lf_alloc-pin.cc File Reference

wait-free concurrent allocator based on pinning addresses. More...

#include <assert.h>
#include <stddef.h>
#include <sys/types.h>
#include <atomic>
#include "lf.h"
#include "my_atomic.h"
#include "my_compiler.h"
#include "my_inttypes.h"
#include "my_sys.h"
#include "my_thread.h"
#include "mysql/service_mysql_alloc.h"
#include "mysys/mysys_priv.h"

Classes
struct	st_match_and_save_arg

Macros
#define	LF_PINBOX_MAX_PINS   65536
#define	pnext_node(P, X)   (*((void **)(((char *)(X)) + (P)->free_ptr_offset)))
#define	anext_node(X)   next_node(&allocator->pinbox, (X))

Functions
static void	lf_pinbox_real_free (LF_PINS *pins)
void	lf_pinbox_init (LF_PINBOX *pinbox, uint free_ptr_offset, lf_pinbox_free_func *free_func, void *free_func_arg)
void	lf_pinbox_destroy (LF_PINBOX *pinbox)
LF_PINS *	lf_pinbox_get_pins (LF_PINBOX *pinbox)
void	lf_pinbox_put_pins (LF_PINS *pins)
static void	add_to_purgatory (LF_PINS *pins, void *addr)
void	lf_pinbox_free (LF_PINS *pins, void *addr)
static int	match_and_save (void *v_el, void *v_arg)
static std::atomic< uchar * > &	next_node (LF_PINBOX *P, uchar *X)
static void	alloc_free (void *v_first, void *v_last, void *v_allocator)
void	lf_alloc_init2 (LF_ALLOCATOR *allocator, uint size, uint free_ptr_offset, lf_allocator_func *ctor, lf_allocator_func *dtor)
	Initialize lock-free allocator. More...
void	lf_alloc_destroy (LF_ALLOCATOR *allocator)
void *	lf_alloc_new (LF_PINS *pins)
uint	lf_alloc_pool_count (LF_ALLOCATOR *allocator)

Detailed Description

wait-free concurrent allocator based on pinning addresses.

It works as follows: every thread (strictly speaking - every CPU, but it's too difficult to do) has a small array of pointers. They're called "pins". Before using an object its address must be stored in this array (pinned). When an object is no longer necessary its address must be removed from this array (unpinned). When a thread wants to free() an object it scans all pins of all threads to see if somebody has this object pinned. If yes - the object is not freed (but stored in a "purgatory"). To reduce the cost of a single free() pins are not scanned on every free() but only added to (thread-local) purgatory. On every LF_PURGATORY_SIZE free() purgatory is scanned and all unpinned objects are freed.

Pins are used to solve ABA problem. To use pins one must obey a pinning protocol:

1. Let's assume that PTR is a shared pointer to an object. Shared means that any thread may modify it anytime to point to a different object and free the old object. Later the freed object may be potentially allocated by another thread. If we're unlucky that other thread may set PTR to point to this object again. This is ABA problem.
2. Create a local pointer LOCAL_PTR.
3. Pin the PTR in a loop: do { LOCAL_PTR= PTR; pin(PTR, PIN_NUMBER); } while (LOCAL_PTR != PTR)
4. It is guaranteed that after the loop has ended, LOCAL_PTR points to an object (or NULL, if PTR may be NULL), that will never be freed. It is not guaranteed though that LOCAL_PTR == PTR (as PTR can change any time)
5. When done working with the object, remove the pin: unpin(PIN_NUMBER)
6. When copying pins (as in the list traversing loop: pin(CUR, 1); while () { do // standard { // pinning NEXT=CUR->next; // loop pin(NEXT, 0); // see #3 } while (NEXT != CUR->next); // above ... ... CUR=NEXT; pin(CUR, 1); // copy pin[0] to pin[1] } which keeps CUR address constantly pinned), note than pins may be copied only upwards (!!!), that is pin[N] to pin[M], M > N.
7. Don't keep the object pinned longer than necessary - the number of pins you have is limited (and small), keeping an object pinned prevents its reuse and cause unnecessary mallocs.

Explanations:

1. The loop is important. The following can occur: thread1> LOCAL_PTR= PTR thread2> free(PTR); PTR=0; thread1> pin(PTR, PIN_NUMBER); now thread1 cannot access LOCAL_PTR, even if it's pinned, because it points to a freed memory. That is, it must verify that it has indeed pinned PTR, the shared pointer.
2. When a thread wants to free some LOCAL_PTR, and it scans all lists of pins to see whether it's pinned, it does it upwards, from low pin numbers to high. Thus another thread must copy an address from one pin to another in the same direction - upwards, otherwise the scanning thread may miss it.

Implementation details:

Pins are given away from a "pinbox". Pinbox is stack-based allocator. It used dynarray for storing pins, new elements are allocated by dynarray as necessary, old are pushed in the stack for reuse. ABA is solved by versioning a pointer - because we use an array, a pointer to pins is 16 bit, upper 16 bits are used for a version.

Macro Definition Documentation

anext_node

#define anext_node

(

X

)

next_node(&allocator->pinbox, (X))

LF_PINBOX_MAX_PINS

#define LF_PINBOX_MAX_PINS   65536

pnext_node

#define pnext_node	(		P,
			X
	)		(*((void **)(((char *)(X)) + (P)->free_ptr_offset)))

Function Documentation

add_to_purgatory()

static void add_to_purgatory ( LF_PINS *  pins, void *  addr  )

inlinestatic

alloc_free()

static void alloc_free ( void *  v_first, void *  v_last, void *  v_allocator  )

static

lf_alloc_destroy()

void lf_alloc_destroy

(

LF_ALLOCATOR *

allocator

)

lf_alloc_init2()

void lf_alloc_init2	(	LF_ALLOCATOR *	allocator,
		uint	size,
		uint	free_ptr_offset,
		lf_allocator_func *	ctor,
		lf_allocator_func *	dtor
	)

Initialize lock-free allocator.

Parameters

allocator	Allocator structure to initialize.
size	A size of an object to allocate.
free_ptr_offset	An offset inside the object to a sizeof(void *) memory that is guaranteed to be unused after the object is put in the purgatory. Unused by ANY thread, not only the purgatory owner. This memory will be used to link waiting-to-be-freed objects in a purgatory list.
ctor	Function to be called after object was malloc()'ed.
dtor	Function to be called before object is free()'d.

lf_alloc_new()

void * lf_alloc_new

(

LF_PINS *

pins

)

lf_alloc_pool_count()

uint lf_alloc_pool_count

(

LF_ALLOCATOR *

allocator

)

lf_pinbox_destroy()

void lf_pinbox_destroy

(

LF_PINBOX *

pinbox

)

lf_pinbox_free()

void lf_pinbox_free	(	LF_PINS *	pins,
		void *	addr
	)

lf_pinbox_get_pins()

LF_PINS * lf_pinbox_get_pins

(

LF_PINBOX *

pinbox

)

lf_pinbox_init()

void lf_pinbox_init	(	LF_PINBOX *	pinbox,
		uint	free_ptr_offset,
		lf_pinbox_free_func *	free_func,
		void *	free_func_arg
	)

lf_pinbox_put_pins()

void lf_pinbox_put_pins

(

LF_PINS *

pins

)

lf_pinbox_real_free()

static void lf_pinbox_real_free ( LF_PINS *  pins )

static

match_and_save()

static int match_and_save ( void *  v_el, void *  v_arg  )

static

next_node()

static std::atomic< uchar * > & next_node ( LF_PINBOX *  P, uchar *  X  )

inlinestatic