From 5930e8d0ab3689f1e239566443ca8f53e45e01cc Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 15 Oct 2013 16:55:22 +0200 Subject: net/mlx4: Fix typo, move similar defs to same location Small code cleanup: 1. change MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN to MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN 2. put MLX4_SET_PORT_PRIO2TC and MLX4_SET_PORT_SCHEDULER in the same union with the other MLX4_SET_PORT_yyy Signed-off-by: Or Gerlitz Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 6 ++---- include/linux/mlx4/device.h | 2 +- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux/mlx4') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index cd1fdf75103b..8df61bc5da00 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -154,10 +154,6 @@ enum { MLX4_CMD_QUERY_IF_STAT = 0X54, MLX4_CMD_SET_IF_STAT = 0X55, - /* set port opcode modifiers */ - MLX4_SET_PORT_PRIO2TC = 0x8, - MLX4_SET_PORT_SCHEDULER = 0x9, - /* register/delete flow steering network rules */ MLX4_QP_FLOW_STEERING_ATTACH = 0x65, MLX4_QP_FLOW_STEERING_DETACH = 0x66, @@ -182,6 +178,8 @@ enum { MLX4_SET_PORT_VLAN_TABLE = 0x3, MLX4_SET_PORT_PRIO_MAP = 0x4, MLX4_SET_PORT_GID_TABLE = 0x5, + MLX4_SET_PORT_PRIO2TC = 0x8, + MLX4_SET_PORT_SCHEDULER = 0x9, }; enum { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 24ce6bdd540e..9ad0c18495ad 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -155,7 +155,7 @@ enum { MLX4_DEV_CAP_FLAG2_RSS_TOP = 1LL << 1, MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2, MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3, - MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4, + MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN = 1LL << 4, MLX4_DEV_CAP_FLAG2_TS = 1LL << 5, MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6, MLX4_DEV_CAP_FLAG2_FSM = 1LL << 7, -- cgit v1.2.2 From acddd5dd44d4fd9b45dd5ee69cd8b183052b1cdc Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sun, 3 Nov 2013 10:03:18 +0200 Subject: net/mlx4_core: Fix reg/unreg vlan/mac to conform to the firmware spec The functions mlx4_register_vlan, mlx4_unregister_vlan, mlx4_register_mac, mlx4_unregister_mac all made illegal use of the out_param in multifunc mode to pass the port number. The firmware spec specifies that the port number should be passed in bits 8..15 of the input-modifier field for ALLOC_RES and FREE_RES (sections 20.15.1 and 20.15.2). For MAC register/unregister, this patch contains workarounds so that guests running previous kernels continue to work on a new Hypervisor, and guests running the new kernel will continue to work on old hypervisors. Vlan registeration capability is still not operational in multifunction mode, since the vlan wrapper functions are not implemented in this patch. Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mlx4') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 9ad0c18495ad..297a16309f00 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -54,6 +54,7 @@ enum { MLX4_FLAG_MASTER = 1 << 2, MLX4_FLAG_SLAVE = 1 << 3, MLX4_FLAG_SRIOV = 1 << 4, + MLX4_FLAG_OLD_REG_MAC = 1 << 6, }; enum { -- cgit v1.2.2 From 2009d0059c084288f060b1ffe3d14229588acb67 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sun, 3 Nov 2013 10:03:19 +0200 Subject: net/mlx4_en: Use vlan id instead of vlan index for unregistration Use of vlan_index created problems unregistering vlans on guests. In addition, tools delete vlan by tag, not by index, lets follow that. Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mlx4') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 297a16309f00..e2e92885bdc1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1079,7 +1079,7 @@ int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw, u8 *pg, u16 *ratelimit); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); -void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index); +void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan); int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list, int npages, u64 iova, u32 *lkey, u32 *rkey); -- cgit v1.2.2 From 5a0d0a6161aecbbc76e4c1d2b82e4c7cef88bb29 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sun, 3 Nov 2013 10:03:23 +0200 Subject: mlx4: Structures and init/teardown for VF resource quotas This is step #1 for implementing SRIOV resource quotas for VFs. Quotas are implemented per resource type for VFs and the PF, to prevent any entity from simply grabbing all the resources for itself and leaving the other entities unable to obtain such resources. Resources which are allocated using quotas: QPs, CQs, SRQs, MPTs, MTTs, MAC, VLAN, and Counters. The quota system works as follows: Each entity (VF or PF) is given a max number of a given resource (its quota), and a guaranteed minimum number for each resource (starvation prevention). For QPs, CQs, SRQs, MPTs and MTTs: 