kernel/linux.git/include/linux/mlx5/device.h, branch v4.7.4

net/mlx5: Fix flow steering NIC capabilities check

2016-06-10T05:06:25+00:00

Flow steering infrastructure is currently used only on link layer ethernet, therefore the driver should initialize the flow steering when the device link layer is ethernet. In addition, add missing capability check before initializing the namespace of NIC RX flow tables. Fixes: 2530236303d9 ('net/mlx5_core: Flow steering tree initialization') Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller

net/mlx5: Fix MLX5_CMD_OP_MAX to be defined correctly

2016-06-10T05:06:25+00:00

Having MLX5_CMD_OP_MAX on another file causes us to repeatedly miss accounting new commands added to the driver and hence there're no entries for them in debugfs. To solve that, we integrate it into the commands enum as the last entry. Fixes: 34a40e689393 ('net/mlx5_core: Introduce modify flow table command') Signed-off-by: Shahar Klein Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller

net/mlx5e: CQE compression

2016-05-11T23:42:39+00:00

CQE compression feature is meant to save PCIe bandwidth by compressing few CQEs into smaller amount of bytes on PCIe. CQE compression can be selectively enabled per CQ. By default is disabled for now and will be enabled later on. Signed-off-by: Tariq Toukan Signed-off-by: Eugenia Emantayev Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller

net/mlx5: Flow steering, Add vport ACL support

2016-05-04T18:04:46+00:00

Update the relevant flow steering device structs and commands to support vport. Update the flow steering core API to receive vport number. Add ingress and egress ACL flow table name spaces. Add ACL flow table support: * ACL (Access Control List) flow table is a table that contains only allow/drop steering rules. * We have two types of ACL flow tables - ingress and egress. * ACLs handle traffic sent from/to E-Switch FDB table, Ingress refers to traffic sent from Vport to E-Switch and Egress refers to traffic sent from E-Switch to vport. * Ingress ACL flow table allow/drop rules is checked against traffic sent from VF. * Egress ACL flow table allow/drop rules is checked against traffic sent to VF. Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

2016-05-04T04:52:29+00:00

Conflicts: net/ipv4/ip_gre.c Minor conflicts between tunnel bug fixes in net and ipv6 tunnel cleanups in net-next. Signed-off-by: David S. Miller

IB/mlx5: Expose correct max_sge_rd limit

2016-04-28T14:49:17+00:00

mlx5 devices (Connect-IB, ConnectX-4, ConnectX-4-LX) has a limitation where rdma read work queue entries cannot exceed 512 bytes. A rdma_read wqe needs to fit in 512 bytes: - wqe control segment (16 bytes) - rdma segment (16 bytes) - scatter elements (16 bytes each) So max_sge_rd should be: (512 - 16 - 16) / 16 = 30. Cc: linux-stable@vger.kernel.org Reported-by: Christoph Hellwig Tested-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford

net/mlx5e: Fix checksum handling for non-stripped vlan packets

2016-04-26T19:58:03+00:00

Now as rx-vlan offload can be disabled, packets can be received with vlan tag not stripped, which means is_first_ethertype_ip will return false, for that we need to check if the hardware reported csum OK so we will report CHECKSUM_UNNECESSARY for those packets. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller

net/mlx5e: Add link down events counter

2016-04-26T19:58:01+00:00

Expose link_down_events counter through ethtool -S. This counter is read from PPort statistics, then proccessed and stored as a special handling software counter. This counter is stored along software counters since it is the only PPort counter that it's size is not 64 bits. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller

net/mlx5e: Statistics handling refactoring

2016-04-26T19:58:01+00:00

Redesign ethtool statistics handling and reporting in the driver: 1. Move counters to a separate file (en_stats.h). 2. Remove unnecessary dependencies between stats and strings. 3. Use counter descriptors which hold a name and offset for each counter, and will be used to decide which counters will be exposed. For example when adding a new software counter to ethtool, instead of: 1. Add to stats struct. 2. Add to strings struct in the same order. 3. Change macro defining number of software counters. The only thing needed is to link the new counter to a counter descriptor. VPort counters are a set of hardware traffic counters created automatically for each virtual port opened. PPort counters are a set of counters describing per physical port performance statistics. These counters are gathered from hardware register and divided to groups according to different protocols. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller

net/mlx5e: Support RX multi-packet WQE (Striding RQ)

2016-04-21T19:09:05+00:00

Introduce the feature of multi-packet WQE (RX Work Queue Element) referred to as (MPWQE or Striding RQ), in which WQEs are larger and serve multiple packets each. Every WQE consists of many strides of the same size, every received packet is aligned to a beginning of a stride and is written to consecutive strides within a WQE. In the regular approach, each regular WQE is big enough to be capable of serving one received packet of any size up to MTU or 64K in case of device LRO is enabled, making it very wasteful when dealing with small packets or device LRO is enabled. For its flexibility, MPWQE allows a better memory utilization (implying improvements in CPU utilization and packet rate) as packets consume strides according to their size, preserving the rest of the WQE to be available for other packets. MPWQE default configuration: Num of WQEs = 16 Strides Per WQE = 2048 Stride Size = 64 byte The default WQEs memory footprint went from 1024*mtu (~1.5MB) to 16 * 2048 * 64 = 2MB per ring. However, HW LRO can now be supported at no additional cost in memory footprint, and hence we turn it on by default and get an even better performance. Performance tested on ConnectX4-Lx 50G. To isolate the feature under test, the numbers below were measured with HW LRO turned off. We verified that the performance just improves when LRO is turned back on. * Netperf single TCP stream: - BW raised by 10-15% for representative packet sizes: default, 64B, 1024B, 1478B, 65536B. * Netperf multi TCP stream: - No degradation, line rate reached. * Pktgen: packet rate raised by 2-10% for traffic of different message sizes: 64B, 128B, 256B, 1024B, and 1500B. * Pktgen: packet loss in bursts of small messages (64byte), single stream: - | num packets | packets loss before | packets loss after | 2K | ~ 1K | 0 | 8K | ~ 6K | 0 | 16K | ~13K | 0 | 32K | ~28K | 0 | 64K | ~57K | ~24K As expected as the driver can receive as many small packets (<=64B) as the number of total strides in the ring (default = 2048 * 16) vs. 1024 (default ring size regardless of packets size) before this feature. Signed-off-by: Tariq Toukan Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller