Merge tag 'block-5.6-2020-02-16' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Not a lot here, which is great, basically just three small bcache
  fixes from Coly, and four NVMe fixes via Keith"

* tag 'block-5.6-2020-02-16' of git://git.kernel.dk/linux-block:
  nvme: fix the parameter order for nvme_get_log in nvme_get_fw_slot_info
  nvme/pci: move cqe check after device shutdown
  nvme: prevent warning triggered by nvme_stop_keep_alive
  nvme/tcp: fix bug on double requeue when send fails
  bcache: remove macro nr_to_fifo_front()
  bcache: Revert "bcache: shrink btree node cache after bch_btree_check()"
  bcache: ignore pending signals when creating gc and allocator thread

8 files changed, 63 insertions, 38 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index a1df0d95151c..8bc1faf71ff2 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -67,6 +67,7 @@
 #include <linux/blkdev.h>
 #include <linux/kthread.h>
 #include <linux/random.h>
+#include <linux/sched/signal.h>
 #include <trace/events/bcache.h>
 
 #define MAX_OPEN_BUCKETS 128
@@ -733,8 +734,21 @@ int bch_open_buckets_alloc(struct cache_set *c)
 
 int bch_cache_allocator_start(struct cache *ca)
 {
-	struct task_struct *k = kthread_run(bch_allocator_thread,
-					    ca, "bcache_allocator");
+	struct task_struct *k;
+
+	/*
+	 * In case previous btree check operation occupies too many
+	 * system memory for bcache btree node cache, and the
+	 * registering process is selected by OOM killer. Here just
+	 * ignore the SIGKILL sent by OOM killer if there is, to
+	 * avoid kthread_run() being failed by pending signals. The
+	 * bcache registering process will exit after the registration
+	 * done.
+	 */
+	if (signal_pending(current))
+		flush_signals(current);
+
+	k = kthread_run(bch_allocator_thread, ca, "bcache_allocator");
 	if (IS_ERR(k))
 		return PTR_ERR(k);
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index fa872df4e770..b12186c87f52 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -34,6 +34,7 @@
 #include <linux/random.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/signal.h>
 #include <linux/rculist.h>
 #include <linux/delay.h>
 #include <trace/events/bcache.h>
@@ -1913,6 +1914,18 @@ static int bch_gc_thread(void *arg)
 
 int bch_gc_thread_start(struct cache_set *c)
 {
+	/*
+	 * In case previous btree check operation occupies too many
+	 * system memory for bcache btree node cache, and the
+	 * registering process is selected by OOM killer. Here just
+	 * ignore the SIGKILL sent by OOM killer if there is, to
+	 * avoid kthread_run() being failed by pending signals. The
+	 * bcache registering process will exit after the registration
+	 * done.
+	 */
+	if (signal_pending(current))
+		flush_signals(current);
+
 	c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc");
 	return PTR_ERR_OR_ZERO(c->gc_thread);
 }
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 6730820780b0..0e3ff9745ac7 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -417,8 +417,6 @@ err:
 
 /* Journalling */
 
-#define nr_to_fifo_front(p, front_p, mask)	(((p) - (front_p)) & (mask))
-
 static void btree_flush_write(struct cache_set *c)
 {
 	struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR];
@@ -510,9 +508,8 @@ static void btree_flush_write(struct cache_set *c)
 		 *   journal entry can be reclaimed). These selected nodes
 		 *   will be ignored and skipped in the folowing for-loop.
 		 */
-		if (nr_to_fifo_front(btree_current_write(b)->journal,
-				     fifo_front_p,
-				     mask) != 0) {
+		if (((btree_current_write(b)->journal - fifo_front_p) &
+		     mask) != 0) {
 			mutex_unlock(&b->write_lock);
 			continue;
 		}
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2749daf09724..0c3c5419c52b 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1917,23 +1917,6 @@ static int run_cache_set(struct cache_set *c)
 		if (bch_btree_check(c))
 			goto err;
 