50% of the available quantity for the resource is divided equally among the PF and all the active VFs (i.e., the number of VFs in the mlx4_core module parameter "num_vfs"). This 50% represents the "guaranteed minimum" pool. The other 50% is the "free pool", allocated on a first-come-first-serve basis. For each VF/PF, resources are first allocated from its "guaranteed-minimum" pool. When that pool is exhausted, the driver attempts to allocate from the resource "free-pool". The quota (i.e., max) for the VFs and the PF is: The free-pool amount (50% of the real max) + the guaranteed minimum For MACs: Guarantee 2 MACs per VF/PF per port. As a result, since we have only 128 MACs per port, reduce the allowable number of VFs from 64 to 63. Any remaining MACs are put into a free pool. For VLANs: For the PF, the per-port quota is 128 and guarantee is 64 (to allow the PF to register at least a VLAN per VF in VST mode). For the VFs, the per-port quota is 64 and the guarantee is 0. We assume that VGT VFs are trusted not to abuse the VLAN resource. For Counters: For all functions (PF and VFs), the quota is 128 and the guarantee is 0. In this patch, we define the needed structures, which are added to the resource-tracker struct. In addition, we do initialization for the resource quota, and adjust the query_device response to use quotas rather than resource maxima. As part of the implementation, we introduce a new field in mlx4_dev: quotas. This field holds the resource quotas used to report maxima to the upper layers (ib_core, via query_device). The HCA maxima of these values are passed to the VFs (via QUERY_HCA) so that they may continue to use these in handling QPs, CQs, SRQs and MPTs. Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux/mlx4') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e2e92885bdc1..f6f59271f857 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -641,12 +641,23 @@ struct mlx4_counter { __be64 tx_bytes; }; +struct mlx4_quotas { + int qp; + int cq; + int srq; + int mpt; + int mtt; + int counter; + int xrcd; +}; + struct mlx4_dev { struct pci_dev *pdev; unsigned long flags; unsigned long num_slaves; struct mlx4_caps caps; struct mlx4_phys_caps phys_caps; + struct mlx4_quotas quotas; struct radix_tree_root qp_table_tree; u8 rev_id; char board_id[MLX4_BOARD_ID_LEN]; @@ -772,6 +783,12 @@ static inline int mlx4_is_master(struct mlx4_dev *dev) return dev->flags & MLX4_FLAG_MASTER; } +static inline int mlx4_num_reserved_sqps(struct mlx4_dev *dev) +{ + return dev->phys_caps.base_sqpn + 8 + + 16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev); +} + static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn) { return (qpn < dev->phys_caps.base_sqpn + 8 + -- cgit v1.2.2 From 6e7136ed7793fa4948b0192dcd6862d12a50d67c Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Thu, 7 Nov 2013 12:19:53 +0200 Subject: net/mlx4_core: ICM pages are allocated on device NUMA node This is done to optimize FW/HW access to host memory. Signed-off-by: Yevgeny Petrilin Signed-off-by: Eugenia Emantayev Reviewed-by: Hadar Hen Zion Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mlx4') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index f6f59271f857..4cf0b0153639 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -662,6 +662,7 @@ struct mlx4_dev { u8 rev_id; char board_id[MLX4_BOARD_ID_LEN]; int num_vfs; + int numa_node; int oper_log_mgm_entry_size; u64 regid_promisc_array[MLX4_MAX_PORTS + 1]; u64 regid_allmulti_array[MLX4_MAX_PORTS + 1]; -- cgit v1.2.2 From 163561a4e2f8af44e96453bc10c7a4f9bcc736e1 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Thu, 7 Nov 2013 12:19:54 +0200 Subject: net/mlx4_en: Datapath structures are allocated per NUMA node For each RX/TX ring and its CQ, allocation is done on a NUMA node that corresponds to the core that the data structure should operate on. The assumption is that the core number is reflected by the ring index. The affected allocations are the ring/CQ data structures, the TX/RX info and the shared HW/SW buffer. For TX rings, each core has rings of all UPs. Signed-off-by: Yevgeny Petrilin Signed-off-by: Eugenia Emantayev Reviewed-by: Hadar Hen Zion Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mlx4') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 4cf0b0153639..7d3a523160ba 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -835,7 +835,7 @@ void mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn); int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar); void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar); -int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf); +int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf, int node); void mlx4_bf_free(struct mlx4_dev *dev, struct mlx4_bf *bf); int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift, -- cgit v1.2.2