summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2016-03-21IB/mlx5: Fix decision on using MAD_IFCEli Cohen1-1/+1
Fix the condition that dictates when MAD_IFC should be used. According to firmware specifications, MAD_IFC commands must be used only if the ib_virt capability is off. Signed-off-by: Eli Cohen <eli@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-21net/core: Add support for configuring VF GUIDsEli Cohen3-0/+46
Add two new NLAs to support configuration of Infiniband node or port GUIDs. New applications can choose to use this interface to configure GUIDs with iproute2 with commands such as: ip link set dev ib0 vf 0 node_guid 00:02:c9:03:00:21:6e:70 ip link set dev ib0 vf 0 port_guid 00:02:c9:03:00:21:6e:78 A new ndo, ndo_sef_vf_guid is introduced to notify the net device of the request to change the GUID. Signed-off-by: Eli Cohen <eli@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-21IB/{core, ulp} Support above 32 possible device capability flagsLeon Romanovsky3-3/+3
The old bitwise device_cap_flags variable was limited to u32 which has all bits already defined. In order to overcome it, we converted device_cap_flags variable to be u64 type. Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-21IB/core: Replace setting the zero values in ib_uverbs_ex_query_deviceLeon Romanovsky1-12/+3
The setting to zero during variable initialization eliminates the need to explicitly set to zero variables and structures. Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-21net/mlx5_core: Introduce offload arithmetic hardware capabilitiesSagi Grimberg3-1/+42
Define the necessary hardware structures for the offload arithmetic capabilities and read/cache them on driver load. Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-21net/mlx5_core: Refactor device capability functionLeon Romanovsky3-62/+24
Device capability function was called similar in all places. It was called twice for every queried parameter, while the difference between calls was in HCA capability mode only. The change proposed unify these calls into one function. Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-21net/mlx5_core: Fix caching ATOMIC endian mode capabilityLeon Romanovsky1-0/+4
Add caching of maximum device capability of ATOMIC endian mode. Fixes: f91e6d8941bf ('net/mlx5_core: Add setting ATOMIC endian mode') Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-21ib_srpt: fix a WARN_ON() messageDan Carpenter1-1/+1
The first argument of WARN_ON() is a condition, so it means the warning message here will just be the name without the ->qp_num information. Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-16Merge branches 'nes', 'cxgb4' and 'iwpm' into k.o/for-4.6Doug Ledford23-753/+442
2016-03-16iwpm: crash fix for large connections testFaisal Latif3-13/+13
During large connection test, there is a crash at wake_up() in the callback as waitq is not yet initialized. Callback can happen before iwpm_wait_complete_req() is called to initialize waitq. To resolve, using signaling semaphore instead of waitq. Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com> Reviewed-by: Tatyana E Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Faisal Latif <faisal.latif@intel.com> Reviewed-by: Steve Wise <swise@opengridcomputing.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-16iw_cxgb3: support for iWARP port mappingSteve Wise1-8/+8
Now with the new iWARP port mapping service in the iwcm, it is trivial to add cxgb3 support. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-16iw_cxgb4: remove port mapper related codeSteve Wise3-264/+65
Now that most of the port mapper code been moved to iwcm, we can remove it from iw_cxgb4. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-16iw_nes: remove port mapper related codeFaisal Latif4-309/+80
Now that most of the port mapper code been moved to iwcm, we can remove it from port mapper service user drivers. Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com> Signed-off-by: Tatyana E. Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Faisal Latif <faisal.latif@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-16iwcm: common code for port mapperFaisal Latif4-30/+172
moved port mapper related code from drivers into common code Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com> Signed-off-by: Tatyana E. Nikolova <tatyana.e.nikolova@intel.com> Signed-off-by: Faisal Latif <faisal.latif@intel.com> Reviewed-by: Steve Wise <swise@opengridcomputing.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-16Merge branches 'mlx4', 'mlx5' and 'ocrdma' into k.o/for-4.6Doug Ledford49-356/+2452
2016-03-15Merge branches 'ib_core', 'ib_ipoib', 'srpt', 'drain-cq-v4' and 'net/9p' ↵Doug Ledford17-736/+610
into k.o/for-4.6
2016-03-11net/9p: convert to new CQ APIChristoph Hellwig1-55/+31
Trivial conversion to the new RDMA CQ API. Signed-off-by: Christoph Hellwig <hch@lst.de> Acked-by: Dominique Martinet <dominique.martinet@cea.fr> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10IB/mlx5: Add support for don't trap rulesMaor Gottlieb3-8/+55
Each bypass flow steering priority will be split into two priorities: 1. Priority for don't trap rules. 2. Priority for normal rules. When user creates a flow using IB_FLOW_ATTR_FLAGS_DONT_TRAP flag, the driver creates two flow rules, one used for receiving the traffic and the other one for forwarding the packet to continue matching in lower or equal priorities. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10net/mlx5_core: Introduce forward to next priority actionMaor Gottlieb4-13/+188
Add support to create flow rule that forward packets to the first flow table in the next priority (next priority could be the first priority in the next namespace or the next priority in the same namespace). This feature could be used for DONT_TRAP rules or rules that only want to mark the packet with flow tag. In order to do it optimally, each flow table has list of all rules that point to this flow table, when a flow table is destroyed/created, we update the list head correspondingly. This kind of rule is created when destination is NULL and action is MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-10net/mlx5_core: Create anchor of last flow tableMaor Gottlieb3-1/+46
Create an empty flow table in the end of NIC rx namesapce. Adding this flow table simplify the implementation of "forward to next prio" rules. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-04iser: Accept arbitrary sg lists mapping if the device supports itSagi Grimberg2-9/+25
If the device support arbitrary sg list mapping (device cap IB_DEVICE_SG_GAPS_REG set) we allocate the memory regions with IB_MR_TYPE_SG_GAPS and allow the block layer to pass us gaps by skip setting the queue virt_boundary. Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-04mlx5: Add arbitrary sg list supportSagi Grimberg4-8/+60
Allocate proper context for arbitrary scatterlist registration If ib_alloc_mr is called with IB_MR_MAP_ARB_SG, the driver allocate a private klm list instead of a private page list. Set the UMR wqe correctly when posting the fast registration. Also, expose device cap IB_DEVICE_MAP_ARB_SG according to the device id (until we have a FW bit that correctly exposes it). Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-04IB/core: Add arbitrary sg_list supportSagi Grimberg2-0/+8
Devices that are capable in registering SG lists with gaps can now expose it in the core to ULPs using a new device capability IB_DEVICE_SG_GAPS_REG (in a new field device_cap_flags_ex in the device attributes as we ran out of bits), and a new mr_type IB_MR_TYPE_SG_GAPS_REG which allocates a memory region which is capable of handling SG lists with gaps. Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-04IB/mlx5: Expose correct max_fast_reg_page_list_lenSagi Grimberg1-1/+2
While documentation indicates that the number of translation entries per memory key is unlimited, in practice, we can only fit a finite amount of translation entries in a single registration wqe (which is log_max_klm_list_size). Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-04IB/mlx5: Make coding style more consistentDoug Ledford1-4/+2
These three related functions can't agree whether to put the umrwr on the stack dirty and then memset it, or to initialize it on the stack. Make them all agree. Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-04IB/mlx5: Convert UMR CQ to new CQ APIChristoph Hellwig3-40/+27
Simplifies the code, and makes it more fair vs other users by using a softirq for polling. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Haggai Eran <haggaie@mellanox.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/ocrdma: Skip using unneeded intermediate variableMarkus Elfring1-3/+1
Return the value from a call of the ocrdma_mbx_modify_qp() function without using an extra assignment for the local variable "status". Signed-off-by: Markus Elfring <elfring@users.sourceforge.net> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/ocrdma: Skip using unneeded intermediate variableMarkus Elfring1-2/+1
Return zero at the end without using the local variable "status". Signed-off-by: Markus Elfring <elfring@users.sourceforge.net> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/ocrdma: Delete unnecessary variable initialisations in 11 functionsMarkus Elfring4-11/+11
