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

Pull block fixes from Jens Axboe:
 - fix for a memory leak on certain unplug events
 - a collection of bcache fixes from Kent and Nicolas
 - a few null_blk fixes and updates form Matias
 - a marking of static of functions in the stec pci-e driver

* 'for-linus' of git://git.kernel.dk/linux-block:
  null_blk: support submit_queues on use_per_node_hctx
  null_blk: set use_per_node_hctx param to false
  null_blk: corrections to documentation
  null_blk: warning on ignored submit_queues param
  null_blk: refactor init and init errors code paths
  null_blk: documentation
  null_blk: mem garbage on NUMA systems during init
  drivers: block: Mark the functions as static in skd_main.c
  bcache: New writeback PD controller
  bcache: bugfix for race between moving_gc and bucket_invalidate
  bcache: fix for gc and writeback race
  bcache: bugfix - moving_gc now moves only correct buckets
  bcache: fix for gc crashing when no sectors are used
  bcache: Fix heap_peek() macro
  bcache: Fix for can_attach_cache()
  bcache: Fix dirty_data accounting
  bcache: Use uninterruptible sleep in writeback
  bcache: kthread don't set writeback task to INTERUPTIBLE
  block: fix memory leaks on unplugging block device
  bcache: fix sparse non static symbol warning

Documentation/block/null_blk.txt

@@ -0,0 +1,72 @@
+Null block device driver
+================================================================================
+
+I. Overview
+
+The null block device (/dev/nullb*) is used for benchmarking the various
+block-layer implementations. It emulates a block device of X gigabytes in size.
+The following instances are possible:
+
+  Single-queue block-layer
+    - Request-based.
+    - Single submission queue per device.
+    - Implements IO scheduling algorithms (CFQ, Deadline, noop).
+  Multi-queue block-layer
+    - Request-based.
+    - Configurable submission queues per device.
+  No block-layer (Known as bio-based)
+    - Bio-based. IO requests are submitted directly to the device driver.
+    - Directly accepts bio data structure and returns them.
+
+All of them have a completion queue for each core in the system.
+
+II. Module parameters applicable for all instances:
+
+queue_mode=[0-2]: Default: 2-Multi-queue
+  Selects which block-layer the module should instantiate with.
+
+  0: Bio-based.
+  1: Single-queue.
+  2: Multi-queue.
+
+home_node=[0--nr_nodes]: Default: NUMA_NO_NODE
+  Selects what CPU node the data structures are allocated from.
+
+gb=[Size in GB]: Default: 250GB
+  The size of the device reported to the system.
+
+bs=[Block size (in bytes)]: Default: 512 bytes
+  The block size reported to the system.
+
+nr_devices=[Number of devices]: Default: 2
+  Number of block devices instantiated. They are instantiated as /dev/nullb0,
+  etc.
+
+irq_mode=[0-2]: Default: 1-Soft-irq
+  The completion mode used for completing IOs to the block-layer.
+
+  0: None.
+  1: Soft-irq. Uses IPI to complete IOs across CPU nodes. Simulates the overhead
+     when IOs are issued from another CPU node than the home the device is
+     connected to.
+  2: Timer: Waits a specific period (completion_nsec) for each IO before
+     completion.
+
+completion_nsec=[ns]: Default: 10.000ns
+  Combined with irq_mode=2 (timer). The time each completion event must wait.
+
+submit_queues=[0..nr_cpus]:
+  The number of submission queues attached to the device driver. If unset, it
+  defaults to 1 on single-queue and bio-based instances. For multi-queue,
+  it is ignored when use_per_node_hctx module parameter is 1.
+
+hw_queue_depth=[0..qdepth]: Default: 64
+  The hardware queue depth of the device.
+
+III: Multi-queue specific parameters
+
+use_per_node_hctx=[0/1]: Default: 0
+  0: The number of submit queues are set to the value of the submit_queues
+     parameter.
+  1: The multi-queue block layer is instantiated with a hardware dispatch
+     queue for each CPU node in the system.

