2009/5/31 Martin Fuzzey <mfuzzey@xxxxxxxxx>: > Hi, > I've found out why test13 is failing for me on i.MX21. I don't think > it's related to my HCD but I'm not sure if it's an ARM or USB problem : > > When the problem occurs I noticed that both the setup phase buffer and > the data phase buffer are in the same 32 byte block. > As dma_get_cache_alignment() returns 32 on this platform I believe they > share a cache line. > > So this means that when performing the GET_STATUS request the usb core > is calling: > dma_map_single(DMA_TO_DEVICE) for the 8 byte setup buffer > dma_map_single(DMA_FROM_DEVICE) for the 2 byte data buffer > > and that when the problem occurs both buffers are in the same cache line.. > This causes the data seen in main memory for the data buffer to be > incorrect. > > Attached is a patch to demonstrate the problem. > It adds a new usbtest case (#20) which uses the -s parameter to mean > alignment. > It then just does GET_STATUS requests in a loop (without halts or > anything else). > > So > ./testusb -c 1000 -s 32 -a -t 20 never fails > whereas > ./testusb -c 1000 -s 16 -a -t 20 fails within a few iterations > > I'm not sure how to fix this - normally the setup buffer and data > buffers are obtained from separate kmallocs - I was just unlucky to get > nearby addresses. No, it is nothing to do with USB, it is a rule that buffer allocated by kmalloc() is cache-line aligned. Thanks. -- Lei Ming -- To unsubscribe from this list: send the line "unsubscribe linux-usb" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
