dmaengine: idxd: fix missed completion on abort path

Ming reported that with the abort path of the descriptor submission, there
can be a window where a completed descriptor can be missed to be completed
by the irq completion thread:

CPU A				CPU B
Submit (successful)

Submit (fail)
				irq_process_work_list() // empty

llist_abort_desc()
// remove all descs from pending list

				irq_process_pending_llist() // empty
				exit idxd_wq_thread() with no processing

Add opportunistic descriptor completion in the abort path in order to
remove the missed completion.

Fixes: 6b4b87f2c31a ("dmaengine: idxd: fix submission race window")
Reported-by: Ming Li <ming4.li@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163898288714.443911.16084982766671976640.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>

diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index de76fb4abac24af94f143f5255ff51aa8fe93c37..83452fbbb168b156ff75f481124198564c3c21d3 100644 (file)
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -106,6 +106,7 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 {
        struct idxd_desc *d, *t, *found = NULL;
        struct llist_node *head;
+       LIST_HEAD(flist);
 
        desc->completion->status = IDXD_COMP_DESC_ABORT;
        /*
@@ -120,7 +121,11 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
                                found = desc;
                                continue;
                        }
-                       list_add_tail(&desc->list, &ie->work_list);
+
+                       if (d->completion->status)
+                               list_add_tail(&d->list, &flist);
+                       else
+                               list_add_tail(&d->list, &ie->work_list);
                }
        }
 
@@ -130,6 +135,17 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 
        if (found)
                complete_desc(found, IDXD_COMPLETE_ABORT);
+
+       /*
+        * complete_desc() will return desc to allocator and the desc can be
+        * acquired by a different process and the desc->list can be modified.
+        * Delete desc from list so the list trasversing does not get corrupted
+        * by the other process.
+        */
+       list_for_each_entry_safe(d, t, &flist, list) {
+               list_del_init(&d->list);
+               complete_desc(d, IDXD_COMPLETE_NORMAL);
+       }
 }
 
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)