Update

Improve `align_up` performance using a bitmask

Cargo.lock

@@ -1,5 +1,11 @@
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
+[[package]]
+name = "autocfg"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8aac770f1885fd7e387acedd76065302551364496e46b3dd00860b2f8359b9d"
+
 [[package]]
 name = "bit_field"
 version = "0.9.0"
@@ -17,6 +23,9 @@ name = "blog_os"
 version = "0.1.0"
 dependencies = [
  "bootloader",
+ "conquer-once",
+ "crossbeam-queue",
+ "futures-util",
  "lazy_static",
  "linked_list_allocator",
  "pc-keyboard",
@@ -30,8 +39,27 @@ dependencies = [
 [[package]]
 name = "bootloader"
 version = "0.8.8"
+
+[[package]]
+name = "cfg-if"
+version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c3ed4f735c4e455ba86a3d2939b1c0729414153642106c9d035693355630a42c"
+checksum = "4785bdd1c96b2a846b2bd7cc02e86b6b3dbf14e7e53446c4f54c92a361040822"
+
+[[package]]
+name = "conquer-once"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f7644600a548ecad74e4a918392af1798f7dd045be610be3203b9e129b4f98f"
+dependencies = [
+ "conquer-util",
+]
+
+[[package]]
+name = "conquer-util"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "654fb2472cc369d311c547103a1fa81d467bef370ae7a0680f65939895b1182a"
 
 [[package]]
 name = "cpuio"
@@ -39,6 +67,49 @@ version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "22b8e308ccfc5acf3b82f79c0eac444cf6114cb2ac67a230ca6c177210068daa"
 
+[[package]]
+name = "crossbeam-queue"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c695eeca1e7173472a32221542ae469b3e9aac3a4fc81f7696bcad82029493db"
+dependencies = [
+ "cfg-if",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3c7c73a2d1e9fc0886a08b93e98eb643461230d5f1925e4036204d5f2e261a8"
+dependencies = [
+ "autocfg",
+ "cfg-if",
+]
+
+[[package]]
+name = "futures-core"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f25592f769825e89b92358db00d26f965761e094951ac44d3663ef25b7ac464a"
+
+[[package]]
+name = "futures-task"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7b0a34e53cf6cdcd0178aa573aed466b646eb3db769570841fda0c7ede375a27"
+
+[[package]]
+name = "futures-util"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22766cf25d64306bedf0384da004d05c9974ab104fcc4528f1236181c18004c5"
+dependencies = [
+ "futures-core",
+ "futures-task",
+ "pin-utils",
+]
+
 [[package]]
 name = "lazy_static"
 version = "1.4.0"
@@ -81,6 +152,12 @@ dependencies = [
  "cpuio",
 ]
 
+[[package]]
+name = "pin-utils"
+version = "0.1.0-alpha.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5894c618ce612a3fa23881b152b608bafb8c56cfc22f434a3ba3120b40f7b587"
+
 [[package]]
 name = "scopeguard"
 version = "1.1.0"

Cargo.toml

@@ -26,6 +26,19 @@ linked_list_allocator = "0.8.0"
 version = "1.0"
 features = ["spin_no_std"]
 
+[dependencies.crossbeam-queue]
+version = "0.2.1"
+default-features = false
+features = ["alloc"]
+
+[dependencies.conquer-once]
+version = "0.2.0"
+default-features = false
+
+[dependencies.futures-util]
+version = "0.3.4"
+default-features = false
+features = ["alloc", "async-await"]
 
 [package.metadata.bootimage]
 test-args = [

src/allocator.rs

@@ -1,6 +1,6 @@
 use alloc::alloc::{GlobalAlloc, Layout};
 use core::ptr::null_mut;
-use linked_list_allocator::LockedHeap;
+use fixed_size_block::FixedSizeBlockAllocator;
 use x86_64::{
     structures::paging::{
         mapper::MapToError, FrameAllocator, Mapper, Page, PageTableFlags, Size4KiB,
@@ -8,11 +8,15 @@ use x86_64::{
     VirtAddr,
 };
 
