Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the main pull request for block storage for 4.15-rc1.

  Nothing out of the ordinary in here, and no API changes or anything
  like that. Just various new features for drivers, core changes, etc.
  In particular, this pull request contains:

   - A patch series from Bart, closing the whole on blk/scsi-mq queue
     quescing.

   - A series from Christoph, building towards hidden gendisks (for
     multipath) and ability to move bio chains around.

   - NVMe
        - Support for native multipath for NVMe (Christoph).
        - Userspace notifications for AENs (Keith).
        - Command side-effects support (Keith).
        - SGL support (Chaitanya Kulkarni)
        - FC fixes and improvements (James Smart)
        - Lots of fixes and tweaks (Various)

   - bcache
        - New maintainer (Michael Lyle)
        - Writeback control improvements (Michael)
        - Various fixes (Coly, Elena, Eric, Liang, et al)

   - lightnvm updates, mostly centered around the pblk interface
     (Javier, Hans, and Rakesh).

   - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)

   - Writeback series that fix the much discussed hundreds of millions
     of sync-all units. This goes all the way, as discussed previously
     (me).

   - Fix for missing wakeup on writeback timer adjustments (Yafang
     Shao).

   - Fix laptop mode on blk-mq (me).

   - {mq,name} tupple lookup for IO schedulers, allowing us to have
     alias names. This means you can use 'deadline' on both !mq and on
     mq (where it's called mq-deadline). (me).

   - blktrace race fix, oopsing on sg load (me).

   - blk-mq optimizations (me).

   - Obscure waitqueue race fix for kyber (Omar).

   - NBD fixes (Josef).

   - Disable writeback throttling by default on bfq, like we do on cfq
     (Luca Miccio).

   - Series from Ming that enable us to treat flush requests on blk-mq
     like any other request. This is a really nice cleanup.

   - Series from Ming that improves merging on blk-mq with schedulers,
     getting us closer to flipping the switch on scsi-mq again.

   - BFQ updates (Paolo).

   - blk-mq atomic flags memory ordering fixes (Peter Z).

   - Loop cgroup support (Shaohua).

   - Lots of minor fixes from lots of different folks, both for core and
     driver code"

* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
  nvme: fix visibility of "uuid" ns attribute
  blk-mq: fixup some comment typos and lengths
  ide: ide-atapi: fix compile error with defining macro DEBUG
  blk-mq: improve tag waiting setup for non-shared tags
  brd: remove unused brd_mutex
  blk-mq: only run the hardware queue if IO is pending
  block: avoid null pointer dereference on null disk
  fs: guard_bio_eod() needs to consider partitions
  xtensa/simdisk: fix compile error
  nvme: expose subsys attribute to sysfs
  nvme: create 'slaves' and 'holders' entries for hidden controllers
  block: create 'slaves' and 'holders' entries for hidden gendisks
  nvme: also expose the namespace identification sysfs files for mpath nodes
  nvme: implement multipath access to nvme subsystems
  nvme: track shared namespaces
  nvme: introduce a nvme_ns_ids structure
  nvme: track subsystems
  block, nvme: Introduce blk_mq_req_flags_t
  block, scsi: Make SCSI quiesce and resume work reliably
  block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
  ...

10 files changed, 41 insertions, 28 deletions

diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 7b2df7a54d87..923b417eaf4c 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -68,9 +68,13 @@ config AMIGA_Z2RAM
 	  To compile this driver as a module, choose M here: the
 	  module will be called z2ram.
 
+config CDROM
+	tristate
+
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
+	select CDROM
 	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
@@ -348,6 +352,7 @@ config BLK_DEV_RAM_DAX
 config CDROM_PKTCDVD
 	tristate "Packet writing on CD/DVD media (DEPRECATED)"
 	depends on !UML
+	select CDROM
 	select BLK_SCSI_REQUEST
 	help
 	  Note: This driver is deprecated and will be removed from the
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 2d7178f7754e..c1cf87718c2e 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -60,7 +60,6 @@ struct brd_device {
 /*
  * Look up and return a brd's page for a given sector.
  */
-static DEFINE_MUTEX(brd_mutex);
 static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
 {
 	pgoff_t idx;
diff --git a/drivers/block/cryptoloop.c b/drivers/block/cryptoloop.c
index 74e03aa537ad..7033a4beda66 100644
--- a/drivers/block/cryptoloop.c
+++ b/drivers/block/cryptoloop.c
@@ -43,7 +43,6 @@ cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info)
 	int cipher_len;
 	int mode_len;
 	char cms[LO_NAME_SIZE];			/* cipher-mode string */
-	char *cipher;
 	char *mode;
 	char *cmsp = cms;			/* c-m string pointer */
 	struct crypto_skcipher *tfm;
@@ -56,7 +55,6 @@ cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info)
 	strncpy(cms, info->lo_crypt_name, LO_NAME_SIZE);
 	cms[LO_NAME_SIZE - 1] = 0;
 
