On Wed, 2017-01-11 at 13:26 +0100, Jinpu Wang wrote: > On Mon, Jan 2, 2017 at 1:15 PM, Jinpu Wang <jinpu.wang@profitbricks.c > om> wrote: > > > > Hi Folks, > > > > This is my forth attempt to fix rdma_revolve_addr may resolve to > > first > > port even it's down[1]. > > > > As Jason and Hefty suggested, I now cache port_state in ib_core, > > and > > update cma_resolve_ib_dev and cma_bind_loopback to use it. > > > > 0001-IB-core-add-port-state-cache.patch > > 0002-IB-core-export-ib_get_cached_port_state.patch > > 0003-cma-resolve-to-first-active-ib-port.patch > > 0004-cma-use-cached-port-state-when-bind-loopback.patch > > > > [1]http://marc.info/?l=linux-rdma&m=148102306632521&w=2 > > > > Changes from v1: > > - Add Hefty's Acked-by. > > - rebase on Doug's rdma/k.o/for-4.10 (commit > > 5cc8fabc5e4c588c75a5ec21423e7c3425f69f48) > > - fix a mem leak in ib_cache_setup_one in error case in first > > patch. > > > > -- > Ping Doug? Sorry, I didn't see this before I wrote my last email. You've already captured Sean's acks, that's good. You modified the first patch in a way that negates the comment request I made, so that's fine. But the patches are still coming through mangled. If you look at them in patchworks, you can see telltale signs, such as seeing part of the patch in the patchwork comments and then the full patch later on in the patch section. When I download those patches, they are mangled. You can *not* both send the patch inline and as an attachment. The prefered way to send patches, if your mailer is messing with your submissions, is to use "git send-email" and let it send the patches directly for you. However, this time I have fixed the patches up and applied them, but please don't send mangled patches like this in the future. -- Doug Ledford <dledford@xxxxxxxxxx> GPG KeyID: B826A3330E572FDD Key fingerprint = AE6B 1BDA 122B 23B4 265B 1274 B826 A333 0E57 2FDD
Attachment:
signature.asc
Description: This is a digitally signed message part