scsi: cxlflash: Flush pending commands in cleanup path

When the AFU is reset in an error path, pending scsi commands can be
silently dropped without completion or a formal abort. This puts the onus
on the cxlflash driver to notify mid-layer and indicating that the command
can be retried.

Once the card has been quiesced, the hardware send queue lock is acquired
to prevent any data movement while the pending commands are processed.

Signed-off-by: Uma Krishnan <ukrishn@linux.vnet.ibm.com>
Acked-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index 3eaa3be43d24164606ac2b44bdae3d5ca43670e5..11a5b0a10a341f2437185e6f917deeeba154ef5f 100644 (file)
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -157,7 +157,9 @@ struct afu_cmd {
        struct list_head queue;
        u32 hwq_index;
 
-       u8 cmd_tmf:1;
+       u8 cmd_tmf:1,
+          cmd_aborted:1;
+
        struct list_head list;  /* Pending commands link */
 
        /* As per the SISLITE spec the IOARCB EA has to be 16-byte aligned.
@@ -176,6 +178,7 @@ static inline struct afu_cmd *sc_to_afucz(struct scsi_cmnd *sc)
        struct afu_cmd *afuc = sc_to_afuc(sc);
 
        memset(afuc, 0, sizeof(*afuc));
+       INIT_LIST_HEAD(&afuc->queue);
        return afuc;
 }
 

diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 1446fabe4cf616ae227309c6031851b4608a335c..0a3de42310eccbd16a1a275ca1123d9a4d53edff 100644 (file)
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -193,6 +193,36 @@ static void cmd_complete(struct afu_cmd *cmd)
                complete(&cmd->cevent);
 }
 
+/**
+ * flush_pending_cmds() - flush all pending commands on this hardware queue
+ * @hwq:       Hardware queue to flush.
+ *
+ * The hardware send queue lock associated with this hardware queue must be
+ * held when calling this routine.
+ */
+static void flush_pending_cmds(struct hwq *hwq)
+{
+       struct afu_cmd *cmd, *tmp;
+       struct scsi_cmnd *scp;
+
+       list_for_each_entry_safe(cmd, tmp, &hwq->pending_cmds, list) {
+               /* Bypass command when on a doneq, cmd_complete() will handle */
+               if (!list_empty(&cmd->queue))
+                       continue;
+
+               list_del(&cmd->list);
+
+               if (cmd->scp) {
+                       scp = cmd->scp;
+                       scp->result = (DID_IMM_RETRY << 16);
+                       scp->scsi_done(scp);
+               } else {
+                       cmd->cmd_aborted = true;
+                       complete(&cmd->cevent);
+               }
+       }
+}
+
 /**
  * context_reset() - reset context via specified register
  * @hwq:       Hardware queue owning the context to be reset.
@@ -357,6 +387,9 @@ static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
        if (!timeout)
                rc = -ETIMEDOUT;
 
+       if (cmd->cmd_aborted)
+               rc = -EAGAIN;
+
        if (unlikely(cmd->sa.ioasc != 0)) {
                dev_err(dev, "%s: cmd %02x failed, ioasc=%08x\n",
                        __func__, cmd->rcb.cdb[0], cmd->sa.ioasc);
@@ -702,6 +735,7 @@ static void term_mc(struct cxlflash_cfg *cfg, u32 index)
        struct afu *afu = cfg->afu;
        struct device *dev = &cfg->dev->dev;
        struct hwq *hwq;
+       ulong lock_flags;
 
        if (!afu) {
                dev_err(dev, "%s: returning with NULL afu\n", __func__);
@@ -719,6 +753,10 @@ static void term_mc(struct cxlflash_cfg *cfg, u32 index)
        if (index != PRIMARY_HWQ)
                WARN_ON(cxl_release_context(hwq->ctx));
        hwq->ctx = NULL;
+
+       spin_lock_irqsave(&hwq->hsq_slock, lock_flags);
+       flush_pending_cmds(hwq);
+       spin_unlock_irqrestore(&hwq->hsq_slock, lock_flags);
 }
 
 /**
@@ -2155,7 +2193,7 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 
        mutex_lock(&sync_active);
        atomic_inc(&afu->cmds_active);
-       buf = kzalloc(sizeof(*cmd) + __alignof__(*cmd) - 1, GFP_KERNEL);
+       buf = kmalloc(sizeof(*cmd) + __alignof__(*cmd) - 1, GFP_KERNEL);
        if (unlikely(!buf)) {
                dev_err(dev, "%s: no memory for command\n", __func__);
                rc = -ENOMEM;
@@ -2165,6 +2203,8 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
        cmd = (struct afu_cmd *)PTR_ALIGN(buf, __alignof__(*cmd));
 
 retry:
+       memset(cmd, 0, sizeof(*cmd));
+       INIT_LIST_HEAD(&cmd->queue);
        init_completion(&cmd->cevent);
        cmd->parent = afu;
        cmd->hwq_index = hwq->index;
@@ -2191,11 +2231,20 @@ retry:
        }
 
        rc = wait_resp(afu, cmd);
-       if (rc == -ETIMEDOUT) {
+       switch (rc) {
+       case -ETIMEDOUT:
                rc = afu->context_reset(hwq);
-               if (!rc && ++nretry < 2)
+               if (rc) {
+                       cxlflash_schedule_async_reset(cfg);
+                       break;
+               }
+               /* fall through to retry */
+       case -EAGAIN:
+               if (++nretry < 2)
                        goto retry;
-               cxlflash_schedule_async_reset(cfg);
+               /* fall through to exit */
+       default:
+               break;
        }
 
 out: