aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/mellanox (follow)
AgeCommit message (Collapse)AuthorFilesLines
2016-02-18mlxsw: spectrum: Allow for PVID deletionIdo Schimmel3-9/+63
When PVID is toggled off on a port member in a VLAN filtering bridge or the PVID VLAN is deleted, make the port drop untagged packets. Reverse the operation when PVID is toggled back on. Set the PVID back to the default (1), when leaving the bridge so that untagged traffic will be directed to the CPU. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-18mlxsw: reg: Add the Switch Port Acceptable Frame Types registerIdo Schimmel1-0/+58
When VLAN filtering is enabled on a bridge and PVID is deleted from a bridge port, then untagged frames are not allowed to ingress into the bridge from this port. Add the Switch Port Acceptable Frame Types (SPAFT) register, which configures the frame admittance of the port. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17mlxsw: spectrum: Set STP state when leaving 802.1D bridgeIdo Schimmel1-0/+8
When a VLAN device leaves a bridge its STP state is set to DISABLED, which causes the hardware to discard any packets coming through the port with this VLAN. Fix that by setting STP state to FORWARDING when the device leaves its bridge and allow traffic to be directed to CPU. Fixes: 26f0e7fb15de ("mlxsw: spectrum: Add support for VLAN devices bridging") Reported-by: Elad Raz <eladr@mellanox.com> Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17mlxsw: Treat local port 64 as validIdo Schimmel1-1/+1
MLXSW_PORT_MAX_PORTS represents the maximum number of local ports, which is 65 for both ASICs (SwitchX-2 and Spectrum) supported by this driver. Fixes: 93c1edb27f9e ("mlxsw: Introduce Mellanox switch driver core") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17net/mlx4_en: Avoid changing dev->features directly in run-timeEugenia Emantayev1-4/+5
It's forbidden to manually change dev->features in run-time. Currently, this is done in the driver to make sure that GSO_UDP_TUNNEL is advertized only when VXLAN tunnel is set. However, since the stack actually does features intersection with hw_enc_features, we can safely revert to advertizing features early when registering the netdevice. Fixes: f4a1edd56120 ('net/mlx4_en: Advertize encapsulation offloads [...]') Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17net/mlx4_core: Set UAR page size to 4KB regardless of system page sizeHuy Nguyen6-20/+66
problem description: The current code sets UAR page size equal to system page size. The ConnectX-3 and ConnectX-3 Pro HWs require minimum 128 UAR pages. The mlx4 kernel drivers are not loaded if there is less than 128 UAR pages. solution: Always set UAR page to 4KB. This allows more UAR pages if the OS has PAGE_SIZE larger than 4KB. For example, PowerPC kernel use 64KB system page size, with 4MB uar region, there are 4MB/2/64KB = 32 uars (half for uar, half for blueflame). This does not meet minimum 128 UAR pages requirement. With 4KB UAR page, there are 4MB/2/4KB = 512 uars which meet the minimum requirement. Note that only codes in mlx4_core that deal with firmware know that uar page size is 4KB. Codes that deal with usr page in cq and qp context (mlx4_ib, mlx4_en and part of mlx4_core) still have the same assumption that uar page size equals to system page size. Note that with this implementation, on 64KB system page size kernel, there are 16 uars per system page but only one uars is used. The other 15 uars are ignored because of the above assumption. Regarding SR-IOV, mlx4_core in hypervisor will set the uar page size to 4KB and mlx4_core code in virtual OS will obtain the uar page size from firmware. Regarding backward compatibility in SR-IOV, if hypervisor has this new code, the virtual OS must be updated. If hypervisor has old code, and the virtual OS has this new code, the new code will be backward compatible with the old code. If the uar size is big enough, this new code in VF continues to work with 64 KB uar page size (on PowerPc kernel). If the uar size does not meet 128 uars requirement, this new code not loaded in VF and print the same error message as the old code in Hypervisor. Signed-off-by: Huy Nguyen <huyn@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17net/mlx4_core: Do not BUG_ON during reset when PCI is offlineDaniel Jurgens1-2/+9
The PCI channel could go offline during reset due to EEH. Don't bug on in this case, the error is recoverable. Fixes: f6bc11e42646 ('net/mlx4_core: Enhance the catas flow to support device reset') Signed-off-by: Daniel Jurgens <danielj@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17net/mlx4_core: Fix potential corruption in counters databaseEran Ben Elisha1-4/+6
