flags, local_page_list, NULL, NULL);
up_read(&owning_mm->mmap_sem);
- if (npages < 0)
+ if (npages < 0) {
+ if (npages != -EAGAIN)
+ pr_warn("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
+ else
+ pr_debug("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
break;
+ }
bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
mutex_lock(&umem_odp->umem_mutex);
ret = ib_umem_odp_map_dma_single_page(
umem_odp, k, local_page_list[j],
access_mask, current_seq);
- if (ret < 0)
+ if (ret < 0) {
+ if (ret != -EAGAIN)
+ pr_warn("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
+ else
+ pr_debug("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
break;
+ }
p = page_to_phys(local_page_list[j]);
k++;
obj-$(CONFIG_MLX5_INFINIBAND) += mlx5_ib.o
-mlx5_ib-y := main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o cong.o
+mlx5_ib-y := main.o cq.o doorbell.o qp.o mem.o srq_cmd.o \
+ srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o \
+ cong.o
mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o
mlx5_ib-$(CONFIG_MLX5_ESWITCH) += ib_rep.o
mlx5_ib-$(CONFIG_INFINIBAND_USER_ACCESS) += devx.o
#include <rdma/ib_user_verbs.h>
#include <rdma/ib_cache.h>
#include "mlx5_ib.h"
+#include "srq.h"
static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq)
{
cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
- if (likely((cqe64->op_own) >> 4 != MLX5_CQE_INVALID) &&
+ if (likely(get_cqe_opcode(cqe64) != MLX5_CQE_INVALID) &&
!((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) {
return cqe;
} else {
struct mlx5_core_srq *msrq = NULL;
if (qp->ibqp.xrcd) {
- msrq = mlx5_core_get_srq(dev->mdev,
- be32_to_cpu(cqe->srqn));
+ msrq = mlx5_cmd_get_srq(dev, be32_to_cpu(cqe->srqn));
srq = to_mibsrq(msrq);
} else {
srq = to_msrq(qp->ibqp.srq);
}
wc->byte_len = be32_to_cpu(cqe->byte_cnt);
- switch (cqe->op_own >> 4) {
+ switch (get_cqe_opcode(cqe)) {
case MLX5_CQE_RESP_WR_IMM:
wc->opcode = IB_WC_RECV_RDMA_WITH_IMM;
wc->wc_flags = IB_WC_WITH_IMM;
*/
rmb();
- opcode = cqe64->op_own >> 4;
+ opcode = get_cqe_opcode(cqe64);
if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) {
if (likely(cq->resize_buf)) {
free_cq_buf(dev, &cq->buf);
return -EINVAL;
}
- while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) {
+ while (get_cqe_opcode(scqe64) != MLX5_CQE_RESIZE_CQ) {
dcqe = mlx5_frag_buf_get_wqe(&cq->resize_buf->fbc,
(i + 1) & cq->resize_buf->nent);
dcqe64 = dsize == 64 ? dcqe : dcqe + 64;
*/
#include "ib_rep.h"
+#include "srq.h"
static const struct mlx5_ib_profile rep_profile = {
STAGE_CREATE(MLX5_IB_STAGE_INIT,
STAGE_CREATE(MLX5_IB_STAGE_ROCE,
mlx5_ib_stage_rep_roce_init,
mlx5_ib_stage_rep_roce_cleanup),
+ STAGE_CREATE(MLX5_IB_STAGE_SRQ,
+ mlx5_init_srq_table,
+ mlx5_cleanup_srq_table),
STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
mlx5_ib_stage_dev_res_init,
mlx5_ib_stage_dev_res_cleanup),
#include "mlx5_ib.h"
#include "ib_rep.h"
#include "cmd.h"
+#include "srq.h"
#include <linux/mlx5/fs_helpers.h>
#include <linux/mlx5/accel.h>
#include <rdma/uverbs_std_types.h>
struct mlx5_ib_event_work {
struct work_struct work;
- struct mlx5_core_dev *dev;
- void *context;
- enum mlx5_dev_event event;
- unsigned long param;
+ union {
+ struct mlx5_ib_dev *dev;
+ struct mlx5_ib_multiport_info *mpi;
+ };
+ bool is_slave;
+ unsigned int event;
+ void *param;
};
enum {
ntohs(ib_spec->gre.val.protocol));
memcpy(MLX5_ADDR_OF(fte_match_set_misc, misc_params_c,
- gre_key_h),
+ gre_key.nvgre.hi),
&ib_spec->gre.mask.key,
sizeof(ib_spec->gre.mask.key));
memcpy(MLX5_ADDR_OF(fte_match_set_misc, misc_params_v,
- gre_key_h),
+ gre_key.nvgre.hi),
&ib_spec->gre.val.key,
sizeof(ib_spec->gre.val.key));
break;
mutex_unlock(&delay_drop->lock);
}
+static void handle_general_event(struct mlx5_ib_dev *ibdev, struct mlx5_eqe *eqe,
+ struct ib_event *ibev)
+{
+ switch (eqe->sub_type) {
+ case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
+ schedule_work(&ibdev->delay_drop.delay_drop_work);
+ break;
+ default: /* do nothing */
+ return;
+ }
+}
+
+static int handle_port_change(struct mlx5_ib_dev *ibdev, struct mlx5_eqe *eqe,
+ struct ib_event *ibev)
+{
+ u8 port = (eqe->data.port.port >> 4) & 0xf;
+
+ ibev->element.port_num = port;
+
+ switch (eqe->sub_type) {
+ case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+ case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+ case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
+ /* In RoCE, port up/down events are handled in
+ * mlx5_netdev_event().
+ */
+ if (mlx5_ib_port_link_layer(&ibdev->ib_dev, port) ==
+ IB_LINK_LAYER_ETHERNET)
+ return -EINVAL;
+
+ ibev->event = (eqe->sub_type == MLX5_PORT_CHANGE_SUBTYPE_ACTIVE) ?
+ IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
+ break;
+
+ case MLX5_PORT_CHANGE_SUBTYPE_LID:
+ ibev->event = IB_EVENT_LID_CHANGE;
+ break;
+
+ case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
+ ibev->event = IB_EVENT_PKEY_CHANGE;
+ schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work);
+ break;
+
+ case MLX5_PORT_CHANGE_SUBTYPE_GUID:
+ ibev->event = IB_EVENT_GID_CHANGE;
+ break;
+
+ case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
+ ibev->event = IB_EVENT_CLIENT_REREGISTER;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static void mlx5_ib_handle_event(struct work_struct *_work)
{
struct mlx5_ib_event_work *work =
struct mlx5_ib_dev *ibdev;
struct ib_event ibev;
bool fatal = false;
- u8 port = (u8)work->param;
- if (mlx5_core_is_mp_slave(work->dev)) {
- ibdev = mlx5_ib_get_ibdev_from_mpi(work->context);
+ if (work->is_slave) {
+ ibdev = mlx5_ib_get_ibdev_from_mpi(work->mpi);
if (!ibdev)
goto out;
} else {
- ibdev = work->context;
+ ibdev = work->dev;
}
switch (work->event) {
case MLX5_DEV_EVENT_SYS_ERROR:
ibev.event = IB_EVENT_DEVICE_FATAL;
mlx5_ib_handle_internal_error(ibdev);
+ ibev.element.port_num = (u8)(unsigned long)work->param;
fatal = true;
break;
-
- case MLX5_DEV_EVENT_PORT_UP:
- case MLX5_DEV_EVENT_PORT_DOWN:
- case MLX5_DEV_EVENT_PORT_INITIALIZED:
- /* In RoCE, port up/down events are handled in
- * mlx5_netdev_event().
- */
- if (mlx5_ib_port_link_layer(&ibdev->ib_dev, port) ==
- IB_LINK_LAYER_ETHERNET)
+ case MLX5_EVENT_TYPE_PORT_CHANGE:
+ if (handle_port_change(ibdev, work->param, &ibev))
goto out;
-
- ibev.event = (work->event == MLX5_DEV_EVENT_PORT_UP) ?
- IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
break;
-
- case MLX5_DEV_EVENT_LID_CHANGE:
- ibev.event = IB_EVENT_LID_CHANGE;
- break;
-
- case MLX5_DEV_EVENT_PKEY_CHANGE:
- ibev.event = IB_EVENT_PKEY_CHANGE;
- schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work);
- break;
-
- case MLX5_DEV_EVENT_GUID_CHANGE:
- ibev.event = IB_EVENT_GID_CHANGE;
- break;
-
- case MLX5_DEV_EVENT_CLIENT_REREG:
- ibev.event = IB_EVENT_CLIENT_REREGISTER;
- break;
- case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT:
- schedule_work(&ibdev->delay_drop.delay_drop_work);
- goto out;
+ case MLX5_EVENT_TYPE_GENERAL_EVENT:
+ handle_general_event(ibdev, work->param, &ibev);
+ /* fall through */
default:
goto out;
}
- ibev.device = &ibdev->ib_dev;
- ibev.element.port_num = port;
+ ibev.device = &ibdev->ib_dev;
- if (!rdma_is_port_valid(&ibdev->ib_dev, port)) {
- mlx5_ib_warn(ibdev, "warning: event on port %d\n", port);
+ if (!rdma_is_port_valid(&ibdev->ib_dev, ibev.element.port_num)) {
+ mlx5_ib_warn(ibdev, "warning: event on port %d\n", ibev.element.port_num);
goto out;
}
kfree(work);
}
-static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
- enum mlx5_dev_event event, unsigned long param)
+static int mlx5_ib_event(struct notifier_block *nb,
+ unsigned long event, void *param)
{
struct mlx5_ib_event_work *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (!work)
- return;
+ return NOTIFY_DONE;
INIT_WORK(&work->work, mlx5_ib_handle_event);
- work->dev = dev;
+ work->dev = container_of(nb, struct mlx5_ib_dev, mdev_events);
+ work->is_slave = false;
work->param = param;
- work->context = context;
work->event = event;
queue_work(mlx5_ib_event_wq, &work->work);
+
+ return NOTIFY_OK;
+}
+
+static int mlx5_ib_event_slave_port(struct notifier_block *nb,
+ unsigned long event, void *param)
+{
+ struct mlx5_ib_event_work *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work)
+ return NOTIFY_DONE;
+
+ INIT_WORK(&work->work, mlx5_ib_handle_event);
+ work->mpi = container_of(nb, struct mlx5_ib_multiport_info, mdev_events);
+ work->is_slave = true;
+ work->param = param;
+ work->event = event;
+ queue_work(mlx5_ib_event_wq, &work->work);
+
+ return NOTIFY_OK;
}
static int set_has_smi_cap(struct mlx5_ib_dev *dev)
{
struct mlx5_ib_dev *dev = to_mdev(ibdev);
- return mlx5_get_vector_affinity_hint(dev->mdev, comp_vector);
+ return mlx5_comp_irq_get_affinity_mask(dev->mdev, comp_vector);
}
/* The mlx5_ib_multiport_mutex should be held when calling this function */
spin_unlock(&port->mp.mpi_lock);
return;
}
+
+ if (mpi->mdev_events.notifier_call)
+ mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
+ mpi->mdev_events.notifier_call = NULL;
+
mpi->ibdev = NULL;
spin_unlock(&port->mp.mpi_lock);
ibdev->port[port_num].mp.mpi = mpi;
mpi->ibdev = ibdev;
+ mpi->mdev_events.notifier_call = NULL;
spin_unlock(&ibdev->port[port_num].mp.mpi_lock);
err = mlx5_nic_vport_affiliate_multiport(ibdev->mdev, mpi->mdev);
goto unbind;
}
+ mpi->mdev_events.notifier_call = mlx5_ib_event_slave_port;
+ mlx5_notifier_register(mpi->mdev, &mpi->mdev_events);
+
err = mlx5_ib_init_cong_debugfs(ibdev, port_num);
if (err)
goto unbind;
dev->ib_dev.node_type = RDMA_NODE_IB_CA;
dev->ib_dev.local_dma_lkey = 0 /* not supported for now */;
dev->ib_dev.phys_port_cnt = dev->num_ports;
- dev->ib_dev.num_comp_vectors =
- dev->mdev->priv.eq_table.num_comp_vectors;
+ dev->ib_dev.num_comp_vectors = mlx5_comp_vectors_count(mdev);
dev->ib_dev.dev.parent = &mdev->pdev->dev;
mutex_init(&dev->cap_mask_mutex);
return mlx5_ib_odp_init_one(dev);
}
+void mlx5_ib_stage_odp_cleanup(struct mlx5_ib_dev *dev)
+{
+ mlx5_ib_odp_cleanup_one(dev);
+}
+
int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev)
{
if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
mlx5_ib_unregister_vport_reps(dev);
}
+static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev)
+{
+ dev->mdev_events.notifier_call = mlx5_ib_event;
+ mlx5_notifier_register(dev->mdev, &dev->mdev_events);
+ return 0;
+}
+
+static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev)
+{
+ mlx5_notifier_unregister(dev->mdev, &dev->mdev_events);
+}
+
+static int mlx5_ib_stage_devx_init(struct mlx5_ib_dev *dev)
+{
+ int uid;
+
+ uid = mlx5_ib_devx_create(dev);
+ if (uid > 0)
+ dev->devx_whitelist_uid = uid;
+
+ return 0;
+}
+static void mlx5_ib_stage_devx_cleanup(struct mlx5_ib_dev *dev)
+{
+ if (dev->devx_whitelist_uid)
+ mlx5_ib_devx_destroy(dev, dev->devx_whitelist_uid);
+}
+
void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
const struct mlx5_ib_profile *profile,
int stage)
profile->stage[stage].cleanup(dev);
}
- if (dev->devx_whitelist_uid)
- mlx5_ib_devx_destroy(dev, dev->devx_whitelist_uid);
ib_dealloc_device((struct ib_device *)dev);
}
{
int err;
int i;
- int uid;
for (i = 0; i < MLX5_IB_STAGE_MAX; i++) {
if (profile->stage[i].init) {
}
}
- uid = mlx5_ib_devx_create(dev);
- if (uid > 0)
- dev->devx_whitelist_uid = uid;
-
dev->profile = profile;
dev->ib_active = true;
STAGE_CREATE(MLX5_IB_STAGE_ROCE,
mlx5_ib_stage_roce_init,
mlx5_ib_stage_roce_cleanup),
+ STAGE_CREATE(MLX5_IB_STAGE_SRQ,
+ mlx5_init_srq_table,
+ mlx5_cleanup_srq_table),
STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
mlx5_ib_stage_dev_res_init,
mlx5_ib_stage_dev_res_cleanup),
+ STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER,
+ mlx5_ib_stage_dev_notifier_init,
+ mlx5_ib_stage_dev_notifier_cleanup),
STAGE_CREATE(MLX5_IB_STAGE_ODP,
mlx5_ib_stage_odp_init,
- NULL),
+ mlx5_ib_stage_odp_cleanup),
STAGE_CREATE(MLX5_IB_STAGE_COUNTERS,
mlx5_ib_stage_counters_init,
mlx5_ib_stage_counters_cleanup),
STAGE_CREATE(MLX5_IB_STAGE_SPECS,
mlx5_ib_stage_populate_specs,
NULL),
+ STAGE_CREATE(MLX5_IB_STAGE_WHITELIST_UID,
+ mlx5_ib_stage_devx_init,
+ mlx5_ib_stage_devx_cleanup),
STAGE_CREATE(MLX5_IB_STAGE_IB_REG,
mlx5_ib_stage_ib_reg_init,
mlx5_ib_stage_ib_reg_cleanup),
STAGE_CREATE(MLX5_IB_STAGE_ROCE,
mlx5_ib_stage_rep_roce_init,
mlx5_ib_stage_rep_roce_cleanup),
+ STAGE_CREATE(MLX5_IB_STAGE_SRQ,
+ mlx5_init_srq_table,
+ mlx5_cleanup_srq_table),
STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES,
mlx5_ib_stage_dev_res_init,
mlx5_ib_stage_dev_res_cleanup),
+ STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER,
+ mlx5_ib_stage_dev_notifier_init,
+ mlx5_ib_stage_dev_notifier_cleanup),
STAGE_CREATE(MLX5_IB_STAGE_COUNTERS,
mlx5_ib_stage_counters_init,
mlx5_ib_stage_counters_cleanup),
static struct mlx5_interface mlx5_ib_interface = {
.add = mlx5_ib_add,
.remove = mlx5_ib_remove,
- .event = mlx5_ib_event,
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- .pfault = mlx5_ib_pfault,
-#endif
.protocol = MLX5_INTERFACE_PROTOCOL_IB,
};
#include <linux/mlx5/cq.h>
#include <linux/mlx5/fs.h>
#include <linux/mlx5/qp.h>
-#include <linux/mlx5/srq.h>
#include <linux/mlx5/fs.h>
#include <linux/types.h>
#include <linux/mlx5/transobj.h>
#include <rdma/uverbs_ioctl.h>
#include <rdma/mlx5_user_ioctl_cmds.h>
+#include "srq.h"
+
#define mlx5_ib_dbg(_dev, format, arg...) \
dev_dbg(&(_dev)->ib_dev.dev, "%s:%d:(pid %d): " format, __func__, \
__LINE__, current->pid, ##arg)
MLX5_IB_STAGE_CAPS,
MLX5_IB_STAGE_NON_DEFAULT_CB,
MLX5_IB_STAGE_ROCE,
+ MLX5_IB_STAGE_SRQ,
MLX5_IB_STAGE_DEVICE_RESOURCES,
+ MLX5_IB_STAGE_DEVICE_NOTIFIER,
MLX5_IB_STAGE_ODP,
MLX5_IB_STAGE_COUNTERS,
MLX5_IB_STAGE_CONG_DEBUGFS,
MLX5_IB_STAGE_BFREG,
MLX5_IB_STAGE_PRE_IB_REG_UMR,
MLX5_IB_STAGE_SPECS,
+ MLX5_IB_STAGE_WHITELIST_UID,
MLX5_IB_STAGE_IB_REG,
MLX5_IB_STAGE_POST_IB_REG_UMR,
MLX5_IB_STAGE_DELAY_DROP,
struct list_head list;
struct mlx5_ib_dev *ibdev;
struct mlx5_core_dev *mdev;
+ struct notifier_block mdev_events;
struct completion unref_comp;
u64 sys_image_guid;
u32 mdev_refcnt;
bool enabled;
};
+struct mlx5_ib_pf_eq {
+ struct mlx5_ib_dev *dev;
+ struct mlx5_eq *core;
+ struct work_struct work;
+ spinlock_t lock; /* Pagefaults spinlock */
+ struct workqueue_struct *wq;
+ mempool_t *pool;
+};
+
struct mlx5_ib_dev {
struct ib_device ib_dev;
const struct uverbs_object_tree_def *driver_trees[7];
struct mlx5_core_dev *mdev;
+ struct notifier_block mdev_events;
struct mlx5_roce roce[MLX5_MAX_PORTS];
int num_ports;
/* serialize update of capability mask
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
struct ib_odp_caps odp_caps;
u64 odp_max_size;
+ struct mlx5_ib_pf_eq odp_pf_eq;
+
/*
* Sleepable RCU that prevents destruction of MRs while they are still
* being used by a page fault handler.
u64 sys_image_guid;
struct mlx5_memic memic;
u16 devx_whitelist_uid;
+ struct mlx5_srq_table srq_table;
};
static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev);
-void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
- struct mlx5_pagefault *pfault);
int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev);
+void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev);
int __init mlx5_ib_odp_init(void);
void mlx5_ib_odp_cleanup(void);
void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
}
static inline int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev) { return 0; }
+static inline void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev) {}
static inline int mlx5_ib_odp_init(void) { return 0; }
static inline void mlx5_ib_odp_cleanup(void) {}
static inline void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent) {}
#include "mlx5_ib.h"
#include "cmd.h"
+#include <linux/mlx5/eq.h>
+
+/* Contains the details of a pagefault. */
+struct mlx5_pagefault {
+ u32 bytes_committed;
+ u32 token;
+ u8 event_subtype;
+ u8 type;
+ union {
+ /* Initiator or send message responder pagefault details. */
+ struct {
+ /* Received packet size, only valid for responders. */
+ u32 packet_size;
+ /*
+ * Number of resource holding WQE, depends on type.
+ */
+ u32 wq_num;
+ /*
+ * WQE index. Refers to either the send queue or
+ * receive queue, according to event_subtype.
+ */
+ u16 wqe_index;
+ } wqe;
+ /* RDMA responder pagefault details */
+ struct {
+ u32 r_key;
+ /*
+ * Received packet size, minimal size page fault
+ * resolution required for forward progress.
+ */
+ u32 packet_size;
+ u32 rdma_op_len;
+ u64 rdma_va;
+ } rdma;
+ };
+
+ struct mlx5_ib_pf_eq *eq;
+ struct work_struct work;
+};
+
#define MAX_PREFETCH_LEN (4*1024*1024U)
/* Timeout in ms to wait for an active mmu notifier to complete when handling
{
int wq_num = pfault->event_subtype == MLX5_PFAULT_SUBTYPE_WQE ?
pfault->wqe.wq_num : pfault->token;
- int ret = mlx5_core_page_fault_resume(dev->mdev,
- pfault->token,
- wq_num,
- pfault->type,
- error);
- if (ret)
- mlx5_ib_err(dev, "Failed to resolve the page fault on WQ 0x%x\n",
- wq_num);
+ u32 out[MLX5_ST_SZ_DW(page_fault_resume_out)] = { };
+ u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)] = { };
+ int err;
+
+ MLX5_SET(page_fault_resume_in, in, opcode, MLX5_CMD_OP_PAGE_FAULT_RESUME);
+ MLX5_SET(page_fault_resume_in, in, page_fault_type, pfault->type);
+ MLX5_SET(page_fault_resume_in, in, token, pfault->token);
+ MLX5_SET(page_fault_resume_in, in, wq_number, wq_num);
+ MLX5_SET(page_fault_resume_in, in, error, !!error);
+
+ err = mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ mlx5_ib_err(dev, "Failed to resolve the page fault on WQ 0x%x err %d\n",
+ wq_num, err);
}
static struct mlx5_ib_mr *implicit_mr_alloc(struct ib_pd *pd,
if (!wait_for_completion_timeout(
&odp->notifier_completion,
timeout)) {
- mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d\n",
- current_seq, odp->notifiers_seq);
+ mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n",
+ current_seq, odp->notifiers_seq, odp->notifiers_count);
}
} else {
/* The MR is being killed, kill the QP as well. */
return 0;
}
-static struct mlx5_ib_qp *mlx5_ib_odp_find_qp(struct mlx5_ib_dev *dev,
- u32 wq_num)
+static inline struct mlx5_core_rsc_common *odp_get_rsc(struct mlx5_ib_dev *dev,
+ u32 wq_num, int pf_type)
{
- struct mlx5_core_qp *mqp = __mlx5_qp_lookup(dev->mdev, wq_num);
+ enum mlx5_res_type res_type;
- if (!mqp) {
- mlx5_ib_err(dev, "QPN 0x%6x not found\n", wq_num);
+ switch (pf_type) {
+ case MLX5_WQE_PF_TYPE_RMP:
+ res_type = MLX5_RES_SRQ;
+ break;
+ case MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE:
+ case MLX5_WQE_PF_TYPE_RESP:
+ case MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC:
+ res_type = MLX5_RES_QP;
+ break;
+ default:
return NULL;
}
+ return mlx5_core_res_hold(dev->mdev, wq_num, res_type);
+}
+
+static inline struct mlx5_ib_qp *res_to_qp(struct mlx5_core_rsc_common *res)
+{
+ struct mlx5_core_qp *mqp = (struct mlx5_core_qp *)res;
+
return to_mibqp(mqp);
}
int resume_with_error = 1;
u16 wqe_index = pfault->wqe.wqe_index;
int requestor = pfault->type & MLX5_PFAULT_REQUESTOR;
+ struct mlx5_core_rsc_common *res;
struct mlx5_ib_qp *qp;
+ res = odp_get_rsc(dev, pfault->wqe.wq_num, pfault->type);
+ if (!res) {
+ mlx5_ib_dbg(dev, "wqe page fault for missing resource %d\n", pfault->wqe.wq_num);
+ return;
+ }
+
+ switch (res->res) {
+ case MLX5_RES_QP:
+ qp = res_to_qp(res);
+ break;
+ default:
+ mlx5_ib_err(dev, "wqe page fault for unsupported type %d\n", pfault->type);
+ goto resolve_page_fault;
+ }
+
buffer = (char *)__get_free_page(GFP_KERNEL);
if (!buffer) {
mlx5_ib_err(dev, "Error allocating memory for IO page fault handling.\n");
goto resolve_page_fault;
}
- qp = mlx5_ib_odp_find_qp(dev, pfault->wqe.wq_num);
- if (!qp)
- goto resolve_page_fault;
-
ret = mlx5_ib_read_user_wqe(qp, requestor, wqe_index, buffer,
PAGE_SIZE, &qp->trans_qp.base);
if (ret < 0) {
mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x resume_with_error=%d, type: 0x%x\n",
pfault->wqe.wq_num, resume_with_error,
pfault->type);
+ mlx5_core_res_put(res);
free_page((unsigned long)buffer);
}
}
}
-void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
- struct mlx5_pagefault *pfault)
+static void mlx5_ib_pfault(struct mlx5_ib_dev *dev, struct mlx5_pagefault *pfault)
{
- struct mlx5_ib_dev *dev = context;
u8 event_subtype = pfault->event_subtype;
switch (event_subtype) {
}
}
+static void mlx5_ib_eqe_pf_action(struct work_struct *work)
+{
+ struct mlx5_pagefault *pfault = container_of(work,
+ struct mlx5_pagefault,
+ work);
+ struct mlx5_ib_pf_eq *eq = pfault->eq;
+
+ mlx5_ib_pfault(eq->dev, pfault);
+ mempool_free(pfault, eq->pool);
+}
+
+static void mlx5_ib_eq_pf_process(struct mlx5_ib_pf_eq *eq)
+{
+ struct mlx5_eqe_page_fault *pf_eqe;
+ struct mlx5_pagefault *pfault;
+ struct mlx5_eqe *eqe;
+ int cc = 0;
+
+ while ((eqe = mlx5_eq_get_eqe(eq->core, cc))) {
+ pfault = mempool_alloc(eq->pool, GFP_ATOMIC);
+ if (!pfault) {
+ schedule_work(&eq->work);
+ break;
+ }
+
+ pf_eqe = &eqe->data.page_fault;
+ pfault->event_subtype = eqe->sub_type;
+ pfault->bytes_committed = be32_to_cpu(pf_eqe->bytes_committed);
+
+ mlx5_ib_dbg(eq->dev,
+ "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x\n",
+ eqe->sub_type, pfault->bytes_committed);
+
+ switch (eqe->sub_type) {
+ case MLX5_PFAULT_SUBTYPE_RDMA:
+ /* RDMA based event */
+ pfault->type =
+ be32_to_cpu(pf_eqe->rdma.pftype_token) >> 24;
+ pfault->token =
+ be32_to_cpu(pf_eqe->rdma.pftype_token) &
+ MLX5_24BIT_MASK;
+ pfault->rdma.r_key =
+ be32_to_cpu(pf_eqe->rdma.r_key);
+ pfault->rdma.packet_size =
+ be16_to_cpu(pf_eqe->rdma.packet_length);
+ pfault->rdma.rdma_op_len =
+ be32_to_cpu(pf_eqe->rdma.rdma_op_len);
+ pfault->rdma.rdma_va =
+ be64_to_cpu(pf_eqe->rdma.rdma_va);
+ mlx5_ib_dbg(eq->dev,
+ "PAGE_FAULT: type:0x%x, token: 0x%06x, r_key: 0x%08x\n",
+ pfault->type, pfault->token,
+ pfault->rdma.r_key);
+ mlx5_ib_dbg(eq->dev,
+ "PAGE_FAULT: rdma_op_len: 0x%08x, rdma_va: 0x%016llx\n",
+ pfault->rdma.rdma_op_len,
+ pfault->rdma.rdma_va);
+ break;
+
+ case MLX5_PFAULT_SUBTYPE_WQE:
+ /* WQE based event */
+ pfault->type =
+ (be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24) & 0x7;
+ pfault->token =
+ be32_to_cpu(pf_eqe->wqe.token);
+ pfault->wqe.wq_num =
+ be32_to_cpu(pf_eqe->wqe.pftype_wq) &
+ MLX5_24BIT_MASK;
+ pfault->wqe.wqe_index =
+ be16_to_cpu(pf_eqe->wqe.wqe_index);
+ pfault->wqe.packet_size =
+ be16_to_cpu(pf_eqe->wqe.packet_length);
+ mlx5_ib_dbg(eq->dev,
+ "PAGE_FAULT: type:0x%x, token: 0x%06x, wq_num: 0x%06x, wqe_index: 0x%04x\n",
+ pfault->type, pfault->token,
+ pfault->wqe.wq_num,
+ pfault->wqe.wqe_index);
+ break;
+
+ default:
+ mlx5_ib_warn(eq->dev,
+ "Unsupported page fault event sub-type: 0x%02hhx\n",
+ eqe->sub_type);
+ /* Unsupported page faults should still be
+ * resolved by the page fault handler
+ */
+ }
+
+ pfault->eq = eq;
+ INIT_WORK(&pfault->work, mlx5_ib_eqe_pf_action);
+ queue_work(eq->wq, &pfault->work);
+
+ cc = mlx5_eq_update_cc(eq->core, ++cc);
+ }
+
+ mlx5_eq_update_ci(eq->core, cc, 1);
+}
+
+static irqreturn_t mlx5_ib_eq_pf_int(int irq, void *eq_ptr)
+{
+ struct mlx5_ib_pf_eq *eq = eq_ptr;
+ unsigned long flags;
+
+ if (spin_trylock_irqsave(&eq->lock, flags)) {
+ mlx5_ib_eq_pf_process(eq);
+ spin_unlock_irqrestore(&eq->lock, flags);
+ } else {
+ schedule_work(&eq->work);
+ }
+
+ return IRQ_HANDLED;
+}
+
+/* mempool_refill() was proposed but unfortunately wasn't accepted
+ * http://lkml.iu.edu/hypermail/linux/kernel/1512.1/05073.html
+ * Cheap workaround.
+ */
+static void mempool_refill(mempool_t *pool)
+{
+ while (pool->curr_nr < pool->min_nr)
+ mempool_free(mempool_alloc(pool, GFP_KERNEL), pool);
+}
+
+static void mlx5_ib_eq_pf_action(struct work_struct *work)
+{
+ struct mlx5_ib_pf_eq *eq =
+ container_of(work, struct mlx5_ib_pf_eq, work);
+
+ mempool_refill(eq->pool);
+
+ spin_lock_irq(&eq->lock);
+ mlx5_ib_eq_pf_process(eq);
+ spin_unlock_irq(&eq->lock);
+}
+
+enum {
+ MLX5_IB_NUM_PF_EQE = 0x1000,
+ MLX5_IB_NUM_PF_DRAIN = 64,
+};
+
+static int
+mlx5_ib_create_pf_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
+{
+ struct mlx5_eq_param param = {};
+ int err;
+
+ INIT_WORK(&eq->work, mlx5_ib_eq_pf_action);
+ spin_lock_init(&eq->lock);
+ eq->dev = dev;
+
+ eq->pool = mempool_create_kmalloc_pool(MLX5_IB_NUM_PF_DRAIN,
+ sizeof(struct mlx5_pagefault));
+ if (!eq->pool)
+ return -ENOMEM;
+
+ eq->wq = alloc_workqueue("mlx5_ib_page_fault",
+ WQ_HIGHPRI | WQ_UNBOUND | WQ_MEM_RECLAIM,
+ MLX5_NUM_CMD_EQE);
+ if (!eq->wq) {
+ err = -ENOMEM;
+ goto err_mempool;
+ }
+
+ param = (struct mlx5_eq_param) {
+ .index = MLX5_EQ_PFAULT_IDX,
+ .mask = 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
+ .nent = MLX5_IB_NUM_PF_EQE,
+ .context = eq,
+ .handler = mlx5_ib_eq_pf_int
+ };
+ eq->core = mlx5_eq_create_generic(dev->mdev, "mlx5_ib_page_fault_eq", ¶m);
+ if (IS_ERR(eq->core)) {
+ err = PTR_ERR(eq->core);
+ goto err_wq;
+ }
+
+ return 0;
+err_wq:
+ destroy_workqueue(eq->wq);
+err_mempool:
+ mempool_destroy(eq->pool);
+ return err;
+}
+
+static int
+mlx5_ib_destroy_pf_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
+{
+ int err;
+
+ err = mlx5_eq_destroy_generic(dev->mdev, eq->core);
+ cancel_work_sync(&eq->work);
+ destroy_workqueue(eq->wq);
+ mempool_destroy(eq->pool);
+
+ return err;
+}
+
void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent)
{
if (!(ent->dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
{
- int ret;
+ int ret = 0;
if (dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT) {
ret = mlx5_cmd_null_mkey(dev->mdev, &dev->null_mkey);
}
}
- return 0;
+ if (!MLX5_CAP_GEN(dev->mdev, pg))
+ return ret;
+
+ ret = mlx5_ib_create_pf_eq(dev, &dev->odp_pf_eq);
+
+ return ret;
+}
+
+void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *dev)
+{
+ if (!MLX5_CAP_GEN(dev->mdev, pg))
+ return;
+
+ mlx5_ib_destroy_pf_eq(dev, &dev->odp_pf_eq);
}
int mlx5_ib_odp_init(void)
return 0;
}
-
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/*
- * Copyright (c) 2013-2015, Mellanox Technologies. 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.
+ * Copyright (c) 2013-2018, Mellanox Technologies inc. All rights reserved.
*/
#include <linux/module.h>
#include <linux/mlx5/qp.h>
-#include <linux/mlx5/srq.h>
#include <linux/slab.h>
#include <rdma/ib_umem.h>
#include <rdma/ib_user_verbs.h>
-
#include "mlx5_ib.h"
-
-/* not supported currently */
-static int srq_signature;
+#include "srq.h"
static void *get_wqe(struct mlx5_ib_srq *srq, int n)
{
err = -ENOMEM;
goto err_in;
}
- srq->wq_sig = !!srq_signature;
+ srq->wq_sig = 0;
in->log_page_size = srq->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1 &&
in.pd = to_mpd(pd)->pdn;
in.db_record = srq->db.dma;
- err = mlx5_core_create_srq(dev->mdev, &srq->msrq, &in);
+ err = mlx5_cmd_create_srq(dev, &srq->msrq, &in);
kvfree(in.pas);
if (err) {
mlx5_ib_dbg(dev, "create SRQ failed, err %d\n", err);
return &srq->ibsrq;
err_core:
- mlx5_core_destroy_srq(dev->mdev, &srq->msrq);
+ mlx5_cmd_destroy_srq(dev, &srq->msrq);
err_usr_kern_srq:
if (pd->uobject)
return -EINVAL;
mutex_lock(&srq->mutex);
- ret = mlx5_core_arm_srq(dev->mdev, &srq->msrq, attr->srq_limit, 1);
+ ret = mlx5_cmd_arm_srq(dev, &srq->msrq, attr->srq_limit, 1);
mutex_unlock(&srq->mutex);
if (ret)
if (!out)
return -ENOMEM;
- ret = mlx5_core_query_srq(dev->mdev, &srq->msrq, out);
+ ret = mlx5_cmd_query_srq(dev, &srq->msrq, out);
if (ret)
goto out_box;
struct mlx5_ib_dev *dev = to_mdev(srq->device);
struct mlx5_ib_srq *msrq = to_msrq(srq);
- mlx5_core_destroy_srq(dev->mdev, &msrq->msrq);
+ mlx5_cmd_destroy_srq(dev, &msrq->msrq);
if (srq->uobject) {
mlx5_ib_db_unmap_user(to_mucontext(srq->uobject->context), &msrq->db);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2013-2018, Mellanox Technologies. All rights reserved.
+ */
+
+#ifndef MLX5_IB_SRQ_H
+#define MLX5_IB_SRQ_H
+
+enum {
+ MLX5_SRQ_FLAG_ERR = (1 << 0),
+ MLX5_SRQ_FLAG_WQ_SIG = (1 << 1),
+ MLX5_SRQ_FLAG_RNDV = (1 << 2),
+};
+
+struct mlx5_srq_attr {
+ u32 type;
+ u32 flags;
+ u32 log_size;
+ u32 wqe_shift;
+ u32 log_page_size;
+ u32 wqe_cnt;
+ u32 srqn;
+ u32 xrcd;
+ u32 page_offset;
+ u32 cqn;
+ u32 pd;
+ u32 lwm;
+ u32 user_index;
+ u64 db_record;
+ __be64 *pas;
+ u32 tm_log_list_size;
+ u32 tm_next_tag;
+ u32 tm_hw_phase_cnt;
+ u32 tm_sw_phase_cnt;
+ u16 uid;
+};
+
+struct mlx5_ib_dev;
+
+struct mlx5_core_srq {
+ struct mlx5_core_rsc_common common; /* must be first */
+ u32 srqn;
+ int max;
+ size_t max_gs;
+ size_t max_avail_gather;
+ int wqe_shift;
+ void (*event)(struct mlx5_core_srq *srq, enum mlx5_event e);
+
+ atomic_t refcount;
+ struct completion free;
+ u16 uid;
+};
+
+struct mlx5_srq_table {
+ struct notifier_block nb;
+ /* protect radix tree
+ */
+ spinlock_t lock;
+ struct radix_tree_root tree;
+};
+
+int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *in);
+int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq);
+int mlx5_cmd_query_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *out);
+int mlx5_cmd_arm_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ u16 lwm, int is_srq);
+struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn);
+
+int mlx5_init_srq_table(struct mlx5_ib_dev *dev);
+void mlx5_cleanup_srq_table(struct mlx5_ib_dev *dev);
+#endif /* MLX5_IB_SRQ_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2013-2018, Mellanox Technologies inc. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/cmd.h>
+#include "mlx5_ib.h"
+#include "srq.h"
+
+static int get_pas_size(struct mlx5_srq_attr *in)
+{
+ u32 log_page_size = in->log_page_size + 12;
+ u32 log_srq_size = in->log_size;
+ u32 log_rq_stride = in->wqe_shift;
+ u32 page_offset = in->page_offset;
+ u32 po_quanta = 1 << (log_page_size - 6);
+ u32 rq_sz = 1 << (log_srq_size + 4 + log_rq_stride);
+ u32 page_size = 1 << log_page_size;
+ u32 rq_sz_po = rq_sz + (page_offset * po_quanta);
+ u32 rq_num_pas = DIV_ROUND_UP(rq_sz_po, page_size);
+
+ return rq_num_pas * sizeof(u64);
+}
+
+static void set_wq(void *wq, struct mlx5_srq_attr *in)
+{
+ MLX5_SET(wq, wq, wq_signature, !!(in->flags
+ & MLX5_SRQ_FLAG_WQ_SIG));
+ MLX5_SET(wq, wq, log_wq_pg_sz, in->log_page_size);
+ MLX5_SET(wq, wq, log_wq_stride, in->wqe_shift + 4);
+ MLX5_SET(wq, wq, log_wq_sz, in->log_size);
+ MLX5_SET(wq, wq, page_offset, in->page_offset);
+ MLX5_SET(wq, wq, lwm, in->lwm);
+ MLX5_SET(wq, wq, pd, in->pd);
+ MLX5_SET64(wq, wq, dbr_addr, in->db_record);
+}
+
+static void set_srqc(void *srqc, struct mlx5_srq_attr *in)
+{
+ MLX5_SET(srqc, srqc, wq_signature, !!(in->flags
+ & MLX5_SRQ_FLAG_WQ_SIG));
+ MLX5_SET(srqc, srqc, log_page_size, in->log_page_size);
+ MLX5_SET(srqc, srqc, log_rq_stride, in->wqe_shift);
+ MLX5_SET(srqc, srqc, log_srq_size, in->log_size);
+ MLX5_SET(srqc, srqc, page_offset, in->page_offset);
+ MLX5_SET(srqc, srqc, lwm, in->lwm);
+ MLX5_SET(srqc, srqc, pd, in->pd);
+ MLX5_SET64(srqc, srqc, dbr_addr, in->db_record);
+ MLX5_SET(srqc, srqc, xrcd, in->xrcd);
+ MLX5_SET(srqc, srqc, cqn, in->cqn);
+}
+
+static void get_wq(void *wq, struct mlx5_srq_attr *in)
+{
+ if (MLX5_GET(wq, wq, wq_signature))
+ in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
+ in->log_page_size = MLX5_GET(wq, wq, log_wq_pg_sz);
+ in->wqe_shift = MLX5_GET(wq, wq, log_wq_stride) - 4;
+ in->log_size = MLX5_GET(wq, wq, log_wq_sz);
+ in->page_offset = MLX5_GET(wq, wq, page_offset);
+ in->lwm = MLX5_GET(wq, wq, lwm);
+ in->pd = MLX5_GET(wq, wq, pd);
+ in->db_record = MLX5_GET64(wq, wq, dbr_addr);
+}
+
+static void get_srqc(void *srqc, struct mlx5_srq_attr *in)
+{
+ if (MLX5_GET(srqc, srqc, wq_signature))
+ in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
+ in->log_page_size = MLX5_GET(srqc, srqc, log_page_size);
+ in->wqe_shift = MLX5_GET(srqc, srqc, log_rq_stride);
+ in->log_size = MLX5_GET(srqc, srqc, log_srq_size);
+ in->page_offset = MLX5_GET(srqc, srqc, page_offset);
+ in->lwm = MLX5_GET(srqc, srqc, lwm);
+ in->pd = MLX5_GET(srqc, srqc, pd);
+ in->db_record = MLX5_GET64(srqc, srqc, dbr_addr);
+}
+
+struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn)
+{
+ struct mlx5_srq_table *table = &dev->srq_table;
+ struct mlx5_core_srq *srq;
+
+ spin_lock(&table->lock);
+
+ srq = radix_tree_lookup(&table->tree, srqn);
+ if (srq)
+ atomic_inc(&srq->refcount);
+
+ spin_unlock(&table->lock);
+
+ return srq;
+}
+
+static int create_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *in)
+{
+ u32 create_out[MLX5_ST_SZ_DW(create_srq_out)] = {0};
+ void *create_in;
+ void *srqc;
+ void *pas;
+ int pas_size;
+ int inlen;
+ int err;
+
+ pas_size = get_pas_size(in);
+ inlen = MLX5_ST_SZ_BYTES(create_srq_in) + pas_size;
+ create_in = kvzalloc(inlen, GFP_KERNEL);
+ if (!create_in)
+ return -ENOMEM;
+
+ MLX5_SET(create_srq_in, create_in, uid, in->uid);
+ srqc = MLX5_ADDR_OF(create_srq_in, create_in, srq_context_entry);
+ pas = MLX5_ADDR_OF(create_srq_in, create_in, pas);
+
+ set_srqc(srqc, in);
+ memcpy(pas, in->pas, pas_size);
+
+ MLX5_SET(create_srq_in, create_in, opcode,
+ MLX5_CMD_OP_CREATE_SRQ);
+
+ err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out,
+ sizeof(create_out));
+ kvfree(create_in);
+ if (!err) {
+ srq->srqn = MLX5_GET(create_srq_out, create_out, srqn);
+ srq->uid = in->uid;
+ }
+
+ return err;
+}
+
+static int destroy_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
+{
+ u32 srq_in[MLX5_ST_SZ_DW(destroy_srq_in)] = {0};
+ u32 srq_out[MLX5_ST_SZ_DW(destroy_srq_out)] = {0};
+
+ MLX5_SET(destroy_srq_in, srq_in, opcode,
+ MLX5_CMD_OP_DESTROY_SRQ);
+ MLX5_SET(destroy_srq_in, srq_in, srqn, srq->srqn);
+ MLX5_SET(destroy_srq_in, srq_in, uid, srq->uid);
+
+ return mlx5_cmd_exec(dev->mdev, srq_in, sizeof(srq_in), srq_out,
+ sizeof(srq_out));
+}
+
+static int arm_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ u16 lwm, int is_srq)
+{
+ u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
+ u32 srq_out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
+
+ MLX5_SET(arm_rq_in, srq_in, opcode, MLX5_CMD_OP_ARM_RQ);
+ MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ);
+ MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn);
+ MLX5_SET(arm_rq_in, srq_in, lwm, lwm);
+ MLX5_SET(arm_rq_in, srq_in, uid, srq->uid);
+
+ return mlx5_cmd_exec(dev->mdev, srq_in, sizeof(srq_in), srq_out,
+ sizeof(srq_out));
+}
+
+static int query_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *out)
+{
+ u32 srq_in[MLX5_ST_SZ_DW(query_srq_in)] = {0};
+ u32 *srq_out;
+ void *srqc;
+ int err;
+
+ srq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_srq_out), GFP_KERNEL);
+ if (!srq_out)
+ return -ENOMEM;
+
+ MLX5_SET(query_srq_in, srq_in, opcode,
+ MLX5_CMD_OP_QUERY_SRQ);
+ MLX5_SET(query_srq_in, srq_in, srqn, srq->srqn);
+ err = mlx5_cmd_exec(dev->mdev, srq_in, sizeof(srq_in), srq_out,
+ MLX5_ST_SZ_BYTES(query_srq_out));
+ if (err)
+ goto out;
+
+ srqc = MLX5_ADDR_OF(query_srq_out, srq_out, srq_context_entry);
+ get_srqc(srqc, out);
+ if (MLX5_GET(srqc, srqc, state) != MLX5_SRQC_STATE_GOOD)
+ out->flags |= MLX5_SRQ_FLAG_ERR;
+out:
+ kvfree(srq_out);
+ return err;
+}
+
+static int create_xrc_srq_cmd(struct mlx5_ib_dev *dev,
+ struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *in)
+{
+ u32 create_out[MLX5_ST_SZ_DW(create_xrc_srq_out)];
+ void *create_in;
+ void *xrc_srqc;
+ void *pas;
+ int pas_size;
+ int inlen;
+ int err;
+
+ pas_size = get_pas_size(in);
+ inlen = MLX5_ST_SZ_BYTES(create_xrc_srq_in) + pas_size;
+ create_in = kvzalloc(inlen, GFP_KERNEL);
+ if (!create_in)
+ return -ENOMEM;
+
+ MLX5_SET(create_xrc_srq_in, create_in, uid, in->uid);
+ xrc_srqc = MLX5_ADDR_OF(create_xrc_srq_in, create_in,
+ xrc_srq_context_entry);
+ pas = MLX5_ADDR_OF(create_xrc_srq_in, create_in, pas);
+
+ set_srqc(xrc_srqc, in);
+ MLX5_SET(xrc_srqc, xrc_srqc, user_index, in->user_index);
+ memcpy(pas, in->pas, pas_size);
+ MLX5_SET(create_xrc_srq_in, create_in, opcode,
+ MLX5_CMD_OP_CREATE_XRC_SRQ);
+
+ memset(create_out, 0, sizeof(create_out));
+ err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out,
+ sizeof(create_out));
+ if (err)
+ goto out;
+
+ srq->srqn = MLX5_GET(create_xrc_srq_out, create_out, xrc_srqn);
+ srq->uid = in->uid;
+out:
+ kvfree(create_in);
+ return err;
+}
+
+static int destroy_xrc_srq_cmd(struct mlx5_ib_dev *dev,
+ struct mlx5_core_srq *srq)
+{
+ u32 xrcsrq_in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)] = {0};
+ u32 xrcsrq_out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
+
+ MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, opcode,
+ MLX5_CMD_OP_DESTROY_XRC_SRQ);
+ MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+ MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, uid, srq->uid);
+
+ return mlx5_cmd_exec(dev->mdev, xrcsrq_in, sizeof(xrcsrq_in),
+ xrcsrq_out, sizeof(xrcsrq_out));
+}
+
+static int arm_xrc_srq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ u16 lwm)
+{
+ u32 xrcsrq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)] = {0};
+ u32 xrcsrq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
+
+ MLX5_SET(arm_xrc_srq_in, xrcsrq_in, opcode, MLX5_CMD_OP_ARM_XRC_SRQ);
+ MLX5_SET(arm_xrc_srq_in, xrcsrq_in, op_mod, MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
+ MLX5_SET(arm_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+ MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm, lwm);
+ MLX5_SET(arm_xrc_srq_in, xrcsrq_in, uid, srq->uid);
+
+ return mlx5_cmd_exec(dev->mdev, xrcsrq_in, sizeof(xrcsrq_in),
+ xrcsrq_out, sizeof(xrcsrq_out));
+}
+
+static int query_xrc_srq_cmd(struct mlx5_ib_dev *dev,
+ struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *out)
+{
+ u32 xrcsrq_in[MLX5_ST_SZ_DW(query_xrc_srq_in)];
+ u32 *xrcsrq_out;
+ void *xrc_srqc;
+ int err;
+
+ xrcsrq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_xrc_srq_out), GFP_KERNEL);
+ if (!xrcsrq_out)
+ return -ENOMEM;
+ memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
+
+ MLX5_SET(query_xrc_srq_in, xrcsrq_in, opcode,
+ MLX5_CMD_OP_QUERY_XRC_SRQ);
+ MLX5_SET(query_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+
+ err = mlx5_cmd_exec(dev->mdev, xrcsrq_in, sizeof(xrcsrq_in),
+ xrcsrq_out, MLX5_ST_SZ_BYTES(query_xrc_srq_out));
+ if (err)
+ goto out;
+
+ xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, xrcsrq_out,
+ xrc_srq_context_entry);
+ get_srqc(xrc_srqc, out);
+ if (MLX5_GET(xrc_srqc, xrc_srqc, state) != MLX5_XRC_SRQC_STATE_GOOD)
+ out->flags |= MLX5_SRQ_FLAG_ERR;
+
+out:
+ kvfree(xrcsrq_out);
+ return err;
+}
+
+static int create_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *in)
+{
+ void *create_out = NULL;
+ void *create_in = NULL;
+ void *rmpc;
+ void *wq;
+ int pas_size;
+ int outlen;
+ int inlen;
+ int err;
+
+ pas_size = get_pas_size(in);
+ inlen = MLX5_ST_SZ_BYTES(create_rmp_in) + pas_size;
+ outlen = MLX5_ST_SZ_BYTES(create_rmp_out);
+ create_in = kvzalloc(inlen, GFP_KERNEL);
+ create_out = kvzalloc(outlen, GFP_KERNEL);
+ if (!create_in || !create_out) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ rmpc = MLX5_ADDR_OF(create_rmp_in, create_in, ctx);
+ wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
+
+ MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
+ MLX5_SET(create_rmp_in, create_in, uid, in->uid);
+ set_wq(wq, in);
+ memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size);
+
+ MLX5_SET(create_rmp_in, create_in, opcode, MLX5_CMD_OP_CREATE_RMP);
+ err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out, outlen);
+ if (!err) {
+ srq->srqn = MLX5_GET(create_rmp_out, create_out, rmpn);
+ srq->uid = in->uid;
+ }
+
+out:
+ kvfree(create_in);
+ kvfree(create_out);
+ return err;
+}
+
+static int destroy_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)] = {};
+ u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {};
+
+ MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
+ MLX5_SET(destroy_rmp_in, in, rmpn, srq->srqn);
+ MLX5_SET(destroy_rmp_in, in, uid, srq->uid);
+ return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int arm_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ u16 lwm)
+{
+ void *out = NULL;
+ void *in = NULL;
+ void *rmpc;
+ void *wq;
+ void *bitmask;
+ int outlen;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(modify_rmp_in);
+ outlen = MLX5_ST_SZ_BYTES(modify_rmp_out);
+
+ in = kvzalloc(inlen, GFP_KERNEL);
+ out = kvzalloc(outlen, GFP_KERNEL);
+ if (!in || !out) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ rmpc = MLX5_ADDR_OF(modify_rmp_in, in, ctx);
+ bitmask = MLX5_ADDR_OF(modify_rmp_in, in, bitmask);
+ wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
+
+ MLX5_SET(modify_rmp_in, in, rmp_state, MLX5_RMPC_STATE_RDY);
+ MLX5_SET(modify_rmp_in, in, rmpn, srq->srqn);
+ MLX5_SET(modify_rmp_in, in, uid, srq->uid);
+ MLX5_SET(wq, wq, lwm, lwm);
+ MLX5_SET(rmp_bitmask, bitmask, lwm, 1);
+ MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
+ MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
+
+ err = mlx5_cmd_exec(dev->mdev, in, inlen, out, outlen);
+
+out:
+ kvfree(in);
+ kvfree(out);
+ return err;
+}
+
+static int query_rmp_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *out)
+{
+ u32 *rmp_out = NULL;
+ u32 *rmp_in = NULL;
+ void *rmpc;
+ int outlen;
+ int inlen;
+ int err;
+
+ outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
+ inlen = MLX5_ST_SZ_BYTES(query_rmp_in);
+
+ rmp_out = kvzalloc(outlen, GFP_KERNEL);
+ rmp_in = kvzalloc(inlen, GFP_KERNEL);
+ if (!rmp_out || !rmp_in) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ MLX5_SET(query_rmp_in, rmp_in, opcode, MLX5_CMD_OP_QUERY_RMP);
+ MLX5_SET(query_rmp_in, rmp_in, rmpn, srq->srqn);
+ err = mlx5_cmd_exec(dev->mdev, rmp_in, inlen, rmp_out, outlen);
+ if (err)
+ goto out;
+
+ rmpc = MLX5_ADDR_OF(query_rmp_out, rmp_out, rmp_context);
+ get_wq(MLX5_ADDR_OF(rmpc, rmpc, wq), out);
+ if (MLX5_GET(rmpc, rmpc, state) != MLX5_RMPC_STATE_RDY)
+ out->flags |= MLX5_SRQ_FLAG_ERR;
+
+out:
+ kvfree(rmp_out);
+ kvfree(rmp_in);
+ return err;
+}
+
+static int create_xrq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *in)
+{
+ u32 create_out[MLX5_ST_SZ_DW(create_xrq_out)] = {0};
+ void *create_in;
+ void *xrqc;
+ void *wq;
+ int pas_size;
+ int inlen;
+ int err;
+
+ pas_size = get_pas_size(in);
+ inlen = MLX5_ST_SZ_BYTES(create_xrq_in) + pas_size;
+ create_in = kvzalloc(inlen, GFP_KERNEL);
+ if (!create_in)
+ return -ENOMEM;
+
+ xrqc = MLX5_ADDR_OF(create_xrq_in, create_in, xrq_context);
+ wq = MLX5_ADDR_OF(xrqc, xrqc, wq);
+
+ set_wq(wq, in);
+ memcpy(MLX5_ADDR_OF(xrqc, xrqc, wq.pas), in->pas, pas_size);
+
+ if (in->type == IB_SRQT_TM) {
+ MLX5_SET(xrqc, xrqc, topology, MLX5_XRQC_TOPOLOGY_TAG_MATCHING);
+ if (in->flags & MLX5_SRQ_FLAG_RNDV)
+ MLX5_SET(xrqc, xrqc, offload, MLX5_XRQC_OFFLOAD_RNDV);
+ MLX5_SET(xrqc, xrqc,
+ tag_matching_topology_context.log_matching_list_sz,
+ in->tm_log_list_size);
+ }
+ MLX5_SET(xrqc, xrqc, user_index, in->user_index);
+ MLX5_SET(xrqc, xrqc, cqn, in->cqn);
+ MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ);
+ MLX5_SET(create_xrq_in, create_in, uid, in->uid);
+ err = mlx5_cmd_exec(dev->mdev, create_in, inlen, create_out,
+ sizeof(create_out));
+ kvfree(create_in);
+ if (!err) {
+ srq->srqn = MLX5_GET(create_xrq_out, create_out, xrqn);
+ srq->uid = in->uid;
+ }
+
+ return err;
+}
+
+static int destroy_xrq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_xrq_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(destroy_xrq_out)] = {0};
+
+ MLX5_SET(destroy_xrq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRQ);
+ MLX5_SET(destroy_xrq_in, in, xrqn, srq->srqn);
+ MLX5_SET(destroy_xrq_in, in, uid, srq->uid);
+
+ return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int arm_xrq_cmd(struct mlx5_ib_dev *dev,
+ struct mlx5_core_srq *srq,
+ u16 lwm)
+{
+ u32 out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
+ u32 in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
+
+ MLX5_SET(arm_rq_in, in, opcode, MLX5_CMD_OP_ARM_RQ);
+ MLX5_SET(arm_rq_in, in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_XRQ);
+ MLX5_SET(arm_rq_in, in, srq_number, srq->srqn);
+ MLX5_SET(arm_rq_in, in, lwm, lwm);
+ MLX5_SET(arm_rq_in, in, uid, srq->uid);
+
+ return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int query_xrq_cmd(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *out)
+{
+ u32 in[MLX5_ST_SZ_DW(query_xrq_in)] = {0};
+ u32 *xrq_out;
+ int outlen = MLX5_ST_SZ_BYTES(query_xrq_out);
+ void *xrqc;
+ int err;
+
+ xrq_out = kvzalloc(outlen, GFP_KERNEL);
+ if (!xrq_out)
+ return -ENOMEM;
+
+ MLX5_SET(query_xrq_in, in, opcode, MLX5_CMD_OP_QUERY_XRQ);
+ MLX5_SET(query_xrq_in, in, xrqn, srq->srqn);
+
+ err = mlx5_cmd_exec(dev->mdev, in, sizeof(in), xrq_out, outlen);
+ if (err)
+ goto out;
+
+ xrqc = MLX5_ADDR_OF(query_xrq_out, xrq_out, xrq_context);
+ get_wq(MLX5_ADDR_OF(xrqc, xrqc, wq), out);
+ if (MLX5_GET(xrqc, xrqc, state) != MLX5_XRQC_STATE_GOOD)
+ out->flags |= MLX5_SRQ_FLAG_ERR;
+ out->tm_next_tag =
+ MLX5_GET(xrqc, xrqc,
+ tag_matching_topology_context.append_next_index);
+ out->tm_hw_phase_cnt =
+ MLX5_GET(xrqc, xrqc,
+ tag_matching_topology_context.hw_phase_cnt);
+ out->tm_sw_phase_cnt =
+ MLX5_GET(xrqc, xrqc,
+ tag_matching_topology_context.sw_phase_cnt);
+
+out:
+ kvfree(xrq_out);
+ return err;
+}
+
+static int create_srq_split(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *in)
+{
+ if (!dev->mdev->issi)
+ return create_srq_cmd(dev, srq, in);
+ switch (srq->common.res) {
+ case MLX5_RES_XSRQ:
+ return create_xrc_srq_cmd(dev, srq, in);
+ case MLX5_RES_XRQ:
+ return create_xrq_cmd(dev, srq, in);
+ default:
+ return create_rmp_cmd(dev, srq, in);
+ }
+}
+
+static int destroy_srq_split(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
+{
+ if (!dev->mdev->issi)
+ return destroy_srq_cmd(dev, srq);
+ switch (srq->common.res) {
+ case MLX5_RES_XSRQ:
+ return destroy_xrc_srq_cmd(dev, srq);
+ case MLX5_RES_XRQ:
+ return destroy_xrq_cmd(dev, srq);
+ default:
+ return destroy_rmp_cmd(dev, srq);
+ }
+}
+
+int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *in)
+{
+ struct mlx5_srq_table *table = &dev->srq_table;
+ int err;
+
+ switch (in->type) {
+ case IB_SRQT_XRC:
+ srq->common.res = MLX5_RES_XSRQ;
+ break;
+ case IB_SRQT_TM:
+ srq->common.res = MLX5_RES_XRQ;
+ break;
+ default:
+ srq->common.res = MLX5_RES_SRQ;
+ }
+
+ err = create_srq_split(dev, srq, in);
+ if (err)
+ return err;
+
+ atomic_set(&srq->refcount, 1);
+ init_completion(&srq->free);
+
+ spin_lock_irq(&table->lock);
+ err = radix_tree_insert(&table->tree, srq->srqn, srq);
+ spin_unlock_irq(&table->lock);
+ if (err)
+ goto err_destroy_srq_split;
+
+ return 0;
+
+err_destroy_srq_split:
+ destroy_srq_split(dev, srq);
+
+ return err;
+}
+
+int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
+{
+ struct mlx5_srq_table *table = &dev->srq_table;
+ struct mlx5_core_srq *tmp;
+ int err;
+
+ spin_lock_irq(&table->lock);
+ tmp = radix_tree_delete(&table->tree, srq->srqn);
+ spin_unlock_irq(&table->lock);
+ if (!tmp || tmp != srq)
+ return -EINVAL;
+
+ err = destroy_srq_split(dev, srq);
+ if (err)
+ return err;
+
+ if (atomic_dec_and_test(&srq->refcount))
+ complete(&srq->free);
+ wait_for_completion(&srq->free);
+
+ return 0;
+}
+
+int mlx5_cmd_query_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ struct mlx5_srq_attr *out)
+{
+ if (!dev->mdev->issi)
+ return query_srq_cmd(dev, srq, out);
+ switch (srq->common.res) {
+ case MLX5_RES_XSRQ:
+ return query_xrc_srq_cmd(dev, srq, out);
+ case MLX5_RES_XRQ:
+ return query_xrq_cmd(dev, srq, out);
+ default:
+ return query_rmp_cmd(dev, srq, out);
+ }
+}
+
+int mlx5_cmd_arm_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
+ u16 lwm, int is_srq)
+{
+ if (!dev->mdev->issi)
+ return arm_srq_cmd(dev, srq, lwm, is_srq);
+ switch (srq->common.res) {
+ case MLX5_RES_XSRQ:
+ return arm_xrc_srq_cmd(dev, srq, lwm);
+ case MLX5_RES_XRQ:
+ return arm_xrq_cmd(dev, srq, lwm);
+ default:
+ return arm_rmp_cmd(dev, srq, lwm);
+ }
+}
+
+static int srq_event_notifier(struct notifier_block *nb,
+ unsigned long type, void *data)
+{
+ struct mlx5_srq_table *table;
+ struct mlx5_core_srq *srq;
+ struct mlx5_eqe *eqe;
+ u32 srqn;
+
+ if (type != MLX5_EVENT_TYPE_SRQ_CATAS_ERROR &&
+ type != MLX5_EVENT_TYPE_SRQ_RQ_LIMIT)
+ return NOTIFY_DONE;
+
+ table = container_of(nb, struct mlx5_srq_table, nb);
+
+ eqe = data;
+ srqn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+
+ spin_lock(&table->lock);
+
+ srq = radix_tree_lookup(&table->tree, srqn);
+ if (srq)
+ atomic_inc(&srq->refcount);
+
+ spin_unlock(&table->lock);
+
+ if (!srq)
+ return NOTIFY_OK;
+
+ srq->event(srq, eqe->type);
+
+ if (atomic_dec_and_test(&srq->refcount))
+ complete(&srq->free);
+
+ return NOTIFY_OK;
+}
+
+int mlx5_init_srq_table(struct mlx5_ib_dev *dev)
+{
+ struct mlx5_srq_table *table = &dev->srq_table;
+
+ memset(table, 0, sizeof(*table));
+ spin_lock_init(&table->lock);
+ INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+
+ table->nb.notifier_call = srq_event_notifier;
+ mlx5_notifier_register(dev->mdev, &table->nb);
+
+ return 0;
+}
+
+void mlx5_cleanup_srq_table(struct mlx5_ib_dev *dev)
+{
+ struct mlx5_srq_table *table = &dev->srq_table;
+
+ mlx5_notifier_unregister(dev->mdev, &table->nb);
+}
# mlx5 core basic
#
mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
- health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
+ health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
- fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \
+ fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
diag/fs_tracepoint.o diag/fw_tracer.o
#
#include <linux/random.h>
#include <linux/io-mapping.h>
#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
#include <linux/debugfs.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
enum {
