Re: [PATCH 1/1] Fix dst_neigh_lookup/dst_neigh_lookup_skb return value handling bug

2013-03-14 Thread Cong Wang
On Thu, 14 Mar 2013 at 03:41 GMT, Zhouyi Zhou zhouzho...@gmail.com wrote: Tested on my x86_64 machine Signed-off-by: Zhouyi Zhou zhouzho...@gmail.com --- drivers/infiniband/hw/cxgb4/cm.c | 12 include/net/dst.h|6 -- 2 files changed, 16 insertions(+),

Re: [PATCH] libibmad: Fixes for failures when not all ports of HCA are connected

2013-03-14 Thread Or Gerlitz
On 13/03/2013 21:36, Ira Weiny wrote: Furthermore, I'm reluctant to modify errno in this library. Yep, this should be avoided unless impossible... Or. It is not documented and in general is poor form. I realize that the interface does not currently allow for an alternative.:-( -- To

Re: [RFC 00/11] Add support for iSCSI Extentions for RDMA (ISER) target

2013-03-14 Thread Or Gerlitz
On 08/03/2013 03:45, Nicholas A. Bellinger wrote: This series is first RFC for iSCSI Extentions for RDMA (ISER) target support with existing iscsi-target TCP based socket code for a future v3.10 merge. This code is available in git here:

Re: [RFC 10/11] iser-target: Add logic for core

2013-03-14 Thread Or Gerlitz
On 08/03/2013 03:45, Nicholas A. Bellinger wrote: +void +isert_dump_ib_wc(struct ib_wc *wc) +{ + pr_debug(wc-wr_id: %llu\n, wc-wr_id); + pr_debug(wc-status: 0x%08x\n, wc-status); This helper is called for a CQ completion with error, but when this happens all the WC fields except

Re: [RFC 09/11] iser-target: Add logic for verbs

2013-03-14 Thread Or Gerlitz
On 08/03/2013 03:45, Nicholas A. Bellinger wrote: +++ b/drivers/infiniband/ulp/isert/isert_verbs.c +#define ISERT_ADDR_ROUTE_TIMEOUT 1000 remove this define, its irrelevant and you don't use that anywhere +static void +isert_qp_event_callback(struct ib_event *e, void *context) +{ +

Re: [RFC 08/11] iser-target: Add base + proto includes

2013-03-14 Thread Or Gerlitz
On 08/03/2013 03:45, Nicholas A. Bellinger wrote: +++ b/drivers/infiniband/ulp/isert/isert_base.h @@ -0,0 +1,123 @@ +#include linux/socket.h +#include linux/in.h +#include linux/in6.h +#include rdma/ib_verbs.h +#include rdma/ib_fmr_pool.h you include rdma/ib_fmr_pool.h in multiple places but

Re: [RFC 09/11] iser-target: Add logic for verbs

2013-03-14 Thread Or Gerlitz
On 08/03/2013 03:45, Nicholas A. Bellinger wrote: isert_conn-conn_rx_cq = ib_create_cq(ib_dev, isert_cq_rx_callback, + isert_cq_event_callback, + (void *)isert_conn, +

Re: [RFC 10/11] iser-target: Add logic for core

2013-03-14 Thread Or Gerlitz
On 08/03/2013 03:45, Nicholas A. Bellinger wrote: +void +iser_cq_tx_tasklet(unsigned long data) +{ + struct isert_conn *isert_conn = (struct isert_conn *)data; + struct ib_cq *tx_cq = isert_conn-conn_tx_cq; + struct iser_tx_desc *tx_desc; + struct ib_wc wc; + +

Re: [PATCH] libibmad: To fix compilation warning: need typecasts

2013-03-14 Thread Ira Weiny
On Tue, Mar 12, 2013 at 8:34 AM, Boris Chiu boris.c...@oracle.com wrote: From: Brendan Doyle brendan.do...@oracle.com Signed-off-by: Brendan Doyle brendan.do...@oracle.com Thanks Applied, Ira -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to

