scsi: qla2xxx: Fix exchange oversubscription

[ Upstream commit 41e5afe51f75f2858f5563145348f6c26d307b8f ]

In large environment, it is possible to experience command timeout and
escalation of path recovery. Currently the driver does not track the number
of exchanges/commands sent to FW. If there is a delay for commands at the
head of the queue, then this will create back pressure for commands at the
back of the queue.

Check for exchange availability before command submission.

Fixes: 89c72f4245a8 ("scsi: qla2xxx: Add IOCB resource tracking")
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index a26a373be9da302290c36fed9fb26f5881459769..cd4eb11b07079a2e2d097503761c0903c6ba2fd2 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -660,7 +660,7 @@ enum {
 
 struct iocb_resource {
        u8 res_type;
-       u8 pad;
+       u8  exch_cnt;
        u16 iocb_cnt;
 };
 
@@ -3721,6 +3721,10 @@ struct qla_fw_resources {
        u16 iocbs_limit;
        u16 iocbs_qp_limit;
        u16 iocbs_used;
+       u16 exch_total;
+       u16 exch_limit;
+       u16 exch_used;
+       u16 pad;
 };
 
 #define QLA_IOCB_PCT_LIMIT 95

diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c
index 00ccc41cef147279e884e5eab3ba5143ac0a1905..d17ba6275b685d94aad28a47bc7b81d985e73d5c 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_edif.c
+++ b/drivers/scsi/qla2xxx/qla_edif.c
@@ -2989,9 +2989,10 @@ qla28xx_start_scsi_edif(srb_t *sp)
        tot_dsds = nseg;
        req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
 
-       sp->iores.res_type = RESOURCE_INI;
+       sp->iores.res_type = RESOURCE_IOCB | RESOURCE_EXCH;
+       sp->iores.exch_cnt = 1;
        sp->iores.iocb_cnt = req_cnt;
-       if (qla_get_iocbs(sp->qpair, &sp->iores))
+       if (qla_get_fw_resources(sp->qpair, &sp->iores))
                goto queuing_error;
 
        if (req->cnt < (req_cnt + 2)) {
@@ -3185,7 +3186,7 @@ queuing_error:
                mempool_free(sp->u.scmd.ct6_ctx, ha->ctx_mempool);
                sp->u.scmd.ct6_ctx = NULL;
        }
-       qla_put_iocbs(sp->qpair, &sp->iores);
+       qla_put_fw_resources(sp->qpair, &sp->iores);
        spin_unlock_irqrestore(lock, flags);
 
        return QLA_FUNCTION_FAILED;

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 432f47fc5e1f3ec385ff030f82b37ffabd6b550d..66e8a2e5dfaf605e3f1f0a0f0bc93992b8c8808c 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -128,12 +128,14 @@ static void qla24xx_abort_iocb_timeout(void *data)
                    sp->cmd_sp)) {
                        qpair->req->outstanding_cmds[handle] = NULL;
                        cmdsp_found = 1;
+                       qla_put_fw_resources(qpair, &sp->cmd_sp->iores);
                }
 
