On Fri, Dec 20, 2019 at 07:32:16PM +0000, Alexey Brodkin wrote: > Well it somehow used to work for quite some time now with the data-buffer > being allocated with 4 words offset (which is 16 bytes for 32-bit platform 3 words, devres_node is 3 words. Which is exactly why we had to change it, the odd alignment caused ARC to explode. > and 32 for 64-bit which is still much less than mentioned 128 bytes). > Or we just never managed to identify those rare cases when data corruption > really happened? The races are rather rare methinks, you'd have to get a list-op concurrently with a DMA. If you get the list corrupted, I'm thinking the crash is fairly likely, albeit really difficuly to debug. > > No matter which way round you allocate devres and data, by necessity > > they're always going to consume the same total amount of memory. > > So then the next option I guess is to separate meta-data from data buffers > completely. Are there any reasons to not do that Dunno, should work just fine I think. > other than the hack we're > discussing here (meta-data in the beginning of the buffer) used to work OK-ish? If meta-data at the beginngin used to work, I don't see why meta-data at the end wouldn't work equally well. They'd be equally broken. But I'm still flabbergasted at the fact that they're doing non-coherent DMA to kmalloc memory, I thought we had a DMA api for that, with a special allocator and everything (but what do I know, I've never used that). _______________________________________________ linux-snps-arc mailing list linux-snps-arc@xxxxxxxxxxxxxxxxxxx http://lists.infradead.org/mailman/listinfo/linux-snps-arc