CMD_IF_REV = 5,
case MLX5_CMD_OP_FPGA_DESTROY_QP:
case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
case MLX5_CMD_OP_DEALLOC_MEMIC:
+ case MLX5_CMD_OP_PAGE_FAULT_RESUME:
return MLX5_CMD_STAT_OK;
case MLX5_CMD_OP_QUERY_HCA_CAP:
case MLX5_CMD_OP_CREATE_MKEY:
case MLX5_CMD_OP_QUERY_MKEY:
case MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS:
- case MLX5_CMD_OP_PAGE_FAULT_RESUME:
case MLX5_CMD_OP_CREATE_EQ:
case MLX5_CMD_OP_QUERY_EQ:
case MLX5_CMD_OP_GEN_EQE:
case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
case MLX5_CMD_OP_ALLOC_Q_COUNTER:
case MLX5_CMD_OP_QUERY_Q_COUNTER:
+ case MLX5_CMD_OP_SET_MONITOR_COUNTER:
+ case MLX5_CMD_OP_ARM_MONITOR_COUNTER:
case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
case MLX5_CMD_OP_QUERY_RATE_LIMIT:
case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+ MLX5_COMMAND_STR_CASE(SET_MONITOR_COUNTER);
+ MLX5_COMMAND_STR_CASE(ARM_MONITOR_COUNTER);
MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
return MLX5_GET(mbox_in, in->first.data, opcode);
}
+static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
+
static void cb_timeout_handler(struct work_struct *work)
{
struct delayed_work *dwork = container_of(work, struct delayed_work,
up(&cmd->sem);
}
+static int cmd_comp_notifier(struct notifier_block *nb,
+ unsigned long type, void *data)
+{
+ struct mlx5_core_dev *dev;
+ struct mlx5_cmd *cmd;
+ struct mlx5_eqe *eqe;
+
+ cmd = mlx5_nb_cof(nb, struct mlx5_cmd, nb);
+ dev = container_of(cmd, struct mlx5_core_dev, cmd);
+ eqe = data;
+
+ mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
+
+ return NOTIFY_OK;
+}
void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
{
+ MLX5_NB_INIT(&dev->cmd.nb, cmd_comp_notifier, CMD);
+ mlx5_eq_notifier_register(dev, &dev->cmd.nb);
mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
}
void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
{
mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
+ mlx5_eq_notifier_unregister(dev, &dev->cmd.nb);
}
static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
}
}
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
+static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
{
struct mlx5_cmd *cmd = &dev->cmd;
struct mlx5_cmd_work_ent *ent;
}
}
}
-EXPORT_SYMBOL(mlx5_cmd_comp_handler);
+
+void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
+{
+ unsigned long flags;
+ u64 vector;
+
+ /* wait for pending handlers to complete */
+ mlx5_eq_synchronize_cmd_irq(dev);
+ spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
+ vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
+ if (!vector)
+ goto no_trig;
+
+ vector |= MLX5_TRIGGERED_CMD_COMP;
+ spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
+
+ mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
+ mlx5_cmd_comp_handler(dev, vector, true);
+ return;
+
+no_trig:
+ spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
+}
static int status_to_err(u8 status)
{
#include <rdma/ib_verbs.h>
#include <linux/mlx5/cq.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
#define TASKLET_MAX_TIME 2
#define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)];
u32 out[MLX5_ST_SZ_DW(create_cq_out)];
u32 din[MLX5_ST_SZ_DW(destroy_cq_in)];
- struct mlx5_eq *eq;
+ struct mlx5_eq_comp *eq;
int err;
- eq = mlx5_eqn2eq(dev, eqn);
+ eq = mlx5_eqn2comp_eq(dev, eqn);
if (IS_ERR(eq))
return PTR_ERR(eq);
INIT_LIST_HEAD(&cq->tasklet_ctx.list);
/* Add to comp EQ CQ tree to recv comp events */
- err = mlx5_eq_add_cq(eq, cq);
+ err = mlx5_eq_add_cq(&eq->core, cq);
if (err)
goto err_cmd;
/* Add to async EQ CQ tree to recv async events */
- err = mlx5_eq_add_cq(&dev->priv.eq_table.async_eq, cq);
+ err = mlx5_eq_add_cq(mlx5_get_async_eq(dev), cq);
if (err)
goto err_cq_add;
return 0;
err_cq_add:
- mlx5_eq_del_cq(eq, cq);
+ mlx5_eq_del_cq(&eq->core, cq);
err_cmd:
memset(din, 0, sizeof(din));
memset(dout, 0, sizeof(dout));
u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0};
int err;
- err = mlx5_eq_del_cq(&dev->priv.eq_table.async_eq, cq);
+ err = mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
if (err)
return err;
- err = mlx5_eq_del_cq(cq->eq, cq);
+ err = mlx5_eq_del_cq(&cq->eq->core, cq);
if (err)
return err;
#include <linux/mlx5/cq.h>
#include <linux/mlx5/driver.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
enum {
QP_PID,
return param;
}
+static int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+ u32 *out, int outlen)
+{
+ u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {};
+
+ MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
+ MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
static u64 eq_read_field(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
int index)
{
unsigned long state;
};
-struct mlx5_delayed_event {
- struct list_head list;
- struct mlx5_core_dev *dev;
- enum mlx5_dev_event event;
- unsigned long param;
-};
-
enum {
MLX5_INTERFACE_ADDED,
MLX5_INTERFACE_ATTACHED,
};
-static void add_delayed_event(struct mlx5_priv *priv,
- struct mlx5_core_dev *dev,
- enum mlx5_dev_event event,
- unsigned long param)
-{
- struct mlx5_delayed_event *delayed_event;
-
- delayed_event = kzalloc(sizeof(*delayed_event), GFP_ATOMIC);
- if (!delayed_event) {
- mlx5_core_err(dev, "event %d is missed\n", event);
- return;
- }
-
- mlx5_core_dbg(dev, "Accumulating event %d\n", event);
- delayed_event->dev = dev;
- delayed_event->event = event;
- delayed_event->param = param;
- list_add_tail(&delayed_event->list, &priv->waiting_events_list);
-}
-
-static void delayed_event_release(struct mlx5_device_context *dev_ctx,
- struct mlx5_priv *priv)
-{
- struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
- struct mlx5_delayed_event *de;
- struct mlx5_delayed_event *n;
- struct list_head temp;
-
- INIT_LIST_HEAD(&temp);
-
- spin_lock_irq(&priv->ctx_lock);
-
- priv->is_accum_events = false;
- list_splice_init(&priv->waiting_events_list, &temp);
- if (!dev_ctx->context)
- goto out;
- list_for_each_entry_safe(de, n, &temp, list)
- dev_ctx->intf->event(dev, dev_ctx->context, de->event, de->param);
-
-out:
- spin_unlock_irq(&priv->ctx_lock);
-
- list_for_each_entry_safe(de, n, &temp, list) {
- list_del(&de->list);
- kfree(de);
- }
-}
-
-/* accumulating events that can come after mlx5_ib calls to
- * ib_register_device, till adding that interface to the events list.
- */
-static void delayed_event_start(struct mlx5_priv *priv)
-{
- spin_lock_irq(&priv->ctx_lock);
- priv->is_accum_events = true;
- spin_unlock_irq(&priv->ctx_lock);
-}
void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
{
dev_ctx->intf = intf;
- delayed_event_start(priv);
-
dev_ctx->context = intf->add(dev);
if (dev_ctx->context) {
set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
spin_lock_irq(&priv->ctx_lock);
list_add_tail(&dev_ctx->list, &priv->ctx_list);
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- if (dev_ctx->intf->pfault) {
- if (priv->pfault) {
- mlx5_core_err(dev, "multiple page fault handlers not supported");
- } else {
- priv->pfault_ctx = dev_ctx->context;
- priv->pfault = dev_ctx->intf->pfault;
- }
- }
-#endif
spin_unlock_irq(&priv->ctx_lock);
}
- delayed_event_release(dev_ctx, priv);
-
if (!dev_ctx->context)
kfree(dev_ctx);
}
if (!dev_ctx)
return;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- spin_lock_irq(&priv->ctx_lock);
- if (priv->pfault == dev_ctx->intf->pfault)
- priv->pfault = NULL;
- spin_unlock_irq(&priv->ctx_lock);
-
- synchronize_srcu(&priv->pfault_srcu);
-#endif
-
spin_lock_irq(&priv->ctx_lock);
list_del(&dev_ctx->list);
spin_unlock_irq(&priv->ctx_lock);
if (!dev_ctx)
return;
- delayed_event_start(priv);
if (intf->attach) {
if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
- goto out;
+ return;
if (intf->attach(dev, dev_ctx->context))
- goto out;
-
+ return;
set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
} else {
if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
- goto out;
+ return;
dev_ctx->context = intf->add(dev);
if (!dev_ctx->context)
- goto out;
-
+ return;
set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
}
-
-out:
- delayed_event_release(dev_ctx, priv);
}
void mlx5_attach_device(struct mlx5_core_dev *dev)
mutex_unlock(&mlx5_intf_mutex);
}
-void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol)
-{
- struct mlx5_priv *priv = &mdev->priv;
- struct mlx5_device_context *dev_ctx;
- unsigned long flags;
- void *result = NULL;
-
- spin_lock_irqsave(&priv->ctx_lock, flags);
-
- list_for_each_entry(dev_ctx, &mdev->priv.ctx_list, list)
- if ((dev_ctx->intf->protocol == protocol) &&
- dev_ctx->intf->get_dev) {
- result = dev_ctx->intf->get_dev(dev_ctx->context);
- break;
- }
-
- spin_unlock_irqrestore(&priv->ctx_lock, flags);
-
- return result;
-}
-EXPORT_SYMBOL(mlx5_get_protocol_dev);
-
/* Must be called with intf_mutex held */
void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
{
return res;
}
-void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
- unsigned long param)
-{
- struct mlx5_priv *priv = &dev->priv;
- struct mlx5_device_context *dev_ctx;
- unsigned long flags;
-
- spin_lock_irqsave(&priv->ctx_lock, flags);
-
- if (priv->is_accum_events)
- add_delayed_event(priv, dev, event, param);
-
- /* After mlx5_detach_device, the dev_ctx->intf is still set and dev_ctx is
- * still in priv->ctx_list. In this case, only notify the dev_ctx if its
- * ADDED or ATTACHED bit are set.
- */
- list_for_each_entry(dev_ctx, &priv->ctx_list, list)
- if (dev_ctx->intf->event &&
- (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state) ||
- test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)))
- dev_ctx->intf->event(dev, dev_ctx->context, event, param);
-
- spin_unlock_irqrestore(&priv->ctx_lock, flags);
-}
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-void mlx5_core_page_fault(struct mlx5_core_dev *dev,
- struct mlx5_pagefault *pfault)
-{
- struct mlx5_priv *priv = &dev->priv;
- int srcu_idx;
-
- srcu_idx = srcu_read_lock(&priv->pfault_srcu);
- if (priv->pfault)
- priv->pfault(dev, priv->pfault_ctx, pfault);
- srcu_read_unlock(&priv->pfault_srcu, srcu_idx);
-}
-#endif
void mlx5_dev_list_lock(void)
{
PRINT_MASKED_VAL(name, p, format); \
}
DECLARE_MASK_VAL(u64, gre_key) = {
- .m = MLX5_GET(fte_match_set_misc, mask, gre_key_h) << 8 |
- MLX5_GET(fte_match_set_misc, mask, gre_key_l),
- .v = MLX5_GET(fte_match_set_misc, value, gre_key_h) << 8 |
- MLX5_GET(fte_match_set_misc, value, gre_key_l)};
+ .m = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi) << 8 |
+ MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo),
+ .v = MLX5_GET(fte_match_set_misc, value, gre_key.nvgre.hi) << 8 |
+ MLX5_GET(fte_match_set_misc, value, gre_key.nvgre.lo)};
PRINT_MASKED_VAL(gre_key, p, "%llu");
PRINT_MASKED_VAL_MISC(u32, source_sqn, source_sqn, p, "%u");
* SOFTWARE.
*/
#define CREATE_TRACE_POINTS
+#include "lib/eq.h"
#include "fw_tracer.h"
#include "fw_tracer_tracepoint.h"
return ERR_PTR(err);
}
-/* Create HW resources + start tracer
- * must be called before Async EQ is created
- */
+static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data);
+
+/* Create HW resources + start tracer */
int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
{
struct mlx5_core_dev *dev;
goto err_dealloc_pd;
}
+ MLX5_NB_INIT(&tracer->nb, fw_tracer_event, DEVICE_TRACER);
+ mlx5_eq_notifier_register(dev, &tracer->nb);
+
mlx5_fw_tracer_start(tracer);
return 0;
return err;
}
-/* Stop tracer + Cleanup HW resources
- * must be called after Async EQ is destroyed
- */
+/* Stop tracer + Cleanup HW resources */
void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
{
if (IS_ERR_OR_NULL(tracer))
mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n",
tracer->owner);
-
+ mlx5_eq_notifier_unregister(tracer->dev, &tracer->nb);
cancel_work_sync(&tracer->ownership_change_work);
cancel_work_sync(&tracer->handle_traces_work);
kfree(tracer);
}
-void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data)
{
- struct mlx5_fw_tracer *tracer = dev->tracer;
-
- if (!tracer)
- return;
+ struct mlx5_fw_tracer *tracer = mlx5_nb_cof(nb, struct mlx5_fw_tracer, nb);
+ struct mlx5_core_dev *dev = tracer->dev;
+ struct mlx5_eqe *eqe = data;
switch (eqe->sub_type) {
case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE:
mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n",
eqe->sub_type);
}
+
+ return NOTIFY_OK;
}
EXPORT_TRACEPOINT_SYMBOL(mlx5_fw);
struct mlx5_fw_tracer {
struct mlx5_core_dev *dev;
+ struct mlx5_nb nb;
bool owner;
u8 trc_ver;
struct workqueue_struct *work_queue;
int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
-void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
#endif
{
return is_kdump_kernel() ?
MLX5E_MIN_NUM_CHANNELS :
- min_t(int, mdev->priv.eq_table.num_comp_vectors,
- MLX5E_MAX_NUM_CHANNELS);
+ min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS);
}
/* Use this function to get max num channels after netdev was created */
} ____cacheline_aligned_in_smp;
enum {
- MLX5E_STATE_ASYNC_EVENTS_ENABLED,
MLX5E_STATE_OPENED,
MLX5E_STATE_DESTROYING,
};
struct hwtstamp_config tstamp;
u16 q_counter;
u16 drop_rq_q_counter;
+ struct notifier_block events_nb;
+
#ifdef CONFIG_MLX5_CORE_EN_DCB
struct mlx5e_dcbx dcbx;
#endif
#include "lib/clock.h"
#include "en/port.h"
#include "en/xdp.h"
+#include "lib/eq.h"
struct mlx5e_rq_param {
u32 rqc[MLX5_ST_SZ_DW(rqc)];
queue_work(priv->wq, &priv->update_stats_work);
}
-static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
- enum mlx5_dev_event event, unsigned long param)
+static int async_event(struct notifier_block *nb, unsigned long event, void *data)
{
- struct mlx5e_priv *priv = vpriv;
+ struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+ struct mlx5_eqe *eqe = data;
- if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
- return;
+ if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
+ return NOTIFY_DONE;
- switch (event) {
- case MLX5_DEV_EVENT_PORT_UP:
- case MLX5_DEV_EVENT_PORT_DOWN:
+ switch (eqe->sub_type) {
+ case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+ case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
queue_work(priv->wq, &priv->update_carrier_work);
break;
default:
- break;
+ return NOTIFY_DONE;
}
+
+ return NOTIFY_OK;
}
static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
{
- set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
+ priv->events_nb.notifier_call = async_event;
+ mlx5_notifier_register(priv->mdev, &priv->events_nb);
}
static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
{
- clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
- synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
+ mlx5_notifier_unregister(priv->mdev, &priv->events_nb);
}
static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
mlx5e_free_cq(cq);
}
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
- return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
-}
-
static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
struct mlx5e_params *params,
struct mlx5e_channel_param *cparam)
struct mlx5e_channel_param *cparam,
struct mlx5e_channel **cp)
{
+ int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
struct net_dim_cq_moder icocq_moder = {0, 0};
struct net_device *netdev = priv->netdev;
- int cpu = mlx5e_get_cpu(priv, ix);
struct mlx5e_channel *c;
unsigned int irq;
int err;
static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
struct mlx5e_txqsq *sq)
{
- struct mlx5_eq *eq = sq->cq.mcq.eq;
+ struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
u32 eqe_count;
netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
- eq->eqn, eq->cons_index, eq->irqn);
+ eq->core.eqn, eq->core.cons_index, eq->core.irqn);
eqe_count = mlx5_eq_poll_irq_disabled(eq);
if (!eqe_count)
return false;
- netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn);
+ netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn);
sq->channel->stats->eq_rearm++;
return true;
}
netif_carrier_off(netdev);
#ifdef CONFIG_MLX5_EN_ARFS
- netdev->rx_cpu_rmap = mdev->rmap;
+ netdev->rx_cpu_rmap = mlx5_eq_table_get_rmap(mdev);
#endif
return 0;
kfree(ppriv);
}
-static void *mlx5e_get_netdev(void *vpriv)
-{
- struct mlx5e_priv *priv = vpriv;
-
- return priv->netdev;
-}
-
static struct mlx5_interface mlx5e_interface = {
.add = mlx5e_add,
.remove = mlx5e_remove,
.attach = mlx5e_attach,
.detach = mlx5e_detach,
- .event = mlx5e_async_event,
.protocol = MLX5_INTERFACE_PROTOCOL_ETH,
- .get_dev = mlx5e_get_netdev,
};
void mlx5e_init(void)
mlx5_cqwq_pop(&cq->wq);
- if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) {
+ if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
netdev_WARN_ONCE(cq->channel->netdev,
- "Bad OP in ICOSQ CQE: 0x%x\n", cqe->op_own);
+ "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
return;
}
prefetchw(va); /* xdp_frame data area */
prefetch(data);
- if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+ if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
rq->stats->wqe_err++;
return NULL;
}
u16 byte_cnt = cqe_bcnt - headlen;
struct sk_buff *skb;
- if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+ if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
rq->stats->wqe_err++;
return NULL;
}
wi->consumed_strides += cstrides;
- if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+ if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
rq->stats->wqe_err++;
goto mpwrq_cqe_out;
}
* SOFTWARE.
*/
+#include "lib/mlx5.h"
#include "en.h"
#include "en_accel/ipsec.h"
#include "en_accel/tls.h"
}
static const struct counter_desc mlx5e_pme_status_desc[] = {
- { "module_unplug", 8 },
+ { "module_unplug", sizeof(u64) * MLX5_MODULE_STATUS_UNPLUGGED },
};
static const struct counter_desc mlx5e_pme_error_desc[] = {
- { "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */
- { "module_high_temp", 48 }, /* high temperature */
- { "module_bad_shorted", 56 }, /* bad or shorted cable/module */
+ { "module_bus_stuck", sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BUS_STUCK },
+ { "module_high_temp", sizeof(u64) * MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE },
+ { "module_bad_shorted", sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BAD_CABLE },
};
#define NUM_PME_STATUS_STATS ARRAY_SIZE(mlx5e_pme_status_desc)
static int mlx5e_grp_pme_fill_stats(struct mlx5e_priv *priv, u64 *data,
int idx)
{
- struct mlx5_priv *mlx5_priv = &priv->mdev->priv;
+ struct mlx5_pme_stats pme_stats;
int i;
+ mlx5_get_pme_stats(priv->mdev, &pme_stats);
+
for (i = 0; i < NUM_PME_STATUS_STATS; i++)
- data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters,
+ data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.status_counters,
mlx5e_pme_status_desc, i);
for (i = 0; i < NUM_PME_ERR_STATS; i++)
- data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters,
+ data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.error_counters,
mlx5e_pme_error_desc, i);
return idx;
wqe_counter = be16_to_cpu(cqe->wqe_counter);
- if (unlikely(cqe->op_own >> 4 == MLX5_CQE_REQ_ERR)) {
+ if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
&sq->state)) {
mlx5e_dump_error_cqe(sq,
*/
#include <linux/interrupt.h>
+#include <linux/notifier.h>
#include <linux/module.h>
#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
#include <linux/mlx5/cmd.h>
#ifdef CONFIG_RFS_ACCEL
#include <linux/cpu_rmap.h>
#endif
#include "mlx5_core.h"
+#include "lib/eq.h"
#include "fpga/core.h"
#include "eswitch.h"
#include "lib/clock.h"
#include "diag/fw_tracer.h"
enum {
- MLX5_EQE_SIZE = sizeof(struct mlx5_eqe),
MLX5_EQE_OWNER_INIT_VAL = 0x1,
};
};
enum {
- MLX5_NUM_SPARE_EQE = 0x80,
- MLX5_NUM_ASYNC_EQE = 0x1000,
- MLX5_NUM_CMD_EQE = 32,
- MLX5_NUM_PF_DRAIN = 64,
+ MLX5_EQ_DOORBEL_OFFSET = 0x40,
};
-enum {
- MLX5_EQ_DOORBEL_OFFSET = 0x40,
+struct mlx5_irq_info {
+ cpumask_var_t mask;
+ char name[MLX5_MAX_IRQ_NAME];
+ void *context; /* dev_id provided to request_irq */
+};
+
+struct mlx5_eq_table {
+ struct list_head comp_eqs_list;
+ struct mlx5_eq pages_eq;
+ struct mlx5_eq cmd_eq;
+ struct mlx5_eq async_eq;
+
+ struct atomic_notifier_head nh[MLX5_EVENT_TYPE_MAX];
+
+ /* Since CQ DB is stored in async_eq */
+ struct mlx5_nb cq_err_nb;
+
+ struct mutex lock; /* sync async eqs creations */
+ int num_comp_vectors;
+ struct mlx5_irq_info *irq_info;
+#ifdef CONFIG_RFS_ACCEL
+ struct cpu_rmap *rmap;
+#endif
};
#define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG) | \
(1ull << MLX5_EVENT_TYPE_SRQ_LAST_WQE) | \
(1ull << MLX5_EVENT_TYPE_SRQ_RQ_LIMIT))
-struct map_eq_in {
- u64 mask;
- u32 reserved;
- u32 unmap_eqn;
-};
-
-struct cre_des_eq {
- u8 reserved[15];
- u8 eqn;
-};
-
static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
{
u32 out[MLX5_ST_SZ_DW(destroy_eq_out)] = {0};
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
-static struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
-{
- return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
-}
-
-static struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
-{
- struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
-
- return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
-}
-
-static const char *eqe_type_str(u8 type)
-{
- switch (type) {
- case MLX5_EVENT_TYPE_COMP:
- return "MLX5_EVENT_TYPE_COMP";
- case MLX5_EVENT_TYPE_PATH_MIG:
- return "MLX5_EVENT_TYPE_PATH_MIG";
- case MLX5_EVENT_TYPE_COMM_EST:
- return "MLX5_EVENT_TYPE_COMM_EST";
- case MLX5_EVENT_TYPE_SQ_DRAINED:
- return "MLX5_EVENT_TYPE_SQ_DRAINED";
- case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
- return "MLX5_EVENT_TYPE_SRQ_LAST_WQE";
- case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
- return "MLX5_EVENT_TYPE_SRQ_RQ_LIMIT";
- case MLX5_EVENT_TYPE_CQ_ERROR:
- return "MLX5_EVENT_TYPE_CQ_ERROR";
- case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
- return "MLX5_EVENT_TYPE_WQ_CATAS_ERROR";
- case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
- return "MLX5_EVENT_TYPE_PATH_MIG_FAILED";
- case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
- return "MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR";
- case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
- return "MLX5_EVENT_TYPE_WQ_ACCESS_ERROR";
- case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
- return "MLX5_EVENT_TYPE_SRQ_CATAS_ERROR";
- case MLX5_EVENT_TYPE_INTERNAL_ERROR:
- return "MLX5_EVENT_TYPE_INTERNAL_ERROR";
- case MLX5_EVENT_TYPE_PORT_CHANGE:
- return "MLX5_EVENT_TYPE_PORT_CHANGE";
- case MLX5_EVENT_TYPE_GPIO_EVENT:
- return "MLX5_EVENT_TYPE_GPIO_EVENT";
- case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
- return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
- case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
- return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT";
- case MLX5_EVENT_TYPE_REMOTE_CONFIG:
- return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
- case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
- return "MLX5_EVENT_TYPE_DB_BF_CONGESTION";
- case MLX5_EVENT_TYPE_STALL_EVENT:
- return "MLX5_EVENT_TYPE_STALL_EVENT";
- case MLX5_EVENT_TYPE_CMD:
- return "MLX5_EVENT_TYPE_CMD";
- case MLX5_EVENT_TYPE_PAGE_REQUEST:
- return "MLX5_EVENT_TYPE_PAGE_REQUEST";
- case MLX5_EVENT_TYPE_PAGE_FAULT:
- return "MLX5_EVENT_TYPE_PAGE_FAULT";
- case MLX5_EVENT_TYPE_PPS_EVENT:
- return "MLX5_EVENT_TYPE_PPS_EVENT";
- case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
- return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
- case MLX5_EVENT_TYPE_FPGA_ERROR:
- return "MLX5_EVENT_TYPE_FPGA_ERROR";
- case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
- return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
- case MLX5_EVENT_TYPE_GENERAL_EVENT:
- return "MLX5_EVENT_TYPE_GENERAL_EVENT";
- case MLX5_EVENT_TYPE_DEVICE_TRACER:
- return "MLX5_EVENT_TYPE_DEVICE_TRACER";
- default:
- return "Unrecognized event";
- }
-}
-
-static enum mlx5_dev_event port_subtype_event(u8 subtype)
-{
- switch (subtype) {
- case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
- return MLX5_DEV_EVENT_PORT_DOWN;
- case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
- return MLX5_DEV_EVENT_PORT_UP;
- case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
- return MLX5_DEV_EVENT_PORT_INITIALIZED;
- case MLX5_PORT_CHANGE_SUBTYPE_LID:
- return MLX5_DEV_EVENT_LID_CHANGE;
- case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
- return MLX5_DEV_EVENT_PKEY_CHANGE;
- case MLX5_PORT_CHANGE_SUBTYPE_GUID:
- return MLX5_DEV_EVENT_GUID_CHANGE;
- case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
- return MLX5_DEV_EVENT_CLIENT_REREG;
- }
- return -1;
-}
-
-static void eq_update_ci(struct mlx5_eq *eq, int arm)
+/* caller must eventually call mlx5_cq_put on the returned cq */
+static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
{
- __be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
- u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
-
- __raw_writel((__force u32)cpu_to_be32(val), addr);
- /* We still want ordering, just not swabbing, so add a barrier */
- mb();
-}
+ struct mlx5_cq_table *table = &eq->cq_table;
+ struct mlx5_core_cq *cq = NULL;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-static void eqe_pf_action(struct work_struct *work)
-{
- struct mlx5_pagefault *pfault = container_of(work,
- struct mlx5_pagefault,
- work);
- struct mlx5_eq *eq = pfault->eq;
+ spin_lock(&table->lock);
+ cq = radix_tree_lookup(&table->tree, cqn);
+ if (likely(cq))
+ mlx5_cq_hold(cq);
+ spin_unlock(&table->lock);
- mlx5_core_page_fault(eq->dev, pfault);
- mempool_free(pfault, eq->pf_ctx.pool);
+ return cq;
}
-static void eq_pf_process(struct mlx5_eq *eq)
+static irqreturn_t mlx5_eq_comp_int(int irq, void *eq_ptr)
{
- struct mlx5_core_dev *dev = eq->dev;
- struct mlx5_eqe_page_fault *pf_eqe;
- struct mlx5_pagefault *pfault;
+ struct mlx5_eq_comp *eq_comp = eq_ptr;
+ struct mlx5_eq *eq = eq_ptr;
struct mlx5_eqe *eqe;
int set_ci = 0;
+ u32 cqn = -1;
while ((eqe = next_eqe_sw(eq))) {
- pfault = mempool_alloc(eq->pf_ctx.pool, GFP_ATOMIC);
- if (!pfault) {
- schedule_work(&eq->pf_ctx.work);
- break;
- }
-
+ struct mlx5_core_cq *cq;
+ /* Make sure we read EQ entry contents after we've
+ * checked the ownership bit.
