OpenCloudOS-Kernel/drivers/net/ethernet/mellanox/mlx4/mlx4.h

1481 lines
42 KiB
C
Raw Normal View History

/*
* Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
* Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved.
* Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
* Copyright (c) 2004 Voltaire, 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_H
#define MLX4_H
#include <linux/mutex.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
#include <linux/timer.h>
#include <linux/semaphore.h>
#include <linux/workqueue.h>
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <net/devlink.h>
#include <linux/rwsem.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/driver.h>
#include <linux/mlx4/doorbell.h>
#include <linux/mlx4/cmd.h>
#include "fw_qos.h"
#define DRV_NAME "mlx4_core"
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
#define PFX DRV_NAME ": "
#define DRV_VERSION "4.0-0"
#define MLX4_FS_UDP_UC_EN (1 << 1)
#define MLX4_FS_TCP_UC_EN (1 << 2)
#define MLX4_FS_NUM_OF_L2_ADDR 8
#define MLX4_FS_MGM_LOG_ENTRY_SIZE 7
#define MLX4_FS_NUM_MCG (1 << 17)
#define INIT_HCA_TPT_MW_ENABLE (1 << 7)
#define MLX4_QUERY_IF_STAT_RESET BIT(31)
enum {
MLX4_HCR_BASE = 0x80680,
MLX4_HCR_SIZE = 0x0001c,
MLX4_CLR_INT_SIZE = 0x00008,
MLX4_SLAVE_COMM_BASE = 0x0,
MLX4_COMM_PAGESIZE = 0x1000,
MLX4_CLOCK_SIZE = 0x00008,
MLX4_COMM_CHAN_CAPS = 0x8,
MLX4_COMM_CHAN_FLAGS = 0xc
};
enum {
MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE = 10,
MLX4_MIN_MGM_LOG_ENTRY_SIZE = 7,
MLX4_MAX_MGM_LOG_ENTRY_SIZE = 12,
MLX4_MAX_QP_PER_MGM = 4 * ((1 << MLX4_MAX_MGM_LOG_ENTRY_SIZE) / 16 - 2),
MLX4_MTT_ENTRY_PER_SEG = 8,
};
enum {
MLX4_NUM_PDS = 1 << 15
};
enum {
MLX4_CMPT_TYPE_QP = 0,
MLX4_CMPT_TYPE_SRQ = 1,
MLX4_CMPT_TYPE_CQ = 2,
MLX4_CMPT_TYPE_EQ = 3,
MLX4_CMPT_NUM_TYPE
};
enum {
MLX4_CMPT_SHIFT = 24,
MLX4_NUM_CMPTS = MLX4_CMPT_NUM_TYPE << MLX4_CMPT_SHIFT
};
enum mlx4_mpt_state {
MLX4_MPT_DISABLED = 0,
MLX4_MPT_EN_HW,
MLX4_MPT_EN_SW
};
#define MLX4_COMM_TIME 10000
#define MLX4_COMM_OFFLINE_TIME_OUT 30000
#define MLX4_COMM_CMD_NA_OP 0x0
enum {
MLX4_COMM_CMD_RESET,
MLX4_COMM_CMD_VHCR0,
MLX4_COMM_CMD_VHCR1,
MLX4_COMM_CMD_VHCR2,
MLX4_COMM_CMD_VHCR_EN,
MLX4_COMM_CMD_VHCR_POST,
MLX4_COMM_CMD_FLR = 254
};
enum {
MLX4_VF_SMI_DISABLED,
MLX4_VF_SMI_ENABLED
};
/*The flag indicates that the slave should delay the RESET cmd*/
#define MLX4_DELAY_RESET_SLAVE 0xbbbbbbb
/*indicates how many retries will be done if we are in the middle of FLR*/
#define NUM_OF_RESET_RETRIES 10
#define SLEEP_TIME_IN_RESET (2 * 1000)
enum mlx4_resource {
RES_QP,
RES_CQ,
RES_SRQ,
RES_XRCD,
RES_MPT,
RES_MTT,
RES_MAC,
RES_VLAN,
RES_NPORT_ID,
RES_COUNTER,
RES_FS_RULE,
RES_EQ,
MLX4_NUM_OF_RESOURCE_TYPE
};
enum mlx4_alloc_mode {
RES_OP_RESERVE,
RES_OP_RESERVE_AND_MAP,
RES_OP_MAP_ICM,
};
enum mlx4_res_tracker_free_type {
RES_TR_FREE_ALL,
RES_TR_FREE_SLAVES_ONLY,
RES_TR_FREE_STRUCTS_ONLY,
};
/*
*Virtual HCR structures.
* mlx4_vhcr is the sw representation, in machine endianness
*
* mlx4_vhcr_cmd is the formalized structure, the one that is passed
* to FW to go through communication channel.
* It is big endian, and has the same structure as the physical HCR
* used by command interface
*/
struct mlx4_vhcr {
u64 in_param;
u64 out_param;
u32 in_modifier;
u32 errno;
u16 op;
u16 token;
u8 op_modifier;
u8 e_bit;
};
struct mlx4_vhcr_cmd {
__be64 in_param;
__be32 in_modifier;
u32 reserved1;
__be64 out_param;
__be16 token;
u16 reserved;
u8 status;
u8 flags;
__be16 opcode;
};
struct mlx4_cmd_info {
u16 opcode;
bool has_inbox;
bool has_outbox;
bool out_is_imm;
bool encode_slave_id;
int (*verify)(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox);
int (*wrapper)(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
};
#ifdef CONFIG_MLX4_DEBUG
extern int mlx4_debug_level;
#else /* CONFIG_MLX4_DEBUG */
#define mlx4_debug_level (0)
#endif /* CONFIG_MLX4_DEBUG */
#define mlx4_dbg(mdev, format, ...) \
do { \
if (mlx4_debug_level) \
dev_printk(KERN_DEBUG, \
&(mdev)->persist->pdev->dev, format, \
##__VA_ARGS__); \
} while (0)
#define mlx4_err(mdev, format, ...) \
dev_err(&(mdev)->persist->pdev->dev, format, ##__VA_ARGS__)
#define mlx4_info(mdev, format, ...) \
dev_info(&(mdev)->persist->pdev->dev, format, ##__VA_ARGS__)
#define mlx4_warn(mdev, format, ...) \
dev_warn(&(mdev)->persist->pdev->dev, format, ##__VA_ARGS__)
extern int log_mtts_per_seg;
extern int mlx4_internal_err_reset;
#define MLX4_MAX_NUM_SLAVES (min(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF, \
MLX4_MFUNC_MAX))
#define ALL_SLAVES 0xff
struct mlx4_bitmap {
u32 last;
u32 top;
u32 max;
u32 reserved_top;
u32 mask;
u32 avail;
u32 effective_len;
spinlock_t lock;
unsigned long *table;
};
struct mlx4_buddy {
unsigned long **bits;
unsigned int *num_free;
u32 max_order;
spinlock_t lock;
};
struct mlx4_icm;
struct mlx4_icm_table {
u64 virt;
int num_icm;
u32 num_obj;
int obj_size;
int lowmem;
int coherent;
struct mutex mutex;
struct mlx4_icm **icm;
};
#define MLX4_MPT_FLAG_SW_OWNS (0xfUL << 28)
#define MLX4_MPT_FLAG_FREE (0x3UL << 28)
#define MLX4_MPT_FLAG_MIO (1 << 17)
#define MLX4_MPT_FLAG_BIND_ENABLE (1 << 15)
#define MLX4_MPT_FLAG_PHYSICAL (1 << 9)
#define MLX4_MPT_FLAG_REGION (1 << 8)
#define MLX4_MPT_PD_MASK (0x1FFFFUL)
#define MLX4_MPT_PD_VF_MASK (0xFE0000UL)
#define MLX4_MPT_PD_FLAG_FAST_REG (1 << 27)
#define MLX4_MPT_PD_FLAG_RAE (1 << 28)
#define MLX4_MPT_PD_FLAG_EN_INV (3 << 24)
#define MLX4_MPT_QP_FLAG_BOUND_QP (1 << 7)
#define MLX4_MPT_STATUS_SW 0xF0
#define MLX4_MPT_STATUS_HW 0x00
net/mlx4_core: Enable CQE/EQE stride support This feature is intended for archs having cache line larger then 64B. Since our CQE/EQEs are generally 64B in those systems, HW will write twice to the same cache line consecutively, causing pipe locks due to he hazard prevention mechanism. For elements in a cyclic buffer, writes are consecutive, so entries smaller than a cache line should be avoided, especially if they are written at a high rate. Reduce consecutive writes to same cache line in CQs/EQs, by allowing the driver to increase the distance between entries so that each will reside in a different cache line. Until the introduction of this feature, there were two types of CQE/EQE: 1. 32B stride and context in the [0-31] segment 2. 64B stride and context in the [32-63] segment This feature introduces two additional types: 3. 128B stride and context in the [0-31] segment (128B cache line) 4. 256B stride and context in the [0-31] segment (256B cache line) Modify the mlx4_core driver to query the device for the CQE/EQE cache line stride capability and to enable that capability when the host cache line size is larger than 64 bytes (supported cache lines are 128B and 256B). The mlx4 IB driver and libmlx4 need not be aware of this change. The PF context behaviour is changed to require this change in VF drivers running on such archs. Signed-off-by: Ido Shamay <idos@mellanox.com> 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>