The error flow in procedure handle_existing_counter() is wrong. The procedure should exit after encountering the error, not continue as if everything is OK. Fixes: 68230242cdbc ('net/mlx4_core: Add port attribute when tracking counters') Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com> Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17net/mlx4_en: Choose time-stamping shift value according to HW frequencyEugenia Emantayev1-6/+19
Previously, the shift value used for time-stamping was constant and didn't depend on the HW chip frequency. Change that to take the frequency into account and calculate the maximal value in cycles per wraparound of ten seconds. This time slot was chosen since it gives a good accuracy in time synchronization. Algorithm for shift value calculation: * Round up the maximal value in cycles to nearest power of two * Calculate maximal multiplier by division of all 64 bits set to above result * Then, invert the function clocksource_khz2mult() to get the shift from maximal mult value Fixes: ec693d47010e ('net/mlx4_en: Add HW timestamping (TS) support') Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-17net/mlx4_en: Count HW buffer overrun only onceAmir Vadai1-2/+2
RdropOvflw counts overrun of HW buffer, therefore should be used for rx_fifo_errors only. Currently RdropOvflw counter is mistakenly also set into rx_missed_errors and rx_over_errors too, which makes the device total dropped packets accounting to show wrong results. Fix that. Use it for rx_fifo_errors only. Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC') Signed-off-by: Amir Vadai <amir@vadai.me> Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-16net/mlx5e: Use static constant netdevice ndosSaeed Mahameed1-13/+28
Currently our netdevice ops is a one static global variable which is referenced by all mlx5e netdevice instances. This can be problematic when different driver instances do not share same HW capabilities (e.g SRIOV PF and VFs probed to the host). Now we have two constant global netdevice ops variables, one for basic netdevice ops and the other with extended SRIOV ops, on netdevice construction we choose the one suitable for current device capabilities. Fixes: 66e49dedada6 ("net/mlx5e: Add support for SR-IOV ndos") Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-16net/mlx5e: Remove select queue ndo initializationSaeed Mahameed1-3/+0
Currently mlx5e_select_queue is redundant since num_tc is always 1. Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-01Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netLinus Torvalds4-46/+296
Pull networking fixes from David Miller: "This looks like a lot but it's a mixture of regression fixes as well as fixes for longer standing issues. 1) Fix on-channel cancellation in mac80211, from Johannes Berg. 2) Handle CHECKSUM_COMPLETE properly in xt_TCPMSS netfilter xtables module, from Eric Dumazet. 3) Avoid infinite loop in UDP SO_REUSEPORT logic, also from Eric Dumazet. 4) Avoid a NULL deref if we try to set SO_REUSEPORT after a socket is bound, from Craig Gallek. 5) GRO key comparisons don't take lightweight tunnels into account, from Jesse Gross. 6) Fix struct pid leak via SCM credentials in AF_UNIX, from Eric Dumazet. 7) We need to set the rtnl_link_ops of ipv6 SIT tunnels before we register them, otherwise the NEWLINK netlink message is missing the proper attributes. From Thadeu Lima de Souza Cascardo. 8) Several Spectrum chip bug fixes for mlxsw switch driver, from Ido Schimmel 9) Handle fragments properly in ipv4 easly socket demux, from Eric Dumazet. 10) Don't ignore the ifindex key specifier on ipv6 output route lookups, from Paolo Abeni" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (128 commits) tcp: avoid cwnd undo after receiving ECN irda: fix a potential use-after-free in ircomm_param_request net: tg3: avoid uninitialized variable warning net: nb8800: avoid uninitialized variable warning net: vxge: avoid unused function warnings net: bgmac: clarify CONFIG_BCMA dependency net: hp100: remove unnecessary #ifdefs net: davinci_cpdma: use dma_addr_t for DMA address ipv6/udp: use sticky pktinfo egress ifindex on connect() ipv6: enforce flowi6_oif usage in ip6_dst_lookup_tail() netlink: not trim skb for mmaped socket when dump vxlan: fix a out of bounds access in __vxlan_find_mac net: dsa: mv88e6xxx: fix port VLAN maps fib_trie: Fix shift by 32 in fib_table_lookup net: moxart: use correct accessors for DMA memory ipv4: ipconfig: avoid unused ic_proto_used symbol bnxt_en: Fix crash in bnxt_free_tx_skbs() during tx timeout. bnxt_en: Exclude rx_drop_pkts hw counter from the stack's rx_dropped counter. bnxt_en: Ring free response from close path should use completion ring net_sched: drr: check for NULL pointer in drr_dequeue ...
