[PATCH v4 04/10] IB/mlx5: Initialize mlx5_ib_qp signature related

2013-12-16 Thread Sagi Grimberg
If user requested signature enable we Initialize relevant mlx5_ib_qp members. we mark the qp as sig_enable and we check if wqe_size will fit compound REG_SIG_MR work request (UMR + 2 x SET_PSV wqes), if computed wqe_size is smaller we align wqe_size to MLX5_SIG_WQE_SIZE. Signed-off-by: Sagi

[PATCH v4 03/10] IB/mlx5, mlx5_core: Support for create_mr and destroy_mr

2013-12-16 Thread Sagi Grimberg
Support create_mr and destroy_mr verbs. For now, create/destroy routines will only support user request for signature enabled memory regions. The created memory region will be an indirect memory key that will be able to register pre-registered data buffer and protection guards buffer

[PATCH v4 09/10] IB/mlx5: Collect signature error completion

2013-12-16 Thread Sagi Grimberg
This commit takes care of the generated signature error cqe generated by the HW (if happened). The underlying mlx5 driver will handle signature error completions and will lookup the relevant memory region (under a read_lock) and mark it as dirty (contains a signature error). Once the user will

[PATCH v4 01/10] IB/core: Introduce protected memory regions

2013-12-16 Thread Sagi Grimberg
This commit introduces verbs for creating/destoying memory regions which will allow new types of memory key operations such as protected memory registration. Indirect memory registration is registering several (one of more) pre-registered memory regions in a specific layout. The Indirect region

[PATCH v4 02/10] IB/core: Introduce Signature Verbs API

2013-12-16 Thread Sagi Grimberg
This commit Introduces the Verbs Interface for signature related operations. A signature handover operation shall configure the layouts of data and protection attributes both in memory and wire domains. Signature operations are: - INSERT Generate and insert protection information when handing

[PATCH v4 07/10] IB/mlx5: Keep mlx5 MRs in a radix tree under device

2013-12-16 Thread Sagi Grimberg
This radix tree will be useful when processing signature errors on a specific key. The mlx5 driver shall lookup the matching mlx5 memory region structure and mark it as dirty (contains signature errors). The radix tree is protected under a rw_lock as signature error processing is guaranteed not to

[PATCH v4 00/10] Introduce Signature feature

2013-12-16 Thread Sagi Grimberg
This patchset Introduces Verbs level support for signature handover feature. Siganture is intended to implement end-to-end data integrity on a transactional basis in a completely offloaded manner. There are several end-to-end data integrity methods used today in various applications and/or upper

[PATCH v4 10/10] IB/mlx5: Publish support in signature feature

2013-12-16 Thread Sagi Grimberg
Currently support only T10-DIF types of signature handover operations (typs 1|2|3). Signed-off-by: Sagi Grimberg sa...@mellanox.com --- drivers/infiniband/hw/mlx5/main.c |9 + 1 files changed, 9 insertions(+), 0 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c

[PATCH v4 08/10] IB/mlx5: Support IB_WR_REG_SIG_MR

2013-12-16 Thread Sagi Grimberg
This patch implements IB_WR_REG_SIG_MR posted by the user. Baisically this WR involvs 3 WQEs in order to prepare and properly register the signature layout: 1. post UMR WR to register the sig_mr in one of two possible ways: * In case the user registered a single MR for data so the UMR data

[PATCH v4 06/10] IB/mlx5: remove MTT access mode from umr flags helper function

2013-12-16 Thread Sagi Grimberg
get_umr_flags helper function might be used for types of access modes other than ACCESS_MODE_MTT, such as ACCESS_MODE_KLM. so remove it from helper and caller will add it's own access mode flag. This commit does not add/change functionality. Signed-off-by: Sagi Grimberg sa...@mellanox.com ---

[PATCH net 4/9] cxgb4: Account for stid entries properly in case of IPv6

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com IPv6 uses 2 TIDs with CLIP enabled and 4 TIDs without CLIP. Currently we are incrementing STIDs in use by 1 for both IPv4 and IPv6 which is wrong. Further, driver currently does not have interface to query if CLIP is programmed for particular IPv6 address.

