____cacheline_aligned is an insufficient guarantee for non-coherent DMA
on platforms with 128 byte cachelines above L1. Switch to the updated
IIO_DMA_MINALIGN definition.
Update the comment to reflect that DMA safety 'may' require separate
cachelines.
Fixes: 54e018da3141 ("iio:ad7266: Mark transfer buffer as __be16")
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20220508175712.647246-10-jic23@kernel.org
struct gpio_desc *gpios[3];
/*
- * DMA (thus cache coherency maintenance) requires the
+ * DMA (thus cache coherency maintenance) may require the
* transfer buffers to live in their own cache lines.
* The buffer needs to be large enough to hold two samples (4 bytes) and
* the naturally aligned timestamp (8 bytes).
struct {
__be16 sample[2];
s64 timestamp;
- } data ____cacheline_aligned;
+ } data __aligned(IIO_DMA_MINALIGN);
};
static int ad7266_wakeup(struct ad7266_state *st)