UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

RDMA/ocrdma: EQ full catastrophe avoidance 

Stale entries in the CQ being destroyed causes hardware to generate
EQEs indefinitely for a given CQ.  Thus causing uncontrolled execution
of irq_handler.  This patch fixes this using following sementics:

    * irq_handler will ring EQ doorbell atleast once and implement budgeting scheme.
    * cq_destroy will count number of valid entires during destroy and ring
      cq-db so that hardware does not generate uncontrolled EQE.
    * cq_destroy will synchronize with last running irq_handler instance.
    * arm_cq will always defer arming CQ till poll_cq, except for the first arm_cq call.
    * poll_cq will always ring cq-db with arm=SET if arm_cq was called prior to enter poll_cq.
    * poll_cq will always ring cq-db with arm=UNSET if arm_cq was not called prior to enter poll_cq.

Signed-off-by: Devesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: Selvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
This commit is contained in:
Devesh Sharma 2014-02-04 11:56:54 +05:30 committed by Roland Dreier
parent bc1b04ab34
commit ea61762679
4 changed files with 103 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
drivers/infiniband/hw/ocrdma/ocrdma.h
View File

@ -209,8 +209,8 @@ struct ocrdma_cq {
*/
u32 max_hw_cqe;
bool phase_change;
bool armed, solicited;
bool arm_needed;
bool deferred_arm, deferred_sol;
bool first_arm;
spinlock_t cq_lock ____cacheline_aligned; /* provide synchronization
* to cq polling
@ -223,6 +223,7 @@ struct ocrdma_cq {
struct ocrdma_ucontext *ucontext;
dma_addr_t pa;
u32 len;
u32 cqe_cnt;
/* head of all qp's sq and rq for which cqes need to be flushed
* by the software.
@ -436,4 +437,17 @@ static inline int ocrdma_resolve_dmac(struct ocrdma_dev *dev,
return 0;
}
static inline int ocrdma_get_eq_table_index(struct ocrdma_dev *dev,
int eqid)
{
int indx;
for (indx = 0; indx < dev->eq_cnt; indx++) {
if (dev->eq_tbl[indx].q.id == eqid)
return indx;
}
return -EINVAL;
}
#endif

53
drivers/infiniband/hw/ocrdma/ocrdma_hw.c
View File

@ -444,7 +444,7 @@ mbx_err:
return status;
}
static int ocrdma_get_irq(struct ocrdma_dev *dev, struct ocrdma_eq *eq)
int ocrdma_get_irq(struct ocrdma_dev *dev, struct ocrdma_eq *eq)
{
int irq;
@ -574,6 +574,7 @@ static int ocrdma_create_mq(struct ocrdma_dev *dev)
if (status)
goto alloc_err;
dev->eq_tbl[0].cq_cnt++;
status = ocrdma_mbx_mq_cq_create(dev, &dev->mq.cq, &dev->eq_tbl[0].q);
if (status)
goto mbx_cq_free;
@ -858,16 +859,8 @@ static void ocrdma_qp_cq_handler(struct ocrdma_dev *dev, u16 cq_idx)
BUG();
cq = dev->cq_tbl[cq_idx];
if (cq == NULL) {
pr_err("%s%d invalid id=0x%x\n", __func__, dev->id, cq_idx);
if (cq == NULL)
return;
}
spin_lock_irqsave(&cq->cq_lock, flags);
cq->armed = false;
cq->solicited = false;
spin_unlock_irqrestore(&cq->cq_lock, flags);
ocrdma_ring_cq_db(dev, cq->id, false, false, 0);
if (cq->ibcq.comp_handler) {
spin_lock_irqsave(&cq->comp_handler_lock, flags);
@ -892,27 +885,35 @@ static irqreturn_t ocrdma_irq_handler(int irq, void *handle)
struct ocrdma_dev *dev = eq->dev;
struct ocrdma_eqe eqe;
struct ocrdma_eqe *ptr;
u16 eqe_popped = 0;
u16 cq_id;
while (1) {
int budget = eq->cq_cnt;
do {
ptr = ocrdma_get_eqe(eq);
eqe = *ptr;
ocrdma_le32_to_cpu(&eqe, sizeof(eqe));
if ((eqe.id_valid & OCRDMA_EQE_VALID_MASK) == 0)
break;
eqe_popped += 1;
ptr->id_valid = 0;
/* ring eq doorbell as soon as its consumed. */
ocrdma_ring_eq_db(dev, eq->q.id, false, true, 1);
/* check whether its CQE or not. */
if ((eqe.id_valid & OCRDMA_EQE_FOR_CQE_MASK) == 0) {
cq_id = eqe.id_valid >> OCRDMA_EQE_RESOURCE_ID_SHIFT;
ocrdma_cq_handler(dev, cq_id);
}
ocrdma_eq_inc_tail(eq);
}
ocrdma_ring_eq_db(dev, eq->q.id, true, true, eqe_popped);
/* Ring EQ doorbell with num_popped to 0 to enable interrupts again. */
if (dev->nic_info.intr_mode == BE_INTERRUPT_MODE_INTX)
ocrdma_ring_eq_db(dev, eq->q.id, true, true, 0);
/* There can be a stale EQE after the last bound CQ is
* destroyed. EQE valid and budget == 0 implies this.
*/
if (budget)
budget--;
} while (budget);
ocrdma_ring_eq_db(dev, eq->q.id, true, true, 0);
return IRQ_HANDLED;
}
@ -1357,12 +1358,10 @@ static void ocrdma_unbind_eq(struct ocrdma_dev *dev, u16 eq_id)
int i;
mutex_lock(&dev->dev_lock);
for (i = 0; i < dev->eq_cnt; i++) {
if (dev->eq_tbl[i].q.id != eq_id)
continue;
dev->eq_tbl[i].cq_cnt -= 1;
break;
}
i = ocrdma_get_eq_table_index(dev, eq_id);
if (i == -EINVAL)
BUG();
dev->eq_tbl[i].cq_cnt -= 1;
mutex_unlock(&dev->dev_lock);
}
@ -1417,6 +1416,7 @@ int ocrdma_mbx_create_cq(struct ocrdma_dev *dev, struct ocrdma_cq *cq,
cq->eqn = ocrdma_bind_eq(dev);
cmd->cmd.req.rsvd_version = OCRDMA_CREATE_CQ_VER3;
cqe_count = cq->len / cqe_size;
cq->cqe_cnt = cqe_count;
if (cqe_count > 1024) {
/* Set cnt to 3 to indicate more than 1024 cq entries */
cmd->cmd.ev_cnt_flags |= (0x3 << OCRDMA_CREATE_CQ_CNT_SHIFT);
@ -1484,12 +1484,9 @@ int ocrdma_mbx_destroy_cq(struct ocrdma_dev *dev, struct ocrdma_cq *cq)
(cq->id << OCRDMA_DESTROY_CQ_QID_SHIFT) &
OCRDMA_DESTROY_CQ_QID_MASK;
ocrdma_unbind_eq(dev, cq->eqn);
status = ocrdma_mbx_cmd(dev, (struct ocrdma_mqe *)cmd);
if (status)
goto mbx_err;
ocrdma_unbind_eq(dev, cq->eqn);
dma_free_coherent(&dev->nic_info.pdev->dev, cq->len, cq->va, cq->pa);
mbx_err:
kfree(cmd);
return status;
}

1
drivers/infiniband/hw/ocrdma/ocrdma_hw.h
View File

@ -131,5 +131,6 @@ int ocrdma_qp_state_change(struct ocrdma_qp *, enum ib_qp_state new_state,
bool ocrdma_is_qp_in_sq_flushlist(struct ocrdma_cq *, struct ocrdma_qp *);
bool ocrdma_is_qp_in_rq_flushlist(struct ocrdma_cq *, struct ocrdma_qp *);
void ocrdma_flush_qp(struct ocrdma_qp *);
int ocrdma_get_irq(struct ocrdma_dev *dev, struct ocrdma_eq *eq);
#endif /* __OCRDMA_HW_H__ */