2014-09-18 16:50:59 +08:00
#define MLX4_CQE_SIZE_MASK_STRIDE 0x3
#define MLX4_EQE_SIZE_MASK_STRIDE 0x30
#define MLX4_EQ_ASYNC 0
#define MLX4_EQ_TO_CQ_VECTOR(vector) ((vector) - \
!!((int)(vector) >= MLX4_EQ_ASYNC))
#define MLX4_CQ_TO_EQ_VECTOR(vector) ((vector) + \
!!((int)(vector) >= MLX4_EQ_ASYNC))
/*
* Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
*/
struct mlx4_mpt_entry {
__be32 flags;
__be32 qpn;
__be32 key;
__be32 pd_flags;
__be64 start;
__be64 length;
__be32 lkey;
__be32 win_cnt;
u8 reserved1[3];
u8 mtt_rep;
__be64 mtt_addr;
__be32 mtt_sz;
__be32 entity_size;
__be32 first_byte_offset;
} __packed;
/*
* Must be packed because start is 64 bits but only aligned to 32 bits.
*/
struct mlx4_eq_context {
__be32 flags;
u16 reserved1[3];
__be16 page_offset;
u8 log_eq_size;
u8 reserved2[4];
u8 eq_period;
u8 reserved3;
u8 eq_max_count;
u8 reserved4[3];
u8 intr;
u8 log_page_size;
u8 reserved5[2];
u8 mtt_base_addr_h;
__be32 mtt_base_addr_l;
u32 reserved6[2];
__be32 consumer_index;
__be32 producer_index;
u32 reserved7[4];
};
struct mlx4_cq_context {
__be32 flags;
u16 reserved1[3];
__be16 page_offset;
__be32 logsize_usrpage;
__be16 cq_period;
__be16 cq_max_count;
u8 reserved2[3];
u8 comp_eqn;
u8 log_page_size;
u8 reserved3[2];
u8 mtt_base_addr_h;
__be32 mtt_base_addr_l;
__be32 last_notified_index;
__be32 solicit_producer_index;
__be32 consumer_index;
__be32 producer_index;
u32 reserved4[2];
__be64 db_rec_addr;
};
struct mlx4_srq_context {
__be32 state_logsize_srqn;
u8 logstride;
u8 reserved1;
__be16 xrcd;
__be32 pg_offset_cqn;
u32 reserved2;
u8 log_page_size;
u8 reserved3[2];
u8 mtt_base_addr_h;
__be32 mtt_base_addr_l;
__be32 pd;
__be16 limit_watermark;
__be16 wqe_cnt;
u16 reserved4;
__be16 wqe_counter;
u32 reserved5;
__be64 db_rec_addr;
};
struct mlx4_eq_tasklet {
struct list_head list;
struct list_head process_list;
struct tasklet_struct task;
/* lock on completion tasklet list */
spinlock_t lock;
};
struct mlx4_eq {
struct mlx4_dev *dev;
void __iomem *doorbell;
int eqn;
u32 cons_index;
u16 irq;
u16 have_irq;
int nent;
struct mlx4_buf_list *page_list;
struct mlx4_mtt mtt;
struct mlx4_eq_tasklet tasklet_ctx;
struct mlx4_active_ports actv_ports;
u32 ref_count;
cpumask_var_t affinity_mask;
};
struct mlx4_slave_eqe {
u8 type;
u8 port;
u32 param;
};
struct mlx4_slave_event_eq_info {
int eqn;
u16 token;
};
struct mlx4_profile {
int num_qp;
int rdmarc_per_qp;
int num_srq;
int num_cq;
int num_mcg;
int num_mpt;
unsigned num_mtt;
};
struct mlx4_fw {
u64 clr_int_base;
u64 catas_offset;
u64 comm_base;
u64 clock_offset;
struct mlx4_icm *fw_icm;
struct mlx4_icm *aux_icm;
u32 catas_size;
u16 fw_pages;
u8 clr_int_bar;
u8 catas_bar;
u8 comm_bar;
u8 clock_bar;
};
struct mlx4_comm {
u32 slave_write;
u32 slave_read;
};
enum {
MLX4_MCAST_CONFIG = 0,
MLX4_MCAST_DISABLE = 1,
MLX4_MCAST_ENABLE = 2,
};
#define VLAN_FLTR_SIZE 128
struct mlx4_vlan_fltr {
__be32 entry[VLAN_FLTR_SIZE];
};
struct mlx4_mcast_entry {
struct list_head list;
u64 addr;
};
struct mlx4_promisc_qp {
struct list_head list;
u32 qpn;
};
struct mlx4_steer_index {
struct list_head list;
unsigned int index;
struct list_head duplicates;
};
#define MLX4_EVENT_TYPES_NUM 64
struct mlx4_slave_state {
u8 comm_toggle;
u8 last_cmd;
u8 init_port_mask;
bool active;
net/mlx4_core: Don't fail reg/unreg vlan for older guests In upstream kernels under SRIOV, the vlan register/unregister calls were NOPs (doing nothing and returning OK). We detect these old calls from guests (via the comm channel), since previously the port number in mlx4_register_vlan was passed (improperly) in the out_param. This has been corrected so that the port number is now passed in bits 8..15 of the in_modifier field. For old calls, these bits will be zero, so if the passed port number is zero, we can still look at the out_param field to see if it contains a valid port number. If yes, the VM is running an old driver. Since for old drivers, the register/unregister_vlan wrappers were NOPs, we continue this policy -- the reason being that upstream had an additional bug in eth driver running on guests (where procedure mlx4_en_vlan_rx_kill_vid() had the following code: if (!mlx4_find_cached_vlan(mdev->dev, priv->port, vid, &idx)) mlx4_unregister_vlan(mdev->dev, priv->port, idx); else en_err(priv, "could not find vid %d in cache\n", vid); On a VM, mlx4_find_cached_vlan() will always fail, since the vlan cache is located on the Hypervisor; on guests it is empty. Therefore, if we allow upstream guests to register vlans, we will have vlan leakage since the unregister will never be performed. Leaving vlan reg/unreg for old guest drivers as a NOP is not a feature regression, since in upstream the register/unregister vlan wrapper is a NOP. 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 16:03:21 +08:00
bool old_vlan_api;
bool vst_qinq_supported;
u8 function;
dma_addr_t vhcr_dma;
u16 user_mtu[MLX4_MAX_PORTS + 1];
u16 mtu[MLX4_MAX_PORTS + 1];
__be32 ib_cap_mask[MLX4_MAX_PORTS + 1];
struct mlx4_slave_eqe eq[MLX4_MFUNC_MAX_EQES];
struct list_head mcast_filters[MLX4_MAX_PORTS + 1];
struct mlx4_vlan_fltr *vlan_filter[MLX4_MAX_PORTS + 1];
/* event type to eq number lookup */
struct mlx4_slave_event_eq_info event_eq[MLX4_EVENT_TYPES_NUM];
u16 eq_pi;
u16 eq_ci;
spinlock_t lock;
/*initialized via the kzalloc*/
u8 is_slave_going_down;
u32 cookie;
enum slave_port_state port_state[MLX4_MAX_PORTS + 1];
};
#define MLX4_VGT 4095
#define NO_INDX (-1)
struct mlx4_vport_state {
u64 mac;
u16 default_vlan;
u8 default_qos;
__be16 vlan_proto;
u32 tx_rate;
bool spoofchk;
u32 link_state;
u8 qos_vport;
__be64 guid;
};
struct mlx4_vf_admin_state {
struct mlx4_vport_state vport[MLX4_MAX_PORTS + 1];
u8 enable_smi[MLX4_MAX_PORTS + 1];
};
struct mlx4_vport_oper_state {
struct mlx4_vport_state state;
int mac_idx;
int vlan_idx;
};
struct mlx4_vf_oper_state {
struct mlx4_vport_oper_state vport[MLX4_MAX_PORTS + 1];
u8 smi_enabled[MLX4_MAX_PORTS + 1];
};
struct slave_list {
struct mutex mutex;
struct list_head res_list[MLX4_NUM_OF_RESOURCE_TYPE];