+ */
dma_rmb();
- pf_eqe = &eqe->data.page_fault;
- pfault->event_subtype = eqe->sub_type;
- pfault->bytes_committed = be32_to_cpu(pf_eqe->bytes_committed);
-
- mlx5_core_dbg(dev,
- "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x\n",
- eqe->sub_type, pfault->bytes_committed);
-
- switch (eqe->sub_type) {
- case MLX5_PFAULT_SUBTYPE_RDMA:
- /* RDMA based event */
- pfault->type =
- be32_to_cpu(pf_eqe->rdma.pftype_token) >> 24;
- pfault->token =
- be32_to_cpu(pf_eqe->rdma.pftype_token) &
- MLX5_24BIT_MASK;
- pfault->rdma.r_key =
- be32_to_cpu(pf_eqe->rdma.r_key);
- pfault->rdma.packet_size =
- be16_to_cpu(pf_eqe->rdma.packet_length);
- pfault->rdma.rdma_op_len =
- be32_to_cpu(pf_eqe->rdma.rdma_op_len);
- pfault->rdma.rdma_va =
- be64_to_cpu(pf_eqe->rdma.rdma_va);
- mlx5_core_dbg(dev,
- "PAGE_FAULT: type:0x%x, token: 0x%06x, r_key: 0x%08x\n",
- pfault->type, pfault->token,
- pfault->rdma.r_key);
- mlx5_core_dbg(dev,
- "PAGE_FAULT: rdma_op_len: 0x%08x, rdma_va: 0x%016llx\n",
- pfault->rdma.rdma_op_len,
- pfault->rdma.rdma_va);
- break;
-
- case MLX5_PFAULT_SUBTYPE_WQE:
- /* WQE based event */
- pfault->type =
- (be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24) & 0x7;
- pfault->token =
- be32_to_cpu(pf_eqe->wqe.token);
- pfault->wqe.wq_num =
- be32_to_cpu(pf_eqe->wqe.pftype_wq) &
- MLX5_24BIT_MASK;
- pfault->wqe.wqe_index =
- be16_to_cpu(pf_eqe->wqe.wqe_index);
- pfault->wqe.packet_size =
- be16_to_cpu(pf_eqe->wqe.packet_length);
- mlx5_core_dbg(dev,
- "PAGE_FAULT: type:0x%x, token: 0x%06x, wq_num: 0x%06x, wqe_index: 0x%04x\n",
- pfault->type, pfault->token,
- pfault->wqe.wq_num,
- pfault->wqe.wqe_index);
- break;
-
- default:
- mlx5_core_warn(dev,
- "Unsupported page fault event sub-type: 0x%02hhx\n",
- eqe->sub_type);
- /* Unsupported page faults should still be
- * resolved by the page fault handler
- */
+ /* Assume (eqe->type) is always MLX5_EVENT_TYPE_COMP */
+ cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
+
+ cq = mlx5_eq_cq_get(eq, cqn);
+ if (likely(cq)) {
+ ++cq->arm_sn;
+ cq->comp(cq);
+ mlx5_cq_put(cq);
+ } else {
+ mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
}
- pfault->eq = eq;
- INIT_WORK(&pfault->work, eqe_pf_action);
- queue_work(eq->pf_ctx.wq, &pfault->work);
-
++eq->cons_index;
++set_ci;
+ /* The HCA will think the queue has overflowed if we
+ * don't tell it we've been processing events. We
+ * create our EQs with MLX5_NUM_SPARE_EQE extra
+ * entries, so we must update our consumer index at
+ * least that often.
+ */
if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
eq_update_ci(eq, 0);
set_ci = 0;
}
eq_update_ci(eq, 1);
-}
-static irqreturn_t mlx5_eq_pf_int(int irq, void *eq_ptr)
-{
- struct mlx5_eq *eq = eq_ptr;
- unsigned long flags;
-
- if (spin_trylock_irqsave(&eq->pf_ctx.lock, flags)) {
- eq_pf_process(eq);
- spin_unlock_irqrestore(&eq->pf_ctx.lock, flags);
- } else {
- schedule_work(&eq->pf_ctx.work);
- }
+ if (cqn != -1)
+ tasklet_schedule(&eq_comp->tasklet_ctx.task);
return IRQ_HANDLED;
}
-/* mempool_refill() was proposed but unfortunately wasn't accepted
- * http://lkml.iu.edu/hypermail/linux/kernel/1512.1/05073.html
- * Chip workaround.
+/* Some architectures don't latch interrupts when they are disabled, so using
+ * mlx5_eq_poll_irq_disabled could end up losing interrupts while trying to
+ * avoid losing them. It is not recommended to use it, unless this is the last
+ * resort.
*/
-static void mempool_refill(mempool_t *pool)
-{
- while (pool->curr_nr < pool->min_nr)
- mempool_free(mempool_alloc(pool, GFP_KERNEL), pool);
-}
-
-static void eq_pf_action(struct work_struct *work)
-{
- struct mlx5_eq *eq = container_of(work, struct mlx5_eq, pf_ctx.work);
-
- mempool_refill(eq->pf_ctx.pool);
-
- spin_lock_irq(&eq->pf_ctx.lock);
- eq_pf_process(eq);
- spin_unlock_irq(&eq->pf_ctx.lock);
-}
-
-static int init_pf_ctx(struct mlx5_eq_pagefault *pf_ctx, const char *name)
-{
- spin_lock_init(&pf_ctx->lock);
- INIT_WORK(&pf_ctx->work, eq_pf_action);
-
- pf_ctx->wq = alloc_ordered_workqueue(name,
- WQ_MEM_RECLAIM);
- if (!pf_ctx->wq)
- return -ENOMEM;
-
- pf_ctx->pool = mempool_create_kmalloc_pool
- (MLX5_NUM_PF_DRAIN, sizeof(struct mlx5_pagefault));
- if (!pf_ctx->pool)
- goto err_wq;
-
- return 0;
-err_wq:
- destroy_workqueue(pf_ctx->wq);
- return -ENOMEM;
-}
-
-int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
- u32 wq_num, u8 type, int error)
-{
- u32 out[MLX5_ST_SZ_DW(page_fault_resume_out)] = {0};
- u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)] = {0};
-
- MLX5_SET(page_fault_resume_in, in, opcode,
- MLX5_CMD_OP_PAGE_FAULT_RESUME);
- MLX5_SET(page_fault_resume_in, in, error, !!error);
- MLX5_SET(page_fault_resume_in, in, page_fault_type, type);
- MLX5_SET(page_fault_resume_in, in, wq_number, wq_num);
- MLX5_SET(page_fault_resume_in, in, token, token);
-
- return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
-#endif
-
-static void general_event_handler(struct mlx5_core_dev *dev,
- struct mlx5_eqe *eqe)
-{
- switch (eqe->sub_type) {
- case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
- if (dev->event)
- dev->event(dev, MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, 0);
- break;
- default:
- mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
- eqe->sub_type);
- }
-}
-
-static void mlx5_temp_warning_event(struct mlx5_core_dev *dev,
- struct mlx5_eqe *eqe)
-{
- u64 value_lsb;
- u64 value_msb;
-
- value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
- value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
-
- mlx5_core_warn(dev,
- "High temperature on sensors with bit set %llx %llx",
- value_msb, value_lsb);
-}
-
-/* caller must eventually call mlx5_cq_put on the returned cq */
-static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
-{
- struct mlx5_cq_table *table = &eq->cq_table;
- struct mlx5_core_cq *cq = NULL;
-
- spin_lock(&table->lock);
- cq = radix_tree_lookup(&table->tree, cqn);
- if (likely(cq))
- mlx5_cq_hold(cq);
- spin_unlock(&table->lock);
-
- return cq;
-}
-
-static void mlx5_eq_cq_completion(struct mlx5_eq *eq, u32 cqn)
-{
- struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn);
-
- if (unlikely(!cq)) {
- mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
- return;
- }
-
- ++cq->arm_sn;
-
- cq->comp(cq);
-
- mlx5_cq_put(cq);
-}
-
-static void mlx5_eq_cq_event(struct mlx5_eq *eq, u32 cqn, int event_type)
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq)
{
- struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn);
-
- if (unlikely(!cq)) {
- mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
- return;
- }
+ u32 count_eqe;
- cq->event(cq, event_type);
+ disable_irq(eq->core.irqn);
+ count_eqe = eq->core.cons_index;
+ mlx5_eq_comp_int(eq->core.irqn, eq);
+ count_eqe = eq->core.cons_index - count_eqe;
+ enable_irq(eq->core.irqn);
- mlx5_cq_put(cq);
+ return count_eqe;
}
-static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
+static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
{
struct mlx5_eq *eq = eq_ptr;
- struct mlx5_core_dev *dev = eq->dev;
+ struct mlx5_eq_table *eqt;
+ struct mlx5_core_dev *dev;
struct mlx5_eqe *eqe;
int set_ci = 0;
- u32 cqn = -1;
- u32 rsn;
- u8 port;
+
+ dev = eq->dev;
+ eqt = dev->priv.eq_table;
while ((eqe = next_eqe_sw(eq))) {
/*
*/
dma_rmb();
- mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n",
- eq->eqn, eqe_type_str(eqe->type));
- switch (eqe->type) {
- case MLX5_EVENT_TYPE_COMP:
- cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
- mlx5_eq_cq_completion(eq, cqn);
- break;
- case MLX5_EVENT_TYPE_DCT_DRAINED:
- rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
- rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
- mlx5_rsc_event(dev, rsn, eqe->type);
- break;
- case MLX5_EVENT_TYPE_PATH_MIG:
- case MLX5_EVENT_TYPE_COMM_EST:
- case MLX5_EVENT_TYPE_SQ_DRAINED:
- case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
- case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
- case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
- case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
- case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
- rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
- rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
- mlx5_core_dbg(dev, "event %s(%d) arrived on resource 0x%x\n",
- eqe_type_str(eqe->type), eqe->type, rsn);
- mlx5_rsc_event(dev, rsn, eqe->type);
- break;
-
- case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
- case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
- rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
- mlx5_core_dbg(dev, "SRQ event %s(%d): srqn 0x%x\n",
- eqe_type_str(eqe->type), eqe->type, rsn);
- mlx5_srq_event(dev, rsn, eqe->type);
- break;
-
- case MLX5_EVENT_TYPE_CMD:
- mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
- break;
+ if (likely(eqe->type < MLX5_EVENT_TYPE_MAX))
+ atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe);
+ else
+ mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type);
- case MLX5_EVENT_TYPE_PORT_CHANGE:
- port = (eqe->data.port.port >> 4) & 0xf;
- switch (eqe->sub_type) {
- case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
- case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
- case MLX5_PORT_CHANGE_SUBTYPE_LID:
- case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
- case MLX5_PORT_CHANGE_SUBTYPE_GUID:
- case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
- case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
- if (dev->event)
- dev->event(dev, port_subtype_event(eqe->sub_type),
- (unsigned long)port);
- break;
- default:
- mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
- port, eqe->sub_type);
- }
- break;
- case MLX5_EVENT_TYPE_CQ_ERROR:
- cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
- mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
- cqn, eqe->data.cq_err.syndrome);
- mlx5_eq_cq_event(eq, cqn, eqe->type);
- break;
-
- case MLX5_EVENT_TYPE_PAGE_REQUEST:
- {
- u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
- s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages);
-
- mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
- func_id, npages);
- mlx5_core_req_pages_handler(dev, func_id, npages);
- }
- break;
-
- case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
- mlx5_eswitch_vport_event(dev->priv.eswitch, eqe);
- break;
-
- case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
- mlx5_port_module_event(dev, eqe);
- break;
-
- case MLX5_EVENT_TYPE_PPS_EVENT:
- mlx5_pps_event(dev, eqe);
- break;
-
- case MLX5_EVENT_TYPE_FPGA_ERROR:
- case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
- mlx5_fpga_event(dev, eqe->type, &eqe->data.raw);
- break;
-
- case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
- mlx5_temp_warning_event(dev, eqe);
- break;
-
- case MLX5_EVENT_TYPE_GENERAL_EVENT:
- general_event_handler(dev, eqe);
- break;
-
- case MLX5_EVENT_TYPE_DEVICE_TRACER:
- mlx5_fw_tracer_event(dev, eqe);
- break;
-
- default:
- mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
- eqe->type, eq->eqn);
- break;
- }
+ atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe);
++eq->cons_index;
++set_ci;
eq_update_ci(eq, 1);
- if (cqn != -1)
- tasklet_schedule(&eq->tasklet_ctx.task);
-
return IRQ_HANDLED;
}
-/* Some architectures don't latch interrupts when they are disabled, so using
- * mlx5_eq_poll_irq_disabled could end up losing interrupts while trying to
- * avoid losing them. It is not recommended to use it, unless this is the last
- * resort.
- */
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq)
-{
- u32 count_eqe;
-
- disable_irq(eq->irqn);
- count_eqe = eq->cons_index;
- mlx5_eq_int(eq->irqn, eq);
- count_eqe = eq->cons_index - count_eqe;
- enable_irq(eq->irqn);
-
- return count_eqe;
-}
-
static void init_eq_buf(struct mlx5_eq *eq)
{
struct mlx5_eqe *eqe;
}
}
-int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
- int nent, u64 mask, const char *name,
- enum mlx5_eq_type type)
+static int
+create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, const char *name,
+ struct mlx5_eq_param *param)
{
+ struct mlx5_eq_table *eq_table = dev->priv.eq_table;
struct mlx5_cq_table *cq_table = &eq->cq_table;
u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
struct mlx5_priv *priv = &dev->priv;
- irq_handler_t handler;
+ u8 vecidx = param->index;
__be64 *pas;
void *eqc;
int inlen;
u32 *in;
int err;
+ if (eq_table->irq_info[vecidx].context)
+ return -EEXIST;
+
/* Init CQ table */
memset(cq_table, 0, sizeof(*cq_table));
spin_lock_init(&cq_table->lock);
INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
- eq->type = type;
- eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
+ eq->nent = roundup_pow_of_two(param->nent + MLX5_NUM_SPARE_EQE);
eq->cons_index = 0;
err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf);
if (err)
return err;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- if (type == MLX5_EQ_TYPE_PF)
- handler = mlx5_eq_pf_int;
- else
-#endif
- handler = mlx5_eq_int;
-
init_eq_buf(eq);
inlen = MLX5_ST_SZ_BYTES(create_eq_in) +
mlx5_fill_page_array(&eq->buf, pas);
MLX5_SET(create_eq_in, in, opcode, MLX5_CMD_OP_CREATE_EQ);
- MLX5_SET64(create_eq_in, in, event_bitmask, mask);
+ MLX5_SET64(create_eq_in, in, event_bitmask, param->mask);
eqc = MLX5_ADDR_OF(create_eq_in, in, eq_context_entry);
MLX5_SET(eqc, eqc, log_eq_size, ilog2(eq->nent));
if (err)
goto err_in;
- snprintf(priv->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
+ snprintf(eq_table->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
name, pci_name(dev->pdev));
+ eq_table->irq_info[vecidx].context = param->context;
+ eq->vecidx = vecidx;
eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
eq->irqn = pci_irq_vector(dev->pdev, vecidx);
eq->dev = dev;
eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
- err = request_irq(eq->irqn, handler, 0,
- priv->irq_info[vecidx].name, eq);
+ err = request_irq(eq->irqn, param->handler, 0,
+ eq_table->irq_info[vecidx].name, param->context);
if (err)
goto err_eq;
if (err)
goto err_irq;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- if (type == MLX5_EQ_TYPE_PF) {
- err = init_pf_ctx(&eq->pf_ctx, name);
- if (err)
- goto err_irq;
- } else
-#endif
- {
- INIT_LIST_HEAD(&eq->tasklet_ctx.list);
- INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
- spin_lock_init(&eq->tasklet_ctx.lock);
- tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
- (unsigned long)&eq->tasklet_ctx);
- }
-
/* EQs are created in ARMED state
*/
eq_update_ci(eq, 1);
return err;
}
-int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
{
+ struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+ struct mlx5_irq_info *irq_info;
int err;
+ irq_info = &eq_table->irq_info[eq->vecidx];
+
mlx5_debug_eq_remove(dev, eq);
- free_irq(eq->irqn, eq);
+
+ free_irq(eq->irqn, irq_info->context);
+ irq_info->context = NULL;
+
err = mlx5_cmd_destroy_eq(dev, eq->eqn);
if (err)
mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n",
eq->eqn);
synchronize_irq(eq->irqn);
- if (eq->type == MLX5_EQ_TYPE_COMP) {
- tasklet_disable(&eq->tasklet_ctx.task);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- } else if (eq->type == MLX5_EQ_TYPE_PF) {
- cancel_work_sync(&eq->pf_ctx.work);
- destroy_workqueue(eq->pf_ctx.wq);
- mempool_destroy(eq->pf_ctx.pool);
-#endif
- }
mlx5_buf_free(dev, &eq->buf);
return err;
return 0;
}
-int mlx5_eq_init(struct mlx5_core_dev *dev)
+int mlx5_eq_table_init(struct mlx5_core_dev *dev)
{
- int err;
+ struct mlx5_eq_table *eq_table;
+ int i, err;
- spin_lock_init(&dev->priv.eq_table.lock);
+ eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL);
+ if (!eq_table)
+ return -ENOMEM;
+
+ dev->priv.eq_table = eq_table;
err = mlx5_eq_debugfs_init(dev);
+ if (err)
+ goto kvfree_eq_table;
+
+ mutex_init(&eq_table->lock);
+ for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++)
+ ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
+ return 0;
+
+kvfree_eq_table:
+ kvfree(eq_table);
+ dev->priv.eq_table = NULL;
return err;
}
-void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
+void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
{
mlx5_eq_debugfs_cleanup(dev);
+ kvfree(dev->priv.eq_table);
}
-int mlx5_start_eqs(struct mlx5_core_dev *dev)
+/* Async EQs */
+
+static int create_async_eq(struct mlx5_core_dev *dev, const char *name,
+ struct mlx5_eq *eq, struct mlx5_eq_param *param)
{
- struct mlx5_eq_table *table = &dev->priv.eq_table;
- u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
+ struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+ int err;
+
+ mutex_lock(&eq_table->lock);
+ if (param->index >= MLX5_EQ_MAX_ASYNC_EQS) {
+ err = -ENOSPC;
+ goto unlock;
+ }
+
+ err = create_map_eq(dev, eq, name, param);
+unlock:
+ mutex_unlock(&eq_table->lock);
+ return err;
+}
+
+static int destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+{
+ struct mlx5_eq_table *eq_table = dev->priv.eq_table;
int err;
+ mutex_lock(&eq_table->lock);
+ err = destroy_unmap_eq(dev, eq);
+ mutex_unlock(&eq_table->lock);
+ return err;
+}
+
+static int cq_err_event_notifier(struct notifier_block *nb,
+ unsigned long type, void *data)
+{
+ struct mlx5_eq_table *eqt;
+ struct mlx5_core_cq *cq;
+ struct mlx5_eqe *eqe;
+ struct mlx5_eq *eq;
+ u32 cqn;
+
+ /* type == MLX5_EVENT_TYPE_CQ_ERROR */
+
+ eqt = mlx5_nb_cof(nb, struct mlx5_eq_table, cq_err_nb);
+ eq = &eqt->async_eq;
+ eqe = data;
+
+ cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
+ mlx5_core_warn(eq->dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
+ cqn, eqe->data.cq_err.syndrome);
+
+ cq = mlx5_eq_cq_get(eq, cqn);
+ if (unlikely(!cq)) {
+ mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
+ return NOTIFY_OK;
+ }
+
+ cq->event(cq, type);
+
+ mlx5_cq_put(cq);
+
+ return NOTIFY_OK;
+}
+
+static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
+{
+ u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
+
if (MLX5_VPORT_MANAGER(dev))
async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
- err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
- MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
- "mlx5_cmd_eq", MLX5_EQ_TYPE_ASYNC);
+ if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters))
+ async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER);
+
+ return async_event_mask;
+}
+
+static int create_async_eqs(struct mlx5_core_dev *dev)
+{
+ struct mlx5_eq_table *table = dev->priv.eq_table;
+ struct mlx5_eq_param param = {};
+ int err;
+
+ MLX5_NB_INIT(&table->cq_err_nb, cq_err_event_notifier, CQ_ERROR);
+ mlx5_eq_notifier_register(dev, &table->cq_err_nb);
+
+ param = (struct mlx5_eq_param) {
+ .index = MLX5_EQ_CMD_IDX,
+ .mask = 1ull << MLX5_EVENT_TYPE_CMD,
+ .nent = MLX5_NUM_CMD_EQE,
+ .context = &table->cmd_eq,
+ .handler = mlx5_eq_async_int,
+ };
+ err = create_async_eq(dev, "mlx5_cmd_eq", &table->cmd_eq, ¶m);
if (err) {
mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
- return err;
+ goto err0;
}
mlx5_cmd_use_events(dev);
- err = mlx5_create_map_eq(dev, &table->async_eq, MLX5_EQ_VEC_ASYNC,
- MLX5_NUM_ASYNC_EQE, async_event_mask,
- "mlx5_async_eq", MLX5_EQ_TYPE_ASYNC);
+ param = (struct mlx5_eq_param) {
+ .index = MLX5_EQ_ASYNC_IDX,
+ .mask = gather_async_events_mask(dev),
+ .nent = MLX5_NUM_ASYNC_EQE,
+ .context = &table->async_eq,
+ .handler = mlx5_eq_async_int,
+ };
+ err = create_async_eq(dev, "mlx5_async_eq", &table->async_eq, ¶m);
if (err) {
mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
goto err1;
}
- err = mlx5_create_map_eq(dev, &table->pages_eq,
- MLX5_EQ_VEC_PAGES,
- /* TODO: sriov max_vf + */ 1,
- 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq",
- MLX5_EQ_TYPE_ASYNC);
+ param = (struct mlx5_eq_param) {
+ .index = MLX5_EQ_PAGEREQ_IDX,
+ .mask = 1 << MLX5_EVENT_TYPE_PAGE_REQUEST,
+ .nent = /* TODO: sriov max_vf + */ 1,
+ .context = &table->pages_eq,
+ .handler = mlx5_eq_async_int,
+ };
+ err = create_async_eq(dev, "mlx5_pages_eq", &table->pages_eq, ¶m);
if (err) {
mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
goto err2;
}
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- if (MLX5_CAP_GEN(dev, pg)) {
- err = mlx5_create_map_eq(dev, &table->pfault_eq,
- MLX5_EQ_VEC_PFAULT,
- MLX5_NUM_ASYNC_EQE,
- 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
- "mlx5_page_fault_eq",
- MLX5_EQ_TYPE_PF);
- if (err) {
- mlx5_core_warn(dev, "failed to create page fault EQ %d\n",
- err);
- goto err3;
- }
- }
-
- return err;
-err3:
- mlx5_destroy_unmap_eq(dev, &table->pages_eq);
-#else
return err;
-#endif
err2:
- mlx5_destroy_unmap_eq(dev, &table->async_eq);
+ destroy_async_eq(dev, &table->async_eq);
err1:
mlx5_cmd_use_polling(dev);
- mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
+ destroy_async_eq(dev, &table->cmd_eq);
+err0:
+ mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
return err;
}
-void mlx5_stop_eqs(struct mlx5_core_dev *dev)
+static void destroy_async_eqs(struct mlx5_core_dev *dev)
{
- struct mlx5_eq_table *table = &dev->priv.eq_table;
+ struct mlx5_eq_table *table = dev->priv.eq_table;
int err;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- if (MLX5_CAP_GEN(dev, pg)) {
- err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq);
- if (err)
- mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n",
- err);
- }
-#endif
-
- err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
+ err = destroy_async_eq(dev, &table->pages_eq);
if (err)
mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
err);
- err = mlx5_destroy_unmap_eq(dev, &table->async_eq);
+ err = destroy_async_eq(dev, &table->async_eq);
if (err)
mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
err);
+
mlx5_cmd_use_polling(dev);
- err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
+ err = destroy_async_eq(dev, &table->cmd_eq);
if (err)
mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
err);
+
+ mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
}
-int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
- u32 *out, int outlen)
+struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev)
{
- u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {0};
+ return &dev->priv.eq_table->async_eq;
+}
- MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
- MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
- return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev)
+{
+ synchronize_irq(dev->priv.eq_table->async_eq.irqn);
+}
+
+void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev)
+{
+ synchronize_irq(dev->priv.eq_table->cmd_eq.irqn);
+}
+
+/* Generic EQ API for mlx5_core consumers
+ * Needed For RDMA ODP EQ for now
+ */
+struct mlx5_eq *
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+ struct mlx5_eq_param *param)
+{
+ struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL);
+ int err;
+
+ if (!eq)
+ return ERR_PTR(-ENOMEM);
+
+ err = create_async_eq(dev, name, eq, param);
+ if (err) {
+ kvfree(eq);
+ eq = ERR_PTR(err);
+ }
+
+ return eq;
+}
+EXPORT_SYMBOL(mlx5_eq_create_generic);
+
+int mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+{
+ int err;
+
+ if (IS_ERR(eq))
+ return -EINVAL;
+
+ err = destroy_async_eq(dev, eq);
+ if (err)
+ goto out;
+
+ kvfree(eq);
+out:
+ return err;
+}
+EXPORT_SYMBOL(mlx5_eq_destroy_generic);
+
+struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc)
+{
+ u32 ci = eq->cons_index + cc;
+ struct mlx5_eqe *eqe;
+
+ eqe = get_eqe(eq, ci & (eq->nent - 1));
+ eqe = ((eqe->owner & 1) ^ !!(ci & eq->nent)) ? NULL : eqe;
+ /* Make sure we read EQ entry contents after we've
+ * checked the ownership bit.