81
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
View File

@ -910,6 +910,7 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, int entries, int vector,
spin_lock_init(&cq->comp_handler_lock);
INIT_LIST_HEAD(&cq->sq_head);
INIT_LIST_HEAD(&cq->rq_head);
cq->first_arm = true;
if (ib_ctx) {
uctx = get_ocrdma_ucontext(ib_ctx);
@ -927,9 +928,7 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, int entries, int vector,
goto ctx_err;
}
cq->phase = OCRDMA_CQE_VALID;
cq->arm_needed = true;
dev->cq_tbl[cq->id] = cq;
return &cq->ibcq;
ctx_err:
@ -952,15 +951,52 @@ int ocrdma_resize_cq(struct ib_cq *ibcq, int new_cnt,
return status;
}
static void ocrdma_flush_cq(struct ocrdma_cq *cq)
{
int cqe_cnt;
int valid_count = 0;
unsigned long flags;
struct ocrdma_dev *dev = get_ocrdma_dev(cq->ibcq.device);
struct ocrdma_cqe *cqe = NULL;
cqe = cq->va;
cqe_cnt = cq->cqe_cnt;
/* Last irq might have scheduled a polling thread
* sync-up with it before hard flushing.
*/
spin_lock_irqsave(&cq->cq_lock, flags);
while (cqe_cnt) {
if (is_cqe_valid(cq, cqe))
valid_count++;
cqe++;
cqe_cnt--;
}
ocrdma_ring_cq_db(dev, cq->id, false, false, valid_count);
spin_unlock_irqrestore(&cq->cq_lock, flags);
}
int ocrdma_destroy_cq(struct ib_cq *ibcq)
{
int status;
struct ocrdma_cq *cq = get_ocrdma_cq(ibcq);
struct ocrdma_eq *eq = NULL;
struct ocrdma_dev *dev = get_ocrdma_dev(ibcq->device);
int pdid = 0;
u32 irq, indx;
dev->cq_tbl[cq->id] = NULL;
indx = ocrdma_get_eq_table_index(dev, cq->eqn);
if (indx == -EINVAL)
BUG();
eq = &dev->eq_tbl[indx];
irq = ocrdma_get_irq(dev, eq);
synchronize_irq(irq);
ocrdma_flush_cq(cq);
status = ocrdma_mbx_destroy_cq(dev, cq);
if (cq->ucontext) {
pdid = cq->ucontext->cntxt_pd->id;
ocrdma_del_mmap(cq->ucontext, (u64) cq->pa,
@ -969,7 +1005,6 @@ int ocrdma_destroy_cq(struct ib_cq *ibcq)
ocrdma_get_db_addr(dev, pdid),
dev->nic_info.db_page_size);
}
dev->cq_tbl[cq->id] = NULL;
kfree(cq);
return status;
@ -2705,10 +2740,18 @@ expand_cqe:
}
stop_cqe:
cq->getp = cur_getp;
if (polled_hw_cqes || expand || stop) {
ocrdma_ring_cq_db(dev, cq->id, cq->armed, cq->solicited,
if (cq->deferred_arm) {
ocrdma_ring_cq_db(dev, cq->id, true, cq->deferred_sol,
polled_hw_cqes);
cq->deferred_arm = false;
cq->deferred_sol = false;
} else {
/* We need to pop the CQE. No need to arm */
ocrdma_ring_cq_db(dev, cq->id, false, cq->deferred_sol,
polled_hw_cqes);
cq->deferred_sol = false;
}
return i;
}
@ -2780,30 +2823,28 @@ int ocrdma_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags cq_flags)
struct ocrdma_cq *cq = get_ocrdma_cq(ibcq);
struct ocrdma_dev *dev = get_ocrdma_dev(ibcq->device);
u16 cq_id;
u16 cur_getp;
struct ocrdma_cqe *cqe;
unsigned long flags;
bool arm_needed = false, sol_needed = false;
cq_id = cq->id;
spin_lock_irqsave(&cq->cq_lock, flags);
if (cq_flags & IB_CQ_NEXT_COMP || cq_flags & IB_CQ_SOLICITED)
cq->armed = true;
arm_needed = true;
if (cq_flags & IB_CQ_SOLICITED)
cq->solicited = true;
sol_needed = true;
cur_getp = cq->getp;
cqe = cq->va + cur_getp;
/* check whether any valid cqe exist or not, if not then safe to
* arm. If cqe is not yet consumed, then let it get consumed and then
* we arm it to avoid false interrupts.
*/
if (!is_cqe_valid(cq, cqe) || cq->arm_needed) {
cq->arm_needed = false;
ocrdma_ring_cq_db(dev, cq_id, cq->armed, cq->solicited, 0);
if (cq->first_arm) {
ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0);
cq->first_arm = false;
goto skip_defer;
}
cq->deferred_arm = true;
skip_defer:
cq->deferred_sol = sol_needed;
spin_unlock_irqrestore(&cq->cq_lock, flags);
return 0;
}