};
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 resource_allocator {
spinlock_t alloc_lock; /* protect quotas */
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
union {
int res_reserved;
int res_port_rsvd[MLX4_MAX_PORTS];
};
union {
int res_free;
int res_port_free[MLX4_MAX_PORTS];
};
int *quota;
int *allocated;
int *guaranteed;
};
struct mlx4_resource_tracker {
spinlock_t lock;
/* tree for each resources */
struct rb_root res_tree[MLX4_NUM_OF_RESOURCE_TYPE];
/* num_of_slave's lists, one per slave */
struct slave_list *slave_list;
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 resource_allocator res_alloc[MLX4_NUM_OF_RESOURCE_TYPE];
};
#define SLAVE_EVENT_EQ_SIZE 128
struct mlx4_slave_event_eq {
u32 eqn;
u32 cons;
u32 prod;
spinlock_t event_lock;
struct mlx4_eqe event_eqe[SLAVE_EVENT_EQ_SIZE];
};
struct mlx4_qos_manager {
int num_of_qos_vfs;
DECLARE_BITMAP(priority_bm, MLX4_NUM_UP);
};
struct mlx4_master_qp0_state {
int proxy_qp0_active;
int qp0_active;
int port_active;
};
struct mlx4_mfunc_master_ctx {
struct mlx4_slave_state *slave_state;
struct mlx4_vf_admin_state *vf_admin;
struct mlx4_vf_oper_state *vf_oper;
struct mlx4_master_qp0_state qp0_state[MLX4_MAX_PORTS + 1];
int init_port_ref[MLX4_MAX_PORTS + 1];
u16 max_mtu[MLX4_MAX_PORTS + 1];
u16 max_user_mtu[MLX4_MAX_PORTS + 1];
u8 pptx;
u8 pprx;
int disable_mcast_ref[MLX4_MAX_PORTS + 1];
struct mlx4_resource_tracker res_tracker;
struct workqueue_struct *comm_wq;
struct work_struct comm_work;
struct work_struct slave_event_work;
struct work_struct slave_flr_event_work;
spinlock_t slave_state_lock;
__be32 comm_arm_bit_vector[4];
struct mlx4_eqe cmd_eqe;
struct mlx4_slave_event_eq slave_eq;
struct mutex gen_eqe_mutex[MLX4_MFUNC_MAX];
struct mlx4_qos_manager qos_ctl[MLX4_MAX_PORTS + 1];
};
struct mlx4_mfunc {
struct mlx4_comm __iomem *comm;
struct mlx4_vhcr_cmd *vhcr;
dma_addr_t vhcr_dma;
struct mlx4_mfunc_master_ctx master;
};
#define MGM_QPN_MASK 0x00FFFFFF
#define MGM_BLCK_LB_BIT 30
struct mlx4_mgm {
__be32 next_gid_index;
__be32 members_count;
u32 reserved[2];
u8 gid[16];
__be32 qp[MLX4_MAX_QP_PER_MGM];
};
struct mlx4_cmd {
struct pci_pool *pool;
void __iomem *hcr;
struct mutex slave_cmd_mutex;
struct semaphore poll_sem;
struct semaphore event_sem;
struct rw_semaphore switch_sem;
int max_cmds;
spinlock_t context_lock;
int free_head;
struct mlx4_cmd_context *context;
u16 token_mask;
u8 use_events;
u8 toggle;
u8 comm_toggle;
u8 initialized;
};
enum {
MLX4_VF_IMMED_VLAN_FLAG_VLAN = 1 << 0,
MLX4_VF_IMMED_VLAN_FLAG_QOS = 1 << 1,
MLX4_VF_IMMED_VLAN_FLAG_LINK_DISABLE = 1 << 2,
};
struct mlx4_vf_immed_vlan_work {
struct work_struct work;
struct mlx4_priv *priv;
int flags;
int slave;
int vlan_ix;
int orig_vlan_ix;
u8 port;
u8 qos;
u8 qos_vport;
u16 vlan_id;
u16 orig_vlan_id;
__be16 vlan_proto;
};
struct mlx4_uar_table {
struct mlx4_bitmap bitmap;
};
struct mlx4_mr_table {
struct mlx4_bitmap mpt_bitmap;
struct mlx4_buddy mtt_buddy;
u64 mtt_base;
u64 mpt_base;
struct mlx4_icm_table mtt_table;
struct mlx4_icm_table dmpt_table;
};
struct mlx4_cq_table {
struct mlx4_bitmap bitmap;
spinlock_t lock;
struct radix_tree_root tree;
struct mlx4_icm_table table;
struct mlx4_icm_table cmpt_table;
};
struct mlx4_eq_table {
struct mlx4_bitmap bitmap;
char *irq_names;
void __iomem *clr_int;
void __iomem **uar_map;
u32 clr_mask;
struct mlx4_eq *eq;
struct mlx4_icm_table table;
struct mlx4_icm_table cmpt_table;
int have_irq;
u8 inta_pin;
};
struct mlx4_srq_table {
struct mlx4_bitmap bitmap;
spinlock_t lock;
struct radix_tree_root tree;
struct mlx4_icm_table table;
struct mlx4_icm_table cmpt_table;
};
net/mlx4: Add A0 hybrid steering A0 hybrid steering is a form of high performance flow steering. By using this mode, mlx4 cards use a fast limited table based steering, in order to enable fast steering of unicast packets to a QP. In order to implement A0 hybrid steering we allocate resources from different zones: (1) General range (2) Special MAC-assigned QPs [RSS, Raw-Ethernet] each has its own region. When we create a rss QP or a raw ethernet (A0 steerable and BF ready) QP, we try hard to allocate the QP from range (2). Otherwise, we try hard not to allocate from this range. However, when the system is pushed to its limits and one needs every resource, the allocator uses every region it can. Meaning, when we run out of raw-eth qps, the allocator allocates from the general range (and the special-A0 area is no longer active). If we run out of RSS qps, the mechanism tries to allocate from the raw-eth QP zone. If that is also exhausted, the allocator will allocate from the general range (and the A0 region is no longer active). Note that if a raw-eth qp is allocated from the general range, it attempts to allocate the range such that bits 6 and 7 (blueflame bits) in the QP number are not set. When the feature is used in SRIOV, the VF has to notify the PF what kind of QP attributes it needs. In order to do that, along with the "Eth QP blueflame" bit, we reserve a new "A0 steerable QP". According to the combination of these bits, the PF tries to allocate a suitable QP. In order to maintain backward compatibility (with older PFs), the PF notifies which QP attributes it supports via QUERY_FUNC_CAP command. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-11 16:57:57 +08:00
enum mlx4_qp_table_zones {
MLX4_QP_TABLE_ZONE_GENERAL,
MLX4_QP_TABLE_ZONE_RSS,
MLX4_QP_TABLE_ZONE_RAW_ETH,
MLX4_QP_TABLE_ZONE_NUM
};
struct mlx4_qp_table {
net/mlx4: Add A0 hybrid steering A0 hybrid steering is a form of high performance flow steering. By using this mode, mlx4 cards use a fast limited table based steering, in order to enable fast steering of unicast packets to a QP. In order to implement A0 hybrid steering we allocate resources from different zones: (1) General range (2) Special MAC-assigned QPs [RSS, Raw-Ethernet] each has its own region. When we create a rss QP or a raw ethernet (A0 steerable and BF ready) QP, we try hard to allocate the QP from range (2). Otherwise, we try hard not to allocate from this range. However, when the system is pushed to its limits and one needs every resource, the allocator uses every region it can. Meaning, when we run out of raw-eth qps, the allocator allocates from the general range (and the special-A0 area is no longer active). If we run out of RSS qps, the mechanism tries to allocate from the raw-eth QP zone. If that is also exhausted, the allocator will allocate from the general range (and the A0 region is no longer active). Note that if a raw-eth qp is allocated from the general range, it attempts to allocate the range such that bits 6 and 7 (blueflame bits) in the QP number are not set. When the feature is used in SRIOV, the VF has to notify the PF what kind of QP attributes it needs. In order to do that, along with the "Eth QP blueflame" bit, we reserve a new "A0 steerable QP". According to the combination of these bits, the PF tries to allocate a suitable QP. In order to maintain backward compatibility (with older PFs), the PF notifies which QP attributes it supports via QUERY_FUNC_CAP command. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-11 16:57:57 +08:00