+ */
+ if (eqe)
+ dma_rmb();
+
+ return eqe;
+}
+EXPORT_SYMBOL(mlx5_eq_get_eqe);
+
+void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm)
+{
+ __be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
+ u32 val;
+
+ eq->cons_index += cc;
+ val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
+
+ __raw_writel((__force u32)cpu_to_be32(val), addr);
+ /* We still want ordering, just not swabbing, so add a barrier */
+ mb();
+}
+EXPORT_SYMBOL(mlx5_eq_update_ci);
+
+/* Completion EQs */
+
+static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+ struct mlx5_priv *priv = &mdev->priv;
+ int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+ int irq = pci_irq_vector(mdev->pdev, vecidx);
+ struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
+
+ if (!zalloc_cpumask_var(&irq_info->mask, GFP_KERNEL)) {
+ mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+ return -ENOMEM;
+ }
+
+ cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
+ irq_info->mask);
+
+ if (IS_ENABLED(CONFIG_SMP) &&
+ irq_set_affinity_hint(irq, irq_info->mask))
+ mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+
+ return 0;
+}
+
+static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+ int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+ struct mlx5_priv *priv = &mdev->priv;
+ int irq = pci_irq_vector(mdev->pdev, vecidx);
+ struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
+
+ irq_set_affinity_hint(irq, NULL);
+ free_cpumask_var(irq_info->mask);
+}
+
+static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
+{
+ int err;
+ int i;
+
+ for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++) {
+ err = set_comp_irq_affinity_hint(mdev, i);
+ if (err)
+ goto err_out;
+ }
+
+ return 0;
+
+err_out:
+ for (i--; i >= 0; i--)
+ clear_comp_irq_affinity_hint(mdev, i);
+
+ return err;
+}
+
+static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
+{
+ int i;
+
+ for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++)
+ clear_comp_irq_affinity_hint(mdev, i);
+}
+
+static void destroy_comp_eqs(struct mlx5_core_dev *dev)
+{
+ struct mlx5_eq_table *table = dev->priv.eq_table;
+ struct mlx5_eq_comp *eq, *n;
+
+ clear_comp_irqs_affinity_hints(dev);
+
+#ifdef CONFIG_RFS_ACCEL
+ if (table->rmap) {
+ free_irq_cpu_rmap(table->rmap);
+ table->rmap = NULL;
+ }
+#endif
+ list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+ list_del(&eq->list);
+ if (destroy_unmap_eq(dev, &eq->core))
+ mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
+ eq->core.eqn);
+ tasklet_disable(&eq->tasklet_ctx.task);
+ kfree(eq);
+ }
+}
+
+static int create_comp_eqs(struct mlx5_core_dev *dev)
+{
+ struct mlx5_eq_table *table = dev->priv.eq_table;
+ char name[MLX5_MAX_IRQ_NAME];
+ struct mlx5_eq_comp *eq;
+ int ncomp_vec;
+ int nent;
+ int err;
+ int i;
+
+ INIT_LIST_HEAD(&table->comp_eqs_list);
+ ncomp_vec = table->num_comp_vectors;
+ nent = MLX5_COMP_EQ_SIZE;
+#ifdef CONFIG_RFS_ACCEL
+ table->rmap = alloc_irq_cpu_rmap(ncomp_vec);
+ if (!table->rmap)
+ return -ENOMEM;
+#endif
+ for (i = 0; i < ncomp_vec; i++) {
+ int vecidx = i + MLX5_EQ_VEC_COMP_BASE;
+ struct mlx5_eq_param param = {};
+
+ eq = kzalloc(sizeof(*eq), GFP_KERNEL);
+ if (!eq) {
+ err = -ENOMEM;
+ goto clean;
+ }
+
+ INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+ INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+ spin_lock_init(&eq->tasklet_ctx.lock);
+ tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
+ (unsigned long)&eq->tasklet_ctx);
+
+#ifdef CONFIG_RFS_ACCEL
+ irq_cpu_rmap_add(table->rmap, pci_irq_vector(dev->pdev, vecidx));
+#endif
+ snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
+ param = (struct mlx5_eq_param) {
+ .index = vecidx,
+ .mask = 0,
+ .nent = nent,
+ .context = &eq->core,
+ .handler = mlx5_eq_comp_int
+ };
+ err = create_map_eq(dev, &eq->core, name, ¶m);
+ if (err) {
+ kfree(eq);
+ goto clean;
+ }
+ mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
+ /* add tail, to keep the list ordered, for mlx5_vector2eqn to work */
+ list_add_tail(&eq->list, &table->comp_eqs_list);
+ }
+
+ err = set_comp_irq_affinity_hints(dev);
+ if (err) {
+ mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
+ goto clean;
+ }
+
+ return 0;
+
+clean:
+ destroy_comp_eqs(dev);
+ return err;
+}
+
+int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
+ unsigned int *irqn)
+{
+ struct mlx5_eq_table *table = dev->priv.eq_table;
+ struct mlx5_eq_comp *eq, *n;
+ int err = -ENOENT;
+ int i = 0;
+
+ list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+ if (i++ == vector) {
+ *eqn = eq->core.eqn;
+ *irqn = eq->core.irqn;
+ err = 0;
+ break;
+ }
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(mlx5_vector2eqn);
+
+unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
+{
+ return dev->priv.eq_table->num_comp_vectors;
+}
+EXPORT_SYMBOL(mlx5_comp_vectors_count);
+
+struct cpumask *
+mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
+{
+ /* TODO: consider irq_get_affinity_mask(irq) */
+ return dev->priv.eq_table->irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
+}
+EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask);
+
+struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+ return dev->priv.eq_table->rmap;
+#else
+ return NULL;
+#endif
+}
+
+struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
+{
+ struct mlx5_eq_table *table = dev->priv.eq_table;
+ struct mlx5_eq_comp *eq;
+
+ list_for_each_entry(eq, &table->comp_eqs_list, list) {
+ if (eq->core.eqn == eqn)
+ return eq;
+ }
+
+ return ERR_PTR(-ENOENT);
}
/* This function should only be called after mlx5_cmd_force_teardown_hca */
void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
{
- struct mlx5_eq_table *table = &dev->priv.eq_table;
- struct mlx5_eq *eq;
+ struct mlx5_eq_table *table = dev->priv.eq_table;
+ int i, max_eqs;
+
+ clear_comp_irqs_affinity_hints(dev);
#ifdef CONFIG_RFS_ACCEL
- if (dev->rmap) {
- free_irq_cpu_rmap(dev->rmap);
- dev->rmap = NULL;
+ if (table->rmap) {
+ free_irq_cpu_rmap(table->rmap);
+ table->rmap = NULL;
}
#endif
- list_for_each_entry(eq, &table->comp_eqs_list, list)
- free_irq(eq->irqn, eq);
-
- free_irq(table->pages_eq.irqn, &table->pages_eq);
- free_irq(table->async_eq.irqn, &table->async_eq);
- free_irq(table->cmd_eq.irqn, &table->cmd_eq);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- if (MLX5_CAP_GEN(dev, pg))
- free_irq(table->pfault_eq.irqn, &table->pfault_eq);
-#endif
+
+ mutex_lock(&table->lock); /* sync with create/destroy_async_eq */
+ max_eqs = table->num_comp_vectors + MLX5_EQ_VEC_COMP_BASE;
+ for (i = max_eqs - 1; i >= 0; i--) {
+ if (!table->irq_info[i].context)
+ continue;
+ free_irq(pci_irq_vector(dev->pdev, i), table->irq_info[i].context);
+ table->irq_info[i].context = NULL;
+ }
+ mutex_unlock(&table->lock);
+ pci_free_irq_vectors(dev->pdev);
+}
+
+static int alloc_irq_vectors(struct mlx5_core_dev *dev)
+{
+ struct mlx5_priv *priv = &dev->priv;
+ struct mlx5_eq_table *table = priv->eq_table;
+ int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+ MLX5_CAP_GEN(dev, max_num_eqs) :
+ 1 << MLX5_CAP_GEN(dev, log_max_eq);
+ int nvec;
+ int err;
+
+ nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+ MLX5_EQ_VEC_COMP_BASE;
+ nvec = min_t(int, nvec, num_eqs);
+ if (nvec <= MLX5_EQ_VEC_COMP_BASE)
+ return -ENOMEM;
+
+ table->irq_info = kcalloc(nvec, sizeof(*table->irq_info), GFP_KERNEL);
+ if (!table->irq_info)
+ return -ENOMEM;
+
+ nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1,
+ nvec, PCI_IRQ_MSIX);
+ if (nvec < 0) {
+ err = nvec;
+ goto err_free_irq_info;
+ }
+
+ table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
+
+ return 0;
+
+err_free_irq_info:
+ kfree(table->irq_info);
+ return err;
+}
+
+static void free_irq_vectors(struct mlx5_core_dev *dev)
+{
+ struct mlx5_priv *priv = &dev->priv;
+
pci_free_irq_vectors(dev->pdev);
+ kfree(priv->eq_table->irq_info);
+}
+
+int mlx5_eq_table_create(struct mlx5_core_dev *dev)
+{
+ int err;
+
+ err = alloc_irq_vectors(dev);
+ if (err) {
+ mlx5_core_err(dev, "alloc irq vectors failed\n");
+ return err;
+ }
+
+ err = create_async_eqs(dev);
+ if (err) {
+ mlx5_core_err(dev, "Failed to create async EQs\n");
+ goto err_async_eqs;
+ }
+
+ err = create_comp_eqs(dev);
+ if (err) {
+ mlx5_core_err(dev, "Failed to create completion EQs\n");
+ goto err_comp_eqs;
+ }
+
+ return 0;
+err_comp_eqs:
+ destroy_async_eqs(dev);
+err_async_eqs:
+ free_irq_vectors(dev);
+ return err;
+}
+
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev)
+{
+ destroy_comp_eqs(dev);
+ destroy_async_eqs(dev);
+ free_irq_vectors(dev);
+}
+
+int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
+{
+ struct mlx5_eq_table *eqt = dev->priv.eq_table;
+
+ if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
+ return -EINVAL;
+
+ return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb);
+}
+
+int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
+{
+ struct mlx5_eq_table *eqt = dev->priv.eq_table;
+
+ if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
+ return -EINVAL;
+
+ return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb);
}
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
#include "eswitch.h"
#include "fs_core.h"
+#include "lib/eq.h"
#define UPLINK_VPORT 0xFFFF
/* Mark this vport as disabled to discard new events */
vport->enabled = false;
- synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
/* Wait for current already scheduled events to complete */
flush_workqueue(esw->work_queue);
/* Disable events from this vport */
mutex_unlock(&esw->state_lock);
}
+static int eswitch_vport_event(struct notifier_block *nb,
+ unsigned long type, void *data)
+{
+ struct mlx5_eswitch *esw = mlx5_nb_cof(nb, struct mlx5_eswitch, nb);
+ struct mlx5_eqe *eqe = data;
+ struct mlx5_vport *vport;
+ u16 vport_num;
+
+ vport_num = be16_to_cpu(eqe->data.vport_change.vport_num);
+ vport = &esw->vports[vport_num];
+ if (vport->enabled)
+ queue_work(esw->work_queue, &vport->vport_change_handler);
+
+ return NOTIFY_OK;
+}
+
/* Public E-Switch API */
#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
-
int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
{
int err;
for (i = 0; i <= nvfs; i++)
esw_enable_vport(esw, i, enabled_events);
+ if (mode == SRIOV_LEGACY) {
+ MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+ mlx5_eq_notifier_register(esw->dev, &esw->nb);
+ }
+
esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
esw->enabled_vports);
return 0;
mc_promisc = &esw->mc_promisc;
nvports = esw->enabled_vports;
+ if (esw->mode == SRIOV_LEGACY)
+ mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+
for (i = 0; i < esw->total_vports; i++)
esw_disable_vport(esw, i);
kfree(esw);
}
-void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe)
-{
- struct mlx5_eqe_vport_change *vc_eqe = &eqe->data.vport_change;
- u16 vport_num = be16_to_cpu(vc_eqe->vport_num);
- struct mlx5_vport *vport;
-
- if (!esw) {
- pr_warn("MLX5 E-Switch: vport %d got an event while eswitch is not initialized\n",
- vport_num);
- return;
- }
-
- vport = &esw->vports[vport_num];
- if (vport->enabled)
- queue_work(esw->work_queue, &vport->vport_change_handler);
-}
-
/* Vport Administration */
#define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
struct mlx5_eswitch {
struct mlx5_core_dev *dev;
+ struct mlx5_nb nb;
struct mlx5_eswitch_fdb fdb_table;
struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE];
struct workqueue_struct *work_queue;
/* E-Switch API */
int mlx5_eswitch_init(struct mlx5_core_dev *dev);
void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
-void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe);
int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode);
void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw);
int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
/* eswitch API stubs */
static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
-static inline void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe) {}
static inline int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
dest[i].vport.num = attr->out_rep[j]->vport;
dest[i].vport.vhca_id =
MLX5_CAP_GEN(attr->out_mdev[j], vhca_id);
- dest[i].vport.vhca_id_valid =
- !!MLX5_CAP_ESW(esw->dev, merged_eswitch);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ dest[i].vport.flags |=
+ MLX5_FLOW_DEST_VPORT_VHCA_ID;
i++;
}
}
dest[i].vport.num = attr->out_rep[i]->vport;
dest[i].vport.vhca_id =
MLX5_CAP_GEN(attr->out_mdev[i], vhca_id);
- dest[i].vport.vhca_id_valid = !!MLX5_CAP_ESW(esw->dev, merged_eswitch);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
}
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
dest[i].ft = fwd_fdb,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include <linux/mlx5/driver.h>
+
+#include "mlx5_core.h"
+#include "lib/eq.h"
+#include "lib/mlx5.h"
+
+struct mlx5_event_nb {
+ struct mlx5_nb nb;
+ void *ctx;
+};
+
+/* General events handlers for the low level mlx5_core driver
+ *
+ * Other Major feature specific events such as
+ * clock/eswitch/fpga/FW trace and many others, are handled elsewhere, with
+ * separate notifiers callbacks, specifically by those mlx5 components.
+ */
+static int any_notifier(struct notifier_block *, unsigned long, void *);
+static int temp_warn(struct notifier_block *, unsigned long, void *);
+static int port_module(struct notifier_block *, unsigned long, void *);
+
+/* handler which forwards the event to events->nh, driver notifiers */
+static int forward_event(struct notifier_block *, unsigned long, void *);
+
+static struct mlx5_nb events_nbs_ref[] = {
+ /* Events to be proccessed by mlx5_core */
+ {.nb.notifier_call = any_notifier, .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
+ {.nb.notifier_call = temp_warn, .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
+ {.nb.notifier_call = port_module, .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+
+ /* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
+ /* QP/WQ resource events to forward */
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_DCT_DRAINED },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_PATH_MIG },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_COMM_EST },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_SQ_DRAINED },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_SRQ_LAST_WQE },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_WQ_CATAS_ERROR },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_PATH_MIG_FAILED },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_WQ_ACCESS_ERROR },
+ /* SRQ events */
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_SRQ_CATAS_ERROR },
+ {.nb.notifier_call = forward_event, .event_type = MLX5_EVENT_TYPE_SRQ_RQ_LIMIT },
+};
+
+struct mlx5_events {
+ struct mlx5_core_dev *dev;
+ struct mlx5_event_nb notifiers[ARRAY_SIZE(events_nbs_ref)];
+ /* driver notifier chain */
+ struct atomic_notifier_head nh;
+ /* port module events stats */
+ struct mlx5_pme_stats pme_stats;
+};
+
+static const char *eqe_type_str(u8 type)
+{
+ switch (type) {
+ case MLX5_EVENT_TYPE_COMP:
+ return "MLX5_EVENT_TYPE_COMP";
+ case MLX5_EVENT_TYPE_PATH_MIG:
+ return "MLX5_EVENT_TYPE_PATH_MIG";
+ case MLX5_EVENT_TYPE_COMM_EST:
+ return "MLX5_EVENT_TYPE_COMM_EST";
+ case MLX5_EVENT_TYPE_SQ_DRAINED:
+ return "MLX5_EVENT_TYPE_SQ_DRAINED";
+ case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+ return "MLX5_EVENT_TYPE_SRQ_LAST_WQE";
+ case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
+ return "MLX5_EVENT_TYPE_SRQ_RQ_LIMIT";
+ case MLX5_EVENT_TYPE_CQ_ERROR:
+ return "MLX5_EVENT_TYPE_CQ_ERROR";
+ case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+ return "MLX5_EVENT_TYPE_WQ_CATAS_ERROR";
+ case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+ return "MLX5_EVENT_TYPE_PATH_MIG_FAILED";
+ case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+ return "MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR";
+ case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+ return "MLX5_EVENT_TYPE_WQ_ACCESS_ERROR";
+ case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
+ return "MLX5_EVENT_TYPE_SRQ_CATAS_ERROR";
+ case MLX5_EVENT_TYPE_INTERNAL_ERROR:
+ return "MLX5_EVENT_TYPE_INTERNAL_ERROR";
+ case MLX5_EVENT_TYPE_PORT_CHANGE:
+ return "MLX5_EVENT_TYPE_PORT_CHANGE";
+ case MLX5_EVENT_TYPE_GPIO_EVENT:
+ return "MLX5_EVENT_TYPE_GPIO_EVENT";
+ case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+ return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
+ case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
+ return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT";
+ case MLX5_EVENT_TYPE_REMOTE_CONFIG:
+ return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
+ case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
+ return "MLX5_EVENT_TYPE_DB_BF_CONGESTION";
+ case MLX5_EVENT_TYPE_STALL_EVENT:
+ return "MLX5_EVENT_TYPE_STALL_EVENT";
+ case MLX5_EVENT_TYPE_CMD:
+ return "MLX5_EVENT_TYPE_CMD";
+ case MLX5_EVENT_TYPE_PAGE_REQUEST:
+ return "MLX5_EVENT_TYPE_PAGE_REQUEST";
+ case MLX5_EVENT_TYPE_PAGE_FAULT:
+ return "MLX5_EVENT_TYPE_PAGE_FAULT";
+ case MLX5_EVENT_TYPE_PPS_EVENT:
+ return "MLX5_EVENT_TYPE_PPS_EVENT";
+ case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
+ return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
+ case MLX5_EVENT_TYPE_FPGA_ERROR:
+ return "MLX5_EVENT_TYPE_FPGA_ERROR";
+ case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
+ return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
+ case MLX5_EVENT_TYPE_GENERAL_EVENT:
+ return "MLX5_EVENT_TYPE_GENERAL_EVENT";
+ case MLX5_EVENT_TYPE_MONITOR_COUNTER:
+ return "MLX5_EVENT_TYPE_MONITOR_COUNTER";
+ case MLX5_EVENT_TYPE_DEVICE_TRACER:
+ return "MLX5_EVENT_TYPE_DEVICE_TRACER";
+ default:
+ return "Unrecognized event";
+ }
+}
+
+/* handles all FW events, type == eqe->type */
+static int any_notifier(struct notifier_block *nb,
+ unsigned long type, void *data)
+{
+ struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+ struct mlx5_events *events = event_nb->ctx;
+ struct mlx5_eqe *eqe = data;
+
+ mlx5_core_dbg(events->dev, "Async eqe type %s, subtype (%d)\n",
+ eqe_type_str(eqe->type), eqe->sub_type);
+ return NOTIFY_OK;
+}
+
+/* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */
+static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
+{
+ struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+ struct mlx5_events *events = event_nb->ctx;
+ struct mlx5_eqe *eqe = data;
+ u64 value_lsb;
+ u64 value_msb;
+
+ value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+ value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
+
+ mlx5_core_warn(events->dev,
+ "High temperature on sensors with bit set %llx %llx",
+ value_msb, value_lsb);
+
+ return NOTIFY_OK;
+}
+
+/* MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
+static const char *mlx5_pme_status_to_string(enum port_module_event_status_type status)
+{
+ switch (status) {
+ case MLX5_MODULE_STATUS_PLUGGED:
+ return "Cable plugged";
+ case MLX5_MODULE_STATUS_UNPLUGGED:
+ return "Cable unplugged";
+ case MLX5_MODULE_STATUS_ERROR:
+ return "Cable error";
+ case MLX5_MODULE_STATUS_DISABLED:
+ return "Cable disabled";
+ default:
+ return "Unknown status";
+ }
+}
+
+static const char *mlx5_pme_error_to_string(enum port_module_event_error_type error)
+{
+ switch (error) {
+ case MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED:
+ return "Power budget exceeded";
+ case MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX:
+ return "Long Range for non MLNX cable";
+ case MLX5_MODULE_EVENT_ERROR_BUS_STUCK:
+ return "Bus stuck (I2C or data shorted)";
+ case MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT:
+ return "No EEPROM/retry timeout";
+ case MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST:
+ return "Enforce part number list";
+ case MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER:
+ return "Unknown identifier";
+ case MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE:
+ return "High Temperature";
+ case MLX5_MODULE_EVENT_ERROR_BAD_CABLE:
+ return "Bad or shorted cable/module";
+ case MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED:
+ return "One or more network ports have been powered down due to insufficient/unadvertised power on the PCIe slot";
+ default:
+ return "Unknown error";
+ }
+}
+
+/* type == MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
+static int port_module(struct notifier_block *nb, unsigned long type, void *data)
+{
+ struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+ struct mlx5_events *events = event_nb->ctx;
+ struct mlx5_eqe *eqe = data;
+
+ enum port_module_event_status_type module_status;
+ enum port_module_event_error_type error_type;
+ struct mlx5_eqe_port_module *module_event_eqe;
+ const char *status_str, *error_str;
+ u8 module_num;
+
+ module_event_eqe = &eqe->data.port_module;
+ module_num = module_event_eqe->module;
+ module_status = module_event_eqe->module_status &
+ PORT_MODULE_EVENT_MODULE_STATUS_MASK;
+ error_type = module_event_eqe->error_type &
+ PORT_MODULE_EVENT_ERROR_TYPE_MASK;
+
+ if (module_status < MLX5_MODULE_STATUS_NUM)
+ events->pme_stats.status_counters[module_status]++;
+ status_str = mlx5_pme_status_to_string(module_status);
+
+ if (module_status == MLX5_MODULE_STATUS_ERROR) {
+ if (error_type < MLX5_MODULE_EVENT_ERROR_NUM)
+ events->pme_stats.error_counters[error_type]++;
+ error_str = mlx5_pme_error_to_string(error_type);
+ }
+
+ if (!printk_ratelimit())
+ return NOTIFY_OK;
+
+ if (module_status == MLX5_MODULE_STATUS_ERROR)
+ mlx5_core_err(events->dev,
+ "Port module event[error]: module %u, %s, %s\n",
+ module_num, status_str, error_str);
+ else
+ mlx5_core_info(events->dev,
+ "Port module event: module %u, %s\n",
+ module_num, status_str);
+
+ return NOTIFY_OK;
+}
+
+void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
+{
+ *stats = dev->priv.events->pme_stats;
+}
+
+/* forward event as is to registered interfaces (mlx5e/mlx5_ib) */
+static int forward_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+ struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+ struct mlx5_events *events = event_nb->ctx;
+ struct mlx5_eqe *eqe = data;
+
+ mlx5_core_dbg(events->dev, "Async eqe type %s, subtype (%d) forward to interfaces\n",
+ eqe_type_str(eqe->type), eqe->sub_type);
+ atomic_notifier_call_chain(&events->nh, event, data);
+ return NOTIFY_OK;
+}
+
+int mlx5_events_init(struct mlx5_core_dev *dev)
+{
+ struct mlx5_events *events = kzalloc(sizeof(*events), GFP_KERNEL);
+
+ if (!events)
+ return -ENOMEM;
+
+ ATOMIC_INIT_NOTIFIER_HEAD(&events->nh);
+ events->dev = dev;
+ dev->priv.events = events;
+ return 0;
+}
+
+void mlx5_events_cleanup(struct mlx5_core_dev *dev)
+{
+ kvfree(dev->priv.events);
+}
+
+void mlx5_events_start(struct mlx5_core_dev *dev)
+{
+ struct mlx5_events *events = dev->priv.events;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(events_nbs_ref); i++) {
+ events->notifiers[i].nb = events_nbs_ref[i];
+ events->notifiers[i].ctx = events;
+ mlx5_eq_notifier_register(dev, &events->notifiers[i].nb);
+ }
+}
+
+void mlx5_events_stop(struct mlx5_core_dev *dev)
+{
+ struct mlx5_events *events = dev->priv.events;
+ int i;
+
+ for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
+ mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
+}
+
+int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+ struct mlx5_events *events = dev->priv.events;
+
+ return atomic_notifier_chain_register(&events->nh, nb);
+}
+EXPORT_SYMBOL(mlx5_notifier_register);
+
+int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+ struct mlx5_events *events = dev->priv.events;
+
+ return atomic_notifier_chain_unregister(&events->nh, nb);
+}
+EXPORT_SYMBOL(mlx5_notifier_unregister);
+
+int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data)
+{
+ return atomic_notifier_call_chain(&events->nh, event, data);
+}
{
u8 opcode, status = 0;
- opcode = cqe->op_own >> 4;
+ opcode = get_cqe_opcode(cqe);
switch (opcode) {
case MLX5_CQE_REQ_ERR:
#include "mlx5_core.h"
#include "lib/mlx5.h"
+#include "lib/eq.h"
#include "fpga/core.h"
#include "fpga/conn.h"
return 0;
}
+static int mlx5_fpga_event(struct mlx5_fpga_device *, unsigned long, void *);
+
+static int fpga_err_event(struct notifier_block *nb, unsigned long event, void *eqe)
+{
+ struct mlx5_fpga_device *fdev = mlx5_nb_cof(nb, struct mlx5_fpga_device, fpga_err_nb);
+
+ return mlx5_fpga_event(fdev, event, eqe);
+}
+
+static int fpga_qp_err_event(struct notifier_block *nb, unsigned long event, void *eqe)
+{
+ struct mlx5_fpga_device *fdev = mlx5_nb_cof(nb, struct mlx5_fpga_device, fpga_qp_err_nb);
+
+ return mlx5_fpga_event(fdev, event, eqe);
+}
+
int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
{
struct mlx5_fpga_device *fdev = mdev->fpga;
if (err)
goto out;
+ MLX5_NB_INIT(&fdev->fpga_err_nb, fpga_err_event, FPGA_ERROR);
+ MLX5_NB_INIT(&fdev->fpga_qp_err_nb, fpga_qp_err_event, FPGA_QP_ERROR);
+ mlx5_eq_notifier_register(fdev->mdev, &fdev->fpga_err_nb);
+ mlx5_eq_notifier_register(fdev->mdev, &fdev->fpga_qp_err_nb);
+
err = mlx5_fpga_conn_device_init(fdev);
if (err)
goto err_rsvd_gid;
mlx5_fpga_conn_device_cleanup(fdev);
err_rsvd_gid:
+ mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_err_nb);
+ mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_qp_err_nb);
mlx5_core_unreserve_gids(mdev, max_num_qps);
out:
spin_lock_irqsave(&fdev->state_lock, flags);
}
mlx5_fpga_conn_device_cleanup(fdev);
+ mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_err_nb);
+ mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_qp_err_nb);
+
