Memory-mapped I/O barriers, state of affairs?
in [Kernel]
|
Prev: [PATCH -mm 1/3] proc: get_nr_threads() doesn't need ->siglock any longer
Next: [PATCH 8/8] MAINTAINERS: update kgdb, and debug_core info
From: Leon Woestenberg on 22 Mar 2010 15:20 Hello, searching for good info on device IO racing against host memory writes I came upon this 2006 article: http://lwn.net/Articles/198988/ "there is no guaranteed ordering between writes to regular memory and writes to a memory-mapped I/O range. " What is the current solution for that particular problem, i.e. how should I make sure host memory writes are committed before I have an external DMA device act on it? Thanks, -- Leon Woestenberg. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Andreas Bombe on 22 Mar 2010 16:50 On Mon, Mar 22, 2010 at 08:18:49PM +0100, Leon Woestenberg wrote: > What is the current solution for that particular problem, i.e. how > should I make sure host memory writes are committed before I have an > external DMA device act on it? The dma_sync_* functions, if you reuse DMA buffers without unmapping, take care of that. Otherwise the process of mapping them handles it. Documentation/DMA-API.txt and Documentation/PCI/PCI-DMA-mapping.txt document those functions. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Leon Woestenberg on 22 Mar 2010 18:20 Hello Andreas, all, On Mon, Mar 22, 2010 at 9:16 PM, Andreas Bombe <aeb(a)debian.org> wrote: > On Mon, Mar 22, 2010 at 08:18:49PM +0100, Leon Woestenberg wrote: >> What is the current solution for that particular problem, i.e. how >> should I make sure host memory writes are committed before I have an >> external DMA device act on it? > > The dma_sync_* functions, if you reuse DMA buffers without unmapping, > take care of that. �Otherwise the process of mapping them handles it. > The mapping makes the memory cache-coherent. I already use that. But does that mean that this coherency is guaranteed to occur before I start MMIO access to a device, i.e. is there a guaranteed ordering between the writes? Regards, -- Leon -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Robert Hancock on 22 Mar 2010 20:20
On 03/22/2010 04:12 PM, Leon Woestenberg wrote: > Hello Andreas, all, > > On Mon, Mar 22, 2010 at 9:16 PM, Andreas Bombe<aeb(a)debian.org> wrote: >> On Mon, Mar 22, 2010 at 08:18:49PM +0100, Leon Woestenberg wrote: >>> What is the current solution for that particular problem, i.e. how >>> should I make sure host memory writes are committed before I have an >>> external DMA device act on it? >> >> The dma_sync_* functions, if you reuse DMA buffers without unmapping, >> take care of that. Otherwise the process of mapping them handles it. >> > The mapping makes the memory cache-coherent. I already use that. > > But does that mean that this coherency is guaranteed to occur before I > start MMIO access to a device, i.e. is there a guaranteed ordering > between the writes? Well, for a streaming mapping, the device may not see the write to the memory at all until it's synced or unmapped (for one thing, if the kernel is using swiotlb to map the memory, it's an entirely different piece of memory and it needs to copy the data to where the device can actually see it). For a coherent mapping, however, though I can't say for certain what the behavior is "supposed" to be, many drivers seem to depend on writes to these regions being ordered with respect to regular memory and would break if a particular platform didn't obey that. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |