On Mon, Apr 09, 2018 at 09:52:03AM -0700, Matthew Wilcox wrote: > On Mon, Apr 09, 2018 at 05:39:16PM +0200, Christoph Hellwig wrote: > > blk_get_request is used for pass-through style I/O and thus doesn't need > > GFP_NOIO. > > Obviously GFP_KERNEL is a big improvement over GFP_NOIO! But can we take > it all the way to GFP_USER, if this is always done in the ioctl path > (which it seems to be, except for nfsd, which presumably won't have > a cpuset memory allocation policy ... and if it did, the admin might > appreciate it honouring said policy). GFP_USER claims to be for allocations mapped into userspace, and except for a few outliers that is how we use it. I see no reason to change that here.