max_num_qps = MLX5_CAP_FPGA(mdev, shell_caps.max_num_qps);
mlx5_core_unreserve_gids(mdev, max_num_qps);
}
return "Unknown";
}
-void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
+static int mlx5_fpga_event(struct mlx5_fpga_device *fdev,
+ unsigned long event, void *eqe)
{
- struct mlx5_fpga_device *fdev = mdev->fpga;
+ void *data = ((struct mlx5_eqe *)eqe)->data.raw;
const char *event_name;
bool teardown = false;
unsigned long flags;
fpga_qpn = MLX5_GET(fpga_qp_error_event, data, fpga_qpn);
break;
default:
- mlx5_fpga_warn_ratelimited(fdev, "Unexpected event %u\n",
- event);
- return;
+ return NOTIFY_DONE;
}
spin_lock_irqsave(&fdev->state_lock, flags);
*/
if (teardown)
mlx5_trigger_health_work(fdev->mdev);
+
+ return NOTIFY_OK;
}
#ifdef CONFIG_MLX5_FPGA
+#include <linux/mlx5/eq.h>
+
+#include "lib/eq.h"
#include "fpga/cmd.h"
/* Represents an Innova device */
struct mlx5_fpga_device {
struct mlx5_core_dev *mdev;
+ struct mlx5_nb fpga_err_nb;
+ struct mlx5_nb fpga_qp_err_nb;
spinlock_t state_lock; /* Protects state transitions */
enum mlx5_fpga_status state;
enum mlx5_fpga_image last_admin_image;
void mlx5_fpga_cleanup(struct mlx5_core_dev *mdev);
int mlx5_fpga_device_start(struct mlx5_core_dev *mdev);
void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev);
-void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data);
#else
{
}
-static inline void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event,
- void *data)
-{
-}
-
#endif
#endif /* __MLX5_FPGA_CORE_H__ */
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
+static int mlx5_set_extended_dest(struct mlx5_core_dev *dev,
+ struct fs_fte *fte, bool *extended_dest)
+{
+ int fw_log_max_fdb_encap_uplink =
+ MLX5_CAP_ESW(dev, log_max_fdb_encap_uplink);
+ int num_fwd_destinations = 0;
+ struct mlx5_flow_rule *dst;
+ int num_encap = 0;
+
+ *extended_dest = false;
+ if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+ return 0;
+
+ list_for_each_entry(dst, &fte->node.children, node.list) {
+ if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+ continue;
+ if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+ dst->dest_attr.vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)
+ num_encap++;
+ num_fwd_destinations++;
+ }
+ if (num_fwd_destinations > 1 && num_encap > 0)
+ *extended_dest = true;
+
+ if (*extended_dest && !fw_log_max_fdb_encap_uplink) {
+ mlx5_core_warn(dev, "FW does not support extended destination");
+ return -EOPNOTSUPP;
+ }
+ if (num_encap > (1 << fw_log_max_fdb_encap_uplink)) {
+ mlx5_core_warn(dev, "FW does not support more than %d encaps",
+ 1 << fw_log_max_fdb_encap_uplink);
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
int opmod, int modify_mask,
struct mlx5_flow_table *ft,
unsigned group_id,
struct fs_fte *fte)
{
- unsigned int inlen = MLX5_ST_SZ_BYTES(set_fte_in) +
- fte->dests_size * MLX5_ST_SZ_BYTES(dest_format_struct);
u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {0};
+ bool extended_dest = false;
struct mlx5_flow_rule *dst;
void *in_flow_context, *vlan;
void *in_match_value;
+ unsigned int inlen;
+ int dst_cnt_size;
void *in_dests;
u32 *in;
int err;
+ if (mlx5_set_extended_dest(dev, fte, &extended_dest))
+ return -EOPNOTSUPP;
+
+ if (!extended_dest)
+ dst_cnt_size = MLX5_ST_SZ_BYTES(dest_format_struct);
+ else
+ dst_cnt_size = MLX5_ST_SZ_BYTES(extended_dest_format);
+
+ inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fte->dests_size * dst_cnt_size;
in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
return -ENOMEM;
MLX5_SET(flow_context, in_flow_context, group_id, group_id);
MLX5_SET(flow_context, in_flow_context, flow_tag, fte->action.flow_tag);
- MLX5_SET(flow_context, in_flow_context, action, fte->action.action);
- MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
- fte->action.reformat_id);
+ MLX5_SET(flow_context, in_flow_context, extended_destination,
+ extended_dest);
+ if (extended_dest) {
+ u32 action;
+
+ action = fte->action.action &
+ ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+ MLX5_SET(flow_context, in_flow_context, action, action);
+ } else {
+ MLX5_SET(flow_context, in_flow_context, action,
+ fte->action.action);
+ MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+ fte->action.reformat_id);
+ }
MLX5_SET(flow_context, in_flow_context, modify_header_id,
fte->action.modify_id);
id = dst->dest_attr.vport.num;
MLX5_SET(dest_format_struct, in_dests,
destination_eswitch_owner_vhca_id_valid,
- dst->dest_attr.vport.vhca_id_valid);
+ !!(dst->dest_attr.vport.flags &
+ MLX5_FLOW_DEST_VPORT_VHCA_ID));
MLX5_SET(dest_format_struct, in_dests,
destination_eswitch_owner_vhca_id,
dst->dest_attr.vport.vhca_id);
+ if (extended_dest) {
+ MLX5_SET(dest_format_struct, in_dests,
+ packet_reformat,
+ !!(dst->dest_attr.vport.flags &
+ MLX5_FLOW_DEST_VPORT_REFORMAT_ID));
+ MLX5_SET(extended_dest_format, in_dests,
+ packet_reformat_id,
+ dst->dest_attr.vport.reformat_id);
+ }
break;
default:
id = dst->dest_attr.tir_num;
MLX5_SET(dest_format_struct, in_dests, destination_type,
type);
MLX5_SET(dest_format_struct, in_dests, destination_id, id);
- in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
+ in_dests += dst_cnt_size;
list_size++;
}
MLX5_SET(flow_counter_list, in_dests, flow_counter_id,
dst->dest_attr.counter_id);
- in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
+ in_dests += dst_cnt_size;
list_size++;
}
if (list_size > max_list_size) {
struct rhltable fgs_hash;
};
-struct mlx5_fc_cache {
- u64 packets;
- u64 bytes;
- u64 lastuse;
-};
-
-struct mlx5_fc {
- struct list_head list;
- struct llist_node addlist;
- struct llist_node dellist;
-
- /* last{packets,bytes} members are used when calculating the delta since
- * last reading
- */
- u64 lastpackets;
- u64 lastbytes;
-
- u32 id;
- bool aging;
-
- struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
-};
-
struct mlx5_ft_underlay_qp {
struct list_head list;
u32 qpn;
/* Max number of counters to query in bulk read is 32K */
#define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
+struct mlx5_fc_cache {
+ u64 packets;
+ u64 bytes;
+ u64 lastuse;
+};
+
+struct mlx5_fc {
+ struct list_head list;
+ struct llist_node addlist;
+ struct llist_node dellist;
+
+ /* last{packets,bytes} members are used when calculating the delta since
+ * last reading
+ */
+ u64 lastpackets;
+ u64 lastbytes;
+
+ u32 id;
+ bool aging;
+
+ struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
+};
+
/* locking scheme:
*
* It is the responsibility of the user to prevent concurrent calls or bad
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
+#include "lib/mlx5.h"
enum {
MLX5_HEALTH_POLL_INTERVAL = 2 * HZ,
&dev->iseg->cmdq_addr_l_sz);
}
-static void trigger_cmd_completions(struct mlx5_core_dev *dev)
-{
- unsigned long flags;
- u64 vector;
-
- /* wait for pending handlers to complete */
- synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD));
- spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
- vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
- if (!vector)
- goto no_trig;
-
- vector |= MLX5_TRIGGERED_CMD_COMP;
- spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
-
- mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
- mlx5_cmd_comp_handler(dev, vector, true);
- return;
-
-no_trig:
- spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
-}
-
static int in_fatal(struct mlx5_core_dev *dev)
{
struct mlx5_core_health *health = &dev->priv.health;
mlx5_core_err(dev, "start\n");
if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) {
dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
- trigger_cmd_completions(dev);
+ mlx5_cmd_trigger_completions(dev);
}
- mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1);
+ mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1);
mlx5_core_err(dev, "end\n");
unlock:
#include <linux/clocksource.h>
#include <linux/highmem.h>
#include <rdma/mlx5-abi.h>
+#include "lib/eq.h"
#include "en.h"
#include "clock.h"
clock->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
}
-void mlx5_pps_event(struct mlx5_core_dev *mdev,
- struct mlx5_eqe *eqe)
+static int mlx5_pps_event(struct notifier_block *nb,
+ unsigned long type, void *data)
{
- struct mlx5_clock *clock = &mdev->clock;
+ struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
+ struct mlx5_core_dev *mdev = clock->mdev;
struct ptp_clock_event ptp_event;
- struct timespec64 ts;
- u64 nsec_now, nsec_delta;
u64 cycles_now, cycles_delta;
+ u64 nsec_now, nsec_delta, ns;
+ struct mlx5_eqe *eqe = data;
int pin = eqe->data.pps.pin;
- s64 ns;
+ struct timespec64 ts;
unsigned long flags;
switch (clock->ptp_info.pin_config[pin].func) {
} else {
ptp_event.type = PTP_CLOCK_EXTTS;
}
+ /* TODOL clock->ptp can be NULL if ptp_clock_register failes */
ptp_clock_event(clock->ptp, &ptp_event);
break;
case PTP_PF_PEROUT:
write_sequnlock_irqrestore(&clock->lock, flags);
break;
default:
- mlx5_core_err(mdev, " Unhandled event\n");
+ mlx5_core_err(mdev, " Unhandled clock PPS event, func %d\n",
+ clock->ptp_info.pin_config[pin].func);
}
+
+ return NOTIFY_OK;
}
void mlx5_init_clock(struct mlx5_core_dev *mdev)
PTR_ERR(clock->ptp));
clock->ptp = NULL;
}
+
+ MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
+ mlx5_eq_notifier_register(mdev, &clock->pps_nb);
}
void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
return;
+ mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
if (clock->ptp) {
ptp_clock_unregister(clock->ptp);
clock->ptp = NULL;
#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
void mlx5_init_clock(struct mlx5_core_dev *mdev);
void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
-void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
{
#else
static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
-static inline void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) {}
-
static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
{
return -1;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#ifndef __LIB_MLX5_EQ_H__
+#define __LIB_MLX5_EQ_H__
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
+#include <linux/mlx5/cq.h>
+
+#define MLX5_MAX_IRQ_NAME (32)
+#define MLX5_EQE_SIZE (sizeof(struct mlx5_eqe))
+
+struct mlx5_eq_tasklet {
+ struct list_head list;
+ struct list_head process_list;
+ struct tasklet_struct task;
+ spinlock_t lock; /* lock completion tasklet list */
+};
+
+struct mlx5_cq_table {
+ spinlock_t lock; /* protect radix tree */
+ struct radix_tree_root tree;
+};
+
+struct mlx5_eq {
+ struct mlx5_core_dev *dev;
+ struct mlx5_cq_table cq_table;
+ __be32 __iomem *doorbell;
+ u32 cons_index;
+ struct mlx5_frag_buf buf;
+ int size;
+ unsigned int vecidx;
+ unsigned int irqn;
+ u8 eqn;
+ int nent;
+ struct mlx5_rsc_debug *dbg;
+};
+
+struct mlx5_eq_comp {
+ struct mlx5_eq core; /* Must be first */
+ struct mlx5_eq_tasklet tasklet_ctx;
+ struct list_head list;
+};
+
+static inline struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
+{
+ return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
+}
+
+static inline struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
+{
+ struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
+
+ return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
+}
+
+static inline void eq_update_ci(struct mlx5_eq *eq, int arm)
+{
+ __be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
+ u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
+
+ __raw_writel((__force u32)cpu_to_be32(val), addr);
+ /* We still want ordering, just not swabbing, so add a barrier */
+ mb();
+}
+
+int mlx5_eq_table_init(struct mlx5_core_dev *dev);
+void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
+int mlx5_eq_table_create(struct mlx5_core_dev *dev);
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
+
+int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn);
+struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev);
+void mlx5_cq_tasklet_cb(unsigned long data);
+struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix);
+
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq);
+void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev);
+void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev);
+
+int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
+void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
+
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
+
+#ifdef CONFIG_RFS_ACCEL
+struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
+#endif
+
+int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
+int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
+
+#endif
#ifndef __LIB_MLX5_H__
#define __LIB_MLX5_H__
+#include "mlx5_core.h"
+
void mlx5_init_reserved_gids(struct mlx5_core_dev *dev);
void mlx5_cleanup_reserved_gids(struct mlx5_core_dev *dev);
int mlx5_core_reserve_gids(struct mlx5_core_dev *dev, unsigned int count);
int mlx5_core_reserved_gid_alloc(struct mlx5_core_dev *dev, int *gid_index);
void mlx5_core_reserved_gid_free(struct mlx5_core_dev *dev, int gid_index);
+/* TODO move to lib/events.h */
+
+#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF
+#define PORT_MODULE_EVENT_ERROR_TYPE_MASK 0xF
+
+enum port_module_event_status_type {
+ MLX5_MODULE_STATUS_PLUGGED = 0x1,
+ MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
+ MLX5_MODULE_STATUS_ERROR = 0x3,
+ MLX5_MODULE_STATUS_DISABLED = 0x4,
+ MLX5_MODULE_STATUS_NUM,
+};
+
+enum port_module_event_error_type {
+ MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED = 0x0,
+ MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX = 0x1,
+ MLX5_MODULE_EVENT_ERROR_BUS_STUCK = 0x2,
+ MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT = 0x3,
+ MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST = 0x4,
+ MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER = 0x5,
+ MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE = 0x6,
+ MLX5_MODULE_EVENT_ERROR_BAD_CABLE = 0x7,
+ MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED = 0xc,
+ MLX5_MODULE_EVENT_ERROR_NUM,
+};
+
+struct mlx5_pme_stats {
+ u64 status_counters[MLX5_MODULE_STATUS_NUM];
+ u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM];
+};
+
+void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats);
+int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data);
+
#endif
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cq.h>
#include <linux/mlx5/qp.h>
-#include <linux/mlx5/srq.h>
#include <linux/debugfs.h>
#include <linux/kmod.h>
#include <linux/mlx5/mlx5_ifc.h>
#endif
#include <net/devlink.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
#include "fs_core.h"
#include "lib/mpfs.h"
#include "eswitch.h"
pci_release_regions(pdev);
}
-static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
-{
- struct mlx5_priv *priv = &dev->priv;
- struct mlx5_eq_table *table = &priv->eq_table;
- int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
- MLX5_CAP_GEN(dev, max_num_eqs) :
- 1 << MLX5_CAP_GEN(dev, log_max_eq);
- int nvec;
- int err;
-
- nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
- MLX5_EQ_VEC_COMP_BASE;
- nvec = min_t(int, nvec, num_eqs);
- if (nvec <= MLX5_EQ_VEC_COMP_BASE)
- return -ENOMEM;
-
- priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
- if (!priv->irq_info)
- return -ENOMEM;
-
- nvec = pci_alloc_irq_vectors(dev->pdev,
- MLX5_EQ_VEC_COMP_BASE + 1, nvec,
- PCI_IRQ_MSIX);
- if (nvec < 0) {
- err = nvec;
- goto err_free_irq_info;
- }
-
- table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
-
- return 0;
-
-err_free_irq_info:
- kfree(priv->irq_info);
- return err;
-}
-
-static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev)
-{
- struct mlx5_priv *priv = &dev->priv;
-
- pci_free_irq_vectors(dev->pdev);
- kfree(priv->irq_info);
-}
-
struct mlx5_reg_host_endianness {
u8 he;
u8 rsvd[15];
return (u64)timer_l | (u64)timer_h1 << 32;
}
-static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
- struct mlx5_priv *priv = &mdev->priv;
- int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
-
- if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
- mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
- return -ENOMEM;
- }
-
- cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
- priv->irq_info[i].mask);
-
- if (IS_ENABLED(CONFIG_SMP) &&
- irq_set_affinity_hint(irq, priv->irq_info[i].mask))
- mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
-
- return 0;
-}
-
-static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
- struct mlx5_priv *priv = &mdev->priv;
- int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
-
- irq_set_affinity_hint(irq, NULL);
- free_cpumask_var(priv->irq_info[i].mask);
-}
-
-static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
-{
- int err;
- int i;
-
- for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
- err = mlx5_irq_set_affinity_hint(mdev, i);
- if (err)
- goto err_out;
- }
-
- return 0;
-
-err_out:
- for (i--; i >= 0; i--)
- mlx5_irq_clear_affinity_hint(mdev, i);
-
- return err;
-}
-
-static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
-{
- int i;
-
- for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
- mlx5_irq_clear_affinity_hint(mdev, i);
-}
-
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
- unsigned int *irqn)
-{
- struct mlx5_eq_table *table = &dev->priv.eq_table;
- struct mlx5_eq *eq, *n;
- int err = -ENOENT;
-
- spin_lock(&table->lock);
- list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
- if (eq->index == vector) {
- *eqn = eq->eqn;
- *irqn = eq->irqn;
- err = 0;
- break;
- }
- }
- spin_unlock(&table->lock);
-
- return err;
-}
-EXPORT_SYMBOL(mlx5_vector2eqn);
-
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
-{
- struct mlx5_eq_table *table = &dev->priv.eq_table;
- struct mlx5_eq *eq;
-
- spin_lock(&table->lock);
- list_for_each_entry(eq, &table->comp_eqs_list, list)
- if (eq->eqn == eqn) {
- spin_unlock(&table->lock);
- return eq;
- }
-
- spin_unlock(&table->lock);
-
- return ERR_PTR(-ENOENT);
-}
-
-static void free_comp_eqs(struct mlx5_core_dev *dev)
-{
- struct mlx5_eq_table *table = &dev->priv.eq_table;
- struct mlx5_eq *eq, *n;
-
-#ifdef CONFIG_RFS_ACCEL
- if (dev->rmap) {
- free_irq_cpu_rmap(dev->rmap);
- dev->rmap = NULL;
- }
-#endif
- spin_lock(&table->lock);
- list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
- list_del(&eq->list);
- spin_unlock(&table->lock);
- if (mlx5_destroy_unmap_eq(dev, eq))
- mlx5_core_warn(dev, "failed to destroy EQ 0x%x\n",
- eq->eqn);
- kfree(eq);
- spin_lock(&table->lock);
- }
- spin_unlock(&table->lock);
-}
-
-static int alloc_comp_eqs(struct mlx5_core_dev *dev)
-{
- struct mlx5_eq_table *table = &dev->priv.eq_table;
- char name[MLX5_MAX_IRQ_NAME];
- struct mlx5_eq *eq;
- int ncomp_vec;
- int nent;
- int err;
- int i;
-
- INIT_LIST_HEAD(&table->comp_eqs_list);
- ncomp_vec = table->num_comp_vectors;
- nent = MLX5_COMP_EQ_SIZE;
-#ifdef CONFIG_RFS_ACCEL
- dev->rmap = alloc_irq_cpu_rmap(ncomp_vec);
- if (!dev->rmap)
- return -ENOMEM;
-#endif
- for (i = 0; i < ncomp_vec; i++) {
- eq = kzalloc(sizeof(*eq), GFP_KERNEL);
- if (!eq) {
- err = -ENOMEM;
- goto clean;
- }
-
-#ifdef CONFIG_RFS_ACCEL
- irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev,
- MLX5_EQ_VEC_COMP_BASE + i));
-#endif
- snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
- err = mlx5_create_map_eq(dev, eq,
- i + MLX5_EQ_VEC_COMP_BASE, nent, 0,
- name, MLX5_EQ_TYPE_COMP);
- if (err) {
- kfree(eq);
- goto clean;
- }
- mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->eqn);
- eq->index = i;
- spin_lock(&table->lock);
- list_add_tail(&eq->list, &table->comp_eqs_list);
- spin_unlock(&table->lock);
- }
-
- return 0;
-
-clean:
- free_comp_eqs(dev);
- return err;
-}
-
static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
{
u32 query_in[MLX5_ST_SZ_DW(query_issi_in)] = {0};
goto out;
}
- err = mlx5_eq_init(dev);
+ err = mlx5_eq_table_init(dev);
if (err) {
dev_err(&pdev->dev, "failed to initialize eq\n");
goto out;
}
+ err = mlx5_events_init(dev);
+ if (err) {
+ dev_err(&pdev->dev, "failed to initialize events\n");
+ goto err_eq_cleanup;
+ }
+
err = mlx5_cq_debugfs_init(dev);
if (err) {
dev_err(&pdev->dev, "failed to initialize cq debugfs\n");
- goto err_eq_cleanup;
+ goto err_events_cleanup;
}
mlx5_init_qp_table(dev);
- mlx5_init_srq_table(dev);
-
mlx5_init_mkey_table(dev);
mlx5_init_reserved_gids(dev);
err_tables_cleanup:
mlx5_vxlan_destroy(dev->vxlan);
mlx5_cleanup_mkey_table(dev);
- mlx5_cleanup_srq_table(dev);
mlx5_cleanup_qp_table(dev);
mlx5_cq_debugfs_cleanup(dev);
-
+err_events_cleanup:
+ mlx5_events_cleanup(dev);
err_eq_cleanup:
- mlx5_eq_cleanup(dev);
+ mlx5_eq_table_cleanup(dev);
out:
return err;
mlx5_cleanup_clock(dev);
mlx5_cleanup_reserved_gids(dev);
mlx5_cleanup_mkey_table(dev);
- mlx5_cleanup_srq_table(dev);
mlx5_cleanup_qp_table(dev);
mlx5_cq_debugfs_cleanup(dev);
- mlx5_eq_cleanup(dev);
+ mlx5_events_cleanup(dev);
+ mlx5_eq_table_cleanup(dev);
}
static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
goto reclaim_boot_pages;
}
- err = mlx5_pagealloc_start(dev);
- if (err) {
- dev_err(&pdev->dev, "mlx5_pagealloc_start failed\n");
- goto reclaim_boot_pages;
- }
-
err = mlx5_cmd_init_hca(dev, sw_owner_id);
if (err) {
dev_err(&pdev->dev, "init hca failed\n");
- goto err_pagealloc_stop;
+ goto reclaim_boot_pages;
}
mlx5_set_driver_version(dev);
}
}
- err = mlx5_alloc_irq_vectors(dev);
- if (err) {
- dev_err(&pdev->dev, "alloc irq vectors failed\n");
- goto err_cleanup_once;
- }
-
dev->priv.uar = mlx5_get_uars_page(dev);
if (IS_ERR(dev->priv.uar)) {
dev_err(&pdev->dev, "Failed allocating uar, aborting\n");
err = PTR_ERR(dev->priv.uar);
- goto err_disable_msix;
+ goto err_get_uars;
}
- err = mlx5_start_eqs(dev);
+ mlx5_events_start(dev);
+ mlx5_pagealloc_start(dev);
+
+ err = mlx5_eq_table_create(dev);
if (err) {
- dev_err(&pdev->dev, "Failed to start pages and async EQs\n");
- goto err_put_uars;
+ dev_err(&pdev->dev, "Failed to create EQs\n");
+ goto err_eq_table;
}
err = mlx5_fw_tracer_init(dev->tracer);
goto err_fw_tracer;
}
- err = alloc_comp_eqs(dev);
- if (err) {
- dev_err(&pdev->dev, "Failed to alloc completion EQs\n");
- goto err_comp_eqs;
- }
-
- err = mlx5_irq_set_affinity_hints(dev);
- if (err) {
- dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
- goto err_affinity_hints;
- }
-
err = mlx5_fpga_device_start(dev);
if (err) {
dev_err(&pdev->dev, "fpga device start failed %d\n", err);
mlx5_fpga_device_stop(dev);
err_fpga_start:
- mlx5_irq_clear_affinity_hints(dev);
-
-err_affinity_hints:
- free_comp_eqs(dev);
-
-err_comp_eqs:
mlx5_fw_tracer_cleanup(dev->tracer);
err_fw_tracer:
- mlx5_stop_eqs(dev);
+ mlx5_eq_table_destroy(dev);
-err_put_uars:
+err_eq_table:
+ mlx5_pagealloc_stop(dev);
+ mlx5_events_stop(dev);
mlx5_put_uars_page(dev, priv->uar);
-err_disable_msix:
- mlx5_free_irq_vectors(dev);
-
-err_cleanup_once:
+err_get_uars:
if (boot)
mlx5_cleanup_once(dev);
goto out_err;
}
-err_pagealloc_stop:
- mlx5_pagealloc_stop(dev);
-
reclaim_boot_pages:
mlx5_reclaim_startup_pages(dev);
mlx5_accel_ipsec_cleanup(dev);
mlx5_accel_tls_cleanup(dev);
mlx5_fpga_device_stop(dev);
- mlx5_irq_clear_affinity_hints(dev);
- free_comp_eqs(dev);
mlx5_fw_tracer_cleanup(dev->tracer);
- mlx5_stop_eqs(dev);
+ mlx5_eq_table_destroy(dev);
+ mlx5_pagealloc_stop(dev);
+ mlx5_events_stop(dev);
mlx5_put_uars_page(dev, priv->uar);
- mlx5_free_irq_vectors(dev);
if (cleanup)
mlx5_cleanup_once(dev);
mlx5_stop_health_poll(dev, cleanup);
+
err = mlx5_cmd_teardown_hca(dev);
if (err) {
dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
goto out;
}
- mlx5_pagealloc_stop(dev);
mlx5_reclaim_startup_pages(dev);
mlx5_core_disable_hca(dev, 0);
mlx5_cmd_cleanup(dev);
return err;
}
-struct mlx5_core_event_handler {
- void (*event)(struct mlx5_core_dev *dev,
- enum mlx5_dev_event event,
- void *data);
-};
-
static const struct devlink_ops mlx5_devlink_ops = {
#ifdef CONFIG_MLX5_ESWITCH
.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
pci_set_drvdata(pdev, dev);
dev->pdev = pdev;
- dev->event = mlx5_core_event;
dev->profile = &profile[prof_sel];
INIT_LIST_HEAD(&priv->ctx_list);
mutex_init(&dev->pci_status_mutex);
mutex_init(&dev->intf_state_mutex);
- INIT_LIST_HEAD(&priv->waiting_events_list);
- priv->is_accum_events = false;
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- err = init_srcu_struct(&priv->pfault_srcu);
- if (err) {
- dev_err(&pdev->dev, "init_srcu_struct failed with error code %d\n",
- err);
- goto clean_dev;
- }
-#endif
mutex_init(&priv->bfregs.reg_head.lock);
mutex_init(&priv->bfregs.wc_head.lock);
INIT_LIST_HEAD(&priv->bfregs.reg_head.list);
err = mlx5_pci_init(dev, priv);
if (err) {
dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err);
- goto clean_srcu;
+ goto clean_dev;
}
err = mlx5_health_init(dev);
goto close_pci;
}
- mlx5_pagealloc_init(dev);
+ err = mlx5_pagealloc_init(dev);
+ if (err)
+ goto err_pagealloc_init;
err = mlx5_load_one(dev, priv, true);
if (err) {
dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err);
- goto clean_health;
+ goto err_load_one;
}
request_module_nowait(MLX5_IB_MOD);
clean_load:
mlx5_unload_one(dev, priv, true);
-clean_health:
+err_load_one:
mlx5_pagealloc_cleanup(dev);
+err_pagealloc_init:
mlx5_health_cleanup(dev);
close_pci:
mlx5_pci_close(dev, priv);
-clean_srcu:
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- cleanup_srcu_struct(&priv->pfault_srcu);
clean_dev:
-#endif
devlink_free(devlink);
return err;
mlx5_pagealloc_cleanup(dev);
mlx5_health_cleanup(dev);
mlx5_pci_close(dev, priv);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- cleanup_srcu_struct(&priv->pfault_srcu);
-#endif
devlink_free(devlink);
}
* kexec. There is no need to cleanup the mlx5_core software
* contexts.