[PATCH net 8/9] RDMA/cxgb4: Server filters are supported only for IPv4

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com Signed-off-by: Hariprasad Shenai haripra...@chelsio.com Signed-off-by: Kumar Sanghvi kuma...@chelsio.com --- drivers/infiniband/hw/cxgb4/cm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/cxgb4/cm.c

[PATCH net 7/9] RDMA/cxgb4: Calculate the filter server TID properly

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com Based on original work by Santosh Rastapur sant...@chelsio.com Signed-off-by: Hariprasad Shenai haripra...@chelsio.com Signed-off-by: Kumar Sanghvi kuma...@chelsio.com --- drivers/infiniband/hw/cxgb4/cm.c | 4 +--- 1 file changed, 1 insertion(+), 3

[PATCH net 5/9] cxgb4: Assign filter server TIDs properly

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com The LE workaround code is incorrectly reusing the TCAM TIDs (meant for allocation by firmware in case of hash collisions) for filter servers. This patch assigns the filter server TIDs properly starting from sftid_base index. Based on original work by

[PATCH net 2/9] cxgb4: Reserve stid 0 for T4/T5 adapters

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com When creating offload server entries, an IPv6 passive connection request can trigger a reply with a null STID, whereas the driver would expect the reply 'STID to match the value used for the request. This happens due to h/w limitation on T4 and T5. This

[PATCH net 6/9] cxgb4: Add API to correctly calculate tuple fields

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com Adds API cxgb4_select_ntuple so as to enable Upper Level Drivers to correctly calculate the tuple fields. Adds constant definitions for TP_VLAN_PRI_MAP for the Compressed Filter Tuple field widths and structures and uses them. Also, the CPL Parameters

[PATCH net 9/9] RDMA/cxgb4: Use cxgb4_select_ntuple to correctly calculate ntuple fields

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com Signed-off-by: Hariprasad Shenai haripra...@chelsio.com Signed-off-by: Kumar Sanghvi kuma...@chelsio.com --- drivers/infiniband/hw/cxgb4/cm.c | 71 ++-- 1 file changed, 17 insertions(+), 54 deletions(-) diff --git

[PATCH net 3/9] cxgb4: Include TCP as protocol when creating server filters

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com We were creating LE Workaround Server Filters without specifying IPPROTO_TCP (6) in the filters (when F_PROTOCOL is set in TP_VLAN_PRI_MAP). This meant that UDP packets with matching IP Addresses/Ports would get caught up in the filter and be delivered to

[PATCH net 1/9] cxgb4: Properly account for server filter entries

2013-12-16 Thread Hariprasad Shenai
From: Kumar Sanghvi kuma...@chelsio.com When creating server filters via LE-Workaround path, properly track the server filter entries, and don't confuse them with regular server entries. Based on original work by Hariprasad Shenai haripra...@chelsio.com Signed-off-by: Hariprasad Shenai

[PATCH net 0/9] Fixes for server entries and server filter entries for Chelsio T4/T5

2013-12-16 Thread Hariprasad Shenai
Hi All, This patch series provides miscelleneous fixes for Chelsio T4/T5 adapters related to server entries and server filter entries. Also, fixes a bug in ULD (Upper Level Driver) like iw_cxgb4 where-in it calculates wrong tuple values on T5 adapter. So, a new API cxgb4_select_ntuple is

[PATCH v2] ssa_smdb.[c h]: remove 'osm_header.h' dependency from 'ssa_smdb.h'

2013-12-16 Thread Ilya Nelkenbaum
Signed-off-by: Ilya Nelkenbaum il...@mellanox.com --- Changes since version 1: - all method declarations were removed from 'ssa_smdb.h' - argument types were changed back from 'void*' to specific types include/infiniband/ssa_smdb.h | 26 --

Re: [PATCH v2] ssa_smdb.[c h]: remove 'osm_header.h' dependency from 'ssa_smdb.h'

2013-12-16 Thread Ilya Nelkenbaum
Please ignore. On 12/16/2013 3:30 PM, Ilya Nelkenbaum wrote: Signed-off-by: Ilya Nelkenbaum il...@mellanox.com --- Changes since version 1: - all method declarations were removed from 'ssa_smdb.h' - argument types were changed back from 'void*' to specific types

Re: [PATCH V9 libibverbs 0/7] Add extension and XRC QP support

2013-12-16 Thread Roland Dreier
OK, I finally got to merge this to libibverbs. Please take a look at my libibverbs git tree and let me know if there is any issue with the verbs extensions or XRC support. I will probably cut a new libibverbs release in about a week if this looks good to everyone. Thanks! Roland -- To

Re: [PATCH V9 libibverbs 0/7] Add extension and XRC QP support

2013-12-16 Thread Or Gerlitz
On Mon, Dec 16, 2013 at 9:16 PM, Roland Dreier rol...@purestorage.com wrote: OK, I finally got to merge this to libibverbs. Please take a look at my libibverbs git tree and let me know if there is any issue with the verbs extensions or XRC support. Roland, your libibverbs tree which includes

Re: [PATCH V6 for-next 0/7] IP based RoCE GID Addressing

2013-12-16 Thread Or Gerlitz
On Thu, Dec 12, 2013, Or Gerlitz ogerl...@mellanox.com wrote: Changes from V5: - moved the address resolution helper from the uverbs layer to the ib_core module where it belongs. This will also allow to run kernel consumers who don't use the rdma-cm Hi Roland, Anything else, or we