> On Jan 11, 2016, at 1:13 PM, Jason Gunthorpe <jgunthorpe@xxxxxxxxxxxxxxxxxxxx> wrote: > > On Mon, Jan 11, 2016 at 12:57:25PM -0500, Mike Marciniszyn wrote: >> From: Vinit Agnihotri <vinit.abhay.agnihotri@xxxxxxxxx> >> >> The current code is problematic when the QP creation and ipoib is used to >> support NFS and NFS desires to do IO for paging purposes. In that case, the >> GFP_KERNEL allocation in qib_qp.c causes a deadlock in tight memory >> situations. > > Are you trying to do swap over NFS? I didn't think that worked > reliably, or has that changed? Swap on NFS is officially supported. Mel Gorman put in some work a while back to get it in shape. > It doesn't make much sense for one driver to have a different GFP > policy for some calls compared with other drivers. Are you sure the > GFP agrument shouldn't be pushed up to the real caller? -- Chuck Lever -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html