*/
- mlx5_irq_clear_affinity_hints(dev);
mlx5_core_eq_free_irqs(dev);
return 0;
__func__, __LINE__, current->pid, \
##__VA_ARGS__)
+#define mlx5_core_warn_once(__dev, format, ...) \
+ dev_warn_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \
+ __func__, __LINE__, current->pid, \
+ ##__VA_ARGS__)
+
#define mlx5_core_info(__dev, format, ...) \
dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__)
int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
-
-void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
- unsigned long param);
-void mlx5_core_page_fault(struct mlx5_core_dev *dev,
- struct mlx5_pagefault *pfault);
-void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
void mlx5_disable_device(struct mlx5_core_dev *dev);
void mlx5_recover_device(struct mlx5_core_dev *dev);
int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
-int mlx5_eq_init(struct mlx5_core_dev *dev);
-void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
-int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
- int nent, u64 mask, const char *name,
- enum mlx5_eq_type type);
-int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
- u32 *out, int outlen);
-int mlx5_start_eqs(struct mlx5_core_dev *dev);
-void mlx5_stop_eqs(struct mlx5_core_dev *dev);
-/* This function should only be called after mlx5_cmd_force_teardown_hca */
-void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
-void mlx5_cq_tasklet_cb(unsigned long data);
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
-int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
-void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
+void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev);
int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
void mlx5_lag_remove(struct mlx5_core_dev *dev);
+int mlx5_events_init(struct mlx5_core_dev *dev);
+void mlx5_events_cleanup(struct mlx5_core_dev *dev);
+void mlx5_events_start(struct mlx5_core_dev *dev);
+void mlx5_events_stop(struct mlx5_core_dev *dev);
+
void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
void mlx5_attach_device(struct mlx5_core_dev *dev);
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
enum {
MLX5_PAGES_CANT_GIVE = 0,
kfree(req);
}
-void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
- s32 npages)
+static int req_pages_handler(struct notifier_block *nb,
+ unsigned long type, void *data)
{
struct mlx5_pages_req *req;
-
+ struct mlx5_core_dev *dev;
+ struct mlx5_priv *priv;
+ struct mlx5_eqe *eqe;
+ u16 func_id;
+ s32 npages;
+
+ priv = mlx5_nb_cof(nb, struct mlx5_priv, pg_nb);
+ dev = container_of(priv, struct mlx5_core_dev, priv);
+ eqe = data;
+
+ func_id = be16_to_cpu(eqe->data.req_pages.func_id);
+ npages = be32_to_cpu(eqe->data.req_pages.num_pages);
+ mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
+ func_id, npages);
req = kzalloc(sizeof(*req), GFP_ATOMIC);
if (!req) {
mlx5_core_warn(dev, "failed to allocate pages request\n");
- return;
+ return NOTIFY_DONE;
}
req->dev = dev;
req->npages = npages;
INIT_WORK(&req->work, pages_work_handler);
queue_work(dev->priv.pg_wq, &req->work);
+ return NOTIFY_OK;
}
int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
return 0;
}
-void mlx5_pagealloc_init(struct mlx5_core_dev *dev)
+int mlx5_pagealloc_init(struct mlx5_core_dev *dev)
{
dev->priv.page_root = RB_ROOT;
INIT_LIST_HEAD(&dev->priv.free_list);
+ dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
+ if (!dev->priv.pg_wq)
+ return -ENOMEM;
+
+ return 0;
}
void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
{
- /* nothing */
+ destroy_workqueue(dev->priv.pg_wq);
}
-int mlx5_pagealloc_start(struct mlx5_core_dev *dev)
+void mlx5_pagealloc_start(struct mlx5_core_dev *dev)
{
- dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
- if (!dev->priv.pg_wq)
- return -ENOMEM;
-
- return 0;
+ MLX5_NB_INIT(&dev->priv.pg_nb, req_pages_handler, PAGE_REQUEST);
+ mlx5_eq_notifier_register(dev, &dev->priv.pg_nb);
}
void mlx5_pagealloc_stop(struct mlx5_core_dev *dev)
{
- destroy_workqueue(dev->priv.pg_wq);
+ mlx5_eq_notifier_unregister(dev, &dev->priv.pg_nb);
+ flush_workqueue(dev->priv.pg_wq);
}
int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
*enabled = !!(MLX5_GET(pcmr_reg, out, fcs_chk));
}
-static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
- "Cable plugged", /* MLX5_MODULE_STATUS_PLUGGED = 0x1 */
- "Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED = 0x2 */
- "Cable error", /* MLX5_MODULE_STATUS_ERROR = 0x3 */
-};
-
-static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
- "Power budget exceeded",
- "Long Range for non MLNX cable",
- "Bus stuck(I2C or data shorted)",
- "No EEPROM/retry timeout",
- "Enforce part number list",
- "Unknown identifier",
- "High Temperature",
- "Bad or shorted cable/module",
- "Unknown status",
-};
-
-void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
-{
- enum port_module_event_status_type module_status;
- enum port_module_event_error_type error_type;
- struct mlx5_eqe_port_module *module_event_eqe;
- struct mlx5_priv *priv = &dev->priv;
- u8 module_num;
-
- module_event_eqe = &eqe->data.port_module;
- module_num = module_event_eqe->module;
- module_status = module_event_eqe->module_status &
- PORT_MODULE_EVENT_MODULE_STATUS_MASK;
- error_type = module_event_eqe->error_type &
- PORT_MODULE_EVENT_ERROR_TYPE_MASK;
-
- if (module_status < MLX5_MODULE_STATUS_ERROR) {
- priv->pme_stats.status_counters[module_status - 1]++;
- } else if (module_status == MLX5_MODULE_STATUS_ERROR) {
- if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN)
- /* Unknown error type */
- error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN;
- priv->pme_stats.error_counters[error_type]++;
- }
-
- if (!printk_ratelimit())
- return;
-
- if (module_status < MLX5_MODULE_STATUS_ERROR)
- mlx5_core_info(dev,
- "Port module event: module %u, %s\n",
- module_num, mlx5_pme_status[module_status - 1]);
-
- else if (module_status == MLX5_MODULE_STATUS_ERROR)
- mlx5_core_info(dev,
- "Port module event[error]: module %u, %s, %s\n",
- module_num, mlx5_pme_status[module_status - 1],
- mlx5_pme_error[error_type]);
-}
-
int mlx5_query_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size)
{
u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
#include <linux/mlx5/transobj.h>
#include "mlx5_core.h"
+#include "lib/eq.h"
-static struct mlx5_core_rsc_common *mlx5_get_rsc(struct mlx5_core_dev *dev,
- u32 rsn)
+static struct mlx5_core_rsc_common *
+mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
{
- struct mlx5_qp_table *table = &dev->priv.qp_table;
struct mlx5_core_rsc_common *common;
spin_lock(&table->lock);
spin_unlock(&table->lock);
- if (!common) {
- mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n",
- rsn);
- return NULL;
- }
return common;
}
}
}
-void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
+static int rsc_event_notifier(struct notifier_block *nb,
+ unsigned long type, void *data)
{
- struct mlx5_core_rsc_common *common = mlx5_get_rsc(dev, rsn);
+ struct mlx5_core_rsc_common *common;
+ struct mlx5_qp_table *table;
+ struct mlx5_core_dev *dev;
struct mlx5_core_dct *dct;
+ u8 event_type = (u8)type;
struct mlx5_core_qp *qp;
+ struct mlx5_priv *priv;
+ struct mlx5_eqe *eqe;
+ u32 rsn;
+
+ switch (event_type) {
+ case MLX5_EVENT_TYPE_DCT_DRAINED:
+ eqe = data;
+ rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
+ rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
+ break;
+ case MLX5_EVENT_TYPE_PATH_MIG:
+ case MLX5_EVENT_TYPE_COMM_EST:
+ case MLX5_EVENT_TYPE_SQ_DRAINED:
+ case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+ case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+ case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+ case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+ case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+ eqe = data;
+ rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+ rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
+ break;
+ default:
+ return NOTIFY_DONE;
+ }
+
+ table = container_of(nb, struct mlx5_qp_table, nb);
+ priv = container_of(table, struct mlx5_priv, qp_table);
+ dev = container_of(priv, struct mlx5_core_dev, priv);
+
+ mlx5_core_dbg(dev, "event (%d) arrived on resource 0x%x\n", eqe->type, rsn);
- if (!common)
- return;
+ common = mlx5_get_rsc(table, rsn);
+ if (!common) {
+ mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n", rsn);
+ return NOTIFY_OK;
+ }
if (!is_event_type_allowed((rsn >> MLX5_USER_INDEX_LEN), event_type)) {
mlx5_core_warn(dev, "event 0x%.2x is not allowed on resource 0x%.8x\n",
event_type, rsn);
- return;
+ goto out;
}
switch (common->res) {
default:
mlx5_core_warn(dev, "invalid resource type for 0x%x\n", rsn);
}
-
+out:
mlx5_core_put_rsc(common);
+
+ return NOTIFY_OK;
}
static int create_resource_common(struct mlx5_core_dev *dev,
spin_lock_init(&table->lock);
INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
mlx5_qp_debugfs_init(dev);
+
+ table->nb.notifier_call = rsc_event_notifier;
+ mlx5_notifier_register(dev, &table->nb);
}
void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev)
{
+ struct mlx5_qp_table *table = &dev->priv.qp_table;
+
+ mlx5_notifier_unregister(dev, &table->nb);
mlx5_qp_debugfs_cleanup(dev);
}
return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
}
EXPORT_SYMBOL_GPL(mlx5_core_query_q_counter);
+
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+ int res_num,
+ enum mlx5_res_type res_type)
+{
+ u32 rsn = res_num | (res_type << MLX5_USER_INDEX_LEN);
+ struct mlx5_qp_table *table = &dev->priv.qp_table;
+
+ return mlx5_get_rsc(table, rsn);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_hold);
+
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res)
+{
+ mlx5_core_put_rsc(res);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_put);
+++ /dev/null
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. 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.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
-#include <linux/mlx5/srq.h>
-#include <rdma/ib_verbs.h>
-#include "mlx5_core.h"
-#include <linux/mlx5/transobj.h>
-
-void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type)
-{
- struct mlx5_srq_table *table = &dev->priv.srq_table;
- struct mlx5_core_srq *srq;
-
- spin_lock(&table->lock);
-
- srq = radix_tree_lookup(&table->tree, srqn);
- if (srq)
- atomic_inc(&srq->refcount);
-
- spin_unlock(&table->lock);
-
- if (!srq) {
- mlx5_core_warn(dev, "Async event for bogus SRQ 0x%08x\n", srqn);
- return;
- }
-
- srq->event(srq, event_type);
-
- if (atomic_dec_and_test(&srq->refcount))
- complete(&srq->free);
-}
-
-static int get_pas_size(struct mlx5_srq_attr *in)
-{
- u32 log_page_size = in->log_page_size + 12;
- u32 log_srq_size = in->log_size;
- u32 log_rq_stride = in->wqe_shift;
- u32 page_offset = in->page_offset;
- u32 po_quanta = 1 << (log_page_size - 6);
- u32 rq_sz = 1 << (log_srq_size + 4 + log_rq_stride);
- u32 page_size = 1 << log_page_size;
- u32 rq_sz_po = rq_sz + (page_offset * po_quanta);
- u32 rq_num_pas = DIV_ROUND_UP(rq_sz_po, page_size);
-
- return rq_num_pas * sizeof(u64);
-}
-
-static void set_wq(void *wq, struct mlx5_srq_attr *in)
-{
- MLX5_SET(wq, wq, wq_signature, !!(in->flags
- & MLX5_SRQ_FLAG_WQ_SIG));
- MLX5_SET(wq, wq, log_wq_pg_sz, in->log_page_size);
- MLX5_SET(wq, wq, log_wq_stride, in->wqe_shift + 4);
- MLX5_SET(wq, wq, log_wq_sz, in->log_size);
- MLX5_SET(wq, wq, page_offset, in->page_offset);
- MLX5_SET(wq, wq, lwm, in->lwm);
- MLX5_SET(wq, wq, pd, in->pd);
- MLX5_SET64(wq, wq, dbr_addr, in->db_record);
-}
-
-static void set_srqc(void *srqc, struct mlx5_srq_attr *in)
-{
- MLX5_SET(srqc, srqc, wq_signature, !!(in->flags
- & MLX5_SRQ_FLAG_WQ_SIG));
- MLX5_SET(srqc, srqc, log_page_size, in->log_page_size);
- MLX5_SET(srqc, srqc, log_rq_stride, in->wqe_shift);
- MLX5_SET(srqc, srqc, log_srq_size, in->log_size);
- MLX5_SET(srqc, srqc, page_offset, in->page_offset);
- MLX5_SET(srqc, srqc, lwm, in->lwm);
- MLX5_SET(srqc, srqc, pd, in->pd);
- MLX5_SET64(srqc, srqc, dbr_addr, in->db_record);
- MLX5_SET(srqc, srqc, xrcd, in->xrcd);
- MLX5_SET(srqc, srqc, cqn, in->cqn);
-}
-
-static void get_wq(void *wq, struct mlx5_srq_attr *in)
-{
- if (MLX5_GET(wq, wq, wq_signature))
- in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
- in->log_page_size = MLX5_GET(wq, wq, log_wq_pg_sz);
- in->wqe_shift = MLX5_GET(wq, wq, log_wq_stride) - 4;
- in->log_size = MLX5_GET(wq, wq, log_wq_sz);
- in->page_offset = MLX5_GET(wq, wq, page_offset);
- in->lwm = MLX5_GET(wq, wq, lwm);
- in->pd = MLX5_GET(wq, wq, pd);
- in->db_record = MLX5_GET64(wq, wq, dbr_addr);
-}
-
-static void get_srqc(void *srqc, struct mlx5_srq_attr *in)
-{
- if (MLX5_GET(srqc, srqc, wq_signature))
- in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
- in->log_page_size = MLX5_GET(srqc, srqc, log_page_size);
- in->wqe_shift = MLX5_GET(srqc, srqc, log_rq_stride);
- in->log_size = MLX5_GET(srqc, srqc, log_srq_size);
- in->page_offset = MLX5_GET(srqc, srqc, page_offset);
- in->lwm = MLX5_GET(srqc, srqc, lwm);
- in->pd = MLX5_GET(srqc, srqc, pd);
- in->db_record = MLX5_GET64(srqc, srqc, dbr_addr);
-}
-
-struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
-{
- struct mlx5_srq_table *table = &dev->priv.srq_table;
- struct mlx5_core_srq *srq;
-
- spin_lock(&table->lock);
-
- srq = radix_tree_lookup(&table->tree, srqn);
- if (srq)
- atomic_inc(&srq->refcount);
-
- spin_unlock(&table->lock);
-
- return srq;
-}
-EXPORT_SYMBOL(mlx5_core_get_srq);
-
-static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *in)
-{
- u32 create_out[MLX5_ST_SZ_DW(create_srq_out)] = {0};
- void *create_in;
- void *srqc;
- void *pas;
- int pas_size;
- int inlen;
- int err;
-
- pas_size = get_pas_size(in);
- inlen = MLX5_ST_SZ_BYTES(create_srq_in) + pas_size;
- create_in = kvzalloc(inlen, GFP_KERNEL);
- if (!create_in)
- return -ENOMEM;
-
- MLX5_SET(create_srq_in, create_in, uid, in->uid);
- srqc = MLX5_ADDR_OF(create_srq_in, create_in, srq_context_entry);
- pas = MLX5_ADDR_OF(create_srq_in, create_in, pas);
-
- set_srqc(srqc, in);
- memcpy(pas, in->pas, pas_size);
-
- MLX5_SET(create_srq_in, create_in, opcode,
- MLX5_CMD_OP_CREATE_SRQ);
-
- err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
- sizeof(create_out));
- kvfree(create_in);
- if (!err) {
- srq->srqn = MLX5_GET(create_srq_out, create_out, srqn);
- srq->uid = in->uid;
- }
-
- return err;
-}
-
-static int destroy_srq_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq)
-{
- u32 srq_in[MLX5_ST_SZ_DW(destroy_srq_in)] = {0};
- u32 srq_out[MLX5_ST_SZ_DW(destroy_srq_out)] = {0};
-
- MLX5_SET(destroy_srq_in, srq_in, opcode,
- MLX5_CMD_OP_DESTROY_SRQ);
- MLX5_SET(destroy_srq_in, srq_in, srqn, srq->srqn);
- MLX5_SET(destroy_srq_in, srq_in, uid, srq->uid);
-
- return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
- srq_out, sizeof(srq_out));
-}
-
-static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- u16 lwm, int is_srq)
-{
- u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
- u32 srq_out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
-
- MLX5_SET(arm_rq_in, srq_in, opcode, MLX5_CMD_OP_ARM_RQ);
- MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ);
- MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn);
- MLX5_SET(arm_rq_in, srq_in, lwm, lwm);
- MLX5_SET(arm_rq_in, srq_in, uid, srq->uid);
-
- return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
- srq_out, sizeof(srq_out));
-}
-
-static int query_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *out)
-{
- u32 srq_in[MLX5_ST_SZ_DW(query_srq_in)] = {0};
- u32 *srq_out;
- void *srqc;
- int err;
-
- srq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_srq_out), GFP_KERNEL);
- if (!srq_out)
- return -ENOMEM;
-
- MLX5_SET(query_srq_in, srq_in, opcode,
- MLX5_CMD_OP_QUERY_SRQ);
- MLX5_SET(query_srq_in, srq_in, srqn, srq->srqn);
- err = mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
- srq_out, MLX5_ST_SZ_BYTES(query_srq_out));
- if (err)
- goto out;
-
- srqc = MLX5_ADDR_OF(query_srq_out, srq_out, srq_context_entry);
- get_srqc(srqc, out);
- if (MLX5_GET(srqc, srqc, state) != MLX5_SRQC_STATE_GOOD)
- out->flags |= MLX5_SRQ_FLAG_ERR;
-out:
- kvfree(srq_out);
- return err;
-}
-
-static int create_xrc_srq_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *in)
-{
- u32 create_out[MLX5_ST_SZ_DW(create_xrc_srq_out)];
- void *create_in;
- void *xrc_srqc;
- void *pas;
- int pas_size;
- int inlen;
- int err;
-
- pas_size = get_pas_size(in);
- inlen = MLX5_ST_SZ_BYTES(create_xrc_srq_in) + pas_size;
- create_in = kvzalloc(inlen, GFP_KERNEL);
- if (!create_in)
- return -ENOMEM;
-
- MLX5_SET(create_xrc_srq_in, create_in, uid, in->uid);
- xrc_srqc = MLX5_ADDR_OF(create_xrc_srq_in, create_in,
- xrc_srq_context_entry);
- pas = MLX5_ADDR_OF(create_xrc_srq_in, create_in, pas);
-
- set_srqc(xrc_srqc, in);
- MLX5_SET(xrc_srqc, xrc_srqc, user_index, in->user_index);
- memcpy(pas, in->pas, pas_size);
- MLX5_SET(create_xrc_srq_in, create_in, opcode,
- MLX5_CMD_OP_CREATE_XRC_SRQ);
-
- memset(create_out, 0, sizeof(create_out));
- err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
- sizeof(create_out));
- if (err)
- goto out;
-
- srq->srqn = MLX5_GET(create_xrc_srq_out, create_out, xrc_srqn);
- srq->uid = in->uid;
-out:
- kvfree(create_in);
- return err;
-}
-
-static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq)
-{
- u32 xrcsrq_in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)] = {0};
- u32 xrcsrq_out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
-
- MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, opcode,
- MLX5_CMD_OP_DESTROY_XRC_SRQ);
- MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
- MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, uid, srq->uid);
-
- return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
- xrcsrq_out, sizeof(xrcsrq_out));
-}
-
-static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq, u16 lwm)
-{
- u32 xrcsrq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)] = {0};
- u32 xrcsrq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
-
- MLX5_SET(arm_xrc_srq_in, xrcsrq_in, opcode, MLX5_CMD_OP_ARM_XRC_SRQ);
- MLX5_SET(arm_xrc_srq_in, xrcsrq_in, op_mod, MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
- MLX5_SET(arm_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
- MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm, lwm);
- MLX5_SET(arm_xrc_srq_in, xrcsrq_in, uid, srq->uid);
-
- return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
- xrcsrq_out, sizeof(xrcsrq_out));
-}
-
-static int query_xrc_srq_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *out)
-{
- u32 xrcsrq_in[MLX5_ST_SZ_DW(query_xrc_srq_in)];
- u32 *xrcsrq_out;
- void *xrc_srqc;
- int err;
-
- xrcsrq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_xrc_srq_out), GFP_KERNEL);
- if (!xrcsrq_out)
- return -ENOMEM;
- memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
-
- MLX5_SET(query_xrc_srq_in, xrcsrq_in, opcode,
- MLX5_CMD_OP_QUERY_XRC_SRQ);
- MLX5_SET(query_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
-
- err = mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in), xrcsrq_out,
- MLX5_ST_SZ_BYTES(query_xrc_srq_out));
- if (err)
- goto out;
-
- xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, xrcsrq_out,
- xrc_srq_context_entry);
- get_srqc(xrc_srqc, out);
- if (MLX5_GET(xrc_srqc, xrc_srqc, state) != MLX5_XRC_SRQC_STATE_GOOD)
- out->flags |= MLX5_SRQ_FLAG_ERR;
-
-out:
- kvfree(xrcsrq_out);
- return err;
-}
-
-static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *in)
-{
- void *create_in;
- void *rmpc;
- void *wq;
- int pas_size;
- int inlen;
- int err;
-
- pas_size = get_pas_size(in);
- inlen = MLX5_ST_SZ_BYTES(create_rmp_in) + pas_size;
- create_in = kvzalloc(inlen, GFP_KERNEL);
- if (!create_in)
- return -ENOMEM;
-
- rmpc = MLX5_ADDR_OF(create_rmp_in, create_in, ctx);
- wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
-
- MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
- MLX5_SET(create_rmp_in, create_in, uid, in->uid);
- set_wq(wq, in);
- memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size);
-
- err = mlx5_core_create_rmp(dev, create_in, inlen, &srq->srqn);
- if (!err)
- srq->uid = in->uid;
-
- kvfree(create_in);
- return err;
-}
-
-static int destroy_rmp_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq)
-{
- u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)] = {};
- u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {};
-
- MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
- MLX5_SET(destroy_rmp_in, in, rmpn, srq->srqn);
- MLX5_SET(destroy_rmp_in, in, uid, srq->uid);
- return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int arm_rmp_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq,
- u16 lwm)
-{
- void *in;
- void *rmpc;
- void *wq;
- void *bitmask;
- int err;
-
- in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
- if (!in)
- return -ENOMEM;
-
- rmpc = MLX5_ADDR_OF(modify_rmp_in, in, ctx);
- bitmask = MLX5_ADDR_OF(modify_rmp_in, in, bitmask);
- wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
-
- MLX5_SET(modify_rmp_in, in, rmp_state, MLX5_RMPC_STATE_RDY);
- MLX5_SET(modify_rmp_in, in, rmpn, srq->srqn);
- MLX5_SET(modify_rmp_in, in, uid, srq->uid);
- MLX5_SET(wq, wq, lwm, lwm);
- MLX5_SET(rmp_bitmask, bitmask, lwm, 1);
- MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
-
- err = mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
-
- kvfree(in);
- return err;
-}
-
-static int query_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *out)
-{
- u32 *rmp_out;
- void *rmpc;
- int err;
-
- rmp_out = kvzalloc(MLX5_ST_SZ_BYTES(query_rmp_out), GFP_KERNEL);
- if (!rmp_out)
- return -ENOMEM;
-
- err = mlx5_core_query_rmp(dev, srq->srqn, rmp_out);
- if (err)
- goto out;
-
- rmpc = MLX5_ADDR_OF(query_rmp_out, rmp_out, rmp_context);
- get_wq(MLX5_ADDR_OF(rmpc, rmpc, wq), out);
- if (MLX5_GET(rmpc, rmpc, state) != MLX5_RMPC_STATE_RDY)
- out->flags |= MLX5_SRQ_FLAG_ERR;
-
-out:
- kvfree(rmp_out);
- return err;
-}
-
-static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *in)
-{
- u32 create_out[MLX5_ST_SZ_DW(create_xrq_out)] = {0};
- void *create_in;
- void *xrqc;
- void *wq;
- int pas_size;
- int inlen;
- int err;
-
- pas_size = get_pas_size(in);
- inlen = MLX5_ST_SZ_BYTES(create_xrq_in) + pas_size;
- create_in = kvzalloc(inlen, GFP_KERNEL);
- if (!create_in)
- return -ENOMEM;
-
- xrqc = MLX5_ADDR_OF(create_xrq_in, create_in, xrq_context);
- wq = MLX5_ADDR_OF(xrqc, xrqc, wq);
-
- set_wq(wq, in);
- memcpy(MLX5_ADDR_OF(xrqc, xrqc, wq.pas), in->pas, pas_size);
-
- if (in->type == IB_SRQT_TM) {
- MLX5_SET(xrqc, xrqc, topology, MLX5_XRQC_TOPOLOGY_TAG_MATCHING);
- if (in->flags & MLX5_SRQ_FLAG_RNDV)
- MLX5_SET(xrqc, xrqc, offload, MLX5_XRQC_OFFLOAD_RNDV);
- MLX5_SET(xrqc, xrqc,
- tag_matching_topology_context.log_matching_list_sz,
- in->tm_log_list_size);
- }
- MLX5_SET(xrqc, xrqc, user_index, in->user_index);
- MLX5_SET(xrqc, xrqc, cqn, in->cqn);
- MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ);
- MLX5_SET(create_xrq_in, create_in, uid, in->uid);
- err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
- sizeof(create_out));
- kvfree(create_in);
- if (!err) {
- srq->srqn = MLX5_GET(create_xrq_out, create_out, xrqn);
- srq->uid = in->uid;
- }
-
- return err;
-}
-
-static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
-{
- u32 in[MLX5_ST_SZ_DW(destroy_xrq_in)] = {0};
- u32 out[MLX5_ST_SZ_DW(destroy_xrq_out)] = {0};
-
- MLX5_SET(destroy_xrq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRQ);
- MLX5_SET(destroy_xrq_in, in, xrqn, srq->srqn);
- MLX5_SET(destroy_xrq_in, in, uid, srq->uid);
-
- return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int arm_xrq_cmd(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq,
- u16 lwm)
-{
- u32 out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
- u32 in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
-
- MLX5_SET(arm_rq_in, in, opcode, MLX5_CMD_OP_ARM_RQ);
- MLX5_SET(arm_rq_in, in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_XRQ);
- MLX5_SET(arm_rq_in, in, srq_number, srq->srqn);
- MLX5_SET(arm_rq_in, in, lwm, lwm);
- MLX5_SET(arm_rq_in, in, uid, srq->uid);
-
- return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int query_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *out)
-{
- u32 in[MLX5_ST_SZ_DW(query_xrq_in)] = {0};
- u32 *xrq_out;
- int outlen = MLX5_ST_SZ_BYTES(query_xrq_out);
- void *xrqc;
- int err;
-
- xrq_out = kvzalloc(outlen, GFP_KERNEL);
- if (!xrq_out)
- return -ENOMEM;
-
- MLX5_SET(query_xrq_in, in, opcode, MLX5_CMD_OP_QUERY_XRQ);
- MLX5_SET(query_xrq_in, in, xrqn, srq->srqn);
-
- err = mlx5_cmd_exec(dev, in, sizeof(in), xrq_out, outlen);
- if (err)
- goto out;
-
- xrqc = MLX5_ADDR_OF(query_xrq_out, xrq_out, xrq_context);
- get_wq(MLX5_ADDR_OF(xrqc, xrqc, wq), out);
- if (MLX5_GET(xrqc, xrqc, state) != MLX5_XRQC_STATE_GOOD)
- out->flags |= MLX5_SRQ_FLAG_ERR;
- out->tm_next_tag =
- MLX5_GET(xrqc, xrqc,
- tag_matching_topology_context.append_next_index);
- out->tm_hw_phase_cnt =
- MLX5_GET(xrqc, xrqc,
- tag_matching_topology_context.hw_phase_cnt);
- out->tm_sw_phase_cnt =
- MLX5_GET(xrqc, xrqc,
- tag_matching_topology_context.sw_phase_cnt);
-
-out:
- kvfree(xrq_out);
- return err;
-}
-
-static int create_srq_split(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *in)
-{
- if (!dev->issi)
- return create_srq_cmd(dev, srq, in);
- switch (srq->common.res) {
- case MLX5_RES_XSRQ:
- return create_xrc_srq_cmd(dev, srq, in);
- case MLX5_RES_XRQ:
- return create_xrq_cmd(dev, srq, in);
- default:
- return create_rmp_cmd(dev, srq, in);
- }
-}
-
-static int destroy_srq_split(struct mlx5_core_dev *dev,
- struct mlx5_core_srq *srq)
-{
- if (!dev->issi)
- return destroy_srq_cmd(dev, srq);
- switch (srq->common.res) {
- case MLX5_RES_XSRQ:
- return destroy_xrc_srq_cmd(dev, srq);
- case MLX5_RES_XRQ:
- return destroy_xrq_cmd(dev, srq);
- default:
- return destroy_rmp_cmd(dev, srq);
- }
-}
-
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *in)
-{
- int err;
- struct mlx5_srq_table *table = &dev->priv.srq_table;
-
- switch (in->type) {
- case IB_SRQT_XRC:
- srq->common.res = MLX5_RES_XSRQ;
- break;
- case IB_SRQT_TM:
- srq->common.res = MLX5_RES_XRQ;
- break;
- default:
- srq->common.res = MLX5_RES_SRQ;
- }
-
- err = create_srq_split(dev, srq, in);
- if (err)
- return err;
-
- atomic_set(&srq->refcount, 1);
- init_completion(&srq->free);
-
- spin_lock_irq(&table->lock);
- err = radix_tree_insert(&table->tree, srq->srqn, srq);
- spin_unlock_irq(&table->lock);
- if (err) {
- mlx5_core_warn(dev, "err %d, srqn 0x%x\n", err, srq->srqn);
- goto err_destroy_srq_split;
- }
-
- return 0;
-
-err_destroy_srq_split:
- destroy_srq_split(dev, srq);
-
- return err;
-}
-EXPORT_SYMBOL(mlx5_core_create_srq);
-
-int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
-{
- struct mlx5_srq_table *table = &dev->priv.srq_table;
- struct mlx5_core_srq *tmp;
- int err;
-
- spin_lock_irq(&table->lock);
- tmp = radix_tree_delete(&table->tree, srq->srqn);
- spin_unlock_irq(&table->lock);
- if (!tmp) {
- mlx5_core_warn(dev, "srq 0x%x not found in tree\n", srq->srqn);
- return -EINVAL;
- }
- if (tmp != srq) {
- mlx5_core_warn(dev, "corruption on srqn 0x%x\n", srq->srqn);
- return -EINVAL;
- }
-
- err = destroy_srq_split(dev, srq);
- if (err)
- return err;
-
- if (atomic_dec_and_test(&srq->refcount))
- complete(&srq->free);
- wait_for_completion(&srq->free);
-
- return 0;
-}
-EXPORT_SYMBOL(mlx5_core_destroy_srq);
-
-int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *out)
-{
- if (!dev->issi)
- return query_srq_cmd(dev, srq, out);
- switch (srq->common.res) {
- case MLX5_RES_XSRQ:
- return query_xrc_srq_cmd(dev, srq, out);
- case MLX5_RES_XRQ:
- return query_xrq_cmd(dev, srq, out);
- default:
- return query_rmp_cmd(dev, srq, out);
- }
-}
-EXPORT_SYMBOL(mlx5_core_query_srq);
-
-int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- u16 lwm, int is_srq)
-{
- if (!dev->issi)
- return arm_srq_cmd(dev, srq, lwm, is_srq);
- switch (srq->common.res) {
- case MLX5_RES_XSRQ:
- return arm_xrc_srq_cmd(dev, srq, lwm);
- case MLX5_RES_XRQ:
- return arm_xrq_cmd(dev, srq, lwm);
- default:
- return arm_rmp_cmd(dev, srq, lwm);
- }
-}
-EXPORT_SYMBOL(mlx5_core_arm_srq);
-
-void mlx5_init_srq_table(struct mlx5_core_dev *dev)
-{
- struct mlx5_srq_table *table = &dev->priv.srq_table;
-
- memset(table, 0, sizeof(*table));
- spin_lock_init(&table->lock);
- INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
-}
-
-void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev)
-{
- /* nothing */
-}
}
EXPORT_SYMBOL(mlx5_core_destroy_tis);
-int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
- u32 *rmpn)
-{
- u32 out[MLX5_ST_SZ_DW(create_rmp_out)] = {0};
- int err;
-
- MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
- err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
- if (!err)
- *rmpn = MLX5_GET(create_rmp_out, out, rmpn);
-
- return err;
-}
-
-int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen)
-{
- u32 out[MLX5_ST_SZ_DW(modify_rmp_out)] = {0};
-
- MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
- return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-}
-
-int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn)
-{
- u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)] = {0};
- u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {0};
-
- MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
- MLX5_SET(destroy_rmp_in, in, rmpn, rmpn);
- return mlx5_cmd_exec(dev, in, sizeof(in), out,
- sizeof(out));
-}
-
-int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out)
-{
- u32 in[MLX5_ST_SZ_DW(query_rmp_in)] = {0};
- int outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
-
- MLX5_SET(query_rmp_in, in, opcode, MLX5_CMD_OP_QUERY_RMP);
- MLX5_SET(query_rmp_in, in, rmpn, rmpn);
- return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
-int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm)
-{
- void *in;
- void *rmpc;
- void *wq;
- void *bitmask;
- int err;
-
- in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
- if (!in)
- return -ENOMEM;
-
- rmpc = MLX5_ADDR_OF(modify_rmp_in, in, ctx);
- bitmask = MLX5_ADDR_OF(modify_rmp_in, in, bitmask);
- wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
-
- MLX5_SET(modify_rmp_in, in, rmp_state, MLX5_RMPC_STATE_RDY);
- MLX5_SET(modify_rmp_in, in, rmpn, rmpn);
- MLX5_SET(wq, wq, lwm, lwm);
- MLX5_SET(rmp_bitmask, bitmask, lwm, 1);
- MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
-
- err = mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
-
- kvfree(in);
-
- return err;
-}
-
-int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
- u32 *xsrqn)
-{
- u32 out[MLX5_ST_SZ_DW(create_xrc_srq_out)] = {0};
- int err;
-
- MLX5_SET(create_xrc_srq_in, in, opcode, MLX5_CMD_OP_CREATE_XRC_SRQ);
- err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
- if (!err)
- *xsrqn = MLX5_GET(create_xrc_srq_out, out, xrc_srqn);
-
- return err;
-}
-
-int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 xsrqn)
-{
- u32 in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)] = {0};
- u32 out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
-
- MLX5_SET(destroy_xrc_srq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRC_SRQ);
- MLX5_SET(destroy_xrc_srq_in, in, xrc_srqn, xsrqn);
- return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u16 lwm)
-{
- u32 in[MLX5_ST_SZ_DW(arm_xrc_srq_in)] = {0};
- u32 out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
-
- MLX5_SET(arm_xrc_srq_in, in, opcode, MLX5_CMD_OP_ARM_XRC_SRQ);
- MLX5_SET(arm_xrc_srq_in, in, xrc_srqn, xsrqn);
- MLX5_SET(arm_xrc_srq_in, in, lwm, lwm);
- MLX5_SET(arm_xrc_srq_in, in, op_mod,
- MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
- return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
u32 *rqtn)
{
return mlx5_cqwq_ctr2ix(wq, wq->cc);
}
-static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
+static inline struct mlx5_cqe64 *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
{
return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
}
} tasklet_ctx;
int reset_notify_added;
struct list_head reset_notify;
- struct mlx5_eq *eq;
+ struct mlx5_eq_comp *eq;
u16 uid;
};
MLX5_PFAULT_SUBTYPE_RDMA = 1,
};
+enum wqe_page_fault_type {
+ MLX5_WQE_PF_TYPE_RMP = 0,
+ MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE = 1,
+ MLX5_WQE_PF_TYPE_RESP = 2,
+ MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC = 3,
+};
+
enum {
MLX5_PERM_LOCAL_READ = 1 << 2,
MLX5_PERM_LOCAL_WRITE = 1 << 3,
MLX5_EVENT_QUEUE_TYPE_DCT = 6,
};
+/* mlx5 components can subscribe to any one of these events via
+ * mlx5_eq_notifier_register API.
