Message ID | 20170828152254.GB7867@obsidianresearch.com (mailing list archive) |
---|---|
State | Accepted |
Headers | show |
On 8/28/17 8:22 AM, Jason Gunthorpe wrote: > Adit: vmw_rdma is also missing, can you test it? This is probably > the fix: > > diff --git a/kernel-boot/rdma-description.rules b/kernel-boot/rdma-description.rules > index f37e6a86f21efc..bb33dce40bd621 100644 > --- a/kernel-boot/rdma-description.rules > +++ b/kernel-boot/rdma-description.rules > @@ -34,6 +34,7 @@ DRIVERS=="hns", ENV{ID_RDMA_ROCE}="1" > DRIVERS=="mlx4_core", ENV{ID_RDMA_ROCE}="1" > DRIVERS=="mlx5_core", ENV{ID_RDMA_ROCE}="1" > DRIVERS=="qede", ENV{ID_RDMA_ROCE}="1" > +DRIVERS=="vmw_pvrdma", ENV{ID_RDMA_ROCE}="1" > DEVPATH=="*/infiniband/rxe*", ATTR{parent}=="*", ENV{ID_RDMA_ROCE}="1" Thanks. Do I need to generate rpms to test this to install the udev rules? -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Aug 28, 2017 at 10:23:56AM -0700, Adit Ranadive wrote: > On 8/28/17 8:22 AM, Jason Gunthorpe wrote: > > Adit: vmw_rdma is also missing, can you test it? This is probably > > the fix: > > > > diff --git a/kernel-boot/rdma-description.rules b/kernel-boot/rdma-description.rules > > index f37e6a86f21efc..bb33dce40bd621 100644 > > +++ b/kernel-boot/rdma-description.rules > > @@ -34,6 +34,7 @@ DRIVERS=="hns", ENV{ID_RDMA_ROCE}="1" > > DRIVERS=="mlx4_core", ENV{ID_RDMA_ROCE}="1" > > DRIVERS=="mlx5_core", ENV{ID_RDMA_ROCE}="1" > > DRIVERS=="qede", ENV{ID_RDMA_ROCE}="1" > > +DRIVERS=="vmw_pvrdma", ENV{ID_RDMA_ROCE}="1" > > DEVPATH=="*/infiniband/rxe*", ATTR{parent}=="*", ENV{ID_RDMA_ROCE}="1" > > Thanks. Do I need to generate rpms to test this to install the udev rules? For best results, yes.. You have to disable the rdma.service that still comes in the rpms. After booting run udevadm info /sys/class/infiniband/XX where XX is the rdma name of a vmw_pvrdma device, and confirm the ID_RDMA_ROCE is setup. Check the rest of the modules loaded and so forth. Thanks, Jason -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 8/28/17 10:29 AM, Jason Gunthorpe wrote: > On Mon, Aug 28, 2017 at 10:23:56AM -0700, Adit Ranadive wrote: >> On 8/28/17 8:22 AM, Jason Gunthorpe wrote: >>> Adit: vmw_rdma is also missing, can you test it? This is probably >>> the fix: >>> >>> diff --git a/kernel-boot/rdma-description.rules b/kernel-boot/rdma-description.rules >>> index f37e6a86f21efc..bb33dce40bd621 100644 >>> +++ b/kernel-boot/rdma-description.rules >>> @@ -34,6 +34,7 @@ DRIVERS=="hns", ENV{ID_RDMA_ROCE}="1" >>> DRIVERS=="mlx4_core", ENV{ID_RDMA_ROCE}="1" >>> DRIVERS=="mlx5_core", ENV{ID_RDMA_ROCE}="1" >>> DRIVERS=="qede", ENV{ID_RDMA_ROCE}="1" >>> +DRIVERS=="vmw_pvrdma", ENV{ID_RDMA_ROCE}="1" >>> DEVPATH=="*/infiniband/rxe*", ATTR{parent}=="*", ENV{ID_RDMA_ROCE}="1" >> >> Thanks. Do I need to generate rpms to test this to install the udev rules? > > For best results, yes.. You have to disable the rdma.service that still comes in > the rpms. > > After booting run > > udevadm info /sys/class/infiniband/XX > > where XX is the rdma name of a vmw_pvrdma device, and confirm the > ID_RDMA_ROCE is setup. Check the rest of the modules loaded and so forth. Hmm, so I added that line to rdma-description.rules, generated and installed the rpms. udevadm shows me this: $> udevadm info /sys/class/infiniband/vmw_pvrdma0 | grep -i id_rdma E: ID_RDMA_ROCE=1 I'm guessing thats the output you're looking for? Sorry I'm not an expert on the udev stuff but what does the RDMA_ROCE environment correspond to here - just the various modules to be loaded and/or something else? Thanks, Adit -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Tue, Aug 29, 2017 at 05:31:47PM -0700, Adit Ranadive wrote: > > For best results, yes.. You have to disable the rdma.service that still comes in > > the rpms. > > > > After booting run > > > > udevadm info /sys/class/infiniband/XX > > > > where XX is the rdma name of a vmw_pvrdma device, and confirm the > > ID_RDMA_ROCE is setup. Check the rest of the modules loaded and so forth. > > Hmm, so I added that line to rdma-description.rules, generated and installed > the rpms. udevadm shows me this: > > $> udevadm info /sys/class/infiniband/vmw_pvrdma0 | grep -i id_rdma > E: ID_RDMA_ROCE=1 > > I'm guessing thats the output you're looking for? Yes, that is good > Sorry I'm not an expert on the udev stuff but what does the RDMA_ROCE environment > correspond to here - just the various modules to be loaded and/or something else? These variables inside udev are used by other rules inside udev. If anything sets ID_RDMA_ROCE it triggers other udev rules to tell systemd to activate all the roce related rules. I'll send a patch for adding the vmw_pvrdma Jason -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/kernel-boot/rdma-description.rules b/kernel-boot/rdma-description.rules index f37e6a86f21efc..bb33dce40bd621 100644 --- a/kernel-boot/rdma-description.rules +++ b/kernel-boot/rdma-description.rules @@ -34,6 +34,7 @@ DRIVERS=="hns", ENV{ID_RDMA_ROCE}="1" DRIVERS=="mlx4_core", ENV{ID_RDMA_ROCE}="1" DRIVERS=="mlx5_core", ENV{ID_RDMA_ROCE}="1" DRIVERS=="qede", ENV{ID_RDMA_ROCE}="1" +DRIVERS=="vmw_pvrdma", ENV{ID_RDMA_ROCE}="1" DEVPATH=="*/infiniband/rxe*", ATTR{parent}=="*", ENV{ID_RDMA_ROCE}="1" # Setup the usual ID information so that systemd will display a sane name for