OpenCloudOS-Kernel/include/linux/mlx4/device.h

1150 lines
29 KiB
C
Raw Normal View History

/*
* Copyright (c) 2006, 2007 Cisco Systems, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef MLX4_DEVICE_H
#define MLX4_DEVICE_H
#include <linux/if_ether.h>
#include <linux/pci.h>
#include <linux/completion.h>
#include <linux/radix-tree.h>
#include <linux/cpu_rmap.h>
#include <linux/atomic.h>
#include <linux/clocksource.h>
#define MAX_MSIX_P_PORT 17
#define MAX_MSIX 64
#define MSIX_LEGACY_SZ 4
#define MIN_MSIX_P_PORT 5
enum {
MLX4_FLAG_MSI_X = 1 << 0,
MLX4_FLAG_OLD_PORT_CMDS = 1 << 1,
MLX4_FLAG_MASTER = 1 << 2,
MLX4_FLAG_SLAVE = 1 << 3,
MLX4_FLAG_SRIOV = 1 << 4,
MLX4_FLAG_OLD_REG_MAC = 1 << 6,
};
enum {
MLX4_PORT_CAP_IS_SM = 1 << 1,
MLX4_PORT_CAP_DEV_MGMT_SUP = 1 << 19,
};
enum {
MLX4_MAX_PORTS = 2,
MLX4_MAX_PORT_PKEYS = 128
};
mlx4_core: Implement mechanism for reserved Q_Keys The SR-IOV special QP tunneling mechanism uses proxy special QPs (instead of the real special QPs) for MADs on guests. These proxy QPs send their packets to a "tunnel" QP owned by the master. The master then forwards the MAD (after any required paravirtualization) to the real special QP, which sends out the MAD. For security reasons (i.e., to prevent guests from sending MADs to tunnel QPs belonging to other guests), each proxy-tunnel QP pair is assigned a unique, reserved, Q_Key. These Q_Keys are available only for proxy and tunnel QPs -- if the guest tries to use these Q_Keys with other QPs, it will fail. This patch introduces a mechanism for reserving a block of 64K Q_Keys for proxy/tunneling use. The patch introduces also two new fields into mlx4_dev: base_sqpn and base_tunnel_sqpn. In SR-IOV mode, the QP numbers for the "real," proxy, and tunnel sqps are added to the reserved QPN area (so that they will not change). There are 8 special QPs per port in the HCA, and each of them is assigned both a proxy and a tunnel QP, for each VF and for the PF as well in SR-IOV mode. The QPNs for these QPs are arranged as follows: 1. The real SQP numbers (8) 2. The proxy SQPs (8 * (max number of VFs + max number of PFs) 3. The tunnel SQPs (8 * (max number of VFs + max number of PFs) To support these QPs, two new fields are added to struct mlx4_dev: base_sqp: this is the QP number of the first of the real SQPs base_tunnel_sqp: this is the qp number of the first qp in the tunnel sqp region. (On guests, this is the first tunnel sqp of the 8 which are assigned to that guest). In addition, in SR-IOV mode, sqp_start is the number of the first proxy SQP in the proxy SQP region. (In guests, this is the first proxy SQP of the 8 which are assigned to that guest) Note that in non-SR-IOV mode, there are no proxies and no tunnels. In this case, sqp_start is set to sqp_base -- which minimizes code changes. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-19 16:21:42 +08:00
/* base qkey for use in sriov tunnel-qp/proxy-qp communication.
* These qkeys must not be allowed for general use. This is a 64k range,
* and to test for violation, we use the mask (protect against future chg).
*/
#define MLX4_RESERVED_QKEY_BASE (0xFFFF0000)
#define MLX4_RESERVED_QKEY_MASK (0xFFFF0000)
enum {
MLX4_BOARD_ID_LEN = 64
};
enum {
MLX4_MAX_NUM_PF = 16,
MLX4_MAX_NUM_VF = 64,
MLX4_MFUNC_MAX = 80,
MLX4_MAX_EQ_NUM = 1024,
MLX4_MFUNC_EQ_NUM = 4,
MLX4_MFUNC_MAX_EQES = 8,
MLX4_MFUNC_EQE_MASK = (MLX4_MFUNC_MAX_EQES - 1)
};
/* Driver supports 3 diffrent device methods to manage traffic steering:
* -device managed - High level API for ib and eth flow steering. FW is
* managing flow steering tables.
* - B0 steering mode - Common low level API for ib and (if supported) eth.
* - A0 steering mode - Limited low level API for eth. In case of IB,
* B0 mode is in use.
*/
enum {
MLX4_STEERING_MODE_A0,
MLX4_STEERING_MODE_B0,
MLX4_STEERING_MODE_DEVICE_MANAGED
};
static inline const char *mlx4_steering_mode_str(int steering_mode)
{
switch (steering_mode) {
case MLX4_STEERING_MODE_A0:
return "A0 steering";
case MLX4_STEERING_MODE_B0:
return "B0 steering";
case MLX4_STEERING_MODE_DEVICE_MANAGED:
return "Device managed flow steering";
default:
return "Unrecognize steering mode";
}
}
enum {
MLX4_DEV_CAP_FLAG_RC = 1LL << 0,
MLX4_DEV_CAP_FLAG_UC = 1LL << 1,
MLX4_DEV_CAP_FLAG_UD = 1LL << 2,
MLX4_DEV_CAP_FLAG_XRC = 1LL << 3,
MLX4_DEV_CAP_FLAG_SRQ = 1LL << 6,
MLX4_DEV_CAP_FLAG_IPOIB_CSUM = 1LL << 7,
MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8,
MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9,
MLX4_DEV_CAP_FLAG_DPDP = 1LL << 12,
MLX4_DEV_CAP_FLAG_BLH = 1LL << 15,
MLX4_DEV_CAP_FLAG_MEM_WINDOW = 1LL << 16,
MLX4_DEV_CAP_FLAG_APM = 1LL << 17,
MLX4_DEV_CAP_FLAG_ATOMIC = 1LL << 18,
MLX4_DEV_CAP_FLAG_RAW_MCAST = 1LL << 19,
MLX4_DEV_CAP_FLAG_UD_AV_PORT = 1LL << 20,
MLX4_DEV_CAP_FLAG_UD_MCAST = 1LL << 21,
MLX4_DEV_CAP_FLAG_IBOE = 1LL << 30,
MLX4_DEV_CAP_FLAG_UC_LOOPBACK = 1LL << 32,
MLX4_DEV_CAP_FLAG_FCS_KEEP = 1LL << 34,
MLX4_DEV_CAP_FLAG_WOL_PORT1 = 1LL << 37,
MLX4_DEV_CAP_FLAG_WOL_PORT2 = 1LL << 38,
MLX4_DEV_CAP_FLAG_UDP_RSS = 1LL << 40,
MLX4_DEV_CAP_FLAG_VEP_UC_STEER = 1LL << 41,
MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42,
MLX4_DEV_CAP_FLAG_COUNTERS = 1LL << 48,
MLX4_DEV_CAP_FLAG_SET_ETH_SCHED = 1LL << 53,
