Struct mmtk::util::alloc::immix_allocator::ImmixAllocator

#[repr(C)]
pub struct ImmixAllocator<VM: VMBinding> {
    pub tls: VMThread,
    pub bump_pointer: BumpPointer,
    space: &'static ImmixSpace<VM>,
    context: Arc<AllocatorContext<VM>>,
    hot: bool,
    copy: bool,
    pub(super) large_bump_pointer: BumpPointer,
    request_for_large: bool,
    line: Option<Line>,
}

Immix allocator

Fields

tls: VMThread

VMThread associated with this allocator instance

bump_pointer: BumpPointer

The fastpath bump pointer.

space: &'static ImmixSpace<VM>

Space instance associated with this allocator instance.

context: Arc<AllocatorContext<VM>>

hot: bool

unused

copy: bool

Is this a copy allocator?

large_bump_pointer: BumpPointer

Bump pointer for large objects

request_for_large: bool

Is the current request for large or small?

line: Option<Line>

Hole-searching cursor

Implementations

impl<VM: VMBinding> ImmixAllocator<VM>

pub(crate) fn reset(&mut self)

impl<VM: VMBinding> ImmixAllocator<VM>

pub(crate) fn new( tls: VMThread, space: Option<&'static dyn Space<VM>>, context: Arc<AllocatorContext<VM>>, copy: bool ) -> Self

pub(crate) fn immix_space(&self) -> &'static ImmixSpace<VM>

fn overflow_alloc( &mut self, size: usize, align: usize, offset: usize ) -> Address

Large-object (larger than a line) bump allocation.

fn alloc_slow_hot( &mut self, size: usize, align: usize, offset: usize ) -> Address

Bump allocate small objects into recyclable lines (i.e. holes).

fn acquire_recyclable_lines( &mut self, size: usize, align: usize, offset: usize ) -> bool

Search for recyclable lines.

fn acquire_recyclable_block(&mut self) -> bool

Get a recyclable block from ImmixSpace.

fn acquire_clean_block( &mut self, size: usize, align: usize, offset: usize ) -> Address

fn require_new_block( &mut self, size: usize, align: usize, offset: usize ) -> bool

Return whether the TLAB has been exhausted and we need to acquire a new block. Assumes that the buffer limits have been restored using ImmixAllocator::restore_limit_for_stress. Note that this function may implicitly change the limits of the allocator.

fn set_limit_for_stress(&mut self)

Set fake limits for the bump allocation for stress tests. The fake limit is the remaining thread local buffer size, which should be always smaller than the bump cursor. This method may be reentrant. We need to check before setting the values.

fn restore_limit_for_stress(&mut self)

Restore the real limits for the bump allocation so we can properly do a thread local allocation. The fake limit is the remaining thread local buffer size, and we restore the actual limit from the size and the cursor. This method may be reentrant. We need to check before setting the values.

Trait Implementations

impl<VM: VMBinding> Allocator<VM> for ImmixAllocator<VM>

fn alloc_slow_once( &mut self, size: usize, align: usize, offset: usize ) -> Address

Acquire a clean block from ImmixSpace for allocation.

fn alloc_slow_once_precise_stress( &mut self, size: usize, align: usize, offset: usize, need_poll: bool ) -> Address

This is called when precise stress is used. We try use the thread local buffer for the allocation (after restoring the correct limit for thread local buffer). If we cannot allocate from thread local buffer, we will go to the actual slowpath. After allocation, we will set the fake limit so future allocations will fail the slowpath and get here as well.

fn get_space(&self) -> &'static dyn Space<VM>

Return the Space instance associated with this allocator instance.

fn get_context(&self) -> &AllocatorContext<VM>

Return the context for the allocator.

fn does_thread_local_allocation(&self) -> bool

Return if this allocator can do thread local allocation. If an allocator does not do thread local allocation, each allocation will go to slowpath and will have a check for GC polls.

fn get_thread_local_buffer_granularity(&self) -> usize

Return at which granularity the allocator acquires memory from the global space and use them as thread local buffer. For example, the BumpAllocator acquires memory at 32KB blocks. Depending on the actual size for the current object, they always acquire memory of N*32KB (N>=1). Thus the BumpAllocator returns 32KB for this method. Only allocators that do thread local allocation need to implement this method.

fn alloc(&mut self, size: usize, align: usize, offset: usize) -> Address

An allocation attempt. The implementation of this function depends on the allocator used. If an allocator supports thread local allocations, then the allocation will be serviced from its TLAB, otherwise it will default to using the slowpath, i.e. alloc_slow.

fn get_tls(&self) -> VMThread

Return the VMThread associated with this allocator instance.

fn alloc_slow(&mut self, size: usize, align: usize, offset: usize) -> Address

Slowpath allocation attempt. This function is explicitly not inlined for performance considerations.

fn alloc_slow_inline( &mut self, size: usize, align: usize, offset: usize ) -> Address

Slowpath allocation attempt. This function executes the actual slowpath allocation. A slowpath allocation in MMTk attempts to allocate the object using the per-allocator definition of alloc_slow_once. This function also accounts for increasing the allocation bytes in order to support stress testing. In case precise stress testing is being used, the alloc_slow_once_precise_stress function is used instead.

fn alloc_slow_once_traced( &mut self, size: usize, align: usize, offset: usize ) -> Address

A wrapper method for alloc_slow_once to insert USDT tracepoints.

fn on_mutator_destroy(&mut self)

The crate::plan::Mutator that includes this allocator is going to be destroyed. Some allocators may need to save/transfer its thread local data to the space.