would be essential for any Zircon-based OS/2 environment.
    * **Learning Curve:** Studying OSFree's approach can significantly shorten your own learning curve regarding the intricacies of OS/2's low-level behavior.

### 2. 2ine (TwoIne)

* **What it is:** 2ine (TwoIne) is a project focused on providing an OS/2 compatibility layer *on top of Linux*. It aims to run OS/2 applications natively on a Linux kernel, much like Wine runs Windows applications on Linux. This means it implements the OS/2 APIs and ABIs by translating them into Linux system calls.
* **Key Relevance:** This project is *extremely* relevant to your goal. While you're targeting Zircon, the fundamental problem 2ine solves is the same: how to make OS/2 binaries run on a foreign kernel without modification. Their work directly addresses the "untouched user-space components" aspect.
* **How its source code can help:**
    * **API Translation Logic:** This is where 2ine shines for your purpose. You can examine their code to see exactly how they translate specific OS/2 API calls (e.g., `DosCreateThread`, `DosOpen`, `DosRead`) into equivalent Linux system calls. While your target is Zircon, the *logic* of the translation (e.g., "an OS/2 mutex maps to these `futex` operations," or "an OS/2 file handle is managed this way") will be directly applicable. You'd just swap out the Linux syscalls for Zircon ones.
    * **Dynamic Linker (Loader):** How does 2ine load OS/2's LX (Linear eXecutable) format executables and resolve their dependencies on OS/2 DLLs? Their linker code would show how to handle OS/2's specific module format, import/export tables, and dynamic linking mechanisms. This is crucial for running "untouched" binaries.
    * **Emulation of OS/2 Data Structures:** OS/2 applications often expect certain kernel data structures (e.g., the Process Information Block, Thread Information Block) to be present at specific addresses or in a specific format. 2ine would have code that emulates these structures.
    * **Handling of OS/2 Specifics:** They would have dealt with OS/2's unique aspects like semaphores, queues, segmented memory management (to the extent required for compatibility), and exception handling.

### 3. OS2Linux

* **What it is:** OS2Linux seems to be a less active or perhaps earlier project similar in concept to 2ine, aiming to run OS/2 applications on Linux. Information on it is sometimes conflated with the idea of a Linux kernel *running on* OS/2 hardware, or OS/2 applications running *under* Linux. Historically, it appears to be another attempt at OS/2 API/ABI compatibility on a Linux base.
* **Key Relevance:** If you can find its source code, it would offer another perspective on the same problem 2ine tackles. Different projects might have different approaches to solving the same API/ABI compatibility issues, providing alternative solutions or confirming common patterns.
* **How its source code can help:**
    * **Alternative Approaches:** It might offer different strategies for handling complex OS/2 features or optimizations that 2ine might not employ, or vice-versa.
    * **Validation:** If multiple projects converge on similar translation strategies for core APIs, it gives you higher confidence in those approaches.
    * **Debugging Insights:** Examining their issue trackers or commit messages might reveal common pitfalls and challenges encountered when trying to achieve OS/2 binary compatibility.

### General Advice for Using their Source Code

1.  **Start with the Core APIs:** Focus on `DOSCALLS.DLL` and the most fundamental `Dos*` functions first. These are the foundation upon which everything else builds.
2.  **Understand the LX Executable Format:** All OS/2 applications use the Linear Executable (LX) format. You'll need to understand how to parse it to load the code, data, and fixups correctly into Zircon's memory space.
3.  **Prioritize Process and Thread Management:** How are processes and threads created, managed, and scheduled? How are context switches handled?
4.  **Memory Management:** How do they handle memory allocation, shared memory, and segment/selector emulation (if needed) for 32-bit flat model applications.
5.  **I/O and File Systems:** This will be a significant challenge. See how they handle file operations and network I/O.
6.  **Use a Debugger:** The OS/2 Kernel Debugger (`KDB`) information you provided earlier (establishing interrupt vectors, setting breakpoints at `VMINT21`) would be invaluable if you were debugging an actual OS/2 system. For reverse-engineering, a user-mode debugger that can trace calls into the kernel would be helpful when running OS/2 apps on a real OS/2 system to understand their behavior.