The variable "status" will be set to an appropriate value a bit later. Thus let us omit the explicit initialisation at the beginning. Signed-off-by: Markus Elfring <elfring@users.sourceforge.net> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/core: Documentation fix in the MAD header fileHal Rosenstock1-2/+2
In ib_mad.h, ib_mad_snoop_handler uses send_buf rather than send_wr Signed-off-by: Hal Rosenstock <hal@mellanox.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/core: trivial prink cleanup.Parav Pandit10-89/+77
1. Replaced printk with appropriate pr_warn, pr_err, pr_info. 2. Removed unnecessary prints around memory allocation failure which are not required, as reported by the checkpatch script. Signed-off-by: Parav Pandit <pandit.parav@gmail.com> Reviewed-by: Haggai Eran <haggaie@mellanox.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/core: Replace memset with eth_zero_addrAmitoj Kaur Chawla1-1/+1
Use eth_zero_addr to assign the zero address to the given address array instead of memset when second argument is address of zero. The Coccinelle semantic patch used to make this change is as follows: // <smpl> @eth_zero_addr@ expression e; @@ -memset(e,0x00,ETH_ALEN); +eth_zero_addr(e); // </smpl> Signed-off-by: Amitoj Kaur Chawla <amitoj1606@gmail.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/core: Modify conditional on ucontext existenceEli Cohen1-6/+6
Since we allow to call legacy verbs using their extended counterpart, the check on ucontext has to move up to a common area in case this verb is ever extended. Signed-off-by: Eli Cohen <eli@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/core: IB/core: Allow legacy verbs through extended interfacesEli Cohen1-10/+19
When an extended verb is an extension to a legacy verb, the original functionality is preserved. Hence we do not require each hardware driver to set the extended capability. This will allow the use of the extended verb in its simple form with drivers that do not support the extended capability. Signed-off-by: Eli Cohen <eli@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/core: Avoid duplicate codeEli Cohen1-20/+9
Move the check on the validity of the command to a common area. Signed-off-by: Eli Cohen <eli@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03Merge branch 'k.o/for-4.5-rc' into HEADDoug Ledford3-22/+29
2016-03-03IB/{core, mlx5}: Fix input len in vendor part of create_qp/srqMajd Dibbiny2-11/+9
Currently, the inlen field of the vendor's part of the command doesn't match the command buffer. This happens because the inlen accommodates ib_uverbs_cmd_hdr which is deducted from the in buffer. This is problematic since the vendor function could be called either from the legacy verb (where the input length mismatches the actual length) or by the extended verb (where the length matches). The vendor has no idea which function calls it and therefore has no way to know how the length variable should be treated. Fixing this by aligning the inlen to the correct length. All vendor drivers either assumed that inlen >= sizeof(vendor_uhw_cmd) or just failed wrongly (mlx5) and fixed in this patch. Fixes: cfb5e088e26a ('IB/mlx5: Add CQE version 1 support to user QPs and SRQs') Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Reviewed-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/mlx5: Avoid using user-index for SRQsMajd Dibbiny1-11/+19
Normal SRQs, unlike XRC SRQs, don't have user-index, therefore avoid verifying it and using it. Fixes: cfb5e088e26a ('IB/mlx5: Add CQE version 1 support to user QPs and SRQs') Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-03IB/ipoib: Add handling for sending of skb with many fragsHans Westgaard Ry4-3/+45
IPoIB converts skb-fragments to sge adding 1 extra sge when SG is enabled. Current codepath assumes that the max number of sge a device support is at least MAX_SKB_FRAGS+1, there is no interaction with upper layers to limit number of fragments in an skb if a device suports fewer sges. The assumptions also lead to requesting a fixed number of sge when IPoIB creates queue-pairs with SG enabled. A fallback/slowpath is implemented using skb_linearize to handle cases where the conversion would result in more sges than supported. Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com> Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com> Reviewed-by: Wei Lin Guay <wei.lin.guay@oracle.com> Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Add memory windows allocation supportMatan Barak5-1/+120
This patch adds user-space support for memory windows allocation and deallocation. It also exposes the supported types via query_device_caps verb. Signed-off-by: Matan Barak <matanb@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Tested-by: Max Gurtovoy <maxg@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/core: Add vendor's specific data to alloc mwMatan Barak8-8/+23