                /* removing the abort */
                if (qpair->req->outstanding_cmds[handle] == sp) {
                        qpair->req->outstanding_cmds[handle] = NULL;
                        sp_found = 1;
+                       qla_put_fw_resources(qpair, &sp->iores);
                        break;
                }
        }
@@ -2000,6 +2002,7 @@ qla2x00_tmf_iocb_timeout(void *data)
                for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) {
                        if (sp->qpair->req->outstanding_cmds[h] == sp) {
                                sp->qpair->req->outstanding_cmds[h] = NULL;
+                               qla_put_fw_resources(sp->qpair, &sp->iores);
                                break;
                        }
                }
@@ -3943,6 +3946,12 @@ void qla_init_iocb_limit(scsi_qla_host_t *vha)
        ha->base_qpair->fwres.iocbs_limit = limit;
        ha->base_qpair->fwres.iocbs_qp_limit = limit / num_qps;
        ha->base_qpair->fwres.iocbs_used = 0;
+
+       ha->base_qpair->fwres.exch_total = ha->orig_fw_xcb_count;
+       ha->base_qpair->fwres.exch_limit = (ha->orig_fw_xcb_count *
+                                           QLA_IOCB_PCT_LIMIT) / 100;
+       ha->base_qpair->fwres.exch_used  = 0;
+
        for (i = 0; i < ha->max_qpairs; i++) {
                if (ha->queue_pair_map[i])  {
                        ha->queue_pair_map[i]->fwres.iocbs_total =
@@ -3951,6 +3960,10 @@ void qla_init_iocb_limit(scsi_qla_host_t *vha)
                        ha->queue_pair_map[i]->fwres.iocbs_qp_limit =
                                limit / num_qps;
                        ha->queue_pair_map[i]->fwres.iocbs_used = 0;
+                       ha->queue_pair_map[i]->fwres.exch_total = ha->orig_fw_xcb_count;
+                       ha->queue_pair_map[i]->fwres.exch_limit =
+                               (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100;
+                       ha->queue_pair_map[i]->fwres.exch_used = 0;
                }
        }
 }

diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 5185dc5daf80d47cbf279faf95ce0e0a777603f8..2d5a275d8b00078a51597227554e7dd8c4320e0f 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -380,13 +380,16 @@ qla2xxx_get_fc4_priority(struct scsi_qla_host *vha)
 
 enum {
        RESOURCE_NONE,
-       RESOURCE_INI,
+       RESOURCE_IOCB  = BIT_0,
+       RESOURCE_EXCH = BIT_1,  /* exchange */
+       RESOURCE_FORCE = BIT_2,
 };
 
 static inline int
-qla_get_iocbs(struct qla_qpair *qp, struct iocb_resource *iores)
+qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 {
        u16 iocbs_used, i;
+       u16 exch_used;
        struct qla_hw_data *ha = qp->vha->hw;
 
        if (!ql2xenforce_iocb_limit) {
@@ -394,10 +397,7 @@ qla_get_iocbs(struct qla_qpair *qp, struct iocb_resource *iores)
                return 0;
        }
 
-       if ((iores->iocb_cnt + qp->fwres.iocbs_used) < qp->fwres.iocbs_qp_limit) {
-               qp->fwres.iocbs_used += iores->iocb_cnt;
-               return 0;
-       } else {
+       if ((iores->iocb_cnt + qp->fwres.iocbs_used) >= qp->fwres.iocbs_qp_limit) {
                /* no need to acquire qpair lock. It's just rough calculation */
                iocbs_used = ha->base_qpair->fwres.iocbs_used;
                for (i = 0; i < ha->max_qpairs; i++) {
@@ -405,30 +405,48 @@ qla_get_iocbs(struct qla_qpair *qp, struct iocb_resource *iores)
                                iocbs_used += ha->queue_pair_map[i]->fwres.iocbs_used;
                }
 
-               if ((iores->iocb_cnt + iocbs_used) < qp->fwres.iocbs_limit) {
-                       qp->fwres.iocbs_used += iores->iocb_cnt;
-                       return 0;
-               } else {
+               if ((iores->iocb_cnt + iocbs_used) >= qp->fwres.iocbs_limit) {
+                       iores->res_type = RESOURCE_NONE;
+                       return -ENOSPC;
+               }
+       }
+
+       if (iores->res_type & RESOURCE_EXCH) {
+               exch_used = ha->base_qpair->fwres.exch_used;
+               for (i = 0; i < ha->max_qpairs; i++) {
+                       if (ha->queue_pair_map[i])
+                               exch_used += ha->queue_pair_map[i]->fwres.exch_used;
+               }
+
+               if ((exch_used + iores->exch_cnt) >= qp->fwres.exch_limit) {
                        iores->res_type = RESOURCE_NONE;
                        return -ENOSPC;
                }
        }
+       qp->fwres.iocbs_used += iores->iocb_cnt;
+       qp->fwres.exch_used += iores->exch_cnt;
+       return 0;
 }
 