By carefully studying the source code of these projects, especially 2ine for its direct focus on user-space compatibility and OSFree for its comprehensive re-implementation, you can gain invaluable insights and a significant head start in understanding the complexities of OS/2's internals and how to potentially bridge them to a modern microkernel like Zircon.

9
Programming / Re: Brainstorm: OS/2 on a Different Kernel
« on: June 27, 2025, 03:33:13 pm »
Hello

I algo got to discuss the idea of it, but this time using the Zircon kernel, with the Gemini AI.

How do you think we can replace the OS/2 kernel with the FuchsiaOS kernel?

Replacing the OS/2 kernel with the Fuchsia OS kernel (Zircon) would be an incredibly complex and challenging undertaking, far beyond a simple swap. Here's a breakdown of why and what it would entail:

### Fundamental Architectural Differences

1.  **Kernel Type:**
    * **OS/2:** Uses a hybrid kernel. While it has some modularity, many core services (like memory management, task management, interprocess communication, and basic device management) run in the kernel space.
    * **Fuchsia (Zircon):** Is a microkernel. This means only the absolute bare minimum (primitives for processes, threads, virtual memory, IPC, and object management) resides in the kernel. Most traditional OS services like file systems, network stacks, and device drivers run as separate user-space processes. This is a fundamental philosophical difference in how the OS operates and manages resources.

2.  **Design Philosophy:**
    * **OS/2:** Evolved from a DOS-like environment, designed for desktop PCs, with a focus on multitasking and backward compatibility with DOS and Windows applications (via WIN-OS/2). It leverages the protected mode features of Intel 80x86 processors.
    * **Fuchsia:** Built from the ground up for modern computing, with a strong emphasis on security, updatability, and adaptability across a wide range of devices (from embedded systems to smartphones and desktops). It uses a capability-based security model, where applications have no ambient authority and must be explicitly granted access to resources.

3.  **API/ABI Differences:**
    * **OS/2:** Has its own unique set of APIs (Application Programming Interfaces) for system calls and interacting with the kernel. Existing OS/2 applications are built against these APIs.
    * **Fuchsia (Zircon):** Exposes its own set of syscalls, which are very different from traditional Unix-like or Windows/OS/2 APIs. There's no inherent compatibility at the API or ABI (Application Binary Interface) level.

4.  **Hardware Abstraction and Drivers:**
    * **OS/2:** Relies on its own set of device drivers, which are tightly integrated with its kernel architecture.
    * **Fuchsia:** Has a completely different driver model, with drivers often running in user space as isolated components. Existing OS/2 drivers would be completely incompatible.

5.  **Runtime Environment and Languages:**
    * **OS/2:** Applications are typically written in C/C++ and interact directly with OS/2 APIs.
    * **Fuchsia:** While it supports C++, it heavily leverages Dart and the Flutter framework for its user interface and application development. Components are often written in safe languages like Rust.

### Challenges of Replacement

Given these differences, simply "replacing" the OS/2 kernel with Zircon isn't feasible. It would be more akin to building a completely new OS/2-compatible operating system on top of the Zircon kernel. Here are the major challenges:

1.  **Reimplementing OS/2 APIs on Zircon:** This is the biggest hurdle. You'd need a comprehensive compatibility layer that translates OS/2 system calls and APIs into equivalent Zircon syscalls and services. This would involve:
    * **Process and Thread Management:** Mapping OS/2's process and thread model to Zircon's.
    * **Memory Management:** Replicating OS/2's memory allocation and protection schemes on top of Zircon's VMOs (Virtual Memory Objects) and regions.
    * **Interprocess Communication:** Translating OS/2's IPC mechanisms (shared memory, named pipes, semaphores) to Zircon's message passing and object-based communication.
    * **File Systems:** Developing a way for Zircon to understand and interact with OS/2's HPFS (High Performance File System) and FAT file systems, likely requiring user-space file system servers.
    * **Device Management:** Creating a new device driver model or compatibility shims to allow OS/2-era hardware to function, which is a monumental task in itself.

2.  **User-Space Components:** OS/2 has many user-space components (like the Workplace Shell, DLLs, and utilities) that expect specific kernel behaviors and APIs. These would either need to be rewritten or heavily modified to run on Fuchsia's userland architecture.

3.  **Bootstrapping and System Initialization:** The entire boot process and system initialization of OS/2 are specific to its kernel. A Zircon-based system would have a completely different boot sequence.

4.  **Hardware Support:** Zircon currently supports arm64 and x86-64 architectures, with specific CPU support (Intel Broadwell+ and some AMD). Older hardware that OS/2 might run on might not be directly supported by Zircon.

5.  **Lack of Documentation/Expertise:** OS/2 is a legacy operating system with limited active development and public documentation compared to modern OSes. Deep understanding of its internal workings would be critical.

6.  **Performance and Real-time Guarantees:** While Zircon aims for performance, the overhead of a complex compatibility layer might significantly impact the performance of existing OS/2 applications.

### Potential Approach (Highly Theoretical)

If one were to attempt such a monumental task, it would likely involve:

1.  **Developing a Compatibility Layer (Personality):** Similar to how Windows NT had POSIX or OS/2 personalities, a substantial layer would need to be built on top of Zircon to emulate the OS/2 kernel's API and ABI. This would be a massive software engineering effort.
2.  **User-Space Services:** All OS/2 services that traditionally ran in the kernel (or had tight kernel dependencies) would need to be re-architected as Zircon user-space components.
3.  **New Device Drivers:** Writing new drivers for OS/2 compatible hardware that adhere to the Zircon driver model.
4.  **Recompilation/Porting:** Even with a robust compatibility layer, many OS/2 applications might need to be recompiled or at least linked against new compatibility libraries.
5.  **Toolchain and Development Environment:** Setting up a development environment that allows for building and debugging these layers would be complex.

In conclusion, while theoretically possible to build an OS/2-like environment on top of Zircon, it would be an undertaking of immense complexity, effectively a ground-up rewrite rather than a "replacement." The effort would likely far outweigh any potential benefits, given the niche status of OS/2 and the different design goals of Fuchsia.

The goal will be first to have all the "User-Space Components" untouched running over the zircon kernel.

Your goal of running OS/2 user-space components "untouched" over the Zircon kernel is the most challenging aspect of this entire hypothetical project. It implies achieving full binary compatibility for OS/2 applications and libraries. This is an extremely ambitious goal due to the fundamental differences we discussed.

Here's why it's so difficult and what would be required:

### The "Untouched" Challenge: Binary Compatibility

"Untouched" means you cannot recompile, relink, or modify the OS/2 executables (EXEs) and dynamic link libraries (DLLs). They are compiled for a specific instruction set architecture (likely x86, probably 32-bit, possibly even 16-bit segments for older OS/2 versions) and, more importantly, a specific **Application Binary Interface (ABI)**.

The ABI defines:
* **System Call Interface:** How applications interact with the kernel (the specific function numbers, calling conventions, and data structures for system calls).
* **Memory Layout:** How processes are laid out in memory, including stack, heap, and data segments.
* **Data Structures:** The exact size and layout of kernel-provided data structures that user-space components interact with (e.g., process information blocks, file handles).
* **Dynamic Linking:** How DLLs are loaded and resolved at runtime.
* **Exception Handling:** How errors and exceptions are propagated and handled.
* **Processor State:** How registers are used and preserved across calls.

Zircon's ABI is completely different from OS/2's. Zircon is a modern microkernel designed with a capability-based security model and a minimalist set of syscalls. OS/2, while advanced for its time, reflects its 80x86 origins and a hybrid kernel design.

### What "Untouched" Implies: A "Personality" or "Emulator" Layer

To achieve "untouched" execution, you wouldn't just be replacing the kernel; you'd be building a comprehensive **OS/2 personality layer** on top of Zircon. This layer would function similarly to Wine on Linux (for Windows applications) or the compatibility layers used by early versions of Windows NT to run OS/2 applications.