+ */
enum mlx5_event {
+ /* Special value to subscribe to any event */
+ MLX5_EVENT_TYPE_NOTIFY_ANY = 0x0,
+ /* HW events enum start: comp events are not subscribable */
MLX5_EVENT_TYPE_COMP = 0x0,
-
+ /* HW Async events enum start: subscribable events */
MLX5_EVENT_TYPE_PATH_MIG = 0x01,
MLX5_EVENT_TYPE_COMM_EST = 0x02,
MLX5_EVENT_TYPE_SQ_DRAINED = 0x03,
MLX5_EVENT_TYPE_TEMP_WARN_EVENT = 0x17,
MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19,
MLX5_EVENT_TYPE_GENERAL_EVENT = 0x22,
+ MLX5_EVENT_TYPE_MONITOR_COUNTER = 0x24,
MLX5_EVENT_TYPE_PPS_EVENT = 0x25,
MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a,
MLX5_EVENT_TYPE_FPGA_QP_ERROR = 0x21,
MLX5_EVENT_TYPE_DEVICE_TRACER = 0x26,
+
+ MLX5_EVENT_TYPE_MAX = MLX5_EVENT_TYPE_DEVICE_TRACER + 1,
};
enum {
return (cqe->op_own >> 2) & 0x3;
}
+static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe)
+{
+ return cqe->op_own >> 4;
+}
+
static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe)
{
return (cqe->lro_tcppsh_abort_dupack >> 6) & 1;
#include <linux/mempool.h>
#include <linux/interrupt.h>
#include <linux/idr.h>
+#include <linux/notifier.h>
#include <linux/mlx5/device.h>
#include <linux/mlx5/doorbell.h>
-#include <linux/mlx5/srq.h>
+#include <linux/mlx5/eq.h>
#include <linux/timecounter.h>
#include <linux/ptp_clock_kernel.h>
MLX5_MAX_PORTS = 2,
};
-enum {
- MLX5_EQ_VEC_PAGES = 0,
- MLX5_EQ_VEC_CMD = 1,
- MLX5_EQ_VEC_ASYNC = 2,
- MLX5_EQ_VEC_PFAULT = 3,
- MLX5_EQ_VEC_COMP_BASE,
-};
-
-enum {
- MLX5_MAX_IRQ_NAME = 32
-};
-
enum {
MLX5_ATOMIC_MODE_OFFSET = 16,
MLX5_ATOMIC_MODE_IB_COMP = 1,
};
enum mlx5_dev_event {
- MLX5_DEV_EVENT_SYS_ERROR,
- MLX5_DEV_EVENT_PORT_UP,
- MLX5_DEV_EVENT_PORT_DOWN,
- MLX5_DEV_EVENT_PORT_INITIALIZED,
- MLX5_DEV_EVENT_LID_CHANGE,
- MLX5_DEV_EVENT_PKEY_CHANGE,
- MLX5_DEV_EVENT_GUID_CHANGE,
- MLX5_DEV_EVENT_CLIENT_REREG,
- MLX5_DEV_EVENT_PPS,
- MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT,
+ MLX5_DEV_EVENT_SYS_ERROR = 128, /* 0 - 127 are FW events */
};
enum mlx5_port_status {
MLX5_PORT_DOWN = 2,
};
-enum mlx5_eq_type {
- MLX5_EQ_TYPE_COMP,
- MLX5_EQ_TYPE_ASYNC,
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- MLX5_EQ_TYPE_PF,
-#endif
-};
-
struct mlx5_bfreg_info {
u32 *sys_pages;
int num_low_latency_bfregs;
};
struct mlx5_cmd {
+ struct mlx5_nb nb;
+
void *cmd_alloc_buf;
dma_addr_t alloc_dma;
int alloc_size;
u8 log_frag_strides;
};
-struct mlx5_eq_tasklet {
- struct list_head list;
- struct list_head process_list;
- struct tasklet_struct task;
- /* lock on completion tasklet list */
- spinlock_t lock;
-};
-
-struct mlx5_eq_pagefault {
- struct work_struct work;
- /* Pagefaults lock */
- spinlock_t lock;
- struct workqueue_struct *wq;
- mempool_t *pool;
-};
-
-struct mlx5_cq_table {
- /* protect radix tree */
- spinlock_t lock;
- struct radix_tree_root tree;
-};
-
-struct mlx5_eq {
- struct mlx5_core_dev *dev;
- struct mlx5_cq_table cq_table;
- __be32 __iomem *doorbell;
- u32 cons_index;
- struct mlx5_frag_buf buf;
- int size;
- unsigned int irqn;
- u8 eqn;
- int nent;
- u64 mask;
- struct list_head list;
- int index;
- struct mlx5_rsc_debug *dbg;
- enum mlx5_eq_type type;
- union {
- struct mlx5_eq_tasklet tasklet_ctx;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- struct mlx5_eq_pagefault pf_ctx;
-#endif
- };
-};
-
struct mlx5_core_psv {
u32 psv_idx;
struct psv_layout {
struct completion free;
};
-struct mlx5_core_srq {
- struct mlx5_core_rsc_common common; /* must be first */
- u32 srqn;
- int max;
- size_t max_gs;
- size_t max_avail_gather;
- int wqe_shift;
- void (*event) (struct mlx5_core_srq *, enum mlx5_event);
-
- atomic_t refcount;
- struct completion free;
- u16 uid;
-};
-
-struct mlx5_eq_table {
- void __iomem *update_ci;
- void __iomem *update_arm_ci;
- struct list_head comp_eqs_list;
- struct mlx5_eq pages_eq;
- struct mlx5_eq async_eq;
- struct mlx5_eq cmd_eq;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- struct mlx5_eq pfault_eq;
-#endif
- int num_comp_vectors;
- /* protect EQs list
- */
- spinlock_t lock;
-};
-
struct mlx5_uars_page {
void __iomem *map;
bool wc;
};
struct mlx5_qp_table {
- /* protect radix tree
- */
- spinlock_t lock;
- struct radix_tree_root tree;
-};
+ struct notifier_block nb;
-struct mlx5_srq_table {
/* protect radix tree
*/
spinlock_t lock;
int enabled_vfs;
};
-struct mlx5_irq_info {
- cpumask_var_t mask;
- char name[MLX5_MAX_IRQ_NAME];
-};
-
struct mlx5_fc_stats {
spinlock_t counters_idr_lock; /* protects counters_idr */
struct idr counters_idr;
unsigned long sampling_interval; /* jiffies */
};
+struct mlx5_events;
struct mlx5_mpfs;
struct mlx5_eswitch;
struct mlx5_lag;
-struct mlx5_pagefault;
+struct mlx5_eq_table;
struct mlx5_rate_limit {
u32 rate;
struct mlx5_rl_entry *rl_entry;
};
-enum port_module_event_status_type {
- MLX5_MODULE_STATUS_PLUGGED = 0x1,
- MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
- MLX5_MODULE_STATUS_ERROR = 0x3,
- MLX5_MODULE_STATUS_NUM = 0x3,
-};
-
-enum port_module_event_error_type {
- MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED,
- MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE,
- MLX5_MODULE_EVENT_ERROR_BUS_STUCK,
- MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT,
- MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST,
- MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER,
- MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE,
- MLX5_MODULE_EVENT_ERROR_BAD_CABLE,
- MLX5_MODULE_EVENT_ERROR_UNKNOWN,
- MLX5_MODULE_EVENT_ERROR_NUM,
-};
-
-struct mlx5_port_module_event_stats {
- u64 status_counters[MLX5_MODULE_STATUS_NUM];
- u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM];
-};
-
struct mlx5_priv {
char name[MLX5_MAX_NAME_LEN];
- struct mlx5_eq_table eq_table;
- struct mlx5_irq_info *irq_info;
+ struct mlx5_eq_table *eq_table;
/* pages stuff */
+ struct mlx5_nb pg_nb;
struct workqueue_struct *pg_wq;
struct rb_root page_root;
int fw_pages;
struct mlx5_core_health health;
- struct mlx5_srq_table srq_table;
-
/* start: qp staff */
struct mlx5_qp_table qp_table;
struct dentry *qp_debugfs;
struct list_head dev_list;
struct list_head ctx_list;
spinlock_t ctx_lock;
-
- struct list_head waiting_events_list;
- bool is_accum_events;
+ struct mlx5_events *events;
struct mlx5_flow_steering *steering;
struct mlx5_mpfs *mpfs;
struct mlx5_fc_stats fc_stats;
struct mlx5_rl_table rl_table;
- struct mlx5_port_module_event_stats pme_stats;
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- void (*pfault)(struct mlx5_core_dev *dev,
- void *context,
- struct mlx5_pagefault *pfault);
- void *pfault_ctx;
- struct srcu_struct pfault_srcu;
-#endif
struct mlx5_bfreg_data bfregs;
struct mlx5_uars_page *uar;
};
MLX5_PFAULT_RDMA = 1 << 2,
};
-/* Contains the details of a pagefault. */
-struct mlx5_pagefault {
- u32 bytes_committed;
- u32 token;
- u8 event_subtype;
- u8 type;
- union {
- /* Initiator or send message responder pagefault details. */
- struct {
- /* Received packet size, only valid for responders. */
- u32 packet_size;
- /*
- * Number of resource holding WQE, depends on type.
- */
- u32 wq_num;
- /*
- * WQE index. Refers to either the send queue or
- * receive queue, according to event_subtype.
- */
- u16 wqe_index;
- } wqe;
- /* RDMA responder pagefault details */
- struct {
- u32 r_key;
- /*
- * Received packet size, minimal size page fault
- * resolution required for forward progress.
- */
- u32 packet_size;
- u32 rdma_op_len;
- u64 rdma_va;
- } rdma;
- };
-
- struct mlx5_eq *eq;
- struct work_struct work;
-};
-
struct mlx5_td {
struct list_head tirs_list;
u32 tdn;
};
struct mlx5_clock {
+ struct mlx5_core_dev *mdev;
+ struct mlx5_nb pps_nb;
seqlock_t lock;
struct cyclecounter cycles;
struct timecounter tc;
u32 nominal_c_mult;
unsigned long overflow_period;
struct delayed_work overflow_work;
- struct mlx5_core_dev *mdev;
struct ptp_clock *ptp;
struct ptp_clock_info ptp_info;
struct mlx5_pps pps_info;
/* sync interface state */
struct mutex intf_state_mutex;
unsigned long intf_state;
- void (*event) (struct mlx5_core_dev *dev,
- enum mlx5_dev_event event,
- unsigned long param);
struct mlx5_priv priv;
struct mlx5_profile *profile;
atomic_t num_qps;
} roce;
#ifdef CONFIG_MLX5_FPGA
struct mlx5_fpga_device *fpga;
-#endif
-#ifdef CONFIG_RFS_ACCEL
- struct cpu_rmap *rmap;
#endif
struct mlx5_clock clock;
struct mlx5_ib_clock_info *clock_info;
gfp_t flags, int npages);
void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev,
struct mlx5_cmd_mailbox *head);
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *in);
-int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq);
-int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- struct mlx5_srq_attr *out);
-int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
- u16 lwm, int is_srq);
void mlx5_init_mkey_table(struct mlx5_core_dev *dev);
void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev);
int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn);
int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
u16 opmod, u8 port);
-void mlx5_pagealloc_init(struct mlx5_core_dev *dev);
+int mlx5_pagealloc_init(struct mlx5_core_dev *dev);
void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev);
-int mlx5_pagealloc_start(struct mlx5_core_dev *dev);
+void mlx5_pagealloc_start(struct mlx5_core_dev *dev);
void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
s32 npages);
void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas);
void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
-void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
-void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
-struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
unsigned int *irqn);
int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
bool map_wc, bool fast_path);
void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
+unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev);
+struct cpumask *
+mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector);
unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev);
int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
u8 roce_version, u8 roce_l3_type, const u8 *gid,
void (*remove)(struct mlx5_core_dev *dev, void *context);
int (*attach)(struct mlx5_core_dev *dev, void *context);
void (*detach)(struct mlx5_core_dev *dev, void *context);
- void (*event)(struct mlx5_core_dev *dev, void *context,
- enum mlx5_dev_event event, unsigned long param);
- void (*pfault)(struct mlx5_core_dev *dev,
- void *context,
- struct mlx5_pagefault *pfault);
- void * (*get_dev)(void *context);
int protocol;
struct list_head list;
};
-void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol);
int mlx5_register_interface(struct mlx5_interface *intf);
void mlx5_unregister_interface(struct mlx5_interface *intf);
+int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
+int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
+
int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
};
-static inline const struct cpumask *
-mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
-{
- return dev->priv.irq_info[vector].mask;
-}
-
#endif /* MLX5_DRIVER_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef MLX5_CORE_EQ_H
+#define MLX5_CORE_EQ_H
+
+enum {
+ MLX5_EQ_PAGEREQ_IDX = 0,
+ MLX5_EQ_CMD_IDX = 1,
+ MLX5_EQ_ASYNC_IDX = 2,
+ /* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */
+ MLX5_EQ_PFAULT_IDX = 3,
+ MLX5_EQ_MAX_ASYNC_EQS,
+ /* completion eqs vector indices start here */
+ MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
+};
+
+#define MLX5_NUM_CMD_EQE (32)
+#define MLX5_NUM_ASYNC_EQE (0x1000)
+#define MLX5_NUM_SPARE_EQE (0x80)
+
+struct mlx5_eq;
+struct mlx5_core_dev;
+
+struct mlx5_eq_param {
+ u8 index;
+ int nent;
+ u64 mask;
+ void *context;
+ irq_handler_t handler;
+};
+
+struct mlx5_eq *
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+ struct mlx5_eq_param *param);
+int
+mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+
+struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc);
+void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm);
+
+/* The HCA will think the queue has overflowed if we
+ * don't tell it we've been processing events. We
+ * create EQs with MLX5_NUM_SPARE_EQE extra entries,
+ * so we must update our consumer index at
+ * least that often.
+ *
+ * mlx5_eq_update_cc must be called on every EQE @EQ irq handler
+ */
+static inline u32 mlx5_eq_update_cc(struct mlx5_eq *eq, u32 cc)
+{
+ if (unlikely(cc >= MLX5_NUM_SPARE_EQE)) {
+ mlx5_eq_update_ci(eq, cc, 0);
+ cc = 0;
+ }
+ return cc;
+}
+
+struct mlx5_nb {
+ struct notifier_block nb;
+ u8 event_type;
+};
+
+#define mlx5_nb_cof(ptr, type, member) \
+ (container_of(container_of(ptr, struct mlx5_nb, nb), type, member))
+
+#define MLX5_NB_INIT(name, handler, event) do { \
+ (name)->nb.notifier_call = handler; \
+ (name)->event_type = MLX5_EVENT_TYPE_##event; \
+} while (0)
+
+#endif /* MLX5_CORE_EQ_H */
u32 match_value[MLX5_ST_SZ_DW(fte_match_param)];
};
+enum {
+ MLX5_FLOW_DEST_VPORT_VHCA_ID = BIT(0),
+ MLX5_FLOW_DEST_VPORT_REFORMAT_ID = BIT(1),
+};
+
struct mlx5_flow_destination {
enum mlx5_flow_destination_type type;
union {
struct {
u16 num;
u16 vhca_id;
- bool vhca_id_valid;
+ u32 reformat_id;
+ u8 flags;
} vport;
};
};
MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771,
MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772,
MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773,
+ MLX5_CMD_OP_SET_MONITOR_COUNTER = 0x774,
+ MLX5_CMD_OP_ARM_MONITOR_COUNTER = 0x775,
MLX5_CMD_OP_SET_PP_RATE_LIMIT = 0x780,
MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781,
MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782,
u8 reformat_l3_tunnel_to_l2[0x1];
u8 reformat_l2_to_l3_tunnel[0x1];
u8 reformat_and_modify_action[0x1];
- u8 reserved_at_14[0xb];
+ u8 reserved_at_15[0xb];
u8 reserved_at_20[0x2];
u8 log_max_ft_size[0x6];
u8 log_max_modify_header_context[0x8];
union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6;
};
+struct mlx5_ifc_nvgre_key_bits {
+ u8 hi[0x18];
+ u8 lo[0x8];
+};
+
+union mlx5_ifc_gre_key_bits {
+ struct mlx5_ifc_nvgre_key_bits nvgre;
+ u8 key[0x20];
+};
+
struct mlx5_ifc_fte_match_set_misc_bits {
u8 reserved_at_0[0x8];
u8 source_sqn[0x18];
u8 reserved_at_64[0xc];
u8 gre_protocol[0x10];
- u8 gre_key_h[0x18];
- u8 gre_key_l[0x8];
+ union mlx5_ifc_gre_key_bits gre_key;
u8 vxlan_vni[0x18];
u8 reserved_at_b8[0x8];
u8 fdb_multi_path_to_table[0x1];
u8 reserved_at_1d[0x1];
u8 multi_fdb_encap[0x1];
- u8 reserved_at_1e[0x1e1];
+ u8 reserved_at_1f[0x1e1];
struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb;
u8 vxlan_encap_decap[0x1];
u8 nvgre_encap_decap[0x1];
- u8 reserved_at_22[0x9];
+ u8 reserved_at_22[0x1];
+ u8 log_max_fdb_encap_uplink[0x5];
+ u8 reserved_at_21[0x3];
u8 log_max_packet_reformat_context[0x5];
u8 reserved_2b[0x6];
u8 max_encap_header_size[0xa];
struct mlx5_ifc_calc_op calc2;
struct mlx5_ifc_calc_op calc3;
- u8 reserved_at_e0[0x720];
+ u8 reserved_at_c0[0x720];
};
enum {
MLX5_CAP_UMR_FENCE_NONE = 0x2,
};
+enum {
+ MLX5_UCTX_CAP_RAW_TX = 1UL << 0,
+};
+
struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_0[0x30];
u8 vhca_id[0x10];
u8 vector_calc[0x1];
u8 umr_ptr_rlky[0x1];
u8 imaicl[0x1];
- u8 reserved_at_232[0x4];
+ u8 qp_packet_based[0x1];
+ u8 reserved_at_233[0x3];
u8 qkv[0x1];
u8 pkv[0x1];
u8 set_deth_sqpn[0x1];
u8 num_vhca_ports[0x8];
u8 reserved_at_618[0x6];
u8 sw_owner_id[0x1];
- u8 reserved_at_61f[0x1e1];
+ u8 reserved_at_61f[0x1];
+
+ u8 max_num_of_monitor_counters[0x10];
+ u8 num_ppcnt_monitor_counters[0x10];
+
+ u8 reserved_at_640[0x10];
+ u8 num_q_monitor_counters[0x10];
+
+ u8 reserved_at_660[0x40];
+
+ u8 uctx_cap[0x20];
+
+ u8 reserved_at_6c0[0x140];
};
enum mlx5_flow_destination_type {
struct mlx5_ifc_dest_format_struct_bits {
u8 destination_type[0x8];
u8 destination_id[0x18];
+
u8 destination_eswitch_owner_vhca_id_valid[0x1];
- u8 reserved_at_21[0xf];
+ u8 packet_reformat[0x1];
+ u8 reserved_at_22[0xe];
u8 destination_eswitch_owner_vhca_id[0x10];
};
u8 reserved_at_20[0x20];
};
+struct mlx5_ifc_extended_dest_format_bits {
+ struct mlx5_ifc_dest_format_struct_bits destination_entry;
+
+ u8 packet_reformat_id[0x20];
+
+ u8 reserved_at_60[0x20];
+};
+
union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits {
struct mlx5_ifc_dest_format_struct_bits dest_format_struct;
struct mlx5_ifc_flow_counter_list_bits flow_counter_list;
u8 st[0x8];
u8 reserved_at_10[0x3];
u8 pm_state[0x2];
- u8 reserved_at_15[0x3];
+ u8 reserved_at_15[0x1];
+ u8 req_e2e_credit_mode[0x2];
u8 offload_type[0x4];
u8 end_padding_mode[0x2];
u8 reserved_at_1e[0x2];
u8 reserved_at_60[0x10];
u8 action[0x10];
- u8 reserved_at_80[0x8];
+ u8 extended_destination[0x1];
+ u8 reserved_at_80[0x7];
u8 destination_list_size[0x18];
u8 reserved_at_a0[0x8];
MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1,
};
+struct mlx5_ifc_arm_monitor_counter_in_bits {
+ u8 opcode[0x10];
+ u8 uid[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0x20];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_arm_monitor_counter_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+enum {
+ MLX5_QUERY_MONITOR_CNT_TYPE_PPCNT = 0x0,
+ MLX5_QUERY_MONITOR_CNT_TYPE_Q_COUNTER = 0x1,
+};
+
+enum mlx5_monitor_counter_ppcnt {
+ MLX5_QUERY_MONITOR_PPCNT_IN_RANGE_LENGTH_ERRORS = 0X0,
+ MLX5_QUERY_MONITOR_PPCNT_OUT_OF_RANGE_LENGTH_FIELD = 0X1,
+ MLX5_QUERY_MONITOR_PPCNT_FRAME_TOO_LONG_ERRORS = 0X2,
+ MLX5_QUERY_MONITOR_PPCNT_FRAME_CHECK_SEQUENCE_ERRORS = 0X3,
+ MLX5_QUERY_MONITOR_PPCNT_ALIGNMENT_ERRORS = 0X4,
+ MLX5_QUERY_MONITOR_PPCNT_IF_OUT_DISCARDS = 0X5,
+};
+
+enum {
+ MLX5_QUERY_MONITOR_Q_COUNTER_RX_OUT_OF_BUFFER = 0X4,
+};
+
+struct mlx5_ifc_monitor_counter_output_bits {
+ u8 reserved_at_0[0x4];
+ u8 type[0x4];
+ u8 reserved_at_8[0x8];
+ u8 counter[0x10];
+
+ u8 counter_group_id[0x20];
+};
+
+#define MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 (6)
+#define MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1 (1)
+#define MLX5_CMD_SET_MONITOR_NUM_COUNTER (MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 +\
+ MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1)
+
+struct mlx5_ifc_set_monitor_counter_in_bits {
+ u8 opcode[0x10];
+ u8 uid[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0x10];
+ u8 num_of_counters[0x10];
+
+ u8 reserved_at_60[0x20];
+
+ struct mlx5_ifc_monitor_counter_output_bits monitor_counter[MLX5_CMD_SET_MONITOR_NUM_COUNTER];
+};
+
+struct mlx5_ifc_set_monitor_counter_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
struct mlx5_ifc_query_vport_state_in_bits {
u8 opcode[0x10];
u8 reserved_at_10[0x10];
struct mlx5_ifc_modify_nic_vport_field_select_bits {
u8 reserved_at_0[0x12];
u8 affiliation[0x1];
- u8 reserved_at_e[0x1];
+ u8 reserved_at_13[0x1];
u8 disable_uc_local_lb[0x1];
u8 disable_mc_local_lb[0x1];
u8 node_guid[0x1];
u8 dcbx_cee_cap[0x1];
u8 dcbx_ieee_cap[0x1];
u8 dcbx_standby_cap[0x1];
- u8 reserved_at_0[0x5];
+ u8 reserved_at_3[0x5];
u8 port_number[0x8];
u8 reserved_at_10[0xa];
u8 max_application_table_size[6];
struct mlx5_ifc_uctx_bits {
u8 modify_field_select[0x40];
- u8 reserved_at_40[0x1c0];
+ u8 cap[0x20];
+
+ u8 reserved_at_60[0x1a0];
};
struct mlx5_ifc_create_umem_in_bits {
#define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
-#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF
-#define PORT_MODULE_EVENT_ERROR_TYPE_MASK 0xF
-
int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
int ptys_size, int proto_mask, u8 local_port);
int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
int reset, void *out, int out_size);
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+ int res_num,
+ enum mlx5_res_type res_type);
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res);
+
static inline const char *mlx5_qp_type_str(int type)
{
switch (type) {
+++ /dev/null
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. 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 MLX5_SRQ_H
-#define MLX5_SRQ_H
-
-#include <linux/mlx5/driver.h>
-
-enum {
- MLX5_SRQ_FLAG_ERR = (1 << 0),
- MLX5_SRQ_FLAG_WQ_SIG = (1 << 1),
- MLX5_SRQ_FLAG_RNDV = (1 << 2),
-};
-
-struct mlx5_srq_attr {
- u32 type;
- u32 flags;
- u32 log_size;
- u32 wqe_shift;
- u32 log_page_size;
- u32 wqe_cnt;
- u32 srqn;
- u32 xrcd;
- u32 page_offset;
- u32 cqn;
- u32 pd;
- u32 lwm;
- u32 user_index;
- u64 db_record;
- __be64 *pas;
- u32 tm_log_list_size;
- u32 tm_next_tag;
- u32 tm_hw_phase_cnt;
- u32 tm_sw_phase_cnt;
- u16 uid;
-};
-
-struct mlx5_core_dev;
-
-void mlx5_init_srq_table(struct mlx5_core_dev *dev);
-void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev);
-
-#endif /* MLX5_SRQ_H */
int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in,
int inlen);
void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn);
-int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
- u32 *rmpn);
-int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen);
-int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn);
-int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
-int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
-int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
- u32 *rmpn);
-int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 rmpn);
-int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
-
int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
u32 *rqtn);
int mlx5_core_modify_rqt(struct mlx5_core_dev *dev, u32 rqtn, u32 *in,
projects / linux-2.6-block.git / commitdiff