mlx4: Use port management change event instead of smp_snoop The port management change event can replace smp_snoop. If the capability bit for this event is set in dev-caps, the event is used (by the driver setting the PORT_MNG_CHG_EVENT bit in the async event mask in the MAP_EQ fw command). In this case, when the driver passes incoming SMP PORT_INFO SET mads to the FW, the FW generates port management change events to signal any changes to the driver. If the FW generates these events, smp_snoop shouldn't be invoked in ib_process_mad(), or duplicate events will occur (once from the FW-generated event, and once from smp_snoop). In the case where the FW does not generate port management change events smp_snoop needs to be invoked to create these events. The flow in smp_snoop has been modified to make use of the same procedures as in the fw-generated-event event case to generate the port management events (LID change, Client-rereg, Pkey change, and/or GID change). Port management change event handling required changing the mlx4_ib_event and mlx4_dispatch_event prototypes; the "param" argument (last argument) had to be changed to unsigned long in order to accomodate passing the EQE pointer. We also needed to move the definition of struct mlx4_eqe from net/mlx4.h to file device.h -- to make it available to the IB driver, to handle port management change events. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-19 16:21:40 +08:00
MLX4_DEV_CAP_FLAG_SENSE_SUPPORT = 1LL << 55,
MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV = 1LL << 59,
mlx4: 64-byte CQE/EQE support ConnectX-3 devices can use either 64- or 32-byte completion queue entries (CQEs) and event queue entries (EQEs). Using 64-byte EQEs/CQEs performs better because each entry is aligned to a complete cacheline. This patch queries the HCA's capabilities, and if it supports 64-byte CQEs and EQES the driver will configure the HW to work in 64-byte mode. The 32-byte vs 64-byte mode is global per HCA and not per CQ or EQ. Since this mode is global, userspace (libmlx4) must be updated to work with the configured CQE size, and guests using SR-IOV virtual functions need to know both EQE and CQE size. In case one of the 64-byte CQE/EQE capabilities is activated, the patch makes sure that older guest drivers that use the QUERY_DEV_FUNC command (e.g as done in mlx4_core of Linux 3.3..3.6) will notice that they need an update to be able to work with the PPF. This is done by changing the returned pf_context_behaviour not to be zero any more. In case none of these capabilities is activated that value remains zero and older guest drivers can run OK. The SRIOV related flow is as follows 1. the PPF does the detection of the new capabilities using QUERY_DEV_CAP command. 2. the PPF activates the new capabilities using INIT_HCA. 3. the VF detects if the PPF activated the capabilities using QUERY_HCA, and if this is the case activates them for itself too. Note that the VF detects that it must be aware to the new PF behaviour using QUERY_FUNC_CAP. Steps 1 and 2 apply also for native mode. User space notification is done through a new field introduced in struct mlx4_ib_ucontext which holds device capabilities for which user space must take action. This changes the binary interface so the ABI towards libmlx4 exposed through uverbs is bumped from 3 to 4 but only when **needed** i.e. only when the driver does use 64-byte CQEs or future device capabilities which must be in sync by user space. This practice allows to work with unmodified libmlx4 on older devices (e.g A0, B0) which don't support 64-byte CQEs. In order to keep existing systems functional when they update to a newer kernel that contains these changes in VF and userspace ABI, a module parameter enable_64b_cqe_eqe must be set to enable 64-byte mode; the default is currently false. Signed-off-by: Eli Cohen <eli@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-10-21 22:59:24 +08:00
MLX4_DEV_CAP_FLAG_64B_EQE = 1LL << 61,
MLX4_DEV_CAP_FLAG_64B_CQE = 1LL << 62
};
enum {
MLX4_DEV_CAP_FLAG2_RSS = 1LL << 0,
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_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,
MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8
};
mlx4: 64-byte CQE/EQE support ConnectX-3 devices can use either 64- or 32-byte completion queue entries (CQEs) and event queue entries (EQEs). Using 64-byte EQEs/CQEs performs better because each entry is aligned to a complete cacheline. This patch queries the HCA's capabilities, and if it supports 64-byte CQEs and EQES the driver will configure the HW to work in 64-byte mode. The 32-byte vs 64-byte mode is global per HCA and not per CQ or EQ. Since this mode is global, userspace (libmlx4) must be updated to work with the configured CQE size, and guests using SR-IOV virtual functions need to know both EQE and CQE size. In case one of the 64-byte CQE/EQE capabilities is activated, the patch makes sure that older guest drivers that use the QUERY_DEV_FUNC command (e.g as done in mlx4_core of Linux 3.3..3.6) will notice that they need an update to be able to work with the PPF. This is done by changing the returned pf_context_behaviour not to be zero any more. In case none of these capabilities is activated that value remains zero and older guest drivers can run OK. The SRIOV related flow is as follows 1. the PPF does the detection of the new capabilities using QUERY_DEV_CAP command. 2. the PPF activates the new capabilities using INIT_HCA. 3. the VF detects if the PPF activated the capabilities using QUERY_HCA, and if this is the case activates them for itself too. Note that the VF detects that it must be aware to the new PF behaviour using QUERY_FUNC_CAP. Steps 1 and 2 apply also for native mode. User space notification is done through a new field introduced in struct mlx4_ib_ucontext which holds device capabilities for which user space must take action. This changes the binary interface so the ABI towards libmlx4 exposed through uverbs is bumped from 3 to 4 but only when **needed** i.e. only when the driver does use 64-byte CQEs or future device capabilities which must be in sync by user space. This practice allows to work with unmodified libmlx4 on older devices (e.g A0, B0) which don't support 64-byte CQEs. In order to keep existing systems functional when they update to a newer kernel that contains these changes in VF and userspace ABI, a module parameter enable_64b_cqe_eqe must be set to enable 64-byte mode; the default is currently false. Signed-off-by: Eli Cohen <eli@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-10-21 22:59:24 +08:00