+pub mod bump;
+pub mod fixed_size_block;
+pub mod linked_list;
+
 pub const HEAP_START: usize = 0x_4444_4444_0000;
 pub const HEAP_SIZE: usize = 100 * 1024; // 100 KiB
 
 #[global_allocator]
-static ALLOCATOR: LockedHeap = LockedHeap::empty();
+static ALLOCATOR: Locked<FixedSizeBlockAllocator> = Locked::new(FixedSizeBlockAllocator::new());
 
 pub fn init_heap(
     mapper: &mut impl Mapper<Size4KiB>,
@@ -52,3 +56,27 @@ unsafe impl GlobalAlloc for Dummy {
         panic!("dealloc should be never called")
     }
 }
+
+/// A wrapper around spin::Mutex to permit trait implementations.
+pub struct Locked<A> {
+    inner: spin::Mutex<A>,
+}
+
+impl<A> Locked<A> {
+    pub const fn new(inner: A) -> Self {
+        Locked {
+            inner: spin::Mutex::new(inner),
+        }
+    }
+
+    pub fn lock(&self) -> spin::MutexGuard<A> {
+        self.inner.lock()
+    }
+}
+
+/// Align the given address `addr` upwards to alignment `align`.
+///
+/// Requires that `align` is a power of two.
+fn align_up(addr: usize, align: usize) -> usize {
+    (addr + align - 1) & !(align - 1)
+}

src/allocator/bump.rs

@@ -0,0 +1,61 @@
+use super::{align_up, Locked};
+use alloc::alloc::{GlobalAlloc, Layout};
+use core::ptr;
+
+pub struct BumpAllocator {
+    heap_start: usize,
+    heap_end: usize,
+    next: usize,
+    allocations: usize,
+}
+
+impl BumpAllocator {
+    /// Creates a new empty bump allocator.
+    pub const fn new() -> Self {
+        BumpAllocator {
+            heap_start: 0,
+            heap_end: 0,
+            next: 0,
+            allocations: 0,
+        }
+    }
+
+    /// Initializes the bump allocator with the given heap bounds.
+    ///
+    /// This method is unsafe because the caller must ensure that the given
+    /// memory range is unused. Also, this method must be called only once.
+    pub unsafe fn init(&mut self, heap_start: usize, heap_size: usize) {
+        self.heap_start = heap_start;
+        self.heap_end = heap_start.saturating_add(heap_size);
+        self.next = heap_start;
+    }
+}
+
+unsafe impl GlobalAlloc for Locked<BumpAllocator> {
+    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
+        let mut bump = self.lock(); // get a mutable reference
+
+        let alloc_start = align_up(bump.next, layout.align());
+        let alloc_end = match alloc_start.checked_add(layout.size()) {
+            Some(end) => end,
+            None => return ptr::null_mut(),
+        };
+
+        if alloc_end > bump.heap_end {
+            ptr::null_mut() // out of memory
+        } else {
+            bump.next = alloc_end;
+            bump.allocations += 1;
+            alloc_start as *mut u8
+        }
+    }
+
+    unsafe fn dealloc(&self, _ptr: *mut u8, _layout: Layout) {
+        let mut bump = self.lock(); // get a mutable reference
+
+        bump.allocations -= 1;
+        if bump.allocations == 0 {
+            bump.next = bump.heap_start;
+        }
+    }
+}

