4.2-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Keith Busch <keith.bu...@intel.com>

commit 0dfc70c33409afc232ef0b9ec210535dfbf9bc61 upstream.

Resources are reallocated for requeued commands, so unmap and release
the iod for the failed command.

It's a pretty bad memory leak and causes a kernel hang if you remove a
drive because of a busy dma pool. You'll get messages spewing like this:

  nvme 0000:xx:xx.x: dma_pool_destroy prp list 256, ffff880420dec000 busy

and lock up pci and the driver since removal never completes while
holding a lock.

Signed-off-by: Keith Busch <keith.bu...@intel.com>
Reviewed-by: Christoph Hellwig <h...@lst.de>
Signed-off-by: Jens Axboe <ax...@fb.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>


---
 drivers/block/nvme-core.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -597,6 +597,7 @@ static void req_completion(struct nvme_q
        struct nvme_iod *iod = ctx;
        struct request *req = iod_get_private(iod);
        struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+       bool requeue = false;
 
        u16 status = le16_to_cpup(&cqe->status) >> 1;
 
@@ -605,12 +606,13 @@ static void req_completion(struct nvme_q
                    && (jiffies - req->start_time) < req->timeout) {
                        unsigned long flags;
 
+                       requeue = true;
                        blk_mq_requeue_request(req);
                        spin_lock_irqsave(req->q->queue_lock, flags);
                        if (!blk_queue_stopped(req->q))
                                blk_mq_kick_requeue_list(req->q);
                        spin_unlock_irqrestore(req->q->queue_lock, flags);
-                       return;
+                       goto release_iod;
                }
                if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
                        if (cmd_rq->ctx == CMD_CTX_CANCELLED)
@@ -631,7 +633,7 @@ static void req_completion(struct nvme_q
                dev_warn(nvmeq->dev->dev,
                        "completing aborted command with status:%04x\n",
                        status);
-
+ release_iod:
        if (iod->nents) {
                dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents,
                        rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
@@ -644,7 +646,8 @@ static void req_completion(struct nvme_q
        }
        nvme_free_iod(nvmeq->dev, iod);
 
-       blk_mq_complete_request(req);
+       if (likely(!requeue))
+               blk_mq_complete_request(req);
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to