block/blk-mq-sysfs.c

@@ -335,9 +335,22 @@ static struct kobj_type blk_mq_hw_ktype = {
 void blk_mq_unregister_disk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	int i, j;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx_for_each_ctx(hctx, ctx, j) {
+			kobject_del(&ctx->kobj);
+			kobject_put(&ctx->kobj);
+		}
+		kobject_del(&hctx->kobj);
+		kobject_put(&hctx->kobj);
+	}
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
+	kobject_put(&q->mq_kobj);
 
 	kobject_put(&disk_to_dev(disk)->kobj);
 }

drivers/block/null_blk.c

@@ -1,4 +1,5 @@
 #include <linux/module.h>
+
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
@@ -65,7 +66,7 @@ enum {
 	NULL_Q_MQ		= 2,
 };
 
-static int submit_queues = 1;
+static int submit_queues;
 module_param(submit_queues, int, S_IRUGO);
 MODULE_PARM_DESC(submit_queues, "Number of submission queues");
 
@@ -101,9 +102,9 @@ static int hw_queue_depth = 64;
 module_param(hw_queue_depth, int, S_IRUGO);
 MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");
 
-static bool use_per_node_hctx = true;
+static bool use_per_node_hctx = false;
 module_param(use_per_node_hctx, bool, S_IRUGO);
-MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: true");
+MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
 
 static void put_tag(struct nullb_queue *nq, unsigned int tag)
 {
@@ -346,25 +347,62 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq)
 
 static struct blk_mq_hw_ctx *null_alloc_hctx(struct blk_mq_reg *reg, unsigned int hctx_index)
 {
-	return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL,
-				hctx_index);
+	int b_size = DIV_ROUND_UP(reg->nr_hw_queues, nr_online_nodes);
+	int tip = (reg->nr_hw_queues % nr_online_nodes);
+	int node = 0, i, n;
+
+	/*
+	 * Split submit queues evenly wrt to the number of nodes. If uneven,
+	 * fill the first buckets with one extra, until the rest is filled with
+	 * no extra.
+	 */
+	for (i = 0, n = 1; i < hctx_index; i++, n++) {
+		if (n % b_size == 0) {
+			n = 0;
+			node++;
+
+			tip--;
+			if (!tip)
+				b_size = reg->nr_hw_queues / nr_online_nodes;
+		}
+	}
+
+	/*
+	 * A node might not be online, therefore map the relative node id to the
+	 * real node id.
+	 */
+	for_each_online_node(n) {
+		if (!node)
+			break;
+		node--;
+	}
+
+	return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL, n);
 }
 
 static void null_free_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_index)
 {
 	kfree(hctx);
 }
 
+static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
+{
+	BUG_ON(!nullb);
+	BUG_ON(!nq);
+
+	init_waitqueue_head(&nq->wait);
+	nq->queue_depth = nullb->queue_depth;
+}
+
 static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 			  unsigned int index)
 {
 	struct nullb *nullb = data;
 	struct nullb_queue *nq = &nullb->queues[index];
 
-	init_waitqueue_head(&nq->wait);
-	nq->queue_depth = nullb->queue_depth;
-	nullb->nr_queues++;
 	hctx->driver_data = nq;
+	null_init_queue(nullb, nq);
+	nullb->nr_queues++;
 
 	return 0;
 }
@@ -417,13 +455,13 @@ static int setup_commands(struct nullb_queue *nq)
 
 	nq->cmds = kzalloc(nq->queue_depth * sizeof(*cmd), GFP_KERNEL);
 	if (!nq->cmds)
-		return 1;
+		return -ENOMEM;
 
 	tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG;
 	nq->tag_map = kzalloc(tag_size * sizeof(unsigned long), GFP_KERNEL);
 	if (!nq->tag_map) {
 		kfree(nq->cmds);
-		return 1;
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < nq->queue_depth; i++) {
@@ -454,33 +492,37 @@ static void cleanup_queues(struct nullb *nullb)
 
 static int setup_queues(struct nullb *nullb)
 {
-	struct nullb_queue *nq;
-	int i;
-
-	nullb->queues = kzalloc(submit_queues * sizeof(*nq), GFP_KERNEL);
+	nullb->queues = kzalloc(submit_queues * sizeof(struct nullb_queue),
+								GFP_KERNEL);
 	if (!nullb->queues)
-		return 1;
+		return -ENOMEM;
 
 	nullb->nr_queues = 0;
 	nullb->queue_depth = hw_queue_depth;
 