enum {
MLX4_DEV_CAP_64B_EQE_ENABLED = 1LL << 0,
MLX4_DEV_CAP_64B_CQE_ENABLED = 1LL << 1
};
enum {
MLX4_USER_DEV_CAP_64B_CQE = 1L << 0
};
enum {
MLX4_FUNC_CAP_64B_EQE_CQE = 1L << 0
};
#define MLX4_ATTR_EXTENDED_PORT_INFO cpu_to_be16(0xff90)
enum {
MLX4_BMME_FLAG_WIN_TYPE_2B = 1 << 1,
MLX4_BMME_FLAG_LOCAL_INV = 1 << 6,
MLX4_BMME_FLAG_REMOTE_INV = 1 << 7,
MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9,
MLX4_BMME_FLAG_RESERVED_LKEY = 1 << 10,
MLX4_BMME_FLAG_FAST_REG_WR = 1 << 11,
};
enum mlx4_event {
MLX4_EVENT_TYPE_COMP = 0x00,
MLX4_EVENT_TYPE_PATH_MIG = 0x01,
MLX4_EVENT_TYPE_COMM_EST = 0x02,
MLX4_EVENT_TYPE_SQ_DRAINED = 0x03,
MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE = 0x13,
MLX4_EVENT_TYPE_SRQ_LIMIT = 0x14,
MLX4_EVENT_TYPE_CQ_ERROR = 0x04,
MLX4_EVENT_TYPE_WQ_CATAS_ERROR = 0x05,
MLX4_EVENT_TYPE_EEC_CATAS_ERROR = 0x06,
MLX4_EVENT_TYPE_PATH_MIG_FAILED = 0x07,
MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR = 0x10,
MLX4_EVENT_TYPE_WQ_ACCESS_ERROR = 0x11,
MLX4_EVENT_TYPE_SRQ_CATAS_ERROR = 0x12,
MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR = 0x08,
MLX4_EVENT_TYPE_PORT_CHANGE = 0x09,
MLX4_EVENT_TYPE_EQ_OVERFLOW = 0x0f,
MLX4_EVENT_TYPE_ECC_DETECT = 0x0e,
MLX4_EVENT_TYPE_CMD = 0x0a,
MLX4_EVENT_TYPE_VEP_UPDATE = 0x19,
MLX4_EVENT_TYPE_COMM_CHANNEL = 0x18,
MLX4_EVENT_TYPE_OP_REQUIRED = 0x1a,
MLX4_EVENT_TYPE_FATAL_WARNING = 0x1b,
MLX4_EVENT_TYPE_FLR_EVENT = 0x1c,
mlx4: Use port management change event instead of smp_snoop The port management change event can replace smp_snoop. If the capability bit for this event is set in dev-caps, the event is used (by the driver setting the PORT_MNG_CHG_EVENT bit in the async event mask in the MAP_EQ fw command). In this case, when the driver passes incoming SMP PORT_INFO SET mads to the FW, the FW generates port management change events to signal any changes to the driver. If the FW generates these events, smp_snoop shouldn't be invoked in ib_process_mad(), or duplicate events will occur (once from the FW-generated event, and once from smp_snoop). In the case where the FW does not generate port management change events smp_snoop needs to be invoked to create these events. The flow in smp_snoop has been modified to make use of the same procedures as in the fw-generated-event event case to generate the port management events (LID change, Client-rereg, Pkey change, and/or GID change). Port management change event handling required changing the mlx4_ib_event and mlx4_dispatch_event prototypes; the "param" argument (last argument) had to be changed to unsigned long in order to accomodate passing the EQE pointer. We also needed to move the definition of struct mlx4_eqe from net/mlx4.h to file device.h -- to make it available to the IB driver, to handle port management change events. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-19 16:21:40 +08:00
MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT = 0x1d,
MLX4_EVENT_TYPE_NONE = 0xff,
};
enum {
MLX4_PORT_CHANGE_SUBTYPE_DOWN = 1,
MLX4_PORT_CHANGE_SUBTYPE_ACTIVE = 4
};
enum {
MLX4_FATAL_WARNING_SUBTYPE_WARMING = 0,
};
enum slave_port_state {
SLAVE_PORT_DOWN = 0,
SLAVE_PENDING_UP,
SLAVE_PORT_UP,
};
enum slave_port_gen_event {
SLAVE_PORT_GEN_EVENT_DOWN = 0,
SLAVE_PORT_GEN_EVENT_UP,
SLAVE_PORT_GEN_EVENT_NONE,
};
enum slave_port_state_event {
MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN,
MLX4_PORT_STATE_DEV_EVENT_PORT_UP,
MLX4_PORT_STATE_IB_PORT_STATE_EVENT_GID_VALID,
MLX4_PORT_STATE_IB_EVENT_GID_INVALID,
};
enum {
MLX4_PERM_LOCAL_READ = 1 << 10,
MLX4_PERM_LOCAL_WRITE = 1 << 11,
MLX4_PERM_REMOTE_READ = 1 << 12,
MLX4_PERM_REMOTE_WRITE = 1 << 13,
MLX4_PERM_ATOMIC = 1 << 14,
MLX4_PERM_BIND_MW = 1 << 15,
};
enum {
MLX4_OPCODE_NOP = 0x00,
MLX4_OPCODE_SEND_INVAL = 0x01,
MLX4_OPCODE_RDMA_WRITE = 0x08,
MLX4_OPCODE_RDMA_WRITE_IMM = 0x09,
MLX4_OPCODE_SEND = 0x0a,
MLX4_OPCODE_SEND_IMM = 0x0b,
MLX4_OPCODE_LSO = 0x0e,
MLX4_OPCODE_RDMA_READ = 0x10,
MLX4_OPCODE_ATOMIC_CS = 0x11,
MLX4_OPCODE_ATOMIC_FA = 0x12,
MLX4_OPCODE_MASKED_ATOMIC_CS = 0x14,
MLX4_OPCODE_MASKED_ATOMIC_FA = 0x15,
MLX4_OPCODE_BIND_MW = 0x18,
MLX4_OPCODE_FMR = 0x19,
MLX4_OPCODE_LOCAL_INVAL = 0x1b,
MLX4_OPCODE_CONFIG_CMD = 0x1f,
MLX4_RECV_OPCODE_RDMA_WRITE_IMM = 0x00,
MLX4_RECV_OPCODE_SEND = 0x01,
MLX4_RECV_OPCODE_SEND_IMM = 0x02,
MLX4_RECV_OPCODE_SEND_INVAL = 0x03,
MLX4_CQE_OPCODE_ERROR = 0x1e,
MLX4_CQE_OPCODE_RESIZE = 0x16,
};
enum {
MLX4_STAT_RATE_OFFSET = 5
};
enum mlx4_protocol {
MLX4_PROT_IB_IPV6 = 0,
MLX4_PROT_ETH,
MLX4_PROT_IB_IPV4,
MLX4_PROT_FCOE
};
enum {
MLX4_MTT_FLAG_PRESENT = 1
};
enum mlx4_qp_region {
MLX4_QP_REGION_FW = 0,
MLX4_QP_REGION_ETH_ADDR,
MLX4_QP_REGION_FC_ADDR,
MLX4_QP_REGION_FC_EXCH,
MLX4_NUM_QP_REGION
};
enum mlx4_port_type {
MLX4_PORT_TYPE_NONE = 0,
MLX4_PORT_TYPE_IB = 1,
MLX4_PORT_TYPE_ETH = 2,
MLX4_PORT_TYPE_AUTO = 3
};
enum mlx4_special_vlan_idx {
MLX4_NO_VLAN_IDX = 0,
MLX4_VLAN_MISS_IDX,
MLX4_VLAN_REGULAR
};
enum mlx4_steer_type {
MLX4_MC_STEER = 0,
MLX4_UC_STEER,
MLX4_NUM_STEERS
};
enum {
MLX4_NUM_FEXCH = 64 * 1024,
};
enum {
MLX4_MAX_FAST_REG_PAGES = 511,
};