2016-01-28switchdev: Require RTNL mutex to be held when sending FDB notificationsIdo Schimmel2-6/+3
When switchdev drivers process FDB notifications from the underlying device they resolve the netdev to which the entry points to and notify the bridge using the switchdev notifier. However, since the RTNL mutex is not held there is nothing preventing the netdev from disappearing in the middle, which will cause br_switchdev_event() to dereference a non-existing netdev. Make switchdev drivers hold the lock at the beginning of the notification processing session and release it once it ends, after notifying the bridge. Also, remove switchdev_mutex and fdb_lock, as they are no longer needed when RTNL mutex is held. Fixes: 03bf0c281234 ("switchdev: introduce switchdev notifier") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: reg: Use correct offset in field definitonIdo Schimmel1-3/+3
The rx_lane, tx_lane and module fields in the PMLP register don't have an additional offset besides the base one (0x04), so set it to 0x00. Fixes: 4ec14b7634b2 ("mlxsw: Add interface to access registers and process events") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Compare local ports instead of pointersIdo Schimmel1-2/+4
When dumping the FDB we can't compare the actual pointers of the ports structs, as it's possible the struct represents a vPort instead of the underlying physical port. Solve this by comparing the local port number instead, as it's shared between the physical ports and all the vPorts on top of him. Fixes: 54a732018d8e ("mlxsw: spectrum: Adjust switchdev ops for VLAN devices") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Dump LAG FDB records only onceIdo Schimmel1-2/+10
LAG FDB records can only point to LAG devices or VLAN devices configured on top of them. Therefore, when dumping the FDB we shouldn't associate these records with the underlying physical ports. Fixes: 8a1ab5d76639 ("mlxsw: spectrum: Implement FDB add/remove/dump for LAG") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Use correct netdev when notifying bridgeIdo Schimmel1-2/+4
LAG FDB entries pointing to VLAN devices should be reported to the bridge with the matching VLAN device and not the underlying LAG device. Fixes: aac78a440887 ("mlxsw: spectrum: Adjust FDB notifications for VLAN devices") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Don't report VLAN for 802.1D FDB entriesIdo Schimmel1-15/+16
When dumping the hardware FDB we should report entries pointing to VLAN devices with VLAN 0, as packets coming into the bridge are untagged. Likewise, pass FDB_{ADD,DEL} notifications with VLAN 0 for these devices. Fixes: 54a732018d8e ("mlxsw: spectrum: Adjust switchdev ops for VLAN devices") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Notify bridge's FDB only based on learning_syncIdo Schimmel1-8/+6
When we disable learning on bridge port we should still update the software bridge's FDB when entry pointing to this bridge port is aged-out. We can otherwise have an inconsistency between software and hardware tables. Fixes: 8a1ab5d76639 ("mlxsw: spectrum: Implement FDB add/remove/dump for LAG") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Disable learning according to STP stateIdo Schimmel1-1/+1
When port is put into LISTENING state it shouldn't populate the FDB, so set the port's STP state in hardware to DISCARDING instead of LEARNING. It will therefore keep listening to BPDU packets, but discard other non-control packets and won't perform any learning. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Don't forward packets when STP state is DISABLEDIdo Schimmel1-1/+1
When STP state is set to DISABLED the port is assumed to be inactive, but currently we forward packets ingressing through it. Instead, set the port's STP state in hardware to DISCARDING, which means it doesn't forward packets or perform any learning, but it does trap control packets. However, these packets will be dropped by bridge code, which results in the expected behavior. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Flush FDB when leaving bridgeIdo Schimmel1-8/+129
As explained in previous commit, we should always take care of flushing the FDB in the driver and not rely on bridge code. We need to distinguish between two cases with regards to LAG: 1) Port is leaving LAG while LAG is bridged (or VLAN devices on top of it). In this case don't flush the FDB entries pointing to the LAG ID, as this will affect other ports still member in the LAG. Only flush the FDB when the last port in the LAG is leaving the bridge. 2) LAG device is leaving the bridge. In this case the CHANGEUPPER event is simply propagated to each member port, so make each port flush the FDB in its turn. Note that emptying a bridged LAG from ports creates an inconsistency between hardware and software. A user who later (< ageing_time) re-populates the LAG won't have any FDB entries pointing to the LAG ID in hardware, but they will be present in the software bridge's FDB. Currently there is no good solution to this problem, but this will be addressed by us in the future. In order to optimize the flushing process, flush by port or LAG ID if there are no VLAN interfaces on top of the port. Otherwise, flush using (Port / LAG ID, FID=VID} for each of the lower 4K FIDs. In the case of VLAN device simply flush using {Port / LAG ID, vFID} with the vFID to which the VLAN device is mapped to. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: reg: Add the Switch Filtering DB Flush registerIdo Schimmel1-0/+88
When removing a net device from a bridge we should flush the FDB entries associated with this net device. Up until now, we relied upon bridge code to do that for us, but it is possible for user to prevent hardware from syncing with the software bridge (learning_sync=0), so we need to flush overselves. Add the Switch Filtering DB Flush (SFDF) register that is used to flush FDB entries according to different parameters (per-port, per-FID etc). Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28mlxsw: spectrum: Handle port leaving LAG while bridgedIdo Schimmel3-3/+36
It is possible for a user to remove a port from a LAG device, while the LAG device or VLAN devices on top of it are bridged. In these cases, bridge's teardown sequence is never issued, so we need to take care of it ourselves. When LAG's unlinking event is received by port netdev: 1) Traverse its vPorts list and make those member in a bridge leave it. They will be deleted later by LAG code. 2) Make the port netdev itself leave its bridge if member in one. Fixes: 0d65fc13042f ("mlxsw: spectrum: Implement LAG port join/leave") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-23Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdmaLinus Torvalds13-170/+452
Pull rdma updates from Doug Ledford: "Initial roundup of 4.5 merge window patches - Remove usage of ib_query_device and instead store attributes in ib_device struct - Move iopoll out of block and into lib, rename to irqpoll, and use in several places in the rdma stack as our new completion queue polling library mechanism. Update the other block drivers that already used iopoll to use the new mechanism too. - Replace the per-entry GID table locks with a single GID table lock - IPoIB multicast cleanup - Cleanups to the IB MR facility - Add support for 64bit extended IB counters - Fix for netlink oops while parsing RDMA nl messages - RoCEv2 support for the core IB code - mlx4 RoCEv2 support - mlx5 RoCEv2 support - Cross Channel support for mlx5 - Timestamp support for mlx5 - Atomic support for mlx5 - Raw QP support for mlx5 - MAINTAINERS update for mlx4/mlx5 - Misc ocrdma, qib, nes, usNIC, cxgb3, cxgb4, mlx4, mlx5 updates - Add support for remote invalidate to the iSER driver (pushed through the RDMA tree due to dependencies, acknowledged by nab) - Update to NFSoRDMA (pushed through the RDMA tree due to dependencies, acknowledged by Bruce)" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (169 commits) IB/mlx5: Unify CQ create flags check IB/mlx5: Expose Raw Packet QP to user space consumers {IB, net}/mlx5: Move the modify QP operation table to mlx5_ib IB/mlx5: Support setting Ethernet priority for Raw Packet QPs IB/mlx5: Add Raw Packet QP query functionality IB/mlx5: Add create and destroy functionality for Raw Packet QP IB/mlx5: Refactor mlx5_ib_qp to accommodate other QP types IB/mlx5: Allocate a Transport Domain for each ucontext net/mlx5_core: Warn on unsupported events of QP/RQ/SQ net/mlx5_core: Add RQ and SQ event handling net/mlx5_core: Export transport objects IB/mlx5: Expose CQE version to user-space IB/mlx5: Add CQE version 1 support to user QPs and SRQs IB/mlx5: Fix data validation in mlx5_ib_alloc_ucontext IB/sa: Fix netlink local service GFP crash IB/srpt: Remove redundant wc array IB/qib: Improve ipoib UD performance IB/mlx4: Advertise RoCE v2 support IB/mlx4: Create and use another QP1 for RoCEv2 IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers ...