src/allocator/fixed_size_block.rs

@@ -0,0 +1,102 @@
+use super::Locked;
+use alloc::alloc::{GlobalAlloc, Layout};
+use core::{
+    mem,
+    ptr::{self, NonNull},
+};
+
+/// The block sizes to use.
+///
+/// The sizes must each be power of 2 because they are also used as
+/// the block alignment (alignments must be always powers of 2).
+const BLOCK_SIZES: &[usize] = &[8, 16, 32, 64, 128, 256, 512, 1024, 2048];
+
+/// Choose an appropriate block size for the given layout.
+///
+/// Returns an index into the `BLOCK_SIZES` array.
+fn list_index(layout: &Layout) -> Option<usize> {
+    let required_block_size = layout.size().max(layout.align());
+    BLOCK_SIZES.iter().position(|&s| s >= required_block_size)
+}
+
+struct ListNode {
+    next: Option<&'static mut ListNode>,
+}
+
+pub struct FixedSizeBlockAllocator {
+    list_heads: [Option<&'static mut ListNode>; BLOCK_SIZES.len()],
+    fallback_allocator: linked_list_allocator::Heap,
+}
+
+impl FixedSizeBlockAllocator {
+    /// Creates an empty FixedSizeBlockAllocator.
+    pub const fn new() -> Self {
+        FixedSizeBlockAllocator {
+            list_heads: [None; BLOCK_SIZES.len()],
+            fallback_allocator: linked_list_allocator::Heap::empty(),
+        }
+    }
+
+    /// Initialize the allocator with the given heap bounds.
+    ///
+    /// This function is unsafe because the caller must guarantee that the given
+    /// heap bounds are valid and that the heap is unused. This method must be
+    /// called only once.
+    pub unsafe fn init(&mut self, heap_start: usize, heap_size: usize) {
+        self.fallback_allocator.init(heap_start, heap_size);
+    }
+
+    /// Allocates using the fallback allocator.
+    fn fallback_alloc(&mut self, layout: Layout) -> *mut u8 {
+        match self.fallback_allocator.allocate_first_fit(layout) {
+            Ok(ptr) => ptr.as_ptr(),
+            Err(_) => ptr::null_mut(),
+        }
+    }
+}
+
+unsafe impl GlobalAlloc for Locked<FixedSizeBlockAllocator> {
+    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
+        let mut allocator = self.lock();
+        match list_index(&layout) {
+            Some(index) => {
+                match allocator.list_heads[index].take() {
+                    Some(node) => {
+                        allocator.list_heads[index] = node.next.take();
+                        node as *mut ListNode as *mut u8
+                    }
+                    None => {
+                        // no block exists in list => allocate new block
+                        let block_size = BLOCK_SIZES[index];
+                        // only works if all block sizes are a power of 2
+                        let block_align = block_size;
+                        let layout = Layout::from_size_align(block_size, block_align).unwrap();
+                        allocator.fallback_alloc(layout)
+                    }
+                }
+            }
+            None => allocator.fallback_alloc(layout),
+        }
+    }
+
+    unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
+        let mut allocator = self.lock();
+        match list_index(&layout) {
+            Some(index) => {
+                let new_node = ListNode {
+                    next: allocator.list_heads[index].take(),
+                };
+                // verify that block has size and alignment required for storing node
+                assert!(mem::size_of::<ListNode>() <= BLOCK_SIZES[index]);
+                assert!(mem::align_of::<ListNode>() <= BLOCK_SIZES[index]);
+                let new_node_ptr = ptr as *mut ListNode;
+                new_node_ptr.write(new_node);
+                allocator.list_heads[index] = Some(&mut *new_node_ptr);
+            }
+            None => {
+                let ptr = NonNull::new(ptr).unwrap();
+                allocator.fallback_allocator.deallocate(ptr, layout);
+            }
+        }
+    }
+}