Re: [PATCH] libibmad: Conversion specifier; %m is not supported on Solaris

2013-03-14 Thread Ira Weiny
On Tue, Mar 12, 2013 at 8:33 AM, Boris Chiu boris.c...@oracle.com wrote: From: Brendan Doyle brendan.do...@oracle.com Signed-off-by: Brendan Doyle brendan.do...@oracle.com Thanks applied, Ira -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to

[PATCHv4] infiniband-diags/ibqueryerrors.c: obtain destination sl before perf query

2013-03-14 Thread Dan Ben Yosef
1) if use -G or -D option : we obtain sl before doing perf query. 2) if no destination is given : we obtain sl for every pair source-destination. 3) if no destination is given and use --skip-sl option : we don't obtain sl to all nodes in the fabric,in this case sl=0 for all node pairs.

[PATCH] opensm/osm_sw_info_rcv.c: Fix double release of lock in osm_si_rcv_process

2013-03-14 Thread Hal Rosenstock
when node GUID is not found Signed-off-by: Hal Rosenstock h...@mellanox.com --- diff --git a/opensm/osm_sw_info_rcv.c b/opensm/osm_sw_info_rcv.c index 122af89..84e7fe0 100644 --- a/opensm/osm_sw_info_rcv.c +++ b/opensm/osm_sw_info_rcv.c @@ -378,7 +378,7 @@ void osm_si_rcv_process(IN void

[PATCHv5] infiniband-diags/ibqueryerrors.c: obtain destination sl before perf query

2013-03-14 Thread Dan Ben Yosef
1) if use -G or -D option : we obtain sl before doing perf query. 2) if no destination is given : we obtain sl for every pair source-destination. 3) if no destination is given and use --skip-sl option : we don't obtain sl to all nodes in the fabric,in this case sl=0 for all node pairs.

[PATCH v2 net-next 03/22] cxgb4: Initialize T5

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 85 ++---

[PATCH v2 net-next 08/22] cxgb4: Add T5 PCI ids

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 38 +++ 1 files

[PATCH v2 net-next 10/22] cxgb4: Disable SR-IOV support for PF4-7 for T5

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com All T5 adapters will only support VFs on PF0-3 despite the ability of the hardware to support them on PF4-7. This keeps our T4 and T5 adapters more similar which simplifies host driver software. Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2:

[PATCH v2 net-next 11/22] cxgb4vf: Add support for Chelsio T5 adapter

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4vf/adapter.h |1 +

[PATCH v2 net-next 12/22] RDMA/cxgb4: Add Support for Chelsio T5 adapter

2013-03-14 Thread Vipul Pandya
Adds support for Chelsio T5 adapter. Enables T5's Write Combining feature. Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/infiniband/hw/cxgb4/cm.c | 64 +++

[PATCH v2 net-next 14/22] RDMA/cxgb4: Add module_params to enable DB FC Coalescing on T5

2013-03-14 Thread Vipul Pandya
Both DB Flow-Control and DB Coalescing are disabled by default on T5 Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/infiniband/hw/cxgb4/device.c | 25 +++-- drivers/infiniband/hw/cxgb4/iw_cxgb4.h |

[PATCH v2 net-next 00/22] Add support for Chelsio T5 adapter

2013-03-14 Thread Vipul Pandya
Hi All, This patch series adds support for Chelsio's T5 adapter. It also adds support for new features of T5. It adds these in cxgb4, cxgb4vf, RDMA/cxgb4 and csiostor drivers. Chelsio's T5 asic moves the architecture into 40GbE speeds. T5 is a 10/40GbE controller with full offload support of a

[PATCH v2 net-next 02/22] cxgb4: Add macros, structures and inline functions for T5

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/cxgb4.h| 50 -

[PATCH v2 net-next 04/22] cxgb4: Dump T5 registers

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 452 ++- 1 files

[PATCH v2 net-next 06/22] cxgb4: Enable doorbell drop recovery only for T4 adapter

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 87 ++ 1 files

[PATCH v2 net-next 07/22] cxgb4: Add T5 debugfs support

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/cxgb4.h |3 +-

[PATCH v2 net-next 09/22] cxgb4: Update driver version and description

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c |4 ++-- 1 files changed, 2

[PATCH v2 net-next 13/22] RDMA/cxgb4: Turn off db coalescing when RDMA QPs are in use.

