/*
	Copyright (c) 2010-2011 Dmitry Vyukov. All rights reserved.

	Redistribution and use in source and binary forms, with or without
	modification, are permitted provided that the following conditions are met:

	   1. Redistributions of source code must retain the above copyright notice,
		  this list of conditions and the following disclaimer.

	   2. Redistributions in binary form must reproduce the above copyright
		  notice, this list of conditions and the following disclaimer in the
		  documentation and/or other materials provided with the distribution.

	THIS SOFTWARE IS PROVIDED BY DMITRY VYUKOV "AS IS" AND ANY EXPRESS OR
	IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
	MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
	EVENT SHALL DMITRY VYUKOV OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
	INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
	(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
	 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
	 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 
	(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
	 THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

	The views and conclusions contained in the software and documentation are
	those of the authors and should not be interpreted as representing official
	policies, either expressed or implied, of Dmitry Vyukov.
*/


#ifndef	__MPMC_BOUNDED_QUEUE__
#define	__MPMC_BOUNDED_QUEUE__


		#include "thread/atomic_value.h"


// Adapted from https://sites.google.com/site/1024cores/home/lock-free-algorithms/queues/bounded-mpmc-queue
template<typename T> class mpmc_bounded_queue
{
	struct cell_t
	{
		GS::Threading::Atomic32 sequence_;
		T			data_;
	};

		static size_t const	cacheline_size = 64;
		typedef char cacheline_pad_t[cacheline_size];

		cacheline_pad_t	pad0_;
		cell_t * const	buffer_;
		size_t const	buffer_mask_;

		cacheline_pad_t	pad1_;
		GS::Threading::Atomic32 enqueue_pos_;
		cacheline_pad_t	pad2_;
		GS::Threading::Atomic32 dequeue_pos_;
		cacheline_pad_t	pad3_;

		void			operator = (mpmc_bounded_queue const&);

		mpmc_bounded_queue(mpmc_bounded_queue const&);

public:

	bool	enqueue(T const &data)
	{
		cell_t *cell;
		int pos = enqueue_pos_.Get();

		for (;;)
		{
			cell = &buffer_[pos & buffer_mask_];
			size_t seq = cell->sequence_.Get();

			intptr_t dif = (intptr_t)seq - (intptr_t)pos;

			if (dif == 0)
			{
				if (enqueue_pos_.Cas(pos, pos + 1) == pos)
					break;
			}
			else if (dif < 0)
				return false;
			else
				pos = enqueue_pos_.Get();
		}

		cell->data_ = data;
		cell->sequence_.Set(pos + 1);
		return true;
	}
	bool	dequeue(T &data)
	{
		cell_t *cell;
		int pos = dequeue_pos_.Get();

		for (;;)
		{
			cell = &buffer_[pos & buffer_mask_];
			size_t seq = cell->sequence_.Get();

			intptr_t dif = (intptr_t)seq - (intptr_t)(pos + 1);

			if	(dif == 0)
			{
				if	(dequeue_pos_.Cas(pos, pos + 1) == pos)
					break;
			}
			else if	(dif < 0)
				return false;
			else
				pos = dequeue_pos_.Get();
		}
		data = cell->data_;
		cell->sequence_.Set(pos + buffer_mask_ + 1);

		return true;
	}

	mpmc_bounded_queue(size_t buffer_size) : buffer_(new cell_t [buffer_size]), buffer_mask_(buffer_size - 1)
	{
		for (size_t i = 0; i != buffer_size; i += 1)
			buffer_[i].sequence_.Set(i);

		enqueue_pos_.Set(0);
		dequeue_pos_.Set(0);
	}
	~mpmc_bounded_queue()
	{
		delete [] buffer_;
	}
}; 


#endif	// __MPMC_BOUNDED_QUEUE__