src/allocator/linked_list.rs

@@ -0,0 +1,145 @@
+use super::{align_up, Locked};
+use alloc::alloc::{GlobalAlloc, Layout};
+use core::{mem, ptr};
+
+struct ListNode {
+    size: usize,
+    next: Option<&'static mut ListNode>,
+}
+
+impl ListNode {
+    const fn new(size: usize) -> Self {
+        ListNode { size, next: None }
+    }
+
+    fn start_addr(&self) -> usize {
+        self as *const Self as usize
+    }
+
+    fn end_addr(&self) -> usize {
+        self.start_addr() + self.size
+    }
+}
+
+pub struct LinkedListAllocator {
+    head: ListNode,
+}
+
+impl LinkedListAllocator {
+    /// Creates an empty LinkedListAllocator.
+    pub const fn new() -> Self {
+        Self {
+            head: ListNode::new(0),
+        }
+    }
+
+    /// Initialize the allocator with the given heap bounds.
+    ///
+    /// This function is unsafe because the caller must guarantee that the given
+    /// heap bounds are valid and that the heap is unused. This method must be
+    /// called only once.
+    pub unsafe fn init(&mut self, heap_start: usize, heap_size: usize) {
+        self.add_free_region(heap_start, heap_size);
+    }
+
+    /// Adds the given memory region to the front of the list.
+    unsafe fn add_free_region(&mut self, addr: usize, size: usize) {
+        // ensure that the freed region is capable of holding ListNode
+        assert!(align_up(addr, mem::align_of::<ListNode>()) == addr);
+        assert!(size >= mem::size_of::<ListNode>());
+
+        // create a new list node and append it at the start of the list
+        let mut node = ListNode::new(size);
+        node.next = self.head.next.take();
+        let node_ptr = addr as *mut ListNode;
+        node_ptr.write(node);
+        self.head.next = Some(&mut *node_ptr)
+    }
+
+    /// Looks for a free region with the given size and alignment and removes
+    /// it from the list.
+    ///
+    /// Returns a tuple of the list node and the start address of the allocation.
+    fn find_region(&mut self, size: usize, align: usize) -> Option<(&'static mut ListNode, usize)> {
+        // reference to current list node, updated for each iteration
+        let mut current = &mut self.head;
+        // look for a large enough memory region in linked list
+        while let Some(ref mut region) = current.next {
+            if let Ok(alloc_start) = Self::alloc_from_region(&region, size, align) {
+                // region suitable for allocation -> remove node from list
+                let next = region.next.take();
+                let ret = Some((current.next.take().unwrap(), alloc_start));
+                current.next = next;
+                return ret;
+            } else {
+                // region not suitable -> continue with next region
+                current = current.next.as_mut().unwrap();
+            }
+        }
+
+        // no suitable region found
+        None
+    }
+
+    /// Try to use the given region for an allocation with given size and alignment.
+    ///
+    /// Returns the allocation start address on success.
+    fn alloc_from_region(region: &ListNode, size: usize, align: usize) -> Result<usize, ()> {
+        let alloc_start = align_up(region.start_addr(), align);
+        let alloc_end = alloc_start.checked_add(size).ok_or(())?;
+
+        if alloc_end > region.end_addr() {
+            // region too small
+            return Err(());
+        }
+
+        let excess_size = region.end_addr() - alloc_end;
+        if excess_size > 0 && excess_size < mem::size_of::<ListNode>() {
+            // rest of region too small to hold a ListNode (required because the
+            // allocation splits the region in a used and a free part)
+            return Err(());
+        }
+
+        // region suitable for allocation
+        Ok(alloc_start)
+    }
+
+    /// Adjust the given layout so that the resulting allocated memory
+    /// region is also capable of storing a `ListNode`.
+    ///
+    /// Returns the adjusted size and alignment as a (size, align) tuple.
+    fn size_align(layout: Layout) -> (usize, usize) {
+        let layout = layout
+            .align_to(mem::align_of::<ListNode>())
+            .expect("adjusting alignment failed")
+            .pad_to_align();
+        let size = layout.size().max(mem::size_of::<ListNode>());
+        (size, layout.align())
+    }
+}
+
+unsafe impl GlobalAlloc for Locked<LinkedListAllocator> {
+    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
+        // perform layout adjustments
+        let (size, align) = LinkedListAllocator::size_align(layout);
+        let mut allocator = self.lock();
+
+        if let Some((region, alloc_start)) = allocator.find_region(size, align) {
+            let alloc_end = alloc_start.checked_add(size).expect("overflow");
+            let excess_size = region.end_addr() - alloc_end;
+            if excess_size > 0 {
+                allocator.add_free_region(alloc_end, excess_size);
+            }
+            alloc_start as *mut u8
+        } else {
+            ptr::null_mut()
+        }
+    }
+
+    unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
+        // perform layout adjustments
+        let (size, _) = LinkedListAllocator::size_align(layout);
+
+        self.lock().add_free_region(ptr as usize, size)
+    }
+}