2016-01-21{IB, net}/mlx5: Move the modify QP operation table to mlx5_ibmajd@mellanox.com1-46/+2
When modifying a QP, the desired operation was determined in the mlx5_core using a transition table that takes the current state, the final state, and returns the desired operation. Since this logic will be used for Raw Packet QP, move the operation table to the mlx5_ib. Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-21IB/mlx5: Support setting Ethernet priority for Raw Packet QPsmajd@mellanox.com1-0/+12
When the user changes the Address Vector(AV) in the modify QP, he provides an SL. This SL should be translated to Ethernet Priority by taking the 3 LSB bits, and modify the QP's TIS according to this Ethernet priority. Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-21IB/mlx5: Add Raw Packet QP query functionalitymajd@mellanox.com1-0/+24
Since Raw Packet QP is composed of RQ and SQ, the IB QP's state is derived from the sub-objects. Therefore we need to query each one of the sub-objects, and decide on the IB QP's state. Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-21net/mlx5_core: Warn on unsupported events of QP/RQ/SQmajd@mellanox.com1-0/+52
When an event arrives on QP/RQ/SQ, check whether it's supported, and print a warning message otherwise. Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-21net/mlx5_core: Add RQ and SQ event handlingmajd@mellanox.com2-19/+108
RQ/SQ will be used to implement IB verbs QPs, so the IB QP affiliated events are affiliated also with SQs and RQs. Since SQ, RQ and QP resource numbers do not share the same name space, a queue type field was added to the event data to specify the SW object that the event is affiliated with. Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-21net/mlx5_core: Export transport objectsmajd@mellanox.com5-80/+16
To be used by mlx5_ib in the following patches for implementing RAW PACKET QP. Add mlx5_core_ prefix to alloc and delloc transport_domain since they are exposed now. Signed-off-by: Majd Dibbiny <majd@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-21IB/mlx5: Add CQE version 1 support to user QPs and SRQsHaggai Abramovsky3-13/+0
Enforce working with CQE version 1 when the user supports CQE version 1 and asked to work this way. If the user still works with CQE version 0, then use the default CQE version to tell the Firmware that the user still works in the older mode. After this patch, the kernel still reports CQE version 0. Signed-off-by: Haggai Abramovsky <hagaya@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-19net/mlx4_core: Add support for RoCE v2 entropyMoni Shoua1-0/+26
In RoCE v2 we need to choose a source UDP port, we do so by using entropy over the source and dest QPNs. Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-19net/mlx4_core: Add support for configuring RoCE v2 UDP portMoni Shoua1-1/+15
In order to support RoCE v2, the hardware needs to be configured to classify certain UDP packets as RoCE v2 packets and pass it through its RoCE pipeline. This patch enables configuring this UDP port. Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-19net/mlx4_core: Configure mlx4 hardware for mixed RoCE v1/v2 modesMoni Shoua2-1/+11
If the hardware supports RoCE v2 (mixed with RoCE v1) mode, we enable it. This is necessary in order to support RoCE v2. Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-19net/mlx4: Query RoCE supportMoni Shoua1-0/+23
Query the RoCE support from firmware using the appropriate firmware commands. Downstream patches will read these capabilities and act accordingly. Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-01-17net/mlx5_core: Fix trimming down IRQ numberDoron Tsur2-4/+5
With several ConnectX-4 cards installed on a server, one may receive irqn > 255 from the kernel API, which we mistakenly trim to 8bit. This causes EQ creation failure with the following stack trace: [<ffffffff812a11f4>] dump_stack+0x48/0x64 [<ffffffff810ace21>] __setup_irq+0x3a1/0x4f0 [<ffffffff810ad7e0>] request_threaded_irq+0x120/0x180 [<ffffffffa0923660>] ? mlx5_eq_int+0x450/0x450 [mlx5_core] [<ffffffffa0922f64>] mlx5_create_map_eq+0x1e4/0x2b0 [mlx5_core] [<ffffffffa091de01>] alloc_comp_eqs+0xb1/0x180 [mlx5_core] [<ffffffffa091ea99>] mlx5_dev_init+0x5e9/0x6e0 [mlx5_core] [<ffffffffa091ec29>] init_one+0x99/0x1c0 [mlx5_core] [<ffffffff812e2afc>] local_pci_probe+0x4c/0xa0 Fixing it by changing of the irqn type from u8 to unsigned int to support values > 255 Fixes: 61d0e73e0a5a ('net/mlx5_core: Use the the real irqn in eq->irqn') Reported-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Doron Tsur <doront@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-13mlxsw: fix SWITCHDEV_OBJ_ID_PORT_MDBDan Carpenter1-0/+1
There is a missing break statement so we always return -EOPNOTSUPP. Fixes: 3a49b4fde2a1 ('mlxsw: Adding layer 2 multicast support') Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2-0/+6
Conflicts: drivers/net/bonding/bond_main.c drivers/net/ethernet/mellanox/mlxsw/spectrum.h drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c The bond_main.c and mellanox switch conflicts were cases of overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Export flow steering APIMaor Gottlieb1-0/+5