-	cipher = cmsp;
 	cipher_len = strcspn(cmsp, "-");
 
 	mode = cmsp + cipher_len;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 85de67334695..bc8e61506968 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -476,6 +476,8 @@ static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
 {
 	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
 
+	if (cmd->css)
+		css_put(cmd->css);
 	cmd->ret = ret;
 	lo_rw_aio_do_completion(cmd);
 }
@@ -535,6 +537,8 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	cmd->iocb.ki_filp = file;
 	cmd->iocb.ki_complete = lo_rw_aio_complete;
 	cmd->iocb.ki_flags = IOCB_DIRECT;
+	if (cmd->css)
+		kthread_associate_blkcg(cmd->css);
 
 	if (rw == WRITE)
 		ret = call_write_iter(file, &cmd->iocb, &iter);
@@ -542,6 +546,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 		ret = call_read_iter(file, &cmd->iocb, &iter);
 
 	lo_rw_aio_do_completion(cmd);
+	kthread_associate_blkcg(NULL);
 
 	if (ret != -EIOCBQUEUED)
 		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
@@ -1686,6 +1691,14 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		break;
 	}
 
+	/* always use the first bio's css */
+#ifdef CONFIG_BLK_CGROUP
+	if (cmd->use_aio && cmd->rq->bio && cmd->rq->bio->bi_css) {
+		cmd->css = cmd->rq->bio->bi_css;
+		css_get(cmd->css);
+	} else
+#endif
+		cmd->css = NULL;
 	kthread_queue_work(&lo->worker, &cmd->work);
 
 	return BLK_STS_OK;
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 1f3956702993..0f45416e4fcf 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -72,6 +72,7 @@ struct loop_cmd {
 	long ret;
 	struct kiocb iocb;
 	struct bio_vec *bvec;
+	struct cgroup_subsys_state *css;
 };
 
 /* Support for loadable transfer modules */
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 4a3cfc7940de..b8af7352a18f 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -887,12 +887,9 @@ static void mtip_issue_non_ncq_command(struct mtip_port *port, int tag)
 static bool mtip_pause_ncq(struct mtip_port *port,
 				struct host_to_dev_fis *fis)
 {
-	struct host_to_dev_fis *reply;
 	unsigned long task_file_data;
 
-	reply = port->rxfis + RX_FIS_D2H_REG;
 	task_file_data = readl(port->mmio+PORT_TFDATA);
-
 	if ((task_file_data & 1))
 		return false;
 
@@ -1020,7 +1017,6 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 		.opts = opts
 	};
 	int rv = 0;
-	unsigned long start;
 
 	/* Make sure the buffer is 8 byte aligned. This is asic specific. */
 	if (buffer & 0x00000007) {
@@ -1057,7 +1053,6 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	/* Copy the command to the command table */
 	memcpy(int_cmd->command, fis, fis_len*4);
 
-	start = jiffies;
 	rq->timeout = timeout;
 
 	/* insert request and run queue */
@@ -3015,7 +3010,6 @@ static int mtip_hw_init(struct driver_data *dd)
 {
 	int i;
 	int rv;
-	unsigned int num_command_slots;
 	unsigned long timeout, timetaken;
 
 	dd->mmio = pcim_iomap_table(dd->pdev)[MTIP_ABAR];
@@ -3025,7 +3019,6 @@ static int mtip_hw_init(struct driver_data *dd)
 		rv = -EIO;
 		goto out1;
 	}
-	num_command_slots = dd->slot_groups * 32;
 
 	hba_setup(dd);
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 9adfb5445f8d..5f2a4240a204 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -288,15 +288,6 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 		cmd->status = BLK_STS_TIMEOUT;
 		return BLK_EH_HANDLED;
 	}
-
-	/* If we are waiting on our dead timer then we could get timeout
-	 * callbacks for our request.  For this we just want to reset the timer
-	 * and let the queue side take care of everything.
-	 */
-	if (!completion_done(&cmd->send_complete)) {
-		nbd_config_put(nbd);
-		return BLK_EH_RESET_TIMER;
-	}
 	config = nbd->config;
 
 	if (config->num_connections > 1) {
@@ -723,9 +714,9 @@ static int wait_for_reconnect(struct nbd_device *nbd)
 		return 0;
 	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
 		return 0;
-	wait_event_interruptible_timeout(config->conn_wait,
-					 atomic_read(&config->live_connections),
-					 config->dead_conn_timeout);
+	wait_event_timeout(config->conn_wait,
+			   atomic_read(&config->live_connections),
+			   config->dead_conn_timeout);
 	return atomic_read(&config->live_connections);
 }
 
