Merge branch 'fixes' into next

Signed-off-by: NVinod Koul <vkoul@kernel.org>

drivers/dma/idxd/idxd.h

@@ -292,6 +292,14 @@ struct idxd_desc {
 	struct idxd_wq *wq;
 };
 
+/*
+ * This is software defined error for the completion status. We overload the error code
+ * that will never appear in completion status and only SWERR register.
+ */
+enum idxd_completion_status {
+	IDXD_COMP_DESC_ABORT = 0xff,
+};
+
 #define confdev_to_idxd(dev) container_of(dev, struct idxd_device, conf_dev)
 #define confdev_to_wq(dev) container_of(dev, struct idxd_wq, conf_dev)
 
@@ -478,4 +486,10 @@ static inline void perfmon_init(void) {}
 static inline void perfmon_exit(void) {}
 #endif
 
+static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason)
+{
+	idxd_dma_complete_txd(desc, reason);
+	idxd_free_desc(desc->wq, desc);
+}
+
 #endif

drivers/dma/idxd/irq.c

@@ -245,12 +245,6 @@ static inline bool match_fault(struct idxd_desc *desc, u64 fault_addr)
 	return false;
 }
 
-static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason)
-{
-	idxd_dma_complete_txd(desc, reason);
-	idxd_free_desc(desc->wq, desc);
-}
-
 static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry,
 				     enum irq_work_type wtype,
 				     int *processed, u64 data)
@@ -272,8 +266,16 @@ static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry,
 		reason = IDXD_COMPLETE_DEV_FAIL;
 
 	llist_for_each_entry_safe(desc, t, head, llnode) {
-		if (desc->completion->status) {
-			if ((desc->completion->status & DSA_COMP_STATUS_MASK) != DSA_COMP_SUCCESS)
+		u8 status = desc->completion->status & DSA_COMP_STATUS_MASK;
+
+		if (status) {
+			if (unlikely(status == IDXD_COMP_DESC_ABORT)) {
+				complete_desc(desc, IDXD_COMPLETE_ABORT);
+				(*processed)++;
+				continue;
+			}
+
+			if (unlikely(status != DSA_COMP_SUCCESS))
 				match_fault(desc, data);
 			complete_desc(desc, reason);
 			(*processed)++;
@@ -329,7 +331,14 @@ static int irq_process_work_list(struct idxd_irq_entry *irq_entry,
 	spin_unlock_irqrestore(&irq_entry->list_lock, flags);
 
 	list_for_each_entry(desc, &flist, list) {
-		if ((desc->completion->status & DSA_COMP_STATUS_MASK) != DSA_COMP_SUCCESS)
+		u8 status = desc->completion->status & DSA_COMP_STATUS_MASK;
+
+		if (unlikely(status == IDXD_COMP_DESC_ABORT)) {
+			complete_desc(desc, IDXD_COMPLETE_ABORT);
+			continue;
+		}
+
+		if (unlikely(status != DSA_COMP_SUCCESS))
 			match_fault(desc, data);
 		complete_desc(desc, reason);
 	}

drivers/dma/idxd/submit.c

@@ -79,9 +79,64 @@ void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	sbitmap_queue_clear(&wq->sbq, desc->id, cpu);
 }
 
+static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
+					 struct idxd_desc *desc)
+{
+	struct idxd_desc *d, *n;
+
+	lockdep_assert_held(&ie->list_lock);
+	list_for_each_entry_safe(d, n, &ie->work_list, list) {
+		if (d == desc) {
+			list_del(&d->list);
+			return d;
+		}
+	}
+
+	/*
+	 * At this point, the desc needs to be aborted is held by the completion
+	 * handler where it has taken it off the pending list but has not added to the
+	 * work list. It will be cleaned up by the interrupt handler when it sees the
+	 * IDXD_COMP_DESC_ABORT for completion status.
+	 */
+	return NULL;
+}
+
+static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
+			     struct idxd_desc *desc)
+{
+	struct idxd_desc *d, *t, *found = NULL;
+	struct llist_node *head;
+	unsigned long flags;
+
+	desc->completion->status = IDXD_COMP_DESC_ABORT;
+	/*
+	 * Grab the list lock so it will block the irq thread handler. This allows the
+	 * abort code to locate the descriptor need to be aborted.
+	 */
+	spin_lock_irqsave(&ie->list_lock, flags);
+	head = llist_del_all(&ie->pending_llist);
+	if (head) {
+		llist_for_each_entry_safe(d, t, head, llnode) {
+			if (d == desc) {
+				found = desc;
+				continue;
+			}
+			list_add_tail(&desc->list, &ie->work_list);
+		}
+	}
+
+	if (!found)
+		found = list_abort_desc(wq, ie, desc);
+	spin_unlock_irqrestore(&ie->list_lock, flags);
+
+	if (found)
+		complete_desc(found, IDXD_COMPLETE_ABORT);
+}
+
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 {
 	struct idxd_device *idxd = wq->idxd;
+	struct idxd_irq_entry *ie = NULL;
 	void __iomem *portal;
 	int rc;
 
@@ -99,6 +154,16 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	 * even on UP because the recipient is a device.
 	 */
 	wmb();
+
+	/*
+	 * Pending the descriptor to the lockless list for the irq_entry
+	 * that we designated the descriptor to.
+	 */
+	if (desc->hw->flags & IDXD_OP_FLAG_RCI) {
+		ie = &idxd->irq_entries[wq->id + 1];
+		llist_add(&desc->llnode, &ie->pending_llist);
+	}
+
 	if (wq_dedicated(wq)) {
 		iosubmit_cmds512(portal, desc->hw, 1);
 	} else {
@@ -111,18 +176,12 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 		rc = enqcmds(portal, desc->hw);
 		if (rc < 0) {
 			percpu_ref_put(&wq->wq_active);
+			if (ie)
+				llist_abort_desc(wq, ie, desc);
 			return rc;
 		}
 	}
 
 	percpu_ref_put(&wq->wq_active);
-
-	/*
-	 * Pending the descriptor to the lockless list for the irq_entry
-	 * that we designated the descriptor to.
-	 */
-	if (desc->hw->flags & IDXD_OP_FLAG_RCI)
-		llist_add(&desc->llnode, &idxd->irq_entries[wq->id + 1].pending_llist);
-
 	return 0;
 }