 static inline void
-qla_put_iocbs(struct qla_qpair *qp, struct iocb_resource *iores)
+qla_put_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
 {
-       switch (iores->res_type) {
-       case RESOURCE_NONE:
-               break;
-       default:
+       if (iores->res_type & RESOURCE_IOCB) {
                if (qp->fwres.iocbs_used >= iores->iocb_cnt) {
                        qp->fwres.iocbs_used -= iores->iocb_cnt;
                } else {
-                       // should not happen
+                       /* should not happen */
                        qp->fwres.iocbs_used = 0;
                }
-               break;
+       }
+
+       if (iores->res_type & RESOURCE_EXCH) {
+               if (qp->fwres.exch_used >= iores->exch_cnt) {
+                       qp->fwres.exch_used -= iores->exch_cnt;
+               } else {
+                       /* should not happen */
+                       qp->fwres.exch_used = 0;
+               }
        }
        iores->res_type = RESOURCE_NONE;
 }

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 42ce4e1fe7441fe8299e63a5ebaaeaebfe22992e..399ec8da2d73c3354cde61e96036f490efda6142 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -1589,9 +1589,10 @@ qla24xx_start_scsi(srb_t *sp)
        tot_dsds = nseg;
        req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
 
-       sp->iores.res_type = RESOURCE_INI;
+       sp->iores.res_type = RESOURCE_IOCB | RESOURCE_EXCH;
+       sp->iores.exch_cnt = 1;
        sp->iores.iocb_cnt = req_cnt;
-       if (qla_get_iocbs(sp->qpair, &sp->iores))
+       if (qla_get_fw_resources(sp->qpair, &sp->iores))
                goto queuing_error;
 
        if (req->cnt < (req_cnt + 2)) {
@@ -1678,7 +1679,7 @@ queuing_error:
        if (tot_dsds)
                scsi_dma_unmap(cmd);
 
-       qla_put_iocbs(sp->qpair, &sp->iores);
+       qla_put_fw_resources(sp->qpair, &sp->iores);
        spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
        return QLA_FUNCTION_FAILED;
@@ -1793,9 +1794,10 @@ qla24xx_dif_start_scsi(srb_t *sp)
        tot_prot_dsds = nseg;
        tot_dsds += nseg;
 
-       sp->iores.res_type = RESOURCE_INI;
+       sp->iores.res_type = RESOURCE_IOCB | RESOURCE_EXCH;
+       sp->iores.exch_cnt = 1;
        sp->iores.iocb_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
-       if (qla_get_iocbs(sp->qpair, &sp->iores))
+       if (qla_get_fw_resources(sp->qpair, &sp->iores))
                goto queuing_error;
 
        if (req->cnt < (req_cnt + 2)) {
@@ -1883,7 +1885,7 @@ queuing_error:
        }
        /* Cleanup will be performed by the caller (queuecommand) */
 
-       qla_put_iocbs(sp->qpair, &sp->iores);
+       qla_put_fw_resources(sp->qpair, &sp->iores);
        spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
        return QLA_FUNCTION_FAILED;
@@ -1952,9 +1954,10 @@ qla2xxx_start_scsi_mq(srb_t *sp)
        tot_dsds = nseg;
        req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
 
-       sp->iores.res_type = RESOURCE_INI;
+       sp->iores.res_type = RESOURCE_IOCB | RESOURCE_EXCH;
+       sp->iores.exch_cnt = 1;
        sp->iores.iocb_cnt = req_cnt;
-       if (qla_get_iocbs(sp->qpair, &sp->iores))
+       if (qla_get_fw_resources(sp->qpair, &sp->iores))
                goto queuing_error;
 
        if (req->cnt < (req_cnt + 2)) {
@@ -2041,7 +2044,7 @@ queuing_error:
        if (tot_dsds)
                scsi_dma_unmap(cmd);
 
-       qla_put_iocbs(sp->qpair, &sp->iores);
+       qla_put_fw_resources(sp->qpair, &sp->iores);
        spin_unlock_irqrestore(&qpair->qp_lock, flags);
 
        return QLA_FUNCTION_FAILED;
@@ -2171,9 +2174,10 @@ qla2xxx_dif_start_scsi_mq(srb_t *sp)
        tot_prot_dsds = nseg;
        tot_dsds += nseg;
 
-       sp->iores.res_type = RESOURCE_INI;
+       sp->iores.res_type = RESOURCE_IOCB | RESOURCE_EXCH;
+       sp->iores.exch_cnt = 1;
        sp->iores.iocb_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
-       if (qla_get_iocbs(sp->qpair, &sp->iores))
+       if (qla_get_fw_resources(sp->qpair, &sp->iores))
                goto queuing_error;
 
        if (req->cnt < (req_cnt + 2)) {
@@ -2260,7 +2264,7 @@ queuing_error:
        }
        /* Cleanup will be performed by the caller (queuecommand) */
 
-       qla_put_iocbs(sp->qpair, &sp->iores);
+       qla_put_fw_resources(sp->qpair, &sp->iores);
        spin_unlock_irqrestore(&qpair->qp_lock, flags);
 
        return QLA_FUNCTION_FAILED;

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index e19fde304e5c6891b44db73496f9fefe69643398..42d3d2de3d31fa8b68bc74f4b951b8b06754e2a8 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3197,7 +3197,7 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
                }
                return;
        }
-       qla_put_iocbs(sp->qpair, &sp->iores);
+       qla_put_fw_resources(sp->qpair, &sp->iores);
 
        if (sp->cmd_type != TYPE_SRB) {
                req->outstanding_cmds[handle] = NULL;
@@ -3618,7 +3618,6 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt)
        default:
                sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
                if (sp) {
-                       qla_put_iocbs(sp->qpair, &sp->iores);
                        sp->done(sp, res);
                        return 0;
                }

diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 02fdeb0d31ec4afed59a923a75670a8a1dbf6ef3..582d88dd59abec358130bd9926fa8ac0d14e2116 100644 (file)
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -445,13 +445,24 @@ static inline int qla2x00_start_nvme_mq(srb_t *sp)
                goto queuing_error;
        }
        req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
+
+       sp->iores.res_type = RESOURCE_IOCB | RESOURCE_EXCH;
+       sp->iores.exch_cnt = 1;
+       sp->iores.iocb_cnt = req_cnt;
+       if (qla_get_fw_resources(sp->qpair, &sp->iores)) {
+               rval = -EBUSY;
+               goto queuing_error;
+       }
+
        if (req->cnt < (req_cnt + 2)) {
                if (IS_SHADOW_REG_CAPABLE(ha)) {
                        cnt = *req->out_ptr;
                } else {
                        cnt = rd_reg_dword_relaxed(req->req_q_out);
-                       if (qla2x00_check_reg16_for_disconnect(vha, cnt))
+                       if (qla2x00_check_reg16_for_disconnect(vha, cnt)) {
+                               rval = -EBUSY;
                                goto queuing_error;
+                       }
                }
 
                if (req->ring_index < cnt)
@@ -600,6 +611,8 @@ static inline int qla2x00_start_nvme_mq(srb_t *sp)
                qla24xx_process_response_queue(vha, rsp);
 
 queuing_error:
+       if (rval)
+               qla_put_fw_resources(sp->qpair, &sp->iores);
        spin_unlock_irqrestore(&qpair->qp_lock, flags);
 
        return rval;