mlx4: Use port management change event instead of smp_snoop The port management change event can replace smp_snoop. If the capability bit for this event is set in dev-caps, the event is used (by the driver setting the PORT_MNG_CHG_EVENT bit in the async event mask in the MAP_EQ fw command). In this case, when the driver passes incoming SMP PORT_INFO SET mads to the FW, the FW generates port management change events to signal any changes to the driver. If the FW generates these events, smp_snoop shouldn't be invoked in ib_process_mad(), or duplicate events will occur (once from the FW-generated event, and once from smp_snoop). In the case where the FW does not generate port management change events smp_snoop needs to be invoked to create these events. The flow in smp_snoop has been modified to make use of the same procedures as in the fw-generated-event event case to generate the port management events (LID change, Client-rereg, Pkey change, and/or GID change). Port management change event handling required changing the mlx4_ib_event and mlx4_dispatch_event prototypes; the "param" argument (last argument) had to be changed to unsigned long in order to accomodate passing the EQE pointer. We also needed to move the definition of struct mlx4_eqe from net/mlx4.h to file device.h -- to make it available to the IB driver, to handle port management change events. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-19 16:21:40 +08:00
enum {
MLX4_DEV_PMC_SUBTYPE_GUID_INFO = 0x14,
MLX4_DEV_PMC_SUBTYPE_PORT_INFO = 0x15,
MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE = 0x16,
};
/* Port mgmt change event handling */
enum {
MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK = 1 << 0,
MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK = 1 << 1,
MLX4_EQ_PORT_INFO_LID_CHANGE_MASK = 1 << 2,
MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK = 1 << 3,
MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK = 1 << 4,
};
#define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK)
static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
{
return (major << 32) | (minor << 16) | subminor;
}
struct mlx4_phys_caps {
u32 gid_phys_table_len[MLX4_MAX_PORTS + 1];
u32 pkey_phys_table_len[MLX4_MAX_PORTS + 1];
u32 num_phys_eqs;
u32 base_sqpn;
u32 base_proxy_sqpn;
u32 base_tunnel_sqpn;
};
struct mlx4_caps {
u64 fw_ver;
u32 function;
int num_ports;
int vl_cap[MLX4_MAX_PORTS + 1];
int ib_mtu_cap[MLX4_MAX_PORTS + 1];
__be32 ib_port_def_cap[MLX4_MAX_PORTS + 1];
u64 def_mac[MLX4_MAX_PORTS + 1];
int eth_mtu_cap[MLX4_MAX_PORTS + 1];
int gid_table_len[MLX4_MAX_PORTS + 1];
int pkey_table_len[MLX4_MAX_PORTS + 1];
int trans_type[MLX4_MAX_PORTS + 1];
int vendor_oui[MLX4_MAX_PORTS + 1];
int wavelength[MLX4_MAX_PORTS + 1];
u64 trans_code[MLX4_MAX_PORTS + 1];
int local_ca_ack_delay;
int num_uars;
u32 uar_page_size;
int bf_reg_size;
int bf_regs_per_page;
int max_sq_sg;
int max_rq_sg;
int num_qps;
int max_wqes;
int max_sq_desc_sz;
int max_rq_desc_sz;
int max_qp_init_rdma;
int max_qp_dest_rdma;
u32 *qp0_proxy;
u32 *qp1_proxy;
u32 *qp0_tunnel;
u32 *qp1_tunnel;
int num_srqs;
int max_srq_wqes;
int max_srq_sge;
int reserved_srqs;
int num_cqs;
int max_cqes;
int reserved_cqs;
int num_eqs;
int reserved_eqs;
int num_comp_vectors;
int comp_pool;
int num_mpts;
int max_fmr_maps;
int num_mtts;
int fmr_reserved_mtts;
int reserved_mtts;
int reserved_mrws;
int reserved_uars;
int num_mgms;
int num_amgms;
int reserved_mcgs;
int num_qp_per_mgm;
int steering_mode;
int fs_log_max_ucast_qp_range_size;
int num_pds;
int reserved_pds;
int max_xrcds;
int reserved_xrcds;
int mtt_entry_sz;
u32 max_msg_sz;
u32 page_size_cap;
u64 flags;
u64 flags2;
u32 bmme_flags;
u32 reserved_lkey;
u16 stat_rate_support;
u8 port_width_cap[MLX4_MAX_PORTS + 1];
int max_gso_sz;
int max_rss_tbl_sz;
int reserved_qps_cnt[MLX4_NUM_QP_REGION];
int reserved_qps;
int reserved_qps_base[MLX4_NUM_QP_REGION];
int log_num_macs;
int log_num_vlans;
int log_num_prios;
enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
u8 supported_type[MLX4_MAX_PORTS + 1];
u8 suggested_type[MLX4_MAX_PORTS + 1];
u8 default_sense[MLX4_MAX_PORTS + 1];
u32 port_mask[MLX4_MAX_PORTS + 1];
enum mlx4_port_type possible_type[MLX4_MAX_PORTS + 1];
u32 max_counters;
u8 port_ib_mtu[MLX4_MAX_PORTS + 1];
IB/mlx4: SR-IOV IB context objects and proxy/tunnel SQP support 1. Introduce the basic SR-IOV parvirtualization context objects for multiplexing and demultiplexing MADs. 2. Introduce support for the new proxy and tunnel QP types. This patch introduces the objects required by the master for managing QP paravirtualization for guests. struct mlx4_ib_sriov is created by the master only. It is a container for the following: 1. All the info required by the PPF to multiplex and de-multiplex MADs (including those from the PF). (struct mlx4_ib_demux_ctx demux) 2. All the info required to manage alias GUIDs (i.e., the GUID at index 0 that each guest perceives. In fact, this is not the GUID which is actually at index 0, but is, in fact, the GUID which is at index[<VF number>] in the physical table. 3. structures which are used to manage CM paravirtualization 4. structures for managing the real special QPs when running in SR-IOV mode. The real SQPs are controlled by the PPF in this case. All SQPs created and controlled by the ib core layer are proxy SQP. struct mlx4_ib_demux_ctx contains the information per port needed to manage paravirtualization: 1. All multicast paravirt info 2. All tunnel-qp paravirt info for the port. 3. GUID-table and GUID-prefix for the port 4. work queues. struct mlx4_ib_demux_pv_ctx contains all the info for managing the paravirtualized QPs for one slave/port. struct mlx4_ib_demux_pv_qp contains the info need to run an individual QP (either tunnel qp or real SQP). Note: We made use of the 2 most significant bits in enum mlx4_ib_qp_flags (based on enum ib_qp_create_flags in ib_verbs.h). We need these bits in the low-level driver for internal purposes. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-08-03 16:40:40 +08:00
u16 sqp_demux;