2013-03-14 Thread Vipul Pandya
Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/infiniband/hw/cxgb4/qp.c| 20 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 19 +++

[PATCH v2 net-next 15/22] RDMA/cxgb4: Use DSGLs for fastreg and adapter memory writes for T5.

2013-03-14 Thread Vipul Pandya
It enables direct DMA by HW to memory region PBL arrays and fast register PBL arrays from host memory, vs the T4 way of passing these arrays in the WR itself. The result is lower latency for memory registration, and larger PBL array support for fast register operations. This patch also updates

[PATCH v2 net-next 16/22] RDMA/cxgb4: Map pbl buffers for dma if using DSGL.

2013-03-14 Thread Vipul Pandya
Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/infiniband/hw/cxgb4/mem.c | 29 +++-- 1 files changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/mem.c

[PATCH v2 net-next 17/22] RDMA/cxgb4: Bump tcam_full stat and WR reply timeout

2013-03-14 Thread Vipul Pandya
Always bump the tcam_full stat. Also, bump wr reply timeout to 30 seconds. Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/infiniband/hw/cxgb4/cm.c |2 +- drivers/infiniband/hw/cxgb4/iw_cxgb4.h |2 +- 2 files

[PATCH v2 net-next 18/22] RDMA/cxgb4: Fix onchip queue support for T5

2013-03-14 Thread Vipul Pandya
T5 adapter does not support onchip queue memory. Present logic fails to allocate QP for T5 and returns an error. Also, if module parameter ocqp_support is zero then we are unable to allocate QP which should not be the case. Ideally if ocqp_support parameter is 0 or onchip queue support is disable

[PATCH v2 net-next 19/22] csiostor: Segregate T4 adapter operations.

2013-03-14 Thread Vipul Pandya
From: Arvind Bhushan arvi...@chelsio.com This patch separates T4 adapter operations into a new file. Signed-off-by: Arvind Bhushan arvi...@chelsio.com Signed-off-by: Naresh Kumar Inna nar...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db

[PATCH v2 net-next 20/22] csiostor: Add T5 adapter operations.

2013-03-14 Thread Vipul Pandya
From: Arvind Bhushan arvi...@chelsio.com This patch creates a new file for T5 adapter operations. Signed-off-by: Arvind Bhushan arvi...@chelsio.com Signed-off-by: Naresh Kumar Inna nar...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db

[PATCH v2 net-next 21/22] csiostor: Header file modifications for chip support and bug fixes.

2013-03-14 Thread Vipul Pandya
From: Arvind Bhushan arvi...@chelsio.com This patch defines the common operations to support multiple chips. It includes common header file modifications to support the current chips (T4 and T5). It also includes the following bug fixes: - reconfirms the rnode state after an implicit logo. -

[PATCH v2 net-next 22/22] csiostor: Cleanup chip specific operations.

2013-03-14 Thread Vipul Pandya
From: Arvind Bhushan arvi...@chelsio.com This patch removes chip specific operations from the common hardware paths, as well as the Makefile change to accomodate the new files. Signed-off-by: Arvind Bhushan arvi...@chelsio.com Signed-off-by: Naresh Kumar Inna nar...@chelsio.com --- v2: Replaced

[PATCH v2 net-next 01/22] cxgb4: Add register definations for T5

2013-03-14 Thread Vipul Pandya
From: Santosh Rastapur sant...@chelsio.com Signed-off-by: Santosh Rastapur sant...@chelsio.com Signed-off-by: Vipul Pandya vi...@chelsio.com --- v2: Replaced #ifdef with portable interface wmb in ring_tx_db drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 94 ++ 1 files