This personality layer would need to:

1.  **Emulate the OS/2 System Call Interface:**
    * **Trap OS/2 System Calls:** Whenever an OS/2 user-space component attempts to make an OS/2 system call (e.g., `DosOpen`, `DosRead`, `DosAllocMem`), this call must be intercepted by your compatibility layer.
    * **Translate to Zircon Syscalls:** Your layer would then translate the semantics of the OS/2 call into one or more Zircon syscalls. This is non-trivial because OS/2's calls often combine functionality that Zircon splits into multiple, more granular operations.
        * **Example (simplified):** An OS/2 `DosOpen` might require Zircon's `zx_file_open` (or similar VFS client calls), potentially `zx_channel_create` for IPC with a file system service, and `zx_rights_duplicate` to set up proper capabilities.
    * **Handle Parameters and Return Values:** The data structures and calling conventions for parameters and return values would need to be meticulously translated. This might involve copying data between different memory layouts, adjusting pointers, and converting status codes.

2.  **Reimplement OS/2 Runtime Libraries (DLLs):**
    * Many OS/2 user-space components rely on core OS/2 DLLs (e.g., `DOSCALLS.DLL`, `PMWIN.DLL`, `KRNL386.SYS` components exposed to userland). These DLLs themselves make kernel calls. Your personality layer would need to provide functional equivalents of these DLLs, implemented using Zircon's primitives.
    * This is not just about translating syscalls, but reimplementing the logic *within* those DLLs.

3.  **Manage OS/2's Memory Model:**
    * OS/2 uses a segmented/flat memory model, relying on the 80x86 MMU for protection and virtual memory. Zircon uses a flat virtual memory model with VMOs (Virtual Memory Objects) and VM address regions.
    * Your layer would need to map OS/2's memory allocation requests (e.g., `DosAllocMem`) onto Zircon's `zx_vmo_create` and `zx_vmar_map`. This includes handling memory protection, shared memory, and demand paging in a way that satisfies OS/2 applications.

4.  **Emulate OS/2's Process and Thread Model:**
    * OS/2 processes and threads have specific states, priorities, and scheduling behaviors. Your layer would need to map these onto Zircon's `zx_process_create`, `zx_thread_create`, and scheduling primitives.
    * This includes handling OS/2-specific constructs like semaphores, mutexes, and event flags, translating them into Zircon's futexes or other synchronization primitives.

5.  **Replicate OS/2's I/O Subsystem:**
    * **File Systems:** This is huge. You'd need a user-space file system driver for HPFS (High Performance File System) and FAT that speaks the Zircon VFS protocol. This driver would then interpret HPFS structures and translate file operations.
    * **Device Drivers:** OS/2 applications often interact with hardware through specific device driver APIs. This would require either:
        * Rewriting all OS/2 device drivers to conform to Zircon's user-space driver model, or
        * Creating an OS/2 "device driver host" that runs in a virtualized environment or a compatibility layer, forwarding I/O requests. This is incredibly complex.
    * **Console/Display Output:** Emulating the OS/2 text mode and Presentation Manager (GUI) environments on a Zircon-based display system. This would be a massive graphics subsystem rewrite/emulation.

6.  **Exception and Signal Handling:**
    * OS/2's structured exception handling and signal mechanisms are distinct. Your layer would need to intercept CPU exceptions (e.g., page faults, division by zero) and translate them into OS/2's exception dispatching, or vice versa, for applications that register their own handlers.

7.  **Resource Management:**
    * OS/2 manages various system resources (handles, timers, queues). These would need to be tracked and managed by your compatibility layer, mapping them to Zircon's object handles and event mechanisms.