struct mlx4_bitmap *bitmap_gen;
struct mlx4_zone_allocator *zones;
u32 zones_uids[MLX4_QP_TABLE_ZONE_NUM];
u32 rdmarc_base;
int rdmarc_shift;
spinlock_t lock;
struct mlx4_icm_table qp_table;
struct mlx4_icm_table auxc_table;
struct mlx4_icm_table altc_table;
struct mlx4_icm_table rdmarc_table;
struct mlx4_icm_table cmpt_table;
};
struct mlx4_mcg_table {
struct mutex mutex;
struct mlx4_bitmap bitmap;
struct mlx4_icm_table table;
};
struct mlx4_catas_err {
u32 __iomem *map;
struct timer_list timer;
struct list_head list;
};
#define MLX4_MAX_MAC_NUM 128
#define MLX4_MAC_TABLE_SIZE (MLX4_MAX_MAC_NUM << 3)
struct mlx4_mac_table {
__be64 entries[MLX4_MAX_MAC_NUM];
int refs[MLX4_MAX_MAC_NUM];
bool is_dup[MLX4_MAX_MAC_NUM];
struct mutex mutex;
int total;
int max;
};
#define MLX4_ROCE_GID_ENTRY_SIZE 16
struct mlx4_roce_gid_entry {
u8 raw[MLX4_ROCE_GID_ENTRY_SIZE];
};
struct mlx4_roce_gid_table {
struct mlx4_roce_gid_entry roce_gids[MLX4_ROCE_MAX_GIDS];
struct mutex mutex;
};
#define MLX4_MAX_VLAN_NUM 128
#define MLX4_VLAN_TABLE_SIZE (MLX4_MAX_VLAN_NUM << 2)
struct mlx4_vlan_table {
__be32 entries[MLX4_MAX_VLAN_NUM];
int refs[MLX4_MAX_VLAN_NUM];
int is_dup[MLX4_MAX_VLAN_NUM];
struct mutex mutex;
int total;
int max;
};
#define SET_PORT_GEN_ALL_VALID (MLX4_FLAG_V_MTU_MASK | \
MLX4_FLAG_V_PPRX_MASK | \
MLX4_FLAG_V_PPTX_MASK)
#define SET_PORT_PROMISC_SHIFT 31
#define SET_PORT_MC_PROMISC_SHIFT 30
enum {
MCAST_DIRECT_ONLY = 0,
MCAST_DIRECT = 1,
MCAST_DEFAULT = 2
};
struct mlx4_set_port_general_context {
u16 reserved1;
u8 flags2;
u8 flags;
union {
u8 ignore_fcs;
u8 roce_mode;
};
u8 reserved2;
__be16 mtu;
u8 pptx;
u8 pfctx;
u16 reserved3;
u8 pprx;
u8 pfcrx;
u16 reserved4;
u32 reserved5;
u8 phv_en;
u8 reserved6[5];
__be16 user_mtu;
};
struct mlx4_set_port_rqp_calc_context {
__be32 base_qpn;
u8 rererved;
u8 n_mac;
u8 n_vlan;
u8 n_prio;
u8 reserved2[3];
u8 mac_miss;
u8 intra_no_vlan;
u8 no_vlan;
u8 intra_vlan_miss;
u8 vlan_miss;
u8 reserved3[3];
u8 no_vlan_prio;
__be32 promisc;
__be32 mcast;
};
struct mlx4_port_info {
struct mlx4_dev *dev;
int port;
char dev_name[16];
struct device_attribute port_attr;
enum mlx4_port_type tmp_type;
char dev_mtu_name[16];
struct device_attribute port_mtu_attr;
struct mlx4_mac_table mac_table;
struct mlx4_vlan_table vlan_table;
struct mlx4_roce_gid_table gid_table;
int base_qpn;
struct cpu_rmap *rmap;
struct devlink_port devlink_port;
};
struct mlx4_sense {
struct mlx4_dev *dev;
u8 do_sense_port[MLX4_MAX_PORTS + 1];
u8 sense_allowed[MLX4_MAX_PORTS + 1];
struct delayed_work sense_poll;
};
struct mlx4_msix_ctl {
DECLARE_BITMAP(pool_bm, MAX_MSIX);
struct mutex pool_lock;
};
struct mlx4_steer {
struct list_head promisc_qps[MLX4_NUM_STEERS];
struct list_head steer_entries[MLX4_NUM_STEERS];
};
enum {
MLX4_PCI_DEV_IS_VF = 1 << 0,
MLX4_PCI_DEV_FORCE_SENSE_PORT = 1 << 1,
};
mlx4_core: Roll back round robin bitmap allocation commit for CQs, SRQs, and MPTs Commit f4ec9e9 "mlx4_core: Change bitmap allocator to work in round-robin fashion" introduced round-robin allocation (via bitmap) for all resources which allocate via a bitmap. Round robin allocation is desirable for mcgs, counters, pd's, UARs, and xrcds. These are simply numbers, with no involvement of ICM memory mapping. Round robin is required for QPs, since we had a problem with immediate reuse of a 24-bit QP number (commit f4ec9e9). However, for other resources which use the bitmap allocator and involve mapping ICM memory -- MPTs, CQs, SRQs -- round-robin is not desirable. What happens in these cases is the following: ICM memory is allocated and mapped in chunks of 256K. Since the resource allocation index goes up monotonically, the allocator will eventually require mapping a new chunk. Now, chunks are also unmapped when their reference count goes back to zero. Thus, if a single app is running and starts/exits frequently we will have the following situation: When the app starts, a new chunk must be allocated and mapped. When the app exits, the chunk reference count goes back to zero, and the chunk is unmapped and freed. Therefore, the app must pay the cost of allocation and mapping of ICM memory each time it runs (although the price is paid only when allocating the initial entry in the new chunk). For apps which allocate MPTs/SRQs/CQs and which operate as described above, this presented a performance problem. We therefore roll back the round-robin allocator modification for MPTs, CQs, SRQs. Reported-by: Matthew Finlay <matt@mellanox.com> 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>
2013-12-08 22:50:17 +08:00
enum {
MLX4_NO_RR = 0,
MLX4_USE_RR = 1,
};
struct mlx4_priv {
struct mlx4_dev dev;
struct list_head dev_list;
struct list_head ctx_list;
spinlock_t ctx_lock;
int pci_dev_data;
int removed;
struct list_head pgdir_list;
struct mutex pgdir_mutex;
struct mlx4_fw fw;
struct mlx4_cmd cmd;
struct mlx4_mfunc mfunc;
struct mlx4_bitmap pd_bitmap;
struct mlx4_bitmap xrcd_bitmap;
struct mlx4_uar_table uar_table;
struct mlx4_mr_table mr_table;
struct mlx4_cq_table cq_table;
struct mlx4_eq_table eq_table;
struct mlx4_srq_table srq_table;
struct mlx4_qp_table qp_table;
struct mlx4_mcg_table mcg_table;
struct mlx4_bitmap counters_bitmap;
int def_counter[MLX4_MAX_PORTS];
struct mlx4_catas_err catas_err;
void __iomem *clr_base;
struct mlx4_uar driver_uar;
void __iomem *kar;
struct mlx4_port_info port[MLX4_MAX_PORTS + 1];
struct mlx4_sense sense;
struct mutex port_mutex;
struct mlx4_msix_ctl msix_ctl;
struct mlx4_steer *steer;
struct list_head bf_list;
struct mutex bf_mutex;
struct io_mapping *bf_mapping;
void __iomem *clock_mapping;
int reserved_mtts;
int fs_hash_mode;
u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS];
struct mlx4_port_map v2p; /* cached port mapping configuration */