Passing udata to the vendor's driver in order to pass data from the user-space driver to the kernel-space driver. This data will be used in downstream patches. Signed-off-by: Matan Barak <matanb@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01net/mlx5: Refactor mlx5_core_mr to mkeyMatan Barak10-94/+98
Mlx5's mkey mechanism is also used for memory windows. The current code base uses MR (memory region) naming, which is inaccurate. Changing MR to mkey in order to represent its different usages more accurately. Signed-off-by: Matan Barak <matanb@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Added support for re-registration of MRsNoa Osherovich4-3/+227
This patch adds support for re-registration of memory regions in MLX5. The functionality is basically the same as deregister followed by register, but attempts to reuse the existing resources as much as possible. Original memory keys are kept if possible, saving the need to communicate new ones to remote peers. Signed-off-by: Noa Osherovich <noaos@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Refactoring register MR codeNoa Osherovich1-75/+132
In order to add re-registration of memory region, some logic was extracted to separate functions: - ODP related logic. - Some of the UMR WQE preparation code. - DMA mapping. - Umem creation. - Creating MKey using FW interface. - MR fields assignments after successful creation. Signed-off-by: Noa Osherovich <noaos@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/cma: Print warning on different inner and header P_KeysHaggai Eran1-0/+8
Commit 4c21b5bcef73 ("IB/cma: Add net_dev and private data checks to RDMA CM") added checks for incoming RDMA CM requests that they can be matched to a netdev based on the P_Key in the BTH of the request. This behavior was reverted in commit ab3964ad2acf ("IB/cma: Use inner P_Key to determine netdev"), since the mlx5 and ipath drivers didn't send the correct value in the BTH P_Key. Since the ipath driver was removed, and the mlx5 driver can now send GSI packets on different P_Keys, we could revert the patch to let the rdma_cm module look on the BTH P_Key when deciding to what netdev a packet belongs. However, that still breaks compatibility with the older drivers. Change the behavior to print a warning when receiving a request that has a different BTH P_Key and inner payload P_Key. In the future, after users have seen the warnings and upgraded their setups, remove the warning and block these requests. Signed-off-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Eliminate GSI RX QP's send buffersHaggai Eran1-0/+5
Now that the transmission of GSI MADs is done with the special transmission QPs, eliminate the send buffers in the GSI receive QP. Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Pick the right GSI transmission QP for sendingHaggai Eran1-1/+47
Pick the QP to use according to the wr.ud.pkey_index field in the work request. If the QP doesn't exist, it means the P_Key is zero and the packet would have been dropped, so just generate a completion and move on. Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Reorder GSI completionsHaggai Eran1-6/+150
The emulated GSI QP's send completions are generated by multiple hardware QPs, so their completions could arrive out of order with respect to the order their work request were submitted. Reorder the completions by keeping a list of the posted work request and their completions. A newly received completion from the hardware updates the list and marks its work request as completed. However, the completions are only reported to the client according to the list order. In order to support that, create a new private CQ to handle the hardware completions. Signed-off-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Generate completions in softwareHaggai Eran2-5/+88
The GSI QP emulation requires also emulating completions for transmitted MADs. The CQ on which these completions are generated can also be used by the hardware, and the MAD layer is free to use any CQ of the device for the GSI QP. Add a method for generating software completions to each mlx5 CQ. Software completions are polled first, and generate calls to the completion handler callback if necessary. Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-03-01IB/mlx5: Create GSI transmission QPs when P_Key table is changedHaggai Eran3-0/+41
Whenever the P_Key table is changed, we create the required GSI transmission QPs on-demand. Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-28 09:07:51 +0300