mlx4: 64-byte CQE/EQE support ConnectX-3 devices can use either 64- or 32-byte completion queue entries (CQEs) and event queue entries (EQEs). Using 64-byte EQEs/CQEs performs better because each entry is aligned to a complete cacheline. This patch queries the HCA's capabilities, and if it supports 64-byte CQEs and EQES the driver will configure the HW to work in 64-byte mode. The 32-byte vs 64-byte mode is global per HCA and not per CQ or EQ. Since this mode is global, userspace (libmlx4) must be updated to work with the configured CQE size, and guests using SR-IOV virtual functions need to know both EQE and CQE size. In case one of the 64-byte CQE/EQE capabilities is activated, the patch makes sure that older guest drivers that use the QUERY_DEV_FUNC command (e.g as done in mlx4_core of Linux 3.3..3.6) will notice that they need an update to be able to work with the PPF. This is done by changing the returned pf_context_behaviour not to be zero any more. In case none of these capabilities is activated that value remains zero and older guest drivers can run OK. The SRIOV related flow is as follows 1. the PPF does the detection of the new capabilities using QUERY_DEV_CAP command. 2. the PPF activates the new capabilities using INIT_HCA. 3. the VF detects if the PPF activated the capabilities using QUERY_HCA, and if this is the case activates them for itself too. Note that the VF detects that it must be aware to the new PF behaviour using QUERY_FUNC_CAP. Steps 1 and 2 apply also for native mode. User space notification is done through a new field introduced in struct mlx4_ib_ucontext which holds device capabilities for which user space must take action. This changes the binary interface so the ABI towards libmlx4 exposed through uverbs is bumped from 3 to 4 but only when **needed** i.e. only when the driver does use 64-byte CQEs or future device capabilities which must be in sync by user space. This practice allows to work with unmodified libmlx4 on older devices (e.g A0, B0) which don't support 64-byte CQEs. In order to keep existing systems functional when they update to a newer kernel that contains these changes in VF and userspace ABI, a module parameter enable_64b_cqe_eqe must be set to enable 64-byte mode; the default is currently false. Signed-off-by: Eli Cohen <eli@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-10-21 22:59:24 +08:00
u32 eqe_size;
u32 cqe_size;
u8 eqe_factor;
u32 userspace_caps; /* userspace must be aware of these */
u32 function_caps; /* VFs must be aware of these */
u16 hca_core_clock;
};
struct mlx4_buf_list {
void *buf;
dma_addr_t map;
};
struct mlx4_buf {
struct mlx4_buf_list direct;
struct mlx4_buf_list *page_list;
int nbufs;
int npages;
int page_shift;
};
struct mlx4_mtt {
u32 offset;
int order;
int page_shift;
};
enum {
MLX4_DB_PER_PAGE = PAGE_SIZE / 4
};
struct mlx4_db_pgdir {
struct list_head list;
DECLARE_BITMAP(order0, MLX4_DB_PER_PAGE);
DECLARE_BITMAP(order1, MLX4_DB_PER_PAGE / 2);
unsigned long *bits[2];
__be32 *db_page;
dma_addr_t db_dma;
};
struct mlx4_ib_user_db_page;
struct mlx4_db {
__be32 *db;
union {
struct mlx4_db_pgdir *pgdir;
struct mlx4_ib_user_db_page *user_page;
} u;
dma_addr_t dma;
int index;
int order;
};
struct mlx4_hwq_resources {
struct mlx4_db db;
struct mlx4_mtt mtt;
struct mlx4_buf buf;
};
struct mlx4_mr {
struct mlx4_mtt mtt;
u64 iova;
u64 size;
u32 key;
u32 pd;
u32 access;
int enabled;
};
enum mlx4_mw_type {
MLX4_MW_TYPE_1 = 1,
MLX4_MW_TYPE_2 = 2,
};
struct mlx4_mw {
u32 key;
u32 pd;
enum mlx4_mw_type type;
int enabled;
};
struct mlx4_fmr {
struct mlx4_mr mr;
struct mlx4_mpt_entry *mpt;
__be64 *mtts;
dma_addr_t dma_handle;
int max_pages;
int max_maps;
int maps;
u8 page_shift;
};
struct mlx4_uar {
unsigned long pfn;
int index;
struct list_head bf_list;
unsigned free_bf_bmap;
void __iomem *map;
void __iomem *bf_map;
};
struct mlx4_bf {
unsigned long offset;
int buf_size;
struct mlx4_uar *uar;
void __iomem *reg;
};
struct mlx4_cq {
void (*comp) (struct mlx4_cq *);
void (*event) (struct mlx4_cq *, enum mlx4_event);
struct mlx4_uar *uar;
u32 cons_index;
__be32 *set_ci_db;
__be32 *arm_db;
int arm_sn;
int cqn;
unsigned vector;
atomic_t refcount;
struct completion free;
};
struct mlx4_qp {
void (*event) (struct mlx4_qp *, enum mlx4_event);
int qpn;
atomic_t refcount;
struct completion free;
};
struct mlx4_srq {
void (*event) (struct mlx4_srq *, enum mlx4_event);
int srqn;
int max;
int max_gs;
int wqe_shift;
atomic_t refcount;
struct completion free;
};
struct mlx4_av {
__be32 port_pd;
u8 reserved1;
u8 g_slid;
__be16 dlid;
u8 reserved2;
u8 gid_index;
u8 stat_rate;
u8 hop_limit;
__be32 sl_tclass_flowlabel;
u8 dgid[16];
};
struct mlx4_eth_av {
__be32 port_pd;
u8 reserved1;
u8 smac_idx;
u16 reserved2;
u8 reserved3;
u8 gid_index;
u8 stat_rate;
u8 hop_limit;
__be32 sl_tclass_flowlabel;
u8 dgid[16];
u32 reserved4[2];
__be16 vlan;
u8 mac[ETH_ALEN];
};
union mlx4_ext_av {
struct mlx4_av ib;
struct mlx4_eth_av eth;
};
struct mlx4_counter {
u8 reserved1[3];
u8 counter_mode;
__be32 num_ifc;
u32 reserved2[2];
__be64 rx_frames;
__be64 rx_bytes;
__be64 tx_frames;
__be64 tx_bytes;
};
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 <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-03 16:03:23 +08:00
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;
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 <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-03 16:03:23 +08:00
struct mlx4_quotas quotas;
struct radix_tree_root qp_table_tree;
u8 rev_id;
char board_id[MLX4_BOARD_ID_LEN];