struct mutex bond_mutex; /* for bond mode */
__be64 slave_node_guids[MLX4_MFUNC_MAX];
atomic_t opreq_count;
struct work_struct opreq_task;
};
static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
{
return container_of(dev, struct mlx4_priv, dev);
}
#define MLX4_SENSE_RANGE (HZ * 3)
extern struct workqueue_struct *mlx4_wq;
u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
mlx4_core: Roll back round robin bitmap allocation commit for CQs, SRQs, and MPTs Commit f4ec9e9 "mlx4_core: Change bitmap allocator to work in round-robin fashion" introduced round-robin allocation (via bitmap) for all resources which allocate via a bitmap. Round robin allocation is desirable for mcgs, counters, pd's, UARs, and xrcds. These are simply numbers, with no involvement of ICM memory mapping. Round robin is required for QPs, since we had a problem with immediate reuse of a 24-bit QP number (commit f4ec9e9). However, for other resources which use the bitmap allocator and involve mapping ICM memory -- MPTs, CQs, SRQs -- round-robin is not desirable. What happens in these cases is the following: ICM memory is allocated and mapped in chunks of 256K. Since the resource allocation index goes up monotonically, the allocator will eventually require mapping a new chunk. Now, chunks are also unmapped when their reference count goes back to zero. Thus, if a single app is running and starts/exits frequently we will have the following situation: When the app starts, a new chunk must be allocated and mapped. When the app exits, the chunk reference count goes back to zero, and the chunk is unmapped and freed. Therefore, the app must pay the cost of allocation and mapping of ICM memory each time it runs (although the price is paid only when allocating the initial entry in the new chunk). For apps which allocate MPTs/SRQs/CQs and which operate as described above, this presented a performance problem. We therefore roll back the round-robin allocator modification for MPTs, CQs, SRQs. Reported-by: Matthew Finlay <matt@mellanox.com> 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>
2013-12-08 22:50:17 +08:00
void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr);
net/mlx4: Change QP allocation scheme When using BF (Blue-Flame), the QPN overrides the VLAN, CV, and SV fields in the WQE. Thus, BF may only be used for QPNs with bits 6,7 unset. The current Ethernet driver code reserves a Tx QP range with 256b alignment. This is wrong because if there are more than 64 Tx QPs in use, QPNs >= base + 65 will have bits 6/7 set. This problem is not specific for the Ethernet driver, any entity that tries to reserve more than 64 BF-enabled QPs should fail. Also, using ranges is not necessary here and is wasteful. The new mechanism introduced here will support reservation for "Eth QPs eligible for BF" for all drivers: bare-metal, multi-PF, and VFs (when hypervisors support WC in VMs). The flow we use is: 1. In mlx4_en, allocate Tx QPs one by one instead of a range allocation, and request "BF enabled QPs" if BF is supported for the function 2. In the ALLOC_RES FW command, change param1 to: a. param1[23:0] - number of QPs b. param1[31-24] - flags controlling QPs reservation Bit 31 refers to Eth blueflame supported QPs. Those QPs must have bits 6 and 7 unset in order to be used in Ethernet. Bits 24-30 of the flags are currently reserved. When a function tries to allocate a QP, it states the required attributes for this QP. Those attributes are considered "best-effort". If an attribute, such as Ethernet BF enabled QP, is a must-have attribute, the function has to check that attribute is supported before trying to do the allocation. In a lower layer of the code, mlx4_qp_reserve_range masks out the bits which are unsupported. If SRIOV is used, the PF validates those attributes and masks out unsupported attributes as well. In order to notify VFs which attributes are supported, the VF uses QUERY_FUNC_CAP command. This command's mailbox is filled by the PF, which notifies which QP allocation attributes it supports. Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-11 16:57:54 +08:00
u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt,
int align, u32 skip_mask);
mlx4_core: Roll back round robin bitmap allocation commit for CQs, SRQs, and MPTs Commit f4ec9e9 "mlx4_core: Change bitmap allocator to work in round-robin fashion" introduced round-robin allocation (via bitmap) for all resources which allocate via a bitmap. Round robin allocation is desirable for mcgs, counters, pd's, UARs, and xrcds. These are simply numbers, with no involvement of ICM memory mapping. Round robin is required for QPs, since we had a problem with immediate reuse of a 24-bit QP number (commit f4ec9e9). However, for other resources which use the bitmap allocator and involve mapping ICM memory -- MPTs, CQs, SRQs -- round-robin is not desirable. What happens in these cases is the following: ICM memory is allocated and mapped in chunks of 256K. Since the resource allocation index goes up monotonically, the allocator will eventually require mapping a new chunk. Now, chunks are also unmapped when their reference count goes back to zero. Thus, if a single app is running and starts/exits frequently we will have the following situation: When the app starts, a new chunk must be allocated and mapped. When the app exits, the chunk reference count goes back to zero, and the chunk is unmapped and freed. Therefore, the app must pay the cost of allocation and mapping of ICM memory each time it runs (although the price is paid only when allocating the initial entry in the new chunk). For apps which allocate MPTs/SRQs/CQs and which operate as described above, this presented a performance problem. We therefore roll back the round-robin allocator modification for MPTs, CQs, SRQs. Reported-by: Matthew Finlay <matt@mellanox.com> 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>
2013-12-08 22:50:17 +08:00
void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt,
int use_rr);
u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap);
int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
u32 reserved_bot, u32 resetrved_top);
void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap);
int mlx4_reset(struct mlx4_dev *dev);
int mlx4_alloc_eq_table(struct mlx4_dev *dev);
void mlx4_free_eq_table(struct mlx4_dev *dev);
int mlx4_init_pd_table(struct mlx4_dev *dev);
int mlx4_init_xrcd_table(struct mlx4_dev *dev);
int mlx4_init_uar_table(struct mlx4_dev *dev);
int mlx4_init_mr_table(struct mlx4_dev *dev);
int mlx4_init_eq_table(struct mlx4_dev *dev);
int mlx4_init_cq_table(struct mlx4_dev *dev);
int mlx4_init_qp_table(struct mlx4_dev *dev);
int mlx4_init_srq_table(struct mlx4_dev *dev);
int mlx4_init_mcg_table(struct mlx4_dev *dev);
void mlx4_cleanup_pd_table(struct mlx4_dev *dev);
void mlx4_cleanup_xrcd_table(struct mlx4_dev *dev);
void mlx4_cleanup_uar_table(struct mlx4_dev *dev);
void mlx4_cleanup_mr_table(struct mlx4_dev *dev);
void mlx4_cleanup_eq_table(struct mlx4_dev *dev);
void mlx4_cleanup_cq_table(struct mlx4_dev *dev);
void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn);
void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn);
int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn);
void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn);
int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn);
void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn);
int __mlx4_mpt_reserve(struct mlx4_dev *dev);
void __mlx4_mpt_release(struct mlx4_dev *dev, u32 index);
int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index);
void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index);
u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order);
void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order);
int mlx4_WRITE_MTT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SYNC_TPT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_HW2SW_MPT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_MPT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_CONFIG_DEV_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
net/mlx4: Change QP allocation scheme When using BF (Blue-Flame), the QPN overrides the VLAN, CV, and SV fields in the WQE. Thus, BF may only be used for QPNs with bits 6,7 unset. The current Ethernet driver code reserves a Tx QP range with 256b alignment. This is wrong because if there are more than 64 Tx QPs in use, QPNs >= base + 65 will have bits 6/7 set. This problem is not specific for the Ethernet driver, any entity that tries to reserve more than 64 BF-enabled QPs should fail. Also, using ranges is not necessary here and is wasteful. The new mechanism introduced here will support reservation for "Eth QPs eligible for BF" for all drivers: bare-metal, multi-PF, and VFs (when hypervisors support WC in VMs). The flow we use is: 1. In mlx4_en, allocate Tx QPs one by one instead of a range allocation, and request "BF enabled QPs" if BF is supported for the function 2. In the ALLOC_RES FW command, change param1 to: a. param1[23:0] - number of QPs b. param1[31-24] - flags controlling QPs reservation Bit 31 refers to Eth blueflame supported QPs. Those QPs must have bits 6 and 7 unset in order to be used in Ethernet. Bits 24-30 of the flags are currently reserved. When a function tries to allocate a QP, it states the required attributes for this QP. Those attributes are considered "best-effort". If an attribute, such as Ethernet BF enabled QP, is a must-have attribute, the function has to check that attribute is supported before trying to do the allocation. In a lower layer of the code, mlx4_qp_reserve_range masks out the bits which are unsupported. If SRIOV is used, the PF validates those attributes and masks out unsupported attributes as well. In order to notify VFs which attributes are supported, the VF uses QUERY_FUNC_CAP command. This command's mailbox is filled by the PF, which notifies which QP allocation attributes it supports. Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-11 16:57:54 +08:00
int *base, u8 flags);
void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
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_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
int start_index, int npages, u64 *page_list);
int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
void __mlx4_counter_free(struct mlx4_dev *dev, u32 idx);
int mlx4_calc_vf_counters(struct mlx4_dev *dev, int slave, int port,
struct mlx4_counter *data);
int __mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn);
void __mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn);
void mlx4_start_catas_poll(struct mlx4_dev *dev);
void mlx4_stop_catas_poll(struct mlx4_dev *dev);
int mlx4_catas_init(struct mlx4_dev *dev);
void mlx4_catas_end(struct mlx4_dev *dev);
int mlx4_restart_one(struct pci_dev *pdev);
int mlx4_register_device(struct mlx4_dev *dev);
void mlx4_unregister_device(struct mlx4_dev *dev);
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 mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
unsigned long param);
struct mlx4_dev_cap;
struct mlx4_init_hca_param;
u64 mlx4_make_profile(struct mlx4_dev *dev,
struct mlx4_profile *request,
struct mlx4_dev_cap *dev_cap,
struct mlx4_init_hca_param *init_hca);
void mlx4_master_comm_channel(struct work_struct *work);
void mlx4_gen_slave_eqe(struct work_struct *work);
void mlx4_master_handle_slave_flr(struct work_struct *work);
int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_FREE_RES_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_MAP_EQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_COMM_INT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_HW2SW_EQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_EQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_CQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_MODIFY_CQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_SRQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_ARM_SRQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_GEN_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_INIT2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_RTR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_RTS2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SQERR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_2ERR_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_RTS2SQD_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SQD2SQD_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SQD2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_2RST_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe);
enum {
MLX4_CMD_CLEANUP_STRUCT = 1UL << 0,
MLX4_CMD_CLEANUP_POOL = 1UL << 1,
MLX4_CMD_CLEANUP_HCR = 1UL << 2,
MLX4_CMD_CLEANUP_VHCR = 1UL << 3,
MLX4_CMD_CLEANUP_ALL = (MLX4_CMD_CLEANUP_VHCR << 1) - 1
};
int mlx4_cmd_init(struct mlx4_dev *dev);
void mlx4_cmd_cleanup(struct mlx4_dev *dev, int cleanup_mask);