@@ -740,6 +731,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 	if (!refcount_inc_not_zero(&nbd->config_refs)) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Socks array is empty\n");
+		blk_mq_start_request(req);
 		return -EINVAL;
 	}
 	config = nbd->config;
@@ -748,6 +740,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Attempted send on invalid socket\n");
 		nbd_config_put(nbd);
+		blk_mq_start_request(req);
 		return -EINVAL;
 	}
 	cmd->status = BLK_STS_OK;
@@ -771,6 +764,7 @@ again:
 			 */
 			sock_shutdown(nbd);
 			nbd_config_put(nbd);
+			blk_mq_start_request(req);
 			return -EIO;
 		}
 		goto again;
@@ -781,6 +775,7 @@ again:
 	 * here so that it gets put _after_ the request that is already on the
 	 * dispatch list.
 	 */
+	blk_mq_start_request(req);
 	if (unlikely(nsock->pending && nsock->pending != req)) {
 		blk_mq_requeue_request(req, true);
 		ret = 0;
@@ -793,10 +788,10 @@ again:
 	ret = nbd_send_cmd(nbd, cmd, index);
 	if (ret == -EAGAIN) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Request send failed trying another connection\n");
+				    "Request send failed, requeueing\n");
 		nbd_mark_nsock_dead(nbd, nsock, 1);
-		mutex_unlock(&nsock->tx_lock);
-		goto again;
+		blk_mq_requeue_request(req, true);
+		ret = 0;
 	}
 out:
 	mutex_unlock(&nsock->tx_lock);
@@ -820,7 +815,6 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * done sending everything over the wire.
 	 */
 	init_completion(&cmd->send_complete);
-	blk_mq_start_request(bd->rq);
 
 	/* We can be called directly from the user space process, which means we
 	 * could possibly have signals pending so our sendmsg will fail.  In
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index cda69dbefe3b..c61960deb74a 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -154,6 +154,10 @@ enum {
 	NULL_Q_MQ		= 2,
 };
 
+static int g_no_sched;
+module_param_named(no_sched, g_no_sched, int, S_IRUGO);
+MODULE_PARM_DESC(no_sched, "No io scheduler");
+
 static int g_submit_queues = 1;
 module_param_named(submit_queues, g_submit_queues, int, S_IRUGO);
 MODULE_PARM_DESC(submit_queues, "Number of submission queues");
@@ -1754,6 +1758,8 @@ static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
 	set->numa_node = nullb ? nullb->dev->home_node : g_home_node;
 	set->cmd_size	= sizeof(struct nullb_cmd);
 	set->flags = BLK_MQ_F_SHOULD_MERGE;
+	if (g_no_sched)
+		set->flags |= BLK_MQ_F_NO_SCHED;
 	set->driver_data = NULL;
 
 	if ((nullb && nullb->dev->blocking) || g_blocking)
@@ -1985,8 +1991,10 @@ static int __init null_init(void)
 
 	for (i = 0; i < nr_devices; i++) {
 		dev = null_alloc_dev();
-		if (!dev)
+		if (!dev) {
+			ret = -ENOMEM;
 			goto err_dev;
+		}
 		ret = null_add_dev(dev);
 		if (ret) {
 			null_free_dev(dev);
diff --git a/drivers/block/paride/Kconfig b/drivers/block/paride/Kconfig
index b226835a909a..f8bd6ef3605a 100644
--- a/drivers/block/paride/Kconfig
+++ b/drivers/block/paride/Kconfig
@@ -26,6 +26,7 @@ config PARIDE_PD
 config PARIDE_PCD
 	tristate "Parallel port ATAPI CD-ROMs"
 	depends on PARIDE
+	select CDROM
 	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	---help---
 	  This option enables the high-level driver for ATAPI CD-ROM devices
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 64d0fc17c174..2819f23e8bf2 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -1967,7 +1967,8 @@ static void skd_isr_msg_from_dev(struct skd_device *skdev)
 		break;
 
 	case FIT_MTD_CMD_LOG_HOST_ID:
-		skdev->connect_time_stamp = get_seconds();
+		/* hardware interface overflows in y2106 */
+		skdev->connect_time_stamp = (u32)ktime_get_real_seconds();
 		data = skdev->connect_time_stamp & 0xFFFF;
 		mtd = FIT_MXD_CONS(FIT_MTD_CMD_LOG_TIME_STAMP_LO, 0, data);
 		SKD_WRITEL(skdev, mtd, FIT_MSG_TO_DEVICE);