mlx4_core: Modify driver initialization flow to accommodate SRIOV for Ethernet 1. Added module parameters sr_iov and probe_vf for controlling enablement of SRIOV mode. 2. Increased default max num-qps, num-mpts and log_num_macs to accomodate SRIOV mode 3. Added port_type_array as a module parameter to allow driver startup with ports configured as desired. In SRIOV mode, only ETH is supported, and this array is ignored; otherwise, for the case where the FW supports both port types (ETH and IB), the port_type_array parameter is used. By default, the port_type_array is set to configure both ports as IB. 4. When running in sriov mode, the master needs to initialize the ICM eq table to hold the eq's for itself and also for all the slaves. 5. mlx4_set_port_mask() now invoked from mlx4_init_hca, instead of in mlx4_dev_cap. 6. Introduced sriov VF (slave) device startup/teardown logic (mainly procedures mlx4_init_slave, mlx4_slave_exit, mlx4_slave_cap, mlx4_slave_exit and flow modifications in __mlx4_init_one, mlx4_init_hca, and mlx4_setup_hca). VFs obtain their startup information from the PF (master) device via the comm channel. 7. In SRIOV mode (both PF and VF), MSI_X must be enabled, or the driver aborts loading the device. 8. Do not allow setting port type via sysfs when running in SRIOV mode. 9. mlx4_get_ownership: Currently, only one PF is supported by the driver. If the HCA is burned with FW which enables more than one PF, only one of the PFs is allowed to run. The first one up grabs a FW ownership semaphone -- all other PFs will find that semaphore taken, and the driver will not allow them to run. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: Liran Liss <liranl@mellanox.co.il> Signed-off-by: Marcel Apfelbaum <marcela@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-13 12:18:30 +08:00
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];
};
mlx4: Use port management change event instead of smp_snoop The port management change event can replace smp_snoop. If the capability bit for this event is set in dev-caps, the event is used (by the driver setting the PORT_MNG_CHG_EVENT bit in the async event mask in the MAP_EQ fw command). In this case, when the driver passes incoming SMP PORT_INFO SET mads to the FW, the FW generates port management change events to signal any changes to the driver. If the FW generates these events, smp_snoop shouldn't be invoked in ib_process_mad(), or duplicate events will occur (once from the FW-generated event, and once from smp_snoop). In the case where the FW does not generate port management change events smp_snoop needs to be invoked to create these events. The flow in smp_snoop has been modified to make use of the same procedures as in the fw-generated-event event case to generate the port management events (LID change, Client-rereg, Pkey change, and/or GID change). Port management change event handling required changing the mlx4_ib_event and mlx4_dispatch_event prototypes; the "param" argument (last argument) had to be changed to unsigned long in order to accomodate passing the EQE pointer. We also needed to move the definition of struct mlx4_eqe from net/mlx4.h to file device.h -- to make it available to the IB driver, to handle port management change events. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-19 16:21:40 +08:00
struct mlx4_eqe {
u8 reserved1;
u8 type;
u8 reserved2;
u8 subtype;
union {
u32 raw[6];
struct {
__be32 cqn;
} __packed comp;
struct {
u16 reserved1;
__be16 token;
u32 reserved2;
u8 reserved3[3];
u8 status;
__be64 out_param;
} __packed cmd;
struct {
__be32 qpn;
} __packed qp;
struct {
__be32 srqn;
} __packed srq;
struct {
__be32 cqn;
u32 reserved1;
u8 reserved2[3];
u8 syndrome;
} __packed cq_err;
struct {
u32 reserved1[2];
__be32 port;
} __packed port_change;
struct {
#define COMM_CHANNEL_BIT_ARRAY_SIZE 4
u32 reserved;
u32 bit_vec[COMM_CHANNEL_BIT_ARRAY_SIZE];
} __packed comm_channel_arm;
struct {
u8 port;
u8 reserved[3];
__be64 mac;
} __packed mac_update;
struct {
__be32 slave_id;
} __packed flr_event;
struct {
__be16 current_temperature;
__be16 warning_threshold;
} __packed warming;
struct {
u8 reserved[3];
u8 port;
union {
struct {
__be16 mstr_sm_lid;
__be16 port_lid;
__be32 changed_attr;
u8 reserved[3];
u8 mstr_sm_sl;
__be64 gid_prefix;
} __packed port_info;
struct {
__be32 block_ptr;
__be32 tbl_entries_mask;
} __packed tbl_change_info;
} params;
} __packed port_mgmt_change;
} event;
u8 slave_id;
u8 reserved3[2];
u8 owner;
} __packed;
struct mlx4_init_port_param {
int set_guid0;
int set_node_guid;
int set_si_guid;
u16 mtu;
int port_width_cap;
u16 vl_cap;
u16 max_gid;
u16 max_pkey;
u64 guid0;
u64 node_guid;
u64 si_guid;
};
#define mlx4_foreach_port(port, dev, type) \
for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
if ((type) == (dev)->caps.port_mask[(port)])
#define mlx4_foreach_non_ib_transport_port(port, dev) \
for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
if (((dev)->caps.port_mask[port] != MLX4_PORT_TYPE_IB))
#define mlx4_foreach_ib_transport_port(port, dev) \
for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
if (((dev)->caps.port_mask[port] == MLX4_PORT_TYPE_IB) || \
((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
#define MLX4_INVALID_SLAVE_ID 0xFF
mlx4: Use port management change event instead of smp_snoop The port management change event can replace smp_snoop. If the capability bit for this event is set in dev-caps, the event is used (by the driver setting the PORT_MNG_CHG_EVENT bit in the async event mask in the MAP_EQ fw command). In this case, when the driver passes incoming SMP PORT_INFO SET mads to the FW, the FW generates port management change events to signal any changes to the driver. If the FW generates these events, smp_snoop shouldn't be invoked in ib_process_mad(), or duplicate events will occur (once from the FW-generated event, and once from smp_snoop). In the case where the FW does not generate port management change events smp_snoop needs to be invoked to create these events. The flow in smp_snoop has been modified to make use of the same procedures as in the fw-generated-event event case to generate the port management events (LID change, Client-rereg, Pkey change, and/or GID change). Port management change event handling required changing the mlx4_ib_event and mlx4_dispatch_event prototypes; the "param" argument (last argument) had to be changed to unsigned long in order to accomodate passing the EQE pointer. We also needed to move the definition of struct mlx4_eqe from net/mlx4.h to file device.h -- to make it available to the IB driver, to handle port management change events. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-19 16:21:40 +08:00