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 mlx4_multi_func_init(struct mlx4_dev *dev);
int mlx4_ARM_COMM_CHANNEL(struct mlx4_dev *dev);
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
void mlx4_multi_func_cleanup(struct mlx4_dev *dev);
void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param);
int mlx4_cmd_use_events(struct mlx4_dev *dev);
void mlx4_cmd_use_polling(struct mlx4_dev *dev);
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 mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
u16 op, unsigned long timeout);
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
void mlx4_cq_tasklet_cb(unsigned long data);
void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn);
void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type);
void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type);
void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
int mlx4_comm_internal_err(u32 slave_read);
int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
enum mlx4_port_type *type);
void mlx4_do_sense_ports(struct mlx4_dev *dev,
enum mlx4_port_type *stype,
enum mlx4_port_type *defaults);
void mlx4_start_sense(struct mlx4_dev *dev);
void mlx4_stop_sense(struct mlx4_dev *dev);
void mlx4_sense_init(struct mlx4_dev *dev);
int mlx4_check_port_params(struct mlx4_dev *dev,
enum mlx4_port_type *port_type);
int mlx4_change_port_types(struct mlx4_dev *dev,
enum mlx4_port_type *port_types);
void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table);
void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
void mlx4_init_roce_gid_table(struct mlx4_dev *dev,
struct mlx4_roce_gid_table *table);
void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
int mlx4_bond_vlan_table(struct mlx4_dev *dev);
int mlx4_unbond_vlan_table(struct mlx4_dev *dev);
int mlx4_bond_mac_table(struct mlx4_dev *dev);
int mlx4_unbond_mac_table(struct mlx4_dev *dev);
int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port, int pkey_tbl_sz);
/* resource tracker functions*/
int mlx4_get_slave_from_resource_id(struct mlx4_dev *dev,
enum mlx4_resource resource_type,
u64 resource_id, int *slave);
void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave_id);
void mlx4_reset_roce_gids(struct mlx4_dev *dev, int slave);
int mlx4_init_resource_tracker(struct mlx4_dev *dev);
void mlx4_free_resource_tracker(struct mlx4_dev *dev,
enum mlx4_res_tracker_free_type type);
int mlx4_QUERY_FW_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps);
int mlx4_get_slave_pkey_gid_tbl_len(struct mlx4_dev *dev, u8 port,
int *gid_tbl_len, int *pkey_tbl_len);
int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
enum mlx4_protocol prot, enum mlx4_steer_type steer);
int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int block_mcast_loopback, enum mlx4_protocol prot,
enum mlx4_steer_type steer);
int mlx4_trans_to_dmfs_attach(struct mlx4_dev *dev, struct mlx4_qp *qp,
u8 gid[16], u8 port,
int block_mcast_loopback,
enum mlx4_protocol prot, u64 *reg_id);
int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_common_set_vlan_fltr(struct mlx4_dev *dev, int function,
int port, void *buf);
int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_PKEY_TABLE_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_ACCESS_REG_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);
mlx4_core: Added FW commands and their wrappers for supporting SRIOV The following commands are added here: 1. QUERY_FUNC_CAP and its wrapper. This function is used by VFs when they start up to receive configuration information from the PF, such as resource quotas for this VF, which ports should be used (currently two), what protocol is running on the port (currently Ethernet ONLY, or port not active). 2. QUERY_PORT and its wrapper. Previously, this FW command was invoked directly by the ETH driver (en_port.c) using mlx4_cmd_box. Virtualization is now required here (the VF's MAC address must be substituted for the PFs MAC address returned by the FW). We changed the invocation in the ETH driver to use mlx4_QUERY_PORT, and added the wrapper. 3. QUERY_HCA. Used by the VF to determine how the HCA was initialized. For now, we need only the multicast table member entry size (log2_mc_table_entry_sz, in the ConnectX PRM). No wrapper is needed here, because the data may be passed as is to the VF without modification). In this command, we have added a GLOBAL_CAPS field for passing required configuration information from FW to a VF (this field is to allow safely adding new SRIOV capabilities which require support in VF drivers, too). Bits will set here by FW in response to PF-driver configuration commands which will activate as yet undefined new SRIOV features. The VF will test to see that all required capabilities indicated by this field are supported (i.e., if a bit is set and the VF driver does not recognize that bit, it must abort its initialization). Currently, no bits are set. 4. Added a CLOSE_PORT wrapper. The PF context needs to keep track of how many VF contexts have the port open. The PF context will not actually issue the FW close port command until the last port user issues a CLOSE_PORT request. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: Marcel Apfelbaum <marcela@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-13 12:12:40 +08:00
static inline void set_param_l(u64 *arg, u32 val)
{
*arg = (*arg & 0xffffffff00000000ULL) | (u64) val;
mlx4_core: Added FW commands and their wrappers for supporting SRIOV The following commands are added here: 1. QUERY_FUNC_CAP and its wrapper. This function is used by VFs when they start up to receive configuration information from the PF, such as resource quotas for this VF, which ports should be used (currently two), what protocol is running on the port (currently Ethernet ONLY, or port not active). 2. QUERY_PORT and its wrapper. Previously, this FW command was invoked directly by the ETH driver (en_port.c) using mlx4_cmd_box. Virtualization is now required here (the VF's MAC address must be substituted for the PFs MAC address returned by the FW). We changed the invocation in the ETH driver to use mlx4_QUERY_PORT, and added the wrapper. 3. QUERY_HCA. Used by the VF to determine how the HCA was initialized. For now, we need only the multicast table member entry size (log2_mc_table_entry_sz, in the ConnectX PRM). No wrapper is needed here, because the data may be passed as is to the VF without modification). In this command, we have added a GLOBAL_CAPS field for passing required configuration information from FW to a VF (this field is to allow safely adding new SRIOV capabilities which require support in VF drivers, too). Bits will set here by FW in response to PF-driver configuration commands which will activate as yet undefined new SRIOV features. The VF will test to see that all required capabilities indicated by this field are supported (i.e., if a bit is set and the VF driver does not recognize that bit, it must abort its initialization). Currently, no bits are set. 4. Added a CLOSE_PORT wrapper. The PF context needs to keep track of how many VF contexts have the port open. The PF context will not actually issue the FW close port command until the last port user issues a CLOSE_PORT request. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: Marcel Apfelbaum <marcela@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-13 12:12:40 +08:00
