From mboxrd@z Thu Jan 1 00:00:00 1970 From: Adit Ranadive Subject: Re: [PATCH for-next v1 2/2] RDMA/vmw_pvrdma: Update device query parameters and port caps Date: Thu, 24 Aug 2017 14:47:39 -0700 Message-ID: <58ef6e75-a879-e7c5-2c91-8d1f64f1d98f@vmware.com> References: <20170824143338.GB5128@yuvallap> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20170824143338.GB5128@yuvallap> Content-Language: en-US Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Yuval Shaia Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, pv-drivers-pghWNbHTmq7QT0dZR+AlfA@public.gmane.org List-Id: linux-rdma@vger.kernel.org On Thur, Aug 24, 2017 at 07:33:50AM 0700, Yuval Shaia wrote: > On Tue, Aug 22, 2017 at 11:19:01PM -0700, Adit Ranadive wrote: > > Added support for two device caps - max_sge_rd, max_fast_reg_page_list_len > > and the IP_BASED_GIDS port cap flag. > > And IB_PORT_CM_SUP > > > > > Reviewed-by: Jorgen Hansen > > Reviewed-by: Bryan Tan > > Reviewed-by: Aditya Sarwade > > Signed-off-by: Adit Ranadive > > --- > > drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h | 9 ++++++++- > > drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c | 9 +++++++++ > > 2 files changed, 17 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h > > index 3a308ff..df0a6b5 100644 > > --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h > > +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h > > @@ -149,6 +149,13 @@ > > ((_dev->dsr->caps.mode == PVRDMA_DEVICE_MODE_ROCE) && \ > > (PVRDMA_IS_VERSION17(_dev) || PVRDMA_IS_VERSION18(_dev))) > > > > +/* > > + * Get capability values based on device version. > > + */ > > + > > +#define PVRDMA_GET_CAP(_dev, _old_val, _val) \ > > + ((PVRDMA_IS_VERSION18(_dev)) ? _val : _old_val) > > + > > enum pvrdma_pci_resource { > > PVRDMA_PCI_RESOURCE_MSIX, /* BAR0: MSI-X, MMIO. */ > > PVRDMA_PCI_RESOURCE_REG, /* BAR1: Registers, MMIO. */ > > @@ -251,7 +258,7 @@ struct pvrdma_device_caps { > > u8 atomic_ops; /* PVRDMA_ATOMIC_OP_* bits */ > > u8 bmme_flags; /* FRWR Mem Mgmt Extensions */ > > u8 gid_types; /* PVRDMA_GID_TYPE_FLAG_ */ > > - u8 reserved[4]; > > + u32 max_fast_reg_page_list_len; > > }; > > > > struct pvrdma_ring_page_info { > > diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c > > index 2851704..48776f5 100644 > > --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c > > +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c > > @@ -83,6 +83,8 @@ int pvrdma_query_device(struct ib_device *ibdev, > > props->max_qp_wr = dev->dsr->caps.max_qp_wr; > > props->device_cap_flags = dev->dsr->caps.device_cap_flags; > > props->max_sge = dev->dsr->caps.max_sge; > > + props->max_sge_rd = PVRDMA_GET_CAP(dev, dev->dsr->caps.max_sge, > > + dev->dsr->caps.max_sge_rd); > > I tend to agree with Leon on the other thread, i think that the following > code is much more readable: > > props->max_sge_rd = dev->dsr->caps.max_sge; > if (PVRDMA_IS_VERSION18(dev)) > props->max_sge_rd = dev->dsr->caps.max_sge_rd; > > And then in the future add something like this: > if (PVRDMA_IS_VERSION19(dev)) > props->max_sge_rd = dev->dsr->caps.max_sge_19; > > But it is totally up to you. Thanks for taking a look and your suggestion. > > > props->max_cq = dev->dsr->caps.max_cq; > > props->max_cqe = dev->dsr->caps.max_cqe; > > props->max_mr = dev->dsr->caps.max_mr; > > @@ -101,8 +103,14 @@ int pvrdma_query_device(struct ib_device *ibdev, > > (dev->dsr->caps.bmme_flags & PVRDMA_BMME_FLAG_REMOTE_INV) && > > (dev->dsr->caps.bmme_flags & PVRDMA_BMME_FLAG_FAST_REG_WR)) { > > props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; > > + props->max_fast_reg_page_list_len = PVRDMA_GET_CAP(dev, > > + PVRDMA_MAX_FAST_REG_PAGES, > > + dev->dsr->caps.max_fast_reg_page_list_len); > > } > > > > + props->device_cap_flags |= IB_DEVICE_PORT_ACTIVE_EVENT | > > + IB_DEVICE_RC_RNR_NAK_GEN; > > + > > Is it left over from version 17 or a new HW support? No, we have always implicitly supported those. This just makes it more explicit to users. -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html