Add exports to flow steering API for mlx5_ib usage. The following functions are exported: 1. mlx5_create_auto_grouped_flow_table - used to create flow table with auto flow grouping management (create and destroy flow groups). In auto-grouped flow tables, we create groups automatically if needed (if we don't find an existing flow group with same match criteria when we add new rule). 2. mlx5_destroy_flow_table - used to destroy a flow table. 3. mlx5_add_flow_rule - used to add flow rule into a flow table. 4. mlx5_del_flow_rule - used to delete flow rule from its flow table. 5. mlx5_get_flow_namespace - used to get a handle to the required namespace sub-tree. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Enable flow steering support for the IB driverMaor Gottlieb1-8/+47
When the driver is loaded, we create flow steering namespace for kernel bypass with nine priorities and another namespace for leftovers(in order to catch packets that weren't matched). Verbs applications will use these priorities. we found nine as a number that balances the requirements from the user and retains performance. The bypass namespace is used by verbs applications that want to bypass the kernel networking stack. The leftovers namespace is used by verbs applications and the sniffer in order to catch packets that weren't handled by any preceding rules. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Initialize namespaces only when supported by deviceMaor Gottlieb1-21/+49
Before we create the sub tree of a steering namespaces(kernel, bypass, leftovers) we check that the device has the required capabilities in order to create this subtree. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Set priority attributesMaor Gottlieb2-19/+55
Each priority has two attributes: 1. max_ft - maximum allowed flow tables under this priority. 2. start_level - start level range of the flow tables in the priority. These attributes are set by traversing the tree nodes by DFS and set start level and max flow tables to each priority. Start level depends on the max flow tables of the prior priorities in the tree. The leaves of the trees have max_ft set in them. Each node accumulates the max_ft of its children and set it accordingly. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Connect flow tablesMaor Gottlieb3-10/+104
Flow tables from different priorities should be chained together. When a packet arrives we search for a match in the by-pass flow tables (first we search for a match in priority 0 and if we don't find a match we move to the next priority). If we can't find a match in any of the bypass flow-tables, we continue searching in the flow-tables of the next priority, which are the kernel's flow tables. Setting the miss flow table in a new flow table to be the next one in the list is performed via create flow table API. If we want to change an existing flow table, for example in order to point from an existing flow table to the new next-in-list flow table, we use the modify flow table API. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Introduce modify flow table commandMaor Gottlieb2-0/+31
Introduce the modify flow table command. This command is used when we want to change the next flow table of an existing flow table. The next flow table is defined as the table we search (in order to find a match), if we couldn't find a match in any of the flow table entries in the current flow table. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Managing root flow tableMaor Gottlieb4-9/+114
The root Flow Table for each Flow Table Type is defined, by default, as the Flow Table with level 0. In order not to use an empty flow tables and introduce new hops, but still preserve space for flow-tables that have a priority greater(lower number) than the current flow table, we introduce this new set root flow table command. This command tells the HW to start matching packets from the assigned root flow table. This command is used when we create new flow table with level lower than the current lowest flow table or it is the first flow table. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Add utilities to find next and prev flow-tablesMaor Gottlieb1-0/+67
Add two utility functions for find next and prev flow table. Find next flow table function gets priority and return the first flow table of the next priority in the tree. Find prev flow table return the last flow table of the previous priority in the tree. These utility functions are used for chaining flow table from different priorities. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11net/mlx5_core: Introduce flow steering autogrouped flow tableMaor Gottlieb2-19/+152
When user add rule to autogrouped flow table, we search for flow group with the same match criteria, if we don't find such group then we create new flow group with the required match criteria and insert the rule to this group. We divide the flow table into required_groups + 1, in order to reserve a part of the flow table for rules which don't match any existing group. Signed-off-by: Maor Gottlieb <maorg@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-11mlxsw: spectrum: Add FDB lock to prevent session interleavingIdo Schimmel2-0/+6
Dumping the FDB (invoked with a process context) or handling FDB notifications (polled periodicly in delayed work) might each entail multiple EMAD transcations due to the number of entries. While we only allow one EMAD transaction at a time, there is nothing stopping the dump and notification processing sessions from interleaving. However, this is forbidden by the hardware, so we need to make sure only one of these sessions can run at a time. Solve this by adding a mutex ('fdb_lock'), as both kernel threads can sleep while waiting for the response EMAD. Fixes: 56ade8fe3f ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.