}
static inline void set_param_h(u64 *arg, u32 val)
{
*arg = (*arg & 0xffffffff) | ((u64) val << 32);
}
static inline u32 get_param_l(u64 *arg)
{
return (u32) (*arg & 0xffffffff);
}
static inline u32 get_param_h(u64 *arg)
{
return (u32)(*arg >> 32);
}
static inline spinlock_t *mlx4_tlock(struct mlx4_dev *dev)
{
return &mlx4_priv(dev)->mfunc.master.res_tracker.lock;
}
#define NOT_MASKED_PD_BITS 17
void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work);
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
void mlx4_init_quotas(struct mlx4_dev *dev);
net/mlx4_core: Replace VF zero mac with random mac in mlx4_core By design, when no default MAC addresses are set in the Hypervisor for VFs, the VFs are passed zero-macs. When such a MAC is received by the VF, it generates a random MAC address and registers that MAC address with the Hypervisor. This random mac generation is currently done in the mlx4_en module. There is a problem, though, if the mlx4_ib module is loaded by a VF before the mlx4_en module. In this case, for RoCE, mlx4_ib will see the un-replaced zero-mac and register that zero-mac as part of QP1 initialization. Having a zero-mac in the port's MAC table creates problems for a Baseboard Management Console. The BMC occasionally sends packets with a zero-mac destination MAC. If there is a zero-mac present in the port's MAC table, the FW will send such BMC packets to the host driver rather than to the wire, and BMC will stop working. To address this problem, we move the replacement of zero-mac addresses with random-mac addresses to procedure mlx4_slave_cap(), which is part of the driver startup for VFs, and is before activation of mlx4_ib and mlx4_en. As a result, zero-mac addresses will never be registered in the port MAC table by the driver. In addition, when mlx4_en does initialize the net device, it needs to set the NET_ADDR_RANDOM flag in the netdev structure if the address was randomly generated. This is done so that udev on the VM does not create a new device name after each VF probe (VM boot and such). To accomplish this, we add a per-port flag in mlx4_dev which gets set whenever mlx4_core replaces a zero-mac with a randomly-generated mac. This flag is examined when mlx4_en initializes the net-device. Fix was suggested by Matan Barak <matanb@mellanox.com> 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>
2015-10-14 22:43:48 +08:00
/* for VFs, replace zero MACs with randomly-generated MACs at driver start */
void mlx4_replace_zero_macs(struct mlx4_dev *dev);
int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
/* Returns the VF index of slave */
int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
int mlx4_config_mad_demux(struct mlx4_dev *dev);
int mlx4_do_bond(struct mlx4_dev *dev, bool enable);
int mlx4_bond_fs_rules(struct mlx4_dev *dev);
int mlx4_unbond_fs_rules(struct mlx4_dev *dev);
enum mlx4_zone_flags {
MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO = 1UL << 0,
MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO = 1UL << 1,
MLX4_ZONE_FALLBACK_TO_HIGHER_PRIO = 1UL << 2,
MLX4_ZONE_USE_RR = 1UL << 3,
};
enum mlx4_zone_alloc_flags {
/* No two objects could overlap between zones. UID
* could be left unused. If this flag is given and
* two overlapped zones are used, an object will be free'd
* from the smallest possible matching zone.
*/
MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP = 1UL << 0,
};
struct mlx4_zone_allocator;
/* Create a new zone allocator */
struct mlx4_zone_allocator *mlx4_zone_allocator_create(enum mlx4_zone_alloc_flags flags);
/* Attach a mlx4_bitmap <bitmap> of priority <priority> to the zone allocator
* <zone_alloc>. Allocating an object from this zone adds an offset <offset>.
* Similarly, when searching for an object to free, this offset it taken into
* account. The use_rr mlx4_ib parameter for allocating objects from this <bitmap>
* is given through the MLX4_ZONE_USE_RR flag in <flags>.
* When an allocation fails, <zone_alloc> tries to allocate from other zones
* according to the policy set by <flags>. <puid> is the unique identifier
* received to this zone.
*/
int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc,
struct mlx4_bitmap *bitmap,
u32 flags,
int priority,
int offset,
u32 *puid);
/* Remove bitmap indicated by <uid> from <zone_alloc> */
int mlx4_zone_remove_one(struct mlx4_zone_allocator *zone_alloc, u32 uid);
/* Delete the zone allocator <zone_alloc. This function doesn't destroy
* the attached bitmaps.
*/
void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc);
/* Allocate <count> objects with align <align> and skip_mask <skip_mask>
* from the mlx4_bitmap whose uid is <uid>. The bitmap which we actually
* allocated from is returned in <puid>. If the allocation fails, a negative
* number is returned. Otherwise, the offset of the first object is returned.
*/
u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
int align, u32 skip_mask, u32 *puid);
/* Free <count> objects, start from <obj> of the uid <uid> from zone_allocator
* <zones>.
*/
u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones,
u32 uid, u32 obj, u32 count);
/* If <zones> was allocated with MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP, instead of
* specifying the uid when freeing an object, zone allocator could figure it by
* itself. Other parameters are similar to mlx4_zone_free.
*/
u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count);
/* Returns a pointer to mlx4_bitmap that was attached to <zones> with <uid> */
struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 uid);
#endif /* MLX4_H */