src/lib.rs

@@ -3,6 +3,11 @@
 #![feature(custom_test_frameworks)]
 #![feature(abi_x86_interrupt)]
 #![feature(alloc_error_handler)]
+#![feature(const_fn)]
+#![feature(alloc_layout_extra)]
+#![feature(const_in_array_repeat_expressions)]
+#![feature(wake_trait)]
+#![feature(async_closure)]
 #![test_runner(crate::test_runner)]
 #![reexport_test_harness_main = "test_main"]
 
@@ -15,6 +20,7 @@ pub mod gdt;
 pub mod interrupts;
 pub mod memory;
 pub mod serial;
+pub mod task;
 pub mod vga_buffer;
 
 pub fn init() {

src/main.rs

@@ -6,7 +6,6 @@
 
 extern crate alloc;
 
-use alloc::{boxed::Box, rc::Rc, vec, vec::Vec};
 use blog_os::println;
 use bootloader::{entry_point, BootInfo};
 use core::panic::PanicInfo;
@@ -16,6 +15,7 @@ entry_point!(kernel_main);
 fn kernel_main(boot_info: &'static BootInfo) -> ! {
     use blog_os::allocator;
     use blog_os::memory::{self, BootInfoFrameAllocator};
+    use blog_os::task::{simple_executor::SimpleExecutor, Task, keyboard};
     use x86_64::VirtAddr;
 
     println!("Hello World{}", "!");
@@ -27,29 +27,10 @@ fn kernel_main(boot_info: &'static BootInfo) -> ! {
 
     allocator::init_heap(&mut mapper, &mut frame_allocator).expect("heap initialization failed");
 
-    // allocate a number on the heap
-    let heap_value = Box::new(41);
-    println!("heap_value at {:p}", heap_value);
-
-    // create a dynamically sized vector
-    let mut vec = Vec::new();
-    for i in 0..500 {
-        vec.push(i);
-    }
-    println!("vec at {:p}", vec.as_slice());
-
-    // create a reference counted vector -> will be freed when count reaches 0
-    let reference_counted = Rc::new(vec![1, 2, 3]);
-    let cloned_reference = reference_counted.clone();
-    println!(
-        "current reference count is {}",
-        Rc::strong_count(&cloned_reference)
-    );
-    core::mem::drop(reference_counted);
-    println!(
-        "reference count is {} now",
-        Rc::strong_count(&cloned_reference)
-    );
+    let mut executor = SimpleExecutor::new();
+    executor.spawn(Task::new(example_task()));
+    executor.spawn(Task::new(keyboard::print_keypresses()));
+    executor.run();
 
     #[cfg(test)]
     test_main();
@@ -58,6 +39,15 @@ fn kernel_main(boot_info: &'static BootInfo) -> ! {
     blog_os::hlt_loop();
 }
 
+async fn async_number() -> u32 {
+    42
+}
+
+async fn example_task() {
+    let number = async_number().await;
+    println!("async number: {}", number);
+}
+
 /// This function is called on panic.
 #[cfg(not(test))]
 #[panic_handler]