-		/*
-		 * bch_btree_check() may occupy too much system memory which
-		 * has negative effects to user space application (e.g. data
-		 * base) performance. Shrink the mca cache memory proactively
-		 * here to avoid competing memory with user space workloads..
-		 */
-		if (!c->shrinker_disabled) {
-			struct shrink_control sc;
-
-			sc.gfp_mask = GFP_KERNEL;
-			sc.nr_to_scan = c->btree_cache_used * c->btree_pages;
-			/* first run to clear b->accessed tag */
-			c->shrink.scan_objects(&c->shrink, &sc);
-			/* second run to reap non-accessed nodes */
-			c->shrink.scan_objects(&c->shrink, &sc);
-		}
-
 		bch_journal_mark(c, &journal);
 		bch_initial_gc_finish(c);
 		pr_debug("btree_check() done");
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 5dc32b72e7fa..ada59df642d2 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -66,8 +66,8 @@ MODULE_PARM_DESC(streams, "turn on support for Streams write directives");
  * nvme_reset_wq - hosts nvme reset works
  * nvme_delete_wq - hosts nvme delete works
  *
- * nvme_wq will host works such are scan, aen handling, fw activation,
- * keep-alive error recovery, periodic reconnects etc. nvme_reset_wq
+ * nvme_wq will host works such as scan, aen handling, fw activation,
+ * keep-alive, periodic reconnects etc. nvme_reset_wq
  * runs reset works which also flush works hosted on nvme_wq for
  * serialization purposes. nvme_delete_wq host controller deletion
  * works which flush reset works for serialization.
@@ -976,7 +976,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 		startka = true;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static int nvme_keep_alive(struct nvme_ctrl *ctrl)
@@ -1006,7 +1006,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 		dev_dbg(ctrl->device,
 			"reschedule traffic based keep-alive timer\n");
 		ctrl->comp_seen = false;
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 		return;
 	}
 
@@ -1023,7 +1023,7 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
@@ -3867,7 +3867,7 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
 			sizeof(*log), 0))
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index da392b50f73e..9c80f9f08149 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1401,6 +1401,23 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 	nvme_poll_irqdisable(nvmeq, -1);
 }
 
+/*
+ * Called only on a device that has been disabled and after all other threads
+ * that can check this device's completion queues have synced. This is the
+ * last chance for the driver to see a natural completion before
+ * nvme_cancel_request() terminates all incomplete requests.
+ */
+static void nvme_reap_pending_cqes(struct nvme_dev *dev)
+{
+	u16 start, end;
+	int i;
+
+	for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
+		nvme_process_cq(&dev->queues[i], &start, &end, -1);
+		nvme_complete_cqes(&dev->queues[i], start, end);
+	}
+}
+
 static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 				int entry_size)
 {
@@ -2235,11 +2252,6 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
 		if (timeout == 0)
 			return false;
 
-		/* handle any remaining CQEs */
-		if (opcode == nvme_admin_delete_cq &&
-		    !test_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags))
-			nvme_poll_irqdisable(nvmeq, -1);
-
 		sent--;
 		if (nr_queues)
 			goto retry;
@@ -2428,6 +2440,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	nvme_suspend_io_queues(dev);
 	nvme_suspend_queue(&dev->queues[0]);
 	nvme_pci_disable(dev);
+	nvme_reap_pending_cqes(dev);
 
 	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
 	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 2a47c6c5007e..3e85c5cacefd 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1088,7 +1088,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
-	queue_work(nvme_wq, &ctrl->err_work);
+	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
 static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 6d43b23a0fc8..49d4373b84eb 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -422,7 +422,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
-	queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work);
+	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
@@ -1054,7 +1054,12 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		} else if (unlikely(result < 0)) {
 			dev_err(queue->ctrl->ctrl.device,
 				"failed to send request %d\n", result);
-			if (result != -EPIPE)
+
+			/*
+			 * Fail the request unless peer closed the connection,
+			 * in which case error recovery flow will complete all.
+			 */
+			if ((result != -EPIPE) && (result != -ECONNRESET))
 				nvme_tcp_fail_request(queue->request);
 			nvme_tcp_done_send_req(queue);
 			return;