Re: [PATCH v2 net-next 00/22] Add support for Chelsio T5 adapter

2013-03-14 Thread Steve Wise
Acked-by: Steve Wise sw...@opengridcomputing.com -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

[PATCH] IB/qib: change QLogic to Intel

2013-03-14 Thread Mike Marciniszyn
From: Vinit Agnihotri vinit.abhay.agniho...@intel.com These changes modify the qib driver as part of acquiring the Infiniband assets of QLogic. Reviewed-by: Mike Marciniszyn mike.marcinis...@intel.com Signed-off-by: Vinit Agnihotri vinit.abhay.agniho...@intel.com ---

Re: [PATCH v2 net-next 00/22] Add support for Chelsio T5 adapter

2013-03-14 Thread David Miller
From: Vipul Pandya vi...@chelsio.com Date: Thu, 14 Mar 2013 20:38:46 +0530 We request to merge this patch series via David Miller's net-next tree. We are copying respective maintainers of all the drivers for reviewing the changes. Kindly let us know in case of any review comments. All applied

Re: [PATCH] libibmad: To fix big endian problem for both 32-bit 64-bit SPARC

2013-03-14 Thread Boris Chiu
Hi Hal and Or, We are checking on this and will get back. Thanks, Boris On 03/13/13 05:58, Or Gerlitz wrote: On 13/03/2013 14:48, Hal Rosenstock wrote: On 3/12/2013 3:36 PM, Boris Chiu wrote: --- a/src/dump.c +++ b/src/dump.c @@ -46,12 +46,24 @@ void mad_dump_int(char *buf, int bufsz, void

RE: [PATCH v2 net-next 05/22] cxgb4: Add T5 write combining support

2013-03-14 Thread David Laight
This patch implements a low latency Write Combining (aka Write Coalescing) work request path. PCIE maps User Space Doorbell BAR2 region writes to the new interface to SGE. SGE pulls a new message from PCIE new interface and if its a coalesced write work request then pushes it for processing.

[PATCH v2] IB/qib: change QLogic to Intel

2013-03-14 Thread Mike Marciniszyn
From: Vinit Agnihotri vinit.abhay.agniho...@intel.com These changes modify the qib driver as part of acquiring the Infiniband assets of QLogic. Reviewed-by: Mike Marciniszyn mike.marcinis...@intel.com Reviewed-by: Dean Luick dean.lu...@intel.com Signed-off-by: Vinit Agnihotri

Re: [PATCH V3 for-next 3/5] IB/ipoib: Move to multi-queue device

2013-03-14 Thread Or Gerlitz
Marciniszyn, Mike mike.marcinis...@intel.com wrote: This patch will conflict with http://marc.info/?l=linux-rdmam=136190765729001w=2 What sort of conflict? is that on lines that are moving, or something deeper in the proposed design? Or. -- To unsubscribe from this list: send the line

RE: [PATCH V3 for-next 3/5] IB/ipoib: Move to multi-queue device

2013-03-14 Thread Marciniszyn, Mike
The cm side ib_req_notify_cq() is altered in my patch. The same behavior is need to be adopted. Mike -Original Message- From: Or Gerlitz [mailto:or.gerl...@gmail.com] Sent: Thursday, March 14, 2013 4:52 PM To: Marciniszyn, Mike Cc: Or Gerlitz; rol...@kernel.org;

Re: [Fwd: Re: [PATCH] libibmad: Fixes for failures when not all ports of HCA are connected]

2013-03-14 Thread brendan.do...@oracle.com
On 03/15/13 01:23 AM, brendan.do...@oracle.com wrote: So, here is the history... There is an oracle application used to monitor the health of a node by calling ib_resolve_portid_str_via(node GUID). We observed that a call to ib_resolve_portid_str_via() which specified the use of an