### Why this is exceedingly difficult for "Untouched"

* **Undocumented Internals:** Many low-level OS/2 behaviors and undocumented system calls, especially those used by older or specialized applications, would be extremely hard to reverse-engineer and replicate accurately.
* **Performance Overhead:** Such a translation layer would introduce significant performance overhead. Each OS/2 system call would involve multiple Zircon syscalls and considerable data marshaling and unmarshaling.
* **State Management:** Maintaining the correct OS/2 process and system state within a Zircon environment, especially across asynchronous Zircon operations, is a huge challenge.
* **Security Model Mismatch:** OS/2's security model is based on traditional access control lists and user privileges. Zircon's capability-based security model is fundamentally different. Bridging this gap securely, without either compromising Zircon's security or breaking OS/2 applications, is tough.
* **Debugging:** Debugging issues in such a layered system (OS/2 app -> OS/2 personality -> Zircon kernel) would be incredibly complex.

### Initial Steps (Highly Conceptual)

If one were to embark on this, the very first steps would involve:

1.  **Choosing a Target OS/2 Version:** OS/2 evolved. Pick a specific version (e.g., Warp 4) to target, as ABIs could change between versions.
2.  **Deep Dive into OS/2 ABI:** Extensive research and reverse engineering of the OS/2 system call interface, memory management, and process loading mechanisms. This would likely involve using debuggers (like the OS/2 Kernel Debugger you mentioned) and disassemblers on existing OS/2 binaries.
3.  **Minimal Loader and System Call Stub:** Create a basic Zircon application that can load an OS/2 executable (LX format) into a Zircon process and begin executing it. This loader would need to set up the initial memory space.
4.  **Implement Basic Syscall Stubs:** For the most fundamental OS/2 system calls (e.g., `DosExit`, `DosQuerySysInfo`), create stub implementations that return error codes or minimal functionality.
5.  **Iterative Development:** Start with the simplest "Hello World" OS/2 application, trace its system calls, and implement the necessary Zircon translations one by one. This would be a long, painstaking process.

The goal of "untouched" user-space components makes this a task that approaches the complexity of writing a new operating system from scratch, as it requires effectively re-implementing OS/2's core user-kernel interface. It's an intriguing thought experiment, but a monumental engineering challenge in practice.

10
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 27, 2025, 04:58:42 am »
Found a FAQ too, this may be relevant,
Quote
Q: Why am I having so much trouble controlling the pieces?
A: Atris version 1.0.5 introduced the ability to change the keyboard repeat rate. If you find that the pieces move or rotate too quickly for you, consider changing the setting from within the "Special Options" menu. Let us know if you have any other playability problems.

Thanks Dave

I changed on "Special Options" on the Key speed and now it plays perfect for me.

Regards

11
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 25, 2025, 06:08:34 pm »
Thanks Dave

I found some missing files like sounds from the old compile binaries.

In my case it runs too fast when selecting the menus and even the fire shows too fast, but the game is playable.

I added your source code here:
- https://github.com/OS2World/GAME-SDL-PUZZLE-Alizarin_Tetris

I'm attaching the binary release for the public.

Regards

12
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 25, 2025, 04:44:16 am »
It is rockdodger, not RocksnDiamonds which is a completely different game.
Oops... I think I'm falling sleep.

It is fixed now: https://github.com/OS2World/GAME-SDL-ACTION-RockDodger

Regards

13
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 25, 2025, 03:45:39 am »
Hello Dave

Please, if you got the time check also Alizarin Tetris.
- https://github.com/OSSGames/GAME-SDL-PUZZLE-Alizarin_Tetris

Regards

14
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 25, 2025, 03:24:06 am »
Thanks a lot Dave.

Let me know if it is fine how I packed Rock Dodger.

I hope I uploaded the source code correctly on Github:
- https://github.com/OS2World/GAME-SDL-ACTION-RocksnDiamonds

Regards

Update: Corrected version on the file.

15
Article Discussions / Re: Games with older SDL and FSLIB
« on: June 24, 2025, 04:57:12 am »
Thanks for the feedback and for giving it a try.

We don't have an RPM SDL_mixer and rockdodger uses mods for music.

I guess we need to use Andrey Vasilkin SDL 1 port for the missing SDL libs.
- https://hobbesarchive.com/Home/Download?path=/Hobbes/pub/os2/dev/libraries/graphics/SDL_1-2-15_2020-10-05.zip

Regards

Pages: [1] 2 3 ... 343