void handle_port_mgmt_change_event(struct work_struct *work);
static inline int mlx4_master_func_num(struct mlx4_dev *dev)
{
return dev->caps.function;
}
static inline int mlx4_is_master(struct mlx4_dev *dev)
{
return dev->flags & MLX4_FLAG_MASTER;
}
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 <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-03 16:03:23 +08:00
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 +
16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev));
}
static inline int mlx4_is_guest_proxy(struct mlx4_dev *dev, int slave, u32 qpn)
{
int guest_proxy_base = dev->phys_caps.base_proxy_sqpn + slave * 8;
if (qpn >= guest_proxy_base && qpn < guest_proxy_base + 8)
return 1;
return 0;
}
static inline int mlx4_is_mfunc(struct mlx4_dev *dev)
{
return dev->flags & (MLX4_FLAG_SLAVE | MLX4_FLAG_MASTER);
}
static inline int mlx4_is_slave(struct mlx4_dev *dev)
{
return dev->flags & MLX4_FLAG_SLAVE;
}
int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
struct mlx4_buf *buf);
void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf);
static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset)
{
if (BITS_PER_LONG == 64 || buf->nbufs == 1)
return buf->direct.buf + offset;
else
return buf->page_list[offset >> PAGE_SHIFT].buf +
(offset & (PAGE_SIZE - 1));
}
int mlx4_pd_alloc(struct mlx4_dev *dev, u32 *pdn);
void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn);
int mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn);
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);
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,
struct mlx4_mtt *mtt);
void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt);
u64 mlx4_mtt_addr(struct mlx4_dev *dev, struct mlx4_mtt *mtt);
int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
int npages, int page_shift, struct mlx4_mr *mr);
int mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr);
int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr);
int mlx4_mw_alloc(struct mlx4_dev *dev, u32 pd, enum mlx4_mw_type type,
struct mlx4_mw *mw);
void mlx4_mw_free(struct mlx4_dev *dev, struct mlx4_mw *mw);
int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw);
int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
int start_index, int npages, u64 *page_list);
int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
struct mlx4_buf *buf);
int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
int size, int max_direct);
void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres,
int size);
int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
unsigned vector, int collapsed, int timestamp_en);
void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base);
void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp);
void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp);
int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcdn,
struct mlx4_mtt *mtt, u64 db_rec, struct mlx4_srq *srq);
void mlx4_srq_free(struct mlx4_dev *dev, struct mlx4_srq *srq);
int mlx4_srq_arm(struct mlx4_dev *dev, struct mlx4_srq *srq, int limit_watermark);
int mlx4_srq_query(struct mlx4_dev *dev, struct mlx4_srq *srq, int *limit_watermark);
int mlx4_INIT_PORT(struct mlx4_dev *dev, int port);
int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port);
int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int block_mcast_loopback, enum mlx4_protocol prot);
int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
enum mlx4_protocol prot);
int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
u8 port, int block_mcast_loopback,
enum mlx4_protocol protocol, u64 *reg_id);
int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
enum mlx4_protocol protocol, u64 reg_id);
enum {
MLX4_DOMAIN_UVERBS = 0x1000,
MLX4_DOMAIN_ETHTOOL = 0x2000,
MLX4_DOMAIN_RFS = 0x3000,
MLX4_DOMAIN_NIC = 0x5000,
};
enum mlx4_net_trans_rule_id {
MLX4_NET_TRANS_RULE_ID_ETH = 0,
MLX4_NET_TRANS_RULE_ID_IB,
MLX4_NET_TRANS_RULE_ID_IPV6,
MLX4_NET_TRANS_RULE_ID_IPV4,
MLX4_NET_TRANS_RULE_ID_TCP,
MLX4_NET_TRANS_RULE_ID_UDP,
MLX4_NET_TRANS_RULE_NUM, /* should be last */
};
extern const u16 __sw_id_hw[];
static inline int map_hw_to_sw_id(u16 header_id)
{
int i;
for (i = 0; i < MLX4_NET_TRANS_RULE_NUM; i++) {
if (header_id == __sw_id_hw[i])
return i;
}
return -EINVAL;
}
enum mlx4_net_trans_promisc_mode {
MLX4_FS_REGULAR = 1,
MLX4_FS_ALL_DEFAULT,
MLX4_FS_MC_DEFAULT,
MLX4_FS_UC_SNIFFER,
MLX4_FS_MC_SNIFFER,
MLX4_FS_MODE_NUM, /* should be last */
};
struct mlx4_spec_eth {
u8 dst_mac[ETH_ALEN];
u8 dst_mac_msk[ETH_ALEN];
u8 src_mac[ETH_ALEN];
u8 src_mac_msk[ETH_ALEN];
u8 ether_type_enable;
__be16 ether_type;
__be16 vlan_id_msk;
__be16 vlan_id;
};
struct mlx4_spec_tcp_udp {
__be16 dst_port;
__be16 dst_port_msk;
__be16 src_port;
__be16 src_port_msk;
};
struct mlx4_spec_ipv4 {
__be32 dst_ip;
__be32 dst_ip_msk;
__be32 src_ip;
__be32 src_ip_msk;
};
struct mlx4_spec_ib {
__be32 l3_qpn;
__be32 qpn_msk;
u8 dst_gid[16];
u8 dst_gid_msk[16];
};
struct mlx4_spec_list {
struct list_head list;
enum mlx4_net_trans_rule_id id;
union {
struct mlx4_spec_eth eth;
struct mlx4_spec_ib ib;
struct mlx4_spec_ipv4 ipv4;
struct mlx4_spec_tcp_udp tcp_udp;
};
};
enum mlx4_net_trans_hw_rule_queue {
MLX4_NET_TRANS_Q_FIFO,
MLX4_NET_TRANS_Q_LIFO,
};
struct mlx4_net_trans_rule {
struct list_head list;
enum mlx4_net_trans_hw_rule_queue queue_mode;
bool exclusive;
bool allow_loopback;
enum mlx4_net_trans_promisc_mode promisc_mode;
u8 port;
u16 priority;
u32 qpn;
};
struct mlx4_net_trans_rule_hw_ctrl {
__be16 prio;
u8 type;
u8 flags;
u8 rsvd1;
u8 funcid;