src/task/keyboard.rs

@@ -0,0 +1,52 @@
+use conquer_once::spin::OnceCell;
+use crossbeam_queue::ArrayQueue;
+use futures_util::stream::{Stream, StreamExt};
+use core::{pin::Pin, task::{Context, Poll}};
+use pc_keyboard::{layouts, DecodedKey, HandleControl, Keyboard, ScancodeSet1};
+use crate::print;
+
+static SCANCODE_QUEUE: OnceCell<ArrayQueue<u8>> = OnceCell::uninit();
+
+pub struct ScancodeStream {
+    _private: (),
+}
+
+impl ScancodeStream {
+    pub fn new() -> Self {
+        SCANCODE_QUEUE.try_init_once(|| ArrayQueue::new(100))
+            .expect("ScancodeStream::new should only be called once");
+        ScancodeStream {
+            _private: (),
+        }
+    }
+}
+
+impl Stream for ScancodeStream {
+    type Item = u8;
+
+    fn poll_next(self: Pin<&mut Self>, context: &mut Context) -> Poll<Option<u8>> {
+        let queue = SCANCODE_QUEUE
+            .try_get()
+            .expect("scancode queue not initialized");
+        match queue.pop() {
+            Ok(scancode) => Poll::Ready(Some(scancode)),
+            Err(crossbeam_queue::PopError) => Poll::Pending,
+        }
+    }
+}
+
+pub async fn print_keypresses() {
+    let mut scancodes = ScancodeStream::new();
+    let mut keyboard = Keyboard::new(layouts::Us104Key, ScancodeSet1, HandleControl::Ignore);
+
+    while let Some(scancode) = scancodes.next().await {
+        if let Ok(Some(key_event)) = keyboard.add_byte(scancode) {
+            if let Some(key) = keyboard.process_keyevent(key_event) {
+                match key {
+                    DecodedKey::Unicode(character) => print!("{}", character),
+                    DecodedKey::RawKey(key) => print!("{:?}", key),
+                }
+            }
+        }
+    }
+}

src/task/mod.rs

@@ -0,0 +1,22 @@
+use alloc::boxed::Box;
+use core::task::{Context, Poll};
+use core::{future::Future, pin::Pin};
+
+pub mod keyboard;
+pub mod simple_executor;
+
+pub struct Task {
+    future: Pin<Box<dyn Future<Output = ()>>>,
+}
+
+impl Task {
+    pub fn new(future: impl Future<Output = ()> + 'static) -> Task {
+        Task {
+            future: Box::pin(future),
+        }
+    }
+
+    fn poll(&mut self, context: &mut Context) -> Poll<()> {
+        self.future.as_mut().poll(context)
+    }
+}

src/task/simple_executor.rs

@@ -0,0 +1,44 @@
+use super::Task;
+use alloc::{collections::VecDeque, sync::Arc, task::Wake};
+use core::task::{Context, Poll, Waker};
+
+pub struct SimpleExecutor {
+    task_queue: VecDeque<Task>,
+}
+
+impl SimpleExecutor {
+    pub fn new() -> SimpleExecutor {
+        SimpleExecutor {
+            task_queue: VecDeque::new(),
+        }
+    }
+
+    pub fn spawn(&mut self, task: Task) {
+        self.task_queue.push_back(task)
+    }
+
+    pub fn run(&mut self) {
+        while let Some(mut task) = self.task_queue.pop_front() {
+            let waker = DummyWaker.to_waker();
+            let mut context = Context::from_waker(&waker);
+            match task.poll(&mut context) {
+                Poll::Ready(()) => {} // task done
+                Poll::Pending => self.task_queue.push_back(task),
+            }
+        }
+    }
+}
+
+struct DummyWaker;
+
+impl Wake for DummyWaker {
+    fn wake(self: Arc<Self>) {
+        // do nothing
+    }
+}
+
+impl DummyWaker {
+    fn to_waker(self) -> Waker {
+        Waker::from(Arc::new(self))
+    }
+}

tests/heap_allocation.rs

@@ -58,6 +58,18 @@ fn many_boxes() {
     serial_println!("[ok]");
 }
 
+#[test_case]
+fn many_boxes_long_lived() {
+    serial_print!("many_boxes_long_lived... ");
+    let long_lived = Box::new(1); // new
+    for i in 0..HEAP_SIZE {
+        let x = Box::new(i);
+        assert_eq!(*x, i);
+    }
+    assert_eq!(*long_lived, 1); // new
+    serial_println!("[ok]");
+}
+
 #[panic_handler]
 fn panic(info: &PanicInfo) -> ! {
     blog_os::test_panic_handler(info)