Merge tag 'for-linus-20190823' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Here's a set of fixes that should go into this release. This contains:

   - Three minor fixes for NVMe.

   - Three minor tweaks for the io_uring polling logic.

   - Officially mark Song as the MD maintainer, after he's been filling
     that role sucessfully for the last 6 months or so"

* tag 'for-linus-20190823' of git://git.kernel.dk/linux-block:
  io_uring: add need_resched() check in inner poll loop
  md: update MAINTAINERS info
  io_uring: don't enter poll loop if we have CQEs pending
  nvme: Add quirk for LiteON CL1 devices running FW 22301111
  nvme: Fix cntlid validation when not using NVMEoF
  nvme-multipath: fix possible I/O hang when paths are updated
  io_uring: fix potential hang with polled IO

6 files changed, 70 insertions, 23 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 035ffc1e16a3..9cbcf167bdd0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14883,9 +14883,9 @@ F:	include/linux/arm_sdei.h
 F:	include/uapi/linux/arm_sdei.h
 
 SOFTWARE RAID (Multiple Disks) SUPPORT
-M:	Shaohua Li <shli@kernel.org>
+M:	Song Liu <song@kernel.org>
 L:	linux-raid@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shli/md.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/song/md.git
 S:	Supported
 F:	drivers/md/Makefile
 F:	drivers/md/Kconfig
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c258a1ce4b28..d3d6b7bd6903 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2257,6 +2257,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
 		.vid = 0x1179,
 		.mn = "THNSF5256GPUK TOSHIBA",
 		.quirks = NVME_QUIRK_NO_APST,
+	},
+	{
+		/*
+		 * This LiteON CL1-3D*-Q11 firmware version has a race
+		 * condition associated with actions related to suspend to idle
+		 * LiteON has resolved the problem in future firmware
+		 */
+		.vid = 0x14a4,
+		.fr = "22301111",
+		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
 	}
 };
 
@@ -2597,6 +2607,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 			goto out_free;
 	}
 
+	if (!(ctrl->ops->flags & NVME_F_FABRICS))
+		ctrl->cntlid = le16_to_cpu(id->cntlid);
+
 	if (!ctrl->identified) {
 		int i;
 
@@ -2697,7 +2710,6 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 			goto out_free;
 		}
 	} else {
-		ctrl->cntlid = le16_to_cpu(id->cntlid);
 		ctrl->hmpre = le32_to_cpu(id->hmpre);
 		ctrl->hmmin = le32_to_cpu(id->hmmin);
 		ctrl->hmminds = le32_to_cpu(id->hmminds);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 888d4543894e..af831d3d15d0 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -428,6 +428,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
 
+	synchronize_srcu(&ns->head->srcu);
 	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 778b3a0b6adb..2d678fb968c7 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -92,6 +92,11 @@ enum nvme_quirks {
 	 * Broken Write Zeroes.
 	 */
 	NVME_QUIRK_DISABLE_WRITE_ZEROES		= (1 << 9),
+
+	/*
+	 * Force simple suspend/resume path.
+	 */
+	NVME_QUIRK_SIMPLE_SUSPEND		= (1 << 10),
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 6bd9b1033965..732d5b63ec05 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2876,7 +2876,8 @@ static int nvme_suspend(struct device *dev)
 	 * state (which may not be possible if the link is up).
 	 */
 	if (pm_suspend_via_firmware() || !ctrl->npss ||
-	    !pcie_aspm_enabled(pdev)) {
+	    !pcie_aspm_enabled(pdev) ||
+	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND)) {
 		nvme_dev_disable(ndev, true);
 		return 0;
 	}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 24bbe3cb7ad4..cfb48bd088e1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -679,6 +679,13 @@ static void io_put_req(struct io_kiocb *req)
 		io_free_req(req);
 }
 
+static unsigned io_cqring_events(struct io_cq_ring *ring)
+{
+	/* See comment at the top of this file */
+	smp_rmb();
+	return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
+}
+
 /*
  * Find and free completed poll iocbs
  */
@@ -771,7 +778,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
 				long min)
 {
-	while (!list_empty(&ctx->poll_list)) {
+	while (!list_empty(&ctx->poll_list) && !need_resched()) {
 		int ret;
 
 		ret = io_do_iopoll(ctx, nr_events, min);
@@ -798,6 +805,12 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
 		unsigned int nr_events = 0;
 
 		io_iopoll_getevents(ctx, &nr_events, 1);
+
+		/*
+		 * Ensure we allow local-to-the-cpu processing to take place,
+		 * in this case we need to ensure that we reap all events.
+		 */
+		cond_resched();
 	}
 	mutex_unlock(&ctx->uring_lock);
 }
@@ -805,11 +818,42 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
 static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 			   long min)
 {
-	int ret = 0;
+	int iters, ret = 0;
 
+	/*
+	 * We disallow the app entering submit/complete with polling, but we
+	 * still need to lock the ring to prevent racing with polled issue
+	 * that got punted to a workqueue.
+	 */
+	mutex_lock(&ctx->uring_lock);
+
+	iters = 0;
 	do {
 		int tmin = 0;
 
+		/*
+		 * Don't enter poll loop if we already have events pending.
+		 * If we do, we can potentially be spinning for commands that
+		 * already triggered a CQE (eg in error).
+		 */
+		if (io_cqring_events(ctx->cq_ring))
+			break;
+
+		/*
+		 * If a submit got punted to a workqueue, we can have the
+		 * application entering polling for a command before it gets
+		 * issued. That app will hold the uring_lock for the duration
+		 * of the poll right here, so we need to take a breather every
+		 * now and then to ensure that the issue has a chance to add
+		 * the poll to the issued list. Otherwise we can spin here
+		 * forever, while the workqueue is stuck trying to acquire the
+		 * very same mutex.
+		 */
+		if (!(++iters & 7)) {
+			mutex_unlock(&ctx->uring_lock);
+			mutex_lock(&ctx->uring_lock);
+		}
+
 		if (*nr_events < min)
 			tmin = min - *nr_events;
 
@@ -819,6 +863,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 		ret = 0;
 	} while (min && !*nr_events && !need_resched());
 
+	mutex_unlock(&ctx->uring_lock);
 	return ret;
 }
 
@@ -2280,15 +2325,7 @@ static int io_sq_thread(void *data)
 			unsigned nr_events = 0;
 
 			if (ctx->flags & IORING_SETUP_IOPOLL) {
-				/*
-				 * We disallow the app entering submit/complete
-				 * with polling, but we still need to lock the
-				 * ring to prevent racing with polled issue
-				 * that got punted to a workqueue.
-				 */
-				mutex_lock(&ctx->uring_lock);
 				io_iopoll_check(ctx, &nr_events, 0);
-				mutex_unlock(&ctx->uring_lock);
 			} else {
 				/*
 				 * Normal IO, just pretend everything completed.
@@ -2433,13 +2470,6 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 	return submit;
 }
 
-static unsigned io_cqring_events(struct io_cq_ring *ring)
-{
-	/* See comment at the top of this file */
-	smp_rmb();
-	return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
-}
-
 /*
  * Wait until events become available, if we don't already have some. The
  * application must reap them itself, as they reside on the shared cq ring.
@@ -3190,9 +3220,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		min_complete = min(min_complete, ctx->cq_entries);
 
 		if (ctx->flags & IORING_SETUP_IOPOLL) {
-			mutex_lock(&ctx->uring_lock);
 			ret = io_iopoll_check(ctx, &nr_events, min_complete);
-			mutex_unlock(&ctx->uring_lock);
 		} else {
 			ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
 		}