-	if (queue_mode == NULL_Q_MQ)
-		return 0;
+	return 0;
+}
+
+static int init_driver_queues(struct nullb *nullb)
+{
+	struct nullb_queue *nq;
+	int i, ret = 0;
 
 	for (i = 0; i < submit_queues; i++) {
 		nq = &nullb->queues[i];
-		init_waitqueue_head(&nq->wait);
-		nq->queue_depth = hw_queue_depth;
-		if (setup_commands(nq))
-			break;
+
+		null_init_queue(nullb, nq);
+
+		ret = setup_commands(nq);
+		if (ret)
+			goto err_queue;
 		nullb->nr_queues++;
 	}
 
-	if (i == submit_queues)
-		return 0;
-
+	return 0;
+err_queue:
 	cleanup_queues(nullb);
-	return 1;
+	return ret;
 }
 
 static int null_add_dev(void)
@@ -518,11 +560,13 @@ static int null_add_dev(void)
 	} else if (queue_mode == NULL_Q_BIO) {
 		nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node);
 		blk_queue_make_request(nullb->q, null_queue_bio);
+		init_driver_queues(nullb);
 	} else {
 		nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node);
 		blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
 		if (nullb->q)
 			blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
+		init_driver_queues(nullb);
 	}
 
 	if (!nullb->q)
@@ -579,7 +623,13 @@ static int __init null_init(void)
 	}
 #endif
 
-	if (submit_queues > nr_cpu_ids)
+	if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
+		if (submit_queues < nr_online_nodes) {
+			pr_warn("null_blk: submit_queues param is set to %u.",
+							nr_online_nodes);
+			submit_queues = nr_online_nodes;
+		}
+	} else if (submit_queues > nr_cpu_ids)
 		submit_queues = nr_cpu_ids;
 	else if (!submit_queues)
 		submit_queues = 1;

drivers/block/skd_main.c

@@ -5269,7 +5269,7 @@ const char *skd_skdev_state_to_str(enum skd_drvr_state state)
 	}
 }
 
-const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state)
+static const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state)
 {
 	switch (state) {
 	case SKD_MSG_STATE_IDLE:
@@ -5281,7 +5281,7 @@ const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state)
 	}
 }
 
-const char *skd_skreq_state_to_str(enum skd_req_state state)
+static const char *skd_skreq_state_to_str(enum skd_req_state state)
 {
 	switch (state) {
 	case SKD_REQ_STATE_IDLE:

drivers/md/bcache/alloc.c

@@ -421,9 +421,11 @@ long bch_bucket_alloc(struct cache *ca, unsigned watermark, bool wait)
 
 	if (watermark <= WATERMARK_METADATA) {
 		SET_GC_MARK(b, GC_MARK_METADATA);
+		SET_GC_MOVE(b, 0);
 		b->prio = BTREE_PRIO;
 	} else {
 		SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+		SET_GC_MOVE(b, 0);
 		b->prio = INITIAL_PRIO;
 	}
 

drivers/md/bcache/bcache.h

@@ -197,7 +197,7 @@ struct bucket {
 	uint8_t		disk_gen;
 	uint8_t		last_gc; /* Most out of date gen in the btree */
 	uint8_t		gc_gen;
-	uint16_t	gc_mark;
+	uint16_t	gc_mark; /* Bitfield used by GC. See below for field */
 };
 
 /*
@@ -209,7 +209,8 @@ BITMASK(GC_MARK,	 struct bucket, gc_mark, 0, 2);
 #define GC_MARK_RECLAIMABLE	0
 #define GC_MARK_DIRTY		1
 #define GC_MARK_METADATA	2
-BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14);
+BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 13);
+BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1);
 
 #include "journal.h"
 #include "stats.h"
@@ -372,14 +373,14 @@ struct cached_dev {
 	unsigned char		writeback_percent;
 	unsigned		writeback_delay;
 
-	int			writeback_rate_change;
-	int64_t			writeback_rate_derivative;
 	uint64_t		writeback_rate_target;
+	int64_t			writeback_rate_proportional;
+	int64_t			writeback_rate_derivative;
+	int64_t			writeback_rate_change;
 
 	unsigned		writeback_rate_update_seconds;
 	unsigned		writeback_rate_d_term;
 	unsigned		writeback_rate_p_term_inverse;
-	unsigned		writeback_rate_d_smooth;
 };
 
 enum alloc_watermarks {
@@ -445,7 +446,6 @@ struct cache {
 	 * call prio_write() to keep gens from wrapping.
 	 */
 	uint8_t			need_save_prio;
-	unsigned		gc_move_threshold;
 
 	/*
 	 * If nonzero, we know we aren't going to find any buckets to invalidate