From mboxrd@z Thu Jan  1 00:00:00 1970
From: Fredrik Noring <noring-zgYzP9v7iJcdnm+yROfE0A@public.gmane.org>
Subject: Re: WARN_ON(irqs_disabled()) in dma_free_attrs?
Date: Sat, 3 Mar 2018 19:19:06 +0100
Message-ID: <20180303181904.GA19076@localhost.localdomain>
References: <20180302180704.GA3846@localhost.localdomain>
	<20180302213711.GA30356@lst.de>
	<20180303082234.GB24991@localhost.localdomain>
	<20180303161249.GA9516@lst.de>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>
Content-Disposition: inline
In-Reply-To: <20180303161249.GA9516-jcswGhMUV9g@public.gmane.org>
List-Unsubscribe: <https://lists.linuxfoundation.org/mailman/options/iommu>,
	<mailto:iommu-request-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org?subject=unsubscribe>
List-Archive: <http://lists.linuxfoundation.org/pipermail/iommu/>
List-Post: <mailto:iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>
List-Help: <mailto:iommu-request-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org?subject=help>
List-Subscribe: <https://lists.linuxfoundation.org/mailman/listinfo/iommu>,
	<mailto:iommu-request-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org?subject=subscribe>
Sender: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
Errors-To: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
To: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>, Alan Stern <stern-nwvwT67g6+6dFdvTe/nMLpVzexx5G7lz@public.gmane.org>
Cc: =?utf-8?Q?J=C3=BCrgen?= Urban <JuergenUrban-Mmb7MZpHnFY@public.gmane.org>, iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, USB list <linux-usb-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
List-Id: iommu@lists.linux-foundation.org

Christoph, Alan,

> If it is allocating / freeing this memory all the time in the hot path
> it should really use a dma pool (see include/ilinux/dmapool.h).
> The dma coherent APIs aren't really built for being called in the
> hot path.

hcd_buffer_free uses a combination of dma pools and dma coherent APIs:

	...
	for (i = 0; i < HCD_BUFFER_POOLS; i++) {
		if (size <= pool_max[i]) {
			dma_pool_free(hcd->pool[i], addr, dma);
			return;
		}
	}
	dma_free_coherent(hcd->self.sysdev, size, addr, dma);

Alan, can dma_free_coherent be delayed to a point when IRQs are enabled?

[ Links to previous messages on this topic are listed below. ]

Fredrik

https://www.spinics.net/lists/linux-usb/msg162817.html
https://lists.linuxfoundation.org/pipermail/iommu/2018-March/026334.html
https://lists.linuxfoundation.org/pipermail/iommu/2018-March/026335.html
https://lists.linuxfoundation.org/pipermail/iommu/2018-March/026336.html
https://lists.linuxfoundation.org/pipermail/iommu/2018-March/026337.html
https://lists.linuxfoundation.org/pipermail/iommu/2018-March/026338.html
https://lists.linuxfoundation.org/pipermail/iommu/2018-March/026339.html