u8 vep;
u8 port;
__be32 qpn;
__be32 rsvd2;
};
struct mlx4_net_trans_rule_hw_ib {
u8 size;
u8 rsvd1;
__be16 id;
u32 rsvd2;
__be32 l3_qpn;
__be32 qpn_mask;
u8 dst_gid[16];
u8 dst_gid_msk[16];
} __packed;
struct mlx4_net_trans_rule_hw_eth {
u8 size;
u8 rsvd;
__be16 id;
u8 rsvd1[6];
u8 dst_mac[6];
u16 rsvd2;
u8 dst_mac_msk[6];
u16 rsvd3;
u8 src_mac[6];
u16 rsvd4;
u8 src_mac_msk[6];
u8 rsvd5;
u8 ether_type_enable;
__be16 ether_type;
__be16 vlan_tag_msk;
__be16 vlan_tag;
} __packed;
struct mlx4_net_trans_rule_hw_tcp_udp {
u8 size;
u8 rsvd;
__be16 id;
__be16 rsvd1[3];
__be16 dst_port;
__be16 rsvd2;
__be16 dst_port_msk;
__be16 rsvd3;
__be16 src_port;
__be16 rsvd4;
__be16 src_port_msk;
} __packed;
struct mlx4_net_trans_rule_hw_ipv4 {
u8 size;
u8 rsvd;
__be16 id;
__be32 rsvd1;
__be32 dst_ip;
__be32 dst_ip_msk;
__be32 src_ip;
__be32 src_ip_msk;
} __packed;
struct _rule_hw {
union {
struct {
u8 size;
u8 rsvd;
__be16 id;
};
struct mlx4_net_trans_rule_hw_eth eth;
struct mlx4_net_trans_rule_hw_ib ib;
struct mlx4_net_trans_rule_hw_ipv4 ipv4;
struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp;
};
};
int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn,
enum mlx4_net_trans_promisc_mode mode);
int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port,
enum mlx4_net_trans_promisc_mode mode);
int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port, u64 mac, u64 clear, u8 mode);
int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port);
int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
void mlx4_set_stats_bitmap(struct mlx4_dev *dev, u64 *stats_bitmap);
int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx);
int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
u8 promisc);
int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
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, 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);
int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
int max_maps, u8 page_shift, struct mlx4_fmr *fmr);
int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
u32 *lkey, u32 *rkey);
int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
int mlx4_SYNC_TPT(struct mlx4_dev *dev);
int mlx4_test_interrupts(struct mlx4_dev *dev);
int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
int *vector);
void mlx4_release_eq(struct mlx4_dev *dev, int vec);
int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
void mlx4_counter_free(struct mlx4_dev *dev, u32 idx);
int mlx4_flow_attach(struct mlx4_dev *dev,
struct mlx4_net_trans_rule *rule, u64 *reg_id);
int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id);
int mlx4_map_sw_to_hw_steering_mode(struct mlx4_dev *dev,
enum mlx4_net_trans_promisc_mode flow_type);
int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev,
enum mlx4_net_trans_rule_id id);
int mlx4_hw_rule_sz(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id);
void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port,
int i, int val);
mlx4_core: Implement mechanism for reserved Q_Keys The SR-IOV special QP tunneling mechanism uses proxy special QPs (instead of the real special QPs) for MADs on guests. These proxy QPs send their packets to a "tunnel" QP owned by the master. The master then forwards the MAD (after any required paravirtualization) to the real special QP, which sends out the MAD. For security reasons (i.e., to prevent guests from sending MADs to tunnel QPs belonging to other guests), each proxy-tunnel QP pair is assigned a unique, reserved, Q_Key. These Q_Keys are available only for proxy and tunnel QPs -- if the guest tries to use these Q_Keys with other QPs, it will fail. This patch introduces a mechanism for reserving a block of 64K Q_Keys for proxy/tunneling use. The patch introduces also two new fields into mlx4_dev: base_sqpn and base_tunnel_sqpn. In SR-IOV mode, the QP numbers for the "real," proxy, and tunnel sqps are added to the reserved QPN area (so that they will not change). There are 8 special QPs per port in the HCA, and each of them is assigned both a proxy and a tunnel QP, for each VF and for the PF as well in SR-IOV mode. The QPNs for these QPs are arranged as follows: 1. The real SQP numbers (8) 2. The proxy SQPs (8 * (max number of VFs + max number of PFs) 3. The tunnel SQPs (8 * (max number of VFs + max number of PFs) To support these QPs, two new fields are added to struct mlx4_dev: base_sqp: this is the QP number of the first of the real SQPs base_tunnel_sqp: this is the qp number of the first qp in the tunnel sqp region. (On guests, this is the first tunnel sqp of the 8 which are assigned to that guest). In addition, in SR-IOV mode, sqp_start is the number of the first proxy SQP in the proxy SQP region. (In guests, this is the first proxy SQP of the 8 which are assigned to that guest) Note that in non-SR-IOV mode, there are no proxies and no tunnels. In this case, sqp_start is set to sqp_base -- which minimizes code changes. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-19 16:21:42 +08:00
int mlx4_get_parav_qkey(struct mlx4_dev *dev, u32 qpn, u32 *qkey);
int mlx4_is_slave_active(struct mlx4_dev *dev, int slave);
int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port);
int mlx4_gen_guid_change_eqe(struct mlx4_dev *dev, int slave, u8 port);
int mlx4_gen_slaves_port_mgt_ev(struct mlx4_dev *dev, u8 port, int attr);
int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port, u8 port_subtype_change);
enum slave_port_state mlx4_get_slave_port_state(struct mlx4_dev *dev, int slave, u8 port);
int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int event, enum slave_port_gen_event *gen_event);
void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid);
__be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave);
cycle_t mlx4_read_clock(struct mlx4_dev *dev);
#endif /* MLX4_DEVICE_H */