From mboxrd@z Thu Jan 1 00:00:00 1970 From: linux@armlinux.org.uk (Russell King - ARM Linux) Date: Wed, 8 Mar 2017 19:59:01 +0000 Subject: [Question] devm_kmalloc() for DMA ? In-Reply-To: References: Message-ID: <20170308195901.GD21222@n2100.armlinux.org.uk> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Wed, Mar 08, 2017 at 08:48:31PM +0100, Lars-Peter Clausen wrote: > When the DMA memory is mapped for reading from the device the associated > cachelines are invalidated without writeback. There is no guarantee that > the changes made to the devres_node have made it to main memory yet, or > is there? That is incorrect. Overlapping cache lines are always written back on transitions from CPU to device ownership of the buffer (eg, dma_map_*().) Updates that are made by the CPU on overlapping cache lines while the memory is mapped for DMA may end up doing one of two things: either overwriting the newly DMA'd data, or being lost altogether. In the case of devm_* list manipulations, these should only ever happen during device probe and tear down, and if DMA is active at those times, the driver is seriously buggy. -- RMK's Patch system: http://www.armlinux.org.uk/developer/patches/ FTTC broadband for 0.8mile line: currently at 9.6Mbps down 400kbps up according to speedtest.net.